Re: [PATCH] tcp: splice as many packets as possible at once

[David Miller]

From: Evgeniy Polyakov <zbr@xxxxxxxxxxx>
Date: Wed, 14 Jan 2009 03:22:52 +0300

> On Tue, Jan 13, 2009 at 04:16:25PM -0800, David Miller (davem@xxxxxxxxxxxxx) wrote:
> > I wish there were some way we could make this code grab and release a
> > reference to the SKB data area (I mean skb_shinfo(skb)->dataref) to
> > accomplish it's goals.
> 
> Ugh... Clone without cloninig, but by increasing the dataref. Getting
> that splice only needs that skb to track the head of the original, this
> may really work.

Here is something I scrambled together, it is largely based upon
Jarek's patch:

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 5110b35..05126da 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -70,12 +70,17 @@
 static struct kmem_cache *skbuff_head_cache __read_mostly;
 static struct kmem_cache *skbuff_fclone_cache __read_mostly;
 
+static void skb_release_data(struct sk_buff *skb);
+
 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);
+	if (skb)
+		skb_release_data(skb);
+	else
+		put_page(buf->page);
 }
 
 static void sock_pipe_buf_get(struct pipe_inode_info *pipe,
@@ -83,7 +88,10 @@ static void sock_pipe_buf_get(struct pipe_inode_info *pipe,
 {
 	struct sk_buff *skb = (struct sk_buff *) buf->private;
 
-	skb_get(skb);
+	if (skb)
+		atomic_inc(&skb_shinfo(skb)->dataref);
+	else
+		get_page(buf->page);
 }
 
 static int sock_pipe_buf_steal(struct pipe_inode_info *pipe,
@@ -1336,7 +1344,10 @@ 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);
+	if (skb)
+		skb_release_data(skb);
+	else
+		put_page(spd->pages[i]);
 }
 
 /*
@@ -1344,7 +1355,7 @@ static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i)
  */
 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;
@@ -1352,8 +1363,15 @@ static inline int spd_fill_page(struct splice_pipe_desc *spd, struct 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->partial[spd->nr_pages].private =
+		(unsigned long) (linear ? skb : NULL);
 	spd->nr_pages++;
+
+	if (linear)
+		atomic_inc(&skb_shinfo(skb)->dataref);
+	else
+		get_page(page);
+
 	return 0;
 }
 
@@ -1369,7 +1387,7 @@ static inline void __segment_seek(struct page **page, unsigned int *poff,
 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;
@@ -1392,7 +1410,7 @@ static inline int __splice_segment(struct page *page, unsigned int poff,
 		/* 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);
@@ -1419,7 +1437,7 @@ static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset,
 	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;
 
 	/*
@@ -1429,7 +1447,7 @@ static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset,
 		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;
 	}
 
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/