#include <assert.h>
#include <errno.h>
#include <libmnl/libmnl.h>
+#include <linux/gen_stats.h>
#include <linux/if_ether.h>
#include <linux/netlink.h>
#include <linux/pkt_cls.h>
#include <rte_ether.h>
#include <rte_flow.h>
#include <rte_malloc.h>
+#include <rte_common.h>
#include "mlx5.h"
#include "mlx5_flow.h"
#endif /* HAVE_TC_ACT_VLAN */
+#ifdef HAVE_TC_ACT_TUNNEL_KEY
+
+#include <linux/tc_act/tc_tunnel_key.h>
+
+#ifndef HAVE_TCA_TUNNEL_KEY_ENC_DST_PORT
+#define TCA_TUNNEL_KEY_ENC_DST_PORT 9
+#endif
+
+#ifndef HAVE_TCA_TUNNEL_KEY_NO_CSUM
+#define TCA_TUNNEL_KEY_NO_CSUM 10
+#endif
+
+#else /* HAVE_TC_ACT_TUNNEL_KEY */
+
+#define TCA_ACT_TUNNEL_KEY 17
+#define TCA_TUNNEL_KEY_ACT_SET 1
+#define TCA_TUNNEL_KEY_ACT_RELEASE 2
+#define TCA_TUNNEL_KEY_PARMS 2
+#define TCA_TUNNEL_KEY_ENC_IPV4_SRC 3
+#define TCA_TUNNEL_KEY_ENC_IPV4_DST 4
+#define TCA_TUNNEL_KEY_ENC_IPV6_SRC 5
+#define TCA_TUNNEL_KEY_ENC_IPV6_DST 6
+#define TCA_TUNNEL_KEY_ENC_KEY_ID 7
+#define TCA_TUNNEL_KEY_ENC_DST_PORT 9
+#define TCA_TUNNEL_KEY_NO_CSUM 10
+
+struct tc_tunnel_key {
+ tc_gen;
+ int t_action;
+};
+
+#endif /* HAVE_TC_ACT_TUNNEL_KEY */
+
/* Normally found in linux/netlink.h. */
#ifndef NETLINK_CAP_ACK
#define NETLINK_CAP_ACK 10
#ifndef HAVE_TCA_FLOWER_KEY_VLAN_ETH_TYPE
#define TCA_FLOWER_KEY_VLAN_ETH_TYPE 25
#endif
+#ifndef HAVE_TCA_FLOWER_KEY_ENC_KEY_ID
+#define TCA_FLOWER_KEY_ENC_KEY_ID 26
+#endif
+#ifndef HAVE_TCA_FLOWER_KEY_ENC_IPV4_SRC
+#define TCA_FLOWER_KEY_ENC_IPV4_SRC 27
+#endif
+#ifndef HAVE_TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK
+#define TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK 28
+#endif
+#ifndef HAVE_TCA_FLOWER_KEY_ENC_IPV4_DST
+#define TCA_FLOWER_KEY_ENC_IPV4_DST 29
+#endif
+#ifndef HAVE_TCA_FLOWER_KEY_ENC_IPV4_DST_MASK
+#define TCA_FLOWER_KEY_ENC_IPV4_DST_MASK 30
+#endif
+#ifndef HAVE_TCA_FLOWER_KEY_ENC_IPV6_SRC
+#define TCA_FLOWER_KEY_ENC_IPV6_SRC 31
+#endif
+#ifndef HAVE_TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK
+#define TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK 32
+#endif
+#ifndef HAVE_TCA_FLOWER_KEY_ENC_IPV6_DST
+#define TCA_FLOWER_KEY_ENC_IPV6_DST 33
+#endif
+#ifndef HAVE_TCA_FLOWER_KEY_ENC_IPV6_DST_MASK
+#define TCA_FLOWER_KEY_ENC_IPV6_DST_MASK 34
+#endif
+#ifndef HAVE_TCA_FLOWER_KEY_ENC_UDP_SRC_PORT
+#define TCA_FLOWER_KEY_ENC_UDP_SRC_PORT 43
+#endif
+#ifndef HAVE_TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK
+#define TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK 44
+#endif
+#ifndef HAVE_TCA_FLOWER_KEY_ENC_UDP_DST_PORT
+#define TCA_FLOWER_KEY_ENC_UDP_DST_PORT 45
+#endif
+#ifndef HAVE_TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK
+#define TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK 46
+#endif
#ifndef HAVE_TCA_FLOWER_KEY_TCP_FLAGS
#define TCA_FLOWER_KEY_TCP_FLAGS 71
#endif
#define TTL_LEN 1
#endif
+#ifndef TCA_ACT_MAX_PRIO
+#define TCA_ACT_MAX_PRIO 32
+#endif
+
+/** UDP port range of VXLAN devices created by driver. */
+#define MLX5_VXLAN_PORT_MIN 30000
+#define MLX5_VXLAN_PORT_MAX 60000
+#define MLX5_VXLAN_DEVICE_PFX "vmlx_"
+
+/** Tunnel action type, used for @p type in header structure. */
+enum flow_tcf_tunact_type {
+ FLOW_TCF_TUNACT_VXLAN_DECAP,
+ FLOW_TCF_TUNACT_VXLAN_ENCAP,
+};
+
+/** Flags used for @p mask in tunnel action encap descriptors. */
+#define FLOW_TCF_ENCAP_ETH_SRC (1u << 0)
+#define FLOW_TCF_ENCAP_ETH_DST (1u << 1)
+#define FLOW_TCF_ENCAP_IPV4_SRC (1u << 2)
+#define FLOW_TCF_ENCAP_IPV4_DST (1u << 3)
+#define FLOW_TCF_ENCAP_IPV6_SRC (1u << 4)
+#define FLOW_TCF_ENCAP_IPV6_DST (1u << 5)
+#define FLOW_TCF_ENCAP_UDP_SRC (1u << 6)
+#define FLOW_TCF_ENCAP_UDP_DST (1u << 7)
+#define FLOW_TCF_ENCAP_VXLAN_VNI (1u << 8)
+
+/**
+ * Structure for holding netlink context.
+ * Note the size of the message buffer which is MNL_SOCKET_BUFFER_SIZE.
+ * Using this (8KB) buffer size ensures that netlink messages will never be
+ * truncated.
+ */
+struct mlx5_flow_tcf_context {
+ struct mnl_socket *nl; /* NETLINK_ROUTE libmnl socket. */
+ uint32_t seq; /* Message sequence number. */
+ uint32_t buf_size; /* Message buffer size. */
+ uint8_t *buf; /* Message buffer. */
+};
+
+/**
+ * Neigh rule structure. The neigh rule is applied via Netlink to
+ * outer tunnel iface in order to provide destination MAC address
+ * for the VXLAN encapsultion. The neigh rule is implicitly related
+ * to the Flow itself and can be shared by multiple Flows.
+ */
+struct tcf_neigh_rule {
+ LIST_ENTRY(tcf_neigh_rule) next;
+ uint32_t refcnt;
+ struct ether_addr eth;
+ uint16_t mask;
+ union {
+ struct {
+ rte_be32_t dst;
+ } ipv4;
+ struct {
+ uint8_t dst[IPV6_ADDR_LEN];
+ } ipv6;
+ };
+};
+
+/**
+ * Local rule structure. The local rule is applied via Netlink to
+ * outer tunnel iface in order to provide local and peer IP addresses
+ * of the VXLAN tunnel for encapsulation. The local rule is implicitly
+ * related to the Flow itself and can be shared by multiple Flows.
+ */
+struct tcf_local_rule {
+ LIST_ENTRY(tcf_local_rule) next;
+ uint32_t refcnt;
+ uint16_t mask;
+ union {
+ struct {
+ rte_be32_t dst;
+ rte_be32_t src;
+ } ipv4;
+ struct {
+ uint8_t dst[IPV6_ADDR_LEN];
+ uint8_t src[IPV6_ADDR_LEN];
+ } ipv6;
+ };
+};
+
+/** VXLAN virtual netdev. */
+struct tcf_vtep {
+ LIST_ENTRY(tcf_vtep) next;
+ LIST_HEAD(, tcf_neigh_rule) neigh;
+ LIST_HEAD(, tcf_local_rule) local;
+ uint32_t refcnt;
+ unsigned int ifindex; /**< Own interface index. */
+ unsigned int ifouter; /**< Index of device attached to. */
+ uint16_t port;
+ uint8_t created;
+};
+
+/** Tunnel descriptor header, common for all tunnel types. */
+struct flow_tcf_tunnel_hdr {
+ uint32_t type; /**< Tunnel action type. */
+ struct tcf_vtep *vtep; /**< Virtual tunnel endpoint device. */
+ unsigned int ifindex_org; /**< Original dst/src interface */
+ unsigned int *ifindex_ptr; /**< Interface ptr in message. */
+};
+
+struct flow_tcf_vxlan_decap {
+ struct flow_tcf_tunnel_hdr hdr;
+ uint16_t udp_port;
+};
+
+struct flow_tcf_vxlan_encap {
+ struct flow_tcf_tunnel_hdr hdr;
+ uint32_t mask;
+ struct {
+ struct ether_addr dst;
+ struct ether_addr src;
+ } eth;
+ union {
+ struct {
+ rte_be32_t dst;
+ rte_be32_t src;
+ } ipv4;
+ struct {
+ uint8_t dst[IPV6_ADDR_LEN];
+ uint8_t src[IPV6_ADDR_LEN];
+ } ipv6;
+ };
+struct {
+ rte_be16_t src;
+ rte_be16_t dst;
+ } udp;
+ struct {
+ uint8_t vni[3];
+ } vxlan;
+};
+
+/** Structure used when extracting the values of a flow counters
+ * from a netlink message.
+ */
+struct flow_tcf_stats_basic {
+ bool valid;
+ struct gnet_stats_basic counters;
+};
+
/** Empty masks for known item types. */
static const union {
struct rte_flow_item_port_id port_id;
struct rte_flow_item_ipv6 ipv6;
struct rte_flow_item_tcp tcp;
struct rte_flow_item_udp udp;
+ struct rte_flow_item_vxlan vxlan;
} flow_tcf_mask_empty;
/** Supported masks for known item types. */
struct rte_flow_item_ipv6 ipv6;
struct rte_flow_item_tcp tcp;
struct rte_flow_item_udp udp;
+ struct rte_flow_item_vxlan vxlan;
} flow_tcf_mask_supported = {
.port_id = {
.id = 0xffffffff,
.src_port = RTE_BE16(0xffff),
.dst_port = RTE_BE16(0xffff),
},
+ .vxlan = {
+ .vni = "\xff\xff\xff",
+ },
};
#define SZ_NLATTR_HDR MNL_ALIGN(sizeof(struct nlattr))
(MLX5_FLOW_ACTION_OF_POP_VLAN | MLX5_FLOW_ACTION_OF_PUSH_VLAN | \
MLX5_FLOW_ACTION_OF_SET_VLAN_VID | MLX5_FLOW_ACTION_OF_SET_VLAN_PCP)
+#define MLX5_TCF_VXLAN_ACTIONS \
+ (MLX5_FLOW_ACTION_VXLAN_ENCAP | MLX5_FLOW_ACTION_VXLAN_DECAP)
+
#define MLX5_TCF_PEDIT_ACTIONS \
(MLX5_FLOW_ACTION_SET_IPV4_SRC | MLX5_FLOW_ACTION_SET_IPV4_DST | \
MLX5_FLOW_ACTION_SET_IPV6_SRC | MLX5_FLOW_ACTION_SET_IPV6_DST | \
MLX5_FLOW_ACTION_SET_TP_SRC | MLX5_FLOW_ACTION_SET_TP_DST | \
- MLX5_FLOW_ACTION_SET_TTL | MLX5_FLOW_ACTION_DEC_TTL)
+ MLX5_FLOW_ACTION_SET_TTL | MLX5_FLOW_ACTION_DEC_TTL | \
+ MLX5_FLOW_ACTION_SET_MAC_SRC | MLX5_FLOW_ACTION_SET_MAC_DST)
#define MLX5_TCF_CONFIG_ACTIONS \
(MLX5_FLOW_ACTION_PORT_ID | MLX5_FLOW_ACTION_JUMP | \
struct pedit_key_ex keys_ex[MAX_PEDIT_KEYS];
};
+/**
+ * Create space for using the implicitly created TC flow counter.
+ *
+ * @param[in] dev
+ * Pointer to the Ethernet device structure.
+ *
+ * @return
+ * A pointer to the counter data structure, NULL otherwise and
+ * rte_errno is set.
+ */
+static struct mlx5_flow_counter *
+flow_tcf_counter_new(void)
+{
+ struct mlx5_flow_counter *cnt;
+
+ /*
+ * eswitch counter cannot be shared and its id is unknown.
+ * currently returning all with id 0.
+ * in the future maybe better to switch to unique numbers.
+ */
+ struct mlx5_flow_counter tmpl = {
+ .ref_cnt = 1,
+ };
+ cnt = rte_calloc(__func__, 1, sizeof(*cnt), 0);
+ if (!cnt) {
+ rte_errno = ENOMEM;
+ return NULL;
+ }
+ *cnt = tmpl;
+ /* Implicit counter, do not add to list. */
+ return cnt;
+}
+
+/**
+ * Set pedit key of MAC address
+ *
+ * @param[in] actions
+ * pointer to action specification
+ * @param[in,out] p_parser
+ * pointer to pedit_parser
+ */
+static void
+flow_tcf_pedit_key_set_mac(const struct rte_flow_action *actions,
+ struct pedit_parser *p_parser)
+{
+ int idx = p_parser->sel.nkeys;
+ uint32_t off = actions->type == RTE_FLOW_ACTION_TYPE_SET_MAC_SRC ?
+ offsetof(struct ether_hdr, s_addr) :
+ offsetof(struct ether_hdr, d_addr);
+ const struct rte_flow_action_set_mac *conf =
+ (const struct rte_flow_action_set_mac *)actions->conf;
+
+ p_parser->keys[idx].off = off;
+ p_parser->keys[idx].mask = ~UINT32_MAX;
+ p_parser->keys_ex[idx].htype = TCA_PEDIT_KEY_EX_HDR_TYPE_ETH;
+ p_parser->keys_ex[idx].cmd = TCA_PEDIT_KEY_EX_CMD_SET;
+ memcpy(&p_parser->keys[idx].val,
+ conf->mac_addr, SZ_PEDIT_KEY_VAL);
+ idx++;
+ p_parser->keys[idx].off = off + SZ_PEDIT_KEY_VAL;
+ p_parser->keys[idx].mask = 0xFFFF0000;
+ p_parser->keys_ex[idx].htype = TCA_PEDIT_KEY_EX_HDR_TYPE_ETH;
+ p_parser->keys_ex[idx].cmd = TCA_PEDIT_KEY_EX_CMD_SET;
+ memcpy(&p_parser->keys[idx].val,
+ conf->mac_addr + SZ_PEDIT_KEY_VAL,
+ ETHER_ADDR_LEN - SZ_PEDIT_KEY_VAL);
+ p_parser->sel.nkeys = (++idx);
+}
/**
* Set pedit key of decrease/set ttl
flow_tcf_pedit_key_set_dec_ttl(*actions,
&p_parser, item_flags);
break;
+ case RTE_FLOW_ACTION_TYPE_SET_MAC_SRC:
+ case RTE_FLOW_ACTION_TYPE_SET_MAC_DST:
+ flow_tcf_pedit_key_set_mac(*actions, &p_parser);
+ break;
default:
goto pedit_mnl_msg_done;
}
keys += NUM_OF_PEDIT_KEYS(TTL_LEN);
flags |= MLX5_FLOW_ACTION_DEC_TTL;
break;
+ case RTE_FLOW_ACTION_TYPE_SET_MAC_SRC:
+ keys += NUM_OF_PEDIT_KEYS(ETHER_ADDR_LEN);
+ flags |= MLX5_FLOW_ACTION_SET_MAC_SRC;
+ break;
+ case RTE_FLOW_ACTION_TYPE_SET_MAC_DST:
+ keys += NUM_OF_PEDIT_KEYS(ETHER_ADDR_LEN);
+ flags |= MLX5_FLOW_ACTION_SET_MAC_DST;
+ break;
default:
goto get_pedit_action_size_done;
}
}
/**
- * Validate flow for E-Switch.
+ * Validate VXLAN_ENCAP action RTE_FLOW_ITEM_TYPE_ETH item for E-Switch.
+ * The routine checks the L2 fields to be used in encapsulation header.
*
- * @param[in] priv
- * Pointer to the priv 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[in] item
+ * Pointer to the item structure.
* @param[out] error
* Pointer to the error structure.
*
* @return
- * 0 on success, a negative errno value otherwise and rte_ernno is set.
- */
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ **/
static int
-flow_tcf_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)
+flow_tcf_validate_vxlan_encap_eth(const struct rte_flow_item *item,
+ struct rte_flow_error *error)
{
- union {
- const struct rte_flow_item_port_id *port_id;
- const struct rte_flow_item_eth *eth;
- const struct rte_flow_item_vlan *vlan;
- const struct rte_flow_item_ipv4 *ipv4;
- const struct rte_flow_item_ipv6 *ipv6;
- const struct rte_flow_item_tcp *tcp;
- const struct rte_flow_item_udp *udp;
- } spec, mask;
- union {
- const struct rte_flow_action_port_id *port_id;
- const struct rte_flow_action_jump *jump;
- const struct rte_flow_action_of_push_vlan *of_push_vlan;
- const struct rte_flow_action_of_set_vlan_vid *
- of_set_vlan_vid;
- const struct rte_flow_action_of_set_vlan_pcp *
- of_set_vlan_pcp;
- const struct rte_flow_action_set_ipv4 *set_ipv4;
- const struct rte_flow_action_set_ipv6 *set_ipv6;
- } conf;
- uint32_t item_flags = 0;
- uint32_t action_flags = 0;
- uint8_t next_protocol = -1;
- unsigned int tcm_ifindex = 0;
- uint8_t pedit_validated = 0;
- struct flow_tcf_ptoi ptoi[PTOI_TABLE_SZ_MAX(dev)];
- struct rte_eth_dev *port_id_dev = NULL;
- bool in_port_id_set;
- int ret;
+ const struct rte_flow_item_eth *spec = item->spec;
+ const struct rte_flow_item_eth *mask = item->mask;
- claim_nonzero(flow_tcf_build_ptoi_table(dev, ptoi,
- PTOI_TABLE_SZ_MAX(dev)));
- ret = flow_tcf_validate_attributes(attr, error);
- if (ret < 0)
- return ret;
- for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) {
- unsigned int i;
+ if (!spec) {
+ /*
+ * Specification for L2 addresses can be empty
+ * because these ones are optional and not
+ * required directly by tc rule. Kernel tries
+ * to resolve these ones on its own
+ */
+ return 0;
+ }
+ if (!mask) {
+ /* If mask is not specified use the default one. */
+ mask = &rte_flow_item_eth_mask;
+ }
+ if (memcmp(&mask->dst,
+ &flow_tcf_mask_empty.eth.dst,
+ sizeof(flow_tcf_mask_empty.eth.dst))) {
+ if (memcmp(&mask->dst,
+ &rte_flow_item_eth_mask.dst,
+ sizeof(rte_flow_item_eth_mask.dst)))
+ return rte_flow_error_set
+ (error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
+ "no support for partial mask on"
+ " \"eth.dst\" field");
+ }
+ if (memcmp(&mask->src,
+ &flow_tcf_mask_empty.eth.src,
+ sizeof(flow_tcf_mask_empty.eth.src))) {
+ if (memcmp(&mask->src,
+ &rte_flow_item_eth_mask.src,
+ sizeof(rte_flow_item_eth_mask.src)))
+ return rte_flow_error_set
+ (error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
+ "no support for partial mask on"
+ " \"eth.src\" field");
+ }
+ if (mask->type != RTE_BE16(0x0000)) {
+ if (mask->type != RTE_BE16(0xffff))
+ return rte_flow_error_set
+ (error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
+ "no support for partial mask on"
+ " \"eth.type\" field");
+ DRV_LOG(WARNING,
+ "outer ethernet type field"
+ " cannot be forced for vxlan"
+ " encapsulation, parameter ignored");
+ }
+ return 0;
+}
- switch (items->type) {
- case RTE_FLOW_ITEM_TYPE_VOID:
- break;
- case RTE_FLOW_ITEM_TYPE_PORT_ID:
- mask.port_id = flow_tcf_item_mask
- (items, &rte_flow_item_port_id_mask,
- &flow_tcf_mask_supported.port_id,
- &flow_tcf_mask_empty.port_id,
- sizeof(flow_tcf_mask_supported.port_id),
- error);
- if (!mask.port_id)
- return -rte_errno;
- if (mask.port_id == &flow_tcf_mask_empty.port_id) {
- in_port_id_set = 1;
- break;
- }
- spec.port_id = items->spec;
- if (mask.port_id->id && mask.port_id->id != 0xffffffff)
- return rte_flow_error_set
+/**
+ * Validate VXLAN_ENCAP action RTE_FLOW_ITEM_TYPE_IPV4 item for E-Switch.
+ * The routine checks the IPv4 fields to be used in encapsulation header.
+ *
+ * @param[in] item
+ * Pointer to the item structure.
+ * @param[out] error
+ * Pointer to the error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ **/
+static int
+flow_tcf_validate_vxlan_encap_ipv4(const struct rte_flow_item *item,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_ipv4 *spec = item->spec;
+ const struct rte_flow_item_ipv4 *mask = item->mask;
+
+ if (!spec) {
+ /*
+ * Specification for IP addresses cannot be empty
+ * because it is required by tunnel_key parameter.
+ */
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "NULL outer ipv4 address"
+ " specification for vxlan"
+ " encapsulation");
+ }
+ if (!mask)
+ mask = &rte_flow_item_ipv4_mask;
+ if (mask->hdr.dst_addr != RTE_BE32(0x00000000)) {
+ if (mask->hdr.dst_addr != RTE_BE32(0xffffffff))
+ return rte_flow_error_set
+ (error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
+ "no support for partial mask on"
+ " \"ipv4.hdr.dst_addr\" field"
+ " for vxlan encapsulation");
+ /* More IPv4 address validations can be put here. */
+ } else {
+ /*
+ * Kernel uses the destination IP address to determine
+ * the routing path and obtain the MAC destination
+ * address, so IP destination address must be
+ * specified in the tc rule.
+ */
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "outer ipv4 destination address"
+ " must be specified for"
+ " vxlan encapsulation");
+ }
+ if (mask->hdr.src_addr != RTE_BE32(0x00000000)) {
+ if (mask->hdr.src_addr != RTE_BE32(0xffffffff))
+ return rte_flow_error_set
+ (error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
+ "no support for partial mask on"
+ " \"ipv4.hdr.src_addr\" field"
+ " for vxlan encapsulation");
+ /* More IPv4 address validations can be put here. */
+ } else {
+ /*
+ * Kernel uses the source IP address to select the
+ * interface for egress encapsulated traffic, so
+ * it must be specified in the tc rule.
+ */
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "outer ipv4 source address"
+ " must be specified for"
+ " vxlan encapsulation");
+ }
+ return 0;
+}
+
+/**
+ * Validate VXLAN_ENCAP action RTE_FLOW_ITEM_TYPE_IPV6 item for E-Switch.
+ * The routine checks the IPv6 fields to be used in encapsulation header.
+ *
+ * @param[in] item
+ * Pointer to the item structure.
+ * @param[out] error
+ * Pointer to the error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_ernno is set.
+ **/
+static int
+flow_tcf_validate_vxlan_encap_ipv6(const struct rte_flow_item *item,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_ipv6 *spec = item->spec;
+ const struct rte_flow_item_ipv6 *mask = item->mask;
+
+ if (!spec) {
+ /*
+ * Specification for IP addresses cannot be empty
+ * because it is required by tunnel_key parameter.
+ */
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "NULL outer ipv6 address"
+ " specification for"
+ " vxlan encapsulation");
+ }
+ if (!mask)
+ mask = &rte_flow_item_ipv6_mask;
+ if (memcmp(&mask->hdr.dst_addr,
+ &flow_tcf_mask_empty.ipv6.hdr.dst_addr,
+ IPV6_ADDR_LEN)) {
+ if (memcmp(&mask->hdr.dst_addr,
+ &rte_flow_item_ipv6_mask.hdr.dst_addr,
+ IPV6_ADDR_LEN))
+ return rte_flow_error_set
(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ITEM_MASK,
- mask.port_id,
+ RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
"no support for partial mask on"
- " \"id\" field");
- if (!mask.port_id->id)
- i = 0;
- else
- for (i = 0; ptoi[i].ifindex; ++i)
- if (ptoi[i].port_id == spec.port_id->id)
- break;
- if (!ptoi[i].ifindex)
- return rte_flow_error_set
- (error, ENODEV,
- RTE_FLOW_ERROR_TYPE_ITEM_SPEC,
- spec.port_id,
- "missing data to convert port ID to"
- " ifindex");
- if (in_port_id_set && ptoi[i].ifindex != tcm_ifindex)
- return rte_flow_error_set
+ " \"ipv6.hdr.dst_addr\" field"
+ " for vxlan encapsulation");
+ /* More IPv6 address validations can be put here. */
+ } else {
+ /*
+ * Kernel uses the destination IP address to determine
+ * the routing path and obtain the MAC destination
+ * address (heigh or gate), so IP destination address
+ * must be specified within the tc rule.
+ */
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "outer ipv6 destination address"
+ " must be specified for"
+ " vxlan encapsulation");
+ }
+ if (memcmp(&mask->hdr.src_addr,
+ &flow_tcf_mask_empty.ipv6.hdr.src_addr,
+ IPV6_ADDR_LEN)) {
+ if (memcmp(&mask->hdr.src_addr,
+ &rte_flow_item_ipv6_mask.hdr.src_addr,
+ IPV6_ADDR_LEN))
+ return rte_flow_error_set
(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ITEM_SPEC,
- spec.port_id,
- "cannot match traffic for"
- " several port IDs through"
- " a single flow rule");
- tcm_ifindex = ptoi[i].ifindex;
- in_port_id_set = 1;
- break;
- case RTE_FLOW_ITEM_TYPE_ETH:
- ret = mlx5_flow_validate_item_eth(items, item_flags,
- error);
- if (ret < 0)
- return ret;
- item_flags |= MLX5_FLOW_LAYER_OUTER_L2;
- /* TODO:
- * Redundant check due to different supported mask.
- * Same for the rest of items.
- */
- mask.eth = flow_tcf_item_mask
- (items, &rte_flow_item_eth_mask,
- &flow_tcf_mask_supported.eth,
- &flow_tcf_mask_empty.eth,
+ RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
+ "no support for partial mask on"
+ " \"ipv6.hdr.src_addr\" field"
+ " for vxlan encapsulation");
+ /* More L3 address validation can be put here. */
+ } else {
+ /*
+ * Kernel uses the source IP address to select the
+ * interface for egress encapsulated traffic, so
+ * it must be specified in the tc rule.
+ */
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "outer L3 source address"
+ " must be specified for"
+ " vxlan encapsulation");
+ }
+ return 0;
+}
+
+/**
+ * Validate VXLAN_ENCAP action RTE_FLOW_ITEM_TYPE_UDP item for E-Switch.
+ * The routine checks the UDP fields to be used in encapsulation header.
+ *
+ * @param[in] item
+ * Pointer to the item structure.
+ * @param[out] error
+ * Pointer to the error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_ernno is set.
+ **/
+static int
+flow_tcf_validate_vxlan_encap_udp(const struct rte_flow_item *item,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_udp *spec = item->spec;
+ const struct rte_flow_item_udp *mask = item->mask;
+
+ if (!spec) {
+ /*
+ * Specification for UDP ports cannot be empty
+ * because it is required by tunnel_key parameter.
+ */
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "NULL UDP port specification "
+ " for vxlan encapsulation");
+ }
+ if (!mask)
+ mask = &rte_flow_item_udp_mask;
+ if (mask->hdr.dst_port != RTE_BE16(0x0000)) {
+ if (mask->hdr.dst_port != RTE_BE16(0xffff))
+ return rte_flow_error_set
+ (error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
+ "no support for partial mask on"
+ " \"udp.hdr.dst_port\" field"
+ " for vxlan encapsulation");
+ if (!spec->hdr.dst_port)
+ return rte_flow_error_set
+ (error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "outer UDP remote port cannot be"
+ " 0 for vxlan encapsulation");
+ } else {
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "outer UDP remote port"
+ " must be specified for"
+ " vxlan encapsulation");
+ }
+ if (mask->hdr.src_port != RTE_BE16(0x0000)) {
+ if (mask->hdr.src_port != RTE_BE16(0xffff))
+ return rte_flow_error_set
+ (error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
+ "no support for partial mask on"
+ " \"udp.hdr.src_port\" field"
+ " for vxlan encapsulation");
+ DRV_LOG(WARNING,
+ "outer UDP source port cannot be"
+ " forced for vxlan encapsulation,"
+ " parameter ignored");
+ }
+ return 0;
+}
+
+/**
+ * Validate VXLAN_ENCAP action RTE_FLOW_ITEM_TYPE_VXLAN item for E-Switch.
+ * The routine checks the VNIP fields to be used in encapsulation header.
+ *
+ * @param[in] item
+ * Pointer to the item structure.
+ * @param[out] error
+ * Pointer to the error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_ernno is set.
+ **/
+static int
+flow_tcf_validate_vxlan_encap_vni(const struct rte_flow_item *item,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_vxlan *spec = item->spec;
+ const struct rte_flow_item_vxlan *mask = item->mask;
+
+ if (!spec) {
+ /* Outer VNI is required by tunnel_key parameter. */
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "NULL VNI specification"
+ " for vxlan encapsulation");
+ }
+ if (!mask)
+ mask = &rte_flow_item_vxlan_mask;
+ if (!mask->vni[0] && !mask->vni[1] && !mask->vni[2])
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "outer VNI must be specified "
+ "for vxlan encapsulation");
+ if (mask->vni[0] != 0xff ||
+ mask->vni[1] != 0xff ||
+ mask->vni[2] != 0xff)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
+ "no support for partial mask on"
+ " \"vxlan.vni\" field");
+
+ if (!spec->vni[0] && !spec->vni[1] && !spec->vni[2])
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, item,
+ "vxlan vni cannot be 0");
+ return 0;
+}
+
+/**
+ * Validate VXLAN_ENCAP action item list for E-Switch.
+ * The routine checks items to be used in encapsulation header.
+ *
+ * @param[in] action
+ * Pointer to the VXLAN_ENCAP action structure.
+ * @param[out] error
+ * Pointer to the error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_ernno is set.
+ **/
+static int
+flow_tcf_validate_vxlan_encap(const struct rte_flow_action *action,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item *items;
+ int ret;
+ uint32_t item_flags = 0;
+
+ if (!action->conf)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, action,
+ "Missing vxlan tunnel"
+ " action configuration");
+ items = ((const struct rte_flow_action_vxlan_encap *)
+ action->conf)->definition;
+ if (!items)
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, action,
+ "Missing vxlan tunnel"
+ " encapsulation parameters");
+ for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) {
+ switch (items->type) {
+ case RTE_FLOW_ITEM_TYPE_VOID:
+ break;
+ case RTE_FLOW_ITEM_TYPE_ETH:
+ ret = mlx5_flow_validate_item_eth(items, item_flags,
+ error);
+ if (ret < 0)
+ return ret;
+ ret = flow_tcf_validate_vxlan_encap_eth(items, error);
+ if (ret < 0)
+ return ret;
+ item_flags |= MLX5_FLOW_LAYER_OUTER_L2;
+ break;
+ break;
+ case RTE_FLOW_ITEM_TYPE_IPV4:
+ ret = mlx5_flow_validate_item_ipv4(items, item_flags,
+ error);
+ if (ret < 0)
+ return ret;
+ ret = flow_tcf_validate_vxlan_encap_ipv4(items, error);
+ if (ret < 0)
+ return ret;
+ item_flags |= MLX5_FLOW_LAYER_OUTER_L3_IPV4;
+ break;
+ case RTE_FLOW_ITEM_TYPE_IPV6:
+ ret = mlx5_flow_validate_item_ipv6(items, item_flags,
+ error);
+ if (ret < 0)
+ return ret;
+ ret = flow_tcf_validate_vxlan_encap_ipv6(items, error);
+ if (ret < 0)
+ return ret;
+ item_flags |= MLX5_FLOW_LAYER_OUTER_L3_IPV6;
+ break;
+ case RTE_FLOW_ITEM_TYPE_UDP:
+ ret = mlx5_flow_validate_item_udp(items, item_flags,
+ 0xFF, error);
+ if (ret < 0)
+ return ret;
+ ret = flow_tcf_validate_vxlan_encap_udp(items, error);
+ if (ret < 0)
+ return ret;
+ item_flags |= MLX5_FLOW_LAYER_OUTER_L4_UDP;
+ break;
+ case RTE_FLOW_ITEM_TYPE_VXLAN:
+ ret = mlx5_flow_validate_item_vxlan(items,
+ item_flags, error);
+ if (ret < 0)
+ return ret;
+ ret = flow_tcf_validate_vxlan_encap_vni(items, error);
+ if (ret < 0)
+ return ret;
+ item_flags |= MLX5_FLOW_LAYER_VXLAN;
+ break;
+ default:
+ return rte_flow_error_set
+ (error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM, items,
+ "vxlan encap item not supported");
+ }
+ }
+ if (!(item_flags & MLX5_FLOW_LAYER_OUTER_L3))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, action,
+ "no outer IP layer found"
+ " for vxlan encapsulation");
+ if (!(item_flags & MLX5_FLOW_LAYER_OUTER_L4_UDP))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, action,
+ "no outer UDP layer found"
+ " for vxlan encapsulation");
+ if (!(item_flags & MLX5_FLOW_LAYER_VXLAN))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION, action,
+ "no VXLAN VNI found"
+ " for vxlan encapsulation");
+ return 0;
+}
+
+/**
+ * Validate RTE_FLOW_ITEM_TYPE_IPV4 item if VXLAN_DECAP action
+ * is present in actions list.
+ *
+ * @param[in] ipv4
+ * Outer IPv4 address item (if any, NULL otherwise).
+ * @param[out] error
+ * Pointer to the error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_ernno is set.
+ **/
+static int
+flow_tcf_validate_vxlan_decap_ipv4(const struct rte_flow_item *ipv4,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_ipv4 *spec = ipv4->spec;
+ const struct rte_flow_item_ipv4 *mask = ipv4->mask;
+
+ if (!spec) {
+ /*
+ * Specification for IP addresses cannot be empty
+ * because it is required as decap parameter.
+ */
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, ipv4,
+ "NULL outer ipv4 address"
+ " specification for vxlan"
+ " for vxlan decapsulation");
+ }
+ if (!mask)
+ mask = &rte_flow_item_ipv4_mask;
+ if (mask->hdr.dst_addr != RTE_BE32(0x00000000)) {
+ if (mask->hdr.dst_addr != RTE_BE32(0xffffffff))
+ return rte_flow_error_set
+ (error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
+ "no support for partial mask on"
+ " \"ipv4.hdr.dst_addr\" field");
+ /* More IP address validations can be put here. */
+ } else {
+ /*
+ * Kernel uses the destination IP address
+ * to determine the ingress network interface
+ * for traffic being decapsulated.
+ */
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, ipv4,
+ "outer ipv4 destination address"
+ " must be specified for"
+ " vxlan decapsulation");
+ }
+ /* Source IP address is optional for decap. */
+ if (mask->hdr.src_addr != RTE_BE32(0x00000000) &&
+ mask->hdr.src_addr != RTE_BE32(0xffffffff))
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
+ "no support for partial mask on"
+ " \"ipv4.hdr.src_addr\" field");
+ return 0;
+}
+
+/**
+ * Validate RTE_FLOW_ITEM_TYPE_IPV6 item if VXLAN_DECAP action
+ * is present in actions list.
+ *
+ * @param[in] ipv6
+ * Outer IPv6 address item (if any, NULL otherwise).
+ * @param[out] error
+ * Pointer to the error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_ernno is set.
+ **/
+static int
+flow_tcf_validate_vxlan_decap_ipv6(const struct rte_flow_item *ipv6,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_ipv6 *spec = ipv6->spec;
+ const struct rte_flow_item_ipv6 *mask = ipv6->mask;
+
+ if (!spec) {
+ /*
+ * Specification for IP addresses cannot be empty
+ * because it is required as decap parameter.
+ */
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, ipv6,
+ "NULL outer ipv6 address"
+ " specification for vxlan"
+ " decapsulation");
+ }
+ if (!mask)
+ mask = &rte_flow_item_ipv6_mask;
+ if (memcmp(&mask->hdr.dst_addr,
+ &flow_tcf_mask_empty.ipv6.hdr.dst_addr,
+ IPV6_ADDR_LEN)) {
+ if (memcmp(&mask->hdr.dst_addr,
+ &rte_flow_item_ipv6_mask.hdr.dst_addr,
+ IPV6_ADDR_LEN))
+ return rte_flow_error_set
+ (error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
+ "no support for partial mask on"
+ " \"ipv6.hdr.dst_addr\" field");
+ /* More IP address validations can be put here. */
+ } else {
+ /*
+ * Kernel uses the destination IP address
+ * to determine the ingress network interface
+ * for traffic being decapsulated.
+ */
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, ipv6,
+ "outer ipv6 destination address must be "
+ "specified for vxlan decapsulation");
+ }
+ /* Source IP address is optional for decap. */
+ if (memcmp(&mask->hdr.src_addr,
+ &flow_tcf_mask_empty.ipv6.hdr.src_addr,
+ IPV6_ADDR_LEN)) {
+ if (memcmp(&mask->hdr.src_addr,
+ &rte_flow_item_ipv6_mask.hdr.src_addr,
+ IPV6_ADDR_LEN))
+ return rte_flow_error_set
+ (error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
+ "no support for partial mask on"
+ " \"ipv6.hdr.src_addr\" field");
+ }
+ return 0;
+}
+
+/**
+ * Validate RTE_FLOW_ITEM_TYPE_UDP item if VXLAN_DECAP action
+ * is present in actions list.
+ *
+ * @param[in] udp
+ * Outer UDP layer item (if any, NULL otherwise).
+ * @param[out] error
+ * Pointer to the error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_ernno is set.
+ **/
+static int
+flow_tcf_validate_vxlan_decap_udp(const struct rte_flow_item *udp,
+ struct rte_flow_error *error)
+{
+ const struct rte_flow_item_udp *spec = udp->spec;
+ const struct rte_flow_item_udp *mask = udp->mask;
+
+ if (!spec)
+ /*
+ * Specification for UDP ports cannot be empty
+ * because it is required as decap parameter.
+ */
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, udp,
+ "NULL UDP port specification"
+ " for VXLAN decapsulation");
+ if (!mask)
+ mask = &rte_flow_item_udp_mask;
+ if (mask->hdr.dst_port != RTE_BE16(0x0000)) {
+ if (mask->hdr.dst_port != RTE_BE16(0xffff))
+ return rte_flow_error_set
+ (error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
+ "no support for partial mask on"
+ " \"udp.hdr.dst_port\" field");
+ if (!spec->hdr.dst_port)
+ return rte_flow_error_set
+ (error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, udp,
+ "zero decap local UDP port");
+ } else {
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ITEM, udp,
+ "outer UDP destination port must be "
+ "specified for vxlan decapsulation");
+ }
+ if (mask->hdr.src_port != RTE_BE16(0x0000)) {
+ if (mask->hdr.src_port != RTE_BE16(0xffff))
+ return rte_flow_error_set
+ (error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM_MASK, mask,
+ "no support for partial mask on"
+ " \"udp.hdr.src_port\" field");
+ DRV_LOG(WARNING,
+ "outer UDP local port cannot be "
+ "forced for VXLAN encapsulation, "
+ "parameter ignored");
+ }
+ return 0;
+}
+
+/**
+ * Validate flow for E-Switch.
+ *
+ * @param[in] priv
+ * Pointer to the priv structure.
+ * @param[in] attr
+ * Pointer to the flow attributes.
+ * @param[in] items
+ * Pointer to the list of items.
+ * @param[in] actions
+ * Pointer to the list of actions.
+ * @param[out] error
+ * Pointer to the error structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_ernno is set.
+ */
+static int
+flow_tcf_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)
+{
+ union {
+ const struct rte_flow_item_port_id *port_id;
+ const struct rte_flow_item_eth *eth;
+ const struct rte_flow_item_vlan *vlan;
+ const struct rte_flow_item_ipv4 *ipv4;
+ const struct rte_flow_item_ipv6 *ipv6;
+ const struct rte_flow_item_tcp *tcp;
+ const struct rte_flow_item_udp *udp;
+ const struct rte_flow_item_vxlan *vxlan;
+ } spec, mask;
+ union {
+ const struct rte_flow_action_port_id *port_id;
+ const struct rte_flow_action_jump *jump;
+ const struct rte_flow_action_of_push_vlan *of_push_vlan;
+ const struct rte_flow_action_of_set_vlan_vid *
+ of_set_vlan_vid;
+ const struct rte_flow_action_of_set_vlan_pcp *
+ of_set_vlan_pcp;
+ const struct rte_flow_action_vxlan_encap *vxlan_encap;
+ const struct rte_flow_action_set_ipv4 *set_ipv4;
+ const struct rte_flow_action_set_ipv6 *set_ipv6;
+ } conf;
+ uint64_t item_flags = 0;
+ uint64_t action_flags = 0;
+ uint8_t next_protocol = -1;
+ unsigned int tcm_ifindex = 0;
+ uint8_t pedit_validated = 0;
+ struct flow_tcf_ptoi ptoi[PTOI_TABLE_SZ_MAX(dev)];
+ struct rte_eth_dev *port_id_dev = NULL;
+ bool in_port_id_set;
+ int ret;
+
+ claim_nonzero(flow_tcf_build_ptoi_table(dev, ptoi,
+ PTOI_TABLE_SZ_MAX(dev)));
+ ret = flow_tcf_validate_attributes(attr, error);
+ if (ret < 0)
+ return ret;
+ for (; actions->type != RTE_FLOW_ACTION_TYPE_END; actions++) {
+ unsigned int i;
+ uint64_t current_action_flag = 0;
+
+ switch (actions->type) {
+ case RTE_FLOW_ACTION_TYPE_VOID:
+ break;
+ case RTE_FLOW_ACTION_TYPE_PORT_ID:
+ current_action_flag = MLX5_FLOW_ACTION_PORT_ID;
+ if (!actions->conf)
+ break;
+ conf.port_id = actions->conf;
+ if (conf.port_id->original)
+ i = 0;
+ else
+ for (i = 0; ptoi[i].ifindex; ++i)
+ if (ptoi[i].port_id == conf.port_id->id)
+ break;
+ if (!ptoi[i].ifindex)
+ return rte_flow_error_set
+ (error, ENODEV,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ conf.port_id,
+ "missing data to convert port ID to"
+ " ifindex");
+ port_id_dev = &rte_eth_devices[conf.port_id->id];
+ break;
+ case RTE_FLOW_ACTION_TYPE_JUMP:
+ current_action_flag = MLX5_FLOW_ACTION_JUMP;
+ if (!actions->conf)
+ break;
+ conf.jump = actions->conf;
+ if (attr->group >= conf.jump->group)
+ return rte_flow_error_set
+ (error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ actions,
+ "can jump only to a group forward");
+ break;
+ case RTE_FLOW_ACTION_TYPE_DROP:
+ current_action_flag = MLX5_FLOW_ACTION_DROP;
+ break;
+ case RTE_FLOW_ACTION_TYPE_COUNT:
+ break;
+ case RTE_FLOW_ACTION_TYPE_OF_POP_VLAN:
+ current_action_flag = MLX5_FLOW_ACTION_OF_POP_VLAN;
+ break;
+ case RTE_FLOW_ACTION_TYPE_OF_PUSH_VLAN:
+ current_action_flag = MLX5_FLOW_ACTION_OF_PUSH_VLAN;
+ break;
+ case RTE_FLOW_ACTION_TYPE_OF_SET_VLAN_VID:
+ if (!(action_flags & MLX5_FLOW_ACTION_OF_PUSH_VLAN))
+ return rte_flow_error_set
+ (error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION, actions,
+ "vlan modify is not supported,"
+ " set action must follow push action");
+ current_action_flag = MLX5_FLOW_ACTION_OF_SET_VLAN_VID;
+ break;
+ case RTE_FLOW_ACTION_TYPE_OF_SET_VLAN_PCP:
+ if (!(action_flags & MLX5_FLOW_ACTION_OF_PUSH_VLAN))
+ return rte_flow_error_set
+ (error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION, actions,
+ "vlan modify is not supported,"
+ " set action must follow push action");
+ current_action_flag = MLX5_FLOW_ACTION_OF_SET_VLAN_PCP;
+ break;
+ case RTE_FLOW_ACTION_TYPE_VXLAN_DECAP:
+ current_action_flag = MLX5_FLOW_ACTION_VXLAN_DECAP;
+ break;
+ case RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP:
+ ret = flow_tcf_validate_vxlan_encap(actions, error);
+ if (ret < 0)
+ return ret;
+ current_action_flag = MLX5_FLOW_ACTION_VXLAN_ENCAP;
+ break;
+ case RTE_FLOW_ACTION_TYPE_SET_IPV4_SRC:
+ current_action_flag = MLX5_FLOW_ACTION_SET_IPV4_SRC;
+ break;
+ case RTE_FLOW_ACTION_TYPE_SET_IPV4_DST:
+ current_action_flag = MLX5_FLOW_ACTION_SET_IPV4_DST;
+ break;
+ case RTE_FLOW_ACTION_TYPE_SET_IPV6_SRC:
+ current_action_flag = MLX5_FLOW_ACTION_SET_IPV6_SRC;
+ break;
+ case RTE_FLOW_ACTION_TYPE_SET_IPV6_DST:
+ current_action_flag = MLX5_FLOW_ACTION_SET_IPV6_DST;
+ break;
+ case RTE_FLOW_ACTION_TYPE_SET_TP_SRC:
+ current_action_flag = MLX5_FLOW_ACTION_SET_TP_SRC;
+ break;
+ case RTE_FLOW_ACTION_TYPE_SET_TP_DST:
+ current_action_flag = MLX5_FLOW_ACTION_SET_TP_DST;
+ break;
+ case RTE_FLOW_ACTION_TYPE_SET_TTL:
+ current_action_flag = MLX5_FLOW_ACTION_SET_TTL;
+ break;
+ case RTE_FLOW_ACTION_TYPE_DEC_TTL:
+ current_action_flag = MLX5_FLOW_ACTION_DEC_TTL;
+ break;
+ case RTE_FLOW_ACTION_TYPE_SET_MAC_SRC:
+ current_action_flag = MLX5_FLOW_ACTION_SET_MAC_SRC;
+ break;
+ case RTE_FLOW_ACTION_TYPE_SET_MAC_DST:
+ current_action_flag = MLX5_FLOW_ACTION_SET_MAC_DST;
+ break;
+ default:
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ actions,
+ "action not supported");
+ }
+ if (current_action_flag & MLX5_TCF_CONFIG_ACTIONS) {
+ if (!actions->conf)
+ return rte_flow_error_set
+ (error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+ actions,
+ "action configuration not set");
+ }
+ if ((current_action_flag & MLX5_TCF_PEDIT_ACTIONS) &&
+ pedit_validated)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ actions,
+ "set actions should be "
+ "listed successively");
+ if ((current_action_flag & ~MLX5_TCF_PEDIT_ACTIONS) &&
+ (action_flags & MLX5_TCF_PEDIT_ACTIONS))
+ pedit_validated = 1;
+ if ((current_action_flag & MLX5_TCF_FATE_ACTIONS) &&
+ (action_flags & MLX5_TCF_FATE_ACTIONS))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ actions,
+ "can't have multiple fate"
+ " actions");
+ if ((current_action_flag & MLX5_TCF_VXLAN_ACTIONS) &&
+ (action_flags & MLX5_TCF_VXLAN_ACTIONS))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ actions,
+ "can't have multiple vxlan"
+ " actions");
+ if ((current_action_flag & MLX5_TCF_VXLAN_ACTIONS) &&
+ (action_flags & MLX5_TCF_VLAN_ACTIONS))
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ actions,
+ "can't have vxlan and vlan"
+ " actions in the same rule");
+ action_flags |= current_action_flag;
+ }
+ for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) {
+ unsigned int i;
+
+ if ((item_flags & MLX5_FLOW_LAYER_TUNNEL) &&
+ items->type != RTE_FLOW_ITEM_TYPE_ETH)
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM,
+ items,
+ "only L2 inner item"
+ " is supported");
+ switch (items->type) {
+ case RTE_FLOW_ITEM_TYPE_VOID:
+ break;
+ case RTE_FLOW_ITEM_TYPE_PORT_ID:
+ mask.port_id = flow_tcf_item_mask
+ (items, &rte_flow_item_port_id_mask,
+ &flow_tcf_mask_supported.port_id,
+ &flow_tcf_mask_empty.port_id,
+ sizeof(flow_tcf_mask_supported.port_id),
+ error);
+ if (!mask.port_id)
+ return -rte_errno;
+ if (mask.port_id == &flow_tcf_mask_empty.port_id) {
+ in_port_id_set = 1;
+ break;
+ }
+ spec.port_id = items->spec;
+ if (mask.port_id->id && mask.port_id->id != 0xffffffff)
+ return rte_flow_error_set
+ (error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM_MASK,
+ mask.port_id,
+ "no support for partial mask on"
+ " \"id\" field");
+ if (!mask.port_id->id)
+ i = 0;
+ else
+ for (i = 0; ptoi[i].ifindex; ++i)
+ if (ptoi[i].port_id == spec.port_id->id)
+ break;
+ if (!ptoi[i].ifindex)
+ return rte_flow_error_set
+ (error, ENODEV,
+ RTE_FLOW_ERROR_TYPE_ITEM_SPEC,
+ spec.port_id,
+ "missing data to convert port ID to"
+ " ifindex");
+ if (in_port_id_set && ptoi[i].ifindex != tcm_ifindex)
+ return rte_flow_error_set
+ (error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ITEM_SPEC,
+ spec.port_id,
+ "cannot match traffic for"
+ " several port IDs through"
+ " a single flow rule");
+ tcm_ifindex = ptoi[i].ifindex;
+ in_port_id_set = 1;
+ break;
+ case RTE_FLOW_ITEM_TYPE_ETH:
+ ret = mlx5_flow_validate_item_eth(items, item_flags,
+ error);
+ if (ret < 0)
+ return ret;
+ item_flags |= (item_flags & MLX5_FLOW_LAYER_TUNNEL) ?
+ MLX5_FLOW_LAYER_INNER_L2 :
+ MLX5_FLOW_LAYER_OUTER_L2;
+ /* TODO:
+ * Redundant check due to different supported mask.
+ * Same for the rest of items.
+ */
+ mask.eth = flow_tcf_item_mask
+ (items, &rte_flow_item_eth_mask,
+ &flow_tcf_mask_supported.eth,
+ &flow_tcf_mask_empty.eth,
sizeof(flow_tcf_mask_supported.eth),
error);
if (!mask.eth)
next_protocol =
((const struct rte_flow_item_ipv4 *)
(items->spec))->hdr.next_proto_id;
+ if (action_flags & MLX5_FLOW_ACTION_VXLAN_DECAP) {
+ ret = flow_tcf_validate_vxlan_decap_ipv4
+ (items, error);
+ if (ret < 0)
+ return ret;
+ }
break;
case RTE_FLOW_ITEM_TYPE_IPV6:
ret = mlx5_flow_validate_item_ipv6(items, item_flags,
next_protocol =
((const struct rte_flow_item_ipv6 *)
(items->spec))->hdr.proto;
+ if (action_flags & MLX5_FLOW_ACTION_VXLAN_DECAP) {
+ ret = flow_tcf_validate_vxlan_decap_ipv6
+ (items, error);
+ if (ret < 0)
+ return ret;
+ }
break;
case RTE_FLOW_ITEM_TYPE_UDP:
ret = mlx5_flow_validate_item_udp(items, item_flags,
error);
if (!mask.udp)
return -rte_errno;
+ if (action_flags & MLX5_FLOW_ACTION_VXLAN_DECAP) {
+ ret = flow_tcf_validate_vxlan_decap_udp
+ (items, error);
+ if (ret < 0)
+ return ret;
+ }
break;
case RTE_FLOW_ITEM_TYPE_TCP:
ret = mlx5_flow_validate_item_tcp
(items, item_flags,
next_protocol,
&flow_tcf_mask_supported.tcp,
- error);
- if (ret < 0)
- return ret;
- item_flags |= MLX5_FLOW_LAYER_OUTER_L4_TCP;
- mask.tcp = flow_tcf_item_mask
- (items, &rte_flow_item_tcp_mask,
- &flow_tcf_mask_supported.tcp,
- &flow_tcf_mask_empty.tcp,
- sizeof(flow_tcf_mask_supported.tcp),
- error);
- if (!mask.tcp)
- return -rte_errno;
- break;
- default:
- return rte_flow_error_set(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ITEM,
- NULL, "item not supported");
- }
- }
- for (; actions->type != RTE_FLOW_ACTION_TYPE_END; actions++) {
- unsigned int i;
- uint32_t current_action_flag = 0;
-
- switch (actions->type) {
- case RTE_FLOW_ACTION_TYPE_VOID:
- break;
- case RTE_FLOW_ACTION_TYPE_PORT_ID:
- current_action_flag = MLX5_FLOW_ACTION_PORT_ID;
- if (!actions->conf)
- break;
- conf.port_id = actions->conf;
- if (conf.port_id->original)
- i = 0;
- else
- for (i = 0; ptoi[i].ifindex; ++i)
- if (ptoi[i].port_id == conf.port_id->id)
- break;
- if (!ptoi[i].ifindex)
- return rte_flow_error_set
- (error, ENODEV,
- RTE_FLOW_ERROR_TYPE_ACTION_CONF,
- conf.port_id,
- "missing data to convert port ID to"
- " ifindex");
- port_id_dev = &rte_eth_devices[conf.port_id->id];
- break;
- case RTE_FLOW_ACTION_TYPE_JUMP:
- current_action_flag = MLX5_FLOW_ACTION_JUMP;
- if (!actions->conf)
- break;
- conf.jump = actions->conf;
- if (attr->group >= conf.jump->group)
- return rte_flow_error_set
- (error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ACTION,
- actions,
- "can jump only to a group forward");
- break;
- case RTE_FLOW_ACTION_TYPE_DROP:
- current_action_flag = MLX5_FLOW_ACTION_DROP;
- break;
- case RTE_FLOW_ACTION_TYPE_OF_POP_VLAN:
- current_action_flag = MLX5_FLOW_ACTION_OF_POP_VLAN;
- break;
- case RTE_FLOW_ACTION_TYPE_OF_PUSH_VLAN:
- current_action_flag = MLX5_FLOW_ACTION_OF_PUSH_VLAN;
+ error);
+ if (ret < 0)
+ return ret;
+ item_flags |= MLX5_FLOW_LAYER_OUTER_L4_TCP;
+ mask.tcp = flow_tcf_item_mask
+ (items, &rte_flow_item_tcp_mask,
+ &flow_tcf_mask_supported.tcp,
+ &flow_tcf_mask_empty.tcp,
+ sizeof(flow_tcf_mask_supported.tcp),
+ error);
+ if (!mask.tcp)
+ return -rte_errno;
break;
- case RTE_FLOW_ACTION_TYPE_OF_SET_VLAN_VID:
- if (!(action_flags & MLX5_FLOW_ACTION_OF_PUSH_VLAN))
+ case RTE_FLOW_ITEM_TYPE_VXLAN:
+ if (!(action_flags & MLX5_FLOW_ACTION_VXLAN_DECAP))
return rte_flow_error_set
(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ACTION, actions,
- "vlan modify is not supported,"
- " set action must follow push action");
- current_action_flag = MLX5_FLOW_ACTION_OF_SET_VLAN_VID;
- break;
- case RTE_FLOW_ACTION_TYPE_OF_SET_VLAN_PCP:
- if (!(action_flags & MLX5_FLOW_ACTION_OF_PUSH_VLAN))
+ RTE_FLOW_ERROR_TYPE_ITEM,
+ items,
+ "vni pattern should be followed by"
+ " vxlan decapsulation action");
+ ret = mlx5_flow_validate_item_vxlan(items,
+ item_flags, error);
+ if (ret < 0)
+ return ret;
+ item_flags |= MLX5_FLOW_LAYER_VXLAN;
+ mask.vxlan = flow_tcf_item_mask
+ (items, &rte_flow_item_vxlan_mask,
+ &flow_tcf_mask_supported.vxlan,
+ &flow_tcf_mask_empty.vxlan,
+ sizeof(flow_tcf_mask_supported.vxlan), error);
+ if (!mask.vxlan)
+ return -rte_errno;
+ if (mask.vxlan->vni[0] != 0xff ||
+ mask.vxlan->vni[1] != 0xff ||
+ mask.vxlan->vni[2] != 0xff)
return rte_flow_error_set
(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ACTION, actions,
- "vlan modify is not supported,"
- " set action must follow push action");
- current_action_flag = MLX5_FLOW_ACTION_OF_SET_VLAN_PCP;
- break;
- case RTE_FLOW_ACTION_TYPE_SET_IPV4_SRC:
- current_action_flag = MLX5_FLOW_ACTION_SET_IPV4_SRC;
- break;
- case RTE_FLOW_ACTION_TYPE_SET_IPV4_DST:
- current_action_flag = MLX5_FLOW_ACTION_SET_IPV4_DST;
- break;
- case RTE_FLOW_ACTION_TYPE_SET_IPV6_SRC:
- current_action_flag = MLX5_FLOW_ACTION_SET_IPV6_SRC;
- break;
- case RTE_FLOW_ACTION_TYPE_SET_IPV6_DST:
- current_action_flag = MLX5_FLOW_ACTION_SET_IPV6_DST;
- break;
- case RTE_FLOW_ACTION_TYPE_SET_TP_SRC:
- current_action_flag = MLX5_FLOW_ACTION_SET_TP_SRC;
- break;
- case RTE_FLOW_ACTION_TYPE_SET_TP_DST:
- current_action_flag = MLX5_FLOW_ACTION_SET_TP_DST;
- break;
- case RTE_FLOW_ACTION_TYPE_SET_TTL:
- current_action_flag = MLX5_FLOW_ACTION_SET_TTL;
- break;
- case RTE_FLOW_ACTION_TYPE_DEC_TTL:
- current_action_flag = MLX5_FLOW_ACTION_DEC_TTL;
+ RTE_FLOW_ERROR_TYPE_ITEM_MASK,
+ mask.vxlan,
+ "no support for partial or "
+ "empty mask on \"vxlan.vni\" field");
break;
default:
return rte_flow_error_set(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ACTION,
- actions,
- "action not supported");
- }
- if (current_action_flag & MLX5_TCF_CONFIG_ACTIONS) {
- if (!actions->conf)
- return rte_flow_error_set(error, EINVAL,
- RTE_FLOW_ERROR_TYPE_ACTION_CONF,
- actions,
- "action configuration not set");
+ RTE_FLOW_ERROR_TYPE_ITEM,
+ items, "item not supported");
}
- if ((current_action_flag & MLX5_TCF_PEDIT_ACTIONS) &&
- pedit_validated)
- return rte_flow_error_set(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ACTION,
- actions,
- "set actions should be "
- "listed successively");
- if ((current_action_flag & ~MLX5_TCF_PEDIT_ACTIONS) &&
- (action_flags & MLX5_TCF_PEDIT_ACTIONS))
- pedit_validated = 1;
- if ((current_action_flag & MLX5_TCF_FATE_ACTIONS) &&
- (action_flags & MLX5_TCF_FATE_ACTIONS))
- return rte_flow_error_set(error, EINVAL,
- RTE_FLOW_ERROR_TYPE_ACTION,
- actions,
- "can't have multiple fate"
- " actions");
- action_flags |= current_action_flag;
}
if ((action_flags & MLX5_TCF_PEDIT_ACTIONS) &&
(action_flags & MLX5_FLOW_ACTION_DROP))
RTE_FLOW_ERROR_TYPE_ACTION, actions,
"vlan actions are supported"
" only with port_id action");
+ if ((action_flags & MLX5_TCF_VXLAN_ACTIONS) &&
+ !(action_flags & MLX5_FLOW_ACTION_PORT_ID))
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+ "vxlan actions are supported"
+ " only with port_id action");
if (!(action_flags & MLX5_TCF_FATE_ACTIONS))
return rte_flow_error_set(error, EINVAL,
RTE_FLOW_ERROR_TYPE_ACTION, actions,
actions,
"no IP found in pattern");
}
+ if (action_flags &
+ (MLX5_FLOW_ACTION_SET_MAC_SRC | MLX5_FLOW_ACTION_SET_MAC_DST)) {
+ if (!(item_flags & MLX5_FLOW_LAYER_OUTER_L2))
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ actions,
+ "no ethernet found in"
+ " pattern");
+ }
+ if (action_flags & MLX5_FLOW_ACTION_VXLAN_DECAP) {
+ if (!(item_flags &
+ (MLX5_FLOW_LAYER_OUTER_L3_IPV4 |
+ MLX5_FLOW_LAYER_OUTER_L3_IPV6)))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ NULL,
+ "no outer IP pattern found"
+ " for vxlan decap action");
+ if (!(item_flags & MLX5_FLOW_LAYER_OUTER_L4_UDP))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ NULL,
+ "no outer UDP pattern found"
+ " for vxlan decap action");
+ if (!(item_flags & MLX5_FLOW_LAYER_VXLAN))
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ NULL,
+ "no VNI pattern found"
+ " for vxlan decap action");
+ }
return 0;
}
case RTE_FLOW_ITEM_TYPE_IPV6:
size += SZ_NLATTR_TYPE_OF(uint16_t) + /* Ether type. */
SZ_NLATTR_TYPE_OF(uint8_t) + /* IP proto. */
- SZ_NLATTR_TYPE_OF(IPV6_ADDR_LEN) * 4;
+ SZ_NLATTR_DATA_OF(IPV6_ADDR_LEN) * 4;
/* dst/src IP addr and mask. */
flags |= MLX5_FLOW_LAYER_OUTER_L3_IPV6;
break;
/* dst/src port and mask. */
flags |= MLX5_FLOW_LAYER_OUTER_L4_TCP;
break;
+ case RTE_FLOW_ITEM_TYPE_VXLAN:
+ size += SZ_NLATTR_TYPE_OF(uint32_t);
+ flags |= MLX5_FLOW_LAYER_VXLAN;
+ break;
default:
DRV_LOG(WARNING,
"unsupported item %p type %d,"
return size;
}
+/**
+ * Calculate size of memory to store the VXLAN encapsultion
+ * related items in the Netlink message buffer. Items list
+ * is specified by RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP action.
+ * The item list should be validated.
+ *
+ * @param[in] action
+ * RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP action object.
+ * List of pattern items to scan data from.
+ *
+ * @return
+ * The size the part of Netlink message buffer to store the
+ * VXLAN encapsulation item attributes.
+ */
+static int
+flow_tcf_vxlan_encap_size(const struct rte_flow_action *action)
+{
+ const struct rte_flow_item *items;
+ int size = 0;
+
+ assert(action->type == RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP);
+ assert(action->conf);
+
+ items = ((const struct rte_flow_action_vxlan_encap *)
+ action->conf)->definition;
+ assert(items);
+ for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) {
+ switch (items->type) {
+ case RTE_FLOW_ITEM_TYPE_VOID:
+ break;
+ case RTE_FLOW_ITEM_TYPE_ETH:
+ /* This item does not require message buffer. */
+ break;
+ case RTE_FLOW_ITEM_TYPE_IPV4:
+ size += SZ_NLATTR_DATA_OF(IPV4_ADDR_LEN) * 2;
+ break;
+ case RTE_FLOW_ITEM_TYPE_IPV6:
+ size += SZ_NLATTR_DATA_OF(IPV6_ADDR_LEN) * 2;
+ break;
+ case RTE_FLOW_ITEM_TYPE_UDP: {
+ const struct rte_flow_item_udp *udp = items->mask;
+
+ size += SZ_NLATTR_TYPE_OF(uint16_t);
+ if (!udp || udp->hdr.src_port != RTE_BE16(0x0000))
+ size += SZ_NLATTR_TYPE_OF(uint16_t);
+ break;
+ }
+ case RTE_FLOW_ITEM_TYPE_VXLAN:
+ size += SZ_NLATTR_TYPE_OF(uint32_t);
+ break;
+ default:
+ assert(false);
+ DRV_LOG(WARNING,
+ "unsupported item %p type %d,"
+ " items must be validated"
+ " before flow creation",
+ (const void *)items, items->type);
+ return 0;
+ }
+ }
+ return size;
+}
+
/**
* Calculate maximum size of memory for flow actions of Linux TC flower and
* extract specified actions.
SZ_NLATTR_TYPE_OF(struct tc_gact);
flags |= MLX5_FLOW_ACTION_DROP;
break;
+ case RTE_FLOW_ACTION_TYPE_COUNT:
+ break;
case RTE_FLOW_ACTION_TYPE_OF_POP_VLAN:
flags |= MLX5_FLOW_ACTION_OF_POP_VLAN;
goto action_of_vlan;
SZ_NLATTR_TYPE_OF(uint16_t) + /* VLAN ID. */
SZ_NLATTR_TYPE_OF(uint8_t); /* VLAN prio. */
break;
+ case RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP:
+ size += SZ_NLATTR_NEST + /* na_act_index. */
+ SZ_NLATTR_STRZ_OF("tunnel_key") +
+ SZ_NLATTR_NEST + /* TCA_ACT_OPTIONS. */
+ SZ_NLATTR_TYPE_OF(uint8_t);
+ size += SZ_NLATTR_TYPE_OF(struct tc_tunnel_key);
+ size += flow_tcf_vxlan_encap_size(actions) +
+ RTE_ALIGN_CEIL /* preceding encap params. */
+ (sizeof(struct flow_tcf_vxlan_encap),
+ MNL_ALIGNTO);
+ flags |= MLX5_FLOW_ACTION_VXLAN_ENCAP;
+ break;
+ case RTE_FLOW_ACTION_TYPE_VXLAN_DECAP:
+ size += SZ_NLATTR_NEST + /* na_act_index. */
+ SZ_NLATTR_STRZ_OF("tunnel_key") +
+ SZ_NLATTR_NEST + /* TCA_ACT_OPTIONS. */
+ SZ_NLATTR_TYPE_OF(uint8_t);
+ size += SZ_NLATTR_TYPE_OF(struct tc_tunnel_key);
+ size += RTE_ALIGN_CEIL /* preceding decap params. */
+ (sizeof(struct flow_tcf_vxlan_decap),
+ MNL_ALIGNTO);
+ flags |= MLX5_FLOW_ACTION_VXLAN_DECAP;
+ break;
case RTE_FLOW_ACTION_TYPE_SET_IPV4_SRC:
case RTE_FLOW_ACTION_TYPE_SET_IPV4_DST:
case RTE_FLOW_ACTION_TYPE_SET_IPV6_SRC:
case RTE_FLOW_ACTION_TYPE_SET_TP_DST:
case RTE_FLOW_ACTION_TYPE_SET_TTL:
case RTE_FLOW_ACTION_TYPE_DEC_TTL:
+ case RTE_FLOW_ACTION_TYPE_SET_MAC_SRC:
+ case RTE_FLOW_ACTION_TYPE_SET_MAC_DST:
size += flow_tcf_get_pedit_actions_size(&actions,
&flags);
break;
uint64_t *item_flags, uint64_t *action_flags,
struct rte_flow_error *error)
{
- size_t size = sizeof(struct mlx5_flow) +
+ size_t size = RTE_ALIGN_CEIL
+ (sizeof(struct mlx5_flow),
+ alignof(struct flow_tcf_tunnel_hdr)) +
MNL_ALIGN(sizeof(struct nlmsghdr)) +
MNL_ALIGN(sizeof(struct tcmsg));
struct mlx5_flow *dev_flow;
struct nlmsghdr *nlh;
struct tcmsg *tcm;
+ uint8_t *sp, *tun = NULL;
size += flow_tcf_get_items_and_size(attr, items, item_flags);
size += flow_tcf_get_actions_and_size(actions, action_flags);
"not enough memory to create E-Switch flow");
return NULL;
}
- nlh = mnl_nlmsg_put_header((void *)(dev_flow + 1));
+ sp = (uint8_t *)(dev_flow + 1);
+ if (*action_flags & MLX5_FLOW_ACTION_VXLAN_ENCAP) {
+ sp = RTE_PTR_ALIGN
+ (sp, alignof(struct flow_tcf_tunnel_hdr));
+ tun = sp;
+ sp += RTE_ALIGN_CEIL
+ (sizeof(struct flow_tcf_vxlan_encap),
+ MNL_ALIGNTO);
+#ifndef NDEBUG
+ size -= RTE_ALIGN_CEIL
+ (sizeof(struct flow_tcf_vxlan_encap),
+ MNL_ALIGNTO);
+#endif
+ } else if (*action_flags & MLX5_FLOW_ACTION_VXLAN_DECAP) {
+ sp = RTE_PTR_ALIGN
+ (sp, alignof(struct flow_tcf_tunnel_hdr));
+ tun = sp;
+ sp += RTE_ALIGN_CEIL
+ (sizeof(struct flow_tcf_vxlan_decap),
+ MNL_ALIGNTO);
+#ifndef NDEBUG
+ size -= RTE_ALIGN_CEIL
+ (sizeof(struct flow_tcf_vxlan_decap),
+ MNL_ALIGNTO);
+#endif
+ } else {
+ sp = RTE_PTR_ALIGN(sp, MNL_ALIGNTO);
+ }
+ nlh = mnl_nlmsg_put_header(sp);
tcm = mnl_nlmsg_put_extra_header(nlh, sizeof(*tcm));
*dev_flow = (struct mlx5_flow){
.tcf = (struct mlx5_flow_tcf){
+#ifndef NDEBUG
+ .nlsize = size - RTE_ALIGN_CEIL
+ (sizeof(struct mlx5_flow),
+ alignof(struct flow_tcf_tunnel_hdr)),
+#endif
+ .tunnel = (struct flow_tcf_tunnel_hdr *)tun,
.nlh = nlh,
.tcm = tcm,
},
};
+ if (*action_flags & MLX5_FLOW_ACTION_VXLAN_DECAP)
+ dev_flow->tcf.tunnel->type = FLOW_TCF_TUNACT_VXLAN_DECAP;
+ else if (*action_flags & MLX5_FLOW_ACTION_VXLAN_ENCAP)
+ dev_flow->tcf.tunnel->type = FLOW_TCF_TUNACT_VXLAN_ENCAP;
/*
* Generate a reasonably unique handle based on the address of the
* target buffer.
return dev_flow;
}
+/**
+ * Make adjustments for supporting count actions.
+ *
+ * @param[in] dev
+ * Pointer to the Ethernet device structure.
+ * @param[in] dev_flow
+ * Pointer to mlx5_flow.
+ * @param[out] error
+ * Pointer to error structure.
+ *
+ * @return
+ * 0 On success else a negative errno value is returned and rte_errno is set.
+ */
+static int
+flow_tcf_translate_action_count(struct rte_eth_dev *dev __rte_unused,
+ struct mlx5_flow *dev_flow,
+ struct rte_flow_error *error)
+{
+ struct rte_flow *flow = dev_flow->flow;
+
+ if (!flow->counter) {
+ flow->counter = flow_tcf_counter_new();
+ if (!flow->counter)
+ return rte_flow_error_set(error, rte_errno,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ NULL,
+ "cannot get counter"
+ " context.");
+ }
+ return 0;
+}
+
+/**
+ * Convert VXLAN VNI to 32-bit integer.
+ *
+ * @param[in] vni
+ * VXLAN VNI in 24-bit wire format.
+ *
+ * @return
+ * VXLAN VNI as a 32-bit integer value in network endian.
+ */
+static inline rte_be32_t
+vxlan_vni_as_be32(const uint8_t vni[3])
+{
+ union {
+ uint8_t vni[4];
+ rte_be32_t dword;
+ } ret = {
+ .vni = { 0, vni[0], vni[1], vni[2] },
+ };
+ return ret.dword;
+}
+
+/**
+ * Helper function to process RTE_FLOW_ITEM_TYPE_ETH entry in configuration
+ * of action RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP. Fills the MAC address fields
+ * in the encapsulation parameters structure. The item must be prevalidated,
+ * no any validation checks performed by function.
+ *
+ * @param[in] spec
+ * RTE_FLOW_ITEM_TYPE_ETH entry specification.
+ * @param[in] mask
+ * RTE_FLOW_ITEM_TYPE_ETH entry mask.
+ * @param[out] encap
+ * Structure to fill the gathered MAC address data.
+ */
+static void
+flow_tcf_parse_vxlan_encap_eth(const struct rte_flow_item_eth *spec,
+ const struct rte_flow_item_eth *mask,
+ struct flow_tcf_vxlan_encap *encap)
+{
+ /* Item must be validated before. No redundant checks. */
+ assert(spec);
+ if (!mask || !memcmp(&mask->dst,
+ &rte_flow_item_eth_mask.dst,
+ sizeof(rte_flow_item_eth_mask.dst))) {
+ /*
+ * Ethernet addresses are not supported by
+ * tc as tunnel_key parameters. Destination
+ * address is needed to form encap packet
+ * header and retrieved by kernel from
+ * implicit sources (ARP table, etc),
+ * address masks are not supported at all.
+ */
+ encap->eth.dst = spec->dst;
+ encap->mask |= FLOW_TCF_ENCAP_ETH_DST;
+ }
+ if (!mask || !memcmp(&mask->src,
+ &rte_flow_item_eth_mask.src,
+ sizeof(rte_flow_item_eth_mask.src))) {
+ /*
+ * Ethernet addresses are not supported by
+ * tc as tunnel_key parameters. Source ethernet
+ * address is ignored anyway.
+ */
+ encap->eth.src = spec->src;
+ encap->mask |= FLOW_TCF_ENCAP_ETH_SRC;
+ }
+}
+
+/**
+ * Helper function to process RTE_FLOW_ITEM_TYPE_IPV4 entry in configuration
+ * of action RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP. Fills the IPV4 address fields
+ * in the encapsulation parameters structure. The item must be prevalidated,
+ * no any validation checks performed by function.
+ *
+ * @param[in] spec
+ * RTE_FLOW_ITEM_TYPE_IPV4 entry specification.
+ * @param[out] encap
+ * Structure to fill the gathered IPV4 address data.
+ */
+static void
+flow_tcf_parse_vxlan_encap_ipv4(const struct rte_flow_item_ipv4 *spec,
+ struct flow_tcf_vxlan_encap *encap)
+{
+ /* Item must be validated before. No redundant checks. */
+ assert(spec);
+ encap->ipv4.dst = spec->hdr.dst_addr;
+ encap->ipv4.src = spec->hdr.src_addr;
+ encap->mask |= FLOW_TCF_ENCAP_IPV4_SRC |
+ FLOW_TCF_ENCAP_IPV4_DST;
+}
+
+/**
+ * Helper function to process RTE_FLOW_ITEM_TYPE_IPV6 entry in configuration
+ * of action RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP. Fills the IPV6 address fields
+ * in the encapsulation parameters structure. The item must be prevalidated,
+ * no any validation checks performed by function.
+ *
+ * @param[in] spec
+ * RTE_FLOW_ITEM_TYPE_IPV6 entry specification.
+ * @param[out] encap
+ * Structure to fill the gathered IPV6 address data.
+ */
+static void
+flow_tcf_parse_vxlan_encap_ipv6(const struct rte_flow_item_ipv6 *spec,
+ struct flow_tcf_vxlan_encap *encap)
+{
+ /* Item must be validated before. No redundant checks. */
+ assert(spec);
+ memcpy(encap->ipv6.dst, spec->hdr.dst_addr, IPV6_ADDR_LEN);
+ memcpy(encap->ipv6.src, spec->hdr.src_addr, IPV6_ADDR_LEN);
+ encap->mask |= FLOW_TCF_ENCAP_IPV6_SRC |
+ FLOW_TCF_ENCAP_IPV6_DST;
+}
+
+/**
+ * Helper function to process RTE_FLOW_ITEM_TYPE_UDP entry in configuration
+ * of action RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP. Fills the UDP port fields
+ * in the encapsulation parameters structure. The item must be prevalidated,
+ * no any validation checks performed by function.
+ *
+ * @param[in] spec
+ * RTE_FLOW_ITEM_TYPE_UDP entry specification.
+ * @param[in] mask
+ * RTE_FLOW_ITEM_TYPE_UDP entry mask.
+ * @param[out] encap
+ * Structure to fill the gathered UDP port data.
+ */
+static void
+flow_tcf_parse_vxlan_encap_udp(const struct rte_flow_item_udp *spec,
+ const struct rte_flow_item_udp *mask,
+ struct flow_tcf_vxlan_encap *encap)
+{
+ assert(spec);
+ encap->udp.dst = spec->hdr.dst_port;
+ encap->mask |= FLOW_TCF_ENCAP_UDP_DST;
+ if (!mask || mask->hdr.src_port != RTE_BE16(0x0000)) {
+ encap->udp.src = spec->hdr.src_port;
+ encap->mask |= FLOW_TCF_ENCAP_IPV4_SRC;
+ }
+}
+
+/**
+ * Helper function to process RTE_FLOW_ITEM_TYPE_VXLAN entry in configuration
+ * of action RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP. Fills the VNI fields
+ * in the encapsulation parameters structure. The item must be prevalidated,
+ * no any validation checks performed by function.
+ *
+ * @param[in] spec
+ * RTE_FLOW_ITEM_TYPE_VXLAN entry specification.
+ * @param[out] encap
+ * Structure to fill the gathered VNI address data.
+ */
+static void
+flow_tcf_parse_vxlan_encap_vni(const struct rte_flow_item_vxlan *spec,
+ struct flow_tcf_vxlan_encap *encap)
+{
+ /* Item must be validated before. Do not redundant checks. */
+ assert(spec);
+ memcpy(encap->vxlan.vni, spec->vni, sizeof(encap->vxlan.vni));
+ encap->mask |= FLOW_TCF_ENCAP_VXLAN_VNI;
+}
+
+/**
+ * Populate consolidated encapsulation object from list of pattern items.
+ *
+ * Helper function to process configuration of action such as
+ * RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP. The item list should be
+ * validated, there is no way to return an meaningful error.
+ *
+ * @param[in] action
+ * RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP action object.
+ * List of pattern items to gather data from.
+ * @param[out] src
+ * Structure to fill gathered data.
+ */
+static void
+flow_tcf_vxlan_encap_parse(const struct rte_flow_action *action,
+ struct flow_tcf_vxlan_encap *encap)
+{
+ union {
+ const struct rte_flow_item_eth *eth;
+ const struct rte_flow_item_ipv4 *ipv4;
+ const struct rte_flow_item_ipv6 *ipv6;
+ const struct rte_flow_item_udp *udp;
+ const struct rte_flow_item_vxlan *vxlan;
+ } spec, mask;
+ const struct rte_flow_item *items;
+
+ assert(action->type == RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP);
+ assert(action->conf);
+
+ items = ((const struct rte_flow_action_vxlan_encap *)
+ action->conf)->definition;
+ assert(items);
+ for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) {
+ switch (items->type) {
+ case RTE_FLOW_ITEM_TYPE_VOID:
+ break;
+ case RTE_FLOW_ITEM_TYPE_ETH:
+ mask.eth = items->mask;
+ spec.eth = items->spec;
+ flow_tcf_parse_vxlan_encap_eth(spec.eth, mask.eth,
+ encap);
+ break;
+ case RTE_FLOW_ITEM_TYPE_IPV4:
+ spec.ipv4 = items->spec;
+ flow_tcf_parse_vxlan_encap_ipv4(spec.ipv4, encap);
+ break;
+ case RTE_FLOW_ITEM_TYPE_IPV6:
+ spec.ipv6 = items->spec;
+ flow_tcf_parse_vxlan_encap_ipv6(spec.ipv6, encap);
+ break;
+ case RTE_FLOW_ITEM_TYPE_UDP:
+ mask.udp = items->mask;
+ spec.udp = items->spec;
+ flow_tcf_parse_vxlan_encap_udp(spec.udp, mask.udp,
+ encap);
+ break;
+ case RTE_FLOW_ITEM_TYPE_VXLAN:
+ spec.vxlan = items->spec;
+ flow_tcf_parse_vxlan_encap_vni(spec.vxlan, encap);
+ break;
+ default:
+ assert(false);
+ DRV_LOG(WARNING,
+ "unsupported item %p type %d,"
+ " items must be validated"
+ " before flow creation",
+ (const void *)items, items->type);
+ encap->mask = 0;
+ return;
+ }
+ }
+}
+
/**
* Translate flow for Linux TC flower and construct Netlink message.
*
const struct rte_flow_item_ipv6 *ipv6;
const struct rte_flow_item_tcp *tcp;
const struct rte_flow_item_udp *udp;
+ const struct rte_flow_item_vxlan *vxlan;
} spec, mask;
union {
const struct rte_flow_action_port_id *port_id;
const struct rte_flow_action_of_set_vlan_pcp *
of_set_vlan_pcp;
} conf;
+ union {
+ struct flow_tcf_tunnel_hdr *hdr;
+ struct flow_tcf_vxlan_decap *vxlan;
+ } decap = {
+ .hdr = NULL,
+ };
+ union {
+ struct flow_tcf_tunnel_hdr *hdr;
+ struct flow_tcf_vxlan_encap *vxlan;
+ } encap = {
+ .hdr = NULL,
+ };
struct flow_tcf_ptoi ptoi[PTOI_TABLE_SZ_MAX(dev)];
struct nlmsghdr *nlh = dev_flow->tcf.nlh;
struct tcmsg *tcm = dev_flow->tcf.tcm;
struct nlattr *na_vlan_id = NULL;
struct nlattr *na_vlan_priority = NULL;
uint64_t item_flags = 0;
+ int ret;
claim_nonzero(flow_tcf_build_ptoi_table(dev, ptoi,
PTOI_TABLE_SZ_MAX(dev)));
+ if (dev_flow->tcf.tunnel) {
+ switch (dev_flow->tcf.tunnel->type) {
+ case FLOW_TCF_TUNACT_VXLAN_DECAP:
+ decap.vxlan = dev_flow->tcf.vxlan_decap;
+ break;
+ case FLOW_TCF_TUNACT_VXLAN_ENCAP:
+ encap.vxlan = dev_flow->tcf.vxlan_encap;
+ break;
+ /* New tunnel actions can be added here. */
+ default:
+ assert(false);
+ break;
+ }
+ }
nlh = dev_flow->tcf.nlh;
tcm = dev_flow->tcf.tcm;
/* Prepare API must have been called beforehand. */
mnl_attr_put_u32(nlh, TCA_CHAIN, attr->group);
mnl_attr_put_strz(nlh, TCA_KIND, "flower");
na_flower = mnl_attr_nest_start(nlh, TCA_OPTIONS);
- mnl_attr_put_u32(nlh, TCA_FLOWER_FLAGS, TCA_CLS_FLAGS_SKIP_SW);
for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) {
unsigned int i;
tcm->tcm_ifindex = ptoi[i].ifindex;
break;
case RTE_FLOW_ITEM_TYPE_ETH:
- item_flags |= MLX5_FLOW_LAYER_OUTER_L2;
+ item_flags |= (item_flags & MLX5_FLOW_LAYER_VXLAN) ?
+ MLX5_FLOW_LAYER_INNER_L2 :
+ MLX5_FLOW_LAYER_OUTER_L2;
mask.eth = flow_tcf_item_mask
(items, &rte_flow_item_eth_mask,
&flow_tcf_mask_supported.eth,
if (mask.eth == &flow_tcf_mask_empty.eth)
break;
spec.eth = items->spec;
+ if (decap.vxlan &&
+ !(item_flags & MLX5_FLOW_LAYER_VXLAN)) {
+ DRV_LOG(WARNING,
+ "outer L2 addresses cannot be forced"
+ " for vxlan decapsulation, parameter"
+ " ignored");
+ break;
+ }
if (mask.eth->type) {
mnl_attr_put_u16(nlh, TCA_FLOWER_KEY_ETH_TYPE,
spec.eth->type);
ETHER_ADDR_LEN,
mask.eth->src.addr_bytes);
}
+ assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
break;
case RTE_FLOW_ITEM_TYPE_VLAN:
+ assert(!encap.hdr);
+ assert(!decap.hdr);
item_flags |= MLX5_FLOW_LAYER_OUTER_VLAN;
mask.vlan = flow_tcf_item_mask
(items, &rte_flow_item_vlan_mask,
rte_be_to_cpu_16
(spec.vlan->tci &
RTE_BE16(0x0fff)));
+ assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
break;
case RTE_FLOW_ITEM_TYPE_IPV4:
item_flags |= MLX5_FLOW_LAYER_OUTER_L3_IPV4;
sizeof(flow_tcf_mask_supported.ipv4),
error);
assert(mask.ipv4);
- if (!eth_type_set || !vlan_eth_type_set)
- mnl_attr_put_u16(nlh,
+ spec.ipv4 = items->spec;
+ if (!decap.vxlan) {
+ if (!eth_type_set && !vlan_eth_type_set)
+ mnl_attr_put_u16
+ (nlh,
vlan_present ?
TCA_FLOWER_KEY_VLAN_ETH_TYPE :
TCA_FLOWER_KEY_ETH_TYPE,
RTE_BE16(ETH_P_IP));
- eth_type_set = 1;
- vlan_eth_type_set = 1;
- if (mask.ipv4 == &flow_tcf_mask_empty.ipv4)
- break;
- spec.ipv4 = items->spec;
- if (mask.ipv4->hdr.next_proto_id) {
- mnl_attr_put_u8(nlh, TCA_FLOWER_KEY_IP_PROTO,
- spec.ipv4->hdr.next_proto_id);
- ip_proto_set = 1;
+ eth_type_set = 1;
+ vlan_eth_type_set = 1;
+ if (mask.ipv4 == &flow_tcf_mask_empty.ipv4)
+ break;
+ if (mask.ipv4->hdr.next_proto_id) {
+ mnl_attr_put_u8
+ (nlh, TCA_FLOWER_KEY_IP_PROTO,
+ spec.ipv4->hdr.next_proto_id);
+ ip_proto_set = 1;
+ }
+ } else {
+ assert(mask.ipv4 != &flow_tcf_mask_empty.ipv4);
}
if (mask.ipv4->hdr.src_addr) {
- mnl_attr_put_u32(nlh, TCA_FLOWER_KEY_IPV4_SRC,
- spec.ipv4->hdr.src_addr);
- mnl_attr_put_u32(nlh,
- TCA_FLOWER_KEY_IPV4_SRC_MASK,
- mask.ipv4->hdr.src_addr);
+ mnl_attr_put_u32
+ (nlh, decap.vxlan ?
+ TCA_FLOWER_KEY_ENC_IPV4_SRC :
+ TCA_FLOWER_KEY_IPV4_SRC,
+ spec.ipv4->hdr.src_addr);
+ mnl_attr_put_u32
+ (nlh, decap.vxlan ?
+ TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK :
+ TCA_FLOWER_KEY_IPV4_SRC_MASK,
+ mask.ipv4->hdr.src_addr);
}
if (mask.ipv4->hdr.dst_addr) {
- mnl_attr_put_u32(nlh, TCA_FLOWER_KEY_IPV4_DST,
- spec.ipv4->hdr.dst_addr);
- mnl_attr_put_u32(nlh,
- TCA_FLOWER_KEY_IPV4_DST_MASK,
- mask.ipv4->hdr.dst_addr);
+ mnl_attr_put_u32
+ (nlh, decap.vxlan ?
+ TCA_FLOWER_KEY_ENC_IPV4_DST :
+ TCA_FLOWER_KEY_IPV4_DST,
+ spec.ipv4->hdr.dst_addr);
+ mnl_attr_put_u32
+ (nlh, decap.vxlan ?
+ TCA_FLOWER_KEY_ENC_IPV4_DST_MASK :
+ TCA_FLOWER_KEY_IPV4_DST_MASK,
+ mask.ipv4->hdr.dst_addr);
}
+ assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
break;
case RTE_FLOW_ITEM_TYPE_IPV6:
item_flags |= MLX5_FLOW_LAYER_OUTER_L3_IPV6;
sizeof(flow_tcf_mask_supported.ipv6),
error);
assert(mask.ipv6);
- if (!eth_type_set || !vlan_eth_type_set)
- mnl_attr_put_u16(nlh,
+ spec.ipv6 = items->spec;
+ if (!decap.vxlan) {
+ if (!eth_type_set || !vlan_eth_type_set) {
+ mnl_attr_put_u16
+ (nlh,
vlan_present ?
TCA_FLOWER_KEY_VLAN_ETH_TYPE :
TCA_FLOWER_KEY_ETH_TYPE,
RTE_BE16(ETH_P_IPV6));
- eth_type_set = 1;
- vlan_eth_type_set = 1;
- if (mask.ipv6 == &flow_tcf_mask_empty.ipv6)
- break;
- spec.ipv6 = items->spec;
- if (mask.ipv6->hdr.proto) {
- mnl_attr_put_u8(nlh, TCA_FLOWER_KEY_IP_PROTO,
- spec.ipv6->hdr.proto);
- ip_proto_set = 1;
+ }
+ eth_type_set = 1;
+ vlan_eth_type_set = 1;
+ if (mask.ipv6 == &flow_tcf_mask_empty.ipv6)
+ break;
+ if (mask.ipv6->hdr.proto) {
+ mnl_attr_put_u8
+ (nlh, TCA_FLOWER_KEY_IP_PROTO,
+ spec.ipv6->hdr.proto);
+ ip_proto_set = 1;
+ }
+ } else {
+ assert(mask.ipv6 != &flow_tcf_mask_empty.ipv6);
}
if (!IN6_IS_ADDR_UNSPECIFIED(mask.ipv6->hdr.src_addr)) {
- mnl_attr_put(nlh, TCA_FLOWER_KEY_IPV6_SRC,
- sizeof(spec.ipv6->hdr.src_addr),
+ mnl_attr_put(nlh, decap.vxlan ?
+ TCA_FLOWER_KEY_ENC_IPV6_SRC :
+ TCA_FLOWER_KEY_IPV6_SRC,
+ IPV6_ADDR_LEN,
spec.ipv6->hdr.src_addr);
- mnl_attr_put(nlh, TCA_FLOWER_KEY_IPV6_SRC_MASK,
- sizeof(mask.ipv6->hdr.src_addr),
+ mnl_attr_put(nlh, decap.vxlan ?
+ TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK :
+ TCA_FLOWER_KEY_IPV6_SRC_MASK,
+ IPV6_ADDR_LEN,
mask.ipv6->hdr.src_addr);
}
if (!IN6_IS_ADDR_UNSPECIFIED(mask.ipv6->hdr.dst_addr)) {
- mnl_attr_put(nlh, TCA_FLOWER_KEY_IPV6_DST,
- sizeof(spec.ipv6->hdr.dst_addr),
+ mnl_attr_put(nlh, decap.vxlan ?
+ TCA_FLOWER_KEY_ENC_IPV6_DST :
+ TCA_FLOWER_KEY_IPV6_DST,
+ IPV6_ADDR_LEN,
spec.ipv6->hdr.dst_addr);
- mnl_attr_put(nlh, TCA_FLOWER_KEY_IPV6_DST_MASK,
- sizeof(mask.ipv6->hdr.dst_addr),
+ mnl_attr_put(nlh, decap.vxlan ?
+ TCA_FLOWER_KEY_ENC_IPV6_DST_MASK :
+ TCA_FLOWER_KEY_IPV6_DST_MASK,
+ IPV6_ADDR_LEN,
mask.ipv6->hdr.dst_addr);
}
+ assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
break;
case RTE_FLOW_ITEM_TYPE_UDP:
item_flags |= MLX5_FLOW_LAYER_OUTER_L4_UDP;
sizeof(flow_tcf_mask_supported.udp),
error);
assert(mask.udp);
- if (!ip_proto_set)
- mnl_attr_put_u8(nlh, TCA_FLOWER_KEY_IP_PROTO,
- IPPROTO_UDP);
- if (mask.udp == &flow_tcf_mask_empty.udp)
- break;
spec.udp = items->spec;
+ if (!decap.vxlan) {
+ if (!ip_proto_set)
+ mnl_attr_put_u8
+ (nlh, TCA_FLOWER_KEY_IP_PROTO,
+ IPPROTO_UDP);
+ if (mask.udp == &flow_tcf_mask_empty.udp)
+ break;
+ } else {
+ assert(mask.udp != &flow_tcf_mask_empty.udp);
+ decap.vxlan->udp_port =
+ rte_be_to_cpu_16
+ (spec.udp->hdr.dst_port);
+ }
if (mask.udp->hdr.src_port) {
- mnl_attr_put_u16(nlh, TCA_FLOWER_KEY_UDP_SRC,
- spec.udp->hdr.src_port);
- mnl_attr_put_u16(nlh,
- TCA_FLOWER_KEY_UDP_SRC_MASK,
- mask.udp->hdr.src_port);
+ mnl_attr_put_u16
+ (nlh, decap.vxlan ?
+ TCA_FLOWER_KEY_ENC_UDP_SRC_PORT :
+ TCA_FLOWER_KEY_UDP_SRC,
+ spec.udp->hdr.src_port);
+ mnl_attr_put_u16
+ (nlh, decap.vxlan ?
+ TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK :
+ TCA_FLOWER_KEY_UDP_SRC_MASK,
+ mask.udp->hdr.src_port);
}
if (mask.udp->hdr.dst_port) {
- mnl_attr_put_u16(nlh, TCA_FLOWER_KEY_UDP_DST,
- spec.udp->hdr.dst_port);
- mnl_attr_put_u16(nlh,
- TCA_FLOWER_KEY_UDP_DST_MASK,
- mask.udp->hdr.dst_port);
+ mnl_attr_put_u16
+ (nlh, decap.vxlan ?
+ TCA_FLOWER_KEY_ENC_UDP_DST_PORT :
+ TCA_FLOWER_KEY_UDP_DST,
+ spec.udp->hdr.dst_port);
+ mnl_attr_put_u16
+ (nlh, decap.vxlan ?
+ TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK :
+ TCA_FLOWER_KEY_UDP_DST_MASK,
+ mask.udp->hdr.dst_port);
}
+ assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
break;
case RTE_FLOW_ITEM_TYPE_TCP:
item_flags |= MLX5_FLOW_LAYER_OUTER_L4_TCP;
rte_cpu_to_be_16
(mask.tcp->hdr.tcp_flags));
}
+ assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
+ break;
+ case RTE_FLOW_ITEM_TYPE_VXLAN:
+ assert(decap.vxlan);
+ item_flags |= MLX5_FLOW_LAYER_VXLAN;
+ spec.vxlan = items->spec;
+ mnl_attr_put_u32(nlh,
+ TCA_FLOWER_KEY_ENC_KEY_ID,
+ vxlan_vni_as_be32(spec.vxlan->vni));
+ assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
break;
default:
return rte_flow_error_set(error, ENOTSUP,
mnl_attr_put_strz(nlh, TCA_ACT_KIND, "mirred");
na_act = mnl_attr_nest_start(nlh, TCA_ACT_OPTIONS);
assert(na_act);
+ if (encap.hdr) {
+ assert(dev_flow->tcf.tunnel);
+ dev_flow->tcf.tunnel->ifindex_ptr =
+ &((struct tc_mirred *)
+ mnl_attr_get_payload
+ (mnl_nlmsg_get_payload_tail
+ (nlh)))->ifindex;
+ }
mnl_attr_put(nlh, TCA_MIRRED_PARMS,
sizeof(struct tc_mirred),
&(struct tc_mirred){
mnl_attr_nest_end(nlh, na_act);
mnl_attr_nest_end(nlh, na_act_index);
break;
+ case RTE_FLOW_ACTION_TYPE_COUNT:
+ /*
+ * Driver adds the count action implicitly for
+ * each rule it creates.
+ */
+ ret = flow_tcf_translate_action_count(dev,
+ dev_flow, error);
+ if (ret < 0)
+ return ret;
+ break;
case RTE_FLOW_ACTION_TYPE_OF_POP_VLAN:
conf.of_push_vlan = NULL;
vlan_act = TCA_VLAN_ACT_POP;
conf.of_set_vlan_pcp->vlan_pcp;
}
break;
+ case RTE_FLOW_ACTION_TYPE_VXLAN_DECAP:
+ assert(decap.vxlan);
+ assert(dev_flow->tcf.tunnel);
+ dev_flow->tcf.tunnel->ifindex_ptr =
+ (unsigned int *)&tcm->tcm_ifindex;
+ na_act_index =
+ mnl_attr_nest_start(nlh, na_act_index_cur++);
+ assert(na_act_index);
+ mnl_attr_put_strz(nlh, TCA_ACT_KIND, "tunnel_key");
+ na_act = mnl_attr_nest_start(nlh, TCA_ACT_OPTIONS);
+ assert(na_act);
+ mnl_attr_put(nlh, TCA_TUNNEL_KEY_PARMS,
+ sizeof(struct tc_tunnel_key),
+ &(struct tc_tunnel_key){
+ .action = TC_ACT_PIPE,
+ .t_action = TCA_TUNNEL_KEY_ACT_RELEASE,
+ });
+ mnl_attr_nest_end(nlh, na_act);
+ mnl_attr_nest_end(nlh, na_act_index);
+ assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
+ break;
+ case RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP:
+ assert(encap.vxlan);
+ flow_tcf_vxlan_encap_parse(actions, encap.vxlan);
+ na_act_index =
+ mnl_attr_nest_start(nlh, na_act_index_cur++);
+ assert(na_act_index);
+ mnl_attr_put_strz(nlh, TCA_ACT_KIND, "tunnel_key");
+ na_act = mnl_attr_nest_start(nlh, TCA_ACT_OPTIONS);
+ assert(na_act);
+ mnl_attr_put(nlh, TCA_TUNNEL_KEY_PARMS,
+ sizeof(struct tc_tunnel_key),
+ &(struct tc_tunnel_key){
+ .action = TC_ACT_PIPE,
+ .t_action = TCA_TUNNEL_KEY_ACT_SET,
+ });
+ if (encap.vxlan->mask & FLOW_TCF_ENCAP_UDP_DST)
+ mnl_attr_put_u16(nlh,
+ TCA_TUNNEL_KEY_ENC_DST_PORT,
+ encap.vxlan->udp.dst);
+ if (encap.vxlan->mask & FLOW_TCF_ENCAP_IPV4_SRC)
+ mnl_attr_put_u32(nlh,
+ TCA_TUNNEL_KEY_ENC_IPV4_SRC,
+ encap.vxlan->ipv4.src);
+ if (encap.vxlan->mask & FLOW_TCF_ENCAP_IPV4_DST)
+ mnl_attr_put_u32(nlh,
+ TCA_TUNNEL_KEY_ENC_IPV4_DST,
+ encap.vxlan->ipv4.dst);
+ if (encap.vxlan->mask & FLOW_TCF_ENCAP_IPV6_SRC)
+ mnl_attr_put(nlh,
+ TCA_TUNNEL_KEY_ENC_IPV6_SRC,
+ sizeof(encap.vxlan->ipv6.src),
+ &encap.vxlan->ipv6.src);
+ if (encap.vxlan->mask & FLOW_TCF_ENCAP_IPV6_DST)
+ mnl_attr_put(nlh,
+ TCA_TUNNEL_KEY_ENC_IPV6_DST,
+ sizeof(encap.vxlan->ipv6.dst),
+ &encap.vxlan->ipv6.dst);
+ if (encap.vxlan->mask & FLOW_TCF_ENCAP_VXLAN_VNI)
+ mnl_attr_put_u32(nlh,
+ TCA_TUNNEL_KEY_ENC_KEY_ID,
+ vxlan_vni_as_be32
+ (encap.vxlan->vxlan.vni));
+ mnl_attr_put_u8(nlh, TCA_TUNNEL_KEY_NO_CSUM, 0);
+ mnl_attr_nest_end(nlh, na_act);
+ mnl_attr_nest_end(nlh, na_act_index);
+ assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
+ break;
case RTE_FLOW_ACTION_TYPE_SET_IPV4_SRC:
case RTE_FLOW_ACTION_TYPE_SET_IPV4_DST:
case RTE_FLOW_ACTION_TYPE_SET_IPV6_SRC:
case RTE_FLOW_ACTION_TYPE_SET_TP_DST:
case RTE_FLOW_ACTION_TYPE_SET_TTL:
case RTE_FLOW_ACTION_TYPE_DEC_TTL:
+ case RTE_FLOW_ACTION_TYPE_SET_MAC_SRC:
+ case RTE_FLOW_ACTION_TYPE_SET_MAC_DST:
na_act_index =
mnl_attr_nest_start(nlh, na_act_index_cur++);
flow_tcf_create_pedit_mnl_msg(nlh,
assert(na_flower);
assert(na_flower_act);
mnl_attr_nest_end(nlh, na_flower_act);
+ mnl_attr_put_u32(nlh, TCA_FLOWER_FLAGS, decap.vxlan ?
+ 0 : TCA_CLS_FLAGS_SKIP_SW);
mnl_attr_nest_end(nlh, na_flower);
+ if (dev_flow->tcf.tunnel && dev_flow->tcf.tunnel->ifindex_ptr)
+ dev_flow->tcf.tunnel->ifindex_org =
+ *dev_flow->tcf.tunnel->ifindex_ptr;
+ assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
return 0;
}
/**
* Send Netlink message with acknowledgment.
*
- * @param nl
- * Libmnl socket to use.
+ * @param ctx
+ * Flow context to use.
* @param nlh
* Message to send. This function always raises the NLM_F_ACK flag before
* sending.
* 0 on success, a negative errno value otherwise and rte_errno is set.
*/
static int
-flow_tcf_nl_ack(struct mnl_socket *nl, struct nlmsghdr *nlh)
+flow_tcf_nl_ack(struct mlx5_flow_tcf_context *ctx, struct nlmsghdr *nlh)
{
alignas(struct nlmsghdr)
uint8_t ans[mnl_nlmsg_size(sizeof(struct nlmsgerr)) +
nlh->nlmsg_len - sizeof(*nlh)];
- uint32_t seq = random();
+ uint32_t seq = ctx->seq++;
+ struct mnl_socket *nl = ctx->nl;
int ret;
nlh->nlmsg_flags |= NLM_F_ACK;
struct rte_flow_error *error)
{
struct priv *priv = dev->data->dev_private;
- struct mnl_socket *nl = priv->mnl_socket;
+ struct mlx5_flow_tcf_context *ctx = priv->tcf_context;
struct mlx5_flow *dev_flow;
struct nlmsghdr *nlh;
nlh = dev_flow->tcf.nlh;
nlh->nlmsg_type = RTM_NEWTFILTER;
nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE | NLM_F_EXCL;
- if (!flow_tcf_nl_ack(nl, nlh))
+ if (!flow_tcf_nl_ack(ctx, nlh))
return 0;
return rte_flow_error_set(error, rte_errno,
RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
flow_tcf_remove(struct rte_eth_dev *dev, struct rte_flow *flow)
{
struct priv *priv = dev->data->dev_private;
- struct mnl_socket *nl = priv->mnl_socket;
+ struct mlx5_flow_tcf_context *ctx = priv->tcf_context;
struct mlx5_flow *dev_flow;
struct nlmsghdr *nlh;
if (!flow)
return;
+ if (flow->counter) {
+ if (--flow->counter->ref_cnt == 0) {
+ rte_free(flow->counter);
+ flow->counter = NULL;
+ }
+ }
dev_flow = LIST_FIRST(&flow->dev_flows);
if (!dev_flow)
return;
nlh = dev_flow->tcf.nlh;
nlh->nlmsg_type = RTM_DELTFILTER;
nlh->nlmsg_flags = NLM_F_REQUEST;
- flow_tcf_nl_ack(nl, nlh);
+ flow_tcf_nl_ack(ctx, nlh);
}
/**
rte_free(dev_flow);
}
+/**
+ * Helper routine for figuring the space size required for a parse buffer.
+ *
+ * @param array
+ * array of values to use.
+ * @param idx
+ * Current location in array.
+ * @param value
+ * Value to compare with.
+ *
+ * @return
+ * The maximum between the given value and the array value on index.
+ */
+static uint16_t
+flow_tcf_arr_val_max(uint16_t array[], int idx, uint16_t value)
+{
+ return idx < 0 ? (value) : RTE_MAX((array)[idx], value);
+}
+
+/**
+ * Parse rtnetlink message attributes filling the attribute table with the info
+ * retrieved.
+ *
+ * @param tb
+ * Attribute table to be filled.
+ * @param[out] max
+ * Maxinum entry in the attribute table.
+ * @param rte
+ * The attributes section in the message to be parsed.
+ * @param len
+ * The length of the attributes section in the message.
+ */
+static void
+flow_tcf_nl_parse_rtattr(struct rtattr *tb[], int max,
+ struct rtattr *rta, int len)
+{
+ unsigned short type;
+ memset(tb, 0, sizeof(struct rtattr *) * (max + 1));
+ while (RTA_OK(rta, len)) {
+ type = rta->rta_type;
+ if (type <= max && !tb[type])
+ tb[type] = rta;
+ rta = RTA_NEXT(rta, len);
+ }
+}
+
+/**
+ * Extract flow counters from flower action.
+ *
+ * @param rta
+ * flower action stats properties in the Netlink message received.
+ * @param rta_type
+ * The backward sequence of rta_types, as written in the attribute table,
+ * we need to traverse in order to get to the requested object.
+ * @param idx
+ * Current location in rta_type table.
+ * @param[out] data
+ * data holding the count statistics of the rte_flow retrieved from
+ * the message.
+ *
+ * @return
+ * 0 if data was found and retrieved, -1 otherwise.
+ */
+static int
+flow_tcf_nl_action_stats_parse_and_get(struct rtattr *rta,
+ uint16_t rta_type[], int idx,
+ struct gnet_stats_basic *data)
+{
+ int tca_stats_max = flow_tcf_arr_val_max(rta_type, idx,
+ TCA_STATS_BASIC);
+ struct rtattr *tbs[tca_stats_max + 1];
+
+ if (rta == NULL || idx < 0)
+ return -1;
+ flow_tcf_nl_parse_rtattr(tbs, tca_stats_max,
+ RTA_DATA(rta), RTA_PAYLOAD(rta));
+ switch (rta_type[idx]) {
+ case TCA_STATS_BASIC:
+ if (tbs[TCA_STATS_BASIC]) {
+ memcpy(data, RTA_DATA(tbs[TCA_STATS_BASIC]),
+ RTE_MIN(RTA_PAYLOAD(tbs[TCA_STATS_BASIC]),
+ sizeof(*data)));
+ return 0;
+ }
+ break;
+ default:
+ break;
+ }
+ return -1;
+}
+
+/**
+ * Parse flower single action retrieving the requested action attribute,
+ * if found.
+ *
+ * @param arg
+ * flower action properties in the Netlink message received.
+ * @param rta_type
+ * The backward sequence of rta_types, as written in the attribute table,
+ * we need to traverse in order to get to the requested object.
+ * @param idx
+ * Current location in rta_type table.
+ * @param[out] data
+ * Count statistics retrieved from the message query.
+ *
+ * @return
+ * 0 if data was found and retrieved, -1 otherwise.
+ */
+static int
+flow_tcf_nl_parse_one_action_and_get(struct rtattr *arg,
+ uint16_t rta_type[], int idx, void *data)
+{
+ int tca_act_max = flow_tcf_arr_val_max(rta_type, idx, TCA_ACT_STATS);
+ struct rtattr *tb[tca_act_max + 1];
+
+ if (arg == NULL || idx < 0)
+ return -1;
+ flow_tcf_nl_parse_rtattr(tb, tca_act_max,
+ RTA_DATA(arg), RTA_PAYLOAD(arg));
+ if (tb[TCA_ACT_KIND] == NULL)
+ return -1;
+ switch (rta_type[idx]) {
+ case TCA_ACT_STATS:
+ if (tb[TCA_ACT_STATS])
+ return flow_tcf_nl_action_stats_parse_and_get
+ (tb[TCA_ACT_STATS],
+ rta_type, --idx,
+ (struct gnet_stats_basic *)data);
+ break;
+ default:
+ break;
+ }
+ return -1;
+}
+
+/**
+ * Parse flower action section in the message retrieving the requested
+ * attribute from the first action that provides it.
+ *
+ * @param opt
+ * flower section in the Netlink message received.
+ * @param rta_type
+ * The backward sequence of rta_types, as written in the attribute table,
+ * we need to traverse in order to get to the requested object.
+ * @param idx
+ * Current location in rta_type table.
+ * @param[out] data
+ * data retrieved from the message query.
+ *
+ * @return
+ * 0 if data was found and retrieved, -1 otherwise.
+ */
+static int
+flow_tcf_nl_action_parse_and_get(struct rtattr *arg,
+ uint16_t rta_type[], int idx, void *data)
+{
+ struct rtattr *tb[TCA_ACT_MAX_PRIO + 1];
+ int i;
+
+ if (arg == NULL || idx < 0)
+ return -1;
+ flow_tcf_nl_parse_rtattr(tb, TCA_ACT_MAX_PRIO,
+ RTA_DATA(arg), RTA_PAYLOAD(arg));
+ switch (rta_type[idx]) {
+ /*
+ * flow counters are stored in the actions defined by the flow
+ * and not in the flow itself, therefore we need to traverse the
+ * flower chain of actions in search for them.
+ *
+ * Note that the index is not decremented here.
+ */
+ case TCA_ACT_STATS:
+ for (i = 0; i <= TCA_ACT_MAX_PRIO; i++) {
+ if (tb[i] &&
+ !flow_tcf_nl_parse_one_action_and_get(tb[i],
+ rta_type,
+ idx, data))
+ return 0;
+ }
+ break;
+ default:
+ break;
+ }
+ return -1;
+}
+
+/**
+ * Parse flower classifier options in the message, retrieving the requested
+ * attribute if found.
+ *
+ * @param opt
+ * flower section in the Netlink message received.
+ * @param rta_type
+ * The backward sequence of rta_types, as written in the attribute table,
+ * we need to traverse in order to get to the requested object.
+ * @param idx
+ * Current location in rta_type table.
+ * @param[out] data
+ * data retrieved from the message query.
+ *
+ * @return
+ * 0 if data was found and retrieved, -1 otherwise.
+ */
+static int
+flow_tcf_nl_opts_parse_and_get(struct rtattr *opt,
+ uint16_t rta_type[], int idx, void *data)
+{
+ int tca_flower_max = flow_tcf_arr_val_max(rta_type, idx,
+ TCA_FLOWER_ACT);
+ struct rtattr *tb[tca_flower_max + 1];
+
+ if (!opt || idx < 0)
+ return -1;
+ flow_tcf_nl_parse_rtattr(tb, tca_flower_max,
+ RTA_DATA(opt), RTA_PAYLOAD(opt));
+ switch (rta_type[idx]) {
+ case TCA_FLOWER_ACT:
+ if (tb[TCA_FLOWER_ACT])
+ return flow_tcf_nl_action_parse_and_get
+ (tb[TCA_FLOWER_ACT],
+ rta_type, --idx, data);
+ break;
+ default:
+ break;
+ }
+ return -1;
+}
+
+/**
+ * Parse Netlink reply on filter query, retrieving the flow counters.
+ *
+ * @param nlh
+ * Message received from Netlink.
+ * @param rta_type
+ * The backward sequence of rta_types, as written in the attribute table,
+ * we need to traverse in order to get to the requested object.
+ * @param idx
+ * Current location in rta_type table.
+ * @param[out] data
+ * data retrieved from the message query.
+ *
+ * @return
+ * 0 if data was found and retrieved, -1 otherwise.
+ */
+static int
+flow_tcf_nl_filter_parse_and_get(struct nlmsghdr *cnlh,
+ uint16_t rta_type[], int idx, void *data)
+{
+ struct nlmsghdr *nlh = cnlh;
+ struct tcmsg *t = NLMSG_DATA(nlh);
+ int len = nlh->nlmsg_len;
+ int tca_max = flow_tcf_arr_val_max(rta_type, idx, TCA_OPTIONS);
+ struct rtattr *tb[tca_max + 1];
+
+ if (idx < 0)
+ return -1;
+ if (nlh->nlmsg_type != RTM_NEWTFILTER &&
+ nlh->nlmsg_type != RTM_GETTFILTER &&
+ nlh->nlmsg_type != RTM_DELTFILTER)
+ return -1;
+ len -= NLMSG_LENGTH(sizeof(*t));
+ if (len < 0)
+ return -1;
+ flow_tcf_nl_parse_rtattr(tb, tca_max, TCA_RTA(t), len);
+ /* Not a TC flower flow - bail out */
+ if (!tb[TCA_KIND] ||
+ strcmp(RTA_DATA(tb[TCA_KIND]), "flower"))
+ return -1;
+ switch (rta_type[idx]) {
+ case TCA_OPTIONS:
+ if (tb[TCA_OPTIONS])
+ return flow_tcf_nl_opts_parse_and_get(tb[TCA_OPTIONS],
+ rta_type,
+ --idx, data);
+ break;
+ default:
+ break;
+ }
+ return -1;
+}
+
+/**
+ * A callback to parse Netlink reply on TC flower query.
+ *
+ * @param nlh
+ * Message received from Netlink.
+ * @param[out] data
+ * Pointer to data area to be filled by the parsing routine.
+ * assumed to be a pinter to struct flow_tcf_stats_basic.
+ *
+ * @return
+ * MNL_CB_OK value.
+ */
+static int
+flow_tcf_nl_message_get_stats_basic(const struct nlmsghdr *nlh, void *data)
+{
+ /*
+ * The backward sequence of rta_types to pass in order to get
+ * to the counters.
+ */
+ uint16_t rta_type[] = { TCA_STATS_BASIC, TCA_ACT_STATS,
+ TCA_FLOWER_ACT, TCA_OPTIONS };
+ struct flow_tcf_stats_basic *sb_data = data;
+ union {
+ const struct nlmsghdr *c;
+ struct nlmsghdr *nc;
+ } tnlh = { .c = nlh };
+
+ if (!flow_tcf_nl_filter_parse_and_get(tnlh.nc, rta_type,
+ RTE_DIM(rta_type) - 1,
+ (void *)&sb_data->counters))
+ sb_data->valid = true;
+ return MNL_CB_OK;
+}
+
+/**
+ * Query a TC flower rule for its statistics via netlink.
+ *
+ * @param[in] dev
+ * Pointer to Ethernet device.
+ * @param[in] flow
+ * Pointer to the sub flow.
+ * @param[out] data
+ * data retrieved by the query.
+ * @param[out] error
+ * Perform verbose error reporting if not NULL.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+flow_tcf_query_count(struct rte_eth_dev *dev,
+ struct rte_flow *flow,
+ void *data,
+ struct rte_flow_error *error)
+{
+ struct flow_tcf_stats_basic sb_data = { 0 };
+ struct rte_flow_query_count *qc = data;
+ struct priv *priv = dev->data->dev_private;
+ struct mlx5_flow_tcf_context *ctx = priv->tcf_context;
+ struct mnl_socket *nl = ctx->nl;
+ struct mlx5_flow *dev_flow;
+ struct nlmsghdr *nlh;
+ uint32_t seq = priv->tcf_context->seq++;
+ ssize_t ret;
+ assert(qc);
+
+ dev_flow = LIST_FIRST(&flow->dev_flows);
+ /* E-Switch flow can't be expanded. */
+ assert(!LIST_NEXT(dev_flow, next));
+ if (!dev_flow->flow->counter)
+ goto notsup_exit;
+ nlh = dev_flow->tcf.nlh;
+ nlh->nlmsg_type = RTM_GETTFILTER;
+ nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_ECHO;
+ nlh->nlmsg_seq = seq;
+ if (mnl_socket_sendto(nl, nlh, nlh->nlmsg_len) == -1)
+ goto error_exit;
+ do {
+ ret = mnl_socket_recvfrom(nl, ctx->buf, ctx->buf_size);
+ if (ret <= 0)
+ break;
+ ret = mnl_cb_run(ctx->buf, ret, seq,
+ mnl_socket_get_portid(nl),
+ flow_tcf_nl_message_get_stats_basic,
+ (void *)&sb_data);
+ } while (ret > 0);
+ /* Return the delta from last reset. */
+ if (sb_data.valid) {
+ /* Return the delta from last reset. */
+ qc->hits_set = 1;
+ qc->bytes_set = 1;
+ qc->hits = sb_data.counters.packets - flow->counter->hits;
+ qc->bytes = sb_data.counters.bytes - flow->counter->bytes;
+ if (qc->reset) {
+ flow->counter->hits = sb_data.counters.packets;
+ flow->counter->bytes = sb_data.counters.bytes;
+ }
+ return 0;
+ }
+ return rte_flow_error_set(error, EINVAL,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL,
+ "flow does not have counter");
+error_exit:
+ return rte_flow_error_set
+ (error, errno, RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL, "netlink: failed to read flow rule counters");
+notsup_exit:
+ return rte_flow_error_set
+ (error, ENOTSUP, RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL, "counters are not available.");
+}
+
+/**
+ * Query a flow.
+ *
+ * @see rte_flow_query()
+ * @see rte_flow_ops
+ */
+static int
+flow_tcf_query(struct rte_eth_dev *dev,
+ struct rte_flow *flow,
+ const struct rte_flow_action *actions,
+ void *data,
+ struct rte_flow_error *error)
+{
+ int ret = -EINVAL;
+
+ for (; actions->type != RTE_FLOW_ACTION_TYPE_END; actions++) {
+ switch (actions->type) {
+ case RTE_FLOW_ACTION_TYPE_VOID:
+ break;
+ case RTE_FLOW_ACTION_TYPE_COUNT:
+ ret = flow_tcf_query_count(dev, flow, data, error);
+ break;
+ default:
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ actions,
+ "action not supported");
+ }
+ }
+ return ret;
+}
+
const struct mlx5_flow_driver_ops mlx5_flow_tcf_drv_ops = {
.validate = flow_tcf_validate,
.prepare = flow_tcf_prepare,
.apply = flow_tcf_apply,
.remove = flow_tcf_remove,
.destroy = flow_tcf_destroy,
+ .query = flow_tcf_query,
};
/**
- * Initialize ingress qdisc of a given network interface.
+ * Create and configure a libmnl socket for Netlink flow rules.
+ *
+ * @return
+ * A valid libmnl socket object pointer on success, NULL otherwise and
+ * rte_errno is set.
+ */
+static struct mnl_socket *
+flow_tcf_mnl_socket_create(void)
+{
+ struct mnl_socket *nl = mnl_socket_open(NETLINK_ROUTE);
+
+ if (nl) {
+ mnl_socket_setsockopt(nl, NETLINK_CAP_ACK, &(int){ 1 },
+ sizeof(int));
+ if (!mnl_socket_bind(nl, 0, MNL_SOCKET_AUTOPID))
+ return nl;
+ }
+ rte_errno = errno;
+ if (nl)
+ mnl_socket_close(nl);
+ return NULL;
+}
+
+/**
+ * Destroy a libmnl socket.
*
* @param nl
* Libmnl socket of the @p NETLINK_ROUTE kind.
+ */
+static void
+flow_tcf_mnl_socket_destroy(struct mnl_socket *nl)
+{
+ if (nl)
+ mnl_socket_close(nl);
+}
+
+/**
+ * Initialize ingress qdisc of a given network interface.
+ *
+ * @param ctx
+ * Pointer to tc-flower context to use.
* @param ifindex
* Index of network interface to initialize.
* @param[out] error
* 0 on success, a negative errno value otherwise and rte_errno is set.
*/
int
-mlx5_flow_tcf_init(struct mnl_socket *nl, unsigned int ifindex,
- struct rte_flow_error *error)
+mlx5_flow_tcf_init(struct mlx5_flow_tcf_context *ctx,
+ unsigned int ifindex, struct rte_flow_error *error)
{
struct nlmsghdr *nlh;
struct tcmsg *tcm;
tcm->tcm_handle = TC_H_MAKE(TC_H_INGRESS, 0);
tcm->tcm_parent = TC_H_INGRESS;
/* Ignore errors when qdisc is already absent. */
- if (flow_tcf_nl_ack(nl, nlh) &&
+ if (flow_tcf_nl_ack(ctx, nlh) &&
rte_errno != EINVAL && rte_errno != ENOENT)
return rte_flow_error_set(error, rte_errno,
RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
tcm->tcm_handle = TC_H_MAKE(TC_H_INGRESS, 0);
tcm->tcm_parent = TC_H_INGRESS;
mnl_attr_put_strz_check(nlh, sizeof(buf), TCA_KIND, "ingress");
- if (flow_tcf_nl_ack(nl, nlh))
+ if (flow_tcf_nl_ack(ctx, nlh))
return rte_flow_error_set(error, rte_errno,
RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
"netlink: failed to create ingress"
}
/**
- * Create and configure a libmnl socket for Netlink flow rules.
+ * Create libmnl context for Netlink flow rules.
*
* @return
* A valid libmnl socket object pointer on success, NULL otherwise and
* rte_errno is set.
*/
-struct mnl_socket *
-mlx5_flow_tcf_socket_create(void)
+struct mlx5_flow_tcf_context *
+mlx5_flow_tcf_context_create(void)
{
- struct mnl_socket *nl = mnl_socket_open(NETLINK_ROUTE);
-
- if (nl) {
- mnl_socket_setsockopt(nl, NETLINK_CAP_ACK, &(int){ 1 },
- sizeof(int));
- if (!mnl_socket_bind(nl, 0, MNL_SOCKET_AUTOPID))
- return nl;
- }
- rte_errno = errno;
- if (nl)
- mnl_socket_close(nl);
+ struct mlx5_flow_tcf_context *ctx = rte_zmalloc(__func__,
+ sizeof(*ctx),
+ sizeof(uint32_t));
+ if (!ctx)
+ goto error;
+ ctx->nl = flow_tcf_mnl_socket_create();
+ if (!ctx->nl)
+ goto error;
+ ctx->buf_size = MNL_SOCKET_BUFFER_SIZE;
+ ctx->buf = rte_zmalloc(__func__,
+ ctx->buf_size, sizeof(uint32_t));
+ if (!ctx->buf)
+ goto error;
+ ctx->seq = random();
+ return ctx;
+error:
+ mlx5_flow_tcf_context_destroy(ctx);
return NULL;
}
/**
- * Destroy a libmnl socket.
+ * Destroy a libmnl context.
*
- * @param nl
+ * @param ctx
* Libmnl socket of the @p NETLINK_ROUTE kind.
*/
void
-mlx5_flow_tcf_socket_destroy(struct mnl_socket *nl)
+mlx5_flow_tcf_context_destroy(struct mlx5_flow_tcf_context *ctx)
{
- mnl_socket_close(nl);
+ if (!ctx)
+ return;
+ flow_tcf_mnl_socket_destroy(ctx->nl);
+ rte_free(ctx->buf);
+ rte_free(ctx);
}
git.droids-corp.org / dpdk.git / blobdiff