[PATCH 3/3] kernel/workqueue: Suppress a false positive lockdep complaint

[Bart Van Assche]

It can happen that the direct I/O queue creates and destroys an empty
workqueue from inside a work function. Avoid that this triggers the
false positive lockdep complaint shown below.

======================================================
WARNING: possible circular locking dependency detected
4.19.0-dbg+ #1 Not tainted
------------------------------------------------------
fio/4129 is trying to acquire lock:
00000000a01cfe1a ((wq_completion)"dio/%s"sb->s_id){+.+.}, at: flush_workqueue+0xd0/0x970

but task is already holding lock:
00000000a0acecf9 (&sb->s_type->i_mutex_key#14){+.+.}, at: ext4_file_write_iter+0x154/0x710

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #2 (&sb->s_type->i_mutex_key#14){+.+.}:
       down_write+0x3d/0x80
       __generic_file_fsync+0x77/0xf0
       ext4_sync_file+0x3c9/0x780
       vfs_fsync_range+0x66/0x100
       dio_complete+0x2f5/0x360
       dio_aio_complete_work+0x1c/0x20
       process_one_work+0x481/0x9f0
       worker_thread+0x63/0x5a0
       kthread+0x1cf/0x1f0
       ret_from_fork+0x24/0x30

-> #1 ((work_completion)(&dio->complete_work)){+.+.}:
       process_one_work+0x447/0x9f0
       worker_thread+0x63/0x5a0
       kthread+0x1cf/0x1f0
       ret_from_fork+0x24/0x30

-> #0 ((wq_completion)"dio/%s"sb->s_id){+.+.}:
       lock_acquire+0xc5/0x200
       flush_workqueue+0xf3/0x970
       drain_workqueue+0xec/0x220
       destroy_workqueue+0x23/0x350
       sb_init_dio_done_wq+0x6a/0x80
       do_blockdev_direct_IO+0x1f33/0x4be0
       __blockdev_direct_IO+0x79/0x86
       ext4_direct_IO+0x5df/0xbb0
       generic_file_direct_write+0x119/0x220
       __generic_file_write_iter+0x131/0x2d0
       ext4_file_write_iter+0x3fa/0x710
       aio_write+0x235/0x330
       io_submit_one+0x510/0xeb0
       __x64_sys_io_submit+0x122/0x340
       do_syscall_64+0x71/0x220
       entry_SYSCALL_64_after_hwframe+0x49/0xbe

other info that might help us debug this:

Chain exists of:
  (wq_completion)"dio/%s"sb->s_id --> (work_completion)(&dio->complete_work) --> &sb->s_type->i_mutex_key#14

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(&sb->s_type->i_mutex_key#14);
                               lock((work_completion)(&dio->complete_work));
                               lock(&sb->s_type->i_mutex_key#14);
  lock((wq_completion)"dio/%s"sb->s_id);

 *** DEADLOCK ***

1 lock held by fio/4129:
 #0: 00000000a0acecf9 (&sb->s_type->i_mutex_key#14){+.+.}, at: ext4_file_write_iter+0x154/0x710

stack backtrace:
CPU: 3 PID: 4129 Comm: fio Not tainted 4.19.0-dbg+ #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014
Call Trace:
 dump_stack+0x86/0xc5
 print_circular_bug.isra.32+0x20a/0x218
 __lock_acquire+0x1c68/0x1cf0
 lock_acquire+0xc5/0x200
 flush_workqueue+0xf3/0x970
 drain_workqueue+0xec/0x220
 destroy_workqueue+0x23/0x350
 sb_init_dio_done_wq+0x6a/0x80
 do_blockdev_direct_IO+0x1f33/0x4be0
 __blockdev_direct_IO+0x79/0x86
 ext4_direct_IO+0x5df/0xbb0
 generic_file_direct_write+0x119/0x220
 __generic_file_write_iter+0x131/0x2d0
 ext4_file_write_iter+0x3fa/0x710
 aio_write+0x235/0x330
 io_submit_one+0x510/0xeb0
 __x64_sys_io_submit+0x122/0x340
 do_syscall_64+0x71/0x220
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Cc: Johannes Berg <johannes.berg@xxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Sagi Grimberg <sagi@xxxxxxxxxxx>
Signed-off-by: Bart Van Assche <bvanassche@xxxxxxx>
---
 include/linux/workqueue.h | 1 +
 kernel/workqueue.c        | 6 +++++-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 60d673e15632..375ec764f148 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -344,6 +344,7 @@ enum {
 	__WQ_ORDERED		= 1 << 17, /* internal: workqueue is ordered */
 	__WQ_LEGACY		= 1 << 18, /* internal: create*_workqueue() */
 	__WQ_ORDERED_EXPLICIT	= 1 << 19, /* internal: alloc_ordered_workqueue() */
+	__WQ_HAS_BEEN_USED	= 1 << 20, /* internal: work has been queued */
 
 	WQ_MAX_ACTIVE		= 512,	  /* I like 512, better ideas? */
 	WQ_MAX_UNBOUND_PER_CPU	= 4,	  /* 4 * #cpus for unbound wq */
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index fc9129d5909e..0ef275fe526c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1383,6 +1383,10 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 	if (unlikely(wq->flags & __WQ_DRAINING) &&
 	    WARN_ON_ONCE(!is_chained_work(wq)))
 		return;
+
+	if (!(wq->flags & __WQ_HAS_BEEN_USED))
+		wq->flags |= __WQ_HAS_BEEN_USED;
+
 retry:
 	if (req_cpu == WORK_CPU_UNBOUND)
 		cpu = wq_select_unbound_cpu(raw_smp_processor_id());
@@ -2889,7 +2893,7 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr,
 	 * workqueues the deadlock happens when the rescuer stalls, blocking
 	 * forward progress.
 	 */
-	if (!from_cancel &&
+	if (!from_cancel && (pwq->wq->flags & __WQ_HAS_BEEN_USED) &&
 	    (pwq->wq->saved_max_active == 1 || pwq->wq->rescuer)) {
 		lock_acquire_exclusive(&pwq->wq->lockdep_map, 0, 0, NULL,
 				       _THIS_IP_);
-- 
2.19.1.568.g152ad8e336-goog