tools/vm/page-types.c: support KPF_SOFTDIRTY bit

Soft dirty bit allows us to track which pages are written since the last
clear_ref (by "echo 4 > /proc/pid/clear_refs".) This is useful for
userspace applications to know their memory footprints.

Note that the kernel exposes this flag via bit[55] of /proc/pid/pagemap,
and the semantics is not a default one (scheduled to be the default in the
near future.) However, it shifts to the new semantics at the first
clear_ref, and the users of soft dirty bit always do it before utilizing
the bit, so that's not a big deal.  Users must avoid relying on the bit in
page-types before the first clear_ref.

Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 1 insertions, 0 deletions

diff --git a/include/linux/kernel-page-flags.h b/include/linux/kernel-page-flags.h
index 546eb6a76934..f65ce09784f1 100644
--- a/include/linux/kernel-page-flags.h
+++ b/include/linux/kernel-page-flags.h
@@ -15,5 +15,6 @@
 #define KPF_OWNER_PRIVATE       37
 #define KPF_ARCH                38
 #define KPF_UNCACHED            39
+#define KPF_SOFTDIRTY           40
 
 #endif /* LINUX_KERNEL_PAGE_FLAGS_H */