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 <[email protected]>

Author: davem330

include/linux/netfilter.h

@@ -11,6 +11,8 @@
 #include <linux/list.h>
 #include <linux/static_key.h>
 #include <linux/netfilter_defs.h>
+#include <linux/netdevice.h>
+#include <net/net_namespace.h>
 
 #ifdef CONFIG_NETFILTER
 static inline int NF_DROP_GETERR(int verdict)
@@ -118,6 +120,13 @@ struct nf_sockopt_ops {
 };
 
 /* Function to register/unregister hook points. */
+int nf_register_net_hook(struct net *net, const struct nf_hook_ops *ops);
+void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *ops);
+int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg,
+			  unsigned int n);
+void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg,
+			     unsigned int n);
+
 int nf_register_hook(struct nf_hook_ops *reg);
 void nf_unregister_hook(struct nf_hook_ops *reg);
 int nf_register_hooks(struct nf_hook_ops *reg, unsigned int n);
@@ -128,33 +137,26 @@ void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n);
 int nf_register_sockopt(struct nf_sockopt_ops *reg);
 void nf_unregister_sockopt(struct nf_sockopt_ops *reg);
 
-extern struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
-
 #ifdef HAVE_JUMP_LABEL
 extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
 
-static inline bool nf_hook_list_active(struct list_head *nf_hook_list,
+static inline bool nf_hook_list_active(struct list_head *hook_list,
 				       u_int8_t pf, unsigned int hook)
 {
 	if (__builtin_constant_p(pf) &&
 	    __builtin_constant_p(hook))
 		return static_key_false(&nf_hooks_needed[pf][hook]);
 
-	return !list_empty(nf_hook_list);
+	return !list_empty(hook_list);
 }
 #else
-static inline bool nf_hook_list_active(struct list_head *nf_hook_list,
+static inline bool nf_hook_list_active(struct list_head *hook_list,
 				       u_int8_t pf, unsigned int hook)
 {
-	return !list_empty(nf_hook_list);
+	return !list_empty(hook_list);
 }
 #endif
 
-static inline bool nf_hooks_active(u_int8_t pf, unsigned int hook)
-{
-	return nf_hook_list_active(&nf_hooks[pf][hook], pf, hook);
-}
-
 int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state);
 
 /**
@@ -172,10 +174,13 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook,
 				 int (*okfn)(struct sock *, struct sk_buff *),
 				 int thresh)
 {
-	if (nf_hooks_active(pf, hook)) {
+	struct net *net = dev_net(indev ? indev : outdev);
+	struct list_head *hook_list = &net->nf.hooks[pf][hook];
+
+	if (nf_hook_list_active(hook_list, pf, hook)) {
 		struct nf_hook_state state;
 
-		nf_hook_state_init(&state, &nf_hooks[pf][hook], hook, thresh,
+		nf_hook_state_init(&state, hook_list, hook, thresh,
 				   pf, indev, outdev, sk, okfn);
 		return nf_hook_slow(skb, &state);
 	}
@@ -385,4 +390,15 @@ extern struct nfq_ct_hook __rcu *nfq_ct_hook;
 static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {}
 #endif
 
+/**
+ * nf_skb_duplicated - TEE target has sent a packet
+ *
+ * When a xtables target sends a packet, the OUTPUT and POSTROUTING
+ * hooks are traversed again, i.e. nft and xtables are invoked recursively.
+ *
+ * This is used by xtables TEE target to prevent the duplicated skb from
+ * being duplicated again.
+ */
+DECLARE_PER_CPU(bool, nf_skb_duplicated);
+
 #endif /*__LINUX_NETFILTER_H*/

include/linux/netfilter/x_tables.h

@@ -3,6 +3,7 @@
 
 
 #include <linux/netdevice.h>
+#include <linux/static_key.h>
 #include <uapi/linux/netfilter/x_tables.h>
 
 /**
@@ -222,7 +223,6 @@ struct xt_table_info {
 	 * @stacksize jumps (number of user chains) can possibly be made.
 	 */
 	unsigned int stacksize;
-	unsigned int __percpu *stackptr;
 	void ***jumpstack;
 
 	unsigned char entries[0] __aligned(8);
@@ -281,6 +281,12 @@ void xt_free_table_info(struct xt_table_info *info);
  */
 DECLARE_PER_CPU(seqcount_t, xt_recseq);
 
+/* xt_tee_enabled - true if x_tables needs to handle reentrancy
+ *
+ * Enabled if current ip(6)tables ruleset has at least one -j TEE rule.
+ */
+extern struct static_key xt_tee_enabled;
+
 /**
  * xt_write_recseq_begin - start of a write section
  *

include/linux/netfilter_bridge.h

@@ -17,9 +17,6 @@ enum nf_br_hook_priorities {
 
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 
-#define BRNF_BRIDGED_DNAT		0x02
-#define BRNF_NF_BRIDGE_PREROUTING	0x08
-
 int br_handle_frame_finish(struct sock *sk, struct sk_buff *skb);
 
 static inline void br_drop_fake_rtable(struct sk_buff *skb)
@@ -63,8 +60,17 @@ nf_bridge_get_physoutdev(const struct sk_buff *skb)
 {
 	return skb->nf_bridge ? skb->nf_bridge->physoutdev : NULL;
 }
+
+static inline bool nf_bridge_in_prerouting(const struct sk_buff *skb)
+{
+	return skb->nf_bridge && skb->nf_bridge->in_prerouting;
+}
 #else
 #define br_drop_fake_rtable(skb)	        do { } while (0)
+static inline bool nf_bridge_in_prerouting(const struct sk_buff *skb)
+{
+	return false;
+}
 #endif /* CONFIG_BRIDGE_NETFILTER */
 
 #endif

include/linux/skbuff.h

@@ -174,17 +174,24 @@ struct nf_bridge_info {
 		BRNF_PROTO_8021Q,
 		BRNF_PROTO_PPPOE
 	} orig_proto:8;
-	bool			pkt_otherhost;
+	u8			pkt_otherhost:1;
+	u8			in_prerouting:1;
+	u8			bridged_dnat:1;
 	__u16			frag_max_size;
-	unsigned int		mask;
 	struct net_device	*physindev;
 	union {
-		struct net_device *physoutdev;
-		char neigh_header[8];
-	};
-	union {
+		/* prerouting: detect dnat in orig/reply direction */
 		__be32          ipv4_daddr;
 		struct in6_addr ipv6_daddr;
+
+		/* after prerouting + nat detected: store original source
+		 * mac since neigh resolution overwrites it, only used while
+		 * skb is out in neigh layer.
+		 */
+		char neigh_header[8];
+
+		/* always valid & non-NULL from FORWARD on, for physdev match */
+		struct net_device *physoutdev;
 	};
 };
 #endif

include/net/netns/netfilter.h

@@ -14,5 +14,6 @@ struct netns_nf {
 #ifdef CONFIG_SYSCTL
 	struct ctl_table_header *nf_log_dir_header;
 #endif
+	struct list_head hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
 };
 #endif

include/uapi/linux/netfilter/nf_conntrack_sctp.h

@@ -13,6 +13,8 @@ enum sctp_conntrack {
 	SCTP_CONNTRACK_SHUTDOWN_SENT,
 	SCTP_CONNTRACK_SHUTDOWN_RECD,
 	SCTP_CONNTRACK_SHUTDOWN_ACK_SENT,
+	SCTP_CONNTRACK_HEARTBEAT_SENT,
+	SCTP_CONNTRACK_HEARTBEAT_ACKED,
 	SCTP_CONNTRACK_MAX
 };
 

include/uapi/linux/netfilter/nfnetlink_cttimeout.h

@@ -92,6 +92,8 @@ enum ctattr_timeout_sctp {
 	CTA_TIMEOUT_SCTP_SHUTDOWN_SENT,
 	CTA_TIMEOUT_SCTP_SHUTDOWN_RECD,
 	CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT,
+	CTA_TIMEOUT_SCTP_HEARTBEAT_SENT,
+	CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED,
 	__CTA_TIMEOUT_SCTP_MAX
 };
 #define CTA_TIMEOUT_SCTP_MAX (__CTA_TIMEOUT_SCTP_MAX - 1)

net/bridge/br_netfilter_hooks.c

@@ -49,9 +49,9 @@ static struct ctl_table_header *brnf_sysctl_header;
 static int brnf_call_iptables __read_mostly = 1;
 static int brnf_call_ip6tables __read_mostly = 1;
 static int brnf_call_arptables __read_mostly = 1;
-static int brnf_filter_vlan_tagged __read_mostly = 0;
-static int brnf_filter_pppoe_tagged __read_mostly = 0;
-static int brnf_pass_vlan_indev __read_mostly = 0;
+static int brnf_filter_vlan_tagged __read_mostly;
+static int brnf_filter_pppoe_tagged __read_mostly;
+static int brnf_pass_vlan_indev __read_mostly;
 #else
 #define brnf_call_iptables 1
 #define brnf_call_ip6tables 1
@@ -284,7 +284,7 @@ int br_nf_pre_routing_finish_bridge(struct sock *sk, struct sk_buff *skb)
 							 nf_bridge->neigh_header,
 							 ETH_HLEN-ETH_ALEN);
 			/* tell br_dev_xmit to continue with forwarding */
-			nf_bridge->mask |= BRNF_BRIDGED_DNAT;
+			nf_bridge->bridged_dnat = 1;
 			/* FIXME Need to refragment */
 			ret = neigh->output(neigh, skb);
 		}
@@ -356,7 +356,7 @@ static int br_nf_pre_routing_finish(struct sock *sk, struct sk_buff *skb)
 		skb->pkt_type = PACKET_OTHERHOST;
 		nf_bridge->pkt_otherhost = false;
 	}
-	nf_bridge->mask &= ~BRNF_NF_BRIDGE_PREROUTING;
+	nf_bridge->in_prerouting = 0;
 	if (br_nf_ipv4_daddr_was_changed(skb, nf_bridge)) {
 		if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) {
 			struct in_device *in_dev = __in_dev_get_rcu(dev);
@@ -444,7 +444,7 @@ struct net_device *setup_pre_routing(struct sk_buff *skb)
 		nf_bridge->pkt_otherhost = true;
 	}
 
-	nf_bridge->mask |= BRNF_NF_BRIDGE_PREROUTING;
+	nf_bridge->in_prerouting = 1;
 	nf_bridge->physindev = skb->dev;
 	skb->dev = brnf_get_logical_dev(skb, skb->dev);
 
@@ -850,10 +850,8 @@ static unsigned int ip_sabotage_in(const struct nf_hook_ops *ops,
 				   struct sk_buff *skb,
 				   const struct nf_hook_state *state)
 {
-	if (skb->nf_bridge &&
-	    !(skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)) {
+	if (skb->nf_bridge && !skb->nf_bridge->in_prerouting)
 		return NF_STOP;
-	}
 
 	return NF_ACCEPT;
 }
@@ -872,7 +870,7 @@ static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb)
 	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 
 	skb_pull(skb, ETH_HLEN);
-	nf_bridge->mask &= ~BRNF_BRIDGED_DNAT;
+	nf_bridge->bridged_dnat = 0;
 
 	BUILD_BUG_ON(sizeof(nf_bridge->neigh_header) != (ETH_HLEN - ETH_ALEN));
 
@@ -887,7 +885,7 @@ static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb)
 
 static int br_nf_dev_xmit(struct sk_buff *skb)
 {
-	if (skb->nf_bridge && (skb->nf_bridge->mask & BRNF_BRIDGED_DNAT)) {
+	if (skb->nf_bridge && skb->nf_bridge->bridged_dnat) {
 		br_nf_pre_routing_finish_bridge_slow(skb);
 		return 1;
 	}

net/bridge/br_netfilter_ipv6.c

@@ -174,7 +174,7 @@ static int br_nf_pre_routing_finish_ipv6(struct sock *sk, struct sk_buff *skb)
 		skb->pkt_type = PACKET_OTHERHOST;
 		nf_bridge->pkt_otherhost = false;
 	}
-	nf_bridge->mask &= ~BRNF_NF_BRIDGE_PREROUTING;
+	nf_bridge->in_prerouting = 0;
 	if (br_nf_ipv6_daddr_was_changed(skb, nf_bridge)) {
 		skb_dst_drop(skb);
 		v6ops->route_input(skb);

net/ipv4/netfilter/arp_tables.c

@@ -240,7 +240,7 @@ get_entry(const void *base, unsigned int offset)
 	return (struct arpt_entry *)(base + offset);
 }
 
-static inline __pure
+static inline
 struct arpt_entry *arpt_next_entry(const struct arpt_entry *entry)
 {
 	return (void *)entry + entry->next_offset;
@@ -280,6 +280,9 @@ unsigned int arpt_do_table(struct sk_buff *skb,
 	table_base = private->entries;
 	jumpstack  = (struct arpt_entry **)private->jumpstack[cpu];
 
+	/* No TEE support for arptables, so no need to switch to alternate
+	 * stack.  All targets that reenter must return absolute verdicts.
+	 */
 	e = get_entry(table_base, private->hook_entry[hook]);
 
 	acpar.in      = state->in;
@@ -325,21 +328,13 @@ unsigned int arpt_do_table(struct sk_buff *skb,
 			}
 			if (table_base + v
 			    != arpt_next_entry(e)) {
-
-				if (stackidx >= private->stacksize) {
-					verdict = NF_DROP;
-					break;
-				}
 				jumpstack[stackidx++] = e;
 			}
 
 			e = get_entry(table_base, v);
 			continue;
 		}
 
-		/* Targets which reenter must return
-		 * abs. verdicts
-		 */
 		acpar.target   = t->u.kernel.target;
 		acpar.targinfo = t->data;
 		verdict = t->u.kernel.target->target(skb, &acpar);
@@ -372,10 +367,13 @@ static inline bool unconditional(const struct arpt_arp *arp)
 
 /* Figures out from what hook each rule can be called: returns 0 if
  * 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,
+static int 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
@@ -391,6 +389,7 @@ static int 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
@@ -445,6 +444,8 @@ static int 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;
 
@@ -459,6 +460,10 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 						return 0;
 					}
 
+					if (entry0 + newpos != arpt_next_entry(e) &&
+					    ++calldepth > max_calldepth)
+						max_calldepth = calldepth;
+
 					/* This a jump; chase it. */
 					duprintf("Jump rule %u -> %u\n",
 						 pos, newpos);
@@ -475,6 +480,7 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 		next:
 		duprintf("Finished chain %u\n", hook);
 	}
+	newinfo->stacksize = max_calldepth;
 	return 1;
 }
 
@@ -664,9 +670,6 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
 		if (ret != 0)
 			break;
 		++i;
-		if (strcmp(arpt_get_target(iter)->u.user.name,
-		    XT_ERROR_TARGET) == 0)
-			++newinfo->stacksize;
 	}
 	duprintf("translate_table: ARPT_ENTRY_ITERATE gives %d\n", ret);
 	if (ret != 0)
@@ -1439,9 +1442,6 @@ static int translate_compat_table(const char *name,
 			break;
 		}
 		++i;
-		if (strcmp(arpt_get_target(iter1)->u.user.name,
-		    XT_ERROR_TARGET) == 0)
-			++newinfo->stacksize;
 	}
 	if (ret) {
 		/*