io_uring: fix racy overflow count reporting

All ->cq_overflow modifications should be under completion_lock,
otherwise it can report a wrong number to the userspace. Fix it in
io_uring_cancel_files().

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 11f4ab8..6e23225 100644 (file)
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -7847,10 +7847,9 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
                                clear_bit(0, &ctx->cq_check_overflow);
                                ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW;
                        }
-                       spin_unlock_irq(&ctx->completion_lock);
-
                        WRITE_ONCE(ctx->rings->cq_overflow,
                                atomic_inc_return(&ctx->cached_cq_overflow));
+                       spin_unlock_irq(&ctx->completion_lock);
 
                        /*
                         * Put inflight ref and overflow ref. If that's