Merge tag 'pm-4.20-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These make hibernation on 32-bit x86 systems work in all of the cases
  in which it works on 64-bit x86 ones, update the menu cpuidle governor
  and the "polling" state to make them more efficient, add more hardware
  support to cpufreq drivers and fix issues with some of them, fix a bug
  in the conservative cpufreq governor, fix the operating performance
  points (OPP) framework and make it more stable, update the devfreq
  subsystem to take changes in the APIs used by into account and clean
  up some things all over.

  Specifics:

   - Backport hibernation bug fixes from x86-64 to x86-32 and
     consolidate hibernation handling on x86 to allow 32-bit systems to
     work in all of the cases in which 64-bit ones work (Zhimin Gu, Chen
     Yu).

   - Fix hibernation documentation (Vladimir D. Seleznev).

   - Update the menu cpuidle governor to fix a couple of issues with it,
     make it more efficient in some cases and clean it up (Rafael
     Wysocki).

   - Rework the cpuidle polling state implementation to make it more
     efficient (Rafael Wysocki).

   - Clean up the cpuidle core somewhat (Fieah Lim).

   - Fix the cpufreq conservative governor to take policy limits into
     account properly in some cases (Rafael Wysocki).

   - Add support for retrieving guaranteed performance information to
     the ACPI CPPC library and make the intel_pstate driver use it to
     expose the CPU base frequency via sysfs on systems with the
     hardware-managed P-states (HWP) feature enabled (Srinivas
     Pandruvada).

   - Fix clang warning in the CPPC cpufreq driver (Nathan Chancellor).

   - Get rid of device_node.name printing from cpufreq (Rob Herring).

   - Remove unnecessary unlikely() from the cpufreq core (Igor Stoppa).

   - Add support for the r8a7744 SoC to the cpufreq-dt driver (Biju
     Das).

   - Update the dt-platdev cpufreq driver to allow RK3399 to have
     separate tunables per cluster (Dmitry Torokhov).

   - Fix the dma_alloc_coherent() usage in the tegra186 cpufreq driver
     (Christoph Hellwig).

   - Make the imx6q cpufreq driver read OCOTP through nvmem for
     imx6ul/imx6ull (Anson Huang).

   - Fix several bugs in the operating performance points (OPP)
     framework and make it more stable (Viresh Kumar, Dave Gerlach).

   - Update the devfreq subsystem to take changes in the APIs used by
     into account, fix some issues with it and make it stop print
     device_node.name directly (Bjorn Andersson, Enric Balletbo i Serra,
     Matthias Kaehlcke, Rob Herring, Vincent Donnefort, zhong jiang).

   - Prepare the generic power domains (genpd) framework for dealing
     with domains containing CPUs (Ulf Hansson).

   - Prevent sysfs attributes representing low-power S0 residency
     counters from being exposed if low-power S0 support is not
     indicated in ACPI FADT (Rajneesh Bhardwaj).

   - Get rid of custom CPU features macros for Intel CPUs from the
     intel_idle and RAPL drivers (Andy Shevchenko).

   - Update the tasks freezer to list tasks that refused to freeze and
     caused a system transition to a sleep state to be aborted (Todd
     Brandt).

   - Update the pm-graph set of tools to v5.2 (Todd Brandt).

   - Fix some issues in the cpupower utility (Anders Roxell, Prarit
     Bhargava)"

* tag 'pm-4.20-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (73 commits)
  PM / Domains: Document flags for genpd
  PM / Domains: Deal with multiple states but no governor in genpd
  PM / Domains: Don't treat zero found compatible idle states as an error
  cpuidle: menu: Avoid computations when result will be discarded
  cpuidle: menu: Drop redundant comparison
  cpufreq: tegra186: don't pass GFP_DMA32 to dma_alloc_coherent()
  cpufreq: conservative: Take limits changes into account properly
  Documentation: intel_pstate: Add base_frequency information
  cpufreq: intel_pstate: Add base_frequency attribute
  ACPI / CPPC: Add support for guaranteed performance
  cpuidle: menu: Simplify checks related to the polling state
  PM / tools: sleepgraph and bootgraph: upgrade to v5.2
  PM / tools: sleepgraph: first batch of v5.2 changes
  cpupower: Fix coredump on VMWare
  cpupower: Fix AMD Family 0x17 msr_pstate size
  cpufreq: imx6q: read OCOTP through nvmem for imx6ul/imx6ull
  cpufreq: dt-platdev: allow RK3399 to have separate tunables per cluster
  cpuidle: poll_state: Revise loop termination condition
  cpuidle: menu: Move the latency_req == 0 special case check
  cpuidle: menu: Avoid computations for very close timers
  ...

7 files changed, 102 insertions, 61 deletions

diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 4c49bb1330b5..141413067b5c 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/kmod.h>
 #include <linux/sched.h>
 #include <linux/errno.h>
 #include <linux/err.h>
@@ -28,9 +29,6 @@
 #include <linux/of.h>
 #include "governor.h"
 
-#define MAX(a,b)	((a > b) ? a : b)
-#define MIN(a,b)	((a < b) ? a : b)
-
 static struct class *devfreq_class;
 
 /*
@@ -221,6 +219,49 @@ static struct devfreq_governor *find_devfreq_governor(const char *name)
 	return ERR_PTR(-ENODEV);
 }
 
+/**
+ * try_then_request_governor() - Try to find the governor and request the
+ *                               module if is not found.
+ * @name:	name of the governor
+ *
+ * Search the list of devfreq governors and request the module and try again
+ * if is not found. This can happen when both drivers (the governor driver
+ * and the driver that call devfreq_add_device) are built as modules.
+ * devfreq_list_lock should be held by the caller. Returns the matched
+ * governor's pointer.
+ */
+static struct devfreq_governor *try_then_request_governor(const char *name)
+{
+	struct devfreq_governor *governor;
+	int err = 0;
+
+	if (IS_ERR_OR_NULL(name)) {
+		pr_err("DEVFREQ: %s: Invalid parameters\n", __func__);
+		return ERR_PTR(-EINVAL);
+	}
+	WARN(!mutex_is_locked(&devfreq_list_lock),
+	     "devfreq_list_lock must be locked.");
+
+	governor = find_devfreq_governor(name);
+	if (IS_ERR(governor)) {
+		mutex_unlock(&devfreq_list_lock);
+
+		if (!strncmp(name, DEVFREQ_GOV_SIMPLE_ONDEMAND,
+			     DEVFREQ_NAME_LEN))
+			err = request_module("governor_%s", "simpleondemand");
+		else
+			err = request_module("governor_%s", name);
+		/* Restore previous state before return */
+		mutex_lock(&devfreq_list_lock);
+		if (err)
+			return NULL;
+
+		governor = find_devfreq_governor(name);
+	}
+
+	return governor;
+}
+
 static int devfreq_notify_transition(struct devfreq *devfreq,
 		struct devfreq_freqs *freqs, unsigned int state)
 {
@@ -280,14 +321,14 @@ int update_devfreq(struct devfreq *devfreq)
 	 * max_freq
 	 * min_freq
 	 */
-	max_freq = MIN(devfreq->scaling_max_freq, devfreq->max_freq);
-	min_freq = MAX(devfreq->scaling_min_freq, devfreq->min_freq);
+	max_freq = min(devfreq->scaling_max_freq, devfreq->max_freq);
+	min_freq = max(devfreq->scaling_min_freq, devfreq->min_freq);
 
-	if (min_freq && freq < min_freq) {
+	if (freq < min_freq) {
 		freq = min_freq;
 		flags &= ~DEVFREQ_FLAG_LEAST_UPPER_BOUND; /* Use GLB */
 	}
-	if (max_freq && freq > max_freq) {
+	if (freq > max_freq) {
 		freq = max_freq;
 		flags |= DEVFREQ_FLAG_LEAST_UPPER_BOUND; /* Use LUB */
 	}
@@ -534,10 +575,6 @@ static void devfreq_dev_release(struct device *dev)
 	list_del(&devfreq->node);
 	mutex_unlock(&devfreq_list_lock);
 
-	if (devfreq->governor)
-		devfreq->governor->event_handler(devfreq,
-						 DEVFREQ_GOV_STOP, NULL);
-
 	if (devfreq->profile->exit)
 		devfreq->profile->exit(devfreq->dev.parent);
 
@@ -646,9 +683,8 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	mutex_unlock(&devfreq->lock);
 
 	mutex_lock(&devfreq_list_lock);
-	list_add(&devfreq->node, &devfreq_list);
 
-	governor = find_devfreq_governor(devfreq->governor_name);
+	governor = try_then_request_governor(devfreq->governor_name);
 	if (IS_ERR(governor)) {
 		dev_err(dev, "%s: Unable to find governor for the device\n",
 			__func__);
@@ -664,19 +700,20 @@ struct devfreq *devfreq_add_device(struct device *dev,
 			__func__);
 		goto err_init;
 	}
+
+	list_add(&devfreq->node, &devfreq_list);
+
 	mutex_unlock(&devfreq_list_lock);
 
 	return devfreq;
 
 err_init:
-	list_del(&devfreq->node);
 	mutex_unlock(&devfreq_list_lock);
 
-	device_unregister(&devfreq->dev);
+	devfreq_remove_device(devfreq);
 	devfreq = NULL;
 err_dev:
-	if (devfreq)
-		kfree(devfreq);
+	kfree(devfreq);
 err_out:
 	return ERR_PTR(err);
 }
@@ -693,6 +730,9 @@ int devfreq_remove_device(struct devfreq *devfreq)
 	if (!devfreq)
 		return -EINVAL;
 
+	if (devfreq->governor)
+		devfreq->governor->event_handler(devfreq,
+						 DEVFREQ_GOV_STOP, NULL);
 	device_unregister(&devfreq->dev);
 
 	return 0;
@@ -991,7 +1031,7 @@ static ssize_t governor_store(struct device *dev, struct device_attribute *attr,
 		return -EINVAL;
 
 	mutex_lock(&devfreq_list_lock);
-	governor = find_devfreq_governor(str_governor);
+	governor = try_then_request_governor(str_governor);
 	if (IS_ERR(governor)) {
 		ret = PTR_ERR(governor);
 		goto out;
@@ -1126,17 +1166,26 @@ static ssize_t min_freq_store(struct device *dev, struct device_attribute *attr,
 	struct devfreq *df = to_devfreq(dev);
 	unsigned long value;
 	int ret;
-	unsigned long max;
 
 	ret = sscanf(buf, "%lu", &value);
 	if (ret != 1)
 		return -EINVAL;
 
 	mutex_lock(&df->lock);
-	max = df->max_freq;
-	if (value && max && value > max) {
-		ret = -EINVAL;
-		goto unlock;
+
+	if (value) {
+		if (value > df->max_freq) {
+			ret = -EINVAL;
+			goto unlock;
+		}
+	} else {
+		unsigned long *freq_table = df->profile->freq_table;
+
+		/* Get minimum frequency according to sorting order */
+		if (freq_table[0] < freq_table[df->profile->max_state - 1])
+			value = freq_table[0];
+		else
+			value = freq_table[df->profile->max_state - 1];
 	}
 
 	df->min_freq = value;
@@ -1152,7 +1201,7 @@ static ssize_t min_freq_show(struct device *dev, struct device_attribute *attr,
 {
 	struct devfreq *df = to_devfreq(dev);
 
-	return sprintf(buf, "%lu\n", MAX(df->scaling_min_freq, df->min_freq));
+	return sprintf(buf, "%lu\n", max(df->scaling_min_freq, df->min_freq));
 }
 
 static ssize_t max_freq_store(struct device *dev, struct device_attribute *attr,
@@ -1161,17 +1210,26 @@ static ssize_t max_freq_store(struct device *dev, struct device_attribute *attr,
 	struct devfreq *df = to_devfreq(dev);
 	unsigned long value;
 	int ret;
-	unsigned long min;
 
 	ret = sscanf(buf, "%lu", &value);
 	if (ret != 1)
 		return -EINVAL;
 
 	mutex_lock(&df->lock);
-	min = df->min_freq;
-	if (value && min && value < min) {
-		ret = -EINVAL;
-		goto unlock;
+
+	if (value) {
+		if (value < df->min_freq) {
+			ret = -EINVAL;
+			goto unlock;
+		}
+	} else {
+		unsigned long *freq_table = df->profile->freq_table;
+
+		/* Get maximum frequency according to sorting order */
+		if (freq_table[0] < freq_table[df->profile->max_state - 1])
+			value = freq_table[df->profile->max_state - 1];
+		else
+			value = freq_table[0];
 	}
 
 	df->max_freq = value;
@@ -1188,7 +1246,7 @@ static ssize_t max_freq_show(struct device *dev, struct device_attribute *attr,
 {
 	struct devfreq *df = to_devfreq(dev);
 
-	return sprintf(buf, "%lu\n", MIN(df->scaling_max_freq, df->max_freq));
+	return sprintf(buf, "%lu\n", min(df->scaling_max_freq, df->max_freq));
 }
 static DEVICE_ATTR_RW(max_freq);
 
diff --git a/drivers/devfreq/event/exynos-ppmu.c b/drivers/devfreq/event/exynos-ppmu.c
index a9c64f0d3284..c61de0bdf053 100644
--- a/drivers/devfreq/event/exynos-ppmu.c
+++ b/drivers/devfreq/event/exynos-ppmu.c
@@ -535,8 +535,8 @@ static int of_get_devfreq_events(struct device_node *np,
 
 		if (i == ARRAY_SIZE(ppmu_events)) {
 			dev_warn(dev,
-				"don't know how to configure events : %s\n",
-				node->name);
+				"don't know how to configure events : %pOFn\n",
+				node);
 			continue;
 		}
 
diff --git a/drivers/devfreq/governor.h b/drivers/devfreq/governor.h
index cfc50a61a90d..f53339ca610f 100644
--- a/drivers/devfreq/governor.h
+++ b/drivers/devfreq/governor.h
@@ -25,6 +25,9 @@
 #define DEVFREQ_GOV_SUSPEND			0x4
 #define DEVFREQ_GOV_RESUME			0x5
 
+#define DEVFREQ_MIN_FREQ			0
+#define DEVFREQ_MAX_FREQ			ULONG_MAX
+
 /**
  * struct devfreq_governor - Devfreq policy governor
  * @node:		list node - contains registered devfreq governors
@@ -54,9 +57,6 @@ struct devfreq_governor {
 				unsigned int event, void *data);
 };
 
-/* Caution: devfreq->lock must be locked before calling update_devfreq */
-extern int update_devfreq(struct devfreq *devfreq);
-
 extern void devfreq_monitor_start(struct devfreq *devfreq);
 extern void devfreq_monitor_stop(struct devfreq *devfreq);
 extern void devfreq_monitor_suspend(struct devfreq *devfreq);
diff --git a/drivers/devfreq/governor_performance.c b/drivers/devfreq/governor_performance.c
index 4d23ecfbd948..ded429fd51be 100644
--- a/drivers/devfreq/governor_performance.c
+++ b/drivers/devfreq/governor_performance.c
@@ -20,10 +20,7 @@ static int devfreq_performance_func(struct devfreq *df,
 	 * target callback should be able to get floor value as
 	 * said in devfreq.h
 	 */
-	if (!df->max_freq)
-		*freq = UINT_MAX;
-	else
-		*freq = df->max_freq;
+	*freq = DEVFREQ_MAX_FREQ;
 	return 0;
 }
 
diff --git a/drivers/devfreq/governor_powersave.c b/drivers/devfreq/governor_powersave.c
index 0c42f23249ef..9e8897f5ac42 100644
--- a/drivers/devfreq/governor_powersave.c
+++ b/drivers/devfreq/governor_powersave.c
@@ -20,7 +20,7 @@ static int devfreq_powersave_func(struct devfreq *df,
 	 * target callback should be able to get ceiling value as
 	 * said in devfreq.h
 	 */
-	*freq = df->min_freq;
+	*freq = DEVFREQ_MIN_FREQ;
 	return 0;
 }
 
diff --git a/drivers/devfreq/governor_simpleondemand.c b/drivers/devfreq/governor_simpleondemand.c
index 28e0f2de7100..c0417f0e081e 100644
--- a/drivers/devfreq/governor_simpleondemand.c
+++ b/drivers/devfreq/governor_simpleondemand.c
@@ -27,7 +27,6 @@ static int devfreq_simple_ondemand_func(struct devfreq *df,
 	unsigned int dfso_upthreshold = DFSO_UPTHRESHOLD;
 	unsigned int dfso_downdifferential = DFSO_DOWNDIFFERENCTIAL;
 	struct devfreq_simple_ondemand_data *data = df->data;
-	unsigned long max = (df->max_freq) ? df->max_freq : UINT_MAX;
 
 	err = devfreq_update_stats(df);
 	if (err)
@@ -47,7 +46,7 @@ static int devfreq_simple_ondemand_func(struct devfreq *df,
 
 	/* Assume MAX if it is going to be divided by zero */
 	if (stat->total_time == 0) {
-		*freq = max;
+		*freq = DEVFREQ_MAX_FREQ;
 		return 0;
 	}
 
@@ -60,13 +59,13 @@ static int devfreq_simple_ondemand_func(struct devfreq *df,
 	/* Set MAX if it's busy enough */
 	if (stat->busy_time * 100 >
 	    stat->total_time * dfso_upthreshold) {
-		*freq = max;
+		*freq = DEVFREQ_MAX_FREQ;
 		return 0;
 	}
 
 	/* Set MAX if we do not know the initial frequency */
 	if (stat->current_frequency == 0) {
-		*freq = max;
+		*freq = DEVFREQ_MAX_FREQ;
 		return 0;
 	}
 
@@ -85,11 +84,6 @@ static int devfreq_simple_ondemand_func(struct devfreq *df,
 	b = div_u64(b, (dfso_upthreshold - dfso_downdifferential / 2));
 	*freq = (unsigned long) b;
 
-	if (df->min_freq && *freq < df->min_freq)
-		*freq = df->min_freq;
-	if (df->max_freq && *freq > df->max_freq)
-		*freq = df->max_freq;
-
 	return 0;
 }
 
diff --git a/drivers/devfreq/governor_userspace.c b/drivers/devfreq/governor_userspace.c
index 080607c3f34d..378d84c011df 100644
--- a/drivers/devfreq/governor_userspace.c
+++ b/drivers/devfreq/governor_userspace.c
@@ -26,19 +26,11 @@ static int devfreq_userspace_func(struct devfreq *df, unsigned long *freq)
 {
 	struct userspace_data *data = df->data;
 
-	if (data->valid) {
-		unsigned long adjusted_freq = data->user_frequency;
-
-		if (df->max_freq && adjusted_freq > df->max_freq)
-			adjusted_freq = df->max_freq;
-
-		if (df->min_freq && adjusted_freq < df->min_freq)
-			adjusted_freq = df->min_freq;
-
-		*freq = adjusted_freq;
-	} else {
+	if (data->valid)
+		*freq = data->user_frequency;
+	else
 		*freq = df->previous_freq; /* No user freq specified yet */
-	}
+
 	return 0;
 }