X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fvhost%2Frte_eth_vhost.c;h=d198fc8a8e9d7cf72c96e475f3a7fc21dce39ce7;hb=56175f74eaa565cdfde931d83be1db9faaa81667;hp=0ad92480766d57a63d6b3034760e1dfa2fdb8fb8;hpb=e16adf08e54d5b1ff3b1116c372bbca279fced9d;p=dpdk.git diff --git a/drivers/net/vhost/rte_eth_vhost.c b/drivers/net/vhost/rte_eth_vhost.c index 0ad9248076..d198fc8a8e 100644 --- a/drivers/net/vhost/rte_eth_vhost.c +++ b/drivers/net/vhost/rte_eth_vhost.c @@ -5,10 +5,11 @@ #include #include #include +#include #include -#include -#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__) @@ -28,22 +29,26 @@ enum {VIRTIO_RXQ, VIRTIO_TXQ, VIRTIO_QNUM}; #define ETH_VHOST_IFACE_ARG "iface" #define ETH_VHOST_QUEUES_ARG "queues" #define ETH_VHOST_CLIENT_ARG "client" -#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[] = { ETH_VHOST_IFACE_ARG, ETH_VHOST_QUEUES_ARG, ETH_VHOST_CLIENT_ARG, - 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 }; -static struct ether_addr base_eth_addr = { +static struct rte_ether_addr base_eth_addr = { .addr_bytes = { 0x56 /* V */, 0x48 /* H */, @@ -66,6 +71,9 @@ enum vhost_xstats_pkts { VHOST_BROADCAST_PKT, VHOST_MULTICAST_PKT, VHOST_UNICAST_PKT, + VHOST_PKT, + VHOST_BYTE, + VHOST_MISSED_PKT, VHOST_ERRORS_PKT, VHOST_ERRORS_FRAGMENTED, VHOST_ERRORS_JABBER, @@ -89,12 +97,15 @@ 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; @@ -139,11 +150,11 @@ struct vhost_xstats_name_off { /* [rx]_is prepended to the name string here */ static const struct vhost_xstats_name_off vhost_rxport_stat_strings[] = { {"good_packets", - offsetof(struct vhost_queue, stats.pkts)}, + offsetof(struct vhost_queue, stats.xstats[VHOST_PKT])}, {"total_bytes", - offsetof(struct vhost_queue, stats.bytes)}, + offsetof(struct vhost_queue, stats.xstats[VHOST_BYTE])}, {"missed_pkts", - offsetof(struct vhost_queue, stats.missed_pkts)}, + offsetof(struct vhost_queue, stats.xstats[VHOST_MISSED_PKT])}, {"broadcast_packets", offsetof(struct vhost_queue, stats.xstats[VHOST_BROADCAST_PKT])}, {"multicast_packets", @@ -179,11 +190,11 @@ static const struct vhost_xstats_name_off vhost_rxport_stat_strings[] = { /* [tx]_ is prepended to the name string here */ static const struct vhost_xstats_name_off vhost_txport_stat_strings[] = { {"good_packets", - offsetof(struct vhost_queue, stats.pkts)}, + offsetof(struct vhost_queue, stats.xstats[VHOST_PKT])}, {"total_bytes", - offsetof(struct vhost_queue, stats.bytes)}, + offsetof(struct vhost_queue, stats.xstats[VHOST_BYTE])}, {"missed_pkts", - offsetof(struct vhost_queue, stats.missed_pkts)}, + offsetof(struct vhost_queue, stats.xstats[VHOST_MISSED_PKT])}, {"broadcast_packets", offsetof(struct vhost_queue, stats.xstats[VHOST_BROADCAST_PKT])}, {"multicast_packets", @@ -216,7 +227,7 @@ static const struct vhost_xstats_name_off vhost_txport_stat_strings[] = { #define VHOST_NB_XSTATS_TXPORT (sizeof(vhost_txport_stat_strings) / \ sizeof(vhost_txport_stat_strings[0])) -static void +static int vhost_dev_xstats_reset(struct rte_eth_dev *dev) { struct vhost_queue *vq = NULL; @@ -234,6 +245,8 @@ vhost_dev_xstats_reset(struct rte_eth_dev *dev) continue; memset(&vq->stats, 0, sizeof(vq->stats)); } + + return 0; } static int @@ -275,23 +288,6 @@ vhost_dev_xstats_get(struct rte_eth_dev *dev, struct rte_eth_xstat *xstats, if (n < nxstats) return nxstats; - for (i = 0; i < dev->data->nb_rx_queues; i++) { - vq = dev->data->rx_queues[i]; - if (!vq) - continue; - vq->stats.xstats[VHOST_UNICAST_PKT] = vq->stats.pkts - - (vq->stats.xstats[VHOST_BROADCAST_PKT] - + vq->stats.xstats[VHOST_MULTICAST_PKT]); - } - for (i = 0; i < dev->data->nb_tx_queues; i++) { - vq = dev->data->tx_queues[i]; - if (!vq) - continue; - vq->stats.xstats[VHOST_UNICAST_PKT] = vq->stats.pkts - + vq->stats.missed_pkts - - (vq->stats.xstats[VHOST_BROADCAST_PKT] - + vq->stats.xstats[VHOST_MULTICAST_PKT]); - } for (t = 0; t < VHOST_NB_XSTATS_RXPORT; t++) { xstats[count].value = 0; for (i = 0; i < dev->data->nb_rx_queues; i++) { @@ -322,32 +318,39 @@ vhost_dev_xstats_get(struct rte_eth_dev *dev, struct rte_eth_xstat *xstats, } static inline void -vhost_count_multicast_broadcast(struct vhost_queue *vq, +vhost_count_xcast_packets(struct vhost_queue *vq, struct rte_mbuf *mbuf) { - struct ether_addr *ea = NULL; + struct rte_ether_addr *ea = NULL; struct vhost_stats *pstats = &vq->stats; - ea = rte_pktmbuf_mtod(mbuf, struct ether_addr *); - if (is_multicast_ether_addr(ea)) { - if (is_broadcast_ether_addr(ea)) + ea = rte_pktmbuf_mtod(mbuf, struct rte_ether_addr *); + if (rte_is_multicast_ether_addr(ea)) { + if (rte_is_broadcast_ether_addr(ea)) pstats->xstats[VHOST_BROADCAST_PKT]++; else pstats->xstats[VHOST_MULTICAST_PKT]++; + } else { + pstats->xstats[VHOST_UNICAST_PKT]++; } } static void -vhost_update_packet_xstats(struct vhost_queue *vq, - struct rte_mbuf **bufs, - uint16_t count) +vhost_update_packet_xstats(struct vhost_queue *vq, struct rte_mbuf **bufs, + uint16_t count, uint64_t nb_bytes, + uint64_t nb_missed) { uint32_t pkt_len = 0; uint64_t i = 0; uint64_t index; struct vhost_stats *pstats = &vq->stats; + pstats->xstats[VHOST_BYTE] += nb_bytes; + pstats->xstats[VHOST_MISSED_PKT] += nb_missed; + pstats->xstats[VHOST_UNICAST_PKT] += nb_missed; + for (i = 0; i < count ; i++) { + pstats->xstats[VHOST_PKT]++; pkt_len = bufs[i]->pkt_len; if (pkt_len == 64) { pstats->xstats[VHOST_64_PKT]++; @@ -363,7 +366,7 @@ vhost_update_packet_xstats(struct vhost_queue *vq, else if (pkt_len > 1522) pstats->xstats[VHOST_1523_TO_MAX_PKT]++; } - vhost_count_multicast_broadcast(vq, bufs[i]); + vhost_count_xcast_packets(vq, bufs[i]); } } @@ -373,6 +376,7 @@ eth_vhost_rx(void *q, struct rte_mbuf **bufs, uint16_t nb_bufs) struct vhost_queue *r = q; uint16_t i, nb_rx = 0; uint16_t nb_receive = nb_bufs; + uint64_t nb_bytes = 0; if (unlikely(rte_atomic32_read(&r->allow_queuing) == 0)) return 0; @@ -407,10 +411,11 @@ eth_vhost_rx(void *q, struct rte_mbuf **bufs, uint16_t nb_bufs) if (r->internal->vlan_strip) rte_vlan_strip(bufs[i]); - r->stats.bytes += bufs[i]->pkt_len; + nb_bytes += bufs[i]->pkt_len; } - vhost_update_packet_xstats(r, bufs, nb_rx); + r->stats.bytes += nb_bytes; + vhost_update_packet_xstats(r, bufs, nb_rx, nb_bytes, 0); out: rte_atomic32_set(&r->while_queuing, 0); @@ -424,6 +429,8 @@ eth_vhost_tx(void *q, struct rte_mbuf **bufs, uint16_t nb_bufs) struct vhost_queue *r = q; uint16_t i, nb_tx = 0; uint16_t nb_send = 0; + uint64_t nb_bytes = 0; + uint64_t nb_missed = 0; if (unlikely(rte_atomic32_read(&r->allow_queuing) == 0)) return 0; @@ -464,20 +471,23 @@ eth_vhost_tx(void *q, struct rte_mbuf **bufs, uint16_t nb_bufs) break; } + for (i = 0; likely(i < nb_tx); i++) + nb_bytes += bufs[i]->pkt_len; + + nb_missed = nb_bufs - nb_tx; + r->stats.pkts += nb_tx; + r->stats.bytes += nb_bytes; r->stats.missed_pkts += nb_bufs - nb_tx; - for (i = 0; likely(i < nb_tx); i++) - r->stats.bytes += bufs[i]->pkt_len; - - vhost_update_packet_xstats(r, bufs, nb_tx); + vhost_update_packet_xstats(r, bufs, nb_tx, nb_bytes, nb_missed); - /* According to RFC2863 page42 section ifHCOutMulticastPkts and - * ifHCOutBroadcastPkts, the counters "multicast" and "broadcast" - * are increased when packets are not transmitted successfully. + /* According to RFC2863, ifHCOutUcastPkts, ifHCOutMulticastPkts and + * ifHCOutBroadcastPkts counters are increased when packets are not + * transmitted successfully. */ for (i = nb_tx; i < nb_bufs; i++) - vhost_count_multicast_broadcast(r, bufs[i]); + vhost_count_xcast_packets(r, bufs[i]); for (i = 0; likely(i < nb_tx); i++) rte_pktmbuf_free(bufs[i]); @@ -487,17 +497,6 @@ 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) { @@ -526,12 +525,58 @@ 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) { @@ -539,6 +584,18 @@ 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); @@ -573,6 +630,8 @@ 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; } @@ -595,7 +654,6 @@ 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; @@ -625,6 +683,8 @@ 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); @@ -643,14 +703,12 @@ 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; @@ -772,7 +830,7 @@ new_device(int vid) VHOST_LOG(INFO, "Vhost device %d created\n", vid); - _rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_INTR_LSC, NULL); + rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_INTR_LSC, NULL); return 0; } @@ -829,7 +887,48 @@ destroy_device(int vid) VHOST_LOG(INFO, "Vhost device %d destroyed\n", vid); eth_vhost_uninstall_intr(eth_dev); - _rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_INTR_LSC, NULL); + 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 @@ -850,7 +949,16 @@ 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); @@ -858,7 +966,7 @@ vring_state_changed(int vid, uint16_t vring, int enable) VHOST_LOG(INFO, "vring%u is %s\n", vring, enable ? "enabled" : "disabled"); - _rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_QUEUE_STATE, NULL); + rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_QUEUE_STATE, NULL); return 0; } @@ -869,6 +977,74 @@ 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) @@ -935,6 +1111,24 @@ 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) { @@ -959,38 +1153,42 @@ eth_dev_start(struct rte_eth_dev *eth_dev) return 0; } -static void +static int eth_dev_stop(struct rte_eth_dev *dev) { struct pmd_internal *internal = dev->data->dev_private; + dev->data->dev_started = 0; rte_atomic32_set(&internal->started, 0); update_queuing_status(dev); + + return 0; } -static void +static int eth_dev_close(struct rte_eth_dev *dev) { struct pmd_internal *internal; struct internal_list *list; - unsigned int i; + unsigned int i, ret; + + if (rte_eal_process_type() != RTE_PROC_PRIMARY) + return 0; internal = dev->data->dev_private; if (!internal) - return; - - eth_dev_stop(dev); + return 0; - rte_vhost_driver_unregister(internal->iface_name); + ret = eth_dev_stop(dev); 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++) @@ -1000,12 +1198,15 @@ 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]); - rte_free(dev->data->mac_addrs); - free(internal->dev_name); - free(internal->iface_name); + rte_free(internal->iface_name); rte_free(internal); dev->data->dev_private = NULL; + + rte_free(vring_states[dev->data->port_id]); + vring_states[dev->data->port_id] = NULL; + + return ret; } static int @@ -1026,6 +1227,7 @@ 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; @@ -1047,12 +1249,13 @@ 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; } -static void +static int eth_dev_info(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info) { @@ -1061,7 +1264,7 @@ eth_dev_info(struct rte_eth_dev *dev, internal = dev->data->dev_private; if (internal == NULL) { VHOST_LOG(ERR, "Invalid device specified\n"); - return; + return -ENODEV; } dev_info->max_mac_addrs = 1; @@ -1073,13 +1276,15 @@ eth_dev_info(struct rte_eth_dev *dev, dev_info->tx_offload_capa = DEV_TX_OFFLOAD_MULTI_SEGS | DEV_TX_OFFLOAD_VLAN_INSERT; dev_info->rx_offload_capa = DEV_RX_OFFLOAD_VLAN_STRIP; + + return 0; } static int eth_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats) { unsigned i; - unsigned long rx_total = 0, tx_total = 0, tx_missed_total = 0; + unsigned long rx_total = 0, tx_total = 0; unsigned long rx_total_bytes = 0, tx_total_bytes = 0; struct vhost_queue *vq; @@ -1101,7 +1306,6 @@ eth_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats) continue; vq = dev->data->tx_queues[i]; stats->q_opackets[i] = vq->stats.pkts; - tx_missed_total += vq->stats.missed_pkts; tx_total += stats->q_opackets[i]; stats->q_obytes[i] = vq->stats.bytes; @@ -1110,14 +1314,13 @@ eth_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats) stats->ipackets = rx_total; stats->opackets = tx_total; - stats->oerrors = tx_missed_total; stats->ibytes = rx_total_bytes; stats->obytes = tx_total_bytes; return 0; } -static void +static int eth_stats_reset(struct rte_eth_dev *dev) { struct vhost_queue *vq; @@ -1138,6 +1341,8 @@ eth_stats_reset(struct rte_eth_dev *dev) vq->stats.bytes = 0; vq->stats.missed_pkts = 0; } + + return 0; } static void @@ -1186,7 +1391,6 @@ static const struct eth_dev_ops ops = { .rx_queue_release = eth_queue_release, .tx_queue_release = eth_queue_release, .tx_done_cleanup = eth_tx_done_cleanup, - .rx_queue_count = eth_rx_queue_count, .link_update = eth_link_update, .stats_get = eth_stats_get, .stats_reset = eth_stats_reset, @@ -1197,27 +1401,20 @@ static const struct eth_dev_ops ops = { .rx_queue_intr_disable = eth_rxq_intr_disable, }; -static struct rte_vdev_driver pmd_vhost_drv; - 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 ether_addr *eth_addr = NULL; - struct rte_vhost_vring_state *vring_state = NULL; - struct internal_list *list = NULL; + struct rte_ether_addr *eth_addr = 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) @@ -1231,70 +1428,44 @@ 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; + data->dev_flags = RTE_ETH_DEV_INTR_LSC | + RTE_ETH_DEV_AUTOFILL_QUEUE_XSTATS; + data->promiscuous = 1; + data->all_multicast = 1; eth_dev->dev_ops = &ops; + eth_dev->rx_queue_count = eth_rx_queue_count; /* finally assign rx and tx ops */ 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; } @@ -1335,10 +1506,13 @@ 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); @@ -1350,8 +1524,11 @@ 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; @@ -1390,16 +1567,6 @@ rte_pmd_vhost_probe(struct rte_vdev_device *dev) flags |= RTE_VHOST_USER_CLIENT; } - if (rte_kvargs_count(kvlist, ETH_VHOST_DEQUEUE_ZERO_COPY) == 1) { - ret = rte_kvargs_process(kvlist, ETH_VHOST_DEQUEUE_ZERO_COPY, - &open_int, &dequeue_zero_copy); - if (ret < 0) - goto out_free; - - if (dequeue_zero_copy) - flags |= RTE_VHOST_USER_DEQUEUE_ZERO_COPY; - } - if (rte_kvargs_count(kvlist, ETH_VHOST_IOMMU_SUPPORT) == 1) { ret = rte_kvargs_process(kvlist, ETH_VHOST_IOMMU_SUPPORT, &open_int, &iommu_support); @@ -1420,11 +1587,48 @@ 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); @@ -1443,16 +1647,9 @@ rte_pmd_vhost_remove(struct rte_vdev_device *dev) /* find an ethdev entry */ eth_dev = rte_eth_dev_allocated(name); if (eth_dev == NULL) - return -ENODEV; - - if (rte_eal_process_type() != RTE_PROC_PRIMARY) - return rte_eth_dev_release_port_secondary(eth_dev); + return 0; eth_dev_close(eth_dev); - - rte_free(vring_states[eth_dev->data->port_id]); - vring_states[eth_dev->data->port_id] = NULL; - rte_eth_dev_release_port(eth_dev); return 0; @@ -1467,11 +1664,10 @@ RTE_PMD_REGISTER_VDEV(net_vhost, pmd_vhost_drv); RTE_PMD_REGISTER_ALIAS(net_vhost, eth_vhost); RTE_PMD_REGISTER_PARAM_STRING(net_vhost, "iface= " - "queues="); - -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); -} + "queues= " + "client=<0|1> " + "iommu-support=<0|1> " + "postcopy-support=<0|1> " + "tso=<0|1> " + "linear-buffer=<0|1> " + "ext-buffer=<0|1>");