Merge branch 'RTM_GETROUTE--return-fib-result'

Roopa Prabhu says:

====================
net: extend RTM_GETROUTE to return fib result

This series adds a new RTM_F_FIB_MATCH flag to return matched fib result
with RTM_GETROUTE. This is useful for applications and protocols in
userspace wanting to query the selected route.

examples (with patched iproute2):
ipv4:
----
$ip route show
default via 192.168.0.2 dev eth0
10.0.14.0/24
        nexthop via 172.16.0.3  dev dummy0 weight 1
        nexthop via 172.16.1.3  dev dummy1 weight 1

$ip route get 10.0.14.2
10.0.14.2 via 172.16.1.3 dev dummy1  src 172.16.1.1
    cache

$ip route get fibmatch 10.0.14.2
10.0.14.0/24
        nexthop via 172.16.0.3  dev dummy0 weight 1
        nexthop via 172.16.1.3  dev dummy1 weight 1

ipv6:
----
$ip -6 route show
2001:db9:100::/120  metric 1024
        nexthop via 2001:db8:2::2  dev dummy0 weight 1
        nexthop via 2001:db8:12::2  dev dummy1 weight 1

$ip -6 route get 2001:db9:100::1
2001:db9:100::1 from :: via 2001:db8:12::2 dev dummy1  src 2001:db8:12::1  metric 1024  pref medium

$ip -6 route get fibmatch 2001:db9:100::1
2001:db9:100::/120  metric 1024
        nexthop via 2001:db8:12::2  dev dummy1 weight 1
        nexthop via 2001:db8:2::2  dev dummy0 weight 1

v2:
        - pick up new forward port of patch-01 from david
        - inet6_rtm_getroute: use container_of for rt6_info to
          dst conversion
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/ip_fib.h

@@ -136,6 +136,7 @@ struct fib_rule;
 
 struct fib_table;
 struct fib_result {
+	__be32		prefix;
 	unsigned char	prefixlen;
 	unsigned char	nh_sel;
 	unsigned char	type;

include/net/route.h

@@ -113,13 +113,16 @@ struct in_device;
 int ip_rt_init(void);
 void rt_cache_flush(struct net *net);
 void rt_flush_dev(struct net_device *dev);
-struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *flp,
-					  const struct sk_buff *skb);
+struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *flp,
+					const struct sk_buff *skb);
+struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *flp,
+					    struct fib_result *res,
+					    const struct sk_buff *skb);
 
 static inline struct rtable *__ip_route_output_key(struct net *net,
 						   struct flowi4 *flp)
 {
-	return __ip_route_output_key_hash(net, flp, NULL);
+	return ip_route_output_key_hash(net, flp, NULL);
 }
 
 struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp,
@@ -175,6 +178,9 @@ static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4
 
 int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src,
 			 u8 tos, struct net_device *devin);
+int ip_route_input_rcu(struct sk_buff *skb, __be32 dst, __be32 src,
+		       u8 tos, struct net_device *devin,
+		       struct fib_result *res);
 
 static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
 				 u8 tos, struct net_device *devin)

include/uapi/linux/rtnetlink.h

@@ -278,6 +278,7 @@ enum rt_scope_t {
 #define RTM_F_EQUALIZE		0x400	/* Multipath equalizer: NI	*/
 #define RTM_F_PREFIX		0x800	/* Prefix addresses		*/
 #define RTM_F_LOOKUP_TABLE	0x1000	/* set rtm_table to FIB lookup result */
+#define RTM_F_FIB_MATCH	        0x2000	/* return full fib lookup match */
 
 /* Reserved table identifiers */
 

net/ipv4/fib_trie.c

@@ -1452,6 +1452,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
 			if (!(fib_flags & FIB_LOOKUP_NOREF))
 				atomic_inc(&fi->fib_clntref);
 
+			res->prefix = htonl(n->key);
 			res->prefixlen = KEYLENGTH - fa->fa_slen;
 			res->nh_sel = nhsel;
 			res->type = fa->fa_type;

net/ipv4/icmp.c

@@ -489,7 +489,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
 	fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev);
 
 	security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4));
-	rt = __ip_route_output_key_hash(net, fl4, skb_in);
+	rt = ip_route_output_key_hash(net, fl4, skb_in);
 	if (IS_ERR(rt))
 		return rt;
 

net/ipv6/route.c

@@ -3607,11 +3607,13 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 {
 	struct net *net = sock_net(in_skb->sk);
 	struct nlattr *tb[RTA_MAX+1];
+	int err, iif = 0, oif = 0;
+	struct dst_entry *dst;
 	struct rt6_info *rt;
 	struct sk_buff *skb;
 	struct rtmsg *rtm;
 	struct flowi6 fl6;
-	int err, iif = 0, oif = 0;
+	bool fibmatch;
 
 	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy,
 			  extack);
@@ -3622,6 +3624,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	memset(&fl6, 0, sizeof(fl6));
 	rtm = nlmsg_data(nlh);
 	fl6.flowlabel = ip6_make_flowinfo(rtm->rtm_tos, 0);
+	fibmatch = !!(rtm->rtm_flags & RTM_F_FIB_MATCH);
 
 	if (tb[RTA_SRC]) {
 		if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr))
@@ -3667,12 +3670,23 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		if (!ipv6_addr_any(&fl6.saddr))
 			flags |= RT6_LOOKUP_F_HAS_SADDR;
 
-		rt = (struct rt6_info *)ip6_route_input_lookup(net, dev, &fl6,
-							       flags);
+		if (!fibmatch)
+			dst = ip6_route_input_lookup(net, dev, &fl6, flags);
 	} else {
 		fl6.flowi6_oif = oif;
 
-		rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6);
+		if (!fibmatch)
+			dst = ip6_route_output(net, NULL, &fl6);
+	}
+
+	if (fibmatch)
+		dst = ip6_route_lookup(net, &fl6, 0);
+
+	rt = container_of(dst, struct rt6_info, dst);
+	if (rt->dst.error) {
+		err = rt->dst.error;
+		ip6_rt_put(rt);
+		goto errout;
 	}
 
 	if (rt == net->ipv6.ip6_null_entry) {
@@ -3689,10 +3703,14 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	}
 
 	skb_dst_set(skb, &rt->dst);
-
-	err = rt6_fill_node(net, skb, rt, &fl6.daddr, &fl6.saddr, iif,
-			    RTM_NEWROUTE, NETLINK_CB(in_skb).portid,
-			    nlh->nlmsg_seq, 0);
+	if (fibmatch)
+		err = rt6_fill_node(net, skb, rt, NULL, NULL, iif,
+				    RTM_NEWROUTE, NETLINK_CB(in_skb).portid,
+				    nlh->nlmsg_seq, 0);
+	else
+		err = rt6_fill_node(net, skb, rt, &fl6.daddr, &fl6.saddr, iif,
+				    RTM_NEWROUTE, NETLINK_CB(in_skb).portid,
+				    nlh->nlmsg_seq, 0);
 	if (err < 0) {
 		kfree_skb(skb);
 		goto errout;