tools/vm/page-types.c: support KPF_SOFTDIRTY bit
authorNaoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Tue, 12 Nov 2013 23:07:50 +0000 (15:07 -0800)
committerLinus Torvalds <torvalds@linux-foundation.org>
Wed, 13 Nov 2013 03:09:07 +0000 (12:09 +0900)
commit46c77e2bb07eba3b38edfec76873f12942c49dd3
tree2e6dd491627079f3e377e948f23137dd0c4cab40
parentec8e41aec13005fed0dbee002fb8c99b4e001d50
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>
include/linux/kernel-page-flags.h
tools/vm/page-types.c