1 files changed, 114 insertions, 122 deletions

diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 80242172a5d..433672d07d0 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -2,181 +2,173 @@
  * xfrm6_output.c - Common IPsec encapsulation code for IPv6.
  * Copyright (C) 2002 USAGI/WIDE Project
  * Copyright (c) 2004 Herbert Xu <herbert@gondor.apana.org.au>
- * 
+ *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
  * as published by the Free Software Foundation; either version
  * 2 of the License, or (at your option) any later version.
  */
 
-#include <linux/compiler.h>
+#include <linux/if_ether.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/skbuff.h>
-#include <linux/spinlock.h>
 #include <linux/icmpv6.h>
 #include <linux/netfilter_ipv6.h>
-#include <net/dsfield.h>
-#include <net/inet_ecn.h>
+#include <net/dst.h>
 #include <net/ipv6.h>
+#include <net/ip6_route.h>
 #include <net/xfrm.h>
 
-/* Add encapsulation header.
- *
- * In transport mode, the IP header and mutable extension headers will be moved
- * forward to make space for the encapsulation header.
- *
- * In tunnel mode, the top IP header will be constructed per RFC 2401.
- * The following fields in it shall be filled in by x->type->output:
- *	payload_len
- *
- * On exit, skb->h will be set to the start of the encapsulation header to be
- * filled in by x->type->output and skb->nh will be set to the nextheader field
- * of the extension header directly preceding the encapsulation header, or in
- * its absence, that of the top IP header.  The value of skb->data will always
- * point to the top IP header.
- */
-static void xfrm6_encap(struct sk_buff *skb)
+int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb,
+			  u8 **prevhdr)
 {
-	struct dst_entry *dst = skb->dst;
-	struct xfrm_state *x = dst->xfrm;
-	struct ipv6hdr *iph, *top_iph;
-	int dsfield;
+	return ip6_find_1stfragopt(skb, prevhdr);
+}
 
-	skb_push(skb, x->props.header_len);
-	iph = skb->nh.ipv6h;
+EXPORT_SYMBOL(xfrm6_find_1stfragopt);
+
+static int xfrm6_local_dontfrag(struct sk_buff *skb)
+{
+	int proto;
+	struct sock *sk = skb->sk;
 
-	if (!x->props.mode) {
-		u8 *prevhdr;
-		int hdr_len;
+	if (sk) {
+		if (sk->sk_family != AF_INET6)
+			return 0;
 
-		hdr_len = ip6_find_1stfragopt(skb, &prevhdr);
-		skb->nh.raw = prevhdr - x->props.header_len;
-		skb->h.raw = skb->data + hdr_len;
-		memmove(skb->data, iph, hdr_len);
-		return;
+		proto = sk->sk_protocol;
+		if (proto == IPPROTO_UDP || proto == IPPROTO_RAW)
+			return inet6_sk(sk)->dontfrag;
 	}
 
-	skb->nh.raw = skb->data;
-	top_iph = skb->nh.ipv6h;
-	skb->nh.raw = &top_iph->nexthdr;
-	skb->h.ipv6h = top_iph + 1;
-
-	top_iph->version = 6;
-	top_iph->priority = iph->priority;
-	top_iph->flow_lbl[0] = iph->flow_lbl[0];
-	top_iph->flow_lbl[1] = iph->flow_lbl[1];
-	top_iph->flow_lbl[2] = iph->flow_lbl[2];
-	dsfield = ipv6_get_dsfield(top_iph);
-	dsfield = INET_ECN_encapsulate(dsfield, dsfield);
-	if (x->props.flags & XFRM_STATE_NOECN)
-		dsfield &= ~INET_ECN_MASK;
-	ipv6_change_dsfield(top_iph, 0, dsfield);
-	top_iph->nexthdr = IPPROTO_IPV6; 
-	top_iph->hop_limit = dst_metric(dst->child, RTAX_HOPLIMIT);
-	ipv6_addr_copy(&top_iph->saddr, (struct in6_addr *)&x->props.saddr);
-	ipv6_addr_copy(&top_iph->daddr, (struct in6_addr *)&x->id.daddr);
+	return 0;
+}
+
+static void xfrm6_local_rxpmtu(struct sk_buff *skb, u32 mtu)
+{
+	struct flowi6 fl6;
+	struct sock *sk = skb->sk;
+
+	fl6.flowi6_oif = sk->sk_bound_dev_if;
+	fl6.daddr = ipv6_hdr(skb)->daddr;
+
+	ipv6_local_rxpmtu(sk, &fl6, mtu);
+}
+
+void xfrm6_local_error(struct sk_buff *skb, u32 mtu)
+{
+	struct flowi6 fl6;
+	const struct ipv6hdr *hdr;
+	struct sock *sk = skb->sk;
+
+	hdr = skb->encapsulation ? inner_ipv6_hdr(skb) : ipv6_hdr(skb);
+	fl6.fl6_dport = inet_sk(sk)->inet_dport;
+	fl6.daddr = hdr->daddr;
+
+	ipv6_local_error(sk, EMSGSIZE, &fl6, mtu);
 }
 
 static int xfrm6_tunnel_check_size(struct sk_buff *skb)
 {
 	int mtu, ret = 0;
-	struct dst_entry *dst = skb->dst;
+	struct dst_entry *dst = skb_dst(skb);
 
 	mtu = dst_mtu(dst);
 	if (mtu < IPV6_MIN_MTU)
 		mtu = IPV6_MIN_MTU;
 
-	if (skb->len > mtu) {
+	if (!skb->ignore_df && skb->len > mtu) {
 		skb->dev = dst->dev;
-		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev);
+
+		if (xfrm6_local_dontfrag(skb))
+			xfrm6_local_rxpmtu(skb, mtu);
+		else if (skb->sk)
+			xfrm_local_error(skb, mtu);
+		else
+			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		ret = -EMSGSIZE;
 	}
 
 	return ret;
 }
 
-static int xfrm6_output_one(struct sk_buff *skb)
+int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb->dst;
-	struct xfrm_state *x = dst->xfrm;
 	int err;
-	
-	if (skb->ip_summed == CHECKSUM_HW) {
-		err = skb_checksum_help(skb, 0);
-		if (err)
-			goto error_nolock;
-	}
 
-	if (x->props.mode) {
-		err = xfrm6_tunnel_check_size(skb);
-		if (err)
-			goto error_nolock;
-	}
+	err = xfrm6_tunnel_check_size(skb);
+	if (err)
+		return err;
 
-	do {
-		spin_lock_bh(&x->lock);
-		err = xfrm_state_check(x, skb);
-		if (err)
-			goto error;
+	XFRM_MODE_SKB_CB(skb)->protocol = ipv6_hdr(skb)->nexthdr;
 
-		xfrm6_encap(skb);
+	return xfrm6_extract_header(skb);
+}
 
-		err = x->type->output(x, skb);
-		if (err)
-			goto error;
+int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err;
 
-		x->curlft.bytes += skb->len;
-		x->curlft.packets++;
+	err = xfrm_inner_extract_output(x, skb);
+	if (err)
+		return err;
 
-		spin_unlock_bh(&x->lock);
+	skb->ignore_df = 1;
 
-		skb->nh.raw = skb->data;
-		
-		if (!(skb->dst = dst_pop(dst))) {
-			err = -EHOSTUNREACH;
-			goto error_nolock;
-		}
-		dst = skb->dst;
-		x = dst->xfrm;
-	} while (x && !x->props.mode);
+	return x->outer_mode->output2(x, skb);
+}
+EXPORT_SYMBOL(xfrm6_prepare_output);
+
+int xfrm6_output_finish(struct sk_buff *skb)
+{
+	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+	skb->protocol = htons(ETH_P_IPV6);
 
+#ifdef CONFIG_NETFILTER
 	IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED;
-	err = 0;
-
-out_exit:
-	return err;
-error:
-	spin_unlock_bh(&x->lock);
-error_nolock:
-	kfree_skb(skb);
-	goto out_exit;
+#endif
+
+	return xfrm_output(skb);
 }
 
-static int xfrm6_output_finish(struct sk_buff *skb)
+static int __xfrm6_output(struct sk_buff *skb)
 {
-	int err;
+	struct dst_entry *dst = skb_dst(skb);
+	struct xfrm_state *x = dst->xfrm;
+	int mtu;
 
-	while (likely((err = xfrm6_output_one(skb)) == 0)) {
-		nf_reset(skb);
-	
-		err = nf_hook(PF_INET6, NF_IP6_LOCAL_OUT, &skb, NULL,
-			      skb->dst->dev, dst_output);
-		if (unlikely(err != 1))
-			break;
-
-		if (!skb->dst->xfrm)
-			return dst_output(skb);
-
-		err = nf_hook(PF_INET6, NF_IP6_POST_ROUTING, &skb, NULL,
-			      skb->dst->dev, xfrm6_output_finish);
-		if (unlikely(err != 1))
-			break;
+#ifdef CONFIG_NETFILTER
+	if (!x) {
+		IP6CB(skb)->flags |= IP6SKB_REROUTED;
+		return dst_output(skb);
+	}
+#endif
+
+	if (skb->protocol == htons(ETH_P_IPV6))
+		mtu = ip6_skb_dst_mtu(skb);
+	else
+		mtu = dst_mtu(skb_dst(skb));
+
+	if (skb->len > mtu && xfrm6_local_dontfrag(skb)) {
+		xfrm6_local_rxpmtu(skb, mtu);
+		return -EMSGSIZE;
+	} else if (!skb->ignore_df && skb->len > mtu && skb->sk) {
+		xfrm_local_error(skb, mtu);
+		return -EMSGSIZE;
 	}
 
-	return err;
+	if (x->props.mode == XFRM_MODE_TUNNEL &&
+	    ((skb->len > mtu && !skb_is_gso(skb)) ||
+		dst_allfrag(skb_dst(skb)))) {
+			return ip6_fragment(skb, x->outer_mode->afinfo->output_finish);
+	}
+	return x->outer_mode->afinfo->output_finish(skb);
 }
 
-int xfrm6_output(struct sk_buff *skb)
+int xfrm6_output(struct sock *sk, struct sk_buff *skb)
 {
-	return NF_HOOK(PF_INET6, NF_IP6_POST_ROUTING, skb, NULL, skb->dst->dev,
-		       xfrm6_output_finish);
+	return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb,
+			    NULL, skb_dst(skb)->dev, __xfrm6_output,
+			    !(IP6CB(skb)->flags & IP6SKB_REROUTED));
 }