-
-/*
- * This function is called by each data core. It handles all RX/TX registered with the
- * core. For TX the specific lcore linked list is used. For RX, MAC addresses are compared
- * with all devices in the main linked list.
- */
-static int
-switch_worker(__attribute__((unused)) void *arg)
-{
- struct rte_mempool *mbuf_pool = arg;
- struct virtio_net *dev = NULL;
- struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
- struct virtio_net_data_ll *dev_ll;
- struct mbuf_table *tx_q;
- volatile struct lcore_ll_info *lcore_ll;
- const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) / US_PER_S * BURST_TX_DRAIN_US;
- uint64_t prev_tsc, diff_tsc, cur_tsc, ret_count = 0;
- unsigned ret, i;
- const uint16_t lcore_id = rte_lcore_id();
- const uint16_t num_cores = (uint16_t)rte_lcore_count();
- uint16_t rx_count = 0;
- uint32_t mergeable = 0;
-
- RTE_LOG(INFO, VHOST_DATA, "Procesing on Core %u started\n", lcore_id);
- lcore_ll = lcore_info[lcore_id].lcore_ll;
- prev_tsc = 0;
-
- tx_q = &lcore_tx_queue[lcore_id];
- for (i = 0; i < num_cores; i ++) {
- if (lcore_ids[i] == lcore_id) {
- tx_q->txq_id = i;
- break;
- }
- }
-
- while(1) {
- cur_tsc = rte_rdtsc();
- /*
- * TX burst queue drain
- */
- diff_tsc = cur_tsc - prev_tsc;
- if (unlikely(diff_tsc > drain_tsc)) {
-
- if (tx_q->len) {
- LOG_DEBUG(VHOST_DATA, "TX queue drained after timeout with burst size %u \n", tx_q->len);
-
- /*Tx any packets in the queue*/
- ret = rte_eth_tx_burst(ports[0], (uint16_t)tx_q->txq_id,
- (struct rte_mbuf **)tx_q->m_table,
- (uint16_t)tx_q->len);
- if (unlikely(ret < tx_q->len)) {
- do {
- rte_pktmbuf_free(tx_q->m_table[ret]);
- } while (++ret < tx_q->len);
- }
-
- tx_q->len = 0;
- }
-
- prev_tsc = cur_tsc;
-
- }
-
- rte_prefetch0(lcore_ll->ll_root_used);
- /*
- * Inform the configuration core that we have exited the linked list and that no devices are
- * in use if requested.
- */
- if (lcore_ll->dev_removal_flag == REQUEST_DEV_REMOVAL)
- lcore_ll->dev_removal_flag = ACK_DEV_REMOVAL;
-
- /*
- * Process devices
- */
- dev_ll = lcore_ll->ll_root_used;
-
- while (dev_ll != NULL) {
- /*get virtio device ID*/
- dev = dev_ll->dev;
- mergeable =
- dev->features & (1 << VIRTIO_NET_F_MRG_RXBUF);
-
- if (dev->remove) {
- dev_ll = dev_ll->next;
- unlink_vmdq(dev);
- dev->ready = DEVICE_SAFE_REMOVE;
- continue;
- }
- if (likely(dev->ready == DEVICE_RX)) {
- /*Handle guest RX*/
- rx_count = rte_eth_rx_burst(ports[0],
- (uint16_t)dev->vmdq_rx_q, pkts_burst, MAX_PKT_BURST);
-
- if (rx_count) {
- if (likely(mergeable == 0))
- ret_count =
- virtio_dev_rx(dev,
- pkts_burst, rx_count);
- else
- ret_count =
- virtio_dev_merge_rx(dev,
- pkts_burst, rx_count);
-
- if (enable_stats) {
- rte_atomic64_add(
- &dev_statistics[dev_ll->dev->device_fh].rx_total_atomic,
- rx_count);
- rte_atomic64_add(
- &dev_statistics[dev_ll->dev->device_fh].rx_atomic, ret_count);
- }
- while (likely(rx_count)) {
- rx_count--;
- rte_pktmbuf_free(pkts_burst[rx_count]);
- }
-
- }
- }
-
- if (!dev->remove) {
- /*Handle guest TX*/
- if (likely(mergeable == 0))
- virtio_dev_tx(dev, mbuf_pool);
- else
- virtio_dev_merge_tx(dev, mbuf_pool);
- }
-
- /*move to the next device in the list*/
- dev_ll = dev_ll->next;
- }
- }
-
- return 0;
-}
-
-/*
- * This function gets available ring number for zero copy rx.
- * Only one thread will call this funciton for a paticular virtio device,
- * so, it is designed as non-thread-safe function.
- */
-static inline uint32_t __attribute__((always_inline))
-get_available_ring_num_zcp(struct virtio_net *dev)
-{
- struct vhost_virtqueue *vq = dev->virtqueue[VIRTIO_RXQ];
- uint16_t avail_idx;
-
- avail_idx = *((volatile uint16_t *)&vq->avail->idx);
- return (uint32_t)(avail_idx - vq->last_used_idx_res);
-}
-
-/*
- * This function gets available ring index for zero copy rx,
- * it will retry 'burst_rx_retry_num' times till it get enough ring index.
- * Only one thread will call this funciton for a paticular virtio device,
- * so, it is designed as non-thread-safe function.
- */
-static inline uint32_t __attribute__((always_inline))
-get_available_ring_index_zcp(struct virtio_net *dev,
- uint16_t *res_base_idx, uint32_t count)
-{
- struct vhost_virtqueue *vq = dev->virtqueue[VIRTIO_RXQ];
- uint16_t avail_idx;
- uint32_t retry = 0;
- uint16_t free_entries;
-
- *res_base_idx = vq->last_used_idx_res;
- avail_idx = *((volatile uint16_t *)&vq->avail->idx);
- free_entries = (avail_idx - *res_base_idx);
-
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") in get_available_ring_index_zcp: "
- "avail idx: %d, "
- "res base idx:%d, free entries:%d\n",
- dev->device_fh, avail_idx, *res_base_idx,
- free_entries);
-
- /*
- * If retry is enabled and the queue is full then we wait
- * and retry to avoid packet loss.
- */
- if (enable_retry && unlikely(count > free_entries)) {
- for (retry = 0; retry < burst_rx_retry_num; retry++) {
- rte_delay_us(burst_rx_delay_time);
- avail_idx = *((volatile uint16_t *)&vq->avail->idx);
- free_entries = (avail_idx - *res_base_idx);
- if (count <= free_entries)
- break;
- }
- }
-
- /*check that we have enough buffers*/
- if (unlikely(count > free_entries))
- count = free_entries;
-
- if (unlikely(count == 0)) {
- LOG_DEBUG(VHOST_DATA,
- "(%"PRIu64") Fail in get_available_ring_index_zcp: "
- "avail idx: %d, res base idx:%d, free entries:%d\n",
- dev->device_fh, avail_idx,
- *res_base_idx, free_entries);
- return 0;
- }
-
- vq->last_used_idx_res = *res_base_idx + count;
-
- return count;
-}
-
-/*
- * This function put descriptor back to used list.
- */
-static inline void __attribute__((always_inline))
-put_desc_to_used_list_zcp(struct vhost_virtqueue *vq, uint16_t desc_idx)
-{
- uint16_t res_cur_idx = vq->last_used_idx;
- vq->used->ring[res_cur_idx & (vq->size - 1)].id = (uint32_t)desc_idx;
- vq->used->ring[res_cur_idx & (vq->size - 1)].len = 0;
- rte_compiler_barrier();
- *(volatile uint16_t *)&vq->used->idx += 1;
- vq->last_used_idx += 1;
-
- /* Kick the guest if necessary. */
- if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT))
- eventfd_write((int)vq->kickfd, 1);
-}
-
-/*
- * This function get available descriptor from vitio vring and un-attached mbuf
- * from vpool->ring, and then attach them together. It needs adjust the offset
- * for buff_addr and phys_addr accroding to PMD implementation, otherwise the
- * frame data may be put to wrong location in mbuf.
- */
-static inline void __attribute__((always_inline))
-attach_rxmbuf_zcp(struct virtio_net *dev)
-{
- uint16_t res_base_idx, desc_idx;
- uint64_t buff_addr, phys_addr;
- struct vhost_virtqueue *vq;
- struct vring_desc *desc;
- struct rte_mbuf *mbuf = NULL;
- struct vpool *vpool;
- hpa_type addr_type;
-
- vpool = &vpool_array[dev->vmdq_rx_q];
- vq = dev->virtqueue[VIRTIO_RXQ];
-
- do {
- if (unlikely(get_available_ring_index_zcp(dev, &res_base_idx,
- 1) != 1))
- return;
- desc_idx = vq->avail->ring[(res_base_idx) & (vq->size - 1)];
-
- desc = &vq->desc[desc_idx];
- if (desc->flags & VRING_DESC_F_NEXT) {
- desc = &vq->desc[desc->next];
- buff_addr = gpa_to_vva(dev, desc->addr);
- phys_addr = gpa_to_hpa(dev, desc->addr, desc->len,
- &addr_type);
- } else {
- buff_addr = gpa_to_vva(dev,
- desc->addr + vq->vhost_hlen);
- phys_addr = gpa_to_hpa(dev,
- desc->addr + vq->vhost_hlen,
- desc->len, &addr_type);
- }
-
- if (unlikely(addr_type == PHYS_ADDR_INVALID)) {
- RTE_LOG(ERR, VHOST_DATA, "(%"PRIu64") Invalid frame buffer"
- " address found when attaching RX frame buffer"
- " address!\n", dev->device_fh);
- put_desc_to_used_list_zcp(vq, desc_idx);
- continue;
- }
-
- /*
- * Check if the frame buffer address from guest crosses
- * sub-region or not.
- */
- if (unlikely(addr_type == PHYS_ADDR_CROSS_SUBREG)) {
- RTE_LOG(ERR, VHOST_DATA,
- "(%"PRIu64") Frame buffer address cross "
- "sub-regioin found when attaching RX frame "
- "buffer address!\n",
- dev->device_fh);
- put_desc_to_used_list_zcp(vq, desc_idx);
- continue;
- }
- } while (unlikely(phys_addr == 0));
-
- rte_ring_sc_dequeue(vpool->ring, (void **)&mbuf);
- if (unlikely(mbuf == NULL)) {
- LOG_DEBUG(VHOST_DATA,
- "(%"PRIu64") in attach_rxmbuf_zcp: "
- "ring_sc_dequeue fail.\n",
- dev->device_fh);
- put_desc_to_used_list_zcp(vq, desc_idx);
- return;
- }
-
- if (unlikely(vpool->buf_size > desc->len)) {
- LOG_DEBUG(VHOST_DATA,
- "(%"PRIu64") in attach_rxmbuf_zcp: frame buffer "
- "length(%d) of descriptor idx: %d less than room "
- "size required: %d\n",
- dev->device_fh, desc->len, desc_idx, vpool->buf_size);
- put_desc_to_used_list_zcp(vq, desc_idx);
- rte_ring_sp_enqueue(vpool->ring, (void *)mbuf);
- return;
- }
-
- mbuf->buf_addr = (void *)(uintptr_t)(buff_addr - RTE_PKTMBUF_HEADROOM);
- mbuf->data_off = RTE_PKTMBUF_HEADROOM;
- mbuf->buf_physaddr = phys_addr - RTE_PKTMBUF_HEADROOM;
- mbuf->data_len = desc->len;
- MBUF_HEADROOM_UINT32(mbuf) = (uint32_t)desc_idx;
-
- LOG_DEBUG(VHOST_DATA,
- "(%"PRIu64") in attach_rxmbuf_zcp: res base idx:%d, "
- "descriptor idx:%d\n",
- dev->device_fh, res_base_idx, desc_idx);
-
- __rte_mbuf_raw_free(mbuf);
-
- return;
-}
-
-/*
- * Detach an attched packet mbuf -
- * - restore original mbuf address and length values.
- * - reset pktmbuf data and data_len to their default values.
- * All other fields of the given packet mbuf will be left intact.
- *
- * @param m
- * The attached packet mbuf.
- */
-static inline void pktmbuf_detach_zcp(struct rte_mbuf *m)
-{
- const struct rte_mempool *mp = m->pool;
- void *buf = RTE_MBUF_TO_BADDR(m);
- uint32_t buf_ofs;
- uint32_t buf_len = mp->elt_size - sizeof(*m);
- m->buf_physaddr = rte_mempool_virt2phy(mp, m) + sizeof(*m);
-
- m->buf_addr = buf;
- m->buf_len = (uint16_t)buf_len;
-
- buf_ofs = (RTE_PKTMBUF_HEADROOM <= m->buf_len) ?
- RTE_PKTMBUF_HEADROOM : m->buf_len;
- m->data_off = buf_ofs;
-
- m->data_len = 0;
-}
-
-/*
- * This function is called after packets have been transimited. It fetchs mbuf
- * from vpool->pool, detached it and put into vpool->ring. It also update the
- * used index and kick the guest if necessary.
- */
-static inline uint32_t __attribute__((always_inline))
-txmbuf_clean_zcp(struct virtio_net *dev, struct vpool *vpool)
-{
- struct rte_mbuf *mbuf;
- struct vhost_virtqueue *vq = dev->virtqueue[VIRTIO_TXQ];
- uint32_t used_idx = vq->last_used_idx & (vq->size - 1);
- uint32_t index = 0;
- uint32_t mbuf_count = rte_mempool_count(vpool->pool);
-
- LOG_DEBUG(VHOST_DATA,
- "(%"PRIu64") in txmbuf_clean_zcp: mbuf count in mempool before "
- "clean is: %d\n",
- dev->device_fh, mbuf_count);
- LOG_DEBUG(VHOST_DATA,
- "(%"PRIu64") in txmbuf_clean_zcp: mbuf count in ring before "
- "clean is : %d\n",
- dev->device_fh, rte_ring_count(vpool->ring));
-
- for (index = 0; index < mbuf_count; index++) {
- mbuf = __rte_mbuf_raw_alloc(vpool->pool);
- if (likely(RTE_MBUF_INDIRECT(mbuf)))
- pktmbuf_detach_zcp(mbuf);
- rte_ring_sp_enqueue(vpool->ring, mbuf);
-
- /* Update used index buffer information. */
- vq->used->ring[used_idx].id = MBUF_HEADROOM_UINT32(mbuf);
- vq->used->ring[used_idx].len = 0;
-
- used_idx = (used_idx + 1) & (vq->size - 1);
- }
-
- LOG_DEBUG(VHOST_DATA,
- "(%"PRIu64") in txmbuf_clean_zcp: mbuf count in mempool after "
- "clean is: %d\n",
- dev->device_fh, rte_mempool_count(vpool->pool));
- LOG_DEBUG(VHOST_DATA,
- "(%"PRIu64") in txmbuf_clean_zcp: mbuf count in ring after "
- "clean is : %d\n",
- dev->device_fh, rte_ring_count(vpool->ring));
- LOG_DEBUG(VHOST_DATA,
- "(%"PRIu64") in txmbuf_clean_zcp: before updated "
- "vq->last_used_idx:%d\n",
- dev->device_fh, vq->last_used_idx);
-
- vq->last_used_idx += mbuf_count;
-
- LOG_DEBUG(VHOST_DATA,
- "(%"PRIu64") in txmbuf_clean_zcp: after updated "
- "vq->last_used_idx:%d\n",
- dev->device_fh, vq->last_used_idx);
-
- rte_compiler_barrier();
-
- *(volatile uint16_t *)&vq->used->idx += mbuf_count;
-
- /* Kick guest if required. */
- if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT))
- eventfd_write((int)vq->kickfd, 1);
-
- return 0;
-}
-
-/*
- * This function is called when a virtio device is destroy.
- * It fetchs mbuf from vpool->pool, and detached it, and put into vpool->ring.
- */
-static void mbuf_destroy_zcp(struct vpool *vpool)
-{
- struct rte_mbuf *mbuf = NULL;
- uint32_t index, mbuf_count = rte_mempool_count(vpool->pool);
-
- LOG_DEBUG(VHOST_CONFIG,
- "in mbuf_destroy_zcp: mbuf count in mempool before "
- "mbuf_destroy_zcp is: %d\n",
- mbuf_count);
- LOG_DEBUG(VHOST_CONFIG,
- "in mbuf_destroy_zcp: mbuf count in ring before "
- "mbuf_destroy_zcp is : %d\n",
- rte_ring_count(vpool->ring));
-
- for (index = 0; index < mbuf_count; index++) {
- mbuf = __rte_mbuf_raw_alloc(vpool->pool);
- if (likely(mbuf != NULL)) {
- if (likely(RTE_MBUF_INDIRECT(mbuf)))
- pktmbuf_detach_zcp(mbuf);
- rte_ring_sp_enqueue(vpool->ring, (void *)mbuf);
- }
- }
-
- LOG_DEBUG(VHOST_CONFIG,
- "in mbuf_destroy_zcp: mbuf count in mempool after "
- "mbuf_destroy_zcp is: %d\n",
- rte_mempool_count(vpool->pool));
- LOG_DEBUG(VHOST_CONFIG,
- "in mbuf_destroy_zcp: mbuf count in ring after "
- "mbuf_destroy_zcp is : %d\n",
- rte_ring_count(vpool->ring));
-}
-
-/*
- * This function update the use flag and counter.
- */
-static inline uint32_t __attribute__((always_inline))
-virtio_dev_rx_zcp(struct virtio_net *dev, struct rte_mbuf **pkts,
- uint32_t count)
-{
- struct vhost_virtqueue *vq;
- struct vring_desc *desc;
- struct rte_mbuf *buff;
- /* The virtio_hdr is initialised to 0. */
- struct virtio_net_hdr_mrg_rxbuf virtio_hdr
- = {{0, 0, 0, 0, 0, 0}, 0};
- uint64_t buff_hdr_addr = 0;
- uint32_t head[MAX_PKT_BURST], packet_len = 0;
- uint32_t head_idx, packet_success = 0;
- uint16_t res_cur_idx;
-
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") virtio_dev_rx()\n", dev->device_fh);
-
- if (count == 0)
- return 0;
-
- vq = dev->virtqueue[VIRTIO_RXQ];
- count = (count > MAX_PKT_BURST) ? MAX_PKT_BURST : count;
-
- res_cur_idx = vq->last_used_idx;
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") Current Index %d| End Index %d\n",
- dev->device_fh, res_cur_idx, res_cur_idx + count);
-
- /* Retrieve all of the head indexes first to avoid caching issues. */
- for (head_idx = 0; head_idx < count; head_idx++)
- head[head_idx] = MBUF_HEADROOM_UINT32(pkts[head_idx]);
-
- /*Prefetch descriptor index. */
- rte_prefetch0(&vq->desc[head[packet_success]]);
-
- while (packet_success != count) {
- /* Get descriptor from available ring */
- desc = &vq->desc[head[packet_success]];
-
- buff = pkts[packet_success];
- LOG_DEBUG(VHOST_DATA,
- "(%"PRIu64") in dev_rx_zcp: update the used idx for "
- "pkt[%d] descriptor idx: %d\n",
- dev->device_fh, packet_success,
- MBUF_HEADROOM_UINT32(buff));
-
- PRINT_PACKET(dev,
- (uintptr_t)(((uint64_t)(uintptr_t)buff->buf_addr)
- + RTE_PKTMBUF_HEADROOM),
- rte_pktmbuf_data_len(buff), 0);
-
- /* Buffer address translation for virtio header. */
- buff_hdr_addr = gpa_to_vva(dev, desc->addr);
- packet_len = rte_pktmbuf_data_len(buff) + vq->vhost_hlen;
-
- /*
- * If the descriptors are chained the header and data are
- * placed in separate buffers.
- */
- if (desc->flags & VRING_DESC_F_NEXT) {
- desc->len = vq->vhost_hlen;
- desc = &vq->desc[desc->next];
- desc->len = rte_pktmbuf_data_len(buff);
- } else {
- desc->len = packet_len;
- }
-
- /* Update used ring with desc information */
- vq->used->ring[res_cur_idx & (vq->size - 1)].id
- = head[packet_success];
- vq->used->ring[res_cur_idx & (vq->size - 1)].len
- = packet_len;
- res_cur_idx++;
- packet_success++;
-
- /* A header is required per buffer. */
- rte_memcpy((void *)(uintptr_t)buff_hdr_addr,
- (const void *)&virtio_hdr, vq->vhost_hlen);
-
- PRINT_PACKET(dev, (uintptr_t)buff_hdr_addr, vq->vhost_hlen, 1);
-
- if (likely(packet_success < count)) {
- /* Prefetch descriptor index. */
- rte_prefetch0(&vq->desc[head[packet_success]]);
- }
- }
-
- rte_compiler_barrier();
-
- LOG_DEBUG(VHOST_DATA,
- "(%"PRIu64") in dev_rx_zcp: before update used idx: "
- "vq.last_used_idx: %d, vq->used->idx: %d\n",
- dev->device_fh, vq->last_used_idx, vq->used->idx);
-
- *(volatile uint16_t *)&vq->used->idx += count;
- vq->last_used_idx += count;
-
- LOG_DEBUG(VHOST_DATA,
- "(%"PRIu64") in dev_rx_zcp: after update used idx: "
- "vq.last_used_idx: %d, vq->used->idx: %d\n",
- dev->device_fh, vq->last_used_idx, vq->used->idx);
-
- /* Kick the guest if necessary. */
- if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT))
- eventfd_write((int)vq->kickfd, 1);
-
- return count;
-}
-
-/*
- * This function routes the TX packet to the correct interface.
- * This may be a local device or the physical port.
- */
-static inline void __attribute__((always_inline))
-virtio_tx_route_zcp(struct virtio_net *dev, struct rte_mbuf *m,
- uint32_t desc_idx, uint8_t need_copy)
-{
- struct mbuf_table *tx_q;
- struct rte_mbuf **m_table;
- struct rte_mbuf *mbuf = NULL;
- unsigned len, ret, offset = 0;
- struct vpool *vpool;
- struct virtio_net_data_ll *dev_ll = ll_root_used;
- struct ether_hdr *pkt_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);
- uint16_t vlan_tag = (uint16_t)vlan_tags[(uint16_t)dev->device_fh];
-
- /*Add packet to the port tx queue*/
- tx_q = &tx_queue_zcp[(uint16_t)dev->vmdq_rx_q];
- len = tx_q->len;
-
- /* Allocate an mbuf and populate the structure. */
- vpool = &vpool_array[MAX_QUEUES + (uint16_t)dev->vmdq_rx_q];
- rte_ring_sc_dequeue(vpool->ring, (void **)&mbuf);
- if (unlikely(mbuf == NULL)) {
- struct vhost_virtqueue *vq = dev->virtqueue[VIRTIO_TXQ];
- RTE_LOG(ERR, VHOST_DATA,
- "(%"PRIu64") Failed to allocate memory for mbuf.\n",
- dev->device_fh);
- put_desc_to_used_list_zcp(vq, desc_idx);
- return;
- }
-
- if (vm2vm_mode == VM2VM_HARDWARE) {
- /* Avoid using a vlan tag from any vm for external pkt, such as
- * vlan_tags[dev->device_fh], oterwise, it conflicts when pool
- * selection, MAC address determines it as an external pkt
- * which should go to network, while vlan tag determine it as
- * a vm2vm pkt should forward to another vm. Hardware confuse
- * such a ambiguous situation, so pkt will lost.
- */
- vlan_tag = external_pkt_default_vlan_tag;
- while (dev_ll != NULL) {
- if (likely(dev_ll->dev->ready == DEVICE_RX) &&
- ether_addr_cmp(&(pkt_hdr->d_addr),
- &dev_ll->dev->mac_address)) {
-
- /*
- * Drop the packet if the TX packet is destined
- * for the TX device.
- */
- if (unlikely(dev_ll->dev->device_fh
- == dev->device_fh)) {
- LOG_DEBUG(VHOST_DATA,
- "(%"PRIu64") TX: Source and destination"
- "MAC addresses are the same. Dropping "
- "packet.\n",
- dev_ll->dev->device_fh);
- MBUF_HEADROOM_UINT32(mbuf)
- = (uint32_t)desc_idx;
- __rte_mbuf_raw_free(mbuf);
- return;
- }
-
- /*
- * Packet length offset 4 bytes for HW vlan
- * strip when L2 switch back.
- */
- offset = 4;
- vlan_tag =
- (uint16_t)
- vlan_tags[(uint16_t)dev_ll->dev->device_fh];
-
- LOG_DEBUG(VHOST_DATA,
- "(%"PRIu64") TX: pkt to local VM device id:"
- "(%"PRIu64") vlan tag: %d.\n",
- dev->device_fh, dev_ll->dev->device_fh,
- vlan_tag);
-
- break;
- }
- dev_ll = dev_ll->next;
- }
- }
-
- mbuf->nb_segs = m->nb_segs;
- mbuf->next = m->next;
- mbuf->data_len = m->data_len + offset;
- mbuf->pkt_len = mbuf->data_len;
- if (unlikely(need_copy)) {
- /* Copy the packet contents to the mbuf. */
- rte_memcpy(rte_pktmbuf_mtod(mbuf, void *),
- rte_pktmbuf_mtod(m, void *),
- m->data_len);
- } else {
- mbuf->data_off = m->data_off;
- mbuf->buf_physaddr = m->buf_physaddr;
- mbuf->buf_addr = m->buf_addr;
- }
- mbuf->ol_flags = PKT_TX_VLAN_PKT;
- mbuf->vlan_tci = vlan_tag;
- mbuf->l2_len = sizeof(struct ether_hdr);
- mbuf->l3_len = sizeof(struct ipv4_hdr);
- MBUF_HEADROOM_UINT32(mbuf) = (uint32_t)desc_idx;
-
- tx_q->m_table[len] = mbuf;
- len++;
-
- LOG_DEBUG(VHOST_DATA,
- "(%"PRIu64") in tx_route_zcp: pkt: nb_seg: %d, next:%s\n",
- dev->device_fh,
- mbuf->nb_segs,
- (mbuf->next == NULL) ? "null" : "non-null");
-
- if (enable_stats) {
- dev_statistics[dev->device_fh].tx_total++;
- dev_statistics[dev->device_fh].tx++;
- }
-
- if (unlikely(len == MAX_PKT_BURST)) {
- m_table = (struct rte_mbuf **)tx_q->m_table;
- ret = rte_eth_tx_burst(ports[0],
- (uint16_t)tx_q->txq_id, m_table, (uint16_t) len);
-
- /*
- * Free any buffers not handled by TX and update
- * the port stats.
- */
- if (unlikely(ret < len)) {
- do {
- rte_pktmbuf_free(m_table[ret]);
- } while (++ret < len);
- }
-
- len = 0;
- txmbuf_clean_zcp(dev, vpool);
- }
-
- tx_q->len = len;
-
- return;
-}
-
-/*
- * This function TX all available packets in virtio TX queue for one
- * virtio-net device. If it is first packet, it learns MAC address and
- * setup VMDQ.
- */
-static inline void __attribute__((always_inline))
-virtio_dev_tx_zcp(struct virtio_net *dev)
-{
- struct rte_mbuf m;
- struct vhost_virtqueue *vq;
- struct vring_desc *desc;
- uint64_t buff_addr = 0, phys_addr;
- uint32_t head[MAX_PKT_BURST];
- uint32_t i;
- uint16_t free_entries, packet_success = 0;
- uint16_t avail_idx;
- uint8_t need_copy = 0;
- hpa_type addr_type;
-
- vq = dev->virtqueue[VIRTIO_TXQ];
- avail_idx = *((volatile uint16_t *)&vq->avail->idx);
-
- /* If there are no available buffers then return. */
- if (vq->last_used_idx_res == avail_idx)
- return;
-
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") virtio_dev_tx()\n", dev->device_fh);
-
- /* Prefetch available ring to retrieve head indexes. */
- rte_prefetch0(&vq->avail->ring[vq->last_used_idx_res & (vq->size - 1)]);
-
- /* Get the number of free entries in the ring */
- free_entries = (avail_idx - vq->last_used_idx_res);
-
- /* Limit to MAX_PKT_BURST. */
- free_entries
- = (free_entries > MAX_PKT_BURST) ? MAX_PKT_BURST : free_entries;
-
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") Buffers available %d\n",
- dev->device_fh, free_entries);
-
- /* Retrieve all of the head indexes first to avoid caching issues. */
- for (i = 0; i < free_entries; i++)
- head[i]
- = vq->avail->ring[(vq->last_used_idx_res + i)
- & (vq->size - 1)];
-
- vq->last_used_idx_res += free_entries;
-
- /* Prefetch descriptor index. */
- rte_prefetch0(&vq->desc[head[packet_success]]);
- rte_prefetch0(&vq->used->ring[vq->last_used_idx & (vq->size - 1)]);
-
- while (packet_success < free_entries) {
- desc = &vq->desc[head[packet_success]];
-
- /* Discard first buffer as it is the virtio header */
- desc = &vq->desc[desc->next];
-
- /* Buffer address translation. */
- buff_addr = gpa_to_vva(dev, desc->addr);
- phys_addr = gpa_to_hpa(dev, desc->addr, desc->len, &addr_type);
-
- if (likely(packet_success < (free_entries - 1)))
- /* Prefetch descriptor index. */
- rte_prefetch0(&vq->desc[head[packet_success + 1]]);
-
- if (unlikely(addr_type == PHYS_ADDR_INVALID)) {
- RTE_LOG(ERR, VHOST_DATA,
- "(%"PRIu64") Invalid frame buffer address found"
- "when TX packets!\n",
- dev->device_fh);
- packet_success++;
- continue;
- }
-
- /* Prefetch buffer address. */
- rte_prefetch0((void *)(uintptr_t)buff_addr);
-
- /*
- * Setup dummy mbuf. This is copied to a real mbuf if
- * transmitted out the physical port.
- */
- m.data_len = desc->len;
- m.nb_segs = 1;
- m.next = NULL;
- m.data_off = 0;
- m.buf_addr = (void *)(uintptr_t)buff_addr;
- m.buf_physaddr = phys_addr;
-
- /*
- * Check if the frame buffer address from guest crosses
- * sub-region or not.
- */
- if (unlikely(addr_type == PHYS_ADDR_CROSS_SUBREG)) {
- RTE_LOG(ERR, VHOST_DATA,
- "(%"PRIu64") Frame buffer address cross "
- "sub-regioin found when attaching TX frame "
- "buffer address!\n",
- dev->device_fh);
- need_copy = 1;
- } else
- need_copy = 0;
-
- PRINT_PACKET(dev, (uintptr_t)buff_addr, desc->len, 0);
-
- /*
- * If this is the first received packet we need to learn
- * the MAC and setup VMDQ
- */
- if (unlikely(dev->ready == DEVICE_MAC_LEARNING)) {
- if (dev->remove || (link_vmdq(dev, &m) == -1)) {
- /*
- * Discard frame if device is scheduled for
- * removal or a duplicate MAC address is found.
- */
- packet_success += free_entries;
- vq->last_used_idx += packet_success;
- break;
- }
- }
-
- virtio_tx_route_zcp(dev, &m, head[packet_success], need_copy);
- packet_success++;
- }
-}
-
-/*
- * This function is called by each data core. It handles all RX/TX registered
- * with the core. For TX the specific lcore linked list is used. For RX, MAC
- * addresses are compared with all devices in the main linked list.
- */
-static int
-switch_worker_zcp(__attribute__((unused)) void *arg)
-{
- struct virtio_net *dev = NULL;
- struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
- struct virtio_net_data_ll *dev_ll;
- struct mbuf_table *tx_q;
- volatile struct lcore_ll_info *lcore_ll;
- const uint64_t drain_tsc
- = (rte_get_tsc_hz() + US_PER_S - 1) / US_PER_S
- * BURST_TX_DRAIN_US;
- uint64_t prev_tsc, diff_tsc, cur_tsc, ret_count = 0;
- unsigned ret;
- const uint16_t lcore_id = rte_lcore_id();
- uint16_t count_in_ring, rx_count = 0;
-
- RTE_LOG(INFO, VHOST_DATA, "Procesing on Core %u started\n", lcore_id);
-
- lcore_ll = lcore_info[lcore_id].lcore_ll;
- prev_tsc = 0;
-
- while (1) {
- cur_tsc = rte_rdtsc();
-
- /* TX burst queue drain */
- diff_tsc = cur_tsc - prev_tsc;
- if (unlikely(diff_tsc > drain_tsc)) {
- /*
- * Get mbuf from vpool.pool and detach mbuf and
- * put back into vpool.ring.
- */
- dev_ll = lcore_ll->ll_root_used;
- while ((dev_ll != NULL) && (dev_ll->dev != NULL)) {
- /* Get virtio device ID */
- dev = dev_ll->dev;
-
- if (likely(!dev->remove)) {
- tx_q = &tx_queue_zcp[(uint16_t)dev->vmdq_rx_q];
- if (tx_q->len) {
- LOG_DEBUG(VHOST_DATA,
- "TX queue drained after timeout"
- " with burst size %u\n",
- tx_q->len);
-
- /*
- * Tx any packets in the queue
- */
- ret = rte_eth_tx_burst(
- ports[0],
- (uint16_t)tx_q->txq_id,
- (struct rte_mbuf **)
- tx_q->m_table,
- (uint16_t)tx_q->len);
- if (unlikely(ret < tx_q->len)) {
- do {
- rte_pktmbuf_free(
- tx_q->m_table[ret]);
- } while (++ret < tx_q->len);
- }
- tx_q->len = 0;
-
- txmbuf_clean_zcp(dev,
- &vpool_array[MAX_QUEUES+dev->vmdq_rx_q]);
- }
- }
- dev_ll = dev_ll->next;
- }
- prev_tsc = cur_tsc;
- }
-
- rte_prefetch0(lcore_ll->ll_root_used);
-
- /*
- * Inform the configuration core that we have exited the linked
- * list and that no devices are in use if requested.
- */
- if (lcore_ll->dev_removal_flag == REQUEST_DEV_REMOVAL)
- lcore_ll->dev_removal_flag = ACK_DEV_REMOVAL;
-
- /* Process devices */
- dev_ll = lcore_ll->ll_root_used;
-
- while ((dev_ll != NULL) && (dev_ll->dev != NULL)) {
- dev = dev_ll->dev;
- if (unlikely(dev->remove)) {
- dev_ll = dev_ll->next;
- unlink_vmdq(dev);
- dev->ready = DEVICE_SAFE_REMOVE;
- continue;
- }
-
- if (likely(dev->ready == DEVICE_RX)) {
- uint32_t index = dev->vmdq_rx_q;
- uint16_t i;
- count_in_ring
- = rte_ring_count(vpool_array[index].ring);
- uint16_t free_entries
- = (uint16_t)get_available_ring_num_zcp(dev);
-
- /*
- * Attach all mbufs in vpool.ring and put back
- * into vpool.pool.
- */
- for (i = 0;
- i < RTE_MIN(free_entries,
- RTE_MIN(count_in_ring, MAX_PKT_BURST));
- i++)
- attach_rxmbuf_zcp(dev);
-
- /* Handle guest RX */
- rx_count = rte_eth_rx_burst(ports[0],
- (uint16_t)dev->vmdq_rx_q, pkts_burst,
- MAX_PKT_BURST);
-
- if (rx_count) {
- ret_count = virtio_dev_rx_zcp(dev,
- pkts_burst, rx_count);
- if (enable_stats) {
- dev_statistics[dev->device_fh].rx_total
- += rx_count;
- dev_statistics[dev->device_fh].rx
- += ret_count;
- }
- while (likely(rx_count)) {
- rx_count--;
- pktmbuf_detach_zcp(
- pkts_burst[rx_count]);
- rte_ring_sp_enqueue(
- vpool_array[index].ring,
- (void *)pkts_burst[rx_count]);
- }
- }
- }
-
- if (likely(!dev->remove))
- /* Handle guest TX */
- virtio_dev_tx_zcp(dev);
-
- /* Move to the next device in the list */
- dev_ll = dev_ll->next;
- }
- }
-
- return 0;
-}
-
-
-/*
- * Add an entry to a used linked list. A free entry must first be found
- * in the free linked list using get_data_ll_free_entry();
- */
-static void
-add_data_ll_entry(struct virtio_net_data_ll **ll_root_addr,
- struct virtio_net_data_ll *ll_dev)
-{
- struct virtio_net_data_ll *ll = *ll_root_addr;
-
- /* Set next as NULL and use a compiler barrier to avoid reordering. */
- ll_dev->next = NULL;
- rte_compiler_barrier();
-
- /* If ll == NULL then this is the first device. */
- if (ll) {
- /* Increment to the tail of the linked list. */
- while ((ll->next != NULL) )
- ll = ll->next;
-
- ll->next = ll_dev;
- } else {
- *ll_root_addr = ll_dev;
- }
-}
-
-/*
- * Remove an entry from a used linked list. The entry must then be added to
- * the free linked list using put_data_ll_free_entry().
- */
-static void
-rm_data_ll_entry(struct virtio_net_data_ll **ll_root_addr,
- struct virtio_net_data_ll *ll_dev,
- struct virtio_net_data_ll *ll_dev_last)
-{
- struct virtio_net_data_ll *ll = *ll_root_addr;
-
- if (unlikely((ll == NULL) || (ll_dev == NULL)))
- return;
-
- if (ll_dev == ll)
- *ll_root_addr = ll_dev->next;
- else
- if (likely(ll_dev_last != NULL))
- ll_dev_last->next = ll_dev->next;
- else
- RTE_LOG(ERR, VHOST_CONFIG, "Remove entry form ll failed.\n");
-}
-
-/*
- * Find and return an entry from the free linked list.
- */
-static struct virtio_net_data_ll *
-get_data_ll_free_entry(struct virtio_net_data_ll **ll_root_addr)
-{
- struct virtio_net_data_ll *ll_free = *ll_root_addr;
- struct virtio_net_data_ll *ll_dev;
-
- if (ll_free == NULL)
- return NULL;
-
- ll_dev = ll_free;
- *ll_root_addr = ll_free->next;
-
- return ll_dev;
-}
-
-/*
- * Place an entry back on to the free linked list.
- */
-static void
-put_data_ll_free_entry(struct virtio_net_data_ll **ll_root_addr,
- struct virtio_net_data_ll *ll_dev)
-{
- struct virtio_net_data_ll *ll_free = *ll_root_addr;
-
- if (ll_dev == NULL)
- return;
-
- ll_dev->next = ll_free;
- *ll_root_addr = ll_dev;
-}
-
-/*
- * Creates a linked list of a given size.
- */
-static struct virtio_net_data_ll *
-alloc_data_ll(uint32_t size)
-{
- struct virtio_net_data_ll *ll_new;
- uint32_t i;
-
- /* Malloc and then chain the linked list. */
- ll_new = malloc(size * sizeof(struct virtio_net_data_ll));
- if (ll_new == NULL) {
- RTE_LOG(ERR, VHOST_CONFIG, "Failed to allocate memory for ll_new.\n");
- return NULL;
- }
-
- for (i = 0; i < size - 1; i++) {
- ll_new[i].dev = NULL;
- ll_new[i].next = &ll_new[i+1];
- }
- ll_new[i].next = NULL;
-
- return (ll_new);
-}
-
-/*
- * Create the main linked list along with each individual cores linked list. A used and a free list
- * are created to manage entries.
- */
-static int
-init_data_ll (void)
-{
- int lcore;
-
- RTE_LCORE_FOREACH_SLAVE(lcore) {
- lcore_info[lcore].lcore_ll = malloc(sizeof(struct lcore_ll_info));
- if (lcore_info[lcore].lcore_ll == NULL) {
- RTE_LOG(ERR, VHOST_CONFIG, "Failed to allocate memory for lcore_ll.\n");
- return -1;
- }
-
- lcore_info[lcore].lcore_ll->device_num = 0;
- lcore_info[lcore].lcore_ll->dev_removal_flag = ACK_DEV_REMOVAL;
- lcore_info[lcore].lcore_ll->ll_root_used = NULL;
- if (num_devices % num_switching_cores)
- lcore_info[lcore].lcore_ll->ll_root_free = alloc_data_ll((num_devices / num_switching_cores) + 1);
- else
- lcore_info[lcore].lcore_ll->ll_root_free = alloc_data_ll(num_devices / num_switching_cores);
- }
-
- /* Allocate devices up to a maximum of MAX_DEVICES. */
- ll_root_free = alloc_data_ll(MIN((num_devices), MAX_DEVICES));
-
- return 0;
-}
-
-/*
- * Set virtqueue flags so that we do not receive interrupts.
- */
-static void
-set_irq_status (struct virtio_net *dev)
-{
- dev->virtqueue[VIRTIO_RXQ]->used->flags = VRING_USED_F_NO_NOTIFY;
- dev->virtqueue[VIRTIO_TXQ]->used->flags = VRING_USED_F_NO_NOTIFY;
-}
-
-/*
- * Remove a device from the specific data core linked list and from the main linked list. Synchonization
- * occurs through the use of the lcore dev_removal_flag. Device is made volatile here to avoid re-ordering
- * of dev->remove=1 which can cause an infinite loop in the rte_pause loop.
- */
-static void
-destroy_device (volatile struct virtio_net *dev)
-{
- struct virtio_net_data_ll *ll_lcore_dev_cur;
- struct virtio_net_data_ll *ll_main_dev_cur;
- struct virtio_net_data_ll *ll_lcore_dev_last = NULL;
- struct virtio_net_data_ll *ll_main_dev_last = NULL;
- int lcore;
-
- dev->flags &= ~VIRTIO_DEV_RUNNING;
-
- /*set the remove flag. */
- dev->remove = 1;
-
- while(dev->ready != DEVICE_SAFE_REMOVE) {
- rte_pause();
- }
-
- /* Search for entry to be removed from lcore ll */
- ll_lcore_dev_cur = lcore_info[dev->coreid].lcore_ll->ll_root_used;
- while (ll_lcore_dev_cur != NULL) {
- if (ll_lcore_dev_cur->dev == dev) {
- break;
- } else {
- ll_lcore_dev_last = ll_lcore_dev_cur;
- ll_lcore_dev_cur = ll_lcore_dev_cur->next;
- }
- }
-
- if (ll_lcore_dev_cur == NULL) {
- RTE_LOG(ERR, VHOST_CONFIG,
- "(%"PRIu64") Failed to find the dev to be destroy.\n",
- dev->device_fh);
- return;
- }
-
- /* Search for entry to be removed from main ll */
- ll_main_dev_cur = ll_root_used;
- ll_main_dev_last = NULL;
- while (ll_main_dev_cur != NULL) {
- if (ll_main_dev_cur->dev == dev) {
- break;
- } else {
- ll_main_dev_last = ll_main_dev_cur;
- ll_main_dev_cur = ll_main_dev_cur->next;
- }
- }
-
- /* Remove entries from the lcore and main ll. */
- rm_data_ll_entry(&lcore_info[ll_lcore_dev_cur->dev->coreid].lcore_ll->ll_root_used, ll_lcore_dev_cur, ll_lcore_dev_last);
- rm_data_ll_entry(&ll_root_used, ll_main_dev_cur, ll_main_dev_last);
-
- /* Set the dev_removal_flag on each lcore. */
- RTE_LCORE_FOREACH_SLAVE(lcore) {
- lcore_info[lcore].lcore_ll->dev_removal_flag = REQUEST_DEV_REMOVAL;
- }
-
- /*
- * Once each core has set the dev_removal_flag to ACK_DEV_REMOVAL we can be sure that
- * they can no longer access the device removed from the linked lists and that the devices
- * are no longer in use.
- */
- RTE_LCORE_FOREACH_SLAVE(lcore) {
- while (lcore_info[lcore].lcore_ll->dev_removal_flag != ACK_DEV_REMOVAL) {
- rte_pause();
- }
- }
-
- /* Add the entries back to the lcore and main free ll.*/
- put_data_ll_free_entry(&lcore_info[ll_lcore_dev_cur->dev->coreid].lcore_ll->ll_root_free, ll_lcore_dev_cur);
- put_data_ll_free_entry(&ll_root_free, ll_main_dev_cur);
-
- /* Decrement number of device on the lcore. */
- lcore_info[ll_lcore_dev_cur->dev->coreid].lcore_ll->device_num--;
-
- RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") Device has been removed from data core\n", dev->device_fh);
-
- if (zero_copy) {
- struct vpool *vpool = &vpool_array[dev->vmdq_rx_q];
-
- /* Stop the RX queue. */
- if (rte_eth_dev_rx_queue_stop(ports[0], dev->vmdq_rx_q) != 0) {
- LOG_DEBUG(VHOST_CONFIG,
- "(%"PRIu64") In destroy_device: Failed to stop "
- "rx queue:%d\n",
- dev->device_fh,
- dev->vmdq_rx_q);
- }
-
- LOG_DEBUG(VHOST_CONFIG,
- "(%"PRIu64") in destroy_device: Start put mbuf in "
- "mempool back to ring for RX queue: %d\n",
- dev->device_fh, dev->vmdq_rx_q);
-
- mbuf_destroy_zcp(vpool);
-
- /* Stop the TX queue. */
- if (rte_eth_dev_tx_queue_stop(ports[0], dev->vmdq_rx_q) != 0) {
- LOG_DEBUG(VHOST_CONFIG,
- "(%"PRIu64") In destroy_device: Failed to "
- "stop tx queue:%d\n",
- dev->device_fh, dev->vmdq_rx_q);
- }
-
- vpool = &vpool_array[dev->vmdq_rx_q + MAX_QUEUES];
-
- LOG_DEBUG(VHOST_CONFIG,
- "(%"PRIu64") destroy_device: Start put mbuf in mempool "
- "back to ring for TX queue: %d, dev:(%"PRIu64")\n",
- dev->device_fh, (dev->vmdq_rx_q + MAX_QUEUES),
- dev->device_fh);
-
- mbuf_destroy_zcp(vpool);
- }
-
-}
-
-/*
- * A new device is added to a data core. First the device is added to the main linked list
- * and the allocated to a specific data core.
- */
-static int
-new_device (struct virtio_net *dev)
-{
- struct virtio_net_data_ll *ll_dev;
- int lcore, core_add = 0;
- uint32_t device_num_min = num_devices;
-
- /* Add device to main ll */
- ll_dev = get_data_ll_free_entry(&ll_root_free);
- if (ll_dev == NULL) {
- RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") No free entry found in linked list. Device limit "
- "of %d devices per core has been reached\n",
- dev->device_fh, num_devices);
- return -1;
- }
- ll_dev->dev = dev;
- add_data_ll_entry(&ll_root_used, ll_dev);
- ll_dev->dev->vmdq_rx_q
- = ll_dev->dev->device_fh * (num_queues / num_devices);
-
- if (zero_copy) {
- uint32_t index = ll_dev->dev->vmdq_rx_q;
- uint32_t count_in_ring, i;
- struct mbuf_table *tx_q;
-
- count_in_ring = rte_ring_count(vpool_array[index].ring);
-
- LOG_DEBUG(VHOST_CONFIG,
- "(%"PRIu64") in new_device: mbuf count in mempool "
- "before attach is: %d\n",
- dev->device_fh,
- rte_mempool_count(vpool_array[index].pool));
- LOG_DEBUG(VHOST_CONFIG,
- "(%"PRIu64") in new_device: mbuf count in ring "
- "before attach is : %d\n",
- dev->device_fh, count_in_ring);
-
- /*
- * Attach all mbufs in vpool.ring and put back intovpool.pool.
- */
- for (i = 0; i < count_in_ring; i++)
- attach_rxmbuf_zcp(dev);
-
- LOG_DEBUG(VHOST_CONFIG, "(%"PRIu64") in new_device: mbuf count in "
- "mempool after attach is: %d\n",
- dev->device_fh,
- rte_mempool_count(vpool_array[index].pool));
- LOG_DEBUG(VHOST_CONFIG, "(%"PRIu64") in new_device: mbuf count in "
- "ring after attach is : %d\n",
- dev->device_fh,
- rte_ring_count(vpool_array[index].ring));
-
- tx_q = &tx_queue_zcp[(uint16_t)dev->vmdq_rx_q];
- tx_q->txq_id = dev->vmdq_rx_q;
-
- if (rte_eth_dev_tx_queue_start(ports[0], dev->vmdq_rx_q) != 0) {
- struct vpool *vpool = &vpool_array[dev->vmdq_rx_q];
-
- LOG_DEBUG(VHOST_CONFIG,
- "(%"PRIu64") In new_device: Failed to start "
- "tx queue:%d\n",
- dev->device_fh, dev->vmdq_rx_q);
-
- mbuf_destroy_zcp(vpool);
- return -1;
- }
-
- if (rte_eth_dev_rx_queue_start(ports[0], dev->vmdq_rx_q) != 0) {
- struct vpool *vpool = &vpool_array[dev->vmdq_rx_q];
-
- LOG_DEBUG(VHOST_CONFIG,
- "(%"PRIu64") In new_device: Failed to start "
- "rx queue:%d\n",
- dev->device_fh, dev->vmdq_rx_q);
-
- /* Stop the TX queue. */
- if (rte_eth_dev_tx_queue_stop(ports[0],
- dev->vmdq_rx_q) != 0) {
- LOG_DEBUG(VHOST_CONFIG,
- "(%"PRIu64") In new_device: Failed to "
- "stop tx queue:%d\n",
- dev->device_fh, dev->vmdq_rx_q);
- }
-
- mbuf_destroy_zcp(vpool);
- return -1;
- }
-
- }
-
- /*reset ready flag*/
- dev->ready = DEVICE_MAC_LEARNING;
- dev->remove = 0;
-
- /* Find a suitable lcore to add the device. */
- RTE_LCORE_FOREACH_SLAVE(lcore) {
- if (lcore_info[lcore].lcore_ll->device_num < device_num_min) {
- device_num_min = lcore_info[lcore].lcore_ll->device_num;
- core_add = lcore;
- }
- }
- /* Add device to lcore ll */
- ll_dev->dev->coreid = core_add;
- ll_dev = get_data_ll_free_entry(&lcore_info[ll_dev->dev->coreid].lcore_ll->ll_root_free);
- if (ll_dev == NULL) {
- RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") Failed to add device to data core\n", dev->device_fh);
- dev->ready = DEVICE_SAFE_REMOVE;
- destroy_device(dev);
- return -1;
- }
- ll_dev->dev = dev;
- add_data_ll_entry(&lcore_info[ll_dev->dev->coreid].lcore_ll->ll_root_used, ll_dev);
-
- /* Initialize device stats */
- memset(&dev_statistics[dev->device_fh], 0, sizeof(struct device_statistics));
-
- /* Disable notifications. */
- set_irq_status(dev);
- lcore_info[ll_dev->dev->coreid].lcore_ll->device_num++;
- dev->flags |= VIRTIO_DEV_RUNNING;
-
- RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") Device has been added to data core %d\n", dev->device_fh, dev->coreid);
-
- return 0;
-}
-
-/*
- * These callback allow devices to be added to the data core when configuration
- * has been fully complete.
- */
-static const struct virtio_net_device_ops virtio_net_device_ops =
-{
- .new_device = new_device,
- .destroy_device = destroy_device,
-};
-
-/*
- * This is a thread will wake up after a period to print stats if the user has
- * enabled them.
- */
-static void
-print_stats(void)
-{
- struct virtio_net_data_ll *dev_ll;
- uint64_t tx_dropped, rx_dropped;
- uint64_t tx, tx_total, rx, rx_total;
- uint32_t device_fh;
- const char clr[] = { 27, '[', '2', 'J', '\0' };
- const char top_left[] = { 27, '[', '1', ';', '1', 'H','\0' };
-
- while(1) {
- sleep(enable_stats);
-
- /* Clear screen and move to top left */
- printf("%s%s", clr, top_left);
-
- printf("\nDevice statistics ====================================");
-
- dev_ll = ll_root_used;
- while (dev_ll != NULL) {
- device_fh = (uint32_t)dev_ll->dev->device_fh;
- tx_total = dev_statistics[device_fh].tx_total;
- tx = dev_statistics[device_fh].tx;
- tx_dropped = tx_total - tx;
- if (zero_copy == 0) {
- rx_total = rte_atomic64_read(
- &dev_statistics[device_fh].rx_total_atomic);
- rx = rte_atomic64_read(
- &dev_statistics[device_fh].rx_atomic);
- } else {
- rx_total = dev_statistics[device_fh].rx_total;
- rx = dev_statistics[device_fh].rx;
- }
- rx_dropped = rx_total - rx;
-
- printf("\nStatistics for device %"PRIu32" ------------------------------"
- "\nTX total: %"PRIu64""
- "\nTX dropped: %"PRIu64""
- "\nTX successful: %"PRIu64""
- "\nRX total: %"PRIu64""
- "\nRX dropped: %"PRIu64""
- "\nRX successful: %"PRIu64"",
- device_fh,
- tx_total,
- tx_dropped,
- tx,
- rx_total,
- rx_dropped,
- rx);
-
- dev_ll = dev_ll->next;
- }
- printf("\n======================================================\n");
- }
-}
-
-static void
-setup_mempool_tbl(int socket, uint32_t index, char *pool_name,
- char *ring_name, uint32_t nb_mbuf)
-{
- uint16_t roomsize = VIRTIO_DESCRIPTOR_LEN_ZCP + RTE_PKTMBUF_HEADROOM;
- vpool_array[index].pool
- = rte_mempool_create(pool_name, nb_mbuf, MBUF_SIZE_ZCP,
- MBUF_CACHE_SIZE_ZCP, sizeof(struct rte_pktmbuf_pool_private),
- rte_pktmbuf_pool_init, (void *)(uintptr_t)roomsize,
- rte_pktmbuf_init, NULL, socket, 0);
- if (vpool_array[index].pool != NULL) {
- vpool_array[index].ring
- = rte_ring_create(ring_name,
- rte_align32pow2(nb_mbuf + 1),
- socket, RING_F_SP_ENQ | RING_F_SC_DEQ);
- if (likely(vpool_array[index].ring != NULL)) {
- LOG_DEBUG(VHOST_CONFIG,
- "in setup_mempool_tbl: mbuf count in "
- "mempool is: %d\n",
- rte_mempool_count(vpool_array[index].pool));
- LOG_DEBUG(VHOST_CONFIG,
- "in setup_mempool_tbl: mbuf count in "
- "ring is: %d\n",
- rte_ring_count(vpool_array[index].ring));
- } else {
- rte_exit(EXIT_FAILURE, "ring_create(%s) failed",
- ring_name);
- }
-
- /* Need consider head room. */
- vpool_array[index].buf_size = roomsize - RTE_PKTMBUF_HEADROOM;
- } else {
- rte_exit(EXIT_FAILURE, "mempool_create(%s) failed", pool_name);
- }
-}
-
-
-/*
- * Main function, does initialisation and calls the per-lcore functions. The CUSE
- * device is also registered here to handle the IOCTLs.
- */
-int
-MAIN(int argc, char *argv[])
-{
- struct rte_mempool *mbuf_pool = NULL;
- unsigned lcore_id, core_id = 0;
- unsigned nb_ports, valid_num_ports;
- int ret;
- uint8_t portid, queue_id = 0;
- static pthread_t tid;
-
- /* init EAL */
- ret = rte_eal_init(argc, argv);
- if (ret < 0)
- rte_exit(EXIT_FAILURE, "Error with EAL initialization\n");
- argc -= ret;
- argv += ret;
-
- /* parse app arguments */
- ret = us_vhost_parse_args(argc, argv);
- if (ret < 0)
- rte_exit(EXIT_FAILURE, "Invalid argument\n");
-
- for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id ++)
- if (rte_lcore_is_enabled(lcore_id))
- lcore_ids[core_id ++] = lcore_id;
-
- if (rte_lcore_count() > RTE_MAX_LCORE)
- rte_exit(EXIT_FAILURE,"Not enough cores\n");
-
- /*set the number of swithcing cores available*/
- num_switching_cores = rte_lcore_count()-1;
-
- /* Get the number of physical ports. */
- nb_ports = rte_eth_dev_count();
- if (nb_ports > RTE_MAX_ETHPORTS)
- nb_ports = RTE_MAX_ETHPORTS;
-
- /*
- * Update the global var NUM_PORTS and global array PORTS
- * and get value of var VALID_NUM_PORTS according to system ports number
- */
- valid_num_ports = check_ports_num(nb_ports);
-
- if ((valid_num_ports == 0) || (valid_num_ports > MAX_SUP_PORTS)) {
- RTE_LOG(INFO, VHOST_PORT, "Current enabled port number is %u,"
- "but only %u port can be enabled\n",num_ports, MAX_SUP_PORTS);
- return -1;
- }
-
- if (zero_copy == 0) {
- /* Create the mbuf pool. */
- mbuf_pool = rte_mempool_create(
- "MBUF_POOL",
- NUM_MBUFS_PER_PORT
- * valid_num_ports,
- MBUF_SIZE, MBUF_CACHE_SIZE,
- sizeof(struct rte_pktmbuf_pool_private),
- rte_pktmbuf_pool_init, NULL,
- rte_pktmbuf_init, NULL,
- rte_socket_id(), 0);
- if (mbuf_pool == NULL)
- rte_exit(EXIT_FAILURE, "Cannot create mbuf pool\n");
-
- for (queue_id = 0; queue_id < MAX_QUEUES + 1; queue_id++)
- vpool_array[queue_id].pool = mbuf_pool;
-
- if (vm2vm_mode == VM2VM_HARDWARE) {
- /* Enable VT loop back to let L2 switch to do it. */
- vmdq_conf_default.rx_adv_conf.vmdq_rx_conf.enable_loop_back = 1;
- LOG_DEBUG(VHOST_CONFIG,
- "Enable loop back for L2 switch in vmdq.\n");
- }
- } else {
- uint32_t nb_mbuf;
- char pool_name[RTE_MEMPOOL_NAMESIZE];
- char ring_name[RTE_MEMPOOL_NAMESIZE];
-
- /*
- * Zero copy defers queue RX/TX start to the time when guest
- * finishes its startup and packet buffers from that guest are
- * available.
- */
- rx_conf_default.rx_deferred_start = (uint8_t)zero_copy;
- rx_conf_default.rx_drop_en = 0;
- tx_conf_default.tx_deferred_start = (uint8_t)zero_copy;
- nb_mbuf = num_rx_descriptor
- + num_switching_cores * MBUF_CACHE_SIZE_ZCP
- + num_switching_cores * MAX_PKT_BURST;
-
- for (queue_id = 0; queue_id < MAX_QUEUES; queue_id++) {
- snprintf(pool_name, sizeof(pool_name),
- "rxmbuf_pool_%u", queue_id);
- snprintf(ring_name, sizeof(ring_name),
- "rxmbuf_ring_%u", queue_id);
- setup_mempool_tbl(rte_socket_id(), queue_id,
- pool_name, ring_name, nb_mbuf);
- }
-
- nb_mbuf = num_tx_descriptor
- + num_switching_cores * MBUF_CACHE_SIZE_ZCP
- + num_switching_cores * MAX_PKT_BURST;
-
- for (queue_id = 0; queue_id < MAX_QUEUES; queue_id++) {
- snprintf(pool_name, sizeof(pool_name),
- "txmbuf_pool_%u", queue_id);
- snprintf(ring_name, sizeof(ring_name),
- "txmbuf_ring_%u", queue_id);
- setup_mempool_tbl(rte_socket_id(),
- (queue_id + MAX_QUEUES),
- pool_name, ring_name, nb_mbuf);
- }
-
- if (vm2vm_mode == VM2VM_HARDWARE) {
- /* Enable VT loop back to let L2 switch to do it. */
- vmdq_conf_default.rx_adv_conf.vmdq_rx_conf.enable_loop_back = 1;
- LOG_DEBUG(VHOST_CONFIG,
- "Enable loop back for L2 switch in vmdq.\n");
- }
- }
- /* Set log level. */
- rte_set_log_level(LOG_LEVEL);
-
- /* initialize all ports */
- for (portid = 0; portid < nb_ports; portid++) {
- /* skip ports that are not enabled */
- if ((enabled_port_mask & (1 << portid)) == 0) {
- RTE_LOG(INFO, VHOST_PORT,
- "Skipping disabled port %d\n", portid);
- continue;
- }
- if (port_init(portid) != 0)
- rte_exit(EXIT_FAILURE,
- "Cannot initialize network ports\n");
- }
-
- /* Initialise all linked lists. */
- if (init_data_ll() == -1)
- rte_exit(EXIT_FAILURE, "Failed to initialize linked list\n");
-
- /* Initialize device stats */
- memset(&dev_statistics, 0, sizeof(dev_statistics));
-
- /* Enable stats if the user option is set. */
- if (enable_stats)
- pthread_create(&tid, NULL, (void*)print_stats, NULL );
-
- /* Launch all data cores. */
- if (zero_copy == 0) {
- RTE_LCORE_FOREACH_SLAVE(lcore_id) {
- rte_eal_remote_launch(switch_worker,
- mbuf_pool, lcore_id);
- }
- } else {
- uint32_t count_in_mempool, index, i;
- for (index = 0; index < 2*MAX_QUEUES; index++) {
- /* For all RX and TX queues. */
- count_in_mempool
- = rte_mempool_count(vpool_array[index].pool);
-
- /*
- * Transfer all un-attached mbufs from vpool.pool
- * to vpoo.ring.
- */
- for (i = 0; i < count_in_mempool; i++) {
- struct rte_mbuf *mbuf
- = __rte_mbuf_raw_alloc(
- vpool_array[index].pool);
- rte_ring_sp_enqueue(vpool_array[index].ring,
- (void *)mbuf);
- }
-
- LOG_DEBUG(VHOST_CONFIG,
- "in MAIN: mbuf count in mempool at initial "
- "is: %d\n", count_in_mempool);
- LOG_DEBUG(VHOST_CONFIG,
- "in MAIN: mbuf count in ring at initial is :"
- " %d\n",
- rte_ring_count(vpool_array[index].ring));
- }
-
- RTE_LCORE_FOREACH_SLAVE(lcore_id)
- rte_eal_remote_launch(switch_worker_zcp, NULL,
- lcore_id);
- }
-
- /* Register CUSE device to handle IOCTLs. */
- ret = register_cuse_device((char*)&dev_basename, dev_index, get_virtio_net_callbacks());
- if (ret != 0)
- rte_exit(EXIT_FAILURE,"CUSE device setup failure.\n");
-
- init_virtio_net(&virtio_net_device_ops);
-
- /* Start CUSE session. */
- start_cuse_session_loop();
- return 0;
-
-}
-