aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4/ipvs/ip_vs_proto_udp.c
blob: 54aa7603591f5c3e9091cb341d6ae4aab4bcd96f (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
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
/*
 * ip_vs_proto_udp.c:	UDP load balancing support for IPVS
 *
 * Version:     $Id: ip_vs_proto_udp.c,v 1.3 2002/11/30 01:50:35 wensong Exp $
 *
 * Authors:     Wensong Zhang <wensong@linuxvirtualserver.org>
 *              Julian Anastasov <ja@ssi.bg>
 *
 *              This program is free software; you can redistribute it and/or
 *              modify it under the terms of the GNU General Public License
 *              as published by the Free Software Foundation; either version
 *              2 of the License, or (at your option) any later version.
 *
 * Changes:
 *
 */

#include <linux/in.h>
#include <linux/ip.h>
#include <linux/kernel.h>
#include <linux/netfilter_ipv4.h>
#include <linux/udp.h>

#include <net/ip_vs.h>


static struct ip_vs_conn *
udp_conn_in_get(const struct sk_buff *skb, struct ip_vs_protocol *pp,
		const struct iphdr *iph, unsigned int proto_off, int inverse)
{
	struct ip_vs_conn *cp;
	__be16 _ports[2], *pptr;

	pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports);
	if (pptr == NULL)
		return NULL;

	if (likely(!inverse)) {
		cp = ip_vs_conn_in_get(iph->protocol,
				       iph->saddr, pptr[0],
				       iph->daddr, pptr[1]);
	} else {
		cp = ip_vs_conn_in_get(iph->protocol,
				       iph->daddr, pptr[1],
				       iph->saddr, pptr[0]);
	}

	return cp;
}


static struct ip_vs_conn *
udp_conn_out_get(const struct sk_buff *skb, struct ip_vs_protocol *pp,
		 const struct iphdr *iph, unsigned int proto_off, int inverse)
{
	struct ip_vs_conn *cp;
	__be16 _ports[2], *pptr;

	pptr = skb_header_pointer(skb, skb->nh.iph->ihl*4,
				  sizeof(_ports), _ports);
	if (pptr == NULL)
		return NULL;

	if (likely(!inverse)) {
		cp = ip_vs_conn_out_get(iph->protocol,
					iph->saddr, pptr[0],
					iph->daddr, pptr[1]);
	} else {
		cp = ip_vs_conn_out_get(iph->protocol,
					iph->daddr, pptr[1],
					iph->saddr, pptr[0]);
	}

	return cp;
}


static int
udp_conn_schedule(struct sk_buff *skb, struct ip_vs_protocol *pp,
		  int *verdict, struct ip_vs_conn **cpp)
{
	struct ip_vs_service *svc;
	struct udphdr _udph, *uh;

	uh = skb_header_pointer(skb, skb->nh.iph->ihl*4,
				sizeof(_udph), &_udph);
	if (uh == NULL) {
		*verdict = NF_DROP;
		return 0;
	}

	if ((svc = ip_vs_service_get(skb->nfmark, skb->nh.iph->protocol,
				     skb->nh.iph->daddr, uh->dest))) {
		if (ip_vs_todrop()) {
			/*
			 * It seems that we are very loaded.
			 * We have to drop this packet :(
			 */
			ip_vs_service_put(svc);
			*verdict = NF_DROP;
			return 0;
		}

		/*
		 * Let the virtual server select a real server for the
		 * incoming connection, and create a connection entry.
		 */
		*cpp = ip_vs_schedule(svc, skb);
		if (!*cpp) {
			*verdict = ip_vs_leave(svc, skb, pp);
			return 0;
		}
		ip_vs_service_put(svc);
	}
	return 1;
}


static inline void
udp_fast_csum_update(struct udphdr *uhdr, __be32 oldip, __be32 newip,
		     __be16 oldport, __be16 newport)
{
	uhdr->check =
		ip_vs_check_diff(~oldip, newip,
				 ip_vs_check_diff(oldport ^ htonl(0xFFFF),
						  newport, uhdr->check));
	if (!uhdr->check)
		uhdr->check = htonl(0xFFFF);
}

static int
udp_snat_handler(struct sk_buff **pskb,
		 struct ip_vs_protocol *pp, struct ip_vs_conn *cp)
{
	struct udphdr *udph;
	unsigned int udphoff = (*pskb)->nh.iph->ihl * 4;

	/* csum_check requires unshared skb */
	if (!ip_vs_make_skb_writable(pskb, udphoff+sizeof(*udph)))
		return 0;

	if (unlikely(cp->app != NULL)) {
		/* Some checks before mangling */
		if (pp->csum_check && !pp->csum_check(*pskb, pp))
			return 0;

		/*
		 *	Call application helper if needed
		 */
		if (!ip_vs_app_pkt_out(cp, pskb))
			return 0;
	}

	udph = (void *)(*pskb)->nh.iph + udphoff;
	udph->source = cp->vport;

	/*
	 *	Adjust UDP checksums
	 */
	if (!cp->app && (udph->check != 0)) {
		/* Only port and addr are changed, do fast csum update */
		udp_fast_csum_update(udph, cp->daddr, cp->vaddr,
				     cp->dport, cp->vport);
		if ((*pskb)->ip_summed == CHECKSUM_COMPLETE)
			(*pskb)->ip_summed = CHECKSUM_NONE;
	} else {
		/* full checksum calculation */
		udph->check = 0;
		(*pskb)->csum = skb_checksum(*pskb, udphoff,
					     (*pskb)->len - udphoff, 0);
		udph->check = csum_tcpudp_magic(cp->vaddr, cp->caddr,
						(*pskb)->len - udphoff,
						cp->protocol,
						(*pskb)->csum);
		if (udph->check == 0)
			udph->check = htonl(0xFFFF);
		IP_VS_DBG(11, "O-pkt: %s O-csum=%d (+%zd)\n",
			  pp->name, udph->check,
			  (char*)&(udph->check) - (char*)udph);
	}
	return 1;
}


static int
udp_dnat_handler(struct sk_buff **pskb,
		 struct ip_vs_protocol *pp, struct ip_vs_conn *cp)
{
	struct udphdr *udph;
	unsigned int udphoff = (*pskb)->nh.iph->ihl * 4;

	/* csum_check requires unshared skb */
	if (!ip_vs_make_skb_writable(pskb, udphoff+sizeof(*udph)))
		return 0;

	if (unlikely(cp->app != NULL)) {
		/* Some checks before mangling */
		if (pp->csum_check && !pp->csum_check(*pskb, pp))
			return 0;

		/*
		 *	Attempt ip_vs_app call.
		 *	It will fix ip_vs_conn
		 */
		if (!ip_vs_app_pkt_in(cp, pskb))
			return 0;
	}

	udph = (void *)(*pskb)->nh.iph + udphoff;
	udph->dest = cp->dport;

	/*
	 *	Adjust UDP checksums
	 */
	if (!cp->app && (udph->check != 0)) {
		/* Only port and addr are changed, do fast csum update */
		udp_fast_csum_update(udph, cp->vaddr, cp->daddr,
				     cp->vport, cp->dport);
		if ((*pskb)->ip_summed == CHECKSUM_COMPLETE)
			(*pskb)->ip_summed = CHECKSUM_NONE;
	} else {
		/* full checksum calculation */
		udph->check = 0;
		(*pskb)->csum = skb_checksum(*pskb, udphoff,
					     (*pskb)->len - udphoff, 0);
		udph->check = csum_tcpudp_magic(cp->caddr, cp->daddr,
						(*pskb)->len - udphoff,
						cp->protocol,
						(*pskb)->csum);
		if (udph->check == 0)
			udph->check = 0xFFFF;
		(*pskb)->ip_summed = CHECKSUM_UNNECESSARY;
	}
	return 1;
}


static int
udp_csum_check(struct sk_buff *skb, struct ip_vs_protocol *pp)
{
	struct udphdr _udph, *uh;
	unsigned int udphoff = skb->nh.iph->ihl*4;

	uh = skb_header_pointer(skb, udphoff, sizeof(_udph), &_udph);
	if (uh == NULL)
		return 0;

	if (uh->check != 0) {
		switch (skb->ip_summed) {
		case CHECKSUM_NONE:
			skb->csum = skb_checksum(skb, udphoff,
						 skb->len - udphoff, 0);
		case CHECKSUM_COMPLETE:
			if (csum_tcpudp_magic(skb->nh.iph->saddr,
					      skb->nh.iph->daddr,
					      skb->len - udphoff,
					      skb->nh.iph->protocol,
					      skb->csum)) {
				IP_VS_DBG_RL_PKT(0, pp, skb, 0,
						 "Failed checksum for");
				return 0;
			}
			break;
		default:
			/* No need to checksum. */
			break;
		}
	}
	return 1;
}


/*
 *	Note: the caller guarantees that only one of register_app,
 *	unregister_app or app_conn_bind is called each time.
 */

#define	UDP_APP_TAB_BITS	4
#define	UDP_APP_TAB_SIZE	(1 << UDP_APP_TAB_BITS)
#define	UDP_APP_TAB_MASK	(UDP_APP_TAB_SIZE - 1)

static struct list_head udp_apps[UDP_APP_TAB_SIZE];
static DEFINE_SPINLOCK(udp_app_lock);

static inline __u16 udp_app_hashkey(__u16 port)
{
	return ((port >> UDP_APP_TAB_BITS) ^ port) & UDP_APP_TAB_MASK;
}


static int udp_register_app(struct ip_vs_app *inc)
{
	struct ip_vs_app *i;
	__u16 hash, port = inc->port;
	int ret = 0;

	hash = udp_app_hashkey(port);


	spin_lock_bh(&udp_app_lock);
	list_for_each_entry(i, &udp_apps[hash], p_list) {
		if (i->port == port) {
			ret = -EEXIST;
			goto out;
		}
	}
	list_add(&inc->p_list, &udp_apps[hash]);
	atomic_inc(&ip_vs_protocol_udp.appcnt);

  out:
	spin_unlock_bh(&udp_app_lock);
	return ret;
}


static void
udp_unregister_app(struct ip_vs_app *inc)
{
	spin_lock_bh(&udp_app_lock);
	atomic_dec(&ip_vs_protocol_udp.appcnt);
	list_del(&inc->p_list);
	spin_unlock_bh(&udp_app_lock);
}


static int udp_app_conn_bind(struct ip_vs_conn *cp)
{
	int hash;
	struct ip_vs_app *inc;
	int result = 0;

	/* Default binding: bind app only for NAT */
	if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)
		return 0;

	/* Lookup application incarnations and bind the right one */
	hash = udp_app_hashkey(cp->vport);

	spin_lock(&udp_app_lock);
	list_for_each_entry(inc, &udp_apps[hash], p_list) {
		if (inc->port == cp->vport) {
			if (unlikely(!ip_vs_app_inc_get(inc)))
				break;
			spin_unlock(&udp_app_lock);

			IP_VS_DBG(9, "%s: Binding conn %u.%u.%u.%u:%u->"
				  "%u.%u.%u.%u:%u to app %s on port %u\n",
				  __FUNCTION__,
				  NIPQUAD(cp->caddr), ntohs(cp->cport),
				  NIPQUAD(cp->vaddr), ntohs(cp->vport),
				  inc->name, ntohs(inc->port));
			cp->app = inc;
			if (inc->init_conn)
				result = inc->init_conn(inc, cp);
			goto out;
		}
	}
	spin_unlock(&udp_app_lock);

  out:
	return result;
}


static int udp_timeouts[IP_VS_UDP_S_LAST+1] = {
	[IP_VS_UDP_S_NORMAL]		=	5*60*HZ,
	[IP_VS_UDP_S_LAST]		=	2*HZ,
};

static char * udp_state_name_table[IP_VS_UDP_S_LAST+1] = {
	[IP_VS_UDP_S_NORMAL]		=	"UDP",
	[IP_VS_UDP_S_LAST]		=	"BUG!",
};


static int
udp_set_state_timeout(struct ip_vs_protocol *pp, char *sname, int to)
{
	return ip_vs_set_state_timeout(pp->timeout_table, IP_VS_UDP_S_LAST,
				       udp_state_name_table, sname, to);
}

static const char * udp_state_name(int state)
{
	if (state >= IP_VS_UDP_S_LAST)
		return "ERR!";
	return udp_state_name_table[state] ? udp_state_name_table[state] : "?";
}

static int
udp_state_transition(struct ip_vs_conn *cp, int direction,
		     const struct sk_buff *skb,
		     struct ip_vs_protocol *pp)
{
	cp->timeout = pp->timeout_table[IP_VS_UDP_S_NORMAL];
	return 1;
}

static void udp_init(struct ip_vs_protocol *pp)
{
	IP_VS_INIT_HASH_TABLE(udp_apps);
	pp->timeout_table = udp_timeouts;
}

static void udp_exit(struct ip_vs_protocol *pp)
{
}


struct ip_vs_protocol ip_vs_protocol_udp = {
	.name =			"UDP",
	.protocol =		IPPROTO_UDP,
	.dont_defrag =		0,
	.init =			udp_init,
	.exit =			udp_exit,
	.conn_schedule =	udp_conn_schedule,
	.conn_in_get =		udp_conn_in_get,
	.conn_out_get =		udp_conn_out_get,
	.snat_handler =		udp_snat_handler,
	.dnat_handler =		udp_dnat_handler,
	.csum_check =		udp_csum_check,
	.state_transition =	udp_state_transition,
	.state_name =		udp_state_name,
	.register_app =		udp_register_app,
	.unregister_app =	udp_unregister_app,
	.app_conn_bind =	udp_app_conn_bind,
	.debug_packet =		ip_vs_tcpudp_debug_packet,
	.timeout_change =	NULL,
	.set_state_timeout =	udp_set_state_timeout,
};