Merge branches 'powercap' and 'pm-devfreq'

Merge devfreq changes and a new CPU idle time injection framework
for 4.19.

* powercap:
  powercap / idle_inject: Add an idle injection framework

* pm-devfreq:
  PM / devfreq: rk3399_dmc: Fix duplicated opp table on reload.
  PM / devfreq: Init user limits from OPP limits, not viceversa
  PM / devfreq: rk3399_dmc: fix spelling mistakes.
  PM / devfreq: rk3399_dmc: do not print error when get supply and clk defer.
  dt-bindings: devfreq: rk3399_dmc: move interrupts to be optional.
  PM / devfreq: rk3399_dmc: remove wait for dcf irq event.
  dt-bindings: clock: add rk3399 DDR3 standard speed bins.
  dt-bindings: devfreq: rk3399_dmc: improve binding documentation.
  PM / devfreq: use put_device() instead of kfree()
  PM / devfreq: exynos-ppmu: Delete an error message for a failed memory allocation in exynos_ppmu_probe()

Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt

-* Rockchip rk3399 DMC(Dynamic Memory Controller) device
+* Rockchip rk3399 DMC (Dynamic Memory Controller) device
 
 Required properties:
 - compatible:		 Must be "rockchip,rk3399-dmc".
 - devfreq-events:	 Node to get DDR loading, Refer to
-			 Documentation/devicetree/bindings/devfreq/
+			 Documentation/devicetree/bindings/devfreq/event/
 			 rockchip-dfi.txt
-- interrupts:		 The interrupt number to the CPU. The interrupt
-			 specifier format depends on the interrupt controller.
-			 It should be DCF interrupts, when DDR dvfs finish,
-			 it will happen.
 - clocks:		 Phandles for clock specified in "clock-names" property
 - clock-names :		 The name of clock used by the DFI, must be
 			 "pclk_ddr_mon";
@@ -17,139 +13,148 @@ Required properties:
 - center-supply:	 DMC supply node.
 - status:		 Marks the node enabled/disabled.
 
-Following properties are ddr timing:
-
-- rockchip,dram_speed_bin :	  Value reference include/dt-bindings/clock/ddr.h,
-				  it select ddr3 cl-trp-trcd type, default value
-				  "DDR3_DEFAULT".it must selected according to
-				  "Speed Bin" in ddr3 datasheet, DO NOT use
-				  smaller "Speed Bin" than ddr3 exactly is.
-
-- rockchip,pd_idle :		  Config the PD_IDLE value, defined the power-down
-				  idle period, memories are places into power-down
-				  mode if bus is idle for PD_IDLE DFI clocks.
-
-- rockchip,sr_idle :		  Configure the SR_IDLE value, defined the
-				  selfrefresh idle period, memories are places
-				  into self-refresh mode if bus is idle for
-				  SR_IDLE*1024 DFI clocks (DFI clocks freq is
-				  half of dram's clocks), defaule value is "0".
-
-- rockchip,sr_mc_gate_idle :	  Defined the self-refresh with memory and
-				  controller clock gating idle period, memories
-				  are places into self-refresh mode and memory
-				  controller clock arg gating if bus is idle for
-				  sr_mc_gate_idle*1024 DFI clocks.
-
-- rockchip,srpd_lite_idle :	  Defined the self-refresh power down idle
-				  period, memories are places into self-refresh
-				  power down mode if bus is idle for
-				  srpd_lite_idle*1024 DFI clocks. This parameter
-				  is for LPDDR4 only.
-
-- rockchip,standby_idle :	  Defined the standby idle period, memories are
-				  places into self-refresh than controller, pi,
-				  phy and dram clock will gating if bus is idle
-				  for standby_idle * DFI clocks.
-
-- rockchip,dram_dll_disb_freq :  It's defined the DDR3 dll bypass frequency in
-				  MHz, when ddr freq less than DRAM_DLL_DISB_FREQ,
-				  ddr3 dll will bypssed note: if dll was bypassed,
-				  the odt also stop working.
-
-- rockchip,phy_dll_disb_freq :	  Defined the PHY dll bypass frequency in
-				  MHz (Mega Hz), when ddr freq less than
-				  DRAM_DLL_DISB_FREQ, phy dll will bypssed.
-				  note: phy dll and phy odt are independent.
-
-- rockchip,ddr3_odt_disb_freq :  When dram type is DDR3, this parameter defined
-				  the odt disable frequency in MHz (Mega Hz),
-				  when ddr frequency less then ddr3_odt_disb_freq,
-				  the odt on dram side and controller side are
+Optional properties:
+- interrupts:		 The CPU interrupt number. The interrupt specifier
+			 format depends on the interrupt controller.
+			 It should be a DCF interrupt. When DDR DVFS finishes
+			 a DCF interrupt is triggered.
+
+Following properties relate to DDR timing:
+
+- rockchip,dram_speed_bin :	  Value reference include/dt-bindings/clock/rk3399-ddr.h,
+				  it selects the DDR3 cl-trp-trcd type. It must be
+				  set according to "Speed Bin" in DDR3 datasheet,
+				  DO NOT use a smaller "Speed Bin" than specified
+				  for the DDR3 being used.
+
+- rockchip,pd_idle :		  Configure the PD_IDLE value. Defines the
+				  power-down idle period in which memories are
+				  placed into power-down mode if bus is idle
+				  for PD_IDLE DFI clock cycles.
+
+- rockchip,sr_idle :		  Configure the SR_IDLE value. Defines the
+				  self-refresh idle period in which memories are
+				  placed into self-refresh mode if bus is idle
+				  for SR_IDLE * 1024 DFI clock cycles (DFI
+				  clocks freq is half of DRAM clock), default
+				  value is "0".
+
+- rockchip,sr_mc_gate_idle :	  Defines the memory self-refresh and controller
+				  clock gating idle period. Memories are placed
+				  into self-refresh mode and memory controller
+				  clock arg gating started if bus is idle for
+				  sr_mc_gate_idle*1024 DFI clock cycles.
+
+- rockchip,srpd_lite_idle :	  Defines the self-refresh power down idle
+				  period in which memories are placed into
+				  self-refresh power down mode if bus is idle
+				  for srpd_lite_idle * 1024 DFI clock cycles.
+				  This parameter is for LPDDR4 only.
+
+- rockchip,standby_idle :	  Defines the standby idle period in which
+				  memories are placed into self-refresh mode.
+				  The controller, pi, PHY and DRAM clock will
+				  be gated if bus is idle for standby_idle * DFI
+				  clock cycles.
+
+- rockchip,dram_dll_dis_freq :	  Defines the DDR3 DLL bypass frequency in MHz.
+				  When DDR frequency is less than DRAM_DLL_DISB_FREQ,
+				  DDR3 DLL will be bypassed. Note: if DLL was bypassed,
+				  the odt will also stop working.
+
+- rockchip,phy_dll_dis_freq :	  Defines the PHY dll bypass frequency in
+				  MHz (Mega Hz). When DDR frequency is less than
+				  DRAM_DLL_DISB_FREQ, PHY DLL will be bypassed.
+				  Note: PHY DLL and PHY ODT are independent.
+
+- rockchip,ddr3_odt_dis_freq :	  When the DRAM type is DDR3, this parameter defines
+				  the ODT disable frequency in MHz (Mega Hz).
+				  when the DDR frequency is  less then ddr3_odt_dis_freq,
+				  the ODT on the DRAM side and controller side are
 				  both disabled.
 
-- rockchip,ddr3_drv :		  When dram type is DDR3, this parameter define
-				  the dram side driver stength in ohm, default
+- rockchip,ddr3_drv :		  When the DRAM type is DDR3, this parameter defines
+				  the DRAM side driver strength in ohms. Default
 				  value is DDR3_DS_40ohm.
 
-- rockchip,ddr3_odt :		  When dram type is DDR3, this parameter define
-				  the dram side ODT stength in ohm, default value
+- rockchip,ddr3_odt :		  When the DRAM type is DDR3, this parameter defines
+				  the DRAM side ODT strength in ohms. Default value
 				  is DDR3_ODT_120ohm.
 
-- rockchip,phy_ddr3_ca_drv :	  When dram type is DDR3, this parameter define
-				  the phy side CA line(incluing command line,
+- rockchip,phy_ddr3_ca_drv :	  When the DRAM type is DDR3, this parameter defines
+				  the phy side CA line (incluing command line,
 				  address line and clock line) driver strength.
 				  Default value is PHY_DRV_ODT_40.
 
-- rockchip,phy_ddr3_dq_drv :	  When dram type is DDR3, this parameter define
-				  the phy side DQ line(incluing DQS/DQ/DM line)
-				  driver strength. default value is PHY_DRV_ODT_40.
+- rockchip,phy_ddr3_dq_drv :	  When the DRAM type is DDR3, this parameter defines
+				  the PHY side DQ line (including DQS/DQ/DM line)
+				  driver strength. Default value is PHY_DRV_ODT_40.
 
-- rockchip,phy_ddr3_odt : 	  When dram type is DDR3, this parameter define the
-				  phy side odt strength, default value is
+- rockchip,phy_ddr3_odt : 	  When the DRAM type is DDR3, this parameter defines
+				  the PHY side ODT strength. Default value is
 				  PHY_DRV_ODT_240.
 
-- rockchip,lpddr3_odt_disb_freq : When dram type is LPDDR3, this parameter defined
-				  then odt disable frequency in MHz (Mega Hz),
-				  when ddr frequency less then ddr3_odt_disb_freq,
-				  the odt on dram side and controller side are
+- rockchip,lpddr3_odt_dis_freq : When the DRAM type is LPDDR3, this parameter defines
+				  then ODT disable frequency in MHz (Mega Hz).
+				  When DDR frequency is less then ddr3_odt_dis_freq,
+				  the ODT on the DRAM side and controller side are
 				  both disabled.
 
-- rockchip,lpddr3_drv :	  When dram type is LPDDR3, this parameter define
-				  the dram side driver stength in ohm, default
+- rockchip,lpddr3_drv :		  When the DRAM type is LPDDR3, this parameter defines
+				  the DRAM side driver strength in ohms. Default
 				  value is LP3_DS_34ohm.
 
-- rockchip,lpddr3_odt :	  When dram type is LPDDR3, this parameter define
-				  the dram side ODT stength in ohm, default value
+- rockchip,lpddr3_odt :		  When the DRAM type is LPDDR3, this parameter defines
+				  the DRAM side ODT strength in ohms. Default value
 				  is LP3_ODT_240ohm.
 
-- rockchip,phy_lpddr3_ca_drv :	  When dram type is LPDDR3, this parameter define
-				  the phy side CA line(incluing command line,
+- rockchip,phy_lpddr3_ca_drv :	  When the DRAM type is LPDDR3, this parameter defines
+				  the PHY side CA line (including command line,
 				  address line and clock line) driver strength.
-				  default value is PHY_DRV_ODT_40.
+				  Default value is PHY_DRV_ODT_40.
 
-- rockchip,phy_lpddr3_dq_drv :	  When dram type is LPDDR3, this parameter define
-				  the phy side DQ line(incluing DQS/DQ/DM line)
-				  driver strength. default value is
+- rockchip,phy_lpddr3_dq_drv :	  When the DRAM type is LPDDR3, this parameter defines
+				  the PHY side DQ line (including DQS/DQ/DM line)
+				  driver strength. Default value is
 				  PHY_DRV_ODT_40.
 
 - rockchip,phy_lpddr3_odt : 	  When dram type is LPDDR3, this parameter define
 				  the phy side odt strength, default value is
 				  PHY_DRV_ODT_240.
 
-- rockchip,lpddr4_odt_disb_freq : When dram type is LPDDR4, this parameter
-				  defined the odt disable frequency in
-				  MHz (Mega Hz), when ddr frequency less then
-				  ddr3_odt_disb_freq, the odt on dram side and
+- rockchip,lpddr4_odt_dis_freq : When the DRAM type is LPDDR4, this parameter
+				  defines the ODT disable frequency in
+				  MHz (Mega Hz). When the DDR frequency is less then
+				  ddr3_odt_dis_freq, the ODT on the DRAM side and
 				  controller side are both disabled.
 
-- rockchip,lpddr4_drv :	  When dram type is LPDDR4, this parameter define
-				  the dram side driver stength in ohm, default
+- rockchip,lpddr4_drv :		  When the DRAM type is LPDDR4, this parameter defines
+				  the DRAM side driver strength in ohms. Default
 				  value is LP4_PDDS_60ohm.
 
-- rockchip,lpddr4_dq_odt : 	  When dram type is LPDDR4, this parameter define
-				  the dram side ODT on dqs/dq line stength in ohm,
-				  default value is LP4_DQ_ODT_40ohm.
+- rockchip,lpddr4_dq_odt : 	  When the DRAM type is LPDDR4, this parameter defines
+				  the DRAM side ODT on DQS/DQ line strength in ohms.
+				  Default value is LP4_DQ_ODT_40ohm.
 
-- rockchip,lpddr4_ca_odt :	  When dram type is LPDDR4, this parameter define
-				  the dram side ODT on ca line stength in ohm,
-				  default value is LP4_CA_ODT_40ohm.
+- rockchip,lpddr4_ca_odt :	  When the DRAM type is LPDDR4, this parameter defines
+				  the DRAM side ODT on CA line strength in ohms.
+				  Default value is LP4_CA_ODT_40ohm.
 
-- rockchip,phy_lpddr4_ca_drv :	  When dram type is LPDDR4, this parameter define
-				  the phy side  CA line(incluing command address
-				  line) driver strength. default value is
+- rockchip,phy_lpddr4_ca_drv :	  When the DRAM type is LPDDR4, this parameter defines
+				  the PHY side CA line (including command address
+				  line) driver strength. Default value is
 				  PHY_DRV_ODT_40.
 
-- rockchip,phy_lpddr4_ck_cs_drv : When dram type is LPDDR4, this parameter define
-				  the phy side clock line and cs line driver
-				  strength. default value is PHY_DRV_ODT_80.
+- rockchip,phy_lpddr4_ck_cs_drv : When the DRAM type is LPDDR4, this parameter defines
+				  the PHY side clock line and CS line driver
+				  strength. Default value is PHY_DRV_ODT_80.
 
-- rockchip,phy_lpddr4_dq_drv :	  When dram type is LPDDR4, this parameter define
-				  the phy side DQ line(incluing DQS/DQ/DM line)
-				  driver strength. default value is PHY_DRV_ODT_80.
+- rockchip,phy_lpddr4_dq_drv :	  When the DRAM type is LPDDR4, this parameter defines
+				  the PHY side DQ line (including DQS/DQ/DM line)
+				  driver strength. Default value is PHY_DRV_ODT_80.
 
-- rockchip,phy_lpddr4_odt :	  When dram type is LPDDR4, this parameter define
-				  the phy side odt strength, default value is
+- rockchip,phy_lpddr4_odt :	  When the DRAM type is LPDDR4, this parameter defines
+				  the PHY side ODT strength. Default value is
 				  PHY_DRV_ODT_60.
 
 Example:

drivers/devfreq/devfreq.c

@@ -604,28 +604,29 @@ struct devfreq *devfreq_add_device(struct device *dev,
 		mutex_lock(&devfreq->lock);
 	}
 
-	devfreq->min_freq = find_available_min_freq(devfreq);
-	if (!devfreq->min_freq) {
+	devfreq->scaling_min_freq = find_available_min_freq(devfreq);
+	if (!devfreq->scaling_min_freq) {
 		mutex_unlock(&devfreq->lock);
 		err = -EINVAL;
 		goto err_dev;
 	}
-	devfreq->scaling_min_freq = devfreq->min_freq;
+	devfreq->min_freq = devfreq->scaling_min_freq;
 
-	devfreq->max_freq = find_available_max_freq(devfreq);
-	if (!devfreq->max_freq) {
+	devfreq->scaling_max_freq = find_available_max_freq(devfreq);
+	if (!devfreq->scaling_max_freq) {
 		mutex_unlock(&devfreq->lock);
 		err = -EINVAL;
 		goto err_dev;
 	}
-	devfreq->scaling_max_freq = devfreq->max_freq;
+	devfreq->max_freq = devfreq->scaling_max_freq;
 
 	dev_set_name(&devfreq->dev, "devfreq%d",
 				atomic_inc_return(&devfreq_no));
 	err = device_register(&devfreq->dev);
 	if (err) {
 		mutex_unlock(&devfreq->lock);
-		goto err_dev;
+		put_device(&devfreq->dev);
+		goto err_out;
 	}
 
 	devfreq->trans_table =
@@ -672,6 +673,7 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	mutex_unlock(&devfreq_list_lock);
 
 	device_unregister(&devfreq->dev);
+	devfreq = NULL;
 err_dev:
 	if (devfreq)
 		kfree(devfreq);

drivers/devfreq/event/exynos-ppmu.c

@@ -627,11 +627,9 @@ static int exynos_ppmu_probe(struct platform_device *pdev)
 
 	size = sizeof(struct devfreq_event_dev *) * info->num_events;
 	info->edev = devm_kzalloc(&pdev->dev, size, GFP_KERNEL);
-	if (!info->edev) {
-		dev_err(&pdev->dev,
-			"failed to allocate memory devfreq-event devices\n");
+	if (!info->edev)
 		return -ENOMEM;
-	}
+
 	edev = info->edev;
 	platform_set_drvdata(pdev, info);
 

drivers/devfreq/rk3399_dmc.c

@@ -68,15 +68,6 @@ struct rk3399_dmcfreq {
 	struct devfreq_event_dev *edev;
 	struct mutex lock;
 	struct dram_timing timing;
-
-	/*
-	 * DDR Converser of Frequency (DCF) is used to implement DDR frequency
-	 * conversion without the participation of CPU, we will implement and
-	 * control it in arm trust firmware.
-	 */
-	wait_queue_head_t	wait_dcf_queue;
-	int irq;
-	int wait_dcf_flag;
 	struct regulator *vdd_center;
 	unsigned long rate, target_rate;
 	unsigned long volt, target_volt;
@@ -112,30 +103,21 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
 		err = regulator_set_voltage(dmcfreq->vdd_center, target_volt,
 					    target_volt);
 		if (err) {
-			dev_err(dev, "Cannot to set voltage %lu uV\n",
+			dev_err(dev, "Cannot set voltage %lu uV\n",
 				target_volt);
 			goto out;
 		}
 	}
-	dmcfreq->wait_dcf_flag = 1;
 
 	err = clk_set_rate(dmcfreq->dmc_clk, target_rate);
 	if (err) {
-		dev_err(dev, "Cannot to set frequency %lu (%d)\n",
-			target_rate, err);
+		dev_err(dev, "Cannot set frequency %lu (%d)\n", target_rate,
+			err);
 		regulator_set_voltage(dmcfreq->vdd_center, dmcfreq->volt,
 				      dmcfreq->volt);
 		goto out;
 	}
 
-	/*
-	 * Wait until bcf irq happen, it means freq scaling finish in
-	 * arm trust firmware, use 100ms as timeout time.
-	 */
-	if (!wait_event_timeout(dmcfreq->wait_dcf_queue,
-				!dmcfreq->wait_dcf_flag, HZ / 10))
-		dev_warn(dev, "Timeout waiting for dcf interrupt\n");
-
 	/*
 	 * Check the dpll rate,
 	 * There only two result we will get,
@@ -146,8 +128,8 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
 
 	/* If get the incorrect rate, set voltage to old value. */
 	if (dmcfreq->rate != target_rate) {
-		dev_err(dev, "Get wrong ddr frequency, Request frequency %lu,\
-			Current frequency %lu\n", target_rate, dmcfreq->rate);
+		dev_err(dev, "Got wrong frequency, Request %lu, Current %lu\n",
+			target_rate, dmcfreq->rate);
 		regulator_set_voltage(dmcfreq->vdd_center, dmcfreq->volt,
 				      dmcfreq->volt);
 		goto out;
@@ -155,7 +137,7 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
 		err = regulator_set_voltage(dmcfreq->vdd_center, target_volt,
 					    target_volt);
 	if (err)
-		dev_err(dev, "Cannot to set vol %lu uV\n", target_volt);
+		dev_err(dev, "Cannot set voltage %lu uV\n", target_volt);
 
 	dmcfreq->rate = target_rate;
 	dmcfreq->volt = target_volt;
@@ -241,22 +223,6 @@ static __maybe_unused int rk3399_dmcfreq_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(rk3399_dmcfreq_pm, rk3399_dmcfreq_suspend,
 			 rk3399_dmcfreq_resume);
 
-static irqreturn_t rk3399_dmc_irq(int irq, void *dev_id)
-{
-	struct rk3399_dmcfreq *dmcfreq = dev_id;
-	struct arm_smccc_res res;
-
-	dmcfreq->wait_dcf_flag = 0;
-	wake_up(&dmcfreq->wait_dcf_queue);
-
-	/* Clear the DCF interrupt */
-	arm_smccc_smc(ROCKCHIP_SIP_DRAM_FREQ, 0, 0,
-		      ROCKCHIP_SIP_CONFIG_DRAM_CLR_IRQ,
-		      0, 0, 0, 0, &res);
-
-	return IRQ_HANDLED;
-}
-
 static int of_get_ddr_timings(struct dram_timing *timing,
 			      struct device_node *np)
 {
@@ -330,16 +296,10 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct device_node *np = pdev->dev.of_node;
 	struct rk3399_dmcfreq *data;
-	int ret, irq, index, size;
+	int ret, index, size;
 	uint32_t *timing;
 	struct dev_pm_opp *opp;
 
-	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(&pdev->dev,
-			"Cannot get the dmc interrupt resource: %d\n", irq);
-		return irq;
-	}
 	data = devm_kzalloc(dev, sizeof(struct rk3399_dmcfreq), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
@@ -348,27 +308,22 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 
 	data->vdd_center = devm_regulator_get(dev, "center");
 	if (IS_ERR(data->vdd_center)) {
+		if (PTR_ERR(data->vdd_center) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+
 		dev_err(dev, "Cannot get the regulator \"center\"\n");
 		return PTR_ERR(data->vdd_center);
 	}
 
 	data->dmc_clk = devm_clk_get(dev, "dmc_clk");
 	if (IS_ERR(data->dmc_clk)) {
+		if (PTR_ERR(data->dmc_clk) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+
 		dev_err(dev, "Cannot get the clk dmc_clk\n");
 		return PTR_ERR(data->dmc_clk);
 	};
 
-	data->irq = irq;
-	ret = devm_request_irq(dev, irq, rk3399_dmc_irq, 0,
-			       dev_name(dev), data);
-	if (ret) {
-		dev_err(dev, "Failed to request dmc irq: %d\n", ret);
-		return ret;
-	}
-
-	init_waitqueue_head(&data->wait_dcf_queue);
-	data->wait_dcf_flag = 0;
-
 	data->edev = devfreq_event_get_edev_by_phandle(dev, 0);
 	if (IS_ERR(data->edev))
 		return -EPROBE_DEFER;
@@ -420,8 +375,10 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 	data->rate = clk_get_rate(data->dmc_clk);
 
 	opp = devfreq_recommended_opp(dev, &data->rate, 0);
-	if (IS_ERR(opp))
-		return PTR_ERR(opp);
+	if (IS_ERR(opp)) {
+		ret = PTR_ERR(opp);
+		goto err_free_opp;
+	}
 
 	data->rate = dev_pm_opp_get_freq(opp);
 	data->volt = dev_pm_opp_get_voltage(opp);
@@ -433,13 +390,33 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 					   &rk3399_devfreq_dmc_profile,
 					   DEVFREQ_GOV_SIMPLE_ONDEMAND,
 					   &data->ondemand_data);
-	if (IS_ERR(data->devfreq))
-		return PTR_ERR(data->devfreq);
+	if (IS_ERR(data->devfreq)) {
+		ret = PTR_ERR(data->devfreq);
+		goto err_free_opp;
+	}
+
 	devm_devfreq_register_opp_notifier(dev, data->devfreq);
 
 	data->dev = dev;
 	platform_set_drvdata(pdev, data);
 
+	return 0;
+
+err_free_opp:
+	dev_pm_opp_of_remove_table(&pdev->dev);
+	return ret;
+}
+
+static int rk3399_dmcfreq_remove(struct platform_device *pdev)
+{
+	struct rk3399_dmcfreq *dmcfreq = dev_get_drvdata(&pdev->dev);
+
+	/*
+	 * Before remove the opp table we need to unregister the opp notifier.
+	 */
+	devm_devfreq_unregister_opp_notifier(dmcfreq->dev, dmcfreq->devfreq);
+	dev_pm_opp_of_remove_table(dmcfreq->dev);
+
 	return 0;
 }
 
@@ -451,6 +428,7 @@ MODULE_DEVICE_TABLE(of, rk3399dmc_devfreq_of_match);
 
 static struct platform_driver rk3399_dmcfreq_driver = {
 	.probe	= rk3399_dmcfreq_probe,
+	.remove = rk3399_dmcfreq_remove,
 	.driver = {
 		.name	= "rk3399-dmc-freq",
 		.pm	= &rk3399_dmcfreq_pm,

drivers/powercap/Kconfig

@@ -29,4 +29,14 @@ config INTEL_RAPL
 	  controller, CPU core (Power Plance 0), graphics uncore (Power Plane
 	  1), etc.
 
+config IDLE_INJECT
+	bool "Idle injection framework"
+	depends on CPU_IDLE
+	default n
+	help
+	  This enables support for the idle injection framework. It
+	  provides a way to force idle periods on a set of specified
+	  CPUs for power capping. Idle period can be injected
+	  synchronously on a set of specified CPUs or alternatively
+	  on a per CPU basis.
 endif

drivers/powercap/Makefile

 obj-$(CONFIG_POWERCAP)	+= powercap_sys.o
 obj-$(CONFIG_INTEL_RAPL) += intel_rapl.o
+obj-$(CONFIG_IDLE_INJECT) += idle_inject.o

drivers/powercap/idle_inject.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2018 Linaro Limited
+ *
+ * Author: Daniel Lezcano <daniel.lezcano@linaro.org>
+ *
+ * The idle injection framework provides a way to force CPUs to enter idle
+ * states for a specified fraction of time over a specified period.
+ *
+ * It relies on the smpboot kthreads feature providing common code for CPU
+ * hotplug and thread [un]parking.
+ *
+ * All of the kthreads used for idle injection are created at init time.
+ *
+ * Next, the users of the the idle injection framework provide a cpumask via
+ * its register function. The kthreads will be synchronized with respect to
+ * this cpumask.
+ *
+ * The idle + run duration is specified via separate helpers and that allows
+ * idle injection to be started.
+ *
+ * The idle injection kthreads will call play_idle() with the idle duration
+ * specified as per the above.
+ *
+ * After all of them have been woken up, a timer is set to start the next idle
+ * injection cycle.
+ *
+ * The timer interrupt handler will wake up the idle injection kthreads for
+ * all of the CPUs in the cpumask provided by the user.
+ *
+ * Idle injection is stopped synchronously and no leftover idle injection
+ * kthread activity after its completion is guaranteed.
+ *
+ * It is up to the user of this framework to provide a lock for higher-level
+ * synchronization to prevent race conditions like starting idle injection
+ * while unregistering from the framework.
+ */
+#define pr_fmt(fmt) "ii_dev: " fmt
+
+#include <linux/cpu.h>
+#include <linux/hrtimer.h>
+#include <linux/kthread.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/smpboot.h>
+
+#include <uapi/linux/sched/types.h>
+
+/**
+ * struct idle_inject_thread - task on/off switch structure
+ * @tsk: task injecting the idle cycles
+ * @should_run: whether or not to run the task (for the smpboot kthread API)
+ */
+struct idle_inject_thread {
+	struct task_struct *tsk;
+	int should_run;
+};
+
+/**
+ * struct idle_inject_device - idle injection data
+ * @timer: idle injection period timer
+ * @idle_duration_ms: duration of CPU idle time to inject
+ * @run_duration_ms: duration of CPU run time to allow
+ * @cpumask: mask of CPUs affected by idle injection
+ */
+struct idle_inject_device {
+	struct hrtimer timer;
+	unsigned int idle_duration_ms;
+	unsigned int run_duration_ms;
+	unsigned long int cpumask[0];
+};
+
+static DEFINE_PER_CPU(struct idle_inject_thread, idle_inject_thread);
+static DEFINE_PER_CPU(struct idle_inject_device *, idle_inject_device);
+
+/**
+ * idle_inject_wakeup - Wake up idle injection threads
+ * @ii_dev: target idle injection device
+ *
+ * Every idle injection task associated with the given idle injection device
+ * and running on an online CPU will be woken up.
+ */
+static void idle_inject_wakeup(struct idle_inject_device *ii_dev)
+{
+	struct idle_inject_thread *iit;
+	unsigned int cpu;
+
+	for_each_cpu_and(cpu, to_cpumask(ii_dev->cpumask), cpu_online_mask) {
+		iit = per_cpu_ptr(&idle_inject_thread, cpu);
+		iit->should_run = 1;
+		wake_up_process(iit->tsk);
+	}
+}
+
+/**
+ * idle_inject_timer_fn - idle injection timer function
+ * @timer: idle injection hrtimer
+ *
+ * This function is called when the idle injection timer expires.  It wakes up
+ * idle injection tasks associated with the timer and they, in turn, invoke
+ * play_idle() to inject a specified amount of CPU idle time.
+ *
+ * Return: HRTIMER_RESTART.
+ */
+static enum hrtimer_restart idle_inject_timer_fn(struct hrtimer *timer)
+{
+	unsigned int duration_ms;
+	struct idle_inject_device *ii_dev =
+		container_of(timer, struct idle_inject_device, timer);
+
+	duration_ms = READ_ONCE(ii_dev->run_duration_ms);
+	duration_ms += READ_ONCE(ii_dev->idle_duration_ms);
+
+	idle_inject_wakeup(ii_dev);
+
+	hrtimer_forward_now(timer, ms_to_ktime(duration_ms));
+
+	return HRTIMER_RESTART;
+}
+
+/**
+ * idle_inject_fn - idle injection work function
+ * @cpu: the CPU owning the task
+ *
+ * This function calls play_idle() to inject a specified amount of CPU idle
+ * time.
+ */
+static void idle_inject_fn(unsigned int cpu)
+{
+	struct idle_inject_device *ii_dev;
+	struct idle_inject_thread *iit;
+
+	ii_dev = per_cpu(idle_inject_device, cpu);
+	iit = per_cpu_ptr(&idle_inject_thread, cpu);
+
+	/*
+	 * Let the smpboot main loop know that the task should not run again.
+	 */
+	iit->should_run = 0;
+
+	play_idle(READ_ONCE(ii_dev->idle_duration_ms));
+}
+
+/**
+ * idle_inject_set_duration - idle and run duration update helper
+ * @run_duration_ms: CPU run time to allow in milliseconds
+ * @idle_duration_ms: CPU idle time to inject in milliseconds
+ */
+void idle_inject_set_duration(struct idle_inject_device *ii_dev,
+			      unsigned int run_duration_ms,
+			      unsigned int idle_duration_ms)
+{
+	if (run_duration_ms && idle_duration_ms) {
+		WRITE_ONCE(ii_dev->run_duration_ms, run_duration_ms);
+		WRITE_ONCE(ii_dev->idle_duration_ms, idle_duration_ms);
+	}
+}
+
+/**
+ * idle_inject_get_duration - idle and run duration retrieval helper
+ * @run_duration_ms: memory location to store the current CPU run time
+ * @idle_duration_ms: memory location to store the current CPU idle time
+ */
+void idle_inject_get_duration(struct idle_inject_device *ii_dev,
+			      unsigned int *run_duration_ms,
+			      unsigned int *idle_duration_ms)
+{
+	*run_duration_ms = READ_ONCE(ii_dev->run_duration_ms);
+	*idle_duration_ms = READ_ONCE(ii_dev->idle_duration_ms);
+}
+
+/**
+ * idle_inject_start - start idle injections
+ * @ii_dev: idle injection control device structure
+ *
+ * The function starts idle injection by first waking up all of the idle
+ * injection kthreads associated with @ii_dev to let them inject CPU idle time
+ * sets up a timer to start the next idle injection period.
+ *
+ * Return: -EINVAL if the CPU idle or CPU run time is not set or 0 on success.
+ */
+int idle_inject_start(struct idle_inject_device *ii_dev)
+{
+	unsigned int idle_duration_ms = READ_ONCE(ii_dev->idle_duration_ms);
+	unsigned int run_duration_ms = READ_ONCE(ii_dev->run_duration_ms);
+
+	if (!idle_duration_ms || !run_duration_ms)
+		return -EINVAL;
+
+	pr_debug("Starting injecting idle cycles on CPUs '%*pbl'\n",
+		 cpumask_pr_args(to_cpumask(ii_dev->cpumask)));
+
+	idle_inject_wakeup(ii_dev);
+
+	hrtimer_start(&ii_dev->timer,
+		      ms_to_ktime(idle_duration_ms + run_duration_ms),
+		      HRTIMER_MODE_REL);
+
+	return 0;
+}
+
+/**
+ * idle_inject_stop - stops idle injections
+ * @ii_dev: idle injection control device structure
+ *
+ * The function stops idle injection and waits for the threads to finish work.
+ * If CPU idle time is being injected when this function runs, then it will
+ * wait until the end of the cycle.
+ *
+ * When it returns, there is no more idle injection kthread activity.  The
+ * kthreads are scheduled out and the periodic timer is off.
+ */
+void idle_inject_stop(struct idle_inject_device *ii_dev)
+{
+	struct idle_inject_thread *iit;
+	unsigned int cpu;
+
+	pr_debug("Stopping idle injection on CPUs '%*pbl'\n",
+		 cpumask_pr_args(to_cpumask(ii_dev->cpumask)));
+
+	hrtimer_cancel(&ii_dev->timer);
+
+	/*
+	 * Stopping idle injection requires all of the idle injection kthreads
+	 * associated with the given cpumask to be parked and stay that way, so
+	 * prevent CPUs from going online at this point.  Any CPUs going online
+	 * after the loop below will be covered by clearing the should_run flag
+	 * that will cause the smpboot main loop to schedule them out.
+	 */
+	cpu_hotplug_disable();
+
+	/*
+	 * Iterate over all (online + offline) CPUs here in case one of them
+	 * goes offline with the should_run flag set so as to prevent its idle
+	 * injection kthread from running when the CPU goes online again after
+	 * the ii_dev has been freed.
+	 */
+	for_each_cpu(cpu, to_cpumask(ii_dev->cpumask)) {
+		iit = per_cpu_ptr(&idle_inject_thread, cpu);
+		iit->should_run = 0;
+
+		wait_task_inactive(iit->tsk, 0);
+	}
+
+	cpu_hotplug_enable();
+}
+
+/**
+ * idle_inject_setup - prepare the current task for idle injection
+ * @cpu: not used
+ *
+ * Called once, this function is in charge of setting the current task's
+ * scheduler parameters to make it an RT task.
+ */
+static void idle_inject_setup(unsigned int cpu)
+{
+	struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO / 2 };
+
+	sched_setscheduler(current, SCHED_FIFO, &param);
+}
+
+/**
+ * idle_inject_should_run - function helper for the smpboot API
+ * @cpu: CPU the kthread is running on
+ *
+ * Return: whether or not the thread can run.
+ */
+static int idle_inject_should_run(unsigned int cpu)
+{
+	struct idle_inject_thread *iit =
+		per_cpu_ptr(&idle_inject_thread, cpu);
+
+	return iit->should_run;
+}
+
+/**
+ * idle_inject_register - initialize idle injection on a set of CPUs
+ * @cpumask: CPUs to be affected by idle injection
+ *
+ * This function creates an idle injection control device structure for the
+ * given set of CPUs and initializes the timer associated with it.  It does not
+ * start any injection cycles.
+ *
+ * Return: NULL if memory allocation fails, idle injection control device
+ * pointer on success.
+ */
+struct idle_inject_device *idle_inject_register(struct cpumask *cpumask)
+{
+	struct idle_inject_device *ii_dev;
+	int cpu, cpu_rb;
+
+	ii_dev = kzalloc(sizeof(*ii_dev) + cpumask_size(), GFP_KERNEL);
+	if (!ii_dev)
+		return NULL;
+
+	cpumask_copy(to_cpumask(ii_dev->cpumask), cpumask);
+	hrtimer_init(&ii_dev->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	ii_dev->timer.function = idle_inject_timer_fn;
+
+	for_each_cpu(cpu, to_cpumask(ii_dev->cpumask)) {
+
+		if (per_cpu(idle_inject_device, cpu)) {
+			pr_err("cpu%d is already registered\n", cpu);
+			goto out_rollback;
+		}
+
+		per_cpu(idle_inject_device, cpu) = ii_dev;
+	}
+
+	return ii_dev;
+
+out_rollback:
+	for_each_cpu(cpu_rb, to_cpumask(ii_dev->cpumask)) {
+		if (cpu == cpu_rb)
+			break;
+		per_cpu(idle_inject_device, cpu_rb) = NULL;
+	}
+
+	kfree(ii_dev);
+
+	return NULL;
+}
+
+/**
+ * idle_inject_unregister - unregister idle injection control device
+ * @ii_dev: idle injection control device to unregister
+ *
+ * The function stops idle injection for the given control device,
+ * unregisters its kthreads and frees memory allocated when that device was
+ * created.
+ */
+void idle_inject_unregister(struct idle_inject_device *ii_dev)
+{
+	unsigned int cpu;
+
+	idle_inject_stop(ii_dev);
+
+	for_each_cpu(cpu, to_cpumask(ii_dev->cpumask))
+		per_cpu(idle_inject_device, cpu) = NULL;
+
+	kfree(ii_dev);
+}
+
+static struct smp_hotplug_thread idle_inject_threads = {
+	.store = &idle_inject_thread.tsk,
+	.setup = idle_inject_setup,
+	.thread_fn = idle_inject_fn,
+	.thread_comm = "idle_inject/%u",
+	.thread_should_run = idle_inject_should_run,
+};
+
+static int __init idle_inject_init(void)
+{
+	return smpboot_register_percpu_thread(&idle_inject_threads);
+}
+early_initcall(idle_inject_init);

include/dt-bindings/clock/rk3399-ddr.h

+/* SPDX-License-Identifier: (GPL-2.0+ OR MIT) */
+
+#ifndef DT_BINDINGS_DDR_H
+#define DT_BINDINGS_DDR_H
+
+/*
+ * DDR3 SDRAM Standard Speed Bins include tCK, tRCD, tRP, tRAS and tRC for
+ * each corresponding bin.
+ */
+
+/* DDR3-800 (5-5-5) */
+#define DDR3_800D	0
+/* DDR3-800 (6-6-6) */
+#define DDR3_800E	1
+/* DDR3-1066 (6-6-6) */
+#define DDR3_1066E	2
+/* DDR3-1066 (7-7-7) */
+#define DDR3_1066F	3
+/* DDR3-1066 (8-8-8) */
+#define DDR3_1066G	4
+/* DDR3-1333 (7-7-7) */
+#define DDR3_1333F	5
+/* DDR3-1333 (8-8-8) */
+#define DDR3_1333G	6
+/* DDR3-1333 (9-9-9) */
+#define DDR3_1333H	7
+/* DDR3-1333 (10-10-10) */
+#define DDR3_1333J 	8
+/* DDR3-1600 (8-8-8) */
+#define DDR3_1600G	9
+/* DDR3-1600 (9-9-9) */
+#define DDR3_1600H	10
+/* DDR3-1600 (10-10-10) */
+#define DDR3_1600J	11
+/* DDR3-1600 (11-11-11) */
+#define DDR3_1600K	12
+/* DDR3-1600 (10-10-10) */
+#define DDR3_1866J	13
+/* DDR3-1866 (11-11-11) */
+#define DDR3_1866K	14
+/* DDR3-1866 (12-12-12) */
+#define DDR3_1866L	15
+/* DDR3-1866 (13-13-13) */
+#define DDR3_1866M	16
+/* DDR3-2133 (11-11-11) */
+#define DDR3_2133K	17
+/* DDR3-2133 (12-12-12) */
+#define DDR3_2133L	18
+/* DDR3-2133 (13-13-13) */
+#define DDR3_2133M	19
+/* DDR3-2133 (14-14-14) */
+#define DDR3_2133N	20
+/* DDR3 ATF default */
+#define DDR3_DEFAULT	21
+
+#endif

include/linux/idle_inject.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 Linaro Ltd
+ *
+ * Author: Daniel Lezcano <daniel.lezcano@linaro.org>
+ *
+ */
+#ifndef __IDLE_INJECT_H__
+#define __IDLE_INJECT_H__
+
+/* private idle injection device structure */
+struct idle_inject_device;
+
+struct idle_inject_device *idle_inject_register(struct cpumask *cpumask);
+
+void idle_inject_unregister(struct idle_inject_device *ii_dev);
+
+int idle_inject_start(struct idle_inject_device *ii_dev);
+
+void idle_inject_stop(struct idle_inject_device *ii_dev);
+
+void idle_inject_set_duration(struct idle_inject_device *ii_dev,
+				 unsigned int run_duration_ms,
+				 unsigned int idle_duration_ms);
+
+void idle_inject_get_duration(struct idle_inject_device *ii_dev,
+				 unsigned int *run_duration_ms,
+				 unsigned int *idle_duration_ms);
+#endif /* __IDLE_INJECT_H__ */