Merge tag 'pm-5.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These are PM-runtime framework changes to use ktime instead of jiffies
  for accounting, new PM core flag to mark devices that don't need any
  form of power management, cpuidle updates including driver API
  documentation and a new governor, cpufreq updates including a new
  driver for Armada 8K, thermal cleanups and more, some energy-aware
  scheduling (EAS) enabling changes, new chips support in the intel_idle
  and RAPL drivers and assorted cleanups in some other places.

  Specifics:

   - Update the PM-runtime framework to use ktime instead of jiffies for
     accounting (Thara Gopinath, Vincent Guittot)

   - Optimize the autosuspend code in the PM-runtime framework somewhat
     (Ladislav Michl)

   - Add a PM core flag to mark devices that don't need any form of
     power management (Sudeep Holla)

   - Introduce driver API documentation for cpuidle and add a new
     cpuidle governor for tickless systems (Rafael Wysocki)

   - Add Jacobsville support to the intel_idle driver (Zhang Rui)

   - Clean up a cpuidle core header file and the cpuidle-dt and ACPI
     processor-idle drivers (Yangtao Li, Joseph Lo, Yazen Ghannam)

   - Add new cpufreq driver for Armada 8K (Gregory Clement)

   - Fix and clean up cpufreq core (Rafael Wysocki, Viresh Kumar, Amit
     Kucheria)

   - Add support for light-weight tear-down and bring-up of CPUs to the
     cpufreq core and use it in the cpufreq-dt driver (Viresh Kumar)

   - Fix cpu_cooling Kconfig dependencies, add support for CPU cooling
     auto-registration to the cpufreq core and use it in multiple
     cpufreq drivers (Amit Kucheria)

   - Fix some minor issues and do some cleanups in the davinci,
     e_powersaver, ap806, s5pv210, qcom and kryo cpufreq drivers
     (Bartosz Golaszewski, Gustavo Silva, Julia Lawall, Paweł Chmiel,
     Taniya Das, Viresh Kumar)

   - Add a Hisilicon CPPC quirk to the cppc_cpufreq driver (Xiongfeng
     Wang)

   - Clean up the intel_pstate and acpi-cpufreq drivers (Erwan Velu,
     Rafael Wysocki)

   - Clean up multiple cpufreq drivers (Yangtao Li)

   - Update cpufreq-related MAINTAINERS entries (Baruch Siach, Lukas
     Bulwahn)

   - Add support for exposing the Energy Model via debugfs and make
     multiple cpufreq drivers register an Energy Model to support
     energy-aware scheduling (Quentin Perret, Dietmar Eggemann, Matthias
     Kaehlcke)

   - Add Ice Lake mobile and Jacobsville support to the Intel RAPL
     power-capping driver (Gayatri Kammela, Zhang Rui)

   - Add a power estimation helper to the operating performance points
     (OPP) framework and clean up a core function in it (Quentin Perret,
     Viresh Kumar)

   - Make minor improvements in the generic power domains (genpd), OPP
     and system suspend frameworks and in the PM core (Aditya Pakki,
     Douglas Anderson, Greg Kroah-Hartman, Rafael Wysocki, Yangtao Li)"

* tag 'pm-5.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (80 commits)
  cpufreq: kryo: Release OPP tables on module removal
  cpufreq: ap806: add missing of_node_put after of_device_is_available
  cpufreq: acpi-cpufreq: Report if CPU doesn't support boost technologies
  cpufreq: Pass updated policy to driver ->setpolicy() callback
  cpufreq: Fix two debug messages in cpufreq_set_policy()
  cpufreq: Reorder and simplify cpufreq_update_policy()
  cpufreq: Add kerneldoc comments for two core functions
  PM / core: Add support to skip power management in device/driver model
  cpufreq: intel_pstate: Rework iowait boosting to be less aggressive
  cpufreq: intel_pstate: Eliminate intel_pstate_get_base_pstate()
  cpufreq: intel_pstate: Avoid redundant initialization of local vars
  powercap/intel_rapl: add Ice Lake mobile
  ACPI / processor: Set P_LVL{2,3} idle state descriptions
  cpufreq / cppc: Work around for Hisilicon CPPC cpufreq
  ACPI / CPPC: Add a helper to get desired performance
  cpufreq: davinci: move configuration to include/linux/platform_data
  cpufreq: speedstep: convert BUG() to BUG_ON()
  cpufreq: powernv: fix missing check of return value in init_powernv_pstates()
  cpufreq: longhaul: remove unneeded semicolon
  cpufreq: pcc-cpufreq: remove unneeded semicolon
  ..

50 files changed, 1396 insertions, 409 deletions

diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 217a782c3e55..1b207fca1420 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -1051,6 +1051,48 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val)
 }
 
 /**
+ * cppc_get_desired_perf - Get the value of desired performance register.
+ * @cpunum: CPU from which to get desired performance.
+ * @desired_perf: address of a variable to store the returned desired performance
+ *
+ * Return: 0 for success, -EIO otherwise.
+ */
+int cppc_get_desired_perf(int cpunum, u64 *desired_perf)
+{
+	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum);
+	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum);
+	struct cpc_register_resource *desired_reg;
+	struct cppc_pcc_data *pcc_ss_data = NULL;
+
+	desired_reg = &cpc_desc->cpc_regs[DESIRED_PERF];
+
+	if (CPC_IN_PCC(desired_reg)) {
+		int ret = 0;
+
+		if (pcc_ss_id < 0)
+			return -EIO;
+
+		pcc_ss_data = pcc_data[pcc_ss_id];
+
+		down_write(&pcc_ss_data->pcc_lock);
+
+		if (send_pcc_cmd(pcc_ss_id, CMD_READ) >= 0)
+			cpc_read(cpunum, desired_reg, desired_perf);
+		else
+			ret = -EIO;
+
+		up_write(&pcc_ss_data->pcc_lock);
+
+		return ret;
+	}
+
+	cpc_read(cpunum, desired_reg, desired_perf);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cppc_get_desired_perf);
+
+/**
  * cppc_get_perf_caps - Get a CPUs performance capabilities.
  * @cpunum: CPU from which to get capabilities info.
  * @perf_caps: ptr to cppc_perf_caps. See cppc_acpi.h
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index b2131c4ea124..98d4ec5bf450 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -282,6 +282,13 @@ static int acpi_processor_get_power_info_fadt(struct acpi_processor *pr)
 			  pr->power.states[ACPI_STATE_C2].address,
 			  pr->power.states[ACPI_STATE_C3].address));
 
+	snprintf(pr->power.states[ACPI_STATE_C2].desc,
+			 ACPI_CX_DESC_LEN, "ACPI P_LVL2 IOPORT 0x%x",
+			 pr->power.states[ACPI_STATE_C2].address);
+	snprintf(pr->power.states[ACPI_STATE_C3].desc,
+			 ACPI_CX_DESC_LEN, "ACPI P_LVL3 IOPORT 0x%x",
+			 pr->power.states[ACPI_STATE_C3].address);
+
 	return 0;
 }
 
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index eb9443d5bae1..6ce93a52bf3f 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -427,6 +427,7 @@ __cpu_device_create(struct device *parent, void *drvdata,
 	dev->parent = parent;
 	dev->groups = groups;
 	dev->release = device_create_release;
+	device_set_pm_not_required(dev);
 	dev_set_drvdata(dev, drvdata);
 
 	retval = kobject_set_name_vargs(&dev->kobj, fmt, args);
diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
index 5a42ae4078c2..365ad751ce0f 100644
--- a/drivers/base/power/clock_ops.c
+++ b/drivers/base/power/clock_ops.c
@@ -65,10 +65,15 @@ static void pm_clk_acquire(struct device *dev, struct pm_clock_entry *ce)
 	if (IS_ERR(ce->clk)) {
 		ce->status = PCE_STATUS_ERROR;
 	} else {
-		clk_prepare(ce->clk);
-		ce->status = PCE_STATUS_ACQUIRED;
-		dev_dbg(dev, "Clock %pC con_id %s managed by runtime PM.\n",
-			ce->clk, ce->con_id);
+		if (clk_prepare(ce->clk)) {
+			ce->status = PCE_STATUS_ERROR;
+			dev_err(dev, "clk_prepare() failed\n");
+		} else {
+			ce->status = PCE_STATUS_ACQUIRED;
+			dev_dbg(dev,
+				"Clock %pC con_id %s managed by runtime PM.\n",
+				ce->clk, ce->con_id);
+		}
 	}
 }
 
diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c
index b413951c6abc..22aedb28aad7 100644
--- a/drivers/base/power/common.c
+++ b/drivers/base/power/common.c
@@ -160,7 +160,7 @@ EXPORT_SYMBOL_GPL(dev_pm_domain_attach_by_id);
  * For a detailed function description, see dev_pm_domain_attach_by_id().
  */
 struct device *dev_pm_domain_attach_by_name(struct device *dev,
-					    char *name)
+					    const char *name)
 {
 	if (dev->pm_domain)
 		return ERR_PTR(-EEXIST);
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 500de1dee967..2c334c01fc43 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -2483,7 +2483,7 @@ EXPORT_SYMBOL_GPL(genpd_dev_pm_attach_by_id);
  * power-domain-names DT property. For further description see
  * genpd_dev_pm_attach_by_id().
  */
-struct device *genpd_dev_pm_attach_by_name(struct device *dev, char *name)
+struct device *genpd_dev_pm_attach_by_name(struct device *dev, const char *name)
 {
 	int index;
 
@@ -2948,18 +2948,11 @@ static int __init genpd_debug_init(void)
 
 	genpd_debugfs_dir = debugfs_create_dir("pm_genpd", NULL);
 
-	if (!genpd_debugfs_dir)
-		return -ENOMEM;
-
-	d = debugfs_create_file("pm_genpd_summary", S_IRUGO,
-			genpd_debugfs_dir, NULL, &summary_fops);
-	if (!d)
-		return -ENOMEM;
+	debugfs_create_file("pm_genpd_summary", S_IRUGO, genpd_debugfs_dir,
+			    NULL, &summary_fops);
 
 	list_for_each_entry(genpd, &gpd_list, gpd_list_node) {
 		d = debugfs_create_dir(genpd->name, genpd_debugfs_dir);
-		if (!d)
-			return -ENOMEM;
 
 		debugfs_create_file("current_state", 0444,
 				d, genpd, &status_fops);
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 0992e67e862b..893ae464bfd6 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -124,6 +124,10 @@ void device_pm_unlock(void)
  */
 void device_pm_add(struct device *dev)
 {
+	/* Skip PM setup/initialization. */
+	if (device_pm_not_required(dev))
+		return;
+
 	pr_debug("PM: Adding info for %s:%s\n",
 		 dev->bus ? dev->bus->name : "No Bus", dev_name(dev));
 	device_pm_check_callbacks(dev);
@@ -142,6 +146,9 @@ void device_pm_add(struct device *dev)
  */
 void device_pm_remove(struct device *dev)
 {
+	if (device_pm_not_required(dev))
+		return;
+
 	pr_debug("PM: Removing info for %s:%s\n",
 		 dev->bus ? dev->bus->name : "No Bus", dev_name(dev));
 	complete_all(&dev->power.completion);
@@ -1741,8 +1748,10 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 	if (dev->power.direct_complete) {
 		if (pm_runtime_status_suspended(dev)) {
 			pm_runtime_disable(dev);
-			if (pm_runtime_status_suspended(dev))
+			if (pm_runtime_status_suspended(dev)) {
+				pm_dev_dbg(dev, state, "direct-complete ");
 				goto Complete;
+			}
 
 			pm_runtime_enable(dev);
 		}
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index ccd296dbb95c..78937c45278c 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -66,20 +66,30 @@ static int rpm_suspend(struct device *dev, int rpmflags);
  */
 void update_pm_runtime_accounting(struct device *dev)
 {
-	unsigned long now = jiffies;
-	unsigned long delta;
+	u64 now, last, delta;
 
-	delta = now - dev->power.accounting_timestamp;
+	if (dev->power.disable_depth > 0)
+		return;
+
+	last = dev->power.accounting_timestamp;
 
+	now = ktime_get_mono_fast_ns();
 	dev->power.accounting_timestamp = now;
 
-	if (dev->power.disable_depth > 0)
+	/*
+	 * Because ktime_get_mono_fast_ns() is not monotonic during
+	 * timekeeping updates, ensure that 'now' is after the last saved
+	 * timesptamp.
+	 */
+	if (now < last)
 		return;
 
+	delta = now - last;
+
 	if (dev->power.runtime_status == RPM_SUSPENDED)
-		dev->power.suspended_jiffies += delta;
+		dev->power.suspended_time += delta;
 	else
-		dev->power.active_jiffies += delta;
+		dev->power.active_time += delta;
 }
 
 static void __update_runtime_status(struct device *dev, enum rpm_status status)
@@ -88,6 +98,22 @@ static void __update_runtime_status(struct device *dev, enum rpm_status status)
 	dev->power.runtime_status = status;
 }
 
+u64 pm_runtime_suspended_time(struct device *dev)
+{
+	u64 time;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+
+	update_pm_runtime_accounting(dev);
+	time = dev->power.suspended_time;
+
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	return time;
+}
+EXPORT_SYMBOL_GPL(pm_runtime_suspended_time);
+
 /**
  * pm_runtime_deactivate_timer - Deactivate given device's suspend timer.
  * @dev: Device to handle.
@@ -129,24 +155,21 @@ static void pm_runtime_cancel_pending(struct device *dev)
 u64 pm_runtime_autosuspend_expiration(struct device *dev)
 {
 	int autosuspend_delay;
-	u64 last_busy, expires = 0;
-	u64 now = ktime_get_mono_fast_ns();
+	u64 expires;
 
 	if (!dev->power.use_autosuspend)
-		goto out;
+		return 0;
 
 	autosuspend_delay = READ_ONCE(dev->power.autosuspend_delay);
 	if (autosuspend_delay < 0)
-		goto out;
-
-	last_busy = READ_ONCE(dev->power.last_busy);
+		return 0;
 
-	expires = last_busy + (u64)autosuspend_delay * NSEC_PER_MSEC;
-	if (expires <= now)
-		expires = 0;	/* Already expired. */
+	expires  = READ_ONCE(dev->power.last_busy);
+	expires += (u64)autosuspend_delay * NSEC_PER_MSEC;
+	if (expires > ktime_get_mono_fast_ns())
+		return expires;	/* Expires in the future */
 
- out:
-	return expires;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(pm_runtime_autosuspend_expiration);
 
@@ -1276,6 +1299,9 @@ void __pm_runtime_disable(struct device *dev, bool check_resume)
 		pm_runtime_put_noidle(dev);
 	}
 
+	/* Update time accounting before disabling PM-runtime. */
+	update_pm_runtime_accounting(dev);
+
 	if (!dev->power.disable_depth++)
 		__pm_runtime_barrier(dev);
 
@@ -1294,10 +1320,15 @@ void pm_runtime_enable(struct device *dev)
 
 	spin_lock_irqsave(&dev->power.lock, flags);
 
-	if (dev->power.disable_depth > 0)
+	if (dev->power.disable_depth > 0) {
 		dev->power.disable_depth--;
-	else
+
+		/* About to enable runtime pm, set accounting_timestamp to now */
+		if (!dev->power.disable_depth)
+			dev->power.accounting_timestamp = ktime_get_mono_fast_ns();
+	} else {
 		dev_warn(dev, "Unbalanced %s!\n", __func__);
+	}
 
 	WARN(!dev->power.disable_depth &&
 	     dev->power.runtime_status == RPM_SUSPENDED &&
@@ -1494,7 +1525,6 @@ void pm_runtime_init(struct device *dev)
 	dev->power.request_pending = false;
 	dev->power.request = RPM_REQ_NONE;
 	dev->power.deferred_resume = false;
-	dev->power.accounting_timestamp = jiffies;
 	INIT_WORK(&dev->power.work, pm_runtime_work);
 
 	dev->power.timer_expires = 0;
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index d713738ce796..c6bf76124184 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -125,9 +125,12 @@ static ssize_t runtime_active_time_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
 	int ret;
+	u64 tmp;
 	spin_lock_irq(&dev->power.lock);
 	update_pm_runtime_accounting(dev);
-	ret = sprintf(buf, "%i\n", jiffies_to_msecs(dev->power.active_jiffies));
+	tmp = dev->power.active_time;
+	do_div(tmp, NSEC_PER_MSEC);
+	ret = sprintf(buf, "%llu\n", tmp);
 	spin_unlock_irq(&dev->power.lock);
 	return ret;
 }
@@ -138,10 +141,12 @@ static ssize_t runtime_suspended_time_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
 	int ret;
+	u64 tmp;
 	spin_lock_irq(&dev->power.lock);
 	update_pm_runtime_accounting(dev);
-	ret = sprintf(buf, "%i\n",
-		jiffies_to_msecs(dev->power.suspended_jiffies));
+	tmp = dev->power.suspended_time;
+	do_div(tmp, NSEC_PER_MSEC);
+	ret = sprintf(buf, "%llu\n", tmp);
 	spin_unlock_irq(&dev->power.lock);
 	return ret;
 }
@@ -648,6 +653,10 @@ int dpm_sysfs_add(struct device *dev)
 {
 	int rc;
 
+	/* No need to create PM sysfs if explicitly disabled. */
+	if (device_pm_not_required(dev))
+		return 0;
+
 	rc = sysfs_create_group(&dev->kobj, &pm_attr_group);
 	if (rc)
 		return rc;
@@ -727,6 +736,8 @@ void rpm_sysfs_remove(struct device *dev)
 
 void dpm_sysfs_remove(struct device *dev)
 {
+	if (device_pm_not_required(dev))
+		return;
 	sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group);
 	dev_pm_qos_constraints_destroy(dev);
 	rpm_sysfs_remove(dev);
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index 5fa1898755a3..f1fee72ed970 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -783,7 +783,7 @@ void pm_wakeup_ws_event(struct wakeup_source *ws, unsigned int msec, bool hard)
 EXPORT_SYMBOL_GPL(pm_wakeup_ws_event);
 
 /**
- * pm_wakeup_event - Notify the PM core of a wakeup event.
+ * pm_wakeup_dev_event - Notify the PM core of a wakeup event.
  * @dev: Device the wakeup event is related to.
  * @msec: Anticipated event processing time (in milliseconds).
  * @hard: If set, abort suspends in progress and wake up from suspend-to-idle.
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 608af20a3494..b22e6bba71f1 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -207,8 +207,6 @@ comment "CPU frequency scaling drivers"
 config CPUFREQ_DT
 	tristate "Generic DT based cpufreq driver"
 	depends on HAVE_CLK && OF
-	# if CPU_THERMAL is on and THERMAL=m, CPUFREQ_DT cannot be =y:
-	depends on !CPU_THERMAL || THERMAL
 	select CPUFREQ_DT_PLATDEV
 	select PM_OPP
 	help
@@ -327,7 +325,6 @@ endif
 config QORIQ_CPUFREQ
 	tristate "CPU frequency scaling driver for Freescale QorIQ SoCs"
 	depends on OF && COMMON_CLK && (PPC_E500MC || ARM || ARM64)
-	depends on !CPU_THERMAL || THERMAL
 	select CLK_QORIQ
 	help
 	  This adds the CPUFreq driver support for Freescale QorIQ SoCs
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 1a6778e81f90..179a1d302f48 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -25,12 +25,21 @@ config ARM_ARMADA_37XX_CPUFREQ
 	  This adds the CPUFreq driver support for Marvell Armada 37xx SoCs.
 	  The Armada 37xx PMU supports 4 frequency and VDD levels.
 
+config ARM_ARMADA_8K_CPUFREQ
+	tristate "Armada 8K CPUFreq driver"
+	depends on ARCH_MVEBU && CPUFREQ_DT
+	help
+	  This enables the CPUFreq driver support for Marvell
+	  Armada8k SOCs.
+	  Armada8K device has the AP806 which supports scaling
+	  to any full integer divider.
+
+	  If in doubt, say N.
+
 # big LITTLE core layer and glue drivers
 config ARM_BIG_LITTLE_CPUFREQ
 	tristate "Generic ARM big LITTLE CPUfreq driver"
 	depends on ARM_CPU_TOPOLOGY && HAVE_CLK
-	# if CPU_THERMAL is on and THERMAL=m, ARM_BIT_LITTLE_CPUFREQ cannot be =y
-	depends on !CPU_THERMAL || THERMAL
 	select PM_OPP
 	help
 	  This enables the Generic CPUfreq driver for ARM big.LITTLE platforms.
@@ -38,7 +47,6 @@ config ARM_BIG_LITTLE_CPUFREQ
 config ARM_SCPI_CPUFREQ
 	tristate "SCPI based CPUfreq driver"
 	depends on ARM_SCPI_PROTOCOL && COMMON_CLK_SCPI
-	depends on !CPU_THERMAL || THERMAL
 	help
 	  This adds the CPUfreq driver support for ARM platforms using SCPI
 	  protocol for CPU power management.
@@ -93,7 +101,6 @@ config ARM_KIRKWOOD_CPUFREQ
 config ARM_MEDIATEK_CPUFREQ
 	tristate "CPU Frequency scaling support for MediaTek SoCs"
 	depends on ARCH_MEDIATEK && REGULATOR
-	depends on !CPU_THERMAL || THERMAL
 	select PM_OPP
 	help
 	  This adds the CPUFreq driver support for MediaTek SoCs.
@@ -233,7 +240,6 @@ config ARM_SA1110_CPUFREQ
 config ARM_SCMI_CPUFREQ
 	tristate "SCMI based CPUfreq driver"
 	depends on ARM_SCMI_PROTOCOL || COMPILE_TEST
-	depends on !CPU_THERMAL || THERMAL
 	select PM_OPP
 	help
 	  This adds the CPUfreq driver support for ARM platforms using SCMI
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 08c071be2491..689b26c6f949 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -50,6 +50,7 @@ obj-$(CONFIG_X86_SFI_CPUFREQ)		+= sfi-cpufreq.o
 obj-$(CONFIG_ARM_BIG_LITTLE_CPUFREQ)	+= arm_big_little.o
 
 obj-$(CONFIG_ARM_ARMADA_37XX_CPUFREQ)	+= armada-37xx-cpufreq.o
+obj-$(CONFIG_ARM_ARMADA_8K_CPUFREQ)	+= armada-8k-cpufreq.o
 obj-$(CONFIG_ARM_BRCMSTB_AVS_CPUFREQ)	+= brcmstb-avs-cpufreq.o
 obj-$(CONFIG_ACPI_CPPC_CPUFREQ)		+= cppc_cpufreq.o
 obj-$(CONFIG_ARCH_DAVINCI)		+= davinci-cpufreq.o
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index d62fd374d5c7..c72258a44ba4 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -916,8 +916,10 @@ static void __init acpi_cpufreq_boost_init(void)
 {
 	int ret;
 
-	if (!(boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA)))
+	if (!(boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA))) {
+		pr_debug("Boost capabilities not present in the processor\n");
 		return;
+	}
 
 	acpi_cpufreq_driver.set_boost = set_boost;
 	acpi_cpufreq_driver.boost_enabled = boost_state(0);
diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c
index cf62a1f64dd7..7fe52fcddcf1 100644
--- a/drivers/cpufreq/arm_big_little.c
+++ b/drivers/cpufreq/arm_big_little.c
@@ -487,6 +487,8 @@ static int bL_cpufreq_init(struct cpufreq_policy *policy)
 	policy->cpuinfo.transition_latency =
 				arm_bL_ops->get_transition_latency(cpu_dev);
 
+	dev_pm_opp_of_register_em(policy->cpus);
+
 	if (is_bL_switching_enabled())
 		per_cpu(cpu_last_req_freq, policy->cpu) = clk_get_cpu_rate(policy->cpu);
 
diff --git a/drivers/cpufreq/armada-8k-cpufreq.c b/drivers/cpufreq/armada-8k-cpufreq.c
new file mode 100644
index 000000000000..b3f4bd647e9b
--- /dev/null
+++ b/drivers/cpufreq/armada-8k-cpufreq.c
@@ -0,0 +1,206 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * CPUFreq support for Armada 8K
+ *
+ * Copyright (C) 2018 Marvell
+ *
+ * Omri Itach <omrii@marvell.com>
+ * Gregory Clement <gregory.clement@bootlin.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/clk.h>
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_opp.h>
+#include <linux/slab.h>
+
+/*
+ * Setup the opps list with the divider for the max frequency, that
+ * will be filled at runtime.
+ */
+static const int opps_div[] __initconst = {1, 2, 3, 4};
+
+static struct platform_device *armada_8k_pdev;
+
+struct freq_table {
+	struct device *cpu_dev;
+	unsigned int freq[ARRAY_SIZE(opps_div)];
+};
+
+/* If the CPUs share the same clock, then they are in the same cluster. */
+static void __init armada_8k_get_sharing_cpus(struct clk *cur_clk,
+					      struct cpumask *cpumask)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct device *cpu_dev;
+		struct clk *clk;
+
+		cpu_dev = get_cpu_device(cpu);
+		if (!cpu_dev) {
+			pr_warn("Failed to get cpu%d device\n", cpu);
+			continue;
+		}
+
+		clk = clk_get(cpu_dev, 0);
+		if (IS_ERR(clk)) {
+			pr_warn("Cannot get clock for CPU %d\n", cpu);
+		} else {
+			if (clk_is_match(clk, cur_clk))
+				cpumask_set_cpu(cpu, cpumask);
+
+			clk_put(clk);
+		}
+	}
+}
+
+static int __init armada_8k_add_opp(struct clk *clk, struct device *cpu_dev,
+				    struct freq_table *freq_tables,
+				    int opps_index)
+{
+	unsigned int cur_frequency;
+	unsigned int freq;
+	int i, ret;
+
+	/* Get nominal (current) CPU frequency. */
+	cur_frequency = clk_get_rate(clk);
+	if (!cur_frequency) {
+		dev_err(cpu_dev, "Failed to get clock rate for this C