diff --git a/mm/mprotect.c b/mm/mprotect.c index 7967825f6d33..95dee88f782b 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -161,6 +161,31 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, return pages; } +/* + * Used when setting automatic NUMA hinting protection where it is + * critical that a numa hinting PMD is not confused with a bad PMD. + */ +static inline int pmd_none_or_clear_bad_unless_trans_huge(pmd_t *pmd) +{ + pmd_t pmdval = pmd_read_atomic(pmd); + + /* See pmd_none_or_trans_huge_or_clear_bad for info on barrier */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + barrier(); +#endif + + if (pmd_none(pmdval)) + return 1; + if (pmd_trans_huge(pmdval)) + return 0; + if (unlikely(pmd_bad(pmdval))) { + pmd_clear_bad(pmd); + return 1; + } + + return 0; +} + static inline unsigned long change_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, pgprot_t newprot, int dirty_accountable, int prot_numa) @@ -178,8 +203,17 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, unsigned long this_pages; next = pmd_addr_end(addr, end); - if (!is_swap_pmd(*pmd) && !pmd_trans_huge(*pmd) && !pmd_devmap(*pmd) - && pmd_none_or_clear_bad(pmd)) + + /* + * Automatic NUMA balancing walks the tables with mmap_sem + * held for read. It's possible a parallel update to occur + * between pmd_trans_huge() and a pmd_none_or_clear_bad() + * check leading to a false positive and clearing. + * Hence, it's necessary to atomically read the PMD value + * for all the checks. + */ + if (!is_swap_pmd(*pmd) && !pmd_devmap(*pmd) && + pmd_none_or_clear_bad_unless_trans_huge(pmd)) goto next; /* invoke the mmu notifier if the pmd is populated */