Merge branch 'master' of git://1984.lsi.us.es/nf-next

Pablo Neira Ayuso says:

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

* Better performance in nfnetlink_queue by avoiding copy from the
  packet to netlink message, from Eric Dumazet.

* Remove unnecessary locking in the exit path of ebt_ulog, from Gao Feng.

* Use new function ipv6_iface_scope_id in nf_ct_ipv6, from Hannes Frederic Sowa.

* A couple of sparse fixes for IPVS, from Julian Anastasov.

* Use xor hashing in nfnetlink_queue, as suggested by Eric Dumazet, from
  myself.

* Allow to dump expectations per master conntrack via ctnetlink, from myself.

* A couple of cleanups to use PTR_RET in module init path, from Silviu-Mihai
  Popescu.

* Remove nf_conntrack module a bit faster if netns are in use, from
  Vladimir Davydov.

* Use checksum_partial in ip6t_NPT, from YOSHIFUJI Hideaki.

* Sparse fix for nf_conntrack, from Stephen Hemminger.
====================

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

include/net/ip_vs.h

@@ -459,7 +459,7 @@ struct ip_vs_estimator {
 struct ip_vs_stats {
 	struct ip_vs_stats_user	ustats;		/* statistics */
 	struct ip_vs_estimator	est;		/* estimator */
-	struct ip_vs_cpu_stats	*cpustats;	/* per cpu counters */
+	struct ip_vs_cpu_stats __percpu	*cpustats;	/* per cpu counters */
 	spinlock_t		lock;		/* spin lock */
 	struct ip_vs_stats_user	ustats0;	/* reset values */
 };

include/net/netfilter/nf_conntrack_core.h

@@ -27,6 +27,7 @@ extern unsigned int nf_conntrack_in(struct net *net,
 
 extern int nf_conntrack_init_net(struct net *net);
 extern void nf_conntrack_cleanup_net(struct net *net);
+extern void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list);
 
 extern int nf_conntrack_proto_pernet_init(struct net *net);
 extern void nf_conntrack_proto_pernet_fini(struct net *net);

net/bridge/netfilter/ebt_ulog.c

@@ -319,12 +319,11 @@ static void __exit ebt_ulog_fini(void)
 	for (i = 0; i < EBT_ULOG_MAXNLGROUPS; i++) {
 		ub = &ulog_buffers[i];
 		del_timer(&ub->timer);
-		spin_lock_bh(&ub->lock);
+
 		if (ub->skb) {
 			kfree_skb(ub->skb);
 			ub->skb = NULL;
 		}
-		spin_unlock_bh(&ub->lock);
 	}
 	netlink_kernel_release(ebtulognl);
 }

net/bridge/netfilter/ebtable_broute.c

@@ -64,9 +64,7 @@ static int ebt_broute(struct sk_buff *skb)
 static int __net_init broute_net_init(struct net *net)
 {
 	net->xt.broute_table = ebt_register_table(net, &broute_table);
-	if (IS_ERR(net->xt.broute_table))
+	return PTR_RET(net->xt.broute_table);
-		return PTR_ERR(net->xt.broute_table);
-	return 0;
 }
 
 static void __net_exit broute_net_exit(struct net *net)

net/ipv4/netfilter/arptable_filter.c

@@ -48,9 +48,7 @@ static int __net_init arptable_filter_net_init(struct net *net)
 	net->ipv4.arptable_filter =
 		arpt_register_table(net, &packet_filter, repl);
 	kfree(repl);
-	if (IS_ERR(net->ipv4.arptable_filter))
+	return PTR_RET(net->ipv4.arptable_filter);
-		return PTR_ERR(net->ipv4.arptable_filter);
-	return 0;
 }
 
 static void __net_exit arptable_filter_net_exit(struct net *net)

net/ipv6/netfilter/ip6t_NPT.c

@@ -18,9 +18,8 @@
 static int ip6t_npt_checkentry(const struct xt_tgchk_param *par)
 {
 	struct ip6t_npt_tginfo *npt = par->targinfo;
-	__wsum src_sum = 0, dst_sum = 0;
 	struct in6_addr pfx;
-	unsigned int i;
+	__wsum src_sum, dst_sum;
 
 	if (npt->src_pfx_len > 64 || npt->dst_pfx_len > 64)
 		return -EINVAL;
@@ -33,12 +32,8 @@ static int ip6t_npt_checkentry(const struct xt_tgchk_param *par)
 	if (!ipv6_addr_equal(&pfx, &npt->dst_pfx.in6))
 		return -EINVAL;
 
-	for (i = 0; i < ARRAY_SIZE(npt->src_pfx.in6.s6_addr16); i++) {
+	src_sum = csum_partial(&npt->src_pfx.in6, sizeof(npt->src_pfx.in6), 0);
-		src_sum = csum_add(src_sum,
+	dst_sum = csum_partial(&npt->dst_pfx.in6, sizeof(npt->dst_pfx.in6), 0);
-				(__force __wsum)npt->src_pfx.in6.s6_addr16[i]);
-		dst_sum = csum_add(dst_sum,
-				(__force __wsum)npt->dst_pfx.in6.s6_addr16[i]);
-	}
 
 	npt->adjustment = ~csum_fold(csum_sub(src_sum, dst_sum));
 	return 0;

net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c

@@ -330,12 +330,8 @@ ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len)
 					sizeof(sin6.sin6_addr));
 
 	nf_ct_put(ct);
-
+	sin6.sin6_scope_id = ipv6_iface_scope_id(&sin6.sin6_addr,
-	if (ipv6_addr_type(&sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL)
+						 sk->sk_bound_dev_if);
-		sin6.sin6_scope_id = sk->sk_bound_dev_if;
-	else
-		sin6.sin6_scope_id = 0;
-
 	return copy_to_user(user, &sin6, sizeof(sin6)) ? -EFAULT : 0;
 }
 

net/netfilter/ipvs/ip_vs_core.c

@@ -69,10 +69,7 @@ EXPORT_SYMBOL(ip_vs_conn_put);
 EXPORT_SYMBOL(ip_vs_get_debug_level);
 #endif
 
-int ip_vs_net_id __read_mostly;
+static int ip_vs_net_id __read_mostly;
-#ifdef IP_VS_GENERIC_NETNS
-EXPORT_SYMBOL(ip_vs_net_id);
-#endif
 /* netns cnt used for uniqueness */
 static atomic_t ipvs_netns_cnt = ATOMIC_INIT(0);
 
@@ -1181,9 +1178,6 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 						iph.len)))) {
 #ifdef CONFIG_IP_VS_IPV6
 				if (af == AF_INET6) {
-					struct net *net =
-						dev_net(skb_dst(skb)->dev);
-
 					if (!skb->dev)
 						skb->dev = net->loopback_dev;
 					icmpv6_send(skb,

net/netfilter/ipvs/ip_vs_ctl.c

@@ -271,16 +271,18 @@ ip_vs_svc_hashkey(struct net *net, int af, unsigned int proto,
 {
 	register unsigned int porth = ntohs(port);
 	__be32 addr_fold = addr->ip;
+	__u32 ahash;
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6)
 		addr_fold = addr->ip6[0]^addr->ip6[1]^
 			    addr->ip6[2]^addr->ip6[3];
 #endif
-	addr_fold ^= ((size_t)net>>8);
+	ahash = ntohl(addr_fold);
+	ahash ^= ((size_t) net >> 8);
 
-	return (proto^ntohl(addr_fold)^(porth>>IP_VS_SVC_TAB_BITS)^porth)
+	return (proto ^ ahash ^ (porth >> IP_VS_SVC_TAB_BITS) ^ porth) &
-		& IP_VS_SVC_TAB_MASK;
+	       IP_VS_SVC_TAB_MASK;
 }
 
 /*

net/netfilter/ipvs/ip_vs_est.c

@@ -56,7 +56,7 @@
  * Make a summary from each cpu
  */
 static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum,
-				 struct ip_vs_cpu_stats *stats)
+				 struct ip_vs_cpu_stats __percpu *stats)
 {
 	int i;
 

net/netfilter/nf_conntrack_core.c

@@ -48,6 +48,7 @@
 #include <net/netfilter/nf_conntrack_labels.h>
 #include <net/netfilter/nf_nat.h>
 #include <net/netfilter/nf_nat_core.h>
+#include <net/netfilter/nf_nat_helper.h>
 
 #define NF_CONNTRACK_VERSION	"0.5.0"
 
@@ -1364,20 +1365,37 @@ void nf_conntrack_cleanup_end(void)
  */
 void nf_conntrack_cleanup_net(struct net *net)
 {
+	LIST_HEAD(single);
+
+	list_add(&net->exit_list, &single);
+	nf_conntrack_cleanup_net_list(&single);
+}
+
+void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list)
+{
+	int busy;
+	struct net *net;
+
 	/*
 	 * This makes sure all current packets have passed through
 	 *  netfilter framework.  Roll on, two-stage module
 	 *  delete...
 	 */
 	synchronize_net();
- i_see_dead_people:
+i_see_dead_people:
+	busy = 0;
+	list_for_each_entry(net, net_exit_list, exit_list) {
 		nf_ct_iterate_cleanup(net, kill_all, NULL);
 		nf_ct_release_dying_list(net);
-	if (atomic_read(&net->ct.count) != 0) {
+		if (atomic_read(&net->ct.count) != 0)
+			busy = 1;
+	}
+	if (busy) {
 		schedule();
 		goto i_see_dead_people;
 	}
 
+	list_for_each_entry(net, net_exit_list, exit_list) {
 		nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size);
 		nf_conntrack_proto_pernet_fini(net);
 		nf_conntrack_helper_pernet_fini(net);
@@ -1388,6 +1406,7 @@ void nf_conntrack_cleanup_net(struct net *net)
 		kmem_cache_destroy(net->ct.nf_conntrack_cachep);
 		kfree(net->ct.slabname);
 		free_percpu(net->ct.stat);
+	}
 }
 
 void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls)

net/netfilter/nf_conntrack_netlink.c

@@ -2409,6 +2409,92 @@ out:
 	return skb->len;
 }
 
+static int
+ctnetlink_exp_ct_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct nf_conntrack_expect *exp, *last;
+	struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
+	struct nf_conn *ct = cb->data;
+	struct nf_conn_help *help = nfct_help(ct);
+	u_int8_t l3proto = nfmsg->nfgen_family;
+
+	if (cb->args[0])
+		return 0;
+
+	rcu_read_lock();
+	last = (struct nf_conntrack_expect *)cb->args[1];
+restart:
+	hlist_for_each_entry(exp, &help->expectations, lnode) {
+		if (l3proto && exp->tuple.src.l3num != l3proto)
+			continue;
+		if (cb->args[1]) {
+			if (exp != last)
+				continue;
+			cb->args[1] = 0;
+		}
+		if (ctnetlink_exp_fill_info(skb, NETLINK_CB(cb->skb).portid,
+					    cb->nlh->nlmsg_seq,
+					    IPCTNL_MSG_EXP_NEW,
+					    exp) < 0) {
+			if (!atomic_inc_not_zero(&exp->use))
+				continue;
+			cb->args[1] = (unsigned long)exp;
+			goto out;
+		}
+	}
+	if (cb->args[1]) {
+		cb->args[1] = 0;
+		goto restart;
+	}
+	cb->args[0] = 1;
+out:
+	rcu_read_unlock();
+	if (last)
+		nf_ct_expect_put(last);
+
+	return skb->len;
+}
+
+static int ctnetlink_dump_exp_ct(struct sock *ctnl, struct sk_buff *skb,
+				 const struct nlmsghdr *nlh,
+				 const struct nlattr * const cda[])
+{
+	int err;
+	struct net *net = sock_net(ctnl);
+	struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+	u_int8_t u3 = nfmsg->nfgen_family;
+	struct nf_conntrack_tuple tuple;
+	struct nf_conntrack_tuple_hash *h;
+	struct nf_conn *ct;
+	u16 zone = 0;
+	struct netlink_dump_control c = {
+		.dump = ctnetlink_exp_ct_dump_table,
+		.done = ctnetlink_exp_done,
+	};
+
+	err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER, u3);
+	if (err < 0)
+		return err;
+
+	if (cda[CTA_EXPECT_ZONE]) {
+		err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone);
+		if (err < 0)
+			return err;
+	}
+
+	h = nf_conntrack_find_get(net, zone, &tuple);
+	if (!h)
+		return -ENOENT;
+
+	ct = nf_ct_tuplehash_to_ctrack(h);
+	c.data = ct;
+
+	err = netlink_dump_start(ctnl, skb, nlh, &c);
+	nf_ct_put(ct);
+
+	return err;
+}
+
 static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = {
 	[CTA_EXPECT_MASTER]	= { .type = NLA_NESTED },
 	[CTA_EXPECT_TUPLE]	= { .type = NLA_NESTED },
@@ -2439,12 +2525,16 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb,
 	int err;
 
 	if (nlh->nlmsg_flags & NLM_F_DUMP) {
+		if (cda[CTA_EXPECT_MASTER])
+			return ctnetlink_dump_exp_ct(ctnl, skb, nlh, cda);
+		else {
 			struct netlink_dump_control c = {
 				.dump = ctnetlink_exp_dump_table,
 				.done = ctnetlink_exp_done,
 			};
 			return netlink_dump_start(ctnl, skb, nlh, &c);
 		}
+	}
 
 	err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone);
 	if (err < 0)

net/netfilter/nf_conntrack_standalone.c

@@ -545,16 +545,20 @@ out_init:
 	return ret;
 }
 
-static void nf_conntrack_pernet_exit(struct net *net)
+static void nf_conntrack_pernet_exit(struct list_head *net_exit_list)
 {
+	struct net *net;
+
+	list_for_each_entry(net, net_exit_list, exit_list) {
 		nf_conntrack_standalone_fini_sysctl(net);
 		nf_conntrack_standalone_fini_proc(net);
-	nf_conntrack_cleanup_net(net);
+	}
+	nf_conntrack_cleanup_net_list(net_exit_list);
 }
 
 static struct pernet_operations nf_conntrack_net_ops = {
 	.init		= nf_conntrack_pernet_init,
-	.exit = nf_conntrack_pernet_exit,
+	.exit_batch	= nf_conntrack_pernet_exit,
 };
 
 static int __init nf_conntrack_standalone_init(void)

net/netfilter/nfnetlink_queue_core.c

@@ -73,7 +73,7 @@ static struct hlist_head instance_table[INSTANCE_BUCKETS] __read_mostly;
 
 static inline u_int8_t instance_hashfn(u_int16_t queue_num)
 {
-	return ((queue_num >> 8) | queue_num) % INSTANCE_BUCKETS;
+	return ((queue_num >> 8) ^ queue_num) % INSTANCE_BUCKETS;
 }
 
 static struct nfqnl_instance *
@@ -217,14 +217,59 @@ nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn, unsigned long data)
 	spin_unlock_bh(&queue->lock);
 }
 
+static void
+nfqnl_zcopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen)
+{
+	int i, j = 0;
+	int plen = 0; /* length of skb->head fragment */
+	struct page *page;
+	unsigned int offset;
+
+	/* dont bother with small payloads */
+	if (len <= skb_tailroom(to)) {
+		skb_copy_bits(from, 0, skb_put(to, len), len);
+		return;
+	}
+
+	if (hlen) {
+		skb_copy_bits(from, 0, skb_put(to, hlen), hlen);
+		len -= hlen;
+	} else {
+		plen = min_t(int, skb_headlen(from), len);
+		if (plen) {
+			page = virt_to_head_page(from->head);
+			offset = from->data - (unsigned char *)page_address(page);
+			__skb_fill_page_desc(to, 0, page, offset, plen);
+			get_page(page);
+			j = 1;
+			len -= plen;
+		}
+	}
+
+	to->truesize += len + plen;
+	to->len += len + plen;
+	to->data_len += len + plen;
+
+	for (i = 0; i < skb_shinfo(from)->nr_frags; i++) {
+		if (!len)
+			break;
+		skb_shinfo(to)->frags[j] = skb_shinfo(from)->frags[i];
+		skb_shinfo(to)->frags[j].size = min_t(int, skb_shinfo(to)->frags[j].size, len);
+		len -= skb_shinfo(to)->frags[j].size;
+		skb_frag_ref(to, j);
+		j++;
+	}
+	skb_shinfo(to)->nr_frags = j;
+}
+
 static struct sk_buff *
 nfqnl_build_packet_message(struct nfqnl_instance *queue,
 			   struct nf_queue_entry *entry,
 			   __be32 **packet_id_ptr)
 {
-	sk_buff_data_t old_tail;
 	size_t size;
 	size_t data_len = 0, cap_len = 0;
+	int hlen = 0;
 	struct sk_buff *skb;
 	struct nlattr *nla;
 	struct nfqnl_msg_packet_hdr *pmsg;
@@ -246,8 +291,10 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue,
 #endif
 		+ nla_total_size(sizeof(u_int32_t))	/* mark */
 		+ nla_total_size(sizeof(struct nfqnl_msg_packet_hw))
-		+ nla_total_size(sizeof(struct nfqnl_msg_packet_timestamp)
+		+ nla_total_size(sizeof(u_int32_t));	/* cap_len */
-		+ nla_total_size(sizeof(u_int32_t)));	/* cap_len */
+
+	if (entskb->tstamp.tv64)
+		size += nla_total_size(sizeof(struct nfqnl_msg_packet_timestamp));
 
 	outdev = entry->outdev;
 
@@ -265,7 +312,16 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue,
 		if (data_len == 0 || data_len > entskb->len)
 			data_len = entskb->len;
 
-		size += nla_total_size(data_len);
+
+		if (!entskb->head_frag ||
+		    skb_headlen(entskb) < L1_CACHE_BYTES ||
+		    skb_shinfo(entskb)->nr_frags >= MAX_SKB_FRAGS)
+			hlen = skb_headlen(entskb);
+
+		if (skb_has_frag_list(entskb))
+			hlen = entskb->len;
+		hlen = min_t(int, data_len, hlen);
+		size += sizeof(struct nlattr) + hlen;
 		cap_len = entskb->len;
 		break;
 	}
@@ -277,7 +333,6 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue,
 	if (!skb)
 		return NULL;
 
-	old_tail = skb->tail;
 	nlh = nlmsg_put(skb, 0, 0,
 			NFNL_SUBSYS_QUEUE << 8 | NFQNL_MSG_PACKET,
 			sizeof(struct nfgenmsg), 0);
@@ -382,31 +437,26 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue,
 			goto nla_put_failure;
 	}
 
-	if (data_len) {
-		struct nlattr *nla;
-		int sz = nla_attr_size(data_len);
-
-		if (skb_tailroom(skb) < nla_total_size(data_len)) {
-			printk(KERN_WARNING "nf_queue: no tailroom!\n");
-			kfree_skb(skb);
-			return NULL;
-		}
-
-		nla = (struct nlattr *)skb_put(skb, nla_total_size(data_len));
-		nla->nla_type = NFQA_PAYLOAD;
-		nla->nla_len = sz;
-
-		if (skb_copy_bits(entskb, 0, nla_data(nla), data_len))
-			BUG();
-	}
-
 	if (ct && nfqnl_ct_put(skb, ct, ctinfo) < 0)
 		goto nla_put_failure;
 
 	if (cap_len > 0 && nla_put_be32(skb, NFQA_CAP_LEN, htonl(cap_len)))
 		goto nla_put_failure;
 
-	nlh->nlmsg_len = skb->tail - old_tail;
+	if (data_len) {
+		struct nlattr *nla;
+
+		if (skb_tailroom(skb) < sizeof(*nla) + hlen)
+			goto nla_put_failure;
+
+		nla = (struct nlattr *)skb_put(skb, sizeof(*nla));
+		nla->nla_type = NFQA_PAYLOAD;
+		nla->nla_len = nla_attr_size(data_len);
+
+		nfqnl_zcopy(skb, entskb, data_len, hlen);
+	}
+
+	nlh->nlmsg_len = skb->len;
 	return skb;
 
 nla_put_failure: