Merge tag 'for-5.5/dm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper fixes from Mike Snitzer:

 - Fix DM multipath by restoring full path selector functionality for
   bio-based configurations that don't haave a SCSI device handler.

 - Fix dm-btree removal to ensure non-root btree nodes have at least
   (max_entries / 3) entries. This resolves userspace thin_check
   utility's report of "too few entries in btree_node".

 - Fix both the DM thin-provisioning and dm-clone targets to properly
   flush the data device prior to metadata commit. This resolves the
   potential for inconsistency across a power loss event when the data
   device has a volatile writeback cache.

 - Small documentation fixes to dm-clone and dm-integrity.

* tag 'for-5.5/dm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  docs: dm-integrity: remove reference to ARC4
  dm thin: Flush data device before committing metadata
  dm thin metadata: Add support for a pre-commit callback
  dm clone: Flush destination device before committing metadata
  dm clone metadata: Use a two phase commit
  dm clone metadata: Track exact changes per transaction
  dm btree: increase rebalance threshold in __rebalance2()
  dm: add dm-clone to the documentation index
  dm mpath: remove harmful bio-based optimization

1 files changed, 40 insertions, 2 deletions

diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 5a2c494cb552..57626c27a54b 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -328,6 +328,7 @@ struct pool_c {
 	dm_block_t low_water_blocks;
 	struct pool_features requested_pf; /* Features requested during table load */
 	struct pool_features adjusted_pf;  /* Features used after adjusting for constituent devices */
+	struct bio flush_bio;
 };
 
 /*
@@ -2383,8 +2384,16 @@ static void process_deferred_bios(struct pool *pool)
 	while ((bio = bio_list_pop(&bio_completions)))
 		bio_endio(bio);
 
-	while ((bio = bio_list_pop(&bios)))
-		generic_make_request(bio);
+	while ((bio = bio_list_pop(&bios))) {
+		/*
+		 * The data device was flushed as part of metadata commit,
+		 * so complete redundant flushes immediately.
+		 */
+		if (bio->bi_opf & REQ_PREFLUSH)
+			bio_endio(bio);
+		else
+			generic_make_request(bio);
+	}
 }
 
 static void do_worker(struct work_struct *ws)
@@ -3115,6 +3124,7 @@ static void pool_dtr(struct dm_target *ti)
 	__pool_dec(pt->pool);
 	dm_put_device(ti, pt->metadata_dev);
 	dm_put_device(ti, pt->data_dev);
+	bio_uninit(&pt->flush_bio);
 	kfree(pt);
 
 	mutex_unlock(&dm_thin_pool_table.mutex);
@@ -3180,6 +3190,29 @@ static void metadata_low_callback(void *context)
 	dm_table_event(pool->ti->table);
 }
 
+/*
+ * We need to flush the data device **before** committing the metadata.
+ *
+ * This ensures that the data blocks of any newly inserted mappings are
+ * properly written to non-volatile storage and won't be lost in case of a
+ * crash.
+ *
+ * Failure to do so can result in data corruption in the case of internal or
+ * external snapshots and in the case of newly provisioned blocks, when block
+ * zeroing is enabled.
+ */
+static int metadata_pre_commit_callback(void *context)
+{
+	struct pool_c *pt = context;
+	struct bio *flush_bio = &pt->flush_bio;
+
+	bio_reset(flush_bio);
+	bio_set_dev(flush_bio, pt->data_dev->bdev);
+	flush_bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
+
+	return submit_bio_wait(flush_bio);
+}
+
 static sector_t get_dev_size(struct block_device *bdev)
 {
 	return i_size_read(bdev->bd_inode) >> SECTOR_SHIFT;
@@ -3348,6 +3381,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	pt->data_dev = data_dev;
 	pt->low_water_blocks = low_water_blocks;
 	pt->adjusted_pf = pt->requested_pf = pf;
+	bio_init(&pt->flush_bio, NULL, 0);
 	ti->num_flush_bios = 1;
 
 	/*
@@ -3374,6 +3408,10 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	if (r)
 		goto out_flags_changed;
 
+	dm_pool_register_pre_commit_callback(pt->pool->pmd,
+					     metadata_pre_commit_callback,
+					     pt);
+
 	pt->callbacks.congested_fn = pool_is_congested;
 	dm_table_add_target_callbacks(ti->table, &pt->callbacks);