When hv_sock was originally added, __vsock_stream_recvmsg() and vsock_stream_has_data() actually only needed to know whether there is any readable data or not, so hvs_stream_has_data() was written to return 1 or 0 for simplicity. However, now hvs_stream_has_data() should return the readable bytes because vsock_data_ready() -> vsock_stream_has_data() needs to know the actual bytes rather than a boolean value of 1 or 0. The SIOCINQ ioctl support also needs hvs_stream_has_data() to return the readable bytes. Let hvs_stream_has_data() return the readable bytes of the payload in the next host-to-guest VMBus hv_sock packet. Note: there may be multpile incoming hv_sock packets pending in the VMBus channel's ringbuffer, but so far there is not a VMBus API that allows us to know all the readable bytes in total without reading and caching the payload of the multiple packets, so let's just return the readable bytes of the next single packet. In the future, we'll either add a VMBus API that allows us to know the total readable bytes without touching the data in the ringbuffer, or the hv_sock driver needs to understand the VMBus packet format and parse the packets directly. Signed-off-by: Dexuan Cui Signed-off-by: Xuewei Niu --- net/vmw_vsock/hyperv_transport.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index 31342ab502b4..64f1290a9ae7 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -694,15 +694,25 @@ static ssize_t hvs_stream_enqueue(struct vsock_sock *vsk, struct msghdr *msg, static s64 hvs_stream_has_data(struct vsock_sock *vsk) { struct hvsock *hvs = vsk->trans; + bool need_refill = !hvs->recv_desc; s64 ret; if (hvs->recv_data_len > 0) - return 1; + return hvs->recv_data_len; switch (hvs_channel_readable_payload(hvs->chan)) { case 1: - ret = 1; - break; + if (!need_refill) + return -EIO; + + hvs->recv_desc = hv_pkt_iter_first(hvs->chan); + if (!hvs->recv_desc) + return -ENOBUFS; + + ret = hvs_update_recv_data(hvs); + if (ret) + return ret; + return hvs->recv_data_len; case 0: vsk->peer_shutdown |= SEND_SHUTDOWN; ret = 0; -- 2.34.1 Wrap the ioctl in `ioctl_int()`, which takes a pointer to the actual int value and an expected int value. The function will not return until either the ioctl returns the expected value or a timeout occurs, thus avoiding immediate failure. Signed-off-by: Xuewei Niu --- tools/testing/vsock/util.c | 32 +++++++++++++++++++++++--------- tools/testing/vsock/util.h | 1 + 2 files changed, 24 insertions(+), 9 deletions(-) diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c index 0c7e9cbcbc85..481c395227e4 100644 --- a/tools/testing/vsock/util.c +++ b/tools/testing/vsock/util.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include @@ -97,28 +98,41 @@ void vsock_wait_remote_close(int fd) close(epollfd); } -/* Wait until transport reports no data left to be sent. - * Return false if transport does not implement the unsent_bytes() callback. +/* Wait until ioctl gives an expected int value. + * Return false if the op is not supported. */ -bool vsock_wait_sent(int fd) +bool vsock_ioctl_int(int fd, unsigned long op, int *actual, int expected) { - int ret, sock_bytes_unsent; + int ret; + char name[32]; + + snprintf(name, sizeof(name), "ioctl(%lu)", op); timeout_begin(TIMEOUT); do { - ret = ioctl(fd, SIOCOUTQ, &sock_bytes_unsent); + ret = ioctl(fd, op, actual); if (ret < 0) { if (errno == EOPNOTSUPP) break; - perror("ioctl(SIOCOUTQ)"); + perror(name); exit(EXIT_FAILURE); } - timeout_check("SIOCOUTQ"); - } while (sock_bytes_unsent != 0); + timeout_check(name); + } while (*actual != expected); timeout_end(); - return !ret; + return ret >= 0; +} + +/* Wait until transport reports no data left to be sent. + * Return false if transport does not implement the unsent_bytes() callback. + */ +bool vsock_wait_sent(int fd) +{ + int sock_bytes_unsent; + + return vsock_ioctl_int(fd, SIOCOUTQ, &sock_bytes_unsent, 0); } /* Create socket , bind to and return the file descriptor. */ diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h index 5e2db67072d5..d59581f68d61 100644 --- a/tools/testing/vsock/util.h +++ b/tools/testing/vsock/util.h @@ -54,6 +54,7 @@ int vsock_stream_listen(unsigned int cid, unsigned int port); int vsock_seqpacket_accept(unsigned int cid, unsigned int port, struct sockaddr_vm *clientaddrp); void vsock_wait_remote_close(int fd); +bool vsock_ioctl_int(int fd, unsigned long op, int *actual, int expected); bool vsock_wait_sent(int fd); void send_buf(int fd, const void *buf, size_t len, int flags, ssize_t expected_ret); -- 2.34.1 Add SIOCINQ ioctl tests for both SOCK_STREAM and SOCK_SEQPACKET. The client waits for the server to send data, and checks if the SIOCINQ ioctl value matches the data size. After consuming the data, the client checks if the SIOCINQ value is 0. Signed-off-by: Xuewei Niu --- tools/testing/vsock/vsock_test.c | 80 ++++++++++++++++++++++++++++++++ 1 file changed, 80 insertions(+) diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index f669baaa0dca..1f525a7e0098 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -1305,6 +1305,56 @@ static void test_unsent_bytes_client(const struct test_opts *opts, int type) close(fd); } +static void test_unread_bytes_server(const struct test_opts *opts, int type) +{ + unsigned char buf[MSG_BUF_IOCTL_LEN]; + int client_fd; + + client_fd = vsock_accept(VMADDR_CID_ANY, opts->peer_port, NULL, type); + if (client_fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + for (int i = 0; i < sizeof(buf); i++) + buf[i] = rand() & 0xFF; + + send_buf(client_fd, buf, sizeof(buf), 0, sizeof(buf)); + control_writeln("SENT"); + + close(client_fd); +} + +static void test_unread_bytes_client(const struct test_opts *opts, int type) +{ + unsigned char buf[MSG_BUF_IOCTL_LEN]; + int fd; + int sock_bytes_unread; + + fd = vsock_connect(opts->peer_cid, opts->peer_port, type); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + control_expectln("SENT"); + /* The data has arrived but has not been read. The expected is + * MSG_BUF_IOCTL_LEN. + */ + if (!vsock_ioctl_int(fd, TIOCINQ, &sock_bytes_unread, + MSG_BUF_IOCTL_LEN)) { + fprintf(stderr, "Test skipped, TIOCINQ not supported.\n"); + goto out; + } + + recv_buf(fd, buf, sizeof(buf), 0, sizeof(buf)); + /* All data has been consumed, so the expected is 0. */ + vsock_ioctl_int(fd, TIOCINQ, &sock_bytes_unread, 0); + +out: + close(fd); +} + static void test_stream_unsent_bytes_client(const struct test_opts *opts) { test_unsent_bytes_client(opts, SOCK_STREAM); @@ -1325,6 +1375,26 @@ static void test_seqpacket_unsent_bytes_server(const struct test_opts *opts) test_unsent_bytes_server(opts, SOCK_SEQPACKET); } +static void test_stream_unread_bytes_client(const struct test_opts *opts) +{ + test_unread_bytes_client(opts, SOCK_STREAM); +} + +static void test_stream_unread_bytes_server(const struct test_opts *opts) +{ + test_unread_bytes_server(opts, SOCK_STREAM); +} + +static void test_seqpacket_unread_bytes_client(const struct test_opts *opts) +{ + test_unread_bytes_client(opts, SOCK_SEQPACKET); +} + +static void test_seqpacket_unread_bytes_server(const struct test_opts *opts) +{ + test_unread_bytes_server(opts, SOCK_SEQPACKET); +} + #define RCVLOWAT_CREDIT_UPD_BUF_SIZE (1024 * 128) /* This define is the same as in 'include/linux/virtio_vsock.h': * it is used to decide when to send credit update message during @@ -2051,6 +2121,16 @@ static struct test_case test_cases[] = { .run_client = test_stream_nolinger_client, .run_server = test_stream_nolinger_server, }, + { + .name = "SOCK_STREAM ioctl(SIOCINQ) functionality", + .run_client = test_stream_unread_bytes_client, + .run_server = test_stream_unread_bytes_server, + }, + { + .name = "SOCK_SEQPACKET ioctl(SIOCINQ) functionality", + .run_client = test_seqpacket_unread_bytes_client, + .run_server = test_seqpacket_unread_bytes_server, + }, {}, }; -- 2.34.1