tegra124: Add PSCI support for Tegra124

This is based on Thierry Reding's work and uses Ian Campell's
preparatory patches. It comes with full support for CPU_ON/OFF PSCI
services. The algorithm used in this version for turning CPUs on and
off was proposed by Peter De Schrijver and Thierry Reding in
http://thread.gmane.org/gmane.comp.boot-loaders.u-boot/210881. It
consists of first enabling CPU1..3 via the PMC, just to powergate them
again with the help of the Flow Controller. Once the Flow Controller is
in place, we can leave the PMC alone while processing CPU_ON and CPU_OFF
PSCI requests.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Tom Warren <twarren@nvidia.com>

arch/arm/include/asm/arch-tegra124/flow.h

@@ -37,4 +37,10 @@ struct flow_ctlr {
 /* FLOW_CTLR_CLUSTER_CONTROL_0 0x2c */
 #define ACTIVE_LP		(1 << 0)
 
+/* CPUn_CSR_0 */
+#define CSR_ENABLE		(1 << 0)
+#define CSR_IMMEDIATE_WAKE	(1 << 3)
+#define CSR_WAIT_WFI_SHIFT	8
+#define CSR_PWR_OFF_STS		(1 << 16)
+
 #endif	/*  _TEGRA124_FLOW_H_ */

arch/arm/mach-tegra/Makefile

@@ -26,6 +26,10 @@ obj-y += xusb-padctl.o
 obj-$(CONFIG_DISPLAY_CPUINFO) += sys_info.o
 obj-$(CONFIG_TEGRA124) += vpr.o
 
+ifndef CONFIG_SPL_BUILD
+obj-$(CONFIG_ARMV7_PSCI) += psci.o
+endif
+
 obj-$(CONFIG_TEGRA20) += tegra20/
 obj-$(CONFIG_TEGRA30) += tegra30/
 obj-$(CONFIG_TEGRA114) += tegra114/

arch/arm/mach-tegra/psci.S

@@ -0,0 +1,101 @@
+/*
+ * Copyright (C) 2014, NVIDIA
+ * Copyright (C) 2015, Siemens AG
+ *
+ * Authors:
+ *  Thierry Reding <treding@nvidia.com>
+ *  Jan Kiszka <jan.kiszka@siemens.com>
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+
+#include <linux/linkage.h>
+#include <asm/macro.h>
+#include <asm/psci.h>
+
+	.pushsection ._secure.text, "ax"
+	.arch_extension sec
+
+#define TEGRA_SB_CSR_0			0x6000c200
+#define NS_RST_VEC_WR_DIS		(1 << 1)
+
+#define TEGRA_RESET_EXCEPTION_VECTOR	0x6000f100
+
+#define TEGRA_FLOW_CTRL_BASE		0x60007000
+#define FLOW_CTRL_CPU_CSR		0x08
+#define CSR_ENABLE			(1 << 0)
+#define CSR_IMMEDIATE_WAKE		(1 << 3)
+#define CSR_WAIT_WFI_SHIFT		8
+#define FLOW_CTRL_CPU1_CSR		0x18
+
+@ converts CPU ID into FLOW_CTRL_CPUn_CSR offset
+.macro get_csr_reg cpu, ofs, tmp
+	cmp	\cpu, #0		@ CPU0?
+	lsl	\tmp, \cpu, #3	@ multiple by 8 (register offset CPU1-3)
+	moveq	\ofs, #FLOW_CTRL_CPU_CSR
+	addne	\ofs, \tmp, #FLOW_CTRL_CPU1_CSR - 8
+.endm
+
+ENTRY(psci_arch_init)
+	mov	r6, lr
+
+	mrc	p15, 0, r5, c1, c1, 0	@ Read SCR
+	bic	r5, r5, #1		@ Secure mode
+	mcr	p15, 0, r5, c1, c1, 0	@ Write SCR
+	isb
+
+	@ lock reset vector for non-secure
+	ldr	r4, =TEGRA_SB_CSR_0
+	ldr	r5, [r4]
+	orr	r5, r5, #NS_RST_VEC_WR_DIS
+	str	r5, [r4]
+
+	bl	psci_get_cpu_id		@ CPU ID => r0
+	bl	psci_get_cpu_stack_top	@ stack top => r0
+	mov	sp, r0
+
+	bx	r6
+ENDPROC(psci_arch_init)
+
+ENTRY(psci_cpu_off)
+	bl	psci_cpu_off_common
+
+	bl	psci_get_cpu_id		@ CPU ID => r0
+
+	get_csr_reg r0, r2, r3
+
+	ldr	r6, =TEGRA_FLOW_CTRL_BASE
+	mov	r5, #(CSR_ENABLE)
+	mov	r4, #(1 << CSR_WAIT_WFI_SHIFT)
+	add	r5, r4, lsl r0
+	str	r5, [r6, r2]
+
+_loop:	wfi
+	b	_loop
+ENDPROC(psci_cpu_off)
+
+ENTRY(psci_cpu_on)
+	push	{lr}
+
+	mov	r0, r1
+	bl	psci_get_cpu_stack_top	@ get stack top of target CPU
+	str	r2, [r0]		@ store target PC at stack top
+	dsb
+
+	ldr	r6, =TEGRA_RESET_EXCEPTION_VECTOR
+	ldr	r5, =psci_cpu_entry
+	str	r5, [r6]
+
+	get_csr_reg r1, r2, r3
+
+	ldr	r6, =TEGRA_FLOW_CTRL_BASE
+	mov	r5, #(CSR_IMMEDIATE_WAKE | CSR_ENABLE)
+	str	r5, [r6, r2]
+
+	mov	r0, #ARM_PSCI_RET_SUCCESS	@ Return PSCI_RET_SUCCESS
+	pop	{pc}
+ENDPROC(psci_cpu_on)
+
+	.globl psci_text_end
+psci_text_end:
+	.popsection

arch/arm/mach-tegra/tegra124/Makefile

@@ -11,3 +11,7 @@ obj-y	+= clock.o
 obj-y	+= funcmux.o
 obj-y	+= pinmux.o
 obj-y	+= xusb-padctl.o
+
+ifndef CONFIG_SPL_BUILD
+obj-$(CONFIG_ARMV7_NONSEC) += psci.o
+endif

arch/arm/mach-tegra/tegra124/psci.c

@@ -0,0 +1,59 @@
+/*
+ * (C) Copyright 2015, Siemens AG
+ * Author: Jan Kiszka <jan.kiszka@siemens.com>
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+
+#include <common.h>
+#include <asm/io.h>
+#include <asm/psci.h>
+#include <asm/arch/flow.h>
+#include <asm/arch/powergate.h>
+#include <asm/arch-tegra/ap.h>
+#include <asm/arch-tegra/pmc.h>
+
+static void park_cpu(void)
+{
+	while (1)
+		asm volatile("wfi");
+}
+
+/**
+ * Initialize power management for application processors
+ */
+void psci_board_init(void)
+{
+	struct flow_ctlr *flow = (struct flow_ctlr *)NV_PA_FLOW_BASE;
+
+	writel((u32)park_cpu, EXCEP_VECTOR_CPU_RESET_VECTOR);
+
+	/*
+	 * The naturally expected order of putting these CPUs under Flow
+	 * Controller regime would be
+	 *  - configure the Flow Controller
+	 *  - power up the CPUs
+	 *  - wait for the CPUs to hit wfi and be powered down again
+	 *
+	 * However, this doesn't work in practice. We rather need to power them
+	 * up first and park them in wfi. While they are waiting there, we can
+	 * indeed program the Flow Controller to powergate them on wfi, which
+	 * will then happen immediately as they are already in that state.
+	 */
+	tegra_powergate_power_on(TEGRA_POWERGATE_CPU1);
+	tegra_powergate_power_on(TEGRA_POWERGATE_CPU2);
+	tegra_powergate_power_on(TEGRA_POWERGATE_CPU3);
+
+	writel((2 << CSR_WAIT_WFI_SHIFT) | CSR_ENABLE, &flow->cpu1_csr);
+	writel((4 << CSR_WAIT_WFI_SHIFT) | CSR_ENABLE, &flow->cpu2_csr);
+	writel((8 << CSR_WAIT_WFI_SHIFT) | CSR_ENABLE, &flow->cpu3_csr);
+
+	writel(EVENT_MODE_STOP, &flow->halt_cpu1_events);
+	writel(EVENT_MODE_STOP, &flow->halt_cpu2_events);
+	writel(EVENT_MODE_STOP, &flow->halt_cpu3_events);
+
+	while (!(readl(&flow->cpu1_csr) & CSR_PWR_OFF_STS) ||
+		!(readl(&flow->cpu2_csr) & CSR_PWR_OFF_STS) ||
+		!(readl(&flow->cpu3_csr) & CSR_PWR_OFF_STS))
+		/* wait */;
+}