btrfs: introduce mount option rescue=ignorebadroots

In the face of extent root corruption, or any other core fs wide root
corruption we will fail to mount the file system.  This makes recovery
kind of a pain, because you need to fall back to userspace tools to
scrape off data.  Instead provide a mechanism to gracefully handle bad
roots, so we can at least mount read-only and possibly recover data from
the file system.

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/block-group.c

@@ -1985,6 +1985,51 @@ static int read_one_block_group(struct btrfs_fs_info *info,
 	return ret;
 }
 
+static int fill_dummy_bgs(struct btrfs_fs_info *fs_info)
+{
+	struct extent_map_tree *em_tree = &fs_info->mapping_tree;
+	struct btrfs_space_info *space_info;
+	struct rb_node *node;
+	int ret = 0;
+
+	for (node = rb_first_cached(&em_tree->map); node; node = rb_next(node)) {
+		struct extent_map *em;
+		struct map_lookup *map;
+		struct btrfs_block_group *bg;
+
+		em = rb_entry(node, struct extent_map, rb_node);
+		map = em->map_lookup;
+		bg = btrfs_create_block_group_cache(fs_info, em->start);
+		if (!bg) {
+			ret = -ENOMEM;
+			break;
+		}
+
+		/* Fill dummy cache as FULL */
+		bg->length = em->len;
+		bg->flags = map->type;
+		bg->last_byte_to_unpin = (u64)-1;
+		bg->cached = BTRFS_CACHE_FINISHED;
+		bg->used = em->len;
+		bg->flags = map->type;
+		ret = btrfs_add_block_group_cache(fs_info, bg);
+		if (ret) {
+			btrfs_remove_free_space_cache(bg);
+			btrfs_put_block_group(bg);
+			break;
+		}
+		btrfs_update_space_info(fs_info, bg->flags, em->len, em->len,
+					0, &space_info);
+		bg->space_info = space_info;
+		link_block_group(bg);
+
+		set_avail_alloc_bits(fs_info, bg->flags);
+	}
+	if (!ret)
+		btrfs_init_global_block_rsv(fs_info);
+	return ret;
+}
+
 int btrfs_read_block_groups(struct btrfs_fs_info *info)
 {
 	struct btrfs_path *path;
@@ -1995,6 +2040,9 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 	int need_clear = 0;
 	u64 cache_gen;
 
+	if (!info->extent_root)
+		return fill_dummy_bgs(info);
+
 	key.objectid = 0;
 	key.offset = 0;
 	key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;

fs/btrfs/block-rsv.c

@@ -426,6 +426,14 @@ void btrfs_init_global_block_rsv(struct btrfs_fs_info *fs_info)
 	fs_info->delayed_block_rsv.space_info = space_info;
 	fs_info->delayed_refs_rsv.space_info = space_info;
 
+	/*
+	 * Our various recovery options can leave us with NULL roots, so check
+	 * here and just bail before we go dereferencing NULLs everywhere.
+	 */
+	if (!fs_info->extent_root || !fs_info->csum_root ||
+	    !fs_info->dev_root || !fs_info->chunk_root || !fs_info->tree_root)
+		return;
+
 	fs_info->extent_root->block_rsv = &fs_info->delayed_refs_rsv;
 	fs_info->csum_root->block_rsv = &fs_info->delayed_refs_rsv;
 	fs_info->dev_root->block_rsv = &fs_info->global_block_rsv;

fs/btrfs/compression.c

@@ -150,7 +150,7 @@ static int check_compressed_csum(struct btrfs_inode *inode, struct bio *bio,
 	struct compressed_bio *cb = bio->bi_private;
 	u8 *cb_sum = cb->sums;
 
-	if (inode->flags & BTRFS_INODE_NODATASUM)
+	if (!fs_info->csum_root || (inode->flags & BTRFS_INODE_NODATASUM))
 		return 0;
 
 	shash->tfm = fs_info->csum_shash;

fs/btrfs/ctree.h

@@ -1298,6 +1298,7 @@ static inline u32 BTRFS_MAX_XATTR_SIZE(const struct btrfs_fs_info *info)
 #define BTRFS_MOUNT_NOLOGREPLAY		(1 << 27)
 #define BTRFS_MOUNT_REF_VERIFY		(1 << 28)
 #define BTRFS_MOUNT_DISCARD_ASYNC	(1 << 29)
+#define BTRFS_MOUNT_IGNOREBADROOTS	(1 << 30)
 
 #define BTRFS_DEFAULT_COMMIT_INTERVAL	(30)
 #define BTRFS_DEFAULT_MAX_INLINE	(2048)

fs/btrfs/disk-io.c

@@ -2307,30 +2307,39 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info)
 
 	root = btrfs_read_tree_root(tree_root, &location);
 	if (IS_ERR(root)) {
-		ret = PTR_ERR(root);
-		goto out;
+		if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) {
+			ret = PTR_ERR(root);
+			goto out;
+		}
+	} else {
+		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
+		fs_info->extent_root = root;
 	}
-	set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
-	fs_info->extent_root = root;
 
 	location.objectid = BTRFS_DEV_TREE_OBJECTID;
 	root = btrfs_read_tree_root(tree_root, &location);
 	if (IS_ERR(root)) {
-		ret = PTR_ERR(root);
-		goto out;
+		if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) {
+			ret = PTR_ERR(root);
+			goto out;
+		}
+	} else {
+		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
+		fs_info->dev_root = root;
+		btrfs_init_devices_late(fs_info);
 	}
-	set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
-	fs_info->dev_root = root;
-	btrfs_init_devices_late(fs_info);
 
 	location.objectid = BTRFS_CSUM_TREE_OBJECTID;
 	root = btrfs_read_tree_root(tree_root, &location);
 	if (IS_ERR(root)) {
-		ret = PTR_ERR(root);
-		goto out;
+		if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) {
+			ret = PTR_ERR(root);
+			goto out;
+		}
+	} else {
+		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
+		fs_info->csum_root = root;
 	}
-	set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
-	fs_info->csum_root = root;
 
 	/*
 	 * This tree can share blocks with some other fs tree during relocation
@@ -2339,11 +2348,14 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info)
 	root = btrfs_get_fs_root(tree_root->fs_info,
 				 BTRFS_DATA_RELOC_TREE_OBJECTID, true);
 	if (IS_ERR(root)) {
-		ret = PTR_ERR(root);
-		goto out;
+		if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) {
+			ret = PTR_ERR(root);
+			goto out;
+		}
+	} else {
+		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
+		fs_info->data_reloc_root = root;
 	}
-	set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
-	fs_info->data_reloc_root = root;
 
 	location.objectid = BTRFS_QUOTA_TREE_OBJECTID;
 	root = btrfs_read_tree_root(tree_root, &location);
@@ -2356,9 +2368,11 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info)
 	location.objectid = BTRFS_UUID_TREE_OBJECTID;
 	root = btrfs_read_tree_root(tree_root, &location);
 	if (IS_ERR(root)) {
-		ret = PTR_ERR(root);
-		if (ret != -ENOENT)
-			goto out;
+		if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) {
+			ret = PTR_ERR(root);
+			if (ret != -ENOENT)
+				goto out;
+		}
 	} else {
 		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
 		fs_info->uuid_root = root;
@@ -2368,11 +2382,14 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info)
 		location.objectid = BTRFS_FREE_SPACE_TREE_OBJECTID;
 		root = btrfs_read_tree_root(tree_root, &location);
 		if (IS_ERR(root)) {
-			ret = PTR_ERR(root);
-			goto out;
+			if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) {
+				ret = PTR_ERR(root);
+				goto out;
+			}
+		}  else {
+			set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
+			fs_info->free_space_root = root;
 		}
-		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
-		fs_info->free_space_root = root;
 	}
 
 	return 0;

fs/btrfs/file-item.c

@@ -272,7 +272,7 @@ blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
 	int count = 0;
 	u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
 
-	if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)
+	if (!fs_info->csum_root || (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM))
 		return BLK_STS_OK;
 
 	path = btrfs_alloc_path();

fs/btrfs/inode.c

@@ -2187,7 +2187,8 @@ blk_status_t btrfs_submit_data_bio(struct inode *inode, struct bio *bio,
 	int skip_sum;
 	int async = !atomic_read(&BTRFS_I(inode)->sync_writers);
 
-	skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
+	skip_sum = (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM) ||
+		   !fs_info->csum_root;
 
 	if (btrfs_is_free_space_inode(BTRFS_I(inode)))
 		metadata = BTRFS_WQ_ENDIO_FREE_SPACE;
@@ -2902,6 +2903,9 @@ int btrfs_verify_data_csum(struct btrfs_io_bio *io_bio, u64 phy_offset,
 	if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)
 		return 0;
 
+	if (!root->fs_info->csum_root)
+		return 0;
+
 	if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID &&
 	    test_range_bit(io_tree, start, end, EXTENT_NODATASUM, 1, NULL)) {
 		clear_extent_bits(io_tree, start, end, EXTENT_NODATASUM);

fs/btrfs/super.c

@@ -360,6 +360,7 @@ enum {
 	Opt_rescue,
 	Opt_usebackuproot,
 	Opt_nologreplay,
+	Opt_ignorebadroots,
 
 	/* Deprecated options */
 	Opt_recovery,
@@ -455,6 +456,8 @@ static const match_table_t tokens = {
 static const match_table_t rescue_tokens = {
 	{Opt_usebackuproot, "usebackuproot"},
 	{Opt_nologreplay, "nologreplay"},
+	{Opt_ignorebadroots, "ignorebadroots"},
+	{Opt_ignorebadroots, "ibadroots"},
 	{Opt_err, NULL},
 };
 
@@ -498,6 +501,10 @@ static int parse_rescue_options(struct btrfs_fs_info *info, const char *options)
 			btrfs_set_and_info(info, NOLOGREPLAY,
 					   "disabling log replay at mount time");
 			break;
+		case Opt_ignorebadroots:
+			btrfs_set_and_info(info, IGNOREBADROOTS,
+					   "ignoring bad roots");
+			break;
 		case Opt_err:
 			btrfs_info(info, "unrecognized rescue option '%s'", p);
 			ret = -EINVAL;
@@ -983,7 +990,8 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 	if (new_flags & SB_RDONLY)
 		goto out;
 
-	if (check_ro_option(info, BTRFS_MOUNT_NOLOGREPLAY, "nologreplay"))
+	if (check_ro_option(info, BTRFS_MOUNT_NOLOGREPLAY, "nologreplay") ||
+	    check_ro_option(info, BTRFS_MOUNT_IGNOREBADROOTS, "ignorebadroots"))
 		ret = -EINVAL;
 out:
 	if (btrfs_fs_compat_ro(info, FREE_SPACE_TREE) &&
@@ -1439,6 +1447,8 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 		print_rescue_option(seq, "nologreplay", &printed);
 	if (btrfs_test_opt(info, USEBACKUPROOT))
 		print_rescue_option(seq, "usebackuproot", &printed);
+	if (btrfs_test_opt(info, IGNOREBADROOTS))
+		print_rescue_option(seq, "ignorebadroots", &printed);
 	if (btrfs_test_opt(info, FLUSHONCOMMIT))
 		seq_puts(seq, ",flushoncommit");
 	if (btrfs_test_opt(info, DISCARD_SYNC))

fs/btrfs/sysfs.c

@@ -332,6 +332,7 @@ BTRFS_ATTR(static_feature, send_stream_version, send_stream_version_show);
 static const char *rescue_opts[] = {
 	"usebackuproot",
 	"nologreplay",
+	"ignorebadroots",
 };
 
 static ssize_t supported_rescue_options_show(struct kobject *kobj,

fs/btrfs/volumes.c

@@ -7659,6 +7659,19 @@ int btrfs_verify_dev_extents(struct btrfs_fs_info *fs_info)
 	u64 prev_dev_ext_end = 0;
 	int ret = 0;
 
+	/*
+	 * We don't have a dev_root because we mounted with ignorebadroots and
+	 * failed to load the root, so we want to skip the verification in this
+	 * case for sure.
+	 *
+	 * However if the dev root is fine, but the tree itself is corrupted
+	 * we'd still fail to mount.  This verification is only to make sure
+	 * writes can happen safely, so instead just bypass this check
+	 * completely in the case of IGNOREBADROOTS.
+	 */
+	if (btrfs_test_opt(fs_info, IGNOREBADROOTS))
+		return 0;
+
 	key.objectid = 1;
 	key.type = BTRFS_DEV_EXTENT_KEY;
 	key.offset = 0;