+ /* Register new encap/decap resource. */
+ cache_resource = rte_calloc(__func__, 1, sizeof(*cache_resource), 0);
+ if (!cache_resource)
+ return rte_flow_error_set(error, ENOMEM,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
+ "cannot allocate resource memory");
+ *cache_resource = *resource;
+ cache_resource->verbs_action =
+ mlx5_glue->dv_create_flow_action_packet_reformat
+ (sh->ctx, cache_resource->reformat_type,
+ cache_resource->ft_type, domain, cache_resource->flags,
+ cache_resource->size,
+ (cache_resource->size ? cache_resource->buf : NULL));
+ if (!cache_resource->verbs_action) {
+ rte_free(cache_resource);
+ return rte_flow_error_set(error, ENOMEM,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL, "cannot create action");
+ }
+ rte_atomic32_init(&cache_resource->refcnt);
+ rte_atomic32_inc(&cache_resource->refcnt);
+ LIST_INSERT_HEAD(&sh->encaps_decaps, cache_resource, next);
+ dev_flow->dv.encap_decap = cache_resource;
+ DRV_LOG(DEBUG, "new encap/decap resource %p: refcnt %d++",
+ (void *)cache_resource,
+ rte_atomic32_read(&cache_resource->refcnt));
+ return 0;
+}
+
+/**
+ * Find existing table jump resource or create and register a new one.
+ *
+ * @param dev[in, out]
+ * Pointer to rte_eth_dev structure.
+ * @param[in, out] resource
+ * Pointer to jump table resource.
+ * @parm[in, out] dev_flow
+ * Pointer to the dev_flow.
+ * @param[out] error
+ * pointer to error structure.
+ *
+ * @return
+ * 0 on success otherwise -errno and errno is set.
+ */
+static int
+flow_dv_jump_tbl_resource_register
+ (struct rte_eth_dev *dev,
+ struct mlx5_flow_dv_jump_tbl_resource *resource,
+ struct mlx5_flow *dev_flow,
+ struct rte_flow_error *error)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_ibv_shared *sh = priv->sh;
+ struct mlx5_flow_dv_jump_tbl_resource *cache_resource;
+
+ /* Lookup a matching resource from cache. */
+ LIST_FOREACH(cache_resource, &sh->jump_tbl, next) {
+ if (resource->tbl == cache_resource->tbl) {
+ DRV_LOG(DEBUG, "jump table resource resource %p: refcnt %d++",
+ (void *)cache_resource,
+ rte_atomic32_read(&cache_resource->refcnt));
+ rte_atomic32_inc(&cache_resource->refcnt);
+ dev_flow->dv.jump = cache_resource;
+ return 0;
+ }
+ }
+ /* Register new jump table resource. */
+ cache_resource = rte_calloc(__func__, 1, sizeof(*cache_resource), 0);
+ if (!cache_resource)
+ return rte_flow_error_set(error, ENOMEM,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
+ "cannot allocate resource memory");
+ *cache_resource = *resource;
+ cache_resource->action =
+ mlx5_glue->dr_create_flow_action_dest_flow_tbl
+ (resource->tbl->obj);
+ if (!cache_resource->action) {
+ rte_free(cache_resource);
+ return rte_flow_error_set(error, ENOMEM,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL, "cannot create action");
+ }
+ rte_atomic32_init(&cache_resource->refcnt);
+ rte_atomic32_inc(&cache_resource->refcnt);
+ LIST_INSERT_HEAD(&sh->jump_tbl, cache_resource, next);
+ dev_flow->dv.jump = cache_resource;
+ DRV_LOG(DEBUG, "new jump table resource %p: refcnt %d++",
+ (void *)cache_resource,
+ rte_atomic32_read(&cache_resource->refcnt));
+ return 0;
+}
+
+/**
+ * Find existing table port ID resource or create and register a new one.
+ *
+ * @param dev[in, out]
+ * Pointer to rte_eth_dev structure.
+ * @param[in, out] resource
+ * Pointer to port ID action resource.
+ * @parm[in, out] dev_flow
+ * Pointer to the dev_flow.
+ * @param[out] error
+ * pointer to error structure.
+ *
+ * @return
+ * 0 on success otherwise -errno and errno is set.
+ */
+static int
+flow_dv_port_id_action_resource_register
+ (struct rte_eth_dev *dev,
+ struct mlx5_flow_dv_port_id_action_resource *resource,
+ struct mlx5_flow *dev_flow,
+ struct rte_flow_error *error)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_ibv_shared *sh = priv->sh;
+ struct mlx5_flow_dv_port_id_action_resource *cache_resource;
+
+ /* Lookup a matching resource from cache. */
+ LIST_FOREACH(cache_resource, &sh->port_id_action_list, next) {
+ if (resource->port_id == cache_resource->port_id) {
+ DRV_LOG(DEBUG, "port id action resource resource %p: "
+ "refcnt %d++",
+ (void *)cache_resource,
+ rte_atomic32_read(&cache_resource->refcnt));
+ rte_atomic32_inc(&cache_resource->refcnt);
+ dev_flow->dv.port_id_action = cache_resource;
+ return 0;
+ }
+ }
+ /* Register new port id action resource. */
+ cache_resource = rte_calloc(__func__, 1, sizeof(*cache_resource), 0);
+ if (!cache_resource)
+ return rte_flow_error_set(error, ENOMEM,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
+ "cannot allocate resource memory");
+ *cache_resource = *resource;
+ cache_resource->action =
+ mlx5_glue->dr_create_flow_action_dest_vport
+ (priv->sh->fdb_domain, resource->port_id);
+ if (!cache_resource->action) {
+ rte_free(cache_resource);
+ return rte_flow_error_set(error, ENOMEM,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL, "cannot create action");
+ }
+ rte_atomic32_init(&cache_resource->refcnt);
+ rte_atomic32_inc(&cache_resource->refcnt);
+ LIST_INSERT_HEAD(&sh->port_id_action_list, cache_resource, next);
+ dev_flow->dv.port_id_action = cache_resource;
+ DRV_LOG(DEBUG, "new port id action resource %p: refcnt %d++",
+ (void *)cache_resource,
+ rte_atomic32_read(&cache_resource->refcnt));
+ return 0;
+}
+
+/**
+ * Find existing push vlan resource or create and register a new one.
+ *
+ * @param dev[in, out]
+ * Pointer to rte_eth_dev structure.
+ * @param[in, out] resource
+ * Pointer to port ID action resource.
+ * @parm[in, out] dev_flow
+ * Pointer to the dev_flow.
+ * @param[out] error
+ * pointer to error structure.
+ *
+ * @return
+ * 0 on success otherwise -errno and errno is set.
+ */
+static int
+flow_dv_push_vlan_action_resource_register
+ (struct rte_eth_dev *dev,
+ struct mlx5_flow_dv_push_vlan_action_resource *resource,
+ struct mlx5_flow *dev_flow,
+ struct rte_flow_error *error)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_ibv_shared *sh = priv->sh;
+ struct mlx5_flow_dv_push_vlan_action_resource *cache_resource;
+ struct mlx5dv_dr_domain *domain;
+
+ /* Lookup a matching resource from cache. */
+ LIST_FOREACH(cache_resource, &sh->push_vlan_action_list, next) {
+ if (resource->vlan_tag == cache_resource->vlan_tag &&
+ resource->ft_type == cache_resource->ft_type) {
+ DRV_LOG(DEBUG, "push-VLAN action resource resource %p: "
+ "refcnt %d++",
+ (void *)cache_resource,
+ rte_atomic32_read(&cache_resource->refcnt));
+ rte_atomic32_inc(&cache_resource->refcnt);
+ dev_flow->dv.push_vlan_res = cache_resource;
+ return 0;
+ }
+ }
+ /* Register new push_vlan action resource. */
+ cache_resource = rte_calloc(__func__, 1, sizeof(*cache_resource), 0);
+ if (!cache_resource)
+ return rte_flow_error_set(error, ENOMEM,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
+ "cannot allocate resource memory");
+ *cache_resource = *resource;
+ if (resource->ft_type == MLX5DV_FLOW_TABLE_TYPE_FDB)
+ domain = sh->fdb_domain;
+ else if (resource->ft_type == MLX5DV_FLOW_TABLE_TYPE_NIC_RX)
+ domain = sh->rx_domain;
+ else
+ domain = sh->tx_domain;
+ cache_resource->action =
+ mlx5_glue->dr_create_flow_action_push_vlan(domain,
+ resource->vlan_tag);
+ if (!cache_resource->action) {
+ rte_free(cache_resource);
+ return rte_flow_error_set(error, ENOMEM,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL, "cannot create action");
+ }
+ rte_atomic32_init(&cache_resource->refcnt);
+ rte_atomic32_inc(&cache_resource->refcnt);
+ LIST_INSERT_HEAD(&sh->push_vlan_action_list, cache_resource, next);
+ dev_flow->dv.push_vlan_res = cache_resource;
+ DRV_LOG(DEBUG, "new push vlan action resource %p: refcnt %d++",
+ (void *)cache_resource,
+ rte_atomic32_read(&cache_resource->refcnt));
+ return 0;
+}
+/**
+ * Get the size of specific rte_flow_item_type
+ *
+ * @param[in] item_type
+ * Tested rte_flow_item_type.
+ *
+ * @return
+ * sizeof struct item_type, 0 if void or irrelevant.
+ */
+static size_t
+flow_dv_get_item_len(const enum rte_flow_item_type item_type)
+{
+ size_t retval;
+
+ switch (item_type) {
+ case RTE_FLOW_ITEM_TYPE_ETH:
+ retval = sizeof(struct rte_flow_item_eth);
+ break;
+ case RTE_FLOW_ITEM_TYPE_VLAN:
+ retval = sizeof(struct rte_flow_item_vlan);
+ break;
+ case RTE_FLOW_ITEM_TYPE_IPV4:
+ retval = sizeof(struct rte_flow_item_ipv4);
+ break;
+ case RTE_FLOW_ITEM_TYPE_IPV6:
+ retval = sizeof(struct rte_flow_item_ipv6);
+ break;
+ case RTE_FLOW_ITEM_TYPE_UDP:
+ retval = sizeof(struct rte_flow_item_udp);
+ break;
+ case RTE_FLOW_ITEM_TYPE_TCP:
+ retval = sizeof(struct rte_flow_item_tcp);
+ break;
+ case RTE_FLOW_ITEM_TYPE_VXLAN:
+ retval = sizeof(struct rte_flow_item_vxlan);
+ break;
+ case RTE_FLOW_ITEM_TYPE_GRE:
+ retval = sizeof(struct rte_flow_item_gre);
+ break;
+ case RTE_FLOW_ITEM_TYPE_NVGRE:
+ retval = sizeof(struct rte_flow_item_nvgre);
+ break;
+ case RTE_FLOW_ITEM_TYPE_VXLAN_GPE:
+ retval = sizeof(struct rte_flow_item_vxlan_gpe);
+ break;
+ case RTE_FLOW_ITEM_TYPE_MPLS:
+ retval = sizeof(struct rte_flow_item_mpls);
+ break;
+ case RTE_FLOW_ITEM_TYPE_VOID: /* Fall through. */
+ default:
+ retval = 0;
+ break;
+ }
+ return retval;
+}
+
+#define MLX5_ENCAP_IPV4_VERSION 0x40
+#define MLX5_ENCAP_IPV4_IHL_MIN 0x05
+#define MLX5_ENCAP_IPV4_TTL_DEF 0x40
+#define MLX5_ENCAP_IPV6_VTC_FLOW 0x60000000
+#define MLX5_ENCAP_IPV6_HOP_LIMIT 0xff
+#define MLX5_ENCAP_VXLAN_FLAGS 0x08000000
+#define MLX5_ENCAP_VXLAN_GPE_FLAGS 0x04
+
+/**
+ * Convert the encap action data from list of rte_flow_item to raw buffer
+ *
+ * @param[in] items
+ * Pointer to rte_flow_item objects list.
+ * @param[out] buf
+ * Pointer to the output buffer.
+ * @param[out] size
+ * Pointer to the output buffer size.
+ * @param[out] error
+ * Pointer to the error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+flow_dv_convert_encap_data(const struct rte_flow_item *items, uint8_t *buf,
+ size_t *size, struct rte_flow_error *error)
+{
+ struct rte_ether_hdr *eth = NULL;
+ struct rte_vlan_hdr *vlan = NULL;
+ struct rte_ipv4_hdr *ipv4 = NULL;
+ struct rte_ipv6_hdr *ipv6 = NULL;
+ struct rte_udp_hdr *udp = NULL;
+ struct rte_vxlan_hdr *vxlan = NULL;
+ struct rte_vxlan_gpe_hdr *vxlan_gpe = NULL;
+ struct rte_gre_hdr *gre = NULL;
+ size_t len;
+ size_t temp_size = 0;
+
+ if (!items)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ NULL, "invalid empty data");
+ for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) {
+ len = flow_dv_get_item_len(items->type);
+ if (len + temp_size > MLX5_ENCAP_MAX_LEN)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ (void *)items->type,
+ "items total size is too big"
+ " for encap action");
+ rte_memcpy((void *)&buf[temp_size], items->spec, len);
+ switch (items->type) {
+ case RTE_FLOW_ITEM_TYPE_ETH:
+ eth = (struct rte_ether_hdr *)&buf[temp_size];
+ break;
+ case RTE_FLOW_ITEM_TYPE_VLAN:
+ vlan = (struct rte_vlan_hdr *)&buf[temp_size];
+ if (!eth)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ (void *)items->type,
+ "eth header not found");
+ if (!eth->ether_type)
+ eth->ether_type = RTE_BE16(RTE_ETHER_TYPE_VLAN);
+ break;
+ case RTE_FLOW_ITEM_TYPE_IPV4:
+ ipv4 = (struct rte_ipv4_hdr *)&buf[temp_size];
+ if (!vlan && !eth)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ (void *)items->type,
+ "neither eth nor vlan"
+ " header found");
+ if (vlan && !vlan->eth_proto)
+ vlan->eth_proto = RTE_BE16(RTE_ETHER_TYPE_IPV4);
+ else if (eth && !eth->ether_type)
+ eth->ether_type = RTE_BE16(RTE_ETHER_TYPE_IPV4);
+ if (!ipv4->version_ihl)
+ ipv4->version_ihl = MLX5_ENCAP_IPV4_VERSION |
+ MLX5_ENCAP_IPV4_IHL_MIN;
+ if (!ipv4->time_to_live)
+ ipv4->time_to_live = MLX5_ENCAP_IPV4_TTL_DEF;
+ break;
+ case RTE_FLOW_ITEM_TYPE_IPV6:
+ ipv6 = (struct rte_ipv6_hdr *)&buf[temp_size];
+ if (!vlan && !eth)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ (void *)items->type,
+ "neither eth nor vlan"
+ " header found");
+ if (vlan && !vlan->eth_proto)
+ vlan->eth_proto = RTE_BE16(RTE_ETHER_TYPE_IPV6);
+ else if (eth && !eth->ether_type)
+ eth->ether_type = RTE_BE16(RTE_ETHER_TYPE_IPV6);
+ if (!ipv6->vtc_flow)
+ ipv6->vtc_flow =
+ RTE_BE32(MLX5_ENCAP_IPV6_VTC_FLOW);
+ if (!ipv6->hop_limits)
+ ipv6->hop_limits = MLX5_ENCAP_IPV6_HOP_LIMIT;
+ break;
+ case RTE_FLOW_ITEM_TYPE_UDP:
+ udp = (struct rte_udp_hdr *)&buf[temp_size];
+ if (!ipv4 && !ipv6)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ (void *)items->type,
+ "ip header not found");
+ if (ipv4 && !ipv4->next_proto_id)
+ ipv4->next_proto_id = IPPROTO_UDP;
+ else if (ipv6 && !ipv6->proto)
+ ipv6->proto = IPPROTO_UDP;
+ break;
+ case RTE_FLOW_ITEM_TYPE_VXLAN:
+ vxlan = (struct rte_vxlan_hdr *)&buf[temp_size];
+ if (!udp)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ (void *)items->type,
+ "udp header not found");
+ if (!udp->dst_port)
+ udp->dst_port = RTE_BE16(MLX5_UDP_PORT_VXLAN);
+ if (!vxlan->vx_flags)
+ vxlan->vx_flags =
+ RTE_BE32(MLX5_ENCAP_VXLAN_FLAGS);
+ break;
+ case RTE_FLOW_ITEM_TYPE_VXLAN_GPE:
+ vxlan_gpe = (struct rte_vxlan_gpe_hdr *)&buf[temp_size];
+ if (!udp)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ (void *)items->type,
+ "udp header not found");
+ if (!vxlan_gpe->proto)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ (void *)items->type,
+ "next protocol not found");
+ if (!udp->dst_port)
+ udp->dst_port =
+ RTE_BE16(MLX5_UDP_PORT_VXLAN_GPE);
+ if (!vxlan_gpe->vx_flags)
+ vxlan_gpe->vx_flags =
+ MLX5_ENCAP_VXLAN_GPE_FLAGS;
+ break;
+ case RTE_FLOW_ITEM_TYPE_GRE:
+ case RTE_FLOW_ITEM_TYPE_NVGRE:
+ gre = (struct rte_gre_hdr *)&buf[temp_size];
+ if (!gre->proto)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ (void *)items->type,
+ "next protocol not found");
+ if (!ipv4 && !ipv6)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ (void *)items->type,
+ "ip header not found");
+ if (ipv4 && !ipv4->next_proto_id)
+ ipv4->next_proto_id = IPPROTO_GRE;
+ else if (ipv6 && !ipv6->proto)
+ ipv6->proto = IPPROTO_GRE;
+ break;
+ case RTE_FLOW_ITEM_TYPE_VOID:
+ break;
+ default:
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ (void *)items->type,
+ "unsupported item type");
+ break;
+ }
+ temp_size += len;
+ }
+ *size = temp_size;
+ return 0;
+}
+
+static int
+flow_dv_zero_encap_udp_csum(void *data, struct rte_flow_error *error)
+{
+ struct rte_ether_hdr *eth = NULL;
+ struct rte_vlan_hdr *vlan = NULL;
+ struct rte_ipv6_hdr *ipv6 = NULL;
+ struct rte_udp_hdr *udp = NULL;
+ char *next_hdr;
+ uint16_t proto;
+
+ eth = (struct rte_ether_hdr *)data;
+ next_hdr = (char *)(eth + 1);
+ proto = RTE_BE16(eth->ether_type);
+
+ /* VLAN skipping */
+ while (proto == RTE_ETHER_TYPE_VLAN || proto == RTE_ETHER_TYPE_QINQ) {
+ vlan = (struct rte_vlan_hdr *)next_hdr;
+ proto = RTE_BE16(vlan->eth_proto);
+ next_hdr += sizeof(struct rte_vlan_hdr);
+ }
+
+ /* HW calculates IPv4 csum. no need to proceed */
+ if (proto == RTE_ETHER_TYPE_IPV4)
+ return 0;
+
+ /* non IPv4/IPv6 header. not supported */
+ if (proto != RTE_ETHER_TYPE_IPV6) {
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ NULL, "Cannot offload non IPv4/IPv6");
+ }
+
+ ipv6 = (struct rte_ipv6_hdr *)next_hdr;
+
+ /* ignore non UDP */
+ if (ipv6->proto != IPPROTO_UDP)
+ return 0;
+
+ udp = (struct rte_udp_hdr *)(ipv6 + 1);
+ udp->dgram_cksum = 0;
+
+ return 0;
+}
+
+/**
+ * Convert L2 encap action to DV specification.
+ *
+ * @param[in] dev
+ * Pointer to rte_eth_dev structure.
+ * @param[in] action
+ * Pointer to action structure.
+ * @param[in, out] dev_flow
+ * Pointer to the mlx5_flow.
+ * @param[in] transfer
+ * Mark if the flow is E-Switch flow.
+ * @param[out] error
+ * Pointer to the error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+flow_dv_create_action_l2_encap(struct rte_eth_dev *dev,
+ const struct rte_flow_action *action,
+ struct mlx5_flow *dev_flow,
+ uint8_t transfer,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item *encap_data;
+ const struct rte_flow_action_raw_encap *raw_encap_data;
+ struct mlx5_flow_dv_encap_decap_resource res = {
+ .reformat_type =
+ MLX5DV_FLOW_ACTION_PACKET_REFORMAT_TYPE_L2_TO_L2_TUNNEL,
+ .ft_type = transfer ? MLX5DV_FLOW_TABLE_TYPE_FDB :
+ MLX5DV_FLOW_TABLE_TYPE_NIC_TX,
+ };
+
+ if (action->type == RTE_FLOW_ACTION_TYPE_RAW_ENCAP) {
+ raw_encap_data =
+ (const struct rte_flow_action_raw_encap *)action->conf;
+ res.size = raw_encap_data->size;
+ memcpy(res.buf, raw_encap_data->data, res.size);
+ if (flow_dv_zero_encap_udp_csum(res.buf, error))
+ return -rte_errno;
+ } else {
+ if (action->type == RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP)
+ encap_data =
+ ((const struct rte_flow_action_vxlan_encap *)
+ action->conf)->definition;
+ else
+ encap_data =
+ ((const struct rte_flow_action_nvgre_encap *)
+ action->conf)->definition;
+ if (flow_dv_convert_encap_data(encap_data, res.buf,
+ &res.size, error))
+ return -rte_errno;
+ }
+ if (flow_dv_encap_decap_resource_register(dev, &res, dev_flow, error))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ NULL, "can't create L2 encap action");
+ return 0;
+}
+
+/**
+ * Convert L2 decap action to DV specification.
+ *
+ * @param[in] dev
+ * Pointer to rte_eth_dev structure.
+ * @param[in, out] dev_flow
+ * Pointer to the mlx5_flow.
+ * @param[in] transfer
+ * Mark if the flow is E-Switch flow.
+ * @param[out] error
+ * Pointer to the error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+flow_dv_create_action_l2_decap(struct rte_eth_dev *dev,
+ struct mlx5_flow *dev_flow,
+ uint8_t transfer,
+ struct rte_flow_error *error)
+{
+ struct mlx5_flow_dv_encap_decap_resource res = {
+ .size = 0,
+ .reformat_type =
+ MLX5DV_FLOW_ACTION_PACKET_REFORMAT_TYPE_L2_TUNNEL_TO_L2,
+ .ft_type = transfer ? MLX5DV_FLOW_TABLE_TYPE_FDB :
+ MLX5DV_FLOW_TABLE_TYPE_NIC_RX,
+ };
+
+ if (flow_dv_encap_decap_resource_register(dev, &res, dev_flow, error))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ NULL, "can't create L2 decap action");
+ return 0;
+}
+
+/**
+ * Convert raw decap/encap (L3 tunnel) action to DV specification.
+ *
+ * @param[in] dev
+ * Pointer to rte_eth_dev structure.
+ * @param[in] action
+ * Pointer to action structure.
+ * @param[in, out] dev_flow
+ * Pointer to the mlx5_flow.
+ * @param[in] attr
+ * Pointer to the flow attributes.
+ * @param[out] error
+ * Pointer to the error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+flow_dv_create_action_raw_encap(struct rte_eth_dev *dev,
+ const struct rte_flow_action *action,
+ struct mlx5_flow *dev_flow,
+ const struct rte_flow_attr *attr,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_action_raw_encap *encap_data;
+ struct mlx5_flow_dv_encap_decap_resource res;
+
+ encap_data = (const struct rte_flow_action_raw_encap *)action->conf;
+ res.size = encap_data->size;
+ memcpy(res.buf, encap_data->data, res.size);
+ res.reformat_type = attr->egress ?
+ MLX5DV_FLOW_ACTION_PACKET_REFORMAT_TYPE_L2_TO_L3_TUNNEL :
+ MLX5DV_FLOW_ACTION_PACKET_REFORMAT_TYPE_L3_TUNNEL_TO_L2;
+ if (attr->transfer)
+ res.ft_type = MLX5DV_FLOW_TABLE_TYPE_FDB;
+ else
+ res.ft_type = attr->egress ? MLX5DV_FLOW_TABLE_TYPE_NIC_TX :
+ MLX5DV_FLOW_TABLE_TYPE_NIC_RX;
+ if (flow_dv_encap_decap_resource_register(dev, &res, dev_flow, error))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ NULL, "can't create encap action");
+ return 0;
+}
+
+/**
+ * Create action push VLAN.
+ *
+ * @param[in] dev
+ * Pointer to rte_eth_dev structure.
+ * @param[in] vlan_tag
+ * the vlan tag to push to the Ethernet header.
+ * @param[in, out] dev_flow
+ * Pointer to the mlx5_flow.
+ * @param[in] attr
+ * Pointer to the flow attributes.
+ * @param[out] error
+ * Pointer to the error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+flow_dv_create_action_push_vlan(struct rte_eth_dev *dev,
+ const struct rte_flow_attr *attr,
+ const struct rte_vlan_hdr *vlan,
+ struct mlx5_flow *dev_flow,
+ struct rte_flow_error *error)
+{
+ struct mlx5_flow_dv_push_vlan_action_resource res;
+
+ res.vlan_tag =
+ rte_cpu_to_be_32(((uint32_t)vlan->eth_proto) << 16 |
+ vlan->vlan_tci);
+ if (attr->transfer)
+ res.ft_type = MLX5DV_FLOW_TABLE_TYPE_FDB;
+ else
+ res.ft_type = attr->egress ? MLX5DV_FLOW_TABLE_TYPE_NIC_TX :
+ MLX5DV_FLOW_TABLE_TYPE_NIC_RX;
+ return flow_dv_push_vlan_action_resource_register
+ (dev, &res, dev_flow, error);
+}
+
+/**
+ * Validate the modify-header actions.
+ *
+ * @param[in] action_flags
+ * Holds the actions detected until now.
+ * @param[in] action
+ * Pointer to the modify action.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+flow_dv_validate_action_modify_hdr(const uint64_t action_flags,
+ const struct rte_flow_action *action,
+ struct rte_flow_error *error)
+{
+ if (action->type != RTE_FLOW_ACTION_TYPE_DEC_TTL && !action->conf)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ NULL, "action configuration not set");
+ if (action_flags & MLX5_FLOW_ENCAP_ACTIONS)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't have encap action before"
+ " modify action");
+ return 0;
+}
+
+/**
+ * Validate the modify-header MAC address actions.
+ *
+ * @param[in] action_flags
+ * Holds the actions detected until now.
+ * @param[in] action
+ * Pointer to the modify action.
+ * @param[in] item_flags
+ * Holds the items detected.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+flow_dv_validate_action_modify_mac(const uint64_t action_flags,
+ const struct rte_flow_action *action,
+ const uint64_t item_flags,
+ struct rte_flow_error *error)
+{
+ int ret = 0;
+
+ ret = flow_dv_validate_action_modify_hdr(action_flags, action, error);
+ if (!ret) {
+ if (!(item_flags & MLX5_FLOW_LAYER_L2))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ NULL,
+ "no L2 item in pattern");
+ }
+ return ret;
+}
+
+/**
+ * Validate the modify-header IPv4 address actions.
+ *
+ * @param[in] action_flags
+ * Holds the actions detected until now.
+ * @param[in] action
+ * Pointer to the modify action.
+ * @param[in] item_flags
+ * Holds the items detected.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+flow_dv_validate_action_modify_ipv4(const uint64_t action_flags,
+ const struct rte_flow_action *action,
+ const uint64_t item_flags,
+ struct rte_flow_error *error)
+{
+ int ret = 0;
+
+ ret = flow_dv_validate_action_modify_hdr(action_flags, action, error);
+ if (!ret) {
+ if (!(item_flags & MLX5_FLOW_LAYER_L3_IPV4))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ NULL,
+ "no ipv4 item in pattern");
+ }
+ return ret;
+}
+
+/**
+ * Validate the modify-header IPv6 address actions.
+ *
+ * @param[in] action_flags
+ * Holds the actions detected until now.
+ * @param[in] action
+ * Pointer to the modify action.
+ * @param[in] item_flags
+ * Holds the items detected.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+flow_dv_validate_action_modify_ipv6(const uint64_t action_flags,
+ const struct rte_flow_action *action,
+ const uint64_t item_flags,
+ struct rte_flow_error *error)
+{
+ int ret = 0;
+
+ ret = flow_dv_validate_action_modify_hdr(action_flags, action, error);
+ if (!ret) {
+ if (!(item_flags & MLX5_FLOW_LAYER_L3_IPV6))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ NULL,
+ "no ipv6 item in pattern");
+ }
+ return ret;
+}
+
+/**
+ * Validate the modify-header TP actions.
+ *
+ * @param[in] action_flags
+ * Holds the actions detected until now.
+ * @param[in] action
+ * Pointer to the modify action.
+ * @param[in] item_flags
+ * Holds the items detected.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+flow_dv_validate_action_modify_tp(const uint64_t action_flags,
+ const struct rte_flow_action *action,
+ const uint64_t item_flags,
+ struct rte_flow_error *error)
+{
+ int ret = 0;
+
+ ret = flow_dv_validate_action_modify_hdr(action_flags, action, error);
+ if (!ret) {
+ if (!(item_flags & MLX5_FLOW_LAYER_L4))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ NULL, "no transport layer "
+ "in pattern");
+ }
+ return ret;
+}
+
+/**
+ * Validate the modify-header actions of increment/decrement
+ * TCP Sequence-number.
+ *
+ * @param[in] action_flags
+ * Holds the actions detected until now.
+ * @param[in] action
+ * Pointer to the modify action.
+ * @param[in] item_flags
+ * Holds the items detected.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+flow_dv_validate_action_modify_tcp_seq(const uint64_t action_flags,
+ const struct rte_flow_action *action,
+ const uint64_t item_flags,
+ struct rte_flow_error *error)
+{
+ int ret = 0;
+
+ ret = flow_dv_validate_action_modify_hdr(action_flags, action, error);
+ if (!ret) {
+ if (!(item_flags & MLX5_FLOW_LAYER_OUTER_L4_TCP))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ NULL, "no TCP item in"
+ " pattern");
+ if ((action->type == RTE_FLOW_ACTION_TYPE_INC_TCP_SEQ &&
+ (action_flags & MLX5_FLOW_ACTION_DEC_TCP_SEQ)) ||
+ (action->type == RTE_FLOW_ACTION_TYPE_DEC_TCP_SEQ &&
+ (action_flags & MLX5_FLOW_ACTION_INC_TCP_SEQ)))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ NULL,
+ "cannot decrease and increase"
+ " TCP sequence number"
+ " at the same time");
+ }
+ return ret;
+}
+
+/**
+ * Validate the modify-header actions of increment/decrement
+ * TCP Acknowledgment number.
+ *
+ * @param[in] action_flags
+ * Holds the actions detected until now.
+ * @param[in] action
+ * Pointer to the modify action.
+ * @param[in] item_flags
+ * Holds the items detected.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+flow_dv_validate_action_modify_tcp_ack(const uint64_t action_flags,
+ const struct rte_flow_action *action,
+ const uint64_t item_flags,
+ struct rte_flow_error *error)
+{
+ int ret = 0;
+
+ ret = flow_dv_validate_action_modify_hdr(action_flags, action, error);
+ if (!ret) {
+ if (!(item_flags & MLX5_FLOW_LAYER_OUTER_L4_TCP))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ NULL, "no TCP item in"
+ " pattern");
+ if ((action->type == RTE_FLOW_ACTION_TYPE_INC_TCP_ACK &&
+ (action_flags & MLX5_FLOW_ACTION_DEC_TCP_ACK)) ||
+ (action->type == RTE_FLOW_ACTION_TYPE_DEC_TCP_ACK &&
+ (action_flags & MLX5_FLOW_ACTION_INC_TCP_ACK)))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ NULL,
+ "cannot decrease and increase"
+ " TCP acknowledgment number"
+ " at the same time");
+ }
+ return ret;
+}
+
+/**
+ * Validate the modify-header TTL actions.
+ *
+ * @param[in] action_flags
+ * Holds the actions detected until now.
+ * @param[in] action
+ * Pointer to the modify action.
+ * @param[in] item_flags
+ * Holds the items detected.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+flow_dv_validate_action_modify_ttl(const uint64_t action_flags,
+ const struct rte_flow_action *action,
+ const uint64_t item_flags,
+ struct rte_flow_error *error)
+{
+ int ret = 0;
+
+ ret = flow_dv_validate_action_modify_hdr(action_flags, action, error);
+ if (!ret) {
+ if (!(item_flags & MLX5_FLOW_LAYER_L3))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ NULL,
+ "no IP protocol in pattern");
+ }
+ return ret;
+}
+
+/**
+ * Validate jump action.
+ *
+ * @param[in] action
+ * Pointer to the jump action.
+ * @param[in] action_flags
+ * Holds the actions detected until now.
+ * @param[in] attributes
+ * Pointer to flow attributes
+ * @param[in] external
+ * Action belongs to flow rule created by request external to PMD.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+flow_dv_validate_action_jump(const struct rte_flow_action *action,
+ uint64_t action_flags,
+ const struct rte_flow_attr *attributes,
+ bool external, struct rte_flow_error *error)
+{
+ uint32_t max_group = attributes->transfer ? MLX5_MAX_TABLES_FDB :
+ MLX5_MAX_TABLES;
+ uint32_t target_group, table;
+ int ret = 0;
+
+ if (action_flags & (MLX5_FLOW_FATE_ACTIONS |
+ MLX5_FLOW_FATE_ESWITCH_ACTIONS))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't have 2 fate actions in"
+ " same flow");
+ if (!action->conf)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ NULL, "action configuration not set");
+ target_group =
+ ((const struct rte_flow_action_jump *)action->conf)->group;
+ ret = mlx5_flow_group_to_table(attributes, external, target_group,
+ &table, error);
+ if (ret)
+ return ret;
+ if (table >= max_group)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ATTR_GROUP, NULL,
+ "target group index out of range");
+ if (attributes->group >= target_group)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "target group must be higher than"
+ " the current flow group");
+ return 0;
+}
+
+/*
+ * Validate the port_id action.
+ *
+ * @param[in] dev
+ * Pointer to rte_eth_dev structure.
+ * @param[in] action_flags
+ * Bit-fields that holds the actions detected until now.
+ * @param[in] action
+ * Port_id RTE action structure.
+ * @param[in] attr
+ * Attributes of flow that includes this action.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+flow_dv_validate_action_port_id(struct rte_eth_dev *dev,
+ uint64_t action_flags,
+ const struct rte_flow_action *action,
+ const struct rte_flow_attr *attr,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_action_port_id *port_id;
+ struct mlx5_priv *act_priv;
+ struct mlx5_priv *dev_priv;
+ uint16_t port;
+
+ if (!attr->transfer)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL,
+ "port id action is valid in transfer"
+ " mode only");
+ if (!action || !action->conf)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ NULL,
+ "port id action parameters must be"
+ " specified");
+ if (action_flags & (MLX5_FLOW_FATE_ACTIONS |
+ MLX5_FLOW_FATE_ESWITCH_ACTIONS))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can have only one fate actions in"
+ " a flow");
+ dev_priv = mlx5_dev_to_eswitch_info(dev);
+ if (!dev_priv)
+ return rte_flow_error_set(error, rte_errno,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL,
+ "failed to obtain E-Switch info");
+ port_id = action->conf;
+ port = port_id->original ? dev->data->port_id : port_id->id;
+ act_priv = mlx5_port_to_eswitch_info(port);
+ if (!act_priv)
+ return rte_flow_error_set
+ (error, rte_errno,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF, port_id,
+ "failed to obtain E-Switch port id for port");
+ if (act_priv->domain_id != dev_priv->domain_id)
+ return rte_flow_error_set
+ (error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "port does not belong to"
+ " E-Switch being configured");
+ return 0;
+}
+
+/**
+ * Find existing modify-header resource or create and register a new one.
+ *
+ * @param dev[in, out]
+ * Pointer to rte_eth_dev structure.
+ * @param[in, out] resource
+ * Pointer to modify-header resource.
+ * @parm[in, out] dev_flow
+ * Pointer to the dev_flow.
+ * @param[out] error
+ * pointer to error structure.
+ *
+ * @return
+ * 0 on success otherwise -errno and errno is set.
+ */
+static int
+flow_dv_modify_hdr_resource_register
+ (struct rte_eth_dev *dev,
+ struct mlx5_flow_dv_modify_hdr_resource *resource,
+ struct mlx5_flow *dev_flow,
+ struct rte_flow_error *error)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_ibv_shared *sh = priv->sh;
+ struct mlx5_flow_dv_modify_hdr_resource *cache_resource;
+ struct mlx5dv_dr_domain *ns;
+
+ if (resource->ft_type == MLX5DV_FLOW_TABLE_TYPE_FDB)
+ ns = sh->fdb_domain;
+ else if (resource->ft_type == MLX5DV_FLOW_TABLE_TYPE_NIC_TX)
+ ns = sh->tx_domain;
+ else
+ ns = sh->rx_domain;
+ resource->flags =
+ dev_flow->flow->group ? 0 : MLX5DV_DR_ACTION_FLAGS_ROOT_LEVEL;
+ /* Lookup a matching resource from cache. */
+ LIST_FOREACH(cache_resource, &sh->modify_cmds, next) {
+ if (resource->ft_type == cache_resource->ft_type &&
+ resource->actions_num == cache_resource->actions_num &&
+ resource->flags == cache_resource->flags &&
+ !memcmp((const void *)resource->actions,
+ (const void *)cache_resource->actions,
+ (resource->actions_num *
+ sizeof(resource->actions[0])))) {
+ DRV_LOG(DEBUG, "modify-header resource %p: refcnt %d++",
+ (void *)cache_resource,
+ rte_atomic32_read(&cache_resource->refcnt));
+ rte_atomic32_inc(&cache_resource->refcnt);
+ dev_flow->dv.modify_hdr = cache_resource;
+ return 0;
+ }
+ }
+ /* Register new modify-header resource. */
+ cache_resource = rte_calloc(__func__, 1, sizeof(*cache_resource), 0);
+ if (!cache_resource)
+ return rte_flow_error_set(error, ENOMEM,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
+ "cannot allocate resource memory");
+ *cache_resource = *resource;
+ cache_resource->verbs_action =
+ mlx5_glue->dv_create_flow_action_modify_header
+ (sh->ctx, cache_resource->ft_type,
+ ns, cache_resource->flags,
+ cache_resource->actions_num *
+ sizeof(cache_resource->actions[0]),
+ (uint64_t *)cache_resource->actions);
+ if (!cache_resource->verbs_action) {
+ rte_free(cache_resource);
+ return rte_flow_error_set(error, ENOMEM,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL, "cannot create action");
+ }
+ rte_atomic32_init(&cache_resource->refcnt);
+ rte_atomic32_inc(&cache_resource->refcnt);
+ LIST_INSERT_HEAD(&sh->modify_cmds, cache_resource, next);
+ dev_flow->dv.modify_hdr = cache_resource;
+ DRV_LOG(DEBUG, "new modify-header resource %p: refcnt %d++",
+ (void *)cache_resource,
+ rte_atomic32_read(&cache_resource->refcnt));
+ return 0;
+}
+
+#define MLX5_CNT_CONTAINER_RESIZE 64
+
+/**
+ * Get or create a flow counter.
+ *
+ * @param[in] dev
+ * Pointer to the Ethernet device structure.
+ * @param[in] shared
+ * Indicate if this counter is shared with other flows.
+ * @param[in] id
+ * Counter identifier.
+ *
+ * @return
+ * pointer to flow counter on success, NULL otherwise and rte_errno is set.
+ */
+static struct mlx5_flow_counter *
+flow_dv_counter_alloc_fallback(struct rte_eth_dev *dev, uint32_t shared,
+ uint32_t id)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_flow_counter *cnt = NULL;
+ struct mlx5_devx_obj *dcs = NULL;
+
+ if (!priv->config.devx) {
+ rte_errno = ENOTSUP;
+ return NULL;
+ }
+ if (shared) {
+ TAILQ_FOREACH(cnt, &priv->sh->cmng.flow_counters, next) {
+ if (cnt->shared && cnt->id == id) {
+ cnt->ref_cnt++;
+ return cnt;
+ }
+ }
+ }
+ dcs = mlx5_devx_cmd_flow_counter_alloc(priv->sh->ctx, 0);
+ if (!dcs)
+ return NULL;
+ cnt = rte_calloc(__func__, 1, sizeof(*cnt), 0);
+ if (!cnt) {
+ claim_zero(mlx5_devx_cmd_destroy(cnt->dcs));
+ rte_errno = ENOMEM;
+ return NULL;
+ }
+ struct mlx5_flow_counter tmpl = {
+ .shared = shared,
+ .ref_cnt = 1,
+ .id = id,
+ .dcs = dcs,
+ };
+ tmpl.action = mlx5_glue->dv_create_flow_action_counter(dcs->obj, 0);
+ if (!tmpl.action) {
+ claim_zero(mlx5_devx_cmd_destroy(cnt->dcs));
+ rte_errno = errno;
+ rte_free(cnt);
+ return NULL;
+ }
+ *cnt = tmpl;
+ TAILQ_INSERT_HEAD(&priv->sh->cmng.flow_counters, cnt, next);
+ return cnt;
+}
+
+/**
+ * Release a flow counter.
+ *
+ * @param[in] dev
+ * Pointer to the Ethernet device structure.
+ * @param[in] counter
+ * Pointer to the counter handler.
+ */
+static void
+flow_dv_counter_release_fallback(struct rte_eth_dev *dev,
+ struct mlx5_flow_counter *counter)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+
+ if (!counter)
+ return;
+ if (--counter->ref_cnt == 0) {
+ TAILQ_REMOVE(&priv->sh->cmng.flow_counters, counter, next);
+ claim_zero(mlx5_devx_cmd_destroy(counter->dcs));
+ rte_free(counter);
+ }
+}
+
+/**
+ * Query a devx flow counter.
+ *
+ * @param[in] dev
+ * Pointer to the Ethernet device structure.
+ * @param[in] cnt
+ * Pointer to the flow counter.
+ * @param[out] pkts
+ * The statistics value of packets.
+ * @param[out] bytes
+ * The statistics value of bytes.
+ *
+ * @return
+ * 0 on success, otherwise a negative errno value and rte_errno is set.
+ */
+static inline int
+_flow_dv_query_count_fallback(struct rte_eth_dev *dev __rte_unused,
+ struct mlx5_flow_counter *cnt, uint64_t *pkts,
+ uint64_t *bytes)
+{
+ return mlx5_devx_cmd_flow_counter_query(cnt->dcs, 0, 0, pkts, bytes,
+ 0, NULL, NULL, 0);
+}
+
+/**
+ * Get a pool by a counter.
+ *
+ * @param[in] cnt
+ * Pointer to the counter.
+ *
+ * @return
+ * The counter pool.
+ */
+static struct mlx5_flow_counter_pool *
+flow_dv_counter_pool_get(struct mlx5_flow_counter *cnt)
+{
+ if (!cnt->batch) {
+ cnt -= cnt->dcs->id % MLX5_COUNTERS_PER_POOL;
+ return (struct mlx5_flow_counter_pool *)cnt - 1;
+ }
+ return cnt->pool;
+}
+
+/**
+ * Get a pool by devx counter ID.
+ *
+ * @param[in] cont
+ * Pointer to the counter container.
+ * @param[in] id
+ * The counter devx ID.
+ *
+ * @return
+ * The counter pool pointer if exists, NULL otherwise,
+ */
+static struct mlx5_flow_counter_pool *
+flow_dv_find_pool_by_id(struct mlx5_pools_container *cont, int id)
+{
+ struct mlx5_flow_counter_pool *pool;
+
+ TAILQ_FOREACH(pool, &cont->pool_list, next) {
+ int base = (pool->min_dcs->id / MLX5_COUNTERS_PER_POOL) *
+ MLX5_COUNTERS_PER_POOL;
+
+ if (id >= base && id < base + MLX5_COUNTERS_PER_POOL)
+ return pool;
+ };
+ return NULL;
+}
+
+/**
+ * Allocate a new memory for the counter values wrapped by all the needed
+ * management.
+ *
+ * @param[in] dev
+ * Pointer to the Ethernet device structure.
+ * @param[in] raws_n
+ * The raw memory areas - each one for MLX5_COUNTERS_PER_POOL counters.
+ *
+ * @return
+ * The new memory management pointer on success, otherwise NULL and rte_errno
+ * is set.
+ */
+static struct mlx5_counter_stats_mem_mng *
+flow_dv_create_counter_stat_mem_mng(struct rte_eth_dev *dev, int raws_n)
+{
+ struct mlx5_ibv_shared *sh = ((struct mlx5_priv *)
+ (dev->data->dev_private))->sh;
+ struct mlx5_devx_mkey_attr mkey_attr;
+ struct mlx5_counter_stats_mem_mng *mem_mng;
+ volatile struct flow_counter_stats *raw_data;
+ int size = (sizeof(struct flow_counter_stats) *
+ MLX5_COUNTERS_PER_POOL +
+ sizeof(struct mlx5_counter_stats_raw)) * raws_n +
+ sizeof(struct mlx5_counter_stats_mem_mng);
+ uint8_t *mem = rte_calloc(__func__, 1, size, sysconf(_SC_PAGESIZE));
+ int i;
+
+ if (!mem) {
+ rte_errno = ENOMEM;
+ return NULL;
+ }
+ mem_mng = (struct mlx5_counter_stats_mem_mng *)(mem + size) - 1;
+ size = sizeof(*raw_data) * MLX5_COUNTERS_PER_POOL * raws_n;
+ mem_mng->umem = mlx5_glue->devx_umem_reg(sh->ctx, mem, size,
+ IBV_ACCESS_LOCAL_WRITE);
+ if (!mem_mng->umem) {
+ rte_errno = errno;
+ rte_free(mem);
+ return NULL;
+ }
+ mkey_attr.addr = (uintptr_t)mem;
+ mkey_attr.size = size;
+ mkey_attr.umem_id = mem_mng->umem->umem_id;
+ mkey_attr.pd = sh->pdn;
+ mem_mng->dm = mlx5_devx_cmd_mkey_create(sh->ctx, &mkey_attr);
+ if (!mem_mng->dm) {
+ mlx5_glue->devx_umem_dereg(mem_mng->umem);
+ rte_errno = errno;
+ rte_free(mem);
+ return NULL;
+ }
+ mem_mng->raws = (struct mlx5_counter_stats_raw *)(mem + size);
+ raw_data = (volatile struct flow_counter_stats *)mem;
+ for (i = 0; i < raws_n; ++i) {
+ mem_mng->raws[i].mem_mng = mem_mng;
+ mem_mng->raws[i].data = raw_data + i * MLX5_COUNTERS_PER_POOL;
+ }
+ LIST_INSERT_HEAD(&sh->cmng.mem_mngs, mem_mng, next);
+ return mem_mng;
+}
+
+/**
+ * Resize a counter container.
+ *
+ * @param[in] dev
+ * Pointer to the Ethernet device structure.
+ * @param[in] batch
+ * Whether the pool is for counter that was allocated by batch command.
+ *
+ * @return
+ * The new container pointer on success, otherwise NULL and rte_errno is set.
+ */
+static struct mlx5_pools_container *
+flow_dv_container_resize(struct rte_eth_dev *dev, uint32_t batch)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_pools_container *cont =
+ MLX5_CNT_CONTAINER(priv->sh, batch, 0);
+ struct mlx5_pools_container *new_cont =
+ MLX5_CNT_CONTAINER_UNUSED(priv->sh, batch, 0);
+ struct mlx5_counter_stats_mem_mng *mem_mng;
+ uint32_t resize = cont->n + MLX5_CNT_CONTAINER_RESIZE;
+ uint32_t mem_size = sizeof(struct mlx5_flow_counter_pool *) * resize;
+ int i;
+
+ if (cont != MLX5_CNT_CONTAINER(priv->sh, batch, 1)) {
+ /* The last resize still hasn't detected by the host thread. */
+ rte_errno = EAGAIN;
+ return NULL;
+ }
+ new_cont->pools = rte_calloc(__func__, 1, mem_size, 0);
+ if (!new_cont->pools) {
+ rte_errno = ENOMEM;
+ return NULL;
+ }
+ if (cont->n)
+ memcpy(new_cont->pools, cont->pools, cont->n *
+ sizeof(struct mlx5_flow_counter_pool *));
+ mem_mng = flow_dv_create_counter_stat_mem_mng(dev,
+ MLX5_CNT_CONTAINER_RESIZE + MLX5_MAX_PENDING_QUERIES);
+ if (!mem_mng) {
+ rte_free(new_cont->pools);
+ return NULL;
+ }
+ for (i = 0; i < MLX5_MAX_PENDING_QUERIES; ++i)
+ LIST_INSERT_HEAD(&priv->sh->cmng.free_stat_raws,
+ mem_mng->raws + MLX5_CNT_CONTAINER_RESIZE +
+ i, next);
+ new_cont->n = resize;
+ rte_atomic16_set(&new_cont->n_valid, rte_atomic16_read(&cont->n_valid));
+ TAILQ_INIT(&new_cont->pool_list);
+ TAILQ_CONCAT(&new_cont->pool_list, &cont->pool_list, next);
+ new_cont->init_mem_mng = mem_mng;
+ rte_cio_wmb();
+ /* Flip the master container. */
+ priv->sh->cmng.mhi[batch] ^= (uint8_t)1;
+ return new_cont;
+}
+
+/**
+ * Query a devx flow counter.
+ *
+ * @param[in] dev
+ * Pointer to the Ethernet device structure.
+ * @param[in] cnt
+ * Pointer to the flow counter.
+ * @param[out] pkts
+ * The statistics value of packets.
+ * @param[out] bytes
+ * The statistics value of bytes.
+ *
+ * @return
+ * 0 on success, otherwise a negative errno value and rte_errno is set.
+ */
+static inline int
+_flow_dv_query_count(struct rte_eth_dev *dev,
+ struct mlx5_flow_counter *cnt, uint64_t *pkts,
+ uint64_t *bytes)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_flow_counter_pool *pool =
+ flow_dv_counter_pool_get(cnt);
+ int offset = cnt - &pool->counters_raw[0];
+
+ if (priv->counter_fallback)
+ return _flow_dv_query_count_fallback(dev, cnt, pkts, bytes);
+
+ rte_spinlock_lock(&pool->sl);
+ /*
+ * The single counters allocation may allocate smaller ID than the
+ * current allocated in parallel to the host reading.
+ * In this case the new counter values must be reported as 0.
+ */
+ if (unlikely(!cnt->batch && cnt->dcs->id < pool->raw->min_dcs_id)) {
+ *pkts = 0;
+ *bytes = 0;
+ } else {
+ *pkts = rte_be_to_cpu_64(pool->raw->data[offset].hits);
+ *bytes = rte_be_to_cpu_64(pool->raw->data[offset].bytes);
+ }
+ rte_spinlock_unlock(&pool->sl);
+ return 0;
+}
+
+/**
+ * Create and initialize a new counter pool.
+ *
+ * @param[in] dev
+ * Pointer to the Ethernet device structure.
+ * @param[out] dcs
+ * The devX counter handle.
+ * @param[in] batch
+ * Whether the pool is for counter that was allocated by batch command.
+ *
+ * @return
+ * A new pool pointer on success, NULL otherwise and rte_errno is set.
+ */
+static struct mlx5_flow_counter_pool *
+flow_dv_pool_create(struct rte_eth_dev *dev, struct mlx5_devx_obj *dcs,
+ uint32_t batch)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_flow_counter_pool *pool;
+ struct mlx5_pools_container *cont = MLX5_CNT_CONTAINER(priv->sh, batch,
+ 0);
+ int16_t n_valid = rte_atomic16_read(&cont->n_valid);
+ uint32_t size;
+
+ if (cont->n == n_valid) {
+ cont = flow_dv_container_resize(dev, batch);
+ if (!cont)
+ return NULL;
+ }
+ size = sizeof(*pool) + MLX5_COUNTERS_PER_POOL *
+ sizeof(struct mlx5_flow_counter);
+ pool = rte_calloc(__func__, 1, size, 0);
+ if (!pool) {
+ rte_errno = ENOMEM;
+ return NULL;
+ }
+ pool->min_dcs = dcs;
+ pool->raw = cont->init_mem_mng->raws + n_valid %
+ MLX5_CNT_CONTAINER_RESIZE;
+ pool->raw_hw = NULL;
+ rte_spinlock_init(&pool->sl);
+ /*
+ * The generation of the new allocated counters in this pool is 0, 2 in
+ * the pool generation makes all the counters valid for allocation.
+ */
+ rte_atomic64_set(&pool->query_gen, 0x2);
+ TAILQ_INIT(&pool->counters);
+ TAILQ_INSERT_TAIL(&cont->pool_list, pool, next);
+ cont->pools[n_valid] = pool;
+ /* Pool initialization must be updated before host thread access. */
+ rte_cio_wmb();
+ rte_atomic16_add(&cont->n_valid, 1);
+ return pool;
+}
+
+/**
+ * Prepare a new counter and/or a new counter pool.
+ *
+ * @param[in] dev
+ * Pointer to the Ethernet device structure.
+ * @param[out] cnt_free
+ * Where to put the pointer of a new counter.
+ * @param[in] batch
+ * Whether the pool is for counter that was allocated by batch command.
+ *
+ * @return
+ * The free counter pool pointer and @p cnt_free is set on success,
+ * NULL otherwise and rte_errno is set.
+ */
+static struct mlx5_flow_counter_pool *
+flow_dv_counter_pool_prepare(struct rte_eth_dev *dev,
+ struct mlx5_flow_counter **cnt_free,
+ uint32_t batch)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_flow_counter_pool *pool;
+ struct mlx5_devx_obj *dcs = NULL;
+ struct mlx5_flow_counter *cnt;
+ uint32_t i;
+
+ if (!batch) {
+ /* bulk_bitmap must be 0 for single counter allocation. */
+ dcs = mlx5_devx_cmd_flow_counter_alloc(priv->sh->ctx, 0);
+ if (!dcs)
+ return NULL;
+ pool = flow_dv_find_pool_by_id
+ (MLX5_CNT_CONTAINER(priv->sh, batch, 0), dcs->id);
+ if (!pool) {
+ pool = flow_dv_pool_create(dev, dcs, batch);
+ if (!pool) {
+ mlx5_devx_cmd_destroy(dcs);
+ return NULL;
+ }
+ } else if (dcs->id < pool->min_dcs->id) {
+ rte_atomic64_set(&pool->a64_dcs,
+ (int64_t)(uintptr_t)dcs);
+ }
+ cnt = &pool->counters_raw[dcs->id % MLX5_COUNTERS_PER_POOL];
+ TAILQ_INSERT_HEAD(&pool->counters, cnt, next);
+ cnt->dcs = dcs;
+ *cnt_free = cnt;
+ return pool;
+ }
+ /* bulk_bitmap is in 128 counters units. */
+ if (priv->config.hca_attr.flow_counter_bulk_alloc_bitmap & 0x4)
+ dcs = mlx5_devx_cmd_flow_counter_alloc(priv->sh->ctx, 0x4);
+ if (!dcs) {
+ rte_errno = ENODATA;
+ return NULL;
+ }
+ pool = flow_dv_pool_create(dev, dcs, batch);
+ if (!pool) {
+ mlx5_devx_cmd_destroy(dcs);
+ return NULL;
+ }
+ for (i = 0; i < MLX5_COUNTERS_PER_POOL; ++i) {
+ cnt = &pool->counters_raw[i];
+ cnt->pool = pool;
+ TAILQ_INSERT_HEAD(&pool->counters, cnt, next);
+ }
+ *cnt_free = &pool->counters_raw[0];
+ return pool;
+}
+
+/**
+ * Search for existed shared counter.
+ *
+ * @param[in] cont
+ * Pointer to the relevant counter pool container.
+ * @param[in] id
+ * The shared counter ID to search.
+ *
+ * @return
+ * NULL if not existed, otherwise pointer to the shared counter.
+ */
+static struct mlx5_flow_counter *
+flow_dv_counter_shared_search(struct mlx5_pools_container *cont,
+ uint32_t id)
+{
+ static struct mlx5_flow_counter *cnt;
+ struct mlx5_flow_counter_pool *pool;
+ int i;
+
+ TAILQ_FOREACH(pool, &cont->pool_list, next) {
+ for (i = 0; i < MLX5_COUNTERS_PER_POOL; ++i) {
+ cnt = &pool->counters_raw[i];
+ if (cnt->ref_cnt && cnt->shared && cnt->id == id)
+ return cnt;
+ }
+ }
+ return NULL;
+}
+
+/**
+ * Allocate a flow counter.
+ *
+ * @param[in] dev
+ * Pointer to the Ethernet device structure.
+ * @param[in] shared
+ * Indicate if this counter is shared with other flows.
+ * @param[in] id
+ * Counter identifier.
+ * @param[in] group
+ * Counter flow group.
+ *
+ * @return
+ * pointer to flow counter on success, NULL otherwise and rte_errno is set.
+ */
+static struct mlx5_flow_counter *
+flow_dv_counter_alloc(struct rte_eth_dev *dev, uint32_t shared, uint32_t id,
+ uint16_t group)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_flow_counter_pool *pool = NULL;
+ struct mlx5_flow_counter *cnt_free = NULL;
+ /*
+ * Currently group 0 flow counter cannot be assigned to a flow if it is
+ * not the first one in the batch counter allocation, so it is better
+ * to allocate counters one by one for these flows in a separate
+ * container.
+ * A counter can be shared between different groups so need to take
+ * shared counters from the single container.
+ */
+ uint32_t batch = (group && !shared) ? 1 : 0;
+ struct mlx5_pools_container *cont = MLX5_CNT_CONTAINER(priv->sh, batch,
+ 0);
+
+ if (priv->counter_fallback)
+ return flow_dv_counter_alloc_fallback(dev, shared, id);
+ if (!priv->config.devx) {
+ rte_errno = ENOTSUP;
+ return NULL;
+ }
+ if (shared) {
+ cnt_free = flow_dv_counter_shared_search(cont, id);
+ if (cnt_free) {
+ if (cnt_free->ref_cnt + 1 == 0) {
+ rte_errno = E2BIG;
+ return NULL;
+ }
+ cnt_free->ref_cnt++;
+ return cnt_free;
+ }
+ }
+ /* Pools which has a free counters are in the start. */
+ TAILQ_FOREACH(pool, &cont->pool_list, next) {
+ /*
+ * The free counter reset values must be updated between the
+ * counter release to the counter allocation, so, at least one
+ * query must be done in this time. ensure it by saving the
+ * query generation in the release time.
+ * The free list is sorted according to the generation - so if
+ * the first one is not updated, all the others are not
+ * updated too.
+ */
+ cnt_free = TAILQ_FIRST(&pool->counters);
+ if (cnt_free && cnt_free->query_gen + 1 <
+ rte_atomic64_read(&pool->query_gen))
+ break;
+ cnt_free = NULL;
+ }
+ if (!cnt_free) {
+ pool = flow_dv_counter_pool_prepare(dev, &cnt_free, batch);
+ if (!pool)
+ return NULL;
+ }
+ cnt_free->batch = batch;
+ /* Create a DV counter action only in the first time usage. */
+ if (!cnt_free->action) {
+ uint16_t offset;
+ struct mlx5_devx_obj *dcs;
+
+ if (batch) {
+ offset = cnt_free - &pool->counters_raw[0];
+ dcs = pool->min_dcs;
+ } else {
+ offset = 0;
+ dcs = cnt_free->dcs;
+ }
+ cnt_free->action = mlx5_glue->dv_create_flow_action_counter
+ (dcs->obj, offset);
+ if (!cnt_free->action) {
+ rte_errno = errno;
+ return NULL;
+ }
+ }
+ /* Update the counter reset values. */
+ if (_flow_dv_query_count(dev, cnt_free, &cnt_free->hits,
+ &cnt_free->bytes))
+ return NULL;
+ cnt_free->shared = shared;
+ cnt_free->ref_cnt = 1;
+ cnt_free->id = id;
+ if (!priv->sh->cmng.query_thread_on)
+ /* Start the asynchronous batch query by the host thread. */
+ mlx5_set_query_alarm(priv->sh);
+ TAILQ_REMOVE(&pool->counters, cnt_free, next);
+ if (TAILQ_EMPTY(&pool->counters)) {
+ /* Move the pool to the end of the container pool list. */
+ TAILQ_REMOVE(&cont->pool_list, pool, next);
+ TAILQ_INSERT_TAIL(&cont->pool_list, pool, next);
+ }
+ return cnt_free;
+}
+
+/**
+ * Release a flow counter.
+ *
+ * @param[in] dev
+ * Pointer to the Ethernet device structure.
+ * @param[in] counter
+ * Pointer to the counter handler.
+ */
+static void
+flow_dv_counter_release(struct rte_eth_dev *dev,
+ struct mlx5_flow_counter *counter)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+
+ if (!counter)
+ return;
+ if (priv->counter_fallback) {
+ flow_dv_counter_release_fallback(dev, counter);
+ return;
+ }
+ if (--counter->ref_cnt == 0) {
+ struct mlx5_flow_counter_pool *pool =
+ flow_dv_counter_pool_get(counter);
+
+ /* Put the counter in the end - the last updated one. */
+ TAILQ_INSERT_TAIL(&pool->counters, counter, next);
+ counter->query_gen = rte_atomic64_read(&pool->query_gen);
+ }
+}
+
+/**
+ * Verify the @p attributes will be correctly understood by the NIC and store
+ * them in the @p flow if everything is correct.
+ *
+ * @param[in] dev
+ * Pointer to dev struct.
+ * @param[in] attributes
+ * Pointer to flow attributes
+ * @param[in] external
+ * This flow rule is created by request external to PMD.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+flow_dv_validate_attributes(struct rte_eth_dev *dev,
+ const struct rte_flow_attr *attributes,
+ bool external __rte_unused,
+ struct rte_flow_error *error)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ uint32_t priority_max = priv->config.flow_prio - 1;
+
+#ifndef HAVE_MLX5DV_DR
+ if (attributes->group)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ATTR_GROUP,
+ NULL,
+ "groups are not supported");
+#else
+ uint32_t max_group = attributes->transfer ? MLX5_MAX_TABLES_FDB :
+ MLX5_MAX_TABLES;
+ uint32_t table;
+ int ret;
+
+ ret = mlx5_flow_group_to_table(attributes, external,
+ attributes->group,
+ &table, error);
+ if (ret)
+ return ret;
+ if (table >= max_group)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ATTR_GROUP, NULL,
+ "group index out of range");
+#endif
+ if (attributes->priority != MLX5_FLOW_PRIO_RSVD &&
+ attributes->priority >= priority_max)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ATTR_PRIORITY,
+ NULL,
+ "priority out of range");
+ if (attributes->transfer) {
+ if (!priv->config.dv_esw_en)
+ return rte_flow_error_set
+ (error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
+ "E-Switch dr is not supported");
+ if (!(priv->representor || priv->master))
+ return rte_flow_error_set
+ (error, EINVAL, RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL, "E-Switch configuration can only be"
+ " done by a master or a representor device");
+ if (attributes->egress)
+ return rte_flow_error_set
+ (error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ATTR_EGRESS, attributes,
+ "egress is not supported");
+ }
+ if (!(attributes->egress ^ attributes->ingress))
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ATTR, NULL,
+ "must specify exactly one of "
+ "ingress or egress");
+ return 0;
+}
+
+/**
+ * Internal validation function. For validating both actions and items.
+ *
+ * @param[in] dev
+ * Pointer to the rte_eth_dev structure.
+ * @param[in] attr
+ * Pointer to the flow attributes.
+ * @param[in] items
+ * Pointer to the list of items.
+ * @param[in] actions
+ * Pointer to the list of actions.
+ * @param[in] external
+ * This flow rule is created by request external to PMD.
+ * @param[out] error
+ * Pointer to the error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+flow_dv_validate(struct rte_eth_dev *dev, const struct rte_flow_attr *attr,
+ const struct rte_flow_item items[],
+ const struct rte_flow_action actions[],
+ bool external, struct rte_flow_error *error)
+{
+ int ret;
+ uint64_t action_flags = 0;
+ uint64_t item_flags = 0;
+ uint64_t last_item = 0;
+ uint8_t next_protocol = 0xff;
+ int actions_n = 0;
+ const struct rte_flow_item *gre_item = NULL;
+ struct rte_flow_item_tcp nic_tcp_mask = {
+ .hdr = {
+ .tcp_flags = 0xFF,
+ .src_port = RTE_BE16(UINT16_MAX),
+ .dst_port = RTE_BE16(UINT16_MAX),
+ }
+ };
+
+ if (items == NULL)
+ return -1;
+ ret = flow_dv_validate_attributes(dev, attr, external, error);
+ if (ret < 0)
+ return ret;
+ for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) {
+ int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
+ switch (items->type) {
+ case RTE_FLOW_ITEM_TYPE_VOID:
+ break;
+ case RTE_FLOW_ITEM_TYPE_PORT_ID:
+ ret = flow_dv_validate_item_port_id
+ (dev, items, attr, item_flags, error);
+ if (ret < 0)
+ return ret;
+ last_item = MLX5_FLOW_ITEM_PORT_ID;
+ break;
+ case RTE_FLOW_ITEM_TYPE_ETH:
+ ret = mlx5_flow_validate_item_eth(items, item_flags,
+ error);
+ if (ret < 0)
+ return ret;
+ last_item = tunnel ? MLX5_FLOW_LAYER_INNER_L2 :
+ MLX5_FLOW_LAYER_OUTER_L2;
+ break;
+ case RTE_FLOW_ITEM_TYPE_VLAN:
+ ret = mlx5_flow_validate_item_vlan(items, item_flags,
+ dev, error);
+ if (ret < 0)
+ return ret;
+ last_item = tunnel ? MLX5_FLOW_LAYER_INNER_VLAN :
+ MLX5_FLOW_LAYER_OUTER_VLAN;
+ break;
+ case RTE_FLOW_ITEM_TYPE_IPV4:
+ mlx5_flow_tunnel_ip_check(items, next_protocol,
+ &item_flags, &tunnel);
+ ret = mlx5_flow_validate_item_ipv4(items, item_flags,
+ NULL, error);
+ if (ret < 0)
+ return ret;
+ last_item = tunnel ? MLX5_FLOW_LAYER_INNER_L3_IPV4 :
+ MLX5_FLOW_LAYER_OUTER_L3_IPV4;
+ if (items->mask != NULL &&
+ ((const struct rte_flow_item_ipv4 *)
+ items->mask)->hdr.next_proto_id) {
+ next_protocol =
+ ((const struct rte_flow_item_ipv4 *)
+ (items->spec))->hdr.next_proto_id;
+ next_protocol &=
+ ((const struct rte_flow_item_ipv4 *)
+ (items->mask))->hdr.next_proto_id;
+ } else {
+ /* Reset for inner layer. */
+ next_protocol = 0xff;
+ }
+ break;
+ case RTE_FLOW_ITEM_TYPE_IPV6:
+ mlx5_flow_tunnel_ip_check(items, next_protocol,
+ &item_flags, &tunnel);
+ ret = mlx5_flow_validate_item_ipv6(items, item_flags,
+ NULL, error);
+ if (ret < 0)
+ return ret;
+ last_item = tunnel ? MLX5_FLOW_LAYER_INNER_L3_IPV6 :
+ MLX5_FLOW_LAYER_OUTER_L3_IPV6;
+ if (items->mask != NULL &&
+ ((const struct rte_flow_item_ipv6 *)
+ items->mask)->hdr.proto) {
+ next_protocol =
+ ((const struct rte_flow_item_ipv6 *)
+ items->spec)->hdr.proto;
+ next_protocol &=
+ ((const struct rte_flow_item_ipv6 *)
+ items->mask)->hdr.proto;
+ } else {
+ /* Reset for inner layer. */
+ next_protocol = 0xff;
+ }
+ break;
+ case RTE_FLOW_ITEM_TYPE_TCP:
+ ret = mlx5_flow_validate_item_tcp
+ (items, item_flags,
+ next_protocol,
+ &nic_tcp_mask,
+ error);
+ if (ret < 0)
+ return ret;
+ last_item = tunnel ? MLX5_FLOW_LAYER_INNER_L4_TCP :
+ MLX5_FLOW_LAYER_OUTER_L4_TCP;
+ break;
+ case RTE_FLOW_ITEM_TYPE_UDP:
+ ret = mlx5_flow_validate_item_udp(items, item_flags,
+ next_protocol,
+ error);
+ if (ret < 0)
+ return ret;
+ last_item = tunnel ? MLX5_FLOW_LAYER_INNER_L4_UDP :
+ MLX5_FLOW_LAYER_OUTER_L4_UDP;
+ break;
+ case RTE_FLOW_ITEM_TYPE_GRE:
+ ret = mlx5_flow_validate_item_gre(items, item_flags,
+ next_protocol, error);
+ if (ret < 0)
+ return ret;
+ gre_item = items;
+ last_item = MLX5_FLOW_LAYER_GRE;
+ break;
+ case RTE_FLOW_ITEM_TYPE_NVGRE:
+ ret = mlx5_flow_validate_item_nvgre(items, item_flags,
+ next_protocol,
+ error);
+ if (ret < 0)
+ return ret;
+ last_item = MLX5_FLOW_LAYER_NVGRE;
+ break;
+ case RTE_FLOW_ITEM_TYPE_GRE_KEY:
+ ret = mlx5_flow_validate_item_gre_key
+ (items, item_flags, gre_item, error);
+ if (ret < 0)
+ return ret;
+ last_item = MLX5_FLOW_LAYER_GRE_KEY;
+ break;
+ case RTE_FLOW_ITEM_TYPE_VXLAN:
+ ret = mlx5_flow_validate_item_vxlan(items, item_flags,
+ error);
+ if (ret < 0)
+ return ret;
+ last_item = MLX5_FLOW_LAYER_VXLAN;
+ break;
+ case RTE_FLOW_ITEM_TYPE_VXLAN_GPE:
+ ret = mlx5_flow_validate_item_vxlan_gpe(items,
+ item_flags, dev,
+ error);
+ if (ret < 0)
+ return ret;
+ last_item = MLX5_FLOW_LAYER_VXLAN_GPE;
+ break;
+ case RTE_FLOW_ITEM_TYPE_GENEVE:
+ ret = mlx5_flow_validate_item_geneve(items,
+ item_flags, dev,
+ error);
+ if (ret < 0)
+ return ret;
+ last_item = MLX5_FLOW_LAYER_VXLAN_GPE;
+ break;
+ case RTE_FLOW_ITEM_TYPE_MPLS:
+ ret = mlx5_flow_validate_item_mpls(dev, items,
+ item_flags,
+ last_item, error);
+ if (ret < 0)
+ return ret;
+ last_item = MLX5_FLOW_LAYER_MPLS;
+ break;
+ case RTE_FLOW_ITEM_TYPE_META:
+ ret = flow_dv_validate_item_meta(dev, items, attr,
+ error);
+ if (ret < 0)
+ return ret;
+ last_item = MLX5_FLOW_ITEM_METADATA;
+ break;
+ case RTE_FLOW_ITEM_TYPE_ICMP:
+ ret = mlx5_flow_validate_item_icmp(items, item_flags,
+ next_protocol,
+ error);
+ if (ret < 0)
+ return ret;
+ last_item = MLX5_FLOW_LAYER_ICMP;
+ break;
+ case RTE_FLOW_ITEM_TYPE_ICMP6:
+ ret = mlx5_flow_validate_item_icmp6(items, item_flags,
+ next_protocol,
+ error);
+ if (ret < 0)
+ return ret;
+ last_item = MLX5_FLOW_LAYER_ICMP6;
+ break;
+ default:
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM,
+ NULL, "item not supported");
+ }
+ item_flags |= last_item;
+ }
+ for (; actions->type != RTE_FLOW_ACTION_TYPE_END; actions++) {
+ if (actions_n == MLX5_DV_MAX_NUMBER_OF_ACTIONS)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ actions, "too many actions");
+ switch (actions->type) {
+ case RTE_FLOW_ACTION_TYPE_VOID:
+ break;
+ case RTE_FLOW_ACTION_TYPE_PORT_ID:
+ ret = flow_dv_validate_action_port_id(dev,
+ action_flags,
+ actions,
+ attr,
+ error);
+ if (ret)
+ return ret;
+ action_flags |= MLX5_FLOW_ACTION_PORT_ID;
+ ++actions_n;
+ break;
+ case RTE_FLOW_ACTION_TYPE_FLAG:
+ ret = mlx5_flow_validate_action_flag(action_flags,
+ attr, error);
+ if (ret < 0)
+ return ret;
+ action_flags |= MLX5_FLOW_ACTION_FLAG;
+ ++actions_n;
+ break;
+ case RTE_FLOW_ACTION_TYPE_MARK:
+ ret = mlx5_flow_validate_action_mark(actions,
+ action_flags,
+ attr, error);
+ if (ret < 0)
+ return ret;
+ action_flags |= MLX5_FLOW_ACTION_MARK;
+ ++actions_n;
+ break;
+ case RTE_FLOW_ACTION_TYPE_DROP:
+ ret = mlx5_flow_validate_action_drop(action_flags,
+ attr, error);
+ if (ret < 0)
+ return ret;
+ action_flags |= MLX5_FLOW_ACTION_DROP;
+ ++actions_n;
+ break;
+ case RTE_FLOW_ACTION_TYPE_QUEUE:
+ ret = mlx5_flow_validate_action_queue(actions,
+ action_flags, dev,
+ attr, error);
+ if (ret < 0)
+ return ret;
+ action_flags |= MLX5_FLOW_ACTION_QUEUE;
+ ++actions_n;
+ break;
+ case RTE_FLOW_ACTION_TYPE_RSS:
+ ret = mlx5_flow_validate_action_rss(actions,
+ action_flags, dev,
+ attr, item_flags,
+ error);
+ if (ret < 0)
+ return ret;
+ action_flags |= MLX5_FLOW_ACTION_RSS;
+ ++actions_n;
+ break;
+ case RTE_FLOW_ACTION_TYPE_COUNT:
+ ret = flow_dv_validate_action_count(dev, error);
+ if (ret < 0)
+ return ret;
+ action_flags |= MLX5_FLOW_ACTION_COUNT;
+ ++actions_n;
+ break;
+ case RTE_FLOW_ACTION_TYPE_OF_POP_VLAN:
+ if (flow_dv_validate_action_pop_vlan(dev,
+ action_flags,
+ actions,
+ item_flags, attr,
+ error))
+ return -rte_errno;
+ action_flags |= MLX5_FLOW_ACTION_OF_POP_VLAN;
+ ++actions_n;
+ break;
+ case RTE_FLOW_ACTION_TYPE_OF_PUSH_VLAN:
+ ret = flow_dv_validate_action_push_vlan(action_flags,
+ actions, attr,
+ error);
+ if (ret < 0)
+ return ret;
+ action_flags |= MLX5_FLOW_ACTION_OF_PUSH_VLAN;
+ ++actions_n;
+ break;
+ case RTE_FLOW_ACTION_TYPE_OF_SET_VLAN_PCP:
+ ret = flow_dv_validate_action_set_vlan_pcp
+ (action_flags, actions, error);
+ if (ret < 0)
+ return ret;
+ /* Count PCP with push_vlan command. */
+ break;
+ case RTE_FLOW_ACTION_TYPE_OF_SET_VLAN_VID:
+ ret = flow_dv_validate_action_set_vlan_vid
+ (item_flags, actions, error);
+ if (ret < 0)
+ return ret;
+ /* Count VID with push_vlan command. */
+ break;
+ case RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP:
+ case RTE_FLOW_ACTION_TYPE_NVGRE_ENCAP:
+ ret = flow_dv_validate_action_l2_encap(action_flags,
+ actions, attr,
+ error);
+ if (ret < 0)
+ return ret;
+ action_flags |= actions->type ==
+ RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP ?
+ MLX5_FLOW_ACTION_VXLAN_ENCAP :
+ MLX5_FLOW_ACTION_NVGRE_ENCAP;
+ ++actions_n;
+ break;
+ case RTE_FLOW_ACTION_TYPE_VXLAN_DECAP:
+ case RTE_FLOW_ACTION_TYPE_NVGRE_DECAP:
+ ret = flow_dv_validate_action_l2_decap(action_flags,
+ attr, error);
+ if (ret < 0)
+ return ret;
+ action_flags |= actions->type ==
+ RTE_FLOW_ACTION_TYPE_VXLAN_DECAP ?
+ MLX5_FLOW_ACTION_VXLAN_DECAP :
+ MLX5_FLOW_ACTION_NVGRE_DECAP;
+ ++actions_n;
+ break;
+ case RTE_FLOW_ACTION_TYPE_RAW_ENCAP:
+ ret = flow_dv_validate_action_raw_encap(action_flags,
+ actions, attr,
+ error);
+ if (ret < 0)
+ return ret;
+ action_flags |= MLX5_FLOW_ACTION_RAW_ENCAP;
+ ++actions_n;
+ break;
+ case RTE_FLOW_ACTION_TYPE_RAW_DECAP:
+ ret = flow_dv_validate_action_raw_decap(action_flags,
+ actions, attr,
+ error);
+ if (ret < 0)
+ return ret;
+ action_flags |= MLX5_FLOW_ACTION_RAW_DECAP;
+ ++actions_n;
+ break;
+ case RTE_FLOW_ACTION_TYPE_SET_MAC_SRC:
+ case RTE_FLOW_ACTION_TYPE_SET_MAC_DST:
+ ret = flow_dv_validate_action_modify_mac(action_flags,
+ actions,
+ item_flags,
+ error);
+ if (ret < 0)
+ return ret;
+ /* Count all modify-header actions as one action. */
+ if (!(action_flags & MLX5_FLOW_MODIFY_HDR_ACTIONS))
+ ++actions_n;
+ action_flags |= actions->type ==
+ RTE_FLOW_ACTION_TYPE_SET_MAC_SRC ?
+ MLX5_FLOW_ACTION_SET_MAC_SRC :
+ MLX5_FLOW_ACTION_SET_MAC_DST;
+ break;
+
+ case RTE_FLOW_ACTION_TYPE_SET_IPV4_SRC:
+ case RTE_FLOW_ACTION_TYPE_SET_IPV4_DST:
+ ret = flow_dv_validate_action_modify_ipv4(action_flags,
+ actions,
+ item_flags,
+ error);
+ if (ret < 0)
+ return ret;
+ /* Count all modify-header actions as one action. */
+ if (!(action_flags & MLX5_FLOW_MODIFY_HDR_ACTIONS))
+ ++actions_n;
+ action_flags |= actions->type ==
+ RTE_FLOW_ACTION_TYPE_SET_IPV4_SRC ?
+ MLX5_FLOW_ACTION_SET_IPV4_SRC :
+ MLX5_FLOW_ACTION_SET_IPV4_DST;
+ break;
+ case RTE_FLOW_ACTION_TYPE_SET_IPV6_SRC:
+ case RTE_FLOW_ACTION_TYPE_SET_IPV6_DST:
+ ret = flow_dv_validate_action_modify_ipv6(action_flags,
+ actions,
+ item_flags,
+ error);
+ if (ret < 0)
+ return ret;
+ /* Count all modify-header actions as one action. */
+ if (!(action_flags & MLX5_FLOW_MODIFY_HDR_ACTIONS))
+ ++actions_n;
+ action_flags |= actions->type ==
+ RTE_FLOW_ACTION_TYPE_SET_IPV6_SRC ?
+ MLX5_FLOW_ACTION_SET_IPV6_SRC :
+ MLX5_FLOW_ACTION_SET_IPV6_DST;
+ break;
+ case RTE_FLOW_ACTION_TYPE_SET_TP_SRC:
+ case RTE_FLOW_ACTION_TYPE_SET_TP_DST:
+ ret = flow_dv_validate_action_modify_tp(action_flags,
+ actions,
+ item_flags,
+ error);
+ if (ret < 0)
+ return ret;
+ /* Count all modify-header actions as one action. */
+ if (!(action_flags & MLX5_FLOW_MODIFY_HDR_ACTIONS))
+ ++actions_n;
+ action_flags |= actions->type ==
+ RTE_FLOW_ACTION_TYPE_SET_TP_SRC ?
+ MLX5_FLOW_ACTION_SET_TP_SRC :
+ MLX5_FLOW_ACTION_SET_TP_DST;
+ break;
+ case RTE_FLOW_ACTION_TYPE_DEC_TTL:
+ case RTE_FLOW_ACTION_TYPE_SET_TTL:
+ ret = flow_dv_validate_action_modify_ttl(action_flags,
+ actions,
+ item_flags,
+ error);
+ if (ret < 0)
+ return ret;
+ /* Count all modify-header actions as one action. */
+ if (!(action_flags & MLX5_FLOW_MODIFY_HDR_ACTIONS))
+ ++actions_n;
+ action_flags |= actions->type ==
+ RTE_FLOW_ACTION_TYPE_SET_TTL ?
+ MLX5_FLOW_ACTION_SET_TTL :
+ MLX5_FLOW_ACTION_DEC_TTL;
+ break;
+ case RTE_FLOW_ACTION_TYPE_JUMP:
+ ret = flow_dv_validate_action_jump(actions,
+ action_flags,
+ attr, external,
+ error);
+ if (ret)
+ return ret;
+ ++actions_n;
+ action_flags |= MLX5_FLOW_ACTION_JUMP;
+ break;
+ case RTE_FLOW_ACTION_TYPE_INC_TCP_SEQ:
+ case RTE_FLOW_ACTION_TYPE_DEC_TCP_SEQ:
+ ret = flow_dv_validate_action_modify_tcp_seq
+ (action_flags,
+ actions,
+ item_flags,
+ error);
+ if (ret < 0)
+ return ret;
+ /* Count all modify-header actions as one action. */
+ if (!(action_flags & MLX5_FLOW_MODIFY_HDR_ACTIONS))
+ ++actions_n;
+ action_flags |= actions->type ==
+ RTE_FLOW_ACTION_TYPE_INC_TCP_SEQ ?
+ MLX5_FLOW_ACTION_INC_TCP_SEQ :
+ MLX5_FLOW_ACTION_DEC_TCP_SEQ;
+ break;
+ case RTE_FLOW_ACTION_TYPE_INC_TCP_ACK:
+ case RTE_FLOW_ACTION_TYPE_DEC_TCP_ACK:
+ ret = flow_dv_validate_action_modify_tcp_ack
+ (action_flags,
+ actions,
+ item_flags,
+ error);
+ if (ret < 0)
+ return ret;
+ /* Count all modify-header actions as one action. */
+ if (!(action_flags & MLX5_FLOW_MODIFY_HDR_ACTIONS))
+ ++actions_n;
+ action_flags |= actions->type ==
+ RTE_FLOW_ACTION_TYPE_INC_TCP_ACK ?
+ MLX5_FLOW_ACTION_INC_TCP_ACK :
+ MLX5_FLOW_ACTION_DEC_TCP_ACK;
+ break;
+ default:
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ actions,
+ "action not supported");
+ }
+ }
+ if ((action_flags & MLX5_FLOW_LAYER_TUNNEL) &&
+ (action_flags & MLX5_FLOW_VLAN_ACTIONS))
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ actions,
+ "can't have vxlan and vlan"
+ " actions in the same rule");
+ /* Eswitch has few restrictions on using items and actions */
+ if (attr->transfer) {
+ if (action_flags & MLX5_FLOW_ACTION_FLAG)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ NULL,
+ "unsupported action FLAG");
+ if (action_flags & MLX5_FLOW_ACTION_MARK)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ NULL,
+ "unsupported action MARK");
+ if (action_flags & MLX5_FLOW_ACTION_QUEUE)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ NULL,
+ "unsupported action QUEUE");
+ if (action_flags & MLX5_FLOW_ACTION_RSS)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ NULL,
+ "unsupported action RSS");
+ if (!(action_flags & MLX5_FLOW_FATE_ESWITCH_ACTIONS))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ actions,
+ "no fate action is found");
+ } else {
+ if (!(action_flags & MLX5_FLOW_FATE_ACTIONS) && attr->ingress)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ actions,
+ "no fate action is found");
+ }
+ return 0;
+}
+
+/**
+ * Internal preparation function. Allocates the DV flow size,
+ * this size is constant.
+ *
+ * @param[in] attr
+ * Pointer to the flow attributes.
+ * @param[in] items
+ * Pointer to the list of items.
+ * @param[in] actions
+ * Pointer to the list of actions.
+ * @param[out] error
+ * Pointer to the error structure.
+ *
+ * @return
+ * Pointer to mlx5_flow object on success,
+ * otherwise NULL and rte_errno is set.
+ */
+static struct mlx5_flow *
+flow_dv_prepare(const struct rte_flow_attr *attr __rte_unused,
+ const struct rte_flow_item items[] __rte_unused,
+ const struct rte_flow_action actions[] __rte_unused,
+ struct rte_flow_error *error)
+{
+ uint32_t size = sizeof(struct mlx5_flow);
+ struct mlx5_flow *flow;
+
+ flow = rte_calloc(__func__, 1, size, 0);
+ if (!flow) {
+ rte_flow_error_set(error, ENOMEM,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
+ "not enough memory to create flow");
+ return NULL;
+ }
+ flow->dv.value.size = MLX5_ST_SZ_BYTES(fte_match_param);
+ return flow;
+}
+
+#ifndef NDEBUG
+/**
+ * Sanity check for match mask and value. Similar to check_valid_spec() in
+ * kernel driver. If unmasked bit is present in value, it returns failure.
+ *
+ * @param match_mask
+ * pointer to match mask buffer.
+ * @param match_value
+ * pointer to match value buffer.
+ *
+ * @return
+ * 0 if valid, -EINVAL otherwise.
+ */
+static int
+flow_dv_check_valid_spec(void *match_mask, void *match_value)
+{
+ uint8_t *m = match_mask;
+ uint8_t *v = match_value;
+ unsigned int i;
+
+ for (i = 0; i < MLX5_ST_SZ_BYTES(fte_match_param); ++i) {
+ if (v[i] & ~m[i]) {
+ DRV_LOG(ERR,
+ "match_value differs from match_criteria"
+ " %p[%u] != %p[%u]",
+ match_value, i, match_mask, i);
+ return -EINVAL;
+ }
+ }
+ return 0;
+}
+#endif
+
+/**
+ * Add Ethernet item to matcher and to the value.
+ *
+ * @param[in, out] matcher
+ * Flow matcher.
+ * @param[in, out] key
+ * Flow matcher value.
+ * @param[in] item
+ * Flow pattern to translate.
+ * @param[in] inner
+ * Item is inner pattern.
+ */
+static void
+flow_dv_translate_item_eth(void *matcher, void *key,
+ const struct rte_flow_item *item, int inner)
+{
+ const struct rte_flow_item_eth *eth_m = item->mask;
+ const struct rte_flow_item_eth *eth_v = item->spec;
+ const struct rte_flow_item_eth nic_mask = {
+ .dst.addr_bytes = "\xff\xff\xff\xff\xff\xff",
+ .src.addr_bytes = "\xff\xff\xff\xff\xff\xff",
+ .type = RTE_BE16(0xffff),
+ };
+ void *headers_m;
+ void *headers_v;
+ char *l24_v;
+ unsigned int i;
+
+ if (!eth_v)
+ return;
+ if (!eth_m)
+ eth_m = &nic_mask;
+ if (inner) {
+ headers_m = MLX5_ADDR_OF(fte_match_param, matcher,
+ inner_headers);
+ headers_v = MLX5_ADDR_OF(fte_match_param, key, inner_headers);
+ } else {
+ headers_m = MLX5_ADDR_OF(fte_match_param, matcher,
+ outer_headers);
+ headers_v = MLX5_ADDR_OF(fte_match_param, key, outer_headers);
+ }
+ memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_m, dmac_47_16),
+ ð_m->dst, sizeof(eth_m->dst));
+ /* The value must be in the range of the mask. */
+ l24_v = MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, dmac_47_16);
+ for (i = 0; i < sizeof(eth_m->dst); ++i)
+ l24_v[i] = eth_m->dst.addr_bytes[i] & eth_v->dst.addr_bytes[i];
+ memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_m, smac_47_16),
+ ð_m->src, sizeof(eth_m->src));
+ l24_v = MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, smac_47_16);
+ /* The value must be in the range of the mask. */
+ for (i = 0; i < sizeof(eth_m->dst); ++i)
+ l24_v[i] = eth_m->src.addr_bytes[i] & eth_v->src.addr_bytes[i];
+ MLX5_SET(fte_match_set_lyr_2_4, headers_m, ethertype,
+ rte_be_to_cpu_16(eth_m->type));
+ l24_v = MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, ethertype);
+ *(uint16_t *)(l24_v) = eth_m->type & eth_v->type;
+}
+
+/**
+ * Add VLAN item to matcher and to the value.
+ *
+ * @param[in, out] dev_flow
+ * Flow descriptor.
+ * @param[in, out] matcher
+ * Flow matcher.
+ * @param[in, out] key
+ * Flow matcher value.
+ * @param[in] item
+ * Flow pattern to translate.
+ * @param[in] inner
+ * Item is inner pattern.
+ */
+static void
+flow_dv_translate_item_vlan(struct mlx5_flow *dev_flow,
+ void *matcher, void *key,
+ const struct rte_flow_item *item,
+ int inner)
+{
+ const struct rte_flow_item_vlan *vlan_m = item->mask;
+ const struct rte_flow_item_vlan *vlan_v = item->spec;
+ void *headers_m;
+ void *headers_v;
+ uint16_t tci_m;
+ uint16_t tci_v;
+
+ if (!vlan_v)
+ return;
+ if (!vlan_m)
+ vlan_m = &rte_flow_item_vlan_mask;
+ if (inner) {
+ headers_m = MLX5_ADDR_OF(fte_match_param, matcher,
+ inner_headers);
+ headers_v = MLX5_ADDR_OF(fte_match_param, key, inner_headers);
+ } else {
+ headers_m = MLX5_ADDR_OF(fte_match_param, matcher,
+ outer_headers);
+ headers_v = MLX5_ADDR_OF(fte_match_param, key, outer_headers);
+ /*
+ * This is workaround, masks are not supported,
+ * and pre-validated.
+ */
+ dev_flow->dv.vf_vlan.tag =
+ rte_be_to_cpu_16(vlan_v->tci) & 0x0fff;
+ }
+ tci_m = rte_be_to_cpu_16(vlan_m->tci);
+ tci_v = rte_be_to_cpu_16(vlan_m->tci & vlan_v->tci);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_m, cvlan_tag, 1);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, cvlan_tag, 1);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_m, first_vid, tci_m);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_vid, tci_v);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_m, first_cfi, tci_m >> 12);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_cfi, tci_v >> 12);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_m, first_prio, tci_m >> 13);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_prio, tci_v >> 13);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_m, ethertype,
+ rte_be_to_cpu_16(vlan_m->inner_type));
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype,
+ rte_be_to_cpu_16(vlan_m->inner_type & vlan_v->inner_type));
+}
+
+/**
+ * Add IPV4 item to matcher and to the value.
+ *
+ * @param[in, out] matcher
+ * Flow matcher.
+ * @param[in, out] key
+ * Flow matcher value.
+ * @param[in] item
+ * Flow pattern to translate.
+ * @param[in] inner
+ * Item is inner pattern.
+ * @param[in] group
+ * The group to insert the rule.
+ */
+static void
+flow_dv_translate_item_ipv4(void *matcher, void *key,
+ const struct rte_flow_item *item,
+ int inner, uint32_t group)
+{
+ const struct rte_flow_item_ipv4 *ipv4_m = item->mask;
+ const struct rte_flow_item_ipv4 *ipv4_v = item->spec;
+ const struct rte_flow_item_ipv4 nic_mask = {
+ .hdr = {
+ .src_addr = RTE_BE32(0xffffffff),
+ .dst_addr = RTE_BE32(0xffffffff),
+ .type_of_service = 0xff,
+ .next_proto_id = 0xff,
+ },
+ };
+ void *headers_m;
+ void *headers_v;
+ char *l24_m;
+ char *l24_v;
+ uint8_t tos;
+
+ if (inner) {
+ headers_m = MLX5_ADDR_OF(fte_match_param, matcher,
+ inner_headers);
+ headers_v = MLX5_ADDR_OF(fte_match_param, key, inner_headers);
+ } else {
+ headers_m = MLX5_ADDR_OF(fte_match_param, matcher,
+ outer_headers);
+ headers_v = MLX5_ADDR_OF(fte_match_param, key, outer_headers);
+ }
+ if (group == 0)
+ MLX5_SET(fte_match_set_lyr_2_4, headers_m, ip_version, 0xf);
+ else
+ MLX5_SET(fte_match_set_lyr_2_4, headers_m, ip_version, 0x4);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_version, 4);
+ if (!ipv4_v)
+ return;
+ if (!ipv4_m)
+ ipv4_m = &nic_mask;
+ l24_m = MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_m,
+ dst_ipv4_dst_ipv6.ipv4_layout.ipv4);
+ l24_v = MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
+ dst_ipv4_dst_ipv6.ipv4_layout.ipv4);
+ *(uint32_t *)l24_m = ipv4_m->hdr.dst_addr;
+ *(uint32_t *)l24_v = ipv4_m->hdr.dst_addr & ipv4_v->hdr.dst_addr;
+ l24_m = MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_m,
+ src_ipv4_src_ipv6.ipv4_layout.ipv4);
+ l24_v = MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
+ src_ipv4_src_ipv6.ipv4_layout.ipv4);
+ *(uint32_t *)l24_m = ipv4_m->hdr.src_addr;
+ *(uint32_t *)l24_v = ipv4_m->hdr.src_addr & ipv4_v->hdr.src_addr;
+ tos = ipv4_m->hdr.type_of_service & ipv4_v->hdr.type_of_service;
+ MLX5_SET(fte_match_set_lyr_2_4, headers_m, ip_ecn,
+ ipv4_m->hdr.type_of_service);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_ecn, tos);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_m, ip_dscp,
+ ipv4_m->hdr.type_of_service >> 2);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_dscp, tos >> 2);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_m, ip_protocol,
+ ipv4_m->hdr.next_proto_id);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol,
+ ipv4_v->hdr.next_proto_id & ipv4_m->hdr.next_proto_id);
+}
+
+/**
+ * Add IPV6 item to matcher and to the value.
+ *
+ * @param[in, out] matcher
+ * Flow matcher.
+ * @param[in, out] key
+ * Flow matcher value.
+ * @param[in] item
+ * Flow pattern to translate.
+ * @param[in] inner
+ * Item is inner pattern.
+ * @param[in] group
+ * The group to insert the rule.
+ */
+static void
+flow_dv_translate_item_ipv6(void *matcher, void *key,
+ const struct rte_flow_item *item,
+ int inner, uint32_t group)
+{
+ const struct rte_flow_item_ipv6 *ipv6_m = item->mask;
+ const struct rte_flow_item_ipv6 *ipv6_v = item->spec;
+ const struct rte_flow_item_ipv6 nic_mask = {
+ .hdr = {
+ .src_addr =
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff",
+ .dst_addr =
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff",
+ .vtc_flow = RTE_BE32(0xffffffff),
+ .proto = 0xff,
+ .hop_limits = 0xff,
+ },
+ };
+ void *headers_m;
+ void *headers_v;
+ void *misc_m = MLX5_ADDR_OF(fte_match_param, matcher, misc_parameters);
+ void *misc_v = MLX5_ADDR_OF(fte_match_param, key, misc_parameters);
+ char *l24_m;
+ char *l24_v;
+ uint32_t vtc_m;
+ uint32_t vtc_v;
+ int i;
+ int size;
+
+ if (inner) {
+ headers_m = MLX5_ADDR_OF(fte_match_param, matcher,
+ inner_headers);
+ headers_v = MLX5_ADDR_OF(fte_match_param, key, inner_headers);
+ } else {
+ headers_m = MLX5_ADDR_OF(fte_match_param, matcher,
+ outer_headers);
+ headers_v = MLX5_ADDR_OF(fte_match_param, key, outer_headers);
+ }
+ if (group == 0)
+ MLX5_SET(fte_match_set_lyr_2_4, headers_m, ip_version, 0xf);
+ else
+ MLX5_SET(fte_match_set_lyr_2_4, headers_m, ip_version, 0x6);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_version, 6);
+ if (!ipv6_v)
+ return;
+ if (!ipv6_m)
+ ipv6_m = &nic_mask;
+ size = sizeof(ipv6_m->hdr.dst_addr);
+ l24_m = MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_m,
+ dst_ipv4_dst_ipv6.ipv6_layout.ipv6);
+ l24_v = MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
+ dst_ipv4_dst_ipv6.ipv6_layout.ipv6);
+ memcpy(l24_m, ipv6_m->hdr.dst_addr, size);
+ for (i = 0; i < size; ++i)
+ l24_v[i] = l24_m[i] & ipv6_v->hdr.dst_addr[i];
+ l24_m = MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_m,
+ src_ipv4_src_ipv6.ipv6_layout.ipv6);
+ l24_v = MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
+ src_ipv4_src_ipv6.ipv6_layout.ipv6);
+ memcpy(l24_m, ipv6_m->hdr.src_addr, size);
+ for (i = 0; i < size; ++i)
+ l24_v[i] = l24_m[i] & ipv6_v->hdr.src_addr[i];
+ /* TOS. */
+ vtc_m = rte_be_to_cpu_32(ipv6_m->hdr.vtc_flow);
+ vtc_v = rte_be_to_cpu_32(ipv6_m->hdr.vtc_flow & ipv6_v->hdr.vtc_flow);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_m, ip_ecn, vtc_m >> 20);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_ecn, vtc_v >> 20);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_m, ip_dscp, vtc_m >> 22);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_dscp, vtc_v >> 22);
+ /* Label. */
+ if (inner) {
+ MLX5_SET(fte_match_set_misc, misc_m, inner_ipv6_flow_label,
+ vtc_m);
+ MLX5_SET(fte_match_set_misc, misc_v, inner_ipv6_flow_label,
+ vtc_v);
+ } else {
+ MLX5_SET(fte_match_set_misc, misc_m, outer_ipv6_flow_label,
+ vtc_m);
+ MLX5_SET(fte_match_set_misc, misc_v, outer_ipv6_flow_label,
+ vtc_v);