All of lore.kernel.org
 help / color / mirror / Atom feed
From: "H. Peter Anvin" <hpa@zytor.com>
To: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Avi Kivity <avi@qumranet.com>, Arnd Bergmann <arnd@arndb.de>,
	kvm-devel@lists.sourceforge.net, akpm@osdl.org,
	linux-kernel@vger.kernel.org
Subject: Re: [kvm-devel] [PATCH] KVM: Avoid using vmx instruction directly
Date: Tue, 21 Nov 2006 10:35:48 -0800	[thread overview]
Message-ID: <45634704.8020407@zytor.com> (raw)
In-Reply-To: <4553BC18.6090207@goop.org>

Jeremy Fitzhardinge wrote:
> Avi Kivity wrote:
>>> Or gcc
>>> might move the assignment of phys_addr to after the inline assembly.
>>>   
>> "asm volatile" prevents that (and I'm not 100% sure it's necessary).
> 
> No, it won't necessarily.  "asm volatile" simply forces gcc to emit the
> assembler, even if it thinks its output doesn't get used.  It makes no
> ordering guarantees with respect to other code (or even other "asm
> volatiles").   The "memory" clobbers should fix the ordering of the asms
> though.
> 

I think you're wrong about that; in particular, I'm pretty sure "asm 
volatiles" are ordered among themselves.  What the "volatile" means is 
"this has side effects you (the compiler) don't understand", and gcc 
can't assume that it can reorder such side effects.

	-hpa

WARNING: multiple messages have this Message-ID (diff)
From: "H. Peter Anvin" <hpa-YMNOUZJC4hwAvxtiuMwx3w@public.gmane.org>
To: Jeremy Fitzhardinge <jeremy-TSDbQ3PG+2Y@public.gmane.org>
Cc: kvm-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org,
	akpm-3NddpPZAyC0@public.gmane.org,
	linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Subject: Re: [PATCH] KVM: Avoid using vmx instruction directly
Date: Tue, 21 Nov 2006 10:35:48 -0800	[thread overview]
Message-ID: <45634704.8020407@zytor.com> (raw)
In-Reply-To: <4553BC18.6090207-TSDbQ3PG+2Y@public.gmane.org>

Jeremy Fitzhardinge wrote:
> Avi Kivity wrote:
>>> Or gcc
>>> might move the assignment of phys_addr to after the inline assembly.
>>>   
>> "asm volatile" prevents that (and I'm not 100% sure it's necessary).
> 
> No, it won't necessarily.  "asm volatile" simply forces gcc to emit the
> assembler, even if it thinks its output doesn't get used.  It makes no
> ordering guarantees with respect to other code (or even other "asm
> volatiles").   The "memory" clobbers should fix the ordering of the asms
> though.
> 

I think you're wrong about that; in particular, I'm pretty sure "asm 
volatiles" are ordered among themselves.  What the "volatile" means is 
"this has side effects you (the compiler) don't understand", and gcc 
can't assume that it can reorder such side effects.

	-hpa

-------------------------------------------------------------------------
Take Surveys. Earn Cash. Influence the Future of IT
Join SourceForge.net's Techsay panel and you'll get the chance to share your
opinions on IT & business topics through brief surveys - and earn cash
http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV

  parent reply	other threads:[~2006-11-21 18:36 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-11-09 11:08 [PATCH] KVM: Avoid using vmx instruction directly Avi Kivity
2006-11-09 11:08 ` Avi Kivity
2006-11-09 13:29 ` [kvm-devel] " Arnd Bergmann
2006-11-09 13:29   ` Arnd Bergmann
2006-11-09 13:36   ` [kvm-devel] " Avi Kivity
2006-11-09 13:36     ` Avi Kivity
2006-11-09 14:42     ` [kvm-devel] " Arnd Bergmann
2006-11-09 14:42       ` Arnd Bergmann
2006-11-09 14:52       ` [kvm-devel] " Avi Kivity
2006-11-09 16:37         ` Arnd Bergmann
2006-11-09 16:51           ` Avi Kivity
2006-11-09 23:39         ` Jeremy Fitzhardinge
2006-11-10 12:46           ` Martin Schwidefsky
2006-11-10 19:38             ` Jeremy Fitzhardinge
2006-11-10 19:38               ` Jeremy Fitzhardinge
2006-11-21 18:35           ` H. Peter Anvin [this message]
2006-11-21 18:35             ` H. Peter Anvin
2006-11-21 19:41             ` [kvm-devel] " Avi Kivity
2006-11-21 19:41               ` Avi Kivity
2006-11-21 20:50             ` [kvm-devel] " Jeremy Fitzhardinge
2006-11-21 20:50               ` Jeremy Fitzhardinge
2006-11-22  6:42               ` [kvm-devel] " Avi Kivity
2006-11-22  6:42                 ` Avi Kivity
2006-11-22  9:10                 ` [kvm-devel] " Jeremy Fitzhardinge
2006-11-22  9:10                   ` Jeremy Fitzhardinge

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=45634704.8020407@zytor.com \
    --to=hpa@zytor.com \
    --cc=akpm@osdl.org \
    --cc=arnd@arndb.de \
    --cc=avi@qumranet.com \
    --cc=jeremy@goop.org \
    --cc=kvm-devel@lists.sourceforge.net \
    --cc=linux-kernel@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.