[PATCH] __io_uring_get_cqe: eliminate unnecessary io_uring_enter() syscalls

[Xiaoguang Wang <xiaoguang.wang@xxxxxxxxxxxxxxxxx>]

When user applis programming mode, like sumbit one sqe and wait its
completion event, __io_uring_get_cqe() will result in many unnecessary
syscalls, see below test program:

    int main(int argc, char *argv[])
    {
            struct io_uring ring;
            int fd, ret;
            struct io_uring_sqe *sqe;
            struct io_uring_cqe *cqe;
            struct iovec iov;
            off_t offset, filesize = 0;
            void *buf;

            if (argc < 2) {
                    printf("%s: file\n", argv[0]);
                    return 1;
            }

            ret = io_uring_queue_init(4, &ring, 0);
            if (ret < 0) {
                    fprintf(stderr, "queue_init: %s\n", strerror(-ret));
                    return 1;
            }

            fd = open(argv[1], O_RDONLY | O_DIRECT);
            if (fd < 0) {
                    perror("open");
                    return 1;
            }

            if (posix_memalign(&buf, 4096, 4096))
                    return 1;
            iov.iov_base = buf;
            iov.iov_len = 4096;

            offset = 0;
            do {
                    sqe = io_uring_get_sqe(&ring);
                    if (!sqe) {
                            printf("here\n");
                            break;
                    }
                    io_uring_prep_readv(sqe, fd, &iov, 1, offset);

                    ret = io_uring_submit(&ring);
                    if (ret < 0) {
                            fprintf(stderr, "io_uring_submit: %s\n", strerror(-ret));
                            return 1;
                    }

                    ret = io_uring_wait_cqe(&ring, &cqe);
                    if (ret < 0) {
                            fprintf(stderr, "io_uring_wait_cqe: %s\n", strerror(-ret));
                            return 1;
                    }

                    if (cqe->res <= 0) {
                            if (cqe->res < 0) {
                                    fprintf(stderr, "got eror: %d\n", cqe->res);
                                    ret = 1;
                            }
                            io_uring_cqe_seen(&ring, cqe);
                            break;
                    }
                    offset += cqe->res;
                    filesize += cqe->res;
                    io_uring_cqe_seen(&ring, cqe);
            } while (1);

            printf("filesize: %ld\n", filesize);
            close(fd);
            io_uring_queue_exit(&ring);
            return 0;
    }

dd if=/dev/zero of=testfile bs=4096 count=16
./test  testfile
and use bpftrace to trace io_uring_enter syscalls, in original codes,
[lege@localhost ~]$ sudo bpftrace -e "tracepoint:syscalls:sys_enter_io_uring_enter {@c[tid] = count();}"
Attaching 1 probe...
@c[11184]: 49
Above test issues 49 syscalls, it's counterintuitive. After looking
into the codes, it's because __io_uring_get_cqe issue one more syscall,
indded when __io_uring_get_cqe issues the first syscall, one cqe should
already be ready, we don't need to wait again.

To fix this issue, after the first syscall, set wait_nr to be zero, with
tihs patch, bpftrace shows the number of io_uring_enter syscall is 33.

Signed-off-by: Xiaoguang Wang <xiaoguang.wang@xxxxxxxxxxxxxxxxx>
---
 src/queue.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/src/queue.c b/src/queue.c
index ef2cc2b..99a4a0c 100644
--- a/src/queue.c
+++ b/src/queue.c
@@ -53,6 +53,8 @@ int __io_uring_get_cqe(struct io_uring *ring, struct io_uring_cqe **cqe_ptr,
 		if (wait_nr || submit)
 			ret = __sys_io_uring_enter(ring->ring_fd, submit,
 						   wait_nr, flags, sigmask);
+		if (wait_nr)
+			wait_nr = 0;
 		if (ret < 0)
 			err = -errno;
 		submit -= ret;
-- 
2.17.2