diff --git a/arch/arm/mach-shmobile/include/mach/common.h b/arch/arm/mach-shmobile/include/mach/common.h
index cfe3977..3460bb1 100644
--- a/arch/arm/mach-shmobile/include/mach/common.h
+++ b/arch/arm/mach-shmobile/include/mach/common.h
@@ -22,6 +22,12 @@
 					   struct task_struct *idle);
 extern void shmobile_smp_scu_cpu_die(unsigned int cpu);
 extern int shmobile_smp_scu_cpu_kill(unsigned int cpu);
+extern void shmobile_smp_apmu_prepare_cpus(unsigned int max_cpus);
+extern int shmobile_smp_apmu_boot_secondary(unsigned int cpu,
+					    struct task_struct *idle);
+extern void shmobile_smp_apmu_cpu_die(unsigned int cpu);
+extern int shmobile_smp_apmu_cpu_kill(unsigned int cpu);
+extern void shmobile_invalidate_start(void);
 struct clk;
 extern int shmobile_clk_init(void);
 extern void shmobile_handle_irq_intc(struct pt_regs *);
diff --git a/arch/arm/mach-shmobile/platsmp-apmu.c b/arch/arm/mach-shmobile/platsmp-apmu.c
new file mode 100644
index 0000000..34dc40d
--- /dev/null
+++ b/arch/arm/mach-shmobile/platsmp-apmu.c
@@ -0,0 +1,178 @@
+/*
+ * SMP support for SoCs with APMU
+ *
+ * Copyright (C) 2013  Magnus Damm
+ *
+ * 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/delay.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/of_address.h>
+#include <linux/smp.h>
+#include <asm/cacheflush.h>
+#include <asm/cp15.h>
+#include <asm/smp_plat.h>
+#include <mach/common.h>
+
+static struct {
+	void __iomem *iomem;
+	int bit;
+} apmu_cpus[CONFIG_NR_CPUS];
+
+#define WUPCR_OFFS 0x10
+#define PSTR_OFFS 0x40
+#define CPUNCR_OFFS(n) (0x100 + (0x10 * (n)))
+
+static int apmu_power_on(void __iomem *p, int bit)
+{
+	/* request power on */
+	writel_relaxed(BIT(bit), p + WUPCR_OFFS);
+
+	/* wait for APMU to finish */
+	while (readl_relaxed(p + WUPCR_OFFS) != 0)
+		;
+
+	return 0;
+}
+
+static int apmu_power_off(void __iomem *p, int bit)
+{
+	/* request Core Standby for next WFI */
+	writel_relaxed(3, p + CPUNCR_OFFS(bit));
+	return 0;
+}
+
+static int apmu_power_off_poll(void __iomem *p, int bit)
+{
+	int k;
+
+	for (k = 0; k < 1000; k++) {
+		if (((readl_relaxed(p + PSTR_OFFS) >> (bit * 4)) & 0x03) == 3)
+			return 1;
+
+		mdelay(1);
+	}
+
+	return 0;
+}
+
+static int apmu_wrap(int cpu, int (*fn)(void __iomem *p, int cpu))
+{
+	void __iomem *p = apmu_cpus[cpu].iomem;
+
+	return p ? fn(p, apmu_cpus[cpu].bit) : -EINVAL;
+}
+
+static void apmu_init_cpu(struct resource *res, int cpu, int bit)
+{
+	if (apmu_cpus[cpu].iomem)
+		return;
+
+	apmu_cpus[cpu].iomem = ioremap_nocache(res->start, resource_size(res));
+	apmu_cpus[cpu].bit = bit;
+
+	pr_debug("apmu ioremap %d %d 0x%08x 0x%08x\n", cpu, bit,
+		 res->start, resource_size(res));
+}
+
+static struct {
+	struct resource iomem;
+	int cpus[4];
+} apmu_config[] = {
+	{
+		.iomem = DEFINE_RES_MEM(0xe6152000, 0x88),
+		.cpus = { 0, 1, 2, 3 },
+	}
+};
+
+static void apmu_parse_cfg(void (*fn)(struct resource *res, int cpu, int bit))
+{
+	u32 id;
+	int k;
+	int bit, index;
+
+	for (k = 0; k < ARRAY_SIZE(apmu_config); k++) {
+		for (bit = 0; bit < ARRAY_SIZE(apmu_config[k].cpus); bit++) {
+			id = apmu_config[k].cpus[bit];
+			if (id >= 0) {
+				index = get_logical_index(id);
+				if (index >= 0)
+					fn(&apmu_config[k].iomem, index, bit);
+			}
+		}
+	}
+}
+
+void __init shmobile_smp_apmu_prepare_cpus(unsigned int max_cpus)
+{
+	/* install boot code shared by all CPUs */
+	shmobile_boot_fn = virt_to_phys(shmobile_smp_boot);
+	shmobile_boot_arg = MPIDR_HWID_BITMASK;
+
+	/* perform per-cpu setup */
+	apmu_parse_cfg(apmu_init_cpu);
+}
+
+int shmobile_smp_apmu_boot_secondary(unsigned int cpu, struct task_struct *idle)
+{
+	/* For this particular CPU register boot vector */
+	shmobile_smp_hook(cpu, virt_to_phys(shmobile_invalidate_start), 0);
+
+	return apmu_wrap(cpu, apmu_power_on);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+/* nicked from arch/arm/mach-exynos/hotplug.c */
+static inline void cpu_enter_lowpower_a15(void)
+{
+	unsigned int v;
+
+	asm volatile(
+	"       mrc     p15, 0, %0, c1, c0, 0\n"
+	"       bic     %0, %0, %1\n"
+	"       mcr     p15, 0, %0, c1, c0, 0\n"
+		: "=&r" (v)
+		: "Ir" (CR_C)
+		: "cc");
+
+	flush_cache_louis();
+
+	asm volatile(
+	/*
+	 * Turn off coherency
+	 */
+	"       mrc     p15, 0, %0, c1, c0, 1\n"
+	"       bic     %0, %0, %1\n"
+	"       mcr     p15, 0, %0, c1, c0, 1\n"
+		: "=&r" (v)
+		: "Ir" (0x40)
+		: "cc");
+
+	isb();
+	dsb();
+}
+
+void shmobile_smp_apmu_cpu_die(unsigned int cpu)
+{
+	/* For this particular CPU deregister boot vector */
+	shmobile_smp_hook(cpu, 0, 0);
+
+	/* Select next sleep mode using the APMU */
+	apmu_wrap(cpu, apmu_power_off);
+
+	/* Do ARM specific CPU shutdown */
+	cpu_enter_lowpower_a15();
+
+	/* jump to shared mach-shmobile sleep / reset code */
+	shmobile_smp_sleep();
+}
+
+int shmobile_smp_apmu_cpu_kill(unsigned int cpu)
+{
+	return apmu_wrap(cpu, apmu_power_off_poll);
+}
+#endif