Merge back cpufreq changes for 6.4-rc1.

Author: rafaeljw

Documentation/admin-guide/kernel-parameters.txt

@@ -339,6 +339,29 @@
 			             This mode requires kvm-amd.avic=1.
 			             (Default when IOMMU HW support is present.)
 
+	amd_pstate=	[X86]
+			disable
+			  Do not enable amd_pstate as the default
+			  scaling driver for the supported processors
+			passive
+			  Use amd_pstate with passive mode as a scaling driver.
+			  In this mode autonomous selection is disabled.
+			  Driver requests a desired performance level and platform
+			  tries to match the same performance level if it is
+			  satisfied by guaranteed performance level.
+			active
+			  Use amd_pstate_epp driver instance as the scaling driver,
+			  driver provides a hint to the hardware if software wants
+			  to bias toward performance (0x0) or energy efficiency (0xff)
+			  to the CPPC firmware. then CPPC power algorithm will
+			  calculate the runtime workload and adjust the realtime cores
+			  frequency.
+			guided
+			  Activate guided autonomous mode. Driver requests minimum and
+			  maximum performance level and the platform autonomously
+			  selects a performance level in this range and appropriate
+			  to the current workload.
+
 	amijoy.map=	[HW,JOY] Amiga joystick support
 			Map of devices attached to JOY0DAT and JOY1DAT
 			Format: <a>,<b>
@@ -7059,20 +7082,3 @@
 				xmon commands.
 			off	xmon is disabled.
 
-	amd_pstate=	[X86]
-			disable
-			  Do not enable amd_pstate as the default
-			  scaling driver for the supported processors
-			passive
-			  Use amd_pstate as a scaling driver, driver requests a
-			  desired performance on this abstract scale and the power
-			  management firmware translates the requests into actual
-			  hardware states (core frequency, data fabric and memory
-			  clocks etc.)
-			active
-			  Use amd_pstate_epp driver instance as the scaling driver,
-			  driver provides a hint to the hardware if software wants
-			  to bias toward performance (0x0) or energy efficiency (0xff)
-			  to the CPPC firmware. then CPPC power algorithm will
-			  calculate the runtime workload and adjust the realtime cores
-			  frequency.

Documentation/admin-guide/pm/amd-pstate.rst

@@ -303,13 +303,18 @@ efficiency frequency management method on AMD processors.
 AMD Pstate Driver Operation Modes
 =================================
 
-``amd_pstate`` CPPC has two operation modes: CPPC Autonomous(active) mode and
-CPPC non-autonomous(passive) mode.
-active mode and passive mode can be chosen by different kernel parameters.
-When in Autonomous mode, CPPC ignores requests done in the Desired Performance
-Target register and takes into account only the values set to the Minimum requested
-performance, Maximum requested performance, and Energy Performance Preference
-registers. When Autonomous is disabled, it only considers the Desired Performance Target.
+``amd_pstate`` CPPC has 3 operation modes: autonomous (active) mode,
+non-autonomous (passive) mode and guided autonomous (guided) mode.
+Active/passive/guided mode can be chosen by different kernel parameters.
+
+- In autonomous mode, platform ignores the desired performance level request
+  and takes into account only the values set to the minimum, maximum and energy
+  performance preference registers.
+- In non-autonomous mode, platform gets desired performance level
+  from OS directly through Desired Performance Register.
+- In guided-autonomous mode, platform sets operating performance level
+  autonomously according to the current workload and within the limits set by
+  OS through min and max performance registers.
 
 Active Mode
 ------------
@@ -338,6 +343,15 @@ to the Performance Reduction Tolerance register. Above the nominal performance l
 processor must provide at least nominal performance requested and go higher if current
 operating conditions allow.
 
+Guided Mode
+-----------
+
+``amd_pstate=guided``
+
+If ``amd_pstate=guided`` is passed to kernel command line option then this mode
+is activated.  In this mode, driver requests minimum and maximum performance
+level and the platform autonomously selects a performance level in this range
+and appropriate to the current workload.
 
 User Space Interface in ``sysfs`` - General
 ===========================================
@@ -358,6 +372,9 @@ control its functionality at the system level.  They are located in the
 	"passive"
 		The driver is functional and in the ``passive mode``
 
+	"guided"
+		The driver is functional and in the ``guided mode``
+
 	"disable"
 		The driver is unregistered and not functional now.
 

drivers/acpi/cppc_acpi.c

@@ -1433,6 +1433,102 @@ int cppc_set_epp_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls, bool enable)
 }
 EXPORT_SYMBOL_GPL(cppc_set_epp_perf);
 
+/**
+ * cppc_get_auto_sel_caps - Read autonomous selection register.
+ * @cpunum : CPU from which to read register.
+ * @perf_caps : struct where autonomous selection register value is updated.
+ */
+int cppc_get_auto_sel_caps(int cpunum, struct cppc_perf_caps *perf_caps)
+{
+	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum);
+	struct cpc_register_resource *auto_sel_reg;
+	u64  auto_sel;
+
+	if (!cpc_desc) {
+		pr_debug("No CPC descriptor for CPU:%d\n", cpunum);
+		return -ENODEV;
+	}
+
+	auto_sel_reg = &cpc_desc->cpc_regs[AUTO_SEL_ENABLE];
+
+	if (!CPC_SUPPORTED(auto_sel_reg))
+		pr_warn_once("Autonomous mode is not unsupported!\n");
+
+	if (CPC_IN_PCC(auto_sel_reg)) {
+		int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum);
+		struct cppc_pcc_data *pcc_ss_data = NULL;
+		int ret = 0;
+
+		if (pcc_ss_id < 0)
+			return -ENODEV;
+
+		pcc_ss_data = pcc_data[pcc_ss_id];
+
+		down_write(&pcc_ss_data->pcc_lock);
+
+		if (send_pcc_cmd(pcc_ss_id, CMD_READ) >= 0) {
+			cpc_read(cpunum, auto_sel_reg, &auto_sel);
+			perf_caps->auto_sel = (bool)auto_sel;
+		} else {
+			ret = -EIO;
+		}
+
+		up_write(&pcc_ss_data->pcc_lock);
+
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cppc_get_auto_sel_caps);
+
+/**
+ * cppc_set_auto_sel - Write autonomous selection register.
+ * @cpu    : CPU to which to write register.
+ * @enable : the desired value of autonomous selection resiter to be updated.
+ */
+int cppc_set_auto_sel(int cpu, bool enable)
+{
+	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
+	struct cpc_register_resource *auto_sel_reg;
+	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu);
+	struct cppc_pcc_data *pcc_ss_data = NULL;
+	int ret = -EINVAL;
+
+	if (!cpc_desc) {
+		pr_debug("No CPC descriptor for CPU:%d\n", cpu);
+		return -ENODEV;
+	}
+
+	auto_sel_reg = &cpc_desc->cpc_regs[AUTO_SEL_ENABLE];
+
+	if (CPC_IN_PCC(auto_sel_reg)) {
+		if (pcc_ss_id < 0) {
+			pr_debug("Invalid pcc_ss_id\n");
+			return -ENODEV;
+		}
+
+		if (CPC_SUPPORTED(auto_sel_reg)) {
+			ret = cpc_write(cpu, auto_sel_reg, enable);
+			if (ret)
+				return ret;
+		}
+
+		pcc_ss_data = pcc_data[pcc_ss_id];
+
+		down_write(&pcc_ss_data->pcc_lock);
+		/* after writing CPC, transfer the ownership of PCC to platform */
+		ret = send_pcc_cmd(pcc_ss_id, CMD_WRITE);
+		up_write(&pcc_ss_data->pcc_lock);
+	} else {
+		ret = -ENOTSUPP;
+		pr_debug("_CPC in PCC is not supported\n");
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cppc_set_auto_sel);
+
 /**
  * cppc_set_enable - Set to enable CPPC on the processor by writing the
  * Continuous Performance Control package EnableRegister field.
@@ -1488,7 +1584,7 @@ EXPORT_SYMBOL_GPL(cppc_set_enable);
 int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
 {
 	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu);
-	struct cpc_register_resource *desired_reg;
+	struct cpc_register_resource *desired_reg, *min_perf_reg, *max_perf_reg;
 	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
 	struct cppc_pcc_data *pcc_ss_data = NULL;
 	int ret = 0;
@@ -1499,6 +1595,8 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
 	}
 
 	desired_reg = &cpc_desc->cpc_regs[DESIRED_PERF];
+	min_perf_reg = &cpc_desc->cpc_regs[MIN_PERF];
+	max_perf_reg = &cpc_desc->cpc_regs[MAX_PERF];
 
 	/*
 	 * This is Phase-I where we want to write to CPC registers
@@ -1507,7 +1605,7 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
 	 * Since read_lock can be acquired by multiple CPUs simultaneously we
 	 * achieve that goal here
 	 */
-	if (CPC_IN_PCC(desired_reg)) {
+	if (CPC_IN_PCC(desired_reg) || CPC_IN_PCC(min_perf_reg) || CPC_IN_PCC(max_perf_reg)) {
 		if (pcc_ss_id < 0) {
 			pr_debug("Invalid pcc_ss_id\n");
 			return -ENODEV;
@@ -1530,13 +1628,19 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
 		cpc_desc->write_cmd_status = 0;
 	}
 
+	cpc_write(cpu, desired_reg, perf_ctrls->desired_perf);
+
 	/*
-	 * Skip writing MIN/MAX until Linux knows how to come up with
-	 * useful values.
+	 * Only write if min_perf and max_perf not zero. Some drivers pass zero
+	 * value to min and max perf, but they don't mean to set the zero value,
+	 * they just don't want to write to those registers.
 	 */
-	cpc_write(cpu, desired_reg, perf_ctrls->desired_perf);
+	if (perf_ctrls->min_perf)
+		cpc_write(cpu, min_perf_reg, perf_ctrls->min_perf);
+	if (perf_ctrls->max_perf)
+		cpc_write(cpu, max_perf_reg, perf_ctrls->max_perf);
 
-	if (CPC_IN_PCC(desired_reg))
+	if (CPC_IN_PCC(desired_reg) || CPC_IN_PCC(min_perf_reg) || CPC_IN_PCC(max_perf_reg))
 		up_read(&pcc_ss_data->pcc_lock);	/* END Phase-I */
 	/*
 	 * This is Phase-II where we transfer the ownership of PCC to Platform
@@ -1584,7 +1688,7 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
 	 * case during a CMD_READ and if there are pending writes it delivers
 	 * the write command before servicing the read command
 	 */
-	if (CPC_IN_PCC(desired_reg)) {
+	if (CPC_IN_PCC(desired_reg) || CPC_IN_PCC(min_perf_reg) || CPC_IN_PCC(max_perf_reg)) {
 		if (down_write_trylock(&pcc_ss_data->pcc_lock)) {/* BEGIN Phase-II */
 			/* Update only if there are pending write commands */
 			if (pcc_ss_data->pending_pcc_write_cmd)

drivers/cpufreq/Kconfig.arm

@@ -95,7 +95,7 @@ config ARM_BRCMSTB_AVS_CPUFREQ
 	help
 	  Some Broadcom STB SoCs use a co-processor running proprietary firmware
 	  ("AVS") to handle voltage and frequency scaling. This driver provides
-	  a standard CPUfreq interface to to the firmware.
+	  a standard CPUfreq interface to the firmware.
 
 	  Say Y, if you have a Broadcom SoC with AVS support for DFS or DVFS.