Merge earlier changes in Intel thermal drivers for v6.7.

Author: rafaeljw

Documentation/driver-api/thermal/intel_dptf.rst

@@ -315,3 +315,57 @@ DPTF Fan Control
 ----------------------------------------
 
 Refer to Documentation/admin-guide/acpi/fan_performance_states.rst
+
+Workload Type Hints
+----------------------------------------
+
+The firmware in Meteor Lake processor generation is capable of identifying
+workload type and passing hints regarding it to the OS. A special sysfs
+interface is provided to allow user space to obtain workload type hints from
+the firmware and control the rate at which they are provided.
+
+User space can poll attribute "workload_type_index" for the current hint or
+can receive a notification whenever the value of this attribute is updated.
+
+file:`/sys/bus/pci/devices/0000:00:04.0/workload_hint/`
+Segment 0, bus 0, device 4, function 0 is reserved for the processor thermal
+device on all Intel client processors. So, the above path doesn't change
+based on the processor generation.
+
+``workload_hint_enable`` (RW)
+	Enable firmware to send workload type hints to user space.
+
+``notification_delay_ms`` (RW)
+	Minimum delay in milliseconds before firmware will notify OS. This is
+	for the rate control of notifications. This delay is between changing
+	the workload type prediction in the firmware and notifying the OS about
+	the change. The default delay is 1024 ms. The delay of 0 is invalid.
+	The delay is rounded up to the nearest power of 2 to simplify firmware
+	programming of the delay value. The read of notification_delay_ms
+	attribute shows the effective value used.
+
+``workload_type_index`` (RO)
+	Predicted workload type index. User space can get notification of
+	change via existing sysfs attribute change notification mechanism.
+
+	The supported index values and their meaning for the Meteor Lake
+	processor generation are as follows:
+
+	0 -  Idle: System performs no tasks, power and idle residency are
+		consistently low for long periods of time.
+
+	1 – Battery Life: Power is relatively low, but the processor may
+		still be actively performing a task, such as video playback for
+		a long period of time.
+
+	2 – Sustained: Power level that is relatively high for a long period
+		of time, with very few to no periods of idleness, which will
+		eventually exhaust RAPL Power Limit 1 and 2.
+
+	3 – Bursty: Consumes a relatively constant average amount of power, but
+		periods of relative idleness are interrupted by bursts of
+		activity. The bursts are relatively short and the periods of
+		relative idleness between them typically prevent RAPL Power
+		Limit 1 from being exhausted.
+
+	4 – Unknown: Can't classify.

drivers/thermal/intel/int340x_thermal/Makefile

@@ -10,5 +10,7 @@ obj-$(CONFIG_INT340X_THERMAL)	+= processor_thermal_device_pci.o
 obj-$(CONFIG_PROC_THERMAL_MMIO_RAPL) += processor_thermal_rapl.o
 obj-$(CONFIG_INT340X_THERMAL)	+= processor_thermal_rfim.o
 obj-$(CONFIG_INT340X_THERMAL)	+= processor_thermal_mbox.o
+obj-$(CONFIG_INT340X_THERMAL)	+= processor_thermal_wt_req.o
+obj-$(CONFIG_INT340X_THERMAL)	+= processor_thermal_wt_hint.o
 obj-$(CONFIG_INT3406_THERMAL)	+= int3406_thermal.o
 obj-$(CONFIG_ACPI_THERMAL_REL)	+= acpi_thermal_rel.o

drivers/thermal/intel/int340x_thermal/processor_thermal_device.c

@@ -346,12 +346,18 @@ int proc_thermal_mmio_add(struct pci_dev *pdev,
 		}
 	}
 
-	if (feature_mask & PROC_THERMAL_FEATURE_MBOX) {
-		ret = proc_thermal_mbox_add(pdev, proc_priv);
+	if (feature_mask & PROC_THERMAL_FEATURE_WT_REQ) {
+		ret = proc_thermal_wt_req_add(pdev, proc_priv);
 		if (ret) {
 			dev_err(&pdev->dev, "failed to add MBOX interface\n");
 			goto err_rem_rfim;
 		}
+	} else if (feature_mask & PROC_THERMAL_FEATURE_WT_HINT) {
+		ret = proc_thermal_wt_hint_add(pdev, proc_priv);
+		if (ret) {
+			dev_err(&pdev->dev, "failed to add WT Hint\n");
+			goto err_rem_rfim;
+		}
 	}
 
 	return 0;
@@ -374,12 +380,15 @@ void proc_thermal_mmio_remove(struct pci_dev *pdev, struct proc_thermal_device *
 	    proc_priv->mmio_feature_mask & PROC_THERMAL_FEATURE_DVFS)
 		proc_thermal_rfim_remove(pdev);
 
-	if (proc_priv->mmio_feature_mask & PROC_THERMAL_FEATURE_MBOX)
-		proc_thermal_mbox_remove(pdev);
+	if (proc_priv->mmio_feature_mask & PROC_THERMAL_FEATURE_WT_REQ)
+		proc_thermal_wt_req_remove(pdev);
+	else if (proc_priv->mmio_feature_mask & PROC_THERMAL_FEATURE_WT_HINT)
+		proc_thermal_wt_hint_remove(pdev);
 }
 EXPORT_SYMBOL_GPL(proc_thermal_mmio_remove);
 
 MODULE_IMPORT_NS(INTEL_TCC);
+MODULE_IMPORT_NS(INT340X_THERMAL);
 MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>");
 MODULE_DESCRIPTION("Processor Thermal Reporting Device Driver");
 MODULE_LICENSE("GPL v2");

drivers/thermal/intel/int340x_thermal/processor_thermal_device.h

@@ -10,6 +10,7 @@
 #include <linux/intel_rapl.h>
 
 #define PCI_DEVICE_ID_INTEL_ADL_THERMAL	0x461d
+#define PCI_DEVICE_ID_INTEL_ARL_S_THERMAL 0xAD03
 #define PCI_DEVICE_ID_INTEL_BDW_THERMAL	0x1603
 #define PCI_DEVICE_ID_INTEL_BSW_THERMAL	0x22DC
 
@@ -59,8 +60,9 @@ struct rapl_mmio_regs {
 #define PROC_THERMAL_FEATURE_RAPL	0x01
 #define PROC_THERMAL_FEATURE_FIVR	0x02
 #define PROC_THERMAL_FEATURE_DVFS	0x04
-#define PROC_THERMAL_FEATURE_MBOX	0x08
+#define PROC_THERMAL_FEATURE_WT_REQ	0x08
 #define PROC_THERMAL_FEATURE_DLVR	0x10
+#define PROC_THERMAL_FEATURE_WT_HINT	0x20
 
 #if IS_ENABLED(CONFIG_PROC_THERMAL_MMIO_RAPL)
 int proc_thermal_rapl_add(struct pci_dev *pdev, struct proc_thermal_device *proc_priv);
@@ -80,13 +82,27 @@ static void __maybe_unused proc_thermal_rapl_remove(void)
 int proc_thermal_rfim_add(struct pci_dev *pdev, struct proc_thermal_device *proc_priv);
 void proc_thermal_rfim_remove(struct pci_dev *pdev);
 
-int proc_thermal_mbox_add(struct pci_dev *pdev, struct proc_thermal_device *proc_priv);
-void proc_thermal_mbox_remove(struct pci_dev *pdev);
+int proc_thermal_wt_req_add(struct pci_dev *pdev, struct proc_thermal_device *proc_priv);
+void proc_thermal_wt_req_remove(struct pci_dev *pdev);
+
+#define MBOX_CMD_WORKLOAD_TYPE_READ	0x0E
+#define MBOX_CMD_WORKLOAD_TYPE_WRITE	0x0F
+
+#define MBOX_DATA_BIT_AC_DC		30
+#define MBOX_DATA_BIT_VALID		31
 
 int processor_thermal_send_mbox_read_cmd(struct pci_dev *pdev, u16 id, u64 *resp);
 int processor_thermal_send_mbox_write_cmd(struct pci_dev *pdev, u16 id, u32 data);
+int processor_thermal_mbox_interrupt_config(struct pci_dev *pdev, bool enable, int enable_bit,
+					    int time_window);
 int proc_thermal_add(struct device *dev, struct proc_thermal_device *priv);
 void proc_thermal_remove(struct proc_thermal_device *proc_priv);
+
+int proc_thermal_wt_hint_add(struct pci_dev *pdev, struct proc_thermal_device *proc_priv);
+void proc_thermal_wt_hint_remove(struct pci_dev *pdev);
+void proc_thermal_wt_intr_callback(struct pci_dev *pdev, struct proc_thermal_device *proc_priv);
+bool proc_thermal_check_wt_intr(struct proc_thermal_device *proc_priv);
+
 int proc_thermal_suspend(struct device *dev);
 int proc_thermal_resume(struct device *dev);
 int proc_thermal_mmio_add(struct pci_dev *pdev,

drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c

@@ -15,6 +15,11 @@
 
 #define DRV_NAME "proc_thermal_pci"
 
+static bool use_msi;
+module_param(use_msi, bool, 0644);
+MODULE_PARM_DESC(use_msi,
+	"Use PCI MSI based interrupts for processor thermal device.");
+
 struct proc_thermal_pci {
 	struct pci_dev *pdev;
 	struct proc_thermal_device *proc_priv;
@@ -117,20 +122,44 @@ static void pkg_thermal_schedule_work(struct delayed_work *work)
 	schedule_delayed_work(work, ms);
 }
 
+static irqreturn_t proc_thermal_irq_thread_handler(int irq, void *devid)
+{
+	struct proc_thermal_pci *pci_info = devid;
+
+	proc_thermal_wt_intr_callback(pci_info->pdev, pci_info->proc_priv);
+
+	return IRQ_HANDLED;
+}
+
 static irqreturn_t proc_thermal_irq_handler(int irq, void *devid)
 {
 	struct proc_thermal_pci *pci_info = devid;
+	struct proc_thermal_device *proc_priv;
+	int ret = IRQ_HANDLED;
 	u32 status;
 
+	proc_priv = pci_info->proc_priv;
+
+	if (proc_priv->mmio_feature_mask & PROC_THERMAL_FEATURE_WT_HINT) {
+		if (proc_thermal_check_wt_intr(pci_info->proc_priv))
+			ret = IRQ_WAKE_THREAD;
+	}
+
+	/*
+	 * Since now there are two sources of interrupts: one from thermal threshold
+	 * and another from workload hint, add a check if there was really a threshold
+	 * interrupt before scheduling work function for thermal threshold.
+	 */
 	proc_thermal_mmio_read(pci_info, PROC_THERMAL_MMIO_INT_STATUS_0, &status);
+	if (status) {
+		/* Disable enable interrupt flag */
+		proc_thermal_mmio_write(pci_info, PROC_THERMAL_MMIO_INT_ENABLE_0, 0);
+		pkg_thermal_schedule_work(&pci_info->work);
+	}
 
-	/* Disable enable interrupt flag */
-	proc_thermal_mmio_write(pci_info, PROC_THERMAL_MMIO_INT_ENABLE_0, 0);
 	pci_write_config_byte(pci_info->pdev, 0xdc, 0x01);
 
-	pkg_thermal_schedule_work(&pci_info->work);
-
-	return IRQ_HANDLED;
+	return ret;
 }
 
 static int sys_get_curr_temp(struct thermal_zone_device *tzd, int *temp)
@@ -203,6 +232,7 @@ static int proc_thermal_pci_probe(struct pci_dev *pdev, const struct pci_device_
 	struct proc_thermal_device *proc_priv;
 	struct proc_thermal_pci *pci_info;
 	int irq_flag = 0, irq, ret;
+	bool msi_irq = false;
 
 	proc_priv = devm_kzalloc(&pdev->dev, sizeof(*proc_priv), GFP_KERNEL);
 	if (!proc_priv)
@@ -248,18 +278,23 @@ static int proc_thermal_pci_probe(struct pci_dev *pdev, const struct pci_device_
 		goto err_ret_mmio;
 	}
 
-	/* request and enable interrupt */
-	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to allocate vectors!\n");
-		goto err_ret_tzone;
-	}
-	if (!pdev->msi_enabled && !pdev->msix_enabled)
+	if (use_msi && (pdev->msi_enabled || pdev->msix_enabled)) {
+		/* request and enable interrupt */
+		ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "Failed to allocate vectors!\n");
+			goto err_ret_tzone;
+		}
+
+		irq =  pci_irq_vector(pdev, 0);
+		msi_irq = true;
+	} else {
 		irq_flag = IRQF_SHARED;
+		irq = pdev->irq;
+	}
 
-	irq =  pci_irq_vector(pdev, 0);
 	ret = devm_request_threaded_irq(&pdev->dev, irq,
-					proc_thermal_irq_handler, NULL,
+					proc_thermal_irq_handler, proc_thermal_irq_thread_handler,
 					irq_flag, KBUILD_MODNAME, pci_info);
 	if (ret) {
 		dev_err(&pdev->dev, "Request IRQ %d failed\n", pdev->irq);
@@ -273,7 +308,8 @@ static int proc_thermal_pci_probe(struct pci_dev *pdev, const struct pci_device_
 	return 0;
 
 err_free_vectors:
-	pci_free_irq_vectors(pdev);
+	if (msi_irq)
+		pci_free_irq_vectors(pdev);
 err_ret_tzone:
 	thermal_zone_device_unregister(pci_info->tzone);
 err_ret_mmio:
@@ -350,9 +386,15 @@ static SIMPLE_DEV_PM_OPS(proc_thermal_pci_pm, proc_thermal_pci_suspend,
 			 proc_thermal_pci_resume);
 
 static const struct pci_device_id proc_thermal_pci_ids[] = {
-	{ PCI_DEVICE_DATA(INTEL, ADL_THERMAL, PROC_THERMAL_FEATURE_RAPL | PROC_THERMAL_FEATURE_FIVR | PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_MBOX) },
-	{ PCI_DEVICE_DATA(INTEL, MTLP_THERMAL, PROC_THERMAL_FEATURE_RAPL | PROC_THERMAL_FEATURE_FIVR | PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_MBOX | PROC_THERMAL_FEATURE_DLVR) },
-	{ PCI_DEVICE_DATA(INTEL, RPL_THERMAL, PROC_THERMAL_FEATURE_RAPL | PROC_THERMAL_FEATURE_FIVR | PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_MBOX) },
+	{ PCI_DEVICE_DATA(INTEL, ADL_THERMAL, PROC_THERMAL_FEATURE_RAPL |
+	  PROC_THERMAL_FEATURE_FIVR | PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_WT_REQ) },
+	{ PCI_DEVICE_DATA(INTEL, MTLP_THERMAL, PROC_THERMAL_FEATURE_RAPL |
+	  PROC_THERMAL_FEATURE_FIVR | PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_DLVR |
+	  PROC_THERMAL_FEATURE_WT_HINT) },
+	{ PCI_DEVICE_DATA(INTEL, ARL_S_THERMAL, PROC_THERMAL_FEATURE_RAPL |
+	  PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_DLVR | PROC_THERMAL_FEATURE_WT_HINT) },
+	{ PCI_DEVICE_DATA(INTEL, RPL_THERMAL, PROC_THERMAL_FEATURE_RAPL |
+	  PROC_THERMAL_FEATURE_FIVR | PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_WT_REQ) },
 	{ },
 };
 
@@ -368,6 +410,8 @@ static struct pci_driver proc_thermal_pci_driver = {
 
 module_pci_driver(proc_thermal_pci_driver);
 
+MODULE_IMPORT_NS(INT340X_THERMAL);
+
 MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>");
 MODULE_DESCRIPTION("Processor Thermal Reporting Device Driver");
 MODULE_LICENSE("GPL v2");

drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci_legacy.c

@@ -137,7 +137,8 @@ static const struct pci_device_id proc_thermal_pci_ids[] = {
 	{ PCI_DEVICE_DATA(INTEL, ICL_THERMAL, PROC_THERMAL_FEATURE_RAPL) },
 	{ PCI_DEVICE_DATA(INTEL, JSL_THERMAL, 0) },
 	{ PCI_DEVICE_DATA(INTEL, SKL_THERMAL, PROC_THERMAL_FEATURE_RAPL) },
-	{ PCI_DEVICE_DATA(INTEL, TGL_THERMAL, PROC_THERMAL_FEATURE_RAPL | PROC_THERMAL_FEATURE_FIVR | PROC_THERMAL_FEATURE_MBOX) },
+	{ PCI_DEVICE_DATA(INTEL, TGL_THERMAL, PROC_THERMAL_FEATURE_RAPL |
+	  PROC_THERMAL_FEATURE_FIVR | PROC_THERMAL_FEATURE_WT_REQ) },
 	{ },
 };