mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Thomas Gleixner <tglx@linutronix.de>
To: Davidlohr Bueso <davidlohr@hp.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	Ingo Molnar <mingo@kernel.org>,
	Darren Hart <dvhart@linux.intel.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Mike Galbraith <efault@gmx.de>,
	jeffm@suse.com, "Norton, Scott J" <scott.norton@hp.com>,
	tom.vaden@hp.com, "Chandramouleeswaran, Aswin" <aswin@hp.com>,
	Waiman Long <Waiman.Long@hp.com>, Jason Low <jason.low2@hp.com>,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Subject: Re: [PATCH 4/5] futex: Avoid taking hb lock if nothing to wakeup
Date: Mon, 25 Nov 2013 20:47:38 +0100 (CET)	[thread overview]
Message-ID: <alpine.DEB.2.02.1311251938570.30673@ionos.tec.linutronix.de> (raw)
In-Reply-To: <alpine.DEB.2.02.1311231206380.30673@ionos.tec.linutronix.de>

On Sat, 23 Nov 2013, Thomas Gleixner wrote:
> On Fri, 22 Nov 2013, Davidlohr Bueso wrote:
> So with the atomic ops you are changing that to:
> 
> CPU 0					CPU 1
> 
>     val = *futex;
>     futex_wait(futex, val);
> 
>     spin_lock(&hb->lock);
> 
>     atomic_inc(&hb->waiters);
>     uval = *futex;
> 					*futex = newval;
> 
>     if (uval != val) {			futex_wake();
>        spin_unlock(&hb->lock);		if (!atomic_read(&hb->waiters))
>        return;				   return;
>     }
>    					spin_lock((&hb->lock);	
>     plist_add(hb, self);
>     spin_unlock(&hb->lock);
>     schedule();				wakeup_waiters(hb);
>     ...
> 
> which restores the ordering guarantee, which the hash bucket lock
> provided so far.

Actually that's not true by design, it just happens to work.

atomic_inc() on x86 is a "lock incl".

 The LOCK prefix just guarantees that the cache line which is affected
 by the INCL is locked. And it guarantees that locked operations
 serialize all outstanding load and store operations.

 But Documentation/atomic_ops.txt says about atomic_inc():

 "One very important aspect of these two routines is that they DO NOT
  require any explicit memory barriers.  They need only perform the
  atomic_t counter update in an SMP safe manner."

 So while this has a barrier on x86, it's not guaranteed.

atomic_read() is a simple read.

 This does not guarantee anything. And if you read
 Documentation/atomic_ops.txt it's well documented:

 "*** WARNING: atomic_read() and atomic_set() DO NOT IMPLY BARRIERS! ***"


So now your code melts down to:

 write(hb->waiters)    |    write(uaddr)
 mb		       |    read(hb->waiters)
 read(uaddr)

I fear you simply managed to make the window small enough that your
testing was not longer able expose it.

Thanks,

	tglx





  parent reply	other threads:[~2013-11-25 19:47 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-11-23  0:56 [PATCH 0/5] futex: Wakeup optimizations Davidlohr Bueso
2013-11-23  0:56 ` [PATCH 1/5] futex: Misc cleanups Davidlohr Bueso
2013-11-23  6:52   ` Darren Hart
2013-11-23  0:56 ` [PATCH 2/5] futex: Check for pi futex_q only once Davidlohr Bueso
2013-11-23  6:33   ` Darren Hart
2013-11-24  5:19     ` Davidlohr Bueso
2013-11-23  0:56 ` [PATCH 3/5] futex: Larger hash table Davidlohr Bueso
2013-11-23  6:52   ` Darren Hart
2013-11-23  0:56 ` [PATCH 4/5] futex: Avoid taking hb lock if nothing to wakeup Davidlohr Bueso
2013-11-23  1:25   ` Linus Torvalds
2013-11-23  3:03     ` Jason Low
2013-11-23  3:19     ` Davidlohr Bueso
2013-11-23  7:23       ` Darren Hart
2013-11-23 13:16       ` Thomas Gleixner
2013-11-24  3:46         ` Linus Torvalds
2013-11-24  5:15           ` Davidlohr Bueso
2013-11-25 12:01             ` Thomas Gleixner
2013-11-25 16:23           ` Thomas Gleixner
2013-11-25 16:36             ` Peter Zijlstra
2013-11-25 17:32               ` Thomas Gleixner
2013-11-25 17:38                 ` Peter Zijlstra
2013-11-25 18:55                 ` Davidlohr Bueso
2013-11-25 19:52                   ` Thomas Gleixner
2013-11-25 19:47         ` Thomas Gleixner [this message]
2013-11-25 20:03           ` Darren Hart
2013-11-25 20:26             ` Thomas Gleixner
2013-11-26 13:53             ` Thomas Gleixner
2013-11-23  4:05     ` Waiman Long
2013-11-23  5:40   ` Darren Hart
2013-11-23  5:42     ` Hart, Darren
2013-11-23  7:20   ` Darren Hart
2013-11-23  0:56 ` [PATCH 5/5] sched,futex: Provide delayed wakeup list Davidlohr Bueso
2013-11-23 11:48   ` Peter Zijlstra
2013-11-23 12:01     ` Peter Zijlstra
2013-11-24  5:25       ` Davidlohr Bueso
2013-11-23  5:55 ` [PATCH 0/5] futex: Wakeup optimizations Darren Hart
2013-11-23  6:35   ` Mike Galbraith
2013-11-23  6:38   ` Davidlohr Bueso
2014-01-12 23:31 [PATCH v6 " Davidlohr Bueso
2014-01-12 23:31 ` [PATCH 4/5] futex: Avoid taking hb lock if nothing to wakeup Davidlohr Bueso

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=alpine.DEB.2.02.1311251938570.30673@ionos.tec.linutronix.de \
    --to=tglx@linutronix.de \
    --cc=Waiman.Long@hp.com \
    --cc=aswin@hp.com \
    --cc=davidlohr@hp.com \
    --cc=dvhart@linux.intel.com \
    --cc=efault@gmx.de \
    --cc=jason.low2@hp.com \
    --cc=jeffm@suse.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=peterz@infradead.org \
    --cc=scott.norton@hp.com \
    --cc=tom.vaden@hp.com \
    --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

all inboxes | Powered by JetHome®