#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>
struct sk_buff;
-struct dst_entry
-{
+struct dst_entry {
struct rcu_head rcu_head;
struct dst_entry *child;
struct net_device *dev;
unsigned short header_len; /* more space at head required */
unsigned short trailer_len; /* space to reserve at tail */
- u32 metrics[RTAX_MAX];
- struct dst_entry *path;
-
+ unsigned int rate_tokens;
unsigned long rate_last; /* rate limiting for ICMP */
- unsigned long rate_tokens;
+
+ struct dst_entry *path;
struct neighbour *neighbour;
struct hh_cache *hh;
+#ifdef CONFIG_XFRM
struct xfrm_state *xfrm;
-
+#else
+ void *__pad1;
+#endif
int (*input)(struct sk_buff*);
int (*output)(struct sk_buff*);
+ struct dst_ops *ops;
+
+ u32 metrics[RTAX_MAX];
+
#ifdef CONFIG_NET_CLS_ROUTE
__u32 tclassid;
+#else
+ __u32 __pad2;
#endif
- struct dst_ops *ops;
-
- unsigned long lastuse;
+
+ /*
+ * Align __refcnt to a 64 bytes alignment
+ * (L1_CACHE_SIZE would be too much)
+ */
+#ifdef CONFIG_64BIT
+ long __pad_to_align_refcnt[1];
+#endif
+ /*
+ * __refcnt wants to be on a different cache line from
+ * input/output/ops or performance tanks badly
+ */
atomic_t __refcnt; /* client references */
int __use;
+ unsigned long lastuse;
union {
struct dst_entry *next;
struct rtable *rt_next;
struct rt6_info *rt6_next;
struct dn_route *dn_next;
};
- char info[0];
-};
-
-
-struct dst_ops
-{
- unsigned short family;
- __be16 protocol;
- unsigned gc_thresh;
-
- int (*gc)(void);
- 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;
-
- atomic_t entries;
- struct kmem_cache *kmem_cachep;
};
#ifdef __KERNEL__
return dst->metrics[metric-1];
}
+static inline u32
+dst_feature(const struct dst_entry *dst, u32 feature)
+{
+ return dst_metric(dst, RTAX_FEATURES) & feature;
+}
+
static inline u32 dst_mtu(const struct dst_entry *dst)
{
u32 mtu = dst_metric(dst, RTAX_MTU);
return mtu;
}
+/* 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 void set_dst_metric_rtt(struct dst_entry *dst, int metric,
+ unsigned long rtt)
+{
+ dst->metrics[metric-1] = 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 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);
}
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)
{
return dst;
}
-static inline
-void dst_release(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_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)
{
- if (dst) {
- WARN_ON(atomic_read(&dst->__refcnt) < 1);
- smp_mb__before_atomic_dec();
- atomic_dec(&dst->__refcnt);
+ 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, and perform accounting.
+ */
+static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev)
+{
+ skb->dev = dev;
+ /* TODO : stats should be SMP safe */
+ dev->stats.rx_packets++;
+ dev->stats.rx_bytes += skb->len;
+ skb->rxhash = 0;
+ skb_dst_drop(skb);
+ nf_reset(skb);
+}
+
/* 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;
}
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;
+ struct dst_entry *dst = skb_dst(skb);
if (dst && dst->ops && dst->ops->link_failure)
dst->ops->link_failure(skb);
}
/* Output packet to network from transport. */
static inline int dst_output(struct sk_buff *skb)
{
- return skb->dst->output(skb);
+ return skb_dst(skb)->output(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)
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 int xfrm_lookup(struct net *net, struct dst_entry **dst_p,
+ struct flowi *fl, struct sock *sk, int flags)
{
return 0;
}
-static inline int __xfrm_lookup(struct dst_entry **dst_p, struct flowi *fl,
- struct sock *sk, int flags)
+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 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);
+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
#endif