Merging upstream version 6.1.85.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

23 files changed, 136 insertions, 88 deletions

diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 100a6a236..ec662f97b 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -614,7 +614,7 @@ static void use_dmio(struct dm_buffer *b, enum req_op op, sector_t sector,
 		io_req.mem.ptr.vma = (char *)b->data + offset;
 	}
 
-	r = dm_io(&io_req, 1, &region, NULL);
+	r = dm_io(&io_req, 1, &region, NULL, IOPRIO_DEFAULT);
 	if (unlikely(r))
 		b->end_io(b, errno_to_blk_status(r));
 }
@@ -1375,7 +1375,7 @@ int dm_bufio_issue_flush(struct dm_bufio_client *c)
 
 	BUG_ON(dm_bufio_in_request());
 
-	return dm_io(&io_req, 1, &io_reg, NULL);
+	return dm_io(&io_req, 1, &io_reg, NULL, IOPRIO_DEFAULT);
 }
 EXPORT_SYMBOL_GPL(dm_bufio_issue_flush);
 
@@ -1398,7 +1398,7 @@ int dm_bufio_issue_discard(struct dm_bufio_client *c, sector_t block, sector_t c
 
 	BUG_ON(dm_bufio_in_request());
 
-	return dm_io(&io_req, 1, &io_reg, NULL);
+	return dm_io(&io_req, 1, &io_reg, NULL, IOPRIO_DEFAULT);
 }
 EXPORT_SYMBOL_GPL(dm_bufio_issue_discard);
 
diff --git a/drivers/md/dm-cache-policy.h b/drivers/md/dm-cache-policy.h
index 6ba3e9c91..8bc21d548 100644
--- a/drivers/md/dm-cache-policy.h
+++ b/drivers/md/dm-cache-policy.h
@@ -75,7 +75,7 @@ struct dm_cache_policy {
 	 * background work.
 	 */
 	int (*get_background_work)(struct dm_cache_policy *p, bool idle,
-			           struct policy_work **result);
+				   struct policy_work **result);
 
 	/*
 	 * You must pass in the same work pointer that you were given, not
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 3e215aa85..25e51dc6e 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -52,11 +52,11 @@
 struct convert_context {
 	struct completion restart;
 	struct bio *bio_in;
-	struct bio *bio_out;
 	struct bvec_iter iter_in;
+	struct bio *bio_out;
 	struct bvec_iter iter_out;
-	u64 cc_sector;
 	atomic_t cc_pending;
+	u64 cc_sector;
 	union {
 		struct skcipher_request *req;
 		struct aead_request *req_aead;
@@ -2535,7 +2535,7 @@ static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string
 		type = &key_type_encrypted;
 		set_key = set_key_encrypted;
 	} else if (IS_ENABLED(CONFIG_TRUSTED_KEYS) &&
-	           !strncmp(key_string, "trusted:", key_desc - key_string + 1)) {
+		   !strncmp(key_string, "trusted:", key_desc - key_string + 1)) {
 		type = &key_type_trusted;
 		set_key = set_key_trusted;
 	} else {
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 3da4359f5..696365f8f 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -579,7 +579,7 @@ static int sync_rw_sb(struct dm_integrity_c *ic, blk_opf_t opf)
 		}
 	}
 
-	r = dm_io(&io_req, 1, &io_loc, NULL);
+	r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT);
 	if (unlikely(r))
 		return r;
 
@@ -1089,7 +1089,7 @@ static void rw_journal_sectors(struct dm_integrity_c *ic, blk_opf_t opf,
 	io_loc.sector = ic->start + SB_SECTORS + sector;
 	io_loc.count = n_sectors;
 
-	r = dm_io(&io_req, 1, &io_loc, NULL);
+	r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT);
 	if (unlikely(r)) {
 		dm_integrity_io_error(ic, (opf & REQ_OP_MASK) == REQ_OP_READ ?
 				      "reading journal" : "writing journal", r);
@@ -1205,7 +1205,7 @@ static void copy_from_journal(struct dm_integrity_c *ic, unsigned int section, u
 	io_loc.sector = target;
 	io_loc.count = n_sectors;
 
-	r = dm_io(&io_req, 1, &io_loc, NULL);
+	r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT);
 	if (unlikely(r)) {
 		WARN_ONCE(1, "asynchronous dm_io failed: %d", r);
 		fn(-1UL, data);
@@ -1532,7 +1532,7 @@ static void dm_integrity_flush_buffers(struct dm_integrity_c *ic, bool flush_dat
 		fr.io_reg.count = 0,
 		fr.ic = ic;
 		init_completion(&fr.comp);
-		r = dm_io(&fr.io_req, 1, &fr.io_reg, NULL);
+		r = dm_io(&fr.io_req, 1, &fr.io_reg, NULL, IOPRIO_DEFAULT);
 		BUG_ON(r);
 	}
 
@@ -1709,7 +1709,6 @@ static noinline void integrity_recheck(struct dm_integrity_io *dio, char *checks
 	struct bio_vec bv;
 	sector_t sector, logical_sector, area, offset;
 	struct page *page;
-	void *buffer;
 
 	get_area_and_offset(ic, dio->range.logical_sector, &area, &offset);
 	dio->metadata_block = get_metadata_sector_and_offset(ic, area, offset,
@@ -1718,13 +1717,14 @@ static noinline void integrity_recheck(struct dm_integrity_io *dio, char *checks
 	logical_sector = dio->range.logical_sector;
 
 	page = mempool_alloc(&ic->recheck_pool, GFP_NOIO);
-	buffer = page_to_virt(page);
 
 	__bio_for_each_segment(bv, bio, iter, dio->bio_details.bi_iter) {
 		unsigned pos = 0;
 
 		do {
+			sector_t alignment;
 			char *mem;
+			char *buffer = page_to_virt(page);
 			int r;
 			struct dm_io_request io_req;
 			struct dm_io_region io_loc;
@@ -1737,7 +1737,15 @@ static noinline void integrity_recheck(struct dm_integrity_io *dio, char *checks
 			io_loc.sector = sector;
 			io_loc.count = ic->sectors_per_block;
 
-			r = dm_io(&io_req, 1, &io_loc, NULL);
+			/* Align the bio to logical block size */
+			alignment = dio->range.logical_sector | bio_sectors(bio) | (PAGE_SIZE >> SECTOR_SHIFT);
+			alignment &= -alignment;
+			io_loc.sector = round_down(io_loc.sector, alignment);
+			io_loc.count += sector - io_loc.sector;
+			buffer += (sector - io_loc.sector) << SECTOR_SHIFT;
+			io_loc.count = round_up(io_loc.count, alignment);
+
+			r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT);
 			if (unlikely(r)) {
 				dio->bi_status = errno_to_blk_status(r);
 				goto free_ret;
@@ -1856,12 +1864,12 @@ again:
 			r = dm_integrity_rw_tag(ic, checksums, &dio->metadata_block, &dio->metadata_offset,
 						checksums_ptr - checksums, dio->op == REQ_OP_READ ? TAG_CMP : TAG_WRITE);
 			if (unlikely(r)) {
+				if (likely(checksums != checksums_onstack))
+					kfree(checksums);
 				if (r > 0) {
-					integrity_recheck(dio, checksums);
+					integrity_recheck(dio, checksums_onstack);
 					goto skip_io;
 				}
-				if (likely(checksums != checksums_onstack))
-					kfree(checksums);
 				goto error;
 			}
 
@@ -2367,7 +2375,6 @@ offload_to_thread:
 		else
 skip_check:
 			dec_in_flight(dio);
-
 	} else {
 		INIT_WORK(&dio->work, integrity_metadata);
 		queue_work(ic->metadata_wq, &dio->work);
@@ -2775,7 +2782,7 @@ next_chunk:
 	io_loc.sector = get_data_sector(ic, area, offset);
 	io_loc.count = n_sectors;
 
-	r = dm_io(&io_req, 1, &io_loc, NULL);
+	r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT);
 	if (unlikely(r)) {
 		dm_integrity_io_error(ic, "reading data", r);
 		goto err;
@@ -4151,7 +4158,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv
 		} else if (sscanf(opt_string, "block_size:%u%c", &val, &dummy) == 1) {
 			if (val < 1 << SECTOR_SHIFT ||
 			    val > MAX_SECTORS_PER_BLOCK << SECTOR_SHIFT ||
-			    (val & (val -1))) {
+			    (val & (val - 1))) {
 				r = -EINVAL;
 				ti->error = "Invalid block_size argument";
 				goto bad;
@@ -4160,7 +4167,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv
 		} else if (sscanf(opt_string, "sectors_per_bit:%llu%c", &llval, &dummy) == 1) {
 			log2_sectors_per_bitmap_bit = !llval ? 0 : __ilog2_u64(llval);
 		} else if (sscanf(opt_string, "bitmap_flush_interval:%u%c", &val, &dummy) == 1) {
-			if (val >= (uint64_t)UINT_MAX * 1000 / HZ) {
+			if ((uint64_t)val >= (uint64_t)UINT_MAX * 1000 / HZ) {
 				r = -EINVAL;
 				ti->error = "Invalid bitmap_flush_interval argument";
 				goto bad;
@@ -4477,7 +4484,7 @@ try_smaller_buffer:
 	if (ic->internal_hash) {
 		size_t recalc_tags_size;
 		ic->recalc_wq = alloc_workqueue("dm-integrity-recalc", WQ_MEM_RECLAIM, 1);
-		if (!ic->recalc_wq ) {
+		if (!ic->recalc_wq) {
 			ti->error = "Cannot allocate workqueue";
 			r = -ENOMEM;
 			goto bad;
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index e488b05e3..ec9765838 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -295,7 +295,7 @@ static void km_dp_init(struct dpages *dp, void *data)
  *---------------------------------------------------------------*/
 static void do_region(const blk_opf_t opf, unsigned int region,
 		      struct dm_io_region *where, struct dpages *dp,
-		      struct io *io)
+		      struct io *io, unsigned short ioprio)
 {
 	struct bio *bio;
 	struct page *page;
@@ -344,6 +344,7 @@ static void do_region(const blk_opf_t opf, unsigned int region,
 				       &io->client->bios);
 		bio->bi_iter.bi_sector = where->sector + (where->count - remaining);
 		bio->bi_end_io = endio;
+		bio->bi_ioprio = ioprio;
 		store_io_and_region_in_bio(bio, io, region);
 
 		if (op == REQ_OP_DISCARD || op == REQ_OP_WRITE_ZEROES) {
@@ -371,7 +372,7 @@ static void do_region(const blk_opf_t opf, unsigned int region,
 
 static void dispatch_io(blk_opf_t opf, unsigned int num_regions,
 			struct dm_io_region *where, struct dpages *dp,
-			struct io *io, int sync)
+			struct io *io, int sync, unsigned short ioprio)
 {
 	int i;
 	struct dpages old_pages = *dp;
@@ -388,7 +389,7 @@ static void dispatch_io(blk_opf_t opf, unsigned int num_regions,
 	for (i = 0; i < num_regions; i++) {
 		*dp = old_pages;
 		if (where[i].count || (opf & REQ_PREFLUSH))
-			do_region(opf, i, where + i, dp, io);
+			do_region(opf, i, where + i, dp, io, ioprio);
 	}
 
 	/*
@@ -413,7 +414,7 @@ static void sync_io_complete(unsigned long error, void *context)
 
 static int sync_io(struct dm_io_client *client, unsigned int num_regions,
 		   struct dm_io_region *where, blk_opf_t opf, struct dpages *dp,
-		   unsigned long *error_bits)
+		   unsigned long *error_bits, unsigned short ioprio)
 {
 	struct io *io;
 	struct sync_io sio;
@@ -435,7 +436,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
 	io->vma_invalidate_address = dp->vma_invalidate_address;
 	io->vma_invalidate_size = dp->vma_invalidate_size;
 
-	dispatch_io(opf, num_regions, where, dp, io, 1);
+	dispatch_io(opf, num_regions, where, dp, io, 1, ioprio);
 
 	wait_for_completion_io(&sio.wait);
 
@@ -447,7 +448,8 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
 
 static int async_io(struct dm_io_client *client, unsigned int num_regions,
 		    struct dm_io_region *where, blk_opf_t opf,
-		    struct dpages *dp, io_notify_fn fn, void *context)
+		    struct dpages *dp, io_notify_fn fn, void *context,
+		    unsigned short ioprio)
 {
 	struct io *io;
 
@@ -467,7 +469,7 @@ static int async_io(struct dm_io_client *client, unsigned int num_regions,
 	io->vma_invalidate_address = dp->vma_invalidate_address;
 	io->vma_invalidate_size = dp->vma_invalidate_size;
 
-	dispatch_io(opf, num_regions, where, dp, io, 0);
+	dispatch_io(opf, num_regions, where, dp, io, 0, ioprio);
 	return 0;
 }
 
@@ -509,7 +511,8 @@ static int dp_init(struct dm_io_request *io_req, struct dpages *dp,
 }
 
 int dm_io(struct dm_io_request *io_req, unsigned int num_regions,
-	  struct dm_io_region *where, unsigned long *sync_error_bits)
+	  struct dm_io_region *where, unsigned long *sync_error_bits,
+	  unsigned short ioprio)
 {
 	int r;
 	struct dpages dp;
@@ -520,11 +523,11 @@ int dm_io(struct dm_io_request *io_req, unsigned int num_regions,
 
 	if (!io_req->notify.fn)
 		return sync_io(io_req->client, num_regions, where,
-			       io_req->bi_opf, &dp, sync_error_bits);
+			       io_req->bi_opf, &dp, sync_error_bits, ioprio);
 
 	return async_io(io_req->client, num_regions, where,
 			io_req->bi_opf, &dp, io_req->notify.fn,
-			io_req->notify.context);
+			io_req->notify.context, ioprio);
 }
 EXPORT_SYMBOL(dm_io);
 
diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c
index 0ef78e56a..fda51bd14 100644
--- a/drivers/md/dm-kcopyd.c
+++ b/drivers/md/dm-kcopyd.c
@@ -572,9 +572,9 @@ static int run_io_job(struct kcopyd_job *job)
 	io_job_start(job->kc->throttle);
 
 	if (job->op == REQ_OP_READ)
-		r = dm_io(&io_req, 1, &job->source, NULL);
+		r = dm_io(&io_req, 1, &job->source, NULL, IOPRIO_DEFAULT);
 	else
-		r = dm_io(&io_req, job->num_dests, job->dests, NULL);
+		r = dm_io(&io_req, job->num_dests, job->dests, NULL, IOPRIO_DEFAULT);
 
 	return r;
 }
diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c
index 05141eea1..da77878cb 100644
--- a/drivers/md/dm-log.c
+++ b/drivers/md/dm-log.c
@@ -295,7 +295,7 @@ static int rw_header(struct log_c *lc, enum req_op op)
 {
 	lc->io_req.bi_opf = op;
 
-	return dm_io(&lc->io_req, 1, &lc->header_location, NULL);
+	return dm_io(&lc->io_req, 1, &lc->header_location, NULL, IOPRIO_DEFAULT);
 }
 
 static int flush_header(struct log_c *lc)
@@ -308,7 +308,7 @@ static int flush_header(struct log_c *lc)
 
 	lc->io_req.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
 
-	return dm_io(&lc->io_req, 1, &null_location, NULL);
+	return dm_io(&lc->io_req, 1, &null_location, NULL, IOPRIO_DEFAULT);
 }
 
 static int read_header(struct log_c *log)
@@ -756,8 +756,8 @@ static void core_set_region_sync(struct dm_dirty_log *log, region_t region,
 	log_clear_bit(lc, lc->recovering_bits, region);
 	if (in_sync) {
 		log_set_bit(lc, lc->sync_bits, region);
-                lc->sync_count++;
-        } else if (log_test_bit(lc->sync_bits, region)) {
+		lc->sync_count++;
+	} else if (log_test_bit(lc->sync_bits, region)) {
 		lc->sync_count--;
 		log_clear_bit(lc, lc->sync_bits, region);
 	}
@@ -765,9 +765,9 @@ static void core_set_region_sync(struct dm_dirty_log *log, region_t region,
 
 static region_t core_get_sync_count(struct dm_dirty_log *log)
 {
-        struct log_c *lc = (struct log_c *) log->context;
+	struct log_c *lc = (struct log_c *) log->context;
 
-        return lc->sync_count;
+	return lc->sync_count;
 }
 
 #define	DMEMIT_SYNC \
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 4b7528dc2..99b4738e8 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -362,8 +362,8 @@ static struct {
 	const int mode;
 	const char *param;
 } _raid456_journal_mode[] = {
-	{ R5C_JOURNAL_MODE_WRITE_THROUGH , "writethrough" },
-	{ R5C_JOURNAL_MODE_WRITE_BACK    , "writeback" }
+	{ R5C_JOURNAL_MODE_WRITE_THROUGH, "writethrough" },
+	{ R5C_JOURNAL_MODE_WRITE_BACK,    "writeback" }
 };
 
 /* Return MD raid4/5/6 journal mode for dm @journal_mode one */
@@ -1114,7 +1114,7 @@ too_many:
  *    [stripe_cache <sectors>]		Stripe cache size for higher RAIDs
  *    [region_size <sectors>]		Defines granularity of bitmap
  *    [journal_dev <dev>]		raid4/5/6 journaling deviice
- *    					(i.e. write hole closing log)
+ *					(i.e. write hole closing log)
  *
  * RAID10-only options:
  *    [raid10_copies <# copies>]	Number of copies.  (Default: 2)
@@ -3325,14 +3325,14 @@ static int raid_map(struct dm_target *ti, struct bio *bio)
 	struct mddev *mddev = &rs->md;
 
 	/*
-	 * If we're reshaping to add disk(s)), ti->len and
+	 * If we're reshaping to add disk(s), ti->len and
 	 * mddev->array_sectors will differ during the process
 	 * (ti->len > mddev->array_sectors), so we have to requeue
 	 * bios with addresses > mddev->array_sectors here or
 	 * there will occur accesses past EOD of the component
 	 * data images thus erroring the raid set.
 	 */
-	if (unlikely(bio_end_sector(bio) > mddev->array_sectors))
+	if (unlikely(bio_has_data(bio) && bio_end_sector(bio) > mddev->array_sectors))
 		return DM_MAPIO_REQUEUE;
 
 	md_handle_request(mddev, bio);
@@ -3999,7 +3999,7 @@ static int raid_preresume(struct dm_target *ti)
 	}
 
 	/* Resize bitmap to adjust to changed region size (aka MD bitmap chunksize) or grown device size */
-        if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) && mddev->bitmap &&
+	if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) && mddev->bitmap &&
 	    (test_bit(RT_FLAG_RS_GROW, &rs->runtime_flags) ||
 	     (rs->requested_bitmap_chunk_sectors &&
 	       mddev->bitmap_info.chunksize != to_bytes(rs->requested_bitmap_chunk_sectors)))) {
@@ -4046,7 +4046,9 @@ static void raid_resume(struct dm_target *ti)
 		 * Take this opportunity to check whether any failed
 		 * devices are reachable again.
 		 */
+		mddev_lock_nointr(mddev);
 		attempt_restore_of_faulty_devices(rs);
+		mddev_unlock(mddev);
 	}
 
 	if (test_and_clear_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) {
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index c38e63706..1004199ae 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -273,7 +273,7 @@ static int mirror_flush(struct dm_target *ti)
 	}
 
 	error_bits = -1;
-	dm_io(&io_req, ms->nr_mirrors, io, &error_bits);
+	dm_io(&io_req, ms->nr_mirrors, io, &error_bits, IOPRIO_DEFAULT);
 	if (unlikely(error_bits != 0)) {
 		for (i = 0; i < ms->nr_mirrors; i++)
 			if (test_bit(i, &error_bits))
@@ -543,7 +543,7 @@ static void read_async_bio(struct mirror *m, struct bio *bio)
 
 	map_region(&io, m, bio);
 	bio_set_m(bio, m);
-	BUG_ON(dm_io(&io_req, 1, &io, NULL));
+	BUG_ON(dm_io(&io_req, 1, &io, NULL, IOPRIO_DEFAULT));
 }
 
 static inline int region_in_sync(struct mirror_set *ms, region_t region,
@@ -670,7 +670,7 @@ static void do_write(struct mirror_set *ms, struct bio *bio)
 	 */
 	bio_set_m(bio, get_default_mirror(ms));
 
-	BUG_ON(dm_io(&io_req, ms->nr_mirrors, io, NULL));
+	BUG_ON(dm_io(&io_req, ms->nr_mirrors, io, NULL, IOPRIO_DEFAULT));
 }
 
 static void do_writes(struct mirror_set *ms, struct bio_list *writes)
@@ -902,7 +902,7 @@ static struct mirror_set *alloc_context(unsigned int nr_mirrors,
 	if (IS_ERR(ms->io_client)) {
 		ti->error = "Error creating dm_io client";
 		kfree(ms);
- 		return NULL;
+		return NULL;
 	}
 
 	ms->rh = dm_region_hash_create(ms, dispatch_bios, wakeup_mirrord,
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index 80b95746a..eee1cd3aa 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -220,7 +220,7 @@ static void do_metadata(struct work_struct *work)
 {
 	struct mdata_req *req = container_of(work, struct mdata_req, work);
 
-	req->result = dm_io(req->io_req, 1, req->where, NULL);
+	req->result = dm_io(req->io_req, 1, req->where, NULL, IOPRIO_DEFAULT);
 }
 
 /*
@@ -244,7 +244,7 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, blk_opf_t opf,
 	struct mdata_req req;
 
 	if (!metadata)
-		return dm_io(&io_req, 1, &where, NULL);
+		return dm_io(&io_req, 1, &where, NULL, IOPRIO_DEFAULT);
 
 	req.where = &where;
 	req.io_req = &io_req;
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index b748901a4..1c601508c 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -679,8 +679,10 @@ static void dm_exception_table_exit(struct dm_exception_table *et,
 	for (i = 0; i < size; i++) {
 		slot = et->table + i;
 
-		hlist_bl_for_each_entry_safe(ex, pos, n, slot, hash_list)
+		hlist_bl_for_each_entry_safe(ex, pos, n, slot, hash_list) {
 			kmem_cache_free(mem, ex);
+			cond_resched();
+		}
 	}
 
 	kvfree(et->table);
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index e0367a672..aabb24350 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -72,7 +72,7 @@ static sector_t high(struct dm_table *t, unsigned int l, unsigned int n)
 		n = get_child(n, CHILDREN_PER_NODE - 1);
 
 	if (n >= t->counts[l])
-		return (sector_t) - 1;
+		return (sector_t) -1;
 
 	return get_node(t, l, n)[KEYS_PER_NODE - 1];
 }
@@ -1533,7 +1533,7 @@ static bool dm_table_any_dev_attr(struct dm_table *t,
 		if (ti->type->iterate_devices &&
 		    ti->type->iterate_devices(ti, func, data))
 			return true;
-        }
+	}
 
 	return false;
 }
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 601f9e4e6..f24d89af7 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -1179,9 +1179,9 @@ static void process_prepared_discard_passdown_pt1(struct dm_thin_new_mapping *m)
 	discard_parent = bio_alloc(NULL, 1, 0, GFP_NOIO);
 	discard_parent->bi_end_io = passdown_endio;
 	discard_parent->bi_private = m;
- 	if (m->maybe_shared)
- 		passdown_double_checking_shared_status(m, discard_parent);
- 	else {
+	if (m->maybe_shared)
+		passdown_double_checking_shared_status(m, discard_parent);
+	else {
 		struct discard_op op;
 
 		begin_discard(&op, tc, discard_parent);
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index b48e1b59e..6a707b41d 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -503,7 +503,7 @@ static noinline int verity_recheck(struct dm_verity *v, struct dm_verity_io *io,
 	io_loc.bdev = v->data_dev->bdev;
 	io_loc.sector = cur_block << (v->data_dev_block_bits - SECTOR_SHIFT);
 	io_loc.count = 1 << (v->data_dev_block_bits - SECTOR_SHIFT);
-	r = dm_io(&io_req, 1, &io_loc, NULL);
+	r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT);
 	if (unlikely(r))
 		goto free_ret;
 
diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h
index 4620a98c9..db93a9116 100644
--- a/drivers/md/dm-verity.h
+++ b/drivers/md/dm-verity.h
@@ -80,12 +80,12 @@ struct dm_verity_io {
 	/* original value of bio->bi_end_io */
 	bio_end_io_t *orig_bi_end_io;
 
+	struct bvec_iter iter;
+
 	sector_t block;
 	unsigned int n_blocks;
 	bool in_tasklet;
 
-	struct bvec_iter iter;
-
 	struct work_struct work;
 
 	char *recheck_buffer;
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index c6ff43a8f..20fc84b24 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -531,7 +531,7 @@ static void ssd_commit_flushed(struct dm_writecache *wc, bool wait_for_ios)
 		req.notify.context = &endio;
 
 		/* writing via async dm-io (implied by notify.fn above) won't return an error */
-	        (void) dm_io(&req, 1, &region, NULL);
+		(void) dm_io(&req, 1, &region, NULL, IOPRIO_DEFAULT);
 		i = j;
 	}
 
@@ -568,7 +568,7 @@ static void ssd_commit_superblock(struct dm_writecache *wc)
 	req.notify.fn = NULL;
 	req.notify.context = NULL;
 
-	r = dm_io(&req, 1, &region, NULL);
+	r = dm_io(&req, 1, &region, NULL, IOPRIO_DEFAULT);
 	if (unlikely(r))
 		writecache_error(wc, r, "error writing superblock");
 }
@@ -596,7 +596,7 @@ static void writecache_disk_flush(struct dm_writecache *wc, struct dm_dev *dev)
 	req.client = wc->dm_io;
 	req.notify.fn = NULL;
 
-	r = dm_io(&req, 1, &region, NULL);
+	r = dm_io(&req, 1, &region, NULL, IOPRIO_DEFAULT);
 	if (unlikely(r))
 		writecache_error(wc, r, "error flushing metadata: %d", r);
 }
@@ -984,7 +984,7 @@ static int writecache_read_metadata(struct dm_writecache *wc, sector_t n_sectors
 	req.client = wc->dm_io;
 	req.notify.fn = NULL;
 
-	return dm_io(&req, 1, &region, NULL);
+	return dm_io(&req, 1, &region, NULL, IOPRIO_DEFAULT);
 }
 
 static void writecache_resume(struct dm_target *ti)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 0ec85d159..29270f6f2 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2897,6 +2897,9 @@ static void __dm_internal_suspend(struct mapped_device *md, unsigned int suspend
 
 static void __dm_internal_resume(struct mapped_device *md)
 {
+	int r;
+	struct dm_table *map;
+
 	BUG_ON(!md->internal_suspend_count);
 
 	if (--md->internal_suspend_count)
@@ -2905,12 +2908,23 @@ static void __dm_internal_resume(struct mapped_device *md)
 	if (dm_suspended_md(md))
 		goto done; /* resume from nested suspend */
 
-	/*
-	 * NOTE: existing callers don't need to call dm_table_resume_targets
-	 * (which may fail -- so best to avoid it for now by passing NULL map)
-	 */
-	(void) __dm_resume(md, NULL);
-
+	map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock));
+	r = __dm_resume(md, map);
+	if (r) {
+		/*
+		 * If a preresume method of some target failed, we are in a
+		 * tricky situation. We can't return an error to the caller. We
+		 * can't fake success because then the "resume" and
+		 * "postsuspend" methods would not be paired correctly, and it
+		 * would break various targets, for example it would cause list
+		 * corruption in the "origin" target.
+		 *
+		 * So, we fake normal suspend here, to make sure that the
+		 * "resume" and "postsuspend" methods will be paired correctly.
+		 */
+		DMERR("Preresume method failed: %d", r);
+		set_bit(DMF_SUSPENDED, &md->flags);
+	}
 done:
 	clear_bit(DMF_SUSPENDED_INTERNALLY, &md->flags);
 	smp_mb__after_atomic();
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 846bdee4d..788acc81e 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -4903,11 +4903,21 @@ action_store(struct mddev *mddev, const char *page, size_t len)
 			return -EINVAL;
 		err = mddev_lock(mddev);
 		if (!err) {
-			if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+			if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
 				err =  -EBUSY;
-			else {
+			} else if (mddev->reshape_position == MaxSector ||
+				   mddev->pers->check_reshape == NULL ||
+				   mddev->pers->check_reshape(mddev)) {
 				clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 				err = mddev->pers->start_reshape(mddev);
+			} else {
+				/*
+				 * If reshape is still in progress, and
+				 * md_check_recovery() can continue to reshape,
+				 * don't restart reshape because data can be
+				 * corrupted for raid456.
+				 */
+				clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 			}
 			mddev_unlock(mddev);
 		}
@@ -6233,7 +6243,15 @@ static void md_clean(struct mddev *mddev)
 	mddev->persistent = 0;
 	mddev->level = LEVEL_NONE;
 	mddev->clevel[0] = 0;
-	mddev->flags = 0;
+	/*
+	 * Don't clear MD_CLOSING, or mddev can be opened again.
+	 * 'hold_active != 0' means mddev is still in the creation
+	 * process and will be used later.
+	 */
+	if (mddev->hold_active)
+		mddev->flags = 0;
+	else
+		mddev->flags &= BIT_ULL_MASK(MD_CLOSING);
 	mddev->sb_flags = 0;
 	mddev->ro = MD_RDWR;
 	mddev->metadata_type[0] = 0;
@@ -7561,7 +7579,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 	int err = 0;
 	void __user *argp = (void __user *)arg;
 	struct mddev *mddev = NULL;
-	bool did_set_md_closing = false;
 
 	if (!md_ioctl_valid(cmd))
 		return -ENOTTY;
@@ -7648,7 +7665,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 			err = -EBUSY;
 			goto out;
 		}
-		did_set_md_closing = true;
 		mutex_unlock(&mddev->open_mutex);
 		sync_blockdev(bdev);
 	}
@@ -7811,7 +7827,7 @@ unlock:
 		mddev->hold_active = 0;
 	mddev_unlock(mddev);
 out:
-	if(did_set_md_closing)
+	if (cmd == STOP_ARRAY_RO || (err && cmd == STOP_ARRAY))
 		clear_bit(MD_CLOSING, &mddev->flags);
 	return err;
 }
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
index 1cc783d70..18d949d63 100644
--- a/drivers/md/persistent-data/dm-btree.c
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -726,7 +726,7 @@ static int shadow_child(struct dm_btree_info *info, struct dm_btree_value_type *
  * nodes, so saves metadata space.
  */
 static int split_two_into_three(struct shadow_spine *s, unsigned int parent_index,
-                                struct dm_btree_value_type *vt, uint64_t key)
+				struct dm_btree_value_type *vt, uint64_t key)
 {
 	int r;
 	unsigned int middle_index;
@@ -781,7 +781,7 @@ static int split_two_into_three(struct shadow_spine *s, unsigned int parent_inde
 		if (shadow_current(s) != right)
 			unlock_block(s->info, right);
 
-	        return r;
+		return r;
 	}
 
 
@@ -1216,7 +1216,7 @@ int btree_get_overwrite_leaf(struct dm_btree_info *info, dm_block_t root,
 static bool need_insert(struct btree_node *node, uint64_t *keys,
 			unsigned int level, unsigned int index)
 {
-        return ((index >= le32_to_cpu(node->header.nr_entries)) ||
+	return ((index >= le32_to_cpu(node->header.nr_entries)) ||
 		(le64_to_cpu(node->keys[index]) != keys[level]));
 }
 
diff --git a/drivers/md/persistent-data/dm-space-map-common.c b/drivers/md/persistent-data/dm-space-map-common.c
index af800efed..4833a3998 100644
--- a/drivers/md/persistent-data/dm-space-map-common.c
+++ b/drivers/md/persistent-data/dm-space-map-common.c
@@ -390,7 +390,7 @@ int sm_ll_find_free_block(struct ll_disk *ll, dm_block_t begin,
 }
 
 int sm_ll_find_common_free_block(struct ll_disk *old_ll, struct ll_disk *new_ll,
-	                         dm_block_t begin, dm_block_t end, dm_block_t *b)
+				 dm_block_t begin, dm_block_t end, dm_block_t *b)
 {
 	int r;
 	uint32_t count;
diff --git a/drivers/md/persistent-data/dm-space-map-common.h b/drivers/md/persistent-data/dm-space-map-common.h
index 706ceb85d..63d9a72e3 100644
--- a/drivers/md/persistent-data/dm-space-map-common.h
+++ b/drivers/md/persistent-data/dm-space-map-common.h
@@ -120,7 +120,7 @@ int sm_ll_lookup(struct ll_disk *ll, dm_block_t b, uint32_t *result);
 int sm_ll_find_free_block(struct ll_disk *ll, dm_block_t begin,
 			  dm_block_t end, dm_block_t *result);
 int sm_ll_find_common_free_block(struct ll_disk *old_ll, struct ll_disk *new_ll,
-	                         dm_block_t begin, dm_block_t end, dm_block_t *result);
+				 dm_block_t begin, dm_block_t end, dm_block_t *result);
 
 /*
  * The next three functions return (via nr_allocations) the net number of
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 7b318e7e8..009f7ffe4 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -920,6 +920,7 @@ static void flush_pending_writes(struct r10conf *conf)
 
 			raid1_submit_write(bio);
 			bio = next;
+			cond_resched();
 		}
 		blk_finish_plug(&plug);
 	} else
@@ -1130,6 +1131,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
 
 		raid1_submit_write(bio);
 		bio = next;
+		cond_resched();
 	}
 	kfree(plug);
 }
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index e4564ca1f..8cf231785 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2420,7 +2420,7 @@ static int grow_one_stripe(struct r5conf *conf, gfp_t gfp)
 	atomic_inc(&conf->active_stripes);
 
 	raid5_release_stripe(sh);
-	conf->max_nr_stripes++;
+	WRITE_ONCE(conf->max_nr_stripes, conf->max_nr_stripes + 1);
 	return 1;
 }
 
@@ -2717,7 +2717,7 @@ static int drop_one_stripe(struct r5conf *conf)
 	shrink_buffers(sh);
 	free_stripe(conf->slab_cache, sh);
 	atomic_dec(&conf->active_stripes);
-	conf->max_nr_stripes--;
+	WRITE_ONCE(conf->max_nr_stripes, conf->max_nr_stripes - 1);
 	return 1;
 }
 
@@ -6891,7 +6891,7 @@ raid5_set_cache_size(struct mddev *mddev, int size)
 	if (size <= 16 || size > 32768)
 		return -EINVAL;
 
-	conf->min_nr_stripes = size;
+	WRITE_ONCE(conf->min_nr_stripes, size);
 	mutex_lock(&conf->cache_size_mutex);
 	while (size < conf->max_nr_stripes &&
 	       drop_one_stripe(conf))
@@ -6903,7 +6903,7 @@ raid5_set_cache_size(struct mddev *mddev, int size)
 	mutex_lock(&conf->cache_size_mutex);
 	while (size > conf->max_nr_stripes)
 		if (!grow_one_stripe(conf, GFP_KERNEL)) {
-			conf->min_nr_stripes = conf->max_nr_stripes;
+			WRITE_ONCE(conf->min_nr_stripes, conf->max_nr_stripes);
 			result = -ENOMEM;
 			break;
 		}
@@ -7468,11 +7468,13 @@ static unsigned long raid5_cache_count(struct shrinker *shrink,
 				       struct shrink_control *sc)
 {
 	struct r5conf *conf = container_of(shrink, struct r5conf, shrinker);
+	int max_stripes = READ_ONCE(conf->max_nr_stripes);
+	int min_stripes = READ_ONCE(conf->min_nr_stripes);
 
-	if (conf->max_nr_stripes < conf->min_nr_stripes)
+	if (max_stripes < min_stripes)
 		/* unlikely, but not impossible */
 		return 0;
-	return conf->max_nr_stripes - conf->min_nr_stripes;
+	return max_stripes - min_stripes;
 }
 
 static struct r5conf *setup_conf(struct mddev *mddev)