skbuff.c

linux 内核源代码

/*
 *	Routines having to do with the 'struct sk_buff' memory handlers.
 *
 *	Authors:	Alan Cox <[e-mail]>
 *			Florian La Roche <[e-mail]>
 *
 *	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/module.h>
#include <linux/types.h>
#include <linux/kernel.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/scatterlist.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>

#include "kmap_skb.h"

static struct kmem_cache *skbuff_head_cache __read_mostly;
static struct kmem_cache *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:%#lx end:%#lx dev:%s\n",
	       here, skb->len, sz, skb->head, skb->data,
	       (unsigned long)skb->tail, (unsigned long)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:%#lx end:%#lx dev:%s\n",
	       here, skb->len, sz, skb->head, skb->data,
	       (unsigned long)skb->tail, (unsigned long)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
 *	@node: numa node to allocate memory on
 *
 *	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, int node)
{
	struct kmem_cache *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_node(cache, gfp_mask & ~__GFP_DMA, node);
	if (!skb)
		goto out;

	size = SKB_DATA_ALIGN(size);
	data = kmalloc_node_track_caller(size + sizeof(struct skb_shared_info),
			gfp_mask, node);
	if (!data)
		goto nodata;

	/*
	 * See comment in sk_buff definition, just before the 'tail' member
	 */
	memset(skb, 0, offsetof(struct sk_buff, tail));
	skb->truesize = size + sizeof(struct sk_buff);
	atomic_set(&skb->users, 1);
	skb->head = data;
	skb->data = data;
	skb_reset_tail_pointer(skb);
	skb->end = skb->tail + size;
	/* make sure we initialize shinfo sequentially */
	shinfo = skb_shinfo(skb);
	atomic_set(&shinfo->dataref, 1);
	shinfo->nr_frags  = 0;
	shinfo->gso_size = 0;
	shinfo->gso_segs = 0;
	shinfo->gso_type = 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;
}

/**
 *	__netdev_alloc_skb - allocate an skbuff for rx on a specific device
 *	@dev: network device to receive on
 *	@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.
 */
struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
		unsigned int length, gfp_t gfp_mask)
{
	int node = dev->dev.parent ? dev_to_node(dev->dev.parent) : -1;
	struct sk_buff *skb;

	skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, node);
	if (likely(skb)) {
		skb_reserve(skb, NET_SKB_PAD);
		skb->dev = dev;
	}
	return skb;
}

static void skb_drop_list(struct sk_buff **listp)
{
	struct sk_buff *list = *listp;

	*listp = NULL;

	do {
		struct sk_buff *this = list;
		list = list->next;
		kfree_skb(this);
	} while (list);
}

static inline void skb_drop_fraglist(struct sk_buff *skb)
{
	skb_drop_list(&skb_shinfo(skb)->frag_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);
}

static 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.
 */
static void kfree_skbmem(struct sk_buff *skb)
{
	struct sk_buff *other;
	atomic_t *fclone_ref;

	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;
	}
}

/* Free everything but the sk_buff shell. */
static void skb_release_all(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);
	}
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
	nf_conntrack_put(skb->nfct);
	nf_conntrack_put_reasm(skb->nfct_reasm);
#endif
#ifdef CONFIG_BRIDGE_NETFILTER
	nf_bridge_put(skb->nf_bridge);
#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
	skb_release_data(skb);
}

/**
 *	__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)
{
	skb_release_all(skb);
	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);
}

static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
{
	new->tstamp		= old->tstamp;
	new->dev		= old->dev;
	new->transport_header	= old->transport_header;
	new->network_header	= old->network_header;
	new->mac_header		= old->mac_header;
	new->dst		= dst_clone(old->dst);
#ifdef CONFIG_INET
	new->sp			= secpath_get(old->sp);
#endif
	memcpy(new->cb, old->cb, sizeof(old->cb));
	new->csum_start		= old->csum_start;
	new->csum_offset	= old->csum_offset;
	new->local_df		= old->local_df;
	new->pkt_type		= old->pkt_type;
	new->ip_summed		= old->ip_summed;
	skb_copy_queue_mapping(new, old);
	new->priority		= old->priority;
#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
	new->ipvs_property	= old->ipvs_property;
#endif
	new->protocol		= old->protocol;
	new->mark		= old->mark;
	__nf_copy(new, old);
#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
    defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
	new->nf_trace		= old->nf_trace;
#endif
#ifdef CONFIG_NET_SCHED
	new->tc_index		= old->tc_index;
#ifdef CONFIG_NET_CLS_ACT
	new->tc_verd		= old->tc_verd;
#endif
#endif
	skb_copy_secmark(new, old);
}

static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb)
{
#define C(x) n->x = skb->x

	n->next = n->prev = NULL;
	n->sk = NULL;
	__copy_skb_header(n, skb);

	C(len);
	C(data_len);
	C(mac_len);
	n->hdr_len = skb->nohdr ? skb_headroom(skb) : skb->hdr_len;
	n->cloned = 1;
	n->nohdr = 0;
	n->destructor = NULL;
	C(iif);
	C(tail);
	C(end);
	C(head);
	C(data);
	C(truesize);
	atomic_set(&n->users, 1);

	atomic_inc(&(skb_shinfo(skb)->dataref));
	skb->cloned = 1;

	return n;
#undef C
}

/**
 *	skb_morph	-	morph one skb into another
 *	@dst: the skb to receive the contents
 *	@src: the skb to supply the contents
 *
 *	This is identical to skb_clone except that the target skb is
 *	supplied by the user.
 *
 *	The target skb is returned upon exit.
 */
struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src)
{
	skb_release_all(dst);
	return __skb_clone(dst, src);
}
EXPORT_SYMBOL_GPL(skb_morph);

/**
 *	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;
	}

	return __skb_clone(n, skb);
}

static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
{
#ifndef NET_SKBUFF_DATA_USES_OFFSET
	/*
	 *	Shift between the two data areas in bytes
	 */
	unsigned long offset = new->data - old->data;
#endif

	__copy_skb_header(new, old);

#ifndef NET_SKBUFF_DATA_USES_OFFSET
	/* {transport,network,mac}_header are relative to skb->head */
	new->transport_header += offset;
	new->network_header   += offset;
	new->mac_header	      += offset;
#endif
	skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size;
	skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs;
	skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type;
}

/**
 *	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;
#ifdef NET_SKBUFF_DATA_USES_OFFSET
	n = alloc_skb(skb->end + skb->data_len, gfp_mask);
#else
	n = alloc_skb(skb->end - skb->head + skb->data_len, gfp_mask);
#endif
	if (!n)
		return NULL;

	/* Set the data pointer */
	skb_reserve(n, headerlen);
	/* Set the tail pointer and length */
	skb_put(n, skb->len);

	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