Re: [PATCH v5 4/5] arm64: mm: implement the architecture-specific clear_flush_young_ptes()

[Alistair Popple <apopple@nvidia.com>]

On 2026-02-09 at 21:13 +1100, Baolin Wang <baolin.wang@linux.alibaba.com> wrote...
> 
> 
> On 2/9/26 5:55 PM, David Hildenbrand (Arm) wrote:
> > On 2/9/26 10:36, Baolin Wang wrote:
> > > 
> > > 
> > > On 2/9/26 5:09 PM, David Hildenbrand (Arm) wrote:
> > > > On 1/29/26 02:42, Baolin Wang wrote:
> > > > > 
> > > > > 
> > > > > 
> > > > > Indeed. I previously discussed with Ryan whether using
> > > > > pte_cont() was enough, and we believed that invalid PTEs
> > > > > wouldn’t have the PTE_CONT bit set. But we clearly missed
> > > > > the device-folio cases. Thanks for reporting.
> > > > > 
> > > > > Andrew, could you please squash the following fix into this
> > > > > patch? If you prefer a new version, please let me know.
> > > > > Thanks.
> > > > 
> > > > Isn't the real problem that we should never ever ever ever, try
> > > > clearing the young bit on a non-present pte?
> > > > 
> > > > See damon_ptep_mkold() how that is handled with the flushing/notify.
> > > > 
> > > > There needs to be a pte_present() check in the caller.
> > > 
> > > The handling of ZONE_DEVICE memory in check_pte() makes me me doubt
> > > my earlier understanding. And I think you are right.
> > > 
> > >      } else if (pte_present(ptent)) {
> > >          pfn = pte_pfn(ptent);
> > >      } else {
> > >          const softleaf_t entry = softleaf_from_pte(ptent);
> > > 
> > >          /* Handle un-addressable ZONE_DEVICE memory */
> > >          if (!softleaf_is_device_private(entry) &&
> > >              !softleaf_is_device_exclusive(entry))
> > >              return false;
> > > 
> > >          pfn = softleaf_to_pfn(entry);
> > >      }
> > > 
> > > 
> > > > BUT
> > > > 
> > > > I recall that folio_referenced() should never apply to
> > > > ZONE_DEVICE folios. folio_referenced() is only called from
> > > > memory reclaim code, and ZONE_DEVICE pages never get reclaimed
> > > > through vmscan.c

Agree this is true, although I've always found the reason somewhat difficult to
see in code because there are no explicit checks for ZONE_DEVICE pages. Instead
it relies on the fact ZONE_DEVICE pages can't be put on any LRU in the first
place, hence reclaim can't find them.

> > > 
> > > Thanks for clarifying. So I can drop the pte valid check.
> > 
> > We should probably add a safety check in folio_referenced(), warning
> > if we would ever get a ZONE_DEVICE folio passed.
> > 
> > Can someone look into that ? :)
> 
> Sure, I can take a close look and address that in my follow-up patchset.
>