common/mlx5: add Netlink event helpers

Introduce mlx5_nl_read_events() to read Netlink events
(technically, messages) from a socket that was configured
to listen for them via a new mlx5_nl_init() parameter.
Add mlx5_nl_parse_link_status_update() helper
to extract information from link-related events.
This patch is a shared base for later fixes.

Cc: stable@dpdk.org

Signed-off-by: Dmitry Kozlyuk <dkozlyuk@nvidia.com>
Reviewed-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>

drivers/common/mlx5/linux/mlx5_common_os.c

@@ -590,7 +590,7 @@ mlx5_os_get_ibv_device(const struct rte_pci_addr *addr)
 static int
 mlx5_nl_roce_disable(const char *addr)
 {
-	int nlsk_fd = mlx5_nl_init(NETLINK_GENERIC);
+	int nlsk_fd = mlx5_nl_init(NETLINK_GENERIC, 0);
 	int devlink_id;
 	int enable;
 	int ret;

drivers/common/mlx5/linux/mlx5_nl.c

@@ -185,19 +185,22 @@ uint32_t atomic_sn;
  *
  * @param protocol
  *   Netlink protocol (e.g. NETLINK_ROUTE, NETLINK_RDMA).
+ * @param groups
+ *   Groups to listen (e.g. RTMGRP_LINK), can be 0.
  *
  * @return
  *   A file descriptor on success, a negative errno value otherwise and
  *   rte_errno is set.
  */
 int
-mlx5_nl_init(int protocol)
+mlx5_nl_init(int protocol, int groups)
 {
 	int fd;
 	int buf_size;
 	socklen_t opt_size;
 	struct sockaddr_nl local = {
 		.nl_family = AF_NETLINK,
+		.nl_groups = groups,
 	};
 	int ret;
 
@@ -1862,3 +1865,100 @@ mlx5_nl_enable_roce_set(int nlsk_fd, int family_id, const char *pci_addr,
 	/* Now, need to reload the driver. */
 	return mlx5_nl_driver_reload(nlsk_fd, family_id, pci_addr);
 }
+
+/**
+ * Try to parse a Netlink message as a link status update.
+ *
+ * @param hdr
+ *  Netlink message header.
+ * @param[out] ifindex
+ *  Index of the updated interface.
+ *
+ * @return
+ *  0 on success, negative on failure.
+ */
+int
+mlx5_nl_parse_link_status_update(struct nlmsghdr *hdr, uint32_t *ifindex)
+{
+	struct ifinfomsg *info;
+
+	switch (hdr->nlmsg_type) {
+	case RTM_NEWLINK:
+	case RTM_DELLINK:
+	case RTM_GETLINK:
+	case RTM_SETLINK:
+		info = NLMSG_DATA(hdr);
+		*ifindex = info->ifi_index;
+		return 0;
+	}
+	return -1;
+}
+
+/**
+ * Read pending events from a Netlink socket.
+ *
+ * @param nlsk_fd
+ *  Netlink socket.
+ * @param cb
+ *  Callback invoked for each of the events.
+ * @param cb_arg
+ *  User data for the callback.
+ *
+ * @return
+ *  0 on success, including the case when there are no events.
+ *  Negative on failure and rte_errno is set.
+ */
+int
+mlx5_nl_read_events(int nlsk_fd, mlx5_nl_event_cb *cb, void *cb_arg)
+{
+	char buf[8192];
+	struct sockaddr_nl addr;
+	struct iovec iov = {
+		.iov_base = buf,
+		.iov_len = sizeof(buf),
+	};
+	struct msghdr msg = {
+		.msg_name = &addr,
+		.msg_namelen = sizeof(addr),
+		.msg_iov = &iov,
+		.msg_iovlen = 1,
+	};
+	struct nlmsghdr *hdr;
+	ssize_t size;
+
+	while (1) {
+		size = recvmsg(nlsk_fd, &msg, MSG_DONTWAIT);
+		if (size < 0) {
+			if (errno == EAGAIN)
+				return 0;
+			if (errno == EINTR)
+				continue;
+			DRV_LOG(DEBUG, "Failed to receive netlink message: %s",
+				strerror(errno));
+			rte_errno = errno;
+			return -rte_errno;
+		}
+		hdr = (struct nlmsghdr *)buf;
+		while (size >= (ssize_t)sizeof(*hdr)) {
+			ssize_t msg_len = hdr->nlmsg_len;
+			ssize_t data_len = msg_len - sizeof(*hdr);
+			ssize_t aligned_len;
+
+			if (data_len < 0) {
+				DRV_LOG(DEBUG, "Netlink message too short");
+				rte_errno = EINVAL;
+				return -rte_errno;
+			}
+			aligned_len = NLMSG_ALIGN(msg_len);
+			if (aligned_len > size) {
+				DRV_LOG(DEBUG, "Netlink message too long");
+				rte_errno = EINVAL;
+				return -rte_errno;
+			}
+			cb(hdr, cb_arg);
+			hdr = RTE_PTR_ADD(hdr, aligned_len);
+			size -= aligned_len;
+		}
+	}
+	return 0;
+}

drivers/common/mlx5/linux/mlx5_nl.h

@@ -11,6 +11,7 @@
 
 #include "mlx5_common.h"
 
+typedef void (mlx5_nl_event_cb)(struct nlmsghdr *hdr, void *user_data);
 
 /* VLAN netdev for VLAN workaround. */
 struct mlx5_nl_vlan_dev {
@@ -30,7 +31,7 @@ struct mlx5_nl_vlan_vmwa_context {
 };
 
 __rte_internal
-int mlx5_nl_init(int protocol);
+int mlx5_nl_init(int protocol, int groups);
 __rte_internal
 int mlx5_nl_mac_addr_add(int nlsk_fd, unsigned int iface_idx, uint64_t *mac_own,
 			 struct rte_ether_addr *mac, uint32_t index);
@@ -75,4 +76,9 @@ int mlx5_nl_enable_roce_get(int nlsk_fd, int family_id, const char *pci_addr,
 int mlx5_nl_enable_roce_set(int nlsk_fd, int family_id, const char *pci_addr,
 			    int enable);
 
+__rte_internal
+int mlx5_nl_read_events(int nlsk_fd, mlx5_nl_event_cb *cb, void *cb_arg);
+__rte_internal
+int mlx5_nl_parse_link_status_update(struct nlmsghdr *hdr, uint32_t *ifindex);
+
 #endif /* RTE_PMD_MLX5_NL_H_ */

drivers/common/mlx5/version.map

@@ -127,9 +127,11 @@ INTERNAL {
 	mlx5_nl_mac_addr_flush; # WINDOWS_NO_EXPORT
 	mlx5_nl_mac_addr_remove; # WINDOWS_NO_EXPORT
 	mlx5_nl_mac_addr_sync; # WINDOWS_NO_EXPORT
+	mlx5_nl_parse_link_status_update; # WINDOWS_NO_EXPORT
 	mlx5_nl_port_state; # WINDOWS_NO_EXPORT
 	mlx5_nl_portnum; # WINDOWS_NO_EXPORT
 	mlx5_nl_promisc; # WINDOWS_NO_EXPORT
+	mlx5_nl_read_events; # WINDOWS_NO_EXPORT
 	mlx5_nl_switch_info; # WINDOWS_NO_EXPORT
 	mlx5_nl_vf_mac_addr_modify; # WINDOWS_NO_EXPORT
 	mlx5_nl_vlan_vmwa_create; # WINDOWS_NO_EXPORT

drivers/net/mlx5/linux/mlx5_os.c

@@ -1117,7 +1117,7 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 	sh = mlx5_alloc_shared_dev_ctx(spawn, mkvlist);
 	if (!sh)
 		return NULL;
-	nl_rdma = mlx5_nl_init(NETLINK_RDMA);
+	nl_rdma = mlx5_nl_init(NETLINK_RDMA, 0);
 	/* Check port status. */
 	if (spawn->phys_port <= UINT8_MAX) {
 		/* Legacy Verbs api only support u8 port number. */
@@ -1180,7 +1180,7 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 	priv->mtu = RTE_ETHER_MTU;
 	/* Some internal functions rely on Netlink sockets, open them now. */
 	priv->nl_socket_rdma = nl_rdma;
-	priv->nl_socket_route =	mlx5_nl_init(NETLINK_ROUTE);
+	priv->nl_socket_route =	mlx5_nl_init(NETLINK_ROUTE, 0);
 	priv->representor = !!switch_info->representor;
 	priv->master = !!switch_info->master;
 	priv->domain_id = RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID;
@@ -1927,8 +1927,8 @@ mlx5_os_pci_probe_pf(struct mlx5_common_device *cdev,
 	 * matching ones, gathering into the list.
 	 */
 	struct ibv_device *ibv_match[ret + 1];
-	int nl_route = mlx5_nl_init(NETLINK_ROUTE);
-	int nl_rdma = mlx5_nl_init(NETLINK_RDMA);
+	int nl_route = mlx5_nl_init(NETLINK_ROUTE, 0);
+	int nl_rdma = mlx5_nl_init(NETLINK_RDMA, 0);
 	unsigned int i;
 
 	while (ret-- > 0) {

drivers/net/mlx5/linux/mlx5_vlan_os.c

@@ -135,7 +135,7 @@ mlx5_vlan_vmwa_init(struct rte_eth_dev *dev, uint32_t ifindex)
 		return NULL;
 	}
 	rte_spinlock_init(&vmwa->sl);
-	vmwa->nl_socket = mlx5_nl_init(NETLINK_ROUTE);
+	vmwa->nl_socket = mlx5_nl_init(NETLINK_ROUTE, 0);
 	if (vmwa->nl_socket < 0) {
 		DRV_LOG(WARNING,
 			"Can not create Netlink socket"