Merge tag 'pm-5.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These add some new hardware support (for example, IceLake-D idle
  states in intel_idle), fix some issues (for example, the handling of
  negative "sleep length" values in cpuidle governors), add new
  functionality to the existing drivers (for example, scale-invariance
  support in the ACPI CPPC cpufreq driver) and clean up code all over.

  Specifics:

   - Add idle states table for IceLake-D to the intel_idle driver and
     update IceLake-X C6 data in it (Artem Bityutskiy).

   - Fix the C7 idle state on Tegra114 in the tegra cpuidle driver and
     drop the unused do_idle() firmware call from it (Dmitry Osipenko).

   - Fix cpuidle-qcom-spm Kconfig entry (He Ying).

   - Fix handling of possible negative tick_nohz_get_next_hrtimer()
     return values of in cpuidle governors (Rafael Wysocki).

   - Add support for frequency-invariance to the ACPI CPPC cpufreq
     driver and update the frequency-invariance engine (FIE) to use it
     as needed (Viresh Kumar).

   - Simplify the default delay_us setting in the ACPI CPPC cpufreq
     driver (Tom Saeger).

   - Clean up frequency-related computations in the intel_pstate cpufreq
     driver (Rafael Wysocki).

   - Fix TBG parent setting for load levels in the armada-37xx cpufreq
     driver and drop the CPU PM clock .set_parent method for armada-37xx
     (Marek Behún).

   - Fix multiple issues in the armada-37xx cpufreq driver (Pali Rohár).

   - Fix handling of dev_pm_opp_of_cpumask_add_table() return values in
     cpufreq-dt to take the -EPROBE_DEFER one into acconut as
     appropriate (Quanyang Wang).

   - Fix format string in ia64-acpi-cpufreq (Sergei Trofimovich).

   - Drop the unused for_each_policy() macro from cpufreq (Shaokun
     Zhang).

   - Simplify computations in the schedutil cpufreq governor to avoid
     unnecessary overhead (Yue Hu).

   - Fix typos in the s5pv210 cpufreq driver (Bhaskar Chowdhury).

   - Fix cpufreq documentation links in Kconfig (Alexander Monakov).

   - Fix PCI device power state handling in pci_enable_device_flags() to
     avoid issuse in some cases when the device depends on an ACPI power
     resource (Rafael Wysocki).

   - Add missing documentation of pm_runtime_resume_and_get() (Alan
     Stern).

   - Add missing static inline stub for pm_runtime_has_no_callbacks() to
     pm_runtime.h and drop the unused try_to_freeze_nowarn() definition
     (YueHaibing).

   - Drop duplicate struct device declaration from pm.h and fix a
     structure type declaration in intel_rapl.h (Wan Jiabing).

   - Use dev_set_name() instead of an open-coded equivalent of it in the
     wakeup sources code and drop a redundant local variable
     initialization from it (Andy Shevchenko, Colin Ian King).

   - Use crc32 instead of md5 for e820 memory map integrity check during
     resume from hibernation on x86 (Chris von Recklinghausen).

   - Fix typos in comments in the system-wide and hibernation support
     code (Lu Jialin).

   - Modify the generic power domains (genpd) code to avoid resuming
     devices in the "prepare" phase of system-wide suspend and
     hibernation (Ulf Hansson).

   - Add Hygon Fam18h RAPL support to the intel_rapl power capping
     driver (Pu Wen).

   - Add MAINTAINERS entry for the dynamic thermal power management
     (DTPM) code (Daniel Lezcano).

   - Add devm variants of operating performance points (OPP) API
     functions and switch over some users of the OPP framework to the
     new resource-managed API (Yangtao Li and Dmitry Osipenko).

   - Update devfreq core:

      * Register devfreq devices as cooling devices on demand (Daniel
        Lezcano).

      * Add missing unlock opeation in devfreq_add_device() (Lukasz
        Luba).

      * Use the next frequency as resume_freq instead of the previous
        frequency when using the opp-suspend property (Dong Aisheng).

      * Check get_dev_status in devfreq_update_stats() (Dong Aisheng).

      * Fix set_freq path for the userspace governor in Kconfig (Dong
        Aisheng).

      * Remove invalid description of get_target_freq() (Dong Aisheng).

   - Update devfreq drivers:

      * imx8m-ddrc: Remove imx8m_ddrc_get_dev_status() and unneeded
        of_match_ptr() (Dong Aisheng, Fabio Estevam).

      * rk3399_dmc: dt-bindings: Add rockchip,pmu phandle and drop
        references to undefined symbols (Enric Balletbo i Serra, Gaël
        PORTAY).

      * rk3399_dmc: Use dev_err_probe() to simplify the code (Krzysztof
        Kozlowski).

      * imx-bus: Remove unneeded of_match_ptr() (Fabio Estevam).

   - Fix kernel-doc warnings in three places (Pierre-Louis Bossart).

   - Fix typo in the pm-graph utility code (Ricardo Ribalda)"

* tag 'pm-5.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (74 commits)
  PM: wakeup: remove redundant assignment to variable retval
  PM: hibernate: x86: Use crc32 instead of md5 for hibernation e820 integrity check
  cpufreq: Kconfig: fix documentation links
  PM: wakeup: use dev_set_name() directly
  PM: runtime: Add documentation for pm_runtime_resume_and_get()
  cpufreq: intel_pstate: Simplify intel_pstate_update_perf_limits()
  cpufreq: armada-37xx: Fix module unloading
  cpufreq: armada-37xx: Remove cur_frequency variable
  cpufreq: armada-37xx: Fix determining base CPU frequency
  cpufreq: armada-37xx: Fix driver cleanup when registration failed
  clk: mvebu: armada-37xx-periph: Fix workaround for switching from L1 to L0
  clk: mvebu: armada-37xx-periph: Fix switching CPU freq from 250 Mhz to 1 GHz
  cpufreq: armada-37xx: Fix the AVS value for load L1
  clk: mvebu: armada-37xx-periph: remove .set_parent method for CPU PM clock
  cpufreq: armada-37xx: Fix setting TBG parent for load levels
  cpuidle: Fix ARM_QCOM_SPM_CPUIDLE configuration
  cpuidle: tegra: Remove do_idle firmware call
  cpuidle: tegra: Fix C7 idling state on Tegra114
  PM: sleep: fix typos in comments
  cpufreq: Remove unused for_each_policy macro
  ...

42 files changed, 801 insertions, 484 deletions

diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index de8587cc119e..c1179edc0f3b 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -21,17 +21,94 @@
 #include <linux/sched.h>
 #include <linux/smp.h>
 
+static DEFINE_PER_CPU(struct scale_freq_data *, sft_data);
+static struct cpumask scale_freq_counters_mask;
+static bool scale_freq_invariant;
+
+static bool supports_scale_freq_counters(const struct cpumask *cpus)
+{
+	return cpumask_subset(cpus, &scale_freq_counters_mask);
+}
+
 bool topology_scale_freq_invariant(void)
 {
 	return cpufreq_supports_freq_invariance() ||
-	       arch_freq_counters_available(cpu_online_mask);
+	       supports_scale_freq_counters(cpu_online_mask);
 }
 
-__weak bool arch_freq_counters_available(const struct cpumask *cpus)
+static void update_scale_freq_invariant(bool status)
 {
-	return false;
+	if (scale_freq_invariant == status)
+		return;
+
+	/*
+	 * Task scheduler behavior depends on frequency invariance support,
+	 * either cpufreq or counter driven. If the support status changes as
+	 * a result of counter initialisation and use, retrigger the build of
+	 * scheduling domains to ensure the information is propagated properly.
+	 */
+	if (topology_scale_freq_invariant() == status) {
+		scale_freq_invariant = status;
+		rebuild_sched_domains_energy();
+	}
 }
-DEFINE_PER_CPU(unsigned long, freq_scale) = SCHED_CAPACITY_SCALE;
+
+void topology_set_scale_freq_source(struct scale_freq_data *data,
+				    const struct cpumask *cpus)
+{
+	struct scale_freq_data *sfd;
+	int cpu;
+
+	/*
+	 * Avoid calling rebuild_sched_domains() unnecessarily if FIE is
+	 * supported by cpufreq.
+	 */
+	if (cpumask_empty(&scale_freq_counters_mask))
+		scale_freq_invariant = topology_scale_freq_invariant();
+
+	for_each_cpu(cpu, cpus) {
+		sfd = per_cpu(sft_data, cpu);
+
+		/* Use ARCH provided counters whenever possible */
+		if (!sfd || sfd->source != SCALE_FREQ_SOURCE_ARCH) {
+			per_cpu(sft_data, cpu) = data;
+			cpumask_set_cpu(cpu, &scale_freq_counters_mask);
+		}
+	}
+
+	update_scale_freq_invariant(true);
+}
+EXPORT_SYMBOL_GPL(topology_set_scale_freq_source);
+
+void topology_clear_scale_freq_source(enum scale_freq_source source,
+				      const struct cpumask *cpus)
+{
+	struct scale_freq_data *sfd;
+	int cpu;
+
+	for_each_cpu(cpu, cpus) {
+		sfd = per_cpu(sft_data, cpu);
+
+		if (sfd && sfd->source == source) {
+			per_cpu(sft_data, cpu) = NULL;
+			cpumask_clear_cpu(cpu, &scale_freq_counters_mask);
+		}
+	}
+
+	update_scale_freq_invariant(false);
+}
+EXPORT_SYMBOL_GPL(topology_clear_scale_freq_source);
+
+void topology_scale_freq_tick(void)
+{
+	struct scale_freq_data *sfd = *this_cpu_ptr(&sft_data);
+
+	if (sfd)
+		sfd->set_freq_scale();
+}
+
+DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE;
+EXPORT_PER_CPU_SYMBOL_GPL(arch_freq_scale);
 
 void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq,
 			     unsigned long max_freq)
@@ -47,13 +124,13 @@ void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq,
 	 * want to update the scale factor with information from CPUFREQ.
 	 * Instead the scale factor will be updated from arch_scale_freq_tick.
 	 */
-	if (arch_freq_counters_available(cpus))
+	if (supports_scale_freq_counters(cpus))
 		return;
 
 	scale = (cur_freq << SCHED_CAPACITY_SHIFT) / max_freq;
 
 	for_each_cpu(i, cpus)
-		per_cpu(freq_scale, i) = scale;
+		per_cpu(arch_freq_scale, i) = scale;
 }
 
 DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE;
diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
index 84d5acb6301b..0251f3e6e61d 100644
--- a/drivers/base/power/clock_ops.c
+++ b/drivers/base/power/clock_ops.c
@@ -140,7 +140,7 @@ static void pm_clk_op_unlock(struct pm_subsys_data *psd, unsigned long *flags)
 }
 
 /**
- * pm_clk_enable - Enable a clock, reporting any errors
+ * __pm_clk_enable - Enable a clock, reporting any errors
  * @dev: The device for the given clock
  * @ce: PM clock entry corresponding to the clock.
  */
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 78c310d3179d..b6a782c31613 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -1088,34 +1088,6 @@ static void genpd_sync_power_on(struct generic_pm_domain *genpd, bool use_lock,
 }
 
 /**
- * resume_needed - Check whether to resume a device before system suspend.
- * @dev: Device to check.
- * @genpd: PM domain the device belongs to.
- *
- * There are two cases in which a device that can wake up the system from sleep
- * states should be resumed by genpd_prepare(): (1) if the device is enabled
- * to wake up the system and it has to remain active for this purpose while the
- * system is in the sleep state and (2) if the device is not enabled to wake up
- * the system from sleep states and it generally doesn't generate wakeup signals
- * by itself (those signals are generated on its behalf by other parts of the
- * system).  In the latter case it may be necessary to reconfigure the device's
- * wakeup settings during system suspend, because it may have been set up to
- * signal remote wakeup from the system's working state as needed by runtime PM.
- * Return 'true' in either of the above cases.
- */
-static bool resume_needed(struct device *dev,
-			  const struct generic_pm_domain *genpd)
-{
-	bool active_wakeup;
-
-	if (!device_can_wakeup(dev))
-		return false;
-
-	active_wakeup = genpd_is_active_wakeup(genpd);
-	return device_may_wakeup(dev) ? active_wakeup : !active_wakeup;
-}
-
-/**
  * genpd_prepare - Start power transition of a device in a PM domain.
  * @dev: Device to start the transition of.
  *
@@ -1135,14 +1107,6 @@ static int genpd_prepare(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	/*
-	 * If a wakeup request is pending for the device, it should be woken up
-	 * at this point and a system wakeup event should be reported if it's
-	 * set up to wake up the system from sleep states.
-	 */
-	if (resume_needed(dev, genpd))
-		pm_runtime_resume(dev);
-
 	genpd_lock(genpd);
 
 	if (genpd->prepared_count++ == 0)
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index fe1dad68aee4..1fc1a992f90c 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -951,7 +951,7 @@ static void pm_runtime_work(struct work_struct *work)
 
 /**
  * pm_suspend_timer_fn - Timer function for pm_schedule_suspend().
- * @data: Device pointer passed by pm_schedule_suspend().
+ * @timer: hrtimer used by pm_schedule_suspend().
  *
  * Check if the time is right and queue a suspend request.
  */
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index 92073ac68473..f0b37c188514 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -400,9 +400,9 @@ void device_wakeup_detach_irq(struct device *dev)
 }
 
 /**
- * device_wakeup_arm_wake_irqs(void)
+ * device_wakeup_arm_wake_irqs -
  *
- * Itereates over the list of device wakeirqs to arm them.
+ * Iterates over the list of device wakeirqs to arm them.
  */
 void device_wakeup_arm_wake_irqs(void)
 {
@@ -416,9 +416,9 @@ void device_wakeup_arm_wake_irqs(void)
 }
 
 /**
- * device_wakeup_disarm_wake_irqs(void)
+ * device_wakeup_disarm_wake_irqs -
  *
- * Itereates over the list of device wakeirqs to disarm them.
+ * Iterates over the list of device wakeirqs to disarm them.
  */
 void device_wakeup_disarm_wake_irqs(void)
 {
@@ -532,6 +532,7 @@ EXPORT_SYMBOL_GPL(device_init_wakeup);
 /**
  * device_set_wakeup_enable - Enable or disable a device to wake up the system.
  * @dev: Device to handle.
+ * @enable: enable/disable flag
  */
 int device_set_wakeup_enable(struct device *dev, bool enable)
 {
@@ -581,7 +582,7 @@ static bool wakeup_source_not_registered(struct wakeup_source *ws)
  */
 
 /**
- * wakup_source_activate - Mark given wakeup source as active.
+ * wakeup_source_activate - Mark given wakeup source as active.
  * @ws: Wakeup source to handle.
  *
  * Update the @ws' statistics and, if @ws has just been activated, notify the PM
@@ -686,7 +687,7 @@ static inline void update_prevent_sleep_time(struct wakeup_source *ws,
 #endif
 
 /**
- * wakup_source_deactivate - Mark given wakeup source as inactive.
+ * wakeup_source_deactivate - Mark given wakeup source as inactive.
  * @ws: Wakeup source to handle.
  *
  * Update the @ws' statistics and notify the PM core that the wakeup source has
@@ -785,7 +786,7 @@ EXPORT_SYMBOL_GPL(pm_relax);
 
 /**
  * pm_wakeup_timer_fn - Delayed finalization of a wakeup event.
- * @data: Address of the wakeup source object associated with the event source.
+ * @t: timer list
  *
  * Call wakeup_source_deactivate() for the wakeup source whose address is stored
  * in @data if it is currently active and its timer has not been canceled and
@@ -1021,7 +1022,7 @@ bool pm_save_wakeup_count(unsigned int count)
 #ifdef CONFIG_PM_AUTOSLEEP
 /**
  * pm_wakep_autosleep_enabled - Modify autosleep_enabled for all wakeup sources.
- * @enabled: Whether to set or to clear the autosleep_enabled flags.
+ * @set: Whether to set or to clear the autosleep_enabled flags.
  */
 void pm_wakep_autosleep_enabled(bool set)
 {
diff --git a/drivers/base/power/wakeup_stats.c b/drivers/base/power/wakeup_stats.c
index 5ade7539ac02..924fac493c4f 100644
--- a/drivers/base/power/wakeup_stats.c
+++ b/drivers/base/power/wakeup_stats.c
@@ -137,7 +137,7 @@ static struct device *wakeup_source_device_create(struct device *parent,
 						  struct wakeup_source *ws)
 {
 	struct device *dev = NULL;
-	int retval = -ENODEV;
+	int retval;
 
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
 	if (!dev) {
diff --git a/drivers/clk/mvebu/armada-37xx-periph.c b/drivers/clk/mvebu/armada-37xx-periph.c
index f5746f9ea929..32ac6b6b7530 100644
--- a/drivers/clk/mvebu/armada-37xx-periph.c
+++ b/drivers/clk/mvebu/armada-37xx-periph.c
@@ -84,6 +84,7 @@ struct clk_pm_cpu {
 	void __iomem *reg_div;
 	u8 shift_div;
 	struct regmap *nb_pm_base;
+	unsigned long l1_expiration;
 };
 
 #define to_clk_double_div(_hw) container_of(_hw, struct clk_double_div, hw)
@@ -440,33 +441,6 @@ static u8 clk_pm_cpu_get_parent(struct clk_hw *hw)
 	return val;
 }
 
-static int clk_pm_cpu_set_parent(struct clk_hw *hw, u8 index)
-{
-	struct clk_pm_cpu *pm_cpu = to_clk_pm_cpu(hw);
-	struct regmap *base = pm_cpu->nb_pm_base;
-	int load_level;
-
-	/*
-	 * We set the clock parent only if the DVFS is available but
-	 * not enabled.
-	 */
-	if (IS_ERR(base) || armada_3700_pm_dvfs_is_enabled(base))
-		return -EINVAL;
-
-	/* Set the parent clock for all the load level */
-	for (load_level = 0; load_level < LOAD_LEVEL_NR; load_level++) {
-		unsigned int reg, mask,  val,
-			offset = ARMADA_37XX_NB_TBG_SEL_OFF;
-
-		armada_3700_pm_dvfs_update_regs(load_level, &reg, &offset);
-
-		val = index << offset;
-		mask = ARMADA_37XX_NB_TBG_SEL_MASK << offset;
-		regmap_update_bits(base, reg, mask, val);
-	}
-	return 0;
-}
-
 static unsigned long clk_pm_cpu_recalc_rate(struct clk_hw *hw,
 					    unsigned long parent_rate)
 {
@@ -514,8 +488,10 @@ static long clk_pm_cpu_round_rate(struct clk_hw *hw, unsigned long rate,
 }
 
 /*
- * Switching the CPU from the L2 or L3 frequencies (300 and 200 Mhz
- * respectively) to L0 frequency (1.2 Ghz) requires a significant
+ * Workaround when base CPU frequnecy is 1000 or 1200 MHz
+ *
+ * Switching the CPU from the L2 or L3 frequencies (250/300 or 200 MHz
+ * respectively) to L0 frequency (1/1.2 GHz) requires a significant
  * amount of time to let VDD stabilize to the appropriate
  * voltage. This amount of time is large enough that it cannot be
  * covered by the hardware countdown register. Due to this, the CPU
@@ -525,26 +501,56 @@ static long clk_pm_cpu_round_rate(struct clk_hw *hw, unsigned long rate,
  * To work around this problem, we prevent switching directly from the
  * L2/L3 frequencies to the L0 frequency, and instead switch to the L1
  * frequency in-between. The sequence therefore becomes:
- * 1. First switch from L2/L3(200/300MHz) to L1(600MHZ)
+ * 1. First switch from L2/L3 (200/250/300 MHz) to L1 (500/600 MHz)
  * 2. Sleep 20ms for stabling VDD voltage
- * 3. Then switch from L1(600MHZ) to L0(1200Mhz).
+ * 3. Then switch from L1 (500/600 MHz) to L0 (1000/1200 MHz).
  */
-static void clk_pm_cpu_set_rate_wa(unsigned long rate, struct regmap *base)
+static void clk_pm_cpu_set_rate_wa(struct clk_pm_cpu *pm_cpu,
+				   unsigned int new_level, unsigned long rate,
+				   struct regmap *base)
 {
 	unsigned int cur_level;
 
-	if (rate != 1200 * 1000 * 1000)
-		return;
-
 	regmap_read(base, ARMADA_37XX_NB_CPU_LOAD, &cur_level);
 	cur_level &= ARMADA_37XX_NB_CPU_LOAD_MASK;
-	if (cur_level <= ARMADA_37XX_DVFS_LOAD_1)
+
+	if (cur_level == new_level)
+		return;
+
+	/*
+	 * System wants to go to L1 on its own. If we are going from L2/L3,
+	 * remember when 20ms will expire. If from L0, set the value so that
+	 * next switch to L0 won't have to wait.
+	 */
+	if (new_level == ARMADA_37XX_DVFS_LOAD_1) {
+		if (cur_level == ARMADA_37XX_DVFS_LOAD_0)
+			pm_cpu->l1_expiration = jiffies;
+		else
+			pm_cpu->l1_expiration = jiffies + msecs_to_jiffies(20);
 		return;
+	}
+
+	/*
+	 * If we are setting to L2/L3, just invalidate L1 expiration time,
+	 * sleeping is not needed.
+	 */
+	if (rate < 1000*1000*1000)
+		goto invalidate_l1_exp;
+
+	/*
+	 * We are going to L0 with rate >= 1GHz. Check whether we have been at
+	 * L1 for long enough time. If not, go to L1 for 20ms.
+	 */
+	if (pm_cpu->l1_expiration && jiffies >= pm_cpu->l1_expiration)
+		goto invalidate_l1_exp;
 
 	regmap_update_bits(base, ARMADA_37XX_NB_CPU_LOAD,
 			   ARMADA_37XX_NB_CPU_LOAD_MASK,
 			   ARMADA_37XX_DVFS_LOAD_1);
 	msleep(20);
+
+invalidate_l1_exp:
+	pm_cpu->l1_expiration = 0;
 }
 
 static int clk_pm_cpu_set_rate(struct clk_hw *hw, unsigned long rate,
@@ -578,7 +584,9 @@ static int clk_pm_cpu_set_rate(struct clk_hw *hw, unsigned long rate,
 			reg = ARMADA_37XX_NB_CPU_LOAD;
 			mask = ARMADA_37XX_NB_CPU_LOAD_MASK;
 
-			clk_pm_cpu_set_rate_wa(rate, base);
+			/* Apply workaround when base CPU frequency is 1000 or 1200 MHz */
+			if (parent_rate >= 1000*1000*1000)
+				clk_pm_cpu_set_rate_wa(pm_cpu, load_level, rate, base);
 
 			regmap_update_bits(base, reg, mask, load_level);
 
@@ -592,7 +600,6 @@ static int clk_pm_cpu_set_rate(struct clk_hw *hw, unsigned long rate,
 
 static const struct clk_ops clk_pm_cpu_ops = {
 	.get_parent = clk_pm_cpu_get_parent,
-	.set_parent = clk_pm_cpu_set_parent,
 	.round_rate = clk_pm_cpu_round_rate,
 	.set_rate = clk_pm_cpu_set_rate,
 	.recalc_rate = clk_pm_cpu_recalc_rate,
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 85de313ddec2..c3038cdc6865 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -13,7 +13,8 @@ config CPU_FREQ
 	  clock speed, you need to either enable a dynamic cpufreq governor
 	  (see below) after boot, or use a userspace tool.
 
-	  For details, take a look at <file:Documentation/cpu-freq>.
+	  For details, take a look at
+	  <file:Documentation/admin-guide/pm/cpufreq.rst>.
 
 	  If in doubt, say N.
 
@@ -140,8 +141,6 @@ config CPU_FREQ_GOV_USERSPACE
 	  To compile this driver as a module, choose M here: the
 	  module will be called cpufreq_userspace.
 
-	  For details, take a look at <file:Documentation/cpu-freq/>.
-
 	  If in doubt, say Y.
 
 config CPU_FREQ_GOV_ONDEMAND
@@ -158,7 +157,8 @@ config CPU_FREQ_GOV_ONDEMAND
 	  To compile this driver as a module, choose M here: the
 	  module will be called cpufreq_ondemand.
 
-	  For details, take a look at linux/Documentation/cpu-freq.
+	  For details, take a look at
+	  <file:Documentation/admin-guide/pm/cpufreq.rst>.
 
 	  If in doubt, say N.
 
@@ -182,7 +182,8 @@ config CPU_FREQ_GOV_CONSERVATIVE
 	  To compile this driver as a module, choose M here: the
 	  module will be called cpufreq_conservative.
 
-	  For details, take a look at linux/Documentation/cpu-freq.
+	  For details, take a look at
+	  <file:Documentation/admin-guide/pm/cpufreq.rst>.
 
 	  If in doubt, say N.
 
@@ -246,8 +247,6 @@ config IA64_ACPI_CPUFREQ
 	This driver adds a CPUFreq driver which utilizes the ACPI
 	Processor Performance States.
 
-	For details, take a look at <file:Documentation/cpu-freq/>.
-
 	If in doubt, say N.
 endif
 
@@ -271,8 +270,6 @@ config LOONGSON2_CPUFREQ
 
 	  Loongson2F and it's successors support this feature.
 
-	  For details, take a look at <file:Documentation/cpu-freq/>.
-
 	  If in doubt, say N.
 
 config LOONGSON1_CPUFREQ
@@ -282,8 +279,6 @@ config LOONGSON1_CPUFREQ
 	  This option adds a CPUFreq driver for loongson1 processors which
 	  support software configurable cpu frequency.
 
-	  For details, take a look at <file:Documentation/cpu-freq/>.
-
 	  If in doubt, say N.
 endif
 
@@ -293,8 +288,6 @@ config SPARC_US3_CPUFREQ
 	help
 	  This adds the CPUFreq driver for UltraSPARC-III processors.
 
-	  For details, take a look at <file:Documentation/cpu-freq>.
-
 	  If in doubt, say N.
 
 config SPARC_US2E_CPUFREQ
@@ -302,8 +295,6 @@ config SPARC_US2E_CPUFREQ
 	help
 	  This adds the CPUFreq driver for UltraSPARC-IIe processors.
 
-	  For details, take a look at <file:Documentation/cpu-freq>.
-
 	  If in doubt, say N.
 endif
 
@@ -318,8 +309,6 @@ config SH_CPU_FREQ
 	  will also generate a notice in the boot log before disabling
 	  itself if the CPU in question is not capable of rate rounding.
 
-	  For details, take a look at <file:Documentation/cpu-freq>.
-
 	  If unsure, say N.
 endif
 
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index e65e0a43be64..a5c5f70acfc9 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -19,6 +19,16 @@ config ACPI_CPPC_CPUFREQ
 
 	  If in doubt, say N.
 
+config ACPI_CPPC_CPUFREQ_FIE
+	bool "Frequency Invariance support for CPPC cpufreq driver"
+	depends on ACPI_CPPC_CPUFREQ && GENERIC_ARCH_TOPOLOGY
+	default y
+	help
+	  This extends frequency invariance support in the CPPC cpufreq driver,
+	  by using CPPC delivered and reference performance counters.
+
+	  If in doubt, say N.
+
 config ARM_ALLWINNER_SUN50I_CPUFREQ_NVMEM
 	tristate "Allwinner nvmem based SUN50I CPUFreq driver"
 	depends on ARCH_SUNXI
diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c
index b4af4094309b..3fc98a3ffd91 100644
--- a/drivers/cpufreq/armada-37xx-cpufreq.c
+++ b/drivers/cpufreq/armada-37xx-cpufreq.c
@@ -25,6 +25,10 @@
 
 #include "cpufreq-dt.h"
 
+/* Clk register set */
+#define ARMADA_37XX_CLK_TBG_SEL		0
+#define ARMADA_37XX_CLK_TBG_SEL_CPU_OFF	22
+
 /* Power management in North Bridge register set */
 #define ARMADA_37XX_NB_L0L1	0x18
 #define ARMADA_37XX_NB_L2L3	0x1C
@@ -69,6 +73,8 @@
 #define LOAD_LEVEL_NR	4
 
 #define MIN_VOLT_MV 1000
+#define MIN_VOLT_MV_FOR_L1_1000MHZ 1108
+#define MIN_VOLT_MV_FOR_L1_1200MHZ 1155
 
 /*  AVS value for the corresponding voltage (in mV) */
 static int avs_map[] = {
@@ -80,6 +86,8 @@ static int avs_map[] = {
 };
 
 struct armada37xx_cpufreq_state {
+	struct platform_device *pdev;
+	struct device *cpu_dev;
 	struct regmap *regmap;
 	u32 nb_l0l1;
 	u32 nb_l2l3;
@@ -120,10 +128,15 @@ static struct armada_37xx_dvfs *armada_37xx_cpu_freq_info_get(u32 freq)
  * will be configured then the DVFS will be enabled.
  */
 static void __init armada37xx_cpufreq_dvfs_setup(struct regmap *base,
-						 struct clk *clk, u8 *divider)
+						 struct regmap *clk_base, u8 *divider)
 {
+	u32 cpu_tbg_sel;
 	int load_lvl;
-	struct clk *parent;
+
+	/* Determine to which TBG clock is CPU connected */
+	regmap_read(clk_base, ARMADA_37XX_CLK_TBG_SEL, &cpu_tbg_sel);
+	cpu_tbg_sel >>= ARMADA_37XX_CLK_TBG_SEL_CPU_OFF;
+	cpu_tbg_sel &= ARMADA_37XX_NB_TBG_SEL_MASK;
 
 	for (load_lvl = 0; load_lvl < LOAD_LEVEL_NR; load_lvl++) {
 		unsigned int reg, mask, val, offset = 0;
@@ -142,6 +155,11 @@ static void __init armada37xx_cpufreq_dvfs_setup(struct regmap *base,
 		mask = (ARMADA_37XX_NB_CLK_SEL_MASK
 			<< ARMADA_37XX_NB_CLK_SEL_OFF);
 
+		/* Set TBG index, for all levels we use the same TBG */
+		val = cpu_tbg_sel << ARMADA_37XX_NB_TBG_SEL_OFF;
+		mask = (ARMADA_37XX_NB_TBG_SEL_MASK
+			<< ARMADA_37XX_NB_TBG_SEL_OFF);
+
 		/*
 		 * Set cpu divider based on the pre-computed array in
 		 * order to have balanced step.
@@ -160,14 +178,6 @@ static void __init armada37xx_cpufreq_dvfs_setup(struct regmap *base,
 
 		regmap_update_bits(base, reg, mask, val);
 	}
-
-	/*
-	 * Set cpu clock source, for all the level we keep the same
-	 * clock source that the one already configured. For this one
-	 * we need to use the clock framework
-	 */
-	parent = clk_get_parent(clk);
-	clk_set_parent(clk, parent);
 }
 
 /*
@@ -202,6 +212,8 @@ static u32 armada_37xx_avs_val_match(int target_vm)
  * - 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.
+ * When base CPU frequency is 1000 or 1200 MHz then there is additional
+ * minimal avs value for load L1.
  */
 static void __init armada37xx_cpufreq_avs_configure(struct regmap *base,
 						struct armada_37xx_dvfs *dvfs)
@@ -233,6 +245,19 @@ static void __init armada37xx_cpufreq_avs_configure(struct regmap *base,
 		for (load_level = 1; load_level < LOAD_LEVEL_NR; load_level++)
 			dvfs->avs[load_level] = avs_min;
 
+		/*
+		 * Set the avs values for load L0 and L1 when base CPU frequency
+		 * is 1000/1200 MHz to its typical initial values according to
+		 * the Armada 3700 Hardware Specifications.
+		 */
+		if (dvfs->cpu_freq_max >= 1000*1000*1000) {
+			if (dvfs->cpu_freq_max >= 1200*1000*1000)
+				avs_min = armada_37xx_avs_val_match(MIN_VOLT_MV_FOR_L1_1200MHZ);
+			else
+				avs_min = armada_37xx_avs_val_match(MIN_VOLT_MV_FOR_L1_1000MHZ);
+			dvfs->avs[0] = dvfs->avs[1] = avs_min;
+		}
+
 		return;
 	}
 
@@ -252,6 +277,26 @@ static void __init armada37xx_cpufreq_avs_configure(struct regmap *base,
 	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);
+
+	/*
+	 * Fix the avs value for load L1 when base CPU frequency is 1000/1200 MHz,
+	 * otherwise the CPU gets stuck when switching from load L1 to load L0.
+	 * Also ensure that avs value for load L1 is not higher than for L0.
+	 */
+	if (dvfs->cpu_freq_max >= 1000*1000*1000) {
+		u32 avs_min_l1;
+
+		if (dvfs->cpu_freq_max >= 1200*1000*1000)
+			avs_min_l1 = armada_37xx_avs_val_match(MIN_VOLT_MV_FOR_L1_1200MHZ);
+		else
+			avs_min_l1 = armada_37xx_avs_val_match(MIN_VOLT_MV_FOR_L1_1000MHZ);
+
+		if (avs_min_l1 > dvfs->avs[0])
+			avs_min_l1 = dvfs->avs[0];
+
+		if (dvfs->avs[1] < avs_min_l1)
+			dvfs->avs[1] = avs_min_l1;
+	}
 }
 
 static void __init armada37xx_cpufreq_avs_setup(struct regmap *base,
@@ -357,12 +402,17 @@ static int __init armada37xx_cpufreq_driver_init(void)
 	struct armada_37xx_dvfs *dvfs;
 	struct platform_device *pdev;
 	unsigned long freq;
-	unsigned int cur_frequency, base_frequency;
-	struct regmap *nb_pm_base, *avs_base;
+	unsigned int base_frequency;
+	struct regmap *nb_clk_base, *nb_pm_base, *avs_base;
 	struct device *cpu_dev;
 	int load_lvl, ret;
 	struct clk *clk, *parent;
 
+	nb_clk_base =
+		syscon_regmap_lookup_by_compatible("marvell,armada-3700-periph-clock-nb");
+	if (IS_ERR(nb_clk_base))
+		return -ENODEV;
+
 	nb_pm_base =
 		syscon_regmap_lookup_by_compatible("marvell,armada-3700-nb-pm");
 
@@ -413,15 +463,7 @@ static int __init armada37xx_cpufreq_driver_init(void)
 		return -EINVAL;
 	}
 
-	/* Get nominal (current) CPU frequency */
-	cur_frequency = clk_get_rate(clk);
-	if (!cur_frequency) {
-		dev_err(cpu_dev, "Failed to get clock rate for CPU\n");
-		clk_put(clk);
-		return -EINVAL;
-	}
-
-	dvfs = armada_37xx_cpu_freq_info_get(cur_frequency);
+	dvfs = armada_37xx_cpu_freq_info_get(base_frequency);
 	if (!dvfs) {
 		clk_put(clk);
 		return -EINVAL;
@@ -439,7 +481,7 @@ static int __init armada37xx_cpufreq_driver_init(void)
 	armada37xx_cpufreq_avs_configure(avs_base, dvfs);
 	armada37xx_cpufreq_avs_setup(avs_base, dvfs);
 
-	armada37xx_cpufreq_dvfs_setup(nb_pm_base, clk, dvfs->divider);
+	armada37xx_cpufreq_dvfs_setup(nb_pm_base, nb_clk_base, dvfs->divider);
 	clk_put(clk);
 
 	for (load_lvl = ARMADA_37XX_DVFS_LOAD_0; load_lvl < LOAD_LEVEL_NR;
@@ -466,6 +508,9 @@ static int __init armada37xx_cpufreq_driver_init(void)
 	if (ret)
 		goto disable_dvfs;
 
+	armada37xx_cpufreq_state->cpu_dev = cpu_dev;
+	armada37xx_cpufreq_state->pdev = pdev;
+	platform_set_drvdata(pdev, dvfs);
 	return 0;
 
 disable_dvfs:
@@ -473,7 +518,7 @@ disable_dvfs:
 remove_opp:
 	/* clean-up the already added opp before leaving */
 	while (load_lvl-- > ARMADA_37XX_DVFS_LOAD_0) {
-		freq = cur_frequency / dvfs->divider[load_lvl];
+		freq = base_frequency / dvfs->divider[load_lvl];
 		dev_pm_opp_remove(cpu_dev, freq);
 	}
 
@@ -484,6 +529,26 @@ remove_opp:
 /* late_initcall, to guarantee the driver is loaded after A37xx clock driver */
 late_initcall(armada37xx_cpufreq_driver_init);
 
+static void __exit armada37xx_cpufreq_driver_exit(void)
+{
+	struct platform_device *pdev = armada37xx_cpufreq_state->pdev;
+	struct armada_37xx_dvfs *dvfs = platform_get_drvdata(pdev);
+	unsigned long freq;
+	int load_lvl;
+
+	platform_device_unregister(pdev);
+
+	armada37xx_cpufreq_disable_dvfs(armada37xx_cpufreq_state->regmap);
+
+	for (load_lvl = ARMADA_37XX_DVFS_LOAD_0; load_lvl < LOAD_LEVEL_NR; load_lvl++) {
+		freq = dvfs->cpu_freq_max / dvfs->divider[load_lvl];
+		dev_pm_opp_remove(armada37xx_cpufreq_state->cpu_dev, freq);
+	}
+
+	kfree(armada37xx_cpufreq_state);
+}
+module_exit(armada37xx_cpufreq_driver_exit);
+
 static const struct of_device_id __maybe_unused armada37xx_cpufreq_of_match[] = {
 	{ .compatible = "marvell,armada-3700-nb-pm" },
 	{ },
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index 8a482c434ea6..3848b4c222e1 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -10,14 +10,18 @@
 
 #define pr_fmt(fmt)	"CPPC Cpufreq:"	fmt
 
+#include <linux/arch_topology.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/dmi.h>
+#include <linux/irq_work.h>
+#include <linux/kthread.h>
 #include <linux/time.h>
 #include <linux/vmalloc.h>
+#include <uapi/linux/sched/types.h>
 
 #include <asm/unaligned.h>
 
@@ -57,6 +61,204 @@ static struct cppc_workaround_oem_info wa_info[] = {
 	}
 };
 
+#ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE
+
+/* Frequency invariance support */
+struct cppc_freq_invariance {
+	int cpu;
+	struct irq_work irq_work;
+	struct kthread_work work;
+	struct cppc_perf_fb_ctrs prev_perf_fb_ctrs;
+	struct cppc_cpudata *cpu_data;
+};
+
+static DEFINE_PER_CPU(struct cppc_freq_invariance, cppc_freq_inv);
+static struct kthread_worker *kworker_fie;
+static bool fie_disabled;
+
+static struct cpufreq_driver cppc_cpufreq_driver;
+static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu);
+static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data,
+				 struct cppc_perf_fb_ctrs fb_ctrs_t0,
+				 struct cppc_perf_fb_ctrs fb_ctrs_t1);
+
+/**
+ * cppc_scale_freq_workfn - CPPC arch_freq_scale updater for frequency invariance
+ * @work: The work item.
+ *
+ * The CPPC driver register itself with the topology core to provide its own
+ * implementation (cppc_scale_freq_tick()) of topology_scale_freq_tick() which
+ * gets called by the scheduler on every tick.
+ *
+ * Note that the arch specific counters have higher priority than CPPC counters,
+ * if available, though the CPPC driver doesn't need to have any special
+ * handling for that.
+ *
+ * On an invocation of cppc_scale_freq_tick(), we schedule an irq work (since we
+ * reach here from hard-irq context), which then schedules a normal work item
+ * and cppc_scale_freq_workfn() updates the per_cpu arch_freq_scale variable
+ * based on the counter updates since the last tick.
+ */
+static void cppc_scale_freq_workfn(struct kthread_work *work)
+{
+	struct cppc_freq_invariance *cppc_fi;
+	struct cppc_perf_fb_ctrs fb_ctrs = {0};
+	struct cppc_cpudata *cpu_data;
+	unsigned long local_freq_scale;
+	u64 perf;
+
+	cppc_fi = container_of(work, struct cppc_freq_invariance, work);
+	cpu_data = cppc_fi->cpu_data;
+
+	if (cppc_get_perf_ctrs(cppc_fi->cpu, &fb_ctrs)) {
+		pr_warn("%s: failed to read perf counters\n", __func__);
+		return;
+	}
+
+	cppc_fi->prev_perf_fb_ctrs = fb_ctrs;
+	perf = cppc_perf_from_fbctrs(cpu_data, cppc_fi->prev_perf_fb_ctrs,
+				     fb_ctrs);
+
+	perf <<= SCHED_CAPACITY_SHIFT;
+	local_freq_scale = div64_u64(perf, cpu_data->perf_caps.highest_perf);
+	if (WARN_ON(local_freq_scale > 1024))
+		local_freq_scale = 1024;
+
+	per_cpu(arch_freq_scale, cppc_fi->cpu) = local_freq_scale;
+}
+
+static void cppc_irq_work(struct irq_work *irq_work)
+{
+	struct cppc_freq_invariance *cppc_fi;
+
+	cppc_fi = container_of(irq_work, struct cppc_freq_invariance, irq_work);
+	kthread_queue_work(kworker_fie, &cppc_fi->work);
+}
+
+static void cppc_scale_freq_tick(void)
+{
+	struct cppc_freq_invariance *cppc_fi = &per_cpu(cppc_freq_inv, smp_processor_id());
+
+	/*
+	 * cppc_get_perf_ctrs() can potentially sleep, call that from the right
+	 * context.
+	 */
+	irq_work_queue(&cppc_fi->irq_work);
+}
+
+static struct scale_freq_data cppc_sftd = {
+	.source = SCALE_FREQ_SOURCE_CPPC,
+	.set_freq_scale = cppc_scale_freq_tick,
+};
+
+static void cppc_freq_invariance_policy_init(struct cpufreq_policy *policy,
+					     struct cppc_cpudata *cpu_data)
+{
+	struct cppc_perf_fb_ctrs fb_ctrs = {0};
+	struct cppc_freq_invariance *cppc_fi;
+	int i, ret;
+
+	if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate)
+		return;
+
+	if (fie_disabled)
+		return;
+
+	for_each_cpu(i, policy->cpus) {
+		cppc_fi = &per_cpu(cppc_freq_inv, i);
+		cppc_fi->cpu = i;
+		cppc_fi->cpu_data = cpu_data;
+		kthread_init_work(&cppc_fi->work, cppc_scale_freq_workfn);
+		init_irq_work(&cppc_fi->irq_work, cppc_irq_work);
+
+		ret = cppc_get_perf_ctrs(i, &fb_ctrs);
+		if (ret) {
+			pr_warn("%s: failed to read perf counters: %d\n",
+				__func__, ret);
+			fie_disabled = true;
+		} else {
+			cppc_fi->prev_perf_fb_ctrs = fb_ctrs;
+		}
+	}
+}
+
+static void __init cppc_freq_invariance_init(void)
+{
+	struct sched_attr attr = {
+		.size		= sizeof(struct sched_attr),
+		.sched_policy	= SCHED_DEADLINE,
+		.sched_nice	= 0,
+		.sched_priority	= 0,
+		/*
+		 * Fake (unused) bandwidth; workaround to "fix"
+		 * priority inheritance.
+		 */
+		.sched_runtime	= 1000000,
+		.sched_deadline = 10000000,
+		.sched_period	= 10000000,
+	};
+	int ret;
+
+	if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate)
+		return;
+
+	if (fie_disabled)
+		return;
+
+	kworker_fie = kthread_create_worker(0, "cppc_fie");
+	if (IS_ERR(kworker_fie))
+		return;
+
+	ret = sched_setattr_nocheck(kworker_fie->task, &attr);
+	if (ret) {
+		pr_warn("%s: failed to set SCHED_DEADLINE: %d\n", __func__,
+			ret);
+		kthread_destroy_worker(kworker_fie);
+		return;
+	}
+
+	/* Register for freq-invariance */
+	topology_set_scale_freq_source(&cppc_sftd, cpu_present_mask);
+}
+
+static void cppc_freq_invariance_exit(void)
+{
+	struct cppc_freq_invariance *cppc_fi;
+	int i;
+
+	if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate)
+		return;
+
+	if (fie_disabled)
+		return;
+
+	topology_clear_scale_freq_source(SCALE_FREQ_SOURCE_CPPC, cpu_present_mask);
+
+	for_each_possible_cpu(i) {
+		cppc_fi = &per_cpu(cppc_freq_inv, i);
+		irq_work_sync(&cppc_fi->irq_work);
+	}
+
+	kthread_destroy_worker(kworker_fie);
+	kworker_fie = NULL;
+}
+
+#else
+static inline void
+cppc_freq_invariance_policy_init(struct cpufreq_policy *policy,
+				 struct cppc_cpudata *cpu_data)
+{
+}
+
+static inline void cppc_freq_invariance_init(void)
+{
+}
+
+static inline void cppc_freq_invariance_exit(void)
+{
+}
+#endif /* CONFIG_ACPI_CPPC_CPUFREQ_FIE */
+
 /* Callback function used to retrieve the max frequency from DMI */
 static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private)
 {
@@ -216,26 +418,16 @@ static unsigned int cppc_cpufreq_get_transition_delay_us(unsigned int cpu)
 {
 	unsigned long implementor = read_cpuid_implementor();
 	unsigned long part_num = read_cpuid_part_number();
-	unsigned int delay_us = 0;
 
 	switch (implementor) {
 	case ARM_CPU_IMP_QCOM:
 		switch (part_num) {
 		case QCOM_CPU_PART_FALKOR_V1:
 		case QCOM_CPU_PART_FALKOR:
-			delay_us = 10000;
-			break;
-		default:
-			delay_us = cppc_get_transition_latency(cpu) / NSEC_PER_USEC;
-			break;
+			return 10000;
 		}
-		break;
-	default:
-		delay_us = cppc_get_transition_latency(cpu) / NSEC_PER_USEC;
-		break;
 	}
-
-	return delay_us;
+	return cppc_get_transition_latency(cpu) / NSEC_PER_USEC;
 }
 
 #else
@@ -355,9 +547,12 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	cpu_data->perf_ctrls.desired_perf =  caps->highest_perf;
 
 	ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls);
-	if (ret)
+	if (ret) {
 		pr_debug("Err setting perf value:%d on CPU:%d. ret:%d\n",
 			 caps->highest_perf, cpu, ret);
+	} else {
+		cppc_freq_invariance_policy_init(policy, cpu_data);
+	}
 
 	return ret;
 }
@@ -370,12 +565,12 @@ static inline u64 get_delta(u64 t1, u64 t0)
 	return (u32)t1 - (u32)t0;
 }
 
-static int cppc_get_rate_from_fbctrs(struct cppc_cpudata *cpu_data,
-				     struct cppc_perf_fb_ctrs fb_ctrs_t0,
-				     struct cppc_perf_fb_ctrs fb_ctrs_t1)
+static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data,
+				 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;
+	u64 reference_perf;
 
 	reference_perf = fb_ctrs_t0.reference_perf;
 
@@ -384,12 +579,21 @@ static int cppc_get_rate_from_fbctrs(struct cppc_cpudata *cpu_data,
 	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_data->perf_ctrls.desired_perf;
+	/* Check to avoid divide-by zero and invalid delivered_perf */
+	if (!delta_reference || !delta_delivered)
+		return cpu_data->perf_ctrls.desired_perf;
+
+	return (reference_perf * delta_delivered) / delta_reference;
+}
+
+static int cppc_get_rate_from_fbctrs(struct cppc_cpudata *cpu_data,
+				     struct cppc_perf_fb_ctrs fb_ctrs_t0,
+				     struct cppc_perf_fb_ctrs fb_ctrs_t1)
+{
+	u64 delivered_perf;
+
+	delivered_perf = cppc_perf_from_fbctrs(cpu_data, fb_ctrs_t0,
+					       fb_ctrs_t1);
 
 	return cppc_cpufreq_perf_to_khz(cpu_data, delivered_perf);
 }
@@ -514,6 +718,8 @@ static void cppc_check_hisi_workaround(void)
 
 static int __init cppc_cpufreq_init(void)
 {
+	int ret;
+
 	if ((acpi_disabled) || !acpi_cpc_valid())
 		return -ENODEV;
 
@@ -521,7 +727,11 @@ static int __init cppc_cpufreq_init(void)
 
 	cppc_check_hisi_workaround();
 
-	return cpufreq_register_driver(&cppc_cpufreq_driver);
+	ret = cpufreq_register_driver(&cppc_cpufreq_driver);
+	if (!ret)
+		cppc_freq_invariance_init();
+
+	return ret;
 }
 
 static inline void free_cpu_data(void)
@@ -538,6 +748,7 @@ static inline void free_cpu_data(void)
 
 static void __exit cppc_cpufreq_exit(void)
 {
+	cppc_freq_invariance_exit();
 	cpufreq_unregister_driver(&cppc_cpufreq_driver);
 
 	free_cpu_data();
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index b1e1bdc63b01..ece52863ba62 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -255,10 +255,15 @@ static int dt_cpufreq_early_init(struct device *dev, int cpu)
 	 * before updating priv->cpus. Otherwise, we will end up creating
 	 * duplicate OPPs for the CPUs.
 	 *
-	 * OPPs might be populated at runtime, don't check for error here.
+	 * OPPs might be populated at runtime, don't fail for error here unless
+	 * it is -EPROBE_DEFER.
 	 */
-	if (!dev_pm_opp_of_cpumask_add_table(priv->cpus))
+	ret = dev_pm_opp_of_cpumask_add_table(priv->cpus);
+	if (!ret) {
 		priv->have_static_opps = true;
+	} else if (ret == -EPROBE_DEFER) {
+		goto out;
+	}
 
 	/*
 	 * The OPP table must be initialized, statically or dynamically, by this
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 1d1b563cea4b..802abc925b2a 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -42,9 +42,6 @@ static LIST_HEAD(cpufreq_policy_list);
 #define for_each_inactive_policy(__policy)		\
 	for_each_suitable_policy(__policy, false)
 
-#define for_each_policy(__policy)			\
-	list_for_each_entry(__policy, &cpufreq_policy_list, policy_list)
-
 /* Iterate over governors */
 static LIST_HEAD(cpufreq_governor_list);
 #define for_each_governor(__governor)				\
diff --git a/drivers/cpufreq/ia64-acpi-cpufreq.c b/drivers/cpufreq/ia64-acpi-cpufreq.c
index 2efe7189ccc4..c6bdc455517f 100644
--- a/drivers/cpufreq/ia64-acpi-cpufreq.c
+++ b/drivers/cpufreq/ia64-acpi-cpufreq.c
@@ -54,7 +54,7 @@ processor_set_pstate (
 	retval = ia64_pal_set_pstate((u64)value);
 
 	if (retval) {
-		pr_debug("Failed to set freq to 0x%x, with error 0x%lx\n",
+		pr_debug("Failed to set freq to 0x%x, with error 0x%llx\n",
 		        value, retval);
 		return -ENODEV;
 	}
@@ -77,7 +77,7 @@ processor_get_pstate (
 
 	if (retval)
 		pr_debug("Failed to get current freq with "
-			"error 0x%lx, idx 0x%x\n", retval, *value);
+			"error 0x%llx, idx 0x%x\n", retval, *value);
 
 	return (int)retval;
 }
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 5175ae3cac44..f0401064d7aa 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -819,19 +819,21 @@ static struct freq_attr *hwp_cpufreq_attrs[] = {
 	NULL,
 };
 
-static void intel_pstate_get_hwp_max(struct cpudata *cpu, int *phy_max,
-				     int *current_max)
+static void __intel_pstate_get_hwp_cap(struct cpudata *cpu)
 {
 	u64 cap;
 
 	rdmsrl_on_cpu(cpu->cpu, MSR_HWP_CAPABILITIES, &cap);
 	WRITE_ONCE(cpu->hwp_cap_cached, cap);
-	if (global.no_turbo || global.turbo_disabled)
-		*current_max = HWP_GUARANTEED_PERF(cap);
-	else
-		*current_max = HWP_HIGHEST_PERF(cap);
+	cpu->pstate.max_pstate = HWP_GUARANTEED_PERF(cap);
+	cpu->pstate.turbo_pstate = HWP_HIGHEST_PERF(cap);
+}
 
-	*phy_max = HWP_HIGHEST_PERF(cap);
+static void intel_pstate_get_hwp_cap(struct cpudata *cpu)
+{
+	__intel_pstate_get_hwp_cap(cpu);
+	cpu->pstate.max_freq = cpu->pstate.max_pstate * cpu->pstate.scaling;
+	cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
 }
 
 static void intel_pstate_hwp_set(unsigned int cpu)
@@ -1195,12 +1197,13 @@ static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b,
 
 static void update_qos_request(enum freq_qos_req_type type)
 {
-	int max_state, turbo_max, freq, i, perf_pct;
 	struct freq_qos_request *req;
 	struct cpufreq_policy *policy;
+	int i;
 
 	for_each_possible_cpu(i) {
 		struct cpudata *cpu = all_cpu_data[i];
+		unsigned int freq, perf_pct;
 
 		policy = cpufreq_cpu_get(i);
 		if (!policy)
@@ -1213,9 +1216,7 @@ static void update_qos_request(enum freq_qos_req_type type)
 			continue;
 
 		if (hwp_active)
-			intel_pstate_get_hwp_max(cpu, &turbo_max, &max_state);
-		else
-			turbo_max = cpu->pstate.turbo_pstate;
+			intel_pstate_get_hwp_cap(cpu);
 
 		if (type == FREQ_QOS_MIN) {
 			perf_pct = global.min_perf_pct;
@@ -1224,8 +1225,7 @@ static void update_qos_request(enum freq_qos_req_type type)
 			perf_pct = global.max_perf_pct;
 		}
 
-		freq = DIV_ROUND_UP(turbo_max * perf_pct, 100);
-		freq *= cpu->pstate.scaling;
+		freq = DIV_ROUND_UP(cpu->pstate.turbo_freq * perf_pct, 100);
 
 		if (freq_qos_update_request(req, freq) < 0)
 			pr_warn("Failed to update freq constraint: CPU%d\n", i);
@@ -1715,21 +1715,17 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 {
 	cpu->pstate.min_pstate = pstate_funcs.get_min();
 	cpu->pstate.max_pstate_physical = pstate_funcs.get_max_physical();
-	cpu->pstate.turbo_pstate = pstate_funcs.get_turbo();
 	cpu->pstate.scaling = pstate_funcs.get_scaling();
 
 	if (hwp_active && !hwp_mode_bdw) {
-		unsigned int phy_max, current_max;
-
-		intel_pstate_get_hwp_max(cpu, &phy_max, &current_max);
-		cpu->pstate.turbo_freq = phy_max * cpu->pstate.scaling;
-		cpu->pstate.turbo_pstate = phy_max;
-		cpu->pstate.max_pstate = HWP_GUARANTEED_PERF(READ_ONCE(cpu->hwp_cap_cached));
+		__intel_pstate_get_hwp_cap(cpu);
 	} else {
-		cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
 		cpu->pstate.max_pstate = pstate_funcs.get_max();
+		cpu->pstate.turbo_pstate = pstate_funcs.get_turbo();
 	}
+
 	cpu->pstate.max_freq = cpu->pstate.max_pstate * cpu->pstate.scaling;
+	cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
 
 	if (pstate_funcs.get_aperf_mperf_shift)
 		cpu->aperf_mperf_shift = pstate_funcs.get_aperf_mperf_shift();
@@ -2199,41 +2195,34 @@ static void intel_pstate_update_perf_limits(struct cpudata *cpu,
 					    unsigned int policy_min,
 					    unsigned int policy_max)
 {
+	int scaling = cpu->pstate.scaling;
 	int32_t max_policy_perf, min_policy_perf;
-	int max_state, turbo_max;
-	int max_freq;
 
 	/*
-	 * HWP needs some special consideration, because on BDX the
-	 * HWP_REQUEST uses abstract value to represent performance
-	 * rather than pure ratios.
+	 * HWP needs some special consideration, because HWP_REQUEST uses
+	 * abstract values to represent performance rather than pure ratios.
 	 */
-	if (hwp_active) {
-		intel_pstate_get_hwp_max(cpu, &turbo_max, &max_state);
-	} else {
-		max_state = global.no_turbo || global.turbo_disabled ?
-			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
-		turbo_max = cpu->pstate.turbo_pstate;
-	}
-	max_freq = max_state * cpu->pstate.scaling;
+	if (hwp_active)
+		intel_pstate_get_hwp_cap(cpu);
 
-	max_policy_perf = max_state * policy_max / max_freq;
+	max_policy_perf = policy_max / scaling;
 	if (policy_max == policy_min) {
 		min_policy_perf = max_policy_perf;
 	} else {
-		min_policy_perf = max_state * policy_min / max_freq;
+		min_policy_perf = policy_min / scaling;
 		min_policy_perf = clamp_t(int32_t, min_policy_perf,
 					  0, max_policy_perf);
 	}
 
-	pr_debug("cpu:%d max_state %d min_policy_perf:%d max_policy_perf:%d\n",
-		 cpu->cpu, max_state, min_policy_perf, max_policy_perf);
+	pr_debug("cpu:%d min_policy_perf:%d max_policy_perf:%d\n",
+		 cpu->cpu, min_policy_perf, max_policy_perf);
 
 	/* Normalize user input to [min_perf, max_perf] */
 	if (per_cpu_limits) {
 		cpu->min_perf_ratio = min_policy_perf;
 		cpu->max_perf_ratio = max_policy_perf;
 	} else {
+		int turbo_max = cpu->pstate.turbo_pstate;
 		int32_t global_min, global_max;
 
 		/* Global limits are in percent of the maximum turbo P-state. */
@@ -2322,10 +2311,9 @@ static void intel_pstate_verify_cpu_policy(struct cpudata *cpu,
 
 	update_turbo_state();
 	if (hwp_active) {
-		int max_state, turbo_max;
-
-		intel_pstate_get_hwp_max(cpu, &turbo_max, &max_state);
-		max_freq = max_state * cpu->pstate.scaling;
+		intel_pstate_get_hwp_cap(cpu);
+		max_freq = global.no_turbo || global.turbo_disabled ?
+				cpu->pstate.max_freq : cpu->pstate.turbo_freq;
 	} else {
 		max_freq = intel_pstate_get_max_freq(cpu);
 	}
@@ -2416,25 +2404,15 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy)
 	cpu->max_perf_ratio = 0xFF;
 	cpu->min_perf_ratio = 0;
 
-	policy->min = cpu->pstate.min_pstate * cpu->pstate.scaling;
-	policy->max = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
-
 	/* cpuinfo and default policy values */
 	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling;
 	update_turbo_state();
 	global.turbo_disabled_mf = global.turbo_disabled;
 	policy->cpuinfo.max_freq = global.turbo_disabled ?
-			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;
-	}
+
+	policy->min = policy->cpuinfo.min_freq;
+	policy->max = policy->cpuinfo.max_freq;
 
 	intel_pstate_init_acpi_perf_limits(policy);
 
@@ -2683,10 +2661,10 @@ static void intel_cpufreq_adjust_perf(unsigned int cpunum,
 
 static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
-	int max_state, turbo_max, min_freq, max_freq, ret;
 	struct freq_qos_request *req;
 	struct cpudata *cpu;
 	struct device *dev;
+	int ret, freq;
 
 	dev = get_cpu_device(policy->cpu);
 	if (!dev)
@@ -2711,30 +2689,31 @@ static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	if (hwp_active) {
 		u64 value;
 
-		intel_pstate_get_hwp_max(cpu, &turbo_max, &max_state);
 		policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY_HWP;
+
+		intel_pstate_get_hwp_cap(cpu);
+
 		rdmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, &value);
 		WRITE_ONCE(cpu->hwp_req_cached, value);
+
 		cpu->epp_cached = intel_pstate_get_epp(cpu, value);
 	} else {
-		turbo_max = cpu->pstate.turbo_pstate;
 		policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY;
 	}
 
-	min_freq = DIV_ROUND_UP(turbo_max * global.min_perf_pct, 100);
-	min_freq *= cpu->pstate.scaling;
-	max_freq = DIV_ROUND_UP(turbo_max * global.max_perf_pct, 100);
-	max_freq *= cpu->pstate.scaling;
+	freq = DIV_ROUND_UP(cpu->pstate.turbo_freq * global.min_perf_pct, 100);
 
 	ret = freq_qos_add_request(&policy->constraints, req, FREQ_QOS_MIN,
-				   min_freq);
+				   freq);
 	if (ret < 0) {
 		dev_err(dev, "Failed to add min-freq constraint (%d)\n", ret);
 		goto free_req;
 	}
 
+	freq = DIV_ROUND_UP(cpu->pstate.turbo_freq * global.max_perf_pct, 100);
+
 	ret = freq_qos_add_request(&policy->constraints, req + 1, FREQ_QOS_MAX,
-				   max_freq);
+				   freq);
 	if (ret < 0) {
 		dev_err(dev, "Failed to add max-freq constraint (%d)\n", ret);
 		goto remove_min_req;
diff --git a/drivers/cpufreq/s5pv210-cpufreq.c b/drivers/cpufreq/s5pv210-cpufreq.c
index 69786e5bbf05..ad7d4f272ddc 100644
--- a/drivers/cpufreq/s5pv210-cpufreq.c
+++ b/drivers/cpufreq/s5pv210-cpufreq.c
@@ -91,7 +91,7 @@ static DEFINE_MUTEX(set_freq_lock);
 /* Use 800MHz when entering sleep mode */
 #define SLEEP_FREQ	(800 * 1000)
 
-/* Tracks if cpu freqency can be updated anymore */
+/* Tracks if CPU frequency can be updated anymore */
 static bool no_cpufreq_access;
 
 /*
@@ -190,7 +190,7 @@ static u32 clkdiv_val[5][11] = {
 
 /*
  * This function set DRAM refresh counter
- * accoriding to operating frequency of DRAM
+ * according to operating frequency of DRAM
  * ch: DMC port number 0 or 1
  * freq: Operating frequency of DRAM(KHz)
  */
@@ -320,7 +320,7 @@ static int s5pv210_target(struct cpufreq_policy *policy, unsigned int index)
 
 		/*
 		 * 3. DMC1 refresh count for 133Mhz if (index == L4) is
-		 * true refresh counter is already programed in upper
+		 * true refresh counter is already programmed in upper
 		 * code. 0x287@83Mhz
 		 */
 		if (!bus_speed_changing)
@@ -378,7 +378,7 @@ static int s5pv210_target(struct cpufreq_policy *policy, unsigned int index)
 		/*
 		 * 6. Turn on APLL
 		 * 6-1. Set PMS values
-		 * 6-2. Wait untile the PLL is locked
+		 * 6-2. Wait until the PLL is locked
 		 */
 		if (index == L0)
 			writel_relaxed(APLL_VAL_1000, S5P_APLL_CON);
@@ -390,7 +390,7 @@ static int s5pv210_target(struct cpufreq_policy *policy, unsigned int index)
 		} while (!(reg & (0x1 << 29)));
 
 		/*
-		 * 7. Change souce clock from SCLKMPLL(667Mhz)
+		 * 7. Change source clock from SCLKMPLL(667Mhz)
 		 * to SCLKA2M(200Mhz) in MFC_MUX and G3D MUX
 		 * (667/4=166)->(200/4=50)Mhz
 		 */
@@ -439,8 +439,8 @@ static int s5pv210_target(struct cpufreq_policy *policy, unsigned int index)
 	}
 
 	/*
-	 * L4 level need to change memory bus speed, hence onedram clock divier
-	 * and memory refresh parameter should be changed
+	 * L4 level needs to change memory bus speed, hence ONEDRAM clock
+	 * divider and memory refresh parameter should be changed
 	 */
 	if (bus_speed_changing) {
 		reg = readl_relaxed(S5P_CLK_DIV6);
diff --git a/drivers/cpuidle/Kconfig.arm b/drivers/cpuidle/Kconfig.arm
index 0844fadc4be8..334f83e56120 100644
--- a/drivers/cpuidle/Kconfig.arm
+++ b/drivers/cpuidle/Kconfig.arm
@@ -107,7 +107,7 @@ config ARM_TEGRA_CPUIDLE
 
 config ARM_QCOM_SPM_CPUIDLE
 	bool "CPU Idle Driver for Qualcomm Subsystem Power Manager (SPM)"
-	depends on (ARCH_QCOM || COMPILE_TEST) && !ARM64
+	depends on (ARCH_QCOM || COMPILE_TEST) && !ARM64 && MMU
 	select ARM_CPU_SUSPEND
 	select CPU_IDLE_MULTIPLE_DRIVERS
 	select DT_IDLE_STATES
diff --git a/drivers/cpuidle/cpuidle-tegra.c b/drivers/cpuidle/cpuidle-tegra.c
index 191966dc8d02..508bd9f23792 100644
--- a/drivers/cpuidle/cpuidle-tegra.c
+++ b/drivers/cpuidle/cpuidle-tegra.c
@@ -48,11 +48,6 @@ enum tegra_state {
 static atomic_t tegra_idle_barrier;
 static atomic_t tegra_abort_flag;
 
-static inline bool tegra_cpuidle_using_firmware(void)
-{
-	return firmware_ops->prepare_idle && firmware_ops->do_idle;
-}
-
 static void tegra_cpuidle_report_cpus_state(void)
 {
 	unsigned long cpu, lcpu, csr;
@@ -135,13 +130,9 @@ static int tegra_cpuidle_c7_enter(void)
 {
 	int err;
 
-	if (tegra_cpuidle_using_firmware()) {
-		err = call_firmware_op(prepare_idle, TF_PM_MODE_LP2_NOFLUSH_L2);
-		if (err)
-			return err;
-
-		return call_firmware_op(do_idle, 0);
-	}
+	err = call_firmware_op(prepare_idle, TF_PM_MODE_LP2_NOFLUSH_L2);
+	if (err && err != -ENOSYS)
+		return err;
 
 	return cpu_suspend(0, tegra30_pm_secondary_cpu_suspend);
 }
@@ -356,9 +347,7 @@ static int tegra_cpuidle_probe(struct platform_device *pdev)
 	 * is disabled.
 	 */
 	if (!IS_ENABLED(CONFIG_PM_SLEEP)) {
-		if (!tegra_cpuidle_using_firmware())
-			tegra_cpuidle_disable_state(TEGRA_C7);
-
+		tegra_cpuidle_disable_state(TEGRA_C7);
 		tegra_cpuidle_disable_state(TEGRA_CC6);
 	}
 
diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c
index 4070e573bf43..f70aa17e2a8e 100644
--- a/drivers/cpuidle/driver.c
+++ b/drivers/cpuidle/driver.c
@@ -181,9 +181,13 @@ static void __cpuidle_driver_init(struct cpuidle_driver *drv)
 		 */
 		if (s->target_residency > 0)
 			s->target_residency_ns = s->target_residency * NSEC_PER_USEC;
+		else if (s->target_residency_ns < 0)
+			s->target_residency_ns = 0;
 
 		if (s->exit_latency > 0)
 			s->exit_latency_ns = s->exit_latency * NSEC_PER_USEC;
+		else if (s->exit_latency_ns < 0)
+			s->exit_latency_ns =  0;
 	}
 }
 
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index b0a7ad566081..c3aa8d6ccee3 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -271,7 +271,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	u64 predicted_ns;
 	u64 interactivity_req;
 	unsigned long nr_iowaiters;
-	ktime_t delta_next;
+	ktime_t delta, delta_tick;
 	int i, idx;
 
 	if (data->needs_update) {
@@ -280,7 +280,12 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	}
 
 	/* determine the expected residency time, round up */
-	data->next_timer_ns = tick_nohz_get_sleep_length(&delta_next);
+	delta = tick_nohz_get_sleep_length(&delta_tick);
+	if (unlikely(delta < 0)) {
+		delta = 0;
+		delta_tick = 0;
+	}
+	data->next_timer_ns = delta;
 
 	nr_iowaiters = nr_iowait_cpu(dev->cpu);
 	data->bucket = which_bucket(data->next_timer_ns, nr_iowaiters);
@@ -318,7 +323,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		 * state selection.
 		 */
 		if (predicted_ns < TICK_NSEC)
-			predicted_ns = delta_next;
+			predicted_ns = data->next_timer_ns;
 	} else {
 		/*
 		 * Use the performance multiplier and the user-configurable
@@ -377,7 +382,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 			 * stuck in the shallow one for too long.
 			 */
 			if (drv->states[idx].target_residency_ns < TICK_NSEC &&
-			    s->target_residency_ns <= delta_next)
+			    s->target_residency_ns <= delta_tick)
 				idx = i;
 
 			return idx;
@@ -399,7 +404,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	     predicted_ns < TICK_NSEC) && !tick_nohz_tick_stopped()) {
 		*stop_tick = false;
 
-		if (idx > 0 && drv->states[idx].target_residency_ns > delta_next) {
+		if (idx > 0 && drv->states[idx].target_residency_ns > delta_tick) {
 			/*
 			 * The tick is not going to be stopped and the target
 			 * residency of the state to be returned is not within
@@ -411,7 +416,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 					continue;
 
 				idx = i;
-				if (drv->states[i].target_residency_ns <= delta_next)
+				if (drv->states[i].target_residency_ns <= delta_tick)
 					break;
 			}
 		}
diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c
index 6deaaf5f05b5..ac4bb27d69b0 100644
--- a/drivers/cpuidle/governors/teo.c
+++ b/drivers/cpuidle/governors/teo.c
@@ -100,8 +100,8 @@ struct teo_idle_state {
  * @intervals: Saved idle duration values.
  */
 struct teo_cpu {
-	u64 time_span_ns;
-	u64 sleep_length_ns;
+	s64 time_span_ns;
+	s64 sleep_length_ns;
 	struct teo_idle_state states[CPUIDLE_STATE_MAX];
 	int interval_idx;
 	u64 intervals[INTERVALS];
@@ -117,7 +117,8 @@ static DEFINE_PER_CPU(struct teo_cpu, teo_cpus);
 static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {
 	struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu);
-	int i, idx_hit = -1, idx_timer = -1;
+	int i, idx_hit = 0, idx_timer = 0;
+	unsigned int hits, misses;
 	u64 measured_ns;
 
 	if (cpu_data->time_span_ns >= cpu_data->sleep_length_ns) {
@@ -174,25 +175,22 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	 * also increase the "early hits" metric for the state that actually
 	 * matches the measured idle duration.
 	 */
-	if (idx_timer >= 0) {
-		unsigned int hits = cpu_data->states[idx_timer].hits;
-		unsigned int misses = cpu_data->states[idx_timer].misses;
-
-		hits -= hits >> DECAY_SHIFT;
-		misses -= misses >> DECAY_SHIFT;
-
-		if (idx_timer > idx_hit) {
-			misses += PULSE;
-			if (idx_hit >= 0)
-				cpu_data->states[idx_hit].early_hits += PULSE;
-		} else {
-			hits += PULSE;
-		}
+	hits = cpu_data->states[idx_timer].hits;
+	hits -= hits >> DECAY_SHIFT;
+
+	misses = cpu_data->states[idx_timer].misses;
+	misses -= misses >> DECAY_SHIFT;
 
-		cpu_data->states[idx_timer].misses = misses;
-		cpu_data->states[idx_timer].hits = hits;
+	if (idx_timer == idx_hit) {
+		hits += PULSE;
+	} else {
+		misses += PULSE;
+		cpu_data->states[idx_hit].early_hits += PULSE;
 	}
 
+	cpu_data->states[idx_timer].misses = misses;
+	cpu_data->states[idx_timer].hits = hits;
+
 	/*
 	 * Save idle duration values corresponding to non-timer wakeups for
 	 * pattern detection.
@@ -216,7 +214,7 @@ static bool teo_time_ok(u64 interval_ns)
  */
 static int teo_find_shallower_state(struct cpuidle_driver *drv,
 				    struct cpuidle_device *dev, int state_idx,
-				    u64 duration_ns)
+				    s64 duration_ns)
 {
 	int i;
 
@@ -242,10 +240,10 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 {
 	struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu);
 	s64 latency_req = cpuidle_governor_latency_req(dev->cpu);
-	u64 duration_ns;
+	int max_early_idx, prev_max_early_idx, constraint_idx, idx0, idx, i;
 	unsigned int hits, misses, early_hits;
-	int max_early_idx, prev_max_early_idx, constraint_idx, idx, i;
 	ktime_t delta_tick;
+	s64 duration_ns;
 
 	if (dev->last_state_idx >= 0) {
 		teo_update(drv, dev);
@@ -264,6 +262,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	prev_max_early_idx = -1;
 	constraint_idx = drv->state_count;
 	idx = -1;
+	idx0 = idx;
 
 	for (i = 0; i < drv->state_count; i++) {
 		struct cpuidle_state *s = &drv->states[i];
@@ -324,6 +323,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 			idx = i; /* first enabled state */
 			hits = cpu_data->states[i].hits;
 			misses = cpu_data->states[i].misses;
+			idx0 = i;
 		}
 
 		if (s->target_residency_ns > duration_ns)
@@ -376,11 +376,16 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 
 	if (idx < 0) {
 		idx = 0; /* No states enabled. Must use 0. */
-	} else if (idx > 0) {
+	} else if (idx > idx0) {
 		unsigned int count = 0;
 		u64 sum = 0;
 
 		/*
+		 * The target residencies of at least two different enabled idle
+		 * states are less than or equal to the current expected idle
+		 * duration.  Try to refine the selection using the most recent
+		 * measured idle duration values.
+		 *
 		 * Count and sum the most recent idle duration values less than
 		 * the current expected idle duration value.
 		 */
@@ -428,7 +433,8 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		 * till the closest timer including the tick, try to correct
 		 * that.
 		 */
-		if (idx > 0 && drv->states[idx].target_residency_ns > delta_tick)
+		if (idx > idx0 &&
+		    drv->states[idx].target_residency_ns > delta_tick)
 			idx = teo_find_shallower_state(drv, dev, idx, delta_tick);
 	}
 
diff --git a/drivers/devfreq/Kconfig b/drivers/devfreq/Kconfig
index 00704efe6398..20373a893b44 100644
--- a/drivers/devfreq/Kconfig
+++ b/drivers/devfreq/Kconfig
@@ -62,7 +62,7 @@ config DEVFREQ_GOV_USERSPACE
 	help
 	  Sets the frequency at the user specified one.
 	  This governor returns the user configured frequency if there
-	  has been an input to /sys/devices/.../power/devfreq_set_freq.
+	  has been an input to /sys/devices/.../userspace/set_freq.
 	  Otherwise, the governor does not change the frequency
 	  given at the initialization.
 
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index bf3047896e41..fe08c46642f7 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -11,6 +11,7 @@
 #include <linux/kmod.h>
 #include <linux/sched.h>
 #include <linux/debugfs.h>
+#include <linux/devfreq_cooling.h>
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/init.h>
@@ -387,7 +388,7 @@ static int devfreq_set_target(struct devfreq *devfreq, unsigned long new_freq,
 	devfreq->previous_freq = new_freq;
 
 	if (devfreq->suspend_freq)
-		devfreq->resume_freq = cur_freq;
+		devfreq->resume_freq = new_freq;
 
 	return err;
 }
@@ -821,7 +822,8 @@ struct devfreq *devfreq_add_device(struct device *dev,
 
 	if (devfreq->profile->timer < 0
 		|| devfreq->profile->timer >= DEVFREQ_TIMER_NUM) {
-		goto err_out;
+		mutex_unlock(&devfreq->lock);
+		goto err_dev;
 	}
 
 	if (!devfreq->profile->max_state && !devfreq->profile->freq_table) {
@@ -935,6 +937,12 @@ struct devfreq *devfreq_add_device(struct device *dev,
 
 	mutex_unlock(&devfreq_list_lock);
 
+	if (devfreq->profile->is_cooling_device) {
+		devfreq->cdev = devfreq_cooling_em_register(devfreq, NULL);
+		if (IS_ERR(devfreq->cdev))
+			devfreq->cdev = NULL;
+	}
+
 	return devfreq;
 
 err_init:
@@ -960,6 +968,8 @@ int devfreq_remove_device(struct devfreq *devfreq)
 	if (!devfreq)
 		return -EINVAL;
 
+	devfreq_cooling_unregister(devfreq->cdev);
+
 	if (devfreq->governor) {
 		devfreq->governor->event_handler(devfreq,
 						 DEVFREQ_GOV_STOP, NULL);
diff --git a/drivers/devfreq/governor.h b/drivers/devfreq/governor.h
index 70f44b3ca42e..2d69a0ce6291 100644
--- a/drivers/devfreq/governor.h
+++ b/drivers/devfreq/governor.h
@@ -57,8 +57,6 @@
  *			Basically, get_target_freq will run
  *			devfreq_dev_profile.get_dev_status() to get the
  *			status of the device (load = busy_time / total_time).
- *			If no_central_polling is set, this callback is called
- *			only with update_devfreq() notified by OPP.
  * @event_handler:      Callback for devfreq core framework to notify events
  *                      to governors. Events include per device governor
  *                      init and exit, opp changes out of devfreq, suspend
@@ -91,6 +89,9 @@ int devfreq_update_target(struct devfreq *devfreq, unsigned long freq);
 
 static inline int devfreq_update_stats(struct devfreq *df)
 {
+	if (!df->profile->get_dev_status)
+		return -EINVAL;
+
 	return df->profile->get_dev_status(df->dev.parent, &df->last_status);
 }
 #endif /* _GOVERNOR_H */
diff --git a/drivers/devfreq/imx-bus.c b/drivers/devfreq/imx-bus.c
index 4f38455ad742..3fc3fd77492d 100644
--- a/drivers/devfreq/imx-bus.c
+++ b/drivers/devfreq/imx-bus.c
@@ -169,7 +169,7 @@ static struct platform_driver imx_bus_platdrv = {
 	.probe		= imx_bus_probe,
 	.driver = {
 		.name	= "imx-bus-devfreq",
-		.of_match_table = of_match_ptr(imx_bus_of_match),
+		.of_match_table = imx_bus_of_match,
 	},
 };
 module_platform_driver(imx_bus_platdrv);
diff --git a/drivers/devfreq/imx8m-ddrc.c b/drivers/devfreq/imx8m-ddrc.c
index bc82d3653bff..16636973eb10 100644
--- a/drivers/devfreq/imx8m-ddrc.c
+++ b/drivers/devfreq/imx8m-ddrc.c
@@ -280,18 +280,6 @@ static int imx8m_ddrc_get_cur_freq(struct device *dev, unsigned long *freq)
 	return 0;
 }
 
-static int imx8m_ddrc_get_dev_status(struct device *dev,
-				     struct devfreq_dev_status *stat)
-{
-	struct imx8m_ddrc *priv = dev_get_drvdata(dev);
-
-	stat->busy_time = 0;
-	stat->total_time = 0;
-	stat->current_frequency = clk_get_rate(priv->dram_core);
-
-	return 0;
-}
-
 static int imx8m_ddrc_init_freq_info(struct device *dev)
 {
 	struct imx8m_ddrc *priv = dev_get_drvdata(dev);
@@ -429,9 +417,7 @@ static int imx8m_ddrc_probe(struct platform_device *pdev)
 	if (ret < 0)
 		goto err;
 
-	priv->profile.polling_ms = 1000;
 	priv->profile.target = imx8m_ddrc_target;
-	priv->profile.get_dev_status = imx8m_ddrc_get_dev_status;
 	priv->profile.exit = imx8m_ddrc_exit;
 	priv->profile.get_cur_freq = imx8m_ddrc_get_cur_freq;
 	priv->profile.initial_freq = clk_get_rate(priv->dram_core);
@@ -461,7 +447,7 @@ static struct platform_driver imx8m_ddrc_platdrv = {
 	.probe		= imx8m_ddrc_probe,
 	.driver = {
 		.name	= "imx8m-ddrc-devfreq",
-		.of_match_table = of_match_ptr(imx8m_ddrc_of_match),
+		.of_match_table = imx8m_ddrc_of_match,
 	},
 };
 module_platform_driver(imx8m_ddrc_platdrv);
diff --git a/drivers/devfreq/rk3399_dmc.c b/drivers/devfreq/rk3399_dmc.c
index 9e9d3b4c6d48..293857ebfd75 100644
--- a/drivers/devfreq/rk3399_dmc.c
+++ b/drivers/devfreq/rk3399_dmc.c
@@ -324,22 +324,14 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 	mutex_init(&data->lock);
 
 	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);
-	}
+	if (IS_ERR(data->vdd_center))
+		return dev_err_probe(dev, PTR_ERR(data->vdd_center),
+				     "Cannot get the regulator \"center\"\n");
 
 	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);
-	}
+	if (IS_ERR(data->dmc_clk))
+		return dev_err_probe(dev, PTR_ERR(data->dmc_clk),
+				     "Cannot get the clk dmc_clk\n");
 
 	data->edev = devfreq_event_get_edev_by_phandle(dev, "devfreq-events", 0);
 	if (IS_ERR(data->edev))
diff --git a/drivers/gpu/drm/lima/lima_devfreq.c b/drivers/gpu/drm/lima/lima_devfreq.c
index 5686ad4aaf7c..dbc1d1eb9543 100644
--- a/drivers/gpu/drm/lima/lima_devfreq.c
+++ b/drivers/gpu/drm/lima/lima_devfreq.c
@@ -99,20 +99,12 @@ void lima_devfreq_fini(struct lima_device *ldev)
 		devm_devfreq_remove_device(ldev->dev, devfreq->devfreq);
 		devfreq->devfreq = NULL;
 	}
-
-	dev_pm_opp_of_remove_table(ldev->dev);
-
-	dev_pm_opp_put_regulators(devfreq->regulators_opp_table);
-	dev_pm_opp_put_clkname(devfreq->clkname_opp_table);
-	devfreq->regulators_opp_table = NULL;
-	devfreq->clkname_opp_table = NULL;
 }
 
 int lima_devfreq_init(struct lima_device *ldev)
 {
 	struct thermal_cooling_device *cooling;
 	struct device *dev = ldev->dev;
-	struct opp_table *opp_table;
 	struct devfreq *devfreq;
 	struct lima_devfreq *ldevfreq = &ldev->devfreq;
 	struct dev_pm_opp *opp;
@@ -125,40 +117,28 @@ int lima_devfreq_init(struct lima_device *ldev)
 
 	spin_lock_init(&ldevfreq->lock);
 
-	opp_table = dev_pm_opp_set_clkname(dev, "core");
-	if (IS_ERR(opp_table)) {
-		ret = PTR_ERR(opp_table);
-		goto err_fini;
-	}
-
-	ldevfreq->clkname_opp_table = opp_table;
-
-	opp_table = dev_pm_opp_set_regulators(dev,
-					      (const char *[]){ "mali" },
-					      1);
-	if (IS_ERR(opp_table)) {
-		ret = PTR_ERR(opp_table);
+	ret = devm_pm_opp_set_clkname(dev, "core");
+	if (ret)
+		return ret;
 
+	ret = devm_pm_opp_set_regulators(dev, (const char *[]){ "mali" }, 1);
+	if (ret) {
 		/* Continue if the optional regulator is missing */
 		if (ret != -ENODEV)
-			goto err_fini;
-	} else {
-		ldevfreq->regulators_opp_table = opp_table;
+			return ret;
 	}
 
-	ret = dev_pm_opp_of_add_table(dev);
+	ret = devm_pm_opp_of_add_table(dev);
 	if (ret)
-		goto err_fini;
+		return ret;
 
 	lima_devfreq_reset(ldevfreq);
 
 	cur_freq = clk_get_rate(ldev->clk_gpu);
 
 	opp = devfreq_recommended_opp(dev, &cur_freq, 0);
-	if (IS_ERR(opp)) {
-		ret = PTR_ERR(opp);
-		goto err_fini;
-	}
+	if (IS_ERR(opp))
+		return PTR_ERR(opp);
 
 	lima_devfreq_profile.initial_freq = cur_freq;
 	dev_pm_opp_put(opp);
@@ -167,8 +147,7 @@ int lima_devfreq_init(struct lima_device *ldev)
 					  DEVFREQ_GOV_SIMPLE_ONDEMAND, NULL);
 	if (IS_ERR(devfreq)) {
 		dev_err(dev, "Couldn't initialize GPU devfreq\n");
-		ret = PTR_ERR(devfreq);
-		goto err_fini;
+		return PTR_ERR(devfreq);
 	}
 
 	ldevfreq->devfreq = devfreq;
@@ -180,10 +159,6 @@ int lima_devfreq_init(struct lima_device *ldev)
 		ldevfreq->cooling = cooling;
 
 	return 0;
-
-err_fini:
-	lima_devfreq_fini(ldev);
-	return ret;
 }
 
 void lima_devfreq_record_busy(struct lima_devfreq *devfreq)
diff --git a/drivers/gpu/drm/lima/lima_devfreq.h b/drivers/gpu/drm/lima/lima_devfreq.h
index 2d9b3008ce77..688ee71e263a 100644
--- a/drivers/gpu/drm/lima/lima_devfreq.h
+++ b/drivers/gpu/drm/lima/lima_devfreq.h
@@ -8,15 +8,12 @@
 #include <linux/ktime.h>
 
 struct devfreq;
-struct opp_table;
 struct thermal_cooling_device;
 
 struct lima_device;
 
 struct lima_devfreq {
 	struct devfreq *devfreq;
-	struct opp_table *clkname_opp_table;
-	struct opp_table *regulators_opp_table;
 	struct thermal_cooling_device *cooling;
 
 	ktime_t busy_time;
diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
index 56b3f5935703..c878391f3e8c 100644
--- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c
+++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
@@ -89,29 +89,25 @@ int panfrost_devfreq_init(struct panfrost_device *pfdev)
 	unsigned long cur_freq;
 	struct device *dev = &pfdev->pdev->dev;
 	struct devfreq *devfreq;
-	struct opp_table *opp_table;
 	struct thermal_cooling_device *cooling;
 	struct panfrost_devfreq *pfdevfreq = &pfdev->pfdevfreq;
 
-	opp_table = dev_pm_opp_set_regulators(dev, pfdev->comp->supply_names,
-					      pfdev->comp->num_supplies);
-	if (IS_ERR(opp_table)) {
-		ret = PTR_ERR(opp_table);
+	ret = devm_pm_opp_set_regulators(dev, pfdev->comp->supply_names,
+					 pfdev->comp->num_supplies);
+	if (ret) {
 		/* Continue if the optional regulator is missing */
 		if (ret != -ENODEV) {
 			DRM_DEV_ERROR(dev, "Couldn't set OPP regulators\n");
-			goto err_fini;
+			return ret;
 		}
-	} else {
-		pfdevfreq->regulators_opp_table = opp_table;
 	}
 
-	ret = dev_pm_opp_of_add_table(dev);
+	ret = devm_pm_opp_of_add_table(dev);
 	if (ret) {
 		/* Optional, continue without devfreq */
 		if (ret == -ENODEV)
 			ret = 0;
-		goto err_fini;
+		return ret;
 	}
 	pfdevfreq->opp_of_table_added = true;
 
@@ -122,10 +118,8 @@ int panfrost_devfreq_init(struct panfrost_device *pfdev)
 	cur_freq = clk_get_rate(pfdev->clock);
 
 	opp = devfreq_recommended_opp(dev, &cur_freq, 0);
-	if (IS_ERR(opp)) {
-		ret = PTR_ERR(opp);
-		goto err_fini;
-	}
+	if (IS_ERR(opp))
+		return PTR_ERR(opp);
 
 	panfrost_devfreq_profile.initial_freq = cur_freq;
 	dev_pm_opp_put(opp);
@@ -134,8 +128,7 @@ int panfrost_devfreq_init(struct panfrost_device *pfdev)
 					  DEVFREQ_GOV_SIMPLE_ONDEMAND, NULL);
 	if (IS_ERR(devfreq)) {
 		DRM_DEV_ERROR(dev, "Couldn't initialize GPU devfreq\n");
-		ret = PTR_ERR(devfreq);
-		goto err_fini;
+		return PTR_ERR(devfreq);
 	}
 	pfdevfreq->devfreq = devfreq;
 
@@ -146,10 +139,6 @@ int panfrost_devfreq_init(struct panfrost_device *pfdev)
 		pfdevfreq->cooling = cooling;
 
 	return 0;
-
-err_fini:
-	panfrost_devfreq_fini(pfdev);
-	return ret;
 }
 
 void panfrost_devfreq_fini(struct panfrost_device *pfdev)
@@ -160,14 +149,6 @@ void panfrost_devfreq_fini(struct panfrost_device *pfdev)
 		devfreq_cooling_unregister(pfdevfreq->cooling);
 		pfdevfreq->cooling = NULL;
 	}
-
-	if (pfdevfreq->opp_of_table_added) {
-		dev_pm_opp_of_remove_table(&pfdev->pdev->dev);
-		pfdevfreq->opp_of_table_added = false;
-	}
-
-	dev_pm_opp_put_regulators(pfdevfreq->regulators_opp_table);
-	pfdevfreq->regulators_opp_table = NULL;
 }
 
 void panfrost_devfreq_resume(struct panfrost_device *pfdev)
diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.h b/drivers/gpu/drm/panfrost/panfrost_devfreq.h
index db6ea48e21f9..210269944687 100644
--- a/drivers/gpu/drm/panfrost/panfrost_devfreq.h
+++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.h
@@ -8,14 +8,12 @@
 #include <linux/ktime.h>
 
 struct devfreq;
-struct opp_table;
 struct thermal_cooling_device;
 
 struct panfrost_device;
 
 struct panfrost_devfreq {
 	struct devfreq *devfreq;
-	struct opp_table *regulators_opp_table;
 	struct thermal_cooling_device *cooling;
 	bool opp_of_table_added;
 
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 3273360f30f7..ec1b9d306ba6 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -744,8 +744,8 @@ static struct cpuidle_state icx_cstates[] __initdata = {
 		.name = "C6",
 		.desc = "MWAIT 0x20",
 		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
-		.exit_latency = 128,
-		.target_residency = 384,
+		.exit_latency = 170,
+		.target_residency = 600,
 		.enter = &intel_idle,
 		.enter_s2idle = intel_idle_s2idle, },
 	{
@@ -1156,6 +1156,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE,		&idle_cpu_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X,		&idle_cpu_skx),
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		&idle_cpu_icx),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D,		&idle_cpu_icx),
 	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL,	&idle_cpu_knl),
 	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM,	&idle_cpu_knl),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT,	&idle_cpu_bxt),
diff --git a/drivers/memory/samsung/exynos5422-dmc.c b/drivers/memory/samsung/exynos5422-dmc.c
index dee503640e12..9c8318923ed0 100644
--- a/drivers/memory/samsung/exynos5422-dmc.c
+++ b/drivers/memory/samsung/exynos5422-dmc.c
@@ -343,7 +343,7 @@ static int exynos5_init_freq_table(struct exynos5_dmc *dmc,
 	int idx;
 	unsigned long freq;
 
-	ret = dev_pm_opp_of_add_table(dmc->dev);
+	ret = devm_pm_opp_of_add_table(dmc->dev);
 	if (ret < 0) {
 		dev_err(dmc->dev, "Failed to get OPP table\n");
 		return ret;
@@ -354,7 +354,7 @@ static int exynos5_init_freq_table(struct exynos5_dmc *dmc,
 	dmc->opp = devm_kmalloc_array(dmc->dev, dmc->opp_count,
 				      sizeof(struct dmc_opp_table), GFP_KERNEL);
 	if (!dmc->opp)
-		goto err_opp;
+		return -ENOMEM;
 
 	idx = dmc->opp_count - 1;
 	for (i = 0, freq = ULONG_MAX; i < dmc->opp_count; i++, freq--) {
@@ -362,7 +362,7 @@ static int exynos5_init_freq_table(struct exynos5_dmc *dmc,
 
 		opp = dev_pm_opp_find_freq_floor(dmc->dev, &freq);
 		if (IS_ERR(opp))
-			goto err_opp;
+			return PTR_ERR(opp);
 
 		dmc->opp[idx - i].freq_hz = freq;
 		dmc->opp[idx - i].volt_uv = dev_pm_opp_get_voltage(opp);
@@ -371,11 +371,6 @@ static int exynos5_init_freq_table(struct exynos5_dmc *dmc,
 	}
 
 	return 0;
-
-err_opp:
-	dev_pm_opp_of_remove_table(dmc->dev);
-
-	return -EINVAL;
 }
 
 /**
@@ -1569,8 +1564,6 @@ static int exynos5_dmc_remove(struct platform_device *pdev)
 	clk_disable_unprepare(dmc->mout_bpll);
 	clk_disable_unprepare(dmc->fout_bpll);
 
-	dev_pm_opp_remove_table(dmc->dev);
-
 	return 0;
 }
 
diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c
index 5e1da4df096f..d170c919e6e4 100644
--- a/drivers/mmc/host/sdhci-msm.c
+++ b/drivers/mmc/host/sdhci-msm.c
@@ -264,7 +264,6 @@ struct sdhci_msm_host {
 	struct clk_bulk_data bulk_clks[5];
 	unsigned long clk_rate;
 	struct mmc_host *mmc;
-	struct opp_table *opp_table;
 	bool use_14lpp_dll_reset;
 	bool tuning_done;
 	bool calibration_done;
@@ -2551,17 +2550,15 @@ static int sdhci_msm_probe(struct platform_device *pdev)
 	if (ret)
 		goto bus_clk_disable;
 
-	msm_host->opp_table = dev_pm_opp_set_clkname(&pdev->dev, "core");
-	if (IS_ERR(msm_host->opp_table)) {
-		ret = PTR_ERR(msm_host->opp_table);
+	ret = devm_pm_opp_set_clkname(&pdev->dev, "core");
+	if (ret)
 		goto bus_clk_disable;
-	}
 
 	/* OPP table is optional */
-	ret = dev_pm_opp_of_add_table(&pdev->dev);
+	ret = devm_pm_opp_of_add_table(&pdev->dev);
 	if (ret && ret != -ENODEV) {
 		dev_err(&pdev->dev, "Invalid OPP table in Device tree\n");
-		goto opp_put_clkname;
+		goto bus_clk_disable;
 	}
 
 	/* Vote for maximum clock rate for maximum performance */
@@ -2587,7 +2584,7 @@ static int sdhci_msm_probe(struct platform_device *pdev)
 	ret = clk_bulk_prepare_enable(ARRAY_SIZE(msm_host->bulk_clks),
 				      msm_host->bulk_clks);
 	if (ret)
-		goto opp_cleanup;
+		goto bus_clk_disable;
 
 	/*
 	 * xo clock is needed for FLL feature of cm_dll.
@@ -2732,10 +2729,6 @@ pm_runtime_disable:
 clk_disable:
 	clk_bulk_disable_unprepare(ARRAY_SIZE(msm_host->bulk_clks),
 				   msm_host->bulk_clks);
-opp_cleanup:
-	dev_pm_opp_of_remove_table(&pdev->dev);
-opp_put_clkname:
-	dev_pm_opp_put_clkname(msm_host->opp_table);
 bus_clk_disable:
 	if (!IS_ERR(msm_host->bus_clk))
 		clk_disable_unprepare(msm_host->bus_clk);
@@ -2754,8 +2747,6 @@ static int sdhci_msm_remove(struct platform_device *pdev)
 
 	sdhci_remove_host(host, dead);
 
-	dev_pm_opp_of_remove_table(&pdev->dev);
-	dev_pm_opp_put_clkname(msm_host->opp_table);
 	pm_runtime_get_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_put_noidle(&pdev->dev);
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 1556998425d5..e366218d6736 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -1857,6 +1857,35 @@ void dev_pm_opp_put_supported_hw(struct opp_table *opp_table)
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_put_supported_hw);
 
+static void devm_pm_opp_supported_hw_release(void *data)
+{
+	dev_pm_opp_put_supported_hw(data);
+}
+
+/**
+ * devm_pm_opp_set_supported_hw() - Set supported platforms
+ * @dev: Device for which supported-hw has to be set.
+ * @versions: Array of hierarchy of versions to match.
+ * @count: Number of elements in the array.
+ *
+ * This is a resource-managed variant of dev_pm_opp_set_supported_hw().
+ *
+ * Return: 0 on success and errorno otherwise.
+ */
+int devm_pm_opp_set_supported_hw(struct device *dev, const u32 *versions,
+				 unsigned int count)
+{
+	struct opp_table *opp_table;
+
+	opp_table = dev_pm_opp_set_supported_hw(dev, versions, count);
+	if (IS_ERR(opp_table))
+		return PTR_ERR(opp_table);
+
+	return devm_add_action_or_reset(dev, devm_pm_opp_supported_hw_release,
+					opp_table);
+}
+EXPORT_SYMBOL_GPL(devm_pm_opp_set_supported_hw);
+
 /**
  * dev_pm_opp_set_prop_name() - Set prop-extn name
  * @dev: Device for which the prop-name has to be set.
@@ -2047,6 +2076,36 @@ put_opp_table:
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulators);
 
+static void devm_pm_opp_regulators_release(void *data)
+{
+	dev_pm_opp_put_regulators(data);
+}
+
+/**
+ * devm_pm_opp_set_regulators() - Set regulator names for the device
+ * @dev: Device for which regulator name is being set.
+ * @names: Array of pointers to the names of the regulator.
+ * @count: Number of regulators.
+ *
+ * This is a resource-managed variant of dev_pm_opp_set_regulators().
+ *
+ * Return: 0 on success and errorno otherwise.
+ */
+int devm_pm_opp_set_regulators(struct device *dev,
+			       const char * const names[],
+			       unsigned int count)
+{
+	struct opp_table *opp_table;
+
+	opp_table = dev_pm_opp_set_regulators(dev, names, count);
+	if (IS_ERR(opp_table))
+		return PTR_ERR(opp_table);
+
+	return devm_add_action_or_reset(dev, devm_pm_opp_regulators_release,
+					opp_table);
+}
+EXPORT_SYMBOL_GPL(devm_pm_opp_set_regulators);
+
 /**
  * dev_pm_opp_set_clkname() - Set clk name for the device
  * @dev: Device for which clk name is being set.
@@ -2119,6 +2178,33 @@ void dev_pm_opp_put_clkname(struct opp_table *opp_table)
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_put_clkname);
 
+static void devm_pm_opp_clkname_release(void *data)
+{
+	dev_pm_opp_put_clkname(data);
+}
+
+/**
+ * devm_pm_opp_set_clkname() - Set clk name for the device
+ * @dev: Device for which clk name is being set.
+ * @name: Clk name.
+ *
+ * This is a resource-managed variant of dev_pm_opp_set_clkname().
+ *
+ * Return: 0 on success and errorno otherwise.
+ */
+int devm_pm_opp_set_clkname(struct device *dev, const char *name)
+{
+	struct opp_table *opp_table;
+
+	opp_table = dev_pm_opp_set_clkname(dev, name);
+	if (IS_ERR(opp_table))
+		return PTR_ERR(opp_table);
+
+	return devm_add_action_or_reset(dev, devm_pm_opp_clkname_release,
+					opp_table);
+}
+EXPORT_SYMBOL_GPL(devm_pm_opp_set_clkname);
+
 /**
  * dev_pm_opp_register_set_opp_helper() - Register custom set OPP helper
  * @dev: Device for which the helper is getting registered.
@@ -2209,25 +2295,19 @@ static void devm_pm_opp_unregister_set_opp_helper(void *data)
  *
  * This is a resource-managed version of dev_pm_opp_register_set_opp_helper().
  *
- * Return: pointer to 'struct opp_table' on success and errorno otherwise.
+ * Return: 0 on success and errorno otherwise.
  */
-struct opp_table *
-devm_pm_opp_register_set_opp_helper(struct device *dev,
-				    int (*set_opp)(struct dev_pm_set_opp_data *data))
+int devm_pm_opp_register_set_opp_helper(struct device *dev,
+					int (*set_opp)(struct dev_pm_set_opp_data *data))
 {
 	struct opp_table *opp_table;
-	int err;
 
 	opp_table = dev_pm_opp_register_set_opp_helper(dev, set_opp);
 	if (IS_ERR(opp_table))
-		return opp_table;
-
-	err = devm_add_action_or_reset(dev, devm_pm_opp_unregister_set_opp_helper,
-				       opp_table);
-	if (err)
-		return ERR_PTR(err);
+		return PTR_ERR(opp_table);
 
-	return opp_table;
+	return devm_add_action_or_reset(dev, devm_pm_opp_unregister_set_opp_helper,
+					opp_table);
 }
 EXPORT_SYMBOL_GPL(devm_pm_opp_register_set_opp_helper);
 
@@ -2380,25 +2460,19 @@ static void devm_pm_opp_detach_genpd(void *data)
  *
  * This is a resource-managed version of dev_pm_opp_attach_genpd().
  *
- * Return: pointer to 'struct opp_table' on success and errorno otherwise.
+ * Return: 0 on success and errorno otherwise.
  */
-struct opp_table *
-devm_pm_opp_attach_genpd(struct device *dev, const char **names,
-			 struct device ***virt_devs)
+int devm_pm_opp_attach_genpd(struct device *dev, const char **names,
+			     struct device ***virt_devs)
 {
 	struct opp_table *opp_table;
-	int err;
 
 	opp_table = dev_pm_opp_attach_genpd(dev, names, virt_devs);
 	if (IS_ERR(opp_table))
-		return opp_table;
-
-	err = devm_add_action_or_reset(dev, devm_pm_opp_detach_genpd,
-				       opp_table);
-	if (err)
-		return ERR_PTR(err);
+		return PTR_ERR(opp_table);
 
-	return opp_table;
+	return devm_add_action_or_reset(dev, devm_pm_opp_detach_genpd,
+					opp_table);
 }
 EXPORT_SYMBOL_GPL(devm_pm_opp_attach_genpd);
 
diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index f480c10e6314..c582a9ca397b 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -1104,6 +1104,42 @@ static int _of_add_table_indexed(struct device *dev, int index, bool getclk)
 	return ret;
 }
 
+static void devm_pm_opp_of_table_release(void *data)
+{
+	dev_pm_opp_of_remove_table(data);
+}
+
+/**
+ * devm_pm_opp_of_add_table() - Initialize opp table from device tree
+ * @dev:	device pointer used to lookup OPP table.
+ *
+ * Register the initial OPP table with the OPP library for given device.
+ *
+ * The opp_table structure will be freed after the device is destroyed.
+ *
+ * Return:
+ * 0		On success OR
+ *		Duplicate OPPs (both freq and volt are same) and opp->available
+ * -EEXIST	Freq are same and volt are different OR
+ *		Duplicate OPPs (both freq and volt are same) and !opp->available
+ * -ENOMEM	Memory allocation failure
+ * -ENODEV	when 'operating-points' property is not found or is invalid data
+ *		in device node.
+ * -ENODATA	when empty 'operating-points' property is found
+ * -EINVAL	when invalid entries are found in opp-v2 table
+ */
+int devm_pm_opp_of_add_table(struct device *dev)
+{
+	int ret;
+
+	ret = dev_pm_opp_of_add_table(dev);
+	if (ret)
+		return ret;
+
+	return devm_add_action_or_reset(dev, devm_pm_opp_of_table_release, dev);
+}
+EXPORT_SYMBOL_GPL(devm_pm_opp_of_add_table);
+
 /**
  * dev_pm_opp_of_add_table() - Initialize opp table from device tree
  * @dev:	device pointer used to lookup OPP table.
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 16a17215f633..e4d4e399004b 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1870,20 +1870,10 @@ static int pci_enable_device_flags(struct pci_dev *dev, unsigned long flags)
 	int err;
 	int i, bars = 0;
 
-	/*
-	 * Power state could be unknown at this point, either due to a fresh
-	 * boot or a device removal call.  So get the current power state
-	 * so that things like MSI message writing will behave as expected
-	 * (e.g. if the device really is in D0 at enable time).
-	 */
-	if (dev->pm_cap) {
-		u16 pmcsr;
-		pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr);
-		dev->current_state = (pmcsr & PCI_PM_CTRL_STATE_MASK);
-	}
-
-	if (atomic_inc_return(&dev->enable_cnt) > 1)
+	if (atomic_inc_return(&dev->enable_cnt) > 1) {
+		pci_update_current_state(dev, dev->current_state);
 		return 0;		/* already enabled */
+	}
 
 	bridge = pci_upstream_bridge(dev);
 	if (bridge)
diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index fdda2a737186..73cf68af9770 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -1069,6 +1069,7 @@ static const struct x86_cpu_id rapl_ids[] __initconst = {
 
 	X86_MATCH_VENDOR_FAM(AMD, 0x17, &rapl_defaults_amd),
 	X86_MATCH_VENDOR_FAM(AMD, 0x19, &rapl_defaults_amd),
+	X86_MATCH_VENDOR_FAM(HYGON, 0x18, &rapl_defaults_amd),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, rapl_ids);
diff --git a/drivers/powercap/intel_rapl_msr.c b/drivers/powercap/intel_rapl_msr.c
index 78213d4b5b16..cc3b22881bfe 100644
--- a/drivers/powercap/intel_rapl_msr.c
+++ b/drivers/powercap/intel_rapl_msr.c
@@ -150,6 +150,7 @@ static int rapl_msr_probe(struct platform_device *pdev)
 	case X86_VENDOR_INTEL:
 		rapl_msr_priv = &rapl_msr_priv_intel;
 		break;
+	case X86_VENDOR_HYGON:
 	case X86_VENDOR_AMD:
 		rapl_msr_priv = &rapl_msr_priv_amd;
 		break;
diff --git a/drivers/spi/spi-geni-qcom.c b/drivers/spi/spi-geni-qcom.c
index 881f645661cc..3d0d8ddd5772 100644
--- a/drivers/spi/spi-geni-qcom.c
+++ b/drivers/spi/spi-geni-qcom.c
@@ -691,14 +691,15 @@ static int spi_geni_probe(struct platform_device *pdev)
 	mas->se.wrapper = dev_get_drvdata(dev->parent);
 	mas->se.base = base;
 	mas->se.clk = clk;
-	mas->se.opp_table = dev_pm_opp_set_clkname(&pdev->dev, "se");
-	if (IS_ERR(mas->se.opp_table))
-		return PTR_ERR(mas->se.opp_table);
+
+	ret = devm_pm_opp_set_clkname(&pdev->dev, "se");
+	if (ret)
+		return ret;
 	/* OPP table is optional */
-	ret = dev_pm_opp_of_add_table(&pdev->dev);
+	ret = devm_pm_opp_of_add_table(&pdev->dev);
 	if (ret && ret != -ENODEV) {
 		dev_err(&pdev->dev, "invalid OPP table in device tree\n");
-		goto put_clkname;
+		return ret;
 	}
 
 	spi->bus_num = -1;
@@ -750,9 +751,6 @@ spi_geni_probe_free_irq:
 	free_irq(mas->irq, spi);
 spi_geni_probe_runtime_disable:
 	pm_runtime_disable(dev);
-	dev_pm_opp_of_remove_table(&pdev->dev);
-put_clkname:
-	dev_pm_opp_put_clkname(mas->se.opp_table);
 	return ret;
 }
 
@@ -766,8 +764,6 @@ static int spi_geni_remove(struct platform_device *pdev)
 
 	free_irq(mas->irq, spi);
 	pm_runtime_disable(&pdev->dev);
-	dev_pm_opp_of_remove_table(&pdev->dev);
-	dev_pm_opp_put_clkname(mas->se.opp_table);
 	return 0;
 }
 
diff --git a/drivers/spi/spi-qcom-qspi.c b/drivers/spi/spi-qcom-qspi.c
index 1dbcc410cd35..c334dfec4117 100644
--- a/drivers/spi/spi-qcom-qspi.c
+++ b/drivers/spi/spi-qcom-qspi.c
@@ -142,7 +142,6 @@ struct qcom_qspi {
 	struct clk_bulk_data *clks;
 	struct qspi_xfer xfer;
 	struct icc_path *icc_path_cpu_to_qspi;
-	struct opp_table *opp_table;
 	unsigned long last_speed;
 	/* Lock to protect data accessed by IRQs */
 	spinlock_t lock;
@@ -530,14 +529,14 @@ static int qcom_qspi_probe(struct platform_device *pdev)
 	master->handle_err = qcom_qspi_handle_err;
 	master->auto_runtime_pm = true;
 
-	ctrl->opp_table = dev_pm_opp_set_clkname(&pdev->dev, "core");
-	if (IS_ERR(ctrl->opp_table))
-		return PTR_ERR(ctrl->opp_table);
+	ret = devm_pm_opp_set_clkname(&pdev->dev, "core");
+	if (ret)
+		return ret;
 	/* OPP table is optional */
-	ret = dev_pm_opp_of_add_table(&pdev->dev);
+	ret = devm_pm_opp_of_add_table(&pdev->dev);
 	if (ret && ret != -ENODEV) {
 		dev_err(&pdev->dev, "invalid OPP table in device tree\n");
-		goto exit_probe_put_clkname;
+		return ret;
 	}
 
 	pm_runtime_use_autosuspend(dev);
@@ -549,10 +548,6 @@ static int qcom_qspi_probe(struct platform_device *pdev)
 		return 0;
 
 	pm_runtime_disable(dev);
-	dev_pm_opp_of_remove_table(&pdev->dev);
-
-exit_probe_put_clkname:
-	dev_pm_opp_put_clkname(ctrl->opp_table);
 
 	return ret;
 }
@@ -560,14 +555,11 @@ exit_probe_put_clkname:
 static int qcom_qspi_remove(struct platform_device *pdev)
 {
 	struct spi_master *master = platform_get_drvdata(pdev);
-	struct qcom_qspi *ctrl = spi_master_get_devdata(master);
 
 	/* Unregister _before_ disabling pm_runtime() so we stop transfers */
 	spi_unregister_master(master);
 
 	pm_runtime_disable(&pdev->dev);
-	dev_pm_opp_of_remove_table(&pdev->dev);
-	dev_pm_opp_put_clkname(ctrl->opp_table);
 
 	return 0;
 }
diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c
index 00bb88a71606..23d729ed3bf6 100644
--- a/drivers/tty/serial/qcom_geni_serial.c
+++ b/drivers/tty/serial/qcom_geni_serial.c
@@ -1426,14 +1426,14 @@ static int qcom_geni_serial_probe(struct platform_device *pdev)
 	if (of_property_read_bool(pdev->dev.of_node, "cts-rts-swap"))
 		port->cts_rts_swap = true;
 
-	port->se.opp_table = dev_pm_opp_set_clkname(&pdev->dev, "se");
-	if (IS_ERR(port->se.opp_table))
-		return PTR_ERR(port->se.opp_table);
+	ret = devm_pm_opp_set_clkname(&pdev->dev, "se");
+	if (ret)
+		return ret;
 	/* OPP table is optional */
-	ret = dev_pm_opp_of_add_table(&pdev->dev);
+	ret = devm_pm_opp_of_add_table(&pdev->dev);
 	if (ret && ret != -ENODEV) {
 		dev_err(&pdev->dev, "invalid OPP table in device tree\n");
-		goto put_clkname;
+		return ret;
 	}
 
 	port->private_data.drv = drv;
@@ -1443,7 +1443,7 @@ static int qcom_geni_serial_probe(struct platform_device *pdev)
 
 	ret = uart_add_one_port(drv, uport);
 	if (ret)
-		goto err;
+		return ret;
 
 	irq_set_status_flags(uport->irq, IRQ_NOAUTOEN);
 	ret = devm_request_irq(uport->dev, uport->irq, qcom_geni_serial_isr,
@@ -1451,7 +1451,7 @@ static int qcom_geni_serial_probe(struct platform_device *pdev)
 	if (ret) {
 		dev_err(uport->dev, "Failed to get IRQ ret %d\n", ret);
 		uart_remove_one_port(drv, uport);
-		goto err;
+		return ret;
 	}
 
 	/*
@@ -1468,16 +1468,11 @@ static int qcom_geni_serial_probe(struct platform_device *pdev)
 		if (ret) {
 			device_init_wakeup(&pdev->dev, false);
 			uart_remove_one_port(drv, uport);
-			goto err;
+			return ret;
 		}
 	}
 
 	return 0;
-err:
-	dev_pm_opp_of_remove_table(&pdev->dev);
-put_clkname:
-	dev_pm_opp_put_clkname(port->se.opp_table);
-	return ret;
 }
 
 static int qcom_geni_serial_remove(struct platform_device *pdev)
@@ -1485,8 +1480,6 @@ static int qcom_geni_serial_remove(struct platform_device *pdev)
 	struct qcom_geni_serial_port *port = platform_get_drvdata(pdev);
 	struct uart_driver *drv = port->private_data.drv;
 
-	dev_pm_opp_of_remove_table(&pdev->dev);
-	dev_pm_opp_put_clkname(port->se.opp_table);
 	dev_pm_clear_wake_irq(&pdev->dev);
 	device_init_wakeup(&pdev->dev, false);
 	uart_remove_one_port(drv, &port->uport);