[PATCH] fix get_user_pages bug

Checking pte_dirty instead of pte_write in __follow_page is problematic
for s390, and for copy_one_pte which leaves dirty when clearing write.

So revert __follow_page to check pte_write as before, and make
do_wp_page pass back a special extra VM_FAULT_WRITE bit to say it has
done its full job: once get_user_pages receives this value, it no longer
requires pte_write in __follow_page.

But most callers of handle_mm_fault, in the various architectures, have
switch statements which do not expect this new case.  To avoid changing
them all in a hurry, make an inline wrapper function (using the old
name) that masks off the new bit, and use the extended interface with
double underscores.

Yes, we do have a call to do_wp_page from do_swap_page, but no need to
change that: in rare case it's needed, another do_wp_page will follow.

Signed-off-by: Hugh Dickins <hugh@veritas.com>
[ Cleanups by Nick Piggin ]
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 17 insertions, 5 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 6eb7f48317f..82d7024f076 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -625,10 +625,16 @@ static inline int page_mapped(struct page *page)
  * Used to decide whether a process gets delivered SIGBUS or
  * just gets major/minor fault counters bumped up.
  */
-#define VM_FAULT_OOM	(-1)
-#define VM_FAULT_SIGBUS	0
-#define VM_FAULT_MINOR	1
-#define VM_FAULT_MAJOR	2
+#define VM_FAULT_OOM	0x00
+#define VM_FAULT_SIGBUS	0x01
+#define VM_FAULT_MINOR	0x02
+#define VM_FAULT_MAJOR	0x03
+
+/* 
+ * Special case for get_user_pages.
+ * Must be in a distinct bit from the above VM_FAULT_ flags.
+ */
+#define VM_FAULT_WRITE	0x10
 
 #define offset_in_page(p)	((unsigned long)(p) & ~PAGE_MASK)
 
@@ -704,7 +710,13 @@ extern pte_t *FASTCALL(pte_alloc_kernel(struct mm_struct *mm, pmd_t *pmd, unsign
 extern pte_t *FASTCALL(pte_alloc_map(struct mm_struct *mm, pmd_t *pmd, unsigned long address));
 extern int install_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot);
 extern int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long pgoff, pgprot_t prot);
-extern int handle_mm_fault(struct mm_struct *mm,struct vm_area_struct *vma, unsigned long address, int write_access);
+extern int __handle_mm_fault(struct mm_struct *mm,struct vm_area_struct *vma, unsigned long address, int write_access);
+
+static inline int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, int write_access)
+{
+	return __handle_mm_fault(mm, vma, address, write_access) & (~VM_FAULT_WRITE);
+}
+
 extern int make_pages_present(unsigned long addr, unsigned long end);
 extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write);
 void install_arg_page(struct vm_area_struct *, struct page *, unsigned long);