From 84c406e74524e0a81e4d77034e7e4e72a32e5dd1 Mon Sep 17 00:00:00 2001 From: Ori Kam Date: Mon, 24 Sep 2018 23:17:39 +0000 Subject: [PATCH] net/mlx5: add flow translate function This commit modify the conversion of the input parameters into Verbs spec, in order to support all previous changes. Some of those changes are: removing the use of the parser, storing each flow in its own flow structure. Signed-off-by: Ori Kam Acked-by: Yongseok Koh --- drivers/net/mlx5/Makefile | 1 + drivers/net/mlx5/meson.build | 1 + drivers/net/mlx5/mlx5.c | 2 + drivers/net/mlx5/mlx5_flow.c | 2654 +++------------------------- drivers/net/mlx5/mlx5_flow.h | 259 +++ drivers/net/mlx5/mlx5_flow_verbs.c | 1697 ++++++++++++++++++ 6 files changed, 2172 insertions(+), 2442 deletions(-) create mode 100644 drivers/net/mlx5/mlx5_flow.h create mode 100644 drivers/net/mlx5/mlx5_flow_verbs.c diff --git a/drivers/net/mlx5/Makefile b/drivers/net/mlx5/Makefile index 2e70dec5ba..9bd6bfb829 100644 --- a/drivers/net/mlx5/Makefile +++ b/drivers/net/mlx5/Makefile @@ -31,6 +31,7 @@ SRCS-$(CONFIG_RTE_LIBRTE_MLX5_PMD) += mlx5_stats.c SRCS-$(CONFIG_RTE_LIBRTE_MLX5_PMD) += mlx5_rss.c SRCS-$(CONFIG_RTE_LIBRTE_MLX5_PMD) += mlx5_mr.c SRCS-$(CONFIG_RTE_LIBRTE_MLX5_PMD) += mlx5_flow.c +SRCS-$(CONFIG_RTE_LIBRTE_MLX5_PMD) += mlx5_flow_verbs.c SRCS-$(CONFIG_RTE_LIBRTE_MLX5_PMD) += mlx5_socket.c SRCS-$(CONFIG_RTE_LIBRTE_MLX5_PMD) += mlx5_nl.c SRCS-$(CONFIG_RTE_LIBRTE_MLX5_PMD) += mlx5_nl_flow.c diff --git a/drivers/net/mlx5/meson.build b/drivers/net/mlx5/meson.build index 289c7a4c07..40cc95038f 100644 --- a/drivers/net/mlx5/meson.build +++ b/drivers/net/mlx5/meson.build @@ -31,6 +31,7 @@ if build 'mlx5.c', 'mlx5_ethdev.c', 'mlx5_flow.c', + 'mlx5_flow_verbs.c', 'mlx5_mac.c', 'mlx5_mr.c', 'mlx5_nl.c', diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c index af4a78ce94..7493180afc 100644 --- a/drivers/net/mlx5/mlx5.c +++ b/drivers/net/mlx5/mlx5.c @@ -46,6 +46,7 @@ #include "mlx5_defs.h" #include "mlx5_glue.h" #include "mlx5_mr.h" +#include "mlx5_flow.h" /* Device parameter to enable RX completion queue compression. */ #define MLX5_RXQ_CQE_COMP_EN "rxq_cqe_comp_en" @@ -1187,6 +1188,7 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, if (err < 0) goto error; priv->config.flow_prio = err; + mlx5_flow_init_driver_ops(eth_dev); /* * Once the device is added to the list of memory event * callback, its global MR cache table cannot be expanded diff --git a/drivers/net/mlx5/mlx5_flow.c b/drivers/net/mlx5/mlx5_flow.c index 83155c7a07..6c3046640b 100644 --- a/drivers/net/mlx5/mlx5_flow.c +++ b/drivers/net/mlx5/mlx5_flow.c @@ -3,6 +3,7 @@ * Copyright 2016 Mellanox Technologies, Ltd */ +#include #include #include #include @@ -31,86 +32,12 @@ #include "mlx5_defs.h" #include "mlx5_prm.h" #include "mlx5_glue.h" +#include "mlx5_flow.h" /* Dev ops structure defined in mlx5.c */ extern const struct eth_dev_ops mlx5_dev_ops; extern const struct eth_dev_ops mlx5_dev_ops_isolate; -/* Pattern outer Layer bits. */ -#define MLX5_FLOW_LAYER_OUTER_L2 (1u << 0) -#define MLX5_FLOW_LAYER_OUTER_L3_IPV4 (1u << 1) -#define MLX5_FLOW_LAYER_OUTER_L3_IPV6 (1u << 2) -#define MLX5_FLOW_LAYER_OUTER_L4_UDP (1u << 3) -#define MLX5_FLOW_LAYER_OUTER_L4_TCP (1u << 4) -#define MLX5_FLOW_LAYER_OUTER_VLAN (1u << 5) - -/* Pattern inner Layer bits. */ -#define MLX5_FLOW_LAYER_INNER_L2 (1u << 6) -#define MLX5_FLOW_LAYER_INNER_L3_IPV4 (1u << 7) -#define MLX5_FLOW_LAYER_INNER_L3_IPV6 (1u << 8) -#define MLX5_FLOW_LAYER_INNER_L4_UDP (1u << 9) -#define MLX5_FLOW_LAYER_INNER_L4_TCP (1u << 10) -#define MLX5_FLOW_LAYER_INNER_VLAN (1u << 11) - -/* Pattern tunnel Layer bits. */ -#define MLX5_FLOW_LAYER_VXLAN (1u << 12) -#define MLX5_FLOW_LAYER_VXLAN_GPE (1u << 13) -#define MLX5_FLOW_LAYER_GRE (1u << 14) -#define MLX5_FLOW_LAYER_MPLS (1u << 15) - -/* Outer Masks. */ -#define MLX5_FLOW_LAYER_OUTER_L3 \ - (MLX5_FLOW_LAYER_OUTER_L3_IPV4 | MLX5_FLOW_LAYER_OUTER_L3_IPV6) -#define MLX5_FLOW_LAYER_OUTER_L4 \ - (MLX5_FLOW_LAYER_OUTER_L4_UDP | MLX5_FLOW_LAYER_OUTER_L4_TCP) -#define MLX5_FLOW_LAYER_OUTER \ - (MLX5_FLOW_LAYER_OUTER_L2 | MLX5_FLOW_LAYER_OUTER_L3 | \ - MLX5_FLOW_LAYER_OUTER_L4) - -/* Tunnel Masks. */ -#define MLX5_FLOW_LAYER_TUNNEL \ - (MLX5_FLOW_LAYER_VXLAN | MLX5_FLOW_LAYER_VXLAN_GPE | \ - MLX5_FLOW_LAYER_GRE | MLX5_FLOW_LAYER_MPLS) - -/* Inner Masks. */ -#define MLX5_FLOW_LAYER_INNER_L3 \ - (MLX5_FLOW_LAYER_INNER_L3_IPV4 | MLX5_FLOW_LAYER_INNER_L3_IPV6) -#define MLX5_FLOW_LAYER_INNER_L4 \ - (MLX5_FLOW_LAYER_INNER_L4_UDP | MLX5_FLOW_LAYER_INNER_L4_TCP) -#define MLX5_FLOW_LAYER_INNER \ - (MLX5_FLOW_LAYER_INNER_L2 | MLX5_FLOW_LAYER_INNER_L3 | \ - MLX5_FLOW_LAYER_INNER_L4) - -/* Actions that modify the fate of matching traffic. */ -#define MLX5_FLOW_FATE_DROP (1u << 0) -#define MLX5_FLOW_FATE_QUEUE (1u << 1) -#define MLX5_FLOW_FATE_RSS (1u << 2) - -/* Modify a packet. */ -#define MLX5_FLOW_MOD_FLAG (1u << 0) -#define MLX5_FLOW_MOD_MARK (1u << 1) -#define MLX5_FLOW_MOD_COUNT (1u << 2) - -/* Actions */ -#define MLX5_FLOW_ACTION_DROP (1u << 0) -#define MLX5_FLOW_ACTION_QUEUE (1u << 1) -#define MLX5_FLOW_ACTION_RSS (1u << 2) -#define MLX5_FLOW_ACTION_FLAG (1u << 3) -#define MLX5_FLOW_ACTION_MARK (1u << 4) -#define MLX5_FLOW_ACTION_COUNT (1u << 5) - -#define MLX5_FLOW_FATE_ACTIONS \ - (MLX5_FLOW_ACTION_DROP | MLX5_FLOW_ACTION_QUEUE | MLX5_FLOW_ACTION_RSS) - -/* possible L3 layers protocols filtering. */ -#define MLX5_IP_PROTOCOL_TCP 6 -#define MLX5_IP_PROTOCOL_UDP 17 -#define MLX5_IP_PROTOCOL_GRE 47 -#define MLX5_IP_PROTOCOL_MPLS 147 - -/* Priority reserved for default flows. */ -#define MLX5_FLOW_PRIO_RSVD ((uint32_t)-1) - enum mlx5_expansion { MLX5_EXPANSION_ROOT, MLX5_EXPANSION_ROOT_OUTER, @@ -281,62 +208,6 @@ static const struct rte_flow_expand_node mlx5_support_expansion[] = { }, }; -/** Handles information leading to a drop fate. */ -struct mlx5_flow_verbs { - LIST_ENTRY(mlx5_flow_verbs) next; - unsigned int size; /**< Size of the attribute. */ - struct { - struct ibv_flow_attr *attr; - /**< Pointer to the Specification buffer. */ - uint8_t *specs; /**< Pointer to the specifications. */ - }; - struct ibv_flow *flow; /**< Verbs flow pointer. */ - struct mlx5_hrxq *hrxq; /**< Hash Rx queue object. */ - uint64_t hash_fields; /**< Verbs hash Rx queue hash fields. */ -}; - -/** Device flow structure. */ -struct mlx5_flow { - LIST_ENTRY(mlx5_flow) next; - struct rte_flow *flow; /**< Pointer to the main flow. */ - union { - struct mlx5_flow_verbs verbs; /**< Holds the verbs dev-flow. */ - }; -}; - -/* Counters information. */ -struct mlx5_flow_counter { - LIST_ENTRY(mlx5_flow_counter) next; /**< Pointer to the next counter. */ - uint32_t shared:1; /**< Share counter ID with other flow rules. */ - uint32_t ref_cnt:31; /**< Reference counter. */ - uint32_t id; /**< Counter ID. */ - struct ibv_counter_set *cs; /**< Holds the counters for the rule. */ - uint64_t hits; /**< Number of packets matched by the rule. */ - uint64_t bytes; /**< Number of bytes matched by the rule. */ -}; - -/* Flow structure. */ -struct rte_flow { - TAILQ_ENTRY(rte_flow) next; /**< Pointer to the next flow structure. */ - struct rte_flow_attr attributes; /**< User flow attribute. */ - uint32_t layers; - /**< Bit-fields of present layers see MLX5_FLOW_LAYER_*. */ - uint32_t modifier; - /**< Bit-fields of present modifier see MLX5_FLOW_MOD_*. */ - uint32_t fate; - /**< Bit-fields of present fate see MLX5_FLOW_FATE_*. */ - LIST_HEAD(verbs, mlx5_flow_verbs) verbs; /**< Verbs flows list. */ - struct mlx5_flow_verbs *cur_verbs; - /**< Current Verbs flow structure being filled. */ - struct mlx5_flow_counter *counter; /**< Holds Verbs flow counter. */ - struct rte_flow_action_rss rss;/**< RSS context. */ - uint8_t key[MLX5_RSS_HASH_KEY_LEN]; /**< RSS hash key. */ - uint16_t (*queue)[]; /**< Destination queues to redirect traffic to. */ - void *nl_flow; /**< Netlink flow buffer if relevant. */ - LIST_HEAD(dev_flows, mlx5_flow) dev_flows; - /**< Device flows that are part of the flow. */ -}; - static const struct rte_flow_ops mlx5_flow_ops = { .validate = mlx5_flow_validate, .create = mlx5_flow_create, @@ -372,23 +243,6 @@ struct mlx5_fdir { struct rte_flow_action_queue queue; }; -/* Verbs specification header. */ -struct ibv_spec_header { - enum ibv_flow_spec_type type; - uint16_t size; -}; - -/* - * Number of sub priorities. - * For each kind of pattern matching i.e. L2, L3, L4 to have a correct - * matching on the NIC (firmware dependent) L4 most have the higher priority - * followed by L3 and ending with L2. - */ -#define MLX5_PRIORITY_MAP_L2 2 -#define MLX5_PRIORITY_MAP_L3 1 -#define MLX5_PRIORITY_MAP_L4 0 -#define MLX5_PRIORITY_MAP_MAX 3 - /* Map of Verbs to Flow priority with 8 Verbs priorities. */ static const uint32_t priority_map_3[][MLX5_PRIORITY_MAP_MAX] = { { 0, 1, 2 }, { 2, 3, 4 }, { 5, 6, 7 }, @@ -429,11 +283,14 @@ static struct mlx5_flow_tunnel_info tunnels_info[] = { }, }; +/* Holds the nic operations that should be used. */ +struct mlx5_flow_driver_ops nic_ops; + /** * Discover the maximum number of priority available. * * @param[in] dev - * Pointer to Ethernet device. + * Pointer to the Ethernet device structure. * * @return * number of supported flow priority on success, a negative errno @@ -498,131 +355,33 @@ mlx5_flow_discover_priorities(struct rte_eth_dev *dev) } /** - * Adjust flow priority. + * Adjust flow priority based on the highest layer and the request priority. * - * @param dev - * Pointer to Ethernet device. - * @param flow - * Pointer to an rte flow. + * @param[in] dev + * Pointer to the Ethernet device structure. + * @param[in] priority + * The rule base priority. + * @param[in] subpriority + * The priority based on the items. + * + * @return + * The new priority. */ -static void -mlx5_flow_adjust_priority(struct rte_eth_dev *dev, struct rte_flow *flow) +uint32_t mlx5_flow_adjust_priority(struct rte_eth_dev *dev, int32_t priority, + uint32_t subpriority) { + uint32_t res = 0; struct priv *priv = dev->data->dev_private; - uint32_t priority = flow->attributes.priority; - uint32_t subpriority = flow->cur_verbs->attr->priority; switch (priv->config.flow_prio) { case RTE_DIM(priority_map_3): - priority = priority_map_3[priority][subpriority]; + res = priority_map_3[priority][subpriority]; break; case RTE_DIM(priority_map_5): - priority = priority_map_5[priority][subpriority]; + res = priority_map_5[priority][subpriority]; break; } - flow->cur_verbs->attr->priority = priority; -} - -/** - * Get a flow counter. - * - * @param[in] dev - * Pointer to Ethernet device. - * @param[in] shared - * Indicate if this counter is shared with other flows. - * @param[in] id - * Counter identifier. - * - * @return - * A pointer to the counter, NULL otherwise and rte_errno is set. - */ -static struct mlx5_flow_counter * -mlx5_flow_counter_new(struct rte_eth_dev *dev, uint32_t shared, uint32_t id) -{ - struct priv *priv = dev->data->dev_private; - struct mlx5_flow_counter *cnt; - - LIST_FOREACH(cnt, &priv->flow_counters, next) { - if (!cnt->shared || cnt->shared != shared) - continue; - if (cnt->id != id) - continue; - cnt->ref_cnt++; - return cnt; - } -#ifdef HAVE_IBV_DEVICE_COUNTERS_SET_SUPPORT - - struct mlx5_flow_counter tmpl = { - .shared = shared, - .id = id, - .cs = mlx5_glue->create_counter_set - (priv->ctx, - &(struct ibv_counter_set_init_attr){ - .counter_set_id = id, - }), - .hits = 0, - .bytes = 0, - }; - - if (!tmpl.cs) { - rte_errno = errno; - return NULL; - } - cnt = rte_calloc(__func__, 1, sizeof(*cnt), 0); - if (!cnt) { - rte_errno = ENOMEM; - return NULL; - } - *cnt = tmpl; - LIST_INSERT_HEAD(&priv->flow_counters, cnt, next); - return cnt; -#endif - rte_errno = ENOTSUP; - return NULL; -} - -/** - * Release a flow counter. - * - * @param[in] counter - * Pointer to the counter handler. - */ -static void -mlx5_flow_counter_release(struct mlx5_flow_counter *counter) -{ - if (--counter->ref_cnt == 0) { - claim_zero(mlx5_glue->destroy_counter_set(counter->cs)); - LIST_REMOVE(counter, next); - rte_free(counter); - } -} - -/** - * 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 Ethernet device structure. - * @param[in] attributes - * Pointer to flow attributes - * @param[in, out] flow - * Pointer to the rte_flow structure. - * - * @return - * 0 on success. - */ -static int -mlx5_flow_attributes(struct rte_eth_dev *dev, - const struct rte_flow_attr *attributes, - struct rte_flow *flow) -{ - struct priv *priv = dev->data->dev_private; - uint32_t priority_max = priv->config.flow_prio - 1; - - flow->attributes = *attributes; - if (attributes->priority == MLX5_FLOW_PRIO_RSVD) - flow->attributes.priority = priority_max; - return 0; + return res; } /** @@ -686,1659 +445,161 @@ mlx5_flow_item_acceptable(const struct rte_flow_item *item, } /** - * Add a verbs item specification into @p flow. + * 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[in, out] flow - * Pointer to flow structure. - * @param[in] src - * Create specification. - * @param[in] size - * Size in bytes of the specification to copy. + * @param rxq_ctrl + * Rx queue to update. */ static void -mlx5_flow_spec_verbs_add(struct rte_flow *flow, void *src, unsigned int size) +mlx5_flow_rxq_tunnel_ptype_update(struct mlx5_rxq_ctrl *rxq_ctrl) { - struct mlx5_flow_verbs *verbs = flow->cur_verbs; - - if (verbs->specs) { - void *dst; + unsigned int i; + uint32_t tunnel_ptype = 0; - dst = (void *)(verbs->specs + verbs->size); - memcpy(dst, src, size); - ++verbs->attr->num_of_specs; + /* 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; + } } - verbs->size += size; + rxq_ctrl->rxq.tunnel = tunnel_ptype; } /** - * Adjust verbs hash fields according to the @p flow information. + * Set the Rx queue flags (Mark/Flag and Tunnel Ptypes) according to the flow. * - * @param[in, out] flow. + * @param[in] dev + * Pointer to the Ethernet device structure. + * @param[in] flow * Pointer to flow structure. - * @param[in] tunnel - * 1 when the hash field is for a tunnel item. - * @param[in] layer_types - * ETH_RSS_* types. - * @param[in] hash_fields - * Item hash fields. */ static void -mlx5_flow_verbs_hashfields_adjust(struct rte_flow *flow, - int tunnel __rte_unused, - uint32_t layer_types, uint64_t hash_fields) -{ -#ifdef HAVE_IBV_DEVICE_TUNNEL_SUPPORT - hash_fields |= (tunnel ? IBV_RX_HASH_INNER : 0); - if (flow->rss.level == 2 && !tunnel) - hash_fields = 0; - else if (flow->rss.level < 2 && tunnel) - hash_fields = 0; -#endif - if (!(flow->rss.types & layer_types)) - hash_fields = 0; - flow->cur_verbs->hash_fields |= hash_fields; -} - -/** - * 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. - * - * @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_eth(const struct rte_flow_item *item, struct rte_flow *flow, - const size_t flow_size) +mlx5_flow_rxq_flags_set(struct rte_eth_dev *dev, struct rte_flow *flow) { - const struct rte_flow_item_eth *spec = item->spec; - const struct rte_flow_item_eth *mask = item->mask; + struct priv *priv = dev->data->dev_private; + const int mark = !!(flow->actions & + (MLX5_FLOW_ACTION_FLAG | MLX5_FLOW_ACTION_MARK)); const int tunnel = !!(flow->layers & MLX5_FLOW_LAYER_TUNNEL); - const unsigned int size = sizeof(struct ibv_flow_spec_eth); - struct ibv_flow_spec_eth eth = { - .type = IBV_FLOW_SPEC_ETH | (tunnel ? IBV_FLOW_SPEC_INNER : 0), - .size = size, - }; + unsigned int i; - if (!mask) - mask = &rte_flow_item_eth_mask; - flow->layers |= tunnel ? MLX5_FLOW_LAYER_INNER_L2 : - MLX5_FLOW_LAYER_OUTER_L2; - if (size > flow_size) - return size; - if (spec) { - 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; - memcpy(ð.val.dst_mac, spec->dst.addr_bytes, ETHER_ADDR_LEN); - memcpy(ð.val.src_mac, spec->src.addr_bytes, ETHER_ADDR_LEN); - eth.val.ether_type = spec->type; - memcpy(ð.mask.dst_mac, mask->dst.addr_bytes, ETHER_ADDR_LEN); - memcpy(ð.mask.src_mac, mask->src.addr_bytes, ETHER_ADDR_LEN); - eth.mask.ether_type = mask->type; - /* Remove unwanted bits from values. */ - for (i = 0; i < ETHER_ADDR_LEN; ++i) { - eth.val.dst_mac[i] &= eth.mask.dst_mac[i]; - eth.val.src_mac[i] &= eth.mask.src_mac[i]; + /* 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); } - eth.val.ether_type &= eth.mask.ether_type; } - flow->cur_verbs->attr->priority = MLX5_PRIORITY_MAP_L2; - mlx5_flow_spec_verbs_add(flow, ð, size); - return size; } /** - * Update the VLAN tag in the Verbs Ethernet specification. + * 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[in, out] attr - * Pointer to Verbs attributes structure. - * @param[in] eth - * Verbs structure containing the VLAN information to copy. + * @param dev + * Pointer to Ethernet device. + * @param[in] flow + * Pointer to the flow. */ static void -mlx5_flow_item_vlan_update(struct ibv_flow_attr *attr, - struct ibv_flow_spec_eth *eth) +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->actions & + (MLX5_FLOW_ACTION_FLAG | MLX5_FLOW_ACTION_MARK)); + const int tunnel = !!(flow->layers & MLX5_FLOW_LAYER_TUNNEL); unsigned int i; - const enum ibv_flow_spec_type search = eth->type; - struct ibv_spec_header *hdr = (struct ibv_spec_header *) - ((uint8_t *)attr + sizeof(struct ibv_flow_attr)); - for (i = 0; i != attr->num_of_specs; ++i) { - if (hdr->type == search) { - struct ibv_flow_spec_eth *e = - (struct ibv_flow_spec_eth *)hdr; + 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; - e->val.vlan_tag = eth->val.vlan_tag; - e->mask.vlan_tag = eth->mask.vlan_tag; - e->val.ether_type = eth->val.ether_type; - e->mask.ether_type = eth->mask.ether_type; - break; + /* 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); } - hdr = (struct ibv_spec_header *)((uint8_t *)hdr + hdr->size); } } /** - * Convert the @p item into @p flow (or by updating the already present - * Ethernet 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. + * Clear the Mark/Flag and Tunnel ptype information in all Rx queues. * - * @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. + * @param dev + * Pointer to Ethernet device. */ -static int -mlx5_flow_item_vlan(const struct rte_flow_item *item, struct rte_flow *flow, - const size_t flow_size) +static void +mlx5_flow_rxq_flags_clear(struct rte_eth_dev *dev) { - const struct rte_flow_item_vlan *spec = item->spec; - const struct rte_flow_item_vlan *mask = item->mask; - unsigned int size = sizeof(struct ibv_flow_spec_eth); - const int tunnel = !!(flow->layers & MLX5_FLOW_LAYER_TUNNEL); - struct ibv_flow_spec_eth eth = { - .type = IBV_FLOW_SPEC_ETH | (tunnel ? IBV_FLOW_SPEC_INNER : 0), - .size = size, - }; - const uint32_t l2m = tunnel ? MLX5_FLOW_LAYER_INNER_L2 : - MLX5_FLOW_LAYER_OUTER_L2; + struct priv *priv = dev->data->dev_private; + unsigned int i; - if (!mask) - mask = &rte_flow_item_vlan_mask; - if (spec) { - eth.val.vlan_tag = spec->tci; - eth.mask.vlan_tag = mask->tci; - eth.val.vlan_tag &= eth.mask.vlan_tag; - eth.val.ether_type = spec->inner_type; - eth.mask.ether_type = mask->inner_type; - eth.val.ether_type &= eth.mask.ether_type; - } - if (!(flow->layers & l2m)) { - if (size <= flow_size) { - flow->cur_verbs->attr->priority = MLX5_PRIORITY_MAP_L2; - mlx5_flow_spec_verbs_add(flow, ð, size); - } - } else { - if (flow->cur_verbs) - mlx5_flow_item_vlan_update(flow->cur_verbs->attr, - ð); - size = 0; /* Only an update is done in eth specification. */ + 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; } - flow->layers |= tunnel ? - (MLX5_FLOW_LAYER_INNER_L2 | MLX5_FLOW_LAYER_INNER_VLAN) : - (MLX5_FLOW_LAYER_OUTER_L2 | MLX5_FLOW_LAYER_OUTER_VLAN); - 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. +/* + * Validate the flag action. * - * @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[in] action_flags + * Bit-fields that holds the actions detected until now. + * @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. + * 0 on success, a negative errno value otherwise and rte_errno is set. */ -static int -mlx5_flow_item_ipv4(const struct rte_flow_item *item, struct rte_flow *flow, - const size_t flow_size) -{ - const struct rte_flow_item_ipv4 *spec = item->spec; - const struct rte_flow_item_ipv4 *mask = item->mask; - const int tunnel = !!(flow->layers & MLX5_FLOW_LAYER_TUNNEL); - unsigned int size = sizeof(struct ibv_flow_spec_ipv4_ext); - struct ibv_flow_spec_ipv4_ext ipv4 = { - .type = IBV_FLOW_SPEC_IPV4_EXT | - (tunnel ? IBV_FLOW_SPEC_INNER : 0), - .size = size, - }; - - if (!mask) - mask = &rte_flow_item_ipv4_mask; - flow->layers |= tunnel ? MLX5_FLOW_LAYER_INNER_L3_IPV4 : - MLX5_FLOW_LAYER_OUTER_L3_IPV4; - if (spec) { - ipv4.val = (struct ibv_flow_ipv4_ext_filter){ - .src_ip = spec->hdr.src_addr, - .dst_ip = spec->hdr.dst_addr, - .proto = spec->hdr.next_proto_id, - .tos = spec->hdr.type_of_service, - }; - ipv4.mask = (struct ibv_flow_ipv4_ext_filter){ - .src_ip = mask->hdr.src_addr, - .dst_ip = mask->hdr.dst_addr, - .proto = mask->hdr.next_proto_id, - .tos = mask->hdr.type_of_service, - }; - /* Remove unwanted bits from values. */ - ipv4.val.src_ip &= ipv4.mask.src_ip; - ipv4.val.dst_ip &= ipv4.mask.dst_ip; - ipv4.val.proto &= ipv4.mask.proto; - ipv4.val.tos &= ipv4.mask.tos; - } - if (size <= flow_size) { - mlx5_flow_verbs_hashfields_adjust - (flow, tunnel, - (ETH_RSS_IPV4 | ETH_RSS_FRAG_IPV4 | - ETH_RSS_NONFRAG_IPV4_TCP | - ETH_RSS_NONFRAG_IPV4_UDP | - ETH_RSS_NONFRAG_IPV4_OTHER), - (IBV_RX_HASH_SRC_IPV4 | IBV_RX_HASH_DST_IPV4)); - flow->cur_verbs->attr->priority = MLX5_PRIORITY_MAP_L3; - mlx5_flow_spec_verbs_add(flow, &ipv4, size); - } - 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. - * - * @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_ipv6(const struct rte_flow_item *item, struct rte_flow *flow, - const size_t flow_size) -{ - const struct rte_flow_item_ipv6 *spec = item->spec; - const struct rte_flow_item_ipv6 *mask = item->mask; - const int tunnel = !!(flow->layers & MLX5_FLOW_LAYER_TUNNEL); - unsigned int size = sizeof(struct ibv_flow_spec_ipv6); - struct ibv_flow_spec_ipv6 ipv6 = { - .type = IBV_FLOW_SPEC_IPV6 | (tunnel ? IBV_FLOW_SPEC_INNER : 0), - .size = size, - }; - - if (!mask) - mask = &rte_flow_item_ipv6_mask; - flow->layers |= tunnel ? MLX5_FLOW_LAYER_INNER_L3_IPV6 : - MLX5_FLOW_LAYER_OUTER_L3_IPV6; - if (spec) { - unsigned int i; - uint32_t vtc_flow_val; - uint32_t vtc_flow_mask; - - memcpy(&ipv6.val.src_ip, spec->hdr.src_addr, - RTE_DIM(ipv6.val.src_ip)); - memcpy(&ipv6.val.dst_ip, spec->hdr.dst_addr, - RTE_DIM(ipv6.val.dst_ip)); - memcpy(&ipv6.mask.src_ip, mask->hdr.src_addr, - RTE_DIM(ipv6.mask.src_ip)); - memcpy(&ipv6.mask.dst_ip, mask->hdr.dst_addr, - RTE_DIM(ipv6.mask.dst_ip)); - vtc_flow_val = rte_be_to_cpu_32(spec->hdr.vtc_flow); - vtc_flow_mask = rte_be_to_cpu_32(mask->hdr.vtc_flow); - ipv6.val.flow_label = - rte_cpu_to_be_32((vtc_flow_val & IPV6_HDR_FL_MASK) >> - IPV6_HDR_FL_SHIFT); - ipv6.val.traffic_class = (vtc_flow_val & IPV6_HDR_TC_MASK) >> - IPV6_HDR_TC_SHIFT; - ipv6.val.next_hdr = spec->hdr.proto; - ipv6.val.hop_limit = spec->hdr.hop_limits; - ipv6.mask.flow_label = - rte_cpu_to_be_32((vtc_flow_mask & IPV6_HDR_FL_MASK) >> - IPV6_HDR_FL_SHIFT); - ipv6.mask.traffic_class = (vtc_flow_mask & IPV6_HDR_TC_MASK) >> - IPV6_HDR_TC_SHIFT; - ipv6.mask.next_hdr = mask->hdr.proto; - ipv6.mask.hop_limit = mask->hdr.hop_limits; - /* Remove unwanted bits from values. */ - for (i = 0; i < RTE_DIM(ipv6.val.src_ip); ++i) { - ipv6.val.src_ip[i] &= ipv6.mask.src_ip[i]; - ipv6.val.dst_ip[i] &= ipv6.mask.dst_ip[i]; - } - ipv6.val.flow_label &= ipv6.mask.flow_label; - ipv6.val.traffic_class &= ipv6.mask.traffic_class; - ipv6.val.next_hdr &= ipv6.mask.next_hdr; - ipv6.val.hop_limit &= ipv6.mask.hop_limit; - } - if (size <= flow_size) { - mlx5_flow_verbs_hashfields_adjust - (flow, tunnel, - (ETH_RSS_IPV6 | ETH_RSS_FRAG_IPV6 | - ETH_RSS_NONFRAG_IPV6_TCP | ETH_RSS_NONFRAG_IPV6_UDP | - ETH_RSS_NONFRAG_IPV6_OTHER | ETH_RSS_IPV6_EX | - ETH_RSS_IPV6_TCP_EX | ETH_RSS_IPV6_UDP_EX), - (IBV_RX_HASH_SRC_IPV6 | IBV_RX_HASH_DST_IPV6)); - flow->cur_verbs->attr->priority = MLX5_PRIORITY_MAP_L3; - mlx5_flow_spec_verbs_add(flow, &ipv6, size); - } - 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. - * - * @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_udp(const struct rte_flow_item *item, struct rte_flow *flow, - const size_t flow_size) -{ - const struct rte_flow_item_udp *spec = item->spec; - const struct rte_flow_item_udp *mask = item->mask; - const int tunnel = !!(flow->layers & MLX5_FLOW_LAYER_TUNNEL); - unsigned int size = sizeof(struct ibv_flow_spec_tcp_udp); - struct ibv_flow_spec_tcp_udp udp = { - .type = IBV_FLOW_SPEC_UDP | (tunnel ? IBV_FLOW_SPEC_INNER : 0), - .size = size, - }; - - if (!mask) - mask = &rte_flow_item_udp_mask; - flow->layers |= tunnel ? MLX5_FLOW_LAYER_INNER_L4_UDP : - MLX5_FLOW_LAYER_OUTER_L4_UDP; - if (spec) { - udp.val.dst_port = spec->hdr.dst_port; - udp.val.src_port = spec->hdr.src_port; - udp.mask.dst_port = mask->hdr.dst_port; - udp.mask.src_port = mask->hdr.src_port; - /* Remove unwanted bits from values. */ - udp.val.src_port &= udp.mask.src_port; - udp.val.dst_port &= udp.mask.dst_port; - } - if (size <= flow_size) { - mlx5_flow_verbs_hashfields_adjust(flow, tunnel, ETH_RSS_UDP, - (IBV_RX_HASH_SRC_PORT_UDP | - IBV_RX_HASH_DST_PORT_UDP)); - flow->cur_verbs->attr->priority = MLX5_PRIORITY_MAP_L4; - mlx5_flow_spec_verbs_add(flow, &udp, size); - } - 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. - */ -static int -mlx5_flow_item_tcp(const struct rte_flow_item *item, struct rte_flow *flow, - const size_t flow_size) -{ - const struct rte_flow_item_tcp *spec = item->spec; - const struct rte_flow_item_tcp *mask = item->mask; - const int tunnel = !!(flow->layers & MLX5_FLOW_LAYER_TUNNEL); - unsigned int size = sizeof(struct ibv_flow_spec_tcp_udp); - struct ibv_flow_spec_tcp_udp tcp = { - .type = IBV_FLOW_SPEC_TCP | (tunnel ? IBV_FLOW_SPEC_INNER : 0), - .size = size, - }; - - if (!mask) - mask = &rte_flow_item_tcp_mask; - flow->layers |= tunnel ? MLX5_FLOW_LAYER_INNER_L4_TCP : - MLX5_FLOW_LAYER_OUTER_L4_TCP; - if (spec) { - tcp.val.dst_port = spec->hdr.dst_port; - tcp.val.src_port = spec->hdr.src_port; - tcp.mask.dst_port = mask->hdr.dst_port; - tcp.mask.src_port = mask->hdr.src_port; - /* Remove unwanted bits from values. */ - tcp.val.src_port &= tcp.mask.src_port; - tcp.val.dst_port &= tcp.mask.dst_port; - } - if (size <= flow_size) { - mlx5_flow_verbs_hashfields_adjust(flow, tunnel, ETH_RSS_TCP, - (IBV_RX_HASH_SRC_PORT_TCP | - IBV_RX_HASH_DST_PORT_TCP)); - flow->cur_verbs->attr->priority = MLX5_PRIORITY_MAP_L4; - mlx5_flow_spec_verbs_add(flow, &tcp, size); - } - 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. - */ -static int -mlx5_flow_item_vxlan(const struct rte_flow_item *item, struct rte_flow *flow, - const size_t flow_size) -{ - const struct rte_flow_item_vxlan *spec = item->spec; - const struct rte_flow_item_vxlan *mask = item->mask; - unsigned int size = sizeof(struct ibv_flow_spec_tunnel); - struct ibv_flow_spec_tunnel vxlan = { - .type = IBV_FLOW_SPEC_VXLAN_TUNNEL, - .size = size, - }; - union vni { - uint32_t vlan_id; - uint8_t vni[4]; - } id = { .vlan_id = 0, }; - - if (!mask) - mask = &rte_flow_item_vxlan_mask; - if (spec) { - memcpy(&id.vni[1], spec->vni, 3); - vxlan.val.tunnel_id = id.vlan_id; - memcpy(&id.vni[1], mask->vni, 3); - vxlan.mask.tunnel_id = id.vlan_id; - /* Remove unwanted bits from values. */ - vxlan.val.tunnel_id &= vxlan.mask.tunnel_id; - } - if (size <= flow_size) { - mlx5_flow_spec_verbs_add(flow, &vxlan, size); - flow->cur_verbs->attr->priority = MLX5_PRIORITY_MAP_L2; - } - flow->layers |= MLX5_FLOW_LAYER_VXLAN; - 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. - */ -static int -mlx5_flow_item_vxlan_gpe(const struct rte_flow_item *item, - struct rte_flow *flow, const size_t flow_size) -{ - const struct rte_flow_item_vxlan_gpe *spec = item->spec; - const struct rte_flow_item_vxlan_gpe *mask = item->mask; - unsigned int size = sizeof(struct ibv_flow_spec_tunnel); - struct ibv_flow_spec_tunnel vxlan_gpe = { - .type = IBV_FLOW_SPEC_VXLAN_TUNNEL, - .size = size, - }; - union vni { - uint32_t vlan_id; - uint8_t vni[4]; - } 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 +int mlx5_flow_validate_action_flag(uint64_t action_flags, struct rte_flow_error *error) { @@ -2372,7 +633,7 @@ mlx5_flow_validate_action_flag(uint64_t action_flags, * @return * 0 on success, a negative errno value otherwise and rte_errno is set. */ -static int +int mlx5_flow_validate_action_mark(const struct rte_flow_action *action, uint64_t action_flags, struct rte_flow_error *error) @@ -2417,7 +678,7 @@ mlx5_flow_validate_action_mark(const struct rte_flow_action *action, * @return * 0 on success, a negative errno value otherwise and rte_ernno is set. */ -static int +int mlx5_flow_validate_action_drop(uint64_t action_flags, struct rte_flow_error *error) { @@ -2452,7 +713,7 @@ mlx5_flow_validate_action_drop(uint64_t action_flags, * @return * 0 on success, a negative errno value otherwise and rte_ernno is set. */ -static int +int mlx5_flow_validate_action_queue(const struct rte_flow_action *action, uint64_t action_flags, struct rte_eth_dev *dev, @@ -2494,7 +755,7 @@ mlx5_flow_validate_action_queue(const struct rte_flow_action *action, * @return * 0 on success, a negative errno value otherwise and rte_ernno is set. */ -static int +int mlx5_flow_validate_action_rss(const struct rte_flow_action *action, uint64_t action_flags, struct rte_eth_dev *dev, @@ -2565,7 +826,7 @@ mlx5_flow_validate_action_rss(const struct rte_flow_action *action, * @return * 0 on success, a negative errno value otherwise and rte_ernno is set. */ -static int +int mlx5_flow_validate_action_count(struct rte_eth_dev *dev, struct rte_flow_error *error) { @@ -2592,7 +853,7 @@ mlx5_flow_validate_action_count(struct rte_eth_dev *dev, * @return * 0 on success, a negative errno value otherwise and rte_errno is set. */ -static int +int mlx5_flow_validate_attributes(struct rte_eth_dev *dev, const struct rte_flow_attr *attributes, struct rte_flow_error *error) @@ -2638,7 +899,7 @@ mlx5_flow_validate_attributes(struct rte_eth_dev *dev, * @return * 0 on success, a negative errno value otherwise and rte_errno is set. */ -static int +int mlx5_flow_validate_item_eth(const struct rte_flow_item *item, uint64_t item_flags, struct rte_flow_error *error) @@ -2682,7 +943,7 @@ mlx5_flow_validate_item_eth(const struct rte_flow_item *item, * @return * 0 on success, a negative errno value otherwise and rte_errno is set. */ -static int +int mlx5_flow_validate_item_vlan(const struct rte_flow_item *item, int64_t item_flags, struct rte_flow_error *error) @@ -2748,7 +1009,7 @@ mlx5_flow_validate_item_vlan(const struct rte_flow_item *item, * @return * 0 on success, a negative errno value otherwise and rte_errno is set. */ -static int +int mlx5_flow_validate_item_ipv4(const struct rte_flow_item *item, int64_t item_flags, struct rte_flow_error *error) @@ -2799,7 +1060,7 @@ mlx5_flow_validate_item_ipv4(const struct rte_flow_item *item, * @return * 0 on success, a negative errno value otherwise and rte_errno is set. */ -static int +int mlx5_flow_validate_item_ipv6(const struct rte_flow_item *item, uint64_t item_flags, struct rte_flow_error *error) @@ -2868,7 +1129,7 @@ mlx5_flow_validate_item_ipv6(const struct rte_flow_item *item, * @return * 0 on success, a negative errno value otherwise and rte_errno is set. */ -static int +int mlx5_flow_validate_item_udp(const struct rte_flow_item *item, uint64_t item_flags, uint8_t target_protocol, @@ -2878,7 +1139,7 @@ mlx5_flow_validate_item_udp(const struct rte_flow_item *item, const int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL); int ret; - if (target_protocol != 0xff && target_protocol != MLX5_IP_PROTOCOL_UDP) + if (target_protocol != 0xff && target_protocol != IPPROTO_UDP) return rte_flow_error_set(error, EINVAL, RTE_FLOW_ERROR_TYPE_ITEM, item, "protocol filtering not compatible" @@ -2919,7 +1180,7 @@ mlx5_flow_validate_item_udp(const struct rte_flow_item *item, * @return * 0 on success, a negative errno value otherwise and rte_errno is set. */ -static int +int mlx5_flow_validate_item_tcp(const struct rte_flow_item *item, uint64_t item_flags, uint8_t target_protocol, @@ -2929,7 +1190,7 @@ mlx5_flow_validate_item_tcp(const struct rte_flow_item *item, const int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL); int ret; - if (target_protocol != 0xff && target_protocol != MLX5_IP_PROTOCOL_TCP) + if (target_protocol != 0xff && target_protocol != IPPROTO_TCP) return rte_flow_error_set(error, EINVAL, RTE_FLOW_ERROR_TYPE_ITEM, item, "protocol filtering not compatible" @@ -2970,7 +1231,7 @@ mlx5_flow_validate_item_tcp(const struct rte_flow_item *item, * @return * 0 on success, a negative errno value otherwise and rte_errno is set. */ -static int +int mlx5_flow_validate_item_vxlan(const struct rte_flow_item *item, uint64_t item_flags, struct rte_flow_error *error) @@ -3049,7 +1310,7 @@ mlx5_flow_validate_item_vxlan(const struct rte_flow_item *item, * @return * 0 on success, a negative errno value otherwise and rte_errno is set. */ -static int +int mlx5_flow_validate_item_vxlan_gpe(const struct rte_flow_item *item, uint64_t item_flags, struct rte_eth_dev *dev, @@ -3139,7 +1400,7 @@ mlx5_flow_validate_item_vxlan_gpe(const struct rte_flow_item *item, * @return * 0 on success, a negative errno value otherwise and rte_errno is set. */ -static int +int mlx5_flow_validate_item_gre(const struct rte_flow_item *item, uint64_t item_flags, uint8_t target_protocol, @@ -3149,7 +1410,7 @@ mlx5_flow_validate_item_gre(const struct rte_flow_item *item, const struct rte_flow_item_gre *mask = item->mask; int ret; - if (target_protocol != 0xff && target_protocol != MLX5_IP_PROTOCOL_GRE) + if (target_protocol != 0xff && target_protocol != IPPROTO_GRE) return rte_flow_error_set(error, EINVAL, RTE_FLOW_ERROR_TYPE_ITEM, item, "protocol filtering not compatible" @@ -3196,7 +1457,7 @@ mlx5_flow_validate_item_gre(const struct rte_flow_item *item, * @return * 0 on success, a negative errno value otherwise and rte_errno is set. */ -static int +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, @@ -3206,7 +1467,7 @@ mlx5_flow_validate_item_mpls(const struct rte_flow_item *item __rte_unused, const struct rte_flow_item_mpls *mask = item->mask; int ret; - if (target_protocol != 0xff && target_protocol != MLX5_IP_PROTOCOL_MPLS) + if (target_protocol != 0xff && target_protocol != IPPROTO_MPLS) return rte_flow_error_set(error, EINVAL, RTE_FLOW_ERROR_TYPE_ITEM, item, "protocol filtering not compatible" @@ -3232,209 +1493,6 @@ mlx5_flow_validate_item_mpls(const struct rte_flow_item *item __rte_unused, " 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; - - if (items == NULL) - return -1; - ret = mlx5_flow_validate_attributes(dev, attr, error); - if (ret < 0) - return ret; - for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) { - int ret = 0; - switch (items->type) { - case RTE_FLOW_ITEM_TYPE_VOID: - break; - case RTE_FLOW_ITEM_TYPE_ETH: - ret = mlx5_flow_validate_item_eth(items, item_flags, - error); - if (ret < 0) - return ret; - item_flags |= tunnel ? MLX5_FLOW_LAYER_INNER_L2 : - MLX5_FLOW_LAYER_OUTER_L2; - break; - case RTE_FLOW_ITEM_TYPE_VLAN: - ret = mlx5_flow_validate_item_vlan(items, item_flags, - error); - if (ret < 0) - return ret; - item_flags |= tunnel ? MLX5_FLOW_LAYER_INNER_VLAN : - MLX5_FLOW_LAYER_OUTER_VLAN; - break; - case RTE_FLOW_ITEM_TYPE_IPV4: - ret = mlx5_flow_validate_item_ipv4(items, item_flags, - error); - if (ret < 0) - return ret; - item_flags |= tunnel ? MLX5_FLOW_LAYER_INNER_L3_IPV4 : - MLX5_FLOW_LAYER_OUTER_L3_IPV4; - if (items->mask != NULL && - ((const struct rte_flow_item_ipv4 *) - items->mask)->hdr.next_proto_id) - next_protocol = - ((const struct rte_flow_item_ipv4 *) - (items->spec))->hdr.next_proto_id; - break; - case RTE_FLOW_ITEM_TYPE_IPV6: - ret = mlx5_flow_validate_item_ipv6(items, item_flags, - error); - if (ret < 0) - return ret; - item_flags |= tunnel ? MLX5_FLOW_LAYER_INNER_L3_IPV6 : - MLX5_FLOW_LAYER_OUTER_L3_IPV6; - if (items->mask != NULL && - ((const struct rte_flow_item_ipv6 *) - items->mask)->hdr.proto) - next_protocol = - ((const struct rte_flow_item_ipv6 *) - items->spec)->hdr.proto; - break; - case RTE_FLOW_ITEM_TYPE_UDP: - ret = mlx5_flow_validate_item_udp(items, item_flags, - next_protocol, - error); - if (ret < 0) - return ret; - item_flags |= tunnel ? MLX5_FLOW_LAYER_INNER_L4_UDP : - MLX5_FLOW_LAYER_OUTER_L4_UDP; - break; - case RTE_FLOW_ITEM_TYPE_TCP: - ret = mlx5_flow_validate_item_tcp(items, item_flags, - next_protocol, error); - if (ret < 0) - return ret; - item_flags |= tunnel ? MLX5_FLOW_LAYER_INNER_L4_TCP : - MLX5_FLOW_LAYER_OUTER_L4_TCP; - break; - case RTE_FLOW_ITEM_TYPE_VXLAN: - ret = mlx5_flow_validate_item_vxlan(items, item_flags, - error); - if (ret < 0) - return ret; - item_flags |= MLX5_FLOW_LAYER_VXLAN; - break; - case RTE_FLOW_ITEM_TYPE_VXLAN_GPE: - ret = mlx5_flow_validate_item_vxlan_gpe(items, - item_flags, - dev, error); - if (ret < 0) - return ret; - item_flags |= MLX5_FLOW_LAYER_VXLAN_GPE; - break; - case RTE_FLOW_ITEM_TYPE_GRE: - ret = mlx5_flow_validate_item_gre(items, item_flags, - next_protocol, error); - if (ret < 0) - return ret; - item_flags |= MLX5_FLOW_LAYER_GRE; - break; - case RTE_FLOW_ITEM_TYPE_MPLS: - ret = mlx5_flow_validate_item_mpls(items, item_flags, - next_protocol, - error); - if (ret < 0) - return ret; - if (next_protocol != 0xff && - next_protocol != MLX5_IP_PROTOCOL_MPLS) - return rte_flow_error_set - (error, ENOTSUP, - RTE_FLOW_ERROR_TYPE_ITEM, items, - "protocol filtering not compatible" - " with MPLS layer"); - item_flags |= MLX5_FLOW_LAYER_MPLS; - break; - default: - return rte_flow_error_set(error, ENOTSUP, - RTE_FLOW_ERROR_TYPE_ITEM, - NULL, - "item not supported"); - } - } - for (; actions->type != RTE_FLOW_ACTION_TYPE_END; actions++) { - tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL); - switch (actions->type) { - case RTE_FLOW_ACTION_TYPE_VOID: - break; - case RTE_FLOW_ACTION_TYPE_FLAG: - ret = mlx5_flow_validate_action_flag(action_flags, - error); - if (ret < 0) - return ret; - action_flags |= MLX5_FLOW_ACTION_FLAG; - break; - case RTE_FLOW_ACTION_TYPE_MARK: - ret = mlx5_flow_validate_action_mark(actions, - action_flags, - error); - if (ret < 0) - return ret; - action_flags |= MLX5_FLOW_ACTION_MARK; - break; - case RTE_FLOW_ACTION_TYPE_DROP: - ret = mlx5_flow_validate_action_drop(action_flags, - error); - if (ret < 0) - return ret; - action_flags |= MLX5_FLOW_ACTION_DROP; - break; - case RTE_FLOW_ACTION_TYPE_QUEUE: - ret = mlx5_flow_validate_action_queue(actions, - action_flags, dev, - error); - if (ret < 0) - return ret; - action_flags |= MLX5_FLOW_ACTION_QUEUE; - break; - case RTE_FLOW_ACTION_TYPE_RSS: - ret = mlx5_flow_validate_action_rss(actions, - action_flags, dev, - error); - if (ret < 0) - return ret; - action_flags |= MLX5_FLOW_ACTION_RSS; - break; - case RTE_FLOW_ACTION_TYPE_COUNT: - ret = mlx5_flow_validate_action_count(dev, error); - if (ret < 0) - return ret; - action_flags |= MLX5_FLOW_ACTION_COUNT; - break; - default: - return rte_flow_error_set(error, ENOTSUP, - RTE_FLOW_ERROR_TYPE_ACTION, - actions, - "action not supported"); - } - } - return 0; -} - /** * Validate a flow supported by the NIC. * @@ -3450,158 +1508,12 @@ mlx5_flow_validate(struct rte_eth_dev *dev, { int ret; - ret = mlx5_flow_verbs_validate(dev, attr, items, actions, error); + ret = nic_ops.validate(dev, attr, items, actions, error); if (ret < 0) return ret; return 0; } -/** - * Calculate the required bytes that are needed for the action part of the verbs - * flow, in addtion returns bit-fields with all the detected action, in order to - * avoid another interation over the actions. - * - * @param[in] actions - * Pointer to the list of actions. - * @param[out] action_flags - * Pointer to the detected actions. - * - * @return - * The size of the memory needed for all actions. - */ -static int -mlx5_flow_verbs_get_actions_and_size(const struct rte_flow_action actions[], - uint64_t *action_flags) -{ - int size = 0; - uint64_t detected_actions = 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: - size += sizeof(struct ibv_flow_spec_action_tag); - detected_actions |= MLX5_FLOW_ACTION_FLAG; - break; - case RTE_FLOW_ACTION_TYPE_MARK: - size += sizeof(struct ibv_flow_spec_action_tag); - detected_actions |= MLX5_FLOW_ACTION_MARK; - break; - case RTE_FLOW_ACTION_TYPE_DROP: - size += sizeof(struct ibv_flow_spec_action_drop); - detected_actions |= MLX5_FLOW_ACTION_DROP; - break; - case RTE_FLOW_ACTION_TYPE_QUEUE: - detected_actions |= MLX5_FLOW_ACTION_QUEUE; - break; - case RTE_FLOW_ACTION_TYPE_RSS: - detected_actions |= MLX5_FLOW_ACTION_RSS; - break; - case RTE_FLOW_ACTION_TYPE_COUNT: -#ifdef HAVE_IBV_DEVICE_COUNTERS_SET_SUPPORT - size += sizeof(struct ibv_flow_spec_counter_action); -#endif - detected_actions |= MLX5_FLOW_ACTION_COUNT; - break; - default: - break; - } - } - *action_flags = detected_actions; - return size; -} - -/** - * Calculate the required bytes that are needed for the item part of the verbs - * flow, in addtion returns bit-fields with all the detected action, in order to - * avoid another interation over the actions. - * - * @param[in] actions - * Pointer to the list of items. - * @param[in, out] item_flags - * Pointer to the detected items. - * - * @return - * The size of the memory needed for all items. - */ -static int -mlx5_flow_verbs_get_items_and_size(const struct rte_flow_item items[], - uint64_t *item_flags) -{ - int size = 0; - uint64_t detected_items = 0; - const int tunnel = !!(*item_flags & MLX5_FLOW_LAYER_TUNNEL); - - for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) { - switch (items->type) { - case RTE_FLOW_ITEM_TYPE_VOID: - break; - case RTE_FLOW_ITEM_TYPE_ETH: - size += sizeof(struct ibv_flow_spec_eth); - detected_items |= tunnel ? MLX5_FLOW_LAYER_INNER_L2 : - MLX5_FLOW_LAYER_OUTER_L2; - break; - case RTE_FLOW_ITEM_TYPE_VLAN: - size += sizeof(struct ibv_flow_spec_eth); - detected_items |= tunnel ? MLX5_FLOW_LAYER_INNER_VLAN : - MLX5_FLOW_LAYER_OUTER_VLAN; - break; - case RTE_FLOW_ITEM_TYPE_IPV4: - size += sizeof(struct ibv_flow_spec_ipv4_ext); - detected_items |= tunnel ? - MLX5_FLOW_LAYER_INNER_L3_IPV4 : - MLX5_FLOW_LAYER_OUTER_L3_IPV4; - break; - case RTE_FLOW_ITEM_TYPE_IPV6: - size += sizeof(struct ibv_flow_spec_ipv6); - detected_items |= tunnel ? - MLX5_FLOW_LAYER_INNER_L3_IPV6 : - MLX5_FLOW_LAYER_OUTER_L3_IPV6; - break; - case RTE_FLOW_ITEM_TYPE_UDP: - size += sizeof(struct ibv_flow_spec_tcp_udp); - detected_items |= tunnel ? - MLX5_FLOW_LAYER_INNER_L4_UDP : - MLX5_FLOW_LAYER_OUTER_L4_UDP; - break; - case RTE_FLOW_ITEM_TYPE_TCP: - size += sizeof(struct ibv_flow_spec_tcp_udp); - detected_items |= tunnel ? - MLX5_FLOW_LAYER_INNER_L4_TCP : - MLX5_FLOW_LAYER_OUTER_L4_TCP; - break; - case RTE_FLOW_ITEM_TYPE_VXLAN: - size += sizeof(struct ibv_flow_spec_tunnel); - detected_items |= MLX5_FLOW_LAYER_VXLAN; - break; - case RTE_FLOW_ITEM_TYPE_VXLAN_GPE: - size += sizeof(struct ibv_flow_spec_tunnel); - detected_items |= MLX5_FLOW_LAYER_VXLAN_GPE; - break; - case RTE_FLOW_ITEM_TYPE_GRE: -#ifdef HAVE_IBV_DEVICE_MPLS_SUPPORT - size += sizeof(struct ibv_flow_spec_gre); - detected_items |= MLX5_FLOW_LAYER_GRE; -#else - size += sizeof(struct ibv_flow_spec_tunnel); - detected_items |= MLX5_FLOW_LAYER_TUNNEL; -#endif - break; - case RTE_FLOW_ITEM_TYPE_MPLS: -#ifdef HAVE_IBV_DEVICE_MPLS_SUPPORT - size += sizeof(struct ibv_flow_spec_mpls); - detected_items |= MLX5_FLOW_LAYER_MPLS; -#endif - break; - default: - break; - } - } - *item_flags = detected_items; - return size; -} - /** * Get RSS action from the action list. * @@ -3626,173 +1538,23 @@ mlx5_flow_get_rss_action(const struct rte_flow_action actions[]) return NULL; } -/** - * Internal preparation function. Allocate mlx5_flow with the required size. - * The required size is calculate based on the actions and items. This function - * also returns the detected actions and items for later use. - * - * @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] item_flags - * Pointer to bit mask of all items detected. - * @param[out] action_flags - * Pointer to bit mask of all actions detected. - * @param[out] error - * Pointer to the error structure. - * - * @return - * Pointer to mlx5_flow object on success, otherwise NULL and rte_errno - * is set. - */ -static struct mlx5_flow * -mlx5_flow_verbs_prepare(const struct rte_flow_attr *attr __rte_unused, - const struct rte_flow_item items[], - const struct rte_flow_action actions[], - uint64_t *item_flags, - uint64_t *action_flags, - struct rte_flow_error *error) -{ - uint32_t size = sizeof(struct ibv_flow_attr); - struct mlx5_flow *flow; - - size += mlx5_flow_verbs_get_actions_and_size(actions, action_flags); - size += mlx5_flow_verbs_get_items_and_size(items, item_flags); - flow = rte_calloc(__func__, 1, size, 0); - if (!flow) { - rte_flow_error_set(error, ENOMEM, - RTE_FLOW_ERROR_TYPE_UNSPECIFIED, - NULL, - "not enough memory to create flow"); - return NULL; - } - return flow; -} - -/** - * Remove the flow. - * - * @param[in] dev - * Pointer to the Ethernet device structure. - * @param[in, out] flow - * Pointer to flow structure. - */ -static void -mlx5_flow_remove(struct rte_eth_dev *dev, struct rte_flow *flow) -{ - struct priv *priv = dev->data->dev_private; - struct mlx5_flow_verbs *verbs; - - if (flow->nl_flow && priv->mnl_socket) - mlx5_nl_flow_destroy(priv->mnl_socket, flow->nl_flow, NULL); - LIST_FOREACH(verbs, &flow->verbs, next) { - if (verbs->flow) { - claim_zero(mlx5_glue->destroy_flow(verbs->flow)); - verbs->flow = NULL; - } - if (verbs->hrxq) { - if (flow->fate & MLX5_FLOW_FATE_DROP) - mlx5_hrxq_drop_release(dev); - else - mlx5_hrxq_release(dev, verbs->hrxq); - verbs->hrxq = NULL; - } - } - if (flow->counter) { - mlx5_flow_counter_release(flow->counter); - flow->counter = NULL; - } -} - -/** - * Apply the flow. - * - * @param[in] dev - * Pointer to the Ethernet device structure. - * @param[in, out] flow - * Pointer to flow structure. - * @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_apply(struct rte_eth_dev *dev, struct rte_flow *flow, - struct rte_flow_error *error) +static unsigned int +mlx5_find_graph_root(const struct rte_flow_item pattern[], uint32_t rss_level) { - struct priv *priv = dev->data->dev_private; - struct mlx5_flow_verbs *verbs; - int err; - - LIST_FOREACH(verbs, &flow->verbs, next) { - if (flow->fate & MLX5_FLOW_FATE_DROP) { - verbs->hrxq = mlx5_hrxq_drop_new(dev); - if (!verbs->hrxq) { - rte_flow_error_set - (error, errno, - RTE_FLOW_ERROR_TYPE_UNSPECIFIED, - NULL, - "cannot get drop hash queue"); - goto error; - } - } else { - struct mlx5_hrxq *hrxq; + const struct rte_flow_item *item; + unsigned int has_vlan = 0; - hrxq = mlx5_hrxq_get(dev, flow->key, - MLX5_RSS_HASH_KEY_LEN, - verbs->hash_fields, - (*flow->queue), - flow->rss.queue_num); - if (!hrxq) - hrxq = mlx5_hrxq_new(dev, flow->key, - MLX5_RSS_HASH_KEY_LEN, - verbs->hash_fields, - (*flow->queue), - flow->rss.queue_num, - !!(flow->layers & - MLX5_FLOW_LAYER_TUNNEL)); - if (!hrxq) { - rte_flow_error_set - (error, rte_errno, - RTE_FLOW_ERROR_TYPE_UNSPECIFIED, - NULL, - "cannot get hash queue"); - goto error; - } - verbs->hrxq = hrxq; - } - verbs->flow = - mlx5_glue->create_flow(verbs->hrxq->qp, verbs->attr); - if (!verbs->flow) { - rte_flow_error_set(error, errno, - RTE_FLOW_ERROR_TYPE_UNSPECIFIED, - NULL, - "hardware refuses to create flow"); - goto error; - } - } - if (flow->nl_flow && - priv->mnl_socket && - mlx5_nl_flow_create(priv->mnl_socket, flow->nl_flow, error)) - goto error; - return 0; -error: - err = rte_errno; /* Save rte_errno before cleanup. */ - LIST_FOREACH(verbs, &flow->verbs, next) { - if (verbs->hrxq) { - if (flow->fate & MLX5_FLOW_FATE_DROP) - mlx5_hrxq_drop_release(dev); - else - mlx5_hrxq_release(dev, verbs->hrxq); - verbs->hrxq = NULL; + for (item = pattern; item->type != RTE_FLOW_ITEM_TYPE_END; item++) { + if (item->type == RTE_FLOW_ITEM_TYPE_VLAN) { + has_vlan = 1; + break; } } - rte_errno = err; /* Restore rte_errno. */ - return -rte_errno; + 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; } /** @@ -3824,7 +1586,6 @@ mlx5_flow_list_create(struct rte_eth_dev *dev, { struct rte_flow *flow = NULL; struct mlx5_flow *dev_flow; - size_t size = 0; uint64_t action_flags = 0; uint64_t item_flags = 0; const struct rte_flow_action_rss *rss; @@ -3835,13 +1596,21 @@ mlx5_flow_list_create(struct rte_eth_dev *dev, struct rte_flow_expand_rss *buf = &expand_buffer.buf; int ret; uint32_t i; + uint32_t flow_size; ret = mlx5_flow_validate(dev, attr, items, actions, error); if (ret < 0) return NULL; - flow = rte_calloc(__func__, 1, sizeof(*flow), 0); - LIST_INIT(&flow->dev_flows); + flow_size = sizeof(struct rte_flow); rss = mlx5_flow_get_rss_action(actions); + if (rss) + flow_size += RTE_ALIGN_CEIL(rss->queue_num * sizeof(uint16_t), + sizeof(void *)); + else + flow_size += RTE_ALIGN_CEIL(sizeof(uint16_t), sizeof(void *)); + flow = rte_calloc(__func__, 1, flow_size, 0); + flow->queue = (void *)(flow + 1); + LIST_INIT(&flow->dev_flows); if (rss && rss->types) { unsigned int graph_root; @@ -3857,45 +1626,34 @@ mlx5_flow_list_create(struct rte_eth_dev *dev, buf->entry[0].pattern = (void *)(uintptr_t)items; } for (i = 0; i < buf->entries; ++i) { - dev_flow = mlx5_flow_verbs_prepare(attr, buf->entry[i].pattern, - actions, &item_flags, - &action_flags, error); + dev_flow = nic_ops.prepare(attr, buf->entry[i].pattern, + actions, &item_flags, + &action_flags, error); + if (!dev_flow) + goto error; dev_flow->flow = flow; LIST_INSERT_HEAD(&flow->dev_flows, dev_flow, next); + ret = nic_ops.translate(dev, dev_flow, attr, + buf->entry[i].pattern, + actions, error); + if (ret < 0) + goto error; } - ret = mlx5_flow_merge(dev, flow, size, attr, items, actions, error); - if (ret < 0) - return NULL; - size = ret; - flow = rte_calloc(__func__, 1, size, 0); - if (!flow) { - rte_flow_error_set(error, ENOMEM, - RTE_FLOW_ERROR_TYPE_UNSPECIFIED, - NULL, - "not enough memory to create flow"); - return NULL; - } - ret = mlx5_flow_merge(dev, flow, size, attr, items, actions, error); - if (ret < 0) { - rte_free(flow); - return NULL; - } - assert((size_t)ret == size); if (dev->data->dev_started) { - ret = mlx5_flow_apply(dev, flow, error); - if (ret < 0) { - ret = rte_errno; /* Save rte_errno before cleanup. */ - if (flow) { - mlx5_flow_remove(dev, flow); - rte_free(flow); - } - rte_errno = ret; /* Restore rte_errno. */ - return NULL; - } + ret = nic_ops.apply(dev, flow, error); + if (ret < 0) + goto error; } TAILQ_INSERT_TAIL(list, flow, next); mlx5_flow_rxq_flags_set(dev, flow); return flow; +error: + ret = rte_errno; /* Save rte_errno before cleanup. */ + assert(flow); + nic_ops.destroy(dev, flow); + rte_free(flow); + rte_errno = ret; /* Restore rte_errno. */ + return NULL; } /** @@ -3930,7 +1688,7 @@ static void mlx5_flow_list_destroy(struct rte_eth_dev *dev, struct mlx5_flows *list, struct rte_flow *flow) { - mlx5_flow_remove(dev, flow); + nic_ops.destroy(dev, flow); TAILQ_REMOVE(list, flow, next); /* * Update RX queue flags only if port is started, otherwise it is @@ -3974,7 +1732,7 @@ mlx5_flow_stop(struct rte_eth_dev *dev, struct mlx5_flows *list) struct rte_flow *flow; TAILQ_FOREACH_REVERSE(flow, list, mlx5_flows, next) - mlx5_flow_remove(dev, flow); + nic_ops.remove(dev, flow); mlx5_flow_rxq_flags_clear(dev); } @@ -3997,7 +1755,7 @@ mlx5_flow_start(struct rte_eth_dev *dev, struct mlx5_flows *list) int ret = 0; TAILQ_FOREACH(flow, list, next) { - ret = mlx5_flow_apply(dev, flow, &error); + ret = nic_ops.apply(dev, flow, &error); if (ret < 0) goto error; mlx5_flow_rxq_flags_set(dev, flow); @@ -4213,7 +1971,7 @@ mlx5_flow_query_count(struct rte_flow *flow __rte_unused, struct rte_flow_error *error) { #ifdef HAVE_IBV_DEVICE_COUNTERS_SET_SUPPORT - if (flow->modifier & MLX5_FLOW_MOD_COUNT) { + if (flow->actions & MLX5_FLOW_ACTION_COUNT) { struct rte_flow_query_count *qc = data; uint64_t counters[2] = {0, 0}; struct ibv_query_counter_set_attr query_cs_attr = { @@ -4688,3 +2446,15 @@ mlx5_dev_filter_ctrl(struct rte_eth_dev *dev, } return 0; } + +/** + * Init the driver ops structure. + * + * @param dev + * Pointer to Ethernet device structure. + */ +void +mlx5_flow_init_driver_ops(struct rte_eth_dev *dev __rte_unused) +{ + mlx5_flow_verbs_get_driver_ops(&nic_ops); +} diff --git a/drivers/net/mlx5/mlx5_flow.h b/drivers/net/mlx5/mlx5_flow.h new file mode 100644 index 0000000000..467b5a8543 --- /dev/null +++ b/drivers/net/mlx5/mlx5_flow.h @@ -0,0 +1,259 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright 2018 Mellanox Technologies, Ltd + */ + +#ifndef RTE_PMD_MLX5_FLOW_H_ +#define RTE_PMD_MLX5_FLOW_H_ + +#include +#include +#include +#include +#include + +/* Verbs header. */ +/* ISO C doesn't support unnamed structs/unions, disabling -pedantic. */ +#ifdef PEDANTIC +#pragma GCC diagnostic ignored "-Wpedantic" +#endif +#include +#ifdef PEDANTIC +#pragma GCC diagnostic error "-Wpedantic" +#endif + +/* Pattern outer Layer bits. */ +#define MLX5_FLOW_LAYER_OUTER_L2 (1u << 0) +#define MLX5_FLOW_LAYER_OUTER_L3_IPV4 (1u << 1) +#define MLX5_FLOW_LAYER_OUTER_L3_IPV6 (1u << 2) +#define MLX5_FLOW_LAYER_OUTER_L4_UDP (1u << 3) +#define MLX5_FLOW_LAYER_OUTER_L4_TCP (1u << 4) +#define MLX5_FLOW_LAYER_OUTER_VLAN (1u << 5) + +/* Pattern inner Layer bits. */ +#define MLX5_FLOW_LAYER_INNER_L2 (1u << 6) +#define MLX5_FLOW_LAYER_INNER_L3_IPV4 (1u << 7) +#define MLX5_FLOW_LAYER_INNER_L3_IPV6 (1u << 8) +#define MLX5_FLOW_LAYER_INNER_L4_UDP (1u << 9) +#define MLX5_FLOW_LAYER_INNER_L4_TCP (1u << 10) +#define MLX5_FLOW_LAYER_INNER_VLAN (1u << 11) + +/* Pattern tunnel Layer bits. */ +#define MLX5_FLOW_LAYER_VXLAN (1u << 12) +#define MLX5_FLOW_LAYER_VXLAN_GPE (1u << 13) +#define MLX5_FLOW_LAYER_GRE (1u << 14) +#define MLX5_FLOW_LAYER_MPLS (1u << 15) + +/* Outer Masks. */ +#define MLX5_FLOW_LAYER_OUTER_L3 \ + (MLX5_FLOW_LAYER_OUTER_L3_IPV4 | MLX5_FLOW_LAYER_OUTER_L3_IPV6) +#define MLX5_FLOW_LAYER_OUTER_L4 \ + (MLX5_FLOW_LAYER_OUTER_L4_UDP | MLX5_FLOW_LAYER_OUTER_L4_TCP) +#define MLX5_FLOW_LAYER_OUTER \ + (MLX5_FLOW_LAYER_OUTER_L2 | MLX5_FLOW_LAYER_OUTER_L3 | \ + MLX5_FLOW_LAYER_OUTER_L4) + +/* Tunnel Masks. */ +#define MLX5_FLOW_LAYER_TUNNEL \ + (MLX5_FLOW_LAYER_VXLAN | MLX5_FLOW_LAYER_VXLAN_GPE | \ + MLX5_FLOW_LAYER_GRE | MLX5_FLOW_LAYER_MPLS) + +/* Inner Masks. */ +#define MLX5_FLOW_LAYER_INNER_L3 \ + (MLX5_FLOW_LAYER_INNER_L3_IPV4 | MLX5_FLOW_LAYER_INNER_L3_IPV6) +#define MLX5_FLOW_LAYER_INNER_L4 \ + (MLX5_FLOW_LAYER_INNER_L4_UDP | MLX5_FLOW_LAYER_INNER_L4_TCP) +#define MLX5_FLOW_LAYER_INNER \ + (MLX5_FLOW_LAYER_INNER_L2 | MLX5_FLOW_LAYER_INNER_L3 | \ + MLX5_FLOW_LAYER_INNER_L4) + +/* Actions that modify the fate of matching traffic. */ +#define MLX5_FLOW_FATE_DROP (1u << 0) +#define MLX5_FLOW_FATE_QUEUE (1u << 1) +#define MLX5_FLOW_FATE_RSS (1u << 2) + +/* Modify a packet. */ +#define MLX5_FLOW_MOD_FLAG (1u << 0) +#define MLX5_FLOW_MOD_MARK (1u << 1) +#define MLX5_FLOW_MOD_COUNT (1u << 2) + +/* Actions */ +#define MLX5_FLOW_ACTION_DROP (1u << 0) +#define MLX5_FLOW_ACTION_QUEUE (1u << 1) +#define MLX5_FLOW_ACTION_RSS (1u << 2) +#define MLX5_FLOW_ACTION_FLAG (1u << 3) +#define MLX5_FLOW_ACTION_MARK (1u << 4) +#define MLX5_FLOW_ACTION_COUNT (1u << 5) + +#define MLX5_FLOW_FATE_ACTIONS \ + (MLX5_FLOW_ACTION_DROP | MLX5_FLOW_ACTION_QUEUE | MLX5_FLOW_ACTION_RSS) + +#ifndef IPPROTO_MPLS +#define IPPROTO_MPLS 137 +#endif + +/* Priority reserved for default flows. */ +#define MLX5_FLOW_PRIO_RSVD ((uint32_t)-1) + +/* + * Number of sub priorities. + * For each kind of pattern matching i.e. L2, L3, L4 to have a correct + * matching on the NIC (firmware dependent) L4 most have the higher priority + * followed by L3 and ending with L2. + */ +#define MLX5_PRIORITY_MAP_L2 2 +#define MLX5_PRIORITY_MAP_L3 1 +#define MLX5_PRIORITY_MAP_L4 0 +#define MLX5_PRIORITY_MAP_MAX 3 + +/* Verbs specification header. */ +struct ibv_spec_header { + enum ibv_flow_spec_type type; + uint16_t size; +}; + +/** Handles information leading to a drop fate. */ +struct mlx5_flow_verbs { + LIST_ENTRY(mlx5_flow_verbs) next; + unsigned int size; /**< Size of the attribute. */ + struct { + struct ibv_flow_attr *attr; + /**< Pointer to the Specification buffer. */ + uint8_t *specs; /**< Pointer to the specifications. */ + }; + struct ibv_flow *flow; /**< Verbs flow pointer. */ + struct mlx5_hrxq *hrxq; /**< Hash Rx queue object. */ + uint64_t hash_fields; /**< Verbs hash Rx queue hash fields. */ +}; + +/** Device flow structure. */ +struct mlx5_flow { + LIST_ENTRY(mlx5_flow) next; + struct rte_flow *flow; /**< Pointer to the main flow. */ + uint32_t layers; /**< Bit-fields that holds the detected layers. */ + union { + struct mlx5_flow_verbs verbs; /**< Holds the verbs dev-flow. */ + }; +}; + +/* Counters information. */ +struct mlx5_flow_counter { + LIST_ENTRY(mlx5_flow_counter) next; /**< Pointer to the next counter. */ + uint32_t shared:1; /**< Share counter ID with other flow rules. */ + uint32_t ref_cnt:31; /**< Reference counter. */ + uint32_t id; /**< Counter ID. */ + struct ibv_counter_set *cs; /**< Holds the counters for the rule. */ + uint64_t hits; /**< Number of packets matched by the rule. */ + uint64_t bytes; /**< Number of bytes matched by the rule. */ +}; + +/* Flow structure. */ +struct rte_flow { + TAILQ_ENTRY(rte_flow) next; /**< Pointer to the next flow structure. */ + struct rte_flow_attr attributes; /**< User flow attribute. */ + uint32_t layers; + /**< Bit-fields of present layers see MLX5_FLOW_LAYER_*. */ + struct mlx5_flow_counter *counter; /**< Holds flow counter. */ + struct rte_flow_action_rss rss;/**< RSS context. */ + uint8_t key[MLX5_RSS_HASH_KEY_LEN]; /**< RSS hash key. */ + uint16_t (*queue)[]; /**< Destination queues to redirect traffic to. */ + void *nl_flow; /**< Netlink flow buffer if relevant. */ + LIST_HEAD(dev_flows, mlx5_flow) dev_flows; + /**< Device flows that are part of the flow. */ + uint32_t actions; /**< Bit-fields which mark all detected actions. */ +}; +typedef int (*mlx5_flow_validate_t)(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); +typedef struct mlx5_flow *(*mlx5_flow_prepare_t) + (const struct rte_flow_attr *attr, const struct rte_flow_item items[], + const struct rte_flow_action actions[], uint64_t *item_flags, + uint64_t *action_flags, struct rte_flow_error *error); +typedef int (*mlx5_flow_translate_t)(struct rte_eth_dev *dev, + struct mlx5_flow *dev_flow, + const struct rte_flow_attr *attr, + const struct rte_flow_item items[], + const struct rte_flow_action actions[], + struct rte_flow_error *error); +typedef int (*mlx5_flow_apply_t)(struct rte_eth_dev *dev, struct rte_flow *flow, + struct rte_flow_error *error); +typedef void (*mlx5_flow_remove_t)(struct rte_eth_dev *dev, + struct rte_flow *flow); +typedef void (*mlx5_flow_destroy_t)(struct rte_eth_dev *dev, + struct rte_flow *flow); +struct mlx5_flow_driver_ops { + mlx5_flow_validate_t validate; + mlx5_flow_prepare_t prepare; + mlx5_flow_translate_t translate; + mlx5_flow_apply_t apply; + mlx5_flow_remove_t remove; + mlx5_flow_destroy_t destroy; +}; + +/* mlx5_flow.c */ + +uint32_t mlx5_flow_adjust_priority(struct rte_eth_dev *dev, int32_t priority, + uint32_t subpriority); +int mlx5_flow_validate_action_count(struct rte_eth_dev *dev, + struct rte_flow_error *error); +int mlx5_flow_validate_action_drop(uint64_t action_flags, + struct rte_flow_error *error); +int mlx5_flow_validate_action_flag(uint64_t action_flags, + struct rte_flow_error *error); +int mlx5_flow_validate_action_mark(const struct rte_flow_action *action, + uint64_t action_flags, + struct rte_flow_error *error); +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); +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); +int mlx5_flow_validate_attributes(struct rte_eth_dev *dev, + const struct rte_flow_attr *attributes, + struct rte_flow_error *error); +int mlx5_flow_validate_item_eth(const struct rte_flow_item *item, + uint64_t item_flags, + struct rte_flow_error *error); +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); +int mlx5_flow_validate_item_ipv4(const struct rte_flow_item *item, + int64_t item_flags, + struct rte_flow_error *error); +int mlx5_flow_validate_item_ipv6(const struct rte_flow_item *item, + uint64_t item_flags, + struct rte_flow_error *error); +int mlx5_flow_validate_item_mpls(const struct rte_flow_item *item, + uint64_t item_flags, + uint8_t target_protocol, + struct rte_flow_error *error); +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); +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); +int mlx5_flow_validate_item_vlan(const struct rte_flow_item *item, + int64_t item_flags, + struct rte_flow_error *error); +int mlx5_flow_validate_item_vxlan(const struct rte_flow_item *item, + uint64_t item_flags, + struct rte_flow_error *error); +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); +void mlx5_flow_init_driver_ops(struct rte_eth_dev *dev); + +/* mlx5_flow_verbs.c */ + +void mlx5_flow_verbs_get_driver_ops(struct mlx5_flow_driver_ops *flow_ops); + +#endif /* RTE_PMD_MLX5_FLOW_H_ */ diff --git a/drivers/net/mlx5/mlx5_flow_verbs.c b/drivers/net/mlx5/mlx5_flow_verbs.c new file mode 100644 index 0000000000..b9f475d59a --- /dev/null +++ b/drivers/net/mlx5/mlx5_flow_verbs.c @@ -0,0 +1,1697 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright 2018 Mellanox Technologies, Ltd + */ + +#include +#include +#include +#include +#include + +/* Verbs header. */ +/* ISO C doesn't support unnamed structs/unions, disabling -pedantic. */ +#ifdef PEDANTIC +#pragma GCC diagnostic ignored "-Wpedantic" +#endif +#include +#ifdef PEDANTIC +#pragma GCC diagnostic error "-Wpedantic" +#endif + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "mlx5.h" +#include "mlx5_defs.h" +#include "mlx5_prm.h" +#include "mlx5_glue.h" +#include "mlx5_flow.h" + +/** + * Get a flow counter. + * + * @param[in] dev + * Pointer to the Ethernet device structure. + * @param[in] shared + * Indicate if this counter is shared with other flows. + * @param[in] id + * Counter identifier. + * + * @return + * A pointer to the counter, NULL otherwise and rte_errno is set. + */ +static struct mlx5_flow_counter * +flow_verbs_counter_new(struct rte_eth_dev *dev, uint32_t shared, uint32_t id) +{ + struct priv *priv = dev->data->dev_private; + struct mlx5_flow_counter *cnt; + + LIST_FOREACH(cnt, &priv->flow_counters, next) { + if (!cnt->shared || cnt->shared != shared) + continue; + if (cnt->id != id) + continue; + cnt->ref_cnt++; + return cnt; + } +#ifdef HAVE_IBV_DEVICE_COUNTERS_SET_SUPPORT + + struct mlx5_flow_counter tmpl = { + .shared = shared, + .id = id, + .cs = mlx5_glue->create_counter_set + (priv->ctx, + &(struct ibv_counter_set_init_attr){ + .counter_set_id = id, + }), + .hits = 0, + .bytes = 0, + }; + + if (!tmpl.cs) { + rte_errno = errno; + return NULL; + } + cnt = rte_calloc(__func__, 1, sizeof(*cnt), 0); + if (!cnt) { + rte_errno = ENOMEM; + return NULL; + } + *cnt = tmpl; + LIST_INSERT_HEAD(&priv->flow_counters, cnt, next); + return cnt; +#endif + rte_errno = ENOTSUP; + return NULL; +} + +/** + * Release a flow counter. + * + * @param[in] counter + * Pointer to the counter handler. + */ +static void +flow_verbs_counter_release(struct mlx5_flow_counter *counter) +{ + if (--counter->ref_cnt == 0) { + claim_zero(mlx5_glue->destroy_counter_set(counter->cs)); + LIST_REMOVE(counter, next); + rte_free(counter); + } +} + +/** + * Add a verbs item specification into @p flow. + * + * @param[in, out] flow + * Pointer to flow structure. + * @param[in] src + * Create specification. + * @param[in] size + * Size in bytes of the specification to copy. + */ +static void +flow_verbs_spec_add(struct mlx5_flow *flow, void *src, unsigned int size) +{ + struct mlx5_flow_verbs *verbs = &flow->verbs; + + if (verbs->specs) { + void *dst; + + dst = (void *)(verbs->specs + verbs->size); + memcpy(dst, src, size); + ++verbs->attr->num_of_specs; + } + verbs->size += size; +} + +/** + * Adjust verbs hash fields according to the @p flow information. + * + * @param[in] dev_flow. + * Pointer to dev flow structure. + * @param[in] tunnel + * 1 when the hash field is for a tunnel item. + * @param[in] layer_types + * ETH_RSS_* types. + * @param[in] hash_fields + * Item hash fields. + */ +static void +flow_verbs_hashfields_adjust(struct mlx5_flow *dev_flow, + int tunnel __rte_unused, + uint32_t layer_types, uint64_t hash_fields) +{ +#ifdef HAVE_IBV_DEVICE_TUNNEL_SUPPORT + int rss_request_inner = dev_flow->flow->rss.level >= 2; + + hash_fields |= (tunnel ? IBV_RX_HASH_INNER : 0); + if (rss_request_inner && !tunnel) + hash_fields = 0; + else if (rss_request_inner < 2 && tunnel) + hash_fields = 0; +#endif + if (!(dev_flow->flow->rss.types & layer_types)) + hash_fields = 0; + dev_flow->verbs.hash_fields |= hash_fields; +} + +/** + * Convert the @p item into a Verbs specification. This function assumes that + * the input is valid and that there is space to insert the requested item + * into the flow. + * + * @param[in] item + * Item specification. + * @param[in] item_flags + * Bit field with all detected items. + * @param[in, out] dev_flow + * Pointer to dev_flow structure. + */ +static void +flow_verbs_translate_item_eth(const struct rte_flow_item *item, + uint64_t *item_flags, + struct mlx5_flow *dev_flow) +{ + const struct rte_flow_item_eth *spec = item->spec; + const struct rte_flow_item_eth *mask = item->mask; + const int tunnel = !!(*item_flags & MLX5_FLOW_LAYER_TUNNEL); + const unsigned int size = sizeof(struct ibv_flow_spec_eth); + struct ibv_flow_spec_eth eth = { + .type = IBV_FLOW_SPEC_ETH | (tunnel ? IBV_FLOW_SPEC_INNER : 0), + .size = size, + }; + + if (!mask) + mask = &rte_flow_item_eth_mask; + if (spec) { + unsigned int i; + + memcpy(ð.val.dst_mac, spec->dst.addr_bytes, ETHER_ADDR_LEN); + memcpy(ð.val.src_mac, spec->src.addr_bytes, ETHER_ADDR_LEN); + eth.val.ether_type = spec->type; + memcpy(ð.mask.dst_mac, mask->dst.addr_bytes, ETHER_ADDR_LEN); + memcpy(ð.mask.src_mac, mask->src.addr_bytes, ETHER_ADDR_LEN); + eth.mask.ether_type = mask->type; + /* Remove unwanted bits from values. */ + for (i = 0; i < ETHER_ADDR_LEN; ++i) { + eth.val.dst_mac[i] &= eth.mask.dst_mac[i]; + eth.val.src_mac[i] &= eth.mask.src_mac[i]; + } + eth.val.ether_type &= eth.mask.ether_type; + dev_flow->verbs.attr->priority = MLX5_PRIORITY_MAP_L2; + } + flow_verbs_spec_add(dev_flow, ð, size); + *item_flags |= tunnel ? MLX5_FLOW_LAYER_INNER_L2 : + MLX5_FLOW_LAYER_OUTER_L2; +} + +/** + * Update the VLAN tag in the Verbs Ethernet specification. + * This function assumes that the input is valid and there is space to add + * the requested item. + * + * @param[in, out] attr + * Pointer to Verbs attributes structure. + * @param[in] eth + * Verbs structure containing the VLAN information to copy. + */ +static void +flow_verbs_item_vlan_update(struct ibv_flow_attr *attr, + struct ibv_flow_spec_eth *eth) +{ + unsigned int i; + const enum ibv_flow_spec_type search = eth->type; + struct ibv_spec_header *hdr = (struct ibv_spec_header *) + ((uint8_t *)attr + sizeof(struct ibv_flow_attr)); + + for (i = 0; i != attr->num_of_specs; ++i) { + if (hdr->type == search) { + struct ibv_flow_spec_eth *e = + (struct ibv_flow_spec_eth *)hdr; + + e->val.vlan_tag = eth->val.vlan_tag; + e->mask.vlan_tag = eth->mask.vlan_tag; + e->val.ether_type = eth->val.ether_type; + e->mask.ether_type = eth->mask.ether_type; + break; + } + hdr = (struct ibv_spec_header *)((uint8_t *)hdr + hdr->size); + } +} + +/** + * Convert the @p item into a Verbs specification. This function assumes that + * the input is valid and that there is space to insert the requested item + * into the flow. + * + * @param[in] item + * Item specification. + * @param[in, out] item_flags + * Bit mask that holds all detected items. + * @param[in, out] dev_flow + * Pointer to dev_flow structure. + */ +static void +flow_verbs_translate_item_vlan(const struct rte_flow_item *item, + uint64_t *item_flags, + struct mlx5_flow *dev_flow) +{ + const struct rte_flow_item_vlan *spec = item->spec; + const struct rte_flow_item_vlan *mask = item->mask; + unsigned int size = sizeof(struct ibv_flow_spec_eth); + const int tunnel = !!(*item_flags & MLX5_FLOW_LAYER_TUNNEL); + struct ibv_flow_spec_eth eth = { + .type = IBV_FLOW_SPEC_ETH | (tunnel ? IBV_FLOW_SPEC_INNER : 0), + .size = size, + }; + const uint32_t l2m = tunnel ? MLX5_FLOW_LAYER_INNER_L2 : + MLX5_FLOW_LAYER_OUTER_L2; + + if (!mask) + mask = &rte_flow_item_vlan_mask; + if (spec) { + eth.val.vlan_tag = spec->tci; + eth.mask.vlan_tag = mask->tci; + eth.val.vlan_tag &= eth.mask.vlan_tag; + eth.val.ether_type = spec->inner_type; + eth.mask.ether_type = mask->inner_type; + eth.val.ether_type &= eth.mask.ether_type; + } + if (!(*item_flags & l2m)) { + dev_flow->verbs.attr->priority = MLX5_PRIORITY_MAP_L2; + flow_verbs_spec_add(dev_flow, ð, size); + } else { + flow_verbs_item_vlan_update(dev_flow->verbs.attr, ð); + size = 0; /* Only an update is done in eth specification. */ + } + *item_flags |= tunnel ? + (MLX5_FLOW_LAYER_INNER_L2 | MLX5_FLOW_LAYER_INNER_VLAN) : + (MLX5_FLOW_LAYER_OUTER_L2 | MLX5_FLOW_LAYER_OUTER_VLAN); +} + +/** + * Convert the @p item into a Verbs specification. This function assumes that + * the input is valid and that there is space to insert the requested item + * into the flow. + * + * @param[in] item + * Item specification. + * @param[in, out] item_flags + * Bit mask that marks all detected items. + * @param[in, out] dev_flow + * Pointer to sepacific flow structure. + */ +static void +flow_verbs_translate_item_ipv4(const struct rte_flow_item *item, + uint64_t *item_flags, + struct mlx5_flow *dev_flow) +{ + const struct rte_flow_item_ipv4 *spec = item->spec; + const struct rte_flow_item_ipv4 *mask = item->mask; + const int tunnel = !!(*item_flags & MLX5_FLOW_LAYER_TUNNEL); + unsigned int size = sizeof(struct ibv_flow_spec_ipv4_ext); + struct ibv_flow_spec_ipv4_ext ipv4 = { + .type = IBV_FLOW_SPEC_IPV4_EXT | + (tunnel ? IBV_FLOW_SPEC_INNER : 0), + .size = size, + }; + + if (!mask) + mask = &rte_flow_item_ipv4_mask; + *item_flags |= tunnel ? MLX5_FLOW_LAYER_INNER_L3_IPV4 : + MLX5_FLOW_LAYER_OUTER_L3_IPV4; + if (spec) { + ipv4.val = (struct ibv_flow_ipv4_ext_filter){ + .src_ip = spec->hdr.src_addr, + .dst_ip = spec->hdr.dst_addr, + .proto = spec->hdr.next_proto_id, + .tos = spec->hdr.type_of_service, + }; + ipv4.mask = (struct ibv_flow_ipv4_ext_filter){ + .src_ip = mask->hdr.src_addr, + .dst_ip = mask->hdr.dst_addr, + .proto = mask->hdr.next_proto_id, + .tos = mask->hdr.type_of_service, + }; + /* Remove unwanted bits from values. */ + ipv4.val.src_ip &= ipv4.mask.src_ip; + ipv4.val.dst_ip &= ipv4.mask.dst_ip; + ipv4.val.proto &= ipv4.mask.proto; + ipv4.val.tos &= ipv4.mask.tos; + } + flow_verbs_hashfields_adjust(dev_flow, tunnel, + (ETH_RSS_IPV4 | ETH_RSS_FRAG_IPV4 | + ETH_RSS_NONFRAG_IPV4_TCP | + ETH_RSS_NONFRAG_IPV4_UDP | + ETH_RSS_NONFRAG_IPV4_OTHER), + (IBV_RX_HASH_SRC_IPV4 | + IBV_RX_HASH_DST_IPV4)); + dev_flow->verbs.attr->priority = MLX5_PRIORITY_MAP_L3; + flow_verbs_spec_add(dev_flow, &ipv4, size); +} + +/** + * Convert the @p item into a Verbs specification. This function assumes that + * the input is valid and that there is space to insert the requested item + * into the flow. + * + * @param[in] item + * Item specification. + * @param[in, out] item_flags + * Bit mask that marks all detected items. + * @param[in, out] dev_flow + * Pointer to sepacific flow structure. + */ +static void +flow_verbs_translate_item_ipv6(const struct rte_flow_item *item, + uint64_t *item_flags, + struct mlx5_flow *dev_flow) +{ + const struct rte_flow_item_ipv6 *spec = item->spec; + const struct rte_flow_item_ipv6 *mask = item->mask; + const int tunnel = !!(dev_flow->flow->layers & MLX5_FLOW_LAYER_TUNNEL); + unsigned int size = sizeof(struct ibv_flow_spec_ipv6); + struct ibv_flow_spec_ipv6 ipv6 = { + .type = IBV_FLOW_SPEC_IPV6 | (tunnel ? IBV_FLOW_SPEC_INNER : 0), + .size = size, + }; + + if (!mask) + mask = &rte_flow_item_ipv6_mask; + *item_flags |= tunnel ? MLX5_FLOW_LAYER_INNER_L3_IPV6 : + MLX5_FLOW_LAYER_OUTER_L3_IPV6; + if (spec) { + unsigned int i; + uint32_t vtc_flow_val; + uint32_t vtc_flow_mask; + + memcpy(&ipv6.val.src_ip, spec->hdr.src_addr, + RTE_DIM(ipv6.val.src_ip)); + memcpy(&ipv6.val.dst_ip, spec->hdr.dst_addr, + RTE_DIM(ipv6.val.dst_ip)); + memcpy(&ipv6.mask.src_ip, mask->hdr.src_addr, + RTE_DIM(ipv6.mask.src_ip)); + memcpy(&ipv6.mask.dst_ip, mask->hdr.dst_addr, + RTE_DIM(ipv6.mask.dst_ip)); + vtc_flow_val = rte_be_to_cpu_32(spec->hdr.vtc_flow); + vtc_flow_mask = rte_be_to_cpu_32(mask->hdr.vtc_flow); + ipv6.val.flow_label = + rte_cpu_to_be_32((vtc_flow_val & IPV6_HDR_FL_MASK) >> + IPV6_HDR_FL_SHIFT); + ipv6.val.traffic_class = (vtc_flow_val & IPV6_HDR_TC_MASK) >> + IPV6_HDR_TC_SHIFT; + ipv6.val.next_hdr = spec->hdr.proto; + ipv6.val.hop_limit = spec->hdr.hop_limits; + ipv6.mask.flow_label = + rte_cpu_to_be_32((vtc_flow_mask & IPV6_HDR_FL_MASK) >> + IPV6_HDR_FL_SHIFT); + ipv6.mask.traffic_class = (vtc_flow_mask & IPV6_HDR_TC_MASK) >> + IPV6_HDR_TC_SHIFT; + ipv6.mask.next_hdr = mask->hdr.proto; + ipv6.mask.hop_limit = mask->hdr.hop_limits; + /* Remove unwanted bits from values. */ + for (i = 0; i < RTE_DIM(ipv6.val.src_ip); ++i) { + ipv6.val.src_ip[i] &= ipv6.mask.src_ip[i]; + ipv6.val.dst_ip[i] &= ipv6.mask.dst_ip[i]; + } + ipv6.val.flow_label &= ipv6.mask.flow_label; + ipv6.val.traffic_class &= ipv6.mask.traffic_class; + ipv6.val.next_hdr &= ipv6.mask.next_hdr; + ipv6.val.hop_limit &= ipv6.mask.hop_limit; + } + flow_verbs_hashfields_adjust(dev_flow, tunnel, + (ETH_RSS_IPV6 | ETH_RSS_FRAG_IPV6 | + ETH_RSS_NONFRAG_IPV6_TCP | + ETH_RSS_NONFRAG_IPV6_UDP | + ETH_RSS_IPV6_EX | + ETH_RSS_IPV6_TCP_EX | + ETH_RSS_IPV6_UDP_EX | + ETH_RSS_NONFRAG_IPV6_OTHER), + (IBV_RX_HASH_SRC_IPV6 | + IBV_RX_HASH_DST_IPV6)); + dev_flow->verbs.attr->priority = MLX5_PRIORITY_MAP_L3; + flow_verbs_spec_add(dev_flow, &ipv6, size); +} + +/** + * Convert the @p item into a Verbs specification. This function assumes that + * the input is valid and that there is space to insert the requested item + * into the flow. + * + * @param[in] item + * Item specification. + * @param[in, out] item_flags + * Bit mask that marks all detected items. + * @param[in, out] dev_flow + * Pointer to sepacific flow structure. + */ +static void +flow_verbs_translate_item_udp(const struct rte_flow_item *item, + uint64_t *item_flags, + struct mlx5_flow *dev_flow) +{ + const struct rte_flow_item_udp *spec = item->spec; + const struct rte_flow_item_udp *mask = item->mask; + const int tunnel = !!(*item_flags & MLX5_FLOW_LAYER_TUNNEL); + unsigned int size = sizeof(struct ibv_flow_spec_tcp_udp); + struct ibv_flow_spec_tcp_udp udp = { + .type = IBV_FLOW_SPEC_UDP | (tunnel ? IBV_FLOW_SPEC_INNER : 0), + .size = size, + }; + + if (!mask) + mask = &rte_flow_item_udp_mask; + *item_flags |= tunnel ? MLX5_FLOW_LAYER_INNER_L4_UDP : + MLX5_FLOW_LAYER_OUTER_L4_UDP; + if (spec) { + udp.val.dst_port = spec->hdr.dst_port; + udp.val.src_port = spec->hdr.src_port; + udp.mask.dst_port = mask->hdr.dst_port; + udp.mask.src_port = mask->hdr.src_port; + /* Remove unwanted bits from values. */ + udp.val.src_port &= udp.mask.src_port; + udp.val.dst_port &= udp.mask.dst_port; + } + flow_verbs_hashfields_adjust(dev_flow, + tunnel, ETH_RSS_UDP, + (IBV_RX_HASH_SRC_PORT_UDP | + IBV_RX_HASH_DST_PORT_UDP)); + dev_flow->verbs.attr->priority = MLX5_PRIORITY_MAP_L4; + flow_verbs_spec_add(dev_flow, &udp, size); +} + +/** + * Convert the @p item into a Verbs specification. This function assumes that + * the input is valid and that there is space to insert the requested item + * into the flow. + * + * @param[in] item + * Item specification. + * @param[in, out] item_flags + * Bit mask that marks all detected items. + * @param[in, out] dev_flow + * Pointer to sepacific flow structure. + */ +static void +flow_verbs_translate_item_tcp(const struct rte_flow_item *item, + uint64_t *item_flags, + struct mlx5_flow *dev_flow) +{ + const struct rte_flow_item_tcp *spec = item->spec; + const struct rte_flow_item_tcp *mask = item->mask; + const int tunnel = !!(dev_flow->flow->layers & MLX5_FLOW_LAYER_TUNNEL); + unsigned int size = sizeof(struct ibv_flow_spec_tcp_udp); + struct ibv_flow_spec_tcp_udp tcp = { + .type = IBV_FLOW_SPEC_TCP | (tunnel ? IBV_FLOW_SPEC_INNER : 0), + .size = size, + }; + + if (!mask) + mask = &rte_flow_item_tcp_mask; + *item_flags |= tunnel ? MLX5_FLOW_LAYER_INNER_L4_TCP : + MLX5_FLOW_LAYER_OUTER_L4_TCP; + if (spec) { + tcp.val.dst_port = spec->hdr.dst_port; + tcp.val.src_port = spec->hdr.src_port; + tcp.mask.dst_port = mask->hdr.dst_port; + tcp.mask.src_port = mask->hdr.src_port; + /* Remove unwanted bits from values. */ + tcp.val.src_port &= tcp.mask.src_port; + tcp.val.dst_port &= tcp.mask.dst_port; + } + flow_verbs_hashfields_adjust(dev_flow, + tunnel, ETH_RSS_TCP, + (IBV_RX_HASH_SRC_PORT_TCP | + IBV_RX_HASH_DST_PORT_TCP)); + dev_flow->verbs.attr->priority = MLX5_PRIORITY_MAP_L4; + flow_verbs_spec_add(dev_flow, &tcp, size); +} + +/** + * Convert the @p item into a Verbs specification. This function assumes that + * the input is valid and that there is space to insert the requested item + * into the flow. + * + * @param[in] item + * Item specification. + * @param[in, out] item_flags + * Bit mask that marks all detected items. + * @param[in, out] dev_flow + * Pointer to sepacific flow structure. + */ +static void +flow_verbs_translate_item_vxlan(const struct rte_flow_item *item, + uint64_t *item_flags, + struct mlx5_flow *dev_flow) +{ + const struct rte_flow_item_vxlan *spec = item->spec; + const struct rte_flow_item_vxlan *mask = item->mask; + unsigned int size = sizeof(struct ibv_flow_spec_tunnel); + struct ibv_flow_spec_tunnel vxlan = { + .type = IBV_FLOW_SPEC_VXLAN_TUNNEL, + .size = size, + }; + union vni { + uint32_t vlan_id; + uint8_t vni[4]; + } id = { .vlan_id = 0, }; + + if (!mask) + mask = &rte_flow_item_vxlan_mask; + if (spec) { + memcpy(&id.vni[1], spec->vni, 3); + vxlan.val.tunnel_id = id.vlan_id; + memcpy(&id.vni[1], mask->vni, 3); + vxlan.mask.tunnel_id = id.vlan_id; + /* Remove unwanted bits from values. */ + vxlan.val.tunnel_id &= vxlan.mask.tunnel_id; + } + flow_verbs_spec_add(dev_flow, &vxlan, size); + dev_flow->verbs.attr->priority = MLX5_PRIORITY_MAP_L2; + *item_flags |= MLX5_FLOW_LAYER_VXLAN; +} + +/** + * Convert the @p item into a Verbs specification. This function assumes that + * the input is valid and that there is space to insert the requested item + * into the flow. + * + * @param[in] item + * Item specification. + * @param[in, out] item_flags + * Bit mask that marks all detected items. + * @param[in, out] dev_flow + * Pointer to sepacific flow structure. + */ +static void +flow_verbs_translate_item_vxlan_gpe(const struct rte_flow_item *item, + uint64_t *item_flags, + struct mlx5_flow *dev_flow) +{ + const struct rte_flow_item_vxlan_gpe *spec = item->spec; + const struct rte_flow_item_vxlan_gpe *mask = item->mask; + unsigned int size = sizeof(struct ibv_flow_spec_tunnel); + struct ibv_flow_spec_tunnel vxlan_gpe = { + .type = IBV_FLOW_SPEC_VXLAN_TUNNEL, + .size = size, + }; + union vni { + uint32_t vlan_id; + uint8_t vni[4]; + } 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; + } + flow_verbs_spec_add(dev_flow, &vxlan_gpe, size); + dev_flow->verbs.attr->priority = MLX5_PRIORITY_MAP_L2; + *item_flags |= MLX5_FLOW_LAYER_VXLAN_GPE; +} + +/** + * 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 +flow_verbs_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. This function assumes that + * the input is valid and that there is space to insert the requested item + * into the flow. + * + * @param[in] item + * Item specification. + * @param[in, out] item_flags + * Bit mask that marks all detected items. + * @param[in, out] dev_flow + * Pointer to sepacific flow structure. + */ +static void +flow_verbs_translate_item_gre(const struct rte_flow_item *item __rte_unused, + uint64_t *item_flags, + struct mlx5_flow *dev_flow) +{ + struct mlx5_flow_verbs *verbs = &dev_flow->verbs; +#ifndef HAVE_IBV_DEVICE_MPLS_SUPPORT + unsigned int size = sizeof(struct ibv_flow_spec_tunnel); + struct ibv_flow_spec_tunnel tunnel = { + .type = IBV_FLOW_SPEC_VXLAN_TUNNEL, + .size = size, + }; +#else + 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, + }; + + 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; + } +#endif + if (*item_flags & MLX5_FLOW_LAYER_OUTER_L3_IPV4) + flow_verbs_item_gre_ip_protocol_update(verbs->attr, + IBV_FLOW_SPEC_IPV4_EXT, + IPPROTO_GRE); + else + flow_verbs_item_gre_ip_protocol_update(verbs->attr, + IBV_FLOW_SPEC_IPV6, + IPPROTO_GRE); + flow_verbs_spec_add(dev_flow, &tunnel, size); + verbs->attr->priority = MLX5_PRIORITY_MAP_L2; + *item_flags |= MLX5_FLOW_LAYER_GRE; +} + +/** + * Convert the @p action into a Verbs specification. This function assumes that + * the input is valid and that there is space to insert the requested action + * into the flow. This function also return the action that was added. + * + * @param[in] item + * Item specification. + * @param[in, out] item_flags + * Bit mask that marks all detected items. + * @param[in, out] dev_flow + * Pointer to sepacific flow structure. + */ +static void +flow_verbs_translate_item_mpls(const struct rte_flow_item *item __rte_unused, + uint64_t *action_flags __rte_unused, + struct mlx5_flow *dev_flow __rte_unused) +{ +#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; + } + flow_verbs_spec_add(dev_flow, &mpls, size); + dev_flow->verbs.attr->priority = MLX5_PRIORITY_MAP_L2; + *action_flags |= MLX5_FLOW_LAYER_MPLS; +#endif +} + +/** + * Convert the @p action into a Verbs specification. This function assumes that + * the input is valid and that there is space to insert the requested action + * into the flow. This function also return the action that was added. + * + * @param[in, out] action_flags + * Pointer to the detected actions. + * @param[in] dev_flow + * Pointer to mlx5_flow. + */ +static void +flow_verbs_translate_action_drop(uint64_t *action_flags, + struct mlx5_flow *dev_flow) +{ + 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, + }; + + flow_verbs_spec_add(dev_flow, &drop, size); + *action_flags |= MLX5_FLOW_ACTION_DROP; +} + +/** + * Convert the @p action into a Verbs specification. This function assumes that + * the input is valid and that there is space to insert the requested action + * into the flow. This function also return the action that was added. + * + * @param[in] action + * Action configuration. + * @param[in, out] action_flags + * Pointer to the detected actions. + * @param[in] dev_flow + * Pointer to mlx5_flow. + */ +static void +flow_verbs_translate_action_queue(const struct rte_flow_action *action, + uint64_t *action_flags, + struct mlx5_flow *dev_flow) +{ + const struct rte_flow_action_queue *queue = action->conf; + struct rte_flow *flow = dev_flow->flow; + + if (flow->queue) + (*flow->queue)[0] = queue->index; + flow->rss.queue_num = 1; + *action_flags |= MLX5_FLOW_ACTION_QUEUE; +} + +/** + * Convert the @p action into a Verbs specification. This function assumes that + * the input is valid and that there is space to insert the requested action + * into the flow. This function also return the action that was added. + * + * @param[in] action + * Action configuration. + * @param[in, out] action_flags + * Pointer to the detected actions. + * @param[in] dev_flow + * Pointer to mlx5_flow. + */ +static void +flow_verbs_translate_action_rss(const struct rte_flow_action *action, + uint64_t *action_flags, + struct mlx5_flow *dev_flow) +{ + const struct rte_flow_action_rss *rss = action->conf; + struct rte_flow *flow = dev_flow->flow; + + 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; + *action_flags |= MLX5_FLOW_ACTION_RSS; +} + +/** + * Convert the @p action into a Verbs specification. This function assumes that + * the input is valid and that there is space to insert the requested action + * into the flow. This function also return the action that was added. + * + * @param[in] action + * Action configuration. + * @param[in, out] action_flags + * Pointer to the detected actions. + * @param[in] dev_flow + * Pointer to mlx5_flow. + */ +static void +flow_verbs_translate_action_flag + (const struct rte_flow_action *action __rte_unused, + uint64_t *action_flags, + struct mlx5_flow *dev_flow) +{ + 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), + }; + *action_flags |= MLX5_FLOW_ACTION_MARK; + flow_verbs_spec_add(dev_flow, &tag, 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 +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 a Verbs specification. This function assumes that + * the input is valid and that there is space to insert the requested action + * into the flow. This function also return the action that was added. + * + * @param[in] action + * Action configuration. + * @param[in, out] action_flags + * Pointer to the detected actions. + * @param[in] dev_flow + * Pointer to mlx5_flow. + */ +static void +flow_verbs_translate_action_mark(const struct rte_flow_action *action, + uint64_t *action_flags, + struct mlx5_flow *dev_flow) +{ + 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 = &dev_flow->verbs; + + if (*action_flags & MLX5_FLOW_ACTION_FLAG) { + flow_verbs_mark_update(verbs, mark->id); + size = 0; + } else { + tag.tag_id = mlx5_flow_mark_set(mark->id); + flow_verbs_spec_add(dev_flow, &tag, size); + } + *action_flags |= MLX5_FLOW_ACTION_MARK; +} + +/** + * Convert the @p action into a Verbs specification. This function assumes that + * the input is valid and that there is space to insert the requested action + * into the flow. This function also return the action that was added. + * + * @param[in] dev + * Pointer to the Ethernet device structure. + * @param[in] action + * Action configuration. + * @param[in, out] action_flags + * Pointer to the detected actions. + * @param[in] dev_flow + * Pointer to mlx5_flow. + * @param[out] error + * Pointer to error structure. + * + * @return + * 0 On success else a negative errno value is returned and rte_errno is set. + */ +static int +flow_verbs_translate_action_count(struct rte_eth_dev *dev, + const struct rte_flow_action *action, + uint64_t *action_flags, + struct mlx5_flow *dev_flow, + struct rte_flow_error *error) +{ + const struct rte_flow_action_count *count = action->conf; + struct rte_flow *flow = dev_flow->flow; +#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 = flow_verbs_counter_new(dev, count->shared, + count->id); + if (!flow->counter) + return rte_flow_error_set(error, rte_errno, + RTE_FLOW_ERROR_TYPE_ACTION, + action, + "cannot get counter" + " context."); + } + *action_flags |= MLX5_FLOW_ACTION_COUNT; +#ifdef HAVE_IBV_DEVICE_COUNTERS_SET_SUPPORT + counter.counter_set_handle = flow->counter->cs->handle; + flow_verbs_spec_add(dev_flow, &counter, size); +#endif + return 0; +} + +/** + * Internal validation function. For validating both actions and items. + * + * @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_errno is set. + */ +static int +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; + + if (items == NULL) + return -1; + ret = mlx5_flow_validate_attributes(dev, attr, error); + if (ret < 0) + return ret; + for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) { + int ret = 0; + switch (items->type) { + case RTE_FLOW_ITEM_TYPE_VOID: + break; + case RTE_FLOW_ITEM_TYPE_ETH: + ret = mlx5_flow_validate_item_eth(items, item_flags, + error); + if (ret < 0) + return ret; + item_flags |= tunnel ? MLX5_FLOW_LAYER_INNER_L2 : + MLX5_FLOW_LAYER_OUTER_L2; + break; + case RTE_FLOW_ITEM_TYPE_VLAN: + ret = mlx5_flow_validate_item_vlan(items, item_flags, + error); + if (ret < 0) + return ret; + item_flags |= tunnel ? MLX5_FLOW_LAYER_INNER_VLAN : + MLX5_FLOW_LAYER_OUTER_VLAN; + break; + case RTE_FLOW_ITEM_TYPE_IPV4: + ret = mlx5_flow_validate_item_ipv4(items, item_flags, + error); + if (ret < 0) + return ret; + item_flags |= tunnel ? MLX5_FLOW_LAYER_INNER_L3_IPV4 : + MLX5_FLOW_LAYER_OUTER_L3_IPV4; + if (items->mask != NULL && + ((const struct rte_flow_item_ipv4 *) + items->mask)->hdr.next_proto_id) + next_protocol = + ((const struct rte_flow_item_ipv4 *) + (items->spec))->hdr.next_proto_id; + break; + case RTE_FLOW_ITEM_TYPE_IPV6: + ret = mlx5_flow_validate_item_ipv6(items, item_flags, + error); + if (ret < 0) + return ret; + item_flags |= tunnel ? MLX5_FLOW_LAYER_INNER_L3_IPV6 : + MLX5_FLOW_LAYER_OUTER_L3_IPV6; + if (items->mask != NULL && + ((const struct rte_flow_item_ipv6 *) + items->mask)->hdr.proto) + next_protocol = + ((const struct rte_flow_item_ipv6 *) + items->spec)->hdr.proto; + break; + case RTE_FLOW_ITEM_TYPE_UDP: + ret = mlx5_flow_validate_item_udp(items, item_flags, + next_protocol, + error); + if (ret < 0) + return ret; + item_flags |= tunnel ? MLX5_FLOW_LAYER_INNER_L4_UDP : + MLX5_FLOW_LAYER_OUTER_L4_UDP; + break; + case RTE_FLOW_ITEM_TYPE_TCP: + ret = mlx5_flow_validate_item_tcp(items, item_flags, + next_protocol, error); + if (ret < 0) + return ret; + item_flags |= tunnel ? MLX5_FLOW_LAYER_INNER_L4_TCP : + MLX5_FLOW_LAYER_OUTER_L4_TCP; + break; + case RTE_FLOW_ITEM_TYPE_VXLAN: + ret = mlx5_flow_validate_item_vxlan(items, item_flags, + error); + if (ret < 0) + return ret; + item_flags |= MLX5_FLOW_LAYER_VXLAN; + break; + case RTE_FLOW_ITEM_TYPE_VXLAN_GPE: + ret = mlx5_flow_validate_item_vxlan_gpe(items, + item_flags, + dev, error); + if (ret < 0) + return ret; + item_flags |= MLX5_FLOW_LAYER_VXLAN_GPE; + break; + case RTE_FLOW_ITEM_TYPE_GRE: + ret = mlx5_flow_validate_item_gre(items, item_flags, + next_protocol, error); + if (ret < 0) + return ret; + item_flags |= MLX5_FLOW_LAYER_GRE; + break; + case RTE_FLOW_ITEM_TYPE_MPLS: + ret = mlx5_flow_validate_item_mpls(items, item_flags, + next_protocol, + error); + if (ret < 0) + return ret; + if (next_protocol != 0xff && + next_protocol != IPPROTO_MPLS) + return rte_flow_error_set + (error, EINVAL, + RTE_FLOW_ERROR_TYPE_ITEM, items, + "protocol filtering not compatible" + " with MPLS layer"); + item_flags |= MLX5_FLOW_LAYER_MPLS; + break; + default: + return rte_flow_error_set(error, ENOTSUP, + RTE_FLOW_ERROR_TYPE_ITEM, + NULL, "item not supported"); + } + } + for (; actions->type != RTE_FLOW_ACTION_TYPE_END; actions++) { + tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL); + switch (actions->type) { + case RTE_FLOW_ACTION_TYPE_VOID: + break; + case RTE_FLOW_ACTION_TYPE_FLAG: + ret = mlx5_flow_validate_action_flag(action_flags, + error); + if (ret < 0) + return ret; + action_flags |= MLX5_FLOW_ACTION_FLAG; + break; + case RTE_FLOW_ACTION_TYPE_MARK: + ret = mlx5_flow_validate_action_mark(actions, + action_flags, + error); + if (ret < 0) + return ret; + action_flags |= MLX5_FLOW_ACTION_MARK; + break; + case RTE_FLOW_ACTION_TYPE_DROP: + ret = mlx5_flow_validate_action_drop(action_flags, + error); + if (ret < 0) + return ret; + action_flags |= MLX5_FLOW_ACTION_DROP; + break; + case RTE_FLOW_ACTION_TYPE_QUEUE: + ret = mlx5_flow_validate_action_queue(actions, + action_flags, dev, + error); + if (ret < 0) + return ret; + action_flags |= MLX5_FLOW_ACTION_QUEUE; + break; + case RTE_FLOW_ACTION_TYPE_RSS: + ret = mlx5_flow_validate_action_rss(actions, + action_flags, dev, + error); + if (ret < 0) + return ret; + action_flags |= MLX5_FLOW_ACTION_RSS; + break; + case RTE_FLOW_ACTION_TYPE_COUNT: + ret = mlx5_flow_validate_action_count(dev, error); + if (ret < 0) + return ret; + action_flags |= MLX5_FLOW_ACTION_COUNT; + break; + default: + return rte_flow_error_set(error, ENOTSUP, + RTE_FLOW_ERROR_TYPE_ACTION, + actions, + "action not supported"); + } + } + if (!(action_flags & MLX5_FLOW_FATE_ACTIONS)) + return rte_flow_error_set(error, EINVAL, + RTE_FLOW_ERROR_TYPE_ACTION, actions, + "no fate action is found"); + return 0; +} + +/** + * Calculate the required bytes that are needed for the action part of the verbs + * flow, in addtion returns bit-fields with all the detected action, in order to + * avoid another interation over the actions. + * + * @param[in] actions + * Pointer to the list of actions. + * @param[out] action_flags + * Pointer to the detected actions. + * + * @return + * The size of the memory needed for all actions. + */ +static int +flow_verbs_get_actions_and_size(const struct rte_flow_action actions[], + uint64_t *action_flags) +{ + int size = 0; + uint64_t detected_actions = 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: + size += sizeof(struct ibv_flow_spec_action_tag); + detected_actions |= MLX5_FLOW_ACTION_FLAG; + break; + case RTE_FLOW_ACTION_TYPE_MARK: + size += sizeof(struct ibv_flow_spec_action_tag); + detected_actions |= MLX5_FLOW_ACTION_MARK; + break; + case RTE_FLOW_ACTION_TYPE_DROP: + size += sizeof(struct ibv_flow_spec_action_drop); + detected_actions |= MLX5_FLOW_ACTION_DROP; + break; + case RTE_FLOW_ACTION_TYPE_QUEUE: + detected_actions |= MLX5_FLOW_ACTION_QUEUE; + break; + case RTE_FLOW_ACTION_TYPE_RSS: + detected_actions |= MLX5_FLOW_ACTION_RSS; + break; + case RTE_FLOW_ACTION_TYPE_COUNT: +#ifdef HAVE_IBV_DEVICE_COUNTERS_SET_SUPPORT + size += sizeof(struct ibv_flow_spec_counter_action); +#endif + detected_actions |= MLX5_FLOW_ACTION_COUNT; + break; + default: + break; + } + } + *action_flags = detected_actions; + return size; +} + +/** + * Calculate the required bytes that are needed for the item part of the verbs + * flow, in addtion returns bit-fields with all the detected action, in order to + * avoid another interation over the actions. + * + * @param[in] actions + * Pointer to the list of items. + * @param[in, out] item_flags + * Pointer to the detected items. + * + * @return + * The size of the memory needed for all items. + */ +static int +flow_verbs_get_items_and_size(const struct rte_flow_item items[], + uint64_t *item_flags) +{ + int size = 0; + uint64_t detected_items = 0; + const int tunnel = !!(*item_flags & MLX5_FLOW_LAYER_TUNNEL); + + for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) { + switch (items->type) { + case RTE_FLOW_ITEM_TYPE_VOID: + break; + case RTE_FLOW_ITEM_TYPE_ETH: + size += sizeof(struct ibv_flow_spec_eth); + detected_items |= tunnel ? MLX5_FLOW_LAYER_INNER_L2 : + MLX5_FLOW_LAYER_OUTER_L2; + break; + case RTE_FLOW_ITEM_TYPE_VLAN: + size += sizeof(struct ibv_flow_spec_eth); + detected_items |= tunnel ? MLX5_FLOW_LAYER_INNER_VLAN : + MLX5_FLOW_LAYER_OUTER_VLAN; + break; + case RTE_FLOW_ITEM_TYPE_IPV4: + size += sizeof(struct ibv_flow_spec_ipv4_ext); + detected_items |= tunnel ? + MLX5_FLOW_LAYER_INNER_L3_IPV4 : + MLX5_FLOW_LAYER_OUTER_L3_IPV4; + break; + case RTE_FLOW_ITEM_TYPE_IPV6: + size += sizeof(struct ibv_flow_spec_ipv6); + detected_items |= tunnel ? + MLX5_FLOW_LAYER_INNER_L3_IPV6 : + MLX5_FLOW_LAYER_OUTER_L3_IPV6; + break; + case RTE_FLOW_ITEM_TYPE_UDP: + size += sizeof(struct ibv_flow_spec_tcp_udp); + detected_items |= tunnel ? + MLX5_FLOW_LAYER_INNER_L4_UDP : + MLX5_FLOW_LAYER_OUTER_L4_UDP; + break; + case RTE_FLOW_ITEM_TYPE_TCP: + size += sizeof(struct ibv_flow_spec_tcp_udp); + detected_items |= tunnel ? + MLX5_FLOW_LAYER_INNER_L4_TCP : + MLX5_FLOW_LAYER_OUTER_L4_TCP; + break; + case RTE_FLOW_ITEM_TYPE_VXLAN: + size += sizeof(struct ibv_flow_spec_tunnel); + detected_items |= MLX5_FLOW_LAYER_VXLAN; + break; + case RTE_FLOW_ITEM_TYPE_VXLAN_GPE: + size += sizeof(struct ibv_flow_spec_tunnel); + detected_items |= MLX5_FLOW_LAYER_VXLAN_GPE; + break; +#ifdef HAVE_IBV_DEVICE_MPLS_SUPPORT + case RTE_FLOW_ITEM_TYPE_GRE: + size += sizeof(struct ibv_flow_spec_gre); + detected_items |= MLX5_FLOW_LAYER_GRE; + break; + case RTE_FLOW_ITEM_TYPE_MPLS: + size += sizeof(struct ibv_flow_spec_mpls); + detected_items |= MLX5_FLOW_LAYER_MPLS; + break; +#else + case RTE_FLOW_ITEM_TYPE_GRE: + size += sizeof(struct ibv_flow_spec_tunnel); + detected_items |= MLX5_FLOW_LAYER_TUNNEL; + break; +#endif + default: + break; + } + } + *item_flags = detected_items; + return size; +} + +/** + * Internal preparation function. Allocate mlx5_flow with the required size. + * The required size is calculate based on the actions and items. This function + * also returns the detected actions and items for later use. + * + * @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] item_flags + * Pointer to bit mask of all items detected. + * @param[out] action_flags + * Pointer to bit mask of all actions detected. + * @param[out] error + * Pointer to the error structure. + * + * @return + * Pointer to mlx5_flow object on success, otherwise NULL and rte_errno + * is set. + */ +static struct mlx5_flow * +flow_verbs_prepare(const struct rte_flow_attr *attr __rte_unused, + const struct rte_flow_item items[], + const struct rte_flow_action actions[], + uint64_t *item_flags, + uint64_t *action_flags, + struct rte_flow_error *error) +{ + uint32_t size = sizeof(struct mlx5_flow) + sizeof(struct ibv_flow_attr); + struct mlx5_flow *flow; + + size += flow_verbs_get_actions_and_size(actions, action_flags); + size += flow_verbs_get_items_and_size(items, item_flags); + flow = rte_calloc(__func__, 1, size, 0); + if (!flow) { + rte_flow_error_set(error, ENOMEM, + RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL, + "not enough memory to create flow"); + return NULL; + } + flow->verbs.attr = (void *)(flow + 1); + flow->verbs.specs = + (uint8_t *)(flow + 1) + sizeof(struct ibv_flow_attr); + return flow; +} + +/** + * Fill the flow with verb spec. + * + * @param[in] dev + * Pointer to Ethernet device. + * @param[in, out] dev_flow + * Pointer to the mlx5 flow. + * @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, else a negative errno value otherwise and rte_ernno is set. + */ +static int +flow_verbs_translate(struct rte_eth_dev *dev, + struct mlx5_flow *dev_flow, + const struct rte_flow_attr *attr, + const struct rte_flow_item items[], + const struct rte_flow_action actions[], + struct rte_flow_error *error) +{ + uint64_t action_flags = 0; + uint64_t item_flags = 0; + uint64_t priority = attr->priority; + struct priv *priv = dev->data->dev_private; + + if (priority == MLX5_FLOW_PRIO_RSVD) + priority = priv->config.flow_prio - 1; + for (; actions->type != RTE_FLOW_ACTION_TYPE_END; actions++) { + int ret; + switch (actions->type) { + case RTE_FLOW_ACTION_TYPE_VOID: + break; + case RTE_FLOW_ACTION_TYPE_FLAG: + flow_verbs_translate_action_flag(actions, + &action_flags, + dev_flow); + break; + case RTE_FLOW_ACTION_TYPE_MARK: + flow_verbs_translate_action_mark(actions, + &action_flags, + dev_flow); + break; + case RTE_FLOW_ACTION_TYPE_DROP: + flow_verbs_translate_action_drop(&action_flags, + dev_flow); + break; + case RTE_FLOW_ACTION_TYPE_QUEUE: + flow_verbs_translate_action_queue(actions, + &action_flags, + dev_flow); + break; + case RTE_FLOW_ACTION_TYPE_RSS: + flow_verbs_translate_action_rss(actions, + &action_flags, + dev_flow); + break; + case RTE_FLOW_ACTION_TYPE_COUNT: + ret = flow_verbs_translate_action_count(dev, + actions, + &action_flags, + dev_flow, + error); + if (ret < 0) + return ret; + break; + default: + return rte_flow_error_set(error, ENOTSUP, + RTE_FLOW_ERROR_TYPE_ACTION, + actions, + "action not supported"); + } + } + dev_flow->flow->actions |= action_flags; + for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) { + switch (items->type) { + case RTE_FLOW_ITEM_TYPE_VOID: + break; + case RTE_FLOW_ITEM_TYPE_ETH: + flow_verbs_translate_item_eth(items, &item_flags, + dev_flow); + break; + case RTE_FLOW_ITEM_TYPE_VLAN: + flow_verbs_translate_item_vlan(items, &item_flags, + dev_flow); + break; + case RTE_FLOW_ITEM_TYPE_IPV4: + flow_verbs_translate_item_ipv4(items, &item_flags, + dev_flow); + break; + case RTE_FLOW_ITEM_TYPE_IPV6: + flow_verbs_translate_item_ipv6(items, &item_flags, + dev_flow); + break; + case RTE_FLOW_ITEM_TYPE_UDP: + flow_verbs_translate_item_udp(items, &item_flags, + dev_flow); + break; + case RTE_FLOW_ITEM_TYPE_TCP: + flow_verbs_translate_item_tcp(items, &item_flags, + dev_flow); + break; + case RTE_FLOW_ITEM_TYPE_VXLAN: + flow_verbs_translate_item_vxlan(items, &item_flags, + dev_flow); + break; + case RTE_FLOW_ITEM_TYPE_VXLAN_GPE: + flow_verbs_translate_item_vxlan_gpe(items, &item_flags, + dev_flow); + break; + case RTE_FLOW_ITEM_TYPE_GRE: + flow_verbs_translate_item_gre(items, &item_flags, + dev_flow); + break; + case RTE_FLOW_ITEM_TYPE_MPLS: + flow_verbs_translate_item_mpls(items, &item_flags, + dev_flow); + break; + default: + return rte_flow_error_set(error, ENOTSUP, + RTE_FLOW_ERROR_TYPE_ITEM, + NULL, + "item not supported"); + } + } + dev_flow->verbs.attr->priority = + mlx5_flow_adjust_priority(dev, priority, + dev_flow->verbs.attr->priority); + return 0; +} + +/** + * Remove the flow from the NIC but keeps it in memory. + * + * @param[in] dev + * Pointer to the Ethernet device structure. + * @param[in, out] flow + * Pointer to flow structure. + */ +static void +flow_verbs_remove(struct rte_eth_dev *dev, struct rte_flow *flow) +{ + struct mlx5_flow_verbs *verbs; + struct mlx5_flow *dev_flow; + + if (!flow) + return; + LIST_FOREACH(dev_flow, &flow->dev_flows, next) { + verbs = &dev_flow->verbs; + if (verbs->flow) { + claim_zero(mlx5_glue->destroy_flow(verbs->flow)); + verbs->flow = NULL; + } + if (verbs->hrxq) { + if (flow->actions & MLX5_FLOW_ACTION_DROP) + mlx5_hrxq_drop_release(dev); + else + mlx5_hrxq_release(dev, verbs->hrxq); + verbs->hrxq = NULL; + } + } + if (flow->counter) { + flow_verbs_counter_release(flow->counter); + flow->counter = NULL; + } +} + +/** + * Remove the flow from the NIC and the memory. + * + * @param[in] dev + * Pointer to the Ethernet device structure. + * @param[in, out] flow + * Pointer to flow structure. + */ +static void +flow_verbs_destroy(struct rte_eth_dev *dev, struct rte_flow *flow) +{ + struct mlx5_flow *dev_flow; + + if (!flow) + return; + flow_verbs_remove(dev, flow); + while (!LIST_EMPTY(&flow->dev_flows)) { + dev_flow = LIST_FIRST(&flow->dev_flows); + LIST_REMOVE(dev_flow, next); + rte_free(dev_flow); + } +} + +/** + * Apply the flow to the NIC. + * + * @param[in] dev + * Pointer to the Ethernet device structure. + * @param[in, out] flow + * Pointer to flow structure. + * @param[out] error + * Pointer to error structure. + * + * @return + * 0 on success, a negative errno value otherwise and rte_errno is set. + */ +static int +flow_verbs_apply(struct rte_eth_dev *dev, struct rte_flow *flow, + struct rte_flow_error *error) +{ + struct mlx5_flow_verbs *verbs; + struct mlx5_flow *dev_flow; + int err; + + LIST_FOREACH(dev_flow, &flow->dev_flows, next) { + verbs = &dev_flow->verbs; + if (flow->actions & MLX5_FLOW_ACTION_DROP) { + verbs->hrxq = mlx5_hrxq_drop_new(dev); + if (!verbs->hrxq) { + rte_flow_error_set + (error, errno, + RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL, + "cannot get drop hash queue"); + goto error; + } + } else { + struct mlx5_hrxq *hrxq; + + hrxq = mlx5_hrxq_get(dev, flow->key, + MLX5_RSS_HASH_KEY_LEN, + verbs->hash_fields, + (*flow->queue), + flow->rss.queue_num); + if (!hrxq) + hrxq = mlx5_hrxq_new(dev, flow->key, + MLX5_RSS_HASH_KEY_LEN, + verbs->hash_fields, + (*flow->queue), + flow->rss.queue_num, + !!(flow->layers & + MLX5_FLOW_LAYER_TUNNEL)); + if (!hrxq) { + rte_flow_error_set + (error, rte_errno, + RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL, + "cannot get hash queue"); + goto error; + } + verbs->hrxq = hrxq; + } + verbs->flow = mlx5_glue->create_flow(verbs->hrxq->qp, + verbs->attr); + if (!verbs->flow) { + rte_flow_error_set(error, errno, + RTE_FLOW_ERROR_TYPE_UNSPECIFIED, + NULL, + "hardware refuses to create flow"); + goto error; + } + } + return 0; +error: + err = rte_errno; /* Save rte_errno before cleanup. */ + LIST_FOREACH(dev_flow, &flow->dev_flows, next) { + verbs = &dev_flow->verbs; + if (verbs->hrxq) { + if (flow->actions & MLX5_FLOW_ACTION_DROP) + mlx5_hrxq_drop_release(dev); + else + mlx5_hrxq_release(dev, verbs->hrxq); + verbs->hrxq = NULL; + } + } + rte_errno = err; /* Restore rte_errno. */ + return -rte_errno; +} + +void +mlx5_flow_verbs_get_driver_ops(struct mlx5_flow_driver_ops *flow_ops) +{ + *flow_ops = (struct mlx5_flow_driver_ops) { + .validate = flow_verbs_validate, + .prepare = flow_verbs_prepare, + .translate = flow_verbs_translate, + .apply = flow_verbs_apply, + .remove = flow_verbs_remove, + .destroy = flow_verbs_destroy, + }; +} -- 2.20.1