[PATCH net-next v3 1/3] ipv4: support sport, dport and ip_proto in RTM_GETROUTE

[Roopa Prabhu <roopa@cumulusnetworks.com>]

From: Roopa Prabhu <roopa@cumulusnetworks.com>

This is a followup to fib rules sport, dport and ipproto
match support. Only supports tcp, udp and icmp for ipproto.
Used by fib rule self tests. Before this patch getroute used
same skb to pass through the route lookup and for the netlink
getroute reply msg. This patch allocates separate skb's to keep
flow dissector happy.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
---
 include/net/ip.h               |   3 +
 include/uapi/linux/rtnetlink.h |   3 +
 net/ipv4/Makefile              |   2 +-
 net/ipv4/fib_frontend.c        |   4 +
 net/ipv4/netlink.c             |  23 +++++
 net/ipv4/route.c               | 190 ++++++++++++++++++++++++++++++-----------
 6 files changed, 173 insertions(+), 52 deletions(-)
 create mode 100644 net/ipv4/netlink.c

diff --git a/include/net/ip.h b/include/net/ip.h
index bada1f1..0d2281b 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -664,4 +664,7 @@ extern int sysctl_icmp_msgs_burst;
 int ip_misc_proc_init(void);
 #endif
 
+int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto,
+				struct netlink_ext_ack *extack);
+
 #endif	/* _IP_H */
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 9b15005..cabb210 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -327,6 +327,9 @@ enum rtattr_type_t {
 	RTA_PAD,
 	RTA_UID,
 	RTA_TTL_PROPAGATE,
+	RTA_IP_PROTO,
+	RTA_SPORT,
+	RTA_DPORT,
 	__RTA_MAX
 };
 
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index b379520..13f2ba9 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -14,7 +14,7 @@ obj-y     := route.o inetpeer.o protocol.o \
 	     udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \
 	     fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \
 	     inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o \
-	     metrics.o
+	     metrics.o netlink.o
 
 obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
 obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index f05afaf..d7092c5 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -643,6 +643,10 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = {
 	[RTA_ENCAP]		= { .type = NLA_NESTED },
 	[RTA_UID]		= { .type = NLA_U32 },
 	[RTA_MARK]		= { .type = NLA_U32 },
+	[RTA_TABLE]		= { .type = NLA_U32 },
+	[RTA_IP_PROTO]		= { .type = NLA_U8 },
+	[RTA_SPORT]		= { .type = NLA_U16 },
+	[RTA_DPORT]		= { .type = NLA_U16 },
 };
 
 static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
diff --git a/net/ipv4/netlink.c b/net/ipv4/netlink.c
new file mode 100644
index 0000000..f86bb4f
--- /dev/null
+++ b/net/ipv4/netlink.c
@@ -0,0 +1,23 @@
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <linux/types.h>
+#include <net/net_namespace.h>
+#include <net/netlink.h>
+#include <net/ip.h>
+
+int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto,
+				struct netlink_ext_ack *extack)
+{
+	*ip_proto = nla_get_u8(attr);
+
+	switch (*ip_proto) {
+	case IPPROTO_TCP:
+	case IPPROTO_UDP:
+	case IPPROTO_ICMP:
+		return 0;
+	default:
+		NL_SET_ERR_MSG(extack, "Unsupported ip proto");
+		return -EOPNOTSUPP;
+	}
+}
+EXPORT_SYMBOL_GPL(rtm_getroute_parse_ip_proto);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 29268ef..073c849 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2569,11 +2569,10 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
 EXPORT_SYMBOL_GPL(ip_route_output_flow);
 
 /* called with rcu_read_lock held */
-static int rt_fill_info(struct net *net,  __be32 dst, __be32 src, u32 table_id,
-			struct flowi4 *fl4, struct sk_buff *skb, u32 portid,
-			u32 seq)
+static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
+			struct rtable *rt, u32 table_id, struct flowi4 *fl4,
+			struct sk_buff *skb, u32 portid, u32 seq)
 {
-	struct rtable *rt = skb_rtable(skb);
 	struct rtmsg *r;
 	struct nlmsghdr *nlh;
 	unsigned long expires = 0;
@@ -2669,7 +2668,7 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src, u32 table_id,
 			}
 		} else
 #endif
-			if (nla_put_u32(skb, RTA_IIF, skb->dev->ifindex))
+			if (nla_put_u32(skb, RTA_IIF, fl4->flowi4_iif))
 				goto nla_put_failure;
 	}
 
@@ -2684,43 +2683,128 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src, u32 table_id,
 	return -EMSGSIZE;
 }
 
+static int inet_rtm_getroute_reply(struct sk_buff *in_skb, struct nlmsghdr *nlh,
+				   __be32 dst, __be32 src, struct flowi4 *fl4,
+				   struct rtable *rt, struct fib_result *res)
+{
+	struct net *net = sock_net(in_skb->sk);
+	struct rtmsg *rtm = nlmsg_data(nlh);
+	u32 table_id = RT_TABLE_MAIN;
+	struct sk_buff *skb;
+	int err = 0;
+
+	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+	if (!skb)
+		return -ENOMEM;
+
+	if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE)
+		table_id = res->table ? res->table->tb_id : 0;
+
+	if (rtm->rtm_flags & RTM_F_FIB_MATCH)
+		err = fib_dump_info(skb, NETLINK_CB(in_skb).portid,
+				    nlh->nlmsg_seq, RTM_NEWROUTE, table_id,
+				    rt->rt_type, res->prefix, res->prefixlen,
+				    fl4->flowi4_tos, res->fi, 0);
+	else
+		err = rt_fill_info(net, dst, src, rt, table_id,
+				   fl4, skb, NETLINK_CB(in_skb).portid,
+				   nlh->nlmsg_seq);
+	if (err < 0)
+		goto errout;
+
+	return rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
+
+errout:
+	kfree_skb(skb);
+	return err;
+}
+
+static struct sk_buff *inet_rtm_getroute_build_skb(__be32 src, __be32 dst,
+						   u8 ip_proto, __be16 sport,
+						   __be16 dport)
+{
+	struct sk_buff *skb;
+	struct iphdr *iph;
+
+	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!skb)
+		return NULL;
+
+	/* Reserve room for dummy headers, this skb can pass
+	 * through good chunk of routing engine.
+	 */
+	skb_reset_mac_header(skb);
+	skb_reset_network_header(skb);
+	skb->protocol = htons(ETH_P_IP);
+	iph = skb_put(skb, sizeof(struct iphdr));
+	iph->protocol = ip_proto;
+	iph->saddr = src;
+	iph->daddr = dst;
+	iph->version = 0x4;
+	iph->frag_off = 0;
+	iph->ihl = 0x5;
+	skb_set_transport_header(skb, skb->len);
+
+	switch (iph->protocol) {
+	case IPPROTO_UDP: {
+		struct udphdr *udph;
+
+		udph = skb_put_zero(skb, sizeof(struct udphdr));
+		udph->source = sport;
+		udph->dest = dport;
+		udph->len = sizeof(struct udphdr);
+		udph->check = 0;
+		break;
+	}
+	case IPPROTO_TCP: {
+		struct tcphdr *tcph;
+
+		tcph = skb_put_zero(skb, sizeof(struct tcphdr));
+		tcph->source	= sport;
+		tcph->dest	= dport;
+		tcph->doff	= sizeof(struct tcphdr) / 4;
+		tcph->rst = 1;
+		tcph->check = ~tcp_v4_check(sizeof(struct tcphdr),
+					    src, dst, 0);
+		break;
+	}
+	case IPPROTO_ICMP: {
+		struct icmphdr *icmph;
+
+		icmph = skb_put_zero(skb, sizeof(struct icmphdr));
+		icmph->type = ICMP_ECHO;
+		icmph->code = 0;
+	}
+	}
+
+	return skb;
+}
+
 static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 			     struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(in_skb->sk);
-	struct rtmsg *rtm;
 	struct nlattr *tb[RTA_MAX+1];
+	__be16 sport = 0, dport = 0;
 	struct fib_result res = {};
+	u8 ip_proto = IPPROTO_UDP;
 	struct rtable *rt = NULL;
+	struct sk_buff *skb;
+	struct rtmsg *rtm;
 	struct flowi4 fl4;
 	__be32 dst = 0;
 	__be32 src = 0;
+	kuid_t uid;
 	u32 iif;
 	int err;
 	int mark;
-	struct sk_buff *skb;
-	u32 table_id = RT_TABLE_MAIN;
-	kuid_t uid;
 
 	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy,
 			  extack);
 	if (err < 0)
-		goto errout;
+		return err;
 
 	rtm = nlmsg_data(nlh);
-
-	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
-	if (!skb) {
-		err = -ENOBUFS;
-		goto errout;
-	}
-
-	/* Reserve room for dummy headers, this skb can pass
-	   through good chunk of routing engine.
-	 */
-	skb_reset_mac_header(skb);
-	skb_reset_network_header(skb);
-
 	src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0;
 	dst = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0;
 	iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0;
@@ -2730,14 +2814,23 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	else
 		uid = (iif ? INVALID_UID : current_uid());
 
-	/* Bugfix: need to give ip_route_input enough of an IP header to
-	 * not gag.
-	 */
-	ip_hdr(skb)->protocol = IPPROTO_UDP;
-	ip_hdr(skb)->saddr = src;
-	ip_hdr(skb)->daddr = dst;
+	if (tb[RTA_IP_PROTO]) {
+		err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO],
+						  &ip_proto, extack);
+		if (err)
+			return err;
+	}
+
+	if (tb[RTA_SPORT])
+		sport = nla_get_be16(tb[RTA_SPORT]);
 
-	skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr));
+	if (tb[RTA_DPORT])
+		dport = nla_get_be16(tb[RTA_DPORT]);
+
+
+	skb = inet_rtm_getroute_build_skb(src, dst, ip_proto, sport, dport);
+	if (!skb)
+		return -ENOBUFS;
 
 	memset(&fl4, 0, sizeof(fl4));
 	fl4.daddr = dst;
@@ -2746,6 +2839,11 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0;
 	fl4.flowi4_mark = mark;
 	fl4.flowi4_uid = uid;
+	if (sport)
+		fl4.fl4_sport = sport;
+	if (dport)
+		fl4.fl4_dport = dport;
+	fl4.flowi4_proto = ip_proto;
 
 	rcu_read_lock();
 
@@ -2755,10 +2853,10 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		dev = dev_get_by_index_rcu(net, iif);
 		if (!dev) {
 			err = -ENODEV;
-			goto errout_free;
+			goto errout_rcu;
 		}
 
-		skb->protocol	= htons(ETH_P_IP);
+		fl4.flowi4_iif = iif; /* for rt_fill_info */
 		skb->dev	= dev;
 		skb->mark	= mark;
 		err = ip_route_input_rcu(skb, dst, src, rtm->rtm_tos,
@@ -2778,42 +2876,32 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	}
 
 	if (err)
-		goto errout_free;
+		goto errout_rcu;
 
 	if (rtm->rtm_flags & RTM_F_NOTIFY)
 		rt->rt_flags |= RTCF_NOTIFY;
 
-	if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE)
-		table_id = res.table ? res.table->tb_id : 0;
-
 	if (rtm->rtm_flags & RTM_F_FIB_MATCH) {
 		if (!res.fi) {
 			err = fib_props[res.type].error;
 			if (!err)
 				err = -EHOSTUNREACH;
-			goto errout_free;
+			goto errout_rcu;
 		}
-		err = fib_dump_info(skb, NETLINK_CB(in_skb).portid,
-				    nlh->nlmsg_seq, RTM_NEWROUTE, table_id,
-				    rt->rt_type, res.prefix, res.prefixlen,
-				    fl4.flowi4_tos, res.fi, 0);
-	} else {
-		err = rt_fill_info(net, dst, src, table_id, &fl4, skb,
-				   NETLINK_CB(in_skb).portid, nlh->nlmsg_seq);
 	}
+
+	err = inet_rtm_getroute_reply(in_skb, nlh, dst, src, &fl4, rt, &res);
 	if (err < 0)
-		goto errout_free;
+		goto errout_rcu;
 
 	rcu_read_unlock();
 
-	err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
-errout:
-	return err;
-
 errout_free:
-	rcu_read_unlock();
 	kfree_skb(skb);
-	goto errout;
+	return err;
+errout_rcu:
+	rcu_read_unlock();
+	goto errout_free;
 }
 
 void ip_rt_multicast_event(struct in_device *in_dev)
-- 
2.1.4