Merge tag 'pm-4.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These update the cpuidle poll state definition to reduce excessive
  energy usage related to it, add new CPU ID to the RAPL power capping
  driver, update the ACPI system suspend code to handle some special
  cases better, extend the PM core's device links code slightly, add new
  sysfs attribute for better suspend-to-idle diagnostics and easier
  hibernation handling, update power management tools and clean up
  cpufreq quite a bit.

  Specifics:

   - Modify the cpuidle poll state implementation to prevent CPUs from
     staying in the loop in there for excessive times (Rafael Wysocki).

   - Add Intel Cannon Lake chips support to the RAPL power capping
     driver (Joe Konno).

   - Add reference counting to the device links handling code in the PM
     core (Lukas Wunner).

   - Avoid reconfiguring GPEs on suspend-to-idle in the ACPI system
     suspend code (Rafael Wysocki).

   - Allow devices to be put into deeper low-power states via ACPI if
     both _SxD and _SxW are missing (Daniel Drake).

   - Reorganize the core ACPI suspend-to-idle wakeup code to avoid a
     keyboard wakeup issue on Asus UX331UA (Chris Chiu).

   - Prevent the PCMCIA library code from aborting suspend-to-idle due
     to noirq suspend failures resulting from incorrect assumptions
     (Rafael Wysocki).

   - Add coupled cpuidle supprt to the Exynos3250 platform (Marek
     Szyprowski).

   - Add new sysfs file to make it easier to specify the image storage
     location during hibernation (Mario Limonciello).

   - Add sysfs files for collecting suspend-to-idle usage and time
     statistics for CPU idle states (Rafael Wysocki).

   - Update the pm-graph utilities (Todd Brandt).

   - Reduce the kernel log noise related to reporting Low-power Idle
     constraings by the ACPI system suspend code (Rafael Wysocki).

   - Make it easier to distinguish dedicated wakeup IRQs in the
     /proc/interrupts output (Tony Lindgren).

   - Add the frequency table validation in cpufreq to the core and drop
     it from a number of cpufreq drivers (Viresh Kumar).

   - Drop "cooling-{min|max}-level" for CPU nodes from a couple of DT
     bindings (Viresh Kumar).

   - Clean up the CPU online error code path in the cpufreq core (Viresh
     Kumar).

   - Fix assorted issues in the SCPI, CPPC, mediatek and tegra186
     cpufreq drivers (Arnd Bergmann, Chunyu Hu, George Cherian, Viresh
     Kumar).

   - Drop memory allocation error messages from a few places in cpufreq
     and cpuildle drivers (Markus Elfring)"

* tag 'pm-4.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (56 commits)
  ACPI / PM: Fix keyboard wakeup from suspend-to-idle on ASUS UX331UA
  cpufreq: CPPC: Use transition_delay_us depending transition_latency
  PM / hibernate: Change message when writing to /sys/power/resume
  PM / hibernate: Make passing hibernate offsets more friendly
  cpuidle: poll_state: Avoid invoking local_clock() too often
  PM: cpuidle/suspend: Add s2idle usage and time state attributes
  cpuidle: Enable coupled cpuidle support on Exynos3250 platform
  cpuidle: poll_state: Add time limit to poll_idle()
  cpufreq: tegra186: Don't validate the frequency table twice
  cpufreq: speedstep: Don't validate the frequency table twice
  cpufreq: sparc: Don't validate the frequency table twice
  cpufreq: sh: Don't validate the frequency table twice
  cpufreq: sfi: Don't validate the frequency table twice
  cpufreq: scpi: Don't validate the frequency table twice
  cpufreq: sc520: Don't validate the frequency table twice
  cpufreq: s3c24xx: Don't validate the frequency table twice
  cpufreq: qoirq: Don't validate the frequency table twice
  cpufreq: pxa: Don't validate the frequency table twice
  cpufreq: ppc_cbe: Don't validate the frequency table twice
  cpufreq: powernow: Don't validate the frequency table twice
  ...

47 files changed, 261 insertions, 200 deletions

diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index c4d0a1c912f0..3d96e4da2d98 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -543,6 +543,7 @@ static int acpi_dev_pm_get_state(struct device *dev, struct acpi_device *adev,
 	unsigned long long ret;
 	int d_min, d_max;
 	bool wakeup = false;
+	bool has_sxd = false;
 	acpi_status status;
 
 	/*
@@ -581,6 +582,10 @@ static int acpi_dev_pm_get_state(struct device *dev, struct acpi_device *adev,
 			else
 				return -ENODATA;
 		}
+
+		if (status == AE_OK)
+			has_sxd = true;
+
 		d_min = ret;
 		wakeup = device_may_wakeup(dev) && adev->wakeup.flags.valid
 			&& adev->wakeup.sleep_state >= target_state;
@@ -599,7 +604,11 @@ static int acpi_dev_pm_get_state(struct device *dev, struct acpi_device *adev,
 		method[3] = 'W';
 		status = acpi_evaluate_integer(handle, method, NULL, &ret);
 		if (status == AE_NOT_FOUND) {
-			if (target_state > ACPI_STATE_S0)
+			/* No _SxW. In this case, the ACPI spec says that we
+			 * must not go into any power state deeper than the
+			 * value returned from _SxD.
+			 */
+			if (has_sxd && target_state > ACPI_STATE_S0)
 				d_max = d_min;
 		} else if (ACPI_SUCCESS(status) && ret <= ACPI_STATE_D3_COLD) {
 			/* Fall back to D3cold if ret is not a valid state. */
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index b35923e3a926..99a1a650326d 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -849,23 +849,25 @@ static void lpi_check_constraints(void)
 	int i;
 
 	for (i = 0; i < lpi_constraints_table_size; ++i) {
+		acpi_handle handle = lpi_constraints_table[i].handle;
 		struct acpi_device *adev;
 
-		if (acpi_bus_get_device(lpi_constraints_table[i].handle, &adev))
+		if (!handle || acpi_bus_get_device(handle, &adev))
 			continue;
 
-		acpi_handle_debug(adev->handle,
+		acpi_handle_debug(handle,
 			"LPI: required min power state:%s current power state:%s\n",
 			acpi_power_state_string(lpi_constraints_table[i].min_dstate),
 			acpi_power_state_string(adev->power.state));
 
 		if (!adev->flags.power_manageable) {
-			acpi_handle_info(adev->handle, "LPI: Device not power manageble\n");
+			acpi_handle_info(handle, "LPI: Device not power manageable\n");
+			lpi_constraints_table[i].handle = NULL;
 			continue;
 		}
 
 		if (adev->power.state < lpi_constraints_table[i].min_dstate)
-			acpi_handle_info(adev->handle,
+			acpi_handle_info(handle,
 				"LPI: Constraint not met; min power state:%s current power state:%s\n",
 				acpi_power_state_string(lpi_constraints_table[i].min_dstate),
 				acpi_power_state_string(adev->power.state));
@@ -951,15 +953,8 @@ static int acpi_s2idle_prepare(void)
 	if (lps0_device_handle) {
 		acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_OFF);
 		acpi_sleep_run_lps0_dsm(ACPI_LPS0_ENTRY);
-	} else {
-		/*
-		 * The configuration of GPEs is changed here to avoid spurious
-		 * wakeups, but that should not be necessary if this is a
-		 * "low-power S0" platform and the low-power S0 _DSM is present.
-		 */
-		acpi_enable_all_wakeup_gpes();
-		acpi_os_wait_events_complete();
 	}
+
 	if (acpi_sci_irq_valid())
 		enable_irq_wake(acpi_sci_irq);
 
@@ -992,8 +987,9 @@ static void acpi_s2idle_sync(void)
 	 * The EC driver uses the system workqueue and an additional special
 	 * one, so those need to be flushed too.
 	 */
+	acpi_os_wait_events_complete();	/* synchronize SCI IRQ handling */
 	acpi_ec_flush_work();
-	acpi_os_wait_events_complete();
+	acpi_os_wait_events_complete();	/* synchronize Notify handling */
 	s2idle_wakeup = false;
 }
 
@@ -1005,8 +1001,6 @@ static void acpi_s2idle_restore(void)
 	if (lps0_device_handle) {
 		acpi_sleep_run_lps0_dsm(ACPI_LPS0_EXIT);
 		acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_ON);
-	} else {
-		acpi_enable_all_runtime_gpes();
 	}
 }
 
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 5847364f25d9..b610816eb887 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -196,8 +196,10 @@ struct device_link *device_link_add(struct device *consumer,
 	}
 
 	list_for_each_entry(link, &supplier->links.consumers, s_node)
-		if (link->consumer == consumer)
+		if (link->consumer == consumer) {
+			kref_get(&link->kref);
 			goto out;
+		}
 
 	link = kzalloc(sizeof(*link), GFP_KERNEL);
 	if (!link)
@@ -222,6 +224,7 @@ struct device_link *device_link_add(struct device *consumer,
 	link->consumer = consumer;
 	INIT_LIST_HEAD(&link->c_node);
 	link->flags = flags;
+	kref_init(&link->kref);
 
 	/* Determine the initial link state. */
 	if (flags & DL_FLAG_STATELESS) {
@@ -292,8 +295,10 @@ static void __device_link_free_srcu(struct rcu_head *rhead)
 	device_link_free(container_of(rhead, struct device_link, rcu_head));
 }
 
-static void __device_link_del(struct device_link *link)
+static void __device_link_del(struct kref *kref)
 {
+	struct device_link *link = container_of(kref, struct device_link, kref);
+
 	dev_info(link->consumer, "Dropping the link to %s\n",
 		 dev_name(link->supplier));
 
@@ -305,8 +310,10 @@ static void __device_link_del(struct device_link *link)
 	call_srcu(&device_links_srcu, &link->rcu_head, __device_link_free_srcu);
 }
 #else /* !CONFIG_SRCU */
-static void __device_link_del(struct device_link *link)
+static void __device_link_del(struct kref *kref)
 {
+	struct device_link *link = container_of(kref, struct device_link, kref);
+
 	dev_info(link->consumer, "Dropping the link to %s\n",
 		 dev_name(link->supplier));
 
@@ -324,13 +331,15 @@ static void __device_link_del(struct device_link *link)
  * @link: Device link to delete.
  *
  * The caller must ensure proper synchronization of this function with runtime
- * PM.
+ * PM.  If the link was added multiple times, it needs to be deleted as often.
+ * Care is required for hotplugged devices:  Their links are purged on removal
+ * and calling device_link_del() is then no longer allowed.
  */
 void device_link_del(struct device_link *link)
 {
 	device_links_write_lock();
 	device_pm_lock();
-	__device_link_del(link);
+	kref_put(&link->kref, __device_link_del);
 	device_pm_unlock();
 	device_links_write_unlock();
 }
@@ -444,7 +453,7 @@ static void __device_links_no_driver(struct device *dev)
 			continue;
 
 		if (link->flags & DL_FLAG_AUTOREMOVE)
-			__device_link_del(link);
+			kref_put(&link->kref, __device_link_del);
 		else if (link->status != DL_STATE_SUPPLIER_UNBIND)
 			WRITE_ONCE(link->status, DL_STATE_AVAILABLE);
 	}
@@ -597,13 +606,13 @@ static void device_links_purge(struct device *dev)
 
 	list_for_each_entry_safe_reverse(link, ln, &dev->links.suppliers, c_node) {
 		WARN_ON(link->status == DL_STATE_ACTIVE);
-		__device_link_del(link);
+		__device_link_del(&link->kref);
 	}
 
 	list_for_each_entry_safe_reverse(link, ln, &dev->links.consumers, s_node) {
 		WARN_ON(link->status != DL_STATE_DORMANT &&
 			link->status != DL_STATE_NONE);
-		__device_link_del(link);
+		__device_link_del(&link->kref);
 	}
 
 	device_links_write_unlock();
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index 21244c53e377..86e67e70b509 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -31,6 +31,7 @@ struct wake_irq {
 	struct device *dev;
 	unsigned int status;
 	int irq;
+	const char *name;
 };
 
 extern void dev_pm_arm_wake_irq(struct wake_irq *wirq);
diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c
index 6637fc319269..b8fa5c0f2d13 100644
--- a/drivers/base/power/wakeirq.c
+++ b/drivers/base/power/wakeirq.c
@@ -112,6 +112,7 @@ void dev_pm_clear_wake_irq(struct device *dev)
 		free_irq(wirq->irq, wirq);
 		wirq->status &= ~WAKE_IRQ_DEDICATED_MASK;
 	}
+	kfree(wirq->name);
 	kfree(wirq);
 }
 EXPORT_SYMBOL_GPL(dev_pm_clear_wake_irq);
@@ -184,6 +185,12 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq)
 	if (!wirq)
 		return -ENOMEM;
 
+	wirq->name = kasprintf(GFP_KERNEL, "%s:wakeup", dev_name(dev));
+	if (!wirq->name) {
+		err = -ENOMEM;
+		goto err_free;
+	}
+
 	wirq->dev = dev;
 	wirq->irq = irq;
 	irq_set_status_flags(irq, IRQ_NOAUTOEN);
@@ -196,9 +203,9 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq)
 	 * so we use a threaded irq.
 	 */
 	err = request_threaded_irq(irq, NULL, handle_threaded_wake_irq,
-				   IRQF_ONESHOT, dev_name(dev), wirq);
+				   IRQF_ONESHOT, wirq->name, wirq);
 	if (err)
-		goto err_free;
+		goto err_free_name;
 
 	err = dev_pm_attach_wake_irq(dev, irq, wirq);
 	if (err)
@@ -210,6 +217,8 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq)
 
 err_free_irq:
 	free_irq(irq, wirq);
+err_free_name:
+	kfree(wirq->name);
 err_free:
 	kfree(wirq);
 
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index fb586e09682d..833b5f41f596 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -45,6 +45,7 @@ config ARM_DT_BL_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.
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index d0c34df0529c..9449657d72f0 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -794,15 +794,9 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		valid_states++;
 	}
 	freq_table[valid_states].frequency = CPUFREQ_TABLE_END;
+	policy->freq_table = freq_table;
 	perf->state = 0;
 
-	result = cpufreq_table_validate_and_show(policy, freq_table);
-	if (result)
-		goto err_freqfree;
-
-	if (perf->states[0].core_frequency * 1000 != policy->cpuinfo.max_freq)
-		pr_warn(FW_WARN "P-state 0 is not max freq\n");
-
 	switch (perf->control_register.space_id) {
 	case ACPI_ADR_SPACE_SYSTEM_IO:
 		/*
@@ -842,8 +836,6 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
 	return result;
 
-err_freqfree:
-	kfree(freq_table);
 err_unreg:
 	acpi_processor_unregister_performance(cpu);
 err_free_mask:
@@ -871,6 +863,15 @@ static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 	return 0;
 }
 
+static void acpi_cpufreq_cpu_ready(struct cpufreq_policy *policy)
+{
+	struct acpi_processor_performance *perf = per_cpu_ptr(acpi_perf_data,
+							      policy->cpu);
+
+	if (perf->states[0].core_frequency * 1000 != policy->cpuinfo.max_freq)
+		pr_warn(FW_WARN "P-state 0 is not max freq\n");
+}
+
 static int acpi_cpufreq_resume(struct cpufreq_policy *policy)
 {
 	struct acpi_cpufreq_data *data = policy->driver_data;
@@ -898,6 +899,7 @@ static struct cpufreq_driver acpi_cpufreq_driver = {
 	.bios_limit	= acpi_processor_get_bios_limit,
 	.init		= acpi_cpufreq_cpu_init,
 	.exit		= acpi_cpufreq_cpu_exit,
+	.ready		= acpi_cpufreq_cpu_ready,
 	.resume		= acpi_cpufreq_resume,
 	.name		= "acpi-cpufreq",
 	.attr		= acpi_cpufreq_attr,
diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c
index c56b57dcfda5..1d7ef5fc1977 100644
--- a/drivers/cpufreq/arm_big_little.c
+++ b/drivers/cpufreq/arm_big_little.c
@@ -483,14 +483,7 @@ static int bL_cpufreq_init(struct cpufreq_policy *policy)
 	if (ret)
 		return ret;
 
-	ret = cpufreq_table_validate_and_show(policy, freq_table[cur_cluster]);
-	if (ret) {
-		dev_err(cpu_dev, "CPU %d, cluster: %d invalid freq table\n",
-			policy->cpu, cur_cluster);
-		put_cluster_clk_and_freq_table(cpu_dev, policy->cpus);
-		return ret;
-	}
-
+	policy->freq_table = freq_table[cur_cluster];
 	policy->cpuinfo.transition_latency =
 				arm_bL_ops->get_transition_latency(cpu_dev);
 
diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c
index 7281a2c19c36..6cdac1aaf23c 100644
--- a/drivers/cpufreq/brcmstb-avs-cpufreq.c
+++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c
@@ -902,11 +902,7 @@ static int brcm_avs_cpufreq_init(struct cpufreq_policy *policy)
 		return ret;
 	}
 
-	ret = cpufreq_table_validate_and_show(policy, freq_table);
-	if (ret) {
-		dev_err(dev, "invalid frequency table: %d\n", ret);
-		return ret;
-	}
+	policy->freq_table = freq_table;
 
 	/* All cores share the same clock and thus the same policy. */
 	cpumask_setall(policy->cpus);
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index a1c3025f9df7..8300a9fcb80c 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -20,6 +20,7 @@
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/dmi.h>
+#include <linux/time.h>
 #include <linux/vmalloc.h>
 
 #include <asm/unaligned.h>
@@ -162,6 +163,8 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	policy->cpuinfo.max_freq = cppc_dmi_max_khz;
 
 	policy->cpuinfo.transition_latency = cppc_get_transition_latency(cpu_num);
+	policy->transition_delay_us = cppc_get_transition_latency(cpu_num) /
+		NSEC_PER_USEC;
 	policy->shared_type = cpu->shared_type;
 
 	if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY)
@@ -230,8 +233,13 @@ static int __init cppc_cpufreq_init(void)
 	return ret;
 
 out:
-	for_each_possible_cpu(i)
-		kfree(all_cpu_data[i]);
+	for_each_possible_cpu(i) {
+		cpu = all_cpu_data[i];
+		if (!cpu)
+			break;
+		free_cpumask_var(cpu->shared_cpu_map);
+		kfree(cpu);
+	}
 
 	kfree(all_cpu_data);
 	return -ENODEV;
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index de3d104c25d7..190ea0dccb79 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -258,16 +258,10 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	priv->cpu_dev = cpu_dev;
 	policy->driver_data = priv;
 	policy->clk = cpu_clk;
+	policy->freq_table = freq_table;
 
 	policy->suspend_freq = dev_pm_opp_get_suspend_opp_freq(cpu_dev) / 1000;
 
-	ret = cpufreq_table_validate_and_show(policy, freq_table);
-	if (ret) {
-		dev_err(cpu_dev, "%s: invalid frequency table: %d\n", __func__,
-			ret);
-		goto out_free_cpufreq_table;
-	}
-
 	/* Support turbo/boost mode */
 	if (policy_has_boost_freq(policy)) {
 		/* This gets disabled by core on driver unregister */
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index de33ebf008ad..075d18f6ba7a 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -178,14 +178,7 @@ int cpufreq_generic_init(struct cpufreq_policy *policy,
 		struct cpufreq_frequency_table *table,
 		unsigned int transition_latency)
 {
-	int ret;
-
-	ret = cpufreq_table_validate_and_show(policy, table);
-	if (ret) {
-		pr_err("%s: invalid frequency table: %d\n", __func__, ret);
-		return ret;
-	}
-
+	policy->freq_table = table;
 	policy->cpuinfo.transition_latency = transition_latency;
 
 	/*
@@ -1219,6 +1212,10 @@ static int cpufreq_online(unsigned int cpu)
 		goto out_free_policy;
 	}
 
+	ret = cpufreq_table_validate_and_sort(policy);
+	if (ret)
+		goto out_exit_policy;
+
 	down_write(&policy->rwsem);
 
 	if (new_policy) {
@@ -1249,7 +1246,7 @@ static int cpufreq_online(unsigned int cpu)
 		policy->cur = cpufreq_driver->get(policy->cpu);
 		if (!policy->cur) {
 			pr_err("%s: ->get() failed\n", __func__);
-			goto out_exit_policy;
+			goto out_destroy_policy;
 		}
 	}
 
@@ -1296,7 +1293,7 @@ static int cpufreq_online(unsigned int cpu)
 	if (new_policy) {
 		ret = cpufreq_add_dev_interface(policy);
 		if (ret)
-			goto out_exit_policy;
+			goto out_destroy_policy;
 
 		cpufreq_stats_create_table(policy);
 
@@ -1311,7 +1308,7 @@ static int cpufreq_online(unsigned int cpu)
 		       __func__, cpu, ret);
 		/* cpufreq_policy_free() will notify based on this */
 		new_policy = false;
-		goto out_exit_policy;
+		goto out_destroy_policy;
 	}
 
 	up_write(&policy->rwsem);
@@ -1326,15 +1323,16 @@ static int cpufreq_online(unsigned int cpu)
 
 	return 0;
 
-out_exit_policy:
+out_destroy_policy:
+	for_each_cpu(j, policy->real_cpus)
+		remove_cpu_dev_symlink(policy, get_cpu_device(j));
+
 	up_write(&policy->rwsem);
 
+out_exit_policy:
 	if (cpufreq_driver->exit)
 		cpufreq_driver->exit(policy);
 
-	for_each_cpu(j, policy->real_cpus)
-		remove_cpu_dev_symlink(policy, get_cpu_device(j));
-
 out_free_policy:
 	cpufreq_policy_free(policy);
 	return ret;
diff --git a/drivers/cpufreq/e_powersaver.c b/drivers/cpufreq/e_powersaver.c
index cdf097b29862..60bea302abbe 100644
--- a/drivers/cpufreq/e_powersaver.c
+++ b/drivers/cpufreq/e_powersaver.c
@@ -184,7 +184,6 @@ static int eps_cpu_init(struct cpufreq_policy *policy)
 	struct cpuinfo_x86 *c = &cpu_data(0);
 	struct cpufreq_frequency_table *f_table;
 	int k, step, voltage;
-	int ret;
 	int states;
 #if IS_ENABLED(CONFIG_ACPI_PROCESSOR)
 	unsigned int limit;
@@ -359,12 +358,7 @@ static int eps_cpu_init(struct cpufreq_policy *policy)
 	}
 
 	policy->cpuinfo.transition_latency = 140000; /* 844mV -> 700mV in ns */
-
-	ret = cpufreq_table_validate_and_show(policy, &centaur->freq_table[0]);
-	if (ret) {
-		kfree(centaur);
-		return ret;
-	}
+	policy->freq_table = &centaur->freq_table[0];
 
 	return 0;
 }
diff --git a/drivers/cpufreq/elanfreq.c b/drivers/cpufreq/elanfreq.c
index 45e2ca62515e..03419f064752 100644
--- a/drivers/cpufreq/elanfreq.c
+++ b/drivers/cpufreq/elanfreq.c
@@ -165,7 +165,8 @@ static int elanfreq_cpu_init(struct cpufreq_policy *policy)
 		if (pos->frequency > max_freq)
 			pos->frequency = CPUFREQ_ENTRY_INVALID;
 
-	return cpufreq_table_validate_and_show(policy, elanfreq_table);
+	policy->freq_table = elanfreq_table;
+	return 0;
 }
 
 
diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
index 6d007f824ca7..10e119ae66dd 100644
--- a/drivers/cpufreq/freq_table.c
+++ b/drivers/cpufreq/freq_table.c
@@ -362,10 +362,24 @@ int cpufreq_table_validate_and_show(struct cpufreq_policy *policy,
 		return ret;
 
 	policy->freq_table = table;
-	return set_freq_table_sorted(policy);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(cpufreq_table_validate_and_show);
 
+int cpufreq_table_validate_and_sort(struct cpufreq_policy *policy)
+{
+	int ret;
+
+	if (!policy->freq_table)
+		return 0;
+
+	ret = cpufreq_frequency_table_cpuinfo(policy, policy->freq_table);
+	if (ret)
+		return ret;
+
+	return set_freq_table_sorted(policy);
+}
+
 MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>");
 MODULE_DESCRIPTION("CPUfreq frequency table helpers");
 MODULE_LICENSE("GPL");
diff --git a/drivers/cpufreq/ia64-acpi-cpufreq.c b/drivers/cpufreq/ia64-acpi-cpufreq.c
index a757c0a1e7b5..7974a2fdb760 100644
--- a/drivers/cpufreq/ia64-acpi-cpufreq.c
+++ b/drivers/cpufreq/ia64-acpi-cpufreq.c
@@ -270,10 +270,7 @@ acpi_cpufreq_cpu_init (
 		}
 	}
 
-	result = cpufreq_table_validate_and_show(policy, freq_table);
-	if (result) {
-		goto err_freqfree;
-	}
+	policy->freq_table = freq_table;
 
 	/* notify BIOS that we exist */
 	acpi_processor_notify_smm(THIS_MODULE);
@@ -296,8 +293,6 @@ acpi_cpufreq_cpu_init (
 
 	return (result);
 
- err_freqfree:
-	kfree(freq_table);
  err_unreg:
 	acpi_processor_unregister_performance(cpu);
  err_free:
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index ff67859948b3..83cf631fc9bc 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -52,6 +52,7 @@ static struct clk_bulk_data clks[] = {
 static struct device *cpu_dev;
 static bool free_opp;
 static struct cpufreq_frequency_table *freq_table;
+static unsigned int max_freq;
 static unsigned int transition_latency;
 
 static u32 *imx6_soc_volt;
@@ -196,7 +197,7 @@ static int imx6q_cpufreq_init(struct cpufreq_policy *policy)
 
 	policy->clk = clks[ARM].clk;
 	ret = cpufreq_generic_init(policy, freq_table, transition_latency);
-	policy->suspend_freq = policy-