netfilter: nf_ct_icmp: keep the ICMP ct entries longer

Current conntrack code kills the ICMP conntrack entry as soon as
the first reply is received. This is incorrect, as we then see only
the first ICMP echo reply out of several possible duplicates as
ESTABLISHED, while the rest will be INVALID. Also this unnecessarily
increases the conntrackd traffic on H-A firewalls.

Make all the ICMP conntrack entries (including the replied ones)
last for the default of nf_conntrack_icmp{,v6}_timeout seconds.

Signed-off-by: Jan "Yenya" Kasprzak <[email protected]>
Signed-off-by: Patrick McHardy <[email protected]>

Author: Yenya

include/net/netfilter/ipv4/nf_conntrack_icmp.h

@@ -9,7 +9,6 @@
 
 #ifndef _NF_CONNTRACK_ICMPV6_H
 #define _NF_CONNTRACK_ICMPV6_H
-#include <asm/atomic.h>
 
 #ifndef ICMPV6_NI_QUERY
 #define ICMPV6_NI_QUERY 139
@@ -18,10 +17,4 @@
 #define ICMPV6_NI_REPLY 140
 #endif
 
-struct nf_ct_icmpv6
-{
-	/* Optimization: when number in == number out, forget immediately. */
-	atomic_t count;
-};
-
 #endif /* _NF_CONNTRACK_ICMPV6_H */

include/net/netfilter/ipv6/nf_conntrack_icmpv6.h

@@ -23,7 +23,6 @@
 #include <linux/netfilter/nf_conntrack_dccp.h>
 #include <linux/netfilter/nf_conntrack_sctp.h>
 #include <linux/netfilter/nf_conntrack_proto_gre.h>
-#include <net/netfilter/ipv4/nf_conntrack_icmp.h>
 #include <net/netfilter/ipv6/nf_conntrack_icmpv6.h>
 
 #include <net/netfilter/nf_conntrack_tuple.h>
@@ -34,8 +33,6 @@ union nf_conntrack_proto {
 	struct nf_ct_dccp dccp;
 	struct ip_ct_sctp sctp;
 	struct ip_ct_tcp tcp;
-	struct ip_ct_icmp icmp;
-	struct nf_ct_icmpv6 icmpv6;
 	struct nf_ct_gre gre;
 };
 

include/net/netfilter/nf_conntrack.h

@@ -82,17 +82,10 @@ static int icmp_packet(struct nf_conn *ct,
 		       u_int8_t pf,
 		       unsigned int hooknum)
 {
-	/* Try to delete connection immediately after all replies:
-	   won't actually vanish as we still have skb, and del_timer
-	   means this will only run once even if count hits zero twice
-	   (theoretically possible with SMP) */
-	if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) {
-		if (atomic_dec_and_test(&ct->proto.icmp.count))
-			nf_ct_kill_acct(ct, ctinfo, skb);
-	} else {
-		atomic_inc(&ct->proto.icmp.count);
-		nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_icmp_timeout);
-	}
+	/* Do not immediately delete the connection after the first
+	   successful reply to avoid excessive conntrackd traffic
+	   and also to handle correctly ICMP echo reply duplicates. */
+	nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_icmp_timeout);
 
 	return NF_ACCEPT;
 }
@@ -116,7 +109,6 @@ static bool icmp_new(struct nf_conn *ct, const struct sk_buff *skb,
 		nf_ct_dump_tuple_ip(&ct->tuplehash[0].tuple);
 		return false;
 	}
-	atomic_set(&ct->proto.icmp.count, 0);
 	return true;
 }
 

net/ipv4/netfilter/nf_conntrack_proto_icmp.c

@@ -95,17 +95,10 @@ static int icmpv6_packet(struct nf_conn *ct,
 		       u_int8_t pf,
 		       unsigned int hooknum)
 {
-	/* Try to delete connection immediately after all replies:
-	   won't actually vanish as we still have skb, and del_timer
-	   means this will only run once even if count hits zero twice
-	   (theoretically possible with SMP) */
-	if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) {
-		if (atomic_dec_and_test(&ct->proto.icmp.count))
-			nf_ct_kill_acct(ct, ctinfo, skb);
-	} else {
-		atomic_inc(&ct->proto.icmp.count);
-		nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_icmpv6_timeout);
-	}
+	/* Do not immediately delete the connection after the first
+	   successful reply to avoid excessive conntrackd traffic
+	   and also to handle correctly ICMP echo reply duplicates. */
+	nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_icmpv6_timeout);
 
 	return NF_ACCEPT;
 }
@@ -131,7 +124,6 @@ static bool icmpv6_new(struct nf_conn *ct, const struct sk_buff *skb,
 				      type + 128);
 		return false;
 	}
-	atomic_set(&ct->proto.icmp.count, 0);
 	return true;
 }