Re: [v6 03/15] mm/rmap: extend rmap and migration support device-private entries

[Balbir Singh <balbirs@nvidia.com>]

On 9/23/25 06:13, Zi Yan wrote:
> On 16 Sep 2025, at 8:21, Balbir Singh wrote:
> 
>> Add device-private THP support to reverse mapping infrastructure, enabling
>> proper handling during migration and walk operations.
>>
>> The key changes are:
>> - add_migration_pmd()/remove_migration_pmd(): Handle device-private
>>   entries during folio migration and splitting
>> - page_vma_mapped_walk(): Recognize device-private THP entries during
>>   VMA traversal operations
>>
>> This change supports folio splitting and migration operations on
>> device-private entries.
>>
>> Signed-off-by: Balbir Singh <balbirs@nvidia.com>
>> Reviewed-by: SeongJae Park <sj@kernel.org>
>> 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>
>> ---
>>  mm/damon/ops-common.c | 20 +++++++++++++++++---
>>  mm/huge_memory.c      | 16 +++++++++++++++-
>>  mm/page_idle.c        |  7 +++++--
>>  mm/page_vma_mapped.c  |  7 +++++++
>>  mm/rmap.c             | 21 +++++++++++++++++----
>>  5 files changed, 61 insertions(+), 10 deletions(-)
>>
>> diff --git a/mm/damon/ops-common.c b/mm/damon/ops-common.c
>> index 998c5180a603..eda4de553611 100644
>> --- a/mm/damon/ops-common.c
>> +++ b/mm/damon/ops-common.c
>> @@ -75,12 +75,24 @@ void damon_ptep_mkold(pte_t *pte, struct vm_area_struct *vma, unsigned long addr
>>  void damon_pmdp_mkold(pmd_t *pmd, struct vm_area_struct *vma, unsigned long addr)
>>  {
>>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>> -	struct folio *folio = damon_get_folio(pmd_pfn(pmdp_get(pmd)));
>> +	pmd_t pmdval = pmdp_get(pmd);
>> +	struct folio *folio;
>> +	bool young = false;
>> +	unsigned long pfn;
>> +
>> +	if (likely(pmd_present(pmdval)))
>> +		pfn = pmd_pfn(pmdval);
>> +	else
>> +		pfn = swp_offset_pfn(pmd_to_swp_entry(pmdval));
>>
>> +	folio = damon_get_folio(pfn);
>>  	if (!folio)
>>  		return;
>>
>> -	if (pmdp_clear_young_notify(vma, addr, pmd))
>> +	if (likely(pmd_present(pmdval)))
>> +		young |= pmdp_clear_young_notify(vma, addr, pmd);
>> +	young |= mmu_notifier_clear_young(vma->vm_mm, addr, addr + PAGE_SIZE);
> 
> This should be HPAGE_PMD_SIZE (it is guarded in CONFIG_TRANSPARENT_HUGEPAGE,
> so HPAGE_PMD_SIZE will not trigger a build bug like the one below).
> 
>> +	if (young)
>>  		folio_set_young(folio);
>>
>>  	folio_set_idle(folio);
>> @@ -203,7 +215,9 @@ static bool damon_folio_young_one(struct folio *folio,
>>  				mmu_notifier_test_young(vma->vm_mm, addr);
>>  		} else {
>>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>> -			*accessed = pmd_young(pmdp_get(pvmw.pmd)) ||
>> +			pmd_t pmd = pmdp_get(pvmw.pmd);
>> +
>> +			*accessed = (pmd_present(pmd) && pmd_young(pmd)) ||
>>  				!folio_test_idle(folio) ||
>>  				mmu_notifier_test_young(vma->vm_mm, addr);
>>  #else
>> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
>> index a5e4c2aef191..78166db72f4d 100644
>> --- a/mm/huge_memory.c
>> +++ b/mm/huge_memory.c
>> @@ -4637,7 +4637,10 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
>>  		return 0;
>>
>>  	flush_cache_range(vma, address, address + HPAGE_PMD_SIZE);
>> -	pmdval = pmdp_invalidate(vma, address, pvmw->pmd);
>> +	if (unlikely(!pmd_present(*pvmw->pmd)))
>> +		pmdval = pmdp_huge_get_and_clear(vma->vm_mm, address, pvmw->pmd);
>> +	else
>> +		pmdval = pmdp_invalidate(vma, address, pvmw->pmd);
>>
>>  	/* See folio_try_share_anon_rmap_pmd(): invalidate PMD first. */
>>  	anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(page);
>> @@ -4687,6 +4690,17 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
>>  	entry = pmd_to_swp_entry(*pvmw->pmd);
>>  	folio_get(folio);
>>  	pmde = folio_mk_pmd(folio, READ_ONCE(vma->vm_page_prot));
>> +
>> +	if (folio_is_device_private(folio)) {
>> +		if (pmd_write(pmde))
>> +			entry = make_writable_device_private_entry(
>> +							page_to_pfn(new));
>> +		else
>> +			entry = make_readable_device_private_entry(
>> +							page_to_pfn(new));
>> +		pmde = swp_entry_to_pmd(entry);
>> +	}
>> +
>>  	if (pmd_swp_soft_dirty(*pvmw->pmd))
>>  		pmde = pmd_mksoft_dirty(pmde);
>>  	if (is_writable_migration_entry(entry))
>> diff --git a/mm/page_idle.c b/mm/page_idle.c
>> index a82b340dc204..3bf0fbe05cc2 100644
>> --- a/mm/page_idle.c
>> +++ b/mm/page_idle.c
>> @@ -71,8 +71,11 @@ static bool page_idle_clear_pte_refs_one(struct folio *folio,
>>  				referenced |= ptep_test_and_clear_young(vma, addr, pvmw.pte);
>>  			referenced |= mmu_notifier_clear_young(vma->vm_mm, addr, addr + PAGE_SIZE);
>>  		} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
>> -			if (pmdp_clear_young_notify(vma, addr, pvmw.pmd))
>> -				referenced = true;
>> +			pmd_t pmdval = pmdp_get(pvmw.pmd);
>> +
>> +			if (likely(pmd_present(pmdval)))
>> +				referenced |= pmdp_clear_young_notify(vma, addr, pvmw.pmd);
>> +			referenced |= mmu_notifier_clear_young(vma->vm_mm, addr, addr + PAGE_SIZE);
> 
> This should be HPAGE_PMD_SIZE (or PMD_SIZE, since the code is not compiled
> out when CONFIG_TRANSPARENT_HUGEPAGE is not selected and HPAGE_PMD_SIZE
> will cause a build bug when CONFIG_PGTABLE_HAS_HUGE_LEAVES is not selected).

I'll protect it accordingly, thanks!

> 
>>  		} else {
>>  			/* unexpected pmd-mapped page? */
>>  			WARN_ON_ONCE(1);
>> diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
>> index e981a1a292d2..159953c590cc 100644
>> --- a/mm/page_vma_mapped.c
>> +++ b/mm/page_vma_mapped.c
>> @@ -277,6 +277,13 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
>>  			 * cannot return prematurely, while zap_huge_pmd() has
>>  			 * cleared *pmd but not decremented compound_mapcount().
>>  			 */
>> +			swp_entry_t entry = pmd_to_swp_entry(pmde);
>> +
>> +			if (is_device_private_entry(entry)) {
>> +				pvmw->ptl = pmd_lock(mm, pvmw->pmd);
>> +				return true;
>> +			}
>> +
>>  			if ((pvmw->flags & PVMW_SYNC) &&
>>  			    thp_vma_suitable_order(vma, pvmw->address,
>>  						   PMD_ORDER) &&
>> diff --git a/mm/rmap.c b/mm/rmap.c
>> index 9a2aabfaea6f..080fc4048431 100644
>> --- a/mm/rmap.c
>> +++ b/mm/rmap.c
>> @@ -1063,9 +1063,11 @@ static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw)
>>  		} else {
>>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>>  			pmd_t *pmd = pvmw->pmd;
>> -			pmd_t entry;
>> +			pmd_t entry = pmdp_get(pmd);
>>
>> -			if (!pmd_dirty(*pmd) && !pmd_write(*pmd))
> 
> It is better to add a similar comment as the one above !pte_present().
> Something like:
> PFN swap PMDs, such as ...
> 
> 

Sure, can do and repeat the comment or just say look at the comments for !pte_present() :)

>> +			if (!pmd_present(entry))
>> +				continue;
>> +			if (!pmd_dirty(entry) && !pmd_write(entry))
>>  				continue;
>>
>>  			flush_cache_range(vma, address,
>> @@ -2330,6 +2332,11 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
>>  	while (page_vma_mapped_walk(&pvmw)) {
>>  		/* PMD-mapped THP migration entry */
>>  		if (!pvmw.pte) {
>> +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
>> +			unsigned long pfn;
>> +			pmd_t pmdval;
>> +#endif
>> +
> 
> This looks ugly. IIRC, we now can put variable definition in the middle.
> Maybe for this case, these two can be moved to the below ifdef region.
> 

I can't find any examples of mixing declarations and could not find any clear
guidance in the coding style

>>  			if (flags & TTU_SPLIT_HUGE_PMD) {
>>  				split_huge_pmd_locked(vma, pvmw.address,
>>  						      pvmw.pmd, true);
>> @@ -2338,8 +2345,14 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
>>  				break;
>>  			}
>>  #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
>> -			subpage = folio_page(folio,
>> -				pmd_pfn(*pvmw.pmd) - folio_pfn(folio));
>> +			pmdval = pmdp_get(pvmw.pmd);
>> +			if (likely(pmd_present(pmdval)))
>> +				pfn = pmd_pfn(pmdval);
>> +			else
>> +				pfn = swp_offset_pfn(pmd_to_swp_entry(pmdval));
>> +
>> +			subpage = folio_page(folio, pfn - folio_pfn(folio));
>> +
>>  			VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) ||
>>  					!folio_test_pmd_mappable(folio), folio);
>>
>> -- 
>> 2.50.1
> 
> Otherwise, LGTM. Acked-by: Zi Yan <ziy@nvidia.com>

Thanks for the review,
Balbir