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.

Cc: Karol Herbst <kherbst@redhat.com>
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: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Jane Chu <jane.chu@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Donet Tom <donettom@linux.ibm.com>

Signed-off-by: Balbir Singh <balbirs@nvidia.com>
---
 include/linux/memremap.h | 22 +++++++++++++++++-
 mm/memremap.c            | 50 +++++++++++++++++++++++++++++-----------
 2 files changed, 58 insertions(+), 14 deletions(-)

diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 4aa151914eab..11d586dd8ef1 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -169,6 +169,18 @@ static inline bool folio_is_device_private(const struct folio *folio)
 	return is_device_private_page(&folio->page);
 }
 
+static inline void *folio_zone_device_data(const struct folio *folio)
+{
+	VM_BUG_ON_FOLIO(!folio_is_device_private(folio), folio);
+	return folio->page.zone_device_data;
+}
+
+static inline void folio_set_zone_device_data(struct folio *folio, void *data)
+{
+	VM_BUG_ON_FOLIO(!folio_is_device_private(folio), folio);
+	folio->page.zone_device_data = data;
+}
+
 static inline bool is_pci_p2pdma_page(const struct page *page)
 {
 	return IS_ENABLED(CONFIG_PCI_P2PDMA) &&
@@ -199,7 +211,7 @@ static inline bool folio_is_fsdax(const struct folio *folio)
 }
 
 #ifdef CONFIG_ZONE_DEVICE
-void zone_device_page_init(struct page *page);
+void init_zone_device_folio(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);
@@ -209,6 +221,14 @@ 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);
+
+	init_zone_device_folio(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 b0ce0d8254bd..4085a3893e64 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -427,20 +427,21 @@ EXPORT_SYMBOL_GPL(get_dev_pagemap);
 void free_zone_device_folio(struct folio *folio)
 {
 	struct dev_pagemap *pgmap = folio->pgmap;
+	unsigned int nr = folio_nr_pages(folio);
+	int i;
+	bool anon = folio_test_anon(folio);
+	struct page *page = folio_page(folio, 0);
 
 	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));
+	WARN_ON_ONCE(folio_test_large(folio) && !anon);
+
+	for (i = 0; i < nr; i++) {
+		if (anon)
+			__ClearPageAnonExclusive(folio_page(folio, i));
 	}
 
 	/*
@@ -464,10 +465,19 @@ void free_zone_device_folio(struct folio *folio)
 
 	switch (pgmap->type) {
 	case MEMORY_DEVICE_PRIVATE:
+		if (folio_test_large(folio)) {
+			folio_unqueue_deferred_split(folio);
+
+			percpu_ref_put_many(&folio->pgmap->ref, nr - 1);
+		}
+		pgmap->ops->page_free(page);
+		put_dev_pagemap(pgmap);
+		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));
+		pgmap->ops->page_free(page);
 		put_dev_pagemap(pgmap);
 		break;
 
@@ -491,14 +501,28 @@ void free_zone_device_folio(struct folio *folio)
 	}
 }
 
-void zone_device_page_init(struct page *page)
+void init_zone_device_folio(struct folio *folio, unsigned int order)
 {
+	struct page *page = folio_page(folio, 0);
+
+	VM_BUG_ON(order > MAX_ORDER_NR_PAGES);
+
+	WARN_ON_ONCE(order && order != HPAGE_PMD_ORDER);
+
 	/*
 	 * 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);
+
+	/*
+	 * Only PMD level migration is supported for THP migration
+	 */
+	if (order > 1) {
+		prep_compound_page(page, order);
+		folio_set_large_rmappable(folio);
+	}
 }
-EXPORT_SYMBOL_GPL(zone_device_page_init);
+EXPORT_SYMBOL_GPL(init_zone_device_folio);
-- 
2.49.0

On Fri, Jul 04, 2025 at 09:35:00AM +1000, 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.
> 
> Cc: Karol Herbst <kherbst@redhat.com>
> 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: "Jérôme Glisse" <jglisse@redhat.com>
> Cc: Shuah Khan <shuah@kernel.org>
> Cc: David Hildenbrand <david@redhat.com>
> Cc: Barry Song <baohua@kernel.org>
> Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
> Cc: Ryan Roberts <ryan.roberts@arm.com>
> Cc: Matthew Wilcox <willy@infradead.org>
> Cc: Peter Xu <peterx@redhat.com>
> Cc: Zi Yan <ziy@nvidia.com>
> Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
> Cc: Jane Chu <jane.chu@oracle.com>
> Cc: Alistair Popple <apopple@nvidia.com>
> Cc: Donet Tom <donettom@linux.ibm.com>
> 
> Signed-off-by: Balbir Singh <balbirs@nvidia.com>
> ---
>  include/linux/memremap.h | 22 +++++++++++++++++-
>  mm/memremap.c            | 50 +++++++++++++++++++++++++++++-----------
>  2 files changed, 58 insertions(+), 14 deletions(-)
> 
> diff --git a/include/linux/memremap.h b/include/linux/memremap.h
> index 4aa151914eab..11d586dd8ef1 100644
> --- a/include/linux/memremap.h
> +++ b/include/linux/memremap.h
> @@ -169,6 +169,18 @@ static inline bool folio_is_device_private(const struct folio *folio)
>  	return is_device_private_page(&folio->page);
>  }
>  
> +static inline void *folio_zone_device_data(const struct folio *folio)
> +{
> +	VM_BUG_ON_FOLIO(!folio_is_device_private(folio), folio);
> +	return folio->page.zone_device_data;
> +}
> +
> +static inline void folio_set_zone_device_data(struct folio *folio, void *data)
> +{
> +	VM_BUG_ON_FOLIO(!folio_is_device_private(folio), folio);
> +	folio->page.zone_device_data = data;
> +}
> +
>  static inline bool is_pci_p2pdma_page(const struct page *page)
>  {
>  	return IS_ENABLED(CONFIG_PCI_P2PDMA) &&
> @@ -199,7 +211,7 @@ static inline bool folio_is_fsdax(const struct folio *folio)
>  }
>  
>  #ifdef CONFIG_ZONE_DEVICE
> -void zone_device_page_init(struct page *page);
> +void init_zone_device_folio(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);
> @@ -209,6 +221,14 @@ 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);
> +
> +	init_zone_device_folio(folio, 0);

Minor nit, but why not call this zone_device_folio_init() to keep the naming
consistent with zone_device_page_init()?

> +}
> +
>  #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 b0ce0d8254bd..4085a3893e64 100644
> --- a/mm/memremap.c
> +++ b/mm/memremap.c
> @@ -427,20 +427,21 @@ EXPORT_SYMBOL_GPL(get_dev_pagemap);
>  void free_zone_device_folio(struct folio *folio)
>  {
>  	struct dev_pagemap *pgmap = folio->pgmap;
> +	unsigned int nr = folio_nr_pages(folio);
> +	int i;
> +	bool anon = folio_test_anon(folio);
> +	struct page *page = folio_page(folio, 0);
>  
>  	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));
> +	WARN_ON_ONCE(folio_test_large(folio) && !anon);
> +
> +	for (i = 0; i < nr; i++) {

The above comment says we should do this for all tail pages, but this appears to
do it for the head page as well. Is there a particular reason for that?

> +		if (anon)
> +			__ClearPageAnonExclusive(folio_page(folio, i));
>  	}
>  
>  	/*
> @@ -464,10 +465,19 @@ void free_zone_device_folio(struct folio *folio)
>  
>  	switch (pgmap->type) {
>  	case MEMORY_DEVICE_PRIVATE:
> +		if (folio_test_large(folio)) {
> +			folio_unqueue_deferred_split(folio);
> +
> +			percpu_ref_put_many(&folio->pgmap->ref, nr - 1);
> +		}
> +		pgmap->ops->page_free(page);
> +		put_dev_pagemap(pgmap);

Why is this needed/added, and where is the associated get_dev_pagemap()? Note
that the whole {get|put}_dev_pagemap() thing is basically unused now. Which
reminds me I should send a patch to remove it.

> +		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));
> +		pgmap->ops->page_free(page);
>  		put_dev_pagemap(pgmap);
>  		break;
>  
> @@ -491,14 +501,28 @@ void free_zone_device_folio(struct folio *folio)
>  	}
>  }
>  
> -void zone_device_page_init(struct page *page)
> +void init_zone_device_folio(struct folio *folio, unsigned int order)

See above for some bike-shedding on the name.

>  {
> +	struct page *page = folio_page(folio, 0);
> +
> +	VM_BUG_ON(order > MAX_ORDER_NR_PAGES);
> +
> +	WARN_ON_ONCE(order && order != HPAGE_PMD_ORDER);
> +
>  	/*
>  	 * 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);
> +
> +	/*
> +	 * Only PMD level migration is supported for THP migration
> +	 */
> +	if (order > 1) {
> +		prep_compound_page(page, order);

Shouldn't this happen for order > 0 not 1? What about calling
INIT_LIST_HEAD(&folio->_deferred_list)? Last time I looked prep_compound_page()
didn't do that and I see above you are calling folio_unqueue_deferred_split() so
I assume you need to do this for DEVICE_PRIVATE pages too.

> +		folio_set_large_rmappable(folio);
> +	}
>  }
> -EXPORT_SYMBOL_GPL(zone_device_page_init);
> +EXPORT_SYMBOL_GPL(init_zone_device_folio);
> -- 
> 2.49.0
> 

On 7/7/25 15:28, Alistair Popple wrote:
> On Fri, Jul 04, 2025 at 09:35:00AM +1000, 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.
>>
>> Cc: Karol Herbst <kherbst@redhat.com>
>> 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: "Jérôme Glisse" <jglisse@redhat.com>
>> Cc: Shuah Khan <shuah@kernel.org>
>> Cc: David Hildenbrand <david@redhat.com>
>> Cc: Barry Song <baohua@kernel.org>
>> Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
>> Cc: Ryan Roberts <ryan.roberts@arm.com>
>> Cc: Matthew Wilcox <willy@infradead.org>
>> Cc: Peter Xu <peterx@redhat.com>
>> Cc: Zi Yan <ziy@nvidia.com>
>> Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
>> Cc: Jane Chu <jane.chu@oracle.com>
>> Cc: Alistair Popple <apopple@nvidia.com>
>> Cc: Donet Tom <donettom@linux.ibm.com>
>>
>> Signed-off-by: Balbir Singh <balbirs@nvidia.com>
>> ---
>>  include/linux/memremap.h | 22 +++++++++++++++++-
>>  mm/memremap.c            | 50 +++++++++++++++++++++++++++++-----------
>>  2 files changed, 58 insertions(+), 14 deletions(-)
>>
>> diff --git a/include/linux/memremap.h b/include/linux/memremap.h
>> index 4aa151914eab..11d586dd8ef1 100644
>> --- a/include/linux/memremap.h
>> +++ b/include/linux/memremap.h
>> @@ -169,6 +169,18 @@ static inline bool folio_is_device_private(const struct folio *folio)
>>  	return is_device_private_page(&folio->page);
>>  }
>>  
>> +static inline void *folio_zone_device_data(const struct folio *folio)
>> +{
>> +	VM_BUG_ON_FOLIO(!folio_is_device_private(folio), folio);
>> +	return folio->page.zone_device_data;
>> +}
>> +
>> +static inline void folio_set_zone_device_data(struct folio *folio, void *data)
>> +{
>> +	VM_BUG_ON_FOLIO(!folio_is_device_private(folio), folio);
>> +	folio->page.zone_device_data = data;
>> +}
>> +
>>  static inline bool is_pci_p2pdma_page(const struct page *page)
>>  {
>>  	return IS_ENABLED(CONFIG_PCI_P2PDMA) &&
>> @@ -199,7 +211,7 @@ static inline bool folio_is_fsdax(const struct folio *folio)
>>  }
>>  
>>  #ifdef CONFIG_ZONE_DEVICE
>> -void zone_device_page_init(struct page *page);
>> +void init_zone_device_folio(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);
>> @@ -209,6 +221,14 @@ 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);
>> +
>> +	init_zone_device_folio(folio, 0);
> 
> Minor nit, but why not call this zone_device_folio_init() to keep the naming
> consistent with zone_device_page_init()?
> 

Ack, will do!

>> +}
>> +
>>  #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 b0ce0d8254bd..4085a3893e64 100644
>> --- a/mm/memremap.c
>> +++ b/mm/memremap.c
>> @@ -427,20 +427,21 @@ EXPORT_SYMBOL_GPL(get_dev_pagemap);
>>  void free_zone_device_folio(struct folio *folio)
>>  {
>>  	struct dev_pagemap *pgmap = folio->pgmap;
>> +	unsigned int nr = folio_nr_pages(folio);
>> +	int i;
>> +	bool anon = folio_test_anon(folio);
>> +	struct page *page = folio_page(folio, 0);
>>  
>>  	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));
>> +	WARN_ON_ONCE(folio_test_large(folio) && !anon);
>> +
>> +	for (i = 0; i < nr; i++) {
> 
> The above comment says we should do this for all tail pages, but this appears to
> do it for the head page as well. Is there a particular reason for that?
> 

The original code clears the head page (when the folio is not large), the only
page. I don't think the head page can be skipped.

>> +		if (anon)
>> +			__ClearPageAnonExclusive(folio_page(folio, i));
>>  	}
>>  
>>  	/*
>> @@ -464,10 +465,19 @@ void free_zone_device_folio(struct folio *folio)
>>  
>>  	switch (pgmap->type) {
>>  	case MEMORY_DEVICE_PRIVATE:
>> +		if (folio_test_large(folio)) {
>> +			folio_unqueue_deferred_split(folio);
>> +
>> +			percpu_ref_put_many(&folio->pgmap->ref, nr - 1);
>> +		}
>> +		pgmap->ops->page_free(page);
>> +		put_dev_pagemap(pgmap);
> 
> Why is this needed/added, and where is the associated get_dev_pagemap()? Note
> that the whole {get|put}_dev_pagemap() thing is basically unused now. Which
> reminds me I should send a patch to remove it.
> 

Thanks, I'll remove these bits

>> +		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));
>> +		pgmap->ops->page_free(page);
>>  		put_dev_pagemap(pgmap);
>>  		break;
>>  
>> @@ -491,14 +501,28 @@ void free_zone_device_folio(struct folio *folio)
>>  	}
>>  }
>>  
>> -void zone_device_page_init(struct page *page)
>> +void init_zone_device_folio(struct folio *folio, unsigned int order)
> 
> See above for some bike-shedding on the name.
> 

Ack

>>  {
>> +	struct page *page = folio_page(folio, 0);
>> +
>> +	VM_BUG_ON(order > MAX_ORDER_NR_PAGES);
>> +
>> +	WARN_ON_ONCE(order && order != HPAGE_PMD_ORDER);
>> +
>>  	/*
>>  	 * 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);
>> +
>> +	/*
>> +	 * Only PMD level migration is supported for THP migration
>> +	 */
>> +	if (order > 1) {
>> +		prep_compound_page(page, order);
> 
> Shouldn't this happen for order > 0 not 1? What about calling
> INIT_LIST_HEAD(&folio->_deferred_list)? Last time I looked prep_compound_page()
> didn't do that and I see above you are calling folio_unqueue_deferred_split() so
> I assume you need to do this for DEVICE_PRIVATE pages too.
> 

order == 1 has no deferred_list. prep_compound_page handles the INIT_LIST_HEAD



>> +		folio_set_large_rmappable(folio);
>> +	}
>>  }
>> -EXPORT_SYMBOL_GPL(zone_device_page_init);
>> +EXPORT_SYMBOL_GPL(init_zone_device_folio);
>> -- 
>> 2.49.0
>>


Thanks for the review
Balbir