Merge tag 'pm-4.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These add a new framework for CPU idle time injection, to be used by
  all of the idle injection code in the kernel in the future, fix some
  issues and add a number of relatively small extensions in multiple
  places.

  Specifics:

   - Add a new framework for CPU idle time injection (Daniel Lezcano).

   - Add AVS support to the armada-37xx cpufreq driver (Gregory
     CLEMENT).

   - Add support for current CPU frequency reporting to the ACPI CPPC
     cpufreq driver (George Cherian).

   - Rework the cooling device registration in the imx6q/thermal driver
     (Bastian Stender).

   - Make the pcc-cpufreq driver refuse to work with dynamic scaling
     governors on systems with many CPUs to avoid scalability issues
     with it (Rafael Wysocki).

   - Fix the intel_pstate driver to report different maximum CPU
     frequencies on systems where they really are different and to
     ignore the turbo active ratio if hardware-managend P-states (HWP)
     are in use; make it use the match_string() helper (Xie Yisheng,
     Srinivas Pandruvada).

   - Fix a minor deferred probe issue in the qcom-kryo cpufreq driver
     (Niklas Cassel).

   - Add a tracepoint for the tracking of frequency limits changes (from
     Andriod) to the cpufreq core (Ruchi Kandoi).

   - Fix a circular lock dependency between CPU hotplug and sysfs
     locking in the cpufreq core reported by lockdep (Waiman Long).

   - Avoid excessive error reports on driver registration failures in
     the ARM cpuidle driver (Sudeep Holla).

   - Add a new device links flag to the driver core to make links go
     away automatically on supplier driver removal (Vivek Gautam).

   - Eliminate potential race condition between system-wide power
     management transitions and system shutdown (Pingfan Liu).

   - Add a quirk to save NVS memory on system suspend for the ASUS 1025C
     laptop (Willy Tarreau).

   - Make more systems use suspend-to-idle (instead of ACPI S3) by
     default (Tristian Celestin).

   - Get rid of stack VLA usage in the low-level hibernation code on
     64-bit x86 (Kees Cook).

   - Fix error handling in the hibernation core and mark an expected
     fall-through switch in it (Chengguang Xu, Gustavo Silva).

   - Extend the generic power domains (genpd) framework to support
     attaching a device to a power domain by name (Ulf Hansson).

   - Fix device reference counting and user limits initialization in the
     devfreq core (Arvind Yadav, Matthias Kaehlcke).

   - Fix a few issues in the rk3399_dmc devfreq driver and improve its
     documentation (Enric Balletbo i Serra, Lin Huang, Nick Milner).

   - Drop a redundant error message from the exynos-ppmu devfreq driver
     (Markus Elfring)"

* tag 'pm-4.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (35 commits)
  PM / reboot: Eliminate race between reboot and suspend
  PM / hibernate: Mark expected switch fall-through
  cpufreq: intel_pstate: Ignore turbo active ratio in HWP
  cpufreq: Fix a circular lock dependency problem
  cpu/hotplug: Add a cpus_read_trylock() function
  x86/power/hibernate_64: Remove VLA usage
  cpufreq: trace frequency limits change
  cpufreq: intel_pstate: Show different max frequency with turbo 3 and HWP
  cpufreq: pcc-cpufreq: Disable dynamic scaling on many-CPU systems
  cpufreq: qcom-kryo: Silently error out on EPROBE_DEFER
  cpufreq / CPPC: Add cpuinfo_cur_freq support for CPPC
  cpufreq: armada-37xx: Add AVS support
  dt-bindings: marvell: Add documentation for the Armada 3700 AVS binding
  PM / devfreq: rk3399_dmc: Fix duplicated opp table on reload.
  PM / devfreq: Init user limits from OPP limits, not viceversa
  PM / devfreq: rk3399_dmc: fix spelling mistakes.
  PM / devfreq: rk3399_dmc: do not print error when get supply and clk defer.
  dt-bindings: devfreq: rk3399_dmc: move interrupts to be optional.
  PM / devfreq: rk3399_dmc: remove wait for dcf irq event.
  dt-bindings: clock: add rk3399 DDR3 standard speed bins.
  ...

23 files changed, 794 insertions, 119 deletions

diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 5d0486f1cfcd..754d59f95500 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -338,6 +338,14 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "K54HR"),
 		},
 	},
+	{
+	.callback = init_nvs_save_s3,
+	.ident = "Asus 1025C",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "1025C"),
+		},
+	},
 	/*
 	 * https://bugzilla.kernel.org/show_bug.cgi?id=189431
 	 * Lenovo G50-45 is a platform later than 2012, but needs nvs memory
@@ -718,9 +726,6 @@ static const struct acpi_device_id lps0_device_ids[] = {
 #define ACPI_LPS0_ENTRY		5
 #define ACPI_LPS0_EXIT		6
 
-#define ACPI_LPS0_SCREEN_MASK	((1 << ACPI_LPS0_SCREEN_OFF) | (1 << ACPI_LPS0_SCREEN_ON))
-#define ACPI_LPS0_PLATFORM_MASK	((1 << ACPI_LPS0_ENTRY) | (1 << ACPI_LPS0_EXIT))
-
 static acpi_handle lps0_device_handle;
 static guid_t lps0_dsm_guid;
 static char lps0_dsm_func_mask;
@@ -924,17 +929,14 @@ static int lps0_device_attach(struct acpi_device *adev,
 	if (out_obj && out_obj->type == ACPI_TYPE_BUFFER) {
 		char bitmask = *(char *)out_obj->buffer.pointer;
 
-		if ((bitmask & ACPI_LPS0_PLATFORM_MASK) == ACPI_LPS0_PLATFORM_MASK ||
-		    (bitmask & ACPI_LPS0_SCREEN_MASK) == ACPI_LPS0_SCREEN_MASK) {
-			lps0_dsm_func_mask = bitmask;
-			lps0_device_handle = adev->handle;
-			/*
-			 * Use suspend-to-idle by default if the default
-			 * suspend mode was not set from the command line.
-			 */
-			if (mem_sleep_default > PM_SUSPEND_MEM)
-				mem_sleep_current = PM_SUSPEND_TO_IDLE;
-		}
+		lps0_dsm_func_mask = bitmask;
+		lps0_device_handle = adev->handle;
+		/*
+		 * Use suspend-to-idle by default if the default
+		 * suspend mode was not set from the command line.
+		 */
+		if (mem_sleep_default > PM_SUSPEND_MEM)
+			mem_sleep_current = PM_SUSPEND_TO_IDLE;
 
 		acpi_handle_debug(adev->handle, "_DSM function mask: 0x%x\n",
 				  bitmask);
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 2ab316d85651..9d3c15d4dde8 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -178,10 +178,10 @@ void device_pm_move_to_tail(struct device *dev)
  * of the link.  If DL_FLAG_PM_RUNTIME is not set, DL_FLAG_RPM_ACTIVE will be
  * ignored.
  *
- * If the DL_FLAG_AUTOREMOVE is set, the link will be removed automatically
- * when the consumer device driver unbinds from it.  The combination of both
- * DL_FLAG_AUTOREMOVE and DL_FLAG_STATELESS set is invalid and will cause NULL
- * to be returned.
+ * If the DL_FLAG_AUTOREMOVE_CONSUMER is set, the link will be removed
+ * automatically when the consumer device driver unbinds from it.
+ * The combination of both DL_FLAG_AUTOREMOVE_CONSUMER and DL_FLAG_STATELESS
+ * set is invalid and will cause NULL to be returned.
  *
  * A side effect of the link creation is re-ordering of dpm_list and the
  * devices_kset list by moving the consumer device and all devices depending
@@ -198,7 +198,8 @@ struct device_link *device_link_add(struct device *consumer,
 	struct device_link *link;
 
 	if (!consumer || !supplier ||
-	    ((flags & DL_FLAG_STATELESS) && (flags & DL_FLAG_AUTOREMOVE)))
+	    ((flags & DL_FLAG_STATELESS) &&
+	     (flags & DL_FLAG_AUTOREMOVE_CONSUMER)))
 		return NULL;
 
 	device_links_write_lock();
@@ -509,7 +510,7 @@ static void __device_links_no_driver(struct device *dev)
 		if (link->flags & DL_FLAG_STATELESS)
 			continue;
 
-		if (link->flags & DL_FLAG_AUTOREMOVE)
+		if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER)
 			kref_put(&link->kref, __device_link_del);
 		else if (link->status != DL_STATE_SUPPLIER_UNBIND)
 			WRITE_ONCE(link->status, DL_STATE_AVAILABLE);
@@ -545,8 +546,18 @@ void device_links_driver_cleanup(struct device *dev)
 		if (link->flags & DL_FLAG_STATELESS)
 			continue;
 
-		WARN_ON(link->flags & DL_FLAG_AUTOREMOVE);
+		WARN_ON(link->flags & DL_FLAG_AUTOREMOVE_CONSUMER);
 		WARN_ON(link->status != DL_STATE_SUPPLIER_UNBIND);
+
+		/*
+		 * autoremove the links between this @dev and its consumer
+		 * devices that are not active, i.e. where the link state
+		 * has moved to DL_STATE_SUPPLIER_UNBIND.
+		 */
+		if (link->status == DL_STATE_SUPPLIER_UNBIND &&
+		    link->flags & DL_FLAG_AUTOREMOVE_SUPPLIER)
+			kref_put(&link->kref, __device_link_del);
+
 		WRITE_ONCE(link->status, DL_STATE_DORMANT);
 	}
 
diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c
index df41b4780b3b..b413951c6abc 100644
--- a/drivers/base/power/common.c
+++ b/drivers/base/power/common.c
@@ -153,6 +153,23 @@ struct device *dev_pm_domain_attach_by_id(struct device *dev,
 EXPORT_SYMBOL_GPL(dev_pm_domain_attach_by_id);
 
 /**
+ * dev_pm_domain_attach_by_name - Associate a device with one of its PM domains.
+ * @dev: The device used to lookup the PM domain.
+ * @name: The name of the PM domain.
+ *
+ * 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)
+{
+	if (dev->pm_domain)
+		return ERR_PTR(-EEXIST);
+
+	return genpd_dev_pm_attach_by_name(dev, name);
+}
+EXPORT_SYMBOL_GPL(dev_pm_domain_attach_by_name);
+
+/**
  * dev_pm_domain_detach - Detach a device from its PM domain.
  * @dev: Device to detach.
  * @power_off: Used to indicate whether we should power off the device.
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 9e8484189034..79bdca70a81a 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -2374,6 +2374,30 @@ struct device *genpd_dev_pm_attach_by_id(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(genpd_dev_pm_attach_by_id);
 
+/**
+ * genpd_dev_pm_attach_by_name - Associate a device with one of its PM domains.
+ * @dev: The device used to lookup the PM domain.
+ * @name: The name of the PM domain.
+ *
+ * Parse device's OF node to find a PM domain specifier using the
+ * 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)
+{
+	int index;
+
+	if (!dev->of_node)
+		return NULL;
+
+	index = of_property_match_string(dev->of_node, "power-domain-names",
+					 name);
+	if (index < 0)
+		return NULL;
+
+	return genpd_dev_pm_attach_by_id(dev, index);
+}
+
 static const struct of_device_id idle_state_match[] = {
 	{ .compatible = "domain-idle-state", },
 	{ }
diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c
index 739da90ff3f6..75491fc841a6 100644
--- a/drivers/cpufreq/armada-37xx-cpufreq.c
+++ b/drivers/cpufreq/armada-37xx-cpufreq.c
@@ -51,6 +51,16 @@
 #define  ARMADA_37XX_DVFS_LOAD_2	2
 #define  ARMADA_37XX_DVFS_LOAD_3	3
 
+/* AVS register set */
+#define ARMADA_37XX_AVS_CTL0		0x0
+#define	 ARMADA_37XX_AVS_ENABLE		BIT(30)
+#define	 ARMADA_37XX_AVS_HIGH_VDD_LIMIT	16
+#define	 ARMADA_37XX_AVS_LOW_VDD_LIMIT	22
+#define	 ARMADA_37XX_AVS_VDD_MASK	0x3F
+#define ARMADA_37XX_AVS_CTL2		0x8
+#define	 ARMADA_37XX_AVS_LOW_VDD_EN	BIT(6)
+#define ARMADA_37XX_AVS_VSET(x)	    (0x1C + 4 * (x))
+
 /*
  * On Armada 37xx the Power management manages 4 level of CPU load,
  * each level can be associated with a CPU clock source, a CPU
@@ -58,6 +68,17 @@
  */
 #define LOAD_LEVEL_NR	4
 
+#define MIN_VOLT_MV 1000
+
+/*  AVS value for the corresponding voltage (in mV) */
+static int avs_map[] = {
+	747, 758, 770, 782, 793, 805, 817, 828, 840, 852, 863, 875, 887, 898,
+	910, 922, 933, 945, 957, 968, 980, 992, 1003, 1015, 1027, 1038, 1050,
+	1062, 1073, 1085, 1097, 1108, 1120, 1132, 1143, 1155, 1167, 1178, 1190,
+	1202, 1213, 1225, 1237, 1248, 1260, 1272, 1283, 1295, 1307, 1318, 1330,
+	1342
+};
+
 struct armada37xx_cpufreq_state {
 	struct regmap *regmap;
 	u32 nb_l0l1;
@@ -71,6 +92,7 @@ static struct armada37xx_cpufreq_state *armada37xx_cpufreq_state;
 struct armada_37xx_dvfs {
 	u32 cpu_freq_max;
 	u8 divider[LOAD_LEVEL_NR];
+	u32 avs[LOAD_LEVEL_NR];
 };
 
 static struct armada_37xx_dvfs armada_37xx_dvfs[] = {
@@ -148,6 +170,128 @@ static void __init armada37xx_cpufreq_dvfs_setup(struct regmap *base,
 	clk_set_parent(clk, parent);
 }
 
+/*
+ * Find out the armada 37x supported AVS value whose voltage value is
+ * the round-up closest to the target voltage value.
+ */
+static u32 armada_37xx_avs_val_match(int target_vm)
+{
+	u32 avs;
+
+	/* Find out the round-up closest supported voltage value */
+	for (avs = 0; avs < ARRAY_SIZE(avs_map); avs++)
+		if (avs_map[avs] >= target_vm)
+			break;
+
+	/*
+	 * If all supported voltages are smaller than target one,
+	 * choose the largest supported voltage
+	 */
+	if (avs == ARRAY_SIZE(avs_map))
+		avs = ARRAY_SIZE(avs_map) - 1;
+
+	return avs;
+}
+
+/*
+ * For Armada 37xx soc, L0(VSET0) VDD AVS value is set to SVC revision
+ * value or a default value when SVC is not supported.
+ * - L0 can be read out from the register of AVS_CTRL_0 and L0 voltage
+ *   can be got from the mapping table of avs_map.
+ * - L1 voltage should be about 100mv smaller than L0 voltage
+ * - L2 & L3 voltage should be about 150mv smaller than L0 voltage.
+ * This function calculates L1 & L2 & L3 AVS values dynamically based
+ * on L0 voltage and fill all AVS values to the AVS value table.
+ */
+static void __init armada37xx_cpufreq_avs_configure(struct regmap *base,
+						struct armada_37xx_dvfs *dvfs)
+{
+	unsigned int target_vm;
+	int load_level = 0;
+	u32 l0_vdd_min;
+
+	if (base == NULL)
+		return;
+
+	/* Get L0 VDD min value */
+	regmap_read(base, ARMADA_37XX_AVS_CTL0, &l0_vdd_min);
+	l0_vdd_min = (l0_vdd_min >> ARMADA_37XX_AVS_LOW_VDD_LIMIT) &
+		ARMADA_37XX_AVS_VDD_MASK;
+	if (l0_vdd_min >= ARRAY_SIZE(avs_map))  {
+		pr_err("L0 VDD MIN %d is not correct.\n", l0_vdd_min);
+		return;
+	}
+	dvfs->avs[0] = l0_vdd_min;
+
+	if (avs_map[l0_vdd_min] <= MIN_VOLT_MV) {
+		/*
+		 * If L0 voltage is smaller than 1000mv, then all VDD sets
+		 * use L0 voltage;
+		 */
+		u32 avs_min = armada_37xx_avs_val_match(MIN_VOLT_MV);
+
+		for (load_level = 1; load_level < LOAD_LEVEL_NR; load_level++)
+			dvfs->avs[load_level] = avs_min;
+
+		return;
+	}
+
+	/*
+	 * L1 voltage is equal to L0 voltage - 100mv and it must be
+	 * larger than 1000mv
+	 */
+
+	target_vm = avs_map[l0_vdd_min] - 100;
+	target_vm = target_vm > MIN_VOLT_MV ? target_vm : MIN_VOLT_MV;
+	dvfs->avs[1] = armada_37xx_avs_val_match(target_vm);
+
+	/*
+	 * L2 & L3 voltage is equal to L0 voltage - 150mv and it must
+	 * be larger than 1000mv
+	 */
+	target_vm = avs_map[l0_vdd_min] - 150;
+	target_vm = target_vm > MIN_VOLT_MV ? target_vm : MIN_VOLT_MV;
+	dvfs->avs[2] = dvfs->avs[3] = armada_37xx_avs_val_match(target_vm);
+}
+
+static void __init armada37xx_cpufreq_avs_setup(struct regmap *base,
+						struct armada_37xx_dvfs *dvfs)
+{
+	unsigned int avs_val = 0, freq;
+	int load_level = 0;
+
+	if (base == NULL)
+		return;
+
+	/* Disable AVS before the configuration */
+	regmap_update_bits(base, ARMADA_37XX_AVS_CTL0,
+			   ARMADA_37XX_AVS_ENABLE, 0);
+
+
+	/* Enable low voltage mode */
+	regmap_update_bits(base, ARMADA_37XX_AVS_CTL2,
+			   ARMADA_37XX_AVS_LOW_VDD_EN,
+			   ARMADA_37XX_AVS_LOW_VDD_EN);
+
+
+	for (load_level = 1; load_level < LOAD_LEVEL_NR; load_level++) {
+		freq = dvfs->cpu_freq_max / dvfs->divider[load_level];
+
+		avs_val = dvfs->avs[load_level];
+		regmap_update_bits(base, ARMADA_37XX_AVS_VSET(load_level-1),
+		    ARMADA_37XX_AVS_VDD_MASK << ARMADA_37XX_AVS_HIGH_VDD_LIMIT |
+		    ARMADA_37XX_AVS_VDD_MASK << ARMADA_37XX_AVS_LOW_VDD_LIMIT,
+		    avs_val << ARMADA_37XX_AVS_HIGH_VDD_LIMIT |
+		    avs_val << ARMADA_37XX_AVS_LOW_VDD_LIMIT);
+	}
+
+	/* Enable AVS after the configuration */
+	regmap_update_bits(base, ARMADA_37XX_AVS_CTL0,
+			   ARMADA_37XX_AVS_ENABLE,
+			   ARMADA_37XX_AVS_ENABLE);
+
+}
+
 static void armada37xx_cpufreq_disable_dvfs(struct regmap *base)
 {
 	unsigned int reg = ARMADA_37XX_NB_DYN_MOD,
@@ -216,7 +360,7 @@ static int __init armada37xx_cpufreq_driver_init(void)
 	struct platform_device *pdev;
 	unsigned long freq;
 	unsigned int cur_frequency;
-	struct regmap *nb_pm_base;
+	struct regmap *nb_pm_base, *avs_base;
 	struct device *cpu_dev;
 	int load_lvl, ret;
 	struct clk *clk;
@@ -227,6 +371,14 @@ static int __init armada37xx_cpufreq_driver_init(void)
 	if (IS_ERR(nb_pm_base))
 		return -ENODEV;
 
+	avs_base =
+		syscon_regmap_lookup_by_compatible("marvell,armada-3700-avs");
+
+	/* if AVS is not present don't use it but still try to setup dvfs */
+	if (IS_ERR(avs_base)) {
+		pr_info("Syscon failed for Adapting Voltage Scaling: skip it\n");
+		avs_base = NULL;
+	}
 	/* Before doing any configuration on the DVFS first, disable it */
 	armada37xx_cpufreq_disable_dvfs(nb_pm_base);
 
@@ -270,16 +422,21 @@ static int __init armada37xx_cpufreq_driver_init(void)
 
 	armada37xx_cpufreq_state->regmap = nb_pm_base;
 
+	armada37xx_cpufreq_avs_configure(avs_base, dvfs);
+	armada37xx_cpufreq_avs_setup(avs_base, dvfs);
+
 	armada37xx_cpufreq_dvfs_setup(nb_pm_base, clk, dvfs->divider);
 	clk_put(clk);
 
 	for (load_lvl = ARMADA_37XX_DVFS_LOAD_0; load_lvl < LOAD_LEVEL_NR;
 	     load_lvl++) {
+		unsigned long u_volt = avs_map[dvfs->avs[load_lvl]] * 1000;
 		freq = cur_frequency / dvfs->divider[load_lvl];
-
-		ret = dev_pm_opp_add(cpu_dev, freq, 0);
+		ret = dev_pm_opp_add(cpu_dev, freq, u_volt);
 		if (ret)
 			goto remove_opp;
+
+
 	}
 
 	/* Now that everything is setup, enable the DVFS at hardware level */
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index a9d3eec32795..30f302149730 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -296,10 +296,62 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	return ret;
 }
 
+static inline u64 get_delta(u64 t1, u64 t0)
+{
+	if (t1 > t0 || t0 > ~(u32)0)
+		return t1 - t0;
+
+	return (u32)t1 - (u32)t0;
+}
+
+static int cppc_get_rate_from_fbctrs(struct cppc_cpudata *cpu,
+				     struct cppc_perf_fb_ctrs fb_ctrs_t0,
+				     struct cppc_perf_fb_ctrs fb_ctrs_t1)
+{
+	u64 delta_reference, delta_delivered;
+	u64 reference_perf, delivered_perf;
+
+	reference_perf = fb_ctrs_t0.reference_perf;
+
+	delta_reference = get_delta(fb_ctrs_t1.reference,
+				    fb_ctrs_t0.reference);
+	delta_delivered = get_delta(fb_ctrs_t1.delivered,
+				    fb_ctrs_t0.delivered);
+
+	/* Check to avoid divide-by zero */
+	if (delta_reference || delta_delivered)
+		delivered_perf = (reference_perf * delta_delivered) /
+					delta_reference;
+	else
+		delivered_perf = cpu->perf_ctrls.desired_perf;
+
+	return cppc_cpufreq_perf_to_khz(cpu, delivered_perf);
+}
+
+static unsigned int cppc_cpufreq_get_rate(unsigned int cpunum)
+{
+	struct cppc_perf_fb_ctrs fb_ctrs_t0 = {0}, fb_ctrs_t1 = {0};
+	struct cppc_cpudata *cpu = all_cpu_data[cpunum];
+	int ret;
+
+	ret = cppc_get_perf_ctrs(cpunum, &fb_ctrs_t0);
+	if (ret)
+		return ret;
+
+	udelay(2); /* 2usec delay between sampling */
+
+	ret = cppc_get_perf_ctrs(cpunum, &fb_ctrs_t1);
+	if (ret)
+		return ret;
+
+	return cppc_get_rate_from_fbctrs(cpu, fb_ctrs_t0, fb_ctrs_t1);
+}
+
 static struct cpufreq_driver cppc_cpufreq_driver = {
 	.flags = CPUFREQ_CONST_LOOPS,
 	.verify = cppc_verify_policy,
 	.target = cppc_cpufreq_set_target,
+	.get = cppc_cpufreq_get_rate,
 	.init = cppc_cpufreq_cpu_init,
 	.stop_cpu = cppc_cpufreq_stop_cpu,
 	.name = "cppc_cpufreq",
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index b0dfd3222013..f53fb41efb7b 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -923,7 +923,12 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
 	struct freq_attr *fattr = to_attr(attr);
 	ssize_t ret = -EINVAL;
 
-	cpus_read_lock();
+	/*
+	 * cpus_read_trylock() is used here to work around a circular lock
+	 * dependency problem with respect to the cpufreq_register_driver().
+	 */
+	if (!cpus_read_trylock())
+		return -EBUSY;
 
 	if (cpu_online(policy->cpu)) {
 		down_write(&policy->rwsem);
@@ -2236,6 +2241,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 
 	policy->min = new_policy->min;
 	policy->max = new_policy->max;
+	trace_cpu_frequency_limits(policy);
 
 	policy->cached_target_freq = UINT_MAX;
 
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index 8b3c2a79ad6c..b2ff423ad7f8 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -9,6 +9,7 @@
 #include <linux/clk.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
+#include <linux/cpu_cooling.h>
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -50,6 +51,7 @@ static struct clk_bulk_data clks[] = {
 };
 
 static struct device *cpu_dev;
+static struct thermal_cooling_device *cdev;
 static bool free_opp;
 static struct cpufreq_frequency_table *freq_table;
 static unsigned int max_freq;
@@ -191,6 +193,16 @@ static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index)
 	return 0;
 }
 
+static void imx6q_cpufreq_ready(struct cpufreq_policy *policy)
+{
+	cdev = of_cpufreq_cooling_register(policy);
+
+	if (!cdev)
+		dev_err(cpu_dev,
+			"running cpufreq without cooling device: %ld\n",
+			PTR_ERR(cdev));
+}
+
 static int imx6q_cpufreq_init(struct cpufreq_policy *policy)
 {
 	int ret;
@@ -202,13 +214,22 @@ static int imx6q_cpufreq_init(struct cpufreq_policy *policy)
 	return ret;
 }
 
+static int imx6q_cpufreq_exit(struct cpufreq_policy *policy)
+{
+	cpufreq_cooling_unregister(cdev);
+
+	return 0;
+}
+
 static struct cpufreq_driver imx6q_cpufreq_driver = {
 	.flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK,
 	.verify = cpufreq_generic_frequency_table_verify,
 	.target_index = imx6q_set_target,
 	.get = cpufreq_generic_get,
 	.init = imx6q_cpufreq_init,
+	.exit = imx6q_cpufreq_exit,
 	.name = "imx6q-cpufreq",
+	.ready = imx6q_cpufreq_ready,
 	.attr = cpufreq_generic_attr,
 	.suspend = cpufreq_generic_suspend,
 };
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index d4ed0022b0dd..b6a1aadaff9f 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -670,21 +670,18 @@ static ssize_t store_energy_performance_preference(
 {
 	struct cpudata *cpu_data = all_cpu_data[policy->cpu];
 	char str_preference[21];
-	int ret, i = 0;
+	int ret;
 
 	ret = sscanf(buf, "%20s", str_preference);
 	if (ret != 1)
 		return -EINVAL;
 
-	while (energy_perf_strings[i] != NULL) {
-		if (!strcmp(str_preference, energy_perf_strings[i])) {
-			intel_pstate_set_energy_pref_index(cpu_data, i);
-			return count;
-		}
-		++i;
-	}
+	ret = match_string(energy_perf_strings, -1, str_preference);
+	if (ret < 0)
+		return ret;
 
-	return -EINVAL;
+	intel_pstate_set_energy_pref_index(cpu_data, ret);
+	return count;
 }
 
 static ssize_t show_energy_performance_preference(
@@ -2011,7 +2008,8 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 static void intel_pstate_adjust_policy_max(struct cpufreq_policy *policy,
 					 struct cpudata *cpu)
 {
-	if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
+	if (!hwp_active &&
+	    cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
 	    policy->max < policy->cpuinfo.max_freq &&
 	    policy->max > cpu->pstate.max_freq) {
 		pr_debug("policy->max > max non turbo frequency\n");
@@ -2085,6 +2083,15 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy)
 			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
 	policy->cpuinfo.max_freq *= cpu->pstate.scaling;
 
+	if (hwp_active) {
+		unsigned int max_freq;
+
+		max_freq = global.turbo_disabled ?
+			cpu->pstate.max_freq : cpu->pstate.turbo_freq;
+		if (max_freq < policy->cpuinfo.max_freq)
+			policy->cpuinfo.max_freq = max_freq;
+	}
+
 	intel_pstate_init_acpi_perf_limits(policy);
 
 	policy->fast_switch_possible = true;
diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c
index 0c56c9759672..099a849396f6 100644
--- a/drivers/cpufreq/pcc-cpufreq.c
+++ b/drivers/cpufreq/pcc-cpufreq.c
@@ -593,6 +593,15 @@ static int __init pcc_cpufreq_init(void)
 		return ret;
 	}
 
+	if (num_present_cpus() > 4) {
+		pcc_cpufreq_driver.flags |= CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING;
+		pr_err("%s: Too many CPUs, dynamic performance scaling disabled\n",
+		       __func__);
+		pr_err("%s: Try to enable another scaling driver through BIOS settings\n",
+		       __func__);
+		pr_err("%s: and complain to the system vendor\n", __func__);
+	}
+
 	ret = cpufreq_register_driver(&pcc_cpufreq_driver);
 
 	return ret;
diff --git a/drivers/cpufreq/qcom-cpufreq-kryo.c b/drivers/cpufreq/qcom-cpufreq-kryo.c
index efc9a7ae4857..a1830fa25fc5 100644
--- a/drivers/cpufreq/qcom-cpufreq-kryo.c
+++ b/drivers/cpufreq/qcom-cpufreq-kryo.c
@@ -109,8 +109,9 @@ static int qcom_cpufreq_kryo_probe(struct platform_device *pdev)
 	speedbin_nvmem = of_nvmem_cell_get(np, NULL);
 	of_node_put(np);
 	if (IS_ERR(speedbin_nvmem)) {
-		dev_err(cpu_dev, "Could not get nvmem cell: %ld\n",
-			PTR_ERR(speedbin_nvmem));
+		if (PTR_ERR(speedbin_nvmem) != -EPROBE_DEFER)
+			dev_err(cpu_dev, "Could not get nvmem cell: %ld\n",
+				PTR_ERR(speedbin_nvmem));
 		return PTR_ERR(speedbin_nvmem);
 	}
 
diff --git a/drivers/cpuidle/cpuidle-arm.c b/drivers/cpuidle/cpuidle-arm.c
index e07bc7ace774..073557f433eb 100644
--- a/drivers/cpuidle/cpuidle-arm.c
+++ b/drivers/cpuidle/cpuidle-arm.c
@@ -105,7 +105,8 @@ static int __init arm_idle_init_cpu(int cpu)
 
 	ret = cpuidle_register_driver(drv);
 	if (ret) {
-		pr_err("Failed to register cpuidle driver\n");
+		if (ret != -EBUSY)
+			pr_err("Failed to register cpuidle driver\n");
 		goto out_kfree_drv;
 	}
 
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 0b5b3abe054e..4c49bb1330b5 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -604,28 +604,29 @@ struct devfreq *devfreq_add_device(struct device *dev,
 		mutex_lock(&devfreq->lock);
 	}
 
-	devfreq->min_freq = find_available_min_freq(devfreq);
-	if (!devfreq->min_freq) {
+	devfreq->scaling_min_freq = find_available_min_freq(devfreq);
+	if (!devfreq->scaling_min_freq) {
 		mutex_unlock(&devfreq->lock);
 		err = -EINVAL;
 		goto err_dev;
 	}
-	devfreq->scaling_min_freq = devfreq->min_freq;
+	devfreq->min_freq = devfreq->scaling_min_freq;
 
-	devfreq->max_freq = find_available_max_freq(devfreq);
-	if (!devfreq->max_freq) {
+	devfreq->scaling_max_freq = find_available_max_freq(devfreq);
+	if (!devfreq->scaling_max_freq) {
 		mutex_unlock(&devfreq->lock);
 		err = -EINVAL;
 		goto err_dev;
 	}
-	devfreq->scaling_max_freq = devfreq->max_freq;
+	devfreq->max_freq = devfreq->scaling_max_freq;
 
 	dev_set_name(&devfreq->dev, "devfreq%d",
 				atomic_inc_return(&devfreq_no));
 	err = device_register(&devfreq->dev);
 	if (err) {
 		mutex_unlock(&devfreq->lock);
-		goto err_dev;
+		put_device(&devfreq->dev);
+		goto err_out;
 	}
 
 	devfreq->trans_table =
@@ -672,6 +673,7 @@ err_init:
 	mutex_unlock(&devfreq_list_lock);
 
 	device_unregister(&devfreq->dev);
+	devfreq = NULL;
 err_dev:
 	if (devfreq)
 		kfree(devfreq);
diff --git a/drivers/devfreq/event/exynos-ppmu.c b/drivers/devfreq/event/exynos-ppmu.c
index 3cd6a184fe7c..a9c64f0d3284 100644
--- a/drivers/devfreq/event/exynos-ppmu.c
+++ b/drivers/devfreq/event/exynos-ppmu.c
@@ -627,11 +627,9 @@ static int exynos_ppmu_probe(struct platform_device *pdev)
 
 	size = sizeof(struct devfreq_event_dev *) * info->num_events;
 	info->edev = devm_kzalloc(&pdev->dev, size, GFP_KERNEL);
-	if (!info->edev) {
-		dev_err(&pdev->dev,
-			"failed to allocate memory devfreq-event devices\n");
+	if (!info->edev)
 		return -ENOMEM;
-	}
+
 	edev = info->edev;
 	platform_set_drvdata(pdev, info);
 
diff --git a/drivers/devfreq/rk3399_dmc.c b/drivers/devfreq/rk3399_dmc.c
index 5dfbfa3cc878..e795ad2b3f6b 100644
--- a/drivers/devfreq/rk3399_dmc.c
+++ b/drivers/devfreq/rk3399_dmc.c
@@ -68,15 +68,6 @@ struct rk3399_dmcfreq {
 	struct devfreq_event_dev *edev;
 	struct mutex lock;
 	struct dram_timing timing;
-
-	/*
-	 * DDR Converser of Frequency (DCF) is used to implement DDR frequency
-	 * conversion without the participation of CPU, we will implement and
-	 * control it in arm trust firmware.
-	 */
-	wait_queue_head_t	wait_dcf_queue;
-	int irq;
-	int wait_dcf_flag;
 	struct regulator *vdd_center;
 	unsigned long rate, target_rate;
 	unsigned long volt, target_volt;
@@ -112,31 +103,22 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
 		err = regulator_set_voltage(dmcfreq->vdd_center, target_volt,
 					    target_volt);
 		if (err) {
-			dev_err(dev, "Cannot to set voltage %lu uV\n",
+			dev_err(dev, "Cannot set voltage %lu uV\n",
 				target_volt);
 			goto out;
 		}
 	}
-	dmcfreq->wait_dcf_flag = 1;
 
 	err = clk_set_rate(dmcfreq->dmc_clk, target_rate);
 	if (err) {
-		dev_err(dev, "Cannot to set frequency %lu (%d)\n",
-			target_rate, err);
+		dev_err(dev, "Cannot set frequency %lu (%d)\n", target_rate,
+			err);
 		regulator_set_voltage(dmcfreq->vdd_center, dmcfreq->volt,
 				      dmcfreq->volt);
 		goto out;
 	}
 
 	/*
-	 * Wait until bcf irq happen, it means freq scaling finish in
-	 * arm trust firmware, use 100ms as timeout time.
-	 */
-	if (!wait_event_timeout(dmcfreq->wait_dcf_queue,
-				!dmcfreq->wait_dcf_flag, HZ / 10))
-		dev_warn(dev, "Timeout waiting for dcf interrupt\n");
-
-	/*
 	 * Check the dpll rate,
 	 * There only two result we will get,
 	 * 1. Ddr frequency scaling fail, we still get the old rate.
@@ -146,8 +128,8 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
 
 	/* If get the incorrect rate, set voltage to old value. */
 	if (dmcfreq->rate != target_rate) {
-		dev_err(dev, "Get wrong ddr frequency, Request frequency %lu,\
-			Current frequency %lu\n", target_rate, dmcfreq->rate);
+		dev_err(dev, "Got wrong frequency, Request %lu, Current %lu\n",
+			target_rate, dmcfreq->rate);
 		regulator_set_voltage(dmcfreq->vdd_center, dmcfreq->volt,
 				      dmcfreq->volt);
 		goto out;
@@ -155,7 +137,7 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
 		err = regulator_set_voltage(dmcfreq->vdd_center, target_volt,
 					    target_volt);
 	if (err)
-		dev_err(dev, "Cannot to set vol %lu uV\n", target_volt);
+		dev_err(dev, "Cannot set voltage %lu uV\n", target_volt);
 
 	dmcfreq->rate = target_rate;
 	dmcfreq->volt = target_volt;
@@ -241,22 +223,6 @@ static __maybe_unused int rk3399_dmcfreq_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(rk3399_dmcfreq_pm, rk3399_dmcfreq_suspend,
 			 rk3399_dmcfreq_resume);
 
-static irqreturn_t rk3399_dmc_irq(int irq, void *dev_id)
-{
-	struct rk3399_dmcfreq *dmcfreq = dev_id;
-	struct arm_smccc_res res;
-
-	dmcfreq->wait_dcf_flag = 0;
-	wake_up(&dmcfreq->wait_dcf_queue);
-
-	/* Clear the DCF interrupt */
-	arm_smccc_smc(ROCKCHIP_SIP_DRAM_FREQ, 0, 0,
-		      ROCKCHIP_SIP_CONFIG_DRAM_CLR_IRQ,
-		      0, 0, 0, 0, &res);
-
-	return IRQ_HANDLED;
-}
-
 static int of_get_ddr_timings(struct dram_timing *timing,
 			      struct device_node *np)
 {
@@ -330,16 +296,10 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct device_node *np = pdev->dev.of_node;
 	struct rk3399_dmcfreq *data;
-	int ret, irq, index, size;
+	int ret, index, size;
 	uint32_t *timing;
 	struct dev_pm_opp *opp;
 
-	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(&pdev->dev,
-			"Cannot get the dmc interrupt resource: %d\n", irq);
-		return irq;
-	}
 	data = devm_kzalloc(dev, sizeof(struct rk3399_dmcfreq), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
@@ -348,27 +308,22 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 
 	data->vdd_center = devm_regulator_get(dev, "center");
 	if (IS_ERR(data->vdd_center)) {
+		if (PTR_ERR(data->vdd_center) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+
 		dev_err(dev, "Cannot get the regulator \"center\"\n");
 		return PTR_ERR(data->vdd_center);
 	}
 
 	data->dmc_clk = devm_clk_get(dev, "dmc_clk");
 	if (IS_ERR(data->dmc_clk)) {
+		if (PTR_ERR(data->dmc_clk) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+
 		dev_err(dev, "Cannot get the clk dmc_clk\n");
 		return PTR_ERR(data->dmc_clk);
 	};
 
-	data->irq = irq;
-	ret = devm_request_irq(dev, irq, rk3399_dmc_irq, 0,
-			       dev_name(dev), data);
-	if (ret) {
-		dev_err(dev, "Failed to request dmc irq: %d\n", ret);
-		return ret;
-	}
-
-	init_waitqueue_head(&data->wait_dcf_queue);
-	data->wait_dcf_flag = 0;
-
 	data->edev = devfreq_event_get_edev_by_phandle(dev, 0);
 	if (IS_ERR(data->edev))
 		return -EPROBE_DEFER;
@@ -420,8 +375,10 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 	data->rate = clk_get_rate(data->dmc_clk);
 
 	opp = devfreq_recommended_opp(dev, &data->rate, 0);
-	if (IS_ERR(opp))
-		return PTR_ERR(opp);
+	if (IS_ERR(opp)) {
+		ret = PTR_ERR(opp);
+		goto err_free_opp;
+	}
 
 	data->rate = dev_pm_opp_get_freq(opp);
 	data->volt = dev_pm_opp_get_voltage(opp);
@@ -433,14 +390,34 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 					   &rk3399_devfreq_dmc_profile,
 					   DEVFREQ_GOV_SIMPLE_ONDEMAND,
 					   &data->ondemand_data);
-	if (IS_ERR(data->devfreq))
-		return PTR_ERR(data->devfreq);
+	if (IS_ERR(data->devfreq)) {
+		ret = PTR_ERR(data->devfreq);
+		goto err_free_opp;
+	}
+
 	devm_devfreq_register_opp_notifier(dev, data->devfreq);
 
 	data->dev = dev;
 	platform_set_drvdata(pdev, data);
 
 	return 0;
+
+err_free_opp:
+	dev_pm_opp_of_remove_table(&pdev->dev);
+	return ret;
+}
+
+static int rk3399_dmcfreq_remove(struct platform_device *pdev)
+{
+	struct rk3399_dmcfreq *dmcfreq = dev_get_drvdata(&pdev->dev);
+
+	/*
+	 * Before remove the opp table we need to unregister the opp notifier.
+	 */
+	devm_devfreq_unregister_opp_notifier(dmcfreq->dev, dmcfreq->devfreq);
+	dev_pm_opp_of_remove_table(dmcfreq->dev);
+
+	return 0;
 }
 
 static const struct of_device_id rk3399dmc_devfreq_of_match[] = {
@@ -451,6 +428,7 @@ MODULE_DEVICE_TABLE(of, rk3399dmc_devfreq_of_match);
 
 static struct platform_driver rk3399_dmcfreq_driver = {
 	.probe	= rk3399_dmcfreq_probe,
+	.remove = rk3399_dmcfreq_remove,
 	.driver = {
 		.name	= "rk3399-dmc-freq",
 		.pm	= &rk3399_dmcfreq_pm,
diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c
index c3afe7b2237e..965088afcfad 100644
--- a/drivers/gpu/drm/tegra/dc.c
+++ b/drivers/gpu/drm/tegra/dc.c
@@ -2312,7 +2312,7 @@ static int tegra_dc_couple(struct tegra_dc *dc)
 	 * POWER_CONTROL registers during CRTC enabling.
 	 */
 	if (dc->soc->coupled_pm && dc->pipe == 1) {
-		u32 flags = DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE;
+		u32 flags = DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_CONSUMER;
 		struct device_link *link;
 		struct device *partner;
 
diff --git a/drivers/gpu/ipu-v3/ipu-pre.c b/drivers/gpu/ipu-v3/ipu-pre.c
index 0f70e8847540..2f8db9d62551 100644
--- a/drivers/gpu/ipu-v3/ipu-pre.c
+++ b/drivers/gpu/ipu-v3/ipu-pre.c
@@ -128,7 +128,8 @@ ipu_pre_lookup_by_phandle(struct device *dev, const char *name, int index)
 	list_for_each_entry(pre, &ipu_pre_list, list) {
 		if (pre_node == pre->dev->of_node) {
 			mutex_unlock(&ipu_pre_list_mutex);
-			device_link_add(dev, pre->dev, DL_FLAG_AUTOREMOVE);
+			device_link_add(dev, pre->dev,
+					DL_FLAG_AUTOREMOVE_CONSUMER);
 			of_node_put(pre_node);
 			return pre;
 		}
diff --git a/drivers/gpu/ipu-v3/ipu-prg.c b/drivers/gpu/ipu-v3/ipu-prg.c
index 83f9dd934a5d..38a3a9764e49 100644
--- a/drivers/gpu/ipu-v3/ipu-prg.c
+++ b/drivers/gpu/ipu-v3/ipu-prg.c
@@ -100,7 +100,8 @@ ipu_prg_lookup_by_phandle(struct device *dev, const char *name, int ipu_id)
 	list_for_each_entry(prg, &ipu_prg_list, list) {
 		if (prg_node == prg->dev->of_node) {
 			mutex_unlock(&ipu_prg_list_mutex);
-			device_link_add(dev, prg->dev, DL_FLAG_AUTOREMOVE);
+			device_link_add(dev, prg->dev,
+					DL_FLAG_AUTOREMOVE_CONSUMER);
 			prg->id = ipu_id;
 			of_node_put(prg_node);
 			return prg;
diff --git a/drivers/powercap/Kconfig b/drivers/powercap/Kconfig
index 85727ef6ce8e..6ac27e5908f5 100644
--- a/drivers/powercap/Kconfig
+++ b/drivers/powercap/Kconfig
@@ -29,4 +29,14 @@ config INTEL_RAPL
 	  controller, CPU core (Power Plance 0), graphics uncore (Power Plane
 	  1), etc.
 
+config IDLE_INJECT
+	bool "Idle injection framework"
+	depends on CPU_IDLE
+	default n
+	help
+	  This enables support for the idle injection framework. It
+	  provides a way to force idle periods on a set of specified
+	  CPUs for power capping. Idle period can be injected
+	  synchronously on a set of specified CPUs or alternatively
+	  on a per CPU basis.
 endif
diff --git a/drivers/powercap/Makefile b/drivers/powercap/Makefile
index 0a21ef31372b..1b328854b36e 100644
--- a/drivers/powercap/Makefile
+++ b/drivers/powercap/Makefile
@@ -1,2 +1,3 @@
 obj-$(CONFIG_POWERCAP)	+= powercap_sys.o
 obj-$(CONFIG_INTEL_RAPL) += intel_rapl.o
+obj-$(CONFIG_IDLE_INJECT) += idle_inject.o
diff --git a/drivers/powercap/idle_inject.c b/drivers/powercap/idle_inject.c
new file mode 100644
index 000000000000..24ff2a068978
--- /dev/null
+++ b/drivers/powercap/idle_inject.c
@@ -0,0 +1,356 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2018 Linaro Limited
+ *
+ * Author: Daniel Lezcano <daniel.lezcano@linaro.org>
+ *
+ * The idle injection framework provides a way to force CPUs to enter idle
+ * states for a specified fraction of time over a specified period.
+ *
+ * It relies on the smpboot kthreads feature providing common code for CPU
+ * hotplug and thread [un]parking.
+ *
+ * All of the kthreads used for idle injection are created at init time.
+ *
+ * Next, the users of the the idle injection framework provide a cpumask via
+ * its register function. The kthreads will be synchronized with respect to
+ * this cpumask.
+ *
+ * The idle + run duration is specified via separate helpers and that allows
+ * idle injection to be started.
+ *
+ * The idle injection kthreads will call play_idle() with the idle duration
+ * specified as per the above.
+ *
+ * After all of them have been woken up, a timer is set to start the next idle
+ * injection cycle.
+ *
+ * The timer interrupt handler will wake up the idle injection kthreads for
+ * all of the CPUs in the cpumask provided by the user.
+ *
+ * Idle injection is stopped synchronously and no leftover idle injection
+ * kthread activity after its completion is guaranteed.
+ *
+ * It is up to the user of this framework to provide a lock for higher-level
+ * synchronization to prevent race conditions like starting idle injection
+ * while unregistering from the framework.
+ */
+#define pr_fmt(fmt) "ii_dev: " fmt
+
+#include <linux/cpu.h>
+#include <linux/hrtimer.h>
+#include <linux/kthread.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/smpboot.h>
+
+#include <uapi/linux/sched/types.h>
+
+/**
+ * struct idle_inject_thread - task on/off switch structure
+ * @tsk: task injecting the idle cycles
+ * @should_run: whether or not to run the task (for the smpboot kthread API)
+ */
+struct idle_inject_thread {
+	struct task_struct *tsk;
+	int should_run;
+};
+
+/**
+ * struct idle_inject_device - idle injection data
+ * @timer: idle injection period timer
+ * @idle_duration_ms: duration of CPU idle time to inject
+ * @run_duration_ms: duration of CPU run time to allow
+ * @cpumask: mask of CPUs affected by idle injection
+ */
+struct idle_inject_device {
+	struct hrtimer timer;
+	unsigned int idle_duration_ms;
+	unsigned int run_duration_ms;
+	unsigned long int cpumask[0];
+};
+
+static DEFINE_PER_CPU(struct idle_inject_thread, idle_inject_thread);
+static DEFINE_PER_CPU(struct idle_inject_device *, idle_inject_device);
+
+/**
+ * idle_inject_wakeup - Wake up idle injection threads
+ * @ii_dev: target idle injection device
+ *
+ * Every idle injection task associated with the given idle injection device
+ * and running on an online CPU will be woken up.
+ */
+static void idle_inject_wakeup(struct idle_inject_device *ii_dev)
+{
+	struct idle_inject_thread *iit;
+	unsigned int cpu;
+
+	for_each_cpu_and(cpu, to_cpumask(ii_dev->cpumask), cpu_online_mask) {
+		iit = per_cpu_ptr(&idle_inject_thread, cpu);
+		iit->should_run = 1;
+		wake_up_process(iit->tsk);
+	}
+}
+
+/**
+ * idle_inject_timer_fn - idle injection timer function
+ * @timer: idle injection hrtimer
+ *
+ * This function is called when the idle injection timer expires.  It wakes up
+ * idle injection tasks associated with the timer and they, in turn, invoke
+ * play_idle() to inject a specified amount of CPU idle time.
+ *
+ * Return: HRTIMER_RESTART.
+ */
+static enum hrtimer_restart idle_inject_timer_fn(struct hrtimer *timer)
+{
+	unsigned int duration_ms;
+	struct idle_inject_device *ii_dev =
+		container_of(timer, struct idle_inject_device, timer);
+
+	duration_ms = READ_ONCE(ii_dev->run_duration_ms);
+	duration_ms += READ_ONCE(ii_dev->idle_duration_ms);
+
+	idle_inject_wakeup(ii_dev);
+
+	hrtimer_forward_now(timer, ms_to_ktime(duration_ms));
+
+	return HRTIMER_RESTART;
+}
+
+/**
+ * idle_inject_fn - idle injection work function
+ * @cpu: the CPU owning the task
+ *
+ * This function calls play_idle() to inject a specified amount of CPU idle
+ * time.
+ */
+static void idle_inject_fn(unsigned int cpu)
+{
+	struct idle_inject_device *ii_dev;
+	struct idle_inject_thread *iit;
+
+	ii_dev = per_cpu(idle_inject_device, cpu);
+	iit = per_cpu_ptr(&idle_inject_thread, cpu);
+
+	/*
+	 * Let the smpboot main loop know that the task should not run again.
+	 */
+	iit->should_run = 0;
+
+	play_idle(READ_ONCE(ii_dev->idle_duration_ms));
+}
+
+/**
+ * idle_inject_set_duration - idle and run duration update helper
+ * @run_duration_ms: CPU run time to allow in milliseconds
+ * @idle_duration_ms: CPU idle time to inject in milliseconds
+ */
+void idle_inject_set_duration(struct idle_inject_device *ii_dev,
+			      unsigned int run_duration_ms,
+			      unsigned int idle_duration_ms)
+{
+	if (run_duration_ms && idle_duration_ms) {
+		WRITE_ONCE(ii_dev->run_duration_ms, run_duration_ms);
+		WRITE_ONCE(ii_dev->idle_duration_ms, idle_duration_ms);
+	}
+}
+
+/**
+ * idle_inject_get_duration - idle and run duration retrieval helper
+ * @run_duration_ms: memory location to store the current CPU run time
+ * @idle_duration_ms: memory location to store the current CPU idle time
+ */
+void idle_inject_get_duration(struct idle_inject_device *ii_dev,
+			      unsigned int *run_duration_ms,
+			      unsigned int *idle_duration_ms)
+{
+	*run_duration_ms = READ_ONCE(ii_dev->run_duration_ms);
+	*idle_duration_ms = READ_ONCE(ii_dev->idle_duration_ms);
+}
+
+/**
+ * idle_inject_start - start idle injections
+ * @ii_dev: idle injection control device structure
+ *
+ * The function starts idle injection by first waking up all of the idle
+ * injection kthreads associated with @ii_dev to let them inject CPU idle time
+ * sets up a timer to start the next idle injection period.
+ *
+ * Return: -EINVAL if the CPU idle or CPU run time is not set or 0 on success.
+ */
+int idle_inject_start(struct idle_inject_device *ii_dev)
+{
+	unsigned int idle_duration_ms = READ_ONCE(ii_dev->idle_duration_ms);
+	unsigned int run_duration_ms = READ_ONCE(ii_dev->run_duration_ms);
+
+	if (!idle_duration_ms || !run_duration_ms)
+		return -EINVAL;
+
+	pr_debug("Starting injecting idle cycles on CPUs '%*pbl'\n",
+		 cpumask_pr_args(to_cpumask(ii_dev->cpumask)));
+
+	idle_inject_wakeup(ii_dev);
+
+	hrtimer_start(&ii_dev->timer,
+		      ms_to_ktime(idle_duration_ms + run_duration_ms),
+		      HRTIMER_MODE_REL);
+
+	return 0;
+}
+
+/**
+ * idle_inject_stop - stops idle injections
+ * @ii_dev: idle injection control device structure
+ *
+ * The function stops idle injection and waits for the threads to finish work.
+ * If CPU idle time is being injected when this function runs, then it will
+ * wait until the end of the cycle.
+ *
+ * When it returns, there is no more idle injection kthread activity.  The
+ * kthreads are scheduled out and the periodic timer is off.
+ */
+void idle_inject_stop(struct idle_inject_device *ii_dev)
+{
+	struct idle_inject_thread *iit;
+	unsigned int cpu;
+
+	pr_debug("Stopping idle injection on CPUs '%*pbl'\n",
+		 cpumask_pr_args(to_cpumask(ii_dev->cpumask)));
+
+	hrtimer_cancel(&ii_dev->timer);
+
+	/*
+	 * Stopping idle injection requires all of the idle injection kthreads
+	 * associated with the given cpumask to be parked and stay that way, so
+	 * prevent CPUs from going online at this point.  Any CPUs going online
+	 * after the loop below will be covered by clearing the should_run flag
+	 * that will cause the smpboot main loop to schedule them out.
+	 */
+	cpu_hotplug_disable();
+
+	/*
+	 * Iterate over all (online + offline) CPUs here in case one of them
+	 * goes offline with the should_run flag set so as to prevent its idle
+	 * injection kthread from running when the CPU goes online again after
+	 * the ii_dev has been freed.
+	 */
+	for_each_cpu(cpu, to_cpumask(ii_dev->cpumask)) {
+		iit = per_cpu_ptr(&idle_inject_thread, cpu);
+		iit->should_run = 0;
+
+		wait_task_inactive(iit->tsk, 0);
+	}
+
+	cpu_hotplug_enable();
+}
+
+/**
+ * idle_inject_setup - prepare the current task for idle injection
+ * @cpu: not used
+ *
+ * Called once, this function is in charge of setting the current task's
+ * scheduler parameters to make it an RT task.
+ */
+static void idle_inject_setup(unsigned int cpu)
+{
+	struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO / 2 };
+
+	sched_setscheduler(current, SCHED_FIFO, &param);
+}
+
+/**
+ * idle_inject_should_run - function helper for the smpboot API
+ * @cpu: CPU the kthread is running on
+ *
+ * Return: whether or not the thread can run.
+ */
+static int idle_inject_should_run(unsigned int cpu)
+{
+	struct idle_inject_thread *iit =
+		per_cpu_ptr(&idle_inject_thread, cpu);
+
+	return iit->should_run;
+}
+
+/**
+ * idle_inject_register - initialize idle injection on a set of CPUs
+ * @cpumask: CPUs to be affected by idle injection
+ *
+ * This function creates an idle injection control device structure for the
+ * given set of CPUs and initializes the timer associated with it.  It does not
+ * start any injection cycles.
+ *
+ * Return: NULL if memory allocation fails, idle injection control device
+ * pointer on success.
+ */
+struct idle_inject_device *idle_inject_register(struct cpumask *cpumask)
+{
+	struct idle_inject_device *ii_dev;
+	int cpu, cpu_rb;
+
+	ii_dev = kzalloc(sizeof(*ii_dev) + cpumask_size(), GFP_KERNEL);
+	if (!ii_dev)
+		return NULL;
+
+	cpumask_copy(to_cpumask(ii_dev->cpumask), cpumask);
+	hrtimer_init(&ii_dev->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	ii_dev->timer.function = idle_inject_timer_fn;
+
+	for_each_cpu(cpu, to_cpumask(ii_dev->cpumask)) {
+
+		if (per_cpu(idle_inject_device, cpu)) {
+			pr_err("cpu%d is already registered\n", cpu);
+			goto out_rollback;
+		}
+
+		per_cpu(idle_inject_device, cpu) = ii_dev;
+	}
+
+	return ii_dev;
+
+out_rollback:
+	for_each_cpu(cpu_rb, to_cpumask(ii_dev->cpumask)) {
+		if (cpu == cpu_rb)
+			break;
+		per_cpu(idle_inject_device, cpu_rb) = NULL;
+	}
+
+	kfree(ii_dev);
+
+	return NULL;
+}
+
+/**
+ * idle_inject_unregister - unregister idle injection control device
+ * @ii_dev: idle injection control device to unregister
+ *
+ * The function stops idle injection for the given control device,
+ * unregisters its kthreads and frees memory allocated when that device was
+ * created.
+ */
+void idle_inject_unregister(struct idle_inject_device *ii_dev)
+{
+	unsigned int cpu;
+
+	idle_inject_stop(ii_dev);
+
+	for_each_cpu(cpu, to_cpumask(ii_dev->cpumask))
+		per_cpu(idle_inject_device, cpu) = NULL;
+
+	kfree(ii_dev);
+}
+
+static struct smp_hotplug_thread idle_inject_threads = {
+	.store = &idle_inject_thread.tsk,
+	.setup = idle_inject_setup,
+	.thread_fn = idle_inject_fn,
+	.thread_comm = "idle_inject/%u",
+	.thread_should_run = idle_inject_should_run,
+};
+
+static int __init idle_inject_init(void)
+{
+	return smpboot_register_percpu_thread(&idle_inject_threads);
+}
+early_initcall(idle_inject_init);
diff --git a/drivers/soc/imx/gpc.c b/drivers/soc/imx/gpc.c
index 0097a939487f..546960a18d60 100644
--- a/drivers/soc/imx/gpc.c
+++ b/drivers/soc/imx/gpc.c
@@ -209,7 +209,7 @@ static int imx_pgc_power_domain_probe(struct platform_device *pdev)
 			goto genpd_err;
 	}
 
-	device_link_add(dev, dev->parent, DL_FLAG_AUTOREMOVE);
+	device_link_add(dev, dev->parent, DL_FLAG_AUTOREMOVE_CONSUMER);
 
 	return 0;
 
diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c
index 334d98be03b9..cbfcca828cd7 100644
--- a/drivers/thermal/imx_thermal.c
+++ b/drivers/thermal/imx_thermal.c
@@ -3,6 +3,7 @@
 // Copyright 2013 Freescale Semiconductor, Inc.
 
 #include <linux/clk.h>
+#include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/cpu_cooling.h>
 #include <linux/delay.h>
@@ -644,6 +645,27 @@ static const struct of_device_id of_imx_thermal_match[] = {
 };
 MODULE_DEVICE_TABLE(of, of_imx_thermal_match);
 
+/*
+ * Create cooling device in case no #cooling-cells property is available in
+ * CPU node
+ */
+static int imx_thermal_register_legacy_cooling(struct imx_thermal_data *data)
+{
+	struct device_node *np = of_get_cpu_node(data->policy->cpu, NULL);
+	int ret;
+
+	if (!np || !of_find_property(np, "#cooling-cells", NULL)) {
+		data->cdev = cpufreq_cooling_register(data->policy);
+		if (IS_ERR(data->cdev)) {
+			ret = PTR_ERR(data->cdev);
+			cpufreq_cpu_put(data->policy);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
 static int imx_thermal_probe(struct platform_device *pdev)
 {
 	struct imx_thermal_data *data;
@@ -724,12 +746,10 @@ static int imx_thermal_probe(struct platform_device *pdev)
 		return -EPROBE_DEFER;
 	}
 
-	data->cdev = cpufreq_cooling_register(data->policy);
-	if (IS_ERR(data->cdev)) {
-		ret = PTR_ERR(data->cdev);
+	ret = imx_thermal_register_legacy_cooling(data);
+	if (ret) {
 		dev_err(&pdev->dev,
 			"failed to register cpufreq cooling device: %d\n", ret);
-		cpufreq_cpu_put(data->policy);
 		return ret;
 	}