Merge branch 'linux-linaro-lsk-v3.14' into linux-linaro-lsk-v3.14-android

66 files changed, 7176 insertions, 89 deletions

diff --git a/Documentation/devicetree/bindings/arm/pmu.txt b/Documentation/devicetree/bindings/arm/pmu.txt
index 3e1e498fea96..a2dbf67c1cb7 100644
--- a/Documentation/devicetree/bindings/arm/pmu.txt
+++ b/Documentation/devicetree/bindings/arm/pmu.txt
@@ -17,6 +17,9 @@ Required properties:
 	"arm,arm1176-pmu"
 	"arm,arm1136-pmu"
 - interrupts : 1 combined interrupt or 1 per core.
+- cluster : a phandle to the cluster to which it belongs
+	If there are more than one cluster with same CPU type
+	then there should be separate PMU nodes per cluster.
 
 Example:
 
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index 982d8ab9235a..fad06762f73c 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -312,7 +312,14 @@ dtb-$(CONFIG_ARCH_U300) += ste-u300.dtb
 dtb-$(CONFIG_ARCH_VEXPRESS) += vexpress-v2p-ca5s.dtb \
 	vexpress-v2p-ca9.dtb \
 	vexpress-v2p-ca15-tc1.dtb \
-	vexpress-v2p-ca15_a7.dtb
+	vexpress-v2p-ca15_a7.dtb \
+	rtsm_ve-cortex_a9x2.dtb \
+	rtsm_ve-cortex_a9x4.dtb \
+	rtsm_ve-cortex_a15x1.dtb \
+	rtsm_ve-cortex_a15x2.dtb \
+	rtsm_ve-cortex_a15x4.dtb \
+	rtsm_ve-v2p-ca15x1-ca7x1.dtb \
+	rtsm_ve-v2p-ca15x4-ca7x4.dtb
 dtb-$(CONFIG_ARCH_VIRT) += xenvm-4.2.dtb
 dtb-$(CONFIG_ARCH_VT8500) += vt8500-bv07.dtb \
 	wm8505-ref.dtb \
diff --git a/arch/arm/boot/dts/clcd-panels.dtsi b/arch/arm/boot/dts/clcd-panels.dtsi
new file mode 100644
index 000000000000..0b0ff6ead4b2
--- /dev/null
+++ b/arch/arm/boot/dts/clcd-panels.dtsi
@@ -0,0 +1,52 @@
+/*
+ * ARM Ltd. Versatile Express
+ *
+ */
+
+/ {
+	panels {
+		panel@0 {
+			compatible	= "panel";
+			mode		= "VGA";
+			refresh		= <60>;
+			xres		= <640>;
+			yres		= <480>;
+			pixclock	= <39721>;
+			left_margin	= <40>;
+			right_margin	= <24>;
+			upper_margin	= <32>;
+			lower_margin	= <11>;
+			hsync_len	= <96>;
+			vsync_len	= <2>;
+			sync		= <0>;
+			vmode		= "FB_VMODE_NONINTERLACED";
+
+			tim2		= "TIM2_BCD", "TIM2_IPC";
+			cntl		= "CNTL_LCDTFT", "CNTL_BGR", "CNTL_LCDVCOMP(1)";
+			caps		= "CLCD_CAP_5551", "CLCD_CAP_565", "CLCD_CAP_888";
+			bpp		= <16>;
+		};
+
+		panel@1 {
+			compatible	= "panel";
+			mode		= "XVGA";
+			refresh		= <60>;
+			xres		= <1024>;
+			yres		= <768>;
+			pixclock	= <15748>;
+			left_margin	= <152>;
+			right_margin	= <48>;
+			upper_margin	= <23>;
+			lower_margin	= <3>;
+			hsync_len	= <104>;
+			vsync_len	= <4>;
+			sync		= <0>;
+			vmode		= "FB_VMODE_NONINTERLACED";
+
+			tim2		= "TIM2_BCD", "TIM2_IPC";
+			cntl		= "CNTL_LCDTFT", "CNTL_BGR", "CNTL_LCDVCOMP(1)";
+			caps		= "CLCD_CAP_5551", "CLCD_CAP_565", "CLCD_CAP_888";
+			bpp		= <16>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a15x1.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a15x1.dts
new file mode 100644
index 000000000000..c9eee916aa7e
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a15x1.dts
@@ -0,0 +1,159 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x1CT
+ *
+ * RTSM_VE_Cortex_A15x1.lisa
+ */
+
+/dts-v1/;
+
+/ {
+	model = "RTSM_VE_CortexA15x1";
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,rtsm_ve,cortex_a15x1", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0 0x80000000 0 0x80000000>;
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0 0x2c001000 0 0x1000>,
+		      <0 0x2c002000 0 0x1000>,
+		      <0 0x2c004000 0 0x2000>,
+		      <0 0x2c006000 0 0x2000>;
+		interrupts = <1 9 0xf04>;
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupts = <1 13 0xf08>,
+			     <1 14 0xf08>,
+			     <1 11 0xf08>,
+			     <1 10 0xf08>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			/* ACLK clock to the AXI master port on the test chip */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 0>;
+			freq-range = <30000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "extsaxiclk";
+		};
+
+		oscclk1: osc@1 {
+			/* Reference clock for the CLCD */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 1>;
+			freq-range = <10000000 80000000>;
+			#clock-cells = <0>;
+			clock-output-names = "clcdclk";
+		};
+
+		smbclk: oscclk2: osc@2 {
+			/* Reference clock for the test chip internal PLLs */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 2>;
+			freq-range = <33000000 100000000>;
+			#clock-cells = <0>;
+			clock-output-names = "tcrefclk";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a15x2.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a15x2.dts
new file mode 100644
index 000000000000..853a166e3c32
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a15x2.dts
@@ -0,0 +1,165 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x2CT
+ *
+ * RTSM_VE_Cortex_A15x2.lisa
+ */
+
+/dts-v1/;
+
+/ {
+	model = "RTSM_VE_CortexA15x2";
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,rtsm_ve,cortex_a15x2", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+		};
+
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <1>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0 0x80000000 0 0x80000000>;
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0 0x2c001000 0 0x1000>,
+		      <0 0x2c002000 0 0x1000>,
+		      <0 0x2c004000 0 0x2000>,
+		      <0 0x2c006000 0 0x2000>;
+		interrupts = <1 9 0xf04>;
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupts = <1 13 0xf08>,
+			     <1 14 0xf08>,
+			     <1 11 0xf08>,
+			     <1 10 0xf08>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			/* ACLK clock to the AXI master port on the test chip */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 0>;
+			freq-range = <30000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "extsaxiclk";
+		};
+
+		oscclk1: osc@1 {
+			/* Reference clock for the CLCD */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 1>;
+			freq-range = <10000000 80000000>;
+			#clock-cells = <0>;
+			clock-output-names = "clcdclk";
+		};
+
+		smbclk: oscclk2: osc@2 {
+			/* Reference clock for the test chip internal PLLs */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 2>;
+			freq-range = <33000000 100000000>;
+			#clock-cells = <0>;
+			clock-output-names = "tcrefclk";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a15x4.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a15x4.dts
new file mode 100644
index 000000000000..c1947a3a5c88
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a15x4.dts
@@ -0,0 +1,177 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x4CT
+ *
+ * RTSM_VE_Cortex_A15x4.lisa
+ */
+
+/dts-v1/;
+
+/ {
+	model = "RTSM_VE_CortexA15x4";
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,rtsm_ve,cortex_a15x4", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+		};
+
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <1>;
+		};
+
+		cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <2>;
+		};
+
+		cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <3>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0 0x80000000 0 0x80000000>;
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0 0x2c001000 0 0x1000>,
+		      <0 0x2c002000 0 0x1000>,
+		      <0 0x2c004000 0 0x2000>,
+		      <0 0x2c006000 0 0x2000>;
+		interrupts = <1 9 0xf04>;
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupts = <1 13 0xf08>,
+			     <1 14 0xf08>,
+			     <1 11 0xf08>,
+			     <1 10 0xf08>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			/* ACLK clock to the AXI master port on the test chip */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 0>;
+			freq-range = <30000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "extsaxiclk";
+		};
+
+		oscclk1: osc@1 {
+			/* Reference clock for the CLCD */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 1>;
+			freq-range = <10000000 80000000>;
+			#clock-cells = <0>;
+			clock-output-names = "clcdclk";
+		};
+
+		smbclk: oscclk2: osc@2 {
+			/* Reference clock for the test chip internal PLLs */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 2>;
+			freq-range = <33000000 100000000>;
+			#clock-cells = <0>;
+			clock-output-names = "tcrefclk";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a9x2.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a9x2.dts
new file mode 100644
index 000000000000..fca6b2f79677
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a9x2.dts
@@ -0,0 +1,171 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA9MPx2CT
+ *
+ * RTSM_VE_Cortex_A9x2.lisa
+ */
+
+/dts-v1/;
+
+/ {
+	model = "RTSM_VE_CortexA9x2";
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,rtsm_ve,cortex_a9x2", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <0>;
+		};
+
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <1>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x80000000 0x80000000>;
+	};
+
+	scu@2c000000 {
+		compatible = "arm,cortex-a9-scu";
+		reg = <0x2c000000 0x58>;
+	};
+
+	timer@2c000600 {
+		compatible = "arm,cortex-a9-twd-timer";
+		reg = <0x2c000600 0x20>;
+		interrupts = <1 13 0xf04>;
+	};
+
+	watchdog@2c000620 {
+		compatible = "arm,cortex-a9-twd-wdt";
+		reg = <0x2c000620 0x20>;
+		interrupts = <1 14 0xf04>;
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0x2c001000 0x1000>,
+		      <0x2c000100 0x100>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			/* ACLK clock to the AXI master port on the test chip */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 0>;
+			freq-range = <30000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "extsaxiclk";
+		};
+
+		oscclk1: osc@1 {
+			/* Reference clock for the CLCD */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 1>;
+			freq-range = <10000000 80000000>;
+			#clock-cells = <0>;
+			clock-output-names = "clcdclk";
+		};
+
+		smbclk: oscclk2: osc@2 {
+			/* Reference clock for the test chip internal PLLs */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 2>;
+			freq-range = <33000000 100000000>;
+			#clock-cells = <0>;
+			clock-output-names = "tcrefclk";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0x08000000 0x04000000>,
+			 <1 0 0x14000000 0x04000000>,
+			 <2 0 0x18000000 0x04000000>,
+			 <3 0 0x1c000000 0x04000000>,
+			 <4 0 0x0c000000 0x04000000>,
+			 <5 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a9x4.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a9x4.dts
new file mode 100644
index 000000000000..fd8a6ed97a04
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a9x4.dts
@@ -0,0 +1,183 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA9MPx4CT
+ *
+ * RTSM_VE_Cortex_A9x4.lisa
+ */
+
+/dts-v1/;
+
+/ {
+	model = "RTSM_VE_CortexA9x4";
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,rtsm_ve,cortex_a9x4", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <0>;
+		};
+
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <1>;
+		};
+
+		cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <2>;
+		};
+
+		cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <3>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x80000000 0x80000000>;
+	};
+
+	scu@2c000000 {
+		compatible = "arm,cortex-a9-scu";
+		reg = <0x2c000000 0x58>;
+	};
+
+	timer@2c000600 {
+		compatible = "arm,cortex-a9-twd-timer";
+		reg = <0x2c000600 0x20>;
+		interrupts = <1 13 0xf04>;
+	};
+
+	watchdog@2c000620 {
+		compatible = "arm,cortex-a9-twd-wdt";
+		reg = <0x2c000620 0x20>;
+		interrupts = <1 14 0xf04>;
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0x2c001000 0x1000>,
+		      <0x2c000100 0x100>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			/* ACLK clock to the AXI master port on the test chip */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 0>;
+			freq-range = <30000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "extsaxiclk";
+		};
+
+		oscclk1: osc@1 {
+			/* Reference clock for the CLCD */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 1>;
+			freq-range = <10000000 80000000>;
+			#clock-cells = <0>;
+			clock-output-names = "clcdclk";
+		};
+
+		smbclk: oscclk2: osc@2 {
+			/* Reference clock for the test chip internal PLLs */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 2>;
+			freq-range = <33000000 100000000>;
+			#clock-cells = <0>;
+			clock-output-names = "tcrefclk";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0x08000000 0x04000000>,
+			 <1 0 0x14000000 0x04000000>,
+			 <2 0 0x18000000 0x04000000>,
+			 <3 0 0x1c000000 0x04000000>,
+			 <4 0 0x0c000000 0x04000000>,
+			 <5 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-motherboard.dtsi b/arch/arm/boot/dts/rtsm_ve-motherboard.dtsi
new file mode 100644
index 000000000000..a2d895ee5faa
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-motherboard.dtsi
@@ -0,0 +1,231 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * Motherboard component
+ *
+ * VEMotherBoard.lisa
+ */
+
+	motherboard {
+		compatible = "arm,vexpress,v2m-p1", "simple-bus";
+		arm,hbi = <0x190>;
+		arm,vexpress,site = <0>;
+		arm,v2m-memory-map = "rs1";
+		#address-cells = <2>; /* SMB chipselect number and offset */
+		#size-cells = <1>;
+		#interrupt-cells = <1>;
+		ranges;
+
+		flash@0,00000000 {
+			compatible = "arm,vexpress-flash", "cfi-flash";
+			reg = <0 0x00000000 0x04000000>,
+			      <4 0x00000000 0x04000000>;
+			bank-width = <4>;
+		};
+
+		vram@2,00000000 {
+			compatible = "arm,vexpress-vram";
+			reg = <2 0x00000000 0x00800000>;
+		};
+
+		ethernet@2,02000000 {
+			compatible = "smsc,lan91c111";
+			reg = <2 0x02000000 0x10000>;
+			interrupts = <15>;
+		};
+
+		iofpga@3,00000000 {
+			compatible = "arm,amba-bus", "simple-bus";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 3 0 0x200000>;
+
+			v2m_sysreg: sysreg@010000 {
+				compatible = "arm,vexpress-sysreg";
+				reg = <0x010000 0x1000>;
+				gpio-controller;
+				#gpio-cells = <2>;
+			};
+
+			v2m_sysctl: sysctl@020000 {
+				compatible = "arm,sp810", "arm,primecell";
+				reg = <0x020000 0x1000>;
+				clocks = <&v2m_refclk32khz>, <&v2m_refclk1mhz>, <&smbclk>;
+				clock-names = "refclk", "timclk", "apb_pclk";
+				#clock-cells = <1>;
+				clock-output-names = "timerclken0", "timerclken1", "timerclken2", "timerclken3";
+			};
+
+			aaci@040000 {
+				compatible = "arm,pl041", "arm,primecell";
+				reg = <0x040000 0x1000>;
+				interrupts = <11>;
+				clocks = <&smbclk>;
+				clock-names = "apb_pclk";
+			};
+
+			mmci@050000 {
+				compatible = "arm,pl180", "arm,primecell";
+				reg = <0x050000 0x1000>;
+				interrupts = <9 10>;
+				cd-gpios = <&v2m_sysreg 0 0>;
+				wp-gpios = <&v2m_sysreg 1 0>;
+				max-frequency = <12000000>;
+				vmmc-supply = <&v2m_fixed_3v3>;
+				clocks = <&v2m_clk24mhz>, <&smbclk>;
+				clock-names = "mclk", "apb_pclk";
+			};
+
+			kmi@060000 {
+				compatible = "arm,pl050", "arm,primecell";
+				reg = <0x060000 0x1000>;
+				interrupts = <12>;
+				clocks = <&v2m_clk24mhz>, <&smbclk>;
+				clock-names = "KMIREFCLK", "apb_pclk";
+			};
+
+			kmi@070000 {
+				compatible = "arm,pl050", "arm,primecell";
+				reg = <0x070000 0x1000>;
+				interrupts = <13>;
+				clocks = <&v2m_clk24mhz>, <&smbclk>;
+				clock-names = "KMIREFCLK", "apb_pclk";
+			};
+
+			v2m_serial0: uart@090000 {
+				compatible = "arm,pl011", "arm,primecell";
+				reg = <0x090000 0x1000>;
+				interrupts = <5>;
+				clocks = <&v2m_clk24mhz>, <&smbclk>;
+				clock-names = "uartclk", "apb_pclk";
+			};
+
+			v2m_serial1: uart@0a0000 {
+				compatible = "arm,pl011", "arm,primecell";
+				reg = <0x0a0000 0x1000>;
+				interrupts = <6>;
+				clocks = <&v2m_clk24mhz>, <&smbclk>;
+				clock-names = "uartclk", "apb_pclk";
+			};
+
+			v2m_serial2: uart@0b0000 {
+				compatible = "arm,pl011", "arm,primecell";
+				reg = <0x0b0000 0x1000>;
+				interrupts = <7>;
+				clocks = <&v2m_clk24mhz>, <&smbclk>;
+				clock-names = "uartclk", "apb_pclk";
+			};
+
+			v2m_serial3: uart@0c0000 {
+				compatible = "arm,pl011", "arm,primecell";
+				reg = <0x0c0000 0x1000>;
+				interrupts = <8>;
+				clocks = <&v2m_clk24mhz>, <&smbclk>;
+				clock-names = "uartclk", "apb_pclk";
+			};
+
+			wdt@0f0000 {
+				compatible = "arm,sp805", "arm,primecell";
+				reg = <0x0f0000 0x1000>;
+				interrupts = <0>;
+				clocks = <&v2m_refclk32khz>, <&smbclk>;
+				clock-names = "wdogclk", "apb_pclk";
+			};
+
+			v2m_timer01: timer@110000 {
+				compatible = "arm,sp804", "arm,primecell";
+				reg = <0x110000 0x1000>;
+				interrupts = <2>;
+				clocks = <&v2m_sysctl 0>, <&v2m_sysctl 1>, <&smbclk>;
+				clock-names = "timclken1", "timclken2", "apb_pclk";
+			};
+
+			v2m_timer23: timer@120000 {
+				compatible = "arm,sp804", "arm,primecell";
+				reg = <0x120000 0x1000>;
+				interrupts = <3>;
+				clocks = <&v2m_sysctl 2>, <&v2m_sysctl 3>, <&smbclk>;
+				clock-names = "timclken1", "timclken2", "apb_pclk";
+			};
+
+			rtc@170000 {
+				compatible = "arm,pl031", "arm,primecell";
+				reg = <0x170000 0x1000>;
+				interrupts = <4>;
+				clocks = <&smbclk>;
+				clock-names = "apb_pclk";
+			};
+
+			clcd@1f0000 {
+				compatible = "arm,pl111", "arm,primecell";
+				reg = <0x1f0000 0x1000>;
+				interrupts = <14>;
+				clocks = <&v2m_oscclk1>, <&smbclk>;
+				clock-names = "v2m:oscclk1", "apb_pclk";
+				mode = "VGA";
+				use_dma = <0>;
+				framebuffer = <0x18000000 0x00180000>;
+			};
+
+			virtio_block@0130000 {
+				compatible = "virtio,mmio";
+				reg = <0x130000 0x200>;
+				interrupts = <42>;
+			};
+
+		};
+
+		v2m_fixed_3v3: fixedregulator@0 {
+			compatible = "regulator-fixed";
+			regulator-name = "3V3";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-always-on;
+		};
+
+		v2m_clk24mhz: clk24mhz {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <24000000>;
+			clock-output-names = "v2m:clk24mhz";
+		};
+
+		v2m_refclk1mhz: refclk1mhz {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <1000000>;
+			clock-output-names = "v2m:refclk1mhz";
+		};
+
+		v2m_refclk32khz: refclk32khz {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <32768>;
+			clock-output-names = "v2m:refclk32khz";
+		};
+
+		mcc {
+			compatible = "simple-bus";
+			arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+			v2m_oscclk1: osc@1 {
+				/* CLCD clock */
+				compatible = "arm,vexpress-osc";
+				arm,vexpress-sysreg,func = <1 1>;
+				freq-range = <23750000 63500000>;
+				#clock-cells = <0>;
+				clock-output-names = "v2m:oscclk1";
+			};
+
+			muxfpga@0 {
+				compatible = "arm,vexpress-muxfpga";
+				arm,vexpress-sysreg,func = <7 0>;
+			};
+
+			shutdown@0 {
+				compatible = "arm,vexpress-shutdown";
+				arm,vexpress-sysreg,func = <8 0>;
+			};
+		};
+	};
diff --git a/arch/arm/boot/dts/rtsm_ve-v2p-ca15x1-ca7x1.dts b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x1-ca7x1.dts
new file mode 100644
index 000000000000..c59f4b5cdf9e
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x1-ca7x1.dts
@@ -0,0 +1,233 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x4CT
+ * ARMCortexA7x4CT
+ * RTSM_VE_Cortex_A15x1_A7x1.lisa
+ */
+
+/dts-v1/;
+
+/memreserve/ 0xff000000 0x01000000;
+
+/ {
+	model = "RTSM_VE_CortexA15x1-A7x1";
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,rtsm_ve,cortex_a15x1_a7x1", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	clusters {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cluster0: cluster@0 {
+			reg = <0>;
+//			freqs = <500000000 600000000 700000000 800000000 900000000 1000000000 1100000000 1200000000>;
+			cores {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				core0: core@0 {
+					reg = <0>;
+				};
+
+			};
+		};
+
+		cluster1: cluster@1 {
+			reg = <1>;
+//			freqs = <350000000 400000000 500000000 600000000 700000000 800000000 900000000 1000000000>;
+			cores {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				core1: core@0 {
+					reg = <0>;
+				};
+
+			};
+		};
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+			cluster = <&cluster0>;
+			core = <&core0>;
+//			clock-frequency = <1000000000>;
+			cci-control-port = <&cci_control1>;
+		};
+
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x100>;
+			cluster = <&cluster1>;
+			core = <&core1>;
+//			clock-frequency = <800000000>;
+			cci-control-port = <&cci_control2>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0 0x80000000 0 0x80000000>;
+	};
+
+	cci@2c090000 {
+		compatible = "arm,cci-400", "arm,cci";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		reg = <0 0x2c090000 0 0x1000>;
+		ranges = <0x0 0x0 0x2c090000 0x10000>;
+
+		cci_control1: slave-if@4000 {
+			compatible = "arm,cci-400-ctrl-if";
+			interface-type = "ace";
+			reg = <0x4000 0x1000>;
+		};
+
+		cci_control2: slave-if@5000 {
+			compatible = "arm,cci-400-ctrl-if";
+			interface-type = "ace";
+			reg = <0x5000 0x1000>;
+		};
+	};
+
+	dcscb@60000000 {
+		compatible = "arm,rtsm,dcscb";
+		reg = <0 0x60000000 0 0x1000>;
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0 0x2c001000 0 0x1000>,
+		      <0 0x2c002000 0 0x1000>,
+		      <0 0x2c004000 0 0x2000>,
+		      <0 0x2c006000 0 0x2000>;
+		interrupts = <1 9 0xf04>;
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupts = <1 13 0xf08>,
+			     <1 14 0xf08>,
+			     <1 11 0xf08>,
+			     <1 10 0xf08>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			/* ACLK clock to the AXI master port on the test chip */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 0>;
+			freq-range = <30000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "extsaxiclk";
+		};
+
+		oscclk1: osc@1 {
+			/* Reference clock for the CLCD */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 1>;
+			freq-range = <10000000 80000000>;
+			#clock-cells = <0>;
+			clock-output-names = "clcdclk";
+		};
+
+		smbclk: oscclk2: osc@2 {
+			/* Reference clock for the test chip internal PLLs */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 2>;
+			freq-range = <33000000 100000000>;
+			#clock-cells = <0>;
+			clock-output-names = "tcrefclk";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-v2p-ca15x4-ca7x4.dts b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x4-ca7x4.dts
new file mode 100644
index 000000000000..5f1e727be28c
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x4-ca7x4.dts
@@ -0,0 +1,317 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x4CT
+ * ARMCortexA7x4CT
+ * RTSM_VE_Cortex_A15x4_A7x4.lisa
+ */
+
+/dts-v1/;
+
+/memreserve/ 0xff000000 0x01000000;
+
+/ {
+	model = "RTSM_VE_CortexA15x4-A7x4";
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,rtsm_ve,cortex_a15x4_a7x4", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	clusters {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cluster0: cluster@0 {
+			reg = <0>;
+//			freqs = <500000000 600000000 700000000 800000000 900000000 1000000000 1100000000 1200000000>;
+			cores {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				core0: core@0 {
+					reg = <0>;
+				};
+
+				core1: core@1 {
+					reg = <1>;
+				};
+
+				core2: core@2 {
+					reg = <2>;
+				};
+
+				core3: core@3 {
+					reg = <3>;
+				};
+
+			};
+		};
+
+		cluster1: cluster@1 {
+			reg = <1>;
+//			freqs = <350000000 400000000 500000000 600000000 700000000 800000000 900000000 1000000000>;
+			cores {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				core4: core@0 {
+					reg = <0>;
+				};
+
+				core5: core@1 {
+					reg = <1>;
+				};
+
+				core6: core@2 {
+					reg = <2>;
+				};
+				
+				core7: core@3 {
+					reg = <3>;
+				};
+				
+			};
+		};
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+			cluster = <&cluster0>;
+			core = <&core0>;
+//			clock-frequency = <1000000000>;
+			cci-control-port = <&cci_control1>;
+		};
+
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <1>;
+			cluster = <&cluster0>;
+			core = <&core1>;
+//			clock-frequency = <1000000000>;
+			cci-control-port = <&cci_control1>;
+		};
+
+		cpu2: cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <2>;
+			cluster = <&cluster0>;
+			core = <&core2>;
+//			clock-frequency = <1000000000>;
+			cci-control-port = <&cci_control1>;
+		};
+
+		cpu3: cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <3>;
+			cluster = <&cluster0>;
+			core = <&core3>;
+//			clock-frequency = <1000000000>;
+			cci-control-port = <&cci_control1>;
+		};
+
+		cpu4: cpu@4 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x100>;
+			cluster = <&cluster1>;
+			core = <&core4>;
+//			clock-frequency = <800000000>;
+			cci-control-port = <&cci_control2>;
+		};
+
+		cpu5: cpu@5 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x101>;
+			cluster = <&cluster1>;
+			core = <&core5>;
+//			clock-frequency = <800000000>;
+			cci-control-port = <&cci_control2>;
+		};
+		
+		cpu6: cpu@6 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x102>;
+			cluster = <&cluster1>;
+			core = <&core6>;
+//			clock-frequency = <800000000>;
+			cci-control-port = <&cci_control2>;
+		};
+		
+		cpu7: cpu@7 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x103>;
+			cluster = <&cluster1>;
+			core = <&core7>;
+//			clock-frequency = <800000000>;
+			cci-control-port = <&cci_control2>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0 0x80000000 0 0x80000000>;
+	};
+
+	cci@2c090000 {
+		compatible = "arm,cci-400", "arm,cci";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		reg = <0 0x2c090000 0 0x1000>;
+		ranges = <0x0 0x0 0x2c090000 0x10000>;
+
+		cci_control1: slave-if@4000 {
+			compatible = "arm,cci-400-ctrl-if";
+			interface-type = "ace";
+			reg = <0x4000 0x1000>;
+		};
+
+		cci_control2: slave-if@5000 {
+			compatible = "arm,cci-400-ctrl-if";
+			interface-type = "ace";
+			reg = <0x5000 0x1000>;
+		};
+	};
+
+	dcscb@60000000 {
+		compatible = "arm,rtsm,dcscb";
+		reg = <0 0x60000000 0 0x1000>;
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0 0x2c001000 0 0x1000>,
+		      <0 0x2c002000 0 0x1000>,
+		      <0 0x2c004000 0 0x2000>,
+		      <0 0x2c006000 0 0x2000>;
+		interrupts = <1 9 0xf04>;
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupts = <1 13 0xf08>,
+			     <1 14 0xf08>,
+			     <1 11 0xf08>,
+			     <1 10 0xf08>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			/* ACLK clock to the AXI master port on the test chip */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 0>;
+			freq-range = <30000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "extsaxiclk";
+		};
+
+		oscclk1: osc@1 {
+			/* Reference clock for the CLCD */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 1>;
+			freq-range = <10000000 80000000>;
+			#clock-cells = <0>;
+			clock-output-names = "clcdclk";
+		};
+
+		smbclk: oscclk2: osc@2 {
+			/* Reference clock for the test chip internal PLLs */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 2>;
+			freq-range = <33000000 100000000>;
+			#clock-cells = <0>;
+			clock-output-names = "tcrefclk";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
index ac870fb3fa0d..9584232ee6b6 100644
--- a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
+++ b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
@@ -228,6 +228,7 @@
 			};
 
 			clcd@1f0000 {
+				status = "disabled";
 				compatible = "arm,pl111", "arm,primecell";
 				reg = <0x1f0000 0x1000>;
 				interrupts = <14>;
diff --git a/arch/arm/boot/dts/vexpress-v2m.dtsi b/arch/arm/boot/dts/vexpress-v2m.dtsi
index f1420368355b..6593398c11ae 100644
--- a/arch/arm/boot/dts/vexpress-v2m.dtsi
+++ b/arch/arm/boot/dts/vexpress-v2m.dtsi
@@ -227,6 +227,7 @@
 			};
 
 			clcd@1f000 {
+				status = "disabled";
 				compatible = "arm,pl111", "arm,primecell";
 				reg = <0x1f000 0x1000>;
 				interrupts = <14>;
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts b/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts
index 9420053acc14..7cbe38cecf6c 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts
@@ -9,6 +9,8 @@
 
 /dts-v1/;
 
+/memreserve/ 0xbf000000 0x01000000;
+
 / {
 	model = "V2P-CA15";
 	arm,hbi = <0x237>;
@@ -57,6 +59,8 @@
 		interrupts = <0 85 4>;
 		clocks = <&oscclk5>;
 		clock-names = "pxlclk";
+		mode = "1024x768-16@60";
+		framebuffer = <0 0xbf000000 0 0x01000000>;
 	};
 
 	memory-controller@2b0a0000 {
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
index 15f98cbcb75a..e56356a249cd 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
@@ -9,6 +9,8 @@
 
 /dts-v1/;
 
+/memreserve/ 0xff000000 0x01000000;
+
 / {
 	model = "V2P-CA15_CA7";
 	arm,hbi = <0x249>;
@@ -29,29 +31,60 @@
 		i2c1 = &v2m_i2c_pcie;
 	};
 
-	cpus {
+	clusters {
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		cpu0: cpu@0 {
-			device_type = "cpu";
-			compatible = "arm,cortex-a15";
+		cluster0: cluster@0 {
 			reg = <0>;
-			cci-control-port = <&cci_control1>;
+			cores {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				core0: core@0 {
+					reg = <0>;
+				};
+
+				core1: core@1 {
+					reg = <1>;
+				};
+
+			};
 		};
 
-		cpu1: cpu@1 {
-			device_type = "cpu";
-			compatible = "arm,cortex-a15";
+		cluster1: cluster@1 {
 			reg = <1>;
-			cci-control-port = <&cci_control1>;
+			cores {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				core2: core@0 {
+					reg = <0>;
+				};
+
+				core3: core@1 {
+					reg = <1>;
+				};
+
+				core4: core@2 {
+					reg = <2>;
+				};
+			};
 		};
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
 
 		cpu2: cpu@2 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a7";
 			reg = <0x100>;
 			cci-control-port = <&cci_control2>;
+			cluster = <&cluster1>;
+			core = <&core2>;
+			clock-frequency = <800000000>;
 		};
 
 		cpu3: cpu@3 {
@@ -59,6 +92,9 @@
 			compatible = "arm,cortex-a7";
 			reg = <0x101>;
 			cci-control-port = <&cci_control2>;
+			cluster = <&cluster1>;
+			core = <&core3>;
+			clock-frequency = <800000000>;
 		};
 
 		cpu4: cpu@4 {
@@ -66,12 +102,35 @@
 			compatible = "arm,cortex-a7";
 			reg = <0x102>;
 			cci-control-port = <&cci_control2>;
+			cluster = <&cluster1>;
+			core = <&core4>;
+			clock-frequency = <800000000>;
+		};
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+			cci-control-port = <&cci_control1>;
+			cluster = <&cluster0>;
+			core = <&core0>;
+			clock-frequency = <1000000000>;
+		};
+
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <1>;
+			cci-control-port = <&cci_control1>;
+			cluster = <&cluster0>;
+			core = <&core1>;
+			clock-frequency = <1000000000>;
 		};
 	};
 
 	memory@80000000 {
 		device_type = "memory";
-		reg = <0 0x80000000 0 0x40000000>;
+		reg = <0 0x80000000 0 0x80000000>;
 	};
 
 	wdt@2a490000 {
@@ -86,6 +145,8 @@
 		compatible = "arm,hdlcd";
 		reg = <0 0x2b000000 0 0x1000>;
 		interrupts = <0 85 4>;
+		mode = "1024x768-16@60";
+		framebuffer = <0 0xff000000 0 0x01000000>;
 		clocks = <&oscclk5>;
 		clock-names = "pxlclk";
 	};
@@ -127,6 +188,16 @@
 			interface-type = "ace";
 			reg = <0x5000 0x1000>;
 		};
+
+		pmu@9000 {
+			 compatible = "arm,cci-400-pmu";
+			 reg = <0x9000 0x5000>;
+			 interrupts = <0 101 4>,
+				      <0 102 4>,
+				      <0 103 4>,
+				      <0 104 4>,
+				      <0 105 4>;
+		};
 	};
 
 	memory-controller@7ffd0000 {
@@ -164,12 +235,21 @@
 			     <1 10 0xf08>;
 	};
 
-	pmu {
+	pmu_a15 {
 		compatible = "arm,cortex-a15-pmu";
+		cluster  = <&cluster0>;
 		interrupts = <0 68 4>,
 			     <0 69 4>;
 	};
 
+	pmu_a7 {
+		compatible = "arm,cortex-a7-pmu";
+		cluster  = <&cluster1>;
+		interrupts = <0 128 4>,
+			     <0 129 4>,
+			     <0 130 4>;
+	};
+
 	oscclk6a: oscclk6a {
 		/* Reference 24MHz clock */
 		compatible = "fixed-clock";
@@ -178,6 +258,19 @@
 		clock-output-names = "oscclk6a";
 	};
 
+/* PSCI requires support from firmware and is not present in the normal TC2
+ * distribution, so this node is commented out by default...
+
+	psci {
+		compatible      = "arm,psci";
+		method          = "smc";
+		cpu_suspend     = <0x80100001>;
+		cpu_off         = <0x80100002>;
+		cpu_on          = <0x80100003>;
+		migrate         = <0x80100004>;
+	};
+*/
+
 	dcc {
 		compatible = "arm,vexpress,config-bus";
 		arm,vexpress,config-bridge = <&v2m_sysreg>;
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts
index c544a5504591..cf633ed6a1b4 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts
@@ -9,6 +9,8 @@
 
 /dts-v1/;
 
+/memreserve/ 0xbf000000 0x01000000;
+
 / {
 	model = "V2P-CA5s";
 	arm,hbi = <0x225>;
@@ -59,6 +61,8 @@
 		interrupts = <0 85 4>;
 		clocks = <&oscclk3>;
 		clock-names = "pxlclk";
+		mode = "640x480-16@60";
+		framebuffer = <0xbf000000 0x01000000>;
 	};
 
 	memory-controller@2a150000 {
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca9.dts b/arch/arm/boot/dts/vexpress-v2p-ca9.dts
index 62d9b225dcce..f83706bd3f9a 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca9.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca9.dts
@@ -9,6 +9,8 @@
 
 /dts-v1/;
 
+/include/ "clcd-panels.dtsi"
+
 / {
 	model = "V2P-CA9";
 	arm,hbi = <0x191>;
@@ -73,6 +75,8 @@
 		interrupts = <0 44 4>;
 		clocks = <&oscclk1>, <&oscclk2>;
 		clock-names = "clcdclk", "apb_pclk";
+		mode = "XVGA";
+		use_dma = <1>;
 	};
 
 	memory-controller@100e0000 {
diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile
index 4ff5d4c226bc..14e592312033 100644
--- a/arch/arm/common/Makefile
+++ b/arch/arm/common/Makefile
@@ -15,6 +15,7 @@ obj-$(CONFIG_SHARP_SCOOP)	+= scoop.o
 obj-$(CONFIG_PCI_HOST_ITE8152)  += it8152.o
 obj-$(CONFIG_ARM_TIMER_SP804)	+= timer-sp.o
 obj-$(CONFIG_MCPM)		+= mcpm_head.o mcpm_entry.o mcpm_platsmp.o vlock.o
+CFLAGS_REMOVE_mcpm_entry.o	= -pg
 AFLAGS_mcpm_head.o		:= -march=armv7-a
 AFLAGS_vlock.o			:= -march=armv7-a
 obj-$(CONFIG_TI_PRIV_EDMA)	+= edma.o
diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h
index 0704e0cf5571..be467f3780dd 100644
--- a/arch/arm/include/asm/arch_timer.h
+++ b/arch/arm/include/asm/arch_timer.h
@@ -107,7 +107,6 @@ static inline void arch_counter_set_user_access(void)
 	/* Also disable virtual event stream */
 	cntkctl &= ~(ARCH_TIMER_USR_PT_ACCESS_EN
 			| ARCH_TIMER_USR_VT_ACCESS_EN
-			| ARCH_TIMER_VIRT_EVT_EN
 			| ARCH_TIMER_USR_VCT_ACCESS_EN
 			| ARCH_TIMER_USR_PCT_ACCESS_EN);
 	arch_timer_set_cntkctl(cntkctl);
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h
index f24edad26c70..0cd7824ca762 100644
--- a/arch/arm/include/asm/pmu.h
+++ b/arch/arm/include/asm/pmu.h
@@ -62,9 +62,19 @@ struct pmu_hw_events {
 	raw_spinlock_t		pmu_lock;
 };
 
+struct cpupmu_regs {
+	u32 pmc;
+	u32 pmcntenset;
+	u32 pmuseren;
+	u32 pmintenset;
+	u32 pmxevttype[8];
+	u32 pmxevtcnt[8];
+};
+
 struct arm_pmu {
 	struct pmu	pmu;
 	cpumask_t	active_irqs;
+	cpumask_t	valid_cpus;
 	char		*name;
 	irqreturn_t	(*handle_irq)(int irq_num, void *dev);
 	void		(*enable)(struct perf_event *event);
@@ -81,6 +91,8 @@ struct arm_pmu {
 	int		(*request_irq)(struct arm_pmu *, irq_handler_t handler);
 	void		(*free_irq)(struct arm_pmu *);
 	int		(*map_event)(struct perf_event *event);
+	void		(*save_regs)(struct arm_pmu *, struct cpupmu_regs *);
+	void		(*restore_regs)(struct arm_pmu *, struct cpupmu_regs *);
 	int		num_events;
 	atomic_t	active_events;
 	struct mutex	reserve_mutex;
diff --git a/arch/arm/include/asm/psci.h b/arch/arm/include/asm/psci.h
index c4ae171850f8..eb628a6679e8 100644
--- a/arch/arm/include/asm/psci.h
+++ b/arch/arm/include/asm/psci.h
@@ -16,6 +16,10 @@
 
 #define PSCI_POWER_STATE_TYPE_STANDBY		0
 #define PSCI_POWER_STATE_TYPE_POWER_DOWN	1
+#define PSCI_POWER_STATE_AFFINITY_LEVEL0	0
+#define PSCI_POWER_STATE_AFFINITY_LEVEL1	1
+#define PSCI_POWER_STATE_AFFINITY_LEVEL2	2
+#define PSCI_POWER_STATE_AFFINITY_LEVEL3	3
 
 struct psci_power_state {
 	u16	id;
@@ -42,4 +46,12 @@ static inline void psci_init(void) { }
 static inline bool psci_smp_available(void) { return false; }
 #endif
 
+#ifdef CONFIG_ARM_PSCI
+extern int psci_probe(void);
+#else
+static inline int psci_probe(void)
+{
+	return -ENODEV;
+}
+#endif
 #endif /* __ASM_ARM_PSCI_H */
diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index 58b8b84adcd2..611edefaeaf1 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -26,11 +26,14 @@ extern struct cputopo_arm cpu_topology[NR_CPUS];
 void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
 const struct cpumask *cpu_coregroup_mask(int cpu);
+int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask);
 
 #else
 
 static inline void init_cpu_topology(void) { }
 static inline void store_cpu_topology(unsigned int cpuid) { }
+static inline int cluster_to_logical_mask(unsigned int socket_id,
+	cpumask_t *cluster_mask) { return -EINVAL; }
 
 #endif
 
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 789d846a9184..42059a54a9c0 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -12,6 +12,7 @@
  */
 #define pr_fmt(fmt) "hw perfevents: " fmt
 
+#include <linux/cpumask.h>
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
@@ -86,6 +87,9 @@ armpmu_map_event(struct perf_event *event,
 		return armpmu_map_cache_event(cache_map, config);
 	case PERF_TYPE_RAW:
 		return armpmu_map_raw_event(raw_event_mask, config);
+	default:
+		if (event->attr.type >= PERF_TYPE_MAX)
+			return armpmu_map_raw_event(raw_event_mask, config);
 	}
 
 	return -ENOENT;
@@ -159,6 +163,8 @@ armpmu_stop(struct perf_event *event, int flags)
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+		return;
 	/*
 	 * ARM pmu always has to update the counter, so ignore
 	 * PERF_EF_UPDATE, see comments in armpmu_start().
@@ -175,6 +181,8 @@ static void armpmu_start(struct perf_event *event, int flags)
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+		return;
 	/*
 	 * ARM pmu always has to reprogram the period, so ignore
 	 * PERF_EF_RELOAD, see the comment below.
@@ -202,6 +210,9 @@ armpmu_del(struct perf_event *event, int flags)
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+		return;
+
 	armpmu_stop(event, PERF_EF_UPDATE);
 	hw_events->events[idx] = NULL;
 	clear_bit(idx, hw_events->used_mask);
@@ -218,6 +229,10 @@ armpmu_add(struct perf_event *event, int flags)
 	int idx;
 	int err = 0;
 
+	/* An event following a process won't be stopped earlier */
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+		return 0;
+
 	perf_pmu_disable(event->pmu);
 
 	/* If we don't have a space for the counter then finish early. */
@@ -419,6 +434,10 @@ static int armpmu_event_init(struct perf_event *event)
 	int err = 0;
 	atomic_t *active_events = &armpmu->active_events;
 
+	if (event->cpu != -1 &&
+		!cpumask_test_cpu(event->cpu, &armpmu->valid_cpus))
+		return -ENOENT;
+
 	/* does not support taken branch sampling */
 	if (has_branch_stack(event))
 		return -EOPNOTSUPP;
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index 20d553c9f5e2..31c5cdefae3f 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -19,6 +19,7 @@
 #define pr_fmt(fmt) "CPU PMU: " fmt
 
 #include <linux/bitmap.h>
+#include <linux/cpu_pm.h>
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/of.h>
@@ -31,33 +32,36 @@
 #include <asm/pmu.h>
 
 /* Set at runtime when we know what CPU type we are. */
-static struct arm_pmu *cpu_pmu;
+static DEFINE_PER_CPU(struct arm_pmu *, cpu_pmu);
 
 static DEFINE_PER_CPU(struct perf_event * [ARMPMU_MAX_HWEVENTS], hw_events);
 static DEFINE_PER_CPU(unsigned long [BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)], used_mask);
 static DEFINE_PER_CPU(struct pmu_hw_events, cpu_hw_events);
 
+static DEFINE_PER_CPU(struct cpupmu_regs, cpu_pmu_regs);
+
 /*
  * Despite the names, these two functions are CPU-specific and are used
  * by the OProfile/perf code.
  */
 const char *perf_pmu_name(void)
 {
-	if (!cpu_pmu)
+	struct arm_pmu *pmu = per_cpu(cpu_pmu, 0);
+	if (!pmu)
 		return NULL;
 
-	return cpu_pmu->name;
+	return pmu->name;
 }
 EXPORT_SYMBOL_GPL(perf_pmu_name);
 
 int perf_num_counters(void)
 {
-	int max_events = 0;
+	struct arm_pmu *pmu = per_cpu(cpu_pmu, 0);
 
-	if (cpu_pmu != NULL)
-		max_events = cpu_pmu->num_events;
+	if (!pmu)
+		return 0;
 
-	return max_events;
+	return pmu->num_events;
 }
 EXPORT_SYMBOL_GPL(perf_num_counters);
 
@@ -75,11 +79,13 @@ static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
 {
 	int i, irq, irqs;
 	struct platform_device *pmu_device = cpu_pmu->plat_device;
+	int cpu = -1;
 
 	irqs = min(pmu_device->num_resources, num_possible_cpus());
 
 	for (i = 0; i < irqs; ++i) {
-		if (!cpumask_test_and_clear_cpu(i, &cpu_pmu->active_irqs))
+		cpu = cpumask_next(cpu, &cpu_pmu->valid_cpus);
+		if (!cpumask_test_and_clear_cpu(cpu, &cpu_pmu->active_irqs))
 			continue;
 		irq = platform_get_irq(pmu_device, i);
 		if (irq >= 0)
@@ -91,6 +97,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 {
 	int i, err, irq, irqs;
 	struct platform_device *pmu_device = cpu_pmu->plat_device;
+	int cpu = -1;
 
 	if (!pmu_device)
 		return -ENODEV;
@@ -103,6 +110,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 
 	for (i = 0; i < irqs; ++i) {
 		err = 0;
+		cpu = cpumask_next(cpu, &cpu_pmu->valid_cpus);
 		irq = platform_get_irq(pmu_device, i);
 		if (irq < 0)
 			continue;
@@ -112,7 +120,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 		 * assume that we're running on a uniprocessor machine and
 		 * continue. Otherwise, continue without this interrupt.
 		 */
-		if (irq_set_affinity(irq, cpumask_of(i)) && irqs > 1) {
+		if (irq_set_affinity(irq, cpumask_of(cpu)) && irqs > 1) {
 			pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
 				    irq, i);
 			continue;
@@ -127,7 +135,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 			return err;
 		}
 
-		cpumask_set_cpu(i, &cpu_pmu->active_irqs);
+		cpumask_set_cpu(cpu, &cpu_pmu->active_irqs);
 	}
 
 	return 0;
@@ -136,7 +144,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	int cpu;
-	for_each_possible_cpu(cpu) {
+	for_each_cpu_mask(cpu, cpu_pmu->valid_cpus) {
 		struct pmu_hw_events *events = &per_cpu(cpu_hw_events, cpu);
 		events->events = per_cpu(hw_events, cpu);
 		events->used_mask = per_cpu(used_mask, cpu);
@@ -149,7 +157,7 @@ static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
 
 	/* Ensure the PMU has sane values out of reset. */
 	if (cpu_pmu->reset)
-		on_each_cpu(cpu_pmu->reset, cpu_pmu, 1);
+		on_each_cpu_mask(&cpu_pmu->valid_cpus, cpu_pmu->reset, cpu_pmu, 1);
 }
 
 /*
@@ -161,21 +169,46 @@ static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
 static int cpu_pmu_notify(struct notifier_block *b, unsigned long action,
 			  void *hcpu)
 {
+	struct arm_pmu *pmu = per_cpu(cpu_pmu, (long)hcpu);
+
 	if ((action & ~CPU_TASKS_FROZEN) != CPU_STARTING)
 		return NOTIFY_DONE;
 
-	if (cpu_pmu && cpu_pmu->reset)
-		cpu_pmu->reset(cpu_pmu);
+	if (pmu && pmu->reset)
+		pmu->reset(pmu);
 	else
 		return NOTIFY_DONE;
 
 	return NOTIFY_OK;
 }
 
+static int cpu_pmu_pm_notify(struct notifier_block *b,
+				    unsigned long action, void *hcpu)
+{
+	int cpu = smp_processor_id();
+	struct arm_pmu *pmu = per_cpu(cpu_pmu, cpu);
+	struct cpupmu_regs *pmuregs = &per_cpu(cpu_pmu_regs, cpu);
+
+	if (!pmu)
+		return NOTIFY_DONE;
+
+	if (action == CPU_PM_ENTER && pmu->save_regs) {
+		pmu->save_regs(pmu, pmuregs);
+	} else if (action == CPU_PM_EXIT && pmu->restore_regs) {
+		pmu->restore_regs(pmu, pmuregs);
+	}
+
+	return NOTIFY_OK;
+}
+
 static struct notifier_block cpu_pmu_hotplug_notifier = {
 	.notifier_call = cpu_pmu_notify,
 };
 
+static struct notifier_block cpu_pmu_pm_notifier = {
+	.notifier_call = cpu_pmu_pm_notify,
+};
+
 /*
  * PMU platform driver and devicetree bindings.
  */
@@ -247,6 +280,9 @@ static int probe_current_pmu(struct arm_pmu *pmu)
 		}
 	}
 
+	/* assume PMU support all the CPUs in this case */
+	cpumask_setall(&pmu->valid_cpus);
+
 	put_cpu();
 	return ret;
 }
@@ -254,15 +290,10 @@ static int probe_current_pmu(struct arm_pmu *pmu)
 static int cpu_pmu_device_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *of_id;
-	const int (*init_fn)(struct arm_pmu *);
 	struct device_node *node = pdev->dev.of_node;
 	struct arm_pmu *pmu;
-	int ret = -ENODEV;
-
-	if (cpu_pmu) {
-		pr_info("attempt to register multiple PMU devices!");
-		return -ENOSPC;
-	}
+	int ret = 0;
+	int cpu;
 
 	pmu = kzalloc(sizeof(struct arm_pmu), GFP_KERNEL);
 	if (!pmu) {
@@ -271,8 +302,28 @@ static int cpu_pmu_device_probe(struct platform_device *pdev)
 	}
 
 	if (node && (of_id = of_match_node(cpu_pmu_of_device_ids, pdev->dev.of_node))) {
-		init_fn = of_id->data;
-		ret = init_fn(pmu);
+		smp_call_func_t init_fn = (smp_call_func_t)of_id->data;
+		struct device_node *ncluster;
+		int cluster = -1;
+		cpumask_t sibling_mask;
+
+		ncluster = of_parse_phandle(node, "cluster", 0);
+		if (ncluster) {
+			int len;
+			const u32 *hwid;
+			hwid = of_get_property(ncluster, "reg", &len);
+			if (hwid && len == 4)
+				cluster = be32_to_cpup(hwid);
+		}
+		/* set sibling mask to all cpu mask if socket is not specified */
+		if (cluster == -1 ||
+			cluster_to_logical_mask(cluster, &sibling_mask))
+			cpumask_setall(&sibling_mask);
+
+		smp_call_function_any(&sibling_mask, init_fn, pmu, 1);
+
+		/* now set the valid_cpus after init */
+		cpumask_copy(&pmu->valid_cpus, &sibling_mask);
 	} else {
 		ret = probe_current_pmu(pmu);
 	}
@@ -282,10 +333,12 @@ static int cpu_pmu_device_probe(struct platform_device *pdev)
 		goto out_free;
 	}
 
-	cpu_pmu = pmu;
-	cpu_pmu->plat_device = pdev;
-	cpu_pmu_init(cpu_pmu);
-	ret = armpmu_register(cpu_pmu, PERF_TYPE_RAW);
+	for_each_cpu_mask(cpu, pmu->valid_cpus)
+		per_cpu(cpu_pmu, cpu) = pmu;
+
+	pmu->plat_device = pdev;
+	cpu_pmu_init(pmu);
+	ret = armpmu_register(pmu, -1);
 
 	if (!ret)
 		return 0;
@@ -314,9 +367,17 @@ static int __init register_pmu_driver(void)
 	if (err)
 		return err;
 
+	err = cpu_pm_register_notifier(&cpu_pmu_pm_notifier);
+	if (err) {
+		unregister_cpu_notifier(&cpu_pmu_hotplug_notifier);
+		return err;
+	}
+
 	err = platform_driver_register(&cpu_pmu_driver);
-	if (err)
+	if (err) {
+		cpu_pm_unregister_notifier(&cpu_pmu_pm_notifier);
 		unregister_cpu_notifier(&cpu_pmu_hotplug_notifier);
+	}
 
 	return err;
 }
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 039cffb053a7..654db5030c31 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -950,6 +950,51 @@ static void armv7_pmnc_dump_regs(struct arm_pmu *cpu_pmu)
 }
 #endif
 
+static void armv7pmu_save_regs(struct arm_pmu *cpu_pmu,
+					struct cpupmu_regs *regs)
+{
+	unsigned int cnt;
+	asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (regs->pmc));
+	if (!(regs->pmc & ARMV7_PMNC_E))
+		return;
+
+	asm volatile("mrc p15, 0, %0, c9, c12, 1" : "=r" (regs->pmcntenset));
+	asm volatile("mrc p15, 0, %0, c9, c14, 0" : "=r" (regs->pmuseren));
+	asm volatile("mrc p15, 0, %0, c9, c14, 1" : "=r" (regs->pmintenset));
+	asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (regs->pmxevtcnt[0]));
+	for (cnt = ARMV7_IDX_COUNTER0;
+			cnt <= ARMV7_IDX_COUNTER_LAST(cpu_pmu); cnt++) {
+		armv7_pmnc_select_counter(cnt);
+		asm volatile("mrc p15, 0, %0, c9, c13, 1"
+					: "=r"(regs->pmxevttype[cnt]));
+		asm volatile("mrc p15, 0, %0, c9, c13, 2"
+					: "=r"(regs->pmxevtcnt[cnt]));
+	}
+	return;
+}
+
+static void armv7pmu_restore_regs(struct arm_pmu *cpu_pmu,
+					struct cpupmu_regs *regs)
+{
+	unsigned int cnt;
+	if (!(regs->pmc & ARMV7_PMNC_E))
+		return;
+
+	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (regs->pmcntenset));
+	asm volatile("mcr p15, 0, %0, c9, c14, 0" : : "r" (regs->pmuseren));
+	asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (regs->pmintenset));
+	asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (regs->pmxevtcnt[0]));
+	for (cnt = ARMV7_IDX_COUNTER0;
+			cnt <= ARMV7_IDX_COUNTER_LAST(cpu_pmu); cnt++) {
+		armv7_pmnc_select_counter(cnt);
+		asm volatile("mcr p15, 0, %0, c9, c13, 1"
+					: : "r"(regs->pmxevttype[cnt]));
+		asm volatile("mcr p15, 0, %0, c9, c13, 2"
+					: : "r"(regs->pmxevtcnt[cnt]));
+	}
+	asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r" (regs->pmc));
+}
+
 static void armv7pmu_enable_event(struct perf_event *event)
 {
 	unsigned long flags;
@@ -1223,6 +1268,8 @@ static void armv7pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->start		= armv7pmu_start;
 	cpu_pmu->stop		= armv7pmu_stop;
 	cpu_pmu->reset		= armv7pmu_reset;
+	cpu_pmu->save_regs	= armv7pmu_save_regs;
+	cpu_pmu->restore_regs	= armv7pmu_restore_regs;
 	cpu_pmu->max_period	= (1LLU << 32) - 1;
 };
 
@@ -1240,7 +1287,7 @@ static u32 armv7_read_num_pmnc_events(void)
 static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A8";
+	cpu_pmu->name		= "ARMv7_Cortex_A8";
 	cpu_pmu->map_event	= armv7_a8_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	return 0;
@@ -1249,7 +1296,7 @@ static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A9";
+	cpu_pmu->name		= "ARMv7_Cortex_A9";
 	cpu_pmu->map_event	= armv7_a9_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	return 0;
@@ -1258,7 +1305,7 @@ static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A5";
+	cpu_pmu->name		= "ARMv7_Cortex_A5";
 	cpu_pmu->map_event	= armv7_a5_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	return 0;
@@ -1267,7 +1314,7 @@ static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A15";
+	cpu_pmu->name		= "ARMv7_Cortex_A15";
 	cpu_pmu->map_event	= armv7_a15_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
@@ -1277,7 +1324,7 @@ static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A7";
+	cpu_pmu->name		= "ARMv7_Cortex_A7";
 	cpu_pmu->map_event	= armv7_a7_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
diff --git a/arch/arm/kernel/psci.c b/arch/arm/kernel/psci.c
index 46931880093d..e2c3fa8632e8 100644
--- a/arch/arm/kernel/psci.c
+++ b/arch/arm/kernel/psci.c
@@ -42,6 +42,7 @@ static u32 psci_function_id[PSCI_FN_MAX];
 #define PSCI_RET_EOPNOTSUPP		-1
 #define PSCI_RET_EINVAL			-2
 #define PSCI_RET_EPERM			-3
+#define PSCI_RET_EALREADYON		-4
 
 static int psci_to_linux_errno(int errno)
 {
@@ -54,6 +55,8 @@ static int psci_to_linux_errno(int errno)
 		return -EINVAL;
 	case PSCI_RET_EPERM:
 		return -EPERM;
+	case PSCI_RET_EALREADYON:
+		return -EAGAIN;
 	};
 
 	return -EINVAL;
@@ -153,7 +156,7 @@ static int psci_migrate(unsigned long cpuid)
 	return psci_to_linux_errno(err);
 }
 
-static const struct of_device_id psci_of_match[] __initconst = {
+static const struct of_device_id psci_of_match[] = {
 	{ .compatible = "arm,psci",	},
 	{},
 };
@@ -208,3 +211,16 @@ out_put_node:
 	of_node_put(np);
 	return;
 }
+
+int psci_probe(void)
+{
+	struct device_node *np;
+	int ret = -ENODEV;
+
+	np = of_find_matching_node(NULL, psci_of_match);
+	if (np)
+		ret = 0;
+
+	of_node_put(np);
+	return ret;
+}
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 1e8b030dbefd..4a5e9430f16b 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -273,6 +273,19 @@ static int cpu_has_aliasing_icache(unsigned int arch)
 	int aliasing_icache;
 	unsigned int id_reg, num_sets, line_size;
 
+#ifdef CONFIG_BIG_LITTLE
+	/*
+	 * We expect a combination of Cortex-A15 and Cortex-A7 cores.
+	 * A7 = VIPT aliasing I-cache
+	 * A15 = PIPT (non-aliasing) I-cache
+	 * To cater for this discrepancy, let's assume aliasing I-cache
+	 * all the time.  This means unneeded extra work on the A15 but
+	 * only ptrace is affected which is not performance critical.
+	 */
+	if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc0f0)
+		return 1;
+#endif
+
 	/* PIPT caches never alias. */
 	if (icache_is_pipt())
 		return 0;
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 0bc94b1fd1ae..d325410e02c8 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -267,6 +267,33 @@ void store_cpu_topology(unsigned int cpuid)
 }
 
 /*
+ * cluster_to_logical_mask - return cpu logical mask of CPUs in a cluster
+ * @socket_id:		cluster HW identifier
+ * @cluster_mask:	the cpumask location to be initialized, modified by the
+ *			function only if return value == 0
+ *
+ * Return:
+ *
+ * 0 on success
+ * -EINVAL if cluster_mask is NULL or there is no record matching socket_id
+ */
+int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask)
+{
+	int cpu;
+
+	if (!cluster_mask)
+		return -EINVAL;
+
+	for_each_online_cpu(cpu)
+		if (socket_id == topology_physical_package_id(cpu)) {
+			cpumask_copy(cluster_mask, topology_core_cpumask(cpu));
+			return 0;
+		}
+
+	return -EINVAL;
+}
+
+/*
  * init_cpu_topology is called at boot when only one cpu is running
  * which prevent simultaneous write access to cpu_topology array
  */
diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig
index 4a70be485ff8..556b01d305a8 100644
--- a/arch/arm/mach-vexpress/Kconfig
+++ b/arch/arm/mach-vexpress/Kconfig
@@ -55,6 +55,7 @@ config ARCH_VEXPRESS_CORTEX_A5_A9_ERRATA
 
 config ARCH_VEXPRESS_CA9X4
 	bool "Versatile Express Cortex-A9x4 tile"
+	select ARM_ERRATA_643719
 
 config ARCH_VEXPRESS_DCSCB
 	bool "Dual Cluster System Control Block (DCSCB) support"
diff --git a/arch/arm/mach-vexpress/Makefile b/arch/arm/mach-vexpress/Makefile
index 0997e0b7494c..191f2b591adc 100644
--- a/arch/arm/mach-vexpress/Makefile
+++ b/arch/arm/mach-vexpress/Makefile
@@ -8,8 +8,15 @@ obj-y					:= v2m.o
 obj-$(CONFIG_ARCH_VEXPRESS_CA9X4)	+= ct-ca9x4.o
 obj-$(CONFIG_ARCH_VEXPRESS_DCSCB)	+= dcscb.o	dcscb_setup.o
 CFLAGS_dcscb.o				+= -march=armv7-a
+CFLAGS_REMOVE_dcscb.o			= -pg
 obj-$(CONFIG_ARCH_VEXPRESS_SPC)		+= spc.o
+CFLAGS_REMOVE_spc.o			= -pg
 obj-$(CONFIG_ARCH_VEXPRESS_TC2_PM)	+= tc2_pm.o
 CFLAGS_tc2_pm.o				+= -march=armv7-a
+CFLAGS_REMOVE_tc2_pm.o			= -pg
+ifeq ($(CONFIG_ARCH_VEXPRESS_TC2_PM),y)
+obj-$(CONFIG_ARM_PSCI)			+= tc2_pm_psci.o
+CFLAGS_REMOVE_tc2_pm_psci.o		= -pg
+endif
 obj-$(CONFIG_SMP)			+= platsmp.o
 obj-$(CONFIG_HOTPLUG_CPU)		+= hotplug.o
diff --git a/arch/arm/mach-vexpress/dcscb.c b/arch/arm/mach-vexpress/dcscb.c
index 14d499688736..b35700f8e01f 100644
--- a/arch/arm/mach-vexpress/dcscb.c
+++ b/arch/arm/mach-vexpress/dcscb.c
@@ -23,6 +23,7 @@
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
 #include <asm/cp15.h>
+#include <asm/psci.h>
 
 
 #define RST_HOLD0	0x0
@@ -193,6 +194,12 @@ static int __init dcscb_init(void)
 	unsigned int cfg;
 	int ret;
 
+	ret = psci_probe();
+	if (!ret) {
+		pr_debug("psci found. Aborting native init\n");
+		return -ENODEV;
+	}
+
 	if (!cci_probed())
 		return -ENODEV;
 
diff --git a/arch/arm/mach-vexpress/tc2_pm.c b/arch/arm/mach-vexpress/tc2_pm.c
index 29e7785a54bc..a32a179080d5 100644
--- a/arch/arm/mach-vexpress/tc2_pm.c
+++ b/arch/arm/mach-vexpress/tc2_pm.c
@@ -27,6 +27,7 @@
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
 #include <asm/cp15.h>
+#include <asm/psci.h>
 
 #include <linux/arm-cci.h>
 
@@ -329,6 +330,12 @@ static int __init tc2_pm_init(void)
 	u32 a15_cluster_id, a7_cluster_id, sys_info;
 	struct device_node *np;
 
+	ret = psci_probe();
+	if (!ret) {
+		pr_debug("psci found. Aborting native init\n");
+		return -ENODEV;
+	}
+
 	/*
 	 * The power management-related features are hidden behind
 	 * SCC registers. We need to extract runtime information like
diff --git a/arch/arm/mach-vexpress/tc2_pm_psci.c b/arch/arm/mach-vexpress/tc2_pm_psci.c
new file mode 100644
index 000000000000..7cb2148caebc
--- /dev/null
+++ b/arch/arm/mach-vexpress/tc2_pm_psci.c
@@ -0,0 +1,173 @@
+/*
+ * arch/arm/mach-vexpress/tc2_pm_psci.c - TC2 PSCI support
+ *
+ * Created by: Achin Gupta, December 2012
+ * Copyright:  (C) 2012  ARM Limited
+ *
+ * Some portions of this file were originally written by Nicolas Pitre
+ * Copyright:   (C) 2012  Linaro Limited
+ *
+ * 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.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/spinlock.h>
+#include <linux/errno.h>
+
+#include <asm/mcpm.h>
+#include <asm/proc-fns.h>
+#include <asm/cacheflush.h>
+#include <asm/psci.h>
+#include <asm/atomic.h>
+#include <asm/cputype.h>
+#include <asm/cp15.h>
+
+#include <mach/motherboard.h>
+
+#include <linux/vexpress.h>
+
+/*
+ * Platform specific state id understood by the firmware and used to
+ * program the power controller
+ */
+#define PSCI_POWER_STATE_ID           0
+
+#define TC2_CLUSTERS			2
+#define TC2_MAX_CPUS_PER_CLUSTER	3
+
+static atomic_t tc2_pm_use_count[TC2_MAX_CPUS_PER_CLUSTER][TC2_CLUSTERS];
+
+static int tc2_pm_psci_power_up(unsigned int cpu, unsigned int cluster)
+{
+	unsigned int mpidr = (cluster << 8) | cpu;
+	int ret = 0;
+
+	BUG_ON(!psci_ops.cpu_on);
+
+	switch (atomic_inc_return(&tc2_pm_use_count[cpu][cluster])) {
+	case 1:
+		/*
+		 * This is a request to power up a cpu that linux thinks has
+		 * been powered down. Retries are needed if the firmware has
+		 * seen the power down request as yet.
+		 */
+		do
+			ret = psci_ops.cpu_on(mpidr,
+					      virt_to_phys(mcpm_entry_point));
+		while (ret == -EAGAIN);
+
+		return ret;
+	case 2:
+		/* This power up request has overtaken a power down request */
+		return ret;
+	default:
+		/* Any other value is a bug */
+		BUG();
+	}
+}
+
+static void tc2_pm_psci_power_down(void)
+{
+	struct psci_power_state power_state;
+	unsigned int mpidr, cpu, cluster;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+	BUG_ON(!psci_ops.cpu_off);
+
+	switch (atomic_dec_return(&tc2_pm_use_count[cpu][cluster])) {
+	case 1:
+		/*
+		 * Overtaken by a power up. Flush caches, exit coherency,
+		 * return & fake a reset
+		 */
+		set_cr(get_cr() & ~CR_C);
+
+		flush_cache_louis();
+
+		asm volatile ("clrex");
+		set_auxcr(get_auxcr() & ~(1 << 6));
+
+		return;
+	case 0:
+		/* A normal request to possibly power down the cluster */
+		power_state.id = PSCI_POWER_STATE_ID;
+		power_state.type = PSCI_POWER_STATE_TYPE_POWER_DOWN;
+		power_state.affinity_level = PSCI_POWER_STATE_AFFINITY_LEVEL1;
+
+		psci_ops.cpu_off(power_state);
+
+		/* On success this function never returns */
+	default:
+		/* Any other value is a bug */
+		BUG();
+	}
+}
+
+static void tc2_pm_psci_suspend(u64 unused)
+{
+	struct psci_power_state power_state;
+
+	BUG_ON(!psci_ops.cpu_suspend);
+
+	/* On TC2 always attempt to power down the cluster */
+	power_state.id = PSCI_POWER_STATE_ID;
+	power_state.type = PSCI_POWER_STATE_TYPE_POWER_DOWN;
+	power_state.affinity_level = PSCI_POWER_STATE_AFFINITY_LEVEL1;
+
+	psci_ops.cpu_suspend(power_state, virt_to_phys(mcpm_entry_point));
+
+	/* On success this function never returns */
+	BUG();
+}
+
+static const struct mcpm_platform_ops tc2_pm_power_ops = {
+	.power_up      = tc2_pm_psci_power_up,
+	.power_down    = tc2_pm_psci_power_down,
+	.suspend       = tc2_pm_psci_suspend,
+};
+
+static void __init tc2_pm_usage_count_init(void)
+{
+	unsigned int mpidr, cpu, cluster;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+	BUG_ON(cluster >= TC2_CLUSTERS || cpu >= TC2_MAX_CPUS_PER_CLUSTER);
+
+	atomic_set(&tc2_pm_use_count[cpu][cluster], 1);
+}
+
+static int __init tc2_pm_psci_init(void)
+{
+	int ret;
+
+	ret = psci_probe();
+	if (ret) {
+		pr_debug("psci not found. Aborting psci init\n");
+		return -ENODEV;
+	}
+
+	if (!of_machine_is_compatible("arm,vexpress,v2p-ca15_a7"))
+		return -ENODEV;
+
+	tc2_pm_usage_count_init();
+
+	ret = mcpm_platform_register(&tc2_pm_power_ops);
+	if (!ret)
+		ret = mcpm_sync_init(NULL);
+	if (!ret)
+		pr_info("TC2 power management using PSCI initialized\n");
+	return ret;
+}
+
+early_initcall(tc2_pm_psci_init);
diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c
index 4f8b8cb17ff5..ffa9b73b7d34 100644
--- a/arch/arm/mach-vexpress/v2m.c
+++ b/arch/arm/mach-vexpress/v2m.c
@@ -7,6 +7,7 @@
 #include <linux/io.h>
 #include <linux/smp.h>
 #include <linux/init.h>
+#include <linux/memblock.h>
 #include <linux/of_address.h>
 #include <linux/of_fdt.h>
 #include <linux/of_irq.h>
@@ -369,6 +370,31 @@ MACHINE_START(VEXPRESS, "ARM-Versatile Express")
 	.init_machine	= v2m_init,
 MACHINE_END
 
+static void __init v2m_dt_hdlcd_init(void)
+{
+	struct device_node *node;
+	int len, na, ns;
+	const __be32 *prop;
+	phys_addr_t fb_base, fb_size;
+
+	node = of_find_compatible_node(NULL, NULL, "arm,hdlcd");
+	if (!node)
+		return;
+
+	na = of_n_addr_cells(node);
+	ns = of_n_size_cells(node);
+
+	prop = of_get_property(node, "framebuffer", &len);
+	if (WARN_ON(!prop || len < (na + ns) * sizeof(*prop)))
+		return;
+
+	fb_base = of_read_number(prop, na);
+	fb_size = of_read_number(prop + na, ns);
+
+	if (WARN_ON(memblock_remove(fb_base, fb_size)))
+		return;
+};
+
 static struct map_desc v2m_rs1_io_desc __initdata = {
 	.virtual	= V2M_PERIPH,
 	.pfn		= __phys_to_pfn(0x1c000000),
@@ -421,6 +447,8 @@ void __init v2m_dt_init_early(void)
 	}
 
 	versatile_sched_clock_init(vexpress_get_24mhz_clock_base(), 24000000);
+
+	v2m_dt_hdlcd_init();
 }
 
 static const struct of_device_id v2m_dt_bus_match[] __initconst = {
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index b784579545e8..3bbfd5dbe741 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -449,8 +449,16 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 
 	if (pud_none(*pud_k))
 		goto bad_area;
-	if (!pud_present(*pud))
+	if (!pud_present(*pud)) {
 		set_pud(pud, *pud_k);
+		/*
+		 * There is a small window during free_pgtables() where the
+		 * user *pud entry is 0 but the TLB has not been invalidated
+		 * and we get a level 2 (pmd) translation fault caused by the
+		 * intermediate TLB caching of the old level 1 (pud) entry.
+		 */
+		flush_tlb_kernel_page(addr);
+	}
 
 	pmd = pmd_offset(pud, addr);
 	pmd_k = pmd_offset(pud_k, addr);
@@ -473,8 +481,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 #endif
 	if (pmd_none(pmd_k[index]))
 		goto bad_area;
+	if (!pmd_present(pmd[index]))
+		copy_pmd(pmd, pmd_k);
 
-	copy_pmd(pmd, pmd_k);
 	return 0;
 
 bad_area:
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index bede54fbcac3..845e7f157867 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -455,5 +455,8 @@ source "arch/arm64/Kconfig.debug"
 source "security/Kconfig"
 
 source "crypto/Kconfig"
+if CRYPTO
+source "arch/arm64/crypto/Kconfig"
+endif
 
 source "lib/Kconfig"
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 2fceb71ac3b7..8185a913c5ed 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -45,6 +45,7 @@ export	TEXT_OFFSET GZFLAGS
 core-y		+= arch/arm64/kernel/ arch/arm64/mm/
 core-$(CONFIG_KVM) += arch/arm64/kvm/
 core-$(CONFIG_XEN) += arch/arm64/xen/
+core-$(CONFIG_CRYPTO) += arch/arm64/crypto/
 libs-y		:= arch/arm64/lib/ $(libs-y)
 libs-y		+= $(LIBGCC)
 
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
new file mode 100644
index 000000000000..5562652c5316
--- /dev/null
+++ b/arch/arm64/crypto/Kconfig
@@ -0,0 +1,53 @@
+
+menuconfig ARM64_CRYPTO
+	bool "ARM64 Accelerated Cryptographic Algorithms"
+	depends on ARM64
+	help
+	  Say Y here to choose from a selection of cryptographic algorithms
+	  implemented using ARM64 specific CPU features or instructions.
+
+if ARM64_CRYPTO
+
+config CRYPTO_SHA1_ARM64_CE
+	tristate "SHA-1 digest algorithm (ARMv8 Crypto Extensions)"
+	depends on ARM64 && KERNEL_MODE_NEON
+	select CRYPTO_HASH
+
+config CRYPTO_SHA2_ARM64_CE
+	tristate "SHA-224/SHA-256 digest algorithm (ARMv8 Crypto Extensions)"
+	depends on ARM64 && KERNEL_MODE_NEON
+	select CRYPTO_HASH
+
+config CRYPTO_GHASH_ARM64_CE
+	tristate "GHASH (for GCM chaining mode) using ARMv8 Crypto Extensions"
+	depends on ARM64 && KERNEL_MODE_NEON
+	select CRYPTO_HASH
+
+config CRYPTO_AES_ARM64_CE
+	tristate "AES core cipher using ARMv8 Crypto Extensions"
+	depends on ARM64 && KERNEL_MODE_NEON
+	select CRYPTO_ALGAPI
+	select CRYPTO_AES
+
+config CRYPTO_AES_ARM64_CE_CCM
+	tristate "AES in CCM mode using ARMv8 Crypto Extensions"
+	depends on ARM64 && KERNEL_MODE_NEON
+	select CRYPTO_ALGAPI
+	select CRYPTO_AES
+	select CRYPTO_AEAD
+
+config CRYPTO_AES_ARM64_CE_BLK
+	tristate "AES in ECB/CBC/CTR/XTS modes using ARMv8 Crypto Extensions"
+	depends on ARM64 && KERNEL_MODE_NEON
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_AES
+	select CRYPTO_ABLK_HELPER
+
+config CRYPTO_AES_ARM64_NEON_BLK
+	tristate "AES in ECB/CBC/CTR/XTS modes using NEON instructions"
+	depends on ARM64 && KERNEL_MODE_NEON
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_AES
+	select CRYPTO_ABLK_HELPER
+
+endif
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
new file mode 100644
index 000000000000..2070a56ecc46
--- /dev/null
+++ b/arch/arm64/crypto/Makefile
@@ -0,0 +1,38 @@
+#
+# linux/arch/arm64/crypto/Makefile
+#
+# Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+#
+# 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.
+#
+
+obj-$(CONFIG_CRYPTO_SHA1_ARM64_CE) += sha1-ce.o
+sha1-ce-y := sha1-ce-glue.o sha1-ce-core.o
+
+obj-$(CONFIG_CRYPTO_SHA2_ARM64_CE) += sha2-ce.o
+sha2-ce-y := sha2-ce-glue.o sha2-ce-core.o
+
+obj-$(CONFIG_CRYPTO_GHASH_ARM64_CE) += ghash-ce.o
+ghash-ce-y := ghash-ce-glue.o ghash-ce-core.o
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_CE) += aes-ce-cipher.o
+CFLAGS_aes-ce-cipher.o += -march=armv8-a+crypto
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_CE_CCM) += aes-ce-ccm.o
+aes-ce-ccm-y := aes-ce-ccm-glue.o aes-ce-ccm-core.o
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_CE_BLK) += aes-ce-blk.o
+aes-ce-blk-y := aes-glue-ce.o aes-ce.o
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_NEON_BLK) += aes-neon-blk.o
+aes-neon-blk-y := aes-glue-neon.o aes-neon.o
+
+AFLAGS_aes-ce.o		:= -DINTERLEAVE=2 -DINTERLEAVE_INLINE
+AFLAGS_aes-neon.o	:= -DINTERLEAVE=4
+
+CFLAGS_aes-glue-ce.o	:= -DUSE_V8_CRYPTO_EXTENSIONS
+
+$(obj)/aes-glue-%.o: $(src)/aes-glue.c FORCE
+	$(call if_changed_dep,cc_o_c)
diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S
new file mode 100644
index 000000000000..432e4841cd81
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-ccm-core.S
@@ -0,0 +1,222 @@
+/*
+ * aesce-ccm-core.S - AES-CCM transform for ARMv8 with Crypto Extensions
+ *
+ * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * 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.
+ */
+
+#include <linux/linkage.h>
+
+	.text
+	.arch	armv8-a+crypto
+
+	/*
+	 * void ce_aes_ccm_auth_data(u8 mac[], u8 const in[], u32 abytes,
+	 *			     u32 *macp, u8 const rk[], u32 rounds);
+	 */
+ENTRY(ce_aes_ccm_auth_data)
+	ldr	w8, [x3]			/* leftover from prev round? */
+	ld1	{v0.2d}, [x0]			/* load mac */
+	cbz	w8, 1f
+	sub	w8, w8, #16
+	eor	v1.16b, v1.16b, v1.16b
+0:	ldrb	w7, [x1], #1			/* get 1 byte of input */
+	subs	w2, w2, #1
+	add	w8, w8, #1
+	ins	v1.b[0], w7
+	ext	v1.16b, v1.16b, v1.16b, #1	/* rotate in the input bytes */
+	beq	8f				/* out of input? */
+	cbnz	w8, 0b
+	eor	v0.16b, v0.16b, v1.16b
+1:	ld1	{v3.2d}, [x4]			/* load first round key */
+	prfm	pldl1strm, [x1]
+	cmp	w5, #12				/* which key size? */
+	add	x6, x4, #16
+	sub	w7, w5, #2			/* modified # of rounds */
+	bmi	2f
+	bne	5f
+	mov	v5.16b, v3.16b
+	b	4f
+2:	mov	v4.16b, v3.16b
+	ld1	{v5.2d}, [x6], #16		/* load 2nd round key */
+3:	aese	v0.16b, v4.16b
+	aesmc	v0.16b, v0.16b
+4:	ld1	{v3.2d}, [x6], #16		/* load next round key */
+	aese	v0.16b, v5.16b
+	aesmc	v0.16b, v0.16b
+5:	ld1	{v4.2d}, [x6], #16		/* load next round key */
+	subs	w7, w7, #3
+	aese	v0.16b, v3.16b
+	aesmc	v0.16b, v0.16b
+	ld1	{v5.2d}, [x6], #16		/* load next round key */
+	bpl	3b
+	aese	v0.16b, v4.16b
+	subs	w2, w2, #16			/* last data? */
+	eor	v0.16b, v0.16b, v5.16b		/* final round */
+	bmi	6f
+	ld1	{v1.16b}, [x1], #16		/* load next input block */
+	eor	v0.16b, v0.16b, v1.16b		/* xor with mac */
+	bne	1b
+6:	st1	{v0.2d}, [x0]			/* store mac */
+	beq	10f
+	adds	w2, w2, #16
+	beq	10f
+	mov	w8, w2
+7:	ldrb	w7, [x1], #1
+	umov	w6, v0.b[0]
+	eor	w6, w6, w7
+	strb	w6, [x0], #1
+	subs	w2, w2, #1
+	beq	10f
+	ext	v0.16b, v0.16b, v0.16b, #1	/* rotate out the mac bytes */
+	b	7b
+8:	mov	w7, w8
+	add	w8, w8, #16
+9:	ext	v1.16b, v1.16b, v1.16b, #1
+	adds	w7, w7, #1
+	bne	9b
+	eor	v0.16b, v0.16b, v1.16b
+	st1	{v0.2d}, [x0]
+10:	str	w8, [x3]
+	ret
+ENDPROC(ce_aes_ccm_auth_data)
+
+	/*
+	 * void ce_aes_ccm_final(u8 mac[], u8 const ctr[], u8 const rk[],
+	 * 			 u32 rounds);
+	 */
+ENTRY(ce_aes_ccm_final)
+	ld1	{v3.2d}, [x2], #16		/* load first round key */
+	ld1	{v0.2d}, [x0]			/* load mac */
+	cmp	w3, #12				/* which key size? */
+	sub	w3, w3, #2			/* modified # of rounds */
+	ld1	{v1.2d}, [x1]			/* load 1st ctriv */
+	bmi	0f
+	bne	3f
+	mov	v5.16b, v3.16b
+	b	2f
+0:	mov	v4.16b, v3.16b
+1:	ld1	{v5.2d}, [x2], #16		/* load next round key */
+	aese	v0.16b, v4.16b
+	aese	v1.16b, v4.16b
+	aesmc	v0.16b, v0.16b
+	aesmc	v1.16b, v1.16b
+2:	ld1	{v3.2d}, [x2], #16		/* load next round key */
+	aese	v0.16b, v5.16b
+	aese	v1.16b, v5.16b
+	aesmc	v0.16b, v0.16b
+	aesmc	v1.16b, v1.16b
+3:	ld1	{v4.2d}, [x2], #16		/* load next round key */
+	subs	w3, w3, #3
+	aese	v0.16b, v3.16b
+	aese	v1.16b, v3.16b
+	aesmc	v0.16b, v0.16b
+	aesmc	v1.16b, v1.16b
+	bpl	1b
+	aese	v0.16b, v4.16b
+	aese	v1.16b, v4.16b
+	/* final round key cancels out */
+	eor	v0.16b, v0.16b, v1.16b		/* en-/decrypt the mac */
+	st1	{v0.2d}, [x0]			/* store result */
+	ret
+ENDPROC(ce_aes_ccm_final)
+
+	.macro	aes_ccm_do_crypt,enc
+	ldr	x8, [x6, #8]			/* load lower ctr */
+	ld1	{v0.2d}, [x5]			/* load mac */
+	rev	x8, x8				/* keep swabbed ctr in reg */
+0:	/* outer loop */
+	ld1	{v1.1d}, [x6]			/* load upper ctr */
+	prfm	pldl1strm, [x1]
+	add	x8, x8, #1
+	rev	x9, x8
+	cmp	w4, #12				/* which key size? */
+	sub	w7, w4, #2			/* get modified # of rounds */
+	ins	v1.d[1], x9			/* no carry in lower ctr */
+	ld1	{v3.2d}, [x3]			/* load first round key */
+	add	x10, x3, #16
+	bmi	1f
+	bne	4f
+	mov	v5.16b, v3.16b
+	b	3f
+1:	mov	v4.16b, v3.16b
+	ld1	{v5.2d}, [x10], #16		/* load 2nd round key */
+2:	/* inner loop: 3 rounds, 2x interleaved */
+	aese	v0.16b, v4.16b
+	aese	v1.16b, v4.16b
+	aesmc	v0.16b, v0.16b
+	aesmc	v1.16b, v1.16b
+3:	ld1	{v3.2d}, [x10], #16		/* load next round key */
+	aese	v0.16b, v5.16b
+	aese	v1.16b, v5.16b
+	aesmc	v0.16b, v0.16b
+	aesmc	v1.16b, v1.16b
+4:	ld1	{v4.2d}, [x10], #16		/* load next round key */
+	subs	w7, w7, #3
+	aese	v0.16b, v3.16b
+	aese	v1.16b, v3.16b
+	aesmc	v0.16b, v0.16b
+	aesmc	v1.16b, v1.16b
+	ld1	{v5.2d}, [x10], #16		/* load next round key */
+	bpl	2b
+	aese	v0.16b, v4.16b
+	aese	v1.16b, v4.16b
+	subs	w2, w2, #16
+	bmi	6f				/* partial block? */
+	ld1	{v2.16b}, [x1], #16		/* load next input block */
+	.if	\enc == 1
+	eor	v2.16b, v2.16b, v5.16b		/* final round enc+mac */
+	eor	v1.16b, v1.16b, v2.16b		/* xor with crypted ctr */
+	.else
+	eor	v2.16b, v2.16b, v1.16b		/* xor with crypted ctr */
+	eor	v1.16b, v2.16b, v5.16b		/* final round enc */
+	.endif
+	eor	v0.16b, v0.16b, v2.16b		/* xor mac with pt ^ rk[last] */
+	st1	{v1.16b}, [x0], #16		/* write output block */
+	bne	0b
+	rev	x8, x8
+	st1	{v0.2d}, [x5]			/* store mac */
+	str	x8, [x6, #8]			/* store lsb end of ctr (BE) */
+5:	ret
+
+6:	eor	v0.16b, v0.16b, v5.16b		/* final round mac */
+	eor	v1.16b, v1.16b, v5.16b		/* final round enc */
+	st1	{v0.2d}, [x5]			/* store mac */
+	add	w2, w2, #16			/* process partial tail block */
+7:	ldrb	w9, [x1], #1			/* get 1 byte of input */
+	umov	w6, v1.b[0]			/* get top crypted ctr byte */
+	umov	w7, v0.b[0]			/* get top mac byte */
+	.if	\enc == 1
+	eor	w7, w7, w9
+	eor	w9, w9, w6
+	.else
+	eor	w9, w9, w6
+	eor	w7, w7, w9
+	.endif
+	strb	w9, [x0], #1			/* store out byte */
+	strb	w7, [x5], #1			/* store mac byte */
+	subs	w2, w2, #1
+	beq	5b
+	ext	v0.16b, v0.16b, v0.16b, #1	/* shift out mac byte */
+	ext	v1.16b, v1.16b, v1.16b, #1	/* shift out ctr byte */
+	b	7b
+	.endm
+
+	/*
+	 * void ce_aes_ccm_encrypt(u8 out[], u8 const in[], u32 cbytes,
+	 * 			   u8 const rk[], u32 rounds, u8 mac[],
+	 * 			   u8 ctr[]);
+	 * void ce_aes_ccm_decrypt(u8 out[], u8 const in[], u32 cbytes,
+	 * 			   u8 const rk[], u32 rounds, u8 mac[],
+	 * 			   u8 ctr[]);
+	 */
+ENTRY(ce_aes_ccm_encrypt)
+	aes_ccm_do_crypt	1
+ENDPROC(ce_aes_ccm_encrypt)
+
+ENTRY(ce_aes_ccm_decrypt)
+	aes_ccm_do_crypt	0
+ENDPROC(ce_aes_ccm_decrypt)
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
new file mode 100644
index 000000000000..9e6cdde9b43d
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -0,0 +1,297 @@
+/*
+ * aes-ccm-glue.c - AES-CCM transform for ARMv8 with Crypto Extensions
+ *
+ * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * 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.
+ */
+
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+#include <crypto/aes.h>
+#include <crypto/algapi.h>
+#include <crypto/scatterwalk.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+static int num_rounds(struct crypto_aes_ctx *ctx)
+{
+	/*
+	 * # of rounds specified by AES:
+	 * 128 bit key		10 rounds
+	 * 192 bit key		12 rounds
+	 * 256 bit key		14 rounds
+	 * => n byte key	=> 6 + (n/4) rounds
+	 */
+	return 6 + ctx->key_length / 4;
+}
+
+asmlinkage void ce_aes_ccm_auth_data(u8 mac[], u8 const in[], u32 abytes,
+				     u32 *macp, u32 const rk[], u32 rounds);
+
+asmlinkage void ce_aes_ccm_encrypt(u8 out[], u8 const in[], u32 cbytes,
+				   u32 const rk[], u32 rounds, u8 mac[],
+				   u8 ctr[]);
+
+asmlinkage void ce_aes_ccm_decrypt(u8 out[], u8 const in[], u32 cbytes,
+				   u32 const rk[], u32 rounds, u8 mac[],
+				   u8 ctr[]);
+
+asmlinkage void ce_aes_ccm_final(u8 mac[], u8 const ctr[], u32 const rk[],
+				 u32 rounds);
+
+static int ccm_setkey(struct crypto_aead *tfm, const u8 *in_key,
+		      unsigned int key_len)
+{
+	struct crypto_aes_ctx *ctx = crypto_aead_ctx(tfm);
+	int ret;
+
+	ret = crypto_aes_expand_key(ctx, in_key, key_len);
+	if (!ret)
+		return 0;
+
+	tfm->base.crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+	return -EINVAL;
+}
+
+static int ccm_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
+{
+	if ((authsize & 1) || authsize < 4)
+		return -EINVAL;
+	return 0;
+}
+
+static int ccm_init_mac(struct aead_request *req, u8 maciv[], u32 msglen)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	__be32 *n = (__be32 *)&maciv[AES_BLOCK_SIZE - 8];
+	u32 l = req->iv[0] + 1;
+
+	/* verify that CCM dimension 'L' is set correctly in the IV */
+	if (l < 2 || l > 8)
+		return -EINVAL;
+
+	/* verify that msglen can in fact be represented in L bytes */
+	if (l < 4 && msglen >> (8 * l))
+		return -EOVERFLOW;
+
+	/*
+	 * Even if the CCM spec allows L values of up to 8, the Linux cryptoapi
+	 * uses a u32 type to represent msglen so the top 4 bytes are always 0.
+	 */
+	n[0] = 0;
+	n[1] = cpu_to_be32(msglen);
+
+	memcpy(maciv, req->iv, AES_BLOCK_SIZE - l);
+
+	/*
+	 * Meaning of byte 0 according to CCM spec (RFC 3610/NIST 800-38C)
+	 * - bits 0..2	: max # of bytes required to represent msglen, minus 1
+	 *                (already set by caller)
+	 * - bits 3..5	: size of auth tag (1 => 4 bytes, 2 => 6 bytes, etc)
+	 * - bit 6	: indicates presence of authenticate-only data
+	 */
+	maciv[0] |= (crypto_aead_authsize(aead) - 2) << 2;
+	if (req->assoclen)
+		maciv[0] |= 0x40;
+
+	memset(&req->iv[AES_BLOCK_SIZE - l], 0, l);
+	return 0;
+}
+
+static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[])
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead);
+	struct __packed { __be16 l; __be32 h; u16 len; } ltag;
+	struct scatter_walk walk;
+	u32 len = req->assoclen;
+	u32 macp = 0;
+
+	/* prepend the AAD with a length tag */
+	if (len < 0xff00) {
+		ltag.l = cpu_to_be16(len);
+		ltag.len = 2;
+	} else  {
+		ltag.l = cpu_to_be16(0xfffe);
+		put_unaligned_be32(len, &ltag.h);
+		ltag.len = 6;
+	}
+
+	ce_aes_ccm_auth_data(mac, (u8 *)&ltag, ltag.len, &macp, ctx->key_enc,
+			     num_rounds(ctx));
+	scatterwalk_start(&walk, req->assoc);
+
+	do {
+		u32 n = scatterwalk_clamp(&walk, len);
+		u8 *p;
+
+		if (!n) {
+			scatterwalk_start(&walk, sg_next(walk.sg));
+			n = scatterwalk_clamp(&walk, len);
+		}
+		p = scatterwalk_map(&walk);
+		ce_aes_ccm_auth_data(mac, p, n, &macp, ctx->key_enc,
+				     num_rounds(ctx));
+		len -= n;
+
+		scatterwalk_unmap(p);
+		scatterwalk_advance(&walk, n);
+		scatterwalk_done(&walk, 0, len);
+	} while (len);
+}
+
+static int ccm_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead);
+	struct blkcipher_desc desc = { .info = req->iv };
+	struct blkcipher_walk walk;
+	u8 __aligned(8) mac[AES_BLOCK_SIZE];
+	u8 buf[AES_BLOCK_SIZE];
+	u32 len = req->cryptlen;
+	int err;
+
+	err = ccm_init_mac(req, mac, len);
+	if (err)
+		return err;
+
+	kernel_neon_begin_partial(6);
+
+	if (req->assoclen)
+		ccm_calculate_auth_mac(req, mac);
+
+	/* preserve the original iv for the final round */
+	memcpy(buf, req->iv, AES_BLOCK_SIZE);
+
+	blkcipher_walk_init(&walk, req->dst, req->src, len);
+	err = blkcipher_aead_walk_virt_block(&desc, &walk, aead,
+					     AES_BLOCK_SIZE);
+
+	while (walk.nbytes) {
+		u32 tail = walk.nbytes % AES_BLOCK_SIZE;
+
+		if (walk.nbytes == len)
+			tail = 0;
+
+		ce_aes_ccm_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				   walk.nbytes - tail, ctx->key_enc,
+				   num_rounds(ctx), mac, walk.iv);
+
+		len -= walk.nbytes - tail;
+		err = blkcipher_walk_done(&desc, &walk, tail);
+	}
+	if (!err)
+		ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx));
+
+	kernel_neon_end();
+
+	if (err)
+		return err;
+
+	/* copy authtag to end of dst */
+	scatterwalk_map_and_copy(mac, req->dst, req->cryptlen,
+				 crypto_aead_authsize(aead), 1);
+
+	return 0;
+}
+
+static int ccm_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead);
+	unsigned int authsize = crypto_aead_authsize(aead);
+	struct blkcipher_desc desc = { .info = req->iv };
+	struct blkcipher_walk walk;
+	u8 __aligned(8) mac[AES_BLOCK_SIZE];
+	u8 buf[AES_BLOCK_SIZE];
+	u32 len = req->cryptlen - authsize;
+	int err;
+
+	err = ccm_init_mac(req, mac, len);
+	if (err)
+		return err;
+
+	kernel_neon_begin_partial(6);
+
+	if (req->assoclen)
+		ccm_calculate_auth_mac(req, mac);
+
+	/* preserve the original iv for the final round */
+	memcpy(buf, req->iv, AES_BLOCK_SIZE);
+
+	blkcipher_walk_init(&walk, req->dst, req->src, len);
+	err = blkcipher_aead_walk_virt_block(&desc, &walk, aead,
+					     AES_BLOCK_SIZE);
+
+	while (walk.nbytes) {
+		u32 tail = walk.nbytes % AES_BLOCK_SIZE;
+
+		if (walk.nbytes == len)
+			tail = 0;
+
+		ce_aes_ccm_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				   walk.nbytes - tail, ctx->key_enc,
+				   num_rounds(ctx), mac, walk.iv);
+
+		len -= walk.nbytes - tail;
+		err = blkcipher_walk_done(&desc, &walk, tail);
+	}
+	if (!err)
+		ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx));
+
+	kernel_neon_end();
+
+	if (err)
+		return err;
+
+	/* compare calculated auth tag with the stored one */
+	scatterwalk_map_and_copy(buf, req->src, req->cryptlen - authsize,
+				 authsize, 0);
+
+	if (memcmp(mac, buf, authsize))
+		return -EBADMSG;
+	return 0;
+}
+
+static struct crypto_alg ccm_aes_alg = {
+	.cra_name		= "ccm(aes)",
+	.cra_driver_name	= "ccm-aes-ce",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_AEAD,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_aead_type,
+	.cra_module		= THIS_MODULE,
+	.cra_aead = {
+		.ivsize		= AES_BLOCK_SIZE,
+		.maxauthsize	= AES_BLOCK_SIZE,
+		.setkey		= ccm_setkey,
+		.setauthsize	= ccm_setauthsize,
+		.encrypt	= ccm_encrypt,
+		.decrypt	= ccm_decrypt,
+	}
+};
+
+static int __init aes_mod_init(void)
+{
+	if (!(elf_hwcap & HWCAP_AES))
+		return -ENODEV;
+	return crypto_register_alg(&ccm_aes_alg);
+}
+
+static void __exit aes_mod_exit(void)
+{
+	crypto_unregister_alg(&ccm_aes_alg);
+}
+
+module_init(aes_mod_init);
+module_exit(aes_mod_exit);
+
+MODULE_DESCRIPTION("Synchronous AES in CCM mode using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("ccm(aes)");
diff --git a/arch/arm64/crypto/aes-ce-cipher.c b/arch/arm64/crypto/aes-ce-cipher.c
new file mode 100644
index 000000000000..2075e1acae6b
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-cipher.c
@@ -0,0 +1,155 @@
+/*
+ * aes-ce-cipher.c - core AES cipher using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * 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.
+ */
+
+#include <asm/neon.h>
+#include <crypto/aes.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("Synchronous AES cipher using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+struct aes_block {
+	u8 b[AES_BLOCK_SIZE];
+};
+
+static int num_rounds(struct crypto_aes_ctx *ctx)
+{
+	/*
+	 * # of rounds specified by AES:
+	 * 128 bit key		10 rounds
+	 * 192 bit key		12 rounds
+	 * 256 bit key		14 rounds
+	 * => n byte key	=> 6 + (n/4) rounds
+	 */
+	return 6 + ctx->key_length / 4;
+}
+
+static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
+{
+	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct aes_block *out = (struct aes_block *)dst;
+	struct aes_block const *in = (struct aes_block *)src;
+	void *dummy0;
+	int dummy1;
+
+	kernel_neon_begin_partial(4);
+
+	__asm__("	ld1	{v0.16b}, %[in]			;"
+		"	ld1	{v1.2d}, [%[key]], #16		;"
+		"	cmp	%w[rounds], #10			;"
+		"	bmi	0f				;"
+		"	bne	3f				;"
+		"	mov	v3.16b, v1.16b			;"
+		"	b	2f				;"
+		"0:	mov	v2.16b, v1.16b			;"
+		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"1:	aese	v0.16b, v2.16b			;"
+		"	aesmc	v0.16b, v0.16b			;"
+		"2:	ld1	{v1.2d}, [%[key]], #16		;"
+		"	aese	v0.16b, v3.16b			;"
+		"	aesmc	v0.16b, v0.16b			;"
+		"3:	ld1	{v2.2d}, [%[key]], #16		;"
+		"	subs	%w[rounds], %w[rounds], #3	;"
+		"	aese	v0.16b, v1.16b			;"
+		"	aesmc	v0.16b, v0.16b			;"
+		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"	bpl	1b				;"
+		"	aese	v0.16b, v2.16b			;"
+		"	eor	v0.16b, v0.16b, v3.16b		;"
+		"	st1	{v0.16b}, %[out]		;"
+
+	:	[out]		"=Q"(*out),
+		[key]		"=r"(dummy0),
+		[rounds]	"=r"(dummy1)
+	:	[in]		"Q"(*in),
+				"1"(ctx->key_enc),
+				"2"(num_rounds(ctx) - 2)
+	:	"cc");
+
+	kernel_neon_end();
+}
+
+static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
+{
+	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct aes_block *out = (struct aes_block *)dst;
+	struct aes_block const *in = (struct aes_block *)src;
+	void *dummy0;
+	int dummy1;
+
+	kernel_neon_begin_partial(4);
+
+	__asm__("	ld1	{v0.16b}, %[in]			;"
+		"	ld1	{v1.2d}, [%[key]], #16		;"
+		"	cmp	%w[rounds], #10			;"
+		"	bmi	0f				;"
+		"	bne	3f				;"
+		"	mov	v3.16b, v1.16b			;"
+		"	b	2f				;"
+		"0:	mov	v2.16b, v1.16b			;"
+		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"1:	aesd	v0.16b, v2.16b			;"
+		"	aesimc	v0.16b, v0.16b			;"
+		"2:	ld1	{v1.2d}, [%[key]], #16		;"
+		"	aesd	v0.16b, v3.16b			;"
+		"	aesimc	v0.16b, v0.16b			;"
+		"3:	ld1	{v2.2d}, [%[key]], #16		;"
+		"	subs	%w[rounds], %w[rounds], #3	;"
+		"	aesd	v0.16b, v1.16b			;"
+		"	aesimc	v0.16b, v0.16b			;"
+		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"	bpl	1b				;"
+		"	aesd	v0.16b, v2.16b			;"
+		"	eor	v0.16b, v0.16b, v3.16b		;"
+		"	st1	{v0.16b}, %[out]		;"
+
+	:	[out]		"=Q"(*out),
+		[key]		"=r"(dummy0),
+		[rounds]	"=r"(dummy1)
+	:	[in]		"Q"(*in),
+				"1"(ctx->key_dec),
+				"2"(num_rounds(ctx) - 2)
+	:	"cc");
+
+	kernel_neon_end();
+}
+
+static struct crypto_alg aes_alg = {
+	.cra_name		= "aes",
+	.cra_driver_name	= "aes-ce",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+	.cra_module		= THIS_MODULE,
+	.cra_cipher = {
+		.cia_min_keysize	= AES_MIN_KEY_SIZE,
+		.cia_max_keysize	= AES_MAX_KEY_SIZE,
+		.cia_setkey		= crypto_aes_set_key,
+		.cia_encrypt		= aes_cipher_encrypt,
+		.cia_decrypt		= aes_cipher_decrypt
+	}
+};
+
+static int __init aes_mod_init(void)
+{
+	return crypto_register_alg(&aes_alg);
+}
+
+static void __exit aes_mod_exit(void)
+{
+	crypto_unregister_alg(&aes_alg);
+}
+
+module_cpu_feature_match(AES, aes_mod_init);
+module_exit(aes_mod_exit);
diff --git a/arch/arm64/crypto/aes-ce.S b/arch/arm64/crypto/aes-ce.S
new file mode 100644
index 000000000000..685a18f731eb
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce.S
@@ -0,0 +1,133 @@
+/*
+ * linux/arch/arm64/crypto/aes-ce.S - AES cipher for ARMv8 with
+ *                                    Crypto Extensions
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * 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.
+ */
+
+#include <linux/linkage.h>
+
+#define AES_ENTRY(func)		ENTRY(ce_ ## func)
+#define AES_ENDPROC(func)	ENDPROC(ce_ ## func)
+
+	.arch		armv8-a+crypto
+
+	/* preload all round keys */
+	.macro		load_round_keys, rounds, rk
+	cmp		\rounds, #12
+	blo		2222f		/* 128 bits */
+	beq		1111f		/* 192 bits */
+	ld1		{v17.16b-v18.16b}, [\rk], #32
+1111:	ld1		{v19.16b-v20.16b}, [\rk], #32
+2222:	ld1		{v21.16b-v24.16b}, [\rk], #64
+	ld1		{v25.16b-v28.16b}, [\rk], #64
+	ld1		{v29.16b-v31.16b}, [\rk]
+	.endm
+
+	/* prepare for encryption with key in rk[] */
+	.macro		enc_prepare, rounds, rk, ignore
+	load_round_keys	\rounds, \rk
+	.endm
+
+	/* prepare for encryption (again) but with new key in rk[] */
+	.macro		enc_switch_key, rounds, rk, ignore
+	load_round_keys	\rounds, \rk
+	.endm
+
+	/* prepare for decryption with key in rk[] */
+	.macro		dec_prepare, rounds, rk, ignore
+	load_round_keys	\rounds, \rk
+	.endm
+
+	.macro		do_enc_Nx, de, mc, k, i0, i1, i2, i3
+	aes\de		\i0\().16b, \k\().16b
+	.ifnb		\i1
+	aes\de		\i1\().16b, \k\().16b
+	.ifnb		\i3
+	aes\de		\i2\().16b, \k\().16b
+	aes\de		\i3\().16b, \k\().16b
+	.endif
+	.endif
+	aes\mc		\i0\().16b, \i0\().16b
+	.ifnb		\i1
+	aes\mc		\i1\().16b, \i1\().16b
+	.ifnb		\i3
+	aes\mc		\i2\().16b, \i2\().16b
+	aes\mc		\i3\().16b, \i3\().16b
+	.endif
+	.endif
+	.endm
+
+	/* up to 4 interleaved encryption rounds with the same round key */
+	.macro		round_Nx, enc, k, i0, i1, i2, i3
+	.ifc		\enc, e
+	do_enc_Nx	e, mc, \k, \i0, \i1, \i2, \i3
+	.else
+	do_enc_Nx	d, imc, \k, \i0, \i1, \i2, \i3
+	.endif
+	.endm
+
+	/* up to 4 interleaved final rounds */
+	.macro		fin_round_Nx, de, k, k2, i0, i1, i2, i3
+	aes\de		\i0\().16b, \k\().16b
+	.ifnb		\i1
+	aes\de		\i1\().16b, \k\().16b
+	.ifnb		\i3
+	aes\de		\i2\().16b, \k\().16b
+	aes\de		\i3\().16b, \k\().16b
+	.endif
+	.endif
+	eor		\i0\().16b, \i0\().16b, \k2\().16b
+	.ifnb		\i1
+	eor		\i1\().16b, \i1\().16b, \k2\().16b
+	.ifnb		\i3
+	eor		\i2\().16b, \i2\().16b, \k2\().16b
+	eor		\i3\().16b, \i3\().16b, \k2\().16b
+	.endif
+	.endif
+	.endm
+
+	/* up to 4 interleaved blocks */
+	.macro		do_block_Nx, enc, rounds, i0, i1, i2, i3
+	cmp		\rounds, #12
+	blo		2222f		/* 128 bits */
+	beq		1111f		/* 192 bits */
+	round_Nx	\enc, v17, \i0, \i1, \i2, \i3
+	round_Nx	\enc, v18, \i0, \i1, \i2, \i3
+1111:	round_Nx	\enc, v19, \i0, \i1, \i2, \i3
+	round_Nx	\enc, v20, \i0, \i1, \i2, \i3
+2222:	.irp		key, v21, v22, v23, v24, v25, v26, v27, v28, v29
+	round_Nx	\enc, \key, \i0, \i1, \i2, \i3
+	.endr
+	fin_round_Nx	\enc, v30, v31, \i0, \i1, \i2, \i3
+	.endm
+
+	.macro		encrypt_block, in, rounds, t0, t1, t2
+	do_block_Nx	e, \rounds, \in
+	.endm
+
+	.macro		encrypt_block2x, i0, i1, rounds, t0, t1, t2
+	do_block_Nx	e, \rounds, \i0, \i1
+	.endm
+
+	.macro		encrypt_block4x, i0, i1, i2, i3, rounds, t0, t1, t2
+	do_block_Nx	e, \rounds, \i0, \i1, \i2, \i3
+	.endm
+
+	.macro		decrypt_block, in, rounds, t0, t1, t2
+	do_block_Nx	d, \rounds, \in
+	.endm
+
+	.macro		decrypt_block2x, i0, i1, rounds, t0, t1, t2
+	do_block_Nx	d, \rounds, \i0, \i1
+	.endm
+
+	.macro		decrypt_block4x, i0, i1, i2, i3, rounds, t0, t1, t2
+	do_block_Nx	d, \rounds, \i0, \i1, \i2, \i3
+	.endm
+
+#include "aes-modes.S"
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
new file mode 100644
index 000000000000..60f2f4c12256
--- /dev/null
+++ b/arch/arm64/crypto/aes-glue.c
@@ -0,0 +1,446 @@
+/*
+ * linux/arch/arm64/crypto/aes-glue.c - wrapper code for ARMv8 AES
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * 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.
+ */
+
+#include <asm/neon.h>
+#include <asm/hwcap.h>
+#include <crypto/aes.h>
+#include <crypto/ablk_helper.h>
+#include <crypto/algapi.h>
+#include <linux/module.h>
+#include <linux/cpufeature.h>
+
+#ifdef USE_V8_CRYPTO_EXTENSIONS
+#define MODE			"ce"
+#define PRIO			300
+#define aes_ecb_encrypt		ce_aes_ecb_encrypt
+#define aes_ecb_decrypt		ce_aes_ecb_decrypt
+#define aes_cbc_encrypt		ce_aes_cbc_encrypt
+#define aes_cbc_decrypt		ce_aes_cbc_decrypt
+#define aes_ctr_encrypt		ce_aes_ctr_encrypt
+#define aes_xts_encrypt		ce_aes_xts_encrypt
+#define aes_xts_decrypt		ce_aes_xts_decrypt
+MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 Crypto Extensions");
+#else
+#define MODE			"neon"
+#define PRIO			200
+#define aes_ecb_encrypt		neon_aes_ecb_encrypt
+#define aes_ecb_decrypt		neon_aes_ecb_decrypt
+#define aes_cbc_encrypt		neon_aes_cbc_encrypt
+#define aes_cbc_decrypt		neon_aes_cbc_decrypt
+#define aes_ctr_encrypt		neon_aes_ctr_encrypt
+#define aes_xts_encrypt		neon_aes_xts_encrypt
+#define aes_xts_decrypt		neon_aes_xts_decrypt
+MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 NEON");
+MODULE_ALIAS("ecb(aes)");
+MODULE_ALIAS("cbc(aes)");
+MODULE_ALIAS("ctr(aes)");
+MODULE_ALIAS("xts(aes)");
+#endif
+
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+/* defined in aes-modes.S */
+asmlinkage void aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[],
+				int rounds, int blocks, int first);
+asmlinkage void aes_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[],
+				int rounds, int blocks, int first);
+
+asmlinkage void aes_cbc_encrypt(u8 out[], u8 const in[], u8 const rk[],
+				int rounds, int blocks, u8 iv[], int first);
+asmlinkage void aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[],
+				int rounds, int blocks, u8 iv[], int first);
+
+asmlinkage void aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
+				int rounds, int blocks, u8 ctr[], int first);
+
+asmlinkage void aes_xts_encrypt(u8 out[], u8 const in[], u8 const rk1[],
+				int rounds, int blocks, u8 const rk2[], u8 iv[],
+				int first);
+asmlinkage void aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[],
+				int rounds, int blocks, u8 const rk2[], u8 iv[],
+				int first);
+
+struct crypto_aes_xts_ctx {
+	struct crypto_aes_ctx key1;
+	struct crypto_aes_ctx __aligned(8) key2;
+};
+
+static int xts_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+		       unsigned int key_len)
+{
+	struct crypto_aes_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+	int ret;
+
+	ret = crypto_aes_expand_key(&ctx->key1, in_key, key_len / 2);
+	if (!ret)
+		ret = crypto_aes_expand_key(&ctx->key2, &in_key[key_len / 2],
+					    key_len / 2);
+	if (!ret)
+		return 0;
+
+	tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+	return -EINVAL;
+}
+
+static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	int err, first, rounds = 6 + ctx->key_length / 4;
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		aes_ecb_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				(u8 *)ctx->key_enc, rounds, blocks, first);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	kernel_neon_end();
+	return err;
+}
+
+static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	int err, first, rounds = 6 + ctx->key_length / 4;
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		aes_ecb_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				(u8 *)ctx->key_dec, rounds, blocks, first);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	kernel_neon_end();
+	return err;
+}
+
+static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	int err, first, rounds = 6 + ctx->key_length / 4;
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		aes_cbc_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				(u8 *)ctx->key_enc, rounds, blocks, walk.iv,
+				first);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	kernel_neon_end();
+	return err;
+}
+
+static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	int err, first, rounds = 6 + ctx->key_length / 4;
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		aes_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				(u8 *)ctx->key_dec, rounds, blocks, walk.iv,
+				first);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	kernel_neon_end();
+	return err;
+}
+
+static int ctr_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	int err, first, rounds = 6 + ctx->key_length / 4;
+	struct blkcipher_walk walk;
+	int blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE);
+
+	first = 1;
+	kernel_neon_begin();
+	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		aes_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				(u8 *)ctx->key_enc, rounds, blocks, walk.iv,
+				first);
+		first = 0;
+		nbytes -= blocks * AES_BLOCK_SIZE;
+		if (nbytes && nbytes == walk.nbytes % AES_BLOCK_SIZE)
+			break;
+		err = blkcipher_walk_done(desc, &walk,
+					  walk.nbytes % AES_BLOCK_SIZE);
+	}
+	if (nbytes) {
+		u8 *tdst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
+		u8 *tsrc = walk.src.virt.addr + blocks * AES_BLOCK_SIZE;
+		u8 __aligned(8) tail[AES_BLOCK_SIZE];
+
+		/*
+		 * Minimum alignment is 8 bytes, so if nbytes is <= 8, we need
+		 * to tell aes_ctr_encrypt() to only read half a block.
+		 */
+		blocks = (nbytes <= 8) ? -1 : 1;
+
+		aes_ctr_encrypt(tail, tsrc, (u8 *)ctx->key_enc, rounds,
+				blocks, walk.iv, first);
+		memcpy(tdst, tail, nbytes);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	kernel_neon_end();
+
+	return err;
+}
+
+static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	int err, first, rounds = 6 + ctx->key1.key_length / 4;
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		aes_xts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				(u8 *)ctx->key1.key_enc, rounds, blocks,
+				(u8 *)ctx->key2.key_enc, walk.iv, first);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	kernel_neon_end();
+
+	return err;
+}
+
+static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	int err, first, rounds = 6 + ctx->key1.key_length / 4;
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		aes_xts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				(u8 *)ctx->key1.key_dec, rounds, blocks,
+				(u8 *)ctx->key2.key_enc, walk.iv, first);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	kernel_neon_end();
+
+	return err;
+}
+
+static struct crypto_alg aes_algs[] = { {
+	.cra_name		= "__ecb-aes-" MODE,
+	.cra_driver_name	= "__driver-ecb-aes-" MODE,
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_blkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= crypto_aes_set_key,
+		.encrypt	= ecb_encrypt,
+		.decrypt	= ecb_decrypt,
+	},
+}, {
+	.cra_name		= "__cbc-aes-" MODE,
+	.cra_driver_name	= "__driver-cbc-aes-" MODE,
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_blkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= crypto_aes_set_key,
+		.encrypt	= cbc_encrypt,
+		.decrypt	= cbc_decrypt,
+	},
+}, {
+	.cra_name		= "__ctr-aes-" MODE,
+	.cra_driver_name	= "__driver-ctr-aes-" MODE,
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_blkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= crypto_aes_set_key,
+		.encrypt	= ctr_encrypt,
+		.decrypt	= ctr_encrypt,
+	},
+}, {
+	.cra_name		= "__xts-aes-" MODE,
+	.cra_driver_name	= "__driver-xts-aes-" MODE,
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct crypto_aes_xts_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_blkcipher = {
+		.min_keysize	= 2 * AES_MIN_KEY_SIZE,
+		.max_keysize	= 2 * AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= xts_set_key,
+		.encrypt	= xts_encrypt,
+		.decrypt	= xts_decrypt,
+	},
+}, {
+	.cra_name		= "ecb(aes)",
+	.cra_driver_name	= "ecb-aes-" MODE,
+	.cra_priority		= PRIO,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= ablk_set_key,
+		.encrypt	= ablk_encrypt,
+		.decrypt	= ablk_decrypt,
+	}
+}, {
+	.cra_name		= "cbc(aes)",
+	.cra_driver_name	= "cbc-aes-" MODE,
+	.cra_priority		= PRIO,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= ablk_set_key,
+		.encrypt	= ablk_encrypt,
+		.decrypt	= ablk_decrypt,
+	}
+}, {
+	.cra_name		= "ctr(aes)",
+	.cra_driver_name	= "ctr-aes-" MODE,
+	.cra_priority		= PRIO,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= ablk_set_key,
+		.encrypt	= ablk_encrypt,
+		.decrypt	= ablk_decrypt,
+	}
+}, {
+	.cra_name		= "xts(aes)",
+	.cra_driver_name	= "xts-aes-" MODE,
+	.cra_priority		= PRIO,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_ablkcipher = {
+		.min_keysize	= 2 * AES_MIN_KEY_SIZE,
+		.max_keysize	= 2 * AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= ablk_set_key,
+		.encrypt	= ablk_encrypt,
+		.decrypt	= ablk_decrypt,
+	}
+} };
+
+static int __init aes_init(void)
+{
+	return crypto_register_algs(aes_algs, ARRAY_SIZE(aes_algs));
+}
+
+static void __exit aes_exit(void)
+{
+	crypto_unregister_algs(aes_algs, ARRAY_SIZE(aes_algs));
+}
+
+#ifdef USE_V8_CRYPTO_EXTENSIONS
+module_cpu_feature_match(AES, aes_init);
+#else
+module_init(aes_init);
+#endif
+module_exit(aes_exit);
diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S
new file mode 100644
index 000000000000..f6e372c528eb
--- /dev/null
+++ b/arch/arm64/crypto/aes-modes.S
@@ -0,0 +1,532 @@
+/*
+ * linux/arch/arm64/crypto/aes-modes.S - chaining mode wrappers for AES
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * 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.
+ */
+
+/* included by aes-ce.S and aes-neon.S */
+
+	.text
+	.align		4
+
+/*
+ * There are several ways to instantiate this code:
+ * - no interleave, all inline
+ * - 2-way interleave, 2x calls out of line (-DINTERLEAVE=2)
+ * - 2-way interleave, all inline (-DINTERLEAVE=2 -DINTERLEAVE_INLINE)
+ * - 4-way interleave, 4x calls out of line (-DINTERLEAVE=4)
+ * - 4-way interleave, all inline (-DINTERLEAVE=4 -DINTERLEAVE_INLINE)
+ *
+ * Macros imported by this code:
+ * - enc_prepare	- setup NEON registers for encryption
+ * - dec_prepare	- setup NEON registers for decryption
+ * - enc_switch_key	- change to new key after having prepared for encryption
+ * - encrypt_block	- encrypt a single block
+ * - decrypt block	- decrypt a single block
+ * - encrypt_block2x	- encrypt 2 blocks in parallel (if INTERLEAVE == 2)
+ * - decrypt_block2x	- decrypt 2 blocks in parallel (if INTERLEAVE == 2)
+ * - encrypt_block4x	- encrypt 4 blocks in parallel (if INTERLEAVE == 4)
+ * - decrypt_block4x	- decrypt 4 blocks in parallel (if INTERLEAVE == 4)
+ */
+
+#if defined(INTERLEAVE) && !defined(INTERLEAVE_INLINE)
+#define FRAME_PUSH	stp x29, x30, [sp,#-16]! ; mov x29, sp
+#define FRAME_POP	ldp x29, x30, [sp],#16
+
+#if INTERLEAVE == 2
+
+aes_encrypt_block2x:
+	encrypt_block2x	v0, v1, w3, x2, x6, w7
+	ret
+ENDPROC(aes_encrypt_block2x)
+
+aes_decrypt_block2x:
+	decrypt_block2x	v0, v1, w3, x2, x6, w7
+	ret
+ENDPROC(aes_decrypt_block2x)
+
+#elif INTERLEAVE == 4
+
+aes_encrypt_block4x:
+	encrypt_block4x	v0, v1, v2, v3, w3, x2, x6, w7
+	ret
+ENDPROC(aes_encrypt_block4x)
+
+aes_decrypt_block4x:
+	decrypt_block4x	v0, v1, v2, v3, w3, x2, x6, w7
+	ret
+ENDPROC(aes_decrypt_block4x)
+
+#else
+#error INTERLEAVE should equal 2 or 4
+#endif
+
+	.macro		do_encrypt_block2x
+	bl		aes_encrypt_block2x
+	.endm
+
+	.macro		do_decrypt_block2x
+	bl		aes_decrypt_block2x
+	.endm
+
+	.macro		do_encrypt_block4x
+	bl		aes_encrypt_block4x
+	.endm
+
+	.macro		do_decrypt_block4x
+	bl		aes_decrypt_block4x
+	.endm
+
+#else
+#define FRAME_PUSH
+#define FRAME_POP
+
+	.macro		do_encrypt_block2x
+	encrypt_block2x	v0, v1, w3, x2, x6, w7
+	.endm
+
+	.macro		do_decrypt_block2x
+	decrypt_block2x	v0, v1, w3, x2, x6, w7
+	.endm
+
+	.macro		do_encrypt_block4x
+	encrypt_block4x	v0, v1, v2, v3, w3, x2, x6, w7
+	.endm
+
+	.macro		do_decrypt_block4x
+	decrypt_block4x	v0, v1, v2, v3, w3, x2, x6, w7
+	.endm
+
+#endif
+
+	/*
+	 * aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		   int blocks, int first)
+	 * aes_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		   int blocks, int first)
+	 */
+
+AES_ENTRY(aes_ecb_encrypt)
+	FRAME_PUSH
+	cbz		w5, .LecbencloopNx
+
+	enc_prepare	w3, x2, x5
+
+.LecbencloopNx:
+#if INTERLEAVE >= 2
+	subs		w4, w4, #INTERLEAVE
+	bmi		.Lecbenc1x
+#if INTERLEAVE == 2
+	ld1		{v0.16b-v1.16b}, [x1], #32	/* get 2 pt blocks */
+	do_encrypt_block2x
+	st1		{v0.16b-v1.16b}, [x0], #32
+#else
+	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 pt blocks */
+	do_encrypt_block4x
+	st1		{v0.16b-v3.16b}, [x0], #64
+#endif
+	b		.LecbencloopNx
+.Lecbenc1x:
+	adds		w4, w4, #INTERLEAVE
+	beq		.Lecbencout
+#endif
+.Lecbencloop:
+	ld1		{v0.16b}, [x1], #16		/* get next pt block */
+	encrypt_block	v0, w3, x2, x5, w6
+	st1		{v0.16b}, [x0], #16
+	subs		w4, w4, #1
+	bne		.Lecbencloop
+.Lecbencout:
+	FRAME_POP
+	ret
+AES_ENDPROC(aes_ecb_encrypt)
+
+
+AES_ENTRY(aes_ecb_decrypt)
+	FRAME_PUSH
+	cbz		w5, .LecbdecloopNx
+
+	dec_prepare	w3, x2, x5
+
+.LecbdecloopNx:
+#if INTERLEAVE >= 2
+	subs		w4, w4, #INTERLEAVE
+	bmi		.Lecbdec1x
+#if INTERLEAVE == 2
+	ld1		{v0.16b-v1.16b}, [x1], #32	/* get 2 ct blocks */
+	do_decrypt_block2x
+	st1		{v0.16b-v1.16b}, [x0], #32
+#else
+	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 ct blocks */
+	do_decrypt_block4x
+	st1		{v0.16b-v3.16b}, [x0], #64
+#endif
+	b		.LecbdecloopNx
+.Lecbdec1x:
+	adds		w4, w4, #INTERLEAVE
+	beq		.Lecbdecout
+#endif
+.Lecbdecloop:
+	ld1		{v0.16b}, [x1], #16		/* get next ct block */
+	decrypt_block	v0, w3, x2, x5, w6
+	st1		{v0.16b}, [x0], #16
+	subs		w4, w4, #1
+	bne		.Lecbdecloop
+.Lecbdecout:
+	FRAME_POP
+	ret
+AES_ENDPROC(aes_ecb_decrypt)
+
+
+	/*
+	 * aes_cbc_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		   int blocks, u8 iv[], int first)
+	 * aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		   int blocks, u8 iv[], int first)
+	 */
+
+AES_ENTRY(aes_cbc_encrypt)
+	cbz		w6, .Lcbcencloop
+
+	ld1		{v0.16b}, [x5]			/* get iv */
+	enc_prepare	w3, x2, x5
+
+.Lcbcencloop:
+	ld1		{v1.16b}, [x1], #16		/* get next pt block */
+	eor		v0.16b, v0.16b, v1.16b		/* ..and xor with iv */
+	encrypt_block	v0, w3, x2, x5, w6
+	st1		{v0.16b}, [x0], #16
+	subs		w4, w4, #1
+	bne		.Lcbcencloop
+	ret
+AES_ENDPROC(aes_cbc_encrypt)
+
+
+AES_ENTRY(aes_cbc_decrypt)
+	FRAME_PUSH
+	cbz		w6, .LcbcdecloopNx
+
+	ld1		{v7.16b}, [x5]			/* get iv */
+	dec_prepare	w3, x2, x5
+
+.LcbcdecloopNx:
+#if INTERLEAVE >= 2
+	subs		w4, w4, #INTERLEAVE
+	bmi		.Lcbcdec1x
+#if INTERLEAVE == 2
+	ld1		{v0.16b-v1.16b}, [x1], #32	/* get 2 ct blocks */
+	mov		v2.16b, v0.16b
+	mov		v3.16b, v1.16b
+	do_decrypt_block2x
+	eor		v0.16b, v0.16b, v7.16b
+	eor		v1.16b, v1.16b, v2.16b
+	mov		v7.16b, v3.16b
+	st1		{v0.16b-v1.16b}, [x0], #32
+#else
+	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 ct blocks */
+	mov		v4.16b, v0.16b
+	mov		v5.16b, v1.16b
+	mov		v6.16b, v2.16b
+	do_decrypt_block4x
+	sub		x1, x1, #16
+	eor		v0.16b, v0.16b, v7.16b
+	eor		v1.16b, v1.16b, v4.16b
+	ld1		{v7.16b}, [x1], #16		/* reload 1 ct block */
+	eor		v2.16b, v2.16b, v5.16b
+	eor		v3.16b, v3.16b, v6.16b
+	st1		{v0.16b-v3.16b}, [x0], #64
+#endif
+	b		.LcbcdecloopNx
+.Lcbcdec1x:
+	adds		w4, w4, #INTERLEAVE
+	beq		.Lcbcdecout
+#endif
+.Lcbcdecloop:
+	ld1		{v1.16b}, [x1], #16		/* get next ct block */
+	mov		v0.16b, v1.16b			/* ...and copy to v0 */
+	decrypt_block	v0, w3, x2, x5, w6
+	eor		v0.16b, v0.16b, v7.16b		/* xor with iv => pt */
+	mov		v7.16b, v1.16b			/* ct is next iv */
+	st1		{v0.16b}, [x0], #16
+	subs		w4, w4, #1
+	bne		.Lcbcdecloop
+.Lcbcdecout:
+	FRAME_POP
+	ret
+AES_ENDPROC(aes_cbc_decrypt)
+
+
+	/*
+	 * aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		   int blocks, u8 ctr[], int first)
+	 */
+
+AES_ENTRY(aes_ctr_encrypt)
+	FRAME_PUSH
+	cbnz		w6, .Lctrfirst		/* 1st time around? */
+	umov		x5, v4.d[1]		/* keep swabbed ctr in reg */
+	rev		x5, x5
+#if INTERLEAVE >= 2
+	cmn		w5, w4			/* 32 bit overflow? */
+	bcs		.Lctrinc
+	add		x5, x5, #1		/* increment BE ctr */
+	b		.LctrincNx
+#else
+	b		.Lctrinc
+#endif
+.Lctrfirst:
+	enc_prepare	w3, x2, x6
+	ld1		{v4.16b}, [x5]
+	umov		x5, v4.d[1]		/* keep swabbed ctr in reg */
+	rev		x5, x5
+#if INTERLEAVE >= 2
+	cmn		w5, w4			/* 32 bit overflow? */
+	bcs		.Lctrloop
+.LctrloopNx:
+	subs		w4, w4, #INTERLEAVE
+	bmi		.Lctr1x
+#if INTERLEAVE == 2
+	mov		v0.8b, v4.8b
+	mov		v1.8b, v4.8b
+	rev		x7, x5
+	add		x5, x5, #1
+	ins		v0.d[1], x7
+	rev		x7, x5
+	add		x5, x5, #1
+	ins		v1.d[1], x7
+	ld1		{v2.16b-v3.16b}, [x1], #32	/* get 2 input blocks */
+	do_encrypt_block2x
+	eor		v0.16b, v0.16b, v2.16b
+	eor		v1.16b, v1.16b, v3.16b
+	st1		{v0.16b-v1.16b}, [x0], #32
+#else
+	ldr		q8, =0x30000000200000001	/* addends 1,2,3[,0] */
+	dup		v7.4s, w5
+	mov		v0.16b, v4.16b
+	add		v7.4s, v7.4s, v8.4s
+	mov		v1.16b, v4.16b
+	rev32		v8.16b, v7.16b
+	mov		v2.16b, v4.16b
+	mov		v3.16b, v4.16b
+	mov		v1.s[3], v8.s[0]
+	mov		v2.s[3], v8.s[1]
+	mov		v3.s[3], v8.s[2]
+	ld1		{v5.16b-v7.16b}, [x1], #48	/* get 3 input blocks */
+	do_encrypt_block4x
+	eor		v0.16b, v5.16b, v0.16b
+	ld1		{v5.16b}, [x1], #16		/* get 1 input block  */
+	eor		v1.16b, v6.16b, v1.16b
+	eor		v2.16b, v7.16b, v2.16b
+	eor		v3.16b, v5.16b, v3.16b
+	st1		{v0.16b-v3.16b}, [x0], #64
+	add		x5, x5, #INTERLEAVE
+#endif
+	cbz		w4, .LctroutNx
+.LctrincNx:
+	rev		x7, x5
+	ins		v4.d[1], x7
+	b		.LctrloopNx
+.LctroutNx:
+	sub		x5, x5, #1
+	rev		x7, x5
+	ins		v4.d[1], x7
+	b		.Lctrout
+.Lctr1x:
+	adds		w4, w4, #INTERLEAVE
+	beq		.Lctrout
+#endif
+.Lctrloop:
+	mov		v0.16b, v4.16b
+	encrypt_block	v0, w3, x2, x6, w7
+	subs		w4, w4, #1
+	bmi		.Lctrhalfblock		/* blocks < 0 means 1/2 block */
+	ld1		{v3.16b}, [x1], #16
+	eor		v3.16b, v0.16b, v3.16b
+	st1		{v3.16b}, [x0], #16
+	beq		.Lctrout
+.Lctrinc:
+	adds		x5, x5, #1		/* increment BE ctr */
+	rev		x7, x5
+	ins		v4.d[1], x7
+	bcc		.Lctrloop		/* no overflow? */
+	umov		x7, v4.d[0]		/* load upper word of ctr  */
+	rev		x7, x7			/* ... to handle the carry */
+	add		x7, x7, #1
+	rev		x7, x7
+	ins		v4.d[0], x7
+	b		.Lctrloop
+.Lctrhalfblock:
+	ld1		{v3.8b}, [x1]
+	eor		v3.8b, v0.8b, v3.8b
+	st1		{v3.8b}, [x0]
+.Lctrout:
+	FRAME_POP
+	ret
+AES_ENDPROC(aes_ctr_encrypt)
+	.ltorg
+
+
+	/*
+	 * aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[], int rounds,
+	 *		   int blocks, u8 const rk2[], u8 iv[], int first)
+	 * aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[], int rounds,
+	 *		   int blocks, u8 const rk2[], u8 iv[], int first)
+	 */
+
+	.macro		next_tweak, out, in, const, tmp
+	sshr		\tmp\().2d,  \in\().2d,   #63
+	and		\tmp\().16b, \tmp\().16b, \const\().16b
+	add		\out\().2d,  \in\().2d,   \in\().2d
+	ext		\tmp\().16b, \tmp\().16b, \tmp\().16b, #8
+	eor		\out\().16b, \out\().16b, \tmp\().16b
+	.endm
+
+.Lxts_mul_x:
+	.word		1, 0, 0x87, 0
+
+AES_ENTRY(aes_xts_encrypt)
+	FRAME_PUSH
+	cbz		w7, .LxtsencloopNx
+
+	ld1		{v4.16b}, [x6]
+	enc_prepare	w3, x5, x6
+	encrypt_block	v4, w3, x5, x6, w7		/* first tweak */
+	enc_switch_key	w3, x2, x6
+	ldr		q7, .Lxts_mul_x
+	b		.LxtsencNx
+
+.LxtsencloopNx:
+	ldr		q7, .Lxts_mul_x
+	next_tweak	v4, v4, v7, v8
+.LxtsencNx:
+#if INTERLEAVE >= 2
+	subs		w4, w4, #INTERLEAVE
+	bmi		.Lxtsenc1x
+#if INTERLEAVE == 2
+	ld1		{v0.16b-v1.16b}, [x1], #32	/* get 2 pt blocks */
+	next_tweak	v5, v4, v7, v8
+	eor		v0.16b, v0.16b, v4.16b
+	eor		v1.16b, v1.16b, v5.16b
+	do_encrypt_block2x
+	eor		v0.16b, v0.16b, v4.16b
+	eor		v1.16b, v1.16b, v5.16b
+	st1		{v0.16b-v1.16b}, [x0], #32
+	cbz		w4, .LxtsencoutNx
+	next_tweak	v4, v5, v7, v8
+	b		.LxtsencNx
+.LxtsencoutNx:
+	mov		v4.16b, v5.16b
+	b		.Lxtsencout
+#else
+	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 pt blocks */
+	next_tweak	v5, v4, v7, v8
+	eor		v0.16b, v0.16b, v4.16b
+	next_tweak	v6, v5, v7, v8
+	eor		v1.16b, v1.16b, v5.16b
+	eor		v2.16b, v2.16b, v6.16b
+	next_tweak	v7, v6, v7, v8
+	eor		v3.16b, v3.16b, v7.16b
+	do_encrypt_block4x
+	eor		v3.16b, v3.16b, v7.16b
+	eor		v0.16b, v0.16b, v4.16b
+	eor		v1.16b, v1.16b, v5.16b
+	eor		v2.16b, v2.16b, v6.16b
+	st1		{v0.16b-v3.16b}, [x0], #64
+	mov		v4.16b, v7.16b
+	cbz		w4, .Lxtsencout
+	b		.LxtsencloopNx
+#endif
+.Lxtsenc1x:
+	adds		w4, w4, #INTERLEAVE
+	beq		.Lxtsencout
+#endif
+.Lxtsencloop:
+	ld1		{v1.16b}, [x1], #16
+	eor		v0.16b, v1.16b, v4.16b
+	encrypt_block	v0, w3, x2, x6, w7
+	eor		v0.16b, v0.16b, v4.16b
+	st1		{v0.16b}, [x0], #16
+	subs		w4, w4, #1
+	beq		.Lxtsencout
+	next_tweak	v4, v4, v7, v8
+	b		.Lxtsencloop
+.Lxtsencout:
+	FRAME_POP
+	ret
+AES_ENDPROC(aes_xts_encrypt)
+
+
+AES_ENTRY(aes_xts_decrypt)
+	FRAME_PUSH
+	cbz		w7, .LxtsdecloopNx
+
+	ld1		{v4.16b}, [x6]
+	enc_prepare	w3, x5, x6
+	encrypt_block	v4, w3, x5, x6, w7		/* first tweak */
+	dec_prepare	w3, x2, x6
+	ldr		q7, .Lxts_mul_x
+	b		.LxtsdecNx
+
+.LxtsdecloopNx:
+	ldr		q7, .Lxts_mul_x
+	next_tweak	v4, v4, v7, v8
+.LxtsdecNx:
+#if INTERLEAVE >= 2
+	subs		w4, w4, #INTERLEAVE
+	bmi		.Lxtsdec1x
+#if INTERLEAVE == 2
+	ld1		{v0.16b-v1.16b}, [x1], #32	/* get 2 ct blocks */
+	next_tweak	v5, v4, v7, v8
+	eor		v0.16b, v0.16b, v4.16b
+	eor		v1.16b, v1.16b, v5.16b
+	do_decrypt_block2x
+	eor		v0.16b, v0.16b, v4.16b
+	eor		v1.16b, v1.16b, v5.16b
+	st1		{v0.16b-v1.16b}, [x0], #32
+	cbz		w4, .LxtsdecoutNx
+	next_tweak	v4, v5, v7, v8
+	b		.LxtsdecNx
+.LxtsdecoutNx:
+	mov		v4.16b, v5.16b
+	b		.Lxtsdecout
+#else
+	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 ct blocks */
+	next_tweak	v5, v4, v7, v8
+	eor		v0.16b, v0.16b, v4.16b
+	next_tweak	v6, v5, v7, v8
+	eor		v1.16b, v1.16b, v5.16b
+	eor		v2.16b, v2.16b, v6.16b
+	next_tweak	v7, v6, v7, v8
+	eor		v3.16b, v3.16b, v7.16b
+	do_decrypt_block4x
+	eor		v3.16b, v3.16b, v7.16b
+	eor		v0.16b, v0.16b, v4.16b
+	eor		v1.16b, v1.16b, v5.16b
+	eor		v2.16b, v2.16b, v6.16b
+	st1		{v0.16b-v3.16b}, [x0], #64
+	mov		v4.16b, v7.16b
+	cbz		w4, .Lxtsdecout
+	b		.LxtsdecloopNx
+#endif
+.Lxtsdec1x:
+	adds		w4, w4, #INTERLEAVE
+	beq		.Lxtsdecout
+#endif
+.Lxtsdecloop:
+	ld1		{v1.16b}, [x1], #16
+	eor		v0.16b, v1.16b, v4.16b
+	decrypt_block	v0, w3, x2, x6, w7
+	eor		v0.16b, v0.16b, v4.16b
+	st1		{v0.16b}, [x0], #16
+	subs		w4, w4, #1
+	beq		.Lxtsdecout
+	next_tweak	v4, v4, v7, v8
+	b		.Lxtsdecloop
+.Lxtsdecout:
+	FRAME_POP
+	ret
+AES_ENDPROC(aes_xts_decrypt)
diff --git a/arch/arm64/crypto/aes-neon.S b/arch/arm64/crypto/aes-neon.S
new file mode 100644
index 000000000000..b93170e1cc93
--- /dev/null
+++ b/arch/arm64/crypto/aes-neon.S
@@ -0,0 +1,382 @@
+/*
+ * linux/arch/arm64/crypto/aes-neon.S - AES cipher for ARMv8 NEON
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * 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.
+ */
+
+#include <linux/linkage.h>
+
+#define AES_ENTRY(func)		ENTRY(neon_ ## func)
+#define AES_ENDPROC(func)	ENDPROC(neon_ ## func)
+
+	/* multiply by polynomial 'x' in GF(2^8) */
+	.macro		mul_by_x, out, in, temp, const
+	sshr		\temp, \in, #7
+	add		\out, \in, \in
+	and		\temp, \temp, \const
+	eor		\out, \out, \temp
+	.endm
+
+	/* preload the entire Sbox */
+	.macro		prepare, sbox, shiftrows, temp
+	adr		\temp, \sbox
+	movi		v12.16b, #0x40
+	ldr		q13, \shiftrows
+	movi		v14.16b, #0x1b
+	ld1		{v16.16b-v19.16b}, [\temp], #64
+	ld1		{v20.16b-v23.16b}, [\temp], #64
+	ld1		{v24.16b-v27.16b}, [\temp], #64
+	ld1		{v28.16b-v31.16b}, [\temp]
+	.endm
+
+	/* do preload for encryption */
+	.macro		enc_prepare, ignore0, ignore1, temp
+	prepare		.LForward_Sbox, .LForward_ShiftRows, \temp
+	.endm
+
+	.macro		enc_switch_key, ignore0, ignore1, temp
+	/* do nothing */
+	.endm
+
+	/* do preload for decryption */
+	.macro		dec_prepare, ignore0, ignore1, temp
+	prepare		.LReverse_Sbox, .LReverse_ShiftRows, \temp
+	.endm
+
+	/* apply SubBytes transformation using the the preloaded Sbox */
+	.macro		sub_bytes, in
+	sub		v9.16b, \in\().16b, v12.16b
+	tbl		\in\().16b, {v16.16b-v19.16b}, \in\().16b
+	sub		v10.16b, v9.16b, v12.16b
+	tbx		\in\().16b, {v20.16b-v23.16b}, v9.16b
+	sub		v11.16b, v10.16b, v12.16b
+	tbx		\in\().16b, {v24.16b-v27.16b}, v10.16b
+	tbx		\in\().16b, {v28.16b-v31.16b}, v11.16b
+	.endm
+
+	/* apply MixColumns transformation */
+	.macro		mix_columns, in
+	mul_by_x	v10.16b, \in\().16b, v9.16b, v14.16b
+	rev32		v8.8h, \in\().8h
+	eor		\in\().16b, v10.16b, \in\().16b
+	shl		v9.4s, v8.4s, #24
+	shl		v11.4s, \in\().4s, #24
+	sri		v9.4s, v8.4s, #8
+	sri		v11.4s, \in\().4s, #8
+	eor		v9.16b, v9.16b, v8.16b
+	eor		v10.16b, v10.16b, v9.16b
+	eor		\in\().16b, v10.16b, v11.16b
+	.endm
+
+	/* Inverse MixColumns: pre-multiply by { 5, 0, 4, 0 } */
+	.macro		inv_mix_columns, in
+	mul_by_x	v11.16b, \in\().16b, v10.16b, v14.16b
+	mul_by_x	v11.16b, v11.16b, v10.16b, v14.16b
+	eor		\in\().16b, \in\().16b, v11.16b
+	rev32		v11.8h, v11.8h
+	eor		\in\().16b, \in\().16b, v11.16b
+	mix_columns	\in
+	.endm
+
+	.macro		do_block, enc, in, rounds, rk, rkp, i
+	ld1		{v15.16b}, [\rk]
+	add		\rkp, \rk, #16
+	mov		\i, \rounds
+1111:	eor		\in\().16b, \in\().16b, v15.16b		/* ^round key */
+	tbl		\in\().16b, {\in\().16b}, v13.16b	/* ShiftRows */
+	sub_bytes	\in
+	ld1		{v15.16b}, [\rkp], #16
+	subs		\i, \i, #1
+	beq		2222f
+	.if		\enc == 1
+	mix_columns	\in
+	.else
+	inv_mix_columns	\in
+	.endif
+	b		1111b
+2222:	eor		\in\().16b, \in\().16b, v15.16b		/* ^round key */
+	.endm
+
+	.macro		encrypt_block, in, rounds, rk, rkp, i
+	do_block	1, \in, \rounds, \rk, \rkp, \i
+	.endm
+
+	.macro		decrypt_block, in, rounds, rk, rkp, i
+	do_block	0, \in, \rounds, \rk, \rkp, \i
+	.endm
+
+	/*
+	 * Interleaved versions: functionally equivalent to the
+	 * ones above, but applied to 2 or 4 AES states in parallel.
+	 */
+
+	.macro		sub_bytes_2x, in0, in1
+	sub		v8.16b, \in0\().16b, v12.16b
+	sub		v9.16b, \in1\().16b, v12.16b
+	tbl		\in0\().16b, {v16.16b-v19.16b}, \in0\().16b
+	tbl		\in1\().16b, {v16.16b-v19.16b}, \in1\().16b
+	sub		v10.16b, v8.16b, v12.16b
+	sub		v11.16b, v9.16b, v12.16b
+	tbx		\in0\().16b, {v20.16b-v23.16b}, v8.16b
+	tbx		\in1\().16b, {v20.16b-v23.16b}, v9.16b
+	sub		v8.16b, v10.16b, v12.16b
+	sub		v9.16b, v11.16b, v12.16b
+	tbx		\in0\().16b, {v24.16b-v27.16b}, v10.16b
+	tbx		\in1\().16b, {v24.16b-v27.16b}, v11.16b
+	tbx		\in0\().16b, {v28.16b-v31.16b}, v8.16b
+	tbx		\in1\().16b, {v28.16b-v31.16b}, v9.16b
+	.endm
+
+	.macro		sub_bytes_4x, in0, in1, in2, in3
+	sub		v8.16b, \in0\().16b, v12.16b
+	tbl		\in0\().16b, {v16.16b-v19.16b}, \in0\().16b
+	sub		v9.16b, \in1\().16b, v12.16b
+	tbl		\in1\().16b, {v16.16b-v19.16b}, \in1\().16b
+	sub		v10.16b, \in2\().16b, v12.16b
+	tbl		\in2\().16b, {v16.16b-v19.16b}, \in2\().16b
+	sub		v11.16b, \in3\().16b, v12.16b
+	tbl		\in3\().16b, {v16.16b-v19.16b}, \in3\().16b
+	tbx		\in0\().16b, {v20.16b-v23.16b}, v8.16b
+	tbx		\in1\().16b, {v20.16b-v23.16b}, v9.16b
+	sub		v8.16b, v8.16b, v12.16b
+	tbx		\in2\().16b, {v20.16b-v23.16b}, v10.16b
+	sub		v9.16b, v9.16b, v12.16b
+	tbx		\in3\().16b, {v20.16b-v23.16b}, v11.16b
+	sub		v10.16b, v10.16b, v12.16b
+	tbx		\in0\().16b, {v24.16b-v27.16b}, v8.16b
+	sub		v11.16b, v11.16b, v12.16b
+	tbx		\in1\().16b, {v24.16b-v27.16b}, v9.16b
+	sub		v8.16b, v8.16b, v12.16b
+	tbx		\in2\().16b, {v24.16b-v27.16b}, v10.16b
+	sub		v9.16b, v9.16b, v12.16b
+	tbx		\in3\().16b, {v24.16b-v27.16b}, v11.16b
+	sub		v10.16b, v10.16b, v12.16b
+	tbx		\in0\().16b, {v28.16b-v31.16b}, v8.16b
+	sub		v11.16b, v11.16b, v12.16b
+	tbx		\in1\().16b, {v28.16b-v31.16b}, v9.16b
+	tbx		\in2\().16b, {v28.16b-v31.16b}, v10.16b
+	tbx		\in3\().16b, {v28.16b-v31.16b}, v11.16b
+	.endm
+
+	.macro		mul_by_x_2x, out0, out1, in0, in1, tmp0, tmp1, const
+	sshr		\tmp0\().16b, \in0\().16b,  #7
+	add		\out0\().16b, \in0\().16b,  \in0\().16b
+	sshr		\tmp1\().16b, \in1\().16b,  #7
+	and		\tmp0\().16b, \tmp0\().16b, \const\().16b
+	add		\out1\().16b, \in1\().16b,  \in1\().16b
+	and		\tmp1\().16b, \tmp1\().16b, \const\().16b
+	eor		\out0\().16b, \out0\().16b, \tmp0\().16b
+	eor		\out1\().16b, \out1\().16b, \tmp1\().16b
+	.endm
+
+	.macro		mix_columns_2x, in0, in1
+	mul_by_x_2x	v8, v9, \in0, \in1, v10, v11, v14
+	rev32		v10.8h, \in0\().8h
+	rev32		v11.8h, \in1\().8h
+	eor		\in0\().16b, v8.16b, \in0\().16b
+	eor		\in1\().16b, v9.16b, \in1\().16b
+	shl		v12.4s, v10.4s, #24
+	shl		v13.4s, v11.4s, #24
+	eor		v8.16b, v8.16b, v10.16b
+	sri		v12.4s, v10.4s, #8
+	shl		v10.4s, \in0\().4s, #24
+	eor		v9.16b, v9.16b, v11.16b
+	sri		v13.4s, v11.4s, #8
+	shl		v11.4s, \in1\().4s, #24
+	sri		v10.4s, \in0\().4s, #8
+	eor		\in0\().16b, v8.16b, v12.16b
+	sri		v11.4s, \in1\().4s, #8
+	eor		\in1\().16b, v9.16b, v13.16b
+	eor		\in0\().16b, v10.16b, \in0\().16b
+	eor		\in1\().16b, v11.16b, \in1\().16b
+	.endm
+
+	.macro		inv_mix_cols_2x, in0, in1
+	mul_by_x_2x	v8, v9, \in0, \in1, v10, v11, v14
+	mul_by_x_2x	v8, v9, v8, v9, v10, v11, v14
+	eor		\in0\().16b, \in0\().16b, v8.16b
+	eor		\in1\().16b, \in1\().16b, v9.16b
+	rev32		v8.8h, v8.8h
+	rev32		v9.8h, v9.8h
+	eor		\in0\().16b, \in0\().16b, v8.16b
+	eor		\in1\().16b, \in1\().16b, v9.16b
+	mix_columns_2x	\in0, \in1
+	.endm
+
+	.macro		inv_mix_cols_4x, in0, in1, in2, in3
+	mul_by_x_2x	v8, v9, \in0, \in1, v10, v11, v14
+	mul_by_x_2x	v10, v11, \in2, \in3, v12, v13, v14
+	mul_by_x_2x	v8, v9, v8, v9, v12, v13, v14
+	mul_by_x_2x	v10, v11, v10, v11, v12, v13, v14
+	eor		\in0\().16b, \in0\().16b, v8.16b
+	eor		\in1\().16b, \in1\().16b, v9.16b
+	eor		\in2\().16b, \in2\().16b, v10.16b
+	eor		\in3\().16b, \in3\().16b, v11.16b
+	rev32		v8.8h, v8.8h
+	rev32		v9.8h, v9.8h
+	rev32		v10.8h, v10.8h
+	rev32		v11.8h, v11.8h
+	eor		\in0\().16b, \in0\().16b, v8.16b
+	eor		\in1\().16b, \in1\().16b, v9.16b
+	eor		\in2\().16b, \in2\().16b, v10.16b
+	eor		\in3\().16b, \in3\().16b, v11.16b
+	mix_columns_2x	\in0, \in1
+	mix_columns_2x	\in2, \in3
+	.endm
+
+	.macro		do_block_2x, enc, in0, in1 rounds, rk, rkp, i
+	ld1		{v15.16b}, [\rk]
+	add		\rkp, \rk, #16
+	mov		\i, \rounds
+1111:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
+	eor		\in1\().16b, \in1\().16b, v15.16b	/* ^round key */
+	sub_bytes_2x	\in0, \in1
+	tbl		\in0\().16b, {\in0\().16b}, v13.16b	/* ShiftRows */
+	tbl		\in1\().16b, {\in1\().16b}, v13.16b	/* ShiftRows */
+	ld1		{v15.16b}, [\rkp], #16
+	subs		\i, \i, #1
+	beq		2222f
+	.if		\enc == 1
+	mix_columns_2x	\in0, \in1
+	ldr		q13, .LForward_ShiftRows
+	.else
+	inv_mix_cols_2x	\in0, \in1
+	ldr		q13, .LReverse_ShiftRows
+	.endif
+	movi		v12.16b, #0x40
+	b		1111b
+2222:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
+	eor		\in1\().16b, \in1\().16b, v15.16b	/* ^round key */
+	.endm
+
+	.macro		do_block_4x, enc, in0, in1, in2, in3, rounds, rk, rkp, i
+	ld1		{v15.16b}, [\rk]
+	add		\rkp, \rk, #16
+	mov		\i, \rounds
+1111:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
+	eor		\in1\().16b, \in1\().16b, v15.16b	/* ^round key */
+	eor		\in2\().16b, \in2\().16b, v15.16b	/* ^round key */
+	eor		\in3\().16b, \in3\().16b, v15.16b	/* ^round key */
+	sub_bytes_4x	\in0, \in1, \in2, \in3
+	tbl		\in0\().16b, {\in0\().16b}, v13.16b	/* ShiftRows */
+	tbl		\in1\().16b, {\in1\().16b}, v13.16b	/* ShiftRows */
+	tbl		\in2\().16b, {\in2\().16b}, v13.16b	/* ShiftRows */
+	tbl		\in3\().16b, {\in3\().16b}, v13.16b	/* ShiftRows */
+	ld1		{v15.16b}, [\rkp], #16
+	subs		\i, \i, #1
+	beq		2222f
+	.if		\enc == 1
+	mix_columns_2x	\in0, \in1
+	mix_columns_2x	\in2, \in3
+	ldr		q13, .LForward_ShiftRows
+	.else
+	inv_mix_cols_4x	\in0, \in1, \in2, \in3
+	ldr		q13, .LReverse_ShiftRows
+	.endif
+	movi		v12.16b, #0x40
+	b		1111b
+2222:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
+	eor		\in1\().16b, \in1\().16b, v15.16b	/* ^round key */
+	eor		\in2\().16b, \in2\().16b, v15.16b	/* ^round key */
+	eor		\in3\().16b, \in3\().16b, v15.16b	/* ^round key */
+	.endm
+
+	.macro		encrypt_block2x, in0, in1, rounds, rk, rkp, i
+	do_block_2x	1, \in0, \in1, \rounds, \rk, \rkp, \i
+	.endm
+
+	.macro		decrypt_block2x, in0, in1, rounds, rk, rkp, i
+	do_block_2x	0, \in0, \in1, \rounds, \rk, \rkp, \i
+	.endm
+
+	.macro		encrypt_block4x, in0, in1, in2, in3, rounds, rk, rkp, i
+	do_block_4x	1, \in0, \in1, \in2, \in3, \rounds, \rk, \rkp, \i
+	.endm
+
+	.macro		decrypt_block4x, in0, in1, in2, in3, rounds, rk, rkp, i
+	do_block_4x	0, \in0, \in1, \in2, \in3, \rounds, \rk, \rkp, \i
+	.endm
+
+#include "aes-modes.S"
+
+	.text
+	.align		4
+.LForward_ShiftRows:
+	.byte		0x0, 0x5, 0xa, 0xf, 0x4, 0x9, 0xe, 0x3
+	.byte		0x8, 0xd, 0x2, 0x7, 0xc, 0x1, 0x6, 0xb
+
+.LReverse_ShiftRows:
+	.byte		0x0, 0xd, 0xa, 0x7, 0x4, 0x1, 0xe, 0xb
+	.byte		0x8, 0x5, 0x2, 0xf, 0xc, 0x9, 0x6, 0x3
+
+.LForward_Sbox:
+	.byte		0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5
+	.byte		0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76
+	.byte		0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0
+	.byte		0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0
+	.byte		0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc
+	.byte		0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15
+	.byte		0x04, 0xc7, 0x23, 0xc3, 0x18, 0x96, 0x05, 0x9a
+	.byte		0x07, 0x12, 0x80, 0xe2, 0xeb, 0x27, 0xb2, 0x75
+	.byte		0x09, 0x83, 0x2c, 0x1a, 0x1b, 0x6e, 0x5a, 0xa0
+	.byte		0x52, 0x3b, 0xd6, 0xb3, 0x29, 0xe3, 0x2f, 0x84
+	.byte		0x53, 0xd1, 0x00, 0xed, 0x20, 0xfc, 0xb1, 0x5b
+	.byte		0x6a, 0xcb, 0xbe, 0x39, 0x4a, 0x4c, 0x58, 0xcf
+	.byte		0xd0, 0xef, 0xaa, 0xfb, 0x43, 0x4d, 0x33, 0x85
+	.byte		0x45, 0xf9, 0x02, 0x7f, 0x50, 0x3c, 0x9f, 0xa8
+	.byte		0x51, 0xa3, 0x40, 0x8f, 0x92, 0x9d, 0x38, 0xf5
+	.byte		0xbc, 0xb6, 0xda, 0x21, 0x10, 0xff, 0xf3, 0xd2
+	.byte		0xcd, 0x0c, 0x13, 0xec, 0x5f, 0x97, 0x44, 0x17
+	.byte		0xc4, 0xa7, 0x7e, 0x3d, 0x64, 0x5d, 0x19, 0x73
+	.byte		0x60, 0x81, 0x4f, 0xdc, 0x22, 0x2a, 0x90, 0x88
+	.byte		0x46, 0xee, 0xb8, 0x14, 0xde, 0x5e, 0x0b, 0xdb
+	.byte		0xe0, 0x32, 0x3a, 0x0a, 0x49, 0x06, 0x24, 0x5c
+	.byte		0xc2, 0xd3, 0xac, 0x62, 0x91, 0x95, 0xe4, 0x79
+	.byte		0xe7, 0xc8, 0x37, 0x6d, 0x8d, 0xd5, 0x4e, 0xa9
+	.byte		0x6c, 0x56, 0xf4, 0xea, 0x65, 0x7a, 0xae, 0x08
+	.byte		0xba, 0x78, 0x25, 0x2e, 0x1c, 0xa6, 0xb4, 0xc6
+	.byte		0xe8, 0xdd, 0x74, 0x1f, 0x4b, 0xbd, 0x8b, 0x8a
+	.byte		0x70, 0x3e, 0xb5, 0x66, 0x48, 0x03, 0xf6, 0x0e
+	.byte		0x61, 0x35, 0x57, 0xb9, 0x86, 0xc1, 0x1d, 0x9e
+	.byte		0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94
+	.byte		0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf
+	.byte		0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68
+	.byte		0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16
+
+.LReverse_Sbox:
+	.byte		0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38
+	.byte		0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb
+	.byte		0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87
+	.byte		0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb
+	.byte		0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d
+	.byte		0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e
+	.byte		0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2
+	.byte		0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25
+	.byte		0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16
+	.byte		0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92
+	.byte		0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda
+	.byte		0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84
+	.byte		0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a
+	.byte		0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06
+	.byte		0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02
+	.byte		0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b
+	.byte		0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea
+	.byte		0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73
+	.byte		0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85
+	.byte		0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e
+	.byte		0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89
+	.byte		0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b
+	.byte		0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20
+	.byte		0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4
+	.byte		0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31
+	.byte		0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f
+	.byte		0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d
+	.byte		0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef
+	.byte		0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0
+	.byte		0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61
+	.byte		0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26
+	.byte		0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d
diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
new file mode 100644
index 000000000000..dc457015884e
--- /dev/null
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -0,0 +1,79 @@
+/*
+ * Accelerated GHASH implementation with ARMv8 PMULL instructions.
+ *
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * 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.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	SHASH	.req	v0
+	SHASH2	.req	v1
+	T1	.req	v2
+	T2	.req	v3
+	MASK	.req	v4
+	XL	.req	v5
+	XM	.req	v6
+	XH	.req	v7
+	IN1	.req	v7
+
+	.text
+	.arch		armv8-a+crypto
+
+	/*
+	 * void pmull_ghash_update(int blocks, u64 dg[], const char *src,
+	 *			   struct ghash_key const *k, const char *head)
+	 */
+ENTRY(pmull_ghash_update)
+	ld1		{SHASH.16b}, [x3]
+	ld1		{XL.16b}, [x1]
+	movi		MASK.16b, #0xe1
+	ext		SHASH2.16b, SHASH.16b, SHASH.16b, #8
+	shl		MASK.2d, MASK.2d, #57
+	eor		SHASH2.16b, SHASH2.16b, SHASH.16b
+
+	/* do the head block first, if supplied */
+	cbz		x4, 0f
+	ld1		{T1.2d}, [x4]
+	b		1f
+
+0:	ld1		{T1.2d}, [x2], #16
+	sub		w0, w0, #1
+
+1:	/* multiply XL by SHASH in GF(2^128) */
+CPU_LE(	rev64		T1.16b, T1.16b	)
+
+	ext		T2.16b, XL.16b, XL.16b, #8
+	ext		IN1.16b, T1.16b, T1.16b, #8
+	eor		T1.16b, T1.16b, T2.16b
+	eor		XL.16b, XL.16b, IN1.16b
+
+	pmull2		XH.1q, SHASH.2d, XL.2d		// a1 * b1
+	eor		T1.16b, T1.16b, XL.16b
+	pmull		XL.1q, SHASH.1d, XL.1d		// a0 * b0
+	pmull		XM.1q, SHASH2.1d, T1.1d		// (a1 + a0)(b1 + b0)
+
+	ext		T1.16b, XL.16b, XH.16b, #8
+	eor		T2.16b, XL.16b, XH.16b
+	eor		XM.16b, XM.16b, T1.16b
+	eor		XM.16b, XM.16b, T2.16b
+	pmull		T2.1q, XL.1d, MASK.1d
+
+	mov		XH.d[0], XM.d[1]
+	mov		XM.d[1], XL.d[0]
+
+	eor		XL.16b, XM.16b, T2.16b
+	ext		T2.16b, XL.16b, XL.16b, #8
+	pmull		XL.1q, XL.1d, MASK.1d
+	eor		T2.16b, T2.16b, XH.16b
+	eor		XL.16b, XL.16b, T2.16b
+
+	cbnz		w0, 0b
+
+	st1		{XL.16b}, [x1]
+	ret
+ENDPROC(pmull_ghash_update)
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
new file mode 100644
index 000000000000..833ec1e3f3e9
--- /dev/null
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -0,0 +1,156 @@
+/*
+ * Accelerated GHASH implementation with ARMv8 PMULL instructions.
+ *
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * 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.
+ */
+
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("GHASH secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+#define GHASH_BLOCK_SIZE	16
+#define GHASH_DIGEST_SIZE	16
+
+struct ghash_key {
+	u64 a;
+	u64 b;
+};
+
+struct ghash_desc_ctx {
+	u64 digest[GHASH_DIGEST_SIZE/sizeof(u64)];
+	u8 buf[GHASH_BLOCK_SIZE];
+	u32 count;
+};
+
+asmlinkage void pmull_ghash_update(int blocks, u64 dg[], const char *src,
+				   struct ghash_key const *k, const char *head);
+
+static int ghash_init(struct shash_desc *desc)
+{
+	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	*ctx = (struct ghash_desc_ctx){};
+	return 0;
+}
+
+static int ghash_update(struct shash_desc *desc, const u8 *src,
+			unsigned int len)
+{
+	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+	unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
+
+	ctx->count += len;
+
+	if ((partial + len) >= GHASH_BLOCK_SIZE) {
+		struct ghash_key *key = crypto_shash_ctx(desc->tfm);
+		int blocks;
+
+		if (partial) {
+			int p = GHASH_BLOCK_SIZE - partial;
+
+			memcpy(ctx->buf + partial, src, p);
+			src += p;
+			len -= p;
+		}
+
+		blocks = len / GHASH_BLOCK_SIZE;
+		len %= GHASH_BLOCK_SIZE;
+
+		kernel_neon_begin_partial(8);
+		pmull_ghash_update(blocks, ctx->digest, src, key,
+				   partial ? ctx->buf : NULL);
+		kernel_neon_end();
+		src += blocks * GHASH_BLOCK_SIZE;
+		partial = 0;
+	}
+	if (len)
+		memcpy(ctx->buf + partial, src, len);
+	return 0;
+}
+
+static int ghash_final(struct shash_desc *desc, u8 *dst)
+{
+	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+	unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
+
+	if (partial) {
+		struct ghash_key *key = crypto_shash_ctx(desc->tfm);
+
+		memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial);
+
+		kernel_neon_begin_partial(8);
+		pmull_ghash_update(1, ctx->digest, ctx->buf, key, NULL);
+		kernel_neon_end();
+	}
+	put_unaligned_be64(ctx->digest[1], dst);
+	put_unaligned_be64(ctx->digest[0], dst + 8);
+
+	*ctx = (struct ghash_desc_ctx){};
+	return 0;
+}
+
+static int ghash_setkey(struct crypto_shash *tfm,
+			const u8 *inkey, unsigned int keylen)
+{
+	struct ghash_key *key = crypto_shash_ctx(tfm);
+	u64 a, b;
+
+	if (keylen != GHASH_BLOCK_SIZE) {
+		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	/* perform multiplication by 'x' in GF(2^128) */
+	b = get_unaligned_be64(inkey);
+	a = get_unaligned_be64(inkey + 8);
+
+	key->a = (a << 1) | (b >> 63);
+	key->b = (b << 1) | (a >> 63);
+
+	if (b >> 63)
+		key->b ^= 0xc200000000000000UL;
+
+	return 0;
+}
+
+static struct shash_alg ghash_alg = {
+	.digestsize	= GHASH_DIGEST_SIZE,
+	.init		= ghash_init,
+	.update		= ghash_update,
+	.final		= ghash_final,
+	.setkey		= ghash_setkey,
+	.descsize	= sizeof(struct ghash_desc_ctx),
+	.base		= {
+		.cra_name		= "ghash",
+		.cra_driver_name	= "ghash-ce",
+		.cra_priority		= 200,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= GHASH_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct ghash_key),
+		.cra_module		= THIS_MODULE,
+	},
+};
+
+static int __init ghash_ce_mod_init(void)
+{
+	return crypto_register_shash(&ghash_alg);
+}
+
+static void __exit ghash_ce_mod_exit(void)
+{
+	crypto_unregister_shash(&ghash_alg);
+}
+
+module_cpu_feature_match(PMULL, ghash_ce_mod_init);
+module_exit(ghash_ce_mod_exit);
diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S
new file mode 100644
index 000000000000..09d57d98609c
--- /dev/null
+++ b/arch/arm64/crypto/sha1-ce-core.S
@@ -0,0 +1,153 @@
+/*
+ * sha1-ce-core.S - SHA-1 secure hash using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * 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.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.text
+	.arch		armv8-a+crypto
+
+	k0		.req	v0
+	k1		.req	v1
+	k2		.req	v2
+	k3		.req	v3
+
+	t0		.req	v4
+	t1		.req	v5
+
+	dga		.req	q6
+	dgav		.req	v6
+	dgb		.req	s7
+	dgbv		.req	v7
+
+	dg0q		.req	q12
+	dg0s		.req	s12
+	dg0v		.req	v12
+	dg1s		.req	s13
+	dg1v		.req	v13
+	dg2s		.req	s14
+
+	.macro		add_only, op, ev, rc, s0, dg1
+	.ifc		\ev, ev
+	add		t1.4s, v\s0\().4s, \rc\().4s
+	sha1h		dg2s, dg0s
+	.ifnb		\dg1
+	sha1\op		dg0q, \dg1, t0.4s
+	.else
+	sha1\op		dg0q, dg1s, t0.4s
+	.endif
+	.else
+	.ifnb		\s0
+	add		t0.4s, v\s0\().4s, \rc\().4s
+	.endif
+	sha1h		dg1s, dg0s
+	sha1\op		dg0q, dg2s, t1.4s
+	.endif
+	.endm
+
+	.macro		add_update, op, ev, rc, s0, s1, s2, s3, dg1
+	sha1su0		v\s0\().4s, v\s1\().4s, v\s2\().4s
+	add_only	\op, \ev, \rc, \s1, \dg1
+	sha1su1		v\s0\().4s, v\s3\().4s
+	.endm
+
+	/*
+	 * The SHA1 round constants
+	 */
+	.align		4
+.Lsha1_rcon:
+	.word		0x5a827999, 0x6ed9eba1, 0x8f1bbcdc, 0xca62c1d6
+
+	/*
+	 * void sha1_ce_transform(int blocks, u8 const *src, u32 *state,
+	 * 			  u8 *head, long bytes)
+	 */
+ENTRY(sha1_ce_transform)
+	/* load round constants */
+	adr		x6, .Lsha1_rcon
+	ld1r		{k0.4s}, [x6], #4
+	ld1r		{k1.4s}, [x6], #4
+	ld1r		{k2.4s}, [x6], #4
+	ld1r		{k3.4s}, [x6]
+
+	/* load state */
+	ldr		dga, [x2]
+	ldr		dgb, [x2, #16]
+
+	/* load partial state (if supplied) */
+	cbz		x3, 0f
+	ld1		{v8.4s-v11.4s}, [x3]
+	b		1f
+
+	/* load input */
+0:	ld1		{v8.4s-v11.4s}, [x1], #64
+	sub		w0, w0, #1
+
+1:
+CPU_LE(	rev32		v8.16b, v8.16b		)
+CPU_LE(	rev32		v9.16b, v9.16b		)
+CPU_LE(	rev32		v10.16b, v10.16b	)
+CPU_LE(	rev32		v11.16b, v11.16b	)
+
+2:	add		t0.4s, v8.4s, k0.4s
+	mov		dg0v.16b, dgav.16b
+
+	add_update	c, ev, k0,  8,  9, 10, 11, dgb
+	add_update	c, od, k0,  9, 10, 11,  8
+	add_update	c, ev, k0, 10, 11,  8,  9
+	add_update	c, od, k0, 11,  8,  9, 10
+	add_update	c, ev, k1,  8,  9, 10, 11
+
+	add_update	p, od, k1,  9, 10, 11,  8
+	add_update	p, ev, k1, 10, 11,  8,  9
+	add_update	p, od, k1, 11,  8,  9, 10
+	add_update	p, ev, k1,  8,  9, 10, 11
+	add_update	p, od, k2,  9, 10, 11,  8
+
+	add_update	m, ev, k2, 10, 11,  8,  9
+	add_update	m, od, k2, 11,  8,  9, 10
+	add_update	m, ev, k2,  8,  9, 10, 11
+	add_update	m, od, k2,  9, 10, 11,  8
+	add_update	m, ev, k3, 10, 11,  8,  9
+
+	add_update	p, od, k3, 11,  8,  9, 10
+	add_only	p, ev, k3,  9
+	add_only	p, od, k3, 10
+	add_only	p, ev, k3, 11
+	add_only	p, od
+
+	/* update state */
+	add		dgbv.2s, dgbv.2s, dg1v.2s
+	add		dgav.4s, dgav.4s, dg0v.4s
+
+	cbnz		w0, 0b
+
+	/*
+	 * Final block: add padding and total bit count.
+	 * Skip if we have no total byte count in x4. In that case, the input
+	 * size was not a round multiple of the block size, and the padding is
+	 * handled by the C code.
+	 */
+	cbz		x4, 3f
+	movi		v9.2d, #0
+	mov		x8, #0x80000000
+	movi		v10.2d, #0
+	ror		x7, x4, #29		// ror(lsl(x4, 3), 32)
+	fmov		d8, x8
+	mov		x4, #0
+	mov		v11.d[0], xzr
+	mov		v11.d[1], x7
+	b		2b
+
+	/* store new state */
+3:	str		dga, [x2]
+	str		dgb, [x2, #16]
+	ret
+ENDPROC(sha1_ce_transform)
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
new file mode 100644
index 000000000000..6fe83f37a750
--- /dev/null
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -0,0 +1,174 @@
+/*
+ * sha1-ce-glue.c - SHA-1 secure hash using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * 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.
+ */
+
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <crypto/sha.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("SHA1 secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+asmlinkage void sha1_ce_transform(int blocks, u8 const *src, u32 *state,
+				  u8 *head, long bytes);
+
+static int sha1_init(struct shash_desc *desc)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+
+	*sctx = (struct sha1_state){
+		.state = { SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 },
+	};
+	return 0;
+}
+
+static int sha1_update(struct shash_desc *desc, const u8 *data,
+		       unsigned int len)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+	unsigned int partial = sctx->count % SHA1_BLOCK_SIZE;
+
+	sctx->count += len;
+
+	if ((partial + len) >= SHA1_BLOCK_SIZE) {
+		int blocks;
+
+		if (partial) {
+			int p = SHA1_BLOCK_SIZE - partial;
+
+			memcpy(sctx->buffer + partial, data, p);
+			data += p;
+			len -= p;
+		}
+
+		blocks = len / SHA1_BLOCK_SIZE;
+		len %= SHA1_BLOCK_SIZE;
+
+		kernel_neon_begin_partial(16);
+		sha1_ce_transform(blocks, data, sctx->state,
+				  partial ? sctx->buffer : NULL, 0);
+		kernel_neon_end();
+
+		data += blocks * SHA1_BLOCK_SIZE;
+		partial = 0;
+	}
+	if (len)
+		memcpy(sctx->buffer + partial, data, len);
+	return 0;
+}
+
+static int sha1_final(struct shash_desc *desc, u8 *out)
+{
+	static const u8 padding[SHA1_BLOCK_SIZE] = { 0x80, };
+
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+	__be64 bits = cpu_to_be64(sctx->count << 3);
+	__be32 *dst = (__be32 *)out;
+	int i;
+
+	u32 padlen = SHA1_BLOCK_SIZE
+		     - ((sctx->count + sizeof(bits)) % SHA1_BLOCK_SIZE);
+
+	sha1_update(desc, padding, padlen);
+	sha1_update(desc, (const u8 *)&bits, sizeof(bits));
+
+	for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(__be32); i++)
+		put_unaligned_be32(sctx->state[i], dst++);
+
+	*sctx = (struct sha1_state){};
+	return 0;
+}
+
+static int sha1_finup(struct shash_desc *desc, const u8 *data,
+		      unsigned int len, u8 *out)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+	__be32 *dst = (__be32 *)out;
+	int blocks;
+	int i;
+
+	if (sctx->count || !len || (len % SHA1_BLOCK_SIZE)) {
+		sha1_update(desc, data, len);
+		return sha1_final(desc, out);
+	}
+
+	/*
+	 * Use a fast path if the input is a multiple of 64 bytes. In
+	 * this case, there is no need to copy data around, and we can
+	 * perform the entire digest calculation in a single invocation
+	 * of sha1_ce_transform()
+	 */
+	blocks = len / SHA1_BLOCK_SIZE;
+
+	kernel_neon_begin_partial(16);
+	sha1_ce_transform(blocks, data, sctx->state, NULL, len);
+	kernel_neon_end();
+
+	for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(__be32); i++)
+		put_unaligned_be32(sctx->state[i], dst++);
+
+	*sctx = (struct sha1_state){};
+	return 0;
+}
+
+static int sha1_export(struct shash_desc *desc, void *out)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+	struct sha1_state *dst = out;
+
+	*dst = *sctx;
+	return 0;
+}
+
+static int sha1_import(struct shash_desc *desc, const void *in)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+	struct sha1_state const *src = in;
+
+	*sctx = *src;
+	return 0;
+}
+
+static struct shash_alg alg = {
+	.init			= sha1_init,
+	.update			= sha1_update,
+	.final			= sha1_final,
+	.finup			= sha1_finup,
+	.export			= sha1_export,
+	.import			= sha1_import,
+	.descsize		= sizeof(struct sha1_state),
+	.digestsize		= SHA1_DIGEST_SIZE,
+	.statesize		= sizeof(struct sha1_state),
+	.base			= {
+		.cra_name		= "sha1",
+		.cra_driver_name	= "sha1-ce",
+		.cra_priority		= 200,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA1_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+};
+
+static int __init sha1_ce_mod_init(void)
+{
+	return crypto_register_shash(&alg);
+}
+
+static void __exit sha1_ce_mod_fini(void)
+{
+	crypto_unregister_shash(&alg);
+}
+
+module_cpu_feature_match(SHA1, sha1_ce_mod_init);
+module_exit(sha1_ce_mod_fini);
diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S
new file mode 100644
index 000000000000..7f29fc031ea8
--- /dev/null
+++ b/arch/arm64/crypto/sha2-ce-core.S
@@ -0,0 +1,156 @@
+/*
+ * sha2-ce-core.S - core SHA-224/SHA-256 transform using v8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * 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.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.text
+	.arch		armv8-a+crypto
+
+	dga		.req	q20
+	dgav		.req	v20
+	dgb		.req	q21
+	dgbv		.req	v21
+
+	t0		.req	v22
+	t1		.req	v23
+
+	dg0q		.req	q24
+	dg0v		.req	v24
+	dg1q		.req	q25
+	dg1v		.req	v25
+	dg2q		.req	q26
+	dg2v		.req	v26
+
+	.macro		add_only, ev, rc, s0
+	mov		dg2v.16b, dg0v.16b
+	.ifeq		\ev
+	add		t1.4s, v\s0\().4s, \rc\().4s
+	sha256h		dg0q, dg1q, t0.4s
+	sha256h2	dg1q, dg2q, t0.4s
+	.else
+	.ifnb		\s0
+	add		t0.4s, v\s0\().4s, \rc\().4s
+	.endif
+	sha256h		dg0q, dg1q, t1.4s
+	sha256h2	dg1q, dg2q, t1.4s
+	.endif
+	.endm
+
+	.macro		add_update, ev, rc, s0, s1, s2, s3
+	sha256su0	v\s0\().4s, v\s1\().4s
+	add_only	\ev, \rc, \s1
+	sha256su1	v\s0\().4s, v\s2\().4s, v\s3\().4s
+	.endm
+
+	/*
+	 * The SHA-256 round constants
+	 */
+	.align		4
+.Lsha2_rcon:
+	.word		0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5
+	.word		0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5
+	.word		0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3
+	.word		0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174
+	.word		0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc
+	.word		0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da
+	.word		0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7
+	.word		0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967
+	.word		0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13
+	.word		0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85
+	.word		0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3
+	.word		0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070
+	.word		0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5
+	.word		0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3
+	.word		0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208
+	.word		0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
+
+	/*
+	 * void sha2_ce_transform(int blocks, u8 const *src, u32 *state,
+	 *                        u8 *head, long bytes)
+	 */
+ENTRY(sha2_ce_transform)
+	/* load round constants */
+	adr		x8, .Lsha2_rcon
+	ld1		{ v0.4s- v3.4s}, [x8], #64
+	ld1		{ v4.4s- v7.4s}, [x8], #64
+	ld1		{ v8.4s-v11.4s}, [x8], #64
+	ld1		{v12.4s-v15.4s}, [x8]
+
+	/* load state */
+	ldp		dga, dgb, [x2]
+
+	/* load partial input (if supplied) */
+	cbz		x3, 0f
+	ld1		{v16.4s-v19.4s}, [x3]
+	b		1f
+
+	/* load input */
+0:	ld1		{v16.4s-v19.4s}, [x1], #64
+	sub		w0, w0, #1
+
+1:
+CPU_LE(	rev32		v16.16b, v16.16b	)
+CPU_LE(	rev32		v17.16b, v17.16b	)
+CPU_LE(	rev32		v18.16b, v18.16b	)
+CPU_LE(	rev32		v19.16b, v19.16b	)
+
+2:	add		t0.4s, v16.4s, v0.4s
+	mov		dg0v.16b, dgav.16b
+	mov		dg1v.16b, dgbv.16b
+
+	add_update	0,  v1, 16, 17, 18, 19
+	add_update	1,  v2, 17, 18, 19, 16
+	add_update	0,  v3, 18, 19, 16, 17
+	add_update	1,  v4, 19, 16, 17, 18
+
+	add_update	0,  v5, 16, 17, 18, 19
+	add_update	1,  v6, 17, 18, 19, 16
+	add_update	0,  v7, 18, 19, 16, 17
+	add_update	1,  v8, 19, 16, 17, 18
+
+	add_update	0,  v9, 16, 17, 18, 19
+	add_update	1, v10, 17, 18, 19, 16
+	add_update	0, v11, 18, 19, 16, 17
+	add_update	1, v12, 19, 16, 17, 18
+
+	add_only	0, v13, 17
+	add_only	1, v14, 18
+	add_only	0, v15, 19
+	add_only	1
+
+	/* update state */
+	add		dgav.4s, dgav.4s, dg0v.4s
+	add		dgbv.4s, dgbv.4s, dg1v.4s
+
+	/* handled all input blocks? */
+	cbnz		w0, 0b
+
+	/*
+	 * Final block: add padding and total bit count.
+	 * Skip if we have no total byte count in x4. In that case, the input
+	 * size was not a round multiple of the block size, and the padding is
+	 * handled by the C code.
+	 */
+	cbz		x4, 3f
+	movi		v17.2d, #0
+	mov		x8, #0x80000000
+	movi		v18.2d, #0
+	ror		x7, x4, #29		// ror(lsl(x4, 3), 32)
+	fmov		d16, x8
+	mov		x4, #0
+	mov		v19.d[0], xzr
+	mov		v19.d[1], x7
+	b		2b
+
+	/* store new state */
+3:	stp		dga, dgb, [x2]
+	ret
+ENDPROC(sha2_ce_transform)
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
new file mode 100644
index 000000000000..c294e67d3925
--- /dev/null
+++ b/arch/arm64/crypto/sha2-ce-glue.c
@@ -0,0 +1,255 @@
+/*
+ * sha2-ce-glue.c - SHA-224/SHA-256 using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * 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.
+ */
+
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <crypto/sha.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+asmlinkage int sha2_ce_transform(int blocks, u8 const *src, u32 *state,
+				 u8 *head, long bytes);
+
+static int sha224_init(struct shash_desc *desc)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+
+	*sctx = (struct sha256_state){
+		.state = {
+			SHA224_H0, SHA224_H1, SHA224_H2, SHA224_H3,
+			SHA224_H4, SHA224_H5, SHA224_H6, SHA224_H7,
+		}
+	};
+	return 0;
+}
+
+static int sha256_init(struct shash_desc *desc)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+
+	*sctx = (struct sha256_state){
+		.state = {
+			SHA256_H0, SHA256_H1, SHA256_H2, SHA256_H3,
+			SHA256_H4, SHA256_H5, SHA256_H6, SHA256_H7,
+		}
+	};
+	return 0;
+}
+
+static int sha2_update(struct shash_desc *desc, const u8 *data,
+		       unsigned int len)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	unsigned int partial = sctx->count % SHA256_BLOCK_SIZE;
+
+	sctx->count += len;
+
+	if ((partial + len) >= SHA256_BLOCK_SIZE) {
+		int blocks;
+
+		if (partial) {
+			int p = SHA256_BLOCK_SIZE - partial;
+
+			memcpy(sctx->buf + partial, data, p);
+			data += p;
+			len -= p;
+		}
+
+		blocks = len / SHA256_BLOCK_SIZE;
+		len %= SHA256_BLOCK_SIZE;
+
+		kernel_neon_begin_partial(28);
+		sha2_ce_transform(blocks, data, sctx->state,
+				  partial ? sctx->buf : NULL, 0);
+		kernel_neon_end();
+
+		data += blocks * SHA256_BLOCK_SIZE;
+		partial = 0;
+	}
+	if (len)
+		memcpy(sctx->buf + partial, data, len);
+	return 0;
+}
+
+static void sha2_final(struct shash_desc *desc)
+{
+	static const u8 padding[SHA256_BLOCK_SIZE] = { 0x80, };
+
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	__be64 bits = cpu_to_be64(sctx->count << 3);
+	u32 padlen = SHA256_BLOCK_SIZE
+		     - ((sctx->count + sizeof(bits)) % SHA256_BLOCK_SIZE);
+
+	sha2_update(desc, padding, padlen);
+	sha2_update(desc, (const u8 *)&bits, sizeof(bits));
+}
+
+static int sha224_final(struct shash_desc *desc, u8 *out)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	__be32 *dst = (__be32 *)out;
+	int i;
+
+	sha2_final(desc);
+
+	for (i = 0; i < SHA224_DIGEST_SIZE / sizeof(__be32); i++)
+		put_unaligned_be32(sctx->state[i], dst++);
+
+	*sctx = (struct sha256_state){};
+	return 0;
+}
+
+static int sha256_final(struct shash_desc *desc, u8 *out)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	__be32 *dst = (__be32 *)out;
+	int i;
+
+	sha2_final(desc);
+
+	for (i = 0; i < SHA256_DIGEST_SIZE / sizeof(__be32); i++)
+		put_unaligned_be32(sctx->state[i], dst++);
+
+	*sctx = (struct sha256_state){};
+	return 0;
+}
+
+static void sha2_finup(struct shash_desc *desc, const u8 *data,
+		       unsigned int len)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	int blocks;
+
+	if (sctx->count || !len || (len % SHA256_BLOCK_SIZE)) {
+		sha2_update(desc, data, len);
+		sha2_final(desc);
+		return;
+	}
+
+	/*
+	 * Use a fast path if the input is a multiple of 64 bytes. In
+	 * this case, there is no need to copy data around, and we can
+	 * perform the entire digest calculation in a single invocation
+	 * of sha2_ce_transform()
+	 */
+	blocks = len / SHA256_BLOCK_SIZE;
+
+	kernel_neon_begin_partial(28);
+	sha2_ce_transform(blocks, data, sctx->state, NULL, len);
+	kernel_neon_end();
+	data += blocks * SHA256_BLOCK_SIZE;
+}
+
+static int sha224_finup(struct shash_desc *desc, const u8 *data,
+			unsigned int len, u8 *out)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	__be32 *dst = (__be32 *)out;
+	int i;
+
+	sha2_finup(desc, data, len);
+
+	for (i = 0; i < SHA224_DIGEST_SIZE / sizeof(__be32); i++)
+		put_unaligned_be32(sctx->state[i], dst++);
+
+	*sctx = (struct sha256_state){};
+	return 0;
+}
+
+static int sha256_finup(struct shash_desc *desc, const u8 *data,
+			unsigned int len, u8 *out)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	__be32 *dst = (__be32 *)out;
+	int i;
+
+	sha2_finup(desc, data, len);
+
+	for (i = 0; i < SHA256_DIGEST_SIZE / sizeof(__be32); i++)
+		put_unaligned_be32(sctx->state[i], dst++);
+
+	*sctx = (struct sha256_state){};
+	return 0;
+}
+
+static int sha2_export(struct shash_desc *desc, void *out)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	struct sha256_state *dst = out;
+
+	*dst = *sctx;
+	return 0;
+}
+
+static int sha2_import(struct shash_desc *desc, const void *in)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	struct sha256_state const *src = in;
+
+	*sctx = *src;
+	return 0;
+}
+
+static struct shash_alg algs[] = { {
+	.init			= sha224_init,
+	.update			= sha2_update,
+	.final			= sha224_final,
+	.finup			= sha224_finup,
+	.export			= sha2_export,
+	.import			= sha2_import,
+	.descsize		= sizeof(struct sha256_state),
+	.digestsize		= SHA224_DIGEST_SIZE,
+	.statesize		= sizeof(struct sha256_state),
+	.base			= {
+		.cra_name		= "sha224",
+		.cra_driver_name	= "sha224-ce",
+		.cra_priority		= 200,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA256_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+}, {
+	.init			= sha256_init,
+	.update			= sha2_update,
+	.final			= sha256_final,
+	.finup			= sha256_finup,
+	.export			= sha2_export,
+	.import			= sha2_import,
+	.descsize		= sizeof(struct sha256_state),
+	.digestsize		= SHA256_DIGEST_SIZE,
+	.statesize		= sizeof(struct sha256_state),
+	.base			= {
+		.cra_name		= "sha256",
+		.cra_driver_name	= "sha256-ce",
+		.cra_priority		= 200,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA256_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+} };
+
+static int __init sha2_ce_mod_init(void)
+{
+	return crypto_register_shashes(algs, ARRAY_SIZE(algs));
+}
+
+static void __exit sha2_ce_mod_fini(void)
+{
+	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+}
+
+module_cpu_feature_match(SHA2, sha2_ce_mod_init);
+module_exit(sha2_ce_mod_fini);
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 71c53ecfcc3a..43a2c9d2d6f4 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -35,6 +35,7 @@ generic-y += segment.h
 generic-y += sembuf.h
 generic-y += serial.h
 generic-y += shmbuf.h
+generic-y += simd.h
 generic-y += sizes.h
 generic-y += socket.h
 generic-y += sockios.h
diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c
index a79e7e9ab86e..0122bec38564 100644
--- a/crypto/blkcipher.c
+++ b/crypto/blkcipher.c
@@ -70,14 +70,12 @@ static inline u8 *blkcipher_get_spot(u8 *start, unsigned int len)
 	return max(start, end_page);
 }
 
-static inline unsigned int blkcipher_done_slow(struct crypto_blkcipher *tfm,
-					       struct blkcipher_walk *walk,
+static inline unsigned int blkcipher_done_slow(struct blkcipher_walk *walk,
 					       unsigned int bsize)
 {
 	u8 *addr;
-	unsigned int alignmask = crypto_blkcipher_alignmask(tfm);
 
-	addr = (u8 *)ALIGN((unsigned long)walk->buffer, alignmask + 1);
+	addr = (u8 *)ALIGN((unsigned long)walk->buffer, walk->alignmask + 1);
 	addr = blkcipher_get_spot(addr, bsize);
 	scatterwalk_copychunks(addr, &walk->out, bsize, 1);
 	return bsize;
@@ -105,7 +103,6 @@ static inline unsigned int blkcipher_done_fast(struct blkcipher_walk *walk,
 int blkcipher_walk_done(struct blkcipher_desc *desc,
 			struct blkcipher_walk *walk, int err)
 {
-	struct crypto_blkcipher *tfm = desc->tfm;
 	unsigned int nbytes = 0;
 
 	if (likely(err >= 0)) {
@@ -117,7 +114,7 @@ int blkcipher_walk_done(struct blkcipher_desc *desc,
 			err = -EINVAL;
 			goto err;
 		} else
-			n = blkcipher_done_slow(tfm, walk, n);
+			n = blkcipher_done_slow(walk, n);
 
 		nbytes = walk->total - n;
 		err = 0;
@@ -136,7 +133,7 @@ err:
 	}
 
 	if (walk->iv != desc->info)
-		memcpy(desc->info, walk->iv, crypto_blkcipher_ivsize(tfm));
+		memcpy(desc->info, walk->iv, walk->ivsize);
 	if (walk->buffer != walk->page)
 		kfree(walk->buffer);
 	if (walk->page)
@@ -226,22 +223,20 @@ static inline int blkcipher_next_fast(struct blkcipher_desc *desc,
 static int blkcipher_walk_next(struct blkcipher_desc *desc,
 			       struct blkcipher_walk *walk)
 {
-	struct crypto_blkcipher *tfm = desc->tfm;
-	unsigned int alignmask = crypto_blkcipher_alignmask(tfm);
 	unsigned int bsize;
 	unsigned int n;
 	int err;
 
 	n = walk->total;
-	if (unlikely(n < crypto_blkcipher_blocksize(tfm))) {
+	if (unlikely(n < walk->cipher_blocksize)) {
 		desc->flags |= CRYPTO_TFM_RES_BAD_BLOCK_LEN;
 		return blkcipher_walk_done(desc, walk, -EINVAL);
 	}
 
 	walk->flags &= ~(BLKCIPHER_WALK_SLOW | BLKCIPHER_WALK_COPY |
 			 BLKCIPHER_WALK_DIFF);
-	if (!scatterwalk_aligned(&walk->in, alignmask) ||
-	    !scatterwalk_aligned(&walk->out, alignmask)) {
+	if (!scatterwalk_aligned(&walk->in, walk->alignmask) ||
+	    !scatterwalk_aligned(&walk->out, walk->alignmask)) {
 		walk->flags |= BLKCIPHER_WALK_COPY;
 		if (!walk->page) {
 			walk->page = (void *)__get_free_page(GFP_ATOMIC);
@@ -250,12 +245,12 @@ static int blkcipher_walk_next(struct blkcipher_desc *desc,
 		}
 	}
 
-	bsize = min(walk->blocksize, n);
+	bsize = min(walk->walk_blocksize, n);
 	n = scatterwalk_clamp(&walk->in, n);
 	n = scatterwalk_clamp(&walk->out, n);
 
 	if (unlikely(n < bsize)) {
-		err = blkcipher_next_slow(desc, walk, bsize, alignmask);
+		err = blkcipher_next_slow(desc, walk, bsize, walk->alignmask);
 		goto set_phys_lowmem;
 	}
 
@@ -277,28 +272,26 @@ set_phys_lowmem:
 	return err;
 }
 
-static inline int blkcipher_copy_iv(struct blkcipher_walk *walk,
-				    struct crypto_blkcipher *tfm,
-				    unsigned int alignmask)
+static inline int blkcipher_copy_iv(struct blkcipher_walk *walk)
 {
-	unsigned bs = walk->blocksize;
-	unsigned int ivsize = crypto_blkcipher_ivsize(tfm);
-	unsigned aligned_bs = ALIGN(bs, alignmask + 1);
-	unsigned int size = aligned_bs * 2 + ivsize + max(aligned_bs, ivsize) -
-			    (alignmask + 1);
+	unsigned bs = walk->walk_blocksize;
+	unsigned aligned_bs = ALIGN(bs, walk->alignmask + 1);
+	unsigned int size = aligned_bs * 2 +
+			    walk->ivsize + max(aligned_bs, walk->ivsize) -
+			    (walk->alignmask + 1);
 	u8 *iv;
 
-	size += alignmask & ~(crypto_tfm_ctx_alignment() - 1);
+	size += walk->alignmask & ~(crypto_tfm_ctx_alignment() - 1);
 	walk->buffer = kmalloc(size, GFP_ATOMIC);
 	if (!walk->buffer)
 		return -ENOMEM;
 
-	iv = (u8 *)ALIGN((unsigned long)walk->buffer, alignmask + 1);
+	iv = (u8 *)ALIGN((unsigned long)walk->buffer, walk->alignmask + 1);
 	iv = blkcipher_get_spot(iv, bs) + aligned_bs;
 	iv = blkcipher_get_spot(iv, bs) + aligned_bs;
-	iv = blkcipher_get_spot(iv, ivsize);
+	iv = blkcipher_get_spot(iv, walk->ivsize);
 
-	walk->iv = memcpy(iv, walk->iv, ivsize);
+	walk->iv = memcpy(iv, walk->iv, walk->ivsize);
 	return 0;
 }
 
@@ -306,7 +299,10 @@ int blkcipher_walk_virt(struct blkcipher_desc *desc,
 			struct blkcipher_walk *walk)
 {
 	walk->flags &= ~BLKCIPHER_WALK_PHYS;
-	walk->blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->walk_blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->cipher_blocksize = walk->walk_blocksize;
+	walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
+	walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
 	return blkcipher_walk_first(desc, walk);
 }
 EXPORT_SYMBOL_GPL(blkcipher_walk_virt);
@@ -315,7 +311,10 @@ int blkcipher_walk_phys(struct blkcipher_desc *desc,
 			struct blkcipher_walk *walk)
 {
 	walk->flags |= BLKCIPHER_WALK_PHYS;
-	walk->blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->walk_blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->cipher_blocksize = walk->walk_blocksize;
+	walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
+	walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
 	return blkcipher_walk_first(desc, walk);
 }
 EXPORT_SYMBOL_GPL(blkcipher_walk_phys);
@@ -323,9 +322,6 @@ EXPORT_SYMBOL_GPL(blkcipher_walk_phys);
 static int blkcipher_walk_first(struct blkcipher_desc *desc,
 				struct blkcipher_walk *walk)
 {
-	struct crypto_blkcipher *tfm = desc->tfm;
-	unsigned int alignmask = crypto_blkcipher_alignmask(tfm);
-
 	if (WARN_ON_ONCE(in_irq()))
 		return -EDEADLK;
 
@@ -335,8 +331,8 @@ static int blkcipher_walk_first(struct blkcipher_desc *desc,
 
 	walk->buffer = NULL;
 	walk->iv = desc->info;
-	if (unlikely(((unsigned long)walk->iv & alignmask))) {
-		int err = blkcipher_copy_iv(walk, tfm, alignmask);
+	if (unlikely(((unsigned long)walk->iv & walk->alignmask))) {
+		int err = blkcipher_copy_iv(walk);
 		if (err)
 			return err;
 	}
@@ -353,11 +349,28 @@ int blkcipher_walk_virt_block(struct blkcipher_desc *desc,
 			      unsigned int blocksize)
 {
 	walk->flags &= ~BLKCIPHER_WALK_PHYS;
-	walk->blocksize = blocksize;
+	walk->walk_blocksize = blocksize;
+	walk->cipher_blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
+	walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
 	return blkcipher_walk_first(desc, walk);
 }
 EXPORT_SYMBOL_GPL(blkcipher_walk_virt_block);
 
+int blkcipher_aead_walk_virt_block(struct blkcipher_desc *desc,
+				   struct blkcipher_walk *walk,
+				   struct crypto_aead *tfm,
+				   unsigned int blocksize)
+{
+	walk->flags &= ~BLKCIPHER_WALK_PHYS;
+	walk->walk_blocksize = blocksize;
+	walk->cipher_blocksize = crypto_aead_blocksize(tfm);
+	walk->ivsize = crypto_aead_ivsize(tfm);
+	walk->alignmask = crypto_aead_alignmask(tfm);
+	return blkcipher_walk_first(desc, walk);
+}
+EXPORT_SYMBOL_GPL(blkcipher_aead_walk_virt_block);
+
 static int setkey_unaligned(struct crypto_tfm *tfm, const u8 *key,
 			    unsigned int keylen)
 {
diff --git a/drivers/bus/arm-cci.c b/drivers/bus/arm-cci.c
index 962fd35cbd8d..bc8e1af279c0 100644
--- a/drivers/bus/arm-cci.c
+++ b/drivers/bus/arm-cci.c
@@ -26,6 +26,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/irq_regs.h>
+#include <asm/psci.h>
 #include <asm/pmu.h>
 #include <asm/smp_plat.h>
 
@@ -544,6 +545,7 @@ static int cci_pmu_init(struct arm_pmu *cci_pmu, struct platform_device *pdev)
 
 	cci_pmu->plat_device = pdev;
 	cci_pmu->num_events = pmu_get_max_counters();
+	cpumask_setall(&cci_pmu->valid_cpus);
 
 	return armpmu_register(cci_pmu, -1);
 }
@@ -969,6 +971,11 @@ static int cci_probe(void)
 	const char *match_str;
 	bool is_ace;
 
+	if (psci_probe() == 0) {
+		pr_debug("psci found. Aborting cci probe\n");
+		return -ENODEV;
+	}
+
 	np = of_find_matching_node(NULL, arm_cci_matches);
 	if (!np)
 		return -ENODEV;
diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig
index e90061f56128..99e145ee0cef 100644
--- a/drivers/video/Kconfig
+++ b/drivers/video/Kconfig
@@ -39,6 +39,11 @@ config VIDEOMODE_HELPERS
 config HDMI
 	bool
 
+config VEXPRESS_DVI_CONTROL
+	bool "Versatile Express DVI control"
+	depends on FB && VEXPRESS_CONFIG
+	default y
+
 menuconfig FB
 	tristate "Support for frame buffer devices"
 	---help---
@@ -327,6 +332,21 @@ config FB_ARMCLCD
 	  here and read <file:Documentation/kbuild/modules.txt>.  The module
 	  will be called amba-clcd.
 
+config FB_ARMHDLCD
+	tristate "ARM High Definition LCD support"
+	depends on FB && ARM
+	select FB_CFB_FILLRECT
+	select FB_CFB_COPYAREA
+	select FB_CFB_IMAGEBLIT
+	help
+	  This framebuffer device driver is for the ARM High Definition
+	  Colour LCD controller.
+
+	  If you want to compile this as a module (=code which can be
+	  inserted into and removed from the running kernel), say M
+	  here and read <file:Documentation/kbuild/modules.txt>.  The module
+	  will be called arm-hdlcd.
+
 config FB_ACORN
 	bool "Acorn VIDC support"
 	depends on (FB = y) && ARM && ARCH_ACORN
diff --git a/drivers/video/Makefile b/drivers/video/Makefile
index accf67ae97b8..8abfb4db9b71 100644
--- a/drivers/video/Makefile
+++ b/drivers/video/Makefile
@@ -100,6 +100,7 @@ obj-$(CONFIG_FB_ATMEL)		  += atmel_lcdfb.o
 obj-$(CONFIG_FB_PVR2)             += pvr2fb.o
 obj-$(CONFIG_FB_VOODOO1)          += sstfb.o
 obj-$(CONFIG_FB_ARMCLCD)	  += amba-clcd.o
+obj-$(CONFIG_FB_ARMHDLCD)	  += arm-hdlcd.o
 obj-$(CONFIG_FB_GOLDFISH)         += goldfishfb.o
 obj-$(CONFIG_FB_68328)            += 68328fb.o
 obj-$(CONFIG_FB_GBE)              += gbefb.o
@@ -179,3 +180,6 @@ obj-$(CONFIG_VIDEOMODE_HELPERS) += display_timing.o videomode.o
 ifeq ($(CONFIG_OF),y)
 obj-$(CONFIG_VIDEOMODE_HELPERS) += of_display_timing.o of_videomode.o
 endif
+
+# platform specific output drivers
+obj-$(CONFIG_VEXPRESS_DVI_CONTROL) += vexpress-dvi.o
diff --git a/drivers/video/amba-clcd.c b/drivers/video/amba-clcd.c
index 14d6b3793e0a..12f8c4640397 100644
--- a/drivers/video/amba-clcd.c
+++ b/drivers/video/amba-clcd.c
@@ -17,7 +17,10 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/memblock.h>
 #include <linux/mm.h>
+#include <linux/of.h>
 #include <linux/fb.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
@@ -31,8 +34,20 @@
 
 #define to_clcd(info)	container_of(info, struct clcd_fb, fb)
 
+#ifdef CONFIG_ARM
+#define clcdfb_dma_alloc	dma_alloc_writecombine
+#define clcdfb_dma_free		dma_free_writecombine
+#define clcdfb_dma_mmap		dma_mmap_writecombine
+#else
+#define clcdfb_dma_alloc	dma_alloc_coherent
+#define clcdfb_dma_free		dma_free_coherent
+#define clcdfb_dma_mmap		dma_mmap_coherent
+#endif
+
 /* This is limited to 16 characters when displayed by X startup */
 static const char *clcd_name = "CLCD FB";
+static char *def_mode;
+module_param_named(mode, def_mode, charp, 0);
 
 /*
  * Unfortunately, the enable/disable functions may be called either from
@@ -234,6 +249,17 @@ clcdfb_set_bitfields(struct clcd_fb *fb, struct fb_var_screeninfo *var)
 		bgr = caps & CLCD_CAP_BGR && var->blue.offset == 0;
 		rgb = caps & CLCD_CAP_RGB && var->red.offset == 0;
 
+		/*
+		 * Seems that for 32-bit mode there is confusion about RGB
+		 * ordering somewhere between user-side, kernel and hardware.
+		 * The following hack seems get things working, at least on
+		 * vexpress hardware and models...
+		 */
+		if (var->bits_per_pixel == 32) {
+			bgr = false;
+			rgb = true;
+		}
+
 		if (!bgr && !rgb)
 			/*
 			 * The requested format was not possible, try just
@@ -393,6 +419,44 @@ static int clcdfb_blank(int blank_mode, struct fb_info *info)
 	return 0;
 }
 
+int clcdfb_mmap_dma(struct clcd_fb *fb, struct vm_area_struct *vma)
+{
+	return clcdfb_dma_mmap(&fb->dev->dev, vma,
+			       fb->fb.screen_base,
+			       fb->fb.fix.smem_start,
+			       fb->fb.fix.smem_len);
+}
+
+int clcdfb_mmap_io(struct clcd_fb *fb, struct vm_area_struct *vma)
+{
+	unsigned long user_count, count, pfn, off;
+
+	user_count	= (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	count		= PAGE_ALIGN(fb->fb.fix.smem_len) >> PAGE_SHIFT;
+	pfn		= fb->fb.fix.smem_start >> PAGE_SHIFT;
+	off		= vma->vm_pgoff;
+
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+	if (off < count && user_count <= (count - off))
+		return remap_pfn_range(vma, vma->vm_start, pfn + off,
+				       user_count << PAGE_SHIFT,
+				       vma->vm_page_prot);
+
+	return -ENXIO;
+}
+
+void clcdfb_remove_dma(struct clcd_fb *fb)
+{
+	clcdfb_dma_free(&fb->dev->dev, fb->fb.fix.smem_len,
+			fb->fb.screen_base, fb->fb.fix.smem_start);
+}
+
+void clcdfb_remove_io(struct clcd_fb *fb)
+{
+	iounmap(fb->fb.screen_base);
+}
+
 static int clcdfb_mmap(struct fb_info *info,
 		       struct vm_area_struct *vma)
 {
@@ -543,14 +607,247 @@ static int clcdfb_register(struct clcd_fb *fb)
 	return ret;
 }
 
+struct string_lookup {
+	const char *string;
+	const u32	val;
+};
+
+static struct string_lookup vmode_lookups[] = {
+	{ "FB_VMODE_NONINTERLACED", FB_VMODE_NONINTERLACED},
+	{ "FB_VMODE_INTERLACED",    FB_VMODE_INTERLACED},
+	{ "FB_VMODE_DOUBLE",        FB_VMODE_DOUBLE},
+	{ "FB_VMODE_ODD_FLD_FIRST", FB_VMODE_ODD_FLD_FIRST},
+	{ NULL, 0 },
+};
+
+static struct string_lookup tim2_lookups[] = {
+	{ "TIM2_CLKSEL", TIM2_CLKSEL},
+	{ "TIM2_IVS",    TIM2_IVS},
+	{ "TIM2_IHS",    TIM2_IHS},
+	{ "TIM2_IPC",    TIM2_IPC},
+	{ "TIM2_IOE",    TIM2_IOE},
+	{ "TIM2_BCD",    TIM2_BCD},
+	{ NULL, 0},
+};
+static struct string_lookup cntl_lookups[] = {
+	{"CNTL_LCDEN",        CNTL_LCDEN},
+	{"CNTL_LCDBPP1",      CNTL_LCDBPP1},
+	{"CNTL_LCDBPP2",      CNTL_LCDBPP2},
+	{"CNTL_LCDBPP4",      CNTL_LCDBPP4},
+	{"CNTL_LCDBPP8",      CNTL_LCDBPP8},
+	{"CNTL_LCDBPP16",     CNTL_LCDBPP16},
+	{"CNTL_LCDBPP16_565", CNTL_LCDBPP16_565},
+	{"CNTL_LCDBPP16_444", CNTL_LCDBPP16_444},
+	{"CNTL_LCDBPP24",     CNTL_LCDBPP24},
+	{"CNTL_LCDBW",        CNTL_LCDBW},
+	{"CNTL_LCDTFT",       CNTL_LCDTFT},
+	{"CNTL_LCDMONO8",     CNTL_LCDMONO8},
+	{"CNTL_LCDDUAL",      CNTL_LCDDUAL},
+	{"CNTL_BGR",          CNTL_BGR},
+	{"CNTL_BEBO",         CNTL_BEBO},
+	{"CNTL_BEPO",         CNTL_BEPO},
+	{"CNTL_LCDPWR",       CNTL_LCDPWR},
+	{"CNTL_LCDVCOMP(1)",  CNTL_LCDVCOMP(1)},
+	{"CNTL_LCDVCOMP(2)",  CNTL_LCDVCOMP(2)},
+	{"CNTL_LCDVCOMP(3)",  CNTL_LCDVCOMP(3)},
+	{"CNTL_LCDVCOMP(4)",  CNTL_LCDVCOMP(4)},
+	{"CNTL_LCDVCOMP(5)",  CNTL_LCDVCOMP(5)},
+	{"CNTL_LCDVCOMP(6)",  CNTL_LCDVCOMP(6)},
+	{"CNTL_LCDVCOMP(7)",  CNTL_LCDVCOMP(7)},
+	{"CNTL_LDMAFIFOTIME", CNTL_LDMAFIFOTIME},
+	{"CNTL_WATERMARK",    CNTL_WATERMARK},
+	{ NULL, 0},
+};
+static struct string_lookup caps_lookups[] = {
+	{"CLCD_CAP_RGB444",  CLCD_CAP_RGB444},
+	{"CLCD_CAP_RGB5551", CLCD_CAP_RGB5551},
+	{"CLCD_CAP_RGB565",  CLCD_CAP_RGB565},
+	{"CLCD_CAP_RGB888",  CLCD_CAP_RGB888},
+	{"CLCD_CAP_BGR444",  CLCD_CAP_BGR444},
+	{"CLCD_CAP_BGR5551", CLCD_CAP_BGR5551},
+	{"CLCD_CAP_BGR565",  CLCD_CAP_BGR565},
+	{"CLCD_CAP_BGR888",  CLCD_CAP_BGR888},
+	{"CLCD_CAP_444",     CLCD_CAP_444},
+	{"CLCD_CAP_5551",    CLCD_CAP_5551},
+	{"CLCD_CAP_565",     CLCD_CAP_565},
+	{"CLCD_CAP_888",     CLCD_CAP_888},
+	{"CLCD_CAP_RGB",     CLCD_CAP_RGB},
+	{"CLCD_CAP_BGR",     CLCD_CAP_BGR},
+	{"CLCD_CAP_ALL",     CLCD_CAP_ALL},
+	{ NULL, 0},
+};
+
+u32 parse_setting(struct string_lookup *lookup, const char *name)
+{
+	int i = 0;
+	while (lookup[i].string != NULL) {
+		if (strcmp(lookup[i].string, name) == 0)
+			return lookup[i].val;
+		++i;
+	}
+	return -EINVAL;
+}
+
+u32 get_string_lookup(struct device_node *node, const char *name,
+		      struct string_lookup *lookup)
+{
+	const char *string;
+	int count, i, ret = 0;
+
+	count = of_property_count_strings(node, name);
+	if (count >= 0)
+		for (i = 0; i < count; i++)
+			if (of_property_read_string_index(node, name, i,
+					&string) == 0)
+				ret |= parse_setting(lookup, string);
+	return ret;
+}
+
+int get_val(struct device_node *node, const char *string)
+{
+	u32 ret = 0;
+
+	if (of_property_read_u32(node, string, &ret))
+		ret = -1;
+	return ret;
+}
+
+struct clcd_panel *getPanel(struct device_node *node)
+{
+	static struct clcd_panel panel;
+
+	panel.mode.refresh      = get_val(node, "refresh");
+	panel.mode.xres         = get_val(node, "xres");
+	panel.mode.yres         = get_val(node, "yres");
+	panel.mode.pixclock     = get_val(node, "pixclock");
+	panel.mode.left_margin  = get_val(node, "left_margin");
+	panel.mode.right_margin = get_val(node, "right_margin");
+	panel.mode.upper_margin = get_val(node, "upper_margin");
+	panel.mode.lower_margin = get_val(node, "lower_margin");
+	panel.mode.hsync_len    = get_val(node, "hsync_len");
+	panel.mode.vsync_len    = get_val(node, "vsync_len");
+	panel.mode.sync         = get_val(node, "sync");
+	panel.bpp               = get_val(node, "bpp");
+	panel.width             = (signed short) get_val(node, "width");
+	panel.height            = (signed short) get_val(node, "height");
+
+	panel.mode.vmode = get_string_lookup(node, "vmode", vmode_lookups);
+	panel.tim2       = get_string_lookup(node, "tim2",  tim2_lookups);
+	panel.cntl       = get_string_lookup(node, "cntl",  cntl_lookups);
+	panel.caps       = get_string_lookup(node, "caps",  caps_lookups);
+
+	return &panel;
+}
+
+struct clcd_panel *clcdfb_get_panel(const char *name)
+{
+	struct device_node *node = NULL;
+	const char *mode;
+	struct clcd_panel *panel = NULL;
+
+	do {
+		node = of_find_compatible_node(node, NULL, "panel");
+		if (node)
+			if (of_property_read_string(node, "mode", &mode) == 0)
+				if (strcmp(mode, name) == 0) {
+					panel = getPanel(node);
+					panel->mode.name = name;
+				}
+	} while (node != NULL);
+
+	return panel;
+}
+
+#ifdef CONFIG_OF
+static int clcdfb_dt_init(struct clcd_fb *fb)
+{
+	int err = 0;
+	struct device_node *node;
+	const char *mode;
+	dma_addr_t dma;
+	u32 use_dma;
+	const __be32 *prop;
+	int len, na, ns;
+	phys_addr_t fb_base, fb_size;
+
+	node = fb->dev->dev.of_node;
+	if (!node)
+		return -ENODEV;
+
+	na = of_n_addr_cells(node);
+	ns = of_n_size_cells(node);
+
+	if (def_mode && strlen(def_mode) > 0) {
+		fb->panel = clcdfb_get_panel(def_mode);
+		if (!fb->panel)
+			printk(KERN_ERR "CLCD: invalid mode specified on the command line (%s)\n", def_mode);
+	}
+
+	if (!fb->panel) {
+		if (WARN_ON(of_property_read_string(node, "mode", &mode)))
+			return -ENODEV;
+		fb->panel = clcdfb_get_panel(mode);
+	}
+
+	if (!fb->panel)
+		return -EINVAL;
+	fb->fb.fix.smem_len = fb->panel->mode.xres * fb->panel->mode.yres * 4;
+
+	fb->board->name		= "Device Tree CLCD PL111";
+	fb->board->caps		= CLCD_CAP_5551 | CLCD_CAP_565 | CLCD_CAP_888;
+	fb->board->check	= clcdfb_check;
+	fb->board->decode	= clcdfb_decode;
+
+	if (of_property_read_u32(node, "use_dma", &use_dma))
+		use_dma = 0;
+
+	if (use_dma) {
+		fb->fb.screen_base = clcdfb_dma_alloc(&fb->dev->dev,
+						      fb->fb.fix.smem_len,
+						      &dma, GFP_KERNEL);
+		if (!fb->fb.screen_base) {
+			pr_err("CLCD: unable to map framebuffer\n");
+			return -ENOMEM;
+		}
+
+		fb->fb.fix.smem_start	= dma;
+		fb->board->mmap		= clcdfb_mmap_dma;
+		fb->board->remove	= clcdfb_remove_dma;
+	} else {
+		prop = of_get_property(node, "framebuffer", &len);
+		if (WARN_ON(!prop || len < (na + ns) * sizeof(*prop)))
+			return -EINVAL;
+
+		fb_base = of_read_number(prop, na);
+		fb_size = of_read_number(prop + na, ns);
+
+		fb->fb.fix.smem_start	= fb_base;
+		fb->fb.screen_base	= ioremap_wc(fb_base, fb_size);
+		fb->board->mmap		= clcdfb_mmap_io;
+		fb->board->remove	= clcdfb_remove_io;
+	}
+
+	return err;
+}
+#endif /* CONFIG_OF */
+
 static int clcdfb_probe(struct amba_device *dev, const struct amba_id *id)
 {
 	struct clcd_board *board = dev_get_platdata(&dev->dev);
 	struct clcd_fb *fb;
 	int ret;
 
-	if (!board)
-		return -EINVAL;
+	if (!board) {
+#ifdef CONFIG_OF
+		if (dev->dev.of_node) {
+			board = kzalloc(sizeof(struct clcd_board), GFP_KERNEL);
+			if (!board)
+				return -ENOMEM;
+			board->setup   = clcdfb_dt_init;
+		} else
+#endif
+			return -EINVAL;
+	}
 
 	ret = dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32));
 	if (ret)
diff --git a/drivers/video/arm-hdlcd.c b/drivers/video/arm-hdlcd.c
new file mode 100644
index 000000000000..cfd631e3dc52
--- /dev/null
+++ b/drivers/video/arm-hdlcd.c
@@ -0,0 +1,844 @@
+/*
+ * drivers/video/arm-hdlcd.c
+ *
+ * Copyright (C) 2011 ARM Limited
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive
+ * for more details.
+ *
+ *  ARM HDLCD Controller
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/mm.h>
+#include <linux/delay.h>
+#include <linux/of.h>
+#include <linux/fb.h>
+#include <linux/clk.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/ioport.h>
+#include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
+#include <linux/memblock.h>
+#include <linux/arm-hdlcd.h>
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#endif
+
+#include "edid.h"
+
+#ifdef CONFIG_SERIAL_AMBA_PCU_UART
+int get_edid(u8 *msgbuf);
+#else
+#endif
+
+#define to_hdlcd_device(info)	container_of(info, struct hdlcd_device, fb)
+
+static struct of_device_id  hdlcd_of_matches[] = {
+	{ .compatible	= "arm,hdlcd" },
+	{},
+};
+
+/* Framebuffer size.  */
+static unsigned long framebuffer_size;
+
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+static unsigned long buffer_underrun_events;
+static DEFINE_SPINLOCK(hdlcd_underrun_lock);
+
+static void hdlcd_underrun_set(unsigned long val)
+{
+	spin_lock(&hdlcd_underrun_lock);
+	buffer_underrun_events = val;
+	spin_unlock(&hdlcd_underrun_lock);
+}
+
+static unsigned long hdlcd_underrun_get(void)
+{
+	unsigned long val;
+	spin_lock(&hdlcd_underrun_lock);
+	val = buffer_underrun_events;
+	spin_unlock(&hdlcd_underrun_lock);
+	return val;
+}
+
+#ifdef CONFIG_PROC_FS
+static int hdlcd_underrun_show(struct seq_file *m, void *v)
+{
+	unsigned char underrun_string[32];
+	snprintf(underrun_string, 32, "%lu\n", hdlcd_underrun_get());
+	seq_puts(m, underrun_string);
+	return 0;
+}
+
+static int proc_hdlcd_underrun_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hdlcd_underrun_show, NULL);
+}
+
+static const struct file_operations proc_hdlcd_underrun_operations = {
+	.open		= proc_hdlcd_underrun_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int hdlcd_underrun_init(void)
+{
+	hdlcd_underrun_set(0);
+	proc_create("hdlcd_underrun", 0, NULL, &proc_hdlcd_underrun_operations);
+	return 0;
+}
+static void hdlcd_underrun_close(void)
+{
+	remove_proc_entry("hdlcd_underrun", NULL);
+}
+#else
+static int hdlcd_underrun_init(void) { return 0; }
+static void hdlcd_underrun_close(void) { }
+#endif
+#endif
+
+static char *fb_mode = "1680x1050-32@60\0\0\0\0\0";
+
+static struct fb_var_screeninfo cached_var_screeninfo;
+
+static struct fb_videomode hdlcd_default_mode = {
+	.refresh	= 60,
+	.xres		= 1680,
+	.yres		= 1050,
+	.pixclock	= 8403,
+	.left_margin	= 80,
+	.right_margin	= 48,
+	.upper_margin	= 21,
+	.lower_margin	= 3,
+	.hsync_len	= 32,
+	.vsync_len	= 6,
+	.sync		= FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+	.vmode		= FB_VMODE_NONINTERLACED
+};
+
+static inline void hdlcd_enable(struct hdlcd_device *hdlcd)
+{
+	dev_dbg(hdlcd->dev, "HDLCD: output enabled\n");
+	writel(1, hdlcd->base + HDLCD_REG_COMMAND);
+}
+
+static inline void hdlcd_disable(struct hdlcd_device *hdlcd)
+{
+	dev_dbg(hdlcd->dev, "HDLCD: output disabled\n");
+	writel(0, hdlcd->base + HDLCD_REG_COMMAND);
+}
+
+static int hdlcd_set_bitfields(struct hdlcd_device *hdlcd,
+				struct fb_var_screeninfo *var)
+{
+	int ret = 0;
+
+	memset(&var->transp, 0, sizeof(var->transp));
+	var->red.msb_right = 0;
+	var->green.msb_right = 0;
+	var->blue.msb_right = 0;
+	var->blue.offset = 0;
+
+	switch (var->bits_per_pixel) {
+	case 8:
+		/* pseudocolor */
+		var->red.length = 8;
+		var->green.length = 8;
+		var->blue.length = 8;
+		break;
+	case 16:
+		/* 565 format */
+		var->red.length = 5;
+		var->green.length = 6;
+		var->blue.length = 5;
+		break;
+	case 32:
+		var->transp.length = 8;
+	case 24:
+		var->red.length = 8;
+		var->green.length = 8;
+		var->blue.length = 8;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	if (!ret) {
+		if(var->bits_per_pixel != 32)
+		{
+			var->green.offset = var->blue.length;
+			var->red.offset = var->green.offset + var->green.length;
+		}
+		else
+		{
+			/* Previously, the byte ordering for 32-bit color was
+			 * (msb)<alpha><red><green><blue>(lsb)
+			 * but this does not match what android expects and
+			 * the colors are odd. Instead, use
+			 * <alpha><blue><green><red>
+			 * Since we tell fb what we are doing, console
+			 * , X and directfb access should work fine.
+			 */
+			var->green.offset = var->red.length;
+			var->blue.offset = var->green.offset + var->green.length;
+			var->transp.offset = var->blue.offset + var->blue.length;
+		}
+	}
+
+	return ret;
+}
+
+static int hdlcd_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
+{
+	struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+	int bytes_per_pixel = var->bits_per_pixel / 8;
+
+#ifdef HDLCD_NO_VIRTUAL_SCREEN
+	var->yres_virtual = var->yres;
+#else
+	var->yres_virtual = 2 * var->yres;
+#endif
+
+	if ((var->xres_virtual * bytes_per_pixel * var->yres_virtual) > hdlcd->fb.fix.smem_len)
+		return -ENOMEM;
+
+	if (var->xres > HDLCD_MAX_XRES || var->yres > HDLCD_MAX_YRES)
+		return -EINVAL;
+
+	/* make sure the bitfields are set appropriately */
+	return hdlcd_set_bitfields(hdlcd, var);
+}
+
+/* prototype */
+static int hdlcd_pan_display(struct fb_var_screeninfo *var,
+	struct fb_info *info);
+
+#define WRITE_HDLCD_REG(reg, value)	writel((value), hdlcd->base + (reg))
+#define READ_HDLCD_REG(reg)		readl(hdlcd->base + (reg))
+
+static int hdlcd_set_par(struct fb_info *info)
+{
+	struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+	int bytes_per_pixel = hdlcd->fb.var.bits_per_pixel / 8;
+	int polarities;
+	int old_yoffset;
+
+	/* check for shortcuts */
+	old_yoffset = cached_var_screeninfo.yoffset;
+	cached_var_screeninfo.yoffset = info->var.yoffset;
+	if (!memcmp(&info->var, &cached_var_screeninfo,
+				sizeof(struct fb_var_screeninfo))) {
+		if(old_yoffset != info->var.yoffset) {
+			/* we only changed yoffset, and we already
+			 * already recorded it a couple lines up
+			 */
+			hdlcd_pan_display(&info->var, info);
+		}
+		/* or no change */
+		return 0;
+	}
+
+	hdlcd->fb.fix.line_length = hdlcd->fb.var.xres * bytes_per_pixel;
+
+	if (hdlcd->fb.var.bits_per_pixel >= 16)
+		hdlcd->fb.fix.visual = FB_VISUAL_TRUECOLOR;
+	else
+		hdlcd->fb.fix.visual = FB_VISUAL_PSEUDOCOLOR;
+
+	memcpy(&cached_var_screeninfo, &info->var, sizeof(struct fb_var_screeninfo));
+
+	polarities = HDLCD_POLARITY_DATAEN |
+#ifndef CONFIG_ARCH_TUSCAN
+		HDLCD_POLARITY_PIXELCLK |
+#endif
+		HDLCD_POLARITY_DATA;
+	polarities |= (hdlcd->fb.var.sync & FB_SYNC_HOR_HIGH_ACT) ? HDLCD_POLARITY_HSYNC : 0;
+	polarities |= (hdlcd->fb.var.sync & FB_SYNC_VERT_HIGH_ACT) ? HDLCD_POLARITY_VSYNC : 0;
+
+	hdlcd_disable(hdlcd);
+
+	WRITE_HDLCD_REG(HDLCD_REG_FB_LINE_LENGTH, hdlcd->fb.var.xres * bytes_per_pixel);
+	WRITE_HDLCD_REG(HDLCD_REG_FB_LINE_PITCH, hdlcd->fb.var.xres * bytes_per_pixel);
+	WRITE_HDLCD_REG(HDLCD_REG_FB_LINE_COUNT, hdlcd->fb.var.yres - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_V_SYNC, hdlcd->fb.var.vsync_len - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_V_BACK_PORCH, hdlcd->fb.var.upper_margin - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_V_DATA, hdlcd->fb.var.yres - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_V_FRONT_PORCH, hdlcd->fb.var.lower_margin - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_H_SYNC, hdlcd->fb.var.hsync_len - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_H_BACK_PORCH, hdlcd->fb.var.left_margin - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_H_DATA, hdlcd->fb.var.xres - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_H_FRONT_PORCH, hdlcd->fb.var.right_margin - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_POLARITIES, polarities);
+	WRITE_HDLCD_REG(HDLCD_REG_PIXEL_FORMAT, (bytes_per_pixel - 1) << 3);
+#ifdef HDLCD_RED_DEFAULT_COLOUR
+	WRITE_HDLCD_REG(HDLCD_REG_RED_SELECT, (0x00ff0000 | (hdlcd->fb.var.red.length & 0xf) << 8) \
+													  | hdlcd->fb.var.red.offset);
+#else
+	WRITE_HDLCD_REG(HDLCD_REG_RED_SELECT, ((hdlcd->fb.var.red.length & 0xf) << 8) | hdlcd->fb.var.red.offset);
+#endif
+	WRITE_HDLCD_REG(HDLCD_REG_GREEN_SELECT, ((hdlcd->fb.var.green.length & 0xf) << 8) | hdlcd->fb.var.green.offset);
+	WRITE_HDLCD_REG(HDLCD_REG_BLUE_SELECT, ((hdlcd->fb.var.blue.length & 0xf) << 8) | hdlcd->fb.var.blue.offset);
+
+	clk_set_rate(hdlcd->clk, (1000000000 / hdlcd->fb.var.pixclock) * 1000);
+	clk_enable(hdlcd->clk);
+
+	hdlcd_enable(hdlcd);
+
+	return 0;
+}
+
+static int hdlcd_setcolreg(unsigned int regno, unsigned int red, unsigned int green,
+		unsigned int blue, unsigned int transp, struct fb_info *info)
+{
+	if (regno < 16) {
+		u32 *pal = info->pseudo_palette;
+
+		pal[regno] = ((red >> 8) << info->var.red.offset) |
+			((green >> 8) << info->var.green.offset) |
+			((blue >> 8) << info->var.blue.offset);
+	}
+
+	return 0;
+}
+
+static irqreturn_t hdlcd_irq(int irq, void *data)
+{
+	struct hdlcd_device *hdlcd = data;
+	unsigned long irq_mask, irq_status;
+
+	irq_mask = READ_HDLCD_REG(HDLCD_REG_INT_MASK);
+	irq_status = READ_HDLCD_REG(HDLCD_REG_INT_STATUS);
+
+	/* acknowledge interrupt(s) */
+	WRITE_HDLCD_REG(HDLCD_REG_INT_CLEAR, irq_status);
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+	if (irq_status & HDLCD_INTERRUPT_UNDERRUN) {
+		/* increment the count */
+		hdlcd_underrun_set(hdlcd_underrun_get() + 1);
+	}
+#endif
+	if (irq_status & HDLCD_INTERRUPT_VSYNC) {
+		/* disable future VSYNC interrupts */
+		WRITE_HDLCD_REG(HDLCD_REG_INT_MASK, irq_mask & ~HDLCD_INTERRUPT_VSYNC);
+
+		complete(&hdlcd->vsync_completion);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int hdlcd_wait_for_vsync(struct fb_info *info)
+{
+	struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+	unsigned long irq_mask;
+	int err;
+
+	/* enable VSYNC interrupt */
+	irq_mask = READ_HDLCD_REG(HDLCD_REG_INT_MASK);
+	WRITE_HDLCD_REG(HDLCD_REG_INT_MASK, irq_mask | HDLCD_INTERRUPT_VSYNC);
+
+	err = wait_for_completion_interruptible_timeout(&hdlcd->vsync_completion,
+							msecs_to_jiffies(100));
+
+	if (!err)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int hdlcd_blank(int blank_mode, struct fb_info *info)
+{
+	struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+
+	switch (blank_mode) {
+	case FB_BLANK_POWERDOWN:
+		clk_disable(hdlcd->clk);
+	case FB_BLANK_NORMAL:
+		hdlcd_disable(hdlcd);
+		break;
+	case FB_BLANK_UNBLANK:
+		clk_enable(hdlcd->clk);
+		hdlcd_enable(hdlcd);
+		break;
+	case FB_BLANK_VSYNC_SUSPEND:
+	case FB_BLANK_HSYNC_SUSPEND:
+	default:
+		return 1;
+	}
+
+	return 0;
+}
+
+static void hdlcd_mmap_open(struct vm_area_struct *vma)
+{
+}
+
+static void hdlcd_mmap_close(struct vm_area_struct *vma)
+{
+}
+
+static struct vm_operations_struct hdlcd_mmap_ops = {
+	.open	= hdlcd_mmap_open,
+	.close	= hdlcd_mmap_close,
+};
+
+static int hdlcd_mmap(struct fb_info *info, struct vm_area_struct *vma)
+{
+	struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+	unsigned long off;
+	unsigned long start;
+	unsigned long len = hdlcd->fb.fix.smem_len;
+
+	if (vma->vm_end - vma->vm_start == 0)
+		return 0;
+	if (vma->vm_pgoff > (~0UL >> PAGE_SHIFT))
+		return -EINVAL;
+
+	off = vma->vm_pgoff << PAGE_SHIFT;
+	if ((off >= len) || (vma->vm_end - vma->vm_start + off) > len)
+		return -EINVAL;
+
+	start = hdlcd->fb.fix.smem_start;
+	off += start;
+
+	vma->vm_pgoff = off >> PAGE_SHIFT;
+	vma->vm_flags |= VM_IO;
+	vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+	vma->vm_ops = &hdlcd_mmap_ops;
+	if (io_remap_pfn_range(vma, vma->vm_start, off >> PAGE_SHIFT,
+				vma->vm_end - vma->vm_start,
+				vma->vm_page_prot))
+		return -EAGAIN;
+
+	return 0;
+}
+
+static int hdlcd_pan_display(struct fb_var_screeninfo *var, struct fb_info *info)
+{
+	struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+
+	hdlcd->fb.var.yoffset = var->yoffset;
+	WRITE_HDLCD_REG(HDLCD_REG_FB_BASE, hdlcd->fb.fix.smem_start +
+			(var->yoffset * hdlcd->fb.fix.line_length));
+
+	hdlcd_wait_for_vsync(info);
+
+	return 0;
+}
+
+static int hdlcd_ioctl(struct fb_info *info, unsigned int cmd, unsigned long arg)
+{
+	int err;
+
+	switch (cmd) {
+	case FBIO_WAITFORVSYNC:
+		err = hdlcd_wait_for_vsync(info);
+		break;
+	default:
+		err = -ENOIOCTLCMD;
+		break;
+	}
+
+	return err;
+}
+
+static struct fb_ops hdlcd_ops = {
+	.owner			= THIS_MODULE,
+	.fb_check_var		= hdlcd_check_var,
+	.fb_set_par		= hdlcd_set_par,
+	.fb_setcolreg		= hdlcd_setcolreg,
+	.fb_blank		= hdlcd_blank,
+	.fb_fillrect		= cfb_fillrect,
+	.fb_copyarea		= cfb_copyarea,
+	.fb_imageblit		= cfb_imageblit,
+	.fb_mmap		= hdlcd_mmap,
+	.fb_pan_display		= hdlcd_pan_display,
+	.fb_ioctl		= hdlcd_ioctl,
+	.fb_compat_ioctl	= hdlcd_ioctl
+};
+
+static int hdlcd_setup(struct hdlcd_device *hdlcd)
+{
+	u32 version;
+	int err = -EFAULT;
+
+	hdlcd->fb.device = hdlcd->dev;
+
+	hdlcd->clk = clk_get(hdlcd->dev, NULL);
+	if (IS_ERR(hdlcd->clk)) {
+		dev_err(hdlcd->dev, "HDLCD: unable to find clock data\n");
+		return PTR_ERR(hdlcd->clk);
+	}
+
+	err = clk_prepare(hdlcd->clk);
+	if (err)
+		goto clk_prepare_err;
+
+	hdlcd->base = ioremap_nocache(hdlcd->fb.fix.mmio_start, hdlcd->fb.fix.mmio_len);
+	if (!hdlcd->base) {
+		dev_err(hdlcd->dev, "HDLCD: unable to map registers\n");
+		goto remap_err;
+	}
+
+	hdlcd->fb.pseudo_palette = kmalloc(sizeof(u32) * 16, GFP_KERNEL);
+	if (!hdlcd->fb.pseudo_palette) {
+		dev_err(hdlcd->dev, "HDLCD: unable to allocate pseudo_palette memory\n");
+		err = -ENOMEM;
+		goto kmalloc_err;
+	}
+
+	version = readl(hdlcd->base + HDLCD_REG_VERSION);
+	if ((version & HDLCD_PRODUCT_MASK) != HDLCD_PRODUCT_ID) {
+		dev_err(hdlcd->dev, "HDLCD: unknown product id: 0x%x\n", version);
+		err = -EINVAL;
+		goto kmalloc_err;
+	}
+	dev_info(hdlcd->dev, "HDLCD: found ARM HDLCD version r%dp%d\n",
+		(version & HDLCD_VERSION_MAJOR_MASK) >> 8,
+		version & HDLCD_VERSION_MINOR_MASK);
+
+	strcpy(hdlcd->fb.fix.id, "hdlcd");
+	hdlcd->fb.fbops			= &hdlcd_ops;
+	hdlcd->fb.flags			= FBINFO_FLAG_DEFAULT/* | FBINFO_VIRTFB*/;
+
+	hdlcd->fb.fix.type		= FB_TYPE_PACKED_PIXELS;
+	hdlcd->fb.fix.type_aux		= 0;
+	hdlcd->fb.fix.xpanstep		= 0;
+	hdlcd->fb.fix.ypanstep		= 1;
+	hdlcd->fb.fix.ywrapstep		= 0;
+	hdlcd->fb.fix.accel		= FB_ACCEL_NONE;
+
+	hdlcd->fb.var.nonstd		= 0;
+	hdlcd->fb.var.activate		= FB_ACTIVATE_NOW;
+	hdlcd->fb.var.height		= -1;
+	hdlcd->fb.var.width		= -1;
+	hdlcd->fb.var.accel_flags	= 0;
+
+	init_completion(&hdlcd->vsync_completion);
+
+	if (hdlcd->edid) {
+		/* build modedb from EDID */
+		fb_edid_to_monspecs(hdlcd->edid, &hdlcd->fb.monspecs);
+		fb_videomode_to_modelist(hdlcd->fb.monspecs.modedb,
+					hdlcd->fb.monspecs.modedb_len,
+					&hdlcd->fb.modelist);
+		fb_find_mode(&hdlcd->fb.var, &hdlcd->fb, fb_mode,
+			hdlcd->fb.monspecs.modedb,
+			hdlcd->fb.monspecs.modedb_len,
+			&hdlcd_default_mode, 32);
+	} else {
+		hdlcd->fb.monspecs.hfmin	= 0;
+		hdlcd->fb.monspecs.hfmax	= 100000;
+		hdlcd->fb.monspecs.vfmin	= 0;
+		hdlcd->fb.monspecs.vfmax	= 400;
+		hdlcd->fb.monspecs.dclkmin	= 1000000;
+		hdlcd->fb.monspecs.dclkmax	= 100000000;
+		fb_find_mode(&hdlcd->fb.var, &hdlcd->fb, fb_mode, NULL, 0, &hdlcd_default_mode, 32);
+	}
+
+	dev_info(hdlcd->dev, "using %dx%d-%d@%d mode\n", hdlcd->fb.var.xres,
+		hdlcd->fb.var.yres, hdlcd->fb.var.bits_per_pixel,
+		hdlcd->fb.mode ? hdlcd->fb.mode->refresh : 60);
+	hdlcd->fb.var.xres_virtual	= hdlcd->fb.var.xres;
+#ifdef HDLCD_NO_VIRTUAL_SCREEN
+	hdlcd->fb.var.yres_virtual	= hdlcd->fb.var.yres;
+#else
+	hdlcd->fb.var.yres_virtual	= hdlcd->fb.var.yres * 2;
+#endif
+
+	/* initialise and set the palette */
+	if (fb_alloc_cmap(&hdlcd->fb.cmap, NR_PALETTE, 0)) {
+		dev_err(hdlcd->dev, "failed to allocate cmap memory\n");
+		err = -ENOMEM;
+		goto setup_err;
+	}
+	fb_set_cmap(&hdlcd->fb.cmap, &hdlcd->fb);
+
+	/* Allow max number of outstanding requests with the largest beat burst */
+	WRITE_HDLCD_REG(HDLCD_REG_BUS_OPTIONS, HDLCD_BUS_MAX_OUTSTAND | HDLCD_BUS_BURST_16);
+	/* Set the framebuffer base to start of allocated memory */
+	WRITE_HDLCD_REG(HDLCD_REG_FB_BASE, hdlcd->fb.fix.smem_start);
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+	/* turn on underrun interrupt for counting */
+	WRITE_HDLCD_REG(HDLCD_REG_INT_MASK, HDLCD_INTERRUPT_UNDERRUN);
+#else
+	/* Ensure interrupts are disabled */
+	WRITE_HDLCD_REG(HDLCD_REG_INT_MASK, 0);
+#endif	
+	fb_set_var(&hdlcd->fb, &hdlcd->fb.var);
+
+	if (!register_framebuffer(&hdlcd->fb)) {
+		return 0;
+	}
+
+	dev_err(hdlcd->dev, "HDLCD: cannot register framebuffer\n");
+
+	fb_dealloc_cmap(&hdlcd->fb.cmap);
+setup_err:
+	iounmap(hdlcd->base);
+kmalloc_err:
+	kfree(hdlcd->fb.pseudo_palette);
+remap_err:
+	clk_unprepare(hdlcd->clk);
+clk_prepare_err:
+	clk_put(hdlcd->clk);
+	return err;
+}
+
+static inline unsigned char atohex(u8 data)
+{
+	if (!isxdigit(data))
+		return 0;
+	/* truncate the upper nibble and add 9 to non-digit values */
+	return (data > 0x39) ? ((data & 0xf) + 9) : (data & 0xf);
+}
+
+/* EDID data is passed from devicetree in a literal string that can contain spaces and
+   the hexadecimal dump of the data */
+static int parse_edid_data(struct hdlcd_device *hdlcd, const u8 *edid_data, int data_len)
+{
+	int i, j;
+
+	if (!edid_data)
+		return -EINVAL;
+
+	hdlcd->edid = kzalloc(EDID_LENGTH, GFP_KERNEL);
+	if (!hdlcd->edid)
+		return -ENOMEM;
+
+	for (i = 0, j = 0; i < data_len; i++) {
+		if (isspace(edid_data[i]))
+			continue;
+		hdlcd->edid[j++] = atohex(edid_data[i]);
+		if (j >= EDID_LENGTH)
+			break;
+	}
+
+	if (j < EDID_LENGTH) {
+		kfree(hdlcd->edid);
+		hdlcd->edid = NULL;
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int hdlcd_probe(struct platform_device *pdev)
+{
+	int err = 0, i;
+	struct hdlcd_device *hdlcd;
+	struct resource *mem;
+#ifdef CONFIG_OF
+	struct device_node *of_node;
+#endif
+
+	memset(&cached_var_screeninfo, 0, sizeof(struct fb_var_screeninfo));
+
+	dev_dbg(&pdev->dev, "HDLCD: probing\n");
+
+	hdlcd = kzalloc(sizeof(*hdlcd), GFP_KERNEL);
+	if (!hdlcd)
+		return -ENOMEM;
+
+#ifdef CONFIG_OF
+	of_node = pdev->dev.of_node;
+	if (of_node) {
+		int len;
+		const u8 *edid;
+		const __be32 *prop = of_get_property(of_node, "mode", &len);
+		if (prop)
+			strncpy(fb_mode, (char *)prop, len);
+		prop = of_get_property(of_node, "framebuffer", &len);
+		if (prop) {
+			hdlcd->fb.fix.smem_start = of_read_ulong(prop,
+					of_n_addr_cells(of_node));
+			prop += of_n_addr_cells(of_node);
+			framebuffer_size = of_read_ulong(prop,
+					of_n_size_cells(of_node));
+			if (framebuffer_size > HDLCD_MAX_FRAMEBUFFER_SIZE)
+				framebuffer_size = HDLCD_MAX_FRAMEBUFFER_SIZE;
+			dev_dbg(&pdev->dev, "HDLCD: phys_addr = 0x%lx, size = 0x%lx\n",
+				hdlcd->fb.fix.smem_start, framebuffer_size);
+		}
+		edid = of_get_property(of_node, "edid", &len);
+		if (edid) {
+			err = parse_edid_data(hdlcd, edid, len);
+#ifdef CONFIG_SERIAL_AMBA_PCU_UART
+		} else {
+			/* ask the firmware to fetch the EDID */
+			dev_dbg(&pdev->dev, "HDLCD: Requesting EDID data\n");
+			hdlcd->edid = kzalloc(EDID_LENGTH, GFP_KERNEL);
+			if (!hdlcd->edid)
+				return -ENOMEM;
+			err = get_edid(hdlcd->edid);
+#endif /* CONFIG_SERIAL_AMBA_PCU_UART */
+		}
+		if (err)
+			dev_info(&pdev->dev, "HDLCD: Failed to parse EDID data\n");
+	}
+#endif /* CONFIG_OF */
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!mem) {
+		dev_err(&pdev->dev, "HDLCD: cannot get platform resources\n");
+		err = -EINVAL;
+		goto resource_err;
+	}
+
+	i = platform_get_irq(pdev, 0);
+	if (i < 0) {
+		dev_err(&pdev->dev, "HDLCD: no irq defined for vsync\n");
+		err = -ENOENT;
+		goto resource_err;
+	} else {
+		err = request_irq(i, hdlcd_irq, 0, dev_name(&pdev->dev), hdlcd);
+		if (err) {
+			dev_err(&pdev->dev, "HDLCD: unable to request irq\n");
+			goto resource_err;
+		}
+		hdlcd->irq = i;
+	}
+
+	if (!request_mem_region(mem->start, resource_size(mem),	dev_name(&pdev->dev))) {
+		err = -ENXIO;
+		goto request_err;
+	}
+
+	if (!hdlcd->fb.fix.smem_start) {
+		dev_err(&pdev->dev, "platform did not allocate frame buffer memory\n");
+		err = -ENOMEM;
+		goto memalloc_err;
+	}
+	hdlcd->fb.screen_base = ioremap_wc(hdlcd->fb.fix.smem_start, framebuffer_size);
+	if (!hdlcd->fb.screen_base) {
+		dev_err(&pdev->dev, "unable to ioremap framebuffer\n");
+		err = -ENOMEM;
+		goto probe_err;
+	}
+
+	hdlcd->fb.screen_size = framebuffer_size;
+	hdlcd->fb.fix.smem_len = framebuffer_size;
+	hdlcd->fb.fix.mmio_start = mem->start;
+	hdlcd->fb.fix.mmio_len = resource_size(mem);
+
+	/* Clear the framebuffer */
+	memset(hdlcd->fb.screen_base, 0, framebuffer_size);
+
+	hdlcd->dev = &pdev->dev;
+
+	dev_dbg(&pdev->dev, "HDLCD: framebuffer virt base %p, phys base 0x%lX\n",
+		hdlcd->fb.screen_base, (unsigned long)hdlcd->fb.fix.smem_start);
+
+	err = hdlcd_setup(hdlcd);
+
+	if (err)
+		goto probe_err;
+
+	platform_set_drvdata(pdev, hdlcd);
+	return 0;
+
+probe_err:
+	iounmap(hdlcd->fb.screen_base);
+	memblock_free(hdlcd->fb.fix.smem_start, hdlcd->fb.fix.smem_start);
+
+memalloc_err:
+	release_mem_region(mem->start, resource_size(mem));
+
+request_err:
+	free_irq(hdlcd->irq, hdlcd);
+
+resource_err:
+	kfree(hdlcd);
+
+	return err;
+}
+
+static int hdlcd_remove(struct platform_device *pdev)
+{
+	struct hdlcd_device *hdlcd = platform_get_drvdata(pdev);
+
+	clk_disable(hdlcd->clk);
+	clk_unprepare(hdlcd->clk);
+	clk_put(hdlcd->clk);
+
+	/* unmap memory */
+	iounmap(hdlcd->fb.screen_base);
+	iounmap(hdlcd->base);
+
+	/* deallocate fb memory */
+	fb_dealloc_cmap(&hdlcd->fb.cmap);
+	kfree(hdlcd->fb.pseudo_palette);
+	memblock_free(hdlcd->fb.fix.smem_start, hdlcd->fb.fix.smem_start);
+	release_mem_region(hdlcd->fb.fix.mmio_start, hdlcd->fb.fix.mmio_len);
+
+	free_irq(hdlcd->irq, NULL);
+	kfree(hdlcd);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int hdlcd_suspend(struct platform_device *pdev, pm_message_t state)
+{
+	/* not implemented yet */
+	return 0;
+}
+
+static int hdlcd_resume(struct platform_device *pdev)
+{
+	/* not implemented yet */
+	return 0;
+}
+#else
+#define hdlcd_suspend	NULL
+#define hdlcd_resume	NULL
+#endif
+
+static struct platform_driver hdlcd_driver = {
+	.probe		= hdlcd_probe,
+	.remove		= hdlcd_remove,
+	.suspend	= hdlcd_suspend,
+	.resume		= hdlcd_resume,
+	.driver	= {
+		.name		= "hdlcd",
+		.owner		= THIS_MODULE,
+		.of_match_table	= hdlcd_of_matches,
+	},
+};
+
+static int __init hdlcd_init(void)
+{
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+	int err = platform_driver_register(&hdlcd_driver);
+	if (!err)
+		hdlcd_underrun_init();
+	return err;
+#else
+	return platform_driver_register(&hdlcd_driver);
+#endif
+}
+
+void __exit hdlcd_exit(void)
+{
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+	hdlcd_underrun_close();
+#endif
+	platform_driver_unregister(&hdlcd_driver);
+}
+
+module_init(hdlcd_init);
+module_exit(hdlcd_exit);
+
+MODULE_AUTHOR("Liviu Dudau");
+MODULE_DESCRIPTION("ARM HDLCD core driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/video/vexpress-dvi.c b/drivers/video/vexpress-dvi.c
new file mode 100644
index 000000000000..f08753450ee4
--- /dev/null
+++ b/drivers/video/vexpress-dvi.c
@@ -0,0 +1,220 @@
+/*
+ * 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.
+ *
+ * Copyright (C) 2012 ARM Limited
+ */
+
+#define pr_fmt(fmt) "vexpress-dvi: " fmt
+
+#include <linux/fb.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/vexpress.h>
+
+
+static struct vexpress_config_func *vexpress_dvimode_func;
+
+static struct {
+	u32 xres, yres, mode;
+} vexpress_dvi_dvimodes[] = {
+	{ 640, 480, 0 }, /* VGA */
+	{ 800, 600, 1 }, /* SVGA */
+	{ 1024, 768, 2 }, /* XGA */
+	{ 1280, 1024, 3 }, /* SXGA */
+	{ 1600, 1200, 4 }, /* UXGA */
+	{ 1920, 1080, 5 }, /* HD1080 */
+};
+
+static void vexpress_dvi_mode_set(struct fb_info *info, u32 xres, u32 yres)
+{
+	int err = -ENOENT;
+	int i;
+
+	if (!vexpress_dvimode_func)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(vexpress_dvi_dvimodes); i++) {
+		if (vexpress_dvi_dvimodes[i].xres == xres &&
+				vexpress_dvi_dvimodes[i].yres == yres) {
+			pr_debug("mode: %ux%u = %d\n", xres, yres,
+					vexpress_dvi_dvimodes[i].mode);
+			err = vexpress_config_write(vexpress_dvimode_func, 0,
+					vexpress_dvi_dvimodes[i].mode);
+			break;
+		}
+	}
+
+	if (err)
+		pr_warn("Failed to set %ux%u mode! (%d)\n", xres, yres, err);
+}
+
+
+static struct vexpress_config_func *vexpress_muxfpga_func;
+static int vexpress_dvi_fb = -1;
+
+static int vexpress_dvi_mux_set(struct fb_info *info)
+{
+	int err;
+	u32 site = vexpress_get_site_by_dev(info->device);
+
+	if (!vexpress_muxfpga_func)
+		return -ENXIO;
+
+	err = vexpress_config_write(vexpress_muxfpga_func, 0, site);
+	if (!err) {
+		pr_debug("Selected MUXFPGA input %d (fb%d)\n", site,
+				info->node);
+		vexpress_dvi_fb = info->node;
+		vexpress_dvi_mode_set(info, info->var.xres,
+				info->var.yres);
+	} else {
+		pr_warn("Failed to select MUXFPGA input %d (fb%d)! (%d)\n",
+				site, info->node, err);
+	}
+
+	return err;
+}
+
+static int vexpress_dvi_fb_select(int fb)
+{
+	int err;
+	struct fb_info *info;
+
+	/* fb0 is the default */
+	if (fb < 0)
+		fb = 0;
+
+	info = registered_fb[fb];
+	if (!info || !lock_fb_info(info))
+		return -ENODEV;
+
+	err = vexpress_dvi_mux_set(info);
+
+	unlock_fb_info(info);
+
+	return err;
+}
+
+static ssize_t vexpress_dvi_fb_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", vexpress_dvi_fb);
+}
+
+static ssize_t vexpress_dvi_fb_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	long value;
+	int err = kstrtol(buf, 0, &value);
+
+	if (!err)
+		err = vexpress_dvi_fb_select(value);
+
+	return err ? err : count;
+}
+
+DEVICE_ATTR(fb, S_IRUGO | S_IWUSR, vexpress_dvi_fb_show,
+		vexpress_dvi_fb_store);
+
+
+static int vexpress_dvi_fb_event_notify(struct notifier_block *self,
+			      unsigned long action, void *data)
+{
+	struct fb_event *event = data;
+	struct fb_info *info = event->info;
+	struct fb_videomode *mode = event->data;
+
+	switch (action) {
+	case FB_EVENT_FB_REGISTERED:
+		if (vexpress_dvi_fb < 0)
+			vexpress_dvi_mux_set(info);
+		break;
+	case FB_EVENT_MODE_CHANGE:
+	case FB_EVENT_MODE_CHANGE_ALL:
+		if (info->node == vexpress_dvi_fb)
+			vexpress_dvi_mode_set(info, mode->xres, mode->yres);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block vexpress_dvi_fb_notifier = {
+	.notifier_call = vexpress_dvi_fb_event_notify,
+};
+static bool vexpress_dvi_fb_notifier_registered;
+
+
+enum vexpress_dvi_func { FUNC_MUXFPGA, FUNC_DVIMODE };
+
+static struct of_device_id vexpress_dvi_of_match[] = {
+	{
+		.compatible = "arm,vexpress-muxfpga",
+		.data = (void *)FUNC_MUXFPGA,
+	}, {
+		.compatible = "arm,vexpress-dvimode",
+		.data = (void *)FUNC_DVIMODE,
+	},
+	{}
+};
+
+static int vexpress_dvi_probe(struct platform_device *pdev)
+{
+	enum vexpress_dvi_func func;
+	const struct of_device_id *match =
+			of_match_device(vexpress_dvi_of_match, &pdev->dev);
+
+	if (match)
+		func = (enum vexpress_dvi_func)match->data;
+	else
+		func = pdev->id_entry->driver_data;
+
+	switch (func) {
+	case FUNC_MUXFPGA:
+		vexpress_muxfpga_func =
+				vexpress_config_func_get_by_dev(&pdev->dev);
+		device_create_file(&pdev->dev, &dev_attr_fb);
+		break;
+	case FUNC_DVIMODE:
+		vexpress_dvimode_func =
+				vexpress_config_func_get_by_dev(&pdev->dev);
+		break;
+	}
+
+	if (!vexpress_dvi_fb_notifier_registered) {
+		fb_register_client(&vexpress_dvi_fb_notifier);
+		vexpress_dvi_fb_notifier_registered = true;
+	}
+
+	vexpress_dvi_fb_select(vexpress_dvi_fb);
+
+	return 0;
+}
+
+static const struct platform_device_id vexpress_dvi_id_table[] = {
+	{ .name = "vexpress-muxfpga", .driver_data = FUNC_MUXFPGA, },
+	{ .name = "vexpress-dvimode", .driver_data = FUNC_DVIMODE, },
+	{}
+};
+
+static struct platform_driver vexpress_dvi_driver = {
+	.probe = vexpress_dvi_probe,
+	.driver = {
+		.name = "vexpress-dvi",
+		.of_match_table = vexpress_dvi_of_match,
+	},
+	.id_table = vexpress_dvi_id_table,
+};
+
+static int __init vexpress_dvi_init(void)
+{
+	return platform_driver_register(&vexpress_dvi_driver);
+}
+device_initcall(vexpress_dvi_init);
diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index a66768ebc8d1..3def5122904a 100644
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -1,5 +1,6 @@
 config BTRFS_FS
 	tristate "Btrfs filesystem support"
+	select LIBCRC32C
 	select CRYPTO
 	select CRYPTO_CRC32C
 	select ZLIB_INFLATE
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index e73c19e90e38..016c2f110f63 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -100,9 +100,12 @@ struct blkcipher_walk {
 	void *page;
 	u8 *buffer;
 	u8 *iv;
+	unsigned int ivsize;
 
 	int flags;
-	unsigned int blocksize;
+	unsigned int walk_blocksize;
+	unsigned int cipher_blocksize;
+	unsigned int alignmask;
 };
 
 struct ablkcipher_walk {
@@ -192,6 +195,10 @@ int blkcipher_walk_phys(struct blkcipher_desc *desc,
 int blkcipher_walk_virt_block(struct blkcipher_desc *desc,
 			      struct blkcipher_walk *walk,
 			      unsigned int blocksize);
+int blkcipher_aead_walk_virt_block(struct blkcipher_desc *desc,
+				   struct blkcipher_walk *walk,
+				   struct crypto_aead *tfm,
+				   unsigned int blocksize);
 
 int ablkcipher_walk_done(struct ablkcipher_request *req,
 			 struct ablkcipher_walk *walk, int err);
diff --git a/include/linux/amba/clcd.h b/include/linux/amba/clcd.h
index e82e3ee2c54a..4a53250f970e 100644
--- a/include/linux/amba/clcd.h
+++ b/include/linux/amba/clcd.h
@@ -243,6 +243,9 @@ static inline void clcdfb_decode(struct clcd_fb *fb, struct clcd_regs *regs)
 			val |= CNTL_BGR;
 	}
 
+	/* Reset the current colour depth */
+	val &= ~CNTL_LCDBPP16_444;
+
 	switch (var->bits_per_pixel) {
 	case 1:
 		val |= CNTL_LCDBPP1;
@@ -264,14 +267,15 @@ static inline void clcdfb_decode(struct clcd_fb *fb, struct clcd_regs *regs)
 		 */
 		if (amba_part(fb->dev) == 0x110 ||
 		    var->green.length == 5)
-			val |= CNTL_LCDBPP16;
+			val |= CNTL_LCDBPP16 | CNTL_BGR;
 		else if (var->green.length == 6)
-			val |= CNTL_LCDBPP16_565;
+			val |= CNTL_LCDBPP16_565 | CNTL_BGR;
 		else
-			val |= CNTL_LCDBPP16_444;
+			val |= CNTL_LCDBPP16_444 | CNTL_BGR;
 		break;
 	case 32:
 		val |= CNTL_LCDBPP24;
+		val &= ~CNTL_BGR;
 		break;
 	}
 
diff --git a/include/linux/arm-hdlcd.h b/include/linux/arm-hdlcd.h
new file mode 100644
index 000000000000..939f3a81d56b
--- /dev/null
+++ b/include/linux/arm-hdlcd.h
@@ -0,0 +1,122 @@
+/*
+ * include/linux/arm-hdlcd.h
+ *
+ * Copyright (C) 2011 ARM Limited
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive
+ * for more details.
+ *
+ *  ARM HDLCD Controller register definition
+ */
+
+#include <linux/fb.h>
+#include <linux/completion.h>
+
+/* register offsets */
+#define HDLCD_REG_VERSION		0x0000	/* ro */
+#define HDLCD_REG_INT_RAWSTAT		0x0010	/* rw */
+#define HDLCD_REG_INT_CLEAR		0x0014	/* wo */
+#define HDLCD_REG_INT_MASK		0x0018	/* rw */
+#define HDLCD_REG_INT_STATUS		0x001c	/* ro */
+#define HDLCD_REG_USER_OUT		0x0020	/* rw */
+#define HDLCD_REG_FB_BASE		0x0100	/* rw */
+#define HDLCD_REG_FB_LINE_LENGTH	0x0104	/* rw */
+#define HDLCD_REG_FB_LINE_COUNT		0x0108	/* rw */
+#define HDLCD_REG_FB_LINE_PITCH		0x010c	/* rw */
+#define HDLCD_REG_BUS_OPTIONS		0x0110	/* rw */
+#define HDLCD_REG_V_SYNC		0x0200	/* rw */
+#define HDLCD_REG_V_BACK_PORCH		0x0204	/* rw */
+#define HDLCD_REG_V_DATA		0x0208	/* rw */
+#define HDLCD_REG_V_FRONT_PORCH		0x020c	/* rw */
+#define HDLCD_REG_H_SYNC		0x0210	/* rw */
+#define HDLCD_REG_H_BACK_PORCH		0x0214	/* rw */
+#define HDLCD_REG_H_DATA		0x0218	/* rw */
+#define HDLCD_REG_H_FRONT_PORCH		0x021c	/* rw */
+#define HDLCD_REG_POLARITIES		0x0220	/* rw */
+#define HDLCD_REG_COMMAND		0x0230	/* rw */
+#define HDLCD_REG_PIXEL_FORMAT		0x0240	/* rw */
+#define HDLCD_REG_BLUE_SELECT		0x0244	/* rw */
+#define HDLCD_REG_GREEN_SELECT		0x0248	/* rw */
+#define HDLCD_REG_RED_SELECT		0x024c	/* rw */
+
+/* version */
+#define HDLCD_PRODUCT_ID		0x1CDC0000
+#define HDLCD_PRODUCT_MASK		0xFFFF0000
+#define HDLCD_VERSION_MAJOR_MASK	0x0000FF00
+#define HDLCD_VERSION_MINOR_MASK	0x000000FF
+
+/* interrupts */
+#define HDLCD_INTERRUPT_DMA_END		(1 << 0)
+#define HDLCD_INTERRUPT_BUS_ERROR	(1 << 1)
+#define HDLCD_INTERRUPT_VSYNC		(1 << 2)
+#define HDLCD_INTERRUPT_UNDERRUN	(1 << 3)
+
+/* polarity */
+#define HDLCD_POLARITY_VSYNC		(1 << 0)
+#define HDLCD_POLARITY_HSYNC		(1 << 1)
+#define HDLCD_POLARITY_DATAEN		(1 << 2)
+#define HDLCD_POLARITY_DATA		(1 << 3)
+#define HDLCD_POLARITY_PIXELCLK		(1 << 4)
+
+/* commands */
+#define HDLCD_COMMAND_DISABLE		(0 << 0)
+#define HDLCD_COMMAND_ENABLE		(1 << 0)
+
+/* pixel format */
+#define HDLCD_PIXEL_FMT_LITTLE_ENDIAN	(0 << 31)
+#define HDLCD_PIXEL_FMT_BIG_ENDIAN	(1 << 31)
+#define HDLCD_BYTES_PER_PIXEL_MASK	(3 << 3)
+
+/* bus options */
+#define HDLCD_BUS_BURST_MASK		0x01f
+#define HDLCD_BUS_MAX_OUTSTAND		0xf00
+#define HDLCD_BUS_BURST_NONE		(0 << 0)
+#define HDLCD_BUS_BURST_1		(1 << 0)
+#define HDLCD_BUS_BURST_2		(1 << 1)
+#define HDLCD_BUS_BURST_4		(1 << 2)
+#define HDLCD_BUS_BURST_8		(1 << 3)
+#define HDLCD_BUS_BURST_16		(1 << 4)
+
+/* Max resolution supported is 4096x4096, 8 bit per color component,
+   8 bit alpha, but we are going to choose the usual hardware default
+   (2048x2048, 32 bpp) and enable double buffering */
+#define HDLCD_MAX_XRES			2048
+#define HDLCD_MAX_YRES			2048
+#define HDLCD_MAX_FRAMEBUFFER_SIZE	(HDLCD_MAX_XRES * HDLCD_MAX_YRES << 2)
+
+#define HDLCD_MEM_BASE			(CONFIG_PAGE_OFFSET - 0x1000000)
+
+#define NR_PALETTE	256
+
+/* OEMs using HDLCD may wish to enable these settings if
+ * display disruption is apparent and you suspect HDLCD
+ * access to RAM may be starved.
+ */
+/* Turn HDLCD default color red instead of black so
+ * that it's easy to see pixel clock data underruns
+ * (compared to other visual disruption)
+ */
+//#define HDLCD_RED_DEFAULT_COLOUR
+/* Add a counter in the IRQ handler to count buffer underruns
+ * and /proc/hdlcd_underrun to read the counter
+ */
+//#define HDLCD_COUNT_BUFFERUNDERRUNS
+/* Restrict height to 1x screen size
+ *
+ */
+//#define HDLCD_NO_VIRTUAL_SCREEN
+
+#ifdef CONFIG_ANDROID
+#define HDLCD_NO_VIRTUAL_SCREEN
+#endif
+
+struct hdlcd_device {
+	struct fb_info		fb;
+	struct device		*dev;
+	struct clk		*clk;
+	void __iomem		*base;
+	int			irq;
+	struct completion	vsync_completion;
+	unsigned char		*edid;
+};
diff --git a/linaro/configs/vexpress-tuning.conf b/linaro/configs/vexpress-tuning.conf
new file mode 100644
index 000000000000..adea6cc66ded
--- /dev/null
+++ b/linaro/configs/vexpress-tuning.conf
@@ -0,0 +1 @@
+# CONFIG_PROVE_LOCKING is not set
diff --git a/linaro/configs/vexpress.conf b/linaro/configs/vexpress.conf
new file mode 100644
index 000000000000..0f02f3abd96f
--- /dev/null
+++ b/linaro/configs/vexpress.conf
@@ -0,0 +1,64 @@
+CONFIG_ARCH_VEXPRESS=y
+CONFIG_ARCH_VEXPRESS_CA9X4=y
+CONFIG_HAVE_ARM_ARCH_TIMER=y
+CONFIG_NR_CPUS=8
+CONFIG_HIGHMEM=y
+CONFIG_HIGHPTE=y
+CONFIG_ARM_PSCI=y
+CONFIG_MCPM=y
+CONFIG_ARCH_VEXPRESS_DCSCB=y
+CONFIG_ARCH_VEXPRESS_TC2_PM=y
+CONFIG_ARM_BIG_LITTLE_CPUIDLE=y
+CONFIG_BIG_LITTLE=y
+CONFIG_ARM_VEXPRESS_SPC_CPUFREQ=y
+CONFIG_PM_OPP=y
+CONFIG_CPU_FREQ=y
+CONFIG_CPU_FREQ_GOV_ONDEMAND=y
+CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
+CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
+CONFIG_CMDLINE="console=ttyAMA0,38400n8 root=/dev/mmcblk0p2 rootwait mmci.fmax=4000000"
+CONFIG_VFP=y
+CONFIG_NEON=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_SMSC911X=y
+CONFIG_SMC91X=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_SERIO_AMBAKMI=y
+CONFIG_SERIAL_AMBA_PL011=y
+CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+CONFIG_FB=y
+CONFIG_FB_ARMCLCD=y
+CONFIG_FB_ARMHDLCD=y
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+CONFIG_SOUND=y
+CONFIG_SND=y
+CONFIG_SND_ARMAACI=y
+CONFIG_USB=y
+CONFIG_USB_ISP1760_HCD=y
+CONFIG_USB_STORAGE=y
+CONFIG_MMC=y
+CONFIG_MMC_ARMMMCI=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_PL031=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_ROOT_NFS=y
+CONFIG_VEXPRESS_CONFIG=y
+CONFIG_SENSORS_VEXPRESS=y
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_VEXPRESS=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_HEARTBEAT=y
+CONFIG_LEDS_TRIGGER_CPU=y
+CONFIG_VIRTIO=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y