X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_vhost%2Fsocket.c;h=8bc1e3a03c99d962e52b8085d9ac887deb5e0ebb;hb=3010f08599e36bcd5690a3b8081390e86e61a4f4;hp=c278e9b5beb1af93d8c70400cbb0fd716b12fb81;hpb=c00bb88d35fe975ede0ea35bdf4f765a2cece7e8;p=dpdk.git diff --git a/lib/librte_vhost/socket.c b/lib/librte_vhost/socket.c index c278e9b5be..8bc1e3a03c 100644 --- a/lib/librte_vhost/socket.c +++ b/lib/librte_vhost/socket.c @@ -40,6 +40,8 @@ struct vhost_user_socket { bool dequeue_zero_copy; bool iommu_support; bool use_builtin_virtio_net; + bool extbuf; + bool linearbuf; /* * The "supported_features" indicates the feature bits the @@ -51,6 +53,8 @@ struct vhost_user_socket { uint64_t supported_features; uint64_t features; + uint64_t protocol_features; + /* * Device id to identify a specific backend device. * It's set to -1 for the default software implementation. @@ -88,6 +92,7 @@ static struct vhost_user vhost_user = { .fdset = { .fd = { [0 ... MAX_FDS - 1] = {-1, NULL, NULL, NULL, 0} }, .fd_mutex = PTHREAD_MUTEX_INITIALIZER, + .fd_pooling_mutex = PTHREAD_MUTEX_INITIALIZER, .num = 0 }, .vsocket_cnt = 0, @@ -122,12 +127,12 @@ read_fd_message(int sockfd, char *buf, int buflen, int *fds, int max_fds, ret = recvmsg(sockfd, &msgh, 0); if (ret <= 0) { - RTE_LOG(ERR, VHOST_CONFIG, "recvmsg failed\n"); + VHOST_LOG_CONFIG(ERR, "recvmsg failed\n"); return ret; } if (msgh.msg_flags & (MSG_TRUNC | MSG_CTRUNC)) { - RTE_LOG(ERR, VHOST_CONFIG, "truncted msg\n"); + VHOST_LOG_CONFIG(ERR, "truncated msg\n"); return -1; } @@ -172,7 +177,7 @@ send_fd_message(int sockfd, char *buf, int buflen, int *fds, int fd_num) msgh.msg_controllen = sizeof(control); cmsg = CMSG_FIRSTHDR(&msgh); if (cmsg == NULL) { - RTE_LOG(ERR, VHOST_CONFIG, "cmsg == NULL\n"); + VHOST_LOG_CONFIG(ERR, "cmsg == NULL\n"); errno = EINVAL; return -1; } @@ -190,7 +195,7 @@ send_fd_message(int sockfd, char *buf, int buflen, int *fds, int fd_num) } while (ret < 0 && errno == EINTR); if (ret < 0) { - RTE_LOG(ERR, VHOST_CONFIG, "sendmsg error\n"); + VHOST_LOG_CONFIG(ERR, "sendmsg error\n"); return ret; } @@ -229,15 +234,21 @@ vhost_user_add_connection(int fd, struct vhost_user_socket *vsocket) if (vsocket->dequeue_zero_copy) vhost_enable_dequeue_zero_copy(vid); - RTE_LOG(INFO, VHOST_CONFIG, "new device, handle is %d\n", vid); + if (vsocket->extbuf) + vhost_enable_extbuf(vid); + + if (vsocket->linearbuf) + vhost_enable_linearbuf(vid); + + VHOST_LOG_CONFIG(INFO, "new device, handle is %d\n", vid); if (vsocket->notify_ops->new_connection) { ret = vsocket->notify_ops->new_connection(vid); if (ret < 0) { - RTE_LOG(ERR, VHOST_CONFIG, + VHOST_LOG_CONFIG(ERR, "failed to add vhost user connection with fd %d\n", fd); - goto err; + goto err_cleanup; } } @@ -247,14 +258,14 @@ vhost_user_add_connection(int fd, struct vhost_user_socket *vsocket) ret = fdset_add(&vhost_user.fdset, fd, vhost_user_read_cb, NULL, conn); if (ret < 0) { - RTE_LOG(ERR, VHOST_CONFIG, + VHOST_LOG_CONFIG(ERR, "failed to add fd %d into vhost server fdset\n", fd); if (vsocket->notify_ops->destroy_connection) vsocket->notify_ops->destroy_connection(conn->vid); - goto err; + goto err_cleanup; } pthread_mutex_lock(&vsocket->conn_mutex); @@ -264,6 +275,8 @@ vhost_user_add_connection(int fd, struct vhost_user_socket *vsocket) fdset_pipe_notify(&vhost_user.fdset); return; +err_cleanup: + vhost_destroy_device(vid); err: free(conn); close(fd); @@ -279,7 +292,7 @@ vhost_user_server_new_connection(int fd, void *dat, int *remove __rte_unused) if (fd < 0) return; - RTE_LOG(INFO, VHOST_CONFIG, "new vhost user connection is %d\n", fd); + VHOST_LOG_CONFIG(INFO, "new vhost user connection is %d\n", fd); vhost_user_add_connection(fd, vsocket); } @@ -292,13 +305,19 @@ vhost_user_read_cb(int connfd, void *dat, int *remove) ret = vhost_user_msg_handler(conn->vid, connfd); if (ret < 0) { + struct virtio_net *dev = get_device(conn->vid); + close(connfd); *remove = 1; - vhost_destroy_device(conn->vid); + + if (dev) + vhost_destroy_device_notify(dev); if (vsocket->notify_ops->destroy_connection) vsocket->notify_ops->destroy_connection(conn->vid); + vhost_destroy_device(conn->vid); + pthread_mutex_lock(&vsocket->conn_mutex); TAILQ_REMOVE(&vsocket->conn_list, conn, next); pthread_mutex_unlock(&vsocket->conn_mutex); @@ -321,11 +340,11 @@ create_unix_socket(struct vhost_user_socket *vsocket) fd = socket(AF_UNIX, SOCK_STREAM, 0); if (fd < 0) return -1; - RTE_LOG(INFO, VHOST_CONFIG, "vhost-user %s: socket created, fd: %d\n", + VHOST_LOG_CONFIG(INFO, "vhost-user %s: socket created, fd: %d\n", vsocket->is_server ? "server" : "client", fd); if (!vsocket->is_server && fcntl(fd, F_SETFL, O_NONBLOCK)) { - RTE_LOG(ERR, VHOST_CONFIG, + VHOST_LOG_CONFIG(ERR, "vhost-user: can't set nonblocking mode for socket, fd: " "%d (%s)\n", fd, strerror(errno)); close(fd); @@ -360,12 +379,12 @@ vhost_user_start_server(struct vhost_user_socket *vsocket) */ ret = bind(fd, (struct sockaddr *)&vsocket->un, sizeof(vsocket->un)); if (ret < 0) { - RTE_LOG(ERR, VHOST_CONFIG, + VHOST_LOG_CONFIG(ERR, "failed to bind to %s: %s; remove it and try again\n", path, strerror(errno)); goto err; } - RTE_LOG(INFO, VHOST_CONFIG, "bind to %s\n", path); + VHOST_LOG_CONFIG(INFO, "bind to %s\n", path); ret = listen(fd, MAX_VIRTIO_BACKLOG); if (ret < 0) @@ -374,7 +393,7 @@ vhost_user_start_server(struct vhost_user_socket *vsocket) ret = fdset_add(&vhost_user.fdset, fd, vhost_user_server_new_connection, NULL, vsocket); if (ret < 0) { - RTE_LOG(ERR, VHOST_CONFIG, + VHOST_LOG_CONFIG(ERR, "failed to add listen fd %d to vhost server fdset\n", fd); goto err; @@ -415,12 +434,12 @@ vhost_user_connect_nonblock(int fd, struct sockaddr *un, size_t sz) flags = fcntl(fd, F_GETFL, 0); if (flags < 0) { - RTE_LOG(ERR, VHOST_CONFIG, + VHOST_LOG_CONFIG(ERR, "can't get flags for connfd %d\n", fd); return -2; } if ((flags & O_NONBLOCK) && fcntl(fd, F_SETFL, flags & ~O_NONBLOCK)) { - RTE_LOG(ERR, VHOST_CONFIG, + VHOST_LOG_CONFIG(ERR, "can't disable nonblocking on fd %d\n", fd); return -2; } @@ -449,7 +468,7 @@ vhost_user_client_reconnect(void *arg __rte_unused) sizeof(reconn->un)); if (ret == -2) { close(reconn->fd); - RTE_LOG(ERR, VHOST_CONFIG, + VHOST_LOG_CONFIG(ERR, "reconnection for fd %d failed\n", reconn->fd); goto remove_fd; @@ -457,7 +476,7 @@ vhost_user_client_reconnect(void *arg __rte_unused) if (ret == -1) continue; - RTE_LOG(INFO, VHOST_CONFIG, + VHOST_LOG_CONFIG(INFO, "%s: connected\n", reconn->vsocket->path); vhost_user_add_connection(reconn->fd, reconn->vsocket); remove_fd: @@ -479,7 +498,7 @@ vhost_user_reconnect_init(void) ret = pthread_mutex_init(&reconn_list.mutex, NULL); if (ret < 0) { - RTE_LOG(ERR, VHOST_CONFIG, "failed to initialize mutex"); + VHOST_LOG_CONFIG(ERR, "failed to initialize mutex"); return ret; } TAILQ_INIT(&reconn_list.head); @@ -487,9 +506,9 @@ vhost_user_reconnect_init(void) ret = rte_ctrl_thread_create(&reconn_tid, "vhost_reconn", NULL, vhost_user_client_reconnect, NULL); if (ret != 0) { - RTE_LOG(ERR, VHOST_CONFIG, "failed to create reconnect thread"); + VHOST_LOG_CONFIG(ERR, "failed to create reconnect thread"); if (pthread_mutex_destroy(&reconn_list.mutex)) { - RTE_LOG(ERR, VHOST_CONFIG, + VHOST_LOG_CONFIG(ERR, "failed to destroy reconnect mutex"); } } @@ -512,7 +531,7 @@ vhost_user_start_client(struct vhost_user_socket *vsocket) return 0; } - RTE_LOG(WARNING, VHOST_CONFIG, + VHOST_LOG_CONFIG(WARNING, "failed to connect to %s: %s\n", path, strerror(errno)); @@ -521,10 +540,10 @@ vhost_user_start_client(struct vhost_user_socket *vsocket) return -1; } - RTE_LOG(INFO, VHOST_CONFIG, "%s: reconnecting...\n", path); + VHOST_LOG_CONFIG(INFO, "%s: reconnecting...\n", path); reconn = malloc(sizeof(*reconn)); if (reconn == NULL) { - RTE_LOG(ERR, VHOST_CONFIG, + VHOST_LOG_CONFIG(ERR, "failed to allocate memory for reconnect\n"); close(fd); return -1; @@ -544,6 +563,9 @@ find_vhost_user_socket(const char *path) { int i; + if (path == NULL) + return NULL; + for (i = 0; i < vhost_user.vsocket_cnt; i++) { struct vhost_user_socket *vsocket = vhost_user.vsockets[i]; @@ -559,7 +581,7 @@ rte_vhost_driver_attach_vdpa_device(const char *path, int did) { struct vhost_user_socket *vsocket; - if (rte_vdpa_get_device(did) == NULL) + if (rte_vdpa_get_device(did) == NULL || path == NULL) return -1; pthread_mutex_lock(&vhost_user.mutex); @@ -676,7 +698,7 @@ rte_vhost_driver_get_features(const char *path, uint64_t *features) pthread_mutex_lock(&vhost_user.mutex); vsocket = find_vhost_user_socket(path); if (!vsocket) { - RTE_LOG(ERR, VHOST_CONFIG, + VHOST_LOG_CONFIG(ERR, "socket file %s is not registered yet.\n", path); ret = -1; goto unlock_exit; @@ -690,7 +712,7 @@ rte_vhost_driver_get_features(const char *path, uint64_t *features) } if (vdpa_dev->ops->get_features(did, &vdpa_features) < 0) { - RTE_LOG(ERR, VHOST_CONFIG, + VHOST_LOG_CONFIG(ERR, "failed to get vdpa features " "for socket file %s.\n", path); ret = -1; @@ -704,6 +726,20 @@ unlock_exit: return ret; } +int +rte_vhost_driver_set_protocol_features(const char *path, + uint64_t protocol_features) +{ + struct vhost_user_socket *vsocket; + + pthread_mutex_lock(&vhost_user.mutex); + vsocket = find_vhost_user_socket(path); + if (vsocket) + vsocket->protocol_features = protocol_features; + pthread_mutex_unlock(&vhost_user.mutex); + return vsocket ? 0 : -1; +} + int rte_vhost_driver_get_protocol_features(const char *path, uint64_t *protocol_features) @@ -717,7 +753,7 @@ rte_vhost_driver_get_protocol_features(const char *path, pthread_mutex_lock(&vhost_user.mutex); vsocket = find_vhost_user_socket(path); if (!vsocket) { - RTE_LOG(ERR, VHOST_CONFIG, + VHOST_LOG_CONFIG(ERR, "socket file %s is not registered yet.\n", path); ret = -1; goto unlock_exit; @@ -726,20 +762,20 @@ rte_vhost_driver_get_protocol_features(const char *path, did = vsocket->vdpa_dev_id; vdpa_dev = rte_vdpa_get_device(did); if (!vdpa_dev || !vdpa_dev->ops->get_protocol_features) { - *protocol_features = VHOST_USER_PROTOCOL_FEATURES; + *protocol_features = vsocket->protocol_features; goto unlock_exit; } if (vdpa_dev->ops->get_protocol_features(did, &vdpa_protocol_features) < 0) { - RTE_LOG(ERR, VHOST_CONFIG, + VHOST_LOG_CONFIG(ERR, "failed to get vdpa protocol features " "for socket file %s.\n", path); ret = -1; goto unlock_exit; } - *protocol_features = VHOST_USER_PROTOCOL_FEATURES + *protocol_features = vsocket->protocol_features & vdpa_protocol_features; unlock_exit: @@ -759,7 +795,7 @@ rte_vhost_driver_get_queue_num(const char *path, uint32_t *queue_num) pthread_mutex_lock(&vhost_user.mutex); vsocket = find_vhost_user_socket(path); if (!vsocket) { - RTE_LOG(ERR, VHOST_CONFIG, + VHOST_LOG_CONFIG(ERR, "socket file %s is not registered yet.\n", path); ret = -1; goto unlock_exit; @@ -773,7 +809,7 @@ rte_vhost_driver_get_queue_num(const char *path, uint32_t *queue_num) } if (vdpa_dev->ops->get_queue_num(did, &vdpa_queue_num) < 0) { - RTE_LOG(ERR, VHOST_CONFIG, + VHOST_LOG_CONFIG(ERR, "failed to get vdpa queue number " "for socket file %s.\n", path); ret = -1; @@ -818,7 +854,7 @@ rte_vhost_driver_register(const char *path, uint64_t flags) pthread_mutex_lock(&vhost_user.mutex); if (vhost_user.vsocket_cnt == MAX_VHOST_SOCKET) { - RTE_LOG(ERR, VHOST_CONFIG, + VHOST_LOG_CONFIG(ERR, "error: the number of vhost sockets reaches maximum\n"); goto out; } @@ -829,7 +865,7 @@ rte_vhost_driver_register(const char *path, uint64_t flags) memset(vsocket, 0, sizeof(struct vhost_user_socket)); vsocket->path = strdup(path); if (vsocket->path == NULL) { - RTE_LOG(ERR, VHOST_CONFIG, + VHOST_LOG_CONFIG(ERR, "error: failed to copy socket path string\n"); vhost_user_socket_mem_free(vsocket); goto out; @@ -837,11 +873,22 @@ rte_vhost_driver_register(const char *path, uint64_t flags) TAILQ_INIT(&vsocket->conn_list); ret = pthread_mutex_init(&vsocket->conn_mutex, NULL); if (ret) { - RTE_LOG(ERR, VHOST_CONFIG, + VHOST_LOG_CONFIG(ERR, "error: failed to init connection mutex\n"); goto out_free; } + vsocket->vdpa_dev_id = -1; vsocket->dequeue_zero_copy = flags & RTE_VHOST_USER_DEQUEUE_ZERO_COPY; + vsocket->extbuf = flags & RTE_VHOST_USER_EXTBUF_SUPPORT; + vsocket->linearbuf = flags & RTE_VHOST_USER_LINEARBUF_SUPPORT; + + if (vsocket->dequeue_zero_copy && + (flags & RTE_VHOST_USER_IOMMU_SUPPORT)) { + VHOST_LOG_CONFIG(ERR, + "error: enabling dequeue zero copy and IOMMU features " + "simultaneously is not supported\n"); + goto out_mutex; + } /* * Set the supported features correctly for the builtin vhost-user @@ -858,11 +905,51 @@ rte_vhost_driver_register(const char *path, uint64_t flags) vsocket->use_builtin_virtio_net = true; vsocket->supported_features = VIRTIO_NET_SUPPORTED_FEATURES; vsocket->features = VIRTIO_NET_SUPPORTED_FEATURES; + vsocket->protocol_features = VHOST_USER_PROTOCOL_FEATURES; - /* Dequeue zero copy can't assure descriptors returned in order */ + /* + * Dequeue zero copy can't assure descriptors returned in order. + * Also, it requires that the guest memory is populated, which is + * not compatible with postcopy. + */ if (vsocket->dequeue_zero_copy) { + if (vsocket->extbuf) { + VHOST_LOG_CONFIG(ERR, + "error: zero copy is incompatible with external buffers\n"); + ret = -1; + goto out_mutex; + } + if (vsocket->linearbuf) { + VHOST_LOG_CONFIG(ERR, + "error: zero copy is incompatible with linear buffers\n"); + ret = -1; + goto out_mutex; + } vsocket->supported_features &= ~(1ULL << VIRTIO_F_IN_ORDER); vsocket->features &= ~(1ULL << VIRTIO_F_IN_ORDER); + + VHOST_LOG_CONFIG(INFO, + "Dequeue zero copy requested, disabling postcopy support\n"); + vsocket->protocol_features &= + ~(1ULL << VHOST_USER_PROTOCOL_F_PAGEFAULT); + } + + /* + * We'll not be able to receive a buffer from guest in linear mode + * without external buffer if it will not fit in a single mbuf, which is + * likely if segmentation offloading enabled. + */ + if (vsocket->linearbuf && !vsocket->extbuf) { + uint64_t seg_offload_features = + (1ULL << VIRTIO_NET_F_HOST_TSO4) | + (1ULL << VIRTIO_NET_F_HOST_TSO6) | + (1ULL << VIRTIO_NET_F_HOST_UFO); + + VHOST_LOG_CONFIG(INFO, + "Linear buffers requested without external buffers, " + "disabling host segmentation offloading support\n"); + vsocket->supported_features &= ~seg_offload_features; + vsocket->features &= ~seg_offload_features; } if (!(flags & RTE_VHOST_USER_IOMMU_SUPPORT)) { @@ -870,6 +957,18 @@ rte_vhost_driver_register(const char *path, uint64_t flags) vsocket->features &= ~(1ULL << VIRTIO_F_IOMMU_PLATFORM); } + if (!(flags & RTE_VHOST_USER_POSTCOPY_SUPPORT)) { + vsocket->protocol_features &= + ~(1ULL << VHOST_USER_PROTOCOL_F_PAGEFAULT); + } else { +#ifndef RTE_LIBRTE_VHOST_POSTCOPY + VHOST_LOG_CONFIG(ERR, + "Postcopy requested but not compiled\n"); + ret = -1; + goto out_mutex; +#endif + } + if ((flags & RTE_VHOST_USER_CLIENT) != 0) { vsocket->reconnect = !(flags & RTE_VHOST_USER_NO_RECONNECT); if (vsocket->reconnect && reconn_tid == 0) { @@ -891,7 +990,7 @@ rte_vhost_driver_register(const char *path, uint64_t flags) out_mutex: if (pthread_mutex_destroy(&vsocket->conn_mutex)) { - RTE_LOG(ERR, VHOST_CONFIG, + VHOST_LOG_CONFIG(ERR, "error: failed to destroy connection mutex\n"); } out_free: @@ -936,13 +1035,16 @@ rte_vhost_driver_unregister(const char *path) int count; struct vhost_user_connection *conn, *next; + if (path == NULL) + return -1; + +again: pthread_mutex_lock(&vhost_user.mutex); for (i = 0; i < vhost_user.vsocket_cnt; i++) { struct vhost_user_socket *vsocket = vhost_user.vsockets[i]; if (!strcmp(vsocket->path, path)) { -again: pthread_mutex_lock(&vsocket->conn_mutex); for (conn = TAILQ_FIRST(&vsocket->conn_list); conn != NULL; @@ -958,10 +1060,11 @@ again: conn->connfd) == -1) { pthread_mutex_unlock( &vsocket->conn_mutex); + pthread_mutex_unlock(&vhost_user.mutex); goto again; } - RTE_LOG(INFO, VHOST_CONFIG, + VHOST_LOG_CONFIG(INFO, "free connfd = %d for device '%s'\n", conn->connfd, path); close(conn->connfd); @@ -1045,7 +1148,7 @@ rte_vhost_driver_start(const char *path) * rebuild the wait list of poll. */ if (fdset_pipe_init(&vhost_user.fdset) < 0) { - RTE_LOG(ERR, VHOST_CONFIG, + VHOST_LOG_CONFIG(ERR, "failed to create pipe for vhost fdset\n"); return -1; } @@ -1054,7 +1157,7 @@ rte_vhost_driver_start(const char *path) "vhost-events", NULL, fdset_event_dispatch, &vhost_user.fdset); if (ret != 0) { - RTE_LOG(ERR, VHOST_CONFIG, + VHOST_LOG_CONFIG(ERR, "failed to create fdset handling thread"); fdset_pipe_uninit(&vhost_user.fdset);