diff options
Diffstat (limited to 'fs/btrfs')
| -rw-r--r-- | fs/btrfs/backref.c | 34 | ||||
| -rw-r--r-- | fs/btrfs/ctree.c | 10 | ||||
| -rw-r--r-- | fs/btrfs/ctree.h | 6 | ||||
| -rw-r--r-- | fs/btrfs/disk-io.c | 27 | ||||
| -rw-r--r-- | fs/btrfs/disk-io.h | 3 | ||||
| -rw-r--r-- | fs/btrfs/extent-tree.c | 25 | ||||
| -rw-r--r-- | fs/btrfs/ioctl.c | 19 | ||||
| -rw-r--r-- | fs/btrfs/send.c | 62 |
8 files changed, 156 insertions, 30 deletions
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 78556447e1d5..ef66db38cedb 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1454,8 +1454,8 @@ int btrfs_find_all_roots(struct btrfs_trans_handle *trans, * callers (such as fiemap) which want to know whether the extent is * shared but do not need a ref count. * - * This attempts to allocate a transaction in order to account for - * delayed refs, but continues on even when the alloc fails. + * This attempts to attach to the running transaction in order to account for + * delayed refs, but continues on even when no running transaction exists. * * Return: 0 if extent is not shared, 1 if it is shared, < 0 on error. */ @@ -1478,13 +1478,16 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr) tmp = ulist_alloc(GFP_NOFS); roots = ulist_alloc(GFP_NOFS); if (!tmp || !roots) { - ulist_free(tmp); - ulist_free(roots); - return -ENOMEM; + ret = -ENOMEM; + goto out; } - trans = btrfs_join_transaction(root); + trans = btrfs_attach_transaction(root); if (IS_ERR(trans)) { + if (PTR_ERR(trans) != -ENOENT && PTR_ERR(trans) != -EROFS) { + ret = PTR_ERR(trans); + goto out; + } trans = NULL; down_read(&fs_info->commit_root_sem); } else { @@ -1517,6 +1520,7 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr) } else { up_read(&fs_info->commit_root_sem); } +out: ulist_free(tmp); ulist_free(roots); return ret; @@ -1906,13 +1910,19 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info, extent_item_objectid); if (!search_commit_root) { - trans = btrfs_join_transaction(fs_info->extent_root); - if (IS_ERR(trans)) - return PTR_ERR(trans); + trans = btrfs_attach_transaction(fs_info->extent_root); + if (IS_ERR(trans)) { + if (PTR_ERR(trans) != -ENOENT && + PTR_ERR(trans) != -EROFS) + return PTR_ERR(trans); + trans = NULL; + } + } + + if (trans) btrfs_get_tree_mod_seq(fs_info, &tree_mod_seq_elem); - } else { + else down_read(&fs_info->commit_root_sem); - } ret = btrfs_find_all_leafs(trans, fs_info, extent_item_objectid, tree_mod_seq_elem.seq, &refs, @@ -1945,7 +1955,7 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info, free_leaf_list(refs); out: - if (!search_commit_root) { + if (trans) { btrfs_put_tree_mod_seq(fs_info, &tree_mod_seq_elem); btrfs_end_transaction(trans); } else { diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 5a6c39b44c84..7672932aa5b4 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -2401,6 +2401,16 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p, if (tmp) { /* first we do an atomic uptodate check */ if (btrfs_buffer_uptodate(tmp, gen, 1) > 0) { + /* + * Do extra check for first_key, eb can be stale due to + * being cached, read from scrub, or have multiple + * parents (shared tree blocks). + */ + if (btrfs_verify_level_key(fs_info, tmp, + parent_level - 1, &first_key, gen)) { + free_extent_buffer(tmp); + return -EUCLEAN; + } *eb_ret = tmp; return 0; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 7a2a2621f0d9..9019265a2bf9 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1316,6 +1316,12 @@ struct btrfs_root { * manipulation with the read-only status via SUBVOL_SETFLAGS */ int send_in_progress; + /* + * Number of currently running deduplication operations that have a + * destination inode belonging to this root. Protected by the lock + * root_item_lock. + */ + int dedupe_in_progress; struct btrfs_subvolume_writers *subv_writers; atomic_t will_be_snapshotted; atomic_t snapshot_force_cow; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 888d72dda794..90a3c50d751b 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -414,9 +414,9 @@ static int btrfs_check_super_csum(struct btrfs_fs_info *fs_info, return ret; } -static int verify_level_key(struct btrfs_fs_info *fs_info, - struct extent_buffer *eb, int level, - struct btrfs_key *first_key, u64 parent_transid) +int btrfs_verify_level_key(struct btrfs_fs_info *fs_info, + struct extent_buffer *eb, int level, + struct btrfs_key *first_key, u64 parent_transid) { int found_level; struct btrfs_key found_key; @@ -493,8 +493,8 @@ static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info, if (verify_parent_transid(io_tree, eb, parent_transid, 0)) ret = -EIO; - else if (verify_level_key(fs_info, eb, level, - first_key, parent_transid)) + else if (btrfs_verify_level_key(fs_info, eb, level, + first_key, parent_transid)) ret = -EUCLEAN; else break; @@ -1017,13 +1017,18 @@ void readahead_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr) { struct extent_buffer *buf = NULL; struct inode *btree_inode = fs_info->btree_inode; + int ret; buf = btrfs_find_create_tree_block(fs_info, bytenr); if (IS_ERR(buf)) return; - read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree, - buf, WAIT_NONE, 0); - free_extent_buffer(buf); + + ret = read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree, buf, + WAIT_NONE, 0); + if (ret < 0) + free_extent_buffer_stale(buf); + else + free_extent_buffer(buf); } int reada_tree_block_flagged(struct btrfs_fs_info *fs_info, u64 bytenr, @@ -1043,12 +1048,12 @@ int reada_tree_block_flagged(struct btrfs_fs_info *fs_info, u64 bytenr, ret = read_extent_buffer_pages(io_tree, buf, WAIT_PAGE_LOCK, mirror_num); if (ret) { - free_extent_buffer(buf); + free_extent_buffer_stale(buf); return ret; } if (test_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags)) { - free_extent_buffer(buf); + free_extent_buffer_stale(buf); return -EIO; } else if (extent_buffer_uptodate(buf)) { *eb = buf; @@ -1102,7 +1107,7 @@ struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, ret = btree_read_extent_buffer_pages(fs_info, buf, parent_transid, level, first_key); if (ret) { - free_extent_buffer(buf); + free_extent_buffer_stale(buf); return ERR_PTR(ret); } return buf; diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 987a64bc0c66..67a9fe2d29c7 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -39,6 +39,9 @@ static inline u64 btrfs_sb_offset(int mirror) struct btrfs_device; struct btrfs_fs_devices; +int btrfs_verify_level_key(struct btrfs_fs_info *fs_info, + struct extent_buffer *eb, int level, + struct btrfs_key *first_key, 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); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 1b68700bc1c5..a19bbfce449e 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -11192,9 +11192,9 @@ int btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info, * held back allocations. */ static int btrfs_trim_free_extents(struct btrfs_device *device, - u64 minlen, u64 *trimmed) + struct fstrim_range *range, u64 *trimmed) { - u64 start = 0, len = 0; + u64 start = range->start, len = 0; int ret; *trimmed = 0; @@ -11237,8 +11237,8 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, if (!trans) up_read(&fs_info->commit_root_sem); - ret = find_free_dev_extent_start(trans, device, minlen, start, - &start, &len); + ret = find_free_dev_extent_start(trans, device, range->minlen, + start, &start, &len); if (trans) { up_read(&fs_info->commit_root_sem); btrfs_put_transaction(trans); @@ -11251,6 +11251,16 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, break; } + /* If we are out of the passed range break */ + if (start > range->start + range->len - 1) { + mutex_unlock(&fs_info->chunk_mutex); + ret = 0; + break; + } + + start = max(range->start, start); + len = min(range->len, len); + ret = btrfs_issue_discard(device->bdev, start, len, &bytes); mutex_unlock(&fs_info->chunk_mutex); @@ -11260,6 +11270,10 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, start += len; *trimmed += bytes; + /* We've trimmed enough */ + if (*trimmed >= range->len) + break; + if (fatal_signal_pending(current)) { ret = -ERESTARTSYS; break; @@ -11343,8 +11357,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) mutex_lock(&fs_info->fs_devices->device_list_mutex); devices = &fs_info->fs_devices->devices; list_for_each_entry(device, devices, dev_list) { - ret = btrfs_trim_free_extents(device, range->minlen, - &group_trimmed); + ret = btrfs_trim_free_extents(device, range, &group_trimmed); if (ret) { dev_failed++; dev_ret = ret; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 1d64a6b8e413..679303bf8e74 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3275,6 +3275,19 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen, int ret; int num_pages = PAGE_ALIGN(BTRFS_MAX_DEDUPE_LEN) >> PAGE_SHIFT; u64 i, tail_len, chunk_count; + struct btrfs_root *root_dst = BTRFS_I(dst)->root; + + spin_lock(&root_dst->root_item_lock); + if (root_dst->send_in_progress) { + btrfs_warn_rl(root_dst->fs_info, +"cannot deduplicate to root %llu while send operations are using it (%d in progress)", + root_dst->root_key.objectid, + root_dst->send_in_progress); + spin_unlock(&root_dst->root_item_lock); + return -EAGAIN; + } + root_dst->dedupe_in_progress++; + spin_unlock(&root_dst->root_item_lock); /* don't make the dst file partly checksummed */ if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) != @@ -3293,7 +3306,7 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen, ret = btrfs_extent_same_range(src, loff, BTRFS_MAX_DEDUPE_LEN, dst, dst_loff); if (ret) - return ret; + goto out; loff += BTRFS_MAX_DEDUPE_LEN; dst_loff += BTRFS_MAX_DEDUPE_LEN; @@ -3302,6 +3315,10 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen, if (tail_len > 0) ret = btrfs_extent_same_range(src, loff, tail_len, dst, dst_loff); +out: + spin_lock(&root_dst->root_item_lock); + root_dst->dedupe_in_progress--; + spin_unlock(&root_dst->root_item_lock); return ret; } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 7ea2d6b1f170..19b00b1668ed 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -6579,6 +6579,38 @@ commit_trans: return btrfs_commit_transaction(trans); } +/* + * Make sure any existing dellaloc is flushed for any root used by a send + * operation so that we do not miss any data and we do not race with writeback + * finishing and changing a tree while send is using the tree. This could + * happen if a subvolume is in RW mode, has delalloc, is turned to RO mode and + * a send operation then uses the subvolume. + * After flushing delalloc ensure_commit_roots_uptodate() must be called. + */ +static int flush_delalloc_roots(struct send_ctx *sctx) +{ + struct btrfs_root *root = sctx->parent_root; + int ret; + int i; + + if (root) { + ret = btrfs_start_delalloc_snapshot(root); + if (ret) + return ret; + btrfs_wait_ordered_extents(root, U64_MAX, 0, U64_MAX); + } + + for (i = 0; i < sctx->clone_roots_cnt; i++) { + root = sctx->clone_roots[i].root; + ret = btrfs_start_delalloc_snapshot(root); + if (ret) + return ret; + btrfs_wait_ordered_extents(root, U64_MAX, 0, U64_MAX); + } + + return 0; +} + static void btrfs_root_dec_send_in_progress(struct btrfs_root* root) { spin_lock(&root->root_item_lock); @@ -6594,6 +6626,13 @@ static void btrfs_root_dec_send_in_progress(struct btrfs_root* root) spin_unlock(&root->root_item_lock); } +static void dedupe_in_progress_warn(const struct btrfs_root *root) +{ + btrfs_warn_rl(root->fs_info, +"cannot use root %llu for send while deduplications on it are in progress (%d in progress)", + root->root_key.objectid, root->dedupe_in_progress); +} + long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) { int ret = 0; @@ -6617,6 +6656,11 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) * making it RW. This also protects against deletion. */ spin_lock(&send_root->root_item_lock); + if (btrfs_root_readonly(send_root) && send_root->dedupe_in_progress) { + dedupe_in_progress_warn(send_root); + spin_unlock(&send_root->root_item_lock); + return -EAGAIN; + } send_root->send_in_progress++; spin_unlock(&send_root->root_item_lock); @@ -6751,6 +6795,13 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) ret = -EPERM; goto out; } + if (clone_root->dedupe_in_progress) { + dedupe_in_progress_warn(clone_root); + spin_unlock(&clone_root->root_item_lock); + srcu_read_unlock(&fs_info->subvol_srcu, index); + ret = -EAGAIN; + goto out; + } clone_root->send_in_progress++; spin_unlock(&clone_root->root_item_lock); srcu_read_unlock(&fs_info->subvol_srcu, index); @@ -6785,6 +6836,13 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) ret = -EPERM; goto out; } + if (sctx->parent_root->dedupe_in_progress) { + dedupe_in_progress_warn(sctx->parent_root); + spin_unlock(&sctx->parent_root->root_item_lock); + srcu_read_unlock(&fs_info->subvol_srcu, index); + ret = -EAGAIN; + goto out; + } spin_unlock(&sctx->parent_root->root_item_lock); srcu_read_unlock(&fs_info->subvol_srcu, index); @@ -6803,6 +6861,10 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) NULL); sort_clone_roots = 1; + ret = flush_delalloc_roots(sctx); + if (ret) + goto out; + ret = ensure_commit_roots_uptodate(sctx); if (ret) goto out; |