The MPOL_LOCAL mode has been implemented by
Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
(commit: 479e2802d09f1e18a97262c4c6f8f17ae5884bd8).
Add the documentation for this mode.
Signed-off-by: Piotr Kwapulinski <kwapulinski.piotr@xxxxxxxxx>
---
Documentation/vm/numa_memory_policy.txt | 8 ++++++++
mm/mempolicy.c | 4 ++++
2 files changed, 12 insertions(+)
diff --git a/Documentation/vm/numa_memory_policy.txt b/Documentation/vm/numa_memory_policy.txt
index 622b927..dcb490e 100644
--- a/Documentation/vm/numa_memory_policy.txt
+++ b/Documentation/vm/numa_memory_policy.txt
@@ -212,6 +212,14 @@ Components of Memory Policies
the temporary interleaved system default policy works in this
mode.
+ MPOL_LOCAL: This mode specifies "local allocation". It must be
+ used along with an empty nodemask. It acts like the MPOL_PREFERRED
+ mode specified with an empty nodemask. For details refer to
+ the MPOL_PREFERRED mode described above.
+
+ Internally, it is transformed into MPOL_PREFERRED mode with an
+ empty nodemask.
+
Linux memory policy supports the following optional mode flags:
MPOL_F_STATIC_NODES: This flag specifies that the nodemask passed by
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 2da72a5..02dc43e 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -35,6 +35,10 @@
* use the process policy. This is what Linux always did
* in a NUMA aware kernel and still does by, ahem, default.
*
+ * local "Local allocation". It acts like a special case of
+ * "preferred" memory policy: NUMA_NO_NODE (see above
+ * for details).
+ *
* The process policy is applied for most non interrupt memory allocations
* in that process' context. Interrupts ignore the policies and always
* try to allocate on the local CPU. The VMA policy is only applied for memory
--
2.10.0
--
To unsubscribe from this list: send the line "unsubscribe linux-api" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
