1 files changed, 154 insertions, 86 deletions

diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index ae0779d82c5..7ebd6e37875 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -1,78 +1,77 @@
-/* IPv4 specific functions of netfilter core */
-
-#include <linux/config.h>
-#ifdef CONFIG_NETFILTER
-
+/*
+ * IPv4 specific functions of netfilter core
+ *
+ * Rusty Russell (C) 2000 -- This code is GPL.
+ * Patrick McHardy (C) 2006-2012
+ */
 #include <linux/kernel.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter_ipv4.h>
-
-#include <linux/tcp.h>
-#include <linux/udp.h>
-#include <linux/icmp.h>
-#include <net/route.h>
 #include <linux/ip.h>
+#include <linux/skbuff.h>
+#include <linux/gfp.h>
+#include <linux/export.h>
+#include <net/route.h>
+#include <net/xfrm.h>
+#include <net/ip.h>
+#include <net/netfilter/nf_queue.h>
 
 /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
-int ip_route_me_harder(struct sk_buff **pskb)
+int ip_route_me_harder(struct sk_buff *skb, unsigned int addr_type)
 {
-	struct iphdr *iph = (*pskb)->nh.iph;
+	struct net *net = dev_net(skb_dst(skb)->dev);
+	const struct iphdr *iph = ip_hdr(skb);
 	struct rtable *rt;
-	struct flowi fl = {};
-	struct dst_entry *odst;
+	struct flowi4 fl4 = {};
+	__be32 saddr = iph->saddr;
+	__u8 flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0;
 	unsigned int hh_len;
 
+	if (addr_type == RTN_UNSPEC)
+		addr_type = inet_addr_type(net, saddr);
+	if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST)
+		flags |= FLOWI_FLAG_ANYSRC;
+	else
+		saddr = 0;
+
 	/* some non-standard hacks like ipt_REJECT.c:send_reset() can cause
-	 * packets with foreign saddr to appear on the NF_IP_LOCAL_OUT hook.
+	 * packets with foreign saddr to appear on the NF_INET_LOCAL_OUT hook.
 	 */
-	if (inet_addr_type(iph->saddr) == RTN_LOCAL) {
-		fl.nl_u.ip4_u.daddr = iph->daddr;
-		fl.nl_u.ip4_u.saddr = iph->saddr;
-		fl.nl_u.ip4_u.tos = RT_TOS(iph->tos);
-		fl.oif = (*pskb)->sk ? (*pskb)->sk->sk_bound_dev_if : 0;
-#ifdef CONFIG_IP_ROUTE_FWMARK
-		fl.nl_u.ip4_u.fwmark = (*pskb)->nfmark;
-#endif
-		fl.proto = iph->protocol;
-		if (ip_route_output_key(&rt, &fl) != 0)
-			return -1;
-
-		/* Drop old route. */
-		dst_release((*pskb)->dst);
-		(*pskb)->dst = &rt->u.dst;
-	} else {
-		/* non-local src, find valid iif to satisfy
-		 * rp-filter when calling ip_route_input. */
-		fl.nl_u.ip4_u.daddr = iph->saddr;
-		if (ip_route_output_key(&rt, &fl) != 0)
-			return -1;
-
-		odst = (*pskb)->dst;
-		if (ip_route_input(*pskb, iph->daddr, iph->saddr,
-				   RT_TOS(iph->tos), rt->u.dst.dev) != 0) {
-			dst_release(&rt->u.dst);
-			return -1;
-		}
-		dst_release(&rt->u.dst);
-		dst_release(odst);
+	fl4.daddr = iph->daddr;
+	fl4.saddr = saddr;
+	fl4.flowi4_tos = RT_TOS(iph->tos);
+	fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0;
+	fl4.flowi4_mark = skb->mark;
+	fl4.flowi4_flags = flags;
+	rt = ip_route_output_key(net, &fl4);
+	if (IS_ERR(rt))
+		return PTR_ERR(rt);
+
+	/* Drop old route. */
+	skb_dst_drop(skb);
+	skb_dst_set(skb, &rt->dst);
+
+	if (skb_dst(skb)->error)
+		return skb_dst(skb)->error;
+
+#ifdef CONFIG_XFRM
+	if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
+	    xfrm_decode_session(skb, flowi4_to_flowi(&fl4), AF_INET) == 0) {
+		struct dst_entry *dst = skb_dst(skb);
+		skb_dst_set(skb, NULL);
+		dst = xfrm_lookup(net, dst, flowi4_to_flowi(&fl4), skb->sk, 0);
+		if (IS_ERR(dst))
+			return PTR_ERR(dst);
+		skb_dst_set(skb, dst);
 	}
-	
-	if ((*pskb)->dst->error)
-		return -1;
+#endif
 
 	/* Change in oif may mean change in hh_len. */
-	hh_len = (*pskb)->dst->dev->hard_header_len;
-	if (skb_headroom(*pskb) < hh_len) {
-		struct sk_buff *nskb;
-
-		nskb = skb_realloc_headroom(*pskb, hh_len);
-		if (!nskb) 
-			return -1;
-		if ((*pskb)->sk)
-			skb_set_owner_w(nskb, (*pskb)->sk);
-		kfree_skb(*pskb);
-		*pskb = nskb;
-	}
+	hh_len = skb_dst(skb)->dev->hard_header_len;
+	if (skb_headroom(skb) < hh_len &&
+	    pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)),
+				0, GFP_ATOMIC))
+		return -ENOMEM;
 
 	return 0;
 }
@@ -84,56 +83,125 @@ EXPORT_SYMBOL(ip_route_me_harder);
  */
 
 struct ip_rt_info {
-	u_int32_t daddr;
-	u_int32_t saddr;
+	__be32 daddr;
+	__be32 saddr;
 	u_int8_t tos;
+	u_int32_t mark;
 };
 
-static void queue_save(const struct sk_buff *skb, struct nf_info *info)
+static void nf_ip_saveroute(const struct sk_buff *skb,
+			    struct nf_queue_entry *entry)
 {
-	struct ip_rt_info *rt_info = nf_info_reroute(info);
+	struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry);
 
-	if (info->hook == NF_IP_LOCAL_OUT) {
-		const struct iphdr *iph = skb->nh.iph;
+	if (entry->hook == NF_INET_LOCAL_OUT) {
+		const struct iphdr *iph = ip_hdr(skb);
 
 		rt_info->tos = iph->tos;
 		rt_info->daddr = iph->daddr;
 		rt_info->saddr = iph->saddr;
+		rt_info->mark = skb->mark;
 	}
 }
 
-static int queue_reroute(struct sk_buff **pskb, const struct nf_info *info)
+static int nf_ip_reroute(struct sk_buff *skb,
+			 const struct nf_queue_entry *entry)
 {
-	const struct ip_rt_info *rt_info = nf_info_reroute(info);
+	const struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry);
 
-	if (info->hook == NF_IP_LOCAL_OUT) {
-		struct iphdr *iph = (*pskb)->nh.iph;
+	if (entry->hook == NF_INET_LOCAL_OUT) {
+		const struct iphdr *iph = ip_hdr(skb);
 
-		if (!(iph->tos == rt_info->tos
-		      && iph->daddr == rt_info->daddr
-		      && iph->saddr == rt_info->saddr))
-			return ip_route_me_harder(pskb);
+		if (!(iph->tos == rt_info->tos &&
+		      skb->mark == rt_info->mark &&
+		      iph->daddr == rt_info->daddr &&
+		      iph->saddr == rt_info->saddr))
+			return ip_route_me_harder(skb, RTN_UNSPEC);
 	}
 	return 0;
 }
 
-static struct nf_queue_rerouter ip_reroute = {
-	.rer_size	= sizeof(struct ip_rt_info),
-	.save		= queue_save,
-	.reroute	= queue_reroute,
-};
+__sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook,
+			    unsigned int dataoff, u_int8_t protocol)
+{
+	const struct iphdr *iph = ip_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 ((protocol == 0 && !csum_fold(skb->csum)) ||
+		    !csum_tcpudp_magic(iph->saddr, iph->daddr,
+				       skb->len - dataoff, protocol,
+				       skb->csum)) {
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+			break;
+		}
+		/* fall through */
+	case CHECKSUM_NONE:
+		if (protocol == 0)
+			skb->csum = 0;
+		else
+			skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
+						       skb->len - dataoff,
+						       protocol, 0);
+		csum = __skb_checksum_complete(skb);
+	}
+	return csum;
+}
+EXPORT_SYMBOL(nf_ip_checksum);
 
-static int init(void)
+static __sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook,
+				      unsigned int dataoff, unsigned int len,
+				      u_int8_t protocol)
 {
-	return nf_register_queue_rerouter(PF_INET, &ip_reroute);
+	const struct iphdr *iph = ip_hdr(skb);
+	__sum16 csum = 0;
+
+	switch (skb->ip_summed) {
+	case CHECKSUM_COMPLETE:
+		if (len == skb->len - dataoff)
+			return nf_ip_checksum(skb, hook, dataoff, protocol);
+		/* fall through */
+	case CHECKSUM_NONE:
+		skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr, protocol,
+					       skb->len - dataoff, 0);
+		skb->ip_summed = CHECKSUM_NONE;
+		return __skb_checksum_complete_head(skb, dataoff + len);
+	}
+	return csum;
 }
 
-static void fini(void)
+static int nf_ip_route(struct net *net, struct dst_entry **dst,
+		       struct flowi *fl, bool strict __always_unused)
 {
-	nf_unregister_queue_rerouter(PF_INET);
+	struct rtable *rt = ip_route_output_key(net, &fl->u.ip4);
+	if (IS_ERR(rt))
+		return PTR_ERR(rt);
+	*dst = &rt->dst;
+	return 0;
 }
 
-module_init(init);
-module_exit(fini);
+static const struct nf_afinfo nf_ip_afinfo = {
+	.family			= AF_INET,
+	.checksum		= nf_ip_checksum,
+	.checksum_partial	= nf_ip_checksum_partial,
+	.route			= nf_ip_route,
+	.saveroute		= nf_ip_saveroute,
+	.reroute		= nf_ip_reroute,
+	.route_key_size		= sizeof(struct ip_rt_info),
+};
+
+static int __init ipv4_netfilter_init(void)
+{
+	return nf_register_afinfo(&nf_ip_afinfo);
+}
+
+static void __exit ipv4_netfilter_fini(void)
+{
+	nf_unregister_afinfo(&nf_ip_afinfo);
+}
 
-#endif /* CONFIG_NETFILTER */
+module_init(ipv4_netfilter_init);
+module_exit(ipv4_netfilter_fini);