skbuff.c

linux 内核源代码

		frag = &skb_shinfo(st->cur_skb)->frags[st->frag_idx];
		block_limit = frag->size + st->stepped_offset;

		if (abs_offset < block_limit) {
			if (!st->frag_data)
				st->frag_data = kmap_skb_frag(frag);

			*data = (u8 *) st->frag_data + frag->page_offset +
				(abs_offset - st->stepped_offset);

			return block_limit - abs_offset;
		}

		if (st->frag_data) {
			kunmap_skb_frag(st->frag_data);
			st->frag_data = NULL;
		}

		st->frag_idx++;
		st->stepped_offset += frag->size;
	}

	if (st->frag_data) {
		kunmap_skb_frag(st->frag_data);
		st->frag_data = NULL;
	}

	if (st->cur_skb->next) {
		st->cur_skb = st->cur_skb->next;
		st->frag_idx = 0;
		goto next_skb;
	} else if (st->root_skb == st->cur_skb &&
		   skb_shinfo(st->root_skb)->frag_list) {
		st->cur_skb = skb_shinfo(st->root_skb)->frag_list;
		goto next_skb;
	}

	return 0;
}

/**
 * skb_abort_seq_read - Abort a sequential read of skb data
 * @st: state variable
 *
 * Must be called if skb_seq_read() was not called until it
 * returned 0.
 */
void skb_abort_seq_read(struct skb_seq_state *st)
{
	if (st->frag_data)
		kunmap_skb_frag(st->frag_data);
}

#define TS_SKB_CB(state)	((struct skb_seq_state *) &((state)->cb))

static unsigned int skb_ts_get_next_block(unsigned int offset, const u8 **text,
					  struct ts_config *conf,
					  struct ts_state *state)
{
	return skb_seq_read(offset, text, TS_SKB_CB(state));
}

static void skb_ts_finish(struct ts_config *conf, struct ts_state *state)
{
	skb_abort_seq_read(TS_SKB_CB(state));
}

/**
 * skb_find_text - Find a text pattern in skb data
 * @skb: the buffer to look in
 * @from: search offset
 * @to: search limit
 * @config: textsearch configuration
 * @state: uninitialized textsearch state variable
 *
 * Finds a pattern in the skb data according to the specified
 * textsearch configuration. Use textsearch_next() to retrieve
 * subsequent occurrences of the pattern. Returns the offset
 * to the first occurrence or UINT_MAX if no match was found.
 */
unsigned int skb_find_text(struct sk_buff *skb, unsigned int from,
			   unsigned int to, struct ts_config *config,
			   struct ts_state *state)
{
	unsigned int ret;

	config->get_next_block = skb_ts_get_next_block;
	config->finish = skb_ts_finish;

	skb_prepare_seq_read(skb, from, to, TS_SKB_CB(state));

	ret = textsearch_find(config, state);
	return (ret <= to - from ? ret : UINT_MAX);
}

/**
 * skb_append_datato_frags: - append the user data to a skb
 * @sk: sock  structure
 * @skb: skb structure to be appened with user data.
 * @getfrag: call back function to be used for getting the user data
 * @from: pointer to user message iov
 * @length: length of the iov message
 *
 * Description: This procedure append the user data in the fragment part
 * of the skb if any page alloc fails user this procedure returns  -ENOMEM
 */
int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb,
			int (*getfrag)(void *from, char *to, int offset,
					int len, int odd, struct sk_buff *skb),
			void *from, int length)
{
	int frg_cnt = 0;
	skb_frag_t *frag = NULL;
	struct page *page = NULL;
	int copy, left;
	int offset = 0;
	int ret;

	do {
		/* Return error if we don't have space for new frag */
		frg_cnt = skb_shinfo(skb)->nr_frags;
		if (frg_cnt >= MAX_SKB_FRAGS)
			return -EFAULT;

		/* allocate a new page for next frag */
		page = alloc_pages(sk->sk_allocation, 0);

		/* If alloc_page fails just return failure and caller will
		 * free previous allocated pages by doing kfree_skb()
		 */
		if (page == NULL)
			return -ENOMEM;

		/* initialize the next frag */
		sk->sk_sndmsg_page = page;
		sk->sk_sndmsg_off = 0;
		skb_fill_page_desc(skb, frg_cnt, page, 0, 0);
		skb->truesize += PAGE_SIZE;
		atomic_add(PAGE_SIZE, &sk->sk_wmem_alloc);

		/* get the new initialized frag */
		frg_cnt = skb_shinfo(skb)->nr_frags;
		frag = &skb_shinfo(skb)->frags[frg_cnt - 1];

		/* copy the user data to page */
		left = PAGE_SIZE - frag->page_offset;
		copy = (length > left)? left : length;

		ret = getfrag(from, (page_address(frag->page) +
			    frag->page_offset + frag->size),
			    offset, copy, 0, skb);
		if (ret < 0)
			return -EFAULT;

		/* copy was successful so update the size parameters */
		sk->sk_sndmsg_off += copy;
		frag->size += copy;
		skb->len += copy;
		skb->data_len += copy;
		offset += copy;
		length -= copy;

	} while (length > 0);

	return 0;
}

/**
 *	skb_pull_rcsum - pull skb and update receive checksum
 *	@skb: buffer to update
 *	@start: start of data before pull
 *	@len: length of data pulled
 *
 *	This function performs an skb_pull on the packet and updates
 *	update the CHECKSUM_COMPLETE checksum.  It should be used on
 *	receive path processing instead of skb_pull unless you know
 *	that the checksum difference is zero (e.g., a valid IP header)
 *	or you are setting ip_summed to CHECKSUM_NONE.
 */
unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len)
{
	BUG_ON(len > skb->len);
	skb->len -= len;
	BUG_ON(skb->len < skb->data_len);
	skb_postpull_rcsum(skb, skb->data, len);
	return skb->data += len;
}

EXPORT_SYMBOL_GPL(skb_pull_rcsum);

/**
 *	skb_segment - Perform protocol segmentation on skb.
 *	@skb: buffer to segment
 *	@features: features for the output path (see dev->features)
 *
 *	This function performs segmentation on the given skb.  It returns
 *	the segment at the given position.  It returns NULL if there are
 *	no more segments to generate, or when an error is encountered.
 */
struct sk_buff *skb_segment(struct sk_buff *skb, int features)
{
	struct sk_buff *segs = NULL;
	struct sk_buff *tail = NULL;
	unsigned int mss = skb_shinfo(skb)->gso_size;
	unsigned int doffset = skb->data - skb_mac_header(skb);
	unsigned int offset = doffset;
	unsigned int headroom;
	unsigned int len;
	int sg = features & NETIF_F_SG;
	int nfrags = skb_shinfo(skb)->nr_frags;
	int err = -ENOMEM;
	int i = 0;
	int pos;

	__skb_push(skb, doffset);
	headroom = skb_headroom(skb);
	pos = skb_headlen(skb);

	do {
		struct sk_buff *nskb;
		skb_frag_t *frag;
		int hsize;
		int k;
		int size;

		len = skb->len - offset;
		if (len > mss)
			len = mss;

		hsize = skb_headlen(skb) - offset;
		if (hsize < 0)
			hsize = 0;
		if (hsize > len || !sg)
			hsize = len;

		nskb = alloc_skb(hsize + doffset + headroom, GFP_ATOMIC);
		if (unlikely(!nskb))
			goto err;

		if (segs)
			tail->next = nskb;
		else
			segs = nskb;
		tail = nskb;

		nskb->dev = skb->dev;
		skb_copy_queue_mapping(nskb, skb);
		nskb->priority = skb->priority;
		nskb->protocol = skb->protocol;
		nskb->dst = dst_clone(skb->dst);
		memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
		nskb->pkt_type = skb->pkt_type;
		nskb->mac_len = skb->mac_len;

		skb_reserve(nskb, headroom);
		skb_reset_mac_header(nskb);
		skb_set_network_header(nskb, skb->mac_len);
		nskb->transport_header = (nskb->network_header +
					  skb_network_header_len(skb));
		skb_copy_from_linear_data(skb, skb_put(nskb, doffset),
					  doffset);
		if (!sg) {
			nskb->csum = skb_copy_and_csum_bits(skb, offset,
							    skb_put(nskb, len),
							    len, 0);
			continue;
		}

		frag = skb_shinfo(nskb)->frags;
		k = 0;

		nskb->ip_summed = CHECKSUM_PARTIAL;
		nskb->csum = skb->csum;
		skb_copy_from_linear_data_offset(skb, offset,
						 skb_put(nskb, hsize), hsize);

		while (pos < offset + len) {
			BUG_ON(i >= nfrags);

			*frag = skb_shinfo(skb)->frags[i];
			get_page(frag->page);
			size = frag->size;

			if (pos < offset) {
				frag->page_offset += offset - pos;
				frag->size -= offset - pos;
			}

			k++;

			if (pos + size <= offset + len) {
				i++;
				pos += size;
			} else {
				frag->size -= pos + size - (offset + len);
				break;
			}

			frag++;
		}

		skb_shinfo(nskb)->nr_frags = k;
		nskb->data_len = len - hsize;
		nskb->len += nskb->data_len;
		nskb->truesize += nskb->data_len;
	} while ((offset += len) < skb->len);

	return segs;

err:
	while ((skb = segs)) {
		segs = skb->next;
		kfree_skb(skb);
	}
	return ERR_PTR(err);
}

EXPORT_SYMBOL_GPL(skb_segment);

void __init skb_init(void)
{
	skbuff_head_cache = kmem_cache_create("skbuff_head_cache",
					      sizeof(struct sk_buff),
					      0,
					      SLAB_HWCACHE_ALIGN|SLAB_PANIC,
					      NULL);
	skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache",
						(2*sizeof(struct sk_buff)) +
						sizeof(atomic_t),
						0,
						SLAB_HWCACHE_ALIGN|SLAB_PANIC,
						NULL);
}

/**
 *	skb_to_sgvec - Fill a scatter-gather list from a socket buffer
 *	@skb: Socket buffer containing the buffers to be mapped
 *	@sg: The scatter-gather list to map into
 *	@offset: The offset into the buffer's contents to start mapping
 *	@len: Length of buffer space to be mapped
 *
 *	Fill the specified scatter-gather list with mappings/pointers into a
 *	region of the buffer space attached to a socket buffer.
 */
static int
__skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
{
	int start = skb_headlen(skb);
	int i, copy = start - offset;
	int elt = 0;

	if (copy > 0) {
		if (copy > len)
			copy = len;
		sg_set_buf(sg, skb->data + offset, copy);
		elt++;
		if ((len -= copy) == 0)
			return elt;
		offset += 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) {
			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];

			if (copy > len)
				copy = len;
			sg_set_page(&sg[elt], frag->page, copy,
					frag->page_offset+offset-start);
			elt++;
			if (!(len -= copy))
				return elt;
			offset += 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;
				elt += __skb_to_sgvec(list, sg+elt, offset - start,
						      copy);
				if ((len -= copy) == 0)
					return elt;
				offset += copy;
			}
			start = end;
		}
	}
	BUG_ON(len);
	return elt;
}

int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
{
	int nsg = __skb_to_sgvec(skb, sg, offset, len);

	sg_mark_end(&sg[nsg - 1]);

	return nsg;
}

/**
 *	skb_cow_data - Check that a socket buffer's data buffers are writable
 *	@skb: The socket buffer to check.
 *	@tailbits: Amount of trailing space to be added
 *	@trailer: Returned pointer to the skb where the @tailbits space begins
 *
 *	Make sure that the data buffers attached to a socket buffer are
 *	writable. If they are not, private copies are made of the data buffers
 *	and the socket buffer is set to use these instead.
 *
 *	If @tailbits is given, make sure that there is space to write @tailbits
 *	bytes of data beyond current end of socket buffer.  @trailer will be
 *	set to point to the skb in which this space begins.
 *
 *	The number of scatterlist elements required to completely map the
 *	COW'd and extended socket buffer will be returned.
 */
int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer)
{
	int copyflag;
	int elt;
	struct sk_buff *skb1, **skb_p;

	/* If skb is cloned or its head is paged, reallocate
	 * head pulling out all the pages (pages are considered not writable
	 * at the moment even if they are anonymous).
	 */
	if ((skb_cloned(skb) || skb_shinfo(skb)->nr_frags) &&
	    __pskb_pull_tail(skb, skb_pagelen(skb)-skb_headlen(skb)) == NULL)
		return -ENOMEM;

	/* Easy case. Most of packets will go this way. */
	if (!skb_shinfo(skb)->frag_list) {
		/* A little of trouble, not enough of space for trailer.
		 * This should not happen, when stack is tuned to generate
		 * good frames. OK, on miss we reallocate and reserve even more
		 * space, 128 bytes is fair. */

		if (skb_tailroom(skb) < tailbits &&
		    pskb_expand_head(skb, 0, tailbits-skb_tailroom(skb)+128, GFP_ATOMIC))
			return -ENOMEM;

		/* Voila! */
		*trailer = skb;
		return 1;
	}

	/* Misery. We are in troubles, going to mincer fragments... */

	elt = 1;
	skb_p = &skb_shinfo(skb)->frag_list;
	copyflag = 0;

	while ((skb1 = *skb_p) != NULL) {
		int ntail = 0;

		/* The fragment is partially pulled by someone,
		 * this can happen on input. Copy it and everything
		 * after it. */

		if (skb_shared(skb1))
			copyflag = 1;

		/* If the skb is the last, worry about trailer. */

		if (skb1->next == NULL && tailbits) {
			if (skb_shinfo(skb1)->nr_frags ||
			    skb_shinfo(skb1)->frag_list ||
			    skb_tailroom(skb1) < tailbits)
				ntail = tailbits + 128;
		}

		if (copyflag ||
		    skb_cloned(skb1) ||
		    ntail ||
		    skb_shinfo(skb1)->nr_frags ||
		    skb_shinfo(skb1)->frag_list) {
			struct sk_buff *skb2;

			/* Fuck, we are miserable poor guys... */
			if (ntail == 0)
				skb2 = skb_copy(skb1, GFP_ATOMIC);
			else
				skb2 = skb_copy_expand(skb1,
						       skb_headroom(skb1),
						       ntail,
						       GFP_ATOMIC);
			if (unlikely(skb2 == NULL))
				return -ENOMEM;

			if (skb1->sk)
				skb_set_owner_w(skb2, skb1->sk);

			/* Looking around. Are we still alive?
			 * OK, link new skb, drop old one */

			skb2->next = skb1->next;
			*skb_p = skb2;
			kfree_skb(skb1);
			skb1 = skb2;
		}
		elt++;
		*trailer = skb1;
		skb_p = &skb1->next;
	}

	return elt;
}

EXPORT_SYMBOL(___pskb_trim);
EXPORT_SYMBOL(__kfree_skb);
EXPORT_SYMBOL(kfree_skb);
EXPORT_SYMBOL(__pskb_pull_tail);
EXPORT_SYMBOL(__alloc_skb);
EXPORT_SYMBOL(__netdev_alloc_skb);
EXPORT_SYMBOL(pskb_copy);
EXPORT_SYMBOL(pskb_expand_head);
EXPORT_SYMBOL(skb_checksum);
EXPORT_SYMBOL(skb_clone);
EXPORT_SYMBOL(skb_copy);
EXPORT_SYMBOL(skb_copy_and_csum_bits);
EXPORT_SYMBOL(skb_copy_and_csum_dev);
EXPORT_SYMBOL(skb_copy_bits);
EXPORT_SYMBOL(skb_copy_expand);
EXPORT_SYMBOL(skb_over_panic);
EXPORT_SYMBOL(skb_pad);
EXPORT_SYMBOL(skb_realloc_headroom);
EXPORT_SYMBOL(skb_under_panic);
EXPORT_SYMBOL(skb_dequeue);
EXPORT_SYMBOL(skb_dequeue_tail);
EXPORT_SYMBOL(skb_insert);
EXPORT_SYMBOL(skb_queue_purge);
EXPORT_SYMBOL(skb_queue_head);
EXPORT_SYMBOL(skb_queue_tail);
EXPORT_SYMBOL(skb_unlink);
EXPORT_SYMBOL(skb_append);
EXPORT_SYMBOL(skb_split);
EXPORT_SYMBOL(skb_prepare_seq_read);
EXPORT_SYMBOL(skb_seq_read);
EXPORT_SYMBOL(skb_abort_seq_read);
EXPORT_SYMBOL(skb_find_text);
EXPORT_SYMBOL(skb_append_datato_frags);

EXPORT_SYMBOL_GPL(skb_to_sgvec);
EXPORT_SYMBOL_GPL(skb_cow_data);