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 <a...@linux-foundation.org>
Cc: David Hildenbrand <da...@redhat.com>
Cc: Zi Yan <z...@nvidia.com>
Cc: Joshua Hahn <joshua.hah...@gmail.com>
Cc: Rakie Kim <rakie....@sk.com>
Cc: Byungchul Park <byungc...@sk.com>
Cc: Gregory Price <gou...@gourry.net>
Cc: Ying Huang <ying.hu...@linux.alibaba.com>
Cc: Alistair Popple <apop...@nvidia.com>
Cc: Oscar Salvador <osalva...@suse.de>
Cc: Lorenzo Stoakes <lorenzo.stoa...@oracle.com>
Cc: Baolin Wang <baolin.w...@linux.alibaba.com>
Cc: "Liam R. Howlett" <liam.howl...@oracle.com>
Cc: Nico Pache <npa...@redhat.com>
Cc: Ryan Roberts <ryan.robe...@arm.com>
Cc: Dev Jain <dev.j...@arm.com>
Cc: Barry Song <bao...@kernel.org>
Cc: Lyude Paul <ly...@redhat.com>
Cc: Danilo Krummrich <d...@kernel.org>
Cc: David Airlie <airl...@gmail.com>
Cc: Simona Vetter <sim...@ffwll.ch>
Cc: Ralph Campbell <rcampb...@nvidia.com>
Cc: Mika Penttilä <mpent...@redhat.com>
Cc: Matthew Brost <matthew.br...@intel.com>
Cc: Francois Dugast <francois.dug...@intel.com>
Signed-off-by: Balbir Singh <balb...@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
