skbuff.c

《嵌入式系统设计与实例开发实验教材二源码》Linux内核移植与编译实验

 *	@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)
{
	int i;
	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 == NULL)
		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));

	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->end  = data+size;

	skb->data += off;
	skb->tail += off;
	skb->mac.raw += off;
	skb->h.raw += off;
	skb->nh.raw += off;
	skb->cloned = 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)
		return pskb_copy(skb, GFP_ATOMIC);

	skb2 = skb_clone(skb, GFP_ATOMIC);
	if (skb2 == NULL ||
	    !pskb_expand_head(skb2, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC))
		return skb2;

	kfree_skb(skb2);
	return NULL;
}


/**
 *	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,
				int gfp_mask)
{
	struct sk_buff *n;

	/*
	 *	Allocate the copy buffer
	 */
 	 
	n=alloc_skb(newheadroom + skb->len + newtailroom,
		    gfp_mask);
	if(n==NULL)
		return NULL;

	skb_reserve(n,newheadroom);

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

	/* Copy the data only. */
	if (skb_copy_bits(skb, 0, n->data, skb->len))
		BUG();

	copy_skb_header(n, skb);
	return n;
}

/* Trims skb to length len. It can change skb pointers, if "realloc" is 1.
 * If realloc==0 and trimming is impossible without change of data,
 * it is BUG().
 */

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

	for (i=0; i<nfrags; i++) {
		int end = offset + skb_shinfo(skb)->frags[i].size;
		if (end > len) {
			if (skb_cloned(skb)) {
				if (!realloc)
					BUG();
				if (!pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
					return -ENOMEM;
			}
			if (len <= offset) {
				put_page(skb_shinfo(skb)->frags[i].page);
				skb_shinfo(skb)->nr_frags--;
			} else {
				skb_shinfo(skb)->frags[i].size = len-offset;
			}
		}
		offset = end;
	}

	if (offset < len) {
		skb->data_len -= skb->len - len;
		skb->len = len;
	} else {
		if (len <= skb_headlen(skb)) {
			skb->len = len;
			skb->data_len = 0;
			skb->tail = skb->data + len;
			if (skb_shinfo(skb)->frag_list && !skb_cloned(skb))
				skb_drop_fraglist(skb);
		} else {
			skb->data_len -= skb->len - len;
			skb->len = 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)
{
	int i, k, eat;

	/* 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.
	 */
	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, delta))
		BUG();

	/* Optimization: no fragments, no reasons to preestimate
	 * size of pulled pages. Superb.
	 */
	if (skb_shinfo(skb)->frag_list == NULL)
		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 {
			if (list == NULL)
				BUG();

			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 == NULL)
						return NULL;
					insp = list->next;
					list = clone;
				} else {
					/* This may be pulled without
					 * problems. */
					insp = list;
				}
				if (pskb_pull(list, eat) == NULL) {
					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;
}

/* 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->len - skb->data_len;

	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;
	}

	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;

		for (list = skb_shinfo(skb)->frag_list; 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 == 0)
		return 0;

fault:
	return -EFAULT;
}

/* Checksum skb data. */

unsigned int skb_checksum(const struct sk_buff *skb, int offset, int len, unsigned int csum)
{
	int i, copy;
	int start = skb->len - skb->data_len;
	int pos = 0;

	/* Checksum header. */
	if ((copy = start-offset) > 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) {
			unsigned int 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;

		for (list = skb_shinfo(skb)->frag_list; list; list=list->next) {
			int end;

			BUG_TRAP(start <= offset+len);

			end = start + list->len;
			if ((copy = end-offset) > 0) {
				unsigned int 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;
		}
	}
	if (len == 0)
		return csum;

	BUG();
	return csum;
}

/* Both of above in one bottle. */

unsigned int skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int len, unsigned int csum)
{
	int i, copy;
	int start = skb->len - skb->data_len;
	int pos = 0;

	/* Copy header. */
	if ((copy = start-offset) > 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) {
			unsigned int 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;

		for (list = skb_shinfo(skb)->frag_list; list; list=list->next) {
			unsigned int 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;
		}
	}
	if (len == 0)
		return csum;

	BUG();
	return csum;
}

void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to)
{
	unsigned int csum;
	long csstart;

	if (skb->ip_summed == CHECKSUM_HW)
		csstart = skb->h.raw - skb->data;
	else
		csstart = skb->len - skb->data_len;

	if (csstart > skb->len - skb->data_len)
		BUG();

	memcpy(to, skb->data, 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_HW) {
		long csstuff = csstart + skb->csum;

		*((unsigned short *)(to + csstuff)) = csum_fold(csum);
	}
}

#if 0
/* 
 * 	Tune the memory allocator for a new MTU size.
 */
void skb_add_mtu(int mtu)
{
	/* Must match allocation in alloc_skb */
	mtu = SKB_DATA_ALIGN(mtu) + sizeof(struct skb_shared_info);

	kmem_add_cache_size(mtu);
}
#endif

void __init skb_init(void)
{
	int i;

	skbuff_head_cache = kmem_cache_create("skbuff_head_cache",
					      sizeof(struct sk_buff),
					      0,
					      SLAB_HWCACHE_ALIGN,
					      skb_headerinit, NULL);
	if (!skbuff_head_cache)
		panic("cannot create skbuff cache");

	for (i=0; i<NR_CPUS; i++)
		skb_queue_head_init(&skb_head_pool[i].list);
}