reassembly.c 18.1 KB
Newer Older
L
Linus Torvalds 已提交
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
/*
 *	IPv6 fragment reassembly
 *	Linux INET6 implementation 
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>	
 *
 *	$Id: reassembly.c,v 1.26 2001/03/07 22:00:57 davem Exp $
 *
 *	Based on: net/ipv4/ip_fragment.c
 *
 *	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.
 */

/* 
 *	Fixes:	
 *	Andi Kleen	Make it work with multiple hosts.
 *			More RFC compliance.
 *
 *      Horst von Brand Add missing #include <linux/string.h>
 *	Alexey Kuznetsov	SMP races, threading, cleanup.
 *	Patrick McHardy		LRU queue of frag heads for evictor.
 *	Mitsuru KANDA @USAGI	Register inet6_protocol{}.
 *	David Stevens and
 *	YOSHIFUJI,H. @USAGI	Always remove fragment header to
 *				calculate ICV correctly.
 */
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/jiffies.h>
#include <linux/net.h>
#include <linux/list.h>
#include <linux/netdevice.h>
#include <linux/in6.h>
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/random.h>
#include <linux/jhash.h>

#include <net/sock.h>
#include <net/snmp.h>

#include <net/ipv6.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/rawv6.h>
#include <net/ndisc.h>
#include <net/addrconf.h>

int sysctl_ip6frag_high_thresh = 256*1024;
int sysctl_ip6frag_low_thresh = 192*1024;

int sysctl_ip6frag_time = IPV6_FRAG_TIMEOUT;

struct ip6frag_skb_cb
{
	struct inet6_skb_parm	h;
	int			offset;
};

#define FRAG6_CB(skb)	((struct ip6frag_skb_cb*)((skb)->cb))


/*
 *	Equivalent of ipv4 struct ipq
 */

struct frag_queue
{
76
	struct hlist_node	list;
L
Linus Torvalds 已提交
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
	struct list_head lru_list;		/* lru list member	*/

	__u32			id;		/* fragment id		*/
	struct in6_addr		saddr;
	struct in6_addr		daddr;

	spinlock_t		lock;
	atomic_t		refcnt;
	struct timer_list	timer;		/* expire timer		*/
	struct sk_buff		*fragments;
	int			len;
	int			meat;
	int			iif;
	struct timeval		stamp;
	unsigned int		csum;
	__u8			last_in;	/* has first/last segment arrived? */
#define COMPLETE		4
#define FIRST_IN		2
#define LAST_IN			1
	__u16			nhoffset;
};

/* Hash table. */

#define IP6Q_HASHSZ	64

103
static struct hlist_head ip6_frag_hash[IP6Q_HASHSZ];
L
Linus Torvalds 已提交
104 105 106 107 108 109 110
static DEFINE_RWLOCK(ip6_frag_lock);
static u32 ip6_frag_hash_rnd;
static LIST_HEAD(ip6_frag_lru_list);
int ip6_frag_nqueues = 0;

static __inline__ void __fq_unlink(struct frag_queue *fq)
{
111
	hlist_del(&fq->list);
L
Linus Torvalds 已提交
112 113 114 115 116 117 118 119 120 121 122
	list_del(&fq->lru_list);
	ip6_frag_nqueues--;
}

static __inline__ void fq_unlink(struct frag_queue *fq)
{
	write_lock(&ip6_frag_lock);
	__fq_unlink(fq);
	write_unlock(&ip6_frag_lock);
}

123 124 125 126
/*
 * callers should be careful not to use the hash value outside the ipfrag_lock
 * as doing so could race with ipfrag_hash_rnd being recalculated.
 */
L
Linus Torvalds 已提交
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
static unsigned int ip6qhashfn(u32 id, struct in6_addr *saddr,
			       struct in6_addr *daddr)
{
	u32 a, b, c;

	a = saddr->s6_addr32[0];
	b = saddr->s6_addr32[1];
	c = saddr->s6_addr32[2];

	a += JHASH_GOLDEN_RATIO;
	b += JHASH_GOLDEN_RATIO;
	c += ip6_frag_hash_rnd;
	__jhash_mix(a, b, c);

	a += saddr->s6_addr32[3];
	b += daddr->s6_addr32[0];
	c += daddr->s6_addr32[1];
	__jhash_mix(a, b, c);

	a += daddr->s6_addr32[2];
	b += daddr->s6_addr32[3];
	c += id;
	__jhash_mix(a, b, c);

	return c & (IP6Q_HASHSZ - 1);
}

static struct timer_list ip6_frag_secret_timer;
int sysctl_ip6frag_secret_interval = 10 * 60 * HZ;

static void ip6_frag_secret_rebuild(unsigned long dummy)
{
	unsigned long now = jiffies;
	int i;

	write_lock(&ip6_frag_lock);
	get_random_bytes(&ip6_frag_hash_rnd, sizeof(u32));
	for (i = 0; i < IP6Q_HASHSZ; i++) {
		struct frag_queue *q;
166
		struct hlist_node *p, *n;
L
Linus Torvalds 已提交
167

168
		hlist_for_each_entry_safe(q, p, n, &ip6_frag_hash[i], list) {
L
Linus Torvalds 已提交
169 170 171 172 173
			unsigned int hval = ip6qhashfn(q->id,
						       &q->saddr,
						       &q->daddr);

			if (hval != i) {
174
				hlist_del(&q->list);
L
Linus Torvalds 已提交
175 176

				/* Relink to new hash chain. */
177 178
				hlist_add_head(&q->list,
					       &ip6_frag_hash[hval]);
L
Linus Torvalds 已提交
179

180
			}
L
Linus Torvalds 已提交
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
		}
	}
	write_unlock(&ip6_frag_lock);

	mod_timer(&ip6_frag_secret_timer, now + sysctl_ip6frag_secret_interval);
}

atomic_t ip6_frag_mem = ATOMIC_INIT(0);

/* Memory Tracking Functions. */
static inline void frag_kfree_skb(struct sk_buff *skb, int *work)
{
	if (work)
		*work -= skb->truesize;
	atomic_sub(skb->truesize, &ip6_frag_mem);
	kfree_skb(skb);
}

static inline void frag_free_queue(struct frag_queue *fq, int *work)
{
	if (work)
		*work -= sizeof(struct frag_queue);
	atomic_sub(sizeof(struct frag_queue), &ip6_frag_mem);
	kfree(fq);
}

static inline struct frag_queue *frag_alloc_queue(void)
{
209
	struct frag_queue *fq = kzalloc(sizeof(struct frag_queue), GFP_ATOMIC);
L
Linus Torvalds 已提交
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

	if(!fq)
		return NULL;
	atomic_add(sizeof(struct frag_queue), &ip6_frag_mem);
	return fq;
}

/* Destruction primitives. */

/* Complete destruction of fq. */
static void ip6_frag_destroy(struct frag_queue *fq, int *work)
{
	struct sk_buff *fp;

	BUG_TRAP(fq->last_in&COMPLETE);
	BUG_TRAP(del_timer(&fq->timer) == 0);

	/* Release all fragment data. */
	fp = fq->fragments;
	while (fp) {
		struct sk_buff *xp = fp->next;

		frag_kfree_skb(fp, work);
		fp = xp;
	}

	frag_free_queue(fq, work);
}

static __inline__ void fq_put(struct frag_queue *fq, int *work)
{
	if (atomic_dec_and_test(&fq->refcnt))
		ip6_frag_destroy(fq, work);
}

/* Kill fq entry. It is not destroyed immediately,
 * because caller (and someone more) holds reference count.
 */
static __inline__ void fq_kill(struct frag_queue *fq)
{
	if (del_timer(&fq->timer))
		atomic_dec(&fq->refcnt);

	if (!(fq->last_in & COMPLETE)) {
		fq_unlink(fq);
		atomic_dec(&fq->refcnt);
		fq->last_in |= COMPLETE;
	}
}

static void ip6_evictor(void)
{
	struct frag_queue *fq;
	struct list_head *tmp;
	int work;

	work = atomic_read(&ip6_frag_mem) - sysctl_ip6frag_low_thresh;
	if (work <= 0)
		return;

	while(work > 0) {
		read_lock(&ip6_frag_lock);
		if (list_empty(&ip6_frag_lru_list)) {
			read_unlock(&ip6_frag_lock);
			return;
		}
		tmp = ip6_frag_lru_list.next;
		fq = list_entry(tmp, struct frag_queue, lru_list);
		atomic_inc(&fq->refcnt);
		read_unlock(&ip6_frag_lock);

		spin_lock(&fq->lock);
		if (!(fq->last_in&COMPLETE))
			fq_kill(fq);
		spin_unlock(&fq->lock);

		fq_put(fq, &work);
		IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
	}
}

static void ip6_frag_expire(unsigned long data)
{
	struct frag_queue *fq = (struct frag_queue *) data;
294
	struct net_device *dev;
L
Linus Torvalds 已提交
295 296 297 298 299 300 301 302 303 304 305

	spin_lock(&fq->lock);

	if (fq->last_in & COMPLETE)
		goto out;

	fq_kill(fq);

	IP6_INC_STATS_BH(IPSTATS_MIB_REASMTIMEOUT);
	IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);

306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321
	/* Don't send error if the first segment did not arrive. */
	if (!(fq->last_in&FIRST_IN) || !fq->fragments)
		goto out;

	dev = dev_get_by_index(fq->iif);
	if (!dev)
		goto out;

	/*
	   But use as source device on which LAST ARRIVED
	   segment was received. And do not use fq->dev
	   pointer directly, device might already disappeared.
	 */
	fq->fragments->dev = dev;
	icmpv6_send(fq->fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0, dev);
	dev_put(dev);
L
Linus Torvalds 已提交
322 323 324 325 326 327 328 329
out:
	spin_unlock(&fq->lock);
	fq_put(fq, NULL);
}

/* Creation primitives. */


330
static struct frag_queue *ip6_frag_intern(struct frag_queue *fq_in)
L
Linus Torvalds 已提交
331 332
{
	struct frag_queue *fq;
333
	unsigned int hash;
334 335 336
#ifdef CONFIG_SMP
	struct hlist_node *n;
#endif
L
Linus Torvalds 已提交
337 338

	write_lock(&ip6_frag_lock);
339
	hash = ip6qhashfn(fq_in->id, &fq_in->saddr, &fq_in->daddr);
L
Linus Torvalds 已提交
340
#ifdef CONFIG_SMP
341
	hlist_for_each_entry(fq, n, &ip6_frag_hash[hash], list) {
L
Linus Torvalds 已提交
342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358
		if (fq->id == fq_in->id && 
		    ipv6_addr_equal(&fq_in->saddr, &fq->saddr) &&
		    ipv6_addr_equal(&fq_in->daddr, &fq->daddr)) {
			atomic_inc(&fq->refcnt);
			write_unlock(&ip6_frag_lock);
			fq_in->last_in |= COMPLETE;
			fq_put(fq_in, NULL);
			return fq;
		}
	}
#endif
	fq = fq_in;

	if (!mod_timer(&fq->timer, jiffies + sysctl_ip6frag_time))
		atomic_inc(&fq->refcnt);

	atomic_inc(&fq->refcnt);
359
	hlist_add_head(&fq->list, &ip6_frag_hash[hash]);
L
Linus Torvalds 已提交
360 361 362 363 364 365 366 367 368
	INIT_LIST_HEAD(&fq->lru_list);
	list_add_tail(&fq->lru_list, &ip6_frag_lru_list);
	ip6_frag_nqueues++;
	write_unlock(&ip6_frag_lock);
	return fq;
}


static struct frag_queue *
369
ip6_frag_create(u32 id, struct in6_addr *src, struct in6_addr *dst)
L
Linus Torvalds 已提交
370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385
{
	struct frag_queue *fq;

	if ((fq = frag_alloc_queue()) == NULL)
		goto oom;

	fq->id = id;
	ipv6_addr_copy(&fq->saddr, src);
	ipv6_addr_copy(&fq->daddr, dst);

	init_timer(&fq->timer);
	fq->timer.function = ip6_frag_expire;
	fq->timer.data = (long) fq;
	spin_lock_init(&fq->lock);
	atomic_set(&fq->refcnt, 1);

386
	return ip6_frag_intern(fq);
L
Linus Torvalds 已提交
387 388 389 390 391 392 393 394 395 396

oom:
	IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
	return NULL;
}

static __inline__ struct frag_queue *
fq_find(u32 id, struct in6_addr *src, struct in6_addr *dst)
{
	struct frag_queue *fq;
397
	struct hlist_node *n;
398
	unsigned int hash;
L
Linus Torvalds 已提交
399 400

	read_lock(&ip6_frag_lock);
401
	hash = ip6qhashfn(id, src, dst);
402
	hlist_for_each_entry(fq, n, &ip6_frag_hash[hash], list) {
L
Linus Torvalds 已提交
403 404 405 406 407 408 409 410 411 412
		if (fq->id == id && 
		    ipv6_addr_equal(src, &fq->saddr) &&
		    ipv6_addr_equal(dst, &fq->daddr)) {
			atomic_inc(&fq->refcnt);
			read_unlock(&ip6_frag_lock);
			return fq;
		}
	}
	read_unlock(&ip6_frag_lock);

413
	return ip6_frag_create(id, src, dst);
L
Linus Torvalds 已提交
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
}


static void ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, 
			   struct frag_hdr *fhdr, int nhoff)
{
	struct sk_buff *prev, *next;
	int offset, end;

	if (fq->last_in & COMPLETE)
		goto err;

	offset = ntohs(fhdr->frag_off) & ~0x7;
	end = offset + (ntohs(skb->nh.ipv6h->payload_len) -
			((u8 *) (fhdr + 1) - (u8 *) (skb->nh.ipv6h + 1)));

	if ((unsigned int)end > IPV6_MAXPLEN) {
		IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
 		icmpv6_param_prob(skb,ICMPV6_HDR_FIELD, (u8*)&fhdr->frag_off - skb->nh.raw);
 		return;
	}

 	if (skb->ip_summed == CHECKSUM_HW)
 		skb->csum = csum_sub(skb->csum,
 				     csum_partial(skb->nh.raw, (u8*)(fhdr+1)-skb->nh.raw, 0));

	/* Is this the final fragment? */
	if (!(fhdr->frag_off & htons(IP6_MF))) {
		/* If we already have some bits beyond end
		 * or have different end, the segment is corrupted.
		 */
		if (end < fq->len ||
		    ((fq->last_in & LAST_IN) && end != fq->len))
			goto err;
		fq->last_in |= LAST_IN;
		fq->len = end;
	} else {
		/* Check if the fragment is rounded to 8 bytes.
		 * Required by the RFC.
		 */
		if (end & 0x7) {
			/* RFC2460 says always send parameter problem in
			 * this case. -DaveM
			 */
			IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
			icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, 
					  offsetof(struct ipv6hdr, payload_len));
			return;
		}
		if (end > fq->len) {
			/* Some bits beyond end -> corruption. */
			if (fq->last_in & LAST_IN)
				goto err;
			fq->len = end;
		}
	}

	if (end == offset)
		goto err;

	/* Point into the IP datagram 'data' part. */
	if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data))
		goto err;
477 478 479
	
	if (pskb_trim_rcsum(skb, end - offset))
		goto err;
L
Linus Torvalds 已提交
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

	/* Find out which fragments are in front and at the back of us
	 * in the chain of fragments so far.  We must know where to put
	 * this fragment, right?
	 */
	prev = NULL;
	for(next = fq->fragments; next != NULL; next = next->next) {
		if (FRAG6_CB(next)->offset >= offset)
			break;	/* bingo! */
		prev = next;
	}

	/* We found where to put this one.  Check for overlap with
	 * preceding fragment, and, if needed, align things so that
	 * any overlaps are eliminated.
	 */
	if (prev) {
		int i = (FRAG6_CB(prev)->offset + prev->len) - offset;

		if (i > 0) {
			offset += i;
			if (end <= offset)
				goto err;
			if (!pskb_pull(skb, i))
				goto err;
			if (skb->ip_summed != CHECKSUM_UNNECESSARY)
				skb->ip_summed = CHECKSUM_NONE;
		}
	}

	/* Look for overlap with succeeding segments.
	 * If we can merge fragments, do it.
	 */
	while (next && FRAG6_CB(next)->offset < end) {
		int i = end - FRAG6_CB(next)->offset; /* overlap is 'i' bytes */

		if (i < next->len) {
			/* Eat head of the next overlapped fragment
			 * and leave the loop. The next ones cannot overlap.
			 */
			if (!pskb_pull(next, i))
				goto err;
			FRAG6_CB(next)->offset += i;	/* next fragment */
			fq->meat -= i;
			if (next->ip_summed != CHECKSUM_UNNECESSARY)
				next->ip_summed = CHECKSUM_NONE;
			break;
		} else {
			struct sk_buff *free_it = next;

			/* Old fragment is completely overridden with
			 * new one drop it.
			 */
			next = next->next;

			if (prev)
				prev->next = next;
			else
				fq->fragments = next;

			fq->meat -= free_it->len;
			frag_kfree_skb(free_it, NULL);
		}
	}

	FRAG6_CB(skb)->offset = offset;

	/* Insert this fragment in the chain of fragments. */
	skb->next = next;
	if (prev)
		prev->next = skb;
	else
		fq->fragments = skb;

	if (skb->dev)
		fq->iif = skb->dev->ifindex;
	skb->dev = NULL;
557
	skb_get_timestamp(skb, &fq->stamp);
L
Linus Torvalds 已提交
558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657
	fq->meat += skb->len;
	atomic_add(skb->truesize, &ip6_frag_mem);

	/* The first fragment.
	 * nhoffset is obtained from the first fragment, of course.
	 */
	if (offset == 0) {
		fq->nhoffset = nhoff;
		fq->last_in |= FIRST_IN;
	}
	write_lock(&ip6_frag_lock);
	list_move_tail(&fq->lru_list, &ip6_frag_lru_list);
	write_unlock(&ip6_frag_lock);
	return;

err:
	IP6_INC_STATS(IPSTATS_MIB_REASMFAILS);
	kfree_skb(skb);
}

/*
 *	Check if this packet is complete.
 *	Returns NULL on failure by any reason, and pointer
 *	to current nexthdr field in reassembled frame.
 *
 *	It is called with locked fq, and caller must check that
 *	queue is eligible for reassembly i.e. it is not COMPLETE,
 *	the last and the first frames arrived and all the bits are here.
 */
static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff **skb_in,
			  struct net_device *dev)
{
	struct sk_buff *fp, *head = fq->fragments;
	int    payload_len;
	unsigned int nhoff;

	fq_kill(fq);

	BUG_TRAP(head != NULL);
	BUG_TRAP(FRAG6_CB(head)->offset == 0);

	/* Unfragmented part is taken from the first segment. */
	payload_len = (head->data - head->nh.raw) - sizeof(struct ipv6hdr) + fq->len - sizeof(struct frag_hdr);
	if (payload_len > IPV6_MAXPLEN)
		goto out_oversize;

	/* Head of list must not be cloned. */
	if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC))
		goto out_oom;

	/* If the first fragment is fragmented itself, we split
	 * it to two chunks: the first with data and paged part
	 * and the second, holding only fragments. */
	if (skb_shinfo(head)->frag_list) {
		struct sk_buff *clone;
		int i, plen = 0;

		if ((clone = alloc_skb(0, GFP_ATOMIC)) == NULL)
			goto out_oom;
		clone->next = head->next;
		head->next = clone;
		skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
		skb_shinfo(head)->frag_list = NULL;
		for (i=0; i<skb_shinfo(head)->nr_frags; i++)
			plen += skb_shinfo(head)->frags[i].size;
		clone->len = clone->data_len = head->data_len - plen;
		head->data_len -= clone->len;
		head->len -= clone->len;
		clone->csum = 0;
		clone->ip_summed = head->ip_summed;
		atomic_add(clone->truesize, &ip6_frag_mem);
	}

	/* We have to remove fragment header from datagram and to relocate
	 * header in order to calculate ICV correctly. */
	nhoff = fq->nhoffset;
	head->nh.raw[nhoff] = head->h.raw[0];
	memmove(head->head + sizeof(struct frag_hdr), head->head, 
		(head->data - head->head) - sizeof(struct frag_hdr));
	head->mac.raw += sizeof(struct frag_hdr);
	head->nh.raw += sizeof(struct frag_hdr);

	skb_shinfo(head)->frag_list = head->next;
	head->h.raw = head->data;
	skb_push(head, head->data - head->nh.raw);
	atomic_sub(head->truesize, &ip6_frag_mem);

	for (fp=head->next; fp; fp = fp->next) {
		head->data_len += fp->len;
		head->len += fp->len;
		if (head->ip_summed != fp->ip_summed)
			head->ip_summed = CHECKSUM_NONE;
		else if (head->ip_summed == CHECKSUM_HW)
			head->csum = csum_add(head->csum, fp->csum);
		head->truesize += fp->truesize;
		atomic_sub(fp->truesize, &ip6_frag_mem);
	}

	head->next = NULL;
	head->dev = dev;
658
	skb_set_timestamp(head, &fq->stamp);
L
Linus Torvalds 已提交
659
	head->nh.ipv6h->payload_len = htons(payload_len);
660
	IP6CB(head)->nhoff = nhoff;
L
Linus Torvalds 已提交
661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683

	*skb_in = head;

	/* Yes, and fold redundant checksum back. 8) */
	if (head->ip_summed == CHECKSUM_HW)
		head->csum = csum_partial(head->nh.raw, head->h.raw-head->nh.raw, head->csum);

	IP6_INC_STATS_BH(IPSTATS_MIB_REASMOKS);
	fq->fragments = NULL;
	return 1;

out_oversize:
	if (net_ratelimit())
		printk(KERN_DEBUG "ip6_frag_reasm: payload len = %d\n", payload_len);
	goto out_fail;
out_oom:
	if (net_ratelimit())
		printk(KERN_DEBUG "ip6_frag_reasm: no memory for reassembly\n");
out_fail:
	IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
	return -1;
}

684
static int ipv6_frag_rcv(struct sk_buff **skbp)
L
Linus Torvalds 已提交
685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715
{
	struct sk_buff *skb = *skbp; 
	struct net_device *dev = skb->dev;
	struct frag_hdr *fhdr;
	struct frag_queue *fq;
	struct ipv6hdr *hdr;

	hdr = skb->nh.ipv6h;

	IP6_INC_STATS_BH(IPSTATS_MIB_REASMREQDS);

	/* Jumbo payload inhibits frag. header */
	if (hdr->payload_len==0) {
		IP6_INC_STATS(IPSTATS_MIB_INHDRERRORS);
		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb->h.raw-skb->nh.raw);
		return -1;
	}
	if (!pskb_may_pull(skb, (skb->h.raw-skb->data)+sizeof(struct frag_hdr))) {
		IP6_INC_STATS(IPSTATS_MIB_INHDRERRORS);
		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb->h.raw-skb->nh.raw);
		return -1;
	}

	hdr = skb->nh.ipv6h;
	fhdr = (struct frag_hdr *)skb->h.raw;

	if (!(fhdr->frag_off & htons(0xFFF9))) {
		/* It is not a fragmented frame */
		skb->h.raw += sizeof(struct frag_hdr);
		IP6_INC_STATS_BH(IPSTATS_MIB_REASMOKS);

716
		IP6CB(skb)->nhoff = (u8*)fhdr - skb->nh.raw;
L
Linus Torvalds 已提交
717 718 719 720 721 722 723 724 725 726 727
		return 1;
	}

	if (atomic_read(&ip6_frag_mem) > sysctl_ip6frag_high_thresh)
		ip6_evictor();

	if ((fq = fq_find(fhdr->identification, &hdr->saddr, &hdr->daddr)) != NULL) {
		int ret = -1;

		spin_lock(&fq->lock);

728
		ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);
L
Linus Torvalds 已提交
729 730 731

		if (fq->last_in == (FIRST_IN|LAST_IN) &&
		    fq->meat == fq->len)
732
			ret = ip6_frag_reasm(fq, skbp, dev);
L
Linus Torvalds 已提交
733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762

		spin_unlock(&fq->lock);
		fq_put(fq, NULL);
		return ret;
	}

	IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
	kfree_skb(skb);
	return -1;
}

static struct inet6_protocol frag_protocol =
{
	.handler	=	ipv6_frag_rcv,
	.flags		=	INET6_PROTO_NOPOLICY,
};

void __init ipv6_frag_init(void)
{
	if (inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT) < 0)
		printk(KERN_ERR "ipv6_frag_init: Could not register protocol\n");

	ip6_frag_hash_rnd = (u32) ((num_physpages ^ (num_physpages>>7)) ^
				   (jiffies ^ (jiffies >> 6)));

	init_timer(&ip6_frag_secret_timer);
	ip6_frag_secret_timer.function = ip6_frag_secret_rebuild;
	ip6_frag_secret_timer.expires = jiffies + sysctl_ip6frag_secret_interval;
	add_timer(&ip6_frag_secret_timer);
}