From c33d1bdff9c4c24e73e7c7f48ce8f8c1819a233f Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 20 Oct 2016 14:11:10 -0700 Subject: [PATCH] UPSTREAM: mm: remove gup_flags FOLL_WRITE games from __get_user_pages() (cherry-picked from 9691eac5593ff1e2f82391ad327f21d90322aec1) commit 19be0eaffa3ac7d8eb6784ad9bdbc7d67ed8e619 upstream. This is an ancient bug that was actually attempted to be fixed once (badly) by me eleven years ago in commit 4ceb5db9757a ("Fix get_user_pages() race for write access") but that was then undone due to problems on s390 by commit f33ea7f404e5 ("fix get_user_pages bug"). In the meantime, the s390 situation has long been fixed, and we can now fix it by checking the pte_dirty() bit properly (and do it better). The s390 dirty bit was implemented in abf09bed3cce ("s390/mm: implement software dirty bits") which made it into v3.9. Earlier kernels will have to look at the page state itself. Also, the VM has become more scalable, and what used a purely theoretical race back then has become easier to trigger. To fix it, we introduce a new internal FOLL_COW flag to mark the "yes, we already did a COW" rather than play racy games with FOLL_WRITE that is very fundamental, and then use the pte dirty flag to validate that the FOLL_COW flag is still valid. Reported-and-tested-by: Phil "not Paul" Oester Acked-by: Hugh Dickins Reviewed-by: Michal Hocko Cc: Andy Lutomirski Cc: Kees Cook Cc: Oleg Nesterov Cc: Willy Tarreau Cc: Nick Piggin Cc: Greg Thelen Cc: stable@vger.kernel.org Signed-off-by: Linus Torvalds [wt: s/gup.c/memory.c; s/follow_page_pte/follow_page_mask; s/faultin_page/__get_user_page] Signed-off-by: Willy Tarreau Change-Id: I42e448ecacad4781b460c4c989026307169ba1b5 Bug: 32141528 --- include/linux/mm.h | 1 + mm/memory.c | 14 ++++++++++++-- 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index b582c9d07fcd5..54567b0c41d63 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1752,6 +1752,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma, #define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */ #define FOLL_NUMA 0x200 /* force NUMA hinting page fault */ #define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */ +#define FOLL_COW 0x4000 /* internal GUP flag */ typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, void *data); diff --git a/mm/memory.c b/mm/memory.c index ac61bc57e3ef4..fd453654d3008 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1467,6 +1467,16 @@ int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, } EXPORT_SYMBOL_GPL(zap_vma_ptes); +/* + * FOLL_FORCE can write to even unwritable pte's, but only + * after we've gone through a COW cycle and they are dirty. + */ +static inline bool can_follow_write_pte(pte_t pte, unsigned int flags) +{ + return pte_write(pte) || + ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte)); +} + /** * follow_page_mask - look up a page descriptor from a user-virtual address * @vma: vm_area_struct mapping @address @@ -1574,7 +1584,7 @@ struct page *follow_page_mask(struct vm_area_struct *vma, } if ((flags & FOLL_NUMA) && pte_numa(pte)) goto no_page; - if ((flags & FOLL_WRITE) && !pte_write(pte)) + if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) goto unlock; page = vm_normal_page(vma, address, pte); @@ -1894,7 +1904,7 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, */ if ((ret & VM_FAULT_WRITE) && !(vma->vm_flags & VM_WRITE)) - foll_flags &= ~FOLL_WRITE; + foll_flags |= FOLL_COW; cond_resched(); }