From: Guillaume Nault gnault@redhat.com
[ Upstream commit 544b4dd568e3b09c1ab38a759d3187e7abda11a0 ]
The PMTU update and ICMP redirect helper functions initialise their fl4 variable with either __build_flow_key() or build_sk_flow_key(). These initialisation functions always set ->flowi4_scope with RT_SCOPE_UNIVERSE and might set the ECN bits of ->flowi4_tos. This is not a problem when the route lookup is later done via ip_route_output_key_hash(), which properly clears the ECN bits from ->flowi4_tos and initialises ->flowi4_scope based on the RTO_ONLINK flag. However, some helpers call fib_lookup() directly, without sanitising the tos and scope fields, so the route lookup can fail and, as a result, the ICMP redirect or PMTU update aren't taken into account.
Fix this by extracting the ->flowi4_tos and ->flowi4_scope sanitisation code into ip_rt_fix_tos(), then use this function in handlers that call fib_lookup() directly.
Note 1: We can't sanitise ->flowi4_tos and ->flowi4_scope in a central place (like __build_flow_key() or flowi4_init_output()), because ip_route_output_key_hash() expects non-sanitised values. When called with sanitised values, it can erroneously overwrite RT_SCOPE_LINK with RT_SCOPE_UNIVERSE in ->flowi4_scope. Therefore we have to be careful to sanitise the values only for those paths that don't call ip_route_output_key_hash().
Note 2: The problem is mostly about sanitising ->flowi4_tos. Having ->flowi4_scope initialised with RT_SCOPE_UNIVERSE instead of RT_SCOPE_LINK probably wasn't really a problem: sockets with the SOCK_LOCALROUTE flag set (those that'd result in RTO_ONLINK being set) normally shouldn't receive ICMP redirects or PMTU updates.
Fixes: 4895c771c7f0 ("ipv4: Add FIB nexthop exceptions.") Signed-off-by: Guillaume Nault gnault@redhat.com Reviewed-by: David Ahern dsahern@kernel.org Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/route.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ce787c386793..c72d0de8bf71 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -529,6 +529,15 @@ void __ip_select_ident(struct net *net, struct iphdr *iph, int segs) } EXPORT_SYMBOL(__ip_select_ident);
+static void ip_rt_fix_tos(struct flowi4 *fl4) +{ + __u8 tos = RT_FL_TOS(fl4); + + fl4->flowi4_tos = tos & IPTOS_RT_MASK; + fl4->flowi4_scope = tos & RTO_ONLINK ? + RT_SCOPE_LINK : RT_SCOPE_UNIVERSE; +} + static void __build_flow_key(const struct net *net, struct flowi4 *fl4, const struct sock *sk, const struct iphdr *iph, @@ -853,6 +862,7 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf rt = (struct rtable *) dst;
__build_flow_key(net, &fl4, sk, iph, oif, tos, prot, mark, 0); + ip_rt_fix_tos(&fl4); __ip_do_redirect(rt, skb, &fl4, true); }
@@ -1077,6 +1087,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct flowi4 fl4;
ip_rt_build_flow_key(&fl4, sk, skb); + ip_rt_fix_tos(&fl4);
/* Don't make lookup fail for bridged encapsulations */ if (skb && netif_is_any_bridge_port(skb->dev)) @@ -1151,6 +1162,8 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) goto out;
new = true; + } else { + ip_rt_fix_tos(&fl4); }
__ip_rt_update_pmtu((struct rtable *)xfrm_dst_path(&rt->dst), &fl4, mtu); @@ -2524,7 +2537,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res, struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, const struct sk_buff *skb) { - __u8 tos = RT_FL_TOS(fl4); struct fib_result res = { .type = RTN_UNSPEC, .fi = NULL, @@ -2534,9 +2546,7 @@ struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, struct rtable *rth;
fl4->flowi4_iif = LOOPBACK_IFINDEX; - fl4->flowi4_tos = tos & IPTOS_RT_MASK; - fl4->flowi4_scope = ((tos & RTO_ONLINK) ? - RT_SCOPE_LINK : RT_SCOPE_UNIVERSE); + ip_rt_fix_tos(fl4);
rcu_read_lock(); rth = ip_route_output_key_hash_rcu(net, fl4, &res, skb);