X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fvhost%2Frte_eth_vhost.c;h=e55278af696047359fcef7c7eb182dd2d2f5089f;hb=8716f9942a408a79a114ac0496e4e7d55bc9944c;hp=c3ba602767e484a5e7fd1c08cb61f1de93f75622;hpb=9970a9ad07db7745ca6bc441819b287940ae86ea;p=dpdk.git diff --git a/drivers/net/vhost/rte_eth_vhost.c b/drivers/net/vhost/rte_eth_vhost.c index c3ba602767..e55278af69 100644 --- a/drivers/net/vhost/rte_eth_vhost.c +++ b/drivers/net/vhost/rte_eth_vhost.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include @@ -18,7 +19,7 @@ #include "rte_eth_vhost.h" -static int vhost_logtype; +RTE_LOG_REGISTER(vhost_logtype, pmd.net.vhost, NOTICE); #define VHOST_LOG(level, ...) \ rte_log(RTE_LOG_ ## level, vhost_logtype, __VA_ARGS__) @@ -31,6 +32,9 @@ enum {VIRTIO_RXQ, VIRTIO_TXQ, VIRTIO_QNUM}; #define ETH_VHOST_DEQUEUE_ZERO_COPY "dequeue-zero-copy" #define ETH_VHOST_IOMMU_SUPPORT "iommu-support" #define ETH_VHOST_POSTCOPY_SUPPORT "postcopy-support" +#define ETH_VHOST_VIRTIO_NET_F_HOST_TSO "tso" +#define ETH_VHOST_LINEAR_BUF "linear-buffer" +#define ETH_VHOST_EXT_BUF "ext-buffer" #define VHOST_MAX_PKT_BURST 32 static const char *valid_arguments[] = { @@ -40,6 +44,9 @@ static const char *valid_arguments[] = { ETH_VHOST_DEQUEUE_ZERO_COPY, ETH_VHOST_IOMMU_SUPPORT, ETH_VHOST_POSTCOPY_SUPPORT, + ETH_VHOST_VIRTIO_NET_F_HOST_TSO, + ETH_VHOST_LINEAR_BUF, + ETH_VHOST_EXT_BUF, NULL }; @@ -89,12 +96,15 @@ struct vhost_queue { uint16_t port; uint16_t virtqueue_id; struct vhost_stats stats; + int intr_enable; + rte_spinlock_t intr_lock; }; struct pmd_internal { rte_atomic32_t dev_attached; - char *dev_name; char *iface_name; + uint64_t flags; + uint64_t disable_flags; uint16_t max_queues; int vid; rte_atomic32_t started; @@ -489,17 +499,6 @@ out: return nb_tx; } -static int -eth_dev_configure(struct rte_eth_dev *dev __rte_unused) -{ - struct pmd_internal *internal = dev->data->dev_private; - const struct rte_eth_rxmode *rxmode = &dev->data->dev_conf.rxmode; - - internal->vlan_strip = !!(rxmode->offloads & DEV_RX_OFFLOAD_VLAN_STRIP); - - return 0; -} - static inline struct internal_list * find_internal_resource(char *ifname) { @@ -528,12 +527,58 @@ find_internal_resource(char *ifname) return list; } +static int +eth_vhost_update_intr(struct rte_eth_dev *eth_dev, uint16_t rxq_idx) +{ + struct rte_intr_handle *handle = eth_dev->intr_handle; + struct rte_epoll_event rev; + int epfd, ret; + + if (!handle) + return 0; + + if (handle->efds[rxq_idx] == handle->elist[rxq_idx].fd) + return 0; + + VHOST_LOG(INFO, "kickfd for rxq-%d was changed, updating handler.\n", + rxq_idx); + + if (handle->elist[rxq_idx].fd != -1) + VHOST_LOG(ERR, "Unexpected previous kickfd value (Got %d, expected -1).\n", + handle->elist[rxq_idx].fd); + + /* + * First remove invalid epoll event, and then install + * the new one. May be solved with a proper API in the + * future. + */ + epfd = handle->elist[rxq_idx].epfd; + rev = handle->elist[rxq_idx]; + ret = rte_epoll_ctl(epfd, EPOLL_CTL_DEL, rev.fd, + &handle->elist[rxq_idx]); + if (ret) { + VHOST_LOG(ERR, "Delete epoll event failed.\n"); + return ret; + } + + rev.fd = handle->efds[rxq_idx]; + handle->elist[rxq_idx] = rev; + ret = rte_epoll_ctl(epfd, EPOLL_CTL_ADD, rev.fd, + &handle->elist[rxq_idx]); + if (ret) { + VHOST_LOG(ERR, "Add epoll event failed.\n"); + return ret; + } + + return 0; +} + static int eth_rxq_intr_enable(struct rte_eth_dev *dev, uint16_t qid) { struct rte_vhost_vring vring; struct vhost_queue *vq; - int ret = 0; + int old_intr_enable, ret = 0; vq = dev->data->rx_queues[qid]; if (!vq) { @@ -541,6 +586,18 @@ eth_rxq_intr_enable(struct rte_eth_dev *dev, uint16_t qid) return -1; } + rte_spinlock_lock(&vq->intr_lock); + old_intr_enable = vq->intr_enable; + vq->intr_enable = 1; + ret = eth_vhost_update_intr(dev, qid); + rte_spinlock_unlock(&vq->intr_lock); + + if (ret < 0) { + VHOST_LOG(ERR, "Failed to update rxq%d's intr\n", qid); + vq->intr_enable = old_intr_enable; + return ret; + } + ret = rte_vhost_get_vhost_vring(vq->vid, (qid << 1) + 1, &vring); if (ret < 0) { VHOST_LOG(ERR, "Failed to get rxq%d's vring\n", qid); @@ -575,6 +632,8 @@ eth_rxq_intr_disable(struct rte_eth_dev *dev, uint16_t qid) rte_vhost_enable_guest_notification(vq->vid, (qid << 1) + 1, 0); rte_wmb(); + vq->intr_enable = 0; + return 0; } @@ -597,7 +656,6 @@ eth_vhost_install_intr(struct rte_eth_dev *dev) { struct rte_vhost_vring vring; struct vhost_queue *vq; - int count = 0; int nb_rxq = dev->data->nb_rx_queues; int i; int ret; @@ -627,6 +685,8 @@ eth_vhost_install_intr(struct rte_eth_dev *dev) VHOST_LOG(INFO, "Prepare intr vec\n"); for (i = 0; i < nb_rxq; i++) { + dev->intr_handle->intr_vec[i] = RTE_INTR_VEC_RXTX_OFFSET + i; + dev->intr_handle->efds[i] = -1; vq = dev->data->rx_queues[i]; if (!vq) { VHOST_LOG(INFO, "rxq-%d not setup yet, skip!\n", i); @@ -645,14 +705,12 @@ eth_vhost_install_intr(struct rte_eth_dev *dev) "rxq-%d's kickfd is invalid, skip!\n", i); continue; } - dev->intr_handle->intr_vec[i] = RTE_INTR_VEC_RXTX_OFFSET + i; dev->intr_handle->efds[i] = vring.kickfd; - count++; VHOST_LOG(INFO, "Installed intr vec for rxq-%d\n", i); } - dev->intr_handle->nb_efd = count; - dev->intr_handle->max_intr = count + 1; + dev->intr_handle->nb_efd = nb_rxq; + dev->intr_handle->max_intr = nb_rxq + 1; dev->intr_handle->type = RTE_INTR_HANDLE_VDEV; return 0; @@ -834,6 +892,47 @@ destroy_device(int vid) _rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_INTR_LSC, NULL); } +static int +vring_conf_update(int vid, struct rte_eth_dev *eth_dev, uint16_t vring_id) +{ + struct rte_eth_conf *dev_conf = ð_dev->data->dev_conf; + struct pmd_internal *internal = eth_dev->data->dev_private; + struct vhost_queue *vq; + struct rte_vhost_vring vring; + int rx_idx = vring_id % 2 ? (vring_id - 1) >> 1 : -1; + int ret = 0; + + /* + * The vring kickfd may be changed after the new device notification. + * Update it when the vring state is updated. + */ + if (rx_idx >= 0 && rx_idx < eth_dev->data->nb_rx_queues && + rte_atomic32_read(&internal->dev_attached) && + rte_atomic32_read(&internal->started) && + dev_conf->intr_conf.rxq) { + ret = rte_vhost_get_vhost_vring(vid, vring_id, &vring); + if (ret) { + VHOST_LOG(ERR, "Failed to get vring %d information.\n", + vring_id); + return ret; + } + eth_dev->intr_handle->efds[rx_idx] = vring.kickfd; + + vq = eth_dev->data->rx_queues[rx_idx]; + if (!vq) { + VHOST_LOG(ERR, "rxq%d is not setup yet\n", rx_idx); + return -1; + } + + rte_spinlock_lock(&vq->intr_lock); + if (vq->intr_enable) + ret = eth_vhost_update_intr(eth_dev, rx_idx); + rte_spinlock_unlock(&vq->intr_lock); + } + + return ret; +} + static int vring_state_changed(int vid, uint16_t vring, int enable) { @@ -852,7 +951,16 @@ vring_state_changed(int vid, uint16_t vring, int enable) eth_dev = list->eth_dev; /* won't be NULL */ state = vring_states[eth_dev->data->port_id]; + + if (enable && vring_conf_update(vid, eth_dev, vring)) + VHOST_LOG(INFO, "Failed to update vring-%d configuration.\n", + (int)vring); + rte_spinlock_lock(&state->lock); + if (state->cur[vring] == enable) { + rte_spinlock_unlock(&state->lock); + return 0; + } state->cur[vring] = enable; state->max_vring = RTE_MAX(vring, state->max_vring); rte_spinlock_unlock(&state->lock); @@ -871,6 +979,74 @@ static struct vhost_device_ops vhost_ops = { .vring_state_changed = vring_state_changed, }; +static int +vhost_driver_setup(struct rte_eth_dev *eth_dev) +{ + struct pmd_internal *internal = eth_dev->data->dev_private; + struct internal_list *list = NULL; + struct rte_vhost_vring_state *vring_state = NULL; + unsigned int numa_node = eth_dev->device->numa_node; + const char *name = eth_dev->device->name; + + /* Don't try to setup again if it has already been done. */ + list = find_internal_resource(internal->iface_name); + if (list) + return 0; + + list = rte_zmalloc_socket(name, sizeof(*list), 0, numa_node); + if (list == NULL) + return -1; + + vring_state = rte_zmalloc_socket(name, sizeof(*vring_state), + 0, numa_node); + if (vring_state == NULL) + goto free_list; + + list->eth_dev = eth_dev; + pthread_mutex_lock(&internal_list_lock); + TAILQ_INSERT_TAIL(&internal_list, list, next); + pthread_mutex_unlock(&internal_list_lock); + + rte_spinlock_init(&vring_state->lock); + vring_states[eth_dev->data->port_id] = vring_state; + + if (rte_vhost_driver_register(internal->iface_name, internal->flags)) + goto list_remove; + + if (internal->disable_flags) { + if (rte_vhost_driver_disable_features(internal->iface_name, + internal->disable_flags)) + goto drv_unreg; + } + + if (rte_vhost_driver_callback_register(internal->iface_name, + &vhost_ops) < 0) { + VHOST_LOG(ERR, "Can't register callbacks\n"); + goto drv_unreg; + } + + if (rte_vhost_driver_start(internal->iface_name) < 0) { + VHOST_LOG(ERR, "Failed to start driver for %s\n", + internal->iface_name); + goto drv_unreg; + } + + return 0; + +drv_unreg: + rte_vhost_driver_unregister(internal->iface_name); +list_remove: + vring_states[eth_dev->data->port_id] = NULL; + pthread_mutex_lock(&internal_list_lock); + TAILQ_REMOVE(&internal_list, list, next); + pthread_mutex_unlock(&internal_list_lock); + rte_free(vring_state); +free_list: + rte_free(list); + + return -1; +} + int rte_eth_vhost_get_queue_event(uint16_t port_id, struct rte_eth_vhost_queue_event *event) @@ -937,6 +1113,24 @@ rte_eth_vhost_get_vid_from_port_id(uint16_t port_id) return vid; } +static int +eth_dev_configure(struct rte_eth_dev *dev) +{ + struct pmd_internal *internal = dev->data->dev_private; + const struct rte_eth_rxmode *rxmode = &dev->data->dev_conf.rxmode; + + /* NOTE: the same process has to operate a vhost interface + * from beginning to end (from eth_dev configure to eth_dev close). + * It is user's responsibility at the moment. + */ + if (vhost_driver_setup(dev) < 0) + return -1; + + internal->vlan_strip = !!(rxmode->offloads & DEV_RX_OFFLOAD_VLAN_STRIP); + + return 0; +} + static int eth_dev_start(struct rte_eth_dev *eth_dev) { @@ -983,16 +1177,14 @@ eth_dev_close(struct rte_eth_dev *dev) eth_dev_stop(dev); - rte_vhost_driver_unregister(internal->iface_name); - list = find_internal_resource(internal->iface_name); - if (!list) - return; - - pthread_mutex_lock(&internal_list_lock); - TAILQ_REMOVE(&internal_list, list, next); - pthread_mutex_unlock(&internal_list_lock); - rte_free(list); + if (list) { + rte_vhost_driver_unregister(internal->iface_name); + pthread_mutex_lock(&internal_list_lock); + TAILQ_REMOVE(&internal_list, list, next); + pthread_mutex_unlock(&internal_list_lock); + rte_free(list); + } if (dev->data->rx_queues) for (i = 0; i < dev->data->nb_rx_queues; i++) @@ -1002,8 +1194,7 @@ eth_dev_close(struct rte_eth_dev *dev) for (i = 0; i < dev->data->nb_tx_queues; i++) rte_free(dev->data->tx_queues[i]); - free(internal->dev_name); - free(internal->iface_name); + rte_free(internal->iface_name); rte_free(internal); dev->data->dev_private = NULL; @@ -1030,6 +1221,7 @@ eth_rx_queue_setup(struct rte_eth_dev *dev, uint16_t rx_queue_id, vq->mb_pool = mb_pool; vq->virtqueue_id = rx_queue_id * VIRTIO_QNUM + VIRTIO_TXQ; + rte_spinlock_init(&vq->intr_lock); dev->data->rx_queues[rx_queue_id] = vq; return 0; @@ -1051,6 +1243,7 @@ eth_tx_queue_setup(struct rte_eth_dev *dev, uint16_t tx_queue_id, } vq->virtqueue_id = tx_queue_id * VIRTIO_QNUM + VIRTIO_RXQ; + rte_spinlock_init(&vq->intr_lock); dev->data->tx_queues[tx_queue_id] = vq; return 0; @@ -1205,23 +1398,18 @@ static const struct eth_dev_ops ops = { static int eth_dev_vhost_create(struct rte_vdev_device *dev, char *iface_name, - int16_t queues, const unsigned int numa_node, uint64_t flags) + int16_t queues, const unsigned int numa_node, uint64_t flags, + uint64_t disable_flags) { const char *name = rte_vdev_device_name(dev); struct rte_eth_dev_data *data; struct pmd_internal *internal = NULL; struct rte_eth_dev *eth_dev = NULL; struct rte_ether_addr *eth_addr = NULL; - struct rte_vhost_vring_state *vring_state = NULL; - struct internal_list *list = NULL; VHOST_LOG(INFO, "Creating VHOST-USER backend on numa socket %u\n", numa_node); - list = rte_zmalloc_socket(name, sizeof(*list), 0, numa_node); - if (list == NULL) - goto error; - /* reserve an ethdev entry */ eth_dev = rte_eth_vdev_allocate(dev, sizeof(*internal)); if (eth_dev == NULL) @@ -1235,38 +1423,28 @@ eth_dev_vhost_create(struct rte_vdev_device *dev, char *iface_name, *eth_addr = base_eth_addr; eth_addr->addr_bytes[5] = eth_dev->data->port_id; - vring_state = rte_zmalloc_socket(name, - sizeof(*vring_state), 0, numa_node); - if (vring_state == NULL) - goto error; - /* now put it all together * - store queue data in internal, * - point eth_dev_data to internals * - and point eth_dev structure to new eth_dev_data structure */ internal = eth_dev->data->dev_private; - internal->dev_name = strdup(name); - if (internal->dev_name == NULL) - goto error; - internal->iface_name = strdup(iface_name); + internal->iface_name = rte_malloc_socket(name, strlen(iface_name) + 1, + 0, numa_node); if (internal->iface_name == NULL) goto error; - - list->eth_dev = eth_dev; - pthread_mutex_lock(&internal_list_lock); - TAILQ_INSERT_TAIL(&internal_list, list, next); - pthread_mutex_unlock(&internal_list_lock); - - rte_spinlock_init(&vring_state->lock); - vring_states[eth_dev->data->port_id] = vring_state; + strcpy(internal->iface_name, iface_name); data->nb_rx_queues = queues; data->nb_tx_queues = queues; internal->max_queues = queues; internal->vid = -1; + internal->flags = flags; + internal->disable_flags = disable_flags; data->dev_link = pmd_link; data->dev_flags = RTE_ETH_DEV_INTR_LSC | RTE_ETH_DEV_CLOSE_REMOVE; + data->promiscuous = 1; + data->all_multicast = 1; eth_dev->dev_ops = &ops; @@ -1274,31 +1452,13 @@ eth_dev_vhost_create(struct rte_vdev_device *dev, char *iface_name, eth_dev->rx_pkt_burst = eth_vhost_rx; eth_dev->tx_pkt_burst = eth_vhost_tx; - if (rte_vhost_driver_register(iface_name, flags)) - goto error; - - if (rte_vhost_driver_callback_register(iface_name, &vhost_ops) < 0) { - VHOST_LOG(ERR, "Can't register callbacks\n"); - goto error; - } - - if (rte_vhost_driver_start(iface_name) < 0) { - VHOST_LOG(ERR, "Failed to start driver for %s\n", - iface_name); - goto error; - } - rte_eth_dev_probing_finish(eth_dev); - return data->port_id; + return 0; error: - if (internal) { - free(internal->iface_name); - free(internal->dev_name); - } - rte_free(vring_state); + if (internal) + rte_free(internal->iface_name); rte_eth_dev_release_port(eth_dev); - rte_free(list); return -1; } @@ -1339,10 +1499,14 @@ rte_pmd_vhost_probe(struct rte_vdev_device *dev) char *iface_name; uint16_t queues; uint64_t flags = 0; + uint64_t disable_flags = 0; int client_mode = 0; int dequeue_zero_copy = 0; int iommu_support = 0; int postcopy_support = 0; + int tso = 0; + int linear_buf = 0; + int ext_buf = 0; struct rte_eth_dev *eth_dev; const char *name = rte_vdev_device_name(dev); @@ -1354,8 +1518,11 @@ rte_pmd_vhost_probe(struct rte_vdev_device *dev) VHOST_LOG(ERR, "Failed to probe %s\n", name); return -1; } - /* TODO: request info from primary to set up Rx and Tx */ + eth_dev->rx_pkt_burst = eth_vhost_rx; + eth_dev->tx_pkt_burst = eth_vhost_tx; eth_dev->dev_ops = &ops; + if (dev->device.numa_node == SOCKET_ID_ANY) + dev->device.numa_node = rte_socket_id(); eth_dev->device = &dev->device; rte_eth_dev_probing_finish(eth_dev); return 0; @@ -1424,11 +1591,48 @@ rte_pmd_vhost_probe(struct rte_vdev_device *dev) flags |= RTE_VHOST_USER_POSTCOPY_SUPPORT; } + if (rte_kvargs_count(kvlist, ETH_VHOST_VIRTIO_NET_F_HOST_TSO) == 1) { + ret = rte_kvargs_process(kvlist, + ETH_VHOST_VIRTIO_NET_F_HOST_TSO, + &open_int, &tso); + if (ret < 0) + goto out_free; + + if (tso == 0) { + disable_flags |= (1ULL << VIRTIO_NET_F_HOST_TSO4); + disable_flags |= (1ULL << VIRTIO_NET_F_HOST_TSO6); + } + } + + if (rte_kvargs_count(kvlist, ETH_VHOST_LINEAR_BUF) == 1) { + ret = rte_kvargs_process(kvlist, + ETH_VHOST_LINEAR_BUF, + &open_int, &linear_buf); + if (ret < 0) + goto out_free; + + if (linear_buf == 1) + flags |= RTE_VHOST_USER_LINEARBUF_SUPPORT; + } + + if (rte_kvargs_count(kvlist, ETH_VHOST_EXT_BUF) == 1) { + ret = rte_kvargs_process(kvlist, + ETH_VHOST_EXT_BUF, + &open_int, &ext_buf); + if (ret < 0) + goto out_free; + + if (ext_buf == 1) + flags |= RTE_VHOST_USER_EXTBUF_SUPPORT; + } + if (dev->device.numa_node == SOCKET_ID_ANY) dev->device.numa_node = rte_socket_id(); - eth_dev_vhost_create(dev, iface_name, queues, dev->device.numa_node, - flags); + ret = eth_dev_vhost_create(dev, iface_name, queues, + dev->device.numa_node, flags, disable_flags); + if (ret == -1) + VHOST_LOG(ERR, "Failed to create %s\n", name); out_free: rte_kvargs_free(kvlist); @@ -1472,11 +1676,7 @@ RTE_PMD_REGISTER_PARAM_STRING(net_vhost, "client=<0|1> " "dequeue-zero-copy=<0|1> " "iommu-support=<0|1> " - "postcopy-support=<0|1>"); - -RTE_INIT(vhost_init_log) -{ - vhost_logtype = rte_log_register("pmd.net.vhost"); - if (vhost_logtype >= 0) - rte_log_set_level(vhost_logtype, RTE_LOG_NOTICE); -} + "postcopy-support=<0|1> " + "tso=<0|1> " + "linear-buffer=<0|1> " + "ext-buffer=<0|1>");