Re: [PATCH v5] mm: Fix a hmm_range_fault() livelock / starvation problem

[Matthew Brost <matthew.brost@intel.com>]

On Thu, Feb 12, 2026 at 09:54:50AM +1100, Alistair Popple wrote:
> On 2026-02-12 at 09:23 +1100, Davidlohr Bueso <dave@stgolabs.net> wrote...
> > On Tue, 10 Feb 2026, Thomas Hellstr�m wrote:
> > 
> > > @@ -176,7 +176,7 @@ static int migrate_vma_collect_huge_pmd(pmd_t *pmdp, unsigned long start,
> > > 		}
> > > 
> > > 		if (softleaf_is_migration(entry)) {
> > > -			migration_entry_wait_on_locked(entry, ptl);
> > > +			softleaf_entry_wait_on_locked(entry, ptl);
> > > 			spin_unlock(ptl);
> > 
> > softleaf_entry_wait_on_locked() unconditionally drops the ptl.
> 
> As does migration_entry_wait_on_locked() so obviously a pre-existing issue.
> I'm not sure why we would wait on a migration entry here though, maybe Balbir
> can help?

I noticed this recently as being odd, given that we don’t wait on PTE
migration entries.

Looking again, this is unreachable code, since we bail out just above
this if statement on !softleaf_is_device_private(entry). So we should
just delete this entire if statement.

Matt

> 
> > > 			return -EAGAIN;
> > > 		}