skbuff.c 42.4 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
/*
 *	Routines having to do with the 'struct sk_buff' memory handlers.
 *
 *	Authors:	Alan Cox <iiitac@pyr.swan.ac.uk>
 *			Florian La Roche <rzsfl@rz.uni-sb.de>
 *
 *	Version:	$Id: skbuff.c,v 1.90 2001/11/07 05:56:19 davem Exp $
 *
 *	Fixes:
 *		Alan Cox	:	Fixed the worst of the load
 *					balancer bugs.
 *		Dave Platt	:	Interrupt stacking fix.
 *	Richard Kooijman	:	Timestamp fixes.
 *		Alan Cox	:	Changed buffer format.
 *		Alan Cox	:	destructor hook for AF_UNIX etc.
 *		Linus Torvalds	:	Better skb_clone.
 *		Alan Cox	:	Added skb_copy.
 *		Alan Cox	:	Added all the changed routines Linus
 *					only put in the headers
 *		Ray VanTassle	:	Fixed --skb->lock in free
 *		Alan Cox	:	skb_copy copy arp field
 *		Andi Kleen	:	slabified it.
 *		Robert Olsson	:	Removed skb_head_pool
 *
 *	NOTE:
 *		The __skb_ routines should be called with interrupts
 *	disabled, or you better be *real* sure that the operation is atomic
 *	with respect to whatever list is being frobbed (e.g. via lock_sock()
 *	or via disabling bottom half handlers, etc).
 *
 *	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.
 */

/*
 *	The functions in this file will not compile correctly with gcc 2.4.x
 */

#include <linux/config.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/slab.h>
#include <linux/netdevice.h>
#ifdef CONFIG_NET_CLS_ACT
#include <net/pkt_sched.h>
#endif
#include <linux/string.h>
#include <linux/skbuff.h>
#include <linux/cache.h>
#include <linux/rtnetlink.h>
#include <linux/init.h>
#include <linux/highmem.h>

#include <net/protocol.h>
#include <net/dst.h>
#include <net/sock.h>
#include <net/checksum.h>
#include <net/xfrm.h>

#include <asm/uaccess.h>
#include <asm/system.h>

static kmem_cache_t *skbuff_head_cache;
72
static kmem_cache_t *skbuff_fclone_cache;
L
Linus Torvalds 已提交
73

74 75
struct timeval __read_mostly skb_tv_base;

L
Linus Torvalds 已提交
76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91
/*
 *	Keep out-of-line to prevent kernel bloat.
 *	__builtin_return_address is not used because it is not always
 *	reliable.
 */

/**
 *	skb_over_panic	- 	private function
 *	@skb: buffer
 *	@sz: size
 *	@here: address
 *
 *	Out of line support code for skb_put(). Not user callable.
 */
void skb_over_panic(struct sk_buff *skb, int sz, void *here)
{
92 93 94 95
	printk(KERN_EMERG "skb_over_panic: text:%p len:%d put:%d head:%p "
	                  "data:%p tail:%p end:%p dev:%s\n",
	       here, skb->len, sz, skb->head, skb->data, skb->tail, skb->end,
	       skb->dev ? skb->dev->name : "<NULL>");
L
Linus Torvalds 已提交
96 97 98 99 100 101 102 103 104 105 106 107 108 109
	BUG();
}

/**
 *	skb_under_panic	- 	private function
 *	@skb: buffer
 *	@sz: size
 *	@here: address
 *
 *	Out of line support code for skb_push(). Not user callable.
 */

void skb_under_panic(struct sk_buff *skb, int sz, void *here)
{
110 111 112 113
	printk(KERN_EMERG "skb_under_panic: text:%p len:%d put:%d head:%p "
	                  "data:%p tail:%p end:%p dev:%s\n",
	       here, skb->len, sz, skb->head, skb->data, skb->tail, skb->end,
	       skb->dev ? skb->dev->name : "<NULL>");
L
Linus Torvalds 已提交
114 115 116 117 118 119 120 121 122 123
	BUG();
}

/* 	Allocate a new skbuff. We do this ourselves so we can fill in a few
 *	'private' fields and also do memory statistics to find all the
 *	[BEEP] leaks.
 *
 */

/**
124
 *	__alloc_skb	-	allocate a network buffer
L
Linus Torvalds 已提交
125 126 127 128 129 130 131 132 133 134
 *	@size: size to allocate
 *	@gfp_mask: allocation mask
 *
 *	Allocate a new &sk_buff. The returned buffer has no headroom and a
 *	tail room of size bytes. The object has a reference count of one.
 *	The return is the buffer. On a failure the return is %NULL.
 *
 *	Buffers may only be allocated from interrupts using a @gfp_mask of
 *	%GFP_ATOMIC.
 */
135 136
struct sk_buff *__alloc_skb(unsigned int size, unsigned int __nocast gfp_mask,
			    int fclone)
L
Linus Torvalds 已提交
137 138 139 140 141
{
	struct sk_buff *skb;
	u8 *data;

	/* Get the HEAD */
142 143 144 145 146 147 148
	if (fclone)
		skb = kmem_cache_alloc(skbuff_fclone_cache,
				       gfp_mask & ~__GFP_DMA);
	else
		skb = kmem_cache_alloc(skbuff_head_cache,
				       gfp_mask & ~__GFP_DMA);

L
Linus Torvalds 已提交
149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164
	if (!skb)
		goto out;

	/* Get the DATA. Size must match skb_add_mtu(). */
	size = SKB_DATA_ALIGN(size);
	data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask);
	if (!data)
		goto nodata;

	memset(skb, 0, offsetof(struct sk_buff, truesize));
	skb->truesize = size + sizeof(struct sk_buff);
	atomic_set(&skb->users, 1);
	skb->head = data;
	skb->data = data;
	skb->tail = data;
	skb->end  = data + size;
165 166 167
	if (fclone) {
		struct sk_buff *child = skb + 1;
		atomic_t *fclone_ref = (atomic_t *) (child + 1);
L
Linus Torvalds 已提交
168

169 170 171 172 173
		skb->fclone = SKB_FCLONE_ORIG;
		atomic_set(fclone_ref, 1);

		child->fclone = SKB_FCLONE_UNAVAILABLE;
	}
L
Linus Torvalds 已提交
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
	atomic_set(&(skb_shinfo(skb)->dataref), 1);
	skb_shinfo(skb)->nr_frags  = 0;
	skb_shinfo(skb)->tso_size = 0;
	skb_shinfo(skb)->tso_segs = 0;
	skb_shinfo(skb)->frag_list = NULL;
out:
	return skb;
nodata:
	kmem_cache_free(skbuff_head_cache, skb);
	skb = NULL;
	goto out;
}

/**
 *	alloc_skb_from_cache	-	allocate a network buffer
 *	@cp: kmem_cache from which to allocate the data area
 *           (object size must be big enough for @size bytes + skb overheads)
 *	@size: size to allocate
 *	@gfp_mask: allocation mask
 *
 *	Allocate a new &sk_buff. The returned buffer has no headroom and
 *	tail room of size bytes. The object has a reference count of one.
 *	The return is the buffer. On a failure the return is %NULL.
 *
 *	Buffers may only be allocated from interrupts using a @gfp_mask of
 *	%GFP_ATOMIC.
 */
struct sk_buff *alloc_skb_from_cache(kmem_cache_t *cp,
V
Victor Fusco 已提交
202 203
				     unsigned int size,
				     unsigned int __nocast gfp_mask)
L
Linus Torvalds 已提交
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
{
	struct sk_buff *skb;
	u8 *data;

	/* Get the HEAD */
	skb = kmem_cache_alloc(skbuff_head_cache,
			       gfp_mask & ~__GFP_DMA);
	if (!skb)
		goto out;

	/* Get the DATA. */
	size = SKB_DATA_ALIGN(size);
	data = kmem_cache_alloc(cp, gfp_mask);
	if (!data)
		goto nodata;

	memset(skb, 0, offsetof(struct sk_buff, truesize));
	skb->truesize = size + sizeof(struct sk_buff);
	atomic_set(&skb->users, 1);
	skb->head = data;
	skb->data = data;
	skb->tail = data;
	skb->end  = data + size;

	atomic_set(&(skb_shinfo(skb)->dataref), 1);
	skb_shinfo(skb)->nr_frags  = 0;
	skb_shinfo(skb)->tso_size = 0;
	skb_shinfo(skb)->tso_segs = 0;
	skb_shinfo(skb)->frag_list = NULL;
out:
	return skb;
nodata:
	kmem_cache_free(skbuff_head_cache, skb);
	skb = NULL;
	goto out;
}


static void skb_drop_fraglist(struct sk_buff *skb)
{
	struct sk_buff *list = skb_shinfo(skb)->frag_list;

	skb_shinfo(skb)->frag_list = NULL;

	do {
		struct sk_buff *this = list;
		list = list->next;
		kfree_skb(this);
	} while (list);
}

static void skb_clone_fraglist(struct sk_buff *skb)
{
	struct sk_buff *list;

	for (list = skb_shinfo(skb)->frag_list; list; list = list->next)
		skb_get(list);
}

void skb_release_data(struct sk_buff *skb)
{
	if (!skb->cloned ||
	    !atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1,
			       &skb_shinfo(skb)->dataref)) {
		if (skb_shinfo(skb)->nr_frags) {
			int i;
			for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
				put_page(skb_shinfo(skb)->frags[i].page);
		}

		if (skb_shinfo(skb)->frag_list)
			skb_drop_fraglist(skb);

		kfree(skb->head);
	}
}

/*
 *	Free an skbuff by memory without cleaning the state.
 */
void kfree_skbmem(struct sk_buff *skb)
{
286 287 288
	struct sk_buff *other;
	atomic_t *fclone_ref;

L
Linus Torvalds 已提交
289
	skb_release_data(skb);
290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313
	switch (skb->fclone) {
	case SKB_FCLONE_UNAVAILABLE:
		kmem_cache_free(skbuff_head_cache, skb);
		break;

	case SKB_FCLONE_ORIG:
		fclone_ref = (atomic_t *) (skb + 2);
		if (atomic_dec_and_test(fclone_ref))
			kmem_cache_free(skbuff_fclone_cache, skb);
		break;

	case SKB_FCLONE_CLONE:
		fclone_ref = (atomic_t *) (skb + 1);
		other = skb - 1;

		/* The clone portion is available for
		 * fast-cloning again.
		 */
		skb->fclone = SKB_FCLONE_UNAVAILABLE;

		if (atomic_dec_and_test(fclone_ref))
			kmem_cache_free(skbuff_fclone_cache, other);
		break;
	};
L
Linus Torvalds 已提交
314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330
}

/**
 *	__kfree_skb - private function
 *	@skb: buffer
 *
 *	Free an sk_buff. Release anything attached to the buffer.
 *	Clean the state. This is an internal helper function. Users should
 *	always call kfree_skb
 */

void __kfree_skb(struct sk_buff *skb)
{
	dst_release(skb->dst);
#ifdef CONFIG_XFRM
	secpath_put(skb->sp);
#endif
331 332
	if (skb->destructor) {
		WARN_ON(in_irq());
L
Linus Torvalds 已提交
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
		skb->destructor(skb);
	}
#ifdef CONFIG_NETFILTER
	nf_conntrack_put(skb->nfct);
#ifdef CONFIG_BRIDGE_NETFILTER
	nf_bridge_put(skb->nf_bridge);
#endif
#endif
/* XXX: IS this still necessary? - JHS */
#ifdef CONFIG_NET_SCHED
	skb->tc_index = 0;
#ifdef CONFIG_NET_CLS_ACT
	skb->tc_verd = 0;
#endif
#endif

	kfree_skbmem(skb);
}

/**
 *	skb_clone	-	duplicate an sk_buff
 *	@skb: buffer to clone
 *	@gfp_mask: allocation priority
 *
 *	Duplicate an &sk_buff. The new one is not owned by a socket. Both
 *	copies share the same packet data but not structure. The new
 *	buffer has a reference count of 1. If the allocation fails the
 *	function returns %NULL otherwise the new buffer is returned.
 *
 *	If this function is called from an interrupt gfp_mask() must be
 *	%GFP_ATOMIC.
 */

V
Victor Fusco 已提交
366
struct sk_buff *skb_clone(struct sk_buff *skb, unsigned int __nocast gfp_mask)
L
Linus Torvalds 已提交
367
{
368 369 370 371 372 373 374 375 376 377 378 379 380 381
	struct sk_buff *n;

	n = skb + 1;
	if (skb->fclone == SKB_FCLONE_ORIG &&
	    n->fclone == SKB_FCLONE_UNAVAILABLE) {
		atomic_t *fclone_ref = (atomic_t *) (n + 1);
		n->fclone = SKB_FCLONE_CLONE;
		atomic_inc(fclone_ref);
	} else {
		n = kmem_cache_alloc(skbuff_head_cache, gfp_mask);
		if (!n)
			return NULL;
		n->fclone = SKB_FCLONE_UNAVAILABLE;
	}
L
Linus Torvalds 已提交
382 383 384 385 386

#define C(x) n->x = skb->x

	n->next = n->prev = NULL;
	n->sk = NULL;
387
	C(tstamp);
L
Linus Torvalds 已提交
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
	C(dev);
	C(h);
	C(nh);
	C(mac);
	C(dst);
	dst_clone(skb->dst);
	C(sp);
#ifdef CONFIG_INET
	secpath_get(skb->sp);
#endif
	memcpy(n->cb, skb->cb, sizeof(skb->cb));
	C(len);
	C(data_len);
	C(csum);
	C(local_df);
	n->cloned = 1;
	n->nohdr = 0;
	C(pkt_type);
	C(ip_summed);
	C(priority);
	C(protocol);
	n->destructor = NULL;
#ifdef CONFIG_NETFILTER
	C(nfmark);
	C(nfct);
	nf_conntrack_get(skb->nfct);
	C(nfctinfo);
#ifdef CONFIG_BRIDGE_NETFILTER
	C(nf_bridge);
	nf_bridge_get(skb->nf_bridge);
#endif
#endif /*CONFIG_NETFILTER*/
#ifdef CONFIG_NET_SCHED
	C(tc_index);
#ifdef CONFIG_NET_CLS_ACT
	n->tc_verd = SET_TC_VERD(skb->tc_verd,0);
424 425
	n->tc_verd = CLR_TC_OK2MUNGE(n->tc_verd);
	n->tc_verd = CLR_TC_MUNGED(n->tc_verd);
L
Linus Torvalds 已提交
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
	C(input_dev);
#endif

#endif
	C(truesize);
	atomic_set(&n->users, 1);
	C(head);
	C(data);
	C(tail);
	C(end);

	atomic_inc(&(skb_shinfo(skb)->dataref));
	skb->cloned = 1;

	return n;
}

static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
{
	/*
	 *	Shift between the two data areas in bytes
	 */
	unsigned long offset = new->data - old->data;

	new->sk		= NULL;
	new->dev	= old->dev;
	new->priority	= old->priority;
	new->protocol	= old->protocol;
	new->dst	= dst_clone(old->dst);
#ifdef CONFIG_INET
	new->sp		= secpath_get(old->sp);
#endif
	new->h.raw	= old->h.raw + offset;
	new->nh.raw	= old->nh.raw + offset;
	new->mac.raw	= old->mac.raw + offset;
	memcpy(new->cb, old->cb, sizeof(old->cb));
	new->local_df	= old->local_df;
463
	new->fclone	= SKB_FCLONE_UNAVAILABLE;
L
Linus Torvalds 已提交
464
	new->pkt_type	= old->pkt_type;
465
	new->tstamp	= old->tstamp;
L
Linus Torvalds 已提交
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
	new->destructor = NULL;
#ifdef CONFIG_NETFILTER
	new->nfmark	= old->nfmark;
	new->nfct	= old->nfct;
	nf_conntrack_get(old->nfct);
	new->nfctinfo	= old->nfctinfo;
#ifdef CONFIG_BRIDGE_NETFILTER
	new->nf_bridge	= old->nf_bridge;
	nf_bridge_get(old->nf_bridge);
#endif
#endif
#ifdef CONFIG_NET_SCHED
#ifdef CONFIG_NET_CLS_ACT
	new->tc_verd = old->tc_verd;
#endif
	new->tc_index	= old->tc_index;
#endif
	atomic_set(&new->users, 1);
	skb_shinfo(new)->tso_size = skb_shinfo(old)->tso_size;
	skb_shinfo(new)->tso_segs = skb_shinfo(old)->tso_segs;
}

/**
 *	skb_copy	-	create private copy of an sk_buff
 *	@skb: buffer to copy
 *	@gfp_mask: allocation priority
 *
 *	Make a copy of both an &sk_buff and its data. This is used when the
 *	caller wishes to modify the data and needs a private copy of the
 *	data to alter. Returns %NULL on failure or the pointer to the buffer
 *	on success. The returned buffer has a reference count of 1.
 *
 *	As by-product this function converts non-linear &sk_buff to linear
 *	one, so that &sk_buff becomes completely private and caller is allowed
 *	to modify all the data of returned buffer. This means that this
 *	function is not recommended for use in circumstances when only
 *	header is going to be modified. Use pskb_copy() instead.
 */

V
Victor Fusco 已提交
505
struct sk_buff *skb_copy(const struct sk_buff *skb, unsigned int __nocast gfp_mask)
L
Linus Torvalds 已提交
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
{
	int headerlen = skb->data - skb->head;
	/*
	 *	Allocate the copy buffer
	 */
	struct sk_buff *n = alloc_skb(skb->end - skb->head + skb->data_len,
				      gfp_mask);
	if (!n)
		return NULL;

	/* Set the data pointer */
	skb_reserve(n, headerlen);
	/* Set the tail pointer and length */
	skb_put(n, skb->len);
	n->csum	     = skb->csum;
	n->ip_summed = skb->ip_summed;

	if (skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len))
		BUG();

	copy_skb_header(n, skb);
	return n;
}


/**
 *	pskb_copy	-	create copy of an sk_buff with private head.
 *	@skb: buffer to copy
 *	@gfp_mask: allocation priority
 *
 *	Make a copy of both an &sk_buff and part of its data, located
 *	in header. Fragmented data remain shared. This is used when
 *	the caller wishes to modify only header of &sk_buff and needs
 *	private copy of the header to alter. Returns %NULL on failure
 *	or the pointer to the buffer on success.
 *	The returned buffer has a reference count of 1.
 */

V
Victor Fusco 已提交
544
struct sk_buff *pskb_copy(struct sk_buff *skb, unsigned int __nocast gfp_mask)
L
Linus Torvalds 已提交
545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601
{
	/*
	 *	Allocate the copy buffer
	 */
	struct sk_buff *n = alloc_skb(skb->end - skb->head, gfp_mask);

	if (!n)
		goto out;

	/* Set the data pointer */
	skb_reserve(n, skb->data - skb->head);
	/* Set the tail pointer and length */
	skb_put(n, skb_headlen(skb));
	/* Copy the bytes */
	memcpy(n->data, skb->data, n->len);
	n->csum	     = skb->csum;
	n->ip_summed = skb->ip_summed;

	n->data_len  = skb->data_len;
	n->len	     = skb->len;

	if (skb_shinfo(skb)->nr_frags) {
		int i;

		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
			skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i];
			get_page(skb_shinfo(n)->frags[i].page);
		}
		skb_shinfo(n)->nr_frags = i;
	}

	if (skb_shinfo(skb)->frag_list) {
		skb_shinfo(n)->frag_list = skb_shinfo(skb)->frag_list;
		skb_clone_fraglist(n);
	}

	copy_skb_header(n, skb);
out:
	return n;
}

/**
 *	pskb_expand_head - reallocate header of &sk_buff
 *	@skb: buffer to reallocate
 *	@nhead: room to add at head
 *	@ntail: room to add at tail
 *	@gfp_mask: allocation priority
 *
 *	Expands (or creates identical copy, if &nhead and &ntail are zero)
 *	header of skb. &sk_buff itself is not changed. &sk_buff MUST have
 *	reference count of 1. Returns zero in the case of success or error,
 *	if expansion failed. In the last case, &sk_buff is not changed.
 *
 *	All the pointers pointing into skb header may change and must be
 *	reloaded after call to this function.
 */

V
Victor Fusco 已提交
602 603
int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
		     unsigned int __nocast gfp_mask)
L
Linus Torvalds 已提交
604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692
{
	int i;
	u8 *data;
	int size = nhead + (skb->end - skb->head) + ntail;
	long off;

	if (skb_shared(skb))
		BUG();

	size = SKB_DATA_ALIGN(size);

	data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask);
	if (!data)
		goto nodata;

	/* Copy only real data... and, alas, header. This should be
	 * optimized for the cases when header is void. */
	memcpy(data + nhead, skb->head, skb->tail - skb->head);
	memcpy(data + size, skb->end, sizeof(struct skb_shared_info));

	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
		get_page(skb_shinfo(skb)->frags[i].page);

	if (skb_shinfo(skb)->frag_list)
		skb_clone_fraglist(skb);

	skb_release_data(skb);

	off = (data + nhead) - skb->head;

	skb->head     = data;
	skb->end      = data + size;
	skb->data    += off;
	skb->tail    += off;
	skb->mac.raw += off;
	skb->h.raw   += off;
	skb->nh.raw  += off;
	skb->cloned   = 0;
	skb->nohdr    = 0;
	atomic_set(&skb_shinfo(skb)->dataref, 1);
	return 0;

nodata:
	return -ENOMEM;
}

/* Make private copy of skb with writable head and some headroom */

struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom)
{
	struct sk_buff *skb2;
	int delta = headroom - skb_headroom(skb);

	if (delta <= 0)
		skb2 = pskb_copy(skb, GFP_ATOMIC);
	else {
		skb2 = skb_clone(skb, GFP_ATOMIC);
		if (skb2 && pskb_expand_head(skb2, SKB_DATA_ALIGN(delta), 0,
					     GFP_ATOMIC)) {
			kfree_skb(skb2);
			skb2 = NULL;
		}
	}
	return skb2;
}


/**
 *	skb_copy_expand	-	copy and expand sk_buff
 *	@skb: buffer to copy
 *	@newheadroom: new free bytes at head
 *	@newtailroom: new free bytes at tail
 *	@gfp_mask: allocation priority
 *
 *	Make a copy of both an &sk_buff and its data and while doing so
 *	allocate additional space.
 *
 *	This is used when the caller wishes to modify the data and needs a
 *	private copy of the data to alter as well as more space for new fields.
 *	Returns %NULL on failure or the pointer to the buffer
 *	on success. The returned buffer has a reference count of 1.
 *
 *	You must pass %GFP_ATOMIC as the allocation priority if this function
 *	is called from an interrupt.
 *
 *	BUG ALERT: ip_summed is not copied. Why does this work? Is it used
 *	only by netfilter in the cases when checksum is recalculated? --ANK
 */
struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
V
Victor Fusco 已提交
693 694
				int newheadroom, int newtailroom,
				unsigned int __nocast gfp_mask)
L
Linus Torvalds 已提交
695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021
{
	/*
	 *	Allocate the copy buffer
	 */
	struct sk_buff *n = alloc_skb(newheadroom + skb->len + newtailroom,
				      gfp_mask);
	int head_copy_len, head_copy_off;

	if (!n)
		return NULL;

	skb_reserve(n, newheadroom);

	/* Set the tail pointer and length */
	skb_put(n, skb->len);

	head_copy_len = skb_headroom(skb);
	head_copy_off = 0;
	if (newheadroom <= head_copy_len)
		head_copy_len = newheadroom;
	else
		head_copy_off = newheadroom - head_copy_len;

	/* Copy the linear header and data. */
	if (skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off,
			  skb->len + head_copy_len))
		BUG();

	copy_skb_header(n, skb);

	return n;
}

/**
 *	skb_pad			-	zero pad the tail of an skb
 *	@skb: buffer to pad
 *	@pad: space to pad
 *
 *	Ensure that a buffer is followed by a padding area that is zero
 *	filled. Used by network drivers which may DMA or transfer data
 *	beyond the buffer end onto the wire.
 *
 *	May return NULL in out of memory cases.
 */
 
struct sk_buff *skb_pad(struct sk_buff *skb, int pad)
{
	struct sk_buff *nskb;
	
	/* If the skbuff is non linear tailroom is always zero.. */
	if (skb_tailroom(skb) >= pad) {
		memset(skb->data+skb->len, 0, pad);
		return skb;
	}
	
	nskb = skb_copy_expand(skb, skb_headroom(skb), skb_tailroom(skb) + pad, GFP_ATOMIC);
	kfree_skb(skb);
	if (nskb)
		memset(nskb->data+nskb->len, 0, pad);
	return nskb;
}	
 
/* Trims skb to length len. It can change skb pointers, if "realloc" is 1.
 * If realloc==0 and trimming is impossible without change of data,
 * it is BUG().
 */

int ___pskb_trim(struct sk_buff *skb, unsigned int len, int realloc)
{
	int offset = skb_headlen(skb);
	int nfrags = skb_shinfo(skb)->nr_frags;
	int i;

	for (i = 0; i < nfrags; i++) {
		int end = offset + skb_shinfo(skb)->frags[i].size;
		if (end > len) {
			if (skb_cloned(skb)) {
				if (!realloc)
					BUG();
				if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
					return -ENOMEM;
			}
			if (len <= offset) {
				put_page(skb_shinfo(skb)->frags[i].page);
				skb_shinfo(skb)->nr_frags--;
			} else {
				skb_shinfo(skb)->frags[i].size = len - offset;
			}
		}
		offset = end;
	}

	if (offset < len) {
		skb->data_len -= skb->len - len;
		skb->len       = len;
	} else {
		if (len <= skb_headlen(skb)) {
			skb->len      = len;
			skb->data_len = 0;
			skb->tail     = skb->data + len;
			if (skb_shinfo(skb)->frag_list && !skb_cloned(skb))
				skb_drop_fraglist(skb);
		} else {
			skb->data_len -= skb->len - len;
			skb->len       = len;
		}
	}

	return 0;
}

/**
 *	__pskb_pull_tail - advance tail of skb header
 *	@skb: buffer to reallocate
 *	@delta: number of bytes to advance tail
 *
 *	The function makes a sense only on a fragmented &sk_buff,
 *	it expands header moving its tail forward and copying necessary
 *	data from fragmented part.
 *
 *	&sk_buff MUST have reference count of 1.
 *
 *	Returns %NULL (and &sk_buff does not change) if pull failed
 *	or value of new tail of skb in the case of success.
 *
 *	All the pointers pointing into skb header may change and must be
 *	reloaded after call to this function.
 */

/* Moves tail of skb head forward, copying data from fragmented part,
 * when it is necessary.
 * 1. It may fail due to malloc failure.
 * 2. It may change skb pointers.
 *
 * It is pretty complicated. Luckily, it is called only in exceptional cases.
 */
unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta)
{
	/* If skb has not enough free space at tail, get new one
	 * plus 128 bytes for future expansions. If we have enough
	 * room at tail, reallocate without expansion only if skb is cloned.
	 */
	int i, k, eat = (skb->tail + delta) - skb->end;

	if (eat > 0 || skb_cloned(skb)) {
		if (pskb_expand_head(skb, 0, eat > 0 ? eat + 128 : 0,
				     GFP_ATOMIC))
			return NULL;
	}

	if (skb_copy_bits(skb, skb_headlen(skb), skb->tail, delta))
		BUG();

	/* Optimization: no fragments, no reasons to preestimate
	 * size of pulled pages. Superb.
	 */
	if (!skb_shinfo(skb)->frag_list)
		goto pull_pages;

	/* Estimate size of pulled pages. */
	eat = delta;
	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
		if (skb_shinfo(skb)->frags[i].size >= eat)
			goto pull_pages;
		eat -= skb_shinfo(skb)->frags[i].size;
	}

	/* If we need update frag list, we are in troubles.
	 * Certainly, it possible to add an offset to skb data,
	 * but taking into account that pulling is expected to
	 * be very rare operation, it is worth to fight against
	 * further bloating skb head and crucify ourselves here instead.
	 * Pure masohism, indeed. 8)8)
	 */
	if (eat) {
		struct sk_buff *list = skb_shinfo(skb)->frag_list;
		struct sk_buff *clone = NULL;
		struct sk_buff *insp = NULL;

		do {
			if (!list)
				BUG();

			if (list->len <= eat) {
				/* Eaten as whole. */
				eat -= list->len;
				list = list->next;
				insp = list;
			} else {
				/* Eaten partially. */

				if (skb_shared(list)) {
					/* Sucks! We need to fork list. :-( */
					clone = skb_clone(list, GFP_ATOMIC);
					if (!clone)
						return NULL;
					insp = list->next;
					list = clone;
				} else {
					/* This may be pulled without
					 * problems. */
					insp = list;
				}
				if (!pskb_pull(list, eat)) {
					if (clone)
						kfree_skb(clone);
					return NULL;
				}
				break;
			}
		} while (eat);

		/* Free pulled out fragments. */
		while ((list = skb_shinfo(skb)->frag_list) != insp) {
			skb_shinfo(skb)->frag_list = list->next;
			kfree_skb(list);
		}
		/* And insert new clone at head. */
		if (clone) {
			clone->next = list;
			skb_shinfo(skb)->frag_list = clone;
		}
	}
	/* Success! Now we may commit changes to skb data. */

pull_pages:
	eat = delta;
	k = 0;
	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
		if (skb_shinfo(skb)->frags[i].size <= eat) {
			put_page(skb_shinfo(skb)->frags[i].page);
			eat -= skb_shinfo(skb)->frags[i].size;
		} else {
			skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i];
			if (eat) {
				skb_shinfo(skb)->frags[k].page_offset += eat;
				skb_shinfo(skb)->frags[k].size -= eat;
				eat = 0;
			}
			k++;
		}
	}
	skb_shinfo(skb)->nr_frags = k;

	skb->tail     += delta;
	skb->data_len -= delta;

	return skb->tail;
}

/* Copy some data bits from skb to kernel buffer. */

int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len)
{
	int i, copy;
	int start = skb_headlen(skb);

	if (offset > (int)skb->len - len)
		goto fault;

	/* Copy header. */
	if ((copy = start - offset) > 0) {
		if (copy > len)
			copy = len;
		memcpy(to, skb->data + offset, copy);
		if ((len -= copy) == 0)
			return 0;
		offset += copy;
		to     += copy;
	}

	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
		int end;

		BUG_TRAP(start <= offset + len);

		end = start + skb_shinfo(skb)->frags[i].size;
		if ((copy = end - offset) > 0) {
			u8 *vaddr;

			if (copy > len)
				copy = len;

			vaddr = kmap_skb_frag(&skb_shinfo(skb)->frags[i]);
			memcpy(to,
			       vaddr + skb_shinfo(skb)->frags[i].page_offset+
			       offset - start, copy);
			kunmap_skb_frag(vaddr);

			if ((len -= copy) == 0)
				return 0;
			offset += copy;
			to     += copy;
		}
		start = end;
	}

	if (skb_shinfo(skb)->frag_list) {
		struct sk_buff *list = skb_shinfo(skb)->frag_list;

		for (; list; list = list->next) {
			int end;

			BUG_TRAP(start <= offset + len);

			end = start + list->len;
			if ((copy = end - offset) > 0) {
				if (copy > len)
					copy = len;
				if (skb_copy_bits(list, offset - start,
						  to, copy))
					goto fault;
				if ((len -= copy) == 0)
					return 0;
				offset += copy;
				to     += copy;
			}
			start = end;
		}
	}
	if (!len)
		return 0;

fault:
	return -EFAULT;
}

1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109
/**
 *	skb_store_bits - store bits from kernel buffer to skb
 *	@skb: destination buffer
 *	@offset: offset in destination
 *	@from: source buffer
 *	@len: number of bytes to copy
 *
 *	Copy the specified number of bytes from the source buffer to the
 *	destination skb.  This function handles all the messy bits of
 *	traversing fragment lists and such.
 */

int skb_store_bits(const struct sk_buff *skb, int offset, void *from, int len)
{
	int i, copy;
	int start = skb_headlen(skb);

	if (offset > (int)skb->len - len)
		goto fault;

	if ((copy = start - offset) > 0) {
		if (copy > len)
			copy = len;
		memcpy(skb->data + offset, from, copy);
		if ((len -= copy) == 0)
			return 0;
		offset += copy;
		from += copy;
	}

	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
		int end;

		BUG_TRAP(start <= offset + len);

		end = start + frag->size;
		if ((copy = end - offset) > 0) {
			u8 *vaddr;

			if (copy > len)
				copy = len;

			vaddr = kmap_skb_frag(frag);
			memcpy(vaddr + frag->page_offset + offset - start,
			       from, copy);
			kunmap_skb_frag(vaddr);

			if ((len -= copy) == 0)
				return 0;
			offset += copy;
			from += copy;
		}
		start = end;
	}

	if (skb_shinfo(skb)->frag_list) {
		struct sk_buff *list = skb_shinfo(skb)->frag_list;

		for (; list; list = list->next) {
			int end;

			BUG_TRAP(start <= offset + len);

			end = start + list->len;
			if ((copy = end - offset) > 0) {
				if (copy > len)
					copy = len;
				if (skb_store_bits(list, offset - start,
						   from, copy))
					goto fault;
				if ((len -= copy) == 0)
					return 0;
				offset += copy;
				from += copy;
			}
			start = end;
		}
	}
	if (!len)
		return 0;

fault:
	return -EFAULT;
}

EXPORT_SYMBOL(skb_store_bits);

L
Linus Torvalds 已提交
1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387
/* Checksum skb data. */

unsigned int skb_checksum(const struct sk_buff *skb, int offset,
			  int len, unsigned int csum)
{
	int start = skb_headlen(skb);
	int i, copy = start - offset;
	int pos = 0;

	/* Checksum header. */
	if (copy > 0) {
		if (copy > len)
			copy = len;
		csum = csum_partial(skb->data + offset, copy, csum);
		if ((len -= copy) == 0)
			return csum;
		offset += copy;
		pos	= copy;
	}

	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
		int end;

		BUG_TRAP(start <= offset + len);

		end = start + skb_shinfo(skb)->frags[i].size;
		if ((copy = end - offset) > 0) {
			unsigned int csum2;
			u8 *vaddr;
			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];

			if (copy > len)
				copy = len;
			vaddr = kmap_skb_frag(frag);
			csum2 = csum_partial(vaddr + frag->page_offset +
					     offset - start, copy, 0);
			kunmap_skb_frag(vaddr);
			csum = csum_block_add(csum, csum2, pos);
			if (!(len -= copy))
				return csum;
			offset += copy;
			pos    += copy;
		}
		start = end;
	}

	if (skb_shinfo(skb)->frag_list) {
		struct sk_buff *list = skb_shinfo(skb)->frag_list;

		for (; list; list = list->next) {
			int end;

			BUG_TRAP(start <= offset + len);

			end = start + list->len;
			if ((copy = end - offset) > 0) {
				unsigned int csum2;
				if (copy > len)
					copy = len;
				csum2 = skb_checksum(list, offset - start,
						     copy, 0);
				csum = csum_block_add(csum, csum2, pos);
				if ((len -= copy) == 0)
					return csum;
				offset += copy;
				pos    += copy;
			}
			start = end;
		}
	}
	if (len)
		BUG();

	return csum;
}

/* Both of above in one bottle. */

unsigned int skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
				    u8 *to, int len, unsigned int csum)
{
	int start = skb_headlen(skb);
	int i, copy = start - offset;
	int pos = 0;

	/* Copy header. */
	if (copy > 0) {
		if (copy > len)
			copy = len;
		csum = csum_partial_copy_nocheck(skb->data + offset, to,
						 copy, csum);
		if ((len -= copy) == 0)
			return csum;
		offset += copy;
		to     += copy;
		pos	= copy;
	}

	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
		int end;

		BUG_TRAP(start <= offset + len);

		end = start + skb_shinfo(skb)->frags[i].size;
		if ((copy = end - offset) > 0) {
			unsigned int csum2;
			u8 *vaddr;
			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];

			if (copy > len)
				copy = len;
			vaddr = kmap_skb_frag(frag);
			csum2 = csum_partial_copy_nocheck(vaddr +
							  frag->page_offset +
							  offset - start, to,
							  copy, 0);
			kunmap_skb_frag(vaddr);
			csum = csum_block_add(csum, csum2, pos);
			if (!(len -= copy))
				return csum;
			offset += copy;
			to     += copy;
			pos    += copy;
		}
		start = end;
	}

	if (skb_shinfo(skb)->frag_list) {
		struct sk_buff *list = skb_shinfo(skb)->frag_list;

		for (; list; list = list->next) {
			unsigned int csum2;
			int end;

			BUG_TRAP(start <= offset + len);

			end = start + list->len;
			if ((copy = end - offset) > 0) {
				if (copy > len)
					copy = len;
				csum2 = skb_copy_and_csum_bits(list,
							       offset - start,
							       to, copy, 0);
				csum = csum_block_add(csum, csum2, pos);
				if ((len -= copy) == 0)
					return csum;
				offset += copy;
				to     += copy;
				pos    += copy;
			}
			start = end;
		}
	}
	if (len)
		BUG();
	return csum;
}

void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to)
{
	unsigned int csum;
	long csstart;

	if (skb->ip_summed == CHECKSUM_HW)
		csstart = skb->h.raw - skb->data;
	else
		csstart = skb_headlen(skb);

	if (csstart > skb_headlen(skb))
		BUG();

	memcpy(to, skb->data, csstart);

	csum = 0;
	if (csstart != skb->len)
		csum = skb_copy_and_csum_bits(skb, csstart, to + csstart,
					      skb->len - csstart, 0);

	if (skb->ip_summed == CHECKSUM_HW) {
		long csstuff = csstart + skb->csum;

		*((unsigned short *)(to + csstuff)) = csum_fold(csum);
	}
}

/**
 *	skb_dequeue - remove from the head of the queue
 *	@list: list to dequeue from
 *
 *	Remove the head of the list. The list lock is taken so the function
 *	may be used safely with other locking list functions. The head item is
 *	returned or %NULL if the list is empty.
 */

struct sk_buff *skb_dequeue(struct sk_buff_head *list)
{
	unsigned long flags;
	struct sk_buff *result;

	spin_lock_irqsave(&list->lock, flags);
	result = __skb_dequeue(list);
	spin_unlock_irqrestore(&list->lock, flags);
	return result;
}

/**
 *	skb_dequeue_tail - remove from the tail of the queue
 *	@list: list to dequeue from
 *
 *	Remove the tail of the list. The list lock is taken so the function
 *	may be used safely with other locking list functions. The tail item is
 *	returned or %NULL if the list is empty.
 */
struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list)
{
	unsigned long flags;
	struct sk_buff *result;

	spin_lock_irqsave(&list->lock, flags);
	result = __skb_dequeue_tail(list);
	spin_unlock_irqrestore(&list->lock, flags);
	return result;
}

/**
 *	skb_queue_purge - empty a list
 *	@list: list to empty
 *
 *	Delete all buffers on an &sk_buff list. Each buffer is removed from
 *	the list and one reference dropped. This function takes the list
 *	lock and is atomic with respect to other list locking functions.
 */
void skb_queue_purge(struct sk_buff_head *list)
{
	struct sk_buff *skb;
	while ((skb = skb_dequeue(list)) != NULL)
		kfree_skb(skb);
}

/**
 *	skb_queue_head - queue a buffer at the list head
 *	@list: list to use
 *	@newsk: buffer to queue
 *
 *	Queue a buffer at the start of the list. This function takes the
 *	list lock and can be used safely with other locking &sk_buff functions
 *	safely.
 *
 *	A buffer cannot be placed on two lists at the same time.
 */
void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk)
{
	unsigned long flags;

	spin_lock_irqsave(&list->lock, flags);
	__skb_queue_head(list, newsk);
	spin_unlock_irqrestore(&list->lock, flags);
}

/**
 *	skb_queue_tail - queue a buffer at the list tail
 *	@list: list to use
 *	@newsk: buffer to queue
 *
 *	Queue a buffer at the tail of the list. This function takes the
 *	list lock and can be used safely with other locking &sk_buff functions
 *	safely.
 *
 *	A buffer cannot be placed on two lists at the same time.
 */
void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk)
{
	unsigned long flags;

	spin_lock_irqsave(&list->lock, flags);
	__skb_queue_tail(list, newsk);
	spin_unlock_irqrestore(&list->lock, flags);
}
D
David S. Miller 已提交
1388

L
Linus Torvalds 已提交
1389 1390 1391
/**
 *	skb_unlink	-	remove a buffer from a list
 *	@skb: buffer to remove
D
David S. Miller 已提交
1392
 *	@list: list to use
L
Linus Torvalds 已提交
1393
 *
D
David S. Miller 已提交
1394 1395
 *	Remove a packet from a list. The list locks are taken and this
 *	function is atomic with respect to other list locked calls
L
Linus Torvalds 已提交
1396
 *
D
David S. Miller 已提交
1397
 *	You must know what list the SKB is on.
L
Linus Torvalds 已提交
1398
 */
D
David S. Miller 已提交
1399
void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list)
L
Linus Torvalds 已提交
1400
{
D
David S. Miller 已提交
1401
	unsigned long flags;
L
Linus Torvalds 已提交
1402

D
David S. Miller 已提交
1403 1404 1405
	spin_lock_irqsave(&list->lock, flags);
	__skb_unlink(skb, list);
	spin_unlock_irqrestore(&list->lock, flags);
L
Linus Torvalds 已提交
1406 1407 1408 1409 1410 1411
}

/**
 *	skb_append	-	append a buffer
 *	@old: buffer to insert after
 *	@newsk: buffer to insert
D
David S. Miller 已提交
1412
 *	@list: list to use
L
Linus Torvalds 已提交
1413 1414 1415 1416 1417
 *
 *	Place a packet after a given packet in a list. The list locks are taken
 *	and this function is atomic with respect to other list locked calls.
 *	A buffer cannot be placed on two lists at the same time.
 */
D
David S. Miller 已提交
1418
void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list)
L
Linus Torvalds 已提交
1419 1420 1421
{
	unsigned long flags;

D
David S. Miller 已提交
1422 1423 1424
	spin_lock_irqsave(&list->lock, flags);
	__skb_append(old, newsk, list);
	spin_unlock_irqrestore(&list->lock, flags);
L
Linus Torvalds 已提交
1425 1426 1427 1428 1429 1430 1431
}


/**
 *	skb_insert	-	insert a buffer
 *	@old: buffer to insert before
 *	@newsk: buffer to insert
D
David S. Miller 已提交
1432 1433 1434 1435 1436
 *	@list: list to use
 *
 *	Place a packet before a given packet in a list. The list locks are
 * 	taken and this function is atomic with respect to other list locked
 *	calls.
L
Linus Torvalds 已提交
1437 1438 1439
 *
 *	A buffer cannot be placed on two lists at the same time.
 */
D
David S. Miller 已提交
1440
void skb_insert(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list)
L
Linus Torvalds 已提交
1441 1442 1443
{
	unsigned long flags;

D
David S. Miller 已提交
1444 1445 1446
	spin_lock_irqsave(&list->lock, flags);
	__skb_insert(newsk, old->prev, old, list);
	spin_unlock_irqrestore(&list->lock, flags);
L
Linus Torvalds 已提交
1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539
}

#if 0
/*
 * 	Tune the memory allocator for a new MTU size.
 */
void skb_add_mtu(int mtu)
{
	/* Must match allocation in alloc_skb */
	mtu = SKB_DATA_ALIGN(mtu) + sizeof(struct skb_shared_info);

	kmem_add_cache_size(mtu);
}
#endif

static inline void skb_split_inside_header(struct sk_buff *skb,
					   struct sk_buff* skb1,
					   const u32 len, const int pos)
{
	int i;

	memcpy(skb_put(skb1, pos - len), skb->data + len, pos - len);

	/* And move data appendix as is. */
	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
		skb_shinfo(skb1)->frags[i] = skb_shinfo(skb)->frags[i];

	skb_shinfo(skb1)->nr_frags = skb_shinfo(skb)->nr_frags;
	skb_shinfo(skb)->nr_frags  = 0;
	skb1->data_len		   = skb->data_len;
	skb1->len		   += skb1->data_len;
	skb->data_len		   = 0;
	skb->len		   = len;
	skb->tail		   = skb->data + len;
}

static inline void skb_split_no_header(struct sk_buff *skb,
				       struct sk_buff* skb1,
				       const u32 len, int pos)
{
	int i, k = 0;
	const int nfrags = skb_shinfo(skb)->nr_frags;

	skb_shinfo(skb)->nr_frags = 0;
	skb1->len		  = skb1->data_len = skb->len - len;
	skb->len		  = len;
	skb->data_len		  = len - pos;

	for (i = 0; i < nfrags; i++) {
		int size = skb_shinfo(skb)->frags[i].size;

		if (pos + size > len) {
			skb_shinfo(skb1)->frags[k] = skb_shinfo(skb)->frags[i];

			if (pos < len) {
				/* Split frag.
				 * We have two variants in this case:
				 * 1. Move all the frag to the second
				 *    part, if it is possible. F.e.
				 *    this approach is mandatory for TUX,
				 *    where splitting is expensive.
				 * 2. Split is accurately. We make this.
				 */
				get_page(skb_shinfo(skb)->frags[i].page);
				skb_shinfo(skb1)->frags[0].page_offset += len - pos;
				skb_shinfo(skb1)->frags[0].size -= len - pos;
				skb_shinfo(skb)->frags[i].size	= len - pos;
				skb_shinfo(skb)->nr_frags++;
			}
			k++;
		} else
			skb_shinfo(skb)->nr_frags++;
		pos += size;
	}
	skb_shinfo(skb1)->nr_frags = k;
}

/**
 * skb_split - Split fragmented skb to two parts at length len.
 * @skb: the buffer to split
 * @skb1: the buffer to receive the second part
 * @len: new length for skb
 */
void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len)
{
	int pos = skb_headlen(skb);

	if (len < pos)	/* Split line is inside header. */
		skb_split_inside_header(skb, skb1, len, pos);
	else		/* Second chunk has no header, nothing to copy. */
		skb_split_no_header(skb, skb1, len, pos);
}

1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653
/**
 * skb_prepare_seq_read - Prepare a sequential read of skb data
 * @skb: the buffer to read
 * @from: lower offset of data to be read
 * @to: upper offset of data to be read
 * @st: state variable
 *
 * Initializes the specified state variable. Must be called before
 * invoking skb_seq_read() for the first time.
 */
void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from,
			  unsigned int to, struct skb_seq_state *st)
{
	st->lower_offset = from;
	st->upper_offset = to;
	st->root_skb = st->cur_skb = skb;
	st->frag_idx = st->stepped_offset = 0;
	st->frag_data = NULL;
}

/**
 * skb_seq_read - Sequentially read skb data
 * @consumed: number of bytes consumed by the caller so far
 * @data: destination pointer for data to be returned
 * @st: state variable
 *
 * Reads a block of skb data at &consumed relative to the
 * lower offset specified to skb_prepare_seq_read(). Assigns
 * the head of the data block to &data and returns the length
 * of the block or 0 if the end of the skb data or the upper
 * offset has been reached.
 *
 * The caller is not required to consume all of the data
 * returned, i.e. &consumed is typically set to the number
 * of bytes already consumed and the next call to
 * skb_seq_read() will return the remaining part of the block.
 *
 * Note: The size of each block of data returned can be arbitary,
 *       this limitation is the cost for zerocopy seqeuental
 *       reads of potentially non linear data.
 *
 * Note: Fragment lists within fragments are not implemented
 *       at the moment, state->root_skb could be replaced with
 *       a stack for this purpose.
 */
unsigned int skb_seq_read(unsigned int consumed, const u8 **data,
			  struct skb_seq_state *st)
{
	unsigned int block_limit, abs_offset = consumed + st->lower_offset;
	skb_frag_t *frag;

	if (unlikely(abs_offset >= st->upper_offset))
		return 0;

next_skb:
	block_limit = skb_headlen(st->cur_skb);

	if (abs_offset < block_limit) {
		*data = st->cur_skb->data + abs_offset;
		return block_limit - abs_offset;
	}

	if (st->frag_idx == 0 && !st->frag_data)
		st->stepped_offset += skb_headlen(st->cur_skb);

	while (st->frag_idx < skb_shinfo(st->cur_skb)->nr_frags) {
		frag = &skb_shinfo(st->cur_skb)->frags[st->frag_idx];
		block_limit = frag->size + st->stepped_offset;

		if (abs_offset < block_limit) {
			if (!st->frag_data)
				st->frag_data = kmap_skb_frag(frag);

			*data = (u8 *) st->frag_data + frag->page_offset +
				(abs_offset - st->stepped_offset);

			return block_limit - abs_offset;
		}

		if (st->frag_data) {
			kunmap_skb_frag(st->frag_data);
			st->frag_data = NULL;
		}

		st->frag_idx++;
		st->stepped_offset += frag->size;
	}

	if (st->cur_skb->next) {
		st->cur_skb = st->cur_skb->next;
		st->frag_idx = 0;
		goto next_skb;
	} else if (st->root_skb == st->cur_skb &&
		   skb_shinfo(st->root_skb)->frag_list) {
		st->cur_skb = skb_shinfo(st->root_skb)->frag_list;
		goto next_skb;
	}

	return 0;
}

/**
 * skb_abort_seq_read - Abort a sequential read of skb data
 * @st: state variable
 *
 * Must be called if skb_seq_read() was not called until it
 * returned 0.
 */
void skb_abort_seq_read(struct skb_seq_state *st)
{
	if (st->frag_data)
		kunmap_skb_frag(st->frag_data);
}

1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692
#define TS_SKB_CB(state)	((struct skb_seq_state *) &((state)->cb))

static unsigned int skb_ts_get_next_block(unsigned int offset, const u8 **text,
					  struct ts_config *conf,
					  struct ts_state *state)
{
	return skb_seq_read(offset, text, TS_SKB_CB(state));
}

static void skb_ts_finish(struct ts_config *conf, struct ts_state *state)
{
	skb_abort_seq_read(TS_SKB_CB(state));
}

/**
 * skb_find_text - Find a text pattern in skb data
 * @skb: the buffer to look in
 * @from: search offset
 * @to: search limit
 * @config: textsearch configuration
 * @state: uninitialized textsearch state variable
 *
 * Finds a pattern in the skb data according to the specified
 * textsearch configuration. Use textsearch_next() to retrieve
 * subsequent occurrences of the pattern. Returns the offset
 * to the first occurrence or UINT_MAX if no match was found.
 */
unsigned int skb_find_text(struct sk_buff *skb, unsigned int from,
			   unsigned int to, struct ts_config *config,
			   struct ts_state *state)
{
	config->get_next_block = skb_ts_get_next_block;
	config->finish = skb_ts_finish;

	skb_prepare_seq_read(skb, from, to, TS_SKB_CB(state));

	return textsearch_find(config, state);
}

L
Linus Torvalds 已提交
1693 1694 1695 1696 1697 1698 1699 1700 1701
void __init skb_init(void)
{
	skbuff_head_cache = kmem_cache_create("skbuff_head_cache",
					      sizeof(struct sk_buff),
					      0,
					      SLAB_HWCACHE_ALIGN,
					      NULL, NULL);
	if (!skbuff_head_cache)
		panic("cannot create skbuff cache");
1702 1703 1704 1705 1706 1707 1708 1709 1710 1711

	skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache",
						(2*sizeof(struct sk_buff)) +
						sizeof(atomic_t),
						0,
						SLAB_HWCACHE_ALIGN,
						NULL, NULL);
	if (!skbuff_fclone_cache)
		panic("cannot create skbuff cache");

1712
	do_gettimeofday(&skb_tv_base);
L
Linus Torvalds 已提交
1713 1714 1715 1716 1717
}

EXPORT_SYMBOL(___pskb_trim);
EXPORT_SYMBOL(__kfree_skb);
EXPORT_SYMBOL(__pskb_pull_tail);
1718
EXPORT_SYMBOL(__alloc_skb);
L
Linus Torvalds 已提交
1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741
EXPORT_SYMBOL(pskb_copy);
EXPORT_SYMBOL(pskb_expand_head);
EXPORT_SYMBOL(skb_checksum);
EXPORT_SYMBOL(skb_clone);
EXPORT_SYMBOL(skb_clone_fraglist);
EXPORT_SYMBOL(skb_copy);
EXPORT_SYMBOL(skb_copy_and_csum_bits);
EXPORT_SYMBOL(skb_copy_and_csum_dev);
EXPORT_SYMBOL(skb_copy_bits);
EXPORT_SYMBOL(skb_copy_expand);
EXPORT_SYMBOL(skb_over_panic);
EXPORT_SYMBOL(skb_pad);
EXPORT_SYMBOL(skb_realloc_headroom);
EXPORT_SYMBOL(skb_under_panic);
EXPORT_SYMBOL(skb_dequeue);
EXPORT_SYMBOL(skb_dequeue_tail);
EXPORT_SYMBOL(skb_insert);
EXPORT_SYMBOL(skb_queue_purge);
EXPORT_SYMBOL(skb_queue_head);
EXPORT_SYMBOL(skb_queue_tail);
EXPORT_SYMBOL(skb_unlink);
EXPORT_SYMBOL(skb_append);
EXPORT_SYMBOL(skb_split);
1742 1743 1744
EXPORT_SYMBOL(skb_prepare_seq_read);
EXPORT_SYMBOL(skb_seq_read);
EXPORT_SYMBOL(skb_abort_seq_read);
1745
EXPORT_SYMBOL(skb_find_text);
1746
EXPORT_SYMBOL(skb_tv_base);