Merge branch 'intel_idle+acpi'

Merge changes updating the ACPI processor driver in order to export
acpi_processor_evaluate_cst() to the code outside of it and adding
ACPI support to the intel_idle driver based on that.

* intel_idle+acpi:
  Documentation: admin-guide: PM: Add intel_idle document
  intel_idle: Use ACPI _CST on server systems
  intel_idle: Add module parameter to prevent ACPI _CST from being used
  intel_idle: Allow ACPI _CST to be used for selected known processors
  cpuidle: Allow idle states to be disabled by default
  intel_idle: Use ACPI _CST for processor models without C-state tables
  intel_idle: Refactor intel_idle_cpuidle_driver_init()
  ACPI: processor: Export acpi_processor_evaluate_cst()
  ACPI: processor: Make ACPI_PROCESSOR_CSTATE depend on ACPI_PROCESSOR
  ACPI: processor: Clean up acpi_processor_evaluate_cst()
  ACPI: processor: Introduce acpi_processor_evaluate_cst()
  ACPI: processor: Export function to claim _CST control

Documentation/ABI/testing/sysfs-devices-system-cpu

@@ -196,6 +196,12 @@ Description:
 		does not reflect it. Likewise, if one enables a deep state but a
 		lighter state still is disabled, then this has no effect.
 
+What:		/sys/devices/system/cpu/cpuX/cpuidle/stateN/default_status
+Date:		December 2019
+KernelVersion:	v5.6
+Contact:	Linux power management list <linux-pm@vger.kernel.org>
+Description:
+		(RO) The default status of this state, "enabled" or "disabled".
 
 What:		/sys/devices/system/cpu/cpuX/cpuidle/stateN/residency
 Date:		March 2014

Documentation/admin-guide/pm/cpuidle.rst

@@ -506,6 +506,9 @@ object corresponding to it, as follows:
 ``disable``
 	Whether or not this idle state is disabled.
 
+``default_status``
+	The default status of this state, "enabled" or "disabled".
+
 ``latency``
 	Exit latency of the idle state in microseconds.
 

Documentation/admin-guide/pm/working-state.rst

@@ -8,6 +8,7 @@ Working-State Power Management
    :maxdepth: 2
 
    cpuidle
+   intel_idle
    cpufreq
    intel_pstate
    intel_epb

drivers/acpi/Kconfig

@@ -241,6 +241,7 @@ config ACPI_CPU_FREQ_PSS
 
 config ACPI_PROCESSOR_CSTATE
 	def_bool y
+	depends on ACPI_PROCESSOR
 	depends on IA64 || X86
 
 config ACPI_PROCESSOR_IDLE

drivers/acpi/acpi_processor.c

@@ -705,3 +705,185 @@ void __init acpi_processor_init(void)
 	acpi_scan_add_handler_with_hotplug(&processor_handler, "processor");
 	acpi_scan_add_handler(&processor_container_handler);
 }
+
+#ifdef CONFIG_ACPI_PROCESSOR_CSTATE
+/**
+ * acpi_processor_claim_cst_control - Request _CST control from the platform.
+ */
+bool acpi_processor_claim_cst_control(void)
+{
+	static bool cst_control_claimed;
+	acpi_status status;
+
+	if (!acpi_gbl_FADT.cst_control || cst_control_claimed)
+		return true;
+
+	status = acpi_os_write_port(acpi_gbl_FADT.smi_command,
+				    acpi_gbl_FADT.cst_control, 8);
+	if (ACPI_FAILURE(status)) {
+		pr_warn("ACPI: Failed to claim processor _CST control\n");
+		return false;
+	}
+
+	cst_control_claimed = true;
+	return true;
+}
+EXPORT_SYMBOL_GPL(acpi_processor_claim_cst_control);
+
+/**
+ * acpi_processor_evaluate_cst - Evaluate the processor _CST control method.
+ * @handle: ACPI handle of the processor object containing the _CST.
+ * @cpu: The numeric ID of the target CPU.
+ * @info: Object write the C-states information into.
+ *
+ * Extract the C-state information for the given CPU from the output of the _CST
+ * control method under the corresponding ACPI processor object (or processor
+ * device object) and populate @info with it.
+ *
+ * If any ACPI_ADR_SPACE_FIXED_HARDWARE C-states are found, invoke
+ * acpi_processor_ffh_cstate_probe() to verify them and update the
+ * cpu_cstate_entry data for @cpu.
+ */
+int acpi_processor_evaluate_cst(acpi_handle handle, u32 cpu,
+				struct acpi_processor_power *info)
+{
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+	union acpi_object *cst;
+	acpi_status status;
+	u64 count;
+	int last_index = 0;
+	int i, ret = 0;
+
+	status = acpi_evaluate_object(handle, "_CST", NULL, &buffer);
+	if (ACPI_FAILURE(status)) {
+		acpi_handle_debug(handle, "No _CST\n");
+		return -ENODEV;
+	}
+
+	cst = buffer.pointer;
+
+	/* There must be at least 2 elements. */
+	if (!cst || cst->type != ACPI_TYPE_PACKAGE || cst->package.count < 2) {
+		acpi_handle_warn(handle, "Invalid _CST output\n");
+		ret = -EFAULT;
+		goto end;
+	}
+
+	count = cst->package.elements[0].integer.value;
+
+	/* Validate the number of C-states. */
+	if (count < 1 || count != cst->package.count - 1) {
+		acpi_handle_warn(handle, "Inconsistent _CST data\n");
+		ret = -EFAULT;
+		goto end;
+	}
+
+	for (i = 1; i <= count; i++) {
+		union acpi_object *element;
+		union acpi_object *obj;
+		struct acpi_power_register *reg;
+		struct acpi_processor_cx cx;
+
+		/*
+		 * If there is not enough space for all C-states, skip the
+		 * excess ones and log a warning.
+		 */
+		if (last_index >= ACPI_PROCESSOR_MAX_POWER - 1) {
+			acpi_handle_warn(handle,
+					 "No room for more idle states (limit: %d)\n",
+					 ACPI_PROCESSOR_MAX_POWER - 1);
+			break;
+		}
+
+		memset(&cx, 0, sizeof(cx));
+
+		element = &cst->package.elements[i];
+		if (element->type != ACPI_TYPE_PACKAGE)
+			continue;
+
+		if (element->package.count != 4)
+			continue;
+
+		obj = &element->package.elements[0];
+
+		if (obj->type != ACPI_TYPE_BUFFER)
+			continue;
+
+		reg = (struct acpi_power_register *)obj->buffer.pointer;
+
+		obj = &element->package.elements[1];
+		if (obj->type != ACPI_TYPE_INTEGER)
+			continue;
+
+		cx.type = obj->integer.value;
+		/*
+		 * There are known cases in which the _CST output does not
+		 * contain C1, so if the type of the first state found is not
+		 * C1, leave an empty slot for C1 to be filled in later.
+		 */
+		if (i == 1 && cx.type != ACPI_STATE_C1)
+			last_index = 1;
+
+		cx.address = reg->address;
+		cx.index = last_index + 1;
+
+		if (reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE) {
+			if (!acpi_processor_ffh_cstate_probe(cpu, &cx, reg)) {
+				/*
+				 * In the majority of cases _CST describes C1 as
+				 * a FIXED_HARDWARE C-state, but if the command
+				 * line forbids using MWAIT, use CSTATE_HALT for
+				 * C1 regardless.
+				 */
+				if (cx.type == ACPI_STATE_C1 &&
+				    boot_option_idle_override == IDLE_NOMWAIT) {
+					cx.entry_method = ACPI_CSTATE_HALT;
+					snprintf(cx.desc, ACPI_CX_DESC_LEN, "ACPI HLT");
+				} else {
+					cx.entry_method = ACPI_CSTATE_FFH;
+				}
+			} else if (cx.type == ACPI_STATE_C1) {
+				/*
+				 * In the special case of C1, FIXED_HARDWARE can
+				 * be handled by executing the HLT instruction.
+				 */
+				cx.entry_method = ACPI_CSTATE_HALT;
+				snprintf(cx.desc, ACPI_CX_DESC_LEN, "ACPI HLT");
+			} else {
+				continue;
+			}
+		} else if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) {
+			cx.entry_method = ACPI_CSTATE_SYSTEMIO;
+			snprintf(cx.desc, ACPI_CX_DESC_LEN, "ACPI IOPORT 0x%x",
+				 cx.address);
+		} else {
+			continue;
+		}
+
+		if (cx.type == ACPI_STATE_C1)
+			cx.valid = 1;
+
+		obj = &element->package.elements[2];
+		if (obj->type != ACPI_TYPE_INTEGER)
+			continue;
+
+		cx.latency = obj->integer.value;
+
+		obj = &element->package.elements[3];
+		if (obj->type != ACPI_TYPE_INTEGER)
+			continue;
+
+		memcpy(&info->states[++last_index], &cx, sizeof(cx));
+	}
+
+	acpi_handle_info(handle, "Found %d idle states\n", last_index);
+
+	info->count = last_index;
+
+      end:
+	kfree(buffer.pointer);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(acpi_processor_evaluate_cst);
+#endif /* CONFIG_ACPI_PROCESSOR_CSTATE */

drivers/acpi/processor_idle.c

@@ -299,164 +299,24 @@ static int acpi_processor_get_power_info_default(struct acpi_processor *pr)
 
 static int acpi_processor_get_power_info_cst(struct acpi_processor *pr)
 {
-	acpi_status status;
-	u64 count;
-	int current_count;
-	int i, ret = 0;
-	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
-	union acpi_object *cst;
+	int ret;
 
 	if (nocst)
 		return -ENODEV;
 
-	current_count = 0;
-
-	status = acpi_evaluate_object(pr->handle, "_CST", NULL, &buffer);
-	if (ACPI_FAILURE(status)) {
-		ACPI_DEBUG_PRINT((ACPI_DB_INFO, "No _CST, giving up\n"));
-		return -ENODEV;
-	}
-
-	cst = buffer.pointer;
-
-	/* There must be at least 2 elements */
-	if (!cst || (cst->type != ACPI_TYPE_PACKAGE) || cst->package.count < 2) {
-		pr_err("not enough elements in _CST\n");
-		ret = -EFAULT;
-		goto end;
-	}
-
-	count = cst->package.elements[0].integer.value;
+	ret = acpi_processor_evaluate_cst(pr->handle, pr->id, &pr->power);
+	if (ret)
+		return ret;
 
-	/* Validate number of power states. */
-	if (count < 1 || count != cst->package.count - 1) {
-		pr_err("count given by _CST is not valid\n");
-		ret = -EFAULT;
-		goto end;
-	}
+	/*
+	 * It is expected that there will be at least 2 states, C1 and
+	 * something else (C2 or C3), so fail if that is not the case.
+	 */
+	if (pr->power.count < 2)
+		return -EFAULT;
 
-	/* Tell driver that at least _CST is supported. */
 	pr->flags.has_cst = 1;
-
-	for (i = 1; i <= count; i++) {
-		union acpi_object *element;
-		union acpi_object *obj;
-		struct acpi_power_register *reg;
-		struct acpi_processor_cx cx;
-
-		memset(&cx, 0, sizeof(cx));
-
-		element = &(cst->package.elements[i]);
-		if (element->type != ACPI_TYPE_PACKAGE)
-			continue;
-
-		if (element->package.count != 4)
-			continue;
-
-		obj = &(element->package.elements[0]);
-
-		if (obj->type != ACPI_TYPE_BUFFER)
-			continue;
-
-		reg = (struct acpi_power_register *)obj->buffer.pointer;
-
-		if (reg->space_id != ACPI_ADR_SPACE_SYSTEM_IO &&
-		    (reg->space_id != ACPI_ADR_SPACE_FIXED_HARDWARE))
-			continue;
-
-		/* There should be an easy way to extract an integer... */
-		obj = &(element->package.elements[1]);
-		if (obj->type != ACPI_TYPE_INTEGER)
-			continue;
-
-		cx.type = obj->integer.value;
-		/*
-		 * Some buggy BIOSes won't list C1 in _CST -
-		 * Let acpi_processor_get_power_info_default() handle them later
-		 */
-		if (i == 1 && cx.type != ACPI_STATE_C1)
-			current_count++;
-
-		cx.address = reg->address;
-		cx.index = current_count + 1;
-
-		cx.entry_method = ACPI_CSTATE_SYSTEMIO;
-		if (reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE) {
-			if (acpi_processor_ffh_cstate_probe
-					(pr->id, &cx, reg) == 0) {
-				cx.entry_method = ACPI_CSTATE_FFH;
-			} else if (cx.type == ACPI_STATE_C1) {
-				/*
-				 * C1 is a special case where FIXED_HARDWARE
-				 * can be handled in non-MWAIT way as well.
-				 * In that case, save this _CST entry info.
-				 * Otherwise, ignore this info and continue.
-				 */
-				cx.entry_method = ACPI_CSTATE_HALT;
-				snprintf(cx.desc, ACPI_CX_DESC_LEN, "ACPI HLT");
-			} else {
-				continue;
-			}
-			if (cx.type == ACPI_STATE_C1 &&
-			    (boot_option_idle_override == IDLE_NOMWAIT)) {
-				/*
-				 * In most cases the C1 space_id obtained from
-				 * _CST object is FIXED_HARDWARE access mode.
-				 * But when the option of idle=halt is added,
-				 * the entry_method type should be changed from
-				 * CSTATE_FFH to CSTATE_HALT.
-				 * When the option of idle=nomwait is added,
-				 * the C1 entry_method type should be
-				 * CSTATE_HALT.
-				 */
-				cx.entry_method = ACPI_CSTATE_HALT;
-				snprintf(cx.desc, ACPI_CX_DESC_LEN, "ACPI HLT");
-			}
-		} else {
-			snprintf(cx.desc, ACPI_CX_DESC_LEN, "ACPI IOPORT 0x%x",
-				 cx.address);
-		}
-
-		if (cx.type == ACPI_STATE_C1) {
-			cx.valid = 1;
-		}
-
-		obj = &(element->package.elements[2]);
-		if (obj->type != ACPI_TYPE_INTEGER)
-			continue;
-
-		cx.latency = obj->integer.value;
-
-		obj = &(element->package.elements[3]);
-		if (obj->type != ACPI_TYPE_INTEGER)
-			continue;
-
-		current_count++;
-		memcpy(&(pr->power.states[current_count]), &cx, sizeof(cx));
-
-		/*
-		 * We support total ACPI_PROCESSOR_MAX_POWER - 1
-		 * (From 1 through ACPI_PROCESSOR_MAX_POWER - 1)
-		 */
-		if (current_count >= (ACPI_PROCESSOR_MAX_POWER - 1)) {
-			pr_warn("Limiting number of power states to max (%d)\n",
-				ACPI_PROCESSOR_MAX_POWER);
-			pr_warn("Please increase ACPI_PROCESSOR_MAX_POWER if needed.\n");
-			break;
-		}
-	}
-
-	ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found %d power states\n",
-			  current_count));
-
-	/* Validate number of power states discovered */
-	if (current_count < 2)
-		ret = -EFAULT;
-
-      end:
-	kfree(buffer.pointer);
-
-	return ret;
+	return 0;
 }
 
 static void acpi_processor_power_verify_c3(struct acpi_processor *pr,
@@ -909,7 +769,6 @@ static int acpi_processor_setup_cstates(struct acpi_processor *pr)
 
 static inline void acpi_processor_cstate_first_run_checks(void)
 {
-	acpi_status status;
 	static int first_run;
 
 	if (first_run)
@@ -921,13 +780,10 @@ static inline void acpi_processor_cstate_first_run_checks(void)
 			  max_cstate);
 	first_run++;
 
-	if (acpi_gbl_FADT.cst_control && !nocst) {
-		status = acpi_os_write_port(acpi_gbl_FADT.smi_command,
-					    acpi_gbl_FADT.cst_control, 8);
-		if (ACPI_FAILURE(status))
-			ACPI_EXCEPTION((AE_INFO, status,
-					"Notifying BIOS of _CST ability failed"));
-	}
+	if (nocst)
+		return;
+
+	acpi_processor_claim_cst_control();
 }
 #else
 

drivers/cpuidle/cpuidle.c

@@ -575,10 +575,14 @@ static int __cpuidle_register_device(struct cpuidle_device *dev)
 	if (!try_module_get(drv->owner))
 		return -EINVAL;
 
-	for (i = 0; i < drv->state_count; i++)
+	for (i = 0; i < drv->state_count; i++) {
 		if (drv->states[i].flags & CPUIDLE_FLAG_UNUSABLE)
 			dev->states_usage[i].disable |= CPUIDLE_STATE_DISABLED_BY_DRIVER;
 
+		if (drv->states[i].flags & CPUIDLE_FLAG_OFF)
+			dev->states_usage[i].disable |= CPUIDLE_STATE_DISABLED_BY_USER;
+	}
+
 	per_cpu(cpuidle_devices, dev->cpu) = dev;
 	list_add(&dev->device_list, &cpuidle_detected_devices);
 

drivers/cpuidle/sysfs.c

@@ -329,6 +329,14 @@ static ssize_t store_state_disable(struct cpuidle_state *state,
 	return size;
 }
 
+static ssize_t show_state_default_status(struct cpuidle_state *state,
+					  struct cpuidle_state_usage *state_usage,
+					  char *buf)
+{
+	return sprintf(buf, "%s\n",
+		       state->flags & CPUIDLE_FLAG_OFF ? "disabled" : "enabled");
+}
+
 define_one_state_ro(name, show_state_name);
 define_one_state_ro(desc, show_state_desc);
 define_one_state_ro(latency, show_state_exit_latency);
@@ -339,6 +347,7 @@ define_one_state_ro(time, show_state_time);
 define_one_state_rw(disable, show_state_disable, store_state_disable);
 define_one_state_ro(above, show_state_above);
 define_one_state_ro(below, show_state_below);
+define_one_state_ro(default_status, show_state_default_status);
 
 static struct attribute *cpuidle_state_default_attrs[] = {
 	&attr_name.attr,
@@ -351,6 +360,7 @@ static struct attribute *cpuidle_state_default_attrs[] = {
 	&attr_disable.attr,
 	&attr_above.attr,
 	&attr_below.attr,
+	&attr_default_status.attr,
 	NULL
 };
 

include/linux/acpi.h

@@ -279,6 +279,21 @@ static inline bool invalid_phys_cpuid(phys_cpuid_t phys_id)
 
 /* Validate the processor object's proc_id */
 bool acpi_duplicate_processor_id(int proc_id);
+/* Processor _CTS control */
+struct acpi_processor_power;
+
+#ifdef CONFIG_ACPI_PROCESSOR_CSTATE
+bool acpi_processor_claim_cst_control(void);
+int acpi_processor_evaluate_cst(acpi_handle handle, u32 cpu,
+				struct acpi_processor_power *info);
+#else
+static inline bool acpi_processor_claim_cst_control(void) { return false; }
+static inline int acpi_processor_evaluate_cst(acpi_handle handle, u32 cpu,
+					      struct acpi_processor_power *info)
+{
+	return -ENODEV;
+}
+#endif
 
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
 /* Arch dependent functions for cpu hotplug support */

include/linux/cpuidle.h

@@ -77,6 +77,7 @@ struct cpuidle_state {
 #define CPUIDLE_FLAG_COUPLED	BIT(1) /* state applies to multiple cpus */
 #define CPUIDLE_FLAG_TIMER_STOP BIT(2) /* timer is stopped on this state */
 #define CPUIDLE_FLAG_UNUSABLE	BIT(3) /* avoid using this state */
+#define CPUIDLE_FLAG_OFF	BIT(4) /* disable this state by default */
 
 struct cpuidle_device_kobj;
 struct cpuidle_state_kobj;