Merge v6.18.40linux-rolling-lts

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

20 files changed, 172 insertions, 140 deletions

diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index f41f649c01d4..b7cbe5874094 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -2215,7 +2215,9 @@ int dm_bufio_issue_discard(struct dm_bufio_client *c, sector_t block, sector_t c
 	struct dm_io_region io_reg = {
 		.bdev = c->bdev,
 		.sector = block_to_sector(c, block),
-		.count = block_to_sector(c, count),
+		.count = likely(c->sectors_per_block_bits >= 0) ?
+			count << c->sectors_per_block_bits :
+			count * (c->block_size >> SECTOR_SHIFT),
 	};
 
 	if (WARN_ON_ONCE(dm_bufio_in_request()))
diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c
index 9c84e9d13eca..883d1549cfc0 100644
--- a/drivers/md/dm-era-target.c
+++ b/drivers/md/dm-era-target.c
@@ -810,8 +810,10 @@ static struct era_metadata *metadata_open(struct block_device *bdev,
 	int r;
 	struct era_metadata *md = kzalloc(sizeof(*md), GFP_KERNEL);
 
-	if (!md)
-		return NULL;
+	if (!md) {
+		DMERR("could not allocate metadata struct");
+		return ERR_PTR(-ENOMEM);
+	}
 
 	md->bdev = bdev;
 	md->block_size = block_size;
@@ -1229,6 +1231,7 @@ static dm_block_t get_block(struct era *era, struct bio *bio)
 static void remap_to_origin(struct era *era, struct bio *bio)
 {
 	bio_set_dev(bio, era->origin_dev->bdev);
+	bio->bi_iter.bi_sector = dm_target_offset(era->ti, bio->bi_iter.bi_sector);
 }
 
 /*
@@ -1560,7 +1563,7 @@ static void era_dtr(struct dm_target *ti)
 static int era_map(struct dm_target *ti, struct bio *bio)
 {
 	struct era *era = ti->private;
-	dm_block_t block = get_block(era, bio);
+	dm_block_t block;
 
 	/*
 	 * All bios get remapped to the origin device.  We do this now, but
@@ -1568,6 +1571,7 @@ static int era_map(struct dm_target *ti, struct bio *bio)
 	 * block is marked in this era.
 	 */
 	remap_to_origin(era, bio);
+	block = get_block(era, bio);
 
 	/*
 	 * REQ_PREFLUSH bios carry no data, so we're not interested in them.
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index a9c0157bf42f..cd602b39481d 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -1479,9 +1479,6 @@ thorough_test:
 			*metadata_offset = 0;
 		}
 
-		if (unlikely(!is_power_of_2(ic->tag_size)))
-			hash_offset = (hash_offset + to_copy) % ic->tag_size;
-
 		total_size -= to_copy;
 	} while (unlikely(total_size));
 
@@ -2522,6 +2519,9 @@ static int dm_integrity_map_inline(struct dm_integrity_io *dio, bool from_map)
 	if (unlikely((bio->bi_opf & REQ_PREFLUSH) != 0))
 		return DM_MAPIO_REMAPPED;
 
+	if (unlikely(!dm_integrity_check_limits(ic, bio->bi_iter.bi_sector, bio)))
+		return DM_MAPIO_KILL;
+
 retry:
 	if (!dio->integrity_payload) {
 		unsigned digest_size, extra_size;
@@ -2586,10 +2586,6 @@ skip_spinlock:
 
 	dio->bio_details.bi_iter = bio->bi_iter;
 
-	if (unlikely(!dm_integrity_check_limits(ic, bio->bi_iter.bi_sector, bio))) {
-		return DM_MAPIO_KILL;
-	}
-
 	bio->bi_iter.bi_sector += ic->start + SB_SECTORS;
 
 	bip = bio_integrity_alloc(bio, GFP_NOIO, 1);
@@ -2605,7 +2601,7 @@ skip_spinlock:
 			struct bio_vec bv = bio_iter_iovec(bio, dio->bio_details.bi_iter);
 			const char *mem = integrity_kmap(ic, bv.bv_page);
 			if (ic->tag_size < ic->tuple_size)
-				memset(dio->integrity_payload + pos + ic->tag_size, 0, ic->tuple_size - ic->tuple_size);
+				memset(dio->integrity_payload + pos + ic->tag_size, 0, ic->tuple_size - ic->tag_size);
 			integrity_sector_checksum(ic, &dio->ahash_req, dio->bio_details.bi_iter.bi_sector, mem, bv.bv_offset, dio->integrity_payload + pos);
 			integrity_kunmap(ic, mem);
 			pos += ic->tuple_size;
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 128dd1a93925..f8d048ece982 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -683,7 +683,7 @@ static void list_version_get_info(struct target_type *tt, void *param)
 	struct vers_iter *info = param;
 
 	/* Check space - it might have changed since the first iteration */
-	if ((char *)info->vers + sizeof(tt->version) + strlen(tt->name) + 1 > info->end) {
+	if ((char *)info->vers + sizeof(struct dm_target_versions) + strlen(tt->name) + 1 > info->end) {
 		info->flags = DM_BUFFER_FULL_FLAG;
 		return;
 	}
@@ -2341,7 +2341,7 @@ int __init dm_early_create(struct dm_ioctl *dmi,
 	/* resume device */
 	r = dm_resume(md);
 	if (r)
-		goto err_destroy_table;
+		goto err_hash_remove;
 
 	DMINFO("%s (%s) is ready", md->disk->disk_name, dmi->name);
 	dm_put(md);
diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c
index 4a1369b8f44a..c8a1f9b6385f 100644
--- a/drivers/md/dm-log.c
+++ b/drivers/md/dm-log.c
@@ -425,6 +425,9 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
 	 */
 	bitset_size = dm_round_up(region_count, BITS_PER_LONG);
 	bitset_size >>= BYTE_SHIFT;
+	/* Handle dm_round_up rollover on 32-bit systems */
+	if (!bitset_size)
+		bitset_size = 1UL << (BITS_PER_LONG - BYTE_SHIFT);
 
 	lc->bitset_uint32_count = bitset_size / sizeof(*lc->clean_bits);
 
diff --git a/drivers/md/dm-pcache/dm_pcache.c b/drivers/md/dm-pcache/dm_pcache.c
index e5f5936fa6f0..87bcc1c515a6 100644
--- a/drivers/md/dm-pcache/dm_pcache.c
+++ b/drivers/md/dm-pcache/dm_pcache.c
@@ -168,6 +168,10 @@ static int parse_cache_opts(struct dm_pcache *pcache, struct dm_arg_set *as,
 		argc--;
 
 		if (!strcmp(arg, "cache_mode")) {
+			if (!argc) {
+				*error = "Missing value for cache_mode";
+				return -EINVAL;
+			}
 			arg = dm_shift_arg(as);
 			if (!strcmp(arg, "writeback")) {
 				opts->cache_mode = PCACHE_CACHE_MODE_WRITEBACK;
@@ -177,6 +181,10 @@ static int parse_cache_opts(struct dm_pcache *pcache, struct dm_arg_set *as,
 			}
 			argc--;
 		} else if (!strcmp(arg, "data_crc")) {
+			if (!argc) {
+				*error = "Missing value for data_crc";
+				return -EINVAL;
+			}
 			arg = dm_shift_arg(as);
 			if (!strcmp(arg, "true")) {
 				opts->data_crc = true;
diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c
index 1e5d988f44da..dbff4922e068 100644
--- a/drivers/md/dm-stats.c
+++ b/drivers/md/dm-stats.c
@@ -692,10 +692,8 @@ void dm_stats_account_io(struct dm_stats *stats, unsigned long bi_rw,
 		 */
 		last = raw_cpu_ptr(stats->last);
 		stats_aux->merged =
-			(bi_sector == (READ_ONCE(last->last_sector) &&
-				       ((bi_rw == WRITE) ==
-					(READ_ONCE(last->last_rw) == WRITE))
-				       ));
+			bi_sector == READ_ONCE(last->last_sector) &&
+				(bi_rw == WRITE) == (READ_ONCE(last->last_rw) == WRITE);
 		WRITE_ONCE(last->last_sector, end_sector);
 		WRITE_ONCE(last->last_rw, bi_rw);
 	} else
@@ -842,10 +840,10 @@ static unsigned long long dm_jiffies_to_msec64(struct dm_stat *s, unsigned long
 		result = jiffies_to_msecs(j & 0x3fffff);
 	if (j >= 1 << 22) {
 		mult = jiffies_to_msecs(1 << 22);
-		result += (unsigned long long)mult * (unsigned long long)jiffies_to_msecs((j >> 22) & 0x3fffff);
+		result += (unsigned long long)mult * ((j >> 22) & 0x3fffff);
 	}
 	if (j >= 1ULL << 44)
-		result += (unsigned long long)mult * (unsigned long long)mult * (unsigned long long)jiffies_to_msecs(j >> 44);
+		result += (unsigned long long)mult * (unsigned long long)(1 << 22) * (j >> 44);
 
 	return result;
 }
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index f90679cfec5b..9224d91fca71 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -186,6 +186,7 @@ struct dm_pool_metadata {
 	uint32_t time;
 	dm_block_t root;
 	dm_block_t details_root;
+	dm_block_t held_root;
 	struct list_head thin_devices;
 	uint64_t trans_id;
 	unsigned long flags;
@@ -748,6 +749,7 @@ static int __open_metadata(struct dm_pool_metadata *pmd)
 	 */
 	pmd->root = le64_to_cpu(disk_super->data_mapping_root);
 	pmd->details_root = le64_to_cpu(disk_super->device_details_root);
+	pmd->held_root = le64_to_cpu(disk_super->held_root);
 
 	__setup_btree_details(pmd);
 	dm_bm_unlock(sblock);
@@ -838,6 +840,7 @@ static int __begin_transaction(struct dm_pool_metadata *pmd)
 	pmd->time = le32_to_cpu(disk_super->time);
 	pmd->root = le64_to_cpu(disk_super->data_mapping_root);
 	pmd->details_root = le64_to_cpu(disk_super->device_details_root);
+	pmd->held_root = le64_to_cpu(disk_super->held_root);
 	pmd->trans_id = le64_to_cpu(disk_super->trans_id);
 	pmd->flags = le32_to_cpu(disk_super->flags);
 	pmd->data_block_size = le32_to_cpu(disk_super->data_block_size);
@@ -928,6 +931,7 @@ static int __commit_transaction(struct dm_pool_metadata *pmd)
 	disk_super->time = cpu_to_le32(pmd->time);
 	disk_super->data_mapping_root = cpu_to_le64(pmd->root);
 	disk_super->device_details_root = cpu_to_le64(pmd->details_root);
+	disk_super->held_root = cpu_to_le64(pmd->held_root);
 	disk_super->trans_id = cpu_to_le64(pmd->trans_id);
 	disk_super->flags = cpu_to_le32(pmd->flags);
 
@@ -1333,9 +1337,14 @@ static int __reserve_metadata_snap(struct dm_pool_metadata *pmd)
 {
 	int r, inc;
 	struct thin_disk_superblock *disk_super;
-	struct dm_block *copy, *sblock;
+	struct dm_block *copy;
 	dm_block_t held_root;
 
+	if (pmd->held_root) {
+		DMWARN("Pool metadata snapshot already exists: release this before taking another.");
+		return -EBUSY;
+	}
+
 	/*
 	 * We commit to ensure the btree roots which we increment in a
 	 * moment are up to date.
@@ -1353,22 +1362,16 @@ static int __reserve_metadata_snap(struct dm_pool_metadata *pmd)
 	dm_sm_inc_block(pmd->metadata_sm, THIN_SUPERBLOCK_LOCATION);
 	r = dm_tm_shadow_block(pmd->tm, THIN_SUPERBLOCK_LOCATION,
 			       &sb_validator, &copy, &inc);
-	if (r)
+	if (r) {
+		dm_sm_dec_block(pmd->metadata_sm, THIN_SUPERBLOCK_LOCATION);
 		return r;
+	}
 
 	BUG_ON(!inc);
 
 	held_root = dm_block_location(copy);
 	disk_super = dm_block_data(copy);
 
-	if (le64_to_cpu(disk_super->held_root)) {
-		DMWARN("Pool metadata snapshot already exists: release this before taking another.");
-
-		dm_tm_dec(pmd->tm, held_root);
-		dm_tm_unlock(pmd->tm, copy);
-		return -EBUSY;
-	}
-
 	/*
 	 * Wipe the spacemap since we're not publishing this.
 	 */
@@ -1384,18 +1387,8 @@ static int __reserve_metadata_snap(struct dm_pool_metadata *pmd)
 	dm_tm_inc(pmd->tm, le64_to_cpu(disk_super->device_details_root));
 	dm_tm_unlock(pmd->tm, copy);
 
-	/*
-	 * Write the held root into the superblock.
-	 */
-	r = superblock_lock(pmd, &sblock);
-	if (r) {
-		dm_tm_dec(pmd->tm, held_root);
-		return r;
-	}
+	pmd->held_root = held_root;
 
-	disk_super = dm_block_data(sblock);
-	disk_super->held_root = cpu_to_le64(held_root);
-	dm_bm_unlock(sblock);
 	return 0;
 }
 
@@ -1415,18 +1408,10 @@ static int __release_metadata_snap(struct dm_pool_metadata *pmd)
 {
 	int r;
 	struct thin_disk_superblock *disk_super;
-	struct dm_block *sblock, *copy;
+	struct dm_block *copy;
 	dm_block_t held_root;
 
-	r = superblock_lock(pmd, &sblock);
-	if (r)
-		return r;
-
-	disk_super = dm_block_data(sblock);
-	held_root = le64_to_cpu(disk_super->held_root);
-	disk_super->held_root = cpu_to_le64(0);
-
-	dm_bm_unlock(sblock);
+	held_root = pmd->held_root;
 
 	if (!held_root) {
 		DMWARN("No pool metadata snapshot found: nothing to release.");
@@ -1437,13 +1422,15 @@ static int __release_metadata_snap(struct dm_pool_metadata *pmd)
 	if (r)
 		return r;
 
+	pmd->held_root = 0;
+
 	disk_super = dm_block_data(copy);
 	dm_btree_del(&pmd->info, le64_to_cpu(disk_super->data_mapping_root));
 	dm_btree_del(&pmd->details_info, le64_to_cpu(disk_super->device_details_root));
-	dm_sm_dec_block(pmd->metadata_sm, held_root);
-
 	dm_tm_unlock(pmd->tm, copy);
 
+	dm_sm_dec_block(pmd->metadata_sm, held_root);
+
 	return 0;
 }
 
@@ -1462,19 +1449,7 @@ int dm_pool_release_metadata_snap(struct dm_pool_metadata *pmd)
 static int __get_metadata_snap(struct dm_pool_metadata *pmd,
 			       dm_block_t *result)
 {
-	int r;
-	struct thin_disk_superblock *disk_super;
-	struct dm_block *sblock;
-
-	r = dm_bm_read_lock(pmd->bm, THIN_SUPERBLOCK_LOCATION,
-			    &sb_validator, &sblock);
-	if (r)
-		return r;
-
-	disk_super = dm_block_data(sblock);
-	*result = le64_to_cpu(disk_super->held_root);
-
-	dm_bm_unlock(sblock);
+	*result = pmd->held_root;
 
 	return 0;
 }
diff --git a/drivers/md/dm-verity-loadpin.c b/drivers/md/dm-verity-loadpin.c
index 0666699b6858..9a64f575ae5f 100644
--- a/drivers/md/dm-verity-loadpin.c
+++ b/drivers/md/dm-verity-loadpin.c
@@ -70,7 +70,7 @@ bool dm_verity_loadpin_is_bdev_trusted(struct block_device *bdev)
 
 	table = dm_get_live_table(md, &srcu_idx);
 
-	if (table->num_targets != 1)
+	if (!table || table->num_targets != 1)
 		goto out;
 
 	ti = dm_table_get_target(table, 0);
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index a5cd55b2ba02..40c0664fa034 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -25,7 +25,7 @@
 
 #define DM_MSG_PREFIX			"verity"
 
-#define DM_VERITY_ENV_LENGTH		42
+#define DM_VERITY_ENV_LENGTH		46
 #define DM_VERITY_ENV_VAR_NAME		"DM_VERITY_ERR_BLOCK_NR"
 
 #define DM_VERITY_DEFAULT_PREFETCH_SIZE	262144
@@ -165,14 +165,16 @@ static int verity_handle_err(struct dm_verity *v, enum verity_block_type type,
 	char *envp[] = { verity_env, NULL };
 	const char *type_str = "";
 	struct mapped_device *md = dm_table_get_md(v->ti->table);
+	int ce;
 
 	/* Corruption should be visible in device status in all modes */
 	v->hash_failed = true;
 
-	if (v->corrupted_errs >= DM_VERITY_MAX_CORRUPTED_ERRS)
-		goto out;
-
-	v->corrupted_errs++;
+	ce = atomic_read(&v->corrupted_errs);
+	do {
+		if (ce >= DM_VERITY_MAX_CORRUPTED_ERRS)
+			goto out;
+	} while (!atomic_try_cmpxchg(&v->corrupted_errs, &ce, ce + 1));
 
 	switch (type) {
 	case DM_VERITY_BLOCK_TYPE_DATA:
@@ -188,7 +190,7 @@ static int verity_handle_err(struct dm_verity *v, enum verity_block_type type,
 	DMERR_LIMIT("%s: %s block %llu is corrupted", v->data_dev->name,
 		    type_str, block);
 
-	if (v->corrupted_errs == DM_VERITY_MAX_CORRUPTED_ERRS) {
+	if (ce + 1 == DM_VERITY_MAX_CORRUPTED_ERRS) {
 		DMERR("%s: reached maximum errors", v->data_dev->name);
 		dm_audit_log_target(DM_MSG_PREFIX, "max-corrupted-errors", v->ti, 0);
 	}
@@ -1194,6 +1196,8 @@ static int verity_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v,
 			continue;
 
 		} else if (!strcasecmp(arg_name, DM_VERITY_OPT_TASKLET_VERIFY)) {
+			if (v->use_bh_wq)
+				continue;
 			v->use_bh_wq = true;
 			static_branch_inc(&use_bh_wq_enabled);
 			continue;
diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h
index 6d141abd965c..2ed44b60042b 100644
--- a/drivers/md/dm-verity.h
+++ b/drivers/md/dm-verity.h
@@ -62,7 +62,7 @@ struct dm_verity {
 	unsigned int digest_size;	/* digest size for the current hash algorithm */
 	enum verity_mode mode;	/* mode for handling verification errors */
 	enum verity_mode error_mode;/* mode for handling I/O errors */
-	unsigned int corrupted_errs;/* Number of errors for corrupted blocks */
+	atomic_t corrupted_errs;/* Number of errors for corrupted blocks */
 
 	struct workqueue_struct *verify_wq;
 
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index 35943f5f6834..2a9584078292 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -2064,18 +2064,23 @@ static void bitmap_end_behind_write(struct mddev *mddev)
 		 bitmap->mddev->bitmap_info.max_write_behind);
 }
 
-static void bitmap_wait_behind_writes(struct mddev *mddev)
+static bool bitmap_wait_behind_writes(struct mddev *mddev, bool nowait)
 {
 	struct bitmap *bitmap = mddev->bitmap;
 
 	/* wait for behind writes to complete */
 	if (bitmap && atomic_read(&bitmap->behind_writes) > 0) {
+		if (nowait)
+			return false;
+
 		pr_debug("md:%s: behind writes in progress - waiting to stop.\n",
 			 mdname(mddev));
 		/* need to kick something here to make sure I/O goes? */
 		wait_event(bitmap->behind_wait,
 			   atomic_read(&bitmap->behind_writes) == 0);
 	}
+
+	return true;
 }
 
 static void bitmap_destroy(struct mddev *mddev)
@@ -2085,8 +2090,8 @@ static void bitmap_destroy(struct mddev *mddev)
 	if (!bitmap) /* there was no bitmap */
 		return;
 
-	bitmap_wait_behind_writes(mddev);
-	if (!mddev->serialize_policy)
+	bitmap_wait_behind_writes(mddev, false);
+	if (!test_bit(MD_SERIALIZE_POLICY, &mddev->flags))
 		mddev_destroy_serial_pool(mddev, NULL);
 
 	mutex_lock(&mddev->bitmap_info.mutex);
@@ -2864,7 +2869,7 @@ backlog_store(struct mddev *mddev, const char *buf, size_t len)
 	mddev->bitmap_info.max_write_behind = backlog;
 	if (!backlog && mddev->serial_info_pool) {
 		/* serial_info_pool is not needed if backlog is zero */
-		if (!mddev->serialize_policy)
+		if (!test_bit(MD_SERIALIZE_POLICY, &mddev->flags))
 			mddev_destroy_serial_pool(mddev, NULL);
 	} else if (backlog && !mddev->serial_info_pool) {
 		/* serial_info_pool is needed since backlog is not zero */
diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h
index 214f623c7e79..f46674bdfeb9 100644
--- a/drivers/md/md-bitmap.h
+++ b/drivers/md/md-bitmap.h
@@ -98,7 +98,7 @@ struct bitmap_operations {
 
 	void (*start_behind_write)(struct mddev *mddev);
 	void (*end_behind_write)(struct mddev *mddev);
-	void (*wait_behind_writes)(struct mddev *mddev);
+	bool (*wait_behind_writes)(struct mddev *mddev, bool nowait);
 
 	md_bitmap_fn *start_write;
 	md_bitmap_fn *end_write;
diff --git a/drivers/md/md-llbitmap.c b/drivers/md/md-llbitmap.c
index 50eeddf7f539..dc9b72494a81 100644
--- a/drivers/md/md-llbitmap.c
+++ b/drivers/md/md-llbitmap.c
@@ -1432,16 +1432,19 @@ static void llbitmap_end_behind_write(struct mddev *mddev)
 		wake_up(&llbitmap->behind_wait);
 }
 
-static void llbitmap_wait_behind_writes(struct mddev *mddev)
+static bool llbitmap_wait_behind_writes(struct mddev *mddev, bool nowait)
 {
 	struct llbitmap *llbitmap = mddev->bitmap;
 
-	if (!llbitmap)
-		return;
+	if (llbitmap && atomic_read(&llbitmap->behind_writes) > 0) {
+		if (nowait)
+			return false;
 
-	wait_event(llbitmap->behind_wait,
-		   atomic_read(&llbitmap->behind_writes) == 0);
+		wait_event(llbitmap->behind_wait,
+			   atomic_read(&llbitmap->behind_writes) == 0);
+	}
 
+	return true;
 }
 
 static ssize_t bits_show(struct mddev *mddev, char *page)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index b7d47c018a12..0d60c211e7c0 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -278,7 +278,8 @@ void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev)
 
 		rdev_for_each(temp, mddev) {
 			if (!rdev) {
-				if (!mddev->serialize_policy ||
+				if (!test_bit(MD_SERIALIZE_POLICY,
+					      &mddev->flags) ||
 				    !rdev_need_serial(temp))
 					rdev_uninit_serial(temp);
 				else
@@ -5868,11 +5869,11 @@ __ATTR(consistency_policy, S_IRUGO | S_IWUSR, consistency_policy_show,
 
 static ssize_t fail_last_dev_show(struct mddev *mddev, char *page)
 {
-	return sprintf(page, "%d\n", mddev->fail_last_dev);
+	return sprintf(page, "%d\n", test_bit(MD_FAILLAST_DEV, &mddev->flags));
 }
 
 /*
- * Setting fail_last_dev to true to allow last device to be forcibly removed
+ * Setting MD_FAILLAST_DEV to allow last device to be forcibly removed
  * from RAID1/RAID10.
  */
 static ssize_t
@@ -5885,8 +5886,10 @@ fail_last_dev_store(struct mddev *mddev, const char *buf, size_t len)
 	if (ret)
 		return ret;
 
-	if (value != mddev->fail_last_dev)
-		mddev->fail_last_dev = value;
+	if (value)
+		set_bit(MD_FAILLAST_DEV, &mddev->flags);
+	else
+		clear_bit(MD_FAILLAST_DEV, &mddev->flags);
 
 	return len;
 }
@@ -5899,11 +5902,12 @@ static ssize_t serialize_policy_show(struct mddev *mddev, char *page)
 	if (mddev->pers == NULL || (mddev->pers->head.id != ID_RAID1))
 		return sprintf(page, "n/a\n");
 	else
-		return sprintf(page, "%d\n", mddev->serialize_policy);
+		return sprintf(page, "%d\n",
+			       test_bit(MD_SERIALIZE_POLICY, &mddev->flags));
 }
 
 /*
- * Setting serialize_policy to true to enforce write IO is not reordered
+ * Setting MD_SERIALIZE_POLICY enforce write IO is not reordered
  * for raid1.
  */
 static ssize_t
@@ -5916,7 +5920,7 @@ serialize_policy_store(struct mddev *mddev, const char *buf, size_t len)
 	if (err)
 		return err;
 
-	if (value == mddev->serialize_policy)
+	if (value == test_bit(MD_SERIALIZE_POLICY, &mddev->flags))
 		return len;
 
 	err = mddev_suspend_and_lock(mddev);
@@ -5928,11 +5932,13 @@ serialize_policy_store(struct mddev *mddev, const char *buf, size_t len)
 		goto unlock;
 	}
 
-	if (value)
+	if (value) {
 		mddev_create_serial_pool(mddev, NULL);
-	else
+		set_bit(MD_SERIALIZE_POLICY, &mddev->flags);
+	} else {
 		mddev_destroy_serial_pool(mddev, NULL);
-	mddev->serialize_policy = value;
+		clear_bit(MD_SERIALIZE_POLICY, &mddev->flags);
+	}
 unlock:
 	mddev_unlock_and_resume(mddev);
 	return err ?: len;
@@ -6537,7 +6543,7 @@ int md_run(struct mddev *mddev)
 	 * the only valid external interface is through the md
 	 * device.
 	 */
-	mddev->has_superblocks = false;
+	clear_bit(MD_HAS_SUPERBLOCK, &mddev->flags);
 	rdev_for_each(rdev, mddev) {
 		if (test_bit(Faulty, &rdev->flags))
 			continue;
@@ -6550,7 +6556,7 @@ int md_run(struct mddev *mddev)
 		}
 
 		if (rdev->sb_page)
-			mddev->has_superblocks = true;
+			set_bit(MD_HAS_SUPERBLOCK, &mddev->flags);
 
 		/* perform some consistency tests on the device.
 		 * We don't want the data to overlap the metadata,
@@ -6905,7 +6911,7 @@ static void __md_stop_writes(struct mddev *mddev)
 		md_update_sb(mddev, 1);
 	}
 	/* disable policy to guarantee rdevs free resources for serialization */
-	mddev->serialize_policy = 0;
+	clear_bit(MD_SERIALIZE_POLICY, &mddev->flags);
 	mddev_destroy_serial_pool(mddev, NULL);
 }
 
@@ -6922,7 +6928,7 @@ EXPORT_SYMBOL_GPL(md_stop_writes);
 static void mddev_detach(struct mddev *mddev)
 {
 	if (md_bitmap_enabled(mddev, false))
-		mddev->bitmap_ops->wait_behind_writes(mddev);
+		mddev->bitmap_ops->wait_behind_writes(mddev, false);
 	if (mddev->pers && mddev->pers->quiesce && !is_md_suspended(mddev)) {
 		mddev->pers->quiesce(mddev, 1);
 		mddev->pers->quiesce(mddev, 0);
@@ -9173,7 +9179,7 @@ void md_write_start(struct mddev *mddev, struct bio *bi)
 	rcu_read_unlock();
 	if (did_change)
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
-	if (!mddev->has_superblocks)
+	if (!test_bit(MD_HAS_SUPERBLOCK, &mddev->flags))
 		return;
 	wait_event(mddev->sb_wait,
 		   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
diff --git a/drivers/md/md.h b/drivers/md/md.h
index da312d469285..2960a9874760 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -340,6 +340,9 @@ struct md_cluster_operations;
  *		   array is ready yet.
  * @MD_BROKEN: This is used to stop writes and mark array as failed.
  * @MD_DELETED: This device is being deleted
+ * @MD_HAS_SUPERBLOCK: There is persistence sb in member disks.
+ * @MD_FAILLAST_DEV: Allow last rdev to be removed.
+ * @MD_SERIALIZE_POLICY: Enforce write IO is not reordered, just used by raid1.
  *
  * change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added
  */
@@ -356,6 +359,9 @@ enum mddev_flags {
 	MD_BROKEN,
 	MD_DO_DELETE,
 	MD_DELETED,
+	MD_HAS_SUPERBLOCK,
+	MD_FAILLAST_DEV,
+	MD_SERIALIZE_POLICY,
 };
 
 enum mddev_sb_flags {
@@ -621,10 +627,6 @@ struct mddev {
 
 	/* The sequence number for sync thread */
 	atomic_t sync_seq;
-
-	bool	has_superblocks:1;
-	bool	fail_last_dev:1;
-	bool	serialize_policy:1;
 };
 
 enum recovery_flags {
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index e443e478645a..0bdba5944af9 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -27,7 +27,9 @@ module_param(default_layout, int, 0644);
 	 (1L << MD_JOURNAL_CLEAN) |	\
 	 (1L << MD_FAILFAST_SUPPORTED) |\
 	 (1L << MD_HAS_PPL) |		\
-	 (1L << MD_HAS_MULTIPLE_PPLS))
+	 (1L << MD_HAS_MULTIPLE_PPLS) |	\
+	 (1L << MD_FAILLAST_DEV) |	\
+	 (1L << MD_SERIALIZE_POLICY))
 
 /*
  * inform the user of the raid configuration
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 84dbf801e9b1..16625b79788b 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -542,7 +542,7 @@ static void raid1_end_write_request(struct bio *bio)
 				call_bio_endio(r1_bio);
 			}
 		}
-	} else if (rdev->mddev->serialize_policy)
+	} else if (test_bit(MD_SERIALIZE_POLICY, &rdev->mddev->flags))
 		remove_serial(rdev, lo, hi);
 	if (r1_bio->bios[mirror] == NULL)
 		rdev_dec_pending(rdev, conf->mddev);
@@ -1319,6 +1319,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	int max_sectors;
 	int rdisk;
 	bool r1bio_existed = !!r1_bio;
+	bool nowait = bio->bi_opf & REQ_NOWAIT;
 
 	/*
 	 * If r1_bio is set, we are blocking the raid1d thread
@@ -1331,9 +1332,14 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	 * Still need barrier for READ in case that whole
 	 * array is frozen.
 	 */
-	if (!wait_read_barrier(conf, bio->bi_iter.bi_sector,
-				bio->bi_opf & REQ_NOWAIT)) {
+	if (!wait_read_barrier(conf, bio->bi_iter.bi_sector, nowait)) {
 		bio_wouldblock_error(bio);
+
+		if (r1bio_existed) {
+			set_bit(R1BIO_Returned, &r1_bio->state);
+			raid_end_bio_io(r1_bio);
+		}
+
 		return;
 	}
 
@@ -1373,7 +1379,11 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 		 * over-take any writes that are 'behind'
 		 */
 		mddev_add_trace_msg(mddev, "raid1 wait behind writes");
-		mddev->bitmap_ops->wait_behind_writes(mddev);
+		if (!mddev->bitmap_ops->wait_behind_writes(mddev, nowait)) {
+			bio_wouldblock_error(bio);
+			set_bit(R1BIO_Returned, &r1_bio->state);
+			goto err_handle;
+		}
 	}
 
 	if (max_sectors < bio_sectors(bio)) {
@@ -1581,8 +1591,10 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 				 * complexity of supporting that is not worth
 				 * the benefit.
 				 */
-				if (bio->bi_opf & REQ_ATOMIC)
+				if (bio->bi_opf & REQ_ATOMIC) {
+					rdev_dec_pending(rdev, mddev);
 					goto err_handle;
+				}
 
 				good_sectors = first_bad - r1_bio->sector;
 				if (good_sectors < max_sectors)
@@ -1644,7 +1656,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 			mbio = bio_alloc_clone(rdev->bdev, bio, GFP_NOIO,
 					       &mddev->bio_set);
 
-			if (mddev->serialize_policy)
+			if (test_bit(MD_SERIALIZE_POLICY, &mddev->flags))
 				wait_for_serialization(rdev, r1_bio);
 		}
 
@@ -1746,7 +1758,7 @@ static void raid1_status(struct seq_file *seq, struct mddev *mddev)
  *	- &mddev->degraded is bumped.
  *
  * @rdev is marked as &Faulty excluding case when array is failed and
- * &mddev->fail_last_dev is off.
+ * MD_FAILLAST_DEV is not set.
  */
 static void raid1_error(struct mddev *mddev, struct md_rdev *rdev)
 {
@@ -1759,7 +1771,7 @@ static void raid1_error(struct mddev *mddev, struct md_rdev *rdev)
 	    (conf->raid_disks - mddev->degraded) == 1) {
 		set_bit(MD_BROKEN, &mddev->flags);
 
-		if (!mddev->fail_last_dev) {
+		if (!test_bit(MD_FAILLAST_DEV, &mddev->flags)) {
 			conf->recovery_disabled = mddev->recovery_disabled;
 			spin_unlock_irqrestore(&conf->device_lock, flags);
 			return;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 2815c05d1c9f..d6b174454b1a 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1727,6 +1727,7 @@ retry_discard:
 	r10_bio->mddev = mddev;
 	r10_bio->state = 0;
 	r10_bio->sectors = 0;
+	r10_bio->read_slot = -1;
 	memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * geo->raid_disks);
 	wait_blocked_dev(mddev, r10_bio);
 
@@ -1990,7 +1991,7 @@ static int enough(struct r10conf *conf, int ignore)
  *	- &mddev->degraded is bumped.
  *
  * @rdev is marked as &Faulty excluding case when array is failed and
- * &mddev->fail_last_dev is off.
+ * MD_FAILLAST_DEV is not set.
  */
 static void raid10_error(struct mddev *mddev, struct md_rdev *rdev)
 {
@@ -2002,7 +2003,7 @@ static void raid10_error(struct mddev *mddev, struct md_rdev *rdev)
 	if (test_bit(In_sync, &rdev->flags) && !enough(conf, rdev->raid_disk)) {
 		set_bit(MD_BROKEN, &mddev->flags);
 
-		if (!mddev->fail_last_dev) {
+		if (!test_bit(MD_FAILLAST_DEV, &mddev->flags)) {
 			spin_unlock_irqrestore(&conf->device_lock, flags);
 			return;
 		}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index b9f0d01ce01c..b19d870e4171 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -56,7 +56,11 @@
 #include "md-bitmap.h"
 #include "raid5-log.h"
 
-#define UNSUPPORTED_MDDEV_FLAGS	(1L << MD_FAILFAST_SUPPORTED)
+#define UNSUPPORTED_MDDEV_FLAGS		\
+	((1L << MD_FAILFAST_SUPPORTED) |	\
+	 (1L << MD_FAILLAST_DEV) |		\
+	 (1L << MD_SERIALIZE_POLICY))
+
 
 #define cpu_to_group(cpu) cpu_to_node(cpu)
 #define ANY_GROUP NUMA_NO_NODE
@@ -4849,55 +4853,62 @@ static void break_stripe_batch_list(struct stripe_head *head_sh,
 {
 	struct stripe_head *sh, *next;
 	int i;
+	unsigned long state;
 
 	list_for_each_entry_safe(sh, next, &head_sh->batch_list, batch_list) {
 
 		list_del_init(&sh->batch_list);
 
-		WARN_ONCE(sh->state & ((1 << STRIPE_ACTIVE) |
-					  (1 << STRIPE_SYNCING) |
-					  (1 << STRIPE_REPLACED) |
-					  (1 << STRIPE_DELAYED) |
-					  (1 << STRIPE_BIT_DELAY) |
-					  (1 << STRIPE_FULL_WRITE) |
-					  (1 << STRIPE_BIOFILL_RUN) |
-					  (1 << STRIPE_COMPUTE_RUN)  |
-					  (1 << STRIPE_DISCARD) |
-					  (1 << STRIPE_BATCH_READY) |
-					  (1 << STRIPE_BATCH_ERR)),
-			"stripe state: %lx\n", sh->state);
-		WARN_ONCE(head_sh->state & ((1 << STRIPE_DISCARD) |
-					      (1 << STRIPE_REPLACED)),
-			"head stripe state: %lx\n", head_sh->state);
+		state = READ_ONCE(sh->state);
+		WARN_ONCE(state & ((1 << STRIPE_ACTIVE) |
+				   (1 << STRIPE_SYNCING) |
+				   (1 << STRIPE_REPLACED) |
+				   (1 << STRIPE_DELAYED) |
+				   (1 << STRIPE_BIT_DELAY) |
+				   (1 << STRIPE_FULL_WRITE) |
+				   (1 << STRIPE_BIOFILL_RUN) |
+				   (1 << STRIPE_COMPUTE_RUN)  |
+				   (1 << STRIPE_DISCARD) |
+				   (1 << STRIPE_BATCH_READY) |
+				   (1 << STRIPE_BATCH_ERR)),
+			"stripe state: %lx\n", state);
+
+		state = READ_ONCE(head_sh->state);
+		WARN_ONCE(state & ((1 << STRIPE_DISCARD) |
+				   (1 << STRIPE_REPLACED)),
+			"head stripe state: %lx\n", state);
 
 		set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS |
 					    (1 << STRIPE_PREREAD_ACTIVE) |
 					    (1 << STRIPE_ON_UNPLUG_LIST)),
-			      head_sh->state & (1 << STRIPE_INSYNC));
+			      state & (1 << STRIPE_INSYNC));
 
 		sh->check_state = head_sh->check_state;
 		sh->reconstruct_state = head_sh->reconstruct_state;
 		spin_lock_irq(&sh->stripe_lock);
-		sh->batch_head = NULL;
-		spin_unlock_irq(&sh->stripe_lock);
 		for (i = 0; i < sh->disks; i++) {
 			if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
 				wake_up_bit(&sh->dev[i].flags, R5_Overlap);
-			sh->dev[i].flags = head_sh->dev[i].flags &
+			sh->dev[i].flags = READ_ONCE(head_sh->dev[i].flags) &
 				(~((1 << R5_WriteError) | (1 << R5_Overlap)));
 		}
-		if (handle_flags == 0 ||
-		    sh->state & handle_flags)
+		sh->batch_head = NULL;
+		spin_unlock_irq(&sh->stripe_lock);
+
+		state = READ_ONCE(sh->state);
+		if (handle_flags == 0 || (state & handle_flags))
 			set_bit(STRIPE_HANDLE, &sh->state);
 		raid5_release_stripe(sh);
 	}
 	spin_lock_irq(&head_sh->stripe_lock);
-	head_sh->batch_head = NULL;
-	spin_unlock_irq(&head_sh->stripe_lock);
 	for (i = 0; i < head_sh->disks; i++)
 		if (test_and_clear_bit(R5_Overlap, &head_sh->dev[i].flags))
 			wake_up_bit(&head_sh->dev[i].flags, R5_Overlap);
-	if (head_sh->state & handle_flags)
+	head_sh->batch_head = NULL;
+	spin_unlock_irq(&head_sh->stripe_lock);
+
+	state = READ_ONCE(head_sh->state);
+	if (state & handle_flags)
 		set_bit(STRIPE_HANDLE, &head_sh->state);
 }