mm: softdirty: keep bit when zapping file pte

This fixes the same bug as b43790eedd ("mm: softdirty: don't forget to
save file map softdiry bit on unmap") and 9aed8614af ("mm/memory.c:
don't forget to set softdirty on file mapped fault") where the return
value of pte_*mksoft_dirty was being ignored.

To be sure that no other pte/pmd "mk" function return values were being
ignored, I annotated the functions in arch/x86/include/asm/pgtable.h
with __must_check and rebuilt.

The userspace effect of this bug is that the softdirty mark might be
lost if a file mapped pte get zapped.

Signed-off-by: Peter Feiner <pfeiner@google.com>
Acked-by: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Jamie Liu <jamieliu@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: <stable@vger.kernel.org>	[3.12+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Peter Feiner 2014-09-25 16:05:29 -07:00 committed by Linus Torvalds
parent 6ff66ac77a
commit dbab31aa2c

View File

@ -1127,7 +1127,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
addr) != page->index) {
pte_t ptfile = pgoff_to_pte(page->index);
if (pte_soft_dirty(ptent))
pte_file_mksoft_dirty(ptfile);
ptfile = pte_file_mksoft_dirty(ptfile);
set_pte_at(mm, addr, pte, ptfile);
}
if (PageAnon(page))