+
+/**
+ * Enable promiscuous / all multicast mode through Netlink.
+ *
+ * @param dev
+ * Pointer to Ethernet device structure.
+ * @param flags
+ * IFF_PROMISC for promiscuous, IFF_ALLMULTI for allmulti.
+ * @param enable
+ * Nonzero to enable, disable otherwise.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_nl_device_flags(struct rte_eth_dev *dev, uint32_t flags, int enable)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ unsigned int iface_idx = mlx5_ifindex(dev);
+ struct {
+ struct nlmsghdr hdr;
+ struct ifinfomsg ifi;
+ } req = {
+ .hdr = {
+ .nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)),
+ .nlmsg_type = RTM_NEWLINK,
+ .nlmsg_flags = NLM_F_REQUEST,
+ },
+ .ifi = {
+ .ifi_flags = enable ? flags : 0,
+ .ifi_change = flags,
+ .ifi_index = iface_idx,
+ },
+ };
+ int fd;
+ int ret;
+
+ assert(!(flags & ~(IFF_PROMISC | IFF_ALLMULTI)));
+ if (priv->nl_socket_route < 0)
+ return 0;
+ fd = priv->nl_socket_route;
+ ret = mlx5_nl_send(fd, &req.hdr, priv->nl_sn++);
+ if (ret < 0)
+ return ret;
+ return 0;
+}
+
+/**
+ * Enable promiscuous mode through Netlink.
+ *
+ * @param dev
+ * Pointer to Ethernet device structure.
+ * @param enable
+ * Nonzero to enable, disable otherwise.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_nl_promisc(struct rte_eth_dev *dev, int enable)
+{
+ int ret = mlx5_nl_device_flags(dev, IFF_PROMISC, enable);
+
+ if (ret)
+ DRV_LOG(DEBUG,
+ "port %u cannot %s promisc mode: Netlink error %s",
+ dev->data->port_id, enable ? "enable" : "disable",
+ strerror(rte_errno));
+ return ret;
+}
+
+/**
+ * Enable all multicast mode through Netlink.
+ *
+ * @param dev
+ * Pointer to Ethernet device structure.
+ * @param enable
+ * Nonzero to enable, disable otherwise.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_nl_allmulti(struct rte_eth_dev *dev, int enable)
+{
+ int ret = mlx5_nl_device_flags(dev, IFF_ALLMULTI, enable);
+
+ if (ret)
+ DRV_LOG(DEBUG,
+ "port %u cannot %s allmulti mode: Netlink error %s",
+ dev->data->port_id, enable ? "enable" : "disable",
+ strerror(rte_errno));
+ return ret;
+}
+
+/**
+ * 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_cmdget_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;
+ uint32_t portnum = 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;
+ case RDMA_NLDEV_ATTR_PORT_INDEX:
+ portnum = *(uint32_t *)payload;
+ break;
+ default:
+ break;
+ }
+ off += NLA_ALIGN(na->nla_len);
+ }
+ if (found) {
+ data->ibindex = ibindex;
+ data->ifindex = ifindex;
+ data->portnum = portnum;
+ }
+ 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.
+ * @param[in] pindex
+ * IB device port index, starting from 1
+ * @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, uint32_t pindex)
+{
+ 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_cmdget_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_cmdget_cb, &data);
+ if (ret < 0)
+ return 0;
+ if (!data.ifindex)
+ goto error;
+ return data.ifindex;
+error:
+ rte_errno = ENODEV;
+ return 0;
+}
+
+/**
+ * Get the number of physical ports of given IB device.
+ *
+ * @param nl
+ * Netlink socket of the RDMA kind (NETLINK_RDMA).
+ * @param[in] name
+ * IB device name.
+ *
+ * @return
+ * A valid (nonzero) number of ports on success, 0 otherwise
+ * and rte_errno is set.
+ */
+unsigned int
+mlx5_nl_portnum(int nl, const char *name)
+{
+ uint32_t seq = random();
+ struct mlx5_nl_ifindex_data data = {
+ .name = name,
+ .ibindex = 0,
+ .ifindex = 0,
+ .portnum = 0,
+ };
+ struct nlmsghdr req = {
+ .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,
+ };
+ int ret;
+
+ ret = mlx5_nl_send(nl, &req, seq);
+ if (ret < 0)
+ return 0;
+ ret = mlx5_nl_recv(nl, seq, mlx5_nl_cmdget_cb, &data);
+ if (ret < 0)
+ return 0;
+ if (!data.ibindex) {
+ rte_errno = ENODEV;
+ return 0;
+ }
+ if (!data.portnum)
+ rte_errno = EINVAL;
+ return data.portnum;
+}
+
+/**
+ * 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,
+ .name_type = MLX5_PHYS_PORT_NAME_TYPE_NOTSET,
+ .port_name = 0,
+ .switch_id = 0,
+ };
+ size_t off = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+ bool switch_id_set = false;
+ bool num_vf_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);
+ unsigned int i;
+
+ if (ra->rta_len > nh->nlmsg_len - off)
+ goto error;
+ switch (ra->rta_type) {
+ case IFLA_NUM_VF:
+ num_vf_set = true;
+ break;
+ case IFLA_PHYS_PORT_NAME:
+ mlx5_translate_port_name((char *)payload, &info);
+ 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);
+ }
+ if (switch_id_set) {
+ /* We have some E-Switch configuration. */
+ mlx5_nl_check_switch_info(num_vf_set, &info);
+ }
+ assert(!(info.master && info.representor));
+ 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;
+ struct rtattr rta;
+ uint32_t extmask;
+ } req = {
+ .nh = {
+ .nlmsg_len = NLMSG_LENGTH
+ (sizeof(req.info) +
+ RTA_LENGTH(sizeof(uint32_t))),
+ .nlmsg_type = RTM_GETLINK,
+ .nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK,
+ },
+ .info = {
+ .ifi_family = AF_UNSPEC,
+ .ifi_index = ifindex,
+ },
+ .rta = {
+ .rta_type = IFLA_EXT_MASK,
+ .rta_len = RTA_LENGTH(sizeof(int32_t)),
+ },
+ .extmask = RTE_LE32(1),
+ };
+ 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);
+ if (info->master && info->representor) {
+ DRV_LOG(ERR, "ifindex %u device is recognized as master"
+ " and as representor", ifindex);
+ rte_errno = ENODEV;
+ ret = -rte_errno;
+ }
+ return ret;
+}