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);
+ put_page(buf->page);
}
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);
+ get_page(buf->page);
}
static int sock_pipe_buf_steal(struct pipe_inode_info *pipe,
BUG();
}
-void skb_truesize_bug(struct sk_buff *skb)
-{
- WARN(net_ratelimit(), KERN_ERR "SKB BUG: Invalid truesize (%u) "
- "len=%u, sizeof(sk_buff)=%Zd\n",
- skb->truesize, skb->len, sizeof(struct sk_buff));
-}
-EXPORT_SYMBOL(skb_truesize_bug);
-
/* Allocate a new skbuff. We do this ourselves so we can fill in a few
* 'private' fields and also do memory statistics to find all the
* [BEEP] leaks.
*/
static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i)
{
- struct sk_buff *skb = (struct sk_buff *) spd->partial[i].private;
+ put_page(spd->pages[i]);
+}
- kfree_skb(skb);
+static inline struct page *linear_to_page(struct page *page, unsigned int len,
+ unsigned int offset)
+{
+ struct page *p = alloc_pages(GFP_KERNEL, 0);
+
+ if (!p)
+ return NULL;
+ memcpy(page_address(p) + offset, page_address(page) + offset, len);
+
+ return p;
}
/*
*/
static inline int spd_fill_page(struct splice_pipe_desc *spd, struct page *page,
unsigned int len, unsigned int offset,
- struct sk_buff *skb)
+ struct sk_buff *skb, int linear)
{
if (unlikely(spd->nr_pages == PIPE_BUFFERS))
return 1;
+ if (linear) {
+ page = linear_to_page(page, len, offset);
+ if (!page)
+ return 1;
+ } else
+ get_page(page);
+
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 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)
+ struct splice_pipe_desc *spd, int linear)
{
if (!*len)
return 1;
/* 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))
+ if (spd_fill_page(spd, page, flen, poff, skb, linear))
return 1;
__segment_seek(&page, &poff, &plen, flen);
if (__splice_segment(virt_to_page(skb->data),
(unsigned long) skb->data & (PAGE_SIZE - 1),
skb_headlen(skb),
- offset, len, skb, spd))
+ offset, len, skb, spd, 1))
return 1;
/*
const skb_frag_t *f = &skb_shinfo(skb)->frags[seg];
if (__splice_segment(f->page, f->page_offset, f->size,
- offset, len, skb, spd))
+ offset, len, skb, spd, 0))
return 1;
}
* 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,
+int skb_splice_bits(struct sk_buff *skb, unsigned int offset,
struct pipe_inode_info *pipe, unsigned int tlen,
unsigned int 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,
}
done:
- /*
- * drop our reference to the clone, the pipe consumption will
- * drop the rest.
- */
- kfree_skb(skb);
-
if (spd.nr_pages) {
+ struct sock *sk = skb->sk;
int ret;
- struct sock *sk = __skb->sk;
/*
* Drop the socket lock, otherwise we have reverse
return 0;
next_skb:
- block_limit = skb_headlen(st->cur_skb);
+ block_limit = skb_headlen(st->cur_skb) + st->stepped_offset;
if (abs_offset < block_limit) {
- *data = st->cur_skb->data + abs_offset;
+ *data = st->cur_skb->data + (abs_offset - st->stepped_offset);
return block_limit - abs_offset;
}
st->frag_data = NULL;
}
- if (st->cur_skb->next) {
- st->cur_skb = st->cur_skb->next;
+ if (st->root_skb == st->cur_skb &&
+ skb_shinfo(st->root_skb)->frag_list) {
+ st->cur_skb = skb_shinfo(st->root_skb)->frag_list;
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;
+ } else if (st->cur_skb->next) {
+ st->cur_skb = st->cur_skb->next;
+ st->frag_idx = 0;
goto next_skb;
}
struct sk_buff *nskb;
unsigned int headroom;
unsigned int hlen = p->data - skb_mac_header(p);
+ unsigned int len = skb->len;
- if (hlen + p->len + skb->len >= 65536)
+ if (hlen + p->len + len >= 65536)
return -E2BIG;
if (skb_shinfo(p)->frag_list)
goto merge;
+ else if (!skb_headlen(p) && !skb_headlen(skb) &&
+ skb_shinfo(p)->nr_frags + skb_shinfo(skb)->nr_frags <
+ MAX_SKB_FRAGS) {
+ memcpy(skb_shinfo(p)->frags + skb_shinfo(p)->nr_frags,
+ skb_shinfo(skb)->frags,
+ skb_shinfo(skb)->nr_frags * sizeof(skb_frag_t));
+
+ skb_shinfo(p)->nr_frags += skb_shinfo(skb)->nr_frags;
+ skb_shinfo(skb)->nr_frags = 0;
+
+ skb->truesize -= skb->data_len;
+ skb->len -= skb->data_len;
+ skb->data_len = 0;
+
+ NAPI_GRO_CB(skb)->free = 1;
+ goto done;
+ }
headroom = skb_headroom(p);
nskb = netdev_alloc_skb(p->dev, headroom);
*NAPI_GRO_CB(nskb) = *NAPI_GRO_CB(p);
skb_shinfo(nskb)->frag_list = p;
+ skb_shinfo(nskb)->gso_size = skb_shinfo(p)->gso_size;
skb_header_release(p);
nskb->prev = p;
p = nskb;
merge:
- NAPI_GRO_CB(p)->count++;
p->prev->next = skb;
p->prev = skb;
skb_header_release(skb);
- p->data_len += skb->len;
- p->truesize += skb->len;
- p->len += skb->len;
+done:
+ NAPI_GRO_CB(p)->count++;
+ p->data_len += len;
+ p->truesize += len;
+ p->len += len;
NAPI_GRO_CB(skb)->same_flow = 1;
return 0;