io_uring: fix cancellation taking mutex while TASK_UNINTERRUPTIBLE

do not call blocking ops when !TASK_RUNNING; state=2 set at
	[<00000000ced9dbfc>] prepare_to_wait+0x1f4/0x3b0
	kernel/sched/wait.c:262
WARNING: CPU: 1 PID: 19888 at kernel/sched/core.c:7853
	__might_sleep+0xed/0x100 kernel/sched/core.c:7848
RIP: 0010:__might_sleep+0xed/0x100 kernel/sched/core.c:7848
Call Trace:
 __mutex_lock_common+0xc4/0x2ef0 kernel/locking/mutex.c:935
 __mutex_lock kernel/locking/mutex.c:1103 [inline]
 mutex_lock_nested+0x1a/0x20 kernel/locking/mutex.c:1118
 io_wq_submit_work+0x39a/0x720 fs/io_uring.c:6411
 io_run_cancel fs/io-wq.c:856 [inline]
 io_wqe_cancel_pending_work fs/io-wq.c:990 [inline]
 io_wq_cancel_cb+0x614/0xcb0 fs/io-wq.c:1027
 io_uring_cancel_files fs/io_uring.c:8874 [inline]
 io_uring_cancel_task_requests fs/io_uring.c:8952 [inline]
 __io_uring_files_cancel+0x115d/0x19e0 fs/io_uring.c:9038
 io_uring_files_cancel include/linux/io_uring.h:51 [inline]
 do_exit+0x2e6/0x2490 kernel/exit.c:780
 do_group_exit+0x168/0x2d0 kernel/exit.c:922
 get_signal+0x16b5/0x2030 kernel/signal.c:2770
 arch_do_signal_or_restart+0x8e/0x6a0 arch/x86/kernel/signal.c:811
 handle_signal_work kernel/entry/common.c:147 [inline]
 exit_to_user_mode_loop kernel/entry/common.c:171 [inline]
 exit_to_user_mode_prepare+0xac/0x1e0 kernel/entry/common.c:201
 __syscall_exit_to_user_mode_work kernel/entry/common.c:291 [inline]
 syscall_exit_to_user_mode+0x48/0x190 kernel/entry/common.c:302
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Rewrite io_uring_cancel_files() to mimic __io_uring_task_cancel()'s
counting scheme, so it does all the heavy work before setting
TASK_UNINTERRUPTIBLE.

Cc: stable@vger.kernel.org # 5.9+
Reported-by: syzbot+f655445043a26a7cfab8@syzkaller.appspotmail.com
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
[axboe: fix inverted task check]
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 09aada1..bb0270e 100644 (file)
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -8873,30 +8873,31 @@ static void io_cancel_defer_files(struct io_ring_ctx *ctx,
        }
 }
 
+static int io_uring_count_inflight(struct io_ring_ctx *ctx,
+                                  struct task_struct *task,
+                                  struct files_struct *files)
+{
+       struct io_kiocb *req;
+       int cnt = 0;
+
+       spin_lock_irq(&ctx->inflight_lock);
+       list_for_each_entry(req, &ctx->inflight_list, inflight_entry)
+               cnt += io_match_task(req, task, files);
+       spin_unlock_irq(&ctx->inflight_lock);
+       return cnt;
+}
+
 static void io_uring_cancel_files(struct io_ring_ctx *ctx,
                                  struct task_struct *task,
                                  struct files_struct *files)
 {
        while (!list_empty_careful(&ctx->inflight_list)) {
                struct io_task_cancel cancel = { .task = task, .files = files };
-               struct io_kiocb *req;
                DEFINE_WAIT(wait);
-               bool found = false;
-
-               spin_lock_irq(&ctx->inflight_lock);
-               list_for_each_entry(req, &ctx->inflight_list, inflight_entry) {
-                       if (!io_match_task(req, task, files))
-                               continue;
-                       found = true;
-                       break;
-               }
-               if (found)
-                       prepare_to_wait(&task->io_uring->wait, &wait,
-                                       TASK_UNINTERRUPTIBLE);
-               spin_unlock_irq(&ctx->inflight_lock);
+               int inflight;
 
-               /* We need to keep going until we don't find a matching req */
-               if (!found)
+               inflight = io_uring_count_inflight(ctx, task, files);
+               if (!inflight)
                        break;
 
                io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, &cancel, true);
@@ -8905,7 +8906,11 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
                io_cqring_overflow_flush(ctx, true, task, files);
                /* cancellations _may_ trigger task work */
                io_run_task_work();
-               schedule();
+
+               prepare_to_wait(&task->io_uring->wait, &wait,
+                               TASK_UNINTERRUPTIBLE);
+               if (inflight == io_uring_count_inflight(ctx, task, files))
+                       schedule();
                finish_wait(&task->io_uring->wait, &wait);
        }
 }