From: Avi Kivity <avi@redhat.com>
To: Christoph Lameter <cl@linux.com>
Cc: akpm@linux-foundation.org, Pekka Enberg <penberg@cs.helsinki.fi>,
linux-kernel@vger.kernel.org,
Eric Dumazet <eric.dumazet@gmail.com>,
Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
Tejun Heo <tj@kernel.org>
Subject: Re: [rfc: cpuops adv V1 3/8] x86: this_cpu_cmpxchg and this_cpu_cmpxchg_double operations
Date: Tue, 07 Dec 2010 11:31:17 +0200 [thread overview]
Message-ID: <4CFDFEE5.6030509@redhat.com> (raw)
In-Reply-To: <alpine.DEB.2.00.1012061134170.2866@router.home>
On 12/06/2010 07:35 PM, Christoph Lameter wrote:
> On Mon, 6 Dec 2010, Avi Kivity wrote:
>
> > On 12/02/2010 11:53 PM, Christoph Lameter wrote:
> > > Provide support as far as the hardware capabilities of the x86 cpus
> > > allow.
> > >
> > >
> > >
> > > +/*
> > > + * Beware: xchg on x86 has an implied lock prefix. There will be the cost
> > > of
> > > + * full lock semantics even though they are not needed.
> > > + */
> >
> > Perhaps we can use cmpxchg instead of xchg to avoid this? costs one more
> > instruction but may be worth it.
>
> Hmmm... Maybe good since I also need a xchg_double. And xchg_double can
> only be realized with cmpxchg16b. Using cmpxchg would make it consistent.
I don't think we need to worry about consistency, this is an
implementation not an interface.
We have three choices:
xchg %1, %0
atomic, one instruction
1: cmpxchg %2, %0
jnz 1b
two non-atomic instructions, potential mispredicted jump, extra clobber
(%1 == "=a")
mov %0, %1
1: cmpxchg %2, %0
jnz 1b
three non-atomic instructions, no mispredict, extra clobber
--
error compiling committee.c: too many arguments to function
next prev parent reply other threads:[~2010-12-07 9:31 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-12-02 21:53 [rfc: cpuops adv V1 0/8] Cmpxchg and xchg support for cpu ops Christoph Lameter
2010-12-02 21:53 ` [rfc: cpuops adv V1 1/8] percpu: generic this_cpu_cmpxchg() and this_cpu_cmpxchg_double support Christoph Lameter
2010-12-02 21:53 ` [rfc: cpuops adv V1 2/8] --- include/linux/percpu.h | 31 +++---------------------------- 1 file changed, 3 insertions(+), 28 deletions(-) Christoph Lameter
2010-12-02 22:06 ` [rfc: cpuops adv V1 2/8] Fallback to atomic xchg, cmpxchg Christoph Lameter
2010-12-02 21:53 ` [rfc: cpuops adv V1 3/8] x86: this_cpu_cmpxchg and this_cpu_cmpxchg_double operations Christoph Lameter
2010-12-06 17:14 ` Avi Kivity
2010-12-06 17:35 ` Christoph Lameter
2010-12-07 9:31 ` Avi Kivity [this message]
2010-12-02 21:53 ` [rfc: cpuops adv V1 4/8] irq_work: Use per cpu atomics instead of regular atomics Christoph Lameter
2010-12-02 21:53 ` [rfc: cpuops adv V1 5/8] vmstat: User per cpu atomics to avoid interrupt disable / enable Christoph Lameter
2010-12-02 21:53 ` [rfc: cpuops adv V1 6/8] Lockless (and preemptless) fastpaths for slub Christoph Lameter
2010-12-02 21:53 ` [rfc: cpuops adv V1 7/8] slub: Add PageSlubPartial Christoph Lameter
2010-12-02 21:53 ` [rfc: cpuops adv V1 8/8] slub: [RFC] Partially lockless freepath slowpath Christoph Lameter
2010-12-04 19:29 ` [rfc: cpuops adv V1 0/8] Cmpxchg and xchg support for cpu ops Pekka Enberg
2010-12-04 19:31 ` Tejun Heo
2010-12-06 15:52 ` Christoph Lameter
2010-12-06 15:51 ` Christoph Lameter
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=4CFDFEE5.6030509@redhat.com \
--to=avi@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=cl@linux.com \
--cc=eric.dumazet@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=penberg@cs.helsinki.fi \
--cc=tj@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