From 6d5f904904608a9cd32854d7d0a4dd65b27f9935 Mon Sep 17 00:00:00 2001
From: Xiaoguang Wang <xiaoguang.wang@linux.alibaba.com>
Date: Thu, 9 Jul 2020 09:15:29 +0800
Subject: io_uring: export cq overflow status to userspace

For those applications which are not willing to use io_uring_enter()
to reap and handle cqes, they may completely rely on liburing's
io_uring_peek_cqe(), but if cq ring has overflowed, currently because
io_uring_peek_cqe() is not aware of this overflow, it won't enter
kernel to flush cqes, below test program can reveal this bug:

static void test_cq_overflow(struct io_uring *ring)
{
        struct io_uring_cqe *cqe;
        struct io_uring_sqe *sqe;
        int issued = 0;
        int ret = 0;

        do {
                sqe = io_uring_get_sqe(ring);
                if (!sqe) {
                        fprintf(stderr, "get sqe failed\n");
                        break;;
                }
                ret = io_uring_submit(ring);
                if (ret <= 0) {
                        if (ret != -EBUSY)
                                fprintf(stderr, "sqe submit failed: %d\n", ret);
                        break;
                }
                issued++;
        } while (ret > 0);
        assert(ret == -EBUSY);

        printf("issued requests: %d\n", issued);

        while (issued) {
                ret = io_uring_peek_cqe(ring, &cqe);
                if (ret) {
                        if (ret != -EAGAIN) {
                                fprintf(stderr, "peek completion failed: %s\n",
                                        strerror(ret));
                                break;
                        }
                        printf("left requets: %d\n", issued);
                        continue;
                }
                io_uring_cqe_seen(ring, cqe);
                issued--;
                printf("left requets: %d\n", issued);
        }
}

int main(int argc, char *argv[])
{
        int ret;
        struct io_uring ring;

        ret = io_uring_queue_init(16, &ring, 0);
        if (ret) {
                fprintf(stderr, "ring setup failed: %d\n", ret);
                return 1;
        }

        test_cq_overflow(&ring);
        return 0;
}

To fix this issue, export cq overflow status to userspace by adding new
IORING_SQ_CQ_OVERFLOW flag, then helper functions() in liburing, such as
io_uring_peek_cqe, can be aware of this cq overflow and do flush accordingly.

Signed-off-by: Xiaoguang Wang <xiaoguang.wang@linux.alibaba.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/io_uring.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 92c22699a5a7..7843742b8b74 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -197,6 +197,7 @@ struct io_sqring_offsets {
  * sq_ring->flags
  */
 #define IORING_SQ_NEED_WAKEUP	(1U << 0) /* needs io_uring_enter wakeup */
+#define IORING_SQ_CQ_OVERFLOW	(1U << 1) /* CQ ring is overflown */
 
 struct io_cqring_offsets {
 	__u32 head;
-- 
cgit v1.2.3