diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 25c7d7509cf49efe4bc29ed811f05df8de9b6a48..25ef59b7ee3482d797a21f9a69bb916bbfc67ebb 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1558,8 +1558,20 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) * We are not sure a pending tlb flush here is for a huge page * mapping or not. Hence use the tlb range variant */ - if (mm_tlb_flush_pending(vma->vm_mm)) + if (mm_tlb_flush_pending(vma->vm_mm)) { flush_tlb_range(vma, haddr, haddr + HPAGE_PMD_SIZE); + /* + * change_huge_pmd() released the pmd lock before + * invalidating the secondary MMUs sharing the primary + * MMU pagetables (with ->invalidate_range()). The + * mmu_notifier_invalidate_range_end() (which + * internally calls ->invalidate_range()) in + * change_pmd_range() will run after us, so we can't + * rely on it here and we need an explicit invalidate. + */ + mmu_notifier_invalidate_range(vma->vm_mm, haddr, + haddr + HPAGE_PMD_SIZE); + } /* * Migrate the THP to the requested node, returns with page unlocked diff --git a/mm/migrate.c b/mm/migrate.c index 93d9a1e25aad3c76b0ef2febdd1055f891da6af0..905c2264c7885cdf23f4e6f6382153daaff2bd60 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1975,8 +1975,8 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, int isolated = 0; struct page *new_page = NULL; int page_lru = page_is_file_cache(page); - unsigned long mmun_start = address & HPAGE_PMD_MASK; - unsigned long mmun_end = mmun_start + HPAGE_PMD_SIZE; + unsigned long start = address & HPAGE_PMD_MASK; + unsigned long end = start + HPAGE_PMD_SIZE; new_page = alloc_pages_node(node, (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE), @@ -2003,11 +2003,9 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, WARN_ON(PageLRU(new_page)); /* Recheck the target PMD */ - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); ptl = pmd_lock(mm, pmd); if (unlikely(!pmd_same(*pmd, entry) || !page_ref_freeze(page, 2))) { spin_unlock(ptl); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); /* Reverse changes made by migrate_page_copy() */ if (TestClearPageActive(new_page)) @@ -2038,8 +2036,8 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, * new page and page_add_new_anon_rmap guarantee the copy is * visible before the pagetable update. */ - flush_cache_range(vma, mmun_start, mmun_end); - page_add_anon_rmap(new_page, vma, mmun_start, true); + flush_cache_range(vma, start, end); + page_add_anon_rmap(new_page, vma, start, true); /* * At this point the pmd is numa/protnone (i.e. non present) and the TLB * has already been flushed globally. So no TLB can be currently @@ -2051,7 +2049,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, * MADV_DONTNEED won't wait on the pmd lock and it'll skip clearing this * pmd. */ - set_pmd_at(mm, mmun_start, pmd, entry); + set_pmd_at(mm, start, pmd, entry); update_mmu_cache_pmd(vma, address, &entry); page_ref_unfreeze(page, 2); @@ -2060,11 +2058,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, set_page_owner_migrate_reason(new_page, MR_NUMA_MISPLACED); spin_unlock(ptl); - /* - * No need to double call mmu_notifier->invalidate_range() callback as - * the above pmdp_huge_clear_flush_notify() did already call it. - */ - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); /* Take an "isolate" reference and put new page on the LRU. */ get_page(new_page); @@ -2088,7 +2081,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, ptl = pmd_lock(mm, pmd); if (pmd_same(*pmd, entry)) { entry = pmd_modify(entry, vma->vm_page_prot); - set_pmd_at(mm, mmun_start, pmd, entry); + set_pmd_at(mm, start, pmd, entry); update_mmu_cache_pmd(vma, address, &entry); } spin_unlock(ptl);