Merge tag 'marvell-armadaxp-smp-for-3.8' of github.com:MISL-EBU-System-SW/mainline-public into mevbu-dt-additions

SMP support for Armada XP

The purpose of this series is to add the SMP support for the Armada XP
SoCs. Beside the SMP support itself brought by the last 3 commits,
this series also adds the support for the coherency fabric unit and
the power management service unit.

The coherency fabric is responsible for ensuring hardware coherency
between all CPUs and between CPUs and I/O masters. This unit is also
available for Armada 370 and will be used in an incoming patch set
for hardware I/O cache coherency.

The power management service unit is responsible for powering down and
waking up CPUs and other SOC units.

Conflicts:
	arch/arm/mach-mvebu/armada-370-xp.c

Documentation/devicetree/bindings/arm/armada-370-xp-mpic.txt

@@ -6,9 +6,15 @@ Required properties:
 - interrupt-controller: Identifies the node as an interrupt controller.
 - #interrupt-cells: The number of cells to define the interrupts. Should be 1.
   The cell is the IRQ number
+
 - reg: Should contain PMIC registers location and length. First pair
   for the main interrupt registers, second pair for the per-CPU
-  interrupt registers
+  interrupt registers. For this last pair, to be compliant with SMP
+  support, the "virtual" must be use (For the record, these registers
+  automatically map to the interrupt controller registers of the
+  current CPU)
+
+
 
 Example:
 
@@ -18,6 +24,6 @@ Example:
               #address-cells = <1>;
               #size-cells = <1>;
               interrupt-controller;
-              reg = <0xd0020000 0x1000>,
-                    <0xd0021000 0x1000>;
+              reg = <0xd0020a00 0x1d0>,
+                    <0xd0021070 0x58>;
         };

Documentation/devicetree/bindings/arm/armada-370-xp-pmsu.txt

@@ -0,0 +1,20 @@
+Power Management Service Unit(PMSU)
+-----------------------------------
+Available on Marvell SOCs: Armada 370 and Armada XP
+
+Required properties:
+
+- compatible: "marvell,armada-370-xp-pmsu"
+
+- reg: Should contain PMSU registers location and length. First pair
+  for the per-CPU SW Reset Control registers, second pair for the
+  Power Management Service Unit.
+
+Example:
+
+armada-370-xp-pmsu@d0022000 {
+	compatible = "marvell,armada-370-xp-pmsu";
+	reg = <0xd0022100 0x430>,
+	      <0xd0020800 0x20>;
+};
+

Documentation/devicetree/bindings/arm/coherency-fabric.txt

@@ -0,0 +1,16 @@
+Coherency fabric
+----------------
+Available on Marvell SOCs: Armada 370 and Armada XP
+
+Required properties:
+
+- compatible: "marvell,coherency-fabric"
+- reg: Should contain,coherency fabric registers location and length.
+
+Example:
+
+coherency-fabric@d0020200 {
+	compatible = "marvell,coherency-fabric";
+	reg = <0xd0020200 0xb0>;
+};
+

arch/arm/boot/dts/armada-370-xp.dtsi

@@ -36,6 +36,11 @@
 	      interrupt-controller;
 	};
 
+	coherency-fabric@d0020200 {
+		compatible = "marvell,coherency-fabric";
+		reg = <0xd0020200 0xb0>;
+	};
+
 	soc {
 		#address-cells = <1>;
 		#size-cells = <1>;

arch/arm/boot/dts/armada-xp.dtsi

@@ -24,7 +24,13 @@
 
 	mpic: interrupt-controller@d0020000 {
 	      reg = <0xd0020a00 0x1d0>,
-		    <0xd0021870 0x58>;
+		    <0xd0021070 0x58>;
+	};
+
+	armada-370-xp-pmsu@d0022000 {
+		compatible = "marvell,armada-370-xp-pmsu";
+		reg = <0xd0022100 0x430>,
+		      <0xd0020800 0x20>;
 	};
 
 	soc {

arch/arm/configs/mvebu_defconfig

@@ -12,6 +12,9 @@ CONFIG_ARCH_MVEBU=y
 CONFIG_MACH_ARMADA_370=y
 CONFIG_MACH_ARMADA_XP=y
 # CONFIG_CACHE_L2X0 is not set
+# CONFIG_SWP_EMULATE is not set
+CONFIG_SMP=y
+# CONFIG_LOCAL_TIMERS is not set
 CONFIG_AEABI=y
 CONFIG_HIGHMEM=y
 # CONFIG_COMPACTION is not set

arch/arm/mach-mvebu/Kconfig

@@ -21,7 +21,8 @@ menu "Marvell SOC with device tree"
 config MACH_ARMADA_370_XP
 	bool
 	select ARMADA_370_XP_TIMER
-	select CPU_V7
+	select HAVE_SMP
+	select CPU_PJ4B
 
 config MACH_ARMADA_370
 	bool "Marvell Armada 370 boards"

arch/arm/mach-mvebu/Makefile

@@ -2,4 +2,6 @@ ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \
 	-I$(srctree)/arch/arm/plat-orion/include
 
 obj-y += system-controller.o
-obj-$(CONFIG_MACH_ARMADA_370_XP) += armada-370-xp.o irq-armada-370-xp.o addr-map.o
+obj-$(CONFIG_MACH_ARMADA_370_XP) += armada-370-xp.o irq-armada-370-xp.o addr-map.o coherency.o coherency_ll.o pmsu.o
+obj-$(CONFIG_SMP)                += platsmp.o headsmp.o
+obj-$(CONFIG_HOTPLUG_CPU)        += hotplug.o

arch/arm/mach-mvebu/armada-370-xp.c

@@ -24,6 +24,7 @@
 #include <asm/mach/time.h>
 #include "armada-370-xp.h"
 #include "common.h"
+#include "coherency.h"
 
 static struct map_desc armada_370_xp_io_desc[] __initdata = {
 	{
@@ -62,6 +63,7 @@ struct sys_timer armada_370_xp_timer = {
 static void __init armada_370_xp_dt_init(void)
 {
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
+	coherency_init();
 }
 
 static const char * const armada_370_xp_dt_compat[] = {
@@ -70,6 +72,7 @@ static const char * const armada_370_xp_dt_compat[] = {
 };
 
 DT_MACHINE_START(ARMADA_XP_DT, "Marvell Armada 370/XP (Device Tree)")
+	.smp		= smp_ops(armada_xp_smp_ops),
 	.init_machine	= armada_370_xp_dt_init,
 	.map_io		= armada_370_xp_map_io,
 	.init_early	= armada_370_xp_init_early,

arch/arm/mach-mvebu/armada-370-xp.h

@@ -19,4 +19,11 @@
 #define ARMADA_370_XP_REGS_VIRT_BASE	IOMEM(0xfeb00000)
 #define ARMADA_370_XP_REGS_SIZE		SZ_1M
 
+#ifdef CONFIG_SMP
+#include <linux/cpumask.h>
+
+void armada_mpic_send_doorbell(const struct cpumask *mask, unsigned int irq);
+void armada_xp_mpic_smp_cpu_init(void);
+#endif
+
 #endif /* __MACH_ARMADA_370_XP_H */

arch/arm/mach-mvebu/coherency.c

@@ -0,0 +1,82 @@
+/*
+ * Coherency fabric (Aurora) support for Armada 370 and XP platforms.
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Yehuda Yitschak <yehuday@marvell.com>
+ * Gregory Clement <gregory.clement@free-electrons.com>
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ *
+ * The Armada 370 and Armada XP SOCs have a coherency fabric which is
+ * responsible for ensuring hardware coherency between all CPUs and between
+ * CPUs and I/O masters. This file initializes the coherency fabric and
+ * supplies basic routines for configuring and controlling hardware coherency
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/of_address.h>
+#include <linux/io.h>
+#include <linux/smp.h>
+#include <asm/smp_plat.h>
+#include "armada-370-xp.h"
+
+/*
+ * Some functions in this file are called very early during SMP
+ * initialization. At that time the device tree framework is not yet
+ * ready, and it is not possible to get the register address to
+ * ioremap it. That's why the pointer below is given with an initial
+ * value matching its virtual mapping
+ */
+static void __iomem *coherency_base = ARMADA_370_XP_REGS_VIRT_BASE + 0x20200;
+
+/* Coherency fabric registers */
+#define COHERENCY_FABRIC_CFG_OFFSET		   0x4
+
+static struct of_device_id of_coherency_table[] = {
+	{.compatible = "marvell,coherency-fabric"},
+	{ /* end of list */ },
+};
+
+#ifdef CONFIG_SMP
+int coherency_get_cpu_count(void)
+{
+	int reg, cnt;
+
+	reg = readl(coherency_base + COHERENCY_FABRIC_CFG_OFFSET);
+	cnt = (reg & 0xF) + 1;
+
+	return cnt;
+}
+#endif
+
+/* Function defined in coherency_ll.S */
+int ll_set_cpu_coherent(void __iomem *base_addr, unsigned int hw_cpu_id);
+
+int set_cpu_coherent(unsigned int hw_cpu_id, int smp_group_id)
+{
+	if (!coherency_base) {
+		pr_warn("Can't make CPU %d cache coherent.\n", hw_cpu_id);
+		pr_warn("Coherency fabric is not initialized\n");
+		return 1;
+	}
+
+	return ll_set_cpu_coherent(coherency_base, hw_cpu_id);
+}
+
+int __init coherency_init(void)
+{
+	struct device_node *np;
+
+	np = of_find_matching_node(NULL, of_coherency_table);
+	if (np) {
+		pr_info("Initializing Coherency fabric\n");
+		coherency_base = of_iomap(np, 0);
+	}
+
+	return 0;
+}

arch/arm/mach-mvebu/coherency.h

@@ -0,0 +1,24 @@
+/*
+ * arch/arm/mach-mvebu/include/mach/coherency.h
+ *
+ *
+ * Coherency fabric (Aurora) support for Armada 370 and XP platforms.
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#ifndef __MACH_370_XP_COHERENCY_H
+#define __MACH_370_XP_COHERENCY_H
+
+#ifdef CONFIG_SMP
+int coherency_get_cpu_count(void);
+#endif
+
+int set_cpu_coherent(int cpu_id, int smp_group_id);
+int coherency_init(void);
+
+#endif	/* __MACH_370_XP_COHERENCY_H */

arch/arm/mach-mvebu/coherency_ll.S

@@ -0,0 +1,49 @@
+/*
+ * Coherency fabric: low level functions
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ *
+ * This file implements the assembly function to add a CPU to the
+ * coherency fabric. This function is called by each of the secondary
+ * CPUs during their early boot in an SMP kernel, this why this
+ * function have to callable from assembly. It can also be called by a
+ * primary CPU from C code during its boot.
+ */
+
+#include <linux/linkage.h>
+#define ARMADA_XP_CFB_CTL_REG_OFFSET 0x0
+#define ARMADA_XP_CFB_CFG_REG_OFFSET 0x4
+
+	.text
+/*
+ * r0: Coherency fabric base register address
+ * r1: HW CPU id
+ */
+ENTRY(ll_set_cpu_coherent)
+	/* Create bit by cpu index */
+	mov	r3, #(1 << 24)
+	lsl	r1, r3, r1
+
+	/* Add CPU to SMP group - Atomic */
+	add	r3, r0, #ARMADA_XP_CFB_CTL_REG_OFFSET
+	ldr	r2, [r3]
+	orr	r2, r2, r1
+	str	r2, [r3]
+
+	/* Enable coherency on CPU - Atomic */
+	add	r3, r0, #ARMADA_XP_CFB_CFG_REG_OFFSET
+	ldr	r2, [r3]
+	orr	r2, r2, r1
+	str	r2, [r3]
+
+	dsb
+
+	mov	r0, #0
+	mov	pc, lr
+ENDPROC(ll_set_cpu_coherent)

arch/arm/mach-mvebu/common.h

@@ -20,4 +20,9 @@ void mvebu_restart(char mode, const char *cmd);
 void armada_370_xp_init_irq(void);
 void armada_370_xp_handle_irq(struct pt_regs *regs);
 
+void armada_xp_cpu_die(unsigned int cpu);
+int armada_370_xp_coherency_init(void);
+int armada_370_xp_pmsu_init(void);
+void armada_xp_secondary_startup(void);
+extern struct smp_operations armada_xp_smp_ops;
 #endif

arch/arm/mach-mvebu/headsmp.S

@@ -0,0 +1,49 @@
+/*
+ * SMP support: Entry point for secondary CPUs
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Yehuda Yitschak <yehuday@marvell.com>
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ *
+ * This file implements the assembly entry point for secondary CPUs in
+ * an SMP kernel. The only thing we need to do is to add the CPU to
+ * the coherency fabric by writing to 2 registers. Currently the base
+ * register addresses are hard coded due to the early initialisation
+ * problems.
+ */
+
+#include <linux/linkage.h>
+#include <linux/init.h>
+
+/*
+ * At this stage the secondary CPUs don't have acces yet to the MMU, so
+ * we have to provide physical addresses
+ */
+#define ARMADA_XP_CFB_BASE	     0xD0020200
+
+	__CPUINIT
+
+/*
+ * Armada XP specific entry point for secondary CPUs.
+ * We add the CPU to the coherency fabric and then jump to secondary
+ * startup
+ */
+ENTRY(armada_xp_secondary_startup)
+
+	/* Read CPU id */
+	mrc     p15, 0, r1, c0, c0, 5
+	and     r1, r1, #0xF
+
+	/* Add CPU to coherency fabric */
+	ldr     r0, =ARMADA_XP_CFB_BASE
+
+	bl	ll_set_cpu_coherent
+	b	secondary_startup
+
+ENDPROC(armada_xp_secondary_startup)

arch/arm/mach-mvebu/hotplug.c

@@ -0,0 +1,30 @@
+/*
+ * Symmetric Multi Processing (SMP) support for Armada XP
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Lior Amsalem <alior@marvell.com>
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/smp.h>
+#include <asm/proc-fns.h>
+
+/*
+ * platform-specific code to shutdown a CPU
+ *
+ * Called with IRQs disabled
+ */
+void __ref armada_xp_cpu_die(unsigned int cpu)
+{
+	cpu_do_idle();
+
+	/* We should never return from idle */
+	panic("mvebu: cpu %d unexpectedly exit from shutdown\n", cpu);
+}

arch/arm/mach-mvebu/irq-armada-370-xp.c

@@ -24,6 +24,7 @@
 #include <linux/irqdomain.h>
 #include <asm/mach/arch.h>
 #include <asm/exception.h>
+#include <asm/smp_plat.h>
 
 /* Interrupt Controller Registers Map */
 #define ARMADA_370_XP_INT_SET_MASK_OFFS		(0x48)
@@ -35,6 +36,12 @@
 
 #define ARMADA_370_XP_CPU_INTACK_OFFS		(0x44)
 
+#define ARMADA_370_XP_SW_TRIG_INT_OFFS           (0x4)
+#define ARMADA_370_XP_IN_DRBEL_MSK_OFFS          (0xc)
+#define ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS        (0x8)
+
+#define ACTIVE_DOORBELLS			(8)
+
 static void __iomem *per_cpu_int_base;
 static void __iomem *main_int_base;
 static struct irq_domain *armada_370_xp_mpic_domain;
@@ -51,11 +58,22 @@ static void armada_370_xp_irq_unmask(struct irq_data *d)
 	       per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
 }
 
+#ifdef CONFIG_SMP
+static int armada_xp_set_affinity(struct irq_data *d,
+				  const struct cpumask *mask_val, bool force)
+{
+	return 0;
+}
+#endif
+
 static struct irq_chip armada_370_xp_irq_chip = {
 	.name		= "armada_370_xp_irq",
 	.irq_mask       = armada_370_xp_irq_mask,
 	.irq_mask_ack   = armada_370_xp_irq_mask,
 	.irq_unmask     = armada_370_xp_irq_unmask,
+#ifdef CONFIG_SMP
+	.irq_set_affinity = armada_xp_set_affinity,
+#endif
 };
 
 static int armada_370_xp_mpic_irq_map(struct irq_domain *h,
@@ -72,6 +90,41 @@ static int armada_370_xp_mpic_irq_map(struct irq_domain *h,
 	return 0;
 }
 
+#ifdef CONFIG_SMP
+void armada_mpic_send_doorbell(const struct cpumask *mask, unsigned int irq)
+{
+	int cpu;
+	unsigned long map = 0;
+
+	/* Convert our logical CPU mask into a physical one. */
+	for_each_cpu(cpu, mask)
+		map |= 1 << cpu_logical_map(cpu);
+
+	/*
+	 * Ensure that stores to Normal memory are visible to the
+	 * other CPUs before issuing the IPI.
+	 */
+	dsb();
+
+	/* submit softirq */
+	writel((map << 8) | irq, main_int_base +
+		ARMADA_370_XP_SW_TRIG_INT_OFFS);
+}
+
+void armada_xp_mpic_smp_cpu_init(void)
+{
+	/* Clear pending IPIs */
+	writel(0, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS);
+
+	/* Enable first 8 IPIs */
+	writel((1 << ACTIVE_DOORBELLS) - 1, per_cpu_int_base +
+		ARMADA_370_XP_IN_DRBEL_MSK_OFFS);
+
+	/* Unmask IPI interrupt */
+	writel(0, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
+}
+#endif /* CONFIG_SMP */
+
 static struct irq_domain_ops armada_370_xp_mpic_irq_ops = {
 	.map = armada_370_xp_mpic_irq_map,
 	.xlate = irq_domain_xlate_onecell,
@@ -91,13 +144,18 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node,
 	control = readl(main_int_base + ARMADA_370_XP_INT_CONTROL);
 
 	armada_370_xp_mpic_domain =
-	    irq_domain_add_linear(node, (control >> 2) & 0x3ff,
-				  &armada_370_xp_mpic_irq_ops, NULL);
+		irq_domain_add_linear(node, (control >> 2) & 0x3ff,
+				&armada_370_xp_mpic_irq_ops, NULL);
 
 	if (!armada_370_xp_mpic_domain)
 		panic("Unable to add Armada_370_Xp MPIC irq domain (DT)\n");
 
 	irq_set_default_host(armada_370_xp_mpic_domain);
+
+#ifdef CONFIG_SMP
+	armada_xp_mpic_smp_cpu_init();
+#endif
+
 	return 0;
 }
 
@@ -111,14 +169,36 @@ asmlinkage void __exception_irq_entry armada_370_xp_handle_irq(struct pt_regs
 					ARMADA_370_XP_CPU_INTACK_OFFS);
 		irqnr = irqstat & 0x3FF;
 
-		if (irqnr < 1023) {
-			irqnr =
-			    irq_find_mapping(armada_370_xp_mpic_domain, irqnr);
+		if (irqnr > 1022)
+			break;
+
+		if (irqnr >= 8) {
+			irqnr =	irq_find_mapping(armada_370_xp_mpic_domain,
+					irqnr);
 			handle_IRQ(irqnr, regs);
 			continue;
 		}
+#ifdef CONFIG_SMP
+		/* IPI Handling */
+		if (irqnr == 0) {
+			u32 ipimask, ipinr;
+
+			ipimask = readl_relaxed(per_cpu_int_base +
+						ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS)
+				& 0xFF;
+
+			writel(0x0, per_cpu_int_base +
+				ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS);
+
+			/* Handle all pending doorbells */
+			for (ipinr = 0; ipinr < ACTIVE_DOORBELLS; ipinr++) {
+				if (ipimask & (0x1 << ipinr))
+					handle_IPI(ipinr, regs);
+			}
+			continue;
+		}
+#endif
 
-		break;
 	} while (1);
 }
 

arch/arm/mach-mvebu/platsmp.c

@@ -0,0 +1,122 @@
+/*
+ * Symmetric Multi Processing (SMP) support for Armada XP
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Lior Amsalem <alior@marvell.com>
+ * Yehuda Yitschak <yehuday@marvell.com>
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ *
+ * The Armada XP SoC has 4 ARMv7 PJ4B CPUs running in full HW coherency
+ * This file implements the routines for preparing the SMP infrastructure
+ * and waking up the secondary CPUs
+ */
+
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <asm/cacheflush.h>
+#include <asm/smp_plat.h>
+#include "common.h"
+#include "armada-370-xp.h"
+#include "pmsu.h"
+#include "coherency.h"
+
+void __init set_secondary_cpus_clock(void)
+{
+	int thiscpu;
+	unsigned long rate;
+	struct clk *cpu_clk = NULL;
+	struct device_node *np = NULL;
+
+	thiscpu = smp_processor_id();
+	for_each_node_by_type(np, "cpu") {
+		int err;
+		int cpu;
+
+		err = of_property_read_u32(np, "reg", &cpu);
+		if (WARN_ON(err))
+			return;
+
+		if (cpu == thiscpu) {
+			cpu_clk = of_clk_get(np, 0);
+			break;
+		}
+	}
+	if (WARN_ON(IS_ERR(cpu_clk)))
+		return;
+	clk_prepare_enable(cpu_clk);
+	rate = clk_get_rate(cpu_clk);
+
+	/* set all the other CPU clk to the same rate than the boot CPU */
+	for_each_node_by_type(np, "cpu") {
+		int err;
+		int cpu;
+
+		err = of_property_read_u32(np, "reg", &cpu);
+		if (WARN_ON(err))
+			return;
+
+		if (cpu != thiscpu) {
+			cpu_clk = of_clk_get(np, 0);
+			clk_set_rate(cpu_clk, rate);
+		}
+	}
+}
+
+static void __cpuinit armada_xp_secondary_init(unsigned int cpu)
+{
+	armada_xp_mpic_smp_cpu_init();
+}
+
+static int __cpuinit armada_xp_boot_secondary(unsigned int cpu,
+					      struct task_struct *idle)
+{
+	pr_info("Booting CPU %d\n", cpu);
+
+	armada_xp_boot_cpu(cpu, armada_xp_secondary_startup);
+
+	return 0;
+}
+
+static void __init armada_xp_smp_init_cpus(void)
+{
+	unsigned int i, ncores;
+	ncores = coherency_get_cpu_count();
+
+	/* Limit possible CPUs to defconfig */
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %d CPUs physically present. Only %d configured.",
+			ncores, nr_cpu_ids);
+		pr_warn("Clipping CPU count to %d\n", nr_cpu_ids);
+		ncores = nr_cpu_ids;
+	}
+
+	for (i = 0; i < ncores; i++)
+		set_cpu_possible(i, true);
+
+	set_smp_cross_call(armada_mpic_send_doorbell);
+}
+
+void __init armada_xp_smp_prepare_cpus(unsigned int max_cpus)
+{
+	set_secondary_cpus_clock();
+	flush_cache_all();
+	set_cpu_coherent(cpu_logical_map(smp_processor_id()), 0);
+}
+
+struct smp_operations armada_xp_smp_ops __initdata = {
+	.smp_init_cpus		= armada_xp_smp_init_cpus,
+	.smp_prepare_cpus	= armada_xp_smp_prepare_cpus,
+	.smp_secondary_init	= armada_xp_secondary_init,
+	.smp_boot_secondary	= armada_xp_boot_secondary,
+#ifdef CONFIG_HOTPLUG_CPU
+	.cpu_die		= armada_xp_cpu_die,
+#endif
+};

arch/arm/mach-mvebu/pmsu.c

@@ -0,0 +1,75 @@
+/*
+ * Power Management Service Unit(PMSU) support for Armada 370/XP platforms.
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Yehuda Yitschak <yehuday@marvell.com>
+ * Gregory Clement <gregory.clement@free-electrons.com>
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ *
+ * The Armada 370 and Armada XP SOCs have a power management service
+ * unit which is responsible for powering down and waking up CPUs and
+ * other SOC units
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/of_address.h>
+#include <linux/io.h>
+#include <linux/smp.h>
+#include <asm/smp_plat.h>
+
+static void __iomem *pmsu_mp_base;
+static void __iomem *pmsu_reset_base;
+
+#define PMSU_BOOT_ADDR_REDIRECT_OFFSET(cpu)	((cpu * 0x100) + 0x24)
+#define PMSU_RESET_CTL_OFFSET(cpu)		(cpu * 0x8)
+
+static struct of_device_id of_pmsu_table[] = {
+	{.compatible = "marvell,armada-370-xp-pmsu"},
+	{ /* end of list */ },
+};
+
+#ifdef CONFIG_SMP
+int armada_xp_boot_cpu(unsigned int cpu_id, void *boot_addr)
+{
+	int reg, hw_cpu;
+
+	if (!pmsu_mp_base || !pmsu_reset_base) {
+		pr_warn("Can't boot CPU. PMSU is uninitialized\n");
+		return 1;
+	}
+
+	hw_cpu = cpu_logical_map(cpu_id);
+
+	writel(virt_to_phys(boot_addr), pmsu_mp_base +
+			PMSU_BOOT_ADDR_REDIRECT_OFFSET(hw_cpu));
+
+	/* Release CPU from reset by clearing reset bit*/
+	reg = readl(pmsu_reset_base + PMSU_RESET_CTL_OFFSET(hw_cpu));
+	reg &= (~0x1);
+	writel(reg, pmsu_reset_base + PMSU_RESET_CTL_OFFSET(hw_cpu));
+
+	return 0;
+}
+#endif
+
+int __init armada_370_xp_pmsu_init(void)
+{
+	struct device_node *np;
+
+	np = of_find_matching_node(NULL, of_pmsu_table);
+	if (np) {
+		pr_info("Initializing Power Management Service Unit\n");
+		pmsu_mp_base = of_iomap(np, 0);
+		pmsu_reset_base = of_iomap(np, 1);
+	}
+
+	return 0;
+}
+
+early_initcall(armada_370_xp_pmsu_init);

arch/arm/mach-mvebu/pmsu.h

@@ -0,0 +1,16 @@
+/*
+ * Power Management Service Unit (PMSU) support for Armada 370/XP platforms.
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#ifndef __MACH_MVEBU_PMSU_H
+#define __MACH_MVEBU_PMSU_H
+
+int armada_xp_boot_cpu(unsigned int cpu_id, void *phys_addr);
+
+#endif	/* __MACH_370_XP_PMSU_H */

arch/arm/mm/Kconfig

@@ -352,6 +352,10 @@ config CPU_PJ4
 	select ARM_THUMBEE
 	select CPU_V7
 
+config CPU_PJ4B
+	bool
+	select CPU_V7
+
 # ARMv6
 config CPU_V6
 	bool "Support ARM V6 processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB || MACH_REALVIEW_PBX

arch/arm/mm/proc-v7.S

@@ -169,6 +169,63 @@ __v7_ca15mp_setup:
 	orreq	r0, r0, r10			@ Enable CPU-specific SMP bits
 	mcreq	p15, 0, r0, c1, c0, 1
 #endif
+
+__v7_pj4b_setup:
+#ifdef CONFIG_CPU_PJ4B
+
+/* Auxiliary Debug Modes Control 1 Register */
+#define PJ4B_STATIC_BP (1 << 2) /* Enable Static BP */
+#define PJ4B_INTER_PARITY (1 << 8) /* Disable Internal Parity Handling */
+#define PJ4B_BCK_OFF_STREX (1 << 5) /* Enable the back off of STREX instr */
+#define PJ4B_CLEAN_LINE (1 << 16) /* Disable data transfer for clean line */
+
+/* Auxiliary Debug Modes Control 2 Register */
+#define PJ4B_FAST_LDR (1 << 23) /* Disable fast LDR */
+#define PJ4B_SNOOP_DATA (1 << 25) /* Do not interleave write and snoop data */
+#define PJ4B_CWF (1 << 27) /* Disable Critical Word First feature */
+#define PJ4B_OUTSDNG_NC (1 << 29) /* Disable outstanding non cacheable rqst */
+#define PJ4B_L1_REP_RR (1 << 30) /* L1 replacement - Strict round robin */
+#define PJ4B_AUX_DBG_CTRL2 (PJ4B_SNOOP_DATA | PJ4B_CWF |\
+			    PJ4B_OUTSDNG_NC | PJ4B_L1_REP_RR)
+
+/* Auxiliary Functional Modes Control Register 0 */
+#define PJ4B_SMP_CFB (1 << 1) /* Set SMP mode. Join the coherency fabric */
+#define PJ4B_L1_PAR_CHK (1 << 2) /* Support L1 parity checking */
+#define PJ4B_BROADCAST_CACHE (1 << 8) /* Broadcast Cache and TLB maintenance */
+
+/* Auxiliary Debug Modes Control 0 Register */
+#define PJ4B_WFI_WFE (1 << 22) /* WFI/WFE - serve the DVM and back to idle */
+
+	/* Auxiliary Debug Modes Control 1 Register */
+	mrc	p15, 1,	r0, c15, c1, 1
+	orr     r0, r0, #PJ4B_CLEAN_LINE
+	orr     r0, r0, #PJ4B_BCK_OFF_STREX
+	orr     r0, r0, #PJ4B_INTER_PARITY
+	bic	r0, r0, #PJ4B_STATIC_BP
+	mcr	p15, 1,	r0, c15, c1, 1
+
+	/* Auxiliary Debug Modes Control 2 Register */
+	mrc	p15, 1,	r0, c15, c1, 2
+	bic	r0, r0, #PJ4B_FAST_LDR
+	orr	r0, r0, #PJ4B_AUX_DBG_CTRL2
+	mcr	p15, 1,	r0, c15, c1, 2
+
+	/* Auxiliary Functional Modes Control Register 0 */
+	mrc	p15, 1,	r0, c15, c2, 0
+#ifdef CONFIG_SMP
+	orr	r0, r0, #PJ4B_SMP_CFB
+#endif
+	orr	r0, r0, #PJ4B_L1_PAR_CHK
+	orr	r0, r0, #PJ4B_BROADCAST_CACHE
+	mcr	p15, 1,	r0, c15, c2, 0
+
+	/* Auxiliary Debug Modes Control 0 Register */
+	mrc	p15, 1,	r0, c15, c1, 0
+	orr	r0, r0, #PJ4B_WFI_WFE
+	mcr	p15, 1,	r0, c15, c1, 0
+
+#endif /* CONFIG_CPU_PJ4B */
+
 __v7_setup:
 	adr	r12, __v7_setup_stack		@ the local stack
 	stmia	r12, {r0-r5, r7, r9, r11, lr}
@@ -342,6 +399,16 @@ __v7_ca9mp_proc_info:
 	.long	0xff0ffff0
 	__v7_proc __v7_ca9mp_setup
 	.size	__v7_ca9mp_proc_info, . - __v7_ca9mp_proc_info
+
+	/*
+	 * Marvell PJ4B processor.
+	 */
+	.type   __v7_pj4b_proc_info, #object
+__v7_pj4b_proc_info:
+	.long	0x562f5840
+	.long	0xfffffff0
+	__v7_proc __v7_pj4b_setup
+	.size	__v7_pj4b_proc_info, . - __v7_pj4b_proc_info
 #endif	/* CONFIG_ARM_LPAE */
 
 	/*