ARMv8: Add basic PSCI framework

This patch introduces a generic ARMv8 PSCI framework, with all functions
returning a dummy ARM_PSCI_RET_NI (Not Implemented), then it is up to each
platform to implement their own functions based on this framework.

Signed-off-by: Hongbo Zhang <hongbo.zhang@nxp.com>
Reviewed-by: Tom Rini <trini@konsulko.com>
Reviewed-by: York Sun <york.sun@nxp.com>
diff --git a/arch/arm/cpu/armv8/Kconfig b/arch/arm/cpu/armv8/Kconfig
index edae43d..22dce88 100644
--- a/arch/arm/cpu/armv8/Kconfig
+++ b/arch/arm/cpu/armv8/Kconfig
@@ -58,6 +58,16 @@
 	  It is no problem to set a larger value than the number of CPUs in
 	  the actual hardware implementation.
 
+config ARMV8_PSCI_CPUS_PER_CLUSTER
+	int "Number of CPUs per cluster"
+	depends on ARMV8_PSCI
+	default 0
+	help
+	  The number of CPUs per cluster, suppose each cluster has same number
+	  of CPU cores, platforms with asymmetric clusters don't apply here.
+	  A value 0 or no definition of it works for single cluster system.
+	  System with multi-cluster should difine their own exact value.
+
 if SYS_HAS_ARMV8_SECURE_BASE
 
 config ARMV8_SECURE_BASE
diff --git a/arch/arm/cpu/armv8/Makefile b/arch/arm/cpu/armv8/Makefile
index dea1465..28ba786 100644
--- a/arch/arm/cpu/armv8/Makefile
+++ b/arch/arm/cpu/armv8/Makefile
@@ -25,3 +25,4 @@
 obj-$(CONFIG_S32V234) += s32v234/
 obj-$(CONFIG_ARCH_ZYNQMP) += zynqmp/
 obj-$(CONFIG_TARGET_HIKEY) += hisilicon/
+obj-$(CONFIG_ARMV8_PSCI) += psci.o
diff --git a/arch/arm/cpu/armv8/psci.S b/arch/arm/cpu/armv8/psci.S
new file mode 100644
index 0000000..43d5d6b
--- /dev/null
+++ b/arch/arm/cpu/armv8/psci.S
@@ -0,0 +1,286 @@
+/*
+ * Copyright 2016 Freescale Semiconductor, Inc.
+ * Author: Hongbo Zhang <hongbo.zhang@nxp.com>
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ * This file implements LS102X platform PSCI SYSTEM-SUSPEND function
+ */
+
+#include <config.h>
+#include <linux/linkage.h>
+#include <asm/psci.h>
+
+/* Default PSCI function, return -1, Not Implemented */
+#define PSCI_DEFAULT(__fn) \
+	ENTRY(__fn); \
+	mov	w0, #ARM_PSCI_RET_NI; \
+	ret; \
+	ENDPROC(__fn); \
+	.weak __fn
+
+/* PSCI function and ID table definition*/
+#define PSCI_TABLE(__id, __fn) \
+	.word __id; \
+	.word __fn
+
+.pushsection ._secure.text, "ax"
+
+/* 32 bits PSCI default functions */
+PSCI_DEFAULT(psci_version)
+PSCI_DEFAULT(psci_cpu_suspend)
+PSCI_DEFAULT(psci_cpu_off)
+PSCI_DEFAULT(psci_cpu_on)
+PSCI_DEFAULT(psci_affinity_info)
+PSCI_DEFAULT(psci_migrate)
+PSCI_DEFAULT(psci_migrate_info_type)
+PSCI_DEFAULT(psci_migrate_info_up_cpu)
+PSCI_DEFAULT(psci_system_off)
+PSCI_DEFAULT(psci_system_reset)
+PSCI_DEFAULT(psci_features)
+PSCI_DEFAULT(psci_cpu_freeze)
+PSCI_DEFAULT(psci_cpu_default_suspend)
+PSCI_DEFAULT(psci_node_hw_state)
+PSCI_DEFAULT(psci_system_suspend)
+PSCI_DEFAULT(psci_set_suspend_mode)
+PSCI_DEFAULT(psi_stat_residency)
+PSCI_DEFAULT(psci_stat_count)
+
+.align 3
+_psci_32_table:
+PSCI_TABLE(ARM_PSCI_FN_CPU_SUSPEND, psci_cpu_suspend)
+PSCI_TABLE(ARM_PSCI_FN_CPU_OFF, psci_cpu_off)
+PSCI_TABLE(ARM_PSCI_FN_CPU_ON, psci_cpu_on)
+PSCI_TABLE(ARM_PSCI_FN_MIGRATE, psci_migrate)
+PSCI_TABLE(ARM_PSCI_0_2_FN_PSCI_VERSION, psci_version)
+PSCI_TABLE(ARM_PSCI_0_2_FN_CPU_SUSPEND, psci_cpu_suspend)
+PSCI_TABLE(ARM_PSCI_0_2_FN_CPU_OFF, psci_cpu_off)
+PSCI_TABLE(ARM_PSCI_0_2_FN_CPU_ON, psci_cpu_on)
+PSCI_TABLE(ARM_PSCI_0_2_FN_AFFINITY_INFO, psci_affinity_info)
+PSCI_TABLE(ARM_PSCI_0_2_FN_MIGRATE, psci_migrate)
+PSCI_TABLE(ARM_PSCI_0_2_FN_MIGRATE_INFO_TYPE, psci_migrate_info_type)
+PSCI_TABLE(ARM_PSCI_0_2_FN_MIGRATE_INFO_UP_CPU, psci_migrate_info_up_cpu)
+PSCI_TABLE(ARM_PSCI_0_2_FN_SYSTEM_OFF, psci_system_off)
+PSCI_TABLE(ARM_PSCI_0_2_FN_SYSTEM_RESET, psci_system_reset)
+PSCI_TABLE(ARM_PSCI_1_0_FN_PSCI_FEATURES, psci_features)
+PSCI_TABLE(ARM_PSCI_1_0_FN_CPU_FREEZE, psci_cpu_freeze)
+PSCI_TABLE(ARM_PSCI_1_0_FN_CPU_DEFAULT_SUSPEND, psci_cpu_default_suspend)
+PSCI_TABLE(ARM_PSCI_1_0_FN_NODE_HW_STATE, psci_node_hw_state)
+PSCI_TABLE(ARM_PSCI_1_0_FN_SYSTEM_SUSPEND, psci_system_suspend)
+PSCI_TABLE(ARM_PSCI_1_0_FN_SET_SUSPEND_MODE, psci_set_suspend_mode)
+PSCI_TABLE(ARM_PSCI_1_0_FN_STAT_RESIDENCY, psi_stat_residency)
+PSCI_TABLE(ARM_PSCI_1_0_FN_STAT_COUNT, psci_stat_count)
+PSCI_TABLE(0, 0)
+
+/* 64 bits PSCI default functions */
+PSCI_DEFAULT(psci_cpu_suspend_64)
+PSCI_DEFAULT(psci_cpu_on_64)
+PSCI_DEFAULT(psci_affinity_info_64)
+PSCI_DEFAULT(psci_migrate_64)
+PSCI_DEFAULT(psci_migrate_info_up_cpu_64)
+PSCI_DEFAULT(psci_cpu_default_suspend_64)
+PSCI_DEFAULT(psci_node_hw_state_64)
+PSCI_DEFAULT(psci_system_suspend_64)
+PSCI_DEFAULT(psci_stat_residency_64)
+PSCI_DEFAULT(psci_stat_count_64)
+
+.align 3
+_psci_64_table:
+PSCI_TABLE(ARM_PSCI_0_2_FN64_CPU_SUSPEND, psci_cpu_suspend_64)
+PSCI_TABLE(ARM_PSCI_0_2_FN64_CPU_ON, psci_cpu_on_64)
+PSCI_TABLE(ARM_PSCI_0_2_FN64_AFFINITY_INFO, psci_affinity_info_64)
+PSCI_TABLE(ARM_PSCI_0_2_FN64_MIGRATE, psci_migrate_64)
+PSCI_TABLE(ARM_PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU, psci_migrate_info_up_cpu_64)
+PSCI_TABLE(ARM_PSCI_1_0_FN64_CPU_DEFAULT_SUSPEND, psci_cpu_default_suspend_64)
+PSCI_TABLE(ARM_PSCI_1_0_FN64_NODE_HW_STATE, psci_node_hw_state_64)
+PSCI_TABLE(ARM_PSCI_1_0_FN64_SYSTEM_SUSPEND, psci_system_suspend_64)
+PSCI_TABLE(ARM_PSCI_1_0_FN64_STAT_RESIDENCY, psci_stat_residency_64)
+PSCI_TABLE(ARM_PSCI_1_0_FN64_STAT_COUNT, psci_stat_count_64)
+PSCI_TABLE(0, 0)
+
+.macro	psci_enter
+	/* PSCI call is Fast Call(atomic), so mask DAIF */
+	mrs	x15, DAIF
+	stp	x15, xzr, [sp, #-16]!
+	ldr	x15, =0x3C0
+	msr	DAIF, x15
+	/* SMC convention, x18 ~ x30 should be saved by callee */
+	stp	x29, x30, [sp, #-16]!
+	stp	x27, x28, [sp, #-16]!
+	stp	x25, x26, [sp, #-16]!
+	stp	x23, x24, [sp, #-16]!
+	stp	x21, x22, [sp, #-16]!
+	stp	x19, x20, [sp, #-16]!
+	mrs	x15, elr_el3
+	stp	x18, x15, [sp, #-16]!
+.endm
+
+.macro	psci_return
+	/* restore registers */
+	ldp	x18, x15, [sp], #16
+	msr	elr_el3, x15
+	ldp	x19, x20, [sp], #16
+	ldp	x21, x22, [sp], #16
+	ldp	x23, x24, [sp], #16
+	ldp	x25, x26, [sp], #16
+	ldp	x27, x28, [sp], #16
+	ldp	x29, x30, [sp], #16
+	/* restore DAIF */
+	ldp	x15, xzr, [sp], #16
+	msr	DAIF, x15
+	eret
+.endm
+
+/* Caller must put PSCI function-ID table base in x9 */
+handle_psci:
+	psci_enter
+1:	ldr x10, [x9]			/* Load PSCI function table */
+	ubfx x11, x10, #32, #32
+	ubfx x10, x10, #0, #32
+	cbz	x10, 3f			/* If reach the end, bail out */
+	cmp	x10, x0
+	b.eq	2f			/* PSCI function found */
+	add x9, x9, #8			/* If not match, try next entry */
+	b	1b
+
+2:	blr	x11			/* Call PSCI function */
+	psci_return
+
+3:	mov	x0, #ARM_PSCI_RET_NI
+	psci_return
+
+unknown_smc_id:
+	ldr	x0, =0xFFFFFFFF
+	eret
+
+handle_smc32:
+	/* SMC function ID  0x84000000-0x8400001F: 32 bits PSCI */
+	ldr	w9, =0x8400001F
+	cmp	w0, w9
+	b.gt	unknown_smc_id
+	ldr	w9, =0x84000000
+	cmp	w0, w9
+	b.lt	unknown_smc_id
+
+	adr	x9, _psci_32_table
+	b	handle_psci
+
+handle_smc64:
+	/* check SMC32 or SMC64 calls */
+	ubfx	x9, x0, #30, #1
+	cbz	x9, handle_smc32
+
+	/* SMC function ID 0xC4000000-0xC400001F: 64 bits PSCI */
+	ldr	x9, =0xC400001F
+	cmp	x0, x9
+	b.gt	unknown_smc_id
+	ldr	x9, =0xC4000000
+	cmp	x0, x9
+	b.lt	unknown_smc_id
+
+	adr	x9, _psci_64_table
+	b	handle_psci
+
+/*
+ * Get CPU ID from MPIDR, suppose every cluster has same number of CPU cores,
+ * Platform with asymmetric clusters should implement their own interface.
+ * In case this function being called by other platform's C code, the ARM
+ * Architecture Procedure Call Standard is considered, e.g. register X0 is
+ * used for the return value, while in this PSCI environment, X0 usually holds
+ * the SMC function identifier, so X0 should be saved by caller function.
+ */
+ENTRY(psci_get_cpu_id)
+#ifdef CONFIG_ARMV8_PSCI_CPUS_PER_CLUSTER
+	mrs	x9, MPIDR_EL1
+	ubfx	x9, x9, #8, #8
+	ldr	x10, =CONFIG_ARMV8_PSCI_CPUS_PER_CLUSTER
+	mul	x9, x10, x9
+#else
+	mov	x9, xzr
+#endif
+	mrs	x10, MPIDR_EL1
+	ubfx	x10, x10, #0, #8
+	add	x0, x10, x9
+	ret
+ENDPROC(psci_get_cpu_id)
+.weak psci_get_cpu_id
+
+/* CPU ID input in x0, stack top output in x0*/
+LENTRY(psci_get_cpu_stack_top)
+	adr	x9, __secure_stack_end
+	lsl	x0, x0, #ARM_PSCI_STACK_SHIFT
+	sub	x0, x9, x0
+	ret
+ENDPROC(psci_get_cpu_stack_top)
+
+unhandled_exception:
+	b	unhandled_exception	/* simply dead loop */
+
+handle_sync:
+	mov	x15, x30
+	mov	x14, x0
+
+	bl	psci_get_cpu_id
+	bl	psci_get_cpu_stack_top
+	mov	x9, #1
+	msr	spsel, x9
+	mov	sp, x0
+
+	mov	x0, x14
+	mov	x30, x15
+
+	mrs	x9, esr_el3
+	ubfx	x9, x9, #26, #6
+	cmp	x9, #0x13
+	b.eq	handle_smc32
+	cmp	x9, #0x17
+	b.eq	handle_smc64
+
+	b	unhandled_exception
+
+	.align	11
+	.globl	el3_exception_vectors
+el3_exception_vectors:
+	b	unhandled_exception	/* Sync, Current EL using SP0 */
+	.align	7
+	b	unhandled_exception	/* IRQ, Current EL using SP0 */
+	.align	7
+	b	unhandled_exception	/* FIQ, Current EL using SP0 */
+	.align	7
+	b	unhandled_exception	/* SError, Current EL using SP0 */
+	.align	7
+	b	unhandled_exception	/* Sync, Current EL using SPx */
+	.align	7
+	b	unhandled_exception	/* IRQ, Current EL using SPx */
+	.align	7
+	b	unhandled_exception	/* FIQ, Current EL using SPx */
+	.align	7
+	b	unhandled_exception	/* SError, Current EL using SPx */
+	.align	7
+	b	handle_sync		/* Sync, Lower EL using AArch64 */
+	.align	7
+	b	unhandled_exception	/* IRQ, Lower EL using AArch64 */
+	.align	7
+	b	unhandled_exception	/* FIQ, Lower EL using AArch64 */
+	.align	7
+	b	unhandled_exception	/* SError, Lower EL using AArch64 */
+	.align	7
+	b	unhandled_exception	/* Sync, Lower EL using AArch32 */
+	.align	7
+	b	unhandled_exception	/* IRQ, Lower EL using AArch32 */
+	.align	7
+	b	unhandled_exception	/* FIQ, Lower EL using AArch32 */
+	.align	7
+	b	unhandled_exception	/* SError, Lower EL using AArch32 */
+
+ENTRY(psci_setup_vectors)
+	adr	x0, el3_exception_vectors
+	msr	vbar_el3, x0
+	ret
+ENDPROC(psci_setup_vectors)
+
+ENTRY(psci_arch_init)
+	ret
+ENDPROC(psci_arch_init)
+.weak psci_arch_init
+
+.popsection
diff --git a/arch/arm/include/asm/psci.h b/arch/arm/include/asm/psci.h
index 9f1f779..ac8b00d 100644
--- a/arch/arm/include/asm/psci.h
+++ b/arch/arm/include/asm/psci.h
@@ -45,6 +45,9 @@
 #define ARM_PSCI_0_2_FN_BASE			0x84000000
 #define ARM_PSCI_0_2_FN(n)			(ARM_PSCI_0_2_FN_BASE + (n))
 
+#define ARM_PSCI_0_2_FN64_BASE			0xC4000000
+#define ARM_PSCI_0_2_FN64(n)			(ARM_PSCI_0_2_FN64_BASE + (n))
+
 #define ARM_PSCI_0_2_FN_PSCI_VERSION		ARM_PSCI_0_2_FN(0)
 #define ARM_PSCI_0_2_FN_CPU_SUSPEND		ARM_PSCI_0_2_FN(1)
 #define ARM_PSCI_0_2_FN_CPU_OFF			ARM_PSCI_0_2_FN(2)
@@ -56,6 +59,12 @@
 #define ARM_PSCI_0_2_FN_SYSTEM_OFF		ARM_PSCI_0_2_FN(8)
 #define ARM_PSCI_0_2_FN_SYSTEM_RESET		ARM_PSCI_0_2_FN(9)
 
+#define ARM_PSCI_0_2_FN64_CPU_SUSPEND		ARM_PSCI_0_2_FN64(1)
+#define ARM_PSCI_0_2_FN64_CPU_ON		ARM_PSCI_0_2_FN64(3)
+#define ARM_PSCI_0_2_FN64_AFFINITY_INFO		ARM_PSCI_0_2_FN64(4)
+#define ARM_PSCI_0_2_FN64_MIGRATE		ARM_PSCI_0_2_FN64(5)
+#define ARM_PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU	ARM_PSCI_0_2_FN64(7)
+
 /* PSCI 1.0 interface */
 #define ARM_PSCI_1_0_FN_PSCI_FEATURES		ARM_PSCI_0_2_FN(10)
 #define ARM_PSCI_1_0_FN_CPU_FREEZE		ARM_PSCI_0_2_FN(11)
@@ -66,6 +75,12 @@
 #define ARM_PSCI_1_0_FN_STAT_RESIDENCY		ARM_PSCI_0_2_FN(16)
 #define ARM_PSCI_1_0_FN_STAT_COUNT		ARM_PSCI_0_2_FN(17)
 
+#define ARM_PSCI_1_0_FN64_CPU_DEFAULT_SUSPEND	ARM_PSCI_0_2_FN64(12)
+#define ARM_PSCI_1_0_FN64_NODE_HW_STATE		ARM_PSCI_0_2_FN64(13)
+#define ARM_PSCI_1_0_FN64_SYSTEM_SUSPEND	ARM_PSCI_0_2_FN64(14)
+#define ARM_PSCI_1_0_FN64_STAT_RESIDENCY	ARM_PSCI_0_2_FN64(16)
+#define ARM_PSCI_1_0_FN64_STAT_COUNT		ARM_PSCI_0_2_FN64(17)
+
 /* 1KB stack per core */
 #define ARM_PSCI_STACK_SHIFT	10
 #define ARM_PSCI_STACK_SIZE	(1 << ARM_PSCI_STACK_SHIFT)