skbuff.h

来自「linux 内核源代码」· C头文件 代码 · 共 1,809 行 · 第 1/4 页

/*
 *	Definitions for the 'struct sk_buff' memory handlers.
 *
 *	Authors:
 *		Alan Cox, <[e-mail]>
 *		Florian La Roche, <[e-mail]>
 *
 *	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>
#include <linux/textsearch.h>
#include <net/checksum.h>
#include <linux/rcupdate.h>
#include <linux/dmaengine.h>
#include <linux/hrtimer.h>

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

/* Don't change this without changing skb_csum_unnecessary! */
#define CHECKSUM_NONE 0
#define CHECKSUM_UNNECESSARY 1
#define CHECKSUM_COMPLETE 2
#define CHECKSUM_PARTIAL 3

#define SKB_DATA_ALIGN(X)	(((X) + (SMP_CACHE_BYTES - 1)) & \
				 ~(SMP_CACHE_BYTES - 1))
#define SKB_WITH_OVERHEAD(X)	\
	((X) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
#define SKB_MAX_ORDER(X, ORDER) \
	SKB_WITH_OVERHEAD((PAGE_SIZE << (ORDER)) - (X))
#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)
 *
 *	COMPLETE: the most generic way. Device supplied checksum of _all_
 *	    the packet as seen by netif_rx in skb->csum.
 *	    NOTE: Even if device supports only some protocols, but
 *	    is able to produce some skb->csum, it MUST use COMPLETE,
 *	    not UNNECESSARY.
 *
 *	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.
 *
 * B. Checksumming on output.
 *
 *	NONE: skb is checksummed by protocol or csum is not required.
 *
 *	PARTIAL: device is required to csum packet as seen by hard_start_xmit
 *	from skb->csum_start to the end and to record the checksum
 *	at skb->csum_start + skb->csum_offset.
 *
 *	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)
 *	NETIF_F_IPV6_CSUM about as dumb as the last one but does IPv6 instead.
 *
 *	Any questions? No questions, good. 		--ANK
 */

struct net_device;
struct scatterlist;

#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
struct nf_conntrack {
	atomic_t use;
};
#endif

#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;
	__u32 page_offset;
	__u32 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;
	unsigned short	nr_frags;
	unsigned short	gso_size;
	/* Warning: this field is not always filled in (UFO)! */
	unsigned short	gso_segs;
	unsigned short  gso_type;
	__be32          ip6_frag_id;
	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
 * the entire skb->data.  A clone of a headerless skb holds the length of
 * the header in skb->hdr_len.
 *
 * 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)


enum {
	SKB_FCLONE_UNAVAILABLE,
	SKB_FCLONE_ORIG,
	SKB_FCLONE_CLONE,
};

enum {
	SKB_GSO_TCPV4 = 1 << 0,
	SKB_GSO_UDP = 1 << 1,

	/* This indicates the skb is from an untrusted source. */
	SKB_GSO_DODGY = 1 << 2,

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

	SKB_GSO_TCPV6 = 1 << 4,
};

#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

/** 
 *	struct sk_buff - socket buffer
 *	@next: Next buffer in list
 *	@prev: Previous buffer in list
 *	@sk: Socket we are owned by
 *	@tstamp: Time we arrived
 *	@dev: Device we arrived on/are leaving by
 *	@transport_header: Transport layer header
 *	@network_header: Network layer header
 *	@mac_header: Link layer header
 *	@dst: destination entry
 *	@sp: the security path, used for xfrm
 *	@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
 *	@hdr_len: writable header length of cloned skb
 *	@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
 *	@local_df: allow local fragmentation
 *	@cloned: Head may be cloned (check refcnt to be sure)
 *	@nohdr: Payload reference only, must not modify header
 *	@pkt_type: Packet class
 *	@fclone: skbuff clone status
 *	@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
 *	@mark: Generic packet mark
 *	@nfct: Associated connection, if any
 *	@ipvs_property: skbuff is owned by ipvs
 *	@nf_trace: netfilter packet trace flag
 *	@nfctinfo: Relationship of this skb to the connection
 *	@nfct_reasm: netfilter conntrack re-assembly pointer
 *	@nf_bridge: Saved data about a bridged frame - see br_netfilter.c
 *	@iif: ifindex of device we arrived on
 *	@queue_mapping: Queue mapping for multiqueue devices
 *	@tc_index: Traffic control index
 *	@tc_verd: traffic control verdict
 *	@dma_cookie: a cookie to one of several possible DMA operations
 *		done by skb DMA functions
 *	@secmark: security marking
 */

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

	struct sock		*sk;
	ktime_t			tstamp;
	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.
	 */
	char			cb[48];

	unsigned int		len,
				data_len;
	__u16			mac_len,
				hdr_len;
	union {
		__wsum		csum;
		struct {
			__u16	csum_start;
			__u16	csum_offset;
		};
	};
	__u32			priority;
	__u8			local_df:1,
				cloned:1,
				ip_summed:2,
				nohdr:1,
				nfctinfo:3;
	__u8			pkt_type:3,
				fclone:2,
				ipvs_property:1,
				nf_trace:1;
	__be16			protocol;

	void			(*destructor)(struct sk_buff *skb);
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
	struct nf_conntrack	*nfct;
	struct sk_buff		*nfct_reasm;
#endif
#ifdef CONFIG_BRIDGE_NETFILTER
	struct nf_bridge_info	*nf_bridge;
#endif

	int			iif;
#ifdef CONFIG_NETDEVICES_MULTIQUEUE
	__u16			queue_mapping;
#endif
#ifdef CONFIG_NET_SCHED
	__u16			tc_index;	/* traffic control index */
#ifdef CONFIG_NET_CLS_ACT
	__u16			tc_verd;	/* traffic control verdict */
#endif
#endif
	/* 2 byte hole */

#ifdef CONFIG_NET_DMA
	dma_cookie_t		dma_cookie;
#endif
#ifdef CONFIG_NETWORK_SECMARK
	__u32			secmark;
#endif

	__u32			mark;

	sk_buff_data_t		transport_header;
	sk_buff_data_t		network_header;
	sk_buff_data_t		mac_header;
	/* These elements must be at the end, see alloc_skb() for details.  */
	sk_buff_data_t		tail;
	sk_buff_data_t		end;
	unsigned char		*head,
				*data;
	unsigned int		truesize;
	atomic_t		users;
};

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

#include <asm/system.h>

extern void kfree_skb(struct sk_buff *skb);
extern void	       __kfree_skb(struct sk_buff *skb);
extern struct sk_buff *__alloc_skb(unsigned int size,
				   gfp_t priority, int fclone, int node);
static inline struct sk_buff *alloc_skb(unsigned int size,
					gfp_t priority)
{
	return __alloc_skb(size, priority, 0, -1);
}

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

extern struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src);
extern struct sk_buff *skb_clone(struct sk_buff *skb,
				 gfp_t priority);
extern struct sk_buff *skb_copy(const struct sk_buff *skb,
				gfp_t priority);
extern struct sk_buff *pskb_copy(struct sk_buff *skb,
				 gfp_t gfp_mask);
extern int	       pskb_expand_head(struct sk_buff *skb,
					int nhead, int ntail,
					gfp_t gfp_mask);
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,
				       gfp_t priority);
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);
extern int	       skb_pad(struct sk_buff *skb, int pad);
#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);
extern void	      skb_truesize_bug(struct sk_buff *skb);

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

	if (unlikely((int)skb->truesize < len))
		skb_truesize_bug(skb);
}

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);

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);

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

#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

/* Internal */
#define skb_shinfo(SKB)	((struct skb_shared_info *)(skb_end_pointer(SKB)))

/**
 *	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.