Merge tag 'dm-3.15-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper changes from Mike Snitzer:

 - Fix dm-cache corruption caused by discard_block_size > cache_block_size

 - Fix a lock-inversion detected by LOCKDEP in dm-cache

 - Fix a dangling bio bug in the dm-thinp target's process_deferred_bios
   error path

 - Fix corruption due to non-atomic transaction commit which allowed a
   metadata superblock to be written before all other metadata was
   successfully written -- this is common to all targets that use the
   persistent-data library's transaction manager (dm-thinp, dm-cache and
   dm-era).

 - Various small cleanups in the DM core

 - Add the dm-era target which is useful for keeping track of which
   blocks were written within a user defined period of time called an
   'era'.  Use cases include tracking changed blocks for backup
   software, and partially invalidating the contents of a cache to
   restore cache coherency after rolling back a vendor snapshot.

 - Improve the on-disk layout of multithreaded writes to the
   dm-thin-pool by splitting the pool's deferred bio list to be a
   per-thin device list and then sorting that list using an rb_tree.
   The subsequent read throughput of the data written via multiple
   threads improved by ~70%.

 - Simplify the multipath target's handling of queuing IO by pushing
   requests back to the request queue rather than queueing the IO
   internally.

* tag 'dm-3.15-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (24 commits)
  dm cache: fix a lock-inversion
  dm thin: sort the per thin deferred bios using an rb_tree
  dm thin: use per thin device deferred bio lists
  dm thin: simplify pool_is_congested
  dm thin: fix dangling bio in process_deferred_bios error path
  dm mpath: print more useful warnings in multipath_message()
  dm-mpath: do not activate failed paths
  dm mpath: remove extra nesting in map function
  dm mpath: remove map_io()
  dm mpath: reduce memory pressure when requeuing
  dm mpath: remove process_queued_ios()
  dm mpath: push back requests instead of queueing
  dm table: add dm_table_run_md_queue_async
  dm mpath: do not call pg_init when it is already running
  dm: use RCU_INIT_POINTER instead of rcu_assign_pointer in __unbind
  dm: stop using bi_private
  dm: remove dm_get_mapinfo
  dm: make dm_table_alloc_md_mempools static
  dm: take care to copy the space map roots before locking the superblock
  dm transaction manager: fix corruption due to non-atomic transaction commit
  ...

1 files changed, 28 insertions, 103 deletions

diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 074b9c8e4cf..1bf4a71919e 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -237,9 +237,8 @@ struct cache {
 	/*
 	 * origin_blocks entries, discarded if set.
 	 */
-	dm_dblock_t discard_nr_blocks;
+	dm_oblock_t discard_nr_blocks;
 	unsigned long *discard_bitset;
-	uint32_t discard_block_size; /* a power of 2 times sectors per block */
 
 	/*
 	 * Rather than reconstructing the table line for the status we just
@@ -526,48 +525,33 @@ static dm_block_t block_div(dm_block_t b, uint32_t n)
 	return b;
 }
 
-static dm_dblock_t oblock_to_dblock(struct cache *cache, dm_oblock_t oblock)
-{
-	uint32_t discard_blocks = cache->discard_block_size;
-	dm_block_t b = from_oblock(oblock);
-
-	if (!block_size_is_power_of_two(cache))
-		discard_blocks = discard_blocks / cache->sectors_per_block;
-	else
-		discard_blocks >>= cache->sectors_per_block_shift;
-
-	b = block_div(b, discard_blocks);
-
-	return to_dblock(b);
-}
-
-static void set_discard(struct cache *cache, dm_dblock_t b)
+static void set_discard(struct cache *cache, dm_oblock_t b)
 {
 	unsigned long flags;
 
 	atomic_inc(&cache->stats.discard_count);
 
 	spin_lock_irqsave(&cache->lock, flags);
-	set_bit(from_dblock(b), cache->discard_bitset);
+	set_bit(from_oblock(b), cache->discard_bitset);
 	spin_unlock_irqrestore(&cache->lock, flags);
 }
 
-static void clear_discard(struct cache *cache, dm_dblock_t b)
+static void clear_discard(struct cache *cache, dm_oblock_t b)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&cache->lock, flags);
-	clear_bit(from_dblock(b), cache->discard_bitset);
+	clear_bit(from_oblock(b), cache->discard_bitset);
 	spin_unlock_irqrestore(&cache->lock, flags);
 }
 
-static bool is_discarded(struct cache *cache, dm_dblock_t b)
+static bool is_discarded(struct cache *cache, dm_oblock_t b)
 {
 	int r;
 	unsigned long flags;
 
 	spin_lock_irqsave(&cache->lock, flags);
-	r = test_bit(from_dblock(b), cache->discard_bitset);
+	r = test_bit(from_oblock(b), cache->discard_bitset);
 	spin_unlock_irqrestore(&cache->lock, flags);
 
 	return r;
@@ -579,8 +563,7 @@ static bool is_discarded_oblock(struct cache *cache, dm_oblock_t b)
 	unsigned long flags;
 
 	spin_lock_irqsave(&cache->lock, flags);
-	r = test_bit(from_dblock(oblock_to_dblock(cache, b)),
-		     cache->discard_bitset);
+	r = test_bit(from_oblock(b), cache->discard_bitset);
 	spin_unlock_irqrestore(&cache->lock, flags);
 
 	return r;
@@ -705,7 +688,7 @@ static void remap_to_origin_clear_discard(struct cache *cache, struct bio *bio,
 	check_if_tick_bio_needed(cache, bio);
 	remap_to_origin(cache, bio);
 	if (bio_data_dir(bio) == WRITE)
-		clear_discard(cache, oblock_to_dblock(cache, oblock));
+		clear_discard(cache, oblock);
 }
 
 static void remap_to_cache_dirty(struct cache *cache, struct bio *bio,
@@ -715,7 +698,7 @@ static void remap_to_cache_dirty(struct cache *cache, struct bio *bio,
 	remap_to_cache(cache, bio, cblock);
 	if (bio_data_dir(bio) == WRITE) {
 		set_dirty(cache, oblock, cblock);
-		clear_discard(cache, oblock_to_dblock(cache, oblock));
+		clear_discard(cache, oblock);
 	}
 }
 
@@ -1288,14 +1271,14 @@ static void process_flush_bio(struct cache *cache, struct bio *bio)
 static void process_discard_bio(struct cache *cache, struct bio *bio)
 {
 	dm_block_t start_block = dm_sector_div_up(bio->bi_iter.bi_sector,
-						  cache->discard_block_size);
+						  cache->sectors_per_block);
 	dm_block_t end_block = bio_end_sector(bio);
 	dm_block_t b;
 
-	end_block = block_div(end_block, cache->discard_block_size);
+	end_block = block_div(end_block, cache->sectors_per_block);
 
 	for (b = start_block; b < end_block; b++)
-		set_discard(cache, to_dblock(b));
+		set_discard(cache, to_oblock(b));
 
 	bio_endio(bio, 0);
 }
@@ -2171,35 +2154,6 @@ static int create_cache_policy(struct cache *cache, struct cache_args *ca,
 	return 0;
 }
 
-/*
- * We want the discard block size to be a power of two, at least the size
- * of the cache block size, and have no more than 2^14 discard blocks
- * across the origin.
- */
-#define MAX_DISCARD_BLOCKS (1 << 14)
-
-static bool too_many_discard_blocks(sector_t discard_block_size,
-				    sector_t origin_size)
-{
-	(void) sector_div(origin_size, discard_block_size);
-
-	return origin_size > MAX_DISCARD_BLOCKS;
-}
-
-static sector_t calculate_discard_block_size(sector_t cache_block_size,
-					     sector_t origin_size)
-{
-	sector_t discard_block_size;
-
-	discard_block_size = roundup_pow_of_two(cache_block_size);
-
-	if (origin_size)
-		while (too_many_discard_blocks(discard_block_size, origin_size))
-			discard_block_size *= 2;
-
-	return discard_block_size;
-}
-
 #define DEFAULT_MIGRATION_THRESHOLD 2048
 
 static int cache_create(struct cache_args *ca, struct cache **result)
@@ -2321,16 +2275,13 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 	}
 	clear_bitset(cache->dirty_bitset, from_cblock(cache->cache_size));
 
-	cache->discard_block_size =
-		calculate_discard_block_size(cache->sectors_per_block,
-					     cache->origin_sectors);
-	cache->discard_nr_blocks = oblock_to_dblock(cache, cache->origin_blocks);
-	cache->discard_bitset = alloc_bitset(from_dblock(cache->discard_nr_blocks));
+	cache->discard_nr_blocks = cache->origin_blocks;
+	cache->discard_bitset = alloc_bitset(from_oblock(cache->discard_nr_blocks));
 	if (!cache->discard_bitset) {
 		*error = "could not allocate discard bitset";
 		goto bad;
 	}
-	clear_bitset(cache->discard_bitset, from_dblock(cache->discard_nr_blocks));
+	clear_bitset(cache->discard_bitset, from_oblock(cache->discard_nr_blocks));
 
 	cache->copier = dm_kcopyd_client_create(&dm_kcopyd_throttle);
 	if (IS_ERR(cache->copier)) {
@@ -2614,16 +2565,16 @@ static int write_discard_bitset(struct cache *cache)
 {
 	unsigned i, r;
 
-	r = dm_cache_discard_bitset_resize(cache->cmd, cache->discard_block_size,
-					   cache->discard_nr_blocks);
+	r = dm_cache_discard_bitset_resize(cache->cmd, cache->sectors_per_block,
+					   cache->origin_blocks);
 	if (r) {
 		DMERR("could not resize on-disk discard bitset");
 		return r;
 	}
 
-	for (i = 0; i < from_dblock(cache->discard_nr_blocks); i++) {
-		r = dm_cache_set_discard(cache->cmd, to_dblock(i),
-					 is_discarded(cache, to_dblock(i)));
+	for (i = 0; i < from_oblock(cache->discard_nr_blocks); i++) {
+		r = dm_cache_set_discard(cache->cmd, to_oblock(i),
+					 is_discarded(cache, to_oblock(i)));
 		if (r)
 			return r;
 	}
@@ -2631,30 +2582,6 @@ static int write_discard_bitset(struct cache *cache)
 	return 0;
 }
 
-static int save_hint(void *context, dm_cblock_t cblock, dm_oblock_t oblock,
-		     uint32_t hint)
-{
-	struct cache *cache = context;
-	return dm_cache_save_hint(cache->cmd, cblock, hint);
-}
-
-static int write_hints(struct cache *cache)
-{
-	int r;
-
-	r = dm_cache_begin_hints(cache->cmd, cache->policy);
-	if (r) {
-		DMERR("dm_cache_begin_hints failed");
-		return r;
-	}
-
-	r = policy_walk_mappings(cache->policy, save_hint, cache);
-	if (r)
-		DMERR("policy_walk_mappings failed");
-
-	return r;
-}
-
 /*
  * returns true on success
  */
@@ -2672,7 +2599,7 @@ static bool sync_metadata(struct cache *cache)
 
 	save_stats(cache);
 
-	r3 = write_hints(cache);
+	r3 = dm_cache_write_hints(cache->cmd, cache->policy);
 	if (r3)
 		DMERR("could not write hints");
 
@@ -2720,16 +2647,14 @@ static int load_mapping(void *context, dm_oblock_t oblock, dm_cblock_t cblock,
 }
 
 static int load_discard(void *context, sector_t discard_block_size,
-			dm_dblock_t dblock, bool discard)
+			dm_oblock_t oblock, bool discard)
 {
 	struct cache *cache = context;
 
-	/* FIXME: handle mis-matched block size */
-
 	if (discard)
-		set_discard(cache, dblock);
+		set_discard(cache, oblock);
 	else
-		clear_discard(cache, dblock);
+		clear_discard(cache, oblock);
 
 	return 0;
 }
@@ -3120,8 +3045,8 @@ static void set_discard_limits(struct cache *cache, struct queue_limits *limits)
 	/*
 	 * FIXME: these limits may be incompatible with the cache device
 	 */
-	limits->max_discard_sectors = cache->discard_block_size * 1024;
-	limits->discard_granularity = cache->discard_block_size << SECTOR_SHIFT;
+	limits->max_discard_sectors = cache->sectors_per_block;
+	limits->discard_granularity = cache->sectors_per_block << SECTOR_SHIFT;
 }
 
 static void cache_io_hints(struct dm_target *ti, struct queue_limits *limits)
@@ -3145,7 +3070,7 @@ static void cache_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static struct target_type cache_target = {
 	.name = "cache",
-	.version = {1, 3, 0},
+	.version = {1, 4, 0},
 	.module = THIS_MODULE,
 	.ctr = cache_ctr,
 	.dtr = cache_dtr,