From: Wengang Wang <wen.gang.wang@xxxxxxxxxx>
commit 90bd070aae6c4fb5d302f9c4b9c88be60c8197ec upstream.
The following deadlock is detected:
truncate -> setattr path is waiting for pending direct IO to be done (inode->i_dio_count become zero) with inode->i_rwsem held (down_write).
PID: 14827 TASK: ffff881686a9af80 CPU: 20 COMMAND: "ora_p005_hrltd9"
#0 __schedule at ffffffff818667cc
#1 schedule at ffffffff81866de6
#2 inode_dio_wait at ffffffff812a2d04
#3 ocfs2_setattr at ffffffffc05f322e [ocfs2]
#4 notify_change at ffffffff812a5a09
#5 do_truncate at ffffffff812808f5
#6 do_sys_ftruncate.constprop.18 at ffffffff81280cf2
#7 sys_ftruncate at ffffffff81280d8e
#8 do_syscall_64 at ffffffff81003949
#9 entry_SYSCALL_64_after_hwframe at ffffffff81a001ad
dio completion path is going to complete one direct IO (decrement
inode->i_dio_count), but before that it hung at locking inode->i_rwsem:
#0 __schedule+700 at ffffffff818667cc
#1 schedule+54 at ffffffff81866de6
#2 rwsem_down_write_failed+536 at ffffffff8186aa28
#3 call_rwsem_down_write_failed+23 at ffffffff8185a1b7
#4 down_write+45 at ffffffff81869c9d
#5 ocfs2_dio_end_io_write+180 at ffffffffc05d5444 [ocfs2]
#6 ocfs2_dio_end_io+85 at ffffffffc05d5a85 [ocfs2]
#7 dio_complete+140 at ffffffff812c873c
#8 dio_aio_complete_work+25 at ffffffff812c89f9
#9 process_one_work+361 at ffffffff810b1889
#10 worker_thread+77 at ffffffff810b233d
#11 kthread+261 at ffffffff810b7fd5
#12 ret_from_fork+62 at ffffffff81a0035e
Thus above forms ABBA deadlock. The same deadlock was mentioned in
upstream commit 28f5a8a7c033 ("ocfs2: should wait dio before inode lock
in ocfs2_setattr()"). It seems that that commit only removed the
cluster lock (the victim of above dead lock) from the ABBA deadlock
party.
End-user visible effects: Process hang in truncate -> ocfs2_setattr path
and other processes hang at ocfs2_dio_end_io_write path.
This is to fix the deadlock itself. It removes inode_lock() call from
dio completion path to remove the deadlock and add ip_alloc_sem lock in
setattr path to synchronize the inode modifications.
[wen.gang.wang@xxxxxxxxxx: remove the "had_alloc_lock" as suggested]
Link: https://lkml.kernel.org/r/20210402171344.1605-1-wen.gang.wang@xxxxxxxxxx
Link: https://lkml.kernel.org/r/20210331203654.3911-1-wen.gang.wang@xxxxxxxxxx
Signed-off-by: Wengang Wang <wen.gang.wang@xxxxxxxxxx>
Reviewed-by: Joseph Qi <joseph.qi@xxxxxxxxxxxxxxxxx>
Cc: Mark Fasheh <mark@xxxxxxxxxx>
Cc: Joel Becker <jlbec@xxxxxxxxxxxx>
Cc: Junxiao Bi <junxiao.bi@xxxxxxxxxx>
Cc: Changwei Ge <gechangwei@xxxxxxx>
Cc: Gang He <ghe@xxxxxxxx>
Cc: Jun Piao <piaojun@xxxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
fs/ocfs2/aops.c | 11 +----------
fs/ocfs2/file.c | 8 ++++++--
2 files changed, 7 insertions(+), 12 deletions(-)
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -2295,7 +2295,7 @@ static int ocfs2_dio_end_io_write(struct
struct ocfs2_alloc_context *meta_ac = NULL;
handle_t *handle = NULL;
loff_t end = offset + bytes;
- int ret = 0, credits = 0, locked = 0;
+ int ret = 0, credits = 0;
ocfs2_init_dealloc_ctxt(&dealloc);
@@ -2306,13 +2306,6 @@ static int ocfs2_dio_end_io_write(struct
!dwc->dw_orphaned)
goto out;
- /* ocfs2_file_write_iter will get i_mutex, so we need not lock if we
- * are in that context. */
- if (dwc->dw_writer_pid != task_pid_nr(current)) {
- inode_lock(inode);
- locked = 1;
- }
-
ret = ocfs2_inode_lock(inode, &di_bh, 1);
if (ret < 0) {
mlog_errno(ret);
@@ -2393,8 +2386,6 @@ out:
if (meta_ac)
ocfs2_free_alloc_context(meta_ac);
ocfs2_run_deallocs(osb, &dealloc);
- if (locked)
- inode_unlock(inode);
ocfs2_dio_free_write_ctx(inode, dwc);
return ret;
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1244,22 +1244,24 @@ int ocfs2_setattr(struct dentry *dentry,
goto bail_unlock;
}
}
+ down_write(&OCFS2_I(inode)->ip_alloc_sem);
handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS +
2 * ocfs2_quota_trans_credits(sb));
if (IS_ERR(handle)) {
status = PTR_ERR(handle);
mlog_errno(status);
- goto bail_unlock;
+ goto bail_unlock_alloc;
}
status = __dquot_transfer(inode, transfer_to);
if (status < 0)
goto bail_commit;
} else {
+ down_write(&OCFS2_I(inode)->ip_alloc_sem);
handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
if (IS_ERR(handle)) {
status = PTR_ERR(handle);
mlog_errno(status);
- goto bail_unlock;
+ goto bail_unlock_alloc;
}
}
@@ -1272,6 +1274,8 @@ int ocfs2_setattr(struct dentry *dentry,
bail_commit:
ocfs2_commit_trans(osb, handle);
+bail_unlock_alloc:
+ up_write(&OCFS2_I(inode)->ip_alloc_sem);
bail_unlock:
if (status && inode_locked) {
ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock);
