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 net-next, they are:

1) A couple of cleanups for the netfilter core hook from Eric Biederman.

2) Net namespace hook registration, also from Eric. This adds a dependency with
   the rtnl_lock. This should be fine by now but we have to keep an eye on this
   because if we ever get the per-subsys nfnl_lock before rtnl we have may
   problems in the future. But we have room to remove this in the future by
   propagating the complexity to the clients, by registering hooks for the init
   netns functions.

3) Update nf_tables to use the new net namespace hook infrastructure, also from
   Eric.

4) Three patches to refine and to address problems from the new net namespace
   hook infrastructure.

5) Switch to alternate jumpstack in xtables iff the packet is reentering. This
   only applies to a very special case, the TEE target, but Eric Dumazet
   reports that this is slowing down things for everyone else. So let's only
   switch to the alternate jumpstack if the tee target is in used through a
   static key. This batch also comes with offline precalculation of the
   jumpstack based on the callchain depth. From Florian Westphal.

6) Minimal SCTP multihoming support for our conntrack helper, from Michal
   Kubecek.

7) Reduce nf_bridge_info per skbuff scratchpad area to 32 bytes, from Florian
   Westphal.

8) Fix several checkpatch errors in bridge netfilter, from Bernhard Thaler.

9) Get rid of useless debug message in ip6t_REJECT, from Subash Abhinov.
====================

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

3 files changed, 33 insertions, 31 deletions

diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 3c35ced39b42..4e21f80228be 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -305,7 +305,7 @@ static void trace_packet(const struct sk_buff *skb,
 }
 #endif
 
-static inline __pure struct ip6t_entry *
+static inline struct ip6t_entry *
 ip6t_next_entry(const struct ip6t_entry *entry)
 {
 	return (void *)entry + entry->next_offset;
@@ -324,12 +324,13 @@ ip6t_do_table(struct sk_buff *skb,
 	const char *indev, *outdev;
 	const void *table_base;
 	struct ip6t_entry *e, **jumpstack;
-	unsigned int *stackptr, origptr, cpu;
+	unsigned int stackidx, cpu;
 	const struct xt_table_info *private;
 	struct xt_action_param acpar;
 	unsigned int addend;
 
 	/* Initialization */
+	stackidx = 0;
 	indev = state->in ? state->in->name : nulldevname;
 	outdev = state->out ? state->out->name : nulldevname;
 	/* We handle fragments by dealing with the first fragment as
@@ -357,8 +358,16 @@ ip6t_do_table(struct sk_buff *skb,
 	cpu        = smp_processor_id();
 	table_base = private->entries;
 	jumpstack  = (struct ip6t_entry **)private->jumpstack[cpu];
-	stackptr   = per_cpu_ptr(private->stackptr, cpu);
-	origptr    = *stackptr;
+
+	/* Switch to alternate jumpstack if we're being invoked via TEE.
+	 * TEE issues XT_CONTINUE verdict on original skb so we must not
+	 * clobber the jumpstack.
+	 *
+	 * For recursion via REJECT or SYNPROXY the stack will be clobbered
+	 * but it is no problem since absolute verdict is issued by these.
+	 */
+	if (static_key_false(&xt_tee_enabled))
+		jumpstack += private->stacksize * __this_cpu_read(nf_skb_duplicated);
 
 	e = get_entry(table_base, private->hook_entry[hook]);
 
@@ -406,20 +415,16 @@ ip6t_do_table(struct sk_buff *skb,
 					verdict = (unsigned int)(-v) - 1;
 					break;
 				}
-				if (*stackptr <= origptr)
+				if (stackidx == 0)
 					e = get_entry(table_base,
 					    private->underflow[hook]);
 				else
-					e = ip6t_next_entry(jumpstack[--*stackptr]);
+					e = ip6t_next_entry(jumpstack[--stackidx]);
 				continue;
 			}
 			if (table_base + v != ip6t_next_entry(e) &&
 			    !(e->ipv6.flags & IP6T_F_GOTO)) {
-				if (*stackptr >= private->stacksize) {
-					verdict = NF_DROP;
-					break;
-				}
-				jumpstack[(*stackptr)++] = e;
+				jumpstack[stackidx++] = e;
 			}
 
 			e = get_entry(table_base, v);
@@ -437,8 +442,6 @@ ip6t_do_table(struct sk_buff *skb,
 			break;
 	} while (!acpar.hotdrop);
 
-	*stackptr = origptr;
-
  	xt_write_recseq_end(addend);
  	local_bh_enable();
 
@@ -452,11 +455,15 @@ ip6t_do_table(struct sk_buff *skb,
 }
 
 /* Figures out from what hook each rule can be called: returns 0 if
-   there are loops.  Puts hook bitmask in comefrom. */
+ * there are loops.  Puts hook bitmask in comefrom.
+ *
+ * Keeps track of largest call depth seen and stores it in newinfo->stacksize.
+ */
 static int
-mark_source_chains(const struct xt_table_info *newinfo,
+mark_source_chains(struct xt_table_info *newinfo,
 		   unsigned int valid_hooks, void *entry0)
 {
+	unsigned int calldepth, max_calldepth = 0;
 	unsigned int hook;
 
 	/* No recursion; use packet counter to save back ptrs (reset
@@ -470,6 +477,7 @@ mark_source_chains(const struct xt_table_info *newinfo,
 
 		/* Set initial back pointer. */
 		e->counters.pcnt = pos;
+		calldepth = 0;
 
 		for (;;) {
 			const struct xt_standard_target *t
@@ -531,6 +539,8 @@ mark_source_chains(const struct xt_table_info *newinfo,
 					(entry0 + pos + size);
 				e->counters.pcnt = pos;
 				pos += size;
+				if (calldepth > 0)
+					--calldepth;
 			} else {
 				int newpos = t->verdict;
 
@@ -544,6 +554,11 @@ mark_source_chains(const struct xt_table_info *newinfo,
 								newpos);
 						return 0;
 					}
+					if (entry0 + newpos != ip6t_next_entry(e) &&
+					    !(e->ipv6.flags & IP6T_F_GOTO) &&
+					    ++calldepth > max_calldepth)
+						max_calldepth = calldepth;
+
 					/* This a jump; chase it. */
 					duprintf("Jump rule %u -> %u\n",
 						 pos, newpos);
@@ -560,6 +575,7 @@ mark_source_chains(const struct xt_table_info *newinfo,
 		next:
 		duprintf("Finished chain %u\n", hook);
 	}
+	newinfo->stacksize = max_calldepth;
 	return 1;
 }
 
@@ -839,9 +855,6 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
 		if (ret != 0)
 			return ret;
 		++i;
-		if (strcmp(ip6t_get_target(iter)->u.user.name,
-		    XT_ERROR_TARGET) == 0)
-			++newinfo->stacksize;
 	}
 
 	if (i != repl->num_entries) {
@@ -1754,9 +1767,6 @@ translate_compat_table(struct net *net,
 		if (ret != 0)
 			break;
 		++i;
-		if (strcmp(ip6t_get_target(iter1)->u.user.name,
-		    XT_ERROR_TARGET) == 0)
-			++newinfo->stacksize;
 	}
 	if (ret) {
 		/*
diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c
index 12331efd49cf..567367a75172 100644
--- a/net/ipv6/netfilter/ip6t_REJECT.c
+++ b/net/ipv6/netfilter/ip6t_REJECT.c
@@ -35,14 +35,12 @@ MODULE_AUTHOR("Yasuyuki KOZAKAI <yasuyuki.kozakai@toshiba.co.jp>");
 MODULE_DESCRIPTION("Xtables: packet \"rejection\" target for IPv6");
 MODULE_LICENSE("GPL");
 
-
 static unsigned int
 reject_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 {
 	const struct ip6t_reject_info *reject = par->targinfo;
 	struct net *net = dev_net((par->in != NULL) ? par->in : par->out);
 
-	pr_debug("%s: medium point\n", __func__);
 	switch (reject->with) {
 	case IP6T_ICMP6_NO_ROUTE:
 		nf_send_unreach6(net, skb, ICMPV6_NOROUTE, par->hooknum);
@@ -65,9 +63,6 @@ reject_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 	case IP6T_TCP_RESET:
 		nf_send_reset6(net, skb, par->hooknum);
 		break;
-	default:
-		net_info_ratelimited("case %u not handled yet\n", reject->with);
-		break;
 	}
 
 	return NF_DROP;
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index a45db0b4785c..267fb8d5876e 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -39,12 +39,9 @@ static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum,
 	if (skb->nfct)
 		zone = nf_ct_zone((struct nf_conn *)skb->nfct);
 #endif
-
-#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-	if (skb->nf_bridge &&
-	    skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)
+	if (nf_bridge_in_prerouting(skb))
 		return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone;
-#endif
+
 	if (hooknum == NF_INET_PRE_ROUTING)
 		return IP6_DEFRAG_CONNTRACK_IN + zone;
 	else