metag: Inhibit NUMA balancing.

The metag NUMA implementation follows the SH model, using different nodes for
memories with different latencies. As such, we ensure that automated balancing
between nodes is inhibited, by way of the new ARCH_WANT_VARIABLE_LOCALITY.

Signed-off-by: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: James Hogan <james.hogan@imgtec.com>

diff --git a/arch/metag/mm/Kconfig b/arch/metag/mm/Kconfig
index cd7f2f2ad416b9bf91fd7206c29117f753d1041f..975f2f4e3ecf55f17521a3605c883bfd434fe554 100644 (file)
--- a/arch/metag/mm/Kconfig
+++ b/arch/metag/mm/Kconfig
@@ -40,6 +40,7 @@ endchoice
 
 config NUMA
        bool "Non Uniform Memory Access (NUMA) Support"
+       select ARCH_WANT_NUMA_VARIABLE_LOCALITY
        help
          Some Meta systems have MMU-mappable on-chip memories with
          lower latencies than main memory. This enables support for