io_uring: finish waiting before flushing overflow entries

If we have overflow entries being generated after we've done the
initial flush in io_cqring_wait(), then we could be flushing them in the
main wait loop as well. If that's done after having added ourselves
to the cq_wait waitqueue, then the task state can be != TASK_RUNNING
when we enter the overflow flush.

Check for the need to overflow flush, and finish our wait cycle first
if we have to do so.

Reported-and-tested-by: syzbot+cf6ea1d6bb30a4ce10b2@syzkaller.appspotmail.com
Link: https://lore.kernel.org/io-uring/000000000000cb143a05f04eee15@google.com/
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index ff2bbac..ac5d39e 100644 (file)
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -677,16 +677,20 @@ static void __io_cqring_overflow_flush(struct io_ring_ctx *ctx)
        io_cq_unlock_post(ctx);
 }
 
+static void io_cqring_do_overflow_flush(struct io_ring_ctx *ctx)
+{
+       /* iopoll syncs against uring_lock, not completion_lock */
+       if (ctx->flags & IORING_SETUP_IOPOLL)
+               mutex_lock(&ctx->uring_lock);
+       __io_cqring_overflow_flush(ctx);
+       if (ctx->flags & IORING_SETUP_IOPOLL)
+               mutex_unlock(&ctx->uring_lock);
+}
+
 static void io_cqring_overflow_flush(struct io_ring_ctx *ctx)
 {
-       if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) {
-               /* iopoll syncs against uring_lock, not completion_lock */
-               if (ctx->flags & IORING_SETUP_IOPOLL)
-                       mutex_lock(&ctx->uring_lock);
-               __io_cqring_overflow_flush(ctx);
-               if (ctx->flags & IORING_SETUP_IOPOLL)
-                       mutex_unlock(&ctx->uring_lock);
-       }
+       if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq))
+               io_cqring_do_overflow_flush(ctx);
 }
 
 void __io_put_task(struct task_struct *task, int nr)
@@ -2549,7 +2553,10 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 
        trace_io_uring_cqring_wait(ctx, min_events);
        do {
-               io_cqring_overflow_flush(ctx);
+               if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) {
+                       finish_wait(&ctx->cq_wait, &iowq.wq);
+                       io_cqring_do_overflow_flush(ctx);
+               }
                prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq,
                                                TASK_INTERRUPTIBLE);
                ret = io_cqring_wait_schedule(ctx, &iowq, timeout);