Re: [RFC][PATCH -v2 4/4] locking/mutex: Add lock handoff to avoid starvation

[Waiman Long]

On 08/30/2016 07:53 AM, Peter Zijlstra wrote:
> On Mon, Aug 29, 2016 at 05:41:09PM +0200, Peter Zijlstra wrote:
> > On Fri, Aug 26, 2016 at 07:40:34PM -0400, Waiman Long wrote:
> > > On 08/26/2016 11:18 AM, Peter Zijlstra wrote:
> > > > Still need to look at adding spinning to the handoff case.
> > > > Also need to look at writing (much) better changelogs, they stink.
> > > I have looked at the handoff code and I didn't see any problem.
> > So I found (or rather the buildbot did) a problem with it.
> >
> > locking-selftest has testcases like:
> >
> >
> > 	lock(&A);
> > 	if (trylock(&A))
> > 		/* fail */
> >
> >    and
> >
> > 	ww_lock(&A)
> > 	if (ww_lock(&A) != -EDEADLK)
> > 		/* fail */
> >
> > But with the 'trylock' accepting the lock if owner==current, in order to
> > accept the hand-off, this breaks in interesting ways.
> >
> > Now, ARCH_MIN_TASKALIGN is at least 8 (mips, s390, parisc) which would
> > give us one more FLAG bit to play with.
> >
> >
> > The below seems to make things happy again..
> Much simpler solution... only accept handoffs when we're stuck in the
> wait loop (which precludes doing recursive locking, since that would've
> failed much earlier).
>
> Now, let me look at that spinner patch you sent.

Yes, that is like my original mutex patch that sets a flag (the handoff 
bit) that disable the optimistic spinner from grabbing the lock. I 
hadn't been thinking about the corner case of a trylock after lock. 
Fortunately, we have test that can uncover those problems.

Cheers,
Longman