skbuff.h 47.9 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25
/*
 *	Definitions for the 'struct sk_buff' memory handlers.
 *
 *	Authors:
 *		Alan Cox, <gw4pts@gw4pts.ampr.org>
 *		Florian La Roche, <rzsfl@rz.uni-sb.de>
 *
 *	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.
 */

#ifndef _LINUX_SKBUFF_H
#define _LINUX_SKBUFF_H

#include <linux/kernel.h>
#include <linux/compiler.h>
#include <linux/time.h>
#include <linux/cache.h>

#include <asm/atomic.h>
#include <asm/types.h>
#include <linux/spinlock.h>
#include <linux/net.h>
26
#include <linux/textsearch.h>
L
Linus Torvalds 已提交
27
#include <net/checksum.h>
28
#include <linux/rcupdate.h>
29
#include <linux/dmaengine.h>
30
#include <linux/hrtimer.h>
L
Linus Torvalds 已提交
31 32 33 34

#define HAVE_ALLOC_SKB		/* For the drivers to know */
#define HAVE_ALIGNABLE_SKB	/* Ditto 8)		   */

35
/* Don't change this without changing skb_csum_unnecessary! */
L
Linus Torvalds 已提交
36
#define CHECKSUM_NONE 0
37 38 39
#define CHECKSUM_UNNECESSARY 1
#define CHECKSUM_COMPLETE 2
#define CHECKSUM_PARTIAL 3
L
Linus Torvalds 已提交
40 41 42

#define SKB_DATA_ALIGN(X)	(((X) + (SMP_CACHE_BYTES - 1)) & \
				 ~(SMP_CACHE_BYTES - 1))
43 44 45 46 47
#define SKB_WITH_OVERHEAD(X)	\
	(((X) - sizeof(struct skb_shared_info)) & \
	 ~(SMP_CACHE_BYTES - 1))
#define SKB_MAX_ORDER(X, ORDER) \
	SKB_WITH_OVERHEAD((PAGE_SIZE << (ORDER)) - (X))
L
Linus Torvalds 已提交
48 49 50 51 52 53 54 55 56 57 58 59 60 61
#define SKB_MAX_HEAD(X)		(SKB_MAX_ORDER((X), 0))
#define SKB_MAX_ALLOC		(SKB_MAX_ORDER(0, 2))

/* A. Checksumming of received packets by device.
 *
 *	NONE: device failed to checksum this packet.
 *		skb->csum is undefined.
 *
 *	UNNECESSARY: device parsed packet and wouldbe verified checksum.
 *		skb->csum is undefined.
 *	      It is bad option, but, unfortunately, many of vendors do this.
 *	      Apparently with secret goal to sell you new device, when you
 *	      will add new protocol to your host. F.e. IPv6. 8)
 *
62
 *	COMPLETE: the most generic way. Device supplied checksum of _all_
L
Linus Torvalds 已提交
63 64
 *	    the packet as seen by netif_rx in skb->csum.
 *	    NOTE: Even if device supports only some protocols, but
65
 *	    is able to produce some skb->csum, it MUST use COMPLETE,
L
Linus Torvalds 已提交
66 67 68 69 70 71
 *	    not UNNECESSARY.
 *
 * B. Checksumming on output.
 *
 *	NONE: skb is checksummed by protocol or csum is not required.
 *
72
 *	PARTIAL: device is required to csum packet as seen by hard_start_xmit
73 74
 *	from skb->transport_header to the end and to record the checksum
 *	at skb->transport_header + skb->csum.
L
Linus Torvalds 已提交
75 76 77 78 79 80 81 82 83 84 85 86 87 88 89
 *
 *	Device must show its capabilities in dev->features, set
 *	at device setup time.
 *	NETIF_F_HW_CSUM	- it is clever device, it is able to checksum
 *			  everything.
 *	NETIF_F_NO_CSUM - loopback or reliable single hop media.
 *	NETIF_F_IP_CSUM - device is dumb. It is able to csum only
 *			  TCP/UDP over IPv4. Sigh. Vendors like this
 *			  way by an unknown reason. Though, see comment above
 *			  about CHECKSUM_UNNECESSARY. 8)
 *
 *	Any questions? No questions, good. 		--ANK
 */

struct net_device;
90
struct scatterlist;
L
Linus Torvalds 已提交
91

92
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
L
Linus Torvalds 已提交
93 94 95
struct nf_conntrack {
	atomic_t use;
};
96
#endif
L
Linus Torvalds 已提交
97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137

#ifdef CONFIG_BRIDGE_NETFILTER
struct nf_bridge_info {
	atomic_t use;
	struct net_device *physindev;
	struct net_device *physoutdev;
#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE)
	struct net_device *netoutdev;
#endif
	unsigned int mask;
	unsigned long data[32 / sizeof(unsigned long)];
};
#endif

struct sk_buff_head {
	/* These two members must be first. */
	struct sk_buff	*next;
	struct sk_buff	*prev;

	__u32		qlen;
	spinlock_t	lock;
};

struct sk_buff;

/* To allow 64K frame to be packed as single skb without frag_list */
#define MAX_SKB_FRAGS (65536/PAGE_SIZE + 2)

typedef struct skb_frag_struct skb_frag_t;

struct skb_frag_struct {
	struct page *page;
	__u16 page_offset;
	__u16 size;
};

/* This data is invariant across clones and lives at
 * the end of the header data, ie. at skb->end.
 */
struct skb_shared_info {
	atomic_t	dataref;
B
Benjamin LaHaise 已提交
138
	unsigned short	nr_frags;
139 140 141 142
	unsigned short	gso_size;
	/* Warning: this field is not always filled in (UFO)! */
	unsigned short	gso_segs;
	unsigned short  gso_type;
A
Al Viro 已提交
143
	__be32          ip6_frag_id;
L
Linus Torvalds 已提交
144 145 146 147 148 149
	struct sk_buff	*frag_list;
	skb_frag_t	frags[MAX_SKB_FRAGS];
};

/* We divide dataref into two halves.  The higher 16 bits hold references
 * to the payload part of skb->data.  The lower 16 bits hold references to
150 151
 * the entire skb->data.  A clone of a headerless skb holds the length of
 * the header in skb->hdr_len.
L
Linus Torvalds 已提交
152 153 154 155 156 157 158 159 160 161
 *
 * All users must obey the rule that the skb->data reference count must be
 * greater than or equal to the payload reference count.
 *
 * Holding a reference to the payload part means that the user does not
 * care about modifications to the header part of skb->data.
 */
#define SKB_DATAREF_SHIFT 16
#define SKB_DATAREF_MASK ((1 << SKB_DATAREF_SHIFT) - 1)

162 163 164 165 166 167 168

enum {
	SKB_FCLONE_UNAVAILABLE,
	SKB_FCLONE_ORIG,
	SKB_FCLONE_CLONE,
};

169 170
enum {
	SKB_GSO_TCPV4 = 1 << 0,
H
Herbert Xu 已提交
171
	SKB_GSO_UDP = 1 << 1,
172 173 174

	/* This indicates the skb is from an untrusted source. */
	SKB_GSO_DODGY = 1 << 2,
M
Michael Chan 已提交
175 176

	/* This indicates the tcp segment has CWR set. */
H
Herbert Xu 已提交
177 178 179
	SKB_GSO_TCP_ECN = 1 << 3,

	SKB_GSO_TCPV6 = 1 << 4,
180 181
};

182 183 184 185 186 187 188 189 190 191
#if BITS_PER_LONG > 32
#define NET_SKBUFF_DATA_USES_OFFSET 1
#endif

#ifdef NET_SKBUFF_DATA_USES_OFFSET
typedef unsigned int sk_buff_data_t;
#else
typedef unsigned char *sk_buff_data_t;
#endif

L
Linus Torvalds 已提交
192 193 194 195 196
/** 
 *	struct sk_buff - socket buffer
 *	@next: Next buffer in list
 *	@prev: Previous buffer in list
 *	@sk: Socket we are owned by
H
Herbert Xu 已提交
197
 *	@tstamp: Time we arrived
L
Linus Torvalds 已提交
198
 *	@dev: Device we arrived on/are leaving by
R
Randy Dunlap 已提交
199
 *	@transport_header: Transport layer header
200 201
 *	@network_header: Network layer header
 *	@mac_header: Link layer header
202 203
 *	@dst: destination entry
 *	@sp: the security path, used for xfrm
L
Linus Torvalds 已提交
204 205 206 207
 *	@cb: Control buffer. Free for use by every layer. Put private vars here
 *	@len: Length of actual data
 *	@data_len: Data length
 *	@mac_len: Length of link layer header
208
 *	@hdr_len: writable header length of cloned skb
209 210 211
 *	@csum: Checksum (must include start/offset pair)
 *	@csum_start: Offset from skb->head where checksumming should start
 *	@csum_offset: Offset from csum_start where checksum should be stored
212
 *	@local_df: allow local fragmentation
L
Linus Torvalds 已提交
213 214 215
 *	@cloned: Head may be cloned (check refcnt to be sure)
 *	@nohdr: Payload reference only, must not modify header
 *	@pkt_type: Packet class
216
 *	@fclone: skbuff clone status
L
Linus Torvalds 已提交
217 218 219 220 221 222 223 224 225 226
 *	@ip_summed: Driver fed us an IP checksum
 *	@priority: Packet queueing priority
 *	@users: User count - see {datagram,tcp}.c
 *	@protocol: Packet protocol from driver
 *	@truesize: Buffer size 
 *	@head: Head of buffer
 *	@data: Data head pointer
 *	@tail: Tail pointer
 *	@end: End pointer
 *	@destructor: Destruct function
T
Thomas Graf 已提交
227
 *	@mark: Generic packet mark
L
Linus Torvalds 已提交
228
 *	@nfct: Associated connection, if any
229
 *	@ipvs_property: skbuff is owned by ipvs
L
Linus Torvalds 已提交
230
 *	@nfctinfo: Relationship of this skb to the connection
R
Randy Dunlap 已提交
231
 *	@nfct_reasm: netfilter conntrack re-assembly pointer
L
Linus Torvalds 已提交
232
 *	@nf_bridge: Saved data about a bridged frame - see br_netfilter.c
233 234
 *	@iif: ifindex of device we arrived on
 *	@queue_mapping: Queue mapping for multiqueue devices
L
Linus Torvalds 已提交
235 236
 *	@tc_index: Traffic control index
 *	@tc_verd: traffic control verdict
R
Randy Dunlap 已提交
237 238
 *	@dma_cookie: a cookie to one of several possible DMA operations
 *		done by skb DMA functions
239
 *	@secmark: security marking
L
Linus Torvalds 已提交
240 241 242 243 244 245 246 247
 */

struct sk_buff {
	/* These two members must be first. */
	struct sk_buff		*next;
	struct sk_buff		*prev;

	struct sock		*sk;
248
	ktime_t			tstamp;
L
Linus Torvalds 已提交
249 250 251 252 253 254 255 256 257 258 259
	struct net_device	*dev;

	struct  dst_entry	*dst;
	struct	sec_path	*sp;

	/*
	 * This is the control buffer. It is free to use for every
	 * layer. Please put your private variables there. If you
	 * want to keep them across layers you have to do a skb_clone()
	 * first. This is owned by whoever has the skb queued ATM.
	 */
260
	char			cb[48];
L
Linus Torvalds 已提交
261 262

	unsigned int		len,
263 264 265
				data_len;
	__u16			mac_len,
				hdr_len;
A
Al Viro 已提交
266 267
	union {
		__wsum		csum;
268 269 270 271
		struct {
			__u16	csum_start;
			__u16	csum_offset;
		};
A
Al Viro 已提交
272
	};
L
Linus Torvalds 已提交
273
	__u32			priority;
274 275 276
	__u8			local_df:1,
				cloned:1,
				ip_summed:2,
277 278
				nohdr:1,
				nfctinfo:3;
279
	__u8			pkt_type:3,
280 281
				fclone:2,
				ipvs_property:1;
282
	__be16			protocol;
L
Linus Torvalds 已提交
283 284

	void			(*destructor)(struct sk_buff *skb);
285
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
286
	struct nf_conntrack	*nfct;
287 288
	struct sk_buff		*nfct_reasm;
#endif
L
Linus Torvalds 已提交
289 290 291
#ifdef CONFIG_BRIDGE_NETFILTER
	struct nf_bridge_info	*nf_bridge;
#endif
292 293 294 295

	int			iif;
	__u16			queue_mapping;

L
Linus Torvalds 已提交
296
#ifdef CONFIG_NET_SCHED
297
	__u16			tc_index;	/* traffic control index */
L
Linus Torvalds 已提交
298
#ifdef CONFIG_NET_CLS_ACT
299
	__u16			tc_verd;	/* traffic control verdict */
L
Linus Torvalds 已提交
300 301
#endif
#endif
302 303
	/* 2 byte hole */

304 305 306
#ifdef CONFIG_NET_DMA
	dma_cookie_t		dma_cookie;
#endif
307 308 309
#ifdef CONFIG_NETWORK_SECMARK
	__u32			secmark;
#endif
L
Linus Torvalds 已提交
310

T
Thomas Graf 已提交
311
	__u32			mark;
L
Linus Torvalds 已提交
312

313 314 315
	sk_buff_data_t		transport_header;
	sk_buff_data_t		network_header;
	sk_buff_data_t		mac_header;
L
Linus Torvalds 已提交
316
	/* These elements must be at the end, see alloc_skb() for details.  */
317
	sk_buff_data_t		tail;
318
	sk_buff_data_t		end;
L
Linus Torvalds 已提交
319
	unsigned char		*head,
320
				*data;
321 322
	unsigned int		truesize;
	atomic_t		users;
L
Linus Torvalds 已提交
323 324 325 326 327 328 329 330 331 332
};

#ifdef __KERNEL__
/*
 *	Handling routines are only of interest to the kernel
 */
#include <linux/slab.h>

#include <asm/system.h>

333
extern void kfree_skb(struct sk_buff *skb);
L
Linus Torvalds 已提交
334
extern void	       __kfree_skb(struct sk_buff *skb);
335
extern struct sk_buff *__alloc_skb(unsigned int size,
336
				   gfp_t priority, int fclone, int node);
337
static inline struct sk_buff *alloc_skb(unsigned int size,
A
Al Viro 已提交
338
					gfp_t priority)
339
{
340
	return __alloc_skb(size, priority, 0, -1);
341 342 343
}

static inline struct sk_buff *alloc_skb_fclone(unsigned int size,
A
Al Viro 已提交
344
					       gfp_t priority)
345
{
346
	return __alloc_skb(size, priority, 1, -1);
347 348
}

L
Linus Torvalds 已提交
349
extern void	       kfree_skbmem(struct sk_buff *skb);
V
Victor Fusco 已提交
350
extern struct sk_buff *skb_clone(struct sk_buff *skb,
A
Al Viro 已提交
351
				 gfp_t priority);
V
Victor Fusco 已提交
352
extern struct sk_buff *skb_copy(const struct sk_buff *skb,
A
Al Viro 已提交
353
				gfp_t priority);
V
Victor Fusco 已提交
354
extern struct sk_buff *pskb_copy(struct sk_buff *skb,
A
Al Viro 已提交
355
				 gfp_t gfp_mask);
L
Linus Torvalds 已提交
356
extern int	       pskb_expand_head(struct sk_buff *skb,
V
Victor Fusco 已提交
357
					int nhead, int ntail,
A
Al Viro 已提交
358
					gfp_t gfp_mask);
L
Linus Torvalds 已提交
359 360 361 362
extern struct sk_buff *skb_realloc_headroom(struct sk_buff *skb,
					    unsigned int headroom);
extern struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
				       int newheadroom, int newtailroom,
A
Al Viro 已提交
363
				       gfp_t priority);
364 365 366 367 368
extern int	       skb_to_sgvec(struct sk_buff *skb,
				    struct scatterlist *sg, int offset,
				    int len);
extern int	       skb_cow_data(struct sk_buff *skb, int tailbits,
				    struct sk_buff **trailer);
369
extern int	       skb_pad(struct sk_buff *skb, int pad);
L
Linus Torvalds 已提交
370 371 372 373 374
#define dev_kfree_skb(a)	kfree_skb(a)
extern void	      skb_over_panic(struct sk_buff *skb, int len,
				     void *here);
extern void	      skb_under_panic(struct sk_buff *skb, int len,
				      void *here);
375 376 377 378 379 380 381
extern void	      skb_truesize_bug(struct sk_buff *skb);

static inline void skb_truesize_check(struct sk_buff *skb)
{
	if (unlikely((int)skb->truesize < sizeof(struct sk_buff) + skb->len))
		skb_truesize_bug(skb);
}
L
Linus Torvalds 已提交
382

383 384 385 386 387
extern int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb,
			int getfrag(void *from, char *to, int offset,
			int len,int odd, struct sk_buff *skb),
			void *from, int length);

388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405
struct skb_seq_state
{
	__u32		lower_offset;
	__u32		upper_offset;
	__u32		frag_idx;
	__u32		stepped_offset;
	struct sk_buff	*root_skb;
	struct sk_buff	*cur_skb;
	__u8		*frag_data;
};

extern void	      skb_prepare_seq_read(struct sk_buff *skb,
					   unsigned int from, unsigned int to,
					   struct skb_seq_state *st);
extern unsigned int   skb_seq_read(unsigned int consumed, const u8 **data,
				   struct skb_seq_state *st);
extern void	      skb_abort_seq_read(struct skb_seq_state *st);

406 407 408 409
extern unsigned int   skb_find_text(struct sk_buff *skb, unsigned int from,
				    unsigned int to, struct ts_config *config,
				    struct ts_state *state);

410 411 412 413 414 415 416 417 418 419 420 421
#ifdef NET_SKBUFF_DATA_USES_OFFSET
static inline unsigned char *skb_end_pointer(const struct sk_buff *skb)
{
	return skb->head + skb->end;
}
#else
static inline unsigned char *skb_end_pointer(const struct sk_buff *skb)
{
	return skb->end;
}
#endif

L
Linus Torvalds 已提交
422
/* Internal */
423
#define skb_shinfo(SKB)	((struct skb_shared_info *)(skb_end_pointer(SKB)))
L
Linus Torvalds 已提交
424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526

/**
 *	skb_queue_empty - check if a queue is empty
 *	@list: queue head
 *
 *	Returns true if the queue is empty, false otherwise.
 */
static inline int skb_queue_empty(const struct sk_buff_head *list)
{
	return list->next == (struct sk_buff *)list;
}

/**
 *	skb_get - reference buffer
 *	@skb: buffer to reference
 *
 *	Makes another reference to a socket buffer and returns a pointer
 *	to the buffer.
 */
static inline struct sk_buff *skb_get(struct sk_buff *skb)
{
	atomic_inc(&skb->users);
	return skb;
}

/*
 * If users == 1, we are the only owner and are can avoid redundant
 * atomic change.
 */

/**
 *	skb_cloned - is the buffer a clone
 *	@skb: buffer to check
 *
 *	Returns true if the buffer was generated with skb_clone() and is
 *	one of multiple shared copies of the buffer. Cloned buffers are
 *	shared data so must not be written to under normal circumstances.
 */
static inline int skb_cloned(const struct sk_buff *skb)
{
	return skb->cloned &&
	       (atomic_read(&skb_shinfo(skb)->dataref) & SKB_DATAREF_MASK) != 1;
}

/**
 *	skb_header_cloned - is the header a clone
 *	@skb: buffer to check
 *
 *	Returns true if modifying the header part of the buffer requires
 *	the data to be copied.
 */
static inline int skb_header_cloned(const struct sk_buff *skb)
{
	int dataref;

	if (!skb->cloned)
		return 0;

	dataref = atomic_read(&skb_shinfo(skb)->dataref);
	dataref = (dataref & SKB_DATAREF_MASK) - (dataref >> SKB_DATAREF_SHIFT);
	return dataref != 1;
}

/**
 *	skb_header_release - release reference to header
 *	@skb: buffer to operate on
 *
 *	Drop a reference to the header part of the buffer.  This is done
 *	by acquiring a payload reference.  You must not read from the header
 *	part of skb->data after this.
 */
static inline void skb_header_release(struct sk_buff *skb)
{
	BUG_ON(skb->nohdr);
	skb->nohdr = 1;
	atomic_add(1 << SKB_DATAREF_SHIFT, &skb_shinfo(skb)->dataref);
}

/**
 *	skb_shared - is the buffer shared
 *	@skb: buffer to check
 *
 *	Returns true if more than one person has a reference to this
 *	buffer.
 */
static inline int skb_shared(const struct sk_buff *skb)
{
	return atomic_read(&skb->users) != 1;
}

/**
 *	skb_share_check - check if buffer is shared and if so clone it
 *	@skb: buffer to check
 *	@pri: priority for memory allocation
 *
 *	If the buffer is shared the buffer is cloned and the old copy
 *	drops a reference. A new clone with a single reference is returned.
 *	If the buffer is not shared the original buffer is returned. When
 *	being called from interrupt status or with spinlocks held pri must
 *	be GFP_ATOMIC.
 *
 *	NULL is returned on a memory allocation failure.
 */
V
Victor Fusco 已提交
527
static inline struct sk_buff *skb_share_check(struct sk_buff *skb,
A
Al Viro 已提交
528
					      gfp_t pri)
L
Linus Torvalds 已提交
529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558
{
	might_sleep_if(pri & __GFP_WAIT);
	if (skb_shared(skb)) {
		struct sk_buff *nskb = skb_clone(skb, pri);
		kfree_skb(skb);
		skb = nskb;
	}
	return skb;
}

/*
 *	Copy shared buffers into a new sk_buff. We effectively do COW on
 *	packets to handle cases where we have a local reader and forward
 *	and a couple of other messy ones. The normal one is tcpdumping
 *	a packet thats being forwarded.
 */

/**
 *	skb_unshare - make a copy of a shared buffer
 *	@skb: buffer to check
 *	@pri: priority for memory allocation
 *
 *	If the socket buffer is a clone then this function creates a new
 *	copy of the data, drops a reference count on the old copy and returns
 *	the new copy with the reference count at 1. If the buffer is not a clone
 *	the original buffer is returned. When called with a spinlock held or
 *	from interrupt state @pri must be %GFP_ATOMIC
 *
 *	%NULL is returned on a memory allocation failure.
 */
559
static inline struct sk_buff *skb_unshare(struct sk_buff *skb,
A
Al Viro 已提交
560
					  gfp_t pri)
L
Linus Torvalds 已提交
561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623
{
	might_sleep_if(pri & __GFP_WAIT);
	if (skb_cloned(skb)) {
		struct sk_buff *nskb = skb_copy(skb, pri);
		kfree_skb(skb);	/* Free our shared copy */
		skb = nskb;
	}
	return skb;
}

/**
 *	skb_peek
 *	@list_: list to peek at
 *
 *	Peek an &sk_buff. Unlike most other operations you _MUST_
 *	be careful with this one. A peek leaves the buffer on the
 *	list and someone else may run off with it. You must hold
 *	the appropriate locks or have a private queue to do this.
 *
 *	Returns %NULL for an empty list or a pointer to the head element.
 *	The reference count is not incremented and the reference is therefore
 *	volatile. Use with caution.
 */
static inline struct sk_buff *skb_peek(struct sk_buff_head *list_)
{
	struct sk_buff *list = ((struct sk_buff *)list_)->next;
	if (list == (struct sk_buff *)list_)
		list = NULL;
	return list;
}

/**
 *	skb_peek_tail
 *	@list_: list to peek at
 *
 *	Peek an &sk_buff. Unlike most other operations you _MUST_
 *	be careful with this one. A peek leaves the buffer on the
 *	list and someone else may run off with it. You must hold
 *	the appropriate locks or have a private queue to do this.
 *
 *	Returns %NULL for an empty list or a pointer to the tail element.
 *	The reference count is not incremented and the reference is therefore
 *	volatile. Use with caution.
 */
static inline struct sk_buff *skb_peek_tail(struct sk_buff_head *list_)
{
	struct sk_buff *list = ((struct sk_buff *)list_)->prev;
	if (list == (struct sk_buff *)list_)
		list = NULL;
	return list;
}

/**
 *	skb_queue_len	- get queue length
 *	@list_: list to measure
 *
 *	Return the length of an &sk_buff queue.
 */
static inline __u32 skb_queue_len(const struct sk_buff_head *list_)
{
	return list_->qlen;
}

624 625 626 627 628 629 630 631
/*
 * This function creates a split out lock class for each invocation;
 * this is needed for now since a whole lot of users of the skb-queue
 * infrastructure in drivers have different locking usage (in hardirq)
 * than the networking core (in softirq only). In the long run either the
 * network layer or drivers should need annotation to consolidate the
 * main types of usage into 3 classes.
 */
L
Linus Torvalds 已提交
632 633 634 635 636 637 638
static inline void skb_queue_head_init(struct sk_buff_head *list)
{
	spin_lock_init(&list->lock);
	list->prev = list->next = (struct sk_buff *)list;
	list->qlen = 0;
}

639 640 641 642 643 644 645
static inline void skb_queue_head_init_class(struct sk_buff_head *list,
		struct lock_class_key *class)
{
	skb_queue_head_init(list);
	lockdep_set_class(&list->lock, class);
}

L
Linus Torvalds 已提交
646 647 648 649 650 651 652 653
/*
 *	Insert an sk_buff at the start of a list.
 *
 *	The "__skb_xxxx()" functions are the non-atomic ones that
 *	can only be called with interrupts disabled.
 */

/**
654
 *	__skb_queue_after - queue a buffer at the list head
L
Linus Torvalds 已提交
655
 *	@list: list to use
656
 *	@prev: place after this buffer
L
Linus Torvalds 已提交
657 658
 *	@newsk: buffer to queue
 *
659
 *	Queue a buffer int the middle of a list. This function takes no locks
L
Linus Torvalds 已提交
660 661 662 663
 *	and you must therefore hold required locks before calling it.
 *
 *	A buffer cannot be placed on two lists at the same time.
 */
664 665 666
static inline void __skb_queue_after(struct sk_buff_head *list,
				     struct sk_buff *prev,
				     struct sk_buff *newsk)
L
Linus Torvalds 已提交
667
{
668
	struct sk_buff *next;
L
Linus Torvalds 已提交
669
	list->qlen++;
670

L
Linus Torvalds 已提交
671 672 673 674 675 676
	next = prev->next;
	newsk->next = next;
	newsk->prev = prev;
	next->prev  = prev->next = newsk;
}

677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693
/**
 *	__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 a list. This function takes no locks
 *	and you must therefore hold required locks before calling it.
 *
 *	A buffer cannot be placed on two lists at the same time.
 */
extern void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk);
static inline void __skb_queue_head(struct sk_buff_head *list,
				    struct sk_buff *newsk)
{
	__skb_queue_after(list, (struct sk_buff *)list, newsk);
}

L
Linus Torvalds 已提交
694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749
/**
 *	__skb_queue_tail - queue a buffer at the list tail
 *	@list: list to use
 *	@newsk: buffer to queue
 *
 *	Queue a buffer at the end of a list. This function takes no locks
 *	and you must therefore hold required locks before calling it.
 *
 *	A buffer cannot be placed on two lists at the same time.
 */
extern void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk);
static inline void __skb_queue_tail(struct sk_buff_head *list,
				   struct sk_buff *newsk)
{
	struct sk_buff *prev, *next;

	list->qlen++;
	next = (struct sk_buff *)list;
	prev = next->prev;
	newsk->next = next;
	newsk->prev = prev;
	next->prev  = prev->next = newsk;
}


/**
 *	__skb_dequeue - remove from the head of the queue
 *	@list: list to dequeue from
 *
 *	Remove the head of the list. This function does not take any locks
 *	so must be used with appropriate locks held only. The head item is
 *	returned or %NULL if the list is empty.
 */
extern struct sk_buff *skb_dequeue(struct sk_buff_head *list);
static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list)
{
	struct sk_buff *next, *prev, *result;

	prev = (struct sk_buff *) list;
	next = prev->next;
	result = NULL;
	if (next != prev) {
		result	     = next;
		next	     = next->next;
		list->qlen--;
		next->prev   = prev;
		prev->next   = next;
		result->next = result->prev = NULL;
	}
	return result;
}


/*
 *	Insert a packet on a list.
 */
D
David S. Miller 已提交
750
extern void        skb_insert(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list);
L
Linus Torvalds 已提交
751 752 753 754 755 756 757 758 759 760 761 762 763
static inline void __skb_insert(struct sk_buff *newsk,
				struct sk_buff *prev, struct sk_buff *next,
				struct sk_buff_head *list)
{
	newsk->next = next;
	newsk->prev = prev;
	next->prev  = prev->next = newsk;
	list->qlen++;
}

/*
 *	Place a packet after a given packet in a list.
 */
D
David S. Miller 已提交
764 765
extern void	   skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list);
static inline void __skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list)
L
Linus Torvalds 已提交
766
{
D
David S. Miller 已提交
767
	__skb_insert(newsk, old, old->next, list);
L
Linus Torvalds 已提交
768 769 770 771 772 773
}

/*
 * remove sk_buff from list. _Must_ be called atomically, and with
 * the list known..
 */
D
David S. Miller 已提交
774
extern void	   skb_unlink(struct sk_buff *skb, struct sk_buff_head *list);
L
Linus Torvalds 已提交
775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841
static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list)
{
	struct sk_buff *next, *prev;

	list->qlen--;
	next	   = skb->next;
	prev	   = skb->prev;
	skb->next  = skb->prev = NULL;
	next->prev = prev;
	prev->next = next;
}


/* XXX: more streamlined implementation */

/**
 *	__skb_dequeue_tail - remove from the tail of the queue
 *	@list: list to dequeue from
 *
 *	Remove the tail of the list. This function does not take any locks
 *	so must be used with appropriate locks held only. The tail item is
 *	returned or %NULL if the list is empty.
 */
extern struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list);
static inline struct sk_buff *__skb_dequeue_tail(struct sk_buff_head *list)
{
	struct sk_buff *skb = skb_peek_tail(list);
	if (skb)
		__skb_unlink(skb, list);
	return skb;
}


static inline int skb_is_nonlinear(const struct sk_buff *skb)
{
	return skb->data_len;
}

static inline unsigned int skb_headlen(const struct sk_buff *skb)
{
	return skb->len - skb->data_len;
}

static inline int skb_pagelen(const struct sk_buff *skb)
{
	int i, len = 0;

	for (i = (int)skb_shinfo(skb)->nr_frags - 1; i >= 0; i--)
		len += skb_shinfo(skb)->frags[i].size;
	return len + skb_headlen(skb);
}

static inline void skb_fill_page_desc(struct sk_buff *skb, int i,
				      struct page *page, int off, int size)
{
	skb_frag_t *frag = &skb_shinfo(skb)->frags[i];

	frag->page		  = page;
	frag->page_offset	  = off;
	frag->size		  = size;
	skb_shinfo(skb)->nr_frags = i + 1;
}

#define SKB_PAGE_ASSERT(skb) 	BUG_ON(skb_shinfo(skb)->nr_frags)
#define SKB_FRAG_ASSERT(skb) 	BUG_ON(skb_shinfo(skb)->frag_list)
#define SKB_LINEAR_ASSERT(skb)  BUG_ON(skb_is_nonlinear(skb))

842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872
#ifdef NET_SKBUFF_DATA_USES_OFFSET
static inline unsigned char *skb_tail_pointer(const struct sk_buff *skb)
{
	return skb->head + skb->tail;
}

static inline void skb_reset_tail_pointer(struct sk_buff *skb)
{
	skb->tail = skb->data - skb->head;
}

static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset)
{
	skb_reset_tail_pointer(skb);
	skb->tail += offset;
}
#else /* NET_SKBUFF_DATA_USES_OFFSET */
static inline unsigned char *skb_tail_pointer(const struct sk_buff *skb)
{
	return skb->tail;
}

static inline void skb_reset_tail_pointer(struct sk_buff *skb)
{
	skb->tail = skb->data;
}

static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset)
{
	skb->tail = skb->data + offset;
}
873

874 875
#endif /* NET_SKBUFF_DATA_USES_OFFSET */

L
Linus Torvalds 已提交
876 877 878 879 880
/*
 *	Add data to an sk_buff
 */
static inline unsigned char *__skb_put(struct sk_buff *skb, unsigned int len)
{
881
	unsigned char *tmp = skb_tail_pointer(skb);
L
Linus Torvalds 已提交
882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898
	SKB_LINEAR_ASSERT(skb);
	skb->tail += len;
	skb->len  += len;
	return tmp;
}

/**
 *	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.
 */
static inline unsigned char *skb_put(struct sk_buff *skb, unsigned int len)
{
899
	unsigned char *tmp = skb_tail_pointer(skb);
L
Linus Torvalds 已提交
900 901 902
	SKB_LINEAR_ASSERT(skb);
	skb->tail += len;
	skb->len  += len;
903
	if (unlikely(skb->tail > skb->end))
L
Linus Torvalds 已提交
904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998
		skb_over_panic(skb, len, current_text_addr());
	return tmp;
}

static inline unsigned char *__skb_push(struct sk_buff *skb, unsigned int len)
{
	skb->data -= len;
	skb->len  += len;
	return skb->data;
}

/**
 *	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.
 */
static inline 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, current_text_addr());
	return skb->data;
}

static inline unsigned char *__skb_pull(struct sk_buff *skb, unsigned int len)
{
	skb->len -= len;
	BUG_ON(skb->len < skb->data_len);
	return skb->data += len;
}

/**
 *	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.
 */
static inline unsigned char *skb_pull(struct sk_buff *skb, unsigned int len)
{
	return unlikely(len > skb->len) ? NULL : __skb_pull(skb, len);
}

extern unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta);

static inline unsigned char *__pskb_pull(struct sk_buff *skb, unsigned int len)
{
	if (len > skb_headlen(skb) &&
	    !__pskb_pull_tail(skb, len-skb_headlen(skb)))
		return NULL;
	skb->len -= len;
	return skb->data += len;
}

static inline unsigned char *pskb_pull(struct sk_buff *skb, unsigned int len)
{
	return unlikely(len > skb->len) ? NULL : __pskb_pull(skb, len);
}

static inline int pskb_may_pull(struct sk_buff *skb, unsigned int len)
{
	if (likely(len <= skb_headlen(skb)))
		return 1;
	if (unlikely(len > skb->len))
		return 0;
	return __pskb_pull_tail(skb, len-skb_headlen(skb)) != NULL;
}

/**
 *	skb_headroom - bytes at buffer head
 *	@skb: buffer to check
 *
 *	Return the number of bytes of free space at the head of an &sk_buff.
 */
static inline int skb_headroom(const struct sk_buff *skb)
{
	return skb->data - skb->head;
}

/**
 *	skb_tailroom - bytes at buffer end
 *	@skb: buffer to check
 *
 *	Return the number of bytes of free space at the tail of an sk_buff
 */
static inline int skb_tailroom(const struct sk_buff *skb)
{
999
	return skb_is_nonlinear(skb) ? 0 : skb->end - skb->tail;
L
Linus Torvalds 已提交
1000 1001 1002 1003 1004 1005 1006 1007 1008 1009
}

/**
 *	skb_reserve - adjust headroom
 *	@skb: buffer to alter
 *	@len: bytes to move
 *
 *	Increase the headroom of an empty &sk_buff by reducing the tail
 *	room. This is only allowed for an empty buffer.
 */
1010
static inline void skb_reserve(struct sk_buff *skb, int len)
L
Linus Torvalds 已提交
1011 1012 1013 1014 1015
{
	skb->data += len;
	skb->tail += len;
}

1016
#ifdef NET_SKBUFF_DATA_USES_OFFSET
1017 1018
static inline unsigned char *skb_transport_header(const struct sk_buff *skb)
{
1019
	return skb->head + skb->transport_header;
1020 1021
}

1022 1023
static inline void skb_reset_transport_header(struct sk_buff *skb)
{
1024
	skb->transport_header = skb->data - skb->head;
1025 1026
}

1027 1028 1029
static inline void skb_set_transport_header(struct sk_buff *skb,
					    const int offset)
{
1030 1031
	skb_reset_transport_header(skb);
	skb->transport_header += offset;
1032 1033
}

1034 1035
static inline unsigned char *skb_network_header(const struct sk_buff *skb)
{
1036
	return skb->head + skb->network_header;
1037 1038
}

1039 1040
static inline void skb_reset_network_header(struct sk_buff *skb)
{
1041
	skb->network_header = skb->data - skb->head;
1042 1043
}

1044 1045
static inline void skb_set_network_header(struct sk_buff *skb, const int offset)
{
1046 1047
	skb_reset_network_header(skb);
	skb->network_header += offset;
1048 1049
}

1050
static inline unsigned char *skb_mac_header(const struct sk_buff *skb)
1051
{
1052
	return skb->head + skb->mac_header;
1053 1054
}

1055
static inline int skb_mac_header_was_set(const struct sk_buff *skb)
1056
{
1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101
	return skb->mac_header != ~0U;
}

static inline void skb_reset_mac_header(struct sk_buff *skb)
{
	skb->mac_header = skb->data - skb->head;
}

static inline void skb_set_mac_header(struct sk_buff *skb, const int offset)
{
	skb_reset_mac_header(skb);
	skb->mac_header += offset;
}

#else /* NET_SKBUFF_DATA_USES_OFFSET */

static inline unsigned char *skb_transport_header(const struct sk_buff *skb)
{
	return skb->transport_header;
}

static inline void skb_reset_transport_header(struct sk_buff *skb)
{
	skb->transport_header = skb->data;
}

static inline void skb_set_transport_header(struct sk_buff *skb,
					    const int offset)
{
	skb->transport_header = skb->data + offset;
}

static inline unsigned char *skb_network_header(const struct sk_buff *skb)
{
	return skb->network_header;
}

static inline void skb_reset_network_header(struct sk_buff *skb)
{
	skb->network_header = skb->data;
}

static inline void skb_set_network_header(struct sk_buff *skb, const int offset)
{
	skb->network_header = skb->data + offset;
1102 1103
}

1104 1105
static inline unsigned char *skb_mac_header(const struct sk_buff *skb)
{
1106
	return skb->mac_header;
1107 1108 1109 1110
}

static inline int skb_mac_header_was_set(const struct sk_buff *skb)
{
1111
	return skb->mac_header != NULL;
1112 1113
}

1114 1115
static inline void skb_reset_mac_header(struct sk_buff *skb)
{
1116
	skb->mac_header = skb->data;
1117 1118
}

1119 1120
static inline void skb_set_mac_header(struct sk_buff *skb, const int offset)
{
1121
	skb->mac_header = skb->data + offset;
1122
}
1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138
#endif /* NET_SKBUFF_DATA_USES_OFFSET */

static inline int skb_transport_offset(const struct sk_buff *skb)
{
	return skb_transport_header(skb) - skb->data;
}

static inline u32 skb_network_header_len(const struct sk_buff *skb)
{
	return skb->transport_header - skb->network_header;
}

static inline int skb_network_offset(const struct sk_buff *skb)
{
	return skb_network_header(skb) - skb->data;
}
1139

L
Linus Torvalds 已提交
1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163
/*
 * CPUs often take a performance hit when accessing unaligned memory
 * locations. The actual performance hit varies, it can be small if the
 * hardware handles it or large if we have to take an exception and fix it
 * in software.
 *
 * Since an ethernet header is 14 bytes network drivers often end up with
 * the IP header at an unaligned offset. The IP header can be aligned by
 * shifting the start of the packet by 2 bytes. Drivers should do this
 * with:
 *
 * skb_reserve(NET_IP_ALIGN);
 *
 * The downside to this alignment of the IP header is that the DMA is now
 * unaligned. On some architectures the cost of an unaligned DMA is high
 * and this cost outweighs the gains made by aligning the IP header.
 * 
 * Since this trade off varies between architectures, we allow NET_IP_ALIGN
 * to be overridden.
 */
#ifndef NET_IP_ALIGN
#define NET_IP_ALIGN	2
#endif

1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182
/*
 * The networking layer reserves some headroom in skb data (via
 * dev_alloc_skb). This is used to avoid having to reallocate skb data when
 * the header has to grow. In the default case, if the header has to grow
 * 16 bytes or less we avoid the reallocation.
 *
 * Unfortunately this headroom changes the DMA alignment of the resulting
 * network packet. As for NET_IP_ALIGN, this unaligned DMA is expensive
 * on some architectures. An architecture can override this value,
 * perhaps setting it to a cacheline in size (since that will maintain
 * cacheline alignment of the DMA). It must be a power of 2.
 *
 * Various parts of the networking layer expect at least 16 bytes of
 * headroom, you should not reduce this.
 */
#ifndef NET_SKB_PAD
#define NET_SKB_PAD	16
#endif

1183
extern int ___pskb_trim(struct sk_buff *skb, unsigned int len);
L
Linus Torvalds 已提交
1184 1185 1186

static inline void __skb_trim(struct sk_buff *skb, unsigned int len)
{
1187 1188 1189 1190
	if (unlikely(skb->data_len)) {
		WARN_ON(1);
		return;
	}
1191 1192
	skb->len = len;
	skb_set_tail_pointer(skb, len);
L
Linus Torvalds 已提交
1193 1194 1195 1196 1197 1198 1199 1200 1201
}

/**
 *	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.
1202
 *	The skb must be linear.
L
Linus Torvalds 已提交
1203 1204 1205 1206 1207 1208 1209 1210 1211 1212
 */
static inline void skb_trim(struct sk_buff *skb, unsigned int len)
{
	if (skb->len > len)
		__skb_trim(skb, len);
}


static inline int __pskb_trim(struct sk_buff *skb, unsigned int len)
{
1213 1214 1215 1216
	if (skb->data_len)
		return ___pskb_trim(skb, len);
	__skb_trim(skb, len);
	return 0;
L
Linus Torvalds 已提交
1217 1218 1219 1220 1221 1222 1223
}

static inline int pskb_trim(struct sk_buff *skb, unsigned int len)
{
	return (len < skb->len) ? __pskb_trim(skb, len) : 0;
}

1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238
/**
 *	pskb_trim_unique - remove end from a paged unique (not cloned) buffer
 *	@skb: buffer to alter
 *	@len: new length
 *
 *	This is identical to pskb_trim except that the caller knows that
 *	the skb is not cloned so we should never get an error due to out-
 *	of-memory.
 */
static inline void pskb_trim_unique(struct sk_buff *skb, unsigned int len)
{
	int err = pskb_trim(skb, len);
	BUG_ON(err);
}

L
Linus Torvalds 已提交
1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271
/**
 *	skb_orphan - orphan a buffer
 *	@skb: buffer to orphan
 *
 *	If a buffer currently has an owner then we call the owner's
 *	destructor function and make the @skb unowned. The buffer continues
 *	to exist but is no longer charged to its former owner.
 */
static inline void skb_orphan(struct sk_buff *skb)
{
	if (skb->destructor)
		skb->destructor(skb);
	skb->destructor = NULL;
	skb->sk		= NULL;
}

/**
 *	__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 does not take the
 *	list lock and the caller must hold the relevant locks to use it.
 */
extern void skb_queue_purge(struct sk_buff_head *list);
static inline void __skb_queue_purge(struct sk_buff_head *list)
{
	struct sk_buff *skb;
	while ((skb = __skb_dequeue(list)) != NULL)
		kfree_skb(skb);
}

/**
1272
 *	__dev_alloc_skb - allocate an skbuff for receiving
L
Linus Torvalds 已提交
1273 1274 1275 1276 1277 1278 1279 1280
 *	@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.
 *
1281
 *	%NULL is returned if there is no free memory.
L
Linus Torvalds 已提交
1282 1283
 */
static inline struct sk_buff *__dev_alloc_skb(unsigned int length,
A
Al Viro 已提交
1284
					      gfp_t gfp_mask)
L
Linus Torvalds 已提交
1285
{
1286
	struct sk_buff *skb = alloc_skb(length + NET_SKB_PAD, gfp_mask);
L
Linus Torvalds 已提交
1287
	if (likely(skb))
1288
		skb_reserve(skb, NET_SKB_PAD);
L
Linus Torvalds 已提交
1289 1290 1291 1292
	return skb;
}

/**
1293
 *	dev_alloc_skb - allocate an skbuff for receiving
L
Linus Torvalds 已提交
1294 1295 1296 1297 1298 1299 1300
 *	@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.
 *
1301
 *	%NULL is returned if there is no free memory. Although this function
L
Linus Torvalds 已提交
1302 1303 1304 1305 1306 1307 1308
 *	allocates memory it can be called from an interrupt.
 */
static inline struct sk_buff *dev_alloc_skb(unsigned int length)
{
	return __dev_alloc_skb(length, GFP_ATOMIC);
}

1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330
extern struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
		unsigned int length, gfp_t gfp_mask);

/**
 *	netdev_alloc_skb - allocate an skbuff for rx on a specific device
 *	@dev: network device to receive on
 *	@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.
 */
static inline struct sk_buff *netdev_alloc_skb(struct net_device *dev,
		unsigned int length)
{
	return __netdev_alloc_skb(dev, length, GFP_ATOMIC);
}

1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344
/**
 *	skb_clone_writable - is the header of a clone writable
 *	@skb: buffer to check
 *	@len: length up to which to write
 *
 *	Returns true if modifying the header part of the cloned buffer
 *	does not requires the data to be copied.
 */
static inline int skb_clone_writable(struct sk_buff *skb, int len)
{
	return !skb_header_cloned(skb) &&
	       skb_headroom(skb) + len <= skb->hdr_len;
}

L
Linus Torvalds 已提交
1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358
/**
 *	skb_cow - copy header of skb when it is required
 *	@skb: buffer to cow
 *	@headroom: needed headroom
 *
 *	If the skb passed lacks sufficient headroom or its data part
 *	is shared, data is reallocated. If reallocation fails, an error
 *	is returned and original skb is not changed.
 *
 *	The result is skb with writable area skb->head...skb->tail
 *	and at least @headroom of space at head.
 */
static inline int skb_cow(struct sk_buff *skb, unsigned int headroom)
{
1359 1360
	int delta = (headroom > NET_SKB_PAD ? headroom : NET_SKB_PAD) -
			skb_headroom(skb);
L
Linus Torvalds 已提交
1361 1362 1363 1364 1365

	if (delta < 0)
		delta = 0;

	if (delta || skb_cloned(skb))
1366 1367
		return pskb_expand_head(skb, (delta + (NET_SKB_PAD-1)) &
				~(NET_SKB_PAD-1), 0, GFP_ATOMIC);
L
Linus Torvalds 已提交
1368 1369 1370 1371 1372 1373 1374 1375 1376 1377
	return 0;
}

/**
 *	skb_padto	- pad an skbuff up to a minimal size
 *	@skb: buffer to pad
 *	@len: minimal length
 *
 *	Pads up a buffer to ensure the trailing bytes exist and are
 *	blanked. If the buffer already contains sufficient data it
1378 1379
 *	is untouched. Otherwise it is extended. Returns zero on
 *	success. The skb is freed on error.
L
Linus Torvalds 已提交
1380 1381
 */
 
1382
static inline int skb_padto(struct sk_buff *skb, unsigned int len)
L
Linus Torvalds 已提交
1383 1384 1385
{
	unsigned int size = skb->len;
	if (likely(size >= len))
1386
		return 0;
L
Linus Torvalds 已提交
1387 1388 1389 1390 1391 1392 1393 1394 1395 1396
	return skb_pad(skb, len-size);
}

static inline int skb_add_data(struct sk_buff *skb,
			       char __user *from, int copy)
{
	const int off = skb->len;

	if (skb->ip_summed == CHECKSUM_NONE) {
		int err = 0;
1397
		__wsum csum = csum_and_copy_from_user(from, skb_put(skb, copy),
L
Linus Torvalds 已提交
1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421
							    copy, 0, &err);
		if (!err) {
			skb->csum = csum_block_add(skb->csum, csum, off);
			return 0;
		}
	} else if (!copy_from_user(skb_put(skb, copy), from, copy))
		return 0;

	__skb_trim(skb, off);
	return -EFAULT;
}

static inline int skb_can_coalesce(struct sk_buff *skb, int i,
				   struct page *page, int off)
{
	if (i) {
		struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i - 1];

		return page == frag->page &&
		       off == frag->page_offset + frag->size;
	}
	return 0;
}

H
Herbert Xu 已提交
1422 1423 1424 1425 1426
static inline int __skb_linearize(struct sk_buff *skb)
{
	return __pskb_pull_tail(skb, skb->data_len) ? 0 : -ENOMEM;
}

L
Linus Torvalds 已提交
1427 1428 1429 1430 1431 1432 1433
/**
 *	skb_linearize - convert paged skb to linear one
 *	@skb: buffer to linarize
 *
 *	If there is no free memory -ENOMEM is returned, otherwise zero
 *	is returned and the old skb data released.
 */
H
Herbert Xu 已提交
1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446
static inline int skb_linearize(struct sk_buff *skb)
{
	return skb_is_nonlinear(skb) ? __skb_linearize(skb) : 0;
}

/**
 *	skb_linearize_cow - make sure skb is linear and writable
 *	@skb: buffer to process
 *
 *	If there is no free memory -ENOMEM is returned, otherwise zero
 *	is returned and the old skb data released.
 */
static inline int skb_linearize_cow(struct sk_buff *skb)
L
Linus Torvalds 已提交
1447
{
H
Herbert Xu 已提交
1448 1449
	return skb_is_nonlinear(skb) || skb_cloned(skb) ?
	       __skb_linearize(skb) : 0;
L
Linus Torvalds 已提交
1450 1451 1452 1453 1454 1455 1456 1457 1458
}

/**
 *	skb_postpull_rcsum - update checksum for received skb after pull
 *	@skb: buffer to update
 *	@start: start of data before pull
 *	@len: length of data pulled
 *
 *	After doing a pull on a received packet, you need to call this to
1459 1460
 *	update the CHECKSUM_COMPLETE checksum, or set ip_summed to
 *	CHECKSUM_NONE so that it can be recomputed from scratch.
L
Linus Torvalds 已提交
1461 1462 1463
 */

static inline void skb_postpull_rcsum(struct sk_buff *skb,
1464
				      const void *start, unsigned int len)
L
Linus Torvalds 已提交
1465
{
1466
	if (skb->ip_summed == CHECKSUM_COMPLETE)
L
Linus Torvalds 已提交
1467 1468 1469
		skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0));
}

1470 1471
unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len);

L
Linus Torvalds 已提交
1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482
/**
 *	pskb_trim_rcsum - trim received skb and update checksum
 *	@skb: buffer to trim
 *	@len: new length
 *
 *	This is exactly the same as pskb_trim except that it ensures the
 *	checksum of received packets are still valid after the operation.
 */

static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len)
{
1483
	if (likely(len >= skb->len))
L
Linus Torvalds 已提交
1484
		return 0;
1485
	if (skb->ip_summed == CHECKSUM_COMPLETE)
L
Linus Torvalds 已提交
1486 1487 1488 1489 1490 1491 1492 1493 1494
		skb->ip_summed = CHECKSUM_NONE;
	return __pskb_trim(skb, len);
}

#define skb_queue_walk(queue, skb) \
		for (skb = (queue)->next;					\
		     prefetch(skb->next), (skb != (struct sk_buff *)(queue));	\
		     skb = skb->next)

1495 1496 1497 1498 1499
#define skb_queue_walk_safe(queue, skb, tmp)					\
		for (skb = (queue)->next, tmp = skb->next;			\
		     skb != (struct sk_buff *)(queue);				\
		     skb = tmp, tmp = skb->next)

1500 1501 1502 1503 1504
#define skb_queue_reverse_walk(queue, skb) \
		for (skb = (queue)->prev;					\
		     prefetch(skb->prev), (skb != (struct sk_buff *)(queue));	\
		     skb = skb->prev)

L
Linus Torvalds 已提交
1505 1506 1507 1508 1509 1510 1511 1512

extern struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags,
					 int noblock, int *err);
extern unsigned int    datagram_poll(struct file *file, struct socket *sock,
				     struct poll_table_struct *wait);
extern int	       skb_copy_datagram_iovec(const struct sk_buff *from,
					       int offset, struct iovec *to,
					       int size);
1513
extern int	       skb_copy_and_csum_datagram_iovec(struct sk_buff *skb,
L
Linus Torvalds 已提交
1514 1515 1516
							int hlen,
							struct iovec *iov);
extern void	       skb_free_datagram(struct sock *sk, struct sk_buff *skb);
1517 1518
extern void	       skb_kill_datagram(struct sock *sk, struct sk_buff *skb,
					 unsigned int flags);
1519 1520
extern __wsum	       skb_checksum(const struct sk_buff *skb, int offset,
				    int len, __wsum csum);
L
Linus Torvalds 已提交
1521 1522
extern int	       skb_copy_bits(const struct sk_buff *skb, int offset,
				     void *to, int len);
1523 1524
extern int	       skb_store_bits(struct sk_buff *skb, int offset,
				      const void *from, int len);
1525
extern __wsum	       skb_copy_and_csum_bits(const struct sk_buff *skb,
L
Linus Torvalds 已提交
1526
					      int offset, u8 *to, int len,
1527
					      __wsum csum);
L
Linus Torvalds 已提交
1528 1529 1530 1531
extern void	       skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to);
extern void	       skb_split(struct sk_buff *skb,
				 struct sk_buff *skb1, const u32 len);

1532
extern struct sk_buff *skb_segment(struct sk_buff *skb, int features);
1533

L
Linus Torvalds 已提交
1534 1535 1536 1537 1538
static inline void *skb_header_pointer(const struct sk_buff *skb, int offset,
				       int len, void *buffer)
{
	int hlen = skb_headlen(skb);

1539
	if (hlen - offset >= len)
L
Linus Torvalds 已提交
1540 1541 1542 1543 1544 1545 1546 1547
		return skb->data + offset;

	if (skb_copy_bits(skb, offset, buffer, len) < 0)
		return NULL;

	return buffer;
}

1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561
static inline void skb_copy_from_linear_data(const struct sk_buff *skb,
					     void *to,
					     const unsigned int len)
{
	memcpy(to, skb->data, len);
}

static inline void skb_copy_from_linear_data_offset(const struct sk_buff *skb,
						    const int offset, void *to,
						    const unsigned int len)
{
	memcpy(to, skb->data + offset, len);
}

1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576
static inline void skb_copy_to_linear_data(struct sk_buff *skb,
					   const void *from,
					   const unsigned int len)
{
	memcpy(skb->data, from, len);
}

static inline void skb_copy_to_linear_data_offset(struct sk_buff *skb,
						  const int offset,
						  const void *from,
						  const unsigned int len)
{
	memcpy(skb->data + offset, from, len);
}

L
Linus Torvalds 已提交
1577 1578
extern void skb_init(void);

1579 1580 1581 1582 1583 1584 1585 1586 1587
/**
 *	skb_get_timestamp - get timestamp from a skb
 *	@skb: skb to get stamp from
 *	@stamp: pointer to struct timeval to store stamp in
 *
 *	Timestamps are stored in the skb as offsets to a base timestamp.
 *	This function converts the offset back to a struct timeval and stores
 *	it in stamp.
 */
1588
static inline void skb_get_timestamp(const struct sk_buff *skb, struct timeval *stamp)
1589
{
1590
	*stamp = ktime_to_timeval(skb->tstamp);
1591 1592
}

1593
static inline void __net_timestamp(struct sk_buff *skb)
1594
{
1595
	skb->tstamp = ktime_get_real();
1596 1597
}

1598 1599 1600 1601 1602
static inline ktime_t net_timedelta(ktime_t t)
{
	return ktime_sub(ktime_get_real(), t);
}

1603 1604 1605 1606
static inline ktime_t net_invalid_timestamp(void)
{
	return ktime_set(0, 0);
}
1607

1608
extern __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len);
1609
extern __sum16 __skb_checksum_complete(struct sk_buff *skb);
1610

1611 1612 1613 1614 1615
static inline int skb_csum_unnecessary(const struct sk_buff *skb)
{
	return skb->ip_summed & CHECKSUM_UNNECESSARY;
}

1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633
/**
 *	skb_checksum_complete - Calculate checksum of an entire packet
 *	@skb: packet to process
 *
 *	This function calculates the checksum over the entire packet plus
 *	the value of skb->csum.  The latter can be used to supply the
 *	checksum of a pseudo header as used by TCP/UDP.  It returns the
 *	checksum.
 *
 *	For protocols that contain complete checksums such as ICMP/TCP/UDP,
 *	this function can be used to verify that checksum on received
 *	packets.  In that case the function should return zero if the
 *	checksum is correct.  In particular, this function will return zero
 *	if skb->ip_summed is CHECKSUM_UNNECESSARY which indicates that the
 *	hardware has already verified the correctness of the checksum.
 */
static inline unsigned int skb_checksum_complete(struct sk_buff *skb)
{
1634 1635
	return skb_csum_unnecessary(skb) ?
	       0 : __skb_checksum_complete(skb);
1636 1637
}

1638
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
1639
extern void nf_conntrack_destroy(struct nf_conntrack *nfct);
L
Linus Torvalds 已提交
1640 1641 1642
static inline void nf_conntrack_put(struct nf_conntrack *nfct)
{
	if (nfct && atomic_dec_and_test(&nfct->use))
1643
		nf_conntrack_destroy(nfct);
L
Linus Torvalds 已提交
1644 1645 1646 1647 1648 1649
}
static inline void nf_conntrack_get(struct nf_conntrack *nfct)
{
	if (nfct)
		atomic_inc(&nfct->use);
}
1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660
static inline void nf_conntrack_get_reasm(struct sk_buff *skb)
{
	if (skb)
		atomic_inc(&skb->users);
}
static inline void nf_conntrack_put_reasm(struct sk_buff *skb)
{
	if (skb)
		kfree_skb(skb);
}
#endif
L
Linus Torvalds 已提交
1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672
#ifdef CONFIG_BRIDGE_NETFILTER
static inline void nf_bridge_put(struct nf_bridge_info *nf_bridge)
{
	if (nf_bridge && atomic_dec_and_test(&nf_bridge->use))
		kfree(nf_bridge);
}
static inline void nf_bridge_get(struct nf_bridge_info *nf_bridge)
{
	if (nf_bridge)
		atomic_inc(&nf_bridge->use);
}
#endif /* CONFIG_BRIDGE_NETFILTER */
1673 1674
static inline void nf_reset(struct sk_buff *skb)
{
1675
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686
	nf_conntrack_put(skb->nfct);
	skb->nfct = NULL;
	nf_conntrack_put_reasm(skb->nfct_reasm);
	skb->nfct_reasm = NULL;
#endif
#ifdef CONFIG_BRIDGE_NETFILTER
	nf_bridge_put(skb->nf_bridge);
	skb->nf_bridge = NULL;
#endif
}

1687 1688 1689
/* Note: This doesn't put any conntrack and bridge info in dst. */
static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src)
{
1690
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702
	dst->nfct = src->nfct;
	nf_conntrack_get(src->nfct);
	dst->nfctinfo = src->nfctinfo;
	dst->nfct_reasm = src->nfct_reasm;
	nf_conntrack_get_reasm(src->nfct_reasm);
#endif
#ifdef CONFIG_BRIDGE_NETFILTER
	dst->nf_bridge  = src->nf_bridge;
	nf_bridge_get(src->nf_bridge);
#endif
}

1703 1704 1705
static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src)
{
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
1706
	nf_conntrack_put(dst->nfct);
1707 1708 1709 1710 1711 1712 1713 1714
	nf_conntrack_put_reasm(dst->nfct_reasm);
#endif
#ifdef CONFIG_BRIDGE_NETFILTER
	nf_bridge_put(dst->nf_bridge);
#endif
	__nf_copy(dst, src);
}

1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732
#ifdef CONFIG_NETWORK_SECMARK
static inline void skb_copy_secmark(struct sk_buff *to, const struct sk_buff *from)
{
	to->secmark = from->secmark;
}

static inline void skb_init_secmark(struct sk_buff *skb)
{
	skb->secmark = 0;
}
#else
static inline void skb_copy_secmark(struct sk_buff *to, const struct sk_buff *from)
{ }

static inline void skb_init_secmark(struct sk_buff *skb)
{ }
#endif

1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746
static inline void skb_set_queue_mapping(struct sk_buff *skb, u16 queue_mapping)
{
#ifdef CONFIG_NETDEVICES_MULTIQUEUE
	skb->queue_mapping = queue_mapping;
#endif
}

static inline void skb_copy_queue_mapping(struct sk_buff *to, const struct sk_buff *from)
{
#ifdef CONFIG_NETDEVICES_MULTIQUEUE
	to->queue_mapping = from->queue_mapping;
#endif
}

H
Herbert Xu 已提交
1747 1748 1749 1750 1751
static inline int skb_is_gso(const struct sk_buff *skb)
{
	return skb_shinfo(skb)->gso_size;
}

1752 1753 1754 1755 1756 1757 1758
static inline void skb_forward_csum(struct sk_buff *skb)
{
	/* Unfortunately we don't support this one.  Any brave souls? */
	if (skb->ip_summed == CHECKSUM_COMPLETE)
		skb->ip_summed = CHECKSUM_NONE;
}

L
Linus Torvalds 已提交
1759 1760
#endif	/* __KERNEL__ */
#endif	/* _LINUX_SKBUFF_H */