Merge branch 'tracking-armlt-tc2' into integration-linaro-vexpress

13 files changed, 758 insertions, 84 deletions

diff --git a/Documentation/devicetree/bindings/arm/cpus.txt b/Documentation/devicetree/bindings/arm/cpus.txt
new file mode 100644
index 00000000000..f32494dbfe1
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/cpus.txt
@@ -0,0 +1,77 @@
+* ARM CPUs binding description
+
+The device tree allows to describe the layout of CPUs in a system through
+the "cpus" node, which in turn contains a number of subnodes (ie "cpu")
+defining properties for every cpu.
+
+Bindings for CPU nodes follow the ePAPR standard, available from:
+
+http://devicetree.org
+
+For the ARM architecture every CPU node must contain the following properties:
+
+- device_type:	must be "cpu"
+- reg:		property matching the CPU MPIDR[23:0] register bits
+		reg[31:24] bits must be set to 0
+- compatible:	should be one of:
+		"arm,arm1020"
+		"arm,arm1020e"
+		"arm,arm1022"
+		"arm,arm1026"
+		"arm,arm720"
+		"arm,arm740"
+		"arm,arm7tdmi"
+		"arm,arm920"
+		"arm,arm922"
+		"arm,arm925"
+		"arm,arm926"
+		"arm,arm940"
+		"arm,arm946"
+		"arm,arm9tdmi"
+		"arm,cortex-a5"
+		"arm,cortex-a7"
+		"arm,cortex-a8"
+		"arm,cortex-a9"
+		"arm,cortex-a15"
+		"arm,arm1136"
+		"arm,arm1156"
+		"arm,arm1176"
+		"arm,arm11mpcore"
+		"faraday,fa526"
+		"intel,sa110"
+		"intel,sa1100"
+		"marvell,feroceon"
+		"marvell,mohawk"
+		"marvell,xsc3"
+		"marvell,xscale"
+
+Example:
+
+	cpus {
+		#size-cells = <0>;
+		#address-cells = <1>;
+
+		CPU0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x0>;
+		};
+
+		CPU1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x1>;
+		};
+
+		CPU2: cpu@100 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x100>;
+		};
+
+		CPU3: cpu@101 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x101>;
+		};
+	};
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index 0d196de5aef..31403357f89 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -100,6 +100,7 @@ dtb-$(CONFIG_ARCH_VERSATILE) += versatile-ab.dtb \
 dtb-$(CONFIG_ARCH_VEXPRESS) += vexpress-v2p-ca5s.dtb \
 	vexpress-v2p-ca9.dtb \
 	vexpress-v2p-ca15-tc1.dtb \
+	vexpress-v2p-ca15-tc2.dtb \
 	vexpress-v2p-ca15_a7.dtb \
 	xenvm-4.2.dtb \
 	rtsm_ve-cortex_a9x2.dtb \
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15-tc2.dts b/arch/arm/boot/dts/vexpress-v2p-ca15-tc2.dts
new file mode 100644
index 00000000000..4609562de9b
--- /dev/null
+++ b/arch/arm/boot/dts/vexpress-v2p-ca15-tc2.dts
@@ -0,0 +1,464 @@
+/*
+ * ARM Ltd. Versatile Express
+ *
+ * CoreTile Express A15x2 A7x3
+ * Cortex-A15_A7 MPCore (V2P-CA15_A7)
+ *
+ * HBI-0249A
+ */
+
+/dts-v1/;
+
+/memreserve/ 0xff000000 0x01000000;
+
+/ {
+	model = "V2P-CA15_CA7";
+	arm,hbi = <0x249>;
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,vexpress,v2p-ca15,tc2", "arm,vexpress,v2p-ca15", "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;
+		i2c0 = &v2m_i2c_dvi;
+		i2c1 = &v2m_i2c_pcie;
+	};
+
+	clusters {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cluster0: cluster@0 {
+			reg = <0>;
+			cores {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				core0: core@0 {
+					reg = <0>;
+				};
+
+				core1: core@1 {
+					reg = <1>;
+				};
+
+			};
+		};
+
+		cluster1: cluster@1 {
+			reg = <1>;
+			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>;
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+			cluster = <&cluster0>;
+			core = <&core0>;
+			clock-frequency = <1000000000>;
+		};
+
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <1>;
+			cluster = <&cluster0>;
+			core = <&core1>;
+			clock-frequency = <1000000000>;
+		};
+
+		cpu2: cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x100>;
+			cluster = <&cluster1>;
+			core = <&core2>;
+			clock-frequency = <800000000>;
+		};
+
+		cpu3: cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x101>;
+			cluster = <&cluster1>;
+			core = <&core3>;
+			clock-frequency = <800000000>;
+		};
+
+		cpu4: cpu@4 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x102>;
+			cluster = <&cluster1>;
+			core = <&core4>;
+			clock-frequency = <800000000>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0 0x80000000 0 0x80000000>;
+	};
+
+	wdt@2a490000 {
+		compatible = "arm,sp805", "arm,primecell";
+		reg = <0 0x2a490000 0 0x1000>;
+		interrupts = <98>;
+		clocks = <&oscclk6a>, <&oscclk6a>;
+		clock-names = "wdogclk", "apb_pclk";
+	};
+
+	hdlcd@2b000000 {
+		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";
+	};
+
+	memory-controller@2b0a0000 {
+		compatible = "arm,pl341", "arm,primecell";
+		reg = <0 0x2b0a0000 0 0x1000>;
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+	};
+
+	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>;
+
+		gic-cpuif@0 {
+			compatible = "arm,gic-cpuif";
+			cpuif-id = <0>;
+			cpu = <&cpu0>;
+		};
+		gic-cpuif@1 {
+			compatible = "arm,gic-cpuif";
+			cpuif-id = <1>;
+			cpu = <&cpu1>;
+		};
+		gic-cpuif@2 {
+			compatible = "arm,gic-cpuif";
+			cpuif-id = <2>;
+			cpu = <&cpu2>;
+		};
+
+		gic-cpuif@3 {
+			compatible = "arm,gic-cpuif";
+			cpuif-id = <3>;
+			cpu = <&cpu3>;
+		};
+
+		gic-cpuif@4 {
+			compatible = "arm,gic-cpuif";
+			cpuif-id = <4>;
+			cpu = <&cpu4>;
+		};
+	};
+
+	memory-controller@7ffd0000 {
+		compatible = "arm,pl354", "arm,primecell";
+		reg = <0 0x7ffd0000 0 0x1000>;
+		interrupts = <0 86 4>,
+			     <0 87 4>;
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+	};
+
+	dma@7ff00000 {
+		compatible = "arm,pl330", "arm,primecell";
+		reg = <0 0x7ff00000 0 0x1000>;
+		interrupts = <0 92 4>,
+			     <0 88 4>,
+			     <0 89 4>,
+			     <0 90 4>,
+			     <0 91 4>;
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupts = <1 13 0xf08>,
+			     <1 14 0xf08>,
+			     <1 11 0xf08>,
+			     <1 10 0xf08>;
+	};
+
+	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";
+		#clock-cells = <0>;
+		clock-frequency = <24000000>;
+		clock-output-names = "oscclk6a";
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			/* A15 PLL 0 reference clock */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 0>;
+			freq-range = <17000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "oscclk0";
+		};
+
+		osc@1 {
+			/* A15 PLL 1 reference clock */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 1>;
+			freq-range = <17000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "oscclk1";
+		};
+
+		osc@2 {
+			/* A7 PLL 0 reference clock */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 2>;
+			freq-range = <17000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "oscclk2";
+		};
+
+		osc@3 {
+			/* A7 PLL 1 reference clock */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 3>;
+			freq-range = <17000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "oscclk3";
+		};
+
+		osc@4 {
+			/* External AXI master clock */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 4>;
+			freq-range = <20000000 40000000>;
+			#clock-cells = <0>;
+			clock-output-names = "oscclk4";
+		};
+
+		oscclk5: osc@5 {
+			/* HDLCD PLL reference clock */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 5>;
+			freq-range = <23750000 165000000>;
+			#clock-cells = <0>;
+			clock-output-names = "oscclk5";
+		};
+
+		smbclk: osc@6 {
+			/* Static memory controller clock */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 6>;
+			freq-range = <20000000 40000000>;
+			#clock-cells = <0>;
+			clock-output-names = "oscclk6";
+		};
+
+		osc@7 {
+			/* SYS PLL reference clock */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 7>;
+			freq-range = <17000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "oscclk7";
+		};
+
+		osc@8 {
+			/* DDR2 PLL reference clock */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 8>;
+			freq-range = <20000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "oscclk8";
+		};
+
+		volt@0 {
+			/* A15 CPU core voltage */
+			compatible = "arm,vexpress-volt";
+			arm,vexpress-sysreg,func = <2 0>;
+			regulator-name = "A15 Vcore";
+			regulator-min-microvolt = <800000>;
+			regulator-max-microvolt = <1050000>;
+			regulator-always-on;
+			label = "A15 Vcore";
+		};
+
+		volt@1 {
+			/* A7 CPU core voltage */
+			compatible = "arm,vexpress-volt";
+			arm,vexpress-sysreg,func = <2 1>;
+			regulator-name = "A7 Vcore";
+			regulator-min-microvolt = <800000>;
+			regulator-max-microvolt = <1050000>;
+			regulator-always-on;
+			label = "A7 Vcore";
+		};
+
+		amp@0 {
+			/* Total current for the two A15 cores */
+			compatible = "arm,vexpress-amp";
+			arm,vexpress-sysreg,func = <3 0>;
+			label = "A15 Icore";
+		};
+
+		amp@1 {
+			/* Total current for the three A7 cores */
+			compatible = "arm,vexpress-amp";
+			arm,vexpress-sysreg,func = <3 1>;
+			label = "A7 Icore";
+		};
+
+		temp@0 {
+			/* DCC internal temperature */
+			compatible = "arm,vexpress-temp";
+			arm,vexpress-sysreg,func = <4 0>;
+			label = "DCC";
+		};
+
+		power@0 {
+			/* Total power for the two A15 cores */
+			compatible = "arm,vexpress-power";
+			arm,vexpress-sysreg,func = <12 0>;
+			label = "A15 Pcore";
+		};
+		power@1 {
+			/* Total power for the three A7 cores */
+			compatible = "arm,vexpress-power";
+			arm,vexpress-sysreg,func = <12 1>;
+			label = "A7 Pcore";
+		};
+
+		energy@0 {
+			/* Total energy for the two A15 cores */
+			compatible = "arm,vexpress-energy";
+			arm,vexpress-sysreg,func = <13 0>;
+			label = "A15 Jcore";
+		};
+
+		energy@2 {
+			/* Total energy for the three A7 cores */
+			compatible = "arm,vexpress-energy";
+			arm,vexpress-sysreg,func = <13 2>;
+			label = "A7 Jcore";
+		};
+	};
+
+	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/ "vexpress-v2m-rs1.dtsi"
+	};
+};
diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c
index aa526998418..36ae03a3f5d 100644
--- a/arch/arm/common/gic.c
+++ b/arch/arm/common/gic.c
@@ -70,6 +70,14 @@ struct gic_chip_data {
 static DEFINE_RAW_SPINLOCK(irq_controller_lock);
 
 /*
+ * The GIC mapping of CPU interfaces does not necessarily match
+ * the logical CPU numbering.  Let's use a mapping as returned
+ * by the GIC itself.
+ */
+#define NR_GIC_CPU_IF 8
+static u8 gic_cpu_map[NR_GIC_CPU_IF] __read_mostly;
+
+/*
  * Supported arch specific GIC irq extension.
  * Default make them NULL.
  */
@@ -238,11 +246,11 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 	unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask);
 	u32 val, mask, bit;
 
-	if (cpu >= 8 || cpu >= nr_cpu_ids)
+	if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids)
 		return -EINVAL;
 
 	mask = 0xff << shift;
-	bit = 1 << (cpu_logical_map(cpu) + shift);
+	bit = gic_cpu_map[cpu] << shift;
 
 	raw_spin_lock(&irq_controller_lock);
 	val = readl_relaxed(reg) & ~mask;
@@ -349,11 +357,6 @@ static void __init gic_dist_init(struct gic_chip_data *gic)
 	u32 cpumask;
 	unsigned int gic_irqs = gic->gic_irqs;
 	void __iomem *base = gic_data_dist_base(gic);
-	u32 cpu = cpu_logical_map(smp_processor_id());
-
-	cpumask = 1 << cpu;
-	cpumask |= cpumask << 8;
-	cpumask |= cpumask << 16;
 
 	writel_relaxed(0, base + GIC_DIST_CTRL);
 
@@ -366,6 +369,7 @@ static void __init gic_dist_init(struct gic_chip_data *gic)
 	/*
 	 * Set all global interrupts to this CPU only.
 	 */
+	cpumask = readl_relaxed(base + GIC_DIST_TARGET + 0);
 	for (i = 32; i < gic_irqs; i += 4)
 		writel_relaxed(cpumask, base + GIC_DIST_TARGET + i * 4 / 4);
 
@@ -389,9 +393,25 @@ static void __cpuinit gic_cpu_init(struct gic_chip_data *gic)
 {
 	void __iomem *dist_base = gic_data_dist_base(gic);
 	void __iomem *base = gic_data_cpu_base(gic);
+	unsigned int cpu_mask, cpu = smp_processor_id();
 	int i;
 
 	/*
+	 * Get what the GIC says our CPU mask is.
+	 */
+	BUG_ON(cpu >= NR_GIC_CPU_IF);
+	cpu_mask = readl_relaxed(dist_base + GIC_DIST_TARGET + 0);
+	gic_cpu_map[cpu] = cpu_mask;
+
+	/*
+	 * Clear our mask from the other map entries in case they're
+	 * still undefined.
+	 */
+	for (i = 0; i < NR_GIC_CPU_IF; i++)
+		if (i != cpu)
+			gic_cpu_map[i] &= ~cpu_mask;
+
+	/*
 	 * Deal with the banked PPI and SGI interrupts - disable all
 	 * PPI interrupts, ensure all SGI interrupts are enabled.
 	 */
@@ -646,7 +666,7 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 {
 	irq_hw_number_t hwirq_base;
 	struct gic_chip_data *gic;
-	int gic_irqs, irq_base;
+	int gic_irqs, irq_base, i;
 
 	BUG_ON(gic_nr >= MAX_GIC_NR);
 
@@ -683,6 +703,13 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 	}
 
 	/*
+	 * Initialize the CPU interface map to all CPUs.
+	 * It will be refined as each CPU probes its ID.
+	 */
+	for (i = 0; i < NR_GIC_CPU_IF; i++)
+		gic_cpu_map[i] = 0xff;
+
+	/*
 	 * For primary GICs, skip over SGIs.
 	 * For secondary GICs, skip over PPIs, too.
 	 */
@@ -737,7 +764,7 @@ void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 
 	/* Convert our logical CPU mask into a physical one. */
 	for_each_cpu(cpu, mask)
-		map |= 1 << cpu_logical_map(cpu);
+		map |= gic_cpu_map[cpu];
 
 	/*
 	 * Ensure that stores to Normal memory are visible to the
diff --git a/arch/arm/include/asm/cpu.h b/arch/arm/include/asm/cpu.h
index d797223b39d..2744f060255 100644
--- a/arch/arm/include/asm/cpu.h
+++ b/arch/arm/include/asm/cpu.h
@@ -15,6 +15,7 @@
 
 struct cpuinfo_arm {
 	struct cpu	cpu;
+	u32		cpuid;
 #ifdef CONFIG_SMP
 	unsigned int	loops_per_jiffy;
 #endif
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index cb47d28cbe1..a59dcb5ab5f 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -25,6 +25,19 @@
 #define CPUID_EXT_ISAR4	"c2, 4"
 #define CPUID_EXT_ISAR5	"c2, 5"
 
+#define MPIDR_SMP_BITMASK (0x3 << 30)
+#define MPIDR_SMP_VALUE (0x2 << 30)
+
+#define MPIDR_MT_BITMASK (0x1 << 24)
+
+#define MPIDR_HWID_BITMASK 0xFFFFFF
+
+#define MPIDR_LEVEL_BITS 8
+#define MPIDR_LEVEL_MASK ((1 << MPIDR_LEVEL_BITS) - 1)
+
+#define MPIDR_AFFINITY_LEVEL(mpidr, level) \
+	((mpidr >> (MPIDR_LEVEL_BITS * level)) & MPIDR_LEVEL_MASK)
+
 extern unsigned int processor_id;
 
 #ifdef CONFIG_CPU_CP15
diff --git a/arch/arm/include/asm/prom.h b/arch/arm/include/asm/prom.h
index aeae9c609df..8dd51dc1a36 100644
--- a/arch/arm/include/asm/prom.h
+++ b/arch/arm/include/asm/prom.h
@@ -15,6 +15,7 @@
 
 extern struct machine_desc *setup_machine_fdt(unsigned int dt_phys);
 extern void arm_dt_memblock_reserve(void);
+extern void __init arm_dt_init_cpu_maps(void);
 
 #else /* CONFIG_OF */
 
@@ -24,6 +25,7 @@ static inline struct machine_desc *setup_machine_fdt(unsigned int dt_phys)
 }
 
 static inline void arm_dt_memblock_reserve(void) { }
+static inline void arm_dt_init_cpu_maps(void) { }
 
 #endif /* CONFIG_OF */
 #endif /* ASMARM_PROM_H */
diff --git a/arch/arm/include/asm/smp_plat.h b/arch/arm/include/asm/smp_plat.h
index 558d6c80aca..deabc7806d3 100644
--- a/arch/arm/include/asm/smp_plat.h
+++ b/arch/arm/include/asm/smp_plat.h
@@ -5,6 +5,9 @@
 #ifndef __ASMARM_SMP_PLAT_H
 #define __ASMARM_SMP_PLAT_H
 
+#include <linux/cpumask.h>
+#include <linux/err.h>
+
 #include <asm/cputype.h>
 
 /*
@@ -49,4 +52,13 @@ static inline int cache_ops_need_broadcast(void)
 extern int __cpu_logical_map[];
 #define cpu_logical_map(cpu)	__cpu_logical_map[cpu]
 
+static inline int get_logical_index(u32 mpidr)
+{
+	int cpu;
+	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+		if (cpu_logical_map(cpu) == mpidr)
+			return cpu;
+	return -EINVAL;
+}
+
 #endif
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index bee7f9d47f0..70f1bdeb241 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -19,8 +19,10 @@
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 
+#include <asm/cputype.h>
 #include <asm/setup.h>
 #include <asm/page.h>
+#include <asm/smp_plat.h>
 #include <asm/mach/arch.h>
 #include <asm/mach-types.h>
 
@@ -61,6 +63,108 @@ void __init arm_dt_memblock_reserve(void)
 	}
 }
 
+/*
+ * arm_dt_init_cpu_maps - Function retrieves cpu nodes from the device tree
+ * and builds the cpu logical map array containing MPIDR values related to
+ * logical cpus
+ *
+ * Updates the cpu possible mask with the number of parsed cpu nodes
+ */
+void __init arm_dt_init_cpu_maps(void)
+{
+	/*
+	 * Temp logical map is initialized with UINT_MAX values that are
+	 * considered invalid logical map entries since the logical map must
+	 * contain a list of MPIDR[23:0] values where MPIDR[31:24] must
+	 * read as 0.
+	 */
+	struct device_node *cpu, *cpus;
+	u32 i, j, cpuidx = 1;
+	u32 mpidr = is_smp() ? read_cpuid_mpidr() & MPIDR_HWID_BITMASK : 0;
+
+	u32 tmp_map[NR_CPUS] = { [0 ... NR_CPUS-1] = UINT_MAX };
+	bool bootcpu_valid = false;
+	cpus = of_find_node_by_path("/cpus");
+
+	if (!cpus)
+		return;
+
+	for_each_child_of_node(cpus, cpu) {
+		u32 hwid;
+
+		pr_debug(" * %s...\n", cpu->full_name);
+		/*
+		 * A device tree containing CPU nodes with missing "reg"
+		 * properties is considered invalid to build the
+		 * cpu_logical_map.
+		 */
+		if (of_property_read_u32(cpu, "reg", &hwid)) {
+			pr_debug(" * %s missing reg property\n",
+				     cpu->full_name);
+			return;
+		}
+
+		/*
+		 * 8 MSBs must be set to 0 in the DT since the reg property
+		 * defines the MPIDR[23:0].
+		 */
+		if (hwid & ~MPIDR_HWID_BITMASK)
+			return;
+
+		/*
+		 * Duplicate MPIDRs are a recipe for disaster.
+		 * Scan all initialized entries and check for
+		 * duplicates. If any is found just bail out.
+		 * temp values were initialized to UINT_MAX
+		 * to avoid matching valid MPIDR[23:0] values.
+		 */
+		for (j = 0; j < cpuidx; j++)
+			if (WARN(tmp_map[j] == hwid, "Duplicate /cpu reg "
+						     "properties in the DT\n"))
+				return;
+
+		/*
+		 * Build a stashed array of MPIDR values. Numbering scheme
+		 * requires that if detected the boot CPU must be assigned
+		 * logical id 0. Other CPUs get sequential indexes starting
+		 * from 1. If a CPU node with a reg property matching the
+		 * boot CPU MPIDR is detected, this is recorded so that the
+		 * logical map built from DT is validated and can be used
+		 * to override the map created in smp_setup_processor_id().
+		 */
+		if (hwid == mpidr) {
+			i = 0;
+			bootcpu_valid = true;
+		} else {
+			i = cpuidx++;
+		}
+
+		if (WARN(cpuidx > nr_cpu_ids, "DT /cpu %u nodes greater than "
+					       "max cores %u, capping them\n",
+					       cpuidx, nr_cpu_ids)) {
+			cpuidx = nr_cpu_ids;
+			break;
+		}
+
+		tmp_map[i] = hwid;
+	}
+
+	if (WARN(!bootcpu_valid, "DT missing boot CPU MPIDR[23:0], "
+				 "fall back to default cpu_logical_map\n"))
+		return;
+
+	/*
+	 * Since the boot CPU node contains proper data, and all nodes have
+	 * a reg property, the DT CPU list can be considered valid and the
+	 * logical map created in smp_setup_processor_id() can be overridden
+	 */
+	for (i = 0; i < cpuidx; i++) {
+		set_cpu_possible(i, true);
+		cpu_logical_map(i) = tmp_map[i];
+		pr_debug("cpu logical map 0x%x\n", cpu_logical_map(i));
+	}
+}
+
 /**
  * setup_machine_fdt - Machine setup when an dtb was passed to the kernel
  * @dt_phys: physical address of dt blob
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index da1d1aa20ad..f739fb1d217 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -426,13 +426,14 @@ int __cpu_logical_map[NR_CPUS];
 void __init smp_setup_processor_id(void)
 {
 	int i;
-	u32 cpu = is_smp() ? read_cpuid_mpidr() & 0xff : 0;
+	u32 mpidr = is_smp() ? read_cpuid_mpidr() & MPIDR_HWID_BITMASK : 0;
+	u32 cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
 
 	cpu_logical_map(0) = cpu;
-	for (i = 1; i < NR_CPUS; ++i)
+	for (i = 1; i < nr_cpu_ids; ++i)
 		cpu_logical_map(i) = i == cpu ? 0 : i;
 
-	printk(KERN_INFO "Booting Linux on physical CPU %d\n", cpu);
+	printk(KERN_INFO "Booting Linux on physical CPU 0x%x\n", mpidr);
 }
 
 static void __init setup_processor(void)
@@ -758,6 +759,7 @@ void __init setup_arch(char **cmdline_p)
 
 	unflatten_device_tree();
 
+	arm_dt_init_cpu_maps();
 #ifdef CONFIG_SMP
 	if (is_smp()) {
 		smp_set_ops(mdesc->smp);
@@ -841,12 +843,9 @@ static const char *hwcap_str[] = {
 
 static int c_show(struct seq_file *m, void *v)
 {
-	int i;
-
-	seq_printf(m, "Processor\t: %s rev %d (%s)\n",
-		   cpu_name, read_cpuid_id() & 15, elf_platform);
+	int i, j;
+	u32 cpuid;
 
-#if defined(CONFIG_SMP)
 	for_each_online_cpu(i) {
 		/*
 		 * glibc reads /proc/cpuinfo to determine the number of
@@ -854,45 +853,48 @@ static int c_show(struct seq_file *m, void *v)
 		 * "processor".  Give glibc what it expects.
 		 */
 		seq_printf(m, "processor\t: %d\n", i);
-		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n\n",
+		cpuid = is_smp() ? per_cpu(cpu_data, i).cpuid : read_cpuid_id();
+		seq_printf(m, "model name\t: %s rev %d (%s)\n",
+			   cpu_name, cpuid & 15, elf_platform);
+
+#if defined(CONFIG_SMP)
+		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
 			   per_cpu(cpu_data, i).loops_per_jiffy / (500000UL/HZ),
 			   (per_cpu(cpu_data, i).loops_per_jiffy / (5000UL/HZ)) % 100);
-	}
-#else /* CONFIG_SMP */
-	seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
-		   loops_per_jiffy / (500000/HZ),
-		   (loops_per_jiffy / (5000/HZ)) % 100);
+#else
+		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
+			   loops_per_jiffy / (500000/HZ),
+			   (loops_per_jiffy / (5000/HZ)) % 100);
 #endif
+		/* dump out the processor features */
+		seq_puts(m, "Features\t: ");
 
-	/* dump out the processor features */
-	seq_puts(m, "Features\t: ");
-
-	for (i = 0; hwcap_str[i]; i++)
-		if (elf_hwcap & (1 << i))
-			seq_printf(m, "%s ", hwcap_str[i]);
+		for (j = 0; hwcap_str[j]; j++)
+			if (elf_hwcap & (1 << j))
+				seq_printf(m, "%s ", hwcap_str[j]);
 
-	seq_printf(m, "\nCPU implementer\t: 0x%02x\n", read_cpuid_id() >> 24);
-	seq_printf(m, "CPU architecture: %s\n", proc_arch[cpu_architecture()]);
+		seq_printf(m, "\nCPU implementer\t: 0x%02x\n", cpuid >> 24);
+		seq_printf(m, "CPU architecture: %s\n",
+			   proc_arch[cpu_architecture()]);
 
-	if ((read_cpuid_id() & 0x0008f000) == 0x00000000) {
-		/* pre-ARM7 */
-		seq_printf(m, "CPU part\t: %07x\n", read_cpuid_id() >> 4);
-	} else {
-		if ((read_cpuid_id() & 0x0008f000) == 0x00007000) {
-			/* ARM7 */
-			seq_printf(m, "CPU variant\t: 0x%02x\n",
-				   (read_cpuid_id() >> 16) & 127);
+		if ((cpuid & 0x0008f000) == 0x00000000) {
+			/* pre-ARM7 */
+			seq_printf(m, "CPU part\t: %07x\n", cpuid >> 4);
 		} else {
-			/* post-ARM7 */
-			seq_printf(m, "CPU variant\t: 0x%x\n",
-				   (read_cpuid_id() >> 20) & 15);
+			if ((cpuid & 0x0008f000) == 0x00007000) {
+				/* ARM7 */
+				seq_printf(m, "CPU variant\t: 0x%02x\n",
+					   (cpuid >> 16) & 127);
+			} else {
+				/* post-ARM7 */
+				seq_printf(m, "CPU variant\t: 0x%x\n",
+					   (cpuid >> 20) & 15);
+			}
+			seq_printf(m, "CPU part\t: 0x%03x\n",
+				   (cpuid >> 4) & 0xfff);
 		}
-		seq_printf(m, "CPU part\t: 0x%03x\n",
-			   (read_cpuid_id() >> 4) & 0xfff);
+		seq_printf(m, "CPU revision\t: %d\n\n", cpuid & 15);
 	}
-	seq_printf(m, "CPU revision\t: %d\n", read_cpuid_id() & 15);
-
-	seq_puts(m, "\n");
 
 	seq_printf(m, "Hardware\t: %s\n", machine_name);
 	seq_printf(m, "Revision\t: %04x\n", system_rev);
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 9da08ce9cd1..eeb75e1f794 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -282,6 +282,7 @@ static void __cpuinit smp_store_cpu_info(unsigned int cpuid)
 	struct cpuinfo_arm *cpu_info = &per_cpu(cpu_data, cpuid);
 
 	cpu_info->loops_per_jiffy = loops_per_jiffy;
+	cpu_info->cpuid = read_cpuid_id();
 
 	store_cpu_topology(cpuid);
 }
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 4d34e0e7e94..aafacaf59f4 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -196,32 +196,7 @@ static inline void parse_dt_topology(void) {}
 static inline void update_cpu_power(unsigned int cpuid, unsigned int mpidr) {}
 #endif
 
-
-/*
- * cpu topology management
- */
-
-#define MPIDR_SMP_BITMASK (0x3 << 30)
-#define MPIDR_SMP_VALUE (0x2 << 30)
-
-#define MPIDR_MT_BITMASK (0x1 << 24)
-
-/*
- * These masks reflect the current use of the affinity levels.
- * The affinity level can be up to 16 bits according to ARM ARM
- */
-#define MPIDR_HWID_BITMASK 0xFFFFFF
-
-#define MPIDR_LEVEL0_MASK 0x3
-#define MPIDR_LEVEL0_SHIFT 0
-
-#define MPIDR_LEVEL1_MASK 0xF
-#define MPIDR_LEVEL1_SHIFT 8
-
-#define MPIDR_LEVEL2_MASK 0xFF
-#define MPIDR_LEVEL2_SHIFT 16
-
-/*
+ /*
  * cpu topology table
  */
 struct cputopo_arm cpu_topology[NR_CPUS];
@@ -287,19 +262,14 @@ void store_cpu_topology(unsigned int cpuid)
 
 		if (mpidr & MPIDR_MT_BITMASK) {
 			/* core performance interdependency */
-			cpuid_topo->thread_id = (mpidr >> MPIDR_LEVEL0_SHIFT)
-				& MPIDR_LEVEL0_MASK;
-			cpuid_topo->core_id = (mpidr >> MPIDR_LEVEL1_SHIFT)
-				& MPIDR_LEVEL1_MASK;
-			cpuid_topo->socket_id = (mpidr >> MPIDR_LEVEL2_SHIFT)
-				& MPIDR_LEVEL2_MASK;
+			cpuid_topo->thread_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+			cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+			cpuid_topo->socket_id = MPIDR_AFFINITY_LEVEL(mpidr, 2);
 		} else {
 			/* largely independent cores */
 			cpuid_topo->thread_id = -1;
-			cpuid_topo->core_id = (mpidr >> MPIDR_LEVEL0_SHIFT)
-				& MPIDR_LEVEL0_MASK;
-			cpuid_topo->socket_id = (mpidr >> MPIDR_LEVEL1_SHIFT)
-				& MPIDR_LEVEL1_MASK;
+			cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+			cpuid_topo->socket_id = MPIDR_AFFINITY_LEVEL(mpidr, 1);
 		}
 	} else {
 		/*
diff --git a/arch/arm/plat-versatile/headsmp.S b/arch/arm/plat-versatile/headsmp.S
index dd703ef09b8..b178d44e9ea 100644
--- a/arch/arm/plat-versatile/headsmp.S
+++ b/arch/arm/plat-versatile/headsmp.S
@@ -20,7 +20,7 @@
  */
 ENTRY(versatile_secondary_startup)
 	mrc	p15, 0, r0, c0, c0, 5
-	and	r0, r0, #15
+	bic	r0, #0xff000000
 	adr	r4, 1f
 	ldmia	r4, {r5, r6}
 	sub	r4, r4, r5