#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)
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;
+ union {
+ unsigned long expires;
+ /* point to where the dst_entry copied from */
+ struct dst_entry *from;
+ };
struct dst_entry *path;
-
- struct neighbour *neighbour;
- struct hh_cache *hh;
+ struct neighbour __rcu *_neighbour;
#ifdef CONFIG_XFRM
struct xfrm_state *xfrm;
#else
int (*input)(struct sk_buff*);
int (*output)(struct sk_buff*);
- struct dst_ops *ops;
-
- u32 metrics[RTAX_MAX];
+ int 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_NOPEER 0x0040
-#ifdef CONFIG_NET_CLS_ROUTE
+ short error;
+ short obsolete;
+ 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];
-#else
- long __pad_to_align_refcnt[1];
#endif
/*
* __refcnt wants to be on a different cache line from
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__
+static inline struct neighbour *dst_get_neighbour_noref(struct dst_entry *dst)
+{
+ return rcu_dereference(dst->_neighbour);
+}
+
+static inline struct neighbour *dst_get_neighbour_noref_raw(struct dst_entry *dst)
+{
+ return rcu_dereference_raw(dst->_neighbour);
+}
+
+static inline void dst_set_neighbour(struct dst_entry *dst, struct neighbour *neigh)
+{
+ rcu_assign_pointer(dst->_neighbour, neigh);
+}
+
+extern u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old);
+extern const u32 dst_default_metrics[RTAX_MAX];
+
+#define DST_METRICS_READ_ONLY 0x1UL
+#define __DST_METRICS_PTR(Y) \
+ ((u32 *)((Y) & ~DST_METRICS_READ_ONLY))
+#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;
+}
+
+extern void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old);
+
+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, int metric)
+dst_metric(const struct dst_entry *dst, const int metric)
{
- return dst->metrics[metric-1];
+ 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;
+}
+
+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_feature(const struct dst_entry *dst, u32 feature)
{
- return (dst ? dst_metric(dst, RTAX_FEATURES) & feature : 0);
+ 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 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_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);
}
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)
{
}
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;
+
+ /*
+ * Clear rxhash so that we can recalulate the hash for the
+ * encapsulated packet, unless we have already determine the hash
+ * over the L4 4-tuple.
+ */
+ if (!skb->l4_rxhash)
+ 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 = 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_alloc(struct dst_ops * ops, struct net_device *dev,
+ int initial_ref, int initial_obsolete, int flags);
extern void __dst_free(struct dst_entry * dst);
extern struct dst_entry *dst_destroy(struct dst_entry * dst);
static inline void dst_confirm(struct dst_entry *dst)
{
- if (dst)
- neigh_confirm(dst->neighbour);
+ if (dst) {
+ struct neighbour *n;
+
+ rcu_read_lock();
+ n = dst_get_neighbour_noref(dst);
+ neigh_confirm(n);
+ rcu_read_unlock();
+ }
}
-static inline void dst_negative_advice(struct dst_entry **dst_p,
- struct sock *sk)
+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);
-
- if (dst != *dst_p) {
- extern void sk_reset_txq(struct sock *sk);
-
- sk_reset_txq(sk);
- }
- }
+ return dst->ops->neigh_lookup(dst, daddr);
}
static inline void dst_link_failure(struct sk_buff *skb)
/* 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 net *net, 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 net *net, struct dst_entry **dst_p,
- struct flowi *fl, struct sock *sk, int flags)
-{
- return 0;
-}
#else
-extern int xfrm_lookup(struct net *net, struct dst_entry **dst_p,
- struct flowi *fl, struct sock *sk, int flags);
-extern int __xfrm_lookup(struct net *net, struct dst_entry **dst_p,
- struct flowi *fl, struct sock *sk, int flags);
-#endif
+extern struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
+ const struct flowi *fl, struct sock *sk,
+ int flags);
#endif
#endif /* _NET_DST_H */