skbuff.c

linux 内核源代码

 *	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, gfp_t gfp_mask)
{
	/*
	 *	Allocate the copy buffer
	 */
	struct sk_buff *n;
#ifdef NET_SKBUFF_DATA_USES_OFFSET
	n = alloc_skb(skb->end, gfp_mask);
#else
	n = alloc_skb(skb->end - skb->head, gfp_mask);
#endif
	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 */
	skb_copy_from_linear_data(skb, n->data, n->len);

	n->truesize += skb->data_len;
	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;
	}

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

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

/**
 *	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,
		     gfp_t gfp_mask)
{
	int i;
	u8 *data;
#ifdef NET_SKBUFF_DATA_USES_OFFSET
	int size = nhead + skb->end + ntail;
#else
	int size = nhead + (skb->end - skb->head) + ntail;
#endif
	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. */
#ifdef NET_SKBUFF_DATA_USES_OFFSET
	memcpy(data + nhead, skb->head, skb->tail);
#else
	memcpy(data + nhead, skb->head, skb->tail - skb->head);
#endif
	memcpy(data + size, skb_end_pointer(skb),
	       sizeof(struct skb_shared_info));

	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
		get_page(skb_shinfo(skb)->frags[i].page);

	if (skb_shinfo(skb)->frag_list)
		skb_clone_fraglist(skb);

	skb_release_data(skb);

	off = (data + nhead) - skb->head;

	skb->head     = data;
	skb->data    += off;
#ifdef NET_SKBUFF_DATA_USES_OFFSET
	skb->end      = size;
	off           = nhead;
#else
	skb->end      = skb->head + size;
#endif
	/* {transport,network,mac}_header and tail are relative to skb->head */
	skb->tail	      += off;
	skb->transport_header += off;
	skb->network_header   += off;
	skb->mac_header	      += off;
	skb->csum_start       += nhead;
	skb->cloned   = 0;
	skb->hdr_len  = 0;
	skb->nohdr    = 0;
	atomic_set(&skb_shinfo(skb)->dataref, 1);
	return 0;

nodata:
	return -ENOMEM;
}

/* 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_clone(skb, GFP_ATOMIC);
		if (skb2 && pskb_expand_head(skb2, SKB_DATA_ALIGN(delta), 0,
					     GFP_ATOMIC)) {
			kfree_skb(skb2);
			skb2 = NULL;
		}
	}
	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.
 */
struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
				int newheadroom, int newtailroom,
				gfp_t gfp_mask)
{
	/*
	 *	Allocate the copy buffer
	 */
	struct sk_buff *n = alloc_skb(newheadroom + skb->len + newtailroom,
				      gfp_mask);
	int oldheadroom = skb_headroom(skb);
	int head_copy_len, head_copy_off;
	int off;

	if (!n)
		return NULL;

	skb_reserve(n, newheadroom);

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

	head_copy_len = oldheadroom;
	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);

	off                  = newheadroom - oldheadroom;
	n->csum_start       += off;
#ifdef NET_SKBUFF_DATA_USES_OFFSET
	n->transport_header += off;
	n->network_header   += off;
	n->mac_header	    += off;
#endif

	return n;
}

/**
 *	skb_pad			-	zero pad the tail of an skb
 *	@skb: buffer to pad
 *	@pad: space to pad
 *
 *	Ensure that a buffer is followed by a padding area that is zero
 *	filled. Used by network drivers which may DMA or transfer data
 *	beyond the buffer end onto the wire.
 *
 *	May return error in out of memory cases. The skb is freed on error.
 */

int skb_pad(struct sk_buff *skb, int pad)
{
	int err;
	int ntail;

	/* If the skbuff is non linear tailroom is always zero.. */
	if (!skb_cloned(skb) && skb_tailroom(skb) >= pad) {
		memset(skb->data+skb->len, 0, pad);
		return 0;
	}

	ntail = skb->data_len + pad - (skb->end - skb->tail);
	if (likely(skb_cloned(skb) || ntail > 0)) {
		err = pskb_expand_head(skb, 0, ntail, GFP_ATOMIC);
		if (unlikely(err))
			goto free_skb;
	}

	/* FIXME: The use of this function with non-linear skb's really needs
	 * to be audited.
	 */
	err = skb_linearize(skb);
	if (unlikely(err))
		goto free_skb;

	memset(skb->data + skb->len, 0, pad);
	return 0;

free_skb:
	kfree_skb(skb);
	return err;
}

/* Trims skb to length len. It can change skb pointers.
 */

int ___pskb_trim(struct sk_buff *skb, unsigned int len)
{
	struct sk_buff **fragp;
	struct sk_buff *frag;
	int offset = skb_headlen(skb);
	int nfrags = skb_shinfo(skb)->nr_frags;
	int i;
	int err;

	if (skb_cloned(skb) &&
	    unlikely((err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))))
		return err;

	i = 0;
	if (offset >= len)
		goto drop_pages;

	for (; i < nfrags; i++) {
		int end = offset + skb_shinfo(skb)->frags[i].size;

		if (end < len) {
			offset = end;
			continue;
		}

		skb_shinfo(skb)->frags[i++].size = len - offset;

drop_pages:
		skb_shinfo(skb)->nr_frags = i;

		for (; i < nfrags; i++)
			put_page(skb_shinfo(skb)->frags[i].page);

		if (skb_shinfo(skb)->frag_list)
			skb_drop_fraglist(skb);
		goto done;
	}

	for (fragp = &skb_shinfo(skb)->frag_list; (frag = *fragp);
	     fragp = &frag->next) {
		int end = offset + frag->len;

		if (skb_shared(frag)) {
			struct sk_buff *nfrag;

			nfrag = skb_clone(frag, GFP_ATOMIC);
			if (unlikely(!nfrag))
				return -ENOMEM;

			nfrag->next = frag->next;
			kfree_skb(frag);
			frag = nfrag;
			*fragp = frag;
		}

		if (end < len) {
			offset = end;
			continue;
		}

		if (end > len &&
		    unlikely((err = pskb_trim(frag, len - offset))))
			return err;

		if (frag->next)
			skb_drop_list(&frag->next);
		break;
	}

done:
	if (len > skb_headlen(skb)) {
		skb->data_len -= skb->len - len;
		skb->len       = len;
	} else {
		skb->len       = len;
		skb->data_len  = 0;
		skb_set_tail_pointer(skb, len);
	}

	return 0;
}

/**
 *	__pskb_pull_tail - advance tail of skb header
 *	@skb: buffer to reallocate
 *	@delta: number of bytes to advance tail
 *
 *	The function makes a sense only on a fragmented &sk_buff,
 *	it expands header moving its tail forward and copying necessary
 *	data from fragmented part.
 *
 *	&sk_buff MUST have reference count of 1.
 *
 *	Returns %NULL (and &sk_buff does not change) if pull failed
 *	or value of new tail of skb in the case of success.
 *
 *	All the pointers pointing into skb header may change and must be
 *	reloaded after call to this function.
 */

/* Moves tail of skb head forward, copying data from fragmented part,
 * when it is necessary.
 * 1. It may fail due to malloc failure.
 * 2. It may change skb pointers.
 *
 * It is pretty complicated. Luckily, it is called only in exceptional cases.
 */
unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta)
{
	/* If skb has not enough free space at tail, get new one
	 * plus 128 bytes for future expansions. If we have enough
	 * room at tail, reallocate without expansion only if skb is cloned.
	 */
	int i, k, eat = (skb->tail + delta) - skb->end;

	if (eat > 0 || skb_cloned(skb)) {
		if (pskb_expand_head(skb, 0, eat > 0 ? eat + 128 : 0,
				     GFP_ATOMIC))
			return NULL;
	}

	if (skb_copy_bits(skb, skb_headlen(skb), skb_tail_pointer(skb), delta))
		BUG();

	/* Optimization: no fragments, no reasons to preestimate
	 * size of pulled pages. Superb.
	 */
	if (!skb_shinfo(skb)->frag_list)
		goto pull_pages;

	/* Estimate size of pulled pages. */
	eat = delta;
	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
		if (skb_shinfo(skb)->frags[i].size >= eat)
			goto pull_pages;
		eat -= skb_shinfo(skb)->frags[i].size;
	}

	/* If we need update frag list, we are in troubles.
	 * Certainly, it possible to add an offset to skb data,
	 * but taking into account that pulling is expected to
	 * be very rare operation, it is worth to fight against
	 * further bloating skb head and crucify ourselves here instead.
	 * Pure masohism, indeed. 8)8)
	 */
	if (eat) {
		struct sk_buff *list = skb_shinfo(skb)->frag_list;
		struct sk_buff *clone = NULL;
		struct sk_buff *insp = NULL;

		do {
			BUG_ON(!list);

			if (list->len <= eat) {
				/* Eaten as whole. */
				eat -= list->len;
				list = list->next;
				insp = list;
			} else {
				/* Eaten partially. */

				if (skb_shared(list)) {
					/* Sucks! We need to fork list. :-( */
					clone = skb_clone(list, GFP_ATOMIC);
					if (!clone)
						return NULL;
					insp = list->next;
					list = clone;
				} else {
					/* This may be pulled without
					 * problems. */
					insp = list;
				}
				if (!pskb_pull(list, eat)) {
					if (clone)
						kfree_skb(clone);
					return NULL;
				}
				break;
			}
		} while (eat);

		/* Free pulled out fragments. */
		while ((list = skb_shinfo(skb)->frag_list) != insp) {
			skb_shinfo(skb)->frag_list = list->next;
			kfree_skb(list);
		}
		/* And insert new clone at head. */
		if (clone) {
			clone->next = list;
			skb_shinfo(skb)->frag_list = clone;
		}
	}
	/* Success! Now we may commit changes to skb data. */

pull_pages:
	eat = delta;
	k = 0;
	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
		if (skb_shinfo(skb)->frags[i].size <= eat) {
			put_page(skb_shinfo(skb)->frags[i].page);
			eat -= skb_shinfo(skb)->frags[i].size;
		} else {
			skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i];
			if (eat) {
				skb_shinfo(skb)->frags[k].page_offset += eat;
				skb_shinfo(skb)->frags[k].size -= eat;
				eat = 0;
			}
			k++;
		}
	}
	skb_shinfo(skb)->nr_frags = k;

	skb->tail     += delta;
	skb->data_len -= delta;

	return skb_tail_pointer(skb);
}

/* 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 i, 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;
		skb_copy_from_linear_data_offset(skb, offset, to, copy);
		if ((len -= copy) == 0)
			return 0;
		offset += copy;
		to     += 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) {
			u8 *vaddr;

			if (copy > len)
				copy = len;

			vaddr = kmap_skb_frag(&skb_shinfo(skb)->frags[i]);
			memcpy(to,
			       vaddr + skb_shinfo(skb)->frags[i].page_offset+
			       offset - start, copy);
			kunmap_skb_frag(vaddr);

			if ((len -= copy) == 0)
				return 0;
			offset += copy;
			to     += 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_copy_bits(list, offset - start,
						  to, copy))
					goto fault;
				if ((len -= copy) == 0)
					return 0;
				offset += copy;
				to     += copy;
			}
			start = end;
		}
	}
	if (!len)
		return 0;

fault:
	return -EFAULT;
}

/**
 *	skb_store_bits - store bits from kernel buffer to skb
 *	@skb: destination buffer
 *	@offset: offset in destination