diff options
Diffstat (limited to 'fs/btrfs/ctree.c')
| -rw-r--r-- | fs/btrfs/ctree.c | 834 |
1 files changed, 542 insertions, 292 deletions
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 61b5bcd57b7..aeab453b8e2 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -39,9 +39,8 @@ static int balance_node_right(struct btrfs_trans_handle *trans, struct extent_buffer *src_buf); static void del_ptr(struct btrfs_root *root, struct btrfs_path *path, int level, int slot); -static void tree_mod_log_free_eb(struct btrfs_fs_info *fs_info, +static int tree_mod_log_free_eb(struct btrfs_fs_info *fs_info, struct extent_buffer *eb); -static int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path); struct btrfs_path *btrfs_alloc_path(void) { @@ -225,7 +224,8 @@ static struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root) static void add_root_to_dirty_list(struct btrfs_root *root) { spin_lock(&root->fs_info->trans_lock); - if (root->track_dirty && list_empty(&root->dirty_list)) { + if (test_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state) && + list_empty(&root->dirty_list)) { list_add(&root->dirty_list, &root->fs_info->dirty_cowonly_roots); } @@ -247,9 +247,10 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, int level; struct btrfs_disk_key disk_key; - WARN_ON(root->ref_cows && trans->transid != - root->fs_info->running_transaction->transid); - WARN_ON(root->ref_cows && trans->transid != root->last_trans); + WARN_ON(test_bit(BTRFS_ROOT_REF_COWS, &root->state) && + trans->transid != root->fs_info->running_transaction->transid); + WARN_ON(test_bit(BTRFS_ROOT_REF_COWS, &root->state) && + trans->transid != root->last_trans); level = btrfs_header_level(buf); if (level == 0) @@ -274,7 +275,7 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, else btrfs_set_header_owner(cow, new_root_objectid); - write_extent_buffer(cow, root->fs_info->fsid, btrfs_header_fsid(cow), + write_extent_buffer(cow, root->fs_info->fsid, btrfs_header_fsid(), BTRFS_FSID_SIZE); WARN_ON(btrfs_header_generation(buf) > trans->transid); @@ -355,44 +356,14 @@ static inline void tree_mod_log_write_unlock(struct btrfs_fs_info *fs_info) } /* - * Increment the upper half of tree_mod_seq, set lower half zero. - * - * Must be called with fs_info->tree_mod_seq_lock held. + * Pull a new tree mod seq number for our operation. */ -static inline u64 btrfs_inc_tree_mod_seq_major(struct btrfs_fs_info *fs_info) -{ - u64 seq = atomic64_read(&fs_info->tree_mod_seq); - seq &= 0xffffffff00000000ull; - seq += 1ull << 32; - atomic64_set(&fs_info->tree_mod_seq, seq); - return seq; -} - -/* - * Increment the lower half of tree_mod_seq. - * - * Must be called with fs_info->tree_mod_seq_lock held. The way major numbers - * are generated should not technically require a spin lock here. (Rationale: - * incrementing the minor while incrementing the major seq number is between its - * atomic64_read and atomic64_set calls doesn't duplicate sequence numbers, it - * just returns a unique sequence number as usual.) We have decided to leave - * that requirement in here and rethink it once we notice it really imposes a - * problem on some workload. - */ -static inline u64 btrfs_inc_tree_mod_seq_minor(struct btrfs_fs_info *fs_info) +static inline u64 btrfs_inc_tree_mod_seq(struct btrfs_fs_info *fs_info) { return atomic64_inc_return(&fs_info->tree_mod_seq); } /* - * return the last minor in the previous major tree_mod_seq number - */ -u64 btrfs_tree_mod_seq_prev(u64 seq) -{ - return (seq & 0xffffffff00000000ull) - 1ull; -} - -/* * This adds a new blocker to the tree mod log's blocker list if the @elem * passed does not already have a sequence number set. So when a caller expects * to record tree modifications, it should ensure to set elem->seq to zero @@ -403,19 +374,16 @@ u64 btrfs_tree_mod_seq_prev(u64 seq) u64 btrfs_get_tree_mod_seq(struct btrfs_fs_info *fs_info, struct seq_list *elem) { - u64 seq; - tree_mod_log_write_lock(fs_info); spin_lock(&fs_info->tree_mod_seq_lock); if (!elem->seq) { - elem->seq = btrfs_inc_tree_mod_seq_major(fs_info); + elem->seq = btrfs_inc_tree_mod_seq(fs_info); list_add_tail(&elem->list, &fs_info->tree_mod_seq_list); } - seq = btrfs_inc_tree_mod_seq_minor(fs_info); spin_unlock(&fs_info->tree_mod_seq_lock); tree_mod_log_write_unlock(fs_info); - return seq; + return elem->seq; } void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info, @@ -475,6 +443,8 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info, * the index is the shifted logical of the *new* root node for root replace * operations, or the shifted logical of the affected block for all other * operations. + * + * Note: must be called with write lock (tree_mod_log_write_lock). */ static noinline int __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm) @@ -483,27 +453,10 @@ __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm) struct rb_node **new; struct rb_node *parent = NULL; struct tree_mod_elem *cur; - int ret = 0; BUG_ON(!tm); - tree_mod_log_write_lock(fs_info); - if (list_empty(&fs_info->tree_mod_seq_list)) { - tree_mod_log_write_unlock(fs_info); - /* - * Ok we no longer care about logging modifications, free up tm - * and return 0. Any callers shouldn't be using tm after - * calling tree_mod_log_insert, but if they do we can just - * change this to return a special error code to let the callers - * do their own thing. - */ - kfree(tm); - return 0; - } - - spin_lock(&fs_info->tree_mod_seq_lock); - tm->seq = btrfs_inc_tree_mod_seq_minor(fs_info); - spin_unlock(&fs_info->tree_mod_seq_lock); + tm->seq = btrfs_inc_tree_mod_seq(fs_info); tm_root = &fs_info->tree_mod_log; new = &tm_root->rb_node; @@ -518,18 +471,13 @@ __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm) new = &((*new)->rb_left); else if (cur->seq > tm->seq) new = &((*new)->rb_right); - else { - ret = -EEXIST; - kfree(tm); - goto out; - } + else + return -EEXIST; } rb_link_node(&tm->node, parent, new); rb_insert_color(&tm->node, tm_root); -out: - tree_mod_log_write_unlock(fs_info); - return ret; + return 0; } /* @@ -545,19 +493,38 @@ static inline int tree_mod_dont_log(struct btrfs_fs_info *fs_info, return 1; if (eb && btrfs_header_level(eb) == 0) return 1; + + tree_mod_log_write_lock(fs_info); + if (list_empty(&(fs_info)->tree_mod_seq_list)) { + tree_mod_log_write_unlock(fs_info); + return 1; + } + return 0; } -static inline int -__tree_mod_log_insert_key(struct btrfs_fs_info *fs_info, - struct extent_buffer *eb, int slot, - enum mod_log_op op, gfp_t flags) +/* Similar to tree_mod_dont_log, but doesn't acquire any locks. */ +static inline int tree_mod_need_log(const struct btrfs_fs_info *fs_info, + struct extent_buffer *eb) +{ + smp_mb(); + if (list_empty(&(fs_info)->tree_mod_seq_list)) + return 0; + if (eb && btrfs_header_level(eb) == 0) + return 0; + + return 1; +} + +static struct tree_mod_elem * +alloc_tree_mod_elem(struct extent_buffer *eb, int slot, + enum mod_log_op op, gfp_t flags) { struct tree_mod_elem *tm; tm = kzalloc(sizeof(*tm), flags); if (!tm) - return -ENOMEM; + return NULL; tm->index = eb->start >> PAGE_CACHE_SHIFT; if (op != MOD_LOG_KEY_ADD) { @@ -567,8 +534,9 @@ __tree_mod_log_insert_key(struct btrfs_fs_info *fs_info, tm->op = op; tm->slot = slot; tm->generation = btrfs_node_ptr_generation(eb, slot); + RB_CLEAR_NODE(&tm->node); - return __tree_mod_log_insert(fs_info, tm); + return tm; } static noinline int @@ -576,10 +544,27 @@ tree_mod_log_insert_key(struct btrfs_fs_info *fs_info, struct extent_buffer *eb, int slot, enum mod_log_op op, gfp_t flags) { - if (tree_mod_dont_log(fs_info, eb)) + struct tree_mod_elem *tm; + int ret; + + if (!tree_mod_need_log(fs_info, eb)) return 0; - return __tree_mod_log_insert_key(fs_info, eb, slot, op, flags); + tm = alloc_tree_mod_elem(eb, slot, op, flags); + if (!tm) + return -ENOMEM; + + if (tree_mod_dont_log(fs_info, eb)) { + kfree(tm); + return 0; + } + + ret = __tree_mod_log_insert(fs_info, tm); + tree_mod_log_write_unlock(fs_info); + if (ret) + kfree(tm); + + return ret; } static noinline int @@ -587,53 +572,95 @@ tree_mod_log_insert_move(struct btrfs_fs_info *fs_info, struct extent_buffer *eb, int dst_slot, int src_slot, int nr_items, gfp_t flags) { - struct tree_mod_elem *tm; - int ret; + struct tree_mod_elem *tm = NULL; + struct tree_mod_elem **tm_list = NULL; + int ret = 0; int i; + int locked = 0; - if (tree_mod_dont_log(fs_info, eb)) + if (!tree_mod_need_log(fs_info, eb)) return 0; + tm_list = kzalloc(nr_items * sizeof(struct tree_mod_elem *), flags); + if (!tm_list) + return -ENOMEM; + + tm = kzalloc(sizeof(*tm), flags); + if (!tm) { + ret = -ENOMEM; + goto free_tms; + } + + tm->index = eb->start >> PAGE_CACHE_SHIFT; + tm->slot = src_slot; + tm->move.dst_slot = dst_slot; + tm->move.nr_items = nr_items; + tm->op = MOD_LOG_MOVE_KEYS; + + for (i = 0; i + dst_slot < src_slot && i < nr_items; i++) { + tm_list[i] = alloc_tree_mod_elem(eb, i + dst_slot, + MOD_LOG_KEY_REMOVE_WHILE_MOVING, flags); + if (!tm_list[i]) { + ret = -ENOMEM; + goto free_tms; + } + } + + if (tree_mod_dont_log(fs_info, eb)) + goto free_tms; + locked = 1; + /* * When we override something during the move, we log these removals. * This can only happen when we move towards the beginning of the * buffer, i.e. dst_slot < src_slot. */ for (i = 0; i + dst_slot < src_slot && i < nr_items; i++) { - ret = __tree_mod_log_insert_key(fs_info, eb, i + dst_slot, - MOD_LOG_KEY_REMOVE_WHILE_MOVING, GFP_NOFS); - BUG_ON(ret < 0); + ret = __tree_mod_log_insert(fs_info, tm_list[i]); + if (ret) + goto free_tms; } - tm = kzalloc(sizeof(*tm), flags); - if (!tm) - return -ENOMEM; + ret = __tree_mod_log_insert(fs_info, tm); + if (ret) + goto free_tms; + tree_mod_log_write_unlock(fs_info); + kfree(tm_list); - tm->index = eb->start >> PAGE_CACHE_SHIFT; - tm->slot = src_slot; - tm->move.dst_slot = dst_slot; - tm->move.nr_items = nr_items; - tm->op = MOD_LOG_MOVE_KEYS; + return 0; +free_tms: + for (i = 0; i < nr_items; i++) { + if (tm_list[i] && !RB_EMPTY_NODE(&tm_list[i]->node)) + rb_erase(&tm_list[i]->node, &fs_info->tree_mod_log); + kfree(tm_list[i]); + } + if (locked) + tree_mod_log_write_unlock(fs_info); + kfree(tm_list); + kfree(tm); - return __tree_mod_log_insert(fs_info, tm); + return ret; } -static inline void -__tree_mod_log_free_eb(struct btrfs_fs_info *fs_info, struct extent_buffer *eb) +static inline int +__tree_mod_log_free_eb(struct btrfs_fs_info *fs_info, + struct tree_mod_elem **tm_list, + int nritems) { - int i; - u32 nritems; + int i, j; int ret; - if (btrfs_header_level(eb) == 0) - return; - - nritems = btrfs_header_nritems(eb); for (i = nritems - 1; i >= 0; i--) { - ret = __tree_mod_log_insert_key(fs_info, eb, i, - MOD_LOG_KEY_REMOVE_WHILE_FREEING, GFP_NOFS); - BUG_ON(ret < 0); + ret = __tree_mod_log_insert(fs_info, tm_list[i]); + if (ret) { + for (j = nritems - 1; j > i; j--) + rb_erase(&tm_list[j]->node, + &fs_info->tree_mod_log); + return ret; + } } + + return 0; } static noinline int @@ -642,17 +669,38 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info, struct extent_buffer *new_root, gfp_t flags, int log_removal) { - struct tree_mod_elem *tm; + struct tree_mod_elem *tm = NULL; + struct tree_mod_elem **tm_list = NULL; + int nritems = 0; + int ret = 0; + int i; - if (tree_mod_dont_log(fs_info, NULL)) + if (!tree_mod_need_log(fs_info, NULL)) return 0; - if (log_removal) - __tree_mod_log_free_eb(fs_info, old_root); + if (log_removal && btrfs_header_level(old_root) > 0) { + nritems = btrfs_header_nritems(old_root); + tm_list = kzalloc(nritems * sizeof(struct tree_mod_elem *), + flags); + if (!tm_list) { + ret = -ENOMEM; + goto free_tms; + } + for (i = 0; i < nritems; i++) { + tm_list[i] = alloc_tree_mod_elem(old_root, i, + MOD_LOG_KEY_REMOVE_WHILE_FREEING, flags); + if (!tm_list[i]) { + ret = -ENOMEM; + goto free_tms; + } + } + } tm = kzalloc(sizeof(*tm), flags); - if (!tm) - return -ENOMEM; + if (!tm) { + ret = -ENOMEM; + goto free_tms; + } tm->index = new_root->start >> PAGE_CACHE_SHIFT; tm->old_root.logical = old_root->start; @@ -660,7 +708,30 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info, tm->generation = btrfs_header_generation(old_root); tm->op = MOD_LOG_ROOT_REPLACE; - return __tree_mod_log_insert(fs_info, tm); + if (tree_mod_dont_log(fs_info, NULL)) + goto free_tms; + + if (tm_list) + ret = __tree_mod_log_free_eb(fs_info, tm_list, nritems); + if (!ret) + ret = __tree_mod_log_insert(fs_info, tm); + + tree_mod_log_write_unlock(fs_info); + if (ret) + goto free_tms; + kfree(tm_list); + + return ret; + +free_tms: + if (tm_list) { + for (i = 0; i < nritems; i++) + kfree(tm_list[i]); + kfree(tm_list); + } + kfree(tm); + + return ret; } static struct tree_mod_elem * @@ -729,31 +800,75 @@ tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq) return __tree_mod_log_search(fs_info, start, min_seq, 0); } -static noinline void +static noinline int tree_mod_log_eb_copy(struct btrfs_fs_info *fs_info, struct extent_buffer *dst, struct extent_buffer *src, unsigned long dst_offset, unsigned long src_offset, int nr_items) { - int ret; + int ret = 0; + struct tree_mod_elem **tm_list = NULL; + struct tree_mod_elem **tm_list_add, **tm_list_rem; int i; + int locked = 0; - if (tree_mod_dont_log(fs_info, NULL)) - return; + if (!tree_mod_need_log(fs_info, NULL)) + return 0; if (btrfs_header_level(dst) == 0 && btrfs_header_level(src) == 0) - return; + return 0; + tm_list = kzalloc(nr_items * 2 * sizeof(struct tree_mod_elem *), + GFP_NOFS); + if (!tm_list) + return -ENOMEM; + + tm_list_add = tm_list; + tm_list_rem = tm_list + nr_items; for (i = 0; i < nr_items; i++) { - ret = __tree_mod_log_insert_key(fs_info, src, - i + src_offset, - MOD_LOG_KEY_REMOVE, GFP_NOFS); - BUG_ON(ret < 0); - ret = __tree_mod_log_insert_key(fs_info, dst, - i + dst_offset, - MOD_LOG_KEY_ADD, - GFP_NOFS); - BUG_ON(ret < 0); + tm_list_rem[i] = alloc_tree_mod_elem(src, i + src_offset, + MOD_LOG_KEY_REMOVE, GFP_NOFS); + if (!tm_list_rem[i]) { + ret = -ENOMEM; + goto free_tms; + } + + tm_list_add[i] = alloc_tree_mod_elem(dst, i + dst_offset, + MOD_LOG_KEY_ADD, GFP_NOFS); + if (!tm_list_add[i]) { + ret = -ENOMEM; + goto free_tms; + } + } + + if (tree_mod_dont_log(fs_info, NULL)) + goto free_tms; + locked = 1; + + for (i = 0; i < nr_items; i++) { + ret = __tree_mod_log_insert(fs_info, tm_list_rem[i]); + if (ret) + goto free_tms; + ret = __tree_mod_log_insert(fs_info, tm_list_add[i]); + if (ret) + goto free_tms; + } + + tree_mod_log_write_unlock(fs_info); + kfree(tm_list); + + return 0; + +free_tms: + for (i = 0; i < nr_items * 2; i++) { + if (tm_list[i] && !RB_EMPTY_NODE(&tm_list[i]->node)) + rb_erase(&tm_list[i]->node, &fs_info->tree_mod_log); + kfree(tm_list[i]); } + if (locked) + tree_mod_log_write_unlock(fs_info); + kfree(tm_list); + + return ret; } static inline void @@ -772,18 +887,58 @@ tree_mod_log_set_node_key(struct btrfs_fs_info *fs_info, { int ret; - ret = __tree_mod_log_insert_key(fs_info, eb, slot, + ret = tree_mod_log_insert_key(fs_info, eb, slot, MOD_LOG_KEY_REPLACE, atomic ? GFP_ATOMIC : GFP_NOFS); BUG_ON(ret < 0); } -static noinline void +static noinline int tree_mod_log_free_eb(struct btrfs_fs_info *fs_info, struct extent_buffer *eb) { + struct tree_mod_elem **tm_list = NULL; + int nritems = 0; + int i; + int ret = 0; + + if (btrfs_header_level(eb) == 0) + return 0; + + if (!tree_mod_need_log(fs_info, NULL)) + return 0; + + nritems = btrfs_header_nritems(eb); + tm_list = kzalloc(nritems * sizeof(struct tree_mod_elem *), + GFP_NOFS); + if (!tm_list) + return -ENOMEM; + + for (i = 0; i < nritems; i++) { + tm_list[i] = alloc_tree_mod_elem(eb, i, + MOD_LOG_KEY_REMOVE_WHILE_FREEING, GFP_NOFS); + if (!tm_list[i]) { + ret = -ENOMEM; + goto free_tms; + } + } + if (tree_mod_dont_log(fs_info, eb)) - return; - __tree_mod_log_free_eb(fs_info, eb); + goto free_tms; + + ret = __tree_mod_log_free_eb(fs_info, tm_list, nritems); + tree_mod_log_write_unlock(fs_info); + if (ret) + goto free_tms; + kfree(tm_list); + + return 0; + +free_tms: + for (i = 0; i < nritems; i++) + kfree(tm_list[i]); + kfree(tm_list); + + return ret; } static noinline void @@ -809,14 +964,14 @@ int btrfs_block_can_be_shared(struct btrfs_root *root, * snapshot and the block was not allocated by tree relocation, * we know the block is not shared. */ - if (root->ref_cows && + if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) && buf != root->node && buf != root->commit_root && (btrfs_header_generation(buf) <= btrfs_root_last_snapshot(&root->root_item) || btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC))) return 1; #ifdef BTRFS_COMPAT_EXTENT_TREE_V0 - if (root->ref_cows && + if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) && btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV) return 1; #endif @@ -958,9 +1113,10 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, btrfs_assert_tree_locked(buf); - WARN_ON(root->ref_cows && trans->transid != - root->fs_info->running_transaction->transid); - WARN_ON(root->ref_cows && trans->transid != root->last_trans); + WARN_ON(test_bit(BTRFS_ROOT_REF_COWS, &root->state) && + trans->transid != root->fs_info->running_transaction->transid); + WARN_ON(test_bit(BTRFS_ROOT_REF_COWS, &root->state) && + trans->transid != root->last_trans); level = btrfs_header_level(buf); @@ -996,7 +1152,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, else btrfs_set_header_owner(cow, root->root_key.objectid); - write_extent_buffer(cow, root->fs_info->fsid, btrfs_header_fsid(cow), + write_extent_buffer(cow, root->fs_info->fsid, btrfs_header_fsid(), BTRFS_FSID_SIZE); ret = update_ref_for_cow(trans, root, buf, cow, &last_ref); @@ -1005,7 +1161,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, return ret; } - if (root->ref_cows) { + if (test_bit(BTRFS_ROOT_REF_COWS, &root->state)) { ret = btrfs_reloc_cow_block(trans, root, buf, cow); if (ret) return ret; @@ -1041,8 +1197,13 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, btrfs_set_node_ptr_generation(parent, parent_slot, trans->transid); btrfs_mark_buffer_dirty(parent); - if (last_ref) - tree_mod_log_free_eb(root->fs_info, buf); + if (last_ref) { + ret = tree_mod_log_free_eb(root->fs_info, buf); + if (ret) { + btrfs_abort_transaction(trans, root, ret); + return ret; + } + } btrfs_free_tree_block(trans, root, buf, parent_start, last_ref); } @@ -1285,11 +1446,10 @@ get_old_root(struct btrfs_root *root, u64 time_seq) free_extent_buffer(eb_root); blocksize = btrfs_level_size(root, old_root->level); old = read_tree_block(root, logical, blocksize, 0); - if (!old || !extent_buffer_uptodate(old)) { + if (WARN_ON(!old || !extent_buffer_uptodate(old))) { free_extent_buffer(old); - pr_warn("btrfs: failed to read tree block %llu from get_old_root\n", - logical); - WARN_ON(1); + btrfs_warn(root->fs_info, + "failed to read tree block %llu from get_old_root", logical); } else { eb = btrfs_clone_extent_buffer(old); free_extent_buffer(old); @@ -1346,6 +1506,10 @@ static inline int should_cow_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf) { +#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS + if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state))) + return 0; +#endif /* ensure we can see the force_cow */ smp_rmb(); @@ -1364,7 +1528,7 @@ static inline int should_cow_block(struct btrfs_trans_handle *trans, !btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN) && !(root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID && btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)) && - !root->force_cow) + !test_bit(BTRFS_ROOT_FORCE_COW, &root->state)) return 0; return 1; } @@ -2463,6 +2627,49 @@ static int key_search(struct extent_buffer *b, struct btrfs_key *key, return 0; } +int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *found_path, + u64 iobjectid, u64 ioff, u8 key_type, + struct btrfs_key *found_key) +{ + int ret; + struct btrfs_key key; + struct extent_buffer *eb; + struct btrfs_path *path; + + key.type = key_type; + key.objectid = iobjectid; + key.offset = ioff; + + if (found_path == NULL) { + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + } else + path = found_path; + + ret = btrfs_search_slot(NULL, fs_root, &key, path, 0, 0); + if ((ret < 0) || (found_key == NULL)) { + if (path != found_path) + btrfs_free_path(path); + return ret; + } + + eb = path->nodes[0]; + if (ret && path->slots[0] >= btrfs_header_nritems(eb)) { + ret = btrfs_next_leaf(fs_root, path); + if (ret) + return ret; + eb = path->nodes[0]; + } + + btrfs_item_key_to_cpu(eb, found_key, path->slots[0]); + if (found_key->type != key.type || + found_key->objectid != key.objectid) + return 1; + + return 0; +} + /* * look for key in the tree. path is filled in with nodes along the way * if key is found, we return zero and you can find the item in the leaf @@ -2496,6 +2703,7 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root lowest_level = p->lowest_level; WARN_ON(lowest_level && ins_len > 0); WARN_ON(p->nodes[0] != NULL); + BUG_ON(!cow && ins_len); if (ins_len < 0) { lowest_unlock = 2; @@ -2533,9 +2741,13 @@ again: * the commit roots are read only * so we always do read locks */ + if (p->need_commit_sem) + down_read(&root->fs_info->commit_root_sem); b = root->commit_root; extent_buffer_get(b); level = btrfs_header_level(b); + if (p->need_commit_sem) + up_read(&root->fs_info->commit_root_sem); if (!p->skip_locking) btrfs_tree_read_lock(b); } else { @@ -2604,8 +2816,6 @@ again: } } cow_done: - BUG_ON(!cow && ins_len); - p->nodes[level] = b; btrfs_clear_path_blocking(p, NULL, 0); @@ -2615,13 +2825,19 @@ cow_done: * It is safe to drop the lock on our parent before we * go through the expensive btree search on b. * - * If cow is true, then we might be changing slot zero, - * which may require changing the parent. So, we can't - * drop the lock until after we know which slot we're - * operating on. + * If we're inserting or deleting (ins_len != 0), then we might + * be changing slot zero, which may require changing the parent. + * So, we can't drop the lock until after we know which slot + * we're operating on. */ - if (!cow) - btrfs_unlock_up_safe(p, level + 1); + if (!ins_len && !p->keep_locks) { + int u = level + 1; + + if (u < BTRFS_MAX_LEVEL && p->locks[u]) { + btrfs_tree_unlock_rw(p->nodes[u], p->locks[u]); + p->locks[u] = 0; + } + } ret = key_search(b, key, level, &prev_cmp, &slot); @@ -2649,7 +2865,7 @@ cow_done: * which means we must have a write lock * on the parent */ - if (slot == 0 && cow && + if (slot == 0 && ins_len && write_lock_level < level + 1) { write_lock_level = level + 1; btrfs_release_path(p); @@ -2758,7 +2974,7 @@ int btrfs_search_old_slot(struct btrfs_root *root, struct btrfs_key *key, int level; int lowest_unlock = 1; u8 lowest_level = 0; - int prev_cmp; + int prev_cmp = -1; lowest_level = p->lowest_level; WARN_ON(p->nodes[0] != NULL); @@ -2769,7 +2985,6 @@ int btrfs_search_old_slot(struct btrfs_root *root, struct btrfs_key *key, } again: - prev_cmp = -1; b = get_old_root(root, time_seq); level = btrfs_header_level(b); p->locks[level] = BTRFS_READ_LOCK; @@ -2787,6 +3002,11 @@ again: */ btrfs_unlock_up_safe(p, level + 1); + /* + * Since we can unwind eb's we want to do a real search every + * time. + */ + prev_cmp = -1; ret = key_search(b, key, level, &prev_cmp, &slot); if (level != 0) { @@ -2898,7 +3118,9 @@ again: if (ret < 0) return ret; if (!ret) { - p->slots[0] = btrfs_header_nritems(leaf) - 1; + leaf = p->nodes[0]; + if (p->slots[0] == btrfs_header_nritems(leaf)) + p->slots[0]--; return 0; } if (!return_any) @@ -3019,8 +3241,12 @@ static int push_node_left(struct btrfs_trans_handle *trans, } else push_items = min(src_nritems - 8, push_items); - tree_mod_log_eb_copy(root->fs_info, dst, src, dst_nritems, 0, - push_items); + ret = tree_mod_log_eb_copy(root->fs_info, dst, src, dst_nritems, 0, + push_items); + if (ret) { + btrfs_abort_transaction(trans, root, ret); + return ret; + } copy_extent_buffer(dst, src, btrfs_node_key_ptr_offset(dst_nritems), btrfs_node_key_ptr_offset(0), @@ -3090,8 +3316,12 @@ static int balance_node_right(struct btrfs_trans_handle *trans, (dst_nritems) * sizeof(struct btrfs_key_ptr)); - tree_mod_log_eb_copy(root->fs_info, dst, src, 0, - src_nritems - push_items, push_items); + ret = tree_mod_log_eb_copy(root->fs_info, dst, src, 0, + src_nritems - push_items, push_items); + if (ret) { + btrfs_abort_transaction(trans, root, ret); + return ret; + } copy_extent_buffer(dst, src, btrfs_node_key_ptr_offset(0), btrfs_node_key_ptr_offset(src_nritems - push_items), @@ -3148,7 +3378,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans, btrfs_set_header_backref_rev(c, BTRFS_MIXED_BACKREF_REV); btrfs_set_header_owner(c, root->root_key.objectid); - write_extent_buffer(c, root->fs_info->fsid, btrfs_header_fsid(c), + write_extent_buffer(c, root->fs_info->fsid, btrfs_header_fsid(), BTRFS_FSID_SIZE); write_extent_buffer(c, root->fs_info->chunk_tree_uuid, @@ -3287,12 +3517,17 @@ static noinline int split_node(struct btrfs_trans_handle *trans, btrfs_set_header_backref_rev(split, BTRFS_MIXED_BACKREF_REV); btrfs_set_header_owner(split, root->root_key.objectid); write_extent_buffer(split, root->fs_info->fsid, - btrfs_header_fsid(split), BTRFS_FSID_SIZE); + btrfs_header_fsid(), BTRFS_FSID_SIZE); write_extent_buffer(split, root->fs_info->chunk_tree_uuid, btrfs_header_chunk_tree_uuid(split), BTRFS_UUID_SIZE); - tree_mod_log_eb_copy(root->fs_info, split, c, 0, mid, c_nritems - mid); + ret = tree_mod_log_eb_copy(root->fs_info, split, c, 0, + mid, c_nritems - mid); + if (ret) { + btrfs_abort_transaction(trans, root, ret); + return ret; + } copy_extent_buffer(split, c, btrfs_node_key_ptr_offset(0), btrfs_node_key_ptr_offset(mid), @@ -3337,8 +3572,8 @@ static int leaf_space_used(struct extent_buffer *l, int start, int nr) if (!nr) return 0; btrfs_init_map_token(&token); - start_item = btrfs_item_nr(l, start); - end_item = btrfs_item_nr(l, end); + start_item = btrfs_item_nr(start); + end_item = btrfs_item_nr(end); data_len = btrfs_token_item_offset(l, start_item, &token) + btrfs_token_item_size(l, start_item, &token); data_len = data_len - btrfs_token_item_offset(l, end_item, &token); @@ -3359,8 +3594,8 @@ noinline int btrfs_leaf_free_space(struct btrfs_root *root, int ret; ret = BTRFS_LEAF_DATA_SIZE(root) - leaf_space_used(leaf, 0, nritems); if (ret < 0) { - printk(KERN_CRIT "leaf free space ret %d, leaf data size %lu, " - "used %d nritems %d\n", + btrfs_crit(root->fs_info, + "leaf free space ret %d, leaf data size %lu, used %d nritems %d", ret, (unsigned long) BTRFS_LEAF_DATA_SIZE(root), leaf_space_used(leaf, 0, nritems), nritems); } @@ -3406,7 +3641,7 @@ static noinline int __push_leaf_right(struct btrfs_trans_handle *trans, slot = path->slots[1]; i = left_nritems - 1; while (i >= nr) { - item = btrfs_item_nr(left, i); + item = btrfs_item_nr(i); if (!empty && push_items > 0) { if (path->slots[0] > i) @@ -3470,7 +3705,7 @@ static noinline int __push_leaf_right(struct btrfs_trans_handle *trans, btrfs_set_header_nritems(right, right_nritems); push_space = BTRFS_LEAF_DATA_SIZE(root); for (i = 0; i < right_nritems; i++) { - item = btrfs_item_nr(right, i); + item = btrfs_item_nr(i); push_space -= btrfs_token_item_size(right, item, &token); btrfs_set_token_item_offset(right, item, push_space, &token); } @@ -3568,6 +3803,19 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root if (left_nritems == 0) goto out_unlock; + if (path->slots[0] == left_nritems && !empty) { + /* Key greater than all keys in the leaf, right neighbor has + * enough room for it and we're not emptying our leaf to delete + * it, therefore use right neighbor to insert the new item and + * no need to touch/dirty our left leaft. */ + btrfs_tree_unlock(left); + free_extent_buffer(left); + path->nodes[0] = right; + path->slots[0] = 0; + path->slots[1]++; + return 0; + } + return __push_leaf_right(trans, root, path, min_data_size, empty, right, free_space, left_nritems, min_slot); out_unlock: @@ -3612,7 +3860,7 @@ static noinline int __push_leaf_left(struct btrfs_trans_handle *trans, nr = min(right_nritems - 1, max_slot); for (i = 0; i < nr; i++) { - item = btrfs_item_nr(right, i); + item = btrfs_item_nr(i); if (!empty && push_items > 0) { if (path->slots[0] < i) @@ -3639,8 +3887,7 @@ static noinline int __push_leaf_left(struct btrfs_trans_handle *trans, ret = 1; goto out; } - if (!empty && push_items == btrfs_header_nritems(right)) - WARN_ON(1); + WARN_ON(!empty && push_items == btrfs_header_nritems(right)); /* push data from right to left */ copy_extent_buffer(left, right, @@ -3663,7 +3910,7 @@ static noinline int __push_leaf_left(struct btrfs_trans_handle *trans, for (i = old_left_nritems; i < old_left_nritems + push_items; i++) { u32 ioff; - item = btrfs_item_nr(left, i); + item = btrfs_item_nr(i); ioff = btrfs_token_item_offset(left, item, &token); btrfs_set_token_item_offset(left, item, @@ -3694,7 +3941,7 @@ static noinline int __push_leaf_left(struct btrfs_trans_handle *trans, btrfs_set_header_nritems(right, right_nritems); push_space = BTRFS_LEAF_DATA_SIZE(root); for (i = 0; i < right_nritems; i++) { - item = btrfs_item_nr(right, i); + item = btrfs_item_nr(i); push_space = push_space - btrfs_token_item_size(right, item, &token); @@ -3835,7 +4082,7 @@ static noinline void copy_for_split(struct btrfs_trans_handle *trans, btrfs_item_end_nr(l, mid); for (i = 0; i < nritems; i++) { - struct btrfs_item *item = btrfs_item_nr(right, i); + struct btrfs_item *item = btrfs_item_nr(i); u32 ioff; ioff = btrfs_token_item_offset(right, item, &token); @@ -3885,14 +4132,17 @@ static noinline int push_for_double_split(struct btrfs_trans_handle *trans, int progress = 0; int slot; u32 nritems; + int space_needed = data_size; slot = path->slots[0]; + if (slot < btrfs_header_nritems(path->nodes[0])) + space_needed -= btrfs_leaf_free_space(root, path->nodes[0]); /* * try to push all the items after our slot into the * right leaf */ - ret = push_leaf_right(trans, root, path, 1, data_size, 0, slot); + ret = push_leaf_right(trans, root, path, 1, space_needed, 0, slot); if (ret < 0) return ret; @@ -3912,7 +4162,7 @@ static noinline int push_for_double_split(struct btrfs_trans_handle *trans, /* try to push all the items before our slot into the next leaf */ slot = path->slots[0]; - ret = push_leaf_left(trans, root, path, 1, data_size, 0, slot); + ret = push_leaf_left(trans, root, path, 1, space_needed, 0, slot); if (ret < 0) return ret; @@ -3956,13 +4206,18 @@ static noinline int split_leaf(struct btrfs_trans_handle *trans, /* first try to make some room by pushing left and right */ if (data_size && path->nodes[1]) { - wret = push_leaf_right(trans, root, path, data_size, - data_size, 0, 0); + int space_needed = data_size; + + if (slot < btrfs_header_nritems(l)) + space_needed -= btrfs_leaf_free_space(root, l); + + wret = push_leaf_right(trans, root, path, space_needed, + space_needed, 0, 0); if (wret < 0) return wret; if (wret) { - wret = push_leaf_left(trans, root, path, data_size, - data_size, 0, (u32)-1); + wret = push_leaf_left(trans, root, path, space_needed, + space_needed, 0, (u32)-1); if (wret < 0) return wret; } @@ -4016,7 +4271,7 @@ again: data_size > BTRFS_LEAF_DATA_SIZE(root)) { if (data_size && !tried_avoid_double) goto push_for_double; - split = 2 ; + split = 2; } } } @@ -4042,7 +4297,7 @@ again: btrfs_set_header_owner(right, root->root_key.objectid); btrfs_set_header_level(right, 0); write_extent_buffer(right, root->fs_info->fsid, - btrfs_header_fsid(right), BTRFS_FSID_SIZE); + btrfs_header_fsid(), BTRFS_FSID_SIZE); write_extent_buffer(right, root->fs_info->chunk_tree_uuid, btrfs_header_chunk_tree_uuid(right), @@ -4177,7 +4432,7 @@ static noinline int split_item(struct btrfs_trans_handle *trans, btrfs_set_path_blocking(path); - item = btrfs_item_nr(leaf, path->slots[0]); + item = btrfs_item_nr(path->slots[0]); orig_offset = btrfs_item_offset(leaf, item); item_size = btrfs_item_size(leaf, item); @@ -4200,7 +4455,7 @@ static noinline int split_item(struct btrfs_trans_handle *trans, btrfs_cpu_key_to_disk(&disk_key, new_key); btrfs_set_item_key(leaf, &disk_key, slot); - new_item = btrfs_item_nr(leaf, slot); + new_item = btrfs_item_nr(slot); btrfs_set_item_offset(leaf, new_item, orig_offset); btrfs_set_item_size(leaf, new_item, item_size - split_offset); @@ -4339,7 +4594,7 @@ void btrfs_truncate_item(struct btrfs_root *root, struct btrfs_path *path, /* first correct the data pointers */ for (i = slot; i < nritems; i++) { u32 ioff; - item = btrfs_item_nr(leaf, i); + item = btrfs_item_nr(i); ioff = btrfs_token_item_offset(leaf, item, &token); btrfs_set_token_item_offset(leaf, item, @@ -4387,7 +4642,7 @@ void btrfs_truncate_item(struct btrfs_root *root, struct btrfs_path *path, fixup_low_keys(root, path, &disk_key, 1); } - item = btrfs_item_nr(leaf, slot); + item = btrfs_item_nr(slot); btrfs_set_item_size(leaf, item, new_size); btrfs_mark_buffer_dirty(leaf); @@ -4430,7 +4685,7 @@ void btrfs_extend_item(struct btrfs_root *root, struct btrfs_path *path, BUG_ON(slot < 0); if (slot >= nritems) { btrfs_print_leaf(root, leaf); - printk(KERN_CRIT "slot %d too large, nritems %d\n", + btrfs_crit(root->fs_info, "slot %d too large, nritems %d", slot, nritems); BUG_ON(1); } @@ -4441,7 +4696,7 @@ void btrfs_extend_item(struct btrfs_root *root, struct btrfs_path *path, /* first correct the data pointers */ for (i = slot; i < nritems; i++) { u32 ioff; - item = btrfs_item_nr(leaf, i); + item = btrfs_item_nr(i); ioff = btrfs_token_item_offset(leaf, item, &token); btrfs_set_token_item_offset(leaf, item, @@ -4455,7 +4710,7 @@ void btrfs_extend_item(struct btrfs_root *root, struct btrfs_path *path, data_end = old_data; old_size = btrfs_item_size_nr(leaf, slot); - item = btrfs_item_nr(leaf, slot); + item = btrfs_item_nr(slot); btrfs_set_item_size(leaf, item, old_size + data_size); btrfs_mark_buffer_dirty(leaf); @@ -4493,7 +4748,7 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path, if (btrfs_leaf_free_space(root, leaf) < total_size) { btrfs_print_leaf(root, leaf); - printk(KERN_CRIT "not enough freespace need %u have %d\n", + btrfs_crit(root->fs_info, "not enough freespace need %u have %d", total_size, btrfs_leaf_free_space(root, leaf)); BUG(); } @@ -4503,7 +4758,7 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path, if (old_data < data_end) { btrfs_print_leaf(root, leaf); - printk(KERN_CRIT "slot %d old_data %d data_end %d\n", + btrfs_crit(root->fs_info, "slot %d old_data %d data_end %d", slot, old_data, data_end); BUG_ON(1); } @@ -4514,7 +4769,7 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path, for (i = slot; i < nritems; i++) { u32 ioff; - item = btrfs_item_nr(leaf, i); + item = btrfs_item_nr( i); ioff = btrfs_token_item_offset(leaf, item, &token); btrfs_set_token_item_offset(leaf, item, ioff - total_data, &token); @@ -4535,7 +4790,7 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path, for (i = 0; i < nr; i++) { btrfs_cpu_key_to_disk(&disk_key, cpu_key + i); btrfs_set_item_key(leaf, &disk_key, slot + i); - item = btrfs_item_nr(leaf, slot + i); + item = btrfs_item_nr(slot + i); btrfs_set_token_item_offset(leaf, item, data_end - data_size[i], &token); data_end -= data_size[i]; @@ -4730,7 +4985,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, for (i = slot + nr; i < nritems; i++) { u32 ioff; - item = btrfs_item_nr(leaf, i); + item = btrfs_item_nr(i); ioff = btrfs_token_item_offset(leaf, item, &token); btrfs_set_token_item_offset(leaf, item, ioff + dsize, &token); @@ -4815,7 +5070,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, * This may release the path, and so you may lose any locks held at the * time you call it. */ -static int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path) +int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path) { struct btrfs_key key; struct btrfs_disk_key found_key; @@ -4823,14 +5078,18 @@ static int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path) btrfs_item_key_to_cpu(path->nodes[0], &key, 0); - if (key.offset > 0) + if (key.offset > 0) { key.offset--; - else if (key.type > 0) + } else if (key.type > 0) { key.type--; - else if (key.objectid > 0) + key.offset = (u64)-1; + } else if (key.objectid > 0) { key.objectid--; - else + key.type = (u8)-1; + key.offset = (u64)-1; + } else { return 1; + } btrfs_release_path(path); ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); @@ -4838,7 +5097,17 @@ static int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path) return ret; btrfs_item_key(path->nodes[0], &found_key, 0); ret = comp_keys(&found_key, &key); - if (ret < 0) + /* + * We might have had an item with the previous key in the tree right + * before we released our path. And after we released our path, that + * item might have been pushed to the first slot (0) of the leaf we + * were holding due to a tree balance. Alternatively, an item with the + * previous key can exist as the only element of a leaf (big fat item). + * Therefore account for these 2 cases, so that our callers (like + * btrfs_previous_item) don't miss an existing item with a key matching + * the previous key we computed above. + */ + if (ret <= 0) return 0; return 1; } @@ -4866,7 +5135,6 @@ static int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path) * was nothing in the tree that matched the search criteria. */ int btrfs_search_forward(struct btrfs_root *root, struct btrfs_key *min_key, - struct btrfs_key *max_key, struct btrfs_path *path, u64 min_trans) { @@ -4911,10 +5179,8 @@ again: * If it is too old, old, skip to the next one. */ while (slot < nritems) { - u64 blockptr; u64 gen; - blockptr = btrfs_node_blockptr(cur, slot); gen = btrfs_node_ptr_generation(cur, slot); if (gen < min_trans) { slot++; @@ -5080,7 +5346,6 @@ int btrfs_compare_trees(struct btrfs_root *left_root, { int ret; int cmp; - struct btrfs_trans_handle *trans = NULL; struct btrfs_path *left_path = NULL; struct btrfs_path *right_path = NULL; struct btrfs_key left_key; @@ -5096,9 +5361,8 @@ int btrfs_compare_trees(struct btrfs_root *left_root, int advance_right; u64 left_blockptr; u64 right_blockptr; - u64 left_start_ctransid; - u64 right_start_ctransid; - u64 ctransid; + u64 left_gen; + u64 right_gen; left_path = btrfs_alloc_path(); if (!left_path) { @@ -5122,21 +5386,6 @@ int btrfs_compare_trees(struct btrfs_root *left_root, right_path->search_commit_root = 1; right_path->skip_locking = 1; - spin_lock(&left_root->root_item_lock); - left_start_ctransid = btrfs_root_ctransid(&left_root->root_item); - spin_unlock(&left_root->root_item_lock); - - spin_lock(&right_root->root_item_lock); - right_start_ctransid = btrfs_root_ctransid(&right_root->root_item); - spin_unlock(&right_root->root_item_lock); - - trans = btrfs_join_transaction(left_root); - if (IS_ERR(trans)) { - ret = PTR_ERR(trans); - trans = NULL; - goto out; - } - /* * Strategy: Go to the first items of both trees. Then do * @@ -5173,6 +5422,7 @@ int btrfs_compare_trees(struct btrfs_root *left_root, * the right if possible or go up and right. */ + down_read(&left_root->fs_info->commit_root_sem); left_level = btrfs_header_level(left_root->commit_root); left_root_level = left_level; left_path->nodes[left_level] = left_root->commit_root; @@ -5182,6 +5432,7 @@ int btrfs_compare_trees(struct btrfs_root *left_root, right_root_level = right_level; right_path->nodes[right_level] = right_root->commit_root; extent_buffer_get(right_path->nodes[right_level]); + up_read(&left_root->fs_info->commit_root_sem); if (left_level == 0) btrfs_item_key_to_cpu(left_path->nodes[left_level], @@ -5200,67 +5451,6 @@ int btrfs_compare_trees(struct btrfs_root *left_root, advance_left = advance_right = 0; while (1) { - /* - * We need to make sure the transaction does not get committed - * while we do anything on commit roots. This means, we need to - * join and leave transactions for every item that we process. - */ - if (trans && btrfs_should_end_transaction(trans, left_root)) { - btrfs_release_path(left_path); - btrfs_release_path(right_path); - - ret = btrfs_end_transaction(trans, left_root); - trans = NULL; - if (ret < 0) - goto out; - } - /* now rejoin the transaction */ - if (!trans) { - trans = btrfs_join_transaction(left_root); - if (IS_ERR(trans)) { - ret = PTR_ERR(trans); - trans = NULL; - goto out; - } - - spin_lock(&left_root->root_item_lock); - ctransid = btrfs_root_ctransid(&left_root->root_item); - spin_unlock(&left_root->root_item_lock); - if (ctransid != left_start_ctransid) - left_start_ctransid = 0; - - spin_lock(&right_root->root_item_lock); - ctransid = btrfs_root_ctransid(&right_root->root_item); - spin_unlock(&right_root->root_item_lock); - if (ctransid != right_start_ctransid) - right_start_ctransid = 0; - - if (!left_start_ctransid || !right_start_ctransid) { - WARN(1, KERN_WARNING - "btrfs: btrfs_compare_tree detected " - "a change in one of the trees while " - "iterating. This is probably a " - "bug.\n"); - ret = -EIO; - goto out; - } - - /* - * the commit root may have changed, so start again - * where we stopped - */ - left_path->lowest_level = left_level; - right_path->lowest_level = right_level; - ret = btrfs_search_slot(NULL, left_root, - &left_key, left_path, 0, 0); - if (ret < 0) - goto out; - ret = btrfs_search_slot(NULL, right_root, - &right_key, right_path, 0, 0); - if (ret < 0) - goto out; - } - if (advance_left && !left_end_reached) { ret = tree_advance(left_root, left_path, &left_level, left_root_level, @@ -5360,7 +5550,14 @@ int btrfs_compare_trees(struct btrfs_root *left_root, right_blockptr = btrfs_node_blockptr( right_path->nodes[right_level], right_path->slots[right_level]); - if (left_blockptr == right_blockptr) { + left_gen = btrfs_node_ptr_generation( + left_path->nodes[left_level], + left_path->slots[left_level]); + right_gen = btrfs_node_ptr_generation( + right_path->nodes[right_level], + right_path->slots[right_level]); + if (left_blockptr == right_blockptr && + left_gen == right_gen) { /* * As we're on a shared block, don't * allow to go deeper. @@ -5383,14 +5580,6 @@ out: btrfs_free_path(left_path); btrfs_free_path(right_path); kfree(tmp_buf); - - if (trans) { - if (!ret) - ret = btrfs_end_transaction(trans, left_root); - else - btrfs_end_transaction(trans, left_root); - } - return ret; } @@ -5529,6 +5718,24 @@ again: ret = 0; goto done; } + /* + * So the above check misses one case: + * - after releasing the path above, someone has removed the item that + * used to be at the very end of the block, and balance between leafs + * gets another one with bigger key.offset to replace it. + * + * This one should be returned as well, or we can get leaf corruption + * later(esp. in __btrfs_drop_extents()). + * + * And a bit more explanation about this check, + * with ret > 0, the key isn't found, the path points to the slot + * where it should be inserted, so the path->slots[0] item must be the + * bigger one. + */ + if (nritems > 0 && ret > 0 && path->slots[0] == nritems - 1) { + ret = 0; + goto done; + } while (level < BTRFS_MAX_LEVEL) { if (!path->nodes[level]) { @@ -5677,3 +5884,46 @@ int btrfs_previous_item(struct btrfs_root *root, } return 1; } + +/* + * search in extent tree to find a previous Metadata/Data extent item with + * min objecitd. + * + * returns 0 if something is found, 1 if nothing was found and < 0 on error + */ +int btrfs_previous_extent_item(struct btrfs_root *root, + struct btrfs_path *path, u64 min_objectid) +{ + struct btrfs_key found_key; + struct extent_buffer *leaf; + u32 nritems; + int ret; + + while (1) { + if (path->slots[0] == 0) { + btrfs_set_path_blocking(path); + ret = btrfs_prev_leaf(root, path); + if (ret != 0) + return ret; + } else { + path->slots[0]--; + } + leaf = path->nodes[0]; + nritems = btrfs_header_nritems(leaf); + if (nritems == 0) + return 1; + if (path->slots[0] == nritems) + path->slots[0]--; + + btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); + if (found_key.objectid < min_objectid) + break; + if (found_key.type == BTRFS_EXTENT_ITEM_KEY || + found_key.type == BTRFS_METADATA_ITEM_KEY) + return 0; + if (found_key.objectid == min_objectid && + found_key.type < BTRFS_EXTENT_ITEM_KEY) + break; + } + return 1; +} |