Merge tag 'pm-6.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These rework cpuidle governors to call tick_nohz_get_sleep_length()
  less often and fix one of them, rework hibernation to avoid storing
  pages filled with zeros in hibernation images, switch over some
  cpufreq drivers to use void remove callbacks, fix and clean up
  multiple cpufreq drivers, fix the devfreq core, update the cpupower
  utility and make other assorted improvements.

  Specifics:

   - Rework the menu and teo cpuidle governors to avoid calling
     tick_nohz_get_sleep_length(), which is likely to become quite
     expensive going forward, too often and improve making decisions
     regarding whether or not to stop the scheduler tick in the teo
     governor (Rafael Wysocki)

   - Improve the performance of cpufreq_stats_create_table() in some
     cases (Liao Chang)

   - Fix two issues in the amd-pstate-ut cpufreq driver (Swapnil Sapkal)

   - Use clamp() helper macro to improve the code readability in
     cpufreq_verify_within_limits() (Liao Chang)

   - Set stale CPU frequency to minimum in intel_pstate (Doug Smythies)

   - Migrate cpufreq drivers for various platforms to use void remove
     callback (Yangtao Li)

   - Add online/offline/exit hooks for Tegra driver (Sumit Gupta)

   - Explicitly include correct DT includes in cpufreq (Rob Herring)

   - Frequency domain updates for qcom-hw driver (Neil Armstrong)

   - Modify AMD pstate driver return the highest_perf value (Meng Li)

   - Generic cleanups for cppc, mediatek and powernow driver (Liao
     Chang, Konrad Dybcio)

   - Add more platforms to cpufreq-arm driver's blocklist
     (AngeloGioacchino Del Regno and Konrad Dybcio)

   - brcmstb-avs-cpufreq: Fix -Warray-bounds bug (Gustavo A. R. Silva)

   - Add device PM helpers to allow a device to remain powered-on during
     system-wide transitions (Ulf Hansson)

   - Rework hibernation memory snapshotting to avoid storing pages
     filled with zeros in hibernation image files (Brian Geffon)

   - Add check to make sure that CPU latency QoS constraints do not use
     negative values (Clive Lin)

   - Optimize rp->domains memory allocation in the Intel RAPL power
     capping driver (xiongxin)

   - Remove recursion while parsing zones in the arm_scmi power capping
     driver (Cristian Marussi)

   - Fix memory leak in devfreq_dev_release() (Boris Brezillon)

   - Rewrite devfreq_monitor_start() kerneldoc comment (Manivannan
     Sadhasivam)

   - Explicitly include correct DT includes in devfreq (Rob Herring)

   - Remove unsued pm_runtime_update_max_time_suspended() extern
     declaration (YueHaibing)

   - Add turbo-boost support to cpupower (Wyes Karny)

   - Add support for amd_pstate mode change to cpupower (Wyes Karny)

   - Fix 'cpupower idle_set' command to accept only numeric values of
     arguments (Likhitha Korrapati)

   - Clean up OPP code and add new frequency related APIs to it (Viresh
     Kumar, Manivannan Sadhasivam)

   - Convert ti cpufreq/opp bindings to json schema (Nishanth Menon)"

* tag 'pm-6.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (74 commits)
  cpufreq: tegra194: remove opp table in exit hook
  cpufreq: powernow-k8: Use related_cpus instead of cpus in driver.exit()
  cpufreq: tegra194: add online/offline hooks
  cpuidle: teo: Avoid unnecessary variable assignments
  cpufreq: qcom-cpufreq-hw: add support for 4 freq domains
  dt-bindings: cpufreq: qcom-hw: add a 4th frequency domain
  cpufreq: amd-pstate-ut: Fix kernel panic when loading the driver
  cpufreq: amd-pstate-ut: Remove module parameter access
  cpufreq: Use clamp() helper macro to improve the code readability
  PM: sleep: Add helpers to allow a device to remain powered-on
  PM: QoS: Add check to make sure CPU latency is non-negative
  PM: runtime: Remove unsued extern declaration of pm_runtime_update_max_time_suspended()
  cpufreq: intel_pstate: set stale CPU frequency to minimum
  cpufreq: stats: Improve the performance of cpufreq_stats_create_table()
  dt-bindings: cpufreq: Convert ti-cpufreq to json schema
  dt-bindings: opp: Convert ti-omap5-opp-supply to json schema
  OPP: Fix argument name in doc comment
  cpuidle: menu: Skip tick_nohz_get_sleep_length() call in some cases
  cpufreq: cppc: Set fie_disabled to FIE_DISABLED if fails to create kworker_fie
  cpufreq: cppc: cppc_cpufreq_get_rate() returns zero in all error cases.
  ...

44 files changed, 534 insertions, 336 deletions

diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index b2f05d27167e..37f1cdf46d29 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -1011,22 +1011,20 @@ static int __init acpi_cpufreq_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int acpi_cpufreq_remove(struct platform_device *pdev)
+static void acpi_cpufreq_remove(struct platform_device *pdev)
 {
 	pr_debug("%s\n", __func__);
 
 	cpufreq_unregister_driver(&acpi_cpufreq_driver);
 
 	free_acpi_perf_data();
-
-	return 0;
 }
 
 static struct platform_driver acpi_cpufreq_platdrv = {
 	.driver = {
 		.name	= "acpi-cpufreq",
 	},
-	.remove		= acpi_cpufreq_remove,
+	.remove_new	= acpi_cpufreq_remove,
 };
 
 static int __init acpi_cpufreq_init(void)
diff --git a/drivers/cpufreq/amd-pstate-ut.c b/drivers/cpufreq/amd-pstate-ut.c
index 7f3fe2048981..f04ae67dda37 100644
--- a/drivers/cpufreq/amd-pstate-ut.c
+++ b/drivers/cpufreq/amd-pstate-ut.c
@@ -64,27 +64,9 @@ static struct amd_pstate_ut_struct amd_pstate_ut_cases[] = {
 static bool get_shared_mem(void)
 {
 	bool result = false;
-	char path[] = "/sys/module/amd_pstate/parameters/shared_mem";
-	char buf[5] = {0};
-	struct file *filp = NULL;
-	loff_t pos = 0;
-	ssize_t ret;
-
-	if (!boot_cpu_has(X86_FEATURE_CPPC)) {
-		filp = filp_open(path, O_RDONLY, 0);
-		if (IS_ERR(filp))
-			pr_err("%s unable to open %s file!\n", __func__, path);
-		else {
-			ret = kernel_read(filp, &buf, sizeof(buf), &pos);
-			if (ret < 0)
-				pr_err("%s read %s file fail ret=%ld!\n",
-					__func__, path, (long)ret);
-			filp_close(filp, NULL);
-		}
 
-		if ('Y' == *buf)
-			result = true;
-	}
+	if (!boot_cpu_has(X86_FEATURE_CPPC))
+		result = true;
 
 	return result;
 }
@@ -145,8 +127,6 @@ static void amd_pstate_ut_check_perf(u32 index)
 	struct cpufreq_policy *policy = NULL;
 	struct amd_cpudata *cpudata = NULL;
 
-	highest_perf = amd_get_highest_perf();
-
 	for_each_possible_cpu(cpu) {
 		policy = cpufreq_cpu_get(cpu);
 		if (!policy)
@@ -158,9 +138,10 @@ static void amd_pstate_ut_check_perf(u32 index)
 			if (ret) {
 				amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL;
 				pr_err("%s cppc_get_perf_caps ret=%d error!\n", __func__, ret);
-				return;
+				goto skip_test;
 			}
 
+			highest_perf = cppc_perf.highest_perf;
 			nominal_perf = cppc_perf.nominal_perf;
 			lowest_nonlinear_perf = cppc_perf.lowest_nonlinear_perf;
 			lowest_perf = cppc_perf.lowest_perf;
@@ -169,9 +150,10 @@ static void amd_pstate_ut_check_perf(u32 index)
 			if (ret) {
 				amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL;
 				pr_err("%s read CPPC_CAP1 ret=%d error!\n", __func__, ret);
-				return;
+				goto skip_test;
 			}
 
+			highest_perf = AMD_CPPC_HIGHEST_PERF(cap1);
 			nominal_perf = AMD_CPPC_NOMINAL_PERF(cap1);
 			lowest_nonlinear_perf = AMD_CPPC_LOWNONLIN_PERF(cap1);
 			lowest_perf = AMD_CPPC_LOWEST_PERF(cap1);
@@ -187,7 +169,7 @@ static void amd_pstate_ut_check_perf(u32 index)
 				nominal_perf, cpudata->nominal_perf,
 				lowest_nonlinear_perf, cpudata->lowest_nonlinear_perf,
 				lowest_perf, cpudata->lowest_perf);
-			return;
+			goto skip_test;
 		}
 
 		if (!((highest_perf >= nominal_perf) &&
@@ -198,11 +180,15 @@ static void amd_pstate_ut_check_perf(u32 index)
 			pr_err("%s cpu%d highest=%d >= nominal=%d > lowest_nonlinear=%d > lowest=%d > 0, the formula is incorrect!\n",
 				__func__, cpu, highest_perf, nominal_perf,
 				lowest_nonlinear_perf, lowest_perf);
-			return;
+			goto skip_test;
 		}
+		cpufreq_cpu_put(policy);
 	}
 
 	amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_PASS;
+	return;
+skip_test:
+	cpufreq_cpu_put(policy);
 }
 
 /*
@@ -230,14 +216,14 @@ static void amd_pstate_ut_check_freq(u32 index)
 			pr_err("%s cpu%d max=%d >= nominal=%d > lowest_nonlinear=%d > min=%d > 0, the formula is incorrect!\n",
 				__func__, cpu, cpudata->max_freq, cpudata->nominal_freq,
 				cpudata->lowest_nonlinear_freq, cpudata->min_freq);
-			return;
+			goto skip_test;
 		}
 
 		if (cpudata->min_freq != policy->min) {
 			amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL;
 			pr_err("%s cpu%d cpudata_min_freq=%d policy_min=%d, they should be equal!\n",
 				__func__, cpu, cpudata->min_freq, policy->min);
-			return;
+			goto skip_test;
 		}
 
 		if (cpudata->boost_supported) {
@@ -249,16 +235,20 @@ static void amd_pstate_ut_check_freq(u32 index)
 				pr_err("%s cpu%d policy_max=%d should be equal cpu_max=%d or cpu_nominal=%d !\n",
 					__func__, cpu, policy->max, cpudata->max_freq,
 					cpudata->nominal_freq);
-				return;
+				goto skip_test;
 			}
 		} else {
 			amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL;
 			pr_err("%s cpu%d must support boost!\n", __func__, cpu);
-			return;
+			goto skip_test;
 		}
+		cpufreq_cpu_put(policy);
 	}
 
 	amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_PASS;
+	return;
+skip_test:
+	cpufreq_cpu_put(policy);
 }
 
 static int __init amd_pstate_ut_init(void)
diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c
index b74289a95a17..bea41ccabf1f 100644
--- a/drivers/cpufreq/armada-37xx-cpufreq.c
+++ b/drivers/cpufreq/armada-37xx-cpufreq.c
@@ -14,10 +14,8 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/mfd/syscon.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of_address.h>
-#include <linux/of_device.h>
-#include <linux/of_irq.h>
 #include <linux/platform_device.h>
 #include <linux/pm_opp.h>
 #include <linux/regmap.h>
diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c
index ffea6402189d..35fb3a559ea9 100644
--- a/drivers/cpufreq/brcmstb-avs-cpufreq.c
+++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c
@@ -434,7 +434,11 @@ brcm_avs_get_freq_table(struct device *dev, struct private_data *priv)
 	if (ret)
 		return ERR_PTR(ret);
 
-	table = devm_kcalloc(dev, AVS_PSTATE_MAX + 1, sizeof(*table),
+	/*
+	 * We allocate space for the 5 different P-STATES AVS,
+	 * plus extra space for a terminating element.
+	 */
+	table = devm_kcalloc(dev, AVS_PSTATE_MAX + 1 + 1, sizeof(*table),
 			     GFP_KERNEL);
 	if (!table)
 		return ERR_PTR(-ENOMEM);
@@ -749,13 +753,11 @@ static int brcm_avs_cpufreq_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int brcm_avs_cpufreq_remove(struct platform_device *pdev)
+static void brcm_avs_cpufreq_remove(struct platform_device *pdev)
 {
 	cpufreq_unregister_driver(&brcm_avs_driver);
 
 	brcm_avs_prepare_uninit(pdev);
-
-	return 0;
 }
 
 static const struct of_device_id brcm_avs_cpufreq_match[] = {
@@ -770,7 +772,7 @@ static struct platform_driver brcm_avs_cpufreq_platdrv = {
 		.of_match_table = brcm_avs_cpufreq_match,
 	},
 	.probe		= brcm_avs_cpufreq_probe,
-	.remove		= brcm_avs_cpufreq_remove,
+	.remove_new	= brcm_avs_cpufreq_remove,
 };
 module_platform_driver(brcm_avs_cpufreq_platdrv);
 
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index 022e3555407c..fe08ca419b3d 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -249,15 +249,19 @@ static void __init cppc_freq_invariance_init(void)
 		return;
 
 	kworker_fie = kthread_create_worker(0, "cppc_fie");
-	if (IS_ERR(kworker_fie))
+	if (IS_ERR(kworker_fie)) {
+		pr_warn("%s: failed to create kworker_fie: %ld\n", __func__,
+			PTR_ERR(kworker_fie));
+		fie_disabled = FIE_DISABLED;
 		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;
+		fie_disabled = FIE_DISABLED;
 	}
 }
 
@@ -267,7 +271,6 @@ static void cppc_freq_invariance_exit(void)
 		return;
 
 	kthread_destroy_worker(kworker_fie);
-	kworker_fie = NULL;
 }
 
 #else
@@ -849,13 +852,13 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpu)
 
 	ret = cppc_get_perf_ctrs(cpu, &fb_ctrs_t0);
 	if (ret)
-		return ret;
+		return 0;
 
 	udelay(2); /* 2usec delay between sampling */
 
 	ret = cppc_get_perf_ctrs(cpu, &fb_ctrs_t1);
 	if (ret)
-		return ret;
+		return 0;
 
 	delivered_perf = cppc_perf_from_fbctrs(cpu_data, &fb_ctrs_t0,
 					       &fb_ctrs_t1);
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index e2b20080de3a..fb2875ce1fdd 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -143,14 +143,19 @@ static const struct of_device_id blocklist[] __initconst = {
 
 	{ .compatible = "qcom,apq8096", },
 	{ .compatible = "qcom,msm8996", },
+	{ .compatible = "qcom,msm8998", },
+	{ .compatible = "qcom,qcm2290", },
 	{ .compatible = "qcom,qcs404", },
+	{ .compatible = "qcom,qdu1000", },
 	{ .compatible = "qcom,sa8155p" },
 	{ .compatible = "qcom,sa8540p" },
+	{ .compatible = "qcom,sa8775p" },
 	{ .compatible = "qcom,sc7180", },
 	{ .compatible = "qcom,sc7280", },
 	{ .compatible = "qcom,sc8180x", },
 	{ .compatible = "qcom,sc8280xp", },
 	{ .compatible = "qcom,sdm845", },
+	{ .compatible = "qcom,sdx75", },
 	{ .compatible = "qcom,sm6115", },
 	{ .compatible = "qcom,sm6350", },
 	{ .compatible = "qcom,sm6375", },
@@ -158,6 +163,8 @@ static const struct of_device_id blocklist[] __initconst = {
 	{ .compatible = "qcom,sm8150", },
 	{ .compatible = "qcom,sm8250", },
 	{ .compatible = "qcom,sm8350", },
+	{ .compatible = "qcom,sm8450", },
+	{ .compatible = "qcom,sm8550", },
 
 	{ .compatible = "st,stih407", },
 	{ .compatible = "st,stih410", },
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 4aec4b2a5225..8bd6e5e8f121 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -349,11 +349,10 @@ err:
 	return ret;
 }
 
-static int dt_cpufreq_remove(struct platform_device *pdev)
+static void dt_cpufreq_remove(struct platform_device *pdev)
 {
 	cpufreq_unregister_driver(&dt_cpufreq_driver);
 	dt_cpufreq_release();
-	return 0;
 }
 
 static struct platform_driver dt_cpufreq_platdrv = {
@@ -361,7 +360,7 @@ static struct platform_driver dt_cpufreq_platdrv = {
 		.name	= "cpufreq-dt",
 	},
 	.probe		= dt_cpufreq_probe,
-	.remove		= dt_cpufreq_remove,
+	.remove_new	= dt_cpufreq_remove,
 };
 module_platform_driver(dt_cpufreq_platdrv);
 
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 50bbc969ffe5..a757f90aa9d6 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1234,16 +1234,16 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 	ret = freq_qos_add_notifier(&policy->constraints, FREQ_QOS_MIN,
 				    &policy->nb_min);
 	if (ret) {
-		dev_err(dev, "Failed to register MIN QoS notifier: %d (%*pbl)\n",
-			ret, cpumask_pr_args(policy->cpus));
+		dev_err(dev, "Failed to register MIN QoS notifier: %d (CPU%u)\n",
+			ret, cpu);
 		goto err_kobj_remove;
 	}
 
 	ret = freq_qos_add_notifier(&policy->constraints, FREQ_QOS_MAX,
 				    &policy->nb_max);
 	if (ret) {
-		dev_err(dev, "Failed to register MAX QoS notifier: %d (%*pbl)\n",
-			ret, cpumask_pr_args(policy->cpus));
+		dev_err(dev, "Failed to register MAX QoS notifier: %d (CPU%u)\n",
+			ret, cpu);
 		goto err_min_qos_notifier;
 	}
 
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index 55c7ffd37d1c..a33df3c66c88 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -243,7 +243,8 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy)
 
 	/* Find valid-unique entries */
 	cpufreq_for_each_valid_entry(pos, policy->freq_table)
-		if (freq_table_get_index(stats, pos->frequency) == -1)
+		if (policy->freq_table_sorted != CPUFREQ_TABLE_UNSORTED ||
+		    freq_table_get_index(stats, pos->frequency) == -1)
 			stats->freq_table[i++] = pos->frequency;
 
 	stats->state_num = i;
diff --git a/drivers/cpufreq/davinci-cpufreq.c b/drivers/cpufreq/davinci-cpufreq.c
index ebb3a8102681..7d2754411d8c 100644
--- a/drivers/cpufreq/davinci-cpufreq.c
+++ b/drivers/cpufreq/davinci-cpufreq.c
@@ -131,7 +131,7 @@ static int __init davinci_cpufreq_probe(struct platform_device *pdev)
 	return cpufreq_register_driver(&davinci_driver);
 }
 
-static int __exit davinci_cpufreq_remove(struct platform_device *pdev)
+static void __exit davinci_cpufreq_remove(struct platform_device *pdev)
 {
 	cpufreq_unregister_driver(&davinci_driver);
 
@@ -139,15 +139,13 @@ static int __exit davinci_cpufreq_remove(struct platform_device *pdev)
 
 	if (cpufreq.asyncclk)
 		clk_put(cpufreq.asyncclk);
-
-	return 0;
 }
 
 static struct platform_driver davinci_cpufreq_driver = {
 	.driver = {
 		.name	 = "cpufreq-davinci",
 	},
-	.remove = __exit_p(davinci_cpufreq_remove),
+	.remove_new = __exit_p(davinci_cpufreq_remove),
 };
 
 int __init davinci_cpufreq_init(void)
diff --git a/drivers/cpufreq/imx-cpufreq-dt.c b/drivers/cpufreq/imx-cpufreq-dt.c
index 535867a7dfdd..577bb9e2f112 100644
--- a/drivers/cpufreq/imx-cpufreq-dt.c
+++ b/drivers/cpufreq/imx-cpufreq-dt.c
@@ -172,20 +172,18 @@ static int imx_cpufreq_dt_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int imx_cpufreq_dt_remove(struct platform_device *pdev)
+static void imx_cpufreq_dt_remove(struct platform_device *pdev)
 {
 	platform_device_unregister(cpufreq_dt_pdev);
 	if (!of_machine_is_compatible("fsl,imx7ulp"))
 		dev_pm_opp_put_supported_hw(cpufreq_opp_token);
 	else
 		clk_bulk_put(ARRAY_SIZE(imx7ulp_clks), imx7ulp_clks);
-
-	return 0;
 }
 
 static struct platform_driver imx_cpufreq_dt_driver = {
 	.probe = imx_cpufreq_dt_probe,
-	.remove = imx_cpufreq_dt_remove,
+	.remove_new = imx_cpufreq_dt_remove,
 	.driver = {
 		.name = "imx-cpufreq-dt",
 	},
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index 9fb1501033bb..494d044b9e72 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -519,7 +519,7 @@ put_node:
 	return ret;
 }
 
-static int imx6q_cpufreq_remove(struct platform_device *pdev)
+static void imx6q_cpufreq_remove(struct platform_device *pdev)
 {
 	cpufreq_unregister_driver(&imx6q_cpufreq_driver);
 	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table);
@@ -530,8 +530,6 @@ static int imx6q_cpufreq_remove(struct platform_device *pdev)
 	regulator_put(soc_reg);
 
 	clk_bulk_put(num_clks, clks);
-
-	return 0;
 }
 
 static struct platform_driver imx6q_cpufreq_platdrv = {
@@ -539,7 +537,7 @@ static struct platform_driver imx6q_cpufreq_platdrv = {
 		.name	= "imx6q-cpufreq",
 	},
 	.probe		= imx6q_cpufreq_probe,
-	.remove		= imx6q_cpufreq_remove,
+	.remove_new	= imx6q_cpufreq_remove,
 };
 module_platform_driver(imx6q_cpufreq_platdrv);
 
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 8ca2bce4341a..dc50c9fb488d 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -2609,6 +2609,11 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 			intel_pstate_clear_update_util_hook(policy->cpu);
 		intel_pstate_hwp_set(policy->cpu);
 	}
+	/*
+	 * policy->cur is never updated with the intel_pstate driver, but it
+	 * is used as a stale frequency value. So, keep it within limits.
+	 */
+	policy->cur = policy->min;
 
 	mutex_unlock(&intel_pstate_limits_lock);
 
diff --git a/drivers/cpufreq/kirkwood-cpufreq.c b/drivers/cpufreq/kirkwood-cpufreq.c
index 95588101efbd..fd20b986d1f2 100644
--- a/drivers/cpufreq/kirkwood-cpufreq.c
+++ b/drivers/cpufreq/kirkwood-cpufreq.c
@@ -178,20 +178,18 @@ out_node:
 	return err;
 }
 
-static int kirkwood_cpufreq_remove(struct platform_device *pdev)
+static void kirkwood_cpufreq_remove(struct platform_device *pdev)
 {
 	cpufreq_unregister_driver(&kirkwood_cpufreq_driver);
 
 	clk_disable_unprepare(priv.powersave_clk);
 	clk_disable_unprepare(priv.ddr_clk);
 	clk_disable_unprepare(priv.cpu_clk);
-
-	return 0;
 }
 
 static struct platform_driver kirkwood_cpufreq_platform_driver = {
 	.probe = kirkwood_cpufreq_probe,
-	.remove = kirkwood_cpufreq_remove,
+	.remove_new = kirkwood_cpufreq_remove,
 	.driver = {
 		.name = "kirkwood-cpufreq",
 	},
diff --git a/drivers/cpufreq/mediatek-cpufreq-hw.c b/drivers/cpufreq/mediatek-cpufreq-hw.c
index b22f5cc8a463..d46afb3c0092 100644
--- a/drivers/cpufreq/mediatek-cpufreq-hw.c
+++ b/drivers/cpufreq/mediatek-cpufreq-hw.c
@@ -10,8 +10,9 @@
 #include <linux/iopoll.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/of_address.h>
+#include <linux/of.h>
 #include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/slab.h>
 
 #define LUT_MAX_ENTRIES			32U
@@ -315,11 +316,9 @@ static int mtk_cpufreq_hw_driver_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int mtk_cpufreq_hw_driver_remove(struct platform_device *pdev)
+static void mtk_cpufreq_hw_driver_remove(struct platform_device *pdev)
 {
 	cpufreq_unregister_driver(&cpufreq_mtk_hw_driver);
-
-	return 0;
 }
 
 static const struct of_device_id mtk_cpufreq_hw_match[] = {
@@ -330,7 +329,7 @@ MODULE_DEVICE_TABLE(of, mtk_cpufreq_hw_match);
 
 static struct platform_driver mtk_cpufreq_hw_driver = {
 	.probe = mtk_cpufreq_hw_driver_probe,
-	.remove = mtk_cpufreq_hw_driver_remove,
+	.remove_new = mtk_cpufreq_hw_driver_remove,
 	.driver = {
 		.name = "mtk-cpufreq-hw",
 		.of_match_table = mtk_cpufreq_hw_match,
diff --git a/drivers/cpufreq/mediatek-cpufreq.c b/drivers/cpufreq/mediatek-cpufreq.c
index fef68cb2b38f..a0a61919bc4c 100644
--- a/drivers/cpufreq/mediatek-cpufreq.c
+++ b/drivers/cpufreq/mediatek-cpufreq.c
@@ -313,8 +313,6 @@ out:
 	return ret;
 }
 
-#define DYNAMIC_POWER "dynamic-power-coefficient"
-
 static int mtk_cpufreq_opp_notifier(struct notifier_block *nb,
 				    unsigned long event, void *data)
 {
diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c
index 81649a1969b6..895690856665 100644
--- a/drivers/cpufreq/omap-cpufreq.c
+++ b/drivers/cpufreq/omap-cpufreq.c
@@ -182,11 +182,9 @@ static int omap_cpufreq_probe(struct platform_device *pdev)
 	return cpufreq_register_driver(&omap_driver);
 }
 
-static int omap_cpufreq_remove(struct platform_device *pdev)
+static void omap_cpufreq_remove(struct platform_device *pdev)
 {
 	cpufreq_unregister_driver(&omap_driver);
-
-	return 0;
 }
 
 static struct platform_driver omap_cpufreq_platdrv = {
@@ -194,7 +192,7 @@ static struct platform_driver omap_cpufreq_platdrv = {
 		.name	= "omap-cpufreq",
 	},
 	.probe		= omap_cpufreq_probe,
-	.remove		= omap_cpufreq_remove,
+	.remove_new	= omap_cpufreq_remove,
 };
 module_platform_driver(omap_cpufreq_platdrv);
 
diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c
index 73efbcf5513b..84fe37def0f1 100644
--- a/drivers/cpufreq/pcc-cpufreq.c
+++ b/drivers/cpufreq/pcc-cpufreq.c
@@ -608,22 +608,20 @@ static int __init pcc_cpufreq_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int pcc_cpufreq_remove(struct platform_device *pdev)
+static void pcc_cpufreq_remove(struct platform_device *pdev)
 {
 	cpufreq_unregister_driver(&pcc_cpufreq_driver);
 
 	pcc_clear_mapping();
 
 	free_percpu(pcc_cpu_info);
-
-	return 0;
 }
 
 static struct platform_driver pcc_cpufreq_platdrv = {
 	.driver = {
 		.name	= "pcc-cpufreq",
 	},
-	.remove		= pcc_cpufreq_remove,
+	.remove_new	= pcc_cpufreq_remove,
 };
 
 static int __init pcc_cpufreq_init(void)
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index d289036beff2..b10f7a1b77f1 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -1101,7 +1101,8 @@ static int powernowk8_cpu_exit(struct cpufreq_policy *pol)
 
 	kfree(data->powernow_table);
 	kfree(data);
-	for_each_cpu(cpu, pol->cpus)
+	/* pol->cpus will be empty here, use related_cpus instead. */
+	for_each_cpu(cpu, pol->related_cpus)
 		per_cpu(powernow_data, cpu) = NULL;
 
 	return 0;
diff --git a/drivers/cpufreq/ppc_cbe_cpufreq.c b/drivers/cpufreq/ppc_cbe_cpufreq.c
index e3313ce63b38..88afc49941b7 100644
--- a/drivers/cpufreq/ppc_cbe_cpufreq.c
+++ b/drivers/cpufreq/ppc_cbe_cpufreq.c
@@ -9,7 +9,7 @@
 
 #include <linux/cpufreq.h>
 #include <linux/module.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
 
 #include <asm/machdep.h>
 #include <asm/cell-regs.h>
diff --git a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
index 4fba3637b115..6f0c32592416 100644
--- a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
+++ b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
@@ -11,7 +11,6 @@
 #include <linux/types.h>
 #include <linux/timer.h>
 #include <linux/init.h>
-#include <linux/of_platform.h>
 #include <linux/pm_qos.h>
 #include <linux/slab.h>
 
diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index f2830371d25f..70b0f21968a0 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -28,7 +28,7 @@
 
 #define GT_IRQ_STATUS			BIT(2)
 
-#define MAX_FREQ_DOMAINS		3
+#define MAX_FREQ_DOMAINS		4
 
 struct qcom_cpufreq_soc_data {
 	u32 reg_enable;
@@ -730,16 +730,14 @@ static int qcom_cpufreq_hw_driver_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int qcom_cpufreq_hw_driver_remove(struct platform_device *pdev)
+static void qcom_cpufreq_hw_driver_remove(struct platform_device *pdev)
 {
 	cpufreq_unregister_driver(&cpufreq_qcom_hw_driver);
-
-	return 0;
 }
 
 static struct platform_driver qcom_cpufreq_hw_driver = {
 	.probe = qcom_cpufreq_hw_driver_probe,
-	.remove = qcom_cpufreq_hw_driver_remove,
+	.remove_new = qcom_cpufreq_hw_driver_remove,
 	.driver = {
 		.name = "qcom-cpufreq-hw",
 		.of_match_table = qcom_cpufreq_hw_match,
diff --git a/drivers/cpufreq/qcom-cpufreq-nvmem.c b/drivers/cpufreq/qcom-cpufreq-nvmem.c
index a88b6fe5db50..84d7033e5efe 100644
--- a/drivers/cpufreq/qcom-cpufreq-nvmem.c
+++ b/drivers/cpufreq/qcom-cpufreq-nvmem.c
@@ -22,7 +22,6 @@
 #include <linux/module.h>
 #include <linux/nvmem-consumer.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pm_domain.h>
 #include <linux/pm_opp.h>
@@ -334,7 +333,7 @@ free_drv:
 	return ret;
 }
 
-static int qcom_cpufreq_remove(struct platform_device *pdev)
+static void qcom_cpufreq_remove(struct platform_device *pdev)
 {
 	struct qcom_cpufreq_drv *drv = platform_get_drvdata(pdev);
 	unsigned int cpu;
@@ -346,13 +345,11 @@ static int qcom_cpufreq_remove(struct platform_device *pdev)
 
 	kfree(drv->opp_tokens);
 	kfree(drv);
-
-	return 0;
 }
 
 static struct platform_driver qcom_cpufreq_driver = {
 	.probe = qcom_cpufreq_probe,
-	.remove = qcom_cpufreq_remove,
+	.remove_new = qcom_cpufreq_remove,
 	.driver = {
 		.name = "qcom-cpufreq-nvmem",
 	},
diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c
index 573b417e1483..0aecaecbb0e6 100644
--- a/drivers/cpufreq/qoriq-cpufreq.c
+++ b/drivers/cpufreq/qoriq-cpufreq.c
@@ -288,11 +288,9 @@ static int qoriq_cpufreq_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int qoriq_cpufreq_remove(struct platform_device *pdev)
+static void qoriq_cpufreq_remove(struct platform_device *pdev)
 {
 	cpufreq_unregister_driver(&qoriq_cpufreq_driver);
-
-	return 0;
 }
 
 static struct platform_driver qoriq_cpufreq_platform_driver = {
@@ -300,7 +298,7 @@ static struct platform_driver qoriq_cpufreq_platform_driver = {
 		.name = "qoriq-cpufreq",
 	},
 	.probe = qoriq_cpufreq_probe,
-	.remove = qoriq_cpufreq_remove,
+	.remove_new = qoriq_cpufreq_remove,
 };
 module_platform_driver(qoriq_cpufreq_platform_driver);
 
diff --git a/drivers/cpufreq/raspberrypi-cpufreq.c b/drivers/cpufreq/raspberrypi-cpufreq.c
index 2bc7d9734272..e0705cc9a57d 100644
--- a/drivers/cpufreq/raspberrypi-cpufreq.c
+++ b/drivers/cpufreq/raspberrypi-cpufreq.c
@@ -65,7 +65,7 @@ remove_opp:
 	return ret;
 }
 
-static int raspberrypi_cpufreq_remove(struct platform_device *pdev)
+static void raspberrypi_cpufreq_remove(struct platform_device *pdev)
 {
 	struct device *cpu_dev;
 
@@ -74,8 +74,6 @@ static int raspberrypi_cpufreq_remove(struct platform_device *pdev)
 		dev_pm_opp_remove_all_dynamic(cpu_dev);
 
 	platform_device_unregister(cpufreq_dt);
-
-	return 0;
 }
 
 /*
@@ -87,7 +85,7 @@ static struct platform_driver raspberrypi_cpufreq_driver = {
 		.name = "raspberrypi-cpufreq",
 	},
 	.probe          = raspberrypi_cpufreq_probe,
-	.remove		= raspberrypi_cpufreq_remove,
+	.remove_new	= raspberrypi_cpufreq_remove,
 };
 module_platform_driver(raspberrypi_cpufreq_driver);
 
diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c
index fd2c16821d54..d33be56983ed 100644
--- a/drivers/cpufreq/scpi-cpufreq.c
+++ b/drivers/cpufreq/scpi-cpufreq.c
@@ -14,7 +14,7 @@
 #include <linux/cpumask.h>
 #include <linux/export.h>
 #include <linux/module.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/pm_opp.h>
 #include <linux/scpi_protocol.h>
 #include <linux/slab.h>
@@ -208,11 +208,10 @@ static int scpi_cpufreq_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int scpi_cpufreq_remove(struct platform_device *pdev)
+static void scpi_cpufreq_remove(struct platform_device *pdev)
 {
 	cpufreq_unregister_driver(&scpi_cpufreq_driver);
 	scpi_ops = NULL;
-	return 0;
 }
 
 static struct platform_driver scpi_cpufreq_platdrv = {
@@ -220,7 +219,7 @@ static struct platform_driver scpi_cpufreq_platdrv = {
 		.name	= "scpi-cpufreq",
 	},
 	.probe		= scpi_cpufreq_probe,
-	.remove		= scpi_cpufreq_remove,
+	.remove_new	= scpi_cpufreq_remove,
 };
 module_platform_driver(scpi_cpufreq_platdrv);
 
diff --git a/drivers/cpufreq/sti-cpufreq.c b/drivers/cpufreq/sti-cpufreq.c
index 1a63aeea8711..9c542e723a15 100644
--- a/drivers/cpufreq/sti-cpufreq.c
+++ b/drivers/cpufreq/sti-cpufreq.c
@@ -13,7 +13,7 @@
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/pm_opp.h>
 #include <linux/regmap.h>
 
diff --git a/drivers/cpufreq/sun50i-cpufreq-nvmem.c b/drivers/cpufreq/sun50i-cpufreq-nvmem.c
index 4321d7bbe769..32a9c88f8ff6 100644
--- a/drivers/cpufreq/sun50i-cpufreq-nvmem.c
+++ b/drivers/cpufreq/sun50i-cpufreq-nvmem.c
@@ -137,7 +137,7 @@ free_opp:
 	return ret;
 }
 
-static int sun50i_cpufreq_nvmem_remove(struct platform_device *pdev)
+static void sun50i_cpufreq_nvmem_remove(struct platform_device *pdev)
 {
 	int *opp_tokens = platform_get_drvdata(pdev);
 	unsigned int cpu;
@@ -148,13 +148,11 @@ static int sun50i_cpufreq_nvmem_remove(struct platform_device *pdev)
 		dev_pm_opp_put_prop_name(opp_tokens[cpu]);
 
 	kfree(opp_tokens);
-
-	return 0;
 }
 
 static struct platform_driver sun50i_cpufreq_driver = {
 	.probe = sun50i_cpufreq_nvmem_probe,
-	.remove = sun50i_cpufreq_nvmem_remove,
+	.remove_new = sun50i_cpufreq_nvmem_remove,
 	.driver = {
 		.name = "sun50i-cpufreq-nvmem",
 	},
diff --git a/drivers/cpufreq/tegra186-cpufreq.c b/drivers/cpufreq/tegra186-cpufreq.c
index f98f53bf1011..7b8fcfa55038 100644
--- a/drivers/cpufreq/tegra186-cpufreq.c
+++ b/drivers/cpufreq/tegra186-cpufreq.c
@@ -259,11 +259,9 @@ put_bpmp:
 	return err;
 }
 
-static int tegra186_cpufreq_remove(struct platform_device *pdev)
+static void tegra186_cpufreq_remove(struct platform_device *pdev)
 {
 	cpufreq_unregister_driver(&tegra186_cpufreq_driver);
-
-	return 0;
 }
 
 static const struct of_device_id tegra186_cpufreq_of_match[] = {
@@ -278,7 +276,7 @@ static struct platform_driver tegra186_cpufreq_platform_driver = {
 		.of_match_table = tegra186_cpufreq_of_match,
 	},
 	.probe = tegra186_cpufreq_probe,
-	.remove = tegra186_cpufreq_remove,
+	.remove_new = tegra186_cpufreq_remove,
 };
 module_platform_driver(tegra186_cpufreq_platform_driver);
 
diff --git a/drivers/cpufreq/tegra194-cpufreq.c b/drivers/cpufreq/tegra194-cpufreq.c
index 36dad5ea5947..88ef5e57ccd0 100644
--- a/drivers/cpufreq/tegra194-cpufreq.c
+++ b/drivers/cpufreq/tegra194-cpufreq.c
@@ -508,6 +508,32 @@ static int tegra194_cpufreq_init(struct cpufreq_policy *policy)
 	return 0;
 }
 
+static int tegra194_cpufreq_online(struct cpufreq_policy *policy)
+{
+	/* We did light-weight tear down earlier, nothing to do here */
+	return 0;
+}
+
+static int tegra194_cpufreq_offline(struct cpufreq_policy *policy)
+{
+	/*
+	 * Preserve policy->driver_data and don't free resources on light-weight
+	 * tear down.
+	 */
+
+	return 0;
+}
+
+static int tegra194_cpufreq_exit(struct cpufreq_policy *policy)
+{
+	struct device *cpu_dev = get_cpu_device(policy->cpu);
+
+	dev_pm_opp_remove_all_dynamic(cpu_dev);
+	dev_pm_opp_of_cpumask_remove_table(policy->related_cpus);
+
+	return 0;
+}
+
 static int tegra194_cpufreq_set_target(struct cpufreq_policy *policy,
 				       unsigned int index)
 {
@@ -535,6 +561,9 @@ static struct cpufreq_driver tegra194_cpufreq_driver = {
 	.target_index = tegra194_cpufreq_set_target,
 	.get = tegra194_get_speed,
 	.init = tegra194_cpufreq_init,
+	.exit = tegra194_cpufreq_exit,
+	.online = tegra194_cpufreq_online,
+	.offline = tegra194_cpufreq_offline,
 	.attr = cpufreq_generic_attr,
 };
 
@@ -708,12 +737,10 @@ put_bpmp:
 	return err;
 }
 
-static int tegra194_cpufreq_remove(struct platform_device *pdev)
+static void tegra194_cpufreq_remove(struct platform_device *pdev)
 {
 	cpufreq_unregister_driver(&tegra194_cpufreq_driver);
 	tegra194_cpufreq_free_resources();
-
-	return 0;
 }
 
 static const struct of_device_id tegra194_cpufreq_of_match[] = {
@@ -730,7 +757,7 @@ static struct platform_driver tegra194_ccplex_driver = {
 		.of_match_table = tegra194_cpufreq_of_match,
 	},
 	.probe = tegra194_cpufreq_probe,
-	.remove = tegra194_cpufreq_remove,
+	.remove_new = tegra194_cpufreq_remove,
 };
 module_platform_driver(tegra194_ccplex_driver);
 
diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c
index d5cd2fd25cad..3c37d7899660 100644
--- a/drivers/cpufreq/ti-cpufreq.c
+++ b/drivers/cpufreq/ti-cpufreq.c
@@ -12,7 +12,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/of.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/pm_opp.h>
 #include <linux/regmap.h>
 #include <linux/slab.h>
diff --git a/drivers/cpufreq/vexpress-spc-cpufreq.c b/drivers/cpufreq/vexpress-spc-cpufreq.c
index d295f405c4bb..9ac4ea50b874 100644
--- a/drivers/cpufreq/vexpress-spc-cpufreq.c
+++ b/drivers/cpufreq/vexpress-spc-cpufreq.c
@@ -18,7 +18,6 @@
 #include <linux/device.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
-#include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/pm_opp.h>
 #include <linux/slab.h>
@@ -552,7 +551,7 @@ static int ve_spc_cpufreq_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int ve_spc_cpufreq_remove(struct platform_device *pdev)
+static void ve_spc_cpufreq_remove(struct platform_device *pdev)
 {
 	bL_switcher_get_enabled();
 	__bLs_unregister_notifier();
@@ -560,7 +559,6 @@ static int ve_spc_cpufreq_remove(struct platform_device *pdev)
 	bL_switcher_put_enabled();
 	pr_info("%s: Un-registered platform driver: %s\n", __func__,
 		ve_spc_cpufreq_driver.name);
-	return 0;
 }
 
 static struct platform_driver ve_spc_cpufreq_platdrv = {
@@ -568,7 +566,7 @@ static struct platform_driver ve_spc_cpufreq_platdrv = {
 		.name	= "vexpress-spc-cpufreq",
 	},
 	.probe		= ve_spc_cpufreq_probe,
-	.remove		= ve_spc_cpufreq_remove,
+	.remove_new	= ve_spc_cpufreq_remove,
 };
 module_platform_driver(ve_spc_cpufreq_platdrv);
 
diff --git a/drivers/cpuidle/governors/gov.h b/drivers/cpuidle/governors/gov.h
new file mode 100644
index 000000000000..99e067d9668c
--- /dev/null
+++ b/drivers/cpuidle/governors/gov.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/* Common definitions for cpuidle governors. */
+
+#ifndef __CPUIDLE_GOVERNOR_H
+#define __CPUIDLE_GOVERNOR_H
+
+/*
+ * Idle state target residency threshold used for deciding whether or not to
+ * check the time till the closest expected timer event.
+ */
+#define RESIDENCY_THRESHOLD_NS	(15 * NSEC_PER_USEC)
+
+#endif /* __CPUIDLE_GOVERNOR_H */
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index c4922684f305..b96e3da0fedd 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -19,6 +19,8 @@
 #include <linux/sched/stat.h>
 #include <linux/math64.h>
 
+#include "gov.h"
+
 #define BUCKETS 12
 #define INTERVAL_SHIFT 3
 #define INTERVALS (1UL << INTERVAL_SHIFT)
@@ -166,8 +168,7 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev);
  * of points is below a threshold. If it is... then use the
  * average of these 8 points as the estimated value.
  */
-static unsigned int get_typical_interval(struct menu_device *data,
-					 unsigned int predicted_us)
+static unsigned int get_typical_interval(struct menu_device *data)
 {
 	int i, divisor;
 	unsigned int min, max, thresh, avg;
@@ -195,11 +196,7 @@ again:
 		}
 	}
 
-	/*
-	 * If the result of the computation is going to be discarded anyway,
-	 * avoid the computation altogether.
-	 */
-	if (min >= predicted_us)
+	if (!max)
 		return UINT_MAX;
 
 	if (divisor == INTERVALS)
@@ -267,7 +264,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 {
 	struct menu_device *data = this_cpu_ptr(&menu_devices);
 	s64 latency_req = cpuidle_governor_latency_req(dev->cpu);
-	unsigned int predicted_us;
 	u64 predicted_ns;
 	u64 interactivity_req;
 	unsigned int nr_iowaiters;
@@ -279,16 +275,41 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		data->needs_update = 0;
 	}
 
-	/* determine the expected residency time, round up */
-	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);
+
+	/* Find the shortest expected idle interval. */
+	predicted_ns = get_typical_interval(data) * NSEC_PER_USEC;
+	if (predicted_ns > RESIDENCY_THRESHOLD_NS) {
+		unsigned int timer_us;
+
+		/* Determine the time till the closest timer. */
+		delta = tick_nohz_get_sleep_length(&delta_tick);
+		if (unlikely(delta < 0)) {
+			delta = 0;
+			delta_tick = 0;
+		}
+
+		data->next_timer_ns = delta;
+		data->bucket = which_bucket(data->next_timer_ns, nr_iowaiters);
+
+		/* Round up the result for half microseconds. */
+		timer_us = div_u64((RESOLUTION * DECAY * NSEC_PER_USEC) / 2 +
+					data->next_timer_ns *
+						data->correction_factor[data->bucket],
+				   RESOLUTION * DECAY * NSEC_PER_USEC);
+		/* Use the lowest expected idle interval to pick the idle state. */
+		predicted_ns = min((u64)timer_us * NSEC_PER_USEC, predicted_ns);
+	} else {
+		/*
+		 * Because the next timer event is not going to be determined
+		 * in this case, assume that without the tick the closest timer
+		 * will be in distant future and that the closest tick will occur
+		 * after 1/2 of the tick period.
+		 */
+		data->next_timer_ns = KTIME_MAX;
+		delta_tick = TICK_NSEC / 2;
+		data->bucket = which_bucket(KTIME_MAX, nr_iowaiters);
+	}
 
 	if (unlikely(drv->state_count <= 1 || latency_req == 0) ||
 	    ((data->next_timer_ns < drv->states[1].target_residency_ns ||
@@ -303,16 +324,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		return 0;
 	}
 
-	/* Round up the result for half microseconds. */
-	predicted_us = div_u64(data->next_timer_ns *
-			       data->correction_factor[data->bucket] +
-			       (RESOLUTION * DECAY * NSEC_PER_USEC) / 2,
-			       RESOLUTION * DECAY * NSEC_PER_USEC);
-	/* Use the lowest expected idle interval to pick the idle state. */
-	predicted_ns = (u64)min(predicted_us,
-				get_typical_interval(data, predicted_us)) *
-				NSEC_PER_USEC;
-
 	if (tick_nohz_tick_stopped()) {
 		/*
 		 * If the tick is already stopped, the cost of possible short
diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c
index 987fc5f3997d..7244f71c59c5 100644
--- a/drivers/cpuidle/governors/teo.c
+++ b/drivers/cpuidle/governors/teo.c
@@ -140,6 +140,8 @@
 #include <linux/sched/topology.h>
 #include <linux/tick.h>
 
+#include "gov.h"
+
 /*
  * The number of bits to shift the CPU's capacity by in order to determine
  * the utilized threshold.
@@ -152,7 +154,6 @@
  */
 #define UTIL_THRESHOLD_SHIFT 6
 
-
 /*
  * The PULSE value is added to metrics when they grow and the DECAY_SHIFT value
  * is used for decreasing metrics on a regular basis.
@@ -186,8 +187,8 @@ struct teo_bin {
  * @total: Grand total of the "intercepts" and "hits" metrics for all bins.
  * @next_recent_idx: Index of the next @recent_idx entry to update.
  * @recent_idx: Indices of bins corresponding to recent "intercepts".
+ * @tick_hits: Number of "hits" after TICK_NSEC.
  * @util_threshold: Threshold above which the CPU is considered utilized
- * @utilized: Whether the last sleep on the CPU happened while utilized
  */
 struct teo_cpu {
 	s64 time_span_ns;
@@ -196,8 +197,8 @@ struct teo_cpu {
 	unsigned int total;
 	int next_recent_idx;
 	int recent_idx[NR_RECENT];
+	unsigned int tick_hits;
 	unsigned long util_threshold;
-	bool utilized;
 };
 
 static DEFINE_PER_CPU(struct teo_cpu, teo_cpus);
@@ -228,6 +229,7 @@ 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_timer = 0, idx_duration = 0;
+	s64 target_residency_ns;
 	u64 measured_ns;
 
 	if (cpu_data->time_span_ns >= cpu_data->sleep_length_ns) {
@@ -268,7 +270,6 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	 * fall into.
 	 */
 	for (i = 0; i < drv->state_count; i++) {
-		s64 target_residency_ns = drv->states[i].target_residency_ns;
 		struct teo_bin *bin = &cpu_data->state_bins[i];
 
 		bin->hits -= bin->hits >> DECAY_SHIFT;
@@ -276,6 +277,8 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 
 		cpu_data->total += bin->hits + bin->intercepts;
 
+		target_residency_ns = drv->states[i].target_residency_ns;
+
 		if (target_residency_ns <= cpu_data->sleep_length_ns) {
 			idx_timer = i;
 			if (target_residency_ns <= measured_ns)
@@ -291,6 +294,26 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		cpu_data->state_bins[cpu_data->recent_idx[i]].recent--;
 
 	/*
+	 * If the deepest state's target residency is below the tick length,
+	 * make a record of it to help teo_select() decide whether or not
+	 * to stop the tick.  This effectively adds an extra hits-only bin
+	 * beyond the last state-related one.
+	 */
+	if (target_residency_ns < TICK_NSEC) {
+		cpu_data->tick_hits -= cpu_data->tick_hits >> DECAY_SHIFT;
+
+		cpu_data->total += cpu_data->tick_hits;
+
+		if (TICK_NSEC <= cpu_data->sleep_length_ns) {
+			idx_timer = drv->state_count;
+			if (TICK_NSEC <= measured_ns) {
+				cpu_data->tick_hits += PULSE;
+				goto end;
+			}
+		}
+	}
+
+	/*
 	 * If the measured idle duration falls into the same bin as the sleep
 	 * length, this is a "hit", so update the "hits" metric for that bin.
 	 * Otherwise, update the "intercepts" metric for the bin fallen into by
@@ -305,18 +328,14 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		cpu_data->recent_idx[i] = idx_duration;
 	}
 
+end:
 	cpu_data->total += PULSE;
 }
 
-static bool teo_time_ok(u64 interval_ns)
+static bool teo_state_ok(int i, struct cpuidle_driver *drv)
 {
-	return !tick_nohz_tick_stopped() || interval_ns >= TICK_NSEC;
-}
-
-static s64 teo_middle_of_bin(int idx, struct cpuidle_driver *drv)
-{
-	return (drv->states[idx].target_residency_ns +
-		drv->states[idx+1].target_residency_ns) / 2;
+	return !tick_nohz_tick_stopped() ||
+		drv->states[i].target_residency_ns >= TICK_NSEC;
 }
 
 /**
@@ -356,6 +375,8 @@ 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);
+	ktime_t delta_tick = TICK_NSEC / 2;
+	unsigned int tick_intercept_sum = 0;
 	unsigned int idx_intercept_sum = 0;
 	unsigned int intercept_sum = 0;
 	unsigned int idx_recent_sum = 0;
@@ -365,7 +386,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	int constraint_idx = 0;
 	int idx0 = 0, idx = -1;
 	bool alt_intercepts, alt_recent;
-	ktime_t delta_tick;
+	bool cpu_utilized;
 	s64 duration_ns;
 	int i;
 
@@ -375,44 +396,48 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	}
 
 	cpu_data->time_span_ns = local_clock();
-
-	duration_ns = tick_nohz_get_sleep_length(&delta_tick);
-	cpu_data->sleep_length_ns = duration_ns;
+	/*
+	 * Set the expected sleep length to infinity in case of an early
+	 * return.
+	 */
+	cpu_data->sleep_length_ns = KTIME_MAX;
 
 	/* Check if there is any choice in the first place. */
 	if (drv->state_count < 2) {
 		idx = 0;
-		goto end;
+		goto out_tick;
 	}
-	if (!dev->states_usage[0].disable) {
+
+	if (!dev->states_usage[0].disable)
 		idx = 0;
-		if (drv->states[1].target_residency_ns > duration_ns)
-			goto end;
-	}
 
-	cpu_data->utilized = teo_cpu_is_utilized(dev->cpu, cpu_data);
+	cpu_utilized = teo_cpu_is_utilized(dev->cpu, cpu_data);
 	/*
 	 * If the CPU is being utilized over the threshold and there are only 2
 	 * states to choose from, the metrics need not be considered, so choose
 	 * the shallowest non-polling state and exit.
 	 */
-	if (drv->state_count < 3 && cpu_data->utilized) {
-		for (i = 0; i < drv->state_count; ++i) {
-			if (!dev->states_usage[i].disable &&
-			    !(drv->states[i].flags & CPUIDLE_FLAG_POLLING)) {
-				idx = i;
-				goto end;
-			}
+	if (drv->state_count < 3 && cpu_utilized) {
+		/*
+		 * If state 0 is enabled and it is not a polling one, select it
+		 * right away unless the scheduler tick has been stopped, in
+		 * which case care needs to be taken to leave the CPU in a deep
+		 * enough state in case it is not woken up any time soon after
+		 * all.  If state 1 is disabled, though, state 0 must be used
+		 * anyway.
+		 */
+		if ((!idx && !(drv->states[0].flags & CPUIDLE_FLAG_POLLING) &&
+		    teo_state_ok(0, drv)) || dev->states_usage[1].disable) {
+			idx = 0;
+			goto out_tick;
 		}
+		/* Assume that state 1 is not a polling one and use it. */
+		idx = 1;
+		duration_ns = drv->states[1].target_residency_ns;
+		goto end;
 	}
 
-	/*
-	 * Find the deepest idle state whose target residency does not exceed
-	 * the current sleep length and the deepest idle state not deeper than
-	 * the former whose exit latency does not exceed the current latency
-	 * constraint.  Compute the sums of metrics for early wakeup pattern
-	 * detection.
-	 */
+	/* Compute the sums of metrics for early wakeup pattern detection. */
 	for (i = 1; i < drv->state_count; i++) {
 		struct teo_bin *prev_bin = &cpu_data->state_bins[i-1];
 		struct cpuidle_state *s = &drv->states[i];
@@ -428,19 +453,15 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		if (dev->states_usage[i].disable)
 			continue;
 
-		if (idx < 0) {
-			idx = i; /* first enabled state */
-			idx0 = i;
-		}
-
-		if (s->target_residency_ns > duration_ns)
-			break;
+		if (idx < 0)
+			idx0 = i; /* first enabled state */
 
 		idx = i;
 
 		if (s->exit_latency_ns <= latency_req)
 			constraint_idx = i;
 
+		/* Save the sums for the current state. */
 		idx_intercept_sum = intercept_sum;
 		idx_hit_sum = hit_sum;
 		idx_recent_sum = recent_sum;
@@ -449,11 +470,21 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	/* Avoid unnecessary overhead. */
 	if (idx < 0) {
 		idx = 0; /* No states enabled, must use 0. */
-		goto end;
-	} else if (idx == idx0) {
+		goto out_tick;
+	}
+
+	if (idx == idx0) {
+		/*
+		 * Only one idle state is enabled, so use it, but do not
+		 * allow the tick to be stopped it is shallow enough.
+		 */
+		duration_ns = drv->states[idx].target_residency_ns;
 		goto end;
 	}
 
+	tick_intercept_sum = intercept_sum +
+			cpu_data->state_bins[drv->state_count-1].intercepts;
+
 	/*
 	 * If the sum of the intercepts metric for all of the idle states
 	 * shallower than the current candidate one (idx) is greater than the
@@ -461,13 +492,11 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	 * all of the deeper states, or the sum of the numbers of recent
 	 * intercepts over all of the states shallower than the candidate one
 	 * is greater than a half of the number of recent events taken into
-	 * account, the CPU is likely to wake up early, so find an alternative
-	 * idle state to select.
+	 * account, a shallower idle state is likely to be a better choice.
 	 */
 	alt_intercepts = 2 * idx_intercept_sum > cpu_data->total - idx_hit_sum;
 	alt_recent = idx_recent_sum > NR_RECENT / 2;
 	if (alt_recent || alt_intercepts) {
-		s64 first_suitable_span_ns = duration_ns;
 		int first_suitable_idx = idx;
 
 		/*
@@ -476,44 +505,39 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		 * cases (both with respect to intercepts overall and with
 		 * respect to the recent intercepts only) in the past.
 		 *
-		 * Take the possible latency constraint and duration limitation
-		 * present if the tick has been stopped already into account.
+		 * Take the possible duration limitation present if the tick
+		 * has been stopped already into account.
 		 */
 		intercept_sum = 0;
 		recent_sum = 0;
 
 		for (i = idx - 1; i >= 0; i--) {
 			struct teo_bin *bin = &cpu_data->state_bins[i];
-			s64 span_ns;
 
 			intercept_sum += bin->intercepts;
 			recent_sum += bin->recent;
 
-			span_ns = teo_middle_of_bin(i, drv);
-
 			if ((!alt_recent || 2 * recent_sum > idx_recent_sum) &&
 			    (!alt_intercepts ||
 			     2 * intercept_sum > idx_intercept_sum)) {
-				if (teo_time_ok(span_ns) &&
-				    !dev->states_usage[i].disable) {
+				/*
+				 * Use the current state unless it is too
+				 * shallow or disabled, in which case take the
+				 * first enabled state that is deep enough.
+				 */
+				if (teo_state_ok(i, drv) &&
+				    !dev->states_usage[i].disable)
 					idx = i;
-					duration_ns = span_ns;
-				} else {
-					/*
-					 * The current state is too shallow or
-					 * disabled, so take the first enabled
-					 * deeper state with suitable time span.
-					 */
+				else
 					idx = first_suitable_idx;
-					duration_ns = first_suitable_span_ns;
-				}
+
 				break;
 			}
 
 			if (dev->states_usage[i].disable)
 				continue;
 
-			if (!teo_time_ok(span_ns)) {
+			if (!teo_state_ok(i, drv)) {
 				/*
 				 * The current state is too shallow, but if an
 				 * alternative candidate state has been found,
@@ -525,7 +549,6 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 				break;
 			}
 
-			first_suitable_span_ns = span_ns;
 			first_suitable_idx = i;
 		}
 	}
@@ -539,31 +562,75 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 
 	/*
 	 * If the CPU is being utilized over the threshold, choose a shallower
-	 * non-polling state to improve latency
+	 * non-polling state to improve latency, unless the scheduler tick has
+	 * been stopped already and the shallower state's target residency is
+	 * not sufficiently large.
 	 */
-	if (cpu_data->utilized)
-		idx = teo_find_shallower_state(drv, dev, idx, duration_ns, true);
+	if (cpu_utilized) {
+		i = teo_find_shallower_state(drv, dev, idx, KTIME_MAX, true);
+		if (teo_state_ok(i, drv))
+			idx = i;
+	}
 
-end:
 	/*
-	 * Don't stop the tick if the selected state is a polling one or if the
-	 * expected idle duration is shorter than the tick period length.
+	 * Skip the timers check if state 0 is the current candidate one,
+	 * because an immediate non-timer wakeup is expected in that case.
 	 */
-	if (((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) ||
-	    duration_ns < TICK_NSEC) && !tick_nohz_tick_stopped()) {
-		*stop_tick = false;
+	if (!idx)
+		goto out_tick;
 
-		/*
-		 * The tick is not going to be stopped, so if the target
-		 * residency of the state to be returned is not within the time
-		 * till the closest timer including the tick, try to correct
-		 * that.
-		 */
-		if (idx > idx0 &&
-		    drv->states[idx].target_residency_ns > delta_tick)
-			idx = teo_find_shallower_state(drv, dev, idx, delta_tick, false);
+	/*
+	 * If state 0 is a polling one, check if the target residency of
+	 * the current candidate state is low enough and skip the timers
+	 * check in that case too.
+	 */
+	if ((drv->states[0].flags & CPUIDLE_FLAG_POLLING) &&
+	    drv->states[idx].target_residency_ns < RESIDENCY_THRESHOLD_NS)
+		goto out_tick;
+
+	duration_ns = tick_nohz_get_sleep_length(&delta_tick);
+	cpu_data->sleep_length_ns = duration_ns;
+
+	/*
+	 * If the closest expected timer is before the terget residency of the
+	 * candidate state, a shallower one needs to be found.
+	 */
+	if (drv->states[idx].target_residency_ns > duration_ns) {
+		i = teo_find_shallower_state(drv, dev, idx, duration_ns, false);
+		if (teo_state_ok(i, drv))
+			idx = i;
 	}
 
+	/*
+	 * If the selected state's target residency is below the tick length
+	 * and intercepts occurring before the tick length are the majority of
+	 * total wakeup events, do not stop the tick.
+	 */
+	if (drv->states[idx].target_residency_ns < TICK_NSEC &&
+	    tick_intercept_sum > cpu_data->total / 2 + cpu_data->total / 8)
+		duration_ns = TICK_NSEC / 2;
+
+end:
+	/*
+	 * Allow the tick to be stopped unless the selected state is a polling
+	 * one or the expected idle duration is shorter than the tick period
+	 * length.
+	 */
+	if ((!(drv->states[idx].flags & CPUIDLE_FLAG_POLLING) &&
+	    duration_ns >= TICK_NSEC) || tick_nohz_tick_stopped())
+		return idx;
+
+	/*
+	 * The tick is not going to be stopped, so if the target residency of
+	 * the state to be returned is not within the time till the closest
+	 * timer including the tick, try to correct that.
+	 */
+	if (idx > idx0 &&
+	    drv->states[idx].target_residency_ns > delta_tick)
+		idx = teo_find_shallower_state(drv, dev, idx, delta_tick, false);
+
+out_tick:
+	*stop_tick = false;
 	return idx;
 }
 
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index e36cbb920ec8..474d81831ad3 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -472,10 +472,11 @@ static void devfreq_monitor(struct work_struct *work)
  * devfreq_monitor_start() - Start load monitoring of devfreq instance
  * @devfreq:	the devfreq instance.
  *
- * Helper function for starting devfreq device load monitoring. By
- * default delayed work based monitoring is supported. Function
- * to be called from governor in response to DEVFREQ_GOV_START
- * event when device is added to devfreq framework.
+ * Helper function for starting devfreq device load monitoring. By default,
+ * deferrable timer is used for load monitoring. But the users can change this
+ * behavior using the "timer" type in devfreq_dev_profile. This function will be
+ * called by devfreq governor in response to the DEVFREQ_GOV_START event
+ * generated while adding a device to the devfreq framework.
  */
 void devfreq_monitor_start(struct devfreq *devfreq)
 {
@@ -763,6 +764,7 @@ static void devfreq_dev_release(struct device *dev)
 		dev_pm_opp_put_opp_table(devfreq->opp_table);
 
 	mutex_destroy(&devfreq->lock);
+	srcu_cleanup_notifier_head(&devfreq->transition_notifier_list);
 	kfree(devfreq);
 }
 
diff --git a/drivers/devfreq/imx-bus.c b/drivers/devfreq/imx-bus.c
index a727067980fb..86850b7dea09 100644
--- a/drivers/devfreq/imx-bus.c
+++ b/drivers/devfreq/imx-bus.c
@@ -7,7 +7,7 @@
 #include <linux/devfreq.h>
 #include <linux/device.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/pm_opp.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
diff --git a/drivers/devfreq/imx8m-ddrc.c b/drivers/devfreq/imx8m-ddrc.c
index 16636973eb10..e1348490c8aa 100644
--- a/drivers/devfreq/imx8m-ddrc.c
+++ b/drivers/devfreq/imx8m-ddrc.c
@@ -3,9 +3,9 @@
  * Copyright 2019 NXP
  */
 
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/device.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/devfreq.h>
 #include <linux/pm_opp.h>
diff --git a/drivers/devfreq/mtk-cci-devfreq.c b/drivers/devfreq/mtk-cci-devfreq.c
index 6354622eda65..83a73f0ccd80 100644
--- a/drivers/devfreq/mtk-cci-devfreq.c
+++ b/drivers/devfreq/mtk-cci-devfreq.c
@@ -8,7 +8,6 @@
 #include <linux/minmax.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pm_opp.h>
 #include <linux/regulator/consumer.h>
diff --git a/drivers/devfreq/tegra30-devfreq.c b/drivers/devfreq/tegra30-devfreq.c
index 503376b894b6..4a4f0106ab9d 100644
--- a/drivers/devfreq/tegra30-devfreq.c
+++ b/drivers/devfreq/tegra30-devfreq.c
@@ -13,7 +13,7 @@
 #include <linux/io.h>
 #include <linux/irq.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pm_opp.h>
 #include <linux/reset.h>
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 3f46e499d615..919cc53bc02e 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -177,25 +177,24 @@ unsigned long dev_pm_opp_get_power(struct dev_pm_opp *opp)
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_power);
 
 /**
- * dev_pm_opp_get_freq() - Gets the frequency corresponding to an available opp
- * @opp:	opp for which frequency has to be returned for
+ * dev_pm_opp_get_freq_indexed() - Gets the frequency corresponding to an
+ *				   available opp with specified index
+ * @opp: opp for which frequency has to be returned for
+ * @index: index of the frequency within the required opp
  *
- * Return: frequency in hertz corresponding to the opp, else
- * return 0
+ * Return: frequency in hertz corresponding to the opp with specified index,
+ * else return 0
  */
-unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp)
+unsigned long dev_pm_opp_get_freq_indexed(struct dev_pm_opp *opp, u32 index)
 {
-	if (IS_ERR_OR_NULL(opp)) {
+	if (IS_ERR_OR_NULL(opp) || index >= opp->opp_table->clk_count) {
 		pr_err("%s: Invalid parameters\n", __func__);
 		return 0;
 	}
 
-	if (!assert_single_clk(opp->opp_table))
-		return 0;
-
-	return opp->rates[0];
+	return opp->rates[index];
 }
-EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq);
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq_indexed);
 
 /**
  * dev_pm_opp_get_level() - Gets the level corresponding to an available opp
@@ -227,20 +226,18 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_level);
 unsigned int dev_pm_opp_get_required_pstate(struct dev_pm_opp *opp,
 					    unsigned int index)
 {
-	struct opp_table *opp_table = opp->opp_table;
-
 	if (IS_ERR_OR_NULL(opp) || !opp->available ||
-	    index >= opp_table->required_opp_count) {
+	    index >= opp->opp_table->required_opp_count) {
 		pr_err("%s: Invalid parameters\n", __func__);
 		return 0;
 	}
 
 	/* required-opps not fully initialized yet */
-	if (lazy_linking_pending(opp_table))
+	if (lazy_linking_pending(opp->opp_table))
 		return 0;
 
 	/* The required OPP table must belong to a genpd */
-	if (unlikely(!opp_table->required_opp_tables[index]->is_genpd)) {
+	if (unlikely(!opp->opp_table->required_opp_tables[index]->is_genpd)) {
 		pr_err("%s: Performance state is only valid for genpds.\n", __func__);
 		return 0;
 	}
@@ -450,7 +447,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_count);
 /* Helpers to read keys */
 static unsigned long _read_freq(struct dev_pm_opp *opp, int index)
 {
-	return opp->rates[0];
+	return opp->rates[index];
 }
 
 static unsigned long _read_level(struct dev_pm_opp *opp, int index)
@@ -626,6 +623,34 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_exact);
 
+/**
+ * dev_pm_opp_find_freq_exact_indexed() - Search for an exact freq for the
+ *					 clock corresponding to the index
+ * @dev:	Device for which we do this operation
+ * @freq:	frequency to search for
+ * @index:	Clock index
+ * @available:	true/false - match for available opp
+ *
+ * Search for the matching exact OPP for the clock corresponding to the
+ * specified index from a starting freq for a device.
+ *
+ * Return: matching *opp , else returns ERR_PTR in case of error and should be
+ * handled using IS_ERR. Error return values can be:
+ * EINVAL:	for bad pointer
+ * ERANGE:	no match found for search
+ * ENODEV:	if device not found in list of registered devices
+ *
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
+ */
+struct dev_pm_opp *
+dev_pm_opp_find_freq_exact_indexed(struct device *dev, unsigned long freq,
+				   u32 index, bool available)
+{
+	return _find_key_exact(dev, freq, index, available, _read_freq, NULL);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_exact_indexed);
+
 static noinline struct dev_pm_opp *_find_freq_ceil(struct opp_table *opp_table,
 						   unsigned long *freq)
 {
@@ -659,6 +684,34 @@ struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_ceil);
 
 /**
+ * dev_pm_opp_find_freq_ceil_indexed() - Search for a rounded ceil freq for the
+ *					 clock corresponding to the index
+ * @dev:	Device for which we do this operation
+ * @freq:	Start frequency
+ * @index:	Clock index
+ *
+ * Search for the matching ceil *available* OPP for the clock corresponding to
+ * the specified index from a starting freq for a device.
+ *
+ * Return: matching *opp and refreshes *freq accordingly, else returns
+ * ERR_PTR in case of error and should be handled using IS_ERR. Error return
+ * values can be:
+ * EINVAL:	for bad pointer
+ * ERANGE:	no match found for search
+ * ENODEV:	if device not found in list of registered devices
+ *
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
+ */
+struct dev_pm_opp *
+dev_pm_opp_find_freq_ceil_indexed(struct device *dev, unsigned long *freq,
+				  u32 index)
+{
+	return _find_key_ceil(dev, freq, index, true, _read_freq, NULL);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_ceil_indexed);
+
+/**
  * dev_pm_opp_find_freq_floor() - Search for a rounded floor freq
  * @dev:	device for which we do this operation
  * @freq:	Start frequency
@@ -684,6 +737,34 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_floor);
 
 /**
+ * dev_pm_opp_find_freq_floor_indexed() - Search for a rounded floor freq for the
+ *					  clock corresponding to the index
+ * @dev:	Device for which we do this operation
+ * @freq:	Start frequency
+ * @index:	Clock index
+ *
+ * Search for the matching floor *available* OPP for the clock corresponding to
+ * the specified index from a starting freq for a device.
+ *
+ * Return: matching *opp and refreshes *freq accordingly, else returns
+ * ERR_PTR in case of error and should be handled using IS_ERR. Error return
+ * values can be:
+ * EINVAL:	for bad pointer
+ * ERANGE:	no match found for search
+ * ENODEV:	if device not found in list of registered devices
+ *
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
+ */
+struct dev_pm_opp *
+dev_pm_opp_find_freq_floor_indexed(struct device *dev, unsigned long *freq,
+				   u32 index)
+{
+	return _find_key_floor(dev, freq, index, true, _read_freq, NULL);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_floor_indexed);
+
+/**
  * dev_pm_opp_find_level_exact() - search for an exact level
  * @dev:		device for which we do this operation
  * @level:		level to search for
@@ -2379,7 +2460,7 @@ static int _opp_attach_genpd(struct opp_table *opp_table, struct device *dev,
 
 		virt_dev = dev_pm_domain_attach_by_name(dev, *name);
 		if (IS_ERR_OR_NULL(virt_dev)) {
-			ret = PTR_ERR(virt_dev) ? : -ENODEV;
+			ret = virt_dev ? PTR_ERR(virt_dev) : -ENODEV;
 			dev_err(dev, "Couldn't attach to pm_domain: %d\n", ret);
 			goto err;
 		}
diff --git a/drivers/opp/cpu.c b/drivers/opp/cpu.c
index 3c3506021501..12c429b407ca 100644
--- a/drivers/opp/cpu.c
+++ b/drivers/opp/cpu.c
@@ -24,7 +24,7 @@
 /**
  * dev_pm_opp_init_cpufreq_table() - create a cpufreq table for a device
  * @dev:	device for which we do this operation
- * @table:	Cpufreq table returned back to caller
+ * @opp_table:	Cpufreq table returned back to caller
  *
  * Generate a cpufreq table for a provided device- this assumes that the
  * opp table is already initialized and ready for usage.
@@ -89,7 +89,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_init_cpufreq_table);
 /**
  * dev_pm_opp_free_cpufreq_table() - free the cpufreq table
  * @dev:	device for which we do this operation
- * @table:	table to free
+ * @opp_table:	table to free
  *
  * Free up the table allocated by dev_pm_opp_init_cpufreq_table
  */
diff --git a/drivers/powercap/arm_scmi_powercap.c b/drivers/powercap/arm_scmi_powercap.c
index 5231f6d52ae3..a081f177e702 100644
--- a/drivers/powercap/arm_scmi_powercap.c
+++ b/drivers/powercap/arm_scmi_powercap.c
@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <linux/powercap.h>
 #include <linux/scmi_protocol.h>
+#include <linux/slab.h>
 
 #define to_scmi_powercap_zone(z)		\
 	container_of(z, struct scmi_powercap_zone, zone)
@@ -19,6 +20,8 @@
 static const struct scmi_powercap_proto_ops *powercap_ops;
 
 struct scmi_powercap_zone {
+	bool registered;
+	bool invalid;
 	unsigned int height;
 	struct device *dev;
 	struct scmi_protocol_handle *ph;
@@ -32,6 +35,7 @@ struct scmi_powercap_root {
 	unsigned int num_zones;
 	struct scmi_powercap_zone *spzones;
 	struct list_head *registered_zones;
+	struct list_head scmi_zones;
 };
 
 static struct powercap_control_type *scmi_top_pcntrl;
@@ -271,12 +275,6 @@ static void scmi_powercap_unregister_all_zones(struct scmi_powercap_root *pr)
 	}
 }
 
-static inline bool
-scmi_powercap_is_zone_registered(struct scmi_powercap_zone *spz)
-{
-	return !list_empty(&spz->node);
-}
-
 static inline unsigned int
 scmi_powercap_get_zone_height(struct scmi_powercap_zone *spz)
 {
@@ -295,11 +293,46 @@ scmi_powercap_get_parent_zone(struct scmi_powercap_zone *spz)
 	return &spz->spzones[spz->info->parent_id];
 }
 
+static int scmi_powercap_register_zone(struct scmi_powercap_root *pr,
+				       struct scmi_powercap_zone *spz,
+				       struct scmi_powercap_zone *parent)
+{
+	int ret = 0;
+	struct powercap_zone *z;
+
+	if (spz->invalid) {
+		list_del(&spz->node);
+		return -EINVAL;
+	}
+
+	z = powercap_register_zone(&spz->zone, scmi_top_pcntrl, spz->info->name,
+				   parent ? &parent->zone : NULL,
+				   &zone_ops, 1, &constraint_ops);
+	if (!IS_ERR(z)) {
+		spz->height = scmi_powercap_get_zone_height(spz);
+		spz->registered = true;
+		list_move(&spz->node, &pr->registered_zones[spz->height]);
+		dev_dbg(spz->dev, "Registered node %s - parent %s - height:%d\n",
+			spz->info->name, parent ? parent->info->name : "ROOT",
+			spz->height);
+	} else {
+		list_del(&spz->node);
+		ret = PTR_ERR(z);
+		dev_err(spz->dev,
+			"Error registering node:%s - parent:%s - h:%d - ret:%d\n",
+			spz->info->name,
+			parent ? parent->info->name : "ROOT",
+			spz->height, ret);
+	}
+
+	return ret;
+}
+
 /**
- * scmi_powercap_register_zone  - Register an SCMI powercap zone recursively
+ * scmi_zones_register- Register SCMI powercap zones starting from parent zones
  *
+ * @dev: A reference to the SCMI device
  * @pr: A reference to the root powercap zones descriptors
- * @spz: A reference to the SCMI powercap zone to register
  *
  * When registering SCMI powercap zones with the powercap framework we should
  * take care to always register zones starting from the root ones and to
@@ -309,10 +342,10 @@ scmi_powercap_get_parent_zone(struct scmi_powercap_zone *spz)
  * zones provided by the SCMI platform firmware is built to comply with such
  * requirement.
  *
- * This function, given an SCMI powercap zone to register, takes care to walk
- * the SCMI powercap zones tree up to the root looking recursively for
- * unregistered parent zones before registering the provided zone; at the same
- * time each registered zone height in such a tree is accounted for and each
+ * This function, given the set of SCMI powercap zones to register, takes care
+ * to walk the SCMI powercap zones trees up to the root registering any
+ * unregistered parent zone before registering the child zones; at the same
+ * time each registered-zone height in such a tree is accounted for and each
  * zone, once registered, is stored in the @registered_zones array that is
  * indexed by zone height: this way will be trivial, at unregister time, to walk
  * the @registered_zones array backward and unregister all the zones starting
@@ -330,57 +363,55 @@ scmi_powercap_get_parent_zone(struct scmi_powercap_zone *spz)
  *
  * Return: 0 on Success
  */
-static int scmi_powercap_register_zone(struct scmi_powercap_root *pr,
-				       struct scmi_powercap_zone *spz)
+static int scmi_zones_register(struct device *dev,
+			       struct scmi_powercap_root *pr)
 {
 	int ret = 0;
-	struct scmi_powercap_zone *parent;
-
-	if (!spz->info)
-		return ret;
+	unsigned int sp = 0, reg_zones = 0;
+	struct scmi_powercap_zone *spz, **zones_stack;
 
-	parent = scmi_powercap_get_parent_zone(spz);
-	if (parent && !scmi_powercap_is_zone_registered(parent)) {
-		/*
-		 * Bail out if a parent domain was marked as unsupported:
-		 * only domains participating as leaves can be skipped.
-		 */
-		if (!parent->info)
-			return -ENODEV;
+	zones_stack = kcalloc(pr->num_zones, sizeof(spz), GFP_KERNEL);
+	if (!zones_stack)
+		return -ENOMEM;
 
-		ret = scmi_powercap_register_zone(pr, parent);
-		if (ret)
-			return ret;
-	}
+	spz = list_first_entry_or_null(&pr->scmi_zones,
+				       struct scmi_powercap_zone, node);
+	while (spz) {
+		struct scmi_powercap_zone *parent;
 
-	if (!scmi_powercap_is_zone_registered(spz)) {
-		struct powercap_zone *z;
-
-		z = powercap_register_zone(&spz->zone,
-					   scmi_top_pcntrl,
-					   spz->info->name,
-					   parent ? &parent->zone : NULL,
-					   &zone_ops, 1, &constraint_ops);
-		if (!IS_ERR(z)) {
-			spz->height = scmi_powercap_get_zone_height(spz);
-			list_add(&spz->node,
-				 &pr->registered_zones[spz->height]);
-			dev_dbg(spz->dev,
-				"Registered node %s - parent %s - height:%d\n",
-				spz->info->name,
-				parent ? parent->info->name : "ROOT",
-				spz->height);
-			ret = 0;
+		parent = scmi_powercap_get_parent_zone(spz);
+		if (parent && !parent->registered) {
+			zones_stack[sp++] = spz;
+			spz = parent;
 		} else {
-			ret = PTR_ERR(z);
-			dev_err(spz->dev,
-				"Error registering node:%s - parent:%s - h:%d - ret:%d\n",
-				 spz->info->name,
-				 parent ? parent->info->name : "ROOT",
-				 spz->height, ret);
+			ret = scmi_powercap_register_zone(pr, spz, parent);
+			if (!ret) {
+				reg_zones++;
+			} else if (sp) {
+				/* Failed to register a non-leaf zone.
+				 * Bail-out.
+				 */
+				dev_err(dev,
+					"Failed to register non-leaf zone - ret:%d\n",
+					ret);
+				scmi_powercap_unregister_all_zones(pr);
+				reg_zones = 0;
+				goto out;
+			}
+			/* Pick next zone to process */
+			if (sp)
+				spz = zones_stack[--sp];
+			else
+				spz = list_first_entry_or_null(&pr->scmi_zones,
+							       struct scmi_powercap_zone,
+							       node);
 		}
 	}
 
+out:
+	kfree(zones_stack);
+	dev_info(dev, "Registered %d SCMI Powercap domains !\n", reg_zones);
+
 	return ret;
 }
 
@@ -424,6 +455,8 @@ static int scmi_powercap_probe(struct scmi_device *sdev)
 	if (!pr->registered_zones)
 		return -ENOMEM;
 
+	INIT_LIST_HEAD(&pr->scmi_zones);
+
 	for (i = 0, spz = pr->spzones; i < pr->num_zones; i++, spz++) {
 		/*
 		 * Powercap domains are validate by the protocol layer, i.e.
@@ -438,6 +471,7 @@ static int scmi_powercap_probe(struct scmi_device *sdev)
 		INIT_LIST_HEAD(&spz->node);
 		INIT_LIST_HEAD(&pr->registered_zones[i]);
 
+		list_add_tail(&spz->node, &pr->scmi_zones);
 		/*
 		 * Forcibly skip powercap domains using an abstract scale.
 		 * Note that only leaves domains can be skipped, so this could
@@ -448,7 +482,7 @@ static int scmi_powercap_probe(struct scmi_device *sdev)
 			dev_warn(dev,
 				 "Abstract power scale not supported. Skip %s.\n",
 				 spz->info->name);
-			spz->info = NULL;
+			spz->invalid = true;
 			continue;
 		}
 	}
@@ -457,21 +491,12 @@ static int scmi_powercap_probe(struct scmi_device *sdev)
 	 * Scan array of retrieved SCMI powercap domains and register them
 	 * recursively starting from the root domains.
 	 */
-	for (i = 0, spz = pr->spzones; i < pr->num_zones; i++, spz++) {
-		ret = scmi_powercap_register_zone(pr, spz);
-		if (ret) {
-			dev_err(dev,
-				"Failed to register powercap zone %s - ret:%d\n",
-				spz->info->name, ret);
-			scmi_powercap_unregister_all_zones(pr);
-			return ret;
-		}
-	}
+	ret = scmi_zones_register(dev, pr);
+	if (ret)
+		return ret;
 
 	dev_set_drvdata(dev, pr);
 
-	dev_info(dev, "Registered %d SCMI Powercap domains !\n", pr->num_zones);
-
 	return ret;
 }
 
diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index 72a8d336f980..5c2e6d5eea2a 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -1485,7 +1485,7 @@ static int rapl_detect_domains(struct rapl_package *rp)
 	}
 	pr_debug("found %d domains on %s\n", rp->nr_domains, rp->name);
 
-	rp->domains = kcalloc(rp->nr_domains + 1, sizeof(struct rapl_domain),
+	rp->domains = kcalloc(rp->nr_domains, sizeof(struct rapl_domain),
 			      GFP_KERNEL);
 	if (!rp->domains)
 		return -ENOMEM;