2041 lines · 49.3 KB · C
RawDownload
/* *	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/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 <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:%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 *	@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; 	/* Get the DATA. Size must match skb_add_mtu(). */	size = SKB_DATA_ALIGN(size);	data = kmalloc_node_track_caller(size + sizeof(struct skb_shared_info),			gfp_mask, node);	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->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. */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);#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(mac_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;	C(mark);#ifdef CONFIG_NETFILTER	C(nfct);	nf_conntrack_get(skb->nfct);	C(nfctinfo);#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(iif);#endif	skb_copy_secmark(n, skb);#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;	new->mark	= old->mark;#ifdef CONFIG_NETFILTER	new->nfct	= old->nfct;	nf_conntrack_get(old->nfct);	new->nfctinfo	= old->nfctinfo;#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

Lines 1–500 of 2041.