netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Ian Campbell <ian.campbell@citrix.com>
To: netdev@vger.kernel.org
Cc: Ian Campbell <ian.campbell@citrix.com>,
	"David S. Miller" <davem@davemloft.net>,
	Eric Dumazet <eric.dumazet@gmail.com>
Subject: [PATCH v3 2/6] net: move destructor_arg to the front of sk_buff.
Date: Wed, 25 Jan 2012 12:27:10 +0000	[thread overview]
Message-ID: <1327494434-21566-2-git-send-email-ian.campbell@citrix.com> (raw)
In-Reply-To: <1327494389.24561.316.camel@zakaz.uk.xensource.com>

As of the previous patch we align the end (rather than the start) of the struct
to a cache line and so, with 32 and 64 byte cache lines and the shinfo size
increase from the next patch, the first 8 bytes of the struct end up on a
different cache line to the rest of it so make sure it is something relatively
unimportant to avoid hitting an extra cache line on hot operations such as
kfree_skb.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
---
 include/linux/skbuff.h |   15 ++++++++++-----
 net/core/skbuff.c      |    5 ++++-
 2 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index f04333b..7b82ed1 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -242,6 +242,15 @@ struct ubuf_info {
  * the end of the header data, ie. at skb->end.
  */
 struct skb_shared_info {
+	/* Intermediate layers must ensure that destructor_arg
+	 * remains valid until skb destructor */
+	void		*destructor_arg;
+
+	/*
+	 * Warning: all fields from here until dataref are cleared in
+	 * __alloc_skb()
+	 *
+	 */
 	unsigned char	nr_frags;
 	__u8		tx_flags;
 	unsigned short	gso_size;
@@ -253,14 +262,10 @@ struct skb_shared_info {
 	__be32          ip6_frag_id;
 
 	/*
-	 * Warning : all fields before dataref are cleared in __alloc_skb()
+	 * Warning: all fields before dataref are cleared in __alloc_skb()
 	 */
 	atomic_t	dataref;
 
-	/* Intermediate layers must ensure that destructor_arg
-	 * remains valid until skb destructor */
-	void *		destructor_arg;
-
 	/* must be last field, see pskb_expand_head() */
 	skb_frag_t	frags[MAX_SKB_FRAGS];
 };
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b6de604..934a9b4 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -219,7 +219,10 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 
 	/* make sure we initialize shinfo sequentially */
 	shinfo = skb_shinfo(skb);
-	memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
+
+	memset(&shinfo->nr_frags, 0,
+	       offsetof(struct skb_shared_info, dataref)
+	       - offsetof(struct skb_shared_info, nr_frags));
 	atomic_set(&shinfo->dataref, 1);
 	kmemcheck_annotate_variable(shinfo->destructor_arg);
 
-- 
1.7.2.5

  parent reply	other threads:[~2012-01-25 12:27 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-01-25 12:26 [PATCH v3 0/6] skb paged fragment destructors Ian Campbell
2012-01-25 12:27 ` [PATCH v3 1/6] net: pad skb data and shinfo as a whole rather than individually Ian Campbell
2012-01-25 12:51   ` Eric Dumazet
2012-01-25 13:09     ` Ian Campbell
2012-01-25 13:12       ` Eric Dumazet
2012-01-31 14:35         ` Ian Campbell
2012-01-31 14:45           ` Eric Dumazet
2012-02-01  9:39             ` Ian Campbell
2012-02-01 10:02               ` Eric Dumazet
2012-02-01 10:09                 ` Ian Campbell
2012-01-31 14:54           ` Francois Romieu
2012-02-01  9:38             ` Ian Campbell
2012-01-25 12:27 ` Ian Campbell [this message]
2012-01-25 12:27 ` [PATCH v3 3/6] net: add support for per-paged-fragment destructors Ian Campbell
2012-01-25 12:27 ` [PATCH v3 4/6] net: only allow paged fragments with the same destructor to be coalesced Ian Campbell
     [not found] ` <1327494389.24561.316.camel-o4Be2W7LfRlXesXXhkcM7miJhflN2719@public.gmane.org>
2012-01-25 12:27   ` [PATCH v3 5/6] net: add paged frag destructor support to kernel_sendpage Ian Campbell
2012-01-25 12:27 ` [PATCH v3 6/6] sunrpc: use SKB fragment destructors to delay completion until page is released by network stack Ian Campbell
     [not found]   ` <1327494434-21566-6-git-send-email-ian.campbell-Sxgqhf6Nn4DQT0dZR+AlfA@public.gmane.org>
2012-01-26 13:11     ` Michael S. Tsirkin
     [not found]       ` <20120126131136.GA16400-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2012-01-30 15:51         ` Ian Campbell
2012-01-30 16:23           ` Michael S. Tsirkin
     [not found]             ` <20120130162306.GB9345-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2012-01-30 16:43               ` Ian Campbell
     [not found]                 ` <1327941813.26983.270.camel-o4Be2W7LfRlXesXXhkcM7miJhflN2719@public.gmane.org>
2012-01-30 18:06                   ` Michael S. Tsirkin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1327494434-21566-2-git-send-email-ian.campbell@citrix.com \
    --to=ian.campbell@citrix.com \
    --cc=davem@davemloft.net \
    --cc=eric.dumazet@gmail.com \
    --cc=netdev@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).