- (*mac)[0], (*mac)[1], (*mac)[2],
- (*mac)[3], (*mac)[4], (*mac)[5]
- },
- .vlan_tag = ((vlan_index != -1u) ?
- htons(priv->vlan_filter[vlan_index].id) :
- 0),
- },
- .mask = {
- .dst_mac = "\xff\xff\xff\xff\xff\xff",
- .vlan_tag = ((vlan_index != -1u) ? htons(0xfff) : 0),
- }
- };
- DEBUG("%p: adding MAC address %02x:%02x:%02x:%02x:%02x:%02x index %u"
- " (VLAN %s %" PRIu16 ")",
- (void *)rxq,
- (*mac)[0], (*mac)[1], (*mac)[2], (*mac)[3], (*mac)[4], (*mac)[5],
- mac_index,
- ((vlan_index != -1u) ? "ID" : "index"),
- ((vlan_index != -1u) ? priv->vlan_filter[vlan_index].id : -1u));
- /* Create related flow. */
- errno = 0;
- flow = ibv_create_flow(rxq->qp, attr);
- if (flow == NULL) {
- /* It's not clear whether errno is always set in this case. */
- ERROR("%p: flow configuration failed, errno=%d: %s",
- (void *)rxq, errno,
- (errno ? strerror(errno) : "Unknown error"));
- if (errno)
- return errno;
- return EINVAL;
- }
- if (vlan_index == -1u)
- vlan_index = 0;
- assert(rxq->mac_flow[mac_index][vlan_index] == NULL);
- rxq->mac_flow[mac_index][vlan_index] = flow;
- return 0;
-}
-
-/**
- * Register a MAC address in a RX queue.
- *
- * @param rxq
- * Pointer to RX queue structure.
- * @param mac_index
- * MAC address index to register.
- *
- * @return
- * 0 on success, errno value on failure.
- */
-static int
-rxq_mac_addr_add(struct rxq *rxq, unsigned int mac_index)
-{
- struct priv *priv = rxq->priv;
- unsigned int i;
- unsigned int vlans = 0;
- int ret;
-
- assert(mac_index < elemof(priv->mac));
- if (BITFIELD_ISSET(rxq->mac_configured, mac_index))
- rxq_mac_addr_del(rxq, mac_index);
- /* Fill VLAN specifications. */
- for (i = 0; (i != elemof(priv->vlan_filter)); ++i) {
- if (!priv->vlan_filter[i].enabled)
- continue;
- /* Create related flow. */
- ret = rxq_add_flow(rxq, mac_index, i);
- if (!ret) {
- vlans++;
- continue;
- }
- /* Failure, rollback. */
- while (i != 0)
- if (priv->vlan_filter[--i].enabled)
- rxq_del_flow(rxq, mac_index, i);
- assert(ret > 0);
- return ret;
- }
- /* In case there is no VLAN filter. */
- if (!vlans) {
- ret = rxq_add_flow(rxq, mac_index, -1);
- if (ret)
- return ret;
- }
- BITFIELD_SET(rxq->mac_configured, mac_index);
- return 0;
-}
-
-/**
- * Register all MAC addresses in a RX queue.
- *
- * @param rxq
- * Pointer to RX queue structure.
- *
- * @return
- * 0 on success, errno value on failure.
- */
-static int
-rxq_mac_addrs_add(struct rxq *rxq)
-{
- struct priv *priv = rxq->priv;
- unsigned int i;
- int ret;
-
- for (i = 0; (i != elemof(priv->mac)); ++i) {
- if (!BITFIELD_ISSET(priv->mac_configured, i))
- continue;
- ret = rxq_mac_addr_add(rxq, i);
- if (!ret)
- continue;
- /* Failure, rollback. */
- while (i != 0)
- rxq_mac_addr_del(rxq, --i);
- assert(ret > 0);
- return ret;
- }
- return 0;
-}
-
-/**
- * Unregister a MAC address.
- *
- * In RSS mode, the MAC address is unregistered from the parent queue,
- * otherwise it is unregistered from each queue directly.
- *
- * @param priv
- * Pointer to private structure.
- * @param mac_index
- * MAC address index.
- */
-static void
-priv_mac_addr_del(struct priv *priv, unsigned int mac_index)
-{
- unsigned int i;
-
- assert(mac_index < elemof(priv->mac));
- if (!BITFIELD_ISSET(priv->mac_configured, mac_index))
- return;
- if (priv->rss) {
- rxq_mac_addr_del(&priv->rxq_parent, mac_index);
- goto end;
- }
- for (i = 0; (i != priv->dev->data->nb_rx_queues); ++i)
- rxq_mac_addr_del((*priv->rxqs)[i], mac_index);
-end:
- BITFIELD_RESET(priv->mac_configured, mac_index);
-}
-
-/**
- * Register a MAC address.
- *
- * In RSS mode, the MAC address is registered in the parent queue,
- * otherwise it is registered in each queue directly.
- *
- * @param priv
- * Pointer to private structure.
- * @param mac_index
- * MAC address index to use.
- * @param mac
- * MAC address to register.
- *
- * @return
- * 0 on success, errno value on failure.
- */
-static int
-priv_mac_addr_add(struct priv *priv, unsigned int mac_index,
- const uint8_t (*mac)[ETHER_ADDR_LEN])
-{
- unsigned int i;
- int ret;
-
- assert(mac_index < elemof(priv->mac));
- /* First, make sure this address isn't already configured. */
- for (i = 0; (i != elemof(priv->mac)); ++i) {
- /* Skip this index, it's going to be reconfigured. */
- if (i == mac_index)
- continue;
- if (!BITFIELD_ISSET(priv->mac_configured, i))
- continue;
- if (memcmp(priv->mac[i].addr_bytes, *mac, sizeof(*mac)))
- continue;
- /* Address already configured elsewhere, return with error. */
- return EADDRINUSE;
- }
- if (BITFIELD_ISSET(priv->mac_configured, mac_index))
- priv_mac_addr_del(priv, mac_index);
- priv->mac[mac_index] = (struct ether_addr){
- {
- (*mac)[0], (*mac)[1], (*mac)[2],
- (*mac)[3], (*mac)[4], (*mac)[5]
- }
- };
- /* If device isn't started, this is all we need to do. */
- if (!priv->started) {
-#ifndef NDEBUG
- /* Verify that all queues have this index disabled. */
- for (i = 0; (i != priv->rxqs_n); ++i) {
- if ((*priv->rxqs)[i] == NULL)
- continue;
- assert(!BITFIELD_ISSET
- ((*priv->rxqs)[i]->mac_configured, mac_index));
- }
-#endif
- goto end;
- }
- if (priv->rss) {
- ret = rxq_mac_addr_add(&priv->rxq_parent, mac_index);
- if (ret)
- return ret;
- goto end;
- }
- for (i = 0; (i != priv->rxqs_n); ++i) {
- if ((*priv->rxqs)[i] == NULL)
- continue;
- ret = rxq_mac_addr_add((*priv->rxqs)[i], mac_index);
- if (!ret)
- continue;
- /* Failure, rollback. */
- while (i != 0)
- if ((*priv->rxqs)[(--i)] != NULL)
- rxq_mac_addr_del((*priv->rxqs)[i], mac_index);
- return ret;
- }
-end:
- BITFIELD_SET(priv->mac_configured, mac_index);
- return 0;
-}
-
-/**
- * Enable allmulti mode in a RX queue.
- *
- * @param rxq
- * Pointer to RX queue structure.
- *
- * @return
- * 0 on success, errno value on failure.
- */
-static int
-rxq_allmulticast_enable(struct rxq *rxq)
-{
- struct ibv_flow *flow;
- struct ibv_flow_attr attr = {
- .type = IBV_FLOW_ATTR_MC_DEFAULT,
- .num_of_specs = 0,
- .port = rxq->priv->port,
- .flags = 0
- };
-
- DEBUG("%p: enabling allmulticast mode", (void *)rxq);
- if (rxq->allmulti_flow != NULL)
- return EBUSY;
- errno = 0;
- flow = ibv_create_flow(rxq->qp, &attr);
- if (flow == NULL) {
- /* It's not clear whether errno is always set in this case. */
- ERROR("%p: flow configuration failed, errno=%d: %s",
- (void *)rxq, errno,
- (errno ? strerror(errno) : "Unknown error"));
- if (errno)
- return errno;
- return EINVAL;
- }
- rxq->allmulti_flow = flow;
- DEBUG("%p: allmulticast mode enabled", (void *)rxq);
- return 0;
-}
-
-/**
- * Disable allmulti mode in a RX queue.
- *
- * @param rxq
- * Pointer to RX queue structure.
- */
-static void
-rxq_allmulticast_disable(struct rxq *rxq)
-{
- DEBUG("%p: disabling allmulticast mode", (void *)rxq);
- if (rxq->allmulti_flow == NULL)
- return;
- claim_zero(ibv_destroy_flow(rxq->allmulti_flow));
- rxq->allmulti_flow = NULL;
- DEBUG("%p: allmulticast mode disabled", (void *)rxq);
-}
-
-/**
- * Enable promiscuous mode in a RX queue.
- *
- * @param rxq
- * Pointer to RX queue structure.
- *
- * @return
- * 0 on success, errno value on failure.
- */
-static int
-rxq_promiscuous_enable(struct rxq *rxq)
-{
- struct ibv_flow *flow;
- struct ibv_flow_attr attr = {
- .type = IBV_FLOW_ATTR_ALL_DEFAULT,
- .num_of_specs = 0,
- .port = rxq->priv->port,
- .flags = 0
- };
-
- if (rxq->priv->vf)
- return 0;
- DEBUG("%p: enabling promiscuous mode", (void *)rxq);
- if (rxq->promisc_flow != NULL)
- return EBUSY;
- errno = 0;
- flow = ibv_create_flow(rxq->qp, &attr);
- if (flow == NULL) {
- /* It's not clear whether errno is always set in this case. */
- ERROR("%p: flow configuration failed, errno=%d: %s",
- (void *)rxq, errno,
- (errno ? strerror(errno) : "Unknown error"));
- if (errno)
- return errno;
- return EINVAL;
- }
- rxq->promisc_flow = flow;
- DEBUG("%p: promiscuous mode enabled", (void *)rxq);
- return 0;
-}
-
-/**
- * Disable promiscuous mode in a RX queue.
- *
- * @param rxq
- * Pointer to RX queue structure.
- */
-static void
-rxq_promiscuous_disable(struct rxq *rxq)
-{
- if (rxq->priv->vf)
- return;
- DEBUG("%p: disabling promiscuous mode", (void *)rxq);
- if (rxq->promisc_flow == NULL)
- return;
- claim_zero(ibv_destroy_flow(rxq->promisc_flow));
- rxq->promisc_flow = NULL;
- DEBUG("%p: promiscuous mode disabled", (void *)rxq);
-}
-
-/**
- * Clean up a RX queue.
- *
- * Destroy objects, free allocated memory and reset the structure for reuse.
- *
- * @param rxq
- * Pointer to RX queue structure.
- */
-static void
-rxq_cleanup(struct rxq *rxq)
-{
- struct ibv_exp_release_intf_params params;
-
- DEBUG("cleaning up %p", (void *)rxq);
- if (rxq->sp)
- rxq_free_elts_sp(rxq);
- else
- rxq_free_elts(rxq);
- if (rxq->if_qp != NULL) {
- assert(rxq->priv != NULL);
- assert(rxq->priv->ctx != NULL);
- assert(rxq->qp != NULL);
- params = (struct ibv_exp_release_intf_params){
- .comp_mask = 0,
- };
- claim_zero(ibv_exp_release_intf(rxq->priv->ctx,
- rxq->if_qp,
- ¶ms));
- }
- if (rxq->if_cq != NULL) {
- assert(rxq->priv != NULL);
- assert(rxq->priv->ctx != NULL);
- assert(rxq->cq != NULL);
- params = (struct ibv_exp_release_intf_params){
- .comp_mask = 0,
- };
- claim_zero(ibv_exp_release_intf(rxq->priv->ctx,
- rxq->if_cq,
- ¶ms));
- }
- if (rxq->qp != NULL) {
- rxq_promiscuous_disable(rxq);
- rxq_allmulticast_disable(rxq);
- rxq_mac_addrs_del(rxq);
- claim_zero(ibv_destroy_qp(rxq->qp));
- }
- if (rxq->cq != NULL)
- claim_zero(ibv_destroy_cq(rxq->cq));
- if (rxq->rd != NULL) {
- struct ibv_exp_destroy_res_domain_attr attr = {
- .comp_mask = 0,
- };
-
- assert(rxq->priv != NULL);
- assert(rxq->priv->ctx != NULL);
- claim_zero(ibv_exp_destroy_res_domain(rxq->priv->ctx,
- rxq->rd,
- &attr));
- }
- if (rxq->mr != NULL)
- claim_zero(ibv_dereg_mr(rxq->mr));
- memset(rxq, 0, sizeof(*rxq));
-}
-
-/**
- * Translate RX completion flags to packet type.
- *
- * @param flags
- * RX completion flags returned by poll_length_flags().
- *
- * @return
- * Packet type for struct rte_mbuf.
- */
-static inline uint32_t
-rxq_cq_to_pkt_type(uint32_t flags)
-{
- uint32_t pkt_type;
-
- if (flags & IBV_EXP_CQ_RX_TUNNEL_PACKET)
- pkt_type =
- TRANSPOSE(flags,
- IBV_EXP_CQ_RX_OUTER_IPV4_PACKET, RTE_PTYPE_L3_IPV4) |
- TRANSPOSE(flags,
- IBV_EXP_CQ_RX_OUTER_IPV6_PACKET, RTE_PTYPE_L3_IPV6) |
- TRANSPOSE(flags,
- IBV_EXP_CQ_RX_IPV4_PACKET, RTE_PTYPE_INNER_L3_IPV4) |
- TRANSPOSE(flags,
- IBV_EXP_CQ_RX_IPV6_PACKET, RTE_PTYPE_INNER_L3_IPV6);
- else
- pkt_type =
- TRANSPOSE(flags,
- IBV_EXP_CQ_RX_IPV4_PACKET, RTE_PTYPE_L3_IPV4) |
- TRANSPOSE(flags,
- IBV_EXP_CQ_RX_IPV6_PACKET, RTE_PTYPE_L3_IPV6);
- return pkt_type;
-}
-
-/**
- * Translate RX completion flags to offload flags.
- *
- * @param[in] rxq
- * Pointer to RX queue structure.
- * @param flags
- * RX completion flags returned by poll_length_flags().
- *
- * @return
- * Offload flags (ol_flags) for struct rte_mbuf.
- */
-static inline uint32_t
-rxq_cq_to_ol_flags(const struct rxq *rxq, uint32_t flags)
-{
- uint32_t ol_flags = 0;
-
- if (rxq->csum)
- ol_flags |=
- TRANSPOSE(~flags,
- IBV_EXP_CQ_RX_IP_CSUM_OK,
- PKT_RX_IP_CKSUM_BAD) |
- TRANSPOSE(~flags,
- IBV_EXP_CQ_RX_TCP_UDP_CSUM_OK,
- PKT_RX_L4_CKSUM_BAD);
- /*
- * PKT_RX_IP_CKSUM_BAD and PKT_RX_L4_CKSUM_BAD are used in place
- * of PKT_RX_EIP_CKSUM_BAD because the latter is not functional
- * (its value is 0).
- */
- if ((flags & IBV_EXP_CQ_RX_TUNNEL_PACKET) && (rxq->csum_l2tun))
- ol_flags |=
- TRANSPOSE(~flags,
- IBV_EXP_CQ_RX_OUTER_IP_CSUM_OK,
- PKT_RX_IP_CKSUM_BAD) |
- TRANSPOSE(~flags,
- IBV_EXP_CQ_RX_OUTER_TCP_UDP_CSUM_OK,
- PKT_RX_L4_CKSUM_BAD);
- return ol_flags;
-}
-
-static uint16_t
-mlx4_rx_burst(void *dpdk_rxq, struct rte_mbuf **pkts, uint16_t pkts_n);
-
-/**
- * DPDK callback for RX with scattered packets support.
- *
- * @param dpdk_rxq
- * Generic pointer to RX queue structure.
- * @param[out] pkts
- * Array to store received packets.
- * @param pkts_n
- * Maximum number of packets in array.
- *
- * @return
- * Number of packets successfully received (<= pkts_n).
- */
-static uint16_t
-mlx4_rx_burst_sp(void *dpdk_rxq, struct rte_mbuf **pkts, uint16_t pkts_n)
-{
- struct rxq *rxq = (struct rxq *)dpdk_rxq;
- struct rxq_elt_sp (*elts)[rxq->elts_n] = rxq->elts.sp;
- const unsigned int elts_n = rxq->elts_n;
- unsigned int elts_head = rxq->elts_head;
- struct ibv_recv_wr head;
- struct ibv_recv_wr **next = &head.next;
- struct ibv_recv_wr *bad_wr;
- unsigned int i;
- unsigned int pkts_ret = 0;
- int ret;
-
- if (unlikely(!rxq->sp))
- return mlx4_rx_burst(dpdk_rxq, pkts, pkts_n);
- if (unlikely(elts == NULL)) /* See RTE_DEV_CMD_SET_MTU. */
- return 0;
- for (i = 0; (i != pkts_n); ++i) {
- struct rxq_elt_sp *elt = &(*elts)[elts_head];
- struct ibv_recv_wr *wr = &elt->wr;
- uint64_t wr_id = wr->wr_id;
- unsigned int len;
- unsigned int pkt_buf_len;
- struct rte_mbuf *pkt_buf = NULL; /* Buffer returned in pkts. */
- struct rte_mbuf **pkt_buf_next = &pkt_buf;
- unsigned int seg_headroom = RTE_PKTMBUF_HEADROOM;
- unsigned int j = 0;
- uint32_t flags;
-
- /* Sanity checks. */
-#ifdef NDEBUG
- (void)wr_id;
-#endif
- assert(wr_id < rxq->elts_n);
- assert(wr->sg_list == elt->sges);
- assert(wr->num_sge == elemof(elt->sges));
- assert(elts_head < rxq->elts_n);
- assert(rxq->elts_head < rxq->elts_n);
- ret = rxq->if_cq->poll_length_flags(rxq->cq, NULL, NULL,
- &flags);
- if (unlikely(ret < 0)) {
- struct ibv_wc wc;
- int wcs_n;
-
- DEBUG("rxq=%p, poll_length() failed (ret=%d)",
- (void *)rxq, ret);
- /* ibv_poll_cq() must be used in case of failure. */
- wcs_n = ibv_poll_cq(rxq->cq, 1, &wc);
- if (unlikely(wcs_n == 0))
- break;
- if (unlikely(wcs_n < 0)) {
- DEBUG("rxq=%p, ibv_poll_cq() failed (wcs_n=%d)",
- (void *)rxq, wcs_n);
- break;
- }
- assert(wcs_n == 1);
- if (unlikely(wc.status != IBV_WC_SUCCESS)) {
- /* Whatever, just repost the offending WR. */
- DEBUG("rxq=%p, wr_id=%" PRIu64 ": bad work"
- " completion status (%d): %s",
- (void *)rxq, wc.wr_id, wc.status,
- ibv_wc_status_str(wc.status));
-#ifdef MLX4_PMD_SOFT_COUNTERS
- /* Increment dropped packets counter. */
- ++rxq->stats.idropped;
-#endif
- /* Link completed WRs together for repost. */
- *next = wr;
- next = &wr->next;
- goto repost;
- }
- ret = wc.byte_len;
- }
- if (ret == 0)
- break;
- len = ret;
- pkt_buf_len = len;
- /* Link completed WRs together for repost. */
- *next = wr;
- next = &wr->next;
- /*
- * Replace spent segments with new ones, concatenate and
- * return them as pkt_buf.
- */
- while (1) {
- struct ibv_sge *sge = &elt->sges[j];
- struct rte_mbuf *seg = elt->bufs[j];
- struct rte_mbuf *rep;
- unsigned int seg_tailroom;
-
- /*
- * Fetch initial bytes of packet descriptor into a
- * cacheline while allocating rep.
- */
- rte_prefetch0(seg);
- rep = __rte_mbuf_raw_alloc(rxq->mp);
- if (unlikely(rep == NULL)) {
- /*
- * Unable to allocate a replacement mbuf,
- * repost WR.
- */
- DEBUG("rxq=%p, wr_id=%" PRIu64 ":"
- " can't allocate a new mbuf",
- (void *)rxq, wr_id);
- if (pkt_buf != NULL) {
- *pkt_buf_next = NULL;
- rte_pktmbuf_free(pkt_buf);
- }
- /* Increase out of memory counters. */
- ++rxq->stats.rx_nombuf;
- ++rxq->priv->dev->data->rx_mbuf_alloc_failed;
- goto repost;
- }
-#ifndef NDEBUG
- /* Poison user-modifiable fields in rep. */
- NEXT(rep) = (void *)((uintptr_t)-1);
- SET_DATA_OFF(rep, 0xdead);
- DATA_LEN(rep) = 0xd00d;
- PKT_LEN(rep) = 0xdeadd00d;
- NB_SEGS(rep) = 0x2a;
- PORT(rep) = 0x2a;
- rep->ol_flags = -1;
-#endif
- assert(rep->buf_len == seg->buf_len);
- assert(rep->buf_len == rxq->mb_len);
- /* Reconfigure sge to use rep instead of seg. */
- assert(sge->lkey == rxq->mr->lkey);
- sge->addr = ((uintptr_t)rep->buf_addr + seg_headroom);
- elt->bufs[j] = rep;
- ++j;
- /* Update pkt_buf if it's the first segment, or link
- * seg to the previous one and update pkt_buf_next. */
- *pkt_buf_next = seg;
- pkt_buf_next = &NEXT(seg);
- /* Update seg information. */
- seg_tailroom = (seg->buf_len - seg_headroom);
- assert(sge->length == seg_tailroom);
- SET_DATA_OFF(seg, seg_headroom);
- if (likely(len <= seg_tailroom)) {
- /* Last segment. */
- DATA_LEN(seg) = len;
- PKT_LEN(seg) = len;
- /* Sanity check. */
- assert(rte_pktmbuf_headroom(seg) ==
- seg_headroom);
- assert(rte_pktmbuf_tailroom(seg) ==
- (seg_tailroom - len));
- break;
- }
- DATA_LEN(seg) = seg_tailroom;
- PKT_LEN(seg) = seg_tailroom;
- /* Sanity check. */
- assert(rte_pktmbuf_headroom(seg) == seg_headroom);
- assert(rte_pktmbuf_tailroom(seg) == 0);
- /* Fix len and clear headroom for next segments. */
- len -= seg_tailroom;
- seg_headroom = 0;