Re: [RFC-PATCH 1/2] mm: Add __GFP_NO_LOCKS flag

[Matthew Wilcox <willy@infradead.org>]

On Thu, Aug 13, 2020 at 06:14:32PM +0200, Thomas Gleixner wrote:
> Matthew Wilcox <willy@infradead.org> writes:
> > On Thu, Aug 13, 2020 at 03:27:15PM +0200, Thomas Gleixner wrote:
> >> And guarding it with RT is not working either because then you are back
> >> to square one with the problem which triggered the discussion in the
> >> first place:
> >> 
> >> raw_spin_lock()
> >>   alloc()
> >>     if (RT && !preemptible())  <- False because RT == false
> >>     	goto bail;
> >> 
> >>     spin_lock(&zone->lock)  --> LOCKDEP complains
> >> 
> >> So either you convince Paul not to do that or you need to do something
> >> like I suggested in my other reply.
> >
> > I'd like to throw in the possibility that we do something like:
> >
> >   raw_spin_lock()
> >     alloc()
> >       if (!spin_trylock(&zone->lock))
> >         if (RT && !preemptible())
> >           goto bail;
> >         spin_lock(&zone->lock);
> >
> > would that make us feel more comfortable about converting zone->lock to
> > a raw spinlock?
> 
> Even if that could cure that particular problem of allocations in deep
> atomic context, making zone->lock raw brings back the problem of
> zone->lock being held/contended for hundreds of microseconds with
> interrupts disabled which is causing RT tasks to miss their deadlines by
> big margins.

Ah, I see.  Yeah, that doesn't work.  Never mind.