Merge branch 'thermal-intel'

Merge thermal control changes related to Intel platforms for 6.3-rc1:

 - Rework ACPI helper functions for thermal control to retrieve a trip
   point temperature instead of initializing a trip point objetc (Rafael
   Wysocki).

 - Clean up and improve the int340x thermal driver ((Rafael Wysocki).

 - Simplify and clean up the intel_pch thermal driver ((Rafael Wysocki).

 - Fix the Intel powerclamp thermal driver and make it use the common
   idle injection framework (Srinivas Pandruvada).

 - Add two module parameters, cpumask and max_idle, to the Intel powerclamp
   thermal driver to allow it to affect only a specific subset of CPUs
   instead of all of them (Srinivas Pandruvada).

 - Make the Intel quark_dts thermal driver Use generic trip point
   objects instead of its own trip point representation (Daniel
   Lezcano).

 - Add toctree entry for thermal documents and fix two issues in the
   Intel powerclamp driver documentation (Bagas Sanjaya).

* thermal-intel: (25 commits)
  Documentation: powerclamp: Fix numbered lists formatting
  Documentation: powerclamp: Escape wildcard in cpumask description
  Documentation: admin-guide: Add toctree entry for thermal docs
  thermal: intel: powerclamp: Add two module parameters
  Documentation: admin-guide: Move intel_powerclamp documentation
  thermal: intel: powerclamp: Fix duration module parameter
  thermal: intel: powerclamp: Return last requested state as cur_state
  thermal: intel: quark_dts: Use generic trip points
  thermal: intel: powerclamp: Use powercap idle-inject feature
  powercap: idle_inject: Add update callback
  powercap: idle_inject: Export symbols
  thermal: intel: powerclamp: Fix cur_state for multi package system
  thermal: intel: intel_pch: Drop struct board_info
  thermal: intel: intel_pch: Rename board ID symbols
  thermal: intel: intel_pch: Fold suspend and resume routines into their callers
  thermal: intel: intel_pch: Fold two functions into their callers
  thermal: intel: intel_pch: Eliminate device operations object
  thermal: intel: intel_pch: Rename device operations callbacks
  thermal: intel: intel_pch: Eliminate redundant return pointers
  thermal: intel: intel_pch: Make pch_wpt_add_acpi_psv_trip() return int
  ...

6 files changed, 580 insertions, 610 deletions

diff --git a/drivers/thermal/intel/Kconfig b/drivers/thermal/intel/Kconfig
index e50fd260484a..b5808f92702d 100644
--- a/drivers/thermal/intel/Kconfig
+++ b/drivers/thermal/intel/Kconfig
@@ -3,6 +3,9 @@ config INTEL_POWERCLAMP
 	tristate "Intel PowerClamp idle injection driver"
 	depends on X86
 	depends on CPU_SUP_INTEL
+	depends on CPU_IDLE
+	select POWERCAP
+	select IDLE_INJECT
 	help
 	  Enable this to enable Intel PowerClamp idle injection driver. This
 	  enforce idle time which results in more package C-state residency. The
diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
index 09b1b51eb6a5..00665967ca52 100644
--- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
+++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
@@ -29,24 +29,27 @@ static int int340x_thermal_get_zone_temp(struct thermal_zone_device *zone,
 		if (conv_temp < 0)
 			return conv_temp;
 
-		*temp = (unsigned long)conv_temp * 10;
-	} else
+		*temp = conv_temp * 10;
+	} else {
 		/* _TMP returns the temperature in tenths of degrees Kelvin */
 		*temp = deci_kelvin_to_millicelsius(tmp);
+	}
 
 	return 0;
 }
 
 static int int340x_thermal_set_trip_temp(struct thermal_zone_device *zone,
-				      int trip, int temp)
+					 int trip, int temp)
 {
 	struct int34x_thermal_zone *d = zone->devdata;
+	char name[] = {'P', 'A', 'T', '0' + trip, '\0'};
 	acpi_status status;
-	char name[10];
 
-	snprintf(name, sizeof(name), "PAT%d", trip);
+	if (trip > 9)
+		return -EINVAL;
+
 	status = acpi_execute_simple_method(d->adev->handle, name,
-			millicelsius_to_deci_kelvin(temp));
+					    millicelsius_to_deci_kelvin(temp));
 	if (ACPI_FAILURE(status))
 		return -EIO;
 
@@ -70,24 +73,34 @@ static int int340x_thermal_read_trips(struct acpi_device *zone_adev,
 {
 	int i, ret;
 
-	ret = thermal_acpi_trip_critical(zone_adev, &zone_trips[trip_cnt]);
-	if (!ret)
+	ret = thermal_acpi_critical_trip_temp(zone_adev,
+					      &zone_trips[trip_cnt].temperature);
+	if (!ret) {
+		zone_trips[trip_cnt].type = THERMAL_TRIP_CRITICAL;
 		trip_cnt++;
+	}
 
-	ret = thermal_acpi_trip_hot(zone_adev, &zone_trips[trip_cnt]);
-	if (!ret)
+	ret = thermal_acpi_hot_trip_temp(zone_adev,
+					 &zone_trips[trip_cnt].temperature);
+	if (!ret) {
+		zone_trips[trip_cnt].type = THERMAL_TRIP_HOT;
 		trip_cnt++;
+	}
 
-	ret = thermal_acpi_trip_passive(zone_adev, &zone_trips[trip_cnt]);
-	if (!ret)
+	ret = thermal_acpi_passive_trip_temp(zone_adev,
+					     &zone_trips[trip_cnt].temperature);
+	if (!ret) {
+		zone_trips[trip_cnt].type = THERMAL_TRIP_PASSIVE;
 		trip_cnt++;
+	}
 
 	for (i = 0; i < INT340X_THERMAL_MAX_ACT_TRIP_COUNT; i++) {
-
-		ret = thermal_acpi_trip_active(zone_adev, i, &zone_trips[trip_cnt]);
+		ret = thermal_acpi_active_trip_temp(zone_adev, i,
+						    &zone_trips[trip_cnt].temperature);
 		if (ret)
 			break;
 
+		zone_trips[trip_cnt].type = THERMAL_TRIP_ACTIVE;
 		trip_cnt++;
 	}
 
@@ -102,7 +115,7 @@ static struct thermal_zone_params int340x_thermal_params = {
 struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *adev,
 						     int (*get_temp) (struct thermal_zone_device *, int *))
 {
-	struct int34x_thermal_zone *int34x_thermal_zone;
+	struct int34x_thermal_zone *int34x_zone;
 	struct thermal_trip *zone_trips;
 	unsigned long long trip_cnt = 0;
 	unsigned long long hyst;
@@ -110,26 +123,25 @@ struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *adev,
 	acpi_status status;
 	int i, ret;
 
-	int34x_thermal_zone = kzalloc(sizeof(*int34x_thermal_zone),
-				      GFP_KERNEL);
-	if (!int34x_thermal_zone)
+	int34x_zone = kzalloc(sizeof(*int34x_zone), GFP_KERNEL);
+	if (!int34x_zone)
 		return ERR_PTR(-ENOMEM);
 
-	int34x_thermal_zone->adev = adev;
+	int34x_zone->adev = adev;
 
-	int34x_thermal_zone->ops = kmemdup(&int340x_thermal_zone_ops,
-					   sizeof(int340x_thermal_zone_ops), GFP_KERNEL);
-	if (!int34x_thermal_zone->ops) {
+	int34x_zone->ops = kmemdup(&int340x_thermal_zone_ops,
+				   sizeof(int340x_thermal_zone_ops), GFP_KERNEL);
+	if (!int34x_zone->ops) {
 		ret = -ENOMEM;
 		goto err_ops_alloc;
 	}
 
 	if (get_temp)
-		int34x_thermal_zone->ops->get_temp = get_temp;
+		int34x_zone->ops->get_temp = get_temp;
 
 	status = acpi_evaluate_integer(adev->handle, "PATC", NULL, &trip_cnt);
-	if (!ACPI_FAILURE(status)) {
-		int34x_thermal_zone->aux_trip_nr = trip_cnt;
+	if (ACPI_SUCCESS(status)) {
+		int34x_zone->aux_trip_nr = trip_cnt;
 		trip_mask = BIT(trip_cnt) - 1;
 	}
 
@@ -156,49 +168,47 @@ struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *adev,
 	for (i = 0; i < trip_cnt; ++i)
 		zone_trips[i].hysteresis = hyst;
 
-	int34x_thermal_zone->trips = zone_trips;
+	int34x_zone->trips = zone_trips;
 
-	int34x_thermal_zone->lpat_table = acpi_lpat_get_conversion_table(
-								adev->handle);
+	int34x_zone->lpat_table = acpi_lpat_get_conversion_table(adev->handle);
 
-	int34x_thermal_zone->zone = thermal_zone_device_register_with_trips(
-						acpi_device_bid(adev),
-						zone_trips, trip_cnt,
-						trip_mask, int34x_thermal_zone,
-						int34x_thermal_zone->ops,
-						&int340x_thermal_params,
-						0, 0);
-	if (IS_ERR(int34x_thermal_zone->zone)) {
-		ret = PTR_ERR(int34x_thermal_zone->zone);
+	int34x_zone->zone = thermal_zone_device_register_with_trips(
+							acpi_device_bid(adev),
+							zone_trips, trip_cnt,
+							trip_mask, int34x_zone,
+							int34x_zone->ops,
+							&int340x_thermal_params,
+							0, 0);
+	if (IS_ERR(int34x_zone->zone)) {
+		ret = PTR_ERR(int34x_zone->zone);
 		goto err_thermal_zone;
 	}
-	ret = thermal_zone_device_enable(int34x_thermal_zone->zone);
+	ret = thermal_zone_device_enable(int34x_zone->zone);
 	if (ret)
 		goto err_enable;
 
-	return int34x_thermal_zone;
+	return int34x_zone;
 
 err_enable:
-	thermal_zone_device_unregister(int34x_thermal_zone->zone);
+	thermal_zone_device_unregister(int34x_zone->zone);
 err_thermal_zone:
-	kfree(int34x_thermal_zone->trips);
-	acpi_lpat_free_conversion_table(int34x_thermal_zone->lpat_table);
+	kfree(int34x_zone->trips);
+	acpi_lpat_free_conversion_table(int34x_zone->lpat_table);
 err_trips_alloc:
-	kfree(int34x_thermal_zone->ops);
+	kfree(int34x_zone->ops);
 err_ops_alloc:
-	kfree(int34x_thermal_zone);
+	kfree(int34x_zone);
 	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(int340x_thermal_zone_add);
 
-void int340x_thermal_zone_remove(struct int34x_thermal_zone
-				 *int34x_thermal_zone)
+void int340x_thermal_zone_remove(struct int34x_thermal_zone *int34x_zone)
 {
-	thermal_zone_device_unregister(int34x_thermal_zone->zone);
-	acpi_lpat_free_conversion_table(int34x_thermal_zone->lpat_table);
-	kfree(int34x_thermal_zone->trips);
-	kfree(int34x_thermal_zone->ops);
-	kfree(int34x_thermal_zone);
+	thermal_zone_device_unregister(int34x_zone->zone);
+	acpi_lpat_free_conversion_table(int34x_zone->lpat_table);
+	kfree(int34x_zone->trips);
+	kfree(int34x_zone->ops);
+	kfree(int34x_zone);
 }
 EXPORT_SYMBOL_GPL(int340x_thermal_zone_remove);
 
@@ -213,22 +223,21 @@ void int340x_thermal_update_trips(struct int34x_thermal_zone *int34x_zone)
 	mutex_lock(&int34x_zone->zone->lock);
 
 	for (i = int34x_zone->aux_trip_nr; i < trip_cnt; i++) {
-		struct thermal_trip trip;
-		int err;
+		int temp, err;
 
 		switch (zone_trips[i].type) {
 		case THERMAL_TRIP_CRITICAL:
-			err = thermal_acpi_trip_critical(zone_adev, &trip);
+			err = thermal_acpi_critical_trip_temp(zone_adev, &temp);
 			break;
 		case THERMAL_TRIP_HOT:
-			err = thermal_acpi_trip_hot(zone_adev, &trip);
+			err = thermal_acpi_hot_trip_temp(zone_adev, &temp);
 			break;
 		case THERMAL_TRIP_PASSIVE:
-			err = thermal_acpi_trip_passive(zone_adev, &trip);
+			err = thermal_acpi_passive_trip_temp(zone_adev, &temp);
 			break;
 		case THERMAL_TRIP_ACTIVE:
-			err = thermal_acpi_trip_active(zone_adev, act_trip_nr++,
-						       &trip);
+			err = thermal_acpi_active_trip_temp(zone_adev, act_trip_nr++,
+							    &temp);
 			break;
 		default:
 			err = -ENODEV;
@@ -238,7 +247,7 @@ void int340x_thermal_update_trips(struct int34x_thermal_zone *int34x_zone)
 			continue;
 		}
 
-		zone_trips[i].temperature = trip.temperature;
+		zone_trips[i].temperature = temp;
 	}
 
 	mutex_unlock(&int34x_zone->zone->lock);
diff --git a/drivers/thermal/intel/intel_pch_thermal.c b/drivers/thermal/intel/intel_pch_thermal.c
index 45a9ea86907e..b855d031a855 100644
--- a/drivers/thermal/intel/intel_pch_thermal.c
+++ b/drivers/thermal/intel/intel_pch_thermal.c
@@ -82,7 +82,6 @@ static char driver_name[] = "Intel PCH thermal driver";
 
 struct pch_thermal_device {
 	void __iomem *hw_base;
-	const struct pch_dev_ops *ops;
 	struct pci_dev *pdev;
 	struct thermal_zone_device *tzd;
 	struct thermal_trip trips[PCH_MAX_TRIPS];
@@ -90,42 +89,107 @@ struct pch_thermal_device {
 };
 
 #ifdef CONFIG_ACPI
-
 /*
  * On some platforms, there is a companion ACPI device, which adds
  * passive trip temperature using _PSV method. There is no specific
  * passive temperature setting in MMIO interface of this PCI device.
  */
-static void pch_wpt_add_acpi_psv_trip(struct pch_thermal_device *ptd,
-				      int *nr_trips)
+static int pch_wpt_add_acpi_psv_trip(struct pch_thermal_device *ptd, int trip)
 {
 	struct acpi_device *adev;
-	int ret;
+	int temp;
 
 	adev = ACPI_COMPANION(&ptd->pdev->dev);
 	if (!adev)
-		return;
+		return 0;
 
-	ret = thermal_acpi_trip_passive(adev, &ptd->trips[*nr_trips]);
-	if (ret || ptd->trips[*nr_trips].temperature <= 0)
-		return;
+	if (thermal_acpi_passive_trip_temp(adev, &temp) || temp <= 0)
+		return 0;
 
-	++(*nr_trips);
+	ptd->trips[trip].type = THERMAL_TRIP_PASSIVE;
+	ptd->trips[trip].temperature = temp;
+	return 1;
 }
 #else
-static void pch_wpt_add_acpi_psv_trip(struct pch_thermal_device *ptd,
-				      int *nr_trips)
+static int pch_wpt_add_acpi_psv_trip(struct pch_thermal_device *ptd, int trip)
 {
-
+	return 0;
 }
 #endif
 
-static int pch_wpt_init(struct pch_thermal_device *ptd, int *nr_trips)
+static int pch_thermal_get_temp(struct thermal_zone_device *tzd, int *temp)
 {
-	u8 tsel;
+	struct pch_thermal_device *ptd = tzd->devdata;
+
+	*temp = GET_WPT_TEMP(WPT_TEMP_TSR & readw(ptd->hw_base + WPT_TEMP));
+	return 0;
+}
+
+static void pch_critical(struct thermal_zone_device *tzd)
+{
+	dev_dbg(&tzd->device, "%s: critical temperature reached\n", tzd->type);
+}
+
+static struct thermal_zone_device_ops tzd_ops = {
+	.get_temp = pch_thermal_get_temp,
+	.critical = pch_critical,
+};
+
+enum pch_board_ids {
+	PCH_BOARD_HSW = 0,
+	PCH_BOARD_WPT,
+	PCH_BOARD_SKL,
+	PCH_BOARD_CNL,
+	PCH_BOARD_CML,
+	PCH_BOARD_LWB,
+	PCH_BOARD_WBG,
+};
+
+static const char *board_names[] = {
+	[PCH_BOARD_HSW] = "pch_haswell",
+	[PCH_BOARD_WPT] = "pch_wildcat_point",
+	[PCH_BOARD_SKL] = "pch_skylake",
+	[PCH_BOARD_CNL] = "pch_cannonlake",
+	[PCH_BOARD_CML] = "pch_cometlake",
+	[PCH_BOARD_LWB] = "pch_lewisburg",
+	[PCH_BOARD_WBG] = "pch_wellsburg",
+};
+
+static int intel_pch_thermal_probe(struct pci_dev *pdev,
+				   const struct pci_device_id *id)
+{
+	enum pch_board_ids board_id = id->driver_data;
+	struct pch_thermal_device *ptd;
+	int nr_trips = 0;
 	u16 trip_temp;
+	u8 tsel;
+	int err;
+
+	ptd = devm_kzalloc(&pdev->dev, sizeof(*ptd), GFP_KERNEL);
+	if (!ptd)
+		return -ENOMEM;
+
+	pci_set_drvdata(pdev, ptd);
+	ptd->pdev = pdev;
+
+	err = pci_enable_device(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable pci device\n");
+		return err;
+	}
+
+	err = pci_request_regions(pdev, driver_name);
+	if (err) {
+		dev_err(&pdev->dev, "failed to request pci region\n");
+		goto error_disable;
+	}
 
-	*nr_trips = 0;
+	ptd->hw_base = pci_ioremap_bar(pdev, 0);
+	if (!ptd->hw_base) {
+		err = -ENOMEM;
+		dev_err(&pdev->dev, "failed to map mem base\n");
+		goto error_release;
+	}
 
 	/* Check if BIOS has already enabled thermal sensor */
 	if (WPT_TSEL_ETS & readb(ptd->hw_base + WPT_TSEL)) {
@@ -140,50 +204,79 @@ static int pch_wpt_init(struct pch_thermal_device *ptd, int *nr_trips)
 	 */
 	if (tsel & WPT_TSEL_PLDB) {
 		dev_err(&ptd->pdev->dev, "Sensor can't be enabled\n");
-		return -ENODEV;
+		err = -ENODEV;
+		goto error_cleanup;
 	}
 
 	writeb(tsel|WPT_TSEL_ETS, ptd->hw_base + WPT_TSEL);
 	if (!(WPT_TSEL_ETS & readb(ptd->hw_base + WPT_TSEL))) {
 		dev_err(&ptd->pdev->dev, "Sensor can't be enabled\n");
-		return -ENODEV;
+		err = -ENODEV;
+		goto error_cleanup;
 	}
 
 read_trips:
 	trip_temp = readw(ptd->hw_base + WPT_CTT);
 	trip_temp &= 0x1FF;
 	if (trip_temp) {
-		ptd->trips[*nr_trips].temperature = GET_WPT_TEMP(trip_temp);
-		ptd->trips[*nr_trips].type = THERMAL_TRIP_CRITICAL;
-		++(*nr_trips);
+		ptd->trips[nr_trips].temperature = GET_WPT_TEMP(trip_temp);
+		ptd->trips[nr_trips++].type = THERMAL_TRIP_CRITICAL;
 	}
 
 	trip_temp = readw(ptd->hw_base + WPT_PHL);
 	trip_temp &= 0x1FF;
 	if (trip_temp) {
-		ptd->trips[*nr_trips].temperature = GET_WPT_TEMP(trip_temp);
-		ptd->trips[*nr_trips].type = THERMAL_TRIP_HOT;
-		++(*nr_trips);
+		ptd->trips[nr_trips].temperature = GET_WPT_TEMP(trip_temp);
+		ptd->trips[nr_trips++].type = THERMAL_TRIP_HOT;
 	}
 
-	pch_wpt_add_acpi_psv_trip(ptd, nr_trips);
+	nr_trips += pch_wpt_add_acpi_psv_trip(ptd, nr_trips);
+
+	ptd->tzd = thermal_zone_device_register_with_trips(board_names[board_id],
+							   ptd->trips, nr_trips,
+							   0, ptd, &tzd_ops,
+							   NULL, 0, 0);
+	if (IS_ERR(ptd->tzd)) {
+		dev_err(&pdev->dev, "Failed to register thermal zone %s\n",
+			board_names[board_id]);
+		err = PTR_ERR(ptd->tzd);
+		goto error_cleanup;
+	}
+	err = thermal_zone_device_enable(ptd->tzd);
+	if (err)
+		goto err_unregister;
 
 	return 0;
+
+err_unregister:
+	thermal_zone_device_unregister(ptd->tzd);
+error_cleanup:
+	iounmap(ptd->hw_base);
+error_release:
+	pci_release_regions(pdev);
+error_disable:
+	pci_disable_device(pdev);
+	dev_err(&pdev->dev, "pci device failed to probe\n");
+	return err;
 }
 
-static int pch_wpt_get_temp(struct pch_thermal_device *ptd, int *temp)
+static void intel_pch_thermal_remove(struct pci_dev *pdev)
 {
-	*temp = GET_WPT_TEMP(WPT_TEMP_TSR & readw(ptd->hw_base + WPT_TEMP));
+	struct pch_thermal_device *ptd = pci_get_drvdata(pdev);
 
-	return 0;
+	thermal_zone_device_unregister(ptd->tzd);
+	iounmap(ptd->hw_base);
+	pci_set_drvdata(pdev, NULL);
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
 }
 
-/* Cool the PCH when it's overheat in .suspend_noirq phase */
-static int pch_wpt_suspend(struct pch_thermal_device *ptd)
+static int intel_pch_thermal_suspend_noirq(struct device *device)
 {
-	u8 tsel;
-	int pch_delay_cnt = 0;
+	struct pch_thermal_device *ptd = dev_get_drvdata(device);
 	u16 pch_thr_temp, pch_cur_temp;
+	int pch_delay_cnt = 0;
+	u8 tsel;
 
 	/* Shutdown the thermal sensor if it is not enabled by BIOS */
 	if (!ptd->bios_enabled) {
@@ -246,8 +339,9 @@ static int pch_wpt_suspend(struct pch_thermal_device *ptd)
 	return 0;
 }
 
-static int pch_wpt_resume(struct pch_thermal_device *ptd)
+static int intel_pch_thermal_resume(struct device *device)
 {
+	struct pch_thermal_device *ptd = dev_get_drvdata(device);
 	u8 tsel;
 
 	if (ptd->bios_enabled)
@@ -260,199 +354,29 @@ static int pch_wpt_resume(struct pch_thermal_device *ptd)
 	return 0;
 }
 
-struct pch_dev_ops {
-	int (*hw_init)(struct pch_thermal_device *ptd, int *nr_trips);
-	int (*get_temp)(struct pch_thermal_device *ptd, int *temp);
-	int (*suspend)(struct pch_thermal_device *ptd);
-	int (*resume)(struct pch_thermal_device *ptd);
-};
-
-
-/* dev ops for Wildcat Point */
-static const struct pch_dev_ops pch_dev_ops_wpt = {
-	.hw_init = pch_wpt_init,
-	.get_temp = pch_wpt_get_temp,
-	.suspend = pch_wpt_suspend,
-	.resume = pch_wpt_resume,
-};
-
-static int pch_thermal_get_temp(struct thermal_zone_device *tzd, int *temp)
-{
-	struct pch_thermal_device *ptd = tzd->devdata;
-
-	return	ptd->ops->get_temp(ptd, temp);
-}
-
-static void pch_critical(struct thermal_zone_device *tzd)
-{
-	dev_dbg(&tzd->device, "%s: critical temperature reached\n", tzd->type);
-}
-
-static struct thermal_zone_device_ops tzd_ops = {
-	.get_temp = pch_thermal_get_temp,
-	.critical = pch_critical,
-};
-
-enum board_ids {
-	board_hsw,
-	board_wpt,
-	board_skl,
-	board_cnl,
-	board_cml,
-	board_lwb,
-	board_wbg,
-};
-
-static const struct board_info {
-	const char *name;
-	const struct pch_dev_ops *ops;
-} board_info[] = {
-	[board_hsw] = {
-		.name = "pch_haswell",
-		.ops = &pch_dev_ops_wpt,
-	},
-	[board_wpt] = {
-		.name = "pch_wildcat_point",
-		.ops = &pch_dev_ops_wpt,
-	},
-	[board_skl] = {
-		.name = "pch_skylake",
-		.ops = &pch_dev_ops_wpt,
-	},
-	[board_cnl] = {
-		.name = "pch_cannonlake",
-		.ops = &pch_dev_ops_wpt,
-	},
-	[board_cml] = {
-		.name = "pch_cometlake",
-		.ops = &pch_dev_ops_wpt,
-	},
-	[board_lwb] = {
-		.name = "pch_lewisburg",
-		.ops = &pch_dev_ops_wpt,
-	},
-	[board_wbg] = {
-		.name = "pch_wellsburg",
-		.ops = &pch_dev_ops_wpt,
-	},
-};
-
-static int intel_pch_thermal_probe(struct pci_dev *pdev,
-				   const struct pci_device_id *id)
-{
-	enum board_ids board_id = id->driver_data;
-	const struct board_info *bi = &board_info[board_id];
-	struct pch_thermal_device *ptd;
-	int err;
-	int nr_trips;
-
-	ptd = devm_kzalloc(&pdev->dev, sizeof(*ptd), GFP_KERNEL);
-	if (!ptd)
-		return -ENOMEM;
-
-	ptd->ops = bi->ops;
-
-	pci_set_drvdata(pdev, ptd);
-	ptd->pdev = pdev;
-
-	err = pci_enable_device(pdev);
-	if (err) {
-		dev_err(&pdev->dev, "failed to enable pci device\n");
-		return err;
-	}
-
-	err = pci_request_regions(pdev, driver_name);
-	if (err) {
-		dev_err(&pdev->dev, "failed to request pci region\n");
-		goto error_disable;
-	}
-
-	ptd->hw_base = pci_ioremap_bar(pdev, 0);
-	if (!ptd->hw_base) {
-		err = -ENOMEM;
-		dev_err(&pdev->dev, "failed to map mem base\n");
-		goto error_release;
-	}
-
-	err = ptd->ops->hw_init(ptd, &nr_trips);
-	if (err)
-		goto error_cleanup;
-
-	ptd->tzd = thermal_zone_device_register_with_trips(bi->name, ptd->trips,
-							   nr_trips, 0, ptd,
-							   &tzd_ops, NULL, 0, 0);
-	if (IS_ERR(ptd->tzd)) {
-		dev_err(&pdev->dev, "Failed to register thermal zone %s\n",
-			bi->name);
-		err = PTR_ERR(ptd->tzd);
-		goto error_cleanup;
-	}
-	err = thermal_zone_device_enable(ptd->tzd);
-	if (err)
-		goto err_unregister;
-
-	return 0;
-
-err_unregister:
-	thermal_zone_device_unregister(ptd->tzd);
-error_cleanup:
-	iounmap(ptd->hw_base);
-error_release:
-	pci_release_regions(pdev);
-error_disable:
-	pci_disable_device(pdev);
-	dev_err(&pdev->dev, "pci device failed to probe\n");
-	return err;
-}
-
-static void intel_pch_thermal_remove(struct pci_dev *pdev)
-{
-	struct pch_thermal_device *ptd = pci_get_drvdata(pdev);
-
-	thermal_zone_device_unregister(ptd->tzd);
-	iounmap(ptd->hw_base);
-	pci_set_drvdata(pdev, NULL);
-	pci_release_regions(pdev);
-	pci_disable_device(pdev);
-}
-
-static int intel_pch_thermal_suspend_noirq(struct device *device)
-{
-	struct pch_thermal_device *ptd = dev_get_drvdata(device);
-
-	return ptd->ops->suspend(ptd);
-}
-
-static int intel_pch_thermal_resume(struct device *device)
-{
-	struct pch_thermal_device *ptd = dev_get_drvdata(device);
-
-	return ptd->ops->resume(ptd);
-}
-
 static const struct pci_device_id intel_pch_thermal_id[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_HSW_1),
-		.driver_data = board_hsw, },
+		.driver_data = PCH_BOARD_HSW, },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_HSW_2),
-		.driver_data = board_hsw, },
+		.driver_data = PCH_BOARD_HSW, },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_WPT),
-		.driver_data = board_wpt, },
+		.driver_data = PCH_BOARD_WPT, },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_SKL),
-		.driver_data = board_skl, },
+		.driver_data = PCH_BOARD_SKL, },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_SKL_H),
-		.driver_data = board_skl, },
+		.driver_data = PCH_BOARD_SKL, },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_CNL),
-		.driver_data = board_cnl, },
+		.driver_data = PCH_BOARD_CNL, },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_CNL_H),
-		.driver_data = board_cnl, },
+		.driver_data = PCH_BOARD_CNL, },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_CNL_LP),
-		.driver_data = board_cnl, },
+		.driver_data = PCH_BOARD_CNL, },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_CML_H),
-		.driver_data = board_cml, },
+		.driver_data = PCH_BOARD_CML, },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_LWB),
-		.driver_data = board_lwb, },
+		.driver_data = PCH_BOARD_LWB, },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_WBG),
-		.driver_data = board_wbg, },
+		.driver_data = PCH_BOARD_WBG, },
 	{ 0, },
 };
 MODULE_DEVICE_TABLE(pci, intel_pch_thermal_id);
diff --git a/drivers/thermal/intel/intel_powerclamp.c b/drivers/thermal/intel/intel_powerclamp.c
index b80e25ec1261..c7ba5680cd48 100644
--- a/drivers/thermal/intel/intel_powerclamp.c
+++ b/drivers/thermal/intel/intel_powerclamp.c
@@ -2,7 +2,7 @@
 /*
  * intel_powerclamp.c - package c-state idle injection
  *
- * Copyright (c) 2012, Intel Corporation.
+ * Copyright (c) 2012-2023, Intel Corporation.
  *
  * Authors:
  *     Arjan van de Ven <arjan@linux.intel.com>
@@ -27,23 +27,17 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/delay.h>
-#include <linux/kthread.h>
 #include <linux/cpu.h>
 #include <linux/thermal.h>
-#include <linux/slab.h>
-#include <linux/tick.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
-#include <linux/sched/rt.h>
-#include <uapi/linux/sched/types.h>
+#include <linux/idle_inject.h>
 
-#include <asm/nmi.h>
 #include <asm/msr.h>
 #include <asm/mwait.h>
 #include <asm/cpu_device_id.h>
-#include <asm/hardirq.h>
 
-#define MAX_TARGET_RATIO (50U)
+#define MAX_TARGET_RATIO (100U)
 /* For each undisturbed clamping period (no extra wake ups during idle time),
  * we increment the confidence counter for the given target ratio.
  * CONFIDENCE_OK defines the level where runtime calibration results are
@@ -57,37 +51,30 @@
 
 static unsigned int target_mwait;
 static struct dentry *debug_dir;
+static bool poll_pkg_cstate_enable;
 
-/* user selected target */
-static unsigned int set_target_ratio;
+/* Idle ratio observed using package C-state counters */
 static unsigned int current_ratio;
-static bool should_skip;
 
-static unsigned int control_cpu; /* The cpu assigned to collect stat and update
-				  * control parameters. default to BSP but BSP
-				  * can be offlined.
-				  */
-static bool clamping;
+/* Skip the idle injection till set to true */
+static bool should_skip;
 
-struct powerclamp_worker_data {
-	struct kthread_worker *worker;
-	struct kthread_work balancing_work;
-	struct kthread_delayed_work idle_injection_work;
+struct powerclamp_data {
 	unsigned int cpu;
 	unsigned int count;
 	unsigned int guard;
 	unsigned int window_size_now;
 	unsigned int target_ratio;
-	unsigned int duration_jiffies;
 	bool clamping;
 };
 
-static struct powerclamp_worker_data __percpu *worker_data;
+static struct powerclamp_data powerclamp_data;
+
 static struct thermal_cooling_device *cooling_dev;
-static unsigned long *cpu_clamping_mask;  /* bit map for tracking per cpu
-					   * clamping kthread worker
-					   */
 
+static DEFINE_MUTEX(powerclamp_lock);
+
+/* This duration is in microseconds */
 static unsigned int duration;
 static unsigned int pkg_cstate_ratio_cur;
 static unsigned int window_size;
@@ -104,25 +91,171 @@ static int duration_set(const char *arg, const struct kernel_param *kp)
 		pr_err("Out of recommended range %lu, between 6-25ms\n",
 			new_duration);
 		ret = -EINVAL;
+		goto exit;
 	}
 
-	duration = clamp(new_duration, 6ul, 25ul);
-	smp_mb();
-
+	mutex_lock(&powerclamp_lock);
+	duration = clamp(new_duration, 6ul, 25ul) * 1000;
+	mutex_unlock(&powerclamp_lock);
 exit:
 
 	return ret;
 }
 
+static int duration_get(char *buf, const struct kernel_param *kp)
+{
+	int ret;
+
+	mutex_lock(&powerclamp_lock);
+	ret = sysfs_emit(buf, "%d\n", duration / 1000);
+	mutex_unlock(&powerclamp_lock);
+
+	return ret;
+}
+
 static const struct kernel_param_ops duration_ops = {
 	.set = duration_set,
-	.get = param_get_int,
+	.get = duration_get,
 };
 
-
-module_param_cb(duration, &duration_ops, &duration, 0644);
+module_param_cb(duration, &duration_ops, NULL, 0644);
 MODULE_PARM_DESC(duration, "forced idle time for each attempt in msec.");
 
+#define DEFAULT_MAX_IDLE	50
+#define MAX_ALL_CPU_IDLE	75
+
+static u8 max_idle = DEFAULT_MAX_IDLE;
+
+static cpumask_var_t idle_injection_cpu_mask;
+
+static int allocate_copy_idle_injection_mask(const struct cpumask *copy_mask)
+{
+	if (cpumask_available(idle_injection_cpu_mask))
+		goto copy_mask;
+
+	/* This mask is allocated only one time and freed during module exit */
+	if (!alloc_cpumask_var(&idle_injection_cpu_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+copy_mask:
+	cpumask_copy(idle_injection_cpu_mask, copy_mask);
+
+	return 0;
+}
+
+/* Return true if the cpumask and idle percent combination is invalid */
+static bool check_invalid(cpumask_var_t mask, u8 idle)
+{
+	if (cpumask_equal(cpu_present_mask, mask) && idle > MAX_ALL_CPU_IDLE)
+		return true;
+
+	return false;
+}
+
+static int cpumask_set(const char *arg, const struct kernel_param *kp)
+{
+	cpumask_var_t new_mask;
+	int ret;
+
+	mutex_lock(&powerclamp_lock);
+
+	/* Can't set mask when cooling device is in use */
+	if (powerclamp_data.clamping) {
+		ret = -EAGAIN;
+		goto skip_cpumask_set;
+	}
+
+	ret = alloc_cpumask_var(&new_mask, GFP_KERNEL);
+	if (!ret)
+		goto skip_cpumask_set;
+
+	ret = bitmap_parse(arg, strlen(arg), cpumask_bits(new_mask),
+			   nr_cpumask_bits);
+	if (ret)
+		goto free_cpumask_set;
+
+	if (cpumask_empty(new_mask) || check_invalid(new_mask, max_idle)) {
+		ret = -EINVAL;
+		goto free_cpumask_set;
+	}
+
+	/*
+	 * When module parameters are passed from kernel command line
+	 * during insmod, the module parameter callback is called
+	 * before powerclamp_init(), so we can't assume that some
+	 * cpumask can be allocated and copied before here. Also
+	 * in this case this cpumask is used as the default mask.
+	 */
+	ret = allocate_copy_idle_injection_mask(new_mask);
+
+free_cpumask_set:
+	free_cpumask_var(new_mask);
+skip_cpumask_set:
+	mutex_unlock(&powerclamp_lock);
+
+	return ret;
+}
+
+static int cpumask_get(char *buf, const struct kernel_param *kp)
+{
+	if (!cpumask_available(idle_injection_cpu_mask))
+		return -ENODEV;
+
+	return bitmap_print_to_pagebuf(false, buf, cpumask_bits(idle_injection_cpu_mask),
+				       nr_cpumask_bits);
+}
+
+static const struct kernel_param_ops cpumask_ops = {
+	.set = cpumask_set,
+	.get = cpumask_get,
+};
+
+module_param_cb(cpumask, &cpumask_ops, NULL, 0644);
+MODULE_PARM_DESC(cpumask, "Mask of CPUs to use for idle injection.");
+
+static int max_idle_set(const char *arg, const struct kernel_param *kp)
+{
+	u8 new_max_idle;
+	int ret = 0;
+
+	mutex_lock(&powerclamp_lock);
+
+	/* Can't set mask when cooling device is in use */
+	if (powerclamp_data.clamping) {
+		ret = -EAGAIN;
+		goto skip_limit_set;
+	}
+
+	ret = kstrtou8(arg, 10, &new_max_idle);
+	if (ret)
+		goto skip_limit_set;
+
+	if (new_max_idle > MAX_TARGET_RATIO) {
+		ret = -EINVAL;
+		goto skip_limit_set;
+	}
+
+	if (check_invalid(idle_injection_cpu_mask, new_max_idle)) {
+		ret = -EINVAL;
+		goto skip_limit_set;
+	}
+
+	max_idle = new_max_idle;
+
+skip_limit_set:
+	mutex_unlock(&powerclamp_lock);
+
+	return ret;
+}
+
+static const struct kernel_param_ops max_idle_ops = {
+	.set = max_idle_set,
+	.get = param_get_int,
+};
+
+module_param_cb(max_idle, &max_idle_ops, &max_idle, 0644);
+MODULE_PARM_DESC(max_idle, "maximum injected idle time to the total CPU time ratio in percent range:1-100");
+
 struct powerclamp_calibration_data {
 	unsigned long confidence;  /* used for calibration, basically a counter
 				    * gets incremented each time a clamping
@@ -261,6 +394,9 @@ static unsigned int get_compensation(int ratio)
 {
 	unsigned int comp = 0;
 
+	if (!poll_pkg_cstate_enable)
+		return 0;
+
 	/* we only use compensation if all adjacent ones are good */
 	if (ratio == 1 &&
 		cal_data[ratio].confidence >= CONFIDENCE_OK &&
@@ -302,7 +438,7 @@ static void adjust_compensation(int target_ratio, unsigned int win)
 	if (d->confidence >= CONFIDENCE_OK)
 		return;
 
-	delta = set_target_ratio - current_ratio;
+	delta = powerclamp_data.target_ratio - current_ratio;
 	/* filter out bad data */
 	if (delta >= 0 && delta <= (1+target_ratio/10)) {
 		if (d->steady_comp)
@@ -341,82 +477,39 @@ static bool powerclamp_adjust_controls(unsigned int target_ratio,
 	adjust_compensation(target_ratio, win);
 
 	/* if we are above target+guard, skip */
-	return set_target_ratio + guard <= current_ratio;
+	return powerclamp_data.target_ratio + guard <= current_ratio;
 }
 
-static void clamp_balancing_func(struct kthread_work *work)
+/*
+ * This function calculates runtime from the current target ratio.
+ * This function gets called under powerclamp_lock.
+ */
+static unsigned int get_run_time(void)
 {
-	struct powerclamp_worker_data *w_data;
-	int sleeptime;
-	unsigned long target_jiffies;
 	unsigned int compensated_ratio;
-	int interval; /* jiffies to sleep for each attempt */
-
-	w_data = container_of(work, struct powerclamp_worker_data,
-			      balancing_work);
+	unsigned int runtime;
 
 	/*
 	 * make sure user selected ratio does not take effect until
 	 * the next round. adjust target_ratio if user has changed
 	 * target such that we can converge quickly.
 	 */
-	w_data->target_ratio = READ_ONCE(set_target_ratio);
-	w_data->guard = 1 + w_data->target_ratio / 20;
-	w_data->window_size_now = window_size;
-	w_data->duration_jiffies = msecs_to_jiffies(duration);
-	w_data->count++;
+	powerclamp_data.guard = 1 + powerclamp_data.target_ratio / 20;
+	powerclamp_data.window_size_now = window_size;
 
 	/*
 	 * systems may have different ability to enter package level
 	 * c-states, thus we need to compensate the injected idle ratio
 	 * to achieve the actual target reported by the HW.
 	 */
-	compensated_ratio = w_data->target_ratio +
-		get_compensation(w_data->target_ratio);
+	compensated_ratio = powerclamp_data.target_ratio +
+		get_compensation(powerclamp_data.target_ratio);
 	if (compensated_ratio <= 0)
 		compensated_ratio = 1;
-	interval = w_data->duration_jiffies * 100 / compensated_ratio;
-
-	/* align idle time */
-	target_jiffies = roundup(jiffies, interval);
-	sleeptime = target_jiffies - jiffies;
-	if (sleeptime <= 0)
-		sleeptime = 1;
-
-	if (clamping && w_data->clamping && cpu_online(w_data->cpu))
-		kthread_queue_delayed_work(w_data->worker,
-					   &w_data->idle_injection_work,
-					   sleeptime);
-}
 
-static void clamp_idle_injection_func(struct kthread_work *work)
-{
-	struct powerclamp_worker_data *w_data;
-
-	w_data = container_of(work, struct powerclamp_worker_data,
-			      idle_injection_work.work);
-
-	/*
-	 * only elected controlling cpu can collect stats and update
-	 * control parameters.
-	 */
-	if (w_data->cpu == control_cpu &&
-	    !(w_data->count % w_data->window_size_now)) {
-		should_skip =
-			powerclamp_adjust_controls(w_data->target_ratio,
-						   w_data->guard,
-						   w_data->window_size_now);
-		smp_mb();
-	}
+	runtime = duration * 100 / compensated_ratio - duration;
 
-	if (should_skip)
-		goto balance;
-
-	play_idle(jiffies_to_usecs(w_data->duration_jiffies));
-
-balance:
-	if (clamping && w_data->clamping && cpu_online(w_data->cpu))
-		kthread_queue_work(w_data->worker, &w_data->balancing_work);
+	return runtime;
 }
 
 /*
@@ -452,126 +545,129 @@ static void poll_pkg_cstate(struct work_struct *dummy)
 	msr_last = msr_now;
 	tsc_last = tsc_now;
 
-	if (true == clamping)
+	mutex_lock(&powerclamp_lock);
+	if (powerclamp_data.clamping)
 		schedule_delayed_work(&poll_pkg_cstate_work, HZ);
+	mutex_unlock(&powerclamp_lock);
 }
 
-static void start_power_clamp_worker(unsigned long cpu)
+static struct idle_inject_device *ii_dev;
+
+/*
+ * This function is called from idle injection core on timer expiry
+ * for the run duration. This allows powerclamp to readjust or skip
+ * injecting idle for this cycle.
+ */
+static bool idle_inject_update(void)
 {
-	struct powerclamp_worker_data *w_data = per_cpu_ptr(worker_data, cpu);
-	struct kthread_worker *worker;
+	bool update = false;
 
-	worker = kthread_create_worker_on_cpu(cpu, 0, "kidle_inj/%ld", cpu);
-	if (IS_ERR(worker))
-		return;
+	/* We can't sleep in this callback */
+	if (!mutex_trylock(&powerclamp_lock))
+		return true;
 
-	w_data->worker = worker;
-	w_data->count = 0;
-	w_data->cpu = cpu;
-	w_data->clamping = true;
-	set_bit(cpu, cpu_clamping_mask);
-	sched_set_fifo(worker->task);
-	kthread_init_work(&w_data->balancing_work, clamp_balancing_func);
-	kthread_init_delayed_work(&w_data->idle_injection_work,
-				  clamp_idle_injection_func);
-	kthread_queue_work(w_data->worker, &w_data->balancing_work);
-}
+	if (!(powerclamp_data.count % powerclamp_data.window_size_now)) {
 
-static void stop_power_clamp_worker(unsigned long cpu)
-{
-	struct powerclamp_worker_data *w_data = per_cpu_ptr(worker_data, cpu);
+		should_skip = powerclamp_adjust_controls(powerclamp_data.target_ratio,
+							 powerclamp_data.guard,
+							 powerclamp_data.window_size_now);
+		update = true;
+	}
 
-	if (!w_data->worker)
-		return;
+	if (update) {
+		unsigned int runtime = get_run_time();
 
-	w_data->clamping = false;
-	/*
-	 * Make sure that all works that get queued after this point see
-	 * the clamping disabled. The counter part is not needed because
-	 * there is an implicit memory barrier when the queued work
-	 * is proceed.
-	 */
-	smp_wmb();
-	kthread_cancel_work_sync(&w_data->balancing_work);
-	kthread_cancel_delayed_work_sync(&w_data->idle_injection_work);
-	/*
-	 * The balancing work still might be queued here because
-	 * the handling of the "clapming" variable, cancel, and queue
-	 * operations are not synchronized via a lock. But it is not
-	 * a big deal. The balancing work is fast and destroy kthread
-	 * will wait for it.
-	 */
-	clear_bit(w_data->cpu, cpu_clamping_mask);
-	kthread_destroy_worker(w_data->worker);
+		idle_inject_set_duration(ii_dev, runtime, duration);
+	}
+
+	powerclamp_data.count++;
+
+	mutex_unlock(&powerclamp_lock);
+
+	if (should_skip)
+		return false;
 
-	w_data->worker = NULL;
+	return true;
 }
 
-static int start_power_clamp(void)
+/* This function starts idle injection by calling idle_inject_start() */
+static void trigger_idle_injection(void)
 {
-	unsigned long cpu;
-
-	set_target_ratio = clamp(set_target_ratio, 0U, MAX_TARGET_RATIO - 1);
-	/* prevent cpu hotplug */
-	cpus_read_lock();
+	unsigned int runtime = get_run_time();
 
-	/* prefer BSP */
-	control_cpu = cpumask_first(cpu_online_mask);
+	idle_inject_set_duration(ii_dev, runtime, duration);
+	idle_inject_start(ii_dev);
+	powerclamp_data.clamping = true;
+}
 
-	clamping = true;
-	schedule_delayed_work(&poll_pkg_cstate_work, 0);
+/*
+ * This function is called from start_power_clamp() to register
+ * CPUS with powercap idle injection register and set default
+ * idle duration and latency.
+ */
+static int powerclamp_idle_injection_register(void)
+{
+	poll_pkg_cstate_enable = false;
+	if (cpumask_equal(cpu_present_mask, idle_injection_cpu_mask)) {
+		ii_dev = idle_inject_register_full(idle_injection_cpu_mask, idle_inject_update);
+		if (topology_max_packages() == 1 && topology_max_die_per_package() == 1)
+			poll_pkg_cstate_enable = true;
+	} else {
+		ii_dev = idle_inject_register(idle_injection_cpu_mask);
+	}
 
-	/* start one kthread worker per online cpu */
-	for_each_online_cpu(cpu) {
-		start_power_clamp_worker(cpu);
+	if (!ii_dev) {
+		pr_err("powerclamp: idle_inject_register failed\n");
+		return -EAGAIN;
 	}
-	cpus_read_unlock();
+
+	idle_inject_set_duration(ii_dev, TICK_USEC, duration);
+	idle_inject_set_latency(ii_dev, UINT_MAX);
 
 	return 0;
 }
 
-static void end_power_clamp(void)
+/*
+ * This function is called from end_power_clamp() to stop idle injection
+ * and unregister CPUS from powercap idle injection core.
+ */
+static void remove_idle_injection(void)
 {
-	int i;
+	if (!powerclamp_data.clamping)
+		return;
 
-	/*
-	 * Block requeuing in all the kthread workers. They will flush and
-	 * stop faster.
-	 */
-	clamping = false;
-	for_each_set_bit(i, cpu_clamping_mask, num_possible_cpus()) {
-		pr_debug("clamping worker for cpu %d alive, destroy\n", i);
-		stop_power_clamp_worker(i);
-	}
+	powerclamp_data.clamping = false;
+	idle_inject_stop(ii_dev);
 }
 
-static int powerclamp_cpu_online(unsigned int cpu)
+/*
+ * This function is called when user change the cooling device
+ * state from zero to some other value.
+ */
+static int start_power_clamp(void)
 {
-	if (clamping == false)
-		return 0;
-	start_power_clamp_worker(cpu);
-	/* prefer BSP as controlling CPU */
-	if (cpu == 0) {
-		control_cpu = 0;
-		smp_mb();
+	int ret;
+
+	ret = powerclamp_idle_injection_register();
+	if (!ret) {
+		trigger_idle_injection();
+		if (poll_pkg_cstate_enable)
+			schedule_delayed_work(&poll_pkg_cstate_work, 0);
 	}
-	return 0;
+
+	return ret;
 }
 
-static int powerclamp_cpu_predown(unsigned int cpu)
+/*
+ * This function is called when user change the cooling device
+ * state from non zero value zero.
+ */
+static void end_power_clamp(void)
 {
-	if (clamping == false)
-		return 0;
-
-	stop_power_clamp_worker(cpu);
-	if (cpu != control_cpu)
-		return 0;
-
-	control_cpu = cpumask_first(cpu_online_mask);
-	if (control_cpu == cpu)
-		control_cpu = cpumask_next(cpu, cpu_online_mask);
-	smp_mb();
-	return 0;
+	if (powerclamp_data.clamping) {
+		remove_idle_injection();
+		idle_inject_unregister(ii_dev);
+	}
 }
 
 static int powerclamp_get_max_state(struct thermal_cooling_device *cdev,
@@ -585,11 +681,9 @@ static int powerclamp_get_max_state(struct thermal_cooling_device *cdev,
 static int powerclamp_get_cur_state(struct thermal_cooling_device *cdev,
 				 unsigned long *state)
 {
-	if (true == clamping)
-		*state = pkg_cstate_ratio_cur;
-	else
-		/* to save power, do not poll idle ratio while not clamping */
-		*state = -1; /* indicates invalid state */
+	mutex_lock(&powerclamp_lock);
+	*state = powerclamp_data.target_ratio;
+	mutex_unlock(&powerclamp_lock);
 
 	return 0;
 }
@@ -599,24 +693,32 @@ static int powerclamp_set_cur_state(struct thermal_cooling_device *cdev,
 {
 	int ret = 0;
 
+	mutex_lock(&powerclamp_lock);
+
 	new_target_ratio = clamp(new_target_ratio, 0UL,
-				(unsigned long) (MAX_TARGET_RATIO-1));
-	if (set_target_ratio == 0 && new_target_ratio > 0) {
+				(unsigned long) (max_idle - 1));
+	if (!powerclamp_data.target_ratio && new_target_ratio > 0) {
 		pr_info("Start idle injection to reduce power\n");
-		set_target_ratio = new_target_ratio;
+		powerclamp_data.target_ratio = new_target_ratio;
 		ret = start_power_clamp();
+		if (ret)
+			powerclamp_data.target_ratio = 0;
 		goto exit_set;
-	} else	if (set_target_ratio > 0 && new_target_ratio == 0) {
+	} else	if (powerclamp_data.target_ratio > 0 && new_target_ratio == 0) {
 		pr_info("Stop forced idle injection\n");
 		end_power_clamp();
-		set_target_ratio = 0;
+		powerclamp_data.target_ratio = 0;
 	} else	/* adjust currently running */ {
-		set_target_ratio = new_target_ratio;
-		/* make new set_target_ratio visible to other cpus */
-		smp_mb();
+		unsigned int runtime;
+
+		powerclamp_data.target_ratio = new_target_ratio;
+		runtime = get_run_time();
+		idle_inject_set_duration(ii_dev, runtime, duration);
 	}
 
 exit_set:
+	mutex_unlock(&powerclamp_lock);
+
 	return ret;
 }
 
@@ -657,7 +759,6 @@ static int powerclamp_debug_show(struct seq_file *m, void *unused)
 {
 	int i = 0;
 
-	seq_printf(m, "controlling cpu: %d\n", control_cpu);
 	seq_printf(m, "pct confidence steady dynamic (compensation)\n");
 	for (i = 0; i < MAX_TARGET_RATIO; i++) {
 		seq_printf(m, "%d\t%lu\t%lu\t%lu\n",
@@ -680,75 +781,57 @@ static inline void powerclamp_create_debug_files(void)
 			    &powerclamp_debug_fops);
 }
 
-static enum cpuhp_state hp_state;
-
 static int __init powerclamp_init(void)
 {
 	int retval;
 
-	cpu_clamping_mask = bitmap_zalloc(num_possible_cpus(), GFP_KERNEL);
-	if (!cpu_clamping_mask)
-		return -ENOMEM;
-
 	/* probe cpu features and ids here */
 	retval = powerclamp_probe();
 	if (retval)
-		goto exit_free;
+		return retval;
+
+	mutex_lock(&powerclamp_lock);
+	retval = allocate_copy_idle_injection_mask(cpu_present_mask);
+	mutex_unlock(&powerclamp_lock);
+
+	if (retval)
+		return retval;
 
 	/* set default limit, maybe adjusted during runtime based on feedback */
 	window_size = 2;
-	retval = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-					   "thermal/intel_powerclamp:online",
-					   powerclamp_cpu_online,
-					   powerclamp_cpu_predown);
-	if (retval < 0)
-		goto exit_free;
-
-	hp_state = retval;
-
-	worker_data = alloc_percpu(struct powerclamp_worker_data);
-	if (!worker_data) {
-		retval = -ENOMEM;
-		goto exit_unregister;
-	}
 
 	cooling_dev = thermal_cooling_device_register("intel_powerclamp", NULL,
-						&powerclamp_cooling_ops);
-	if (IS_ERR(cooling_dev)) {
-		retval = -ENODEV;
-		goto exit_free_thread;
-	}
+						      &powerclamp_cooling_ops);
+	if (IS_ERR(cooling_dev))
+		return -ENODEV;
 
 	if (!duration)
-		duration = jiffies_to_msecs(DEFAULT_DURATION_JIFFIES);
+		duration = jiffies_to_usecs(DEFAULT_DURATION_JIFFIES);
 
 	powerclamp_create_debug_files();
 
 	return 0;
-
-exit_free_thread:
-	free_percpu(worker_data);
-exit_unregister:
-	cpuhp_remove_state_nocalls(hp_state);
-exit_free:
-	bitmap_free(cpu_clamping_mask);
-	return retval;
 }
 module_init(powerclamp_init);
 
 static void __exit powerclamp_exit(void)
 {
+	mutex_lock(&powerclamp_lock);
 	end_power_clamp();
-	cpuhp_remove_state_nocalls(hp_state);
-	free_percpu(worker_data);
+	mutex_unlock(&powerclamp_lock);
+
 	thermal_cooling_device_unregister(cooling_dev);
-	bitmap_free(cpu_clamping_mask);
 
 	cancel_delayed_work_sync(&poll_pkg_cstate_work);
 	debugfs_remove_recursive(debug_dir);
+
+	if (cpumask_available(idle_injection_cpu_mask))
+		free_cpumask_var(idle_injection_cpu_mask);
 }
 module_exit(powerclamp_exit);
 
+MODULE_IMPORT_NS(IDLE_INJECT);
+
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>");
 MODULE_AUTHOR("Jacob Pan <jacob.jun.pan@linux.intel.com>");
diff --git a/drivers/thermal/intel/intel_quark_dts_thermal.c b/drivers/thermal/intel/intel_quark_dts_thermal.c
index 3eafc6b0e6c3..97b843fa7568 100644
--- a/drivers/thermal/intel/intel_quark_dts_thermal.c
+++ b/drivers/thermal/intel/intel_quark_dts_thermal.c
@@ -84,6 +84,7 @@
 #define QRK_DTS_MASK_TP_THRES		0xFF
 #define QRK_DTS_SHIFT_TP		8
 #define QRK_DTS_ID_TP_CRITICAL		0
+#define QRK_DTS_ID_TP_HOT		1
 #define QRK_DTS_SAFE_TP_THRES		105
 
 /* Thermal Sensor Register Lock */
@@ -104,6 +105,7 @@ struct soc_sensor_entry {
 	u32 store_ptps;
 	u32 store_dts_enable;
 	struct thermal_zone_device *tzone;
+	struct thermal_trip trips[QRK_MAX_DTS_TRIPS];
 };
 
 static struct soc_sensor_entry *soc_dts;
@@ -172,9 +174,9 @@ static int soc_dts_disable(struct thermal_zone_device *tzd)
 	return ret;
 }
 
-static int _get_trip_temp(int trip, int *temp)
+static int get_trip_temp(int trip)
 {
-	int status;
+	int status, temp;
 	u32 out;
 
 	mutex_lock(&dts_update_mutex);
@@ -183,7 +185,7 @@ static int _get_trip_temp(int trip, int *temp)
 	mutex_unlock(&dts_update_mutex);
 
 	if (status)
-		return status;
+		return THERMAL_TEMP_INVALID;
 
 	/*
 	 * Thermal Sensor Programmable Trip Point Register has 8-bit
@@ -191,21 +193,10 @@ static int _get_trip_temp(int trip, int *temp)
 	 * thresholds. The threshold value is always offset by its
 	 * temperature base (50 degree Celsius).
 	 */
-	*temp = (out >> (trip * QRK_DTS_SHIFT_TP)) & QRK_DTS_MASK_TP_THRES;
-	*temp -= QRK_DTS_TEMP_BASE;
+	temp = (out >> (trip * QRK_DTS_SHIFT_TP)) & QRK_DTS_MASK_TP_THRES;
+	temp -= QRK_DTS_TEMP_BASE;
 
-	return 0;
-}
-
-static inline int sys_get_trip_temp(struct thermal_zone_device *tzd,
-				int trip, int *temp)
-{
-	return _get_trip_temp(trip, temp);
-}
-
-static inline int sys_get_crit_temp(struct thermal_zone_device *tzd, int *temp)
-{
-	return _get_trip_temp(QRK_DTS_ID_TP_CRITICAL, temp);
+	return temp;
 }
 
 static int update_trip_temp(struct soc_sensor_entry *aux_entry,
@@ -262,17 +253,6 @@ static inline int sys_set_trip_temp(struct thermal_zone_device *tzd, int trip,
 	return update_trip_temp(tzd->devdata, trip, temp);
 }
 
-static int sys_get_trip_type(struct thermal_zone_device *thermal,
-		int trip, enum thermal_trip_type *type)
-{
-	if (trip)
-		*type = THERMAL_TRIP_HOT;
-	else
-		*type = THERMAL_TRIP_CRITICAL;
-
-	return 0;
-}
-
 static int sys_get_curr_temp(struct thermal_zone_device *tzd,
 				int *temp)
 {
@@ -315,10 +295,7 @@ static int sys_change_mode(struct thermal_zone_device *tzd,
 
 static struct thermal_zone_device_ops tzone_ops = {
 	.get_temp = sys_get_curr_temp,
-	.get_trip_temp = sys_get_trip_temp,
-	.get_trip_type = sys_get_trip_type,
 	.set_trip_temp = sys_set_trip_temp,
-	.get_crit_temp = sys_get_crit_temp,
 	.change_mode = sys_change_mode,
 };
 
@@ -385,10 +362,18 @@ static struct soc_sensor_entry *alloc_soc_dts(void)
 			goto err_ret;
 	}
 
-	aux_entry->tzone = thermal_zone_device_register("quark_dts",
-			QRK_MAX_DTS_TRIPS,
-			wr_mask,
-			aux_entry, &tzone_ops, NULL, 0, polling_delay);
+	aux_entry->trips[QRK_DTS_ID_TP_CRITICAL].temperature = get_trip_temp(QRK_DTS_ID_TP_CRITICAL);
+	aux_entry->trips[QRK_DTS_ID_TP_CRITICAL].type = THERMAL_TRIP_CRITICAL;
+
+	aux_entry->trips[QRK_DTS_ID_TP_HOT].temperature = get_trip_temp(QRK_DTS_ID_TP_HOT);
+	aux_entry->trips[QRK_DTS_ID_TP_HOT].type = THERMAL_TRIP_HOT;
+
+	aux_entry->tzone = thermal_zone_device_register_with_trips("quark_dts",
+								   aux_entry->trips,
+								   QRK_MAX_DTS_TRIPS,
+								   wr_mask,
+								   aux_entry, &tzone_ops,
+								   NULL, 0, polling_delay);
 	if (IS_ERR(aux_entry->tzone)) {
 		err = PTR_ERR(aux_entry->tzone);
 		goto err_ret;
diff --git a/drivers/thermal/thermal_acpi.c b/drivers/thermal/thermal_acpi.c
index 671f774a7621..0e5698818f69 100644
--- a/drivers/thermal/thermal_acpi.c
+++ b/drivers/thermal/thermal_acpi.c
@@ -21,42 +21,11 @@
 #define TEMP_MIN_DECIK	2180
 #define TEMP_MAX_DECIK	4480
 
-static int thermal_acpi_trip_init(struct acpi_device *adev,
-				  enum thermal_trip_type type, int id,
-				  struct thermal_trip *trip)
+static int thermal_acpi_trip_temp(struct acpi_device *adev, char *obj_name,
+				  int *ret_temp)
 {
 	unsigned long long temp;
 	acpi_status status;
-	char obj_name[5];
-
-	switch (type) {
-	case THERMAL_TRIP_ACTIVE:
-		if (id < 0 || id > 9)
-			return -EINVAL;
-
-		obj_name[1] = 'A';
-		obj_name[2] = 'C';
-		obj_name[3] = '0' + id;
-		break;
-	case THERMAL_TRIP_PASSIVE:
-		obj_name[1] = 'P';
-		obj_name[2] = 'S';
-		obj_name[3] = 'V';
-		break;
-	case THERMAL_TRIP_HOT:
-		obj_name[1] = 'H';
-		obj_name[2] = 'O';
-		obj_name[3] = 'T';
-		break;
-	case THERMAL_TRIP_CRITICAL:
-		obj_name[1] = 'C';
-		obj_name[2] = 'R';
-		obj_name[3] = 'T';
-		break;
-	}
-
-	obj_name[0] = '_';
-	obj_name[4] = '\0';
 
 	status = acpi_evaluate_integer(adev->handle, obj_name, NULL, &temp);
 	if (ACPI_FAILURE(status)) {
@@ -65,87 +34,84 @@ static int thermal_acpi_trip_init(struct acpi_device *adev,
 	}
 
 	if (temp >= TEMP_MIN_DECIK && temp <= TEMP_MAX_DECIK) {
-		trip->temperature = deci_kelvin_to_millicelsius(temp);
+		*ret_temp = deci_kelvin_to_millicelsius(temp);
 	} else {
 		acpi_handle_debug(adev->handle, "%s result %llu out of range\n",
 				  obj_name, temp);
-		trip->temperature = THERMAL_TEMP_INVALID;
+		*ret_temp = THERMAL_TEMP_INVALID;
 	}
 
-	trip->hysteresis = 0;
-	trip->type = type;
-
 	return 0;
 }
 
 /**
- * thermal_acpi_trip_active - Get the specified active trip point
- * @adev: Thermal zone ACPI device object to get the description from.
+ * thermal_acpi_active_trip_temp - Retrieve active trip point temperature
+ * @adev: Target thermal zone ACPI device object.
  * @id: Active cooling level (0 - 9).
- * @trip: Trip point structure to be populated on success.
+ * @ret_temp: Address to store the retrieved temperature value on success.
  *
  * Evaluate the _ACx object for the thermal zone represented by @adev to obtain
  * the temperature of the active cooling trip point corresponding to the active
- * cooling level given by @id and initialize @trip as an active trip point using
- * that temperature value.
+ * cooling level given by @id.
  *
  * Return 0 on success or a negative error value on failure.
  */
-int thermal_acpi_trip_active(struct acpi_device *adev, int id,
-			     struct thermal_trip *trip)
+int thermal_acpi_active_trip_temp(struct acpi_device *adev, int id, int *ret_temp)
 {
-	return thermal_acpi_trip_init(adev, THERMAL_TRIP_ACTIVE, id, trip);
+	char obj_name[] = {'_', 'A', 'C', '0' + id, '\0'};
+
+	if (id < 0 || id > 9)
+		return -EINVAL;
+
+	return thermal_acpi_trip_temp(adev, obj_name, ret_temp);
 }
-EXPORT_SYMBOL_GPL(thermal_acpi_trip_active);
+EXPORT_SYMBOL_GPL(thermal_acpi_active_trip_temp);
 
 /**
- * thermal_acpi_trip_passive - Get the passive trip point
- * @adev: Thermal zone ACPI device object to get the description from.
- * @trip: Trip point structure to be populated on success.
+ * thermal_acpi_passive_trip_temp - Retrieve passive trip point temperature
+ * @adev: Target thermal zone ACPI device object.
+ * @ret_temp: Address to store the retrieved temperature value on success.
  *
  * Evaluate the _PSV object for the thermal zone represented by @adev to obtain
- * the temperature of the passive cooling trip point and initialize @trip as a
- * passive trip point using that temperature value.
+ * the temperature of the passive cooling trip point.
  *
  * Return 0 on success or -ENODATA on failure.
  */
-int thermal_acpi_trip_passive(struct acpi_device *adev, struct thermal_trip *trip)
+int thermal_acpi_passive_trip_temp(struct acpi_device *adev, int *ret_temp)
 {
-	return thermal_acpi_trip_init(adev, THERMAL_TRIP_PASSIVE, INT_MAX, trip);
+	return thermal_acpi_trip_temp(adev, "_PSV", ret_temp);
 }
-EXPORT_SYMBOL_GPL(thermal_acpi_trip_passive);
+EXPORT_SYMBOL_GPL(thermal_acpi_passive_trip_temp);
 
 /**
- * thermal_acpi_trip_hot - Get the near critical trip point
- * @adev: the ACPI device to get the description from.
- * @trip: a &struct thermal_trip to be filled if the function succeed.
+ * thermal_acpi_hot_trip_temp - Retrieve hot trip point temperature
+ * @adev: Target thermal zone ACPI device object.
+ * @ret_temp: Address to store the retrieved temperature value on success.
  *
  * Evaluate the _HOT object for the thermal zone represented by @adev to obtain
  * the temperature of the trip point at which the system is expected to be put
- * into the S4 sleep state and initialize @trip as a hot trip point using that
- * temperature value.
+ * into the S4 sleep state.
  *
  * Return 0 on success or -ENODATA on failure.
  */
-int thermal_acpi_trip_hot(struct acpi_device *adev, struct thermal_trip *trip)
+int thermal_acpi_hot_trip_temp(struct acpi_device *adev, int *ret_temp)
 {
-	return thermal_acpi_trip_init(adev, THERMAL_TRIP_HOT, INT_MAX, trip);
+	return thermal_acpi_trip_temp(adev, "_HOT", ret_temp);
 }
-EXPORT_SYMBOL_GPL(thermal_acpi_trip_hot);
+EXPORT_SYMBOL_GPL(thermal_acpi_hot_trip_temp);
 
 /**
- * thermal_acpi_trip_critical - Get the critical trip point
- * @adev: the ACPI device to get the description from.
- * @trip: a &struct thermal_trip to be filled if the function succeed.
+ * thermal_acpi_critical_trip_temp - Retrieve critical trip point temperature
+ * @adev: Target thermal zone ACPI device object.
+ * @ret_temp: Address to store the retrieved temperature value on success.
  *
  * Evaluate the _CRT object for the thermal zone represented by @adev to obtain
- * the temperature of the critical cooling trip point and initialize @trip as a
- * critical trip point using that temperature value.
+ * the temperature of the critical cooling trip point.
  *
  * Return 0 on success or -ENODATA on failure.
  */
-int thermal_acpi_trip_critical(struct acpi_device *adev, struct thermal_trip *trip)
+int thermal_acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp)
 {
-	return thermal_acpi_trip_init(adev, THERMAL_TRIP_CRITICAL, INT_MAX, trip);
+	return thermal_acpi_trip_temp(adev, "_CRT", ret_temp);
 }
-EXPORT_SYMBOL_GPL(thermal_acpi_trip_critical);
+EXPORT_SYMBOL_GPL(thermal_acpi_critical_trip_temp);