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 4aa151914eab..a0723b35eeaa 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -199,7 +199,7 @@ static inline bool folio_is_fsdax(const struct folio *folio)
 }
 
 #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);
@@ -209,6 +209,14 @@ 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 b0ce0d8254bd..13e87dd743ad 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -427,20 +427,19 @@ 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));
 	}
 
 	/*
@@ -464,11 +463,15 @@ 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:
@@ -491,14 +494,23 @@ 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 568198e9efc2..b5837075b6e0 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

On 12.08.25 04:40, 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.

[...]


>   #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..13e87dd743ad 100644
> --- a/mm/memremap.c
> +++ b/mm/memremap.c
> @@ -427,20 +427,19 @@ 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;

Not that it will currently matter much but

unsigned long i, nr = folio_nr_pages(folio);

might be more consistent

>   
>   	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));
>   	}
>   
>   	/*
> @@ -464,11 +463,15 @@ void free_zone_device_folio(struct folio *folio)
>   
>   	switch (pgmap->type) {
>   	case MEMORY_DEVICE_PRIVATE:

Why are you effectively dropping the

if (WARN_ON_ONCE(!pgmap->ops || !pgmap->ops->page_free))

> +		percpu_ref_put_many(&folio->pgmap->ref, nr);
> +		pgmap->ops->page_free(&folio->page);


> +		folio->page.mapping = NULL;

Why are we adding this here? Does not seem large-folio specific.

> +		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);

This looks like an independent change that does not belong in this patch.


Can't you just leave the code as is and simply convert percpu_ref_put
to percpu_ref_put_many()? What am I missing?

>   		break;
>   
>   	case MEMORY_DEVICE_GENERIC:
> @@ -491,14 +494,23 @@ 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);

order vs. pages is wrong.

In context of [1] this should probably be

	VM_WARN_ON_ONCE(order > MAX_FOLIO_ORDER);

And before that is in

	VM_WARN_ON_ONCE((1u << order) > MAX_FOLIO_NR_PAGES);

because we don't involve the buddy, so likely buddy limits do not apply.

[1] https://lore.kernel.org/all/20250821200701.1329277-1-david@redhat.com/

> +
>   	/*
>   	 * 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 568198e9efc2..b5837075b6e0 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))

Please indent like the previous line.

if (partially_mapped && folio_test_anon(folio) &&
    !folio_test_partially_mapped(folio) &&
    !folio_is_device_private(folio))

>   		deferred_split_folio(folio, true);
>   
>   	__folio_mod_stat(folio, -nr, -nr_pmdmapped);


-- 
Cheers

David / dhildenb