-/*-
- * 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 <sys/queue.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_eth_ctrl.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_prm.h"
-
-/* Define minimal priority for control plane flows. */
-#define MLX5_CTRL_FLOW_PRIORITY 4
-
-static int
-mlx5_flow_create_eth(const struct rte_flow_item *item,
- const void *default_mask,
- void *data);
-
-static int
-mlx5_flow_create_vlan(const struct rte_flow_item *item,
- const void *default_mask,
- void *data);
-
-static int
-mlx5_flow_create_ipv4(const struct rte_flow_item *item,
- const void *default_mask,
- void *data);
-
-static int
-mlx5_flow_create_ipv6(const struct rte_flow_item *item,
- const void *default_mask,
- void *data);
-
-static int
-mlx5_flow_create_udp(const struct rte_flow_item *item,
- const void *default_mask,
- void *data);
-
-static int
-mlx5_flow_create_tcp(const struct rte_flow_item *item,
- const void *default_mask,
- void *data);
-
-static int
-mlx5_flow_create_vxlan(const struct rte_flow_item *item,
- const void *default_mask,
- void *data);
-
-/** Structure for Drop queue. */
-struct mlx5_hrxq_drop {
- struct ibv_rwq_ind_table *ind_table; /**< Indirection table. */
- struct ibv_qp *qp; /**< Verbs queue pair. */
- struct ibv_wq *wq; /**< Verbs work queue. */
- struct ibv_cq *cq; /**< Verbs completion queue. */
-};
-
-/* Flows structures. */
-struct mlx5_flow {
- uint64_t hash_fields; /**< Fields that participate in the hash. */
- struct mlx5_hrxq *hrxq; /**< Hash Rx queues. */
-};
-
-/* Drop flows structures. */
-struct mlx5_flow_drop {
- struct mlx5_hrxq_drop hrxq; /**< Drop hash Rx queue. */
+#include "mlx5_glue.h"
+
+/* Dev ops structure defined in mlx5.c */
+extern const struct eth_dev_ops mlx5_dev_ops;
+extern const struct eth_dev_ops mlx5_dev_ops_isolate;
+
+/* Pattern Layer bits. */
+#define MLX5_FLOW_LAYER_OUTER_L2 (1u << 0)
+#define MLX5_FLOW_LAYER_OUTER_L3_IPV4 (1u << 1)
+#define MLX5_FLOW_LAYER_OUTER_L3_IPV6 (1u << 2)
+#define MLX5_FLOW_LAYER_OUTER_L4_UDP (1u << 3)
+#define MLX5_FLOW_LAYER_OUTER_L4_TCP (1u << 4)
+#define MLX5_FLOW_LAYER_OUTER_VLAN (1u << 5)
+/* Masks. */
+#define MLX5_FLOW_LAYER_OUTER_L3 \
+ (MLX5_FLOW_LAYER_OUTER_L3_IPV4 | MLX5_FLOW_LAYER_OUTER_L3_IPV6)
+#define MLX5_FLOW_LAYER_OUTER_L4 \
+ (MLX5_FLOW_LAYER_OUTER_L4_UDP | MLX5_FLOW_LAYER_OUTER_L4_TCP)
+
+/* Actions that modify the fate of matching traffic. */
+#define MLX5_FLOW_FATE_DROP (1u << 0)
+#define MLX5_FLOW_FATE_QUEUE (1u << 1)
+
+/** Handles information leading to a drop fate. */
+struct mlx5_flow_verbs {
+ unsigned int size; /**< Size of the attribute. */
+ struct {
+ struct ibv_flow_attr *attr;
+ /**< Pointer to the Specification buffer. */
+ uint8_t *specs; /**< Pointer to the specifications. */
+ };
+ struct ibv_flow *flow; /**< Verbs flow pointer. */
+ struct mlx5_hrxq *hrxq; /**< Hash Rx queue object. */
};
+/* Flow structure. */
struct rte_flow {
TAILQ_ENTRY(rte_flow) next; /**< Pointer to the next flow structure. */
- uint32_t mark:1; /**< Set if the flow is marked. */
- uint32_t drop:1; /**< Drop queue. */
- struct ibv_flow_attr *ibv_attr; /**< Pointer to Verbs attributes. */
- struct ibv_flow *ibv_flow; /**< Verbs flow. */
- uint16_t queues_n; /**< Number of entries in queue[]. */
- uint16_t (*queues)[]; /**< Queues indexes to use. */
- union {
- struct mlx5_flow frxq; /**< Flow with Rx queue. */
- struct mlx5_flow_drop drxq; /**< Flow with drop Rx queue. */
- };
+ struct rte_flow_attr attributes; /**< User flow attribute. */
+ uint32_t layers;
+ /**< Bit-fields of present layers see MLX5_FLOW_LAYER_*. */
+ uint32_t fate;
+ /**< Bit-fields of present fate see MLX5_FLOW_FATE_*. */
+ struct mlx5_flow_verbs verbs; /* Verbs flow. */
+ uint16_t queue; /**< Destination queue to redirect traffic to. */
};
-/** Static initializer for items. */
-#define ITEMS(...) \
- (const enum rte_flow_item_type []){ \
- __VA_ARGS__, RTE_FLOW_ITEM_TYPE_END, \
- }
+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,
+};
-/** 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;
+/* Convert FDIR request to Generic flow. */
+struct mlx5_fdir {
+ struct rte_flow_attr attr;
+ struct rte_flow_action actions[2];
+ 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_queue queue;
};
-/** 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,
+/* Verbs specification header. */
+struct ibv_spec_header {
+ enum ibv_flow_spec_type type;
+ uint16_t size;
};
-/** 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_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,
- },
- [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_flow_spec_ipv4),
- },
- [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_flow_spec_ipv6),
- },
- [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,
- },
+ /**
+ * Discover the maximum number of priority available.
+ *
+ * @param[in] dev
+ * Pointer to Ethernet device.
+ *
+ * @return
+ * number of supported flow priority on success, a negative errno value
+ * otherwise and rte_errno is set.
+ */
+int
+mlx5_flow_discover_priorities(struct rte_eth_dev *dev)
+{
+ 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,
},
- .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_flow_spec_tcp_udp),
- },
- [RTE_FLOW_ITEM_TYPE_TCP] = {
- .actions = valid_actions,
- .mask = &(const struct rte_flow_item_tcp){
- .hdr = {
- .src_port = -1,
- .dst_port = -1,
- },
+ .eth = {
+ .type = IBV_FLOW_SPEC_ETH,
+ .size = sizeof(struct ibv_flow_spec_eth),
},
- .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_flow_spec_tcp_udp),
- },
- [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",
+ .drop = {
+ .size = sizeof(struct ibv_flow_spec_action_drop),
+ .type = IBV_FLOW_SPEC_ACTION_DROP,
},
- .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_flow_spec_tunnel),
- },
-};
-
-/* Structure to parse actions. */
-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 mark_id; /**< Mark identifier. */
- uint16_t queues[RTE_MAX_QUEUES_PER_PORT]; /**< Queues indexes to use. */
- uint16_t queues_n; /**< Number of entries in queue[]. */
-};
-
-/** Structure to pass to the conversion function. */
-struct mlx5_flow_parse {
- struct ibv_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. */
- uint64_t hash_fields; /**< Fields that participate in the hash. */
- struct mlx5_flow_action actions; /**< Parsed action result. */
-};
+ };
+ struct ibv_flow *flow;
+ struct mlx5_hrxq *drop = mlx5_hrxq_drop_new(dev);
+ uint16_t vprio[] = { 8, 16 };
+ int i;
-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,
- .query = NULL,
- .isolate = mlx5_flow_isolate,
-};
+ 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));
+ }
+ mlx5_hrxq_drop_release(dev);
+ DRV_LOG(INFO, "port %u flow maximum priority: %d",
+ dev->data->port_id, vprio[i - 1]);
+ return vprio[i - 1];
+}
/**
- * Manage filter operations.
+ * Verify the @p attributes will be correctly understood by the NIC and store
+ * them in the @p flow if everything is correct.
*
- * @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.
+ * @param[in] dev
+ * Pointer to Ethernet device.
+ * @param[in] attributes
+ * Pointer to flow attributes
+ * @param[in, out] flow
+ * Pointer to the rte_flow structure.
+ * @param[out] error
+ * Pointer to error structure.
*
* @return
- * 0 on success, negative errno value on failure.
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
*/
-int
-mlx5_dev_filter_ctrl(struct rte_eth_dev *dev,
- enum rte_filter_type filter_type,
- enum rte_filter_op filter_op,
- void *arg)
+static int
+mlx5_flow_attributes(struct rte_eth_dev *dev,
+ const struct rte_flow_attr *attributes,
+ struct rte_flow *flow,
+ struct rte_flow_error *error)
{
- int ret = EINVAL;
-
- if (filter_type == RTE_ETH_FILTER_GENERIC) {
- if (filter_op != RTE_ETH_FILTER_GET)
- return -EINVAL;
- *(const void **)arg = &mlx5_flow_ops;
- return 0;
- }
- ERROR("%p: filter type (%d) not supported",
- (void *)dev, filter_type);
- return -ret;
+ uint32_t priority_max =
+ ((struct priv *)dev->data->dev_private)->config.flow_prio;
+
+ if (attributes->group)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ATTR_GROUP,
+ NULL,
+ "groups is not supported");
+ if (attributes->priority >= priority_max)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ATTR_PRIORITY,
+ NULL,
+ "priority out of range");
+ if (attributes->egress)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ATTR_EGRESS,
+ NULL,
+ "egress is not supported");
+ if (attributes->transfer)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ATTR_TRANSFER,
+ NULL,
+ "transfer is not supported");
+ if (!attributes->ingress)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ATTR_INGRESS,
+ NULL,
+ "ingress attribute is mandatory");
+ flow->attributes = *attributes;
+ return 0;
}
/**
- * 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)
+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, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM,
+ item,
+ "range is not supported");
}
- return ret;
+ return 0;
}
/**
- * Validate a flow supported by the NIC.
+ * Add a verbs specification into @p flow.
*
- * @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.
- *
- * @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
+ * Pointer to flow structure.
+ * @param[in] src
+ * Create specification.
+ * @param[in] size
+ * Size in bytes of the specification to copy.
*/
-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_parse *flow)
+static void
+mlx5_flow_spec_verbs_add(struct rte_flow *flow, void *src, unsigned int size)
{
- const struct mlx5_flow_items *cur_item = mlx5_flow_items;
+ if (flow->verbs.specs) {
+ void *dst;
- (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 && attr->priority != MLX5_CTRL_FLOW_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;
+ dst = (void *)(flow->verbs.specs + flow->verbs.size);
+ memcpy(dst, src, size);
+ ++flow->verbs.attr->num_of_specs;
}
- 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;
-
- if (items->type == RTE_FLOW_ITEM_TYPE_VOID)
- 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 (!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;
- } else if (items->type == RTE_FLOW_ITEM_TYPE_VXLAN) {
- if (flow->inner) {
- rte_flow_error_set(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ITEM,
- items,
- "cannot recognize multiple"
- " VXLAN encapsulations");
- return -rte_errno;
- }
- flow->inner = 1;
- }
- 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) {
- flow->actions.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;
- uint16_t n;
- uint16_t found = 0;
-
- if (!queue || (queue->index > (priv->rxqs_n - 1)))
- goto exit_action_not_supported;
- for (n = 0; n < flow->actions.queues_n; ++n) {
- if (flow->actions.queues[n] == queue->index) {
- found = 1;
- break;
- }
- }
- if (flow->actions.queues_n > 1 && !found) {
- rte_flow_error_set(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ACTION,
- actions,
- "queue action not in RSS queues");
- return -rte_errno;
- }
- if (!found) {
- flow->actions.queue = 1;
- flow->actions.queues_n = 1;
- flow->actions.queues[0] = queue->index;
- }
- } else if (actions->type == RTE_FLOW_ACTION_TYPE_RSS) {
- const struct rte_flow_action_rss *rss =
- (const struct rte_flow_action_rss *)
- actions->conf;
- uint16_t n;
-
- if (!rss || !rss->num) {
- rte_flow_error_set(error, EINVAL,
- RTE_FLOW_ERROR_TYPE_ACTION,
- actions,
- "no valid queues");
- return -rte_errno;
- }
- if (flow->actions.queues_n == 1) {
- uint16_t found = 0;
-
- assert(flow->actions.queues_n);
- for (n = 0; n < rss->num; ++n) {
- if (flow->actions.queues[0] ==
- rss->queue[n]) {
- found = 1;
- break;
- }
- }
- if (!found) {
- rte_flow_error_set(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ACTION,
- actions,
- "queue action not in RSS"
- " queues");
- return -rte_errno;
- }
- }
- for (n = 0; n < rss->num; ++n) {
- if (rss->queue[n] >= priv->rxqs_n) {
- rte_flow_error_set(error, EINVAL,
- RTE_FLOW_ERROR_TYPE_ACTION,
- actions,
- "queue id > number of"
- " queues");
- return -rte_errno;
- }
- }
- flow->actions.queue = 1;
- for (n = 0; n < rss->num; ++n)
- flow->actions.queues[n] = rss->queue[n];
- flow->actions.queues_n = rss->num;
- } 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;
- }
- flow->actions.mark = 1;
- flow->actions.mark_id = mark->id;
- } else if (actions->type == RTE_FLOW_ACTION_TYPE_FLAG) {
- flow->actions.mark = 1;
- } else {
- goto exit_action_not_supported;
- }
- }
- if (flow->actions.mark && !flow->ibv_attr && !flow->actions.drop)
- flow->offset += sizeof(struct ibv_flow_spec_action_tag);
- if (!flow->ibv_attr && flow->actions.drop)
- flow->offset += sizeof(struct ibv_flow_spec_action_drop);
- if (!flow->actions.queue && !flow->actions.drop) {
- rte_flow_error_set(error, ENOTSUP, RTE_FLOW_ERROR_TYPE_HANDLE,
- NULL, "no valid action");
- 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.
- *
- * @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)
-{
- struct priv *priv = dev->data->dev_private;
- int ret;
- struct mlx5_flow_parse flow = {
- .offset = sizeof(struct ibv_flow_attr),
- .actions = {
- .mark_id = MLX5_FLOW_MARK_DEFAULT,
- .queues_n = 0,
- },
- };
-
- priv_lock(priv);
- ret = priv_flow_validate(priv, attr, items, actions, error, &flow);
- priv_unlock(priv);
- return ret;
+ flow->verbs.size += size;
}
/**
- * Convert Ethernet item to Verbs specification.
+ * Convert the @p item into a Verbs specification after ensuring the NIC
+ * will understand and process it correctly.
+ * If the necessary size for the conversion is greater than the @p flow_size,
+ * nothing is written in @p flow, the validation is still performed.
*
- * @param item[in]
+ * @param[in] item
* Item specification.
- * @param default_mask[in]
- * Default bit-masks to use when item->mask is not provided.
- * @param data[in, out]
- * User structure.
+ * @param[in, out] flow
+ * Pointer to flow structure.
+ * @param[in] flow_size
+ * Size in bytes of the available space in @p flow, if too small, nothing is
+ * written.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * On success the number of bytes consumed/necessary, if the returned value
+ * is lesser or equal to @p flow_size, the @p item has fully been converted,
+ * otherwise another call with this returned memory size should be done.
+ * On error, a negative errno value is returned and rte_errno is set.
*/
static int
-mlx5_flow_create_eth(const struct rte_flow_item *item,
- const void *default_mask,
- void *data)
+mlx5_flow_item_eth(const struct rte_flow_item *item, struct rte_flow *flow,
+ const size_t flow_size, struct rte_flow_error *error)
{
const struct rte_flow_item_eth *spec = item->spec;
const struct rte_flow_item_eth *mask = item->mask;
- struct mlx5_flow_parse *flow = (struct mlx5_flow_parse *)data;
- struct ibv_flow_spec_eth *eth;
- const unsigned int eth_size = sizeof(struct ibv_flow_spec_eth);
- unsigned int i;
-
- ++flow->ibv_attr->num_of_specs;
- flow->ibv_attr->priority = 2;
- flow->hash_fields = 0;
- eth = (void *)((uintptr_t)flow->ibv_attr + flow->offset);
- *eth = (struct ibv_flow_spec_eth) {
- .type = flow->inner | IBV_FLOW_SPEC_ETH,
- .size = eth_size,
+ 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),
};
- if (!spec)
- return 0;
+ const unsigned int size = sizeof(struct ibv_flow_spec_eth);
+ struct ibv_flow_spec_eth eth = {
+ .type = IBV_FLOW_SPEC_ETH,
+ .size = size,
+ };
+ int ret;
+
+ if (flow->layers & MLX5_FLOW_LAYER_OUTER_L2)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM,
+ item,
+ "L2 layers already configured");
if (!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];
+ mask = &rte_flow_item_eth_mask;
+ ret = mlx5_flow_item_acceptable(item, (const uint8_t *)mask,
+ (const uint8_t *)&nic_mask,
+ sizeof(struct rte_flow_item_eth),
+ error);
+ if (ret)
+ return ret;
+ flow->layers |= MLX5_FLOW_LAYER_OUTER_L2;
+ if (size > flow_size)
+ return size;
+ if (spec) {
+ unsigned int i;
+
+ memcpy(ð.val.dst_mac, spec->dst.addr_bytes, ETHER_ADDR_LEN);
+ memcpy(ð.val.src_mac, spec->src.addr_bytes, ETHER_ADDR_LEN);
+ eth.val.ether_type = spec->type;
+ memcpy(ð.mask.dst_mac, mask->dst.addr_bytes, ETHER_ADDR_LEN);
+ memcpy(ð.mask.src_mac, mask->src.addr_bytes, ETHER_ADDR_LEN);
+ eth.mask.ether_type = mask->type;
+ /* Remove unwanted bits from values. */
+ for (i = 0; i < ETHER_ADDR_LEN; ++i) {
+ eth.val.dst_mac[i] &= eth.mask.dst_mac[i];
+ eth.val.src_mac[i] &= eth.mask.src_mac[i];
+ }
+ eth.val.ether_type &= eth.mask.ether_type;
}
- eth->val.ether_type &= eth->mask.ether_type;
- return 0;
+ mlx5_flow_spec_verbs_add(flow, ð, size);
+ return size;
}
/**
- * Convert VLAN item to Verbs specification.
+ * Update the VLAN tag in the Verbs Ethernet specification.
*
- * @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[in, out] attr
+ * Pointer to Verbs attributes structure.
+ * @param[in] eth
+ * Verbs structure containing the VLAN information to copy.
*/
-static int
-mlx5_flow_create_vlan(const struct rte_flow_item *item,
- const void *default_mask,
- void *data)
+static void
+mlx5_flow_item_vlan_update(struct ibv_flow_attr *attr,
+ struct ibv_flow_spec_eth *eth)
{
- const struct rte_flow_item_vlan *spec = item->spec;
- const struct rte_flow_item_vlan *mask = item->mask;
- struct mlx5_flow_parse *flow = (struct mlx5_flow_parse *)data;
- struct ibv_flow_spec_eth *eth;
- const unsigned int eth_size = sizeof(struct ibv_flow_spec_eth);
-
- 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;
- return 0;
+ unsigned int i;
+ enum ibv_flow_spec_type search = IBV_FLOW_SPEC_ETH;
+ struct ibv_spec_header *hdr = (struct ibv_spec_header *)
+ ((uint8_t *)attr + sizeof(struct ibv_flow_attr));
+
+ for (i = 0; i != attr->num_of_specs; ++i) {
+ if (hdr->type == search) {
+ struct ibv_flow_spec_eth *e =
+ (struct ibv_flow_spec_eth *)hdr;
+
+ e->val.vlan_tag = eth->val.vlan_tag;
+ e->mask.vlan_tag = eth->mask.vlan_tag;
+ e->val.ether_type = eth->val.ether_type;
+ e->mask.ether_type = eth->mask.ether_type;
+ break;
+ }
+ hdr = (struct ibv_spec_header *)((uint8_t *)hdr + hdr->size);
+ }
}
/**
- * Convert IPv4 item to Verbs specification.
+ * Convert the @p item into @p flow (or by updating the already present
+ * Ethernet Verbs) specification after ensuring the NIC will understand and
+ * process it correctly.
+ * If the necessary size for the conversion is greater than the @p flow_size,
+ * nothing is written in @p flow, the validation is still performed.
*
- * @param item[in]
+ * @param[in] item
* Item specification.
- * @param default_mask[in]
- * Default bit-masks to use when item->mask is not provided.
- * @param data[in, out]
- * User structure.
+ * @param[in, out] flow
+ * Pointer to flow structure.
+ * @param[in] flow_size
+ * Size in bytes of the available space in @p flow, if too small, nothing is
+ * written.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * On success the number of bytes consumed/necessary, if the returned value
+ * is lesser or equal to @p flow_size, the @p item has fully been converted,
+ * otherwise another call with this returned memory size should be done.
+ * On error, a negative errno value is returned and rte_errno is set.
*/
static int
-mlx5_flow_create_ipv4(const struct rte_flow_item *item,
- const void *default_mask,
- void *data)
+mlx5_flow_item_vlan(const struct rte_flow_item *item, struct rte_flow *flow,
+ const size_t flow_size, 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_parse *flow = (struct mlx5_flow_parse *)data;
- struct ibv_flow_spec_ipv4_ext *ipv4;
- unsigned int ipv4_size = sizeof(struct ibv_flow_spec_ipv4_ext);
-
- ++flow->ibv_attr->num_of_specs;
- flow->ibv_attr->priority = 1;
- flow->hash_fields = (IBV_RX_HASH_SRC_IPV4 |
- IBV_RX_HASH_DST_IPV4);
- ipv4 = (void *)((uintptr_t)flow->ibv_attr + flow->offset);
- *ipv4 = (struct ibv_flow_spec_ipv4_ext) {
- .type = flow->inner | IBV_FLOW_SPEC_IPV4_EXT,
- .size = ipv4_size,
- };
- if (!spec)
- return 0;
- if (!mask)
- mask = default_mask;
- ipv4->val = (struct ibv_flow_ipv4_ext_filter){
- .src_ip = spec->hdr.src_addr,
- .dst_ip = spec->hdr.dst_addr,
- .proto = spec->hdr.next_proto_id,
- .tos = spec->hdr.type_of_service,
+ 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),
};
- ipv4->mask = (struct ibv_flow_ipv4_ext_filter){
- .src_ip = mask->hdr.src_addr,
- .dst_ip = mask->hdr.dst_addr,
- .proto = mask->hdr.next_proto_id,
- .tos = mask->hdr.type_of_service,
+ unsigned int size = sizeof(struct ibv_flow_spec_eth);
+ struct ibv_flow_spec_eth eth = {
+ .type = IBV_FLOW_SPEC_ETH,
+ .size = size,
};
- /* 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;
- return 0;
+ int ret;
+ const uint32_t l34m = MLX5_FLOW_LAYER_OUTER_L3 |
+ MLX5_FLOW_LAYER_OUTER_L4;
+ const uint32_t vlanm = MLX5_FLOW_LAYER_OUTER_VLAN;
+ const uint32_t l2m = MLX5_FLOW_LAYER_OUTER_L2;
+
+ if (flow->layers & vlanm)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM,
+ item,
+ "VLAN layer already configured");
+ else if ((flow->layers & l34m) != 0)
+ return rte_flow_error_set(error, ENOTSUP,
+ 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) {
+ eth.val.vlan_tag = spec->tci;
+ eth.mask.vlan_tag = mask->tci;
+ eth.val.vlan_tag &= eth.mask.vlan_tag;
+ eth.val.ether_type = spec->inner_type;
+ eth.mask.ether_type = mask->inner_type;
+ eth.val.ether_type &= eth.mask.ether_type;
+ }
+ /*
+ * From verbs perspective an empty VLAN is equivalent
+ * to a packet without VLAN layer.
+ */
+ if (!eth.mask.vlan_tag)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM_SPEC,
+ item->spec,
+ "VLAN cannot be empty");
+ if (!(flow->layers & l2m)) {
+ if (size <= flow_size)
+ mlx5_flow_spec_verbs_add(flow, ð, size);
+ } else {
+ if (flow->verbs.attr)
+ mlx5_flow_item_vlan_update(flow->verbs.attr, ð);
+ size = 0; /* Only an update is done in eth specification. */
+ }
+ flow->layers |= MLX5_FLOW_LAYER_OUTER_L2 |
+ MLX5_FLOW_LAYER_OUTER_VLAN;
+ return size;
}
/**
- * Convert IPv6 item to Verbs specification.
+ * Convert the @p pattern into a Verbs specifications after ensuring the NIC
+ * will understand and process it correctly.
+ * The conversion is performed item per item, each of them is written into
+ * the @p flow if its size is lesser or equal to @p flow_size.
+ * Validation and memory consumption computation are still performed until the
+ * end of @p pattern, unless an error is encountered.
*
- * @param 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[in] pattern
+ * Flow pattern.
+ * @param[in, out] flow
+ * Pointer to the rte_flow structure.
+ * @param[in] flow_size
+ * Size in bytes of the available space in @p flow, if too small some
+ * garbage may be present.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * On success the number of bytes consumed/necessary, if the returned value
+ * is lesser or equal to @p flow_size, the @pattern has fully been
+ * converted, otherwise another call with this returned memory size should
+ * be done.
+ * On error, a negative errno value is returned and rte_errno is set.
*/
static int
-mlx5_flow_create_ipv6(const struct rte_flow_item *item,
- const void *default_mask,
- void *data)
+mlx5_flow_items(const struct rte_flow_item pattern[],
+ struct rte_flow *flow, const size_t flow_size,
+ 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_parse *flow = (struct mlx5_flow_parse *)data;
- struct ibv_flow_spec_ipv6 *ipv6;
- unsigned int ipv6_size = sizeof(struct ibv_flow_spec_ipv6);
- unsigned int i;
+ int remain = flow_size;
+ size_t size = 0;
+
+ for (; pattern->type != RTE_FLOW_ITEM_TYPE_END; pattern++) {
+ int ret = 0;
+
+ switch (pattern->type) {
+ case RTE_FLOW_ITEM_TYPE_VOID:
+ break;
+ case RTE_FLOW_ITEM_TYPE_ETH:
+ ret = mlx5_flow_item_eth(pattern, flow, remain, error);
+ break;
+ case RTE_FLOW_ITEM_TYPE_VLAN:
+ ret = mlx5_flow_item_vlan(pattern, flow, remain, error);
+ break;
+ default:
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM,
+ pattern,
+ "item not supported");
+ }
+ if (ret < 0)
+ return ret;
+ if (remain > ret)
+ remain -= ret;
+ else
+ remain = 0;
+ size += ret;
+ }
+ if (!flow->layers) {
+ const struct rte_flow_item item = {
+ .type = RTE_FLOW_ITEM_TYPE_ETH,
+ };
- ++flow->ibv_attr->num_of_specs;
- flow->ibv_attr->priority = 1;
- flow->hash_fields = (IBV_RX_HASH_SRC_IPV6 |
- IBV_RX_HASH_DST_IPV6);
- ipv6 = (void *)((uintptr_t)flow->ibv_attr + flow->offset);
- *ipv6 = (struct ibv_flow_spec_ipv6) {
- .type = flow->inner | IBV_FLOW_SPEC_IPV6,
- .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;
- /* Remove unwanted bits from values. */
- for (i = 0; i < RTE_DIM(ipv6->val.src_ip); ++i) {
- ipv6->val.src_ip[i] &= ipv6->mask.src_ip[i];
- ipv6->val.dst_ip[i] &= ipv6->mask.dst_ip[i];
+ return mlx5_flow_item_eth(&item, flow, flow_size, error);
}
- 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;
+ return size;
}
/**
- * Convert UDP item to Verbs specification.
+ * Convert the @p action into a Verbs specification after ensuring the NIC
+ * will understand and process it correctly.
+ * If the necessary size for the conversion is greater than the @p flow_size,
+ * nothing is written in @p flow, the validation is still performed.
*
- * @param 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[in] action
+ * Action configuration.
+ * @param[in, out] flow
+ * Pointer to flow structure.
+ * @param[in] flow_size
+ * Size in bytes of the available space in @p flow, if too small, nothing is
+ * written.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * On success the number of bytes consumed/necessary, if the returned value
+ * is lesser or equal to @p flow_size, the @p action has fully been
+ * converted, otherwise another call with this returned memory size should
+ * be done.
+ * On error, a negative errno value is returned and rte_errno is set.
*/
static int
-mlx5_flow_create_udp(const struct rte_flow_item *item,
- const void *default_mask,
- void *data)
+mlx5_flow_action_drop(const struct rte_flow_action *action,
+ struct rte_flow *flow, const size_t flow_size,
+ 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_parse *flow = (struct mlx5_flow_parse *)data;
- struct ibv_flow_spec_tcp_udp *udp;
- unsigned int udp_size = sizeof(struct ibv_flow_spec_tcp_udp);
-
- ++flow->ibv_attr->num_of_specs;
- flow->ibv_attr->priority = 0;
- flow->hash_fields |= (IBV_RX_HASH_SRC_PORT_UDP |
- IBV_RX_HASH_DST_PORT_UDP);
- udp = (void *)((uintptr_t)flow->ibv_attr + flow->offset);
- *udp = (struct ibv_flow_spec_tcp_udp) {
- .type = flow->inner | IBV_FLOW_SPEC_UDP,
- .size = udp_size,
+ unsigned int size = sizeof(struct ibv_flow_spec_action_drop);
+ struct ibv_flow_spec_action_drop drop = {
+ .type = IBV_FLOW_SPEC_ACTION_DROP,
+ .size = size,
};
- if (!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;
- return 0;
+
+ if (flow->fate)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ action,
+ "multiple fate actions are not"
+ " supported");
+ if (size < flow_size)
+ mlx5_flow_spec_verbs_add(flow, &drop, size);
+ flow->fate |= MLX5_FLOW_FATE_DROP;
+ return size;
}
/**
- * Convert TCP item to Verbs specification.
+ * Convert the @p action into @p flow after ensuring the NIC will understand
+ * and process it correctly.
*
- * @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[in] dev
+ * Pointer to Ethernet device structure.
+ * @param[in] action
+ * Action configuration.
+ * @param[in, out] flow
+ * Pointer to flow structure.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
*/
static int
-mlx5_flow_create_tcp(const struct rte_flow_item *item,
- const void *default_mask,
- void *data)
+mlx5_flow_action_queue(struct rte_eth_dev *dev,
+ const struct rte_flow_action *action,
+ struct rte_flow *flow,
+ struct rte_flow_error *error)
{
- const struct rte_flow_item_tcp *spec = item->spec;
- const struct rte_flow_item_tcp *mask = item->mask;
- struct mlx5_flow_parse *flow = (struct mlx5_flow_parse *)data;
- struct ibv_flow_spec_tcp_udp *tcp;
- unsigned int tcp_size = sizeof(struct ibv_flow_spec_tcp_udp);
-
- ++flow->ibv_attr->num_of_specs;
- flow->ibv_attr->priority = 0;
- flow->hash_fields |= (IBV_RX_HASH_SRC_PORT_TCP |
- IBV_RX_HASH_DST_PORT_TCP);
- tcp = (void *)((uintptr_t)flow->ibv_attr + flow->offset);
- *tcp = (struct ibv_flow_spec_tcp_udp) {
- .type = flow->inner | IBV_FLOW_SPEC_TCP,
- .size = tcp_size,
- };
- 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;
+ struct priv *priv = dev->data->dev_private;
+ const struct rte_flow_action_queue *queue = action->conf;
+
+ if (flow->fate)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ action,
+ "multiple fate actions are not"
+ " supported");
+ 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");
+ flow->queue = queue->index;
+ flow->fate |= MLX5_FLOW_FATE_QUEUE;
return 0;
}
/**
- * Convert VXLAN item to Verbs specification.
+ * Convert the @p action into @p flow after ensuring the NIC will understand
+ * and process it correctly.
+ * The conversion is performed action per action, each of them is written into
+ * the @p flow if its size is lesser or equal to @p flow_size.
+ * Validation and memory consumption computation are still performed until the
+ * end of @p action, unless an error is encountered.
*
- * @param 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[in] dev
+ * Pointer to Ethernet device structure.
+ * @param[in] actions
+ * Pointer to flow actions array.
+ * @param[in, out] flow
+ * Pointer to the rte_flow structure.
+ * @param[in] flow_size
+ * Size in bytes of the available space in @p flow, if too small some
+ * garbage may be present.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * On success the number of bytes consumed/necessary, if the returned value
+ * is lesser or equal to @p flow_size, the @p actions has fully been
+ * converted, otherwise another call with this returned memory size should
+ * be done.
+ * On error, a negative errno value is returned and rte_errno is set.
*/
static int
-mlx5_flow_create_vxlan(const struct rte_flow_item *item,
- const void *default_mask,
- void *data)
+mlx5_flow_actions(struct rte_eth_dev *dev,
+ const struct rte_flow_action actions[],
+ struct rte_flow *flow, const size_t flow_size,
+ struct rte_flow_error *error)
{
- const struct rte_flow_item_vxlan *spec = item->spec;
- const struct rte_flow_item_vxlan *mask = item->mask;
- struct mlx5_flow_parse *flow = (struct mlx5_flow_parse *)data;
- struct ibv_flow_spec_tunnel *vxlan;
- unsigned int size = sizeof(struct ibv_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_flow_spec_tunnel) {
- .type = flow->inner | IBV_FLOW_SPEC_VXLAN_TUNNEL,
- .size = size,
- };
- flow->inner = IBV_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;
- return 0;
+ size_t size = 0;
+ int remain = flow_size;
+ int ret = 0;
+
+ for (; actions->type != RTE_FLOW_ACTION_TYPE_END; actions++) {
+ switch (actions->type) {
+ case RTE_FLOW_ACTION_TYPE_VOID:
+ break;
+ case RTE_FLOW_ACTION_TYPE_DROP:
+ ret = mlx5_flow_action_drop(actions, flow, remain,
+ error);
+ break;
+ case RTE_FLOW_ACTION_TYPE_QUEUE:
+ ret = mlx5_flow_action_queue(dev, actions, flow, error);
+ break;
+ default:
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ actions,
+ "action not supported");
+ }
+ if (ret < 0)
+ return ret;
+ if (remain > ret)
+ remain -= ret;
+ else
+ remain = 0;
+ size += ret;
+ }
+ if (!flow->fate)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL,
+ "no fate action found");
+ return size;
}
/**
- * Convert mark/flag action to Verbs specification.
+ * Convert the @p attributes, @p pattern, @p action, into an flow for the NIC
+ * after ensuring the NIC will understand and process it correctly.
+ * The conversion is only performed item/action per item/action, each of
+ * them is written into the @p flow if its size is lesser or equal to @p
+ * flow_size.
+ * Validation and memory consumption computation are still performed until the
+ * end, unless an error is encountered.
*
- * @param flow
- * Pointer to MLX5 flow structure.
- * @param mark_id
- * Mark identifier.
+ * @param[in] dev
+ * Pointer to Ethernet device.
+ * @param[in, out] flow
+ * Pointer to flow structure.
+ * @param[in] flow_size
+ * Size in bytes of the available space in @p flow, if too small some
+ * garbage may be present.
+ * @param[in] attributes
+ * Flow rule attributes.
+ * @param[in] pattern
+ * Pattern specification (list terminated by the END pattern item).
+ * @param[in] actions
+ * Associated actions (list terminated by the END action).
+ * @param[out] error
+ * Perform verbose error reporting if not NULL.
+ *
+ * @return
+ * On success the number of bytes consumed/necessary, if the returned value
+ * is lesser or equal to @p flow_size, the flow has fully been converted and
+ * can be applied, otherwise another call with this returned memory size
+ * should be done.
+ * On error, a negative errno value is returned and rte_errno is set.
*/
static int
-mlx5_flow_create_flag_mark(struct mlx5_flow_parse *flow, uint32_t mark_id)
+mlx5_flow_merge(struct rte_eth_dev *dev, struct rte_flow *flow,
+ const size_t flow_size,
+ const struct rte_flow_attr *attributes,
+ const struct rte_flow_item pattern[],
+ const struct rte_flow_action actions[],
+ struct rte_flow_error *error)
{
- struct ibv_flow_spec_action_tag *tag;
- unsigned int size = sizeof(struct ibv_flow_spec_action_tag);
+ struct rte_flow local_flow = { .layers = 0, };
+ size_t size = sizeof(*flow) + sizeof(struct ibv_flow_attr);
+ int remain = (flow_size > size) ? flow_size - size : 0;
+ int ret;
- tag = (void *)((uintptr_t)flow->ibv_attr + flow->offset);
- *tag = (struct ibv_flow_spec_action_tag){
- .type = IBV_FLOW_SPEC_ACTION_TAG,
- .size = size,
- .tag_id = mlx5_flow_mark_set(mark_id),
- };
- ++flow->ibv_attr->num_of_specs;
- return 0;
+ if (!remain)
+ flow = &local_flow;
+ ret = mlx5_flow_attributes(dev, attributes, flow, error);
+ if (ret < 0)
+ return ret;
+ ret = mlx5_flow_items(pattern, flow, remain, error);
+ if (ret < 0)
+ return ret;
+ size += ret;
+ remain = (flow_size > size) ? flow_size - size : 0;
+ ret = mlx5_flow_actions(dev, actions, flow, remain, error);
+ if (ret < 0)
+ return ret;
+ size += ret;
+ if (size <= flow_size)
+ flow->verbs.attr->priority = flow->attributes.priority;
+ return size;
}
/**
- * Complete flow rule creation with a drop queue.
- *
- * @param priv
- * Pointer to private structure.
- * @param flow
- * MLX5 flow attributes (filled by mlx5_flow_validate()).
- * @param[out] error
- * Perform verbose error reporting if not NULL.
+ * Validate a flow supported by the NIC.
*
- * @return
- * A flow if the rule could be created.
+ * @see rte_flow_validate()
+ * @see rte_flow_ops
*/
-static struct rte_flow *
-priv_flow_create_action_queue_drop(struct priv *priv,
- struct mlx5_flow_parse *flow,
- struct rte_flow_error *error)
+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)
{
- struct rte_flow *rte_flow;
- struct ibv_flow_spec_action_drop *drop;
- unsigned int size = sizeof(struct ibv_flow_spec_action_drop);
+ int ret = mlx5_flow_merge(dev, NULL, 0, attr, items, actions, error);
- 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 (ret < 0)
+ return ret;
+ return 0;
+}
+
+/**
+ * Remove the flow.
+ *
+ * @param[in] dev
+ * Pointer to Ethernet device.
+ * @param[in, out] flow
+ * Pointer to flow structure.
+ */
+static void
+mlx5_flow_remove(struct rte_eth_dev *dev, struct rte_flow *flow)
+{
+ if (flow->fate & MLX5_FLOW_FATE_DROP) {
+ if (flow->verbs.flow) {
+ claim_zero(mlx5_glue->destroy_flow(flow->verbs.flow));
+ flow->verbs.flow = NULL;
+ }
}
- rte_flow->drop = 1;
- drop = (void *)((uintptr_t)flow->ibv_attr + flow->offset);
- *drop = (struct ibv_flow_spec_action_drop){
- .type = IBV_FLOW_SPEC_ACTION_DROP,
- .size = size,
- };
- ++flow->ibv_attr->num_of_specs;
- flow->offset += sizeof(struct ibv_flow_spec_action_drop);
- rte_flow->ibv_attr = flow->ibv_attr;
- if (!priv->dev->data->dev_started)
- return rte_flow;
- rte_flow->drxq.hrxq.qp = priv->flow_drop_queue->qp;
- rte_flow->ibv_flow = ibv_create_flow(rte_flow->drxq.hrxq.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");
- goto error;
+ if (flow->verbs.hrxq) {
+ if (flow->fate & MLX5_FLOW_FATE_DROP)
+ mlx5_hrxq_drop_release(dev);
+ else if (flow->fate & MLX5_FLOW_FATE_QUEUE)
+ mlx5_hrxq_release(dev, flow->verbs.hrxq);
+ flow->verbs.hrxq = NULL;
}
- return rte_flow;
-error:
- assert(rte_flow);
- rte_free(rte_flow);
- return NULL;
}
/**
- * Complete flow rule creation.
+ * Apply the flow.
*
- * @param priv
- * Pointer to private structure.
- * @param flow
- * MLX5 flow attributes (filled by mlx5_flow_validate()).
+ * @param[in] dev
+ * Pointer to Ethernet device structure.
+ * @param[in, out] flow
+ * Pointer to flow structure.
* @param[out] error
- * Perform verbose error reporting if not NULL.
+ * Pointer to error structure.
*
* @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 mlx5_flow_parse *flow,
- struct rte_flow_error *error)
+static int
+mlx5_flow_apply(struct rte_eth_dev *dev, struct rte_flow *flow,
+ struct rte_flow_error *error)
{
- struct rte_flow *rte_flow;
- unsigned int i;
-
- assert(priv->pd);
- assert(priv->ctx);
- assert(!flow->actions.drop);
- rte_flow =
- rte_calloc(__func__, 1,
- sizeof(*flow) +
- flow->actions.queues_n * sizeof(uint16_t),
- 0);
- if (!rte_flow) {
- rte_flow_error_set(error, ENOMEM, RTE_FLOW_ERROR_TYPE_HANDLE,
- NULL, "cannot allocate flow memory");
- return NULL;
+ if (flow->fate & MLX5_FLOW_FATE_DROP) {
+ flow->verbs.hrxq = mlx5_hrxq_drop_new(dev);
+ if (!flow->verbs.hrxq)
+ return rte_flow_error_set
+ (error, errno,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL,
+ "cannot allocate Drop queue");
+ } else if (flow->fate & MLX5_FLOW_FATE_QUEUE) {
+ struct mlx5_hrxq *hrxq;
+
+ hrxq = mlx5_hrxq_get(dev, rss_hash_default_key,
+ rss_hash_default_key_len, 0,
+ &flow->queue, 1, 0, 0);
+ if (!hrxq)
+ hrxq = mlx5_hrxq_new(dev, rss_hash_default_key,
+ rss_hash_default_key_len, 0,
+ &flow->queue, 1, 0, 0);
+ if (!hrxq)
+ return rte_flow_error_set(error, rte_errno,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL,
+ "cannot create flow");
+ flow->verbs.hrxq = hrxq;
}
- rte_flow->mark = flow->actions.mark;
- rte_flow->ibv_attr = flow->ibv_attr;
- rte_flow->queues = (uint16_t (*)[])(rte_flow + 1);
- memcpy(rte_flow->queues, flow->actions.queues,
- flow->actions.queues_n * sizeof(uint16_t));
- rte_flow->queues_n = flow->actions.queues_n;
- rte_flow->frxq.hash_fields = flow->hash_fields;
- rte_flow->frxq.hrxq = mlx5_priv_hrxq_get(priv, rss_hash_default_key,
- rss_hash_default_key_len,
- flow->hash_fields,
- (*rte_flow->queues),
- rte_flow->queues_n);
- if (!rte_flow->frxq.hrxq) {
- rte_flow->frxq.hrxq =
- mlx5_priv_hrxq_new(priv, rss_hash_default_key,
- rss_hash_default_key_len,
- flow->hash_fields,
- (*rte_flow->queues),
- rte_flow->queues_n);
- if (!rte_flow->frxq.hrxq) {
- rte_flow_error_set(error, ENOMEM,
- RTE_FLOW_ERROR_TYPE_HANDLE,
- NULL, "cannot create hash rxq");
- goto error;
- }
+ flow->verbs.flow =
+ mlx5_glue->create_flow(flow->verbs.hrxq->qp, flow->verbs.attr);
+ if (!flow->verbs.flow) {
+ if (flow->fate & MLX5_FLOW_FATE_DROP)
+ mlx5_hrxq_drop_release(dev);
+ else
+ mlx5_hrxq_release(dev, flow->verbs.hrxq);
+ flow->verbs.hrxq = NULL;
+ return rte_flow_error_set(error, errno,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL,
+ "kernel module refuses to create"
+ " flow");
}
- for (i = 0; i != flow->actions.queues_n; ++i) {
- struct mlx5_rxq_data *q =
- (*priv->rxqs)[flow->actions.queues[i]];
-
- q->mark |= flow->actions.mark;
- }
- if (!priv->dev->data->dev_started)
- return rte_flow;
- rte_flow->ibv_flow = ibv_create_flow(rte_flow->frxq.hrxq->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");
- goto error;
- }
- return rte_flow;
-error:
- assert(rte_flow);
- if (rte_flow->frxq.hrxq)
- mlx5_priv_hrxq_release(priv, rte_flow->frxq.hrxq);
- rte_free(rte_flow);
- return NULL;
+ return 0;
}
/**
- * Convert a flow.
+ * Create a flow and add it to @p list.
*
- * @param priv
- * Pointer to private structure.
+ * @param dev
+ * Pointer to Ethernet device.
* @param list
* Pointer to a TAILQ flow list.
* @param[in] attr
* Flow rule attributes.
- * @param[in] pattern
+ * @param[in] items
* Pattern specification (list terminated by the END pattern item).
* @param[in] actions
* Associated actions (list terminated by the END action).
* Perform verbose error reporting if not NULL.
*
* @return
- * A flow on success, NULL otherwise.
+ * A flow on success, NULL otherwise and rte_errno is set.
*/
static struct rte_flow *
-priv_flow_create(struct priv *priv,
- 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)
+mlx5_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 *rte_flow;
- struct mlx5_flow_parse flow = {
- .offset = sizeof(struct ibv_flow_attr),
- .actions = {
- .mark_id = MLX5_FLOW_MARK_DEFAULT,
- .queues = { 0 },
- .queues_n = 0,
- },
- };
- 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_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_flow_attr){
- .type = IBV_FLOW_ATTR_NORMAL,
- .size = sizeof(struct ibv_flow_attr),
- .priority = attr->priority,
- .num_of_specs = 0,
- .port = 0,
- .flags = 0,
- };
- flow.inner = 0;
- flow.hash_fields = 0;
- claim_zero(priv_flow_validate(priv, attr, items, actions,
- error, &flow));
- if (flow.actions.mark && !flow.actions.drop) {
- mlx5_flow_create_flag_mark(&flow, flow.actions.mark_id);
- flow.offset += sizeof(struct ibv_flow_spec_action_tag);
+ struct rte_flow *flow;
+ size_t size;
+ int ret;
+
+ ret = mlx5_flow_merge(dev, NULL, 0, attr, items, actions, error);
+ if (ret < 0)
+ return NULL;
+ size = ret;
+ flow = rte_zmalloc(__func__, size, 0);
+ if (!flow) {
+ rte_flow_error_set(error, ENOMEM,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL,
+ "cannot allocate memory");
+ return NULL;
}
- if (flow.actions.drop)
- rte_flow =
- priv_flow_create_action_queue_drop(priv, &flow, error);
- else
- rte_flow = priv_flow_create_action_queue(priv, &flow, error);
- if (!rte_flow)
- goto exit;
- if (rte_flow) {
- TAILQ_INSERT_TAIL(list, rte_flow, next);
- DEBUG("Flow created %p", (void *)rte_flow);
+ flow->verbs.attr = (struct ibv_flow_attr *)(flow + 1);
+ flow->verbs.specs = (uint8_t *)(flow->verbs.attr + 1);
+ ret = mlx5_flow_merge(dev, flow, size, attr, items, actions, error);
+ if (ret < 0)
+ goto error;
+ assert((size_t)ret == size);
+ if (dev->data->dev_started) {
+ ret = mlx5_flow_apply(dev, flow, error);
+ if (ret < 0)
+ goto error;
}
- return rte_flow;
-exit:
- rte_free(flow.ibv_attr);
+ TAILQ_INSERT_TAIL(list, flow, next);
+ return flow;
+error:
+ ret = rte_errno; /* Save rte_errno before cleanup. */
+ mlx5_flow_remove(dev, flow);
+ rte_free(flow);
+ rte_errno = ret; /* Restore rte_errno. */
return NULL;
}
const struct rte_flow_action actions[],
struct rte_flow_error *error)
{
- struct priv *priv = dev->data->dev_private;
- struct rte_flow *flow;
-
- priv_lock(priv);
- flow = priv_flow_create(priv, &priv->flows, attr, items, actions,
- error);
- priv_unlock(priv);
- return flow;
+ return mlx5_flow_list_create
+ (dev, &((struct priv *)dev->data->dev_private)->flows,
+ attr, items, actions, error);
}
/**
- * Destroy a flow.
+ * Destroy a flow in a list.
*
- * @param priv
- * Pointer to private structure.
+ * @param dev
+ * Pointer to Ethernet device.
* @param list
* Pointer to a TAILQ flow list.
* @param[in] flow
* Flow to destroy.
*/
static void
-priv_flow_destroy(struct priv *priv,
- struct mlx5_flows *list,
- struct rte_flow *flow)
+mlx5_flow_list_destroy(struct rte_eth_dev *dev, struct mlx5_flows *list,
+ struct rte_flow *flow)
{
- unsigned int i;
- uint16_t *queues;
- uint16_t queues_n;
-
- if (flow->drop || !flow->mark)
- goto free;
- queues = flow->frxq.hrxq->ind_table->queues;
- queues_n = flow->frxq.hrxq->ind_table->queues_n;
- for (i = 0; i != queues_n; ++i) {
- struct rte_flow *tmp;
- struct mlx5_rxq_data *rxq_data = (*priv->rxqs)[queues[i]];
- int mark = 0;
-
- /*
- * To remove the mark from the queue, the queue must not be
- * present in any other marked flow (RSS or not).
- */
- TAILQ_FOREACH(tmp, list, next) {
- unsigned int j;
-
- if (!tmp->mark)
- continue;
- for (j = 0;
- (j != tmp->frxq.hrxq->ind_table->queues_n) &&
- !mark;
- j++)
- if (tmp->frxq.hrxq->ind_table->queues[j] ==
- queues[i])
- mark = 1;
- }
- rxq_data->mark = mark;
- }
-free:
- if (flow->ibv_flow)
- claim_zero(ibv_destroy_flow(flow->ibv_flow));
- if (!flow->drop)
- mlx5_priv_hrxq_release(priv, flow->frxq.hrxq);
+ mlx5_flow_remove(dev, flow);
TAILQ_REMOVE(list, flow, next);
- rte_free(flow->ibv_attr);
- DEBUG("Flow destroyed %p", (void *)flow);
rte_free(flow);
}
-/**
- * Destroy a flow.
- *
- * @see rte_flow_destroy()
- * @see rte_flow_ops
- */
-int
-mlx5_flow_destroy(struct rte_eth_dev *dev,
- struct rte_flow *flow,
- struct rte_flow_error *error)
-{
- struct priv *priv = dev->data->dev_private;
-
- (void)error;
- priv_lock(priv);
- priv_flow_destroy(priv, &priv->flows, flow);
- priv_unlock(priv);
- return 0;
-}
-
/**
* Destroy all flows.
*
- * @param priv
- * Pointer to private structure.
+ * @param dev
+ * Pointer to Ethernet device.
* @param list
* Pointer to a TAILQ flow list.
*/
void
-priv_flow_flush(struct priv *priv, struct mlx5_flows *list)
+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);
- priv_flow_destroy(priv, list, flow);
+ mlx5_flow_list_destroy(dev, list, flow);
}
}
-/**
- * Destroy all flows.
- *
- * @see rte_flow_flush()
- * @see rte_flow_ops
- */
-int
-mlx5_flow_flush(struct rte_eth_dev *dev,
- struct rte_flow_error *error)
-{
- struct priv *priv = dev->data->dev_private;
-
- (void)error;
- priv_lock(priv);
- priv_flow_flush(priv, &priv->flows);
- priv_unlock(priv);
- return 0;
-}
-
-/**
- * Create drop queue.
- *
- * @param priv
- * Pointer to private structure.
- *
- * @return
- * 0 on success.
- */
-int
-priv_flow_create_drop_queue(struct priv *priv)
-{
- struct mlx5_hrxq_drop *fdq = NULL;
-
- assert(priv->pd);
- assert(priv->ctx);
- fdq = rte_calloc(__func__, 1, sizeof(*fdq), 0);
- if (!fdq) {
- WARN("cannot allocate memory for drop queue");
- goto error;
- }
- fdq->cq = ibv_create_cq(priv->ctx, 1, NULL, NULL, 0);
- if (!fdq->cq) {
- WARN("cannot allocate CQ for drop queue");
- goto error;
- }
- fdq->wq = ibv_create_wq(priv->ctx,
- &(struct ibv_wq_init_attr){
- .wq_type = IBV_WQT_RQ,
- .max_wr = 1,
- .max_sge = 1,
- .pd = priv->pd,
- .cq = fdq->cq,
- });
- if (!fdq->wq) {
- WARN("cannot allocate WQ for drop queue");
- goto error;
- }
- fdq->ind_table = ibv_create_rwq_ind_table(priv->ctx,
- &(struct ibv_rwq_ind_table_init_attr){
- .log_ind_tbl_size = 0,
- .ind_tbl = &fdq->wq,
- .comp_mask = 0,
- });
- if (!fdq->ind_table) {
- WARN("cannot allocate indirection table for drop queue");
- goto error;
- }
- fdq->qp = ibv_create_qp_ex(priv->ctx,
- &(struct ibv_qp_init_attr_ex){
- .qp_type = IBV_QPT_RAW_PACKET,
- .comp_mask =
- IBV_QP_INIT_ATTR_PD |
- IBV_QP_INIT_ATTR_IND_TABLE |
- IBV_QP_INIT_ATTR_RX_HASH,
- .rx_hash_conf = (struct ibv_rx_hash_conf){
- .rx_hash_function =
- IBV_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 = fdq->ind_table,
- .pd = priv->pd
- });
- if (!fdq->qp) {
- WARN("cannot allocate QP for drop queue");
- goto error;
- }
- priv->flow_drop_queue = fdq;
- return 0;
-error:
- if (fdq->qp)
- claim_zero(ibv_destroy_qp(fdq->qp));
- if (fdq->ind_table)
- claim_zero(ibv_destroy_rwq_ind_table(fdq->ind_table));
- if (fdq->wq)
- claim_zero(ibv_destroy_wq(fdq->wq));
- if (fdq->cq)
- claim_zero(ibv_destroy_cq(fdq->cq));
- if (fdq)
- rte_free(fdq);
- priv->flow_drop_queue = NULL;
- return -1;
-}
-
-/**
- * Delete drop queue.
- *
- * @param priv
- * Pointer to private structure.
- */
-void
-priv_flow_delete_drop_queue(struct priv *priv)
-{
- struct mlx5_hrxq_drop *fdq = priv->flow_drop_queue;
-
- if (!fdq)
- return;
- if (fdq->qp)
- claim_zero(ibv_destroy_qp(fdq->qp));
- if (fdq->ind_table)
- claim_zero(ibv_destroy_rwq_ind_table(fdq->ind_table));
- if (fdq->wq)
- claim_zero(ibv_destroy_wq(fdq->wq));
- if (fdq->cq)
- claim_zero(ibv_destroy_cq(fdq->cq));
- rte_free(fdq);
- priv->flow_drop_queue = NULL;
-}
-
/**
* Remove all flows.
*
- * @param priv
- * Pointer to private structure.
+ * @param dev
+ * Pointer to Ethernet device.
* @param list
* Pointer to a TAILQ flow list.
*/
void
-priv_flow_stop(struct priv *priv, struct mlx5_flows *list)
+mlx5_flow_stop(struct rte_eth_dev *dev, struct mlx5_flows *list)
{
struct rte_flow *flow;
- TAILQ_FOREACH_REVERSE(flow, list, mlx5_flows, next) {
- claim_zero(ibv_destroy_flow(flow->ibv_flow));
- flow->ibv_flow = NULL;
- mlx5_priv_hrxq_release(priv, flow->frxq.hrxq);
- flow->frxq.hrxq = NULL;
- if (flow->mark) {
- unsigned int n;
- struct mlx5_ind_table_ibv *ind_tbl =
- flow->frxq.hrxq->ind_table;
-
- for (n = 0; n < ind_tbl->queues_n; ++n)
- (*priv->rxqs)[ind_tbl->queues[n]]->mark = 0;
- }
- DEBUG("Flow %p removed", (void *)flow);
- }
+ TAILQ_FOREACH_REVERSE(flow, list, mlx5_flows, next)
+ mlx5_flow_remove(dev, flow);
}
/**
* Add all flows.
*
- * @param priv
- * Pointer to private structure.
+ * @param dev
+ * Pointer to Ethernet device.
* @param list
* Pointer to a TAILQ flow list.
*
* @return
- * 0 on success, a errno value otherwise and rte_errno is set.
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
*/
int
-priv_flow_start(struct priv *priv, struct mlx5_flows *list)
+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) {
- if (flow->frxq.hrxq)
- goto flow_create;
- flow->frxq.hrxq =
- mlx5_priv_hrxq_get(priv, rss_hash_default_key,
- rss_hash_default_key_len,
- flow->frxq.hash_fields,
- (*flow->queues),
- flow->queues_n);
- if (flow->frxq.hrxq)
- goto flow_create;
- flow->frxq.hrxq =
- mlx5_priv_hrxq_new(priv, rss_hash_default_key,
- rss_hash_default_key_len,
- flow->frxq.hash_fields,
- (*flow->queues),
- flow->queues_n);
- if (!flow->frxq.hrxq) {
- DEBUG("Flow %p cannot be applied",
- (void *)flow);
- rte_errno = EINVAL;
- return rte_errno;
- }
-flow_create:
- flow->ibv_flow = ibv_create_flow(flow->frxq.hrxq->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->mark) {
- unsigned int n;
-
- for (n = 0;
- n < flow->frxq.hrxq->ind_table->queues_n;
- ++n) {
- uint16_t idx =
- flow->frxq.hrxq->ind_table->queues[n];
- (*priv->rxqs)[idx]->mark = 1;
- }
- }
- }
- return 0;
-}
-
-/**
- * Isolated mode.
- *
- * @see rte_flow_isolate()
- * @see rte_flow_ops
- */
-int
-mlx5_flow_isolate(struct rte_eth_dev *dev,
- int enable,
- struct rte_flow_error *error)
-{
- struct priv *priv = dev->data->dev_private;
-
- priv_lock(priv);
- if (dev->data->dev_started) {
- rte_flow_error_set(error, EBUSY,
- RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
- NULL,
- "port must be stopped first");
- priv_unlock(priv);
- return -rte_errno;
+ ret = mlx5_flow_apply(dev, flow, &error);
+ if (ret < 0)
+ goto error;
}
- priv->isolated = !!enable;
- priv_unlock(priv);
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 priv
- * Pointer to private structure.
+ * @param dev
+ * Pointer to Ethernet device.
*
* @return the number of flows not released.
*/
int
-priv_flow_verify(struct priv *priv)
+mlx5_flow_verify(struct rte_eth_dev *dev)
{
+ struct priv *priv = dev->data->dev_private;
struct rte_flow *flow;
int ret = 0;
TAILQ_FOREACH(flow, &priv->flows, next) {
- DEBUG("%p: flow %p still referenced", (void *)priv,
- (void *)flow);
+ DRV_LOG(DEBUG, "port %u flow %p still referenced",
+ dev->data->port_id, (void *)flow);
++ret;
}
return ret;
* A VLAN flow mask to apply.
*
* @return
- * 0 on success.
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
*/
int
mlx5_ctrl_flow_vlan(struct rte_eth_dev *dev,
struct priv *priv = dev->data->dev_private;
const struct rte_flow_attr attr = {
.ingress = 1,
- .priority = MLX5_CTRL_FLOW_PRIORITY,
+ .priority = priv->config.flow_prio - 1,
};
struct rte_flow_item items[] = {
{
.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_QUEUE,
- .conf = &(struct rte_flow_action_queue){
- .index = 0,
- },
+ .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;
- flow = priv_flow_create(priv, &priv->ctrl_flows, &attr, items, actions,
- &error);
+ if (!priv->reta_idx_n) {
+ rte_errno = EINVAL;
+ return -rte_errno;
+ }
+ for (i = 0; i != priv->reta_idx_n; ++i)
+ queue[i] = (*priv->reta_idx)[i];
+ flow = mlx5_flow_list_create(dev, &priv->ctrl_flows, &attr, items,
+ actions, &error);
if (!flow)
- return rte_errno;
+ return -rte_errno;
return 0;
}
* An Ethernet flow mask to apply.
*
* @return
- * 0 on success.
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
*/
int
mlx5_ctrl_flow(struct rte_eth_dev *dev,
{
return mlx5_ctrl_flow_vlan(dev, eth_spec, eth_mask, NULL, NULL);
}
+
+/**
+ * Destroy a flow.
+ *
+ * @see rte_flow_destroy()
+ * @see rte_flow_ops
+ */
+int
+mlx5_flow_destroy(struct rte_eth_dev *dev,
+ struct rte_flow *flow,
+ struct rte_flow_error *error __rte_unused)
+{
+ struct priv *priv = dev->data->dev_private;
+
+ mlx5_flow_list_destroy(dev, &priv->flows, flow);
+ return 0;
+}
+
+/**
+ * Destroy all flows.
+ *
+ * @see rte_flow_flush()
+ * @see rte_flow_ops
+ */
+int
+mlx5_flow_flush(struct rte_eth_dev *dev,
+ struct rte_flow_error *error __rte_unused)
+{
+ struct priv *priv = dev->data->dev_private;
+
+ mlx5_flow_list_flush(dev, &priv->flows);
+ return 0;
+}
+
+/**
+ * Isolated mode.
+ *
+ * @see rte_flow_isolate()
+ * @see rte_flow_ops
+ */
+int
+mlx5_flow_isolate(struct rte_eth_dev *dev,
+ int enable,
+ struct rte_flow_error *error)
+{
+ struct 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 a flow director filter to a generic flow.
+ *
+ * @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_fdir_filter_convert(struct rte_eth_dev *dev,
+ const struct rte_eth_fdir_filter *fdir_filter,
+ struct mlx5_fdir *attributes)
+{
+ struct 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,
+ };
+ 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 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,
+ .next_proto_id = input->flow.ip4_flow.proto,
+ };
+ attributes->l3_mask.ipv4.hdr = (struct 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 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 udp_hdr){
+ .src_port = input->flow.udp4_flow.src_port,
+ .dst_port = input->flow.udp4_flow.dst_port,
+ };
+ attributes->l4_mask.udp.hdr = (struct 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 tcp_hdr){
+ .src_port = input->flow.tcp4_flow.src_port,
+ .dst_port = input->flow.tcp4_flow.dst_port,
+ };
+ attributes->l4_mask.tcp.hdr = (struct 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 udp_hdr){
+ .src_port = input->flow.udp6_flow.src_port,
+ .dst_port = input->flow.udp6_flow.dst_port,
+ };
+ attributes->l4_mask.udp.hdr = (struct 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 tcp_hdr){
+ .src_port = input->flow.tcp6_flow.src_port,
+ .dst_port = input->flow.tcp6_flow.dst_port,
+ };
+ attributes->l4_mask.tcp.hdr = (struct 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;
+}
+
+/**
+ * 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
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_fdir_filter_add(struct rte_eth_dev *dev,
+ const struct rte_eth_fdir_filter *fdir_filter)
+{
+ struct priv *priv = dev->data->dev_private;
+ struct mlx5_fdir attributes = {
+ .attr.group = 0,
+ .l2_mask = {
+ .dst.addr_bytes = "\x00\x00\x00\x00\x00\x00",
+ .src.addr_bytes = "\x00\x00\x00\x00\x00\x00",
+ .type = 0,
+ },
+ };
+ struct rte_flow_error error;
+ struct rte_flow *flow;
+ int ret;
+
+ ret = mlx5_fdir_filter_convert(dev, fdir_filter, &attributes);
+ if (ret)
+ return ret;
+ flow = mlx5_flow_list_create(dev, &priv->flows, &attributes.attr,
+ attributes.items, attributes.actions,
+ &error);
+ if (flow) {
+ DRV_LOG(DEBUG, "port %u FDIR created %p", dev->data->port_id,
+ (void *)flow);
+ return 0;
+ }
+ return -rte_errno;
+}
+
+/**
+ * Delete specific filter.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param fdir_filter
+ * Filter to be deleted.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_fdir_filter_delete(struct rte_eth_dev *dev __rte_unused,
+ const struct rte_eth_fdir_filter *fdir_filter
+ __rte_unused)
+{
+ rte_errno = ENOTSUP;
+ return -rte_errno;
+}
+
+/**
+ * Update queue for specific filter.
+ *
+ * @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.
+ */
+static int
+mlx5_fdir_filter_update(struct rte_eth_dev *dev,
+ const struct rte_eth_fdir_filter *fdir_filter)
+{
+ int ret;
+
+ ret = mlx5_fdir_filter_delete(dev, fdir_filter);
+ if (ret)
+ return ret;
+ return mlx5_fdir_filter_add(dev, fdir_filter);
+}
+
+/**
+ * Flush all filters.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ */
+static void
+mlx5_fdir_filter_flush(struct rte_eth_dev *dev)
+{
+ struct priv *priv = dev->data->dev_private;
+
+ mlx5_flow_list_flush(dev, &priv->flows);
+}
+
+/**
+ * Get flow director information.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param[out] fdir_info
+ * Resulting flow director information.
+ */
+static void
+mlx5_fdir_info_get(struct rte_eth_dev *dev, struct rte_eth_fdir_info *fdir_info)
+{
+ 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));
+}
+
+/**
+ * Deal with flow director operations.
+ *
+ * @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 int
+mlx5_fdir_ctrl_func(struct rte_eth_dev *dev, enum rte_filter_op filter_op,
+ void *arg)
+{
+ enum rte_fdir_mode fdir_mode =
+ dev->data->dev_conf.fdir_conf.mode;
+
+ 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 mlx5_fdir_filter_add(dev, arg);
+ case RTE_ETH_FILTER_UPDATE:
+ return mlx5_fdir_filter_update(dev, arg);
+ case RTE_ETH_FILTER_DELETE:
+ return mlx5_fdir_filter_delete(dev, arg);
+ case RTE_ETH_FILTER_FLUSH:
+ mlx5_fdir_filter_flush(dev);
+ break;
+ case RTE_ETH_FILTER_INFO:
+ mlx5_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;
+}
+
+/**
+ * Manage filter operations.
+ *
+ * @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_dev_filter_ctrl(struct rte_eth_dev *dev,
+ enum rte_filter_type filter_type,
+ enum rte_filter_op filter_op,
+ void *arg)
+{
+ 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 mlx5_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;
+}