From 5708d96da20b99b4665ad72395e3727016057f70 Mon Sep 17 00:00:00 2001 From: Zi Yan Date: Fri, 11 Oct 2024 11:03:04 -0400 Subject: mm: avoid zeroing user movable page twice with init_on_alloc=1 Commit 6471384af2a6 ("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 Acked-by: Vlastimil Babka Acked-by: David Hildenbrand Cc: Alexander Potapenko Cc: "Huang, Ying" Cc: John Hubbard Cc: Kees Cook Cc: Kefeng Wang Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Ryan Roberts Signed-off-by: Andrew Morton --- mm/huge_memory.c | 8 +++++++- mm/internal.h | 6 ++++++ mm/memory.c | 10 +++++++++- 3 files changed, 22 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 387c046a389e..73194aa0544c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1162,7 +1162,13 @@ static struct folio *vma_alloc_anon_folio_pmd(struct vm_area_struct *vma, } folio_throttle_swaprate(folio, gfp); - folio_zero_user(folio, addr); + /* + * 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 * folio_zero_user writes become visible before the set_pmd_at() diff --git a/mm/internal.h b/mm/internal.h index fc2f523258a3..c743c2b21dba 100644 --- a/mm/internal.h +++ b/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, diff --git a/mm/memory.c b/mm/memory.c index c51bc45a7009..68e57b33363b 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4719,7 +4719,15 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf) goto next; } folio_throttle_swaprate(folio, gfp); - folio_zero_user(folio, vmf->address); + /* + * 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; } next: -- cgit v1.2.3