#define MLX5DV_FLOW_ACTION_COUNTERS_DEVX 0
#endif
+#ifndef HAVE_MLX5DV_DR_ESWITCH
+#ifndef MLX5DV_FLOW_TABLE_TYPE_FDB
+#define MLX5DV_FLOW_TABLE_TYPE_FDB 0
+#endif
+#endif
+
+#ifndef HAVE_MLX5DV_DR
+#define MLX5DV_DR_ACTION_FLAGS_ROOT_LEVEL 1
+#endif
+
union flow_dv_attr {
struct {
uint32_t valid:1;
struct field_modify_info modify_tcp[] = {
{2, 0, MLX5_MODI_OUT_TCP_SPORT},
{2, 2, MLX5_MODI_OUT_TCP_DPORT},
+ {4, 4, MLX5_MODI_OUT_TCP_SEQ_NUM},
+ {4, 8, MLX5_MODI_OUT_TCP_ACK_NUM},
{0, 0, 0},
};
MLX5_MODIFICATION_TYPE_ADD, error);
}
+/**
+ * Convert modify-header increment/decrement TCP Sequence number
+ * to DV specification.
+ *
+ * @param[in,out] resource
+ * Pointer to the modify-header resource.
+ * @param[in] action
+ * Pointer to action specification.
+ * @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_action_modify_tcp_seq
+ (struct mlx5_flow_dv_modify_hdr_resource *resource,
+ const struct rte_flow_action *action,
+ struct rte_flow_error *error)
+{
+ const rte_be32_t *conf = (const rte_be32_t *)(action->conf);
+ uint64_t value = rte_be_to_cpu_32(*conf);
+ struct rte_flow_item item;
+ struct rte_flow_item_tcp tcp;
+ struct rte_flow_item_tcp tcp_mask;
+
+ memset(&tcp, 0, sizeof(tcp));
+ memset(&tcp_mask, 0, sizeof(tcp_mask));
+ if (action->type == RTE_FLOW_ACTION_TYPE_DEC_TCP_SEQ)
+ /*
+ * The HW has no decrement operation, only increment operation.
+ * To simulate decrement X from Y using increment operation
+ * we need to add UINT32_MAX X times to Y.
+ * Each adding of UINT32_MAX decrements Y by 1.
+ */
+ value *= UINT32_MAX;
+ tcp.hdr.sent_seq = rte_cpu_to_be_32((uint32_t)value);
+ tcp_mask.hdr.sent_seq = RTE_BE32(UINT32_MAX);
+ item.type = RTE_FLOW_ITEM_TYPE_TCP;
+ item.spec = &tcp;
+ item.mask = &tcp_mask;
+ return flow_dv_convert_modify_action(&item, modify_tcp, resource,
+ MLX5_MODIFICATION_TYPE_ADD, error);
+}
+
+/**
+ * Convert modify-header increment/decrement TCP Acknowledgment number
+ * to DV specification.
+ *
+ * @param[in,out] resource
+ * Pointer to the modify-header resource.
+ * @param[in] action
+ * Pointer to action specification.
+ * @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_action_modify_tcp_ack
+ (struct mlx5_flow_dv_modify_hdr_resource *resource,
+ const struct rte_flow_action *action,
+ struct rte_flow_error *error)
+{
+ const rte_be32_t *conf = (const rte_be32_t *)(action->conf);
+ uint64_t value = rte_be_to_cpu_32(*conf);
+ struct rte_flow_item item;
+ struct rte_flow_item_tcp tcp;
+ struct rte_flow_item_tcp tcp_mask;
+
+ memset(&tcp, 0, sizeof(tcp));
+ memset(&tcp_mask, 0, sizeof(tcp_mask));
+ if (action->type == RTE_FLOW_ACTION_TYPE_DEC_TCP_ACK)
+ /*
+ * The HW has no decrement operation, only increment operation.
+ * To simulate decrement X from Y using increment operation
+ * we need to add UINT32_MAX X times to Y.
+ * Each adding of UINT32_MAX decrements Y by 1.
+ */
+ value *= UINT32_MAX;
+ tcp.hdr.recv_ack = rte_cpu_to_be_32((uint32_t)value);
+ tcp_mask.hdr.recv_ack = RTE_BE32(UINT32_MAX);
+ item.type = RTE_FLOW_ITEM_TYPE_TCP;
+ item.spec = &tcp;
+ item.mask = &tcp_mask;
+ return flow_dv_convert_modify_action(&item, modify_tcp, resource,
+ MLX5_MODIFICATION_TYPE_ADD, error);
+}
+
/**
* Validate META item.
*
return 0;
}
+/**
+ * Validate vport item.
+ *
+ * @param[in] dev
+ * Pointer to the rte_eth_dev structure.
+ * @param[in] item
+ * Item specification.
+ * @param[in] attr
+ * Attributes of flow that includes this item.
+ * @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
+flow_dv_validate_item_port_id(struct rte_eth_dev *dev,
+ const struct rte_flow_item *item,
+ const struct rte_flow_attr *attr,
+ uint64_t item_flags,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_port_id *spec = item->spec;
+ const struct rte_flow_item_port_id *mask = item->mask;
+ const struct rte_flow_item_port_id switch_mask = {
+ .id = 0xffffffff,
+ };
+ uint16_t esw_domain_id;
+ uint16_t item_port_esw_domain_id;
+ int ret;
+
+ if (!attr->transfer)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM,
+ NULL,
+ "match on port id is valid only"
+ " when transfer flag is enabled");
+ if (item_flags & MLX5_FLOW_ITEM_PORT_ID)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "multiple source ports are not"
+ " supported");
+ if (!mask)
+ mask = &switch_mask;
+ if (mask->id != 0xffffffff)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM_MASK,
+ mask,
+ "no support for partial mask on"
+ " \"id\" field");
+ ret = mlx5_flow_item_acceptable
+ (item, (const uint8_t *)mask,
+ (const uint8_t *)&rte_flow_item_port_id_mask,
+ sizeof(struct rte_flow_item_port_id),
+ error);
+ if (ret)
+ return ret;
+ if (!spec)
+ return 0;
+ ret = mlx5_port_to_eswitch_info(spec->id, &item_port_esw_domain_id,
+ NULL);
+ if (ret)
+ return rte_flow_error_set(error, -ret,
+ RTE_FLOW_ERROR_TYPE_ITEM_SPEC, spec,
+ "failed to obtain E-Switch info for"
+ " port");
+ ret = mlx5_port_to_eswitch_info(dev->data->port_id,
+ &esw_domain_id, NULL);
+ if (ret < 0)
+ return rte_flow_error_set(error, -ret,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL,
+ "failed to obtain E-Switch info");
+ if (item_port_esw_domain_id != esw_domain_id)
+ return rte_flow_error_set(error, -ret,
+ RTE_FLOW_ERROR_TYPE_ITEM_SPEC, spec,
+ "cannot match on a port from a"
+ " different E-Switch");
+ return 0;
+}
+
/**
* Validate count action.
*
RTE_FLOW_ERROR_TYPE_ACTION, NULL,
"can only have a single encap or"
" decap action in a flow");
- if (attr->ingress)
+ if (!attr->transfer && attr->ingress)
return rte_flow_error_set(error, ENOTSUP,
RTE_FLOW_ERROR_TYPE_ATTR_INGRESS,
NULL,
"can only have a single encap"
" action in a flow");
/* encap without preceding decap is not supported for ingress */
- if (attr->ingress && !(action_flags & MLX5_FLOW_ACTION_RAW_DECAP))
+ if (!attr->transfer && attr->ingress &&
+ !(action_flags & MLX5_FLOW_ACTION_RAW_DECAP))
return rte_flow_error_set(error, ENOTSUP,
RTE_FLOW_ERROR_TYPE_ATTR_INGRESS,
NULL,
struct mlx5_ibv_shared *sh = priv->sh;
struct mlx5_flow_dv_encap_decap_resource *cache_resource;
struct rte_flow *flow = dev_flow->flow;
- struct mlx5dv_dr_ns *ns;
+ struct mlx5dv_dr_domain *domain;
resource->flags = flow->group ? 0 : 1;
- if (flow->ingress)
- ns = sh->rx_ns;
+ 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
- ns = sh->tx_ns;
+ domain = sh->tx_domain;
/* Lookup a matching resource from cache. */
LIST_FOREACH(cache_resource, &sh->encaps_decaps, next) {
cache_resource->verbs_action =
mlx5_glue->dv_create_flow_action_packet_reformat
(sh->ctx, cache_resource->reformat_type,
- cache_resource->ft_type, ns, cache_resource->flags,
+ cache_resource->ft_type, domain, cache_resource->flags,
cache_resource->size,
(cache_resource->size ? cache_resource->buf : NULL));
if (!cache_resource->verbs_action) {
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;
+}
+
/**
* Get the size of specific rte_flow_item_type
*
flow_dv_convert_encap_data(const struct rte_flow_item *items, uint8_t *buf,
size_t *size, struct rte_flow_error *error)
{
- struct ether_hdr *eth = NULL;
- struct vlan_hdr *vlan = NULL;
- struct ipv4_hdr *ipv4 = NULL;
- struct ipv6_hdr *ipv6 = NULL;
- struct udp_hdr *udp = NULL;
- struct vxlan_hdr *vxlan = NULL;
- struct vxlan_gpe_hdr *vxlan_gpe = NULL;
- struct gre_hdr *gre = NULL;
+ 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;
rte_memcpy((void *)&buf[temp_size], items->spec, len);
switch (items->type) {
case RTE_FLOW_ITEM_TYPE_ETH:
- eth = (struct ether_hdr *)&buf[temp_size];
+ eth = (struct rte_ether_hdr *)&buf[temp_size];
break;
case RTE_FLOW_ITEM_TYPE_VLAN:
- vlan = (struct vlan_hdr *)&buf[temp_size];
+ 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(ETHER_TYPE_VLAN);
+ eth->ether_type = RTE_BE16(RTE_ETHER_TYPE_VLAN);
break;
case RTE_FLOW_ITEM_TYPE_IPV4:
- ipv4 = (struct ipv4_hdr *)&buf[temp_size];
+ ipv4 = (struct rte_ipv4_hdr *)&buf[temp_size];
if (!vlan && !eth)
return rte_flow_error_set(error, EINVAL,
RTE_FLOW_ERROR_TYPE_ACTION,
"neither eth nor vlan"
" header found");
if (vlan && !vlan->eth_proto)
- vlan->eth_proto = RTE_BE16(ETHER_TYPE_IPv4);
+ vlan->eth_proto = RTE_BE16(RTE_ETHER_TYPE_IPV4);
else if (eth && !eth->ether_type)
- eth->ether_type = RTE_BE16(ETHER_TYPE_IPv4);
+ 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;
ipv4->time_to_live = MLX5_ENCAP_IPV4_TTL_DEF;
break;
case RTE_FLOW_ITEM_TYPE_IPV6:
- ipv6 = (struct ipv6_hdr *)&buf[temp_size];
+ ipv6 = (struct rte_ipv6_hdr *)&buf[temp_size];
if (!vlan && !eth)
return rte_flow_error_set(error, EINVAL,
RTE_FLOW_ERROR_TYPE_ACTION,
"neither eth nor vlan"
" header found");
if (vlan && !vlan->eth_proto)
- vlan->eth_proto = RTE_BE16(ETHER_TYPE_IPv6);
+ vlan->eth_proto = RTE_BE16(RTE_ETHER_TYPE_IPV6);
else if (eth && !eth->ether_type)
- eth->ether_type = RTE_BE16(ETHER_TYPE_IPv6);
+ eth->ether_type = RTE_BE16(RTE_ETHER_TYPE_IPV6);
if (!ipv6->vtc_flow)
ipv6->vtc_flow =
RTE_BE32(MLX5_ENCAP_IPV6_VTC_FLOW);
ipv6->hop_limits = MLX5_ENCAP_IPV6_HOP_LIMIT;
break;
case RTE_FLOW_ITEM_TYPE_UDP:
- udp = (struct udp_hdr *)&buf[temp_size];
+ udp = (struct rte_udp_hdr *)&buf[temp_size];
if (!ipv4 && !ipv6)
return rte_flow_error_set(error, EINVAL,
RTE_FLOW_ERROR_TYPE_ACTION,
ipv6->proto = IPPROTO_UDP;
break;
case RTE_FLOW_ITEM_TYPE_VXLAN:
- vxlan = (struct vxlan_hdr *)&buf[temp_size];
+ vxlan = (struct rte_vxlan_hdr *)&buf[temp_size];
if (!udp)
return rte_flow_error_set(error, EINVAL,
RTE_FLOW_ERROR_TYPE_ACTION,
RTE_BE32(MLX5_ENCAP_VXLAN_FLAGS);
break;
case RTE_FLOW_ITEM_TYPE_VXLAN_GPE:
- vxlan_gpe = (struct vxlan_gpe_hdr *)&buf[temp_size];
+ vxlan_gpe = (struct rte_vxlan_gpe_hdr *)&buf[temp_size];
if (!udp)
return rte_flow_error_set(error, EINVAL,
RTE_FLOW_ERROR_TYPE_ACTION,
break;
case RTE_FLOW_ITEM_TYPE_GRE:
case RTE_FLOW_ITEM_TYPE_NVGRE:
- gre = (struct gre_hdr *)&buf[temp_size];
+ gre = (struct rte_gre_hdr *)&buf[temp_size];
if (!gre->proto)
return rte_flow_error_set(error, EINVAL,
RTE_FLOW_ERROR_TYPE_ACTION,
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) {
+ next_hdr += sizeof(struct rte_vlan_hdr);
+ vlan = (struct rte_vlan_hdr *)next_hdr;
+ proto = RTE_BE16(vlan->eth_proto);
+ }
+
+ /* 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.
*
* 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.
*
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;
struct mlx5_flow_dv_encap_decap_resource res = {
.reformat_type =
MLX5DV_FLOW_ACTION_PACKET_REFORMAT_TYPE_L2_TO_L2_TUNNEL,
- .ft_type = MLX5DV_FLOW_TABLE_TYPE_NIC_TX,
+ .ft_type = transfer ? MLX5DV_FLOW_TABLE_TYPE_FDB :
+ MLX5DV_FLOW_TABLE_TYPE_NIC_TX,
};
if (action->type == RTE_FLOW_ACTION_TYPE_RAW_ENCAP) {
(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 =
* 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.
*
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 = MLX5DV_FLOW_TABLE_TYPE_NIC_RX,
+ .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))
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;
- res.ft_type = attr->egress ? MLX5DV_FLOW_TABLE_TYPE_NIC_TX :
- MLX5DV_FLOW_TABLE_TYPE_NIC_RX;
+ 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,
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.
*
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;
+ uint16_t port;
+ uint16_t esw_domain_id;
+ uint16_t act_port_domain_id;
+ int ret;
+
+ 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");
+ ret = mlx5_port_to_eswitch_info(dev->data->port_id,
+ &esw_domain_id, NULL);
+ if (ret < 0)
+ return rte_flow_error_set(error, -ret,
+ 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;
+ ret = mlx5_port_to_eswitch_info(port, &act_port_domain_id, NULL);
+ if (ret)
+ return rte_flow_error_set
+ (error, -ret,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF, port_id,
+ "failed to obtain E-Switch port id for port");
+ if (act_port_domain_id != esw_domain_id)
+ return rte_flow_error_set
+ (error, -ret,
+ 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.
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;
- struct mlx5dv_dr_ns *ns =
- resource->ft_type == MLX5DV_FLOW_TABLE_TYPE_NIC_TX ?
- sh->tx_ns : sh->rx_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 *
cache_resource->verbs_action =
mlx5_glue->dv_create_flow_action_modify_header
(sh->ctx, cache_resource->ft_type,
- ns, 0,
+ ns, cache_resource->flags,
cache_resource->actions_num *
sizeof(cache_resource->actions[0]),
(uint64_t *)cache_resource->actions);
RTE_FLOW_ERROR_TYPE_ATTR_PRIORITY,
NULL,
"priority out of range");
- if (attributes->transfer)
- return rte_flow_error_set(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ATTR_TRANSFER,
- NULL,
- "transfer is not supported");
+ 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 configurationd 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->group >= MLX5_MAX_TABLES_FDB)
+ return rte_flow_error_set
+ (error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ATTR_TRANSFER,
+ NULL, "group must be smaller than "
+ RTE_STR(MLX5_MAX_FDB_TABLES));
+ }
if (!(attributes->egress ^ attributes->ingress))
return rte_flow_error_set(error, ENOTSUP,
RTE_FLOW_ERROR_TYPE_ATTR, NULL,
uint64_t last_item = 0;
uint8_t next_protocol = 0xff;
int actions_n = 0;
+ 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;
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);
ret = mlx5_flow_validate_item_tcp
(items, item_flags,
next_protocol,
- &rte_flow_item_tcp_mask,
+ &nic_tcp_mask,
error);
if (ret < 0)
return ret;
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;
+ item_flags |= 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;
+ item_flags |= MLX5_FLOW_LAYER_ICMP6;
+ break;
default:
return rte_flow_error_set(error, ENOTSUP,
RTE_FLOW_ERROR_TYPE_ITEM,
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);
++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,
"action not supported");
}
}
- 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");
+ /* 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;
}
"not enough memory to create flow");
return NULL;
}
- flow->dv.value.size = MLX5_ST_SZ_DB(fte_match_param);
+ flow->dv.value.size = MLX5_ST_SZ_BYTES(fte_match_param);
return flow;
}
uint8_t *v = match_value;
unsigned int i;
- for (i = 0; i < MLX5_ST_SZ_DB(fte_match_param); ++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"
rte_be_to_cpu_16(tcp_m->hdr.dst_port));
MLX5_SET(fte_match_set_lyr_2_4, headers_v, tcp_dport,
rte_be_to_cpu_16(tcp_v->hdr.dst_port & tcp_m->hdr.dst_port));
+ MLX5_SET(fte_match_set_lyr_2_4, headers_m, tcp_flags,
+ tcp_m->hdr.tcp_flags);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, tcp_flags,
+ (tcp_v->hdr.tcp_flags & tcp_m->hdr.tcp_flags));
}
/**
case MLX5_FLOW_LAYER_GRE:
MLX5_SET(fte_match_set_misc, misc_m, gre_protocol, 0xffff);
MLX5_SET(fte_match_set_misc, misc_v, gre_protocol,
- ETHER_TYPE_MPLS);
+ RTE_ETHER_TYPE_MPLS);
break;
default:
MLX5_SET(fte_match_set_lyr_2_4, headers_m, ip_protocol, 0xff);
}
}
+/**
+ * Add source vport match to the specified matcher.
+ *
+ * @param[in, out] matcher
+ * Flow matcher.
+ * @param[in, out] key
+ * Flow matcher value.
+ * @param[in] port
+ * Source vport value to match
+ * @param[in] mask
+ * Mask
+ */
+static void
+flow_dv_translate_item_source_vport(void *matcher, void *key,
+ int16_t port, uint16_t mask)
+{
+ void *misc_m = MLX5_ADDR_OF(fte_match_param, matcher, misc_parameters);
+ void *misc_v = MLX5_ADDR_OF(fte_match_param, key, misc_parameters);
+
+ MLX5_SET(fte_match_set_misc, misc_m, source_port, mask);
+ MLX5_SET(fte_match_set_misc, misc_v, source_port, port);
+}
+
+/**
+ * Translate port-id item to eswitch match on port-id.
+ *
+ * @param[in] dev
+ * The devich to configure through.
+ * @param[in, out] matcher
+ * Flow matcher.
+ * @param[in, out] key
+ * Flow matcher value.
+ * @param[in] item
+ * Flow pattern to translate.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise.
+ */
+static int
+flow_dv_translate_item_port_id(struct rte_eth_dev *dev, void *matcher,
+ void *key, const struct rte_flow_item *item)
+{
+ const struct rte_flow_item_port_id *pid_m = item ? item->mask : NULL;
+ const struct rte_flow_item_port_id *pid_v = item ? item->spec : NULL;
+ uint16_t mask, val, id;
+ int ret;
+
+ mask = pid_m ? pid_m->id : 0xffff;
+ id = pid_v ? pid_v->id : dev->data->port_id;
+ ret = mlx5_port_to_eswitch_info(id, NULL, &val);
+ if (ret)
+ return ret;
+ flow_dv_translate_item_source_vport(matcher, key, val, mask);
+ return 0;
+}
+
+/**
+ * Add ICMP6 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_icmp6(void *matcher, void *key,
+ const struct rte_flow_item *item,
+ int inner)
+{
+ const struct rte_flow_item_icmp6 *icmp6_m = item->mask;
+ const struct rte_flow_item_icmp6 *icmp6_v = item->spec;
+ void *headers_m;
+ void *headers_v;
+ void *misc3_m = MLX5_ADDR_OF(fte_match_param, matcher,
+ misc_parameters_3);
+ void *misc3_v = MLX5_ADDR_OF(fte_match_param, key, misc_parameters_3);
+ 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);
+ }
+ MLX5_SET(fte_match_set_lyr_2_4, headers_m, ip_protocol, 0xFF);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, IPPROTO_ICMPV6);
+ if (!icmp6_v)
+ return;
+ if (!icmp6_m)
+ icmp6_m = &rte_flow_item_icmp6_mask;
+ MLX5_SET(fte_match_set_misc3, misc3_m, icmpv6_type, icmp6_m->type);
+ MLX5_SET(fte_match_set_misc3, misc3_v, icmpv6_type,
+ icmp6_v->type & icmp6_m->type);
+ MLX5_SET(fte_match_set_misc3, misc3_m, icmpv6_code, icmp6_m->code);
+ MLX5_SET(fte_match_set_misc3, misc3_v, icmpv6_code,
+ icmp6_v->code & icmp6_m->code);
+}
+
+/**
+ * Add ICMP 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_icmp(void *matcher, void *key,
+ const struct rte_flow_item *item,
+ int inner)
+{
+ const struct rte_flow_item_icmp *icmp_m = item->mask;
+ const struct rte_flow_item_icmp *icmp_v = item->spec;
+ void *headers_m;
+ void *headers_v;
+ void *misc3_m = MLX5_ADDR_OF(fte_match_param, matcher,
+ misc_parameters_3);
+ void *misc3_v = MLX5_ADDR_OF(fte_match_param, key, misc_parameters_3);
+ 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);
+ }
+ MLX5_SET(fte_match_set_lyr_2_4, headers_m, ip_protocol, 0xFF);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, IPPROTO_ICMP);
+ if (!icmp_v)
+ return;
+ if (!icmp_m)
+ icmp_m = &rte_flow_item_icmp_mask;
+ MLX5_SET(fte_match_set_misc3, misc3_m, icmp_type,
+ icmp_m->hdr.icmp_type);
+ MLX5_SET(fte_match_set_misc3, misc3_v, icmp_type,
+ icmp_v->hdr.icmp_type & icmp_m->hdr.icmp_type);
+ MLX5_SET(fte_match_set_misc3, misc3_m, icmp_code,
+ icmp_m->hdr.icmp_code);
+ MLX5_SET(fte_match_set_misc3, misc3_v, icmp_code,
+ icmp_v->hdr.icmp_code & icmp_m->hdr.icmp_code);
+}
+
static uint32_t matcher_zero[MLX5_ST_SZ_DW(fte_match_param)] = { 0 };
#define HEADER_IS_ZERO(match_criteria, headers) \
* Table id to use.
* @param[in] egress
* Direction of the table.
+ * @param[in] transfer
+ * E-Switch or NIC flow.
* @param[out] error
* pointer to error structure.
*
static struct mlx5_flow_tbl_resource *
flow_dv_tbl_resource_get(struct rte_eth_dev *dev,
uint32_t table_id, uint8_t egress,
+ uint8_t transfer,
struct rte_flow_error *error)
{
struct mlx5_priv *priv = dev->data->dev_private;
struct mlx5_flow_tbl_resource *tbl;
#ifdef HAVE_MLX5DV_DR
- if (egress) {
+ if (transfer) {
+ tbl = &sh->fdb_tbl[table_id];
+ if (!tbl->obj)
+ tbl->obj = mlx5_glue->dr_create_flow_tbl
+ (sh->fdb_domain, table_id);
+ } else if (egress) {
tbl = &sh->tx_tbl[table_id];
if (!tbl->obj)
tbl->obj = mlx5_glue->dr_create_flow_tbl
- (sh->tx_ns, table_id);
+ (sh->tx_domain, table_id);
} else {
tbl = &sh->rx_tbl[table_id];
if (!tbl->obj)
tbl->obj = mlx5_glue->dr_create_flow_tbl
- (sh->rx_ns, table_id);
+ (sh->rx_domain, table_id);
}
if (!tbl->obj) {
rte_flow_error_set(error, ENOMEM,
#else
(void)error;
(void)tbl;
- if (egress)
+ if (transfer)
+ return &sh->fdb_tbl[table_id];
+ else if (egress)
return &sh->tx_tbl[table_id];
else
return &sh->rx_tbl[table_id];
matcher->priority == cache_matcher->priority &&
matcher->egress == cache_matcher->egress &&
matcher->group == cache_matcher->group &&
+ matcher->transfer == cache_matcher->transfer &&
!memcmp((const void *)matcher->mask.buf,
(const void *)cache_matcher->mask.buf,
cache_matcher->mask.size)) {
RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
"cannot allocate matcher memory");
tbl = flow_dv_tbl_resource_get(dev, matcher->group * MLX5_GROUP_FACTOR,
- matcher->egress, error);
+ matcher->egress, matcher->transfer,
+ error);
if (!tbl) {
rte_free(cache_matcher);
return rte_flow_error_set(error, ENOMEM,
return 0;
}
-/**
- * Add source vport match to the specified matcher.
- *
- * @param[in, out] matcher
- * Flow matcher.
- * @param[in, out] key
- * Flow matcher value.
- * @param[in] port
- * Source vport value to match
- * @param[in] mask
- * Mask
- */
-static void
-flow_dv_translate_source_vport(void *matcher, void *key,
- int16_t port, uint16_t mask)
-{
- void *misc_m = MLX5_ADDR_OF(fte_match_param, matcher, misc_parameters);
- void *misc_v = MLX5_ADDR_OF(fte_match_param, key, misc_parameters);
-
- MLX5_SET(fte_match_set_misc, misc_m, source_port, mask);
- MLX5_SET(fte_match_set_misc, misc_v, source_port, port);
-}
-
/**
* Find existing tag resource or create and register a new one.
*
return 1;
}
+/**
+ * Translate port ID action to vport.
+ *
+ * @param[in] dev
+ * Pointer to rte_eth_dev structure.
+ * @param[in] action
+ * Pointer to the port ID action.
+ * @param[out] dst_port_id
+ * The target port ID.
+ * @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_translate_action_port_id(struct rte_eth_dev *dev,
+ const struct rte_flow_action *action,
+ uint32_t *dst_port_id,
+ struct rte_flow_error *error)
+{
+ uint32_t port;
+ uint16_t port_id;
+ int ret;
+ const struct rte_flow_action_port_id *conf =
+ (const struct rte_flow_action_port_id *)action->conf;
+
+ port = conf->original ? dev->data->port_id : conf->id;
+ ret = mlx5_port_to_eswitch_info(port, NULL, &port_id);
+ if (ret)
+ return rte_flow_error_set(error, -ret,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ NULL,
+ "No eswitch info was found for port");
+ *dst_port_id = port_id;
+ return 0;
+}
+
/**
* Fill the flow with DV spec.
*
};
union flow_dv_attr flow_attr = { .attr = 0 };
struct mlx5_flow_dv_tag_resource tag_resource;
+ uint32_t modify_action_position = UINT32_MAX;
+ void *match_mask = matcher.mask.buf;
+ void *match_value = dev_flow->dv.value.buf;
+ flow->group = attr->group;
+ if (attr->transfer)
+ res.ft_type = MLX5DV_FLOW_TABLE_TYPE_FDB;
if (priority == MLX5_FLOW_PRIO_RSVD)
priority = priv->config.flow_prio - 1;
for (; !actions_end ; actions++) {
const struct rte_flow_action_jump *jump_data;
struct mlx5_flow_dv_jump_tbl_resource jump_tbl_resource;
struct mlx5_flow_tbl_resource *tbl;
+ uint32_t port_id = 0;
+ struct mlx5_flow_dv_port_id_action_resource port_id_resource;
switch (actions->type) {
case RTE_FLOW_ACTION_TYPE_VOID:
break;
+ case RTE_FLOW_ACTION_TYPE_PORT_ID:
+ if (flow_dv_translate_action_port_id(dev, action,
+ &port_id, error))
+ return -rte_errno;
+ port_id_resource.port_id = port_id;
+ if (flow_dv_port_id_action_resource_register
+ (dev, &port_id_resource, dev_flow, error))
+ return -rte_errno;
+ dev_flow->dv.actions[actions_n++] =
+ dev_flow->dv.port_id_action->action;
+ action_flags |= MLX5_FLOW_ACTION_PORT_ID;
+ break;
case RTE_FLOW_ACTION_TYPE_FLAG:
tag_resource.tag =
mlx5_flow_mark_set(MLX5_FLOW_MARK_DEFAULT);
case RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP:
case RTE_FLOW_ACTION_TYPE_NVGRE_ENCAP:
if (flow_dv_create_action_l2_encap(dev, actions,
- dev_flow, error))
+ dev_flow,
+ attr->transfer,
+ error))
return -rte_errno;
dev_flow->dv.actions[actions_n++] =
dev_flow->dv.encap_decap->verbs_action;
case RTE_FLOW_ACTION_TYPE_VXLAN_DECAP:
case RTE_FLOW_ACTION_TYPE_NVGRE_DECAP:
if (flow_dv_create_action_l2_decap(dev, dev_flow,
+ attr->transfer,
error))
return -rte_errno;
dev_flow->dv.actions[actions_n++] =
dev_flow->dv.encap_decap->verbs_action;
} else {
/* Handle encap without preceding decap. */
- if (flow_dv_create_action_l2_encap(dev, actions,
- dev_flow,
- error))
+ if (flow_dv_create_action_l2_encap
+ (dev, actions, dev_flow, attr->transfer,
+ error))
return -rte_errno;
dev_flow->dv.actions[actions_n++] =
dev_flow->dv.encap_decap->verbs_action;
}
/* Handle decap only if it isn't followed by encap. */
if (action->type != RTE_FLOW_ACTION_TYPE_RAW_ENCAP) {
- if (flow_dv_create_action_l2_decap(dev,
- dev_flow,
- error))
+ if (flow_dv_create_action_l2_decap
+ (dev, dev_flow, attr->transfer, error))
return -rte_errno;
dev_flow->dv.actions[actions_n++] =
dev_flow->dv.encap_decap->verbs_action;
jump_data = action->conf;
tbl = flow_dv_tbl_resource_get(dev, jump_data->group *
MLX5_GROUP_FACTOR,
- attr->egress, error);
+ attr->egress,
+ attr->transfer, error);
if (!tbl)
return rte_flow_error_set
(error, errno,
return -rte_errno;
action_flags |= MLX5_FLOW_ACTION_SET_TTL;
break;
+ case RTE_FLOW_ACTION_TYPE_INC_TCP_SEQ:
+ case RTE_FLOW_ACTION_TYPE_DEC_TCP_SEQ:
+ if (flow_dv_convert_action_modify_tcp_seq(&res, actions,
+ error))
+ return -rte_errno;
+ 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:
+ if (flow_dv_convert_action_modify_tcp_ack(&res, actions,
+ error))
+ return -rte_errno;
+ action_flags |= actions->type ==
+ RTE_FLOW_ACTION_TYPE_INC_TCP_ACK ?
+ MLX5_FLOW_ACTION_INC_TCP_ACK :
+ MLX5_FLOW_ACTION_DEC_TCP_ACK;
+ break;
case RTE_FLOW_ACTION_TYPE_END:
actions_end = true;
if (action_flags & MLX5_FLOW_MODIFY_HDR_ACTIONS) {
dev_flow,
error))
return -rte_errno;
- dev_flow->dv.actions[actions_n++] =
+ dev_flow->dv.actions[modify_action_position] =
dev_flow->dv.modify_hdr->verbs_action;
}
break;
default:
break;
}
+ if ((action_flags & MLX5_FLOW_MODIFY_HDR_ACTIONS) &&
+ modify_action_position == UINT32_MAX)
+ modify_action_position = actions_n++;
}
dev_flow->dv.actions_n = actions_n;
flow->actions = action_flags;
- if (attr->ingress && !attr->transfer &&
- (priv->representor || priv->master)) {
- /* It was validated - we support unidirection flows only. */
- assert(!attr->egress);
- /*
- * Add matching on source vport index only
- * for ingress rules in E-Switch configurations.
- */
- flow_dv_translate_source_vport(matcher.mask.buf,
- dev_flow->dv.value.buf,
- priv->vport_id,
- 0xffff);
- }
for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) {
int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
- void *match_mask = matcher.mask.buf;
- void *match_value = dev_flow->dv.value.buf;
switch (items->type) {
+ case RTE_FLOW_ITEM_TYPE_PORT_ID:
+ flow_dv_translate_item_port_id(dev, match_mask,
+ match_value, items);
+ last_item = MLX5_FLOW_ITEM_PORT_ID;
+ break;
case RTE_FLOW_ITEM_TYPE_ETH:
flow_dv_translate_item_eth(match_mask, match_value,
items, tunnel);
items);
last_item = MLX5_FLOW_ITEM_METADATA;
break;
+ case RTE_FLOW_ITEM_TYPE_ICMP:
+ flow_dv_translate_item_icmp(match_mask, match_value,
+ items, tunnel);
+ item_flags |= MLX5_FLOW_LAYER_ICMP;
+ break;
+ case RTE_FLOW_ITEM_TYPE_ICMP6:
+ flow_dv_translate_item_icmp6(match_mask, match_value,
+ items, tunnel);
+ item_flags |= MLX5_FLOW_LAYER_ICMP6;
+ break;
default:
break;
}
item_flags |= last_item;
}
+ /*
+ * In case of ingress traffic when E-Switch mode is enabled,
+ * we have two cases where we need to set the source port manually.
+ * The first one, is in case of Nic steering rule, and the second is
+ * E-Switch rule where no port_id item was found. In both cases
+ * the source port is set according the current port in use.
+ */
+ if ((attr->ingress && !(item_flags & MLX5_FLOW_ITEM_PORT_ID)) &&
+ (priv->representor || priv->master)) {
+ if (flow_dv_translate_item_port_id(dev, match_mask,
+ match_value, NULL))
+ return -rte_errno;
+ }
assert(!flow_dv_check_valid_spec(matcher.mask.buf,
dev_flow->dv.value.buf));
dev_flow->layers = item_flags;
matcher.priority);
matcher.egress = attr->egress;
matcher.group = attr->group;
+ matcher.transfer = attr->transfer;
if (flow_dv_matcher_register(dev, &matcher, dev_flow, error))
return -rte_errno;
return 0;
{
struct mlx5_flow_dv *dv;
struct mlx5_flow *dev_flow;
+ struct mlx5_priv *priv = dev->data->dev_private;
int n;
int err;
dv = &dev_flow->dv;
n = dv->actions_n;
if (flow->actions & MLX5_FLOW_ACTION_DROP) {
- dv->hrxq = mlx5_hrxq_drop_new(dev);
- if (!dv->hrxq) {
- rte_flow_error_set
- (error, errno,
- RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
- "cannot get drop hash queue");
- goto error;
+ if (flow->transfer) {
+ dv->actions[n++] = priv->sh->esw_drop_action;
+ } else {
+ dv->hrxq = mlx5_hrxq_drop_new(dev);
+ if (!dv->hrxq) {
+ rte_flow_error_set
+ (error, errno,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL,
+ "cannot get drop hash queue");
+ goto error;
+ }
+ dv->actions[n++] = dv->hrxq->action;
}
- dv->actions[n++] =
- mlx5_glue->dv_create_flow_action_dest_ibv_qp
- (dv->hrxq->qp);
} else if (flow->actions &
(MLX5_FLOW_ACTION_QUEUE | MLX5_FLOW_ACTION_RSS)) {
struct mlx5_hrxq *hrxq;
goto error;
}
dv->hrxq = hrxq;
- dv->actions[n++] =
- mlx5_glue->dv_create_flow_action_dest_ibv_qp
- (dv->hrxq->qp);
+ dv->actions[n++] = dv->hrxq->action;
}
dv->flow =
mlx5_glue->dv_create_flow(dv->matcher->matcher_object,
return 1;
}
+/**
+ * Release port ID action resource.
+ *
+ * @param flow
+ * Pointer to mlx5_flow.
+ *
+ * @return
+ * 1 while a reference on it exists, 0 when freed.
+ */
+static int
+flow_dv_port_id_action_resource_release(struct mlx5_flow *flow)
+{
+ struct mlx5_flow_dv_port_id_action_resource *cache_resource =
+ flow->dv.port_id_action;
+
+ assert(cache_resource->action);
+ DRV_LOG(DEBUG, "port ID action resource %p: refcnt %d--",
+ (void *)cache_resource,
+ rte_atomic32_read(&cache_resource->refcnt));
+ if (rte_atomic32_dec_and_test(&cache_resource->refcnt)) {
+ claim_zero(mlx5_glue->destroy_flow_action
+ (cache_resource->action));
+ LIST_REMOVE(cache_resource, next);
+ rte_free(cache_resource);
+ DRV_LOG(DEBUG, "port id action resource %p: removed",
+ (void *)cache_resource);
+ return 0;
+ }
+ return 1;
+}
+
/**
* Remove the flow from the NIC but keeps it in memory.
*
flow_dv_modify_hdr_resource_release(dev_flow);
if (dev_flow->dv.jump)
flow_dv_jump_tbl_resource_release(dev_flow);
+ if (dev_flow->dv.port_id_action)
+ flow_dv_port_id_action_resource_release(dev_flow);
rte_free(dev_flow);
}
}