Add routines to support allocation of large order zone device folios
and helper functions for zone device folios, to check if a folio is
device private and helpers for setting zone device data.

When large folios are used, the existing page_free() callback in
pgmap is called when the folio is freed, this is true for both
PAGE_SIZE and higher order pages.

Zone device private large folios do not support deferred split and
scan like normal THP folios.

Cc: Andrew Morton <akpm@linux-foundation.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>

Signed-off-by: Balbir Singh <balbirs@nvidia.com>
---
 include/linux/memremap.h | 10 +++++++++-
 mm/memremap.c            | 38 +++++++++++++++++++++++++-------------
 mm/rmap.c                |  6 +++++-
 3 files changed, 39 insertions(+), 15 deletions(-)

diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index e5951ba12a28..9c20327c2be5 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -206,7 +206,7 @@ static inline bool is_fsdax_page(const struct page *page)
 }
 
 #ifdef CONFIG_ZONE_DEVICE
-void zone_device_page_init(struct page *page);
+void zone_device_folio_init(struct folio *folio, unsigned int order);
 void *memremap_pages(struct dev_pagemap *pgmap, int nid);
 void memunmap_pages(struct dev_pagemap *pgmap);
 void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap);
@@ -215,6 +215,14 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn);
 bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn);
 
 unsigned long memremap_compat_align(void);
+
+static inline void zone_device_page_init(struct page *page)
+{
+	struct folio *folio = page_folio(page);
+
+	zone_device_folio_init(folio, 0);
+}
+
 #else
 static inline void *devm_memremap_pages(struct device *dev,
 		struct dev_pagemap *pgmap)
diff --git a/mm/memremap.c b/mm/memremap.c
index 46cb1b0b6f72..66f9186b5500 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -416,20 +416,19 @@ EXPORT_SYMBOL_GPL(get_dev_pagemap);
 void free_zone_device_folio(struct folio *folio)
 {
 	struct dev_pagemap *pgmap = folio->pgmap;
+	unsigned long nr = folio_nr_pages(folio);
+	int i;
 
 	if (WARN_ON_ONCE(!pgmap))
 		return;
 
 	mem_cgroup_uncharge(folio);
 
-	/*
-	 * Note: we don't expect anonymous compound pages yet. Once supported
-	 * and we could PTE-map them similar to THP, we'd have to clear
-	 * PG_anon_exclusive on all tail pages.
-	 */
 	if (folio_test_anon(folio)) {
-		VM_BUG_ON_FOLIO(folio_test_large(folio), folio);
-		__ClearPageAnonExclusive(folio_page(folio, 0));
+		for (i = 0; i < nr; i++)
+			__ClearPageAnonExclusive(folio_page(folio, i));
+	} else {
+		VM_WARN_ON_ONCE(folio_test_large(folio));
 	}
 
 	/*
@@ -453,11 +452,15 @@ void free_zone_device_folio(struct folio *folio)
 
 	switch (pgmap->type) {
 	case MEMORY_DEVICE_PRIVATE:
+		percpu_ref_put_many(&folio->pgmap->ref, nr);
+		pgmap->ops->page_free(&folio->page);
+		folio->page.mapping = NULL;
+		break;
 	case MEMORY_DEVICE_COHERENT:
 		if (WARN_ON_ONCE(!pgmap->ops || !pgmap->ops->page_free))
 			break;
-		pgmap->ops->page_free(folio_page(folio, 0));
-		put_dev_pagemap(pgmap);
+		pgmap->ops->page_free(&folio->page);
+		percpu_ref_put(&folio->pgmap->ref);
 		break;
 
 	case MEMORY_DEVICE_GENERIC:
@@ -480,14 +483,23 @@ void free_zone_device_folio(struct folio *folio)
 	}
 }
 
-void zone_device_page_init(struct page *page)
+void zone_device_folio_init(struct folio *folio, unsigned int order)
 {
+	struct page *page = folio_page(folio, 0);
+
+	VM_WARN_ON_ONCE(order > MAX_ORDER_NR_PAGES);
+
 	/*
 	 * Drivers shouldn't be allocating pages after calling
 	 * memunmap_pages().
 	 */
-	WARN_ON_ONCE(!percpu_ref_tryget_live(&page_pgmap(page)->ref));
-	set_page_count(page, 1);
+	WARN_ON_ONCE(!percpu_ref_tryget_many(&page_pgmap(page)->ref, 1 << order));
+	folio_set_count(folio, 1);
 	lock_page(page);
+
+	if (order > 1) {
+		prep_compound_page(page, order);
+		folio_set_large_rmappable(folio);
+	}
 }
-EXPORT_SYMBOL_GPL(zone_device_page_init);
+EXPORT_SYMBOL_GPL(zone_device_folio_init);
diff --git a/mm/rmap.c b/mm/rmap.c
index 34333ae3bd80..236ceff5b276 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1769,9 +1769,13 @@ static __always_inline void __folio_remove_rmap(struct folio *folio,
 	 * the folio is unmapped and at least one page is still mapped.
 	 *
 	 * Check partially_mapped first to ensure it is a large folio.
+	 *
+	 * Device private folios do not support deferred splitting and
+	 * shrinker based scanning of the folios to free.
 	 */
 	if (partially_mapped && folio_test_anon(folio) &&
-	    !folio_test_partially_mapped(folio))
+	    !folio_test_partially_mapped(folio) &&
+		!folio_is_device_private(folio))
 		deferred_split_folio(folio, true);
 
 	__folio_mod_stat(folio, -nr, -nr_pmdmapped);
-- 
2.50.1

[ apologies for resending this, debugging sendmail ]

Hi Balbir,

On Mon,  8 Sep 2025 10:04:34 +1000 Balbir Singh <balbirs@nvidia.com> wrote:
> Add routines to support allocation of large order zone device folios
> and helper functions for zone device folios, to check if a folio is
> device private and helpers for setting zone device data.
> 
> When large folios are used, the existing page_free() callback in
> pgmap is called when the folio is freed, this is true for both
> PAGE_SIZE and higher order pages.
> 
> Zone device private large folios do not support deferred split and
> scan like normal THP folios.

[ ... ]

> diff --git a/mm/memremap.c b/mm/memremap.c
> index 46cb1b0b6f72..66f9186b5500 100644
> --- a/mm/memremap.c
> +++ b/mm/memremap.c
> @@ -453,11 +452,15 @@ void free_zone_device_folio(struct folio *folio)
>  
>  	switch (pgmap->type) {
>  	case MEMORY_DEVICE_PRIVATE:
> +		percpu_ref_put_many(&folio->pgmap->ref, nr);

Here we're dropping nr refs

> +		pgmap->ops->page_free(&folio->page);
> +		folio->page.mapping = NULL;
> +		break;
>  	case MEMORY_DEVICE_COHERENT:
>  		if (WARN_ON_ONCE(!pgmap->ops || !pgmap->ops->page_free))
>  			break;
> -		pgmap->ops->page_free(folio_page(folio, 0));
> -		put_dev_pagemap(pgmap);
> +		pgmap->ops->page_free(&folio->page);
> +		percpu_ref_put(&folio->pgmap->ref);

Here we're dropping one ref?

>  		break;
>  
>  	case MEMORY_DEVICE_GENERIC:
> @@ -480,14 +483,23 @@ void free_zone_device_folio(struct folio *folio)
>  	}
>  }
>  
> -void zone_device_page_init(struct page *page)
> +void zone_device_folio_init(struct folio *folio, unsigned int order)
>  {
> +	struct page *page = folio_page(folio, 0);
> +
> +	VM_WARN_ON_ONCE(order > MAX_ORDER_NR_PAGES);
> +
>  	/*
>  	 * Drivers shouldn't be allocating pages after calling
>  	 * memunmap_pages().
>  	 */
> -	WARN_ON_ONCE(!percpu_ref_tryget_live(&page_pgmap(page)->ref));
> -	set_page_count(page, 1);
> +	WARN_ON_ONCE(!percpu_ref_tryget_many(&page_pgmap(page)->ref, 1 << order));

Here we always bump by 1 << order

I hesitate to send this one because I don't know the code at all, but the
AI review prompts keep flagging this apparent refcount mismatch, and it looks
real to me.

Are the differences in refcount handling inside free_zone_device_folio()
intentional?

-chris

On 9/18/25 22:27, Chris Mason wrote:
> 
> [ apologies for resending this, debugging sendmail ]
> 
> Hi Balbir,
> 
> On Mon,  8 Sep 2025 10:04:34 +1000 Balbir Singh <balbirs@nvidia.com> wrote:
>> Add routines to support allocation of large order zone device folios
>> and helper functions for zone device folios, to check if a folio is
>> device private and helpers for setting zone device data.
>>
>> When large folios are used, the existing page_free() callback in
>> pgmap is called when the folio is freed, this is true for both
>> PAGE_SIZE and higher order pages.
>>
>> Zone device private large folios do not support deferred split and
>> scan like normal THP folios.
> 
> [ ... ]
> 
>> diff --git a/mm/memremap.c b/mm/memremap.c
>> index 46cb1b0b6f72..66f9186b5500 100644
>> --- a/mm/memremap.c
>> +++ b/mm/memremap.c
>> @@ -453,11 +452,15 @@ void free_zone_device_folio(struct folio *folio)
>>  
>>  	switch (pgmap->type) {
>>  	case MEMORY_DEVICE_PRIVATE:
>> +		percpu_ref_put_many(&folio->pgmap->ref, nr);
> 
> Here we're dropping nr refs
> 
>> +		pgmap->ops->page_free(&folio->page);
>> +		folio->page.mapping = NULL;
>> +		break;
>>  	case MEMORY_DEVICE_COHERENT:
>>  		if (WARN_ON_ONCE(!pgmap->ops || !pgmap->ops->page_free))
>>  			break;
>> -		pgmap->ops->page_free(folio_page(folio, 0));
>> -		put_dev_pagemap(pgmap);
>> +		pgmap->ops->page_free(&folio->page);
>> +		percpu_ref_put(&folio->pgmap->ref);
> 
> Here we're dropping one ref?
> 
>>  		break;
>>  
>>  	case MEMORY_DEVICE_GENERIC:
>> @@ -480,14 +483,23 @@ void free_zone_device_folio(struct folio *folio)
>>  	}
>>  }
>>  
>> -void zone_device_page_init(struct page *page)
>> +void zone_device_folio_init(struct folio *folio, unsigned int order)
>>  {
>> +	struct page *page = folio_page(folio, 0);
>> +
>> +	VM_WARN_ON_ONCE(order > MAX_ORDER_NR_PAGES);
>> +
>>  	/*
>>  	 * Drivers shouldn't be allocating pages after calling
>>  	 * memunmap_pages().
>>  	 */
>> -	WARN_ON_ONCE(!percpu_ref_tryget_live(&page_pgmap(page)->ref));
>> -	set_page_count(page, 1);
>> +	WARN_ON_ONCE(!percpu_ref_tryget_many(&page_pgmap(page)->ref, 1 << order));
> 
> Here we always bump by 1 << order
> 
> I hesitate to send this one because I don't know the code at all, but the
> AI review prompts keep flagging this apparent refcount mismatch, and it looks
> real to me.
> 
> Are the differences in refcount handling inside free_zone_device_folio()
> intentional?
> 

Thanks for the review! I've posted a v6, but in general

1. Large folios for supported for device-private pages, hence the nr (from folio_order)
2. The user of the folios specifies the order (for mTHP), a folio gets get created
   with that order
3. What you are seeing with the percpu_ref_put for two different cases
   MEMORY_DEVICE_COHERENT and MEMORY_DEVICE_PRIVATE

The reason I point you to v6, is that the diff is a little bit different there

Balbir

On 08.09.25 02:04, Balbir Singh wrote:
> Add routines to support allocation of large order zone device folios
> and helper functions for zone device folios, to check if a folio is
> device private and helpers for setting zone device data.
> 
> When large folios are used, the existing page_free() callback in
> pgmap is called when the folio is freed, this is true for both
> PAGE_SIZE and higher order pages.
> 
> Zone device private large folios do not support deferred split and
> scan like normal THP folios.
> 
> Cc: Andrew Morton <akpm@linux-foundation.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>
> 
> Signed-off-by: Balbir Singh <balbirs@nvidia.com>
> ---

You missed my comments of this patch in v3.

-- 
Cheers

David / dhildenb

On 9/11/25 21:45, David Hildenbrand wrote:
> On 08.09.25 02:04, Balbir Singh wrote:
>> Add routines to support allocation of large order zone device folios
>> and helper functions for zone device folios, to check if a folio is
>> device private and helpers for setting zone device data.
>>
>> When large folios are used, the existing page_free() callback in
>> pgmap is called when the folio is freed, this is true for both
>> PAGE_SIZE and higher order pages.
>>
>> Zone device private large folios do not support deferred split and
>> scan like normal THP folios.
>>
>> Cc: Andrew Morton <akpm@linux-foundation.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>
>>
>> Signed-off-by: Balbir Singh <balbirs@nvidia.com>
>> ---
> 
> You missed my comments of this patch in v3.
> 

Hi, David

Looks I missed your comments, just checked those were largely about alignment and
integrating the code for DEVICE_COHERENT and DEVICE_PRIVATE cases into similar looking
bits for zone device folio free and code-alignment. I'll take a look and update as needed.

Balbir Singh

On 11.09.25 14:49, Balbir Singh wrote:
> On 9/11/25 21:45, David Hildenbrand wrote:
>> On 08.09.25 02:04, Balbir Singh wrote:
>>> Add routines to support allocation of large order zone device folios
>>> and helper functions for zone device folios, to check if a folio is
>>> device private and helpers for setting zone device data.
>>>
>>> When large folios are used, the existing page_free() callback in
>>> pgmap is called when the folio is freed, this is true for both
>>> PAGE_SIZE and higher order pages.
>>>
>>> Zone device private large folios do not support deferred split and
>>> scan like normal THP folios.
>>>
>>> Cc: Andrew Morton <akpm@linux-foundation.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>
>>>
>>> Signed-off-by: Balbir Singh <balbirs@nvidia.com>
>>> ---
>>
>> You missed my comments of this patch in v3.
>>
> 
> Hi, David
> 
> Looks I missed your comments, just checked those were largely about alignment and
> integrating the code for DEVICE_COHERENT and DEVICE_PRIVATE cases into similar looking
> bits for zone device folio free and code-alignment. I'll take a look and update as needed.

Yes, and the confusing folio->mapping = NULL that I cannot connect to 
THP support.

-- 
Cheers

David / dhildenb

On 9/11/25 22:52, David Hildenbrand wrote:
> On 11.09.25 14:49, Balbir Singh wrote:
>> On 9/11/25 21:45, David Hildenbrand wrote:
>>> On 08.09.25 02:04, Balbir Singh wrote:
>>>> Add routines to support allocation of large order zone device folios
>>>> and helper functions for zone device folios, to check if a folio is
>>>> device private and helpers for setting zone device data.
>>>>
>>>> When large folios are used, the existing page_free() callback in
>>>> pgmap is called when the folio is freed, this is true for both
>>>> PAGE_SIZE and higher order pages.
>>>>
>>>> Zone device private large folios do not support deferred split and
>>>> scan like normal THP folios.
>>>>
>>>> Cc: Andrew Morton <akpm@linux-foundation.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>
>>>>
>>>> Signed-off-by: Balbir Singh <balbirs@nvidia.com>
>>>> ---
>>>
>>> You missed my comments of this patch in v3.
>>>
>>
>> Hi, David
>>
>> Looks I missed your comments, just checked those were largely about alignment and
>> integrating the code for DEVICE_COHERENT and DEVICE_PRIVATE cases into similar looking
>> bits for zone device folio free and code-alignment. I'll take a look and update as needed.
> 
> Yes, and the confusing folio->mapping = NULL that I cannot connect to THP support.
> 

I can remove that, let me reunify those bits, seems relatively straight forward

Balbir

On 12.09.25 06:49, Balbir Singh wrote:
> On 9/11/25 22:52, David Hildenbrand wrote:
>> On 11.09.25 14:49, Balbir Singh wrote:
>>> On 9/11/25 21:45, David Hildenbrand wrote:
>>>> On 08.09.25 02:04, Balbir Singh wrote:
>>>>> Add routines to support allocation of large order zone device folios
>>>>> and helper functions for zone device folios, to check if a folio is
>>>>> device private and helpers for setting zone device data.
>>>>>
>>>>> When large folios are used, the existing page_free() callback in
>>>>> pgmap is called when the folio is freed, this is true for both
>>>>> PAGE_SIZE and higher order pages.
>>>>>
>>>>> Zone device private large folios do not support deferred split and
>>>>> scan like normal THP folios.
>>>>>
>>>>> Cc: Andrew Morton <akpm@linux-foundation.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>
>>>>>
>>>>> Signed-off-by: Balbir Singh <balbirs@nvidia.com>
>>>>> ---
>>>>
>>>> You missed my comments of this patch in v3.
>>>>
>>>
>>> Hi, David
>>>
>>> Looks I missed your comments, just checked those were largely about alignment and
>>> integrating the code for DEVICE_COHERENT and DEVICE_PRIVATE cases into similar looking
>>> bits for zone device folio free and code-alignment. I'll take a look and update as needed.
>>
>> Yes, and the confusing folio->mapping = NULL that I cannot connect to THP support.
>>
> 
> I can remove that, let me reunify those bits, seems relatively straight forward

BTW, I was wondering when we invalidate folio_test_anon() by clearing 
folio->mapping int he current code flow?

I mean, this must happen at some point when freeing device folios.

-- 
Cheers

David / dhildenb

On 9/12/25 19:20, David Hildenbrand wrote:
> On 12.09.25 06:49, Balbir Singh wrote:
>> On 9/11/25 22:52, David Hildenbrand wrote:
>>> On 11.09.25 14:49, Balbir Singh wrote:
>>>> On 9/11/25 21:45, David Hildenbrand wrote:
>>>>> On 08.09.25 02:04, Balbir Singh wrote:
>>>>>> Add routines to support allocation of large order zone device folios
>>>>>> and helper functions for zone device folios, to check if a folio is
>>>>>> device private and helpers for setting zone device data.
>>>>>>
>>>>>> When large folios are used, the existing page_free() callback in
>>>>>> pgmap is called when the folio is freed, this is true for both
>>>>>> PAGE_SIZE and higher order pages.
>>>>>>
>>>>>> Zone device private large folios do not support deferred split and
>>>>>> scan like normal THP folios.
>>>>>>
>>>>>> Cc: Andrew Morton <akpm@linux-foundation.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>
>>>>>>
>>>>>> Signed-off-by: Balbir Singh <balbirs@nvidia.com>
>>>>>> ---
>>>>>
>>>>> You missed my comments of this patch in v3.
>>>>>
>>>>
>>>> Hi, David
>>>>
>>>> Looks I missed your comments, just checked those were largely about alignment and
>>>> integrating the code for DEVICE_COHERENT and DEVICE_PRIVATE cases into similar looking
>>>> bits for zone device folio free and code-alignment. I'll take a look and update as needed.
>>>
>>> Yes, and the confusing folio->mapping = NULL that I cannot connect to THP support.
>>>
>>
>> I can remove that, let me reunify those bits, seems relatively straight forward
> 
> BTW, I was wondering when we invalidate folio_test_anon() by clearing folio->mapping int he current code flow?
> 
> I mean, this must happen at some point when freeing device folios.
> 

The free_zone_device_folio() code does that. Lines 434 onwards there is a comment that explains it

Balbir

On 13.09.25 01:14, Balbir Singh wrote:
> On 9/12/25 19:20, David Hildenbrand wrote:
>> On 12.09.25 06:49, Balbir Singh wrote:
>>> On 9/11/25 22:52, David Hildenbrand wrote:
>>>> On 11.09.25 14:49, Balbir Singh wrote:
>>>>> On 9/11/25 21:45, David Hildenbrand wrote:
>>>>>> On 08.09.25 02:04, Balbir Singh wrote:
>>>>>>> Add routines to support allocation of large order zone device folios
>>>>>>> and helper functions for zone device folios, to check if a folio is
>>>>>>> device private and helpers for setting zone device data.
>>>>>>>
>>>>>>> When large folios are used, the existing page_free() callback in
>>>>>>> pgmap is called when the folio is freed, this is true for both
>>>>>>> PAGE_SIZE and higher order pages.
>>>>>>>
>>>>>>> Zone device private large folios do not support deferred split and
>>>>>>> scan like normal THP folios.
>>>>>>>
>>>>>>> Cc: Andrew Morton <akpm@linux-foundation.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>
>>>>>>>
>>>>>>> Signed-off-by: Balbir Singh <balbirs@nvidia.com>
>>>>>>> ---
>>>>>>
>>>>>> You missed my comments of this patch in v3.
>>>>>>
>>>>>
>>>>> Hi, David
>>>>>
>>>>> Looks I missed your comments, just checked those were largely about alignment and
>>>>> integrating the code for DEVICE_COHERENT and DEVICE_PRIVATE cases into similar looking
>>>>> bits for zone device folio free and code-alignment. I'll take a look and update as needed.
>>>>
>>>> Yes, and the confusing folio->mapping = NULL that I cannot connect to THP support.
>>>>
>>>
>>> I can remove that, let me reunify those bits, seems relatively straight forward
>>
>> BTW, I was wondering when we invalidate folio_test_anon() by clearing folio->mapping int he current code flow?
>>
>> I mean, this must happen at some point when freeing device folios.
>>
> 
> The free_zone_device_folio() code does that. Lines 434 onwards there is a comment that explains it

Ah okay. So it's not required at all in your case because 
MEMORY_DEVICE_PRIVATE is handled through

	if (pgmap->type != MEMORY_DEVICE_FS_DAX &&
	    pgmap->type != MEMORY_DEVICE_GENERIC)
		folio->mapping = NULL;


You using "folio->page.mapping" instead of "folio->mapping" added a bit 
more confusion :)

-- 
Cheers

David / dhildenb