* Authors: Alan Cox <iiitac@pyr.swan.ac.uk>
* Florian La Roche <rzsfl@rz.uni-sb.de>
*
- * Version: $Id: skbuff.c,v 1.90 2001/11/07 05:56:19 davem Exp $
- *
* Fixes:
* Alan Cox : Fixed the worst of the load
* balancer bugs.
#endif
#include <linux/string.h>
#include <linux/skbuff.h>
+#include <linux/splice.h>
#include <linux/cache.h>
#include <linux/rtnetlink.h>
#include <linux/init.h>
static struct kmem_cache *skbuff_head_cache __read_mostly;
static struct kmem_cache *skbuff_fclone_cache __read_mostly;
+static void sock_pipe_buf_release(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf)
+{
+ struct sk_buff *skb = (struct sk_buff *) buf->private;
+
+ kfree_skb(skb);
+}
+
+static void sock_pipe_buf_get(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf)
+{
+ struct sk_buff *skb = (struct sk_buff *) buf->private;
+
+ skb_get(skb);
+}
+
+static int sock_pipe_buf_steal(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf)
+{
+ return 1;
+}
+
+
+/* Pipe buffer operations for a socket. */
+static struct pipe_buf_operations sock_pipe_buf_ops = {
+ .can_merge = 0,
+ .map = generic_pipe_buf_map,
+ .unmap = generic_pipe_buf_unmap,
+ .confirm = generic_pipe_buf_confirm,
+ .release = sock_pipe_buf_release,
+ .steal = sock_pipe_buf_steal,
+ .get = sock_pipe_buf_get,
+};
+
/*
* Keep out-of-line to prevent kernel bloat.
* __builtin_return_address is not used because it is not always
goto nodata;
/*
- * See comment in sk_buff definition, just before the 'tail' member
+ * Only clear those fields we need to clear, not those that we will
+ * actually initialise below. Hence, don't put any more fields after
+ * the tail pointer in struct sk_buff!
*/
memset(skb, 0, offsetof(struct sk_buff, tail));
skb->truesize = size + sizeof(struct sk_buff);
return skb;
}
+/**
+ * dev_alloc_skb - allocate an skbuff for receiving
+ * @length: length to allocate
+ *
+ * Allocate a new &sk_buff and assign it a usage count of one. The
+ * buffer has unspecified headroom built in. Users should allocate
+ * the headroom they think they need without accounting for the
+ * built in space. The built in space is used for optimisations.
+ *
+ * %NULL is returned if there is no free memory. Although this function
+ * allocates memory it can be called from an interrupt.
+ */
+struct sk_buff *dev_alloc_skb(unsigned int length)
+{
+ /*
+ * There is more code here than it seems:
+ * __dev_alloc_skb is an inline
+ */
+ return __dev_alloc_skb(length, GFP_ATOMIC);
+}
+EXPORT_SYMBOL(dev_alloc_skb);
+
static void skb_drop_list(struct sk_buff **listp)
{
struct sk_buff *list = *listp;
new->tc_verd = old->tc_verd;
#endif
#endif
+ new->vlan_tci = old->vlan_tci;
+
skb_copy_secmark(new, old);
}
return err;
}
+/**
+ * skb_put - add data to a buffer
+ * @skb: buffer to use
+ * @len: amount of data to add
+ *
+ * This function extends the used data area of the buffer. If this would
+ * exceed the total buffer size the kernel will panic. A pointer to the
+ * first byte of the extra data is returned.
+ */
+unsigned char *skb_put(struct sk_buff *skb, unsigned int len)
+{
+ unsigned char *tmp = skb_tail_pointer(skb);
+ SKB_LINEAR_ASSERT(skb);
+ skb->tail += len;
+ skb->len += len;
+ if (unlikely(skb->tail > skb->end))
+ skb_over_panic(skb, len, __builtin_return_address(0));
+ return tmp;
+}
+EXPORT_SYMBOL(skb_put);
+
+/**
+ * skb_push - add data to the start of a buffer
+ * @skb: buffer to use
+ * @len: amount of data to add
+ *
+ * This function extends the used data area of the buffer at the buffer
+ * start. If this would exceed the total buffer headroom the kernel will
+ * panic. A pointer to the first byte of the extra data is returned.
+ */
+unsigned char *skb_push(struct sk_buff *skb, unsigned int len)
+{
+ skb->data -= len;
+ skb->len += len;
+ if (unlikely(skb->data<skb->head))
+ skb_under_panic(skb, len, __builtin_return_address(0));
+ return skb->data;
+}
+EXPORT_SYMBOL(skb_push);
+
+/**
+ * skb_pull - remove data from the start of a buffer
+ * @skb: buffer to use
+ * @len: amount of data to remove
+ *
+ * This function removes data from the start of a buffer, returning
+ * the memory to the headroom. A pointer to the next data in the buffer
+ * is returned. Once the data has been pulled future pushes will overwrite
+ * the old data.
+ */
+unsigned char *skb_pull(struct sk_buff *skb, unsigned int len)
+{
+ return unlikely(len > skb->len) ? NULL : __skb_pull(skb, len);
+}
+EXPORT_SYMBOL(skb_pull);
+
+/**
+ * skb_trim - remove end from a buffer
+ * @skb: buffer to alter
+ * @len: new length
+ *
+ * Cut the length of a buffer down by removing data from the tail. If
+ * the buffer is already under the length specified it is not modified.
+ * The skb must be linear.
+ */
+void skb_trim(struct sk_buff *skb, unsigned int len)
+{
+ if (skb->len > len)
+ __skb_trim(skb, len);
+}
+EXPORT_SYMBOL(skb_trim);
+
/* Trims skb to length len. It can change skb pointers.
*/
return -EFAULT;
}
+/*
+ * Callback from splice_to_pipe(), if we need to release some pages
+ * at the end of the spd in case we error'ed out in filling the pipe.
+ */
+static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i)
+{
+ struct sk_buff *skb = (struct sk_buff *) spd->partial[i].private;
+
+ kfree_skb(skb);
+}
+
+/*
+ * Fill page/offset/length into spd, if it can hold more pages.
+ */
+static inline int spd_fill_page(struct splice_pipe_desc *spd, struct page *page,
+ unsigned int len, unsigned int offset,
+ struct sk_buff *skb)
+{
+ if (unlikely(spd->nr_pages == PIPE_BUFFERS))
+ return 1;
+
+ spd->pages[spd->nr_pages] = page;
+ spd->partial[spd->nr_pages].len = len;
+ spd->partial[spd->nr_pages].offset = offset;
+ spd->partial[spd->nr_pages].private = (unsigned long) skb_get(skb);
+ spd->nr_pages++;
+ return 0;
+}
+
+static inline void __segment_seek(struct page **page, unsigned int *poff,
+ unsigned int *plen, unsigned int off)
+{
+ *poff += off;
+ *page += *poff / PAGE_SIZE;
+ *poff = *poff % PAGE_SIZE;
+ *plen -= off;
+}
+
+static inline int __splice_segment(struct page *page, unsigned int poff,
+ unsigned int plen, unsigned int *off,
+ unsigned int *len, struct sk_buff *skb,
+ struct splice_pipe_desc *spd)
+{
+ if (!*len)
+ return 1;
+
+ /* skip this segment if already processed */
+ if (*off >= plen) {
+ *off -= plen;
+ return 0;
+ }
+
+ /* ignore any bits we already processed */
+ if (*off) {
+ __segment_seek(&page, &poff, &plen, *off);
+ *off = 0;
+ }
+
+ do {
+ unsigned int flen = min(*len, plen);
+
+ /* the linear region may spread across several pages */
+ flen = min_t(unsigned int, flen, PAGE_SIZE - poff);
+
+ if (spd_fill_page(spd, page, flen, poff, skb))
+ return 1;
+
+ __segment_seek(&page, &poff, &plen, flen);
+ *len -= flen;
+
+ } while (*len && plen);
+
+ return 0;
+}
+
+/*
+ * Map linear and fragment data from the skb to spd. It reports failure if the
+ * pipe is full or if we already spliced the requested length.
+ */
+static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset,
+ unsigned int *len,
+ struct splice_pipe_desc *spd)
+{
+ int seg;
+
+ /*
+ * map the linear part
+ */
+ if (__splice_segment(virt_to_page(skb->data),
+ (unsigned long) skb->data & (PAGE_SIZE - 1),
+ skb_headlen(skb),
+ offset, len, skb, spd))
+ return 1;
+
+ /*
+ * then map the fragments
+ */
+ for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) {
+ const skb_frag_t *f = &skb_shinfo(skb)->frags[seg];
+
+ if (__splice_segment(f->page, f->page_offset, f->size,
+ offset, len, skb, spd))
+ return 1;
+ }
+
+ return 0;
+}
+
+/*
+ * Map data from the skb to a pipe. Should handle both the linear part,
+ * the fragments, and the frag list. It does NOT handle frag lists within
+ * the frag list, if such a thing exists. We'd probably need to recurse to
+ * handle that cleanly.
+ */
+int skb_splice_bits(struct sk_buff *__skb, unsigned int offset,
+ struct pipe_inode_info *pipe, unsigned int tlen,
+ unsigned int flags)
+{
+ struct partial_page partial[PIPE_BUFFERS];
+ struct page *pages[PIPE_BUFFERS];
+ struct splice_pipe_desc spd = {
+ .pages = pages,
+ .partial = partial,
+ .flags = flags,
+ .ops = &sock_pipe_buf_ops,
+ .spd_release = sock_spd_release,
+ };
+ struct sk_buff *skb;
+
+ /*
+ * I'd love to avoid the clone here, but tcp_read_sock()
+ * ignores reference counts and unconditonally kills the sk_buff
+ * on return from the actor.
+ */
+ skb = skb_clone(__skb, GFP_KERNEL);
+ if (unlikely(!skb))
+ return -ENOMEM;
+
+ /*
+ * __skb_splice_bits() only fails if the output has no room left,
+ * so no point in going over the frag_list for the error case.
+ */
+ if (__skb_splice_bits(skb, &offset, &tlen, &spd))
+ goto done;
+ else if (!tlen)
+ goto done;
+
+ /*
+ * now see if we have a frag_list to map
+ */
+ if (skb_shinfo(skb)->frag_list) {
+ struct sk_buff *list = skb_shinfo(skb)->frag_list;
+
+ for (; list && tlen; list = list->next) {
+ if (__skb_splice_bits(list, &offset, &tlen, &spd))
+ break;
+ }
+ }
+
+done:
+ /*
+ * drop our reference to the clone, the pipe consumption will
+ * drop the rest.
+ */
+ kfree_skb(skb);
+
+ if (spd.nr_pages) {
+ int ret;
+ struct sock *sk = __skb->sk;
+
+ /*
+ * Drop the socket lock, otherwise we have reverse
+ * locking dependencies between sk_lock and i_mutex
+ * here as compared to sendfile(). We enter here
+ * with the socket lock held, and splice_to_pipe() will
+ * grab the pipe inode lock. For sendfile() emulation,
+ * we call into ->sendpage() with the i_mutex lock held
+ * and networking will grab the socket lock.
+ */
+ release_sock(sk);
+ ret = splice_to_pipe(pipe, &spd);
+ lock_sock(sk);
+ return ret;
+ }
+
+ return 0;
+}
+
/**
* skb_store_bits - store bits from kernel buffer to skb
* @skb: destination buffer
unsigned long flags;
spin_lock_irqsave(&list->lock, flags);
- __skb_append(old, newsk, list);
+ __skb_queue_after(list, old, newsk);
spin_unlock_irqrestore(&list->lock, flags);
}
* 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,
+ * Note 1: 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
+ * Note 2: Fragment lists within fragments are not implemented
* at the moment, state->root_skb could be replaced with
* a stack for this purpose.
*/
/**
* 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
+ * 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.
* @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.
+ * a pointer to the first in a list of new skbs for the segments.
+ * In case of error it returns ERR_PTR(err).
*/
struct sk_buff *skb_segment(struct sk_buff *skb, int features)
{
skb_copy_queue_mapping(nskb, skb);
nskb->priority = skb->priority;
nskb->protocol = skb->protocol;
+ nskb->vlan_tci = skb->vlan_tci;
nskb->dst = dst_clone(skb->dst);
memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
nskb->pkt_type = skb->pkt_type;
return elt;
}
+/**
+ * skb_partial_csum_set - set up and verify partial csum values for packet
+ * @skb: the skb to set
+ * @start: the number of bytes after skb->data to start checksumming.
+ * @off: the offset from start to place the checksum.
+ *
+ * For untrusted partially-checksummed packets, we need to make sure the values
+ * for skb->csum_start and skb->csum_offset are valid so we don't oops.
+ *
+ * This function checks and sets those values and skb->ip_summed: if this
+ * returns false you should drop the packet.
+ */
+bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off)
+{
+ if (unlikely(start > skb->len - 2) ||
+ unlikely((int)start + off > skb->len - 2)) {
+ if (net_ratelimit())
+ printk(KERN_WARNING
+ "bad partial csum: csum=%u/%u len=%u\n",
+ start, off, skb->len);
+ return false;
+ }
+ skb->ip_summed = CHECKSUM_PARTIAL;
+ skb->csum_start = skb_headroom(skb) + start;
+ skb->csum_offset = off;
+ return true;
+}
+
+void __skb_warn_lro_forwarding(const struct sk_buff *skb)
+{
+ if (net_ratelimit())
+ pr_warning("%s: received packets cannot be forwarded"
+ " while LRO is enabled\n", skb->dev->name);
+}
+
EXPORT_SYMBOL(___pskb_trim);
EXPORT_SYMBOL(__kfree_skb);
EXPORT_SYMBOL(kfree_skb);
EXPORT_SYMBOL(skb_abort_seq_read);
EXPORT_SYMBOL(skb_find_text);
EXPORT_SYMBOL(skb_append_datato_frags);
+EXPORT_SYMBOL(__skb_warn_lro_forwarding);
EXPORT_SYMBOL_GPL(skb_to_sgvec);
EXPORT_SYMBOL_GPL(skb_cow_data);
+EXPORT_SYMBOL_GPL(skb_partial_csum_set);