Re: [PATCH v1 2/8] mm/page_vma_mapped: Add flags to page_vma_mapped_walk::pfn to track device private pages

[Alistair Popple <apopple@nvidia.com>]

On 2025-12-31 at 15:31 +1100, Jordan Niethe <jniethe@nvidia.com> wrote...
> A future change will remove device private pages from the physical
> address space. This will mean that device private pages no longer have
> normal PFN and must be handled separately.
> 
> Prepare for this by modifying page_vma_mapped_walk::pfn to contain flags
> as well as a PFN. Introduce a PVMW_PFN_DEVICE_PRIVATE flag to indicate
> that a page_vma_mapped_walk::pfn contains a PFN for a device private
> page.
> 
> Signed-off-by: Jordan Niethe <jniethe@nvidia.com>
> Signed-off-by: Alistair Popple <apopple@nvidia.com>
> ---
> v1:
>   - Update for HMM huge page support
> ---
>  include/linux/rmap.h | 30 +++++++++++++++++++++++++++++-
>  mm/page_vma_mapped.c | 18 ++++++++++--------
>  mm/rmap.c            |  4 ++--
>  mm/vmscan.c          |  2 +-
>  4 files changed, 42 insertions(+), 12 deletions(-)
> 
> diff --git a/include/linux/rmap.h b/include/linux/rmap.h
> index daa92a58585d..57c63b6a8f65 100644
> --- a/include/linux/rmap.h
> +++ b/include/linux/rmap.h
> @@ -939,9 +939,37 @@ struct page_vma_mapped_walk {
>  	unsigned int flags;
>  };
>  
> +/* pfn is a device private offset */
> +#define PVMW_PFN_DEVICE_PRIVATE	(1UL << 0)
> +#define PVMW_PFN_SHIFT		1
> +
> +static inline unsigned long page_vma_walk_pfn(unsigned long pfn)
> +{
> +	return (pfn << PVMW_PFN_SHIFT);
> +}
> +
> +static inline unsigned long folio_page_vma_walk_pfn(const struct folio *folio)
> +{
> +	if (folio_is_device_private(folio))
> +		return page_vma_walk_pfn(folio_pfn(folio)) |
> +		       PVMW_PFN_DEVICE_PRIVATE;
> +
> +	return page_vma_walk_pfn(folio_pfn(folio));
> +}
> +
> +static inline struct page *page_vma_walk_pfn_to_page(unsigned long pvmw_pfn)
> +{
> +	return pfn_to_page(pvmw_pfn >> PVMW_PFN_SHIFT);
> +}
> +
> +static inline struct folio *page_vma_walk_pfn_to_folio(unsigned long pvmw_pfn)
> +{
> +	return page_folio(page_vma_walk_pfn_to_page(pvmw_pfn));
> +}
> +
>  #define DEFINE_FOLIO_VMA_WALK(name, _folio, _vma, _address, _flags)	\
>  	struct page_vma_mapped_walk name = {				\
> -		.pfn = folio_pfn(_folio),				\
> +		.pfn = folio_page_vma_walk_pfn(_folio),			\
>  		.nr_pages = folio_nr_pages(_folio),			\
>  		.pgoff = folio_pgoff(_folio),				\
>  		.vma = _vma,						\
> diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
> index b38a1d00c971..7fddafed3ebb 100644
> --- a/mm/page_vma_mapped.c
> +++ b/mm/page_vma_mapped.c
> @@ -129,19 +129,19 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw, unsigned long pte_nr)
>  		pfn = softleaf_to_pfn(entry);
>  	}
>  
> -	if ((pfn + pte_nr - 1) < pvmw->pfn)
> +	if ((pfn + pte_nr - 1) < (pvmw->pfn >> PVMW_PFN_SHIFT))
>  		return false;
> -	if (pfn > (pvmw->pfn + pvmw->nr_pages - 1))
> +	if (pfn > ((pvmw->pfn >> PVMW_PFN_SHIFT) + pvmw->nr_pages - 1))
>  		return false;
>  	return true;
>  }
>  
>  /* Returns true if the two ranges overlap.  Careful to not overflow. */
> -static bool check_pmd(unsigned long pfn, struct page_vma_mapped_walk *pvmw)
> +static bool check_pmd(unsigned long pfn, bool device_private, struct page_vma_mapped_walk *pvmw)

The device_private parameter isn't actually used until patch 8. Looks like you
should just move the usage here.

>  {
> -	if ((pfn + HPAGE_PMD_NR - 1) < pvmw->pfn)
> +	if ((pfn + HPAGE_PMD_NR - 1) < (pvmw->pfn >> PVMW_PFN_SHIFT))
>  		return false;
> -	if (pfn > pvmw->pfn + pvmw->nr_pages - 1)
> +	if (pfn > (pvmw->pfn >> PVMW_PFN_SHIFT) + pvmw->nr_pages - 1)
>  		return false;
>  	return true;
>  }
> @@ -254,14 +254,16 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
>  				entry = softleaf_from_pmd(pmde);
>  
>  				if (!softleaf_is_migration(entry) ||
> -				    !check_pmd(softleaf_to_pfn(entry), pvmw))
> +				    !check_pmd(softleaf_to_pfn(entry),
> +					       softleaf_is_device_private(entry),
> +					       pvmw))
>  					return not_found(pvmw);
>  				return true;
>  			}
>  			if (likely(pmd_trans_huge(pmde))) {
>  				if (pvmw->flags & PVMW_MIGRATION)
>  					return not_found(pvmw);
> -				if (!check_pmd(pmd_pfn(pmde), pvmw))
> +				if (!check_pmd(pmd_pfn(pmde), false, pvmw))
>  					return not_found(pvmw);
>  				return true;
>  			}
> @@ -350,7 +352,7 @@ unsigned long page_mapped_in_vma(const struct page *page,
>  {
>  	const struct folio *folio = page_folio(page);
>  	struct page_vma_mapped_walk pvmw = {
> -		.pfn = page_to_pfn(page),
> +		.pfn = folio_page_vma_walk_pfn(folio),
>  		.nr_pages = 1,
>  		.vma = vma,
>  		.flags = PVMW_SYNC,
> diff --git a/mm/rmap.c b/mm/rmap.c
> index f955f02d570e..79a2478b4aa9 100644
> --- a/mm/rmap.c
> +++ b/mm/rmap.c
> @@ -1112,7 +1112,7 @@ static bool mapping_wrprotect_range_one(struct folio *folio,
>  {
>  	struct wrprotect_file_state *state = (struct wrprotect_file_state *)arg;
>  	struct page_vma_mapped_walk pvmw = {
> -		.pfn		= state->pfn,
> +		.pfn		= page_vma_walk_pfn(state->pfn),
>  		.nr_pages	= state->nr_pages,
>  		.pgoff		= state->pgoff,
>  		.vma		= vma,
> @@ -1190,7 +1190,7 @@ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff,
>  		      struct vm_area_struct *vma)
>  {
>  	struct page_vma_mapped_walk pvmw = {
> -		.pfn		= pfn,
> +		.pfn		= page_vma_walk_pfn(pfn),
>  		.nr_pages	= nr_pages,
>  		.pgoff		= pgoff,
>  		.vma		= vma,
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 670fe9fae5ba..be5682d345b5 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -4203,7 +4203,7 @@ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
>  	pte_t *pte = pvmw->pte;
>  	unsigned long addr = pvmw->address;
>  	struct vm_area_struct *vma = pvmw->vma;
> -	struct folio *folio = pfn_folio(pvmw->pfn);
> +	struct folio *folio = page_vma_walk_pfn_to_folio(pvmw->pfn);
>  	struct mem_cgroup *memcg = folio_memcg(folio);
>  	struct pglist_data *pgdat = folio_pgdat(folio);
>  	struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
> -- 
> 2.34.1
>