mm: avoid zeroing user movable page twice with init_on_alloc=1

Commit 6471384af2 ("mm: security: introduce init_on_alloc=1 and
init_on_free=1 boot options") forces allocated page to be zeroed in
post_alloc_hook() when init_on_alloc=1.

For order-0 folios, if arch does not define
vma_alloc_zeroed_movable_folio(), the default implementation again zeros
the page return from the buddy allocator.  So the page is zeroed twice. 
Fix it by passing __GFP_ZERO instead to avoid double page zeroing.  At the
moment, s390,arm64,x86,alpha,m68k are not impacted since they define their
own vma_alloc_zeroed_movable_folio().

For >0 order folios (mTHP and PMD THP), folio_zero_user() is called to
zero the folio again.  Fix it by calling folio_zero_user() only if
init_on_alloc is set.  All arch are impacted.

Add alloc_zeroed() helper to encapsulate the init_on_alloc check.

[ziy@nvidia.com: comment fixes, per David]
  Link: https://lkml.kernel.org/r/97DB52E1-C594-49B5-9736-89AC302FAB01@nvidia.com
Link: https://lkml.kernel.org/r/20241011150304.709590-1-ziy@nvidia.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

include/linux/highmem.h

@@ -224,13 +224,7 @@ static inline
 struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma,
 				   unsigned long vaddr)
 {
-	struct folio *folio;
-
-	folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr);
-	if (folio)
-		clear_user_highpage(&folio->page, vaddr);
-
-	return folio;
+	return vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr);
 }
 #endif
 

mm/huge_memory.c

@@ -1162,6 +1162,12 @@ static struct folio *vma_alloc_anon_folio_pmd(struct vm_area_struct *vma,
 	}
 	folio_throttle_swaprate(folio, gfp);
 
+       /*
+	* When a folio is not zeroed during allocation (__GFP_ZERO not used),
+	* folio_zero_user() is used to make sure that the page corresponding
+	* to the faulting address will be hot in the cache after zeroing.
+	*/
+	if (!alloc_zeroed())
 		folio_zero_user(folio, addr);
 	/*
 	 * The memory barrier inside __folio_mark_uptodate makes sure that

mm/internal.h

@@ -1276,6 +1276,12 @@ void touch_pud(struct vm_area_struct *vma, unsigned long addr,
 void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
 	       pmd_t *pmd, bool write);
 
+static inline bool alloc_zeroed(void)
+{
+	return static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON,
+			&init_on_alloc);
+}
+
 enum {
 	/* mark page accessed */
 	FOLL_TOUCH = 1 << 16,

mm/memory.c

@@ -4719,6 +4719,14 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf)
 				goto next;
 			}
 			folio_throttle_swaprate(folio, gfp);
+			/*
+			 * When a folio is not zeroed during allocation
+			 * (__GFP_ZERO not used), folio_zero_user() is used
+			 * to make sure that the page corresponding to the
+			 * faulting address will be hot in the cache after
+			 * zeroing.
+			 */
+			if (!alloc_zeroed())
 				folio_zero_user(folio, vmf->address);
 			return folio;
 		}