[PATCH net-next] net: speedup skb_splice_bits()

[Eric Dumazet <eric.dumazet@xxxxxxxxx>]

From: Eric Dumazet <edumazet@xxxxxxxxxx>

Commit 35f3d14db (pipe: add support for shrinking and growing pipes)
added a slowdown for splice(socket -> pipe), as we might grow the spd
used in skb_splice_bits() for each skb we process in splice() syscall.

Its not needed since skb lengths are capped. The default on-stack arrays
are more than enough.

Use MAX_SKB_FRAGS instead of PIPE_DEF_BUFFERS to describe the reasonable
limit per skb.

Add coalescing support to help splicing of GRO skbs built from linear
skbs (linked into frag_list)

Signed-off-by: Eric Dumazet <edumazet@xxxxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
Cc: Tom Herbert <therbert@xxxxxxxxxx>
---
 net/core/skbuff.c |   30 +++++++++++++++++++-----------
 1 file changed, 19 insertions(+), 11 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index bf257de..dfb3040 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1581,11 +1581,20 @@ new_page:
 	memcpy(page_address(p) + off, page_address(page) + *offset, *len);
 	sk->sk_sndmsg_off += *len;
 	*offset = off;
-	get_page(p);
 
 	return p;
 }
 
+static bool spd_can_coalesce(const struct splice_pipe_desc *spd,
+			     struct page *page,
+			     unsigned int offset)
+{
+	return	spd->nr_pages &&
+		spd->pages[spd->nr_pages - 1] == page &&
+		(spd->partial[spd->nr_pages - 1].offset +
+		 spd->partial[spd->nr_pages - 1].len == offset);
+}
+
 /*
  * Fill page/offset/length into spd, if it can hold more pages.
  */
@@ -1595,16 +1604,19 @@ static inline int spd_fill_page(struct splice_pipe_desc *spd,
 				struct sk_buff *skb, int linear,
 				struct sock *sk)
 {
-	if (unlikely(spd->nr_pages == pipe->buffers))
+	if (unlikely(spd->nr_pages == MAX_SKB_FRAGS))
 		return 1;
 
 	if (linear) {
 		page = linear_to_page(page, len, &offset, skb, sk);
 		if (!page)
 			return 1;
-	} else
-		get_page(page);
-
+	}
+	if (spd_can_coalesce(spd, page, offset)) {
+		spd->partial[spd->nr_pages - 1].len += *len;
+		return 0;
+	}
+	get_page(page);
 	spd->pages[spd->nr_pages] = page;
 	spd->partial[spd->nr_pages].len = *len;
 	spd->partial[spd->nr_pages].offset = offset;
@@ -1710,8 +1722,8 @@ 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_DEF_BUFFERS];
-	struct page *pages[PIPE_DEF_BUFFERS];
+	struct partial_page partial[MAX_SKB_FRAGS];
+	struct page *pages[MAX_SKB_FRAGS];
 	struct splice_pipe_desc spd = {
 		.pages = pages,
 		.partial = partial,
@@ -1723,9 +1735,6 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset,
 	struct sock *sk = skb->sk;
 	int ret = 0;
 
-	if (splice_grow_spd(pipe, &spd))
-		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.
@@ -1761,7 +1770,6 @@ done:
 		lock_sock(sk);
 	}
 
-	splice_shrink_spd(pipe, &spd);
 	return ret;
 }
 


--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html