Merge tag 'v6.14-rc4' into next

Sync up with the mainline.

34 files changed, 734 insertions, 300 deletions

diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 1e9db8e4acdf..0b1870a09e1f 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -61,6 +61,19 @@ config MD_BITMAP_FILE
 	  various kernel APIs and can only work with files on a file system not
 	  actually sitting on the MD device.
 
+config MD_LINEAR
+	tristate "Linear (append) mode"
+	depends on BLK_DEV_MD
+	help
+	  If you say Y here, then your multiple devices driver will be able to
+	  use the so-called linear mode, i.e. it will combine the hard disk
+	  partitions by simply appending one to the other.
+
+	  To compile this as a module, choose M here: the module
+	  will be called linear.
+
+	  If unsure, say Y.
+
 config MD_RAID0
 	tristate "RAID-0 (striping) mode"
 	depends on BLK_DEV_MD
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 476a214e4bdc..87bdfc9fe14c 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -29,12 +29,14 @@ dm-zoned-y	+= dm-zoned-target.o dm-zoned-metadata.o dm-zoned-reclaim.o
 
 md-mod-y	+= md.o md-bitmap.o
 raid456-y	+= raid5.o raid5-cache.o raid5-ppl.o
+linear-y       += md-linear.o
 
 # Note: link order is important.  All raid personalities
 # and must come before md.o, as they each initialise
 # themselves, and md.o may use the personalities when it
 # auto-initialised.
 
+obj-$(CONFIG_MD_LINEAR)		+= linear.o
 obj-$(CONFIG_MD_RAID0)		+= raid0.o
 obj-$(CONFIG_MD_RAID1)		+= raid1.o
 obj-$(CONFIG_MD_RAID10)		+= raid10.o
diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
index ef6abf33f926..45ca134cbf02 100644
--- a/drivers/md/bcache/movinggc.c
+++ b/drivers/md/bcache/movinggc.c
@@ -82,7 +82,7 @@ static void moving_init(struct moving_io *io)
 	bio_init(bio, NULL, bio->bi_inline_vecs,
 		 DIV_ROUND_UP(KEY_SIZE(&io->w->key), PAGE_SECTORS), 0);
 	bio_get(bio);
-	bio_set_prio(bio, IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0));
+	bio->bi_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0);
 
 	bio->bi_iter.bi_size	= KEY_SIZE(&io->w->key) << 9;
 	bio->bi_private		= &io->cl;
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index c1d28e365910..453efbbdc8ee 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -334,7 +334,7 @@ static void dirty_init(struct keybuf_key *w)
 	bio_init(bio, NULL, bio->bi_inline_vecs,
 		 DIV_ROUND_UP(KEY_SIZE(&w->key), PAGE_SECTORS), 0);
 	if (!io->dc->writeback_percent)
-		bio_set_prio(bio, IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0));
+		bio->bi_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0);
 
 	bio->bi_iter.bi_size	= KEY_SIZE(&w->key) << 9;
 	bio->bi_private		= w;
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 1ae2c71bb383..02a2919f4e5a 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -59,6 +59,7 @@ struct convert_context {
 	struct bio *bio_out;
 	struct bvec_iter iter_out;
 	atomic_t cc_pending;
+	unsigned int tag_offset;
 	u64 cc_sector;
 	union {
 		struct skcipher_request *req;
@@ -1187,7 +1188,7 @@ static int dm_crypt_integrity_io_alloc(struct dm_crypt_io *io, struct bio *bio)
 
 	tag_len = io->cc->tuple_size * (bio_sectors(bio) >> io->cc->sector_shift);
 
-	bip->bip_iter.bi_sector = io->cc->start + io->sector;
+	bip->bip_iter.bi_sector = bio->bi_iter.bi_sector;
 
 	ret = bio_integrity_add_page(bio, virt_to_page(io->integrity_metadata),
 				     tag_len, offset_in_page(io->integrity_metadata));
@@ -1256,6 +1257,7 @@ static void crypt_convert_init(struct crypt_config *cc,
 	if (bio_out)
 		ctx->iter_out = bio_out->bi_iter;
 	ctx->cc_sector = sector + cc->iv_offset;
+	ctx->tag_offset = 0;
 	init_completion(&ctx->restart);
 }
 
@@ -1588,7 +1590,6 @@ static void crypt_free_req(struct crypt_config *cc, void *req, struct bio *base_
 static blk_status_t crypt_convert(struct crypt_config *cc,
 			 struct convert_context *ctx, bool atomic, bool reset_pending)
 {
-	unsigned int tag_offset = 0;
 	unsigned int sector_step = cc->sector_size >> SECTOR_SHIFT;
 	int r;
 
@@ -1611,9 +1612,9 @@ static blk_status_t crypt_convert(struct crypt_config *cc,
 		atomic_inc(&ctx->cc_pending);
 
 		if (crypt_integrity_aead(cc))
-			r = crypt_convert_block_aead(cc, ctx, ctx->r.req_aead, tag_offset);
+			r = crypt_convert_block_aead(cc, ctx, ctx->r.req_aead, ctx->tag_offset);
 		else
-			r = crypt_convert_block_skcipher(cc, ctx, ctx->r.req, tag_offset);
+			r = crypt_convert_block_skcipher(cc, ctx, ctx->r.req, ctx->tag_offset);
 
 		switch (r) {
 		/*
@@ -1633,8 +1634,8 @@ static blk_status_t crypt_convert(struct crypt_config *cc,
 					 * exit and continue processing in a workqueue
 					 */
 					ctx->r.req = NULL;
+					ctx->tag_offset++;
 					ctx->cc_sector += sector_step;
-					tag_offset++;
 					return BLK_STS_DEV_RESOURCE;
 				}
 			} else {
@@ -1648,8 +1649,8 @@ static blk_status_t crypt_convert(struct crypt_config *cc,
 		 */
 		case -EINPROGRESS:
 			ctx->r.req = NULL;
+			ctx->tag_offset++;
 			ctx->cc_sector += sector_step;
-			tag_offset++;
 			continue;
 		/*
 		 * The request was already processed (synchronously).
@@ -1657,7 +1658,7 @@ static blk_status_t crypt_convert(struct crypt_config *cc,
 		case 0:
 			atomic_dec(&ctx->cc_pending);
 			ctx->cc_sector += sector_step;
-			tag_offset++;
+			ctx->tag_offset++;
 			if (!atomic)
 				cond_resched();
 			continue;
@@ -1719,6 +1720,7 @@ retry:
 	clone->bi_private = io;
 	clone->bi_end_io = crypt_endio;
 	clone->bi_ioprio = io->base_bio->bi_ioprio;
+	clone->bi_iter.bi_sector = cc->start + io->sector;
 
 	remaining_size = size;
 
@@ -1909,7 +1911,6 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
 			crypt_dec_pending(io);
 			return 1;
 		}
-		clone->bi_iter.bi_sector = cc->start + io->sector;
 		crypt_convert_init(cc, &io->ctx, clone, clone, io->sector);
 		io->saved_bi_iter = clone->bi_iter;
 		dm_submit_bio_remap(io->base_bio, clone);
@@ -1925,13 +1926,13 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
 	clone = bio_alloc_clone(cc->dev->bdev, io->base_bio, gfp, &cc->bs);
 	if (!clone)
 		return 1;
+
+	clone->bi_iter.bi_sector = cc->start + io->sector;
 	clone->bi_private = io;
 	clone->bi_end_io = crypt_endio;
 
 	crypt_inc_pending(io);
 
-	clone->bi_iter.bi_sector = cc->start + io->sector;
-
 	if (dm_crypt_integrity_io_alloc(io, clone)) {
 		crypt_dec_pending(io);
 		bio_put(clone);
@@ -2039,8 +2040,6 @@ static void kcryptd_crypt_write_io_submit(struct dm_crypt_io *io, int async)
 	/* crypt_convert should have filled the clone bio */
 	BUG_ON(io->ctx.iter_out.bi_size);
 
-	clone->bi_iter.bi_sector = cc->start + io->sector;
-
 	if ((likely(!async) && test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags)) ||
 	    test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags)) {
 		dm_submit_bio_remap(io->base_bio, clone);
@@ -2092,13 +2091,12 @@ static void kcryptd_crypt_write_continue(struct work_struct *work)
 	struct crypt_config *cc = io->cc;
 	struct convert_context *ctx = &io->ctx;
 	int crypt_finished;
-	sector_t sector = io->sector;
 	blk_status_t r;
 
 	wait_for_completion(&ctx->restart);
 	reinit_completion(&ctx->restart);
 
-	r = crypt_convert(cc, &io->ctx, true, false);
+	r = crypt_convert(cc, &io->ctx, false, false);
 	if (r)
 		io->error = r;
 	crypt_finished = atomic_dec_and_test(&ctx->cc_pending);
@@ -2109,10 +2107,8 @@ static void kcryptd_crypt_write_continue(struct work_struct *work)
 	}
 
 	/* Encryption was already finished, submit io now */
-	if (crypt_finished) {
+	if (crypt_finished)
 		kcryptd_crypt_write_io_submit(io, 0);
-		io->sector = sector;
-	}
 
 	crypt_dec_pending(io);
 }
@@ -2123,14 +2119,13 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 	struct convert_context *ctx = &io->ctx;
 	struct bio *clone;
 	int crypt_finished;
-	sector_t sector = io->sector;
 	blk_status_t r;
 
 	/*
 	 * Prevent io from disappearing until this function completes.
 	 */
 	crypt_inc_pending(io);
-	crypt_convert_init(cc, ctx, NULL, io->base_bio, sector);
+	crypt_convert_init(cc, ctx, NULL, io->base_bio, io->sector);
 
 	clone = crypt_alloc_buffer(io, io->base_bio->bi_iter.bi_size);
 	if (unlikely(!clone)) {
@@ -2147,8 +2142,6 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 		io->ctx.iter_in = clone->bi_iter;
 	}
 
-	sector += bio_sectors(clone);
-
 	crypt_inc_pending(io);
 	r = crypt_convert(cc, ctx,
 			  test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags), true);
@@ -2172,10 +2165,8 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 	}
 
 	/* Encryption was already finished, submit io now */
-	if (crypt_finished) {
+	if (crypt_finished)
 		kcryptd_crypt_write_io_submit(io, 0);
-		io->sector = sector;
-	}
 
 dec:
 	crypt_dec_pending(io);
@@ -2203,7 +2194,7 @@ static void kcryptd_crypt_read_continue(struct work_struct *work)
 	wait_for_completion(&io->ctx.restart);
 	reinit_completion(&io->ctx.restart);
 
-	r = crypt_convert(cc, &io->ctx, true, false);
+	r = crypt_convert(cc, &io->ctx, false, false);
 	if (r)
 		io->error = r;
 
@@ -2221,7 +2212,6 @@ static void kcryptd_crypt_read_convert(struct dm_crypt_io *io)
 	crypt_inc_pending(io);
 
 	if (io->ctx.aead_recheck) {
-		io->ctx.cc_sector = io->sector + cc->iv_offset;
 		r = crypt_convert(cc, &io->ctx,
 				  test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true);
 	} else {
diff --git a/drivers/md/dm-ebs-target.c b/drivers/md/dm-ebs-target.c
index ec5db1478b2f..18ae45dcbfb2 100644
--- a/drivers/md/dm-ebs-target.c
+++ b/drivers/md/dm-ebs-target.c
@@ -442,7 +442,7 @@ static int ebs_iterate_devices(struct dm_target *ti,
 static struct target_type ebs_target = {
 	.name		 = "ebs",
 	.version	 = {1, 0, 1},
-	.features	 = DM_TARGET_PASSES_INTEGRITY,
+	.features	 = 0,
 	.module		 = THIS_MODULE,
 	.ctr		 = ebs_ctr,
 	.dtr		 = ebs_dtr,
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index d7a8e2f40db3..c37668790577 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -379,6 +379,7 @@ static void do_region(const blk_opf_t opf, unsigned int region,
 
 		atomic_inc(&io->count);
 		submit_bio(bio);
+		WARN_ON_ONCE(opf & REQ_ATOMIC && remaining);
 	} while (remaining);
 }
 
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 49fb0f684193..66318aba4bdb 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -199,9 +199,10 @@ static size_t linear_dax_recovery_write(struct dm_target *ti, pgoff_t pgoff,
 
 static struct target_type linear_target = {
 	.name   = "linear",
-	.version = {1, 4, 0},
+	.version = {1, 5, 0},
 	.features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_NOWAIT |
-		    DM_TARGET_ZONED_HM | DM_TARGET_PASSES_CRYPTO,
+		    DM_TARGET_ZONED_HM | DM_TARGET_PASSES_CRYPTO |
+		    DM_TARGET_ATOMIC_WRITES,
 	.report_zones = linear_report_zones,
 	.module = THIS_MODULE,
 	.ctr    = linear_ctr,
diff --git a/drivers/md/dm-ps-io-affinity.c b/drivers/md/dm-ps-io-affinity.c
index 461ee6b2044d..716807e511ee 100644
--- a/drivers/md/dm-ps-io-affinity.c
+++ b/drivers/md/dm-ps-io-affinity.c
@@ -116,7 +116,7 @@ static int ioa_create(struct path_selector *ps, unsigned int argc, char **argv)
 	if (!s)
 		return -ENOMEM;
 
-	s->path_map = kzalloc(nr_cpu_ids * sizeof(struct path_info *),
+	s->path_map = kcalloc(nr_cpu_ids, sizeof(struct path_info *),
 			      GFP_KERNEL);
 	if (!s->path_map)
 		goto free_selector;
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 1e0d3b9b75d6..6adc55fd90d3 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3196,7 +3196,7 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		if (reshape_sectors || rs_is_raid1(rs)) {
 			/*
 			 * We can only prepare for a reshape here, because the
-			 * raid set needs to run to provide the repective reshape
+			 * raid set needs to run to provide the respective reshape
 			 * check functions via its MD personality instance.
 			 *
 			 * So do the reshape check after md_run() succeeded.
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 9511dae5b556..8c6f1f7e6456 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -656,7 +656,7 @@ static void do_write(struct mirror_set *ms, struct bio *bio)
 	unsigned int i;
 	struct dm_io_region io[MAX_NR_MIRRORS], *dest = io;
 	struct mirror *m;
-	blk_opf_t op_flags = bio->bi_opf & (REQ_FUA | REQ_PREFLUSH);
+	blk_opf_t op_flags = bio->bi_opf & (REQ_FUA | REQ_PREFLUSH | REQ_ATOMIC);
 	struct dm_io_request io_req = {
 		.bi_opf = REQ_OP_WRITE | op_flags,
 		.mem.type = DM_IO_BIO,
@@ -1483,8 +1483,9 @@ static int mirror_iterate_devices(struct dm_target *ti,
 
 static struct target_type mirror_target = {
 	.name	 = "mirror",
-	.version = {1, 14, 0},
+	.version = {1, 15, 0},
 	.module	 = THIS_MODULE,
+	.features = DM_TARGET_ATOMIC_WRITES,
 	.ctr	 = mirror_ctr,
 	.dtr	 = mirror_dtr,
 	.map	 = mirror_map,
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index 499f8cc8a39f..e23076f7ece2 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -547,7 +547,7 @@ int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t)
 	md->tag_set->ops = &dm_mq_ops;
 	md->tag_set->queue_depth = dm_get_blk_mq_queue_depth();
 	md->tag_set->numa_node = md->numa_node_id;
-	md->tag_set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_STACKING;
+	md->tag_set->flags = BLK_MQ_F_STACKING;
 	md->tag_set->nr_hw_queues = dm_get_blk_mq_nr_hw_queues();
 	md->tag_set->driver_data = md;
 
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 4112071de0be..3786ac67cefe 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -465,8 +465,9 @@ static void stripe_io_hints(struct dm_target *ti,
 
 static struct target_type stripe_target = {
 	.name   = "striped",
-	.version = {1, 6, 0},
-	.features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_NOWAIT,
+	.version = {1, 7, 0},
+	.features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_NOWAIT |
+		    DM_TARGET_ATOMIC_WRITES,
 	.module = THIS_MODULE,
 	.ctr    = stripe_ctr,
 	.dtr    = stripe_dtr,
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index bd8b796ae683..0ef5203387b2 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1806,6 +1806,32 @@ static bool dm_table_supports_secure_erase(struct dm_table *t)
 	return true;
 }
 
+static int device_not_atomic_write_capable(struct dm_target *ti,
+			struct dm_dev *dev, sector_t start,
+			sector_t len, void *data)
+{
+	return !bdev_can_atomic_write(dev->bdev);
+}
+
+static bool dm_table_supports_atomic_writes(struct dm_table *t)
+{
+	for (unsigned int i = 0; i < t->num_targets; i++) {
+		struct dm_target *ti = dm_table_get_target(t, i);
+
+		if (!dm_target_supports_atomic_writes(ti->type))
+			return false;
+
+		if (!ti->type->iterate_devices)
+			return false;
+
+		if (ti->type->iterate_devices(ti,
+			device_not_atomic_write_capable, NULL)) {
+			return false;
+		}
+	}
+	return true;
+}
+
 int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 			      struct queue_limits *limits)
 {
@@ -1854,6 +1880,9 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 			return r;
 	}
 
+	if (dm_table_supports_atomic_writes(t))
+		limits->features |= BLK_FEAT_ATOMIC_WRITES;
+
 	r = queue_limits_set(q, limits);
 	if (r)
 		return r;
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index bf0f9dddd146..05cf4e3f2bbe 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -2332,10 +2332,9 @@ static struct thin_c *get_first_thin(struct pool *pool)
 	struct thin_c *tc = NULL;
 
 	rcu_read_lock();
-	if (!list_empty(&pool->active_thins)) {
-		tc = list_entry_rcu(pool->active_thins.next, struct thin_c, list);
+	tc = list_first_or_null_rcu(&pool->active_thins, struct thin_c, list);
+	if (tc)
 		thin_get(tc);
-	}
 	rcu_read_unlock();
 
 	return tc;
diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c
index 62b1a44b8dd2..0c41949db784 100644
--- a/drivers/md/dm-verity-fec.c
+++ b/drivers/md/dm-verity-fec.c
@@ -40,35 +40,23 @@ static inline u64 fec_interleave(struct dm_verity *v, u64 offset)
 }
 
 /*
- * Decode an RS block using Reed-Solomon.
- */
-static int fec_decode_rs8(struct dm_verity *v, struct dm_verity_fec_io *fio,
-			  u8 *data, u8 *fec, int neras)
-{
-	int i;
-	uint16_t par[DM_VERITY_FEC_RSM - DM_VERITY_FEC_MIN_RSN];
-
-	for (i = 0; i < v->fec->roots; i++)
-		par[i] = fec[i];
-
-	return decode_rs8(fio->rs, data, par, v->fec->rsn, NULL, neras,
-			  fio->erasures, 0, NULL);
-}
-
-/*
  * Read error-correcting codes for the requested RS block. Returns a pointer
  * to the data block. Caller is responsible for releasing buf.
  */
 static u8 *fec_read_parity(struct dm_verity *v, u64 rsb, int index,
-			   unsigned int *offset, struct dm_buffer **buf,
-			   unsigned short ioprio)
+			   unsigned int *offset, unsigned int par_buf_offset,
+			   struct dm_buffer **buf, unsigned short ioprio)
 {
 	u64 position, block, rem;
 	u8 *res;
 
+	/* We have already part of parity bytes read, skip to the next block */
+	if (par_buf_offset)
+		index++;
+
 	position = (index + rsb) * v->fec->roots;
 	block = div64_u64_rem(position, v->fec->io_size, &rem);
-	*offset = (unsigned int)rem;
+	*offset = par_buf_offset ? 0 : (unsigned int)rem;
 
 	res = dm_bufio_read_with_ioprio(v->fec->bufio, block, buf, ioprio);
 	if (IS_ERR(res)) {
@@ -128,11 +116,13 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_io *io,
 {
 	int r, corrected = 0, res;
 	struct dm_buffer *buf;
-	unsigned int n, i, offset;
+	unsigned int n, i, j, offset, par_buf_offset = 0;
+	uint16_t par_buf[DM_VERITY_FEC_RSM - DM_VERITY_FEC_MIN_RSN];
 	u8 *par, *block;
 	struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_io_data_size);
 
-	par = fec_read_parity(v, rsb, block_offset, &offset, &buf, bio_prio(bio));
+	par = fec_read_parity(v, rsb, block_offset, &offset,
+			      par_buf_offset, &buf, bio->bi_ioprio);
 	if (IS_ERR(par))
 		return PTR_ERR(par);
 
@@ -142,7 +132,11 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_io *io,
 	 */
 	fec_for_each_buffer_rs_block(fio, n, i) {
 		block = fec_buffer_rs_block(v, fio, n, i);
-		res = fec_decode_rs8(v, fio, block, &par[offset], neras);
+		for (j = 0; j < v->fec->roots - par_buf_offset; j++)
+			par_buf[par_buf_offset + j] = par[offset + j];
+		/* Decode an RS block using Reed-Solomon */
+		res = decode_rs8(fio->rs, block, par_buf, v->fec->rsn,
+				 NULL, neras, fio->erasures, 0, NULL);
 		if (res < 0) {
 			r = res;
 			goto error;
@@ -155,12 +149,22 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_io *io,
 		if (block_offset >= 1 << v->data_dev_block_bits)
 			goto done;
 
-		/* read the next block when we run out of parity bytes */
-		offset += v->fec->roots;
+		/* Read the next block when we run out of parity bytes */
+		offset += (v->fec->roots - par_buf_offset);
+		/* Check if parity bytes are split between blocks */
+		if (offset < v->fec->io_size && (offset + v->fec->roots) > v->fec->io_size) {
+			par_buf_offset = v->fec->io_size - offset;
+			for (j = 0; j < par_buf_offset; j++)
+				par_buf[j] = par[offset + j];
+			offset += par_buf_offset;
+		} else
+			par_buf_offset = 0;
+
 		if (offset >= v->fec->io_size) {
 			dm_bufio_release(buf);
 
-			par = fec_read_parity(v, rsb, block_offset, &offset, &buf, bio_prio(bio));
+			par = fec_read_parity(v, rsb, block_offset, &offset,
+					      par_buf_offset, &buf, bio->bi_ioprio);
 			if (IS_ERR(par))
 				return PTR_ERR(par);
 		}
@@ -250,7 +254,7 @@ static int fec_read_bufs(struct dm_verity *v, struct dm_verity_io *io,
 			bufio = v->bufio;
 		}
 
-		bbuf = dm_bufio_read_with_ioprio(bufio, block, &buf, bio_prio(bio));
+		bbuf = dm_bufio_read_with_ioprio(bufio, block, &buf, bio->bi_ioprio);
 		if (IS_ERR(bbuf)) {
 			DMWARN_LIMIT("%s: FEC %llu: read failed (%llu): %ld",
 				     v->data_dev->name,
@@ -724,10 +728,7 @@ int verity_fec_ctr(struct dm_verity *v)
 		return -E2BIG;
 	}
 
-	if ((f->roots << SECTOR_SHIFT) & ((1 << v->data_dev_block_bits) - 1))
-		f->io_size = 1 << v->data_dev_block_bits;
-	else
-		f->io_size = v->fec->roots << SECTOR_SHIFT;
+	f->io_size = 1 << v->data_dev_block_bits;
 
 	f->bufio = dm_bufio_client_create(f->dev->bdev,
 					  f->io_size,
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index 47d595f6a76e..e86c1431b108 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -321,7 +321,7 @@ static int verity_verify_level(struct dm_verity *v, struct dm_verity_io *io,
 		}
 	} else {
 		data = dm_bufio_read_with_ioprio(v->bufio, hash_block,
-						&buf, bio_prio(bio));
+						&buf, bio->bi_ioprio);
 	}
 
 	if (IS_ERR(data))
@@ -789,7 +789,7 @@ static int verity_map(struct dm_target *ti, struct bio *bio)
 
 	verity_fec_init_io(io);
 
-	verity_submit_prefetch(v, io, bio_prio(bio));
+	verity_submit_prefetch(v, io, bio->bi_ioprio);
 
 	submit_bio_noacct(bio);
 
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 12ecf07a3841..4d1e42891d24 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1479,12 +1479,12 @@ static void setup_split_accounting(struct clone_info *ci, unsigned int len)
 
 static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci,
 				struct dm_target *ti, unsigned int num_bios,
-				unsigned *len, gfp_t gfp_flag)
+				unsigned *len)
 {
 	struct bio *bio;
-	int try = (gfp_flag & GFP_NOWAIT) ? 0 : 1;
+	int try;
 
-	for (; try < 2; try++) {
+	for (try = 0; try < 2; try++) {
 		int bio_nr;
 
 		if (try && num_bios > 1)
@@ -1508,8 +1508,7 @@ static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci,
 }
 
 static unsigned int __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti,
-					  unsigned int num_bios, unsigned int *len,
-					  gfp_t gfp_flag)
+					  unsigned int num_bios, unsigned int *len)
 {
 	struct bio_list blist = BIO_EMPTY_LIST;
 	struct bio *clone;
@@ -1526,7 +1525,7 @@ static unsigned int __send_duplicate_bios(struct clone_info *ci, struct dm_targe
 	 * Using alloc_multiple_bios(), even if num_bios is 1, to consistently
 	 * support allocating using GFP_NOWAIT with GFP_NOIO fallback.
 	 */
-	alloc_multiple_bios(&blist, ci, ti, num_bios, len, gfp_flag);
+	alloc_multiple_bios(&blist, ci, ti, num_bios, len);
 	while ((clone = bio_list_pop(&blist))) {
 		if (num_bios > 1)
 			dm_tio_set_flag(clone_to_tio(clone), DM_TIO_IS_DUPLICATE_BIO);
@@ -1564,7 +1563,7 @@ static void __send_empty_flush(struct clone_info *ci)
 
 			atomic_add(ti->num_flush_bios, &ci->io->io_count);
 			bios = __send_duplicate_bios(ci, ti, ti->num_flush_bios,
-						     NULL, GFP_NOWAIT);
+						     NULL);
 			atomic_sub(ti->num_flush_bios - bios, &ci->io->io_count);
 		}
 	} else {
@@ -1612,7 +1611,7 @@ static void __send_abnormal_io(struct clone_info *ci, struct dm_target *ti,
 		    __max_io_len(ti, ci->sector, max_granularity, max_sectors));
 
 	atomic_add(num_bios, &ci->io->io_count);
-	bios = __send_duplicate_bios(ci, ti, num_bios, &len, GFP_NOIO);
+	bios = __send_duplicate_bios(ci, ti, num_bios, &len);
 	/*
 	 * alloc_io() takes one extra reference for submission, so the
 	 * reference won't reach 0 without the following (+1) subtraction
@@ -1746,6 +1745,9 @@ static blk_status_t __split_and_process_bio(struct clone_info *ci)
 	ci->submit_as_polled = !!(ci->bio->bi_opf & REQ_POLLED);
 
 	len = min_t(sector_t, max_io_len(ti, ci->sector), ci->sector_count);
+	if (ci->bio->bi_opf & REQ_ATOMIC && len != ci->sector_count)
+		return BLK_STS_IOERR;
+
 	setup_split_accounting(ci, len);
 
 	if (unlikely(ci->bio->bi_opf & REQ_NOWAIT)) {
@@ -1849,7 +1851,7 @@ static blk_status_t __send_zone_reset_all_emulated(struct clone_info *ci,
 			 * not go crazy with the clone allocation.
 			 */
 			alloc_multiple_bios(&blist, ci, ti, min(nr_reset, 32),
-					    NULL, GFP_NOIO);
+					    NULL);
 		}
 
 		/* Get a clone and change it to a regular reset operation. */
@@ -1881,7 +1883,7 @@ static void __send_zone_reset_all_native(struct clone_info *ci,
 	unsigned int bios;
 
 	atomic_add(1, &ci->io->io_count);
-	bios = __send_duplicate_bios(ci, ti, 1, NULL, GFP_NOIO);
+	bios = __send_duplicate_bios(ci, ti, 1, NULL);
 	atomic_sub(1 - bios, &ci->io->io_count);
 
 	ci->sector_count = 0;
@@ -1969,6 +1971,15 @@ static void dm_split_and_process_bio(struct mapped_device *md,
 
 	/* Only support nowait for normal IO */
 	if (unlikely(bio->bi_opf & REQ_NOWAIT) && !is_abnormal) {
+		/*
+		 * Don't support NOWAIT for FLUSH because it may allocate
+		 * multiple bios and there's no easy way how to undo the
+		 * allocations.
+		 */
+		if (bio->bi_opf & REQ_PREFLUSH) {
+			bio_wouldblock_error(bio);
+			return;
+		}
 		io = alloc_io(md, bio, GFP_NOWAIT);
 		if (unlikely(!io)) {
 			/* Unable to do anything without dm_io. */
diff --git a/drivers/md/md-autodetect.c b/drivers/md/md-autodetect.c
index b2a00f213c2c..4b80165afd23 100644
--- a/drivers/md/md-autodetect.c
+++ b/drivers/md/md-autodetect.c
@@ -49,6 +49,7 @@ static int md_setup_ents __initdata;
  *             instead of just one.  -- KTK
  * 18May2000: Added support for persistent-superblock arrays:
  *             md=n,0,factor,fault,device-list   uses RAID0 for device n
+ *             md=n,-1,factor,fault,device-list  uses LINEAR for device n
  *             md=n,device-list      reads a RAID superblock from the devices
  *             elements in device-list are read by name_to_kdev_t so can be
  *             a hex number or something like /dev/hda1 /dev/sdb
@@ -87,7 +88,7 @@ static int __init md_setup(char *str)
 		md_setup_ents++;
 	switch (get_option(&str, &level)) {	/* RAID level */
 	case 2: /* could be 0 or -1.. */
-		if (level == 0) {
+		if (level == 0 || level == LEVEL_LINEAR) {
 			if (get_option(&str, &factor) != 2 ||	/* Chunk Size */
 					get_option(&str, &fault) != 2) {
 				printk(KERN_WARNING "md: Too few arguments supplied to md=.\n");
@@ -95,7 +96,10 @@ static int __init md_setup(char *str)
 			}
 			md_setup_args[ent].level = level;
 			md_setup_args[ent].chunk = 1 << (factor+12);
-			pername = "raid0";
+			if (level ==  LEVEL_LINEAR)
+				pername = "linear";
+			else
+				pername = "raid0";
 			break;
 		}
 		fallthrough;
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index c3a42dd66ce5..23c09d22fcdb 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -682,7 +682,7 @@ static void bitmap_update_sb(void *data)
 		return;
 	if (!bitmap->storage.sb_page) /* no superblock */
 		return;
-	sb = kmap_atomic(bitmap->storage.sb_page);
+	sb = kmap_local_page(bitmap->storage.sb_page);
 	sb->events = cpu_to_le64(bitmap->mddev->events);
 	if (bitmap->mddev->events < bitmap->events_cleared)
 		/* rocking back to read-only */
@@ -702,7 +702,7 @@ static void bitmap_update_sb(void *data)
 	sb->nodes = cpu_to_le32(bitmap->mddev->bitmap_info.nodes);
 	sb->sectors_reserved = cpu_to_le32(bitmap->mddev->
 					   bitmap_info.space);
-	kunmap_atomic(sb);
+	kunmap_local(sb);
 
 	if (bitmap->storage.file)
 		write_file_page(bitmap, bitmap->storage.sb_page, 1);
@@ -717,7 +717,7 @@ static void bitmap_print_sb(struct bitmap *bitmap)
 
 	if (!bitmap || !bitmap->storage.sb_page)
 		return;
-	sb = kmap_atomic(bitmap->storage.sb_page);
+	sb = kmap_local_page(bitmap->storage.sb_page);
 	pr_debug("%s: bitmap file superblock:\n", bmname(bitmap));
 	pr_debug("         magic: %08x\n", le32_to_cpu(sb->magic));
 	pr_debug("       version: %u\n", le32_to_cpu(sb->version));
@@ -736,7 +736,7 @@ static void bitmap_print_sb(struct bitmap *bitmap)
 	pr_debug("     sync size: %llu KB\n",
 		 (unsigned long long)le64_to_cpu(sb->sync_size)/2);
 	pr_debug("max write behind: %u\n", le32_to_cpu(sb->write_behind));
-	kunmap_atomic(sb);
+	kunmap_local(sb);
 }
 
 /*
@@ -760,7 +760,7 @@ static int md_bitmap_new_disk_sb(struct bitmap *bitmap)
 		return -ENOMEM;
 	bitmap->storage.sb_index = 0;
 
-	sb = kmap_atomic(bitmap->storage.sb_page);
+	sb = kmap_local_page(bitmap->storage.sb_page);
 
 	sb->magic = cpu_to_le32(BITMAP_MAGIC);
 	sb->version = cpu_to_le32(BITMAP_MAJOR_HI);
@@ -768,7 +768,7 @@ static int md_bitmap_new_disk_sb(struct bitmap *bitmap)
 	chunksize = bitmap->mddev->bitmap_info.chunksize;
 	BUG_ON(!chunksize);
 	if (!is_power_of_2(chunksize)) {
-		kunmap_atomic(sb);
+		kunmap_local(sb);
 		pr_warn("bitmap chunksize not a power of 2\n");
 		return -EINVAL;
 	}
@@ -803,7 +803,7 @@ static int md_bitmap_new_disk_sb(struct bitmap *bitmap)
 	sb->events_cleared = cpu_to_le64(bitmap->mddev->events);
 	bitmap->mddev->bitmap_info.nodes = 0;
 
-	kunmap_atomic(sb);
+	kunmap_local(sb);
 
 	return 0;
 }
@@ -865,7 +865,7 @@ re_read:
 		return err;
 
 	err = -EINVAL;
-	sb = kmap_atomic(sb_page);
+	sb = kmap_local_page(sb_page);
 
 	chunksize = le32_to_cpu(sb->chunksize);
 	daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ;
@@ -932,7 +932,7 @@ re_read:
 	err = 0;
 
 out:
-	kunmap_atomic(sb);
+	kunmap_local(sb);
 	if (err == 0 && nodes && (bitmap->cluster_slot < 0)) {
 		/* Assigning chunksize is required for "re_read" */
 		bitmap->mddev->bitmap_info.chunksize = chunksize;
@@ -1161,12 +1161,12 @@ static void md_bitmap_file_set_bit(struct bitmap *bitmap, sector_t block)
 	bit = file_page_offset(&bitmap->storage, chunk);
 
 	/* set the bit */
-	kaddr = kmap_atomic(page);
+	kaddr = kmap_local_page(page);
 	if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags))
 		set_bit(bit, kaddr);
 	else
 		set_bit_le(bit, kaddr);
-	kunmap_atomic(kaddr);
+	kunmap_local(kaddr);
 	pr_debug("set file bit %lu page %lu\n", bit, index);
 	/* record page number so it gets flushed to disk when unplug occurs */
 	set_page_attr(bitmap, index - node_offset, BITMAP_PAGE_DIRTY);
@@ -1190,12 +1190,12 @@ static void md_bitmap_file_clear_bit(struct bitmap *bitmap, sector_t block)
 	if (!page)
 		return;
 	bit = file_page_offset(&bitmap->storage, chunk);
-	paddr = kmap_atomic(page);
+	paddr = kmap_local_page(page);
 	if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags))
 		clear_bit(bit, paddr);
 	else
 		clear_bit_le(bit, paddr);
-	kunmap_atomic(paddr);
+	kunmap_local(paddr);
 	if (!test_page_attr(bitmap, index - node_offset, BITMAP_PAGE_NEEDWRITE)) {
 		set_page_attr(bitmap, index - node_offset, BITMAP_PAGE_PENDING);
 		bitmap->allclean = 0;
@@ -1214,12 +1214,12 @@ static int md_bitmap_file_test_bit(struct bitmap *bitmap, sector_t block)
 	if (!page)
 		return -EINVAL;
 	bit = file_page_offset(&bitmap->storage, chunk);
-	paddr = kmap_atomic(page);
+	paddr = kmap_local_page(page);
 	if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags))
 		set = test_bit(bit, paddr);
 	else
 		set = test_bit_le(bit, paddr);
-	kunmap_atomic(paddr);
+	kunmap_local(paddr);
 	return set;
 }
 
@@ -1388,9 +1388,9 @@ static int md_bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 			 * If the bitmap is out of date, dirty the whole page
 			 * and write it out
 			 */
-			paddr = kmap_atomic(page);
+			paddr = kmap_local_page(page);
 			memset(paddr + offset, 0xff, PAGE_SIZE - offset);
-			kunmap_atomic(paddr);
+			kunmap_local(paddr);
 
 			filemap_write_page(bitmap, i, true);
 			if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags)) {
@@ -1406,12 +1406,12 @@ static int md_bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 		void *paddr;
 		bool was_set;
 
-		paddr = kmap_atomic(page);
+		paddr = kmap_local_page(page);
 		if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags))
 			was_set = test_bit(bit, paddr);
 		else
 			was_set = test_bit_le(bit, paddr);
-		kunmap_atomic(paddr);
+		kunmap_local(paddr);
 
 		if (was_set) {
 			/* if the disk bit is set, set the memory bit */
@@ -1546,10 +1546,10 @@ static void bitmap_daemon_work(struct mddev *mddev)
 		bitmap_super_t *sb;
 		bitmap->need_sync = 0;
 		if (bitmap->storage.filemap) {
-			sb = kmap_atomic(bitmap->storage.sb_page);
+			sb = kmap_local_page(bitmap->storage.sb_page);
 			sb->events_cleared =
 				cpu_to_le64(bitmap->events_cleared);
-			kunmap_atomic(sb);
+			kunmap_local(sb);
 			set_page_attr(bitmap, 0,
 				      BITMAP_PAGE_NEEDWRITE);
 		}
@@ -1671,24 +1671,13 @@ __acquires(bitmap->lock)
 }
 
 static int bitmap_startwrite(struct mddev *mddev, sector_t offset,
-			     unsigned long sectors, bool behind)
+			     unsigned long sectors)
 {
 	struct bitmap *bitmap = mddev->bitmap;
 
 	if (!bitmap)
 		return 0;
 
-	if (behind) {
-		int bw;
-		atomic_inc(&bitmap->behind_writes);
-		bw = atomic_read(&bitmap->behind_writes);
-		if (bw > bitmap->behind_writes_used)
-			bitmap->behind_writes_used = bw;
-
-		pr_debug("inc write-behind count %d/%lu\n",
-			 bw, bitmap->mddev->bitmap_info.max_write_behind);
-	}
-
 	while (sectors) {
 		sector_t blocks;
 		bitmap_counter_t *bmc;
@@ -1737,21 +1726,13 @@ static int bitmap_startwrite(struct mddev *mddev, sector_t offset,
 }
 
 static void bitmap_endwrite(struct mddev *mddev, sector_t offset,
-			    unsigned long sectors, bool success, bool behind)
+			    unsigned long sectors)
 {
 	struct bitmap *bitmap = mddev->bitmap;
 
 	if (!bitmap)
 		return;
 
-	if (behind) {
-		if (atomic_dec_and_test(&bitmap->behind_writes))
-			wake_up(&bitmap->behind_wait);
-		pr_debug("dec write-behind count %d/%lu\n",
-			 atomic_read(&bitmap->behind_writes),
-			 bitmap->mddev->bitmap_info.max_write_behind);
-	}
-
 	while (sectors) {
 		sector_t blocks;
 		unsigned long flags;
@@ -1764,15 +1745,16 @@ static void bitmap_endwrite(struct mddev *mddev, sector_t offset,
 			return;
 		}
 
-		if (success && !bitmap->mddev->degraded &&
-		    bitmap->events_cleared < bitmap->mddev->events) {
-			bitmap->events_cleared = bitmap->mddev->events;
-			bitmap->need_sync = 1;
-			sysfs_notify_dirent_safe(bitmap->sysfs_can_clear);
-		}
-
-		if (!success && !NEEDED(*bmc))
+		if (!bitmap->mddev->degraded) {
+			if (bitmap->events_cleared < bitmap->mddev->events) {
+				bitmap->events_cleared = bitmap->mddev->events;
+				bitmap->need_sync = 1;
+				sysfs_notify_dirent_safe(
+						bitmap->sysfs_can_clear);
+			}
+		} else if (!NEEDED(*bmc)) {
 			*bmc |= NEEDED_MASK;
+		}
 
 		if (COUNTER(*bmc) == COUNTER_MAX)
 			wake_up(&bitmap->overflow_wait);
@@ -2062,6 +2044,37 @@ static void md_bitmap_free(void *data)
 	kfree(bitmap);
 }
 
+static void bitmap_start_behind_write(struct mddev *mddev)
+{
+	struct bitmap *bitmap = mddev->bitmap;
+	int bw;
+
+	if (!bitmap)
+		return;
+
+	atomic_inc(&bitmap->behind_writes);
+	bw = atomic_read(&bitmap->behind_writes);
+	if (bw > bitmap->behind_writes_used)
+		bitmap->behind_writes_used = bw;
+
+	pr_debug("inc write-behind count %d/%lu\n",
+		 bw, bitmap->mddev->bitmap_info.max_write_behind);
+}
+
+static void bitmap_end_behind_write(struct mddev *mddev)
+{
+	struct bitmap *bitmap = mddev->bitmap;
+
+	if (!bitmap)
+		return;
+
+	if (atomic_dec_and_test(&bitmap->behind_writes))
+		wake_up(&bitmap->behind_wait);
+	pr_debug("dec write-behind count %d/%lu\n",
+		 atomic_read(&bitmap->behind_writes),
+		 bitmap->mddev->bitmap_info.max_write_behind);
+}
+
 static void bitmap_wait_behind_writes(struct mddev *mddev)
 {
 	struct bitmap *bitmap = mddev->bitmap;
@@ -2342,7 +2355,10 @@ static int bitmap_get_stats(void *data, struct md_bitmap_stats *stats)
 
 	if (!bitmap)
 		return -ENOENT;
-
+	if (bitmap->mddev->bitmap_info.external)
+		return -ENOENT;
+	if (!bitmap->storage.sb_page) /* no superblock */
+		return -EINVAL;
 	sb = kmap_local_page(bitmap->storage.sb_page);
 	stats->sync_size = le64_to_cpu(sb->sync_size);
 	kunmap_local(sb);
@@ -2981,6 +2997,9 @@ static struct bitmap_operations bitmap_ops = {
 	.dirty_bits		= bitmap_dirty_bits,
 	.unplug			= bitmap_unplug,
 	.daemon_work		= bitmap_daemon_work,
+
+	.start_behind_write	= bitmap_start_behind_write,
+	.end_behind_write	= bitmap_end_behind_write,
 	.wait_behind_writes	= bitmap_wait_behind_writes,
 
 	.startwrite		= bitmap_startwrite,
diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h
index 662e6fc141a7..31c93019c76b 100644
--- a/drivers/md/md-bitmap.h
+++ b/drivers/md/md-bitmap.h
@@ -84,12 +84,15 @@ struct bitmap_operations {
 			   unsigned long e);
 	void (*unplug)(struct mddev *mddev, bool sync);
 	void (*daemon_work)(struct mddev *mddev);
+
+	void (*start_behind_write)(struct mddev *mddev);
+	void (*end_behind_write)(struct mddev *mddev);
 	void (*wait_behind_writes)(struct mddev *mddev);
 
 	int (*startwrite)(struct mddev *mddev, sector_t offset,
-			  unsigned long sectors, bool behind);
+			  unsigned long sectors);
 	void (*endwrite)(struct mddev *mddev, sector_t offset,
-			 unsigned long sectors, bool success, bool behind);
+			 unsigned long sectors);
 	bool (*start_sync)(struct mddev *mddev, sector_t offset,
 			   sector_t *blocks, bool degraded);
 	void (*end_sync)(struct mddev *mddev, sector_t offset, sector_t *blocks);
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
new file mode 100644
index 000000000000..369aed044b40
--- /dev/null
+++ b/drivers/md/md-linear.c
@@ -0,0 +1,352 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * linear.c : Multiple Devices driver for Linux Copyright (C) 1994-96 Marc
+ * ZYNGIER <zyngier@ufr-info-p7.ibp.fr> or <maz@gloups.fdn.fr>
+ */
+
+#include <linux/blkdev.h>
+#include <linux/raid/md_u.h>
+#include <linux/seq_file.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <trace/events/block.h>
+#include "md.h"
+
+struct dev_info {
+	struct md_rdev	*rdev;
+	sector_t	end_sector;
+};
+
+struct linear_conf {
+	struct rcu_head         rcu;
+	sector_t                array_sectors;
+	/* a copy of mddev->raid_disks */
+	int                     raid_disks;
+	struct dev_info         disks[] __counted_by(raid_disks);
+};
+
+/*
+ * find which device holds a particular offset
+ */
+static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector)
+{
+	int lo, mid, hi;
+	struct linear_conf *conf;
+
+	lo = 0;
+	hi = mddev->raid_disks - 1;
+	conf = mddev->private;
+
+	/*
+	 * Binary Search
+	 */
+
+	while (hi > lo) {
+
+		mid = (hi + lo) / 2;
+		if (sector < conf->disks[mid].end_sector)
+			hi = mid;
+		else
+			lo = mid + 1;
+	}
+
+	return conf->disks + lo;
+}
+
+static sector_t linear_size(struct mddev *mddev, sector_t sectors, int raid_disks)
+{
+	struct linear_conf *conf;
+	sector_t array_sectors;
+
+	conf = mddev->private;
+	WARN_ONCE(sectors || raid_disks,
+		  "%s does not support generic reshape\n", __func__);
+	array_sectors = conf->array_sectors;
+
+	return array_sectors;
+}
+
+static int linear_set_limits(struct mddev *mddev)
+{
+	struct queue_limits lim;
+	int err;
+
+	md_init_stacking_limits(&lim);
+	lim.max_hw_sectors = mddev->chunk_sectors;
+	lim.max_write_zeroes_sectors = mddev->chunk_sectors;
+	lim.io_min = mddev->chunk_sectors << 9;
+	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
+	if (err)
+		return err;
+
+	return queue_limits_set(mddev->gendisk->queue, &lim);
+}
+
+static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
+{
+	struct linear_conf *conf;
+	struct md_rdev *rdev;
+	int ret = -EINVAL;
+	int cnt;
+	int i;
+
+	conf = kzalloc(struct_size(conf, disks, raid_disks), GFP_KERNEL);
+	if (!conf)
+		return ERR_PTR(-ENOMEM);
+
+	/*
+	 * 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;
+
+	cnt = 0;
+	conf->array_sectors = 0;
+
+	rdev_for_each(rdev, mddev) {
+		int j = rdev->raid_disk;
+		struct dev_info *disk = conf->disks + j;
+		sector_t sectors;
+
+		if (j < 0 || j >= raid_disks || disk->rdev) {
+			pr_warn("md/linear:%s: disk numbering problem. Aborting!\n",
+				mdname(mddev));
+			goto out;
+		}
+
+		disk->rdev = rdev;
+		if (mddev->chunk_sectors) {
+			sectors = rdev->sectors;
+			sector_div(sectors, mddev->chunk_sectors);
+			rdev->sectors = sectors * mddev->chunk_sectors;
+		}
+
+		conf->array_sectors += rdev->sectors;
+		cnt++;
+	}
+	if (cnt != raid_disks) {
+		pr_warn("md/linear:%s: not enough drives present. Aborting!\n",
+			mdname(mddev));
+		goto out;
+	}
+
+	/*
+	 * Here we calculate the device offsets.
+	 */
+	conf->disks[0].end_sector = conf->disks[0].rdev->sectors;
+
+	for (i = 1; i < raid_disks; i++)
+		conf->disks[i].end_sector =
+			conf->disks[i-1].end_sector +
+			conf->disks[i].rdev->sectors;
+
+	if (!mddev_is_dm(mddev)) {
+		ret = linear_set_limits(mddev);
+		if (ret)
+			goto out;
+	}
+
+	return conf;
+
+out:
+	kfree(conf);
+	return ERR_PTR(ret);
+}
+
+static int linear_run(struct mddev *mddev)
+{
+	struct linear_conf *conf;
+	int ret;
+
+	if (md_check_no_bitmap(mddev))
+		return -EINVAL;
+
+	conf = linear_conf(mddev, mddev->raid_disks);
+	if (IS_ERR(conf))
+		return PTR_ERR(conf);
+
+	mddev->private = conf;
+	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
+
+	ret =  md_integrity_register(mddev);
+	if (ret) {
+		kfree(conf);
+		mddev->private = NULL;
+	}
+	return ret;
+}
+
+static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
+{
+	/* Adding a drive to a linear array allows the array to grow.
+	 * It is permitted if the new drive has a matching superblock
+	 * already on it, with raid_disk equal to raid_disks.
+	 * It is achieved by creating a new linear_private_data structure
+	 * and swapping it in in-place of the current one.
+	 * The current one is never freed until the array is stopped.
+	 * This avoids races.
+	 */
+	struct linear_conf *newconf, *oldconf;
+
+	if (rdev->saved_raid_disk != mddev->raid_disks)
+		return -EINVAL;
+
+	rdev->raid_disk = rdev->saved_raid_disk;
+	rdev->saved_raid_disk = -1;
+
+	newconf = linear_conf(mddev, mddev->raid_disks + 1);
+	if (IS_ERR(newconf))
+		return PTR_ERR(newconf);
+
+	/* 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.
+	 */
+	oldconf = rcu_dereference_protected(mddev->private,
+			lockdep_is_held(&mddev->reconfig_mutex));
+	mddev->raid_disks++;
+	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_and_notify(mddev->gendisk, mddev->array_sectors);
+	kfree_rcu(oldconf, rcu);
+	return 0;
+}
+
+static void linear_free(struct mddev *mddev, void *priv)
+{
+	struct linear_conf *conf = priv;
+
+	kfree(conf);
+}
+
+static bool linear_make_request(struct mddev *mddev, struct bio *bio)
+{
+	struct dev_info *tmp_dev;
+	sector_t start_sector, end_sector, data_offset;
+	sector_t bio_sector = bio->bi_iter.bi_sector;
+
+	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
+	    && md_flush_request(mddev, bio))
+		return true;
+
+	tmp_dev = which_dev(mddev, bio_sector);
+	start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors;
+	end_sector = tmp_dev->end_sector;
+	data_offset = tmp_dev->rdev->data_offset;
+
+	if (unlikely(bio_sector >= end_sector ||
+		     bio_sector < start_sector))
+		goto out_of_bounds;
+
+	if (unlikely(is_rdev_broken(tmp_dev->rdev))) {
+		md_error(mddev, tmp_dev->rdev);
+		bio_io_error(bio);
+		return true;
+	}
+
+	if (unlikely(bio_end_sector(bio) > end_sector)) {
+		/* This bio crosses a device boundary, so we have to split it */
+		struct bio *split = bio_split(bio, end_sector - bio_sector,
+					      GFP_NOIO, &mddev->bio_set);
+
+		if (IS_ERR(split)) {
+			bio->bi_status = errno_to_blk_status(PTR_ERR(split));
+			bio_endio(bio);
+			return true;
+		}
+
+		bio_chain(split, bio);
+		submit_bio_noacct(bio);
+		bio = split;
+	}
+
+	md_account_bio(mddev, &bio);
+	bio_set_dev(bio, tmp_dev->rdev->bdev);
+	bio->bi_iter.bi_sector = bio->bi_iter.bi_sector -
+		start_sector + data_offset;
+
+	if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
+		     !bdev_max_discard_sectors(bio->bi_bdev))) {
+		/* Just ignore it */
+		bio_endio(bio);
+	} else {
+		if (mddev->gendisk)
+			trace_block_bio_remap(bio, disk_devt(mddev->gendisk),
+					      bio_sector);
+		mddev_check_write_zeroes(mddev, bio);
+		submit_bio_noacct(bio);
+	}
+	return true;
+
+out_of_bounds:
+	pr_err("md/linear:%s: make_request: Sector %llu out of bounds on dev %pg: %llu sectors, offset %llu\n",
+	       mdname(mddev),
+	       (unsigned long long)bio->bi_iter.bi_sector,
+	       tmp_dev->rdev->bdev,
+	       (unsigned long long)tmp_dev->rdev->sectors,
+	       (unsigned long long)start_sector);
+	bio_io_error(bio);
+	return true;
+}
+
+static void linear_status(struct seq_file *seq, struct mddev *mddev)
+{
+	seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2);
+}
+
+static void linear_error(struct mddev *mddev, struct md_rdev *rdev)
+{
+	if (!test_and_set_bit(MD_BROKEN, &mddev->flags)) {
+		char *md_name = mdname(mddev);
+
+		pr_crit("md/linear%s: Disk failure on %pg detected, failing array.\n",
+			md_name, rdev->bdev);
+	}
+}
+
+static void linear_quiesce(struct mddev *mddev, int state)
+{
+}
+
+static struct md_personality linear_personality = {
+	.name		= "linear",
+	.level		= LEVEL_LINEAR,
+	.owner		= THIS_MODULE,
+	.make_request	= linear_make_request,
+	.run		= linear_run,
+	.free		= linear_free,
+	.status		= linear_status,
+	.hot_add_disk	= linear_add,
+	.size		= linear_size,
+	.quiesce	= linear_quiesce,
+	.error_handler	= linear_error,
+};
+
+static int __init linear_init(void)
+{
+	return register_md_personality(&linear_personality);
+}
+
+static void linear_exit(void)
+{
+	unregister_md_personality(&linear_personality);
+}
+
+module_init(linear_init);
+module_exit(linear_exit);
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Linear device concatenation personality for MD (deprecated)");
+MODULE_ALIAS("md-personality-1"); /* LINEAR - deprecated*/
+MODULE_ALIAS("md-linear");
+MODULE_ALIAS("md-level--1");
diff --git a/drivers/md/md.c b/drivers/md/md.c
index aebe12b0ee27..30b3dbbce2d2 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -294,7 +294,7 @@ void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev)
 
 static struct ctl_table_header *raid_table_header;
 
-static struct ctl_table raid_table[] = {
+static const struct ctl_table raid_table[] = {
 	{
 		.procname	= "speed_limit_min",
 		.data		= &sysctl_speed_limit_min,
@@ -8124,7 +8124,7 @@ void md_error(struct mddev *mddev, struct md_rdev *rdev)
 		return;
 	mddev->pers->error_handler(mddev, rdev);
 
-	if (mddev->pers->level == 0)
+	if (mddev->pers->level == 0 || mddev->pers->level == LEVEL_LINEAR)
 		return;
 
 	if (mddev->degraded && !test_bit(MD_BROKEN, &mddev->flags))
@@ -8376,6 +8376,10 @@ static int md_seq_show(struct seq_file *seq, void *v)
 		return 0;
 
 	spin_unlock(&all_mddevs_lock);
+
+	/* prevent bitmap to be freed after checking */
+	mutex_lock(&mddev->bitmap_info.mutex);
+
 	spin_lock(&mddev->lock);
 	if (mddev->pers || mddev->raid_disks || !list_empty(&mddev->disks)) {
 		seq_printf(seq, "%s : ", mdname(mddev));
@@ -8451,6 +8455,7 @@ static int md_seq_show(struct seq_file *seq, void *v)
 		seq_printf(seq, "\n");
 	}
 	spin_unlock(&mddev->lock);
+	mutex_unlock(&mddev->bitmap_info.mutex);
 	spin_lock(&all_mddevs_lock);
 
 	if (mddev == list_last_entry(&all_mddevs, struct mddev, all_mddevs))
@@ -8745,12 +8750,32 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
 }
 EXPORT_SYMBOL_GPL(md_submit_discard_bio);
 
+static void md_bitmap_start(struct mddev *mddev,
+			    struct md_io_clone *md_io_clone)
+{
+	if (mddev->pers->bitmap_sector)
+		mddev->pers->bitmap_sector(mddev, &md_io_clone->offset,
+					   &md_io_clone->sectors);
+
+	mddev->bitmap_ops->startwrite(mddev, md_io_clone->offset,
+				      md_io_clone->sectors);
+}
+
+static void md_bitmap_end(struct mddev *mddev, struct md_io_clone *md_io_clone)
+{
+	mddev->bitmap_ops->endwrite(mddev, md_io_clone->offset,
+				    md_io_clone->sectors);
+}
+
 static void md_end_clone_io(struct bio *bio)
 {
 	struct md_io_clone *md_io_clone = bio->bi_private;
 	struct bio *orig_bio = md_io_clone->orig_bio;
 	struct mddev *mddev = md_io_clone->mddev;
 
+	if (bio_data_dir(orig_bio) == WRITE && mddev->bitmap)
+		md_bitmap_end(mddev, md_io_clone);
+
 	if (bio->bi_status && !orig_bio->bi_status)
 		orig_bio->bi_status = bio->bi_status;
 
@@ -8775,6 +8800,12 @@ static void md_clone_bio(struct mddev *mddev, struct bio **bio)
 	if (blk_queue_io_stat(bdev->bd_disk->queue))
 		md_io_clone->start_time = bio_start_io_acct(*bio);
 
+	if (bio_data_dir(*bio) == WRITE && mddev->bitmap) {
+		md_io_clone->offset = (*bio)->bi_iter.bi_sector;
+		md_io_clone->sectors = bio_sectors(*bio);
+		md_bitmap_start(mddev, md_io_clone);
+	}
+
 	clone->bi_end_io = md_end_clone_io;
 	clone->bi_private = md_io_clone;
 	*bio = clone;
@@ -8793,6 +8824,9 @@ void md_free_cloned_bio(struct bio *bio)
 	struct bio *orig_bio = md_io_clone->orig_bio;
 	struct mddev *mddev = md_io_clone->mddev;
 
+	if (bio_data_dir(orig_bio) == WRITE && mddev->bitmap)
+		md_bitmap_end(mddev, md_io_clone);
+
 	if (bio->bi_status && !orig_bio->bi_status)
 		orig_bio->bi_status = bio->bi_status;
 
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 4ba93af36126..def808064ad8 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -746,6 +746,9 @@ struct md_personality
 	void *(*takeover) (struct mddev *mddev);
 	/* Changes the consistency policy of an active array. */
 	int (*change_consistency_policy)(struct mddev *mddev, const char *buf);
+	/* convert io ranges from array to bitmap */
+	void (*bitmap_sector)(struct mddev *mddev, sector_t *offset,
+			      unsigned long *sectors);
 };
 
 struct md_sysfs_entry {
@@ -828,6 +831,8 @@ struct md_io_clone {
 	struct mddev	*mddev;
 	struct bio	*orig_bio;
 	unsigned long	start_time;
+	sector_t	offset;
+	unsigned long	sectors;
 	struct bio	bio_clone;
 };
 
diff --git a/drivers/md/persistent-data/dm-array.c b/drivers/md/persistent-data/dm-array.c
index 157c9bd2fed7..8f8792e55806 100644
--- a/drivers/md/persistent-data/dm-array.c
+++ b/drivers/md/persistent-data/dm-array.c
@@ -917,23 +917,27 @@ static int load_ablock(struct dm_array_cursor *c)
 	if (c->block)
 		unlock_ablock(c->info, c->block);
 
-	c->block = NULL;
-	c->ab = NULL;
 	c->index = 0;
 
 	r = dm_btree_cursor_get_value(&c->cursor, &key, &value_le);
 	if (r) {
 		DMERR("dm_btree_cursor_get_value failed");
-		dm_btree_cursor_end(&c->cursor);
+		goto out;
 
 	} else {
 		r = get_ablock(c->info, le64_to_cpu(value_le), &c->block, &c->ab);
 		if (r) {
 			DMERR("get_ablock failed");
-			dm_btree_cursor_end(&c->cursor);
+			goto out;
 		}
 	}
 
+	return 0;
+
+out:
+	dm_btree_cursor_end(&c->cursor);
+	c->block = NULL;
+	c->ab = NULL;
 	return r;
 }
 
@@ -956,10 +960,10 @@ EXPORT_SYMBOL_GPL(dm_array_cursor_begin);
 
 void dm_array_cursor_end(struct dm_array_cursor *c)
 {
-	if (c->block) {
+	if (c->block)
 		unlock_ablock(c->info, c->block);
-		dm_btree_cursor_end(&c->cursor);
-	}
+
+	dm_btree_cursor_end(&c->cursor);
 }
 EXPORT_SYMBOL_GPL(dm_array_cursor_end);
 
@@ -999,6 +1003,7 @@ int dm_array_cursor_skip(struct dm_array_cursor *c, uint32_t count)
 		}
 
 		count -= remaining;
+		c->index += (remaining - 1);
 		r = dm_array_cursor_next(c);
 
 	} while (!r);
diff --git a/drivers/md/persistent-data/dm-transaction-manager.c b/drivers/md/persistent-data/dm-transaction-manager.c
index c7ba4e6cbbc7..98c745d90f48 100644
--- a/drivers/md/persistent-data/dm-transaction-manager.c
+++ b/drivers/md/persistent-data/dm-transaction-manager.c
@@ -13,6 +13,7 @@
 #include <linux/export.h>
 #include <linux/mutex.h>
 #include <linux/hash.h>
+#include <linux/rbtree.h>
 #include <linux/slab.h>
 #include <linux/device-mapper.h>
 
@@ -77,7 +78,7 @@ static void prefetch_issue(struct prefetch_set *p, struct dm_block_manager *bm)
 /*----------------------------------------------------------------*/
 
 struct shadow_info {
-	struct hlist_node hlist;
+	struct rb_node node;
 	dm_block_t where;
 };
 
@@ -95,7 +96,7 @@ struct dm_transaction_manager {
 	struct dm_space_map *sm;
 
 	spinlock_t lock;
-	struct hlist_head buckets[DM_HASH_SIZE];
+	struct rb_root buckets[DM_HASH_SIZE];
 
 	struct prefetch_set prefetches;
 };
@@ -106,14 +107,22 @@ static int is_shadow(struct dm_transaction_manager *tm, dm_block_t b)
 {
 	int r = 0;
 	unsigned int bucket = dm_hash_block(b, DM_HASH_MASK);
-	struct shadow_info *si;
+	struct rb_node **node;
 
 	spin_lock(&tm->lock);
-	hlist_for_each_entry(si, tm->buckets + bucket, hlist)
-		if (si->where == b) {
+	node = &tm->buckets[bucket].rb_node;
+	while (*node) {
+		struct shadow_info *si =
+			rb_entry(*node, struct shadow_info, node);
+		if (b == si->where) {
 			r = 1;
 			break;
 		}
+		if (b < si->where)
+			node = &si->node.rb_left;
+		else
+			node = &si->node.rb_right;
+	}
 	spin_unlock(&tm->lock);
 
 	return r;
@@ -130,30 +139,41 @@ static void insert_shadow(struct dm_transaction_manager *tm, dm_block_t b)
 
 	si = kmalloc(sizeof(*si), GFP_NOIO);
 	if (si) {
+		struct rb_node **node, *parent;
 		si->where = b;
 		bucket = dm_hash_block(b, DM_HASH_MASK);
+
 		spin_lock(&tm->lock);
-		hlist_add_head(&si->hlist, tm->buckets + bucket);
+		node = &tm->buckets[bucket].rb_node;
+		parent = NULL;
+		while (*node) {
+			struct shadow_info *si =
+				rb_entry(*node, struct shadow_info, node);
+			parent = *node;
+			if (b < si->where)
+				node = &si->node.rb_left;
+			else
+				node = &si->node.rb_right;
+		}
+		rb_link_node(&si->node, parent, node);
+		rb_insert_color(&si->node, &tm->buckets[bucket]);
 		spin_unlock(&tm->lock);
 	}
 }
 
 static void wipe_shadow_table(struct dm_transaction_manager *tm)
 {
-	struct shadow_info *si;
-	struct hlist_node *tmp;
-	struct hlist_head *bucket;
-	int i;
+	unsigned int i;
 
 	spin_lock(&tm->lock);
 	for (i = 0; i < DM_HASH_SIZE; i++) {
-		bucket = tm->buckets + i;
-		hlist_for_each_entry_safe(si, tmp, bucket, hlist)
+		while (!RB_EMPTY_ROOT(&tm->buckets[i])) {
+			struct shadow_info *si =
+				rb_entry(tm->buckets[i].rb_node, struct shadow_info, node);
+			rb_erase(&si->node, &tm->buckets[i]);
 			kfree(si);
-
-		INIT_HLIST_HEAD(bucket);
+		}
 	}
-
 	spin_unlock(&tm->lock);
 }
 
@@ -162,7 +182,7 @@ static void wipe_shadow_table(struct dm_transaction_manager *tm)
 static struct dm_transaction_manager *dm_tm_create(struct dm_block_manager *bm,
 						   struct dm_space_map *sm)
 {
-	int i;
+	unsigned int i;
 	struct dm_transaction_manager *tm;
 
 	tm = kmalloc(sizeof(*tm), GFP_KERNEL);
@@ -176,7 +196,7 @@ static struct dm_transaction_manager *dm_tm_create(struct dm_block_manager *bm,
 
 	spin_lock_init(&tm->lock);
 	for (i = 0; i < DM_HASH_SIZE; i++)
-		INIT_HLIST_HEAD(tm->buckets + i);
+		tm->buckets[i] = RB_ROOT;
 
 	prefetch_init(&tm->prefetches);
 
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 7049ec7fb8eb..70bcc3cdf2cd 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -384,12 +384,10 @@ static int raid0_set_limits(struct mddev *mddev)
 	lim.max_write_zeroes_sectors = mddev->chunk_sectors;
 	lim.io_min = mddev->chunk_sectors << 9;
 	lim.io_opt = lim.io_min * mddev->raid_disks;
-	lim.features |= BLK_FEAT_ATOMIC_WRITES_STACKED;
+	lim.features |= BLK_FEAT_ATOMIC_WRITES;
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
-	if (err) {
-		queue_limits_cancel_update(mddev->gendisk->queue);
+	if (err)
 		return err;
-	}
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 519c56f0ee3d..10ea3af40991 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -420,10 +420,8 @@ static void close_write(struct r1bio *r1_bio)
 		r1_bio->behind_master_bio = NULL;
 	}
 
-	/* clear the bitmap if all writes complete successfully */
-	mddev->bitmap_ops->endwrite(mddev, r1_bio->sector, r1_bio->sectors,
-				    !test_bit(R1BIO_Degraded, &r1_bio->state),
-				    test_bit(R1BIO_BehindIO, &r1_bio->state));
+	if (test_bit(R1BIO_BehindIO, &r1_bio->state))
+		mddev->bitmap_ops->end_behind_write(mddev);
 	md_write_end(mddev);
 }
 
@@ -480,8 +478,6 @@ 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;
@@ -1535,11 +1531,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 			write_behind = true;
 
 		r1_bio->bios[i] = NULL;
-		if (!rdev || test_bit(Faulty, &rdev->flags)) {
-			if (i < conf->raid_disks)
-				set_bit(R1BIO_Degraded, &r1_bio->state);
+		if (!rdev || test_bit(Faulty, &rdev->flags))
 			continue;
-		}
 
 		atomic_inc(&rdev->nr_pending);
 		if (test_bit(WriteErrorSeen, &rdev->flags)) {
@@ -1558,16 +1551,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 					 */
 					max_sectors = bad_sectors;
 				rdev_dec_pending(rdev, mddev);
-				/* We don't set R1BIO_Degraded as that
-				 * only applies if the disk is
-				 * missing, so it might be re-added,
-				 * and we want to know to recover this
-				 * chunk.
-				 * In this case the device is here,
-				 * and the fact that this chunk is not
-				 * in-sync is recorded in the bad
-				 * block log
-				 */
 				continue;
 			}
 			if (is_bad) {
@@ -1645,9 +1628,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 			    stats.behind_writes < max_write_behind)
 				alloc_behind_master_bio(r1_bio, bio);
 
-			mddev->bitmap_ops->startwrite(
-				mddev, r1_bio->sector, r1_bio->sectors,
-				test_bit(R1BIO_BehindIO, &r1_bio->state));
+			if (test_bit(R1BIO_BehindIO, &r1_bio->state))
+				mddev->bitmap_ops->start_behind_write(mddev);
 			first_clone = 0;
 		}
 
@@ -2614,12 +2596,10 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio)
 			 * errors.
 			 */
 			fail = true;
-			if (!narrow_write_error(r1_bio, m)) {
+			if (!narrow_write_error(r1_bio, m))
 				md_error(conf->mddev,
 					 conf->mirrors[m].rdev);
 				/* an I/O failed, we can't clear the bitmap */
-				set_bit(R1BIO_Degraded, &r1_bio->state);
-			}
 			rdev_dec_pending(conf->mirrors[m].rdev,
 					 conf->mddev);
 		}
@@ -2710,8 +2690,6 @@ static void raid1d(struct md_thread *thread)
 			list_del(&r1_bio->retry_list);
 			idx = sector_to_idx(r1_bio->sector);
 			atomic_dec(&conf->nr_queued[idx]);
-			if (mddev->degraded)
-				set_bit(R1BIO_Degraded, &r1_bio->state);
 			if (test_bit(R1BIO_WriteError, &r1_bio->state))
 				close_write(r1_bio);
 			raid_end_bio_io(r1_bio);
@@ -3239,12 +3217,10 @@ static int raid1_set_limits(struct mddev *mddev)
 
 	md_init_stacking_limits(&lim);
 	lim.max_write_zeroes_sectors = 0;
-	lim.features |= BLK_FEAT_ATOMIC_WRITES_STACKED;
+	lim.features |= BLK_FEAT_ATOMIC_WRITES;
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
-	if (err) {
-		queue_limits_cancel_update(mddev->gendisk->queue);
+	if (err)
 		return err;
-	}
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h
index 5300cbaa58a4..33f318fcc268 100644
--- a/drivers/md/raid1.h
+++ b/drivers/md/raid1.h
@@ -188,7 +188,6 @@ struct r1bio {
 enum r1bio_state {
 	R1BIO_Uptodate,
 	R1BIO_IsSync,
-	R1BIO_Degraded,
 	R1BIO_BehindIO,
 /* Set ReadError on bios that experience a readerror so that
  * raid1d knows what to do with them.
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 7d7a8a2524dc..15b9ae5bf84d 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -428,10 +428,6 @@ static void close_write(struct r10bio *r10_bio)
 {
 	struct mddev *mddev = r10_bio->mddev;
 
-	/* clear the bitmap if all writes complete successfully */
-	mddev->bitmap_ops->endwrite(mddev, r10_bio->sector, r10_bio->sectors,
-				    !test_bit(R10BIO_Degraded, &r10_bio->state),
-				    false);
 	md_write_end(mddev);
 }
 
@@ -501,7 +497,6 @@ static void raid10_end_write_request(struct bio *bio)
 				set_bit(R10BIO_WriteError, &r10_bio->state);
 			else {
 				/* Fail the request */
-				set_bit(R10BIO_Degraded, &r10_bio->state);
 				r10_bio->devs[slot].bio = NULL;
 				to_put = bio;
 				dec_rdev = 1;
@@ -1438,10 +1433,8 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 		r10_bio->devs[i].bio = NULL;
 		r10_bio->devs[i].repl_bio = NULL;
 
-		if (!rdev && !rrdev) {
-			set_bit(R10BIO_Degraded, &r10_bio->state);
+		if (!rdev && !rrdev)
 			continue;
-		}
 		if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) {
 			sector_t first_bad;
 			sector_t dev_sector = r10_bio->devs[i].addr;
@@ -1458,14 +1451,6 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 					 * to other devices yet
 					 */
 					max_sectors = bad_sectors;
-				/* We don't set R10BIO_Degraded as that
-				 * only applies if the disk is missing,
-				 * so it might be re-added, and we want to
-				 * know to recover this chunk.
-				 * In this case the device is here, and the
-				 * fact that this chunk is not in-sync is
-				 * recorded in the bad block log.
-				 */
 				continue;
 			}
 			if (is_bad) {
@@ -1519,8 +1504,6 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 	md_account_bio(mddev, &bio);
 	r10_bio->master_bio = bio;
 	atomic_set(&r10_bio->remaining, 1);
-	mddev->bitmap_ops->startwrite(mddev, r10_bio->sector, r10_bio->sectors,
-				      false);
 
 	for (i = 0; i < conf->copies; i++) {
 		if (r10_bio->devs[i].bio)
@@ -2966,11 +2949,8 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
 				rdev_dec_pending(rdev, conf->mddev);
 			} else if (bio != NULL && bio->bi_status) {
 				fail = true;
-				if (!narrow_write_error(r10_bio, m)) {
+				if (!narrow_write_error(r10_bio, m))
 					md_error(conf->mddev, rdev);
-					set_bit(R10BIO_Degraded,
-						&r10_bio->state);
-				}
 				rdev_dec_pending(rdev, conf->mddev);
 			}
 			bio = r10_bio->devs[m].repl_bio;
@@ -3029,8 +3009,6 @@ static void raid10d(struct md_thread *thread)
 			r10_bio = list_first_entry(&tmp, struct r10bio,
 						   retry_list);
 			list_del(&r10_bio->retry_list);
-			if (mddev->degraded)
-				set_bit(R10BIO_Degraded, &r10_bio->state);
 
 			if (test_bit(R10BIO_WriteError,
 				     &r10_bio->state))
@@ -4040,12 +4018,10 @@ static int raid10_set_queue_limits(struct mddev *mddev)
 	lim.max_write_zeroes_sectors = 0;
 	lim.io_min = mddev->chunk_sectors << 9;
 	lim.io_opt = lim.io_min * raid10_nr_stripes(conf);
-	lim.features |= BLK_FEAT_ATOMIC_WRITES_STACKED;
+	lim.features |= BLK_FEAT_ATOMIC_WRITES;
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
-	if (err) {
-		queue_limits_cancel_update(mddev->gendisk->queue);
+	if (err)
 		return err;
-	}
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h
index 2e75e88d0802..3f16ad6904a9 100644
--- a/drivers/md/raid10.h
+++ b/drivers/md/raid10.h
@@ -161,7 +161,6 @@ enum r10bio_state {
 	R10BIO_IsSync,
 	R10BIO_IsRecover,
 	R10BIO_IsReshape,
-	R10BIO_Degraded,
 /* Set ReadError on bios that experience a read error
  * so that raid10d knows what to do with them.
  */
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index b4f7b79fd187..e530271cb86b 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -313,10 +313,6 @@ void r5c_handle_cached_data_endio(struct r5conf *conf,
 		if (sh->dev[i].written) {
 			set_bit(R5_UPTODATE, &sh->dev[i].flags);
 			r5c_return_dev_pending_writes(conf, &sh->dev[i]);
-			conf->mddev->bitmap_ops->endwrite(conf->mddev,
-					sh->sector, RAID5_STRIPE_SECTORS(conf),
-					!test_bit(STRIPE_DEGRADED, &sh->state),
-					false);
 		}
 	}
 }
@@ -1023,10 +1019,10 @@ int r5l_write_stripe(struct r5l_log *log, struct stripe_head *sh)
 		/* checksum is already calculated in last run */
 		if (test_bit(STRIPE_LOG_TRAPPED, &sh->state))
 			continue;
-		addr = kmap_atomic(sh->dev[i].page);
+		addr = kmap_local_page(sh->dev[i].page);
 		sh->dev[i].log_checksum = crc32c_le(log->uuid_checksum,
 						    addr, PAGE_SIZE);
-		kunmap_atomic(addr);
+		kunmap_local(addr);
 	}
 	parity_pages = 1 + !!(sh->qd_idx >= 0);
 	data_pages = write_disks - parity_pages;
@@ -1979,9 +1975,9 @@ r5l_recovery_verify_data_checksum(struct r5l_log *log,
 	u32 checksum;
 
 	r5l_recovery_read_page(log, ctx, page, log_offset);
-	addr = kmap_atomic(page);
+	addr = kmap_local_page(page);
 	checksum = crc32c_le(log->uuid_checksum, addr, PAGE_SIZE);
-	kunmap_atomic(addr);
+	kunmap_local(addr);
 	return (le32_to_cpu(log_checksum) == checksum) ? 0 : -EINVAL;
 }
 
@@ -2381,11 +2377,11 @@ r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log,
 				payload->size = cpu_to_le32(BLOCK_SECTORS);
 				payload->location = cpu_to_le64(
 					raid5_compute_blocknr(sh, i, 0));
-				addr = kmap_atomic(dev->page);
+				addr = kmap_local_page(dev->page);
 				payload->checksum[0] = cpu_to_le32(
 					crc32c_le(log->uuid_checksum, addr,
 						  PAGE_SIZE));
-				kunmap_atomic(addr);
+				kunmap_local(addr);
 				sync_page_io(log->rdev, write_pos, PAGE_SIZE,
 					     dev->page, REQ_OP_WRITE, false);
 				write_pos = r5l_ring_add(log, write_pos,
@@ -2888,10 +2884,10 @@ int r5c_cache_data(struct r5l_log *log, struct stripe_head *sh)
 
 		if (!test_bit(R5_Wantwrite, &sh->dev[i].flags))
 			continue;
-		addr = kmap_atomic(sh->dev[i].page);
+		addr = kmap_local_page(sh->dev[i].page);
 		sh->dev[i].log_checksum = crc32c_le(log->uuid_checksum,
 						    addr, PAGE_SIZE);
-		kunmap_atomic(addr);
+		kunmap_local(addr);
 		pages++;
 	}
 	WARN_ON(pages == 0);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index f09e7677ee9f..5c79429acc64 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -906,8 +906,7 @@ static bool stripe_can_batch(struct stripe_head *sh)
 	if (raid5_has_log(conf) || raid5_has_ppl(conf))
 		return false;
 	return test_bit(STRIPE_BATCH_READY, &sh->state) &&
-		!test_bit(STRIPE_BITMAP_PENDING, &sh->state) &&
-		is_full_stripe_write(sh);
+	       is_full_stripe_write(sh);
 }
 
 /* we only do back search */
@@ -1345,8 +1344,6 @@ again:
 				submit_bio_noacct(rbi);
 		}
 		if (!rdev && !rrdev) {
-			if (op_is_write(op))
-				set_bit(STRIPE_DEGRADED, &sh->state);
 			pr_debug("skip op %d on disc %d for sector %llu\n",
 				bi->bi_opf, i, (unsigned long long)sh->sector);
 			clear_bit(R5_LOCKED, &sh->dev[i].flags);
@@ -2884,7 +2881,6 @@ static void raid5_end_write_request(struct bio *bi)
 			set_bit(R5_MadeGoodRepl, &sh->dev[i].flags);
 	} else {
 		if (bi->bi_status) {
-			set_bit(STRIPE_DEGRADED, &sh->state);
 			set_bit(WriteErrorSeen, &rdev->flags);
 			set_bit(R5_WriteError, &sh->dev[i].flags);
 			if (!test_and_set_bit(WantReplacement, &rdev->flags))
@@ -3548,29 +3544,9 @@ static void __add_stripe_bio(struct stripe_head *sh, struct bio *bi,
 		 (*bip)->bi_iter.bi_sector, sh->sector, dd_idx,
 		 sh->dev[dd_idx].sector);
 
-	if (conf->mddev->bitmap && firstwrite) {
-		/* Cannot hold spinlock over bitmap_startwrite,
-		 * but must ensure this isn't added to a batch until
-		 * we have added to the bitmap and set bm_seq.
-		 * So set STRIPE_BITMAP_PENDING to prevent
-		 * batching.
-		 * If multiple __add_stripe_bio() calls race here they
-		 * much all set STRIPE_BITMAP_PENDING.  So only the first one
-		 * to complete "bitmap_startwrite" gets to set
-		 * STRIPE_BIT_DELAY.  This is important as once a stripe
-		 * is added to a batch, STRIPE_BIT_DELAY cannot be changed
-		 * any more.
-		 */
-		set_bit(STRIPE_BITMAP_PENDING, &sh->state);
-		spin_unlock_irq(&sh->stripe_lock);
-		conf->mddev->bitmap_ops->startwrite(conf->mddev, sh->sector,
-					RAID5_STRIPE_SECTORS(conf), false);
-		spin_lock_irq(&sh->stripe_lock);
-		clear_bit(STRIPE_BITMAP_PENDING, &sh->state);
-		if (!sh->batch_head) {
-			sh->bm_seq = conf->seq_flush+1;
-			set_bit(STRIPE_BIT_DELAY, &sh->state);
-		}
+	if (conf->mddev->bitmap && firstwrite && !sh->batch_head) {
+		sh->bm_seq = conf->seq_flush+1;
+		set_bit(STRIPE_BIT_DELAY, &sh->state);
 	}
 }
 
@@ -3621,7 +3597,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 	BUG_ON(sh->batch_head);
 	for (i = disks; i--; ) {
 		struct bio *bi;
-		int bitmap_end = 0;
 
 		if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
 			struct md_rdev *rdev = conf->disks[i].rdev;
@@ -3646,8 +3621,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 		sh->dev[i].towrite = NULL;
 		sh->overwrite_disks = 0;
 		spin_unlock_irq(&sh->stripe_lock);
-		if (bi)
-			bitmap_end = 1;
 
 		log_stripe_write_finished(sh);
 
@@ -3662,11 +3635,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 			bio_io_error(bi);
 			bi = nextbi;
 		}
-		if (bitmap_end)
-			conf->mddev->bitmap_ops->endwrite(conf->mddev,
-					sh->sector, RAID5_STRIPE_SECTORS(conf),
-					false, false);
-		bitmap_end = 0;
 		/* and fail all 'written' */
 		bi = sh->dev[i].written;
 		sh->dev[i].written = NULL;
@@ -3675,7 +3643,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 			sh->dev[i].page = sh->dev[i].orig_page;
 		}
 
-		if (bi) bitmap_end = 1;
 		while (bi && bi->bi_iter.bi_sector <
 		       sh->dev[i].sector + RAID5_STRIPE_SECTORS(conf)) {
 			struct bio *bi2 = r5_next_bio(conf, bi, sh->dev[i].sector);
@@ -3709,10 +3676,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 				bi = nextbi;
 			}
 		}
-		if (bitmap_end)
-			conf->mddev->bitmap_ops->endwrite(conf->mddev,
-					sh->sector, RAID5_STRIPE_SECTORS(conf),
-					false, false);
 		/* If we were in the middle of a write the parity block might
 		 * still be locked - so just clear all R5_LOCKED flags
 		 */
@@ -4061,10 +4024,7 @@ returnbi:
 					bio_endio(wbi);
 					wbi = wbi2;
 				}
-				conf->mddev->bitmap_ops->endwrite(conf->mddev,
-					sh->sector, RAID5_STRIPE_SECTORS(conf),
-					!test_bit(STRIPE_DEGRADED, &sh->state),
-					false);
+
 				if (head_sh->batch_head) {
 					sh = list_first_entry(&sh->batch_list,
 							      struct stripe_head,
@@ -4341,7 +4301,6 @@ static void handle_parity_checks5(struct r5conf *conf, struct stripe_head *sh,
 		s->locked++;
 		set_bit(R5_Wantwrite, &dev->flags);
 
-		clear_bit(STRIPE_DEGRADED, &sh->state);
 		set_bit(STRIPE_INSYNC, &sh->state);
 		break;
 	case check_state_run:
@@ -4498,7 +4457,6 @@ static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh,
 			clear_bit(R5_Wantwrite, &dev->flags);
 			s->locked--;
 		}
-		clear_bit(STRIPE_DEGRADED, &sh->state);
 
 		set_bit(STRIPE_INSYNC, &sh->state);
 		break;
@@ -4891,8 +4849,7 @@ static void break_stripe_batch_list(struct stripe_head *head_sh,
 					  (1 << STRIPE_COMPUTE_RUN)  |
 					  (1 << STRIPE_DISCARD) |
 					  (1 << STRIPE_BATCH_READY) |
-					  (1 << STRIPE_BATCH_ERR) |
-					  (1 << STRIPE_BITMAP_PENDING)),
+					  (1 << STRIPE_BATCH_ERR)),
 			"stripe state: %lx\n", sh->state);
 		WARN_ONCE(head_sh->state & ((1 << STRIPE_DISCARD) |
 					      (1 << STRIPE_REPLACED)),
@@ -4900,7 +4857,6 @@ static void break_stripe_batch_list(struct stripe_head *head_sh,
 
 		set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS |
 					    (1 << STRIPE_PREREAD_ACTIVE) |
-					    (1 << STRIPE_DEGRADED) |
 					    (1 << STRIPE_ON_UNPLUG_LIST)),
 			      head_sh->state & (1 << STRIPE_INSYNC));
 
@@ -5784,10 +5740,6 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
 		}
 		spin_unlock_irq(&sh->stripe_lock);
 		if (conf->mddev->bitmap) {
-			for (d = 0; d < conf->raid_disks - conf->max_degraded;
-			     d++)
-				mddev->bitmap_ops->startwrite(mddev, sh->sector,
-					RAID5_STRIPE_SECTORS(conf), false);
 			sh->bm_seq = conf->seq_flush + 1;
 			set_bit(STRIPE_BIT_DELAY, &sh->state);
 		}
@@ -5928,6 +5880,54 @@ static enum reshape_loc get_reshape_loc(struct mddev *mddev,
 	return LOC_BEHIND_RESHAPE;
 }
 
+static void raid5_bitmap_sector(struct mddev *mddev, sector_t *offset,
+				unsigned long *sectors)
+{
+	struct r5conf *conf = mddev->private;
+	sector_t start = *offset;
+	sector_t end = start + *sectors;
+	sector_t prev_start = start;
+	sector_t prev_end = end;
+	int sectors_per_chunk;
+	enum reshape_loc loc;
+	int dd_idx;
+
+	sectors_per_chunk = conf->chunk_sectors *
+		(conf->raid_disks - conf->max_degraded);
+	start = round_down(start, sectors_per_chunk);
+	end = round_up(end, sectors_per_chunk);
+
+	start = raid5_compute_sector(conf, start, 0, &dd_idx, NULL);
+	end = raid5_compute_sector(conf, end, 0, &dd_idx, NULL);
+
+	/*
+	 * For LOC_INSIDE_RESHAPE, this IO will wait for reshape to make
+	 * progress, hence it's the same as LOC_BEHIND_RESHAPE.
+	 */
+	loc = get_reshape_loc(mddev, conf, prev_start);
+	if (likely(loc != LOC_AHEAD_OF_RESHAPE)) {
+		*offset = start;
+		*sectors = end - start;
+		return;
+	}
+
+	sectors_per_chunk = conf->prev_chunk_sectors *
+		(conf->previous_raid_disks - conf->max_degraded);
+	prev_start = round_down(prev_start, sectors_per_chunk);
+	prev_end = round_down(prev_end, sectors_per_chunk);
+
+	prev_start = raid5_compute_sector(conf, prev_start, 1, &dd_idx, NULL);
+	prev_end = raid5_compute_sector(conf, prev_end, 1, &dd_idx, NULL);
+
+	/*
+	 * for LOC_AHEAD_OF_RESHAPE, reshape can make progress before this IO
+	 * is handled in make_stripe_request(), we can't know this here hence
+	 * we set bits for both.
+	 */
+	*offset = min(start, prev_start);
+	*sectors = max(end, prev_end) - *offset;
+}
+
 static enum stripe_result make_stripe_request(struct mddev *mddev,
 		struct r5conf *conf, struct stripe_request_ctx *ctx,
 		sector_t logical_sector, struct bio *bi)
@@ -8976,6 +8976,7 @@ static struct md_personality raid6_personality =
 	.takeover	= raid6_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
 	.prepare_suspend = raid5_prepare_suspend,
+	.bitmap_sector	= raid5_bitmap_sector,
 };
 static struct md_personality raid5_personality =
 {
@@ -9001,6 +9002,7 @@ static struct md_personality raid5_personality =
 	.takeover	= raid5_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
 	.prepare_suspend = raid5_prepare_suspend,
+	.bitmap_sector	= raid5_bitmap_sector,
 };
 
 static struct md_personality raid4_personality =
@@ -9027,6 +9029,7 @@ static struct md_personality raid4_personality =
 	.takeover	= raid4_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
 	.prepare_suspend = raid5_prepare_suspend,
+	.bitmap_sector	= raid5_bitmap_sector,
 };
 
 static int __init raid5_init(void)
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index d174e586698f..eafc6e9ed6ee 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -358,7 +358,6 @@ enum {
 	STRIPE_REPLACED,
 	STRIPE_PREREAD_ACTIVE,
 	STRIPE_DELAYED,
-	STRIPE_DEGRADED,
 	STRIPE_BIT_DELAY,
 	STRIPE_EXPANDING,
 	STRIPE_EXPAND_SOURCE,
@@ -372,9 +371,6 @@ enum {
 	STRIPE_ON_RELEASE_LIST,
 	STRIPE_BATCH_READY,
 	STRIPE_BATCH_ERR,
-	STRIPE_BITMAP_PENDING,	/* Being added to bitmap, don't add
-				 * to batch yet.
-				 */
 	STRIPE_LOG_TRAPPED,	/* trapped into log (see raid5-cache.c)
 				 * this bit is used in two scenarios:
 				 *