mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: David Laight <David.Laight@ACULAB.COM>
To: "'Herbert Xu'" <herbert@gondor.apana.org.au>,
	Peter Zijlstra <peterz@infradead.org>
Cc: David Miller <davem@davemloft.net>,
	"eric.dumazet@gmail.com" <eric.dumazet@gmail.com>,
	"elena.reshetova@intel.com" <elena.reshetova@intel.com>,
	"keescook@chromium.org" <keescook@chromium.org>,
	"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
	"bridge@lists.linux-foundation.org" 
	<bridge@lists.linux-foundation.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"kuznet@ms2.inr.ac.ru" <kuznet@ms2.inr.ac.ru>,
	"jmorris@namei.org" <jmorris@namei.org>,
	"kaber@trash.net" <kaber@trash.net>,
	"stephen@networkplumber.org" <stephen@networkplumber.org>,
	"ishkamiel@gmail.com" <ishkamiel@gmail.com>,
	"dwindsor@gmail.com" <dwindsor@gmail.com>,
	"akpm@linux-foundation.org" <akpm@linux-foundation.org>
Subject: RE: [PATCH 07/17] net: convert sock.sk_refcnt from atomic_t to refcount_t
Date: Mon, 20 Mar 2017 14:10:24 +0000	[thread overview]
Message-ID: <063D6719AE5E284EB5DD2968C1650D6DCFFB5483@AcuExch.aculab.com> (raw)
In-Reply-To: <20170320131629.GA26405@gondor.apana.org.au>

From: Herbert Xu
> Sent: 20 March 2017 13:16
> On Mon, Mar 20, 2017 at 11:39:37AM +0100, Peter Zijlstra wrote:
> >
> > Can we at least give a benchmark and have someone run numbers? We should
> > be able to quantify these things.
> 
> Do you realise how many times this thing gets hit at 10Gb/s or
> higher? Anyway, since you're proposing this change you should
> demonstrate that it does not cause a performance regression.

What checks does refcnt_t actually do?

An extra decrement is hard to detect since the item gets freed early.
I guess making the main 'allocate/free' code hold (say) 64k references
would give some leeway for extra decrements.

An extra increment will be detected when the count eventually wraps.
Unless the error is in a very common path that won't happen for a long time.

On x86 the cpu flags from the 'lock inc/dec' could be used to reasonably
cheaply detect errors - provided you actually generate a forwards branch.

Otherwise having a common, but not every packet, code path verify that the
reference count is 'sane' would give reasonable coverage.

	David

  parent reply	other threads:[~2017-03-20 14:15 UTC|newest]

Thread overview: 54+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-03-16 15:28 [PATCH 00/17] net subsystem refcount conversions Elena Reshetova
2017-03-16 15:28 ` [PATCH 01/17] net: convert neighbour.refcnt from atomic_t to refcount_t Elena Reshetova
2017-03-16 15:28 ` [PATCH 02/17] net: convert neigh_params.refcnt " Elena Reshetova
2017-03-16 15:28 ` [PATCH 03/17] net: convert nf_bridge_info.use " Elena Reshetova
2017-03-16 15:28 ` [PATCH 04/17] net: convert sk_buff.users " Elena Reshetova
2017-03-16 15:28 ` [PATCH 05/17] net: convert sk_buff_fclones.fclone_ref " Elena Reshetova
2017-03-16 15:28 ` [PATCH 06/17] net: convert sock.sk_wmem_alloc " Elena Reshetova
2017-03-16 15:28 ` [PATCH 07/17] net: convert sock.sk_refcnt " Elena Reshetova
2017-03-16 16:58   ` Eric Dumazet
2017-03-16 17:38     ` Kees Cook
2017-03-16 19:10       ` David Miller
2017-03-17  7:42         ` Reshetova, Elena
2017-03-17 16:13           ` Eric Dumazet
2017-03-18 16:47             ` Herbert Xu
2017-03-19  1:21               ` David Miller
2017-03-20 10:39                 ` Peter Zijlstra
2017-03-20 13:16                   ` Herbert Xu
2017-03-20 13:23                     ` Peter Zijlstra
2017-03-20 13:27                       ` Herbert Xu
2017-03-20 13:40                         ` Peter Zijlstra
2017-03-20 14:51                           ` Eric Dumazet
2017-03-20 14:59                             ` Eric Dumazet
2017-03-20 16:18                               ` Eric Dumazet
2017-03-20 16:34                                 ` Eric Dumazet
2017-03-20 14:59                             ` Peter Zijlstra
2017-03-21 20:49                           ` Kees Cook
2017-03-21 21:23                             ` Eric Dumazet
2017-03-21 22:36                               ` David Miller
2017-03-21 23:51                               ` Kees Cook
2017-03-22  2:03                                 ` Eric Dumazet
2017-03-22 12:25                                   ` Peter Zijlstra
2017-03-22 13:22                                     ` Eric Dumazet
2017-03-22 14:33                                       ` Peter Zijlstra
2017-03-22 14:54                                         ` Eric Dumazet
2017-03-22 15:08                                           ` Peter Zijlstra
2017-03-22 15:22                                             ` Eric Dumazet
2017-03-22 16:51                                           ` Peter Zijlstra
2017-03-22 19:08                                   ` Kees Cook
2017-03-22 12:11                                 ` Peter Zijlstra
2017-03-20 14:10                     ` David Laight [this message]
2017-03-20 14:28                       ` Peter Zijlstra
2017-03-20 15:00                         ` David Laight
2017-03-16 15:28 ` [PATCH 08/17] net: convert sk_filter.refcnt " Elena Reshetova
2017-03-16 16:04   ` Daniel Borkmann
2017-03-17  8:02     ` Reshetova, Elena
2017-03-16 15:28 ` [PATCH 09/17] net: convert ip_mc_list.refcnt " Elena Reshetova
2017-03-16 15:29 ` [PATCH 10/17] net: convert in_device.refcnt " Elena Reshetova
2017-03-16 15:29 ` [PATCH 11/17] net: convert netpoll_info.refcnt " Elena Reshetova
2017-03-16 15:29 ` [PATCH 12/17] net: convert unix_address.refcnt " Elena Reshetova
2017-03-16 15:29 ` [PATCH 13/17] net: convert fib_rule.refcnt " Elena Reshetova
2017-03-16 15:29 ` [PATCH 14/17] net: convert inet_frag_queue.refcnt " Elena Reshetova
2017-03-16 15:29 ` [PATCH 15/17] net: convert net.passive " Elena Reshetova
2017-03-16 15:29 ` [PATCH 16/17] net: convert netlbl_lsm_cache.refcount " Elena Reshetova
2017-03-16 15:29 ` [PATCH 17/17] net: convert packet_fanout.sk_ref " Elena Reshetova

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=063D6719AE5E284EB5DD2968C1650D6DCFFB5483@AcuExch.aculab.com \
    --to=david.laight@aculab.com \
    --cc=akpm@linux-foundation.org \
    --cc=bridge@lists.linux-foundation.org \
    --cc=davem@davemloft.net \
    --cc=dwindsor@gmail.com \
    --cc=elena.reshetova@intel.com \
    --cc=eric.dumazet@gmail.com \
    --cc=herbert@gondor.apana.org.au \
    --cc=ishkamiel@gmail.com \
    --cc=jmorris@namei.org \
    --cc=kaber@trash.net \
    --cc=keescook@chromium.org \
    --cc=kuznet@ms2.inr.ac.ru \
    --cc=linux-kernel@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=peterz@infradead.org \
    --cc=stephen@networkplumber.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

all inboxes | Powered by JetHome®