Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

7 files changed, 60 insertions, 69 deletions

diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index 5ca18f07683b..257ca393e6f2 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -127,14 +127,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 
 	if (ret <= 0)
 		return ret;
-	if (SET_WITH_TIMEOUT(set) &&
-	    ip_set_timeout_expired(ext_timeout(x, set)))
-		return 0;
-	if (SET_WITH_COUNTER(set))
-		ip_set_update_counter(ext_counter(x, set), ext, mext, flags);
-	if (SET_WITH_SKBINFO(set))
-		ip_set_get_skbinfo(ext_skbinfo(x, set), ext, mext, flags);
-	return 1;
+	return ip_set_match_extensions(set, ext, mext, flags, x);
 }
 
 static int
@@ -227,6 +220,7 @@ mtype_list(const struct ip_set *set,
 	rcu_read_lock();
 	for (; cb->args[IPSET_CB_ARG0] < map->elements;
 	     cb->args[IPSET_CB_ARG0]++) {
+		cond_resched_rcu();
 		id = cb->args[IPSET_CB_ARG0];
 		x = get_ext(set, map, id);
 		if (!test_bit(id, map->members) ||
diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c
index d8975a0b4282..488d6d05c65c 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ip.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ip.c
@@ -263,12 +263,8 @@ bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
 		ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &last_ip);
 		if (ret)
 			return ret;
-		if (first_ip > last_ip) {
-			u32 tmp = first_ip;
-
-			first_ip = last_ip;
-			last_ip = tmp;
-		}
+		if (first_ip > last_ip)
+			swap(first_ip, last_ip);
 	} else if (tb[IPSET_ATTR_CIDR]) {
 		u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
 
diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index 4c279fbd2d5d..c00b6a2e8e3c 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -337,12 +337,8 @@ bitmap_ipmac_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
 		ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &last_ip);
 		if (ret)
 			return ret;
-		if (first_ip > last_ip) {
-			u32 tmp = first_ip;
-
-			first_ip = last_ip;
-			last_ip = tmp;
-		}
+		if (first_ip > last_ip)
+			swap(first_ip, last_ip);
 	} else if (tb[IPSET_ATTR_CIDR]) {
 		u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
 
diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c
index 7f9bbd7c98b5..b561ca8b3659 100644
--- a/net/netfilter/ipset/ip_set_bitmap_port.c
+++ b/net/netfilter/ipset/ip_set_bitmap_port.c
@@ -238,12 +238,8 @@ bitmap_port_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
 
 	first_port = ip_set_get_h16(tb[IPSET_ATTR_PORT]);
 	last_port = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]);
-	if (first_port > last_port) {
-		u16 tmp = first_port;
-
-		first_port = last_port;
-		last_port = tmp;
-	}
+	if (first_port > last_port)
+		swap(first_port, last_port);
 
 	elements = last_port - first_port + 1;
 	set->dsize = ip_set_elem_len(set, tb, 0, 0);
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index cf84f7b37cd9..975a85a48d39 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -57,7 +57,7 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET);
 
 /* When the nfnl mutex is held: */
 #define ip_set_dereference(p)		\
-	rcu_dereference_protected(p, 1)
+	rcu_dereference_protected(p, lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET))
 #define ip_set(inst, id)		\
 	ip_set_dereference((inst)->ip_set_list)[id]
 
@@ -472,6 +472,31 @@ ip_set_put_extensions(struct sk_buff *skb, const struct ip_set *set,
 }
 EXPORT_SYMBOL_GPL(ip_set_put_extensions);
 
+bool
+ip_set_match_extensions(struct ip_set *set, const struct ip_set_ext *ext,
+			struct ip_set_ext *mext, u32 flags, void *data)
+{
+	if (SET_WITH_TIMEOUT(set) &&
+	    ip_set_timeout_expired(ext_timeout(data, set)))
+		return false;
+	if (SET_WITH_COUNTER(set)) {
+		struct ip_set_counter *counter = ext_counter(data, set);
+
+		if (flags & IPSET_FLAG_MATCH_COUNTERS &&
+		    !(ip_set_match_counter(ip_set_get_packets(counter),
+				mext->packets, mext->packets_op) &&
+		      ip_set_match_counter(ip_set_get_bytes(counter),
+				mext->bytes, mext->bytes_op)))
+			return false;
+		ip_set_update_counter(counter, ext, flags);
+	}
+	if (SET_WITH_SKBINFO(set))
+		ip_set_get_skbinfo(ext_skbinfo(data, set),
+				   ext, mext, flags);
+	return true;
+}
+EXPORT_SYMBOL_GPL(ip_set_match_extensions);
+
 /* Creating/destroying/renaming/swapping affect the existence and
  * the properties of a set. All of these can be executed from userspace
  * only and serialized by the nfnl mutex indirectly from nfnetlink.
@@ -1386,11 +1411,9 @@ dump_last:
 				goto next_set;
 			if (set->variant->uref)
 				set->variant->uref(set, cb, true);
-			/* Fall through and add elements */
+			/* fall through */
 		default:
-			rcu_read_lock_bh();
 			ret = set->variant->list(set, skb, cb);
-			rcu_read_unlock_bh();
 			if (!cb->args[IPSET_CB_ARG0])
 				/* Set is done, proceed with next one */
 				goto next_set;
@@ -2055,6 +2078,7 @@ ip_set_net_exit(struct net *net)
 
 	inst->is_deleted = true; /* flag for ip_set_nfnl_put */
 
+	nfnl_lock(NFNL_SUBSYS_IPSET);
 	for (i = 0; i < inst->ip_set_max; i++) {
 		set = ip_set(inst, i);
 		if (set) {
@@ -2062,6 +2086,7 @@ ip_set_net_exit(struct net *net)
 			ip_set_destroy_set(set);
 		}
 	}
+	nfnl_unlock(NFNL_SUBSYS_IPSET);
 	kfree(rcu_dereference_protected(inst->ip_set_list, 1));
 }
 
@@ -2097,7 +2122,6 @@ ip_set_init(void)
 		return ret;
 	}
 
-	pr_info("ip_set: protocol %u\n", IPSET_PROTOCOL);
 	return 0;
 }
 
@@ -2113,3 +2137,5 @@ ip_set_fini(void)
 
 module_init(ip_set_init);
 module_exit(ip_set_fini);
+
+MODULE_DESCRIPTION("ip_set: protocol " __stringify(IPSET_PROTOCOL));
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index efffc8eabafe..bbad940c0137 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -917,12 +917,9 @@ static inline int
 mtype_data_match(struct mtype_elem *data, const struct ip_set_ext *ext,
 		 struct ip_set_ext *mext, struct ip_set *set, u32 flags)
 {
-	if (SET_WITH_COUNTER(set))
-		ip_set_update_counter(ext_counter(data, set),
-				      ext, mext, flags);
-	if (SET_WITH_SKBINFO(set))
-		ip_set_get_skbinfo(ext_skbinfo(data, set),
-				   ext, mext, flags);
+	if (!ip_set_match_extensions(set, ext, mext, flags, data))
+		return 0;
+	/* nomatch entries return -ENOTEMPTY */
 	return mtype_do_data_match(data);
 }
 
@@ -941,9 +938,9 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d,
 	struct mtype_elem *data;
 #if IPSET_NET_COUNT == 2
 	struct mtype_elem orig = *d;
-	int i, j = 0, k;
+	int ret, i, j = 0, k;
 #else
-	int i, j = 0;
+	int ret, i, j = 0;
 #endif
 	u32 key, multi = 0;
 
@@ -969,18 +966,13 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d,
 			data = ahash_data(n, i, set->dsize);
 			if (!mtype_data_equal(data, d, &multi))
 				continue;
-			if (SET_WITH_TIMEOUT(set)) {
-				if (!ip_set_timeout_expired(
-						ext_timeout(data, set)))
-					return mtype_data_match(data, ext,
-								mext, set,
-								flags);
+			ret = mtype_data_match(data, ext, mext, set, flags);
+			if (ret != 0)
+				return ret;
 #ifdef IP_SET_HASH_WITH_MULTI
-				multi = 0;
+			/* No match, reset multiple match flag */
+			multi = 0;
 #endif
-			} else
-				return mtype_data_match(data, ext,
-							mext, set, flags);
 		}
 #if IPSET_NET_COUNT == 2
 		}
@@ -1027,12 +1019,11 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 		if (!test_bit(i, n->used))
 			continue;
 		data = ahash_data(n, i, set->dsize);
-		if (mtype_data_equal(data, d, &multi) &&
-		    !(SET_WITH_TIMEOUT(set) &&
-		      ip_set_timeout_expired(ext_timeout(data, set)))) {
-			ret = mtype_data_match(data, ext, mext, set, flags);
+		if (!mtype_data_equal(data, d, &multi))
+			continue;
+		ret = mtype_data_match(data, ext, mext, set, flags);
+		if (ret != 0)
 			goto out;
-		}
 	}
 out:
 	return ret;
@@ -1143,6 +1134,7 @@ mtype_list(const struct ip_set *set,
 	rcu_read_lock();
 	for (; cb->args[IPSET_CB_ARG0] < jhash_size(t->htable_bits);
 	     cb->args[IPSET_CB_ARG0]++) {
+		cond_resched_rcu();
 		incomplete = skb_tail_pointer(skb);
 		n = rcu_dereference(hbucket(t, cb->args[IPSET_CB_ARG0]));
 		pr_debug("cb->arg bucket: %lu, t %p n %p\n",
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index e864681b8dc5..072a658fde04 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -55,8 +55,9 @@ list_set_ktest(struct ip_set *set, const struct sk_buff *skb,
 	       struct ip_set_adt_opt *opt, const struct ip_set_ext *ext)
 {
 	struct list_set *map = set->data;
+	struct ip_set_ext *mext = &opt->ext;
 	struct set_elem *e;
-	u32 cmdflags = opt->cmdflags;
+	u32 flags = opt->cmdflags;
 	int ret;
 
 	/* Don't lookup sub-counters at all */
@@ -64,21 +65,11 @@ list_set_ktest(struct ip_set *set, const struct sk_buff *skb,
 	if (opt->cmdflags & IPSET_FLAG_SKIP_SUBCOUNTER_UPDATE)
 		opt->cmdflags &= ~IPSET_FLAG_SKIP_COUNTER_UPDATE;
 	list_for_each_entry_rcu(e, &map->members, list) {
-		if (SET_WITH_TIMEOUT(set) &&
-		    ip_set_timeout_expired(ext_timeout(e, set)))
-			continue;
 		ret = ip_set_test(e->id, skb, par, opt);
-		if (ret > 0) {
-			if (SET_WITH_COUNTER(set))
-				ip_set_update_counter(ext_counter(e, set),
-						      ext, &opt->ext,
-						      cmdflags);
-			if (SET_WITH_SKBINFO(set))
-				ip_set_get_skbinfo(ext_skbinfo(e, set),
-						   ext, &opt->ext,
-						   cmdflags);
-			return ret;
-		}
+		if (ret <= 0)
+			continue;
+		if (ip_set_match_extensions(set, ext, mext, flags, e))
+			return 1;
 	}
 	return 0;
 }