Displaying 5 results from an estimated 5 matches for "invalidate_range_start_non_block".
2019 Jul 24
2
[PATCH] mm/hmm: replace hmm_update with mmu_notifier_range
...ange_end:
spin_lock()
counter--
spin_unlock()
And this one:
B invalidate_range_start: (has blocking)
if (!try_mutex_lock())
return -EAGAIN;
counter++
mutex_unlock()
B invalidate_range_end:
spin_lock()
counter--
spin_unlock()
So now the oom path does:
invalidate_range_start_non_blocking:
for each mn:
a->invalidate_range_start
b->invalidate_range_start
rc = EAGAIN
Now we SKIP A's invalidate_range_end even though A had no idea this
would happen has state that needs to be unwound. A is broken.
B survived just fine.
A and B *alone* work fine, combined they fa...
2019 Jul 24
2
[PATCH] mm/hmm: replace hmm_update with mmu_notifier_range
...f (!try_mutex_lock())
> > return -EAGAIN;
> > counter++
> > mutex_unlock()
> >
> > B invalidate_range_end:
> > spin_lock()
> > counter--
> > spin_unlock()
> >
> > So now the oom path does:
> >
> > invalidate_range_start_non_blocking:
> > for each mn:
> > a->invalidate_range_start
> > b->invalidate_range_start
> > rc = EAGAIN
> >
> > Now we SKIP A's invalidate_range_end even though A had no idea this
> > would happen has state that needs to be unwound. A is broke...
2019 Jul 24
0
[PATCH] mm/hmm: replace hmm_update with mmu_notifier_range
...t;
> B invalidate_range_start: (has blocking)
> if (!try_mutex_lock())
> return -EAGAIN;
> counter++
> mutex_unlock()
>
> B invalidate_range_end:
> spin_lock()
> counter--
> spin_unlock()
>
> So now the oom path does:
>
> invalidate_range_start_non_blocking:
> for each mn:
> a->invalidate_range_start
> b->invalidate_range_start
> rc = EAGAIN
>
> Now we SKIP A's invalidate_range_end even though A had no idea this
> would happen has state that needs to be unwound. A is broken.
>
> B survived just fine....
2019 Jul 24
0
[PATCH] mm/hmm: replace hmm_update with mmu_notifier_range
...> > > counter++
> > > mutex_unlock()
> > >
> > > B invalidate_range_end:
> > > spin_lock()
> > > counter--
> > > spin_unlock()
> > >
> > > So now the oom path does:
> > >
> > > invalidate_range_start_non_blocking:
> > > for each mn:
> > > a->invalidate_range_start
> > > b->invalidate_range_start
> > > rc = EAGAIN
> > >
> > > Now we SKIP A's invalidate_range_end even though A had no idea this
> > > would happen has state t...
2019 Jul 24
5
[PATCH] mm/hmm: replace hmm_update with mmu_notifier_range
On Wed, Jul 24, 2019 at 09:05:53AM +0200, Christoph Hellwig wrote:
> Looks good:
>
> Reviewed-by: Christoph Hellwig <hch at lst.de>
>
> One comment on a related cleanup:
>
> > list_for_each_entry(mirror, &hmm->mirrors, list) {
> > int rc;
> >
> > - rc = mirror->ops->sync_cpu_device_pagetables(mirror, &update);
> > +