ipv4: try to cache dst_entries which would cause a redirect

Not caching dst_entries which cause redirects could be exploited by hosts
on the same subnet, causing a severe DoS attack. This effect aggravated
since commit f88649721268999 ("ipv4: fix dst race in sk_dst_get()").

Lookups causing redirects will be allocated with DST_NOCACHE set which
will force dst_release to free them via RCU.  Unfortunately waiting for
RCU grace period just takes too long, we can end up with >1M dst_entries
waiting to be released and the system will run OOM. rcuos threads cannot
catch up under high softirq load.

Attaching the flag to emit a redirect later on to the specific skb allows
us to cache those dst_entries thus reducing the pressure on allocation
and deallocation.

This issue was discovered by Marcelo Leitner.

Cc: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Marcelo Leitner <mleitner@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 13 insertions, 10 deletions

diff --git a/include/net/ip.h b/include/net/ip.h
index 0bb620702929..f7cbd703d15d 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -39,11 +39,12 @@ struct inet_skb_parm {
         struct ip_options       opt;            /* Compiled IP options          */
         unsigned char           flags;
 
-#define IPSKB_FORWARDED         1
-#define IPSKB_XFRM_TUNNEL_SIZE  2
-#define IPSKB_XFRM_TRANSFORMED  4
-#define IPSKB_FRAG_COMPLETE     8
-#define IPSKB_REROUTED          16
+#define IPSKB_FORWARDED         BIT(0)
+#define IPSKB_XFRM_TUNNEL_SIZE  BIT(1)
+#define IPSKB_XFRM_TRANSFORMED  BIT(2)
+#define IPSKB_FRAG_COMPLETE     BIT(3)
+#define IPSKB_REROUTED          BIT(4)
+#define IPSKB_DOREDIRECT        BIT(5)
 
         u16                     frag_max_size;
 };
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 3a83ce5efa80..787b3c294ce6 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -129,7 +129,8 @@ int ip_forward(struct sk_buff *skb)
          *      We now generate an ICMP HOST REDIRECT giving the route
          *      we calculated.
          */
-        if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb))
+        if (IPCB(skb)->flags & IPSKB_DOREDIRECT && !opt->srr &&
+            !skb_sec_path(skb))
                 ip_rt_send_redirect(skb);
 
         skb->priority = rt_tos2priority(iph->tos);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6a2155b02602..d58dd0ec3e53 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1554,11 +1554,10 @@ static int __mkroute_input(struct sk_buff *skb,
 
         do_cache = res->fi && !itag;
         if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) &&
+            skb->protocol == htons(ETH_P_IP) &&
             (IN_DEV_SHARED_MEDIA(out_dev) ||
-             inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) {
-                flags |= RTCF_DOREDIRECT;
-                do_cache = false;
-        }
+             inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
+                IPCB(skb)->flags |= IPSKB_DOREDIRECT;
 
         if (skb->protocol != htons(ETH_P_IP)) {
                 /* Not IP (i.e. ARP). Do not create route, if it is
@@ -2303,6 +2302,8 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
         r->rtm_flags    = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED;
         if (rt->rt_flags & RTCF_NOTIFY)
                 r->rtm_flags |= RTM_F_NOTIFY;
+        if (IPCB(skb)->flags & IPSKB_DOREDIRECT)
+                r->rtm_flags |= RTCF_DOREDIRECT;
 
         if (nla_put_be32(skb, RTA_DST, dst))
                 goto nla_put_failure;