Merge tag 'dm-4.10-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper updates from Mike Snitzer:

 - various fixes and improvements to request-based DM and DM multipath

 - some locking improvements in DM bufio

 - add Kconfig option to disable the DM block manager's extra locking
   which mainly serves as a developer tool

 - a few bug fixes to DM's persistent-data

 - a couple changes to prepare for multipage biovec support in the block
   layer

 - various improvements and cleanups in the DM core, DM cache, DM raid
   and DM crypt

 - add ability to have DM crypt use keys from the kernel key retention
   service

 - add a new "error_writes" feature to the DM flakey target, reads are
   left unchanged in this mode

* tag 'dm-4.10-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (40 commits)
  dm flakey: introduce "error_writes" feature
  dm cache policy smq: use hash_32() instead of hash_32_generic()
  dm crypt: reject key strings containing whitespace chars
  dm space map: always set ev if sm_ll_mutate() succeeds
  dm space map metadata: skip useless memcpy in metadata_ll_init_index()
  dm space map metadata: fix 'struct sm_metadata' leak on failed create
  Documentation: dm raid: define data_offset status field
  dm raid: fix discard support regression
  dm raid: don't allow "write behind" with raid4/5/6
  dm mpath: use hw_handler_params if attached hw_handler is same as requested
  dm crypt: add ability to use keys from the kernel key retention service
  dm array: remove a dead assignment in populate_ablock_with_values()
  dm ioctl: use offsetof() instead of open-coding it
  dm rq: simplify use_blk_mq initialization
  dm: use blk_set_queue_dying() in __dm_destroy()
  dm bufio: drop the lock when doing GFP_NOIO allocation
  dm bufio: don't take the lock in dm_bufio_shrink_count
  dm bufio: avoid sleeping while holding the dm_bufio lock
  dm table: simplify dm_table_determine_type()
  dm table: an 'all_blk_mq' table must be loaded for a blk-mq DM device
  ...

19 files changed, 406 insertions, 173 deletions

diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 02a5345a44a6..b7767da50c26 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -240,9 +240,17 @@ config DM_BUFIO
 	 as a cache, holding recently-read blocks in memory and performing
 	 delayed writes.
 
+config DM_DEBUG_BLOCK_MANAGER_LOCKING
+       bool "Block manager locking"
+       depends on DM_BUFIO
+       ---help---
+	 Block manager locking can catch various metadata corruption issues.
+
+	 If unsure, say N.
+
 config DM_DEBUG_BLOCK_STACK_TRACING
        bool "Keep stack trace of persistent data block lock holders"
-       depends on STACKTRACE_SUPPORT && DM_BUFIO
+       depends on STACKTRACE_SUPPORT && DM_DEBUG_BLOCK_MANAGER_LOCKING
        select STACKTRACE
        ---help---
 	 Enable this for messages that may help debug problems with the
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 262e75365cc0..84d2f0e4c754 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -820,12 +820,14 @@ enum new_flag {
 static struct dm_buffer *__alloc_buffer_wait_no_callback(struct dm_bufio_client *c, enum new_flag nf)
 {
 	struct dm_buffer *b;
+	bool tried_noio_alloc = false;
 
 	/*
 	 * dm-bufio is resistant to allocation failures (it just keeps
 	 * one buffer reserved in cases all the allocations fail).
 	 * So set flags to not try too hard:
-	 *	GFP_NOIO: don't recurse into the I/O layer
+	 *	GFP_NOWAIT: don't wait; if we need to sleep we'll release our
+	 *		    mutex and wait ourselves.
 	 *	__GFP_NORETRY: don't retry and rather return failure
 	 *	__GFP_NOMEMALLOC: don't use emergency reserves
 	 *	__GFP_NOWARN: don't print a warning in case of failure
@@ -835,7 +837,7 @@ static struct dm_buffer *__alloc_buffer_wait_no_callback(struct dm_bufio_client
 	 */
 	while (1) {
 		if (dm_bufio_cache_size_latch != 1) {
-			b = alloc_buffer(c, GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
+			b = alloc_buffer(c, GFP_NOWAIT | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
 			if (b)
 				return b;
 		}
@@ -843,6 +845,15 @@ static struct dm_buffer *__alloc_buffer_wait_no_callback(struct dm_bufio_client
 		if (nf == NF_PREFETCH)
 			return NULL;
 
+		if (dm_bufio_cache_size_latch != 1 && !tried_noio_alloc) {
+			dm_bufio_unlock(c);
+			b = alloc_buffer(c, GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
+			dm_bufio_lock(c);
+			if (b)
+				return b;
+			tried_noio_alloc = true;
+		}
+
 		if (!list_empty(&c->reserved_buffers)) {
 			b = list_entry(c->reserved_buffers.next,
 				       struct dm_buffer, lru_list);
@@ -1585,18 +1596,9 @@ dm_bufio_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 static unsigned long
 dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
 {
-	struct dm_bufio_client *c;
-	unsigned long count;
-
-	c = container_of(shrink, struct dm_bufio_client, shrinker);
-	if (sc->gfp_mask & __GFP_FS)
-		dm_bufio_lock(c);
-	else if (!dm_bufio_trylock(c))
-		return 0;
+	struct dm_bufio_client *c = container_of(shrink, struct dm_bufio_client, shrinker);
 
-	count = c->n_buffers[LIST_CLEAN] + c->n_buffers[LIST_DIRTY];
-	dm_bufio_unlock(c);
-	return count;
+	return ACCESS_ONCE(c->n_buffers[LIST_CLEAN]) + ACCESS_ONCE(c->n_buffers[LIST_DIRTY]);
 }
 
 /*
diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index 695577812cf6..624fe4319b24 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -383,7 +383,6 @@ static int __format_metadata(struct dm_cache_metadata *cmd)
 		goto bad;
 
 	dm_disk_bitset_init(cmd->tm, &cmd->discard_info);
-
 	r = dm_bitset_empty(&cmd->discard_info, &cmd->discard_root);
 	if (r < 0)
 		goto bad;
@@ -789,7 +788,7 @@ static struct dm_cache_metadata *lookup_or_open(struct block_device *bdev,
 static bool same_params(struct dm_cache_metadata *cmd, sector_t data_block_size)
 {
 	if (cmd->data_block_size != data_block_size) {
-		DMERR("data_block_size (%llu) different from that in metadata (%llu)\n",
+		DMERR("data_block_size (%llu) different from that in metadata (%llu)",
 		      (unsigned long long) data_block_size,
 		      (unsigned long long) cmd->data_block_size);
 		return false;
diff --git a/drivers/md/dm-cache-policy-smq.c b/drivers/md/dm-cache-policy-smq.c
index c33f4a6e1d7d..f19c6930a67c 100644
--- a/drivers/md/dm-cache-policy-smq.c
+++ b/drivers/md/dm-cache-policy-smq.c
@@ -1361,7 +1361,7 @@ static void smq_clear_dirty(struct dm_cache_policy *p, dm_oblock_t oblock)
 
 static unsigned random_level(dm_cblock_t cblock)
 {
-	return hash_32_generic(from_cblock(cblock), 9) & (NR_CACHE_LEVELS - 1);
+	return hash_32(from_cblock(cblock), 9) & (NR_CACHE_LEVELS - 1);
 }
 
 static int smq_load_mapping(struct dm_cache_policy *p,
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 59b2c50562e4..e04c61e0839e 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -989,7 +989,8 @@ static void set_cache_mode(struct cache *cache, enum cache_metadata_mode new_mod
 	enum cache_metadata_mode old_mode = get_cache_mode(cache);
 
 	if (dm_cache_metadata_needs_check(cache->cmd, &needs_check)) {
-		DMERR("unable to read needs_check flag, setting failure mode");
+		DMERR("%s: unable to read needs_check flag, setting failure mode.",
+		      cache_device_name(cache));
 		new_mode = CM_FAIL;
 	}
 
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 68a9eb4f3f36..7c6c57216bf2 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/key.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
 #include <linux/mempool.h>
@@ -23,12 +24,14 @@
 #include <linux/atomic.h>
 #include <linux/scatterlist.h>
 #include <linux/rbtree.h>
+#include <linux/ctype.h>
 #include <asm/page.h>
 #include <asm/unaligned.h>
 #include <crypto/hash.h>
 #include <crypto/md5.h>
 #include <crypto/algapi.h>
 #include <crypto/skcipher.h>
+#include <keys/user-type.h>
 
 #include <linux/device-mapper.h>
 
@@ -140,8 +143,9 @@ struct crypt_config {
 
 	char *cipher;
 	char *cipher_string;
+	char *key_string;
 
-	struct crypt_iv_operations *iv_gen_ops;
+	const struct crypt_iv_operations *iv_gen_ops;
 	union {
 		struct iv_essiv_private essiv;
 		struct iv_benbi_private benbi;
@@ -758,15 +762,15 @@ static int crypt_iv_tcw_post(struct crypt_config *cc, u8 *iv,
 	return r;
 }
 
-static struct crypt_iv_operations crypt_iv_plain_ops = {
+static const struct crypt_iv_operations crypt_iv_plain_ops = {
 	.generator = crypt_iv_plain_gen
 };
 
-static struct crypt_iv_operations crypt_iv_plain64_ops = {
+static const struct crypt_iv_operations crypt_iv_plain64_ops = {
 	.generator = crypt_iv_plain64_gen
 };
 
-static struct crypt_iv_operations crypt_iv_essiv_ops = {
+static const struct crypt_iv_operations crypt_iv_essiv_ops = {
 	.ctr       = crypt_iv_essiv_ctr,
 	.dtr       = crypt_iv_essiv_dtr,
 	.init      = crypt_iv_essiv_init,
@@ -774,17 +778,17 @@ static struct crypt_iv_operations crypt_iv_essiv_ops = {
 	.generator = crypt_iv_essiv_gen
 };
 
-static struct crypt_iv_operations crypt_iv_benbi_ops = {
+static const struct crypt_iv_operations crypt_iv_benbi_ops = {
 	.ctr	   = crypt_iv_benbi_ctr,
 	.dtr	   = crypt_iv_benbi_dtr,
 	.generator = crypt_iv_benbi_gen
 };
 
-static struct crypt_iv_operations crypt_iv_null_ops = {
+static const struct crypt_iv_operations crypt_iv_null_ops = {
 	.generator = crypt_iv_null_gen
 };
 
-static struct crypt_iv_operations crypt_iv_lmk_ops = {
+static const struct crypt_iv_operations crypt_iv_lmk_ops = {
 	.ctr	   = crypt_iv_lmk_ctr,
 	.dtr	   = crypt_iv_lmk_dtr,
 	.init	   = crypt_iv_lmk_init,
@@ -793,7 +797,7 @@ static struct crypt_iv_operations crypt_iv_lmk_ops = {
 	.post	   = crypt_iv_lmk_post
 };
 
-static struct crypt_iv_operations crypt_iv_tcw_ops = {
+static const struct crypt_iv_operations crypt_iv_tcw_ops = {
 	.ctr	   = crypt_iv_tcw_ctr,
 	.dtr	   = crypt_iv_tcw_dtr,
 	.init	   = crypt_iv_tcw_init,
@@ -994,7 +998,6 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size)
 	gfp_t gfp_mask = GFP_NOWAIT | __GFP_HIGHMEM;
 	unsigned i, len, remaining_size;
 	struct page *page;
-	struct bio_vec *bvec;
 
 retry:
 	if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM))
@@ -1019,12 +1022,7 @@ retry:
 
 		len = (remaining_size > PAGE_SIZE) ? PAGE_SIZE : remaining_size;
 
-		bvec = &clone->bi_io_vec[clone->bi_vcnt++];
-		bvec->bv_page = page;
-		bvec->bv_len = len;
-		bvec->bv_offset = 0;
-
-		clone->bi_iter.bi_size += len;
+		bio_add_page(clone, page, len, 0);
 
 		remaining_size -= len;
 	}
@@ -1471,7 +1469,7 @@ static int crypt_alloc_tfms(struct crypt_config *cc, char *ciphermode)
 	return 0;
 }
 
-static int crypt_setkey_allcpus(struct crypt_config *cc)
+static int crypt_setkey(struct crypt_config *cc)
 {
 	unsigned subkey_size;
 	int err = 0, i, r;
@@ -1490,25 +1488,157 @@ static int crypt_setkey_allcpus(struct crypt_config *cc)
 	return err;
 }
 
+#ifdef CONFIG_KEYS
+
+static bool contains_whitespace(const char *str)
+{
+	while (*str)
+		if (isspace(*str++))
+			return true;
+	return false;
+}
+
+static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string)
+{
+	char *new_key_string, *key_desc;
+	int ret;
+	struct key *key;
+	const struct user_key_payload *ukp;
+
+	/*
+	 * Reject key_string with whitespace. dm core currently lacks code for
+	 * proper whitespace escaping in arguments on DM_TABLE_STATUS path.
+	 */
+	if (contains_whitespace(key_string)) {
+		DMERR("whitespace chars not allowed in key string");
+		return -EINVAL;
+	}
+
+	/* look for next ':' separating key_type from key_description */
+	key_desc = strpbrk(key_string, ":");
+	if (!key_desc || key_desc == key_string || !strlen(key_desc + 1))
+		return -EINVAL;
+
+	if (strncmp(key_string, "logon:", key_desc - key_string + 1) &&
+	    strncmp(key_string, "user:", key_desc - key_string + 1))
+		return -EINVAL;
+
+	new_key_string = kstrdup(key_string, GFP_KERNEL);
+	if (!new_key_string)
+		return -ENOMEM;
+
+	key = request_key(key_string[0] == 'l' ? &key_type_logon : &key_type_user,
+			  key_desc + 1, NULL);
+	if (IS_ERR(key)) {
+		kzfree(new_key_string);
+		return PTR_ERR(key);
+	}
+
+	rcu_read_lock();
+
+	ukp = user_key_payload(key);
+	if (!ukp) {
+		rcu_read_unlock();
+		key_put(key);
+		kzfree(new_key_string);
+		return -EKEYREVOKED;
+	}
+
+	if (cc->key_size != ukp->datalen) {
+		rcu_read_unlock();
+		key_put(key);
+		kzfree(new_key_string);
+		return -EINVAL;
+	}
+
+	memcpy(cc->key, ukp->data, cc->key_size);
+
+	rcu_read_unlock();
+	key_put(key);
+
+	/* clear the flag since following operations may invalidate previously valid key */
+	clear_bit(DM_CRYPT_KEY_VALID, &cc->flags);
+
+	ret = crypt_setkey(cc);
+
+	/* wipe the kernel key payload copy in each case */
+	memset(cc->key, 0, cc->key_size * sizeof(u8));
+
+	if (!ret) {
+		set_bit(DM_CRYPT_KEY_VALID, &cc->flags);
+		kzfree(cc->key_string);
+		cc->key_string = new_key_string;
+	} else
+		kzfree(new_key_string);
+
+	return ret;
+}
+
+static int get_key_size(char **key_string)
+{
+	char *colon, dummy;
+	int ret;
+
+	if (*key_string[0] != ':')
+		return strlen(*key_string) >> 1;
+
+	/* look for next ':' in key string */
+	colon = strpbrk(*key_string + 1, ":");
+	if (!colon)
+		return -EINVAL;
+
+	if (sscanf(*key_string + 1, "%u%c", &ret, &dummy) != 2 || dummy != ':')
+		return -EINVAL;
+
+	*key_string = colon;
+
+	/* remaining key string should be :<logon|user>:<key_desc> */
+
+	return ret;
+}
+
+#else
+
+static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string)
+{
+	return -EINVAL;
+}
+
+static int get_key_size(char **key_string)
+{
+	return (*key_string[0] == ':') ? -EINVAL : strlen(*key_string) >> 1;
+}
+
+#endif
+
 static int crypt_set_key(struct crypt_config *cc, char *key)
 {
 	int r = -EINVAL;
 	int key_string_len = strlen(key);
 
-	/* The key size may not be changed. */
-	if (cc->key_size != (key_string_len >> 1))
-		goto out;
-
 	/* Hyphen (which gives a key_size of zero) means there is no key. */
 	if (!cc->key_size && strcmp(key, "-"))
 		goto out;
 
-	if (cc->key_size && crypt_decode_key(cc->key, key, cc->key_size) < 0)
+	/* ':' means the key is in kernel keyring, short-circuit normal key processing */
+	if (key[0] == ':') {
+		r = crypt_set_keyring_key(cc, key + 1);
 		goto out;
+	}
 
-	set_bit(DM_CRYPT_KEY_VALID, &cc->flags);
+	/* clear the flag since following operations may invalidate previously valid key */
+	clear_bit(DM_CRYPT_KEY_VALID, &cc->flags);
 
-	r = crypt_setkey_allcpus(cc);
+	/* wipe references to any kernel keyring key */
+	kzfree(cc->key_string);
+	cc->key_string = NULL;
+
+	if (cc->key_size && crypt_decode_key(cc->key, key, cc->key_size) < 0)
+		goto out;
+
+	r = crypt_setkey(cc);
+	if (!r)
+		set_bit(DM_CRYPT_KEY_VALID, &cc->flags);
 
 out:
 	/* Hex key string not needed after here, so wipe it. */
@@ -1521,8 +1651,10 @@ static int crypt_wipe_key(struct crypt_config *cc)
 {
 	clear_bit(DM_CRYPT_KEY_VALID, &cc->flags);
 	memset(&cc->key, 0, cc->key_size * sizeof(u8));
+	kzfree(cc->key_string);
+	cc->key_string = NULL;
 
-	return crypt_setkey_allcpus(cc);
+	return crypt_setkey(cc);
 }
 
 static void crypt_dtr(struct dm_target *ti)
@@ -1558,6 +1690,7 @@ static void crypt_dtr(struct dm_target *ti)
 
 	kzfree(cc->cipher);
 	kzfree(cc->cipher_string);
+	kzfree(cc->key_string);
 
 	/* Must zero key material before freeing */
 	kzfree(cc);
@@ -1726,12 +1859,13 @@ bad_mem:
 
 /*
  * Construct an encryption mapping:
- * <cipher> <key> <iv_offset> <dev_path> <start>
+ * <cipher> [<key>|:<key_size>:<user|logon>:<key_description>] <iv_offset> <dev_path> <start>
  */
 static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 {
 	struct crypt_config *cc;
-	unsigned int key_size, opt_params;
+	int key_size;
+	unsigned int opt_params;
 	unsigned long long tmpll;
 	int ret;
 	size_t iv_size_padding;
@@ -1748,7 +1882,11 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		return -EINVAL;
 	}
 
-	key_size = strlen(argv[1]) >> 1;
+	key_size = get_key_size(&argv[1]);
+	if (key_size < 0) {
+		ti->error = "Cannot parse key size";
+		return -EINVAL;
+	}
 
 	cc = kzalloc(sizeof(*cc) + key_size * sizeof(u8), GFP_KERNEL);
 	if (!cc) {
@@ -1955,10 +2093,13 @@ static void crypt_status(struct dm_target *ti, status_type_t type,
 	case STATUSTYPE_TABLE:
 		DMEMIT("%s ", cc->cipher_string);
 
-		if (cc->key_size > 0)
-			for (i = 0; i < cc->key_size; i++)
-				DMEMIT("%02x", cc->key[i]);
-		else
+		if (cc->key_size > 0) {
+			if (cc->key_string)
+				DMEMIT(":%u:%s", cc->key_size, cc->key_string);
+			else
+				for (i = 0; i < cc->key_size; i++)
+					DMEMIT("%02x", cc->key[i]);
+		} else
 			DMEMIT("-");
 
 		DMEMIT(" %llu %s %llu", (unsigned long long)cc->iv_offset,
@@ -2014,7 +2155,7 @@ static void crypt_resume(struct dm_target *ti)
 static int crypt_message(struct dm_target *ti, unsigned argc, char **argv)
 {
 	struct crypt_config *cc = ti->private;
-	int ret = -EINVAL;
+	int key_size, ret = -EINVAL;
 
 	if (argc < 2)
 		goto error;
@@ -2025,6 +2166,13 @@ static int crypt_message(struct dm_target *ti, unsigned argc, char **argv)
 			return -EINVAL;
 		}
 		if (argc == 3 && !strcasecmp(argv[1], "set")) {
+			/* The key size may not be changed. */
+			key_size = get_key_size(&argv[2]);
+			if (key_size < 0 || cc->key_size != key_size) {
+				memset(argv[2], '0', strlen(argv[2]));
+				return -EINVAL;
+			}
+
 			ret = crypt_set_key(cc, argv[2]);
 			if (ret)
 				return ret;
@@ -2068,7 +2216,7 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static struct target_type crypt_target = {
 	.name   = "crypt",
-	.version = {1, 14, 1},
+	.version = {1, 15, 0},
 	.module = THIS_MODULE,
 	.ctr    = crypt_ctr,
 	.dtr    = crypt_dtr,
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index 6a2e8dd44a1b..13305a182611 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -36,7 +36,8 @@ struct flakey_c {
 };
 
 enum feature_flag_bits {
-	DROP_WRITES
+	DROP_WRITES,
+	ERROR_WRITES
 };
 
 struct per_bio_data {
@@ -76,6 +77,25 @@ static int parse_features(struct dm_arg_set *as, struct flakey_c *fc,
 			if (test_and_set_bit(DROP_WRITES, &fc->flags)) {
 				ti->error = "Feature drop_writes duplicated";
 				return -EINVAL;
+			} else if (test_bit(ERROR_WRITES, &fc->flags)) {
+				ti->error = "Feature drop_writes conflicts with feature error_writes";
+				return -EINVAL;
+			}
+
+			continue;
+		}
+
+		/*
+		 * error_writes
+		 */
+		if (!strcasecmp(arg_name, "error_writes")) {
+			if (test_and_set_bit(ERROR_WRITES, &fc->flags)) {
+				ti->error = "Feature error_writes duplicated";
+				return -EINVAL;
+
+			} else if (test_bit(DROP_WRITES, &fc->flags)) {
+				ti->error = "Feature error_writes conflicts with feature drop_writes";
+				return -EINVAL;
 			}
 
 			continue;
@@ -135,6 +155,10 @@ static int parse_features(struct dm_arg_set *as, struct flakey_c *fc,
 	if (test_bit(DROP_WRITES, &fc->flags) && (fc->corrupt_bio_rw == WRITE)) {
 		ti->error = "drop_writes is incompatible with corrupt_bio_byte with the WRITE flag set";
 		return -EINVAL;
+
+	} else if (test_bit(ERROR_WRITES, &fc->flags) && (fc->corrupt_bio_rw == WRITE)) {
+		ti->error = "error_writes is incompatible with corrupt_bio_byte with the WRITE flag set";
+		return -EINVAL;
 	}
 
 	return 0;
@@ -200,11 +224,13 @@ static int flakey_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	if (!(fc->up_interval + fc->down_interval)) {
 		ti->error = "Total (up + down) interval is zero";
+		r = -EINVAL;
 		goto bad;
 	}
 
 	if (fc->up_interval + fc->down_interval < fc->up_interval) {
 		ti->error = "Interval overflow";
+		r = -EINVAL;
 		goto bad;
 	}
 
@@ -289,22 +315,27 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
 		pb->bio_submitted = true;
 
 		/*
-		 * Error reads if neither corrupt_bio_byte or drop_writes are set.
+		 * Error reads if neither corrupt_bio_byte or drop_writes or error_writes are set.
 		 * Otherwise, flakey_end_io() will decide if the reads should be modified.
 		 */
 		if (bio_data_dir(bio) == READ) {
-			if (!fc->corrupt_bio_byte && !test_bit(DROP_WRITES, &fc->flags))
+			if (!fc->corrupt_bio_byte && !test_bit(DROP_WRITES, &fc->flags) &&
+			    !test_bit(ERROR_WRITES, &fc->flags))
 				return -EIO;
 			goto map_bio;
 		}
 
 		/*
-		 * Drop writes?
+		 * Drop or error writes?
 		 */
 		if (test_bit(DROP_WRITES, &fc->flags)) {
 			bio_endio(bio);
 			return DM_MAPIO_SUBMITTED;
 		}
+		else if (test_bit(ERROR_WRITES, &fc->flags)) {
+			bio_io_error(bio);
+			return DM_MAPIO_SUBMITTED;
+		}
 
 		/*
 		 * Corrupt matching writes.
@@ -340,10 +371,11 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio, int error)
 			 */
 			corrupt_bio_data(bio, fc);
 
-		} else if (!test_bit(DROP_WRITES, &fc->flags)) {
+		} else if (!test_bit(DROP_WRITES, &fc->flags) &&
+			   !test_bit(ERROR_WRITES, &fc->flags)) {
 			/*
 			 * Error read during the down_interval if drop_writes
-			 * wasn't configured.
+			 * and error_writes were not configured.
 			 */
 			return -EIO;
 		}
@@ -357,7 +389,7 @@ static void flakey_status(struct dm_target *ti, status_type_t type,
 {
 	unsigned sz = 0;
 	struct flakey_c *fc = ti->private;
-	unsigned drop_writes;
+	unsigned drop_writes, error_writes;
 
 	switch (type) {
 	case STATUSTYPE_INFO:
@@ -370,10 +402,13 @@ static void flakey_status(struct dm_target *ti, status_type_t type,
 		       fc->down_interval);
 
 		drop_writes = test_bit(DROP_WRITES, &fc->flags);
-		DMEMIT("%u ", drop_writes + (fc->corrupt_bio_byte > 0) * 5);
+		error_writes = test_bit(ERROR_WRITES, &fc->flags);
+		DMEMIT("%u ", drop_writes + error_writes + (fc->corrupt_bio_byte > 0) * 5);
 
 		if (drop_writes)
 			DMEMIT("drop_writes ");
+		else if (error_writes)
+			DMEMIT("error_writes ");
 
 		if (fc->corrupt_bio_byte)
 			DMEMIT("corrupt_bio_byte %u %c %u %u ",
@@ -410,7 +445,7 @@ static int flakey_iterate_devices(struct dm_target *ti, iterate_devices_callout_
 
 static struct target_type flakey_target = {
 	.name   = "flakey",
-	.version = {1, 3, 1},
+	.version = {1, 4, 0},
 	.module = THIS_MODULE,
 	.ctr    = flakey_ctr,
 	.dtr    = flakey_dtr,
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 0bf1a12e35fe..03940bf36f6c 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -162,7 +162,10 @@ struct dpages {
 			 struct page **p, unsigned long *len, unsigned *offset);
 	void (*next_page)(struct dpages *dp);
 
-	unsigned context_u;
+	union {
+		unsigned context_u;
+		struct bvec_iter context_bi;
+	};
 	void *context_ptr;
 
 	void *vma_invalidate_address;
@@ -204,25 +207,36 @@ static void list_dp_init(struct dpages *dp, struct page_list *pl, unsigned offse
 static void bio_get_page(struct dpages *dp, struct page **p,
 			 unsigned long *len, unsigned *offset)
 {
-	struct bio_vec *bvec = dp->context_ptr;
-	*p = bvec->bv_page;
-	*len = bvec->bv_len - dp->context_u;
-	*offset = bvec->bv_offset + dp->context_u;
+	struct bio_vec bvec = bvec_iter_bvec((struct bio_vec *)dp->context_ptr,
+					     dp->context_bi);
+
+	*p = bvec.bv_page;
+	*len = bvec.bv_len;
+	*offset = bvec.bv_offset;
+
+	/* avoid figuring it out again in bio_next_page() */
+	dp->context_bi.bi_sector = (sector_t)bvec.bv_len;
 }
 
 static void bio_next_page(struct dpages *dp)
 {
-	struct bio_vec *bvec = dp->context_ptr;
-	dp->context_ptr = bvec + 1;
-	dp->context_u = 0;
+	unsigned int len = (unsigned int)dp->context_bi.bi_sector;
+
+	bvec_iter_advance((struct bio_vec *)dp->context_ptr,
+			  &dp->context_bi, len);
 }
 
 static void bio_dp_init(struct dpages *dp, struct bio *bio)
 {
 	dp->get_page = bio_get_page;
 	dp->next_page = bio_next_page;
-	dp->context_ptr = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter);
-	dp->context_u = bio->bi_iter.bi_bvec_done;
+
+	/*
+	 * We just use bvec iterator to retrieve pages, so it is ok to
+	 * access the bvec table directly here
+	 */
+	dp->context_ptr = bio->bi_io_vec;
+	dp->context_bi = bio->bi_iter;
 }
 
 /*
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 966eb4b61aed..c72a77048b73 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1697,7 +1697,7 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kern
 {
 	struct dm_ioctl *dmi;
 	int secure_data;
-	const size_t minimum_data_size = sizeof(*param_kernel) - sizeof(param_kernel->data);
+	const size_t minimum_data_size = offsetof(struct dm_ioctl, data);
 
 	if (copy_from_user(param_kernel, user, minimum_data_size))
 		return -EFAULT;
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index e477af8596e2..6400cffb986d 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -372,16 +372,13 @@ static int __pg_init_all_paths(struct multipath *m)
 	return atomic_read(&m->pg_init_in_progress);
 }
 
-static int pg_init_all_paths(struct multipath *m)
+static void pg_init_all_paths(struct multipath *m)
 {
-	int r;
 	unsigned long flags;
 
 	spin_lock_irqsave(&m->lock, flags);
-	r = __pg_init_all_paths(m);
+	__pg_init_all_paths(m);
 	spin_unlock_irqrestore(&m->lock, flags);
-
-	return r;
 }
 
 static void __switch_pg(struct multipath *m, struct priority_group *pg)
@@ -583,16 +580,17 @@ static int __multipath_map(struct dm_target *ti, struct request *clone,
 		 * .request_fn stacked on blk-mq path(s) and
 		 * blk-mq stacked on blk-mq path(s).
 		 */
-		*__clone = blk_mq_alloc_request(bdev_get_queue(bdev),
-						rq_data_dir(rq), BLK_MQ_REQ_NOWAIT);
-		if (IS_ERR(*__clone)) {
-			/* ENOMEM, requeue */
+		clone = blk_mq_alloc_request(bdev_get_queue(bdev),
+					     rq_data_dir(rq), BLK_MQ_REQ_NOWAIT);
+		if (IS_ERR(clone)) {
+			/* EBUSY, ENODEV or EWOULDBLOCK: requeue */
 			clear_request_fn_mpio(m, map_context);
 			return r;
 		}
-		(*__clone)->bio = (*__clone)->biotail = NULL;
-		(*__clone)->rq_disk = bdev->bd_disk;
-		(*__clone)->cmd_flags |= REQ_FAILFAST_TRANSPORT;
+		clone->bio = clone->biotail = NULL;
+		clone->rq_disk = bdev->bd_disk;
+		clone->cmd_flags |= REQ_FAILFAST_TRANSPORT;
+		*__clone = clone;
 	}
 
 	if (pgpath->pg->ps.type->start_io)
@@ -852,18 +850,22 @@ retain:
 		attached_handler_name = scsi_dh_attached_handler_name(q, GFP_KERNEL);
 		if (attached_handler_name) {
 			/*
+			 * Clear any hw_handler_params associated with a
+			 * handler that isn't already attached.
+			 */
+			if (m->hw_handler_name && strcmp(attached_handler_name, m->hw_handler_name)) {
+				kfree(m->hw_handler_params);
+				m->hw_handler_params = NULL;
+			}
+
+			/*
 			 * Reset hw_handler_name to match the attached handler
-			 * and clear any hw_handler_params associated with the
-			 * ignored handler.
 			 *
 			 * NB. This modifies the table line to show the actual
 			 * handler instead of the original table passed in.
 			 */
 			kfree(m->hw_handler_name);
 			m->hw_handler_name = attached_handler_name;
-
-			kfree(m->hw_handler_params);
-			m->hw_handler_params = NULL;
 		}
 	}
 
@@ -1002,6 +1004,8 @@ static int parse_hw_handler(struct dm_arg_set *as, struct multipath *m)
 	}
 
 	m->hw_handler_name = kstrdup(dm_shift_arg(as), GFP_KERNEL);
+	if (!m->hw_handler_name)
+		return -EINVAL;
 
 	if (hw_argc > 1) {
 		char *p;
@@ -1362,7 +1366,7 @@ static int switch_pg_num(struct multipath *m, const char *pgstr)
 	char dummy;
 
 	if (!pgstr || (sscanf(pgstr, "%u%c", &pgnum, &dummy) != 1) || !pgnum ||
-	    (pgnum > m->nr_priority_groups)) {
+	    !m->nr_priority_groups || (pgnum > m->nr_priority_groups)) {
 		DMWARN("invalid PG number supplied to switch_pg_num");
 		return -EINVAL;
 	}
@@ -1394,7 +1398,7 @@ static int bypass_pg_num(struct multipath *m, const char *pgstr, bool bypassed)
 	char dummy;
 
 	if (!pgstr || (sscanf(pgstr, "%u%c", &pgnum, &dummy) != 1) || !pgnum ||
-	    (pgnum > m->nr_priority_groups)) {
+	    !m->nr_priority_groups || (pgnum > m->nr_priority_groups)) {
 		DMWARN("invalid PG number supplied to bypass_pg");
 		return -EINVAL;
 	}
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 953159d9a825..b8f978e551d7 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -160,7 +160,6 @@ struct raid_dev {
 				 CTR_FLAG_DAEMON_SLEEP | \
 				 CTR_FLAG_MIN_RECOVERY_RATE | \
 				 CTR_FLAG_MAX_RECOVERY_RATE | \
-				 CTR_FLAG_MAX_WRITE_BEHIND | \
 				 CTR_FLAG_STRIPE_CACHE | \
 				 CTR_FLAG_REGION_SIZE | \
 				 CTR_FLAG_DELTA_DISKS | \
@@ -171,7 +170,6 @@ struct raid_dev {
 				 CTR_FLAG_DAEMON_SLEEP | \
 				 CTR_FLAG_MIN_RECOVERY_RATE | \
 				 CTR_FLAG_MAX_RECOVERY_RATE | \
-				 CTR_FLAG_MAX_WRITE_BEHIND | \
 				 CTR_FLAG_STRIPE_CACHE | \
 				 CTR_FLAG_REGION_SIZE | \
 				 CTR_FLAG_DELTA_DISKS | \