* Copyright 2016 Mellanox Technologies, Ltd
*/
+#include <netinet/in.h>
#include <sys/queue.h>
+#include <stdalign.h>
#include <stdint.h>
#include <string.h>
#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 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)
-/* 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)
-
-/* Actions that modify the fate of matching traffic. */
-#define MLX5_FLOW_FATE_DROP (1u << 0)
-
-/** Handles information leading to a drop fate. */
-struct mlx5_flow_verbs {
- 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. */
+enum mlx5_expansion {
+ MLX5_EXPANSION_ROOT,
+ MLX5_EXPANSION_ROOT_OUTER,
+ MLX5_EXPANSION_ROOT_ETH_VLAN,
+ MLX5_EXPANSION_ROOT_OUTER_ETH_VLAN,
+ MLX5_EXPANSION_OUTER_ETH,
+ MLX5_EXPANSION_OUTER_ETH_VLAN,
+ MLX5_EXPANSION_OUTER_VLAN,
+ MLX5_EXPANSION_OUTER_IPV4,
+ MLX5_EXPANSION_OUTER_IPV4_UDP,
+ MLX5_EXPANSION_OUTER_IPV4_TCP,
+ MLX5_EXPANSION_OUTER_IPV6,
+ MLX5_EXPANSION_OUTER_IPV6_UDP,
+ MLX5_EXPANSION_OUTER_IPV6_TCP,
+ MLX5_EXPANSION_VXLAN,
+ MLX5_EXPANSION_VXLAN_GPE,
+ MLX5_EXPANSION_GRE,
+ MLX5_EXPANSION_MPLS,
+ MLX5_EXPANSION_ETH,
+ MLX5_EXPANSION_ETH_VLAN,
+ MLX5_EXPANSION_VLAN,
+ MLX5_EXPANSION_IPV4,
+ MLX5_EXPANSION_IPV4_UDP,
+ MLX5_EXPANSION_IPV4_TCP,
+ MLX5_EXPANSION_IPV6,
+ MLX5_EXPANSION_IPV6_UDP,
+ MLX5_EXPANSION_IPV6_TCP,
};
-/* 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 fate;
- /**< Bit-fields of present fate see MLX5_FLOW_FATE_*. */
- struct mlx5_flow_verbs verbs; /* Verbs drop flow. */
+/** Supported expansion of items. */
+static const struct rte_flow_expand_node mlx5_support_expansion[] = {
+ [MLX5_EXPANSION_ROOT] = {
+ .next = RTE_FLOW_EXPAND_RSS_NEXT(MLX5_EXPANSION_ETH,
+ MLX5_EXPANSION_IPV4,
+ MLX5_EXPANSION_IPV6),
+ .type = RTE_FLOW_ITEM_TYPE_END,
+ },
+ [MLX5_EXPANSION_ROOT_OUTER] = {
+ .next = RTE_FLOW_EXPAND_RSS_NEXT(MLX5_EXPANSION_OUTER_ETH,
+ MLX5_EXPANSION_OUTER_IPV4,
+ MLX5_EXPANSION_OUTER_IPV6),
+ .type = RTE_FLOW_ITEM_TYPE_END,
+ },
+ [MLX5_EXPANSION_ROOT_ETH_VLAN] = {
+ .next = RTE_FLOW_EXPAND_RSS_NEXT(MLX5_EXPANSION_ETH_VLAN),
+ .type = RTE_FLOW_ITEM_TYPE_END,
+ },
+ [MLX5_EXPANSION_ROOT_OUTER_ETH_VLAN] = {
+ .next = RTE_FLOW_EXPAND_RSS_NEXT(MLX5_EXPANSION_OUTER_ETH_VLAN),
+ .type = RTE_FLOW_ITEM_TYPE_END,
+ },
+ [MLX5_EXPANSION_OUTER_ETH] = {
+ .next = RTE_FLOW_EXPAND_RSS_NEXT(MLX5_EXPANSION_OUTER_IPV4,
+ MLX5_EXPANSION_OUTER_IPV6,
+ MLX5_EXPANSION_MPLS),
+ .type = RTE_FLOW_ITEM_TYPE_ETH,
+ .rss_types = 0,
+ },
+ [MLX5_EXPANSION_OUTER_ETH_VLAN] = {
+ .next = RTE_FLOW_EXPAND_RSS_NEXT(MLX5_EXPANSION_OUTER_VLAN),
+ .type = RTE_FLOW_ITEM_TYPE_ETH,
+ .rss_types = 0,
+ },
+ [MLX5_EXPANSION_OUTER_VLAN] = {
+ .next = RTE_FLOW_EXPAND_RSS_NEXT(MLX5_EXPANSION_OUTER_IPV4,
+ MLX5_EXPANSION_OUTER_IPV6),
+ .type = RTE_FLOW_ITEM_TYPE_VLAN,
+ },
+ [MLX5_EXPANSION_OUTER_IPV4] = {
+ .next = RTE_FLOW_EXPAND_RSS_NEXT
+ (MLX5_EXPANSION_OUTER_IPV4_UDP,
+ MLX5_EXPANSION_OUTER_IPV4_TCP,
+ MLX5_EXPANSION_GRE),
+ .type = RTE_FLOW_ITEM_TYPE_IPV4,
+ .rss_types = ETH_RSS_IPV4 | ETH_RSS_FRAG_IPV4 |
+ ETH_RSS_NONFRAG_IPV4_OTHER,
+ },
+ [MLX5_EXPANSION_OUTER_IPV4_UDP] = {
+ .next = RTE_FLOW_EXPAND_RSS_NEXT(MLX5_EXPANSION_VXLAN,
+ MLX5_EXPANSION_VXLAN_GPE),
+ .type = RTE_FLOW_ITEM_TYPE_UDP,
+ .rss_types = ETH_RSS_NONFRAG_IPV4_UDP,
+ },
+ [MLX5_EXPANSION_OUTER_IPV4_TCP] = {
+ .type = RTE_FLOW_ITEM_TYPE_TCP,
+ .rss_types = ETH_RSS_NONFRAG_IPV4_TCP,
+ },
+ [MLX5_EXPANSION_OUTER_IPV6] = {
+ .next = RTE_FLOW_EXPAND_RSS_NEXT
+ (MLX5_EXPANSION_OUTER_IPV6_UDP,
+ MLX5_EXPANSION_OUTER_IPV6_TCP),
+ .type = RTE_FLOW_ITEM_TYPE_IPV6,
+ .rss_types = ETH_RSS_IPV6 | ETH_RSS_FRAG_IPV6 |
+ ETH_RSS_NONFRAG_IPV6_OTHER,
+ },
+ [MLX5_EXPANSION_OUTER_IPV6_UDP] = {
+ .next = RTE_FLOW_EXPAND_RSS_NEXT(MLX5_EXPANSION_VXLAN,
+ MLX5_EXPANSION_VXLAN_GPE),
+ .type = RTE_FLOW_ITEM_TYPE_UDP,
+ .rss_types = ETH_RSS_NONFRAG_IPV6_UDP,
+ },
+ [MLX5_EXPANSION_OUTER_IPV6_TCP] = {
+ .type = RTE_FLOW_ITEM_TYPE_TCP,
+ .rss_types = ETH_RSS_NONFRAG_IPV6_TCP,
+ },
+ [MLX5_EXPANSION_VXLAN] = {
+ .next = RTE_FLOW_EXPAND_RSS_NEXT(MLX5_EXPANSION_ETH),
+ .type = RTE_FLOW_ITEM_TYPE_VXLAN,
+ },
+ [MLX5_EXPANSION_VXLAN_GPE] = {
+ .next = RTE_FLOW_EXPAND_RSS_NEXT(MLX5_EXPANSION_ETH,
+ MLX5_EXPANSION_IPV4,
+ MLX5_EXPANSION_IPV6),
+ .type = RTE_FLOW_ITEM_TYPE_VXLAN_GPE,
+ },
+ [MLX5_EXPANSION_GRE] = {
+ .next = RTE_FLOW_EXPAND_RSS_NEXT(MLX5_EXPANSION_IPV4),
+ .type = RTE_FLOW_ITEM_TYPE_GRE,
+ },
+ [MLX5_EXPANSION_MPLS] = {
+ .next = RTE_FLOW_EXPAND_RSS_NEXT(MLX5_EXPANSION_IPV4,
+ MLX5_EXPANSION_IPV6),
+ .type = RTE_FLOW_ITEM_TYPE_MPLS,
+ },
+ [MLX5_EXPANSION_ETH] = {
+ .next = RTE_FLOW_EXPAND_RSS_NEXT(MLX5_EXPANSION_IPV4,
+ MLX5_EXPANSION_IPV6),
+ .type = RTE_FLOW_ITEM_TYPE_ETH,
+ },
+ [MLX5_EXPANSION_ETH_VLAN] = {
+ .next = RTE_FLOW_EXPAND_RSS_NEXT(MLX5_EXPANSION_VLAN),
+ .type = RTE_FLOW_ITEM_TYPE_ETH,
+ },
+ [MLX5_EXPANSION_VLAN] = {
+ .next = RTE_FLOW_EXPAND_RSS_NEXT(MLX5_EXPANSION_IPV4,
+ MLX5_EXPANSION_IPV6),
+ .type = RTE_FLOW_ITEM_TYPE_VLAN,
+ },
+ [MLX5_EXPANSION_IPV4] = {
+ .next = RTE_FLOW_EXPAND_RSS_NEXT(MLX5_EXPANSION_IPV4_UDP,
+ MLX5_EXPANSION_IPV4_TCP),
+ .type = RTE_FLOW_ITEM_TYPE_IPV4,
+ .rss_types = ETH_RSS_IPV4 | ETH_RSS_FRAG_IPV4 |
+ ETH_RSS_NONFRAG_IPV4_OTHER,
+ },
+ [MLX5_EXPANSION_IPV4_UDP] = {
+ .type = RTE_FLOW_ITEM_TYPE_UDP,
+ .rss_types = ETH_RSS_NONFRAG_IPV4_UDP,
+ },
+ [MLX5_EXPANSION_IPV4_TCP] = {
+ .type = RTE_FLOW_ITEM_TYPE_TCP,
+ .rss_types = ETH_RSS_NONFRAG_IPV4_TCP,
+ },
+ [MLX5_EXPANSION_IPV6] = {
+ .next = RTE_FLOW_EXPAND_RSS_NEXT(MLX5_EXPANSION_IPV6_UDP,
+ MLX5_EXPANSION_IPV6_TCP),
+ .type = RTE_FLOW_ITEM_TYPE_IPV6,
+ .rss_types = ETH_RSS_IPV6 | ETH_RSS_FRAG_IPV6 |
+ ETH_RSS_NONFRAG_IPV6_OTHER,
+ },
+ [MLX5_EXPANSION_IPV6_UDP] = {
+ .type = RTE_FLOW_ITEM_TYPE_UDP,
+ .rss_types = ETH_RSS_NONFRAG_IPV6_UDP,
+ },
+ [MLX5_EXPANSION_IPV6_TCP] = {
+ .type = RTE_FLOW_ITEM_TYPE_TCP,
+ .rss_types = ETH_RSS_NONFRAG_IPV6_TCP,
+ },
};
static const struct rte_flow_ops mlx5_flow_ops = {
.destroy = mlx5_flow_destroy,
.flush = mlx5_flow_flush,
.isolate = mlx5_flow_isolate,
+ .query = mlx5_flow_query,
};
/* Convert FDIR request to Generic flow. */
struct rte_flow_action_queue queue;
};
-/* Verbs specification header. */
-struct ibv_spec_header {
- enum ibv_flow_spec_type type;
- uint16_t size;
+/* 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 },
};
- /**
- * Discover the maximum number of priority available.
- *
- * @param[in] dev
- * Pointer to Ethernet device.
- *
- * @return
- * number of supported flow priority on success, a negative errno value
- * otherwise and rte_errno is set.
- */
+/* Map of Verbs to Flow priority with 16 Verbs priorities. */
+static const uint32_t priority_map_5[][MLX5_PRIORITY_MAP_MAX] = {
+ { 0, 1, 2 }, { 3, 4, 5 }, { 6, 7, 8 },
+ { 9, 10, 11 }, { 12, 13, 14 },
+};
+
+/* Tunnel information. */
+struct mlx5_flow_tunnel_info {
+ uint32_t tunnel; /**< Tunnel bit (see MLX5_FLOW_*). */
+ uint32_t ptype; /**< Tunnel Ptype (see RTE_PTYPE_*). */
+};
+
+static struct mlx5_flow_tunnel_info tunnels_info[] = {
+ {
+ .tunnel = MLX5_FLOW_LAYER_VXLAN,
+ .ptype = RTE_PTYPE_TUNNEL_VXLAN | RTE_PTYPE_L4_UDP,
+ },
+ {
+ .tunnel = MLX5_FLOW_LAYER_VXLAN_GPE,
+ .ptype = RTE_PTYPE_TUNNEL_VXLAN_GPE | RTE_PTYPE_L4_UDP,
+ },
+ {
+ .tunnel = MLX5_FLOW_LAYER_GRE,
+ .ptype = RTE_PTYPE_TUNNEL_GRE,
+ },
+ {
+ .tunnel = MLX5_FLOW_LAYER_MPLS | MLX5_FLOW_LAYER_OUTER_L4_UDP,
+ .ptype = RTE_PTYPE_TUNNEL_MPLS_IN_GRE | RTE_PTYPE_L4_UDP,
+ },
+ {
+ .tunnel = MLX5_FLOW_LAYER_MPLS,
+ .ptype = RTE_PTYPE_TUNNEL_MPLS_IN_GRE,
+ },
+};
+
+/* 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 the Ethernet device structure.
+ *
+ * @return
+ * number of supported flow priority on success, a negative errno
+ * value otherwise and rte_errno is set.
+ */
int
mlx5_flow_discover_priorities(struct rte_eth_dev *dev)
{
struct mlx5_hrxq *drop = mlx5_hrxq_drop_new(dev);
uint16_t vprio[] = { 8, 16 };
int i;
+ int priority = 0;
if (!drop) {
rte_errno = ENOTSUP;
if (!flow)
break;
claim_zero(mlx5_glue->destroy_flow(flow));
+ priority = vprio[i];
+ }
+ switch (priority) {
+ case 8:
+ priority = RTE_DIM(priority_map_3);
+ break;
+ case 16:
+ priority = RTE_DIM(priority_map_5);
+ break;
+ default:
+ rte_errno = ENOTSUP;
+ DRV_LOG(ERR,
+ "port %u verbs maximum priority: %d expected 8/16",
+ dev->data->port_id, vprio[i]);
+ return -rte_errno;
}
mlx5_hrxq_drop_release(dev);
DRV_LOG(INFO, "port %u flow maximum priority: %d",
- dev->data->port_id, vprio[i - 1]);
- return vprio[i - 1];
+ dev->data->port_id, priority);
+ return priority;
}
/**
- * Verify the @p attributes will be correctly understood by the NIC and store
- * them in the @p flow if everything is correct.
+ * Adjust flow priority based on the highest layer and the request priority.
*
* @param[in] dev
- * Pointer to Ethernet device.
- * @param[in] attributes
- * Pointer to flow attributes
- * @param[in, out] flow
- * Pointer to the rte_flow structure.
- * @param[out] error
- * Pointer to error structure.
+ * Pointer to the Ethernet device structure.
+ * @param[in] priority
+ * The rule base priority.
+ * @param[in] subpriority
+ * The priority based on the items.
*
* @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
+ * The new priority.
*/
-static int
-mlx5_flow_attributes(struct rte_eth_dev *dev,
- const struct rte_flow_attr *attributes,
- struct rte_flow *flow,
- struct rte_flow_error *error)
+uint32_t mlx5_flow_adjust_priority(struct rte_eth_dev *dev, int32_t priority,
+ uint32_t subpriority)
{
- uint32_t priority_max =
- ((struct priv *)dev->data->dev_private)->config.flow_prio;
+ uint32_t res = 0;
+ struct priv *priv = dev->data->dev_private;
- if (attributes->group)
- return rte_flow_error_set(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ATTR_GROUP,
- NULL,
- "groups is not supported");
- if (attributes->priority >= priority_max)
- return rte_flow_error_set(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ATTR_PRIORITY,
- NULL,
- "priority out of range");
- if (attributes->egress)
- return rte_flow_error_set(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ATTR_EGRESS,
- NULL,
- "egress is not supported");
- if (attributes->transfer)
- return rte_flow_error_set(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ATTR_TRANSFER,
- NULL,
- "transfer is not supported");
- if (!attributes->ingress)
- return rte_flow_error_set(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ATTR_INGRESS,
- NULL,
- "ingress attribute is mandatory");
- flow->attributes = *attributes;
- return 0;
+ switch (priv->config.flow_prio) {
+ case RTE_DIM(priority_map_3):
+ res = priority_map_3[priority][subpriority];
+ break;
+ case RTE_DIM(priority_map_5):
+ res = priority_map_5[priority][subpriority];
+ break;
+ }
+ return res;
}
/**
" bits");
if (!item->spec && (item->mask || item->last))
return rte_flow_error_set(error, EINVAL,
- RTE_FLOW_ERROR_TYPE_ITEM,
- item,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
"mask/last without a spec is not"
" supported");
if (item->spec && item->last) {
}
/**
- * Add a verbs specification into @p flow.
+ * Adjust the hash fields according to the @p flow information.
+ *
+ * @param[in] dev_flow.
+ * Pointer to the mlx5_flow.
+ * @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.
+ *
+ * @return
+ * The hash fileds that should be used.
+ */
+uint64_t
+mlx5_flow_hashfields_adjust(struct mlx5_flow *dev_flow,
+ int tunnel __rte_unused, uint32_t layer_types,
+ uint64_t hash_fields)
+{
+ struct rte_flow *flow = dev_flow->flow;
+#ifdef HAVE_IBV_DEVICE_TUNNEL_SUPPORT
+ int rss_request_inner = flow->rss.level >= 2;
+
+ /* Check RSS hash level for tunnel. */
+ if (tunnel && rss_request_inner)
+ hash_fields |= IBV_RX_HASH_INNER;
+ else if (tunnel || rss_request_inner)
+ return 0;
+#endif
+ /* Check if requested layer matches RSS hash fields. */
+ if (!(flow->rss.types & layer_types))
+ return 0;
+ return hash_fields;
+}
+
+/**
+ * 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, out] flow
+ * @param[in] dev
+ * Pointer to the Ethernet device structure.
+ * @param[in] flow
* Pointer to flow structure.
- * @param[in] src
- * Create specification.
- * @param[in] size
- * Size in bytes of the specification to copy.
*/
static void
-mlx5_flow_spec_verbs_add(struct rte_flow *flow, void *src, unsigned int size)
+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->actions &
+ (MLX5_FLOW_ACTION_FLAG | MLX5_FLOW_ACTION_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)
{
- if (flow->verbs.specs) {
- void *dst;
+ 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;
+
+ 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;
- dst = (void *)(flow->verbs.specs + flow->verbs.size);
- memcpy(dst, src, size);
- ++flow->verbs.attr->num_of_specs;
+ 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->verbs.size += size;
+}
+
+/*
+ * 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.
+ */
+int
+mlx5_flow_validate_action_flag(uint64_t action_flags,
+ struct rte_flow_error *error)
+{
+
+ if (action_flags & MLX5_FLOW_ACTION_DROP)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't drop and flag in same flow");
+ if (action_flags & MLX5_FLOW_ACTION_MARK)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't mark and flag in same flow");
+ if (action_flags & MLX5_FLOW_ACTION_FLAG)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't have 2 flag"
+ " actions in same flow");
+ return 0;
+}
+
+/*
+ * Validate the mark action.
+ *
+ * @param[in] action
+ * Pointer to the queue action.
+ * @param[in] action_flags
+ * Bit-fields that holds the actions detected until now.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_flow_validate_action_mark(const struct rte_flow_action *action,
+ uint64_t action_flags,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_action_mark *mark = action->conf;
+
+ if (!mark)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ action,
+ "configuration cannot be null");
+ if (mark->id >= MLX5_FLOW_MARK_MAX)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ &mark->id,
+ "mark id must in 0 <= id < "
+ RTE_STR(MLX5_FLOW_MARK_MAX));
+ if (action_flags & MLX5_FLOW_ACTION_DROP)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't drop and mark in same flow");
+ if (action_flags & MLX5_FLOW_ACTION_FLAG)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't flag and mark in same flow");
+ if (action_flags & MLX5_FLOW_ACTION_MARK)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't have 2 mark actions in same"
+ " flow");
+ return 0;
+}
+
+/*
+ * Validate the drop action.
+ *
+ * @param[in] action_flags
+ * Bit-fields that holds the actions detected until now.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_ernno is set.
+ */
+int
+mlx5_flow_validate_action_drop(uint64_t action_flags,
+ struct rte_flow_error *error)
+{
+ if (action_flags & MLX5_FLOW_ACTION_FLAG)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't drop and flag in same flow");
+ if (action_flags & MLX5_FLOW_ACTION_MARK)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't drop and mark in same flow");
+ if (action_flags & MLX5_FLOW_FATE_ACTIONS)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't have 2 fate actions in"
+ " same flow");
+ return 0;
+}
+
+/*
+ * Validate the queue action.
+ *
+ * @param[in] action
+ * Pointer to the queue action.
+ * @param[in] action_flags
+ * Bit-fields that holds the actions detected until now.
+ * @param[in] dev
+ * Pointer to the Ethernet device structure.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_ernno is set.
+ */
+int
+mlx5_flow_validate_action_queue(const struct rte_flow_action *action,
+ uint64_t action_flags,
+ struct rte_eth_dev *dev,
+ struct rte_flow_error *error)
+{
+ struct priv *priv = dev->data->dev_private;
+ const struct rte_flow_action_queue *queue = action->conf;
+
+ if (action_flags & MLX5_FLOW_FATE_ACTIONS)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't have 2 fate actions in"
+ " same flow");
+ if (queue->index >= priv->rxqs_n)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ &queue->index,
+ "queue index out of range");
+ if (!(*priv->rxqs)[queue->index])
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ &queue->index,
+ "queue is not configured");
+ return 0;
+}
+
+/*
+ * Validate the rss action.
+ *
+ * @param[in] action
+ * Pointer to the queue action.
+ * @param[in] action_flags
+ * Bit-fields that holds the actions detected until now.
+ * @param[in] dev
+ * Pointer to the Ethernet device structure.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_ernno is set.
+ */
+int
+mlx5_flow_validate_action_rss(const struct rte_flow_action *action,
+ uint64_t action_flags,
+ struct rte_eth_dev *dev,
+ struct rte_flow_error *error)
+{
+ struct priv *priv = dev->data->dev_private;
+ const struct rte_flow_action_rss *rss = action->conf;
+ unsigned int i;
+
+ if (action_flags & MLX5_FLOW_FATE_ACTIONS)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "can't have 2 fate actions"
+ " in same flow");
+ if (rss->func != RTE_ETH_HASH_FUNCTION_DEFAULT &&
+ rss->func != RTE_ETH_HASH_FUNCTION_TOEPLITZ)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ &rss->func,
+ "RSS hash function not supported");
+#ifdef HAVE_IBV_DEVICE_TUNNEL_SUPPORT
+ if (rss->level > 2)
+#else
+ if (rss->level > 1)
+#endif
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ &rss->level,
+ "tunnel RSS is not supported");
+ if (rss->key_len < MLX5_RSS_HASH_KEY_LEN)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ &rss->key_len,
+ "RSS hash key too small");
+ if (rss->key_len > MLX5_RSS_HASH_KEY_LEN)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ &rss->key_len,
+ "RSS hash key too large");
+ if (rss->queue_num > priv->config.ind_table_max_size)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ &rss->queue_num,
+ "number of queues too large");
+ if (rss->types & MLX5_RSS_HF_MASK)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ &rss->types,
+ "some RSS protocols are not"
+ " supported");
+ for (i = 0; i != rss->queue_num; ++i) {
+ if (!(*priv->rxqs)[rss->queue[i]])
+ return rte_flow_error_set
+ (error, EINVAL, RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ &rss->queue[i], "queue is not configured");
+ }
+ return 0;
+}
+
+/*
+ * Validate the count action.
+ *
+ * @param[in] dev
+ * Pointer to the Ethernet device structure.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_ernno is set.
+ */
+int
+mlx5_flow_validate_action_count(struct rte_eth_dev *dev,
+ struct rte_flow_error *error)
+{
+ struct priv *priv = dev->data->dev_private;
+
+ if (!priv->config.flow_counter_en)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "flow counters are not supported.");
+ return 0;
+}
+
+/**
+ * Verify the @p attributes will be correctly understood by the NIC and store
+ * them in the @p flow if everything is correct.
+ *
+ * @param[in] dev
+ * Pointer to the Ethernet device structure.
+ * @param[in] attributes
+ * Pointer to flow attributes
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_flow_validate_attributes(struct rte_eth_dev *dev,
+ const struct rte_flow_attr *attributes,
+ struct rte_flow_error *error)
+{
+ struct priv *priv = dev->data->dev_private;
+ uint32_t priority_max = priv->config.flow_prio - 1;
+
+ if (attributes->group)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ATTR_GROUP,
+ NULL, "groups is not supported");
+ if (attributes->priority != MLX5_FLOW_PRIO_RSVD &&
+ attributes->priority >= priority_max)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ATTR_PRIORITY,
+ NULL, "priority out of range");
+ if (attributes->egress)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ATTR_EGRESS, NULL,
+ "egress is not supported");
+ if (attributes->transfer)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ATTR_TRANSFER,
+ NULL, "transfer is not supported");
+ if (!attributes->ingress)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ATTR_INGRESS,
+ NULL,
+ "ingress attribute is mandatory");
+ return 0;
+}
+
+/**
+ * Validate Ethernet item.
+ *
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit-fields that holds the items detected until now.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_flow_validate_item_eth(const struct rte_flow_item *item,
+ uint64_t item_flags,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_eth *mask = item->mask;
+ const struct rte_flow_item_eth nic_mask = {
+ .dst.addr_bytes = "\xff\xff\xff\xff\xff\xff",
+ .src.addr_bytes = "\xff\xff\xff\xff\xff\xff",
+ .type = RTE_BE16(0xffff),
+ };
+ int ret;
+ int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
+
+ if (item_flags & MLX5_FLOW_LAYER_OUTER_L2)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "3 levels of l2 are not supported");
+ if ((item_flags & MLX5_FLOW_LAYER_INNER_L2) && !tunnel)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "2 L2 without tunnel are not supported");
+ if (!mask)
+ mask = &rte_flow_item_eth_mask;
+ ret = mlx5_flow_item_acceptable(item, (const uint8_t *)mask,
+ (const uint8_t *)&nic_mask,
+ sizeof(struct rte_flow_item_eth),
+ error);
+ return ret;
+}
+
+/**
+ * Validate VLAN item.
+ *
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit-fields that holds the items detected until now.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_flow_validate_item_vlan(const struct rte_flow_item *item,
+ int64_t item_flags,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_vlan *spec = item->spec;
+ const struct rte_flow_item_vlan *mask = item->mask;
+ const struct rte_flow_item_vlan nic_mask = {
+ .tci = RTE_BE16(0x0fff),
+ .inner_type = RTE_BE16(0xffff),
+ };
+ uint16_t vlan_tag = 0;
+ const int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
+ int ret;
+ const uint32_t l34m = tunnel ? (MLX5_FLOW_LAYER_INNER_L3 |
+ MLX5_FLOW_LAYER_INNER_L4) :
+ (MLX5_FLOW_LAYER_OUTER_L3 |
+ MLX5_FLOW_LAYER_OUTER_L4);
+ const uint32_t vlanm = tunnel ? MLX5_FLOW_LAYER_INNER_VLAN :
+ MLX5_FLOW_LAYER_OUTER_VLAN;
+
+ if (item_flags & vlanm)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "VLAN layer already configured");
+ else if ((item_flags & l34m) != 0)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L2 layer cannot follow L3/L4 layer");
+ if (!mask)
+ mask = &rte_flow_item_vlan_mask;
+ ret = mlx5_flow_item_acceptable(item, (const uint8_t *)mask,
+ (const uint8_t *)&nic_mask,
+ sizeof(struct rte_flow_item_vlan),
+ error);
+ if (ret)
+ return ret;
+ if (spec) {
+ vlan_tag = spec->tci;
+ vlan_tag &= mask->tci;
+ }
+ /*
+ * From verbs perspective an empty VLAN is equivalent
+ * to a packet without VLAN layer.
+ */
+ if (!vlan_tag)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM_SPEC,
+ item->spec,
+ "VLAN cannot be empty");
+ return 0;
+}
+
+/**
+ * Validate IPV4 item.
+ *
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit-fields that holds the items detected until now.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_flow_validate_item_ipv4(const struct rte_flow_item *item,
+ int64_t item_flags,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_ipv4 *mask = item->mask;
+ const struct rte_flow_item_ipv4 nic_mask = {
+ .hdr = {
+ .src_addr = RTE_BE32(0xffffffff),
+ .dst_addr = RTE_BE32(0xffffffff),
+ .type_of_service = 0xff,
+ .next_proto_id = 0xff,
+ },
+ };
+ const int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
+ int ret;
+
+ if (item_flags & (tunnel ? MLX5_FLOW_LAYER_INNER_L3 :
+ MLX5_FLOW_LAYER_OUTER_L3))
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "multiple L3 layers not supported");
+ else if (item_flags & (tunnel ? MLX5_FLOW_LAYER_INNER_L4 :
+ MLX5_FLOW_LAYER_OUTER_L4))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L3 cannot follow an L4 layer.");
+ if (!mask)
+ mask = &rte_flow_item_ipv4_mask;
+ ret = mlx5_flow_item_acceptable(item, (const uint8_t *)mask,
+ (const uint8_t *)&nic_mask,
+ sizeof(struct rte_flow_item_ipv4),
+ error);
+ if (ret < 0)
+ return ret;
+ return 0;
+}
+
+/**
+ * Validate IPV6 item.
+ *
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit-fields that holds the items detected until now.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_flow_validate_item_ipv6(const struct rte_flow_item *item,
+ uint64_t item_flags,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_ipv6 *mask = item->mask;
+ const struct rte_flow_item_ipv6 nic_mask = {
+ .hdr = {
+ .src_addr =
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff",
+ .dst_addr =
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff",
+ .vtc_flow = RTE_BE32(0xffffffff),
+ .proto = 0xff,
+ .hop_limits = 0xff,
+ },
+ };
+ const int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
+ int ret;
+
+ if (item_flags & (tunnel ? MLX5_FLOW_LAYER_INNER_L3 :
+ MLX5_FLOW_LAYER_OUTER_L3))
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "multiple L3 layers not supported");
+ else if (item_flags & (tunnel ? MLX5_FLOW_LAYER_INNER_L4 :
+ MLX5_FLOW_LAYER_OUTER_L4))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L3 cannot follow an L4 layer.");
+ /*
+ * IPv6 is not recognised by the NIC inside a GRE tunnel.
+ * Such support has to be disabled as the rule will be
+ * accepted. Issue reproduced with Mellanox OFED 4.3-3.0.2.1 and
+ * Mellanox OFED 4.4-1.0.0.0.
+ */
+ if (tunnel && item_flags & MLX5_FLOW_LAYER_GRE)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "IPv6 inside a GRE tunnel is"
+ " not recognised.");
+ if (!mask)
+ mask = &rte_flow_item_ipv6_mask;
+ ret = mlx5_flow_item_acceptable(item, (const uint8_t *)mask,
+ (const uint8_t *)&nic_mask,
+ sizeof(struct rte_flow_item_ipv6),
+ error);
+ if (ret < 0)
+ return ret;
+ return 0;
+}
+
+/**
+ * Validate UDP item.
+ *
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit-fields that holds the items detected until now.
+ * @param[in] target_protocol
+ * The next protocol in the previous item.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_flow_validate_item_udp(const struct rte_flow_item *item,
+ uint64_t item_flags,
+ uint8_t target_protocol,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_udp *mask = item->mask;
+ const int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
+ int ret;
+
+ if (target_protocol != 0xff && target_protocol != IPPROTO_UDP)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "protocol filtering not compatible"
+ " with UDP layer");
+ if (!(item_flags & (tunnel ? MLX5_FLOW_LAYER_INNER_L3 :
+ MLX5_FLOW_LAYER_OUTER_L3)))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L3 is mandatory to filter on L4");
+ if (item_flags & (tunnel ? MLX5_FLOW_LAYER_INNER_L4 :
+ MLX5_FLOW_LAYER_OUTER_L4))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L4 layer is already present");
+ if (!mask)
+ mask = &rte_flow_item_udp_mask;
+ ret = mlx5_flow_item_acceptable
+ (item, (const uint8_t *)mask,
+ (const uint8_t *)&rte_flow_item_udp_mask,
+ sizeof(struct rte_flow_item_udp), error);
+ if (ret < 0)
+ return ret;
+ return 0;
}
/**
- * 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 TCP item.
*
* @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] item_flags
+ * Bit-fields that holds the items detected until now.
+ * @param[in] target_protocol
+ * The next protocol in the previous item.
* @param[out] error
* Pointer to error structure.
*
* @return
- * 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.
+ * 0 on success, a negative errno value otherwise 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, 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)
{
- const struct rte_flow_item_eth *spec = item->spec;
- const struct rte_flow_item_eth *mask = item->mask;
- const struct rte_flow_item_eth nic_mask = {
- .dst.addr_bytes = "\xff\xff\xff\xff\xff\xff",
- .src.addr_bytes = "\xff\xff\xff\xff\xff\xff",
- .type = RTE_BE16(0xffff),
- };
- const unsigned int size = sizeof(struct ibv_flow_spec_eth);
- struct ibv_flow_spec_eth eth = {
- .type = IBV_FLOW_SPEC_ETH,
- .size = size,
- };
+ const struct rte_flow_item_tcp *mask = item->mask;
+ const int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
int ret;
- if (flow->layers & MLX5_FLOW_LAYER_OUTER_L2)
- return rte_flow_error_set(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ITEM,
- item,
- "L2 layers already configured");
+ 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"
+ " with TCP layer");
+ if (!(item_flags & (tunnel ? MLX5_FLOW_LAYER_INNER_L3 :
+ MLX5_FLOW_LAYER_OUTER_L3)))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L3 is mandatory to filter on L4");
+ if (item_flags & (tunnel ? MLX5_FLOW_LAYER_INNER_L4 :
+ MLX5_FLOW_LAYER_OUTER_L4))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L4 layer is already present");
if (!mask)
- mask = &rte_flow_item_eth_mask;
- ret = mlx5_flow_item_acceptable(item, (const uint8_t *)mask,
- (const uint8_t *)&nic_mask,
- sizeof(struct rte_flow_item_eth),
- error);
- if (ret)
+ mask = &rte_flow_item_tcp_mask;
+ ret = mlx5_flow_item_acceptable
+ (item, (const uint8_t *)mask,
+ (const uint8_t *)&rte_flow_item_tcp_mask,
+ sizeof(struct rte_flow_item_tcp), error);
+ if (ret < 0)
return ret;
- flow->layers |= MLX5_FLOW_LAYER_OUTER_L2;
- if (size > flow_size)
- return size;
- 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;
- }
- mlx5_flow_spec_verbs_add(flow, ð, size);
- return size;
+ return 0;
}
/**
- * 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.
+ * Validate VXLAN item.
+ *
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit-fields that holds the items detected until now.
+ * @param[in] target_protocol
+ * The next protocol in the previous item.
* @param[out] error
* Pointer to error structure.
*
* @return
- * 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.
+ * 0 on success, a negative errno value otherwise 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
+mlx5_flow_validate_item_vxlan(const struct rte_flow_item *item,
+ uint64_t item_flags,
+ 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;
+ const struct rte_flow_item_vxlan *spec = item->spec;
+ const struct rte_flow_item_vxlan *mask = item->mask;
+ int ret;
+ union vni {
+ uint32_t vlan_id;
+ uint8_t vni[4];
+ } id = { .vlan_id = 0, };
+ uint32_t vlan_id = 0;
- switch (pattern->type) {
- case RTE_FLOW_ITEM_TYPE_VOID:
- break;
- case RTE_FLOW_ITEM_TYPE_ETH:
- ret = mlx5_flow_item_eth(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, error);
+ if (item_flags & MLX5_FLOW_LAYER_TUNNEL)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "a tunnel is already present");
+ /*
+ * Verify only UDPv4 is present as defined in
+ * https://tools.ietf.org/html/rfc7348
+ */
+ if (!(item_flags & MLX5_FLOW_LAYER_OUTER_L4_UDP))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "no outer UDP layer found");
+ if (!mask)
+ mask = &rte_flow_item_vxlan_mask;
+ ret = mlx5_flow_item_acceptable
+ (item, (const uint8_t *)mask,
+ (const uint8_t *)&rte_flow_item_vxlan_mask,
+ sizeof(struct rte_flow_item_vxlan),
+ error);
+ if (ret < 0)
+ return ret;
+ if (spec) {
+ memcpy(&id.vni[1], spec->vni, 3);
+ vlan_id = id.vlan_id;
+ memcpy(&id.vni[1], mask->vni, 3);
+ vlan_id &= id.vlan_id;
}
- return size;
+ /*
+ * Tunnel id 0 is equivalent as not adding a VXLAN layer, if
+ * only this layer is defined in the Verbs specification it is
+ * interpreted as wildcard and all packets will match this
+ * rule, if it follows a full stack layer (ex: eth / ipv4 /
+ * udp), all packets matching the layers before will also
+ * match this rule. To avoid such situation, VNI 0 is
+ * currently refused.
+ */
+ if (!vlan_id)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "VXLAN vni cannot be 0");
+ if (!(item_flags & MLX5_FLOW_LAYER_OUTER))
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "VXLAN tunnel must be fully defined");
+ return 0;
}
/**
- * 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.
+ * Validate VXLAN_GPE item.
*
- * @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.
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit-fields that holds the items detected until now.
+ * @param[in] priv
+ * Pointer to the private data structure.
+ * @param[in] target_protocol
+ * The next protocol in the previous item.
* @param[out] error
* Pointer to error structure.
*
* @return
- * 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.
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
*/
-static int
-mlx5_flow_action_drop(const struct rte_flow_action *action,
- struct rte_flow *flow, const size_t flow_size,
- 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)
{
- 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,
- };
+ struct priv *priv = dev->data->dev_private;
+ const struct rte_flow_item_vxlan_gpe *spec = item->spec;
+ const struct rte_flow_item_vxlan_gpe *mask = item->mask;
+ int ret;
+ union vni {
+ uint32_t vlan_id;
+ uint8_t vni[4];
+ } id = { .vlan_id = 0, };
+ uint32_t vlan_id = 0;
- if (flow->fate)
+ if (!priv->config.l3_vxlan_en)
return rte_flow_error_set(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ACTION,
- action,
- "multiple fate actions are not"
- " supported");
- if (size < flow_size)
- mlx5_flow_spec_verbs_add(flow, &drop, size);
- flow->fate |= MLX5_FLOW_FATE_DROP;
- return size;
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L3 VXLAN is not enabled by device"
+ " parameter and/or not configured in"
+ " firmware");
+ if (item_flags & MLX5_FLOW_LAYER_TUNNEL)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "a tunnel is already present");
+ /*
+ * Verify only UDPv4 is present as defined in
+ * https://tools.ietf.org/html/rfc7348
+ */
+ if (!(item_flags & MLX5_FLOW_LAYER_OUTER_L4_UDP))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "no outer UDP layer found");
+ if (!mask)
+ mask = &rte_flow_item_vxlan_gpe_mask;
+ ret = mlx5_flow_item_acceptable
+ (item, (const uint8_t *)mask,
+ (const uint8_t *)&rte_flow_item_vxlan_gpe_mask,
+ sizeof(struct rte_flow_item_vxlan_gpe),
+ error);
+ if (ret < 0)
+ return ret;
+ if (spec) {
+ if (spec->protocol)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM,
+ item,
+ "VxLAN-GPE protocol"
+ " not supported");
+ memcpy(&id.vni[1], spec->vni, 3);
+ vlan_id = id.vlan_id;
+ memcpy(&id.vni[1], mask->vni, 3);
+ vlan_id &= id.vlan_id;
+ }
+ /*
+ * Tunnel id 0 is equivalent as not adding a VXLAN layer, if only this
+ * layer is defined in the Verbs specification it is interpreted as
+ * wildcard and all packets will match this rule, if it follows a full
+ * stack layer (ex: eth / ipv4 / udp), all packets matching the layers
+ * before will also match this rule. To avoid such situation, VNI 0
+ * is currently refused.
+ */
+ if (!vlan_id)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "VXLAN-GPE vni cannot be 0");
+ if (!(item_flags & MLX5_FLOW_LAYER_OUTER))
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "VXLAN-GPE tunnel must be fully"
+ " defined");
+ return 0;
}
/**
- * 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.
+ * Validate GRE item.
*
- * @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[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit flags to mark detected items.
+ * @param[in] target_protocol
+ * The next protocol in the previous item.
* @param[out] error
* Pointer to error structure.
*
* @return
- * 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.
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
*/
-static int
-mlx5_flow_actions(struct rte_eth_dev *dev __rte_unused,
- const struct rte_flow_action actions[],
- struct rte_flow *flow, const size_t flow_size,
- 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)
{
- size_t size = 0;
- int remain = flow_size;
- int ret = 0;
+ const struct rte_flow_item_gre *spec __rte_unused = item->spec;
+ const struct rte_flow_item_gre *mask = item->mask;
+ int ret;
- for (; actions->type != RTE_FLOW_ACTION_TYPE_END; actions++) {
- switch (actions->type) {
- case RTE_FLOW_ACTION_TYPE_VOID:
- break;
- case RTE_FLOW_ACTION_TYPE_DROP:
- ret = mlx5_flow_action_drop(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)
+ 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"
+ " with this GRE layer");
+ if (item_flags & MLX5_FLOW_LAYER_TUNNEL)
return rte_flow_error_set(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
- NULL,
- "no fate action found");
- return size;
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "a tunnel is already present");
+ if (!(item_flags & MLX5_FLOW_LAYER_OUTER_L3))
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L3 Layer is missing");
+ if (!mask)
+ mask = &rte_flow_item_gre_mask;
+ ret = mlx5_flow_item_acceptable
+ (item, (const uint8_t *)mask,
+ (const uint8_t *)&rte_flow_item_gre_mask,
+ sizeof(struct rte_flow_item_gre), error);
+ if (ret < 0)
+ return ret;
+#ifndef HAVE_IBV_DEVICE_MPLS_SUPPORT
+ if (spec && (spec->protocol & mask->protocol))
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "without MPLS support the"
+ " specification cannot be used for"
+ " filtering");
+#endif
+ return 0;
}
/**
- * 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.
+ * Validate MPLS item.
*
- * @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[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit-fields that holds the items detected until now.
+ * @param[in] target_protocol
+ * The next protocol in the previous item.
* @param[out] error
- * Perform verbose error reporting if not NULL.
+ * 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 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.
+ * 0 on success, a negative errno value otherwise 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)
+int
+mlx5_flow_validate_item_mpls(const struct rte_flow_item *item __rte_unused,
+ uint64_t item_flags __rte_unused,
+ uint8_t target_protocol __rte_unused,
+ struct rte_flow_error *error)
{
- struct rte_flow local_flow = { .layers = 0, };
- size_t size = sizeof(*flow) + sizeof(struct ibv_flow_attr);
- int remain = (flow_size > size) ? flow_size - size : 0;
+#ifdef HAVE_IBV_DEVICE_MPLS_SUPPORT
+ const struct rte_flow_item_mpls *mask = item->mask;
int ret;
- if (!remain)
- flow = &local_flow;
- ret = mlx5_flow_attributes(dev, attributes, flow, error);
- if (ret < 0)
- return ret;
- ret = mlx5_flow_items(pattern, flow, remain, error);
- if (ret < 0)
- return ret;
- size += ret;
- remain = (flow_size > size) ? flow_size - size : 0;
- ret = mlx5_flow_actions(dev, actions, flow, remain, error);
+ 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"
+ " with MPLS layer");
+ if (item_flags & MLX5_FLOW_LAYER_TUNNEL)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "a tunnel is already"
+ " present");
+ if (!mask)
+ mask = &rte_flow_item_mpls_mask;
+ ret = mlx5_flow_item_acceptable
+ (item, (const uint8_t *)mask,
+ (const uint8_t *)&rte_flow_item_mpls_mask,
+ sizeof(struct rte_flow_item_mpls), error);
if (ret < 0)
return ret;
- size += ret;
- if (size <= flow_size)
- flow->verbs.attr->priority = flow->attributes.priority;
- return size;
+ return 0;
+#endif
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "MPLS is not supported by Verbs, please"
+ " update.");
}
/**
const struct rte_flow_action actions[],
struct rte_flow_error *error)
{
- int ret = mlx5_flow_merge(dev, NULL, 0, attr, items, actions, error);
+ int ret;
+ ret = nic_ops.validate(dev, attr, items, actions, error);
if (ret < 0)
return ret;
return 0;
}
/**
- * Remove the flow.
+ * Get RSS action from the action list.
*
- * @param[in] dev
- * Pointer to Ethernet device.
- * @param[in, out] flow
- * Pointer to flow structure.
+ * @param[in] actions
+ * Pointer to the list of actions.
+ *
+ * @return
+ * Pointer to the RSS action if exist, else return NULL.
*/
-static void
-mlx5_flow_remove(struct rte_eth_dev *dev, struct rte_flow *flow)
+static const struct rte_flow_action_rss*
+mlx5_flow_get_rss_action(const struct rte_flow_action actions[])
{
- if (flow->fate & MLX5_FLOW_FATE_DROP) {
- if (flow->verbs.flow) {
- claim_zero(mlx5_glue->destroy_flow(flow->verbs.flow));
- flow->verbs.flow = NULL;
+ for (; actions->type != RTE_FLOW_ACTION_TYPE_END; actions++) {
+ switch (actions->type) {
+ case RTE_FLOW_ACTION_TYPE_RSS:
+ return (const struct rte_flow_action_rss *)
+ actions->conf;
+ default:
+ break;
}
}
- if (flow->verbs.hrxq) {
- mlx5_hrxq_drop_release(dev);
- flow->verbs.hrxq = NULL;
- }
+ return NULL;
}
-/**
- * Apply the flow.
- *
- * @param[in] dev
- * Pointer to 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)
{
- flow->verbs.hrxq = mlx5_hrxq_drop_new(dev);
- if (!flow->verbs.hrxq)
- return rte_flow_error_set
- (error, errno,
- RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
- NULL,
- "cannot allocate Drop queue");
- flow->verbs.flow =
- mlx5_glue->create_flow(flow->verbs.hrxq->qp, flow->verbs.attr);
- if (!flow->verbs.flow) {
- mlx5_hrxq_drop_release(dev);
- flow->verbs.hrxq = NULL;
- return rte_flow_error_set(error, errno,
- RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
- NULL,
- "kernel module refuses to create"
- " flow");
+ 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;
+ }
}
- return 0;
+ 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;
}
/**
const struct rte_flow_action actions[],
struct rte_flow_error *error)
{
- struct rte_flow *flow;
- size_t size;
+ struct rte_flow *flow = NULL;
+ struct mlx5_flow *dev_flow;
+ uint64_t action_flags = 0;
+ uint64_t item_flags = 0;
+ const struct rte_flow_action_rss *rss;
+ union {
+ struct rte_flow_expand_rss buf;
+ uint8_t buffer[2048];
+ } expand_buffer;
+ struct rte_flow_expand_rss *buf = &expand_buffer.buf;
int ret;
+ uint32_t i;
+ uint32_t flow_size;
- ret = mlx5_flow_merge(dev, NULL, 0, attr, items, actions, error);
+ ret = mlx5_flow_validate(dev, attr, items, actions, error);
if (ret < 0)
return NULL;
- size = ret;
- flow = rte_zmalloc(__func__, size, 0);
- if (!flow) {
- rte_flow_error_set(error, ENOMEM,
- RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
- NULL,
- "cannot allocate memory");
- return NULL;
+ 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;
+
+ graph_root = mlx5_find_graph_root(items, rss->level);
+ ret = rte_flow_expand_rss(buf, sizeof(expand_buffer.buffer),
+ items, 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)items;
+ }
+ for (i = 0; i < buf->entries; ++i) {
+ 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;
}
- flow->verbs.attr = (struct ibv_flow_attr *)(flow + 1);
- flow->verbs.specs = (uint8_t *)(flow->verbs.attr + 1);
- ret = mlx5_flow_merge(dev, flow, size, attr, items, actions, error);
- if (ret < 0)
- goto error;
- assert((size_t)ret == size);
if (dev->data->dev_started) {
- ret = mlx5_flow_apply(dev, flow, error);
+ 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. */
- mlx5_flow_remove(dev, flow);
+ assert(flow);
+ nic_ops.destroy(dev, flow);
rte_free(flow);
rte_errno = ret; /* Restore rte_errno. */
return NULL;
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
+ * already clean.
+ */
+ if (dev->data->dev_started)
+ mlx5_flow_rxq_flags_trim(dev, flow);
rte_free(flow);
}
* Pointer to a TAILQ flow list.
*/
void
-mlx5_flow_stop(struct rte_eth_dev *dev __rte_unused,
- struct mlx5_flows *list __rte_unused)
+mlx5_flow_stop(struct rte_eth_dev *dev, struct mlx5_flows *list)
{
+ struct rte_flow *flow;
+
+ TAILQ_FOREACH_REVERSE(flow, list, mlx5_flows, next)
+ nic_ops.remove(dev, flow);
+ mlx5_flow_rxq_flags_clear(dev);
}
/**
* 0 on success, a negative errno value otherwise and rte_errno is set.
*/
int
-mlx5_flow_start(struct rte_eth_dev *dev __rte_unused,
- struct mlx5_flows *list __rte_unused)
+mlx5_flow_start(struct rte_eth_dev *dev, struct mlx5_flows *list)
{
+ struct rte_flow *flow;
+ struct rte_flow_error error;
+ int ret = 0;
+
+ TAILQ_FOREACH(flow, list, next) {
+ ret = nic_ops.apply(dev, flow, &error);
+ if (ret < 0)
+ goto error;
+ mlx5_flow_rxq_flags_set(dev, flow);
+ }
return 0;
+error:
+ ret = rte_errno; /* Save rte_errno before cleanup. */
+ mlx5_flow_stop(dev, list);
+ rte_errno = ret; /* Restore rte_errno. */
+ return -rte_errno;
}
/**
struct priv *priv = dev->data->dev_private;
const struct rte_flow_attr attr = {
.ingress = 1,
- .priority = priv->config.flow_prio - 1,
+ .priority = MLX5_FLOW_PRIO_RSVD,
};
struct rte_flow_item items[] = {
{
},
{
.type = (vlan_spec) ? RTE_FLOW_ITEM_TYPE_VLAN :
- RTE_FLOW_ITEM_TYPE_END,
+ RTE_FLOW_ITEM_TYPE_END,
.spec = vlan_spec,
.last = NULL,
.mask = vlan_mask,
return 0;
}
+/**
+ * Query flow counter.
+ *
+ * @param flow
+ * Pointer to the flow.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_flow_query_count(struct rte_flow *flow __rte_unused,
+ void *data __rte_unused,
+ struct rte_flow_error *error)
+{
+#ifdef HAVE_IBV_DEVICE_COUNTERS_SET_SUPPORT
+ 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 = {
+ .cs = flow->counter->cs,
+ .query_flags = IBV_COUNTER_SET_FORCE_UPDATE,
+ };
+ struct ibv_counter_set_data query_out = {
+ .out = counters,
+ .outlen = 2 * sizeof(uint64_t),
+ };
+ int err = mlx5_glue->query_counter_set(&query_cs_attr,
+ &query_out);
+
+ if (err)
+ return rte_flow_error_set
+ (error, err,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL,
+ "cannot read counter");
+ qc->hits_set = 1;
+ qc->bytes_set = 1;
+ qc->hits = counters[0] - flow->counter->hits;
+ qc->bytes = counters[1] - flow->counter->bytes;
+ if (qc->reset) {
+ flow->counter->hits = counters[0];
+ flow->counter->bytes = counters[1];
+ }
+ return 0;
+ }
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL,
+ "flow does not have counter");
+#endif
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL,
+ "counters are not available");
+}
+
+/**
+ * Query a flows.
+ *
+ * @see rte_flow_query()
+ * @see rte_flow_ops
+ */
+int
+mlx5_flow_query(struct rte_eth_dev *dev __rte_unused,
+ struct rte_flow *flow,
+ const struct rte_flow_action *actions,
+ void *data,
+ struct rte_flow_error *error)
+{
+ 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_COUNT:
+ ret = mlx5_flow_query_count(flow, data, error);
+ break;
+ default:
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ actions,
+ "action not supported");
+ }
+ if (ret < 0)
+ return ret;
+ }
+ return 0;
+}
+
/**
* Convert a flow director filter to a generic flow.
*
.dst_addr = input->flow.ip4_flow.dst_ip,
.time_to_live = input->flow.ip4_flow.ttl,
.type_of_service = input->flow.ip4_flow.tos,
- .next_proto_id = input->flow.ip4_flow.proto,
};
attributes->l3_mask.ipv4.hdr = (struct ipv4_hdr){
.src_addr = mask->ipv4_mask.src_ip,
}
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)
+{
+ struct priv *priv __rte_unused = dev->data->dev_private;
+
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+ if (priv->config.dv_flow_en)
+ mlx5_flow_dv_get_driver_ops(&nic_ops);
+ else
+ mlx5_flow_verbs_get_driver_ops(&nic_ops);
+#else
+ mlx5_flow_verbs_get_driver_ops(&nic_ops);
+#endif
+}