io-wq: fix cancellation on create-worker failure

WARNING: CPU: 0 PID: 10392 at fs/io_uring.c:1151 req_ref_put_and_test
fs/io_uring.c:1151 [inline]
WARNING: CPU: 0 PID: 10392 at fs/io_uring.c:1151 req_ref_put_and_test
fs/io_uring.c:1146 [inline]
WARNING: CPU: 0 PID: 10392 at fs/io_uring.c:1151
io_req_complete_post+0xf5b/0x1190 fs/io_uring.c:1794
Modules linked in:
Call Trace:
 tctx_task_work+0x1e5/0x570 fs/io_uring.c:2158
 task_work_run+0xe0/0x1a0 kernel/task_work.c:164
 tracehook_notify_signal include/linux/tracehook.h:212 [inline]
 handle_signal_work kernel/entry/common.c:146 [inline]
 exit_to_user_mode_loop kernel/entry/common.c:172 [inline]
 exit_to_user_mode_prepare+0x232/0x2a0 kernel/entry/common.c:209
 __syscall_exit_to_user_mode_work kernel/entry/common.c:291 [inline]
 syscall_exit_to_user_mode+0x19/0x60 kernel/entry/common.c:302
 do_syscall_64+0x42/0xb0 arch/x86/entry/common.c:86
 entry_SYSCALL_64_after_hwframe+0x44/0xae

When io_wqe_enqueue() -> io_wqe_create_worker() fails, we can't just
call io_run_cancel() to clean up the request, it's already enqueued via
io_wqe_insert_work() and will be executed either by some other worker
during cancellation (e.g. in io_wq_put_and_exit()).

Reported-by: Hao Sun <sunhao.th@gmail.com>
Fixes: 3146cba99aa28 ("io-wq: make worker creation resilient against signals")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/93b9de0fcf657affab0acfd675d4abcd273ee863.1631092071.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/fs/io-wq.c b/fs/io-wq.c
index d80e4a735677d0f2c6832b7e196e42953acf8fac..35e7ee26f7ea7cd3383c76869450ddb01c9682b2 100644 (file)
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -832,6 +832,11 @@ append:
        wq_list_add_after(&work->list, &tail->list, &acct->work_list);
 }
 
+static bool io_wq_work_match_item(struct io_wq_work *work, void *data)
+{
+       return work == data;
+}
+
 static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
 {
        struct io_wqe_acct *acct = io_work_get_acct(wqe, work);
@@ -844,7 +849,6 @@ static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
         */
        if (test_bit(IO_WQ_BIT_EXIT, &wqe->wq->state) ||
            (work->flags & IO_WQ_WORK_CANCEL)) {
-run_cancel:
                io_run_cancel(work, wqe);
                return;
        }
@@ -864,15 +868,22 @@ run_cancel:
                bool did_create;
 
                did_create = io_wqe_create_worker(wqe, acct);
-               if (unlikely(!did_create)) {
-                       raw_spin_lock(&wqe->lock);
-                       /* fatal condition, failed to create the first worker */
-                       if (!acct->nr_workers) {
-                               raw_spin_unlock(&wqe->lock);
-                               goto run_cancel;
-                       }
-                       raw_spin_unlock(&wqe->lock);
+               if (likely(did_create))
+                       return;
+
+               raw_spin_lock(&wqe->lock);
+               /* fatal condition, failed to create the first worker */
+               if (!acct->nr_workers) {
+                       struct io_cb_cancel_data match = {
+                               .fn             = io_wq_work_match_item,
+                               .data           = work,
+                               .cancel_all     = false,
+                       };
+
+                       if (io_acct_cancel_pending_work(wqe, acct, &match))
+                               raw_spin_lock(&wqe->lock);
                }
+               raw_spin_unlock(&wqe->lock);
        }
 }