From: Matthew Brost <[email protected]>

Add free_zone_device_folio_prepare(), a helper that restores large
ZONE_DEVICE folios to a sane, initial state before freeing them.

Compound ZONE_DEVICE folios overwrite per-page state (e.g. pgmap and
compound metadata). Before returning such pages to the device pgmap
allocator, each constituent page must be reset to a standalone
ZONE_DEVICE folio with a valid pgmap and no compound state.

Use this helper prior to folio_free() for device-private and
device-coherent folios to ensure consistent device page state for
subsequent allocations.

Fixes: d245f9b4ab80 ("mm/zone_device: support large zone device private folios")
Cc: Zi Yan <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: Oscar Salvador <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Balbir Singh <[email protected]>
Cc: Lorenzo Stoakes <[email protected]>
Cc: Liam R. Howlett <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Cc: Mike Rapoport <[email protected]>
Cc: Suren Baghdasaryan <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Alistair Popple <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Suggested-by: Alistair Popple <[email protected]>
Signed-off-by: Matthew Brost <[email protected]>
Signed-off-by: Francois Dugast <[email protected]>
---
 include/linux/memremap.h |  1 +
 mm/memremap.c            | 55 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 56 insertions(+)

diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 97fcffeb1c1e..88e1d4707296 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -230,6 +230,7 @@ static inline bool is_fsdax_page(const struct page *page)
 
 #ifdef CONFIG_ZONE_DEVICE
 void zone_device_page_init(struct page *page, unsigned int order);
+void free_zone_device_folio_prepare(struct folio *folio);
 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);
diff --git a/mm/memremap.c b/mm/memremap.c
index 39dc4bd190d0..375a61e18858 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -413,6 +413,60 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn)
 }
 EXPORT_SYMBOL_GPL(get_dev_pagemap);
 
+/**
+ * free_zone_device_folio_prepare() - Prepare a ZONE_DEVICE folio for freeing.
+ * @folio: ZONE_DEVICE folio to prepare for release.
+ *
+ * ZONE_DEVICE pages/folios (e.g., device-private memory or fsdax-backed pages)
+ * can be compound. When freeing a compound ZONE_DEVICE folio, the tail pages
+ * must be restored to a sane ZONE_DEVICE state before they are released.
+ *
+ * This helper:
+ *   - Clears @folio->mapping and, for compound folios, clears each page's
+ *     compound-head state (ClearPageHead()/clear_compound_head()).
+ *   - Resets the compound order metadata (folio_reset_order()) and then
+ *     initializes each constituent page as a standalone ZONE_DEVICE folio:
+ *       * clears ->mapping
+ *       * restores ->pgmap (prep_compound_page() overwrites it)
+ *       * clears ->share (only relevant for fsdax; unused for device-private)
+ *
+ * If @folio is order-0, only the mapping is cleared and no further work is
+ * required.
+ */
+void free_zone_device_folio_prepare(struct folio *folio)
+{
+       struct dev_pagemap *pgmap = page_pgmap(&folio->page);
+       int order, i;
+
+       VM_WARN_ON_FOLIO(!folio_is_zone_device(folio), folio);
+
+       folio->mapping = NULL;
+       order = folio_order(folio);
+       if (!order)
+               return;
+
+       folio_reset_order(folio);
+
+       for (i = 0; i < (1UL << order); i++) {
+               struct page *page = folio_page(folio, i);
+               struct folio *new_folio = (struct folio *)page;
+
+               ClearPageHead(page);
+               clear_compound_head(page);
+
+               new_folio->mapping = NULL;
+               /*
+                * Reset pgmap which was over-written by
+                * prep_compound_page().
+                */
+               new_folio->pgmap = pgmap;
+               new_folio->share = 0;   /* fsdax only, unused for device 
private */
+               VM_WARN_ON_FOLIO(folio_ref_count(new_folio), new_folio);
+               VM_WARN_ON_FOLIO(!folio_is_zone_device(new_folio), new_folio);
+       }
+}
+EXPORT_SYMBOL_GPL(free_zone_device_folio_prepare);
+
 void free_zone_device_folio(struct folio *folio)
 {
        struct dev_pagemap *pgmap = folio->pgmap;
@@ -454,6 +508,7 @@ void free_zone_device_folio(struct folio *folio)
        case MEMORY_DEVICE_COHERENT:
                if (WARN_ON_ONCE(!pgmap->ops || !pgmap->ops->folio_free))
                        break;
+               free_zone_device_folio_prepare(folio);
                pgmap->ops->folio_free(folio, order);
                percpu_ref_put_many(&folio->pgmap->ref, nr);
                break;
-- 
2.43.0

Reply via email to