ip_output.c 34.4 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1
2
3
4
5
6
7
8
9
/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		The Internet Protocol (IP) output module.
 *
 * Version:	$Id: ip_output.c,v 1.100 2002/02/01 22:01:03 davem Exp $
 *
10
 * Authors:	Ross Biro
Linus Torvalds's avatar
Linus Torvalds committed
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
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *		Donald Becker, <becker@super.org>
 *		Alan Cox, <Alan.Cox@linux.org>
 *		Richard Underwood
 *		Stefan Becker, <stefanb@yello.ping.de>
 *		Jorge Cwik, <jorge@laser.satlink.net>
 *		Arnt Gulbrandsen, <agulbra@nvg.unit.no>
 *		Hirokazu Takahashi, <taka@valinux.co.jp>
 *
 *	See ip_input.c for original log
 *
 *	Fixes:
 *		Alan Cox	:	Missing nonblock feature in ip_build_xmit.
 *		Mike Kilburn	:	htons() missing in ip_build_xmit.
 *		Bradford Johnson:	Fix faulty handling of some frames when 
 *					no route is found.
 *		Alexander Demenshin:	Missing sk/skb free in ip_queue_xmit
 *					(in case if packet not accepted by
 *					output firewall rules)
 *		Mike McLagan	:	Routing by source
 *		Alexey Kuznetsov:	use new route cache
 *		Andi Kleen:		Fix broken PMTU recovery and remove
 *					some redundant tests.
 *	Vitaly E. Lavrov	:	Transparent proxy revived after year coma.
 *		Andi Kleen	: 	Replace ip_reply with ip_send_reply.
 *		Andi Kleen	:	Split fast and slow ip_build_xmit path 
 *					for decreased register pressure on x86 
 *					and more readibility. 
 *		Marc Boucher	:	When call_out_firewall returns FW_QUEUE,
 *					silently drop skb instead of failing with -EPERM.
 *		Detlev Wengorz	:	Copy protocol for fragments.
 *		Hirokazu Takahashi:	HW checksumming for outgoing UDP
 *					datagrams.
 *		Hirokazu Takahashi:	sendfile() on UDP works now.
 */

#include <asm/uaccess.h>
#include <asm/system.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/errno.h>

#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/init.h>

#include <net/snmp.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/route.h>
71
#include <net/xfrm.h>
Linus Torvalds's avatar
Linus Torvalds committed
72
73
74
75
76
77
78
79
80
81
82
83
#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/arp.h>
#include <net/icmp.h>
#include <net/checksum.h>
#include <net/inetpeer.h>
#include <net/checksum.h>
#include <linux/igmp.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_bridge.h>
#include <linux/mroute.h>
#include <linux/netlink.h>
84
#include <linux/tcp.h>
Linus Torvalds's avatar
Linus Torvalds committed
85

86
int sysctl_ip_default_ttl __read_mostly = IPDEFTTL;
Linus Torvalds's avatar
Linus Torvalds committed
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

/* Generate a checksum for an outgoing IP datagram. */
__inline__ void ip_send_check(struct iphdr *iph)
{
	iph->check = 0;
	iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
}

/* dev_loopback_xmit for use with netfilter. */
static int ip_dev_loopback_xmit(struct sk_buff *newskb)
{
	newskb->mac.raw = newskb->data;
	__skb_pull(newskb, newskb->nh.raw - newskb->data);
	newskb->pkt_type = PACKET_LOOPBACK;
	newskb->ip_summed = CHECKSUM_UNNECESSARY;
	BUG_TRAP(newskb->dst);
	netif_rx(newskb);
	return 0;
}

static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst)
{
	int ttl = inet->uc_ttl;

	if (ttl < 0)
		ttl = dst_metric(dst, RTAX_HOPLIMIT);
	return ttl;
}

/* 
 *		Add an ip header to a skbuff and send it out.
 *
 */
int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
121
			  __be32 saddr, __be32 daddr, struct ip_options *opt)
Linus Torvalds's avatar
Linus Torvalds committed
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
{
	struct inet_sock *inet = inet_sk(sk);
	struct rtable *rt = (struct rtable *)skb->dst;
	struct iphdr *iph;

	/* Build the IP header. */
	if (opt)
		iph=(struct iphdr *)skb_push(skb,sizeof(struct iphdr) + opt->optlen);
	else
		iph=(struct iphdr *)skb_push(skb,sizeof(struct iphdr));

	iph->version  = 4;
	iph->ihl      = 5;
	iph->tos      = inet->tos;
	if (ip_dont_fragment(sk, &rt->u.dst))
		iph->frag_off = htons(IP_DF);
	else
		iph->frag_off = 0;
	iph->ttl      = ip_select_ttl(inet, &rt->u.dst);
	iph->daddr    = rt->rt_dst;
	iph->saddr    = rt->rt_src;
	iph->protocol = sk->sk_protocol;
	iph->tot_len  = htons(skb->len);
	ip_select_ident(iph, &rt->u.dst, sk);
	skb->nh.iph   = iph;

	if (opt && opt->optlen) {
		iph->ihl += opt->optlen>>2;
		ip_options_build(skb, opt, daddr, rt, 0);
	}
	ip_send_check(iph);

	skb->priority = sk->sk_priority;

	/* Send it out. */
	return NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, skb, NULL, rt->u.dst.dev,
		       dst_output);
}

161
162
EXPORT_SYMBOL_GPL(ip_build_and_send_pkt);

Linus Torvalds's avatar
Linus Torvalds committed
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
static inline int ip_finish_output2(struct sk_buff *skb)
{
	struct dst_entry *dst = skb->dst;
	struct hh_cache *hh = dst->hh;
	struct net_device *dev = dst->dev;
	int hh_len = LL_RESERVED_SPACE(dev);

	/* Be paranoid, rather than too clever. */
	if (unlikely(skb_headroom(skb) < hh_len && dev->hard_header)) {
		struct sk_buff *skb2;

		skb2 = skb_realloc_headroom(skb, LL_RESERVED_SPACE(dev));
		if (skb2 == NULL) {
			kfree_skb(skb);
			return -ENOMEM;
		}
		if (skb->sk)
			skb_set_owner_w(skb2, skb->sk);
		kfree_skb(skb);
		skb = skb2;
	}

	if (hh) {
		int hh_alen;

		read_lock_bh(&hh->hh_lock);
		hh_alen = HH_DATA_ALIGN(hh->hh_len);
  		memcpy(skb->data - hh_alen, hh->hh_data, hh_alen);
		read_unlock_bh(&hh->hh_lock);
	        skb_push(skb, hh->hh_len);
		return hh->hh_output(skb);
	} else if (dst->neighbour)
		return dst->neighbour->output(skb);

	if (net_ratelimit())
		printk(KERN_DEBUG "ip_finish_output2: No header cache and no neighbour!\n");
	kfree_skb(skb);
	return -EINVAL;
}

203
static inline int ip_finish_output(struct sk_buff *skb)
Linus Torvalds's avatar
Linus Torvalds committed
204
{
205
206
#if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
	/* Policy lookup after SNAT yielded a new policy */
207
208
209
210
	if (skb->dst->xfrm != NULL) {
		IPCB(skb)->flags |= IPSKB_REROUTED;
		return dst_output(skb);
	}
211
#endif
Herbert Xu's avatar
Herbert Xu committed
212
	if (skb->len > dst_mtu(skb->dst) && !skb_is_gso(skb))
213
214
215
		return ip_fragment(skb, ip_finish_output2);
	else
		return ip_finish_output2(skb);
Linus Torvalds's avatar
Linus Torvalds committed
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
}

int ip_mc_output(struct sk_buff *skb)
{
	struct sock *sk = skb->sk;
	struct rtable *rt = (struct rtable*)skb->dst;
	struct net_device *dev = rt->u.dst.dev;

	/*
	 *	If the indicated interface is up and running, send the packet.
	 */
	IP_INC_STATS(IPSTATS_MIB_OUTREQUESTS);

	skb->dev = dev;
	skb->protocol = htons(ETH_P_IP);

	/*
	 *	Multicasts are looped back for other local users
	 */

	if (rt->rt_flags&RTCF_MULTICAST) {
		if ((!sk || inet_sk(sk)->mc_loop)
#ifdef CONFIG_IP_MROUTE
		/* Small optimization: do not loopback not local frames,
		   which returned after forwarding; they will be  dropped
		   by ip_mr_input in any case.
		   Note, that local frames are looped back to be delivered
		   to local recipients.

		   This check is duplicated in ip_mr_input at the moment.
		 */
		    && ((rt->rt_flags&RTCF_LOCAL) || !(IPCB(skb)->flags&IPSKB_FORWARDED))
#endif
		) {
			struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
			if (newskb)
				NF_HOOK(PF_INET, NF_IP_POST_ROUTING, newskb, NULL,
					newskb->dev, 
					ip_dev_loopback_xmit);
		}

		/* Multicasts with ttl 0 must not go beyond the host */

		if (skb->nh.iph->ttl == 0) {
			kfree_skb(skb);
			return 0;
		}
	}

	if (rt->rt_flags&RTCF_BROADCAST) {
		struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
		if (newskb)
			NF_HOOK(PF_INET, NF_IP_POST_ROUTING, newskb, NULL,
				newskb->dev, ip_dev_loopback_xmit);
	}

272
273
274
	return NF_HOOK_COND(PF_INET, NF_IP_POST_ROUTING, skb, NULL, skb->dev,
			    ip_finish_output,
			    !(IPCB(skb)->flags & IPSKB_REROUTED));
Linus Torvalds's avatar
Linus Torvalds committed
275
276
277
278
}

int ip_output(struct sk_buff *skb)
{
279
280
	struct net_device *dev = skb->dst->dev;

Linus Torvalds's avatar
Linus Torvalds committed
281
282
	IP_INC_STATS(IPSTATS_MIB_OUTREQUESTS);

283
284
285
	skb->dev = dev;
	skb->protocol = htons(ETH_P_IP);

286
287
288
	return NF_HOOK_COND(PF_INET, NF_IP_POST_ROUTING, skb, NULL, dev,
		            ip_finish_output,
			    !(IPCB(skb)->flags & IPSKB_REROUTED));
Linus Torvalds's avatar
Linus Torvalds committed
289
290
}

291
int ip_queue_xmit(struct sk_buff *skb, struct sock *sk, int ipfragok)
Linus Torvalds's avatar
Linus Torvalds committed
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
{
	struct inet_sock *inet = inet_sk(sk);
	struct ip_options *opt = inet->opt;
	struct rtable *rt;
	struct iphdr *iph;

	/* Skip all of this if the packet is already routed,
	 * f.e. by something like SCTP.
	 */
	rt = (struct rtable *) skb->dst;
	if (rt != NULL)
		goto packet_routed;

	/* Make sure we can route this packet. */
	rt = (struct rtable *)__sk_dst_check(sk, 0);
	if (rt == NULL) {
308
		__be32 daddr;
Linus Torvalds's avatar
Linus Torvalds committed
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329

		/* Use correct destination address if we have options. */
		daddr = inet->daddr;
		if(opt && opt->srr)
			daddr = opt->faddr;

		{
			struct flowi fl = { .oif = sk->sk_bound_dev_if,
					    .nl_u = { .ip4_u =
						      { .daddr = daddr,
							.saddr = inet->saddr,
							.tos = RT_CONN_FLAGS(sk) } },
					    .proto = sk->sk_protocol,
					    .uli_u = { .ports =
						       { .sport = inet->sport,
							 .dport = inet->dport } } };

			/* If this fails, retransmit mechanism of transport layer will
			 * keep trying until route appears or the connection times
			 * itself out.
			 */
330
			security_sk_classify_flow(sk, &fl);
Linus Torvalds's avatar
Linus Torvalds committed
331
332
333
			if (ip_route_output_flow(&rt, &fl, sk, 0))
				goto no_route;
		}
334
		sk_setup_caps(sk, &rt->u.dst);
Linus Torvalds's avatar
Linus Torvalds committed
335
336
337
338
339
340
341
342
343
	}
	skb->dst = dst_clone(&rt->u.dst);

packet_routed:
	if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
		goto no_route;

	/* OK, we know where to send it, allocate and build IP header. */
	iph = (struct iphdr *) skb_push(skb, sizeof(struct iphdr) + (opt ? opt->optlen : 0));
344
	*((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (inet->tos & 0xff));
Linus Torvalds's avatar
Linus Torvalds committed
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
	iph->tot_len = htons(skb->len);
	if (ip_dont_fragment(sk, &rt->u.dst) && !ipfragok)
		iph->frag_off = htons(IP_DF);
	else
		iph->frag_off = 0;
	iph->ttl      = ip_select_ttl(inet, &rt->u.dst);
	iph->protocol = sk->sk_protocol;
	iph->saddr    = rt->rt_src;
	iph->daddr    = rt->rt_dst;
	skb->nh.iph   = iph;
	/* Transport layer set skb->h.foo itself. */

	if (opt && opt->optlen) {
		iph->ihl += opt->optlen >> 2;
		ip_options_build(skb, opt, inet->daddr, rt, 0);
	}

362
	ip_select_ident_more(iph, &rt->u.dst, sk,
363
			     (skb_shinfo(skb)->gso_segs ?: 1) - 1);
Linus Torvalds's avatar
Linus Torvalds committed
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387

	/* Add an IP checksum. */
	ip_send_check(iph);

	skb->priority = sk->sk_priority;

	return NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, skb, NULL, rt->u.dst.dev,
		       dst_output);

no_route:
	IP_INC_STATS(IPSTATS_MIB_OUTNOROUTES);
	kfree_skb(skb);
	return -EHOSTUNREACH;
}


static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
{
	to->pkt_type = from->pkt_type;
	to->priority = from->priority;
	to->protocol = from->protocol;
	dst_release(to->dst);
	to->dst = dst_clone(from->dst);
	to->dev = from->dev;
388
	to->mark = from->mark;
Linus Torvalds's avatar
Linus Torvalds committed
389
390
391
392
393
394
395
396
397
398
399
400
401

	/* Copy the flags to each fragment. */
	IPCB(to)->flags = IPCB(from)->flags;

#ifdef CONFIG_NET_SCHED
	to->tc_index = from->tc_index;
#endif
#ifdef CONFIG_NETFILTER
	/* Connection association is same as pre-frag packet */
	nf_conntrack_put(to->nfct);
	to->nfct = from->nfct;
	nf_conntrack_get(to->nfct);
	to->nfctinfo = from->nfctinfo;
402
403
404
#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
	to->ipvs_property = from->ipvs_property;
#endif
Linus Torvalds's avatar
Linus Torvalds committed
405
406
407
408
409
410
#ifdef CONFIG_BRIDGE_NETFILTER
	nf_bridge_put(to->nf_bridge);
	to->nf_bridge = from->nf_bridge;
	nf_bridge_get(to->nf_bridge);
#endif
#endif
411
	skb_copy_secmark(to, from);
Linus Torvalds's avatar
Linus Torvalds committed
412
413
414
415
416
417
418
419
420
}

/*
 *	This IP datagram is too large to be sent in one piece.  Break it up into
 *	smaller pieces (each of size equal to IP header plus
 *	a block of the data of the original IP data part) that will yet fit in a
 *	single device frame, and queue such a frame for sending.
 */

421
int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff*))
Linus Torvalds's avatar
Linus Torvalds committed
422
423
424
425
426
427
{
	struct iphdr *iph;
	int raw = 0;
	int ptr;
	struct net_device *dev;
	struct sk_buff *skb2;
428
	unsigned int mtu, hlen, left, len, ll_rs, pad;
Linus Torvalds's avatar
Linus Torvalds committed
429
	int offset;
430
	__be16 not_last_frag;
Linus Torvalds's avatar
Linus Torvalds committed
431
432
433
434
435
436
437
438
439
440
441
442
	struct rtable *rt = (struct rtable*)skb->dst;
	int err = 0;

	dev = rt->u.dst.dev;

	/*
	 *	Point into the IP datagram header.
	 */

	iph = skb->nh.iph;

	if (unlikely((iph->frag_off & htons(IP_DF)) && !skb->local_df)) {
443
		IP_INC_STATS(IPSTATS_MIB_FRAGFAILS);
Linus Torvalds's avatar
Linus Torvalds committed
444
445
446
447
448
449
450
451
452
453
454
455
		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
			  htonl(dst_mtu(&rt->u.dst)));
		kfree_skb(skb);
		return -EMSGSIZE;
	}

	/*
	 *	Setup starting values.
	 */

	hlen = iph->ihl * 4;
	mtu = dst_mtu(&rt->u.dst) - hlen;	/* Size of data space */
Herbert Xu's avatar
Herbert Xu committed
456
	IPCB(skb)->flags |= IPSKB_FRAG_COMPLETE;
Linus Torvalds's avatar
Linus Torvalds committed
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

	/* When frag_list is given, use it. First, check its validity:
	 * some transformers could create wrong frag_list or break existing
	 * one, it is not prohibited. In this case fall back to copying.
	 *
	 * LATER: this step can be merged to real generation of fragments,
	 * we can switch to copy when see the first bad fragment.
	 */
	if (skb_shinfo(skb)->frag_list) {
		struct sk_buff *frag;
		int first_len = skb_pagelen(skb);

		if (first_len - hlen > mtu ||
		    ((first_len - hlen) & 7) ||
		    (iph->frag_off & htons(IP_MF|IP_OFFSET)) ||
		    skb_cloned(skb))
			goto slow_path;

		for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next) {
			/* Correct geometry. */
			if (frag->len > mtu ||
			    ((frag->len & 7) && frag->next) ||
			    skb_headroom(frag) < hlen)
			    goto slow_path;

			/* Partially cloned skb? */
			if (skb_shared(frag))
				goto slow_path;
485
486
487
488
489
490
491
492

			BUG_ON(frag->sk);
			if (skb->sk) {
				sock_hold(skb->sk);
				frag->sk = skb->sk;
				frag->destructor = sock_wfree;
				skb->truesize -= frag->truesize;
			}
Linus Torvalds's avatar
Linus Torvalds committed
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
		}

		/* Everything is OK. Generate! */

		err = 0;
		offset = 0;
		frag = skb_shinfo(skb)->frag_list;
		skb_shinfo(skb)->frag_list = NULL;
		skb->data_len = first_len - skb_headlen(skb);
		skb->len = first_len;
		iph->tot_len = htons(first_len);
		iph->frag_off = htons(IP_MF);
		ip_send_check(iph);

		for (;;) {
			/* Prepare header of the next frame,
			 * before previous one went down. */
			if (frag) {
				frag->ip_summed = CHECKSUM_NONE;
				frag->h.raw = frag->data;
				frag->nh.raw = __skb_push(frag, hlen);
				memcpy(frag->nh.raw, iph, hlen);
				iph = frag->nh.iph;
				iph->tot_len = htons(frag->len);
				ip_copy_metadata(frag, skb);
				if (offset == 0)
					ip_options_fragment(frag);
				offset += skb->len - hlen;
				iph->frag_off = htons(offset>>3);
				if (frag->next != NULL)
					iph->frag_off |= htons(IP_MF);
				/* Ready, complete checksum */
				ip_send_check(iph);
			}

			err = output(skb);

530
531
			if (!err)
				IP_INC_STATS(IPSTATS_MIB_FRAGCREATES);
Linus Torvalds's avatar
Linus Torvalds committed
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
			if (err || !frag)
				break;

			skb = frag;
			frag = skb->next;
			skb->next = NULL;
		}

		if (err == 0) {
			IP_INC_STATS(IPSTATS_MIB_FRAGOKS);
			return 0;
		}

		while (frag) {
			skb = frag->next;
			kfree_skb(frag);
			frag = skb;
		}
		IP_INC_STATS(IPSTATS_MIB_FRAGFAILS);
		return err;
	}

slow_path:
	left = skb->len - hlen;		/* Space per frame */
	ptr = raw + hlen;		/* Where to start from */

	/* for bridged IP traffic encapsulated inside f.e. a vlan header,
559
560
561
562
563
564
	 * we need to make room for the encapsulating header
	 */
	pad = nf_bridge_pad(skb);
	ll_rs = LL_RESERVED_SPACE_EXTRA(rt->u.dst.dev, pad);
	mtu -= pad;

Linus Torvalds's avatar
Linus Torvalds committed
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
	/*
	 *	Fragment the datagram.
	 */

	offset = (ntohs(iph->frag_off) & IP_OFFSET) << 3;
	not_last_frag = iph->frag_off & htons(IP_MF);

	/*
	 *	Keep copying data until we run out.
	 */

	while(left > 0)	{
		len = left;
		/* IF: it doesn't fit, use 'mtu' - the data space left */
		if (len > mtu)
			len = mtu;
		/* IF: we are not sending upto and including the packet end
		   then align the next start on an eight byte boundary */
		if (len < left)	{
			len &= ~7;
		}
		/*
		 *	Allocate buffer.
		 */

		if ((skb2 = alloc_skb(len+hlen+ll_rs, GFP_ATOMIC)) == NULL) {
591
			NETDEBUG(KERN_INFO "IP: frag: no memory for new fragment!\n");
Linus Torvalds's avatar
Linus Torvalds committed
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
			err = -ENOMEM;
			goto fail;
		}

		/*
		 *	Set up data on packet
		 */

		ip_copy_metadata(skb2, skb);
		skb_reserve(skb2, ll_rs);
		skb_put(skb2, len + hlen);
		skb2->nh.raw = skb2->data;
		skb2->h.raw = skb2->data + hlen;

		/*
		 *	Charge the memory for the fragment to any owner
		 *	it might possess
		 */

		if (skb->sk)
			skb_set_owner_w(skb2, skb->sk);

		/*
		 *	Copy the packet header into the new buffer.
		 */

		memcpy(skb2->nh.raw, skb->data, hlen);

		/*
		 *	Copy a block of the IP datagram.
		 */
		if (skb_copy_bits(skb, ptr, skb2->h.raw, len))
			BUG();
		left -= len;

		/*
		 *	Fill in the new header fields.
		 */
		iph = skb2->nh.iph;
		iph->frag_off = htons((offset >> 3));

		/* ANK: dirty, but effective trick. Upgrade options only if
		 * the segment to be fragmented was THE FIRST (otherwise,
		 * options are already fixed) and make it ONCE
		 * on the initial skb, so that all the following fragments
		 * will inherit fixed options.
		 */
		if (offset == 0)
			ip_options_fragment(skb);

		/*
		 *	Added AC : If we are fragmenting a fragment that's not the
		 *		   last fragment then keep MF on each bit
		 */
		if (left > 0 || not_last_frag)
			iph->frag_off |= htons(IP_MF);
		ptr += len;
		offset += len;

		/*
		 *	Put this fragment into the sending queue.
		 */
		iph->tot_len = htons(len + hlen);

		ip_send_check(iph);

		err = output(skb2);
		if (err)
			goto fail;
661
662

		IP_INC_STATS(IPSTATS_MIB_FRAGCREATES);
Linus Torvalds's avatar
Linus Torvalds committed
663
664
665
666
667
668
669
670
671
672
673
	}
	kfree_skb(skb);
	IP_INC_STATS(IPSTATS_MIB_FRAGOKS);
	return err;

fail:
	kfree_skb(skb); 
	IP_INC_STATS(IPSTATS_MIB_FRAGFAILS);
	return err;
}

674
675
EXPORT_SYMBOL(ip_fragment);

Linus Torvalds's avatar
Linus Torvalds committed
676
677
678
679
680
int
ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb)
{
	struct iovec *iov = from;

681
	if (skb->ip_summed == CHECKSUM_PARTIAL) {
Linus Torvalds's avatar
Linus Torvalds committed
682
683
684
		if (memcpy_fromiovecend(to, iov, offset, len) < 0)
			return -EFAULT;
	} else {
685
		__wsum csum = 0;
Linus Torvalds's avatar
Linus Torvalds committed
686
687
688
689
690
691
692
		if (csum_partial_copy_fromiovecend(to, iov, offset, len, &csum) < 0)
			return -EFAULT;
		skb->csum = csum_block_add(skb->csum, csum, odd);
	}
	return 0;
}

693
static inline __wsum
Linus Torvalds's avatar
Linus Torvalds committed
694
695
696
csum_page(struct page *page, int offset, int copy)
{
	char *kaddr;
697
	__wsum csum;
Linus Torvalds's avatar
Linus Torvalds committed
698
699
700
701
702
703
	kaddr = kmap(page);
	csum = csum_partial(kaddr + offset, copy, 0);
	kunmap(page);
	return csum;
}

704
static inline int ip_ufo_append_data(struct sock *sk,
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
			int getfrag(void *from, char *to, int offset, int len,
			       int odd, struct sk_buff *skb),
			void *from, int length, int hh_len, int fragheaderlen,
			int transhdrlen, int mtu,unsigned int flags)
{
	struct sk_buff *skb;
	int err;

	/* There is support for UDP fragmentation offload by network
	 * device, so create one single skb packet containing complete
	 * udp datagram
	 */
	if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) {
		skb = sock_alloc_send_skb(sk,
			hh_len + fragheaderlen + transhdrlen + 20,
			(flags & MSG_DONTWAIT), &err);

		if (skb == NULL)
			return err;

		/* reserve space for Hardware header */
		skb_reserve(skb, hh_len);

		/* create space for UDP/IP header */
		skb_put(skb,fragheaderlen + transhdrlen);

		/* initialize network header pointer */
		skb->nh.raw = skb->data;

		/* initialize protocol header pointer */
		skb->h.raw = skb->data + fragheaderlen;

737
		skb->ip_summed = CHECKSUM_PARTIAL;
738
739
740
741
742
743
744
745
		skb->csum = 0;
		sk->sk_sndmsg_off = 0;
	}

	err = skb_append_datato_frags(sk,skb, getfrag, from,
			       (length - transhdrlen));
	if (!err) {
		/* specify the length of each IP datagram fragment*/
746
		skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
747
		skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
748
749
750
751
752
753
754
755
756
757
758
		__skb_queue_tail(&sk->sk_write_queue, skb);

		return 0;
	}
	/* There is not enough support do UFO ,
	 * so follow normal path
	 */
	kfree_skb(skb);
	return err;
}

Linus Torvalds's avatar
Linus Torvalds committed
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
/*
 *	ip_append_data() and ip_append_page() can make one large IP datagram
 *	from many pieces of data. Each pieces will be holded on the socket
 *	until ip_push_pending_frames() is called. Each piece can be a page
 *	or non-page data.
 *	
 *	Not only UDP, other transport protocols - e.g. raw sockets - can use
 *	this interface potentially.
 *
 *	LATER: length must be adjusted by pad at tail, when it is required.
 */
int ip_append_data(struct sock *sk,
		   int getfrag(void *from, char *to, int offset, int len,
			       int odd, struct sk_buff *skb),
		   void *from, int length, int transhdrlen,
		   struct ipcm_cookie *ipc, struct rtable *rt,
		   unsigned int flags)
{
	struct inet_sock *inet = inet_sk(sk);
	struct sk_buff *skb;

	struct ip_options *opt = NULL;
	int hh_len;
	int exthdrlen;
	int mtu;
	int copy;
	int err;
	int offset = 0;
	unsigned int maxfraglen, fragheaderlen;
	int csummode = CHECKSUM_NONE;

	if (flags&MSG_PROBE)
		return 0;

	if (skb_queue_empty(&sk->sk_write_queue)) {
		/*
		 * setup for corking.
		 */
		opt = ipc->opt;
		if (opt) {
			if (inet->cork.opt == NULL) {
				inet->cork.opt = kmalloc(sizeof(struct ip_options) + 40, sk->sk_allocation);
				if (unlikely(inet->cork.opt == NULL))
					return -ENOBUFS;
			}
			memcpy(inet->cork.opt, opt, sizeof(struct ip_options)+opt->optlen);
			inet->cork.flags |= IPCORK_OPT;
			inet->cork.addr = ipc->addr;
		}
		dst_hold(&rt->u.dst);
		inet->cork.fragsize = mtu = dst_mtu(rt->u.dst.path);
		inet->cork.rt = rt;
		inet->cork.length = 0;
		sk->sk_sndmsg_page = NULL;
		sk->sk_sndmsg_off = 0;
		if ((exthdrlen = rt->u.dst.header_len) != 0) {
			length += exthdrlen;
			transhdrlen += exthdrlen;
		}
	} else {
		rt = inet->cork.rt;
		if (inet->cork.flags & IPCORK_OPT)
			opt = inet->cork.opt;

		transhdrlen = 0;
		exthdrlen = 0;
		mtu = inet->cork.fragsize;
	}
	hh_len = LL_RESERVED_SPACE(rt->u.dst.dev);

	fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;

	if (inet->cork.length + length > 0xFFFF - fragheaderlen) {
		ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->dport, mtu-exthdrlen);
		return -EMSGSIZE;
	}

	/*
	 * transhdrlen > 0 means that this is the first fragment and we wish
	 * it won't be fragmented in the future.
	 */
	if (transhdrlen &&
	    length + fragheaderlen <= mtu &&
843
	    rt->u.dst.dev->features & NETIF_F_ALL_CSUM &&
Linus Torvalds's avatar
Linus Torvalds committed
844
	    !exthdrlen)
845
		csummode = CHECKSUM_PARTIAL;
Linus Torvalds's avatar
Linus Torvalds committed
846
847

	inet->cork.length += length;
848
849
850
	if (((length > mtu) && (sk->sk_protocol == IPPROTO_UDP)) &&
			(rt->u.dst.dev->features & NETIF_F_UFO)) {

851
852
853
854
		err = ip_ufo_append_data(sk, getfrag, from, length, hh_len,
					 fragheaderlen, transhdrlen, mtu,
					 flags);
		if (err)
855
856
857
			goto error;
		return 0;
	}
Linus Torvalds's avatar
Linus Torvalds committed
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907

	/* So, what's going on in the loop below?
	 *
	 * We use calculated fragment length to generate chained skb,
	 * each of segments is IP fragment ready for sending to network after
	 * adding appropriate IP header.
	 */

	if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL)
		goto alloc_new_skb;

	while (length > 0) {
		/* Check if the remaining data fits into current packet. */
		copy = mtu - skb->len;
		if (copy < length)
			copy = maxfraglen - skb->len;
		if (copy <= 0) {
			char *data;
			unsigned int datalen;
			unsigned int fraglen;
			unsigned int fraggap;
			unsigned int alloclen;
			struct sk_buff *skb_prev;
alloc_new_skb:
			skb_prev = skb;
			if (skb_prev)
				fraggap = skb_prev->len - maxfraglen;
			else
				fraggap = 0;

			/*
			 * If remaining data exceeds the mtu,
			 * we know we need more fragment(s).
			 */
			datalen = length + fraggap;
			if (datalen > mtu - fragheaderlen)
				datalen = maxfraglen - fragheaderlen;
			fraglen = datalen + fragheaderlen;

			if ((flags & MSG_MORE) && 
			    !(rt->u.dst.dev->features&NETIF_F_SG))
				alloclen = mtu;
			else
				alloclen = datalen + fragheaderlen;

			/* The last fragment gets additional space at tail.
			 * Note, with MSG_MORE we overallocate on fragments,
			 * because we have no idea what fragment will be
			 * the last.
			 */
908
			if (datalen == length + fraggap)
Linus Torvalds's avatar
Linus Torvalds committed
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
				alloclen += rt->u.dst.trailer_len;

			if (transhdrlen) {
				skb = sock_alloc_send_skb(sk, 
						alloclen + hh_len + 15,
						(flags & MSG_DONTWAIT), &err);
			} else {
				skb = NULL;
				if (atomic_read(&sk->sk_wmem_alloc) <=
				    2 * sk->sk_sndbuf)
					skb = sock_wmalloc(sk, 
							   alloclen + hh_len + 15, 1,
							   sk->sk_allocation);
				if (unlikely(skb == NULL))
					err = -ENOBUFS;
			}
			if (skb == NULL)
				goto error;

			/*
			 *	Fill in the control structures
			 */
			skb->ip_summed = csummode;
			skb->csum = 0;
			skb_reserve(skb, hh_len);

			/*
			 *	Find where to start putting bytes.
			 */
			data = skb_put(skb, fraglen);
			skb->nh.raw = data + exthdrlen;
			data += fragheaderlen;
			skb->h.raw = data + exthdrlen;

			if (fraggap) {
				skb->csum = skb_copy_and_csum_bits(
					skb_prev, maxfraglen,
					data + transhdrlen, fraggap, 0);
				skb_prev->csum = csum_sub(skb_prev->csum,
							  skb->csum);
				data += fraggap;
950
				pskb_trim_unique(skb_prev, maxfraglen);
Linus Torvalds's avatar
Linus Torvalds committed
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
			}

			copy = datalen - transhdrlen - fraggap;
			if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
				err = -EFAULT;
				kfree_skb(skb);
				goto error;
			}

			offset += copy;
			length -= datalen - fraggap;
			transhdrlen = 0;
			exthdrlen = 0;
			csummode = CHECKSUM_NONE;

			/*
			 * Put the packet on the pending queue.
			 */
			__skb_queue_tail(&sk->sk_write_queue, skb);
			continue;
		}

		if (copy > length)
			copy = length;

		if (!(rt->u.dst.dev->features&NETIF_F_SG)) {
			unsigned int off;

			off = skb->len;
			if (getfrag(from, skb_put(skb, copy), 
					offset, copy, off, skb) < 0) {
				__skb_trim(skb, off);
				err = -EFAULT;
				goto error;
			}
		} else {
			int i = skb_shinfo(skb)->nr_frags;
			skb_frag_t *frag = &skb_shinfo(skb)->frags[i-1];
			struct page *page = sk->sk_sndmsg_page;
			int off = sk->sk_sndmsg_off;
			unsigned int left;

			if (page && (left = PAGE_SIZE - off) > 0) {
				if (copy >= left)
					copy = left;
				if (page != frag->page) {
					if (i == MAX_SKB_FRAGS) {
						err = -EMSGSIZE;
						goto error;
					}