xfrm: Move child route linkage into xfrm_dst.

XFRM bundle child chains look like this:

	xdst1 --> xdst2 --> xdst3 --> path_dst

All of xdstN are xfrm_dst objects and xdst->u.dst.xfrm is non-NULL.
The final child pointer in the chain, here called 'path_dst', is some
other kind of route such as an ipv4 or ipv6 one.

The xfrm output path pops routes, one at a time, via the child
pointer, until we hit one which has a dst->xfrm pointer which
is NULL.

We can easily preserve the above mechanisms with child sitting
only in the xfrm_dst structure.  All children in the chain
before we break out of the xfrm_output() loop have dst->xfrm
non-NULL and are therefore xfrm_dst objects.

Since we break out of the loop when we find dst->xfrm NULL, we
will not try to dereference 'dst' as if it were an xfrm_dst.

Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 26 insertions, 18 deletions

diff --git a/include/net/dst.h b/include/net/dst.h
index acbb3fb89c4d..cef46207408c 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -35,7 +35,6 @@ struct sk_buff;
 struct dst_entry {
 	struct net_device       *dev;
 	struct rcu_head		rcu_head;
-	struct dst_entry	*child;
 	struct  dst_ops	        *ops;
 	unsigned long		_metrics;
 	unsigned long           expires;
@@ -89,7 +88,7 @@ struct dst_entry {
 	 * Align __refcnt to a 64 bytes alignment
 	 * (L1_CACHE_SIZE would be too much)
 	 */
-	long			__pad_to_align_refcnt[2];
+	long			__pad_to_align_refcnt[3];
 #endif
 	/*
 	 * __refcnt wants to be on a different cache line from
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 4c08eb0d46ce..0009dab61528 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -968,7 +968,7 @@ static inline bool xfrm_sec_ctx_match(struct xfrm_sec_ctx *s1, struct xfrm_sec_c
 
 /* A struct encoding bundle of transformations to apply to some set of flow.
  *
- * dst->child points to the next element of bundle.
+ * xdst->child points to the next element of bundle.
  * dst->xfrm  points to an instanse of transformer.
  *
  * Due to unfortunate limitations of current routing cache, which we
@@ -984,6 +984,7 @@ struct xfrm_dst {
 		struct rt6_info		rt6;
 	} u;
 	struct dst_entry *route;
+	struct dst_entry *child;
 	struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
 	int num_pols, num_xfrms;
 	u32 xfrm_genid;
@@ -997,8 +998,10 @@ struct xfrm_dst {
 static inline struct dst_entry *xfrm_dst_child(const struct dst_entry *dst)
 {
 #ifdef CONFIG_XFRM
-	if (dst->xfrm)
-		return dst->child;
+	if (dst->xfrm) {
+		struct xfrm_dst *xdst = (struct xfrm_dst *) dst;
+		return xdst->child;
+	}
 #endif
 	return NULL;
 }
@@ -1006,7 +1009,7 @@ static inline struct dst_entry *xfrm_dst_child(const struct dst_entry *dst)
 #ifdef CONFIG_XFRM
 static inline void xfrm_dst_set_child(struct xfrm_dst *xdst, struct dst_entry *child)
 {
-	xdst->u.dst.child = child;
+	xdst->child = child;
 }
 
 static inline void xfrm_dst_destroy(struct xfrm_dst *xdst)
@@ -1880,12 +1883,14 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x);
 static inline bool xfrm_dst_offload_ok(struct dst_entry *dst)
 {
 	struct xfrm_state *x = dst->xfrm;
+	struct xfrm_dst *xdst;
 
 	if (!x || !x->type_offload)
 		return false;
 
+	xdst = (struct xfrm_dst *) dst;
 	if (x->xso.offload_handle && (x->xso.dev == dst->path->dev) &&
-	    !dst->child->xfrm)
+	    !xdst->child->xfrm)
 		return true;
 
 	return false;
diff --git a/net/core/dst.c b/net/core/dst.c
index 6a3c21b8fc8d..5cf96179e8e0 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -21,6 +21,7 @@
 #include <linux/sched.h>
 #include <linux/prefetch.h>
 #include <net/lwtunnel.h>
+#include <net/xfrm.h>
 
 #include <net/dst.h>
 #include <net/dst_metadata.h>
@@ -62,7 +63,6 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops,
 	      struct net_device *dev, int initial_ref, int initial_obsolete,
 	      unsigned short flags)
 {
-	dst->child = NULL;
 	dst->dev = dev;
 	if (dev)
 		dev_hold(dev);
@@ -121,8 +121,11 @@ struct dst_entry *dst_destroy(struct dst_entry * dst)
 	smp_rmb();
 
 #ifdef CONFIG_XFRM
-	if (dst->xfrm)
-		child = dst->child;
+	if (dst->xfrm) {
+		struct xfrm_dst *xdst = (struct xfrm_dst *) dst;
+
+		child = xdst->child;
+	}
 #endif
 	if (!(dst->flags & DST_NOCOUNT))
 		dst_entries_add(dst->ops, -1);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index f95a15086225..b9ce241cd28c 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -399,7 +399,7 @@ struct pktgen_dev {
 	__u8	ipsmode;		/* IPSEC mode (config) */
 	__u8	ipsproto;		/* IPSEC type (config) */
 	__u32	spi;
-	struct dst_entry dst;
+	struct xfrm_dst xdst;
 	struct dst_ops dstops;
 #endif
 	char result[512];
@@ -2609,7 +2609,7 @@ static int pktgen_output_ipsec(struct sk_buff *skb, struct pktgen_dev *pkt_dev)
 	 * supports both transport/tunnel mode + ESP/AH type.
 	 */
 	if ((x->props.mode == XFRM_MODE_TUNNEL) && (pkt_dev->spi != 0))
-		skb->_skb_refdst = (unsigned long)&pkt_dev->dst | SKB_DST_NOREF;
+		skb->_skb_refdst = (unsigned long)&pkt_dev->xdst.u.dst | SKB_DST_NOREF;
 
 	rcu_read_lock_bh();
 	err = x->outer_mode->output(x, skb);
@@ -3742,10 +3742,10 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname)
 	 * performance under such circumstance.
 	 */
 	pkt_dev->dstops.family = AF_INET;
-	pkt_dev->dst.dev = pkt_dev->odev;
-	dst_init_metrics(&pkt_dev->dst, pktgen_dst_metrics, false);
-	pkt_dev->dst.child = &pkt_dev->dst;
-	pkt_dev->dst.ops = &pkt_dev->dstops;
+	pkt_dev->xdst.u.dst.dev = pkt_dev->odev;
+	dst_init_metrics(&pkt_dev->xdst.u.dst, pktgen_dst_metrics, false);
+	pkt_dev->xdst.child = &pkt_dev->xdst.u.dst;
+	pkt_dev->xdst.u.dst.ops = &pkt_dev->dstops;
 #endif
 
 	return add_dev_to_thread(t, pkt_dev);
diff --git a/net/netfilter/xt_policy.c b/net/netfilter/xt_policy.c
index 2b4ab189bba7..5639fb03bdd9 100644
--- a/net/netfilter/xt_policy.c
+++ b/net/netfilter/xt_policy.c
@@ -93,7 +93,8 @@ match_policy_out(const struct sk_buff *skb, const struct xt_policy_info *info,
 	if (dst->xfrm == NULL)
 		return -1;
 
-	for (i = 0; dst && dst->xfrm; dst = dst->child, i++) {
+	for (i = 0; dst && dst->xfrm;
+	     dst = ((struct xfrm_dst *)dst)->child, i++) {
 		pos = strict ? i : 0;
 		if (pos >= info->len)
 			return 0;
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 30e5746085b8..c5851ddddd2a 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -121,7 +121,7 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
 		return false;
 
 	if ((x->xso.offload_handle && (dev == dst->path->dev)) &&
-	     !dst->child->xfrm && x->type->get_mtu) {
+	     !xdst->child->xfrm && x->type->get_mtu) {
 		mtu = x->type->get_mtu(x, xdst->child_mtu_cached);
 
 		if (skb->len <= mtu)