On Sat, Jun 30, 2012 at 12:58:25AM -0400, Konrad Rzeszutek Wilk wrote:

On Thu, Jun 28, 2012 at 02:55:51PM +0200, Andrea Arcangeli wrote:

quoted

These flags are the ones tweaked through sysfs, they control the
behavior of autonuma, from enabling disabling it, to selecting various
runtime options.

Signed-off-by: Andrea Arcangeli <redacted>
---
 include/linux/autonuma_flags.h |   62 ++++++++++++++++++++++++++++++++++++++++
 1 files changed, 62 insertions(+), 0 deletions(-)
 create mode 100644 include/linux/autonuma_flags.h

diff --git a/include/linux/autonuma_flags.h b/include/linux/autonuma_flags.h
new file mode 100644
index 0000000..5e29a75
--- /dev/null
+++ b/include/linux/autonuma_flags.h

@@ -0,0 +1,62 @@
+#ifndef _LINUX_AUTONUMA_FLAGS_H
+#define _LINUX_AUTONUMA_FLAGS_H
+
+enum autonuma_flag {

These aren't really flags. They are bit-fields.
A

quoted

+	AUTONUMA_FLAG,

Looking at the code, this is to turn it on. Perhaps a better name such
as: AUTONUMA_ACTIVE_FLAG ?

quoted

+	AUTONUMA_IMPOSSIBLE_FLAG,
+	AUTONUMA_DEBUG_FLAG,
+	AUTONUMA_SCHED_LOAD_BALANCE_STRICT_FLAG,

I might have gotten my math wrong, but if you have
AUTONUMA_SCHED_LOAD_BALACE.. set (so 3), that also means
that bit 0 and 1 are on. In other words AUTONUMA_FLAG
and AUTONUMA_IMPOSSIBLE_FLAG are turned on.

quoted

+	AUTONUMA_SCHED_CLONE_RESET_FLAG,
+	AUTONUMA_SCHED_FORK_RESET_FLAG,
+	AUTONUMA_SCAN_PMD_FLAG,

So this is 6, which means 110 bits. So AUTONUMA_FLAG
gets turned off.

Ignore that pls. I had in my mind that test_bit was doing boolean logic (anding and masking,
and such), but that is not the case.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>