From dd4cd47e41206aa2eae1d6c9507830aa466cb8b4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 12 Jun 2014 16:13:06 -0700 Subject: [PATCH] udp: ipv4: do not waste time in __udp4_lib_mcast_demux_lookup Its too easy to add thousand of UDP sockets on a particular bucket, and slow down an innocent multicast receiver. Early demux is supposed to be an optimization, we should avoid spending too much time in it. It is interesting to note __udp4_lib_demux_lookup() only tries to match first socket in the chain. 10 is the threshold we already have in __udp4_lib_lookup() to switch to secondary hash. Fixes: f6730a094d567 ("udp: ipv4: Add udp early demux") Signed-off-by: Eric Dumazet Reported-by: David Held Cc: Shawn Bohrer Signed-off-by: David S. Miller --- net/ipv4/udp.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 185ed3e598027..d92f94b7e4025 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1861,6 +1861,10 @@ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net, unsigned int count, slot = udp_hashfn(net, hnum, udp_table.mask); struct udp_hslot *hslot = &udp_table.hash[slot]; + /* Do not bother scanning a too big list */ + if (hslot->count > 10) + return NULL; + rcu_read_lock(); begin: count = 0; -- 2.39.5