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, they are:

1) Stash ctinfo 3-bit field into pointer to nf_conntrack object from
   sk_buff so we only access one single cacheline in the conntrack
   hotpath. Patchset from Florian Westphal.

2) Don't leak pointer to internal structures when exporting x_tables
   ruleset back to userspace, from Willem DeBruijn. This includes new
   helper functions to copy data to userspace such as xt_data_to_user()
   as well as conversions of our ip_tables, ip6_tables and arp_tables
   clients to use it. Not surprinsingly, ebtables requires an ad-hoc
   update. There is also a new field in x_tables extensions to indicate
   the amount of bytes that we copy to userspace.

3) Add nf_log_all_netns sysctl: This new knob allows you to enable
   logging via nf_log infrastructure for all existing netnamespaces.
   Given the effort to provide pernet syslog has been discontinued,
   let's provide a way to restore logging using netfilter kernel logging
   facilities in trusted environments. Patch from Michal Kubecek.

4) Validate SCTP checksum from conntrack helper, from Davide Caratti.

5) Merge UDPlite conntrack and NAT helpers into UDP, this was mostly
   a copy&paste from the original helper, from Florian Westphal.

6) Reset netfilter state when duplicating packets, also from Florian.

7) Remove unnecessary check for broadcast in IPv6 in pkttype match and
   nft_meta, from Liping Zhang.

8) Add missing code to deal with loopback packets from nft_meta when
   used by the netdev family, also from Liping.

9) Several cleanups on nf_tables, one to remove unnecessary check from
   the netlink control plane path to add table, set and stateful objects
   and code consolidation when unregister chain hooks, from Gao Feng.

10) Fix harmless reference counter underflow in IPVS that, however,
    results in problems with the introduction of the new refcount_t
    type, from David Windsor.

11) Enable LIBCRC32C from nf_ct_sctp instead of nf_nat_sctp,
    from Davide Caratti.

12) Missing documentation on nf_tables uapi header, from Liping Zhang.

13) Use rb_entry() helper in xt_connlimit, from Geliang Tang.
====================

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

9 files changed, 31 insertions, 47 deletions

diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index a467e1236c43..6241a81fd7f5 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -677,11 +677,6 @@ static int copy_entries_to_user(unsigned int total_size,
 		return PTR_ERR(counters);
 
 	loc_cpu_entry = private->entries;
-	/* ... then copy entire thing ... */
-	if (copy_to_user(userptr, loc_cpu_entry, total_size) != 0) {
-		ret = -EFAULT;
-		goto free_counters;
-	}
 
 	/* FIXME: use iterator macros --RR */
 	/* ... then go back and fix counters and names */
@@ -689,6 +684,10 @@ static int copy_entries_to_user(unsigned int total_size,
 		const struct xt_entry_target *t;
 
 		e = (struct arpt_entry *)(loc_cpu_entry + off);
+		if (copy_to_user(userptr + off, e, sizeof(*e))) {
+			ret = -EFAULT;
+			goto free_counters;
+		}
 		if (copy_to_user(userptr + off
 				 + offsetof(struct arpt_entry, counters),
 				 &counters[num],
@@ -698,11 +697,7 @@ static int copy_entries_to_user(unsigned int total_size,
 		}
 
 		t = arpt_get_target_c(e);
-		if (copy_to_user(userptr + off + e->target_offset
-				 + offsetof(struct xt_entry_target,
-					    u.user.name),
-				 t->u.kernel.target->name,
-				 strlen(t->u.kernel.target->name)+1) != 0) {
+		if (xt_target_to_user(t, userptr + off + e->target_offset)) {
 			ret = -EFAULT;
 			goto free_counters;
 		}
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 91656a1d8fbd..384b85713e06 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -826,10 +826,6 @@ copy_entries_to_user(unsigned int total_size,
 		return PTR_ERR(counters);
 
 	loc_cpu_entry = private->entries;
-	if (copy_to_user(userptr, loc_cpu_entry, total_size) != 0) {
-		ret = -EFAULT;
-		goto free_counters;
-	}
 
 	/* FIXME: use iterator macros --RR */
 	/* ... then go back and fix counters and names */
@@ -839,6 +835,10 @@ copy_entries_to_user(unsigned int total_size,
 		const struct xt_entry_target *t;
 
 		e = (struct ipt_entry *)(loc_cpu_entry + off);
+		if (copy_to_user(userptr + off, e, sizeof(*e))) {
+			ret = -EFAULT;
+			goto free_counters;
+		}
 		if (copy_to_user(userptr + off
 				 + offsetof(struct ipt_entry, counters),
 				 &counters[num],
@@ -852,23 +852,14 @@ copy_entries_to_user(unsigned int total_size,
 		     i += m->u.match_size) {
 			m = (void *)e + i;
 
-			if (copy_to_user(userptr + off + i
-					 + offsetof(struct xt_entry_match,
-						    u.user.name),
-					 m->u.kernel.match->name,
-					 strlen(m->u.kernel.match->name)+1)
-			    != 0) {
+			if (xt_match_to_user(m, userptr + off + i)) {
 				ret = -EFAULT;
 				goto free_counters;
 			}
 		}
 
 		t = ipt_get_target_c(e);
-		if (copy_to_user(userptr + off + e->target_offset
-				 + offsetof(struct xt_entry_target,
-					    u.user.name),
-				 t->u.kernel.target->name,
-				 strlen(t->u.kernel.target->name)+1) != 0) {
+		if (xt_target_to_user(t, userptr + off + e->target_offset)) {
 			ret = -EFAULT;
 			goto free_counters;
 		}
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 0a783cd73faf..52f26459efc3 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -485,6 +485,7 @@ static struct xt_target clusterip_tg_reg __read_mostly = {
 	.checkentry	= clusterip_tg_check,
 	.destroy	= clusterip_tg_destroy,
 	.targetsize	= sizeof(struct ipt_clusterip_tgt_info),
+	.usersize	= offsetof(struct ipt_clusterip_tgt_info, config),
 #ifdef CONFIG_COMPAT
 	.compatsize	= sizeof(struct compat_ipt_clusterip_tgt_info),
 #endif /* CONFIG_COMPAT */
diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index 30c0de53e254..3240a2614e82 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -57,8 +57,7 @@ synproxy_send_tcp(struct net *net,
 		goto free_nskb;
 
 	if (nfct) {
-		nskb->nfct = nfct;
-		nskb->nfctinfo = ctinfo;
+		nf_ct_set(nskb, (struct nf_conn *)nfct, ctinfo);
 		nf_conntrack_get(nfct);
 	}
 
@@ -107,8 +106,8 @@ synproxy_send_client_synack(struct net *net,
 
 	synproxy_build_options(nth, opts);
 
-	synproxy_send_tcp(net, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY,
-			  niph, nth, tcp_hdr_size);
+	synproxy_send_tcp(net, skb, nskb, skb_nfct(skb),
+			  IP_CT_ESTABLISHED_REPLY, niph, nth, tcp_hdr_size);
 }
 
 static void
@@ -230,8 +229,8 @@ synproxy_send_client_ack(struct net *net,
 
 	synproxy_build_options(nth, opts);
 
-	synproxy_send_tcp(net, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY,
-			  niph, nth, tcp_hdr_size);
+	synproxy_send_tcp(net, skb, nskb, skb_nfct(skb),
+			  IP_CT_ESTABLISHED_REPLY, niph, nth, tcp_hdr_size);
 }
 
 static bool
diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
index d075b3cf2400..73c591d8a9a8 100644
--- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
@@ -128,16 +128,16 @@ static bool icmp_new(struct nf_conn *ct, const struct sk_buff *skb,
 /* Returns conntrack if it dealt with ICMP, and filled in skb fields */
 static int
 icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,
-		 enum ip_conntrack_info *ctinfo,
 		 unsigned int hooknum)
 {
 	struct nf_conntrack_tuple innertuple, origtuple;
 	const struct nf_conntrack_l4proto *innerproto;
 	const struct nf_conntrack_tuple_hash *h;
 	const struct nf_conntrack_zone *zone;
+	enum ip_conntrack_info ctinfo;
 	struct nf_conntrack_zone tmp;
 
-	NF_CT_ASSERT(skb->nfct == NULL);
+	NF_CT_ASSERT(!skb_nfct(skb));
 	zone = nf_ct_zone_tmpl(tmpl, skb, &tmp);
 
 	/* Are they talking about one of our connections? */
@@ -160,7 +160,7 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,
 		return -NF_ACCEPT;
 	}
 
-	*ctinfo = IP_CT_RELATED;
+	ctinfo = IP_CT_RELATED;
 
 	h = nf_conntrack_find_get(net, zone, &innertuple);
 	if (!h) {
@@ -169,11 +169,10 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,
 	}
 
 	if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY)
-		*ctinfo += IP_CT_IS_REPLY;
+		ctinfo += IP_CT_IS_REPLY;
 
 	/* Update skb to refer to this connection */
-	skb->nfct = &nf_ct_tuplehash_to_ctrack(h)->ct_general;
-	skb->nfctinfo = *ctinfo;
+	nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo);
 	return NF_ACCEPT;
 }
 
@@ -181,7 +180,7 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,
 static int
 icmp_error(struct net *net, struct nf_conn *tmpl,
 	   struct sk_buff *skb, unsigned int dataoff,
-	   enum ip_conntrack_info *ctinfo, u_int8_t pf, unsigned int hooknum)
+	   u8 pf, unsigned int hooknum)
 {
 	const struct icmphdr *icmph;
 	struct icmphdr _ih;
@@ -225,7 +224,7 @@ icmp_error(struct net *net, struct nf_conn *tmpl,
 	    icmph->type != ICMP_REDIRECT)
 		return NF_ACCEPT;
 
-	return icmp_error_message(net, tmpl, skb, ctinfo, hooknum);
+	return icmp_error_message(net, tmpl, skb, hooknum);
 }
 
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 49bd6a54404f..346bf7ccac08 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -45,7 +45,7 @@ static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum,
 {
 	u16 zone_id = NF_CT_DEFAULT_ZONE_ID;
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
-	if (skb->nfct) {
+	if (skb_nfct(skb)) {
 		enum ip_conntrack_info ctinfo;
 		const struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
 
@@ -75,7 +75,7 @@ static unsigned int ipv4_conntrack_defrag(void *priv,
 #if !IS_ENABLED(CONFIG_NF_NAT)
 	/* Previously seen (loopback)?  Ignore.  Do this before
 	   fragment check. */
-	if (skb->nfct && !nf_ct_is_template((struct nf_conn *)skb->nfct))
+	if (skb_nfct(skb) && !nf_ct_is_template((struct nf_conn *)skb_nfct(skb)))
 		return NF_ACCEPT;
 #endif
 #endif
diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c
index cf986e1c7bbd..f0dbff05fc28 100644
--- a/net/ipv4/netfilter/nf_dup_ipv4.c
+++ b/net/ipv4/netfilter/nf_dup_ipv4.c
@@ -68,10 +68,9 @@ void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum,
 
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 	/* Avoid counting cloned packets towards the original connection. */
-	nf_conntrack_put(skb->nfct);
-	skb->nfct     = &nf_ct_untracked_get()->ct_general;
-	skb->nfctinfo = IP_CT_NEW;
-	nf_conntrack_get(skb->nfct);
+	nf_reset(skb);
+	nf_ct_set(skb, nf_ct_untracked_get(), IP_CT_NEW);
+	nf_conntrack_get(skb_nfct(skb));
 #endif
 	/*
 	 * If we are in PREROUTING/INPUT, decrease the TTL to mitigate potential
diff --git a/net/ipv4/netfilter/nf_log_arp.c b/net/ipv4/netfilter/nf_log_arp.c
index b24795e2ee6d..f6f713376e6e 100644
--- a/net/ipv4/netfilter/nf_log_arp.c
+++ b/net/ipv4/netfilter/nf_log_arp.c
@@ -87,7 +87,7 @@ static void nf_log_arp_packet(struct net *net, u_int8_t pf,
 	struct nf_log_buf *m;
 
 	/* FIXME: Disabled from containers until syslog ns is supported */
-	if (!net_eq(net, &init_net))
+	if (!net_eq(net, &init_net) && !sysctl_nf_log_all_netns)
 		return;
 
 	m = nf_log_buf_open();
diff --git a/net/ipv4/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c
index 856648966f4c..c83a9963269b 100644
--- a/net/ipv4/netfilter/nf_log_ipv4.c
+++ b/net/ipv4/netfilter/nf_log_ipv4.c
@@ -319,7 +319,7 @@ static void nf_log_ip_packet(struct net *net, u_int8_t pf,
 	struct nf_log_buf *m;
 
 	/* FIXME: Disabled from containers until syslog ns is supported */
-	if (!net_eq(net, &init_net))
+	if (!net_eq(net, &init_net) && !sysctl_nf_log_all_netns)
 		return;
 
 	m = nf_log_buf_open();