Merge arm64 CPU suspend branch

* cpuidle:
  arm64: add PSCI CPU_SUSPEND based cpu_suspend support
  arm64: kernel: introduce cpu_init_idle CPU operation
  arm64: kernel: refactor the CPU suspend API for retention states
  Documentation: arm: define DT idle states bindings

Documentation/devicetree/bindings/arm/cpus.txt

@@ -219,6 +219,12 @@ nodes to be present and contain the properties described below.
 		Value type: <phandle>
 		Definition: Specifies the ACC[2] node associated with this CPU.
 
+	- cpu-idle-states
+		Usage: Optional
+		Value type: <prop-encoded-array>
+		Definition:
+			# List of phandles to idle state nodes supported
+			  by this cpu [3].
 
 Example 1 (dual-cluster big.LITTLE system 32-bit):
 
@@ -415,3 +421,5 @@ cpus {
 --
 [1] arm/msm/qcom,saw2.txt
 [2] arm/msm/qcom,kpss-acc.txt
+[3] ARM Linux kernel documentation - idle states bindings
+    Documentation/devicetree/bindings/arm/idle-states.txt

Documentation/devicetree/bindings/arm/psci.txt

@@ -50,6 +50,16 @@ Main node optional properties:
 
  - migrate       : Function ID for MIGRATE operation
 
+Device tree nodes that require usage of PSCI CPU_SUSPEND function (ie idle
+state nodes, as per bindings in [1]) must specify the following properties:
+
+- arm,psci-suspend-param
+		Usage: Required for state nodes[1] if the corresponding
+                       idle-states node entry-method property is set
+                       to "psci".
+		Value type: <u32>
+		Definition: power_state parameter to pass to the PSCI
+			    suspend call.
 
 Example:
 
@@ -64,7 +74,6 @@ Case 1: PSCI v0.1 only.
 		migrate		= <0x95c10003>;
 	};
 
-
 Case 2: PSCI v0.2 only
 
 	psci {
@@ -88,3 +97,6 @@ Case 3: PSCI v0.2 and PSCI v0.1.
 
 		...
 	};
+
+[1] Kernel documentation - ARM idle states bindings
+    Documentation/devicetree/bindings/arm/idle-states.txt

arch/arm64/include/asm/cpu_ops.h

@@ -28,6 +28,8 @@ struct device_node;
  *		enable-method property.
  * @cpu_init:	Reads any data necessary for a specific enable-method from the
  *		devicetree, for a given cpu node and proposed logical id.
+ * @cpu_init_idle: Reads any data necessary to initialize CPU idle states from
+ *		devicetree, for a given cpu node and proposed logical id.
  * @cpu_prepare: Early one-time preparation step for a cpu. If there is a
  *		mechanism for doing so, tests whether it is possible to boot
  *		the given CPU.
@@ -47,6 +49,7 @@ struct device_node;
 struct cpu_operations {
 	const char	*name;
 	int		(*cpu_init)(struct device_node *, unsigned int);
+	int		(*cpu_init_idle)(struct device_node *, unsigned int);
 	int		(*cpu_prepare)(unsigned int);
 	int		(*cpu_boot)(unsigned int);
 	void		(*cpu_postboot)(void);

arch/arm64/include/asm/cpuidle.h

+#ifndef __ASM_CPUIDLE_H
+#define __ASM_CPUIDLE_H
+
+#ifdef CONFIG_CPU_IDLE
+extern int cpu_init_idle(unsigned int cpu);
+#else
+static inline int cpu_init_idle(unsigned int cpu)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+#endif

arch/arm64/include/asm/suspend.h

@@ -21,6 +21,7 @@ struct sleep_save_sp {
 	phys_addr_t save_ptr_stash_phys;
 };
 
+extern int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long));
 extern void cpu_resume(void);
 extern int cpu_suspend(unsigned long);
 

arch/arm64/kernel/Makefile

@@ -26,6 +26,7 @@ arm64-obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o
 arm64-obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o
 arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 arm64-obj-$(CONFIG_ARM64_CPU_SUSPEND)	+= sleep.o suspend.o
+arm64-obj-$(CONFIG_CPU_IDLE)		+= cpuidle.o
 arm64-obj-$(CONFIG_JUMP_LABEL)		+= jump_label.o
 arm64-obj-$(CONFIG_KGDB)		+= kgdb.o
 arm64-obj-$(CONFIG_EFI)			+= efi.o efi-stub.o efi-entry.o

arch/arm64/kernel/cpuidle.c

+/*
+ * ARM64 CPU idle arch support
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+ *
+ * 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/of.h>
+#include <linux/of_device.h>
+
+#include <asm/cpuidle.h>
+#include <asm/cpu_ops.h>
+
+int cpu_init_idle(unsigned int cpu)
+{
+	int ret = -EOPNOTSUPP;
+	struct device_node *cpu_node = of_cpu_device_node_get(cpu);
+
+	if (!cpu_node)
+		return -ENODEV;
+
+	if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_init_idle)
+		ret = cpu_ops[cpu]->cpu_init_idle(cpu_node, cpu);
+
+	of_node_put(cpu_node);
+	return ret;
+}

arch/arm64/kernel/psci.c

@@ -21,6 +21,7 @@
 #include <linux/reboot.h>
 #include <linux/pm.h>
 #include <linux/delay.h>
+#include <linux/slab.h>
 #include <uapi/linux/psci.h>
 
 #include <asm/compiler.h>
@@ -28,6 +29,7 @@
 #include <asm/errno.h>
 #include <asm/psci.h>
 #include <asm/smp_plat.h>
+#include <asm/suspend.h>
 #include <asm/system_misc.h>
 
 #define PSCI_POWER_STATE_TYPE_STANDBY		0
@@ -65,6 +67,8 @@ enum psci_function {
 	PSCI_FN_MAX,
 };
 
+static DEFINE_PER_CPU_READ_MOSTLY(struct psci_power_state *, psci_power_state);
+
 static u32 psci_function_id[PSCI_FN_MAX];
 
 static int psci_to_linux_errno(int errno)
@@ -93,6 +97,18 @@ static u32 psci_power_state_pack(struct psci_power_state state)
 		 & PSCI_0_2_POWER_STATE_AFFL_MASK);
 }
 
+static void psci_power_state_unpack(u32 power_state,
+				    struct psci_power_state *state)
+{
+	state->id = (power_state & PSCI_0_2_POWER_STATE_ID_MASK) >>
+			PSCI_0_2_POWER_STATE_ID_SHIFT;
+	state->type = (power_state & PSCI_0_2_POWER_STATE_TYPE_MASK) >>
+			PSCI_0_2_POWER_STATE_TYPE_SHIFT;
+	state->affinity_level =
+			(power_state & PSCI_0_2_POWER_STATE_AFFL_MASK) >>
+			PSCI_0_2_POWER_STATE_AFFL_SHIFT;
+}
+
 /*
  * The following two functions are invoked via the invoke_psci_fn pointer
  * and will not be inlined, allowing us to piggyback on the AAPCS.
@@ -199,6 +215,63 @@ static int psci_migrate_info_type(void)
 	return err;
 }
 
+static int __maybe_unused cpu_psci_cpu_init_idle(struct device_node *cpu_node,
+						 unsigned int cpu)
+{
+	int i, ret, count = 0;
+	struct psci_power_state *psci_states;
+	struct device_node *state_node;
+
+	/*
+	 * If the PSCI cpu_suspend function hook has not been initialized
+	 * idle states must not be enabled, so bail out
+	 */
+	if (!psci_ops.cpu_suspend)
+		return -EOPNOTSUPP;
+
+	/* Count idle states */
+	while ((state_node = of_parse_phandle(cpu_node, "cpu-idle-states",
+					      count))) {
+		count++;
+		of_node_put(state_node);
+	}
+
+	if (!count)
+		return -ENODEV;
+
+	psci_states = kcalloc(count, sizeof(*psci_states), GFP_KERNEL);
+	if (!psci_states)
+		return -ENOMEM;
+
+	for (i = 0; i < count; i++) {
+		u32 psci_power_state;
+
+		state_node = of_parse_phandle(cpu_node, "cpu-idle-states", i);
+
+		ret = of_property_read_u32(state_node,
+					   "arm,psci-suspend-param",
+					   &psci_power_state);
+		if (ret) {
+			pr_warn(" * %s missing arm,psci-suspend-param property\n",
+				state_node->full_name);
+			of_node_put(state_node);
+			goto free_mem;
+		}
+
+		of_node_put(state_node);
+		pr_debug("psci-power-state %#x index %d\n", psci_power_state,
+							    i);
+		psci_power_state_unpack(psci_power_state, &psci_states[i]);
+	}
+	/* Idle states parsed correctly, initialize per-cpu pointer */
+	per_cpu(psci_power_state, cpu) = psci_states;
+	return 0;
+
+free_mem:
+	kfree(psci_states);
+	return ret;
+}
+
 static int get_set_conduit_method(struct device_node *np)
 {
 	const char *method;
@@ -436,8 +509,39 @@ static int cpu_psci_cpu_kill(unsigned int cpu)
 #endif
 #endif
 
+static int psci_suspend_finisher(unsigned long index)
+{
+	struct psci_power_state *state = __get_cpu_var(psci_power_state);
+
+	return psci_ops.cpu_suspend(state[index - 1],
+				    virt_to_phys(cpu_resume));
+}
+
+static int __maybe_unused cpu_psci_cpu_suspend(unsigned long index)
+{
+	int ret;
+	struct psci_power_state *state = __get_cpu_var(psci_power_state);
+	/*
+	 * idle state index 0 corresponds to wfi, should never be called
+	 * from the cpu_suspend operations
+	 */
+	if (WARN_ON_ONCE(!index))
+		return -EINVAL;
+
+	if (state->type == PSCI_POWER_STATE_TYPE_STANDBY)
+		ret = psci_ops.cpu_suspend(state[index - 1], 0);
+	else
+		ret = __cpu_suspend(index, psci_suspend_finisher);
+
+	return ret;
+}
+
 const struct cpu_operations cpu_psci_ops = {
 	.name		= "psci",
+#ifdef CONFIG_CPU_IDLE
+	.cpu_init_idle	= cpu_psci_cpu_init_idle,
+	.cpu_suspend	= cpu_psci_cpu_suspend,
+#endif
 #ifdef CONFIG_SMP
 	.cpu_init	= cpu_psci_cpu_init,
 	.cpu_prepare	= cpu_psci_cpu_prepare,

arch/arm64/kernel/sleep.S

@@ -49,28 +49,39 @@
 	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.
+ * Save CPU state for a suspend and execute the suspend finisher.
+ * On success it will return 0 through cpu_resume - ie through a CPU
+ * soft/hard reboot from the reset vector.
+ * On failure it returns the suspend finisher return value or force
+ * -EOPNOTSUPP if the finisher erroneously returns 0 (the suspend finisher
+ * is not allowed to return, if it does this must be considered failure).
+ * It 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
+ *  x1 = suspend finisher function pointer
  */
-ENTRY(__cpu_suspend)
+ENTRY(__cpu_suspend_enter)
 	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]
+	/*
+	 * Stash suspend finisher and its argument in x20 and x19
+	 */
+	mov	x19, x0
+	mov	x20, x1
 	mov	x2, sp
 	sub	sp, sp, #CPU_SUSPEND_SZ	// allocate cpu_suspend_ctx
-	mov	x1, sp
+	mov	x0, sp
 	/*
-	 * x1 now points to struct cpu_suspend_ctx allocated on the stack
+	 * x0 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]
+	str	x2, [x0, #CPU_CTX_SP]
+	ldr	x1, =sleep_save_sp
+	ldr	x1, [x1, #SLEEP_SAVE_SP_VIRT]
 #ifdef CONFIG_SMP
 	mrs	x7, mpidr_el1
 	ldr	x9, =mpidr_hash
@@ -82,11 +93,21 @@ ENTRY(__cpu_suspend)
 	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
+	add	x1, x1, x8, lsl #3
 #endif
-	bl	__cpu_suspend_finisher
+	bl	__cpu_suspend_save
+	/*
+	 * Grab suspend finisher in x20 and its argument in x19
+	 */
+	mov	x0, x19
+	mov	x1, x20
+	/*
+	 * We are ready for power down, fire off the suspend finisher
+	 * in x1, with argument in x0
+	 */
+	blr	x1
         /*
-	 * Never gets here, unless suspend fails.
+	 * Never gets here, unless suspend finisher 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
@@ -103,7 +124,7 @@ ENTRY(__cpu_suspend)
 	ldp	x27, x28, [sp, #80]
 	ldp	x29, lr, [sp], #96
 	ret
-ENDPROC(__cpu_suspend)
+ENDPROC(__cpu_suspend_enter)
 	.ltorg
 
 /*

arch/arm64/kernel/suspend.c

@@ -9,22 +9,19 @@
 #include <asm/suspend.h>
 #include <asm/tlbflush.h>
 
-extern int __cpu_suspend(unsigned long);
+extern int __cpu_suspend_enter(unsigned long arg, int (*fn)(unsigned long));
 /*
- * This is called by __cpu_suspend() to save the state, and do whatever
+ * This is called by __cpu_suspend_enter() 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
+ * 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,
+void notrace __cpu_suspend_save(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);
@@ -35,8 +32,6 @@ int __cpu_suspend_finisher(unsigned long arg, struct cpu_suspend_ctx *ptr,
 	 */
 	__flush_dcache_area(ptr, sizeof(*ptr));
 	__flush_dcache_area(save_ptr, sizeof(*save_ptr));
-
-	return cpu_ops[cpu]->cpu_suspend(arg);
 }
 
 /*
@@ -56,15 +51,15 @@ void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
 }
 
 /**
- * cpu_suspend
+ * cpu_suspend() - function to enter a low-power state
+ * @arg: argument to pass to CPU suspend operations
  *
- * @arg: argument to pass to the finisher function
+ * Return: 0 on success, -EOPNOTSUPP if CPU suspend hook not initialized, CPU
+ * operations back-end error code otherwise.
  */
 int cpu_suspend(unsigned long arg)
 {
-	struct mm_struct *mm = current->active_mm;
-	int ret, cpu = smp_processor_id();
-	unsigned long flags;
+	int cpu = smp_processor_id();
 
 	/*
 	 * If cpu_ops have not been registered or suspend
@@ -72,6 +67,21 @@ int cpu_suspend(unsigned long arg)
 	 */
 	if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_suspend)
 		return -EOPNOTSUPP;
+	return cpu_ops[cpu]->cpu_suspend(arg);
+}
+
+/*
+ * __cpu_suspend
+ *
+ * arg: argument to pass to the finisher function
+ * fn: finisher function pointer
+ *
+ */
+int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
+{
+	struct mm_struct *mm = current->active_mm;
+	int ret;
+	unsigned long flags;
 
 	/*
 	 * From this point debug exceptions are disabled to prevent
@@ -86,7 +96,7 @@ int cpu_suspend(unsigned long arg)
 	 * page tables, so that the thread address space is properly
 	 * set-up on function return.
 	 */
-	ret = __cpu_suspend(arg);
+	ret = __cpu_suspend_enter(arg, fn);
 	if (ret == 0) {
 		cpu_switch_mm(mm->pgd, mm);
 		flush_tlb_all();
@@ -95,7 +105,7 @@ int cpu_suspend(unsigned long arg)
 		 * Restore per-cpu offset before any kernel
 		 * subsystem relying on it has a chance to run.
 		 */
-		set_my_cpu_offset(per_cpu_offset(cpu));
+		set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
 
 		/*
 		 * Restore HW breakpoint registers to sane values