Adding upstream version 5.10.209.upstream/5.10.209

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

4 files changed, 1115 insertions, 0 deletions

diff --git a/drivers/firmware/psci/Kconfig b/drivers/firmware/psci/Kconfig
new file mode 100644
index 000000000..97944168b
--- /dev/null
+++ b/drivers/firmware/psci/Kconfig
@@ -0,0 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config ARM_PSCI_FW
+	bool
+
+config ARM_PSCI_CHECKER
+	bool "ARM PSCI checker"
+	depends on ARM_PSCI_FW && HOTPLUG_CPU && CPU_IDLE && !TORTURE_TEST
+	help
+	  Run the PSCI checker during startup. This checks that hotplug and
+	  suspend operations work correctly when using PSCI.
+
+	  The torture tests may interfere with the PSCI checker by turning CPUs
+	  on and off through hotplug, so for now torture tests and PSCI checker
+	  are mutually exclusive.
diff --git a/drivers/firmware/psci/Makefile b/drivers/firmware/psci/Makefile
new file mode 100644
index 000000000..1956b8824
--- /dev/null
+++ b/drivers/firmware/psci/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+obj-$(CONFIG_ARM_PSCI_FW)	+= psci.o
+obj-$(CONFIG_ARM_PSCI_CHECKER)	+= psci_checker.o
diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c
new file mode 100644
index 000000000..00af99b6f
--- /dev/null
+++ b/drivers/firmware/psci/psci.c
@@ -0,0 +1,605 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *
+ * Copyright (C) 2015 ARM Limited
+ */
+
+#define pr_fmt(fmt) "psci: " fmt
+
+#include <linux/acpi.h>
+#include <linux/arm-smccc.h>
+#include <linux/cpuidle.h>
+#include <linux/errno.h>
+#include <linux/linkage.h>
+#include <linux/of.h>
+#include <linux/pm.h>
+#include <linux/printk.h>
+#include <linux/psci.h>
+#include <linux/reboot.h>
+#include <linux/slab.h>
+#include <linux/suspend.h>
+
+#include <uapi/linux/psci.h>
+
+#include <asm/cpuidle.h>
+#include <asm/cputype.h>
+#include <asm/system_misc.h>
+#include <asm/smp_plat.h>
+#include <asm/suspend.h>
+
+/*
+ * While a 64-bit OS can make calls with SMC32 calling conventions, for some
+ * calls it is necessary to use SMC64 to pass or return 64-bit values.
+ * For such calls PSCI_FN_NATIVE(version, name) will choose the appropriate
+ * (native-width) function ID.
+ */
+#ifdef CONFIG_64BIT
+#define PSCI_FN_NATIVE(version, name)	PSCI_##version##_FN64_##name
+#else
+#define PSCI_FN_NATIVE(version, name)	PSCI_##version##_FN_##name
+#endif
+
+/*
+ * The CPU any Trusted OS is resident on. The trusted OS may reject CPU_OFF
+ * calls to its resident CPU, so we must avoid issuing those. We never migrate
+ * a Trusted OS even if it claims to be capable of migration -- doing so will
+ * require cooperation with a Trusted OS driver.
+ */
+static int resident_cpu = -1;
+struct psci_operations psci_ops;
+static enum arm_smccc_conduit psci_conduit = SMCCC_CONDUIT_NONE;
+
+bool psci_tos_resident_on(int cpu)
+{
+	return cpu == resident_cpu;
+}
+
+typedef unsigned long (psci_fn)(unsigned long, unsigned long,
+				unsigned long, unsigned long);
+static psci_fn *invoke_psci_fn;
+
+enum psci_function {
+	PSCI_FN_CPU_SUSPEND,
+	PSCI_FN_CPU_ON,
+	PSCI_FN_CPU_OFF,
+	PSCI_FN_MIGRATE,
+	PSCI_FN_MAX,
+};
+
+static u32 psci_function_id[PSCI_FN_MAX];
+
+#define PSCI_0_2_POWER_STATE_MASK		\
+				(PSCI_0_2_POWER_STATE_ID_MASK | \
+				PSCI_0_2_POWER_STATE_TYPE_MASK | \
+				PSCI_0_2_POWER_STATE_AFFL_MASK)
+
+#define PSCI_1_0_EXT_POWER_STATE_MASK		\
+				(PSCI_1_0_EXT_POWER_STATE_ID_MASK | \
+				PSCI_1_0_EXT_POWER_STATE_TYPE_MASK)
+
+static u32 psci_cpu_suspend_feature;
+static bool psci_system_reset2_supported;
+
+static inline bool psci_has_ext_power_state(void)
+{
+	return psci_cpu_suspend_feature &
+				PSCI_1_0_FEATURES_CPU_SUSPEND_PF_MASK;
+}
+
+bool psci_has_osi_support(void)
+{
+	return psci_cpu_suspend_feature & PSCI_1_0_OS_INITIATED;
+}
+
+static inline bool psci_power_state_loses_context(u32 state)
+{
+	const u32 mask = psci_has_ext_power_state() ?
+					PSCI_1_0_EXT_POWER_STATE_TYPE_MASK :
+					PSCI_0_2_POWER_STATE_TYPE_MASK;
+
+	return state & mask;
+}
+
+bool psci_power_state_is_valid(u32 state)
+{
+	const u32 valid_mask = psci_has_ext_power_state() ?
+			       PSCI_1_0_EXT_POWER_STATE_MASK :
+			       PSCI_0_2_POWER_STATE_MASK;
+
+	return !(state & ~valid_mask);
+}
+
+static unsigned long __invoke_psci_fn_hvc(unsigned long function_id,
+			unsigned long arg0, unsigned long arg1,
+			unsigned long arg2)
+{
+	struct arm_smccc_res res;
+
+	arm_smccc_hvc(function_id, arg0, arg1, arg2, 0, 0, 0, 0, &res);
+	return res.a0;
+}
+
+static unsigned long __invoke_psci_fn_smc(unsigned long function_id,
+			unsigned long arg0, unsigned long arg1,
+			unsigned long arg2)
+{
+	struct arm_smccc_res res;
+
+	arm_smccc_smc(function_id, arg0, arg1, arg2, 0, 0, 0, 0, &res);
+	return res.a0;
+}
+
+static int psci_to_linux_errno(int errno)
+{
+	switch (errno) {
+	case PSCI_RET_SUCCESS:
+		return 0;
+	case PSCI_RET_NOT_SUPPORTED:
+		return -EOPNOTSUPP;
+	case PSCI_RET_INVALID_PARAMS:
+	case PSCI_RET_INVALID_ADDRESS:
+		return -EINVAL;
+	case PSCI_RET_DENIED:
+		return -EPERM;
+	};
+
+	return -EINVAL;
+}
+
+static u32 psci_get_version(void)
+{
+	return invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0);
+}
+
+int psci_set_osi_mode(bool enable)
+{
+	unsigned long suspend_mode;
+	int err;
+
+	suspend_mode = enable ? PSCI_1_0_SUSPEND_MODE_OSI :
+			PSCI_1_0_SUSPEND_MODE_PC;
+
+	err = invoke_psci_fn(PSCI_1_0_FN_SET_SUSPEND_MODE, suspend_mode, 0, 0);
+	return psci_to_linux_errno(err);
+}
+
+static int psci_cpu_suspend(u32 state, unsigned long entry_point)
+{
+	int err;
+	u32 fn;
+
+	fn = psci_function_id[PSCI_FN_CPU_SUSPEND];
+	err = invoke_psci_fn(fn, state, entry_point, 0);
+	return psci_to_linux_errno(err);
+}
+
+static int psci_cpu_off(u32 state)
+{
+	int err;
+	u32 fn;
+
+	fn = psci_function_id[PSCI_FN_CPU_OFF];
+	err = invoke_psci_fn(fn, state, 0, 0);
+	return psci_to_linux_errno(err);
+}
+
+static int psci_cpu_on(unsigned long cpuid, unsigned long entry_point)
+{
+	int err;
+	u32 fn;
+
+	fn = psci_function_id[PSCI_FN_CPU_ON];
+	err = invoke_psci_fn(fn, cpuid, entry_point, 0);
+	return psci_to_linux_errno(err);
+}
+
+static int psci_migrate(unsigned long cpuid)
+{
+	int err;
+	u32 fn;
+
+	fn = psci_function_id[PSCI_FN_MIGRATE];
+	err = invoke_psci_fn(fn, cpuid, 0, 0);
+	return psci_to_linux_errno(err);
+}
+
+static int psci_affinity_info(unsigned long target_affinity,
+		unsigned long lowest_affinity_level)
+{
+	return invoke_psci_fn(PSCI_FN_NATIVE(0_2, AFFINITY_INFO),
+			      target_affinity, lowest_affinity_level, 0);
+}
+
+static int psci_migrate_info_type(void)
+{
+	return invoke_psci_fn(PSCI_0_2_FN_MIGRATE_INFO_TYPE, 0, 0, 0);
+}
+
+static unsigned long psci_migrate_info_up_cpu(void)
+{
+	return invoke_psci_fn(PSCI_FN_NATIVE(0_2, MIGRATE_INFO_UP_CPU),
+			      0, 0, 0);
+}
+
+static void set_conduit(enum arm_smccc_conduit conduit)
+{
+	switch (conduit) {
+	case SMCCC_CONDUIT_HVC:
+		invoke_psci_fn = __invoke_psci_fn_hvc;
+		break;
+	case SMCCC_CONDUIT_SMC:
+		invoke_psci_fn = __invoke_psci_fn_smc;
+		break;
+	default:
+		WARN(1, "Unexpected PSCI conduit %d\n", conduit);
+	}
+
+	psci_conduit = conduit;
+}
+
+static int get_set_conduit_method(struct device_node *np)
+{
+	const char *method;
+
+	pr_info("probing for conduit method from DT.\n");
+
+	if (of_property_read_string(np, "method", &method)) {
+		pr_warn("missing \"method\" property\n");
+		return -ENXIO;
+	}
+
+	if (!strcmp("hvc", method)) {
+		set_conduit(SMCCC_CONDUIT_HVC);
+	} else if (!strcmp("smc", method)) {
+		set_conduit(SMCCC_CONDUIT_SMC);
+	} else {
+		pr_warn("invalid \"method\" property: %s\n", method);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static void psci_sys_reset(enum reboot_mode reboot_mode, const char *cmd)
+{
+	if ((reboot_mode == REBOOT_WARM || reboot_mode == REBOOT_SOFT) &&
+	    psci_system_reset2_supported) {
+		/*
+		 * reset_type[31] = 0 (architectural)
+		 * reset_type[30:0] = 0 (SYSTEM_WARM_RESET)
+		 * cookie = 0 (ignored by the implementation)
+		 */
+		invoke_psci_fn(PSCI_FN_NATIVE(1_1, SYSTEM_RESET2), 0, 0, 0);
+	} else {
+		invoke_psci_fn(PSCI_0_2_FN_SYSTEM_RESET, 0, 0, 0);
+	}
+}
+
+static void psci_sys_poweroff(void)
+{
+	invoke_psci_fn(PSCI_0_2_FN_SYSTEM_OFF, 0, 0, 0);
+}
+
+static int __init psci_features(u32 psci_func_id)
+{
+	return invoke_psci_fn(PSCI_1_0_FN_PSCI_FEATURES,
+			      psci_func_id, 0, 0);
+}
+
+#ifdef CONFIG_CPU_IDLE
+static int psci_suspend_finisher(unsigned long state)
+{
+	u32 power_state = state;
+
+	return psci_ops.cpu_suspend(power_state, __pa_symbol(cpu_resume));
+}
+
+int psci_cpu_suspend_enter(u32 state)
+{
+	int ret;
+
+	if (!psci_power_state_loses_context(state))
+		ret = psci_ops.cpu_suspend(state, 0);
+	else
+		ret = cpu_suspend(state, psci_suspend_finisher);
+
+	return ret;
+}
+#endif
+
+static int psci_system_suspend(unsigned long unused)
+{
+	return invoke_psci_fn(PSCI_FN_NATIVE(1_0, SYSTEM_SUSPEND),
+			      __pa_symbol(cpu_resume), 0, 0);
+}
+
+static int psci_system_suspend_enter(suspend_state_t state)
+{
+	return cpu_suspend(0, psci_system_suspend);
+}
+
+static const struct platform_suspend_ops psci_suspend_ops = {
+	.valid          = suspend_valid_only_mem,
+	.enter          = psci_system_suspend_enter,
+};
+
+static void __init psci_init_system_reset2(void)
+{
+	int ret;
+
+	ret = psci_features(PSCI_FN_NATIVE(1_1, SYSTEM_RESET2));
+
+	if (ret != PSCI_RET_NOT_SUPPORTED)
+		psci_system_reset2_supported = true;
+}
+
+static void __init psci_init_system_suspend(void)
+{
+	int ret;
+
+	if (!IS_ENABLED(CONFIG_SUSPEND))
+		return;
+
+	ret = psci_features(PSCI_FN_NATIVE(1_0, SYSTEM_SUSPEND));
+
+	if (ret != PSCI_RET_NOT_SUPPORTED)
+		suspend_set_ops(&psci_suspend_ops);
+}
+
+static void __init psci_init_cpu_suspend(void)
+{
+	int feature = psci_features(psci_function_id[PSCI_FN_CPU_SUSPEND]);
+
+	if (feature != PSCI_RET_NOT_SUPPORTED)
+		psci_cpu_suspend_feature = feature;
+}
+
+/*
+ * Detect the presence of a resident Trusted OS which may cause CPU_OFF to
+ * return DENIED (which would be fatal).
+ */
+static void __init psci_init_migrate(void)
+{
+	unsigned long cpuid;
+	int type, cpu = -1;
+
+	type = psci_ops.migrate_info_type();
+
+	if (type == PSCI_0_2_TOS_MP) {
+		pr_info("Trusted OS migration not required\n");
+		return;
+	}
+
+	if (type == PSCI_RET_NOT_SUPPORTED) {
+		pr_info("MIGRATE_INFO_TYPE not supported.\n");
+		return;
+	}
+
+	if (type != PSCI_0_2_TOS_UP_MIGRATE &&
+	    type != PSCI_0_2_TOS_UP_NO_MIGRATE) {
+		pr_err("MIGRATE_INFO_TYPE returned unknown type (%d)\n", type);
+		return;
+	}
+
+	cpuid = psci_migrate_info_up_cpu();
+	if (cpuid & ~MPIDR_HWID_BITMASK) {
+		pr_warn("MIGRATE_INFO_UP_CPU reported invalid physical ID (0x%lx)\n",
+			cpuid);
+		return;
+	}
+
+	cpu = get_logical_index(cpuid);
+	resident_cpu = cpu >= 0 ? cpu : -1;
+
+	pr_info("Trusted OS resident on physical CPU 0x%lx\n", cpuid);
+}
+
+static void __init psci_init_smccc(void)
+{
+	u32 ver = ARM_SMCCC_VERSION_1_0;
+	int feature;
+
+	feature = psci_features(ARM_SMCCC_VERSION_FUNC_ID);
+
+	if (feature != PSCI_RET_NOT_SUPPORTED) {
+		u32 ret;
+		ret = invoke_psci_fn(ARM_SMCCC_VERSION_FUNC_ID, 0, 0, 0);
+		if (ret >= ARM_SMCCC_VERSION_1_1) {
+			arm_smccc_version_init(ret, psci_conduit);
+			ver = ret;
+		}
+	}
+
+	/*
+	 * Conveniently, the SMCCC and PSCI versions are encoded the
+	 * same way. No, this isn't accidental.
+	 */
+	pr_info("SMC Calling Convention v%d.%d\n",
+		PSCI_VERSION_MAJOR(ver), PSCI_VERSION_MINOR(ver));
+
+}
+
+static void __init psci_0_2_set_functions(void)
+{
+	pr_info("Using standard PSCI v0.2 function IDs\n");
+	psci_ops.get_version = psci_get_version;
+
+	psci_function_id[PSCI_FN_CPU_SUSPEND] =
+					PSCI_FN_NATIVE(0_2, CPU_SUSPEND);
+	psci_ops.cpu_suspend = psci_cpu_suspend;
+
+	psci_function_id[PSCI_FN_CPU_OFF] = PSCI_0_2_FN_CPU_OFF;
+	psci_ops.cpu_off = psci_cpu_off;
+
+	psci_function_id[PSCI_FN_CPU_ON] = PSCI_FN_NATIVE(0_2, CPU_ON);
+	psci_ops.cpu_on = psci_cpu_on;
+
+	psci_function_id[PSCI_FN_MIGRATE] = PSCI_FN_NATIVE(0_2, MIGRATE);
+	psci_ops.migrate = psci_migrate;
+
+	psci_ops.affinity_info = psci_affinity_info;
+
+	psci_ops.migrate_info_type = psci_migrate_info_type;
+
+	arm_pm_restart = psci_sys_reset;
+
+	pm_power_off = psci_sys_poweroff;
+}
+
+/*
+ * Probe function for PSCI firmware versions >= 0.2
+ */
+static int __init psci_probe(void)
+{
+	u32 ver = psci_get_version();
+
+	pr_info("PSCIv%d.%d detected in firmware.\n",
+			PSCI_VERSION_MAJOR(ver),
+			PSCI_VERSION_MINOR(ver));
+
+	if (PSCI_VERSION_MAJOR(ver) == 0 && PSCI_VERSION_MINOR(ver) < 2) {
+		pr_err("Conflicting PSCI version detected.\n");
+		return -EINVAL;
+	}
+
+	psci_0_2_set_functions();
+
+	psci_init_migrate();
+
+	if (PSCI_VERSION_MAJOR(ver) >= 1) {
+		psci_init_smccc();
+		psci_init_cpu_suspend();
+		psci_init_system_suspend();
+		psci_init_system_reset2();
+	}
+
+	return 0;
+}
+
+typedef int (*psci_initcall_t)(const struct device_node *);
+
+/*
+ * PSCI init function for PSCI versions >=0.2
+ *
+ * Probe based on PSCI PSCI_VERSION function
+ */
+static int __init psci_0_2_init(struct device_node *np)
+{
+	int err;
+
+	err = get_set_conduit_method(np);
+	if (err)
+		return err;
+
+	/*
+	 * Starting with v0.2, the PSCI specification introduced a call
+	 * (PSCI_VERSION) that allows probing the firmware version, so
+	 * that PSCI function IDs and version specific initialization
+	 * can be carried out according to the specific version reported
+	 * by firmware
+	 */
+	return psci_probe();
+}
+
+/*
+ * PSCI < v0.2 get PSCI Function IDs via DT.
+ */
+static int __init psci_0_1_init(struct device_node *np)
+{
+	u32 id;
+	int err;
+
+	err = get_set_conduit_method(np);
+	if (err)
+		return err;
+
+	pr_info("Using PSCI v0.1 Function IDs from DT\n");
+
+	if (!of_property_read_u32(np, "cpu_suspend", &id)) {
+		psci_function_id[PSCI_FN_CPU_SUSPEND] = id;
+		psci_ops.cpu_suspend = psci_cpu_suspend;
+	}
+
+	if (!of_property_read_u32(np, "cpu_off", &id)) {
+		psci_function_id[PSCI_FN_CPU_OFF] = id;
+		psci_ops.cpu_off = psci_cpu_off;
+	}
+
+	if (!of_property_read_u32(np, "cpu_on", &id)) {
+		psci_function_id[PSCI_FN_CPU_ON] = id;
+		psci_ops.cpu_on = psci_cpu_on;
+	}
+
+	if (!of_property_read_u32(np, "migrate", &id)) {
+		psci_function_id[PSCI_FN_MIGRATE] = id;
+		psci_ops.migrate = psci_migrate;
+	}
+
+	return 0;
+}
+
+static int __init psci_1_0_init(struct device_node *np)
+{
+	int err;
+
+	err = psci_0_2_init(np);
+	if (err)
+		return err;
+
+	if (psci_has_osi_support()) {
+		pr_info("OSI mode supported.\n");
+
+		/* Default to PC mode. */
+		psci_set_osi_mode(false);
+	}
+
+	return 0;
+}
+
+static const struct of_device_id psci_of_match[] __initconst = {
+	{ .compatible = "arm,psci",	.data = psci_0_1_init},
+	{ .compatible = "arm,psci-0.2",	.data = psci_0_2_init},
+	{ .compatible = "arm,psci-1.0",	.data = psci_1_0_init},
+	{},
+};
+
+int __init psci_dt_init(void)
+{
+	struct device_node *np;
+	const struct of_device_id *matched_np;
+	psci_initcall_t init_fn;
+	int ret;
+
+	np = of_find_matching_node_and_match(NULL, psci_of_match, &matched_np);
+
+	if (!np || !of_device_is_available(np))
+		return -ENODEV;
+
+	init_fn = (psci_initcall_t)matched_np->data;
+	ret = init_fn(np);
+
+	of_node_put(np);
+	return ret;
+}
+
+#ifdef CONFIG_ACPI
+/*
+ * We use PSCI 0.2+ when ACPI is deployed on ARM64 and it's
+ * explicitly clarified in SBBR
+ */
+int __init psci_acpi_init(void)
+{
+	if (!acpi_psci_present()) {
+		pr_info("is not implemented in ACPI.\n");
+		return -EOPNOTSUPP;
+	}
+
+	pr_info("probing for conduit method from ACPI.\n");
+
+	if (acpi_psci_use_hvc())
+		set_conduit(SMCCC_CONDUIT_HVC);
+	else
+		set_conduit(SMCCC_CONDUIT_SMC);
+
+	return psci_probe();
+}
+#endif
diff --git a/drivers/firmware/psci/psci_checker.c b/drivers/firmware/psci/psci_checker.c
new file mode 100644
index 000000000..116eb465c
--- /dev/null
+++ b/drivers/firmware/psci/psci_checker.c
@@ -0,0 +1,492 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *
+ * Copyright (C) 2016 ARM Limited
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/atomic.h>
+#include <linux/completion.h>
+#include <linux/cpu.h>
+#include <linux/cpuidle.h>
+#include <linux/cpu_pm.h>
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <uapi/linux/sched/types.h>
+#include <linux/module.h>
+#include <linux/preempt.h>
+#include <linux/psci.h>
+#include <linux/slab.h>
+#include <linux/tick.h>
+#include <linux/topology.h>
+
+#include <asm/cpuidle.h>
+
+#include <uapi/linux/psci.h>
+
+#define NUM_SUSPEND_CYCLE (10)
+
+static unsigned int nb_available_cpus;
+static int tos_resident_cpu = -1;
+
+static atomic_t nb_active_threads;
+static struct completion suspend_threads_started =
+	COMPLETION_INITIALIZER(suspend_threads_started);
+static struct completion suspend_threads_done =
+	COMPLETION_INITIALIZER(suspend_threads_done);
+
+/*
+ * We assume that PSCI operations are used if they are available. This is not
+ * necessarily true on arm64, since the decision is based on the
+ * "enable-method" property of each CPU in the DT, but given that there is no
+ * arch-specific way to check this, we assume that the DT is sensible.
+ */
+static int psci_ops_check(void)
+{
+	int migrate_type = -1;
+	int cpu;
+
+	if (!(psci_ops.cpu_off && psci_ops.cpu_on && psci_ops.cpu_suspend)) {
+		pr_warn("Missing PSCI operations, aborting tests\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (psci_ops.migrate_info_type)
+		migrate_type = psci_ops.migrate_info_type();
+
+	if (migrate_type == PSCI_0_2_TOS_UP_MIGRATE ||
+	    migrate_type == PSCI_0_2_TOS_UP_NO_MIGRATE) {
+		/* There is a UP Trusted OS, find on which core it resides. */
+		for_each_online_cpu(cpu)
+			if (psci_tos_resident_on(cpu)) {
+				tos_resident_cpu = cpu;
+				break;
+			}
+		if (tos_resident_cpu == -1)
+			pr_warn("UP Trusted OS resides on no online CPU\n");
+	}
+
+	return 0;
+}
+
+/*
+ * offlined_cpus is a temporary array but passing it as an argument avoids
+ * multiple allocations.
+ */
+static unsigned int down_and_up_cpus(const struct cpumask *cpus,
+				     struct cpumask *offlined_cpus)
+{
+	int cpu;
+	int err = 0;
+
+	cpumask_clear(offlined_cpus);
+
+	/* Try to power down all CPUs in the mask. */
+	for_each_cpu(cpu, cpus) {
+		int ret = remove_cpu(cpu);
+
+		/*
+		 * cpu_down() checks the number of online CPUs before the TOS
+		 * resident CPU.
+		 */
+		if (cpumask_weight(offlined_cpus) + 1 == nb_available_cpus) {
+			if (ret != -EBUSY) {
+				pr_err("Unexpected return code %d while trying "
+				       "to power down last online CPU %d\n",
+				       ret, cpu);
+				++err;
+			}
+		} else if (cpu == tos_resident_cpu) {
+			if (ret != -EPERM) {
+				pr_err("Unexpected return code %d while trying "
+				       "to power down TOS resident CPU %d\n",
+				       ret, cpu);
+				++err;
+			}
+		} else if (ret != 0) {
+			pr_err("Error occurred (%d) while trying "
+			       "to power down CPU %d\n", ret, cpu);
+			++err;
+		}
+
+		if (ret == 0)
+			cpumask_set_cpu(cpu, offlined_cpus);
+	}
+
+	/* Try to power up all the CPUs that have been offlined. */
+	for_each_cpu(cpu, offlined_cpus) {
+		int ret = add_cpu(cpu);
+
+		if (ret != 0) {
+			pr_err("Error occurred (%d) while trying "
+			       "to power up CPU %d\n", ret, cpu);
+			++err;
+		} else {
+			cpumask_clear_cpu(cpu, offlined_cpus);
+		}
+	}
+
+	/*
+	 * Something went bad at some point and some CPUs could not be turned
+	 * back on.
+	 */
+	WARN_ON(!cpumask_empty(offlined_cpus) ||
+		num_online_cpus() != nb_available_cpus);
+
+	return err;
+}
+
+static void free_cpu_groups(int num, cpumask_var_t **pcpu_groups)
+{
+	int i;
+	cpumask_var_t *cpu_groups = *pcpu_groups;
+
+	for (i = 0; i < num; ++i)
+		free_cpumask_var(cpu_groups[i]);
+	kfree(cpu_groups);
+}
+
+static int alloc_init_cpu_groups(cpumask_var_t **pcpu_groups)
+{
+	int num_groups = 0;
+	cpumask_var_t tmp, *cpu_groups;
+
+	if (!alloc_cpumask_var(&tmp, GFP_KERNEL))
+		return -ENOMEM;
+
+	cpu_groups = kcalloc(nb_available_cpus, sizeof(*cpu_groups),
+			     GFP_KERNEL);
+	if (!cpu_groups) {
+		free_cpumask_var(tmp);
+		return -ENOMEM;
+	}
+
+	cpumask_copy(tmp, cpu_online_mask);
+
+	while (!cpumask_empty(tmp)) {
+		const struct cpumask *cpu_group =
+			topology_core_cpumask(cpumask_any(tmp));
+
+		if (!alloc_cpumask_var(&cpu_groups[num_groups], GFP_KERNEL)) {
+			free_cpumask_var(tmp);
+			free_cpu_groups(num_groups, &cpu_groups);
+			return -ENOMEM;
+		}
+		cpumask_copy(cpu_groups[num_groups++], cpu_group);
+		cpumask_andnot(tmp, tmp, cpu_group);
+	}
+
+	free_cpumask_var(tmp);
+	*pcpu_groups = cpu_groups;
+
+	return num_groups;
+}
+
+static int hotplug_tests(void)
+{
+	int i, nb_cpu_group, err = -ENOMEM;
+	cpumask_var_t offlined_cpus, *cpu_groups;
+	char *page_buf;
+
+	if (!alloc_cpumask_var(&offlined_cpus, GFP_KERNEL))
+		return err;
+
+	nb_cpu_group = alloc_init_cpu_groups(&cpu_groups);
+	if (nb_cpu_group < 0)
+		goto out_free_cpus;
+	page_buf = (char *)__get_free_page(GFP_KERNEL);
+	if (!page_buf)
+		goto out_free_cpu_groups;
+
+	/*
+	 * Of course the last CPU cannot be powered down and cpu_down() should
+	 * refuse doing that.
+	 */
+	pr_info("Trying to turn off and on again all CPUs\n");
+	err = down_and_up_cpus(cpu_online_mask, offlined_cpus);
+
+	/*
+	 * Take down CPUs by cpu group this time. When the last CPU is turned
+	 * off, the cpu group itself should shut down.
+	 */
+	for (i = 0; i < nb_cpu_group; ++i) {
+		ssize_t len = cpumap_print_to_pagebuf(true, page_buf,
+						      cpu_groups[i]);
+		/* Remove trailing newline. */
+		page_buf[len - 1] = '\0';
+		pr_info("Trying to turn off and on again group %d (CPUs %s)\n",
+			i, page_buf);
+		err += down_and_up_cpus(cpu_groups[i], offlined_cpus);
+	}
+
+	free_page((unsigned long)page_buf);
+out_free_cpu_groups:
+	free_cpu_groups(nb_cpu_group, &cpu_groups);
+out_free_cpus:
+	free_cpumask_var(offlined_cpus);
+	return err;
+}
+
+static void dummy_callback(struct timer_list *unused) {}
+
+static int suspend_cpu(struct cpuidle_device *dev,
+		       struct cpuidle_driver *drv, int index)
+{
+	struct cpuidle_state *state = &drv->states[index];
+	bool broadcast = state->flags & CPUIDLE_FLAG_TIMER_STOP;
+	int ret;
+
+	arch_cpu_idle_enter();
+
+	if (broadcast) {
+		/*
+		 * The local timer will be shut down, we need to enter tick
+		 * broadcast.
+		 */
+		ret = tick_broadcast_enter();
+		if (ret) {
+			/*
+			 * In the absence of hardware broadcast mechanism,
+			 * this CPU might be used to broadcast wakeups, which
+			 * may be why entering tick broadcast has failed.
+			 * There is little the kernel can do to work around
+			 * that, so enter WFI instead (idle state 0).
+			 */
+			cpu_do_idle();
+			ret = 0;
+			goto out_arch_exit;
+		}
+	}
+
+	ret = state->enter(dev, drv, index);
+
+	if (broadcast)
+		tick_broadcast_exit();
+
+out_arch_exit:
+	arch_cpu_idle_exit();
+
+	return ret;
+}
+
+static int suspend_test_thread(void *arg)
+{
+	int cpu = (long)arg;
+	int i, nb_suspend = 0, nb_shallow_sleep = 0, nb_err = 0;
+	struct cpuidle_device *dev;
+	struct cpuidle_driver *drv;
+	/* No need for an actual callback, we just want to wake up the CPU. */
+	struct timer_list wakeup_timer;
+
+	/* Wait for the main thread to give the start signal. */
+	wait_for_completion(&suspend_threads_started);
+
+	/* Set maximum priority to preempt all other threads on this CPU. */
+	sched_set_fifo(current);
+
+	dev = this_cpu_read(cpuidle_devices);
+	drv = cpuidle_get_cpu_driver(dev);
+
+	pr_info("CPU %d entering suspend cycles, states 1 through %d\n",
+		cpu, drv->state_count - 1);
+
+	timer_setup_on_stack(&wakeup_timer, dummy_callback, 0);
+	for (i = 0; i < NUM_SUSPEND_CYCLE; ++i) {
+		int index;
+		/*
+		 * Test all possible states, except 0 (which is usually WFI and
+		 * doesn't use PSCI).
+		 */
+		for (index = 1; index < drv->state_count; ++index) {
+			int ret;
+			struct cpuidle_state *state = &drv->states[index];
+
+			/*
+			 * Set the timer to wake this CPU up in some time (which
+			 * should be largely sufficient for entering suspend).
+			 * If the local tick is disabled when entering suspend,
+			 * suspend_cpu() takes care of switching to a broadcast
+			 * tick, so the timer will still wake us up.
+			 */
+			mod_timer(&wakeup_timer, jiffies +
+				  usecs_to_jiffies(state->target_residency));
+
+			/* IRQs must be disabled during suspend operations. */
+			local_irq_disable();
+
+			ret = suspend_cpu(dev, drv, index);
+
+			/*
+			 * We have woken up. Re-enable IRQs to handle any
+			 * pending interrupt, do not wait until the end of the
+			 * loop.
+			 */
+			local_irq_enable();
+
+			if (ret == index) {
+				++nb_suspend;
+			} else if (ret >= 0) {
+				/* We did not enter the expected state. */
+				++nb_shallow_sleep;
+			} else {
+				pr_err("Failed to suspend CPU %d: error %d "
+				       "(requested state %d, cycle %d)\n",
+				       cpu, ret, index, i);
+				++nb_err;
+			}
+		}
+	}
+
+	/*
+	 * Disable the timer to make sure that the timer will not trigger
+	 * later.
+	 */
+	del_timer(&wakeup_timer);
+	destroy_timer_on_stack(&wakeup_timer);
+
+	if (atomic_dec_return_relaxed(&nb_active_threads) == 0)
+		complete(&suspend_threads_done);
+
+	for (;;) {
+		/* Needs to be set first to avoid missing a wakeup. */
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (kthread_should_park())
+			break;
+		schedule();
+	}
+
+	pr_info("CPU %d suspend test results: success %d, shallow states %d, errors %d\n",
+		cpu, nb_suspend, nb_shallow_sleep, nb_err);
+
+	kthread_parkme();
+
+	return nb_err;
+}
+
+static int suspend_tests(void)
+{
+	int i, cpu, err = 0;
+	struct task_struct **threads;
+	int nb_threads = 0;
+
+	threads = kmalloc_array(nb_available_cpus, sizeof(*threads),
+				GFP_KERNEL);
+	if (!threads)
+		return -ENOMEM;
+
+	/*
+	 * Stop cpuidle to prevent the idle tasks from entering a deep sleep
+	 * mode, as it might interfere with the suspend threads on other CPUs.
+	 * This does not prevent the suspend threads from using cpuidle (only
+	 * the idle tasks check this status). Take the idle lock so that
+	 * the cpuidle driver and device look-up can be carried out safely.
+	 */
+	cpuidle_pause_and_lock();
+
+	for_each_online_cpu(cpu) {
+		struct task_struct *thread;
+		/* Check that cpuidle is available on that CPU. */
+		struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu);
+		struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
+
+		if (!dev || !drv) {
+			pr_warn("cpuidle not available on CPU %d, ignoring\n",
+				cpu);
+			continue;
+		}
+
+		thread = kthread_create_on_cpu(suspend_test_thread,
+					       (void *)(long)cpu, cpu,
+					       "psci_suspend_test");
+		if (IS_ERR(thread))
+			pr_err("Failed to create kthread on CPU %d\n", cpu);
+		else
+			threads[nb_threads++] = thread;
+	}
+
+	if (nb_threads < 1) {
+		err = -ENODEV;
+		goto out;
+	}
+
+	atomic_set(&nb_active_threads, nb_threads);
+
+	/*
+	 * Wake up the suspend threads. To avoid the main thread being preempted
+	 * before all the threads have been unparked, the suspend threads will
+	 * wait for the completion of suspend_threads_started.
+	 */
+	for (i = 0; i < nb_threads; ++i)
+		wake_up_process(threads[i]);
+	complete_all(&suspend_threads_started);
+
+	wait_for_completion(&suspend_threads_done);
+
+
+	/* Stop and destroy all threads, get return status. */
+	for (i = 0; i < nb_threads; ++i) {
+		err += kthread_park(threads[i]);
+		err += kthread_stop(threads[i]);
+	}
+ out:
+	cpuidle_resume_and_unlock();
+	kfree(threads);
+	return err;
+}
+
+static int __init psci_checker(void)
+{
+	int ret;
+
+	/*
+	 * Since we're in an initcall, we assume that all the CPUs that all
+	 * CPUs that can be onlined have been onlined.
+	 *
+	 * The tests assume that hotplug is enabled but nobody else is using it,
+	 * otherwise the results will be unpredictable. However, since there
+	 * is no userspace yet in initcalls, that should be fine, as long as
+	 * no torture test is running at the same time (see Kconfig).
+	 */
+	nb_available_cpus = num_online_cpus();
+
+	/* Check PSCI operations are set up and working. */
+	ret = psci_ops_check();
+	if (ret)
+		return ret;
+
+	pr_info("PSCI checker started using %u CPUs\n", nb_available_cpus);
+
+	pr_info("Starting hotplug tests\n");
+	ret = hotplug_tests();
+	if (ret == 0)
+		pr_info("Hotplug tests passed OK\n");
+	else if (ret > 0)
+		pr_err("%d error(s) encountered in hotplug tests\n", ret);
+	else {
+		pr_err("Out of memory\n");
+		return ret;
+	}
+
+	pr_info("Starting suspend tests (%d cycles per state)\n",
+		NUM_SUSPEND_CYCLE);
+	ret = suspend_tests();
+	if (ret == 0)
+		pr_info("Suspend tests passed OK\n");
+	else if (ret > 0)
+		pr_err("%d error(s) encountered in suspend tests\n", ret);
+	else {
+		switch (ret) {
+		case -ENOMEM:
+			pr_err("Out of memory\n");
+			break;
+		case -ENODEV:
+			pr_warn("Could not start suspend tests on any CPU\n");
+			break;
+		}
+	}
+
+	pr_info("PSCI checker completed\n");
+	return ret < 0 ? ret : 0;
+}
+late_initcall(psci_checker);