f2fs: fix to avoid deadlock between checkpoint and writepages
PATCH 8/8 f2fs: fix to avoid deadlock between checkpoint and writepages
This patch fixes to move f2fs_balance_fs out of sbi->writepages' coverage to avoid potential ABBA deadlock which was found by lockdep:
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(&sbi->writepages);
lock(&sbi->cp_mutex);
lock(&sbi->writepages); lock(&sbi->cp_mutex);
*** DEADLOCK ***
stack of CPU0:
[<ffffffff810b8dd1>] __lock_acquire+0x1321/0x1770 [<ffffffff810b92d7>] lock_acquire+0xb7/0x130 [<ffffffff817ad082>] mutex_lock_nested+0x52/0x380 [<ffffffffa07b767b>] f2fs_balance_fs+0x8b/0xa0 [f2fs] [<ffffffffa07afb5b>] f2fs_write_data_page+0x33b/0x460 [f2fs] [<ffffffffa07ab79a>] __f2fs_writepage+0x1a/0x50 [f2fs] [<ffffffffa07ac693>] T.1541+0x293/0x560 [f2fs] [<ffffffffa07aca8c>] f2fs_write_data_pages+0x12c/0x230 [f2fs] [<ffffffff8118adb3>] do_writepages+0x23/0x40 [<ffffffff8117c545>] __filemap_fdatawrite_range+0xb5/0xf0 [<ffffffff8117c623>] filemap_write_and_wait_range+0xa3/0xd0 [<ffffffffa079cc20>] f2fs_symlink+0x180/0x300 [f2fs] [<ffffffff81208187>] vfs_symlink+0xb7/0xe0 [<ffffffff8120acc5>] SyS_symlinkat+0xc5/0x100 [<ffffffff81205ad6>] SyS_symlink+0x16/0x20 [<ffffffff817b15d7>] entry_SYSCALL_64_fastpath+0x12/0x6f
stack of CPU1
[<ffffffff810b92d7>] lock_acquire+0xb7/0x130 [<ffffffff817ad082>] mutex_lock_nested+0x52/0x380 [<ffffffffa07aca7e>] f2fs_write_data_pages+0x11e/0x230 [f2fs] [<ffffffff8118adb3>] do_writepages+0x23/0x40 [<ffffffff8117c545>] __filemap_fdatawrite_range+0xb5/0xf0 [<ffffffff8117c9ef>] filemap_fdatawrite+0x1f/0x30 [<ffffffffa07a728d>] sync_dirty_inodes+0x4d/0xd0 [f2fs] [<ffffffffa07a7381>] block_operations+0x71/0x160 [f2fs] [<ffffffffa07a85f8>] write_checkpoint+0xe8/0xbb0 [f2fs] [<ffffffffa07a043f>] f2fs_sync_fs+0x8f/0xf0 [f2fs] [<ffffffffa07b63af>] f2fs_balance_fs_bg+0x6f/0xd0 [f2fs] [<ffffffffa07b1c97>] f2fs_write_node_pages+0x57/0x150 [f2fs] [<ffffffff8118adb3>] do_writepages+0x23/0x40 [<ffffffff8122c9ed>] __writeback_single_inode+0x6d/0x3d0 [<ffffffff8122ec87>] writeback_sb_inodes+0x2c7/0x520 [<ffffffff8122f193>] wb_writeback+0x133/0x330 [<ffffffff8122f478>] wb_do_writeback+0xe8/0x270 [<ffffffff8122f680>] wb_workfn+0x80/0x1f0 [<ffffffff81081a1c>] process_one_work+0x20c/0x5c0 [<ffffffff81083c62>] worker_thread+0x132/0x5f0 [<ffffffff8108918e>] kthread+0xde/0x100 [<ffffffff817b193f>] ret_from_fork+0x3f/0x70
--- fs/f2fs/data.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
fs/f2fs/data.c +3 -2
@@ -506,7 +506,6 @@ static void __allocate_data_blocks(struct inode *inode, loff_t offset,u64 end_offset;while (len) { -f2fs_balance_fs (sbi);f2fs_lock_op (sbi);/* When reading holes, we need its node page */
@@ -1186,7 +1185,7 @@ out:if (err)ClearPageUptodate (page);unlock_page (page); -if (need_balance_fs) +if (need_balance_fs && !test_opt (sbi,DATA_FLUSH ))f2fs_balance_fs (sbi);if (wbc->for_reclaim) {f2fs_submit_merged_bio (sbi,DATA ,WRITE );
@@ -1617,6 +1616,8 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,trace_f2fs_direct_IO_enter (inode, offset, count, rw);if (rw ==WRITE ) { +f2fs_balance_fs (sbi); +if (serialized)mutex_lock (&sbi->writepages);__allocate_data_blocks (inode, offset, count);
Signature · 1 line
2.6.3
Jaegeuk Kim
maintainerHi Chao,
Quoted 5 lines · Chao Yu
This patch fixes to move
f2fs_balance_fsout ofsbi->writepages' coverage to avoid potential ABBA deadlock which was found by lockdep:Possible unsafe locking scenario:
Quoted 8 lines
CPU0 CPU1 ---- ---- lock(&sbi->writepages); lock(&sbi->cp_mutex); lock(&sbi->writepages);
lock(&sbi->cp_mutex);*** DEADLOCK ***
I expect it will be fine if syncing is done by f2fs_balance_fs_bg().
Thanks,
Quoted 81 lines
stack of CPU0:
[<ffffffff810b8dd1>] __lock_acquire+0x1321/0x1770 [<ffffffff810b92d7>] lock_acquire+0xb7/0x130 [<ffffffff817ad082>] mutex_lock_nested+0x52/0x380 [<ffffffffa07b767b>] f2fs_balance_fs+0x8b/0xa0 [f2fs] [<ffffffffa07afb5b>] f2fs_write_data_page+0x33b/0x460 [f2fs] [<ffffffffa07ab79a>] __f2fs_writepage+0x1a/0x50 [f2fs] [<ffffffffa07ac693>] T.1541+0x293/0x560 [f2fs] [<ffffffffa07aca8c>] f2fs_write_data_pages+0x12c/0x230 [f2fs] [<ffffffff8118adb3>] do_writepages+0x23/0x40 [<ffffffff8117c545>] __filemap_fdatawrite_range+0xb5/0xf0 [<ffffffff8117c623>] filemap_write_and_wait_range+0xa3/0xd0 [<ffffffffa079cc20>] f2fs_symlink+0x180/0x300 [f2fs] [<ffffffff81208187>] vfs_symlink+0xb7/0xe0 [<ffffffff8120acc5>] SyS_symlinkat+0xc5/0x100 [<ffffffff81205ad6>] SyS_symlink+0x16/0x20 [<ffffffff817b15d7>] entry_SYSCALL_64_fastpath+0x12/0x6fstack of CPU1
[<ffffffff810b92d7>] lock_acquire+0xb7/0x130 [<ffffffff817ad082>] mutex_lock_nested+0x52/0x380 [<ffffffffa07aca7e>] f2fs_write_data_pages+0x11e/0x230 [f2fs] [<ffffffff8118adb3>] do_writepages+0x23/0x40 [<ffffffff8117c545>] __filemap_fdatawrite_range+0xb5/0xf0 [<ffffffff8117c9ef>] filemap_fdatawrite+0x1f/0x30 [<ffffffffa07a728d>] sync_dirty_inodes+0x4d/0xd0 [f2fs] [<ffffffffa07a7381>] block_operations+0x71/0x160 [f2fs] [<ffffffffa07a85f8>] write_checkpoint+0xe8/0xbb0 [f2fs] [<ffffffffa07a043f>] f2fs_sync_fs+0x8f/0xf0 [f2fs] [<ffffffffa07b63af>] f2fs_balance_fs_bg+0x6f/0xd0 [f2fs] [<ffffffffa07b1c97>] f2fs_write_node_pages+0x57/0x150 [f2fs] [<ffffffff8118adb3>] do_writepages+0x23/0x40 [<ffffffff8122c9ed>] __writeback_single_inode+0x6d/0x3d0 [<ffffffff8122ec87>] writeback_sb_inodes+0x2c7/0x520 [<ffffffff8122f193>] wb_writeback+0x133/0x330 [<ffffffff8122f478>] wb_do_writeback+0xe8/0x270 [<ffffffff8122f680>] wb_workfn+0x80/0x1f0 [<ffffffff81081a1c>] process_one_work+0x20c/0x5c0 [<ffffffff81083c62>] worker_thread+0x132/0x5f0 [<ffffffff8108918e>] kthread+0xde/0x100 [<ffffffff817b193f>] ret_from_fork+0x3f/0x70Signed-off-by Chao Yu <[email protected]>--- fs/f2fs/data.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)fs/f2fs/data.c +3
-2@@ -506,7 +506,6 @@ static void __allocate_data_blocks(struct inode *inode, loff_t offset,u64 end_offset;while (len) { -f2fs_balance_fs (sbi);f2fs_lock_op (sbi);/* When reading holes, we need its node page */ @@ -1186,7 +1185,7 @@ out:if (err)ClearPageUptodate (page);unlock_page (page); -if (need_balance_fs) +if (need_balance_fs && !test_opt (sbi,DATA_FLUSH ))f2fs_balance_fs (sbi);if (wbc->for_reclaim) {f2fs_submit_merged_bio (sbi,DATA ,WRITE );@@ -1617,6 +1616,8 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,trace_f2fs_direct_IO_enter (inode, offset, count, rw);if (rw ==WRITE ) { +f2fs_balance_fs (sbi); +if (serialized)mutex_lock (&sbi->writepages);__allocate_data_blocks (inode, offset, count);Signature · 1 line
2.6.3
Hi Jaegeuk,
Quoted 22 lines
-----Original Message-----
From: Jaegeuk Kim [mailto:[email protected]]
Sent: Wednesday, December 16, 2015 6:01 AM
To: Chao Yu
Cc: [email protected]; [email protected]
Subject: Re: [PATCH 8/8] f2fs: fix to avoid deadlock between checkpoint and writepagesHi Chao,
Quoted 12 lines · Chao Yu
This patch fixes to move
f2fs_balance_fsout ofsbi->writepages' coverage to avoid potential ABBA deadlock which was found by lockdep:Possible unsafe locking scenario:CPU0 CPU1 ---- ---- lock(&sbi->writepages); lock(&sbi->cp_mutex); lock(&sbi->writepages);
lock(&sbi->cp_mutex);
Quoted 3 lines
Quoted 1 line
*** DEADLOCK ***
I expect it will be fine if syncing is done by
f2fs_balance_fs_bg().
Yes, I will drop this patch.
Thanks,
Quoted 84 lines
Thanks,
Quoted 81 lines
stack of CPU0:
[<ffffffff810b8dd1>] __lock_acquire+0x1321/0x1770 [<ffffffff810b92d7>] lock_acquire+0xb7/0x130 [<ffffffff817ad082>] mutex_lock_nested+0x52/0x380 [<ffffffffa07b767b>] f2fs_balance_fs+0x8b/0xa0 [f2fs] [<ffffffffa07afb5b>] f2fs_write_data_page+0x33b/0x460 [f2fs] [<ffffffffa07ab79a>] __f2fs_writepage+0x1a/0x50 [f2fs] [<ffffffffa07ac693>] T.1541+0x293/0x560 [f2fs] [<ffffffffa07aca8c>] f2fs_write_data_pages+0x12c/0x230 [f2fs] [<ffffffff8118adb3>] do_writepages+0x23/0x40 [<ffffffff8117c545>] __filemap_fdatawrite_range+0xb5/0xf0 [<ffffffff8117c623>] filemap_write_and_wait_range+0xa3/0xd0 [<ffffffffa079cc20>] f2fs_symlink+0x180/0x300 [f2fs] [<ffffffff81208187>] vfs_symlink+0xb7/0xe0 [<ffffffff8120acc5>] SyS_symlinkat+0xc5/0x100 [<ffffffff81205ad6>] SyS_symlink+0x16/0x20 [<ffffffff817b15d7>] entry_SYSCALL_64_fastpath+0x12/0x6fstack of CPU1
[<ffffffff810b92d7>] lock_acquire+0xb7/0x130 [<ffffffff817ad082>] mutex_lock_nested+0x52/0x380 [<ffffffffa07aca7e>] f2fs_write_data_pages+0x11e/0x230 [f2fs] [<ffffffff8118adb3>] do_writepages+0x23/0x40 [<ffffffff8117c545>] __filemap_fdatawrite_range+0xb5/0xf0 [<ffffffff8117c9ef>] filemap_fdatawrite+0x1f/0x30 [<ffffffffa07a728d>] sync_dirty_inodes+0x4d/0xd0 [f2fs] [<ffffffffa07a7381>] block_operations+0x71/0x160 [f2fs] [<ffffffffa07a85f8>] write_checkpoint+0xe8/0xbb0 [f2fs] [<ffffffffa07a043f>] f2fs_sync_fs+0x8f/0xf0 [f2fs] [<ffffffffa07b63af>] f2fs_balance_fs_bg+0x6f/0xd0 [f2fs] [<ffffffffa07b1c97>] f2fs_write_node_pages+0x57/0x150 [f2fs] [<ffffffff8118adb3>] do_writepages+0x23/0x40 [<ffffffff8122c9ed>] __writeback_single_inode+0x6d/0x3d0 [<ffffffff8122ec87>] writeback_sb_inodes+0x2c7/0x520 [<ffffffff8122f193>] wb_writeback+0x133/0x330 [<ffffffff8122f478>] wb_do_writeback+0xe8/0x270 [<ffffffff8122f680>] wb_workfn+0x80/0x1f0 [<ffffffff81081a1c>] process_one_work+0x20c/0x5c0 [<ffffffff81083c62>] worker_thread+0x132/0x5f0 [<ffffffff8108918e>] kthread+0xde/0x100 [<ffffffff817b193f>] ret_from_fork+0x3f/0x70Signed-off-by Chao Yu <[email protected]>--- fs/f2fs/data.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)fs/f2fs/data.c +3
-3@@ -506,7 +506,6 @@ static void __allocate_data_blocks(struct inode *inode, loff_t offset,u64 end_offset;while (len) { -f2fs_balance_fs (sbi);f2fs_lock_op (sbi);/* When reading holes, we need its node page */ @@ -1186,7 +1185,7 @@ out:if (err)ClearPageUptodate (page);unlock_page (page); -if (need_balance_fs) +if (need_balance_fs && !test_opt (sbi,DATA_FLUSH ))f2fs_balance_fs (sbi);if (wbc->for_reclaim) {f2fs_submit_merged_bio (sbi,DATA ,WRITE );@@ -1617,6 +1616,8 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,trace_f2fs_direct_IO_enter (inode, offset, count, rw);if (rw ==WRITE ) { +f2fs_balance_fs (sbi); +if (serialized)mutex_lock (&sbi->writepages);__allocate_data_blocks (inode, offset, count); --2.6.3