skbuff.c

Linux Kernel 2.6.9 for OMAP1710

/*
 *	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/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;

/*
 *	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_INFO "skput:over: %p:%d put:%d dev:%s",
		here, skb->len, sz, 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_INFO "skput:under: %p:%d put:%d dev:%s",
               here, skb->len, sz, skb->dev ? skb->dev->name : "<NULL>");
	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
 *
 *	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, int 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 must match skb_add_mtu(). */
	size = SKB_DATA_ALIGN(size);
	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;

	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_dec_and_test(&(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)
{
	skb_release_data(skb);
	kmem_cache_free(skbuff_head_cache, 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)
{
	if (skb->list) {
	 	printk(KERN_WARNING "Warning: kfree_skb passed an skb still "
		       "on a list (from %p).\n", NET_CALLER(skb));
		BUG();
	}

	dst_release(skb->dst);
#ifdef CONFIG_XFRM
	secpath_put(skb->sp);
#endif
	if(skb->destructor) {
		if (in_irq())
			printk(KERN_WARNING "Warning: kfree_skb on "
					    "hard IRQ %p\n", NET_CALLER(skb));
		skb->destructor(skb);
	}
#ifdef CONFIG_NETFILTER
	nf_conntrack_put(skb->nfct);
#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;
	skb->tc_classid = 0;
#endif
#endif

	kfree_skbmem(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, int gfp_mask)
{
	struct sk_buff *n = kmem_cache_alloc(skbuff_head_cache, gfp_mask);

	if (!n) 
		return NULL;

#define C(x) n->x = skb->x

	n->next = n->prev = NULL;
	n->list = NULL;
	n->sk = NULL;
	C(stamp);
	C(dev);
	C(real_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;
	C(pkt_type);
	C(ip_summed);
	C(priority);
	C(protocol);
	C(security);
	n->destructor = NULL;
#ifdef CONFIG_NETFILTER
	C(nfmark);
	C(nfcache);
	C(nfct);
	nf_conntrack_get(skb->nfct);
	C(nfctinfo);
#ifdef CONFIG_NETFILTER_DEBUG
	C(nf_debug);
#endif
#ifdef CONFIG_BRIDGE_NETFILTER
	C(nf_bridge);
	nf_bridge_get(skb->nf_bridge);
#endif
#endif /*CONFIG_NETFILTER*/
#if defined(CONFIG_HIPPI)
	C(private);
#endif
#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(skb->tc_verd);
	n->tc_verd = CLR_TC_MUNGED(skb->tc_verd);
	C(input_dev);
	C(tc_classid);
#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->list	= NULL;
	new->sk		= NULL;
	new->dev	= old->dev;
	new->real_dev	= old->real_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->pkt_type	= old->pkt_type;
	new->stamp	= old->stamp;
	new->destructor = NULL;
	new->security	= old->security;
#ifdef CONFIG_NETFILTER
	new->nfmark	= old->nfmark;
	new->nfcache	= old->nfcache;
	new->nfct	= old->nfct;
	nf_conntrack_get(old->nfct);
	new->nfctinfo	= old->nfctinfo;
#ifdef CONFIG_NETFILTER_DEBUG
	new->nf_debug	= old->nf_debug;
#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_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, int 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, int 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;
	}
	skb_shinfo(n)->tso_size = skb_shinfo(skb)->tso_size;
	skb_shinfo(n)->tso_segs = skb_shinfo(skb)->tso_segs;

	if (skb_shinfo(skb)->frag_list) {
		skb_shinfo(n)->frag_list = skb_shinfo(skb)->frag_list;
		skb_clone_fraglist(n);