linux/net/core/skbuff.c

1882 lines
46 KiB
C
Raw Normal View History

/*
* Routines having to do with the 'struct sk_buff' memory handlers.
*
* Authors: Alan Cox <iiitac@pyr.swan.ac.uk>
* Florian La Roche <rzsfl@rz.uni-sb.de>
*
* Version: $Id: skbuff.c,v 1.90 2001/11/07 05:56:19 davem Exp $
*
* Fixes:
* Alan Cox : Fixed the worst of the load
* balancer bugs.
* Dave Platt : Interrupt stacking fix.
* Richard Kooijman : Timestamp fixes.
* Alan Cox : Changed buffer format.
* Alan Cox : destructor hook for AF_UNIX etc.
* Linus Torvalds : Better skb_clone.
* Alan Cox : Added skb_copy.
* Alan Cox : Added all the changed routines Linus
* only put in the headers
* Ray VanTassle : Fixed --skb->lock in free
* Alan Cox : skb_copy copy arp field
* Andi Kleen : slabified it.
* Robert Olsson : Removed skb_head_pool
*
* NOTE:
* The __skb_ routines should be called with interrupts
* disabled, or you better be *real* sure that the operation is atomic
* with respect to whatever list is being frobbed (e.g. via lock_sock()
* or via disabling bottom half handlers, etc).
*
* 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.
*/
/*
* The functions in this file will not compile correctly with gcc 2.4.x
*/
#include <linux/config.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/slab.h>
#include <linux/netdevice.h>
#ifdef CONFIG_NET_CLS_ACT
#include <net/pkt_sched.h>
#endif
#include <linux/string.h>
#include <linux/skbuff.h>
#include <linux/cache.h>
#include <linux/rtnetlink.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <net/protocol.h>
#include <net/dst.h>
#include <net/sock.h>
#include <net/checksum.h>
#include <net/xfrm.h>
#include <asm/uaccess.h>
#include <asm/system.h>
static kmem_cache_t *skbuff_head_cache __read_mostly;
static kmem_cache_t *skbuff_fclone_cache __read_mostly;
/*
* Keep out-of-line to prevent kernel bloat.
* __builtin_return_address is not used because it is not always
* reliable.
*/
/**
* skb_over_panic - private function
* @skb: buffer
* @sz: size
* @here: address
*
* Out of line support code for skb_put(). Not user callable.
*/
void skb_over_panic(struct sk_buff *skb, int sz, void *here)
{
printk(KERN_EMERG "skb_over_panic: text:%p len:%d put:%d head:%p "
"data:%p tail:%p end:%p dev:%s\n",
here, skb->len, sz, skb->head, skb->data, skb->tail, skb->end,
skb->dev ? skb->dev->name : "<NULL>");
BUG();
}
/**
* skb_under_panic - private function
* @skb: buffer
* @sz: size
* @here: address
*
* Out of line support code for skb_push(). Not user callable.
*/
void skb_under_panic(struct sk_buff *skb, int sz, void *here)
{
printk(KERN_EMERG "skb_under_panic: text:%p len:%d put:%d head:%p "
"data:%p tail:%p end:%p dev:%s\n",
here, skb->len, sz, skb->head, skb->data, skb->tail, skb->end,
skb->dev ? skb->dev->name : "<NULL>");
BUG();
}
void skb_truesize_bug(struct sk_buff *skb)
{
printk(KERN_ERR "SKB BUG: Invalid truesize (%u) "
"len=%u, sizeof(sk_buff)=%Zd\n",
skb->truesize, skb->len, sizeof(struct sk_buff));
}
EXPORT_SYMBOL(skb_truesize_bug);
/* Allocate a new skbuff. We do this ourselves so we can fill in a few
* 'private' fields and also do memory statistics to find all the
* [BEEP] leaks.
*
*/
/**
* __alloc_skb - allocate a network buffer
* @size: size to allocate
* @gfp_mask: allocation mask
* @fclone: allocate from fclone cache instead of head cache
* and allocate a cloned (child) skb
*
* Allocate a new &sk_buff. The returned buffer has no headroom and a
* tail room of size bytes. The object has a reference count of one.
* The return is the buffer. On a failure the return is %NULL.
*
* Buffers may only be allocated from interrupts using a @gfp_mask of
* %GFP_ATOMIC.
*/
struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
int fclone)
{
kmem_cache_t *cache;
struct skb_shared_info *shinfo;
struct sk_buff *skb;
u8 *data;
cache = fclone ? skbuff_fclone_cache : skbuff_head_cache;
/* Get the HEAD */
skb = kmem_cache_alloc(cache, gfp_mask & ~__GFP_DMA);
if (!skb)
goto out;
/* Get the DATA. Size must match skb_add_mtu(). */
size = SKB_DATA_ALIGN(size);
[PATCH] slab: implement /proc/slab_allocators Implement /proc/slab_allocators. It produces output like: idr_layer_cache: 80 idr_pre_get+0x33/0x4e buffer_head: 2555 alloc_buffer_head+0x20/0x75 mm_struct: 9 mm_alloc+0x1e/0x42 mm_struct: 20 dup_mm+0x36/0x370 vm_area_struct: 384 dup_mm+0x18f/0x370 vm_area_struct: 151 do_mmap_pgoff+0x2e0/0x7c3 vm_area_struct: 1 split_vma+0x5a/0x10e vm_area_struct: 11 do_brk+0x206/0x2e2 vm_area_struct: 2 copy_vma+0xda/0x142 vm_area_struct: 9 setup_arg_pages+0x99/0x214 fs_cache: 8 copy_fs_struct+0x21/0x133 fs_cache: 29 copy_process+0xf38/0x10e3 files_cache: 30 alloc_files+0x1b/0xcf signal_cache: 81 copy_process+0xbaa/0x10e3 sighand_cache: 77 copy_process+0xe65/0x10e3 sighand_cache: 1 de_thread+0x4d/0x5f8 anon_vma: 241 anon_vma_prepare+0xd9/0xf3 size-2048: 1 add_sect_attrs+0x5f/0x145 size-2048: 2 journal_init_revoke+0x99/0x302 size-2048: 2 journal_init_revoke+0x137/0x302 size-2048: 2 journal_init_inode+0xf9/0x1c4 Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexander Nyberg <alexn@telia.com> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Christoph Lameter <clameter@engr.sgi.com> Cc: Ravikiran Thirumalai <kiran@scalex86.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> DESC slab-leaks3-locking-fix EDESC From: Andrew Morton <akpm@osdl.org> Update for slab-remove-cachep-spinlock.patch Cc: Al Viro <viro@ftp.linux.org.uk> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexander Nyberg <alexn@telia.com> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Christoph Lameter <clameter@engr.sgi.com> Cc: Ravikiran Thirumalai <kiran@scalex86.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-25 12:06:39 +01:00
data = ____kmalloc(size + sizeof(struct skb_shared_info), gfp_mask);
if (!data)
goto nodata;
memset(skb, 0, offsetof(struct sk_buff, truesize));
skb->truesize = size + sizeof(struct sk_buff);
atomic_set(&skb->users, 1);
skb->head = data;
skb->data = data;
skb->tail = data;
skb->end = data + size;
/* make sure we initialize shinfo sequentially */
shinfo = skb_shinfo(skb);
atomic_set(&shinfo->dataref, 1);
shinfo->nr_frags = 0;
shinfo->tso_size = 0;
shinfo->tso_segs = 0;
shinfo->ufo_size = 0;
shinfo->ip6_frag_id = 0;
shinfo->frag_list = NULL;
if (fclone) {
struct sk_buff *child = skb + 1;
atomic_t *fclone_ref = (atomic_t *) (child + 1);
skb->fclone = SKB_FCLONE_ORIG;
atomic_set(fclone_ref, 1);
child->fclone = SKB_FCLONE_UNAVAILABLE;
}
out:
return skb;
nodata:
kmem_cache_free(cache, skb);
skb = NULL;
goto out;
}
/**
* alloc_skb_from_cache - allocate a network buffer
* @cp: kmem_cache from which to allocate the data area
* (object size must be big enough for @size bytes + skb overheads)
* @size: size to allocate
* @gfp_mask: allocation mask
*
* Allocate a new &sk_buff. The returned buffer has no headroom and
* tail room of size bytes. The object has a reference count of one.
* The return is the buffer. On a failure the return is %NULL.
*
* Buffers may only be allocated from interrupts using a @gfp_mask of
* %GFP_ATOMIC.
*/
struct sk_buff *alloc_skb_from_cache(kmem_cache_t *cp,
unsigned int size,
gfp_t gfp_mask)
{
struct sk_buff *skb;
u8 *data;
/* Get the HEAD */
skb = kmem_cache_alloc(skbuff_head_cache,
gfp_mask & ~__GFP_DMA);
if (!skb)
goto out;
/* Get the DATA. */
size = SKB_DATA_ALIGN(size);
data = kmem_cache_alloc(cp, gfp_mask);
if (!data)
goto nodata;
memset(skb, 0, offsetof(struct sk_buff, truesize));
skb->truesize = size + sizeof(struct sk_buff);
atomic_set(&skb->users, 1);
skb->head = data;
skb->data = data;
skb->tail = data;
skb->end = data + size;
atomic_set(&(skb_shinfo(skb)->dataref), 1);
skb_shinfo(skb)->nr_frags = 0;
skb_shinfo(skb)->tso_size = 0;
skb_shinfo(skb)->tso_segs = 0;
skb_shinfo(skb)->frag_list = NULL;
out:
return skb;
nodata:
kmem_cache_free(skbuff_head_cache, skb);
skb = NULL;
goto out;
}
static void skb_drop_fraglist(struct sk_buff *skb)
{
struct sk_buff *list = skb_shinfo(skb)->frag_list;
skb_shinfo(skb)->frag_list = NULL;
do {
struct sk_buff *this = list;
list = list->next;
kfree_skb(this);
} while (list);
}
static void skb_clone_fraglist(struct sk_buff *skb)
{
struct sk_buff *list;
for (list = skb_shinfo(skb)->frag_list; list; list = list->next)
skb_get(list);
}
void skb_release_data(struct sk_buff *skb)
{
if (!skb->cloned ||
!atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1,
&skb_shinfo(skb)->dataref)) {
if (skb_shinfo(skb)->nr_frags) {
int i;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
put_page(skb_shinfo(skb)->frags[i].page);
}
if (skb_shinfo(skb)->frag_list)
skb_drop_fraglist(skb);
kfree(skb->head);
}
}
/*
* Free an skbuff by memory without cleaning the state.
*/
void kfree_skbmem(struct sk_buff *skb)
{
struct sk_buff *other;
atomic_t *fclone_ref;
skb_release_data(skb);
switch (skb->fclone) {
case SKB_FCLONE_UNAVAILABLE:
kmem_cache_free(skbuff_head_cache, skb);
break;
case SKB_FCLONE_ORIG:
fclone_ref = (atomic_t *) (skb + 2);
if (atomic_dec_and_test(fclone_ref))
kmem_cache_free(skbuff_fclone_cache, skb);
break;
case SKB_FCLONE_CLONE:
fclone_ref = (atomic_t *) (skb + 1);
other = skb - 1;
/* The clone portion is available for
* fast-cloning again.
*/
skb->fclone = SKB_FCLONE_UNAVAILABLE;
if (atomic_dec_and_test(fclone_ref))
kmem_cache_free(skbuff_fclone_cache, other);
break;
};
}
/**
* __kfree_skb - private function
* @skb: buffer
*
* Free an sk_buff. Release anything attached to the buffer.
* Clean the state. This is an internal helper function. Users should
* always call kfree_skb
*/
void __kfree_skb(struct sk_buff *skb)
{
dst_release(skb->dst);
#ifdef CONFIG_XFRM
secpath_put(skb->sp);
#endif
if (skb->destructor) {
WARN_ON(in_irq());
skb->destructor(skb);
}
#ifdef CONFIG_NETFILTER
nf_conntrack_put(skb->nfct);
[NETFILTER]: Add nf_conntrack subsystem. The existing connection tracking subsystem in netfilter can only handle ipv4. There were basically two choices present to add connection tracking support for ipv6. We could either duplicate all of the ipv4 connection tracking code into an ipv6 counterpart, or (the choice taken by these patches) we could design a generic layer that could handle both ipv4 and ipv6 and thus requiring only one sub-protocol (TCP, UDP, etc.) connection tracking helper module to be written. In fact nf_conntrack is capable of working with any layer 3 protocol. The existing ipv4 specific conntrack code could also not deal with the pecularities of doing connection tracking on ipv6, which is also cured here. For example, these issues include: 1) ICMPv6 handling, which is used for neighbour discovery in ipv6 thus some messages such as these should not participate in connection tracking since effectively they are like ARP messages 2) fragmentation must be handled differently in ipv6, because the simplistic "defrag, connection track and NAT, refrag" (which the existing ipv4 connection tracking does) approach simply isn't feasible in ipv6 3) ipv6 extension header parsing must occur at the correct spots before and after connection tracking decisions, and there were no provisions for this in the existing connection tracking design 4) ipv6 has no need for stateful NAT The ipv4 specific conntrack layer is kept around, until all of the ipv4 specific conntrack helpers are ported over to nf_conntrack and it is feature complete. Once that occurs, the old conntrack stuff will get placed into the feature-removal-schedule and we will fully kill it off 6 months later. Signed-off-by: Yasuyuki Kozakai <yasuyuki.kozakai@toshiba.co.jp> Signed-off-by: Harald Welte <laforge@netfilter.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
2005-11-10 01:38:16 +01:00
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
nf_conntrack_put_reasm(skb->nfct_reasm);
#endif
#ifdef CONFIG_BRIDGE_NETFILTER
nf_bridge_put(skb->nf_bridge);
#endif
#endif
/* XXX: IS this still necessary? - JHS */
#ifdef CONFIG_NET_SCHED
skb->tc_index = 0;
#ifdef CONFIG_NET_CLS_ACT
skb->tc_verd = 0;
#endif
#endif
kfree_skbmem(skb);
}
/**
* kfree_skb - free an sk_buff
* @skb: buffer to free
*
* Drop a reference to the buffer and free it if the usage count has
* hit zero.
*/
void kfree_skb(struct sk_buff *skb)
{
if (unlikely(!skb))
return;
if (likely(atomic_read(&skb->users) == 1))
smp_rmb();
else if (likely(!atomic_dec_and_test(&skb->users)))
return;
__kfree_skb(skb);
}
/**
* skb_clone - duplicate an sk_buff
* @skb: buffer to clone
* @gfp_mask: allocation priority
*
* Duplicate an &sk_buff. The new one is not owned by a socket. Both
* copies share the same packet data but not structure. The new
* buffer has a reference count of 1. If the allocation fails the
* function returns %NULL otherwise the new buffer is returned.
*
* If this function is called from an interrupt gfp_mask() must be
* %GFP_ATOMIC.
*/
struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
{
struct sk_buff *n;
n = skb + 1;
if (skb->fclone == SKB_FCLONE_ORIG &&
n->fclone == SKB_FCLONE_UNAVAILABLE) {
atomic_t *fclone_ref = (atomic_t *) (n + 1);
n->fclone = SKB_FCLONE_CLONE;
atomic_inc(fclone_ref);
} else {
n = kmem_cache_alloc(skbuff_head_cache, gfp_mask);
if (!n)
return NULL;
n->fclone = SKB_FCLONE_UNAVAILABLE;
}
#define C(x) n->x = skb->x
n->next = n->prev = NULL;
n->sk = NULL;
C(tstamp);
C(dev);
C(h);
C(nh);
C(mac);
C(dst);
dst_clone(skb->dst);
C(sp);
#ifdef CONFIG_INET
secpath_get(skb->sp);
#endif
memcpy(n->cb, skb->cb, sizeof(skb->cb));
C(len);
C(data_len);
C(csum);
C(local_df);
n->cloned = 1;
n->nohdr = 0;
C(pkt_type);
C(ip_summed);
C(priority);
#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
C(ipvs_property);
#endif
C(protocol);
n->destructor = NULL;
#ifdef CONFIG_NETFILTER
C(nfmark);
C(nfct);
nf_conntrack_get(skb->nfct);
C(nfctinfo);
[NETFILTER]: Add nf_conntrack subsystem. The existing connection tracking subsystem in netfilter can only handle ipv4. There were basically two choices present to add connection tracking support for ipv6. We could either duplicate all of the ipv4 connection tracking code into an ipv6 counterpart, or (the choice taken by these patches) we could design a generic layer that could handle both ipv4 and ipv6 and thus requiring only one sub-protocol (TCP, UDP, etc.) connection tracking helper module to be written. In fact nf_conntrack is capable of working with any layer 3 protocol. The existing ipv4 specific conntrack code could also not deal with the pecularities of doing connection tracking on ipv6, which is also cured here. For example, these issues include: 1) ICMPv6 handling, which is used for neighbour discovery in ipv6 thus some messages such as these should not participate in connection tracking since effectively they are like ARP messages 2) fragmentation must be handled differently in ipv6, because the simplistic "defrag, connection track and NAT, refrag" (which the existing ipv4 connection tracking does) approach simply isn't feasible in ipv6 3) ipv6 extension header parsing must occur at the correct spots before and after connection tracking decisions, and there were no provisions for this in the existing connection tracking design 4) ipv6 has no need for stateful NAT The ipv4 specific conntrack layer is kept around, until all of the ipv4 specific conntrack helpers are ported over to nf_conntrack and it is feature complete. Once that occurs, the old conntrack stuff will get placed into the feature-removal-schedule and we will fully kill it off 6 months later. Signed-off-by: Yasuyuki Kozakai <yasuyuki.kozakai@toshiba.co.jp> Signed-off-by: Harald Welte <laforge@netfilter.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
2005-11-10 01:38:16 +01:00
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
C(nfct_reasm);
nf_conntrack_get_reasm(skb->nfct_reasm);
#endif
#ifdef CONFIG_BRIDGE_NETFILTER
C(nf_bridge);
nf_bridge_get(skb->nf_bridge);
#endif
#endif /*CONFIG_NETFILTER*/
#ifdef CONFIG_NET_SCHED
C(tc_index);
#ifdef CONFIG_NET_CLS_ACT
n->tc_verd = SET_TC_VERD(skb->tc_verd,0);
n->tc_verd = CLR_TC_OK2MUNGE(n->tc_verd);
n->tc_verd = CLR_TC_MUNGED(n->tc_verd);
C(input_dev);
#endif
#endif
C(truesize);
atomic_set(&n->users, 1);
C(head);
C(data);
C(tail);
C(end);
atomic_inc(&(skb_shinfo(skb)->dataref));
skb->cloned = 1;
return n;
}
static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
{
/*
* Shift between the two data areas in bytes
*/
unsigned long offset = new->data - old->data;
new->sk = NULL;
new->dev = old->dev;
new->priority = old->priority;
new->protocol = old->protocol;
new->dst = dst_clone(old->dst);
#ifdef CONFIG_INET
new->sp = secpath_get(old->sp);
#endif
new->h.raw = old->h.raw + offset;
new->nh.raw = old->nh.raw + offset;
new->mac.raw = old->mac.raw + offset;
memcpy(new->cb, old->cb, sizeof(old->cb));
new->local_df = old->local_df;
new->fclone = SKB_FCLONE_UNAVAILABLE;
new->pkt_type = old->pkt_type;
new->tstamp = old->tstamp;
new->destructor = NULL;
#ifdef CONFIG_NETFILTER
new->nfmark = old->nfmark;
new->nfct = old->nfct;
nf_conntrack_get(old->nfct);
new->nfctinfo = old->nfctinfo;
[NETFILTER]: Add nf_conntrack subsystem. The existing connection tracking subsystem in netfilter can only handle ipv4. There were basically two choices present to add connection tracking support for ipv6. We could either duplicate all of the ipv4 connection tracking code into an ipv6 counterpart, or (the choice taken by these patches) we could design a generic layer that could handle both ipv4 and ipv6 and thus requiring only one sub-protocol (TCP, UDP, etc.) connection tracking helper module to be written. In fact nf_conntrack is capable of working with any layer 3 protocol. The existing ipv4 specific conntrack code could also not deal with the pecularities of doing connection tracking on ipv6, which is also cured here. For example, these issues include: 1) ICMPv6 handling, which is used for neighbour discovery in ipv6 thus some messages such as these should not participate in connection tracking since effectively they are like ARP messages 2) fragmentation must be handled differently in ipv6, because the simplistic "defrag, connection track and NAT, refrag" (which the existing ipv4 connection tracking does) approach simply isn't feasible in ipv6 3) ipv6 extension header parsing must occur at the correct spots before and after connection tracking decisions, and there were no provisions for this in the existing connection tracking design 4) ipv6 has no need for stateful NAT The ipv4 specific conntrack layer is kept around, until all of the ipv4 specific conntrack helpers are ported over to nf_conntrack and it is feature complete. Once that occurs, the old conntrack stuff will get placed into the feature-removal-schedule and we will fully kill it off 6 months later. Signed-off-by: Yasuyuki Kozakai <yasuyuki.kozakai@toshiba.co.jp> Signed-off-by: Harald Welte <laforge@netfilter.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
2005-11-10 01:38:16 +01:00
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
new->nfct_reasm = old->nfct_reasm;
nf_conntrack_get_reasm(old->nfct_reasm);
#endif
#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
new->ipvs_property = old->ipvs_property;
#endif
#ifdef CONFIG_BRIDGE_NETFILTER
new->nf_bridge = old->nf_bridge;
nf_bridge_get(old->nf_bridge);
#endif
#endif
#ifdef CONFIG_NET_SCHED
#ifdef CONFIG_NET_CLS_ACT
new->tc_verd = old->tc_verd;
#endif
new->tc_index = old->tc_index;
#endif
atomic_set(&new->users, 1);
skb_shinfo(new)->tso_size = skb_shinfo(old)->tso_size;
skb_shinfo(new)->tso_segs = skb_shinfo(old)->tso_segs;
}
/**
* skb_copy - create private copy of an sk_buff
* @skb: buffer to copy
* @gfp_mask: allocation priority
*
* Make a copy of both an &sk_buff and its data. This is used when the
* caller wishes to modify the data and needs a private copy of the
* data to alter. Returns %NULL on failure or the pointer to the buffer
* on success. The returned buffer has a reference count of 1.
*
* As by-product this function converts non-linear &sk_buff to linear
* one, so that &sk_buff becomes completely private and caller is allowed
* to modify all the data of returned buffer. This means that this
* function is not recommended for use in circumstances when only
* header is going to be modified. Use pskb_copy() instead.
*/
struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
{
int headerlen = skb->data - skb->head;
/*
* Allocate the copy buffer
*/
struct sk_buff *n = alloc_skb(skb->end - skb->head + skb->data_len,
gfp_mask);
if (!n)
return NULL;
/* Set the data pointer */
skb_reserve(n, headerlen);
/* Set the tail pointer and length */
skb_put(n, skb->len);
n->csum = skb->csum;
n->ip_summed = skb->ip_summed;
if (skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len))
BUG();
copy_skb_header(n, skb);
return n;
}
/**
* pskb_copy - create copy of an sk_buff with private head.
* @skb: buffer to copy
* @gfp_mask: allocation priority
*
* Make a copy of both an &sk_buff and part of its data, located
* in header. Fragmented data remain shared. This is used when
* the caller wishes to modify only header of &sk_buff and needs
* private copy of the header to alter. Returns %NULL on failure
* or the pointer to the buffer on success.
* The returned buffer has a reference count of 1.
*/
struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask)
{
/*
* Allocate the copy buffer
*/
struct sk_buff *n = alloc_skb(skb->end - skb->head, gfp_mask);
if (!n)
goto out;
/* Set the data pointer */
skb_reserve(n, skb->data - skb->head);
/* Set the tail pointer and length */
skb_put(n, skb_headlen(skb));
/* Copy the bytes */
memcpy(n->data, skb->data, n->len);
n->csum = skb->csum;
n->ip_summed = skb->ip_summed;
n->data_len = skb->data_len;
n->len = skb->len;
if (skb_shinfo(skb)->nr_frags) {
int i;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i];
get_page(skb_shinfo(n)->frags[i].page);
}
skb_shinfo(n)->nr_frags = i;
}
if (skb_shinfo(skb)->frag_list) {
skb_shinfo(n)->frag_list = skb_shinfo(skb)->frag_list;
skb_clone_fraglist(n);
}
copy_skb_header(n, skb);
out:
return n;
}
/**
* pskb_expand_head - reallocate header of &sk_buff
* @skb: buffer to reallocate
* @nhead: room to add at head
* @ntail: room to add at tail
* @gfp_mask: allocation priority
*
* Expands (or creates identical copy, if &nhead and &ntail are zero)
* header of skb. &sk_buff itself is not changed. &sk_buff MUST have
* reference count of 1. Returns zero in the case of success or error,
* if expansion failed. In the last case, &sk_buff is not changed.
*
* All the pointers pointing into skb header may change and must be
* reloaded after call to this function.
*/
int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
gfp_t gfp_mask)
{
int i;
u8 *data;
int size = nhead + (skb->end - skb->head) + ntail;
long off;
if (skb_shared(skb))
BUG();
size = SKB_DATA_ALIGN(size);
data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask);
if (!data)
goto nodata;
/* Copy only real data... and, alas, header. This should be
* optimized for the cases when header is void. */
memcpy(data + nhead, skb->head, skb->tail - skb->head);
memcpy(data + size, skb->end, sizeof(struct skb_shared_info));
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
get_page(skb_shinfo(skb)->frags[i].page);
if (skb_shinfo(skb)->frag_list)
skb_clone_fraglist(skb);
skb_release_data(skb);
off = (data + nhead) - skb->head;
skb->head = data;
skb->end = data + size;
skb->data += off;
skb->tail += off;
skb->mac.raw += off;
skb->h.raw += off;
skb->nh.raw += off;
skb->cloned = 0;
skb->nohdr = 0;
atomic_set(&skb_shinfo(skb)->dataref, 1);
return 0;
nodata:
return -ENOMEM;
}
/* Make private copy of skb with writable head and some headroom */
struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom)
{
struct sk_buff *skb2;
int delta = headroom - skb_headroom(skb);
if (delta <= 0)
skb2 = pskb_copy(skb, GFP_ATOMIC);
else {
skb2 = skb_clone(skb, GFP_ATOMIC);
if (skb2 && pskb_expand_head(skb2, SKB_DATA_ALIGN(delta), 0,
GFP_ATOMIC)) {
kfree_skb(skb2);
skb2 = NULL;
}
}
return skb2;
}
/**
* skb_copy_expand - copy and expand sk_buff
* @skb: buffer to copy
* @newheadroom: new free bytes at head
* @newtailroom: new free bytes at tail
* @gfp_mask: allocation priority
*
* Make a copy of both an &sk_buff and its data and while doing so
* allocate additional space.
*
* This is used when the caller wishes to modify the data and needs a
* private copy of the data to alter as well as more space for new fields.
* Returns %NULL on failure or the pointer to the buffer
* on success. The returned buffer has a reference count of 1.
*
* You must pass %GFP_ATOMIC as the allocation priority if this function
* is called from an interrupt.
*
* BUG ALERT: ip_summed is not copied. Why does this work? Is it used
* only by netfilter in the cases when checksum is recalculated? --ANK
*/
struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
int newheadroom, int newtailroom,
gfp_t gfp_mask)
{
/*
* Allocate the copy buffer
*/
struct sk_buff *n = alloc_skb(newheadroom + skb->len + newtailroom,
gfp_mask);
int head_copy_len, head_copy_off;
if (!n)
return NULL;
skb_reserve(n, newheadroom);
/* Set the tail pointer and length */
skb_put(n, skb->len);
head_copy_len = skb_headroom(skb);
head_copy_off = 0;
if (newheadroom <= head_copy_len)
head_copy_len = newheadroom;
else
head_copy_off = newheadroom - head_copy_len;
/* Copy the linear header and data. */
if (skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off,
skb->len + head_copy_len))
BUG();
copy_skb_header(n, skb);
return n;
}
/**
* skb_pad - zero pad the tail of an skb
* @skb: buffer to pad
* @pad: space to pad
*
* Ensure that a buffer is followed by a padding area that is zero
* filled. Used by network drivers which may DMA or transfer data
* beyond the buffer end onto the wire.
*
* May return NULL in out of memory cases.
*/
struct sk_buff *skb_pad(struct sk_buff *skb, int pad)
{
struct sk_buff *nskb;
/* If the skbuff is non linear tailroom is always zero.. */
if (skb_tailroom(skb) >= pad) {
memset(skb->data+skb->len, 0, pad);
return skb;
}
nskb = skb_copy_expand(skb, skb_headroom(skb), skb_tailroom(skb) + pad, GFP_ATOMIC);
kfree_skb(skb);
if (nskb)
memset(nskb->data+nskb->len, 0, pad);
return nskb;
}
/* Trims skb to length len. It can change skb pointers, if "realloc" is 1.
* If realloc==0 and trimming is impossible without change of data,
* it is BUG().
*/
int ___pskb_trim(struct sk_buff *skb, unsigned int len, int realloc)
{
int offset = skb_headlen(skb);
int nfrags = skb_shinfo(skb)->nr_frags;
int i;
for (i = 0; i < nfrags; i++) {
int end = offset + skb_shinfo(skb)->frags[i].size;
if (end > len) {
if (skb_cloned(skb)) {
BUG_ON(!realloc);
if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
return -ENOMEM;
}
if (len <= offset) {
put_page(skb_shinfo(skb)->frags[i].page);
skb_shinfo(skb)->nr_frags--;
} else {
skb_shinfo(skb)->frags[i].size = len - offset;
}
}
offset = end;
}
if (offset < len) {
skb->data_len -= skb->len - len;
skb->len = len;
} else {
if (len <= skb_headlen(skb)) {
skb->len = len;
skb->data_len = 0;
skb->tail = skb->data + len;
if (skb_shinfo(skb)->frag_list && !skb_cloned(skb))
skb_drop_fraglist(skb);
} else {
skb->data_len -= skb->len - len;
skb->len = len;
}
}
return 0;
}
/**
* __pskb_pull_tail - advance tail of skb header
* @skb: buffer to reallocate
* @delta: number of bytes to advance tail
*
* The function makes a sense only on a fragmented &sk_buff,
* it expands header moving its tail forward and copying necessary
* data from fragmented part.
*
* &sk_buff MUST have reference count of 1.
*
* Returns %NULL (and &sk_buff does not change) if pull failed
* or value of new tail of skb in the case of success.
*
* All the pointers pointing into skb header may change and must be
* reloaded after call to this function.
*/
/* Moves tail of skb head forward, copying data from fragmented part,
* when it is necessary.
* 1. It may fail due to malloc failure.
* 2. It may change skb pointers.
*
* It is pretty complicated. Luckily, it is called only in exceptional cases.
*/
unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta)
{
/* If skb has not enough free space at tail, get new one
* plus 128 bytes for future expansions. If we have enough
* room at tail, reallocate without expansion only if skb is cloned.
*/
int i, k, eat = (skb->tail + delta) - skb->end;
if (eat > 0 || skb_cloned(skb)) {
if (pskb_expand_head(skb, 0, eat > 0 ? eat + 128 : 0,
GFP_ATOMIC))
return NULL;
}
if (skb_copy_bits(skb, skb_headlen(skb), skb->tail, delta))
BUG();
/* Optimization: no fragments, no reasons to preestimate
* size of pulled pages. Superb.
*/
if (!skb_shinfo(skb)->frag_list)
goto pull_pages;
/* Estimate size of pulled pages. */
eat = delta;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
if (skb_shinfo(skb)->frags[i].size >= eat)
goto pull_pages;
eat -= skb_shinfo(skb)->frags[i].size;
}
/* If we need update frag list, we are in troubles.
* Certainly, it possible to add an offset to skb data,
* but taking into account that pulling is expected to
* be very rare operation, it is worth to fight against
* further bloating skb head and crucify ourselves here instead.
* Pure masohism, indeed. 8)8)
*/
if (eat) {
struct sk_buff *list = skb_shinfo(skb)->frag_list;
struct sk_buff *clone = NULL;
struct sk_buff *insp = NULL;
do {
BUG_ON(!list);
if (list->len <= eat) {
/* Eaten as whole. */
eat -= list->len;
list = list->next;
insp = list;
} else {
/* Eaten partially. */
if (skb_shared(list)) {
/* Sucks! We need to fork list. :-( */
clone = skb_clone(list, GFP_ATOMIC);
if (!clone)
return NULL;
insp = list->next;
list = clone;
} else {
/* This may be pulled without
* problems. */
insp = list;
}
if (!pskb_pull(list, eat)) {
if (clone)
kfree_skb(clone);
return NULL;
}
break;
}
} while (eat);
/* Free pulled out fragments. */
while ((list = skb_shinfo(skb)->frag_list) != insp) {
skb_shinfo(skb)->frag_list = list->next;
kfree_skb(list);
}
/* And insert new clone at head. */
if (clone) {
clone->next = list;
skb_shinfo(skb)->frag_list = clone;
}
}
/* Success! Now we may commit changes to skb data. */
pull_pages:
eat = delta;
k = 0;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
if (skb_shinfo(skb)->frags[i].size <= eat) {
put_page(skb_shinfo(skb)->frags[i].page);
eat -= skb_shinfo(skb)->frags[i].size;
} else {
skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i];
if (eat) {
skb_shinfo(skb)->frags[k].page_offset += eat;
skb_shinfo(skb)->frags[k].size -= eat;
eat = 0;
}
k++;
}
}
skb_shinfo(skb)->nr_frags = k;
skb->tail += delta;
skb->data_len -= delta;
return skb->tail;
}
/* Copy some data bits from skb to kernel buffer. */
int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len)
{
int i, copy;
int start = skb_headlen(skb);
if (offset > (int)skb->len - len)
goto fault;
/* Copy header. */
if ((copy = start - offset) > 0) {
if (copy > len)
copy = len;
memcpy(to, skb->data + offset, copy);
if ((len -= copy) == 0)
return 0;
offset += copy;
to += copy;
}
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
int end;
BUG_TRAP(start <= offset + len);
end = start + skb_shinfo(skb)->frags[i].size;
if ((copy = end - offset) > 0) {
u8 *vaddr;
if (copy > len)
copy = len;
vaddr = kmap_skb_frag(&skb_shinfo(skb)->frags[i]);
memcpy(to,
vaddr + skb_shinfo(skb)->frags[i].page_offset+
offset - start, copy);
kunmap_skb_frag(vaddr);
if ((len -= copy) == 0)
return 0;
offset += copy;
to += copy;
}
start = end;
}
if (skb_shinfo(skb)->frag_list) {
struct sk_buff *list = skb_shinfo(skb)->frag_list;
for (; list; list = list->next) {
int end;
BUG_TRAP(start <= offset + len);
end = start + list->len;
if ((copy = end - offset) > 0) {
if (copy > len)
copy = len;
if (skb_copy_bits(list, offset - start,
to, copy))
goto fault;
if ((len -= copy) == 0)
return 0;
offset += copy;
to += copy;
}
start = end;
}
}
if (!len)
return 0;
fault:
return -EFAULT;
}
/**
* skb_store_bits - store bits from kernel buffer to skb
* @skb: destination buffer
* @offset: offset in destination
* @from: source buffer
* @len: number of bytes to copy
*
* Copy the specified number of bytes from the source buffer to the
* destination skb. This function handles all the messy bits of
* traversing fragment lists and such.
*/
int skb_store_bits(const struct sk_buff *skb, int offset, void *from, int len)
{
int i, copy;
int start = skb_headlen(skb);
if (offset > (int)skb->len - len)
goto fault;
if ((copy = start - offset) > 0) {
if (copy > len)
copy = len;
memcpy(skb->data + offset, from, copy);
if ((len -= copy) == 0)
return 0;
offset += copy;
from += copy;
}
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
int end;
BUG_TRAP(start <= offset + len);
end = start + frag->size;
if ((copy = end - offset) > 0) {
u8 *vaddr;
if (copy > len)
copy = len;
vaddr = kmap_skb_frag(frag);
memcpy(vaddr + frag->page_offset + offset - start,
from, copy);
kunmap_skb_frag(vaddr);
if ((len -= copy) == 0)
return 0;
offset += copy;
from += copy;
}
start = end;
}
if (skb_shinfo(skb)->frag_list) {
struct sk_buff *list = skb_shinfo(skb)->frag_list;
for (; list; list = list->next) {
int end;
BUG_TRAP(start <= offset + len);
end = start + list->len;
if ((copy = end - offset) > 0) {
if (copy > len)
copy = len;
if (skb_store_bits(list, offset - start,
from, copy))
goto fault;
if ((len -= copy) == 0)
return 0;
offset += copy;
from += copy;
}
start = end;
}
}
if (!len)
return 0;
fault:
return -EFAULT;
}
EXPORT_SYMBOL(skb_store_bits);
/* Checksum skb data. */
unsigned int skb_checksum(const struct sk_buff *skb, int offset,
int len, unsigned int csum)
{
int start = skb_headlen(skb);
int i, copy = start - offset;
int pos = 0;
/* Checksum header. */
if (copy > 0) {
if (copy > len)
copy = len;
csum = csum_partial(skb->data + offset, copy, csum);
if ((len -= copy) == 0)
return csum;
offset += copy;
pos = copy;
}
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
int end;
BUG_TRAP(start <= offset + len);
end = start + skb_shinfo(skb)->frags[i].size;
if ((copy = end - offset) > 0) {
unsigned int csum2;
u8 *vaddr;
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
if (copy > len)
copy = len;
vaddr = kmap_skb_frag(frag);
csum2 = csum_partial(vaddr + frag->page_offset +
offset - start, copy, 0);
kunmap_skb_frag(vaddr);
csum = csum_block_add(csum, csum2, pos);
if (!(len -= copy))
return csum;
offset += copy;
pos += copy;
}
start = end;
}
if (skb_shinfo(skb)->frag_list) {
struct sk_buff *list = skb_shinfo(skb)->frag_list;
for (; list; list = list->next) {
int end;
BUG_TRAP(start <= offset + len);
end = start + list->len;
if ((copy = end - offset) > 0) {
unsigned int csum2;
if (copy > len)
copy = len;
csum2 = skb_checksum(list, offset - start,
copy, 0);
csum = csum_block_add(csum, csum2, pos);
if ((len -= copy) == 0)
return csum;
offset += copy;
pos += copy;
}
start = end;
}
}
BUG_ON(len);
return csum;
}
/* Both of above in one bottle. */
unsigned int skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
u8 *to, int len, unsigned int csum)
{
int start = skb_headlen(skb);
int i, copy = start - offset;
int pos = 0;
/* Copy header. */
if (copy > 0) {
if (copy > len)
copy = len;
csum = csum_partial_copy_nocheck(skb->data + offset, to,
copy, csum);
if ((len -= copy) == 0)
return csum;
offset += copy;
to += copy;
pos = copy;
}
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
int end;
BUG_TRAP(start <= offset + len);
end = start + skb_shinfo(skb)->frags[i].size;
if ((copy = end - offset) > 0) {
unsigned int csum2;
u8 *vaddr;
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
if (copy > len)
copy = len;
vaddr = kmap_skb_frag(frag);
csum2 = csum_partial_copy_nocheck(vaddr +
frag->page_offset +
offset - start, to,
copy, 0);
kunmap_skb_frag(vaddr);
csum = csum_block_add(csum, csum2, pos);
if (!(len -= copy))
return csum;
offset += copy;
to += copy;
pos += copy;
}
start = end;
}
if (skb_shinfo(skb)->frag_list) {
struct sk_buff *list = skb_shinfo(skb)->frag_list;
for (; list; list = list->next) {
unsigned int csum2;
int end;
BUG_TRAP(start <= offset + len);
end = start + list->len;
if ((copy = end - offset) > 0) {
if (copy > len)
copy = len;
csum2 = skb_copy_and_csum_bits(list,
offset - start,
to, copy, 0);
csum = csum_block_add(csum, csum2, pos);
if ((len -= copy) == 0)
return csum;
offset += copy;
to += copy;
pos += copy;
}
start = end;
}
}
BUG_ON(len);
return csum;
}
void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to)
{
unsigned int csum;
long csstart;
if (skb->ip_summed == CHECKSUM_HW)
csstart = skb->h.raw - skb->data;
else
csstart = skb_headlen(skb);
BUG_ON(csstart > skb_headlen(skb));
memcpy(to, skb->data, csstart);
csum = 0;
if (csstart != skb->len)
csum = skb_copy_and_csum_bits(skb, csstart, to + csstart,
skb->len - csstart, 0);
if (skb->ip_summed == CHECKSUM_HW) {
long csstuff = csstart + skb->csum;
*((unsigned short *)(to + csstuff)) = csum_fold(csum);
}
}
/**
* skb_dequeue - remove from the head of the queue
* @list: list to dequeue from
*
* Remove the head of the list. The list lock is taken so the function
* may be used safely with other locking list functions. The head item is
* returned or %NULL if the list is empty.
*/
struct sk_buff *skb_dequeue(struct sk_buff_head *list)
{
unsigned long flags;
struct sk_buff *result;
spin_lock_irqsave(&list->lock, flags);
result = __skb_dequeue(list);
spin_unlock_irqrestore(&list->lock, flags);
return result;
}
/**
* skb_dequeue_tail - remove from the tail of the queue
* @list: list to dequeue from
*
* Remove the tail of the list. The list lock is taken so the function
* may be used safely with other locking list functions. The tail item is
* returned or %NULL if the list is empty.
*/
struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list)
{
unsigned long flags;
struct sk_buff *result;
spin_lock_irqsave(&list->lock, flags);
result = __skb_dequeue_tail(list);
spin_unlock_irqrestore(&list->lock, flags);
return result;
}
/**
* 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 takes the list
* lock and is atomic with respect to other list locking functions.
*/
void skb_queue_purge(struct sk_buff_head *list)
{
struct sk_buff *skb;
while ((skb = skb_dequeue(list)) != NULL)
kfree_skb(skb);
}
/**
* 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 the list. This function takes the
* list lock and can be used safely with other locking &sk_buff functions
* safely.
*
* A buffer cannot be placed on two lists at the same time.
*/
void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk)
{
unsigned long flags;
spin_lock_irqsave(&list->lock, flags);
__skb_queue_head(list, newsk);
spin_unlock_irqrestore(&list->lock, flags);
}
/**
* skb_queue_tail - queue a buffer at the list tail
* @list: list to use
* @newsk: buffer to queue
*
* Queue a buffer at the tail of the list. This function takes the
* list lock and can be used safely with other locking &sk_buff functions
* safely.
*
* A buffer cannot be placed on two lists at the same time.
*/
void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk)
{
unsigned long flags;
spin_lock_irqsave(&list->lock, flags);
__skb_queue_tail(list, newsk);
spin_unlock_irqrestore(&list->lock, flags);
}
/**
* skb_unlink - remove a buffer from a list
* @skb: buffer to remove
* @list: list to use
*
* Remove a packet from a list. The list locks are taken and this
* function is atomic with respect to other list locked calls
*
* You must know what list the SKB is on.
*/
void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list)
{
unsigned long flags;
spin_lock_irqsave(&list->lock, flags);
__skb_unlink(skb, list);
spin_unlock_irqrestore(&list->lock, flags);
}
/**
* skb_append - append a buffer
* @old: buffer to insert after
* @newsk: buffer to insert
* @list: list to use
*
* Place a packet after a given packet in a list. The list locks are taken
* and this function is atomic with respect to other list locked calls.
* A buffer cannot be placed on two lists at the same time.
*/
void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list)
{
unsigned long flags;
spin_lock_irqsave(&list->lock, flags);
__skb_append(old, newsk, list);
spin_unlock_irqrestore(&list->lock, flags);
}
/**
* skb_insert - insert a buffer
* @old: buffer to insert before
* @newsk: buffer to insert
* @list: list to use
*
* Place a packet before a given packet in a list. The list locks are
* taken and this function is atomic with respect to other list locked
* calls.
*
* A buffer cannot be placed on two lists at the same time.
*/
void skb_insert(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list)
{
unsigned long flags;
spin_lock_irqsave(&list->lock, flags);
__skb_insert(newsk, old->prev, old, list);
spin_unlock_irqrestore(&list->lock, flags);
}
#if 0
/*
* Tune the memory allocator for a new MTU size.
*/
void skb_add_mtu(int mtu)
{
/* Must match allocation in alloc_skb */
mtu = SKB_DATA_ALIGN(mtu) + sizeof(struct skb_shared_info);
kmem_add_cache_size(mtu);
}
#endif
static inline void skb_split_inside_header(struct sk_buff *skb,
struct sk_buff* skb1,
const u32 len, const int pos)
{
int i;
memcpy(skb_put(skb1, pos - len), skb->data + len, pos - len);
/* And move data appendix as is. */
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
skb_shinfo(skb1)->frags[i] = skb_shinfo(skb)->frags[i];
skb_shinfo(skb1)->nr_frags = skb_shinfo(skb)->nr_frags;
skb_shinfo(skb)->nr_frags = 0;
skb1->data_len = skb->data_len;
skb1->len += skb1->data_len;
skb->data_len = 0;
skb->len = len;
skb->tail = skb->data + len;
}
static inline void skb_split_no_header(struct sk_buff *skb,
struct sk_buff* skb1,
const u32 len, int pos)
{
int i, k = 0;
const int nfrags = skb_shinfo(skb)->nr_frags;
skb_shinfo(skb)->nr_frags = 0;
skb1->len = skb1->data_len = skb->len - len;
skb->len = len;
skb->data_len = len - pos;
for (i = 0; i < nfrags; i++) {
int size = skb_shinfo(skb)->frags[i].size;
if (pos + size > len) {
skb_shinfo(skb1)->frags[k] = skb_shinfo(skb)->frags[i];
if (pos < len) {
/* Split frag.
* We have two variants in this case:
* 1. Move all the frag to the second
* part, if it is possible. F.e.
* this approach is mandatory for TUX,
* where splitting is expensive.
* 2. Split is accurately. We make this.
*/
get_page(skb_shinfo(skb)->frags[i].page);
skb_shinfo(skb1)->frags[0].page_offset += len - pos;
skb_shinfo(skb1)->frags[0].size -= len - pos;
skb_shinfo(skb)->frags[i].size = len - pos;
skb_shinfo(skb)->nr_frags++;
}
k++;
} else
skb_shinfo(skb)->nr_frags++;
pos += size;
}
skb_shinfo(skb1)->nr_frags = k;
}
/**
* skb_split - Split fragmented skb to two parts at length len.
* @skb: the buffer to split
* @skb1: the buffer to receive the second part
* @len: new length for skb
*/
void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len)
{
int pos = skb_headlen(skb);
if (len < pos) /* Split line is inside header. */
skb_split_inside_header(skb, skb1, len, pos);
else /* Second chunk has no header, nothing to copy. */
skb_split_no_header(skb, skb1, len, pos);
}
/**
* skb_prepare_seq_read - Prepare a sequential read of skb data
* @skb: the buffer to read
* @from: lower offset of data to be read
* @to: upper offset of data to be read
* @st: state variable
*
* Initializes the specified state variable. Must be called before
* invoking skb_seq_read() for the first time.
*/
void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from,
unsigned int to, struct skb_seq_state *st)
{
st->lower_offset = from;
st->upper_offset = to;
st->root_skb = st->cur_skb = skb;
st->frag_idx = st->stepped_offset = 0;
st->frag_data = NULL;
}
/**
* skb_seq_read - Sequentially read skb data
* @consumed: number of bytes consumed by the caller so far
* @data: destination pointer for data to be returned
* @st: state variable
*
* Reads a block of skb data at &consumed relative to the
* lower offset specified to skb_prepare_seq_read(). Assigns
* the head of the data block to &data and returns the length
* of the block or 0 if the end of the skb data or the upper
* offset has been reached.
*
* The caller is not required to consume all of the data
* returned, i.e. &consumed is typically set to the number
* of bytes already consumed and the next call to
* skb_seq_read() will return the remaining part of the block.
*
* Note: The size of each block of data returned can be arbitary,
* this limitation is the cost for zerocopy seqeuental
* reads of potentially non linear data.
*
* Note: Fragment lists within fragments are not implemented
* at the moment, state->root_skb could be replaced with
* a stack for this purpose.
*/
unsigned int skb_seq_read(unsigned int consumed, const u8 **data,
struct skb_seq_state *st)
{
unsigned int block_limit, abs_offset = consumed + st->lower_offset;
skb_frag_t *frag;
if (unlikely(abs_offset >= st->upper_offset))
return 0;
next_skb:
block_limit = skb_headlen(st->cur_skb);
if (abs_offset < block_limit) {
*data = st->cur_skb->data + abs_offset;
return block_limit - abs_offset;
}
if (st->frag_idx == 0 && !st->frag_data)
st->stepped_offset += skb_headlen(st->cur_skb);
while (st->frag_idx < skb_shinfo(st->cur_skb)->nr_frags) {
frag = &skb_shinfo(st->cur_skb)->frags[st->frag_idx];
block_limit = frag->size + st->stepped_offset;
if (abs_offset < block_limit) {
if (!st->frag_data)
st->frag_data = kmap_skb_frag(frag);
*data = (u8 *) st->frag_data + frag->page_offset +
(abs_offset - st->stepped_offset);
return block_limit - abs_offset;
}
if (st->frag_data) {
kunmap_skb_frag(st->frag_data);
st->frag_data = NULL;
}
st->frag_idx++;
st->stepped_offset += frag->size;
}
if (st->cur_skb->next) {
st->cur_skb = st->cur_skb->next;
st->frag_idx = 0;
goto next_skb;
} else if (st->root_skb == st->cur_skb &&
skb_shinfo(st->root_skb)->frag_list) {
st->cur_skb = skb_shinfo(st->root_skb)->frag_list;
goto next_skb;
}
return 0;
}
/**
* skb_abort_seq_read - Abort a sequential read of skb data
* @st: state variable
*
* Must be called if skb_seq_read() was not called until it
* returned 0.
*/
void skb_abort_seq_read(struct skb_seq_state *st)
{
if (st->frag_data)
kunmap_skb_frag(st->frag_data);
}
#define TS_SKB_CB(state) ((struct skb_seq_state *) &((state)->cb))
static unsigned int skb_ts_get_next_block(unsigned int offset, const u8 **text,
struct ts_config *conf,
struct ts_state *state)
{
return skb_seq_read(offset, text, TS_SKB_CB(state));
}
static void skb_ts_finish(struct ts_config *conf, struct ts_state *state)
{
skb_abort_seq_read(TS_SKB_CB(state));
}
/**
* skb_find_text - Find a text pattern in skb data
* @skb: the buffer to look in
* @from: search offset
* @to: search limit
* @config: textsearch configuration
* @state: uninitialized textsearch state variable
*
* Finds a pattern in the skb data according to the specified
* textsearch configuration. Use textsearch_next() to retrieve
* subsequent occurrences of the pattern. Returns the offset
* to the first occurrence or UINT_MAX if no match was found.
*/
unsigned int skb_find_text(struct sk_buff *skb, unsigned int from,
unsigned int to, struct ts_config *config,
struct ts_state *state)
{
config->get_next_block = skb_ts_get_next_block;
config->finish = skb_ts_finish;
skb_prepare_seq_read(skb, from, to, TS_SKB_CB(state));
return textsearch_find(config, state);
}
[IPv4/IPv6]: UFO Scatter-gather approach Attached is kernel patch for UDP Fragmentation Offload (UFO) feature. 1. This patch incorporate the review comments by Jeff Garzik. 2. Renamed USO as UFO (UDP Fragmentation Offload) 3. udp sendfile support with UFO This patches uses scatter-gather feature of skb to generate large UDP datagram. Below is a "how-to" on changes required in network device driver to use the UFO interface. UDP Fragmentation Offload (UFO) Interface: ------------------------------------------- UFO is a feature wherein the Linux kernel network stack will offload the IP fragmentation functionality of large UDP datagram to hardware. This will reduce the overhead of stack in fragmenting the large UDP datagram to MTU sized packets 1) Drivers indicate their capability of UFO using dev->features |= NETIF_F_UFO | NETIF_F_HW_CSUM | NETIF_F_SG NETIF_F_HW_CSUM is required for UFO over ipv6. 2) UFO packet will be submitted for transmission using driver xmit routine. UFO packet will have a non-zero value for "skb_shinfo(skb)->ufo_size" skb_shinfo(skb)->ufo_size will indicate the length of data part in each IP fragment going out of the adapter after IP fragmentation by hardware. skb->data will contain MAC/IP/UDP header and skb_shinfo(skb)->frags[] contains the data payload. The skb->ip_summed will be set to CHECKSUM_HW indicating that hardware has to do checksum calculation. Hardware should compute the UDP checksum of complete datagram and also ip header checksum of each fragmented IP packet. For IPV6 the UFO provides the fragment identification-id in skb_shinfo(skb)->ip6_frag_id. The adapter should use this ID for generating IPv6 fragments. Signed-off-by: Ananda Raju <ananda.raju@neterion.com> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> (forwarded) Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
2005-10-19 00:46:41 +02:00
/**
* skb_append_datato_frags: - append the user data to a skb
* @sk: sock structure
* @skb: skb structure to be appened with user data.
* @getfrag: call back function to be used for getting the user data
* @from: pointer to user message iov
* @length: length of the iov message
*
* Description: This procedure append the user data in the fragment part
* of the skb if any page alloc fails user this procedure returns -ENOMEM
*/
int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb,
int (*getfrag)(void *from, char *to, int offset,
[IPv4/IPv6]: UFO Scatter-gather approach Attached is kernel patch for UDP Fragmentation Offload (UFO) feature. 1. This patch incorporate the review comments by Jeff Garzik. 2. Renamed USO as UFO (UDP Fragmentation Offload) 3. udp sendfile support with UFO This patches uses scatter-gather feature of skb to generate large UDP datagram. Below is a "how-to" on changes required in network device driver to use the UFO interface. UDP Fragmentation Offload (UFO) Interface: ------------------------------------------- UFO is a feature wherein the Linux kernel network stack will offload the IP fragmentation functionality of large UDP datagram to hardware. This will reduce the overhead of stack in fragmenting the large UDP datagram to MTU sized packets 1) Drivers indicate their capability of UFO using dev->features |= NETIF_F_UFO | NETIF_F_HW_CSUM | NETIF_F_SG NETIF_F_HW_CSUM is required for UFO over ipv6. 2) UFO packet will be submitted for transmission using driver xmit routine. UFO packet will have a non-zero value for "skb_shinfo(skb)->ufo_size" skb_shinfo(skb)->ufo_size will indicate the length of data part in each IP fragment going out of the adapter after IP fragmentation by hardware. skb->data will contain MAC/IP/UDP header and skb_shinfo(skb)->frags[] contains the data payload. The skb->ip_summed will be set to CHECKSUM_HW indicating that hardware has to do checksum calculation. Hardware should compute the UDP checksum of complete datagram and also ip header checksum of each fragmented IP packet. For IPV6 the UFO provides the fragment identification-id in skb_shinfo(skb)->ip6_frag_id. The adapter should use this ID for generating IPv6 fragments. Signed-off-by: Ananda Raju <ananda.raju@neterion.com> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> (forwarded) Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
2005-10-19 00:46:41 +02:00
int len, int odd, struct sk_buff *skb),
void *from, int length)
{
int frg_cnt = 0;
skb_frag_t *frag = NULL;
struct page *page = NULL;
int copy, left;
int offset = 0;
int ret;
do {
/* Return error if we don't have space for new frag */
frg_cnt = skb_shinfo(skb)->nr_frags;
if (frg_cnt >= MAX_SKB_FRAGS)
return -EFAULT;
/* allocate a new page for next frag */
page = alloc_pages(sk->sk_allocation, 0);
/* If alloc_page fails just return failure and caller will
* free previous allocated pages by doing kfree_skb()
*/
if (page == NULL)
return -ENOMEM;
/* initialize the next frag */
sk->sk_sndmsg_page = page;
sk->sk_sndmsg_off = 0;
skb_fill_page_desc(skb, frg_cnt, page, 0, 0);
skb->truesize += PAGE_SIZE;
atomic_add(PAGE_SIZE, &sk->sk_wmem_alloc);
/* get the new initialized frag */
frg_cnt = skb_shinfo(skb)->nr_frags;
frag = &skb_shinfo(skb)->frags[frg_cnt - 1];
/* copy the user data to page */
left = PAGE_SIZE - frag->page_offset;
copy = (length > left)? left : length;
ret = getfrag(from, (page_address(frag->page) +
frag->page_offset + frag->size),
offset, copy, 0, skb);
if (ret < 0)
return -EFAULT;
/* copy was successful so update the size parameters */
sk->sk_sndmsg_off += copy;
frag->size += copy;
skb->len += copy;
skb->data_len += copy;
offset += copy;
length -= copy;
} while (length > 0);
return 0;
}
/**
* skb_pull_rcsum - pull skb and update receive checksum
* @skb: buffer to update
* @start: start of data before pull
* @len: length of data pulled
*
* This function performs an skb_pull on the packet and updates
* update the CHECKSUM_HW checksum. It should be used on receive
* path processing instead of skb_pull unless you know that the
* checksum difference is zero (e.g., a valid IP header) or you
* are setting ip_summed to CHECKSUM_NONE.
*/
unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len)
{
BUG_ON(len > skb->len);
skb->len -= len;
BUG_ON(skb->len < skb->data_len);
skb_postpull_rcsum(skb, skb->data, len);
return skb->data += len;
}
EXPORT_SYMBOL_GPL(skb_pull_rcsum);
void __init skb_init(void)
{
skbuff_head_cache = kmem_cache_create("skbuff_head_cache",
sizeof(struct sk_buff),
0,
SLAB_HWCACHE_ALIGN,
NULL, NULL);
if (!skbuff_head_cache)
panic("cannot create skbuff cache");
skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache",
(2*sizeof(struct sk_buff)) +
sizeof(atomic_t),
0,
SLAB_HWCACHE_ALIGN,
NULL, NULL);
if (!skbuff_fclone_cache)
panic("cannot create skbuff cache");
}
EXPORT_SYMBOL(___pskb_trim);
EXPORT_SYMBOL(__kfree_skb);
EXPORT_SYMBOL(kfree_skb);
EXPORT_SYMBOL(__pskb_pull_tail);
EXPORT_SYMBOL(__alloc_skb);
EXPORT_SYMBOL(pskb_copy);
EXPORT_SYMBOL(pskb_expand_head);
EXPORT_SYMBOL(skb_checksum);
EXPORT_SYMBOL(skb_clone);
EXPORT_SYMBOL(skb_clone_fraglist);
EXPORT_SYMBOL(skb_copy);
EXPORT_SYMBOL(skb_copy_and_csum_bits);
EXPORT_SYMBOL(skb_copy_and_csum_dev);
EXPORT_SYMBOL(skb_copy_bits);
EXPORT_SYMBOL(skb_copy_expand);
EXPORT_SYMBOL(skb_over_panic);
EXPORT_SYMBOL(skb_pad);
EXPORT_SYMBOL(skb_realloc_headroom);
EXPORT_SYMBOL(skb_under_panic);
EXPORT_SYMBOL(skb_dequeue);
EXPORT_SYMBOL(skb_dequeue_tail);
EXPORT_SYMBOL(skb_insert);
EXPORT_SYMBOL(skb_queue_purge);
EXPORT_SYMBOL(skb_queue_head);
EXPORT_SYMBOL(skb_queue_tail);
EXPORT_SYMBOL(skb_unlink);
EXPORT_SYMBOL(skb_append);
EXPORT_SYMBOL(skb_split);
EXPORT_SYMBOL(skb_prepare_seq_read);
EXPORT_SYMBOL(skb_seq_read);
EXPORT_SYMBOL(skb_abort_seq_read);
EXPORT_SYMBOL(skb_find_text);
[IPv4/IPv6]: UFO Scatter-gather approach Attached is kernel patch for UDP Fragmentation Offload (UFO) feature. 1. This patch incorporate the review comments by Jeff Garzik. 2. Renamed USO as UFO (UDP Fragmentation Offload) 3. udp sendfile support with UFO This patches uses scatter-gather feature of skb to generate large UDP datagram. Below is a "how-to" on changes required in network device driver to use the UFO interface. UDP Fragmentation Offload (UFO) Interface: ------------------------------------------- UFO is a feature wherein the Linux kernel network stack will offload the IP fragmentation functionality of large UDP datagram to hardware. This will reduce the overhead of stack in fragmenting the large UDP datagram to MTU sized packets 1) Drivers indicate their capability of UFO using dev->features |= NETIF_F_UFO | NETIF_F_HW_CSUM | NETIF_F_SG NETIF_F_HW_CSUM is required for UFO over ipv6. 2) UFO packet will be submitted for transmission using driver xmit routine. UFO packet will have a non-zero value for "skb_shinfo(skb)->ufo_size" skb_shinfo(skb)->ufo_size will indicate the length of data part in each IP fragment going out of the adapter after IP fragmentation by hardware. skb->data will contain MAC/IP/UDP header and skb_shinfo(skb)->frags[] contains the data payload. The skb->ip_summed will be set to CHECKSUM_HW indicating that hardware has to do checksum calculation. Hardware should compute the UDP checksum of complete datagram and also ip header checksum of each fragmented IP packet. For IPV6 the UFO provides the fragment identification-id in skb_shinfo(skb)->ip6_frag_id. The adapter should use this ID for generating IPv6 fragments. Signed-off-by: Ananda Raju <ananda.raju@neterion.com> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> (forwarded) Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
2005-10-19 00:46:41 +02:00
EXPORT_SYMBOL(skb_append_datato_frags);