linux-stable/include/linux/skbuff.h
Eric Dumazet 27b75c95f1 net: avoid RCU for NOCACHE dst
There is no point using RCU for dst we allocate for a very short time
(used once).

Change dst_release() to take DST_NOCACHE into account, but also change
skb_dst_set_noref() to force a refcount increment for such dst.

This is a _huge_ gain, because we dont waste memory to store xx thousand
of dsts. Instead of queueing them to RCU, we can free them instantly.

CPU caches can stay hot, re-using same memory blocks to hold temporary
dsts.

Note : remove unneeded smp_mb__before_atomic_dec(); in dst_release(),
since atomic_dec_return() implies a full memory barrier.

Stress test, 160.000.000 udp frames sent, IP route cache disabled
(DDOS).

Before:

real    0m38.091s
user    0m13.189s
sys     7m53.018s

After:

real	0m29.946s
user	0m12.157s
sys	7m40.605s

For reference, if IP route cache was enabled :

real	0m32.030s
user	0m10.521s
sys	8m15.243s

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-20 03:02:23 -07:00

2231 lines
61 KiB
C

/*
* 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/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>
/* 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;
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;
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;
#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
__u32 page_offset;
__u32 size;
#else
__u16 page_offset;
__u16 size;
#endif
};
#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,
/* ensure the originating sk reference is available on driver level */
SKBTX_DRV_NEEDS_SK_REF = 1 << 3,
};
/* This data is invariant across clones and lives at
* the end of the header data, ie. at skb->end.
*/
struct skb_shared_info {
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;
__u8 tx_flags;
struct sk_buff *frag_list;
struct skb_shared_hwtstamps hwtstamps;
/*
* 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,
};
#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
* @_skb_refdst: destination entry (with norefcount bit)
* @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
* @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
* @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
* @skb_iif: ifindex of device we arrived on
* @rxhash: the packet hash computed on receive
* @queue_mapping: Queue mapping for multiqueue devices
* @tc_index: Traffic control index
* @tc_verd: traffic control verdict
* @ndisc_nodetype: router type (from link layer)
* @dma_cookie: a cookie to one of several possible DMA operations
* done by skb DMA functions
* @secmark: security marking
* @vlan_tci: vlan tag control information
*/
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;
struct sk_buff *nfct_reasm;
#endif
#ifdef CONFIG_BRIDGE_NETFILTER
struct nf_bridge_info *nf_bridge;
#endif
int skb_iif;
#ifdef CONFIG_NET_SCHED
__u16 tc_index; /* traffic control index */
#ifdef CONFIG_NET_CLS_ACT
__u16 tc_verd; /* traffic control verdict */
#endif
#endif
__u32 rxhash;
kmemcheck_bitfield_begin(flags2);
__u16 queue_mapping:16;
#ifdef CONFIG_IPV6_NDISC_NODETYPE
__u8 ndisc_nodetype:2,
deliver_no_wcard:1;
#else
__u8 deliver_no_wcard:1;
#endif
kmemcheck_bitfield_end(flags2);
/* 0/14 bit hole */
#ifdef CONFIG_NET_DMA
dma_cookie_t dma_cookie;
#endif
#ifdef CONFIG_NETWORK_SECMARK
__u32 secmark;
#endif
union {
__u32 mark;
__u32 dropcount;
};
__u16 vlan_tci;
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>
/*
* 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 isnt 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);
}
extern void kfree_skb(struct sk_buff *skb);
extern void consume_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, NUMA_NO_NODE);
}
static inline struct sk_buff *alloc_skb_fclone(unsigned int size,
gfp_t priority)
{
return __alloc_skb(size, priority, 1, NUMA_NO_NODE);
}
extern bool skb_recycle_check(struct sk_buff *skb, int skb_size);
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) consume_skb(a)
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);
extern __u32 __skb_get_rxhash(struct sk_buff *skb);
static inline __u32 skb_get_rxhash(struct sk_buff *skb)
{
if (!skb->rxhash)
skb->rxhash = __skb_get_rxhash(skb);
return skb->rxhash;
}
#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)))
static inline struct skb_shared_hwtstamps *skb_hwtstamps(struct sk_buff *skb)
{
return &skb_shinfo(skb)->hwtstamps;
}
/**
* 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_queue_is_last - check if skb is the last entry in the queue
* @list: queue head
* @skb: buffer
*
* Returns true if @skb is the last buffer on the list.
*/
static inline bool skb_queue_is_last(const struct sk_buff_head *list,
const struct sk_buff *skb)
{
return skb->next == (struct sk_buff *)list;
}
/**
* skb_queue_is_first - check if skb is the first entry in the queue
* @list: queue head
* @skb: buffer
*
* Returns true if @skb is the first buffer on the list.
*/
static inline bool skb_queue_is_first(const struct sk_buff_head *list,
const struct sk_buff *skb)
{
return skb->prev == (struct sk_buff *)list;
}
/**
* skb_queue_next - return the next packet in the queue
* @list: queue head
* @skb: current buffer
*
* Return the next packet in @list after @skb. It is only valid to
* call this if skb_queue_is_last() evaluates to false.
*/
static inline struct sk_buff *skb_queue_next(const struct sk_buff_head *list,
const struct sk_buff *skb)
{
/* This BUG_ON may seem severe, but if we just return then we
* are going to dereference garbage.
*/
BUG_ON(skb_queue_is_last(list, skb));
return skb->next;
}
/**
* skb_queue_prev - return the prev packet in the queue
* @list: queue head
* @skb: current buffer
*
* Return the prev packet in @list before @skb. It is only valid to
* call this if skb_queue_is_first() evaluates to false.
*/
static inline struct sk_buff *skb_queue_prev(const struct sk_buff_head *list,
const struct sk_buff *skb)
{
/* This BUG_ON may seem severe, but if we just return then we
* are going to dereference garbage.
*/
BUG_ON(skb_queue_is_first(list, skb));
return skb->prev;
}
/**
* 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.
*/
static inline struct sk_buff *skb_share_check(struct sk_buff *skb,
gfp_t pri)
{
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.
*/
static inline struct sk_buff *skb_unshare(struct sk_buff *skb,
gfp_t pri)
{
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 - peek at the head of an &sk_buff_head
* @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 - peek at the tail of an &sk_buff_head
* @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;
}
/**
* __skb_queue_head_init - initialize non-spinlock portions of sk_buff_head
* @list: queue to initialize
*
* This initializes only the list and queue length aspects of
* an sk_buff_head object. This allows to initialize the list
* aspects of an sk_buff_head without reinitializing things like
* the spinlock. It can also be used for on-stack sk_buff_head
* objects where the spinlock is known to not be used.
*/
static inline void __skb_queue_head_init(struct sk_buff_head *list)
{
list->prev = list->next = (struct sk_buff *)list;
list->qlen = 0;
}
/*
* 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.
*/
static inline void skb_queue_head_init(struct sk_buff_head *list)
{
spin_lock_init(&list->lock);
__skb_queue_head_init(list);
}
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);
}
/*
* Insert an sk_buff on a list.
*
* The "__skb_xxxx()" functions are the non-atomic ones that
* can only be called with interrupts disabled.
*/
extern void skb_insert(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list);
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++;
}
static inline void __skb_queue_splice(const struct sk_buff_head *list,
struct sk_buff *prev,
struct sk_buff *next)
{
struct sk_buff *first = list->next;
struct sk_buff *last = list->prev;
first->prev = prev;
prev->next = first;
last->next = next;
next->prev = last;
}
/**
* skb_queue_splice - join two skb lists, this is designed for stacks
* @list: the new list to add
* @head: the place to add it in the first list
*/
static inline void skb_queue_splice(const struct sk_buff_head *list,
struct sk_buff_head *head)
{
if (!skb_queue_empty(list)) {
__skb_queue_splice(list, (struct sk_buff *) head, head->next);
head->qlen += list->qlen;
}
}
/**
* skb_queue_splice - join two skb lists and reinitialise the emptied list
* @list: the new list to add
* @head: the place to add it in the first list
*
* The list at @list is reinitialised
*/
static inline void skb_queue_splice_init(struct sk_buff_head *list,
struct sk_buff_head *head)
{
if (!skb_queue_empty(list)) {
__skb_queue_splice(list, (struct sk_buff *) head, head->next);
head->qlen += list->qlen;
__skb_queue_head_init(list);
}
}
/**
* skb_queue_splice_tail - join two skb lists, each list being a queue
* @list: the new list to add
* @head: the place to add it in the first list
*/
static inline void skb_queue_splice_tail(const struct sk_buff_head *list,
struct sk_buff_head *head)
{
if (!skb_queue_empty(list)) {
__skb_queue_splice(list, head->prev, (struct sk_buff *) head);
head->qlen += list->qlen;
}
}
/**
* skb_queue_splice_tail - join two skb lists and reinitialise the emptied list
* @list: the new list to add
* @head: the place to add it in the first list
*
* Each of the lists is a queue.
* The list at @list is reinitialised
*/
static inline void skb_queue_splice_tail_init(struct sk_buff_head *list,
struct sk_buff_head *head)
{
if (!skb_queue_empty(list)) {
__skb_queue_splice(list, head->prev, (struct sk_buff *) head);
head->qlen += list->qlen;
__skb_queue_head_init(list);
}
}
/**
* __skb_queue_after - queue a buffer at the list head
* @list: list to use
* @prev: place after this buffer
* @newsk: buffer to queue
*
* Queue a buffer int the middle 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.
*/
static inline void __skb_queue_after(struct sk_buff_head *list,
struct sk_buff *prev,
struct sk_buff *newsk)
{
__skb_insert(newsk, prev, prev->next, list);
}
extern void skb_append(struct sk_buff *old, struct sk_buff *newsk,
struct sk_buff_head *list);
static inline void __skb_queue_before(struct sk_buff_head *list,
struct sk_buff *next,
struct sk_buff *newsk)
{
__skb_insert(newsk, next->prev, next, list);
}
/**
* __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);
}
/**
* __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)
{
__skb_queue_before(list, (struct sk_buff *)list, newsk);
}
/*
* remove sk_buff from list. _Must_ be called atomically, and with
* the list known..
*/
extern void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list);
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;
}
/**
* __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 *skb = skb_peek(list);
if (skb)
__skb_unlink(skb, list);
return skb;
}
/**
* __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;
}
extern void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page,
int off, int size);
#define SKB_PAGE_ASSERT(skb) BUG_ON(skb_shinfo(skb)->nr_frags)
#define SKB_FRAG_ASSERT(skb) BUG_ON(skb_has_frag_list(skb))
#define SKB_LINEAR_ASSERT(skb) BUG_ON(skb_is_nonlinear(skb))
#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;
}
#endif /* NET_SKBUFF_DATA_USES_OFFSET */
/*
* Add data to an sk_buff
*/
extern unsigned char *skb_put(struct sk_buff *skb, unsigned int len);
static inline unsigned char *__skb_put(struct sk_buff *skb, unsigned int len)
{
unsigned char *tmp = skb_tail_pointer(skb);
SKB_LINEAR_ASSERT(skb);
skb->tail += len;
skb->len += len;
return tmp;
}
extern unsigned char *skb_push(struct sk_buff *skb, unsigned int len);
static inline unsigned char *__skb_push(struct sk_buff *skb, unsigned int len)
{
skb->data -= len;
skb->len += len;
return skb->data;
}
extern unsigned char *skb_pull(struct sk_buff *skb, unsigned int len);
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;
}
static inline unsigned char *skb_pull_inline(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 unsigned 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)
{
return skb_is_nonlinear(skb) ? 0 : skb->end - skb->tail;
}
/**
* 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.
*/
static inline void skb_reserve(struct sk_buff *skb, int len)
{
skb->data += len;
skb->tail += len;
}
#ifdef NET_SKBUFF_DATA_USES_OFFSET
static inline unsigned char *skb_transport_header(const struct sk_buff *skb)
{
return skb->head + skb->transport_header;
}
static inline void skb_reset_transport_header(struct sk_buff *skb)
{
skb->transport_header = skb->data - skb->head;
}
static inline void skb_set_transport_header(struct sk_buff *skb,
const int offset)
{
skb_reset_transport_header(skb);
skb->transport_header += offset;
}
static inline unsigned char *skb_network_header(const struct sk_buff *skb)
{
return skb->head + skb->network_header;
}
static inline void skb_reset_network_header(struct sk_buff *skb)
{
skb->network_header = skb->data - skb->head;
}
static inline void skb_set_network_header(struct sk_buff *skb, const int offset)
{
skb_reset_network_header(skb);
skb->network_header += offset;
}
static inline unsigned char *skb_mac_header(const struct sk_buff *skb)
{
return skb->head + skb->mac_header;
}
static inline int skb_mac_header_was_set(const struct sk_buff *skb)
{
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;
}
static inline unsigned char *skb_mac_header(const struct sk_buff *skb)
{
return skb->mac_header;
}
static inline int skb_mac_header_was_set(const struct sk_buff *skb)
{
return skb->mac_header != NULL;
}
static inline void skb_reset_mac_header(struct sk_buff *skb)
{
skb->mac_header = skb->data;
}
static inline void skb_set_mac_header(struct sk_buff *skb, const int offset)
{
skb->mac_header = skb->data + offset;
}
#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;
}
static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len)
{
return pskb_may_pull(skb, skb_network_offset(skb) + len);
}
/*
* 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(skb, 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
/*
* 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
* 32 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 32 bytes of
* headroom, you should not reduce this.
*
* Using max(32, L1_CACHE_BYTES) makes sense (especially with RPS)
* to reduce average number of cache lines per packet.
* get_rps_cpus() for example only access one 64 bytes aligned block :
* NET_IP_ALIGN(2) + ethernet_header(14) + IP_header(20/40) + ports(8)
*/
#ifndef NET_SKB_PAD
#define NET_SKB_PAD max(32, L1_CACHE_BYTES)
#endif
extern int ___pskb_trim(struct sk_buff *skb, unsigned int len);
static inline void __skb_trim(struct sk_buff *skb, unsigned int len)
{
if (unlikely(skb->data_len)) {
WARN_ON(1);
return;
}
skb->len = len;
skb_set_tail_pointer(skb, len);
}
extern void skb_trim(struct sk_buff *skb, unsigned int len);
static inline int __pskb_trim(struct sk_buff *skb, unsigned int len)
{
if (skb->data_len)
return ___pskb_trim(skb, len);
__skb_trim(skb, len);
return 0;
}
static inline int pskb_trim(struct sk_buff *skb, unsigned int len)
{
return (len < skb->len) ? __pskb_trim(skb, len) : 0;
}
/**
* 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);
}
/**
* 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);
}
/**
* __dev_alloc_skb - allocate an skbuff for receiving
* @length: length to allocate
* @gfp_mask: get_free_pages mask, passed to alloc_skb
*
* Allocate a new &sk_buff and assign it a usage count of one. The
* buffer has unspecified headroom built in. Users should allocate
* the headroom they think they need without accounting for the
* built in space. The built in space is used for optimisations.
*
* %NULL is returned if there is no free memory.
*/
static inline struct sk_buff *__dev_alloc_skb(unsigned int length,
gfp_t gfp_mask)
{
struct sk_buff *skb = alloc_skb(length + NET_SKB_PAD, gfp_mask);
if (likely(skb))
skb_reserve(skb, NET_SKB_PAD);
return skb;
}
extern struct sk_buff *dev_alloc_skb(unsigned int length);
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);
}
static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev,
unsigned int length)
{
struct sk_buff *skb = netdev_alloc_skb(dev, length + NET_IP_ALIGN);
if (NET_IP_ALIGN && skb)
skb_reserve(skb, NET_IP_ALIGN);
return skb;
}
/**
* __netdev_alloc_page - allocate a page for ps-rx on a specific device
* @dev: network device to receive on
* @gfp_mask: alloc_pages_node mask
*
* Allocate a new page. dev currently unused.
*
* %NULL is returned if there is no free memory.
*/
static inline struct page *__netdev_alloc_page(struct net_device *dev, gfp_t gfp_mask)
{
return alloc_pages_node(NUMA_NO_NODE, gfp_mask, 0);
}
/**
* netdev_alloc_page - allocate a page for ps-rx on a specific device
* @dev: network device to receive on
*
* Allocate a new page. dev currently unused.
*
* %NULL is returned if there is no free memory.
*/
static inline struct page *netdev_alloc_page(struct net_device *dev)
{
return __netdev_alloc_page(dev, GFP_ATOMIC);
}
static inline void netdev_free_page(struct net_device *dev, struct page *page)
{
__free_page(page);
}
/**
* 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, unsigned int len)
{
return !skb_header_cloned(skb) &&
skb_headroom(skb) + len <= skb->hdr_len;
}
static inline int __skb_cow(struct sk_buff *skb, unsigned int headroom,
int cloned)
{
int delta = 0;
if (headroom < NET_SKB_PAD)
headroom = NET_SKB_PAD;
if (headroom > skb_headroom(skb))
delta = headroom - skb_headroom(skb);
if (delta || cloned)
return pskb_expand_head(skb, ALIGN(delta, NET_SKB_PAD), 0,
GFP_ATOMIC);
return 0;
}
/**
* 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)
{
return __skb_cow(skb, headroom, skb_cloned(skb));
}
/**
* skb_cow_head - skb_cow but only making the head writable
* @skb: buffer to cow
* @headroom: needed headroom
*
* This function is identical to skb_cow except that we replace the
* skb_cloned check by skb_header_cloned. It should be used when
* you only need to push on some header and do not need to modify
* the data.
*/
static inline int skb_cow_head(struct sk_buff *skb, unsigned int headroom)
{
return __skb_cow(skb, headroom, skb_header_cloned(skb));
}
/**
* 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
* is untouched. Otherwise it is extended. Returns zero on
* success. The skb is freed on error.
*/
static inline int skb_padto(struct sk_buff *skb, unsigned int len)
{
unsigned int size = skb->len;
if (likely(size >= len))
return 0;
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;
__wsum csum = csum_and_copy_from_user(from, skb_put(skb, copy),
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;
}
static inline int __skb_linearize(struct sk_buff *skb)
{
return __pskb_pull_tail(skb, skb->data_len) ? 0 : -ENOMEM;
}
/**
* 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.
*/
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)
{
return skb_is_nonlinear(skb) || skb_cloned(skb) ?
__skb_linearize(skb) : 0;
}
/**
* 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
* update the CHECKSUM_COMPLETE checksum, or set ip_summed to
* CHECKSUM_NONE so that it can be recomputed from scratch.
*/
static inline void skb_postpull_rcsum(struct sk_buff *skb,
const void *start, unsigned int len)
{
if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0));
}
unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len);
/**
* 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)
{
if (likely(len >= skb->len))
return 0;
if (skb->ip_summed == CHECKSUM_COMPLETE)
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)
#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)
#define skb_queue_walk_from(queue, skb) \
for (; prefetch(skb->next), (skb != (struct sk_buff *)(queue)); \
skb = skb->next)
#define skb_queue_walk_from_safe(queue, skb, tmp) \
for (tmp = skb->next; \
skb != (struct sk_buff *)(queue); \
skb = tmp, tmp = skb->next)
#define skb_queue_reverse_walk(queue, skb) \
for (skb = (queue)->prev; \
prefetch(skb->prev), (skb != (struct sk_buff *)(queue)); \
skb = skb->prev)
static inline bool skb_has_frag_list(const struct sk_buff *skb)
{
return skb_shinfo(skb)->frag_list != NULL;
}
static inline void skb_frag_list_init(struct sk_buff *skb)
{
skb_shinfo(skb)->frag_list = NULL;
}
static inline void skb_frag_add_head(struct sk_buff *skb, struct sk_buff *frag)
{
frag->next = skb_shinfo(skb)->frag_list;
skb_shinfo(skb)->frag_list = frag;
}
#define skb_walk_frags(skb, iter) \
for (iter = skb_shinfo(skb)->frag_list; iter; iter = iter->next)
extern struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags,
int *peeked, int *err);
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);
extern int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb,
int hlen,
struct iovec *iov);
extern int skb_copy_datagram_from_iovec(struct sk_buff *skb,
int offset,
const struct iovec *from,
int from_offset,
int len);
extern int skb_copy_datagram_const_iovec(const struct sk_buff *from,
int offset,
const struct iovec *to,
int to_offset,
int size);
extern void skb_free_datagram(struct sock *sk, struct sk_buff *skb);
extern void skb_free_datagram_locked(struct sock *sk,
struct sk_buff *skb);
extern int skb_kill_datagram(struct sock *sk, struct sk_buff *skb,
unsigned int flags);
extern __wsum skb_checksum(const struct sk_buff *skb, int offset,
int len, __wsum csum);
extern int skb_copy_bits(const struct sk_buff *skb, int offset,
void *to, int len);
extern int skb_store_bits(struct sk_buff *skb, int offset,
const void *from, int len);
extern __wsum skb_copy_and_csum_bits(const struct sk_buff *skb,
int offset, u8 *to, int len,
__wsum csum);
extern int skb_splice_bits(struct sk_buff *skb,
unsigned int offset,
struct pipe_inode_info *pipe,
unsigned int len,
unsigned int flags);
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);
extern int skb_shift(struct sk_buff *tgt, struct sk_buff *skb,
int shiftlen);
extern struct sk_buff *skb_segment(struct sk_buff *skb, int features);
static inline void *skb_header_pointer(const struct sk_buff *skb, int offset,
int len, void *buffer)
{
int hlen = skb_headlen(skb);
if (hlen - offset >= len)
return skb->data + offset;
if (skb_copy_bits(skb, offset, buffer, len) < 0)
return NULL;
return buffer;
}
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);
}
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);
}
extern void skb_init(void);
static inline ktime_t skb_get_ktime(const struct sk_buff *skb)
{
return skb->tstamp;
}
/**
* 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.
*/
static inline void skb_get_timestamp(const struct sk_buff *skb,
struct timeval *stamp)
{
*stamp = ktime_to_timeval(skb->tstamp);
}
static inline void skb_get_timestampns(const struct sk_buff *skb,
struct timespec *stamp)
{
*stamp = ktime_to_timespec(skb->tstamp);
}
static inline void __net_timestamp(struct sk_buff *skb)
{
skb->tstamp = ktime_get_real();
}
static inline ktime_t net_timedelta(ktime_t t)
{
return ktime_sub(ktime_get_real(), t);
}
static inline ktime_t net_invalid_timestamp(void)
{
return ktime_set(0, 0);
}
extern void skb_timestamping_init(void);
#ifdef CONFIG_NETWORK_PHY_TIMESTAMPING
extern void skb_clone_tx_timestamp(struct sk_buff *skb);
extern bool skb_defer_rx_timestamp(struct sk_buff *skb);
#else /* CONFIG_NETWORK_PHY_TIMESTAMPING */
static inline void skb_clone_tx_timestamp(struct sk_buff *skb)
{
}
static inline bool skb_defer_rx_timestamp(struct sk_buff *skb)
{
return false;
}
#endif /* !CONFIG_NETWORK_PHY_TIMESTAMPING */
/**
* skb_complete_tx_timestamp() - deliver cloned skb with tx timestamps
*
* @skb: clone of the the original outgoing packet
* @hwtstamps: hardware time stamps
*
*/
void skb_complete_tx_timestamp(struct sk_buff *skb,
struct skb_shared_hwtstamps *hwtstamps);
/**
* skb_tstamp_tx - queue clone of skb with send time stamps
* @orig_skb: the original outgoing packet
* @hwtstamps: hardware time stamps, may be NULL if not available
*
* If the skb has a socket associated, then this function clones the
* skb (thus sharing the actual data and optional structures), stores
* the optional hardware time stamping information (if non NULL) or
* generates a software time stamp (otherwise), then queues the clone
* to the error queue of the socket. Errors are silently ignored.
*/
extern void skb_tstamp_tx(struct sk_buff *orig_skb,
struct skb_shared_hwtstamps *hwtstamps);
static inline void sw_tx_timestamp(struct sk_buff *skb)
{
if (skb_shinfo(skb)->tx_flags & SKBTX_SW_TSTAMP &&
!(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS))
skb_tstamp_tx(skb, NULL);
}
/**
* skb_tx_timestamp() - Driver hook for transmit timestamping
*
* Ethernet MAC Drivers should call this function in their hard_xmit()
* function as soon as possible after giving the sk_buff to the MAC
* hardware, but before freeing the sk_buff.
*
* @skb: A socket buffer.
*/
static inline void skb_tx_timestamp(struct sk_buff *skb)
{
skb_clone_tx_timestamp(skb);
sw_tx_timestamp(skb);
}
extern __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len);
extern __sum16 __skb_checksum_complete(struct sk_buff *skb);
static inline int skb_csum_unnecessary(const struct sk_buff *skb)
{
return skb->ip_summed & CHECKSUM_UNNECESSARY;
}
/**
* 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 __sum16 skb_checksum_complete(struct sk_buff *skb)
{
return skb_csum_unnecessary(skb) ?
0 : __skb_checksum_complete(skb);
}
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
extern void nf_conntrack_destroy(struct nf_conntrack *nfct);
static inline void nf_conntrack_put(struct nf_conntrack *nfct)
{
if (nfct && atomic_dec_and_test(&nfct->use))
nf_conntrack_destroy(nfct);
}
static inline void nf_conntrack_get(struct nf_conntrack *nfct)
{
if (nfct)
atomic_inc(&nfct->use);
}
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
#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 */
static inline void nf_reset(struct sk_buff *skb)
{
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
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
}
/* 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)
{
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
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
}
static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src)
{
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
nf_conntrack_put(dst->nfct);
nf_conntrack_put_reasm(dst->nfct_reasm);
#endif
#ifdef CONFIG_BRIDGE_NETFILTER
nf_bridge_put(dst->nf_bridge);
#endif
__nf_copy(dst, src);
}
#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
static inline void skb_set_queue_mapping(struct sk_buff *skb, u16 queue_mapping)
{
skb->queue_mapping = queue_mapping;
}
static inline u16 skb_get_queue_mapping(const struct sk_buff *skb)
{
return skb->queue_mapping;
}
static inline void skb_copy_queue_mapping(struct sk_buff *to, const struct sk_buff *from)
{
to->queue_mapping = from->queue_mapping;
}
static inline void skb_record_rx_queue(struct sk_buff *skb, u16 rx_queue)
{
skb->queue_mapping = rx_queue + 1;
}
static inline u16 skb_get_rx_queue(const struct sk_buff *skb)
{
return skb->queue_mapping - 1;
}
static inline bool skb_rx_queue_recorded(const struct sk_buff *skb)
{
return skb->queue_mapping != 0;
}
extern u16 skb_tx_hash(const struct net_device *dev,
const struct sk_buff *skb);
#ifdef CONFIG_XFRM
static inline struct sec_path *skb_sec_path(struct sk_buff *skb)
{
return skb->sp;
}
#else
static inline struct sec_path *skb_sec_path(struct sk_buff *skb)
{
return NULL;
}
#endif
static inline int skb_is_gso(const struct sk_buff *skb)
{
return skb_shinfo(skb)->gso_size;
}
static inline int skb_is_gso_v6(const struct sk_buff *skb)
{
return skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6;
}
extern void __skb_warn_lro_forwarding(const struct sk_buff *skb);
static inline bool skb_warn_if_lro(const struct sk_buff *skb)
{
/* LRO sets gso_size but not gso_type, whereas if GSO is really
* wanted then gso_type will be set. */
struct skb_shared_info *shinfo = skb_shinfo(skb);
if (skb_is_nonlinear(skb) && shinfo->gso_size != 0 &&
unlikely(shinfo->gso_type == 0)) {
__skb_warn_lro_forwarding(skb);
return true;
}
return false;
}
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;
}
/**
* skb_checksum_none_assert - make sure skb ip_summed is CHECKSUM_NONE
* @skb: skb to check
*
* fresh skbs have their ip_summed set to CHECKSUM_NONE.
* Instead of forcing ip_summed to CHECKSUM_NONE, we can
* use this helper, to document places where we make this assertion.
*/
static inline void skb_checksum_none_assert(struct sk_buff *skb)
{
#ifdef DEBUG
BUG_ON(skb->ip_summed != CHECKSUM_NONE);
#endif
}
bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off);
#endif /* __KERNEL__ */
#endif /* _LINUX_SKBUFF_H */