Merge tag 'pm-5.19-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull more power management updates from Rafael Wysocki:
 "These update the ARM cpufreq drivers and fix up the CPPC cpufreq
  driver after recent changes, update the OPP code and PM documentation
  and add power sequences support to the system reboot and power off
  code.

  Specifics:

   - Add Tegra234 cpufreq support (Sumit Gupta)

   - Clean up and enhance the Mediatek cpufreq driver (Wan Jiabing,
     Rex-BC Chen, and Jia-Wei Chang)

   - Fix up the CPPC cpufreq driver after recent changes (Zheng Bin,
     Pierre Gondois)

   - Minor update to dt-binding for Qcom's opp-v2-kryo-cpu (Yassine
     Oudjana)

   - Use list iterator only inside the list_for_each_entry loop
     (Xiaomeng Tong, and Jakob Koschel)

   - New APIs related to finding OPP based on interconnect bandwidth
     (Krzysztof Kozlowski)

   - Fix the missing of_node_put() in _bandwidth_supported() (Dan
     Carpenter)

   - Cleanups (Krzysztof Kozlowski, and Viresh Kumar)

   - Add Out of Band mode description to the intel-speed-select utility
     documentation (Srinivas Pandruvada)

   - Add power sequences support to the system reboot and power off code
     and make related platform-specific changes for multiple platforms
     (Dmitry Osipenko, Geert Uytterhoeven)"

* tag 'pm-5.19-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (60 commits)
  cpufreq: CPPC: Fix unused-function warning
  cpufreq: CPPC: Fix build error without CONFIG_ACPI_CPPC_CPUFREQ_FIE
  Documentation: admin-guide: PM: Add Out of Band mode
  kernel/reboot: Change registration order of legacy power-off handler
  m68k: virt: Switch to new sys-off handler API
  kernel/reboot: Add devm_register_restart_handler()
  kernel/reboot: Add devm_register_power_off_handler()
  soc/tegra: pmc: Use sys-off handler API to power off Nexus 7 properly
  reboot: Remove pm_power_off_prepare()
  regulator: pfuze100: Use devm_register_sys_off_handler()
  ACPI: power: Switch to sys-off handler API
  memory: emif: Use kernel_can_power_off()
  mips: Use do_kernel_power_off()
  ia64: Use do_kernel_power_off()
  x86: Use do_kernel_power_off()
  sh: Use do_kernel_power_off()
  m68k: Switch to new sys-off handler API
  powerpc: Use do_kernel_power_off()
  xen/x86: Use do_kernel_power_off()
  parisc: Use do_kernel_power_off()
  ...

10 files changed, 960 insertions, 440 deletions

diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 3147702710af..04ea1569df78 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -1035,20 +1035,22 @@ static void acpi_sleep_hibernate_setup(void)
 static inline void acpi_sleep_hibernate_setup(void) {}
 #endif /* !CONFIG_HIBERNATION */
 
-static void acpi_power_off_prepare(void)
+static int acpi_power_off_prepare(struct sys_off_data *data)
 {
 	/* Prepare to power off the system */
 	acpi_sleep_prepare(ACPI_STATE_S5);
 	acpi_disable_all_gpes();
 	acpi_os_wait_events_complete();
+	return NOTIFY_DONE;
 }
 
-static void acpi_power_off(void)
+static int acpi_power_off(struct sys_off_data *data)
 {
 	/* acpi_sleep_prepare(ACPI_STATE_S5) should have already been called */
 	pr_debug("%s called\n", __func__);
 	local_irq_disable();
 	acpi_enter_sleep_state(ACPI_STATE_S5);
+	return NOTIFY_DONE;
 }
 
 int __init acpi_sleep_init(void)
@@ -1067,8 +1069,14 @@ int __init acpi_sleep_init(void)
 
 	if (acpi_sleep_state_supported(ACPI_STATE_S5)) {
 		sleep_states[ACPI_STATE_S5] = 1;
-		pm_power_off_prepare = acpi_power_off_prepare;
-		pm_power_off = acpi_power_off;
+
+		register_sys_off_handler(SYS_OFF_MODE_POWER_OFF_PREPARE,
+					 SYS_OFF_PRIO_FIRMWARE,
+					 acpi_power_off_prepare, NULL);
+
+		register_sys_off_handler(SYS_OFF_MODE_POWER_OFF,
+					 SYS_OFF_PRIO_FIRMWARE,
+					 acpi_power_off, NULL);
 	} else {
 		acpi_no_s5 = true;
 	}
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index d092c9bb4ba3..24eaf0ec344d 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -61,6 +61,8 @@ static struct cppc_workaround_oem_info wa_info[] = {
 	}
 };
 
+static struct cpufreq_driver cppc_cpufreq_driver;
+
 #ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE
 
 /* Frequency invariance support */
@@ -75,7 +77,6 @@ struct cppc_freq_invariance {
 static DEFINE_PER_CPU(struct cppc_freq_invariance, cppc_freq_inv);
 static struct kthread_worker *kworker_fie;
 
-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,
@@ -440,6 +441,14 @@ static unsigned int cppc_cpufreq_get_transition_delay_us(unsigned int cpu)
 	}
 	return cppc_get_transition_latency(cpu) / NSEC_PER_USEC;
 }
+#else
+static unsigned int cppc_cpufreq_get_transition_delay_us(unsigned int cpu)
+{
+	return cppc_get_transition_latency(cpu) / NSEC_PER_USEC;
+}
+#endif
+
+#if defined(CONFIG_ARM64) && defined(CONFIG_ENERGY_MODEL)
 
 static DEFINE_PER_CPU(unsigned int, efficiency_class);
 static void cppc_cpufreq_register_em(struct cpufreq_policy *policy);
@@ -620,21 +629,12 @@ static void cppc_cpufreq_register_em(struct cpufreq_policy *policy)
 }
 
 #else
-
-static unsigned int cppc_cpufreq_get_transition_delay_us(unsigned int cpu)
-{
-	return cppc_get_transition_latency(cpu) / NSEC_PER_USEC;
-}
 static int populate_efficiency_class(void)
 {
 	return 0;
 }
-static void cppc_cpufreq_register_em(struct cpufreq_policy *policy)
-{
-}
 #endif
 
-
 static struct cppc_cpudata *cppc_cpufreq_get_cpu_data(unsigned int cpu)
 {
 	struct cppc_cpudata *cpu_data;
diff --git a/drivers/cpufreq/mediatek-cpufreq.c b/drivers/cpufreq/mediatek-cpufreq.c
index 866163883b48..37a1eb20f5ba 100644
--- a/drivers/cpufreq/mediatek-cpufreq.c
+++ b/drivers/cpufreq/mediatek-cpufreq.c
@@ -8,18 +8,22 @@
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/cpumask.h>
+#include <linux/minmax.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/regulator/consumer.h>
-#include <linux/slab.h>
-#include <linux/thermal.h>
 
-#define MIN_VOLT_SHIFT		(100000)
-#define MAX_VOLT_SHIFT		(200000)
-#define MAX_VOLT_LIMIT		(1150000)
-#define VOLT_TOL		(10000)
+struct mtk_cpufreq_platform_data {
+	int min_volt_shift;
+	int max_volt_shift;
+	int proc_max_volt;
+	int sram_min_volt;
+	int sram_max_volt;
+	bool ccifreq_supported;
+};
 
 /*
  * The struct mtk_cpu_dvfs_info holds necessary information for doing CPU DVFS
@@ -35,6 +39,7 @@
 struct mtk_cpu_dvfs_info {
 	struct cpumask cpus;
 	struct device *cpu_dev;
+	struct device *cci_dev;
 	struct regulator *proc_reg;
 	struct regulator *sram_reg;
 	struct clk *cpu_clk;
@@ -42,8 +47,20 @@ struct mtk_cpu_dvfs_info {
 	struct list_head list_head;
 	int intermediate_voltage;
 	bool need_voltage_tracking;
+	int vproc_on_boot;
+	int pre_vproc;
+	/* Avoid race condition for regulators between notify and policy */
+	struct mutex reg_lock;
+	struct notifier_block opp_nb;
+	unsigned int opp_cpu;
+	unsigned long current_freq;
+	const struct mtk_cpufreq_platform_data *soc_data;
+	int vtrack_max;
+	bool ccifreq_bound;
 };
 
+static struct platform_device *cpufreq_pdev;
+
 static LIST_HEAD(dvfs_info_list);
 
 static struct mtk_cpu_dvfs_info *mtk_cpu_dvfs_info_lookup(int cpu)
@@ -61,142 +78,123 @@ static struct mtk_cpu_dvfs_info *mtk_cpu_dvfs_info_lookup(int cpu)
 static int mtk_cpufreq_voltage_tracking(struct mtk_cpu_dvfs_info *info,
 					int new_vproc)
 {
+	const struct mtk_cpufreq_platform_data *soc_data = info->soc_data;
 	struct regulator *proc_reg = info->proc_reg;
 	struct regulator *sram_reg = info->sram_reg;
-	int old_vproc, old_vsram, new_vsram, vsram, vproc, ret;
-
-	old_vproc = regulator_get_voltage(proc_reg);
-	if (old_vproc < 0) {
-		pr_err("%s: invalid Vproc value: %d\n", __func__, old_vproc);
-		return old_vproc;
-	}
-	/* Vsram should not exceed the maximum allowed voltage of SoC. */
-	new_vsram = min(new_vproc + MIN_VOLT_SHIFT, MAX_VOLT_LIMIT);
-
-	if (old_vproc < new_vproc) {
-		/*
-		 * When scaling up voltages, Vsram and Vproc scale up step
-		 * by step. At each step, set Vsram to (Vproc + 200mV) first,
-		 * then set Vproc to (Vsram - 100mV).
-		 * Keep doing it until Vsram and Vproc hit target voltages.
-		 */
-		do {
-			old_vsram = regulator_get_voltage(sram_reg);
-			if (old_vsram < 0) {
-				pr_err("%s: invalid Vsram value: %d\n",
-				       __func__, old_vsram);
-				return old_vsram;
-			}
-			old_vproc = regulator_get_voltage(proc_reg);
-			if (old_vproc < 0) {
-				pr_err("%s: invalid Vproc value: %d\n",
-				       __func__, old_vproc);
-				return old_vproc;
-			}
-
-			vsram = min(new_vsram, old_vproc + MAX_VOLT_SHIFT);
+	int pre_vproc, pre_vsram, new_vsram, vsram, vproc, ret;
+	int retry = info->vtrack_max;
+
+	pre_vproc = regulator_get_voltage(proc_reg);
+	if (pre_vproc < 0) {
+		dev_err(info->cpu_dev,
+			"invalid Vproc value: %d\n", pre_vproc);
+		return pre_vproc;
+	}
 
-			if (vsram + VOLT_TOL >= MAX_VOLT_LIMIT) {
-				vsram = MAX_VOLT_LIMIT;
+	pre_vsram = regulator_get_voltage(sram_reg);
+	if (pre_vsram < 0) {
+		dev_err(info->cpu_dev, "invalid Vsram value: %d\n", pre_vsram);
+		return pre_vsram;
+	}
 
-				/*
-				 * If the target Vsram hits the maximum voltage,
-				 * try to set the exact voltage value first.
-				 */
-				ret = regulator_set_voltage(sram_reg, vsram,
-							    vsram);
-				if (ret)
-					ret = regulator_set_voltage(sram_reg,
-							vsram - VOLT_TOL,
-							vsram);
+	new_vsram = clamp(new_vproc + soc_data->min_volt_shift,
+			  soc_data->sram_min_volt, soc_data->sram_max_volt);
 
-				vproc = new_vproc;
-			} else {
-				ret = regulator_set_voltage(sram_reg, vsram,
-							    vsram + VOLT_TOL);
+	do {
+		if (pre_vproc <= new_vproc) {
+			vsram = clamp(pre_vproc + soc_data->max_volt_shift,
+				      soc_data->sram_min_volt, new_vsram);
+			ret = regulator_set_voltage(sram_reg, vsram,
+						    soc_data->sram_max_volt);
 
-				vproc = vsram - MIN_VOLT_SHIFT;
-			}
 			if (ret)
 				return ret;
 
+			if (vsram == soc_data->sram_max_volt ||
+			    new_vsram == soc_data->sram_min_volt)
+				vproc = new_vproc;
+			else
+				vproc = vsram - soc_data->min_volt_shift;
+
 			ret = regulator_set_voltage(proc_reg, vproc,
-						    vproc + VOLT_TOL);
+						    soc_data->proc_max_volt);
 			if (ret) {
-				regulator_set_voltage(sram_reg, old_vsram,
-						      old_vsram);
+				regulator_set_voltage(sram_reg, pre_vsram,
+						      soc_data->sram_max_volt);
 				return ret;
 			}
-		} while (vproc < new_vproc || vsram < new_vsram);
-	} else if (old_vproc > new_vproc) {
-		/*
-		 * When scaling down voltages, Vsram and Vproc scale down step
-		 * by step. At each step, set Vproc to (Vsram - 200mV) first,
-		 * then set Vproc to (Vproc + 100mV).
-		 * Keep doing it until Vsram and Vproc hit target voltages.
-		 */
-		do {
-			old_vproc = regulator_get_voltage(proc_reg);
-			if (old_vproc < 0) {
-				pr_err("%s: invalid Vproc value: %d\n",
-				       __func__, old_vproc);
-				return old_vproc;
-			}
-			old_vsram = regulator_get_voltage(sram_reg);
-			if (old_vsram < 0) {
-				pr_err("%s: invalid Vsram value: %d\n",
-				       __func__, old_vsram);
-				return old_vsram;
-			}
-
-			vproc = max(new_vproc, old_vsram - MAX_VOLT_SHIFT);
+		} else if (pre_vproc > new_vproc) {
+			vproc = max(new_vproc,
+				    pre_vsram - soc_data->max_volt_shift);
 			ret = regulator_set_voltage(proc_reg, vproc,
-						    vproc + VOLT_TOL);
+						    soc_data->proc_max_volt);
 			if (ret)
 				return ret;
 
 			if (vproc == new_vproc)
 				vsram = new_vsram;
 			else
-				vsram = max(new_vsram, vproc + MIN_VOLT_SHIFT);
-
-			if (vsram + VOLT_TOL >= MAX_VOLT_LIMIT) {
-				vsram = MAX_VOLT_LIMIT;
-
-				/*
-				 * If the target Vsram hits the maximum voltage,
-				 * try to set the exact voltage value first.
-				 */
-				ret = regulator_set_voltage(sram_reg, vsram,
-							    vsram);
-				if (ret)
-					ret = regulator_set_voltage(sram_reg,
-							vsram - VOLT_TOL,
-							vsram);
-			} else {
-				ret = regulator_set_voltage(sram_reg, vsram,
-							    vsram + VOLT_TOL);
-			}
+				vsram = max(new_vsram,
+					    vproc + soc_data->min_volt_shift);
 
+			ret = regulator_set_voltage(sram_reg, vsram,
+						    soc_data->sram_max_volt);
 			if (ret) {
-				regulator_set_voltage(proc_reg, old_vproc,
-						      old_vproc);
+				regulator_set_voltage(proc_reg, pre_vproc,
+						      soc_data->proc_max_volt);
 				return ret;
 			}
-		} while (vproc > new_vproc + VOLT_TOL ||
-			 vsram > new_vsram + VOLT_TOL);
-	}
+		}
+
+		pre_vproc = vproc;
+		pre_vsram = vsram;
+
+		if (--retry < 0) {
+			dev_err(info->cpu_dev,
+				"over loop count, failed to set voltage\n");
+			return -EINVAL;
+		}
+	} while (vproc != new_vproc || vsram != new_vsram);
 
 	return 0;
 }
 
 static int mtk_cpufreq_set_voltage(struct mtk_cpu_dvfs_info *info, int vproc)
 {
+	const struct mtk_cpufreq_platform_data *soc_data = info->soc_data;
+	int ret;
+
 	if (info->need_voltage_tracking)
-		return mtk_cpufreq_voltage_tracking(info, vproc);
+		ret = mtk_cpufreq_voltage_tracking(info, vproc);
 	else
-		return regulator_set_voltage(info->proc_reg, vproc,
-					     vproc + VOLT_TOL);
+		ret = regulator_set_voltage(info->proc_reg, vproc,
+					    soc_data->proc_max_volt);
+	if (!ret)
+		info->pre_vproc = vproc;
+
+	return ret;
+}
+
+static bool is_ccifreq_ready(struct mtk_cpu_dvfs_info *info)
+{
+	struct device_link *sup_link;
+
+	if (info->ccifreq_bound)
+		return true;
+
+	sup_link = device_link_add(info->cpu_dev, info->cci_dev,
+				   DL_FLAG_AUTOREMOVE_CONSUMER);
+	if (!sup_link) {
+		dev_err(info->cpu_dev, "cpu%d: sup_link is NULL\n", info->opp_cpu);
+		return false;
+	}
+
+	if (sup_link->supplier->links.status != DL_DEV_DRIVER_BOUND)
+		return false;
+
+	info->ccifreq_bound = true;
+
+	return true;
 }
 
 static int mtk_cpufreq_set_target(struct cpufreq_policy *policy,
@@ -208,219 +206,367 @@ static int mtk_cpufreq_set_target(struct cpufreq_policy *policy,
 	struct mtk_cpu_dvfs_info *info = policy->driver_data;
 	struct device *cpu_dev = info->cpu_dev;
 	struct dev_pm_opp *opp;
-	long freq_hz, old_freq_hz;
-	int vproc, old_vproc, inter_vproc, target_vproc, ret;
+	long freq_hz, pre_freq_hz;
+	int vproc, pre_vproc, inter_vproc, target_vproc, ret;
 
 	inter_vproc = info->intermediate_voltage;
 
-	old_freq_hz = clk_get_rate(cpu_clk);
-	old_vproc = regulator_get_voltage(info->proc_reg);
-	if (old_vproc < 0) {
-		pr_err("%s: invalid Vproc value: %d\n", __func__, old_vproc);
-		return old_vproc;
+	pre_freq_hz = clk_get_rate(cpu_clk);
+
+	mutex_lock(&info->reg_lock);
+
+	if (unlikely(info->pre_vproc <= 0))
+		pre_vproc = regulator_get_voltage(info->proc_reg);
+	else
+		pre_vproc = info->pre_vproc;
+
+	if (pre_vproc < 0) {
+		dev_err(cpu_dev, "invalid Vproc value: %d\n", pre_vproc);
+		ret = pre_vproc;
+		goto out;
 	}
 
 	freq_hz = freq_table[index].frequency * 1000;
 
 	opp = dev_pm_opp_find_freq_ceil(cpu_dev, &freq_hz);
 	if (IS_ERR(opp)) {
-		pr_err("cpu%d: failed to find OPP for %ld\n",
-		       policy->cpu, freq_hz);
-		return PTR_ERR(opp);
+		dev_err(cpu_dev, "cpu%d: failed to find OPP for %ld\n",
+			policy->cpu, freq_hz);
+		ret = PTR_ERR(opp);
+		goto out;
 	}
 	vproc = dev_pm_opp_get_voltage(opp);
 	dev_pm_opp_put(opp);
 
 	/*
+	 * If MediaTek cci is supported but is not ready, we will use the value
+	 * of max(target cpu voltage, booting voltage) to prevent high freqeuncy
+	 * low voltage crash.
+	 */
+	if (info->soc_data->ccifreq_supported && !is_ccifreq_ready(info))
+		vproc = max(vproc, info->vproc_on_boot);
+
+	/*
 	 * If the new voltage or the intermediate voltage is higher than the
 	 * current voltage, scale up voltage first.
 	 */
-	target_vproc = (inter_vproc > vproc) ? inter_vproc : vproc;
-	if (old_vproc < target_vproc) {
+	target_vproc = max(inter_vproc, vproc);
+	if (pre_vproc <= target_vproc) {
 		ret = mtk_cpufreq_set_voltage(info, target_vproc);
 		if (ret) {
-			pr_err("cpu%d: failed to scale up voltage!\n",
-			       policy->cpu);
-			mtk_cpufreq_set_voltage(info, old_vproc);
-			return ret;
+			dev_err(cpu_dev,
+				"cpu%d: failed to scale up voltage!\n", policy->cpu);
+			mtk_cpufreq_set_voltage(info, pre_vproc);
+			goto out;
 		}
 	}
 
 	/* Reparent the CPU clock to intermediate clock. */
 	ret = clk_set_parent(cpu_clk, info->inter_clk);
 	if (ret) {
-		pr_err("cpu%d: failed to re-parent cpu clock!\n",
-		       policy->cpu);
-		mtk_cpufreq_set_voltage(info, old_vproc);
-		WARN_ON(1);
-		return ret;
+		dev_err(cpu_dev,
+			"cpu%d: failed to re-parent cpu clock!\n", policy->cpu);
+		mtk_cpufreq_set_voltage(info, pre_vproc);
+		goto out;
 	}
 
 	/* Set the original PLL to target rate. */
 	ret = clk_set_rate(armpll, freq_hz);
 	if (ret) {
-		pr_err("cpu%d: failed to scale cpu clock rate!\n",
-		       policy->cpu);
+		dev_err(cpu_dev,
+			"cpu%d: failed to scale cpu clock rate!\n", policy->cpu);
 		clk_set_parent(cpu_clk, armpll);
-		mtk_cpufreq_set_voltage(info, old_vproc);
-		return ret;
+		mtk_cpufreq_set_voltage(info, pre_vproc);
+		goto out;
 	}
 
 	/* Set parent of CPU clock back to the original PLL. */
 	ret = clk_set_parent(cpu_clk, armpll);
 	if (ret) {
-		pr_err("cpu%d: failed to re-parent cpu clock!\n",
-		       policy->cpu);
+		dev_err(cpu_dev,
+			"cpu%d: failed to re-parent cpu clock!\n", policy->cpu);
 		mtk_cpufreq_set_voltage(info, inter_vproc);
-		WARN_ON(1);
-		return ret;
+		goto out;
 	}
 
 	/*
 	 * If the new voltage is lower than the intermediate voltage or the
 	 * original voltage, scale down to the new voltage.
 	 */
-	if (vproc < inter_vproc || vproc < old_vproc) {
+	if (vproc < inter_vproc || vproc < pre_vproc) {
 		ret = mtk_cpufreq_set_voltage(info, vproc);
 		if (ret) {
-			pr_err("cpu%d: failed to scale down voltage!\n",
-			       policy->cpu);
+			dev_err(cpu_dev,
+				"cpu%d: failed to scale down voltage!\n", policy->cpu);
 			clk_set_parent(cpu_clk, info->inter_clk);
-			clk_set_rate(armpll, old_freq_hz);
+			clk_set_rate(armpll, pre_freq_hz);
 			clk_set_parent(cpu_clk, armpll);
-			return ret;
+			goto out;
 		}
 	}
 
-	return 0;
+	info->current_freq = freq_hz;
+
+out:
+	mutex_unlock(&info->reg_lock);
+
+	return ret;
 }
 
 #define DYNAMIC_POWER "dynamic-power-coefficient"
 
+static int mtk_cpufreq_opp_notifier(struct notifier_block *nb,
+				    unsigned long event, void *data)
+{
+	struct dev_pm_opp *opp = data;
+	struct dev_pm_opp *new_opp;
+	struct mtk_cpu_dvfs_info *info;
+	unsigned long freq, volt;
+	struct cpufreq_policy *policy;
+	int ret = 0;
+
+	info = container_of(nb, struct mtk_cpu_dvfs_info, opp_nb);
+
+	if (event == OPP_EVENT_ADJUST_VOLTAGE) {
+		freq = dev_pm_opp_get_freq(opp);
+
+		mutex_lock(&info->reg_lock);
+		if (info->current_freq == freq) {
+			volt = dev_pm_opp_get_voltage(opp);
+			ret = mtk_cpufreq_set_voltage(info, volt);
+			if (ret)
+				dev_err(info->cpu_dev,
+					"failed to scale voltage: %d\n", ret);
+		}
+		mutex_unlock(&info->reg_lock);
+	} else if (event == OPP_EVENT_DISABLE) {
+		freq = dev_pm_opp_get_freq(opp);
+
+		/* case of current opp item is disabled */
+		if (info->current_freq == freq) {
+			freq = 1;
+			new_opp = dev_pm_opp_find_freq_ceil(info->cpu_dev,
+							    &freq);
+			if (IS_ERR(new_opp)) {
+				dev_err(info->cpu_dev,
+					"all opp items are disabled\n");
+				ret = PTR_ERR(new_opp);
+				return notifier_from_errno(ret);
+			}
+
+			dev_pm_opp_put(new_opp);
+			policy = cpufreq_cpu_get(info->opp_cpu);
+			if (policy) {
+				cpufreq_driver_target(policy, freq / 1000,
+						      CPUFREQ_RELATION_L);
+				cpufreq_cpu_put(policy);
+			}
+		}
+	}
+
+	return notifier_from_errno(ret);
+}
+
+static struct device *of_get_cci(struct device *cpu_dev)
+{
+	struct device_node *np;
+	struct platform_device *pdev;
+
+	np = of_parse_phandle(cpu_dev->of_node, "mediatek,cci", 0);
+	if (IS_ERR_OR_NULL(np))
+		return NULL;
+
+	pdev = of_find_device_by_node(np);
+	of_node_put(np);
+	if (IS_ERR_OR_NULL(pdev))
+		return NULL;
+
+	return &pdev->dev;
+}
+
 static int mtk_cpu_dvfs_info_init(struct mtk_cpu_dvfs_info *info, int cpu)
 {
 	struct device *cpu_dev;
-	struct regulator *proc_reg = ERR_PTR(-ENODEV);
-	struct regulator *sram_reg = ERR_PTR(-ENODEV);
-	struct clk *cpu_clk = ERR_PTR(-ENODEV);
-	struct clk *inter_clk = ERR_PTR(-ENODEV);
 	struct dev_pm_opp *opp;
 	unsigned long rate;
 	int ret;
 
 	cpu_dev = get_cpu_device(cpu);
 	if (!cpu_dev) {
-		pr_err("failed to get cpu%d device\n", cpu);
+		dev_err(cpu_dev, "failed to get cpu%d device\n", cpu);
 		return -ENODEV;
 	}
+	info->cpu_dev = cpu_dev;
 
-	cpu_clk = clk_get(cpu_dev, "cpu");
-	if (IS_ERR(cpu_clk)) {
-		if (PTR_ERR(cpu_clk) == -EPROBE_DEFER)
-			pr_warn("cpu clk for cpu%d not ready, retry.\n", cpu);
-		else
-			pr_err("failed to get cpu clk for cpu%d\n", cpu);
-
-		ret = PTR_ERR(cpu_clk);
-		return ret;
+	info->ccifreq_bound = false;
+	if (info->soc_data->ccifreq_supported) {
+		info->cci_dev = of_get_cci(info->cpu_dev);
+		if (IS_ERR_OR_NULL(info->cci_dev)) {
+			ret = PTR_ERR(info->cci_dev);
+			dev_err(cpu_dev, "cpu%d: failed to get cci device\n", cpu);
+			return -ENODEV;
+		}
 	}
 
-	inter_clk = clk_get(cpu_dev, "intermediate");
-	if (IS_ERR(inter_clk)) {
-		if (PTR_ERR(inter_clk) == -EPROBE_DEFER)
-			pr_warn("intermediate clk for cpu%d not ready, retry.\n",
-				cpu);
-		else
-			pr_err("failed to get intermediate clk for cpu%d\n",
-			       cpu);
+	info->cpu_clk = clk_get(cpu_dev, "cpu");
+	if (IS_ERR(info->cpu_clk)) {
+		ret = PTR_ERR(info->cpu_clk);
+		return dev_err_probe(cpu_dev, ret,
+				     "cpu%d: failed to get cpu clk\n", cpu);
+	}
 
-		ret = PTR_ERR(inter_clk);
+	info->inter_clk = clk_get(cpu_dev, "intermediate");
+	if (IS_ERR(info->inter_clk)) {
+		ret = PTR_ERR(info->inter_clk);
+		dev_err_probe(cpu_dev, ret,
+			      "cpu%d: failed to get intermediate clk\n", cpu);
 		goto out_free_resources;
 	}
 
-	proc_reg = regulator_get_optional(cpu_dev, "proc");
-	if (IS_ERR(proc_reg)) {
-		if (PTR_ERR(proc_reg) == -EPROBE_DEFER)
-			pr_warn("proc regulator for cpu%d not ready, retry.\n",
-				cpu);
-		else
-			pr_err("failed to get proc regulator for cpu%d\n",
-			       cpu);
+	info->proc_reg = regulator_get_optional(cpu_dev, "proc");
+	if (IS_ERR(info->proc_reg)) {
+		ret = PTR_ERR(info->proc_reg);
+		dev_err_probe(cpu_dev, ret,
+			      "cpu%d: failed to get proc regulator\n", cpu);
+		goto out_free_resources;
+	}
 
-		ret = PTR_ERR(proc_reg);
+	ret = regulator_enable(info->proc_reg);
+	if (ret) {
+		dev_warn(cpu_dev, "cpu%d: failed to enable vproc\n", cpu);
 		goto out_free_resources;
 	}
 
 	/* Both presence and absence of sram regulator are valid cases. */
-	sram_reg = regulator_get_exclusive(cpu_dev, "sram");
+	info->sram_reg = regulator_get_optional(cpu_dev, "sram");
+	if (IS_ERR(info->sram_reg))
+		info->sram_reg = NULL;
+	else {
+		ret = regulator_enable(info->sram_reg);
+		if (ret) {
+			dev_warn(cpu_dev, "cpu%d: failed to enable vsram\n", cpu);
+			goto out_free_resources;
+		}
+	}
 
 	/* Get OPP-sharing information from "operating-points-v2" bindings */
 	ret = dev_pm_opp_of_get_sharing_cpus(cpu_dev, &info->cpus);
 	if (ret) {
-		pr_err("failed to get OPP-sharing information for cpu%d\n",
-		       cpu);
+		dev_err(cpu_dev,
+			"cpu%d: failed to get OPP-sharing information\n", cpu);
 		goto out_free_resources;
 	}
 
 	ret = dev_pm_opp_of_cpumask_add_table(&info->cpus);
 	if (ret) {
-		pr_warn("no OPP table for cpu%d\n", cpu);
+		dev_warn(cpu_dev, "cpu%d: no OPP table\n", cpu);
 		goto out_free_resources;
 	}
 
+	ret = clk_prepare_enable(info->cpu_clk);
+	if (ret)
+		goto out_free_opp_table;
+
+	ret = clk_prepare_enable(info->inter_clk);
+	if (ret)
+		goto out_disable_mux_clock;
+
+	if (info->soc_data->ccifreq_supported) {
+		info->vproc_on_boot = regulator_get_voltage(info->proc_reg);
+		if (info->vproc_on_boot < 0) {
+			dev_err(info->cpu_dev,
+				"invalid Vproc value: %d\n", info->vproc_on_boot);
+			goto out_disable_inter_clock;
+		}
+	}
+
 	/* Search a safe voltage for intermediate frequency. */
-	rate = clk_get_rate(inter_clk);
+	rate = clk_get_rate(info->inter_clk);
 	opp = dev_pm_opp_find_freq_ceil(cpu_dev, &rate);
 	if (IS_ERR(opp)) {
-		pr_err("failed to get intermediate opp for cpu%d\n", cpu);
+		dev_err(cpu_dev, "cpu%d: failed to get intermediate opp\n", cpu);
 		ret = PTR_ERR(opp);
-		goto out_free_opp_table;
+		goto out_disable_inter_clock;
 	}
 	info->intermediate_voltage = dev_pm_opp_get_voltage(opp);
 	dev_pm_opp_put(opp);
 
-	info->cpu_dev = cpu_dev;
-	info->proc_reg = proc_reg;
-	info->sram_reg = IS_ERR(sram_reg) ? NULL : sram_reg;
-	info->cpu_clk = cpu_clk;
-	info->inter_clk = inter_clk;
+	mutex_init(&info->reg_lock);
+	info->current_freq = clk_get_rate(info->cpu_clk);
+
+	info->opp_cpu = cpu;
+	info->opp_nb.notifier_call = mtk_cpufreq_opp_notifier;
+	ret = dev_pm_opp_register_notifier(cpu_dev, &info->opp_nb);
+	if (ret) {
+		dev_err(cpu_dev, "cpu%d: failed to register opp notifier\n", cpu);
+		goto out_disable_inter_clock;
+	}
 
 	/*
 	 * If SRAM regulator is present, software "voltage tracking" is needed
 	 * for this CPU power domain.
 	 */
-	info->need_voltage_tracking = !IS_ERR(sram_reg);
+	info->need_voltage_tracking = (info->sram_reg != NULL);
+
+	/*
+	 * We assume min voltage is 0 and tracking target voltage using
+	 * min_volt_shift for each iteration.
+	 * The vtrack_max is 3 times of expeted iteration count.
+	 */
+	info->vtrack_max = 3 * DIV_ROUND_UP(max(info->soc_data->sram_max_volt,
+						info->soc_data->proc_max_volt),
+					    info->soc_data->min_volt_shift);
 
 	return 0;
 
+out_disable_inter_clock:
+	clk_disable_unprepare(info->inter_clk);
+
+out_disable_mux_clock:
+	clk_disable_unprepare(info->cpu_clk);
+
 out_free_opp_table:
 	dev_pm_opp_of_cpumask_remove_table(&info->cpus);
 
 out_free_resources:
-	if (!IS_ERR(proc_reg))
-		regulator_put(proc_reg);
-	if (!IS_ERR(sram_reg))
-		regulator_put(sram_reg);
-	if (!IS_ERR(cpu_clk))
-		clk_put(cpu_clk);
-	if (!IS_ERR(inter_clk))
-		clk_put(inter_clk);
+	if (regulator_is_enabled(info->proc_reg))
+		regulator_disable(info->proc_reg);
+	if (info->sram_reg && regulator_is_enabled(info->sram_reg))
+		regulator_disable(info->sram_reg);
+
+	if (!IS_ERR(info->proc_reg))
+		regulator_put(info->proc_reg);
+	if (!IS_ERR(info->sram_reg))
+		regulator_put(info->sram_reg);
+	if (!IS_ERR(info->cpu_clk))
+		clk_put(info->cpu_clk);
+	if (!IS_ERR(info->inter_clk))
+		clk_put(info->inter_clk);
 
 	return ret;
 }
 
 static void mtk_cpu_dvfs_info_release(struct mtk_cpu_dvfs_info *info)
 {
-	if (!IS_ERR(info->proc_reg))
+	if (!IS_ERR(info->proc_reg)) {
+		regulator_disable(info->proc_reg);
 		regulator_put(info->proc_reg);
-	if (!IS_ERR(info->sram_reg))
+	}
+	if (!IS_ERR(info->sram_reg)) {
+		regulator_disable(info->sram_reg);
 		regulator_put(info->sram_reg);
-	if (!IS_ERR(info->cpu_clk))
+	}
+	if (!IS_ERR(info->cpu_clk)) {
+		clk_disable_unprepare(info->cpu_clk);
 		clk_put(info->cpu_clk);
-	if (!IS_ERR(info->inter_clk))
+	}
+	if (!IS_ERR(info->inter_clk)) {
+		clk_disable_unprepare(info->inter_clk);
 		clk_put(info->inter_clk);
+	}
 
 	dev_pm_opp_of_cpumask_remove_table(&info->cpus);
+	dev_pm_opp_unregister_notifier(info->cpu_dev, &info->opp_nb);
 }
 
 static int mtk_cpufreq_init(struct cpufreq_policy *policy)
@@ -432,14 +578,15 @@ static int mtk_cpufreq_init(struct cpufreq_policy *policy)
 	info = mtk_cpu_dvfs_info_lookup(policy->cpu);
 	if (!info) {
 		pr_err("dvfs info for cpu%d is not initialized.\n",
-		       policy->cpu);
+			policy->cpu);
 		return -EINVAL;
 	}
 
 	ret = dev_pm_opp_init_cpufreq_table(info->cpu_dev, &freq_table);
 	if (ret) {
-		pr_err("failed to init cpufreq table for cpu%d: %d\n",
-		       policy->cpu, ret);
+		dev_err(info->cpu_dev,
+			"failed to init cpufreq table for cpu%d: %d\n",
+			policy->cpu, ret);
 		return ret;
 	}
 
@@ -476,9 +623,17 @@ static struct cpufreq_driver mtk_cpufreq_driver = {
 
 static int mtk_cpufreq_probe(struct platform_device *pdev)
 {
+	const struct mtk_cpufreq_platform_data *data;
 	struct mtk_cpu_dvfs_info *info, *tmp;
 	int cpu, ret;
 
+	data = dev_get_platdata(&pdev->dev);
+	if (!data) {
+		dev_err(&pdev->dev,
+			"failed to get mtk cpufreq platform data\n");
+		return -ENODEV;
+	}
+
 	for_each_possible_cpu(cpu) {
 		info = mtk_cpu_dvfs_info_lookup(cpu);
 		if (info)
@@ -490,6 +645,7 @@ static int mtk_cpufreq_probe(struct platform_device *pdev)
 			goto release_dvfs_info_list;
 		}
 
+		info->soc_data = data;
 		ret = mtk_cpu_dvfs_info_init(info, cpu);
 		if (ret) {
 			dev_err(&pdev->dev,
@@ -525,20 +681,47 @@ static struct platform_driver mtk_cpufreq_platdrv = {
 	.probe		= mtk_cpufreq_probe,
 };
 
+static const struct mtk_cpufreq_platform_data mt2701_platform_data = {
+	.min_volt_shift = 100000,
+	.max_volt_shift = 200000,
+	.proc_max_volt = 1150000,
+	.sram_min_volt = 0,
+	.sram_max_volt = 1150000,
+	.ccifreq_supported = false,
+};
+
+static const struct mtk_cpufreq_platform_data mt8183_platform_data = {
+	.min_volt_shift = 100000,
+	.max_volt_shift = 200000,
+	.proc_max_volt = 1150000,
+	.sram_min_volt = 0,
+	.sram_max_volt = 1150000,
+	.ccifreq_supported = true,
+};
+
+static const struct mtk_cpufreq_platform_data mt8186_platform_data = {
+	.min_volt_shift = 100000,
+	.max_volt_shift = 250000,
+	.proc_max_volt = 1118750,
+	.sram_min_volt = 850000,
+	.sram_max_volt = 1118750,
+	.ccifreq_supported = true,
+};
+
 /* List of machines supported by this driver */
 static const struct of_device_id mtk_cpufreq_machines[] __initconst = {
-	{ .compatible = "mediatek,mt2701", },
-	{ .compatible = "mediatek,mt2712", },
-	{ .compatible = "mediatek,mt7622", },
-	{ .compatible = "mediatek,mt7623", },
-	{ .compatible = "mediatek,mt8167", },
-	{ .compatible = "mediatek,mt817x", },
-	{ .compatible = "mediatek,mt8173", },
-	{ .compatible = "mediatek,mt8176", },
-	{ .compatible = "mediatek,mt8183", },
-	{ .compatible = "mediatek,mt8365", },
-	{ .compatible = "mediatek,mt8516", },
-
+	{ .compatible = "mediatek,mt2701", .data = &mt2701_platform_data },
+	{ .compatible = "mediatek,mt2712", .data = &mt2701_platform_data },
+	{ .compatible = "mediatek,mt7622", .data = &mt2701_platform_data },
+	{ .compatible = "mediatek,mt7623", .data = &mt2701_platform_data },
+	{ .compatible = "mediatek,mt8167", .data = &mt2701_platform_data },
+	{ .compatible = "mediatek,mt817x", .data = &mt2701_platform_data },
+	{ .compatible = "mediatek,mt8173", .data = &mt2701_platform_data },
+	{ .compatible = "mediatek,mt8176", .data = &mt2701_platform_data },
+	{ .compatible = "mediatek,mt8183", .data = &mt8183_platform_data },
+	{ .compatible = "mediatek,mt8186", .data = &mt8186_platform_data },
+	{ .compatible = "mediatek,mt8365", .data = &mt2701_platform_data },
+	{ .compatible = "mediatek,mt8516", .data = &mt2701_platform_data },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, mtk_cpufreq_machines);
@@ -547,7 +730,7 @@ static int __init mtk_cpufreq_driver_init(void)
 {
 	struct device_node *np;
 	const struct of_device_id *match;
-	struct platform_device *pdev;
+	const struct mtk_cpufreq_platform_data *data;
 	int err;
 
 	np = of_find_node_by_path("/");
@@ -560,6 +743,7 @@ static int __init mtk_cpufreq_driver_init(void)
 		pr_debug("Machine is not compatible with mtk-cpufreq\n");
 		return -ENODEV;
 	}
+	data = match->data;
 
 	err = platform_driver_register(&mtk_cpufreq_platdrv);
 	if (err)
@@ -571,16 +755,24 @@ static int __init mtk_cpufreq_driver_init(void)
 	 * and the device registration codes are put here to handle defer
 	 * probing.
 	 */
-	pdev = platform_device_register_simple("mtk-cpufreq", -1, NULL, 0);
-	if (IS_ERR(pdev)) {
+	cpufreq_pdev = platform_device_register_data(NULL, "mtk-cpufreq", -1,
+						     data, sizeof(*data));
+	if (IS_ERR(cpufreq_pdev)) {
 		pr_err("failed to register mtk-cpufreq platform device\n");
 		platform_driver_unregister(&mtk_cpufreq_platdrv);
-		return PTR_ERR(pdev);
+		return PTR_ERR(cpufreq_pdev);
 	}
 
 	return 0;
 }
-device_initcall(mtk_cpufreq_driver_init);
+module_init(mtk_cpufreq_driver_init)
+
+static void __exit mtk_cpufreq_driver_exit(void)
+{
+	platform_device_unregister(cpufreq_pdev);
+	platform_driver_unregister(&mtk_cpufreq_platdrv);
+}
+module_exit(mtk_cpufreq_driver_exit)
 
 MODULE_DESCRIPTION("MediaTek CPUFreq driver");
 MODULE_AUTHOR("Pi-Cheng Chen <pi-cheng.chen@linaro.org>");
diff --git a/drivers/cpufreq/tegra194-cpufreq.c b/drivers/cpufreq/tegra194-cpufreq.c
index ac381db25dbe..2a6a98764a8c 100644
--- a/drivers/cpufreq/tegra194-cpufreq.c
+++ b/drivers/cpufreq/tegra194-cpufreq.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (c) 2020, NVIDIA CORPORATION. All rights reserved
+ * Copyright (c) 2020 - 2022, NVIDIA CORPORATION. All rights reserved
  */
 
 #include <linux/cpu.h>
@@ -24,6 +24,17 @@
 #define CPUFREQ_TBL_STEP_HZ     (50 * KHZ * KHZ)
 #define MAX_CNT                 ~0U
 
+#define NDIV_MASK              0x1FF
+
+#define CORE_OFFSET(cpu)			(cpu * 8)
+#define CMU_CLKS_BASE				0x2000
+#define SCRATCH_FREQ_CORE_REG(data, cpu)	(data->regs + CMU_CLKS_BASE + CORE_OFFSET(cpu))
+
+#define MMCRAB_CLUSTER_BASE(cl)			(0x30000 + (cl * 0x10000))
+#define CLUSTER_ACTMON_BASE(data, cl) \
+			(data->regs + (MMCRAB_CLUSTER_BASE(cl) + data->soc->actmon_cntr_base))
+#define CORE_ACTMON_CNTR_REG(data, cl, cpu)	(CLUSTER_ACTMON_BASE(data, cl) + CORE_OFFSET(cpu))
+
 /* cpufreq transisition latency */
 #define TEGRA_CPUFREQ_TRANSITION_LATENCY (300 * 1000) /* unit in nanoseconds */
 
@@ -35,12 +46,6 @@ enum cluster {
 	MAX_CLUSTERS,
 };
 
-struct tegra194_cpufreq_data {
-	void __iomem *regs;
-	size_t num_clusters;
-	struct cpufreq_frequency_table **tables;
-};
-
 struct tegra_cpu_ctr {
 	u32 cpu;
 	u32 coreclk_cnt, last_coreclk_cnt;
@@ -52,13 +57,127 @@ struct read_counters_work {
 	struct tegra_cpu_ctr c;
 };
 
+struct tegra_cpufreq_ops {
+	void (*read_counters)(struct tegra_cpu_ctr *c);
+	void (*set_cpu_ndiv)(struct cpufreq_policy *policy, u64 ndiv);
+	void (*get_cpu_cluster_id)(u32 cpu, u32 *cpuid, u32 *clusterid);
+	int (*get_cpu_ndiv)(u32 cpu, u32 cpuid, u32 clusterid, u64 *ndiv);
+};
+
+struct tegra_cpufreq_soc {
+	struct tegra_cpufreq_ops *ops;
+	int maxcpus_per_cluster;
+	phys_addr_t actmon_cntr_base;
+};
+
+struct tegra194_cpufreq_data {
+	void __iomem *regs;
+	size_t num_clusters;
+	struct cpufreq_frequency_table **tables;
+	const struct tegra_cpufreq_soc *soc;
+};
+
 static struct workqueue_struct *read_counters_wq;
 
-static void get_cpu_cluster(void *cluster)
+static void tegra_get_cpu_mpidr(void *mpidr)
+{
+	*((u64 *)mpidr) = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
+}
+
+static void tegra234_get_cpu_cluster_id(u32 cpu, u32 *cpuid, u32 *clusterid)
+{
+	u64 mpidr;
+
+	smp_call_function_single(cpu, tegra_get_cpu_mpidr, &mpidr, true);
+
+	if (cpuid)
+		*cpuid = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+	if (clusterid)
+		*clusterid = MPIDR_AFFINITY_LEVEL(mpidr, 2);
+}
+
+static int tegra234_get_cpu_ndiv(u32 cpu, u32 cpuid, u32 clusterid, u64 *ndiv)
 {
-	u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
+	struct tegra194_cpufreq_data *data = cpufreq_get_driver_data();
+	void __iomem *freq_core_reg;
+	u64 mpidr_id;
+
+	/* use physical id to get address of per core frequency register */
+	mpidr_id = (clusterid * data->soc->maxcpus_per_cluster) + cpuid;
+	freq_core_reg = SCRATCH_FREQ_CORE_REG(data, mpidr_id);
+
+	*ndiv = readl(freq_core_reg) & NDIV_MASK;
+
+	return 0;
+}
 
-	*((uint32_t *)cluster) = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+static void tegra234_set_cpu_ndiv(struct cpufreq_policy *policy, u64 ndiv)
+{
+	struct tegra194_cpufreq_data *data = cpufreq_get_driver_data();
+	void __iomem *freq_core_reg;
+	u32 cpu, cpuid, clusterid;
+	u64 mpidr_id;
+
+	for_each_cpu_and(cpu, policy->cpus, cpu_online_mask) {
+		data->soc->ops->get_cpu_cluster_id(cpu, &cpuid, &clusterid);
+
+		/* use physical id to get address of per core frequency register */
+		mpidr_id = (clusterid * data->soc->maxcpus_per_cluster) + cpuid;
+		freq_core_reg = SCRATCH_FREQ_CORE_REG(data, mpidr_id);
+
+		writel(ndiv, freq_core_reg);
+	}
+}
+
+/*
+ * This register provides access to two counter values with a single
+ * 64-bit read. The counter values are used to determine the average
+ * actual frequency a core has run at over a period of time.
+ *     [63:32] PLLP counter: Counts at fixed frequency (408 MHz)
+ *     [31:0] Core clock counter: Counts on every core clock cycle
+ */
+static void tegra234_read_counters(struct tegra_cpu_ctr *c)
+{
+	struct tegra194_cpufreq_data *data = cpufreq_get_driver_data();
+	void __iomem *actmon_reg;
+	u32 cpuid, clusterid;
+	u64 val;
+
+	data->soc->ops->get_cpu_cluster_id(c->cpu, &cpuid, &clusterid);
+	actmon_reg = CORE_ACTMON_CNTR_REG(data, clusterid, cpuid);
+
+	val = readq(actmon_reg);
+	c->last_refclk_cnt = upper_32_bits(val);
+	c->last_coreclk_cnt = lower_32_bits(val);
+	udelay(US_DELAY);
+	val = readq(actmon_reg);
+	c->refclk_cnt = upper_32_bits(val);
+	c->coreclk_cnt = lower_32_bits(val);
+}
+
+static struct tegra_cpufreq_ops tegra234_cpufreq_ops = {
+	.read_counters = tegra234_read_counters,
+	.get_cpu_cluster_id = tegra234_get_cpu_cluster_id,
+	.get_cpu_ndiv = tegra234_get_cpu_ndiv,
+	.set_cpu_ndiv = tegra234_set_cpu_ndiv,
+};
+
+const struct tegra_cpufreq_soc tegra234_cpufreq_soc = {
+	.ops = &tegra234_cpufreq_ops,
+	.actmon_cntr_base = 0x9000,
+	.maxcpus_per_cluster = 4,
+};
+
+static void tegra194_get_cpu_cluster_id(u32 cpu, u32 *cpuid, u32 *clusterid)
+{
+	u64 mpidr;
+
+	smp_call_function_single(cpu, tegra_get_cpu_mpidr, &mpidr, true);
+
+	if (cpuid)
+		*cpuid = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	if (clusterid)
+		*clusterid = MPIDR_AFFINITY_LEVEL(mpidr, 1);
 }
 
 /*
@@ -85,11 +204,24 @@ static inline u32 map_ndiv_to_freq(struct mrq_cpu_ndiv_limits_response
 	return nltbl->ref_clk_hz / KHZ * ndiv / (nltbl->pdiv * nltbl->mdiv);
 }
 
+static void tegra194_read_counters(struct tegra_cpu_ctr *c)
+{
+	u64 val;
+
+	val = read_freq_feedback();
+	c->last_refclk_cnt = lower_32_bits(val);
+	c->last_coreclk_cnt = upper_32_bits(val);
+	udelay(US_DELAY);
+	val = read_freq_feedback();
+	c->refclk_cnt = lower_32_bits(val);
+	c->coreclk_cnt = upper_32_bits(val);
+}
+
 static void tegra_read_counters(struct work_struct *work)
 {
+	struct tegra194_cpufreq_data *data = cpufreq_get_driver_data();
 	struct read_counters_work *read_counters_work;
 	struct tegra_cpu_ctr *c;
-	u64 val;
 
 	/*
 	 * ref_clk_counter(32 bit counter) runs on constant clk,
@@ -107,13 +239,7 @@ static void tegra_read_counters(struct work_struct *work)
 					  work);
 	c = &read_counters_work->c;
 
-	val = read_freq_feedback();
-	c->last_refclk_cnt = lower_32_bits(val);
-	c->last_coreclk_cnt = upper_32_bits(val);
-	udelay(US_DELAY);
-	val = read_freq_feedback();
-	c->refclk_cnt = lower_32_bits(val);
-	c->coreclk_cnt = upper_32_bits(val);
+	data->soc->ops->read_counters(c);
 }
 
 /*
@@ -177,7 +303,7 @@ static unsigned int tegra194_calculate_speed(u32 cpu)
 	return (rate_mhz * KHZ); /* in KHz */
 }
 
-static void get_cpu_ndiv(void *ndiv)
+static void tegra194_get_cpu_ndiv_sysreg(void *ndiv)
 {
 	u64 ndiv_val;
 
@@ -186,30 +312,43 @@ static void get_cpu_ndiv(void *ndiv)
 	*(u64 *)ndiv = ndiv_val;
 }
 
-static void set_cpu_ndiv(void *data)
+static int tegra194_get_cpu_ndiv(u32 cpu, u32 cpuid, u32 clusterid, u64 *ndiv)
+{
+	int ret;
+
+	ret = smp_call_function_single(cpu, tegra194_get_cpu_ndiv_sysreg, &ndiv, true);
+
+	return ret;
+}
+
+static void tegra194_set_cpu_ndiv_sysreg(void *data)
 {
-	struct cpufreq_frequency_table *tbl = data;
-	u64 ndiv_val = (u64)tbl->driver_data;
+	u64 ndiv_val = *(u64 *)data;
 
 	asm volatile("msr s3_0_c15_c0_4, %0" : : "r" (ndiv_val));
 }
 
+static void tegra194_set_cpu_ndiv(struct cpufreq_policy *policy, u64 ndiv)
+{
+	on_each_cpu_mask(policy->cpus, tegra194_set_cpu_ndiv_sysreg, &ndiv, true);
+}
+
 static unsigned int tegra194_get_speed(u32 cpu)
 {
 	struct tegra194_cpufreq_data *data = cpufreq_get_driver_data();
 	struct cpufreq_frequency_table *pos;
+	u32 cpuid, clusterid;
 	unsigned int rate;
 	u64 ndiv;
 	int ret;
-	u32 cl;
 
-	smp_call_function_single(cpu, get_cpu_cluster, &cl, true);
+	data->soc->ops->get_cpu_cluster_id(cpu, &cpuid, &clusterid);
 
 	/* reconstruct actual cpu freq using counters */
 	rate = tegra194_calculate_speed(cpu);
 
 	/* get last written ndiv value */
-	ret = smp_call_function_single(cpu, get_cpu_ndiv, &ndiv, true);
+	ret = data->soc->ops->get_cpu_ndiv(cpu, cpuid, clusterid, &ndiv);
 	if (WARN_ON_ONCE(ret))
 		return rate;
 
@@ -219,7 +358,7 @@ static unsigned int tegra194_get_speed(u32 cpu)
 	 * to the last written ndiv value from freq_table. This is
 	 * done to return consistent value.
 	 */
-	cpufreq_for_each_valid_entry(pos, data->tables[cl]) {
+	cpufreq_for_each_valid_entry(pos, data->tables[clusterid]) {
 		if (pos->driver_data != ndiv)
 			continue;
 
@@ -237,19 +376,22 @@ static unsigned int tegra194_get_speed(u32 cpu)
 static int tegra194_cpufreq_init(struct cpufreq_policy *policy)
 {
 	struct tegra194_cpufreq_data *data = cpufreq_get_driver_data();
-	u32 cpu;
-	u32 cl;
+	int maxcpus_per_cluster = data->soc->maxcpus_per_cluster;
+	u32 start_cpu, cpu;
+	u32 clusterid;
 
-	smp_call_function_single(policy->cpu, get_cpu_cluster, &cl, true);
+	data->soc->ops->get_cpu_cluster_id(policy->cpu, NULL, &clusterid);
 
-	if (cl >= data->num_clusters || !data->tables[cl])
+	if (clusterid >= data->num_clusters || !data->tables[clusterid])
 		return -EINVAL;
 
+	start_cpu = rounddown(policy->cpu, maxcpus_per_cluster);
 	/* set same policy for all cpus in a cluster */
-	for (cpu = (cl * 2); cpu < ((cl + 1) * 2); cpu++)
-		cpumask_set_cpu(cpu, policy->cpus);
-
-	policy->freq_table = data->tables[cl];
+	for (cpu = start_cpu; cpu < (start_cpu + maxcpus_per_cluster); cpu++) {
+		if (cpu_possible(cpu))
+			cpumask_set_cpu(cpu, policy->cpus);
+	}
+	policy->freq_table = data->tables[clusterid];
 	policy->cpuinfo.transition_latency = TEGRA_CPUFREQ_TRANSITION_LATENCY;
 
 	return 0;
@@ -259,13 +401,14 @@ static int tegra194_cpufreq_set_target(struct cpufreq_policy *policy,
 				       unsigned int index)
 {
 	struct cpufreq_frequency_table *tbl = policy->freq_table + index;
+	struct tegra194_cpufreq_data *data = cpufreq_get_driver_data();
 
 	/*
 	 * Each core writes frequency in per core register. Then both cores
 	 * in a cluster run at same frequency which is the maximum frequency
 	 * request out of the values requested by both cores in that cluster.
 	 */
-	on_each_cpu_mask(policy->cpus, set_cpu_ndiv, tbl, true);
+	data->soc->ops->set_cpu_ndiv(policy, (u64)tbl->driver_data);
 
 	return 0;
 }
@@ -280,6 +423,18 @@ static struct cpufreq_driver tegra194_cpufreq_driver = {
 	.attr = cpufreq_generic_attr,
 };
 
+static struct tegra_cpufreq_ops tegra194_cpufreq_ops = {
+	.read_counters = tegra194_read_counters,
+	.get_cpu_cluster_id = tegra194_get_cpu_cluster_id,
+	.get_cpu_ndiv = tegra194_get_cpu_ndiv,
+	.set_cpu_ndiv = tegra194_set_cpu_ndiv,
+};
+
+const struct tegra_cpufreq_soc tegra194_cpufreq_soc = {
+	.ops = &tegra194_cpufreq_ops,
+	.maxcpus_per_cluster = 2,
+};
+
 static void tegra194_cpufreq_free_resources(void)
 {
 	destroy_workqueue(read_counters_wq);
@@ -359,6 +514,7 @@ init_freq_table(struct platform_device *pdev, struct tegra_bpmp *bpmp,
 
 static int tegra194_cpufreq_probe(struct platform_device *pdev)
 {
+	const struct tegra_cpufreq_soc *soc;
 	struct tegra194_cpufreq_data *data;
 	struct tegra_bpmp *bpmp;
 	int err, i;
@@ -367,12 +523,28 @@ static int tegra194_cpufreq_probe(struct platform_device *pdev)
 	if (!data)
 		return -ENOMEM;
 
+	soc = of_device_get_match_data(&pdev->dev);
+
+	if (soc->ops && soc->maxcpus_per_cluster) {
+		data->soc = soc;
+	} else {
+		dev_err(&pdev->dev, "soc data missing\n");
+		return -EINVAL;
+	}
+
 	data->num_clusters = MAX_CLUSTERS;
 	data->tables = devm_kcalloc(&pdev->dev, data->num_clusters,
 				    sizeof(*data->tables), GFP_KERNEL);
 	if (!data->tables)
 		return -ENOMEM;
 
+	if (soc->actmon_cntr_base) {
+		/* mmio registers are used for frequency request and re-construction */
+		data->regs = devm_platform_ioremap_resource(pdev, 0);
+		if (IS_ERR(data->regs))
+			return PTR_ERR(data->regs);
+	}
+
 	platform_set_drvdata(pdev, data);
 
 	bpmp = tegra_bpmp_get(&pdev->dev);
@@ -416,10 +588,10 @@ static int tegra194_cpufreq_remove(struct platform_device *pdev)
 }
 
 static const struct of_device_id tegra194_cpufreq_of_match[] = {
-	{ .compatible = "nvidia,tegra194-ccplex", },
+	{ .compatible = "nvidia,tegra194-ccplex", .data = &tegra194_cpufreq_soc },
+	{ .compatible = "nvidia,tegra234-ccplex-cluster", .data = &tegra234_cpufreq_soc },
 	{ /* sentinel */ }
 };
-MODULE_DEVICE_TABLE(of, tegra194_cpufreq_of_match);
 
 static struct platform_driver tegra194_ccplex_driver = {
 	.driver = {
diff --git a/drivers/memory/emif.c b/drivers/memory/emif.c
index 6c2a421b86e3..f305643209f0 100644
--- a/drivers/memory/emif.c
+++ b/drivers/memory/emif.c
@@ -630,7 +630,7 @@ static irqreturn_t emif_threaded_isr(int irq, void *dev_id)
 		dev_emerg(emif->dev, "SDRAM temperature exceeds operating limit.. Needs shut down!!!\n");
 
 		/* If we have Power OFF ability, use it, else try restarting */
-		if (pm_power_off) {
+		if (kernel_can_power_off()) {
 			kernel_power_off();
 		} else {
 			WARN(1, "FIXME: NO pm_power_off!!! trying restart\n");
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 740407252298..84063eaebb91 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -456,103 +456,6 @@ 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_level_exact() - search for an exact level
- * @dev:		device for which we do this operation
- * @level:		level to search for
- *
- * Return: Searches for exact match in the opp table and returns pointer to the
- * matching opp if found, 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_level_exact(struct device *dev,
-					       unsigned int level)
-{
-	struct opp_table *opp_table;
-	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
-
-	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		int r = PTR_ERR(opp_table);
-
-		dev_err(dev, "%s: OPP table not found (%d)\n", __func__, r);
-		return ERR_PTR(r);
-	}
-
-	mutex_lock(&opp_table->lock);
-
-	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
-		if (temp_opp->level == level) {
-			opp = temp_opp;
-
-			/* Increment the reference count of OPP */
-			dev_pm_opp_get(opp);
-			break;
-		}
-	}
-
-	mutex_unlock(&opp_table->lock);
-	dev_pm_opp_put_opp_table(opp_table);
-
-	return opp;
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_find_level_exact);
-
-/**
- * dev_pm_opp_find_level_ceil() - search for an rounded up level
- * @dev:		device for which we do this operation
- * @level:		level to search for
- *
- * Return: Searches for rounded up match in the opp table and returns pointer
- * to the  matching opp if found, 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_level_ceil(struct device *dev,
-					      unsigned int *level)
-{
-	struct opp_table *opp_table;
-	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
-
-	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		int r = PTR_ERR(opp_table);
-
-		dev_err(dev, "%s: OPP table not found (%d)\n", __func__, r);
-		return ERR_PTR(r);
-	}
-
-	mutex_lock(&opp_table->lock);
-
-	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
-		if (temp_opp->available && temp_opp->level >= *level) {
-			opp = temp_opp;
-			*level = opp->level;
-
-			/* Increment the reference count of OPP */
-			dev_pm_opp_get(opp);
-			break;
-		}
-	}
-
-	mutex_unlock(&opp_table->lock);
-	dev_pm_opp_put_opp_table(opp_table);
-
-	return opp;
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_find_level_ceil);
-
 static noinline struct dev_pm_opp *_find_freq_ceil(struct opp_table *opp_table,
 						   unsigned long *freq)
 {
@@ -729,6 +632,223 @@ struct dev_pm_opp *dev_pm_opp_find_freq_ceil_by_volt(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_ceil_by_volt);
 
+/**
+ * dev_pm_opp_find_level_exact() - search for an exact level
+ * @dev:		device for which we do this operation
+ * @level:		level to search for
+ *
+ * Return: Searches for exact match in the opp table and returns pointer to the
+ * matching opp if found, 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_level_exact(struct device *dev,
+					       unsigned int level)
+{
+	struct opp_table *opp_table;
+	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
+
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table)) {
+		int r = PTR_ERR(opp_table);
+
+		dev_err(dev, "%s: OPP table not found (%d)\n", __func__, r);
+		return ERR_PTR(r);
+	}
+
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
+		if (temp_opp->level == level) {
+			opp = temp_opp;
+
+			/* Increment the reference count of OPP */
+			dev_pm_opp_get(opp);
+			break;
+		}
+	}
+
+	mutex_unlock(&opp_table->lock);
+	dev_pm_opp_put_opp_table(opp_table);
+
+	return opp;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_find_level_exact);
+
+/**
+ * dev_pm_opp_find_level_ceil() - search for an rounded up level
+ * @dev:		device for which we do this operation
+ * @level:		level to search for
+ *
+ * Return: Searches for rounded up match in the opp table and returns pointer
+ * to the  matching opp if found, 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_level_ceil(struct device *dev,
+					      unsigned int *level)
+{
+	struct opp_table *opp_table;
+	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
+
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table)) {
+		int r = PTR_ERR(opp_table);
+
+		dev_err(dev, "%s: OPP table not found (%d)\n", __func__, r);
+		return ERR_PTR(r);
+	}
+
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
+		if (temp_opp->available && temp_opp->level >= *level) {
+			opp = temp_opp;
+			*level = opp->level;
+
+			/* Increment the reference count of OPP */
+			dev_pm_opp_get(opp);
+			break;
+		}
+	}
+
+	mutex_unlock(&opp_table->lock);
+	dev_pm_opp_put_opp_table(opp_table);
+
+	return opp;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_find_level_ceil);
+
+/**
+ * dev_pm_opp_find_bw_ceil() - Search for a rounded ceil bandwidth
+ * @dev:	device for which we do this operation
+ * @freq:	start bandwidth
+ * @index:	which bandwidth to compare, in case of OPPs with several values
+ *
+ * Search for the matching floor *available* OPP from a starting bandwidth
+ * for a device.
+ *
+ * Return: matching *opp and refreshes *bw 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_bw_ceil(struct device *dev,
+					   unsigned int *bw, int index)
+{
+	struct opp_table *opp_table;
+	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
+
+	if (!dev || !bw) {
+		dev_err(dev, "%s: Invalid argument bw=%p\n", __func__, bw);
+		return ERR_PTR(-EINVAL);
+	}
+
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table))
+		return ERR_CAST(opp_table);
+
+	if (index >= opp_table->path_count)
+		return ERR_PTR(-EINVAL);
+
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
+		if (temp_opp->available && temp_opp->bandwidth) {
+			if (temp_opp->bandwidth[index].peak >= *bw) {
+				opp = temp_opp;
+				*bw = opp->bandwidth[index].peak;
+
+				/* Increment the reference count of OPP */
+				dev_pm_opp_get(opp);
+				break;
+			}
+		}
+	}
+
+	mutex_unlock(&opp_table->lock);
+	dev_pm_opp_put_opp_table(opp_table);
+
+	return opp;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_find_bw_ceil);
+
+/**
+ * dev_pm_opp_find_bw_floor() - Search for a rounded floor bandwidth
+ * @dev:	device for which we do this operation
+ * @freq:	start bandwidth
+ * @index:	which bandwidth to compare, in case of OPPs with several values
+ *
+ * Search for the matching floor *available* OPP from a starting bandwidth
+ * for a device.
+ *
+ * Return: matching *opp and refreshes *bw 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_bw_floor(struct device *dev,
+					    unsigned int *bw, int index)
+{
+	struct opp_table *opp_table;
+	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
+
+	if (!dev || !bw) {
+		dev_err(dev, "%s: Invalid argument bw=%p\n", __func__, bw);
+		return ERR_PTR(-EINVAL);
+	}
+
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table))
+		return ERR_CAST(opp_table);
+
+	if (index >= opp_table->path_count)
+		return ERR_PTR(-EINVAL);
+
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
+		if (temp_opp->available && temp_opp->bandwidth) {
+			/* go to the next node, before choosing prev */
+			if (temp_opp->bandwidth[index].peak > *bw)
+				break;
+			opp = temp_opp;
+		}
+	}
+
+	/* Increment the reference count of OPP */
+	if (!IS_ERR(opp))
+		dev_pm_opp_get(opp);
+	mutex_unlock(&opp_table->lock);
+	dev_pm_opp_put_opp_table(opp_table);
+
+	if (!IS_ERR(opp))
+		*bw = opp->bandwidth[index].peak;
+
+	return opp;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_find_bw_floor);
+
 static int _set_opp_voltage(struct device *dev, struct regulator *reg,
 			    struct dev_pm_opp_supply *supply)
 {
@@ -1486,9 +1606,8 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put);
  */
 void dev_pm_opp_remove(struct device *dev, unsigned long freq)
 {
-	struct dev_pm_opp *opp;
+	struct dev_pm_opp *opp = NULL, *iter;
 	struct opp_table *opp_table;
-	bool found = false;
 
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table))
@@ -1496,16 +1615,16 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq)
 
 	mutex_lock(&opp_table->lock);
 
-	list_for_each_entry(opp, &opp_table->opp_list, node) {
-		if (opp->rate == freq) {
-			found = true;
+	list_for_each_entry(iter, &opp_table->opp_list, node) {
+		if (iter->rate == freq) {
+			opp = iter;
 			break;
 		}
 	}
 
 	mutex_unlock(&opp_table->lock);
 
-	if (found) {
+	if (opp) {
 		dev_pm_opp_put(opp);
 
 		/* Drop the reference taken by dev_pm_opp_add() */
@@ -2019,10 +2138,9 @@ struct opp_table *dev_pm_opp_set_regulators(struct device *dev,
 	for (i = 0; i < count; i++) {
 		reg = regulator_get_optional(dev, names[i]);
 		if (IS_ERR(reg)) {
-			ret = PTR_ERR(reg);
-			if (ret != -EPROBE_DEFER)
-				dev_err(dev, "%s: no regulator (%s) found: %d\n",
-					__func__, names[i], ret);
+			ret = dev_err_probe(dev, PTR_ERR(reg),
+					    "%s: no regulator (%s) found\n",
+					    __func__, names[i]);
 			goto free_regulators;
 		}
 
@@ -2168,11 +2286,8 @@ struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char *name)
 	/* Find clk for the device */
 	opp_table->clk = clk_get(dev, name);
 	if (IS_ERR(opp_table->clk)) {
-		ret = PTR_ERR(opp_table->clk);
-		if (ret != -EPROBE_DEFER) {
-			dev_err(dev, "%s: Couldn't find clock: %d\n", __func__,
-				ret);
-		}
+		ret = dev_err_probe(dev, PTR_ERR(opp_table->clk),
+				    "%s: Couldn't find clock\n", __func__);
 		goto err;
 	}
 
diff --git a/drivers/opp/debugfs.c b/drivers/opp/debugfs.c
index 3fcc1f97f2d1..1b6e5c55c3ed 100644
--- a/drivers/opp/debugfs.c
+++ b/drivers/opp/debugfs.c
@@ -195,14 +195,18 @@ void opp_debug_register(struct opp_device *opp_dev, struct opp_table *opp_table)
 static void opp_migrate_dentry(struct opp_device *opp_dev,
 			       struct opp_table *opp_table)
 {
-	struct opp_device *new_dev;
+	struct opp_device *new_dev = NULL, *iter;
 	const struct device *dev;
 	struct dentry *dentry;
 
 	/* Look for next opp-dev */
-	list_for_each_entry(new_dev, &opp_table->dev_list, node)
-		if (new_dev != opp_dev)
+	list_for_each_entry(iter, &opp_table->dev_list, node)
+		if (iter != opp_dev) {
+			new_dev = iter;
 			break;
+		}
+
+	BUG_ON(!new_dev);
 
 	/* new_dev is guaranteed to be valid here */
 	dev = new_dev->dev;
diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index 485ea980bde7..30394929d700 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -437,11 +437,11 @@ static int _bandwidth_supported(struct device *dev, struct opp_table *opp_table)
 
 	/* Checking only first OPP is sufficient */
 	np = of_get_next_available_child(opp_np, NULL);
+	of_node_put(opp_np);
 	if (!np) {
 		dev_err(dev, "OPP table empty\n");
 		return -EINVAL;
 	}
-	of_node_put(opp_np);
 
 	prop = of_find_property(np, "opp-peak-kBps", NULL);
 	of_node_put(np);
diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c
index aa55cfca9e40..6b617024a67d 100644
--- a/drivers/regulator/pfuze100-regulator.c
+++ b/drivers/regulator/pfuze100-regulator.c
@@ -10,6 +10,7 @@
 #include <linux/of_device.h>
 #include <linux/regulator/of_regulator.h>
 #include <linux/platform_device.h>
+#include <linux/reboot.h>
 #include <linux/regulator/driver.h>
 #include <linux/regulator/machine.h>
 #include <linux/regulator/pfuze100.h>
@@ -571,10 +572,10 @@ static inline struct device_node *match_of_node(int index)
 	return pfuze_matches[index].of_node;
 }
 
-static struct pfuze_chip *syspm_pfuze_chip;
-
-static void pfuze_power_off_prepare(void)
+static int pfuze_power_off_prepare(struct sys_off_data *data)
 {
+	struct pfuze_chip *syspm_pfuze_chip = data->cb_data;
+
 	dev_info(syspm_pfuze_chip->dev, "Configure standby mode for power off");
 
 	/* Switch from default mode: APS/APS to APS/Off */
@@ -609,28 +610,30 @@ static void pfuze_power_off_prepare(void)
 	regmap_update_bits(syspm_pfuze_chip->regmap, PFUZE100_VGEN6VOL,
 			   PFUZE100_VGENxLPWR | PFUZE100_VGENxSTBY,
 			   PFUZE100_VGENxSTBY);
+
+	return NOTIFY_DONE;
 }
 
 static int pfuze_power_off_prepare_init(struct pfuze_chip *pfuze_chip)
 {
+	int err;
+
 	if (pfuze_chip->chip_id != PFUZE100) {
 		dev_warn(pfuze_chip->dev, "Requested pm_power_off_prepare handler for not supported chip\n");
 		return -ENODEV;
 	}
 
-	if (pm_power_off_prepare) {
-		dev_warn(pfuze_chip->dev, "pm_power_off_prepare is already registered.\n");
-		return -EBUSY;
+	err = devm_register_sys_off_handler(pfuze_chip->dev,
+					    SYS_OFF_MODE_POWER_OFF_PREPARE,
+					    SYS_OFF_PRIO_DEFAULT,
+					    pfuze_power_off_prepare,
+					    pfuze_chip);
+	if (err) {
+		dev_err(pfuze_chip->dev, "failed to register sys-off handler: %d\n",
+			err);
+		return err;
 	}
 
-	if (syspm_pfuze_chip) {
-		dev_warn(pfuze_chip->dev, "syspm_pfuze_chip is already set.\n");
-		return -EBUSY;
-	}
-
-	syspm_pfuze_chip = pfuze_chip;
-	pm_power_off_prepare = pfuze_power_off_prepare;
-
 	return 0;
 }
 
@@ -839,23 +842,12 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 	return 0;
 }
 
-static int pfuze100_regulator_remove(struct i2c_client *client)
-{
-	if (syspm_pfuze_chip) {
-		syspm_pfuze_chip = NULL;
-		pm_power_off_prepare = NULL;
-	}
-
-	return 0;
-}
-
 static struct i2c_driver pfuze_driver = {
 	.driver = {
 		.name = "pfuze100-regulator",
 		.of_match_table = pfuze_dt_ids,
 	},
 	.probe = pfuze100_regulator_probe,
-	.remove = pfuze100_regulator_remove,
 };
 module_i2c_driver(pfuze_driver);
 
diff --git a/drivers/soc/tegra/pmc.c b/drivers/soc/tegra/pmc.c
index c77ecf61818b..5611d14d3ba2 100644
--- a/drivers/soc/tegra/pmc.c
+++ b/drivers/soc/tegra/pmc.c
@@ -39,6 +39,7 @@
 #include <linux/platform_device.h>
 #include <linux/pm_domain.h>
 #include <linux/pm_opp.h>
+#include <linux/power_supply.h>
 #include <linux/reboot.h>
 #include <linux/regmap.h>
 #include <linux/reset.h>
@@ -108,6 +109,7 @@
 #define PMC_USB_DEBOUNCE_DEL		0xec
 #define PMC_USB_AO			0xf0
 
+#define PMC_SCRATCH37			0x130
 #define PMC_SCRATCH41			0x140
 
 #define PMC_WAKE2_MASK			0x160
@@ -1101,8 +1103,7 @@ static struct notifier_block tegra_pmc_reboot_notifier = {
 	.notifier_call = tegra_pmc_reboot_notify,
 };
 
-static int tegra_pmc_restart_notify(struct notifier_block *this,
-				    unsigned long action, void *data)
+static void tegra_pmc_restart(void)
 {
 	u32 value;
 
@@ -1110,14 +1111,31 @@ static int tegra_pmc_restart_notify(struct notifier_block *this,
 	value = tegra_pmc_readl(pmc, PMC_CNTRL);
 	value |= PMC_CNTRL_MAIN_RST;
 	tegra_pmc_writel(pmc, value, PMC_CNTRL);
+}
+
+static int tegra_pmc_restart_handler(struct sys_off_data *data)
+{
+	tegra_pmc_restart();
 
 	return NOTIFY_DONE;
 }
 
-static struct notifier_block tegra_pmc_restart_handler = {
-	.notifier_call = tegra_pmc_restart_notify,
-	.priority = 128,
-};
+static int tegra_pmc_power_off_handler(struct sys_off_data *data)
+{
+	/*
+	 * Reboot Nexus 7 into special bootloader mode if USB cable is
+	 * connected in order to display battery status and power off.
+	 */
+	if (of_machine_is_compatible("asus,grouper") &&
+	    power_supply_is_system_supplied()) {
+		const u32 go_to_charger_mode = 0xa5a55a5a;
+
+		tegra_pmc_writel(pmc, go_to_charger_mode, PMC_SCRATCH37);
+		tegra_pmc_restart();
+	}
+
+	return NOTIFY_DONE;
+}
 
 static int powergate_show(struct seq_file *s, void *data)
 {
@@ -2880,6 +2898,42 @@ static int tegra_pmc_probe(struct platform_device *pdev)
 	}
 
 	/*
+	 * PMC should be last resort for restarting since it soft-resets
+	 * CPU without resetting everything else.
+	 */
+	err = devm_register_reboot_notifier(&pdev->dev,
+					    &tegra_pmc_reboot_notifier);
+	if (err) {
+		dev_err(&pdev->dev, "unable to register reboot notifier, %d\n",
+			err);
+		return err;
+	}
+
+	err = devm_register_sys_off_handler(&pdev->dev,
+					    SYS_OFF_MODE_RESTART,
+					    SYS_OFF_PRIO_LOW,
+					    tegra_pmc_restart_handler, NULL);
+	if (err) {
+		dev_err(&pdev->dev, "failed to register sys-off handler: %d\n",
+			err);
+		return err;
+	}
+
+	/*
+	 * PMC should be primary power-off method if it soft-resets CPU,
+	 * asking bootloader to shutdown hardware.
+	 */
+	err = devm_register_sys_off_handler(&pdev->dev,
+					    SYS_OFF_MODE_POWER_OFF,
+					    SYS_OFF_PRIO_FIRMWARE,
+					    tegra_pmc_power_off_handler, NULL);
+	if (err) {
+		dev_err(&pdev->dev, "failed to register sys-off handler: %d\n",
+			err);
+		return err;
+	}
+
+	/*
 	 * PCLK clock rate can't be retrieved using CLK API because it
 	 * causes lockup if CPU enters LP2 idle state from some other
 	 * CLK notifier, hence we're caching the rate's value locally.
@@ -2910,28 +2964,13 @@ static int tegra_pmc_probe(struct platform_device *pdev)
 			goto cleanup_sysfs;
 	}
 
-	err = devm_register_reboot_notifier(&pdev->dev,
-					    &tegra_pmc_reboot_notifier);
-	if (err) {
-		dev_err(&pdev->dev, "unable to register reboot notifier, %d\n",
-			err);
-		goto cleanup_debugfs;
-	}
-
-	err = register_restart_handler(&tegra_pmc_restart_handler);
-	if (err) {
-		dev_err(&pdev->dev, "unable to register restart handler, %d\n",
-			err);
-		goto cleanup_debugfs;
-	}
-
 	err = tegra_pmc_pinctrl_init(pmc);
 	if (err)
-		goto cleanup_restart_handler;
+		goto cleanup_debugfs;
 
 	err = tegra_pmc_regmap_init(pmc);
 	if (err < 0)
-		goto cleanup_restart_handler;
+		goto cleanup_debugfs;
 
 	err = tegra_powergate_init(pmc, pdev->dev.of_node);
 	if (err < 0)
@@ -2954,8 +2993,6 @@ static int tegra_pmc_probe(struct platform_device *pdev)
 
 cleanup_powergates:
 	tegra_powergate_remove_all(pdev->dev.of_node);
-cleanup_restart_handler:
-	unregister_restart_handler(&tegra_pmc_restart_handler);
 cleanup_debugfs:
 	debugfs_remove(pmc->debugfs);
 cleanup_sysfs: