Merge branch 'pm-cpufreq'

* pm-cpufreq: (22 commits)
  cpufreq: Kconfig: fix documentation links
  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
  cpufreq: Remove unused for_each_policy macro
  cpufreq: dt: dev_pm_opp_of_cpumask_add_table() may return -EPROBE_DEFER
  cpufreq: intel_pstate: Clean up frequency computations
  cpufreq: cppc: simplify default delay_us setting
  cpufreq: Rudimentary typos fix in the file s5pv210-cpufreq.c
  cpufreq: CPPC: Add support for frequency invariance
  ia64: fix format string for ia64-acpi-cpu-freq
  cpufreq: schedutil: Call sugov_update_next_freq() before check to fast_switch_enabled
  arch_topology: Export arch_freq_scale and helpers
  ...

16 files changed, 597 insertions, 283 deletions

diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index 3b8dca4eb08d..ec2db3419c41 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -17,17 +17,9 @@ int pcibus_to_node(struct pci_bus *bus);
 #include <linux/arch_topology.h>
 
 void update_freq_counters_refs(void);
-void topology_scale_freq_tick(void);
-
-#ifdef CONFIG_ARM64_AMU_EXTN
-/*
- * Replace task scheduler's default counter-based
- * frequency-invariance scale factor setting.
- */
-#define arch_scale_freq_tick topology_scale_freq_tick
-#endif /* CONFIG_ARM64_AMU_EXTN */
 
 /* Replace task scheduler's default frequency-invariant accounting */
+#define arch_scale_freq_tick topology_scale_freq_tick
 #define arch_set_freq_scale topology_set_freq_scale
 #define arch_scale_freq_capacity topology_get_freq_scale
 #define arch_scale_freq_invariant topology_scale_freq_invariant
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index e08a4126453a..4dd14a6620c1 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -199,12 +199,47 @@ static int freq_inv_set_max_ratio(int cpu, u64 max_rate, u64 ref_rate)
 	return 0;
 }
 
-static DEFINE_STATIC_KEY_FALSE(amu_fie_key);
-#define amu_freq_invariant() static_branch_unlikely(&amu_fie_key)
+static void amu_scale_freq_tick(void)
+{
+	u64 prev_core_cnt, prev_const_cnt;
+	u64 core_cnt, const_cnt, scale;
+
+	prev_const_cnt = this_cpu_read(arch_const_cycles_prev);
+	prev_core_cnt = this_cpu_read(arch_core_cycles_prev);
+
+	update_freq_counters_refs();
+
+	const_cnt = this_cpu_read(arch_const_cycles_prev);
+	core_cnt = this_cpu_read(arch_core_cycles_prev);
+
+	if (unlikely(core_cnt <= prev_core_cnt ||
+		     const_cnt <= prev_const_cnt))
+		return;
+
+	/*
+	 *	    /\core    arch_max_freq_scale
+	 * scale =  ------- * --------------------
+	 *	    /\const   SCHED_CAPACITY_SCALE
+	 *
+	 * See validate_cpu_freq_invariance_counters() for details on
+	 * arch_max_freq_scale and the use of SCHED_CAPACITY_SHIFT.
+	 */
+	scale = core_cnt - prev_core_cnt;
+	scale *= this_cpu_read(arch_max_freq_scale);
+	scale = div64_u64(scale >> SCHED_CAPACITY_SHIFT,
+			  const_cnt - prev_const_cnt);
+
+	scale = min_t(unsigned long, scale, SCHED_CAPACITY_SCALE);
+	this_cpu_write(arch_freq_scale, (unsigned long)scale);
+}
+
+static struct scale_freq_data amu_sfd = {
+	.source = SCALE_FREQ_SOURCE_ARCH,
+	.set_freq_scale = amu_scale_freq_tick,
+};
 
 static void amu_fie_setup(const struct cpumask *cpus)
 {
-	bool invariant;
 	int cpu;
 
 	/* We are already set since the last insmod of cpufreq driver */
@@ -221,25 +256,10 @@ static void amu_fie_setup(const struct cpumask *cpus)
 
 	cpumask_or(amu_fie_cpus, amu_fie_cpus, cpus);
 
-	invariant = topology_scale_freq_invariant();
-
-	/* We aren't fully invariant yet */
-	if (!invariant && !cpumask_equal(amu_fie_cpus, cpu_present_mask))
-		return;
-
-	static_branch_enable(&amu_fie_key);
+	topology_set_scale_freq_source(&amu_sfd, amu_fie_cpus);
 
 	pr_debug("CPUs[%*pbl]: counters will be used for FIE.",
 		 cpumask_pr_args(cpus));
-
-	/*
-	 * 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 (!invariant)
-		rebuild_sched_domains_energy();
 }
 
 static int init_amu_fie_callback(struct notifier_block *nb, unsigned long val,
@@ -256,8 +276,8 @@ static int init_amu_fie_callback(struct notifier_block *nb, unsigned long val,
 	 * initialized AMU support and enabled invariance. The AMU counters will
 	 * keep on working just fine in the absence of the cpufreq driver, and
 	 * for the CPUs for which there are no counters available, the last set
-	 * value of freq_scale will remain valid as that is the frequency those
-	 * CPUs are running at.
+	 * value of arch_freq_scale will remain valid as that is the frequency
+	 * those CPUs are running at.
 	 */
 
 	return 0;
@@ -283,53 +303,6 @@ static int __init init_amu_fie(void)
 }
 core_initcall(init_amu_fie);
 
-bool arch_freq_counters_available(const struct cpumask *cpus)
-{
-	return amu_freq_invariant() &&
-	       cpumask_subset(cpus, amu_fie_cpus);
-}
-
-void topology_scale_freq_tick(void)
-{
-	u64 prev_core_cnt, prev_const_cnt;
-	u64 core_cnt, const_cnt, scale;
-	int cpu = smp_processor_id();
-
-	if (!amu_freq_invariant())
-		return;
-
-	if (!cpumask_test_cpu(cpu, amu_fie_cpus))
-		return;
-
-	prev_const_cnt = this_cpu_read(arch_const_cycles_prev);
-	prev_core_cnt = this_cpu_read(arch_core_cycles_prev);
-
-	update_freq_counters_refs();
-
-	const_cnt = this_cpu_read(arch_const_cycles_prev);
-	core_cnt = this_cpu_read(arch_core_cycles_prev);
-
-	if (unlikely(core_cnt <= prev_core_cnt ||
-		     const_cnt <= prev_const_cnt))
-		return;
-
-	/*
-	 *	    /\core    arch_max_freq_scale
-	 * scale =  ------- * --------------------
-	 *	    /\const   SCHED_CAPACITY_SCALE
-	 *
-	 * See validate_cpu_freq_invariance_counters() for details on
-	 * arch_max_freq_scale and the use of SCHED_CAPACITY_SHIFT.
-	 */
-	scale = core_cnt - prev_core_cnt;
-	scale *= this_cpu_read(arch_max_freq_scale);
-	scale = div64_u64(scale >> SCHED_CAPACITY_SHIFT,
-			  const_cnt - prev_const_cnt);
-
-	scale = min_t(unsigned long, scale, SCHED_CAPACITY_SCALE);
-	this_cpu_write(freq_scale, (unsigned long)scale);
-}
-
 #ifdef CONFIG_ACPI_CPPC_LIB
 #include <acpi/cppc_acpi.h>
 
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/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/include/linux/arch_topology.h b/include/linux/arch_topology.h
index 0f6cd6b73a61..f180240dc95f 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -23,18 +23,31 @@ static inline unsigned long topology_get_cpu_scale(int cpu)
 
 void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity);
 
-DECLARE_PER_CPU(unsigned long, freq_scale);
+DECLARE_PER_CPU(unsigned long, arch_freq_scale);
 
 static inline unsigned long topology_get_freq_scale(int cpu)
 {
-	return per_cpu(freq_scale, cpu);
+	return per_cpu(arch_freq_scale, cpu);
 }
 
 void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq,
 			     unsigned long max_freq);
 bool topology_scale_freq_invariant(void);
 
-bool arch_freq_counters_available(const struct cpumask *cpus);
+enum scale_freq_source {
+	SCALE_FREQ_SOURCE_CPUFREQ = 0,
+	SCALE_FREQ_SOURCE_ARCH,
+	SCALE_FREQ_SOURCE_CPPC,
+};
+
+struct scale_freq_data {
+	enum scale_freq_source source;
+	void (*set_freq_scale)(void);
+};
+
+void topology_scale_freq_tick(void);
+void topology_set_scale_freq_source(struct scale_freq_data *data, const struct cpumask *cpus);
+void topology_clear_scale_freq_source(enum scale_freq_source source, const struct cpumask *cpus);
 
 DECLARE_PER_CPU(unsigned long, thermal_pressure);
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 98191218d891..b2890f6e6d6f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6384,6 +6384,7 @@ int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr)
 {
 	return __sched_setscheduler(p, attr, false, true);
 }
+EXPORT_SYMBOL_GPL(sched_setattr_nocheck);
 
 /**
  * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 50cbad89f7fa..6ee9c9bbe505 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -114,19 +114,8 @@ static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time,
 	return true;
 }
 
-static void sugov_fast_switch(struct sugov_policy *sg_policy, u64 time,
-			      unsigned int next_freq)
+static void sugov_deferred_update(struct sugov_policy *sg_policy)
 {
-	if (sugov_update_next_freq(sg_policy, time, next_freq))
-		cpufreq_driver_fast_switch(sg_policy->policy, next_freq);
-}
-
-static void sugov_deferred_update(struct sugov_policy *sg_policy, u64 time,
-				  unsigned int next_freq)
-{
-	if (!sugov_update_next_freq(sg_policy, time, next_freq))
-		return;
-
 	if (!sg_policy->work_in_progress) {
 		sg_policy->work_in_progress = true;
 		irq_work_queue(&sg_policy->irq_work);
@@ -366,16 +355,19 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
 		sg_policy->cached_raw_freq = cached_freq;
 	}
 
+	if (!sugov_update_next_freq(sg_policy, time, next_f))
+		return;
+
 	/*
 	 * This code runs under rq->lock for the target CPU, so it won't run
 	 * concurrently on two different CPUs for the same target and it is not
 	 * necessary to acquire the lock in the fast switch case.
 	 */
 	if (sg_policy->policy->fast_switch_enabled) {
-		sugov_fast_switch(sg_policy, time, next_f);
+		cpufreq_driver_fast_switch(sg_policy->policy, next_f);
 	} else {
 		raw_spin_lock(&sg_policy->update_lock);
-		sugov_deferred_update(sg_policy, time, next_f);
+		sugov_deferred_update(sg_policy);
 		raw_spin_unlock(&sg_policy->update_lock);
 	}
 }
@@ -454,12 +446,15 @@ sugov_update_shared(struct update_util_data *hook, u64 time, unsigned int flags)
 	if (sugov_should_update_freq(sg_policy, time)) {
 		next_f = sugov_next_freq_shared(sg_cpu, time);
 
+		if (!sugov_update_next_freq(sg_policy, time, next_f))
+			goto unlock;
+
 		if (sg_policy->policy->fast_switch_enabled)
-			sugov_fast_switch(sg_policy, time, next_f);
+			cpufreq_driver_fast_switch(sg_policy->policy, next_f);
 		else
-			sugov_deferred_update(sg_policy, time, next_f);
+			sugov_deferred_update(sg_policy);
 	}
-
+unlock:
 	raw_spin_unlock(&sg_policy->update_lock);
 }