[PATCH RFC v4 20/22] mm: add free_frozen_pages_zeroed

[Michael S. Tsirkin]

Add free_frozen_pages_zeroed(page, order) to free a frozen page
while marking it as zeroed, so the next allocation can skip
redundant zeroing.

An FPI_ZEROED internal flag carries the hint through the free path.
PageZeroed is set after __free_pages_prepare() clears all flags,
so the hint survives on the free list.

Signed-off-by: Michael S. Tsirkin <mst@xxxxxxxxxx>
Assisted-by: Claude:claude-opus-4-6
---
 include/linux/gfp.h |  1 +
 mm/internal.h       |  1 -
 mm/page_alloc.c     | 21 ++++++++++++++++++++-
 3 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index e275cc80e19e..766b1c7f0731 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -394,6 +394,7 @@ __meminit void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mas
 extern void __free_pages(struct page *page, unsigned int order);
 extern void free_pages_nolock(struct page *page, unsigned int order);
 extern void free_pages(unsigned long addr, unsigned int order);
+void free_frozen_pages_zeroed(struct page *page, unsigned int order);
 
 #define __free_page(page) __free_pages((page), 0)
 #define free_page(addr) free_pages((addr), 0)
diff --git a/mm/internal.h b/mm/internal.h
index 0600d824ba03..60b983872d51 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -899,7 +899,6 @@ struct page *__alloc_frozen_pages_noprof(gfp_t, unsigned int order, int nid,
 #define __alloc_frozen_pages(...) \
 	alloc_hooks(__alloc_frozen_pages_noprof(__VA_ARGS__))
 void free_frozen_pages(struct page *page, unsigned int order);
-void free_frozen_pages_zeroed(struct page *page, unsigned int order);
 void free_unref_folios(struct folio_batch *fbatch);
 
 #ifdef CONFIG_NUMA
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1169714406e7..981ddf3566b5 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -90,6 +90,13 @@ typedef int __bitwise fpi_t;
 /* Free the page without taking locks. Rely on trylock only. */
 #define FPI_TRYLOCK		((__force fpi_t)BIT(2))
 
+/*
+ * The page contents are known to be zero (e.g., the host zeroed them
+ * during balloon deflate).  Set PageZeroed after free so the next
+ * allocation can skip redundant zeroing.
+ */
+#define FPI_ZEROED		((__force fpi_t)BIT(3))
+
 /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
 static DEFINE_MUTEX(pcp_batch_high_lock);
 #define MIN_PERCPU_PAGELIST_HIGH_FRACTION (8)
@@ -1624,8 +1631,11 @@ static void __free_pages_ok(struct page *page, unsigned int order,
 	unsigned long pfn = page_to_pfn(page);
 	struct zone *zone = page_zone(page);
 
-	if (__free_pages_prepare(page, order, fpi_flags))
+	if (__free_pages_prepare(page, order, fpi_flags)) {
+		if (fpi_flags & FPI_ZEROED)
+			__SetPageZeroed(page);
 		free_one_page(zone, page, pfn, order, fpi_flags);
+	}
 }
 
 void __meminit __free_pages_core(struct page *page, unsigned int order,
@@ -3032,6 +3042,9 @@ static void __free_frozen_pages(struct page *page, unsigned int order,
 	if (!__free_pages_prepare(page, order, fpi_flags))
 		return;
 
+	if (fpi_flags & FPI_ZEROED)
+		__SetPageZeroed(page);
+
 	/*
 	 * We only track unmovable, reclaimable and movable on pcp lists.
 	 * Place ISOLATE pages on the isolated list because they are being
@@ -3070,6 +3083,12 @@ void free_frozen_pages(struct page *page, unsigned int order)
 	__free_frozen_pages(page, order, FPI_NONE);
 }
 
+void free_frozen_pages_zeroed(struct page *page, unsigned int order)
+{
+	__free_frozen_pages(page, order, FPI_ZEROED);
+}
+EXPORT_SYMBOL(free_frozen_pages_zeroed);
+
 void free_frozen_pages_nolock(struct page *page, unsigned int order)
 {
 	__free_frozen_pages(page, order, FPI_TRYLOCK);
-- 
MST