[IPSEC]: Separate inner/outer mode processing on output

With inter-family transforms the inner mode differs from the outer
mode.  Attempting to handle both sides from the same function means
that it needs to handle both IPv4 and IPv6 which creates duplication
and confusion.

This patch separates the two parts on the output path so that each
function deals with one family only.

In particular, the functions xfrm4_extract_output/xfrm6_extract_output
moves the pertinent fields from the IPv4/IPv6 IP headers into a
neutral format stored in skb->cb.  This is then used by the outer mode
output functions to write the outer IP header.  In this way the output
function no longer has to know about the inner address family.

Since the extract functions are only called by tunnel modes (the only
modes that can support inter-family transforms), I've also moved the
xfrm*_tunnel_check_size calls into them.  This allows the correct ICMP
message to be sent as opposed to now where you might call icmp_send
with an IPv6 packet and vice versa.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

8 files changed, 143 insertions, 83 deletions

diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c
index e42e122414b..94842adce14 100644
--- a/net/ipv4/xfrm4_mode_beet.c
+++ b/net/ipv4/xfrm4_mode_beet.c
@@ -43,7 +43,17 @@ static int xfrm4_beet_output(struct xfrm_state *x, struct sk_buff *skb)
 	ph = (struct ip_beet_phdr *)__skb_pull(skb, sizeof(*iph) - hdrlen);
 
 	top_iph = ip_hdr(skb);
-	memmove(top_iph, iph, sizeof(*iph));
+
+	top_iph->ihl = 5;
+	top_iph->version = 4;
+
+	top_iph->protocol = XFRM_MODE_SKB_CB(skb)->protocol;
+	top_iph->tos = XFRM_MODE_SKB_CB(skb)->tos;
+
+	top_iph->id = XFRM_MODE_SKB_CB(skb)->id;
+	top_iph->frag_off = XFRM_MODE_SKB_CB(skb)->frag_off;
+	top_iph->ttl = XFRM_MODE_SKB_CB(skb)->ttl;
+
 	if (unlikely(optlen)) {
 		BUG_ON(optlen < 0);
 
@@ -111,7 +121,8 @@ out:
 
 static struct xfrm_mode xfrm4_beet_mode = {
 	.input = xfrm4_beet_input,
-	.output = xfrm4_beet_output,
+	.output2 = xfrm4_beet_output,
+	.output = xfrm4_prepare_output,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_BEET,
 	.flags = XFRM_MODE_FLAG_TUNNEL,
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 68a9f56ff09..cc8bbb274e3 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -36,53 +36,37 @@ static inline void ipip6_ecn_decapsulate(struct iphdr *iph, struct sk_buff *skb)
 static int xfrm4_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb->dst;
-	struct xfrm_dst *xdst = (struct xfrm_dst*)dst;
-	struct iphdr *iph, *top_iph;
+	struct iphdr *top_iph;
 	int flags;
 
-	iph = ip_hdr(skb);
-
 	skb_set_network_header(skb, -x->props.header_len);
 	skb->mac_header = skb->network_header +
 			  offsetof(struct iphdr, protocol);
-	skb->transport_header = skb->network_header + sizeof(*iph);
+	skb->transport_header = skb->network_header + sizeof(*top_iph);
 	top_iph = ip_hdr(skb);
 
 	top_iph->ihl = 5;
 	top_iph->version = 4;
 
-	flags = x->props.flags;
+	top_iph->protocol = x->inner_mode->afinfo->proto;
 
 	/* DS disclosed */
-	if (xdst->route->ops->family == AF_INET) {
-		top_iph->protocol = IPPROTO_IPIP;
-		top_iph->tos = INET_ECN_encapsulate(iph->tos, iph->tos);
-		top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
-			0 : (iph->frag_off & htons(IP_DF));
-	}
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
-	else {
-		struct ipv6hdr *ipv6h = (struct ipv6hdr*)iph;
-		top_iph->protocol = IPPROTO_IPV6;
-		top_iph->tos = INET_ECN_encapsulate(iph->tos, ipv6_get_dsfield(ipv6h));
-		top_iph->frag_off = 0;
-	}
-#endif
+	top_iph->tos = INET_ECN_encapsulate(XFRM_MODE_SKB_CB(skb)->tos,
+					    XFRM_MODE_SKB_CB(skb)->tos);
 
+	flags = x->props.flags;
 	if (flags & XFRM_STATE_NOECN)
 		IP_ECN_clear(top_iph);
 
-	if (!top_iph->frag_off)
-		__ip_select_ident(top_iph, dst->child, 0);
+	top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
+			    0 : XFRM_MODE_SKB_CB(skb)->frag_off;
+	ip_select_ident(top_iph, dst->child, NULL);
 
 	top_iph->ttl = dst_metric(dst->child, RTAX_HOPLIMIT);
 
 	top_iph->saddr = x->props.saddr.a4;
 	top_iph->daddr = x->id.daddr.a4;
 
-	skb->protocol = htons(ETH_P_IP);
-
-	memset(&(IPCB(skb)->opt), 0, sizeof(struct ip_options));
 	return 0;
 }
 
@@ -136,7 +120,8 @@ out:
 
 static struct xfrm_mode xfrm4_tunnel_mode = {
 	.input = xfrm4_tunnel_input,
-	.output = xfrm4_tunnel_output,
+	.output2 = xfrm4_tunnel_output,
+	.output = xfrm4_prepare_output,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_TUNNEL,
 	.flags = XFRM_MODE_FLAG_TUNNEL,
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index c4a7156962b..13fd11335e2 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -8,11 +8,12 @@
  * 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/netfilter_ipv4.h>
+#include <net/dst.h>
 #include <net/ip.h>
 #include <net/xfrm.h>
 #include <net/icmp.h>
@@ -25,8 +26,6 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb)
 	if (IPCB(skb)->flags & IPSKB_XFRM_TUNNEL_SIZE)
 		goto out;
 
-	IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE;
-
 	if (!(ip_hdr(skb)->frag_off & htons(IP_DF)) || skb->local_df)
 		goto out;
 
@@ -40,19 +39,39 @@ out:
 	return ret;
 }
 
+int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err;
+
+	err = xfrm4_tunnel_check_size(skb);
+	if (err)
+		return err;
+
+	return xfrm4_extract_header(skb);
+}
+
+int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err;
+
+	err = x->inner_mode->afinfo->extract_output(x, skb);
+	if (err)
+		return err;
+
+	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+	IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE;
+
+	skb->protocol = htons(ETH_P_IP);
+
+	return x->outer_mode->output2(x, skb);
+}
+EXPORT_SYMBOL(xfrm4_prepare_output);
+
 static inline int xfrm4_output_one(struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb->dst;
-	struct xfrm_state *x = dst->xfrm;
 	struct iphdr *iph;
 	int err;
 
-	if (x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL) {
-		err = xfrm4_tunnel_check_size(skb);
-		if (err)
-			goto error_nolock;
-	}
-
 	err = xfrm_output(skb);
 	if (err)
 		goto error_nolock;
diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c
index 13d54a1c333..e6030e74ff6 100644
--- a/net/ipv4/xfrm4_state.c
+++ b/net/ipv4/xfrm4_state.c
@@ -47,12 +47,29 @@ __xfrm4_init_tempsel(struct xfrm_state *x, struct flowi *fl,
 	x->props.family = AF_INET;
 }
 
+int xfrm4_extract_header(struct sk_buff *skb)
+{
+	struct iphdr *iph = ip_hdr(skb);
+
+	XFRM_MODE_SKB_CB(skb)->id = iph->id;
+	XFRM_MODE_SKB_CB(skb)->frag_off = iph->frag_off;
+	XFRM_MODE_SKB_CB(skb)->tos = iph->tos;
+	XFRM_MODE_SKB_CB(skb)->ttl = iph->ttl;
+	XFRM_MODE_SKB_CB(skb)->protocol = iph->protocol;
+	memset(XFRM_MODE_SKB_CB(skb)->flow_lbl, 0,
+	       sizeof(XFRM_MODE_SKB_CB(skb)->flow_lbl));
+
+	return 0;
+}
+
 static struct xfrm_state_afinfo xfrm4_state_afinfo = {
 	.family			= AF_INET,
+	.proto			= IPPROTO_IPIP,
 	.owner			= THIS_MODULE,
 	.init_flags		= xfrm4_init_flags,
 	.init_tempsel		= __xfrm4_init_tempsel,
 	.output			= xfrm4_output,
+	.extract_output		= xfrm4_extract_output,
 };
 
 void __init xfrm4_state_init(void)
diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c
index 2bfb4f05c14..4988ed9c76c 100644
--- a/net/ipv6/xfrm6_mode_beet.c
+++ b/net/ipv6/xfrm6_mode_beet.c
@@ -25,25 +25,24 @@
  */
 static int xfrm6_beet_output(struct xfrm_state *x, struct sk_buff *skb)
 {
-	struct ipv6hdr *iph, *top_iph;
-	u8 *prevhdr;
-	int hdr_len;
+	struct ipv6hdr *top_iph;
 
-	iph = ipv6_hdr(skb);
-
-	hdr_len = ip6_find_1stfragopt(skb, &prevhdr);
-
-	skb_set_mac_header(skb, (prevhdr - x->props.header_len) - skb->data);
 	skb_set_network_header(skb, -x->props.header_len);
-	skb->transport_header = skb->network_header + hdr_len;
-	__skb_pull(skb, hdr_len);
-
+	skb->mac_header = skb->network_header +
+			  offsetof(struct ipv6hdr, nexthdr);
+	skb->transport_header = skb->network_header + sizeof(*top_iph);
 	top_iph = ipv6_hdr(skb);
-	memmove(top_iph, iph, hdr_len);
 
+	top_iph->version = 6;
+
+	memcpy(top_iph->flow_lbl, XFRM_MODE_SKB_CB(skb)->flow_lbl,
+	       sizeof(top_iph->flow_lbl));
+	top_iph->nexthdr = XFRM_MODE_SKB_CB(skb)->protocol;
+
+	ipv6_change_dsfield(top_iph, 0, XFRM_MODE_SKB_CB(skb)->tos);
+	top_iph->hop_limit = XFRM_MODE_SKB_CB(skb)->ttl;
 	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;
 }
 
@@ -76,7 +75,8 @@ out:
 
 static struct xfrm_mode xfrm6_beet_mode = {
 	.input = xfrm6_beet_input,
-	.output = xfrm6_beet_output,
+	.output2 = xfrm6_beet_output,
+	.output = xfrm6_prepare_output,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_BEET,
 	.flags = XFRM_MODE_FLAG_TUNNEL,
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index 9a43ea72248..d45ce5d4419 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -38,33 +38,22 @@ static inline void ip6ip_ecn_decapsulate(struct sk_buff *skb)
 static int xfrm6_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb->dst;
-	struct xfrm_dst *xdst = (struct xfrm_dst*)dst;
-	struct ipv6hdr *iph, *top_iph;
+	struct ipv6hdr *top_iph;
 	int dsfield;
 
-	iph = ipv6_hdr(skb);
-
 	skb_set_network_header(skb, -x->props.header_len);
 	skb->mac_header = skb->network_header +
 			  offsetof(struct ipv6hdr, nexthdr);
-	skb->transport_header = skb->network_header + sizeof(*iph);
+	skb->transport_header = skb->network_header + sizeof(*top_iph);
 	top_iph = ipv6_hdr(skb);
 
 	top_iph->version = 6;
-	if (xdst->route->ops->family == AF_INET6) {
-		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];
-		top_iph->nexthdr = IPPROTO_IPV6;
-	} else {
-		top_iph->priority = 0;
-		top_iph->flow_lbl[0] = 0;
-		top_iph->flow_lbl[1] = 0;
-		top_iph->flow_lbl[2] = 0;
-		top_iph->nexthdr = IPPROTO_IPIP;
-	}
-	dsfield = ipv6_get_dsfield(top_iph);
+
+	memcpy(top_iph->flow_lbl, XFRM_MODE_SKB_CB(skb)->flow_lbl,
+	       sizeof(top_iph->flow_lbl));
+	top_iph->nexthdr = x->inner_mode->afinfo->proto;
+
+	dsfield = XFRM_MODE_SKB_CB(skb)->tos;
 	dsfield = INET_ECN_encapsulate(dsfield, dsfield);
 	if (x->props.flags & XFRM_STATE_NOECN)
 		dsfield &= ~INET_ECN_MASK;
@@ -72,7 +61,6 @@ static int xfrm6_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
 	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);
-	skb->protocol = htons(ETH_P_IPV6);
 	return 0;
 }
 
@@ -116,7 +104,8 @@ out:
 
 static struct xfrm_mode xfrm6_tunnel_mode = {
 	.input = xfrm6_tunnel_input,
-	.output = xfrm6_tunnel_output,
+	.output2 = xfrm6_tunnel_output,
+	.output = xfrm6_prepare_output,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_TUNNEL,
 	.flags = XFRM_MODE_FLAG_TUNNEL,
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 656976760ad..bc2e80e3b0b 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -10,10 +10,12 @@
  */
 
 #include <linux/if_ether.h>
-#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/skbuff.h>
 #include <linux/icmpv6.h>
 #include <linux/netfilter_ipv6.h>
+#include <net/dst.h>
 #include <net/ipv6.h>
 #include <net/xfrm.h>
 
@@ -43,19 +45,38 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb)
 	return ret;
 }
 
+int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err;
+
+	err = xfrm6_tunnel_check_size(skb);
+	if (err)
+		return err;
+
+	return xfrm6_extract_header(skb);
+}
+
+int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err;
+
+	err = x->inner_mode->afinfo->extract_output(x, skb);
+	if (err)
+		return err;
+
+	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+
+	skb->protocol = htons(ETH_P_IPV6);
+
+	return x->outer_mode->output2(x, skb);
+}
+EXPORT_SYMBOL(xfrm6_prepare_output);
+
 static inline int xfrm6_output_one(struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb->dst;
-	struct xfrm_state *x = dst->xfrm;
 	struct ipv6hdr *iph;
 	int err;
 
-	if (x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL) {
-		err = xfrm6_tunnel_check_size(skb);
-		if (err)
-			goto error_nolock;
-	}
-
 	err = xfrm_output(skb);
 	if (err)
 		goto error_nolock;
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
index b392bee396f..98b05f47232 100644
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -14,6 +14,7 @@
 #include <net/xfrm.h>
 #include <linux/pfkeyv2.h>
 #include <linux/ipsec.h>
+#include <net/dsfield.h>
 #include <net/ipv6.h>
 #include <net/addrconf.h>
 
@@ -168,13 +169,30 @@ __xfrm6_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n)
 	return 0;
 }
 
+int xfrm6_extract_header(struct sk_buff *skb)
+{
+	struct ipv6hdr *iph = ipv6_hdr(skb);
+
+	XFRM_MODE_SKB_CB(skb)->id = 0;
+	XFRM_MODE_SKB_CB(skb)->frag_off = htons(IP_DF);
+	XFRM_MODE_SKB_CB(skb)->tos = ipv6_get_dsfield(iph);
+	XFRM_MODE_SKB_CB(skb)->ttl = iph->hop_limit;
+	XFRM_MODE_SKB_CB(skb)->protocol = iph->nexthdr;
+	memcpy(XFRM_MODE_SKB_CB(skb)->flow_lbl, iph->flow_lbl,
+	       sizeof(XFRM_MODE_SKB_CB(skb)->flow_lbl));
+
+	return 0;
+}
+
 static struct xfrm_state_afinfo xfrm6_state_afinfo = {
 	.family			= AF_INET6,
+	.proto			= IPPROTO_IPV6,
 	.owner			= THIS_MODULE,
 	.init_tempsel		= __xfrm6_init_tempsel,
 	.tmpl_sort		= __xfrm6_tmpl_sort,
 	.state_sort		= __xfrm6_state_sort,
 	.output			= xfrm6_output,
+	.extract_output		= xfrm6_extract_output,
 };
 
 void __init xfrm6_state_init(void)