diff options
Diffstat (limited to 'kernel/fs/btrfs')
-rw-r--r-- | kernel/fs/btrfs/acl.c | 6 | ||||
-rw-r--r-- | kernel/fs/btrfs/async-thread.c | 14 | ||||
-rw-r--r-- | kernel/fs/btrfs/async-thread.h | 1 | ||||
-rw-r--r-- | kernel/fs/btrfs/compression.c | 4 | ||||
-rw-r--r-- | kernel/fs/btrfs/ctree.c | 5 | ||||
-rw-r--r-- | kernel/fs/btrfs/ctree.h | 5 | ||||
-rw-r--r-- | kernel/fs/btrfs/delayed-inode.c | 6 | ||||
-rw-r--r-- | kernel/fs/btrfs/disk-io.c | 3 | ||||
-rw-r--r-- | kernel/fs/btrfs/extent-tree.c | 58 | ||||
-rw-r--r-- | kernel/fs/btrfs/extent_io.c | 15 | ||||
-rw-r--r-- | kernel/fs/btrfs/file.c | 39 | ||||
-rw-r--r-- | kernel/fs/btrfs/inode.c | 9 | ||||
-rw-r--r-- | kernel/fs/btrfs/ioctl.c | 21 | ||||
-rw-r--r-- | kernel/fs/btrfs/qgroup.c | 18 | ||||
-rw-r--r-- | kernel/fs/btrfs/qgroup.h | 3 | ||||
-rw-r--r-- | kernel/fs/btrfs/relocation.c | 27 | ||||
-rw-r--r-- | kernel/fs/btrfs/super.c | 2 | ||||
-rw-r--r-- | kernel/fs/btrfs/transaction.h | 2 | ||||
-rw-r--r-- | kernel/fs/btrfs/tree-log.c | 161 |
19 files changed, 317 insertions, 82 deletions
diff --git a/kernel/fs/btrfs/acl.c b/kernel/fs/btrfs/acl.c index 9a0124a95..fb3e64d37 100644 --- a/kernel/fs/btrfs/acl.c +++ b/kernel/fs/btrfs/acl.c @@ -83,11 +83,9 @@ static int __btrfs_set_acl(struct btrfs_trans_handle *trans, case ACL_TYPE_ACCESS: name = POSIX_ACL_XATTR_ACCESS; if (acl) { - ret = posix_acl_equiv_mode(acl, &inode->i_mode); - if (ret < 0) + ret = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (ret) return ret; - if (ret == 0) - acl = NULL; } ret = 0; break; diff --git a/kernel/fs/btrfs/async-thread.c b/kernel/fs/btrfs/async-thread.c index 9aba42b78..a09264d8b 100644 --- a/kernel/fs/btrfs/async-thread.c +++ b/kernel/fs/btrfs/async-thread.c @@ -70,6 +70,20 @@ void btrfs_##name(struct work_struct *arg) \ normal_work_helper(work); \ } +bool btrfs_workqueue_normal_congested(struct btrfs_workqueue *wq) +{ + /* + * We could compare wq->normal->pending with num_online_cpus() + * to support "thresh == NO_THRESHOLD" case, but it requires + * moving up atomic_inc/dec in thresh_queue/exec_hook. Let's + * postpone it until someone needs the support of that case. + */ + if (wq->normal->thresh == NO_THRESHOLD) + return false; + + return atomic_read(&wq->normal->pending) > wq->normal->thresh * 2; +} + BTRFS_WORK_HELPER(worker_helper); BTRFS_WORK_HELPER(delalloc_helper); BTRFS_WORK_HELPER(flush_delalloc_helper); diff --git a/kernel/fs/btrfs/async-thread.h b/kernel/fs/btrfs/async-thread.h index ad4d0647d..8e1d6576d 100644 --- a/kernel/fs/btrfs/async-thread.h +++ b/kernel/fs/btrfs/async-thread.h @@ -80,4 +80,5 @@ void btrfs_queue_work(struct btrfs_workqueue *wq, void btrfs_destroy_workqueue(struct btrfs_workqueue *wq); void btrfs_workqueue_set_max(struct btrfs_workqueue *wq, int max); void btrfs_set_work_high_priority(struct btrfs_work *work); +bool btrfs_workqueue_normal_congested(struct btrfs_workqueue *wq); #endif diff --git a/kernel/fs/btrfs/compression.c b/kernel/fs/btrfs/compression.c index c473c42d7..bae05c5c7 100644 --- a/kernel/fs/btrfs/compression.c +++ b/kernel/fs/btrfs/compression.c @@ -694,7 +694,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, ret = btrfs_map_bio(root, READ, comp_bio, mirror_num, 0); if (ret) { - bio->bi_error = ret; + comp_bio->bi_error = ret; bio_endio(comp_bio); } @@ -723,7 +723,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, ret = btrfs_map_bio(root, READ, comp_bio, mirror_num, 0); if (ret) { - bio->bi_error = ret; + comp_bio->bi_error = ret; bio_endio(comp_bio); } diff --git a/kernel/fs/btrfs/ctree.c b/kernel/fs/btrfs/ctree.c index 5b8e235c4..0f2b7c622 100644 --- a/kernel/fs/btrfs/ctree.c +++ b/kernel/fs/btrfs/ctree.c @@ -1551,6 +1551,7 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans, trans->transid, root->fs_info->generation); if (!should_cow_block(trans, root, buf)) { + trans->dirty = true; *cow_ret = buf; return 0; } @@ -2773,8 +2774,10 @@ again: * then we don't want to set the path blocking, * so we test it here */ - if (!should_cow_block(trans, root, b)) + if (!should_cow_block(trans, root, b)) { + trans->dirty = true; goto cow_done; + } /* * must have write locks on this node and the diff --git a/kernel/fs/btrfs/ctree.h b/kernel/fs/btrfs/ctree.h index 385b449fd..e847573c6 100644 --- a/kernel/fs/btrfs/ctree.h +++ b/kernel/fs/btrfs/ctree.h @@ -1770,6 +1770,7 @@ struct btrfs_fs_info { struct btrfs_workqueue *qgroup_rescan_workers; struct completion qgroup_rescan_completion; struct btrfs_work qgroup_rescan_work; + bool qgroup_rescan_running; /* protected by qgroup_rescan_lock */ /* filesystem state */ unsigned long fs_state; @@ -3069,6 +3070,8 @@ btrfs_disk_balance_args_to_cpu(struct btrfs_balance_args *cpu, cpu->target = le64_to_cpu(disk->target); cpu->flags = le64_to_cpu(disk->flags); cpu->limit = le64_to_cpu(disk->limit); + cpu->stripes_min = le32_to_cpu(disk->stripes_min); + cpu->stripes_max = le32_to_cpu(disk->stripes_max); } static inline void @@ -3087,6 +3090,8 @@ btrfs_cpu_balance_args_to_disk(struct btrfs_disk_balance_args *disk, disk->target = cpu_to_le64(cpu->target); disk->flags = cpu_to_le64(cpu->flags); disk->limit = cpu_to_le64(cpu->limit); + disk->stripes_min = cpu_to_le32(cpu->stripes_min); + disk->stripes_max = cpu_to_le32(cpu->stripes_max); } /* struct btrfs_super_block */ diff --git a/kernel/fs/btrfs/delayed-inode.c b/kernel/fs/btrfs/delayed-inode.c index 02b934d0e..09fa5af97 100644 --- a/kernel/fs/btrfs/delayed-inode.c +++ b/kernel/fs/btrfs/delayed-inode.c @@ -1375,7 +1375,8 @@ release_path: total_done++; btrfs_release_prepared_delayed_node(delayed_node); - if (async_work->nr == 0 || total_done < async_work->nr) + if ((async_work->nr == 0 && total_done < BTRFS_DELAYED_WRITEBACK) || + total_done < async_work->nr) goto again; free_path: @@ -1391,7 +1392,8 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root, { struct btrfs_async_delayed_work *async_work; - if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND) + if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND || + btrfs_workqueue_normal_congested(fs_info->delayed_workers)) return 0; async_work = kmalloc(sizeof(*async_work), GFP_NOFS); diff --git a/kernel/fs/btrfs/disk-io.c b/kernel/fs/btrfs/disk-io.c index 41fb43183..85b207d19 100644 --- a/kernel/fs/btrfs/disk-io.c +++ b/kernel/fs/btrfs/disk-io.c @@ -2276,6 +2276,7 @@ static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info) fs_info->quota_enabled = 0; fs_info->pending_quota_state = 0; fs_info->qgroup_ulist = NULL; + fs_info->qgroup_rescan_running = false; mutex_init(&fs_info->qgroup_rescan_lock); } @@ -3811,7 +3812,7 @@ void close_ctree(struct btrfs_root *root) smp_mb(); /* wait for the qgroup rescan worker to stop */ - btrfs_qgroup_wait_for_completion(fs_info); + btrfs_qgroup_wait_for_completion(fs_info, false); /* wait for the uuid_scan task to finish */ down(&fs_info->uuid_tree_rescan_sem); diff --git a/kernel/fs/btrfs/extent-tree.c b/kernel/fs/btrfs/extent-tree.c index 2368cac11..2a2e37039 100644 --- a/kernel/fs/btrfs/extent-tree.c +++ b/kernel/fs/btrfs/extent-tree.c @@ -2520,11 +2520,11 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, if (ref && ref->seq && btrfs_check_delayed_seq(fs_info, delayed_refs, ref->seq)) { spin_unlock(&locked_ref->lock); - btrfs_delayed_ref_unlock(locked_ref); spin_lock(&delayed_refs->lock); locked_ref->processing = 0; delayed_refs->num_heads_ready++; spin_unlock(&delayed_refs->lock); + btrfs_delayed_ref_unlock(locked_ref); locked_ref = NULL; cond_resched(); count++; @@ -2570,7 +2570,10 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, */ if (must_insert_reserved) locked_ref->must_insert_reserved = 1; + spin_lock(&delayed_refs->lock); locked_ref->processing = 0; + delayed_refs->num_heads_ready++; + spin_unlock(&delayed_refs->lock); btrfs_debug(fs_info, "run_delayed_extent_op returned %d", ret); btrfs_delayed_ref_unlock(locked_ref); return ret; @@ -7856,7 +7859,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, set_extent_dirty(&trans->transaction->dirty_pages, buf->start, buf->start + buf->len - 1, GFP_NOFS); } - trans->blocks_used++; + trans->dirty = true; /* this returns a buffer locked for blocking */ return buf; } @@ -8486,14 +8489,13 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans, ret = btrfs_lookup_extent_info(trans, root, bytenr, level - 1, 1, &wc->refs[level - 1], &wc->flags[level - 1]); - if (ret < 0) { - btrfs_tree_unlock(next); - return ret; - } + if (ret < 0) + goto out_unlock; if (unlikely(wc->refs[level - 1] == 0)) { btrfs_err(root->fs_info, "Missing references."); - BUG(); + ret = -EIO; + goto out_unlock; } *lookup_info = 0; @@ -8545,7 +8547,12 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans, } level--; - BUG_ON(level != btrfs_header_level(next)); + ASSERT(level == btrfs_header_level(next)); + if (level != btrfs_header_level(next)) { + btrfs_err(root->fs_info, "mismatched level"); + ret = -EIO; + goto out_unlock; + } path->nodes[level] = next; path->slots[level] = 0; path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING; @@ -8560,8 +8567,15 @@ skip: if (wc->flags[level] & BTRFS_BLOCK_FLAG_FULL_BACKREF) { parent = path->nodes[level]->start; } else { - BUG_ON(root->root_key.objectid != + ASSERT(root->root_key.objectid == btrfs_header_owner(path->nodes[level])); + if (root->root_key.objectid != + btrfs_header_owner(path->nodes[level])) { + btrfs_err(root->fs_info, + "mismatched block owner"); + ret = -EIO; + goto out_unlock; + } parent = 0; } @@ -8578,12 +8592,18 @@ skip: } ret = btrfs_free_extent(trans, root, bytenr, blocksize, parent, root->root_key.objectid, level - 1, 0); - BUG_ON(ret); /* -ENOMEM */ + if (ret) + goto out_unlock; } + + *lookup_info = 1; + ret = 1; + +out_unlock: btrfs_tree_unlock(next); free_extent_buffer(next); - *lookup_info = 1; - return 1; + + return ret; } /* @@ -9686,6 +9706,11 @@ int btrfs_read_block_groups(struct btrfs_root *root) struct extent_buffer *leaf; int need_clear = 0; u64 cache_gen; + u64 feature; + int mixed; + + feature = btrfs_super_incompat_flags(info->super_copy); + mixed = !!(feature & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS); root = info->extent_root; key.objectid = 0; @@ -9739,6 +9764,15 @@ int btrfs_read_block_groups(struct btrfs_root *root) btrfs_item_ptr_offset(leaf, path->slots[0]), sizeof(cache->item)); cache->flags = btrfs_block_group_flags(&cache->item); + if (!mixed && + ((cache->flags & BTRFS_BLOCK_GROUP_METADATA) && + (cache->flags & BTRFS_BLOCK_GROUP_DATA))) { + btrfs_err(info, +"bg %llu is a mixed block group but filesystem hasn't enabled mixed block groups", + cache->key.objectid); + ret = -EINVAL; + goto error; + } key.objectid = found_key.objectid + found_key.offset; btrfs_release_path(path); diff --git a/kernel/fs/btrfs/extent_io.c b/kernel/fs/btrfs/extent_io.c index 9abe18763..e767f347f 100644 --- a/kernel/fs/btrfs/extent_io.c +++ b/kernel/fs/btrfs/extent_io.c @@ -2786,12 +2786,6 @@ struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask) btrfs_bio->csum = NULL; btrfs_bio->csum_allocated = NULL; btrfs_bio->end_io = NULL; - -#ifdef CONFIG_BLK_CGROUP - /* FIXME, put this into bio_clone_bioset */ - if (bio->bi_css) - bio_associate_blkcg(new, bio->bi_css); -#endif } return new; } @@ -5300,11 +5294,20 @@ int read_extent_buffer_pages(struct extent_io_tree *tree, lock_page(page); } locked_pages++; + } + /* + * We need to firstly lock all pages to make sure that + * the uptodate bit of our pages won't be affected by + * clear_extent_buffer_uptodate(). + */ + for (i = start_i; i < num_pages; i++) { + page = eb->pages[i]; if (!PageUptodate(page)) { num_reads++; all_uptodate = 0; } } + if (all_uptodate) { if (start_i == 0) set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); diff --git a/kernel/fs/btrfs/file.c b/kernel/fs/btrfs/file.c index 0f09526aa..353f4bae6 100644 --- a/kernel/fs/btrfs/file.c +++ b/kernel/fs/btrfs/file.c @@ -1526,27 +1526,24 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, reserve_bytes = num_pages << PAGE_CACHE_SHIFT; - if (BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | - BTRFS_INODE_PREALLOC)) { - ret = check_can_nocow(inode, pos, &write_bytes); - if (ret < 0) - break; - if (ret > 0) { - /* - * For nodata cow case, no need to reserve - * data space. - */ - only_release_metadata = true; - /* - * our prealloc extent may be smaller than - * write_bytes, so scale down. - */ - num_pages = DIV_ROUND_UP(write_bytes + offset, - PAGE_CACHE_SIZE); - reserve_bytes = num_pages << PAGE_CACHE_SHIFT; - goto reserve_metadata; - } + if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | + BTRFS_INODE_PREALLOC)) && + check_can_nocow(inode, pos, &write_bytes) > 0) { + /* + * For nodata cow case, no need to reserve + * data space. + */ + only_release_metadata = true; + /* + * our prealloc extent may be smaller than + * write_bytes, so scale down. + */ + num_pages = DIV_ROUND_UP(write_bytes + offset, + PAGE_CACHE_SIZE); + reserve_bytes = num_pages << PAGE_CACHE_SHIFT; + goto reserve_metadata; } + ret = btrfs_check_data_free_space(inode, pos, write_bytes); if (ret < 0) break; @@ -1885,7 +1882,7 @@ static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end) */ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) { - struct dentry *dentry = file->f_path.dentry; + struct dentry *dentry = file_dentry(file); struct inode *inode = d_inode(dentry); struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_trans_handle *trans; diff --git a/kernel/fs/btrfs/inode.c b/kernel/fs/btrfs/inode.c index 4bc9dbf29..3cff6523f 100644 --- a/kernel/fs/btrfs/inode.c +++ b/kernel/fs/btrfs/inode.c @@ -8691,9 +8691,14 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset, * So even we call qgroup_free_data(), it won't decrease reserved * space. * 2) Not written to disk - * This means the reserved space should be freed here. + * This means the reserved space should be freed here. However, + * if a truncate invalidates the page (by clearing PageDirty) + * and the page is accounted for while allocating extent + * in btrfs_check_data_free_space() we let delayed_ref to + * free the entire extent. */ - btrfs_qgroup_free_data(inode, page_start, PAGE_CACHE_SIZE); + if (PageDirty(page)) + btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE); if (!inode_evicting) { clear_extent_bit(tree, page_start, page_end, EXTENT_LOCKED | EXTENT_DIRTY | diff --git a/kernel/fs/btrfs/ioctl.c b/kernel/fs/btrfs/ioctl.c index f07d01bc4..317b99acd 100644 --- a/kernel/fs/btrfs/ioctl.c +++ b/kernel/fs/btrfs/ioctl.c @@ -1619,6 +1619,9 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file, int namelen; int ret = 0; + if (!S_ISDIR(file_inode(file)->i_mode)) + return -ENOTDIR; + ret = mnt_want_write_file(file); if (ret) goto out; @@ -1648,7 +1651,7 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file, src_inode = file_inode(src.file); if (src_inode->i_sb != file_inode(file)->i_sb) { - btrfs_info(BTRFS_I(src_inode)->root->fs_info, + btrfs_info(BTRFS_I(file_inode(file))->root->fs_info, "Snapshot src from another FS"); ret = -EXDEV; } else if (!inode_owner_or_capable(src_inode)) { @@ -1676,6 +1679,9 @@ static noinline int btrfs_ioctl_snap_create(struct file *file, struct btrfs_ioctl_vol_args *vol_args; int ret; + if (!S_ISDIR(file_inode(file)->i_mode)) + return -ENOTDIR; + vol_args = memdup_user(arg, sizeof(*vol_args)); if (IS_ERR(vol_args)) return PTR_ERR(vol_args); @@ -1699,6 +1705,9 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file, bool readonly = false; struct btrfs_qgroup_inherit *inherit = NULL; + if (!S_ISDIR(file_inode(file)->i_mode)) + return -ENOTDIR; + vol_args = memdup_user(arg, sizeof(*vol_args)); if (IS_ERR(vol_args)) return PTR_ERR(vol_args); @@ -2345,6 +2354,9 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, int ret; int err = 0; + if (!S_ISDIR(dir->i_mode)) + return -ENOTDIR; + vol_args = memdup_user(arg, sizeof(*vol_args)); if (IS_ERR(vol_args)) return PTR_ERR(vol_args); @@ -3813,6 +3825,11 @@ process_slot: } btrfs_release_path(path); key.offset = next_key_min_offset; + + if (fatal_signal_pending(current)) { + ret = -EINTR; + goto out; + } } ret = 0; @@ -5121,7 +5138,7 @@ static long btrfs_ioctl_quota_rescan_wait(struct file *file, void __user *arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; - return btrfs_qgroup_wait_for_completion(root->fs_info); + return btrfs_qgroup_wait_for_completion(root->fs_info, true); } static long _btrfs_ioctl_set_received_subvol(struct file *file, diff --git a/kernel/fs/btrfs/qgroup.c b/kernel/fs/btrfs/qgroup.c index 5279fdae7..88d9b66e2 100644 --- a/kernel/fs/btrfs/qgroup.c +++ b/kernel/fs/btrfs/qgroup.c @@ -995,7 +995,7 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans, goto out; fs_info->quota_enabled = 0; fs_info->pending_quota_state = 0; - btrfs_qgroup_wait_for_completion(fs_info); + btrfs_qgroup_wait_for_completion(fs_info, false); spin_lock(&fs_info->qgroup_lock); quota_root = fs_info->quota_root; fs_info->quota_root = NULL; @@ -2349,6 +2349,9 @@ out: } done: + mutex_lock(&fs_info->qgroup_rescan_lock); + fs_info->qgroup_rescan_running = false; + mutex_unlock(&fs_info->qgroup_rescan_lock); complete_all(&fs_info->qgroup_rescan_completion); } @@ -2390,6 +2393,7 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid, sizeof(fs_info->qgroup_rescan_progress)); fs_info->qgroup_rescan_progress.objectid = progress_objectid; init_completion(&fs_info->qgroup_rescan_completion); + fs_info->qgroup_rescan_running = true; spin_unlock(&fs_info->qgroup_lock); mutex_unlock(&fs_info->qgroup_rescan_lock); @@ -2467,20 +2471,26 @@ btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info) return 0; } -int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info) +int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info, + bool interruptible) { int running; int ret = 0; mutex_lock(&fs_info->qgroup_rescan_lock); spin_lock(&fs_info->qgroup_lock); - running = fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN; + running = fs_info->qgroup_rescan_running; spin_unlock(&fs_info->qgroup_lock); mutex_unlock(&fs_info->qgroup_rescan_lock); - if (running) + if (!running) + return 0; + + if (interruptible) ret = wait_for_completion_interruptible( &fs_info->qgroup_rescan_completion); + else + wait_for_completion(&fs_info->qgroup_rescan_completion); return ret; } diff --git a/kernel/fs/btrfs/qgroup.h b/kernel/fs/btrfs/qgroup.h index ecb2c143e..3d73e4c9c 100644 --- a/kernel/fs/btrfs/qgroup.h +++ b/kernel/fs/btrfs/qgroup.h @@ -46,7 +46,8 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); int btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info); void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info); -int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info); +int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info, + bool interruptible); int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 src, u64 dst); int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans, diff --git a/kernel/fs/btrfs/relocation.c b/kernel/fs/btrfs/relocation.c index b4ca5454e..8ca9aa929 100644 --- a/kernel/fs/btrfs/relocation.c +++ b/kernel/fs/btrfs/relocation.c @@ -921,9 +921,16 @@ again: path2->slots[level]--; eb = path2->nodes[level]; - WARN_ON(btrfs_node_blockptr(eb, path2->slots[level]) != - cur->bytenr); - + if (btrfs_node_blockptr(eb, path2->slots[level]) != + cur->bytenr) { + btrfs_err(root->fs_info, + "couldn't find block (%llu) (level %d) in tree (%llu) with key (%llu %u %llu)", + cur->bytenr, level - 1, root->objectid, + node_key->objectid, node_key->type, + node_key->offset); + err = -ENOENT; + goto out; + } lower = cur; need_check = true; for (; level < BTRFS_MAX_LEVEL; level++) { @@ -2343,6 +2350,10 @@ void free_reloc_roots(struct list_head *list) while (!list_empty(list)) { reloc_root = list_entry(list->next, struct btrfs_root, root_list); + free_extent_buffer(reloc_root->node); + free_extent_buffer(reloc_root->commit_root); + reloc_root->node = NULL; + reloc_root->commit_root = NULL; __del_reloc_root(reloc_root); } } @@ -2676,11 +2687,15 @@ static int do_relocation(struct btrfs_trans_handle *trans, if (!upper->eb) { ret = btrfs_search_slot(trans, root, key, path, 0, 1); - if (ret < 0) { - err = ret; + if (ret) { + if (ret < 0) + err = ret; + else + err = -ENOENT; + + btrfs_release_path(path); break; } - BUG_ON(ret > 0); if (!upper->eb) { upper->eb = path->nodes[upper->level]; diff --git a/kernel/fs/btrfs/super.c b/kernel/fs/btrfs/super.c index fe609b81d..5d34a062c 100644 --- a/kernel/fs/btrfs/super.c +++ b/kernel/fs/btrfs/super.c @@ -239,7 +239,7 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans, trans->aborted = errno; /* Nothing used. The other threads that have joined this * transaction may be able to continue. */ - if (!trans->blocks_used && list_empty(&trans->new_bgs)) { + if (!trans->dirty && list_empty(&trans->new_bgs)) { const char *errstr; errstr = btrfs_decode_error(errno); diff --git a/kernel/fs/btrfs/transaction.h b/kernel/fs/btrfs/transaction.h index 64c8221b6..1e872923e 100644 --- a/kernel/fs/btrfs/transaction.h +++ b/kernel/fs/btrfs/transaction.h @@ -110,7 +110,6 @@ struct btrfs_trans_handle { u64 chunk_bytes_reserved; unsigned long use_count; unsigned long blocks_reserved; - unsigned long blocks_used; unsigned long delayed_ref_updates; struct btrfs_transaction *transaction; struct btrfs_block_rsv *block_rsv; @@ -121,6 +120,7 @@ struct btrfs_trans_handle { bool can_flush_pending_bgs; bool reloc_reserved; bool sync; + bool dirty; unsigned int type; /* * this root is only needed to validate that the root passed to diff --git a/kernel/fs/btrfs/tree-log.c b/kernel/fs/btrfs/tree-log.c index 323e12cc9..ee7832e2d 100644 --- a/kernel/fs/btrfs/tree-log.c +++ b/kernel/fs/btrfs/tree-log.c @@ -1923,12 +1923,11 @@ static noinline int find_dir_range(struct btrfs_root *root, next: /* check the next slot in the tree to see if it is a valid item */ nritems = btrfs_header_nritems(path->nodes[0]); + path->slots[0]++; if (path->slots[0] >= nritems) { ret = btrfs_next_leaf(root, path); if (ret) goto out; - } else { - path->slots[0]++; } btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); @@ -2696,14 +2695,12 @@ static inline void btrfs_remove_all_log_ctxs(struct btrfs_root *root, int index, int error) { struct btrfs_log_ctx *ctx; + struct btrfs_log_ctx *safe; - if (!error) { - INIT_LIST_HEAD(&root->log_ctxs[index]); - return; - } - - list_for_each_entry(ctx, &root->log_ctxs[index], list) + list_for_each_entry_safe(ctx, safe, &root->log_ctxs[index], list) { + list_del_init(&ctx->list); ctx->log_ret = error; + } INIT_LIST_HEAD(&root->log_ctxs[index]); } @@ -2850,6 +2847,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, if (log_root_tree->log_transid_committed >= root_log_ctx.log_transid) { blk_finish_plug(&plug); + list_del_init(&root_log_ctx.list); mutex_unlock(&log_root_tree->log_mutex); ret = root_log_ctx.log_ret; goto out; @@ -2943,13 +2941,9 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, mutex_unlock(&root->log_mutex); out_wake_log_root: - /* - * We needn't get log_mutex here because we are sure all - * the other tasks are blocked. - */ + mutex_lock(&log_root_tree->log_mutex); btrfs_remove_all_log_ctxs(log_root_tree, index2, ret); - mutex_lock(&log_root_tree->log_mutex); log_root_tree->log_transid_committed++; atomic_set(&log_root_tree->log_commit[index2], 0); mutex_unlock(&log_root_tree->log_mutex); @@ -2960,10 +2954,8 @@ out_wake_log_root: if (waitqueue_active(&log_root_tree->log_commit_wait[index2])) wake_up(&log_root_tree->log_commit_wait[index2]); out: - /* See above. */ - btrfs_remove_all_log_ctxs(root, index1, ret); - mutex_lock(&root->log_mutex); + btrfs_remove_all_log_ctxs(root, index1, ret); root->log_transid_committed++; atomic_set(&root->log_commit[index1], 0); mutex_unlock(&root->log_mutex); @@ -4406,6 +4398,127 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans, return ret; } +/* + * When we are logging a new inode X, check if it doesn't have a reference that + * matches the reference from some other inode Y created in a past transaction + * and that was renamed in the current transaction. If we don't do this, then at + * log replay time we can lose inode Y (and all its files if it's a directory): + * + * mkdir /mnt/x + * echo "hello world" > /mnt/x/foobar + * sync + * mv /mnt/x /mnt/y + * mkdir /mnt/x # or touch /mnt/x + * xfs_io -c fsync /mnt/x + * <power fail> + * mount fs, trigger log replay + * + * After the log replay procedure, we would lose the first directory and all its + * files (file foobar). + * For the case where inode Y is not a directory we simply end up losing it: + * + * echo "123" > /mnt/foo + * sync + * mv /mnt/foo /mnt/bar + * echo "abc" > /mnt/foo + * xfs_io -c fsync /mnt/foo + * <power fail> + * + * We also need this for cases where a snapshot entry is replaced by some other + * entry (file or directory) otherwise we end up with an unreplayable log due to + * attempts to delete the snapshot entry (entry of type BTRFS_ROOT_ITEM_KEY) as + * if it were a regular entry: + * + * mkdir /mnt/x + * btrfs subvolume snapshot /mnt /mnt/x/snap + * btrfs subvolume delete /mnt/x/snap + * rmdir /mnt/x + * mkdir /mnt/x + * fsync /mnt/x or fsync some new file inside it + * <power fail> + * + * The snapshot delete, rmdir of x, mkdir of a new x and the fsync all happen in + * the same transaction. + */ +static int btrfs_check_ref_name_override(struct extent_buffer *eb, + const int slot, + const struct btrfs_key *key, + struct inode *inode) +{ + int ret; + struct btrfs_path *search_path; + char *name = NULL; + u32 name_len = 0; + u32 item_size = btrfs_item_size_nr(eb, slot); + u32 cur_offset = 0; + unsigned long ptr = btrfs_item_ptr_offset(eb, slot); + + search_path = btrfs_alloc_path(); + if (!search_path) + return -ENOMEM; + search_path->search_commit_root = 1; + search_path->skip_locking = 1; + + while (cur_offset < item_size) { + u64 parent; + u32 this_name_len; + u32 this_len; + unsigned long name_ptr; + struct btrfs_dir_item *di; + + if (key->type == BTRFS_INODE_REF_KEY) { + struct btrfs_inode_ref *iref; + + iref = (struct btrfs_inode_ref *)(ptr + cur_offset); + parent = key->offset; + this_name_len = btrfs_inode_ref_name_len(eb, iref); + name_ptr = (unsigned long)(iref + 1); + this_len = sizeof(*iref) + this_name_len; + } else { + struct btrfs_inode_extref *extref; + + extref = (struct btrfs_inode_extref *)(ptr + + cur_offset); + parent = btrfs_inode_extref_parent(eb, extref); + this_name_len = btrfs_inode_extref_name_len(eb, extref); + name_ptr = (unsigned long)&extref->name; + this_len = sizeof(*extref) + this_name_len; + } + + if (this_name_len > name_len) { + char *new_name; + + new_name = krealloc(name, this_name_len, GFP_NOFS); + if (!new_name) { + ret = -ENOMEM; + goto out; + } + name_len = this_name_len; + name = new_name; + } + + read_extent_buffer(eb, name, name_ptr, this_name_len); + di = btrfs_lookup_dir_item(NULL, BTRFS_I(inode)->root, + search_path, parent, + name, this_name_len, 0); + if (di && !IS_ERR(di)) { + ret = 1; + goto out; + } else if (IS_ERR(di)) { + ret = PTR_ERR(di); + goto out; + } + btrfs_release_path(search_path); + + cur_offset += this_len; + } + ret = 0; +out: + btrfs_free_path(search_path); + kfree(name); + return ret; +} + /* log a single inode in the tree log. * At least one parent directory for this inode must exist in the tree * or be logged already. @@ -4578,6 +4691,22 @@ again: if (min_key.type == BTRFS_INODE_ITEM_KEY) need_log_inode_item = false; + if ((min_key.type == BTRFS_INODE_REF_KEY || + min_key.type == BTRFS_INODE_EXTREF_KEY) && + BTRFS_I(inode)->generation == trans->transid) { + ret = btrfs_check_ref_name_override(path->nodes[0], + path->slots[0], + &min_key, inode); + if (ret < 0) { + err = ret; + goto out_unlock; + } else if (ret > 0) { + err = 1; + btrfs_set_log_full_commit(root->fs_info, trans); + goto out_unlock; + } + } + /* Skip xattrs, we log them later with btrfs_log_all_xattrs() */ if (min_key.type == BTRFS_XATTR_ITEM_KEY) { if (ins_nr == 0) |