From 605ca5ede7643a01f4c4a15913f9714ac297f8a6 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Thu, 5 Apr 2018 16:23:28 -0700 Subject: [PATCH] mm/huge_memory.c: reorder operations in __split_huge_page_tail() THP split makes non-atomic change of tail page flags. This is almost ok because tail pages are locked and isolated but this breaks recent changes in page locking: non-atomic operation could clear bit PG_waiters. As a result concurrent sequence get_page_unless_zero() -> lock_page() might block forever. Especially if this page was truncated later. Fix is trivial: clone flags before unfreezing page reference counter. This race exists since commit 62906027091f ("mm: add PageWaiters indicating tasks are waiting for a page bit") while unsave unfreeze itself was added in commit 8df651c7059e ("thp: cleanup split_huge_page()"). clear_compound_head() also must be called before unfreezing page reference because after successful get_page_unless_zero() might follow put_page() which needs correct compound_head(). And replace page_ref_inc()/page_ref_add() with page_ref_unfreeze() which is made especially for that and has semantic of smp_store_release(). Link: http://lkml.kernel.org/r/151844393341.210639.13162088407980624477.stgit@buzz Signed-off-by: Konstantin Khlebnikov Acked-by: Kirill A. Shutemov Cc: Michal Hocko Cc: Nicholas Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 36 +++++++++++++++--------------------- 1 file changed, 15 insertions(+), 21 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 5a68730eebd6..f0ae8d1d4329 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2356,26 +2356,13 @@ static void __split_huge_page_tail(struct page *head, int tail, struct page *page_tail = head + tail; VM_BUG_ON_PAGE(atomic_read(&page_tail->_mapcount) != -1, page_tail); - VM_BUG_ON_PAGE(page_ref_count(page_tail) != 0, page_tail); /* - * tail_page->_refcount is zero and not changing from under us. But - * get_page_unless_zero() may be running from under us on the - * tail_page. If we used atomic_set() below instead of atomic_inc() or - * atomic_add(), we would then run atomic_set() concurrently with - * get_page_unless_zero(), and atomic_set() is implemented in C not - * using locked ops. spin_unlock on x86 sometime uses locked ops - * because of PPro errata 66, 92, so unless somebody can guarantee - * atomic_set() here would be safe on all archs (and not only on x86), - * it's safer to use atomic_inc()/atomic_add(). + * Clone page flags before unfreezing refcount. + * + * After successful get_page_unless_zero() might follow flags change, + * for exmaple lock_page() which set PG_waiters. */ - if (PageAnon(head) && !PageSwapCache(head)) { - page_ref_inc(page_tail); - } else { - /* Additional pin to radix tree */ - page_ref_add(page_tail, 2); - } - page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; page_tail->flags |= (head->flags & ((1L << PG_referenced) | @@ -2388,14 +2375,21 @@ static void __split_huge_page_tail(struct page *head, int tail, (1L << PG_unevictable) | (1L << PG_dirty))); - /* - * After clearing PageTail the gup refcount can be released. - * Page flags also must be visible before we make the page non-compound. - */ + /* Page flags must be visible before we make the page non-compound. */ smp_wmb(); + /* + * Clear PageTail before unfreezing page refcount. + * + * After successful get_page_unless_zero() might follow put_page() + * which needs correct compound_head(). + */ clear_compound_head(page_tail); + /* Finally unfreeze refcount. Additional reference from page cache. */ + page_ref_unfreeze(page_tail, 1 + (!PageAnon(head) || + PageSwapCache(head))); + if (page_is_young(head)) set_page_young(page_tail); if (page_is_idle(head))