[PATCH v6 15/30] mm: memfd: skip zeroing for zeroed hugetlb pool pages

[Michael S. Tsirkin]

gather_surplus_pages() pre-allocates hugetlb pages into the pool
during mmap.  Pass __GFP_ZERO so these pages are zeroed by the
buddy allocator, and HPG_zeroed is set by alloc_surplus_hugetlb_folio.

Add bool *zeroed output to alloc_hugetlb_folio_reserve() so
callers can check whether the pool page is known-zero.  memfd's
memfd_alloc_folio() uses this to skip the explicit folio_zero_user()
when the page is already zero.

This avoids redundant zeroing for memfd hugetlb pages that were
pre-allocated into the pool and never mapped to userspace.

Signed-off-by: Michael S. Tsirkin <mst@xxxxxxxxxx>
Assisted-by: Claude:claude-opus-4-6
---
 include/linux/hugetlb.h |  6 ++++--
 mm/hugetlb.c            | 11 +++++++++--
 mm/memfd.c              | 14 ++++++++------
 3 files changed, 21 insertions(+), 10 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 950e1702fbd8..c4e66a371fce 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -714,7 +714,8 @@ struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
 				nodemask_t *nmask, gfp_t gfp_mask,
 				bool allow_alloc_fallback);
 struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid,
-					  nodemask_t *nmask, gfp_t gfp_mask);
+					  nodemask_t *nmask, gfp_t gfp_mask,
+					  bool *zeroed);
 
 int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping,
 			pgoff_t idx);
@@ -1142,7 +1143,8 @@ static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 
 static inline struct folio *
 alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid,
-			    nodemask_t *nmask, gfp_t gfp_mask)
+			    nodemask_t *nmask, gfp_t gfp_mask,
+			    bool *zeroed)
 {
 	return NULL;
 }
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 8710366d14b7..03ad5c1e0655 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2205,7 +2205,7 @@ struct folio *alloc_buddy_hugetlb_folio_with_mpol(struct hstate *h,
 }
 
 struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid,
-		nodemask_t *nmask, gfp_t gfp_mask)
+		nodemask_t *nmask, gfp_t gfp_mask, bool *zeroed)
 {
 	struct folio *folio;
 
@@ -2221,6 +2221,12 @@ struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid,
 		h->resv_huge_pages--;
 
 	spin_unlock_irq(&hugetlb_lock);
+
+	if (zeroed && folio) {
+		*zeroed = folio_test_hugetlb_zeroed(folio);
+		folio_clear_hugetlb_zeroed(folio);
+	}
+
 	return folio;
 }
 
@@ -2305,7 +2311,8 @@ static int gather_surplus_pages(struct hstate *h, long delta)
 		 * It is okay to use NUMA_NO_NODE because we use numa_mem_id()
 		 * down the road to pick the current node if that is the case.
 		 */
-		folio = alloc_surplus_hugetlb_folio(h, htlb_alloc_mask(h),
+		folio = alloc_surplus_hugetlb_folio(h,
+						    htlb_alloc_mask(h) | __GFP_ZERO,
 						    NUMA_NO_NODE, &alloc_nodemask,
 						    USER_ADDR_NONE);
 		if (!folio) {
diff --git a/mm/memfd.c b/mm/memfd.c
index fb425f4e315f..5518f7d2d91f 100644
--- a/mm/memfd.c
+++ b/mm/memfd.c
@@ -69,6 +69,7 @@ struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx)
 #ifdef CONFIG_HUGETLB_PAGE
 	struct folio *folio;
 	gfp_t gfp_mask;
+	bool zeroed;
 
 	if (is_file_hugepages(memfd)) {
 		/*
@@ -93,17 +94,18 @@ struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx)
 		folio = alloc_hugetlb_folio_reserve(h,
 						    numa_node_id(),
 						    NULL,
-						    gfp_mask);
+						    gfp_mask,
+						    &zeroed);
 		if (folio) {
 			u32 hash;
 
 			/*
-			 * Zero the folio to prevent information leaks to userspace.
-			 * Use folio_zero_user() which is optimized for huge/gigantic
-			 * pages. Pass 0 as addr_hint since this is not a faulting path
-			 *  and we don't have a user virtual address yet.
+			 * Zero the folio to prevent information leaks to
+			 * userspace.  Skip if the pool page is known-zero
+			 * (HPG_zeroed set during pool pre-allocation).
 			 */
-			folio_zero_user(folio, 0);
+			if (!zeroed)
+				folio_zero_user(folio, 0);
 
 			/*
 			 * Mark the folio uptodate before adding to page cache,
-- 
MST