From 2da28bfd9665f49d40abb4c7720b43135feaf79a Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Fri, 11 Mar 2011 14:58:29 -0800 Subject: thp: fix page_referenced to modify mapcount/vm_flags only if page is found When vmscan.c calls page_referenced(), if an anon page was created before a process forked, rmap will search for it in both of the processes, even though one of them might have since broken COW. If the child process mlocks the vma where the COWed page belongs to, page_referenced() running on the page mapped by the parent would lead to *vm_flags getting VM_LOCKED set erroneously (leading to the references on the parent page being ignored and evicting the parent page too early). *mapcount would also be decremented by page_referenced_one even if the page wasn't found by page_check_address. This also lets pmdp_clear_flush_young_notify() go ahead on a pmd_trans_splitting() pmd. We hold the page_table_lock so __split_huge_page_map() must wait the pmdp_clear_flush_young_notify() to complete before it can modify the pmd. The pmd is also still mapped in userland so the young bit may materialize through a tlb miss before split_huge_page_map runs. This will provide a more accurate page_referenced() behavior during split_huge_page(). Signed-off-by: Andrea Arcangeli Reported-by: Michel Lespinasse Reviewed-by: Michel Lespinasse Reviewed-by: Minchan Kim Reviewed-by: Johannes Weiner Reviewed-by: Rik van Riel Reviewed-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/rmap.c | 54 +++++++++++++++++++++++++++++++++++------------------- 1 file changed, 35 insertions(+), 19 deletions(-) diff --git a/mm/rmap.c b/mm/rmap.c index f21f4a1d6a1c..941bf82e8961 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -497,41 +497,51 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma, struct mm_struct *mm = vma->vm_mm; int referenced = 0; - /* - * Don't want to elevate referenced for mlocked page that gets this far, - * in order that it progresses to try_to_unmap and is moved to the - * unevictable list. - */ - if (vma->vm_flags & VM_LOCKED) { - *mapcount = 0; /* break early from loop */ - *vm_flags |= VM_LOCKED; - goto out; - } - - /* Pretend the page is referenced if the task has the - swap token and is in the middle of a page fault. */ - if (mm != current->mm && has_swap_token(mm) && - rwsem_is_locked(&mm->mmap_sem)) - referenced++; - if (unlikely(PageTransHuge(page))) { pmd_t *pmd; spin_lock(&mm->page_table_lock); + /* + * rmap might return false positives; we must filter + * these out using page_check_address_pmd(). + */ pmd = page_check_address_pmd(page, mm, address, PAGE_CHECK_ADDRESS_PMD_FLAG); - if (pmd && !pmd_trans_splitting(*pmd) && - pmdp_clear_flush_young_notify(vma, address, pmd)) + if (!pmd) { + spin_unlock(&mm->page_table_lock); + goto out; + } + + if (vma->vm_flags & VM_LOCKED) { + spin_unlock(&mm->page_table_lock); + *mapcount = 0; /* break early from loop */ + *vm_flags |= VM_LOCKED; + goto out; + } + + /* go ahead even if the pmd is pmd_trans_splitting() */ + if (pmdp_clear_flush_young_notify(vma, address, pmd)) referenced++; spin_unlock(&mm->page_table_lock); } else { pte_t *pte; spinlock_t *ptl; + /* + * rmap might return false positives; we must filter + * these out using page_check_address(). + */ pte = page_check_address(page, mm, address, &ptl, 0); if (!pte) goto out; + if (vma->vm_flags & VM_LOCKED) { + pte_unmap_unlock(pte, ptl); + *mapcount = 0; /* break early from loop */ + *vm_flags |= VM_LOCKED; + goto out; + } + if (ptep_clear_flush_young_notify(vma, address, pte)) { /* * Don't treat a reference through a sequentially read @@ -546,6 +556,12 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma, pte_unmap_unlock(pte, ptl); } + /* Pretend the page is referenced if the task has the + swap token and is in the middle of a page fault. */ + if (mm != current->mm && has_swap_token(mm) && + rwsem_is_locked(&mm->mmap_sem)) + referenced++; + (*mapcount)--; if (referenced) -- cgit v1.2.3-58-ga151