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

[Baolin Wang]

On 2/9/26 5:09 PM, David Hildenbrand (Arm) wrote:
> On 1/29/26 02:42, Baolin Wang wrote:
> > On 1/28/26 7:47 PM, Chris Mason wrote:
> > > Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx> wrote:
> > > > Implement the Arm64 architecture-specific clear_flush_young_ptes() 
> > > > to enable
> > > > batched checking of young flags and TLB flushing, improving 
> > > > performance during
> > > > large folio reclamation.
> > > >
> > > > Performance testing:
> > > > Allocate 10G clean file-backed folios by mmap() in a memory cgroup, 
> > > > and try to
> > > > reclaim 8G file-backed folios via the memory.reclaim interface. I 
> > > > can observe
> > > > 33% performance improvement on my Arm64 32-core server (and 10%+ 
> > > > improvement
> > > > on my X86 machine). Meanwhile, the hotspot folio_check_references() 
> > > > dropped
> > > > from approximately 35% to around 5%.
> > >
> > > Hi everyone, I ran mm-new through my AI review prompts and this one was
> > > flagged.  AI review below:
> > >
> > > > diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/ 
> > > > asm/pgtable.h
> > > > --- a/arch/arm64/include/asm/pgtable.h
> > > > +++ b/arch/arm64/include/asm/pgtable.h
> > > > @@ -1838,6 +1838,17 @@ static inline int 
> > > > ptep_clear_flush_young(struct vm_area_struct *vma,
> > > >       return contpte_clear_flush_young_ptes(vma, addr, ptep, 1);
> > > >   }
> > > >
> > > > +#define clear_flush_young_ptes clear_flush_young_ptes
> > > > +static inline int clear_flush_young_ptes(struct vm_area_struct *vma,
> > > > +                     unsigned long addr, pte_t *ptep,
> > > > +                     unsigned int nr)
> > > > +{
> > > > +    if (likely(nr == 1 && !pte_cont(__ptep_get(ptep))))
> > > > +        return __ptep_clear_flush_young(vma, addr, ptep);
> > >
> > > Should this be checking !pte_valid_cont() instead of !pte_cont()?
> > >
> > > The existing ptep_clear_flush_young() above uses !pte_valid_cont() to
> > > determine when to take the fast path. The new function only checks
> > > !pte_cont(), which differs when handling non-present PTEs.
> > >
> > > Non-present PTEs (device-private, device-exclusive) can reach
> > > clear_flush_young_ptes() through folio_referenced_one()->
> > > clear_flush_young_ptes_notify(). These entries may have bit 52 set as
> > > part of their encoding, but they aren't valid contiguous mappings.
> > >
> > > With the current check, wouldn't such entries incorrectly trigger the
> > > contpte path and potentially cause contpte_clear_flush_young_ptes() to
> > > process additional unrelated PTEs beyond the intended single entry?
> >
> > 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

Thanks for clarifying. So I can drop the pte valid check.