public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: paulmck@linux.vnet.ibm.com
Cc: Nick Piggin <nickpiggin@yahoo.com.au>,
	jmerkey@wolfmountaingroup.com,
	Stefan Richter <stefanr@s5r6.in-berlin.de>,
	linux-kernel@vger.kernel.org,
	Linus Torvalds <torvalds@linux-foundation.org>,
	David Howells <dhowells@redhat.com>
Subject: Re: [ANNOUNCE] mdb: Merkey's Linux Kernel Debugger 2.6.27-rc4 released
Date: Thu, 21 Aug 2008 16:48:05 +0200	[thread overview]
Message-ID: <1219330085.8651.144.camel@twins> (raw)
In-Reply-To: <20080821143024.GD6690@linux.vnet.ibm.com>

On Thu, 2008-08-21 at 07:30 -0700, Paul E. McKenney wrote:
> On Thu, Aug 21, 2008 at 04:09:59PM +0200, Peter Zijlstra wrote:
> > On Thu, 2008-08-21 at 23:37 +1000, Nick Piggin wrote:
> > > On Thursday 21 August 2008 22:26, jmerkey@wolfmountaingroup.com wrote:
> > > 
> > > > I used the smp_wmb() functions.  I noted a couple of things.  a) some of
> > > > these macros just emit __asm__ __volatile__ into the code so why not just
> > > > say "volatile" to begin with
> > > 
> > > It is not the same as volatile type. What it does is tell the compiler
> > > to clobber all registers or temporaries. This something pretty well
> > > defined and hard to get wrong compared to volatile type.
> > 
> > Right, asm volatile () means that the asm may not be discarted. Very
> > different from the volatile type qualifier.
> > 
> > > > b) smp_wmb() in some cases worked and in 
> > > > other cases jut optimized away the global reference.
> > > 
> > > Linux barriers aren't going to force a load to be emitted, if it can be
> > > optimized away. If it optimized away a store, then I'd like to see a
> > > test case.
> > 
> > Not sure - I think all barrier clobber the full register and memory set.
> > So if you access a variable after a barrier it will have to issue a
> > load.
> 
> Here is one example (which might or might not be what Nick had in mind):
> 
> 	extern int v;
> 
> 	void foo(void)
> 	{
> 		do_something_with(v);
> 		barrier();
> 		do_something_else_with(v - v);
> 	}
> 
> The second set of loads from v can be optimized away unless v is
> declared volatile.  In contrast:
> 
> 	void bar(void)
> 	{
> 		do_something_with(v);
> 		barrier();
> 		do_something_else_with(v);
> 	}
> 
> Here the compiler must refetch v after the barrier.

Ah, right. But in that case:

 v-v := tmp1 = v; tmp2 = v; sub tmp1,tmp2;

Which you can of course write out more explicitly in C as well and
insert a barrier between the two reads of v, giving the same effect as
volatile.

Still, point taken.


  parent reply	other threads:[~2008-08-21 14:51 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-08-21  2:50 [ANNOUNCE] mdb: Merkey's Linux Kernel Debugger 2.6.27-rc4 released jmerkey
2008-08-21 10:07 ` Peter Zijlstra
2008-08-21 10:57   ` Stefan Richter
2008-08-21 11:02     ` Peter Zijlstra
2008-08-21 11:47       ` Paul E. McKenney
2008-08-21 12:03         ` Peter Zijlstra
2008-08-21 14:53           ` Paul E. McKenney
2008-08-21 14:58             ` jmerkey
2008-08-21 12:05         ` Stefan Richter
2008-08-21 12:26           ` jmerkey
     [not found]             ` <43593.166.70.238.46.1219321595.squirrel@webmail.wolfmountaingroup.com >
2008-08-21 12:35               ` jmerkey
2008-08-21 13:37             ` Nick Piggin
2008-08-21 14:09               ` Stefan Richter
2008-08-22  1:40                 ` Nick Piggin
2008-08-22  6:32                   ` Stefan Richter
2008-08-22 11:54                     ` jmerkey
2008-08-22 12:36                       ` Stefan Richter
2008-08-21 14:09               ` Peter Zijlstra
2008-08-21 14:30                 ` Paul E. McKenney
2008-08-21 14:14                   ` jmerkey
2008-08-21 14:48                   ` Peter Zijlstra [this message]
2008-08-21 16:21                 ` Avi Kivity
2008-08-21 21:06               ` Jeremy Fitzhardinge
2008-08-21 21:18                 ` Linus Torvalds
2008-08-21 21:21                   ` Jeremy Fitzhardinge
2008-08-24  4:25                   ` jmerkey
2008-08-26  8:26                     ` Andi Kleen
2008-08-27  1:49                       ` jmerkey
2008-08-22  1:37                 ` Nick Piggin
2008-08-21 14:02             ` Stefan Richter
2008-08-21 14:08               ` jmerkey
2008-08-21 15:22                 ` Stefan Richter
2008-08-21 15:02                   ` jmerkey
2008-08-21 15:57         ` Linus Torvalds
2008-08-21 16:18           ` Linus Torvalds
2008-08-21 16:48             ` Paul E. McKenney
2008-09-24  0:01               ` Paul E. McKenney
2008-08-21 16:43           ` Paul E. McKenney

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=1219330085.8651.144.camel@twins \
    --to=peterz@infradead.org \
    --cc=dhowells@redhat.com \
    --cc=jmerkey@wolfmountaingroup.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=nickpiggin@yahoo.com.au \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=stefanr@s5r6.in-berlin.de \
    --cc=torvalds@linux-foundation.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