Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next

Pablo Neira Ayuso says:

====================
This is another batch containing Netfilter/IPVS updates for your net-next
tree, they are:

* Six patches to make the ipt_CLUSTERIP target support netnamespace,
  from Gao feng.

* Two cleanups for the nf_conntrack_acct infrastructure, introducing
  a new structure to encapsulate conntrack counters, from Holger
  Eitzenberger.

* Fix missing verdict in SCTP support for IPVS, from Daniel Borkmann.

* Skip checksum recalculation in SCTP support for IPVS, also from
  Daniel Borkmann.

* Fix behavioural change in xt_socket after IP early demux, from
  Florian Westphal.

* Fix bogus large memory allocation in the bitmap port set type in ipset,
  from Jozsef Kadlecsik.

* Fix possible compilation issues in the hash netnet set type in ipset,
  also from Jozsef Kadlecsik.

* Define constants to identify netlink callback data in ipset dumps,
  again from Jozsef Kadlecsik.

* Use sock_gen_put() in xt_socket to replace xt_socket_put_sk,
  from Eric Dumazet.

* Improvements for the SH scheduler in IPVS, from Alexander Frolkin.

* Remove extra delay due to unneeded rcu barrier in IPVS net namespace
  cleanup path, from Julian Anastasov.

* Save some cycles in ip6t_REJECT by skipping checksum validation in
  packets leaving from our stack, from Stanislav Fomichev.

* Fix IPVS_CMD_ATTR_MAX definition in IPVS, larger that required, from
  Julian Anastasov.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

include/linux/netfilter/ipset/ip_set.h

@@ -316,6 +316,16 @@ ip_set_init_counter(struct ip_set_counter *counter,
 		atomic64_set(&(counter)->packets, (long long)(ext->packets));
 }
 
+/* Netlink CB args */
+enum {
+	IPSET_CB_NET = 0,
+	IPSET_CB_DUMP,
+	IPSET_CB_INDEX,
+	IPSET_CB_ARG0,
+	IPSET_CB_ARG1,
+	IPSET_CB_ARG2,
+};
+
 /* register and unregister set references */
 extern ip_set_id_t ip_set_get_byname(struct net *net,
 				     const char *name, struct ip_set **set);

include/net/ip_vs.h

@@ -1442,6 +1442,12 @@ static inline void ip_vs_dest_put(struct ip_vs_dest *dest)
 	atomic_dec(&dest->refcnt);
 }
 
+static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest)
+{
+	if (atomic_dec_return(&dest->refcnt) < 0)
+		kfree(dest);
+}
+
 /*
  *      IPVS sync daemon data and function prototypes
  *      (from ip_vs_sync.c)

include/net/netfilter/nf_conntrack_acct.h

@@ -19,17 +19,21 @@ struct nf_conn_counter {
 	atomic64_t bytes;
 };
 
+struct nf_conn_acct {
+	struct nf_conn_counter counter[IP_CT_DIR_MAX];
+};
+
 static inline
-struct nf_conn_counter *nf_conn_acct_find(const struct nf_conn *ct)
+struct nf_conn_acct *nf_conn_acct_find(const struct nf_conn *ct)
 {
 	return nf_ct_ext_find(ct, NF_CT_EXT_ACCT);
 }
 
 static inline
-struct nf_conn_counter *nf_ct_acct_ext_add(struct nf_conn *ct, gfp_t gfp)
+struct nf_conn_acct *nf_ct_acct_ext_add(struct nf_conn *ct, gfp_t gfp)
 {
 	struct net *net = nf_ct_net(ct);
-	struct nf_conn_counter *acct;
+	struct nf_conn_acct *acct;
 
 	if (!net->ct.sysctl_acct)
 		return NULL;

include/net/netfilter/nf_conntrack_extend.h

@@ -36,7 +36,7 @@ enum nf_ct_ext_id {
 #define NF_CT_EXT_HELPER_TYPE struct nf_conn_help
 #define NF_CT_EXT_NAT_TYPE struct nf_conn_nat
 #define NF_CT_EXT_SEQADJ_TYPE struct nf_conn_seqadj
-#define NF_CT_EXT_ACCT_TYPE struct nf_conn_counter
+#define NF_CT_EXT_ACCT_TYPE struct nf_conn_acct
 #define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache
 #define NF_CT_EXT_ZONE_TYPE struct nf_conntrack_zone
 #define NF_CT_EXT_TSTAMP_TYPE struct nf_conn_tstamp

include/uapi/linux/ip_vs.h

@@ -334,7 +334,7 @@ enum {
 	__IPVS_CMD_ATTR_MAX,
 };
 
-#define IPVS_CMD_ATTR_MAX (__IPVS_SVC_ATTR_MAX - 1)
+#define IPVS_CMD_ATTR_MAX (__IPVS_CMD_ATTR_MAX - 1)
 
 /*
  * Attributes used to describe a service

net/bridge/br_netfilter.c

@@ -559,6 +559,8 @@ static struct net_device *setup_pre_routing(struct sk_buff *skb)
 	else if (skb->protocol == htons(ETH_P_PPP_SES))
 		nf_bridge->mask |= BRNF_PPPoE;
 
+	/* Must drop socket now because of tproxy. */
+	skb_orphan(skb);
 	return skb->dev;
 }
 

net/ipv4/netfilter/ipt_CLUSTERIP.c

@@ -28,6 +28,7 @@
 #include <linux/netfilter_ipv4/ipt_CLUSTERIP.h>
 #include <net/netfilter/nf_conntrack.h>
 #include <net/net_namespace.h>
+#include <net/netns/generic.h>
 #include <net/checksum.h>
 #include <net/ip.h>
 
@@ -57,15 +58,21 @@ struct clusterip_config {
 	struct rcu_head rcu;
 };
 
-static LIST_HEAD(clusterip_configs);
+#ifdef CONFIG_PROC_FS
+static const struct file_operations clusterip_proc_fops;
+#endif
 
-/* clusterip_lock protects the clusterip_configs list */
-static DEFINE_SPINLOCK(clusterip_lock);
+static int clusterip_net_id __read_mostly;
+
+struct clusterip_net {
+	struct list_head configs;
+	/* lock protects the configs list */
+	spinlock_t lock;
 
 #ifdef CONFIG_PROC_FS
-static const struct file_operations clusterip_proc_fops;
-static struct proc_dir_entry *clusterip_procdir;
+	struct proc_dir_entry *procdir;
 #endif
+};
 
 static inline void
 clusterip_config_get(struct clusterip_config *c)
@@ -92,10 +99,13 @@ clusterip_config_put(struct clusterip_config *c)
 static inline void
 clusterip_config_entry_put(struct clusterip_config *c)
 {
+	struct net *net = dev_net(c->dev);
+	struct clusterip_net *cn = net_generic(net, clusterip_net_id);
+
 	local_bh_disable();
-	if (atomic_dec_and_lock(&c->entries, &clusterip_lock)) {
+	if (atomic_dec_and_lock(&c->entries, &cn->lock)) {
 		list_del_rcu(&c->list);
-		spin_unlock(&clusterip_lock);
+		spin_unlock(&cn->lock);
 		local_bh_enable();
 
 		dev_mc_del(c->dev, c->clustermac);
@@ -113,11 +123,12 @@ clusterip_config_entry_put(struct clusterip_config *c)
 }
 
 static struct clusterip_config *
-__clusterip_config_find(__be32 clusterip)
+__clusterip_config_find(struct net *net, __be32 clusterip)
 {
 	struct clusterip_config *c;
+	struct clusterip_net *cn = net_generic(net, clusterip_net_id);
 
-	list_for_each_entry_rcu(c, &clusterip_configs, list) {
+	list_for_each_entry_rcu(c, &cn->configs, list) {
 		if (c->clusterip == clusterip)
 			return c;
 	}
@@ -126,12 +137,12 @@ __clusterip_config_find(__be32 clusterip)
 }
 
 static inline struct clusterip_config *
-clusterip_config_find_get(__be32 clusterip, int entry)
+clusterip_config_find_get(struct net *net, __be32 clusterip, int entry)
 {
 	struct clusterip_config *c;
 
 	rcu_read_lock_bh();
-	c = __clusterip_config_find(clusterip);
+	c = __clusterip_config_find(net, clusterip);
 	if (c) {
 		if (unlikely(!atomic_inc_not_zero(&c->refcount)))
 			c = NULL;
@@ -158,6 +169,7 @@ clusterip_config_init(const struct ipt_clusterip_tgt_info *i, __be32 ip,
 			struct net_device *dev)
 {
 	struct clusterip_config *c;
+	struct clusterip_net *cn = net_generic(dev_net(dev), clusterip_net_id);
 
 	c = kzalloc(sizeof(*c), GFP_ATOMIC);
 	if (!c)
@@ -180,7 +192,7 @@ clusterip_config_init(const struct ipt_clusterip_tgt_info *i, __be32 ip,
 		/* create proc dir entry */
 		sprintf(buffer, "%pI4", &ip);
 		c->pde = proc_create_data(buffer, S_IWUSR|S_IRUSR,
-					  clusterip_procdir,
+					  cn->procdir,
 					  &clusterip_proc_fops, c);
 		if (!c->pde) {
 			kfree(c);
@@ -189,9 +201,9 @@ clusterip_config_init(const struct ipt_clusterip_tgt_info *i, __be32 ip,
 	}
 #endif
 
-	spin_lock_bh(&clusterip_lock);
-	list_add_rcu(&c->list, &clusterip_configs);
-	spin_unlock_bh(&clusterip_lock);
+	spin_lock_bh(&cn->lock);
+	list_add_rcu(&c->list, &cn->configs);
+	spin_unlock_bh(&cn->lock);
 
 	return c;
 }
@@ -370,7 +382,7 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par)
 
 	/* FIXME: further sanity checks */
 
-	config = clusterip_config_find_get(e->ip.dst.s_addr, 1);
+	config = clusterip_config_find_get(par->net, e->ip.dst.s_addr, 1);
 	if (!config) {
 		if (!(cipinfo->flags & CLUSTERIP_FLAG_NEW)) {
 			pr_info("no config found for %pI4, need 'new'\n",
@@ -384,7 +396,7 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par)
 				return -EINVAL;
 			}
 
-			dev = dev_get_by_name(&init_net, e->ip.iniface);
+			dev = dev_get_by_name(par->net, e->ip.iniface);
 			if (!dev) {
 				pr_info("no such interface %s\n",
 					e->ip.iniface);
@@ -492,6 +504,7 @@ arp_mangle(const struct nf_hook_ops *ops,
 	struct arphdr *arp = arp_hdr(skb);
 	struct arp_payload *payload;
 	struct clusterip_config *c;
+	struct net *net = dev_net(in ? in : out);
 
 	/* we don't care about non-ethernet and non-ipv4 ARP */
 	if (arp->ar_hrd != htons(ARPHRD_ETHER) ||
@@ -508,7 +521,7 @@ arp_mangle(const struct nf_hook_ops *ops,
 
 	/* if there is no clusterip configuration for the arp reply's
 	 * source ip, we don't want to mangle it */
-	c = clusterip_config_find_get(payload->src_ip, 0);
+	c = clusterip_config_find_get(net, payload->src_ip, 0);
 	if (!c)
 		return NF_ACCEPT;
 
@@ -698,48 +711,75 @@ static const struct file_operations clusterip_proc_fops = {
 
 #endif /* CONFIG_PROC_FS */
 
+static int clusterip_net_init(struct net *net)
+{
+	struct clusterip_net *cn = net_generic(net, clusterip_net_id);
+
+	INIT_LIST_HEAD(&cn->configs);
+
+	spin_lock_init(&cn->lock);
+
+#ifdef CONFIG_PROC_FS
+	cn->procdir = proc_mkdir("ipt_CLUSTERIP", net->proc_net);
+	if (!cn->procdir) {
+		pr_err("Unable to proc dir entry\n");
+		return -ENOMEM;
+	}
+#endif /* CONFIG_PROC_FS */
+
+	return 0;
+}
+
+static void clusterip_net_exit(struct net *net)
+{
+#ifdef CONFIG_PROC_FS
+	struct clusterip_net *cn = net_generic(net, clusterip_net_id);
+	proc_remove(cn->procdir);
+#endif
+}
+
+static struct pernet_operations clusterip_net_ops = {
+	.init = clusterip_net_init,
+	.exit = clusterip_net_exit,
+	.id   = &clusterip_net_id,
+	.size = sizeof(struct clusterip_net),
+};
+
 static int __init clusterip_tg_init(void)
 {
 	int ret;
 
-	ret = xt_register_target(&clusterip_tg_reg);
+	ret = register_pernet_subsys(&clusterip_net_ops);
 	if (ret < 0)
 		return ret;
 
+	ret = xt_register_target(&clusterip_tg_reg);
+	if (ret < 0)
+		goto cleanup_subsys;
+
 	ret = nf_register_hook(&cip_arp_ops);
 	if (ret < 0)
 		goto cleanup_target;
 
-#ifdef CONFIG_PROC_FS
-	clusterip_procdir = proc_mkdir("ipt_CLUSTERIP", init_net.proc_net);
-	if (!clusterip_procdir) {
-		pr_err("Unable to proc dir entry\n");
-		ret = -ENOMEM;
-		goto cleanup_hook;
-	}
-#endif /* CONFIG_PROC_FS */
-
 	pr_info("ClusterIP Version %s loaded successfully\n",
 		CLUSTERIP_VERSION);
+
 	return 0;
 
-#ifdef CONFIG_PROC_FS
-cleanup_hook:
-	nf_unregister_hook(&cip_arp_ops);
-#endif /* CONFIG_PROC_FS */
 cleanup_target:
 	xt_unregister_target(&clusterip_tg_reg);
+cleanup_subsys:
+	unregister_pernet_subsys(&clusterip_net_ops);
 	return ret;
 }
 
 static void __exit clusterip_tg_exit(void)
 {
 	pr_info("ClusterIP Version %s unloading\n", CLUSTERIP_VERSION);
-#ifdef CONFIG_PROC_FS
-	proc_remove(clusterip_procdir);
-#endif
+
 	nf_unregister_hook(&cip_arp_ops);
 	xt_unregister_target(&clusterip_tg_reg);
+	unregister_pernet_subsys(&clusterip_net_ops);
 
 	/* Wait for completion of call_rcu_bh()'s (clusterip_config_rcu_free) */
 	rcu_barrier_bh();

net/ipv6/netfilter/ip6t_REJECT.c

@@ -39,7 +39,7 @@ MODULE_DESCRIPTION("Xtables: packet \"rejection\" target for IPv6");
 MODULE_LICENSE("GPL");
 
 /* Send RST reply */
-static void send_reset(struct net *net, struct sk_buff *oldskb)
+static void send_reset(struct net *net, struct sk_buff *oldskb, int hook)
 {
 	struct sk_buff *nskb;
 	struct tcphdr otcph, *tcph;
@@ -88,8 +88,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb)
 	}
 
 	/* Check checksum. */
-	if (csum_ipv6_magic(&oip6h->saddr, &oip6h->daddr, otcplen, IPPROTO_TCP,
-			    skb_checksum(oldskb, tcphoff, otcplen, 0))) {
+	if (nf_ip6_checksum(oldskb, hook, tcphoff, IPPROTO_TCP)) {
 		pr_debug("TCP checksum is invalid\n");
 		return;
 	}
@@ -227,7 +226,7 @@ reject_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 		/* Do nothing */
 		break;
 	case IP6T_TCP_RESET:
-		send_reset(net, skb);
+		send_reset(net, skb, par->hooknum);
 		break;
 	default:
 		net_info_ratelimited("case %u not handled yet\n", reject->with);

net/netfilter/ipset/ip_set_bitmap_gen.h

@@ -198,13 +198,14 @@ mtype_list(const struct ip_set *set,
 	struct mtype *map = set->data;
 	struct nlattr *adt, *nested;
 	void *x;
-	u32 id, first = cb->args[2];
+	u32 id, first = cb->args[IPSET_CB_ARG0];
 
 	adt = ipset_nest_start(skb, IPSET_ATTR_ADT);
 	if (!adt)
 		return -EMSGSIZE;
-	for (; cb->args[2] < map->elements; cb->args[2]++) {
-		id = cb->args[2];
+	for (; cb->args[IPSET_CB_ARG0] < map->elements;
+	     cb->args[IPSET_CB_ARG0]++) {
+		id = cb->args[IPSET_CB_ARG0];
 		x = get_ext(set, map, id);
 		if (!test_bit(id, map->members) ||
 		    (SET_WITH_TIMEOUT(set) &&
@@ -231,14 +232,14 @@ mtype_list(const struct ip_set *set,
 	ipset_nest_end(skb, adt);
 
 	/* Set listing finished */
-	cb->args[2] = 0;
+	cb->args[IPSET_CB_ARG0] = 0;
 
 	return 0;
 
 nla_put_failure:
 	nla_nest_cancel(skb, nested);
 	if (unlikely(id == first)) {
-		cb->args[2] = 0;
+		cb->args[IPSET_CB_ARG0] = 0;
 		return -EMSGSIZE;
 	}
 	ipset_nest_end(skb, adt);

net/netfilter/ipset/ip_set_bitmap_port.c

@@ -254,7 +254,7 @@ bitmap_port_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
 		return -ENOMEM;
 
 	map->elements = last_port - first_port + 1;
-	map->memsize = map->elements * sizeof(unsigned long);
+	map->memsize = bitmap_bytes(0, map->elements);
 	set->variant = &bitmap_port;
 	set->dsize = ip_set_elem_len(set, tb, 0);
 	if (!init_map_port(set, map, first_port, last_port)) {

net/netfilter/ipset/ip_set_core.c

@@ -1182,10 +1182,12 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb,
 static int
 ip_set_dump_done(struct netlink_callback *cb)
 {
-	struct ip_set_net *inst = (struct ip_set_net *)cb->data;
-	if (cb->args[2]) {
-		pr_debug("release set %s\n", nfnl_set(inst, cb->args[1])->name);
-		__ip_set_put_byindex(inst, (ip_set_id_t) cb->args[1]);
+	struct ip_set_net *inst = (struct ip_set_net *)cb->args[IPSET_CB_NET];
+	if (cb->args[IPSET_CB_ARG0]) {
+		pr_debug("release set %s\n",
+			 nfnl_set(inst, cb->args[IPSET_CB_INDEX])->name);
+		__ip_set_put_byindex(inst,
+			(ip_set_id_t) cb->args[IPSET_CB_INDEX]);
 	}
 	return 0;
 }
@@ -1203,7 +1205,7 @@ dump_attrs(struct nlmsghdr *nlh)
 }
 
 static int
-dump_init(struct netlink_callback *cb)
+dump_init(struct netlink_callback *cb, struct ip_set_net *inst)
 {
 	struct nlmsghdr *nlh = nlmsg_hdr(cb->skb);
 	int min_len = nlmsg_total_size(sizeof(struct nfgenmsg));
@@ -1211,15 +1213,15 @@ dump_init(struct netlink_callback *cb)
 	struct nlattr *attr = (void *)nlh + min_len;
 	u32 dump_type;
 	ip_set_id_t index;
-	struct ip_set_net *inst = (struct ip_set_net *)cb->data;
 
 	/* Second pass, so parser can't fail */
 	nla_parse(cda, IPSET_ATTR_CMD_MAX,
 		  attr, nlh->nlmsg_len - min_len, ip_set_setname_policy);
 
-	/* cb->args[0] : dump single set/all sets
-	 *         [1] : set index
-	 *         [..]: type specific
+	/* cb->args[IPSET_CB_NET]:	net namespace
+	 *         [IPSET_CB_DUMP]:	dump single set/all sets
+	 *         [IPSET_CB_INDEX]: 	set index
+	 *         [IPSET_CB_ARG0]:	type specific
 	 */
 
 	if (cda[IPSET_ATTR_SETNAME]) {
@@ -1231,7 +1233,7 @@ dump_init(struct netlink_callback *cb)
 			return -ENOENT;
 
 		dump_type = DUMP_ONE;
-		cb->args[1] = index;
+		cb->args[IPSET_CB_INDEX] = index;
 	} else
 		dump_type = DUMP_ALL;
 
@@ -1239,7 +1241,8 @@ dump_init(struct netlink_callback *cb)
 		u32 f = ip_set_get_h32(cda[IPSET_ATTR_FLAGS]);
 		dump_type |= (f << 16);
 	}
-	cb->args[0] = dump_type;
+	cb->args[IPSET_CB_NET] = (unsigned long)inst;
+	cb->args[IPSET_CB_DUMP] = dump_type;
 
 	return 0;
 }
@@ -1251,12 +1254,12 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
 	struct ip_set *set = NULL;
 	struct nlmsghdr *nlh = NULL;
 	unsigned int flags = NETLINK_CB(cb->skb).portid ? NLM_F_MULTI : 0;
+	struct ip_set_net *inst = ip_set_pernet(sock_net(skb->sk));
 	u32 dump_type, dump_flags;
 	int ret = 0;
-	struct ip_set_net *inst = (struct ip_set_net *)cb->data;
 
-	if (!cb->args[0]) {
-		ret = dump_init(cb);
+	if (!cb->args[IPSET_CB_DUMP]) {
+		ret = dump_init(cb, inst);
 		if (ret < 0) {
 			nlh = nlmsg_hdr(cb->skb);
 			/* We have to create and send the error message
@@ -1267,17 +1270,18 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
 		}
 	}
 
-	if (cb->args[1] >= inst->ip_set_max)
+	if (cb->args[IPSET_CB_INDEX] >= inst->ip_set_max)
 		goto out;
 
-	dump_type = DUMP_TYPE(cb->args[0]);
-	dump_flags = DUMP_FLAGS(cb->args[0]);
-	max = dump_type == DUMP_ONE ? cb->args[1] + 1 : inst->ip_set_max;
+	dump_type = DUMP_TYPE(cb->args[IPSET_CB_DUMP]);
+	dump_flags = DUMP_FLAGS(cb->args[IPSET_CB_DUMP]);
+	max = dump_type == DUMP_ONE ? cb->args[IPSET_CB_INDEX] + 1
+				    : inst->ip_set_max;
 dump_last:
-	pr_debug("args[0]: %u %u args[1]: %ld\n",
-		 dump_type, dump_flags, cb->args[1]);
-	for (; cb->args[1] < max; cb->args[1]++) {
-		index = (ip_set_id_t) cb->args[1];
+	pr_debug("dump type, flag: %u %u index: %ld\n",
+		 dump_type, dump_flags, cb->args[IPSET_CB_INDEX]);
+	for (; cb->args[IPSET_CB_INDEX] < max; cb->args[IPSET_CB_INDEX]++) {
+		index = (ip_set_id_t) cb->args[IPSET_CB_INDEX];
 		set = nfnl_set(inst, index);
 		if (set == NULL) {
 			if (dump_type == DUMP_ONE) {
@@ -1294,7 +1298,7 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
 		     !!(set->type->features & IPSET_DUMP_LAST)))
 			continue;
 		pr_debug("List set: %s\n", set->name);
-		if (!cb->args[2]) {
+		if (!cb->args[IPSET_CB_ARG0]) {
 			/* Start listing: make sure set won't be destroyed */
 			pr_debug("reference set\n");
 			__ip_set_get(set);
@@ -1311,7 +1315,7 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
 			goto nla_put_failure;
 		if (dump_flags & IPSET_FLAG_LIST_SETNAME)
 			goto next_set;
-		switch (cb->args[2]) {
+		switch (cb->args[IPSET_CB_ARG0]) {
 		case 0:
 			/* Core header data */
 			if (nla_put_string(skb, IPSET_ATTR_TYPENAME,
@@ -1331,7 +1335,7 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
 			read_lock_bh(&set->lock);
 			ret = set->variant->list(set, skb, cb);
 			read_unlock_bh(&set->lock);
-			if (!cb->args[2])
+			if (!cb->args[IPSET_CB_ARG0])
 				/* Set is done, proceed with next one */
 				goto next_set;
 			goto release_refcount;
@@ -1340,8 +1344,8 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
 	/* If we dump all sets, continue with dumping last ones */
 	if (dump_type == DUMP_ALL) {
 		dump_type = DUMP_LAST;
-		cb->args[0] = dump_type | (dump_flags << 16);
-		cb->args[1] = 0;
+		cb->args[IPSET_CB_DUMP] = dump_type | (dump_flags << 16);
+		cb->args[IPSET_CB_INDEX] = 0;
 		goto dump_last;
 	}
 	goto out;
@@ -1350,15 +1354,15 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
 	ret = -EFAULT;
 next_set:
 	if (dump_type == DUMP_ONE)
-		cb->args[1] = IPSET_INVALID_ID;
+		cb->args[IPSET_CB_INDEX] = IPSET_INVALID_ID;
 	else
-		cb->args[1]++;
+		cb->args[IPSET_CB_INDEX]++;
 release_refcount:
 	/* If there was an error or set is done, release set */
-	if (ret || !cb->args[2]) {
+	if (ret || !cb->args[IPSET_CB_ARG0]) {
 		pr_debug("release set %s\n", nfnl_set(inst, index)->name);
 		__ip_set_put_byindex(inst, index);
-		cb->args[2] = 0;
+		cb->args[IPSET_CB_ARG0] = 0;
 	}
 out:
 	if (nlh) {
@@ -1375,8 +1379,6 @@ ip_set_dump(struct sock *ctnl, struct sk_buff *skb,
 	    const struct nlmsghdr *nlh,
 	    const struct nlattr * const attr[])
 {
-	struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
-
 	if (unlikely(protocol_failed(attr)))
 		return -IPSET_ERR_PROTOCOL;
 
@@ -1384,7 +1386,6 @@ ip_set_dump(struct sock *ctnl, struct sk_buff *skb,
 		struct netlink_dump_control c = {
 			.dump = ip_set_dump_start,
 			.done = ip_set_dump_done,
-			.data = (void *)inst
 		};
 		return netlink_dump_start(ctnl, skb, nlh, &c);
 	}
@@ -1961,7 +1962,6 @@ static int __net_init
 ip_set_net_init(struct net *net)
 {
 	struct ip_set_net *inst = ip_set_pernet(net);
-
 	struct ip_set **list;
 
 	inst->ip_set_max = max_sets ? max_sets : CONFIG_IP_SET_MAX;

net/netfilter/ipset/ip_set_hash_gen.h

@@ -234,7 +234,6 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize)
 #define mtype_uadt		IPSET_TOKEN(MTYPE, _uadt)
 #define mtype			MTYPE
 
-#define mtype_elem		IPSET_TOKEN(MTYPE, _elem)
 #define mtype_add		IPSET_TOKEN(MTYPE, _add)
 #define mtype_del		IPSET_TOKEN(MTYPE, _del)
 #define mtype_test_cidrs	IPSET_TOKEN(MTYPE, _test_cidrs)
@@ -931,7 +930,7 @@ mtype_list(const struct ip_set *set,
 	struct nlattr *atd, *nested;
 	const struct hbucket *n;
 	const struct mtype_elem *e;
-	u32 first = cb->args[2];
+	u32 first = cb->args[IPSET_CB_ARG0];
 	/* We assume that one hash bucket fills into one page */
 	void *incomplete;
 	int i;
@@ -940,20 +939,22 @@ mtype_list(const struct ip_set *set,
 	if (!atd)
 		return -EMSGSIZE;
 	pr_debug("list hash set %s\n", set->name);
-	for (; cb->args[2] < jhash_size(t->htable_bits); cb->args[2]++) {
+	for (; cb->args[IPSET_CB_ARG0] < jhash_size(t->htable_bits);
+	     cb->args[IPSET_CB_ARG0]++) {
 		incomplete = skb_tail_pointer(skb);
-		n = hbucket(t, cb->args[2]);
-		pr_debug("cb->args[2]: %lu, t %p n %p\n", cb->args[2], t, n);
+		n = hbucket(t, cb->args[IPSET_CB_ARG0]);
+		pr_debug("cb->arg bucket: %lu, t %p n %p\n",
+			 cb->args[IPSET_CB_ARG0], t, n);
 		for (i = 0; i < n->pos; i++) {
 			e = ahash_data(n, i, set->dsize);
 			if (SET_WITH_TIMEOUT(set) &&
 			    ip_set_timeout_expired(ext_timeout(e, set)))
 				continue;
 			pr_debug("list hash %lu hbucket %p i %u, data %p\n",
-				 cb->args[2], n, i, e);
+				 cb->args[IPSET_CB_ARG0], n, i, e);
 			nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
 			if (!nested) {
-				if (cb->args[2] == first) {
+				if (cb->args[IPSET_CB_ARG0] == first) {
 					nla_nest_cancel(skb, atd);
 					return -EMSGSIZE;
 				} else
@@ -968,16 +969,16 @@ mtype_list(const struct ip_set *set,
 	}
 	ipset_nest_end(skb, atd);
 	/* Set listing finished */
-	cb->args[2] = 0;
+	cb->args[IPSET_CB_ARG0] = 0;
 
 	return 0;
 
 nla_put_failure:
 	nlmsg_trim(skb, incomplete);
-	if (unlikely(first == cb->args[2])) {
+	if (unlikely(first == cb->args[IPSET_CB_ARG0])) {
 		pr_warning("Can't list set %s: one bucket does not fit into "
 			   "a message. Please report it!\n", set->name);
-		cb->args[2] = 0;
+		cb->args[IPSET_CB_ARG0] = 0;
 		return -EMSGSIZE;
 	}
 	ipset_nest_end(skb, atd);

net/netfilter/ipset/ip_set_hash_netnet.c

@@ -137,12 +137,11 @@ hash_netnet4_kadt(struct ip_set *set, const struct sk_buff *skb,
 {
 	const struct hash_netnet *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
-	struct hash_netnet4_elem e = {
-		.cidr[0] = h->nets[0].cidr[0] ? h->nets[0].cidr[0] : HOST_MASK,
-		.cidr[1] = h->nets[0].cidr[1] ? h->nets[0].cidr[1] : HOST_MASK,
-	};
+	struct hash_netnet4_elem e = { };
 	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 
+	e.cidr[0] = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK);
+	e.cidr[1] = IP_SET_INIT_CIDR(h->nets[0].cidr[1], HOST_MASK);
 	if (adt == IPSET_TEST)
 		e.ccmp = (HOST_MASK << (sizeof(e.cidr[0]) * 8)) | HOST_MASK;
 
@@ -160,14 +159,14 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 {
 	const struct hash_netnet *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
-	struct hash_netnet4_elem e = { .cidr[0] = HOST_MASK,
-				       .cidr[1] = HOST_MASK };
+	struct hash_netnet4_elem e = { };
 	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	u32 ip = 0, ip_to = 0, last;
 	u32 ip2 = 0, ip2_from = 0, ip2_to = 0, last2;
 	u8 cidr, cidr2;
 	int ret;
 
+	e.cidr[0] = e.cidr[1] = HOST_MASK;
 	if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] ||
 		     !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
 		     !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) ||
@@ -364,12 +363,11 @@ hash_netnet6_kadt(struct ip_set *set, const struct sk_buff *skb,
 {
 	const struct hash_netnet *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
-	struct hash_netnet6_elem e = {
-		.cidr[0] = h->nets[0].cidr[0] ? h->nets[0].cidr[0] : HOST_MASK,
-		.cidr[1] = h->nets[0].cidr[1] ? h->nets[0].cidr[1] : HOST_MASK
-	};
+	struct hash_netnet6_elem e = { };
 	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 
+	e.cidr[0] = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK);
+	e.cidr[1] = IP_SET_INIT_CIDR(h->nets[0].cidr[1], HOST_MASK);
 	if (adt == IPSET_TEST)
 		e.ccmp = (HOST_MASK << (sizeof(u8)*8)) | HOST_MASK;
 
@@ -386,11 +384,11 @@ hash_netnet6_uadt(struct ip_set *set, struct nlattr *tb[],
 	       enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
 {
 	ipset_adtfn adtfn = set->variant->adt[adt];
-	struct hash_netnet6_elem e = { .cidr[0] = HOST_MASK,
-				       .cidr[1] = HOST_MASK };
+	struct hash_netnet6_elem e = { };
 	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	int ret;
 
+	e.cidr[0] = e.cidr[1] = HOST_MASK;
 	if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] ||
 		     !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
 		     !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) ||

net/netfilter/ipset/ip_set_hash_netportnet.c

@@ -147,12 +147,11 @@ hash_netportnet4_kadt(struct ip_set *set, const struct sk_buff *skb,
 {
 	const struct hash_netportnet *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
-	struct hash_netportnet4_elem e = {
-		.cidr[0] = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
-		.cidr[1] = IP_SET_INIT_CIDR(h->nets[0].cidr[1], HOST_MASK),
-	};
+	struct hash_netportnet4_elem e = { };
 	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 
+	e.cidr[0] = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK);
+	e.cidr[1] = IP_SET_INIT_CIDR(h->nets[0].cidr[1], HOST_MASK);
 	if (adt == IPSET_TEST)
 		e.ccmp = (HOST_MASK << (sizeof(e.cidr[0]) * 8)) | HOST_MASK;
 
@@ -174,8 +173,7 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 {
 	const struct hash_netportnet *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
-	struct hash_netportnet4_elem e = { .cidr[0] = HOST_MASK,
-					   .cidr[1] = HOST_MASK };
+	struct hash_netportnet4_elem e = { };
 	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	u32 ip = 0, ip_to = 0, ip_last, p = 0, port, port_to;
 	u32 ip2_from = 0, ip2_to = 0, ip2_last, ip2;
@@ -183,6 +181,7 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 	u8 cidr, cidr2;
 	int ret;
 
+	e.cidr[0] = e.cidr[1] = HOST_MASK;
 	if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] ||
 		     !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) ||
 		     !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) ||
@@ -419,12 +418,11 @@ hash_netportnet6_kadt(struct ip_set *set, const struct sk_buff *skb,
 {
 	const struct hash_netportnet *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
-	struct hash_netportnet6_elem e = {
-		.cidr[0] = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
-		.cidr[1] = IP_SET_INIT_CIDR(h->nets[0].cidr[1], HOST_MASK),
-	};
+	struct hash_netportnet6_elem e = { };
 	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 
+	e.cidr[0] = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK);
+	e.cidr[1] = IP_SET_INIT_CIDR(h->nets[0].cidr[1], HOST_MASK);
 	if (adt == IPSET_TEST)
 		e.ccmp = (HOST_MASK << (sizeof(u8) * 8)) | HOST_MASK;
 
@@ -446,13 +444,13 @@ hash_netportnet6_uadt(struct ip_set *set, struct nlattr *tb[],
 {
 	const struct hash_netportnet *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
-	struct hash_netportnet6_elem e = { .cidr[0] = HOST_MASK,
-					   .cidr[1] = HOST_MASK };
+	struct hash_netportnet6_elem e = { };
 	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	u32 port, port_to;
 	bool with_ports = false;
 	int ret;
 
+	e.cidr[0] = e.cidr[1] = HOST_MASK;
 	if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] ||
 		     !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) ||
 		     !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) ||

net/netfilter/ipset/ip_set_list_set.c

@@ -490,14 +490,15 @@ list_set_list(const struct ip_set *set,
 {
 	const struct list_set *map = set->data;
 	struct nlattr *atd, *nested;
-	u32 i, first = cb->args[2];
+	u32 i, first = cb->args[IPSET_CB_ARG0];
 	const struct set_elem *e;
 
 	atd = ipset_nest_start(skb, IPSET_ATTR_ADT);
 	if (!atd)
 		return -EMSGSIZE;
-	for (; cb->args[2] < map->size; cb->args[2]++) {
-		i = cb->args[2];
+	for (; cb->args[IPSET_CB_ARG0] < map->size;
+	     cb->args[IPSET_CB_ARG0]++) {
+		i = cb->args[IPSET_CB_ARG0];
 		e = list_set_elem(set, map, i);
 		if (e->id == IPSET_INVALID_ID)
 			goto finish;
@@ -522,13 +523,13 @@ list_set_list(const struct ip_set *set,
 finish:
 	ipset_nest_end(skb, atd);
 	/* Set listing finished */
-	cb->args[2] = 0;
+	cb->args[IPSET_CB_ARG0] = 0;
 	return 0;
 
 nla_put_failure:
 	nla_nest_cancel(skb, nested);
 	if (unlikely(i == first)) {
-		cb->args[2] = 0;
+		cb->args[IPSET_CB_ARG0] = 0;
 		return -EMSGSIZE;
 	}
 	ipset_nest_end(skb, atd);

net/netfilter/ipvs/ip_vs_ctl.c

@@ -704,7 +704,7 @@ static void ip_vs_dest_free(struct ip_vs_dest *dest)
 	__ip_vs_dst_cache_reset(dest);
 	__ip_vs_svc_put(svc, false);
 	free_percpu(dest->stats.cpustats);
-	kfree(dest);
+	ip_vs_dest_put_and_free(dest);
 }
 
 /*
@@ -3820,10 +3820,6 @@ void __net_exit ip_vs_control_net_cleanup(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
-	/* Some dest can be in grace period even before cleanup, we have to
-	 * defer ip_vs_trash_cleanup until ip_vs_dest_wait_readers is called.
-	 */
-	rcu_barrier();
 	ip_vs_trash_cleanup(net);
 	ip_vs_stop_estimator(net, &ipvs->tot_stats);
 	ip_vs_control_net_cleanup_sysctl(net);

net/netfilter/ipvs/ip_vs_lblc.c

@@ -136,7 +136,7 @@ static void ip_vs_lblc_rcu_free(struct rcu_head *head)
 						   struct ip_vs_lblc_entry,
 						   rcu_head);
 
-	ip_vs_dest_put(en->dest);
+	ip_vs_dest_put_and_free(en->dest);
 	kfree(en);
 }
 

net/netfilter/ipvs/ip_vs_lblcr.c

@@ -130,7 +130,7 @@ static void ip_vs_lblcr_elem_rcu_free(struct rcu_head *head)
 	struct ip_vs_dest_set_elem *e;
 
 	e = container_of(head, struct ip_vs_dest_set_elem, rcu_head);
-	ip_vs_dest_put(e->dest);
+	ip_vs_dest_put_and_free(e->dest);
 	kfree(e);
 }
 

net/netfilter/ipvs/ip_vs_proto_sctp.c

@@ -20,13 +20,18 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 	sctp_sctphdr_t *sh, _sctph;
 
 	sh = skb_header_pointer(skb, iph->len, sizeof(_sctph), &_sctph);
-	if (sh == NULL)
+	if (sh == NULL) {
+		*verdict = NF_DROP;
 		return 0;
+	}
 
 	sch = skb_header_pointer(skb, iph->len + sizeof(sctp_sctphdr_t),
 				 sizeof(_schunkh), &_schunkh);
-	if (sch == NULL)
+	if (sch == NULL) {
+		*verdict = NF_DROP;
 		return 0;
+	}
+
 	net = skb_net(skb);
 	ipvs = net_ipvs(net);
 	rcu_read_lock();
@@ -76,6 +81,7 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 {
 	sctp_sctphdr_t *sctph;
 	unsigned int sctphoff = iph->len;
+	bool payload_csum = false;
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (cp->af == AF_INET6 && iph->fragoffs)
@@ -87,19 +93,31 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		return 0;
 
 	if (unlikely(cp->app != NULL)) {
+		int ret;
+
 		/* Some checks before mangling */
 		if (pp->csum_check && !pp->csum_check(cp->af, skb, pp))
 			return 0;
 
 		/* Call application helper if needed */
-		if (!ip_vs_app_pkt_out(cp, skb))
+		ret = ip_vs_app_pkt_out(cp, skb);
+		if (ret == 0)
 			return 0;
+		/* ret=2: csum update is needed after payload mangling */
+		if (ret == 2)
+			payload_csum = true;
 	}
 
 	sctph = (void *) skb_network_header(skb) + sctphoff;
-	sctph->source = cp->vport;
 
-	sctp_nat_csum(skb, sctph, sctphoff);
+	/* Only update csum if we really have to */
+	if (sctph->source != cp->vport || payload_csum ||
+	    skb->ip_summed == CHECKSUM_PARTIAL) {
+		sctph->source = cp->vport;
+		sctp_nat_csum(skb, sctph, sctphoff);
+	} else {
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+	}
 
 	return 1;
 }
@@ -110,6 +128,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 {
 	sctp_sctphdr_t *sctph;
 	unsigned int sctphoff = iph->len;
+	bool payload_csum = false;
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (cp->af == AF_INET6 && iph->fragoffs)
@@ -121,19 +140,32 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		return 0;
 
 	if (unlikely(cp->app != NULL)) {
+		int ret;
+
 		/* Some checks before mangling */
 		if (pp->csum_check && !pp->csum_check(cp->af, skb, pp))
 			return 0;
 
 		/* Call application helper if needed */
-		if (!ip_vs_app_pkt_in(cp, skb))
+		ret = ip_vs_app_pkt_in(cp, skb);
+		if (ret == 0)
 			return 0;
+		/* ret=2: csum update is needed after payload mangling */
+		if (ret == 2)
+			payload_csum = true;
 	}
 
 	sctph = (void *) skb_network_header(skb) + sctphoff;
-	sctph->dest = cp->dport;
 
-	sctp_nat_csum(skb, sctph, sctphoff);
+	/* Only update csum if we really have to */
+	if (sctph->dest != cp->dport || payload_csum ||
+	    (skb->ip_summed == CHECKSUM_PARTIAL &&
+	     !(skb_dst(skb)->dev->features & NETIF_F_SCTP_CSUM))) {
+		sctph->dest = cp->dport;
+		sctp_nat_csum(skb, sctph, sctphoff);
+	} else if (skb->ip_summed != CHECKSUM_PARTIAL) {
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+	}
 
 	return 1;
 }

net/netfilter/ipvs/ip_vs_sh.c

@@ -115,27 +115,46 @@ ip_vs_sh_get(struct ip_vs_service *svc, struct ip_vs_sh_state *s,
 }
 
 
-/* As ip_vs_sh_get, but with fallback if selected server is unavailable */
+/* As ip_vs_sh_get, but with fallback if selected server is unavailable
+ *
+ * The fallback strategy loops around the table starting from a "random"
+ * point (in fact, it is chosen to be the original hash value to make the
+ * algorithm deterministic) to find a new server.
+ */
 static inline struct ip_vs_dest *
 ip_vs_sh_get_fallback(struct ip_vs_service *svc, struct ip_vs_sh_state *s,
 		      const union nf_inet_addr *addr, __be16 port)
 {
-	unsigned int offset;
-	unsigned int hash;
+	unsigned int offset, roffset;
+	unsigned int hash, ihash;
 	struct ip_vs_dest *dest;
 
+	/* first try the dest it's supposed to go to */
+	ihash = ip_vs_sh_hashkey(svc->af, addr, port, 0);
+	dest = rcu_dereference(s->buckets[ihash].dest);
+	if (!dest)
+		return NULL;
+	if (!is_unavailable(dest))
+		return dest;
+
+	IP_VS_DBG_BUF(6, "SH: selected unavailable server %s:%d, reselecting",
+		      IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port));
+
+	/* if the original dest is unavailable, loop around the table
+	 * starting from ihash to find a new dest
+	 */
 	for (offset = 0; offset < IP_VS_SH_TAB_SIZE; offset++) {
-		hash = ip_vs_sh_hashkey(svc->af, addr, port, offset);
+		roffset = (offset + ihash) % IP_VS_SH_TAB_SIZE;
+		hash = ip_vs_sh_hashkey(svc->af, addr, port, roffset);
 		dest = rcu_dereference(s->buckets[hash].dest);
 		if (!dest)
 			break;
-		if (is_unavailable(dest))
-			IP_VS_DBG_BUF(6, "SH: selected unavailable server "
-				      "%s:%d (offset %d)",
-				      IP_VS_DBG_ADDR(svc->af, &dest->addr),
-				      ntohs(dest->port), offset);
-		else
+		if (!is_unavailable(dest))
 			return dest;
+		IP_VS_DBG_BUF(6, "SH: selected unavailable "
+			      "server %s:%d (offset %d), reselecting",
+			      IP_VS_DBG_ADDR(svc->af, &dest->addr),
+			      ntohs(dest->port), roffset);
 	}
 
 	return NULL;

net/netfilter/nf_conntrack_acct.c

@@ -39,21 +39,23 @@ static struct ctl_table acct_sysctl_table[] = {
 unsigned int
 seq_print_acct(struct seq_file *s, const struct nf_conn *ct, int dir)
 {
-	struct nf_conn_counter *acct;
+	struct nf_conn_acct *acct;
+	struct nf_conn_counter *counter;
 
 	acct = nf_conn_acct_find(ct);
 	if (!acct)
 		return 0;
 
+	counter = acct->counter;
 	return seq_printf(s, "packets=%llu bytes=%llu ",
-			  (unsigned long long)atomic64_read(&acct[dir].packets),
-			  (unsigned long long)atomic64_read(&acct[dir].bytes));
+			  (unsigned long long)atomic64_read(&counter[dir].packets),
+			  (unsigned long long)atomic64_read(&counter[dir].bytes));
 };
 EXPORT_SYMBOL_GPL(seq_print_acct);
 
 static struct nf_ct_ext_type acct_extend __read_mostly = {
-	.len	= sizeof(struct nf_conn_counter[IP_CT_DIR_MAX]),
-	.align	= __alignof__(struct nf_conn_counter[IP_CT_DIR_MAX]),
+	.len	= sizeof(struct nf_conn_acct),
+	.align	= __alignof__(struct nf_conn_acct),
 	.id	= NF_CT_EXT_ACCT,
 };
 

net/netfilter/nf_conntrack_core.c

@@ -1109,12 +1109,14 @@ void __nf_ct_refresh_acct(struct nf_conn *ct,
 
 acct:
 	if (do_acct) {
-		struct nf_conn_counter *acct;
+		struct nf_conn_acct *acct;
 
 		acct = nf_conn_acct_find(ct);
 		if (acct) {
-			atomic64_inc(&acct[CTINFO2DIR(ctinfo)].packets);
-			atomic64_add(skb->len, &acct[CTINFO2DIR(ctinfo)].bytes);
+			struct nf_conn_counter *counter = acct->counter;
+
+			atomic64_inc(&counter[CTINFO2DIR(ctinfo)].packets);
+			atomic64_add(skb->len, &counter[CTINFO2DIR(ctinfo)].bytes);
 		}
 	}
 }
@@ -1126,13 +1128,15 @@ bool __nf_ct_kill_acct(struct nf_conn *ct,
 		       int do_acct)
 {
 	if (do_acct) {
-		struct nf_conn_counter *acct;
+		struct nf_conn_acct *acct;
 
 		acct = nf_conn_acct_find(ct);
 		if (acct) {
-			atomic64_inc(&acct[CTINFO2DIR(ctinfo)].packets);
+			struct nf_conn_counter *counter = acct->counter;
+
+			atomic64_inc(&counter[CTINFO2DIR(ctinfo)].packets);
 			atomic64_add(skb->len - skb_network_offset(skb),
-				     &acct[CTINFO2DIR(ctinfo)].bytes);
+				     &counter[CTINFO2DIR(ctinfo)].bytes);
 		}
 	}
 

net/netfilter/nf_conntrack_netlink.c

@@ -211,13 +211,23 @@ ctnetlink_dump_helpinfo(struct sk_buff *skb, const struct nf_conn *ct)
 }
 
 static int
-dump_counters(struct sk_buff *skb, u64 pkts, u64 bytes,
-	      enum ip_conntrack_dir dir)
+dump_counters(struct sk_buff *skb, struct nf_conn_acct *acct,
+	      enum ip_conntrack_dir dir, int type)
 {
-	enum ctattr_type type = dir ? CTA_COUNTERS_REPLY: CTA_COUNTERS_ORIG;
+	enum ctattr_type attr = dir ? CTA_COUNTERS_REPLY: CTA_COUNTERS_ORIG;
+	struct nf_conn_counter *counter = acct->counter;
 	struct nlattr *nest_count;
+	u64 pkts, bytes;
 
-	nest_count = nla_nest_start(skb, type | NLA_F_NESTED);
+	if (type == IPCTNL_MSG_CT_GET_CTRZERO) {
+		pkts = atomic64_xchg(&counter[dir].packets, 0);
+		bytes = atomic64_xchg(&counter[dir].bytes, 0);
+	} else {
+		pkts = atomic64_read(&counter[dir].packets);
+		bytes = atomic64_read(&counter[dir].bytes);
+	}
+
+	nest_count = nla_nest_start(skb, attr | NLA_F_NESTED);
 	if (!nest_count)
 		goto nla_put_failure;
 
@@ -234,24 +244,19 @@ dump_counters(struct sk_buff *skb, u64 pkts, u64 bytes,
 }
 
 static int
-ctnetlink_dump_counters(struct sk_buff *skb, const struct nf_conn *ct,
-			enum ip_conntrack_dir dir, int type)
+ctnetlink_dump_acct(struct sk_buff *skb, const struct nf_conn *ct, int type)
 {
-	struct nf_conn_counter *acct;
-	u64 pkts, bytes;
+	struct nf_conn_acct *acct = nf_conn_acct_find(ct);
 
-	acct = nf_conn_acct_find(ct);
 	if (!acct)
 		return 0;
 
-	if (type == IPCTNL_MSG_CT_GET_CTRZERO) {
-		pkts = atomic64_xchg(&acct[dir].packets, 0);
-		bytes = atomic64_xchg(&acct[dir].bytes, 0);
-	} else {
-		pkts = atomic64_read(&acct[dir].packets);
-		bytes = atomic64_read(&acct[dir].bytes);
-	}
-	return dump_counters(skb, pkts, bytes, dir);
+	if (dump_counters(skb, acct, IP_CT_DIR_ORIGINAL, type) < 0)
+		return -1;
+	if (dump_counters(skb, acct, IP_CT_DIR_REPLY, type) < 0)
+		return -1;
+
+	return 0;
 }
 
 static int
@@ -488,8 +493,7 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 
 	if (ctnetlink_dump_status(skb, ct) < 0 ||
 	    ctnetlink_dump_timeout(skb, ct) < 0 ||
-	    ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL, type) < 0 ||
-	    ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY, type) < 0 ||
+	    ctnetlink_dump_acct(skb, ct, type) < 0 ||
 	    ctnetlink_dump_timestamp(skb, ct) < 0 ||
 	    ctnetlink_dump_protoinfo(skb, ct) < 0 ||
 	    ctnetlink_dump_helpinfo(skb, ct) < 0 ||
@@ -530,7 +534,7 @@ ctnetlink_proto_size(const struct nf_conn *ct)
 }
 
 static inline size_t
-ctnetlink_counters_size(const struct nf_conn *ct)
+ctnetlink_acct_size(const struct nf_conn *ct)
 {
 	if (!nf_ct_ext_exist(ct, NF_CT_EXT_ACCT))
 		return 0;
@@ -579,7 +583,7 @@ ctnetlink_nlmsg_size(const struct nf_conn *ct)
 	       + 3 * nla_total_size(sizeof(u_int8_t)) /* CTA_PROTO_NUM */
 	       + nla_total_size(sizeof(u_int32_t)) /* CTA_ID */
 	       + nla_total_size(sizeof(u_int32_t)) /* CTA_STATUS */
-	       + ctnetlink_counters_size(ct)
+	       + ctnetlink_acct_size(ct)
 	       + ctnetlink_timestamp_size(ct)
 	       + nla_total_size(sizeof(u_int32_t)) /* CTA_TIMEOUT */
 	       + nla_total_size(0) /* CTA_PROTOINFO */
@@ -673,10 +677,7 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item)
 		goto nla_put_failure;
 
 	if (events & (1 << IPCT_DESTROY)) {
-		if (ctnetlink_dump_counters(skb, ct,
-					    IP_CT_DIR_ORIGINAL, type) < 0 ||
-		    ctnetlink_dump_counters(skb, ct,
-					    IP_CT_DIR_REPLY, type) < 0 ||
+		if (ctnetlink_dump_acct(skb, ct, type) < 0 ||
 		    ctnetlink_dump_timestamp(skb, ct) < 0)
 			goto nla_put_failure;
 	} else {

net/netfilter/xt_connbytes.c

@@ -26,16 +26,18 @@ connbytes_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	u_int64_t what = 0;	/* initialize to make gcc happy */
 	u_int64_t bytes = 0;
 	u_int64_t pkts = 0;
+	const struct nf_conn_acct *acct;
 	const struct nf_conn_counter *counters;
 
 	ct = nf_ct_get(skb, &ctinfo);
 	if (!ct)
 		return false;
 
-	counters = nf_conn_acct_find(ct);
-	if (!counters)
+	acct = nf_conn_acct_find(ct);
+	if (!acct)
 		return false;
 
+	counters = acct->counter;
 	switch (sinfo->what) {
 	case XT_CONNBYTES_PKTS:
 		switch (sinfo->direction) {

net/netfilter/xt_socket.c

@@ -35,15 +35,6 @@
 #include <net/netfilter/nf_conntrack.h>
 #endif
 
-static void
-xt_socket_put_sk(struct sock *sk)
-{
-	if (sk->sk_state == TCP_TIME_WAIT)
-		inet_twsk_put(inet_twsk(sk));
-	else
-		sock_put(sk);
-}
-
 static int
 extract_icmp4_fields(const struct sk_buff *skb,
 		    u8 *protocol,
@@ -216,7 +207,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par,
 					inet_twsk(sk)->tw_transparent));
 
 		if (sk != skb->sk)
-			xt_socket_put_sk(sk);
+			sock_gen_put(sk);
 
 		if (wildcard || !transparent)
 			sk = NULL;
@@ -381,7 +372,7 @@ socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par)
 					inet_twsk(sk)->tw_transparent));
 
 		if (sk != skb->sk)
-			xt_socket_put_sk(sk);
+			sock_gen_put(sk);
 
 		if (wildcard || !transparent)
 			sk = NULL;