1 files changed, 147 insertions, 54 deletions

diff --git a/include/net/dst.h b/include/net/dst.h
index 7fc409c19b37..93b0310317be 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -8,6 +8,7 @@
 #ifndef _NET_DST_H
 #define _NET_DST_H
 
+#include <net/dst_ops.h>
 #include <linux/netdevice.h>
 #include <linux/rtnetlink.h>
 #include <linux/rcupdate.h>
@@ -35,18 +36,18 @@
 
 struct sk_buff;
 
-struct dst_entry
-{
+struct dst_entry {
 	struct rcu_head		rcu_head;
 	struct dst_entry	*child;
 	struct net_device       *dev;
 	short			error;
 	short			obsolete;
 	int			flags;
-#define DST_HOST		1
-#define DST_NOXFRM		2
-#define DST_NOPOLICY		4
-#define DST_NOHASH		8
+#define DST_HOST		0x0001
+#define DST_NOXFRM		0x0002
+#define DST_NOPOLICY		0x0004
+#define DST_NOHASH		0x0008
+#define DST_NOCACHE		0x0010
 	unsigned long		expires;
 
 	unsigned short		header_len;	/* more space at head required */
@@ -69,7 +70,7 @@ struct dst_entry
 
 	struct  dst_ops	        *ops;
 
-	u32			metrics[RTAX_MAX];
+	u32			_metrics[RTAX_MAX];
 
 #ifdef CONFIG_NET_CLS_ROUTE
 	__u32			tclassid;
@@ -83,8 +84,6 @@ struct dst_entry
 	 * (L1_CACHE_SIZE would be too much)
 	 */
 #ifdef CONFIG_64BIT
-	long			__pad_to_align_refcnt[2];
-#else
 	long			__pad_to_align_refcnt[1];
 #endif
 	/*
@@ -95,50 +94,74 @@ struct dst_entry
 	int			__use;
 	unsigned long		lastuse;
 	union {
-		struct dst_entry *next;
-		struct rtable    *rt_next;
-		struct rt6_info   *rt6_next;
-		struct dn_route  *dn_next;
+		struct dst_entry	*next;
+		struct rtable __rcu	*rt_next;
+		struct rt6_info		*rt6_next;
+		struct dn_route __rcu	*dn_next;
 	};
 };
 
+#ifdef __KERNEL__
 
-struct dst_ops
+static inline u32
+dst_metric_raw(const struct dst_entry *dst, const int metric)
 {
-	unsigned short		family;
-	__be16			protocol;
-	unsigned		gc_thresh;
+	return dst->_metrics[metric-1];
+}
 
-	int			(*gc)(struct dst_ops *ops);
-	struct dst_entry *	(*check)(struct dst_entry *, __u32 cookie);
-	void			(*destroy)(struct dst_entry *);
-	void			(*ifdown)(struct dst_entry *,
-					  struct net_device *dev, int how);
-	struct dst_entry *	(*negative_advice)(struct dst_entry *);
-	void			(*link_failure)(struct sk_buff *);
-	void			(*update_pmtu)(struct dst_entry *dst, u32 mtu);
-	int			(*local_out)(struct sk_buff *skb);
+static inline u32
+dst_metric(const struct dst_entry *dst, const int metric)
+{
+	WARN_ON_ONCE(metric == RTAX_HOPLIMIT ||
+		     metric == RTAX_ADVMSS ||
+		     metric == RTAX_MTU);
+	return dst_metric_raw(dst, metric);
+}
 
-	atomic_t		entries;
-	struct kmem_cache 		*kmem_cachep;
-	struct net              *dst_net;
-};
+static inline u32
+dst_metric_advmss(const struct dst_entry *dst)
+{
+	u32 advmss = dst_metric_raw(dst, RTAX_ADVMSS);
 
-#ifdef __KERNEL__
+	if (!advmss)
+		advmss = dst->ops->default_advmss(dst);
+
+	return advmss;
+}
+
+static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val)
+{
+	dst->_metrics[metric-1] = val;
+}
+
+static inline void dst_import_metrics(struct dst_entry *dst, const u32 *src_metrics)
+{
+	memcpy(dst->_metrics, src_metrics, RTAX_MAX * sizeof(u32));
+}
+
+static inline void dst_copy_metrics(struct dst_entry *dest, const struct dst_entry *src)
+{
+	dst_import_metrics(dest, src->_metrics);
+}
+
+static inline u32 *dst_metrics_ptr(struct dst_entry *dst)
+{
+	return dst->_metrics;
+}
 
 static inline u32
-dst_metric(const struct dst_entry *dst, int metric)
+dst_feature(const struct dst_entry *dst, u32 feature)
 {
-	return dst->metrics[metric-1];
+	return dst_metric(dst, RTAX_FEATURES) & feature;
 }
 
 static inline u32 dst_mtu(const struct dst_entry *dst)
 {
-	u32 mtu = dst_metric(dst, RTAX_MTU);
-	/*
-	 * Alexey put it here, so ask him about it :)
-	 */
-	barrier();
+	u32 mtu = dst_metric_raw(dst, RTAX_MTU);
+
+	if (!mtu)
+		mtu = dst->ops->default_mtu(dst);
+
 	return mtu;
 }
 
@@ -151,20 +174,20 @@ static inline unsigned long dst_metric_rtt(const struct dst_entry *dst, int metr
 static inline void set_dst_metric_rtt(struct dst_entry *dst, int metric,
 				      unsigned long rtt)
 {
-	dst->metrics[metric-1] = jiffies_to_msecs(rtt);
+	dst_metric_set(dst, metric, jiffies_to_msecs(rtt));
 }
 
 static inline u32
 dst_allfrag(const struct dst_entry *dst)
 {
-	int ret = dst_metric(dst, RTAX_FEATURES) & RTAX_FEATURE_ALLFRAG;
+	int ret = dst_feature(dst,  RTAX_FEATURE_ALLFRAG);
 	/* Yes, _exactly_. This is paranoia. */
 	barrier();
 	return ret;
 }
 
 static inline int
-dst_metric_locked(struct dst_entry *dst, int metric)
+dst_metric_locked(const struct dst_entry *dst, int metric)
 {
 	return dst_metric(dst, RTAX_LOCK) & (1<<metric);
 }
@@ -186,6 +209,12 @@ static inline void dst_use(struct dst_entry *dst, unsigned long time)
 	dst->lastuse = time;
 }
 
+static inline void dst_use_noref(struct dst_entry *dst, unsigned long time)
+{
+	dst->__use++;
+	dst->lastuse = time;
+}
+
 static inline
 struct dst_entry * dst_clone(struct dst_entry * dst)
 {
@@ -195,22 +224,93 @@ struct dst_entry * dst_clone(struct dst_entry * dst)
 }
 
 extern void dst_release(struct dst_entry *dst);
+
+static inline void refdst_drop(unsigned long refdst)
+{
+	if (!(refdst & SKB_DST_NOREF))
+		dst_release((struct dst_entry *)(refdst & SKB_DST_PTRMASK));
+}
+
+/**
+ * skb_dst_drop - drops skb dst
+ * @skb: buffer
+ *
+ * Drops dst reference count if a reference was taken.
+ */
 static inline void skb_dst_drop(struct sk_buff *skb)
 {
-	if (skb->_skb_dst)
-		dst_release(skb_dst(skb));
-	skb->_skb_dst = 0UL;
+	if (skb->_skb_refdst) {
+		refdst_drop(skb->_skb_refdst);
+		skb->_skb_refdst = 0UL;
+	}
+}
+
+static inline void skb_dst_copy(struct sk_buff *nskb, const struct sk_buff *oskb)
+{
+	nskb->_skb_refdst = oskb->_skb_refdst;
+	if (!(nskb->_skb_refdst & SKB_DST_NOREF))
+		dst_clone(skb_dst(nskb));
+}
+
+/**
+ * skb_dst_force - makes sure skb dst is refcounted
+ * @skb: buffer
+ *
+ * If dst is not yet refcounted, let's do it
+ */
+static inline void skb_dst_force(struct sk_buff *skb)
+{
+	if (skb_dst_is_noref(skb)) {
+		WARN_ON(!rcu_read_lock_held());
+		skb->_skb_refdst &= ~SKB_DST_NOREF;
+		dst_clone(skb_dst(skb));
+	}
+}
+
+
+/**
+ *	__skb_tunnel_rx - prepare skb for rx reinsert
+ *	@skb: buffer
+ *	@dev: tunnel device
+ *
+ *	After decapsulation, packet is going to re-enter (netif_rx()) our stack,
+ *	so make some cleanups. (no accounting done)
+ */
+static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev)
+{
+	skb->dev = dev;
+	skb->rxhash = 0;
+	skb_set_queue_mapping(skb, 0);
+	skb_dst_drop(skb);
+	nf_reset(skb);
+}
+
+/**
+ *	skb_tunnel_rx - prepare skb for rx reinsert
+ *	@skb: buffer
+ *	@dev: tunnel device
+ *
+ *	After decapsulation, packet is going to re-enter (netif_rx()) our stack,
+ *	so make some cleanups, and perform accounting.
+ *	Note: this accounting is not SMP safe.
+ */
+static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev)
+{
+	/* TODO : stats should be SMP safe */
+	dev->stats.rx_packets++;
+	dev->stats.rx_bytes += skb->len;
+	__skb_tunnel_rx(skb, dev);
 }
 
 /* Children define the path of the packet through the
  * Linux networking.  Thus, destinations are stackable.
  */
 
-static inline struct dst_entry *dst_pop(struct dst_entry *dst)
+static inline struct dst_entry *skb_dst_pop(struct sk_buff *skb)
 {
-	struct dst_entry *child = dst_clone(dst->child);
+	struct dst_entry *child = skb_dst(skb)->child;
 
-	dst_release(dst);
+	skb_dst_drop(skb);
 	return child;
 }
 
@@ -243,13 +343,6 @@ static inline void dst_confirm(struct dst_entry *dst)
 		neigh_confirm(dst->neighbour);
 }
 
-static inline void dst_negative_advice(struct dst_entry **dst_p)
-{
-	struct dst_entry * dst = *dst_p;
-	if (dst && dst->ops->negative_advice)
-		*dst_p = dst->ops->negative_advice(dst);
-}
-
 static inline void dst_link_failure(struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);