1 files changed, 166 insertions, 106 deletions

diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 95f3f1da0d7f..46540a5a4331 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -15,28 +15,44 @@
 #include <net/ipv6.h>
 #include <net/ip6_route.h>
 #include <net/xfrm.h>
-#include <net/ip6_checksum.h>
 #include <net/netfilter/nf_queue.h>
+#include <net/netfilter/nf_conntrack_bridge.h>
+#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
+#include "../bridge/br_private.h"
 
-int ip6_route_me_harder(struct sk_buff *skb)
+int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff *skb)
 {
-	struct net *net = dev_net(skb_dst(skb)->dev);
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
+	struct sock *sk = sk_to_full_sk(sk_partial);
+	struct net_device *dev = skb_dst_dev(skb);
+	struct flow_keys flkeys;
 	unsigned int hh_len;
 	struct dst_entry *dst;
+	int strict = (ipv6_addr_type(&iph->daddr) &
+		      (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL));
 	struct flowi6 fl6 = {
-		.flowi6_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0,
+		.flowi6_l3mdev = l3mdev_master_ifindex(dev),
 		.flowi6_mark = skb->mark,
+		.flowi6_uid = sock_net_uid(net, sk),
 		.daddr = iph->daddr,
 		.saddr = iph->saddr,
+		.flowlabel = ip6_flowinfo(iph),
 	};
+	int err;
+
+	if (sk && sk->sk_bound_dev_if)
+		fl6.flowi6_oif = sk->sk_bound_dev_if;
+	else if (strict)
+		fl6.flowi6_oif = dev->ifindex;
 
-	dst = ip6_route_output(net, skb->sk, &fl6);
-	if (dst->error) {
+	fib6_rules_early_flow_dissect(net, skb, &fl6, &flkeys);
+	dst = ip6_route_output(net, sk, &fl6);
+	err = dst->error;
+	if (err) {
 		IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
-		LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n");
+		net_dbg_ratelimited("ip6_route_me_harder: No more route\n");
 		dst_release(dst);
-		return dst->error;
+		return err;
 	}
 
 	/* Drop old route. */
@@ -46,9 +62,12 @@ int ip6_route_me_harder(struct sk_buff *skb)
 
 #ifdef CONFIG_XFRM
 	if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
-	    xfrm_decode_session(skb, flowi6_to_flowi(&fl6), AF_INET6) == 0) {
-		skb_dst_set(skb, NULL);
-		dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), skb->sk, 0);
+	    xfrm_decode_session(net, skb, flowi6_to_flowi(&fl6), AF_INET6) == 0) {
+		/* ignore return value from skb_dstref_steal, xfrm_lookup takes
+		 * care of dropping the refcnt if needed.
+		 */
+		skb_dstref_steal(skb);
+		dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0);
 		if (IS_ERR(dst))
 			return PTR_ERR(dst);
 		skb_dst_set(skb, dst);
@@ -56,7 +75,7 @@ int ip6_route_me_harder(struct sk_buff *skb)
 #endif
 
 	/* Change in oif may mean change in hh_len. */
-	hh_len = skb_dst(skb)->dev->hard_header_len;
+	hh_len = skb_dst_dev(skb)->hard_header_len;
 	if (skb_headroom(skb) < hh_len &&
 	    pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)),
 			     0, GFP_ATOMIC))
@@ -66,48 +85,23 @@ int ip6_route_me_harder(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(ip6_route_me_harder);
 
-/*
- * Extra routing may needed on local out, as the QUEUE target never
- * returns control to the table.
- */
-
-struct ip6_rt_info {
-	struct in6_addr daddr;
-	struct in6_addr saddr;
-	u_int32_t mark;
-};
-
-static void nf_ip6_saveroute(const struct sk_buff *skb,
-			     struct nf_queue_entry *entry)
-{
-	struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry);
-
-	if (entry->hook == NF_INET_LOCAL_OUT) {
-		const struct ipv6hdr *iph = ipv6_hdr(skb);
-
-		rt_info->daddr = iph->daddr;
-		rt_info->saddr = iph->saddr;
-		rt_info->mark = skb->mark;
-	}
-}
-
 static int nf_ip6_reroute(struct sk_buff *skb,
 			  const struct nf_queue_entry *entry)
 {
 	struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry);
 
-	if (entry->hook == NF_INET_LOCAL_OUT) {
+	if (entry->state.hook == NF_INET_LOCAL_OUT) {
 		const struct ipv6hdr *iph = ipv6_hdr(skb);
 		if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) ||
 		    !ipv6_addr_equal(&iph->saddr, &rt_info->saddr) ||
 		    skb->mark != rt_info->mark)
-			return ip6_route_me_harder(skb);
+			return ip6_route_me_harder(entry->state.net, entry->state.sk, skb);
 	}
 	return 0;
 }
 
-static int nf_ip6_route(struct net *net, struct dst_entry **dst,
-			struct flowi *fl, bool strict)
+int __nf_ip6_route(struct net *net, struct dst_entry **dst,
+		   struct flowi *fl, bool strict)
 {
 	static const struct ipv6_pinfo fake_pinfo;
 	static const struct inet_sock fake_sk = {
@@ -127,84 +121,151 @@ static int nf_ip6_route(struct net *net, struct dst_entry **dst,
 		*dst = result;
 	return err;
 }
+EXPORT_SYMBOL_GPL(__nf_ip6_route);
 
-__sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook,
-			     unsigned int dataoff, u_int8_t protocol)
+int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
+		    struct nf_bridge_frag_data *data,
+		    int (*output)(struct net *, struct sock *sk,
+				  const struct nf_bridge_frag_data *data,
+				  struct sk_buff *))
 {
-	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
-	__sum16 csum = 0;
-
-	switch (skb->ip_summed) {
-	case CHECKSUM_COMPLETE:
-		if (hook != NF_INET_PRE_ROUTING && hook != NF_INET_LOCAL_IN)
-			break;
-		if (!csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
-				     skb->len - dataoff, protocol,
-				     csum_sub(skb->csum,
-					      skb_checksum(skb, 0,
-							   dataoff, 0)))) {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			break;
+	int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size;
+	u8 tstamp_type = skb->tstamp_type;
+	ktime_t tstamp = skb->tstamp;
+	struct ip6_frag_state state;
+	u8 *prevhdr, nexthdr = 0;
+	unsigned int mtu, hlen;
+	int hroom, err = 0;
+	__be32 frag_id;
+
+	err = ip6_find_1stfragopt(skb, &prevhdr);
+	if (err < 0)
+		goto blackhole;
+	hlen = err;
+	nexthdr = *prevhdr;
+
+	mtu = skb->dev->mtu;
+	if (frag_max_size > mtu ||
+	    frag_max_size < IPV6_MIN_MTU)
+		goto blackhole;
+
+	mtu = frag_max_size;
+	if (mtu < hlen + sizeof(struct frag_hdr) + 8)
+		goto blackhole;
+	mtu -= hlen + sizeof(struct frag_hdr);
+
+	frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr,
+				    &ipv6_hdr(skb)->saddr);
+
+	if (skb->ip_summed == CHECKSUM_PARTIAL &&
+	    (err = skb_checksum_help(skb)))
+		goto blackhole;
+
+	hroom = LL_RESERVED_SPACE(skb->dev);
+	if (skb_has_frag_list(skb)) {
+		unsigned int first_len = skb_pagelen(skb);
+		struct ip6_fraglist_iter iter;
+		struct sk_buff *frag2;
+
+		if (first_len - hlen > mtu)
+			goto blackhole;
+
+		if (skb_cloned(skb) ||
+		    skb_headroom(skb) < (hroom + sizeof(struct frag_hdr)))
+			goto slow_path;
+
+		skb_walk_frags(skb, frag2) {
+			if (frag2->len > mtu)
+				goto blackhole;
+
+			/* Partially cloned skb? */
+			if (skb_shared(frag2) ||
+			    skb_headroom(frag2) < (hlen + hroom + sizeof(struct frag_hdr)))
+				goto slow_path;
+		}
+
+		err = ip6_fraglist_init(skb, hlen, prevhdr, nexthdr, frag_id,
+					&iter);
+		if (err < 0)
+			goto blackhole;
+
+		for (;;) {
+			/* Prepare header of the next frame,
+			 * before previous one went down.
+			 */
+			if (iter.frag)
+				ip6_fraglist_prepare(skb, &iter);
+
+			skb_set_delivery_time(skb, tstamp, tstamp_type);
+			err = output(net, sk, data, skb);
+			if (err || !iter.frag)
+				break;
+
+			skb = ip6_fraglist_next(&iter);
 		}
-		/* fall through */
-	case CHECKSUM_NONE:
-		skb->csum = ~csum_unfold(
-				csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
-					     skb->len - dataoff,
-					     protocol,
-					     csum_sub(0,
-						      skb_checksum(skb, 0,
-								   dataoff, 0))));
-		csum = __skb_checksum_complete(skb);
+
+		kfree(iter.tmp_hdr);
+		if (!err)
+			return 0;
+
+		kfree_skb_list(iter.frag);
+		return err;
 	}
-	return csum;
-}
-EXPORT_SYMBOL(nf_ip6_checksum);
+slow_path:
+	/* This is a linearized skbuff, the original geometry is lost for us.
+	 * This may also be a clone skbuff, we could preserve the geometry for
+	 * the copies but probably not worth the effort.
+	 */
+	ip6_frag_init(skb, hlen, mtu, skb->dev->needed_tailroom,
+		      LL_RESERVED_SPACE(skb->dev), prevhdr, nexthdr, frag_id,
+		      &state);
 
-static __sum16 nf_ip6_checksum_partial(struct sk_buff *skb, unsigned int hook,
-				       unsigned int dataoff, unsigned int len,
-				       u_int8_t protocol)
-{
-	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
-	__wsum hsum;
-	__sum16 csum = 0;
-
-	switch (skb->ip_summed) {
-	case CHECKSUM_COMPLETE:
-		if (len == skb->len - dataoff)
-			return nf_ip6_checksum(skb, hook, dataoff, protocol);
-		/* fall through */
-	case CHECKSUM_NONE:
-		hsum = skb_checksum(skb, 0, dataoff, 0);
-		skb->csum = ~csum_unfold(csum_ipv6_magic(&ip6h->saddr,
-							 &ip6h->daddr,
-							 skb->len - dataoff,
-							 protocol,
-							 csum_sub(0, hsum)));
-		skb->ip_summed = CHECKSUM_NONE;
-		return __skb_checksum_complete_head(skb, dataoff + len);
+	while (state.left > 0) {
+		struct sk_buff *skb2;
+
+		skb2 = ip6_frag_next(skb, &state);
+		if (IS_ERR(skb2)) {
+			err = PTR_ERR(skb2);
+			goto blackhole;
+		}
+
+		skb_set_delivery_time(skb2, tstamp, tstamp_type);
+		err = output(net, sk, data, skb2);
+		if (err)
+			goto blackhole;
 	}
-	return csum;
-};
+	consume_skb(skb);
+	return err;
 
-static const struct nf_ipv6_ops ipv6ops = {
-	.chk_addr	= ipv6_chk_addr,
-};
+blackhole:
+	kfree_skb(skb);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(br_ip6_fragment);
 
-static const struct nf_afinfo nf_ip6_afinfo = {
-	.family			= AF_INET6,
-	.checksum		= nf_ip6_checksum,
-	.checksum_partial	= nf_ip6_checksum_partial,
-	.route			= nf_ip6_route,
-	.saveroute		= nf_ip6_saveroute,
+static const struct nf_ipv6_ops ipv6ops = {
+#if IS_MODULE(CONFIG_IPV6)
+	.chk_addr		= ipv6_chk_addr,
+	.route_me_harder	= ip6_route_me_harder,
+	.dev_get_saddr		= ipv6_dev_get_saddr,
+	.route			= __nf_ip6_route,
+#if IS_ENABLED(CONFIG_SYN_COOKIES)
+	.cookie_init_sequence	= __cookie_v6_init_sequence,
+	.cookie_v6_check	= __cookie_v6_check,
+#endif
+#endif
+	.route_input		= ip6_route_input,
+	.fragment		= ip6_fragment,
 	.reroute		= nf_ip6_reroute,
-	.route_key_size		= sizeof(struct ip6_rt_info),
+#if IS_MODULE(CONFIG_IPV6)
+	.br_fragment		= br_ip6_fragment,
+#endif
 };
 
 int __init ipv6_netfilter_init(void)
 {
 	RCU_INIT_POINTER(nf_ipv6_ops, &ipv6ops);
-	return nf_register_afinfo(&nf_ip6_afinfo);
+	return 0;
 }
 
 /* This can be called from inet6_init() on errors, so it cannot
@@ -213,5 +274,4 @@ int __init ipv6_netfilter_init(void)
 void ipv6_netfilter_fini(void)
 {
 	RCU_INIT_POINTER(nf_ipv6_ops, NULL);
-	nf_unregister_afinfo(&nf_ip6_afinfo);
 }