From 1bd7112bb9313828b53c51e100f22c0db0427836 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Thu, 6 Sep 2018 16:59:33 -0400 Subject: btrfs: fix error handling in free_log_tree commit 374b0e2d6ba5da7fd1cadb3247731ff27d011f6f upstream. When we hit an I/O error in free_log_tree->walk_log_tree during file system shutdown we can crash due to there not being a valid transaction handle. Use btrfs_handle_fs_error when there's no transaction handle to use. BUG: unable to handle kernel NULL pointer dereference at 0000000000000060 IP: free_log_tree+0xd2/0x140 [btrfs] PGD 0 P4D 0 Oops: 0000 [#1] SMP DEBUG_PAGEALLOC PTI Modules linked in: CPU: 2 PID: 23544 Comm: umount Tainted: G W 4.12.14-kvmsmall #9 SLE15 (unreleased) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.0.0-prebuilt.qemu-project.org 04/01/2014 task: ffff96bfd3478880 task.stack: ffffa7cf40d78000 RIP: 0010:free_log_tree+0xd2/0x140 [btrfs] RSP: 0018:ffffa7cf40d7bd10 EFLAGS: 00010282 RAX: 00000000fffffffb RBX: 00000000fffffffb RCX: 0000000000000002 RDX: 0000000000000000 RSI: ffff96c02f07d4c8 RDI: 0000000000000282 RBP: ffff96c013cf1000 R08: ffff96c02f07d4c8 R09: ffff96c02f07d4d0 R10: 0000000000000000 R11: 0000000000000002 R12: 0000000000000000 R13: ffff96c005e800c0 R14: ffffa7cf40d7bdb8 R15: 0000000000000000 FS: 00007f17856bcfc0(0000) GS:ffff96c03f600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000060 CR3: 0000000045ed6002 CR4: 00000000003606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? wait_for_writer+0xb0/0xb0 [btrfs] btrfs_free_log+0x17/0x30 [btrfs] btrfs_drop_and_free_fs_root+0x9a/0xe0 [btrfs] btrfs_free_fs_roots+0xc0/0x130 [btrfs] ? wait_for_completion+0xf2/0x100 close_ctree+0xea/0x2e0 [btrfs] ? kthread_stop+0x161/0x260 generic_shutdown_super+0x6c/0x120 kill_anon_super+0xe/0x20 btrfs_kill_super+0x13/0x100 [btrfs] deactivate_locked_super+0x3f/0x70 cleanup_mnt+0x3b/0x70 task_work_run+0x78/0x90 exit_to_usermode_loop+0x77/0xa6 do_syscall_64+0x1c5/0x1e0 entry_SYSCALL_64_after_hwframe+0x42/0xb7 RIP: 0033:0x7f1784f90827 RSP: 002b:00007ffdeeb03118 EFLAGS: 00000246 ORIG_RAX: 00000000000000a6 RAX: 0000000000000000 RBX: 0000556a60c62970 RCX: 00007f1784f90827 RDX: 0000000000000001 RSI: 0000000000000000 RDI: 0000556a60c62b50 RBP: 0000000000000000 R08: 0000000000000005 R09: 00000000ffffffff R10: 0000556a60c63900 R11: 0000000000000246 R12: 0000556a60c62b50 R13: 00007f17854a81c4 R14: 0000000000000000 R15: 0000000000000000 RIP: free_log_tree+0xd2/0x140 [btrfs] RSP: ffffa7cf40d7bd10 CR2: 0000000000000060 Fixes: 681ae50917df9 ("Btrfs: cleanup reserved space when freeing tree log on error") CC: # v3.13 Signed-off-by: Jeff Mahoney Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/tree-log.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'fs/btrfs/tree-log.c') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 44966fd00790..c03891f9d96e 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3016,9 +3016,12 @@ static void free_log_tree(struct btrfs_trans_handle *trans, }; ret = walk_log_tree(trans, log, &wc); - /* I don't think this can happen but just in case */ - if (ret) - btrfs_abort_transaction(trans, ret); + if (ret) { + if (trans) + btrfs_abort_transaction(trans, ret); + else + btrfs_handle_fs_error(log->fs_info, ret, NULL); + } while (1) { ret = find_first_extent_bit(&log->dirty_log_pages, -- cgit v1.2.3 From 6a0403a42c2d7d31587aab29639bb0a962d07c4b Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 9 Oct 2018 15:05:29 +0100 Subject: Btrfs: fix wrong dentries after fsync of file that got its parent replaced commit 0f375eed92b5a407657532637ed9652611a682f5 upstream. In a scenario like the following: mkdir /mnt/A # inode 258 mkdir /mnt/B # inode 259 touch /mnt/B/bar # inode 260 sync mv /mnt/B/bar /mnt/A/bar mv -T /mnt/A /mnt/B fsync /mnt/B/bar After replaying the log we end up with file bar having 2 hard links, both with the name 'bar' and one in the directory with inode number 258 and the other in the directory with inode number 259. Also, we end up with the directory inode 259 still existing and with the directory inode 258 still named as 'A', instead of 'B'. In this scenario, file 'bar' should only have one hard link, located at directory inode 258, the directory inode 259 should not exist anymore and the name for directory inode 258 should be 'B'. This incorrect behaviour happens because when attempting to log the old parents of an inode, we skip any parents that no longer exist. Fix this by forcing a full commit if an old parent no longer exists. A test case for fstests follows soon. CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/tree-log.c | 30 +++++++++++++++++++++++++++--- 1 file changed, 27 insertions(+), 3 deletions(-) (limited to 'fs/btrfs/tree-log.c') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index c03891f9d96e..47d11a30bee7 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -5373,9 +5373,33 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans, dir_inode = btrfs_iget(root->fs_info->sb, &inode_key, root, NULL); - /* If parent inode was deleted, skip it. */ - if (IS_ERR(dir_inode)) - continue; + /* + * If the parent inode was deleted, return an error to + * fallback to a transaction commit. This is to prevent + * getting an inode that was moved from one parent A to + * a parent B, got its former parent A deleted and then + * it got fsync'ed, from existing at both parents after + * a log replay (and the old parent still existing). + * Example: + * + * mkdir /mnt/A + * mkdir /mnt/B + * touch /mnt/B/bar + * sync + * mv /mnt/B/bar /mnt/A/bar + * mv -T /mnt/A /mnt/B + * fsync /mnt/B/bar + * + * + * If we ignore the old parent B which got deleted, + * after a log replay we would have file bar linked + * at both parents and the old parent B would still + * exist. + */ + if (IS_ERR(dir_inode)) { + ret = PTR_ERR(dir_inode); + goto out; + } if (ctx) ctx->log_new_dentries = false; -- cgit v1.2.3