Merge branch 'tcp_tsoffset'

[linux-2.6-block.git] / include / linux / skbuff.h

/*
 *	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/kmemcheck.h>
#include <linux/compiler.h>
#include <linux/time.h>
#include <linux/bug.h>
#include <linux/cache.h>

#include <linux/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>
#include <linux/dma-mapping.h>
#include <linux/netdev_features.h>

/* 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))

/* return minimum truesize of one skb containing X bytes of data */
#define SKB_TRUESIZE(X) ((X) +						\
			 SKB_DATA_ALIGN(sizeof(struct sk_buff)) +	\
			 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))

/* 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_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.
 *
 *	UNNECESSARY: device will do per protocol specific csum. Protocol drivers
 *	that do not want net to perform the checksum calculation should use
 *	this flag in their outgoing skbs.
 *	NETIF_F_FCOE_CRC  this indicates the device can do FCoE FC CRC
 *			  offload. Correspondingly, the FCoE protocol driver
 *			  stack should use CHECKSUM_UNNECESSARY.
 *
 *	Any questions? No questions, good. 		--ANK
 */

struct net_device;
struct scatterlist;
struct pipe_inode_info;

#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;
	unsigned int		mask;
	struct net_device	*physindev;
	struct net_device	*physoutdev;
	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 we
 * require 64K/PAGE_SIZE pages plus 1 additional page to allow for
 * buffers which do not start on a page boundary.
 *
 * Since GRO uses frags we allocate at least 16 regardless of page
 * size.
 */
#if (65536/PAGE_SIZE + 1) < 16
#define MAX_SKB_FRAGS 16UL
#else
#define MAX_SKB_FRAGS (65536/PAGE_SIZE + 1)
#endif

typedef struct skb_frag_struct skb_frag_t;

struct skb_frag_struct {
	struct {
		struct page *p;
	} page;
#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
	__u32 page_offset;
	__u32 size;
#else
	__u16 page_offset;
	__u16 size;
#endif
};

static inline unsigned int skb_frag_size(const skb_frag_t *frag)
{
	return frag->size;
}

static inline void skb_frag_size_set(skb_frag_t *frag, unsigned int size)
{
	frag->size = size;
}

static inline void skb_frag_size_add(skb_frag_t *frag, int delta)
{
	frag->size += delta;
}

static inline void skb_frag_size_sub(skb_frag_t *frag, int delta)
{
	frag->size -= delta;
}

#define HAVE_HW_TIME_STAMP

/**
 * struct skb_shared_hwtstamps - hardware time stamps
 * @hwtstamp:	hardware time stamp transformed into duration
 *		since arbitrary point in time
 * @syststamp:	hwtstamp transformed to system time base
 *
 * Software time stamps generated by ktime_get_real() are stored in
 * skb->tstamp. The relation between the different kinds of time
 * stamps is as follows:
 *
 * syststamp and tstamp can be compared against each other in
 * arbitrary combinations.  The accuracy of a
 * syststamp/tstamp/"syststamp from other device" comparison is
 * limited by the accuracy of the transformation into system time
 * base. This depends on the device driver and its underlying
 * hardware.
 *
 * hwtstamps can only be compared against other hwtstamps from
 * the same device.
 *
 * This structure is attached to packets as part of the
 * &skb_shared_info. Use skb_hwtstamps() to get a pointer.
 */
struct skb_shared_hwtstamps {
	ktime_t	hwtstamp;
	ktime_t	syststamp;
};

/* Definitions for tx_flags in struct skb_shared_info */
enum {
	/* generate hardware time stamp */
	SKBTX_HW_TSTAMP = 1 << 0,

	/* generate software time stamp */
	SKBTX_SW_TSTAMP = 1 << 1,

	/* device driver is going to provide hardware time stamp */
	SKBTX_IN_PROGRESS = 1 << 2,

	/* device driver supports TX zero-copy buffers */
	SKBTX_DEV_ZEROCOPY = 1 << 3,

	/* generate wifi status information (where possible) */
	SKBTX_WIFI_STATUS = 1 << 4,
};

/*
 * The callback notifies userspace to release buffers when skb DMA is done in
 * lower device, the skb last reference should be 0 when calling this.
 * The zerocopy_success argument is true if zero copy transmit occurred,
 * false on data copy or out of memory error caused by data copy attempt.
 * The ctx field is used to track device context.
 * The desc field is used to track userspace buffer index.
 */
struct ubuf_info {
	void (*callback)(struct ubuf_info *, bool zerocopy_success);
	void *ctx;
	unsigned long desc;
};

/* This data is invariant across clones and lives at
 * the end of the header data, ie. at skb->end.
 */
struct skb_shared_info {
	unsigned char	nr_frags;
	__u8		tx_flags;
	unsigned short	gso_size;
	/* Warning: this field is not always filled in (UFO)! */
	unsigned short	gso_segs;
	unsigned short  gso_type;
	struct sk_buff	*frag_list;
	struct skb_shared_hwtstamps hwtstamps;
	__be32          ip6_frag_id;

	/*
	 * Warning : all fields before dataref are cleared in __alloc_skb()
	 */
	atomic_t	dataref;

	/* Intermediate layers must ensure that destructor_arg
	 * remains valid until skb destructor */
	void *		destructor_arg;

	/* must be last field, see pskb_expand_head() */
	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,

	SKB_GSO_FCOE = 1 << 5,

	/* This indicates at least one fragment might be overwritten
	 * (as in vmsplice(), sendfile() ...)
	 * If we need to compute a TX checksum, we'll need to copy
	 * all frags to avoid possible bad checksum
	 */
	SKB_GSO_SHARED_FRAG = 1 << 6,
};

#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

#if defined(CONFIG_NF_DEFRAG_IPV4) || defined(CONFIG_NF_DEFRAG_IPV4_MODULE) || \
    defined(CONFIG_NF_DEFRAG_IPV6) || defined(CONFIG_NF_DEFRAG_IPV6_MODULE)
#define NET_SKBUFF_NF_DEFRAG_NEEDED 1
#endif

/** 
 *	struct sk_buff - socket buffer
 *	@next: Next buffer in list
 *	@prev: Previous buffer in list
 *	@tstamp: Time we arrived
 *	@sk: Socket we are owned by
 *	@dev: Device we arrived on/are leaving by
 *	@cb: Control buffer. Free for use by every layer. Put private vars here
 *	@_skb_refdst: destination entry (with norefcount bit)
 *	@sp: the security path, used for xfrm
 *	@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
 *	@priority: Packet queueing priority
 *	@local_df: allow local fragmentation
 *	@cloned: Head may be cloned (check refcnt to be sure)
 *	@ip_summed: Driver fed us an IP checksum
 *	@nohdr: Payload reference only, must not modify header
 *	@nfctinfo: Relationship of this skb to the connection
 *	@pkt_type: Packet class
 *	@fclone: skbuff clone status
 *	@ipvs_property: skbuff is owned by ipvs
 *	@peeked: this packet has been seen already, so stats have been
 *		done for it, don't do them again
 *	@nf_trace: netfilter packet trace flag
 *	@protocol: Packet protocol from driver
 *	@destructor: Destruct function
 *	@nfct: Associated connection, if any
 *	@nfct_reasm: netfilter conntrack re-assembly pointer
 *	@nf_bridge: Saved data about a bridged frame - see br_netfilter.c
 *	@skb_iif: ifindex of device we arrived on
 *	@tc_index: Traffic control index
 *	@tc_verd: traffic control verdict
 *	@rxhash: the packet hash computed on receive
 *	@queue_mapping: Queue mapping for multiqueue devices
 *	@ndisc_nodetype: router type (from link layer)
 *	@ooo_okay: allow the mapping of a socket to a queue to be changed
 *	@l4_rxhash: indicate rxhash is a canonical 4-tuple hash over transport
 *		ports.
 *	@wifi_acked_valid: wifi_acked was set
 *	@wifi_acked: whether frame was acked on wifi or not
 *	@no_fcs:  Request NIC to treat last 4 bytes as Ethernet FCS
 *	@dma_cookie: a cookie to one of several possible DMA operations
 *		done by skb DMA functions
 *	@secmark: security marking
 *	@mark: Generic packet mark
 *	@dropcount: total number of sk_receive_queue overflows
 *	@vlan_tci: vlan tag control information
 *	@inner_transport_header: Inner transport layer header (encapsulation)
 *	@inner_network_header: Network layer header (encapsulation)
 *	@transport_header: Transport layer header
 *	@network_header: Network layer header
 *	@mac_header: Link layer header
 *	@tail: Tail pointer
 *	@end: End pointer
 *	@head: Head of buffer
 *	@data: Data head pointer
 *	@truesize: Buffer size
 *	@users: User count - see {datagram,tcp}.c
 */

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

	ktime_t			tstamp;

	struct sock		*sk;
	struct net_device	*dev;

	/*
	 * 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] __aligned(8);

	unsigned long		_skb_refdst;
#ifdef CONFIG_XFRM
	struct	sec_path	*sp;
#endif
	unsigned int		len,
				data_len;
	__u16			mac_len,
				hdr_len;
	union {
		__wsum		csum;
		struct {
			__u16	csum_start;
			__u16	csum_offset;
		};
	};
	__u32			priority;
	kmemcheck_bitfield_begin(flags1);
	__u8			local_df:1,
				cloned:1,
				ip_summed:2,
				nohdr:1,
				nfctinfo:3;
	__u8			pkt_type:3,
				fclone:2,
				ipvs_property:1,
				peeked:1,
				nf_trace:1;
	kmemcheck_bitfield_end(flags1);
	__be16			protocol;

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

	int			skb_iif;

	__u32			rxhash;

	__u16			vlan_tci;

#ifdef CONFIG_NET_SCHED
	__u16			tc_index;	/* traffic control index */
#ifdef CONFIG_NET_CLS_ACT
	__u16			tc_verd;	/* traffic control verdict */
#endif
#endif

	__u16			queue_mapping;
	kmemcheck_bitfield_begin(flags2);
#ifdef CONFIG_IPV6_NDISC_NODETYPE
	__u8			ndisc_nodetype:2;
#endif
	__u8			pfmemalloc:1;
	__u8			ooo_okay:1;
	__u8			l4_rxhash:1;
	__u8			wifi_acked_valid:1;
	__u8			wifi_acked:1;
	__u8			no_fcs:1;
	__u8			head_frag:1;
	/* Encapsulation protocol and NIC drivers should use
	 * this flag to indicate to each other if the skb contains
	 * encapsulated packet or not and maybe use the inner packet
	 * headers if needed
	 */
	__u8			encapsulation:1;
	/* 7/9 bit hole (depending on ndisc_nodetype presence) */
	kmemcheck_bitfield_end(flags2);

#ifdef CONFIG_NET_DMA
	dma_cookie_t		dma_cookie;
#endif
#ifdef CONFIG_NETWORK_SECMARK
	__u32			secmark;
#endif
	union {
		__u32		mark;
		__u32		dropcount;
		__u32		avail_size;
	};

	sk_buff_data_t		inner_transport_header;
	sk_buff_data_t		inner_network_header;
	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>


#define SKB_ALLOC_FCLONE	0x01
#define SKB_ALLOC_RX		0x02

/* Returns true if the skb was allocated from PFMEMALLOC reserves */
static inline bool skb_pfmemalloc(const struct sk_buff *skb)
{
	return unlikely(skb->pfmemalloc);
}

/*
 * skb might have a dst pointer attached, refcounted or not.
 * _skb_refdst low order bit is set if refcount was _not_ taken
 */
#define SKB_DST_NOREF	1UL
#define SKB_DST_PTRMASK	~(SKB_DST_NOREF)

/**
 * skb_dst - returns skb dst_entry
 * @skb: buffer
 *
 * Returns skb dst_entry, regardless of reference taken or not.
 */
static inline struct dst_entry *skb_dst(const struct sk_buff *skb)
{
	/* If refdst was not refcounted, check we still are in a 
	 * rcu_read_lock section
	 */
	WARN_ON((skb->_skb_refdst & SKB_DST_NOREF) &&
		!rcu_read_lock_held() &&
		!rcu_read_lock_bh_held());
	return (struct dst_entry *)(skb->_skb_refdst & SKB_DST_PTRMASK);
}

/**
 * skb_dst_set - sets skb dst
 * @skb: buffer
 * @dst: dst entry
 *
 * Sets skb dst, assuming a reference was taken on dst and should
 * be released by skb_dst_drop()
 */
static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst)
{
	skb->_skb_refdst = (unsigned long)dst;
}

extern void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst);

/**
 * skb_dst_is_noref - Test if skb dst isn't refcounted
 * @skb: buffer
 */
static inline bool skb_dst_is_noref(const struct sk_buff *skb)
{
	return (skb->_skb_refdst & SKB_DST_NOREF) && skb_dst(skb);
}

static inline struct rtable *skb_rtable(const struct sk_buff *skb)
{
	return (struct rtable *)skb_dst(skb);
}