--- /dev/null
+From 19be0eaffa3ac7d8eb6784ad9bdbc7d67ed8e619 Mon Sep 17 00:00:00 2001
+From: Linus Torvalds <torvalds@linux-foundation.org>
+Date: Thu, 13 Oct 2016 13:07:36 -0700
+Subject: mm: remove gup_flags FOLL_WRITE games from __get_user_pages()
+
+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 <kernel@linuxace.com>
+Acked-by: Hugh Dickins <hughd@google.com>
+Reviewed-by: Michal Hocko <mhocko@suse.com>
+Cc: Andy Lutomirski <luto@kernel.org>
+Cc: Kees Cook <keescook@chromium.org>
+Cc: Oleg Nesterov <oleg@redhat.com>
+Cc: Willy Tarreau <w@1wt.eu>
+Cc: Nick Piggin <npiggin@gmail.com>
+Cc: Greg Thelen <gthelen@google.com>
+Cc: stable@vger.kernel.org
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+---
+ include/linux/mm.h | 1 +
+ mm/memory.c | 15 +++++++++++++-
+ 2 files changed, 14 insertions(+), 2 deletions(-)
+
+diff --git a/include/linux/mm.h b/include/linux/mm.h
+index e9caec6..ed85879 100644
+--- a/include/linux/mm.h
++++ b/include/linux/mm.h
+@@ -1466,6 +1466,7 @@ 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 b6e3037..2d8080c 100644
+--- a/mm/memory.c
++++ b/mm/memory.c
+@@ -1296,6 +1296,17 @@ 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));
++}
++
++
+ /*
+ * Do a quick page-table lookup for a single page.
+ */
+@@ -1385,7 +1396,7 @@ split_fallthrough:
+ migration_entry_wait(mm, pmd, address);
+ goto split_fallthrough;
+ }
+- 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);
+@@ -1618,7 +1629,7 @@ int __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();
+ }
projects / pve-kernel-2.6.32.git / commitdiff