Hi Bobby. Indeed, io_uring presets msg_inq to -1, so that check passes either way. Sending two chunks makes sense: SOCK_NONEMPTY on the first completion, not on the second.
The empty queue case passing without patch 1 is expected. It is there to catch a stale positive hint on the error path rather than to show the new behaviour. Cheers. On Tue, 22 Sept 2026 at 18:34, Bobby Eshleman <[email protected]> wrote: > > On Sun, Sep 20, 2026 at 08:47:10PM +0100, David Carlier wrote: > > Add io_uring receive tests checking IORING_CQE_F_SOCK_NONEMPTY across a > > partial receive, draining while the peer stays connected, EOF, a > > nonblocking receive on an empty queue, a zero-length request, and a > > multishot receive with provided buffers. > > > > Signed-off-by: David Carlier <[email protected]> > > --- > > tools/testing/vsock/vsock_uring_test.c | 367 +++++++++++++++++++++++++ > > 1 file changed, 367 insertions(+) > > > > diff --git a/tools/testing/vsock/vsock_uring_test.c > > b/tools/testing/vsock/vsock_uring_test.c > > index 5c3078969659..318e17bd28bc 100644 > > --- a/tools/testing/vsock/vsock_uring_test.c > > +++ b/tools/testing/vsock/vsock_uring_test.c > > @@ -13,7 +13,10 @@ > > #include <liburing.h> > > #include <unistd.h> > > #include <sys/mman.h> > > +#include <sys/ioctl.h> > > #include <linux/kernel.h> > > +#include <linux/sockios.h> > > +#include <errno.h> > > #include <error.h> > > > > #include "util.h" > > @@ -28,6 +31,10 @@ > > > > #define VSOCK_TEST_DATA_MAX_IOV 3 > > > > +#define HINT_CHUNK_SIZE 4096 > > +#define HINT_BUF_GROUP 1 > > +#define HINT_BUF_ENTRIES 4 > > + > > struct vsock_io_uring_test { > > /* Number of valid elements in 'vecs'. */ > > int vecs_cnt; > > @@ -211,6 +218,341 @@ void test_stream_uring_msg_zc_client(const struct > > test_opts *opts) > > vsock_io_uring_client(opts, &test_data_array[i], true); > > } > > > > +struct uring_inq_ctx { > > + struct io_uring ring; > > + int fd; > > +}; > > + > > +static void inq_server_init(struct uring_inq_ctx *ctx, > > + const struct test_opts *opts) > > +{ > > + ctx->fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL); > > + if (ctx->fd < 0) { > > + perror("accept"); > > + exit(EXIT_FAILURE); > > + } > > + > > + if (io_uring_queue_init(RING_ENTRIES_NUM, &ctx->ring, 0)) > > + error(1, errno, "io_uring_queue_init"); > > +} > > + > > +static void inq_server_exit(struct uring_inq_ctx *ctx) > > +{ > > + io_uring_queue_exit(&ctx->ring); > > + close(ctx->fd); > > +} > > + > > +/* Submit a single receive and report both its result and its CQE flags. */ > > +static int inq_recv(struct uring_inq_ctx *ctx, void *buf, size_t len, > > + int flags, unsigned int *cflags) > > +{ > > + struct io_uring_sqe *sqe; > > + struct io_uring_cqe *cqe; > > + int res; > > + > > + sqe = io_uring_get_sqe(&ctx->ring); > > + io_uring_prep_recv(sqe, ctx->fd, buf, len, flags); > > + > > + if (io_uring_submit(&ctx->ring) != 1) > > + error(1, errno, "io_uring_submit"); > > + > > + if (io_uring_wait_cqe(&ctx->ring, &cqe)) > > + error(1, errno, "io_uring_wait_cqe"); > > + > > + res = cqe->res; > > + *cflags = cqe->flags; > > + io_uring_cqe_seen(&ctx->ring, cqe); > > + > > + return res; > > +} > > + > > +static void expect_res(int res, int expected, const char *what) > > +{ > > + if (res != expected) { > > + fprintf(stderr, "%s: expected %d, got %d\n", what, expected, > > + res); > > + exit(EXIT_FAILURE); > > + } > > +} > > + > > +static void expect_nonempty(unsigned int cflags, bool expected, > > + const char *what) > > +{ > > + bool nonempty = !!(cflags & IORING_CQE_F_SOCK_NONEMPTY); > > + > > + if (nonempty != expected) { > > + fprintf(stderr, "%s: expected SOCK_NONEMPTY %d, got %d\n", > > + what, expected, nonempty); > > + exit(EXIT_FAILURE); > > + } > > +} > > + > > +/* Wait until the whole payload is queued, so the hint is deterministic. */ > > +static void inq_wait_queued(int fd, int len) > > +{ > > + if (!vsock_ioctl_int(fd, SIOCINQ, len)) { > > + fprintf(stderr, "SIOCINQ not supported\n"); > > + exit(EXIT_FAILURE); > > + } > > +} > > + > > +static void inq_send_chunks(const struct test_opts *opts, int chunks) > > +{ > > + char buf[HINT_CHUNK_SIZE]; > > + int fd, i; > > + > > + fd = vsock_stream_connect(opts->peer_cid, opts->peer_port); > > + if (fd < 0) { > > + perror("connect"); > > + exit(EXIT_FAILURE); > > + } > > + > > + memset(buf, 0xa5, sizeof(buf)); > > + for (i = 0; i < chunks; i++) > > + send_buf(fd, buf, sizeof(buf), 0, sizeof(buf)); > > + > > + control_writeln("SENT"); > > + control_expectln("DONE"); > > + close(fd); > > +} > > + > > +static void test_stream_uring_inq_client(const struct test_opts *opts) > > +{ > > + inq_send_chunks(opts, 2); > > +} > > + > > +static void test_stream_uring_inq_server(const struct test_opts *opts) > > +{ > > + char buf[HINT_CHUNK_SIZE]; > > + struct uring_inq_ctx ctx; > > + unsigned int cflags; > > + int res; > > + > > + inq_server_init(&ctx, opts); > > + > > + control_expectln("SENT"); > > + inq_wait_queued(ctx.fd, 2 * HINT_CHUNK_SIZE); > > + > > + /* Data remains after this receive, so the flag must be set. */ > > + res = inq_recv(&ctx, buf, sizeof(buf), 0, &cflags); > > + expect_res(res, HINT_CHUNK_SIZE, "partial receive"); > > + expect_nonempty(cflags, true, "partial receive"); > > + > > + /* This receive drains the queue while the peer stays connected. */ > > + res = inq_recv(&ctx, buf, sizeof(buf), 0, &cflags); > > + expect_res(res, HINT_CHUNK_SIZE, "draining receive"); > > + expect_nonempty(cflags, false, "draining receive"); > > + > > + control_writeln("DONE"); > > + inq_server_exit(&ctx); > > +} > > + > > +static void test_stream_uring_inq_eof_client(const struct test_opts *opts) > > +{ > > + char buf[HINT_CHUNK_SIZE]; > > + int fd; > > + > > + fd = vsock_stream_connect(opts->peer_cid, opts->peer_port); > > + if (fd < 0) { > > + perror("connect"); > > + exit(EXIT_FAILURE); > > + } > > + > > + memset(buf, 0x5a, sizeof(buf)); > > + send_buf(fd, buf, sizeof(buf), 0, sizeof(buf)); > > + control_writeln("SENT"); > > + > > + control_expectln("DRAINED"); > > + close(fd); > > + control_writeln("CLOSED"); > > + > > + control_expectln("DONE"); > > +} > > + > > +static void test_stream_uring_inq_eof_server(const struct test_opts *opts) > > +{ > > + char buf[HINT_CHUNK_SIZE]; > > + struct uring_inq_ctx ctx; > > + unsigned int cflags; > > + int res; > > + > > + inq_server_init(&ctx, opts); > > + > > + control_expectln("SENT"); > > + inq_wait_queued(ctx.fd, HINT_CHUNK_SIZE); > > + > > + res = inq_recv(&ctx, buf, sizeof(buf), 0, &cflags); > > + expect_res(res, HINT_CHUNK_SIZE, "drain before EOF"); > > + expect_nonempty(cflags, false, "drain before EOF"); > > + > > + control_writeln("DRAINED"); > > + control_expectln("CLOSED"); > > + > > + /* The queue is empty and the peer is gone. The hint stays non-zero > > + * so that this receive happens and reports EOF, as TCP does after a > > + * FIN. > > + */ > > + res = inq_recv(&ctx, buf, sizeof(buf), 0, &cflags); > > + expect_res(res, 0, "receive at EOF"); > > + expect_nonempty(cflags, true, "receive at EOF"); > > + > > + control_writeln("DONE"); > > + inq_server_exit(&ctx); > > +} > > + > > +static void test_stream_uring_inq_empty_client(const struct test_opts > > *opts) > > +{ > > + int fd; > > + > > + fd = vsock_stream_connect(opts->peer_cid, opts->peer_port); > > + if (fd < 0) { > > + perror("connect"); > > + exit(EXIT_FAILURE); > > + } > > + > > + control_writeln("READY"); > > + control_expectln("DONE"); > > + close(fd); > > +} > > + > > +static void test_stream_uring_inq_empty_server(const struct test_opts > > *opts) > > +{ > > + char buf[HINT_CHUNK_SIZE]; > > + struct uring_inq_ctx ctx; > > + unsigned int cflags; > > + int res; > > + > > + inq_server_init(&ctx, opts); > > + > > + control_expectln("READY"); > > + > > + /* A failed receive must not leave a stale positive hint. */ > > + res = inq_recv(&ctx, buf, sizeof(buf), MSG_DONTWAIT, &cflags); > > + expect_res(res, -EAGAIN, "empty nonblocking receive"); > > + expect_nonempty(cflags, false, "empty nonblocking receive"); > > > > > + > > + control_writeln("DONE"); > > + inq_server_exit(&ctx); > > +} > > + > > +static void test_stream_uring_inq_zerolen_client(const struct test_opts > > *opts) > > +{ > > + inq_send_chunks(opts, 1); > > +} > > + > > +static void test_stream_uring_inq_zerolen_server(const struct test_opts > > *opts) > > +{ > > + char buf[HINT_CHUNK_SIZE]; > > + struct uring_inq_ctx ctx; > > + unsigned int cflags; > > + int res; > > + > > + inq_server_init(&ctx, opts); > > + > > + control_expectln("SENT"); > > + inq_wait_queued(ctx.fd, HINT_CHUNK_SIZE); > > + > > + /* A zero-length request is not an error and still describes the > > + * queue behind it. > > + */ > > + res = inq_recv(&ctx, buf, 0, 0, &cflags); > > + expect_res(res, 0, "zero-length receive"); > > + expect_nonempty(cflags, true, "zero-length receive"); > > + > > + control_writeln("DONE"); > > + inq_server_exit(&ctx); > > +} > > + > > +static void test_stream_uring_inq_mshot_client(const struct test_opts > > *opts) > > +{ > > + char buf[HINT_CHUNK_SIZE]; > > + int fd; > > + > > + fd = vsock_stream_connect(opts->peer_cid, opts->peer_port); > > + if (fd < 0) { > > + perror("connect"); > > + exit(EXIT_FAILURE); > > + } > > + > > + memset(buf, 0x3c, sizeof(buf)); > > + send_buf(fd, buf, sizeof(buf), 0, sizeof(buf)); > > + control_writeln("SENT"); > > + > > + control_expectln("DRAINED"); > > + close(fd); > > + control_writeln("CLOSED"); > > + > > + control_expectln("DONE"); > > +} > > + > > +static void test_stream_uring_inq_mshot_server(const struct test_opts > > *opts) > > +{ > > + static char bufs[HINT_BUF_ENTRIES][HINT_CHUNK_SIZE]; > > + struct io_uring_buf_ring *br; > > + struct uring_inq_ctx ctx; > > + struct io_uring_sqe *sqe; > > + struct io_uring_cqe *cqe; > > + int i, ret; > > + > > + inq_server_init(&ctx, opts); > > + > > + br = io_uring_setup_buf_ring(&ctx.ring, HINT_BUF_ENTRIES, > > + HINT_BUF_GROUP, 0, &ret); > > + if (!br) { > > + fprintf(stderr, "io_uring_setup_buf_ring: %d\n", ret); > > + exit(EXIT_FAILURE); > > + } > > + > > + for (i = 0; i < HINT_BUF_ENTRIES; i++) > > + io_uring_buf_ring_add(br, bufs[i], HINT_CHUNK_SIZE, i, > > + > > io_uring_buf_ring_mask(HINT_BUF_ENTRIES), > > + i); > > + io_uring_buf_ring_advance(br, HINT_BUF_ENTRIES); > > + > > + sqe = io_uring_get_sqe(&ctx.ring); > > + io_uring_prep_recv_multishot(sqe, ctx.fd, NULL, 0, 0); > > + sqe->flags |= IOSQE_BUFFER_SELECT; > > + sqe->buf_group = HINT_BUF_GROUP; > > + > > + if (io_uring_submit(&ctx.ring) != 1) > > + error(1, errno, "io_uring_submit"); > > + > > + control_expectln("SENT"); > > + > > + /* The payload completion drains the queue and keeps the request > > + * armed, so the hint must report the queue as empty. > > + */ > > + if (io_uring_wait_cqe(&ctx.ring, &cqe)) > > + error(1, errno, "io_uring_wait_cqe"); > > + > > + expect_res(cqe->res, HINT_CHUNK_SIZE, "multishot payload"); > > + expect_nonempty(cqe->flags, false, "multishot payload"); > > It looks like this assertion holds true even without the first patch, > since msg_inq is initalized to -1 and nonempty is only set if msg_inq > > 0. > > As of right now, this test actually passes without the first patch. > After cherry-picking only the tests to net-next and yanking out the > other test cases, I see: > > client exit=0 > server exit=0 > Control socket listening on 0.0.0.0:5200 > Control socket connection accepted... > 0 - SOCK_STREAM io_uring receive hint on empty queue...ok > 1 - SOCK_STREAM io_uring multishot receive hint...ok > All tests have been executed. Waiting other peer...ok > > > I wonder if it might be better to have the sender send two chunks so we > can first assert that NONEMPTY is flipped on, and then again that it has > flipped back off? > > Best, > Bobby > > > + if (!(cqe->flags & IORING_CQE_F_MORE)) { > > + fprintf(stderr, "multishot payload: request not rearmed\n"); > > + exit(EXIT_FAILURE); > > + } > > + io_uring_cqe_seen(&ctx.ring, cqe); > > + > > + control_writeln("DRAINED"); > > + control_expectln("CLOSED"); > > + > > + /* EOF ends multishot regardless of the hint. */ > > + if (io_uring_wait_cqe(&ctx.ring, &cqe)) > > + error(1, errno, "io_uring_wait_cqe"); > > + > > + expect_res(cqe->res, 0, "multishot EOF"); > > + if (cqe->flags & IORING_CQE_F_MORE) { > > + fprintf(stderr, "multishot EOF: request still armed\n"); > > + exit(EXIT_FAILURE); > > + } > > + io_uring_cqe_seen(&ctx.ring, cqe); > > + > > + control_writeln("DONE"); > > + io_uring_free_buf_ring(&ctx.ring, br, HINT_BUF_ENTRIES, > > + HINT_BUF_GROUP); > > + inq_server_exit(&ctx); > > +} > > + > > static struct test_case test_cases[] = { > > { > > .name = "SOCK_STREAM io_uring test", > > @@ -222,6 +564,31 @@ static struct test_case test_cases[] = { > > .run_server = test_stream_uring_msg_zc_server, > > .run_client = test_stream_uring_msg_zc_client, > > }, > > + { > > + .name = "SOCK_STREAM io_uring receive queue hint", > > + .run_server = test_stream_uring_inq_server, > > + .run_client = test_stream_uring_inq_client, > > + }, > > + { > > + .name = "SOCK_STREAM io_uring receive hint at EOF", > > + .run_server = test_stream_uring_inq_eof_server, > > + .run_client = test_stream_uring_inq_eof_client, > > + }, > > + { > > + .name = "SOCK_STREAM io_uring receive hint on empty queue", > > + .run_server = test_stream_uring_inq_empty_server, > > + .run_client = test_stream_uring_inq_empty_client, > > + }, > > + { > > + .name = "SOCK_STREAM io_uring receive hint zero-length", > > + .run_server = test_stream_uring_inq_zerolen_server, > > + .run_client = test_stream_uring_inq_zerolen_client, > > + }, > > + { > > + .name = "SOCK_STREAM io_uring multishot receive hint", > > + .run_server = test_stream_uring_inq_mshot_server, > > + .run_client = test_stream_uring_inq_mshot_client, > > + }, > > {}, > > }; > > > > -- > > 2.55.0 > >
