LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Davidlohr Bueso <dave@stgolabs.net>
To: Jason Low <jason.low2@hp.com>
Cc: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@kernel.org>,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
	Michel Lespinasse <walken@google.com>,
	Tim Chen <tim.c.chen@linux.intel.com>,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH 4/6] locking/rwsem: Avoid deceiving lock spinners
Date: Tue, 27 Jan 2015 19:54:54 -0800	[thread overview]
Message-ID: <1422417294.4604.15.camel@stgolabs.net> (raw)
In-Reply-To: <1422379430.6710.6.camel@j-VirtualBox>

On Tue, 2015-01-27 at 09:23 -0800, Jason Low wrote:
> On Sun, 2015-01-25 at 23:36 -0800, Davidlohr Bueso wrote:
> > When readers hold the semaphore, the ->owner is nil. As such,
> > and unlike mutexes, '!owner' does not necessarily imply that
> > the lock is free. This will cause writer spinners to potentially
> > spin excessively as they've been mislead to thinking they have
> > a chance of acquiring the lock, instead of blocking.
> > 
> > This patch therefore replaces this bogus check to solely rely on
> > the counter to know if the lock is available. Because we don't
> > hold the wait lock, we can obviously do this in an unqueued
> > manner.
> > 
> > Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
> > ---
> >  kernel/locking/rwsem-xadd.c | 8 ++++++--
> >  1 file changed, 6 insertions(+), 2 deletions(-)
> > 
> > diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
> > index 5e425d8..18a50da 100644
> > --- a/kernel/locking/rwsem-xadd.c
> > +++ b/kernel/locking/rwsem-xadd.c
> > @@ -335,6 +335,8 @@ static inline bool owner_running(struct rw_semaphore *sem,
> >  static noinline
> >  bool rwsem_spin_on_owner(struct rw_semaphore *sem, struct task_struct *owner)
> >  {
> > +	long count;
> > +
> >  	rcu_read_lock();
> >  	while (owner_running(sem, owner)) {
> >  		if (need_resched())
> > @@ -347,9 +349,11 @@ bool rwsem_spin_on_owner(struct rw_semaphore *sem, struct task_struct *owner)
> >  	/*
> >  	 * We break out the loop above on need_resched() or when the
> >  	 * owner changed, which is a sign for heavy contention. Return
> > -	 * success only when sem->owner is NULL.
> > +	 * success only when the lock is available in order to attempt
> > +	 * another trylock.
> >  	 */
> > -	return sem->owner == NULL;
> > +	count = READ_ONCE(sem->count);
> > +	return count == 0 || count == RWSEM_WAITING_BIAS;
> 
> If we clear the owner field right before unlocking, would this cause
> some situations where we spin until the owner is cleared (about to
> release the lock), and then the spinner return false from
> rwsem_spin_on_owner?

I'm not sure I understand your concern ;) could you rephrase that? 

So I think you're referring to the window between when we 1) clear the
->owner and 2) update the ->counter in the unlocking paths. That would
lead the function to break out of the loop ("owner changed") and return
a bogus "sem is locked, thus taken by a new owner now, continue
spinning" reason for it (counter !=0 yet, for example). 

And that's perfectly fine, really. We've never held a strict
owner-counter dependency, and the owner pointer is completely
unreliable. So all this would end up doing is causing us to perform an
extra iteration per race. This is a pretty good tradeoff for what the
patch addresses.

Thanks,
Davidlohr


  reply	other threads:[~2015-01-28  3:55 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-01-26  7:36 [PATCH -tip 0/6] rwsem: Fine tuning Davidlohr Bueso
2015-01-26  7:36 ` [PATCH 1/6] locking/rwsem: Use task->state helpers Davidlohr Bueso
2015-02-04 14:38   ` [tip:locking/core] " tip-bot for Davidlohr Bueso
2015-01-26  7:36 ` [PATCH 2/6] locking/rwsem: Document barrier need when waking tasks Davidlohr Bueso
2015-01-27 17:07   ` Peter Zijlstra
2015-01-27 20:30     ` Davidlohr Bueso
2015-01-26  7:36 ` [PATCH 3/6] locking/rwsem: Set lock ownership ASAP Davidlohr Bueso
2015-01-27 17:10   ` Peter Zijlstra
2015-01-27 19:18     ` Davidlohr Bueso
2015-01-26  7:36 ` [PATCH 4/6] locking/rwsem: Avoid deceiving lock spinners Davidlohr Bueso
2015-01-27 17:23   ` Jason Low
2015-01-28  3:54     ` Davidlohr Bueso [this message]
2015-01-28 17:01       ` Tim Chen
2015-01-28 21:03       ` Jason Low
2015-01-29  1:10         ` Davidlohr Bueso
2015-01-29 20:13           ` Jason Low
2015-01-29 20:18             ` Jason Low
2015-01-29 23:15               ` Davidlohr Bueso
2015-01-30  1:52                 ` Refactoring mutex spin on owner code Jason Low
2015-01-30  7:14                   ` Davidlohr Bueso
2015-01-30  7:51                     ` Peter Zijlstra
2015-01-26  7:36 ` [PATCH 5/6] locking/rwsem: Optimize slowpath/sleeping Davidlohr Bueso
2015-01-27 17:34   ` Peter Zijlstra
2015-01-27 21:57     ` Davidlohr Bueso
2015-01-26  7:36 ` [PATCH 6/6] locking/rwsem: Check for active lock before bailing on spinning Davidlohr Bueso
2015-01-27 18:11   ` Jason Low

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=1422417294.4604.15.camel@stgolabs.net \
    --to=dave@stgolabs.net \
    --cc=jason.low2@hp.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=peterz@infradead.org \
    --cc=tim.c.chen@linux.intel.com \
    --cc=walken@google.com \
    --subject='Re: [PATCH 4/6] locking/rwsem: Avoid deceiving lock spinners' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).