From df2c95f33e0a28b22509e4ee85365eedf32a1056 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Mon, 15 Aug 2016 10:36:52 +0800 Subject: btrfs: qgroup: Fix qgroup incorrectness caused by log replay When doing log replay at mount time(after power loss), qgroup will leak numbers of replayed data extents. The cause is almost the same of balance. So fix it by manually informing qgroup for owner changed extents. The bug can be detected by btrfs/119 test case. Cc: Mark Fasheh Signed-off-by: Qu Wenruo Reviewed-and-Tested-by: Goldwyn Rodrigues Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/tree-log.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'fs/btrfs/tree-log.c') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index fff3f3efa436..ffe92da81b8a 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -27,6 +27,7 @@ #include "backref.h" #include "hash.h" #include "compression.h" +#include "qgroup.h" /* magic values for the inode_only field in btrfs_log_inode: * @@ -680,6 +681,21 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, ins.type = BTRFS_EXTENT_ITEM_KEY; offset = key->offset - btrfs_file_extent_offset(eb, item); + /* + * Manually record dirty extent, as here we did a shallow + * file extent item copy and skip normal backref update, + * but modifying extent tree all by ourselves. + * So need to manually record dirty extent for qgroup, + * as the owner of the file extent changed from log tree + * (doesn't affect qgroup) to fs/file tree(affects qgroup) + */ + ret = btrfs_qgroup_insert_dirty_extent(trans, root->fs_info, + btrfs_file_extent_disk_bytenr(eb, item), + btrfs_file_extent_disk_num_bytes(eb, item), + GFP_NOFS); + if (ret < 0) + goto out; + if (ins.objectid > 0) { u64 csum_start; u64 csum_end; -- cgit v1.2.3 From 28a235931b56d4e7bdd51f6733daf95f2b269da8 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 23 Aug 2016 21:13:51 +0100 Subject: Btrfs: fix lockdep warning on deadlock against an inode's log mutex Commit 44f714dae50a ("Btrfs: improve performance on fsync against new inode after rename/unlink"), which landed in 4.8-rc2, introduced a possibility for a deadlock due to double locking of an inode's log mutex by the same task, which lockdep reports with: [23045.433975] ============================================= [23045.434748] [ INFO: possible recursive locking detected ] [23045.435426] 4.7.0-rc6-btrfs-next-34+ #1 Not tainted [23045.436044] --------------------------------------------- [23045.436044] xfs_io/3688 is trying to acquire lock: [23045.436044] (&ei->log_mutex){+.+...}, at: [] btrfs_log_inode+0x13a/0xc95 [btrfs] [23045.436044] but task is already holding lock: [23045.436044] (&ei->log_mutex){+.+...}, at: [] btrfs_log_inode+0x13a/0xc95 [btrfs] [23045.436044] other info that might help us debug this: [23045.436044] Possible unsafe locking scenario: [23045.436044] CPU0 [23045.436044] ---- [23045.436044] lock(&ei->log_mutex); [23045.436044] lock(&ei->log_mutex); [23045.436044] *** DEADLOCK *** [23045.436044] May be due to missing lock nesting notation [23045.436044] 3 locks held by xfs_io/3688: [23045.436044] #0: (&sb->s_type->i_mutex_key#15){+.+...}, at: [] btrfs_sync_file+0x14e/0x425 [btrfs] [23045.436044] #1: (sb_internal#2){.+.+.+}, at: [] __sb_start_write+0x5f/0xb0 [23045.436044] #2: (&ei->log_mutex){+.+...}, at: [] btrfs_log_inode+0x13a/0xc95 [btrfs] [23045.436044] stack backtrace: [23045.436044] CPU: 4 PID: 3688 Comm: xfs_io Not tainted 4.7.0-rc6-btrfs-next-34+ #1 [23045.436044] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.1-0-gb3ef39f-prebuilt.qemu-project.org 04/01/2014 [23045.436044] 0000000000000000 ffff88022f5f7860 ffffffff8127074d ffffffff82a54b70 [23045.436044] ffffffff82a54b70 ffff88022f5f7920 ffffffff81092897 ffff880228015d68 [23045.436044] 0000000000000000 ffffffff82a54b70 ffffffff829c3f00 ffff880228015d68 [23045.436044] Call Trace: [23045.436044] [] dump_stack+0x67/0x90 [23045.436044] [] __lock_acquire+0xcbb/0xe4e [23045.436044] [] ? mark_lock+0x24/0x201 [23045.436044] [] ? mark_held_locks+0x5e/0x74 [23045.436044] [] lock_acquire+0x12f/0x1c3 [23045.436044] [] ? lock_acquire+0x12f/0x1c3 [23045.436044] [] ? btrfs_log_inode+0x13a/0xc95 [btrfs] [23045.436044] [] ? btrfs_log_inode+0x13a/0xc95 [btrfs] [23045.436044] [] mutex_lock_nested+0x77/0x3a7 [23045.436044] [] ? btrfs_log_inode+0x13a/0xc95 [btrfs] [23045.436044] [] ? btrfs_release_delayed_node+0xb/0xd [btrfs] [23045.436044] [] btrfs_log_inode+0x13a/0xc95 [btrfs] [23045.436044] [] ? btrfs_log_inode+0x13a/0xc95 [btrfs] [23045.436044] [] ? vprintk_emit+0x453/0x465 [23045.436044] [] btrfs_log_inode+0x66e/0xc95 [btrfs] [23045.436044] [] log_new_dir_dentries+0x26c/0x359 [btrfs] [23045.436044] [] btrfs_log_inode_parent+0x4a6/0x628 [btrfs] [23045.436044] [] btrfs_log_dentry_safe+0x5a/0x75 [btrfs] [23045.436044] [] btrfs_sync_file+0x304/0x425 [btrfs] [23045.436044] [] vfs_fsync_range+0x8c/0x9e [23045.436044] [] vfs_fsync+0x1c/0x1e [23045.436044] [] do_fsync+0x31/0x4a [23045.436044] [] SyS_fsync+0x10/0x14 [23045.436044] [] entry_SYSCALL_64_fastpath+0x18/0xa8 [23045.436044] [] ? trace_hardirqs_off_caller+0x3f/0xaa An example reproducer for this is: $ mkfs.btrfs -f /dev/sdb $ mount /dev/sdb /mnt $ mkdir /mnt/dir $ touch /mnt/dir/foo $ sync $ mv /mnt/dir/foo /mnt/dir/bar $ touch /mnt/dir/foo $ xfs_io -c "fsync" /mnt/dir/bar This is because while logging the inode of file bar we end up logging its parent directory (since its inode has an unlink_trans field matching the current transaction id due to the rename operation), which in turn logs the inodes for all its new dentries, so that the new inode for the new file named foo gets logged which in turn triggered another logging attempt for the inode we are fsync'ing, since that inode had an old name that corresponds to the name of the new inode. So fix this by ensuring that when logging the inode for a new dentry that has a name matching an old name of some other inode, we don't log again the original inode that we are fsync'ing. Fixes: 44f714dae50a ("Btrfs: improve performance on fsync against new inode after rename/unlink") Signed-off-by: Filipe Manana Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/tree-log.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'fs/btrfs/tree-log.c') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index ffe92da81b8a..e935035ac034 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2823,7 +2823,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, */ mutex_unlock(&root->log_mutex); - btrfs_init_log_ctx(&root_log_ctx); + btrfs_init_log_ctx(&root_log_ctx, NULL); mutex_lock(&log_root_tree->log_mutex); atomic_inc(&log_root_tree->log_batch); @@ -4757,7 +4757,8 @@ again: if (ret < 0) { err = ret; goto out_unlock; - } else if (ret > 0) { + } else if (ret > 0 && ctx && + other_ino != btrfs_ino(ctx->inode)) { struct btrfs_key inode_key; struct inode *other_inode; -- cgit v1.2.3