+
+/**
+ * Process network interface information from Netlink message.
+ *
+ * @param nh
+ * Pointer to Netlink message header.
+ * @param arg
+ * Opaque data pointer for this callback.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_nl_ifindex_cb(struct nlmsghdr *nh, void *arg)
+{
+ struct mlx5_nl_ifindex_data *data = arg;
+ size_t off = NLMSG_HDRLEN;
+ uint32_t ibindex = 0;
+ uint32_t ifindex = 0;
+ int found = 0;
+
+ if (nh->nlmsg_type !=
+ RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET) &&
+ nh->nlmsg_type !=
+ RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_PORT_GET))
+ goto error;
+ while (off < nh->nlmsg_len) {
+ struct nlattr *na = (void *)((uintptr_t)nh + off);
+ void *payload = (void *)((uintptr_t)na + NLA_HDRLEN);
+
+ if (na->nla_len > nh->nlmsg_len - off)
+ goto error;
+ switch (na->nla_type) {
+ case RDMA_NLDEV_ATTR_DEV_INDEX:
+ ibindex = *(uint32_t *)payload;
+ break;
+ case RDMA_NLDEV_ATTR_DEV_NAME:
+ if (!strcmp(payload, data->name))
+ found = 1;
+ break;
+ case RDMA_NLDEV_ATTR_NDEV_INDEX:
+ ifindex = *(uint32_t *)payload;
+ break;
+ default:
+ break;
+ }
+ off += NLA_ALIGN(na->nla_len);
+ }
+ if (found) {
+ data->ibindex = ibindex;
+ data->ifindex = ifindex;
+ }
+ return 0;
+error:
+ rte_errno = EINVAL;
+ return -rte_errno;
+}
+
+/**
+ * Get index of network interface associated with some IB device.
+ *
+ * This is the only somewhat safe method to avoid resorting to heuristics
+ * when faced with port representors. Unfortunately it requires at least
+ * Linux 4.17.
+ *
+ * @param nl
+ * Netlink socket of the RDMA kind (NETLINK_RDMA).
+ * @param[in] name
+ * IB device name.
+ *
+ * @return
+ * A valid (nonzero) interface index on success, 0 otherwise and rte_errno
+ * is set.
+ */
+unsigned int
+mlx5_nl_ifindex(int nl, const char *name)
+{
+ static const uint32_t pindex = 1;
+ uint32_t seq = random();
+ struct mlx5_nl_ifindex_data data = {
+ .name = name,
+ .ibindex = 0, /* Determined during first pass. */
+ .ifindex = 0, /* Determined during second pass. */
+ };
+ union {
+ struct nlmsghdr nh;
+ uint8_t buf[NLMSG_HDRLEN +
+ NLA_HDRLEN + NLA_ALIGN(sizeof(data.ibindex)) +
+ NLA_HDRLEN + NLA_ALIGN(sizeof(pindex))];
+ } req = {
+ .nh = {
+ .nlmsg_len = NLMSG_LENGTH(0),
+ .nlmsg_type = RDMA_NL_GET_TYPE(RDMA_NL_NLDEV,
+ RDMA_NLDEV_CMD_GET),
+ .nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | NLM_F_DUMP,
+ },
+ };
+ struct nlattr *na;
+ int ret;
+
+ ret = mlx5_nl_send(nl, &req.nh, seq);
+ if (ret < 0)
+ return 0;
+ ret = mlx5_nl_recv(nl, seq, mlx5_nl_ifindex_cb, &data);
+ if (ret < 0)
+ return 0;
+ if (!data.ibindex)
+ goto error;
+ ++seq;
+ req.nh.nlmsg_type = RDMA_NL_GET_TYPE(RDMA_NL_NLDEV,
+ RDMA_NLDEV_CMD_PORT_GET);
+ req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+ req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(req.buf) - NLMSG_HDRLEN);
+ na = (void *)((uintptr_t)req.buf + NLMSG_HDRLEN);
+ na->nla_len = NLA_HDRLEN + sizeof(data.ibindex);
+ na->nla_type = RDMA_NLDEV_ATTR_DEV_INDEX;
+ memcpy((void *)((uintptr_t)na + NLA_HDRLEN),
+ &data.ibindex, sizeof(data.ibindex));
+ na = (void *)((uintptr_t)na + NLA_ALIGN(na->nla_len));
+ na->nla_len = NLA_HDRLEN + sizeof(pindex);
+ na->nla_type = RDMA_NLDEV_ATTR_PORT_INDEX;
+ memcpy((void *)((uintptr_t)na + NLA_HDRLEN),
+ &pindex, sizeof(pindex));
+ ret = mlx5_nl_send(nl, &req.nh, seq);
+ if (ret < 0)
+ return 0;
+ ret = mlx5_nl_recv(nl, seq, mlx5_nl_ifindex_cb, &data);
+ if (ret < 0)
+ return 0;
+ if (!data.ifindex)
+ goto error;
+ return data.ifindex;
+error:
+ rte_errno = ENODEV;
+ return 0;
+}
+
+/**
+ * Process switch information from Netlink message.
+ *
+ * @param nh
+ * Pointer to Netlink message header.
+ * @param arg
+ * Opaque data pointer for this callback.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_nl_switch_info_cb(struct nlmsghdr *nh, void *arg)
+{
+ struct mlx5_switch_info info = {
+ .master = 0,
+ .representor = 0,
+ .port_name = 0,
+ .switch_id = 0,
+ };
+ size_t off = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+ bool port_name_set = false;
+ bool switch_id_set = false;
+
+ if (nh->nlmsg_type != RTM_NEWLINK)
+ goto error;
+ while (off < nh->nlmsg_len) {
+ struct rtattr *ra = (void *)((uintptr_t)nh + off);
+ void *payload = RTA_DATA(ra);
+ char *end;
+ unsigned int i;
+
+ if (ra->rta_len > nh->nlmsg_len - off)
+ goto error;
+ switch (ra->rta_type) {
+ case IFLA_PHYS_PORT_NAME:
+ errno = 0;
+ info.port_name = strtol(payload, &end, 0);
+ if (errno ||
+ (size_t)(end - (char *)payload) != strlen(payload))
+ goto error;
+ port_name_set = true;
+ break;
+ case IFLA_PHYS_SWITCH_ID:
+ info.switch_id = 0;
+ for (i = 0; i < RTA_PAYLOAD(ra); ++i) {
+ info.switch_id <<= 8;
+ info.switch_id |= ((uint8_t *)payload)[i];
+ }
+ switch_id_set = true;
+ break;
+ }
+ off += RTA_ALIGN(ra->rta_len);
+ }
+ info.master = switch_id_set && !port_name_set;
+ info.representor = switch_id_set && port_name_set;
+ memcpy(arg, &info, sizeof(info));
+ return 0;
+error:
+ rte_errno = EINVAL;
+ return -rte_errno;
+}
+
+/**
+ * Get switch information associated with network interface.
+ *
+ * @param nl
+ * Netlink socket of the ROUTE kind (NETLINK_ROUTE).
+ * @param ifindex
+ * Network interface index.
+ * @param[out] info
+ * Switch information object, populated in case of success.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_nl_switch_info(int nl, unsigned int ifindex, struct mlx5_switch_info *info)
+{
+ uint32_t seq = random();
+ struct {
+ struct nlmsghdr nh;
+ struct ifinfomsg info;
+ } req = {
+ .nh = {
+ .nlmsg_len = NLMSG_LENGTH(sizeof(req.info)),
+ .nlmsg_type = RTM_GETLINK,
+ .nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK,
+ },
+ .info = {
+ .ifi_family = AF_UNSPEC,
+ .ifi_index = ifindex,
+ },
+ };
+ int ret;
+
+ ret = mlx5_nl_send(nl, &req.nh, seq);
+ if (ret >= 0)
+ ret = mlx5_nl_recv(nl, seq, mlx5_nl_switch_info_cb, info);
+ return ret;
+}