[PATCH v2 1/4] shared/net-util-linux: add support for retrieving egress netdev

[Nilay Shroff <nilay@linux.ibm.com>]

Add a new shared helper, shr_route_get_egress_iface(), which performs
a route lookup and retrieves the egress netdev for a given destination
IPv4/IPv6 address and, optionally, source IPv4/IPv6 address.

Use netlink to perform the route lookup.

This is a preparatory patch. A subsequent patch will use this helper
to determine the egress netdev when calculating the default
--nr-io-queues value for NVMe/TCP connections.

Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
---
 shared/net-util-linux.c | 228 ++++++++++++++++++++++++++++++++++++++++
 shared/net-util.h       |  16 +++
 2 files changed, 244 insertions(+)

diff --git a/shared/net-util-linux.c b/shared/net-util-linux.c
index 57c025b05..b44430f38 100644
--- a/shared/net-util-linux.c
+++ b/shared/net-util-linux.c
@@ -7,15 +7,23 @@
  */
 
 #include <arpa/inet.h>
+#include <asm/types.h>
 #include <errno.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
 #include <net/if.h>
 #include <netinet/in.h>
+#include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <sys/socket.h>
+#include <unistd.h>
 
 #include "net-util.h"
 
+#define NETLINK_BUFFER_SIZE	4096
+#define NETLINK_SEQ_NUM	1
+
 /*
  * Parse @addr (IPv4, or IPv6 with an optional "%scope" suffix on a
  * link-local address) into @ss. @addr is never a hostname -- resolving one
@@ -181,3 +189,223 @@ bool shr_iface_primary_addr_matches(const struct ifaddrs *iface_list,
 
 	return match_found;
 }
+
+static int rtattr_append(struct nlmsghdr *nlh, char *buf, size_t buflen,
+		unsigned short type, void *attrval, int attrlen)
+{
+	struct rtattr *rta;
+	int nlen = NLMSG_ALIGN(nlh->nlmsg_len);
+	int rlen = RTA_LENGTH(attrlen);
+
+	if (nlen + rlen >= buflen)
+		return -ENOSPC;
+
+	rta = (struct rtattr *)(buf + nlen);
+	rta->rta_type = type;
+	rta->rta_len = rlen;
+	memcpy(RTA_DATA(rta), attrval, attrlen);
+
+	nlh->nlmsg_len = nlen + rlen;
+
+	return 0;
+}
+
+int shr_route_get_egress_iface(const char *saddr, const char *daddr,
+		char *ifname, size_t iflen)
+{
+	struct sockaddr_nl nl = {.nl_family = AF_NETLINK};
+	struct sockaddr_storage ss_src, ss_dst;
+	char buf[NETLINK_BUFFER_SIZE] = {};
+	struct sockaddr_in6 *src6, *dst6;
+	struct sockaddr_in *src, *dst;
+	struct msghdr msg = {};
+	struct nlmsghdr *nlh;
+	struct rtmsg *rtmsg;
+	struct rtattr *rta;
+	int nlen, attrlen;
+	struct iovec iov;
+	int fd, ret = 0;
+
+	if (!daddr)
+		return -EINVAL;
+
+	ret = parse_numeric_addr(daddr, &ss_dst);
+	if (ret < 0) {
+		fprintf(stderr, "Invalid dest address\n");
+		return ret;
+	}
+
+	if (saddr) {
+		ret = parse_numeric_addr(saddr, &ss_src);
+		if (ret < 0) {
+			fprintf(stderr, "Invalid src address\n");
+			return ret;
+		}
+
+		if (ss_src.ss_family != ss_dst.ss_family) {
+			fprintf(stderr, "src/dst address family doesn't match\n");
+			return -EINVAL;
+		}
+	}
+
+	if (iflen < IF_NAMESIZE) {
+		fprintf(stderr, "Invalid ifname length\n");
+		return -EINVAL;
+	}
+
+	fd = socket(AF_NETLINK, SOCK_DGRAM, NETLINK_ROUTE);
+	if (fd < 0) {
+		fprintf(stderr, "Opening netlink socket failed\n");
+		return -errno;
+	}
+
+	/* encode nlmsghdr */
+	nlh = (struct nlmsghdr *)buf;
+
+	nlh->nlmsg_type = RTM_GETROUTE;
+	nlh->nlmsg_flags = NLM_F_REQUEST;
+	nlh->nlmsg_pid = 0; /* to kernel */
+	nlh->nlmsg_seq = NETLINK_SEQ_NUM;
+	nlh->nlmsg_len = sizeof(struct nlmsghdr);
+
+	/* append rtmsg */
+	nlh->nlmsg_len = NLMSG_ALIGN(nlh->nlmsg_len);
+
+	rtmsg = (struct rtmsg *)(buf + nlh->nlmsg_len);
+	rtmsg->rtm_family = ss_dst.ss_family;
+	rtmsg->rtm_dst_len = (ss_dst.ss_family == AF_INET) ? 32 : 128;
+
+	nlh->nlmsg_len += sizeof(struct rtmsg);
+
+	/* append attribute RTA_DST */
+	if (ss_dst.ss_family == AF_INET) {
+		dst = (struct sockaddr_in *)&ss_dst;
+
+		ret = rtattr_append(nlh, buf, sizeof(buf), RTA_DST,
+				&dst->sin_addr, sizeof(struct in_addr));
+		if (ret)
+			goto out;
+	} else {
+		dst6 = (struct sockaddr_in6 *)&ss_dst;
+
+		ret = rtattr_append(nlh, buf, sizeof(buf), RTA_DST,
+				&dst6->sin6_addr, sizeof(struct in6_addr));
+		if (ret)
+			goto out;
+	}
+
+	if (saddr) {
+		/* append attribute RTA_SRC */
+		if (ss_src.ss_family == AF_INET) {
+			src = (struct sockaddr_in *)&ss_src;
+
+			ret = rtattr_append(nlh, buf, sizeof(buf), RTA_SRC,
+				&src->sin_addr, sizeof(struct in_addr));
+			if (ret)
+				goto out;
+		} else {
+			src6 = (struct sockaddr_in6 *)&ss_src;
+
+			ret = rtattr_append(nlh, buf, sizeof(buf), RTA_SRC,
+				&src6->sin6_addr, sizeof(struct in6_addr));
+			if (ret)
+				goto out;
+		}
+	}
+
+	/* construct sendmsg and send to kernel */
+	iov.iov_base = buf;
+	iov.iov_len = nlh->nlmsg_len;
+
+	msg.msg_iov = &iov;
+	msg.msg_iovlen = 1;
+	msg.msg_name = &nl;
+	msg.msg_namelen = sizeof(nl);
+
+	if (sendmsg(fd, &msg, 0) < 0) {
+		fprintf(stderr, "Sendmsg to kernel failed\n");
+		ret = -errno;
+		goto out;
+	}
+
+	/* construct recvmsg buffer and wait for the response from kernel */
+	memset(&msg, 0, sizeof(msg));
+	memset(buf, 0, sizeof(buf));
+
+	iov.iov_base = buf;
+	iov.iov_len = sizeof(buf);
+
+	msg.msg_iov = &iov;
+	msg.msg_iovlen = 1;
+	msg.msg_name = &nl;
+	msg.msg_namelen = sizeof(nl);
+
+	nlen = recvmsg(fd, &msg, 0);
+	if (nlen < 0) {
+		fprintf(stderr, "Recvmsg from kernel failed\n");
+		ret = -errno;
+		goto out;
+	}
+	close(fd);
+
+	nlh = msg.msg_iov->iov_base;
+
+	for (; NLMSG_OK(nlh, nlen); nlh = NLMSG_NEXT(nlh, nlen)) {
+
+		if (nlh->nlmsg_type == NLMSG_ERROR) {
+			struct nlmsgerr *err = NLMSG_DATA(nlh);
+
+			/*
+			 * Netlink error message is sent as an ack when user
+			 * explicitly requested for it and in which case
+			 * err->error is set to zero.
+			 */
+			if (!err->error)
+				continue;
+
+			fprintf(stderr, "Received nlmsg error: %s\n",
+					strerror(-err->error));
+			break;
+		}
+
+		if (nlh->nlmsg_type == NLMSG_DONE)
+			break;
+
+		/*
+		 * RTM_GETROUTE reply is expected to be of type RTM_NEWROUTE.
+		 */
+		if (nlh->nlmsg_type != RTM_NEWROUTE)
+			continue;
+
+		if (nlh->nlmsg_seq != NETLINK_SEQ_NUM)
+			continue;
+
+		/* parse and decode received netlink message */
+		rtmsg = NLMSG_DATA(nlh);
+		rta = RTM_RTA(rtmsg);
+		attrlen = RTM_PAYLOAD(nlh);
+
+		for (; RTA_OK(rta, attrlen); rta = RTA_NEXT(rta, attrlen)) {
+
+			switch (rta->rta_type) {
+			case RTA_OIF: {
+				int ifindex;
+
+				ifindex = *((int *)RTA_DATA(rta));
+				if (!if_indextoname(ifindex, ifname)) {
+					fprintf(stderr, "if_indextoname failed\n");
+					ret = -errno;
+				}
+				return ret;
+			}
+			default:
+				break;
+			}
+		}
+	}
+
+	return -ENOENT;
+out:
+	close(fd);
+	return ret;
+}
diff --git a/shared/net-util.h b/shared/net-util.h
index 577e582f6..0208923e5 100644
--- a/shared/net-util.h
+++ b/shared/net-util.h
@@ -48,3 +48,19 @@ const char *shr_iface_matching_addr(const struct ifaddrs *iface_list,
  */
 bool shr_iface_primary_addr_matches(const struct ifaddrs *iface_list,
 		const char *iface, const char *addr);
+
+/*
+ * shr_route_get_egress_iface - Lookup route table and find egress inerface
+ *
+ * @saddr: optional source address
+ * @daddr: destintion address
+ * @ifname: buffer to hold the matching iface name
+ * @iflen: length of ifname buffer (must be greater or equal to IF_NAMESIZE)
+ *
+ * Lookup route table using specified saddr and daddr and find the egress
+ * interface. The saddr is optional however daddr is mandatory.
+ *
+ * Return: 0 on success and negative errno on failure.
+ */
+int shr_route_get_egress_iface(const char *saddr, const char *daddr,
+		char *ifname, size_t iflen);
-- 
2.53.0