From e15f8c01af924e611bc7be1e45449c4a74e5dfdd Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Thu, 10 Feb 2011 15:01:32 -0800 Subject: mlock: fix race when munlocking pages in do_wp_page() vmscan can lazily find pages that are mapped within VM_LOCKED vmas, and set the PageMlocked bit on these pages, transfering them onto the unevictable list. When do_wp_page() breaks COW within a VM_LOCKED vma, it may need to clear PageMlocked on the old page and set it on the new page instead. This change fixes an issue where do_wp_page() was clearing PageMlocked on the old page while the pte was still pointing to it (as well as rmap). Therefore, we were not protected against vmscan immediately transfering the old page back onto the unevictable list. This could cause pages to get stranded there forever. I propose to move the corresponding code to the end of do_wp_page(), after the pte (and rmap) have been pointed to the new page. Additionally, we can use munlock_vma_page() instead of clear_page_mlock(), so that the old page stays mlocked if there are still other VM_LOCKED vmas mapping it. Signed-off-by: Michel Lespinasse Reviewed-by: KAMEZAWA Hiroyuki Acked-by: Hugh Dickins Cc: Rik van Riel Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 26 ++++++++++++-------------- 1 file changed, 12 insertions(+), 14 deletions(-) (limited to 'mm/memory.c') diff --git a/mm/memory.c b/mm/memory.c index 31250faff390..32df03cf13a5 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2219,7 +2219,6 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, &ptl); if (!pte_same(*page_table, orig_pte)) { unlock_page(old_page); - page_cache_release(old_page); goto unlock; } page_cache_release(old_page); @@ -2289,7 +2288,6 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, &ptl); if (!pte_same(*page_table, orig_pte)) { unlock_page(old_page); - page_cache_release(old_page); goto unlock; } @@ -2367,16 +2365,6 @@ gotten: } __SetPageUptodate(new_page); - /* - * Don't let another task, with possibly unlocked vma, - * keep the mlocked page. - */ - if ((vma->vm_flags & VM_LOCKED) && old_page) { - lock_page(old_page); /* for LRU manipulation */ - clear_page_mlock(old_page); - unlock_page(old_page); - } - if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL)) goto oom_free_new; @@ -2444,10 +2432,20 @@ gotten: if (new_page) page_cache_release(new_page); - if (old_page) - page_cache_release(old_page); unlock: pte_unmap_unlock(page_table, ptl); + if (old_page) { + /* + * Don't let another task, with possibly unlocked vma, + * keep the mlocked page. + */ + if ((ret & VM_FAULT_WRITE) && (vma->vm_flags & VM_LOCKED)) { + lock_page(old_page); /* LRU manipulation */ + munlock_vma_page(old_page); + unlock_page(old_page); + } + page_cache_release(old_page); + } return ret; oom_free_new: page_cache_release(new_page); -- cgit v1.2.3