summaryrefslogtreecommitdiff
path: root/net/ipv4/ipvs/ip_vs_xmit.c
blob: a8512a3fd08a02503aae30187f07f6b81ff9732c (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
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
/*
 * ip_vs_xmit.c: various packet transmitters for IPVS
 *
 * Version:     $Id: ip_vs_xmit.c,v 1.2 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/kernel.h>
#include <linux/ip.h>
#include <linux/tcp.h>                  /* for tcphdr */
#include <net/tcp.h>                    /* for csum_tcpudp_magic */
#include <net/udp.h>
#include <net/icmp.h>                   /* for icmp_send */
#include <net/route.h>                  /* for ip_route_output */
#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>

#include <net/ip_vs.h>


/*
 *      Destination cache to speed up outgoing route lookup
 */
static inline void
__ip_vs_dst_set(struct ip_vs_dest *dest, u32 rtos, struct dst_entry *dst)
{
	struct dst_entry *old_dst;

	old_dst = dest->dst_cache;
	dest->dst_cache = dst;
	dest->dst_rtos = rtos;
	dst_release(old_dst);
}

static inline struct dst_entry *
__ip_vs_dst_check(struct ip_vs_dest *dest, u32 rtos, u32 cookie)
{
	struct dst_entry *dst = dest->dst_cache;

	if (!dst)
		return NULL;
	if ((dst->obsolete || rtos != dest->dst_rtos) &&
	    dst->ops->check(dst, cookie) == NULL) {
		dest->dst_cache = NULL;
		dst_release(dst);
		return NULL;
	}
	dst_hold(dst);
	return dst;
}

static inline struct rtable *
__ip_vs_get_out_rt(struct ip_vs_conn *cp, u32 rtos)
{
	struct rtable *rt;			/* Route to the other host */
	struct ip_vs_dest *dest = cp->dest;

	if (dest) {
		spin_lock(&dest->dst_lock);
		if (!(rt = (struct rtable *)
		      __ip_vs_dst_check(dest, rtos, 0))) {
			struct flowi fl = {
				.oif = 0,
				.nl_u = {
					.ip4_u = {
						.daddr = dest->addr,
						.saddr = 0,
						.tos = rtos, } },
			};

			if (ip_route_output_key(&rt, &fl)) {
				spin_unlock(&dest->dst_lock);
				IP_VS_DBG_RL("ip_route_output error, "
					     "dest: %u.%u.%u.%u\n",
					     NIPQUAD(dest->addr));
				return NULL;
			}
			__ip_vs_dst_set(dest, rtos, dst_clone(&rt->u.dst));
			IP_VS_DBG(10, "new dst %u.%u.%u.%u, refcnt=%d, rtos=%X\n",
				  NIPQUAD(dest->addr),
				  atomic_read(&rt->u.dst.__refcnt), rtos);
		}
		spin_unlock(&dest->dst_lock);
	} else {
		struct flowi fl = {
			.oif = 0,
			.nl_u = {
				.ip4_u = {
					.daddr = cp->daddr,
					.saddr = 0,
					.tos = rtos, } },
		};

		if (ip_route_output_key(&rt, &fl)) {
			IP_VS_DBG_RL("ip_route_output error, dest: "
				     "%u.%u.%u.%u\n", NIPQUAD(cp->daddr));
			return NULL;
		}
	}

	return rt;
}


/*
 *	Release dest->dst_cache before a dest is removed
 */
void
ip_vs_dst_reset(struct ip_vs_dest *dest)
{
	struct dst_entry *old_dst;

	old_dst = dest->dst_cache;
	dest->dst_cache = NULL;
	dst_release(old_dst);
}

#define IP_VS_XMIT(skb, rt)				\
do {							\
	(skb)->nfcache |= NFC_IPVS_PROPERTY;		\
	(skb)->ip_summed = CHECKSUM_NONE;		\
	NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, (skb), NULL,	\
		(rt)->u.dst.dev, dst_output);		\
} while (0)


/*
 *      NULL transmitter (do nothing except return NF_ACCEPT)
 */
int
ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
		struct ip_vs_protocol *pp)
{
	/* we do not touch skb and do not need pskb ptr */
	return NF_ACCEPT;
}


/*
 *      Bypass transmitter
 *      Let packets bypass the destination when the destination is not
 *      available, it may be only used in transparent cache cluster.
 */
int
ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
		  struct ip_vs_protocol *pp)
{
	struct rtable *rt;			/* Route to the other host */
	struct iphdr  *iph = skb->nh.iph;
	u8     tos = iph->tos;
	int    mtu;
	struct flowi fl = {
		.oif = 0,
		.nl_u = {
			.ip4_u = {
				.daddr = iph->daddr,
				.saddr = 0,
				.tos = RT_TOS(tos), } },
	};

	EnterFunction(10);

	if (ip_route_output_key(&rt, &fl)) {
		IP_VS_DBG_RL("ip_vs_bypass_xmit(): ip_route_output error, "
			     "dest: %u.%u.%u.%u\n", NIPQUAD(iph->daddr));
		goto tx_error_icmp;
	}

	/* MTU checking */
	mtu = dst_mtu(&rt->u.dst);
	if ((skb->len > mtu) && (iph->frag_off&__constant_htons(IP_DF))) {
		ip_rt_put(rt);
		icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
		IP_VS_DBG_RL("ip_vs_bypass_xmit(): frag needed\n");
		goto tx_error;
	}

	/*
	 * Call ip_send_check because we are not sure it is called
	 * after ip_defrag. Is copy-on-write needed?
	 */
	if (unlikely((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)) {
		ip_rt_put(rt);
		return NF_STOLEN;
	}
	ip_send_check(skb->nh.iph);

	/* drop old route */
	dst_release(skb->dst);
	skb->dst = &rt->u.dst;

	/* Another hack: avoid icmp_send in ip_fragment */
	skb->local_df = 1;

	IP_VS_XMIT(skb, rt);

	LeaveFunction(10);
	return NF_STOLEN;

 tx_error_icmp:
	dst_link_failure(skb);
 tx_error:
	kfree_skb(skb);
	LeaveFunction(10);
	return NF_STOLEN;
}


/*
 *      NAT transmitter (only for outside-to-inside nat forwarding)
 *      Not used for related ICMP
 */
int
ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
	       struct ip_vs_protocol *pp)
{
	struct rtable *rt;		/* Route to the other host */
	int mtu;
	struct iphdr *iph = skb->nh.iph;

	EnterFunction(10);

	/* check if it is a connection of no-client-port */
	if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT)) {
		__u16 _pt, *p;
		p = skb_header_pointer(skb, iph->ihl*4, sizeof(_pt), &_pt);
		if (p == NULL)
			goto tx_error;
		ip_vs_conn_fill_cport(cp, *p);
		IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p));
	}

	if (!(rt = __ip_vs_get_out_rt(cp, RT_TOS(iph->tos))))
		goto tx_error_icmp;

	/* MTU checking */
	mtu = dst_mtu(&rt->u.dst);
	if ((skb->len > mtu) && (iph->frag_off&__constant_htons(IP_DF))) {
		ip_rt_put(rt);
		icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
		IP_VS_DBG_RL_PKT(0, pp, skb, 0, "ip_vs_nat_xmit(): frag needed for");
		goto tx_error;
	}

	/* copy-on-write the packet before mangling it */
	if (!ip_vs_make_skb_writable(&skb, sizeof(struct iphdr)))
		goto tx_error_put;

	if (skb_cow(skb, rt->u.dst.dev->hard_header_len))
		goto tx_error_put;

	/* drop old route */
	dst_release(skb->dst);
	skb->dst = &rt->u.dst;

	/* mangle the packet */
	if (pp->dnat_handler && !pp->dnat_handler(&skb, pp, cp))
		goto tx_error;
	skb->nh.iph->daddr = cp->daddr;
	ip_send_check(skb->nh.iph);

	IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT");

	/* FIXME: when application helper enlarges the packet and the length
	   is larger than the MTU of outgoing device, there will be still
	   MTU problem. */

	/* Another hack: avoid icmp_send in ip_fragment */
	skb->local_df = 1;

	IP_VS_XMIT(skb, rt);

	LeaveFunction(10);
	return NF_STOLEN;

  tx_error_icmp:
	dst_link_failure(skb);
  tx_error:
	LeaveFunction(10);
	kfree_skb(skb);
	return NF_STOLEN;
  tx_error_put:
	ip_rt_put(rt);
	goto tx_error;
}


/*
 *   IP Tunneling transmitter
 *
 *   This function encapsulates the packet in a new IP packet, its
 *   destination will be set to cp->daddr. Most code of this function
 *   is taken from ipip.c.
 *
 *   It is used in VS/TUN cluster. The load balancer selects a real
 *   server from a cluster based on a scheduling algorithm,
 *   encapsulates the request packet and forwards it to the selected
 *   server. For example, all real servers are configured with
 *   "ifconfig tunl0 <Virtual IP Address> up". When the server receives
 *   the encapsulated packet, it will decapsulate the packet, processe
 *   the request and return the response packets directly to the client
 *   without passing the load balancer. This can greatly increase the
 *   scalability of virtual server.
 *
 *   Used for ANY protocol
 */
int
ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
		  struct ip_vs_protocol *pp)
{
	struct rtable *rt;			/* Route to the other host */
	struct net_device *tdev;		/* Device to other host */
	struct iphdr  *old_iph = skb->nh.iph;
	u8     tos = old_iph->tos;
	u16    df = old_iph->frag_off;
	struct iphdr  *iph;			/* Our new IP header */
	int    max_headroom;			/* The extra header space needed */
	int    mtu;

	EnterFunction(10);

	if (skb->protocol != __constant_htons(ETH_P_IP)) {
		IP_VS_DBG_RL("ip_vs_tunnel_xmit(): protocol error, "
			     "ETH_P_IP: %d, skb protocol: %d\n",
			     __constant_htons(ETH_P_IP), skb->protocol);
		goto tx_error;
	}

	if (!(rt = __ip_vs_get_out_rt(cp, RT_TOS(tos))))
		goto tx_error_icmp;

	tdev = rt->u.dst.dev;

	mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr);
	if (mtu < 68) {
		ip_rt_put(rt);
		IP_VS_DBG_RL("ip_vs_tunnel_xmit(): mtu less than 68\n");
		goto tx_error;
	}
	if (skb->dst)
		skb->dst->ops->update_pmtu(skb->dst, mtu);

	df |= (old_iph->frag_off&__constant_htons(IP_DF));

	if ((old_iph->frag_off&__constant_htons(IP_DF))
	    && mtu < ntohs(old_iph->tot_len)) {
		icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
		ip_rt_put(rt);
		IP_VS_DBG_RL("ip_vs_tunnel_xmit(): frag needed\n");
		goto tx_error;
	}

	/*
	 * Okay, now see if we can stuff it in the buffer as-is.
	 */
	max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr);

	if (skb_headroom(skb) < max_headroom
	    || skb_cloned(skb) || skb_shared(skb)) {
		struct sk_buff *new_skb =
			skb_realloc_headroom(skb, max_headroom);
		if (!new_skb) {
			ip_rt_put(rt);
			kfree_skb(skb);
			IP_VS_ERR_RL("ip_vs_tunnel_xmit(): no memory\n");
			return NF_STOLEN;
		}
		kfree_skb(skb);
		skb = new_skb;
		old_iph = skb->nh.iph;
	}

	skb->h.raw = (void *) old_iph;

	/* fix old IP header checksum */
	ip_send_check(old_iph);

	skb->nh.raw = skb_push(skb, sizeof(struct iphdr));
	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));

	/* drop old route */
	dst_release(skb->dst);
	skb->dst = &rt->u.dst;

	/*
	 *	Push down and install the IPIP header.
	 */
	iph			=	skb->nh.iph;
	iph->version		=	4;
	iph->ihl		=	sizeof(struct iphdr)>>2;
	iph->frag_off		=	df;
	iph->protocol		=	IPPROTO_IPIP;
	iph->tos		=	tos;
	iph->daddr		=	rt->rt_dst;
	iph->saddr		=	rt->rt_src;
	iph->ttl		=	old_iph->ttl;
	iph->tot_len		=	htons(skb->len);
	ip_select_ident(iph, &rt->u.dst, NULL);
	ip_send_check(iph);

	/* Another hack: avoid icmp_send in ip_fragment */
	skb->local_df = 1;

	IP_VS_XMIT(skb, rt);

	LeaveFunction(10);

	return NF_STOLEN;

  tx_error_icmp:
	dst_link_failure(skb);
  tx_error:
	kfree_skb(skb);
	LeaveFunction(10);
	return NF_STOLEN;
}


/*
 *      Direct Routing transmitter
 *      Used for ANY protocol
 */
int
ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
	      struct ip_vs_protocol *pp)
{
	struct rtable *rt;			/* Route to the other host */
	struct iphdr  *iph = skb->nh.iph;
	int    mtu;

	EnterFunction(10);

	if (!(rt = __ip_vs_get_out_rt(cp, RT_TOS(iph->tos))))
		goto tx_error_icmp;

	/* MTU checking */
	mtu = dst_mtu(&rt->u.dst);
	if ((iph->frag_off&__constant_htons(IP_DF)) && skb->len > mtu) {
		icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
		ip_rt_put(rt);
		IP_VS_DBG_RL("ip_vs_dr_xmit(): frag needed\n");
		goto tx_error;
	}

	/*
	 * Call ip_send_check because we are not sure it is called
	 * after ip_defrag. Is copy-on-write needed?
	 */
	if (unlikely((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)) {
		ip_rt_put(rt);
		return NF_STOLEN;
	}
	ip_send_check(skb->nh.iph);

	/* drop old route */
	dst_release(skb->dst);
	skb->dst = &rt->u.dst;

	/* Another hack: avoid icmp_send in ip_fragment */
	skb->local_df = 1;

	IP_VS_XMIT(skb, rt);

	LeaveFunction(10);
	return NF_STOLEN;

  tx_error_icmp:
	dst_link_failure(skb);
  tx_error:
	kfree_skb(skb);
	LeaveFunction(10);
	return NF_STOLEN;
}


/*
 *	ICMP packet transmitter
 *	called by the ip_vs_in_icmp
 */
int
ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
		struct ip_vs_protocol *pp, int offset)
{
	struct rtable	*rt;	/* Route to the other host */
	int mtu;
	int rc;

	EnterFunction(10);

	/* The ICMP packet for VS/TUN, VS/DR and LOCALNODE will be
	   forwarded directly here, because there is no need to
	   translate address/port back */
	if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) {
		if (cp->packet_xmit)
			rc = cp->packet_xmit(skb, cp, pp);
		else
			rc = NF_ACCEPT;
		/* do not touch skb anymore */
		atomic_inc(&cp->in_pkts);
		goto out;
	}

	/*
	 * mangle and send the packet here (only for VS/NAT)
	 */

	if (!(rt = __ip_vs_get_out_rt(cp, RT_TOS(skb->nh.iph->tos))))
		goto tx_error_icmp;

	/* MTU checking */
	mtu = dst_mtu(&rt->u.dst);
	if ((skb->len > mtu) && (skb->nh.iph->frag_off&__constant_htons(IP_DF))) {
		ip_rt_put(rt);
		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
		IP_VS_DBG_RL("ip_vs_in_icmp(): frag needed\n");
		goto tx_error;
	}

	/* copy-on-write the packet before mangling it */
	if (!ip_vs_make_skb_writable(&skb, offset))
		goto tx_error_put;

	if (skb_cow(skb, rt->u.dst.dev->hard_header_len))
		goto tx_error_put;

	/* drop the old route when skb is not shared */
	dst_release(skb->dst);
	skb->dst = &rt->u.dst;

	ip_vs_nat_icmp(skb, pp, cp, 0);

	/* Another hack: avoid icmp_send in ip_fragment */
	skb->local_df = 1;

	IP_VS_XMIT(skb, rt);

	rc = NF_STOLEN;
	goto out;

  tx_error_icmp:
	dst_link_failure(skb);
  tx_error:
	dev_kfree_skb(skb);
	rc = NF_STOLEN;
  out:
	LeaveFunction(10);
	return rc;
  tx_error_put:
	ip_rt_put(rt);
	goto tx_error;
}