Merge tag 'topic-numa-20160122.0' into leg-kernel

34 files changed, 2319 insertions, 109 deletions

diff --git a/Documentation/devicetree/bindings/arm/numa.txt b/Documentation/devicetree/bindings/arm/numa.txt
new file mode 100644
index 000000000000..734e5b423056
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/numa.txt
@@ -0,0 +1,272 @@
+==============================================================================
+NUMA binding description.
+==============================================================================
+
+==============================================================================
+1 - Introduction
+==============================================================================
+
+Systems employing a Non Uniform Memory Access (NUMA) architecture contain
+collections of hardware resources including processors, memory, and I/O buses,
+that comprise what is commonly known as a NUMA node.
+Processor accesses to memory within the local NUMA node is generally faster
+than processor accesses to memory outside of the local NUMA node.
+DT defines interfaces that allow the platform to convey NUMA node
+topology information to OS.
+
+==============================================================================
+2 - numa-node-id
+==============================================================================
+
+For the purpose of identification, each NUMA node is associated with a unique
+token known as a node id. For the purpose of this binding
+a node id is a 32-bit integer.
+
+A device node is associated with a NUMA node by the presence of a
+numa-node-id property which contains the node id of the device.
+
+Example:
+	/* numa node 0 */
+	numa-node-id = <0>;
+
+	/* numa node 1 */
+	numa-node-id = <1>;
+
+==============================================================================
+3 - distance-map
+==============================================================================
+
+The device tree node distance-map describes the relative
+distance (memory latency) between all numa nodes.
+
+- compatible : Should at least contain "numa-distance-map-v1".
+
+- distance-matrix
+  This property defines a matrix to describe the relative distances
+  between all numa nodes.
+  It is represented as a list of node pairs and their relative distance.
+
+  Note:
+	1. Each entry represents distance from first node to second node.
+	The distances are equal in either direction.
+	2. The distance from a node to self (local distance) is represented
+	with value 10 and all internode distance should be represented with
+	a value greater than 10.
+	3. distance-matrix should have entries in lexicographical ascending
+	order of nodes.
+	4. There must be only one device node distance-map which must reside in the root node.
+
+Example:
+	4 nodes connected in mesh/ring topology as below,
+
+		0_______20______1
+		|               |
+		|               |
+		20             20
+		|               |
+		|               |
+		|_______________|
+		3       20      2
+
+	if relative distance for each hop is 20,
+	then internode distance would be,
+	      0 -> 1 = 20
+	      1 -> 2 = 20
+	      2 -> 3 = 20
+	      3 -> 0 = 20
+	      0 -> 2 = 40
+	      1 -> 3 = 40
+
+     and dt presentation for this distance matrix is,
+
+		distance-map {
+			 compatible = "numa-distance-map-v1";
+			 distance-matrix = <0 0  10>,
+					   <0 1  20>,
+					   <0 2  40>,
+					   <0 3  20>,
+					   <1 0  20>,
+					   <1 1  10>,
+					   <1 2  20>,
+					   <1 3  40>,
+					   <2 0  40>,
+					   <2 1  20>,
+					   <2 2  10>,
+					   <2 3  20>,
+					   <3 0  20>,
+					   <3 1  40>,
+					   <3 2  20>,
+					   <3 3  10>;
+		};
+
+==============================================================================
+4 - Example dts
+==============================================================================
+
+2 sockets system consists of 2 boards connected through ccn bus and
+each board having one socket/soc of 8 cpus, memory and pci bus.
+
+	memory@00c00000 {
+		device_type = "memory";
+		reg = <0x0 0x00c00000 0x0 0x80000000>;
+		/* node 0 */
+		numa-node-id = <0>;
+	};
+
+	memory@10000000000 {
+		device_type = "memory";
+		reg = <0x100 0x00000000 0x0 0x80000000>;
+		/* node 1 */
+		numa-node-id = <1>;
+	};
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		cpu@000 {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x000>;
+			enable-method = "psci";
+			/* node 0 */
+			numa-node-id = <0>;
+		};
+		cpu@001 {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x001>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@002 {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x002>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@003 {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x003>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@004 {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x004>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@005 {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x005>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@006 {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x006>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@007 {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x007>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@008 {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x008>;
+			enable-method = "psci";
+			/* node 1 */
+			numa-node-id = <1>;
+		};
+		cpu@009 {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x009>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@00a {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x00a>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@00b {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x00b>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@00c {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x00c>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@00d {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x00d>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@00e {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x00e>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@00f {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x00f>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+	};
+
+	pcie0: pcie0@0x8480,00000000 {
+		compatible = "arm,armv8";
+		device_type = "pci";
+		bus-range = <0 255>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		reg = <0x8480 0x00000000 0 0x10000000>;  /* Configuration space */
+		ranges = <0x03000000 0x8010 0x00000000 0x8010 0x00000000 0x70 0x00000000>;
+		/* node 0 */
+		numa-node-id = <0>;
+        };
+
+	pcie1: pcie1@0x9480,00000000 {
+		compatible = "arm,armv8";
+		device_type = "pci";
+		bus-range = <0 255>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		reg = <0x9480 0x00000000 0 0x10000000>;  /* Configuration space */
+		ranges = <0x03000000 0x9010 0x00000000 0x9010 0x00000000 0x70 0x00000000>;
+		/* node 1 */
+		numa-node-id = <1>;
+        };
+
+	distance-map {
+		compatible = "numa-distance-map-v1";
+		distance-matrix = <0 0 10>,
+				  <0 1 20>,
+				  <1 1 10>;
+	};
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 573bebcb93e4..4e7d0e9e5014 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -72,6 +72,7 @@ config ARM64
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS
 	select HAVE_MEMBLOCK
+	select HAVE_MEMBLOCK_NODE_MAP if NUMA
 	select HAVE_PATA_PLATFORM
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
@@ -510,6 +511,40 @@ config HOTPLUG_CPU
 	  Say Y here to experiment with turning CPUs off and on.  CPUs
 	  can be controlled through /sys/devices/system/cpu.
 
+# Common NUMA Features
+config NUMA
+	bool "Numa Memory Allocation and Scheduler Support"
+	depends on SMP
+	help
+	  Enable NUMA (Non Uniform Memory Access) support.
+
+	  The kernel will try to allocate memory used by a CPU on the
+	  local memory of the CPU and add some more
+	  NUMA awareness to the kernel.
+
+config OF_NUMA
+	bool "Device Tree NUMA support"
+	depends on NUMA
+	depends on OF
+	default y
+	help
+	  Enable Device Tree NUMA support.
+	  This enables the numa mapping of cpu, memory, io and
+	  inter node distances using dt bindings.
+
+config NODES_SHIFT
+	int "Maximum NUMA Nodes (as a power of 2)"
+	range 1 10
+	default "2"
+	depends on NEED_MULTIPLE_NODES
+	help
+	  Specify the maximum number of NUMA Nodes available on the target
+	  system.  Increases memory reserved to accommodate various tables.
+
+config USE_PERCPU_NUMA_NODE_ID
+	def_bool y
+	depends on NUMA
+
 source kernel/Kconfig.preempt
 source kernel/Kconfig.hz
 
diff --git a/arch/arm64/boot/dts/cavium/Makefile b/arch/arm64/boot/dts/cavium/Makefile
index e34f89ddabb2..7fe70672d866 100644
--- a/arch/arm64/boot/dts/cavium/Makefile
+++ b/arch/arm64/boot/dts/cavium/Makefile
@@ -1,4 +1,4 @@
-dtb-$(CONFIG_ARCH_THUNDER) += thunder-88xx.dtb
+dtb-$(CONFIG_ARCH_THUNDER) += thunder-88xx.dtb thunder-88xx-2n.dtb
 
 always		:= $(dtb-y)
 subdir-y	:= $(dts-dirs)
diff --git a/arch/arm64/boot/dts/cavium/thunder-88xx-2n.dts b/arch/arm64/boot/dts/cavium/thunder-88xx-2n.dts
new file mode 100644
index 000000000000..5601e87102d8
--- /dev/null
+++ b/arch/arm64/boot/dts/cavium/thunder-88xx-2n.dts
@@ -0,0 +1,83 @@
+/*
+ * Cavium Thunder DTS file - Thunder board description
+ *
+ * Copyright (C) 2014, Cavium Inc.
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This library is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This library is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *     You should have received a copy of the GNU General Public
+ *     License along with this library; if not, write to the Free
+ *     Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston,
+ *     MA 02110-1301 USA
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+
+/include/ "thunder-88xx-2n.dtsi"
+
+/ {
+	model = "Cavium ThunderX CN88XX board";
+	compatible = "cavium,thunder-88xx";
+
+	aliases {
+		serial0 = &uaa0;
+		serial1 = &uaa1;
+	};
+
+	memory@00000000 {
+		device_type = "memory";
+		reg = <0x0 0x01400000 0x3 0xFEC00000>;
+		/* socket 0 */
+		numa-node-id = <0>;
+	};
+
+	memory@10000000000 {
+		device_type = "memory";
+		reg = <0x100 0x00400000 0x3 0xFFC00000>;
+		 /* socket 1 */
+		numa-node-id = <1>;
+	};
+
+	distance-map {
+		compatible = "numa-distance-map-v1";
+		distance-matrix = <0 0  10>,
+				  <0 1  20>,
+				  <1 1  10>;
+	};
+};
diff --git a/arch/arm64/boot/dts/cavium/thunder-88xx-2n.dtsi b/arch/arm64/boot/dts/cavium/thunder-88xx-2n.dtsi
new file mode 100644
index 000000000000..b58e5c764d84
--- /dev/null
+++ b/arch/arm64/boot/dts/cavium/thunder-88xx-2n.dtsi
@@ -0,0 +1,806 @@
+/*
+ * Cavium Thunder DTS file - Thunder SoC description
+ *
+ * Copyright (C) 2014, Cavium Inc.
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This library is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This library is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *     You should have received a copy of the GNU General Public
+ *     License along with this library; if not, write to the Free
+ *     Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston,
+ *     MA 02110-1301 USA
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/ {
+	compatible = "cavium,thunder-88xx";
+	interrupt-parent = <&gic0>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	psci {
+		compatible = "arm,psci-0.2";
+		method = "smc";
+	};
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		cpu@000 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x000>;
+			enable-method = "psci";
+			/* socket 0 */
+			numa-node-id = <0>;
+		};
+		cpu@001 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x001>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@002 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x002>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@003 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x003>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@004 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x004>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@005 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x005>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@006 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x006>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@007 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x007>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@008 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x008>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@009 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x009>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@00a {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x00a>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@00b {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x00b>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@00c {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x00c>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@00d {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x00d>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@00e {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x00e>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@00f {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x00f>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@100 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x100>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@101 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x101>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@102 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x102>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@103 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x103>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@104 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x104>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@105 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x105>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@106 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x106>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@107 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x107>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@108 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x108>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@109 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x109>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@10a {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10a>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@10b {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10b>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@10c {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10c>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@10d {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10d>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@10e {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10e>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@10f {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10f>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@200 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x200>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@201 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x201>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@202 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x202>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@203 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x203>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@204 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x204>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@205 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x205>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@206 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x206>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@207 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x207>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@208 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x208>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@209 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x209>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@20a {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x20a>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@20b {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x20b>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@20c {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x20c>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@20d {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x20d>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@20e {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x20e>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@20f {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x20f>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@10000 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10000>;
+			enable-method = "psci";
+			/* socket 1 */
+			numa-node-id = <1>;
+		};
+		cpu@10001 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10001>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10002 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10002>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10003 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10003>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10004 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10004>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10005 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10005>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10006 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10006>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10007 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10007>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10008 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10008>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10009 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10009>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@1000a {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x1000a>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@1000b {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x1000b>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@1000c {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x1000c>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@1000d {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x1000d>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@1000e {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x1000e>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@1000f {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x1000f>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10100 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10100>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10101 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10101>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10102 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10102>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10103 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10103>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10104 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10104>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10105 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10105>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10106 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10106>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10107 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10107>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10108 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10108>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10109 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10109>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@1010a {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x1010a>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@1010b {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x1010b>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@1010c {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x1010c>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@1010d {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x1010d>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@1010e {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x1010e>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@1010f {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x1010f>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10200 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10200>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10201 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10201>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10202 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10202>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10203 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10203>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10204 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10204>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10205 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10205>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10206 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10206>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10207 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10207>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10208 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10208>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@10209 {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x10209>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@1020a {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x1020a>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@1020b {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x1020b>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@1020c {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x1020c>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@1020d {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x1020d>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@1020e {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x1020e>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@1020f {
+			device_type = "cpu";
+			compatible = "cavium,thunder", "arm,armv8";
+			reg = <0x0 0x1020f>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <1 13 0xff01>,
+		             <1 14 0xff01>,
+		             <1 11 0xff01>,
+		             <1 10 0xff01>;
+	};
+
+	soc {
+		compatible = "simple-bus";
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		refclk50mhz: refclk50mhz {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <50000000>;
+			clock-output-names = "refclk50mhz";
+		};
+
+		gic0: interrupt-controller@8010,00000000 {
+			compatible = "arm,gic-v3";
+			#interrupt-cells = <3>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			#redistributor-regions = <2>;
+			ranges;
+			interrupt-controller;
+			reg = <0x8010 0x00000000 0x0 0x010000>, /* GICD */
+			      <0x8010 0x80000000 0x0 0x600000>, /* GICR Node 0 */
+			      <0x9010 0x80000000 0x0 0x600000>; /* GICR Node 1 */
+			interrupts = <1 9 0xf04>;
+
+			its: gic-its@8010,00020000 {
+				compatible = "arm,gic-v3-its";
+				msi-controller;
+				reg = <0x8010 0x20000 0x0 0x200000>;
+				numa-node-id = <0>;
+			};
+
+			its1: gic-its@9010,00020000 {
+				compatible = "arm,gic-v3-its";
+				msi-controller;
+				reg = <0x9010 0x20000 0x0 0x200000>;
+				numa-node-id = <1>;
+			};
+		};
+
+		uaa0: serial@87e0,24000000 {
+			compatible = "arm,pl011", "arm,primecell";
+			reg = <0x87e0 0x24000000 0x0 0x1000>;
+			interrupts = <1 21 4>;
+			clocks = <&refclk50mhz>;
+			clock-names = "apb_pclk";
+		};
+
+		uaa1: serial@87e0,25000000 {
+			compatible = "arm,pl011", "arm,primecell";
+			reg = <0x87e0 0x25000000 0x0 0x1000>;
+			interrupts = <1 22 4>;
+			clocks = <&refclk50mhz>;
+			clock-names = "apb_pclk";
+		};
+	};
+};
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index caafd63b8092..6db9c6ff53fb 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -96,4 +96,12 @@ static inline const char *acpi_get_enable_method(int cpu)
 pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr);
 #endif
 
+#ifdef CONFIG_ACPI_NUMA
+int arm64_acpi_numa_init(void);
+void acpi_numa_set_node_info(unsigned int cpu, u64 hwid);
+#else
+static inline int arm64_acpi_numa_init(void) { return -ENODEV; }
+static inline void acpi_numa_set_node_info(unsigned int cpu, u64 hwid) { }
+#endif /* CONFIG_ACPI_NUMA */
+
 #endif /*_ASM_ACPI_H*/
diff --git a/arch/arm64/include/asm/mmzone.h b/arch/arm64/include/asm/mmzone.h
new file mode 100644
index 000000000000..2cd804d8159e
--- /dev/null
+++ b/arch/arm64/include/asm/mmzone.h
@@ -0,0 +1,18 @@
+#ifndef __ASM_MMZONE_H
+#define __ASM_MMZONE_H
+
+#ifdef CONFIG_NUMA
+
+#include <linux/mmdebug.h>
+#include <linux/types.h>
+
+#include <asm/smp.h>
+#include <asm/numa.h>
+
+extern struct pglist_data *node_data[];
+
+#define NODE_DATA(nid)		(node_data[(nid)])
+
+#endif /* CONFIG_NUMA */
+
+#endif /* __ASM_MMZONE_H */
diff --git a/arch/arm64/include/asm/numa.h b/arch/arm64/include/asm/numa.h
new file mode 100644
index 000000000000..1beb194ea136
--- /dev/null
+++ b/arch/arm64/include/asm/numa.h
@@ -0,0 +1,53 @@
+#ifndef __ASM_NUMA_H
+#define __ASM_NUMA_H
+
+#include <linux/nodemask.h>
+#include <asm/topology.h>
+
+#ifdef CONFIG_NUMA
+
+#define NR_NODE_MEMBLKS		(MAX_NUMNODES * 2)
+
+/* currently, arm64 implements flat NUMA topology */
+#define parent_node(node)	(node)
+
+extern int __node_distance(int from, int to);
+#define node_distance(a, b) __node_distance(a, b)
+
+extern int cpu_to_node_map[NR_CPUS];
+extern nodemask_t numa_nodes_parsed __initdata;
+
+/* Mappings between node number and cpus on that node. */
+extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+extern void numa_clear_node(unsigned int cpu);
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+extern const struct cpumask *cpumask_of_node(int node);
+#else
+/* Returns a pointer to the cpumask of CPUs on Node 'node'. */
+static inline const struct cpumask *cpumask_of_node(int node)
+{
+	return node_to_cpumask_map[node];
+}
+#endif
+
+void __init arm64_numa_init(void);
+int __init numa_add_memblk(int nodeid, u64 start, u64 end);
+void __init numa_set_distance(int from, int to, int distance);
+void __init numa_reset_distance(void);
+void numa_store_cpu_info(unsigned int cpu);
+#else	/* CONFIG_NUMA */
+static inline void numa_store_cpu_info(unsigned int cpu)		{ }
+static inline void arm64_numa_init(void)		{ }
+#endif	/* CONFIG_NUMA */
+
+struct device_node;
+#ifdef CONFIG_OF_NUMA
+int __init arm64_of_numa_init(void);
+void __init of_numa_set_node_info(unsigned int cpu, struct device_node *dn);
+#else
+static inline int arm64_of_numa_init(void) { return -ENODEV; }
+static inline void of_numa_set_node_info(unsigned int cpu,
+		struct device_node *dn) { }
+#endif
+
+#endif	/* __ASM_NUMA_H */
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index a3e9d6fdbf21..6e1f62c0569f 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -22,6 +22,13 @@ void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
 const struct cpumask *cpu_coregroup_mask(int cpu);
 
+#ifdef CONFIG_NUMA
+
+struct pci_bus;
+int pcibus_to_node(struct pci_bus *bus);
+
+#endif /* CONFIG_NUMA */
+
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_ARM_TOPOLOGY_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 474691f8b13a..555c4a584f40 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -41,6 +41,8 @@ arm64-obj-$(CONFIG_EFI)			+= efi.o efi-entry.stub.o
 arm64-obj-$(CONFIG_PCI)			+= pci.o
 arm64-obj-$(CONFIG_ARMV8_DEPRECATED)	+= armv8_deprecated.o
 arm64-obj-$(CONFIG_ACPI)		+= acpi.o
+arm64-obj-$(CONFIG_OF_NUMA)		+= of_numa.o
+arm64-obj-$(CONFIG_ACPI_NUMA)		+= acpi_numa.o
 
 obj-y					+= $(arm64-obj-y) vdso/
 obj-m					+= $(arm64-obj-m)
diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c
new file mode 100644
index 000000000000..15fb935d9d91
--- /dev/null
+++ b/arch/arm64/kernel/acpi_numa.c
@@ -0,0 +1,204 @@
+/*
+ * ACPI 5.1 based NUMA setup for ARM64
+ * Lots of code was borrowed from arch/x86/mm/srat.c
+ *
+ * Copyright 2004 Andi Kleen, SuSE Labs.
+ * Copyright (C) 2013-2016, Linaro Ltd.
+ *		Author: Hanjun Guo <hanjun.guo@linaro.org>
+ *
+ * Reads the ACPI SRAT table to figure out what memory belongs to which CPUs.
+ *
+ * Called from acpi_numa_init while reading the SRAT and SLIT tables.
+ * Assumes all memory regions belonging to a single proximity domain
+ * are in one chunk. Holes between them will be included in the node.
+ */
+
+#define pr_fmt(fmt) "ACPI: NUMA: " fmt
+
+#include <linux/acpi.h>
+#include <linux/bitmap.h>
+#include <linux/bootmem.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/memblock.h>
+#include <linux/mmzone.h>
+#include <linux/module.h>
+#include <linux/topology.h>
+
+#include <acpi/processor.h>
+#include <asm/numa.h>
+
+int acpi_numa __initdata;
+static int cpus_in_srat;
+
+struct __node_cpu_hwid {
+	u32 node_id;    /* logical node containing this CPU */
+	u64 cpu_hwid;   /* MPIDR for this CPU */
+};
+
+static struct __node_cpu_hwid early_node_cpu_hwid[NR_CPUS] = {
+[0 ... NR_CPUS - 1] = {NUMA_NO_NODE, PHYS_CPUID_INVALID} };
+
+static __init void bad_srat(void)
+{
+	pr_err("SRAT not used.\n");
+	acpi_numa = -1;
+}
+
+static __init inline int srat_disabled(void)
+{
+	return acpi_numa < 0;
+}
+
+void __init acpi_numa_set_node_info(unsigned int cpu, u64 hwid)
+{
+	int nid = 0, i;
+
+	for (i = 0; i < cpus_in_srat; i++) {
+		if (hwid == early_node_cpu_hwid[i].cpu_hwid) {
+			nid = early_node_cpu_hwid[i].node_id;
+			break;
+		}
+	}
+
+	cpu_to_node_map[cpu] = nid;
+}
+
+static int __init get_mpidr_in_madt(int acpi_id, u64 *mpidr)
+{
+	unsigned long madt_end, entry;
+	struct acpi_table_madt *madt;
+	acpi_size tbl_size;
+
+	if (ACPI_FAILURE(acpi_get_table_with_size(ACPI_SIG_MADT, 0,
+			(struct acpi_table_header **)&madt, &tbl_size)))
+		return -ENODEV;
+
+	entry = (unsigned long)madt;
+	madt_end = entry + madt->header.length;
+
+	/* Parse all entries looking for a match. */
+	entry += sizeof(struct acpi_table_madt);
+	while (entry + sizeof(struct acpi_subtable_header) < madt_end) {
+		struct acpi_subtable_header *header =
+			(struct acpi_subtable_header *)entry;
+
+		if (header->type == ACPI_MADT_TYPE_GENERIC_INTERRUPT) {
+			struct acpi_madt_generic_interrupt *gicc =
+				container_of(header,
+				struct acpi_madt_generic_interrupt, header);
+
+			if ((gicc->flags & ACPI_MADT_ENABLED) &&
+			    (gicc->uid == acpi_id)) {
+				*mpidr = gicc->arm_mpidr;
+				early_acpi_os_unmap_memory(madt, tbl_size);
+				return 0;
+			}
+		}
+		entry += header->length;
+	}
+
+	early_acpi_os_unmap_memory(madt, tbl_size);
+	return -ENODEV;
+}
+
+/* Callback for Proximity Domain -> ACPI processor UID mapping */
+void __init acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa)
+{
+	int pxm, node;
+	u64 mpidr;
+
+	if (srat_disabled())
+		return;
+
+	if (pa->header.length < sizeof(struct acpi_srat_gicc_affinity)) {
+		bad_srat();
+		return;
+	}
+
+	if (!(pa->flags & ACPI_SRAT_GICC_ENABLED))
+		return;
+
+	if (cpus_in_srat >= NR_CPUS) {
+		pr_warn_once("SRAT: cpu_to_node_map[%d] is too small, may not be able to use all cpus\n",
+			     NR_CPUS);
+		return;
+	}
+
+	pxm = pa->proximity_domain;
+	node = acpi_map_pxm_to_node(pxm);
+
+	if (node == NUMA_NO_NODE || node >= MAX_NUMNODES) {
+		pr_err("SRAT: Too many proximity domains %d\n", pxm);
+		bad_srat();
+		return;
+	}
+
+	if (get_mpidr_in_madt(pa->acpi_processor_uid, &mpidr)) {
+		pr_warn("SRAT: PXM %d with ACPI ID %d has no valid MPIDR in MADT\n",
+			pxm, pa->acpi_processor_uid);
+		bad_srat();
+		return;
+	}
+
+	early_node_cpu_hwid[cpus_in_srat].node_id = node;
+	early_node_cpu_hwid[cpus_in_srat].cpu_hwid =  mpidr;
+	node_set(node, numa_nodes_parsed);
+	acpi_numa = 1;
+	cpus_in_srat++;
+	pr_info("SRAT: PXM %d -> MPIDR 0x%Lx -> Node %d cpu %d\n",
+		pxm, mpidr, node, cpus_in_srat);
+}
+
+/* Callback for parsing of the Proximity Domain <-> Memory Area mappings */
+int __init acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
+{
+	u64 start, end;
+	int node, pxm;
+
+	if (srat_disabled())
+		return -EINVAL;
+
+	if (ma->header.length != sizeof(struct acpi_srat_mem_affinity)) {
+		bad_srat();
+		return -EINVAL;
+	}
+
+	/* Ignore disabled entries */
+	if (!(ma->flags & ACPI_SRAT_MEM_ENABLED))
+		return -EINVAL;
+
+	start = ma->base_address;
+	end = start + ma->length;
+	pxm = ma->proximity_domain;
+
+	node = acpi_map_pxm_to_node(pxm);
+
+	if (node == NUMA_NO_NODE || node >= MAX_NUMNODES) {
+		pr_err("SRAT: Too many proximity domains.\n");
+		bad_srat();
+		return -EINVAL;
+	}
+
+	pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n",
+		node, pxm,
+		(unsigned long long) start, (unsigned long long) end - 1);
+
+	if (numa_add_memblk(node, start, (end - start)) < 0) {
+		bad_srat();
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int __init arm64_acpi_numa_init(void)
+{
+	int ret;
+
+	ret = acpi_numa_init();
+	if (ret)
+		return ret;
+
+	return srat_disabled() ? -EINVAL : 0;
+}
diff --git a/arch/arm64/kernel/of_numa.c b/arch/arm64/kernel/of_numa.c
new file mode 100644
index 000000000000..2f9e34bea230
--- /dev/null
+++ b/arch/arm64/kernel/of_numa.c
@@ -0,0 +1,257 @@
+/*
+ * OF NUMA Parsing support.
+ *
+ * Copyright (C) 2015 Cavium Inc.
+ * Author: Ganapatrao Kulkarni <gkulkarni@cavium.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/ctype.h>
+#include <linux/memblock.h>
+#include <linux/module.h>
+#include <linux/nodemask.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+
+#include <asm/smp_plat.h>
+
+/* define default numa node to 0 */
+#define DEFAULT_NODE 0
+#define OF_NUMA_PROP "numa-node-id"
+
+/* Returns nid in the range [0..MAX_NUMNODES-1],
+ * or NUMA_NO_NODE if no valid numa-node-id entry found
+ * or DEFAULT_NODE if no numa-node-id entry exists
+ */
+static int of_numa_prop_to_nid(const __be32 *of_numa_prop, int length)
+{
+	int nid;
+
+	if (!of_numa_prop)
+		return DEFAULT_NODE;
+
+	if (length != sizeof(*of_numa_prop)) {
+		pr_warn("NUMA: Invalid of_numa_prop length %d found.\n",
+				length);
+		return NUMA_NO_NODE;
+	}
+
+	nid = of_read_number(of_numa_prop, 1);
+	if (nid >= MAX_NUMNODES) {
+		pr_warn("NUMA: Invalid numa node %d found.\n", nid);
+		return NUMA_NO_NODE;
+	}
+
+	return nid;
+}
+
+/* Must hold reference to node during call */
+static int of_get_numa_nid(struct device_node *device)
+{
+	int length;
+	const __be32 *of_numa_prop;
+
+	of_numa_prop = of_get_property(device, OF_NUMA_PROP, &length);
+
+	return of_numa_prop_to_nid(of_numa_prop, length);
+}
+
+static int __init early_init_of_get_numa_nid(unsigned long node)
+{
+	int length;
+	const __be32 *of_numa_prop;
+
+	of_numa_prop = of_get_flat_dt_prop(node, OF_NUMA_PROP, &length);
+
+	return of_numa_prop_to_nid(of_numa_prop, length);
+}
+
+/* Walk the device tree upwards, looking for a numa-node-id property */
+int of_node_to_nid(struct device_node *device)
+{
+	struct device_node *parent;
+	int nid = NUMA_NO_NODE;
+
+	of_node_get(device);
+	while (device) {
+		const __be32 *of_numa_prop;
+		int length;
+
+		of_numa_prop = of_get_property(device, OF_NUMA_PROP, &length);
+		if (of_numa_prop) {
+			nid = of_numa_prop_to_nid(of_numa_prop, length);
+			break;
+		}
+
+		parent = device;
+		device = of_get_parent(parent);
+		of_node_put(parent);
+	}
+	of_node_put(device);
+
+	return nid;
+}
+
+void __init of_numa_set_node_info(unsigned int cpu, struct device_node *device)
+{
+	int nid = DEFAULT_NODE;
+
+	if (device)
+		nid = of_get_numa_nid(device);
+
+	cpu_to_node_map[cpu] = nid;
+}
+
+/*
+ * Even though we connect cpus to numa domains later in SMP
+ * init, we need to know the node ids now for all cpus.
+*/
+static int __init early_init_parse_cpu_node(unsigned long node)
+{
+	int nid;
+
+	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+
+	/* We are scanning "cpu" nodes only */
+	if (type == NULL)
+		return 0;
+	else if (strcmp(type, "cpu") != 0)
+		return 0;
+
+	nid = early_init_of_get_numa_nid(node);
+
+	if (nid == NUMA_NO_NODE)
+		return -EINVAL;
+
+	node_set(nid, numa_nodes_parsed);
+	return 0;
+}
+
+static int __init early_init_parse_memory_node(unsigned long node)
+{
+	const __be32 *reg, *endp;
+	int length;
+	int nid;
+
+	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+
+	/* We are scanning "memory" nodes only */
+	if (type == NULL)
+		return 0;
+	else if (strcmp(type, "memory") != 0)
+		return 0;
+
+	nid = early_init_of_get_numa_nid(node);
+
+	if (nid == NUMA_NO_NODE)
+		return -EINVAL;
+
+	reg = of_get_flat_dt_prop(node, "reg", &length);
+	endp = reg + (length / sizeof(__be32));
+
+	while ((endp - reg) >= (dt_root_addr_cells + dt_root_size_cells)) {
+		u64 base, size;
+
+		base = dt_mem_next_cell(dt_root_addr_cells, &reg);
+		size = dt_mem_next_cell(dt_root_size_cells, &reg);
+		pr_debug("NUMA-DT:  base = %llx , node = %u\n",
+				base, nid);
+
+		if (numa_add_memblk(nid, base, size) < 0)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int __init early_init_parse_distance_map_v1(unsigned long node,
+		const char *uname)
+{
+
+	const __be32 *prop_dist_matrix;
+	int length = 0, i, matrix_count;
+	int nr_size_cells = OF_ROOT_NODE_SIZE_CELLS_DEFAULT;
+
+	pr_info("NUMA: parsing numa-distance-map-v1\n");
+
+	prop_dist_matrix =
+		of_get_flat_dt_prop(node, "distance-matrix", &length);
+
+	if (!length) {
+		pr_err("NUMA: failed to parse distance-matrix\n");
+		return  -ENODEV;
+	}
+
+	matrix_count = ((length / sizeof(__be32)) / (3 * nr_size_cells));
+
+	if ((matrix_count * sizeof(__be32) * 3 * nr_size_cells) !=  length) {
+		pr_warn("NUMA: invalid distance-matrix length %d\n", length);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < matrix_count; i++) {
+		u32 nodea, nodeb, distance;
+
+		nodea = dt_mem_next_cell(nr_size_cells, &prop_dist_matrix);
+		nodeb = dt_mem_next_cell(nr_size_cells, &prop_dist_matrix);
+		distance = dt_mem_next_cell(nr_size_cells, &prop_dist_matrix);
+		numa_set_distance(nodea, nodeb, distance);
+		pr_debug("NUMA-DT:  distance[node%d -> node%d] = %d\n",
+				nodea, nodeb, distance);
+
+		/* Set default distance of node B->A same as A->B */
+		if (nodeb > nodea)
+			numa_set_distance(nodeb, nodea, distance);
+	}
+
+	return 0;
+}
+
+static int __init early_init_parse_distance_map(unsigned long node,
+		const char *uname)
+{
+
+	if (strcmp(uname, "distance-map") != 0)
+		return 0;
+
+	if (of_flat_dt_is_compatible(node, "numa-distance-map-v1"))
+		return early_init_parse_distance_map_v1(node, uname);
+
+	return -EINVAL;
+}
+
+/**
+ * early_init_of_scan_numa_map - parse memory node and map nid to memory range.
+ */
+int __init early_init_of_scan_numa_map(unsigned long node, const char *uname,
+				     int depth, void *data)
+{
+	int ret;
+
+	ret = early_init_parse_cpu_node(node);
+
+	if (!ret)
+		ret = early_init_parse_memory_node(node);
+
+	if (!ret)
+		ret = early_init_parse_distance_map(node, uname);
+
+	return ret;
+}
+
+/* DT node mapping is done already early_init_of_scan_memory */
+int __init arm64_of_numa_init(void)
+{
+	return of_scan_flat_dt(early_init_of_scan_numa_map, NULL);
+}
diff --git a/arch/arm64/kernel/pci.c b/arch/arm64/kernel/pci.c
index a0929a6163f6..329ca81242a1 100644
--- a/arch/arm64/kernel/pci.c
+++ b/arch/arm64/kernel/pci.c
@@ -59,3 +59,12 @@ int pcibios_add_device(struct pci_dev *dev)
 
 	return 0;
 }
+
+#ifdef CONFIG_NUMA
+int pcibus_to_node(struct pci_bus *bus)
+{
+	return dev_to_node(&bus->dev);
+}
+EXPORT_SYMBOL(pcibus_to_node);
+#endif
+
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 8119479147db..d9b9761e9f60 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -53,6 +53,7 @@
 #include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
 #include <asm/kasan.h>
+#include <asm/numa.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/smp_plat.h>
@@ -372,6 +373,9 @@ static int __init topology_init(void)
 {
 	int i;
 
+	for_each_online_node(i)
+		register_one_node(i);
+
 	for_each_possible_cpu(i) {
 		struct cpu *cpu = &per_cpu(cpu_data.cpu, i);
 		cpu->hotpluggable = 1;
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index b1adc51b2c2e..112a892e30df 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -45,6 +45,7 @@
 #include <asm/cputype.h>
 #include <asm/cpu_ops.h>
 #include <asm/mmu_context.h>
+#include <asm/numa.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/processor.h>
@@ -125,6 +126,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 static void smp_store_cpu_info(unsigned int cpuid)
 {
 	store_cpu_topology(cpuid);
+	numa_store_cpu_info(cpuid);
 }
 
 /*
@@ -445,6 +447,9 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
 	/* map the logical cpu id to cpu MPIDR */
 	cpu_logical_map(cpu_count) = hwid;
 
+	/* map logical cpu to node */
+	acpi_numa_set_node_info(cpu_count, hwid);
+
 	cpu_count++;
 }
 
@@ -518,6 +523,8 @@ static void __init of_parse_and_init_cpus(void)
 
 		pr_debug("cpu logical map 0x%llx\n", hwid);
 		cpu_logical_map(cpu_count) = hwid;
+		/* map logical cpu to node */
+		of_numa_set_node_info(cpu_count, dn);
 next:
 		cpu_count++;
 	}
diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile
index 57f57fde5722..54bb209cae8e 100644
--- a/arch/arm64/mm/Makefile
+++ b/arch/arm64/mm/Makefile
@@ -4,6 +4,7 @@ obj-y				:= dma-mapping.o extable.o fault.o init.o \
 				   context.o proc.o pageattr.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_ARM64_PTDUMP)	+= dump.o
+obj-$(CONFIG_NUMA)		+= numa.o
 
 obj-$(CONFIG_KASAN)		+= kasan_init.o
 KASAN_SANITIZE_kasan_init.o	:= n
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 17bf39ac83ba..295459976416 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -37,6 +37,7 @@
 
 #include <asm/fixmap.h>
 #include <asm/memory.h>
+#include <asm/numa.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/sizes.h>
@@ -77,6 +78,19 @@ static phys_addr_t max_zone_dma_phys(void)
 	return min(offset + (1ULL << 32), memblock_end_of_DRAM());
 }
 
+#ifdef CONFIG_NUMA
+static void __init zone_sizes_init(unsigned long min, unsigned long max)
+{
+	unsigned long max_zone_pfns[MAX_NR_ZONES]  = {0};
+
+	if (IS_ENABLED(CONFIG_ZONE_DMA))
+		max_zone_pfns[ZONE_DMA] = PFN_DOWN(max_zone_dma_phys());
+	max_zone_pfns[ZONE_NORMAL] = max;
+
+	free_area_init_nodes(max_zone_pfns);
+}
+
+#else
 static void __init zone_sizes_init(unsigned long min, unsigned long max)
 {
 	struct memblock_region *reg;
@@ -116,6 +130,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 
 	free_area_init_node(0, zone_size, min, zhole_size);
 }
+#endif /* CONFIG_NUMA */
 
 #ifdef CONFIG_HAVE_ARCH_PFN_VALID
 int pfn_valid(unsigned long pfn)
@@ -133,10 +148,15 @@ static void arm64_memory_present(void)
 static void arm64_memory_present(void)
 {
 	struct memblock_region *reg;
+	int nid = 0;
 
-	for_each_memblock(memory, reg)
-		memory_present(0, memblock_region_memory_base_pfn(reg),
-			       memblock_region_memory_end_pfn(reg));
+	for_each_memblock(memory, reg) {
+#ifdef CONFIG_NUMA
+		nid = reg->nid;
+#endif
+		memory_present(nid, memblock_region_memory_base_pfn(reg),
+				memblock_region_memory_end_pfn(reg));
+	}
 }
 #endif
 
@@ -181,7 +201,6 @@ void __init arm64_memblock_init(void)
 	dma_contiguous_reserve(arm64_dma_phys_limit);
 
 	memblock_allow_resize();
-	memblock_dump_all();
 }
 
 void __init bootmem_init(void)
@@ -193,6 +212,9 @@ void __init bootmem_init(void)
 
 	early_memtest(min << PAGE_SHIFT, max << PAGE_SHIFT);
 
+	max_pfn = max_low_pfn = max;
+
+	arm64_numa_init();
 	/*
 	 * Sparsemem tries to allocate bootmem in memory_present(), so must be
 	 * done after the fixed reservations.
@@ -203,7 +225,6 @@ void __init bootmem_init(void)
 	zone_sizes_init(min, max);
 
 	high_memory = __va((max << PAGE_SHIFT) - 1) + 1;
-	max_pfn = max_low_pfn = max;
 }
 
 #ifndef CONFIG_SPARSEMEM_VMEMMAP
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 873e363048c6..6f6807517eb5 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -453,6 +453,7 @@ void __init paging_init(void)
 	zero_page = early_alloc(PAGE_SIZE);
 
 	bootmem_init();
+	memblock_dump_all();
 
 	empty_zero_page = virt_to_page(zero_page);
 
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
new file mode 100644
index 000000000000..e9749953dcce
--- /dev/null
+++ b/arch/arm64/mm/numa.c
@@ -0,0 +1,394 @@
+/*
+ * NUMA support, based on the x86 implementation.
+ *
+ * Copyright (C) 2015 Cavium Inc.
+ * Author: Ganapatrao Kulkarni <gkulkarni@cavium.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/acpi.h>
+#include <linux/bootmem.h>
+#include <linux/ctype.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/memblock.h>
+#include <linux/module.h>
+#include <linux/mmzone.h>
+#include <linux/nodemask.h>
+#include <linux/sched.h>
+#include <linux/string.h>
+#include <linux/topology.h>
+
+#include <asm/smp_plat.h>
+
+struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
+EXPORT_SYMBOL(node_data);
+nodemask_t numa_nodes_parsed __initdata;
+int cpu_to_node_map[NR_CPUS] = { [0 ... NR_CPUS-1] = NUMA_NO_NODE };
+
+static int numa_off;
+static int numa_distance_cnt;
+static u8 *numa_distance;
+
+static __init int numa_parse_early_param(char *opt)
+{
+	if (!opt)
+		return -EINVAL;
+	if (!strncmp(opt, "off", 3)) {
+		pr_info("%s\n", "NUMA turned off");
+		numa_off = 1;
+	}
+	return 0;
+}
+early_param("numa", numa_parse_early_param);
+
+cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+EXPORT_SYMBOL(node_to_cpumask_map);
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+/*
+ * Returns a pointer to the bitmask of CPUs on Node 'node'.
+ */
+const struct cpumask *cpumask_of_node(int node)
+{
+
+	if (WARN_ON(node >= nr_node_ids))
+		return cpu_none_mask;
+
+	if (WARN_ON(node_to_cpumask_map[node] == NULL))
+		return cpu_online_mask;
+
+	return node_to_cpumask_map[node];
+}
+EXPORT_SYMBOL(cpumask_of_node);
+#endif
+
+static void map_cpu_to_node(unsigned int cpu, int nid)
+{
+	set_cpu_numa_node(cpu, nid);
+	if (nid >= 0)
+		cpumask_set_cpu(cpu, node_to_cpumask_map[nid]);
+}
+
+static void unmap_cpu_to_node(unsigned int cpu)
+{
+	int nid = cpu_to_node(cpu);
+
+	if (nid >= 0)
+		cpumask_clear_cpu(cpu, node_to_cpumask_map[nid]);
+	set_cpu_numa_node(cpu, NUMA_NO_NODE);
+}
+
+void numa_clear_node(unsigned int cpu)
+{
+	unmap_cpu_to_node(cpu);
+}
+
+/*
+ * Allocate node_to_cpumask_map based on number of available nodes
+ * Requires node_possible_map to be valid.
+ *
+ * Note: cpumask_of_node() is not valid until after this is done.
+ * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.)
+ */
+static void __init setup_node_to_cpumask_map(void)
+{
+	unsigned int cpu;
+	int node;
+
+	/* setup nr_node_ids if not done yet */
+	if (nr_node_ids == MAX_NUMNODES)
+		setup_nr_node_ids();
+
+	/* allocate and clear the mapping */
+	for (node = 0; node < nr_node_ids; node++) {
+		alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
+		cpumask_clear(node_to_cpumask_map[node]);
+	}
+
+	for_each_possible_cpu(cpu)
+		set_cpu_numa_node(cpu, NUMA_NO_NODE);
+
+	/* cpumask_of_node() will now work */
+	pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids);
+}
+
+/*
+ *  Set the cpu to node and mem mapping
+ */
+void numa_store_cpu_info(unsigned int cpu)
+{
+	map_cpu_to_node(cpu, numa_off ? 0 : cpu_to_node_map[cpu]);
+}
+
+/**
+ * numa_add_memblk - Set node id to memblk
+ * @nid: NUMA node ID of the new memblk
+ * @start: Start address of the new memblk
+ * @size:  Size of the new memblk
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int __init numa_add_memblk(int nid, u64 start, u64 size)
+{
+	int ret;
+
+	ret = memblock_set_node(start, size, &memblock.memory, nid);
+	if (ret < 0) {
+		pr_err("NUMA: memblock [0x%llx - 0x%llx] failed to add on node %d\n",
+			start, (start + size - 1), nid);
+		return ret;
+	}
+
+	node_set(nid, numa_nodes_parsed);
+	pr_info("NUMA: Adding memblock [0x%llx - 0x%llx] on node %d\n",
+			start, (start + size - 1), nid);
+	return ret;
+}
+EXPORT_SYMBOL(numa_add_memblk);
+
+/* Initialize NODE_DATA for a node on the local memory */
+static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
+{
+	const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES);
+	u64 nd_pa;
+	void *nd;
+	int tnid;
+
+	pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
+			nid, start_pfn << PAGE_SHIFT,
+			(end_pfn << PAGE_SHIFT) - 1);
+
+	nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
+	nd = __va(nd_pa);
+
+	/* report and initialize */
+	pr_info("  NODE_DATA [mem %#010Lx-%#010Lx]\n",
+		nd_pa, nd_pa + nd_size - 1);
+	tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
+	if (tnid != nid)
+		pr_info("    NODE_DATA(%d) on node %d\n", nid, tnid);
+
+	node_data[nid] = nd;
+	memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
+	NODE_DATA(nid)->node_id = nid;
+	NODE_DATA(nid)->node_start_pfn = start_pfn;
+	NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;
+}
+
+/**
+ * numa_reset_distance - Reset NUMA distance table
+ *
+ * The current table is freed.
+ * The next numa_set_distance() call will create a new one.
+ */
+void __init numa_reset_distance(void)
+{
+	size_t size;
+
+	if (!numa_distance)
+		return;
+
+	size = numa_distance_cnt * numa_distance_cnt *
+		sizeof(numa_distance[0]);
+
+	memblock_free(__pa(numa_distance), size);
+	numa_distance_cnt = 0;
+	numa_distance = NULL;
+}
+
+static int __init numa_alloc_distance(void)
+{
+	size_t size;
+	u64 phys;
+	int i, j;
+
+	size = nr_node_ids * nr_node_ids * sizeof(numa_distance[0]);
+	phys = memblock_find_in_range(0, PFN_PHYS(max_pfn),
+				      size, PAGE_SIZE);
+	if (WARN_ON(!phys))
+		return -ENOMEM;
+
+	memblock_reserve(phys, size);
+
+	numa_distance = __va(phys);
+	numa_distance_cnt = nr_node_ids;
+
+	/* fill with the default distances */
+	for (i = 0; i < numa_distance_cnt; i++)
+		for (j = 0; j < numa_distance_cnt; j++)
+			numa_distance[i * numa_distance_cnt + j] = i == j ?
+				LOCAL_DISTANCE : REMOTE_DISTANCE;
+
+	pr_debug("NUMA: Initialized distance table, cnt=%d\n",
+			numa_distance_cnt);
+
+	return 0;
+}
+
+/**
+ * numa_set_distance - Set NUMA distance from one NUMA to another
+ * @from: the 'from' node to set distance
+ * @to: the 'to'  node to set distance
+ * @distance: NUMA distance
+ *
+ * Set the distance from node @from to @to to @distance.  If distance table
+ * doesn't exist, one which is large enough to accommodate all the currently
+ * known nodes will be created.
+ *
+ * If such table cannot be allocated, a warning is printed and further
+ * calls are ignored until the distance table is reset with
+ * numa_reset_distance().
+ *
+ * If @from or @to is higher than the highest known node or lower than zero
+ * at the time of table creation or @distance doesn't make sense, the call
+ * is ignored.
+ * This is to allow simplification of specific NUMA config implementations.
+ */
+void __init numa_set_distance(int from, int to, int distance)
+{
+	if (!numa_distance)
+		return;
+
+	if (from >= numa_distance_cnt || to >= numa_distance_cnt ||
+			from < 0 || to < 0) {
+		pr_warn_once("NUMA: Warning: node ids are out of bound, from=%d to=%d distance=%d\n",
+			    from, to, distance);
+		return;
+	}
+
+	if ((u8)distance != distance ||
+	    (from == to && distance != LOCAL_DISTANCE)) {
+		pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
+			     from, to, distance);
+		return;
+	}
+
+	numa_distance[from * numa_distance_cnt + to] = distance;
+}
+EXPORT_SYMBOL(numa_set_distance);
+
+int __node_distance(int from, int to)
+{
+	if (from >= numa_distance_cnt || to >= numa_distance_cnt)
+		return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE;
+	return numa_distance[from * numa_distance_cnt + to];
+}
+EXPORT_SYMBOL(__node_distance);
+
+static int __init numa_register_nodes(void)
+{
+	int nid;
+	struct memblock_region *mblk;
+
+	/* Check that valid nid is set to memblks */
+	for_each_memblock(memory, mblk)
+		if (mblk->nid == NUMA_NO_NODE || mblk->nid >= MAX_NUMNODES)
+			return -EINVAL;
+
+	/* Finally register nodes. */
+	for_each_node_mask(nid, numa_nodes_parsed) {
+		unsigned long start_pfn, end_pfn;
+
+		get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
+		setup_node_data(nid, start_pfn, end_pfn);
+		node_set_online(nid);
+	}
+
+	/* Setup online nodes to actual nodes*/
+	node_possible_map = numa_nodes_parsed;
+
+	return 0;
+}
+
+static int __init numa_init(int (*init_func)(void))
+{
+	int ret;
+
+	nodes_clear(numa_nodes_parsed);
+	nodes_clear(node_possible_map);
+	nodes_clear(node_online_map);
+	numa_reset_distance();
+
+	ret = init_func();
+	if (ret < 0)
+		return ret;
+
+	if (nodes_empty(numa_nodes_parsed))
+		return -EINVAL;
+
+	ret = numa_register_nodes();
+	if (ret < 0)
+		return ret;
+
+	ret = numa_alloc_distance();
+	if (ret < 0)
+		return ret;
+
+	setup_node_to_cpumask_map();
+
+	/* init boot processor */
+	cpu_to_node_map[0] = 0;
+	map_cpu_to_node(0, 0);
+
+	return 0;
+}
+
+/**
+ * dummy_numa_init - Fallback dummy NUMA init
+ *
+ * Used if there's no underlying NUMA architecture, NUMA initialization
+ * fails, or NUMA is disabled on the command line.
+ *
+ * Must online at least one node (node 0) and add memory blocks that cover all
+ * allowed memory. It is unlikely that this function fails.
+ */
+static int __init dummy_numa_init(void)
+{
+	int ret;
+	struct memblock_region *mblk;
+
+	pr_info("%s\n", "No NUMA configuration found");
+	pr_info("Faking a node at [mem %#018Lx-%#018Lx]\n",
+	       0LLU, PFN_PHYS(max_pfn) - 1);
+
+	for_each_memblock(memory, mblk) {
+		ret = numa_add_memblk(0, mblk->base, mblk->size);
+		if (unlikely(ret < 0))
+			return ret;
+	}
+
+	numa_off = 1;
+	return 0;
+}
+
+/**
+ * arm64_numa_init - Initialize NUMA
+ *
+ * Try each configured NUMA initialization method until one succeeds.  The
+ * last fallback is dummy single node config encomapssing whole memory and
+ * never fails.
+ */
+void __init arm64_numa_init(void)
+{
+	int ret = -ENODEV;
+
+	if (!numa_off)
+		ret = numa_init(acpi_disabled ? arm64_of_numa_init : arm64_acpi_numa_init);
+
+	if (ret)
+		numa_init(dummy_numa_init);
+}
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index eb0249e37981..1285cef47211 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -17,6 +17,7 @@ config IA64
 	select ACPI if (!IA64_HP_SIM)
 	select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI
 	select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI
+	select ACPI_HAS_NUMA_ARCH_FIXUP if ACPI
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select HAVE_IDE
 	select HAVE_OPROFILE
diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
index 3ad8f6988363..2778eb68b615 100644
--- a/arch/ia64/include/asm/topology.h
+++ b/arch/ia64/include/asm/topology.h
@@ -58,10 +58,6 @@ void build_cpu_to_node_map(void);
 
 extern void arch_fix_phys_package_id(int num, u32 slot);
 
-#define cpumask_of_pcibus(bus)	(pcibus_to_node(bus) == -1 ?		\
-				 cpu_all_mask :				\
-				 cpumask_of_node(pcibus_to_node(bus)))
-
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_IA64_TOPOLOGY_H */
diff --git a/arch/metag/include/asm/topology.h b/arch/metag/include/asm/topology.h
index e95f874ded1b..b2851963d207 100644
--- a/arch/metag/include/asm/topology.h
+++ b/arch/metag/include/asm/topology.h
@@ -9,9 +9,6 @@
 #define cpumask_of_node(node)	((void)node, cpu_online_mask)
 
 #define pcibus_to_node(bus)	((void)(bus), -1)
-#define cpumask_of_pcibus(bus)	(pcibus_to_node(bus) == -1 ? \
-					cpu_all_mask : \
-					cpumask_of_node(pcibus_to_node(bus)))
 
 #endif
 
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 8b3b46b7b0f2..eee025d23b36 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -32,10 +32,6 @@ static inline int pcibus_to_node(struct pci_bus *bus)
 }
 #endif
 
-#define cpumask_of_pcibus(bus)	(pcibus_to_node(bus) == -1 ?		\
-				 cpu_all_mask :				\
-				 cpumask_of_node(pcibus_to_node(bus)))
-
 extern int __node_distance(int, int);
 #define node_distance(a, b) __node_distance(a, b)
 
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index c873e682b67f..539fb2dbd694 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -205,7 +205,7 @@ static inline int __pcibus_to_node(const struct pci_bus *bus)
 }
 
 static inline const struct cpumask *
-cpumask_of_pcibus(const struct pci_bus *bus)
+__cpumask_of_pcibus(const struct pci_bus *bus)
 {
 	return cpu_online_mask;
 }
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index 94fc55fc72ce..280eafc6ab7b 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -78,6 +78,7 @@ static inline const struct cpumask *cpumask_of_node(int node)
 #define parent_node(node) (node)
 
 #define pcibus_to_node(bus) __pcibus_to_node(bus)
+#define cpumask_of_pcibus(bus) __cpumask_of_pcibus(bus)
 
 #define node_distance(a, b) __node_distance(a, b)
 
diff --git a/arch/sh/include/asm/topology.h b/arch/sh/include/asm/topology.h
index b0a282d65f6a..357983d51f5f 100644
--- a/arch/sh/include/asm/topology.h
+++ b/arch/sh/include/asm/topology.h
@@ -9,9 +9,6 @@
 #define cpumask_of_node(node)	((void)node, cpu_online_mask)
 
 #define pcibus_to_node(bus)	((void)(bus), -1)
-#define cpumask_of_pcibus(bus)	(pcibus_to_node(bus) == -1 ? \
-					cpu_all_mask : \
-					cpumask_of_node(pcibus_to_node(bus)))
 
 #endif
 
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index a98c022c9089..fcbce830cfe1 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -118,7 +118,7 @@ static inline int __pcibus_to_node(const struct pci_bus *bus)
 }
 
 static inline const struct cpumask *
-cpumask_of_pcibus(const struct pci_bus *bus)
+__cpumask_of_pcibus(const struct pci_bus *bus)
 {
 	int node;
 
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 0fb46482dfde..980f6eea5bbf 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -91,6 +91,7 @@ extern void setup_node_to_cpumask_map(void);
 #define parent_node(node) (node)
 
 #define pcibus_to_node(bus) __pcibus_to_node(bus)
+#define cpumask_of_pcibus(bus) __cpumask_of_pcibus(bus)
 
 extern int __node_distance(int, int);
 #define node_distance(a, b) __node_distance(a, b)
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index c2aea63bee20..92a640a3d259 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -42,33 +42,6 @@ static __init inline int srat_disabled(void)
 	return acpi_numa < 0;
 }
 
-/*
- * Callback for SLIT parsing.  pxm_to_node() returns NUMA_NO_NODE for
- * I/O localities since SRAT does not list them.  I/O localities are
- * not supported at this point.
- */
-void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
-{
-	int i, j;
-
-	for (i = 0; i < slit->locality_count; i++) {
-		const int from_node = pxm_to_node(i);
-
-		if (from_node == NUMA_NO_NODE)
-			continue;
-
-		for (j = 0; j < slit->locality_count; j++) {
-			const int to_node = pxm_to_node(j);
-
-			if (to_node == NUMA_NO_NODE)
-				continue;
-
-			numa_set_distance(from_node, to_node,
-				slit->entry[slit->locality_count * i + j]);
-		}
-	}
-}
-
 /* Callback for Proximity Domain -> x2APIC mapping */
 void __init
 acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
@@ -210,8 +183,6 @@ out_err:
 	return -1;
 }
 
-void __init acpi_numa_arch_fixup(void) {}
-
 int __init x86_acpi_numa_init(void)
 {
 	int ret;
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index e315061a0c93..e1b41243159e 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -60,6 +60,9 @@ config ACPI_CCA_REQUIRED
 config IORT_TABLE
 	bool
 
+config ACPI_HAS_NUMA_ARCH_FIXUP
+	bool
+
 config ACPI_DEBUGGER
 	bool "AML debugger interface (EXPERIMENTAL)"
 	select ACPI_DEBUG
@@ -283,7 +286,7 @@ config ACPI_THERMAL
 config ACPI_NUMA
 	bool "NUMA support"
 	depends on NUMA
-	depends on (X86 || IA64)
+	depends on (X86 || IA64 || ARM64)
 	default y if IA64_GENERIC || IA64_SGI_SN2
 
 config ACPI_CUSTOM_DSDT_FILE
diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c
index 72b6e9ef0ae9..b33915e15761 100644
--- a/drivers/acpi/numa.c
+++ b/drivers/acpi/numa.c
@@ -18,6 +18,9 @@
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  *
  */
+
+#define pr_fmt(fmt) "ACPI: " fmt
+
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -28,12 +31,6 @@
 #include <linux/nodemask.h>
 #include <linux/topology.h>
 
-#define PREFIX "ACPI: "
-
-#define ACPI_NUMA	0x80000000
-#define _COMPONENT	ACPI_NUMA
-ACPI_MODULE_NAME("numa");
-
 static nodemask_t nodes_found_map = NODE_MASK_NONE;
 
 /* maps to convert between proximity domain and logical node ID */
@@ -128,68 +125,63 @@ EXPORT_SYMBOL(acpi_map_pxm_to_online_node);
 static void __init
 acpi_table_print_srat_entry(struct acpi_subtable_header *header)
 {
-
-	ACPI_FUNCTION_NAME("acpi_table_print_srat_entry");
-
-	if (!header)
-		return;
-
 	switch (header->type) {
-
 	case ACPI_SRAT_TYPE_CPU_AFFINITY:
-#ifdef ACPI_DEBUG_OUTPUT
 		{
 			struct acpi_srat_cpu_affinity *p =
 			    (struct acpi_srat_cpu_affinity *)header;
-			ACPI_DEBUG_PRINT((ACPI_DB_INFO,
-					  "SRAT Processor (id[0x%02x] eid[0x%02x]) in proximity domain %d %s\n",
-					  p->apic_id, p->local_sapic_eid,
-					  p->proximity_domain_lo,
-					  (p->flags & ACPI_SRAT_CPU_ENABLED)?
-					  "enabled" : "disabled"));
+			pr_debug("SRAT Processor (id[0x%02x] eid[0x%02x]) in proximity domain %d %s\n",
+				 p->apic_id, p->local_sapic_eid,
+				 p->proximity_domain_lo,
+				 (p->flags & ACPI_SRAT_CPU_ENABLED) ?
+				 "enabled" : "disabled");
 		}
-#endif				/* ACPI_DEBUG_OUTPUT */
 		break;
 
 	case ACPI_SRAT_TYPE_MEMORY_AFFINITY:
-#ifdef ACPI_DEBUG_OUTPUT
 		{
 			struct acpi_srat_mem_affinity *p =
 			    (struct acpi_srat_mem_affinity *)header;
-			ACPI_DEBUG_PRINT((ACPI_DB_INFO,
-					  "SRAT Memory (0x%lx length 0x%lx) in proximity domain %d %s%s%s\n",
-					  (unsigned long)p->base_address,
-					  (unsigned long)p->length,
-					  p->proximity_domain,
-					  (p->flags & ACPI_SRAT_MEM_ENABLED)?
-					  "enabled" : "disabled",
-					  (p->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE)?
-					  " hot-pluggable" : "",
-					  (p->flags & ACPI_SRAT_MEM_NON_VOLATILE)?
-					  " non-volatile" : ""));
+			pr_debug("SRAT Memory (0x%lx length 0x%lx) in proximity domain %d %s%s%s\n",
+				 (unsigned long)p->base_address,
+				 (unsigned long)p->length,
+				 p->proximity_domain,
+				 (p->flags & ACPI_SRAT_MEM_ENABLED) ?
+				 "enabled" : "disabled",
+				 (p->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) ?
+				 " hot-pluggable" : "",
+				 (p->flags & ACPI_SRAT_MEM_NON_VOLATILE) ?
+				 " non-volatile" : "");
 		}
-#endif				/* ACPI_DEBUG_OUTPUT */
 		break;
 
 	case ACPI_SRAT_TYPE_X2APIC_CPU_AFFINITY:
-#ifdef ACPI_DEBUG_OUTPUT
 		{
 			struct acpi_srat_x2apic_cpu_affinity *p =
 			    (struct acpi_srat_x2apic_cpu_affinity *)header;
-			ACPI_DEBUG_PRINT((ACPI_DB_INFO,
-					  "SRAT Processor (x2apicid[0x%08x]) in"
-					  " proximity domain %d %s\n",
-					  p->apic_id,
-					  p->proximity_domain,
-					  (p->flags & ACPI_SRAT_CPU_ENABLED) ?
-					  "enabled" : "disabled"));
+			pr_debug("SRAT Processor (x2apicid[0x%08x]) in proximity domain %d %s\n",
+				 p->apic_id,
+				 p->proximity_domain,
+				 (p->flags & ACPI_SRAT_CPU_ENABLED) ?
+				 "enabled" : "disabled");
+		}
+		break;
+
+	case ACPI_SRAT_TYPE_GICC_AFFINITY:
+		{
+			struct acpi_srat_gicc_affinity *p =
+			    (struct acpi_srat_gicc_affinity *)header;
+			pr_debug("SRAT Processor (acpi id[0x%04x]) in proximity domain %d %s\n",
+				 p->acpi_processor_uid,
+				 p->proximity_domain,
+				 (p->flags & ACPI_SRAT_GICC_ENABLED) ?
+				 "enabled" : "disabled");
 		}
-#endif				/* ACPI_DEBUG_OUTPUT */
 		break;
+
 	default:
-		printk(KERN_WARNING PREFIX
-		       "Found unsupported SRAT entry (type = 0x%x)\n",
-		       header->type);
+		pr_warn("Found unsupported SRAT entry (type = 0x%x)\n",
+			header->type);
 		break;
 	}
 }
@@ -217,12 +209,42 @@ static int __init slit_valid(struct acpi_table_slit *slit)
 	return 1;
 }
 
+/*
+ * Callback for SLIT parsing. It will get the distance information
+ * presented by SLIT and init the distance matrix of numa nodes
+ */
+void __init __weak acpi_numa_slit_init(struct acpi_table_slit *slit)
+{
+	int i, j;
+
+	for (i = 0; i < slit->locality_count; i++) {
+		const int from_node = pxm_to_node(i);
+
+		if (from_node == NUMA_NO_NODE)
+			continue;
+
+		for (j = 0; j < slit->locality_count; j++) {
+			const int to_node = pxm_to_node(j);
+
+			if (to_node == NUMA_NO_NODE)
+				continue;
+
+			numa_set_distance(from_node, to_node,
+				slit->entry[slit->locality_count * i + j]);
+
+			pr_debug("SLIT: Distance[%d][%d] = %d\n",
+				 from_node, to_node,
+				 slit->entry[slit->locality_count * i + j]);
+		}
+	}
+}
+
 static int __init acpi_parse_slit(struct acpi_table_header *table)
 {
 	struct acpi_table_slit *slit = (struct acpi_table_slit *)table;
 
 	if (!slit_valid(slit)) {
-		printk(KERN_INFO "ACPI: SLIT table looks invalid. Not used.\n");
+		pr_info("SLIT table looks invalid. Not used.\n");
 		return -EINVAL;
 	}
 	acpi_numa_slit_init(slit);
@@ -233,12 +255,9 @@ static int __init acpi_parse_slit(struct acpi_table_header *table)
 void __init __weak
 acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
 {
-	printk(KERN_WARNING PREFIX
-	       "Found unsupported x2apic [0x%08x] SRAT entry\n", pa->apic_id);
-	return;
+	pr_warn("Found unsupported x2apic [0x%08x] SRAT entry\n", pa->apic_id);
 }
 
-
 static int __init
 acpi_parse_x2apic_affinity(struct acpi_subtable_header *header,
 			   const unsigned long end)
@@ -275,6 +294,24 @@ acpi_parse_processor_affinity(struct acpi_subtable_header *header,
 	return 0;
 }
 
+static int __init
+acpi_parse_gicc_affinity(struct acpi_subtable_header *header,
+			 const unsigned long end)
+{
+	struct acpi_srat_gicc_affinity *processor_affinity;
+
+	processor_affinity = (struct acpi_srat_gicc_affinity *)header;
+	if (!processor_affinity)
+		return -EINVAL;
+
+	acpi_table_print_srat_entry(header);
+
+	/* let architecture-dependent part to do it */
+	acpi_numa_gicc_affinity_init(processor_affinity);
+
+	return 0;
+}
+
 static int __initdata parsed_numa_memblks;
 
 static int __init
@@ -319,6 +356,9 @@ int __init acpi_numa_init(void)
 {
 	int cnt = 0;
 
+	if (acpi_disabled)
+		return -EINVAL;
+
 	/*
 	 * Should not limit number with cpu num that is from NR_CPUS or nr_cpus=
 	 * SRAT cpu entries could have different order with that in MADT.
@@ -331,6 +371,8 @@ int __init acpi_numa_init(void)
 				     acpi_parse_x2apic_affinity, 0);
 		acpi_table_parse_srat(ACPI_SRAT_TYPE_CPU_AFFINITY,
 				     acpi_parse_processor_affinity, 0);
+		acpi_table_parse_srat(ACPI_SRAT_TYPE_GICC_AFFINITY,
+				      acpi_parse_gicc_affinity, 0);
 		cnt = acpi_table_parse_srat(ACPI_SRAT_TYPE_MEMORY_AFFINITY,
 					    acpi_parse_memory_affinity,
 					    NR_NODE_MEMBLKS);
diff --git a/drivers/pci/host/pci-host-generic.c b/drivers/pci/host/pci-host-generic.c
index 0879fa779702..d329e421d83c 100644
--- a/drivers/pci/host/pci-host-generic.c
+++ b/drivers/pci/host/pci-host-generic.c
@@ -215,12 +215,10 @@ static int gen_pci_probe(struct platform_device *pdev)
 	const struct of_device_id *of_id;
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
-	struct gen_pci *pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL);
+	struct gen_pci *pci;
 	struct pci_bus *bus, *child;
 	struct pci_host_bridge *bridge;
 
-	if (!pci)
-		return -ENOMEM;
 
 	type = of_get_property(np, "device_type", NULL);
 	if (!type || strcmp(type, "pci")) {
@@ -231,6 +229,11 @@ static int gen_pci_probe(struct platform_device *pdev)
 	of_pci_check_probe_only();
 
 	of_id = of_match_node(gen_pci_of_match, np);
+	set_dev_node(dev, of_node_to_nid(np));
+	pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL);
+	if (!pci)
+		return -ENOMEM;
+
 	pci->cfg.ops = (struct gen_pci_cfg_bus_ops *)of_id->data;
 	pci->host.dev.parent = dev;
 	INIT_LIST_HEAD(&pci->host.windows);
diff --git a/include/asm-generic/topology.h b/include/asm-generic/topology.h
index fc824e2828f3..ee305f10bed4 100644
--- a/include/asm-generic/topology.h
+++ b/include/asm-generic/topology.h
@@ -54,14 +54,14 @@
 #define pcibus_to_node(bus)	((void)(bus), -1)
 #endif
 
+#endif	/* !CONFIG_NUMA */
+
 #ifndef cpumask_of_pcibus
 #define cpumask_of_pcibus(bus)	(pcibus_to_node(bus) == -1 ?		\
 				 cpu_all_mask :				\
 				 cpumask_of_node(pcibus_to_node(bus)))
 #endif
 
-#endif	/* CONFIG_NUMA */
-
 #if !defined(CONFIG_NUMA) || !defined(CONFIG_HAVE_MEMORYLESS_NODES)
 
 #ifndef set_numa_mem
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 7c603e4a9574..6c83d9c97ecb 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -170,12 +170,32 @@ int acpi_mcfg_check_entry(struct acpi_table_mcfg *mcfg,
 			  struct acpi_mcfg_allocation *cfg);
 void acpi_table_print_madt_entry (struct acpi_subtable_header *madt);
 
-/* the following four functions are architecture-dependent */
+/* the following numa functions are architecture-dependent */
 void acpi_numa_slit_init (struct acpi_table_slit *slit);
+
+#if defined(CONFIG_X86) || defined(CONFIG_IA64)
 void acpi_numa_processor_affinity_init (struct acpi_srat_cpu_affinity *pa);
+#else
+static inline void
+acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) { }
+#endif
+
 void acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa);
+
+#ifdef CONFIG_ARM64
+void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa);
+#else
+static inline void
+acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { }
+#endif
+
 int acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma);
+
+#ifdef CONFIG_ACPI_HAS_NUMA_ARCH_FIXUP
 void acpi_numa_arch_fixup(void);
+#else
+static inline void acpi_numa_arch_fixup(void) { }
+#endif
 
 #ifndef PHYS_CPUID_INVALID
 typedef u32 phys_cpuid_t;