@@ -211,6 +218,365 @@ 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_uring_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);
+ }
+}
+
+static void expect_uring_more(unsigned int cflags, bool expected,
+ const char *what)
+{
+ bool more = !!(cflags & IORING_CQE_F_MORE);
+
+ if (more != expected) {
+ fprintf(stderr, "%s: expected F_MORE %d, got %d\n",
+ what, expected, more);
+ exit(EXIT_FAILURE);
+ }
+}
+
+/* Wait until the whole payload is queued, so the hint is deterministic.
+ * Return false if the test has to be skipped.
+ */
+static bool inq_wait_queued(int fd, int len)
+{
+ if (!vsock_ioctl_int(fd, SIOCINQ, len)) {
+ fprintf(stderr, "Test skipped, SIOCINQ not supported.\n");
+ return false;
+ }
+
+ return true;
+}
+
+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");
+ if (!inq_wait_queued(ctx.fd, 2 * HINT_CHUNK_SIZE))
+ goto out;
+
+ /* 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_uring_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_uring_nonempty(cflags, false, "draining receive");
+
+out:
+ 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");
+}
+
+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");
+ if (!inq_wait_queued(ctx.fd, HINT_CHUNK_SIZE)) {
+ control_writeln("DRAINED");
+ control_expectln("CLOSED");
+ goto out;
+ }
+
+ res = inq_recv(&ctx, buf, sizeof(buf), 0, &cflags);
+ expect_res(res, HINT_CHUNK_SIZE, "drain before EOF");
+ expect_uring_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_uring_nonempty(cflags, true, "receive at EOF");
+
+out:
+ 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_uring_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");
+ if (!inq_wait_queued(ctx.fd, HINT_CHUNK_SIZE))
+ goto out;
+
+ /* 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_uring_nonempty(cflags, true, "zero-length receive");
+
+out:
+ 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, i;
+
+ fd = vsock_stream_connect(opts->peer_cid, opts->peer_port);
+ if (fd < 0) {
+ perror("connect");
+ exit(EXIT_FAILURE);
+ }
+
+ memset(buf, 0x3c, sizeof(buf));
+ for (i = 0; i < 2; i++)
+ 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);
+
+ control_expectln("SENT");
+ if (!inq_wait_queued(ctx.fd, 2 * HINT_CHUNK_SIZE)) {
+ control_writeln("DRAINED");
+ control_expectln("CLOSED");
+ goto out;
+ }
+
+ /* Arm only once both chunks are queued, so every completion knows
+ * what is left behind it.
+ */
+ 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");
+
+ /* A buffer holds one chunk, so the other one is still queued. */
+ if (io_uring_wait_cqe(&ctx.ring, &cqe))
+ error(1, errno, "io_uring_wait_cqe");
+
+ expect_res(cqe->res, HINT_CHUNK_SIZE, "multishot first chunk");
+ expect_uring_nonempty(cqe->flags, true, "multishot first chunk");
+ expect_uring_more(cqe->flags, true, "multishot first chunk");
+ io_uring_cqe_seen(&ctx.ring, cqe);
+
+ /* This completion drains the queue and keeps the request armed. */
+ if (io_uring_wait_cqe(&ctx.ring, &cqe))
+ error(1, errno, "io_uring_wait_cqe");
+
+ expect_res(cqe->res, HINT_CHUNK_SIZE, "multishot second chunk");
+ expect_uring_nonempty(cqe->flags, false, "multishot second chunk");
+ expect_uring_more(cqe->flags, true, "multishot second chunk");
+ 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");
+ expect_uring_more(cqe->flags, false, "multishot EOF");
+ io_uring_cqe_seen(&ctx.ring, cqe);
+
+out:
+ 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",