Merge tag 'dm-4.11-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper updates from Mike Snitzer:

 - Fix dm-raid transient device failure processing and other smaller
   tweaks.

 - Add journal support to the DM raid target to close the 'write hole'
   on raid 4/5/6.

 - Fix dm-cache corruption, due to rounding bug, when cache exceeds 2TB.

 - Add 'metadata2' feature to dm-cache to separate the dirty bitset out
   from other cache metadata. This improves speed of shutting down a
   large cache device (which implies writing out dirty bits).

 - Fix a memory leak during dm-stats data structure destruction.

 - Fix a DM multipath round-robin path selector performance regression
   that was caused by less precise balancing across all paths.

 - Lastly, introduce a DM core fix for a long-standing DM snapshot
   deadlock that is rooted in the complexity of the device stack used in
   conjunction with block core maintaining bios on current->bio_list to
   manage recursion in generic_make_request(). A more comprehensive fix
   to block core (and its hook in the cpu scheduler) would be wonderful
   but this DM-specific fix is pragmatic considering how difficult it
   has been to make progress on a generic fix.

* tag 'dm-4.11-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (22 commits)
  dm: flush queued bios when process blocks to avoid deadlock
  dm round robin: revert "use percpu 'repeat_count' and 'current_path'"
  dm stats: fix a leaked s->histogram_boundaries array
  dm space map metadata: constify dm_space_map structures
  dm cache metadata: use cursor api in blocks_are_clean_separate_dirty()
  dm persistent data: add cursor skip functions to the cursor APIs
  dm cache metadata: use dm_bitset_new() to create the dirty bitset in format 2
  dm bitset: add dm_bitset_new()
  dm cache metadata: name the cache block that couldn't be loaded
  dm cache metadata: add "metadata2" feature
  dm cache metadata: use bitset cursor api to load discard bitset
  dm bitset: introduce cursor api
  dm btree: use GFP_NOFS in dm_btree_del()
  dm space map common: memcpy the disk root to ensure it's arch aligned
  dm block manager: add unlikely() annotations on dm_bufio error paths
  dm cache: fix corruption seen when using cache > 2TB
  dm raid: cleanup awkward branching in raid_message() option processing
  dm raid: use mddev rather than rdev->mddev
  dm raid: use read_disk_sb() throughout
  dm raid: add raid4/5/6 journaling support
  ...

1 files changed, 25 insertions, 19 deletions

diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 894bc14469c8..9c689b34e6e7 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -179,6 +179,7 @@ enum cache_io_mode {
 struct cache_features {
 	enum cache_metadata_mode mode;
 	enum cache_io_mode io_mode;
+	unsigned metadata_version;
 };
 
 struct cache_stats {
@@ -248,7 +249,7 @@ struct cache {
 	/*
 	 * Fields for converting from sectors to blocks.
 	 */
-	uint32_t sectors_per_block;
+	sector_t sectors_per_block;
 	int sectors_per_block_shift;
 
 	spinlock_t lock;
@@ -2534,13 +2535,14 @@ static void init_features(struct cache_features *cf)
 {
 	cf->mode = CM_WRITE;
 	cf->io_mode = CM_IO_WRITEBACK;
+	cf->metadata_version = 1;
 }
 
 static int parse_features(struct cache_args *ca, struct dm_arg_set *as,
 			  char **error)
 {
 	static struct dm_arg _args[] = {
-		{0, 1, "Invalid number of cache feature arguments"},
+		{0, 2, "Invalid number of cache feature arguments"},
 	};
 
 	int r;
@@ -2566,6 +2568,9 @@ static int parse_features(struct cache_args *ca, struct dm_arg_set *as,
 		else if (!strcasecmp(arg, "passthrough"))
 			cf->io_mode = CM_IO_PASSTHROUGH;
 
+		else if (!strcasecmp(arg, "metadata2"))
+			cf->metadata_version = 2;
+
 		else {
 			*error = "Unrecognised cache feature requested";
 			return -EINVAL;
@@ -2820,7 +2825,8 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 
 	cmd = dm_cache_metadata_open(cache->metadata_dev->bdev,
 				     ca->block_size, may_format,
-				     dm_cache_policy_get_hint_size(cache->policy));
+				     dm_cache_policy_get_hint_size(cache->policy),
+				     ca->features.metadata_version);
 	if (IS_ERR(cmd)) {
 		*error = "Error creating metadata object";
 		r = PTR_ERR(cmd);
@@ -3165,21 +3171,16 @@ static int cache_end_io(struct dm_target *ti, struct bio *bio, int error)
 
 static int write_dirty_bitset(struct cache *cache)
 {
-	unsigned i, r;
+	int r;
 
 	if (get_cache_mode(cache) >= CM_READ_ONLY)
 		return -EINVAL;
 
-	for (i = 0; i < from_cblock(cache->cache_size); i++) {
-		r = dm_cache_set_dirty(cache->cmd, to_cblock(i),
-				       is_dirty(cache, to_cblock(i)));
-		if (r) {
-			metadata_operation_failed(cache, "dm_cache_set_dirty", r);
-			return r;
-		}
-	}
+	r = dm_cache_set_dirty_bits(cache->cmd, from_cblock(cache->cache_size), cache->dirty_bitset);
+	if (r)
+		metadata_operation_failed(cache, "dm_cache_set_dirty_bits", r);
 
-	return 0;
+	return r;
 }
 
 static int write_discard_bitset(struct cache *cache)
@@ -3540,11 +3541,11 @@ static void cache_status(struct dm_target *ti, status_type_t type,
 
 		residency = policy_residency(cache->policy);
 
-		DMEMIT("%u %llu/%llu %u %llu/%llu %u %u %u %u %u %u %lu ",
+		DMEMIT("%u %llu/%llu %llu %llu/%llu %u %u %u %u %u %u %lu ",
 		       (unsigned)DM_CACHE_METADATA_BLOCK_SIZE,
 		       (unsigned long long)(nr_blocks_metadata - nr_free_blocks_metadata),
 		       (unsigned long long)nr_blocks_metadata,
-		       cache->sectors_per_block,
+		       (unsigned long long)cache->sectors_per_block,
 		       (unsigned long long) from_cblock(residency),
 		       (unsigned long long) from_cblock(cache->cache_size),
 		       (unsigned) atomic_read(&cache->stats.read_hit),
@@ -3555,14 +3556,19 @@ static void cache_status(struct dm_target *ti, status_type_t type,
 		       (unsigned) atomic_read(&cache->stats.promotion),
 		       (unsigned long) atomic_read(&cache->nr_dirty));
 
+		if (cache->features.metadata_version == 2)
+			DMEMIT("2 metadata2 ");
+		else
+			DMEMIT("1 ");
+
 		if (writethrough_mode(&cache->features))
-			DMEMIT("1 writethrough ");
+			DMEMIT("writethrough ");
 
 		else if (passthrough_mode(&cache->features))
-			DMEMIT("1 passthrough ");
+			DMEMIT("passthrough ");
 
 		else if (writeback_mode(&cache->features))
-			DMEMIT("1 writeback ");
+			DMEMIT("writeback ");
 
 		else {
 			DMERR("%s: internal error: unknown io mode: %d",
@@ -3810,7 +3816,7 @@ static void cache_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static struct target_type cache_target = {
 	.name = "cache",
-	.version = {1, 9, 0},
+	.version = {1, 10, 0},
 	.module = THIS_MODULE,
 	.ctr = cache_ctr,
 	.dtr = cache_dtr,