Merge tag 'D01-for-3.18' of git://github.com/hisilicon/linux-hisi into next/soc

Merge "pull request for hisilicon hip04 soc and D01 board updates" from Wei Xu:

ARM: mach-hisi: Hisilicon hip04 soc and D01 board updates for 3.18

- Add the CONFIG_MCPM_QUAD_CLUSTER configuration to enlarge cluster number from 2 to 4
- Enable MCPM on HiP04 SoC
- Enable 16 cores on HiP04 SoC
- Add platform & Fabric controller devicetree binding document for HiP04 SoC
- Add hip04.dtsi & hip04-d01.dts for hip04 SoC platform and D01 board
- Enable HiP04 SoC in both hi3xxx_defconfig & multi_v7_defconfig
- Add the support of Hisilicon HiP04 debug uart

* tag 'D01-for-3.18' of git://github.com/hisilicon/linux-hisi:
  ARM: debug: add HiP04 debug uart
  ARM: config: enable hisilicon hip04
  ARM: dts: add hip04 dts
  document: dt: add the binding on HiP04
  ARM: hisi: enable HiP04
  ARM: hisi: enable MCPM implementation
  ARM: mcpm: support 4 clusters
Signed-off-by: Olof Johansson <olof@lixom.net>

Documentation/devicetree/bindings/arm/hisilicon/hisilicon.txt

@@ -5,6 +5,11 @@ Hi4511 Board
 Required root node properties:
 	- compatible = "hisilicon,hi3620-hi4511";
 
+HiP04 D01 Board
+Required root node properties:
+	- compatible = "hisilicon,hip04-d01";
+
+
 Hisilicon system controller
 
 Required properties:
@@ -55,3 +60,21 @@ Example:
 		compatible = "hisilicon,pctrl";
 		reg = <0xfca09000 0x1000>;
 	};
+
+-----------------------------------------------------------------------
+Fabric:
+
+Required Properties:
+- compatible: "hisilicon,hip04-fabric";
+- reg: Address and size of Fabric
+
+-----------------------------------------------------------------------
+Bootwrapper boot method (software protocol on SMP):
+
+Required Properties:
+- compatible: "hisilicon,hip04-bootwrapper";
+- boot-method: Address and size of boot method.
+  [0]: bootwrapper physical address
+  [1]: bootwrapper size
+  [2]: relocation physical address
+  [3]: relocation size

arch/arm/Kconfig

@@ -1406,6 +1406,15 @@ config MCPM
 	  for (multi-)cluster based systems, such as big.LITTLE based
 	  systems.
 
+config MCPM_QUAD_CLUSTER
+	bool
+	depends on MCPM
+	help
+	  To avoid wasting resources unnecessarily, MCPM only supports up
+	  to 2 clusters by default.
+	  Platforms with 3 or 4 clusters that use MCPM must select this
+	  option to allow the additional clusters to be managed.
+
 config BIG_LITTLE
 	bool "big.LITTLE support (Experimental)"
 	depends on CPU_V7 && SMP

arch/arm/Kconfig.debug

@@ -231,6 +231,14 @@ choice
 		  Say Y here if you want kernel low-level debugging support
 		  on Hix5hd2 UART.
 
+	config DEBUG_HIP04_UART
+		bool "Hisilicon HiP04 Debug UART"
+		depends on ARCH_HIP04
+		select DEBUG_UART_8250
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on HIP04 UART.
+
 	config DEBUG_HIGHBANK_UART
 		bool "Kernel low-level debugging messages via Highbank UART"
 		depends on ARCH_HIGHBANK
@@ -1109,6 +1117,7 @@ config DEBUG_UART_PHYS
 	default 0xd4017000 if DEBUG_MMP_UART2
 	default 0xd4018000 if DEBUG_MMP_UART3
 	default 0xe0000000 if ARCH_SPEAR13XX
+	default 0xe4007000 if DEBUG_HIP04_UART
 	default 0xf0000be0 if ARCH_EBSA110
 	default 0xf1012000 if DEBUG_MVEBU_UART_ALTERNATE
 	default 0xf1012000 if ARCH_DOVE || ARCH_MV78XX0 || \
@@ -1152,6 +1161,7 @@ config DEBUG_UART_VIRT
 	default 0xf7008000 if DEBUG_S3C24XX_UART && (DEBUG_S3C_UART2 || \
 				DEBUG_S3C2410_UART2)
 	default 0xf7fc9000 if DEBUG_BERLIN_UART
+	default 0xf8007000 if DEBUG_HIP04_UART
 	default 0xf8009000 if DEBUG_VEXPRESS_UART0_CA9
 	default 0xf8090000 if DEBUG_VEXPRESS_UART0_RS1
 	default 0xfa71e000 if DEBUG_QCOM_UARTDM

arch/arm/boot/dts/Makefile

@@ -90,6 +90,7 @@ dtb-$(CONFIG_ARCH_HI3xxx) += hi3620-hi4511.dtb
 dtb-$(CONFIG_ARCH_HIX5HD2) += hisi-x5hd2-dkb.dtb
 dtb-$(CONFIG_ARCH_HIGHBANK) += highbank.dtb \
 	ecx-2000.dtb
+dtb-$(CONFIG_ARCH_HIP04) += hip04-d01.dtb
 dtb-$(CONFIG_ARCH_INTEGRATOR) += integratorap.dtb \
 	integratorcp.dtb
 dtb-$(CONFIG_ARCH_KEYSTONE) += k2hk-evm.dtb \

arch/arm/boot/dts/hip04-d01.dts

+/*
+ *  Copyright (C) 2013-2014 Linaro Ltd.
+ *  Author: Haojian Zhuang <haojian.zhuang@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
+ *  publishhed by the Free Software Foundation.
+ */
+
+/dts-v1/;
+
+#include "hip04.dtsi"
+
+/ {
+	/* memory bus is 64-bit */
+	#address-cells = <2>;
+	#size-cells = <2>;
+	model = "Hisilicon D01 Development Board";
+	compatible = "hisilicon,hip04-d01";
+
+	memory@00000000,10000000 {
+		device_type = "memory";
+		reg = <0x00000000 0x10000000 0x00000000 0xc0000000>,
+		      <0x00000004 0xc0000000 0x00000003 0x40000000>;
+	};
+
+	soc {
+		uart0: uart@4007000 {
+			status = "ok";
+		};
+	};
+};

arch/arm/boot/dts/hip04.dtsi

+/*
+ * Hisilicon Ltd. HiP04 SoC
+ *
+ * Copyright (C) 2013-2014 Hisilicon Ltd.
+ * Copyright (C) 2013-2014 Linaro Ltd.
+ *
+ * Author: Haojian Zhuang <haojian.zhuang@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.
+ */
+
+/ {
+	/* memory bus is 64-bit */
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	bootwrapper {
+		compatible = "hisilicon,hip04-bootwrapper";
+		boot-method = <0x10c00000 0x10000>, <0xe0000100 0x1000>;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&CPU0>;
+				};
+				core1 {
+					cpu = <&CPU1>;
+				};
+				core2 {
+					cpu = <&CPU2>;
+				};
+				core3 {
+					cpu = <&CPU3>;
+				};
+			};
+			cluster1 {
+				core0 {
+					cpu = <&CPU4>;
+				};
+				core1 {
+					cpu = <&CPU5>;
+				};
+				core2 {
+					cpu = <&CPU6>;
+				};
+				core3 {
+					cpu = <&CPU7>;
+				};
+			};
+			cluster2 {
+				core0 {
+					cpu = <&CPU8>;
+				};
+				core1 {
+					cpu = <&CPU9>;
+				};
+				core2 {
+					cpu = <&CPU10>;
+				};
+				core3 {
+					cpu = <&CPU11>;
+				};
+			};
+			cluster3 {
+				core0 {
+					cpu = <&CPU12>;
+				};
+				core1 {
+					cpu = <&CPU13>;
+				};
+				core2 {
+					cpu = <&CPU14>;
+				};
+				core3 {
+					cpu = <&CPU15>;
+				};
+			};
+		};
+		CPU0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+		};
+		CPU1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <1>;
+		};
+		CPU2: cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <2>;
+		};
+		CPU3: cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <3>;
+		};
+		CPU4: cpu@100 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x100>;
+		};
+		CPU5: cpu@101 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x101>;
+		};
+		CPU6: cpu@102 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x102>;
+		};
+		CPU7: cpu@103 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x103>;
+		};
+		CPU8: cpu@200 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x200>;
+		};
+		CPU9: cpu@201 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x201>;
+		};
+		CPU10: cpu@202 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x202>;
+		};
+		CPU11: cpu@203 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x203>;
+		};
+		CPU12: cpu@300 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x300>;
+		};
+		CPU13: cpu@301 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x301>;
+		};
+		CPU14: cpu@302 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x302>;
+		};
+		CPU15: cpu@303 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x303>;
+		};
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupt-parent = <&gic>;
+		interrupts = <1 13 0xf08>,
+			     <1 14 0xf08>,
+			     <1 11 0xf08>,
+			     <1 10 0xf08>;
+	};
+
+	clk_50m: clk_50m {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <50000000>;
+	};
+
+	clk_168m: clk_168m {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <168000000>;
+	};
+
+	soc {
+		/* It's a 32-bit SoC. */
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "simple-bus";
+		interrupt-parent = <&gic>;
+		ranges = <0 0 0xe0000000 0x10000000>;
+
+		gic: interrupt-controller@c01000 {
+			compatible = "hisilicon,hip04-intc";
+			#interrupt-cells = <3>;
+			#address-cells = <0>;
+			interrupt-controller;
+			interrupts = <1 9 0xf04>;
+
+			reg = <0xc01000 0x1000>, <0xc02000 0x1000>,
+			      <0xc04000 0x2000>, <0xc06000 0x2000>;
+		};
+
+		sysctrl: sysctrl {
+			compatible = "hisilicon,sysctrl";
+			reg = <0x3e00000 0x00100000>;
+		};
+
+		fabric: fabric {
+			compatible = "hisilicon,hip04-fabric";
+			reg = <0x302a000 0x1000>;
+		};
+
+		dual_timer0: dual_timer@3000000 {
+			compatible = "arm,sp804", "arm,primecell";
+			reg = <0x3000000 0x1000>;
+			interrupts = <0 224 4>;
+			clocks = <&clk_50m>, <&clk_50m>;
+			clock-names = "apb_pclk";
+		};
+
+		arm-pmu {
+			compatible = "arm,cortex-a15-pmu";
+			interrupts = <0 64 4>,
+				     <0 65 4>,
+				     <0 66 4>,
+				     <0 67 4>,
+				     <0 68 4>,
+				     <0 69 4>,
+				     <0 70 4>,
+				     <0 71 4>,
+				     <0 72 4>,
+				     <0 73 4>,
+				     <0 74 4>,
+				     <0 75 4>,
+				     <0 76 4>,
+				     <0 77 4>,
+				     <0 78 4>,
+				     <0 79 4>;
+		};
+
+		uart0: uart@4007000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x4007000 0x1000>;
+			interrupts = <0 381 4>;
+			clocks = <&clk_168m>;
+			clock-names = "uartclk";
+			reg-shift = <2>;
+			status = "disabled";
+		};
+
+		sata0: sata@a000000 {
+			compatible = "hisilicon,hisi-ahci";
+			reg = <0xa000000 0x1000000>;
+			interrupts = <0 372 4>;
+		};
+
+	};
+};

arch/arm/configs/hi3xxx_defconfig → arch/arm/configs/hisi_defconfig

@@ -6,10 +6,15 @@ CONFIG_RD_LZMA=y
 CONFIG_ARCH_HISI=y
 CONFIG_ARCH_HI3xxx=y
 CONFIG_ARCH_HIX5HD2=y
+CONFIG_ARCH_HIP04=y
 CONFIG_SMP=y
+CONFIG_NR_CPUS=16
 CONFIG_PREEMPT=y
 CONFIG_AEABI=y
+CONFIG_HIGHMEM=y
 CONFIG_ARM_APPENDED_DTB=y
+CONFIG_ARM_ATAG_DTB_COMPAT=y
+CONFIG_ARM_ATAG_DTB_COMPAT_CMDLINE_FROM_BOOTLOADER=y
 CONFIG_NET=y
 CONFIG_UNIX=y
 CONFIG_INET=y
@@ -21,6 +26,12 @@ CONFIG_BLK_DEV_SD=y
 CONFIG_ATA=y
 CONFIG_SATA_AHCI_PLATFORM=y
 CONFIG_NETDEVICES=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_DEPRECATED_OPTIONS=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=2
+CONFIG_SERIAL_8250_RUNTIME_UARTS=2
+CONFIG_SERIAL_8250_DW=y
 CONFIG_SERIAL_AMBA_PL011=y
 CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
 CONFIG_SERIAL_OF_PLATFORM=y
@@ -56,3 +67,5 @@ CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_LOCKUP_DETECTOR=y
+CONFIG_VFP=y
+CONFIG_VFPv3=y

arch/arm/configs/multi_v7_defconfig

@@ -28,6 +28,7 @@ CONFIG_ARCH_HIGHBANK=y
 CONFIG_ARCH_HISI=y
 CONFIG_ARCH_HI3xxx=y
 CONFIG_ARCH_HIX5HD2=y
+CONFIG_ARCH_HIP04=y
 CONFIG_ARCH_KEYSTONE=y
 CONFIG_ARCH_MXC=y
 CONFIG_SOC_IMX51=y

arch/arm/include/asm/mcpm.h

@@ -20,7 +20,12 @@
  * to consider dynamic allocation.
  */
 #define MAX_CPUS_PER_CLUSTER	4
+
+#ifdef CONFIG_MCPM_QUAD_CLUSTER
+#define MAX_NR_CLUSTERS		4
+#else
 #define MAX_NR_CLUSTERS		2
+#endif
 
 #ifndef __ASSEMBLY__
 

arch/arm/mach-hisi/Kconfig

@@ -22,6 +22,15 @@ config ARCH_HI3xxx
 	help
 	  Support for Hisilicon Hi36xx SoC family
 
+config ARCH_HIP04
+	bool "Hisilicon HiP04 Cortex A15 family" if ARCH_MULTI_V7
+	select ARM_ERRATA_798181 if SMP
+	select HAVE_ARM_ARCH_TIMER
+	select MCPM if SMP
+	select MCPM_QUAD_CLUSTER if SMP
+	help
+	  Support for Hisilicon HiP04 SoC family
+
 config ARCH_HIX5HD2
 	bool "Hisilicon X5HD2 family" if ARCH_MULTI_V7
 	select CACHE_L2X0

arch/arm/mach-hisi/Makefile

@@ -3,4 +3,5 @@
 #
 
 obj-y	+= hisilicon.o
+obj-$(CONFIG_MCPM)		+= platmcpm.o
 obj-$(CONFIG_SMP)		+= platsmp.o hotplug.o headsmp.o

arch/arm/mach-hisi/hisilicon.c

@@ -63,3 +63,12 @@ static const char *hix5hd2_compat[] __initconst = {
 DT_MACHINE_START(HIX5HD2_DT, "Hisilicon HIX5HD2 (Flattened Device Tree)")
 	.dt_compat	= hix5hd2_compat,
 MACHINE_END
+
+static const char *hip04_compat[] __initconst = {
+	"hisilicon,hip04-d01",
+	NULL,
+};
+
+DT_MACHINE_START(HIP04, "Hisilicon HiP04 (Flattened Device Tree)")
+	.dt_compat	= hip04_compat,
+MACHINE_END

arch/arm/mach-hisi/platmcpm.c

+/*
+ * Copyright (c) 2013-2014 Linaro Ltd.
+ * Copyright (c) 2013-2014 Hisilicon Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ */
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/memblock.h>
+#include <linux/of_address.h>
+
+#include <asm/cputype.h>
+#include <asm/cp15.h>
+#include <asm/mcpm.h>
+
+#include "core.h"
+
+/* bits definition in SC_CPU_RESET_REQ[x]/SC_CPU_RESET_DREQ[x]
+ * 1 -- unreset; 0 -- reset
+ */
+#define CORE_RESET_BIT(x)		(1 << x)
+#define NEON_RESET_BIT(x)		(1 << (x + 4))
+#define CORE_DEBUG_RESET_BIT(x)		(1 << (x + 9))
+#define CLUSTER_L2_RESET_BIT		(1 << 8)
+#define CLUSTER_DEBUG_RESET_BIT		(1 << 13)
+
+/*
+ * bits definition in SC_CPU_RESET_STATUS[x]
+ * 1 -- reset status; 0 -- unreset status
+ */
+#define CORE_RESET_STATUS(x)		(1 << x)
+#define NEON_RESET_STATUS(x)		(1 << (x + 4))
+#define CORE_DEBUG_RESET_STATUS(x)	(1 << (x + 9))
+#define CLUSTER_L2_RESET_STATUS		(1 << 8)
+#define CLUSTER_DEBUG_RESET_STATUS	(1 << 13)
+#define CORE_WFI_STATUS(x)		(1 << (x + 16))
+#define CORE_WFE_STATUS(x)		(1 << (x + 20))
+#define CORE_DEBUG_ACK(x)		(1 << (x + 24))
+
+#define SC_CPU_RESET_REQ(x)		(0x520 + (x << 3))	/* reset */
+#define SC_CPU_RESET_DREQ(x)		(0x524 + (x << 3))	/* unreset */
+#define SC_CPU_RESET_STATUS(x)		(0x1520 + (x << 3))
+
+#define FAB_SF_MODE			0x0c
+#define FAB_SF_INVLD			0x10
+
+/* bits definition in FB_SF_INVLD */
+#define FB_SF_INVLD_START		(1 << 8)
+
+#define HIP04_MAX_CLUSTERS		4
+#define HIP04_MAX_CPUS_PER_CLUSTER	4
+
+#define POLL_MSEC	10
+#define TIMEOUT_MSEC	1000
+
+static void __iomem *sysctrl, *fabric;
+static int hip04_cpu_table[HIP04_MAX_CLUSTERS][HIP04_MAX_CPUS_PER_CLUSTER];
+static DEFINE_SPINLOCK(boot_lock);
+static u32 fabric_phys_addr;
+/*
+ * [0]: bootwrapper physical address
+ * [1]: bootwrapper size
+ * [2]: relocation address
+ * [3]: relocation size
+ */
+static u32 hip04_boot_method[4];
+
+static bool hip04_cluster_is_down(unsigned int cluster)
+{
+	int i;
+
+	for (i = 0; i < HIP04_MAX_CPUS_PER_CLUSTER; i++)
+		if (hip04_cpu_table[cluster][i])
+			return false;
+	return true;
+}
+
+static void hip04_set_snoop_filter(unsigned int cluster, unsigned int on)
+{
+	unsigned long data;
+
+	if (!fabric)
+		BUG();
+	data = readl_relaxed(fabric + FAB_SF_MODE);
+	if (on)
+		data |= 1 << cluster;
+	else
+		data &= ~(1 << cluster);
+	writel_relaxed(data, fabric + FAB_SF_MODE);
+	do {
+		cpu_relax();
+	} while (data != readl_relaxed(fabric + FAB_SF_MODE));
+}
+
+static int hip04_mcpm_power_up(unsigned int cpu, unsigned int cluster)
+{
+	unsigned long data;
+	void __iomem *sys_dreq, *sys_status;
+
+	if (!sysctrl)
+		return -ENODEV;
+	if (cluster >= HIP04_MAX_CLUSTERS || cpu >= HIP04_MAX_CPUS_PER_CLUSTER)
+		return -EINVAL;
+
+	spin_lock_irq(&boot_lock);
+
+	if (hip04_cpu_table[cluster][cpu])
+		goto out;
+
+	sys_dreq = sysctrl + SC_CPU_RESET_DREQ(cluster);
+	sys_status = sysctrl + SC_CPU_RESET_STATUS(cluster);
+	if (hip04_cluster_is_down(cluster)) {
+		data = CLUSTER_DEBUG_RESET_BIT;
+		writel_relaxed(data, sys_dreq);
+		do {
+			cpu_relax();
+			data = readl_relaxed(sys_status);
+		} while (data & CLUSTER_DEBUG_RESET_STATUS);
+	}
+
+	data = CORE_RESET_BIT(cpu) | NEON_RESET_BIT(cpu) | \
+	       CORE_DEBUG_RESET_BIT(cpu);
+	writel_relaxed(data, sys_dreq);
+	do {
+		cpu_relax();
+	} while (data == readl_relaxed(sys_status));
+	/*
+	 * We may fail to power up core again without this delay.
+	 * It's not mentioned in document. It's found by test.
+	 */
+	udelay(20);
+out:
+	hip04_cpu_table[cluster][cpu]++;
+	spin_unlock_irq(&boot_lock);
+
+	return 0;
+}
+
+static void hip04_mcpm_power_down(void)
+{
+	unsigned int mpidr, cpu, cluster;
+	bool skip_wfi = false, last_man = false;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+	__mcpm_cpu_going_down(cpu, cluster);
+
+	spin_lock(&boot_lock);
+	BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP);
+	hip04_cpu_table[cluster][cpu]--;
+	if (hip04_cpu_table[cluster][cpu] == 1) {
+		/* A power_up request went ahead of us. */
+		skip_wfi = true;
+	} else if (hip04_cpu_table[cluster][cpu] > 1) {
+		pr_err("Cluster %d CPU%d boots multiple times\n", cluster, cpu);
+		BUG();
+	}
+
+	last_man = hip04_cluster_is_down(cluster);
+	if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) {
+		spin_unlock(&boot_lock);
+		/* Since it's Cortex A15, disable L2 prefetching. */
+		asm volatile(
+		"mcr	p15, 1, %0, c15, c0, 3 \n\t"
+		"isb	\n\t"
+		"dsb	"
+		: : "r" (0x400) );
+		v7_exit_coherency_flush(all);
+		hip04_set_snoop_filter(cluster, 0);
+		__mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN);
+	} else {
+		spin_unlock(&boot_lock);
+		v7_exit_coherency_flush(louis);
+	}
+
+	__mcpm_cpu_down(cpu, cluster);
+
+	if (!skip_wfi)
+		wfi();
+}
+
+static int hip04_mcpm_wait_for_powerdown(unsigned int cpu, unsigned int cluster)
+{
+	unsigned int data, tries, count;
+	int ret = -ETIMEDOUT;
+
+	BUG_ON(cluster >= HIP04_MAX_CLUSTERS ||
+	       cpu >= HIP04_MAX_CPUS_PER_CLUSTER);
+
+	count = TIMEOUT_MSEC / POLL_MSEC;
+	spin_lock_irq(&boot_lock);
+	for (tries = 0; tries < count; tries++) {
+		if (hip04_cpu_table[cluster][cpu]) {
+			ret = -EBUSY;
+			goto err;
+		}
+		cpu_relax();
+		data = readl_relaxed(sysctrl + SC_CPU_RESET_STATUS(cluster));
+		if (data & CORE_WFI_STATUS(cpu))
+			break;
+		spin_unlock_irq(&boot_lock);
+		/* Wait for clean L2 when the whole cluster is down. */
+		msleep(POLL_MSEC);
+		spin_lock_irq(&boot_lock);
+	}
+	if (tries >= count)
+		goto err;
+	data = CORE_RESET_BIT(cpu) | NEON_RESET_BIT(cpu) | \
+	       CORE_DEBUG_RESET_BIT(cpu);
+	writel_relaxed(data, sysctrl + SC_CPU_RESET_REQ(cluster));
+	for (tries = 0; tries < count; tries++) {
+		cpu_relax();
+		data = readl_relaxed(sysctrl + SC_CPU_RESET_STATUS(cluster));
+		if (data & CORE_RESET_STATUS(cpu))
+			break;
+	}
+	if (tries >= count)
+		goto err;
+	spin_unlock_irq(&boot_lock);
+	return 0;
+err:
+	spin_unlock_irq(&boot_lock);
+	return ret;
+}
+
+static void hip04_mcpm_powered_up(void)
+{
+	unsigned int mpidr, cpu, cluster;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+	spin_lock(&boot_lock);
+	if (!hip04_cpu_table[cluster][cpu])
+		hip04_cpu_table[cluster][cpu] = 1;
+	spin_unlock(&boot_lock);
+}
+
+static void __naked hip04_mcpm_power_up_setup(unsigned int affinity_level)
+{
+	asm volatile ("			\n"
+"	cmp	r0, #0			\n"
+"	bxeq	lr			\n"
+	/* calculate fabric phys address */
+"	adr	r2, 2f			\n"
+"	ldmia	r2, {r1, r3}		\n"
+"	sub	r0, r2, r1		\n"
+"	ldr	r2, [r0, r3]		\n"
+	/* get cluster id from MPIDR */
+"	mrc	p15, 0, r0, c0, c0, 5	\n"
+"	ubfx	r1, r0, #8, #8		\n"
+	/* 1 << cluster id */
+"	mov	r0, #1			\n"
+"	mov	r3, r0, lsl r1		\n"
+"	ldr	r0, [r2, #"__stringify(FAB_SF_MODE)"]	\n"
+"	tst	r0, r3			\n"
+"	bxne	lr			\n"
+"	orr	r1, r0, r3		\n"
+"	str	r1, [r2, #"__stringify(FAB_SF_MODE)"]	\n"
+"1:	ldr	r0, [r2, #"__stringify(FAB_SF_MODE)"]	\n"
+"	tst	r0, r3			\n"
+"	beq	1b			\n"
+"	bx	lr			\n"
+
+"	.align	2			\n"
+"2:	.word	.			\n"
+"	.word	fabric_phys_addr	\n"
+	);
+}
+
+static const struct mcpm_platform_ops hip04_mcpm_ops = {
+	.power_up		= hip04_mcpm_power_up,
+	.power_down		= hip04_mcpm_power_down,
+	.wait_for_powerdown	= hip04_mcpm_wait_for_powerdown,
+	.powered_up		= hip04_mcpm_powered_up,
+};
+
+static bool __init hip04_cpu_table_init(void)
+{
+	unsigned int mpidr, cpu, cluster;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+	if (cluster >= HIP04_MAX_CLUSTERS ||
+	    cpu >= HIP04_MAX_CPUS_PER_CLUSTER) {
+		pr_err("%s: boot CPU is out of bound!\n", __func__);
+		return false;
+	}
+	hip04_set_snoop_filter(cluster, 1);
+	hip04_cpu_table[cluster][cpu] = 1;
+	return true;
+}
+
+static int __init hip04_mcpm_init(void)
+{
+	struct device_node *np, *np_sctl, *np_fab;
+	struct resource fab_res;
+	void __iomem *relocation;
+	int ret = -ENODEV;
+
+	np = of_find_compatible_node(NULL, NULL, "hisilicon,hip04-bootwrapper");
+	if (!np)
+		goto err;
+	ret = of_property_read_u32_array(np, "boot-method",
+					 &hip04_boot_method[0], 4);
+	if (ret)
+		goto err;
+	np_sctl = of_find_compatible_node(NULL, NULL, "hisilicon,sysctrl");
+	if (!np_sctl)
+		goto err;
+	np_fab = of_find_compatible_node(NULL, NULL, "hisilicon,hip04-fabric");
+	if (!np_fab)
+		goto err;
+
+	ret = memblock_reserve(hip04_boot_method[0], hip04_boot_method[1]);
+	if (ret)
+		goto err;
+
+	relocation = ioremap(hip04_boot_method[2], hip04_boot_method[3]);
+	if (!relocation) {
+		pr_err("failed to map relocation space\n");
+		ret = -ENOMEM;
+		goto err_reloc;
+	}
+	sysctrl = of_iomap(np_sctl, 0);
+	if (!sysctrl) {
+		pr_err("failed to get sysctrl base\n");
+		ret = -ENOMEM;
+		goto err_sysctrl;
+	}
+	ret = of_address_to_resource(np_fab, 0, &fab_res);
+	if (ret) {
+		pr_err("failed to get fabric base phys\n");
+		goto err_fabric;
+	}
+	fabric_phys_addr = fab_res.start;
+	sync_cache_w(&fabric_phys_addr);
+	fabric = of_iomap(np_fab, 0);
+	if (!fabric) {
+		pr_err("failed to get fabric base\n");
+		ret = -ENOMEM;
+		goto err_fabric;
+	}
+
+	if (!hip04_cpu_table_init()) {
+		ret = -EINVAL;
+		goto err_table;
+	}
+	ret = mcpm_platform_register(&hip04_mcpm_ops);
+	if (ret) {
+		goto err_table;
+	}
+
+	/*
+	 * Fill the instruction address that is used after secondary core
+	 * out of reset.
+	 */
+	writel_relaxed(hip04_boot_method[0], relocation);
+	writel_relaxed(0xa5a5a5a5, relocation + 4);	/* magic number */
+	writel_relaxed(virt_to_phys(mcpm_entry_point), relocation + 8);
+	writel_relaxed(0, relocation + 12);
+	iounmap(relocation);
+
+	mcpm_sync_init(hip04_mcpm_power_up_setup);
+	mcpm_smp_set_ops();
+	pr_info("HiP04 MCPM initialized\n");
+	return ret;
+err_table:
+	iounmap(fabric);
+err_fabric:
+	iounmap(sysctrl);
+err_sysctrl:
+	iounmap(relocation);
+err_reloc:
+	memblock_free(hip04_boot_method[0], hip04_boot_method[1]);
+err:
+	return ret;
+}
+early_initcall(hip04_mcpm_init);