skbuff.h 49.7 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
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>
Linus Torvalds's avatar
Linus Torvalds committed
27
#include <net/checksum.h>
28
#include <linux/rcupdate.h>
29
#include <linux/dmaengine.h>
30
#include <linux/hrtimer.h>
Linus Torvalds's avatar
Linus Torvalds committed
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! */
Linus Torvalds's avatar
Linus Torvalds committed
36
#define CHECKSUM_NONE 0
37 38 39
#define CHECKSUM_UNNECESSARY 1
#define CHECKSUM_COMPLETE 2
#define CHECKSUM_PARTIAL 3
Linus Torvalds's avatar
Linus Torvalds committed
40 41 42

#define SKB_DATA_ALIGN(X)	(((X) + (SMP_CACHE_BYTES - 1)) & \
				 ~(SMP_CACHE_BYTES - 1))
43
#define SKB_WITH_OVERHEAD(X)	\
44
	((X) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
45 46
#define SKB_MAX_ORDER(X, ORDER) \
	SKB_WITH_OVERHEAD((PAGE_SIZE << (ORDER)) - (X))
Linus Torvalds's avatar
Linus Torvalds committed
47 48 49 50 51 52 53 54 55 56 57 58 59 60
#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)
 *
61
 *	COMPLETE: the most generic way. Device supplied checksum of _all_
Linus Torvalds's avatar
Linus Torvalds committed
62 63
 *	    the packet as seen by netif_rx in skb->csum.
 *	    NOTE: Even if device supports only some protocols, but
64
 *	    is able to produce some skb->csum, it MUST use COMPLETE,
Linus Torvalds's avatar
Linus Torvalds committed
65 66
 *	    not UNNECESSARY.
 *
67 68 69 70 71 72 73
 *	PARTIAL: identical to the case for output below.  This may occur
 *	    on a packet received directly from another Linux OS, e.g.,
 *	    a virtualised Linux kernel on the same host.  The packet can
 *	    be treated in the same way as UNNECESSARY except that on
 *	    output (i.e., forwarding) the checksum must be filled in
 *	    by the OS or the hardware.
 *
Linus Torvalds's avatar
Linus Torvalds committed
74 75 76 77
 * B. Checksumming on output.
 *
 *	NONE: skb is checksummed by protocol or csum is not required.
 *
78
 *	PARTIAL: device is required to csum packet as seen by hard_start_xmit
79 80
 *	from skb->csum_start to the end and to record the checksum
 *	at skb->csum_start + skb->csum_offset.
Linus Torvalds's avatar
Linus Torvalds committed
81 82 83 84 85 86 87 88 89 90
 *
 *	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)
91
 *	NETIF_F_IPV6_CSUM about as dumb as the last one but does IPv6 instead.
Linus Torvalds's avatar
Linus Torvalds committed
92 93 94 95 96
 *
 *	Any questions? No questions, good. 		--ANK
 */

struct net_device;
97
struct scatterlist;
Jens Axboe's avatar
Jens Axboe committed
98
struct pipe_inode_info;
Linus Torvalds's avatar
Linus Torvalds committed
99

100
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
Linus Torvalds's avatar
Linus Torvalds committed
101 102 103
struct nf_conntrack {
	atomic_t use;
};
104
#endif
Linus Torvalds's avatar
Linus Torvalds committed
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

#ifdef CONFIG_BRIDGE_NETFILTER
struct nf_bridge_info {
	atomic_t use;
	struct net_device *physindev;
	struct net_device *physoutdev;
	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;
134 135
	__u32 page_offset;
	__u32 size;
Linus Torvalds's avatar
Linus Torvalds committed
136 137 138 139 140 141 142
};

/* 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;
143
	unsigned short	nr_frags;
144 145 146 147
	unsigned short	gso_size;
	/* Warning: this field is not always filled in (UFO)! */
	unsigned short	gso_segs;
	unsigned short  gso_type;
Al Viro's avatar
Al Viro committed
148
	__be32          ip6_frag_id;
Linus Torvalds's avatar
Linus Torvalds committed
149 150 151 152 153 154
	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
155 156
 * the entire skb->data.  A clone of a headerless skb holds the length of
 * the header in skb->hdr_len.
Linus Torvalds's avatar
Linus Torvalds committed
157 158 159 160 161 162 163 164 165 166
 *
 * 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)

167 168 169 170 171 172 173

enum {
	SKB_FCLONE_UNAVAILABLE,
	SKB_FCLONE_ORIG,
	SKB_FCLONE_CLONE,
};

174 175
enum {
	SKB_GSO_TCPV4 = 1 << 0,
176
	SKB_GSO_UDP = 1 << 1,
177 178 179

	/* This indicates the skb is from an untrusted source. */
	SKB_GSO_DODGY = 1 << 2,
Michael Chan's avatar
Michael Chan committed
180 181

	/* This indicates the tcp segment has CWR set. */
182 183 184
	SKB_GSO_TCP_ECN = 1 << 3,

	SKB_GSO_TCPV6 = 1 << 4,
185 186
};

187 188 189 190 191 192 193 194 195 196
#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

Linus Torvalds's avatar
Linus Torvalds committed
197 198 199 200 201
/** 
 *	struct sk_buff - socket buffer
 *	@next: Next buffer in list
 *	@prev: Previous buffer in list
 *	@sk: Socket we are owned by
Herbert Xu's avatar
Herbert Xu committed
202
 *	@tstamp: Time we arrived
Linus Torvalds's avatar
Linus Torvalds committed
203
 *	@dev: Device we arrived on/are leaving by
Randy Dunlap's avatar
Randy Dunlap committed
204
 *	@transport_header: Transport layer header
205 206
 *	@network_header: Network layer header
 *	@mac_header: Link layer header
207 208
 *	@dst: destination entry
 *	@sp: the security path, used for xfrm
Linus Torvalds's avatar
Linus Torvalds committed
209 210 211 212
 *	@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
213
 *	@hdr_len: writable header length of cloned skb
214 215 216
 *	@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
217
 *	@local_df: allow local fragmentation
Linus Torvalds's avatar
Linus Torvalds committed
218 219 220
 *	@cloned: Head may be cloned (check refcnt to be sure)
 *	@nohdr: Payload reference only, must not modify header
 *	@pkt_type: Packet class
221
 *	@fclone: skbuff clone status
Linus Torvalds's avatar
Linus Torvalds committed
222 223 224 225 226 227 228 229 230 231
 *	@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
232
 *	@mark: Generic packet mark
Linus Torvalds's avatar
Linus Torvalds committed
233
 *	@nfct: Associated connection, if any
234
 *	@ipvs_property: skbuff is owned by ipvs
235 236
 *	@peeked: this packet has been seen already, so stats have been
 *		done for it, don't do them again
237
 *	@nf_trace: netfilter packet trace flag
Linus Torvalds's avatar
Linus Torvalds committed
238
 *	@nfctinfo: Relationship of this skb to the connection
Randy Dunlap's avatar
Randy Dunlap committed
239
 *	@nfct_reasm: netfilter conntrack re-assembly pointer
Linus Torvalds's avatar
Linus Torvalds committed
240
 *	@nf_bridge: Saved data about a bridged frame - see br_netfilter.c
241 242
 *	@iif: ifindex of device we arrived on
 *	@queue_mapping: Queue mapping for multiqueue devices
Linus Torvalds's avatar
Linus Torvalds committed
243 244
 *	@tc_index: Traffic control index
 *	@tc_verd: traffic control verdict
Randy Dunlap's avatar
Randy Dunlap committed
245 246
 *	@dma_cookie: a cookie to one of several possible DMA operations
 *		done by skb DMA functions
247
 *	@secmark: security marking
Linus Torvalds's avatar
Linus Torvalds committed
248 249 250 251 252 253 254 255
 */

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

	struct sock		*sk;
256
	ktime_t			tstamp;
Linus Torvalds's avatar
Linus Torvalds committed
257 258 259 260 261 262 263 264 265 266 267
	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.
	 */
268
	char			cb[48];
Linus Torvalds's avatar
Linus Torvalds committed
269 270

	unsigned int		len,
271 272 273
				data_len;
	__u16			mac_len,
				hdr_len;
Al Viro's avatar
Al Viro committed
274 275
	union {
		__wsum		csum;
276 277 278 279
		struct {
			__u16	csum_start;
			__u16	csum_offset;
		};
Al Viro's avatar
Al Viro committed
280
	};
Linus Torvalds's avatar
Linus Torvalds committed
281
	__u32			priority;
282 283 284
	__u8			local_df:1,
				cloned:1,
				ip_summed:2,
285 286
				nohdr:1,
				nfctinfo:3;
287
	__u8			pkt_type:3,
288
				fclone:2,
289
				ipvs_property:1,
290
				peeked:1,
291
				nf_trace:1;
292
	__be16			protocol;
Linus Torvalds's avatar
Linus Torvalds committed
293 294

	void			(*destructor)(struct sk_buff *skb);
295
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
296
	struct nf_conntrack	*nfct;
297 298
	struct sk_buff		*nfct_reasm;
#endif
Linus Torvalds's avatar
Linus Torvalds committed
299 300 301
#ifdef CONFIG_BRIDGE_NETFILTER
	struct nf_bridge_info	*nf_bridge;
#endif
302 303

	int			iif;
304
#ifdef CONFIG_NETDEVICES_MULTIQUEUE
305
	__u16			queue_mapping;
306
#endif
Linus Torvalds's avatar
Linus Torvalds committed
307
#ifdef CONFIG_NET_SCHED
308
	__u16			tc_index;	/* traffic control index */
Linus Torvalds's avatar
Linus Torvalds committed
309
#ifdef CONFIG_NET_CLS_ACT
310
	__u16			tc_verd;	/* traffic control verdict */
Linus Torvalds's avatar
Linus Torvalds committed
311 312
#endif
#endif
313 314
	/* 2 byte hole */

315 316 317
#ifdef CONFIG_NET_DMA
	dma_cookie_t		dma_cookie;
#endif
318 319 320
#ifdef CONFIG_NETWORK_SECMARK
	__u32			secmark;
#endif
Linus Torvalds's avatar
Linus Torvalds committed
321

322
	__u32			mark;
Linus Torvalds's avatar
Linus Torvalds committed
323

324 325 326
	sk_buff_data_t		transport_header;
	sk_buff_data_t		network_header;
	sk_buff_data_t		mac_header;
Linus Torvalds's avatar
Linus Torvalds committed
327
	/* These elements must be at the end, see alloc_skb() for details.  */
328
	sk_buff_data_t		tail;
329
	sk_buff_data_t		end;
Linus Torvalds's avatar
Linus Torvalds committed
330
	unsigned char		*head,
331
				*data;
332 333
	unsigned int		truesize;
	atomic_t		users;
Linus Torvalds's avatar
Linus Torvalds committed
334 335 336 337 338 339 340 341 342 343
};

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

#include <asm/system.h>

344
extern void kfree_skb(struct sk_buff *skb);
Linus Torvalds's avatar
Linus Torvalds committed
345
extern void	       __kfree_skb(struct sk_buff *skb);
346
extern struct sk_buff *__alloc_skb(unsigned int size,
347
				   gfp_t priority, int fclone, int node);
348
static inline struct sk_buff *alloc_skb(unsigned int size,
349
					gfp_t priority)
350
{
351
	return __alloc_skb(size, priority, 0, -1);
352 353 354
}

static inline struct sk_buff *alloc_skb_fclone(unsigned int size,
355
					       gfp_t priority)
356
{
357
	return __alloc_skb(size, priority, 1, -1);
358 359
}

Herbert Xu's avatar
Herbert Xu committed
360
extern struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src);
Victor Fusco's avatar
Victor Fusco committed
361
extern struct sk_buff *skb_clone(struct sk_buff *skb,
362
				 gfp_t priority);
Victor Fusco's avatar
Victor Fusco committed
363
extern struct sk_buff *skb_copy(const struct sk_buff *skb,
364
				gfp_t priority);
Victor Fusco's avatar
Victor Fusco committed
365
extern struct sk_buff *pskb_copy(struct sk_buff *skb,
366
				 gfp_t gfp_mask);
Linus Torvalds's avatar
Linus Torvalds committed
367
extern int	       pskb_expand_head(struct sk_buff *skb,
Victor Fusco's avatar
Victor Fusco committed
368
					int nhead, int ntail,
369
					gfp_t gfp_mask);
Linus Torvalds's avatar
Linus Torvalds committed
370 371 372 373
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,
374
				       gfp_t priority);
375 376 377 378 379
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);
380
extern int	       skb_pad(struct sk_buff *skb, int pad);
Linus Torvalds's avatar
Linus Torvalds committed
381 382 383 384 385
#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);
386 387 388 389
extern void	      skb_truesize_bug(struct sk_buff *skb);

static inline void skb_truesize_check(struct sk_buff *skb)
{
390 391 392
	int len = sizeof(struct sk_buff) + skb->len;

	if (unlikely((int)skb->truesize < len))
393 394
		skb_truesize_bug(skb);
}
Linus Torvalds's avatar
Linus Torvalds committed
395

396 397 398 399 400
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);

401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418
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);

419 420 421 422
extern unsigned int   skb_find_text(struct sk_buff *skb, unsigned int from,
				    unsigned int to, struct ts_config *config,
				    struct ts_state *state);

423 424 425 426 427 428 429 430 431 432 433 434
#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

Linus Torvalds's avatar
Linus Torvalds committed
435
/* Internal */
436
#define skb_shinfo(SKB)	((struct skb_shared_info *)(skb_end_pointer(SKB)))
Linus Torvalds's avatar
Linus Torvalds committed
437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539

/**
 *	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.
 */
Victor Fusco's avatar
Victor Fusco committed
540
static inline struct sk_buff *skb_share_check(struct sk_buff *skb,
541
					      gfp_t pri)
Linus Torvalds's avatar
Linus Torvalds committed
542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571
{
	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.
 */
572
static inline struct sk_buff *skb_unshare(struct sk_buff *skb,
573
					  gfp_t pri)
Linus Torvalds's avatar
Linus Torvalds committed
574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636
{
	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;
}

637 638 639 640 641 642 643 644
/*
 * 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.
 */
Linus Torvalds's avatar
Linus Torvalds committed
645 646 647 648 649 650 651
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;
}

652 653 654 655 656 657 658
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);
}

Linus Torvalds's avatar
Linus Torvalds committed
659 660 661 662 663 664 665 666
/*
 *	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.
 */

/**
667
 *	__skb_queue_after - queue a buffer at the list head
Linus Torvalds's avatar
Linus Torvalds committed
668
 *	@list: list to use
669
 *	@prev: place after this buffer
Linus Torvalds's avatar
Linus Torvalds committed
670 671
 *	@newsk: buffer to queue
 *
672
 *	Queue a buffer int the middle of a list. This function takes no locks
Linus Torvalds's avatar
Linus Torvalds committed
673 674 675 676
 *	and you must therefore hold required locks before calling it.
 *
 *	A buffer cannot be placed on two lists at the same time.
 */
677 678 679
static inline void __skb_queue_after(struct sk_buff_head *list,
				     struct sk_buff *prev,
				     struct sk_buff *newsk)
Linus Torvalds's avatar
Linus Torvalds committed
680
{
681
	struct sk_buff *next;
Linus Torvalds's avatar
Linus Torvalds committed
682
	list->qlen++;
683

Linus Torvalds's avatar
Linus Torvalds committed
684 685 686 687 688 689
	next = prev->next;
	newsk->next = next;
	newsk->prev = prev;
	next->prev  = prev->next = newsk;
}

690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706
/**
 *	__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);
}

Linus Torvalds's avatar
Linus Torvalds committed
707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762
/**
 *	__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.
 */
David S. Miller's avatar
David S. Miller committed
763
extern void        skb_insert(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list);
Linus Torvalds's avatar
Linus Torvalds committed
764 765 766 767 768 769 770 771 772 773 774 775 776
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.
 */
David S. Miller's avatar
David S. Miller committed
777 778
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)
Linus Torvalds's avatar
Linus Torvalds committed
779
{
David S. Miller's avatar
David S. Miller committed
780
	__skb_insert(newsk, old, old->next, list);
Linus Torvalds's avatar
Linus Torvalds committed
781 782 783 784 785 786
}

/*
 * remove sk_buff from list. _Must_ be called atomically, and with
 * the list known..
 */
David S. Miller's avatar
David S. Miller committed
787
extern void	   skb_unlink(struct sk_buff *skb, struct sk_buff_head *list);
Linus Torvalds's avatar
Linus Torvalds committed
788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854
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))

855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885
#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;
}
886

887 888
#endif /* NET_SKBUFF_DATA_USES_OFFSET */

Linus Torvalds's avatar
Linus Torvalds committed
889 890 891 892 893
/*
 *	Add data to an sk_buff
 */
static inline unsigned char *__skb_put(struct sk_buff *skb, unsigned int len)
{
894
	unsigned char *tmp = skb_tail_pointer(skb);
Linus Torvalds's avatar
Linus Torvalds committed
895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911
	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)
{
912
	unsigned char *tmp = skb_tail_pointer(skb);
Linus Torvalds's avatar
Linus Torvalds committed
913 914 915
	SKB_LINEAR_ASSERT(skb);
	skb->tail += len;
	skb->len  += len;
916
	if (unlikely(skb->tail > skb->end))
Linus Torvalds's avatar
Linus Torvalds committed
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.
 */
999
static inline unsigned int skb_headroom(const struct sk_buff *skb)
Linus Torvalds's avatar
Linus Torvalds committed
1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011
{
	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)
{
1012
	return skb_is_nonlinear(skb) ? 0 : skb->end - skb->tail;
Linus Torvalds's avatar
Linus Torvalds committed
1013 1014 1015 1016 1017 1018 1019 1020 1021 1022
}

/**
 *	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.
 */
1023
static inline void skb_reserve(struct sk_buff *skb, int len)
Linus Torvalds's avatar
Linus Torvalds committed
1024 1025 1026 1027 1028
{
	skb->data += len;
	skb->tail += len;
}

1029
#ifdef NET_SKBUFF_DATA_USES_OFFSET
1030 1031
static inline unsigned char *skb_transport_header(const struct sk_buff *skb)
{
1032
	return skb->head + skb->transport_header;
1033 1034
}

1035 1036
static inline void skb_reset_transport_header(struct sk_buff *skb)
{
1037
	skb->transport_header = skb->data - skb->head;
1038 1039
}

1040 1041 1042
static inline void skb_set_transport_header(struct sk_buff *skb,
					    const int offset)
{
1043 1044
	skb_reset_transport_header(skb);
	skb->transport_header += offset;
1045 1046
}

1047 1048
static inline unsigned char *skb_network_header(const struct sk_buff *skb)
{
1049
	return skb->head + skb->network_header;
1050 1051
}

1052 1053
static inline void skb_reset_network_header(struct sk_buff *skb)
{
1054
	skb->network_header = skb->data - skb->head;
1055 1056
}

1057 1058
static inline void skb_set_network_header(struct sk_buff *skb, const int offset)
{
1059 1060
	skb_reset_network_header(skb);
	skb->network_header += offset;
1061 1062
}

1063
static inline unsigned char *skb_mac_header(const struct sk_buff *skb)
1064
{
1065
	return skb->head + skb->mac_header;
1066 1067
}

1068
static inline int skb_mac_header_was_set(const struct sk_buff *skb)
1069
{
1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114
	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;
1115 1116
}

1117 1118
static inline unsigned char *skb_mac_header(const struct sk_buff *skb)
{
1119
	return skb->mac_header;
1120 1121 1122 1123
}

static inline int skb_mac_header_was_set(const struct sk_buff *skb)
{
1124
	return skb->mac_header != NULL;
1125 1126
}

1127 1128
static inline void skb_reset_mac_header(struct sk_buff *skb)
{
1129
	skb->mac_header = skb->data;
1130 1131
}

1132 1133
static inline void skb_set_mac_header(struct sk_buff *skb, const int offset)
{
1134
	skb->mac_header = skb->data + offset;
1135
}
1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151
#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;
}
1152

Linus Torvalds's avatar
Linus Torvalds committed
1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176
/*
 * 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

1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195
/*
 * 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

1196
extern int ___pskb_trim(struct sk_buff *skb, unsigned int len);
Linus Torvalds's avatar
Linus Torvalds committed
1197 1198 1199

static inline void __skb_trim(struct sk_buff *skb, unsigned int len)
{
1200 1201 1202 1203
	if (unlikely(skb->data_len)) {
		WARN_ON(1);
		return;
	}
1204 1205
	skb->len = len;
	skb_set_tail_pointer(skb, len);
Linus Torvalds's avatar
Linus Torvalds committed
1206 1207 1208 1209 1210 1211 1212 1213 1214
}

/**
 *	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.
1215
 *	The skb must be linear.
Linus Torvalds's avatar
Linus Torvalds committed
1216 1217 1218 1219 1220 1221 1222 1223 1224 1225
 */
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)
{
1226 1227 1228 1229
	if (skb->data_len)
		return ___pskb_trim(skb, len);
	__skb_trim(skb, len);
	return 0;
Linus Torvalds's avatar
Linus Torvalds committed
1230 1231 1232 1233 1234 1235 1236
}

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

1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251
/**
 *	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);
}

Linus Torvalds's avatar
Linus Torvalds committed
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
/**
 *	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);
}

/**
1285
 *	__dev_alloc_skb - allocate an skbuff for receiving
Linus Torvalds's avatar
Linus Torvalds committed
1286 1287 1288 1289 1290 1291 1292 1293
 *	@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.
 *
1294
 *	%NULL is returned if there is no free memory.
Linus Torvalds's avatar
Linus Torvalds committed
1295 1296
 */
static inline struct sk_buff *__dev_alloc_skb(unsigned int length,
1297
					      gfp_t gfp_mask)
Linus Torvalds's avatar
Linus Torvalds committed
1298
{
1299
	struct sk_buff *skb = alloc_skb(length + NET_SKB_PAD, gfp_mask);
Linus Torvalds's avatar
Linus Torvalds committed
1300
	if (likely(skb))
1301
		skb_reserve(skb, NET_SKB_PAD);
Linus Torvalds's avatar
Linus Torvalds committed
1302 1303 1304 1305
	return skb;
}

/**
1306
 *	dev_alloc_skb - allocate an skbuff for receiving
Linus Torvalds's avatar
Linus Torvalds committed
1307 1308 1309 1310 1311 1312 1313
 *	@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.
 *
1314
 *	%NULL is returned if there is no free memory. Although this function
Linus Torvalds's avatar
Linus Torvalds committed
1315 1316 1317 1318 1319 1320 1321
 *	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);
}

1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343
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);
}

1344 1345 1346 1347 1348 1349 1350 1351
/**
 *	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.
 */
1352
static inline int skb_clone_writable(struct sk_buff *skb, unsigned