[RFC 01/11] mm/zone_device: support large zone device private folios

[David Hildenbrand]

On 06.03.25 05:42, 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.
> 
> Signed-off-by: Balbir Singh <balbirs at 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;
> +}

Not used.

> +
> +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;
> +}
> +

Not used.

Move both into the patch where they are actually used.

>   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 2aebc1b192da..7d98d0a4c0cd 100644
> --- a/mm/memremap.c
> +++ b/mm/memremap.c
> @@ -459,20 +459,21 @@ 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);

You can easily get rid of this (see below).

> +	struct page *page = folio_page(folio, 0);

Please inline folio_page(folio, 0) below instead.

>   
>   	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));
>   	}

if (folio_test_anon(folio)) {
	for (i = 0; i < nr; i++)
		__ClearPageAnonExclusive(folio_page(folio, i));
} else {
	VM_WARN_ON_ONCE(folio_test_large(folio));
}

>   
>   	/*
> @@ -496,10 +497,19 @@ 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);

Is deferred splitting even a thing for device-private?

Should we ever queue them for deferred splitting?

> +
> +			percpu_ref_put_many(&folio->pgmap->ref, nr - 1);

Looks like we instead want a helper put_dev_pagemap_refs(pgmap, nr) 
below instead

> +		}
> +		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;
>   
> @@ -523,14 +533,28 @@ 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);

VM_WARN_ON_ONCE() or anything else that is not *BUG, please.

> +
> +	WARN_ON_ONCE(order && order != HPAGE_PMD_ORDER);

Why do we need that limitation?

> +
>   	/*
>   	 * 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
> +	 */

I don't understand how that comment interacts with the code below. This 
is basic large folio initialization.

Drop the comment, or move it above the HPAGE_PMD_ORDER check with a 
clear reason why that limitation excists.

> +	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);


-- 
Cheers,

David / dhildenb