ipv4: Fix incorrect TOS in route get reply

The TOS value that is returned to user space in the route get reply is
the one with which the lookup was performed ('fl4->flowi4_tos'). This is
fine when the matched route is configured with a TOS as it would not
match if its TOS value did not match the one with which the lookup was
performed.

However, matching on TOS is only performed when the route's TOS is not
zero. It is therefore possible to have the kernel incorrectly return a
non-zero TOS:

 # ip link add name dummy1 up type dummy
 # ip address add 192.0.2.1/24 dev dummy1
 # ip route get 192.0.2.2 tos 0xfc
 192.0.2.2 tos 0x1c dev dummy1 src 192.0.2.1 uid 0
     cache

Fix by adding a DSCP field to the FIB result structure (inside an
existing 4 bytes hole), populating it in the route lookup and using it
when filling the route get reply.

Output after the patch:

 # ip link add name dummy1 up type dummy
 # ip address add 192.0.2.1/24 dev dummy1
 # ip route get 192.0.2.2 tos 0xfc
 192.0.2.2 dev dummy1 src 192.0.2.1 uid 0
     cache

Fixes: 1a00fee4ffb2 ("ipv4: Remove rt_key_{src,dst,tos} from struct rtable.")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

3 files changed, 9 insertions, 7 deletions

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 6e7984bfb986..72af2f223e59 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -173,6 +173,7 @@ struct fib_result {
 	unsigned char		type;
 	unsigned char		scope;
 	u32			tclassid;
+	dscp_t			dscp;
 	struct fib_nh_common	*nhc;
 	struct fib_info		*fi;
 	struct fib_table	*table;
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index f474106464d2..8f30e3f00b7f 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1629,6 +1629,7 @@ set_result:
 			res->nhc = nhc;
 			res->type = fa->fa_type;
 			res->scope = fi->fib_scope;
+			res->dscp = fa->fa_dscp;
 			res->fi = fi;
 			res->table = tb;
 			res->fa_head = &n->leaf;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 54512acbead7..82b8fe8faeb7 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2867,9 +2867,9 @@ 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,
-			struct rtable *rt, u32 table_id, struct flowi4 *fl4,
-			struct sk_buff *skb, u32 portid, u32 seq,
-			unsigned int flags)
+			struct rtable *rt, u32 table_id, dscp_t dscp,
+			struct flowi4 *fl4, struct sk_buff *skb, u32 portid,
+			u32 seq, unsigned int flags)
 {
 	struct rtmsg *r;
 	struct nlmsghdr *nlh;
@@ -2885,7 +2885,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
 	r->rtm_family	 = AF_INET;
 	r->rtm_dst_len	= 32;
 	r->rtm_src_len	= 0;
-	r->rtm_tos	= fl4 ? fl4->flowi4_tos : 0;
+	r->rtm_tos	= inet_dscp_to_dsfield(dscp);
 	r->rtm_table	= table_id < 256 ? table_id : RT_TABLE_COMPAT;
 	if (nla_put_u32(skb, RTA_TABLE, table_id))
 		goto nla_put_failure;
@@ -3035,7 +3035,7 @@ static int fnhe_dump_bucket(struct net *net, struct sk_buff *skb,
 				goto next;
 
 			err = rt_fill_info(net, fnhe->fnhe_daddr, 0, rt,
-					   table_id, NULL, skb,
+					   table_id, 0, NULL, skb,
 					   NETLINK_CB(cb->skb).portid,
 					   cb->nlh->nlmsg_seq, flags);
 			if (err)
@@ -3358,8 +3358,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		err = fib_dump_info(skb, NETLINK_CB(in_skb).portid,
 				    nlh->nlmsg_seq, RTM_NEWROUTE, &fri, 0);
 	} else {
-		err = rt_fill_info(net, dst, src, rt, table_id, &fl4, skb,
-				   NETLINK_CB(in_skb).portid,
+		err = rt_fill_info(net, dst, src, rt, table_id, res.dscp, &fl4,
+				   skb, NETLINK_CB(in_skb).portid,
 				   nlh->nlmsg_seq, 0);
 	}
 	if (err < 0)