Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

The mptcp conflict was overlapping additions.

The SMC conflict was an additional and removal happening at the same
time.

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

27 files changed, 586 insertions, 276 deletions

diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index dc3d2c1dd9d5..0e3dbc5f3c34 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -34,7 +34,6 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	const struct nf_br_ops *nf_ops;
 	u8 state = BR_STATE_FORWARDING;
 	const unsigned char *dest;
-	struct ethhdr *eth;
 	u16 vid = 0;
 
 	rcu_read_lock();
@@ -54,15 +53,14 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	BR_INPUT_SKB_CB(skb)->frag_max_size = 0;
 
 	skb_reset_mac_header(skb);
-	eth = eth_hdr(skb);
 	skb_pull(skb, ETH_HLEN);
 
 	if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid, &state))
 		goto out;
 
 	if (IS_ENABLED(CONFIG_INET) &&
-	    (eth->h_proto == htons(ETH_P_ARP) ||
-	     eth->h_proto == htons(ETH_P_RARP)) &&
+	    (eth_hdr(skb)->h_proto == htons(ETH_P_ARP) ||
+	     eth_hdr(skb)->h_proto == htons(ETH_P_RARP)) &&
 	    br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED)) {
 		br_do_proxy_suppress_arp(skb, br, vid, NULL);
 	} else if (IS_ENABLED(CONFIG_IPV6) &&
diff --git a/net/core/dev.c b/net/core/dev.c
index dbbfff123196..25dab1598803 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3076,6 +3076,8 @@ static u16 skb_tx_hash(const struct net_device *dev,
 
 	if (skb_rx_queue_recorded(skb)) {
 		hash = skb_get_rx_queue(skb);
+		if (hash >= qoffset)
+			hash -= qoffset;
 		while (unlikely(hash >= qcount))
 			hash -= qcount;
 		return hash + qoffset;
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 49706031ab45..f8af5e2d748b 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -2103,11 +2103,11 @@ err_action_values_put:
 
 static struct devlink_dpipe_table *
 devlink_dpipe_table_find(struct list_head *dpipe_tables,
-			 const char *table_name)
+			 const char *table_name, struct devlink *devlink)
 {
 	struct devlink_dpipe_table *table;
-
-	list_for_each_entry_rcu(table, dpipe_tables, list) {
+	list_for_each_entry_rcu(table, dpipe_tables, list,
+				lockdep_is_held(&devlink->lock)) {
 		if (!strcmp(table->name, table_name))
 			return table;
 	}
@@ -2226,7 +2226,7 @@ static int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb,
 
 	table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]);
 	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
-					 table_name);
+					 table_name, devlink);
 	if (!table)
 		return -EINVAL;
 
@@ -2382,7 +2382,7 @@ static int devlink_dpipe_table_counters_set(struct devlink *devlink,
 	struct devlink_dpipe_table *table;
 
 	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
-					 table_name);
+					 table_name, devlink);
 	if (!table)
 		return -EINVAL;
 
@@ -6935,7 +6935,7 @@ bool devlink_dpipe_table_counter_enabled(struct devlink *devlink,
 
 	rcu_read_lock();
 	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
-					 table_name);
+					 table_name, devlink);
 	enabled = false;
 	if (table)
 		enabled = table->counters_enabled;
@@ -6959,26 +6959,34 @@ int devlink_dpipe_table_register(struct devlink *devlink,
 				 void *priv, bool counter_control_extern)
 {
 	struct devlink_dpipe_table *table;
-
-	if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name))
-		return -EEXIST;
+	int err = 0;
 
 	if (WARN_ON(!table_ops->size_get))
 		return -EINVAL;
 
+	mutex_lock(&devlink->lock);
+
+	if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name,
+				     devlink)) {
+		err = -EEXIST;
+		goto unlock;
+	}
+
 	table = kzalloc(sizeof(*table), GFP_KERNEL);
-	if (!table)
-		return -ENOMEM;
+	if (!table) {
+		err = -ENOMEM;
+		goto unlock;
+	}
 
 	table->name = table_name;
 	table->table_ops = table_ops;
 	table->priv = priv;
 	table->counter_control_extern = counter_control_extern;
 
-	mutex_lock(&devlink->lock);
 	list_add_tail_rcu(&table->list, &devlink->dpipe_table_list);
+unlock:
 	mutex_unlock(&devlink->lock);
-	return 0;
+	return err;
 }
 EXPORT_SYMBOL_GPL(devlink_dpipe_table_register);
 
@@ -6995,7 +7003,7 @@ void devlink_dpipe_table_unregister(struct devlink *devlink,
 
 	mutex_lock(&devlink->lock);
 	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
-					 table_name);
+					 table_name, devlink);
 	if (!table)
 		goto unlock;
 	list_del_rcu(&table->list);
@@ -7152,7 +7160,7 @@ int devlink_dpipe_table_resource_set(struct devlink *devlink,
 
 	mutex_lock(&devlink->lock);
 	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
-					 table_name);
+					 table_name, devlink);
 	if (!table) {
 		err = -EINVAL;
 		goto out;
diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c
index 8977fe1f3946..ef9197541cb3 100644
--- a/net/ethtool/bitset.c
+++ b/net/ethtool/bitset.c
@@ -305,7 +305,8 @@ nla_put_failure:
 static const struct nla_policy bitset_policy[ETHTOOL_A_BITSET_MAX + 1] = {
 	[ETHTOOL_A_BITSET_UNSPEC]	= { .type = NLA_REJECT },
 	[ETHTOOL_A_BITSET_NOMASK]	= { .type = NLA_FLAG },
-	[ETHTOOL_A_BITSET_SIZE]		= { .type = NLA_U32 },
+	[ETHTOOL_A_BITSET_SIZE]		= NLA_POLICY_MAX(NLA_U32,
+							 ETHNL_MAX_BITSET_SIZE),
 	[ETHTOOL_A_BITSET_BITS]		= { .type = NLA_NESTED },
 	[ETHTOOL_A_BITSET_VALUE]	= { .type = NLA_BINARY },
 	[ETHTOOL_A_BITSET_MASK]		= { .type = NLA_BINARY },
diff --git a/net/ethtool/bitset.h b/net/ethtool/bitset.h
index b8247e34109d..b849f9d19676 100644
--- a/net/ethtool/bitset.h
+++ b/net/ethtool/bitset.h
@@ -3,6 +3,8 @@
 #ifndef _NET_ETHTOOL_BITSET_H
 #define _NET_ETHTOOL_BITSET_H
 
+#define ETHNL_MAX_BITSET_SIZE S16_MAX
+
 typedef const char (*const ethnl_string_array_t)[ETH_GSTRING_LEN];
 
 int ethnl_bitset_is_compact(const struct nlattr *bitset, bool *compact);
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 376882215919..0bd10a1f477f 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1724,6 +1724,7 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway)
 {
 	unsigned char optbuf[sizeof(struct ip_options) + 40];
 	struct ip_options *opt = (struct ip_options *)optbuf;
+	int res;
 
 	if (ip_hdr(skb)->protocol == IPPROTO_ICMP || error != -EACCES)
 		return;
@@ -1735,7 +1736,11 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway)
 
 	memset(opt, 0, sizeof(struct ip_options));
 	opt->optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr);
-	if (__ip_options_compile(dev_net(skb->dev), opt, skb, NULL))
+	rcu_read_lock();
+	res = __ip_options_compile(dev_net(skb->dev), opt, skb, NULL);
+	rcu_read_unlock();
+
+	if (res)
 		return;
 
 	if (gateway)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 316ebdf8151d..6b6b57000dad 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6124,7 +6124,11 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk)
 {
 	struct request_sock *req;
 
-	tcp_try_undo_loss(sk, false);
+	/* If we are still handling the SYNACK RTO, see if timestamp ECR allows
+	 * undo. If peer SACKs triggered fast recovery, we can't undo here.
+	 */
+	if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss)
+		tcp_try_undo_loss(sk, false);
 
 	/* Reset rtx states to prevent spurious retransmits_timed_out() */
 	tcp_sk(sk)->retrans_stamp = 0;
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 79fc012dd2ca..debdaeba5d8c 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -183,9 +183,15 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 					retv = -EBUSY;
 					break;
 				}
-			} else if (sk->sk_protocol != IPPROTO_TCP)
+			} else if (sk->sk_protocol == IPPROTO_TCP) {
+				if (sk->sk_prot != &tcpv6_prot) {
+					retv = -EBUSY;
+					break;
+				}
 				break;
-
+			} else {
+				break;
+			}
 			if (sk->sk_state != TCP_ESTABLISHED) {
 				retv = -ENOTCONN;
 				break;
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 9ab0842a7c37..8a2f2fa21916 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -2986,7 +2986,7 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata,
 	    (auth_transaction == 2 &&
 	     ifmgd->auth_data->expected_transaction == 2)) {
 		if (!ieee80211_mark_sta_auth(sdata, bssid))
-			goto out_err;
+			return; /* ignore frame -- wait for timeout */
 	} else if (ifmgd->auth_data->algorithm == WLAN_AUTH_SAE &&
 		   auth_transaction == 2) {
 		sdata_info(sdata, "SAE peer confirmed\n");
@@ -2994,10 +2994,6 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata,
 	}
 
 	cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len);
-	return;
- out_err:
-	mutex_unlock(&sdata->local->sta_mtx);
-	/* ignore frame -- wait for timeout */
 }
 
 #define case_WLAN(type) \
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 6bd24123456d..2ffb4ee467e1 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -4171,7 +4171,7 @@ void __ieee80211_check_fast_rx_iface(struct ieee80211_sub_if_data *sdata)
 
 	lockdep_assert_held(&local->sta_mtx);
 
-	list_for_each_entry_rcu(sta, &local->sta_list, list) {
+	list_for_each_entry(sta, &local->sta_list, list) {
 		if (sdata != sta->sdata &&
 		    (!sta->sdata->bss || sta->sdata->bss != sdata->bss))
 			continue;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 044295707bbf..a8445407d25a 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -666,6 +666,11 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 	}
 }
 
+static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu)
+{
+	return 0;
+}
+
 static void mptcp_worker(struct work_struct *work)
 {
 	struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work);
@@ -686,6 +691,7 @@ static int __mptcp_init_sock(struct sock *sk)
 	INIT_WORK(&msk->work, mptcp_worker);
 
 	msk->first = NULL;
+	inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss;
 
 	return 0;
 }
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 69c107f9ba8d..8dd17589217d 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -723,6 +723,20 @@ ip_set_rcu_get(struct net *net, ip_set_id_t index)
 	return set;
 }
 
+static inline void
+ip_set_lock(struct ip_set *set)
+{
+	if (!set->variant->region_lock)
+		spin_lock_bh(&set->lock);
+}
+
+static inline void
+ip_set_unlock(struct ip_set *set)
+{
+	if (!set->variant->region_lock)
+		spin_unlock_bh(&set->lock);
+}
+
 int
 ip_set_test(ip_set_id_t index, const struct sk_buff *skb,
 	    const struct xt_action_param *par, struct ip_set_adt_opt *opt)
@@ -744,9 +758,9 @@ ip_set_test(ip_set_id_t index, const struct sk_buff *skb,
 	if (ret == -EAGAIN) {
 		/* Type requests element to be completed */
 		pr_debug("element must be completed, ADD is triggered\n");
-		spin_lock_bh(&set->lock);
+		ip_set_lock(set);
 		set->variant->kadt(set, skb, par, IPSET_ADD, opt);
-		spin_unlock_bh(&set->lock);
+		ip_set_unlock(set);
 		ret = 1;
 	} else {
 		/* --return-nomatch: invert matched element */
@@ -775,9 +789,9 @@ ip_set_add(ip_set_id_t index, const struct sk_buff *skb,
 	    !(opt->family == set->family || set->family == NFPROTO_UNSPEC))
 		return -IPSET_ERR_TYPE_MISMATCH;
 
-	spin_lock_bh(&set->lock);
+	ip_set_lock(set);
 	ret = set->variant->kadt(set, skb, par, IPSET_ADD, opt);
-	spin_unlock_bh(&set->lock);
+	ip_set_unlock(set);
 
 	return ret;
 }
@@ -797,9 +811,9 @@ ip_set_del(ip_set_id_t index, const struct sk_buff *skb,
 	    !(opt->family == set->family || set->family == NFPROTO_UNSPEC))
 		return -IPSET_ERR_TYPE_MISMATCH;
 
-	spin_lock_bh(&set->lock);
+	ip_set_lock(set);
 	ret = set->variant->kadt(set, skb, par, IPSET_DEL, opt);
-	spin_unlock_bh(&set->lock);
+	ip_set_unlock(set);
 
 	return ret;
 }
@@ -1264,9 +1278,9 @@ ip_set_flush_set(struct ip_set *set)
 {
 	pr_debug("set: %s\n",  set->name);
 
-	spin_lock_bh(&set->lock);
+	ip_set_lock(set);
 	set->variant->flush(set);
-	spin_unlock_bh(&set->lock);
+	ip_set_unlock(set);
 }
 
 static int ip_set_flush(struct net *net, struct sock *ctnl, struct sk_buff *skb,
@@ -1713,9 +1727,9 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set,
 	bool eexist = flags & IPSET_FLAG_EXIST, retried = false;
 
 	do {
-		spin_lock_bh(&set->lock);
+		ip_set_lock(set);
 		ret = set->variant->uadt(set, tb, adt, &lineno, flags, retried);
-		spin_unlock_bh(&set->lock);
+		ip_set_unlock(set);
 		retried = true;
 	} while (ret == -EAGAIN &&
 		 set->variant->resize &&
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 7480ce55b5c8..e52d7b7597a0 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -7,13 +7,21 @@
 #include <linux/rcupdate.h>
 #include <linux/jhash.h>
 #include <linux/types.h>
+#include <linux/netfilter/nfnetlink.h>
 #include <linux/netfilter/ipset/ip_set.h>
 
-#define __ipset_dereference_protected(p, c)	rcu_dereference_protected(p, c)
-#define ipset_dereference_protected(p, set) \
-	__ipset_dereference_protected(p, lockdep_is_held(&(set)->lock))
-
-#define rcu_dereference_bh_nfnl(p)	rcu_dereference_bh_check(p, 1)
+#define __ipset_dereference(p)		\
+	rcu_dereference_protected(p, 1)
+#define ipset_dereference_nfnl(p)	\
+	rcu_dereference_protected(p,	\
+		lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET))
+#define ipset_dereference_set(p, set) 	\
+	rcu_dereference_protected(p,	\
+		lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET) || \
+		lockdep_is_held(&(set)->lock))
+#define ipset_dereference_bh_nfnl(p)	\
+	rcu_dereference_bh_check(p, 	\
+		lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET))
 
 /* Hashing which uses arrays to resolve clashing. The hash table is resized
  * (doubled) when searching becomes too long.
@@ -72,11 +80,35 @@ struct hbucket {
 		__aligned(__alignof__(u64));
 };
 
+/* Region size for locking == 2^HTABLE_REGION_BITS */
+#define HTABLE_REGION_BITS	10
+#define ahash_numof_locks(htable_bits)		\
+	((htable_bits) < HTABLE_REGION_BITS ? 1	\
+		: jhash_size((htable_bits) - HTABLE_REGION_BITS))
+#define ahash_sizeof_regions(htable_bits)		\
+	(ahash_numof_locks(htable_bits) * sizeof(struct ip_set_region))
+#define ahash_region(n, htable_bits)		\
+	((n) % ahash_numof_locks(htable_bits))
+#define ahash_bucket_start(h,  htable_bits)	\
+	((htable_bits) < HTABLE_REGION_BITS ? 0	\
+		: (h) * jhash_size(HTABLE_REGION_BITS))
+#define ahash_bucket_end(h,  htable_bits)	\
+	((htable_bits) < HTABLE_REGION_BITS ? jhash_size(htable_bits)	\
+		: ((h) + 1) * jhash_size(HTABLE_REGION_BITS))
+
+struct htable_gc {
+	struct delayed_work dwork;
+	struct ip_set *set;	/* Set the gc belongs to */
+	u32 region;		/* Last gc run position */
+};
+
 /* The hash table: the table size stored here in order to make resizing easy */
 struct htable {
 	atomic_t ref;		/* References for resizing */
-	atomic_t uref;		/* References for dumping */
+	atomic_t uref;		/* References for dumping and gc */
 	u8 htable_bits;		/* size of hash table == 2^htable_bits */
+	u32 maxelem;		/* Maxelem per region */
+	struct ip_set_region *hregion;	/* Region locks and ext sizes */
 	struct hbucket __rcu *bucket[0]; /* hashtable buckets */
 };
 
@@ -162,6 +194,10 @@ htable_bits(u32 hashsize)
 #define NLEN			0
 #endif /* IP_SET_HASH_WITH_NETS */
 
+#define SET_ELEM_EXPIRED(set, d)	\
+	(SET_WITH_TIMEOUT(set) &&	\
+	 ip_set_timeout_expired(ext_timeout(d, set)))
+
 #endif /* _IP_SET_HASH_GEN_H */
 
 #ifndef MTYPE
@@ -205,10 +241,12 @@ htable_bits(u32 hashsize)
 #undef mtype_test_cidrs
 #undef mtype_test
 #undef mtype_uref
-#undef mtype_expire
 #undef mtype_resize
+#undef mtype_ext_size
+#undef mtype_resize_ad
 #undef mtype_head
 #undef mtype_list
+#undef mtype_gc_do
 #undef mtype_gc
 #undef mtype_gc_init
 #undef mtype_variant
@@ -247,10 +285,12 @@ htable_bits(u32 hashsize)
 #define mtype_test_cidrs	IPSET_TOKEN(MTYPE, _test_cidrs)
 #define mtype_test		IPSET_TOKEN(MTYPE, _test)
 #define mtype_uref		IPSET_TOKEN(MTYPE, _uref)
-#define mtype_expire		IPSET_TOKEN(MTYPE, _expire)
 #define mtype_resize		IPSET_TOKEN(MTYPE, _resize)
+#define mtype_ext_size		IPSET_TOKEN(MTYPE, _ext_size)
+#define mtype_resize_ad		IPSET_TOKEN(MTYPE, _resize_ad)
 #define mtype_head		IPSET_TOKEN(MTYPE, _head)
 #define mtype_list		IPSET_TOKEN(MTYPE, _list)
+#define mtype_gc_do		IPSET_TOKEN(MTYPE, _gc_do)
 #define mtype_gc		IPSET_TOKEN(MTYPE, _gc)
 #define mtype_gc_init		IPSET_TOKEN(MTYPE, _gc_init)
 #define mtype_variant		IPSET_TOKEN(MTYPE, _variant)
@@ -275,8 +315,7 @@ htable_bits(u32 hashsize)
 /* The generic hash structure */
 struct htype {
 	struct htable __rcu *table; /* the hash table */
-	struct timer_list gc;	/* garbage collection when timeout enabled */
-	struct ip_set *set;	/* attached to this ip_set */
+	struct htable_gc gc;	/* gc workqueue */
 	u32 maxelem;		/* max elements in the hash */
 	u32 initval;		/* random jhash init value */
 #ifdef IP_SET_HASH_WITH_MARKMASK
@@ -288,21 +327,33 @@ struct htype {
 #ifdef IP_SET_HASH_WITH_NETMASK
 	u8 netmask;		/* netmask value for subnets to store */
 #endif
+	struct list_head ad;	/* Resize add|del backlist */
 	struct mtype_elem next; /* temporary storage for uadd */
 #ifdef IP_SET_HASH_WITH_NETS
 	struct net_prefixes nets[NLEN]; /* book-keeping of prefixes */
 #endif
 };
 
+/* ADD|DEL entries saved during resize */
+struct mtype_resize_ad {
+	struct list_head list;
+	enum ipset_adt ad;	/* ADD|DEL element */
+	struct mtype_elem d;	/* Element value */
+	struct ip_set_ext ext;	/* Extensions for ADD */
+	struct ip_set_ext mext;	/* Target extensions for ADD */
+	u32 flags;		/* Flags for ADD */
+};
+
 #ifdef IP_SET_HASH_WITH_NETS
 /* Network cidr size book keeping when the hash stores different
  * sized networks. cidr == real cidr + 1 to support /0.
  */
 static void
-mtype_add_cidr(struct htype *h, u8 cidr, u8 n)
+mtype_add_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n)
 {
 	int i, j;
 
+	spin_lock_bh(&set->lock);
 	/* Add in increasing prefix order, so larger cidr first */
 	for (i = 0, j = -1; i < NLEN && h->nets[i].cidr[n]; i++) {
 		if (j != -1) {
@@ -311,7 +362,7 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 n)
 			j = i;
 		} else if (h->nets[i].cidr[n] == cidr) {
 			h->nets[CIDR_POS(cidr)].nets[n]++;
-			return;
+			goto unlock;
 		}
 	}
 	if (j != -1) {
@@ -320,24 +371,29 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 n)
 	}
 	h->nets[i].cidr[n] = cidr;
 	h->nets[CIDR_POS(cidr)].nets[n] = 1;
+unlock:
+	spin_unlock_bh(&set->lock);
 }
 
 static void
-mtype_del_cidr(struct htype *h, u8 cidr, u8 n)
+mtype_del_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n)
 {
 	u8 i, j, net_end = NLEN - 1;
 
+	spin_lock_bh(&set->lock);
 	for (i = 0; i < NLEN; i++) {
 		if (h->nets[i].cidr[n] != cidr)
 			continue;
 		h->nets[CIDR_POS(cidr)].nets[n]--;
 		if (h->nets[CIDR_POS(cidr)].nets[n] > 0)
-			return;
+			goto unlock;
 		for (j = i; j < net_end && h->nets[j].cidr[n]; j++)
 			h->nets[j].cidr[n] = h->nets[j + 1].cidr[n];
 		h->nets[j].cidr[n] = 0;
-		return;
+		goto unlock;
 	}
+unlock:
+	spin_unlock_bh(&set->lock);
 }
 #endif
 
@@ -345,7 +401,7 @@ mtype_del_cidr(struct htype *h, u8 cidr, u8 n)
 static size_t
 mtype_ahash_memsize(const struct htype *h, const struct htable *t)
 {
-	return sizeof(*h) + sizeof(*t);
+	return sizeof(*h) + sizeof(*t) + ahash_sizeof_regions(t->htable_bits);
 }
 
 /* Get the ith element from the array block n */
@@ -369,24 +425,29 @@ mtype_flush(struct ip_set *set)
 	struct htype *h = set->data;
 	struct htable *t;
 	struct hbucket *n;
-	u32 i;
-
-	t = ipset_dereference_protected(h->table, set);
-	for (i = 0; i < jhash_size(t->htable_bits); i++) {
-		n = __ipset_dereference_protected(hbucket(t, i), 1);
-		if (!n)
-			continue;
-		if (set->extensions & IPSET_EXT_DESTROY)
-			mtype_ext_cleanup(set, n);
-		/* FIXME: use slab cache */
-		rcu_assign_pointer(hbucket(t, i), NULL);
-		kfree_rcu(n, rcu);
+	u32 r, i;
+
+	t = ipset_dereference_nfnl(h->table);
+	for (r = 0; r < ahash_numof_locks(t->htable_bits); r++) {
+		spin_lock_bh(&t->hregion[r].lock);
+		for (i = ahash_bucket_start(r, t->htable_bits);
+		     i < ahash_bucket_end(r, t->htable_bits); i++) {
+			n = __ipset_dereference(hbucket(t, i));
+			if (!n)
+				continue;
+			if (set->extensions & IPSET_EXT_DESTROY)
+				mtype_ext_cleanup(set, n);
+			/* FIXME: use slab cache */
+			rcu_assign_pointer(hbucket(t, i), NULL);
+			kfree_rcu(n, rcu);
+		}
+		t->hregion[r].ext_size = 0;
+		t->hregion[r].elements = 0;
+		spin_unlock_bh(&t->hregion[r].lock);
 	}
 #ifdef IP_SET_HASH_WITH_NETS
 	memset(h->nets, 0, sizeof(h->nets));
 #endif
-	set->elements = 0;
-	set->ext_size = 0;
 }
 
 /* Destroy the hashtable part of the set */
@@ -397,7 +458,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy)
 	u32 i;
 
 	for (i = 0; i < jhash_size(t->htable_bits); i++) {
-		n = __ipset_dereference_protected(hbucket(t, i), 1);
+		n = __ipset_dereference(hbucket(t, i));
 		if (!n)
 			continue;
 		if (set->extensions & IPSET_EXT_DESTROY && ext_destroy)
@@ -406,6 +467,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy)
 		kfree(n);
 	}
 
+	ip_set_free(t->hregion);
 	ip_set_free(t);
 }
 
@@ -414,28 +476,21 @@ static void
 mtype_destroy(struct ip_set *set)
 {
 	struct htype *h = set->data;
+	struct list_head *l, *lt;
 
 	if (SET_WITH_TIMEOUT(set))
-		del_timer_sync(&h->gc);
+		cancel_delayed_work_sync(&h->gc.dwork);
 
-	mtype_ahash_destroy(set,
-			    __ipset_dereference_protected(h->table, 1), true);
+	mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true);
+	list_for_each_safe(l, lt, &h->ad) {
+		list_del(l);
+		kfree(l);
+	}
 	kfree(h);
 
 	set->data = NULL;
 }
 
-static void
-mtype_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t))
-{
-	struct htype *h = set->data;
-
-	timer_setup(&h->gc, gc, 0);
-	mod_timer(&h->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ);
-	pr_debug("gc initialized, run in every %u\n",
-		 IPSET_GC_PERIOD(set->timeout));
-}
-
 static bool
 mtype_same_set(const struct ip_set *a, const struct ip_set *b)
 {
@@ -454,11 +509,9 @@ mtype_same_set(const struct ip_set *a, const struct ip_set *b)
 	       a->extensions == b->extensions;
 }
 
-/* Delete expired elements from the hashtable */
 static void
-mtype_expire(struct ip_set *set, struct htype *h)
+mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r)
 {
-	struct htable *t;
 	struct hbucket *n, *tmp;
 	struct mtype_elem *data;
 	u32 i, j, d;
@@ -466,10 +519,12 @@ mtype_expire(struct ip_set *set, struct htype *h)
 #ifdef IP_SET_HASH_WITH_NETS
 	u8 k;
 #endif
+	u8 htable_bits = t->htable_bits;
 
-	t = ipset_dereference_protected(h->table, set);
-	for (i = 0; i < jhash_size(t->htable_bits); i++) {
-		n = __ipset_dereference_protected(hbucket(t, i), 1);
+	spin_lock_bh(&t->hregion[r].lock);
+	for (i = ahash_bucket_start(r, htable_bits);
+	     i < ahash_bucket_end(r, htable_bits); i++) {
+		n = __ipset_dereference(hbucket(t, i));
 		if (!n)
 			continue;
 		for (j = 0, d = 0; j < n->pos; j++) {
@@ -485,58 +540,100 @@ mtype_expire(struct ip_set *set, struct htype *h)
 			smp_mb__after_atomic();
 #ifdef IP_SET_HASH_WITH_NETS
 			for (k = 0; k < IPSET_NET_COUNT; k++)
-				mtype_del_cidr(h,
+				mtype_del_cidr(set, h,
 					NCIDR_PUT(DCIDR_GET(data->cidr, k)),
 					k);
 #endif
+			t->hregion[r].elements--;
 			ip_set_ext_destroy(set, data);
-			set->elements--;
 			d++;
 		}
 		if (d >= AHASH_INIT_SIZE) {
 			if (d >= n->size) {
+				t->hregion[r].ext_size -=
+					ext_size(n->size, dsize);
 				rcu_assign_pointer(hbucket(t, i), NULL);
 				kfree_rcu(n, rcu);
 				continue;
 			}
 			tmp = kzalloc(sizeof(*tmp) +
-				      (n->size - AHASH_INIT_SIZE) * dsize,
-				      GFP_ATOMIC);
+				(n->size - AHASH_INIT_SIZE) * dsize,
+				GFP_ATOMIC);
 			if (!tmp)
-				/* Still try to delete expired elements */
+				/* Still try to delete expired elements. */
 				continue;
 			tmp->size = n->size - AHASH_INIT_SIZE;
 			for (j = 0, d = 0; j < n->pos; j++) {
 				if (!test_bit(j, n->used))
 					continue;
 				data = ahash_data(n, j, dsize);
-				memcpy(tmp->value + d * dsize, data, dsize);
+				memcpy(tmp->value + d * dsize,
+				       data, dsize);
 				set_bit(d, tmp->used);
 				d++;
 			}
 			tmp->pos = d;
-			set->ext_size -= ext_size(AHASH_INIT_SIZE, dsize);
+			t->hregion[r].ext_size -=
+				ext_size(AHASH_INIT_SIZE, dsize);
 			rcu_assign_pointer(hbucket(t, i), tmp);
 			kfree_rcu(n, rcu);
 		}
 	}
+	spin_unlock_bh(&t->hregion[r].lock);
 }
 
 static void
-mtype_gc(struct timer_list *t)
+mtype_gc(struct work_struct *work)
 {
-	struct htype *h = from_timer(h, t, gc);
-	struct ip_set *set = h->set;
+	struct htable_gc *gc;
+	struct ip_set *set;
+	struct htype *h;
+	struct htable *t;
+	u32 r, numof_locks;
+	unsigned int next_run;
+
+	gc = container_of(work, struct htable_gc, dwork.work);
+	set = gc->set;
+	h = set->data;
 
-	pr_debug("called\n");
 	spin_lock_bh(&set->lock);
-	mtype_expire(set, h);
+	t = ipset_dereference_set(h->table, set);
+	atomic_inc(&t->uref);
+	numof_locks = ahash_numof_locks(t->htable_bits);
+	r = gc->region++;
+	if (r >= numof_locks) {
+		r = gc->region = 0;
+	}
+	next_run = (IPSET_GC_PERIOD(set->timeout) * HZ) / numof_locks;
+	if (next_run < HZ/10)
+		next_run = HZ/10;
 	spin_unlock_bh(&set->lock);
 
-	h->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
-	add_timer(&h->gc);
+	mtype_gc_do(set, h, t, r);
+
+	if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) {
+		pr_debug("Table destroy after resize by expire: %p\n", t);
+		mtype_ahash_destroy(set, t, false);
+	}
+
+	queue_delayed_work(system_power_efficient_wq, &gc->dwork, next_run);
+
+}
+
+static void
+mtype_gc_init(struct htable_gc *gc)
+{
+	INIT_DEFERRABLE_WORK(&gc->dwork, mtype_gc);
+	queue_delayed_work(system_power_efficient_wq, &gc->dwork, HZ);
 }
 
+static int
+mtype_add(struct ip_set *set, void *value, const struct ip_set_e