X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;ds=sidebyside;f=lib%2Flibrte_vhost%2Fsocket.c;h=2d3d20804933825e48ec2d439edb6b35e4f47989;hb=400d758182669035203ba619001b0c03234b9121;hp=4ce916dc2f2cfc4b746fb38178346b22bb5cdd2d;hpb=8b4b949144b80cc7312bbc189d38a3feaf2c74e5;p=dpdk.git diff --git a/lib/librte_vhost/socket.c b/lib/librte_vhost/socket.c index 4ce916dc2f..2d3d208049 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. @@ -88,24 +92,30 @@ 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, .mutex = PTHREAD_MUTEX_INITIALIZER, }; -/* return bytes# of read on success or negative val on failure. */ +/* + * return bytes# of read on success or negative val on failure. Update fdnum + * with number of fds read. + */ int -read_fd_message(int sockfd, char *buf, int buflen, int *fds, int fd_num) +read_fd_message(int sockfd, char *buf, int buflen, int *fds, int max_fds, + int *fd_num) { struct iovec iov; struct msghdr msgh; - size_t fdsize = fd_num * sizeof(int); - char control[CMSG_SPACE(fdsize)]; + char control[CMSG_SPACE(max_fds * sizeof(int))]; struct cmsghdr *cmsg; int got_fds = 0; int ret; + *fd_num = 0; + memset(&msgh, 0, sizeof(msgh)); iov.iov_base = buf; iov.iov_len = buflen; @@ -131,13 +141,14 @@ read_fd_message(int sockfd, char *buf, int buflen, int *fds, int fd_num) if ((cmsg->cmsg_level == SOL_SOCKET) && (cmsg->cmsg_type == SCM_RIGHTS)) { got_fds = (cmsg->cmsg_len - CMSG_LEN(0)) / sizeof(int); + *fd_num = got_fds; memcpy(fds, CMSG_DATA(cmsg), got_fds * sizeof(int)); break; } } /* Clear out unused file descriptors */ - while (got_fds < fd_num) + while (got_fds < max_fds) fds[got_fds++] = -1; return ret; @@ -199,6 +210,9 @@ vhost_user_add_connection(int fd, struct vhost_user_socket *vsocket) struct vhost_user_connection *conn; int ret; + if (vsocket == NULL) + return; + conn = malloc(sizeof(*conn)); if (conn == NULL) { close(fd); @@ -220,6 +234,12 @@ vhost_user_add_connection(int fd, struct vhost_user_socket *vsocket) if (vsocket->dequeue_zero_copy) vhost_enable_dequeue_zero_copy(vid); + if (vsocket->extbuf) + vhost_enable_extbuf(vid); + + if (vsocket->linearbuf) + vhost_enable_linearbuf(vid); + RTE_LOG(INFO, VHOST_CONFIG, "new device, handle is %d\n", vid); if (vsocket->notify_ops->new_connection) { @@ -228,7 +248,7 @@ vhost_user_add_connection(int fd, struct vhost_user_socket *vsocket) RTE_LOG(ERR, VHOST_CONFIG, "failed to add vhost user connection with fd %d\n", fd); - goto err; + goto err_cleanup; } } @@ -245,7 +265,7 @@ vhost_user_add_connection(int fd, struct vhost_user_socket *vsocket) if (vsocket->notify_ops->destroy_connection) vsocket->notify_ops->destroy_connection(conn->vid); - goto err; + goto err_cleanup; } pthread_mutex_lock(&vsocket->conn_mutex); @@ -255,6 +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); @@ -283,13 +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); @@ -535,6 +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]; @@ -550,7 +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); @@ -695,6 +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 +762,7 @@ 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; } @@ -730,7 +775,7 @@ rte_vhost_driver_get_protocol_features(const char *path, goto unlock_exit; } - *protocol_features = VHOST_USER_PROTOCOL_FEATURES + *protocol_features = vsocket->protocol_features & vdpa_protocol_features; unlock_exit: @@ -778,6 +823,20 @@ unlock_exit: return ret; } +static void +vhost_user_socket_mem_free(struct vhost_user_socket *vsocket) +{ + if (vsocket && vsocket->path) { + free(vsocket->path); + vsocket->path = NULL; + } + + if (vsocket) { + free(vsocket); + vsocket = NULL; + } +} + /* * Register a new vhost-user socket; here we could act as server * (the default case), or client (when RTE_VHOST_USER_CLIENT) flag @@ -808,7 +867,7 @@ rte_vhost_driver_register(const char *path, uint64_t flags) if (vsocket->path == NULL) { RTE_LOG(ERR, VHOST_CONFIG, "error: failed to copy socket path string\n"); - free(vsocket); + vhost_user_socket_mem_free(vsocket); goto out; } TAILQ_INIT(&vsocket->conn_list); @@ -819,6 +878,16 @@ rte_vhost_driver_register(const char *path, uint64_t flags) goto out_free; } 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)) { + RTE_LOG(ERR, VHOST_CONFIG, + "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 @@ -835,12 +904,52 @@ 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. + * Also, it requires that the guest memory is populated, which is + * not compatible with postcopy. + */ + if (vsocket->dequeue_zero_copy) { + if (vsocket->extbuf) { + RTE_LOG(ERR, VHOST_CONFIG, + "error: zero copy is incompatible with external buffers\n"); + ret = -1; + goto out_mutex; + } + if (vsocket->linearbuf) { + RTE_LOG(ERR, VHOST_CONFIG, + "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); + + RTE_LOG(INFO, VHOST_CONFIG, + "Dequeue zero copy requested, disabling postcopy support\n"); + vsocket->protocol_features &= + ~(1ULL << VHOST_USER_PROTOCOL_F_PAGEFAULT); + } if (!(flags & RTE_VHOST_USER_IOMMU_SUPPORT)) { vsocket->supported_features &= ~(1ULL << VIRTIO_F_IOMMU_PLATFORM); 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 + RTE_LOG(ERR, VHOST_CONFIG, + "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) { @@ -866,8 +975,7 @@ out_mutex: "error: failed to destroy connection mutex\n"); } out_free: - free(vsocket->path); - free(vsocket); + vhost_user_socket_mem_free(vsocket); out: pthread_mutex_unlock(&vhost_user.mutex); @@ -908,21 +1016,16 @@ 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)) { - if (vsocket->is_server) { - fdset_del(&vhost_user.fdset, vsocket->socket_fd); - close(vsocket->socket_fd); - unlink(path); - } else if (vsocket->reconnect) { - vhost_user_remove_reconnect(vsocket); - } - -again: pthread_mutex_lock(&vsocket->conn_mutex); for (conn = TAILQ_FIRST(&vsocket->conn_list); conn != NULL; @@ -938,6 +1041,7 @@ again: conn->connfd) == -1) { pthread_mutex_unlock( &vsocket->conn_mutex); + pthread_mutex_unlock(&vhost_user.mutex); goto again; } @@ -951,9 +1055,17 @@ again: } pthread_mutex_unlock(&vsocket->conn_mutex); + if (vsocket->is_server) { + fdset_del(&vhost_user.fdset, + vsocket->socket_fd); + close(vsocket->socket_fd); + unlink(path); + } else if (vsocket->reconnect) { + vhost_user_remove_reconnect(vsocket); + } + pthread_mutex_destroy(&vsocket->conn_mutex); - free(vsocket->path); - free(vsocket); + vhost_user_socket_mem_free(vsocket); count = --vhost_user.vsocket_cnt; vhost_user.vsockets[i] = vhost_user.vsockets[count];