mm: numa: pte_numa() and pmd_numa()

Implement pte_numa and pmd_numa.

We must atomically set the numa bit and clear the present bit to
define a pte_numa or pmd_numa.

Once a pte or pmd has been set as pte_numa or pmd_numa, the next time
a thread touches a virtual address in the corresponding virtual range,
a NUMA hinting page fault will trigger. The NUMA hinting page fault
will clear the NUMA bit and set the present bit again to resolve the
page fault.

The expectation is that a NUMA hinting page fault is used as part
of a placement policy that decides if a page should remain on the
current node or migrated to a different node.

Acked-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>

1 files changed, 37 insertions, 0 deletions

diff --git a/init/Kconfig b/init/Kconfig
index 6fdd6e339326..9f00f004796a 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -696,6 +696,43 @@ config LOG_BUF_SHIFT
 config HAVE_UNSTABLE_SCHED_CLOCK
         bool
 
+#
+# For architectures that want to enable the support for NUMA-affine scheduler
+# balancing logic:
+#
+config ARCH_SUPPORTS_NUMA_BALANCING
+        bool
+
+# For architectures that (ab)use NUMA to represent different memory regions
+# all cpu-local but of different latencies, such as SuperH.
+#
+config ARCH_WANT_NUMA_VARIABLE_LOCALITY
+        bool
+
+#
+# For architectures that are willing to define _PAGE_NUMA as _PAGE_PROTNONE
+config ARCH_WANTS_PROT_NUMA_PROT_NONE
+        bool
+
+config ARCH_USES_NUMA_PROT_NONE
+        bool
+        default y
+        depends on ARCH_WANTS_PROT_NUMA_PROT_NONE
+        depends on NUMA_BALANCING
+
+config NUMA_BALANCING
+        bool "Memory placement aware NUMA scheduler"
+        default y
+        depends on ARCH_SUPPORTS_NUMA_BALANCING
+        depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY
+        depends on SMP && NUMA && MIGRATION
+        help
+          This option adds support for automatic NUMA aware memory/task placement.
+          The mechanism is quite primitive and is based on migrating memory when
+          it is references to the node the task is running on.
+
+          This system will be inactive on UMA systems.
+
 menuconfig CGROUPS
         boolean "Control Group support"
         depends on EVENTFD