Re: [v6 02/15] mm/huge_memory: add device-private THP support to PMD operations

[Alistair Popple <apopple@nvidia.com>]

On 2025-09-16 at 22:21 +1000, Balbir Singh <balbirs@nvidia.com> wrote...
> Extend core huge page management functions to handle device-private THP
> entries.  This enables proper handling of large device-private folios in
> fundamental MM operations.
> 
> The following functions have been updated:
> 
> - copy_huge_pmd(): Handle device-private entries during fork/clone
> - zap_huge_pmd(): Properly free device-private THP during munmap
> - change_huge_pmd(): Support protection changes on device-private THP
> - __pte_offset_map(): Add device-private entry awareness
> 
> Signed-off-by: Matthew Brost <matthew.brost@intel.com>
> Signed-off-by: Balbir Singh <balbirs@nvidia.com>
> Cc: David Hildenbrand <david@redhat.com>
> Cc: Zi Yan <ziy@nvidia.com>
> Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
> Cc: Rakie Kim <rakie.kim@sk.com>
> Cc: Byungchul Park <byungchul@sk.com>
> Cc: Gregory Price <gourry@gourry.net>
> Cc: Ying Huang <ying.huang@linux.alibaba.com>
> Cc: Alistair Popple <apopple@nvidia.com>
> Cc: Oscar Salvador <osalvador@suse.de>
> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
> Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
> Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
> Cc: Nico Pache <npache@redhat.com>
> Cc: Ryan Roberts <ryan.roberts@arm.com>
> Cc: Dev Jain <dev.jain@arm.com>
> Cc: Barry Song <baohua@kernel.org>
> Cc: Lyude Paul <lyude@redhat.com>
> Cc: Danilo Krummrich <dakr@kernel.org>
> Cc: David Airlie <airlied@gmail.com>
> Cc: Simona Vetter <simona@ffwll.ch>
> Cc: Ralph Campbell <rcampbell@nvidia.com>
> Cc: Mika Penttilä <mpenttil@redhat.com>
> Cc: Matthew Brost <matthew.brost@intel.com>
> Cc: Francois Dugast <francois.dugast@intel.com>
> ---
>  include/linux/swapops.h | 32 +++++++++++++++++++++++
>  mm/huge_memory.c        | 56 ++++++++++++++++++++++++++++++++++-------
>  mm/pgtable-generic.c    |  2 +-
>  3 files changed, 80 insertions(+), 10 deletions(-)
> 
> diff --git a/include/linux/swapops.h b/include/linux/swapops.h
> index 64ea151a7ae3..2687928a8146 100644
> --- a/include/linux/swapops.h
> +++ b/include/linux/swapops.h
> @@ -594,10 +594,42 @@ static inline int is_pmd_migration_entry(pmd_t pmd)
>  }
>  #endif  /* CONFIG_ARCH_ENABLE_THP_MIGRATION */
>  
> +#if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_ARCH_ENABLE_THP_MIGRATION)
> +
> +/**
> + * is_pmd_device_private_entry() - Check if PMD contains a device private swap entry
> + * @pmd: The PMD to check
> + *
> + * Returns true if the PMD contains a swap entry that represents a device private
> + * page mapping. This is used for zone device private pages that have been
> + * swapped out but still need special handling during various memory management
> + * operations.
> + *
> + * Return: 1 if PMD contains device private entry, 0 otherwise
> + */
> +static inline int is_pmd_device_private_entry(pmd_t pmd)
> +{
> +	return is_swap_pmd(pmd) && is_device_private_entry(pmd_to_swp_entry(pmd));
> +}
> +
> +#else /* CONFIG_ZONE_DEVICE && CONFIG_ARCH_ENABLE_THP_MIGRATION */
> +
> +static inline int is_pmd_device_private_entry(pmd_t pmd)
> +{
> +	return 0;
> +}
> +
> +#endif /* CONFIG_ZONE_DEVICE && CONFIG_ARCH_ENABLE_THP_MIGRATION */
> +
>  static inline int non_swap_entry(swp_entry_t entry)
>  {
>  	return swp_type(entry) >= MAX_SWAPFILES;
>  }
>  
> +static inline int is_pmd_non_present_folio_entry(pmd_t pmd)

I can't think of a better name either although I am curious why open-coding it
was so nasty given we don't have the equivalent for pte entries. Will go read
the previous discussion.

> +{
> +	return is_pmd_migration_entry(pmd) || is_pmd_device_private_entry(pmd);
> +}
> +
>  #endif /* CONFIG_MMU */
>  #endif /* _LINUX_SWAPOPS_H */
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index 5acca24bbabb..a5e4c2aef191 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -1703,17 +1703,45 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
>  	if (unlikely(is_swap_pmd(pmd))) {
>  		swp_entry_t entry = pmd_to_swp_entry(pmd);
>  
> -		VM_BUG_ON(!is_pmd_migration_entry(pmd));
> -		if (!is_readable_migration_entry(entry)) {
> -			entry = make_readable_migration_entry(
> -							swp_offset(entry));
> +		VM_WARN_ON(!is_pmd_non_present_folio_entry(pmd));
> +
> +		if (is_writable_migration_entry(entry) ||
> +		    is_readable_exclusive_migration_entry(entry)) {
> +			entry = make_readable_migration_entry(swp_offset(entry));
>  			pmd = swp_entry_to_pmd(entry);
>  			if (pmd_swp_soft_dirty(*src_pmd))
>  				pmd = pmd_swp_mksoft_dirty(pmd);
>  			if (pmd_swp_uffd_wp(*src_pmd))
>  				pmd = pmd_swp_mkuffd_wp(pmd);
>  			set_pmd_at(src_mm, addr, src_pmd, pmd);
> +		} else if (is_device_private_entry(entry)) {
> +			/*
> +			 * For device private entries, since there are no
> +			 * read exclusive entries, writable = !readable
> +			 */
> +			if (is_writable_device_private_entry(entry)) {
> +				entry = make_readable_device_private_entry(swp_offset(entry));
> +				pmd = swp_entry_to_pmd(entry);
> +
> +				if (pmd_swp_soft_dirty(*src_pmd))
> +					pmd = pmd_swp_mksoft_dirty(pmd);
> +				if (pmd_swp_uffd_wp(*src_pmd))
> +					pmd = pmd_swp_mkuffd_wp(pmd);
> +				set_pmd_at(src_mm, addr, src_pmd, pmd);
> +			}
> +
> +			src_folio = pfn_swap_entry_folio(entry);
> +			VM_WARN_ON(!folio_test_large(src_folio));
> +
> +			folio_get(src_folio);
> +			/*
> +			 * folio_try_dup_anon_rmap_pmd does not fail for
> +			 * device private entries.

Not today. But maybe wrapping this in WARN_ON_ONCE() might be nice in case that
ever changes.

> +			 */
> +			folio_try_dup_anon_rmap_pmd(src_folio, &src_folio->page,
> +							dst_vma, src_vma);
>  		}
> +
>  		add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
>  		mm_inc_nr_ptes(dst_mm);
>  		pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
> @@ -2211,15 +2239,16 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
>  			folio_remove_rmap_pmd(folio, page, vma);
>  			WARN_ON_ONCE(folio_mapcount(folio) < 0);
>  			VM_BUG_ON_PAGE(!PageHead(page), page);
> -		} else if (thp_migration_supported()) {
> +		} else if (is_pmd_non_present_folio_entry(orig_pmd)) {
>  			swp_entry_t entry;
>  
> -			VM_BUG_ON(!is_pmd_migration_entry(orig_pmd));
>  			entry = pmd_to_swp_entry(orig_pmd);
>  			folio = pfn_swap_entry_folio(entry);
>  			flush_needed = 0;
> -		} else
> -			WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!");
> +
> +			if (!thp_migration_supported())
> +				WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!");
> +		}
>  
>  		if (folio_test_anon(folio)) {
>  			zap_deposited_table(tlb->mm, pmd);
> @@ -2239,6 +2268,12 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
>  				folio_mark_accessed(folio);
>  		}
>  
> +		if (folio_is_device_private(folio)) {
> +			folio_remove_rmap_pmd(folio, &folio->page, vma);
> +			WARN_ON_ONCE(folio_mapcount(folio) < 0);
> +			folio_put(folio);
> +		}
> +
>  		spin_unlock(ptl);
>  		if (flush_needed)
>  			tlb_remove_page_size(tlb, &folio->page, HPAGE_PMD_SIZE);
> @@ -2367,7 +2402,7 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
>  		struct folio *folio = pfn_swap_entry_folio(entry);
>  		pmd_t newpmd;
>  
> -		VM_BUG_ON(!is_pmd_migration_entry(*pmd));
> +		VM_WARN_ON(!is_pmd_non_present_folio_entry(*pmd));
>  		if (is_writable_migration_entry(entry)) {
>  			/*
>  			 * A protection check is difficult so
> @@ -2380,6 +2415,9 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
>  			newpmd = swp_entry_to_pmd(entry);
>  			if (pmd_swp_soft_dirty(*pmd))
>  				newpmd = pmd_swp_mksoft_dirty(newpmd);
> +		} else if (is_writable_device_private_entry(entry)) {
> +			entry = make_readable_device_private_entry(swp_offset(entry));
> +			newpmd = swp_entry_to_pmd(entry);
>  		} else {
>  			newpmd = *pmd;
>  		}
> diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
> index 567e2d084071..0c847cdf4fd3 100644
> --- a/mm/pgtable-generic.c
> +++ b/mm/pgtable-generic.c
> @@ -290,7 +290,7 @@ pte_t *___pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp)
>  
>  	if (pmdvalp)
>  		*pmdvalp = pmdval;
> -	if (unlikely(pmd_none(pmdval) || is_pmd_migration_entry(pmdval)))
> +	if (unlikely(pmd_none(pmdval) || !pmd_present(pmdval)))

Why isn't is_pmd_non_present_folio_entry() used here?

>  		goto nomap;
>  	if (unlikely(pmd_trans_huge(pmdval)))
>  		goto nomap;
> -- 
> 2.50.1
>