skbuff.c 61.3 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
/*
 *	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/module.h>
#include <linux/types.h>
#include <linux/kernel.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>
J
Jens Axboe 已提交
55
#include <linux/splice.h>
L
Linus Torvalds 已提交
56 57 58
#include <linux/cache.h>
#include <linux/rtnetlink.h>
#include <linux/init.h>
59
#include <linux/scatterlist.h>
L
Linus Torvalds 已提交
60 61 62 63 64 65 66 67 68 69

#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>

A
Al Viro 已提交
70 71
#include "kmap_skb.h"

72 73
static struct kmem_cache *skbuff_head_cache __read_mostly;
static struct kmem_cache *skbuff_fclone_cache __read_mostly;
L
Linus Torvalds 已提交
74

J
Jens Axboe 已提交
75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108
static void sock_pipe_buf_release(struct pipe_inode_info *pipe,
				  struct pipe_buffer *buf)
{
	struct sk_buff *skb = (struct sk_buff *) buf->private;

	kfree_skb(skb);
}

static void sock_pipe_buf_get(struct pipe_inode_info *pipe,
				struct pipe_buffer *buf)
{
	struct sk_buff *skb = (struct sk_buff *) buf->private;

	skb_get(skb);
}

static int sock_pipe_buf_steal(struct pipe_inode_info *pipe,
			       struct pipe_buffer *buf)
{
	return 1;
}


/* Pipe buffer operations for a socket. */
static struct pipe_buf_operations sock_pipe_buf_ops = {
	.can_merge = 0,
	.map = generic_pipe_buf_map,
	.unmap = generic_pipe_buf_unmap,
	.confirm = generic_pipe_buf_confirm,
	.release = sock_pipe_buf_release,
	.steal = sock_pipe_buf_steal,
	.get = sock_pipe_buf_get,
};

L
Linus Torvalds 已提交
109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124
/*
 *	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)
{
125
	printk(KERN_EMERG "skb_over_panic: text:%p len:%d put:%d head:%p "
126
			  "data:%p tail:%#lx end:%#lx dev:%s\n",
127
	       here, skb->len, sz, skb->head, skb->data,
128
	       (unsigned long)skb->tail, (unsigned long)skb->end,
129
	       skb->dev ? skb->dev->name : "<NULL>");
L
Linus Torvalds 已提交
130 131 132 133 134 135 136 137 138 139 140 141 142 143
	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)
{
144
	printk(KERN_EMERG "skb_under_panic: text:%p len:%d put:%d head:%p "
145
			  "data:%p tail:%#lx end:%#lx dev:%s\n",
146
	       here, skb->len, sz, skb->head, skb->data,
147
	       (unsigned long)skb->tail, (unsigned long)skb->end,
148
	       skb->dev ? skb->dev->name : "<NULL>");
L
Linus Torvalds 已提交
149 150 151
	BUG();
}

152 153 154 155 156 157 158 159
void skb_truesize_bug(struct sk_buff *skb)
{
	printk(KERN_ERR "SKB BUG: Invalid truesize (%u) "
	       "len=%u, sizeof(sk_buff)=%Zd\n",
	       skb->truesize, skb->len, sizeof(struct sk_buff));
}
EXPORT_SYMBOL(skb_truesize_bug);

L
Linus Torvalds 已提交
160 161 162 163 164 165 166
/* 	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.
 *
 */

/**
167
 *	__alloc_skb	-	allocate a network buffer
L
Linus Torvalds 已提交
168 169
 *	@size: size to allocate
 *	@gfp_mask: allocation mask
170 171
 *	@fclone: allocate from fclone cache instead of head cache
 *		and allocate a cloned (child) skb
172
 *	@node: numa node to allocate memory on
L
Linus Torvalds 已提交
173 174 175 176 177 178 179 180
 *
 *	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.
 */
A
Al Viro 已提交
181
struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
182
			    int fclone, int node)
L
Linus Torvalds 已提交
183
{
184
	struct kmem_cache *cache;
B
Benjamin LaHaise 已提交
185
	struct skb_shared_info *shinfo;
L
Linus Torvalds 已提交
186 187 188
	struct sk_buff *skb;
	u8 *data;

189 190
	cache = fclone ? skbuff_fclone_cache : skbuff_head_cache;

L
Linus Torvalds 已提交
191
	/* Get the HEAD */
192
	skb = kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node);
L
Linus Torvalds 已提交
193 194 195 196
	if (!skb)
		goto out;

	size = SKB_DATA_ALIGN(size);
197 198
	data = kmalloc_node_track_caller(size + sizeof(struct skb_shared_info),
			gfp_mask, node);
L
Linus Torvalds 已提交
199 200 201
	if (!data)
		goto nodata;

202 203 204 205
	/*
	 * See comment in sk_buff definition, just before the 'tail' member
	 */
	memset(skb, 0, offsetof(struct sk_buff, tail));
L
Linus Torvalds 已提交
206 207 208 209
	skb->truesize = size + sizeof(struct sk_buff);
	atomic_set(&skb->users, 1);
	skb->head = data;
	skb->data = data;
210
	skb_reset_tail_pointer(skb);
211
	skb->end = skb->tail + size;
B
Benjamin LaHaise 已提交
212 213 214 215
	/* make sure we initialize shinfo sequentially */
	shinfo = skb_shinfo(skb);
	atomic_set(&shinfo->dataref, 1);
	shinfo->nr_frags  = 0;
216 217 218
	shinfo->gso_size = 0;
	shinfo->gso_segs = 0;
	shinfo->gso_type = 0;
B
Benjamin LaHaise 已提交
219 220 221
	shinfo->ip6_frag_id = 0;
	shinfo->frag_list = NULL;

222 223 224
	if (fclone) {
		struct sk_buff *child = skb + 1;
		atomic_t *fclone_ref = (atomic_t *) (child + 1);
L
Linus Torvalds 已提交
225

226 227 228 229 230
		skb->fclone = SKB_FCLONE_ORIG;
		atomic_set(fclone_ref, 1);

		child->fclone = SKB_FCLONE_UNAVAILABLE;
	}
L
Linus Torvalds 已提交
231 232 233
out:
	return skb;
nodata:
234
	kmem_cache_free(cache, skb);
L
Linus Torvalds 已提交
235 236 237 238
	skb = NULL;
	goto out;
}

239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254
/**
 *	__netdev_alloc_skb - allocate an skbuff for rx on a specific device
 *	@dev: network device to receive on
 *	@length: length to allocate
 *	@gfp_mask: get_free_pages mask, passed to alloc_skb
 *
 *	Allocate a new &sk_buff and assign it a usage count of one. The
 *	buffer has unspecified headroom built in. Users should allocate
 *	the headroom they think they need without accounting for the
 *	built in space. The built in space is used for optimisations.
 *
 *	%NULL is returned if there is no free memory.
 */
struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
		unsigned int length, gfp_t gfp_mask)
{
255
	int node = dev->dev.parent ? dev_to_node(dev->dev.parent) : -1;
256 257
	struct sk_buff *skb;

258
	skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, node);
259
	if (likely(skb)) {
260
		skb_reserve(skb, NET_SKB_PAD);
261 262
		skb->dev = dev;
	}
263 264
	return skb;
}
L
Linus Torvalds 已提交
265

266
static void skb_drop_list(struct sk_buff **listp)
L
Linus Torvalds 已提交
267
{
268
	struct sk_buff *list = *listp;
L
Linus Torvalds 已提交
269

270
	*listp = NULL;
L
Linus Torvalds 已提交
271 272 273 274 275 276 277 278

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

279 280 281 282 283
static inline void skb_drop_fraglist(struct sk_buff *skb)
{
	skb_drop_list(&skb_shinfo(skb)->frag_list);
}

L
Linus Torvalds 已提交
284 285 286 287 288 289 290 291
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);
}

292
static void skb_release_data(struct sk_buff *skb)
L
Linus Torvalds 已提交
293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312
{
	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.
 */
313
static void kfree_skbmem(struct sk_buff *skb)
L
Linus Torvalds 已提交
314
{
315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340
	struct sk_buff *other;
	atomic_t *fclone_ref;

	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;
341
	}
L
Linus Torvalds 已提交
342 343
}

344 345
/* Free everything but the sk_buff shell. */
static void skb_release_all(struct sk_buff *skb)
L
Linus Torvalds 已提交
346 347 348 349 350
{
	dst_release(skb->dst);
#ifdef CONFIG_XFRM
	secpath_put(skb->sp);
#endif
351 352
	if (skb->destructor) {
		WARN_ON(in_irq());
L
Linus Torvalds 已提交
353 354
		skb->destructor(skb);
	}
355
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
356
	nf_conntrack_put(skb->nfct);
357 358
	nf_conntrack_put_reasm(skb->nfct_reasm);
#endif
L
Linus Torvalds 已提交
359 360 361 362 363 364 365 366 367 368
#ifdef CONFIG_BRIDGE_NETFILTER
	nf_bridge_put(skb->nf_bridge);
#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
369 370 371 372 373 374 375 376 377 378 379
	skb_release_data(skb);
}

/**
 *	__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
 */
L
Linus Torvalds 已提交
380

381 382 383
void __kfree_skb(struct sk_buff *skb)
{
	skb_release_all(skb);
L
Linus Torvalds 已提交
384 385 386
	kfree_skbmem(skb);
}

387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404
/**
 *	kfree_skb - free an sk_buff
 *	@skb: buffer to free
 *
 *	Drop a reference to the buffer and free it if the usage count has
 *	hit zero.
 */
void kfree_skb(struct sk_buff *skb)
{
	if (unlikely(!skb))
		return;
	if (likely(atomic_read(&skb->users) == 1))
		smp_rmb();
	else if (likely(!atomic_dec_and_test(&skb->users)))
		return;
	__kfree_skb(skb);
}

405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442
static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
{
	new->tstamp		= old->tstamp;
	new->dev		= old->dev;
	new->transport_header	= old->transport_header;
	new->network_header	= old->network_header;
	new->mac_header		= old->mac_header;
	new->dst		= dst_clone(old->dst);
#ifdef CONFIG_INET
	new->sp			= secpath_get(old->sp);
#endif
	memcpy(new->cb, old->cb, sizeof(old->cb));
	new->csum_start		= old->csum_start;
	new->csum_offset	= old->csum_offset;
	new->local_df		= old->local_df;
	new->pkt_type		= old->pkt_type;
	new->ip_summed		= old->ip_summed;
	skb_copy_queue_mapping(new, old);
	new->priority		= old->priority;
#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
	new->ipvs_property	= old->ipvs_property;
#endif
	new->protocol		= old->protocol;
	new->mark		= old->mark;
	__nf_copy(new, old);
#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
    defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
	new->nf_trace		= old->nf_trace;
#endif
#ifdef CONFIG_NET_SCHED
	new->tc_index		= old->tc_index;
#ifdef CONFIG_NET_CLS_ACT
	new->tc_verd		= old->tc_verd;
#endif
#endif
	skb_copy_secmark(new, old);
}

H
Herbert Xu 已提交
443
static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb)
L
Linus Torvalds 已提交
444 445 446 447 448
{
#define C(x) n->x = skb->x

	n->next = n->prev = NULL;
	n->sk = NULL;
449 450
	__copy_skb_header(n, skb);

L
Linus Torvalds 已提交
451 452
	C(len);
	C(data_len);
453
	C(mac_len);
454
	n->hdr_len = skb->nohdr ? skb_headroom(skb) : skb->hdr_len;
455
	n->cloned = 1;
L
Linus Torvalds 已提交
456 457
	n->nohdr = 0;
	n->destructor = NULL;
458
	C(iif);
L
Linus Torvalds 已提交
459 460
	C(tail);
	C(end);
461 462 463 464
	C(head);
	C(data);
	C(truesize);
	atomic_set(&n->users, 1);
L
Linus Torvalds 已提交
465 466 467 468 469

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

	return n;
H
Herbert Xu 已提交
470 471 472 473 474 475 476 477 478 479 480 481 482 483 484
#undef C
}

/**
 *	skb_morph	-	morph one skb into another
 *	@dst: the skb to receive the contents
 *	@src: the skb to supply the contents
 *
 *	This is identical to skb_clone except that the target skb is
 *	supplied by the user.
 *
 *	The target skb is returned upon exit.
 */
struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src)
{
485
	skb_release_all(dst);
H
Herbert Xu 已提交
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
	return __skb_clone(dst, src);
}
EXPORT_SYMBOL_GPL(skb_morph);

/**
 *	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.
 */

struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
{
	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;
	}

	return __skb_clone(n, skb);
L
Linus Torvalds 已提交
522 523 524 525
}

static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
{
526
#ifndef NET_SKBUFF_DATA_USES_OFFSET
L
Linus Torvalds 已提交
527 528 529 530
	/*
	 *	Shift between the two data areas in bytes
	 */
	unsigned long offset = new->data - old->data;
531
#endif
532 533 534

	__copy_skb_header(new, old);

535 536 537 538 539 540
#ifndef NET_SKBUFF_DATA_USES_OFFSET
	/* {transport,network,mac}_header are relative to skb->head */
	new->transport_header += offset;
	new->network_header   += offset;
	new->mac_header	      += offset;
#endif
541 542 543
	skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size;
	skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs;
	skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type;
L
Linus Torvalds 已提交
544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562
}

/**
 *	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.
 */

A
Al Viro 已提交
563
struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
L
Linus Torvalds 已提交
564 565 566 567 568
{
	int headerlen = skb->data - skb->head;
	/*
	 *	Allocate the copy buffer
	 */
569 570 571 572 573 574
	struct sk_buff *n;
#ifdef NET_SKBUFF_DATA_USES_OFFSET
	n = alloc_skb(skb->end + skb->data_len, gfp_mask);
#else
	n = alloc_skb(skb->end - skb->head + skb->data_len, gfp_mask);
#endif
L
Linus Torvalds 已提交
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
	if (!n)
		return NULL;

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

	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.
 */

A
Al Viro 已提交
604
struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask)
L
Linus Torvalds 已提交
605 606 607 608
{
	/*
	 *	Allocate the copy buffer
	 */
609 610 611 612 613 614
	struct sk_buff *n;
#ifdef NET_SKBUFF_DATA_USES_OFFSET
	n = alloc_skb(skb->end, gfp_mask);
#else
	n = alloc_skb(skb->end - skb->head, gfp_mask);
#endif
L
Linus Torvalds 已提交
615 616 617 618 619 620 621 622
	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 */
623
	skb_copy_from_linear_data(skb, n->data, n->len);
L
Linus Torvalds 已提交
624

H
Herbert Xu 已提交
625
	n->truesize += skb->data_len;
L
Linus Torvalds 已提交
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
	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
665
int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
A
Al Viro 已提交
666
		     gfp_t gfp_mask)
L
Linus Torvalds 已提交
667 668 669
{
	int i;
	u8 *data;
670 671 672
#ifdef NET_SKBUFF_DATA_USES_OFFSET
	int size = nhead + skb->end + ntail;
#else
L
Linus Torvalds 已提交
673
	int size = nhead + (skb->end - skb->head) + ntail;
674
#endif
L
Linus Torvalds 已提交
675 676 677 678 679 680 681 682 683 684 685 686 687
	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. */
688
#ifdef NET_SKBUFF_DATA_USES_OFFSET
689
	memcpy(data + nhead, skb->head, skb->tail);
690
#else
691
	memcpy(data + nhead, skb->head, skb->tail - skb->head);
692
#endif
693 694
	memcpy(data + size, skb_end_pointer(skb),
	       sizeof(struct skb_shared_info));
L
Linus Torvalds 已提交
695 696 697 698 699 700 701 702 703 704 705 706 707

	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->data    += off;
708 709
#ifdef NET_SKBUFF_DATA_USES_OFFSET
	skb->end      = size;
710
	off           = nhead;
711 712
#else
	skb->end      = skb->head + size;
713
#endif
714 715
	/* {transport,network,mac}_header and tail are relative to skb->head */
	skb->tail	      += off;
716 717 718
	skb->transport_header += off;
	skb->network_header   += off;
	skb->mac_header	      += off;
719
	skb->csum_start       += nhead;
L
Linus Torvalds 已提交
720
	skb->cloned   = 0;
721
	skb->hdr_len  = 0;
L
Linus Torvalds 已提交
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
	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.
 */
struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
V
Victor Fusco 已提交
770
				int newheadroom, int newtailroom,
A
Al Viro 已提交
771
				gfp_t gfp_mask)
L
Linus Torvalds 已提交
772 773 774 775 776 777
{
	/*
	 *	Allocate the copy buffer
	 */
	struct sk_buff *n = alloc_skb(newheadroom + skb->len + newtailroom,
				      gfp_mask);
778
	int oldheadroom = skb_headroom(skb);
L
Linus Torvalds 已提交
779
	int head_copy_len, head_copy_off;
780
	int off;
L
Linus Torvalds 已提交
781 782 783 784 785 786 787 788 789

	if (!n)
		return NULL;

	skb_reserve(n, newheadroom);

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

790
	head_copy_len = oldheadroom;
L
Linus Torvalds 已提交
791 792 793 794 795 796 797 798 799 800 801 802 803
	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);

804
	off                  = newheadroom - oldheadroom;
805 806
	n->csum_start       += off;
#ifdef NET_SKBUFF_DATA_USES_OFFSET
807 808 809
	n->transport_header += off;
	n->network_header   += off;
	n->mac_header	    += off;
810
#endif
811

L
Linus Torvalds 已提交
812 813 814 815 816 817 818 819 820 821 822 823
	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.
 *
824
 *	May return error in out of memory cases. The skb is freed on error.
L
Linus Torvalds 已提交
825
 */
826

827
int skb_pad(struct sk_buff *skb, int pad)
L
Linus Torvalds 已提交
828
{
829 830
	int err;
	int ntail;
831

L
Linus Torvalds 已提交
832
	/* If the skbuff is non linear tailroom is always zero.. */
833
	if (!skb_cloned(skb) && skb_tailroom(skb) >= pad) {
L
Linus Torvalds 已提交
834
		memset(skb->data+skb->len, 0, pad);
835
		return 0;
L
Linus Torvalds 已提交
836
	}
837

838
	ntail = skb->data_len + pad - (skb->end - skb->tail);
839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855
	if (likely(skb_cloned(skb) || ntail > 0)) {
		err = pskb_expand_head(skb, 0, ntail, GFP_ATOMIC);
		if (unlikely(err))
			goto free_skb;
	}

	/* FIXME: The use of this function with non-linear skb's really needs
	 * to be audited.
	 */
	err = skb_linearize(skb);
	if (unlikely(err))
		goto free_skb;

	memset(skb->data + skb->len, 0, pad);
	return 0;

free_skb:
L
Linus Torvalds 已提交
856
	kfree_skb(skb);
857
	return err;
858 859
}

860
/* Trims skb to length len. It can change skb pointers.
L
Linus Torvalds 已提交
861 862
 */

863
int ___pskb_trim(struct sk_buff *skb, unsigned int len)
L
Linus Torvalds 已提交
864
{
865 866
	struct sk_buff **fragp;
	struct sk_buff *frag;
L
Linus Torvalds 已提交
867 868 869
	int offset = skb_headlen(skb);
	int nfrags = skb_shinfo(skb)->nr_frags;
	int i;
870 871 872 873 874
	int err;

	if (skb_cloned(skb) &&
	    unlikely((err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))))
		return err;
L
Linus Torvalds 已提交
875

876 877 878 879 880
	i = 0;
	if (offset >= len)
		goto drop_pages;

	for (; i < nfrags; i++) {
L
Linus Torvalds 已提交
881
		int end = offset + skb_shinfo(skb)->frags[i].size;
882 883 884 885 886 887

		if (end < len) {
			offset = end;
			continue;
		}

888
		skb_shinfo(skb)->frags[i++].size = len - offset;
889

890
drop_pages:
891 892 893 894 895 896 897
		skb_shinfo(skb)->nr_frags = i;

		for (; i < nfrags; i++)
			put_page(skb_shinfo(skb)->frags[i].page);

		if (skb_shinfo(skb)->frag_list)
			skb_drop_fraglist(skb);
898
		goto done;
899 900 901 902 903 904 905 906 907 908 909 910 911 912
	}

	for (fragp = &skb_shinfo(skb)->frag_list; (frag = *fragp);
	     fragp = &frag->next) {
		int end = offset + frag->len;

		if (skb_shared(frag)) {
			struct sk_buff *nfrag;

			nfrag = skb_clone(frag, GFP_ATOMIC);
			if (unlikely(!nfrag))
				return -ENOMEM;

			nfrag->next = frag->next;
913
			kfree_skb(frag);
914 915
			frag = nfrag;
			*fragp = frag;
L
Linus Torvalds 已提交
916
		}
917 918 919 920 921 922 923 924 925 926 927 928 929

		if (end < len) {
			offset = end;
			continue;
		}

		if (end > len &&
		    unlikely((err = pskb_trim(frag, len - offset))))
			return err;

		if (frag->next)
			skb_drop_list(&frag->next);
		break;
L
Linus Torvalds 已提交
930 931
	}

932
done:
933
	if (len > skb_headlen(skb)) {
L
Linus Torvalds 已提交
934 935 936
		skb->data_len -= skb->len - len;
		skb->len       = len;
	} else {
937 938
		skb->len       = len;
		skb->data_len  = 0;
939
		skb_set_tail_pointer(skb, len);
L
Linus Torvalds 已提交
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
	}

	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.
	 */
976
	int i, k, eat = (skb->tail + delta) - skb->end;
L
Linus Torvalds 已提交
977 978 979 980 981 982 983

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

984
	if (skb_copy_bits(skb, skb_headlen(skb), skb_tail_pointer(skb), delta))
L
Linus Torvalds 已提交
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
		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 {
1014
			BUG_ON(!list);
L
Linus Torvalds 已提交
1015 1016 1017 1018 1019 1020 1021 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

			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;

1080
	return skb_tail_pointer(skb);
L
Linus Torvalds 已提交
1081 1082 1083 1084 1085 1086 1087
}

/* 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;
1088
	int start = skb_headlen(skb);
L
Linus Torvalds 已提交
1089 1090 1091 1092 1093

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

	/* Copy header. */
1094
	if ((copy = start - offset) > 0) {
L
Linus Torvalds 已提交
1095 1096
		if (copy > len)
			copy = len;
1097
		skb_copy_from_linear_data_offset(skb, offset, to, copy);
L
Linus Torvalds 已提交
1098 1099 1100 1101 1102 1103 1104
		if ((len -= copy) == 0)
			return 0;
		offset += copy;
		to     += copy;
	}

	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
1105
		int end;
L
Linus Torvalds 已提交
1106

1107 1108 1109
		BUG_TRAP(start <= offset + len);

		end = start + skb_shinfo(skb)->frags[i].size;
L
Linus Torvalds 已提交
1110 1111 1112 1113 1114 1115 1116 1117
		if ((copy = end - offset) > 0) {
			u8 *vaddr;

			if (copy > len)
				copy = len;

			vaddr = kmap_skb_frag(&skb_shinfo(skb)->frags[i]);
			memcpy(to,
1118 1119
			       vaddr + skb_shinfo(skb)->frags[i].page_offset+
			       offset - start, copy);
L
Linus Torvalds 已提交
1120 1121 1122 1123 1124 1125 1126
			kunmap_skb_frag(vaddr);

			if ((len -= copy) == 0)
				return 0;
			offset += copy;
			to     += copy;
		}
1127
		start = end;
L
Linus Torvalds 已提交
1128 1129 1130 1131 1132 1133
	}

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

		for (; list; list = list->next) {
1134 1135 1136
			int end;

			BUG_TRAP(start <= offset + len);
L
Linus Torvalds 已提交
1137

1138
			end = start + list->len;
L
Linus Torvalds 已提交
1139 1140 1141
			if ((copy = end - offset) > 0) {
				if (copy > len)
					copy = len;
1142 1143
				if (skb_copy_bits(list, offset - start,
						  to, copy))
L
Linus Torvalds 已提交
1144 1145 1146 1147 1148 1149
					goto fault;
				if ((len -= copy) == 0)
					return 0;
				offset += copy;
				to     += copy;
			}
1150
			start = end;
L
Linus Torvalds 已提交
1151 1152 1153 1154 1155 1156 1157 1158 1159
		}
	}
	if (!len)
		return 0;

fault:
	return -EFAULT;
}

J
Jens Axboe 已提交
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
/*
 * Callback from splice_to_pipe(), if we need to release some pages
 * at the end of the spd in case we error'ed out in filling the pipe.
 */
static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i)
{
	struct sk_buff *skb = (struct sk_buff *) spd->partial[i].private;

	kfree_skb(skb);
}

/*
 * Fill page/offset/length into spd, if it can hold more pages.
 */
static inline int spd_fill_page(struct splice_pipe_desc *spd, struct page *page,
				unsigned int len, unsigned int offset,
				struct sk_buff *skb)
{
	if (unlikely(spd->nr_pages == PIPE_BUFFERS))
		return 1;

	spd->pages[spd->nr_pages] = page;
	spd->partial[spd->nr_pages].len = len;
	spd->partial[spd->nr_pages].offset = offset;
	spd->partial[spd->nr_pages].private = (unsigned long) skb_get(skb);
	spd->nr_pages++;
	return 0;
}

/*
 * Map linear and fragment data from the skb to spd. Returns number of
 * pages mapped.
 */
static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset,
			     unsigned int *total_len,
			     struct splice_pipe_desc *spd)
{
	unsigned int nr_pages = spd->nr_pages;
	unsigned int poff, plen, len, toff, tlen;
	int headlen, seg;

	toff = *offset;
	tlen = *total_len;
	if (!tlen)
		goto err;

	/*
	 * if the offset is greater than the linear part, go directly to
	 * the fragments.
	 */
	headlen = skb_headlen(skb);
	if (toff >= headlen) {
		toff -= headlen;
		goto map_frag;
	}

	/*
	 * first map the linear region into the pages/partial map, skipping
	 * any potential initial offset.
	 */
	len = 0;
	while (len < headlen) {
		void *p = skb->data + len;

		poff = (unsigned long) p & (PAGE_SIZE - 1);
		plen = min_t(unsigned int, headlen - len, PAGE_SIZE - poff);
		len += plen;

		if (toff) {
			if (plen <= toff) {
				toff -= plen;
				continue;
			}
			plen -= toff;
			poff += toff;
			toff = 0;
		}

		plen = min(plen, tlen);
		if (!plen)
			break;

		/*
		 * just jump directly to update and return, no point
		 * in going over fragments when the output is full.
		 */
		if (spd_fill_page(spd, virt_to_page(p), plen, poff, skb))
			goto done;

		tlen -= plen;
	}

	/*
	 * then map the fragments
	 */
map_frag:
	for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) {
		const skb_frag_t *f = &skb_shinfo(skb)->frags[seg];

		plen = f->size;
		poff = f->page_offset;

		if (toff) {
			if (plen <= toff) {
				toff -= plen;
				continue;
			}
			plen -= toff;
			poff += toff;
			toff = 0;
		}

		plen = min(plen, tlen);
		if (!plen)
			break;

		if (spd_fill_page(spd, f->page, plen, poff, skb))
			break;

		tlen -= plen;
	}

done:
	if (spd->nr_pages - nr_pages) {
		*offset = 0;
		*total_len = tlen;
		return 0;
	}
err:
	return 1;
}

/*
 * Map data from the skb to a pipe. Should handle both the linear part,
 * the fragments, and the frag list. It does NOT handle frag lists within
 * the frag list, if such a thing exists. We'd probably need to recurse to
 * handle that cleanly.
 */
int skb_splice_bits(struct sk_buff *__skb, unsigned int offset,
		    struct pipe_inode_info *pipe, unsigned int tlen,
		    unsigned int flags)
{
	struct partial_page partial[PIPE_BUFFERS];
	struct page *pages[PIPE_BUFFERS];
	struct splice_pipe_desc spd = {
		.pages = pages,
		.partial = partial,
		.flags = flags,
		.ops = &sock_pipe_buf_ops,
		.spd_release = sock_spd_release,
	};
	struct sk_buff *skb;

	/*
	 * I'd love to avoid the clone here, but tcp_read_sock()
	 * ignores reference counts and unconditonally kills the sk_buff
	 * on return from the actor.
	 */
	skb = skb_clone(__skb, GFP_KERNEL);
	if (unlikely(!skb))
		return -ENOMEM;

	/*
	 * __skb_splice_bits() only fails if the output has no room left,
	 * so no point in going over the frag_list for the error case.
	 */
	if (__skb_splice_bits(skb, &offset, &tlen, &spd))
		goto done;
	else if (!tlen)
		goto done;

	/*
	 * now see if we have a frag_list to map
	 */
	if (skb_shinfo(skb)->frag_list) {
		struct sk_buff *list = skb_shinfo(skb)->frag_list;

		for (; list && tlen; list = list->next) {
			if (__skb_splice_bits(list, &offset, &tlen, &spd))
				break;
		}
	}

done:
	/*
	 * drop our reference to the clone, the pipe consumption will
	 * drop the rest.
	 */
	kfree_skb(skb);

	if (spd.nr_pages) {
		int ret;

		/*
		 * Drop the socket lock, otherwise we have reverse
		 * locking dependencies between sk_lock and i_mutex
		 * here as compared to sendfile(). We enter here
		 * with the socket lock held, and splice_to_pipe() will
		 * grab the pipe inode lock. For sendfile() emulation,
		 * we call into ->sendpage() with the i_mutex lock held
		 * and networking will grab the socket lock.
		 */
		release_sock(__skb->sk);
		ret = splice_to_pipe(pipe, &spd);
		lock_sock(__skb->sk);
		return ret;
	}

	return 0;
}

1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382
/**
 *	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.
 */

1383
int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len)
1384 1385
{
	int i, copy;
1386
	int start = skb_headlen(skb);
1387 1388 1389 1390

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

1391
	if ((copy = start - offset) > 0) {
1392 1393
		if (copy > len)
			copy = len;
1394
		skb_copy_to_linear_data_offset(skb, offset, from, copy);
1395 1396 1397 1398 1399 1400 1401 1402
		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];
1403 1404 1405
		int end;

		BUG_TRAP(start <= offset + len);
1406

1407
		end = start + frag->size;
1408 1409 1410 1411 1412 1413 1414
		if ((copy = end - offset) > 0) {
			u8 *vaddr;

			if (copy > len)
				copy = len;

			vaddr = kmap_skb_frag(frag);
1415 1416
			memcpy(vaddr + frag->page_offset + offset - start,
			       from, copy);
1417 1418 1419 1420 1421 1422 1423
			kunmap_skb_frag(vaddr);

			if ((len -= copy) == 0)
				return 0;
			offset += copy;
			from += copy;
		}
1424
		start = end;
1425 1426 1427 1428 1429 1430
	}

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

		for (; list; list = list->next) {
1431
			int end;
1432

1433 1434 1435
			BUG_TRAP(start <= offset + len);

			end = start + list->len;
1436 1437 1438
			if ((copy = end - offset) > 0) {
				if (copy > len)
					copy = len;
1439 1440
				if (skb_store_bits(list, offset - start,
						   from, copy))
1441 1442 1443 1444 1445 1446
					goto fault;
				if ((len -= copy) == 0)
					return 0;
				offset += copy;
				from += copy;
			}
1447
			start = end;
1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458
		}
	}
	if (!len)
		return 0;

fault:
	return -EFAULT;
}

EXPORT_SYMBOL(skb_store_bits);

L
Linus Torvalds 已提交
1459 1460
/* Checksum skb data. */

1461 1462
__wsum skb_checksum(const struct sk_buff *skb, int offset,
			  int len, __wsum csum)
L
Linus Torvalds 已提交
1463
{
1464 1465
	int start = skb_headlen(skb);
	int i, copy = start - offset;
L
Linus Torvalds 已提交
1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479
	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++) {
1480 1481 1482
		int end;

		BUG_TRAP(start <= offset + len);
L
Linus Torvalds 已提交
1483

1484
		end = start + skb_shinfo(skb)->frags[i].size;
L
Linus Torvalds 已提交
1485
		if ((copy = end - offset) > 0) {
1486
			__wsum csum2;
L
Linus Torvalds 已提交
1487 1488 1489 1490 1491 1492
			u8 *vaddr;
			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];

			if (copy > len)
				copy = len;
			vaddr = kmap_skb_frag(frag);
1493 1494
			csum2 = csum_partial(vaddr + frag->page_offset +
					     offset - start, copy, 0);
L
Linus Torvalds 已提交
1495 1496 1497 1498 1499 1500 1501
			kunmap_skb_frag(vaddr);
			csum = csum_block_add(csum, csum2, pos);
			if (!(len -= copy))
				return csum;
			offset += copy;
			pos    += copy;
		}
1502
		start = end;
L
Linus Torvalds 已提交
1503 1504 1505 1506 1507 1508
	}

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

		for (; list; list = list->next) {
1509
			int end;
L
Linus Torvalds 已提交
1510

1511 1512 1513
			BUG_TRAP(start <= offset + len);

			end = start + list->len;
L
Linus Torvalds 已提交
1514
			if ((copy = end - offset) > 0) {
1515
				__wsum csum2;
L
Linus Torvalds 已提交
1516 1517
				if (copy > len)
					copy = len;
1518 1519
				csum2 = skb_checksum(list, offset - start,
						     copy, 0);
L
Linus Torvalds 已提交
1520 1521 1522 1523 1524 1525
				csum = csum_block_add(csum, csum2, pos);
				if ((len -= copy) == 0)
					return csum;
				offset += copy;
				pos    += copy;
			}
1526
			start = end;
L
Linus Torvalds 已提交
1527 1528
		}
	}
1529
	BUG_ON(len);
L
Linus Torvalds 已提交
1530 1531 1532 1533 1534 1535

	return csum;
}

/* Both of above in one bottle. */

1536 1537
__wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
				    u8 *to, int len, __wsum csum)
L
Linus Torvalds 已提交
1538
{
1539 1540
	int start = skb_headlen(skb);
	int i, copy = start - offset;
L
Linus Torvalds 已提交
1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556
	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++) {
1557 1558 1559
		int end;

		BUG_TRAP(start <= offset + len);
L
Linus Torvalds 已提交
1560

1561
		end = start + skb_shinfo(skb)->frags[i].size;
L
Linus Torvalds 已提交
1562
		if ((copy = end - offset) > 0) {
1563
			__wsum csum2;
L
Linus Torvalds 已提交
1564 1565 1566 1567 1568 1569 1570
			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 +
1571 1572 1573
							  frag->page_offset +
							  offset - start, to,
							  copy, 0);
L
Linus Torvalds 已提交
1574 1575 1576 1577 1578 1579 1580 1581
			kunmap_skb_frag(vaddr);
			csum = csum_block_add(csum, csum2, pos);
			if (!(len -= copy))
				return csum;
			offset += copy;
			to     += copy;
			pos    += copy;
		}
1582
		start = end;
L
Linus Torvalds 已提交
1583 1584 1585 1586 1587 1588
	}

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

		for (; list; list = list->next) {
1589
			__wsum csum2;
1590 1591 1592
			int end;

			BUG_TRAP(start <= offset + len);
L
Linus Torvalds 已提交
1593

1594
			end = start + list->len;
L
Linus Torvalds 已提交
1595 1596 1597
			if ((copy = end - offset) > 0) {
				if (copy > len)
					copy = len;
1598 1599
				csum2 = skb_copy_and_csum_bits(list,
							       offset - start,
L
Linus Torvalds 已提交
1600 1601 1602 1603 1604 1605 1606 1607
							       to, copy, 0);
				csum = csum_block_add(csum, csum2, pos);
				if ((len -= copy) == 0)
					return csum;
				offset += copy;
				to     += copy;
				pos    += copy;
			}
1608
			start = end;
L
Linus Torvalds 已提交
1609 1610
		}
	}
1611
	BUG_ON(len);
L
Linus Torvalds 已提交
1612 1613 1614 1615 1616
	return csum;
}

void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to)
{
1617
	__wsum csum;
L
Linus Torvalds 已提交
1618 1619
	long csstart;

1620
	if (skb->ip_summed == CHECKSUM_PARTIAL)
1621
		csstart = skb->csum_start - skb_headroom(skb);
L
Linus Torvalds 已提交
1622 1623 1624
	else
		csstart = skb_headlen(skb);

1625
	BUG_ON(csstart > skb_headlen(skb));
L
Linus Torvalds 已提交
1626

1627
	skb_copy_from_linear_data(skb, to, csstart);
L
Linus Torvalds 已提交
1628 1629 1630 1631 1632 1633

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

1634
	if (skb->ip_summed == CHECKSUM_PARTIAL) {
A
Al Viro 已提交
1635
		long csstuff = csstart + skb->csum_offset;
L
Linus Torvalds 已提交
1636

1637
		*((__sum16 *)(to + csstuff)) = csum_fold(csum);
L
Linus Torvalds 已提交
1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 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 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733
	}
}

/**
 *	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
1734

L
Linus Torvalds 已提交
1735 1736 1737
/**
 *	skb_unlink	-	remove a buffer from a list
 *	@skb: buffer to remove
D
David S. Miller 已提交
1738
 *	@list: list to use
L
Linus Torvalds 已提交
1739
 *
D
David S. Miller 已提交
1740 1741
 *	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
1742
 *
D
David S. Miller 已提交
1743
 *	You must know what list the SKB is on.
L
Linus Torvalds 已提交
1744
 */
D
David S. Miller 已提交
1745
void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list)
L
Linus Torvalds 已提交
1746
{
D
David S. Miller 已提交
1747
	unsigned long flags;
L
Linus Torvalds 已提交
1748

D
David S. Miller 已提交
1749 1750 1751
	spin_lock_irqsave(&list->lock, flags);
	__skb_unlink(skb, list);
	spin_unlock_irqrestore(&list->lock, flags);
L
Linus Torvalds 已提交
1752 1753 1754 1755 1756 1757
}

/**
 *	skb_append	-	append a buffer
 *	@old: buffer to insert after
 *	@newsk: buffer to insert
D
David S. Miller 已提交
1758
 *	@list: list to use
L
Linus Torvalds 已提交
1759 1760 1761 1762 1763
 *
 *	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
1764
void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list)
L
Linus Torvalds 已提交
1765 1766 1767
{
	unsigned long flags;

D
David S. Miller 已提交
1768 1769 1770
	spin_lock_irqsave(&list->lock, flags);
	__skb_append(old, newsk, list);
	spin_unlock_irqrestore(&list->lock, flags);
L
Linus Torvalds 已提交
1771 1772 1773 1774 1775 1776 1777
}


/**
 *	skb_insert	-	insert a buffer
 *	@old: buffer to insert before
 *	@newsk: buffer to insert
D
David S. Miller 已提交
1778 1779 1780 1781 1782
 *	@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
1783 1784 1785
 *
 *	A buffer cannot be placed on two lists at the same time.
 */
D
David S. Miller 已提交
1786
void skb_insert(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list)
L
Linus Torvalds 已提交
1787 1788 1789
{
	unsigned long flags;

D
David S. Miller 已提交
1790 1791 1792
	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
1793 1794 1795 1796 1797 1798 1799 1800
}

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

1801 1802
	skb_copy_from_linear_data_offset(skb, len, skb_put(skb1, pos - len),
					 pos - len);
L
Linus Torvalds 已提交
1803 1804 1805 1806 1807 1808 1809 1810 1811 1812
	/* 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;
1813
	skb_set_tail_pointer(skb, len);
L
Linus Torvalds 已提交
1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872
}

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);
}

1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909
/**
 * 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.
 *
1910
 * Note 1: The size of each block of data returned can be arbitary,
1911 1912 1913
 *       this limitation is the cost for zerocopy seqeuental
 *       reads of potentially non linear data.
 *
1914
 * Note 2: Fragment lists within fragments are not implemented
1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960
 *       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;
	}

1961 1962 1963 1964 1965
	if (st->frag_data) {
		kunmap_skb_frag(st->frag_data);
		st->frag_data = NULL;
	}

1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991
	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);
}

1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022
#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)
{
2023 2024
	unsigned int ret;

2025 2026 2027 2028 2029
	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));

2030 2031
	ret = textsearch_find(config, state);
	return (ret <= to - from ? ret : UINT_MAX);
2032 2033
}

2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045
/**
 * skb_append_datato_frags: - append the user data to a skb
 * @sk: sock  structure
 * @skb: skb structure to be appened with user data.
 * @getfrag: call back function to be used for getting the user data
 * @from: pointer to user message iov
 * @length: length of the iov message
 *
 * Description: This procedure append the user data in the fragment part
 * of the skb if any page alloc fails user this procedure returns  -ENOMEM
 */
int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb,
2046
			int (*getfrag)(void *from, char *to, int offset,
2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105
					int len, int odd, struct sk_buff *skb),
			void *from, int length)
{
	int frg_cnt = 0;
	skb_frag_t *frag = NULL;
	struct page *page = NULL;
	int copy, left;
	int offset = 0;
	int ret;

	do {
		/* Return error if we don't have space for new frag */
		frg_cnt = skb_shinfo(skb)->nr_frags;
		if (frg_cnt >= MAX_SKB_FRAGS)
			return -EFAULT;

		/* allocate a new page for next frag */
		page = alloc_pages(sk->sk_allocation, 0);

		/* If alloc_page fails just return failure and caller will
		 * free previous allocated pages by doing kfree_skb()
		 */
		if (page == NULL)
			return -ENOMEM;

		/* initialize the next frag */
		sk->sk_sndmsg_page = page;
		sk->sk_sndmsg_off = 0;
		skb_fill_page_desc(skb, frg_cnt, page, 0, 0);
		skb->truesize += PAGE_SIZE;
		atomic_add(PAGE_SIZE, &sk->sk_wmem_alloc);

		/* get the new initialized frag */
		frg_cnt = skb_shinfo(skb)->nr_frags;
		frag = &skb_shinfo(skb)->frags[frg_cnt - 1];

		/* copy the user data to page */
		left = PAGE_SIZE - frag->page_offset;
		copy = (length > left)? left : length;

		ret = getfrag(from, (page_address(frag->page) +
			    frag->page_offset + frag->size),
			    offset, copy, 0, skb);
		if (ret < 0)
			return -EFAULT;

		/* copy was successful so update the size parameters */
		sk->sk_sndmsg_off += copy;
		frag->size += copy;
		skb->len += copy;
		skb->data_len += copy;
		offset += copy;
		length -= copy;

	} while (length > 0);

	return 0;
}

2106 2107 2108 2109 2110 2111
/**
 *	skb_pull_rcsum - pull skb and update receive checksum
 *	@skb: buffer to update
 *	@len: length of data pulled
 *
 *	This function performs an skb_pull on the packet and updates
2112
 *	the CHECKSUM_COMPLETE checksum.  It should be used on
2113 2114 2115
 *	receive path processing instead of skb_pull unless you know
 *	that the checksum difference is zero (e.g., a valid IP header)
 *	or you are setting ip_summed to CHECKSUM_NONE.
2116 2117 2118 2119 2120 2121 2122 2123 2124 2125
 */
unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len)
{
	BUG_ON(len > skb->len);
	skb->len -= len;
	BUG_ON(skb->len < skb->data_len);
	skb_postpull_rcsum(skb, skb->data, len);
	return skb->data += len;
}

2126 2127
EXPORT_SYMBOL_GPL(skb_pull_rcsum);

H
Herbert Xu 已提交
2128 2129 2130
/**
 *	skb_segment - Perform protocol segmentation on skb.
 *	@skb: buffer to segment
2131
 *	@features: features for the output path (see dev->features)
H
Herbert Xu 已提交
2132 2133 2134 2135 2136
 *
 *	This function performs segmentation on the given skb.  It returns
 *	the segment at the given position.  It returns NULL if there are
 *	no more segments to generate, or when an error is encountered.
 */
2137
struct sk_buff *skb_segment(struct sk_buff *skb, int features)
H
Herbert Xu 已提交
2138 2139 2140 2141
{
	struct sk_buff *segs = NULL;
	struct sk_buff *tail = NULL;
	unsigned int mss = skb_shinfo(skb)->gso_size;
2142
	unsigned int doffset = skb->data - skb_mac_header(skb);
H
Herbert Xu 已提交
2143 2144 2145
	unsigned int offset = doffset;
	unsigned int headroom;
	unsigned int len;
2146
	int sg = features & NETIF_F_SG;
H
Herbert Xu 已提交
2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158
	int nfrags = skb_shinfo(skb)->nr_frags;
	int err = -ENOMEM;
	int i = 0;
	int pos;

	__skb_push(skb, doffset);
	headroom = skb_headroom(skb);
	pos = skb_headlen(skb);

	do {
		struct sk_buff *nskb;
		skb_frag_t *frag;
2159
		int hsize;
H
Herbert Xu 已提交
2160 2161 2162 2163 2164 2165 2166 2167 2168 2169
		int k;
		int size;

		len = skb->len - offset;
		if (len > mss)
			len = mss;

		hsize = skb_headlen(skb) - offset;
		if (hsize < 0)
			hsize = 0;
2170 2171
		if (hsize > len || !sg)
			hsize = len;
H
Herbert Xu 已提交
2172

2173
		nskb = alloc_skb(hsize + doffset + headroom, GFP_ATOMIC);
H
Herbert Xu 已提交
2174 2175 2176 2177 2178 2179 2180 2181 2182 2183
		if (unlikely(!nskb))
			goto err;

		if (segs)
			tail->next = nskb;
		else
			segs = nskb;
		tail = nskb;

		nskb->dev = skb->dev;
2184
		skb_copy_queue_mapping(nskb, skb);
H
Herbert Xu 已提交
2185 2186 2187 2188 2189 2190 2191 2192
		nskb->priority = skb->priority;
		nskb->protocol = skb->protocol;
		nskb->dst = dst_clone(skb->dst);
		memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
		nskb->pkt_type = skb->pkt_type;
		nskb->mac_len = skb->mac_len;

		skb_reserve(nskb, headroom);
2193
		skb_reset_mac_header(nskb);
2194
		skb_set_network_header(nskb, skb->mac_len);
2195 2196
		nskb->transport_header = (nskb->network_header +
					  skb_network_header_len(skb));
2197 2198
		skb_copy_from_linear_data(skb, skb_put(nskb, doffset),
					  doffset);
H
Herbert Xu 已提交
2199 2200 2201 2202 2203 2204 2205 2206 2207 2208
		if (!sg) {
			nskb->csum = skb_copy_and_csum_bits(skb, offset,
							    skb_put(nskb, len),
							    len, 0);
			continue;
		}

		frag = skb_shinfo(nskb)->frags;
		k = 0;

2209
		nskb->ip_summed = CHECKSUM_PARTIAL;
H
Herbert Xu 已提交
2210
		nskb->csum = skb->csum;
2211 2212
		skb_copy_from_linear_data_offset(skb, offset,
						 skb_put(nskb, hsize), hsize);
H
Herbert Xu 已提交
2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249

		while (pos < offset + len) {
			BUG_ON(i >= nfrags);

			*frag = skb_shinfo(skb)->frags[i];
			get_page(frag->page);
			size = frag->size;

			if (pos < offset) {
				frag->page_offset += offset - pos;
				frag->size -= offset - pos;
			}

			k++;

			if (pos + size <= offset + len) {
				i++;
				pos += size;
			} else {
				frag->size -= pos + size - (offset + len);
				break;
			}

			frag++;
		}

		skb_shinfo(nskb)->nr_frags = k;
		nskb->data_len = len - hsize;
		nskb->len += nskb->data_len;
		nskb->truesize += nskb->data_len;
	} while ((offset += len) < skb->len);

	return segs;

err:
	while ((skb = segs)) {
		segs = skb->next;
P
Patrick McHardy 已提交
2250
		kfree_skb(skb);
H
Herbert Xu 已提交
2251 2252 2253 2254 2255 2256
	}
	return ERR_PTR(err);
}

EXPORT_SYMBOL_GPL(skb_segment);

L
Linus Torvalds 已提交
2257 2258 2259 2260 2261
void __init skb_init(void)
{
	skbuff_head_cache = kmem_cache_create("skbuff_head_cache",
					      sizeof(struct sk_buff),
					      0,
A
Alexey Dobriyan 已提交
2262
					      SLAB_HWCACHE_ALIGN|SLAB_PANIC,
2263
					      NULL);
2264 2265 2266 2267
	skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache",
						(2*sizeof(struct sk_buff)) +
						sizeof(atomic_t),
						0,
A
Alexey Dobriyan 已提交
2268
						SLAB_HWCACHE_ALIGN|SLAB_PANIC,
2269
						NULL);
L
Linus Torvalds 已提交
2270 2271
}

2272 2273 2274 2275 2276 2277 2278 2279 2280 2281
/**
 *	skb_to_sgvec - Fill a scatter-gather list from a socket buffer
 *	@skb: Socket buffer containing the buffers to be mapped
 *	@sg: The scatter-gather list to map into
 *	@offset: The offset into the buffer's contents to start mapping
 *	@len: Length of buffer space to be mapped
 *
 *	Fill the specified scatter-gather list with mappings/pointers into a
 *	region of the buffer space attached to a socket buffer.
 */
2282 2283
static int
__skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
2284
{
2285 2286
	int start = skb_headlen(skb);
	int i, copy = start - offset;
2287 2288 2289 2290 2291
	int elt = 0;

	if (copy > 0) {
		if (copy > len)
			copy = len;
2292
		sg_set_buf(sg, skb->data + offset, copy);
2293 2294 2295 2296 2297 2298 2299
		elt++;
		if ((len -= copy) == 0)
			return elt;
		offset += copy;
	}

	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
2300
		int end;
2301

2302 2303 2304
		BUG_TRAP(start <= offset + len);

		end = start + skb_shinfo(skb)->frags[i].size;
2305 2306 2307 2308 2309
		if ((copy = end - offset) > 0) {
			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];

			if (copy > len)
				copy = len;
2310 2311
			sg_set_page(&sg[elt], frag->page, copy,
					frag->page_offset+offset-start);
2312 2313 2314 2315 2316
			elt++;
			if (!(len -= copy))
				return elt;
			offset += copy;
		}
2317
		start = end;
2318 2319 2320 2321 2322 2323
	}

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

		for (; list; list = list->next) {
2324 2325 2326
			int end;

			BUG_TRAP(start <= offset + len);
2327

2328
			end = start + list->len;
2329 2330 2331
			if ((copy = end - offset) > 0) {
				if (copy > len)
					copy = len;
2332 2333
				elt += __skb_to_sgvec(list, sg+elt, offset - start,
						      copy);
2334 2335 2336 2337
				if ((len -= copy) == 0)
					return elt;
				offset += copy;
			}
2338
			start = end;
2339 2340 2341 2342 2343 2344
		}
	}
	BUG_ON(len);
	return elt;
}

2345 2346 2347 2348
int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
{
	int nsg = __skb_to_sgvec(skb, sg, offset, len);

J
Jens Axboe 已提交
2349
	sg_mark_end(&sg[nsg - 1]);
2350 2351 2352 2353

	return nsg;
}

2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462
/**
 *	skb_cow_data - Check that a socket buffer's data buffers are writable
 *	@skb: The socket buffer to check.
 *	@tailbits: Amount of trailing space to be added
 *	@trailer: Returned pointer to the skb where the @tailbits space begins
 *
 *	Make sure that the data buffers attached to a socket buffer are
 *	writable. If they are not, private copies are made of the data buffers
 *	and the socket buffer is set to use these instead.
 *
 *	If @tailbits is given, make sure that there is space to write @tailbits
 *	bytes of data beyond current end of socket buffer.  @trailer will be
 *	set to point to the skb in which this space begins.
 *
 *	The number of scatterlist elements required to completely map the
 *	COW'd and extended socket buffer will be returned.
 */
int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer)
{
	int copyflag;
	int elt;
	struct sk_buff *skb1, **skb_p;

	/* If skb is cloned or its head is paged, reallocate
	 * head pulling out all the pages (pages are considered not writable
	 * at the moment even if they are anonymous).
	 */
	if ((skb_cloned(skb) || skb_shinfo(skb)->nr_frags) &&
	    __pskb_pull_tail(skb, skb_pagelen(skb)-skb_headlen(skb)) == NULL)
		return -ENOMEM;

	/* Easy case. Most of packets will go this way. */
	if (!skb_shinfo(skb)->frag_list) {
		/* A little of trouble, not enough of space for trailer.
		 * This should not happen, when stack is tuned to generate
		 * good frames. OK, on miss we reallocate and reserve even more
		 * space, 128 bytes is fair. */

		if (skb_tailroom(skb) < tailbits &&
		    pskb_expand_head(skb, 0, tailbits-skb_tailroom(skb)+128, GFP_ATOMIC))
			return -ENOMEM;

		/* Voila! */
		*trailer = skb;
		return 1;
	}

	/* Misery. We are in troubles, going to mincer fragments... */

	elt = 1;
	skb_p = &skb_shinfo(skb)->frag_list;
	copyflag = 0;

	while ((skb1 = *skb_p) != NULL) {
		int ntail = 0;

		/* The fragment is partially pulled by someone,
		 * this can happen on input. Copy it and everything
		 * after it. */

		if (skb_shared(skb1))
			copyflag = 1;

		/* If the skb is the last, worry about trailer. */

		if (skb1->next == NULL && tailbits) {
			if (skb_shinfo(skb1)->nr_frags ||
			    skb_shinfo(skb1)->frag_list ||
			    skb_tailroom(skb1) < tailbits)
				ntail = tailbits + 128;
		}

		if (copyflag ||
		    skb_cloned(skb1) ||
		    ntail ||
		    skb_shinfo(skb1)->nr_frags ||
		    skb_shinfo(skb1)->frag_list) {
			struct sk_buff *skb2;

			/* Fuck, we are miserable poor guys... */
			if (ntail == 0)
				skb2 = skb_copy(skb1, GFP_ATOMIC);
			else
				skb2 = skb_copy_expand(skb1,
						       skb_headroom(skb1),
						       ntail,
						       GFP_ATOMIC);
			if (unlikely(skb2 == NULL))
				return -ENOMEM;

			if (skb1->sk)
				skb_set_owner_w(skb2, skb1->sk);

			/* Looking around. Are we still alive?
			 * OK, link new skb, drop old one */

			skb2->next = skb1->next;
			*skb_p = skb2;
			kfree_skb(skb1);
			skb1 = skb2;
		}
		elt++;
		*trailer = skb1;
		skb_p = &skb1->next;
	}

	return elt;
}

2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490
/**
 * skb_partial_csum_set - set up and verify partial csum values for packet
 * @skb: the skb to set
 * @start: the number of bytes after skb->data to start checksumming.
 * @off: the offset from start to place the checksum.
 *
 * For untrusted partially-checksummed packets, we need to make sure the values
 * for skb->csum_start and skb->csum_offset are valid so we don't oops.
 *
 * This function checks and sets those values and skb->ip_summed: if this
 * returns false you should drop the packet.
 */
bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off)
{
	if (unlikely(start > skb->len - 2) ||
	    unlikely((int)start + off > skb->len - 2)) {
		if (net_ratelimit())
			printk(KERN_WARNING
			       "bad partial csum: csum=%u/%u len=%u\n",
			       start, off, skb->len);
		return false;
	}
	skb->ip_summed = CHECKSUM_PARTIAL;
	skb->csum_start = skb_headroom(skb) + start;
	skb->csum_offset = off;
	return true;
}

L
Linus Torvalds 已提交
2491 2492
EXPORT_SYMBOL(___pskb_trim);
EXPORT_SYMBOL(__kfree_skb);
2493
EXPORT_SYMBOL(kfree_skb);
L
Linus Torvalds 已提交
2494
EXPORT_SYMBOL(__pskb_pull_tail);
2495
EXPORT_SYMBOL(__alloc_skb);
2496
EXPORT_SYMBOL(__netdev_alloc_skb);
L
Linus Torvalds 已提交
2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518
EXPORT_SYMBOL(pskb_copy);
EXPORT_SYMBOL(pskb_expand_head);
EXPORT_SYMBOL(skb_checksum);
EXPORT_SYMBOL(skb_clone);
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);
2519 2520 2521
EXPORT_SYMBOL(skb_prepare_seq_read);
EXPORT_SYMBOL(skb_seq_read);
EXPORT_SYMBOL(skb_abort_seq_read);
2522
EXPORT_SYMBOL(skb_find_text);
2523
EXPORT_SYMBOL(skb_append_datato_frags);
2524 2525 2526

EXPORT_SYMBOL_GPL(skb_to_sgvec);
EXPORT_SYMBOL_GPL(skb_cow_data);
2527
EXPORT_SYMBOL_GPL(skb_partial_csum_set);