summaryrefslogtreecommitdiffstats
path: root/include/net/dst.h
blob: a8d825f90305a751447c207d140853c9bf79c523 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
/*
 * net/dst.h	Protocol independent destination cache definitions.
 *
 * Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
 *
 */

#ifndef _NET_DST_H
#define _NET_DST_H

#include <linux/netdevice.h>
#include <linux/rtnetlink.h>
#include <linux/rcupdate.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)

/* Each dst_entry has reference count and sits in some parent list(s).
 * When it is removed from parent list, it is "freed" (dst_free).
 * After this it enters dead state (dst->obsolete > 0) and if its refcnt
 * is zero, it can be destroyed immediately, otherwise it is added
 * to gc list and garbage collector periodically checks the refcnt.
 */

struct sk_buff;

struct dst_entry
{
	struct dst_entry        *next;
	atomic_t		__refcnt;	/* client references	*/
	int			__use;
	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_BALANCED            0x10
	unsigned long		lastuse;
	unsigned long		expires;

	unsigned short		header_len;	/* more space at head required */
	unsigned short		nfheader_len;	/* more non-fragment space at head required */
	unsigned short		trailer_len;	/* space to reserve at tail */

	u32			metrics[RTAX_MAX];
	struct dst_entry	*path;

	unsigned long		rate_last;	/* rate limiting for ICMP */
	unsigned long		rate_tokens;

	struct neighbour	*neighbour;
	struct hh_cache		*hh;
	struct xfrm_state	*xfrm;

	int			(*input)(struct sk_buff*);
	int			(*output)(struct sk_buff*);

#ifdef CONFIG_NET_CLS_ROUTE
	__u32			tclassid;
#endif

	struct  dst_ops	        *ops;
	struct rcu_head		rcu_head;
		
	char			info[0];
};


struct dst_ops
{
	unsigned short		family;
	unsigned short		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			entry_size;

	atomic_t		entries;
	kmem_cache_t 		*kmem_cachep;
};

#ifdef __KERNEL__

static inline u32
dst_metric(const struct dst_entry *dst, int metric)
{
	return dst->metrics[metric-1];
}

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;
}

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();
	return ret;
}

static inline int
dst_metric_locked(struct dst_entry *dst, int metric)
{
	return dst_metric(dst, RTAX_LOCK) & (1<<metric);
}

static inline void dst_hold(struct dst_entry * dst)
{
	atomic_inc(&dst->__refcnt);
}

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)
{
	if (dst) {
		WARN_ON(atomic_read(&dst->__refcnt) < 1);
		smp_mb__before_atomic_dec();
		atomic_dec(&dst->__refcnt);
	}
}

/* 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)
{
	struct dst_entry *child = dst_clone(dst->child);

	dst_release(dst);
	return child;
}

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);

static inline void dst_free(struct dst_entry * dst)
{
	if (dst->obsolete > 1)
		return;
	if (!atomic_read(&dst->__refcnt)) {
		dst = dst_destroy(dst);
		if (!dst)
			return;
	}
	__dst_free(dst);
}

static inline void dst_rcu_free(struct rcu_head *head)
{
	struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head);
	dst_free(dst);
}

static inline void dst_confirm(struct dst_entry *dst)
{
	if (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;
	if (dst && dst->ops && dst->ops->link_failure)
		dst->ops->link_failure(skb);
}

static inline void dst_set_expires(struct dst_entry *dst, int timeout)
{
	unsigned long expires = jiffies + timeout;

	if (expires == 0)
		expires = 1;

	if (dst->expires == 0 || time_before(expires, dst->expires))
		dst->expires = expires;
}

/* Output packet to network from transport.  */
static inline int dst_output(struct sk_buff *skb)
{
	return skb->dst->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;
	}
}

static inline struct dst_entry *dst_check(struct dst_entry *dst, u32 cookie)
{
	if (dst->obsolete)
		dst = dst->ops->check(dst, cookie);
	return dst;
}

extern void		dst_init(void);

struct flowi;
#ifndef CONFIG_XFRM
static inline int xfrm_lookup(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);
#endif
#endif

#endif /* _NET_DST_H */