1 files changed, 333 insertions, 120 deletions

diff --git a/include/net/dst.h b/include/net/dst.h
index ae13370e848..71c60f42be4 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -8,20 +8,15 @@
 #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>
+#include <linux/bug.h>
 #include <linux/jiffies.h>
 #include <net/neighbour.h>
 #include <asm/processor.h>
 
-/*
- * 0 - no debugging messages
- * 1 - rare events and bugs (default)
- * 2 - trace mode.
- */
-#define RT_CACHE_DEBUG		0
-
 #define DST_GC_MIN	(HZ/10)
 #define DST_GC_INC	(HZ/2)
 #define DST_GC_MAX	(120*HZ)
@@ -35,44 +30,67 @@
 
 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
-	unsigned long		expires;
-
-	unsigned short		header_len;	/* more space at head required */
-	unsigned short		trailer_len;	/* space to reserve at tail */
-
-	unsigned int		rate_tokens;
-	unsigned long		rate_last;	/* rate limiting for ICMP */
-
+	struct  dst_ops	        *ops;
+	unsigned long		_metrics;
+	unsigned long           expires;
 	struct dst_entry	*path;
-
-	struct neighbour	*neighbour;
-	struct hh_cache		*hh;
+	struct dst_entry	*from;
+#ifdef CONFIG_XFRM
 	struct xfrm_state	*xfrm;
+#else
+	void			*__pad1;
+#endif
+	int			(*input)(struct sk_buff *);
+	int			(*output)(struct sock *sk, struct sk_buff *skb);
+
+	unsigned short		flags;
+#define DST_HOST		0x0001
+#define DST_NOXFRM		0x0002
+#define DST_NOPOLICY		0x0004
+#define DST_NOHASH		0x0008
+#define DST_NOCACHE		0x0010
+#define DST_NOCOUNT		0x0020
+#define DST_FAKE_RTABLE		0x0040
+#define DST_XFRM_TUNNEL		0x0080
+#define DST_XFRM_QUEUE		0x0100
+
+	unsigned short		pending_confirm;
 
-	int			(*input)(struct sk_buff*);
-	int			(*output)(struct sk_buff*);
-
-	struct  dst_ops	        *ops;
-
-	u32			metrics[RTAX_MAX];
+	short			error;
 
-#ifdef CONFIG_NET_CLS_ROUTE
+	/* A non-zero value of dst->obsolete forces by-hand validation
+	 * of the route entry.  Positive values are set by the generic
+	 * dst layer to indicate that the entry has been forcefully
+	 * destroyed.
+	 *
+	 * Negative values are used by the implementation layer code to
+	 * force invocation of the dst_ops->check() method.
+	 */
+	short			obsolete;
+#define DST_OBSOLETE_NONE	0
+#define DST_OBSOLETE_DEAD	2
+#define DST_OBSOLETE_FORCE_CHK	-1
+#define DST_OBSOLETE_KILL	-2
+	unsigned short		header_len;	/* more space at head required */
+	unsigned short		trailer_len;	/* space to reserve at tail */
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	__u32			tclassid;
+#else
+	__u32			__pad2;
 #endif
 
 	/*
+	 * Align __refcnt to a 64 bytes alignment
+	 * (L1_CACHE_SIZE would be too much)
+	 */
+#ifdef CONFIG_64BIT
+	long			__pad_to_align_refcnt[2];
+#endif
+	/*
 	 * __refcnt wants to be on a different cache line from
 	 * input/output/ops or performance tanks badly
 	 */
@@ -80,71 +98,153 @@ 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;
 	};
 };
 
+u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old);
+extern const u32 dst_default_metrics[];
+
+#define DST_METRICS_READ_ONLY		0x1UL
+#define DST_METRICS_FORCE_OVERWRITE	0x2UL
+#define DST_METRICS_FLAGS		0x3UL
+#define __DST_METRICS_PTR(Y)	\
+	((u32 *)((Y) & ~DST_METRICS_FLAGS))
+#define DST_METRICS_PTR(X)	__DST_METRICS_PTR((X)->_metrics)
+
+static inline bool dst_metrics_read_only(const struct dst_entry *dst)
+{
+	return dst->_metrics & DST_METRICS_READ_ONLY;
+}
 
-struct dst_ops
+static inline void dst_metrics_set_force_overwrite(struct dst_entry *dst)
 {
-	unsigned short		family;
-	__be16			protocol;
-	unsigned		gc_thresh;
+	dst->_metrics |= DST_METRICS_FORCE_OVERWRITE;
+}
 
-	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);
-	int			entry_size;
+void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old);
 
-	atomic_t		entries;
-	struct kmem_cache 		*kmem_cachep;
-	struct net              *dst_net;
-};
+static inline void dst_destroy_metrics_generic(struct dst_entry *dst)
+{
+	unsigned long val = dst->_metrics;
+	if (!(val & DST_METRICS_READ_ONLY))
+		__dst_destroy_metrics_generic(dst, val);
+}
+
+static inline u32 *dst_metrics_write_ptr(struct dst_entry *dst)
+{
+	unsigned long p = dst->_metrics;
+
+	BUG_ON(!p);
+
+	if (p & DST_METRICS_READ_ONLY)
+		return dst->ops->cow_metrics(dst, p);
+	return __DST_METRICS_PTR(p);
+}
+
+/* This may only be invoked before the entry has reached global
+ * visibility.
+ */
+static inline void dst_init_metrics(struct dst_entry *dst,
+				    const u32 *src_metrics,
+				    bool read_only)
+{
+	dst->_metrics = ((unsigned long) src_metrics) |
+		(read_only ? DST_METRICS_READ_ONLY : 0);
+}
+
+static inline void dst_copy_metrics(struct dst_entry *dest, const struct dst_entry *src)
+{
+	u32 *dst_metrics = dst_metrics_write_ptr(dest);
+
+	if (dst_metrics) {
+		u32 *src_metrics = DST_METRICS_PTR(src);
+
+		memcpy(dst_metrics, src_metrics, RTAX_MAX * sizeof(u32));
+	}
+}
+
+static inline u32 *dst_metrics_ptr(struct dst_entry *dst)
+{
+	return DST_METRICS_PTR(dst);
+}
+
+static inline u32
+dst_metric_raw(const struct dst_entry *dst, const int metric)
+{
+	u32 *p = DST_METRICS_PTR(dst);
+
+	return p[metric-1];
+}
+
+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);
+}
+
+static inline u32
+dst_metric_advmss(const struct dst_entry *dst)
+{
+	u32 advmss = dst_metric_raw(dst, RTAX_ADVMSS);
+
+	if (!advmss)
+		advmss = dst->ops->default_advmss(dst);
+
+	return advmss;
+}
 
-#ifdef __KERNEL__
+static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val)
+{
+	u32 *p = dst_metrics_write_ptr(dst);
+
+	if (p)
+		p[metric-1] = val;
+}
 
 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();
-	return mtu;
+	return dst->ops->mtu(dst);
+}
+
+/* RTT metrics are stored in milliseconds for user ABI, but used as jiffies */
+static inline unsigned long dst_metric_rtt(const struct dst_entry *dst, int metric)
+{
+	return msecs_to_jiffies(dst_metric(dst, metric));
 }
 
 static inline u32
 dst_allfrag(const struct dst_entry *dst)
 {
-	int ret = dst_metric(dst, RTAX_FEATURES) & RTAX_FEATURE_ALLFRAG;
-	/* Yes, _exactly_. This is paranoia. */
-	barrier();
+	int ret = dst_feature(dst,  RTAX_FEATURE_ALLFRAG);
 	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);
 }
 
-static inline void dst_hold(struct dst_entry * dst)
+static inline void dst_hold(struct dst_entry *dst)
 {
+	/*
+	 * If your kernel compilation stops here, please check
+	 * __pad_to_align_refcnt declaration in struct dst_entry
+	 */
+	BUILD_BUG_ON(offsetof(struct dst_entry, __refcnt) & 63);
 	atomic_inc(&dst->__refcnt);
 }
 
@@ -155,44 +255,131 @@ static inline void dst_use(struct dst_entry *dst, unsigned long time)
 	dst->lastuse = time;
 }
 
-static inline
-struct dst_entry * dst_clone(struct dst_entry * dst)
+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)
 {
 	if (dst)
 		atomic_inc(&dst->__refcnt);
 	return dst;
 }
 
-static inline
-void dst_release(struct dst_entry * dst)
+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 (dst) {
-		WARN_ON(atomic_read(&dst->__refcnt) < 1);
-		smp_mb__before_atomic_dec();
-		atomic_dec(&dst->__refcnt);
+	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
+ *	@net: netns for packet i/o
+ *
+ *	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,
+				   struct net *net)
+{
+	skb->dev = dev;
+
+	/*
+	 * Clear hash so that we can recalulate the hash for the
+	 * encapsulated packet, unless we have already determine the hash
+	 * over the L4 4-tuple.
+	 */
+	skb_clear_hash_if_not_l4(skb);
+	skb_set_queue_mapping(skb, 0);
+	skb_scrub_packet(skb, !net_eq(net, dev_net(dev)));
+}
+
+/**
+ *	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,
+				 struct net *net)
+{
+	/* TODO : stats should be SMP safe */
+	dev->stats.rx_packets++;
+	dev->stats.rx_bytes += skb->len;
+	__skb_tunnel_rx(skb, dev, net);
+}
+
 /* 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 = dst_clone(skb_dst(skb)->child);
 
-	dst_release(dst);
+	skb_dst_drop(skb);
 	return child;
 }
 
-extern int dst_discard(struct sk_buff *skb);
-extern void * dst_alloc(struct dst_ops * ops);
-extern void __dst_free(struct dst_entry * dst);
-extern struct dst_entry *dst_destroy(struct dst_entry * dst);
+int dst_discard_sk(struct sock *sk, struct sk_buff *skb);
+static inline int dst_discard(struct sk_buff *skb)
+{
+	return dst_discard_sk(skb->sk, skb);
+}
+void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_ref,
+		int initial_obsolete, unsigned short flags);
+void __dst_free(struct dst_entry *dst);
+struct dst_entry *dst_destroy(struct dst_entry *dst);
 
-static inline void dst_free(struct dst_entry * dst)
+static inline void dst_free(struct dst_entry *dst)
 {
-	if (dst->obsolete > 1)
+	if (dst->obsolete > 0)
 		return;
 	if (!atomic_read(&dst->__refcnt)) {
 		dst = dst_destroy(dst);
@@ -210,20 +397,46 @@ static inline void dst_rcu_free(struct rcu_head *head)
 
 static inline void dst_confirm(struct dst_entry *dst)
 {
-	if (dst)
-		neigh_confirm(dst->neighbour);
+	dst->pending_confirm = 1;
+}
+
+static inline int dst_neigh_output(struct dst_entry *dst, struct neighbour *n,
+				   struct sk_buff *skb)
+{
+	const struct hh_cache *hh;
+
+	if (dst->pending_confirm) {
+		unsigned long now = jiffies;
+
+		dst->pending_confirm = 0;
+		/* avoid dirtying neighbour */
+		if (n->confirmed != now)
+			n->confirmed = now;
+	}
+
+	hh = &n->hh;
+	if ((n->nud_state & NUD_CONNECTED) && hh->hh_len)
+		return neigh_hh_output(hh, skb);
+	else
+		return n->output(n, skb);
 }
 
-static inline void dst_negative_advice(struct dst_entry **dst_p)
+static inline struct neighbour *dst_neigh_lookup(const struct dst_entry *dst, const void *daddr)
 {
-	struct dst_entry * dst = *dst_p;
-	if (dst && dst->ops->negative_advice)
-		*dst_p = dst->ops->negative_advice(dst);
+	struct neighbour *n = dst->ops->neigh_lookup(dst, NULL, daddr);
+	return IS_ERR(n) ? NULL : n;
+}
+
+static inline struct neighbour *dst_neigh_lookup_skb(const struct dst_entry *dst,
+						     struct sk_buff *skb)
+{
+	struct neighbour *n =  dst->ops->neigh_lookup(dst, skb, NULL);
+	return IS_ERR(n) ? NULL : n;
 }
 
 static inline void dst_link_failure(struct sk_buff *skb)
 {
-	struct dst_entry * dst = skb->dst;
+	struct dst_entry *dst = skb_dst(skb);
 	if (dst && dst->ops && dst->ops->link_failure)
 		dst->ops->link_failure(skb);
 }
@@ -240,25 +453,19 @@ static inline void dst_set_expires(struct dst_entry *dst, int timeout)
 }
 
 /* Output packet to network from transport.  */
+static inline int dst_output_sk(struct sock *sk, struct sk_buff *skb)
+{
+	return skb_dst(skb)->output(sk, skb);
+}
 static inline int dst_output(struct sk_buff *skb)
 {
-	return skb->dst->output(skb);
+	return dst_output_sk(skb->sk, skb);
 }
 
 /* Input packet from network to transport.  */
 static inline int dst_input(struct sk_buff *skb)
 {
-	int err;
-
-	for (;;) {
-		err = skb->dst->input(skb);
-
-		if (likely(err == 0))
-			return err;
-		/* Oh, Jamal... Seems, I will not forgive you this mess. :-) */
-		if (unlikely(err != NET_XMIT_BYPASS))
-			return err;
-	}
+	return skb_dst(skb)->input(skb);
 }
 
 static inline struct dst_entry *dst_check(struct dst_entry *dst, u32 cookie)
@@ -268,32 +475,38 @@ static inline struct dst_entry *dst_check(struct dst_entry *dst, u32 cookie)
 	return dst;
 }
 
-extern void		dst_init(void);
+void dst_init(void);
 
 /* Flags for xfrm_lookup flags argument. */
 enum {
-	XFRM_LOOKUP_WAIT = 1 << 0,
-	XFRM_LOOKUP_ICMP = 1 << 1,
+	XFRM_LOOKUP_ICMP = 1 << 0,
 };
 
 struct flowi;
 #ifndef CONFIG_XFRM
-static inline int xfrm_lookup(struct dst_entry **dst_p, struct flowi *fl,
-		       struct sock *sk, int flags)
+static inline struct dst_entry *xfrm_lookup(struct net *net,
+					    struct dst_entry *dst_orig,
+					    const struct flowi *fl, struct sock *sk,
+					    int flags)
 {
-	return 0;
+	return dst_orig;
 } 
-static inline int __xfrm_lookup(struct dst_entry **dst_p, struct flowi *fl,
-				struct sock *sk, int flags)
+
+static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst)
 {
-	return 0;
+	return NULL;
 }
+
 #else
-extern int xfrm_lookup(struct dst_entry **dst_p, struct flowi *fl,
-		       struct sock *sk, int flags);
-extern int __xfrm_lookup(struct dst_entry **dst_p, struct flowi *fl,
-			 struct sock *sk, int flags);
-#endif
+struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
+			      const struct flowi *fl, struct sock *sk,
+			      int flags);
+
+/* skb attached with this dst needs transformation if dst->xfrm is valid */
+static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst)
+{
+	return dst->xfrm;
+}
 #endif
 
 #endif /* _NET_DST_H */