+ case RTE_FLOW_ACTION_TYPE_JUMP:
+ conf.jump = actions->conf;
+ na_act_index =
+ mnl_attr_nest_start(nlh, na_act_index_cur++);
+ assert(na_act_index);
+ mnl_attr_put_strz(nlh, TCA_ACT_KIND, "gact");
+ na_act = mnl_attr_nest_start(nlh, TCA_ACT_OPTIONS);
+ assert(na_act);
+ mnl_attr_put(nlh, TCA_GACT_PARMS,
+ sizeof(struct tc_gact),
+ &(struct tc_gact){
+ .action = TC_ACT_GOTO_CHAIN |
+ conf.jump->group,
+ });
+ mnl_attr_nest_end(nlh, na_act);
+ mnl_attr_nest_end(nlh, na_act_index);
+ break;
+ case RTE_FLOW_ACTION_TYPE_DROP:
+ na_act_index =
+ mnl_attr_nest_start(nlh, na_act_index_cur++);
+ assert(na_act_index);
+ mnl_attr_put_strz(nlh, TCA_ACT_KIND, "gact");
+ na_act = mnl_attr_nest_start(nlh, TCA_ACT_OPTIONS);
+ assert(na_act);
+ mnl_attr_put(nlh, TCA_GACT_PARMS,
+ sizeof(struct tc_gact),
+ &(struct tc_gact){
+ .action = TC_ACT_SHOT,
+ });
+ 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;
+ goto action_of_vlan;
+ case RTE_FLOW_ACTION_TYPE_OF_PUSH_VLAN:
+ conf.of_push_vlan = actions->conf;
+ vlan_act = TCA_VLAN_ACT_PUSH;
+ goto action_of_vlan;
+ case RTE_FLOW_ACTION_TYPE_OF_SET_VLAN_VID:
+ conf.of_set_vlan_vid = actions->conf;
+ if (na_vlan_id)
+ goto override_na_vlan_id;
+ vlan_act = TCA_VLAN_ACT_MODIFY;
+ goto action_of_vlan;
+ case RTE_FLOW_ACTION_TYPE_OF_SET_VLAN_PCP:
+ conf.of_set_vlan_pcp = actions->conf;
+ if (na_vlan_priority)
+ goto override_na_vlan_priority;
+ vlan_act = TCA_VLAN_ACT_MODIFY;
+ goto action_of_vlan;
+action_of_vlan:
+ na_act_index =
+ mnl_attr_nest_start(nlh, na_act_index_cur++);
+ assert(na_act_index);
+ mnl_attr_put_strz(nlh, TCA_ACT_KIND, "vlan");
+ na_act = mnl_attr_nest_start(nlh, TCA_ACT_OPTIONS);
+ assert(na_act);
+ mnl_attr_put(nlh, TCA_VLAN_PARMS,
+ sizeof(struct tc_vlan),
+ &(struct tc_vlan){
+ .action = TC_ACT_PIPE,
+ .v_action = vlan_act,
+ });
+ if (vlan_act == TCA_VLAN_ACT_POP) {
+ mnl_attr_nest_end(nlh, na_act);
+ mnl_attr_nest_end(nlh, na_act_index);
+ break;
+ }
+ if (vlan_act == TCA_VLAN_ACT_PUSH)
+ mnl_attr_put_u16(nlh,
+ TCA_VLAN_PUSH_VLAN_PROTOCOL,
+ conf.of_push_vlan->ethertype);
+ na_vlan_id = mnl_nlmsg_get_payload_tail(nlh);
+ mnl_attr_put_u16(nlh, TCA_VLAN_PAD, 0);
+ na_vlan_priority = mnl_nlmsg_get_payload_tail(nlh);
+ mnl_attr_put_u8(nlh, TCA_VLAN_PAD, 0);
+ mnl_attr_nest_end(nlh, na_act);
+ mnl_attr_nest_end(nlh, na_act_index);
+ if (actions->type ==
+ RTE_FLOW_ACTION_TYPE_OF_SET_VLAN_VID) {
+override_na_vlan_id:
+ na_vlan_id->nla_type = TCA_VLAN_PUSH_VLAN_ID;
+ *(uint16_t *)mnl_attr_get_payload(na_vlan_id) =
+ rte_be_to_cpu_16
+ (conf.of_set_vlan_vid->vlan_vid);
+ } else if (actions->type ==
+ RTE_FLOW_ACTION_TYPE_OF_SET_VLAN_PCP) {
+override_na_vlan_priority:
+ na_vlan_priority->nla_type =
+ TCA_VLAN_PUSH_VLAN_PRIORITY;
+ *(uint8_t *)mnl_attr_get_payload
+ (na_vlan_priority) =
+ 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_IP_TTL)
+ mnl_attr_put_u8(nlh,
+ TCA_TUNNEL_KEY_ENC_TTL,
+ encap.vxlan->ip_ttl_hop);
+ if (encap.vxlan->mask & FLOW_TCF_ENCAP_IP_TOS)
+ mnl_attr_put_u8(nlh,
+ TCA_TUNNEL_KEY_ENC_TOS,
+ encap.vxlan->ip_tos);
+ 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_IPV6_DST:
+ case RTE_FLOW_ACTION_TYPE_SET_TP_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,
+ &actions, item_flags);
+ mnl_attr_nest_end(nlh, na_act_index);
+ break;
+ default:
+ return rte_flow_error_set(error, ENOTSUP,
+ RTE_FLOW_ERROR_TYPE_ACTION,
+ actions,
+ "action not supported");
+ }
+ }
+ assert(na_flower);
+ assert(na_flower_act);
+ mnl_attr_nest_end(nlh, na_flower_act);
+ dev_flow->tcf.ptc_flags = mnl_attr_get_payload
+ (mnl_nlmsg_get_payload_tail(nlh));
+ 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 tcf
+ * Flow context to use.
+ * @param nlh
+ * Message to send. This function always raises the NLM_F_ACK flag before
+ * sending.
+ * @param[in] cb
+ * Callback handler for received message.
+ * @param[in] arg
+ * Context pointer for callback handler.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+flow_tcf_nl_ack(struct mlx5_flow_tcf_context *tcf,
+ struct nlmsghdr *nlh,
+ mnl_cb_t cb, void *arg)
+{
+ unsigned int portid = mnl_socket_get_portid(tcf->nl);
+ uint32_t seq = tcf->seq++;
+ int ret, err = 0;
+
+ assert(tcf->nl);
+ assert(tcf->buf);
+ if (!seq) {
+ /* seq 0 is reserved for kernel event-driven notifications. */
+ seq = tcf->seq++;
+ }
+ nlh->nlmsg_seq = seq;
+ nlh->nlmsg_flags |= NLM_F_ACK;
+ ret = mnl_socket_sendto(tcf->nl, nlh, nlh->nlmsg_len);
+ if (ret <= 0) {
+ /* Message send error occurred. */
+ rte_errno = errno;
+ return -rte_errno;
+ }
+ nlh = (struct nlmsghdr *)(tcf->buf);
+ /*
+ * The following loop postpones non-fatal errors until multipart
+ * messages are complete.
+ */
+ while (true) {
+ ret = mnl_socket_recvfrom(tcf->nl, tcf->buf, tcf->buf_size);
+ if (ret < 0) {
+ err = errno;
+ /*
+ * In case of overflow Will receive till
+ * end of multipart message. We may lost part
+ * of reply messages but mark and return an error.
+ */
+ if (err != ENOSPC ||
+ !(nlh->nlmsg_flags & NLM_F_MULTI) ||
+ nlh->nlmsg_type == NLMSG_DONE)
+ break;
+ } else {
+ ret = mnl_cb_run(nlh, ret, seq, portid, cb, arg);
+ if (!ret) {
+ /*
+ * libmnl returns 0 if DONE or
+ * success ACK message found.
+ */
+ break;
+ }
+ if (ret < 0) {
+ /*
+ * ACK message with error found
+ * or some error occurred.
+ */
+ err = errno;
+ break;
+ }
+ /* We should continue receiving. */
+ }
+ }
+ if (!err)
+ return 0;
+ rte_errno = err;
+ return -err;
+}
+
+#define MNL_BUF_EXTRA_SPACE 16
+#define MNL_REQUEST_SIZE_MIN 256
+#define MNL_REQUEST_SIZE_MAX 2048
+#define MNL_REQUEST_SIZE RTE_MIN(RTE_MAX(sysconf(_SC_PAGESIZE), \
+ MNL_REQUEST_SIZE_MIN), MNL_REQUEST_SIZE_MAX)
+
+/* Data structures used by flow_tcf_xxx_cb() routines. */
+struct tcf_nlcb_buf {
+ LIST_ENTRY(tcf_nlcb_buf) next;
+ uint32_t size;
+ alignas(struct nlmsghdr)
+ uint8_t msg[]; /**< Netlink message data. */
+};
+
+struct tcf_nlcb_context {
+ unsigned int ifindex; /**< Base interface index. */
+ uint32_t bufsize;
+ LIST_HEAD(, tcf_nlcb_buf) nlbuf;
+};
+
+/**
+ * Allocate space for netlink command in buffer list
+ *
+ * @param[in, out] ctx
+ * Pointer to callback context with command buffers list.
+ * @param[in] size
+ * Required size of data buffer to be allocated.
+ *
+ * @return
+ * Pointer to allocated memory, aligned as message header.
+ * NULL if some error occurred.
+ */
+static struct nlmsghdr *
+flow_tcf_alloc_nlcmd(struct tcf_nlcb_context *ctx, uint32_t size)
+{
+ struct tcf_nlcb_buf *buf;
+ struct nlmsghdr *nlh;
+
+ size = NLMSG_ALIGN(size);
+ buf = LIST_FIRST(&ctx->nlbuf);
+ if (buf && (buf->size + size) <= ctx->bufsize) {
+ nlh = (struct nlmsghdr *)&buf->msg[buf->size];
+ buf->size += size;
+ return nlh;
+ }
+ if (size > ctx->bufsize) {
+ DRV_LOG(WARNING, "netlink: too long command buffer requested");
+ return NULL;
+ }
+ buf = rte_malloc(__func__,
+ ctx->bufsize + sizeof(struct tcf_nlcb_buf),
+ alignof(struct tcf_nlcb_buf));
+ if (!buf) {
+ DRV_LOG(WARNING, "netlink: no memory for command buffer");
+ return NULL;
+ }
+ LIST_INSERT_HEAD(&ctx->nlbuf, buf, next);
+ buf->size = size;
+ nlh = (struct nlmsghdr *)&buf->msg[0];
+ return nlh;
+}
+
+/**
+ * Send the buffers with prepared netlink commands. Scans the list and
+ * sends all found buffers. Buffers are sent and freed anyway in order
+ * to prevent memory leakage if some every message in received packet.
+ *
+ * @param[in] tcf
+ * Context object initialized by mlx5_flow_tcf_context_create().
+ * @param[in, out] ctx
+ * Pointer to callback context with command buffers list.
+ *
+ * @return
+ * Zero value on success, negative errno value otherwise
+ * and rte_errno is set.
+ */
+static int
+flow_tcf_send_nlcmd(struct mlx5_flow_tcf_context *tcf,
+ struct tcf_nlcb_context *ctx)
+{
+ struct tcf_nlcb_buf *bc = LIST_FIRST(&ctx->nlbuf);
+ int ret = 0;
+
+ while (bc) {
+ struct tcf_nlcb_buf *bn = LIST_NEXT(bc, next);
+ struct nlmsghdr *nlh;
+ uint32_t msg = 0;
+ int rc;
+
+ while (msg < bc->size) {
+ /*
+ * Send Netlink commands from buffer in one by one
+ * fashion. If we send multiple rule deletion commands
+ * in one Netlink message and some error occurs it may
+ * cause multiple ACK error messages and break sequence
+ * numbers of Netlink communication, because we expect
+ * the only one ACK reply.
+ */
+ assert((bc->size - msg) >= sizeof(struct nlmsghdr));
+ nlh = (struct nlmsghdr *)&bc->msg[msg];
+ assert((bc->size - msg) >= nlh->nlmsg_len);
+ msg += nlh->nlmsg_len;
+ rc = flow_tcf_nl_ack(tcf, nlh, NULL, NULL);
+ if (rc) {
+ DRV_LOG(WARNING,
+ "netlink: cleanup error %d", rc);
+ if (!ret)
+ ret = rc;
+ }
+ }
+ rte_free(bc);
+ bc = bn;
+ }
+ LIST_INIT(&ctx->nlbuf);
+ return ret;
+}
+
+/**
+ * Collect local IP address rules with scope link attribute on specified
+ * network device. This is callback routine called by libmnl mnl_cb_run()
+ * in loop for every message in received packet.
+ *
+ * @param[in] nlh
+ * Pointer to reply header.
+ * @param[in, out] arg
+ * Opaque data pointer for this callback.
+ *
+ * @return
+ * A positive, nonzero value on success, negative errno value otherwise
+ * and rte_errno is set.
+ */
+static int
+flow_tcf_collect_local_cb(const struct nlmsghdr *nlh, void *arg)
+{
+ struct tcf_nlcb_context *ctx = arg;
+ struct nlmsghdr *cmd;
+ struct ifaddrmsg *ifa;
+ struct nlattr *na;
+ struct nlattr *na_local = NULL;
+ struct nlattr *na_peer = NULL;
+ unsigned char family;
+ uint32_t size;
+
+ if (nlh->nlmsg_type != RTM_NEWADDR) {
+ rte_errno = EINVAL;
+ return -rte_errno;
+ }
+ ifa = mnl_nlmsg_get_payload(nlh);
+ family = ifa->ifa_family;
+ if (ifa->ifa_index != ctx->ifindex ||
+ ifa->ifa_scope != RT_SCOPE_LINK ||
+ !(ifa->ifa_flags & IFA_F_PERMANENT) ||
+ (family != AF_INET && family != AF_INET6))
+ return 1;
+ mnl_attr_for_each(na, nlh, sizeof(*ifa)) {
+ switch (mnl_attr_get_type(na)) {
+ case IFA_LOCAL:
+ na_local = na;
+ break;
+ case IFA_ADDRESS:
+ na_peer = na;
+ break;
+ }
+ if (na_local && na_peer)
+ break;
+ }
+ if (!na_local || !na_peer)
+ return 1;
+ /* Local rule found with scope link, permanent and assigned peer. */
+ size = MNL_ALIGN(sizeof(struct nlmsghdr)) +
+ MNL_ALIGN(sizeof(struct ifaddrmsg)) +
+ (family == AF_INET6 ? 2 * SZ_NLATTR_DATA_OF(IPV6_ADDR_LEN)
+ : 2 * SZ_NLATTR_TYPE_OF(uint32_t));
+ cmd = flow_tcf_alloc_nlcmd(ctx, size);
+ if (!cmd) {
+ rte_errno = ENOMEM;
+ return -rte_errno;
+ }
+ cmd = mnl_nlmsg_put_header(cmd);
+ cmd->nlmsg_type = RTM_DELADDR;
+ cmd->nlmsg_flags = NLM_F_REQUEST;
+ ifa = mnl_nlmsg_put_extra_header(cmd, sizeof(*ifa));
+ ifa->ifa_flags = IFA_F_PERMANENT;
+ ifa->ifa_scope = RT_SCOPE_LINK;
+ ifa->ifa_index = ctx->ifindex;
+ if (family == AF_INET) {
+ ifa->ifa_family = AF_INET;
+ ifa->ifa_prefixlen = 32;
+ mnl_attr_put_u32(cmd, IFA_LOCAL, mnl_attr_get_u32(na_local));
+ mnl_attr_put_u32(cmd, IFA_ADDRESS, mnl_attr_get_u32(na_peer));
+ } else {
+ ifa->ifa_family = AF_INET6;
+ ifa->ifa_prefixlen = 128;
+ mnl_attr_put(cmd, IFA_LOCAL, IPV6_ADDR_LEN,
+ mnl_attr_get_payload(na_local));
+ mnl_attr_put(cmd, IFA_ADDRESS, IPV6_ADDR_LEN,
+ mnl_attr_get_payload(na_peer));
+ }
+ assert(size == cmd->nlmsg_len);
+ return 1;
+}
+
+/**
+ * Cleanup the local IP addresses on outer interface.
+ *
+ * @param[in] tcf
+ * Context object initialized by mlx5_flow_tcf_context_create().
+ * @param[in] ifindex
+ * Network interface index to perform cleanup.
+ */
+static void
+flow_tcf_encap_local_cleanup(struct mlx5_flow_tcf_context *tcf,
+ unsigned int ifindex)
+{
+ struct nlmsghdr *nlh;
+ struct ifaddrmsg *ifa;
+ struct tcf_nlcb_context ctx = {
+ .ifindex = ifindex,
+ .bufsize = MNL_REQUEST_SIZE,
+ .nlbuf = LIST_HEAD_INITIALIZER(),
+ };
+ int ret;
+
+ assert(ifindex);
+ /*
+ * Seek and destroy leftovers of local IP addresses with
+ * matching properties "scope link".
+ */
+ nlh = mnl_nlmsg_put_header(tcf->buf);
+ nlh->nlmsg_type = RTM_GETADDR;
+ nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP;
+ ifa = mnl_nlmsg_put_extra_header(nlh, sizeof(*ifa));
+ ifa->ifa_family = AF_UNSPEC;
+ ifa->ifa_index = ifindex;
+ ifa->ifa_scope = RT_SCOPE_LINK;
+ ret = flow_tcf_nl_ack(tcf, nlh, flow_tcf_collect_local_cb, &ctx);
+ if (ret)
+ DRV_LOG(WARNING, "netlink: query device list error %d", ret);
+ ret = flow_tcf_send_nlcmd(tcf, &ctx);
+ if (ret)
+ DRV_LOG(WARNING, "netlink: device delete error %d", ret);
+}
+
+/**
+ * Collect neigh permanent rules on specified network device.
+ * This is callback routine called by libmnl mnl_cb_run() in loop for
+ * every message in received packet.
+ *
+ * @param[in] nlh
+ * Pointer to reply header.
+ * @param[in, out] arg
+ * Opaque data pointer for this callback.
+ *
+ * @return
+ * A positive, nonzero value on success, negative errno value otherwise
+ * and rte_errno is set.
+ */
+static int
+flow_tcf_collect_neigh_cb(const struct nlmsghdr *nlh, void *arg)
+{
+ struct tcf_nlcb_context *ctx = arg;
+ struct nlmsghdr *cmd;
+ struct ndmsg *ndm;
+ struct nlattr *na;
+ struct nlattr *na_ip = NULL;
+ struct nlattr *na_mac = NULL;
+ unsigned char family;
+ uint32_t size;
+
+ if (nlh->nlmsg_type != RTM_NEWNEIGH) {
+ rte_errno = EINVAL;
+ return -rte_errno;
+ }
+ ndm = mnl_nlmsg_get_payload(nlh);
+ family = ndm->ndm_family;
+ if (ndm->ndm_ifindex != (int)ctx->ifindex ||
+ !(ndm->ndm_state & NUD_PERMANENT) ||
+ (family != AF_INET && family != AF_INET6))
+ return 1;
+ mnl_attr_for_each(na, nlh, sizeof(*ndm)) {
+ switch (mnl_attr_get_type(na)) {
+ case NDA_DST:
+ na_ip = na;
+ break;
+ case NDA_LLADDR:
+ na_mac = na;
+ break;
+ }
+ if (na_mac && na_ip)
+ break;
+ }
+ if (!na_mac || !na_ip)
+ return 1;
+ /* Neigh rule with permanent attribute found. */
+ size = MNL_ALIGN(sizeof(struct nlmsghdr)) +
+ MNL_ALIGN(sizeof(struct ndmsg)) +
+ SZ_NLATTR_DATA_OF(ETHER_ADDR_LEN) +
+ (family == AF_INET6 ? SZ_NLATTR_DATA_OF(IPV6_ADDR_LEN)
+ : SZ_NLATTR_TYPE_OF(uint32_t));
+ cmd = flow_tcf_alloc_nlcmd(ctx, size);
+ if (!cmd) {
+ rte_errno = ENOMEM;
+ return -rte_errno;
+ }
+ cmd = mnl_nlmsg_put_header(cmd);
+ cmd->nlmsg_type = RTM_DELNEIGH;
+ cmd->nlmsg_flags = NLM_F_REQUEST;
+ ndm = mnl_nlmsg_put_extra_header(cmd, sizeof(*ndm));
+ ndm->ndm_ifindex = ctx->ifindex;
+ ndm->ndm_state = NUD_PERMANENT;
+ ndm->ndm_flags = 0;
+ ndm->ndm_type = 0;
+ if (family == AF_INET) {
+ ndm->ndm_family = AF_INET;
+ mnl_attr_put_u32(cmd, NDA_DST, mnl_attr_get_u32(na_ip));
+ } else {
+ ndm->ndm_family = AF_INET6;
+ mnl_attr_put(cmd, NDA_DST, IPV6_ADDR_LEN,
+ mnl_attr_get_payload(na_ip));
+ }
+ mnl_attr_put(cmd, NDA_LLADDR, ETHER_ADDR_LEN,
+ mnl_attr_get_payload(na_mac));
+ assert(size == cmd->nlmsg_len);
+ return 1;
+}
+
+/**
+ * Cleanup the neigh rules on outer interface.
+ *
+ * @param[in] tcf
+ * Context object initialized by mlx5_flow_tcf_context_create().
+ * @param[in] ifindex
+ * Network interface index to perform cleanup.
+ */
+static void
+flow_tcf_encap_neigh_cleanup(struct mlx5_flow_tcf_context *tcf,
+ unsigned int ifindex)
+{
+ struct nlmsghdr *nlh;
+ struct ndmsg *ndm;
+ struct tcf_nlcb_context ctx = {
+ .ifindex = ifindex,
+ .bufsize = MNL_REQUEST_SIZE,
+ .nlbuf = LIST_HEAD_INITIALIZER(),
+ };
+ int ret;
+
+ assert(ifindex);
+ /* Seek and destroy leftovers of neigh rules. */
+ nlh = mnl_nlmsg_put_header(tcf->buf);
+ nlh->nlmsg_type = RTM_GETNEIGH;
+ nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP;
+ ndm = mnl_nlmsg_put_extra_header(nlh, sizeof(*ndm));
+ ndm->ndm_family = AF_UNSPEC;
+ ndm->ndm_ifindex = ifindex;
+ ndm->ndm_state = NUD_PERMANENT;
+ ret = flow_tcf_nl_ack(tcf, nlh, flow_tcf_collect_neigh_cb, &ctx);
+ if (ret)
+ DRV_LOG(WARNING, "netlink: query device list error %d", ret);
+ ret = flow_tcf_send_nlcmd(tcf, &ctx);
+ if (ret)
+ DRV_LOG(WARNING, "netlink: device delete error %d", ret);
+}
+
+/**
+ * Collect indices of VXLAN encap/decap interfaces associated with device.
+ * This is callback routine called by libmnl mnl_cb_run() in loop for
+ * every message in received packet.
+ *
+ * @param[in] nlh
+ * Pointer to reply header.
+ * @param[in, out] arg
+ * Opaque data pointer for this callback.
+ *
+ * @return
+ * A positive, nonzero value on success, negative errno value otherwise
+ * and rte_errno is set.
+ */
+static int
+flow_tcf_collect_vxlan_cb(const struct nlmsghdr *nlh, void *arg)
+{
+ struct tcf_nlcb_context *ctx = arg;
+ struct nlmsghdr *cmd;
+ struct ifinfomsg *ifm;
+ struct nlattr *na;
+ struct nlattr *na_info = NULL;
+ struct nlattr *na_vxlan = NULL;
+ bool found = false;
+ unsigned int vxindex;
+ uint32_t size;
+
+ if (nlh->nlmsg_type != RTM_NEWLINK) {
+ rte_errno = EINVAL;
+ return -rte_errno;
+ }
+ ifm = mnl_nlmsg_get_payload(nlh);
+ if (!ifm->ifi_index) {
+ rte_errno = EINVAL;
+ return -rte_errno;
+ }
+ mnl_attr_for_each(na, nlh, sizeof(*ifm))
+ if (mnl_attr_get_type(na) == IFLA_LINKINFO) {
+ na_info = na;
+ break;
+ }
+ if (!na_info)
+ return 1;
+ mnl_attr_for_each_nested(na, na_info) {
+ switch (mnl_attr_get_type(na)) {
+ case IFLA_INFO_KIND:
+ if (!strncmp("vxlan", mnl_attr_get_str(na),
+ mnl_attr_get_len(na)))
+ found = true;
+ break;
+ case IFLA_INFO_DATA:
+ na_vxlan = na;
+ break;
+ }
+ if (found && na_vxlan)
+ break;
+ }
+ if (!found || !na_vxlan)
+ return 1;
+ found = false;
+ mnl_attr_for_each_nested(na, na_vxlan) {
+ if (mnl_attr_get_type(na) == IFLA_VXLAN_LINK &&
+ mnl_attr_get_u32(na) == ctx->ifindex) {
+ found = true;
+ break;
+ }
+ }
+ if (!found)
+ return 1;
+ /* Attached VXLAN device found, store the command to delete. */
+ vxindex = ifm->ifi_index;
+ size = MNL_ALIGN(sizeof(struct nlmsghdr)) +
+ MNL_ALIGN(sizeof(struct ifinfomsg));
+ cmd = flow_tcf_alloc_nlcmd(ctx, size);
+ if (!cmd) {
+ rte_errno = ENOMEM;
+ return -rte_errno;
+ }
+ cmd = mnl_nlmsg_put_header(cmd);
+ cmd->nlmsg_type = RTM_DELLINK;
+ cmd->nlmsg_flags = NLM_F_REQUEST;
+ ifm = mnl_nlmsg_put_extra_header(cmd, sizeof(*ifm));
+ ifm->ifi_family = AF_UNSPEC;
+ ifm->ifi_index = vxindex;
+ assert(size == cmd->nlmsg_len);
+ return 1;
+}
+
+/**
+ * Cleanup the outer interface. Removes all found vxlan devices
+ * attached to specified index, flushes the neigh and local IP
+ * database.
+ *
+ * @param[in] tcf
+ * Context object initialized by mlx5_flow_tcf_context_create().
+ * @param[in] ifindex
+ * Network inferface index to perform cleanup.
+ */
+static void
+flow_tcf_encap_iface_cleanup(struct mlx5_flow_tcf_context *tcf,
+ unsigned int ifindex)
+{
+ struct nlmsghdr *nlh;
+ struct ifinfomsg *ifm;
+ struct tcf_nlcb_context ctx = {
+ .ifindex = ifindex,
+ .bufsize = MNL_REQUEST_SIZE,
+ .nlbuf = LIST_HEAD_INITIALIZER(),
+ };
+ int ret;
+
+ assert(ifindex);
+ /*
+ * Seek and destroy leftover VXLAN encap/decap interfaces with
+ * matching properties.
+ */
+ nlh = mnl_nlmsg_put_header(tcf->buf);
+ nlh->nlmsg_type = RTM_GETLINK;
+ nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP;
+ ifm = mnl_nlmsg_put_extra_header(nlh, sizeof(*ifm));
+ ifm->ifi_family = AF_UNSPEC;
+ ret = flow_tcf_nl_ack(tcf, nlh, flow_tcf_collect_vxlan_cb, &ctx);
+ if (ret)
+ DRV_LOG(WARNING, "netlink: query device list error %d", ret);
+ ret = flow_tcf_send_nlcmd(tcf, &ctx);
+ if (ret)
+ DRV_LOG(WARNING, "netlink: device delete error %d", ret);
+}
+
+/**
+ * Emit Netlink message to add/remove local address to the outer device.
+ * The address being added is visible within the link only (scope link).
+ *
+ * Note that an implicit route is maintained by the kernel due to the
+ * presence of a peer address (IFA_ADDRESS).
+ *
+ * These rules are used for encapsulation only and allow to assign
+ * the outer tunnel source IP address.
+ *
+ * @param[in] tcf
+ * Libmnl socket context object.
+ * @param[in] encap
+ * Encapsulation properties (source address and its peer).
+ * @param[in] ifindex
+ * Network interface to apply rule.
+ * @param[in] enable
+ * Toggle between add and remove.
+ * @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_rule_local(struct mlx5_flow_tcf_context *tcf,
+ const struct flow_tcf_vxlan_encap *encap,
+ unsigned int ifindex,
+ bool enable,
+ struct rte_flow_error *error)
+{
+ struct nlmsghdr *nlh;
+ struct ifaddrmsg *ifa;
+ alignas(struct nlmsghdr)
+ uint8_t buf[mnl_nlmsg_size(sizeof(*ifa) + 128)];
+
+ nlh = mnl_nlmsg_put_header(buf);
+ nlh->nlmsg_type = enable ? RTM_NEWADDR : RTM_DELADDR;
+ nlh->nlmsg_flags =
+ NLM_F_REQUEST | (enable ? NLM_F_CREATE | NLM_F_REPLACE : 0);
+ nlh->nlmsg_seq = 0;
+ ifa = mnl_nlmsg_put_extra_header(nlh, sizeof(*ifa));
+ ifa->ifa_flags = IFA_F_PERMANENT;
+ ifa->ifa_scope = RT_SCOPE_LINK;
+ ifa->ifa_index = ifindex;
+ if (encap->mask & FLOW_TCF_ENCAP_IPV4_SRC) {
+ ifa->ifa_family = AF_INET;
+ ifa->ifa_prefixlen = 32;
+ mnl_attr_put_u32(nlh, IFA_LOCAL, encap->ipv4.src);
+ if (encap->mask & FLOW_TCF_ENCAP_IPV4_DST)
+ mnl_attr_put_u32(nlh, IFA_ADDRESS,
+ encap->ipv4.dst);
+ } else {
+ assert(encap->mask & FLOW_TCF_ENCAP_IPV6_SRC);
+ ifa->ifa_family = AF_INET6;
+ ifa->ifa_prefixlen = 128;
+ mnl_attr_put(nlh, IFA_LOCAL,
+ sizeof(encap->ipv6.src),
+ &encap->ipv6.src);
+ if (encap->mask & FLOW_TCF_ENCAP_IPV6_DST)
+ mnl_attr_put(nlh, IFA_ADDRESS,
+ sizeof(encap->ipv6.dst),
+ &encap->ipv6.dst);
+ }
+ if (!flow_tcf_nl_ack(tcf, nlh, NULL, NULL))
+ return 0;
+ return rte_flow_error_set(error, rte_errno,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
+ "netlink: cannot complete IFA request"
+ " (ip addr add)");
+}
+
+/**
+ * Emit Netlink message to add/remove neighbor.
+ *
+ * @param[in] tcf
+ * Libmnl socket context object.
+ * @param[in] encap
+ * Encapsulation properties (destination address).
+ * @param[in] ifindex
+ * Network interface.
+ * @param[in] enable
+ * Toggle between add and remove.
+ * @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_rule_neigh(struct mlx5_flow_tcf_context *tcf,
+ const struct flow_tcf_vxlan_encap *encap,
+ unsigned int ifindex,
+ bool enable,
+ struct rte_flow_error *error)
+{
+ struct nlmsghdr *nlh;
+ struct ndmsg *ndm;
+ alignas(struct nlmsghdr)
+ uint8_t buf[mnl_nlmsg_size(sizeof(*ndm) + 128)];
+
+ nlh = mnl_nlmsg_put_header(buf);
+ nlh->nlmsg_type = enable ? RTM_NEWNEIGH : RTM_DELNEIGH;
+ nlh->nlmsg_flags =
+ NLM_F_REQUEST | (enable ? NLM_F_CREATE | NLM_F_REPLACE : 0);
+ nlh->nlmsg_seq = 0;
+ ndm = mnl_nlmsg_put_extra_header(nlh, sizeof(*ndm));
+ ndm->ndm_ifindex = ifindex;
+ ndm->ndm_state = NUD_PERMANENT;
+ ndm->ndm_flags = 0;
+ ndm->ndm_type = 0;
+ if (encap->mask & FLOW_TCF_ENCAP_IPV4_DST) {
+ ndm->ndm_family = AF_INET;
+ mnl_attr_put_u32(nlh, NDA_DST, encap->ipv4.dst);
+ } else {
+ assert(encap->mask & FLOW_TCF_ENCAP_IPV6_DST);
+ ndm->ndm_family = AF_INET6;
+ mnl_attr_put(nlh, NDA_DST, sizeof(encap->ipv6.dst),
+ &encap->ipv6.dst);
+ }
+ if (encap->mask & FLOW_TCF_ENCAP_ETH_SRC && enable)
+ DRV_LOG(WARNING,
+ "outer ethernet source address cannot be "
+ "forced for VXLAN encapsulation");
+ if (encap->mask & FLOW_TCF_ENCAP_ETH_DST)
+ mnl_attr_put(nlh, NDA_LLADDR, sizeof(encap->eth.dst),
+ &encap->eth.dst);
+ if (!flow_tcf_nl_ack(tcf, nlh, NULL, NULL))
+ return 0;
+ return rte_flow_error_set(error, rte_errno,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
+ "netlink: cannot complete ND request"
+ " (ip neigh)");
+}
+
+/**
+ * Manage the local IP addresses and their peers IP addresses on the
+ * outer interface for encapsulation purposes. The kernel searches the
+ * appropriate device for tunnel egress traffic using the outer source
+ * IP, this IP should be assigned to the outer network device, otherwise
+ * kernel rejects the rule.
+ *
+ * Adds or removes the addresses using the Netlink command like this:
+ * ip addr add <src_ip> peer <dst_ip> scope link dev <ifouter>
+ *
+ * The addresses are local to the netdev ("scope link"), this reduces
+ * the risk of conflicts. Note that an implicit route is maintained by
+ * the kernel due to the presence of a peer address (IFA_ADDRESS).
+ *
+ * @param[in] tcf
+ * Libmnl socket context object.
+ * @param[in] iface
+ * Object, contains rule database and ifouter index.
+ * @param[in] dev_flow
+ * Flow object, contains the tunnel parameters (for encap only).
+ * @param[in] enable
+ * Toggle between add and remove.
+ * @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_encap_local(struct mlx5_flow_tcf_context *tcf,
+ struct tcf_irule *iface,
+ struct mlx5_flow *dev_flow,
+ bool enable,
+ struct rte_flow_error *error)
+{
+ const struct flow_tcf_vxlan_encap *encap = dev_flow->tcf.vxlan_encap;
+ struct tcf_local_rule *rule = NULL;
+ int ret;
+
+ assert(encap);
+ assert(encap->hdr.type == FLOW_TCF_TUNACT_VXLAN_ENCAP);
+ if (encap->mask & FLOW_TCF_ENCAP_IPV4_SRC) {
+ assert(encap->mask & FLOW_TCF_ENCAP_IPV4_DST);
+ LIST_FOREACH(rule, &iface->local, next) {
+ if (rule->mask & FLOW_TCF_ENCAP_IPV4_SRC &&
+ encap->ipv4.src == rule->ipv4.src &&
+ encap->ipv4.dst == rule->ipv4.dst) {
+ break;
+ }
+ }
+ } else {
+ assert(encap->mask & FLOW_TCF_ENCAP_IPV6_SRC);
+ assert(encap->mask & FLOW_TCF_ENCAP_IPV6_DST);
+ LIST_FOREACH(rule, &iface->local, next) {
+ if (rule->mask & FLOW_TCF_ENCAP_IPV6_SRC &&
+ !memcmp(&encap->ipv6.src, &rule->ipv6.src,
+ sizeof(encap->ipv6.src)) &&
+ !memcmp(&encap->ipv6.dst, &rule->ipv6.dst,
+ sizeof(encap->ipv6.dst))) {
+ break;
+ }
+ }
+ }
+ if (rule) {
+ if (enable) {
+ rule->refcnt++;
+ return 0;
+ }
+ if (!rule->refcnt || !--rule->refcnt) {
+ LIST_REMOVE(rule, next);
+ return flow_tcf_rule_local(tcf, encap,
+ iface->ifouter, false, error);
+ }
+ return 0;
+ }
+ if (!enable) {
+ DRV_LOG(WARNING, "disabling not existing local rule");
+ rte_flow_error_set(error, ENOENT,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
+ "disabling not existing local rule");
+ return -ENOENT;
+ }
+ rule = rte_zmalloc(__func__, sizeof(struct tcf_local_rule),
+ alignof(struct tcf_local_rule));
+ if (!rule) {
+ rte_flow_error_set(error, ENOMEM,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
+ "unable to allocate memory for local rule");
+ return -rte_errno;
+ }
+ *rule = (struct tcf_local_rule){.refcnt = 0,
+ .mask = 0,
+ };
+ if (encap->mask & FLOW_TCF_ENCAP_IPV4_SRC) {
+ rule->mask = FLOW_TCF_ENCAP_IPV4_SRC
+ | FLOW_TCF_ENCAP_IPV4_DST;
+ rule->ipv4.src = encap->ipv4.src;
+ rule->ipv4.dst = encap->ipv4.dst;
+ } else {
+ rule->mask = FLOW_TCF_ENCAP_IPV6_SRC
+ | FLOW_TCF_ENCAP_IPV6_DST;
+ memcpy(&rule->ipv6.src, &encap->ipv6.src, IPV6_ADDR_LEN);
+ memcpy(&rule->ipv6.dst, &encap->ipv6.dst, IPV6_ADDR_LEN);
+ }
+ ret = flow_tcf_rule_local(tcf, encap, iface->ifouter, true, error);
+ if (ret) {
+ rte_free(rule);
+ return ret;
+ }
+ rule->refcnt++;
+ LIST_INSERT_HEAD(&iface->local, rule, next);
+ return 0;
+}
+
+/**
+ * Manage the destination MAC/IP addresses neigh database, kernel uses
+ * this one to determine the destination MAC address within encapsulation
+ * header. Adds or removes the entries using the Netlink command like this:
+ * ip neigh add dev <ifouter> lladdr <dst_mac> to <dst_ip> nud permanent
+ *
+ * @param[in] tcf
+ * Libmnl socket context object.
+ * @param[in] iface
+ * Object, contains rule database and ifouter index.
+ * @param[in] dev_flow
+ * Flow object, contains the tunnel parameters (for encap only).
+ * @param[in] enable
+ * Toggle between add and remove.
+ * @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_encap_neigh(struct mlx5_flow_tcf_context *tcf,
+ struct tcf_irule *iface,
+ struct mlx5_flow *dev_flow,
+ bool enable,
+ struct rte_flow_error *error)
+{
+ const struct flow_tcf_vxlan_encap *encap = dev_flow->tcf.vxlan_encap;
+ struct tcf_neigh_rule *rule = NULL;
+ int ret;
+
+ assert(encap);
+ assert(encap->hdr.type == FLOW_TCF_TUNACT_VXLAN_ENCAP);
+ if (encap->mask & FLOW_TCF_ENCAP_IPV4_DST) {
+ assert(encap->mask & FLOW_TCF_ENCAP_IPV4_SRC);
+ LIST_FOREACH(rule, &iface->neigh, next) {
+ if (rule->mask & FLOW_TCF_ENCAP_IPV4_DST &&
+ encap->ipv4.dst == rule->ipv4.dst) {
+ break;
+ }
+ }
+ } else {
+ assert(encap->mask & FLOW_TCF_ENCAP_IPV6_SRC);
+ assert(encap->mask & FLOW_TCF_ENCAP_IPV6_DST);
+ LIST_FOREACH(rule, &iface->neigh, next) {
+ if (rule->mask & FLOW_TCF_ENCAP_IPV6_DST &&
+ !memcmp(&encap->ipv6.dst, &rule->ipv6.dst,
+ sizeof(encap->ipv6.dst))) {
+ break;
+ }
+ }
+ }
+ if (rule) {
+ if (memcmp(&encap->eth.dst, &rule->eth,
+ sizeof(encap->eth.dst))) {
+ DRV_LOG(WARNING, "Destination MAC differs"
+ " in neigh rule");
+ rte_flow_error_set(error, EEXIST,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
+ NULL, "Different MAC address"
+ " neigh rule for the same"
+ " destination IP");
+ return -EEXIST;
+ }
+ if (enable) {
+ rule->refcnt++;
+ return 0;
+ }
+ if (!rule->refcnt || !--rule->refcnt) {
+ LIST_REMOVE(rule, next);
+ return flow_tcf_rule_neigh(tcf, encap,
+ iface->ifouter,
+ false, error);
+ }
+ return 0;
+ }
+ if (!enable) {
+ DRV_LOG(WARNING, "Disabling not existing neigh rule");
+ rte_flow_error_set(error, ENOENT,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
+ "unable to allocate memory for neigh rule");
+ return -ENOENT;
+ }
+ rule = rte_zmalloc(__func__, sizeof(struct tcf_neigh_rule),
+ alignof(struct tcf_neigh_rule));
+ if (!rule) {
+ rte_flow_error_set(error, ENOMEM,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
+ "unable to allocate memory for neigh rule");
+ return -rte_errno;
+ }
+ *rule = (struct tcf_neigh_rule){.refcnt = 0,
+ .mask = 0,
+ };
+ if (encap->mask & FLOW_TCF_ENCAP_IPV4_DST) {
+ rule->mask = FLOW_TCF_ENCAP_IPV4_DST;
+ rule->ipv4.dst = encap->ipv4.dst;
+ } else {
+ rule->mask = FLOW_TCF_ENCAP_IPV6_DST;
+ memcpy(&rule->ipv6.dst, &encap->ipv6.dst, IPV6_ADDR_LEN);
+ }
+ memcpy(&rule->eth, &encap->eth.dst, sizeof(rule->eth));
+ ret = flow_tcf_rule_neigh(tcf, encap, iface->ifouter, true, error);
+ if (ret) {
+ rte_free(rule);
+ return ret;
+ }
+ rule->refcnt++;
+ LIST_INSERT_HEAD(&iface->neigh, rule, next);
+ return 0;
+}
+
+/* VXLAN encap rule database for outer interfaces. */
+static LIST_HEAD(, tcf_irule) iface_list_vxlan = LIST_HEAD_INITIALIZER();
+
+/* VTEP device list is shared between PMD port instances. */
+static LIST_HEAD(, tcf_vtep) vtep_list_vxlan = LIST_HEAD_INITIALIZER();
+static pthread_mutex_t vtep_list_mutex = PTHREAD_MUTEX_INITIALIZER;
+
+/**
+ * Acquire the VXLAN encap rules container for specified interface.
+ * First looks for the container in the existing ones list, creates
+ * and initializes the new container if existing not found.
+ *
+ * @param[in] tcf
+ * Context object initialized by mlx5_flow_tcf_context_create().
+ * @param[in] ifouter
+ * Network interface index to create VXLAN encap rules on.
+ * @param[out] error
+ * Perform verbose error reporting if not NULL.
+ * @return
+ * Rule container pointer on success,
+ * NULL otherwise and rte_errno is set.
+ */
+static struct tcf_irule*
+flow_tcf_encap_irule_acquire(struct mlx5_flow_tcf_context *tcf,
+ unsigned int ifouter,
+ struct rte_flow_error *error)
+{
+ struct tcf_irule *iface;
+
+ /* Look whether the container for encap rules is created. */
+ assert(ifouter);
+ LIST_FOREACH(iface, &iface_list_vxlan, next) {
+ if (iface->ifouter == ifouter)
+ break;
+ }
+ if (iface) {
+ /* Container already exists, just increment the reference. */
+ iface->refcnt++;
+ return iface;
+ }
+ /* Not found, we should create the new container. */
+ iface = rte_zmalloc(__func__, sizeof(*iface),
+ alignof(struct tcf_irule));
+ if (!iface) {
+ rte_flow_error_set(error, ENOMEM,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
+ "unable to allocate memory for container");
+ return NULL;
+ }
+ *iface = (struct tcf_irule){
+ .local = LIST_HEAD_INITIALIZER(),
+ .neigh = LIST_HEAD_INITIALIZER(),
+ .ifouter = ifouter,
+ .refcnt = 1,
+ };
+ /* Interface cleanup for new container created. */
+ flow_tcf_encap_iface_cleanup(tcf, ifouter);
+ flow_tcf_encap_local_cleanup(tcf, ifouter);
+ flow_tcf_encap_neigh_cleanup(tcf, ifouter);
+ LIST_INSERT_HEAD(&iface_list_vxlan, iface, next);
+ return iface;
+}
+
+/**
+ * Releases VXLAN encap rules container by pointer. Decrements the
+ * reference counter and deletes the container if counter is zero.
+ *
+ * @param[in] irule
+ * VXLAN rule container pointer to release.
+ */
+static void
+flow_tcf_encap_irule_release(struct tcf_irule *iface)
+{
+ assert(iface->refcnt);
+ if (--iface->refcnt == 0) {
+ /* Reference counter is zero, delete the container. */
+ assert(LIST_EMPTY(&iface->local));
+ assert(LIST_EMPTY(&iface->neigh));
+ LIST_REMOVE(iface, next);
+ rte_free(iface);
+ }
+}
+
+/**
+ * Deletes VTEP network device.
+ *
+ * @param[in] tcf
+ * Context object initialized by mlx5_flow_tcf_context_create().
+ * @param[in] vtep
+ * Object representing the network device to delete. Memory
+ * allocated for this object is freed by routine.
+ */
+static void
+flow_tcf_vtep_delete(struct mlx5_flow_tcf_context *tcf,
+ struct tcf_vtep *vtep)
+{
+ struct nlmsghdr *nlh;
+ struct ifinfomsg *ifm;
+ alignas(struct nlmsghdr)
+ uint8_t buf[mnl_nlmsg_size(MNL_ALIGN(sizeof(*ifm))) +
+ MNL_BUF_EXTRA_SPACE];
+ int ret;
+
+ assert(!vtep->refcnt);
+ /* Delete only ifaces those we actually created. */
+ if (vtep->created && vtep->ifindex) {
+ DRV_LOG(INFO, "VTEP delete (%d)", vtep->ifindex);
+ nlh = mnl_nlmsg_put_header(buf);
+ nlh->nlmsg_type = RTM_DELLINK;
+ nlh->nlmsg_flags = NLM_F_REQUEST;
+ ifm = mnl_nlmsg_put_extra_header(nlh, sizeof(*ifm));
+ ifm->ifi_family = AF_UNSPEC;
+ ifm->ifi_index = vtep->ifindex;
+ assert(sizeof(buf) >= nlh->nlmsg_len);
+ ret = flow_tcf_nl_ack(tcf, nlh, NULL, NULL);
+ if (ret)
+ DRV_LOG(WARNING, "netlink: error deleting vxlan"
+ " encap/decap ifindex %u",
+ ifm->ifi_index);
+ }
+ rte_free(vtep);
+}
+
+/**
+ * Creates VTEP network device.
+ *
+ * @param[in] tcf
+ * Context object initialized by mlx5_flow_tcf_context_create().
+ * @param[in] port
+ * UDP port of created VTEP device.
+ * @param[out] error
+ * Perform verbose error reporting if not NULL.
+ *
+ * @return
+ * Pointer to created device structure on success,
+ * NULL otherwise and rte_errno is set.
+ */
+static struct tcf_vtep*
+flow_tcf_vtep_create(struct mlx5_flow_tcf_context *tcf,
+ uint16_t port, struct rte_flow_error *error)
+{
+ struct tcf_vtep *vtep;
+ struct nlmsghdr *nlh;
+ struct ifinfomsg *ifm;
+ char name[sizeof(MLX5_VXLAN_DEVICE_PFX) + 24];
+ alignas(struct nlmsghdr)
+ uint8_t buf[mnl_nlmsg_size(sizeof(*ifm)) +
+ SZ_NLATTR_DATA_OF(sizeof(name)) +
+ SZ_NLATTR_NEST * 2 +
+ SZ_NLATTR_STRZ_OF("vxlan") +
+ SZ_NLATTR_DATA_OF(sizeof(uint32_t)) +
+ SZ_NLATTR_DATA_OF(sizeof(uint16_t)) +
+ SZ_NLATTR_DATA_OF(sizeof(uint8_t)) * 3 +
+ MNL_BUF_EXTRA_SPACE];
+ struct nlattr *na_info;
+ struct nlattr *na_vxlan;
+ rte_be16_t vxlan_port = rte_cpu_to_be_16(port);
+ int ret;
+
+ vtep = rte_zmalloc(__func__, sizeof(*vtep), alignof(struct tcf_vtep));
+ if (!vtep) {
+ rte_flow_error_set(error, ENOMEM,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
+ "unable to allocate memory for VTEP");
+ return NULL;
+ }
+ *vtep = (struct tcf_vtep){
+ .port = port,
+ };
+ memset(buf, 0, sizeof(buf));
+ nlh = mnl_nlmsg_put_header(buf);
+ nlh->nlmsg_type = RTM_NEWLINK;
+ nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE | NLM_F_EXCL;
+ ifm = mnl_nlmsg_put_extra_header(nlh, sizeof(*ifm));
+ ifm->ifi_family = AF_UNSPEC;
+ ifm->ifi_type = 0;
+ ifm->ifi_index = 0;
+ ifm->ifi_flags = IFF_UP;
+ ifm->ifi_change = 0xffffffff;
+ snprintf(name, sizeof(name), "%s%u", MLX5_VXLAN_DEVICE_PFX, port);
+ mnl_attr_put_strz(nlh, IFLA_IFNAME, name);
+ na_info = mnl_attr_nest_start(nlh, IFLA_LINKINFO);
+ assert(na_info);
+ mnl_attr_put_strz(nlh, IFLA_INFO_KIND, "vxlan");
+ na_vxlan = mnl_attr_nest_start(nlh, IFLA_INFO_DATA);
+ assert(na_vxlan);
+#ifdef HAVE_IFLA_VXLAN_COLLECT_METADATA
+ /*
+ * RH 7.2 does not support metadata for tunnel device.
+ * It does not matter because we are going to use the
+ * hardware offload by mlx5 driver.
+ */
+ mnl_attr_put_u8(nlh, IFLA_VXLAN_COLLECT_METADATA, 1);
+#endif
+ mnl_attr_put_u8(nlh, IFLA_VXLAN_UDP_ZERO_CSUM6_RX, 1);
+ mnl_attr_put_u8(nlh, IFLA_VXLAN_LEARNING, 0);
+ mnl_attr_put_u16(nlh, IFLA_VXLAN_PORT, vxlan_port);
+#ifndef HAVE_IFLA_VXLAN_COLLECT_METADATA
+ /*
+ * We must specify VNI explicitly if metadata not supported.
+ * Note, VNI is transferred with native endianness format.
+ */
+ mnl_attr_put_u16(nlh, IFLA_VXLAN_ID, MLX5_VXLAN_DEFAULT_VNI);
+#endif
+ mnl_attr_nest_end(nlh, na_vxlan);
+ mnl_attr_nest_end(nlh, na_info);
+ assert(sizeof(buf) >= nlh->nlmsg_len);
+ ret = flow_tcf_nl_ack(tcf, nlh, NULL, NULL);
+ if (ret) {
+ DRV_LOG(WARNING,
+ "netlink: VTEP %s create failure (%d)",
+ name, rte_errno);
+ if (rte_errno != EEXIST)
+ /*
+ * Some unhandled error occurred or device is
+ * for encapsulation and cannot be shared.
+ */
+ goto error;
+ } else {
+ /*
+ * Mark device we actually created.
+ * We should explicitly delete
+ * when we do not need it anymore.
+ */
+ vtep->created = 1;
+ vtep->waitreg = 1;
+ }
+ /* Try to get ifindex of created of pre-existing device. */
+ ret = if_nametoindex(name);
+ if (!ret) {
+ DRV_LOG(WARNING,
+ "VTEP %s failed to get index (%d)", name, errno);
+ rte_flow_error_set
+ (error, -errno,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
+ "netlink: failed to retrieve VTEP ifindex");
+ goto error;
+ }
+ vtep->ifindex = ret;
+ memset(buf, 0, sizeof(buf));
+ nlh = mnl_nlmsg_put_header(buf);
+ nlh->nlmsg_type = RTM_NEWLINK;
+ nlh->nlmsg_flags = NLM_F_REQUEST;
+ ifm = mnl_nlmsg_put_extra_header(nlh, sizeof(*ifm));
+ ifm->ifi_family = AF_UNSPEC;
+ ifm->ifi_type = 0;
+ ifm->ifi_index = vtep->ifindex;
+ ifm->ifi_flags = IFF_UP;
+ ifm->ifi_change = IFF_UP;
+ ret = flow_tcf_nl_ack(tcf, nlh, NULL, NULL);
+ if (ret) {
+ rte_flow_error_set(error, -errno,
+ RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
+ "netlink: failed to set VTEP link up");
+ DRV_LOG(WARNING, "netlink: VTEP %s set link up failure (%d)",
+ name, rte_errno);
+ goto clean;
+ }
+ ret = mlx5_flow_tcf_init(tcf, vtep->ifindex, error);
+ if (ret) {
+ DRV_LOG(WARNING, "VTEP %s init failure (%d)", name, rte_errno);
+ goto clean;
+ }
+ DRV_LOG(INFO, "VTEP create (%d, %d)", vtep->port, vtep->ifindex);
+ vtep->refcnt = 1;
+ return vtep;
+clean:
+ flow_tcf_vtep_delete(tcf, vtep);
+ return NULL;
+error:
+ rte_free(vtep);
+ return NULL;
+}
+
+/**
+ * Acquire target interface index for VXLAN tunneling decapsulation.
+ * In order to share the UDP port within the other interfaces the
+ * VXLAN device created as not attached to any interface (if created).
+ *
+ * @param[in] tcf
+ * Context object initialized by mlx5_flow_tcf_context_create().
+ * @param[in] dev_flow
+ * Flow tcf object with tunnel structure pointer set.
+ * @param[out] error
+ * Perform verbose error reporting if not NULL.
+ * @return
+ * Interface descriptor pointer on success,
+ * NULL otherwise and rte_errno is set.
+ */
+static struct tcf_vtep*
+flow_tcf_decap_vtep_acquire(struct mlx5_flow_tcf_context *tcf,
+ struct mlx5_flow *dev_flow,
+ struct rte_flow_error *error)
+{
+ struct tcf_vtep *vtep;
+ uint16_t port = dev_flow->tcf.vxlan_decap->udp_port;
+
+ LIST_FOREACH(vtep, &vtep_list_vxlan, next) {
+ if (vtep->port == port)
+ break;
+ }
+ if (vtep) {
+ /* Device exists, just increment the reference counter. */
+ vtep->refcnt++;
+ assert(vtep->ifindex);
+ return vtep;
+ }
+ /* No decapsulation device exists, try to create the new one. */
+ vtep = flow_tcf_vtep_create(tcf, port, error);
+ if (vtep)
+ LIST_INSERT_HEAD(&vtep_list_vxlan, vtep, next);
+ return vtep;
+}
+
+/**
+ * Acquire target interface index for VXLAN tunneling encapsulation.
+ *
+ * @param[in] tcf
+ * Context object initialized by mlx5_flow_tcf_context_create().
+ * @param[in] ifouter
+ * Network interface index to attach VXLAN encap device to.
+ * @param[in] dev_flow
+ * Flow tcf object with tunnel structure pointer set.
+ * @param[out] error
+ * Perform verbose error reporting if not NULL.
+ * @return
+ * Interface descriptor pointer on success,
+ * NULL otherwise and rte_errno is set.
+ */
+static struct tcf_vtep*
+flow_tcf_encap_vtep_acquire(struct mlx5_flow_tcf_context *tcf,
+ unsigned int ifouter,
+ struct mlx5_flow *dev_flow,
+ struct rte_flow_error *error)
+{
+ static uint16_t port;
+ struct tcf_vtep *vtep;
+ struct tcf_irule *iface;
+ int ret;
+
+ assert(ifouter);
+ /* Look whether the VTEP for specified port is created. */
+ port = rte_be_to_cpu_16(dev_flow->tcf.vxlan_encap->udp.dst);
+ LIST_FOREACH(vtep, &vtep_list_vxlan, next) {
+ if (vtep->port == port)