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

…nel/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
  ...

Documentation/device-mapper/dm-crypt.txt

@@ -21,13 +21,30 @@ Parameters: <cipher> <key> <iv_offset> <device path> \
     /proc/crypto contains supported crypto modes
 
 <key>
-    Key used for encryption. It is encoded as a hexadecimal number.
+    Key used for encryption. It is encoded either as a hexadecimal number
+    or it can be passed as <key_string> prefixed with single colon
+    character (':') for keys residing in kernel keyring service.
     You can only use key sizes that are valid for the selected cipher
     in combination with the selected iv mode.
     Note that for some iv modes the key string can contain additional
     keys (for example IV seed) so the key contains more parts concatenated
     into a single string.
 
+<key_string>
+    The kernel keyring key is identified by string in following format:
+    <key_size>:<key_type>:<key_description>.
+
+<key_size>
+    The encryption key size in bytes. The kernel key payload size must match
+    the value passed in <key_size>.
+
+<key_type>
+    Either 'logon' or 'user' kernel key type.
+
+<key_description>
+    The kernel keyring key description crypt target should look for
+    when loading key of <key_type>.
+
 <keycount>
     Multi-key compatibility mode. You can define <keycount> keys and
     then sectors are encrypted according to their offsets (sector 0 uses key0;
@@ -88,6 +105,12 @@ https://gitlab.com/cryptsetup/cryptsetup
 dmsetup create crypt1 --table "0 `blockdev --getsize $1` crypt aes-cbc-essiv:sha256 babebabebabebabebabebabebabebabe 0 $1 0"
 ]]
 
+[[
+#!/bin/sh
+# Create a crypt device using dmsetup when encryption key is stored in keyring service
+dmsetup create crypt2 --table "0 `blockdev --getsize $1` crypt aes-cbc-essiv:sha256 :32:logon:my_prefix:my_key 0 $1 0"
+]]
+
 [[
 #!/bin/sh
 # Create a crypt device using cryptsetup and LUKS header with default cipher

Documentation/device-mapper/dm-raid.txt

@@ -242,6 +242,10 @@ recovery.  Here is a fuller description of the individual fields:
 			in RAID1/10 or wrong parity values found in RAID4/5/6.
 			This value is valid only after a "check" of the array
 			is performed.  A healthy array has a 'mismatch_cnt' of 0.
+	<data_offset>   The current data offset to the start of the user data on
+			each component device of a raid set (see the respective
+			raid parameter to support out-of-place reshaping).
+
 
 Message Interface
 -----------------

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

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
@@ -835,14 +837,23 @@ 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;
 		}
 
 		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]);
 }
 
 /*

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;

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,

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;
 	}