From ec125cfb7ae2157af3dd45dd8abe823e3e233eec Mon Sep 17 00:00:00 2001 From: Robbie Ko Date: Fri, 28 Oct 2016 10:48:26 +0800 Subject: Btrfs: fix deadlock caused by fsync when logging directory entries While logging new directory entries, at tree-log.c:log_new_dir_dentries(), after we call btrfs_search_forward() we get a leaf with a read lock on it, and without unlocking that leaf we can end up calling btrfs_iget() to get an inode pointer. The later (btrfs_iget()) can end up doing a read-only search on the same tree again, if the inode is not in memory already, which ends up causing a deadlock if some other task in the meanwhile started a write search on the tree and is attempting to write lock the same leaf that btrfs_search_forward() locked while holding write locks on upper levels of the tree blocking the read search from btrfs_iget(). In this scenario we get a deadlock. So fix this by releasing the search path before calling btrfs_iget() at tree-log.c:log_new_dir_dentries(). Example trace of such deadlock: [ 4077.478852] kworker/u24:10 D ffff88107fc90640 0 14431 2 0x00000000 [ 4077.486752] Workqueue: btrfs-endio-write btrfs_endio_write_helper [btrfs] [ 4077.494346] ffff880ffa56bad0 0000000000000046 0000000000009000 ffff880ffa56bfd8 [ 4077.502629] ffff880ffa56bfd8 ffff881016ce21c0 ffffffffa06ecb26 ffff88101a5d6138 [ 4077.510915] ffff880ebb5173b0 ffff880ffa56baf8 ffff880ebb517410 ffff881016ce21c0 [ 4077.519202] Call Trace: [ 4077.528752] [] ? btrfs_tree_lock+0xdd/0x2f0 [btrfs] [ 4077.536049] [] ? wake_up_atomic_t+0x30/0x30 [ 4077.542574] [] ? btrfs_search_slot+0x79f/0xb10 [btrfs] [ 4077.550171] [] ? btrfs_lookup_file_extent+0x33/0x40 [btrfs] [ 4077.558252] [] ? __btrfs_drop_extents+0x13b/0xdf0 [btrfs] [ 4077.566140] [] ? add_delayed_data_ref+0xe2/0x150 [btrfs] [ 4077.573928] [] ? btrfs_add_delayed_data_ref+0x149/0x1d0 [btrfs] [ 4077.582399] [] ? __set_extent_bit+0x4c0/0x5c0 [btrfs] [ 4077.589896] [] ? insert_reserved_file_extent.constprop.75+0xa4/0x320 [btrfs] [ 4077.599632] [] ? start_transaction+0x8d/0x470 [btrfs] [ 4077.607134] [] ? btrfs_finish_ordered_io+0x2e7/0x600 [btrfs] [ 4077.615329] [] ? process_one_work+0x142/0x3d0 [ 4077.622043] [] ? worker_thread+0x109/0x3b0 [ 4077.628459] [] ? manage_workers.isra.26+0x270/0x270 [ 4077.635759] [] ? kthread+0xaf/0xc0 [ 4077.641404] [] ? kthread_create_on_node+0x110/0x110 [ 4077.648696] [] ? ret_from_fork+0x58/0x90 [ 4077.654926] [] ? kthread_create_on_node+0x110/0x110 [ 4078.358087] kworker/u24:15 D ffff88107fcd0640 0 14436 2 0x00000000 [ 4078.365981] Workqueue: btrfs-endio-write btrfs_endio_write_helper [btrfs] [ 4078.373574] ffff880ffa57fad0 0000000000000046 0000000000009000 ffff880ffa57ffd8 [ 4078.381864] ffff880ffa57ffd8 ffff88103004d0a0 ffffffffa06ecb26 ffff88101a5d6138 [ 4078.390163] ffff880fbeffc298 ffff880ffa57faf8 ffff880fbeffc2f8 ffff88103004d0a0 [ 4078.398466] Call Trace: [ 4078.408019] [] ? btrfs_tree_lock+0xdd/0x2f0 [btrfs] [ 4078.415322] [] ? wake_up_atomic_t+0x30/0x30 [ 4078.421844] [] ? btrfs_search_slot+0x79f/0xb10 [btrfs] [ 4078.429438] [] ? btrfs_lookup_file_extent+0x33/0x40 [btrfs] [ 4078.437518] [] ? __btrfs_drop_extents+0x13b/0xdf0 [btrfs] [ 4078.445404] [] ? add_delayed_data_ref+0xe2/0x150 [btrfs] [ 4078.453194] [] ? btrfs_add_delayed_data_ref+0x149/0x1d0 [btrfs] [ 4078.461663] [] ? __set_extent_bit+0x4c0/0x5c0 [btrfs] [ 4078.469161] [] ? insert_reserved_file_extent.constprop.75+0xa4/0x320 [btrfs] [ 4078.478893] [] ? start_transaction+0x8d/0x470 [btrfs] [ 4078.486388] [] ? btrfs_finish_ordered_io+0x2e7/0x600 [btrfs] [ 4078.494561] [] ? process_one_work+0x142/0x3d0 [ 4078.501278] [] ? pwq_activate_delayed_work+0x27/0x40 [ 4078.508673] [] ? worker_thread+0x109/0x3b0 [ 4078.515098] [] ? manage_workers.isra.26+0x270/0x270 [ 4078.522396] [] ? kthread+0xaf/0xc0 [ 4078.528032] [] ? kthread_create_on_node+0x110/0x110 [ 4078.535325] [] ? ret_from_fork+0x58/0x90 [ 4078.541552] [] ? kthread_create_on_node+0x110/0x110 [ 4079.355824] user-space-program D ffff88107fd30640 0 32020 1 0x00000000 [ 4079.363716] ffff880eae8eba10 0000000000000086 0000000000009000 ffff880eae8ebfd8 [ 4079.372003] ffff880eae8ebfd8 ffff881016c162c0 ffffffffa06ecb26 ffff88101a5d6138 [ 4079.380294] ffff880fbed4b4c8 ffff880eae8eba38 ffff880fbed4b528 ffff881016c162c0 [ 4079.388586] Call Trace: [ 4079.398134] [] ? btrfs_tree_lock+0x85/0x2f0 [btrfs] [ 4079.405431] [] ? wake_up_atomic_t+0x30/0x30 [ 4079.411955] [] ? btrfs_lock_root_node+0x2b/0x40 [btrfs] [ 4079.419644] [] ? btrfs_search_slot+0xa03/0xb10 [btrfs] [ 4079.427237] [] ? btrfs_buffer_uptodate+0x52/0x70 [btrfs] [ 4079.435041] [] ? generic_bin_search.constprop.38+0x80/0x190 [btrfs] [ 4079.443897] [] ? btrfs_insert_empty_items+0x74/0xd0 [btrfs] [ 4079.451975] [] ? copy_items+0x128/0x850 [btrfs] [ 4079.458890] [] ? btrfs_log_inode+0x629/0xbf3 [btrfs] [ 4079.466292] [] ? btrfs_log_inode_parent+0xc61/0xf30 [btrfs] [ 4079.474373] [] ? btrfs_log_dentry_safe+0x59/0x80 [btrfs] [ 4079.482161] [] ? btrfs_sync_file+0x20d/0x330 [btrfs] [ 4079.489558] [] ? do_fsync+0x4c/0x80 [ 4079.495300] [] ? SyS_fdatasync+0xa/0x10 [ 4079.501422] [] ? system_call_fastpath+0x16/0x1b [ 4079.508334] user-space-program D ffff88107fc30640 0 32021 1 0x00000004 [ 4079.516226] ffff880eae8efbf8 0000000000000086 0000000000009000 ffff880eae8effd8 [ 4079.524513] ffff880eae8effd8 ffff881030279610 ffffffffa06ecb26 ffff88101a5d6138 [ 4079.532802] ffff880ebb671d88 ffff880eae8efc20 ffff880ebb671de8 ffff881030279610 [ 4079.541092] Call Trace: [ 4079.550642] [] ? btrfs_tree_lock+0x85/0x2f0 [btrfs] [ 4079.557941] [] ? wake_up_atomic_t+0x30/0x30 [ 4079.564463] [] ? btrfs_search_slot+0x79f/0xb10 [btrfs] [ 4079.572058] [] ? btrfs_truncate_inode_items+0x168/0xb90 [btrfs] [ 4079.580526] [] ? join_transaction.isra.15+0x1e/0x3a0 [btrfs] [ 4079.588701] [] ? start_transaction+0x8d/0x470 [btrfs] [ 4079.596196] [] ? block_rsv_add_bytes+0x16/0x50 [btrfs] [ 4079.603789] [] ? btrfs_truncate+0xe9/0x2e0 [btrfs] [ 4079.610994] [] ? btrfs_setattr+0x30b/0x410 [btrfs] [ 4079.618197] [] ? notify_change+0x1dc/0x680 [ 4079.624625] [] ? aa_path_perm+0xd4/0x160 [ 4079.630854] [] ? do_truncate+0x5b/0x90 [ 4079.636889] [] ? do_sys_ftruncate.constprop.15+0x10a/0x160 [ 4079.644869] [] ? SyS_fcntl+0x5b/0x570 [ 4079.650805] [] ? system_call_fastpath+0x16/0x1b [ 4080.410607] user-space-program D ffff88107fc70640 0 32028 12639 0x00000004 [ 4080.418489] ffff880eaeccbbe0 0000000000000086 0000000000009000 ffff880eaeccbfd8 [ 4080.426778] ffff880eaeccbfd8 ffff880f317ef1e0 ffffffffa06ecb26 ffff88101a5d6138 [ 4080.435067] ffff880ef7e93928 ffff880f317ef1e0 ffff880eaeccbc08 ffff880f317ef1e0 [ 4080.443353] Call Trace: [ 4080.452920] [] ? btrfs_tree_read_lock+0xdd/0x190 [btrfs] [ 4080.460703] [] ? wake_up_atomic_t+0x30/0x30 [ 4080.467225] [] ? btrfs_read_lock_root_node+0x2b/0x40 [btrfs] [ 4080.475400] [] ? btrfs_search_slot+0x801/0xb10 [btrfs] [ 4080.482994] [] ? btrfs_clean_one_deleted_snapshot+0xe0/0xe0 [btrfs] [ 4080.491857] [] ? btrfs_lookup_inode+0x26/0x90 [btrfs] [ 4080.499353] [] ? kmem_cache_alloc+0xaf/0xc0 [ 4080.505879] [] ? btrfs_iget+0xd5/0x5d0 [btrfs] [ 4080.512696] [] ? btrfs_get_token_64+0x104/0x120 [btrfs] [ 4080.520387] [] ? btrfs_log_inode_parent+0xbdf/0xf30 [btrfs] [ 4080.528469] [] ? btrfs_log_dentry_safe+0x59/0x80 [btrfs] [ 4080.536258] [] ? btrfs_sync_file+0x20d/0x330 [btrfs] [ 4080.543657] [] ? do_fsync+0x4c/0x80 [ 4080.549399] [] ? SyS_fdatasync+0xa/0x10 [ 4080.555534] [] ? system_call_fastpath+0x16/0x1b Signed-off-by: Robbie Ko Reviewed-by: Filipe Manana Fixes: 2f2ff0ee5e43 (Btrfs: fix metadata inconsistencies after directory fsync) Cc: stable@vger.kernel.org # 4.1+ Signed-off-by: Filipe Manana [Modified changelog for clarity and correctness] --- fs/btrfs/tree-log.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 4b1c0a6eee04..897c9201c088 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -5205,6 +5205,7 @@ process_leaf: if (di_key.type == BTRFS_ROOT_ITEM_KEY) continue; + btrfs_release_path(path); di_inode = btrfs_iget(root->fs_info->sb, &di_key, root, NULL); if (IS_ERR(di_inode)) { @@ -5214,13 +5215,12 @@ process_leaf: if (btrfs_inode_in_log(di_inode, trans->transid)) { iput(di_inode); - continue; + break; } ctx->log_new_dentries = false; if (type == BTRFS_FT_DIR || type == BTRFS_FT_SYMLINK) log_mode = LOG_INODE_ALL; - btrfs_release_path(path); ret = btrfs_log_inode(trans, root, di_inode, log_mode, 0, LLONG_MAX, ctx); if (!ret && -- cgit