io-wq: remove worker to owner tw dependency

INFO: task iou-wrk-6609:6612 blocked for more than 143 seconds.
      Not tainted 5.15.0-rc5-syzkaller #0
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:iou-wrk-6609    state:D stack:27944 pid: 6612 ppid:  6526 flags:0x00004006
Call Trace:
 context_switch kernel/sched/core.c:4940 [inline]
 __schedule+0xb44/0x5960 kernel/sched/core.c:6287
 schedule+0xd3/0x270 kernel/sched/core.c:6366
 schedule_timeout+0x1db/0x2a0 kernel/time/timer.c:1857
 do_wait_for_common kernel/sched/completion.c:85 [inline]
 __wait_for_common kernel/sched/completion.c:106 [inline]
 wait_for_common kernel/sched/completion.c:117 [inline]
 wait_for_completion+0x176/0x280 kernel/sched/completion.c:138
 io_worker_exit fs/io-wq.c:183 [inline]
 io_wqe_worker+0x66d/0xc40 fs/io-wq.c:597
 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:295

io-wq worker may submit a task_work to the master task and upon
io_worker_exit() wait for the tw to get executed. The problem appears
when the master task is waiting in coredump.c:

468                     freezer_do_not_count();
469                     wait_for_completion(&core_state->startup);
470                     freezer_count();

Apparently having some dependency on children threads getting everything
stuck. Workaround it by cancelling the taks_work callback that causes it
before going into io_worker_exit() waiting.

p.s. probably a better option is to not submit tw elevating the refcount
in the first place, but let's leave this excercise for the future.

Cc: stable@vger.kernel.org
Reported-and-tested-by: syzbot+27d62ee6f256b186883e@syzkaller.appspotmail.com
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/142a716f4ed936feae868959059154362bfa8c19.1635509451.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 37 insertions, 9 deletions

diff --git a/fs/io-wq.c b/fs/io-wq.c
index 0c283bb18fb2..fe6b2abcaa49 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -140,6 +140,7 @@ static void io_wqe_dec_running(struct io_worker *worker);
 static bool io_acct_cancel_pending_work(struct io_wqe *wqe,
 					struct io_wqe_acct *acct,
 					struct io_cb_cancel_data *match);
+static void create_worker_cb(struct callback_head *cb);
 
 static bool io_worker_get(struct io_worker *worker)
 {
@@ -174,9 +175,44 @@ static void io_worker_ref_put(struct io_wq *wq)
 		complete(&wq->worker_done);
 }
 
+static void io_worker_cancel_cb(struct io_worker *worker)
+{
+	struct io_wqe_acct *acct = io_wqe_get_acct(worker);
+	struct io_wqe *wqe = worker->wqe;
+	struct io_wq *wq = wqe->wq;
+
+	atomic_dec(&acct->nr_running);
+	raw_spin_lock(&worker->wqe->lock);
+	acct->nr_workers--;
+	raw_spin_unlock(&worker->wqe->lock);
+	io_worker_ref_put(wq);
+	clear_bit_unlock(0, &worker->create_state);
+	io_worker_release(worker);
+}
+
+static bool io_task_worker_match(struct callback_head *cb, void *data)
+{
+	struct io_worker *worker;
+
+	if (cb->func != create_worker_cb)
+		return false;
+	worker = container_of(cb, struct io_worker, create_work);
+	return worker == data;
+}
+
 static void io_worker_exit(struct io_worker *worker)
 {
 	struct io_wqe *wqe = worker->wqe;
+	struct io_wq *wq = wqe->wq;
+
+	while (1) {
+		struct callback_head *cb = task_work_cancel_match(wq->task,
+						io_task_worker_match, worker);
+
+		if (!cb)
+			break;
+		io_worker_cancel_cb(worker);
+	}
 
 	io_worker_release(worker);
 	wait_for_completion(&worker->ref_done);
@@ -1148,17 +1184,9 @@ static void io_wq_exit_workers(struct io_wq *wq)
 
 	while ((cb = task_work_cancel_match(wq->task, io_task_work_match, wq)) != NULL) {
 		struct io_worker *worker;
-		struct io_wqe_acct *acct;
 
 		worker = container_of(cb, struct io_worker, create_work);
-		acct = io_wqe_get_acct(worker);
-		atomic_dec(&acct->nr_running);
-		raw_spin_lock(&worker->wqe->lock);
-		acct->nr_workers--;
-		raw_spin_unlock(&worker->wqe->lock);
-		io_worker_ref_put(wq);
-		clear_bit_unlock(0, &worker->create_state);
-		io_worker_release(worker);
+		io_worker_cancel_cb(worker);
 	}
 
 	rcu_read_lock();