X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fvhost%2Frte_eth_vhost.c;h=e55278af696047359fcef7c7eb182dd2d2f5089f;hb=3d4cd4be577c335f9f07c78d125686f5b073c5a5;hp=04179b4db6629a6f7b187f4979589cd948978438;hpb=f8244c6399d9fae6afab6770ae367aef38742ea5;p=dpdk.git diff --git a/drivers/net/vhost/rte_eth_vhost.c b/drivers/net/vhost/rte_eth_vhost.c index 04179b4db6..e55278af69 100644 --- a/drivers/net/vhost/rte_eth_vhost.c +++ b/drivers/net/vhost/rte_eth_vhost.c @@ -1,57 +1,40 @@ -/*- - * BSD LICENSE - * - * Copyright (c) 2016 IGEL Co., Ltd. - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * * Neither the name of IGEL Co.,Ltd. nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2016 IGEL Co., Ltd. + * Copyright(c) 2016-2018 Intel Corporation */ #include #include #include +#include #include -#include +#include #include #include #include -#include +#include #include #include #include #include "rte_eth_vhost.h" +RTE_LOG_REGISTER(vhost_logtype, pmd.net.vhost, NOTICE); + +#define VHOST_LOG(level, ...) \ + rte_log(RTE_LOG_ ## level, vhost_logtype, __VA_ARGS__) + 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[] = { @@ -59,10 +42,15 @@ static const char *valid_arguments[] = { 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 */, @@ -108,14 +96,19 @@ 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; + uint8_t vlan_strip; }; struct internal_list { @@ -233,7 +226,7 @@ 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; @@ -251,6 +244,8 @@ vhost_dev_xstats_reset(struct rte_eth_dev *dev) continue; memset(&vq->stats, 0, sizeof(vq->stats)); } + + return 0; } static int @@ -342,12 +337,12 @@ static inline void vhost_count_multicast_broadcast(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]++; @@ -419,6 +414,11 @@ eth_vhost_rx(void *q, struct rte_mbuf **bufs, uint16_t nb_bufs) for (i = 0; likely(i < nb_rx); i++) { bufs[i]->port = r->port; + bufs[i]->vlan_tci = 0; + + if (r->internal->vlan_strip) + rte_vlan_strip(bufs[i]); + r->stats.bytes += bufs[i]->pkt_len; } @@ -435,7 +435,7 @@ 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 = nb_bufs; + uint16_t nb_send = 0; if (unlikely(rte_atomic32_read(&r->allow_queuing) == 0)) return 0; @@ -445,6 +445,22 @@ eth_vhost_tx(void *q, struct rte_mbuf **bufs, uint16_t nb_bufs) if (unlikely(rte_atomic32_read(&r->allow_queuing) == 0)) goto out; + for (i = 0; i < nb_bufs; i++) { + struct rte_mbuf *m = bufs[i]; + + /* Do VLAN tag insertion */ + if (m->ol_flags & PKT_TX_VLAN_PKT) { + int error = rte_vlan_insert(&m); + if (unlikely(error)) { + rte_pktmbuf_free(m); + continue; + } + } + + bufs[nb_send] = m; + ++nb_send; + } + /* Enqueue packets to guest RX queue */ while (nb_send) { uint16_t nb_pkts; @@ -483,12 +499,6 @@ out: return nb_tx; } -static int -eth_dev_configure(struct rte_eth_dev *dev __rte_unused) -{ - return 0; -} - static inline struct internal_list * find_internal_resource(char *ifname) { @@ -517,6 +527,195 @@ 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 old_intr_enable, ret = 0; + + vq = dev->data->rx_queues[qid]; + if (!vq) { + VHOST_LOG(ERR, "rxq%d is not setup yet\n", 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); + return ret; + } + VHOST_LOG(INFO, "Enable interrupt for rxq%d\n", qid); + rte_vhost_enable_guest_notification(vq->vid, (qid << 1) + 1, 1); + rte_wmb(); + + return ret; +} + +static int +eth_rxq_intr_disable(struct rte_eth_dev *dev, uint16_t qid) +{ + struct rte_vhost_vring vring; + struct vhost_queue *vq; + int ret = 0; + + vq = dev->data->rx_queues[qid]; + if (!vq) { + VHOST_LOG(ERR, "rxq%d is not setup yet\n", qid); + return -1; + } + + 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", qid); + return ret; + } + VHOST_LOG(INFO, "Disable interrupt for rxq%d\n", qid); + rte_vhost_enable_guest_notification(vq->vid, (qid << 1) + 1, 0); + rte_wmb(); + + vq->intr_enable = 0; + + return 0; +} + +static void +eth_vhost_uninstall_intr(struct rte_eth_dev *dev) +{ + struct rte_intr_handle *intr_handle = dev->intr_handle; + + if (intr_handle) { + if (intr_handle->intr_vec) + free(intr_handle->intr_vec); + free(intr_handle); + } + + dev->intr_handle = NULL; +} + +static int +eth_vhost_install_intr(struct rte_eth_dev *dev) +{ + struct rte_vhost_vring vring; + struct vhost_queue *vq; + int nb_rxq = dev->data->nb_rx_queues; + int i; + int ret; + + /* uninstall firstly if we are reconnecting */ + if (dev->intr_handle) + eth_vhost_uninstall_intr(dev); + + dev->intr_handle = malloc(sizeof(*dev->intr_handle)); + if (!dev->intr_handle) { + VHOST_LOG(ERR, "Fail to allocate intr_handle\n"); + return -ENOMEM; + } + memset(dev->intr_handle, 0, sizeof(*dev->intr_handle)); + + dev->intr_handle->efd_counter_size = sizeof(uint64_t); + + dev->intr_handle->intr_vec = + malloc(nb_rxq * sizeof(dev->intr_handle->intr_vec[0])); + + if (!dev->intr_handle->intr_vec) { + VHOST_LOG(ERR, + "Failed to allocate memory for interrupt vector\n"); + free(dev->intr_handle); + return -ENOMEM; + } + + 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); + continue; + } + + ret = rte_vhost_get_vhost_vring(vq->vid, (i << 1) + 1, &vring); + if (ret < 0) { + VHOST_LOG(INFO, + "Failed to get rxq-%d's vring, skip!\n", i); + continue; + } + + if (vring.kickfd < 0) { + VHOST_LOG(INFO, + "rxq-%d's kickfd is invalid, skip!\n", i); + continue; + } + dev->intr_handle->efds[i] = vring.kickfd; + VHOST_LOG(INFO, "Installed intr vec for rxq-%d\n", i); + } + + 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; +} + static void update_queuing_status(struct rte_eth_dev *dev) { @@ -525,6 +724,9 @@ update_queuing_status(struct rte_eth_dev *dev) unsigned int i; int allow_queuing = 1; + if (!dev->data->rx_queues || !dev->data->tx_queues) + return; + if (rte_atomic32_read(&internal->started) == 0 || rte_atomic32_read(&internal->dev_attached) == 0) allow_queuing = 0; @@ -549,13 +751,37 @@ update_queuing_status(struct rte_eth_dev *dev) } } +static void +queue_setup(struct rte_eth_dev *eth_dev, struct pmd_internal *internal) +{ + struct vhost_queue *vq; + int i; + + for (i = 0; i < eth_dev->data->nb_rx_queues; i++) { + vq = eth_dev->data->rx_queues[i]; + if (!vq) + continue; + vq->vid = internal->vid; + vq->internal = internal; + vq->port = eth_dev->data->port_id; + } + for (i = 0; i < eth_dev->data->nb_tx_queues; i++) { + vq = eth_dev->data->tx_queues[i]; + if (!vq) + continue; + vq->vid = internal->vid; + vq->internal = internal; + vq->port = eth_dev->data->port_id; + } +} + static int new_device(int vid) { struct rte_eth_dev *eth_dev; struct internal_list *list; struct pmd_internal *internal; - struct vhost_queue *vq; + struct rte_eth_conf *dev_conf; unsigned i; char ifname[PATH_MAX]; #ifdef RTE_LIBRTE_VHOST_NUMA @@ -565,12 +791,13 @@ new_device(int vid) rte_vhost_get_ifname(vid, ifname, sizeof(ifname)); list = find_internal_resource(ifname); if (list == NULL) { - RTE_LOG(INFO, PMD, "Invalid device name: %s\n", ifname); + VHOST_LOG(INFO, "Invalid device name: %s\n", ifname); return -1; } eth_dev = list->eth_dev; internal = eth_dev->data->dev_private; + dev_conf = ð_dev->data->dev_conf; #ifdef RTE_LIBRTE_VHOST_NUMA newnode = rte_vhost_get_numa_node(vid); @@ -578,21 +805,19 @@ new_device(int vid) eth_dev->data->numa_node = newnode; #endif - for (i = 0; i < eth_dev->data->nb_rx_queues; i++) { - vq = eth_dev->data->rx_queues[i]; - if (vq == NULL) - continue; - vq->vid = vid; - vq->internal = internal; - vq->port = eth_dev->data->port_id; - } - for (i = 0; i < eth_dev->data->nb_tx_queues; i++) { - vq = eth_dev->data->tx_queues[i]; - if (vq == NULL) - continue; - vq->vid = vid; - vq->internal = internal; - vq->port = eth_dev->data->port_id; + internal->vid = vid; + if (rte_atomic32_read(&internal->started) == 1) { + queue_setup(eth_dev, internal); + + if (dev_conf->intr_conf.rxq) { + if (eth_vhost_install_intr(eth_dev) < 0) { + VHOST_LOG(INFO, + "Failed to install interrupt handler."); + return -1; + } + } + } else { + VHOST_LOG(INFO, "RX/TX queues not exist yet\n"); } for (i = 0; i < rte_vhost_get_vring_num(vid); i++) @@ -605,10 +830,9 @@ new_device(int vid) rte_atomic32_set(&internal->dev_attached, 1); update_queuing_status(eth_dev); - RTE_LOG(INFO, PMD, "New connection established\n"); + VHOST_LOG(INFO, "Vhost device %d created\n", vid); - _rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_INTR_LSC, - NULL, NULL); + _rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_INTR_LSC, NULL); return 0; } @@ -627,7 +851,7 @@ destroy_device(int vid) rte_vhost_get_ifname(vid, ifname, sizeof(ifname)); list = find_internal_resource(ifname); if (list == NULL) { - RTE_LOG(ERR, PMD, "Invalid interface name: %s\n", ifname); + VHOST_LOG(ERR, "Invalid interface name: %s\n", ifname); return; } eth_dev = list->eth_dev; @@ -638,17 +862,19 @@ destroy_device(int vid) eth_dev->data->dev_link.link_status = ETH_LINK_DOWN; - for (i = 0; i < eth_dev->data->nb_rx_queues; i++) { - vq = eth_dev->data->rx_queues[i]; - if (vq == NULL) - continue; - vq->vid = -1; - } - for (i = 0; i < eth_dev->data->nb_tx_queues; i++) { - vq = eth_dev->data->tx_queues[i]; - if (vq == NULL) - continue; - vq->vid = -1; + if (eth_dev->data->rx_queues && eth_dev->data->tx_queues) { + for (i = 0; i < eth_dev->data->nb_rx_queues; i++) { + vq = eth_dev->data->rx_queues[i]; + if (!vq) + continue; + vq->vid = -1; + } + for (i = 0; i < eth_dev->data->nb_tx_queues; i++) { + vq = eth_dev->data->tx_queues[i]; + if (!vq) + continue; + vq->vid = -1; + } } state = vring_states[eth_dev->data->port_id]; @@ -660,10 +886,51 @@ destroy_device(int vid) state->max_vring = 0; rte_spinlock_unlock(&state->lock); - RTE_LOG(INFO, PMD, "Connection closed\n"); + 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, 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 @@ -677,23 +944,31 @@ vring_state_changed(int vid, uint16_t vring, int enable) rte_vhost_get_ifname(vid, ifname, sizeof(ifname)); list = find_internal_resource(ifname); if (list == NULL) { - RTE_LOG(ERR, PMD, "Invalid interface name: %s\n", ifname); + VHOST_LOG(ERR, "Invalid interface name: %s\n", ifname); return -1; } 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); - RTE_LOG(INFO, PMD, "vring%u is %s\n", + 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, NULL); + _rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_QUEUE_STATE, NULL); return 0; } @@ -704,6 +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) @@ -713,13 +1056,13 @@ rte_eth_vhost_get_queue_event(uint16_t port_id, int idx; if (port_id >= RTE_MAX_ETHPORTS) { - RTE_LOG(ERR, PMD, "Invalid port id\n"); + VHOST_LOG(ERR, "Invalid port id\n"); return -1; } state = vring_states[port_id]; if (!state) { - RTE_LOG(ERR, PMD, "Unused port\n"); + VHOST_LOG(ERR, "Unused port\n"); return -1; } @@ -771,12 +1114,43 @@ rte_eth_vhost_get_vid_from_port_id(uint16_t port_id) } static int -eth_dev_start(struct rte_eth_dev *dev) +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) +{ + struct pmd_internal *internal = eth_dev->data->dev_private; + struct rte_eth_conf *dev_conf = ð_dev->data->dev_conf; + + queue_setup(eth_dev, internal); + + if (rte_atomic32_read(&internal->dev_attached) == 1) { + if (dev_conf->intr_conf.rxq) { + if (eth_vhost_install_intr(eth_dev) < 0) { + VHOST_LOG(INFO, + "Failed to install interrupt handler."); + return -1; + } + } + } rte_atomic32_set(&internal->started, 1); - update_queuing_status(dev); + update_queuing_status(eth_dev); return 0; } @@ -803,28 +1177,30 @@ 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; + 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); + } - 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++) + rte_free(dev->data->rx_queues[i]); - for (i = 0; i < dev->data->nb_rx_queues; i++) - rte_free(dev->data->rx_queues[i]); - for (i = 0; i < dev->data->nb_tx_queues; i++) - rte_free(dev->data->tx_queues[i]); + if (dev->data->tx_queues) + 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; } static int @@ -839,12 +1215,13 @@ eth_rx_queue_setup(struct rte_eth_dev *dev, uint16_t rx_queue_id, vq = rte_zmalloc_socket(NULL, sizeof(struct vhost_queue), RTE_CACHE_LINE_SIZE, socket_id); if (vq == NULL) { - RTE_LOG(ERR, PMD, "Failed to allocate memory for rx queue\n"); + VHOST_LOG(ERR, "Failed to allocate memory for rx queue\n"); return -ENOMEM; } 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; @@ -861,17 +1238,18 @@ eth_tx_queue_setup(struct rte_eth_dev *dev, uint16_t tx_queue_id, vq = rte_zmalloc_socket(NULL, sizeof(struct vhost_queue), RTE_CACHE_LINE_SIZE, socket_id); if (vq == NULL) { - RTE_LOG(ERR, PMD, "Failed to allocate memory for tx queue\n"); + VHOST_LOG(ERR, "Failed to allocate memory for tx queue\n"); return -ENOMEM; } 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) { @@ -879,8 +1257,8 @@ eth_dev_info(struct rte_eth_dev *dev, internal = dev->data->dev_private; if (internal == NULL) { - RTE_LOG(ERR, PMD, "Invalid device specified\n"); - return; + VHOST_LOG(ERR, "Invalid device specified\n"); + return -ENODEV; } dev_info->max_mac_addrs = 1; @@ -888,13 +1266,19 @@ eth_dev_info(struct rte_eth_dev *dev, dev_info->max_rx_queues = internal->max_queues; dev_info->max_tx_queues = internal->max_queues; dev_info->min_rx_bufsize = 0; + + 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 void +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; @@ -916,7 +1300,6 @@ 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; @@ -925,12 +1308,13 @@ 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; @@ -951,6 +1335,8 @@ eth_stats_reset(struct rte_eth_dev *dev) vq->stats.bytes = 0; vq->stats.missed_pkts = 0; } + + return 0; } static void @@ -1006,86 +1392,59 @@ static const struct eth_dev_ops ops = { .xstats_reset = vhost_dev_xstats_reset, .xstats_get = vhost_dev_xstats_get, .xstats_get_names = vhost_dev_xstats_get_names, + .rx_queue_intr_enable = eth_rxq_intr_enable, + .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 = NULL; + 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; - RTE_LOG(INFO, PMD, "Creating VHOST-USER backend on numa socket %u\n", + VHOST_LOG(INFO, "Creating VHOST-USER backend on numa socket %u\n", numa_node); - /* now do all data allocation - for eth_dev structure and internal - * (private) data - */ - data = rte_zmalloc_socket(name, sizeof(*data), 0, numa_node); - if (data == NULL) - goto error; - - 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) goto error; + data = eth_dev->data; eth_addr = rte_zmalloc_socket(name, sizeof(*eth_addr), 0, numa_node); if (eth_addr == NULL) goto error; + data->mac_addrs = eth_addr; *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; - - /* We'll replace the 'data' originally allocated by eth_dev. So the - * vhost PMD resources won't be shared between multi processes. - */ - rte_memcpy(data, eth_dev->data, sizeof(*data)); - eth_dev->data = data; + 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->mac_addrs = eth_addr; - data->dev_flags = - RTE_ETH_DEV_DETACHABLE | RTE_ETH_DEV_INTR_LSC; + 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; @@ -1093,34 +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) { - RTE_LOG(ERR, PMD, "Can't register callbacks\n"); - goto error; - } - - if (rte_vhost_driver_start(iface_name) < 0) { - RTE_LOG(ERR, PMD, "Failed to start driver for %s\n", - iface_name); - goto error; - } - - return data->port_id; + rte_eth_dev_probing_finish(eth_dev); + return 0; error: - if (internal) { - free(internal->iface_name); - free(internal->dev_name); - } - rte_free(vring_state); - rte_free(eth_addr); - if (eth_dev) - rte_eth_dev_release_port(eth_dev); - rte_free(internal); - rte_free(list); - rte_free(data); + if (internal) + rte_free(internal->iface_name); + rte_eth_dev_release_port(eth_dev); return -1; } @@ -1161,11 +1499,34 @@ 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); - RTE_LOG(INFO, PMD, "Initializing pmd_vhost for %s\n", - rte_vdev_device_name(dev)); + VHOST_LOG(INFO, "Initializing pmd_vhost for %s\n", name); + + if (rte_eal_process_type() == RTE_PROC_SECONDARY) { + eth_dev = rte_eth_dev_attach_secondary(name); + if (!eth_dev) { + VHOST_LOG(ERR, "Failed to probe %s\n", name); + return -1; + } + 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; + } kvlist = rte_kvargs_parse(rte_vdev_device_args(dev), valid_arguments); if (kvlist == NULL) @@ -1210,11 +1571,68 @@ rte_pmd_vhost_probe(struct rte_vdev_device *dev) 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); + if (ret < 0) + goto out_free; + + if (iommu_support) + flags |= RTE_VHOST_USER_IOMMU_SUPPORT; + } + + if (rte_kvargs_count(kvlist, ETH_VHOST_POSTCOPY_SUPPORT) == 1) { + ret = rte_kvargs_process(kvlist, ETH_VHOST_POSTCOPY_SUPPORT, + &open_int, &postcopy_support); + if (ret < 0) + goto out_free; + + if (postcopy_support) + 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); @@ -1228,19 +1646,17 @@ rte_pmd_vhost_remove(struct rte_vdev_device *dev) struct rte_eth_dev *eth_dev = NULL; name = rte_vdev_device_name(dev); - RTE_LOG(INFO, PMD, "Un-Initializing pmd_vhost for %s\n", name); + VHOST_LOG(INFO, "Un-Initializing pmd_vhost for %s\n", name); /* find an ethdev entry */ eth_dev = rte_eth_dev_allocated(name); if (eth_dev == NULL) - return -ENODEV; + return 0; - eth_dev_close(eth_dev); + if (rte_eal_process_type() != RTE_PROC_PRIMARY) + return rte_eth_dev_release_port(eth_dev); - rte_free(vring_states[eth_dev->data->port_id]); - vring_states[eth_dev->data->port_id] = NULL; - - rte_free(eth_dev->data); + eth_dev_close(eth_dev); rte_eth_dev_release_port(eth_dev); @@ -1256,4 +1672,11 @@ 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="); + "queues= " + "client=<0|1> " + "dequeue-zero-copy=<0|1> " + "iommu-support=<0|1> " + "postcopy-support=<0|1> " + "tso=<0|1> " + "linear-buffer=<0|1> " + "ext-buffer=<0|1>");