From: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx> [ Upstream commit c58f0bb77ed8bf93dfdde762b01cb67eebbdfc29 ] Patch series "Do not lose dirty bit on THP pages", v4. Vlastimil noted that pmdp_invalidate() is not atomic and we can lose dirty and access bits if CPU sets them after pmdp dereference, but before set_pmd_at(). The bug can lead to data loss, but the race window is tiny and I haven't seen any reports that suggested that it happens in reality. So I don't think it worth sending it to stable. Unfortunately, there's no way to address the issue in a generic way. We need to fix all architectures that support THP one-by-one. All architectures that have THP supported have to provide atomic pmdp_invalidate() that returns previous value. If generic implementation of pmdp_invalidate() is used, architecture needs to provide atomic pmdp_estabish(). pmdp_estabish() is not used out-side generic implementation of pmdp_invalidate() so far, but I think this can change in the future. This patch (of 12): This is an implementation of pmdp_establish() that is only suitable for an architecture that doesn't have hardware dirty/accessed bits. In this case we can't race with CPU which sets these bits and non-atomic approach is fine. Link: http://lkml.kernel.org/r/20171213105756.69879-2-kirill.shutemov@xxxxxxxxxxxxxxx Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx> Cc: Vlastimil Babka <vbabka@xxxxxxx> Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx> Cc: Michal Hocko <mhocko@xxxxxxxxxx> Cc: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxxxxxxx> Cc: Catalin Marinas <catalin.marinas@xxxxxxx> Cc: David Daney <david.daney@xxxxxxxxxx> Cc: David Miller <davem@xxxxxxxxxxxxx> Cc: H. Peter Anvin <hpa@xxxxxxxxx> Cc: Hugh Dickins <hughd@xxxxxxxxxx> Cc: Ingo Molnar <mingo@xxxxxxxxxx> Cc: Martin Schwidefsky <schwidefsky@xxxxxxxxxx> Cc: Nitin Gupta <nitin.m.gupta@xxxxxxxxxx> Cc: Ralf Baechle <ralf@xxxxxxxxxxxxxx> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx> Cc: Vineet Gupta <vgupta@xxxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> Signed-off-by: Sasha Levin <alexander.levin@xxxxxxxxxxxxx> --- include/asm-generic/pgtable.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index f6ea0f3c03f8..4e8551c8ef18 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -234,6 +234,21 @@ extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); #endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +/* + * This is an implementation of pmdp_establish() that is only suitable for an + * architecture that doesn't have hardware dirty/accessed bits. In this case we + * can't race with CPU which sets these bits and non-atomic aproach is fine. + */ +static inline pmd_t generic_pmdp_establish(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, pmd_t pmd) +{ + pmd_t old_pmd = *pmdp; + set_pmd_at(vma->vm_mm, address, pmdp, pmd); + return old_pmd; +} +#endif + #ifndef __HAVE_ARCH_PMDP_INVALIDATE extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); -- 2.15.1