skbuff.c 74.6 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1 2 3
/*
 *	Routines having to do with the 'struct sk_buff' memory handlers.
 *
4
 *	Authors:	Alan Cox <alan@lxorguk.ukuu.org.uk>
Linus Torvalds's avatar
Linus Torvalds committed
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
 *			Florian La Roche <rzsfl@rz.uni-sb.de>
 *
 *	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>
42
#include <linux/kmemcheck.h>
Linus Torvalds's avatar
Linus Torvalds committed
43 44 45 46 47 48 49 50 51 52 53
#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>
Jens Axboe's avatar
Jens Axboe committed
54
#include <linux/splice.h>
Linus Torvalds's avatar
Linus Torvalds committed
55 56 57
#include <linux/cache.h>
#include <linux/rtnetlink.h>
#include <linux/init.h>
58
#include <linux/scatterlist.h>
59
#include <linux/errqueue.h>
Linus Torvalds's avatar
Linus Torvalds committed
60 61 62 63 64 65 66 67 68

#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>
69
#include <trace/events/skb.h>
Linus Torvalds's avatar
Linus Torvalds committed
70

71 72
#include "kmap_skb.h"

73 74
static struct kmem_cache *skbuff_head_cache __read_mostly;
static struct kmem_cache *skbuff_fclone_cache __read_mostly;
Linus Torvalds's avatar
Linus Torvalds committed
75

Jens Axboe's avatar
Jens Axboe committed
76 77 78
static void sock_pipe_buf_release(struct pipe_inode_info *pipe,
				  struct pipe_buffer *buf)
{
79
	put_page(buf->page);
Jens Axboe's avatar
Jens Axboe committed
80 81 82 83 84
}

static void sock_pipe_buf_get(struct pipe_inode_info *pipe,
				struct pipe_buffer *buf)
{
85
	get_page(buf->page);
Jens Axboe's avatar
Jens Axboe committed
86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105
}

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,
};

Linus Torvalds's avatar
Linus Torvalds committed
106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121
/*
 *	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)
{
122
	printk(KERN_EMERG "skb_over_panic: text:%p len:%d put:%d head:%p "
123
			  "data:%p tail:%#lx end:%#lx dev:%s\n",
124
	       here, skb->len, sz, skb->head, skb->data,
125
	       (unsigned long)skb->tail, (unsigned long)skb->end,
126
	       skb->dev ? skb->dev->name : "<NULL>");
Linus Torvalds's avatar
Linus Torvalds committed
127 128
	BUG();
}
129
EXPORT_SYMBOL(skb_over_panic);
Linus Torvalds's avatar
Linus Torvalds committed
130 131 132 133 134 135 136 137 138 139 140 141

/**
 *	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)
{
142
	printk(KERN_EMERG "skb_under_panic: text:%p len:%d put:%d head:%p "
143
			  "data:%p tail:%#lx end:%#lx dev:%s\n",
144
	       here, skb->len, sz, skb->head, skb->data,
145
	       (unsigned long)skb->tail, (unsigned long)skb->end,
146
	       skb->dev ? skb->dev->name : "<NULL>");
Linus Torvalds's avatar
Linus Torvalds committed
147 148
	BUG();
}
149
EXPORT_SYMBOL(skb_under_panic);
Linus Torvalds's avatar
Linus Torvalds committed
150 151 152 153 154 155 156 157

/* 	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.
 *
 */

/**
158
 *	__alloc_skb	-	allocate a network buffer
Linus Torvalds's avatar
Linus Torvalds committed
159 160
 *	@size: size to allocate
 *	@gfp_mask: allocation mask
161 162
 *	@fclone: allocate from fclone cache instead of head cache
 *		and allocate a cloned (child) skb
163
 *	@node: numa node to allocate memory on
Linus Torvalds's avatar
Linus Torvalds committed
164 165 166 167 168 169 170 171
 *
 *	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.
 */
172
struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
173
			    int fclone, int node)
Linus Torvalds's avatar
Linus Torvalds committed
174
{
175
	struct kmem_cache *cache;
176
	struct skb_shared_info *shinfo;
Linus Torvalds's avatar
Linus Torvalds committed
177 178 179
	struct sk_buff *skb;
	u8 *data;

180 181
	cache = fclone ? skbuff_fclone_cache : skbuff_head_cache;

Linus Torvalds's avatar
Linus Torvalds committed
182
	/* Get the HEAD */
183
	skb = kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node);
Linus Torvalds's avatar
Linus Torvalds committed
184 185 186 187
	if (!skb)
		goto out;

	size = SKB_DATA_ALIGN(size);
188 189
	data = kmalloc_node_track_caller(size + sizeof(struct skb_shared_info),
			gfp_mask, node);
Linus Torvalds's avatar
Linus Torvalds committed
190 191 192
	if (!data)
		goto nodata;

193
	/*
194 195 196
	 * Only clear those fields we need to clear, not those that we will
	 * actually initialise below. Hence, don't put any more fields after
	 * the tail pointer in struct sk_buff!
197 198
	 */
	memset(skb, 0, offsetof(struct sk_buff, tail));
Linus Torvalds's avatar
Linus Torvalds committed
199 200 201 202
	skb->truesize = size + sizeof(struct sk_buff);
	atomic_set(&skb->users, 1);
	skb->head = data;
	skb->data = data;
203
	skb_reset_tail_pointer(skb);
204
	skb->end = skb->tail + size;
205 206
	kmemcheck_annotate_bitfield(skb, flags1);
	kmemcheck_annotate_bitfield(skb, flags2);
207 208 209 210
#ifdef NET_SKBUFF_DATA_USES_OFFSET
	skb->mac_header = ~0U;
#endif

211 212 213 214
	/* make sure we initialize shinfo sequentially */
	shinfo = skb_shinfo(skb);
	atomic_set(&shinfo->dataref, 1);
	shinfo->nr_frags  = 0;
215 216 217
	shinfo->gso_size = 0;
	shinfo->gso_segs = 0;
	shinfo->gso_type = 0;
218
	shinfo->ip6_frag_id = 0;
219
	shinfo->tx_flags.flags = 0;
220
	skb_frag_list_init(skb);
221
	memset(&shinfo->hwtstamps, 0, sizeof(shinfo->hwtstamps));
222

223 224 225
	if (fclone) {
		struct sk_buff *child = skb + 1;
		atomic_t *fclone_ref = (atomic_t *) (child + 1);
Linus Torvalds's avatar
Linus Torvalds committed
226

227 228
		kmemcheck_annotate_bitfield(child, flags1);
		kmemcheck_annotate_bitfield(child, flags2);
229 230 231 232 233
		skb->fclone = SKB_FCLONE_ORIG;
		atomic_set(fclone_ref, 1);

		child->fclone = SKB_FCLONE_UNAVAILABLE;
	}
Linus Torvalds's avatar
Linus Torvalds committed
234 235 236
out:
	return skb;
nodata:
237
	kmem_cache_free(cache, skb);
Linus Torvalds's avatar
Linus Torvalds committed
238 239 240
	skb = NULL;
	goto out;
}
241
EXPORT_SYMBOL(__alloc_skb);
Linus Torvalds's avatar
Linus Torvalds committed
242

243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258
/**
 *	__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)
{
259
	int node = dev->dev.parent ? dev_to_node(dev->dev.parent) : -1;
260 261
	struct sk_buff *skb;

262
	skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, node);
263
	if (likely(skb)) {
264
		skb_reserve(skb, NET_SKB_PAD);
265 266
		skb->dev = dev;
	}
267 268
	return skb;
}
269
EXPORT_SYMBOL(__netdev_alloc_skb);
Linus Torvalds's avatar
Linus Torvalds committed
270

271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290
struct page *__netdev_alloc_page(struct net_device *dev, gfp_t gfp_mask)
{
	int node = dev->dev.parent ? dev_to_node(dev->dev.parent) : -1;
	struct page *page;

	page = alloc_pages_node(node, gfp_mask, 0);
	return page;
}
EXPORT_SYMBOL(__netdev_alloc_page);

void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
		int size)
{
	skb_fill_page_desc(skb, i, page, off, size);
	skb->len += size;
	skb->data_len += size;
	skb->truesize += size;
}
EXPORT_SYMBOL(skb_add_rx_frag);

291 292 293 294 295 296 297 298 299 300 301 302 303 304
/**
 *	dev_alloc_skb - allocate an skbuff for receiving
 *	@length: length to allocate
 *
 *	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. Although this function
 *	allocates memory it can be called from an interrupt.
 */
struct sk_buff *dev_alloc_skb(unsigned int length)
{
305 306
	/*
	 * There is more code here than it seems:
307
	 * __dev_alloc_skb is an inline
308
	 */
309 310 311 312
	return __dev_alloc_skb(length, GFP_ATOMIC);
}
EXPORT_SYMBOL(dev_alloc_skb);

313
static void skb_drop_list(struct sk_buff **listp)
Linus Torvalds's avatar
Linus Torvalds committed
314
{
315
	struct sk_buff *list = *listp;
Linus Torvalds's avatar
Linus Torvalds committed
316

317
	*listp = NULL;
Linus Torvalds's avatar
Linus Torvalds committed
318 319 320 321 322 323 324 325

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

326 327 328 329 330
static inline void skb_drop_fraglist(struct sk_buff *skb)
{
	skb_drop_list(&skb_shinfo(skb)->frag_list);
}

Linus Torvalds's avatar
Linus Torvalds committed
331 332 333 334
static void skb_clone_fraglist(struct sk_buff *skb)
{
	struct sk_buff *list;

335
	skb_walk_frags(skb, list)
Linus Torvalds's avatar
Linus Torvalds committed
336 337 338
		skb_get(list);
}

339
static void skb_release_data(struct sk_buff *skb)
Linus Torvalds's avatar
Linus Torvalds committed
340 341 342 343 344 345 346 347 348 349
{
	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);
		}

350
		if (skb_has_frags(skb))
Linus Torvalds's avatar
Linus Torvalds committed
351 352 353 354 355 356 357 358 359
			skb_drop_fraglist(skb);

		kfree(skb->head);
	}
}

/*
 *	Free an skbuff by memory without cleaning the state.
 */
360
static void kfree_skbmem(struct sk_buff *skb)
Linus Torvalds's avatar
Linus Torvalds committed
361
{
362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387
	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;
388
	}
Linus Torvalds's avatar
Linus Torvalds committed
389 390
}

391
static void skb_release_head_state(struct sk_buff *skb)
Linus Torvalds's avatar
Linus Torvalds committed
392
{
Eric Dumazet's avatar
Eric Dumazet committed
393
	skb_dst_drop(skb);
Linus Torvalds's avatar
Linus Torvalds committed
394 395 396
#ifdef CONFIG_XFRM
	secpath_put(skb->sp);
#endif
397 398
	if (skb->destructor) {
		WARN_ON(in_irq());
Linus Torvalds's avatar
Linus Torvalds committed
399 400
		skb->destructor(skb);
	}
401
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
402
	nf_conntrack_put(skb->nfct);
403 404
	nf_conntrack_put_reasm(skb->nfct_reasm);
#endif
Linus Torvalds's avatar
Linus Torvalds committed
405 406 407 408 409 410 411 412 413 414
#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
415 416 417 418 419 420
}

/* Free everything but the sk_buff shell. */
static void skb_release_all(struct sk_buff *skb)
{
	skb_release_head_state(skb);
421 422 423 424 425 426 427 428 429 430 431
	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
 */
Linus Torvalds's avatar
Linus Torvalds committed
432

433 434 435
void __kfree_skb(struct sk_buff *skb)
{
	skb_release_all(skb);
Linus Torvalds's avatar
Linus Torvalds committed
436 437
	kfree_skbmem(skb);
}
438
EXPORT_SYMBOL(__kfree_skb);
Linus Torvalds's avatar
Linus Torvalds committed
439

440 441 442 443 444 445 446 447 448 449 450 451 452 453 454
/**
 *	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;
455
	trace_kfree_skb(skb, __builtin_return_address(0));
456 457
	__kfree_skb(skb);
}
458
EXPORT_SYMBOL(kfree_skb);
459

460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479
/**
 *	consume_skb - free an skbuff
 *	@skb: buffer to free
 *
 *	Drop a ref to the buffer and free it if the usage count has hit zero
 *	Functions identically to kfree_skb, but kfree_skb assumes that the frame
 *	is being dropped after a failure and notes that
 */
void consume_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);
}
EXPORT_SYMBOL(consume_skb);

480 481 482 483 484 485 486 487 488 489 490 491
/**
 *	skb_recycle_check - check if skb can be reused for receive
 *	@skb: buffer
 *	@skb_size: minimum receive buffer size
 *
 *	Checks that the skb passed in is not shared or cloned, and
 *	that it is linear and its head portion at least as large as
 *	skb_size so that it can be recycled as a receive buffer.
 *	If these conditions are met, this function does any necessary
 *	reference count dropping and cleans up the skbuff as if it
 *	just came from __alloc_skb().
 */
492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513
int skb_recycle_check(struct sk_buff *skb, int skb_size)
{
	struct skb_shared_info *shinfo;

	if (skb_is_nonlinear(skb) || skb->fclone != SKB_FCLONE_UNAVAILABLE)
		return 0;

	skb_size = SKB_DATA_ALIGN(skb_size + NET_SKB_PAD);
	if (skb_end_pointer(skb) - skb->head < skb_size)
		return 0;

	if (skb_shared(skb) || skb_cloned(skb))
		return 0;

	skb_release_head_state(skb);
	shinfo = skb_shinfo(skb);
	atomic_set(&shinfo->dataref, 1);
	shinfo->nr_frags = 0;
	shinfo->gso_size = 0;
	shinfo->gso_segs = 0;
	shinfo->gso_type = 0;
	shinfo->ip6_frag_id = 0;
514
	shinfo->tx_flags.flags = 0;
515
	skb_frag_list_init(skb);
516
	memset(&shinfo->hwtstamps, 0, sizeof(shinfo->hwtstamps));
517 518 519

	memset(skb, 0, offsetof(struct sk_buff, tail));
	skb->data = skb->head + NET_SKB_PAD;
520
	skb_reset_tail_pointer(skb);
521 522 523 524 525

	return 1;
}
EXPORT_SYMBOL(skb_recycle_check);

526 527 528 529 530 531 532
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;
Eric Dumazet's avatar
Eric Dumazet committed
533
	skb_dst_set(new, dst_clone(skb_dst(old)));
534
#ifdef CONFIG_XFRM
535 536 537
	new->sp			= secpath_get(old->sp);
#endif
	memcpy(new->cb, old->cb, sizeof(old->cb));
538
	new->csum		= old->csum;
539 540 541 542 543 544 545 546 547 548
	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;
549
	new->iif		= old->iif;
550 551 552 553 554 555 556 557 558 559 560
	__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
561 562
	new->vlan_tci		= old->vlan_tci;

563 564 565
	skb_copy_secmark(new, old);
}

566 567 568 569
/*
 * You should not add any new code to this function.  Add it to
 * __copy_skb_header above instead.
 */
Herbert Xu's avatar
Herbert Xu committed
570
static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb)
Linus Torvalds's avatar
Linus Torvalds committed
571 572 573 574 575
{
#define C(x) n->x = skb->x

	n->next = n->prev = NULL;
	n->sk = NULL;
576 577
	__copy_skb_header(n, skb);

Linus Torvalds's avatar
Linus Torvalds committed
578 579
	C(len);
	C(data_len);
580
	C(mac_len);
581
	n->hdr_len = skb->nohdr ? skb_headroom(skb) : skb->hdr_len;
582
	n->cloned = 1;
Linus Torvalds's avatar
Linus Torvalds committed
583 584 585 586
	n->nohdr = 0;
	n->destructor = NULL;
	C(tail);
	C(end);
587 588 589 590
	C(head);
	C(data);
	C(truesize);
	atomic_set(&n->users, 1);
Linus Torvalds's avatar
Linus Torvalds committed
591 592 593 594 595

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

	return n;
Herbert Xu's avatar
Herbert Xu committed
596 597 598 599 600 601 602 603 604 605 606 607 608 609 610
#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)
{
611
	skb_release_all(dst);
Herbert Xu's avatar
Herbert Xu committed
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
	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;
644 645 646

		kmemcheck_annotate_bitfield(n, flags1);
		kmemcheck_annotate_bitfield(n, flags2);
Herbert Xu's avatar
Herbert Xu committed
647 648 649 650
		n->fclone = SKB_FCLONE_UNAVAILABLE;
	}

	return __skb_clone(n, skb);
Linus Torvalds's avatar
Linus Torvalds committed
651
}
652
EXPORT_SYMBOL(skb_clone);
Linus Torvalds's avatar
Linus Torvalds committed
653 654 655

static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
{
656
#ifndef NET_SKBUFF_DATA_USES_OFFSET
Linus Torvalds's avatar
Linus Torvalds committed
657 658 659 660
	/*
	 *	Shift between the two data areas in bytes
	 */
	unsigned long offset = new->data - old->data;
661
#endif
662 663 664

	__copy_skb_header(new, old);

665 666 667 668
#ifndef NET_SKBUFF_DATA_USES_OFFSET
	/* {transport,network,mac}_header are relative to skb->head */
	new->transport_header += offset;
	new->network_header   += offset;
669 670
	if (skb_mac_header_was_set(new))
		new->mac_header	      += offset;
671
#endif
672 673 674
	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;
Linus Torvalds's avatar
Linus Torvalds committed
675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693
}

/**
 *	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.
 */

694
struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
Linus Torvalds's avatar
Linus Torvalds committed
695 696 697 698 699
{
	int headerlen = skb->data - skb->head;
	/*
	 *	Allocate the copy buffer
	 */
700 701 702 703 704 705
	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
Linus Torvalds's avatar
Linus Torvalds committed
706 707 708 709 710 711 712 713 714 715 716 717 718 719
	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;
}
720
EXPORT_SYMBOL(skb_copy);
Linus Torvalds's avatar
Linus Torvalds committed
721 722 723 724 725 726 727 728 729 730 731 732 733 734

/**
 *	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.
 */

735
struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask)
Linus Torvalds's avatar
Linus Torvalds committed
736 737 738 739
{
	/*
	 *	Allocate the copy buffer
	 */
740 741 742 743 744 745
	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
Linus Torvalds's avatar
Linus Torvalds committed
746 747 748 749 750 751 752 753
	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 */
754
	skb_copy_from_linear_data(skb, n->data, n->len);
Linus Torvalds's avatar
Linus Torvalds committed
755

756
	n->truesize += skb->data_len;
Linus Torvalds's avatar
Linus Torvalds committed
757 758 759 760 761 762 763 764 765 766 767 768 769
	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;
	}

770
	if (skb_has_frags(skb)) {
Linus Torvalds's avatar
Linus Torvalds committed
771 772 773 774 775 776 777 778
		skb_shinfo(n)->frag_list = skb_shinfo(skb)->frag_list;
		skb_clone_fraglist(n);
	}

	copy_skb_header(n, skb);
out:
	return n;
}
779
EXPORT_SYMBOL(pskb_copy);
Linus Torvalds's avatar
Linus Torvalds committed
780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796

/**
 *	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.
 */

Victor Fusco's avatar
Victor Fusco committed
797
int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
798
		     gfp_t gfp_mask)
Linus Torvalds's avatar
Linus Torvalds committed
799 800 801
{
	int i;
	u8 *data;
802 803 804
#ifdef NET_SKBUFF_DATA_USES_OFFSET
	int size = nhead + skb->end + ntail;
#else
Linus Torvalds's avatar
Linus Torvalds committed
805
	int size = nhead + (skb->end - skb->head) + ntail;
806
#endif
Linus Torvalds's avatar
Linus Torvalds committed
807 808
	long off;

809 810
	BUG_ON(nhead < 0);

Linus Torvalds's avatar
Linus Torvalds committed
811 812 813 814 815 816 817 818 819 820 821
	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. */
822
#ifdef NET_SKBUFF_DATA_USES_OFFSET
823
	memcpy(data + nhead, skb->head, skb->tail);
824
#else
825
	memcpy(data + nhead, skb->head, skb->tail - skb->head);
826
#endif
827 828
	memcpy(data + size, skb_end_pointer(skb),
	       sizeof(struct skb_shared_info));
Linus Torvalds's avatar
Linus Torvalds committed
829 830 831 832

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

833
	if (skb_has_frags(skb))
Linus Torvalds's avatar
Linus Torvalds committed
834 835 836 837 838 839 840 841
		skb_clone_fraglist(skb);

	skb_release_data(skb);

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

	skb->head     = data;
	skb->data    += off;
842 843
#ifdef NET_SKBUFF_DATA_USES_OFFSET
	skb->end      = size;
844
	off           = nhead;
845 846
#else
	skb->end      = skb->head + size;
847
#endif
848 849
	/* {transport,network,mac}_header and tail are relative to skb->head */
	skb->tail	      += off;
850 851
	skb->transport_header += off;
	skb->network_header   += off;
852 853
	if (skb_mac_header_was_set(skb))
		skb->mac_header += off;
854
	skb->csum_start       += nhead;
Linus Torvalds's avatar
Linus Torvalds committed
855
	skb->cloned   = 0;
856
	skb->hdr_len  = 0;
Linus Torvalds's avatar
Linus Torvalds committed
857 858 859 860 861 862 863
	skb->nohdr    = 0;
	atomic_set(&skb_shinfo(skb)->dataref, 1);
	return 0;

nodata:
	return -ENOMEM;
}
864
EXPORT_SYMBOL(pskb_expand_head);
Linus Torvalds's avatar
Linus Torvalds committed
865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884

/* 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;
}
885
EXPORT_SYMBOL(skb_realloc_headroom);
Linus Torvalds's avatar
Linus Torvalds committed
886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905

/**
 *	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,
Victor Fusco's avatar
Victor Fusco committed
906
				int newheadroom, int newtailroom,
907
				gfp_t gfp_mask)
Linus Torvalds's avatar
Linus Torvalds committed
908 909 910 911 912 913
{
	/*
	 *	Allocate the copy buffer
	 */
	struct sk_buff *n = alloc_skb(newheadroom + skb->len + newtailroom,
				      gfp_mask);
914
	int oldheadroom = skb_headroom(skb);
Linus Torvalds's avatar
Linus Torvalds committed
915
	int head_copy_len, head_copy_off;
916
	int off;
Linus Torvalds's avatar
Linus Torvalds committed
917 918 919 920 921 922 923 924 925

	if (!n)
		return NULL;

	skb_reserve(n, newheadroom);

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

926
	head_copy_len = oldheadroom;
Linus Torvalds's avatar
Linus Torvalds committed
927 928 929 930 931 932 933 934 935 936 937 938 939
	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);

940
	off                  = newheadroom - oldheadroom;
941 942
	n->csum_start       += off;
#ifdef NET_SKBUFF_DATA_USES_OFFSET
943 944
	n->transport_header += off;
	n->network_header   += off;
945 946
	if (skb_mac_header_was_set(skb))
		n->mac_header += off;
947
#endif
948

Linus Torvalds's avatar
Linus Torvalds committed
949 950
	return n;
}
951
EXPORT_SYMBOL(skb_copy_expand);
Linus Torvalds's avatar
Linus Torvalds committed
952 953 954 955 956 957 958 959 960 961

/**
 *	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.
 *
962
 *	May return error in out of memory cases. The skb is freed on error.
Linus Torvalds's avatar
Linus Torvalds committed
963
 */
964

965
int skb_pad(struct sk_buff *skb, int pad)
Linus Torvalds's avatar
Linus Torvalds committed
966
{
967 968
	int err;
	int ntail;
969

Linus Torvalds's avatar
Linus Torvalds committed
970
	/* If the skbuff is non linear tailroom is always zero.. */
971
	if (!skb_cloned(skb) && skb_tailroom(skb) >= pad) {
Linus Torvalds's avatar
Linus Torvalds committed
972
		memset(skb->data+skb->len, 0, pad);
973
		return 0;
Linus Torvalds's avatar
Linus Torvalds committed
974
	}
975

976
	ntail = skb->data_len + pad - (skb->end - skb->tail);
977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993
	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:
Linus Torvalds's avatar
Linus Torvalds committed
994
	kfree_skb(skb);
995
	return err;
996
}
997
EXPORT_SYMBOL(skb_pad);
998

999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019
/**
 *	skb_put - add data to a buffer
 *	@skb: buffer to use
 *	@len: amount of data to add
 *
 *	This function extends the used data area of the buffer. If this would
 *	exceed the total buffer size the kernel will panic. A pointer to the
 *	first byte of the extra data is returned.
 */
unsigned char *skb_put(struct sk_buff *skb, unsigned int len)
{
	unsigned char *tmp = skb_tail_pointer(skb);
	SKB_LINEAR_ASSERT(skb);
	skb->tail += len;
	skb->len  += len;
	if (unlikely(skb->tail > skb->end))
		skb_over_panic(skb, len, __builtin_return_address(0));
	return tmp;
}
EXPORT_SYMBOL(skb_put);

1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038
/**
 *	skb_push - add data to the start of a buffer
 *	@skb: buffer to use
 *	@len: amount of data to add
 *
 *	This function extends the used data area of the buffer at the buffer
 *	start. If this would exceed the total buffer headroom the kernel will
 *	panic. A pointer to the first byte of the extra data is returned.
 */
unsigned char *skb_push(struct sk_buff *skb, unsigned int len)
{
	skb->data -= len;
	skb->len  += len;
	if (unlikely(skb->data<skb->head))
		skb_under_panic(skb, len, __builtin_return_address(0));
	return skb->data;
}
EXPORT_SYMBOL(skb_push);

1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054
/**
 *	skb_pull - remove data from the start of a buffer
 *	@skb: buffer to use
 *	@len: amount of data to remove
 *
 *	This function removes data from the start of a buffer, returning
 *	the memory to the headroom. A pointer to the next data in the buffer
 *	is returned. Once the data has been pulled future pushes will overwrite
 *	the old data.
 */
unsigned char *skb_pull(struct sk_buff *skb, unsigned int len)
{
	return unlikely(len > skb->len) ? NULL : __skb_pull(skb, len);
}
EXPORT_SYMBOL(skb_pull);

1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070
/**
 *	skb_trim - remove end from a buffer
 *	@skb: buffer to alter
 *	@len: new length
 *
 *	Cut the length of a buffer down by removing data from the tail. If
 *	the buffer is already under the length specified it is not modified.
 *	The skb must be linear.
 */
void skb_trim(struct sk_buff *skb, unsigned int len)
{
	if (skb->len > len)
		__skb_trim(skb, len);
}
EXPORT_SYMBOL(skb_trim);

1071
/* Trims skb to length len. It can change skb pointers.
Linus Torvalds's avatar
Linus Torvalds committed
1072 1073
 */

1074
int ___pskb_trim(struct sk_buff *skb, unsigned int len)
Linus Torvalds's avatar
Linus Torvalds committed
1075
{
1076 1077
	struct sk_buff **fragp;
	struct sk_buff *frag;
Linus Torvalds's avatar
Linus Torvalds committed
1078 1079 1080
	int offset = skb_headlen(skb);
	int nfrags = skb_shinfo(skb)->nr_frags;
	int i;
1081 1082 1083 1084 1085
	int err;

	if (skb_cloned(skb) &&
	    unlikely((err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))))
		return err;
Linus Torvalds's avatar
Linus Torvalds committed
1086

1087 1088 1089 1090 1091
	i = 0;
	if (offset >= len)
		goto drop_pages;

	for (; i < nfrags; i++) {
Linus Torvalds's avatar
Linus Torvalds committed
1092
		int end = offset + skb_shinfo(skb)->frags[i].size;
1093 1094 1095 1096 1097 1098

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

1099
		skb_shinfo(skb)->frags[i++].size = len - offset;
1100

1101
drop_pages:
1102 1103 1104 1105 1106
		skb_shinfo(skb)->nr_frags = i;

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

1107
		if (skb_has_frags(skb))
1108
			skb_drop_fraglist(skb);
1109
		goto done;
1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123
	}

	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;
1124
			kfree_skb(frag);
1125 1126
			frag = nfrag;
			*fragp = frag;
Linus Torvalds's avatar
Linus Torvalds committed
1127
		}
1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140

		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;
Linus Torvalds's avatar
Linus Torvalds committed
1141 1142
	}

1143
done:
1144
	if (len > skb_headlen(skb)) {
Linus Torvalds's avatar
Linus Torvalds committed
1145 1146 1147
		skb->data_len -= skb->len - len;
		skb->len       = len;
	} else {
1148 1149
		skb->len       = len;
		skb->data_len  = 0;
1150
		skb_set_tail_pointer(skb, len);
Linus Torvalds's avatar
Linus Torvalds committed
1151 1152 1153 1154
	}

	return 0;
}
1155
EXPORT_SYMBOL(___pskb_trim);
Linus Torvalds's avatar
Linus Torvalds committed
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

/**
 *	__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.
	 */
1188
	int i, k, eat = (skb->tail + delta) - skb->end;
Linus Torvalds's avatar
Linus Torvalds committed
1189 1190 1191 1192 1193 1194 1195

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

1196
	if (skb_copy_bits(skb, skb_headlen(skb), skb_tail_pointer(skb), delta))
Linus Torvalds's avatar
Linus Torvalds committed
1197 1198 1199 1200 1201
		BUG();

	/* Optimization: no fragments, no reasons to preestimate
	 * size of pulled pages. Superb.
	 */
1202
	if (!skb_has_frags(skb))
Linus Torvalds's avatar
Linus Torvalds committed
1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225
		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 {
1226
			BUG_ON(!list);
Linus Torvalds's avatar
Linus Torvalds committed
1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248

			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)) {
1249
					kfree_skb(clone);
Linus Torvalds's avatar
Linus Torvalds committed
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
					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;

1291
	return skb_tail_pointer(skb);
Linus Torvalds's avatar
Linus Torvalds committed
1292
}
1293
EXPORT_SYMBOL(__pskb_pull_tail);
Linus Torvalds's avatar
Linus Torvalds committed
1294 1295 1296 1297 1298

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

int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len)
{
1299
	int start = skb_headlen(skb);
1300 1301
	struct sk_buff *frag_iter;
	int i, copy;
Linus Torvalds's avatar
Linus Torvalds committed
1302 1303 1304 1305 1306

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

	/* Copy header. */
1307
	if ((copy = start - offset) > 0) {
Linus Torvalds's avatar
Linus Torvalds committed
1308 1309
		if (copy > len)
			copy = len;
1310
		skb_copy_from_linear_data_offset(skb, offset, to, copy);
Linus Torvalds's avatar
Linus Torvalds committed
1311 1312 1313 1314 1315 1316 1317
		if ((len -= copy) == 0)
			return 0;
		offset += copy;
		to     += copy;
	}

	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
1318
		int end;
Linus Torvalds's avatar
Linus Torvalds committed
1319

1320
		WARN_ON(start > offset + len);
1321 1322

		end = start + skb_shinfo(skb)->frags[i].size;
Linus Torvalds's avatar
Linus Torvalds committed
1323 1324 1325 1326 1327 1328 1329 1330
		if ((copy = end - offset) > 0) {
			u8 *vaddr;

			if (copy > len)
				copy = len;

			vaddr = kmap_skb_frag(&skb_shinfo(skb)->frags[i]);
			memcpy(to,
1331 1332
			       vaddr + skb_shinfo(skb)->frags[i].page_offset+
			       offset - start, copy);
Linus Torvalds's avatar
Linus Torvalds committed
1333 1334 1335 1336 1337 1338 1339
			kunmap_skb_frag(vaddr);

			if ((len -= copy) == 0)
				return 0;
			offset += copy;
			to     += copy;
		}
1340
		start = end;
Linus Torvalds's avatar
Linus Torvalds committed
1341 1342
	}

1343 1344
	skb_walk_frags(skb, frag_iter) {
		int end;
Linus Torvalds's avatar
Linus Torvalds committed
1345

1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357
		WARN_ON(start > offset + len);

		end = start + frag_iter->len;
		if ((copy = end - offset) > 0) {
			if (copy > len)
				copy = len;
			if (skb_copy_bits(frag_iter, offset - start, to, copy))
				goto fault;
			if ((len -= copy) == 0)
				return 0;
			offset += copy;
			to     += copy;
Linus Torvalds's avatar
Linus Torvalds committed
1358
		}
1359
		start = end;
Linus Torvalds's avatar
Linus Torvalds committed
1360 1361 1362 1363 1364 1365 1366
	}
	if (!len)
		return 0;

fault:
	return -EFAULT;
}
1367
EXPORT_SYMBOL(skb_copy_bits);
Linus Torvalds's avatar
Linus Torvalds committed
1368

Jens Axboe's avatar
Jens Axboe committed
1369 1370 1371 1372 1373 1374
/*
 * 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)
{
1375 1376
	put_page(spd->pages[i]);
}
Jens Axboe's avatar
Jens Axboe committed
1377

1378 1379
static inline struct page *linear_to_page(struct page *page, unsigned int *len,
					  unsigned int *offset,
1380
					  struct sk_buff *skb, struct sock *sk)
1381
{
1382 1383 1384 1385 1386 1387 1388 1389
	struct page *p = sk->sk_sndmsg_page;
	unsigned int off;

	if (!p) {
new_page:
		p = sk->sk_sndmsg_page = alloc_pages(sk->sk_allocation, 0);
		if (!p)
			return NULL;
1390

1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409
		off = sk->sk_sndmsg_off = 0;
		/* hold one ref to this page until it's full */
	} else {
		unsigned int mlen;

		off = sk->sk_sndmsg_off;
		mlen = PAGE_SIZE - off;
		if (mlen < 64 && mlen < *len) {
			put_page(p);
			goto new_page;
		}

		*len = min_t(unsigned int, *len, mlen);
	}

	memcpy(page_address(p) + off, page_address(page) + *offset, *len);
	sk->sk_sndmsg_off += *len;
	*offset = off;
	get_page(p);
1410 1411

	return p;
Jens Axboe's avatar
Jens Axboe committed
1412 1413 1414 1415 1416 1417
}

/*
 * 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,
1418
				unsigned int *len, unsigned int offset,
1419 1420
				struct sk_buff *skb, int linear,
				struct sock *sk)
Jens Axboe's avatar
Jens Axboe committed
1421 1422 1423 1424
{
	if (unlikely(spd->nr_pages == PIPE_BUFFERS))
		return 1;

1425
	if (linear) {
1426
		page = linear_to_page(page, len, &offset, skb, sk);
1427 1428 1429 1430 1431
		if (!page)
			return 1;
	} else
		get_page(page);

Jens Axboe's avatar
Jens Axboe committed
1432
	spd->pages[spd->nr_pages] = page;
1433
	spd->partial[spd->nr_pages].len = *len;
Jens Axboe's avatar
Jens Axboe committed
1434 1435
	spd->partial[spd->nr_pages].offset = offset;
	spd->nr_pages++;
1436

Jens Axboe's avatar
Jens Axboe committed
1437 1438 1439
	return 0;
}

1440 1441 1442
static inline void __segment_seek(struct page **page, unsigned int *poff,
				  unsigned int *plen, unsigned int off)
{
1443 1444
	unsigned long n;

1445
	*poff += off;
1446 1447 1448 1449
	n = *poff / PAGE_SIZE;
	if (n)
		*page = nth_page(*page, n);

1450 1451 1452 1453 1454 1455 1456
	*poff = *poff % PAGE_SIZE;
	*plen -= off;
}

static inline int __splice_segment(struct page *page, unsigned int poff,
				   unsigned int plen, unsigned int *off,
				   unsigned int *len, struct sk_buff *skb,
1457 1458
				   struct splice_pipe_desc *spd, int linear,
				   struct sock *sk)
Jens Axboe's avatar
Jens Axboe committed
1459
{
1460 1461 1462 1463 1464 1465 1466
	if (!*len)
		return 1;

	/* skip this segment if already processed */
	if (*off >= plen) {
		*off -= plen;
		return 0;
1467
	}
Jens Axboe's avatar
Jens Axboe committed
1468

1469 1470 1471 1472
	/* ignore any bits we already processed */
	if (*off) {
		__segment_seek(&page, &poff, &plen, *off);
		*off = 0;
Jens Axboe's avatar
Jens Axboe committed
1473 1474
	}

1475 1476
	do {
		unsigned int flen = min(*len, plen);
Jens Axboe's avatar
Jens Axboe committed
1477

1478 1479
		/* the linear region may spread across several pages  */
		flen = min_t(unsigned int, flen, PAGE_SIZE - poff);
Jens Axboe's avatar
Jens Axboe committed
1480

1481
		if (spd_fill_page(spd, page, &flen, poff, skb, linear, sk))
1482
			return 1;
Jens Axboe's avatar
Jens Axboe committed
1483

1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495
		__segment_seek(&page, &poff, &plen, flen);
		*len -= flen;

	} while (*len && plen);

	return 0;
}

/*
 * Map linear and fragment data from the skb to spd. It reports failure if the
 * pipe is full or if we already spliced the requested length.
 */
1496
static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset,
1497 1498
			     unsigned int *len, struct splice_pipe_desc *spd,
			     struct sock *sk)
1499 1500 1501 1502 1503 1504 1505 1506 1507
{
	int seg;

	/*
	 * map the linear part
	 */
	if (__splice_segment(virt_to_page(skb->data),
			     (unsigned long) skb->data & (PAGE_SIZE - 1),
			     skb_headlen(skb),
1508
			     offset, len, skb, spd, 1, sk))
1509
		return 1;
Jens Axboe's avatar
Jens Axboe committed
1510 1511 1512 1513 1514 1515 1516

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

1517
		if (__splice_segment(f->page, f->page_offset, f->size,
1518
				     offset, len, skb, spd, 0, sk))
1519
			return 1;
Jens Axboe's avatar
Jens Axboe committed
1520 1521
	}

1522
	return 0;
Jens Axboe's avatar
Jens Axboe committed
1523 1524 1525 1526 1527 1528 1529 1530
}

/*
 * 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.
 */
1531
int skb_splice_bits(struct sk_buff *skb, unsigned int offset,
Jens Axboe's avatar
Jens Axboe committed
1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543
		    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,
	};
1544
	struct sk_buff *frag_iter;
1545
	struct sock *sk = skb->sk;
Jens Axboe's avatar
Jens Axboe committed
1546 1547 1548 1549 1550

	/*
	 * __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.
	 */
1551
	if (__skb_splice_bits(skb, &offset, &tlen, &spd, sk))
Jens Axboe's avatar
Jens Axboe committed
1552 1553 1554 1555 1556 1557 1558
		goto done;
	else if (!tlen)
		goto done;

	/*
	 * now see if we have a frag_list to map
	 */
1559 1560 1561 1562 1563
	skb_walk_frags(skb, frag_iter) {
		if (!tlen)
			break;
		if (__skb_splice_bits(frag_iter, &offset, &tlen, &spd, sk))
			break;
Jens Axboe's avatar
Jens Axboe committed
1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578
	}

done:
	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.
		 */
1579
		release_sock(sk);
Jens Axboe's avatar
Jens Axboe committed
1580
		ret = splice_to_pipe(pipe, &spd);
1581
		lock_sock(sk);
Jens Axboe's avatar
Jens Axboe committed
1582 1583 1584 1585 1586 1587
		return ret;
	}

	return 0;
}

1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599
/**
 *	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.
 */

1600
int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len)
1601
{
1602
	int start = skb_headlen(skb);
1603 1604
	struct sk_buff *frag_iter;
	int i, copy;
1605 1606 1607 1608

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

1609
	if ((copy = start - offset) > 0) {
1610 1611
		if (copy > len)
			copy = len;
1612
		skb_copy_to_linear_data_offset(skb, offset, from, copy);
1613 1614 1615 1616 1617 1618 1619 1620
		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];
1621 1622
		int end;

1623
		WARN_ON(start > offset + len);
1624

1625
		end = start + frag->size;
1626 1627 1628 1629 1630 1631 1632
		if ((copy = end - offset) > 0) {
			u8 *vaddr;

			if (copy > len)
				copy = len;

			vaddr = kmap_skb_frag(frag);
1633 1634
			memcpy(vaddr + frag->page_offset + offset - start,
			       from, copy);
1635 1636 1637 1638 1639 1640 1641
			kunmap_skb_frag(vaddr);

			if ((len -= copy) == 0)
				return 0;
			offset += copy;
			from += copy;
		}
1642
		start = end;
1643 1644
	}

1645 1646
	skb_walk_frags(skb, frag_iter) {
		int end;
1647

1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660
		WARN_ON(start > offset + len);

		end = start + frag_iter->len;
		if ((copy = end - offset) > 0) {
			if (copy > len)
				copy = len;
			if (skb_store_bits(frag_iter, offset - start,
					   from, copy))
				goto fault;
			if ((len -= copy) == 0)
				return 0;
			offset += copy;
			from += copy;
1661
		}
1662
		start = end;
1663 1664 1665 1666 1667 1668 1669 1670 1671
	}
	if (!len)
		return 0;

fault:
	return -EFAULT;
}
EXPORT_SYMBOL(skb_store_bits);

Linus Torvalds's avatar
Linus Torvalds committed
1672 1673
/* Checksum skb data. */

1674 1675
__wsum skb_checksum(const struct sk_buff *skb, int offset,
			  int len, __wsum csum)
Linus Torvalds's avatar
Linus Torvalds committed
1676
{
1677 1678
	int start = skb_headlen(skb);
	int i, copy = start - offset;
1679
	struct sk_buff *frag_iter;
Linus Torvalds's avatar
Linus Torvalds committed
1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693
	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++) {
1694 1695
		int end;

1696
		WARN_ON(start > offset + len);
Linus Torvalds's avatar
Linus Torvalds committed
1697

1698
		end = start + skb_shinfo(skb)->frags[i].size;
Linus Torvalds's avatar
Linus Torvalds committed
1699
		if ((copy = end - offset) > 0) {
1700
			__wsum csum2;
Linus Torvalds's avatar
Linus Torvalds committed
1701 1702 1703 1704 1705 1706
			u8 *vaddr;
			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];

			if (copy > len)
				copy = len;
			vaddr = kmap_skb_frag(frag);
1707 1708
			csum2 = csum_partial(vaddr + frag->page_offset +
					     offset - start, copy, 0);
Linus Torvalds's avatar
Linus Torvalds committed
1709 1710 1711 1712 1713 1714 1715
			kunmap_skb_frag(vaddr);
			csum = csum_block_add(csum, csum2, pos);
			if (!(len -= copy))
				return csum;
			offset += copy;
			pos    += copy;
		}
1716
		start = end;
Linus Torvalds's avatar
Linus Torvalds committed
1717 1718
	}

1719 1720
	skb_walk_frags(skb, frag_iter) {
		int end;
Linus Torvalds's avatar
Linus Torvalds committed
1721

1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735
		WARN_ON(start > offset + len);

		end = start + frag_iter->len;
		if ((copy = end - offset) > 0) {
			__wsum csum2;
			if (copy > len)
				copy = len;
			csum2 = skb_checksum(frag_iter, offset - start,
					     copy, 0);
			csum = csum_block_add(csum, csum2, pos);
			if ((len -= copy) == 0)
				return csum;
			offset += copy;
			pos    += copy;
Linus Torvalds's avatar
Linus Torvalds committed
1736
		}
1737
		start = end;
Linus Torvalds's avatar
Linus Torvalds committed
1738
	}
1739
	BUG_ON(len);
Linus Torvalds's avatar
Linus Torvalds committed
1740 1741 1742

	return csum;
}
1743
EXPORT_SYMBOL(skb_checksum);
Linus Torvalds's avatar
Linus Torvalds committed
1744 1745 1746

/* Both of above in one bottle. */

1747 1748
__wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
				    u8 *to, int len, __wsum csum)
Linus Torvalds's avatar
Linus Torvalds committed
1749
{
1750 1751
	int start = skb_headlen(skb);
	int i, copy = start - offset;
1752
	struct sk_buff *frag_iter;
Linus Torvalds's avatar
Linus Torvalds committed
1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768
	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++) {
1769 1770
		int end;

1771
		WARN_ON(start > offset + len);
Linus Torvalds's avatar
Linus Torvalds committed
1772

1773
		end = start + skb_shinfo(skb)->frags[i].size;
Linus Torvalds's avatar
Linus Torvalds committed
1774
		if ((copy = end - offset) > 0) {
1775
			__wsum csum2;
Linus Torvalds's avatar
Linus Torvalds committed
1776 1777 1778 1779 1780 1781 1782
			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 +
1783 1784 1785
							  frag->page_offset +
							  offset - start, to,
							  copy, 0);
Linus Torvalds's avatar
Linus Torvalds committed
1786 1787 1788 1789 1790 1791 1792 1793
			kunmap_skb_frag(vaddr);
			csum = csum_block_add(csum, csum2, pos);
			if (!(len -= copy))
				return csum;
			offset += copy;
			to     += copy;
			pos    += copy;
		}
1794
		start = end;
Linus Torvalds's avatar
Linus Torvalds committed
1795 1796
	}

1797 1798 1799
	skb_walk_frags(skb, frag_iter) {
		__wsum csum2;
		int end;
Linus Torvalds's avatar
Linus Torvalds committed
1800

1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815
		WARN_ON(start > offset + len);

		end = start + frag_iter->len;
		if ((copy = end - offset) > 0) {
			if (copy > len)
				copy = len;
			csum2 = skb_copy_and_csum_bits(frag_iter,
						       offset - start,
						       to, copy, 0);
			csum = csum_block_add(csum, csum2, pos);
			if ((len -= copy) == 0)
				return csum;
			offset += copy;
			to     += copy;
			pos    += copy;
Linus Torvalds's avatar
Linus Torvalds committed
1816
		}
1817
		start = end;
Linus Torvalds's avatar
Linus Torvalds committed
1818
	}
1819
	BUG_ON(len);
Linus Torvalds's avatar
Linus Torvalds committed
1820 1821
	return csum;
}
1822
EXPORT_SYMBOL(skb_copy_and_csum_bits);
Linus Torvalds's avatar
Linus Torvalds committed
1823 1824 1825

void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to)
{
1826
	__wsum csum;
Linus Torvalds's avatar
Linus Torvalds committed
1827 1828
	long csstart;

1829
	if (skb->ip_summed == CHECKSUM_PARTIAL)
1830
		csstart = skb->csum_start - skb_headroom(skb);
Linus Torvalds's avatar
Linus Torvalds committed
1831 1832 1833
	else
		csstart = skb_headlen(skb);

1834
	BUG_ON(csstart > skb_headlen(skb));
Linus Torvalds's avatar
Linus Torvalds committed
1835

1836
	skb_copy_from_linear_data(skb, to, csstart);
Linus Torvalds's avatar
Linus Torvalds committed
1837 1838 1839 1840 1841 1842

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

1843
	if (skb->ip_summed == CHECKSUM_PARTIAL) {
Al Viro's avatar
Al Viro committed
1844
		long csstuff = csstart + skb->csum_offset;
Linus Torvalds's avatar
Linus Torvalds committed
1845

1846
		*((__sum16 *)(to + csstuff)) = csum_fold(csum);
Linus Torvalds's avatar
Linus Torvalds committed
1847 1848
	}
}
1849
EXPORT_SYMBOL(skb_copy_and_csum_dev);
Linus Torvalds's avatar
Linus Torvalds committed
1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869

/**
 *	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;
}
1870
EXPORT_SYMBOL(skb_dequeue);
Linus Torvalds's avatar
Linus Torvalds committed
1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889

/**
 *	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;
}
1890
EXPORT_SYMBOL(skb_dequeue_tail);
Linus Torvalds's avatar
Linus Torvalds committed
1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905

/**
 *	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);
}
1906
EXPORT_SYMBOL(skb_queue_purge);
Linus Torvalds's avatar
Linus Torvalds committed
1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926

/**
 *	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);
}
1927
EXPORT_SYMBOL(skb_queue_head);
Linus Torvalds's avatar
Linus Torvalds committed
1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947

/**
 *	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);
}
1948
EXPORT_SYMBOL(skb_queue_tail);
David S. Miller's avatar
David S. Miller committed
1949

Linus Torvalds's avatar
Linus Torvalds committed
1950 1951 1952
/**
 *	skb_unlink	-	remove a buffer from a list
 *	@skb: buffer to remove
David S. Miller's avatar
David S. Miller committed
1953
 *	@list: list to use
Linus Torvalds's avatar
Linus Torvalds committed
1954
 *
David S. Miller's avatar
David S. Miller committed
1955 1956
 *	Remove a packet from a list. The list locks are taken and this
 *	function is atomic with respect to other list locked calls
Linus Torvalds's avatar
Linus Torvalds committed
1957
 *
David S. Miller's avatar
David S. Miller committed
1958
 *	You must know what list the SKB is on.
Linus Torvalds's avatar
Linus Torvalds committed
1959
 */
David S. Miller's avatar
David S. Miller committed
1960
void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list)
Linus Torvalds's avatar
Linus Torvalds committed
1961
{
David S. Miller's avatar
David S. Miller committed
1962
	unsigned long flags;
Linus Torvalds's avatar
Linus Torvalds committed
1963

David S. Miller's avatar
David S. Miller committed
1964 1965 1966
	spin_lock_irqsave(&list->lock, flags);
	__skb_unlink(skb, list);
	spin_unlock_irqrestore(&list->lock, flags);
Linus Torvalds's avatar
Linus Torvalds committed
1967
}
1968
EXPORT_SYMBOL(skb_unlink);
Linus Torvalds's avatar
Linus Torvalds committed
1969 1970 1971 1972 1973

/**
 *	skb_append	-	append a buffer
 *	@old: buffer to insert after
 *	@newsk: buffer to insert
David S. Miller's avatar
David S. Miller committed
1974
 *	@list: list to use
Linus Torvalds's avatar
Linus Torvalds committed
1975 1976 1977 1978 1979
 *
 *	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.
 */
David S. Miller's avatar
David S. Miller committed
1980
void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list)
Linus Torvalds's avatar
Linus Torvalds committed
1981 1982 1983
{
	unsigned long flags;

David S. Miller's avatar
David S. Miller committed
1984
	spin_lock_irqsave(&list->lock, flags);
1985
	__skb_queue_after(list, old, newsk);
David S. Miller's avatar
David S. Miller committed
1986
	spin_unlock_irqrestore(&list->lock, flags);
Linus Torvalds's avatar
Linus Torvalds committed
1987
}
1988
EXPORT_SYMBOL(skb_append);
Linus Torvalds's avatar
Linus Torvalds committed
1989 1990 1991 1992 1993

/**
 *	skb_insert	-	insert a buffer
 *	@old: buffer to insert before
 *	@newsk: buffer to insert
David S. Miller's avatar
David S. Miller committed
1994 1995 1996 1997 1998
 *	@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.
Linus Torvalds's avatar
Linus Torvalds committed
1999 2000 2001
 *
 *	A buffer cannot be placed on two lists at the same time.
 */
David S. Miller's avatar
David S. Miller committed
2002
void skb_insert(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list)
Linus Torvalds's avatar
Linus Torvalds committed
2003 2004 2005
{
	unsigned long flags;

David S. Miller's avatar
David S. Miller committed
2006 2007 2008
	spin_lock_irqsave(&list->lock, flags);
	__skb_insert(newsk, old->prev, old, list);
	spin_unlock_irqrestore(&list->lock, flags);
Linus Torvalds's avatar
Linus Torvalds committed
2009
}
2010
EXPORT_SYMBOL(skb_insert);
Linus Torvalds's avatar
Linus Torvalds committed
2011 2012 2013 2014 2015 2016 2017

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

2018 2019
	skb_copy_from_linear_data_offset(skb, len, skb_put(skb1, pos - len),
					 pos - len);
Linus Torvalds's avatar
Linus Torvalds committed
2020 2021 2022 2023 2024 2025 2026 2027 2028 2029
	/* 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;
2030
	skb_set_tail_pointer(skb, len);
Linus Torvalds's avatar
Linus Torvalds committed
2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 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
}

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);
}
2089
EXPORT_SYMBOL(skb_split);
Linus Torvalds's avatar
Linus Torvalds committed
2090

2091 2092 2093 2094
/* Shifting from/to a cloned skb is a no-go.
 *
 * Caller cannot keep skb_shinfo related pointers past calling here!
 */
2095 2096
static int skb_prepare_for_shift(struct sk_buff *skb)
{
2097
	return skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145
}

/**
 * skb_shift - Shifts paged data partially from skb to another
 * @tgt: buffer into which tail data gets added
 * @skb: buffer from which the paged data comes from
 * @shiftlen: shift up to this many bytes
 *
 * Attempts to shift up to shiftlen worth of bytes, which may be less than
 * the length of the skb, from tgt to skb. Returns number bytes shifted.
 * It's up to caller to free skb if everything was shifted.
 *
 * If @tgt runs out of frags, the whole operation is aborted.
 *
 * Skb cannot include anything else but paged data while tgt is allowed
 * to have non-paged data as well.
 *
 * TODO: full sized shift could be optimized but that would need
 * specialized skb free'er to handle frags without up-to-date nr_frags.
 */
int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen)
{
	int from, to, merge, todo;
	struct skb_frag_struct *fragfrom, *fragto;

	BUG_ON(shiftlen > skb->len);
	BUG_ON(skb_headlen(skb));	/* Would corrupt stream */

	todo = shiftlen;
	from = 0;
	to = skb_shinfo(tgt)->nr_frags;
	fragfrom = &skb_shinfo(skb)->frags[from];

	/* Actual merge is delayed until the point when we know we can
	 * commit all, so that we don't have to undo partial changes
	 */
	if (!to ||
	    !skb_can_coalesce(tgt, to, fragfrom->page, fragfrom->page_offset)) {
		merge = -1;
	} else {
		merge = to - 1;

		todo -= fragfrom->size;
		if (todo < 0) {
			if (skb_prepare_for_shift(skb) ||
			    skb_prepare_for_shift(tgt))
				return 0;

2146 2147
			/* All previous frag pointers might be stale! */
			fragfrom = &skb_shinfo(skb)->frags[from];
2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232
			fragto = &skb_shinfo(tgt)->frags[merge];

			fragto->size += shiftlen;
			fragfrom->size -= shiftlen;
			fragfrom->page_offset += shiftlen;

			goto onlymerged;
		}

		from++;
	}

	/* Skip full, not-fitting skb to avoid expensive operations */
	if ((shiftlen == skb->len) &&
	    (skb_shinfo(skb)->nr_frags - from) > (MAX_SKB_FRAGS - to))
		return 0;

	if (skb_prepare_for_shift(skb) || skb_prepare_for_shift(tgt))
		return 0;

	while ((todo > 0) && (from < skb_shinfo(skb)->nr_frags)) {
		if (to == MAX_SKB_FRAGS)
			return 0;

		fragfrom = &skb_shinfo(skb)->frags[from];
		fragto = &skb_shinfo(tgt)->frags[to];

		if (todo >= fragfrom->size) {
			*fragto = *fragfrom;
			todo -= fragfrom->size;
			from++;
			to++;

		} else {
			get_page(fragfrom->page);
			fragto->page = fragfrom->page;
			fragto->page_offset = fragfrom->page_offset;
			fragto->size = todo;

			fragfrom->page_offset += todo;
			fragfrom->size -= todo;
			todo = 0;

			to++;
			break;
		}
	}

	/* Ready to "commit" this state change to tgt */
	skb_shinfo(tgt)->nr_frags = to;

	if (merge >= 0) {
		fragfrom = &skb_shinfo(skb)->frags[0];
		fragto = &skb_shinfo(tgt)->frags[merge];

		fragto->size += fragfrom->size;
		put_page(fragfrom->page);
	}

	/* Reposition in the original skb */
	to = 0;
	while (from < skb_shinfo(skb)->nr_frags)
		skb_shinfo(skb)->frags[to++] = skb_shinfo(skb)->frags[from++];
	skb_shinfo(skb)->nr_frags = to;

	BUG_ON(todo > 0 && !skb_shinfo(skb)->nr_frags);

onlymerged:
	/* Most likely the tgt won't ever need its checksum anymore, skb on
	 * the other hand might need it if it needs to be resent
	 */
	tgt->ip_summed = CHECKSUM_PARTIAL;
	skb->ip_summed = CHECKSUM_PARTIAL;

	/* Yak, is it really working this way? Some helper please? */
	skb->len -= shiftlen;
	skb->data_len -= shiftlen;
	skb->truesize -= shiftlen;
	tgt->len += shiftlen;
	tgt->data_len += shiftlen;
	tgt->truesize += shiftlen;

	return shiftlen;
}

2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251
/**
 * 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;
}
2252
EXPORT_SYMBOL(skb_prepare_seq_read);
2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270

/**
 * 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.
 *
2271
 * Note 1: The size of each block of data returned can be arbitary,
2272 2273 2274
 *       this limitation is the cost for zerocopy seqeuental
 *       reads of potentially non linear data.
 *
2275
 * Note 2: Fragment lists within fragments are not implemented
2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288
 *       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:
2289
	block_limit = skb_headlen(st->cur_skb) + st->stepped_offset;
2290

2291
	if (abs_offset < block_limit && !st->frag_data) {
2292
		*data = st->cur_skb->data + (abs_offset - st->stepped_offset);
2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321
		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;
	}

2322 2323 2324 2325 2326
	if (st->frag_data) {
		kunmap_skb_frag(st->frag_data);
		st->frag_data = NULL;
	}

2327
	if (st->root_skb == st->cur_skb && skb_has_frags(st->root_skb)) {
2328
		st->cur_skb = skb_shinfo(st->root_skb)->frag_list;
2329 2330
		st->frag_idx = 0;
		goto next_skb;
2331 2332
	} else if (st->cur_skb->next) {
		st->cur_skb = st->cur_skb->next;
2333
		st->frag_idx = 0;
2334 2335 2336 2337 2338
		goto next_skb;
	}

	return 0;
}
2339
EXPORT_SYMBOL(skb_seq_read);
2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352

/**
 * 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);
}
2353
EXPORT_SYMBOL(skb_abort_seq_read);
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
#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)
{
2386 2387
	unsigned int ret;

2388 2389 2390 2391 2392
	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));

2393 2394
	ret = textsearch_find(config, state);
	return (ret <= to - from ? ret : UINT_MAX);
2395
}
2396
EXPORT_SYMBOL(skb_find_text);
2397

2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409
/**
 * 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,
2410
			int (*getfrag)(void *from, char *to, int offset,
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 2463 2464 2465 2466 2467 2468
					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;
}
2469
EXPORT_SYMBOL(skb_append_datato_frags);
2470

2471 2472 2473 2474 2475 2476
/**
 *	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
2477
 *	the CHECKSUM_COMPLETE checksum.  It should be used on
2478 2479 2480
 *	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.
2481 2482 2483 2484 2485 2486 2487 2488 2489 2490
 */
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;
}

2491 2492
EXPORT_SYMBOL_GPL(skb_pull_rcsum);

Herbert Xu's avatar
Herbert Xu committed
2493 2494 2495
/**
 *	skb_segment - Perform protocol segmentation on skb.
 *	@skb: buffer to segment
2496
 *	@features: features for the output path (see dev->features)
Herbert Xu's avatar
Herbert Xu committed
2497 2498
 *
 *	This function performs segmentation on the given skb.  It returns
2499 2500
 *	a pointer to the first in a list of new skbs for the segments.
 *	In case of error it returns ERR_PTR(err).
Herbert Xu's avatar
Herbert Xu committed
2501
 */
2502
struct sk_buff *skb_segment(struct sk_buff *skb, int features)
Herbert Xu's avatar
Herbert Xu committed
2503 2504 2505
{
	struct sk_buff *segs = NULL;
	struct sk_buff *tail = NULL;
2506
	struct sk_buff *fskb = skb_shinfo(skb)->frag_list;
Herbert Xu's avatar
Herbert Xu committed
2507
	unsigned int mss = skb_shinfo(skb)->gso_size;
2508
	unsigned int doffset = skb->data - skb_mac_header(skb);
Herbert Xu's avatar
Herbert Xu committed
2509 2510 2511
	unsigned int offset = doffset;
	unsigned int headroom;
	unsigned int len;
2512
	int sg = features & NETIF_F_SG;
Herbert Xu's avatar
Herbert Xu committed
2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524
	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;
2525
		int hsize;
Herbert Xu's avatar
Herbert Xu committed
2526 2527 2528 2529 2530 2531 2532 2533 2534
		int size;

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

		hsize = skb_headlen(skb) - offset;
		if (hsize < 0)
			hsize = 0;
2535 2536
		if (hsize > len || !sg)
			hsize = len;
Herbert Xu's avatar
Herbert Xu committed
2537

2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567
		if (!hsize && i >= nfrags) {
			BUG_ON(fskb->len != len);

			pos += len;
			nskb = skb_clone(fskb, GFP_ATOMIC);
			fskb = fskb->next;

			if (unlikely(!nskb))
				goto err;

			hsize = skb_end_pointer(nskb) - nskb->head;
			if (skb_cow_head(nskb, doffset + headroom)) {
				kfree_skb(nskb);
				goto err;
			}

			nskb->truesize += skb_end_pointer(nskb) - nskb->head -
					  hsize;
			skb_release_head_state(nskb);
			__skb_push(nskb, doffset);
		} else {
			nskb = alloc_skb(hsize + doffset + headroom,
					 GFP_ATOMIC);

			if (unlikely(!nskb))
				goto err;

			skb_reserve(nskb, headroom);
			__skb_put(nskb, doffset);
		}
Herbert Xu's avatar
Herbert Xu committed
2568 2569 2570 2571 2572 2573 2574

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

2575
		__copy_skb_header(nskb, skb);
Herbert Xu's avatar
Herbert Xu committed
2576 2577
		nskb->mac_len = skb->mac_len;

2578 2579 2580 2581
		/* nskb and skb might have different headroom */
		if (nskb->ip_summed == CHECKSUM_PARTIAL)
			nskb->csum_start += skb_headroom(nskb) - headroom;

2582
		skb_reset_mac_header(nskb);
2583
		skb_set_network_header(nskb, skb->mac_len);
2584 2585
		nskb->transport_header = (nskb->network_header +
					  skb_network_header_len(skb));
2586 2587
		skb_copy_from_linear_data(skb, nskb->data, doffset);

2588
		if (fskb != skb_shinfo(skb)->frag_list)
2589 2590
			continue;

Herbert Xu's avatar
Herbert Xu committed
2591
		if (!sg) {
2592
			nskb->ip_summed = CHECKSUM_NONE;
Herbert Xu's avatar
Herbert Xu committed
2593 2594 2595 2596 2597 2598 2599 2600
			nskb->csum = skb_copy_and_csum_bits(skb, offset,
							    skb_put(nskb, len),
							    len, 0);
			continue;
		}

		frag = skb_shinfo(nskb)->frags;

2601 2602
		skb_copy_from_linear_data_offset(skb, offset,
						 skb_put(nskb, hsize), hsize);
Herbert Xu's avatar
Herbert Xu committed
2603

2604
		while (pos < offset + len && i < nfrags) {
Herbert Xu's avatar
Herbert Xu committed
2605 2606 2607 2608 2609 2610 2611 2612 2613
			*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;
			}

2614
			skb_shinfo(nskb)->nr_frags++;
Herbert Xu's avatar
Herbert Xu committed
2615 2616 2617 2618 2619 2620

			if (pos + size <= offset + len) {
				i++;
				pos += size;
			} else {
				frag->size -= pos + size - (offset + len);
2621
				goto skip_fraglist;
Herbert Xu's avatar
Herbert Xu committed
2622 2623 2624 2625 2626
			}

			frag++;
		}

2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641
		if (pos < offset + len) {
			struct sk_buff *fskb2 = fskb;

			BUG_ON(pos + fskb->len != offset + len);

			pos += fskb->len;
			fskb = fskb->next;

			if (fskb2->next) {
				fskb2 = skb_clone(fskb2, GFP_ATOMIC);
				if (!fskb2)
					goto err;
			} else
				skb_get(fskb2);

2642
			SKB_FRAG_ASSERT(nskb);
2643 2644 2645 2646
			skb_shinfo(nskb)->frag_list = fskb2;
		}

skip_fraglist:
Herbert Xu's avatar
Herbert Xu committed
2647 2648 2649 2650 2651 2652 2653 2654 2655 2656
		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;
Patrick McHardy's avatar
Patrick McHardy committed
2657
		kfree_skb(skb);
Herbert Xu's avatar
Herbert Xu committed
2658 2659 2660 2661 2662
	}
	return ERR_PTR(err);
}
EXPORT_SYMBOL_GPL(skb_segment);

Herbert Xu's avatar
Herbert Xu committed
2663 2664 2665 2666
int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
{
	struct sk_buff *p = *head;
	struct sk_buff *nskb;
2667 2668
	struct skb_shared_info *skbinfo = skb_shinfo(skb);
	struct skb_shared_info *pinfo = skb_shinfo(p);
Herbert Xu's avatar
Herbert Xu committed
2669
	unsigned int headroom;
2670
	unsigned int len = skb_gro_len(skb);
2671 2672
	unsigned int offset = skb_gro_offset(skb);
	unsigned int headlen = skb_headlen(skb);
Herbert Xu's avatar
Herbert Xu committed
2673

2674
	if (p->len + len >= 65536)
Herbert Xu's avatar
Herbert Xu committed
2675 2676
		return -E2BIG;

2677
	if (pinfo->frag_list)
Herbert Xu's avatar
Herbert Xu committed
2678
		goto merge;
2679
	else if (headlen <= offset) {
2680
		skb_frag_t *frag;
2681
		skb_frag_t *frag2;
2682 2683
		int i = skbinfo->nr_frags;
		int nr_frags = pinfo->nr_frags + i;
2684 2685

		offset -= headlen;
2686

2687
		if (nr_frags > MAX_SKB_FRAGS)
2688 2689
			return -E2BIG;

2690 2691
		pinfo->nr_frags = nr_frags;
		skbinfo->nr_frags = 0;
2692

2693 2694
		frag = pinfo->frags + nr_frags;
		frag2 = skbinfo->frags + i;
2695 2696 2697
		do {
			*--frag = *--frag2;
		} while (--i);
Herbert Xu's avatar
Herbert Xu committed
2698

2699 2700
		frag->page_offset += offset;
		frag->size -= offset;
2701 2702 2703 2704 2705

		skb->truesize -= skb->data_len;
		skb->len -= skb->data_len;
		skb->data_len = 0;

Herbert Xu's avatar
Herbert Xu committed
2706 2707
		NAPI_GRO_CB(skb)->free = 1;
		goto done;
2708 2709
	} else if (skb_gro_len(p) != pinfo->gso_size)
		return -E2BIG;
Herbert Xu's avatar
Herbert Xu committed
2710

2711
	headroom = skb_headroom(p);
2712
	nskb = alloc_skb(headroom + skb_gro_offset(p), GFP_ATOMIC);
Herbert Xu's avatar
Herbert Xu committed
2713 2714 2715 2716 2717 2718 2719
	if (unlikely(!nskb))
		return -ENOMEM;

	__copy_skb_header(nskb, p);
	nskb->mac_len = p->mac_len;

	skb_reserve(nskb, headroom);
2720
	__skb_put(nskb, skb_gro_offset(p));
Herbert Xu's avatar
Herbert Xu committed
2721

2722
	skb_set_mac_header(nskb, skb_mac_header(p) - p->data);
Herbert Xu's avatar
Herbert Xu committed
2723 2724 2725
	skb_set_network_header(nskb, skb_network_offset(p));
	skb_set_transport_header(nskb, skb_transport_offset(p));

2726 2727 2728
	__skb_pull(p, skb_gro_offset(p));
	memcpy(skb_mac_header(nskb), skb_mac_header(p),
	       p->data - skb_mac_header(p));
Herbert Xu's avatar
Herbert Xu committed
2729 2730 2731

	*NAPI_GRO_CB(nskb) = *NAPI_GRO_CB(p);
	skb_shinfo(nskb)->frag_list = p;
2732
	skb_shinfo(nskb)->gso_size = pinfo->gso_size;
2733
	pinfo->gso_size = 0;
Herbert Xu's avatar
Herbert Xu committed
2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747
	skb_header_release(p);
	nskb->prev = p;

	nskb->data_len += p->len;
	nskb->truesize += p->len;
	nskb->len += p->len;

	*head = nskb;
	nskb->next = p->next;
	p->next = NULL;

	p = nskb;

merge:
2748
	if (offset > headlen) {
2749 2750 2751 2752 2753 2754
		unsigned int eat = offset - headlen;

		skbinfo->frags[0].page_offset += eat;
		skbinfo->frags[0].size -= eat;
		skb->data_len -= eat;
		skb->len -= eat;
2755
		offset = headlen;
2756 2757
	}

2758
	__skb_pull(skb, offset);
2759

Herbert Xu's avatar
Herbert Xu committed
2760 2761 2762 2763
	p->prev->next = skb;
	p->prev = skb;
	skb_header_release(skb);

Herbert Xu's avatar
Herbert Xu committed
2764 2765
done:
	NAPI_GRO_CB(p)->count++;
2766 2767 2768
	p->data_len += len;
	p->truesize += len;
	p->len += len;
Herbert Xu's avatar
Herbert Xu committed
2769 2770 2771 2772 2773 2774

	NAPI_GRO_CB(skb)->same_flow = 1;
	return 0;
}
EXPORT_SYMBOL_GPL(skb_gro_receive);

Linus Torvalds's avatar
Linus Torvalds committed
2775 2776 2777 2778 2779
void __init skb_init(void)
{
	skbuff_head_cache = kmem_cache_create("skbuff_head_cache",
					      sizeof(struct sk_buff),
					      0,
Alexey Dobriyan's avatar
Alexey Dobriyan committed
2780
					      SLAB_HWCACHE_ALIGN|SLAB_PANIC,
2781
					      NULL);
2782 2783 2784 2785
	skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache",
						(2*sizeof(struct sk_buff)) +
						sizeof(atomic_t),
						0,
Alexey Dobriyan's avatar
Alexey Dobriyan committed
2786
						SLAB_HWCACHE_ALIGN|SLAB_PANIC,
2787
						NULL);
Linus Torvalds's avatar
Linus Torvalds committed
2788 2789
}

2790 2791 2792 2793 2794 2795 2796 2797 2798 2799
/**
 *	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.
 */
2800 2801
static int
__skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
2802
{
2803 2804
	int start = skb_headlen(skb);
	int i, copy = start - offset;
2805
	struct sk_buff *frag_iter;
2806 2807 2808 2809 2810
	int elt = 0;

	if (copy > 0) {
		if (copy > len)
			copy = len;
2811
		sg_set_buf(sg, skb->data + offset, copy);
2812 2813 2814 2815 2816 2817 2818
		elt++;
		if ((len -= copy) == 0)
			return elt;
		offset += copy;
	}

	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
2819
		int end;
2820

2821
		WARN_ON(start > offset + len);
2822 2823

		end = start + skb_shinfo(skb)->frags[i].size;
2824 2825 2826 2827 2828
		if ((copy = end - offset) > 0) {
			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];

			if (copy > len)
				copy = len;
2829 2830
			sg_set_page(&sg[elt], frag->page, copy,
					frag->page_offset+offset-start);
2831 2832 2833 2834 2835
			elt++;
			if (!(len -= copy))
				return elt;
			offset += copy;
		}
2836
		start = end;
2837 2838
	}

2839 2840
	skb_walk_frags(skb, frag_iter) {
		int end;
2841

2842
		WARN_ON(start > offset + len);
2843

2844 2845 2846 2847 2848 2849 2850 2851 2852
		end = start + frag_iter->len;
		if ((copy = end - offset) > 0) {
			if (copy > len)
				copy = len;
			elt += __skb_to_sgvec(frag_iter, sg+elt, offset - start,
					      copy);
			if ((len -= copy) == 0)
				return elt;
			offset += copy;
2853
		}
2854
		start = end;
2855 2856 2857 2858 2859
	}
	BUG_ON(len);
	return elt;
}

2860 2861 2862 2863
int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
{
	int nsg = __skb_to_sgvec(skb, sg, offset, len);

Jens Axboe's avatar
Jens Axboe committed
2864
	sg_mark_end(&sg[nsg - 1]);
2865 2866 2867

	return nsg;
}
2868
EXPORT_SYMBOL_GPL(skb_to_sgvec);
2869

2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901
/**
 *	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. */
2902
	if (!skb_has_frags(skb)) {
2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936
		/* 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 ||
2937
			    skb_has_frags(skb1) ||
2938 2939 2940 2941 2942 2943 2944 2945
			    skb_tailroom(skb1) < tailbits)
				ntail = tailbits + 128;
		}

		if (copyflag ||
		    skb_cloned(skb1) ||
		    ntail ||
		    skb_shinfo(skb1)->nr_frags ||
2946
		    skb_has_frags(skb1)) {
2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977
			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;
}
2978
EXPORT_SYMBOL_GPL(skb_cow_data);
2979

2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010
void skb_tstamp_tx(struct sk_buff *orig_skb,
		struct skb_shared_hwtstamps *hwtstamps)
{
	struct sock *sk = orig_skb->sk;
	struct sock_exterr_skb *serr;
	struct sk_buff *skb;
	int err;

	if (!sk)
		return;

	skb = skb_clone(orig_skb, GFP_ATOMIC);
	if (!skb)
		return;

	if (hwtstamps) {
		*skb_hwtstamps(skb) =
			*hwtstamps;
	} else {
		/*
		 * no hardware time stamps available,
		 * so keep the skb_shared_tx and only
		 * store software time stamp
		 */
		skb->tstamp = ktime_get_real();
	}

	serr = SKB_EXT_ERR(skb);
	memset(serr, 0, sizeof(*serr));
	serr->ee.ee_errno = ENOMSG;
	serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
3011 3012

	bh_lock_sock(sk);
3013
	err = sock_queue_err_skb(sk, skb);
3014 3015
	bh_unlock_sock(sk);

3016 3017 3018 3019 3020 3021
	if (err)
		kfree_skb(skb);
}
EXPORT_SYMBOL_GPL(skb_tstamp_tx);


3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035
/**
 * 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)
{
3036 3037
	if (unlikely(start > skb_headlen(skb)) ||
	    unlikely((int)start + off > skb_headlen(skb) - 2)) {
3038 3039 3040
		if (net_ratelimit())
			printk(KERN_WARNING
			       "bad partial csum: csum=%u/%u len=%u\n",
3041
			       start, off, skb_headlen(skb));
3042 3043 3044 3045 3046 3047 3048
		return false;
	}
	skb->ip_summed = CHECKSUM_PARTIAL;
	skb->csum_start = skb_headroom(skb) + start;
	skb->csum_offset = off;
	return true;
}
3049
EXPORT_SYMBOL_GPL(skb_partial_csum_set);
3050

3051 3052 3053 3054 3055 3056 3057
void __skb_warn_lro_forwarding(const struct sk_buff *skb)
{
	if (net_ratelimit())
		pr_warning("%s: received packets cannot be forwarded"
			   " while LRO is enabled\n", skb->dev->name);
}
EXPORT_SYMBOL(__skb_warn_lro_forwarding);