dm: take care to copy the space map roots before locking the superblock

In theory copying the space map root can fail, but in practice it never
does because we're careful to check what size buffer is needed.

But make certain we're able to copy the space map roots before
locking the superblock.

Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org # drop dm-era and dm-cache changes as needed

drivers/md/dm-cache-metadata.c

@@ -120,6 +120,12 @@ struct dm_cache_metadata {
 	unsigned policy_version[CACHE_POLICY_VERSION_SIZE];
 	size_t policy_hint_size;
 	struct dm_cache_statistics stats;
+
+	/*
+	 * Reading the space map root can fail, so we read it into this
+	 * buffer before the superblock is locked and updated.
+	 */
+	__u8 metadata_space_map_root[SPACE_MAP_ROOT_SIZE];
 };
 
 /*-------------------------------------------------------------------
@@ -260,11 +266,31 @@ static void __setup_mapping_info(struct dm_cache_metadata *cmd)
 	}
 }
 
+static int __save_sm_root(struct dm_cache_metadata *cmd)
+{
+	int r;
+	size_t metadata_len;
+
+	r = dm_sm_root_size(cmd->metadata_sm, &metadata_len);
+	if (r < 0)
+		return r;
+
+	return dm_sm_copy_root(cmd->metadata_sm, &cmd->metadata_space_map_root,
+			       metadata_len);
+}
+
+static void __copy_sm_root(struct dm_cache_metadata *cmd,
+			   struct cache_disk_superblock *disk_super)
+{
+	memcpy(&disk_super->metadata_space_map_root,
+	       &cmd->metadata_space_map_root,
+	       sizeof(cmd->metadata_space_map_root));
+}
+
 static int __write_initial_superblock(struct dm_cache_metadata *cmd)
 {
 	int r;
 	struct dm_block *sblock;
-	size_t metadata_len;
 	struct cache_disk_superblock *disk_super;
 	sector_t bdev_size = i_size_read(cmd->bdev->bd_inode) >> SECTOR_SHIFT;
 
@@ -272,12 +298,16 @@ static int __write_initial_superblock(struct dm_cache_metadata *cmd)
 	if (bdev_size > DM_CACHE_METADATA_MAX_SECTORS)
 		bdev_size = DM_CACHE_METADATA_MAX_SECTORS;
 
-	r = dm_sm_root_size(cmd->metadata_sm, &metadata_len);
+	r = dm_tm_pre_commit(cmd->tm);
 	if (r < 0)
 		return r;
 
-	r = dm_tm_pre_commit(cmd->tm);
+	/*
-	if (r < 0)
+	 * dm_sm_copy_root() can fail.  So we need to do it before we start
+	 * updating the superblock.
+	 */
+	r = __save_sm_root(cmd);
+	if (r)
 		return r;
 
 	r = superblock_lock_zero(cmd, &sblock);
@@ -293,10 +323,7 @@ static int __write_initial_superblock(struct dm_cache_metadata *cmd)
 	memset(disk_super->policy_version, 0, sizeof(disk_super->policy_version));
 	disk_super->policy_hint_size = 0;
 
-	r = dm_sm_copy_root(cmd->metadata_sm, &disk_super->metadata_space_map_root,
+	__copy_sm_root(cmd, disk_super);
-			    metadata_len);
-	if (r < 0)
-		goto bad_locked;
 
 	disk_super->mapping_root = cpu_to_le64(cmd->root);
 	disk_super->hint_root = cpu_to_le64(cmd->hint_root);
@@ -313,10 +340,6 @@ static int __write_initial_superblock(struct dm_cache_metadata *cmd)
 	disk_super->write_misses = cpu_to_le32(0);
 
 	return dm_tm_commit(cmd->tm, sblock);
-
-bad_locked:
-	dm_bm_unlock(sblock);
-	return r;
 }
 
 static int __format_metadata(struct dm_cache_metadata *cmd)
@@ -560,7 +583,6 @@ static int __commit_transaction(struct dm_cache_metadata *cmd,
 				flags_mutator mutator)
 {
 	int r;
-	size_t metadata_len;
 	struct cache_disk_superblock *disk_super;
 	struct dm_block *sblock;
 
@@ -578,8 +600,8 @@ static int __commit_transaction(struct dm_cache_metadata *cmd,
 	if (r < 0)
 		return r;
 
-	r = dm_sm_root_size(cmd->metadata_sm, &metadata_len);
+	r = __save_sm_root(cmd);
-	if (r < 0)
+	if (r)
 		return r;
 
 	r = superblock_lock(cmd, &sblock);
@@ -606,13 +628,7 @@ static int __commit_transaction(struct dm_cache_metadata *cmd,
 	disk_super->read_misses = cpu_to_le32(cmd->stats.read_misses);
 	disk_super->write_hits = cpu_to_le32(cmd->stats.write_hits);
 	disk_super->write_misses = cpu_to_le32(cmd->stats.write_misses);
-
+	__copy_sm_root(cmd, disk_super);
-	r = dm_sm_copy_root(cmd->metadata_sm, &disk_super->metadata_space_map_root,
-			    metadata_len);
-	if (r < 0) {
-		dm_bm_unlock(sblock);
-		return r;
-	}
 
 	return dm_tm_commit(cmd->tm, sblock);
 }

drivers/md/dm-era-target.c

@@ -289,6 +289,12 @@ struct era_metadata {
 	 * A flag that is set whenever a writeset has been archived.
 	 */
 	bool archived_writesets;
+
+	/*
+	 * Reading the space map root can fail, so we read it into this
+	 * buffer before the superblock is locked and updated.
+	 */
+	__u8 metadata_space_map_root[SPACE_MAP_ROOT_SIZE];
 };
 
 static int superblock_read_lock(struct era_metadata *md,
@@ -453,16 +459,33 @@ static int create_fresh_metadata(struct era_metadata *md)
 	return r;
 }
 
+static int save_sm_root(struct era_metadata *md)
+{
+	int r;
+	size_t metadata_len;
+
+	r = dm_sm_root_size(md->sm, &metadata_len);
+	if (r < 0)
+		return r;
+
+	return dm_sm_copy_root(md->sm, &md->metadata_space_map_root,
+			       metadata_len);
+}
+
+static void copy_sm_root(struct era_metadata *md, struct superblock_disk *disk)
+{
+	memcpy(&disk->metadata_space_map_root,
+	       &md->metadata_space_map_root,
+	       sizeof(md->metadata_space_map_root));
+}
+
 /*
  * Writes a superblock, including the static fields that don't get updated
  * with every commit (possible optimisation here).  'md' should be fully
  * constructed when this is called.
  */
-static int prepare_superblock(struct era_metadata *md, struct superblock_disk *disk)
+static void prepare_superblock(struct era_metadata *md, struct superblock_disk *disk)
 {
-	int r;
-	size_t metadata_len;
-
 	disk->magic = cpu_to_le64(SUPERBLOCK_MAGIC);
 	disk->flags = cpu_to_le32(0ul);
 
@@ -470,14 +493,7 @@ static int prepare_superblock(struct era_metadata *md, struct superblock_disk *d
 	memset(disk->uuid, 0, sizeof(disk->uuid));
 	disk->version = cpu_to_le32(MAX_ERA_VERSION);
 
-	r = dm_sm_root_size(md->sm, &metadata_len);
+	copy_sm_root(md, disk);
-	if (r < 0)
-		return r;
-
-	r = dm_sm_copy_root(md->sm, &disk->metadata_space_map_root,
-			    metadata_len);
-	if (r < 0)
-		return r;
 
 	disk->data_block_size = cpu_to_le32(md->block_size);
 	disk->metadata_block_size = cpu_to_le32(DM_ERA_METADATA_BLOCK_SIZE >> SECTOR_SHIFT);
@@ -488,8 +504,6 @@ static int prepare_superblock(struct era_metadata *md, struct superblock_disk *d
 	disk->writeset_tree_root = cpu_to_le64(md->writeset_tree_root);
 	disk->era_array_root = cpu_to_le64(md->era_array_root);
 	disk->metadata_snap = cpu_to_le64(md->metadata_snap);
-
-	return 0;
 }
 
 static int write_superblock(struct era_metadata *md)
@@ -498,17 +512,18 @@ static int write_superblock(struct era_metadata *md)
 	struct dm_block *sblock;
 	struct superblock_disk *disk;
 
+	r = save_sm_root(md);
+	if (r) {
+		DMERR("%s: save_sm_root failed", __func__);
+		return r;
+	}
+
 	r = superblock_lock_zero(md, &sblock);
 	if (r)
 		return r;
 
 	disk = dm_block_data(sblock);
-	r = prepare_superblock(md, disk);
+	prepare_superblock(md, disk);
-	if (r) {
-		DMERR("%s: prepare_superblock failed", __func__);
-		dm_bm_unlock(sblock); /* FIXME: does this commit? */
-		return r;
-	}
 
 	return dm_tm_commit(md->tm, sblock);
 }
@@ -942,6 +957,12 @@ static int metadata_commit(struct era_metadata *md)
 		}
 	}
 
+	r = save_sm_root(md);
+	if (r) {
+		DMERR("%s: save_sm_root failed", __func__);
+		return r;
+	}
+
 	r = dm_tm_pre_commit(md->tm);
 	if (r) {
 		DMERR("%s: pre commit failed", __func__);
@@ -954,12 +975,7 @@ static int metadata_commit(struct era_metadata *md)
 		return r;
 	}
 
-	r = prepare_superblock(md, dm_block_data(sblock));
+	prepare_superblock(md, dm_block_data(sblock));
-	if (r) {
-		DMERR("%s: prepare_superblock failed", __func__);
-		dm_bm_unlock(sblock); /* FIXME: does this commit? */
-		return r;
-	}
 
 	return dm_tm_commit(md->tm, sblock);
 }

drivers/md/dm-thin-metadata.c

@@ -192,6 +192,13 @@ struct dm_pool_metadata {
 	 * operation possible in this state is the closing of the device.
 	 */
 	bool fail_io:1;
+
+	/*
+	 * Reading the space map roots can fail, so we read it into these
+	 * buffers before the superblock is locked and updated.
+	 */
+	__u8 data_space_map_root[SPACE_MAP_ROOT_SIZE];
+	__u8 metadata_space_map_root[SPACE_MAP_ROOT_SIZE];
 };
 
 struct dm_thin_device {
@@ -431,29 +438,56 @@ static void __setup_btree_details(struct dm_pool_metadata *pmd)
 	pmd->details_info.value_type.equal = NULL;
 }
 
+static int save_sm_roots(struct dm_pool_metadata *pmd)
+{
+	int r;
+	size_t len;
+
+	r = dm_sm_root_size(pmd->metadata_sm, &len);
+	if (r < 0)
+		return r;
+
+	r = dm_sm_copy_root(pmd->metadata_sm, &pmd->metadata_space_map_root, len);
+	if (r < 0)
+		return r;
+
+	r = dm_sm_root_size(pmd->data_sm, &len);
+	if (r < 0)
+		return r;
+
+	return dm_sm_copy_root(pmd->data_sm, &pmd->data_space_map_root, len);
+}
+
+static void copy_sm_roots(struct dm_pool_metadata *pmd,
+			  struct thin_disk_superblock *disk)
+{
+	memcpy(&disk->metadata_space_map_root,
+	       &pmd->metadata_space_map_root,
+	       sizeof(pmd->metadata_space_map_root));
+
+	memcpy(&disk->data_space_map_root,
+	       &pmd->data_space_map_root,
+	       sizeof(pmd->data_space_map_root));
+}
+
 static int __write_initial_superblock(struct dm_pool_metadata *pmd)
 {
 	int r;
 	struct dm_block *sblock;
-	size_t metadata_len, data_len;
 	struct thin_disk_superblock *disk_super;
 	sector_t bdev_size = i_size_read(pmd->bdev->bd_inode) >> SECTOR_SHIFT;
 
 	if (bdev_size > THIN_METADATA_MAX_SECTORS)
 		bdev_size = THIN_METADATA_MAX_SECTORS;
 
-	r = dm_sm_root_size(pmd->metadata_sm, &metadata_len);
-	if (r < 0)
-		return r;
-
-	r = dm_sm_root_size(pmd->data_sm, &data_len);
-	if (r < 0)
-		return r;
-
 	r = dm_sm_commit(pmd->data_sm);
 	if (r < 0)
 		return r;
 
+	r = save_sm_roots(pmd);
+	if (r < 0)
+		return r;
+
 	r = dm_tm_pre_commit(pmd->tm);
 	if (r < 0)
 		return r;
@@ -471,15 +505,7 @@ static int __write_initial_superblock(struct dm_pool_metadata *pmd)
 	disk_super->trans_id = 0;
 	disk_super->held_root = 0;
 
-	r = dm_sm_copy_root(pmd->metadata_sm, &disk_super->metadata_space_map_root,
+	copy_sm_roots(pmd, disk_super);
-			    metadata_len);
-	if (r < 0)
-		goto bad_locked;
-
-	r = dm_sm_copy_root(pmd->data_sm, &disk_super->data_space_map_root,
-			    data_len);
-	if (r < 0)
-		goto bad_locked;
 
 	disk_super->data_mapping_root = cpu_to_le64(pmd->root);
 	disk_super->device_details_root = cpu_to_le64(pmd->details_root);
@@ -488,10 +514,6 @@ static int __write_initial_superblock(struct dm_pool_metadata *pmd)
 	disk_super->data_block_size = cpu_to_le32(pmd->data_block_size);
 
 	return dm_tm_commit(pmd->tm, sblock);
-
-bad_locked:
-	dm_bm_unlock(sblock);
-	return r;
 }
 
 static int __format_metadata(struct dm_pool_metadata *pmd)
@@ -769,6 +791,10 @@ static int __commit_transaction(struct dm_pool_metadata *pmd)
 	if (r < 0)
 		return r;
 
+	r = save_sm_roots(pmd);
+	if (r < 0)
+		return r;
+
 	r = superblock_lock(pmd, &sblock);
 	if (r)
 		return r;
@@ -780,21 +806,9 @@ static int __commit_transaction(struct dm_pool_metadata *pmd)
 	disk_super->trans_id = cpu_to_le64(pmd->trans_id);
 	disk_super->flags = cpu_to_le32(pmd->flags);
 
-	r = dm_sm_copy_root(pmd->metadata_sm, &disk_super->metadata_space_map_root,
+	copy_sm_roots(pmd, disk_super);
-			    metadata_len);
-	if (r < 0)
-		goto out_locked;
-
-	r = dm_sm_copy_root(pmd->data_sm, &disk_super->data_space_map_root,
-			    data_len);
-	if (r < 0)
-		goto out_locked;
 
 	return dm_tm_commit(pmd->tm, sblock);
-
-out_locked:
-	dm_bm_unlock(sblock);
-	return r;
 }
 
 struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev,