+ struct priv *priv = dev->data->dev_private;
+ int ret;
+ struct mlx5_flow flow = { .offset = sizeof(struct ibv_exp_flow_attr) };
+
+ priv_lock(priv);
+ ret = priv_flow_validate(priv, attr, items, actions, error, &flow);
+ priv_unlock(priv);
+ return ret;
+}
+
+/**
+ * Convert Ethernet item to Verbs specification.
+ *
+ * @param item[in]
+ * Item specification.
+ * @param default_mask[in]
+ * Default bit-masks to use when item->mask is not provided.
+ * @param data[in, out]
+ * User structure.
+ */
+static int
+mlx5_flow_create_eth(const struct rte_flow_item *item,
+ const void *default_mask,
+ void *data)
+{
+ const struct rte_flow_item_eth *spec = item->spec;
+ const struct rte_flow_item_eth *mask = item->mask;
+ struct mlx5_flow *flow = (struct mlx5_flow *)data;
+ struct ibv_exp_flow_spec_eth *eth;
+ const unsigned int eth_size = sizeof(struct ibv_exp_flow_spec_eth);
+ unsigned int i;
+
+ ++flow->ibv_attr->num_of_specs;
+ flow->ibv_attr->priority = 2;
+ eth = (void *)((uintptr_t)flow->ibv_attr + flow->offset);
+ *eth = (struct ibv_exp_flow_spec_eth) {
+ .type = IBV_EXP_FLOW_SPEC_ETH,
+ .size = eth_size,
+ };
+ if (!spec)
+ return 0;
+ if (!mask)
+ mask = default_mask;
+ memcpy(eth->val.dst_mac, spec->dst.addr_bytes, ETHER_ADDR_LEN);
+ memcpy(eth->val.src_mac, spec->src.addr_bytes, ETHER_ADDR_LEN);
+ memcpy(eth->mask.dst_mac, mask->dst.addr_bytes, ETHER_ADDR_LEN);
+ memcpy(eth->mask.src_mac, mask->src.addr_bytes, ETHER_ADDR_LEN);
+ /* Remove unwanted bits from values. */
+ for (i = 0; i < ETHER_ADDR_LEN; ++i) {
+ eth->val.dst_mac[i] &= eth->mask.dst_mac[i];
+ eth->val.src_mac[i] &= eth->mask.src_mac[i];
+ }
+ return 0;
+}
+
+/**
+ * Convert IPv4 item to Verbs specification.
+ *
+ * @param item[in]
+ * Item specification.
+ * @param default_mask[in]
+ * Default bit-masks to use when item->mask is not provided.
+ * @param data[in, out]
+ * User structure.
+ */
+static int
+mlx5_flow_create_ipv4(const struct rte_flow_item *item,
+ const void *default_mask,
+ void *data)
+{
+ const struct rte_flow_item_ipv4 *spec = item->spec;
+ const struct rte_flow_item_ipv4 *mask = item->mask;
+ struct mlx5_flow *flow = (struct mlx5_flow *)data;
+ struct ibv_exp_flow_spec_ipv4 *ipv4;
+ unsigned int ipv4_size = sizeof(struct ibv_exp_flow_spec_ipv4);
+
+ ++flow->ibv_attr->num_of_specs;
+ flow->ibv_attr->priority = 1;
+ ipv4 = (void *)((uintptr_t)flow->ibv_attr + flow->offset);
+ *ipv4 = (struct ibv_exp_flow_spec_ipv4) {
+ .type = IBV_EXP_FLOW_SPEC_IPV4,
+ .size = ipv4_size,
+ };
+ if (!spec)
+ return 0;
+ if (!mask)
+ mask = default_mask;
+ ipv4->val = (struct ibv_exp_flow_ipv4_filter){
+ .src_ip = spec->hdr.src_addr,
+ .dst_ip = spec->hdr.dst_addr,
+ };
+ ipv4->mask = (struct ibv_exp_flow_ipv4_filter){
+ .src_ip = mask->hdr.src_addr,
+ .dst_ip = mask->hdr.dst_addr,
+ };
+ /* Remove unwanted bits from values. */
+ ipv4->val.src_ip &= ipv4->mask.src_ip;
+ ipv4->val.dst_ip &= ipv4->mask.dst_ip;
+ return 0;
+}
+
+/**
+ * Convert IPv6 item to Verbs specification.
+ *
+ * @param item[in]
+ * Item specification.
+ * @param default_mask[in]
+ * Default bit-masks to use when item->mask is not provided.
+ * @param data[in, out]
+ * User structure.
+ */
+static int
+mlx5_flow_create_ipv6(const struct rte_flow_item *item,
+ const void *default_mask,
+ void *data)
+{
+ const struct rte_flow_item_ipv6 *spec = item->spec;
+ const struct rte_flow_item_ipv6 *mask = item->mask;
+ struct mlx5_flow *flow = (struct mlx5_flow *)data;
+ struct ibv_exp_flow_spec_ipv6 *ipv6;
+ unsigned int ipv6_size = sizeof(struct ibv_exp_flow_spec_ipv6);
+ unsigned int i;
+
+ ++flow->ibv_attr->num_of_specs;
+ flow->ibv_attr->priority = 1;
+ ipv6 = (void *)((uintptr_t)flow->ibv_attr + flow->offset);
+ *ipv6 = (struct ibv_exp_flow_spec_ipv6) {
+ .type = IBV_EXP_FLOW_SPEC_IPV6,
+ .size = ipv6_size,
+ };
+ if (!spec)
+ return 0;
+ if (!mask)
+ mask = default_mask;
+ memcpy(ipv6->val.src_ip, spec->hdr.src_addr,
+ RTE_DIM(ipv6->val.src_ip));
+ memcpy(ipv6->val.dst_ip, spec->hdr.dst_addr,
+ RTE_DIM(ipv6->val.dst_ip));
+ memcpy(ipv6->mask.src_ip, mask->hdr.src_addr,
+ RTE_DIM(ipv6->mask.src_ip));
+ memcpy(ipv6->mask.dst_ip, mask->hdr.dst_addr,
+ RTE_DIM(ipv6->mask.dst_ip));
+ /* Remove unwanted bits from values. */
+ for (i = 0; i < RTE_DIM(ipv6->val.src_ip); ++i) {
+ ipv6->val.src_ip[i] &= ipv6->mask.src_ip[i];
+ ipv6->val.dst_ip[i] &= ipv6->mask.dst_ip[i];
+ }
+ return 0;
+}
+
+/**
+ * Convert UDP item to Verbs specification.
+ *
+ * @param item[in]
+ * Item specification.
+ * @param default_mask[in]
+ * Default bit-masks to use when item->mask is not provided.
+ * @param data[in, out]
+ * User structure.
+ */
+static int
+mlx5_flow_create_udp(const struct rte_flow_item *item,
+ const void *default_mask,
+ void *data)
+{
+ const struct rte_flow_item_udp *spec = item->spec;
+ const struct rte_flow_item_udp *mask = item->mask;
+ struct mlx5_flow *flow = (struct mlx5_flow *)data;
+ struct ibv_exp_flow_spec_tcp_udp *udp;
+ unsigned int udp_size = sizeof(struct ibv_exp_flow_spec_tcp_udp);
+
+ ++flow->ibv_attr->num_of_specs;
+ flow->ibv_attr->priority = 0;
+ udp = (void *)((uintptr_t)flow->ibv_attr + flow->offset);
+ *udp = (struct ibv_exp_flow_spec_tcp_udp) {
+ .type = IBV_EXP_FLOW_SPEC_UDP,
+ .size = udp_size,
+ };
+ if (!spec)
+ return 0;
+ if (!mask)
+ mask = default_mask;
+ udp->val.dst_port = spec->hdr.dst_port;
+ udp->val.src_port = spec->hdr.src_port;
+ udp->mask.dst_port = mask->hdr.dst_port;
+ udp->mask.src_port = mask->hdr.src_port;
+ /* Remove unwanted bits from values. */
+ udp->val.src_port &= udp->mask.src_port;
+ udp->val.dst_port &= udp->mask.dst_port;
+ return 0;
+}
+
+/**
+ * Convert TCP item to Verbs specification.
+ *
+ * @param item[in]
+ * Item specification.
+ * @param default_mask[in]
+ * Default bit-masks to use when item->mask is not provided.
+ * @param data[in, out]
+ * User structure.
+ */
+static int
+mlx5_flow_create_tcp(const struct rte_flow_item *item,
+ const void *default_mask,
+ void *data)
+{
+ const struct rte_flow_item_tcp *spec = item->spec;
+ const struct rte_flow_item_tcp *mask = item->mask;
+ struct mlx5_flow *flow = (struct mlx5_flow *)data;
+ struct ibv_exp_flow_spec_tcp_udp *tcp;
+ unsigned int tcp_size = sizeof(struct ibv_exp_flow_spec_tcp_udp);
+
+ ++flow->ibv_attr->num_of_specs;
+ flow->ibv_attr->priority = 0;
+ tcp = (void *)((uintptr_t)flow->ibv_attr + flow->offset);
+ *tcp = (struct ibv_exp_flow_spec_tcp_udp) {
+ .type = IBV_EXP_FLOW_SPEC_TCP,
+ .size = tcp_size,
+ };
+ if (!spec)
+ return 0;
+ if (!mask)
+ mask = default_mask;
+ tcp->val.dst_port = spec->hdr.dst_port;
+ tcp->val.src_port = spec->hdr.src_port;
+ tcp->mask.dst_port = mask->hdr.dst_port;
+ tcp->mask.src_port = mask->hdr.src_port;
+ /* Remove unwanted bits from values. */
+ tcp->val.src_port &= tcp->mask.src_port;
+ tcp->val.dst_port &= tcp->mask.dst_port;
+ return 0;
+}
+
+/**
+ * Complete flow rule creation.
+ *
+ * @param priv
+ * Pointer to private structure.
+ * @param ibv_attr
+ * Verbs flow attributes.
+ * @param action
+ * Target action structure.
+ * @param[out] error
+ * Perform verbose error reporting if not NULL.
+ *
+ * @return
+ * A flow if the rule could be created.
+ */
+static struct rte_flow *
+priv_flow_create_action_queue(struct priv *priv,
+ struct ibv_exp_flow_attr *ibv_attr,
+ struct mlx5_flow_action *action,
+ struct rte_flow_error *error)
+{
+ struct rxq_ctrl *rxq;
+ struct rte_flow *rte_flow;
+
+ assert(priv->pd);
+ assert(priv->ctx);
+ rte_flow = rte_calloc(__func__, 1, sizeof(*rte_flow), 0);
+ if (!rte_flow) {
+ rte_flow_error_set(error, ENOMEM, RTE_FLOW_ERROR_TYPE_HANDLE,
+ NULL, "cannot allocate flow memory");
+ return NULL;
+ }
+ if (action->drop) {
+ rte_flow->cq =
+ ibv_exp_create_cq(priv->ctx, 1, NULL, NULL, 0,
+ &(struct ibv_exp_cq_init_attr){
+ .comp_mask = 0,
+ });
+ if (!rte_flow->cq) {
+ rte_flow_error_set(error, ENOMEM,
+ RTE_FLOW_ERROR_TYPE_HANDLE,
+ NULL, "cannot allocate CQ");
+ goto error;
+ }
+ rte_flow->wq = ibv_exp_create_wq(priv->ctx,
+ &(struct ibv_exp_wq_init_attr){
+ .wq_type = IBV_EXP_WQT_RQ,
+ .max_recv_wr = 1,
+ .max_recv_sge = 1,
+ .pd = priv->pd,
+ .cq = rte_flow->cq,
+ });
+ } else {
+ rxq = container_of((*priv->rxqs)[action->queue_id],
+ struct rxq_ctrl, rxq);
+ rte_flow->rxq = &rxq->rxq;
+ rte_flow->wq = rxq->wq;
+ }
+ rte_flow->ibv_attr = ibv_attr;
+ rte_flow->ind_table = ibv_exp_create_rwq_ind_table(
+ priv->ctx,
+ &(struct ibv_exp_rwq_ind_table_init_attr){
+ .pd = priv->pd,
+ .log_ind_tbl_size = 0,
+ .ind_tbl = &rte_flow->wq,
+ .comp_mask = 0,
+ });
+ if (!rte_flow->ind_table) {
+ rte_flow_error_set(error, ENOMEM, RTE_FLOW_ERROR_TYPE_HANDLE,
+ NULL, "cannot allocate indirection table");
+ goto error;
+ }
+ rte_flow->qp = ibv_exp_create_qp(
+ priv->ctx,
+ &(struct ibv_exp_qp_init_attr){
+ .qp_type = IBV_QPT_RAW_PACKET,
+ .comp_mask =
+ IBV_EXP_QP_INIT_ATTR_PD |
+ IBV_EXP_QP_INIT_ATTR_PORT |
+ IBV_EXP_QP_INIT_ATTR_RX_HASH,
+ .pd = priv->pd,
+ .rx_hash_conf = &(struct ibv_exp_rx_hash_conf){
+ .rx_hash_function =
+ IBV_EXP_RX_HASH_FUNC_TOEPLITZ,
+ .rx_hash_key_len = rss_hash_default_key_len,
+ .rx_hash_key = rss_hash_default_key,
+ .rx_hash_fields_mask = 0,
+ .rwq_ind_tbl = rte_flow->ind_table,
+ },
+ .port_num = priv->port,
+ });
+ if (!rte_flow->qp) {
+ rte_flow_error_set(error, ENOMEM, RTE_FLOW_ERROR_TYPE_HANDLE,
+ NULL, "cannot allocate QP");
+ goto error;
+ }
+ rte_flow->ibv_flow = ibv_exp_create_flow(rte_flow->qp,
+ rte_flow->ibv_attr);
+ if (!rte_flow->ibv_flow) {
+ rte_flow_error_set(error, ENOMEM, RTE_FLOW_ERROR_TYPE_HANDLE,
+ NULL, "flow rule creation failure");
+ goto error;
+ }
+ return rte_flow;
+error:
+ assert(rte_flow);
+ if (rte_flow->qp)
+ ibv_destroy_qp(rte_flow->qp);
+ if (rte_flow->ind_table)
+ ibv_exp_destroy_rwq_ind_table(rte_flow->ind_table);
+ if (!rte_flow->rxq && rte_flow->wq)
+ ibv_exp_destroy_wq(rte_flow->wq);
+ if (!rte_flow->rxq && rte_flow->cq)
+ ibv_destroy_cq(rte_flow->cq);
+ rte_free(rte_flow->ibv_attr);
+ rte_free(rte_flow);
+ return NULL;
+}
+
+/**
+ * Convert a flow.
+ *
+ * @param priv
+ * Pointer to private structure.
+ * @param[in] attr
+ * Flow rule attributes.
+ * @param[in] pattern
+ * Pattern specification (list terminated by the END pattern item).
+ * @param[in] actions
+ * Associated actions (list terminated by the END action).
+ * @param[out] error
+ * Perform verbose error reporting if not NULL.
+ *
+ * @return
+ * A flow on success, NULL otherwise.
+ */
+static struct rte_flow *
+priv_flow_create(struct priv *priv,
+ const struct rte_flow_attr *attr,
+ const struct rte_flow_item items[],
+ const struct rte_flow_action actions[],
+ struct rte_flow_error *error)
+{
+ struct rte_flow *rte_flow;
+ struct mlx5_flow_action action;
+ struct mlx5_flow flow = { .offset = sizeof(struct ibv_exp_flow_attr), };
+ int err;
+
+ err = priv_flow_validate(priv, attr, items, actions, error, &flow);
+ if (err)
+ goto exit;
+ flow.ibv_attr = rte_malloc(__func__, flow.offset, 0);
+ flow.offset = sizeof(struct ibv_exp_flow_attr);
+ if (!flow.ibv_attr) {
+ rte_flow_error_set(error, ENOMEM, RTE_FLOW_ERROR_TYPE_HANDLE,
+ NULL, "cannot allocate ibv_attr memory");
+ goto exit;
+ }
+ *flow.ibv_attr = (struct ibv_exp_flow_attr){
+ .type = IBV_EXP_FLOW_ATTR_NORMAL,
+ .size = sizeof(struct ibv_exp_flow_attr),
+ .priority = attr->priority,
+ .num_of_specs = 0,
+ .port = 0,
+ .flags = 0,
+ .reserved = 0,
+ };
+ claim_zero(priv_flow_validate(priv, attr, items, actions,
+ error, &flow));
+ action = (struct mlx5_flow_action){
+ .queue = 0,
+ .drop = 0,
+ };
+ for (; actions->type != RTE_FLOW_ACTION_TYPE_END; ++actions) {
+ if (actions->type == RTE_FLOW_ACTION_TYPE_VOID) {
+ continue;
+ } else if (actions->type == RTE_FLOW_ACTION_TYPE_QUEUE) {
+ action.queue = 1;
+ action.queue_id =
+ ((const struct rte_flow_action_queue *)
+ actions->conf)->index;
+ } else if (actions->type == RTE_FLOW_ACTION_TYPE_DROP) {
+ action.drop = 1;
+ } else {
+ rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ actions, "unsupported action");
+ goto exit;
+ }
+ }
+ rte_flow = priv_flow_create_action_queue(priv, flow.ibv_attr,
+ &action, error);
+ return rte_flow;
+exit:
+ rte_free(flow.ibv_attr);
+ return NULL;