Merge tag 'arm64-suspend' of git://linux-arm.org/linux-2.6-lp into upstream

* tag 'arm64-suspend' of git://linux-arm.org/linux-2.6-lp:
  arm64: add CPU power management menu/entries
  arm64: kernel: add PM build infrastructure
  arm64: kernel: add CPU idle call
  arm64: enable generic clockevent broadcast
  arm64: kernel: implement HW breakpoints CPU PM notifier
  arm64: kernel: refactor code to install/uninstall breakpoints
  arm: kvm: implement CPU PM notifier
  arm64: kernel: implement fpsimd CPU PM notifier
  arm64: kernel: cpu_{suspend/resume} implementation
  arm64: kernel: suspend/resume registers save/restore
  arm64: kernel: build MPIDR_EL1 hash function data structure
  arm64: kernel: add MPIDR_EL1 accessors macros

Conflicts:
	arch/arm64/Kconfig

17 files changed, 737 insertions, 70 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 101683d336c9..249acb9da4e3 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -2,6 +2,7 @@ config ARM64
 	def_bool y
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select ARCH_USE_CMPXCHG_LOCKREF
+	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	select ARCH_WANT_FRAME_POINTERS
@@ -11,8 +12,10 @@ config ARM64
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS
 	select COMMON_CLK
+	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select DCACHE_WORD_ACCESS
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
 	select GENERIC_IOMAP
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
@@ -280,6 +283,24 @@ config SYSVIPC_COMPAT
 
 endmenu
 
+menu "Power management options"
+
+source "kernel/power/Kconfig"
+
+config ARCH_SUSPEND_POSSIBLE
+	def_bool y
+
+config ARM64_CPU_SUSPEND
+	def_bool PM_SLEEP
+
+endmenu
+
+menu "CPU Power Management"
+
+source "drivers/cpuidle/Kconfig"
+
+endmenu
+
 source "net/Kconfig"
 
 source "drivers/Kconfig"
diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h
index c4cdb5e5b73d..152413076503 100644
--- a/arch/arm64/include/asm/cpu_ops.h
+++ b/arch/arm64/include/asm/cpu_ops.h
@@ -39,6 +39,9 @@ struct device_node;
  * 		from the cpu to be killed.
  * @cpu_die:	Makes a cpu leave the kernel. Must not fail. Called from the
  *		cpu being killed.
+ * @cpu_suspend: Suspends a cpu and saves the required context. May fail owing
+ *               to wrong parameters or error conditions. Called from the
+ *               CPU being suspended. Must be called with IRQs disabled.
  */
 struct cpu_operations {
 	const char	*name;
@@ -50,6 +53,9 @@ struct cpu_operations {
 	int		(*cpu_disable)(unsigned int cpu);
 	void		(*cpu_die)(unsigned int cpu);
 #endif
+#ifdef CONFIG_ARM64_CPU_SUSPEND
+	int		(*cpu_suspend)(unsigned long);
+#endif
 };
 
 extern const struct cpu_operations *cpu_ops[NR_CPUS];
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index e1af1b4200d5..c404fb0df3a6 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -20,6 +20,16 @@
 
 #define MPIDR_HWID_BITMASK	0xff00ffffff
 
+#define MPIDR_LEVEL_BITS_SHIFT	3
+#define MPIDR_LEVEL_BITS	(1 << MPIDR_LEVEL_BITS_SHIFT)
+#define MPIDR_LEVEL_MASK	((1 << MPIDR_LEVEL_BITS) - 1)
+
+#define MPIDR_LEVEL_SHIFT(level) \
+	(((1 << level) >> 1) << MPIDR_LEVEL_BITS_SHIFT)
+
+#define MPIDR_AFFINITY_LEVEL(mpidr, level) \
+	((mpidr >> MPIDR_LEVEL_SHIFT(level)) & MPIDR_LEVEL_MASK)
+
 #define read_cpuid(reg) ({						\
 	u64 __val;							\
 	asm("mrs	%0, " #reg : "=r" (__val));			\
diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h
index 990c051e7829..ae4801d77514 100644
--- a/arch/arm64/include/asm/hardirq.h
+++ b/arch/arm64/include/asm/hardirq.h
@@ -20,7 +20,7 @@
 #include <linux/threads.h>
 #include <asm/irq.h>
 
-#define NR_IPI	4
+#define NR_IPI	5
 
 typedef struct {
 	unsigned int __softirq_pending;
diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
index 7cdf466fd0c5..0c657bb54597 100644
--- a/arch/arm64/include/asm/proc-fns.h
+++ b/arch/arm64/include/asm/proc-fns.h
@@ -26,11 +26,14 @@
 #include <asm/page.h>
 
 struct mm_struct;
+struct cpu_suspend_ctx;
 
 extern void cpu_cache_off(void);
 extern void cpu_do_idle(void);
 extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
 extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
+extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr);
+extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
 
 #include <asm/memory.h>
 
diff --git a/arch/arm64/include/asm/smp_plat.h b/arch/arm64/include/asm/smp_plat.h
index ed43a0d2b1b2..59e282311b58 100644
--- a/arch/arm64/include/asm/smp_plat.h
+++ b/arch/arm64/include/asm/smp_plat.h
@@ -21,6 +21,19 @@
 
 #include <asm/types.h>
 
+struct mpidr_hash {
+	u64	mask;
+	u32	shift_aff[4];
+	u32	bits;
+};
+
+extern struct mpidr_hash mpidr_hash;
+
+static inline u32 mpidr_hash_size(void)
+{
+	return 1 << mpidr_hash.bits;
+}
+
 /*
  * Logical CPU mapping.
  */
diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h
new file mode 100644
index 000000000000..e9c149c042e0
--- /dev/null
+++ b/arch/arm64/include/asm/suspend.h
@@ -0,0 +1,27 @@
+#ifndef __ASM_SUSPEND_H
+#define __ASM_SUSPEND_H
+
+#define NR_CTX_REGS 11
+
+/*
+ * struct cpu_suspend_ctx must be 16-byte aligned since it is allocated on
+ * the stack, which must be 16-byte aligned on v8
+ */
+struct cpu_suspend_ctx {
+	/*
+	 * This struct must be kept in sync with
+	 * cpu_do_{suspend/resume} in mm/proc.S
+	 */
+	u64 ctx_regs[NR_CTX_REGS];
+	u64 sp;
+} __aligned(16);
+
+struct sleep_save_sp {
+	phys_addr_t *save_ptr_stash;
+	phys_addr_t save_ptr_stash_phys;
+};
+
+extern void cpu_resume(void);
+extern int cpu_suspend(unsigned long);
+
+#endif
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 5ba2fd43a75b..1cd339d5037b 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -18,6 +18,7 @@ arm64-obj-$(CONFIG_SMP)			+= smp.o smp_spin_table.o
 arm64-obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o
 arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)+= hw_breakpoint.o
 arm64-obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
+arm64-obj-$(CONFIG_ARM64_CPU_SUSPEND)	+= sleep.o suspend.o
 
 obj-y					+= $(arm64-obj-y) vdso/
 obj-m					+= $(arm64-obj-m)
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 666e231d410b..646f888387cd 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -25,6 +25,8 @@
 #include <asm/thread_info.h>
 #include <asm/memory.h>
 #include <asm/cputable.h>
+#include <asm/smp_plat.h>
+#include <asm/suspend.h>
 #include <asm/vdso_datapage.h>
 #include <linux/kbuild.h>
 
@@ -138,5 +140,14 @@ int main(void)
   DEFINE(KVM_VTTBR,		offsetof(struct kvm, arch.vttbr));
   DEFINE(KVM_VGIC_VCTRL,	offsetof(struct kvm, arch.vgic.vctrl_base));
 #endif
+#ifdef CONFIG_ARM64_CPU_SUSPEND
+  DEFINE(CPU_SUSPEND_SZ,	sizeof(struct cpu_suspend_ctx));
+  DEFINE(CPU_CTX_SP,		offsetof(struct cpu_suspend_ctx, sp));
+  DEFINE(MPIDR_HASH_MASK,	offsetof(struct mpidr_hash, mask));
+  DEFINE(MPIDR_HASH_SHIFTS,	offsetof(struct mpidr_hash, shift_aff));
+  DEFINE(SLEEP_SAVE_SP_SZ,	sizeof(struct sleep_save_sp));
+  DEFINE(SLEEP_SAVE_SP_PHYS,	offsetof(struct sleep_save_sp, save_ptr_stash_phys));
+  DEFINE(SLEEP_SAVE_SP_VIRT,	offsetof(struct sleep_save_sp, save_ptr_stash));
+#endif
   return 0;
 }
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index bb785d23dbde..4aef42a04bdc 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -17,6 +17,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/cpu_pm.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/sched.h>
@@ -113,6 +114,39 @@ EXPORT_SYMBOL(kernel_neon_end);
 
 #endif /* CONFIG_KERNEL_MODE_NEON */
 
+#ifdef CONFIG_CPU_PM
+static int fpsimd_cpu_pm_notifier(struct notifier_block *self,
+				  unsigned long cmd, void *v)
+{
+	switch (cmd) {
+	case CPU_PM_ENTER:
+		if (current->mm)
+			fpsimd_save_state(&current->thread.fpsimd_state);
+		break;
+	case CPU_PM_EXIT:
+		if (current->mm)
+			fpsimd_load_state(&current->thread.fpsimd_state);
+		break;
+	case CPU_PM_ENTER_FAILED:
+	default:
+		return NOTIFY_DONE;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block fpsimd_cpu_pm_notifier_block = {
+	.notifier_call = fpsimd_cpu_pm_notifier,
+};
+
+static void fpsimd_pm_init(void)
+{
+	cpu_pm_register_notifier(&fpsimd_cpu_pm_notifier_block);
+}
+
+#else
+static inline void fpsimd_pm_init(void) { }
+#endif /* CONFIG_CPU_PM */
+
 /*
  * FP/SIMD support code initialisation.
  */
@@ -131,6 +165,8 @@ static int __init fpsimd_init(void)
 	else
 		elf_hwcap |= HWCAP_ASIMD;
 
+	fpsimd_pm_init();
+
 	return 0;
 }
 late_initcall(fpsimd_init);
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index ff516f6691e4..bcaaac9e14d6 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -20,6 +20,7 @@
 
 #define pr_fmt(fmt) "hw-breakpoint: " fmt
 
+#include <linux/cpu_pm.h>
 #include <linux/errno.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/perf_event.h>
@@ -169,15 +170,68 @@ static enum debug_el debug_exception_level(int privilege)
 	}
 }
 
-/*
- * Install a perf counter breakpoint.
+enum hw_breakpoint_ops {
+	HW_BREAKPOINT_INSTALL,
+	HW_BREAKPOINT_UNINSTALL,
+	HW_BREAKPOINT_RESTORE
+};
+
+/**
+ * hw_breakpoint_slot_setup - Find and setup a perf slot according to
+ *			      operations
+ *
+ * @slots: pointer to array of slots
+ * @max_slots: max number of slots
+ * @bp: perf_event to setup
+ * @ops: operation to be carried out on the slot
+ *
+ * Return:
+ *	slot index on success
+ *	-ENOSPC if no slot is available/matches
+ *	-EINVAL on wrong operations parameter
  */
-int arch_install_hw_breakpoint(struct perf_event *bp)
+static int hw_breakpoint_slot_setup(struct perf_event **slots, int max_slots,
+				    struct perf_event *bp,
+				    enum hw_breakpoint_ops ops)
+{
+	int i;
+	struct perf_event **slot;
+
+	for (i = 0; i < max_slots; ++i) {
+		slot = &slots[i];
+		switch (ops) {
+		case HW_BREAKPOINT_INSTALL:
+			if (!*slot) {
+				*slot = bp;
+				return i;
+			}
+			break;
+		case HW_BREAKPOINT_UNINSTALL:
+			if (*slot == bp) {
+				*slot = NULL;
+				return i;
+			}
+			break;
+		case HW_BREAKPOINT_RESTORE:
+			if (*slot == bp)
+				return i;
+			break;
+		default:
+			pr_warn_once("Unhandled hw breakpoint ops %d\n", ops);
+			return -EINVAL;
+		}
+	}
+	return -ENOSPC;
+}
+
+static int hw_breakpoint_control(struct perf_event *bp,
+				 enum hw_breakpoint_ops ops)
 {
 	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-	struct perf_event **slot, **slots;
+	struct perf_event **slots;
 	struct debug_info *debug_info = &current->thread.debug;
 	int i, max_slots, ctrl_reg, val_reg, reg_enable;
+	enum debug_el dbg_el = debug_exception_level(info->ctrl.privilege);
 	u32 ctrl;
 
 	if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
@@ -196,67 +250,54 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 		reg_enable = !debug_info->wps_disabled;
 	}
 
-	for (i = 0; i < max_slots; ++i) {
-		slot = &slots[i];
+	i = hw_breakpoint_slot_setup(slots, max_slots, bp, ops);
 
-		if (!*slot) {
-			*slot = bp;
-			break;
-		}
-	}
+	if (WARN_ONCE(i < 0, "Can't find any breakpoint slot"))
+		return i;
 
-	if (WARN_ONCE(i == max_slots, "Can't find any breakpoint slot"))
-		return -ENOSPC;
-
-	/* Ensure debug monitors are enabled at the correct exception level.  */
-	enable_debug_monitors(debug_exception_level(info->ctrl.privilege));
-
-	/* Setup the address register. */
-	write_wb_reg(val_reg, i, info->address);
+	switch (ops) {
+	case HW_BREAKPOINT_INSTALL:
+		/*
+		 * Ensure debug monitors are enabled at the correct exception
+		 * level.
+		 */
+		enable_debug_monitors(dbg_el);
+		/* Fall through */
+	case HW_BREAKPOINT_RESTORE:
+		/* Setup the address register. */
+		write_wb_reg(val_reg, i, info->address);
+
+		/* Setup the control register. */
+		ctrl = encode_ctrl_reg(info->ctrl);
+		write_wb_reg(ctrl_reg, i,
+			     reg_enable ? ctrl | 0x1 : ctrl & ~0x1);
+		break;
+	case HW_BREAKPOINT_UNINSTALL:
+		/* Reset the control register. */
+		write_wb_reg(ctrl_reg, i, 0);
 
-	/* Setup the control register. */
-	ctrl = encode_ctrl_reg(info->ctrl);
-	write_wb_reg(ctrl_reg, i, reg_enable ? ctrl | 0x1 : ctrl & ~0x1);
+		/*
+		 * Release the debug monitors for the correct exception
+		 * level.
+		 */
+		disable_debug_monitors(dbg_el);
+		break;
+	}
 
 	return 0;
 }
 
-void arch_uninstall_hw_breakpoint(struct perf_event *bp)
+/*
+ * Install a perf counter breakpoint.
+ */
+int arch_install_hw_breakpoint(struct perf_event *bp)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-	struct perf_event **slot, **slots;
-	int i, max_slots, base;
-
-	if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
-		/* Breakpoint */
-		base = AARCH64_DBG_REG_BCR;
-		slots = this_cpu_ptr(bp_on_reg);
-		max_slots = core_num_brps;
-	} else {
-		/* Watchpoint */
-		base = AARCH64_DBG_REG_WCR;
-		slots = this_cpu_ptr(wp_on_reg);
-		max_slots = core_num_wrps;
-	}
-
-	/* Remove the breakpoint. */
-	for (i = 0; i < max_slots; ++i) {
-		slot = &slots[i];
-
-		if (*slot == bp) {
-			*slot = NULL;
-			break;
-		}
-	}
-
-	if (WARN_ONCE(i == max_slots, "Can't find any breakpoint slot"))
-		return;
-
-	/* Reset the control register. */
-	write_wb_reg(base, i, 0);
+	return hw_breakpoint_control(bp, HW_BREAKPOINT_INSTALL);
+}
 
-	/* Release the debug monitors for the correct exception level.  */
-	disable_debug_monitors(debug_exception_level(info->ctrl.privilege));
+void arch_uninstall_hw_breakpoint(struct perf_event *bp)
+{
+	hw_breakpoint_control(bp, HW_BREAKPOINT_UNINSTALL);
 }
 
 static int get_hbp_len(u8 hbp_len)
@@ -806,18 +847,36 @@ void hw_breakpoint_thread_switch(struct task_struct *next)
 /*
  * CPU initialisation.
  */
-static void reset_ctrl_regs(void *unused)
+static void hw_breakpoint_reset(void *unused)
 {
 	int i;
-
-	for (i = 0; i < core_num_brps; ++i) {
-		write_wb_reg(AARCH64_DBG_REG_BCR, i, 0UL);
-		write_wb_reg(AARCH64_DBG_REG_BVR, i, 0UL);
+	struct perf_event **slots;
+	/*
+	 * When a CPU goes through cold-boot, it does not have any installed
+	 * slot, so it is safe to share the same function for restoring and
+	 * resetting breakpoints; when a CPU is hotplugged in, it goes
+	 * through the slots, which are all empty, hence it just resets control
+	 * and value for debug registers.
+	 * When this function is triggered on warm-boot through a CPU PM
+	 * notifier some slots might be initialized; if so they are
+	 * reprogrammed according to the debug slots content.
+	 */
+	for (slots = this_cpu_ptr(bp_on_reg), i = 0; i < core_num_brps; ++i) {
+		if (slots[i]) {
+			hw_breakpoint_control(slots[i], HW_BREAKPOINT_RESTORE);
+		} else {
+			write_wb_reg(AARCH64_DBG_REG_BCR, i, 0UL);
+			write_wb_reg(AARCH64_DBG_REG_BVR, i, 0UL);
+		}
 	}
 
-	for (i = 0; i < core_num_wrps; ++i) {
-		write_wb_reg(AARCH64_DBG_REG_WCR, i, 0UL);
-		write_wb_reg(AARCH64_DBG_REG_WVR, i, 0UL);
+	for (slots = this_cpu_ptr(wp_on_reg), i = 0; i < core_num_wrps; ++i) {
+		if (slots[i]) {
+			hw_breakpoint_control(slots[i], HW_BREAKPOINT_RESTORE);
+		} else {
+			write_wb_reg(AARCH64_DBG_REG_WCR, i, 0UL);
+			write_wb_reg(AARCH64_DBG_REG_WVR, i, 0UL);
+		}
 	}
 }
 
@@ -827,7 +886,7 @@ static int hw_breakpoint_reset_notify(struct notifier_block *self,
 {
 	int cpu = (long)hcpu;
 	if (action == CPU_ONLINE)
-		smp_call_function_single(cpu, reset_ctrl_regs, NULL, 1);
+		smp_call_function_single(cpu, hw_breakpoint_reset, NULL, 1);
 	return NOTIFY_OK;
 }
 
@@ -835,6 +894,33 @@ static struct notifier_block hw_breakpoint_reset_nb = {
 	.notifier_call = hw_breakpoint_reset_notify,
 };
 
+#ifdef CONFIG_CPU_PM
+static int hw_breakpoint_cpu_pm_notify(struct notifier_block *self,
+				       unsigned long action,
+				       void *v)
+{
+	if (action == CPU_PM_EXIT) {
+		hw_breakpoint_reset(NULL);
+		return NOTIFY_OK;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block hw_breakpoint_cpu_pm_nb = {
+	.notifier_call = hw_breakpoint_cpu_pm_notify,
+};
+
+static void __init hw_breakpoint_pm_init(void)
+{
+	cpu_pm_register_notifier(&hw_breakpoint_cpu_pm_nb);
+}
+#else
+static inline void hw_breakpoint_pm_init(void)
+{
+}
+#endif
+
 /*
  * One-time initialisation.
  */
@@ -850,8 +936,8 @@ static int __init arch_hw_breakpoint_init(void)
 	 * Reset the breakpoint resources. We assume that a halting
 	 * debugger will leave the world in a nice state for us.
 	 */
-	smp_call_function(reset_ctrl_regs, NULL, 1);
-	reset_ctrl_regs(NULL);
+	smp_call_function(hw_breakpoint_reset, NULL, 1);
+	hw_breakpoint_reset(NULL);
 
 	/* Register debug fault handlers. */
 	hook_debug_fault_code(DBG_ESR_EVT_HWBP, breakpoint_handler, SIGTRAP,
@@ -861,6 +947,7 @@ static int __init arch_hw_breakpoint_init(void)
 
 	/* Register hotplug notifier. */
 	register_cpu_notifier(&hw_breakpoint_reset_nb);
+	hw_breakpoint_pm_init();
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 0adb8f0f4549..248a15db37f2 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -33,6 +33,7 @@
 #include <linux/kallsyms.h>
 #include <linux/init.h>
 #include <linux/cpu.h>
+#include <linux/cpuidle.h>
 #include <linux/elfcore.h>
 #include <linux/pm.h>
 #include <linux/tick.h>
@@ -98,8 +99,10 @@ void arch_cpu_idle(void)
 	 * This should do all the clock switching and wait for interrupt
 	 * tricks
 	 */
-	cpu_do_idle();
-	local_irq_enable();
+	if (cpuidle_idle_call()) {
+		cpu_do_idle();
+		local_irq_enable();
+	}
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index bb33fff09ba2..c8e9effe52e1 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -123,6 +123,75 @@ bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
 	return phys_id == cpu_logical_map(cpu);
 }
 
+struct mpidr_hash mpidr_hash;
+#ifdef CONFIG_SMP
+/**
+ * smp_build_mpidr_hash - Pre-compute shifts required at each affinity
+ *			  level in order to build a linear index from an
+ *			  MPIDR value. Resulting algorithm is a collision
+ *			  free hash carried out through shifting and ORing
+ */
+static void __init smp_build_mpidr_hash(void)
+{
+	u32 i, affinity, fs[4], bits[4], ls;
+	u64 mask = 0;
+	/*
+	 * Pre-scan the list of MPIDRS and filter out bits that do
+	 * not contribute to affinity levels, ie they never toggle.
+	 */
+	for_each_possible_cpu(i)
+		mask |= (cpu_logical_map(i) ^ cpu_logical_map(0));
+	pr_debug("mask of set bits %#llx\n", mask);
+	/*
+	 * Find and stash the last and first bit set at all affinity levels to
+	 * check how many bits are required to represent them.
+	 */
+	for (i = 0; i < 4; i++) {
+		affinity = MPIDR_AFFINITY_LEVEL(mask, i);
+		/*
+		 * Find the MSB bit and LSB bits position
+		 * to determine how many bits are required
+		 * to express the affinity level.
+		 */
+		ls = fls(affinity);
+		fs[i] = affinity ? ffs(affinity) - 1 : 0;
+		bits[i] = ls - fs[i];
+	}
+	/*
+	 * An index can be created from the MPIDR_EL1 by isolating the
+	 * significant bits at each affinity level and by shifting
+	 * them in order to compress the 32 bits values space to a
+	 * compressed set of values. This is equivalent to hashing
+	 * the MPIDR_EL1 through shifting and ORing. It is a collision free
+	 * hash though not minimal since some levels might contain a number
+	 * of CPUs that is not an exact power of 2 and their bit
+	 * representation might contain holes, eg MPIDR_EL1[7:0] = {0x2, 0x80}.
+	 */
+	mpidr_hash.shift_aff[0] = MPIDR_LEVEL_SHIFT(0) + fs[0];
+	mpidr_hash.shift_aff[1] = MPIDR_LEVEL_SHIFT(1) + fs[1] - bits[0];
+	mpidr_hash.shift_aff[2] = MPIDR_LEVEL_SHIFT(2) + fs[2] -
+						(bits[1] + bits[0]);
+	mpidr_hash.shift_aff[3] = MPIDR_LEVEL_SHIFT(3) +
+				  fs[3] - (bits[2] + bits[1] + bits[0]);
+	mpidr_hash.mask = mask;
+	mpidr_hash.bits = bits[3] + bits[2] + bits[1] + bits[0];
+	pr_debug("MPIDR hash: aff0[%u] aff1[%u] aff2[%u] aff3[%u] mask[%#llx] bits[%u]\n",
+		mpidr_hash.shift_aff[0],
+		mpidr_hash.shift_aff[1],
+		mpidr_hash.shift_aff[2],
+		mpidr_hash.shift_aff[3],
+		mpidr_hash.mask,
+		mpidr_hash.bits);
+	/*
+	 * 4x is an arbitrary value used to warn on a hash table much bigger
+	 * than expected on most systems.
+	 */
+	if (mpidr_hash_size() > 4 * num_possible_cpus())
+		pr_warn("Large number of MPIDR hash buckets detected\n");
+	__flush_dcache_area(&mpidr_hash, sizeof(struct mpidr_hash));
+}
+#endif
+
 static void __init setup_processor(void)
 {
 	struct cpu_info *cpu_info;
@@ -273,6 +342,7 @@ void __init setup_arch(char **cmdline_p)
 	cpu_read_bootcpu_ops();
 #ifdef CONFIG_SMP
 	smp_init_cpus();
+	smp_build_mpidr_hash();
 #endif
 
 #ifdef CONFIG_VT
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
new file mode 100644
index 000000000000..b1925729c692
--- /dev/null
+++ b/arch/arm64/kernel/sleep.S
@@ -0,0 +1,184 @@
+#include <linux/errno.h>
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/assembler.h>
+
+	.text
+/*
+ * Implementation of MPIDR_EL1 hash algorithm through shifting
+ * and OR'ing.
+ *
+ * @dst: register containing hash result
+ * @rs0: register containing affinity level 0 bit shift
+ * @rs1: register containing affinity level 1 bit shift
+ * @rs2: register containing affinity level 2 bit shift
+ * @rs3: register containing affinity level 3 bit shift
+ * @mpidr: register containing MPIDR_EL1 value
+ * @mask: register containing MPIDR mask
+ *
+ * Pseudo C-code:
+ *
+ *u32 dst;
+ *
+ *compute_mpidr_hash(u32 rs0, u32 rs1, u32 rs2, u32 rs3, u64 mpidr, u64 mask) {
+ *	u32 aff0, aff1, aff2, aff3;
+ *	u64 mpidr_masked = mpidr & mask;
+ *	aff0 = mpidr_masked & 0xff;
+ *	aff1 = mpidr_masked & 0xff00;
+ *	aff2 = mpidr_masked & 0xff0000;
+ *	aff2 = mpidr_masked & 0xff00000000;
+ *	dst = (aff0 >> rs0 | aff1 >> rs1 | aff2 >> rs2 | aff3 >> rs3);
+ *}
+ * Input registers: rs0, rs1, rs2, rs3, mpidr, mask
+ * Output register: dst
+ * Note: input and output registers must be disjoint register sets
+         (eg: a macro instance with mpidr = x1 and dst = x1 is invalid)
+ */
+	.macro compute_mpidr_hash dst, rs0, rs1, rs2, rs3, mpidr, mask
+	and	\mpidr, \mpidr, \mask		// mask out MPIDR bits
+	and	\dst, \mpidr, #0xff		// mask=aff0
+	lsr	\dst ,\dst, \rs0		// dst=aff0>>rs0
+	and	\mask, \mpidr, #0xff00		// mask = aff1
+	lsr	\mask ,\mask, \rs1
+	orr	\dst, \dst, \mask		// dst|=(aff1>>rs1)
+	and	\mask, \mpidr, #0xff0000	// mask = aff2
+	lsr	\mask ,\mask, \rs2
+	orr	\dst, \dst, \mask		// dst|=(aff2>>rs2)
+	and	\mask, \mpidr, #0xff00000000	// mask = aff3
+	lsr	\mask ,\mask, \rs3
+	orr	\dst, \dst, \mask		// dst|=(aff3>>rs3)
+	.endm
+/*
+ * Save CPU state for a suspend.  This saves callee registers, and allocates
+ * space on the kernel stack to save the CPU specific registers + some
+ * other data for resume.
+ *
+ *  x0 = suspend finisher argument
+ */
+ENTRY(__cpu_suspend)
+	stp	x29, lr, [sp, #-96]!
+	stp	x19, x20, [sp,#16]
+	stp	x21, x22, [sp,#32]
+	stp	x23, x24, [sp,#48]
+	stp	x25, x26, [sp,#64]
+	stp	x27, x28, [sp,#80]
+	mov	x2, sp
+	sub	sp, sp, #CPU_SUSPEND_SZ	// allocate cpu_suspend_ctx
+	mov	x1, sp
+	/*
+	 * x1 now points to struct cpu_suspend_ctx allocated on the stack
+	 */
+	str	x2, [x1, #CPU_CTX_SP]
+	ldr	x2, =sleep_save_sp
+	ldr	x2, [x2, #SLEEP_SAVE_SP_VIRT]
+#ifdef CONFIG_SMP
+	mrs	x7, mpidr_el1
+	ldr	x9, =mpidr_hash
+	ldr	x10, [x9, #MPIDR_HASH_MASK]
+	/*
+	 * Following code relies on the struct mpidr_hash
+	 * members size.
+	 */
+	ldp	w3, w4, [x9, #MPIDR_HASH_SHIFTS]
+	ldp	w5, w6, [x9, #(MPIDR_HASH_SHIFTS + 8)]
+	compute_mpidr_hash x8, x3, x4, x5, x6, x7, x10
+	add	x2, x2, x8, lsl #3
+#endif
+	bl	__cpu_suspend_finisher
+        /*
+	 * Never gets here, unless suspend fails.
+	 * Successful cpu_suspend should return from cpu_resume, returning
+	 * through this code path is considered an error
+	 * If the return value is set to 0 force x0 = -EOPNOTSUPP
+	 * to make sure a proper error condition is propagated
+	 */
+	cmp	x0, #0
+	mov	x3, #-EOPNOTSUPP
+	csel	x0, x3, x0, eq
+	add	sp, sp, #CPU_SUSPEND_SZ	// rewind stack pointer
+	ldp	x19, x20, [sp, #16]
+	ldp	x21, x22, [sp, #32]
+	ldp	x23, x24, [sp, #48]
+	ldp	x25, x26, [sp, #64]
+	ldp	x27, x28, [sp, #80]
+	ldp	x29, lr, [sp], #96
+	ret
+ENDPROC(__cpu_suspend)
+	.ltorg
+
+/*
+ * x0 must contain the sctlr value retrieved from restored context
+ */
+ENTRY(cpu_resume_mmu)
+	ldr	x3, =cpu_resume_after_mmu
+	msr	sctlr_el1, x0		// restore sctlr_el1
+	isb
+	br	x3			// global jump to virtual address
+ENDPROC(cpu_resume_mmu)
+cpu_resume_after_mmu:
+	mov	x0, #0			// return zero on success
+	ldp	x19, x20, [sp, #16]
+	ldp	x21, x22, [sp, #32]
+	ldp	x23, x24, [sp, #48]
+	ldp	x25, x26, [sp, #64]
+	ldp	x27, x28, [sp, #80]
+	ldp	x29, lr, [sp], #96
+	ret
+ENDPROC(cpu_resume_after_mmu)
+
+	.data
+ENTRY(cpu_resume)
+	bl	el2_setup		// if in EL2 drop to EL1 cleanly
+#ifdef CONFIG_SMP
+	mrs	x1, mpidr_el1
+	adr	x4, mpidr_hash_ptr
+	ldr	x5, [x4]
+	add	x8, x4, x5		// x8 = struct mpidr_hash phys address
+        /* retrieve mpidr_hash members to compute the hash */
+	ldr	x2, [x8, #MPIDR_HASH_MASK]
+	ldp	w3, w4, [x8, #MPIDR_HASH_SHIFTS]
+	ldp	w5, w6, [x8, #(MPIDR_HASH_SHIFTS + 8)]
+	compute_mpidr_hash x7, x3, x4, x5, x6, x1, x2
+        /* x7 contains hash index, let's use it to grab context pointer */
+#else
+	mov	x7, xzr
+#endif
+	adr	x0, sleep_save_sp
+	ldr	x0, [x0, #SLEEP_SAVE_SP_PHYS]
+	ldr	x0, [x0, x7, lsl #3]
+	/* load sp from context */
+	ldr	x2, [x0, #CPU_CTX_SP]
+	adr	x1, sleep_idmap_phys
+	/* load physical address of identity map page table in x1 */
+	ldr	x1, [x1]
+	mov	sp, x2
+	/*
+	 * cpu_do_resume expects x0 to contain context physical address
+	 * pointer and x1 to contain physical address of 1:1 page tables
+	 */
+	bl	cpu_do_resume		// PC relative jump, MMU off
+	b	cpu_resume_mmu		// Resume MMU, never returns
+ENDPROC(cpu_resume)
+
+	.align 3
+mpidr_hash_ptr:
+	/*
+	 * offset of mpidr_hash symbol from current location
+	 * used to obtain run-time mpidr_hash address with MMU off
+         */
+	.quad	mpidr_hash - .
+/*
+ * physical address of identity mapped page tables
+ */
+	.type	sleep_idmap_phys, #object
+ENTRY(sleep_idmap_phys)
+	.quad	0
+/*
+ * struct sleep_save_sp {
+ *	phys_addr_t *save_ptr_stash;
+ *	phys_addr_t save_ptr_stash_phys;
+ * };
+ */
+	.type	sleep_save_sp, #object
+ENTRY(sleep_save_sp)
+	.space	SLEEP_SAVE_SP_SZ	// struct sleep_save_sp
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index b5d2031c12c6..1b7617ab499b 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -61,6 +61,7 @@ enum ipi_msg_type {
 	IPI_CALL_FUNC,
 	IPI_CALL_FUNC_SINGLE,
 	IPI_CPU_STOP,
+	IPI_TIMER,
 };
 
 /*
@@ -449,6 +450,7 @@ static const char *ipi_types[NR_IPI] = {
 	S(IPI_CALL_FUNC, "Function call interrupts"),
 	S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"),
 	S(IPI_CPU_STOP, "CPU stop interrupts"),
+	S(IPI_TIMER, "Timer broadcast interrupts"),
 };
 
 void show_ipi_list(struct seq_file *p, int prec)
@@ -534,6 +536,14 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 		irq_exit();
 		break;
 
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+	case IPI_TIMER:
+		irq_enter();
+		tick_receive_broadcast();
+		irq_exit();
+		break;
+#endif
+
 	default:
 		pr_crit("CPU%u: Unknown IPI message 0x%x\n", cpu, ipinr);
 		break;
@@ -546,6 +556,13 @@ void smp_send_reschedule(int cpu)
 	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
 }
 
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+void tick_broadcast(const struct cpumask *mask)
+{
+	smp_cross_call(mask, IPI_TIMER);
+}
+#endif
+
 void smp_send_stop(void)
 {
 	unsigned long timeout;
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
new file mode 100644
index 000000000000..e074b1c32723
--- /dev/null
+++ b/arch/arm64/kernel/suspend.c
@@ -0,0 +1,109 @@
+#include <linux/slab.h>
+#include <asm/cacheflush.h>
+#include <asm/cpu_ops.h>
+#include <asm/debug-monitors.h>
+#include <asm/pgtable.h>
+#include <asm/memory.h>
+#include <asm/smp_plat.h>
+#include <asm/suspend.h>
+#include <asm/tlbflush.h>
+
+extern int __cpu_suspend(unsigned long);
+/*
+ * This is called by __cpu_suspend() to save the state, and do whatever
+ * flushing is required to ensure that when the CPU goes to sleep we have
+ * the necessary data available when the caches are not searched.
+ *
+ * @arg: Argument to pass to suspend operations
+ * @ptr: CPU context virtual address
+ * @save_ptr: address of the location where the context physical address
+ *            must be saved
+ */
+int __cpu_suspend_finisher(unsigned long arg, struct cpu_suspend_ctx *ptr,
+			   phys_addr_t *save_ptr)
+{
+	int cpu = smp_processor_id();
+
+	*save_ptr = virt_to_phys(ptr);
+
+	cpu_do_suspend(ptr);
+	/*
+	 * Only flush the context that must be retrieved with the MMU
+	 * off. VA primitives ensure the flush is applied to all
+	 * cache levels so context is pushed to DRAM.
+	 */
+	__flush_dcache_area(ptr, sizeof(*ptr));
+	__flush_dcache_area(save_ptr, sizeof(*save_ptr));
+
+	return cpu_ops[cpu]->cpu_suspend(arg);
+}
+
+/**
+ * cpu_suspend
+ *
+ * @arg: argument to pass to the finisher function
+ */
+int cpu_suspend(unsigned long arg)
+{
+	struct mm_struct *mm = current->active_mm;
+	int ret, cpu = smp_processor_id();
+	unsigned long flags;
+
+	/*
+	 * If cpu_ops have not been registered or suspend
+	 * has not been initialized, cpu_suspend call fails early.
+	 */
+	if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_suspend)
+		return -EOPNOTSUPP;
+
+	/*
+	 * From this point debug exceptions are disabled to prevent
+	 * updates to mdscr register (saved and restored along with
+	 * general purpose registers) from kernel debuggers.
+	 */
+	local_dbg_save(flags);
+
+	/*
+	 * mm context saved on the stack, it will be restored when
+	 * the cpu comes out of reset through the identity mapped
+	 * page tables, so that the thread address space is properly
+	 * set-up on function return.
+	 */
+	ret = __cpu_suspend(arg);
+	if (ret == 0) {
+		cpu_switch_mm(mm->pgd, mm);
+		flush_tlb_all();
+	}
+
+	/*
+	 * Restore pstate flags. OS lock and mdscr have been already
+	 * restored, so from this point onwards, debugging is fully
+	 * renabled if it was enabled when core started shutdown.
+	 */
+	local_dbg_restore(flags);
+
+	return ret;
+}
+
+extern struct sleep_save_sp sleep_save_sp;
+extern phys_addr_t sleep_idmap_phys;
+
+static int cpu_suspend_init(void)
+{
+	void *ctx_ptr;
+
+	/* ctx_ptr is an array of physical addresses */
+	ctx_ptr = kcalloc(mpidr_hash_size(), sizeof(phys_addr_t), GFP_KERNEL);
+
+	if (WARN_ON(!ctx_ptr))
+		return -ENOMEM;
+
+	sleep_save_sp.save_ptr_stash = ctx_ptr;
+	sleep_save_sp.save_ptr_stash_phys = virt_to_phys(ctx_ptr);
+	sleep_idmap_phys = virt_to_phys(idmap_pg_dir);
+	__flush_dcache_area(&sleep_save_sp, sizeof(struct sleep_save_sp));
+	__flush_dcache_area(&sleep_idmap_phys, sizeof(sleep_idmap_phys));
+
+	return 0;
+}
+early_initcall(cpu_suspend_init);
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 0f7fec52c7f8..bed1f1de1caf 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -80,6 +80,75 @@ ENTRY(cpu_do_idle)
 	ret
 ENDPROC(cpu_do_idle)
 
+#ifdef CONFIG_ARM64_CPU_SUSPEND
+/**
+ * cpu_do_suspend - save CPU registers context
+ *
+ * x0: virtual address of context pointer
+ */
+ENTRY(cpu_do_suspend)
+	mrs	x2, tpidr_el0
+	mrs	x3, tpidrro_el0
+	mrs	x4, contextidr_el1
+	mrs	x5, mair_el1
+	mrs	x6, cpacr_el1
+	mrs	x7, ttbr1_el1
+	mrs	x8, tcr_el1
+	mrs	x9, vbar_el1
+	mrs	x10, mdscr_el1
+	mrs	x11, oslsr_el1
+	mrs	x12, sctlr_el1
+	stp	x2, x3, [x0]
+	stp	x4, x5, [x0, #16]
+	stp	x6, x7, [x0, #32]
+	stp	x8, x9, [x0, #48]
+	stp	x10, x11, [x0, #64]
+	str	x12, [x0, #80]
+	ret
+ENDPROC(cpu_do_suspend)
+
+/**
+ * cpu_do_resume - restore CPU register context
+ *
+ * x0: Physical address of context pointer
+ * x1: ttbr0_el1 to be restored
+ *
+ * Returns:
+ *	sctlr_el1 value in x0
+ */
+ENTRY(cpu_do_resume)
+	/*
+	 * Invalidate local tlb entries before turning on MMU
+	 */
+	tlbi	vmalle1
+	ldp	x2, x3, [x0]
+	ldp	x4, x5, [x0, #16]
+	ldp	x6, x7, [x0, #32]
+	ldp	x8, x9, [x0, #48]
+	ldp	x10, x11, [x0, #64]
+	ldr	x12, [x0, #80]
+	msr	tpidr_el0, x2
+	msr	tpidrro_el0, x3
+	msr	contextidr_el1, x4
+	msr	mair_el1, x5
+	msr	cpacr_el1, x6
+	msr	ttbr0_el1, x1
+	msr	ttbr1_el1, x7
+	msr	tcr_el1, x8
+	msr	vbar_el1, x9
+	msr	mdscr_el1, x10
+	/*
+	 * Restore oslsr_el1 by writing oslar_el1
+	 */
+	ubfx	x11, x11, #1, #1
+	msr	oslar_el1, x11
+	mov	x0, x12
+	dsb	nsh		// Make sure local tlb invalidation completed
+	isb
+	ret
+ENDPROC(cpu_do_resume)
+#endif
+
 /*
  *	cpu_switch_mm(pgd_phys, tsk)
  *