btrfs: Validate child tree block's level and first key

We have several reports about node pointer points to incorrect child
tree blocks, which could have even wrong owner and level but still with
valid generation and checksum.

Although btrfs check could handle it and print error message like:
leaf parent key incorrect 60670574592

Kernel doesn't have enough check on this type of corruption correctly.
At least add such check to read_tree_block() and btrfs_read_buffer(),
where we need two new parameters @level and @first_key to verify the
child tree block.

The new @level check is mandatory and all call sites are already
modified to extract expected level from its call chain.

While @first_key is optional, the following call sites are skipping such
check:
1) Root node/leaf
   As ROOT_ITEM doesn't contain the first key, skip @first_key check.
2) Direct backref
   Only parent bytenr and level is known and we need to resolve the key
   all by ourselves, skip @first_key check.

Another note of this verification is, it needs extra info from nodeptr
or ROOT_ITEM, so it can't fit into current tree-checker framework, which
is limited to node/leaf boundary.

Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 17 insertions, 11 deletions

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 70afd1085033..c91babc6aa4b 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -286,7 +286,7 @@ struct walk_control {
 	 * inside it
 	 */
 	int (*process_func)(struct btrfs_root *log, struct extent_buffer *eb,
-			    struct walk_control *wc, u64 gen);
+			    struct walk_control *wc, u64 gen, int level);
 };
 
 /*
@@ -294,7 +294,7 @@ struct walk_control {
  */
 static int process_one_buffer(struct btrfs_root *log,
 			      struct extent_buffer *eb,
-			      struct walk_control *wc, u64 gen)
+			      struct walk_control *wc, u64 gen, int level)
 {
 	struct btrfs_fs_info *fs_info = log->fs_info;
 	int ret = 0;
@@ -304,7 +304,7 @@ static int process_one_buffer(struct btrfs_root *log,
 	 * pin down any logged extents, so we have to read the block.
 	 */
 	if (btrfs_fs_incompat(fs_info, MIXED_GROUPS)) {
-		ret = btrfs_read_buffer(eb, gen);
+		ret = btrfs_read_buffer(eb, gen, level, NULL);
 		if (ret)
 			return ret;
 	}
@@ -2406,17 +2406,16 @@ out:
  * back refs).
  */
 static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb,
-			     struct walk_control *wc, u64 gen)
+			     struct walk_control *wc, u64 gen, int level)
 {
 	int nritems;
 	struct btrfs_path *path;
 	struct btrfs_root *root = wc->replay_dest;
 	struct btrfs_key key;
-	int level;
 	int i;
 	int ret;
 
-	ret = btrfs_read_buffer(eb, gen);
+	ret = btrfs_read_buffer(eb, gen, level, NULL);
 	if (ret)
 		return ret;
 
@@ -2533,6 +2532,8 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 	WARN_ON(*level >= BTRFS_MAX_LEVEL);
 
 	while (*level > 0) {
+		struct btrfs_key first_key;
+
 		WARN_ON(*level < 0);
 		WARN_ON(*level >= BTRFS_MAX_LEVEL);
 		cur = path->nodes[*level];
@@ -2545,6 +2546,7 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 
 		bytenr = btrfs_node_blockptr(cur, path->slots[*level]);
 		ptr_gen = btrfs_node_ptr_generation(cur, path->slots[*level]);
+		btrfs_node_key_to_cpu(cur, &first_key, path->slots[*level]);
 		blocksize = fs_info->nodesize;
 
 		parent = path->nodes[*level];
@@ -2555,7 +2557,8 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 			return PTR_ERR(next);
 
 		if (*level == 1) {
-			ret = wc->process_func(root, next, wc, ptr_gen);
+			ret = wc->process_func(root, next, wc, ptr_gen,
+					       *level - 1);
 			if (ret) {
 				free_extent_buffer(next);
 				return ret;
@@ -2563,7 +2566,8 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 
 			path->slots[*level]++;
 			if (wc->free) {
-				ret = btrfs_read_buffer(next, ptr_gen);
+				ret = btrfs_read_buffer(next, ptr_gen,
+							*level - 1, &first_key);
 				if (ret) {
 					free_extent_buffer(next);
 					return ret;
@@ -2593,7 +2597,7 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 			free_extent_buffer(next);
 			continue;
 		}
-		ret = btrfs_read_buffer(next, ptr_gen);
+		ret = btrfs_read_buffer(next, ptr_gen, *level - 1, &first_key);
 		if (ret) {
 			free_extent_buffer(next);
 			return ret;
@@ -2643,7 +2647,8 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans,
 
 			root_owner = btrfs_header_owner(parent);
 			ret = wc->process_func(root, path->nodes[*level], wc,
-				 btrfs_header_generation(path->nodes[*level]));
+				 btrfs_header_generation(path->nodes[*level]),
+				 *level);
 			if (ret)
 				return ret;
 
@@ -2725,7 +2730,8 @@ static int walk_log_tree(struct btrfs_trans_handle *trans,
 	/* was the root node processed? if not, catch it here */
 	if (path->nodes[orig_level]) {
 		ret = wc->process_func(log, path->nodes[orig_level], wc,
-			 btrfs_header_generation(path->nodes[orig_level]));
+			 btrfs_header_generation(path->nodes[orig_level]),
+			 orig_level);
 		if (ret)
 			goto out;
 		if (wc->free) {