xen/tools/vnet/vnetd/skbuff.c

/*
 *	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>
 *
 *	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
 *
 *	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.
 */

#include <stddef.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>

#include "allocate.h"
#include "debug.h"
#include "skbuff.h"

#define SKB_DATA_ALIGN(size) ((((size) + 7) >> 3) << 3)

/**
 *	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)
{
        eprintf("skput:over: %p:%d put:%d\n", here, skb->len, sz);
    	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)
{
        eprintf("skput:under: %p:%d put:%d\n", here, skb->len, sz);
        BUG();
}

/**
 *	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.
 */
struct sk_buff *alloc_skb(unsigned int size, int gfp_mask)
{
	struct sk_buff *skb;
	u8 *data;

	/* Get the HEAD */
	skb = ALLOCATE(struct sk_buff);
	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;
        skb->list = NULL;

	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:
	kfree(skb);
	skb = NULL;
	goto out;
}


void skb_release_data(struct sk_buff *skb)
{
        kfree(skb->head);
}

/*
 *	Free an skbuff by memory without cleaning the state.
 */
void kfree_skbmem(struct sk_buff *skb)
{
	skb_release_data(skb);
	kfree(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) {
	 	wprintf("Warning: kfree_skb passed an skb still "
                        "on a list.\n");
		//BUG();
	}

	if(skb->destructor) {
		skb->destructor(skb);
	}
	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)
{
    return pskb_copy(skb, gfp_mask);
}

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->protocol	= old->protocol;
	new->h.raw	= old->h.raw + offset;
	new->nh.raw	= old->nh.raw + offset;
	new->mac.raw	= old->mac.raw + offset;
	new->pkt_type	= old->pkt_type;
	new->destructor = NULL;
	atomic_set(&new->users, 1);
}


/**
 *	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, int gfp_mask)
{
	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));

	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;
	return 0;

nodata:
	return -ENOMEM;
}

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->data_len  = skb->data_len;
	n->len	     = skb->len;

	copy_skb_header(n, skb);
out:
	return n;
}

/* 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_copy_expand(skb, headroom, 0, GFP_ATOMIC);
	}
	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, int 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;
}


/* 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 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;
	}

	if (!len)
		return 0;

fault:
	return -EFAULT;
}


/**
 *	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
 *
 *	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
 *
 *	Works even without knowing the list it is sitting on, which can be
 *	handy at times. It also means that THE LIST MUST EXIST when you
 *	unlink. Thus a list must have its contents unlinked before it is
 *	destroyed.
 */
void skb_unlink(struct sk_buff *skb)
{
	struct sk_buff_head *list = skb->list;

	if (list) {
		unsigned long flags;

		spin_lock_irqsave(&list->lock, flags);
		if (skb->list == list)
			__skb_unlink(skb, skb->list);
		spin_unlock_irqrestore(&list->lock, flags);
	}
}


/**
 *	skb_append	-	append a buffer
 *	@old: buffer to insert after
 *	@newsk: buffer to insert
 *
 *	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)
{
	unsigned long flags;

	spin_lock_irqsave(&old->list->lock, flags);
	__skb_append(old, newsk);
	spin_unlock_irqrestore(&old->list->lock, flags);
}


/**
 *	skb_insert	-	insert a buffer
 *	@old: buffer to insert before
 *	@newsk: buffer to insert
 *
 *	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)
{
	unsigned long flags;

	spin_lock_irqsave(&old->list->lock, flags);
	__skb_insert(newsk, old->prev, old, old->list);
	spin_unlock_irqrestore(&old->list->lock, flags);
}