BUG_ON(ref->key_for_search.type);
BUG_ON(!ref->wanted_disk_byte);
- eb = read_tree_block(fs_info, ref->wanted_disk_byte, 0);
+ eb = read_tree_block(fs_info, ref->wanted_disk_byte, 0,
+ ref->level - 1, NULL);
if (IS_ERR(eb)) {
free_pref(ref);
return PTR_ERR(eb);
ref->level == 0) {
struct extent_buffer *eb;
- eb = read_tree_block(fs_info, ref->parent, 0);
+ eb = read_tree_block(fs_info, ref->parent, 0,
+ ref->level, NULL);
if (IS_ERR(eb)) {
ret = PTR_ERR(eb);
goto out;
struct tree_mod_root *old_root = NULL;
u64 old_generation = 0;
u64 logical;
+ int level;
eb_root = btrfs_read_lock_root_node(root);
tm = __tree_mod_log_oldest_root(eb_root, time_seq);
old_root = &tm->old_root;
old_generation = tm->generation;
logical = old_root->logical;
+ level = old_root->level;
} else {
logical = eb_root->start;
+ level = btrfs_header_level(eb_root);
}
tm = tree_mod_log_search(fs_info, logical, time_seq);
if (old_root && tm && tm->op != MOD_LOG_KEY_REMOVE_WHILE_FREEING) {
btrfs_tree_read_unlock(eb_root);
free_extent_buffer(eb_root);
- old = read_tree_block(fs_info, logical, 0);
+ old = read_tree_block(fs_info, logical, 0, level, NULL);
if (WARN_ON(IS_ERR(old) || !extent_buffer_uptodate(old))) {
if (!IS_ERR(old))
free_extent_buffer(old);
btrfs_set_lock_blocking(parent);
for (i = start_slot; i <= end_slot; i++) {
+ struct btrfs_key first_key;
int close = 1;
btrfs_node_key(parent, &disk_key, i);
progress_passed = 1;
blocknr = btrfs_node_blockptr(parent, i);
gen = btrfs_node_ptr_generation(parent, i);
+ btrfs_node_key_to_cpu(parent, &first_key, i);
if (last_block == 0)
last_block = blocknr;
uptodate = 0;
if (!cur || !uptodate) {
if (!cur) {
- cur = read_tree_block(fs_info, blocknr, gen);
+ cur = read_tree_block(fs_info, blocknr, gen,
+ parent_level - 1,
+ &first_key);
if (IS_ERR(cur)) {
return PTR_ERR(cur);
} else if (!extent_buffer_uptodate(cur)) {
return -EIO;
}
} else if (!uptodate) {
- err = btrfs_read_buffer(cur, gen);
+ err = btrfs_read_buffer(cur, gen,
+ parent_level - 1,&first_key);
if (err) {
free_extent_buffer(cur);
return err;
{
int level = btrfs_header_level(parent);
struct extent_buffer *eb;
+ struct btrfs_key first_key;
if (slot < 0 || slot >= btrfs_header_nritems(parent))
return ERR_PTR(-ENOENT);
BUG_ON(level == 0);
+ btrfs_node_key_to_cpu(parent, &first_key, slot);
eb = read_tree_block(fs_info, btrfs_node_blockptr(parent, slot),
- btrfs_node_ptr_generation(parent, slot));
+ btrfs_node_ptr_generation(parent, slot),
+ level - 1, &first_key);
if (!IS_ERR(eb) && !extent_buffer_uptodate(eb)) {
free_extent_buffer(eb);
eb = ERR_PTR(-EIO);
u64 gen;
struct extent_buffer *b = *eb_ret;
struct extent_buffer *tmp;
+ struct btrfs_key first_key;
int ret;
+ int parent_level;
blocknr = btrfs_node_blockptr(b, slot);
gen = btrfs_node_ptr_generation(b, slot);
+ parent_level = btrfs_header_level(b);
+ btrfs_node_key_to_cpu(b, &first_key, slot);
tmp = find_extent_buffer(fs_info, blocknr);
if (tmp) {
btrfs_set_path_blocking(p);
/* now we're allowed to do a blocking uptodate check */
- ret = btrfs_read_buffer(tmp, gen);
+ ret = btrfs_read_buffer(tmp, gen, parent_level - 1, &first_key);
if (!ret) {
*eb_ret = tmp;
return 0;
btrfs_release_path(p);
ret = -EAGAIN;
- tmp = read_tree_block(fs_info, blocknr, 0);
+ tmp = read_tree_block(fs_info, blocknr, 0, parent_level - 1,
+ &first_key);
if (!IS_ERR(tmp)) {
/*
* If the read above didn't mark this buffer up to date,
return ret;
}
+static int verify_level_key(struct btrfs_fs_info *fs_info,
+ struct extent_buffer *eb, int level,
+ struct btrfs_key *first_key)
+{
+ int found_level;
+ struct btrfs_key found_key;
+ int ret;
+
+ found_level = btrfs_header_level(eb);
+ if (found_level != level) {
+#ifdef CONFIG_BTRFS_DEBUG
+ WARN_ON(1);
+ btrfs_err(fs_info,
+"tree level mismatch detected, bytenr=%llu level expected=%u has=%u",
+ eb->start, level, found_level);
+#endif
+ return -EIO;
+ }
+
+ if (!first_key)
+ return 0;
+
+ if (found_level)
+ btrfs_node_key_to_cpu(eb, &found_key, 0);
+ else
+ btrfs_item_key_to_cpu(eb, &found_key, 0);
+ ret = btrfs_comp_cpu_keys(first_key, &found_key);
+
+#ifdef CONFIG_BTRFS_DEBUG
+ if (ret) {
+ WARN_ON(1);
+ btrfs_err(fs_info,
+"tree first key mismatch detected, bytenr=%llu key expected=(%llu, %u, %llu) has=(%llu, %u, %llu)",
+ eb->start, first_key->objectid, first_key->type,
+ first_key->offset, found_key.objectid,
+ found_key.type, found_key.offset);
+ }
+#endif
+ return ret;
+}
+
/*
* helper to read a given tree block, doing retries as required when
* the checksums don't match and we have alternate mirrors to try.
+ *
+ * @parent_transid: expected transid, skip check if 0
+ * @level: expected level, mandatory check
+ * @first_key: expected key of first slot, skip check if NULL
*/
static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info,
struct extent_buffer *eb,
- u64 parent_transid)
+ u64 parent_transid, int level,
+ struct btrfs_key *first_key)
{
struct extent_io_tree *io_tree;
int failed = 0;
ret = read_extent_buffer_pages(io_tree, eb, WAIT_COMPLETE,
mirror_num);
if (!ret) {
- if (!verify_parent_transid(io_tree, eb,
+ if (verify_parent_transid(io_tree, eb,
parent_transid, 0))
- break;
- else
ret = -EIO;
+ else if (verify_level_key(fs_info, eb, level,
+ first_key))
+ ret = -EUCLEAN;
+ else
+ break;
}
/*
* there is no reason to read the other copies, they won't be
* any less wrong.
*/
- if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags))
+ if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags) ||
+ ret == -EUCLEAN)
break;
num_copies = btrfs_num_copies(fs_info,
buf->start, buf->start + buf->len - 1);
}
+/*
+ * Read tree block at logical address @bytenr and do variant basic but critical
+ * verification.
+ *
+ * @parent_transid: expected transid of this tree block, skip check if 0
+ * @level: expected level, mandatory check
+ * @first_key: expected key in slot 0, skip check if NULL
+ */
struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr,
- u64 parent_transid)
+ u64 parent_transid, int level,
+ struct btrfs_key *first_key)
{
struct extent_buffer *buf = NULL;
int ret;
if (IS_ERR(buf))
return buf;
- ret = btree_read_extent_buffer_pages(fs_info, buf, parent_transid);
+ ret = btree_read_extent_buffer_pages(fs_info, buf, parent_transid,
+ level, first_key);
if (ret) {
free_extent_buffer(buf);
return ERR_PTR(ret);
struct btrfs_path *path;
u64 generation;
int ret;
+ int level;
path = btrfs_alloc_path();
if (!path)
}
generation = btrfs_root_generation(&root->root_item);
+ level = btrfs_root_level(&root->root_item);
root->node = read_tree_block(fs_info,
btrfs_root_bytenr(&root->root_item),
- generation);
+ generation, level, NULL);
if (IS_ERR(root->node)) {
ret = PTR_ERR(root->node);
goto find_fail;
struct btrfs_root *log_tree_root;
struct btrfs_super_block *disk_super = fs_info->super_copy;
u64 bytenr = btrfs_super_log_root(disk_super);
+ int level = btrfs_super_log_root_level(disk_super);
if (fs_devices->rw_devices == 0) {
btrfs_warn(fs_info, "log replay required on RO media");
__setup_root(log_tree_root, fs_info, BTRFS_TREE_LOG_OBJECTID);
log_tree_root->node = read_tree_block(fs_info, bytenr,
- fs_info->generation + 1);
+ fs_info->generation + 1,
+ level, NULL);
if (IS_ERR(log_tree_root->node)) {
btrfs_warn(fs_info, "failed to read log tree");
ret = PTR_ERR(log_tree_root->node);
int num_backups_tried = 0;
int backup_index = 0;
int clear_free_space_tree = 0;
+ int level;
tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
}
generation = btrfs_super_chunk_root_generation(disk_super);
+ level = btrfs_super_chunk_root_level(disk_super);
__setup_root(chunk_root, fs_info, BTRFS_CHUNK_TREE_OBJECTID);
chunk_root->node = read_tree_block(fs_info,
btrfs_super_chunk_root(disk_super),
- generation);
+ generation, level, NULL);
if (IS_ERR(chunk_root->node) ||
!extent_buffer_uptodate(chunk_root->node)) {
btrfs_err(fs_info, "failed to read chunk root");
retry_root_backup:
generation = btrfs_super_generation(disk_super);
+ level = btrfs_super_root_level(disk_super);
tree_root->node = read_tree_block(fs_info,
btrfs_super_root(disk_super),
- generation);
+ generation, level, NULL);
if (IS_ERR(tree_root->node) ||
!extent_buffer_uptodate(tree_root->node)) {
btrfs_warn(fs_info, "failed to read tree root");
__btrfs_btree_balance_dirty(fs_info, 0);
}
-int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid)
+int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid, int level,
+ struct btrfs_key *first_key)
{
struct btrfs_root *root = BTRFS_I(buf->pages[0]->mapping->host)->root;
struct btrfs_fs_info *fs_info = root->fs_info;
- return btree_read_extent_buffer_pages(fs_info, buf, parent_transid);
+ return btree_read_extent_buffer_pages(fs_info, buf, parent_transid,
+ level, first_key);
}
static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info)
struct btrfs_device;
struct btrfs_fs_devices;
-struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info,
- u64 bytenr, u64 parent_transid);
+struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr,
+ u64 parent_transid, int level,
+ struct btrfs_key *first_key);
void readahead_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr);
int reada_tree_block_flagged(struct btrfs_fs_info *fs_info, u64 bytenr,
int mirror_num, struct extent_buffer **eb);
void btrfs_mark_buffer_dirty(struct extent_buffer *buf);
int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
int atomic);
-int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid);
+int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid, int level,
+ struct btrfs_key *first_key);
u32 btrfs_csum_data(const char *data, u32 seed, size_t len);
void btrfs_csum_final(u32 crc, u8 *result);
blk_status_t btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
u64 parent;
u32 blocksize;
struct btrfs_key key;
+ struct btrfs_key first_key;
struct extent_buffer *next;
int level = wc->level;
int reada = 0;
}
bytenr = btrfs_node_blockptr(path->nodes[level], path->slots[level]);
+ btrfs_node_key_to_cpu(path->nodes[level], &first_key,
+ path->slots[level]);
blocksize = fs_info->nodesize;
next = find_extent_buffer(fs_info, bytenr);
if (!next) {
if (reada && level == 1)
reada_walk_down(trans, root, wc, path);
- next = read_tree_block(fs_info, bytenr, generation);
+ next = read_tree_block(fs_info, bytenr, generation, level - 1,
+ &first_key);
if (IS_ERR(next)) {
return PTR_ERR(next);
} else if (!extent_buffer_uptodate(next)) {
btrfs_node_blockptr(c, i));
}
for (i = 0; i < nr; i++) {
- struct extent_buffer *next = read_tree_block(fs_info,
- btrfs_node_blockptr(c, i),
- btrfs_node_ptr_generation(c, i));
+ struct btrfs_key first_key;
+ struct extent_buffer *next;
+
+ btrfs_node_key_to_cpu(c, &first_key, i);
+ next = read_tree_block(fs_info, btrfs_node_blockptr(c, i),
+ btrfs_node_ptr_generation(c, i),
+ level - 1, &first_key);
if (IS_ERR(next)) {
continue;
} else if (!extent_buffer_uptodate(next)) {
return 0;
if (!extent_buffer_uptodate(root_eb)) {
- ret = btrfs_read_buffer(root_eb, root_gen);
+ ret = btrfs_read_buffer(root_eb, root_gen, root_level, NULL);
if (ret)
goto out;
}
level = root_level;
while (level >= 0) {
if (path->nodes[level] == NULL) {
+ struct btrfs_key first_key;
int parent_slot;
u64 child_gen;
u64 child_bytenr;
parent_slot = path->slots[level + 1];
child_bytenr = btrfs_node_blockptr(eb, parent_slot);
child_gen = btrfs_node_ptr_generation(eb, parent_slot);
+ btrfs_node_key_to_cpu(eb, &first_key, parent_slot);
- eb = read_tree_block(fs_info, child_bytenr, child_gen);
+ eb = read_tree_block(fs_info, child_bytenr, child_gen,
+ level, &first_key);
if (IS_ERR(eb)) {
ret = PTR_ERR(eb);
goto out;
while (level >= 0) {
if (level) {
+ struct btrfs_key first_key;
+
block_bytenr = btrfs_node_blockptr(path->nodes[level],
path->slots[level]);
gen = btrfs_node_ptr_generation(path->nodes[level],
path->slots[level]);
- eb = read_tree_block(fs_info, block_bytenr, gen);
+ btrfs_node_key_to_cpu(path->nodes[level], &first_key,
+ path->slots[level]);
+ eb = read_tree_block(fs_info, block_bytenr, gen,
+ level - 1, &first_key);
if (IS_ERR(eb))
return PTR_ERR(eb);
if (!extent_buffer_uptodate(eb)) {
parent = eb;
while (1) {
+ struct btrfs_key first_key;
+
level = btrfs_header_level(parent);
BUG_ON(level < lowest_level);
old_bytenr = btrfs_node_blockptr(parent, slot);
blocksize = fs_info->nodesize;
old_ptr_gen = btrfs_node_ptr_generation(parent, slot);
+ btrfs_node_key_to_cpu(parent, &key, slot);
if (level <= max_level) {
eb = path->nodes[level];
break;
}
- eb = read_tree_block(fs_info, old_bytenr, old_ptr_gen);
+ eb = read_tree_block(fs_info, old_bytenr, old_ptr_gen,
+ level - 1, &first_key);
if (IS_ERR(eb)) {
ret = PTR_ERR(eb);
break;
last_snapshot = btrfs_root_last_snapshot(&root->root_item);
for (i = *level; i > 0; i--) {
+ struct btrfs_key first_key;
+
eb = path->nodes[i];
nritems = btrfs_header_nritems(eb);
while (path->slots[i] < nritems) {
}
bytenr = btrfs_node_blockptr(eb, path->slots[i]);
- eb = read_tree_block(fs_info, bytenr, ptr_gen);
+ btrfs_node_key_to_cpu(eb, &first_key, path->slots[i]);
+ eb = read_tree_block(fs_info, bytenr, ptr_gen, i - 1,
+ &first_key);
if (IS_ERR(eb)) {
return PTR_ERR(eb);
} else if (!extent_buffer_uptodate(eb)) {
path->lowest_level = node->level + 1;
rc->backref_cache.path[node->level] = node;
list_for_each_entry(edge, &node->upper, list[LOWER]) {
+ struct btrfs_key first_key;
+
cond_resched();
upper = edge->node[UPPER];
blocksize = root->fs_info->nodesize;
generation = btrfs_node_ptr_generation(upper->eb, slot);
- eb = read_tree_block(fs_info, bytenr, generation);
+ btrfs_node_key_to_cpu(upper->eb, &first_key, slot);
+ eb = read_tree_block(fs_info, bytenr, generation,
+ upper->level - 1, &first_key);
if (IS_ERR(eb)) {
err = PTR_ERR(eb);
goto next;
struct extent_buffer *eb;
BUG_ON(block->key_ready);
- eb = read_tree_block(fs_info, block->bytenr, block->key.offset);
+ eb = read_tree_block(fs_info, block->bytenr, block->key.offset,
+ block->level, NULL);
if (IS_ERR(eb)) {
return PTR_ERR(eb);
} else if (!extent_buffer_uptodate(eb)) {
* 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);
};
/*
*/
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;
* 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;
}
* 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;
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];
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];
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;
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;
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;
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;
/* 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) {