Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next

Pablo Neira Ayuso says:

====================
Netfilter/IPVS updates for net-next

The following patchset contains Netfilter/IPVS updates for your net-next
tree, they are:

1) Speed up table replacement on busy systems with large tables
   (and many cores) in x_tables. Now xt_replace_table() synchronizes by
   itself by waiting until all cpus had an even seqcount and we use no
   use seqlock when fetching old counters, from Florian Westphal.

2) Add nf_l4proto_log_invalid() and nf_ct_l4proto_log_invalid() to speed
   up packet processing in the fast path when logging is not enabled, from
   Florian Westphal.

3) Precompute masked address from configuration plane in xt_connlimit,
   from Florian.

4) Don't use explicit size for set selection if performance set policy
   is selected.

5) Allow to get elements from an existing set in nf_tables.

6) Fix incorrect check in nft_hash_deactivate(), from Florian.

7) Cache netlink attribute size result in l4proto->nla_size, from
   Florian.

8) Handle NFPROTO_INET in nf_ct_netns_get() from conntrack core.

9) Use power efficient workqueue in conntrack garbage collector, from
   Vincent Guittot.

10) Remove unnecessary parameter, in conntrack l4proto functions, also
    from Florian.

11) Constify struct nf_conntrack_l3proto definitions, from Florian.

12) Remove all typedefs in nf_conntrack_h323 via coccinelle semantic
    patch, from Harsha Sharma.

13) Don't store address in the rbtree nodes in xt_connlimit, they are
    never used, from Florian.

14) Fix out of bound access in the conntrack h323 helper, patch from
    Eric Sesterhenn.

15) Print symbols for the address returned with %pS in IPVS, from
    Helge Deller.

16) Proc output should only display its own netns in IPVS, from
    KUWAZAWA Takuya.

17) Small clean up in size_entry_mwt(), from Colin Ian King.

18) Use test_and_clear_bit from nf_nat_proto_clean() instead of separated
    non-atomic test and then clear bit, from Florian Westphal.

19) Consolidate prefix length maps in ipset, from Aaron Conole.

20) Fix sparse warnings in ipset, from Jozsef Kadlecsik.

21) Simplify list_set_memsize(), from simran singhal.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 58 insertions, 17 deletions

diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 9e2770fd00be..f88221aebc9d 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -634,6 +634,25 @@ static void get_counters(const struct xt_table_info *t,
 	}
 }
 
+static void get_old_counters(const struct xt_table_info *t,
+			     struct xt_counters counters[])
+{
+	struct arpt_entry *iter;
+	unsigned int cpu, i;
+
+	for_each_possible_cpu(cpu) {
+		i = 0;
+		xt_entry_foreach(iter, t->entries, t->size) {
+			struct xt_counters *tmp;
+
+			tmp = xt_get_per_cpu_counter(&iter->counters, cpu);
+			ADD_COUNTER(counters[i], tmp->bcnt, tmp->pcnt);
+			++i;
+		}
+		cond_resched();
+	}
+}
+
 static struct xt_counters *alloc_counters(const struct xt_table *table)
 {
 	unsigned int countersize;
@@ -910,8 +929,7 @@ static int __do_replace(struct net *net, const char *name,
 	    (newinfo->number <= oldinfo->initial_entries))
 		module_put(t->me);
 
-	/* Get the old counters, and synchronize with replace */
-	get_counters(oldinfo, counters);
+	get_old_counters(oldinfo, counters);
 
 	/* Decrease module usage counts and free resource */
 	loc_cpu_old_entry = oldinfo->entries;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 39286e543ee6..4cbe5e80f3bf 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -781,6 +781,26 @@ get_counters(const struct xt_table_info *t,
 	}
 }
 
+static void get_old_counters(const struct xt_table_info *t,
+			     struct xt_counters counters[])
+{
+	struct ipt_entry *iter;
+	unsigned int cpu, i;
+
+	for_each_possible_cpu(cpu) {
+		i = 0;
+		xt_entry_foreach(iter, t->entries, t->size) {
+			const struct xt_counters *tmp;
+
+			tmp = xt_get_per_cpu_counter(&iter->counters, cpu);
+			ADD_COUNTER(counters[i], tmp->bcnt, tmp->pcnt);
+			++i; /* macro does multi eval of i */
+		}
+
+		cond_resched();
+	}
+}
+
 static struct xt_counters *alloc_counters(const struct xt_table *table)
 {
 	unsigned int countersize;
@@ -1070,8 +1090,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
 	    (newinfo->number <= oldinfo->initial_entries))
 		module_put(t->me);
 
-	/* Get the old counters, and synchronize with replace */
-	get_counters(oldinfo, counters);
+	get_old_counters(oldinfo, counters);
 
 	/* Decrease module usage counts and free resource */
 	xt_entry_foreach(iter, oldinfo->entries, oldinfo->size)
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index fe374da4bc13..89af9d88ca21 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -344,7 +344,7 @@ static void ipv4_hooks_unregister(struct net *net)
 	mutex_unlock(&register_ipv4_hooks);
 }
 
-struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 __read_mostly = {
+const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 = {
 	.l3proto	 = PF_INET,
 	.pkt_to_tuple	 = ipv4_pkt_to_tuple,
 	.invert_tuple	 = ipv4_invert_tuple,
diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
index a046c298413a..1849fedd9b81 100644
--- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
@@ -81,7 +81,6 @@ static int icmp_packet(struct nf_conn *ct,
 		       const struct sk_buff *skb,
 		       unsigned int dataoff,
 		       enum ip_conntrack_info ctinfo,
-		       u_int8_t pf,
 		       unsigned int *timeout)
 {
 	/* Do not immediately delete the connection after the first
@@ -165,6 +164,12 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,
 	return NF_ACCEPT;
 }
 
+static void icmp_error_log(const struct sk_buff *skb, struct net *net,
+			   u8 pf, const char *msg)
+{
+	nf_l4proto_log_invalid(skb, net, pf, IPPROTO_ICMP, "%s", msg);
+}
+
 /* Small and modified version of icmp_rcv */
 static int
 icmp_error(struct net *net, struct nf_conn *tmpl,
@@ -177,18 +182,14 @@ icmp_error(struct net *net, struct nf_conn *tmpl,
 	/* Not enough header? */
 	icmph = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_ih), &_ih);
 	if (icmph == NULL) {
-		if (LOG_INVALID(net, IPPROTO_ICMP))
-			nf_log_packet(net, PF_INET, 0, skb, NULL, NULL,
-				      NULL, "nf_ct_icmp: short packet ");
+		icmp_error_log(skb, net, pf, "short packet");
 		return -NF_ACCEPT;
 	}
 
 	/* See ip_conntrack_proto_tcp.c */
 	if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING &&
 	    nf_ip_checksum(skb, hooknum, dataoff, 0)) {
-		if (LOG_INVALID(net, IPPROTO_ICMP))
-			nf_log_packet(net, PF_INET, 0, skb, NULL, NULL, NULL,
-				      "nf_ct_icmp: bad HW ICMP checksum ");
+		icmp_error_log(skb, net, pf, "bad hw icmp checksum");
 		return -NF_ACCEPT;
 	}
 
@@ -199,9 +200,7 @@ icmp_error(struct net *net, struct nf_conn *tmpl,
 	 *		  discarded.
 	 */
 	if (icmph->type > NR_ICMP_TYPES) {
-		if (LOG_INVALID(net, IPPROTO_ICMP))
-			nf_log_packet(net, PF_INET, 0, skb, NULL, NULL, NULL,
-				      "nf_ct_icmp: invalid ICMP type ");
+		icmp_error_log(skb, net, pf, "invalid icmp type");
 		return -NF_ACCEPT;
 	}
 
@@ -259,9 +258,14 @@ static int icmp_nlattr_to_tuple(struct nlattr *tb[],
 	return 0;
 }
 
-static int icmp_nlattr_tuple_size(void)
+static unsigned int icmp_nlattr_tuple_size(void)
 {
-	return nla_policy_len(icmp_nla_policy, CTA_PROTO_MAX + 1);
+	static unsigned int size __read_mostly;
+
+	if (!size)
+		size = nla_policy_len(icmp_nla_policy, CTA_PROTO_MAX + 1);
+
+	return size;
 }
 #endif