-/*-
- * BSD LICENSE
- *
- * Copyright 2016 6WIND S.A.
- * Copyright 2016 Mellanox.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of 6WIND S.A. nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2016 6WIND S.A.
+ * Copyright 2016 Mellanox Technologies, Ltd
*/
+#include <netinet/in.h>
#include <sys/queue.h>
+#include <stdalign.h>
+#include <stdint.h>
#include <string.h>
/* Verbs header. */
#pragma GCC diagnostic error "-Wpedantic"
#endif
-#include <rte_ethdev.h>
+#include <rte_common.h>
+#include <rte_ether.h>
+#include <rte_ethdev_driver.h>
#include <rte_flow.h>
#include <rte_flow_driver.h>
#include <rte_malloc.h>
+#include <rte_ip.h>
#include "mlx5.h"
+#include "mlx5_defs.h"
+#include "mlx5_flow.h"
+#include "mlx5_glue.h"
#include "mlx5_prm.h"
+#include "mlx5_rxtx.h"
-static int
-mlx5_flow_create_eth(const struct rte_flow_item *item,
- const void *default_mask,
- void *data);
+/* 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;
-static int
-mlx5_flow_create_vlan(const struct rte_flow_item *item,
- const void *default_mask,
- void *data);
+/** Device flow drivers. */
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+extern const struct mlx5_flow_driver_ops mlx5_flow_dv_drv_ops;
+#endif
+extern const struct mlx5_flow_driver_ops mlx5_flow_verbs_drv_ops;
-static int
-mlx5_flow_create_ipv4(const struct rte_flow_item *item,
- const void *default_mask,
- void *data);
+const struct mlx5_flow_driver_ops mlx5_flow_null_drv_ops;
-static int
-mlx5_flow_create_ipv6(const struct rte_flow_item *item,
- const void *default_mask,
- void *data);
+const struct mlx5_flow_driver_ops *flow_drv_ops[] = {
+ [MLX5_FLOW_TYPE_MIN] = &mlx5_flow_null_drv_ops,
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+ [MLX5_FLOW_TYPE_DV] = &mlx5_flow_dv_drv_ops,
+#endif
+ [MLX5_FLOW_TYPE_VERBS] = &mlx5_flow_verbs_drv_ops,
+ [MLX5_FLOW_TYPE_MAX] = &mlx5_flow_null_drv_ops
+};
-static int
-mlx5_flow_create_udp(const struct rte_flow_item *item,
- const void *default_mask,
- void *data);
+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,
+};
-static int
-mlx5_flow_create_tcp(const struct rte_flow_item *item,
- const void *default_mask,
- void *data);
+/** 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 int
-mlx5_flow_create_vxlan(const struct rte_flow_item *item,
- const void *default_mask,
- void *data);
-
-struct rte_flow {
- LIST_ENTRY(rte_flow) next; /**< Pointer to the next flow structure. */
- struct ibv_exp_flow_attr *ibv_attr; /**< Pointer to Verbs attributes. */
- struct ibv_exp_rwq_ind_table *ind_table; /**< Indirection table. */
- struct ibv_qp *qp; /**< Verbs queue pair. */
- struct ibv_exp_flow *ibv_flow; /**< Verbs flow. */
- struct ibv_exp_wq *wq; /**< Verbs work queue. */
- struct ibv_cq *cq; /**< Verbs completion queue. */
- struct rxq *rxq; /**< Pointer to the queue, NULL if drop queue. */
- uint32_t mark:1; /**< Set if the flow is marked. */
+static const struct rte_flow_ops mlx5_flow_ops = {
+ .validate = mlx5_flow_validate,
+ .create = mlx5_flow_create,
+ .destroy = mlx5_flow_destroy,
+ .flush = mlx5_flow_flush,
+ .isolate = mlx5_flow_isolate,
+ .query = mlx5_flow_query,
};
-/** Static initializer for items. */
-#define ITEMS(...) \
- (const enum rte_flow_item_type []){ \
- __VA_ARGS__, RTE_FLOW_ITEM_TYPE_END, \
- }
+/* Convert FDIR request to Generic flow. */
+struct mlx5_fdir {
+ struct rte_flow_attr attr;
+ struct rte_flow_item items[4];
+ struct rte_flow_item_eth l2;
+ struct rte_flow_item_eth l2_mask;
+ union {
+ struct rte_flow_item_ipv4 ipv4;
+ struct rte_flow_item_ipv6 ipv6;
+ } l3;
+ union {
+ struct rte_flow_item_ipv4 ipv4;
+ struct rte_flow_item_ipv6 ipv6;
+ } l3_mask;
+ union {
+ struct rte_flow_item_udp udp;
+ struct rte_flow_item_tcp tcp;
+ } l4;
+ union {
+ struct rte_flow_item_udp udp;
+ struct rte_flow_item_tcp tcp;
+ } l4_mask;
+ struct rte_flow_action actions[2];
+ struct rte_flow_action_queue queue;
+};
-/** Structure to generate a simple graph of layers supported by the NIC. */
-struct mlx5_flow_items {
- /** List of possible actions for these items. */
- const enum rte_flow_action_type *const actions;
- /** Bit-masks corresponding to the possibilities for the item. */
- const void *mask;
- /**
- * Default bit-masks to use when item->mask is not provided. When
- * \default_mask is also NULL, the full supported bit-mask (\mask) is
- * used instead.
- */
- const void *default_mask;
- /** Bit-masks size in bytes. */
- const unsigned int mask_sz;
- /**
- * Conversion function from rte_flow to NIC specific flow.
- *
- * @param item
- * rte_flow item to convert.
- * @param default_mask
- * Default bit-masks to use when item->mask is not provided.
- * @param data
- * Internal structure to store the conversion.
- *
- * @return
- * 0 on success, negative value otherwise.
- */
- int (*convert)(const struct rte_flow_item *item,
- const void *default_mask,
- void *data);
- /** Size in bytes of the destination structure. */
- const unsigned int dst_sz;
- /** List of possible following items. */
- const enum rte_flow_item_type *const items;
+/* 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 },
};
-/** Valid action for this PMD. */
-static const enum rte_flow_action_type valid_actions[] = {
- RTE_FLOW_ACTION_TYPE_DROP,
- RTE_FLOW_ACTION_TYPE_QUEUE,
- RTE_FLOW_ACTION_TYPE_MARK,
- RTE_FLOW_ACTION_TYPE_FLAG,
- RTE_FLOW_ACTION_TYPE_END,
+/* 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 },
};
-/** Graph of supported items and associated actions. */
-static const struct mlx5_flow_items mlx5_flow_items[] = {
- [RTE_FLOW_ITEM_TYPE_END] = {
- .items = ITEMS(RTE_FLOW_ITEM_TYPE_ETH,
- RTE_FLOW_ITEM_TYPE_VXLAN),
- },
- [RTE_FLOW_ITEM_TYPE_ETH] = {
- .items = ITEMS(RTE_FLOW_ITEM_TYPE_VLAN,
- RTE_FLOW_ITEM_TYPE_IPV4,
- RTE_FLOW_ITEM_TYPE_IPV6),
- .actions = valid_actions,
- .mask = &(const struct rte_flow_item_eth){
- .dst.addr_bytes = "\xff\xff\xff\xff\xff\xff",
- .src.addr_bytes = "\xff\xff\xff\xff\xff\xff",
- .type = -1,
- },
- .default_mask = &rte_flow_item_eth_mask,
- .mask_sz = sizeof(struct rte_flow_item_eth),
- .convert = mlx5_flow_create_eth,
- .dst_sz = sizeof(struct ibv_exp_flow_spec_eth),
- },
- [RTE_FLOW_ITEM_TYPE_VLAN] = {
- .items = ITEMS(RTE_FLOW_ITEM_TYPE_IPV4,
- RTE_FLOW_ITEM_TYPE_IPV6),
- .actions = valid_actions,
- .mask = &(const struct rte_flow_item_vlan){
- .tci = -1,
- },
- .default_mask = &rte_flow_item_vlan_mask,
- .mask_sz = sizeof(struct rte_flow_item_vlan),
- .convert = mlx5_flow_create_vlan,
- .dst_sz = 0,
+/* Tunnel information. */
+struct mlx5_flow_tunnel_info {
+ uint64_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,
},
- [RTE_FLOW_ITEM_TYPE_IPV4] = {
- .items = ITEMS(RTE_FLOW_ITEM_TYPE_UDP,
- RTE_FLOW_ITEM_TYPE_TCP),
- .actions = valid_actions,
- .mask = &(const struct rte_flow_item_ipv4){
- .hdr = {
- .src_addr = -1,
- .dst_addr = -1,
- .type_of_service = -1,
- .next_proto_id = -1,
- },
- },
- .default_mask = &rte_flow_item_ipv4_mask,
- .mask_sz = sizeof(struct rte_flow_item_ipv4),
- .convert = mlx5_flow_create_ipv4,
- .dst_sz = sizeof(struct ibv_exp_flow_spec_ipv4_ext),
+ {
+ .tunnel = MLX5_FLOW_LAYER_VXLAN_GPE,
+ .ptype = RTE_PTYPE_TUNNEL_VXLAN_GPE | RTE_PTYPE_L4_UDP,
},
- [RTE_FLOW_ITEM_TYPE_IPV6] = {
- .items = ITEMS(RTE_FLOW_ITEM_TYPE_UDP,
- RTE_FLOW_ITEM_TYPE_TCP),
- .actions = valid_actions,
- .mask = &(const struct rte_flow_item_ipv6){
- .hdr = {
- .src_addr = {
- 0xff, 0xff, 0xff, 0xff,
- 0xff, 0xff, 0xff, 0xff,
- 0xff, 0xff, 0xff, 0xff,
- 0xff, 0xff, 0xff, 0xff,
- },
- .dst_addr = {
- 0xff, 0xff, 0xff, 0xff,
- 0xff, 0xff, 0xff, 0xff,
- 0xff, 0xff, 0xff, 0xff,
- 0xff, 0xff, 0xff, 0xff,
- },
- .vtc_flow = -1,
- .proto = -1,
- .hop_limits = -1,
- },
- },
- .default_mask = &rte_flow_item_ipv6_mask,
- .mask_sz = sizeof(struct rte_flow_item_ipv6),
- .convert = mlx5_flow_create_ipv6,
- .dst_sz = sizeof(struct ibv_exp_flow_spec_ipv6_ext),
+ {
+ .tunnel = MLX5_FLOW_LAYER_GRE,
+ .ptype = RTE_PTYPE_TUNNEL_GRE,
},
- [RTE_FLOW_ITEM_TYPE_UDP] = {
- .items = ITEMS(RTE_FLOW_ITEM_TYPE_VXLAN),
- .actions = valid_actions,
- .mask = &(const struct rte_flow_item_udp){
- .hdr = {
- .src_port = -1,
- .dst_port = -1,
- },
- },
- .default_mask = &rte_flow_item_udp_mask,
- .mask_sz = sizeof(struct rte_flow_item_udp),
- .convert = mlx5_flow_create_udp,
- .dst_sz = sizeof(struct ibv_exp_flow_spec_tcp_udp),
+ {
+ .tunnel = MLX5_FLOW_LAYER_MPLS | MLX5_FLOW_LAYER_OUTER_L4_UDP,
+ .ptype = RTE_PTYPE_TUNNEL_MPLS_IN_UDP | RTE_PTYPE_L4_UDP,
},
- [RTE_FLOW_ITEM_TYPE_TCP] = {
- .actions = valid_actions,
- .mask = &(const struct rte_flow_item_tcp){
- .hdr = {
- .src_port = -1,
- .dst_port = -1,
- },
- },
- .default_mask = &rte_flow_item_tcp_mask,
- .mask_sz = sizeof(struct rte_flow_item_tcp),
- .convert = mlx5_flow_create_tcp,
- .dst_sz = sizeof(struct ibv_exp_flow_spec_tcp_udp),
+ {
+ .tunnel = MLX5_FLOW_LAYER_MPLS,
+ .ptype = RTE_PTYPE_TUNNEL_MPLS_IN_GRE,
},
- [RTE_FLOW_ITEM_TYPE_VXLAN] = {
- .items = ITEMS(RTE_FLOW_ITEM_TYPE_ETH),
- .actions = valid_actions,
- .mask = &(const struct rte_flow_item_vxlan){
- .vni = "\xff\xff\xff",
- },
- .default_mask = &rte_flow_item_vxlan_mask,
- .mask_sz = sizeof(struct rte_flow_item_vxlan),
- .convert = mlx5_flow_create_vxlan,
- .dst_sz = sizeof(struct ibv_exp_flow_spec_tunnel),
+ {
+ .tunnel = MLX5_FLOW_LAYER_NVGRE,
+ .ptype = RTE_PTYPE_TUNNEL_NVGRE,
},
};
-/** Structure to pass to the conversion function. */
-struct mlx5_flow {
- struct ibv_exp_flow_attr *ibv_attr; /**< Verbs attribute. */
- unsigned int offset; /**< Offset in bytes in the ibv_attr buffer. */
- uint32_t inner; /**< Set once VXLAN is encountered. */
-};
+/**
+ * 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_priv *priv = dev->data->dev_private;
+ struct {
+ struct ibv_flow_attr attr;
+ struct ibv_flow_spec_eth eth;
+ struct ibv_flow_spec_action_drop drop;
+ } flow_attr = {
+ .attr = {
+ .num_of_specs = 2,
+ .port = (uint8_t)priv->ibv_port,
+ },
+ .eth = {
+ .type = IBV_FLOW_SPEC_ETH,
+ .size = sizeof(struct ibv_flow_spec_eth),
+ },
+ .drop = {
+ .size = sizeof(struct ibv_flow_spec_action_drop),
+ .type = IBV_FLOW_SPEC_ACTION_DROP,
+ },
+ };
+ struct ibv_flow *flow;
+ struct mlx5_hrxq *drop = mlx5_hrxq_drop_new(dev);
+ uint16_t vprio[] = { 8, 16 };
+ int i;
+ int priority = 0;
+
+ if (!drop) {
+ rte_errno = ENOTSUP;
+ return -rte_errno;
+ }
+ for (i = 0; i != RTE_DIM(vprio); i++) {
+ flow_attr.attr.priority = vprio[i] - 1;
+ flow = mlx5_glue->create_flow(drop->qp, &flow_attr.attr);
+ if (!flow)
+ break;
+ claim_zero(mlx5_glue->destroy_flow(flow));
+ priority = vprio[i];
+ }
+ mlx5_hrxq_drop_release(dev);
+ 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, priority);
+ return -rte_errno;
+ }
+ DRV_LOG(INFO, "port %u flow maximum priority: %d",
+ dev->data->port_id, priority);
+ return priority;
+}
-struct mlx5_flow_action {
- uint32_t queue:1; /**< Target is a receive queue. */
- uint32_t drop:1; /**< Target is a drop queue. */
- uint32_t mark:1; /**< Mark is present in the flow. */
- uint32_t queue_id; /**< Identifier of the queue. */
- uint32_t mark_id; /**< Mark identifier. */
-};
+/**
+ * Adjust flow priority based on the highest layer and the request priority.
+ *
+ * @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.
+ */
+uint32_t mlx5_flow_adjust_priority(struct rte_eth_dev *dev, int32_t priority,
+ uint32_t subpriority)
+{
+ uint32_t res = 0;
+ struct mlx5_priv *priv = dev->data->dev_private;
+
+ 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;
+}
/**
- * Check support for a given item.
+ * Verify the @p item specifications (spec, last, mask) are compatible with the
+ * NIC capabilities.
*
- * @param item[in]
+ * @param[in] item
* Item specification.
- * @param mask[in]
- * Bit-masks covering supported fields to compare with spec, last and mask in
- * \item.
- * @param size
- * Bit-Mask size in bytes.
+ * @param[in] mask
+ * @p item->mask or flow default bit-masks.
+ * @param[in] nic_mask
+ * Bit-masks covering supported fields by the NIC to compare with user mask.
+ * @param[in] size
+ * Bit-masks size in bytes.
+ * @param[out] error
+ * Pointer to error structure.
*
* @return
- * 0 on success.
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
*/
-static int
-mlx5_flow_item_validate(const struct rte_flow_item *item,
- const uint8_t *mask, unsigned int size)
+int
+mlx5_flow_item_acceptable(const struct rte_flow_item *item,
+ const uint8_t *mask,
+ const uint8_t *nic_mask,
+ unsigned int size,
+ struct rte_flow_error *error)
{
- int ret = 0;
+ unsigned int i;
+ assert(nic_mask);
+ for (i = 0; i < size; ++i)
+ if ((nic_mask[i] | mask[i]) != nic_mask[i])
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM,
+ item,
+ "mask enables non supported"
+ " bits");
if (!item->spec && (item->mask || item->last))
- return -1;
- if (item->spec && !item->mask) {
- unsigned int i;
- const uint8_t *spec = item->spec;
-
- for (i = 0; i < size; ++i)
- if ((spec[i] | mask[i]) != mask[i])
- return -1;
- }
- if (item->last && !item->mask) {
- unsigned int i;
- const uint8_t *spec = item->last;
-
- for (i = 0; i < size; ++i)
- if ((spec[i] | mask[i]) != mask[i])
- return -1;
- }
- if (item->mask) {
- unsigned int i;
- const uint8_t *spec = item->mask;
-
- for (i = 0; i < size; ++i)
- if ((spec[i] | mask[i]) != mask[i])
- return -1;
- }
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "mask/last without a spec is not"
+ " supported");
if (item->spec && item->last) {
uint8_t spec[size];
uint8_t last[size];
- const uint8_t *apply = mask;
unsigned int i;
+ int ret;
- if (item->mask)
- apply = item->mask;
for (i = 0; i < size; ++i) {
- spec[i] = ((const uint8_t *)item->spec)[i] & apply[i];
- last[i] = ((const uint8_t *)item->last)[i] & apply[i];
+ spec[i] = ((const uint8_t *)item->spec)[i] & mask[i];
+ last[i] = ((const uint8_t *)item->last)[i] & mask[i];
}
ret = memcmp(spec, last, size);
+ if (ret != 0)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM,
+ item,
+ "range is not valid");
}
- return ret;
+ return 0;
}
/**
- * Validate a flow supported by the NIC.
+ * Adjust the hash fields according to the @p flow information.
*
- * @param priv
- * Pointer to private structure.
- * @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.
- * @param[in, out] flow
- * Flow structure to update.
+ * @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
- * 0 on success, a negative errno value otherwise and rte_errno is set.
+ * The hash fields that should be used.
*/
-static int
-priv_flow_validate(struct priv *priv,
- const struct rte_flow_attr *attr,
- const struct rte_flow_item items[],
- const struct rte_flow_action actions[],
- struct rte_flow_error *error,
- struct mlx5_flow *flow)
-{
- const struct mlx5_flow_items *cur_item = mlx5_flow_items;
- struct mlx5_flow_action action = {
- .queue = 0,
- .drop = 0,
- .mark = 0,
- };
+uint64_t
+mlx5_flow_hashfields_adjust(struct mlx5_flow *dev_flow,
+ int tunnel __rte_unused, uint64_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;
+}
- (void)priv;
- if (attr->group) {
- rte_flow_error_set(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ATTR_GROUP,
- NULL,
- "groups are not supported");
- return -rte_errno;
- }
- if (attr->priority) {
- rte_flow_error_set(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ATTR_PRIORITY,
- NULL,
- "priorities are not supported");
- return -rte_errno;
- }
- if (attr->egress) {
- rte_flow_error_set(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ATTR_EGRESS,
- NULL,
- "egress is not supported");
- return -rte_errno;
- }
- if (!attr->ingress) {
- rte_flow_error_set(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ATTR_INGRESS,
- NULL,
- "only ingress is supported");
- return -rte_errno;
- }
- for (; items->type != RTE_FLOW_ITEM_TYPE_END; ++items) {
- const struct mlx5_flow_items *token = NULL;
- unsigned int i;
- int err;
+/**
+ * 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
+flow_rxq_tunnel_ptype_update(struct mlx5_rxq_ctrl *rxq_ctrl)
+{
+ unsigned int i;
+ uint32_t tunnel_ptype = 0;
- if (items->type == RTE_FLOW_ITEM_TYPE_VOID)
+ /* Look up for the ptype to use. */
+ for (i = 0; i != MLX5_FLOW_TUNNEL; ++i) {
+ if (!rxq_ctrl->flow_tunnels_n[i])
continue;
- for (i = 0;
- cur_item->items &&
- cur_item->items[i] != RTE_FLOW_ITEM_TYPE_END;
- ++i) {
- if (cur_item->items[i] == items->type) {
- token = &mlx5_flow_items[items->type];
- break;
- }
+ 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 devive
+ * flow.
+ *
+ * @param[in] dev
+ * Pointer to the Ethernet device structure.
+ * @param[in] dev_flow
+ * Pointer to device flow structure.
+ */
+static void
+flow_drv_rxq_flags_set(struct rte_eth_dev *dev, struct mlx5_flow *dev_flow)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct rte_flow *flow = dev_flow->flow;
+ const int mark = !!(flow->actions &
+ (MLX5_FLOW_ACTION_FLAG | MLX5_FLOW_ACTION_MARK));
+ const int tunnel = !!(dev_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 (!token)
- goto exit_item_not_supported;
- cur_item = token;
- err = mlx5_flow_item_validate(items,
- (const uint8_t *)cur_item->mask,
- cur_item->mask_sz);
- if (err)
- goto exit_item_not_supported;
- if (flow->ibv_attr && cur_item->convert) {
- err = cur_item->convert(items,
- (cur_item->default_mask ?
- cur_item->default_mask :
- cur_item->mask),
- flow);
- if (err)
- goto exit_item_not_supported;
+ if (tunnel) {
+ unsigned int j;
+
+ /* Increase the counter matching the flow. */
+ for (j = 0; j != MLX5_FLOW_TUNNEL; ++j) {
+ if ((tunnels_info[j].tunnel &
+ dev_flow->layers) ==
+ tunnels_info[j].tunnel) {
+ rxq_ctrl->flow_tunnels_n[j]++;
+ break;
+ }
+ }
+ flow_rxq_tunnel_ptype_update(rxq_ctrl);
}
- flow->offset += cur_item->dst_sz;
}
- for (; actions->type != RTE_FLOW_ACTION_TYPE_END; ++actions) {
- if (actions->type == RTE_FLOW_ACTION_TYPE_VOID) {
- continue;
- } else if (actions->type == RTE_FLOW_ACTION_TYPE_DROP) {
- action.drop = 1;
- } else if (actions->type == RTE_FLOW_ACTION_TYPE_QUEUE) {
- const struct rte_flow_action_queue *queue =
- (const struct rte_flow_action_queue *)
- actions->conf;
-
- if (!queue || (queue->index > (priv->rxqs_n - 1)))
- goto exit_action_not_supported;
- action.queue = 1;
- } else if (actions->type == RTE_FLOW_ACTION_TYPE_MARK) {
- const struct rte_flow_action_mark *mark =
- (const struct rte_flow_action_mark *)
- actions->conf;
-
- if (!mark) {
- rte_flow_error_set(error, EINVAL,
- RTE_FLOW_ERROR_TYPE_ACTION,
- actions,
- "mark must be defined");
- return -rte_errno;
- } else if (mark->id >= MLX5_FLOW_MARK_MAX) {
- rte_flow_error_set(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ACTION,
- actions,
- "mark must be between 0"
- " and 16777199");
- return -rte_errno;
+}
+
+/**
+ * Set the Rx queue flags (Mark/Flag and Tunnel Ptypes) for a flow
+ *
+ * @param[in] dev
+ * Pointer to the Ethernet device structure.
+ * @param[in] flow
+ * Pointer to flow structure.
+ */
+static void
+flow_rxq_flags_set(struct rte_eth_dev *dev, struct rte_flow *flow)
+{
+ struct mlx5_flow *dev_flow;
+
+ LIST_FOREACH(dev_flow, &flow->dev_flows, next)
+ flow_drv_rxq_flags_set(dev, dev_flow);
+}
+
+/**
+ * Clear the Rx queue flags (Mark/Flag and Tunnel Ptype) associated with the
+ * device flow if no other flow uses it with the same kind of request.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param[in] dev_flow
+ * Pointer to the device flow.
+ */
+static void
+flow_drv_rxq_flags_trim(struct rte_eth_dev *dev, struct mlx5_flow *dev_flow)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct rte_flow *flow = dev_flow->flow;
+ const int mark = !!(flow->actions &
+ (MLX5_FLOW_ACTION_FLAG | MLX5_FLOW_ACTION_MARK));
+ const int tunnel = !!(dev_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 &
+ dev_flow->layers) ==
+ tunnels_info[j].tunnel) {
+ rxq_ctrl->flow_tunnels_n[j]--;
+ break;
+ }
}
- action.mark = 1;
- } else if (actions->type == RTE_FLOW_ACTION_TYPE_FLAG) {
- action.mark = 1;
- } else {
- goto exit_action_not_supported;
+ flow_rxq_tunnel_ptype_update(rxq_ctrl);
}
}
- if (action.mark && !flow->ibv_attr && !action.drop)
- flow->offset += sizeof(struct ibv_exp_flow_spec_action_tag);
- if (!action.queue && !action.drop) {
- rte_flow_error_set(error, ENOTSUP, RTE_FLOW_ERROR_TYPE_HANDLE,
- NULL, "no valid action");
+}
+
+/**
+ * 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
+flow_rxq_flags_trim(struct rte_eth_dev *dev, struct rte_flow *flow)
+{
+ struct mlx5_flow *dev_flow;
+
+ LIST_FOREACH(dev_flow, &flow->dev_flows, next)
+ flow_drv_rxq_flags_trim(dev, dev_flow);
+}
+
+/**
+ * Clear the Mark/Flag and Tunnel ptype information in all Rx queues.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ */
+static void
+flow_rxq_flags_clear(struct rte_eth_dev *dev)
+{
+ struct mlx5_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[in] attr
+ * Attributes of flow that includes this action.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_flow_validate_action_flag(uint64_t action_flags,
+ const struct rte_flow_attr *attr,
+ 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");
+ if (attr->egress)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ATTR_EGRESS, NULL,
+ "flag action not supported for "
+ "egress");
+ 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[in] attr
+ * Attributes of flow that includes this action.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_flow_validate_action_mark(const struct rte_flow_action *action,
+ uint64_t action_flags,
+ const struct rte_flow_attr *attr,
+ 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");
+ if (attr->egress)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ATTR_EGRESS, NULL,
+ "mark action not supported for "
+ "egress");
+ return 0;
+}
+
+/*
+ * Validate the drop action.
+ *
+ * @param[in] action_flags
+ * Bit-fields that holds the actions detected until now.
+ * @param[in] attr
+ * Attributes of flow that includes this action.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_flow_validate_action_drop(uint64_t action_flags,
+ const struct rte_flow_attr *attr,
+ 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");
+ if (attr->egress)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ATTR_EGRESS, NULL,
+ "drop action not supported for "
+ "egress");
+ 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[in] attr
+ * Attributes of flow that includes this action.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_flow_validate_action_queue(const struct rte_flow_action *action,
+ uint64_t action_flags,
+ struct rte_eth_dev *dev,
+ const struct rte_flow_attr *attr,
+ struct rte_flow_error *error)
+{
+ struct mlx5_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 (!priv->rxqs_n)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ NULL, "No Rx queues configured");
+ 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");
+ if (attr->egress)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ATTR_EGRESS, NULL,
+ "queue action not supported for "
+ "egress");
+ 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[in] attr
+ * Attributes of flow that includes this action.
+ * @param[in] item_flags
+ * Items that were detected.
+ * @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_rss(const struct rte_flow_action *action,
+ uint64_t action_flags,
+ struct rte_eth_dev *dev,
+ const struct rte_flow_attr *attr,
+ uint64_t item_flags,
+ struct rte_flow_error *error)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ const struct rte_flow_action_rss *rss = action->conf;
+ int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
+ 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");
+ /* allow RSS key_len 0 in case of NULL (default) RSS key. */
+ if (rss->key_len == 0 && rss->key != NULL)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ &rss->key_len,
+ "RSS hash key length 0");
+ if (rss->key_len > 0 && 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");
+ if (!priv->rxqs_n)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ NULL, "No Rx queues configured");
+ if (!rss->queue_num)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ NULL, "No queues configured");
+ 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");
+ }
+ if (attr->egress)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ATTR_EGRESS, NULL,
+ "rss action not supported for "
+ "egress");
+ if (rss->level > 1 && !tunnel)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF, NULL,
+ "inner RSS is not supported for "
+ "non-tunnel flows");
+ return 0;
+}
+
+/*
+ * Validate the count action.
+ *
+ * @param[in] dev
+ * Pointer to the Ethernet device structure.
+ * @param[in] attr
+ * Attributes of flow that includes this action.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_flow_validate_action_count(struct rte_eth_dev *dev __rte_unused,
+ const struct rte_flow_attr *attr,
+ struct rte_flow_error *error)
+{
+ if (attr->egress)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ATTR_EGRESS, NULL,
+ "count action not supported for "
+ "egress");
+ 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 mlx5_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 && !priv->config.dv_esw_en)
+ 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 ICMP6 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_icmp6(const struct rte_flow_item *item,
+ uint64_t item_flags,
+ uint8_t target_protocol,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_icmp6 *mask = item->mask;
+ const int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
+ const uint64_t l3m = tunnel ? MLX5_FLOW_LAYER_INNER_L3_IPV6 :
+ MLX5_FLOW_LAYER_OUTER_L3_IPV6;
+ const uint64_t l4m = tunnel ? MLX5_FLOW_LAYER_INNER_L4 :
+ MLX5_FLOW_LAYER_OUTER_L4;
+ int ret;
+
+ if (target_protocol != 0xFF && target_protocol != IPPROTO_ICMPV6)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "protocol filtering not compatible"
+ " with ICMP6 layer");
+ if (!(item_flags & l3m))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "IPv6 is mandatory to filter on"
+ " ICMP6");
+ if (item_flags & l4m)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "multiple L4 layers not supported");
+ if (!mask)
+ mask = &rte_flow_item_icmp6_mask;
+ ret = mlx5_flow_item_acceptable
+ (item, (const uint8_t *)mask,
+ (const uint8_t *)&rte_flow_item_icmp6_mask,
+ sizeof(struct rte_flow_item_icmp6), error);
+ if (ret < 0)
+ return ret;
+ return 0;
+}
+
+/**
+ * Validate ICMP 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_icmp(const struct rte_flow_item *item,
+ uint64_t item_flags,
+ uint8_t target_protocol,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_icmp *mask = item->mask;
+ const int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
+ const uint64_t l3m = tunnel ? MLX5_FLOW_LAYER_INNER_L3_IPV4 :
+ MLX5_FLOW_LAYER_OUTER_L3_IPV4;
+ const uint64_t l4m = tunnel ? MLX5_FLOW_LAYER_INNER_L4 :
+ MLX5_FLOW_LAYER_OUTER_L4;
+ int ret;
+
+ if (target_protocol != 0xFF && target_protocol != IPPROTO_ICMP)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "protocol filtering not compatible"
+ " with ICMP layer");
+ if (!(item_flags & l3m))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "IPv4 is mandatory to filter"
+ " on ICMP");
+ if (item_flags & l4m)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "multiple L4 layers not supported");
+ if (!mask)
+ mask = &rte_flow_item_icmp_mask;
+ ret = mlx5_flow_item_acceptable
+ (item, (const uint8_t *)mask,
+ (const uint8_t *)&rte_flow_item_icmp_mask,
+ sizeof(struct rte_flow_item_icmp), error);
+ if (ret < 0)
+ return ret;
+ 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);
+ const uint64_t ethm = tunnel ? MLX5_FLOW_LAYER_INNER_L2 :
+ MLX5_FLOW_LAYER_OUTER_L2;
+
+ if (item_flags & ethm)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "multiple L2 layers 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,
+ uint64_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 uint64_t l34m = tunnel ? (MLX5_FLOW_LAYER_INNER_L3 |
+ MLX5_FLOW_LAYER_INNER_L4) :
+ (MLX5_FLOW_LAYER_OUTER_L3 |
+ MLX5_FLOW_LAYER_OUTER_L4);
+ const uint64_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,
+ "multiple VLAN layers not supported");
+ 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[in] acc_mask
+ * Acceptable mask, if NULL default internal default mask
+ * will be used to check whether item fields are supported.
+ * @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,
+ uint64_t item_flags,
+ const struct rte_flow_item_ipv4 *acc_mask,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_ipv4 *mask = item->mask;
+ const struct rte_flow_item_ipv4 *spec = item->spec;
+ const struct rte_flow_item_ipv4 nic_mask = {
+ .hdr = {
+ .src_addr = RTE_BE32(0xffffffff),
+ .dst_addr = RTE_BE32(0xffffffff),
+ .type_of_service = 0xff,
+ .next_proto_id = 0xff,
+ },
+ };
+ const int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
+ const uint64_t l3m = tunnel ? MLX5_FLOW_LAYER_INNER_L3 :
+ MLX5_FLOW_LAYER_OUTER_L3;
+ const uint64_t l4m = tunnel ? MLX5_FLOW_LAYER_INNER_L4 :
+ MLX5_FLOW_LAYER_OUTER_L4;
+ int ret;
+ uint8_t next_proto = 0xFF;
+
+ if (item_flags & MLX5_FLOW_LAYER_IPIP) {
+ if (mask && spec)
+ next_proto = mask->hdr.next_proto_id &
+ spec->hdr.next_proto_id;
+ if (next_proto == IPPROTO_IPIP || next_proto == IPPROTO_IPV6)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM,
+ item,
+ "multiple tunnel "
+ "not supported");
+ }
+ if (item_flags & MLX5_FLOW_LAYER_IPV6_ENCAP)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "wrong tunnel type - IPv6 specified "
+ "but IPv4 item provided");
+ if (item_flags & l3m)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "multiple L3 layers not supported");
+ else if (item_flags & l4m)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L3 cannot follow an L4 layer.");
+ else if ((item_flags & MLX5_FLOW_LAYER_NVGRE) &&
+ !(item_flags & MLX5_FLOW_LAYER_INNER_L2))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L3 cannot follow an NVGRE layer.");
+ if (!mask)
+ mask = &rte_flow_item_ipv4_mask;
+ else if (mask->hdr.next_proto_id != 0 &&
+ mask->hdr.next_proto_id != 0xff)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
+ "partial mask is not supported"
+ " for protocol");
+ ret = mlx5_flow_item_acceptable(item, (const uint8_t *)mask,
+ acc_mask ? (const uint8_t *)acc_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[in] acc_mask
+ * Acceptable mask, if NULL default internal default mask
+ * will be used to check whether item fields are supported.
+ * @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,
+ const struct rte_flow_item_ipv6 *acc_mask,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_ipv6 *mask = item->mask;
+ const struct rte_flow_item_ipv6 *spec = item->spec;
+ const struct rte_flow_item_ipv6 nic_mask = {
+ .hdr = {
+ .src_addr =
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff",
+ .dst_addr =
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff",
+ .vtc_flow = RTE_BE32(0xffffffff),
+ .proto = 0xff,
+ .hop_limits = 0xff,
+ },
+ };
+ const int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
+ const uint64_t l3m = tunnel ? MLX5_FLOW_LAYER_INNER_L3 :
+ MLX5_FLOW_LAYER_OUTER_L3;
+ const uint64_t l4m = tunnel ? MLX5_FLOW_LAYER_INNER_L4 :
+ MLX5_FLOW_LAYER_OUTER_L4;
+ int ret;
+ uint8_t next_proto = 0xFF;
+
+ if (item_flags & MLX5_FLOW_LAYER_IPV6_ENCAP) {
+ if (mask && spec)
+ next_proto = mask->hdr.proto & spec->hdr.proto;
+ if (next_proto == IPPROTO_IPIP || next_proto == IPPROTO_IPV6)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM,
+ item,
+ "multiple tunnel "
+ "not supported");
+ }
+ if (item_flags & MLX5_FLOW_LAYER_IPIP)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "wrong tunnel type - IPv4 specified "
+ "but IPv6 item provided");
+ if (item_flags & l3m)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "multiple L3 layers not supported");
+ else if (item_flags & l4m)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L3 cannot follow an L4 layer.");
+ else if ((item_flags & MLX5_FLOW_LAYER_NVGRE) &&
+ !(item_flags & MLX5_FLOW_LAYER_INNER_L2))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L3 cannot follow an NVGRE layer.");
+ if (!mask)
+ mask = &rte_flow_item_ipv6_mask;
+ ret = mlx5_flow_item_acceptable(item, (const uint8_t *)mask,
+ acc_mask ? (const uint8_t *)acc_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[in] flow_mask
+ * mlx5 flow-specific (DV, verbs, etc.) supported header fields mask.
+ * @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);
+ const uint64_t l3m = tunnel ? MLX5_FLOW_LAYER_INNER_L3 :
+ MLX5_FLOW_LAYER_OUTER_L3;
+ const uint64_t l4m = tunnel ? MLX5_FLOW_LAYER_INNER_L4 :
+ MLX5_FLOW_LAYER_OUTER_L4;
+ 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 & l3m))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L3 is mandatory to filter on L4");
+ if (item_flags & l4m)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "multiple L4 layers not supported");
+ if (!mask)
+ mask = &rte_flow_item_udp_mask;
+ ret = mlx5_flow_item_acceptable
+ (item, (const uint8_t *)mask,
+ (const uint8_t *)&rte_flow_item_udp_mask,
+ sizeof(struct rte_flow_item_udp), error);
+ if (ret < 0)
+ return ret;
+ return 0;
+}
+
+/**
+ * Validate TCP item.
+ *
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit-fields that holds the items detected until now.
+ * @param[in] target_protocol
+ * The next protocol in the previous item.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_flow_validate_item_tcp(const struct rte_flow_item *item,
+ uint64_t item_flags,
+ uint8_t target_protocol,
+ const struct rte_flow_item_tcp *flow_mask,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_tcp *mask = item->mask;
+ const int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
+ const uint64_t l3m = tunnel ? MLX5_FLOW_LAYER_INNER_L3 :
+ MLX5_FLOW_LAYER_OUTER_L3;
+ const uint64_t l4m = tunnel ? MLX5_FLOW_LAYER_INNER_L4 :
+ MLX5_FLOW_LAYER_OUTER_L4;
+ int ret;
+
+ assert(flow_mask);
+ 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 & l3m))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L3 is mandatory to filter on L4");
+ if (item_flags & l4m)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "multiple L4 layers not supported");
+ if (!mask)
+ mask = &rte_flow_item_tcp_mask;
+ ret = mlx5_flow_item_acceptable
+ (item, (const uint8_t *)mask,
+ (const uint8_t *)flow_mask,
+ sizeof(struct rte_flow_item_tcp), error);
+ if (ret < 0)
+ return ret;
+ return 0;
+}
+
+/**
+ * Validate VXLAN item.
+ *
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit-fields that holds the items detected until now.
+ * @param[in] target_protocol
+ * The next protocol in the previous item.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_flow_validate_item_vxlan(const struct rte_flow_item *item,
+ uint64_t item_flags,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_vxlan *spec = item->spec;
+ const struct rte_flow_item_vxlan *mask = item->mask;
+ int ret;
+ union vni {
+ uint32_t vlan_id;
+ uint8_t vni[4];
+ } id = { .vlan_id = 0, };
+ uint32_t vlan_id = 0;
+
+
+ if (item_flags & MLX5_FLOW_LAYER_TUNNEL)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "multiple tunnel layers not"
+ " supported");
+ /*
+ * Verify only UDPv4 is present as defined in
+ * https://tools.ietf.org/html/rfc7348
+ */
+ if (!(item_flags & MLX5_FLOW_LAYER_OUTER_L4_UDP))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "no outer UDP layer found");
+ if (!mask)
+ mask = &rte_flow_item_vxlan_mask;
+ ret = mlx5_flow_item_acceptable
+ (item, (const uint8_t *)mask,
+ (const uint8_t *)&rte_flow_item_vxlan_mask,
+ sizeof(struct rte_flow_item_vxlan),
+ error);
+ if (ret < 0)
+ return ret;
+ if (spec) {
+ memcpy(&id.vni[1], spec->vni, 3);
+ vlan_id = id.vlan_id;
+ memcpy(&id.vni[1], mask->vni, 3);
+ vlan_id &= id.vlan_id;
+ }
+ /*
+ * Tunnel id 0 is equivalent as not adding a VXLAN layer, if
+ * only this layer is defined in the Verbs specification it is
+ * interpreted as wildcard and all packets will match this
+ * rule, if it follows a full stack layer (ex: eth / ipv4 /
+ * udp), all packets matching the layers before will also
+ * match this rule. To avoid such situation, VNI 0 is
+ * currently refused.
+ */
+ if (!vlan_id)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "VXLAN vni cannot be 0");
+ if (!(item_flags & MLX5_FLOW_LAYER_OUTER))
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "VXLAN tunnel must be fully defined");
+ return 0;
+}
+
+/**
+ * Validate VXLAN_GPE item.
+ *
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit-fields that holds the items detected until now.
+ * @param[in] priv
+ * Pointer to the private data structure.
+ * @param[in] target_protocol
+ * The next protocol in the previous item.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_flow_validate_item_vxlan_gpe(const struct rte_flow_item *item,
+ uint64_t item_flags,
+ struct rte_eth_dev *dev,
+ struct rte_flow_error *error)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ const struct rte_flow_item_vxlan_gpe *spec = item->spec;
+ const struct rte_flow_item_vxlan_gpe *mask = item->mask;
+ int ret;
+ union vni {
+ uint32_t vlan_id;
+ uint8_t vni[4];
+ } id = { .vlan_id = 0, };
+ uint32_t vlan_id = 0;
+
+ if (!priv->config.l3_vxlan_en)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "L3 VXLAN is not enabled by device"
+ " parameter and/or not configured in"
+ " firmware");
+ if (item_flags & MLX5_FLOW_LAYER_TUNNEL)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "multiple tunnel layers not"
+ " supported");
+ /*
+ * Verify only UDPv4 is present as defined in
+ * https://tools.ietf.org/html/rfc7348
+ */
+ if (!(item_flags & MLX5_FLOW_LAYER_OUTER_L4_UDP))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "no outer UDP layer found");
+ if (!mask)
+ mask = &rte_flow_item_vxlan_gpe_mask;
+ ret = mlx5_flow_item_acceptable
+ (item, (const uint8_t *)mask,
+ (const uint8_t *)&rte_flow_item_vxlan_gpe_mask,
+ sizeof(struct rte_flow_item_vxlan_gpe),
+ error);
+ if (ret < 0)
+ return ret;
+ if (spec) {
+ if (spec->protocol)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM,
+ item,
+ "VxLAN-GPE protocol"
+ " not supported");
+ memcpy(&id.vni[1], spec->vni, 3);
+ vlan_id = id.vlan_id;
+ memcpy(&id.vni[1], mask->vni, 3);
+ vlan_id &= id.vlan_id;
+ }
+ /*
+ * Tunnel id 0 is equivalent as not adding a VXLAN layer, if only this
+ * layer is defined in the Verbs specification it is interpreted as
+ * wildcard and all packets will match this rule, if it follows a full
+ * stack layer (ex: eth / ipv4 / udp), all packets matching the layers
+ * before will also match this rule. To avoid such situation, VNI 0
+ * is currently refused.
+ */
+ if (!vlan_id)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "VXLAN-GPE vni cannot be 0");
+ if (!(item_flags & MLX5_FLOW_LAYER_OUTER))
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "VXLAN-GPE tunnel must be fully"
+ " defined");
+ return 0;
+}
+/**
+ * Validate GRE Key item.
+ *
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit flags to mark detected items.
+ * @param[in] gre_item
+ * Pointer to gre_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_gre_key(const struct rte_flow_item *item,
+ uint64_t item_flags,
+ const struct rte_flow_item *gre_item,
+ struct rte_flow_error *error)
+{
+ const rte_be32_t *mask = item->mask;
+ int ret = 0;
+ rte_be32_t gre_key_default_mask = RTE_BE32(UINT32_MAX);
+ const struct rte_flow_item_gre *gre_spec = gre_item->spec;
+ const struct rte_flow_item_gre *gre_mask = gre_item->mask;
+
+ if (item_flags & MLX5_FLOW_LAYER_GRE_KEY)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "Multiple GRE key not support");
+ if (!(item_flags & MLX5_FLOW_LAYER_GRE))
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "No preceding GRE header");
+ if (item_flags & MLX5_FLOW_LAYER_INNER)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "GRE key following a wrong item");
+ if (!gre_mask)
+ gre_mask = &rte_flow_item_gre_mask;
+ if (gre_spec && (gre_mask->c_rsvd0_ver & RTE_BE16(0x2000)) &&
+ !(gre_spec->c_rsvd0_ver & RTE_BE16(0x2000)))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "Key bit must be on");
+
+ if (!mask)
+ mask = &gre_key_default_mask;
+ ret = mlx5_flow_item_acceptable
+ (item, (const uint8_t *)mask,
+ (const uint8_t *)&gre_key_default_mask,
+ sizeof(rte_be32_t), error);
+ return ret;
+}
+
+/**
+ * Validate GRE item.
+ *
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit flags to mark detected items.
+ * @param[in] target_protocol
+ * The next protocol in the previous item.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_flow_validate_item_gre(const struct rte_flow_item *item,
+ uint64_t item_flags,
+ uint8_t target_protocol,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_gre *spec __rte_unused = item->spec;
+ const struct rte_flow_item_gre *mask = item->mask;
+ int ret;
+ const struct rte_flow_item_gre nic_mask = {
+ .c_rsvd0_ver = RTE_BE16(0xB000),
+ .protocol = RTE_BE16(UINT16_MAX),
+ };
+
+ 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_ITEM, item,
+ "multiple tunnel layers not"
+ " supported");
+ 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 *)&nic_mask,
+ sizeof(struct rte_flow_item_gre), error);
+ if (ret < 0)
+ return ret;
+#ifndef HAVE_MLX5DV_DR
+#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
+#endif
+ return 0;
+}
+
+/**
+ * Validate MPLS item.
+ *
+ * @param[in] dev
+ * Pointer to the rte_eth_dev structure.
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit-fields that holds the items detected until now.
+ * @param[in] prev_layer
+ * The protocol layer indicated in 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_mpls(struct rte_eth_dev *dev __rte_unused,
+ const struct rte_flow_item *item __rte_unused,
+ uint64_t item_flags __rte_unused,
+ uint64_t prev_layer __rte_unused,
+ struct rte_flow_error *error)
+{
+#ifdef HAVE_IBV_DEVICE_MPLS_SUPPORT
+ const struct rte_flow_item_mpls *mask = item->mask;
+ struct mlx5_priv *priv = dev->data->dev_private;
+ int ret;
+
+ if (!priv->config.mpls_en)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "MPLS not supported or"
+ " disabled in firmware"
+ " configuration.");
+ /* MPLS over IP, UDP, GRE is allowed */
+ if (!(prev_layer & (MLX5_FLOW_LAYER_OUTER_L3 |
+ MLX5_FLOW_LAYER_OUTER_L4_UDP |
+ MLX5_FLOW_LAYER_GRE)))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "protocol filtering not compatible"
+ " with MPLS layer");
+ /* Multi-tunnel isn't allowed but MPLS over GRE is an exception. */
+ if ((item_flags & MLX5_FLOW_LAYER_TUNNEL) &&
+ !(item_flags & MLX5_FLOW_LAYER_GRE))
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "multiple tunnel layers not"
+ " supported");
+ if (!mask)
+ mask = &rte_flow_item_mpls_mask;
+ ret = mlx5_flow_item_acceptable
+ (item, (const uint8_t *)mask,
+ (const uint8_t *)&rte_flow_item_mpls_mask,
+ sizeof(struct rte_flow_item_mpls), error);
+ if (ret < 0)
+ return ret;
+ return 0;
+#endif
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "MPLS is not supported by Verbs, please"
+ " update.");
+}
+
+/**
+ * Validate NVGRE item.
+ *
+ * @param[in] item
+ * Item specification.
+ * @param[in] item_flags
+ * Bit flags to mark detected items.
+ * @param[in] target_protocol
+ * The next protocol in the previous item.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_flow_validate_item_nvgre(const struct rte_flow_item *item,
+ uint64_t item_flags,
+ uint8_t target_protocol,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_nvgre *mask = item->mask;
+ int ret;
+
+ 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_ITEM, item,
+ "multiple tunnel layers not"
+ " supported");
+ 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_nvgre_mask;
+ ret = mlx5_flow_item_acceptable
+ (item, (const uint8_t *)mask,
+ (const uint8_t *)&rte_flow_item_nvgre_mask,
+ sizeof(struct rte_flow_item_nvgre), error);
+ if (ret < 0)
+ return ret;
+ return 0;
+}
+
+static int
+flow_null_validate(struct rte_eth_dev *dev __rte_unused,
+ const struct rte_flow_attr *attr __rte_unused,
+ const struct rte_flow_item items[] __rte_unused,
+ const struct rte_flow_action actions[] __rte_unused,
+ struct rte_flow_error *error)
+{
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL, NULL);
+}
+
+static struct mlx5_flow *
+flow_null_prepare(const struct rte_flow_attr *attr __rte_unused,
+ const struct rte_flow_item items[] __rte_unused,
+ const struct rte_flow_action actions[] __rte_unused,
+ struct rte_flow_error *error)
+{
+ rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL, NULL);
+ return NULL;
+}
+
+static int
+flow_null_translate(struct rte_eth_dev *dev __rte_unused,
+ struct mlx5_flow *dev_flow __rte_unused,
+ const struct rte_flow_attr *attr __rte_unused,
+ const struct rte_flow_item items[] __rte_unused,
+ const struct rte_flow_action actions[] __rte_unused,
+ struct rte_flow_error *error)
+{
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL, NULL);
+}
+
+static int
+flow_null_apply(struct rte_eth_dev *dev __rte_unused,
+ struct rte_flow *flow __rte_unused,
+ struct rte_flow_error *error)
+{
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL, NULL);
+}
+
+static void
+flow_null_remove(struct rte_eth_dev *dev __rte_unused,
+ struct rte_flow *flow __rte_unused)
+{
+}
+
+static void
+flow_null_destroy(struct rte_eth_dev *dev __rte_unused,
+ struct rte_flow *flow __rte_unused)
+{
+}
+
+static int
+flow_null_query(struct rte_eth_dev *dev __rte_unused,
+ struct rte_flow *flow __rte_unused,
+ const struct rte_flow_action *actions __rte_unused,
+ void *data __rte_unused,
+ struct rte_flow_error *error)
+{
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL, NULL);
+}
+
+/* Void driver to protect from null pointer reference. */
+const struct mlx5_flow_driver_ops mlx5_flow_null_drv_ops = {
+ .validate = flow_null_validate,
+ .prepare = flow_null_prepare,
+ .translate = flow_null_translate,
+ .apply = flow_null_apply,
+ .remove = flow_null_remove,
+ .destroy = flow_null_destroy,
+ .query = flow_null_query,
+};
+
+/**
+ * Select flow driver type according to flow attributes and device
+ * configuration.
+ *
+ * @param[in] dev
+ * Pointer to the dev structure.
+ * @param[in] attr
+ * Pointer to the flow attributes.
+ *
+ * @return
+ * flow driver type, MLX5_FLOW_TYPE_MAX otherwise.
+ */
+static enum mlx5_flow_drv_type
+flow_get_drv_type(struct rte_eth_dev *dev, const struct rte_flow_attr *attr)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ enum mlx5_flow_drv_type type = MLX5_FLOW_TYPE_MAX;
+
+ if (attr->transfer && priv->config.dv_esw_en)
+ type = MLX5_FLOW_TYPE_DV;
+ if (!attr->transfer)
+ type = priv->config.dv_flow_en ? MLX5_FLOW_TYPE_DV :
+ MLX5_FLOW_TYPE_VERBS;
+ return type;
+}
+
+#define flow_get_drv_ops(type) flow_drv_ops[type]
+
+/**
+ * Flow driver validation API. This abstracts calling driver specific functions.
+ * The type of flow driver is determined according to flow attributes.
+ *
+ * @param[in] dev
+ * Pointer to the dev structure.
+ * @param[in] attr
+ * Pointer to the flow attributes.
+ * @param[in] items
+ * Pointer to the list of items.
+ * @param[in] actions
+ * Pointer to the list of actions.
+ * @param[out] error
+ * Pointer to the error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static inline int
+flow_drv_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)
+{
+ const struct mlx5_flow_driver_ops *fops;
+ enum mlx5_flow_drv_type type = flow_get_drv_type(dev, attr);
+
+ fops = flow_get_drv_ops(type);
+ return fops->validate(dev, attr, items, actions, error);
+}
+
+/**
+ * Flow driver preparation API. This abstracts calling driver specific
+ * functions. Parent flow (rte_flow) should have driver type (drv_type). It
+ * calculates the size of memory required for device flow, allocates the memory,
+ * initializes the device flow and returns the pointer.
+ *
+ * @note
+ * This function initializes device flow structure such as dv or verbs in
+ * struct mlx5_flow. However, it is caller's responsibility to initialize the
+ * rest. For example, adding returning device flow to flow->dev_flow list and
+ * setting backward reference to the flow should be done out of this function.
+ * layers field is not filled either.
+ *
+ * @param[in] attr
+ * Pointer to the flow attributes.
+ * @param[in] items
+ * Pointer to the list of items.
+ * @param[in] actions
+ * Pointer to the list of actions.
+ * @param[out] error
+ * Pointer to the error structure.
+ *
+ * @return
+ * Pointer to device flow on success, otherwise NULL and rte_errno is set.
+ */
+static inline struct mlx5_flow *
+flow_drv_prepare(const struct rte_flow *flow,
+ const struct rte_flow_attr *attr,
+ const struct rte_flow_item items[],
+ const struct rte_flow_action actions[],
+ struct rte_flow_error *error)
+{
+ const struct mlx5_flow_driver_ops *fops;
+ enum mlx5_flow_drv_type type = flow->drv_type;
+
+ assert(type > MLX5_FLOW_TYPE_MIN && type < MLX5_FLOW_TYPE_MAX);
+ fops = flow_get_drv_ops(type);
+ return fops->prepare(attr, items, actions, error);
+}
+
+/**
+ * Flow driver translation API. This abstracts calling driver specific
+ * functions. Parent flow (rte_flow) should have driver type (drv_type). It
+ * translates a generic flow into a driver flow. flow_drv_prepare() must
+ * precede.
+ *
+ * @note
+ * dev_flow->layers could be filled as a result of parsing during translation
+ * if needed by flow_drv_apply(). dev_flow->flow->actions can also be filled
+ * if necessary. As a flow can have multiple dev_flows by RSS flow expansion,
+ * flow->actions could be overwritten even though all the expanded dev_flows
+ * have the same actions.
+ *
+ * @param[in] dev
+ * Pointer to the rte dev structure.
+ * @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, a negative errno value otherwise and rte_errno is set.
+ */
+static inline int
+flow_drv_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)
+{
+ const struct mlx5_flow_driver_ops *fops;
+ enum mlx5_flow_drv_type type = dev_flow->flow->drv_type;
+
+ assert(type > MLX5_FLOW_TYPE_MIN && type < MLX5_FLOW_TYPE_MAX);
+ fops = flow_get_drv_ops(type);
+ return fops->translate(dev, dev_flow, attr, items, actions, error);
+}
+
+/**
+ * Flow driver apply API. This abstracts calling driver specific functions.
+ * Parent flow (rte_flow) should have driver type (drv_type). It applies
+ * translated driver flows on to device. flow_drv_translate() must precede.
+ *
+ * @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 inline int
+flow_drv_apply(struct rte_eth_dev *dev, struct rte_flow *flow,
+ struct rte_flow_error *error)
+{
+ const struct mlx5_flow_driver_ops *fops;
+ enum mlx5_flow_drv_type type = flow->drv_type;
+
+ assert(type > MLX5_FLOW_TYPE_MIN && type < MLX5_FLOW_TYPE_MAX);
+ fops = flow_get_drv_ops(type);
+ return fops->apply(dev, flow, error);
+}
+
+/**
+ * Flow driver remove API. This abstracts calling driver specific functions.
+ * Parent flow (rte_flow) should have driver type (drv_type). It removes a flow
+ * on device. All the resources of the flow should be freed by calling
+ * flow_drv_destroy().
+ *
+ * @param[in] dev
+ * Pointer to Ethernet device.
+ * @param[in, out] flow
+ * Pointer to flow structure.
+ */
+static inline void
+flow_drv_remove(struct rte_eth_dev *dev, struct rte_flow *flow)
+{
+ const struct mlx5_flow_driver_ops *fops;
+ enum mlx5_flow_drv_type type = flow->drv_type;
+
+ assert(type > MLX5_FLOW_TYPE_MIN && type < MLX5_FLOW_TYPE_MAX);
+ fops = flow_get_drv_ops(type);
+ fops->remove(dev, flow);
+}
+
+/**
+ * Flow driver destroy API. This abstracts calling driver specific functions.
+ * Parent flow (rte_flow) should have driver type (drv_type). It removes a flow
+ * on device and releases resources of the flow.
+ *
+ * @param[in] dev
+ * Pointer to Ethernet device.
+ * @param[in, out] flow
+ * Pointer to flow structure.
+ */
+static inline void
+flow_drv_destroy(struct rte_eth_dev *dev, struct rte_flow *flow)
+{
+ const struct mlx5_flow_driver_ops *fops;
+ enum mlx5_flow_drv_type type = flow->drv_type;
+
+ assert(type > MLX5_FLOW_TYPE_MIN && type < MLX5_FLOW_TYPE_MAX);
+ fops = flow_get_drv_ops(type);
+ fops->destroy(dev, flow);
+}
+
+/**
+ * Validate a flow supported by the NIC.
+ *
+ * @see rte_flow_validate()
+ * @see rte_flow_ops
+ */
+int
+mlx5_flow_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;
+
+ ret = flow_drv_validate(dev, attr, items, actions, error);
+ if (ret < 0)
+ return ret;
+ return 0;
+}
+
+/**
+ * Get RSS action from the action list.
+ *
+ * @param[in] actions
+ * Pointer to the list of actions.
+ *
+ * @return
+ * Pointer to the RSS action if exist, else return NULL.
+ */
+static const struct rte_flow_action_rss*
+flow_get_rss_action(const struct rte_flow_action actions[])
+{
+ 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;
+ }
+ }
+ return NULL;
+}
+
+static unsigned int
+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;
+}
+
+/**
+ * Create a flow and add it to @p list.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param list
+ * Pointer to a TAILQ flow list.
+ * @param[in] attr
+ * Flow rule attributes.
+ * @param[in] items
+ * 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 flow on success, NULL otherwise and rte_errno is set.
+ */
+static struct rte_flow *
+flow_list_create(struct rte_eth_dev *dev, struct mlx5_flows *list,
+ const struct rte_flow_attr *attr,
+ const struct rte_flow_item items[],
+ const struct rte_flow_action actions[],
+ struct rte_flow_error *error)
+{
+ struct rte_flow *flow = NULL;
+ struct mlx5_flow *dev_flow;
+ 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 = flow_drv_validate(dev, attr, items, actions, error);
+ if (ret < 0)
+ return NULL;
+ flow_size = sizeof(struct rte_flow);
+ rss = 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);
+ if (!flow) {
+ rte_errno = ENOMEM;
+ return NULL;
+ }
+ flow->drv_type = flow_get_drv_type(dev, attr);
+ flow->ingress = attr->ingress;
+ flow->transfer = attr->transfer;
+ assert(flow->drv_type > MLX5_FLOW_TYPE_MIN &&
+ flow->drv_type < MLX5_FLOW_TYPE_MAX);
+ flow->queue = (void *)(flow + 1);
+ LIST_INIT(&flow->dev_flows);
+ if (rss && rss->types) {
+ unsigned int graph_root;
+
+ graph_root = 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 = flow_drv_prepare(flow, attr, buf->entry[i].pattern,
+ actions, error);
+ if (!dev_flow)
+ goto error;
+ dev_flow->flow = flow;
+ LIST_INSERT_HEAD(&flow->dev_flows, dev_flow, next);
+ ret = flow_drv_translate(dev, dev_flow, attr,
+ buf->entry[i].pattern,
+ actions, error);
+ if (ret < 0)
+ goto error;
+ }
+ if (dev->data->dev_started) {
+ ret = flow_drv_apply(dev, flow, error);
+ if (ret < 0)
+ goto error;
+ }
+ TAILQ_INSERT_TAIL(list, flow, next);
+ flow_rxq_flags_set(dev, flow);
+ return flow;
+error:
+ ret = rte_errno; /* Save rte_errno before cleanup. */
+ assert(flow);
+ flow_drv_destroy(dev, flow);
+ rte_free(flow);
+ rte_errno = ret; /* Restore rte_errno. */
+ return NULL;
+}
+
+/**
+ * Create a flow.
+ *
+ * @see rte_flow_create()
+ * @see rte_flow_ops
+ */
+struct rte_flow *
+mlx5_flow_create(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)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+
+ return flow_list_create(dev, &priv->flows,
+ attr, items, actions, error);
+}
+
+/**
+ * Destroy a flow in a list.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param list
+ * Pointer to a TAILQ flow list.
+ * @param[in] flow
+ * Flow to destroy.
+ */
+static void
+flow_list_destroy(struct rte_eth_dev *dev, struct mlx5_flows *list,
+ struct rte_flow *flow)
+{
+ /*
+ * Update RX queue flags only if port is started, otherwise it is
+ * already clean.
+ */
+ if (dev->data->dev_started)
+ flow_rxq_flags_trim(dev, flow);
+ flow_drv_destroy(dev, flow);
+ TAILQ_REMOVE(list, flow, next);
+ rte_free(flow->fdir);
+ rte_free(flow);
+}
+
+/**
+ * Destroy all flows.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param list
+ * Pointer to a TAILQ flow list.
+ */
+void
+mlx5_flow_list_flush(struct rte_eth_dev *dev, struct mlx5_flows *list)
+{
+ while (!TAILQ_EMPTY(list)) {
+ struct rte_flow *flow;
+
+ flow = TAILQ_FIRST(list);
+ flow_list_destroy(dev, list, flow);
+ }
+}
+
+/**
+ * Remove all flows.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param list
+ * Pointer to a TAILQ flow list.
+ */
+void
+mlx5_flow_stop(struct rte_eth_dev *dev, struct mlx5_flows *list)
+{
+ struct rte_flow *flow;
+
+ TAILQ_FOREACH_REVERSE(flow, list, mlx5_flows, next)
+ flow_drv_remove(dev, flow);
+ flow_rxq_flags_clear(dev);
+}
+
+/**
+ * Add all flows.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param list
+ * Pointer to a TAILQ flow list.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+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 = flow_drv_apply(dev, flow, &error);
+ if (ret < 0)
+ goto error;
+ 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;
+}
+
+/**
+ * Verify the flow list is empty
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ *
+ * @return the number of flows not released.
+ */
+int
+mlx5_flow_verify(struct rte_eth_dev *dev)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct rte_flow *flow;
+ int ret = 0;
+
+ TAILQ_FOREACH(flow, &priv->flows, next) {
+ DRV_LOG(DEBUG, "port %u flow %p still referenced",
+ dev->data->port_id, (void *)flow);
+ ++ret;
+ }
+ return ret;
+}
+
+/**
+ * Enable a control flow configured from the control plane.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param eth_spec
+ * An Ethernet flow spec to apply.
+ * @param eth_mask
+ * An Ethernet flow mask to apply.
+ * @param vlan_spec
+ * A VLAN flow spec to apply.
+ * @param vlan_mask
+ * A VLAN flow mask to apply.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_ctrl_flow_vlan(struct rte_eth_dev *dev,
+ struct rte_flow_item_eth *eth_spec,
+ struct rte_flow_item_eth *eth_mask,
+ struct rte_flow_item_vlan *vlan_spec,
+ struct rte_flow_item_vlan *vlan_mask)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ const struct rte_flow_attr attr = {
+ .ingress = 1,
+ .priority = MLX5_FLOW_PRIO_RSVD,
+ };
+ struct rte_flow_item items[] = {
+ {
+ .type = RTE_FLOW_ITEM_TYPE_ETH,
+ .spec = eth_spec,
+ .last = NULL,
+ .mask = eth_mask,
+ },
+ {
+ .type = (vlan_spec) ? RTE_FLOW_ITEM_TYPE_VLAN :
+ RTE_FLOW_ITEM_TYPE_END,
+ .spec = vlan_spec,
+ .last = NULL,
+ .mask = vlan_mask,
+ },
+ {
+ .type = RTE_FLOW_ITEM_TYPE_END,
+ },
+ };
+ uint16_t queue[priv->reta_idx_n];
+ struct rte_flow_action_rss action_rss = {
+ .func = RTE_ETH_HASH_FUNCTION_DEFAULT,
+ .level = 0,
+ .types = priv->rss_conf.rss_hf,
+ .key_len = priv->rss_conf.rss_key_len,
+ .queue_num = priv->reta_idx_n,
+ .key = priv->rss_conf.rss_key,
+ .queue = queue,
+ };
+ struct rte_flow_action actions[] = {
+ {
+ .type = RTE_FLOW_ACTION_TYPE_RSS,
+ .conf = &action_rss,
+ },
+ {
+ .type = RTE_FLOW_ACTION_TYPE_END,
+ },
+ };
+ struct rte_flow *flow;
+ struct rte_flow_error error;
+ unsigned int i;
+
+ if (!priv->reta_idx_n || !priv->rxqs_n) {
+ return 0;
+ }
+ for (i = 0; i != priv->reta_idx_n; ++i)
+ queue[i] = (*priv->reta_idx)[i];
+ flow = flow_list_create(dev, &priv->ctrl_flows,
+ &attr, items, actions, &error);
+ if (!flow)
return -rte_errno;
- }
return 0;
-exit_item_not_supported:
- rte_flow_error_set(error, ENOTSUP, RTE_FLOW_ERROR_TYPE_ITEM,
- items, "item not supported");
- return -rte_errno;
-exit_action_not_supported:
- rte_flow_error_set(error, ENOTSUP, RTE_FLOW_ERROR_TYPE_ACTION,
- actions, "action not supported");
- return -rte_errno;
}
/**
- * Validate a flow supported by the NIC.
+ * Enable a flow control configured from the control plane.
*
- * @see rte_flow_validate()
- * @see rte_flow_ops
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param eth_spec
+ * An Ethernet flow spec to apply.
+ * @param eth_mask
+ * An Ethernet flow mask to apply.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
*/
int
-mlx5_flow_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)
+mlx5_ctrl_flow(struct rte_eth_dev *dev,
+ struct rte_flow_item_eth *eth_spec,
+ struct rte_flow_item_eth *eth_mask)
{
- struct priv *priv = dev->data->dev_private;
- int ret;
- struct mlx5_flow flow = { .offset = sizeof(struct ibv_exp_flow_attr) };
-
- priv_lock(priv);
- ret = priv_flow_validate(priv, attr, items, actions, error, &flow);
- priv_unlock(priv);
- return ret;
+ return mlx5_ctrl_flow_vlan(dev, eth_spec, eth_mask, NULL, NULL);
}
/**
- * Convert Ethernet item to Verbs specification.
+ * Destroy a flow.
*
- * @param item[in]
- * Item specification.
- * @param default_mask[in]
- * Default bit-masks to use when item->mask is not provided.
- * @param data[in, out]
- * User structure.
+ * @see rte_flow_destroy()
+ * @see rte_flow_ops
*/
-static int
-mlx5_flow_create_eth(const struct rte_flow_item *item,
- const void *default_mask,
- void *data)
+int
+mlx5_flow_destroy(struct rte_eth_dev *dev,
+ struct rte_flow *flow,
+ struct rte_flow_error *error __rte_unused)
{
- const struct rte_flow_item_eth *spec = item->spec;
- const struct rte_flow_item_eth *mask = item->mask;
- struct mlx5_flow *flow = (struct mlx5_flow *)data;
- struct ibv_exp_flow_spec_eth *eth;
- const unsigned int eth_size = sizeof(struct ibv_exp_flow_spec_eth);
- unsigned int i;
+ struct mlx5_priv *priv = dev->data->dev_private;
- ++flow->ibv_attr->num_of_specs;
- flow->ibv_attr->priority = 2;
- eth = (void *)((uintptr_t)flow->ibv_attr + flow->offset);
- *eth = (struct ibv_exp_flow_spec_eth) {
- .type = flow->inner | IBV_EXP_FLOW_SPEC_ETH,
- .size = eth_size,
- };
- if (!spec)
- return 0;
- if (!mask)
- mask = default_mask;
- memcpy(eth->val.dst_mac, spec->dst.addr_bytes, ETHER_ADDR_LEN);
- memcpy(eth->val.src_mac, spec->src.addr_bytes, ETHER_ADDR_LEN);
- eth->val.ether_type = spec->type;
- memcpy(eth->mask.dst_mac, mask->dst.addr_bytes, ETHER_ADDR_LEN);
- memcpy(eth->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;
+ flow_list_destroy(dev, &priv->flows, flow);
return 0;
}
/**
- * Convert VLAN item to Verbs specification.
+ * Destroy all flows.
*
- * @param item[in]
- * Item specification.
- * @param default_mask[in]
- * Default bit-masks to use when item->mask is not provided.
- * @param data[in, out]
- * User structure.
+ * @see rte_flow_flush()
+ * @see rte_flow_ops
*/
-static int
-mlx5_flow_create_vlan(const struct rte_flow_item *item,
- const void *default_mask,
- void *data)
+int
+mlx5_flow_flush(struct rte_eth_dev *dev,
+ struct rte_flow_error *error __rte_unused)
{
- const struct rte_flow_item_vlan *spec = item->spec;
- const struct rte_flow_item_vlan *mask = item->mask;
- struct mlx5_flow *flow = (struct mlx5_flow *)data;
- struct ibv_exp_flow_spec_eth *eth;
- const unsigned int eth_size = sizeof(struct ibv_exp_flow_spec_eth);
+ struct mlx5_priv *priv = dev->data->dev_private;
- eth = (void *)((uintptr_t)flow->ibv_attr + flow->offset - eth_size);
- if (!spec)
- return 0;
- if (!mask)
- mask = default_mask;
- eth->val.vlan_tag = spec->tci;
- eth->mask.vlan_tag = mask->tci;
- eth->val.vlan_tag &= eth->mask.vlan_tag;
+ mlx5_flow_list_flush(dev, &priv->flows);
return 0;
}
/**
- * Convert IPv4 item to Verbs specification.
+ * Isolated mode.
*
- * @param item[in]
- * Item specification.
- * @param default_mask[in]
- * Default bit-masks to use when item->mask is not provided.
- * @param data[in, out]
- * User structure.
+ * @see rte_flow_isolate()
+ * @see rte_flow_ops
*/
-static int
-mlx5_flow_create_ipv4(const struct rte_flow_item *item,
- const void *default_mask,
- void *data)
+int
+mlx5_flow_isolate(struct rte_eth_dev *dev,
+ int enable,
+ struct rte_flow_error *error)
{
- const struct rte_flow_item_ipv4 *spec = item->spec;
- const struct rte_flow_item_ipv4 *mask = item->mask;
- struct mlx5_flow *flow = (struct mlx5_flow *)data;
- struct ibv_exp_flow_spec_ipv4_ext *ipv4;
- unsigned int ipv4_size = sizeof(struct ibv_exp_flow_spec_ipv4_ext);
-
- ++flow->ibv_attr->num_of_specs;
- flow->ibv_attr->priority = 1;
- ipv4 = (void *)((uintptr_t)flow->ibv_attr + flow->offset);
- *ipv4 = (struct ibv_exp_flow_spec_ipv4_ext) {
- .type = flow->inner | IBV_EXP_FLOW_SPEC_IPV4_EXT,
- .size = ipv4_size,
- };
- if (!spec)
- return 0;
- if (!mask)
- mask = default_mask;
- ipv4->val = (struct ibv_exp_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_exp_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;
+ struct mlx5_priv *priv = dev->data->dev_private;
+
+ if (dev->data->dev_started) {
+ rte_flow_error_set(error, EBUSY,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL,
+ "port must be stopped first");
+ return -rte_errno;
+ }
+ priv->isolated = !!enable;
+ if (enable)
+ dev->dev_ops = &mlx5_dev_ops_isolate;
+ else
+ dev->dev_ops = &mlx5_dev_ops;
return 0;
}
/**
- * Convert IPv6 item to Verbs specification.
+ * Query a flow.
*
- * @param item[in]
- * Item specification.
- * @param default_mask[in]
- * Default bit-masks to use when item->mask is not provided.
- * @param data[in, out]
- * User structure.
+ * @see rte_flow_query()
+ * @see rte_flow_ops
*/
static int
-mlx5_flow_create_ipv6(const struct rte_flow_item *item,
- const void *default_mask,
- void *data)
+flow_drv_query(struct rte_eth_dev *dev,
+ struct rte_flow *flow,
+ const struct rte_flow_action *actions,
+ void *data,
+ struct rte_flow_error *error)
{
- const struct rte_flow_item_ipv6 *spec = item->spec;
- const struct rte_flow_item_ipv6 *mask = item->mask;
- struct mlx5_flow *flow = (struct mlx5_flow *)data;
- struct ibv_exp_flow_spec_ipv6_ext *ipv6;
- unsigned int ipv6_size = sizeof(struct ibv_exp_flow_spec_ipv6_ext);
-
- ++flow->ibv_attr->num_of_specs;
- flow->ibv_attr->priority = 1;
- ipv6 = (void *)((uintptr_t)flow->ibv_attr + flow->offset);
- *ipv6 = (struct ibv_exp_flow_spec_ipv6_ext) {
- .type = flow->inner | IBV_EXP_FLOW_SPEC_IPV6_EXT,
- .size = ipv6_size,
- };
- if (!spec)
- return 0;
- if (!mask)
- mask = default_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));
- ipv6->mask.flow_label = mask->hdr.vtc_flow;
- ipv6->mask.next_hdr = mask->hdr.proto;
- ipv6->mask.hop_limit = mask->hdr.hop_limits;
- ipv6->val.flow_label &= ipv6->mask.flow_label;
- ipv6->val.next_hdr &= ipv6->mask.next_hdr;
- ipv6->val.hop_limit &= ipv6->mask.hop_limit;
- return 0;
+ const struct mlx5_flow_driver_ops *fops;
+ enum mlx5_flow_drv_type ftype = flow->drv_type;
+
+ assert(ftype > MLX5_FLOW_TYPE_MIN && ftype < MLX5_FLOW_TYPE_MAX);
+ fops = flow_get_drv_ops(ftype);
+
+ return fops->query(dev, flow, actions, data, error);
}
/**
- * Convert UDP item to Verbs specification.
+ * Query a flow.
*
- * @param item[in]
- * Item specification.
- * @param default_mask[in]
- * Default bit-masks to use when item->mask is not provided.
- * @param data[in, out]
- * User structure.
+ * @see rte_flow_query()
+ * @see rte_flow_ops
*/
-static int
-mlx5_flow_create_udp(const struct rte_flow_item *item,
- const void *default_mask,
- void *data)
+int
+mlx5_flow_query(struct rte_eth_dev *dev,
+ struct rte_flow *flow,
+ const struct rte_flow_action *actions,
+ void *data,
+ struct rte_flow_error *error)
{
- const struct rte_flow_item_udp *spec = item->spec;
- const struct rte_flow_item_udp *mask = item->mask;
- struct mlx5_flow *flow = (struct mlx5_flow *)data;
- struct ibv_exp_flow_spec_tcp_udp *udp;
- unsigned int udp_size = sizeof(struct ibv_exp_flow_spec_tcp_udp);
-
- ++flow->ibv_attr->num_of_specs;
- flow->ibv_attr->priority = 0;
- udp = (void *)((uintptr_t)flow->ibv_attr + flow->offset);
- *udp = (struct ibv_exp_flow_spec_tcp_udp) {
- .type = flow->inner | IBV_EXP_FLOW_SPEC_UDP,
- .size = udp_size,
- };
- if (!spec)
- return 0;
- if (!mask)
- mask = default_mask;
- 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;
+ int ret;
+
+ ret = flow_drv_query(dev, flow, actions, data, error);
+ if (ret < 0)
+ return ret;
return 0;
}
/**
- * Convert TCP item to Verbs specification.
+ * Convert a flow director filter to a generic flow.
*
- * @param item[in]
- * Item specification.
- * @param default_mask[in]
- * Default bit-masks to use when item->mask is not provided.
- * @param data[in, out]
- * User structure.
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param fdir_filter
+ * Flow director filter to add.
+ * @param attributes
+ * Generic flow parameters structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
*/
static int
-mlx5_flow_create_tcp(const struct rte_flow_item *item,
- const void *default_mask,
- void *data)
+flow_fdir_filter_convert(struct rte_eth_dev *dev,
+ const struct rte_eth_fdir_filter *fdir_filter,
+ struct mlx5_fdir *attributes)
{
- const struct rte_flow_item_tcp *spec = item->spec;
- const struct rte_flow_item_tcp *mask = item->mask;
- struct mlx5_flow *flow = (struct mlx5_flow *)data;
- struct ibv_exp_flow_spec_tcp_udp *tcp;
- unsigned int tcp_size = sizeof(struct ibv_exp_flow_spec_tcp_udp);
-
- ++flow->ibv_attr->num_of_specs;
- flow->ibv_attr->priority = 0;
- tcp = (void *)((uintptr_t)flow->ibv_attr + flow->offset);
- *tcp = (struct ibv_exp_flow_spec_tcp_udp) {
- .type = flow->inner | IBV_EXP_FLOW_SPEC_TCP,
- .size = tcp_size,
+ struct mlx5_priv *priv = dev->data->dev_private;
+ const struct rte_eth_fdir_input *input = &fdir_filter->input;
+ const struct rte_eth_fdir_masks *mask =
+ &dev->data->dev_conf.fdir_conf.mask;
+
+ /* Validate queue number. */
+ if (fdir_filter->action.rx_queue >= priv->rxqs_n) {
+ DRV_LOG(ERR, "port %u invalid queue number %d",
+ dev->data->port_id, fdir_filter->action.rx_queue);
+ rte_errno = EINVAL;
+ return -rte_errno;
+ }
+ attributes->attr.ingress = 1;
+ attributes->items[0] = (struct rte_flow_item) {
+ .type = RTE_FLOW_ITEM_TYPE_ETH,
+ .spec = &attributes->l2,
+ .mask = &attributes->l2_mask,
};
- if (!spec)
- return 0;
- if (!mask)
- mask = default_mask;
- 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;
+ switch (fdir_filter->action.behavior) {
+ case RTE_ETH_FDIR_ACCEPT:
+ attributes->actions[0] = (struct rte_flow_action){
+ .type = RTE_FLOW_ACTION_TYPE_QUEUE,
+ .conf = &attributes->queue,
+ };
+ break;
+ case RTE_ETH_FDIR_REJECT:
+ attributes->actions[0] = (struct rte_flow_action){
+ .type = RTE_FLOW_ACTION_TYPE_DROP,
+ };
+ break;
+ default:
+ DRV_LOG(ERR, "port %u invalid behavior %d",
+ dev->data->port_id,
+ fdir_filter->action.behavior);
+ rte_errno = ENOTSUP;
+ return -rte_errno;
+ }
+ attributes->queue.index = fdir_filter->action.rx_queue;
+ /* Handle L3. */
+ switch (fdir_filter->input.flow_type) {
+ case RTE_ETH_FLOW_NONFRAG_IPV4_UDP:
+ case RTE_ETH_FLOW_NONFRAG_IPV4_TCP:
+ case RTE_ETH_FLOW_NONFRAG_IPV4_OTHER:
+ attributes->l3.ipv4.hdr = (struct rte_ipv4_hdr){
+ .src_addr = input->flow.ip4_flow.src_ip,
+ .dst_addr = input->flow.ip4_flow.dst_ip,
+ .time_to_live = input->flow.ip4_flow.ttl,
+ .type_of_service = input->flow.ip4_flow.tos,
+ };
+ attributes->l3_mask.ipv4.hdr = (struct rte_ipv4_hdr){
+ .src_addr = mask->ipv4_mask.src_ip,
+ .dst_addr = mask->ipv4_mask.dst_ip,
+ .time_to_live = mask->ipv4_mask.ttl,
+ .type_of_service = mask->ipv4_mask.tos,
+ .next_proto_id = mask->ipv4_mask.proto,
+ };
+ attributes->items[1] = (struct rte_flow_item){
+ .type = RTE_FLOW_ITEM_TYPE_IPV4,
+ .spec = &attributes->l3,
+ .mask = &attributes->l3_mask,
+ };
+ break;
+ case RTE_ETH_FLOW_NONFRAG_IPV6_UDP:
+ case RTE_ETH_FLOW_NONFRAG_IPV6_TCP:
+ case RTE_ETH_FLOW_NONFRAG_IPV6_OTHER:
+ attributes->l3.ipv6.hdr = (struct rte_ipv6_hdr){
+ .hop_limits = input->flow.ipv6_flow.hop_limits,
+ .proto = input->flow.ipv6_flow.proto,
+ };
+
+ memcpy(attributes->l3.ipv6.hdr.src_addr,
+ input->flow.ipv6_flow.src_ip,
+ RTE_DIM(attributes->l3.ipv6.hdr.src_addr));
+ memcpy(attributes->l3.ipv6.hdr.dst_addr,
+ input->flow.ipv6_flow.dst_ip,
+ RTE_DIM(attributes->l3.ipv6.hdr.src_addr));
+ memcpy(attributes->l3_mask.ipv6.hdr.src_addr,
+ mask->ipv6_mask.src_ip,
+ RTE_DIM(attributes->l3_mask.ipv6.hdr.src_addr));
+ memcpy(attributes->l3_mask.ipv6.hdr.dst_addr,
+ mask->ipv6_mask.dst_ip,
+ RTE_DIM(attributes->l3_mask.ipv6.hdr.src_addr));
+ attributes->items[1] = (struct rte_flow_item){
+ .type = RTE_FLOW_ITEM_TYPE_IPV6,
+ .spec = &attributes->l3,
+ .mask = &attributes->l3_mask,
+ };
+ break;
+ default:
+ DRV_LOG(ERR, "port %u invalid flow type%d",
+ dev->data->port_id, fdir_filter->input.flow_type);
+ rte_errno = ENOTSUP;
+ return -rte_errno;
+ }
+ /* Handle L4. */
+ switch (fdir_filter->input.flow_type) {
+ case RTE_ETH_FLOW_NONFRAG_IPV4_UDP:
+ attributes->l4.udp.hdr = (struct rte_udp_hdr){
+ .src_port = input->flow.udp4_flow.src_port,
+ .dst_port = input->flow.udp4_flow.dst_port,
+ };
+ attributes->l4_mask.udp.hdr = (struct rte_udp_hdr){
+ .src_port = mask->src_port_mask,
+ .dst_port = mask->dst_port_mask,
+ };
+ attributes->items[2] = (struct rte_flow_item){
+ .type = RTE_FLOW_ITEM_TYPE_UDP,
+ .spec = &attributes->l4,
+ .mask = &attributes->l4_mask,
+ };
+ break;
+ case RTE_ETH_FLOW_NONFRAG_IPV4_TCP:
+ attributes->l4.tcp.hdr = (struct rte_tcp_hdr){
+ .src_port = input->flow.tcp4_flow.src_port,
+ .dst_port = input->flow.tcp4_flow.dst_port,
+ };
+ attributes->l4_mask.tcp.hdr = (struct rte_tcp_hdr){
+ .src_port = mask->src_port_mask,
+ .dst_port = mask->dst_port_mask,
+ };
+ attributes->items[2] = (struct rte_flow_item){
+ .type = RTE_FLOW_ITEM_TYPE_TCP,
+ .spec = &attributes->l4,
+ .mask = &attributes->l4_mask,
+ };
+ break;
+ case RTE_ETH_FLOW_NONFRAG_IPV6_UDP:
+ attributes->l4.udp.hdr = (struct rte_udp_hdr){
+ .src_port = input->flow.udp6_flow.src_port,
+ .dst_port = input->flow.udp6_flow.dst_port,
+ };
+ attributes->l4_mask.udp.hdr = (struct rte_udp_hdr){
+ .src_port = mask->src_port_mask,
+ .dst_port = mask->dst_port_mask,
+ };
+ attributes->items[2] = (struct rte_flow_item){
+ .type = RTE_FLOW_ITEM_TYPE_UDP,
+ .spec = &attributes->l4,
+ .mask = &attributes->l4_mask,
+ };
+ break;
+ case RTE_ETH_FLOW_NONFRAG_IPV6_TCP:
+ attributes->l4.tcp.hdr = (struct rte_tcp_hdr){
+ .src_port = input->flow.tcp6_flow.src_port,
+ .dst_port = input->flow.tcp6_flow.dst_port,
+ };
+ attributes->l4_mask.tcp.hdr = (struct rte_tcp_hdr){
+ .src_port = mask->src_port_mask,
+ .dst_port = mask->dst_port_mask,
+ };
+ attributes->items[2] = (struct rte_flow_item){
+ .type = RTE_FLOW_ITEM_TYPE_TCP,
+ .spec = &attributes->l4,
+ .mask = &attributes->l4_mask,
+ };
+ break;
+ case RTE_ETH_FLOW_NONFRAG_IPV4_OTHER:
+ case RTE_ETH_FLOW_NONFRAG_IPV6_OTHER:
+ break;
+ default:
+ DRV_LOG(ERR, "port %u invalid flow type%d",
+ dev->data->port_id, fdir_filter->input.flow_type);
+ rte_errno = ENOTSUP;
+ return -rte_errno;
+ }
return 0;
}
+#define FLOW_FDIR_CMP(f1, f2, fld) \
+ memcmp(&(f1)->fld, &(f2)->fld, sizeof(f1->fld))
+
/**
- * Convert VXLAN item to Verbs specification.
+ * Compare two FDIR flows. If items and actions are identical, the two flows are
+ * regarded as same.
*
- * @param item[in]
- * Item specification.
- * @param default_mask[in]
- * Default bit-masks to use when item->mask is not provided.
- * @param data[in, out]
- * User structure.
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param f1
+ * FDIR flow to compare.
+ * @param f2
+ * FDIR flow to compare.
+ *
+ * @return
+ * Zero on match, 1 otherwise.
*/
static int
-mlx5_flow_create_vxlan(const struct rte_flow_item *item,
- const void *default_mask,
- void *data)
+flow_fdir_cmp(const struct mlx5_fdir *f1, const struct mlx5_fdir *f2)
{
- const struct rte_flow_item_vxlan *spec = item->spec;
- const struct rte_flow_item_vxlan *mask = item->mask;
- struct mlx5_flow *flow = (struct mlx5_flow *)data;
- struct ibv_exp_flow_spec_tunnel *vxlan;
- unsigned int size = sizeof(struct ibv_exp_flow_spec_tunnel);
- union vni {
- uint32_t vlan_id;
- uint8_t vni[4];
- } id;
-
- ++flow->ibv_attr->num_of_specs;
- flow->ibv_attr->priority = 0;
- id.vni[0] = 0;
- vxlan = (void *)((uintptr_t)flow->ibv_attr + flow->offset);
- *vxlan = (struct ibv_exp_flow_spec_tunnel) {
- .type = flow->inner | IBV_EXP_FLOW_SPEC_VXLAN_TUNNEL,
- .size = size,
- };
- flow->inner = IBV_EXP_FLOW_SPEC_INNER;
- if (!spec)
- return 0;
- if (!mask)
- mask = default_mask;
- 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 (FLOW_FDIR_CMP(f1, f2, attr) ||
+ FLOW_FDIR_CMP(f1, f2, l2) ||
+ FLOW_FDIR_CMP(f1, f2, l2_mask) ||
+ FLOW_FDIR_CMP(f1, f2, l3) ||
+ FLOW_FDIR_CMP(f1, f2, l3_mask) ||
+ FLOW_FDIR_CMP(f1, f2, l4) ||
+ FLOW_FDIR_CMP(f1, f2, l4_mask) ||
+ FLOW_FDIR_CMP(f1, f2, actions[0].type))
+ return 1;
+ if (f1->actions[0].type == RTE_FLOW_ACTION_TYPE_QUEUE &&
+ FLOW_FDIR_CMP(f1, f2, queue))
+ return 1;
return 0;
}
/**
- * Convert mark/flag action to Verbs specification.
+ * Search device flow list to find out a matched FDIR flow.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param fdir_flow
+ * FDIR flow to lookup.
*
- * @param flow
- * Pointer to MLX5 flow structure.
- * @param mark_id
- * Mark identifier.
+ * @return
+ * Pointer of flow if found, NULL otherwise.
*/
-static int
-mlx5_flow_create_flag_mark(struct mlx5_flow *flow, uint32_t mark_id)
+static struct rte_flow *
+flow_fdir_filter_lookup(struct rte_eth_dev *dev, struct mlx5_fdir *fdir_flow)
{
- struct ibv_exp_flow_spec_action_tag *tag;
- unsigned int size = sizeof(struct ibv_exp_flow_spec_action_tag);
-
- tag = (void *)((uintptr_t)flow->ibv_attr + flow->offset);
- *tag = (struct ibv_exp_flow_spec_action_tag){
- .type = IBV_EXP_FLOW_SPEC_ACTION_TAG,
- .size = size,
- .tag_id = mlx5_flow_mark_set(mark_id),
- };
- ++flow->ibv_attr->num_of_specs;
- return 0;
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct rte_flow *flow = NULL;
+
+ assert(fdir_flow);
+ TAILQ_FOREACH(flow, &priv->flows, next) {
+ if (flow->fdir && !flow_fdir_cmp(flow->fdir, fdir_flow)) {
+ DRV_LOG(DEBUG, "port %u found FDIR flow %p",
+ dev->data->port_id, (void *)flow);
+ break;
+ }
+ }
+ return flow;
}
/**
- * Complete flow rule creation.
- *
- * @param priv
- * Pointer to private structure.
- * @param ibv_attr
- * Verbs flow attributes.
- * @param action
- * Target action structure.
- * @param[out] error
- * Perform verbose error reporting if not NULL.
+ * Add new flow director filter and store it in list.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param fdir_filter
+ * Flow director filter to add.
*
* @return
- * A flow if the rule could be created.
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
*/
-static struct rte_flow *
-priv_flow_create_action_queue(struct priv *priv,
- struct ibv_exp_flow_attr *ibv_attr,
- struct mlx5_flow_action *action,
- struct rte_flow_error *error)
+static int
+flow_fdir_filter_add(struct rte_eth_dev *dev,
+ const struct rte_eth_fdir_filter *fdir_filter)
{
- struct rxq_ctrl *rxq;
- struct rte_flow *rte_flow;
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_fdir *fdir_flow;
+ struct rte_flow *flow;
+ int ret;
- assert(priv->pd);
- assert(priv->ctx);
- rte_flow = rte_calloc(__func__, 1, sizeof(*rte_flow), 0);
- if (!rte_flow) {
- rte_flow_error_set(error, ENOMEM, RTE_FLOW_ERROR_TYPE_HANDLE,
- NULL, "cannot allocate flow memory");
- return NULL;
- }
- if (action->drop) {
- rte_flow->cq =
- ibv_exp_create_cq(priv->ctx, 1, NULL, NULL, 0,
- &(struct ibv_exp_cq_init_attr){
- .comp_mask = 0,
- });
- if (!rte_flow->cq) {
- rte_flow_error_set(error, ENOMEM,
- RTE_FLOW_ERROR_TYPE_HANDLE,
- NULL, "cannot allocate CQ");
- goto error;
- }
- rte_flow->wq = ibv_exp_create_wq(priv->ctx,
- &(struct ibv_exp_wq_init_attr){
- .wq_type = IBV_EXP_WQT_RQ,
- .max_recv_wr = 1,
- .max_recv_sge = 1,
- .pd = priv->pd,
- .cq = rte_flow->cq,
- });
- if (!rte_flow->wq) {
- rte_flow_error_set(error, ENOMEM,
- RTE_FLOW_ERROR_TYPE_HANDLE,
- NULL, "cannot allocate WQ");
- goto error;
- }
- } else {
- rxq = container_of((*priv->rxqs)[action->queue_id],
- struct rxq_ctrl, rxq);
- rte_flow->rxq = &rxq->rxq;
- rxq->rxq.mark |= action->mark;
- rte_flow->wq = rxq->wq;
+ fdir_flow = rte_zmalloc(__func__, sizeof(*fdir_flow), 0);
+ if (!fdir_flow) {
+ rte_errno = ENOMEM;
+ return -rte_errno;
}
- rte_flow->mark = action->mark;
- rte_flow->ibv_attr = ibv_attr;
- rte_flow->ind_table = ibv_exp_create_rwq_ind_table(
- priv->ctx,
- &(struct ibv_exp_rwq_ind_table_init_attr){
- .pd = priv->pd,
- .log_ind_tbl_size = 0,
- .ind_tbl = &rte_flow->wq,
- .comp_mask = 0,
- });
- if (!rte_flow->ind_table) {
- rte_flow_error_set(error, ENOMEM, RTE_FLOW_ERROR_TYPE_HANDLE,
- NULL, "cannot allocate indirection table");
+ ret = flow_fdir_filter_convert(dev, fdir_filter, fdir_flow);
+ if (ret)
goto error;
- }
- rte_flow->qp = ibv_exp_create_qp(
- priv->ctx,
- &(struct ibv_exp_qp_init_attr){
- .qp_type = IBV_QPT_RAW_PACKET,
- .comp_mask =
- IBV_EXP_QP_INIT_ATTR_PD |
- IBV_EXP_QP_INIT_ATTR_PORT |
- IBV_EXP_QP_INIT_ATTR_RX_HASH,
- .pd = priv->pd,
- .rx_hash_conf = &(struct ibv_exp_rx_hash_conf){
- .rx_hash_function =
- IBV_EXP_RX_HASH_FUNC_TOEPLITZ,
- .rx_hash_key_len = rss_hash_default_key_len,
- .rx_hash_key = rss_hash_default_key,
- .rx_hash_fields_mask = 0,
- .rwq_ind_tbl = rte_flow->ind_table,
- },
- .port_num = priv->port,
- });
- if (!rte_flow->qp) {
- rte_flow_error_set(error, ENOMEM, RTE_FLOW_ERROR_TYPE_HANDLE,
- NULL, "cannot allocate QP");
+ flow = flow_fdir_filter_lookup(dev, fdir_flow);
+ if (flow) {
+ rte_errno = EEXIST;
goto error;
}
- if (!priv->started)
- return rte_flow;
- rte_flow->ibv_flow = ibv_exp_create_flow(rte_flow->qp,
- rte_flow->ibv_attr);
- if (!rte_flow->ibv_flow) {
- rte_flow_error_set(error, ENOMEM, RTE_FLOW_ERROR_TYPE_HANDLE,
- NULL, "flow rule creation failure");
+ flow = flow_list_create(dev, &priv->flows, &fdir_flow->attr,
+ fdir_flow->items, fdir_flow->actions, NULL);
+ if (!flow)
goto error;
- }
- return rte_flow;
+ assert(!flow->fdir);
+ flow->fdir = fdir_flow;
+ DRV_LOG(DEBUG, "port %u created FDIR flow %p",
+ dev->data->port_id, (void *)flow);
+ return 0;
error:
- assert(rte_flow);
- if (rte_flow->qp)
- ibv_destroy_qp(rte_flow->qp);
- if (rte_flow->ind_table)
- ibv_exp_destroy_rwq_ind_table(rte_flow->ind_table);
- if (!rte_flow->rxq && rte_flow->wq)
- ibv_exp_destroy_wq(rte_flow->wq);
- if (!rte_flow->rxq && rte_flow->cq)
- ibv_destroy_cq(rte_flow->cq);
- rte_free(rte_flow);
- return NULL;
+ rte_free(fdir_flow);
+ return -rte_errno;
}
/**
- * Convert a flow.
+ * Delete specific filter.
*
- * @param priv
- * Pointer to private structure.
- * @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.
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param fdir_filter
+ * Filter to be deleted.
*
* @return
- * A flow on success, NULL otherwise.
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
*/
-static struct rte_flow *
-priv_flow_create(struct priv *priv,
- const struct rte_flow_attr *attr,
- const struct rte_flow_item items[],
- const struct rte_flow_action actions[],
- struct rte_flow_error *error)
+static int
+flow_fdir_filter_delete(struct rte_eth_dev *dev,
+ const struct rte_eth_fdir_filter *fdir_filter)
{
- struct rte_flow *rte_flow;
- struct mlx5_flow_action action;
- struct mlx5_flow flow = { .offset = sizeof(struct ibv_exp_flow_attr), };
- int err;
-
- err = priv_flow_validate(priv, attr, items, actions, error, &flow);
- if (err)
- goto exit;
- flow.ibv_attr = rte_malloc(__func__, flow.offset, 0);
- flow.offset = sizeof(struct ibv_exp_flow_attr);
- if (!flow.ibv_attr) {
- rte_flow_error_set(error, ENOMEM, RTE_FLOW_ERROR_TYPE_HANDLE,
- NULL, "cannot allocate ibv_attr memory");
- goto exit;
- }
- *flow.ibv_attr = (struct ibv_exp_flow_attr){
- .type = IBV_EXP_FLOW_ATTR_NORMAL,
- .size = sizeof(struct ibv_exp_flow_attr),
- .priority = attr->priority,
- .num_of_specs = 0,
- .port = 0,
- .flags = 0,
- .reserved = 0,
- };
- flow.inner = 0;
- claim_zero(priv_flow_validate(priv, attr, items, actions,
- error, &flow));
- action = (struct mlx5_flow_action){
- .queue = 0,
- .drop = 0,
- .mark = 0,
- .mark_id = MLX5_FLOW_MARK_DEFAULT,
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct rte_flow *flow;
+ struct mlx5_fdir fdir_flow = {
+ .attr.group = 0,
};
- for (; actions->type != RTE_FLOW_ACTION_TYPE_END; ++actions) {
- if (actions->type == RTE_FLOW_ACTION_TYPE_VOID) {
- continue;
- } else if (actions->type == RTE_FLOW_ACTION_TYPE_QUEUE) {
- action.queue = 1;
- action.queue_id =
- ((const struct rte_flow_action_queue *)
- actions->conf)->index;
- } else if (actions->type == RTE_FLOW_ACTION_TYPE_DROP) {
- action.drop = 1;
- action.mark = 0;
- } else if (actions->type == RTE_FLOW_ACTION_TYPE_MARK) {
- const struct rte_flow_action_mark *mark =
- (const struct rte_flow_action_mark *)
- actions->conf;
-
- if (mark)
- action.mark_id = mark->id;
- action.mark = !action.drop;
- } else if (actions->type == RTE_FLOW_ACTION_TYPE_FLAG) {
- action.mark = 1;
- } else {
- rte_flow_error_set(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ACTION,
- actions, "unsupported action");
- goto exit;
- }
- }
- if (action.mark) {
- mlx5_flow_create_flag_mark(&flow, action.mark_id);
- flow.offset += sizeof(struct ibv_exp_flow_spec_action_tag);
+ int ret;
+
+ ret = flow_fdir_filter_convert(dev, fdir_filter, &fdir_flow);
+ if (ret)
+ return -rte_errno;
+ flow = flow_fdir_filter_lookup(dev, &fdir_flow);
+ if (!flow) {
+ rte_errno = ENOENT;
+ return -rte_errno;
}
- rte_flow = priv_flow_create_action_queue(priv, flow.ibv_attr,
- &action, error);
- if (!rte_flow)
- goto exit;
- return rte_flow;
-exit:
- rte_free(flow.ibv_attr);
- return NULL;
+ flow_list_destroy(dev, &priv->flows, flow);
+ DRV_LOG(DEBUG, "port %u deleted FDIR flow %p",
+ dev->data->port_id, (void *)flow);
+ return 0;
}
/**
- * Create a flow.
+ * Update queue for specific filter.
*
- * @see rte_flow_create()
- * @see rte_flow_ops
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param fdir_filter
+ * Filter to be updated.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
*/
-struct rte_flow *
-mlx5_flow_create(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)
+static int
+flow_fdir_filter_update(struct rte_eth_dev *dev,
+ const struct rte_eth_fdir_filter *fdir_filter)
{
- struct priv *priv = dev->data->dev_private;
- struct rte_flow *flow;
+ int ret;
- priv_lock(priv);
- flow = priv_flow_create(priv, attr, items, actions, error);
- if (flow) {
- LIST_INSERT_HEAD(&priv->flows, flow, next);
- DEBUG("Flow created %p", (void *)flow);
- }
- priv_unlock(priv);
- return flow;
+ ret = flow_fdir_filter_delete(dev, fdir_filter);
+ if (ret)
+ return ret;
+ return flow_fdir_filter_add(dev, fdir_filter);
}
/**
- * Destroy a flow.
+ * Flush all filters.
*
- * @param priv
- * Pointer to private structure.
- * @param[in] flow
- * Flow to destroy.
+ * @param dev
+ * Pointer to Ethernet device.
*/
static void
-priv_flow_destroy(struct priv *priv,
- struct rte_flow *flow)
+flow_fdir_filter_flush(struct rte_eth_dev *dev)
{
- (void)priv;
- LIST_REMOVE(flow, next);
- if (flow->ibv_flow)
- claim_zero(ibv_exp_destroy_flow(flow->ibv_flow));
- if (flow->qp)
- claim_zero(ibv_destroy_qp(flow->qp));
- if (flow->ind_table)
- claim_zero(ibv_exp_destroy_rwq_ind_table(flow->ind_table));
- if (!flow->rxq && flow->wq)
- claim_zero(ibv_exp_destroy_wq(flow->wq));
- if (!flow->rxq && flow->cq)
- claim_zero(ibv_destroy_cq(flow->cq));
- if (flow->mark) {
- struct rte_flow *tmp;
- uint32_t mark_n = 0;
-
- for (tmp = LIST_FIRST(&priv->flows);
- tmp;
- tmp = LIST_NEXT(tmp, next)) {
- if ((flow->rxq == tmp->rxq) && tmp->mark)
- ++mark_n;
- }
- flow->rxq->mark = !!mark_n;
- }
- rte_free(flow->ibv_attr);
- DEBUG("Flow destroyed %p", (void *)flow);
- rte_free(flow);
+ struct mlx5_priv *priv = dev->data->dev_private;
+
+ mlx5_flow_list_flush(dev, &priv->flows);
}
/**
- * Destroy a flow.
+ * Get flow director information.
*
- * @see rte_flow_destroy()
- * @see rte_flow_ops
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param[out] fdir_info
+ * Resulting flow director information.
*/
-int
-mlx5_flow_destroy(struct rte_eth_dev *dev,
- struct rte_flow *flow,
- struct rte_flow_error *error)
+static void
+flow_fdir_info_get(struct rte_eth_dev *dev, struct rte_eth_fdir_info *fdir_info)
{
- struct priv *priv = dev->data->dev_private;
-
- (void)error;
- priv_lock(priv);
- priv_flow_destroy(priv, flow);
- priv_unlock(priv);
- return 0;
+ struct rte_eth_fdir_masks *mask =
+ &dev->data->dev_conf.fdir_conf.mask;
+
+ fdir_info->mode = dev->data->dev_conf.fdir_conf.mode;
+ fdir_info->guarant_spc = 0;
+ rte_memcpy(&fdir_info->mask, mask, sizeof(fdir_info->mask));
+ fdir_info->max_flexpayload = 0;
+ fdir_info->flow_types_mask[0] = 0;
+ fdir_info->flex_payload_unit = 0;
+ fdir_info->max_flex_payload_segment_num = 0;
+ fdir_info->flex_payload_limit = 0;
+ memset(&fdir_info->flex_conf, 0, sizeof(fdir_info->flex_conf));
}
/**
- * Destroy all flows.
+ * Deal with flow director operations.
*
- * @param priv
- * Pointer to private structure.
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param filter_op
+ * Operation to perform.
+ * @param arg
+ * Pointer to operation-specific structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
*/
-static void
-priv_flow_flush(struct priv *priv)
+static int
+flow_fdir_ctrl_func(struct rte_eth_dev *dev, enum rte_filter_op filter_op,
+ void *arg)
{
- while (!LIST_EMPTY(&priv->flows)) {
- struct rte_flow *flow;
+ enum rte_fdir_mode fdir_mode =
+ dev->data->dev_conf.fdir_conf.mode;
- flow = LIST_FIRST(&priv->flows);
- priv_flow_destroy(priv, flow);
+ if (filter_op == RTE_ETH_FILTER_NOP)
+ return 0;
+ if (fdir_mode != RTE_FDIR_MODE_PERFECT &&
+ fdir_mode != RTE_FDIR_MODE_PERFECT_MAC_VLAN) {
+ DRV_LOG(ERR, "port %u flow director mode %d not supported",
+ dev->data->port_id, fdir_mode);
+ rte_errno = EINVAL;
+ return -rte_errno;
}
+ switch (filter_op) {
+ case RTE_ETH_FILTER_ADD:
+ return flow_fdir_filter_add(dev, arg);
+ case RTE_ETH_FILTER_UPDATE:
+ return flow_fdir_filter_update(dev, arg);
+ case RTE_ETH_FILTER_DELETE:
+ return flow_fdir_filter_delete(dev, arg);
+ case RTE_ETH_FILTER_FLUSH:
+ flow_fdir_filter_flush(dev);
+ break;
+ case RTE_ETH_FILTER_INFO:
+ flow_fdir_info_get(dev, arg);
+ break;
+ default:
+ DRV_LOG(DEBUG, "port %u unknown operation %u",
+ dev->data->port_id, filter_op);
+ rte_errno = EINVAL;
+ return -rte_errno;
+ }
+ return 0;
}
/**
- * Destroy all flows.
+ * Manage filter operations.
*
- * @see rte_flow_flush()
- * @see rte_flow_ops
+ * @param dev
+ * Pointer to Ethernet device structure.
+ * @param filter_type
+ * Filter type.
+ * @param filter_op
+ * Operation to perform.
+ * @param arg
+ * Pointer to operation-specific structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
*/
int
-mlx5_flow_flush(struct rte_eth_dev *dev,
- struct rte_flow_error *error)
+mlx5_dev_filter_ctrl(struct rte_eth_dev *dev,
+ enum rte_filter_type filter_type,
+ enum rte_filter_op filter_op,
+ void *arg)
{
- struct priv *priv = dev->data->dev_private;
-
- (void)error;
- priv_lock(priv);
- priv_flow_flush(priv);
- priv_unlock(priv);
+ switch (filter_type) {
+ case RTE_ETH_FILTER_GENERIC:
+ if (filter_op != RTE_ETH_FILTER_GET) {
+ rte_errno = EINVAL;
+ return -rte_errno;
+ }
+ *(const void **)arg = &mlx5_flow_ops;
+ return 0;
+ case RTE_ETH_FILTER_FDIR:
+ return flow_fdir_ctrl_func(dev, filter_op, arg);
+ default:
+ DRV_LOG(ERR, "port %u filter type (%d) not supported",
+ dev->data->port_id, filter_type);
+ rte_errno = ENOTSUP;
+ return -rte_errno;
+ }
return 0;
}
+#define MLX5_POOL_QUERY_FREQ_US 1000000
+
/**
- * Remove all flows.
- *
- * Called by dev_stop() to remove all flows.
+ * Set the periodic procedure for triggering asynchronous batch queries for all
+ * the counter pools.
*
- * @param priv
- * Pointer to private structure.
+ * @param[in] sh
+ * Pointer to mlx5_ibv_shared object.
*/
void
-priv_flow_stop(struct priv *priv)
+mlx5_set_query_alarm(struct mlx5_ibv_shared *sh)
{
- struct rte_flow *flow;
-
- for (flow = LIST_FIRST(&priv->flows);
- flow;
- flow = LIST_NEXT(flow, next)) {
- claim_zero(ibv_exp_destroy_flow(flow->ibv_flow));
- flow->ibv_flow = NULL;
- if (flow->mark)
- flow->rxq->mark = 0;
- DEBUG("Flow %p removed", (void *)flow);
+ struct mlx5_pools_container *cont = MLX5_CNT_CONTAINER(sh, 0, 0);
+ uint32_t pools_n = rte_atomic16_read(&cont->n_valid);
+ uint32_t us;
+
+ cont = MLX5_CNT_CONTAINER(sh, 1, 0);
+ pools_n += rte_atomic16_read(&cont->n_valid);
+ us = MLX5_POOL_QUERY_FREQ_US / pools_n;
+ DRV_LOG(DEBUG, "Set alarm for %u pools each %u us\n", pools_n, us);
+ if (rte_eal_alarm_set(us, mlx5_flow_query_alarm, sh)) {
+ sh->cmng.query_thread_on = 0;
+ DRV_LOG(ERR, "Cannot reinitialize query alarm\n");
+ } else {
+ sh->cmng.query_thread_on = 1;
}
}
/**
- * Add all flows.
+ * The periodic procedure for triggering asynchronous batch queries for all the
+ * counter pools. This function is probably called by the host thread.
*
- * @param priv
- * Pointer to private structure.
+ * @param[in] arg
+ * The parameter for the alarm process.
+ */
+void
+mlx5_flow_query_alarm(void *arg)
+{
+ struct mlx5_ibv_shared *sh = arg;
+ struct mlx5_devx_obj *dcs;
+ uint16_t offset;
+ int ret;
+ uint8_t batch = sh->cmng.batch;
+ uint16_t pool_index = sh->cmng.pool_index;
+ struct mlx5_pools_container *cont;
+ struct mlx5_pools_container *mcont;
+ struct mlx5_flow_counter_pool *pool;
+
+ if (sh->cmng.pending_queries >= MLX5_MAX_PENDING_QUERIES)
+ goto set_alarm;
+next_container:
+ cont = MLX5_CNT_CONTAINER(sh, batch, 1);
+ mcont = MLX5_CNT_CONTAINER(sh, batch, 0);
+ /* Check if resize was done and need to flip a container. */
+ if (cont != mcont) {
+ if (cont->pools) {
+ /* Clean the old container. */
+ rte_free(cont->pools);
+ memset(cont, 0, sizeof(*cont));
+ }
+ rte_cio_wmb();
+ /* Flip the host container. */
+ sh->cmng.mhi[batch] ^= (uint8_t)2;
+ cont = mcont;
+ }
+ if (!cont->pools) {
+ /* 2 empty containers case is unexpected. */
+ if (unlikely(batch != sh->cmng.batch))
+ goto set_alarm;
+ batch ^= 0x1;
+ pool_index = 0;
+ goto next_container;
+ }
+ pool = cont->pools[pool_index];
+ if (pool->raw_hw)
+ /* There is a pool query in progress. */
+ goto set_alarm;
+ pool->raw_hw =
+ LIST_FIRST(&sh->cmng.free_stat_raws);
+ if (!pool->raw_hw)
+ /* No free counter statistics raw memory. */
+ goto set_alarm;
+ dcs = (struct mlx5_devx_obj *)(uintptr_t)rte_atomic64_read
+ (&pool->a64_dcs);
+ offset = batch ? 0 : dcs->id % MLX5_COUNTERS_PER_POOL;
+ ret = mlx5_devx_cmd_flow_counter_query(dcs, 0, MLX5_COUNTERS_PER_POOL -
+ offset, NULL, NULL,
+ pool->raw_hw->mem_mng->dm->id,
+ (void *)(uintptr_t)
+ (pool->raw_hw->data + offset),
+ sh->devx_comp,
+ (uint64_t)(uintptr_t)pool);
+ if (ret) {
+ DRV_LOG(ERR, "Failed to trigger asynchronous query for dcs ID"
+ " %d\n", pool->min_dcs->id);
+ pool->raw_hw = NULL;
+ goto set_alarm;
+ }
+ pool->raw_hw->min_dcs_id = dcs->id;
+ LIST_REMOVE(pool->raw_hw, next);
+ sh->cmng.pending_queries++;
+ pool_index++;
+ if (pool_index >= rte_atomic16_read(&cont->n_valid)) {
+ batch ^= 0x1;
+ pool_index = 0;
+ }
+set_alarm:
+ sh->cmng.batch = batch;
+ sh->cmng.pool_index = pool_index;
+ mlx5_set_query_alarm(sh);
+}
+
+/**
+ * Handler for the HW respond about ready values from an asynchronous batch
+ * query. This function is probably called by the host thread.
*
- * @return
- * 0 on success, a errno value otherwise and rte_errno is set.
+ * @param[in] sh
+ * The pointer to the shared IB device context.
+ * @param[in] async_id
+ * The Devx async ID.
+ * @param[in] status
+ * The status of the completion.
*/
-int
-priv_flow_start(struct priv *priv)
+void
+mlx5_flow_async_pool_query_handle(struct mlx5_ibv_shared *sh,
+ uint64_t async_id, int status)
{
- struct rte_flow *flow;
+ struct mlx5_flow_counter_pool *pool =
+ (struct mlx5_flow_counter_pool *)(uintptr_t)async_id;
+ struct mlx5_counter_stats_raw *raw_to_free;
- for (flow = LIST_FIRST(&priv->flows);
- flow;
- flow = LIST_NEXT(flow, next)) {
- flow->ibv_flow = ibv_exp_create_flow(flow->qp,
- flow->ibv_attr);
- if (!flow->ibv_flow) {
- DEBUG("Flow %p cannot be applied", (void *)flow);
- rte_errno = EINVAL;
- return rte_errno;
- }
- DEBUG("Flow %p applied", (void *)flow);
- if (flow->rxq)
- flow->rxq->mark |= flow->mark;
+ if (unlikely(status)) {
+ raw_to_free = pool->raw_hw;
+ } else {
+ raw_to_free = pool->raw;
+ rte_spinlock_lock(&pool->sl);
+ pool->raw = pool->raw_hw;
+ rte_spinlock_unlock(&pool->sl);
+ rte_atomic64_add(&pool->query_gen, 1);
+ /* Be sure the new raw counters data is updated in memory. */
+ rte_cio_wmb();
}
- return 0;
+ LIST_INSERT_HEAD(&sh->cmng.free_stat_raws, raw_to_free, next);
+ pool->raw_hw = NULL;
+ sh->cmng.pending_queries--;
}