summaryrefslogtreecommitdiffstats
path: root/net/ipv4/route.c
diff options
context:
space:
mode:
authorHannes Frederic Sowa <hannes@stressinduktion.org>2015-01-23 12:01:26 +0100
committerDavid S. Miller <davem@davemloft.net>2015-01-27 02:28:27 +0100
commitdf4d92549f23e1c037e83323aff58a21b3de7fe0 (patch)
treecb82536dd48281496b6652b628266cdcacffb91d /net/ipv4/route.c
parentMerge branch 'bpf' (diff)
downloadlinux-df4d92549f23e1c037e83323aff58a21b3de7fe0.tar.xz
linux-df4d92549f23e1c037e83323aff58a21b3de7fe0.zip
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>
Diffstat (limited to '')
-rw-r--r--net/ipv4/route.c9
1 files changed, 5 insertions, 4 deletions
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;