mm: remove gup_flags FOLL_WRITE games from __get_user_pages()

commit 19be0eaf upstream.

This is an ancient bug that was actually attempted to be fixed once
(badly) by me eleven years ago in commit 4ceb5db9 ("Fix
get_user_pages() race for write access") but that was then undone due to
problems on s390 by commit f33ea7f4 ("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 abf09bed ("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>
[carnil: backport to 3.16, adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>

include/linux/mm.h

@@ -2007,6 +2007,7 @@ 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);

mm/gup.c

@@ -28,6 +28,16 @@ static struct page *no_page_table(struct vm_area_struct *vma,
 	return NULL;
 }
 
+/*
+ * 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));
+}
+
 static struct page *follow_page_pte(struct vm_area_struct *vma,
 		unsigned long address, pmd_t *pmd, unsigned int flags)
 {
@@ -62,7 +72,7 @@ static struct page *follow_page_pte(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)) {
 		pte_unmap_unlock(ptep, ptl);
 		return NULL;
 	}
@@ -302,7 +312,7 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 	 * reCOWed by userspace write).
 	 */
 	if ((ret & VM_FAULT_WRITE) && !(vma->vm_flags & VM_WRITE))
-		*flags &= ~FOLL_WRITE;
+	        *flags |= FOLL_COW;
 	return 0;
 }