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

Pablo Neira Ayuso says:

====================
Netfilter updates for net-next

The following patchset contains Netfilter updates for your net-next
tree. Basically, updates to the conntrack core, enhancements for
nf_tables, conversion of netfilter hooks from linked list to array to
improve memory locality and asorted improvements for the Netfilter
codebase. More specifically, they are:

1) Add expection to hashes after timer initialization to prevent
   access from another CPU that walks on the hashes and calls
   del_timer(), from Florian Westphal.

2) Don't update nf_tables chain counters from hot path, this is only
   used by the x_tables compatibility layer.

3) Get rid of nested rcu_read_lock() calls from netfilter hook path.
   Hooks are always guaranteed to run from rcu read side, so remove
   nested rcu_read_lock() where possible. Patch from Taehee Yoo.

4) nf_tables new ruleset generation notifications include PID and name
   of the process that has updated the ruleset, from Phil Sutter.

5) Use skb_header_pointer() from nft_fib, so we can reuse this code from
   the nf_family netdev family. Patch from Pablo M. Bermudo.

6) Add support for nft_fib in nf_tables netdev family, also from Pablo.

7) Use deferrable workqueue for conntrack garbage collection, to reduce
   power consumption, from Patch from Subash Abhinov Kasiviswanathan.

8) Add nf_ct_expect_iterate_net() helper and use it. From Florian
   Westphal.

9) Call nf_ct_unconfirmed_destroy only from cttimeout, from Florian.

10) Drop references on conntrack removal path when skbuffs has escaped via
    nfqueue, from Florian.

11) Don't queue packets to nfqueue with dying conntrack, from Florian.

12) Constify nf_hook_ops structure, from Florian.

13) Remove neededlessly branch in nf_tables trace code, from Phil Sutter.

14) Add nla_strdup(), from Phil Sutter.

15) Rise nf_tables objects name size up to 255 chars, people want to use
    DNS names, so increase this according to what RFC 1035 specifies.
    Patch series from Phil Sutter.

16) Kill nf_conntrack_default_on, it's broken. Default on conntrack hook
    registration on demand, suggested by Eric Dumazet, patch from Florian.

17) Remove unused variables in compat_copy_entry_from_user both in
    ip_tables and arp_tables code. Patch from Taehee Yoo.

18) Constify struct nf_conntrack_l4proto, from Julia Lawall.

19) Constify nf_loginfo structure, also from Julia.

20) Use a single rb root in connlimit, from Taehee Yoo.

21) Remove unused netfilter_queue_init() prototype, from Taehee Yoo.

22) Use audit_log() instead of open-coding it, from Geliang Tang.

23) Allow to mangle tcp options via nft_exthdr, from Florian.

24) Allow to fetch TCP MSS from nft_rt, from Florian. This includes
    a fix for a miscalculation of the minimal length.

25) Simplify branch logic in h323 helper, from Nick Desaulniers.

26) Calculate netlink attribute size for conntrack tuple at compile
    time, from Florian.

27) Remove protocol name field from nf_conntrack_{l3,l4}proto structure.
    From Florian.

28) Remove holes in nf_conntrack_l4proto structure, so it becomes
    smaller. From Florian.

29) Get rid of print_tuple() indirection for /proc conntrack listing.
    Place all the code in net/netfilter/nf_conntrack_standalone.c.
    Patch from Florian.

30) Do not built in print_conntrack() if CONFIG_NF_CONNTRACK_PROCFS is
    off. From Florian.

31) Constify most nf_conntrack_{l3,l4}proto helper functions, from
    Florian.

32) Fix broken indentation in ebtables extensions, from Colin Ian King.

33) Fix several harmless sparse warning, from Florian.

34) Convert netfilter hook infrastructure to use array for better memory
    locality, joint work done by Florian and Aaron Conole. Moreover, add
    some instrumentation to debug this.

35) Batch nf_unregister_net_hooks() calls, to call synchronize_net once
    per batch, from Florian.

36) Get rid of noisy logging in ICMPv6 conntrack helper, from Florian.

37) Get rid of obsolete NFDEBUG() instrumentation, from Varsha Rao.

38) Remove unused code in the generic protocol tracker, from Davide
    Caratti.

I think I will have material for a second Netfilter batch in my queue if
time allow to make it fit in this merge window.
====================

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

9 files changed, 40 insertions, 60 deletions

diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c
index 77f7f8c7d93d..5bd419c1abc8 100644
--- a/net/ipv6/ila/ila_xlat.c
+++ b/net/ipv6/ila/ila_xlat.c
@@ -208,7 +208,7 @@ ila_nf_input(void *priv,
 	return NF_ACCEPT;
 }
 
-static struct nf_hook_ops ila_nf_hook_ops[] __read_mostly = {
+static const struct nf_hook_ops ila_nf_hook_ops[] = {
 	{
 		.hook = ila_nf_input,
 		.pf = NFPROTO_IPV6,
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 1f90644056ac..9f6644958e5e 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -176,7 +176,7 @@ static const char *const comments[] = {
 	[NF_IP6_TRACE_COMMENT_POLICY]	= "policy",
 };
 
-static struct nf_loginfo trace_loginfo = {
+static const struct nf_loginfo trace_loginfo = {
 	.type = NF_LOG_TYPE_LOG,
 	.u = {
 		.log = {
diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c
index ce203dd729e0..a5cd43d75393 100644
--- a/net/ipv6/netfilter/ip6t_SYNPROXY.c
+++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c
@@ -438,7 +438,7 @@ static unsigned int ipv6_synproxy_hook(void *priv,
 	return NF_ACCEPT;
 }
 
-static struct nf_hook_ops ipv6_synproxy_ops[] __read_mostly = {
+static const struct nf_hook_ops ipv6_synproxy_ops[] = {
 	{
 		.hook		= ipv6_synproxy_hook,
 		.pf		= NFPROTO_IPV6,
diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c
index 7d2bd940291f..991512576c8c 100644
--- a/net/ipv6/netfilter/ip6table_nat.c
+++ b/net/ipv6/netfilter/ip6table_nat.c
@@ -69,7 +69,7 @@ static unsigned int ip6table_nat_local_fn(void *priv,
 	return nf_nat_ipv6_local_fn(priv, skb, state, ip6table_nat_do_chain);
 }
 
-static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = {
+static const struct nf_hook_ops nf_nat_ipv6_ops[] = {
 	/* Before packet filtering, change destination */
 	{
 		.hook		= ip6table_nat_in,
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 4e3402486833..fe01dc953c56 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -67,13 +67,6 @@ static bool ipv6_invert_tuple(struct nf_conntrack_tuple *tuple,
 	return true;
 }
 
-static void ipv6_print_tuple(struct seq_file *s,
-			    const struct nf_conntrack_tuple *tuple)
-{
-	seq_printf(s, "src=%pI6 dst=%pI6 ",
-		   tuple->src.u3.ip6, tuple->dst.u3.ip6);
-}
-
 static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 			    unsigned int *dataoff, u_int8_t *protonum)
 {
@@ -191,7 +184,7 @@ static unsigned int ipv6_conntrack_local(void *priv,
 	return nf_conntrack_in(state->net, PF_INET6, state->hook, skb);
 }
 
-static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = {
+static const struct nf_hook_ops ipv6_conntrack_ops[] = {
 	{
 		.hook		= ipv6_conntrack_in,
 		.pf		= NFPROTO_IPV6,
@@ -308,11 +301,6 @@ static int ipv6_nlattr_to_tuple(struct nlattr *tb[],
 
 	return 0;
 }
-
-static int ipv6_nlattr_tuple_size(void)
-{
-	return nla_policy_len(ipv6_nla_policy, CTA_IP_MAX + 1);
-}
 #endif
 
 static int ipv6_hooks_register(struct net *net)
@@ -353,16 +341,15 @@ static void ipv6_hooks_unregister(struct net *net)
 
 struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 __read_mostly = {
 	.l3proto		= PF_INET6,
-	.name			= "ipv6",
 	.pkt_to_tuple		= ipv6_pkt_to_tuple,
 	.invert_tuple		= ipv6_invert_tuple,
-	.print_tuple		= ipv6_print_tuple,
 	.get_l4proto		= ipv6_get_l4proto,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.tuple_to_nlattr	= ipv6_tuple_to_nlattr,
-	.nlattr_tuple_size	= ipv6_nlattr_tuple_size,
 	.nlattr_to_tuple	= ipv6_nlattr_to_tuple,
 	.nla_policy		= ipv6_nla_policy,
+	.nla_size		= NLA_ALIGN(NLA_HDRLEN + sizeof(u32[4])) +
+				  NLA_ALIGN(NLA_HDRLEN + sizeof(u32[4])),
 #endif
 	.net_ns_get		= ipv6_hooks_register,
 	.net_ns_put		= ipv6_hooks_unregister,
@@ -398,25 +385,12 @@ static struct nf_conntrack_l4proto *builtin_l4proto6[] = {
 
 static int ipv6_net_init(struct net *net)
 {
-	int ret = 0;
-
-	ret = nf_ct_l4proto_pernet_register(net, builtin_l4proto6,
-					    ARRAY_SIZE(builtin_l4proto6));
-	if (ret < 0)
-		return ret;
-
-	ret = nf_ct_l3proto_pernet_register(net, &nf_conntrack_l3proto_ipv6);
-	if (ret < 0) {
-		pr_err("nf_conntrack_ipv6: pernet registration failed.\n");
-		nf_ct_l4proto_pernet_unregister(net, builtin_l4proto6,
-						ARRAY_SIZE(builtin_l4proto6));
-	}
-	return ret;
+	return nf_ct_l4proto_pernet_register(net, builtin_l4proto6,
+					     ARRAY_SIZE(builtin_l4proto6));
 }
 
 static void ipv6_net_exit(struct net *net)
 {
-	nf_ct_l3proto_pernet_unregister(net, &nf_conntrack_l3proto_ipv6);
 	nf_ct_l4proto_pernet_unregister(net, builtin_l4proto6,
 					ARRAY_SIZE(builtin_l4proto6));
 }
@@ -434,6 +408,12 @@ static int __init nf_conntrack_l3proto_ipv6_init(void)
 
 	need_conntrack();
 
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
+	if (WARN_ON(nla_policy_len(ipv6_nla_policy, CTA_IP_MAX + 1) !=
+	    nf_conntrack_l3proto_ipv6.nla_size))
+		return -EINVAL;
+#endif
+
 	ret = nf_register_sockopt(&so_getorigdst6);
 	if (ret < 0) {
 		pr_err("Unable to register netfilter socket option\n");
diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
index d5f028e33f65..43544b975eae 100644
--- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
@@ -84,16 +84,6 @@ static bool icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple,
 	return true;
 }
 
-/* Print out the per-protocol part of the tuple. */
-static void icmpv6_print_tuple(struct seq_file *s,
-			      const struct nf_conntrack_tuple *tuple)
-{
-	seq_printf(s, "type=%u code=%u id=%u ",
-		   tuple->dst.u.icmp.type,
-		   tuple->dst.u.icmp.code,
-		   ntohs(tuple->src.u.icmp.id));
-}
-
 static unsigned int *icmpv6_get_timeouts(struct net *net)
 {
 	return &icmpv6_pernet(net)->timeout;
@@ -131,11 +121,6 @@ static bool icmpv6_new(struct nf_conn *ct, const struct sk_buff *skb,
 		pr_debug("icmpv6: can't create new conn with type %u\n",
 			 type + 128);
 		nf_ct_dump_tuple_ipv6(&ct->tuplehash[0].tuple);
-		if (LOG_INVALID(nf_ct_net(ct), IPPROTO_ICMPV6))
-			nf_log_packet(nf_ct_net(ct), PF_INET6, 0, skb, NULL,
-				      NULL, NULL,
-				      "nf_ct_icmpv6: invalid new with type %d ",
-				      type + 128);
 		return false;
 	}
 	return true;
@@ -367,10 +352,8 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 __read_mostly =
 {
 	.l3proto		= PF_INET6,
 	.l4proto		= IPPROTO_ICMPV6,
-	.name			= "icmpv6",
 	.pkt_to_tuple		= icmpv6_pkt_to_tuple,
 	.invert_tuple		= icmpv6_invert_tuple,
-	.print_tuple		= icmpv6_print_tuple,
 	.packet			= icmpv6_packet,
 	.get_timeouts		= icmpv6_get_timeouts,
 	.new			= icmpv6_new,
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index ada60d1a991b..b326da59257f 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -74,7 +74,7 @@ static unsigned int ipv6_defrag(void *priv,
 	return err == 0 ? NF_ACCEPT : NF_DROP;
 }
 
-static struct nf_hook_ops ipv6_defrag_ops[] = {
+static const struct nf_hook_ops ipv6_defrag_ops[] = {
 	{
 		.hook		= ipv6_defrag,
 		.pf		= NFPROTO_IPV6,
diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c
index 97c724224da7..b397a8fe88b9 100644
--- a/net/ipv6/netfilter/nf_log_ipv6.c
+++ b/net/ipv6/netfilter/nf_log_ipv6.c
@@ -25,7 +25,7 @@
 #include <linux/netfilter/xt_LOG.h>
 #include <net/netfilter/nf_log.h>
 
-static struct nf_loginfo default_loginfo = {
+static const struct nf_loginfo default_loginfo = {
 	.type	= NF_LOG_TYPE_LOG,
 	.u = {
 		.log = {
diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c
index 43f91d9b086c..54b5899543ef 100644
--- a/net/ipv6/netfilter/nft_fib_ipv6.c
+++ b/net/ipv6/netfilter/nft_fib_ipv6.c
@@ -25,9 +25,9 @@ static int get_ifindex(const struct net_device *dev)
 
 static int nft_fib6_flowi_init(struct flowi6 *fl6, const struct nft_fib *priv,
 			       const struct nft_pktinfo *pkt,
-			       const struct net_device *dev)
+			       const struct net_device *dev,
+			       struct ipv6hdr *iph)
 {
-	const struct ipv6hdr *iph = ipv6_hdr(pkt->skb);
 	int lookup_flags = 0;
 
 	if (priv->flags & NFTA_FIB_F_DADDR) {
@@ -55,7 +55,8 @@ static int nft_fib6_flowi_init(struct flowi6 *fl6, const struct nft_fib *priv,
 }
 
 static u32 __nft_fib6_eval_type(const struct nft_fib *priv,
-				const struct nft_pktinfo *pkt)
+				const struct nft_pktinfo *pkt,
+				struct ipv6hdr *iph)
 {
 	const struct net_device *dev = NULL;
 	const struct nf_ipv6_ops *v6ops;
@@ -77,7 +78,7 @@ static u32 __nft_fib6_eval_type(const struct nft_fib *priv,
 	else if (priv->flags & NFTA_FIB_F_OIF)
 		dev = nft_out(pkt);
 
-	nft_fib6_flowi_init(&fl6, priv, pkt, dev);
+	nft_fib6_flowi_init(&fl6, priv, pkt, dev, iph);
 
 	v6ops = nf_get_ipv6_ops();
 	if (dev && v6ops && v6ops->chk_addr(nft_net(pkt), &fl6.daddr, dev, true))
@@ -131,9 +132,17 @@ void nft_fib6_eval_type(const struct nft_expr *expr, struct nft_regs *regs,
 			const struct nft_pktinfo *pkt)
 {
 	const struct nft_fib *priv = nft_expr_priv(expr);
+	int noff = skb_network_offset(pkt->skb);
 	u32 *dest = &regs->data[priv->dreg];
+	struct ipv6hdr *iph, _iph;
 
-	*dest = __nft_fib6_eval_type(priv, pkt);
+	iph = skb_header_pointer(pkt->skb, noff, sizeof(_iph), &_iph);
+	if (!iph) {
+		regs->verdict.code = NFT_BREAK;
+		return;
+	}
+
+	*dest = __nft_fib6_eval_type(priv, pkt, iph);
 }
 EXPORT_SYMBOL_GPL(nft_fib6_eval_type);
 
@@ -141,8 +150,10 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
 		   const struct nft_pktinfo *pkt)
 {
 	const struct nft_fib *priv = nft_expr_priv(expr);
+	int noff = skb_network_offset(pkt->skb);
 	const struct net_device *oif = NULL;
 	u32 *dest = &regs->data[priv->dreg];
+	struct ipv6hdr *iph, _iph;
 	struct flowi6 fl6 = {
 		.flowi6_iif = LOOPBACK_IFINDEX,
 		.flowi6_proto = pkt->tprot,
@@ -155,7 +166,13 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
 	else if (priv->flags & NFTA_FIB_F_OIF)
 		oif = nft_out(pkt);
 
-	lookup_flags = nft_fib6_flowi_init(&fl6, priv, pkt, oif);
+	iph = skb_header_pointer(pkt->skb, noff, sizeof(_iph), &_iph);
+	if (!iph) {
+		regs->verdict.code = NFT_BREAK;
+		return;
+	}
+
+	lookup_flags = nft_fib6_flowi_init(&fl6, priv, pkt, oif, iph);
 
 	if (nft_hook(pkt) == NF_INET_PRE_ROUTING &&
 	    nft_fib_is_loopback(pkt->skb, nft_in(pkt))) {