+ } id = { .vlan_id = 0, };
+
+ if (!mask)
+ mask = &rte_flow_item_vxlan_gpe_mask;
+ if (spec) {
+ memcpy(&id.vni[1], spec->vni, 3);
+ vxlan_gpe.val.tunnel_id = id.vlan_id;
+ memcpy(&id.vni[1], mask->vni, 3);
+ vxlan_gpe.mask.tunnel_id = id.vlan_id;
+ /* Remove unwanted bits from values. */
+ vxlan_gpe.val.tunnel_id &= vxlan_gpe.mask.tunnel_id;
+ }
+ if (size <= flow_size) {
+ mlx5_flow_spec_verbs_add(flow, &vxlan_gpe, size);
+ flow->cur_verbs->attr->priority = MLX5_PRIORITY_MAP_L2;
+ }
+ flow->layers |= MLX5_FLOW_LAYER_VXLAN_GPE;
+ return size;
+}
+
+/**
+ * Update the protocol in Verbs IPv4/IPv6 spec.
+ *
+ * @param[in, out] attr
+ * Pointer to Verbs attributes structure.
+ * @param[in] search
+ * Specification type to search in order to update the IP protocol.
+ * @param[in] protocol
+ * Protocol value to set if none is present in the specification.
+ */
+static void
+mlx5_flow_item_gre_ip_protocol_update(struct ibv_flow_attr *attr,
+ enum ibv_flow_spec_type search,
+ uint8_t protocol)
+{
+ unsigned int i;
+ struct ibv_spec_header *hdr = (struct ibv_spec_header *)
+ ((uint8_t *)attr + sizeof(struct ibv_flow_attr));
+
+ if (!attr)
+ return;
+ for (i = 0; i != attr->num_of_specs; ++i) {
+ if (hdr->type == search) {
+ union {
+ struct ibv_flow_spec_ipv4_ext *ipv4;
+ struct ibv_flow_spec_ipv6 *ipv6;
+ } ip;
+
+ switch (search) {
+ case IBV_FLOW_SPEC_IPV4_EXT:
+ ip.ipv4 = (struct ibv_flow_spec_ipv4_ext *)hdr;
+ if (!ip.ipv4->val.proto) {
+ ip.ipv4->val.proto = protocol;
+ ip.ipv4->mask.proto = 0xff;
+ }
+ break;
+ case IBV_FLOW_SPEC_IPV6:
+ ip.ipv6 = (struct ibv_flow_spec_ipv6 *)hdr;
+ if (!ip.ipv6->val.next_hdr) {
+ ip.ipv6->val.next_hdr = protocol;
+ ip.ipv6->mask.next_hdr = 0xff;
+ }
+ break;
+ default:
+ break;
+ }
+ break;
+ }
+ hdr = (struct ibv_spec_header *)((uint8_t *)hdr + hdr->size);
+ }
+}
+
+/**
+ * Convert the @p item into a Verbs specification after ensuring the NIC
+ * will understand and process it correctly.
+ * It will also update the previous L3 layer with the protocol value matching
+ * the GRE.
+ * If the necessary size for the conversion is greater than the @p flow_size,
+ * nothing is written in @p flow, the validation is still performed.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param[in] item
+ * Item specification.
+ * @param[in, out] flow
+ * Pointer to flow structure.
+ * @param[in] flow_size
+ * Size in bytes of the available space in @p flow, if too small, nothing is
+ * written.
+ *
+ * @return
+ * On success the number of bytes consumed/necessary, if the returned value
+ * is lesser or equal to @p flow_size, the @p item has fully been converted,
+ * otherwise another call with this returned memory size should be done.
+ */
+static int
+mlx5_flow_item_gre(const struct rte_flow_item *item __rte_unused,
+ struct rte_flow *flow, const size_t flow_size)
+{
+ struct mlx5_flow_verbs *verbs = flow->cur_verbs;
+#ifdef HAVE_IBV_DEVICE_MPLS_SUPPORT
+ const struct rte_flow_item_gre *spec = item->spec;
+ const struct rte_flow_item_gre *mask = item->mask;
+ unsigned int size = sizeof(struct ibv_flow_spec_gre);
+ struct ibv_flow_spec_gre tunnel = {
+ .type = IBV_FLOW_SPEC_GRE,
+ .size = size,
+ };
+#else
+ unsigned int size = sizeof(struct ibv_flow_spec_tunnel);
+ struct ibv_flow_spec_tunnel tunnel = {
+ .type = IBV_FLOW_SPEC_VXLAN_TUNNEL,
+ .size = size,
+ };
+#endif
+
+#ifdef HAVE_IBV_DEVICE_MPLS_SUPPORT
+ if (!mask)
+ mask = &rte_flow_item_gre_mask;
+ if (spec) {
+ tunnel.val.c_ks_res0_ver = spec->c_rsvd0_ver;
+ tunnel.val.protocol = spec->protocol;
+ tunnel.mask.c_ks_res0_ver = mask->c_rsvd0_ver;
+ tunnel.mask.protocol = mask->protocol;
+ /* Remove unwanted bits from values. */
+ tunnel.val.c_ks_res0_ver &= tunnel.mask.c_ks_res0_ver;
+ tunnel.val.protocol &= tunnel.mask.protocol;
+ tunnel.val.key &= tunnel.mask.key;
+ }
+#else
+#endif /* !HAVE_IBV_DEVICE_MPLS_SUPPORT */
+ if (size <= flow_size) {
+ if (flow->layers & MLX5_FLOW_LAYER_OUTER_L3_IPV4)
+ mlx5_flow_item_gre_ip_protocol_update
+ (verbs->attr, IBV_FLOW_SPEC_IPV4_EXT,
+ MLX5_IP_PROTOCOL_GRE);
+ else
+ mlx5_flow_item_gre_ip_protocol_update
+ (verbs->attr, IBV_FLOW_SPEC_IPV6,
+ MLX5_IP_PROTOCOL_GRE);
+ mlx5_flow_spec_verbs_add(flow, &tunnel, size);
+ flow->cur_verbs->attr->priority = MLX5_PRIORITY_MAP_L2;
+ }
+ flow->layers |= MLX5_FLOW_LAYER_GRE;
+ return size;
+}
+
+/**
+ * Convert the @p item into a Verbs specification after ensuring the NIC
+ * will understand and process it correctly.
+ * If the necessary size for the conversion is greater than the @p flow_size,
+ * nothing is written in @p flow, the validation is still performed.
+ *
+ * @param[in] item
+ * Item specification.
+ * @param[in, out] flow
+ * Pointer to flow structure.
+ * @param[in] flow_size
+ * Size in bytes of the available space in @p flow, if too small, nothing is
+ * written.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * On success the number of bytes consumed/necessary, if the returned value
+ * is lesser or equal to @p flow_size, the @p item has fully been converted,
+ * otherwise another call with this returned memory size should be done.
+ * On error, a negative errno value is returned and rte_errno is set.
+ */
+static int
+mlx5_flow_item_mpls(const struct rte_flow_item *item __rte_unused,
+ struct rte_flow *flow __rte_unused,
+ const size_t flow_size __rte_unused,
+ struct rte_flow_error *error)
+{
+#ifdef HAVE_IBV_DEVICE_MPLS_SUPPORT
+ const struct rte_flow_item_mpls *spec = item->spec;
+ const struct rte_flow_item_mpls *mask = item->mask;
+ unsigned int size = sizeof(struct ibv_flow_spec_mpls);
+ struct ibv_flow_spec_mpls mpls = {
+ .type = IBV_FLOW_SPEC_MPLS,
+ .size = size,
+ };
+
+ if (!mask)
+ mask = &rte_flow_item_mpls_mask;
+ if (spec) {
+ memcpy(&mpls.val.label, spec, sizeof(mpls.val.label));
+ memcpy(&mpls.mask.label, mask, sizeof(mpls.mask.label));
+ /* Remove unwanted bits from values. */
+ mpls.val.label &= mpls.mask.label;
+ }
+ if (size <= flow_size) {
+ mlx5_flow_spec_verbs_add(flow, &mpls, size);
+ flow->cur_verbs->attr->priority = MLX5_PRIORITY_MAP_L2;
+ }
+ flow->layers |= MLX5_FLOW_LAYER_MPLS;
+ return size;
+#endif /* !HAVE_IBV_DEVICE_MPLS_SUPPORT */
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM,
+ item,
+ "MPLS is not supported by Verbs, please"
+ " update.");
+}
+
+/**
+ * Convert the @p pattern into a Verbs specifications after ensuring the NIC
+ * will understand and process it correctly.
+ * The conversion is performed item per item, each of them is written into
+ * the @p flow if its size is lesser or equal to @p flow_size.
+ * Validation and memory consumption computation are still performed until the
+ * end of @p pattern, unless an error is encountered.
+ *
+ * @param[in] pattern
+ * Flow pattern.
+ * @param[in, out] flow
+ * Pointer to the rte_flow structure.
+ * @param[in] flow_size
+ * Size in bytes of the available space in @p flow, if too small some
+ * garbage may be present.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * On success the number of bytes consumed/necessary, if the returned value
+ * is lesser or equal to @p flow_size, the @pattern has fully been
+ * converted, otherwise another call with this returned memory size should
+ * be done.
+ * On error, a negative errno value is returned and rte_errno is set.
+ */
+static int
+mlx5_flow_items(const struct rte_flow_item pattern[],
+ struct rte_flow *flow, const size_t flow_size,
+ struct rte_flow_error *error)
+{
+ int remain = flow_size;
+ size_t size = 0;
+
+ for (; pattern->type != RTE_FLOW_ITEM_TYPE_END; pattern++) {
+ int ret = 0;
+
+ switch (pattern->type) {
+ case RTE_FLOW_ITEM_TYPE_VOID:
+ break;
+ case RTE_FLOW_ITEM_TYPE_ETH:
+ ret = mlx5_flow_item_eth(pattern, flow, remain);
+ break;
+ case RTE_FLOW_ITEM_TYPE_VLAN:
+ ret = mlx5_flow_item_vlan(pattern, flow, remain);
+ break;
+ case RTE_FLOW_ITEM_TYPE_IPV4:
+ ret = mlx5_flow_item_ipv4(pattern, flow, remain);
+ break;
+ case RTE_FLOW_ITEM_TYPE_IPV6:
+ ret = mlx5_flow_item_ipv6(pattern, flow, remain);
+ break;
+ case RTE_FLOW_ITEM_TYPE_UDP:
+ ret = mlx5_flow_item_udp(pattern, flow, remain);
+ break;
+ case RTE_FLOW_ITEM_TYPE_TCP:
+ ret = mlx5_flow_item_tcp(pattern, flow, remain);
+ break;
+ case RTE_FLOW_ITEM_TYPE_VXLAN:
+ ret = mlx5_flow_item_vxlan(pattern, flow, remain);
+ break;
+ case RTE_FLOW_ITEM_TYPE_VXLAN_GPE:
+ ret = mlx5_flow_item_vxlan_gpe(pattern, flow,
+ remain);
+ break;
+ case RTE_FLOW_ITEM_TYPE_GRE:
+ ret = mlx5_flow_item_gre(pattern, flow, remain);
+ break;
+ case RTE_FLOW_ITEM_TYPE_MPLS:
+ ret = mlx5_flow_item_mpls(pattern, flow, remain, error);
+ break;
+ default:
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM,
+ pattern,
+ "item not supported");
+ }
+ if (ret < 0)
+ return ret;
+ if (remain > ret)
+ remain -= ret;
+ else
+ remain = 0;
+ size += ret;
+ }
+ if (!flow->layers) {
+ const struct rte_flow_item item = {
+ .type = RTE_FLOW_ITEM_TYPE_ETH,
+ };
+
+ return mlx5_flow_item_eth(&item, flow, flow_size);
+ }
+ return size;
+}
+
+/**
+ * Convert the @p action into a Verbs specification after ensuring the NIC
+ * will understand and process it correctly.
+ * If the necessary size for the conversion is greater than the @p flow_size,
+ * nothing is written in @p flow, the validation is still performed.
+ *
+ * @param[in, out] flow
+ * Pointer to flow structure.
+ * @param[in] flow_size
+ * Size in bytes of the available space in @p flow, if too small, nothing is
+ * written.
+ *
+ * @return
+ * On success the number of bytes consumed/necessary, if the returned value
+ * is lesser or equal to @p flow_size, the @p action has fully been
+ * converted, otherwise another call with this returned memory size should
+ * be done.
+ * On error, a negative errno value is returned and rte_errno is set.
+ */
+static int
+mlx5_flow_action_drop(struct rte_flow *flow, const size_t flow_size)
+{
+ unsigned int size = sizeof(struct ibv_flow_spec_action_drop);
+ struct ibv_flow_spec_action_drop drop = {
+ .type = IBV_FLOW_SPEC_ACTION_DROP,
+ .size = size,
+ };
+
+ if (size < flow_size)
+ mlx5_flow_spec_verbs_add(flow, &drop, size);
+ flow->fate |= MLX5_FLOW_FATE_DROP;
+ return size;
+}
+
+/**
+ * Convert the @p action into @p flow after ensuring the NIC will understand
+ * and process it correctly.
+ *
+ * @param[in] action
+ * Action configuration.
+ * @param[in, out] flow
+ * Pointer to flow structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_flow_action_queue(const struct rte_flow_action *action,
+ struct rte_flow *flow)
+{
+ const struct rte_flow_action_queue *queue = action->conf;
+
+ if (flow->queue)
+ (*flow->queue)[0] = queue->index;
+ flow->rss.queue_num = 1;
+ flow->fate |= MLX5_FLOW_FATE_QUEUE;
+ return 0;
+}
+
+/**
+ * Ensure the @p action will be understood and used correctly by the NIC.
+ *
+ * @param[in] action
+ * Action configuration.
+ * @param flow[in, out]
+ * Pointer to the rte_flow structure.
+ *
+ * @return
+ * 0 On success.
+ */
+static int
+mlx5_flow_action_rss(const struct rte_flow_action *action,
+ struct rte_flow *flow)
+{
+ const struct rte_flow_action_rss *rss = action->conf;
+
+ if (flow->queue)
+ memcpy((*flow->queue), rss->queue,
+ rss->queue_num * sizeof(uint16_t));
+ flow->rss.queue_num = rss->queue_num;
+ memcpy(flow->key, rss->key, MLX5_RSS_HASH_KEY_LEN);
+ flow->rss.types = rss->types;
+ flow->rss.level = rss->level;
+ flow->fate |= MLX5_FLOW_FATE_RSS;
+ return 0;
+}
+
+/**
+ * Convert the @p action into a Verbs specification after ensuring the NIC
+ * will understand and process it correctly.
+ * If the necessary size for the conversion is greater than the @p flow_size,
+ * nothing is written in @p flow, the validation is still performed.
+ *
+ * @param[in, out] flow
+ * Pointer to flow structure.
+ * @param[in] flow_size
+ * Size in bytes of the available space in @p flow, if too small, nothing is
+ * written.
+ *
+ * @return
+ * On success the number of bytes consumed/necessary, if the returned value
+ * is lesser or equal to @p flow_size, the @p action has fully been
+ * converted, otherwise another call with this returned memory size should
+ * be done.
+ */
+static int
+mlx5_flow_action_flag(struct rte_flow *flow, const size_t flow_size)
+{
+ unsigned int size = sizeof(struct ibv_flow_spec_action_tag);
+ struct ibv_flow_spec_action_tag tag = {
+ .type = IBV_FLOW_SPEC_ACTION_TAG,
+ .size = size,
+ .tag_id = mlx5_flow_mark_set(MLX5_FLOW_MARK_DEFAULT),
+ };
+ struct mlx5_flow_verbs *verbs = flow->cur_verbs;
+
+ if (flow->modifier & MLX5_FLOW_MOD_MARK)
+ size = 0;
+ else if (size <= flow_size && verbs)
+ mlx5_flow_spec_verbs_add(flow, &tag, size);
+ flow->modifier |= MLX5_FLOW_MOD_FLAG;
+ return size;
+}
+
+/**
+ * Update verbs specification to modify the flag to mark.
+ *
+ * @param[in, out] verbs
+ * Pointer to the mlx5_flow_verbs structure.
+ * @param[in] mark_id
+ * Mark identifier to replace the flag.
+ */
+static void
+mlx5_flow_verbs_mark_update(struct mlx5_flow_verbs *verbs, uint32_t mark_id)
+{
+ struct ibv_spec_header *hdr;
+ int i;
+
+ if (!verbs)
+ return;
+ /* Update Verbs specification. */
+ hdr = (struct ibv_spec_header *)verbs->specs;
+ if (!hdr)
+ return;
+ for (i = 0; i != verbs->attr->num_of_specs; ++i) {
+ if (hdr->type == IBV_FLOW_SPEC_ACTION_TAG) {
+ struct ibv_flow_spec_action_tag *t =
+ (struct ibv_flow_spec_action_tag *)hdr;
+
+ t->tag_id = mlx5_flow_mark_set(mark_id);
+ }
+ hdr = (struct ibv_spec_header *)((uintptr_t)hdr + hdr->size);
+ }
+}
+
+/**
+ * Convert the @p action into @p flow (or by updating the already present
+ * Flag Verbs specification) after ensuring the NIC will understand and
+ * process it correctly.
+ * If the necessary size for the conversion is greater than the @p flow_size,
+ * nothing is written in @p flow, the validation is still performed.
+ *
+ * @param[in] action
+ * Action configuration.
+ * @param[in, out] flow
+ * Pointer to flow structure.
+ * @param[in] flow_size
+ * Size in bytes of the available space in @p flow, if too small, nothing is
+ * written.
+ *
+ * @return
+ * On success the number of bytes consumed/necessary, if the returned value
+ * is lesser or equal to @p flow_size, the @p action has fully been
+ * converted, otherwise another call with this returned memory size should
+ * be done.
+ */
+static int
+mlx5_flow_action_mark(const struct rte_flow_action *action,
+ struct rte_flow *flow, const size_t flow_size)
+{
+ const struct rte_flow_action_mark *mark = action->conf;
+ unsigned int size = sizeof(struct ibv_flow_spec_action_tag);
+ struct ibv_flow_spec_action_tag tag = {
+ .type = IBV_FLOW_SPEC_ACTION_TAG,
+ .size = size,
+ };
+ struct mlx5_flow_verbs *verbs = flow->cur_verbs;
+
+ if (flow->modifier & MLX5_FLOW_MOD_FLAG) {
+ mlx5_flow_verbs_mark_update(verbs, mark->id);
+ size = 0;
+ } else if (size <= flow_size) {
+ tag.tag_id = mlx5_flow_mark_set(mark->id);
+ mlx5_flow_spec_verbs_add(flow, &tag, size);
+ }
+ flow->modifier |= MLX5_FLOW_MOD_MARK;
+ return size;
+}
+
+/**
+ * Convert the @p action into a Verbs specification after ensuring the NIC
+ * will understand and process it correctly.
+ * If the necessary size for the conversion is greater than the @p flow_size,
+ * nothing is written in @p flow, the validation is still performed.
+ *
+ * @param action[in]
+ * Action configuration.
+ * @param flow[in, out]
+ * Pointer to flow structure.
+ * @param flow_size[in]
+ * Size in bytes of the available space in @p flow, if too small, nothing is
+ * written.
+ * @param error[int, out]
+ * Pointer to error structure.
+ *
+ * @return
+ * On success the number of bytes consumed/necessary, if the returned value
+ * is lesser or equal to @p flow_size, the @p action has fully been
+ * converted, otherwise another call with this returned memory size should
+ * be done.
+ * On error, a negative errno value is returned and rte_errno is set.
+ */
+static int
+mlx5_flow_action_count(struct rte_eth_dev *dev,
+ const struct rte_flow_action *action,
+ struct rte_flow *flow,
+ const size_t flow_size __rte_unused,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_action_count *count = action->conf;
+#ifdef HAVE_IBV_DEVICE_COUNTERS_SET_SUPPORT
+ unsigned int size = sizeof(struct ibv_flow_spec_counter_action);
+ struct ibv_flow_spec_counter_action counter = {
+ .type = IBV_FLOW_SPEC_ACTION_COUNT,
+ .size = size,
+ };
+#endif
+
+ if (!flow->counter) {
+ flow->counter = mlx5_flow_counter_new(dev, count->shared,
+ count->id);
+ if (!flow->counter)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ action,
+ "cannot get counter"
+ " context.");
+ }
+ flow->modifier |= MLX5_FLOW_MOD_COUNT;
+#ifdef HAVE_IBV_DEVICE_COUNTERS_SET_SUPPORT
+ counter.counter_set_handle = flow->counter->cs->handle;
+ if (size <= flow_size)
+ mlx5_flow_spec_verbs_add(flow, &counter, size);
+ return size;
+#endif
+ return 0;
+}
+
+/**
+ * Convert the @p action into @p flow after ensuring the NIC will understand
+ * and process it correctly.
+ * The conversion is performed action per action, each of them is written into
+ * the @p flow if its size is lesser or equal to @p flow_size.
+ * Validation and memory consumption computation are still performed until the
+ * end of @p action, unless an error is encountered.
+ *
+ * @param[in] dev
+ * Pointer to Ethernet device structure.
+ * @param[in] actions
+ * Pointer to flow actions array.
+ * @param[in, out] flow
+ * Pointer to the rte_flow structure.
+ * @param[in] flow_size
+ * Size in bytes of the available space in @p flow, if too small some
+ * garbage may be present.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * On success the number of bytes consumed/necessary, if the returned value
+ * is lesser or equal to @p flow_size, the @p actions has fully been
+ * converted, otherwise another call with this returned memory size should
+ * be done.
+ * On error, a negative errno value is returned and rte_errno is set.
+ */
+static int
+mlx5_flow_actions(struct rte_eth_dev *dev,
+ const struct rte_flow_action actions[],
+ struct rte_flow *flow, const size_t flow_size,
+ struct rte_flow_error *error)
+{
+ size_t size = 0;
+ int remain = flow_size;
+ int ret = 0;
+
+ for (; actions->type != RTE_FLOW_ACTION_TYPE_END; actions++) {
+ switch (actions->type) {
+ case RTE_FLOW_ACTION_TYPE_VOID:
+ break;
+ case RTE_FLOW_ACTION_TYPE_FLAG:
+ ret = mlx5_flow_action_flag(flow, remain);
+ break;
+ case RTE_FLOW_ACTION_TYPE_MARK:
+ ret = mlx5_flow_action_mark(actions, flow, remain);
+ break;
+ case RTE_FLOW_ACTION_TYPE_DROP:
+ ret = mlx5_flow_action_drop(flow, remain);
+ break;
+ case RTE_FLOW_ACTION_TYPE_QUEUE:
+ ret = mlx5_flow_action_queue(actions, flow);
+ break;
+ case RTE_FLOW_ACTION_TYPE_RSS:
+ ret = mlx5_flow_action_rss(actions, flow);
+ break;
+ case RTE_FLOW_ACTION_TYPE_COUNT:
+ ret = mlx5_flow_action_count(dev, actions, flow, remain,
+ error);
+ break;
+ default:
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ actions,
+ "action not supported");
+ }
+ if (ret < 0)
+ return ret;
+ if (remain > ret)
+ remain -= ret;
+ else
+ remain = 0;
+ size += ret;
+ }
+ if (!flow->fate)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL,
+ "no fate action found");
+ return size;
+}
+
+/**
+ * Validate flow rule and fill flow structure accordingly.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param[out] flow
+ * Pointer to flow structure.
+ * @param flow_size
+ * Size of allocated space for @p flow.
+ * @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 positive value representing the size of the flow object in bytes
+ * regardless of @p flow_size on success, a negative errno value otherwise
+ * and rte_errno is set.
+ */
+static int
+mlx5_flow_merge_switch(struct rte_eth_dev *dev,
+ struct rte_flow *flow,
+ size_t flow_size,
+ const struct rte_flow_attr *attr,
+ const struct rte_flow_item pattern[],
+ const struct rte_flow_action actions[],
+ struct rte_flow_error *error)
+{
+ unsigned int n = mlx5_dev_to_port_id(dev->device, NULL, 0);
+ uint16_t port_id[!n + n];
+ struct mlx5_nl_flow_ptoi ptoi[!n + n + 1];
+ size_t off = RTE_ALIGN_CEIL(sizeof(*flow), alignof(max_align_t));
+ unsigned int i;
+ unsigned int own = 0;
+ int ret;
+
+ /* At least one port is needed when no switch domain is present. */
+ if (!n) {
+ n = 1;
+ port_id[0] = dev->data->port_id;
+ } else {
+ n = RTE_MIN(mlx5_dev_to_port_id(dev->device, port_id, n), n);
+ }
+ for (i = 0; i != n; ++i) {
+ struct rte_eth_dev_info dev_info;
+
+ rte_eth_dev_info_get(port_id[i], &dev_info);
+ if (port_id[i] == dev->data->port_id)
+ own = i;
+ ptoi[i].port_id = port_id[i];
+ ptoi[i].ifindex = dev_info.if_index;
+ }
+ /* Ensure first entry of ptoi[] is the current device. */
+ if (own) {
+ ptoi[n] = ptoi[0];
+ ptoi[0] = ptoi[own];
+ ptoi[own] = ptoi[n];
+ }
+ /* An entry with zero ifindex terminates ptoi[]. */
+ ptoi[n].port_id = 0;
+ ptoi[n].ifindex = 0;
+ if (flow_size < off)
+ flow_size = 0;
+ ret = mlx5_nl_flow_transpose((uint8_t *)flow + off,
+ flow_size ? flow_size - off : 0,
+ ptoi, attr, pattern, actions, error);
+ if (ret < 0)
+ return ret;
+ if (flow_size) {
+ *flow = (struct rte_flow){
+ .attributes = *attr,
+ .nl_flow = (uint8_t *)flow + off,
+ };
+ /*
+ * Generate a reasonably unique handle based on the address
+ * of the target buffer.
+ *
+ * This is straightforward on 32-bit systems where the flow
+ * pointer can be used directly. Otherwise, its least
+ * significant part is taken after shifting it by the
+ * previous power of two of the pointed buffer size.
+ */
+ if (sizeof(flow) <= 4)
+ mlx5_nl_flow_brand(flow->nl_flow, (uintptr_t)flow);
+ else
+ mlx5_nl_flow_brand
+ (flow->nl_flow,
+ (uintptr_t)flow >>
+ rte_log2_u32(rte_align32prevpow2(flow_size)));
+ }
+ return off + ret;
+}
+
+static unsigned int
+mlx5_find_graph_root(const struct rte_flow_item pattern[], uint32_t rss_level)
+{
+ const struct rte_flow_item *item;
+ unsigned int has_vlan = 0;
+
+ for (item = pattern; item->type != RTE_FLOW_ITEM_TYPE_END; item++) {
+ if (item->type == RTE_FLOW_ITEM_TYPE_VLAN) {
+ has_vlan = 1;
+ break;
+ }
+ }
+ if (has_vlan)
+ return rss_level < 2 ? MLX5_EXPANSION_ROOT_ETH_VLAN :
+ MLX5_EXPANSION_ROOT_OUTER_ETH_VLAN;
+ return rss_level < 2 ? MLX5_EXPANSION_ROOT :
+ MLX5_EXPANSION_ROOT_OUTER;
+}
+
+/**
+ * Convert the @p attributes, @p pattern, @p action, into an flow for the NIC
+ * after ensuring the NIC will understand and process it correctly.
+ * The conversion is only performed item/action per item/action, each of
+ * them is written into the @p flow if its size is lesser or equal to @p
+ * flow_size.
+ * Validation and memory consumption computation are still performed until the
+ * end, unless an error is encountered.
+ *
+ * @param[in] dev
+ * Pointer to Ethernet device.
+ * @param[in, out] flow
+ * Pointer to flow structure.
+ * @param[in] flow_size
+ * Size in bytes of the available space in @p flow, if too small some
+ * garbage may be present.
+ * @param[in] attributes
+ * 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
+ * On success the number of bytes consumed/necessary, if the returned value
+ * is lesser or equal to @p flow_size, the flow has fully been converted and
+ * can be applied, otherwise another call with this returned memory size
+ * should be done.
+ * On error, a negative errno value is returned and rte_errno is set.
+ */
+static int
+mlx5_flow_merge(struct rte_eth_dev *dev, struct rte_flow *flow,
+ const size_t flow_size,
+ const struct rte_flow_attr *attributes,
+ const struct rte_flow_item pattern[],
+ const struct rte_flow_action actions[],
+ struct rte_flow_error *error)
+{
+ struct rte_flow local_flow = { .layers = 0, };
+ size_t size = sizeof(*flow);
+ union {
+ struct rte_flow_expand_rss buf;
+ uint8_t buffer[2048];
+ } expand_buffer;
+ struct rte_flow_expand_rss *buf = &expand_buffer.buf;
+ struct mlx5_flow_verbs *original_verbs = NULL;
+ size_t original_verbs_size = 0;
+ uint32_t original_layers = 0;
+ int expanded_pattern_idx = 0;
+ int ret = 0;
+ uint32_t i;
+
+ if (attributes->transfer)
+ return mlx5_flow_merge_switch(dev, flow, flow_size,
+ attributes, pattern,
+ actions, error);
+ if (size > flow_size)
+ flow = &local_flow;
+ ret = mlx5_flow_attributes(dev->data->dev_private, attributes, flow);
+ if (ret < 0)
+ return ret;
+ ret = mlx5_flow_actions(dev, actions, &local_flow, 0, error);
+ if (ret < 0)
+ return ret;
+ if (local_flow.rss.types) {
+ unsigned int graph_root;
+
+ graph_root = mlx5_find_graph_root(pattern,
+ local_flow.rss.level);
+ ret = rte_flow_expand_rss(buf, sizeof(expand_buffer.buffer),
+ pattern, local_flow.rss.types,
+ mlx5_support_expansion,
+ graph_root);
+ assert(ret > 0 &&
+ (unsigned int)ret < sizeof(expand_buffer.buffer));
+ } else {
+ buf->entries = 1;
+ buf->entry[0].pattern = (void *)(uintptr_t)pattern;
+ }
+ size += RTE_ALIGN_CEIL(local_flow.rss.queue_num * sizeof(uint16_t),
+ sizeof(void *));
+ if (size <= flow_size)
+ flow->queue = (void *)(flow + 1);
+ LIST_INIT(&flow->verbs);
+ flow->layers = 0;
+ flow->modifier = 0;
+ flow->fate = 0;
+ for (i = 0; i != buf->entries; ++i) {
+ size_t off = size;
+ size_t off2;
+
+ flow->layers = original_layers;
+ size += sizeof(struct ibv_flow_attr) +
+ sizeof(struct mlx5_flow_verbs);
+ off2 = size;
+ if (size < flow_size) {
+ flow->cur_verbs = (void *)((uintptr_t)flow + off);
+ flow->cur_verbs->attr = (void *)(flow->cur_verbs + 1);
+ flow->cur_verbs->specs =
+ (void *)(flow->cur_verbs->attr + 1);
+ }
+ /* First iteration convert the pattern into Verbs. */
+ if (i == 0) {
+ /* Actions don't need to be converted several time. */
+ ret = mlx5_flow_actions(dev, actions, flow,
+ (size < flow_size) ?
+ flow_size - size : 0,
+ error);
+ if (ret < 0)
+ return ret;
+ size += ret;
+ } else {
+ /*
+ * Next iteration means the pattern has already been
+ * converted and an expansion is necessary to match
+ * the user RSS request. For that only the expanded
+ * items will be converted, the common part with the
+ * user pattern are just copied into the next buffer
+ * zone.
+ */
+ size += original_verbs_size;
+ if (size < flow_size) {
+ rte_memcpy(flow->cur_verbs->attr,
+ original_verbs->attr,
+ original_verbs_size +
+ sizeof(struct ibv_flow_attr));
+ flow->cur_verbs->size = original_verbs_size;
+ }
+ }
+ ret = mlx5_flow_items
+ ((const struct rte_flow_item *)
+ &buf->entry[i].pattern[expanded_pattern_idx],
+ flow,
+ (size < flow_size) ? flow_size - size : 0, error);
+ if (ret < 0)
+ return ret;
+ size += ret;
+ if (size <= flow_size) {
+ mlx5_flow_adjust_priority(dev, flow);
+ LIST_INSERT_HEAD(&flow->verbs, flow->cur_verbs, next);
+ }
+ /*
+ * Keep a pointer of the first verbs conversion and the layers
+ * it has encountered.
+ */
+ if (i == 0) {
+ original_verbs = flow->cur_verbs;
+ original_verbs_size = size - off2;
+ original_layers = flow->layers;
+ /*
+ * move the index of the expanded pattern to the
+ * first item not addressed yet.
+ */
+ if (pattern->type == RTE_FLOW_ITEM_TYPE_END) {
+ expanded_pattern_idx++;
+ } else {
+ const struct rte_flow_item *item = pattern;
+
+ for (item = pattern;
+ item->type != RTE_FLOW_ITEM_TYPE_END;
+ ++item)
+ expanded_pattern_idx++;
+ }
+ }
+ }
+ /* Restore the origin layers in the flow. */
+ flow->layers = original_layers;
+ return size;
+}
+
+/**
+ * Lookup and set the ptype in the data Rx part. A single Ptype can be used,
+ * if several tunnel rules are used on this queue, the tunnel ptype will be
+ * cleared.
+ *
+ * @param rxq_ctrl
+ * Rx queue to update.
+ */
+static void
+mlx5_flow_rxq_tunnel_ptype_update(struct mlx5_rxq_ctrl *rxq_ctrl)
+{
+ unsigned int i;
+ uint32_t tunnel_ptype = 0;
+
+ /* Look up for the ptype to use. */
+ for (i = 0; i != MLX5_FLOW_TUNNEL; ++i) {
+ if (!rxq_ctrl->flow_tunnels_n[i])
+ continue;
+ if (!tunnel_ptype) {
+ tunnel_ptype = tunnels_info[i].ptype;
+ } else {
+ tunnel_ptype = 0;
+ break;
+ }
+ }
+ rxq_ctrl->rxq.tunnel = tunnel_ptype;
+}
+
+/**
+ * Set the Rx queue flags (Mark/Flag and Tunnel Ptypes) according to the flow.
+ *
+ * @param[in] dev
+ * Pointer to Ethernet device.
+ * @param[in] flow
+ * Pointer to flow structure.
+ */
+static void
+mlx5_flow_rxq_flags_set(struct rte_eth_dev *dev, struct rte_flow *flow)
+{
+ struct priv *priv = dev->data->dev_private;
+ const int mark = !!(flow->modifier &
+ (MLX5_FLOW_MOD_FLAG | MLX5_FLOW_MOD_MARK));
+ const int tunnel = !!(flow->layers & MLX5_FLOW_LAYER_TUNNEL);
+ unsigned int i;
+
+ for (i = 0; i != flow->rss.queue_num; ++i) {
+ int idx = (*flow->queue)[i];
+ struct mlx5_rxq_ctrl *rxq_ctrl =
+ container_of((*priv->rxqs)[idx],
+ struct mlx5_rxq_ctrl, rxq);
+
+ if (mark) {
+ rxq_ctrl->rxq.mark = 1;
+ rxq_ctrl->flow_mark_n++;
+ }
+ if (tunnel) {
+ unsigned int j;
+
+ /* Increase the counter matching the flow. */
+ for (j = 0; j != MLX5_FLOW_TUNNEL; ++j) {
+ if ((tunnels_info[j].tunnel & flow->layers) ==
+ tunnels_info[j].tunnel) {
+ rxq_ctrl->flow_tunnels_n[j]++;
+ break;
+ }
+ }
+ mlx5_flow_rxq_tunnel_ptype_update(rxq_ctrl);
+ }
+ }
+}
+
+/**
+ * Clear the Rx queue flags (Mark/Flag and Tunnel Ptype) associated with the
+ * @p flow if no other flow uses it with the same kind of request.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param[in] flow
+ * Pointer to the flow.
+ */
+static void
+mlx5_flow_rxq_flags_trim(struct rte_eth_dev *dev, struct rte_flow *flow)
+{
+ struct priv *priv = dev->data->dev_private;
+ const int mark = !!(flow->modifier &
+ (MLX5_FLOW_MOD_FLAG | MLX5_FLOW_MOD_MARK));
+ const int tunnel = !!(flow->layers & MLX5_FLOW_LAYER_TUNNEL);
+ unsigned int i;
+
+ assert(dev->data->dev_started);
+ for (i = 0; i != flow->rss.queue_num; ++i) {
+ int idx = (*flow->queue)[i];
+ struct mlx5_rxq_ctrl *rxq_ctrl =
+ container_of((*priv->rxqs)[idx],
+ struct mlx5_rxq_ctrl, rxq);
+
+ if (mark) {
+ rxq_ctrl->flow_mark_n--;
+ rxq_ctrl->rxq.mark = !!rxq_ctrl->flow_mark_n;
+ }
+ if (tunnel) {
+ unsigned int j;
+
+ /* Decrease the counter matching the flow. */
+ for (j = 0; j != MLX5_FLOW_TUNNEL; ++j) {
+ if ((tunnels_info[j].tunnel & flow->layers) ==
+ tunnels_info[j].tunnel) {
+ rxq_ctrl->flow_tunnels_n[j]--;
+ break;
+ }
+ }
+ mlx5_flow_rxq_tunnel_ptype_update(rxq_ctrl);
+ }
+ }
+}
+
+/**
+ * Clear the Mark/Flag and Tunnel ptype information in all Rx queues.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ */
+static void
+mlx5_flow_rxq_flags_clear(struct rte_eth_dev *dev)
+{
+ struct priv *priv = dev->data->dev_private;
+ unsigned int i;
+
+ for (i = 0; i != priv->rxqs_n; ++i) {
+ struct mlx5_rxq_ctrl *rxq_ctrl;
+ unsigned int j;
+
+ if (!(*priv->rxqs)[i])
+ continue;
+ rxq_ctrl = container_of((*priv->rxqs)[i],
+ struct mlx5_rxq_ctrl, rxq);
+ rxq_ctrl->flow_mark_n = 0;
+ rxq_ctrl->rxq.mark = 0;
+ for (j = 0; j != MLX5_FLOW_TUNNEL; ++j)
+ rxq_ctrl->flow_tunnels_n[j] = 0;
+ rxq_ctrl->rxq.tunnel = 0;
+ }
+}
+
+/*
+ * Validate the flag action.
+ *
+ * @param[in] action_flags
+ * Bit-fields that holds the actions detected until now.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_flow_validate_action_flag(uint64_t action_flags,
+ struct rte_flow_error *error)
+{
+
+ if (action_flags & MLX5_FLOW_ACTION_DROP)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't drop and flag in same flow");
+ if (action_flags & MLX5_FLOW_ACTION_MARK)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't mark and flag in same flow");
+ if (action_flags & MLX5_FLOW_ACTION_FLAG)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't have 2 flag"
+ " actions in same flow");
+ return 0;
+}
+
+/*
+ * Validate the mark action.
+ *
+ * @param[in] action
+ * Pointer to the queue action.
+ * @param[in] action_flags
+ * Bit-fields that holds the actions detected until now.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_flow_validate_action_mark(const struct rte_flow_action *action,
+ uint64_t action_flags,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_action_mark *mark = action->conf;
+
+ if (!mark)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ action,
+ "configuration cannot be null");
+ if (mark->id >= MLX5_FLOW_MARK_MAX)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ &mark->id,
+ "mark id must in 0 <= id < "
+ RTE_STR(MLX5_FLOW_MARK_MAX));
+ if (action_flags & MLX5_FLOW_ACTION_DROP)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't drop and mark in same flow");
+ if (action_flags & MLX5_FLOW_ACTION_FLAG)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't flag and mark in same flow");
+ if (action_flags & MLX5_FLOW_ACTION_MARK)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't have 2 mark actions in same"
+ " flow");
+ return 0;
+}
+
+/*
+ * Validate the drop action.
+ *
+ * @param[in] action_flags
+ * Bit-fields that holds the actions detected until now.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_ernno is set.
+ */
+static int
+mlx5_flow_validate_action_drop(uint64_t action_flags,
+ struct rte_flow_error *error)
+{
+ if (action_flags & MLX5_FLOW_ACTION_FLAG)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't drop and flag in same flow");
+ if (action_flags & MLX5_FLOW_ACTION_MARK)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't drop and mark in same flow");
+ if (action_flags & MLX5_FLOW_FATE_ACTIONS)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't have 2 fate actions in"
+ " same flow");
+ return 0;
+}
+
+/*
+ * Validate the queue action.
+ *
+ * @param[in] action
+ * Pointer to the queue action.
+ * @param[in] action_flags
+ * Bit-fields that holds the actions detected until now.
+ * @param[in] dev
+ * Pointer to the Ethernet device structure.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_ernno is set.
+ */
+static int
+mlx5_flow_validate_action_queue(const struct rte_flow_action *action,
+ uint64_t action_flags,
+ struct rte_eth_dev *dev,
+ struct rte_flow_error *error)
+{
+ struct priv *priv = dev->data->dev_private;
+ const struct rte_flow_action_queue *queue = action->conf;
+
+ if (action_flags & MLX5_FLOW_FATE_ACTIONS)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't have 2 fate actions in"
+ " same flow");
+ if (queue->index >= priv->rxqs_n)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ &queue->index,
+ "queue index out of range");
+ if (!(*priv->rxqs)[queue->index])
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ &queue->index,
+ "queue is not configured");
+ return 0;
+}
+
+/*
+ * Validate the rss action.
+ *
+ * @param[in] action
+ * Pointer to the queue action.
+ * @param[in] action_flags
+ * Bit-fields that holds the actions detected until now.
+ * @param[in] dev
+ * Pointer to the Ethernet device structure.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_ernno is set.
+ */
+static int
+mlx5_flow_validate_action_rss(const struct rte_flow_action *action,
+ uint64_t action_flags,
+ struct rte_eth_dev *dev,
+ struct rte_flow_error *error)
+{
+ struct priv *priv = dev->data->dev_private;
+ const struct rte_flow_action_rss *rss = action->conf;
+ unsigned int i;
+
+ if (action_flags & MLX5_FLOW_FATE_ACTIONS)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't have 2 fate actions"
+ " in same flow");
+ if (rss->func != RTE_ETH_HASH_FUNCTION_DEFAULT &&
+ rss->func != RTE_ETH_HASH_FUNCTION_TOEPLITZ)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ &rss->func,
+ "RSS hash function not supported");
+#ifdef HAVE_IBV_DEVICE_TUNNEL_SUPPORT
+ if (rss->level > 2)
+#else
+ if (rss->level > 1)
+#endif
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ &rss->level,
+ "tunnel RSS is not supported");
+ if (rss->key_len < MLX5_RSS_HASH_KEY_LEN)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ &rss->key_len,
+ "RSS hash key too small");
+ if (rss->key_len > MLX5_RSS_HASH_KEY_LEN)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ &rss->key_len,
+ "RSS hash key too large");
+ if (rss->queue_num > priv->config.ind_table_max_size)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ &rss->queue_num,
+ "number of queues too large");
+ if (rss->types & MLX5_RSS_HF_MASK)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ &rss->types,
+ "some RSS protocols are not"
+ " supported");
+ for (i = 0; i != rss->queue_num; ++i) {
+ if (!(*priv->rxqs)[rss->queue[i]])
+ return rte_flow_error_set
+ (error, EINVAL, RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ &rss->queue[i], "queue is not configured");
+ }
+ return 0;
+}
+
+/*
+ * Validate the count action.
+ *
+ * @param[in] dev
+ * Pointer to the Ethernet device structure.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_ernno is set.
+ */
+static int
+mlx5_flow_validate_action_count(struct rte_eth_dev *dev,
+ struct rte_flow_error *error)
+{
+ struct priv *priv = dev->data->dev_private;
+
+ if (!priv->config.flow_counter_en)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "flow counters are not supported.");
+ return 0;
+}
+
+/**
+ * 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 the Ethernet device structure.
+ * @param[in] attributes
+ * Pointer to flow attributes
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_flow_validate_attributes(struct rte_eth_dev *dev,
+ const struct rte_flow_attr *attributes,
+ struct rte_flow_error *error)
+{
+ struct priv *priv = dev->data->dev_private;
+ uint32_t priority_max = priv->config.flow_prio - 1;
+
+ if (attributes->group)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ATTR_GROUP,
+ NULL, "groups is not supported");
+ 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->egress)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ATTR_EGRESS, NULL,
+ "egress is not supported");
+ if (attributes->transfer)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ATTR_TRANSFER,
+ NULL, "transfer is not supported");
+ if (!attributes->ingress)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ATTR_INGRESS,
+ NULL,
+ "ingress attribute is mandatory");
+ return 0;
+}
+
+/**
+ * Validate Ethernet item.
+ *
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit-fields that holds the items detected until now.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_flow_validate_item_eth(const struct rte_flow_item *item,
+ uint64_t item_flags,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_eth *mask = item->mask;
+ 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),
+ };
+ int ret;
+ int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
+
+ if (item_flags & MLX5_FLOW_LAYER_OUTER_L2)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "3 levels of l2 are not supported");
+ if ((item_flags & MLX5_FLOW_LAYER_INNER_L2) && !tunnel)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "2 L2 without tunnel are not supported");
+ if (!mask)
+ mask = &rte_flow_item_eth_mask;
+ ret = mlx5_flow_item_acceptable(item, (const uint8_t *)mask,
+ (const uint8_t *)&nic_mask,
+ sizeof(struct rte_flow_item_eth),
+ error);
+ return ret;
+}
+
+/**
+ * Validate VLAN item.
+ *
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit-fields that holds the items detected until now.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_flow_validate_item_vlan(const struct rte_flow_item *item,
+ int64_t item_flags,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_vlan *spec = item->spec;
+ const struct rte_flow_item_vlan *mask = item->mask;
+ const struct rte_flow_item_vlan nic_mask = {
+ .tci = RTE_BE16(0x0fff),
+ .inner_type = RTE_BE16(0xffff),
+ };
+ uint16_t vlan_tag = 0;
+ const int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
+ int ret;
+ const uint32_t l34m = tunnel ? (MLX5_FLOW_LAYER_INNER_L3 |
+ MLX5_FLOW_LAYER_INNER_L4) :
+ (MLX5_FLOW_LAYER_OUTER_L3 |
+ MLX5_FLOW_LAYER_OUTER_L4);
+ const uint32_t vlanm = tunnel ? MLX5_FLOW_LAYER_INNER_VLAN :
+ MLX5_FLOW_LAYER_OUTER_VLAN;
+
+ if (item_flags & vlanm)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "VLAN layer already configured");
+ else if ((item_flags & l34m) != 0)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L2 layer cannot follow L3/L4 layer");
+ if (!mask)
+ mask = &rte_flow_item_vlan_mask;
+ ret = mlx5_flow_item_acceptable(item, (const uint8_t *)mask,
+ (const uint8_t *)&nic_mask,
+ sizeof(struct rte_flow_item_vlan),
+ error);
+ if (ret)
+ return ret;
+ if (spec) {
+ vlan_tag = spec->tci;
+ vlan_tag &= mask->tci;
+ }
+ /*
+ * From verbs perspective an empty VLAN is equivalent
+ * to a packet without VLAN layer.
+ */
+ if (!vlan_tag)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM_SPEC,
+ item->spec,
+ "VLAN cannot be empty");
+ return 0;
+}
+
+/**
+ * Validate IPV4 item.
+ *
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit-fields that holds the items detected until now.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_flow_validate_item_ipv4(const struct rte_flow_item *item,
+ int64_t item_flags,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_ipv4 *mask = item->mask;
+ 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,
+ },
+ };
+ const int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
+ int ret;
+
+ if (item_flags & (tunnel ? MLX5_FLOW_LAYER_INNER_L3 :
+ MLX5_FLOW_LAYER_OUTER_L3))
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "multiple L3 layers not supported");
+ else if (item_flags & (tunnel ? MLX5_FLOW_LAYER_INNER_L4 :
+ MLX5_FLOW_LAYER_OUTER_L4))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L3 cannot follow an L4 layer.");
+ if (!mask)
+ mask = &rte_flow_item_ipv4_mask;
+ ret = mlx5_flow_item_acceptable(item, (const uint8_t *)mask,
+ (const uint8_t *)&nic_mask,
+ sizeof(struct rte_flow_item_ipv4),
+ error);
+ if (ret < 0)
+ return ret;
+ return 0;
+}
+
+/**
+ * Validate IPV6 item.
+ *
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit-fields that holds the items detected until now.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_flow_validate_item_ipv6(const struct rte_flow_item *item,
+ uint64_t item_flags,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_ipv6 *mask = item->mask;
+ 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,
+ },
+ };
+ const int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
+ int ret;
+
+ if (item_flags & (tunnel ? MLX5_FLOW_LAYER_INNER_L3 :
+ MLX5_FLOW_LAYER_OUTER_L3))
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "multiple L3 layers not supported");
+ else if (item_flags & (tunnel ? MLX5_FLOW_LAYER_INNER_L4 :
+ MLX5_FLOW_LAYER_OUTER_L4))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L3 cannot follow an L4 layer.");
+ /*
+ * IPv6 is not recognised by the NIC inside a GRE tunnel.
+ * Such support has to be disabled as the rule will be
+ * accepted. Issue reproduced with Mellanox OFED 4.3-3.0.2.1 and
+ * Mellanox OFED 4.4-1.0.0.0.
+ */
+ if (tunnel && item_flags & MLX5_FLOW_LAYER_GRE)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "IPv6 inside a GRE tunnel is"
+ " not recognised.");
+ if (!mask)
+ mask = &rte_flow_item_ipv6_mask;
+ ret = mlx5_flow_item_acceptable(item, (const uint8_t *)mask,
+ (const uint8_t *)&nic_mask,
+ sizeof(struct rte_flow_item_ipv6),
+ error);
+ if (ret < 0)
+ return ret;
+ return 0;
+}
+
+/**
+ * Validate UDP item.
+ *
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit-fields that holds the items detected until now.
+ * @param[in] target_protocol
+ * The next protocol in the previous item.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_flow_validate_item_udp(const struct rte_flow_item *item,
+ uint64_t item_flags,
+ uint8_t target_protocol,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_udp *mask = item->mask;
+ const int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
+ int ret;
+
+ if (target_protocol != 0xff && target_protocol != MLX5_IP_PROTOCOL_UDP)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "protocol filtering not compatible"
+ " with UDP layer");
+ if (!(item_flags & (tunnel ? MLX5_FLOW_LAYER_INNER_L3 :
+ MLX5_FLOW_LAYER_OUTER_L3)))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L3 is mandatory to filter on L4");
+ if (item_flags & (tunnel ? MLX5_FLOW_LAYER_INNER_L4 :
+ MLX5_FLOW_LAYER_OUTER_L4))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L4 layer is already present");
+ if (!mask)
+ mask = &rte_flow_item_udp_mask;
+ ret = mlx5_flow_item_acceptable
+ (item, (const uint8_t *)mask,
+ (const uint8_t *)&rte_flow_item_udp_mask,
+ sizeof(struct rte_flow_item_udp), error);
+ if (ret < 0)
+ return ret;
+ return 0;
+}
+
+/**
+ * Validate TCP item.
+ *
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit-fields that holds the items detected until now.
+ * @param[in] target_protocol
+ * The next protocol in the previous item.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_flow_validate_item_tcp(const struct rte_flow_item *item,
+ uint64_t item_flags,
+ uint8_t target_protocol,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_tcp *mask = item->mask;
+ const int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
+ int ret;
+
+ if (target_protocol != 0xff && target_protocol != MLX5_IP_PROTOCOL_TCP)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "protocol filtering not compatible"
+ " with TCP layer");
+ if (!(item_flags & (tunnel ? MLX5_FLOW_LAYER_INNER_L3 :
+ MLX5_FLOW_LAYER_OUTER_L3)))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L3 is mandatory to filter on L4");
+ if (item_flags & (tunnel ? MLX5_FLOW_LAYER_INNER_L4 :
+ MLX5_FLOW_LAYER_OUTER_L4))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L4 layer is already present");
+ if (!mask)
+ mask = &rte_flow_item_tcp_mask;
+ ret = mlx5_flow_item_acceptable
+ (item, (const uint8_t *)mask,
+ (const uint8_t *)&rte_flow_item_tcp_mask,
+ sizeof(struct rte_flow_item_tcp), error);
+ if (ret < 0)
+ return ret;
+ return 0;
+}
+
+/**
+ * Validate VXLAN item.
+ *
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit-fields that holds the items detected until now.
+ * @param[in] target_protocol
+ * The next protocol in the previous item.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_flow_validate_item_vxlan(const struct rte_flow_item *item,
+ uint64_t item_flags,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_vxlan *spec = item->spec;
+ const struct rte_flow_item_vxlan *mask = item->mask;
+ int ret;
+ union vni {
+ uint32_t vlan_id;
+ uint8_t vni[4];
+ } id = { .vlan_id = 0, };
+ uint32_t vlan_id = 0;
+
+
+ if (item_flags & MLX5_FLOW_LAYER_TUNNEL)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "a tunnel is already present");
+ /*
+ * Verify only UDPv4 is present as defined in
+ * https://tools.ietf.org/html/rfc7348
+ */
+ if (!(item_flags & MLX5_FLOW_LAYER_OUTER_L4_UDP))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "no outer UDP layer found");
+ if (!mask)
+ mask = &rte_flow_item_vxlan_mask;
+ ret = mlx5_flow_item_acceptable
+ (item, (const uint8_t *)mask,
+ (const uint8_t *)&rte_flow_item_vxlan_mask,
+ sizeof(struct rte_flow_item_vxlan),
+ error);
+ if (ret < 0)
+ return ret;
+ if (spec) {
+ memcpy(&id.vni[1], spec->vni, 3);
+ vlan_id = id.vlan_id;
+ memcpy(&id.vni[1], mask->vni, 3);
+ vlan_id &= id.vlan_id;
+ }
+ /*
+ * Tunnel id 0 is equivalent as not adding a VXLAN layer, if
+ * only this layer is defined in the Verbs specification it is
+ * interpreted as wildcard and all packets will match this
+ * rule, if it follows a full stack layer (ex: eth / ipv4 /
+ * udp), all packets matching the layers before will also
+ * match this rule. To avoid such situation, VNI 0 is
+ * currently refused.
+ */
+ if (!vlan_id)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "VXLAN vni cannot be 0");
+ if (!(item_flags & MLX5_FLOW_LAYER_OUTER))
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "VXLAN tunnel must be fully defined");
+ return 0;
+}
+
+/**
+ * Validate VXLAN_GPE item.
+ *
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit-fields that holds the items detected until now.
+ * @param[in] priv
+ * Pointer to the private data structure.
+ * @param[in] target_protocol
+ * The next protocol in the previous item.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_flow_validate_item_vxlan_gpe(const struct rte_flow_item *item,
+ uint64_t item_flags,
+ struct rte_eth_dev *dev,
+ struct rte_flow_error *error)
+{
+ struct priv *priv = dev->data->dev_private;
+ const struct rte_flow_item_vxlan_gpe *spec = item->spec;
+ const struct rte_flow_item_vxlan_gpe *mask = item->mask;
+ int ret;
+ union vni {
+ uint32_t vlan_id;
+ uint8_t vni[4];
+ } id = { .vlan_id = 0, };
+ uint32_t vlan_id = 0;
+
+ if (!priv->config.l3_vxlan_en)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L3 VXLAN is not enabled by device"
+ " parameter and/or not configured in"
+ " firmware");
+ if (item_flags & MLX5_FLOW_LAYER_TUNNEL)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "a tunnel is already present");
+ /*
+ * Verify only UDPv4 is present as defined in
+ * https://tools.ietf.org/html/rfc7348
+ */
+ if (!(item_flags & MLX5_FLOW_LAYER_OUTER_L4_UDP))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "no outer UDP layer found");
+ if (!mask)
+ mask = &rte_flow_item_vxlan_gpe_mask;
+ ret = mlx5_flow_item_acceptable
+ (item, (const uint8_t *)mask,
+ (const uint8_t *)&rte_flow_item_vxlan_gpe_mask,
+ sizeof(struct rte_flow_item_vxlan_gpe),
+ error);
+ if (ret < 0)
+ return ret;
+ if (spec) {
+ if (spec->protocol)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM,
+ item,
+ "VxLAN-GPE protocol"
+ " not supported");
+ memcpy(&id.vni[1], spec->vni, 3);
+ vlan_id = id.vlan_id;
+ memcpy(&id.vni[1], mask->vni, 3);
+ vlan_id &= id.vlan_id;
+ }
+ /*
+ * Tunnel id 0 is equivalent as not adding a VXLAN layer, if only this
+ * layer is defined in the Verbs specification it is interpreted as
+ * wildcard and all packets will match this rule, if it follows a full
+ * stack layer (ex: eth / ipv4 / udp), all packets matching the layers
+ * before will also match this rule. To avoid such situation, VNI 0
+ * is currently refused.
+ */
+ if (!vlan_id)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "VXLAN-GPE vni cannot be 0");
+ if (!(item_flags & MLX5_FLOW_LAYER_OUTER))
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "VXLAN-GPE tunnel must be fully"
+ " defined");
+ return 0;
+}
+
+/**
+ * Validate GRE item.
+ *
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit flags to mark detected items.
+ * @param[in] target_protocol
+ * The next protocol in the previous item.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_flow_validate_item_gre(const struct rte_flow_item *item,
+ uint64_t item_flags,
+ uint8_t target_protocol,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_gre *spec __rte_unused = item->spec;
+ const struct rte_flow_item_gre *mask = item->mask;
+ int ret;
+
+ if (target_protocol != 0xff && target_protocol != MLX5_IP_PROTOCOL_GRE)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "protocol filtering not compatible"
+ " with this GRE layer");
+ if (item_flags & MLX5_FLOW_LAYER_TUNNEL)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "a tunnel is already present");
+ if (!(item_flags & MLX5_FLOW_LAYER_OUTER_L3))
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L3 Layer is missing");
+ if (!mask)
+ mask = &rte_flow_item_gre_mask;
+ ret = mlx5_flow_item_acceptable
+ (item, (const uint8_t *)mask,
+ (const uint8_t *)&rte_flow_item_gre_mask,
+ sizeof(struct rte_flow_item_gre), error);
+ if (ret < 0)
+ return ret;
+#ifndef HAVE_IBV_DEVICE_MPLS_SUPPORT
+ if (spec && (spec->protocol & mask->protocol))
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "without MPLS support the"
+ " specification cannot be used for"
+ " filtering");
+#endif
+ return 0;
+}
+
+/**
+ * Validate MPLS item.
+ *
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit-fields that holds the items detected until now.
+ * @param[in] target_protocol
+ * The next protocol in the previous item.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_flow_validate_item_mpls(const struct rte_flow_item *item __rte_unused,
+ uint64_t item_flags __rte_unused,
+ uint8_t target_protocol __rte_unused,
+ struct rte_flow_error *error)
+{
+#ifdef HAVE_IBV_DEVICE_MPLS_SUPPORT
+ const struct rte_flow_item_mpls *mask = item->mask;
+ int ret;
+
+ if (target_protocol != 0xff && target_protocol != MLX5_IP_PROTOCOL_MPLS)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "protocol filtering not compatible"
+ " with MPLS layer");
+ if (item_flags & MLX5_FLOW_LAYER_TUNNEL)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "a tunnel is already"
+ " present");
+ if (!mask)
+ mask = &rte_flow_item_mpls_mask;
+ ret = mlx5_flow_item_acceptable
+ (item, (const uint8_t *)mask,
+ (const uint8_t *)&rte_flow_item_mpls_mask,
+ sizeof(struct rte_flow_item_mpls), error);
+ if (ret < 0)
+ return ret;
+ return 0;
+#endif
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "MPLS is not supported by Verbs, please"
+ " update.");
+}
+
+/**
+ * Internal validation function.
+ *
+ * @param[in] dev
+ * Pointer to the Ethernet device 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[out] error
+ * Pointer to the error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_ernno is set.
+ */
+static int mlx5_flow_verbs_validate(struct rte_eth_dev *dev,
+ const struct rte_flow_attr *attr,
+ const struct rte_flow_item items[],
+ const struct rte_flow_action actions[],
+ struct rte_flow_error *error)
+{
+ int ret;
+ uint32_t action_flags = 0;
+ uint32_t item_flags = 0;
+ int tunnel = 0;
+ uint8_t next_protocol = 0xff;