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
  ...

6 files changed, 24 insertions, 27 deletions

diff --git a/drivers/md/persistent-data/dm-bitset.c b/drivers/md/persistent-data/dm-bitset.c
index cd9a86d4cdf0..36f7cc2c7109 100644
--- a/drivers/md/persistent-data/dm-bitset.c
+++ b/drivers/md/persistent-data/dm-bitset.c
@@ -65,7 +65,7 @@ int dm_bitset_flush(struct dm_disk_bitset *info, dm_block_t root,
 	int r;
 	__le64 value;
 
-	if (!info->current_index_set)
+	if (!info->current_index_set || !info->dirty)
 		return 0;
 
 	value = cpu_to_le64(info->current_bits);
@@ -77,6 +77,8 @@ int dm_bitset_flush(struct dm_disk_bitset *info, dm_block_t root,
 		return r;
 
 	info->current_index_set = false;
+	info->dirty = false;
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(dm_bitset_flush);
@@ -94,6 +96,8 @@ static int read_bits(struct dm_disk_bitset *info, dm_block_t root,
 	info->current_bits = le64_to_cpu(value);
 	info->current_index_set = true;
 	info->current_index = array_index;
+	info->dirty = false;
+
 	return 0;
 }
 
@@ -126,6 +130,8 @@ int dm_bitset_set_bit(struct dm_disk_bitset *info, dm_block_t root,
 		return r;
 
 	set_bit(b, (unsigned long *) &info->current_bits);
+	info->dirty = true;
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(dm_bitset_set_bit);
@@ -141,6 +147,8 @@ int dm_bitset_clear_bit(struct dm_disk_bitset *info, dm_block_t root,
 		return r;
 
 	clear_bit(b, (unsigned long *) &info->current_bits);
+	info->dirty = true;
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(dm_bitset_clear_bit);
diff --git a/drivers/md/persistent-data/dm-bitset.h b/drivers/md/persistent-data/dm-bitset.h
index e1b9bea14aa1..c2287d672ef5 100644
--- a/drivers/md/persistent-data/dm-bitset.h
+++ b/drivers/md/persistent-data/dm-bitset.h
@@ -71,6 +71,7 @@ struct dm_disk_bitset {
 	uint64_t current_bits;
 
 	bool current_index_set:1;
+	bool dirty:1;
 };
 
 /*
diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c
index 455f79279a16..087411c95ffc 100644
--- a/drivers/md/persistent-data/dm-block-manager.c
+++ b/drivers/md/persistent-data/dm-block-manager.c
@@ -595,25 +595,14 @@ int dm_bm_unlock(struct dm_block *b)
 }
 EXPORT_SYMBOL_GPL(dm_bm_unlock);
 
-int dm_bm_flush_and_unlock(struct dm_block_manager *bm,
-			   struct dm_block *superblock)
+int dm_bm_flush(struct dm_block_manager *bm)
 {
-	int r;
-
 	if (bm->read_only)
 		return -EPERM;
 
-	r = dm_bufio_write_dirty_buffers(bm->bufio);
-	if (unlikely(r)) {
-		dm_bm_unlock(superblock);
-		return r;
-	}
-
-	dm_bm_unlock(superblock);
-
 	return dm_bufio_write_dirty_buffers(bm->bufio);
 }
-EXPORT_SYMBOL_GPL(dm_bm_flush_and_unlock);
+EXPORT_SYMBOL_GPL(dm_bm_flush);
 
 void dm_bm_prefetch(struct dm_block_manager *bm, dm_block_t b)
 {
diff --git a/drivers/md/persistent-data/dm-block-manager.h b/drivers/md/persistent-data/dm-block-manager.h
index 13cd58e1fe69..1b95dfc17786 100644
--- a/drivers/md/persistent-data/dm-block-manager.h
+++ b/drivers/md/persistent-data/dm-block-manager.h
@@ -105,8 +105,7 @@ int dm_bm_unlock(struct dm_block *b);
  *
  * This method always blocks.
  */
-int dm_bm_flush_and_unlock(struct dm_block_manager *bm,
-			   struct dm_block *superblock);
+int dm_bm_flush(struct dm_block_manager *bm);
 
 /*
  * Request data is prefetched into the cache.
diff --git a/drivers/md/persistent-data/dm-transaction-manager.c b/drivers/md/persistent-data/dm-transaction-manager.c
index 81da1a26042e..3bc30a0ae3d6 100644
--- a/drivers/md/persistent-data/dm-transaction-manager.c
+++ b/drivers/md/persistent-data/dm-transaction-manager.c
@@ -154,7 +154,7 @@ int dm_tm_pre_commit(struct dm_transaction_manager *tm)
 	if (r < 0)
 		return r;
 
-	return 0;
+	return dm_bm_flush(tm->bm);
 }
 EXPORT_SYMBOL_GPL(dm_tm_pre_commit);
 
@@ -164,8 +164,9 @@ int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *root)
 		return -EWOULDBLOCK;
 
 	wipe_shadow_table(tm);
+	dm_bm_unlock(root);
 
-	return dm_bm_flush_and_unlock(tm->bm, root);
+	return dm_bm_flush(tm->bm);
 }
 EXPORT_SYMBOL_GPL(dm_tm_commit);
 
diff --git a/drivers/md/persistent-data/dm-transaction-manager.h b/drivers/md/persistent-data/dm-transaction-manager.h
index b5b139076ca5..2772ed2a781a 100644
--- a/drivers/md/persistent-data/dm-transaction-manager.h
+++ b/drivers/md/persistent-data/dm-transaction-manager.h
@@ -38,18 +38,17 @@ struct dm_transaction_manager *dm_tm_create_non_blocking_clone(struct dm_transac
 /*
  * We use a 2-phase commit here.
  *
- * i) In the first phase the block manager is told to start flushing, and
- * the changes to the space map are written to disk.  You should interrogate
- * your particular space map to get detail of its root node etc. to be
- * included in your superblock.
+ * i) Make all changes for the transaction *except* for the superblock.
+ * Then call dm_tm_pre_commit() to flush them to disk.
  *
- * ii) @root will be committed last.  You shouldn't use more than the
- * first 512 bytes of @root if you wish the transaction to survive a power
- * failure.  You *must* have a write lock held on @root for both stage (i)
- * and (ii).  The commit will drop the write lock.
+ * ii) Lock your superblock.  Update.  Then call dm_tm_commit() which will
+ * unlock the superblock and flush it.  No other blocks should be updated
+ * during this period.  Care should be taken to never unlock a partially
+ * updated superblock; perform any operations that could fail *before* you
+ * take the superblock lock.
  */
 int dm_tm_pre_commit(struct dm_transaction_manager *tm);
-int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *root);
+int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *superblock);
 
 /*
  * These methods are the only way to get hold of a writeable block.