skbuff.c

linux 内核源代码

 *	@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(struct sk_buff *skb, int offset, const 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;
		skb_copy_to_linear_data_offset(skb, 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. */

__wsum skb_checksum(const struct sk_buff *skb, int offset,
			  int len, __wsum 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) {
			__wsum 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) {
				__wsum 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. */

__wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
				    u8 *to, int len, __wsum 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) {
			__wsum 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) {
			__wsum 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)
{
	__wsum csum;
	long csstart;

	if (skb->ip_summed == CHECKSUM_PARTIAL)
		csstart = skb->csum_start - skb_headroom(skb);
	else
		csstart = skb_headlen(skb);

	BUG_ON(csstart > skb_headlen(skb));

	skb_copy_from_linear_data(skb, to, 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_PARTIAL) {
		long csstuff = csstart + skb->csum_offset;

		*((__sum16 *)(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);
}

static inline void skb_split_inside_header(struct sk_buff *skb,
					   struct sk_buff* skb1,
					   const u32 len, const int pos)
{
	int i;

	skb_copy_from_linear_data_offset(skb, len, skb_put(skb1, pos - 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_set_tail_pointer(skb, 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) {