+/**
+ * Destroy a vdev_netvsc context instance.
+ *
+ * @param ctx
+ * Context to destroy.
+ */
+static void
+vdev_netvsc_ctx_destroy(struct vdev_netvsc_ctx *ctx)
+{
+ if (ctx->pipe[0] != -1)
+ close(ctx->pipe[0]);
+ if (ctx->pipe[1] != -1)
+ close(ctx->pipe[1]);
+ free(ctx);
+}
+
+/**
+ * Determine if a network interface is NetVSC.
+ *
+ * @param[in] iface
+ * Pointer to netdevice description structure (name and index).
+ *
+ * @return
+ * A nonzero value when interface is detected as NetVSC. In case of error,
+ * rte_errno is updated and 0 returned.
+ */
+static int
+vdev_netvsc_iface_is_netvsc(const struct if_nameindex *iface)
+{
+ static const char temp[] = "/sys/class/net/%s/device/class_id";
+ char path[sizeof(temp) + IF_NAMESIZE];
+ FILE *f;
+ int ret;
+ int len = 0;
+
+ ret = snprintf(path, sizeof(path), temp, iface->if_name);
+ if (ret == -1 || (size_t)ret >= sizeof(path)) {
+ rte_errno = ENOBUFS;
+ return 0;
+ }
+ f = fopen(path, "r");
+ if (!f) {
+ rte_errno = errno;
+ return 0;
+ }
+ ret = fscanf(f, NETVSC_CLASS_ID "%n", &len);
+ if (ret == EOF)
+ rte_errno = errno;
+ ret = len == (int)strlen(NETVSC_CLASS_ID);
+ fclose(f);
+ return ret;
+}
+
+/**
+ * Iterate over system network interfaces.
+ *
+ * This function runs a given callback function for each netdevice found on
+ * the system.
+ *
+ * @param func
+ * Callback function pointer. List traversal is aborted when this function
+ * returns a nonzero value.
+ * @param is_netvsc
+ * Indicates the device type to iterate - netvsc or non-netvsc.
+ * @param ...
+ * Variable parameter list passed as @p va_list to @p func.
+ *
+ * @return
+ * 0 when the entire list is traversed successfully, a negative error code
+ * in case or failure, or the nonzero value returned by @p func when list
+ * traversal is aborted.
+ */
+static int
+vdev_netvsc_foreach_iface(int (*func)(const struct if_nameindex *iface,
+ const struct rte_ether_addr *eth_addr,
+ va_list ap), int is_netvsc, ...)
+{
+ struct if_nameindex *iface = if_nameindex();
+ int s = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP);
+ unsigned int i;
+ int ret = 0;
+
+ if (!iface) {
+ ret = -ENOBUFS;
+ DRV_LOG(ERR, "cannot retrieve system network interfaces");
+ goto error;
+ }
+ if (s == -1) {
+ ret = -errno;
+ DRV_LOG(ERR, "cannot open socket: %s", rte_strerror(errno));
+ goto error;
+ }
+ for (i = 0; iface[i].if_name; ++i) {
+ int is_netvsc_ret;
+ struct ifreq req;
+ struct rte_ether_addr eth_addr;
+ va_list ap;
+
+ is_netvsc_ret = vdev_netvsc_iface_is_netvsc(&iface[i]) ? 1 : 0;
+ if (is_netvsc ^ is_netvsc_ret)
+ continue;
+ strlcpy(req.ifr_name, iface[i].if_name, sizeof(req.ifr_name));
+ if (ioctl(s, SIOCGIFHWADDR, &req) == -1) {
+ DRV_LOG(WARNING, "cannot retrieve information about"
+ " interface \"%s\": %s",
+ req.ifr_name, rte_strerror(errno));
+ continue;
+ }
+ if (req.ifr_hwaddr.sa_family != ARPHRD_ETHER)
+ continue;
+ memcpy(eth_addr.addr_bytes, req.ifr_hwaddr.sa_data,
+ RTE_DIM(eth_addr.addr_bytes));
+ va_start(ap, is_netvsc);
+ ret = func(&iface[i], ð_addr, ap);
+ va_end(ap);
+ if (ret)
+ break;
+ }
+error:
+ if (s != -1)
+ close(s);
+ if (iface)
+ if_freenameindex(iface);
+ return ret;
+}
+
+/**
+ * Determine if a network interface has a route.
+ *
+ * @param[in] name
+ * Network device name.
+ * @param[in] family
+ * Address family: AF_INET for IPv4 or AF_INET6 for IPv6.
+ *
+ * @return
+ * 1 when interface has a route, negative errno value in case of error and
+ * 0 otherwise.
+ */
+static int
+vdev_netvsc_has_route(const struct if_nameindex *iface,
+ const unsigned char family)
+{
+ /*
+ * The implementation can be simpler by getifaddrs() function usage but
+ * it works for IPv6 only starting from glibc 2.3.3.
+ */
+ char buf[4096];
+ int len;
+ int ret = 0;
+ int res;
+ int sock;
+ struct nlmsghdr *retmsg = (struct nlmsghdr *)buf;
+ struct sockaddr_nl sa;
+ struct {
+ struct nlmsghdr nlhdr;
+ struct ifaddrmsg addrmsg;
+ } msg;
+
+ if (!iface || (family != AF_INET && family != AF_INET6)) {
+ DRV_LOG(ERR, "%s", rte_strerror(EINVAL));
+ return -EINVAL;
+ }
+ sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+ if (sock == -1) {
+ DRV_LOG(ERR, "cannot open socket: %s", rte_strerror(errno));
+ return -errno;
+ }
+ memset(&sa, 0, sizeof(sa));
+ sa.nl_family = AF_NETLINK;
+ sa.nl_groups = RTMGRP_LINK | RTMGRP_IPV4_IFADDR;
+ res = bind(sock, (struct sockaddr *)&sa, sizeof(sa));
+ if (res == -1) {
+ ret = -errno;
+ DRV_LOG(ERR, "cannot bind socket: %s", rte_strerror(errno));
+ goto close;
+ }
+ memset(&msg, 0, sizeof(msg));
+ msg.nlhdr.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifaddrmsg));
+ msg.nlhdr.nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP;
+ msg.nlhdr.nlmsg_type = RTM_GETADDR;
+ msg.nlhdr.nlmsg_pid = getpid();
+ msg.addrmsg.ifa_family = family;
+ msg.addrmsg.ifa_index = iface->if_index;
+ res = send(sock, &msg, msg.nlhdr.nlmsg_len, 0);
+ if (res == -1) {
+ ret = -errno;
+ DRV_LOG(ERR, "cannot send socket message: %s",
+ rte_strerror(errno));
+ goto close;
+ }
+ memset(buf, 0, sizeof(buf));
+ len = recv(sock, buf, sizeof(buf), 0);
+ if (len == -1) {
+ ret = -errno;
+ DRV_LOG(ERR, "cannot receive socket message: %s",
+ rte_strerror(errno));
+ goto close;
+ }
+ while (NLMSG_OK(retmsg, (unsigned int)len)) {
+ struct ifaddrmsg *retaddr =
+ (struct ifaddrmsg *)NLMSG_DATA(retmsg);
+
+ if (retaddr->ifa_family == family &&
+ retaddr->ifa_index == iface->if_index) {
+ struct rtattr *retrta = IFA_RTA(retaddr);
+ int attlen = IFA_PAYLOAD(retmsg);
+
+ while (RTA_OK(retrta, attlen)) {
+ if (retrta->rta_type == IFA_ADDRESS) {
+ ret = 1;
+ DRV_LOG(DEBUG, "interface %s has IP",
+ iface->if_name);
+ goto close;
+ }
+ retrta = RTA_NEXT(retrta, attlen);
+ }
+ }
+ retmsg = NLMSG_NEXT(retmsg, len);
+ }
+close:
+ close(sock);
+ return ret;
+}
+
+/**
+ * Retrieve network interface data from sysfs symbolic link.
+ *
+ * @param[out] buf
+ * Output data buffer.
+ * @param size
+ * Output buffer size.
+ * @param[in] if_name
+ * Netdevice name.
+ * @param[in] relpath
+ * Symbolic link path relative to netdevice sysfs entry.
+ *
+ * @return
+ * 0 on success, a negative error code otherwise.
+ */
+static int
+vdev_netvsc_sysfs_readlink(char *buf, size_t size, const char *if_name,
+ const char *relpath)
+{
+ struct vdev_netvsc_ctx *ctx;
+ char in[RTE_MAX(sizeof(ctx->yield), 256u)];
+ int ret;
+
+ ret = snprintf(in, sizeof(in), "/sys/class/net/%s/%s",
+ if_name, relpath);
+ if (ret == -1 || (size_t)ret >= sizeof(in))
+ return -ENOBUFS;
+ ret = readlink(in, buf, size);
+ if (ret == -1)
+ return -errno;
+ if ((size_t)ret >= size - 1)
+ return -ENOBUFS;
+ buf[ret] = '\0';
+ return 0;
+}
+
+/**
+ * Probe a network interface to associate with vdev_netvsc context.
+ *
+ * This function determines if the network device matches the properties of
+ * the NetVSC interface associated with the vdev_netvsc context and
+ * communicates its bus address to the fail-safe PMD instance if so.
+ *
+ * It is normally used with vdev_netvsc_foreach_iface().
+ *
+ * @param[in] iface
+ * Pointer to netdevice description structure (name and index).
+ * @param[in] eth_addr
+ * MAC address associated with @p iface.
+ * @param ap
+ * Variable arguments list comprising:
+ *
+ * - struct vdev_netvsc_ctx *ctx:
+ * Context to associate network interface with.
+ *
+ * @return
+ * A nonzero value when interface matches, 0 otherwise or in case of
+ * error.
+ */
+static int
+vdev_netvsc_device_probe(const struct if_nameindex *iface,
+ const struct rte_ether_addr *eth_addr,
+ va_list ap)
+{
+ struct vdev_netvsc_ctx *ctx = va_arg(ap, struct vdev_netvsc_ctx *);
+ char buf[RTE_MAX(sizeof(ctx->yield), 256u)];
+ const char *addr;
+ size_t len;
+ int ret;
+
+ /* Skip non-matching or unwanted NetVSC interfaces. */
+ if (ctx->if_index == iface->if_index) {
+ if (!strcmp(ctx->if_name, iface->if_name))
+ return 0;
+ DRV_LOG(DEBUG,
+ "NetVSC interface \"%s\" (index %u) renamed \"%s\"",
+ ctx->if_name, ctx->if_index, iface->if_name);
+ strlcpy(ctx->if_name, iface->if_name, sizeof(ctx->if_name));
+ return 0;
+ }
+ if (!rte_is_same_ether_addr(eth_addr, &ctx->if_addr))
+ return 0;
+ /* Look for associated PCI device. */
+ ret = vdev_netvsc_sysfs_readlink(buf, sizeof(buf), iface->if_name,
+ "device/subsystem");
+ if (ret)
+ return 0;
+ addr = strrchr(buf, '/');
+ addr = addr ? addr + 1 : buf;
+ if (strcmp(addr, "pci"))
+ return 0;
+ ret = vdev_netvsc_sysfs_readlink(buf, sizeof(buf), iface->if_name,
+ "device");
+ if (ret)
+ return 0;
+ addr = strrchr(buf, '/');
+ addr = addr ? addr + 1 : buf;
+ len = strlen(addr);
+ if (!len)
+ return 0;
+ /* Send PCI device argument to fail-safe PMD instance. */
+ if (strcmp(addr, ctx->yield))
+ DRV_LOG(DEBUG, "associating PCI device \"%s\" with NetVSC"
+ " interface \"%s\" (index %u)", addr, ctx->if_name,
+ ctx->if_index);
+ memmove(buf, addr, len + 1);
+ addr = buf;
+ buf[len] = '\n';
+ ret = write(ctx->pipe[1], addr, len + 1);
+ buf[len] = '\0';
+ if (ret == -1) {
+ if (errno == EINTR || errno == EAGAIN)
+ return 1;
+ DRV_LOG(WARNING, "cannot associate PCI device name \"%s\" with"
+ " interface \"%s\": %s", addr, ctx->if_name,
+ rte_strerror(errno));
+ return 1;
+ }
+ if ((size_t)ret != len + 1) {
+ /*
+ * Attempt to override previous partial write, no need to
+ * recover if that fails.
+ */
+ ret = write(ctx->pipe[1], "\n", 1);
+ (void)ret;
+ return 1;
+ }
+ fsync(ctx->pipe[1]);
+ memcpy(ctx->yield, addr, len + 1);
+ return 1;
+}
+
+/**
+ * Alarm callback that regularly probes system network interfaces.
+ *
+ * This callback runs at a frequency determined by VDEV_NETVSC_PROBE_MS as
+ * long as an vdev_netvsc context instance exists.
+ *
+ * @param arg
+ * Ignored.
+ */
+static void
+vdev_netvsc_alarm(__rte_unused void *arg)
+{
+ struct vdev_netvsc_ctx *ctx;
+ int ret;
+
+ LIST_FOREACH(ctx, &vdev_netvsc_ctx_list, entry) {
+ ret = vdev_netvsc_foreach_iface(vdev_netvsc_device_probe, 0,
+ ctx);
+ if (ret < 0)
+ break;
+ }
+ if (!vdev_netvsc_ctx_count)
+ return;
+ ret = rte_eal_alarm_set(VDEV_NETVSC_PROBE_MS * 1000,
+ vdev_netvsc_alarm, NULL);
+ if (ret < 0) {
+ DRV_LOG(ERR, "unable to reschedule alarm callback: %s",
+ rte_strerror(-ret));
+ }
+}
+
+/**
+ * Probe a NetVSC interface to generate a vdev_netvsc context from.
+ *
+ * This function instantiates vdev_netvsc contexts either for all NetVSC
+ * devices found on the system or only a subset provided as device
+ * arguments.
+ *
+ * It is normally used with vdev_netvsc_foreach_iface().
+ *
+ * @param[in] iface
+ * Pointer to netdevice description structure (name and index).
+ * @param[in] eth_addr
+ * MAC address associated with @p iface.
+ * @param ap
+ * Variable arguments list comprising:
+ *
+ * - const char *name:
+ * Name associated with current driver instance.
+ *
+ * - struct rte_kvargs *kvargs:
+ * Device arguments provided to current driver instance.
+ *
+ * - int force:
+ * Accept specified interface even if not detected as NetVSC.
+ *
+ * - unsigned int specified:
+ * Number of specific netdevices provided as device arguments.
+ *
+ * - unsigned int *matched:
+ * The number of specified netdevices matched by this function.
+ *
+ * @return
+ * A nonzero value when interface matches, 0 otherwise or in case of
+ * error.
+ */
+static int
+vdev_netvsc_netvsc_probe(const struct if_nameindex *iface,
+ const struct rte_ether_addr *eth_addr,
+ va_list ap)
+{
+ const char *name = va_arg(ap, const char *);
+ struct rte_kvargs *kvargs = va_arg(ap, struct rte_kvargs *);
+ unsigned int specified = va_arg(ap, unsigned int);
+ unsigned int *matched = va_arg(ap, unsigned int *);
+ unsigned int i;
+ struct vdev_netvsc_ctx *ctx;
+ int ret;
+
+ /* Probe all interfaces when none are specified. */
+ if (specified) {
+ for (i = 0; i != kvargs->count; ++i) {
+ const struct rte_kvargs_pair *pair = &kvargs->pairs[i];
+
+ if (!strcmp(pair->key, VDEV_NETVSC_ARG_IFACE)) {
+ if (!strcmp(pair->value, iface->if_name))
+ break;
+ } else if (!strcmp(pair->key, VDEV_NETVSC_ARG_MAC)) {
+ struct rte_ether_addr tmp;
+
+ if (sscanf(pair->value,
+ "%" SCNx8 ":%" SCNx8 ":%" SCNx8 ":"
+ "%" SCNx8 ":%" SCNx8 ":%" SCNx8,
+ &tmp.addr_bytes[0],
+ &tmp.addr_bytes[1],
+ &tmp.addr_bytes[2],
+ &tmp.addr_bytes[3],
+ &tmp.addr_bytes[4],
+ &tmp.addr_bytes[5]) != 6) {
+ DRV_LOG(ERR,
+ "invalid MAC address format"
+ " \"%s\"",
+ pair->value);
+ return -EINVAL;
+ }
+ if (rte_is_same_ether_addr(eth_addr, &tmp))
+ break;
+ }
+ }
+ if (i == kvargs->count)
+ return 0;
+ ++(*matched);
+ }
+ /* Weed out interfaces already handled. */
+ LIST_FOREACH(ctx, &vdev_netvsc_ctx_list, entry)
+ if (ctx->if_index == iface->if_index)
+ break;
+ if (ctx) {
+ if (!specified)
+ return 0;
+ DRV_LOG(WARNING,
+ "interface \"%s\" (index %u) is already handled,"
+ " skipping",
+ iface->if_name, iface->if_index);
+ return 0;
+ }
+ /* Routed NetVSC should not be probed. */
+ if (vdev_netvsc_has_route(iface, AF_INET) ||
+ vdev_netvsc_has_route(iface, AF_INET6)) {
+ if (!specified)
+ return 0;
+ DRV_LOG(WARNING, "probably using routed NetVSC interface \"%s\""
+ " (index %u)", iface->if_name, iface->if_index);
+ }
+ /* Create interface context. */
+ ctx = calloc(1, sizeof(*ctx));
+ if (!ctx) {
+ ret = -errno;
+ DRV_LOG(ERR, "cannot allocate context for interface \"%s\": %s",
+ iface->if_name, rte_strerror(errno));
+ goto error;
+ }
+ ctx->id = vdev_netvsc_ctx_count;
+ strlcpy(ctx->if_name, iface->if_name, sizeof(ctx->if_name));
+ ctx->if_index = iface->if_index;
+ ctx->if_addr = *eth_addr;
+ ctx->pipe[0] = -1;
+ ctx->pipe[1] = -1;
+ ctx->yield[0] = '\0';
+ if (pipe(ctx->pipe) == -1) {
+ ret = -errno;
+ DRV_LOG(ERR,
+ "cannot allocate control pipe for interface \"%s\": %s",
+ ctx->if_name, rte_strerror(errno));
+ goto error;
+ }
+ for (i = 0; i != RTE_DIM(ctx->pipe); ++i) {
+ int flf = fcntl(ctx->pipe[i], F_GETFL);
+
+ if (flf != -1 &&
+ fcntl(ctx->pipe[i], F_SETFL, flf | O_NONBLOCK) != -1)
+ continue;
+ ret = -errno;
+ DRV_LOG(ERR, "cannot toggle non-blocking flag on control file"
+ " descriptor #%u (%d): %s", i, ctx->pipe[i],
+ rte_strerror(errno));
+ goto error;
+ }
+ /* Generate virtual device name and arguments. */
+ i = 0;
+ ret = snprintf(ctx->name, sizeof(ctx->name), "%s_id%u",
+ name, ctx->id);
+ if (ret == -1 || (size_t)ret >= sizeof(ctx->name))
+ ++i;
+ ret = snprintf(ctx->devname, sizeof(ctx->devname), "net_failsafe_vsc%u",
+ ctx->id);
+ if (ret == -1 || (size_t)ret >= sizeof(ctx->devname))
+ ++i;
+ ret = snprintf(ctx->devargs, sizeof(ctx->devargs),
+ "fd(%d),dev(net_tap_vsc%u,remote=%s)",
+ ctx->pipe[0], ctx->id, ctx->if_name);
+ if (ret == -1 || (size_t)ret >= sizeof(ctx->devargs))
+ ++i;
+ if (i) {
+ ret = -ENOBUFS;
+ DRV_LOG(ERR, "generated virtual device name or argument list"
+ " too long for interface \"%s\"", ctx->if_name);
+ goto error;
+ }
+ /* Request virtual device generation. */
+ DRV_LOG(DEBUG, "generating virtual device \"%s\" with arguments \"%s\"",
+ ctx->devname, ctx->devargs);
+ vdev_netvsc_foreach_iface(vdev_netvsc_device_probe, 0, ctx);
+ ret = rte_eal_hotplug_add("vdev", ctx->devname, ctx->devargs);
+ if (ret < 0)
+ goto error;
+ LIST_INSERT_HEAD(&vdev_netvsc_ctx_list, ctx, entry);
+ ++vdev_netvsc_ctx_count;
+ DRV_LOG(DEBUG, "added NetVSC interface \"%s\" to context list",
+ ctx->if_name);
+ return 0;
+error:
+ if (ctx)
+ vdev_netvsc_ctx_destroy(ctx);
+ return ret;
+}
+