Merge tag 'pm-5.18-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These are mostly fixes and cleanups all over the code and a new piece
  of documentation for Intel uncore frequency scaling.

  Functionality-wise, the intel_idle driver will support Sapphire Rapids
  Xeons natively now (with some extra facilities for controlling
  C-states more precisely on those systems), virtual guests will take
  the ACPI S4 hardware signature into account by default, the
  intel_pstate driver will take the defualt EPP value from the firmware,
  cpupower utility will support the AMD P-state driver added in the
  previous cycle, and there is a new tracer utility for that driver.

  Specifics:

   - Allow device_pm_check_callbacks() to be called from interrupt
     context without issues (Dmitry Baryshkov).

   - Modify devm_pm_runtime_enable() to automatically handle
     pm_runtime_dont_use_autosuspend() at driver exit time (Douglas
     Anderson).

   - Make the schedutil cpufreq governor use to_gov_attr_set() instead
     of open coding it (Kevin Hao).

   - Replace acpi_bus_get_device() with acpi_fetch_acpi_dev() in the
     cpufreq longhaul driver (Rafael Wysocki).

   - Unify show() and store() naming in cpufreq and make it use
     __ATTR_XX (Lianjie Zhang).

   - Make the intel_pstate driver use the EPP value set by the firmware
     by default (Srinivas Pandruvada).

   - Re-order the init checks in the powernow-k8 cpufreq driver (Mario
     Limonciello).

   - Make the ACPI processor idle driver check for architectural support
     for LPI to avoid using it on x86 by mistake (Mario Limonciello).

   - Add Sapphire Rapids Xeon support to the intel_idle driver (Artem
     Bityutskiy).

   - Add 'preferred_cstates' module argument to the intel_idle driver to
     work around C1 and C1E handling issue on Sapphire Rapids (Artem
     Bityutskiy).

   - Add core C6 optimization on Sapphire Rapids to the intel_idle
     driver (Artem Bityutskiy).

   - Optimize the haltpoll cpuidle driver a bit (Li RongQing).

   - Remove leftover text from intel_idle() kerneldoc comment and fix up
     white space in intel_idle (Rafael Wysocki).

   - Fix load_image_and_restore() error path (Ye Bin).

   - Fix typos in comments in the system wakeup hadling code (Tom Rix).

   - Clean up non-kernel-doc comments in hibernation code (Jiapeng
     Chong).

   - Fix __setup handler error handling in system-wide suspend and
     hibernation core code (Randy Dunlap).

   - Add device name to suspend_report_result() (Youngjin Jang).

   - Make virtual guests honour ACPI S4 hardware signature by default
     (David Woodhouse).

   - Block power off of a parent PM domain unless child is in deepest
     state (Ulf Hansson).

   - Use dev_err_probe() to simplify error handling for generic PM
     domains (Ahmad Fatoum).

   - Fix sleep-in-atomic bug caused by genpd_debug_remove() (Shawn Guo).

   - Document Intel uncore frequency scaling (Srinivas Pandruvada).

   - Add DTPM hierarchy description (Daniel Lezcano).

   - Change the locking scheme in DTPM (Daniel Lezcano).

   - Fix dtpm_cpu cleanup at exit time and missing virtual DTPM pointer
     release (Daniel Lezcano).

   - Make dtpm_node_callback[] static (kernel test robot).

   - Fix spelling mistake "initialze" -> "initialize" in
     dtpm_create_hierarchy() (Colin Ian King).

   - Add tracer tool for the amd-pstate driver (Jinzhou Su).

   - Fix PC6 displaying in turbostat on some systems (Artem Bityutskiy).

   - Add AMD P-State support to the cpupower utility (Huang Rui)"

* tag 'pm-5.18-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (58 commits)
  cpufreq: powernow-k8: Re-order the init checks
  cpuidle: intel_idle: Drop redundant backslash at line end
  cpuidle: intel_idle: Update intel_idle() kerneldoc comment
  PM: hibernate: Honour ACPI hardware signature by default for virtual guests
  cpufreq: intel_pstate: Use firmware default EPP
  cpufreq: unify show() and store() naming and use __ATTR_XX
  PM: core: keep irq flags in device_pm_check_callbacks()
  cpuidle: haltpoll: Call cpuidle_poll_state_init() later
  Documentation: amd-pstate: add tracer tool introduction
  tools/power/x86/amd_pstate_tracer: Add tracer tool for AMD P-state
  tools/power/x86/intel_pstate_tracer: make tracer as a module
  cpufreq: amd-pstate: Add more tracepoint for AMD P-State module
  PM: sleep: Add device name to suspend_report_result()
  turbostat: fix PC6 displaying on some systems
  intel_idle: add core C6 optimization for SPR
  intel_idle: add 'preferred_cstates' module argument
  intel_idle: add SPR support
  PM: runtime: Have devm_pm_runtime_enable() handle pm_runtime_dont_use_autosuspend()
  ACPI: processor idle: Check for architectural support for LPI
  cpuidle: PSCI: Move the `has_lpi` check to the beginning of the function
  ...

1 files changed, 260 insertions, 73 deletions

diff --git a/drivers/powercap/dtpm.c b/drivers/powercap/dtpm.c
index 8cb45f2d3d78..ce920f17f45f 100644
--- a/drivers/powercap/dtpm.c
+++ b/drivers/powercap/dtpm.c
@@ -23,6 +23,9 @@
 #include <linux/powercap.h>
 #include <linux/slab.h>
 #include <linux/mutex.h>
+#include <linux/of.h>
+
+#include "dtpm_subsys.h"
 
 #define DTPM_POWER_LIMIT_FLAG 0
 
@@ -48,9 +51,7 @@ static int get_max_power_range_uw(struct powercap_zone *pcz, u64 *max_power_uw)
 {
 	struct dtpm *dtpm = to_dtpm(pcz);
 
-	mutex_lock(&dtpm_lock);
 	*max_power_uw = dtpm->power_max - dtpm->power_min;
-	mutex_unlock(&dtpm_lock);
 
 	return 0;
 }
@@ -80,14 +81,7 @@ static int __get_power_uw(struct dtpm *dtpm, u64 *power_uw)
 
 static int get_power_uw(struct powercap_zone *pcz, u64 *power_uw)
 {
-	struct dtpm *dtpm = to_dtpm(pcz);
-	int ret;
-
-	mutex_lock(&dtpm_lock);
-	ret = __get_power_uw(dtpm, power_uw);
-	mutex_unlock(&dtpm_lock);
-
-	return ret;
+	return __get_power_uw(to_dtpm(pcz), power_uw);
 }
 
 static void __dtpm_rebalance_weight(struct dtpm *dtpm)
@@ -130,7 +124,16 @@ static void __dtpm_add_power(struct dtpm *dtpm)
 	}
 }
 
-static int __dtpm_update_power(struct dtpm *dtpm)
+/**
+ * dtpm_update_power - Update the power on the dtpm
+ * @dtpm: a pointer to a dtpm structure to update
+ *
+ * Function to update the power values of the dtpm node specified in
+ * parameter. These new values will be propagated to the tree.
+ *
+ * Return: zero on success, -EINVAL if the values are inconsistent
+ */
+int dtpm_update_power(struct dtpm *dtpm)
 {
 	int ret;
 
@@ -153,26 +156,6 @@ static int __dtpm_update_power(struct dtpm *dtpm)
 }
 
 /**
- * dtpm_update_power - Update the power on the dtpm
- * @dtpm: a pointer to a dtpm structure to update
- *
- * Function to update the power values of the dtpm node specified in
- * parameter. These new values will be propagated to the tree.
- *
- * Return: zero on success, -EINVAL if the values are inconsistent
- */
-int dtpm_update_power(struct dtpm *dtpm)
-{
-	int ret;
-
-	mutex_lock(&dtpm_lock);
-	ret = __dtpm_update_power(dtpm);
-	mutex_unlock(&dtpm_lock);
-
-	return ret;
-}
-
-/**
  * dtpm_release_zone - Cleanup when the node is released
  * @pcz: a pointer to a powercap_zone structure
  *
@@ -188,48 +171,28 @@ int dtpm_release_zone(struct powercap_zone *pcz)
 	struct dtpm *dtpm = to_dtpm(pcz);
 	struct dtpm *parent = dtpm->parent;
 
-	mutex_lock(&dtpm_lock);
-
-	if (!list_empty(&dtpm->children)) {
-		mutex_unlock(&dtpm_lock);
+	if (!list_empty(&dtpm->children))
 		return -EBUSY;
-	}
 
 	if (parent)
 		list_del(&dtpm->sibling);
 
 	__dtpm_sub_power(dtpm);
 
-	mutex_unlock(&dtpm_lock);
-
 	if (dtpm->ops)
 		dtpm->ops->release(dtpm);
+	else
+		kfree(dtpm);
 
-	if (root == dtpm)
-		root = NULL;
-
-	kfree(dtpm);
-
-	return 0;
-}
-
-static int __get_power_limit_uw(struct dtpm *dtpm, int cid, u64 *power_limit)
-{
-	*power_limit = dtpm->power_limit;
 	return 0;
 }
 
 static int get_power_limit_uw(struct powercap_zone *pcz,
 			      int cid, u64 *power_limit)
 {
-	struct dtpm *dtpm = to_dtpm(pcz);
-	int ret;
-
-	mutex_lock(&dtpm_lock);
-	ret = __get_power_limit_uw(dtpm, cid, power_limit);
-	mutex_unlock(&dtpm_lock);
-
-	return ret;
+	*power_limit = to_dtpm(pcz)->power_limit;
+	
+	return 0;
 }
 
 /*
@@ -289,7 +252,7 @@ static int __set_power_limit_uw(struct dtpm *dtpm, int cid, u64 power_limit)
 
 			ret = __set_power_limit_uw(child, cid, power);
 			if (!ret)
-				ret = __get_power_limit_uw(child, cid, &power);
+				ret = get_power_limit_uw(&child->zone, cid, &power);
 
 			if (ret)
 				break;
@@ -307,8 +270,6 @@ static int set_power_limit_uw(struct powercap_zone *pcz,
 	struct dtpm *dtpm = to_dtpm(pcz);
 	int ret;
 
-	mutex_lock(&dtpm_lock);
-
 	/*
 	 * Don't allow values outside of the power range previously
 	 * set when initializing the power numbers.
@@ -320,8 +281,6 @@ static int set_power_limit_uw(struct powercap_zone *pcz,
 	pr_debug("%s: power limit: %llu uW, power max: %llu uW\n",
 		 dtpm->zone.name, dtpm->power_limit, dtpm->power_max);
 
-	mutex_unlock(&dtpm_lock);
-
 	return ret;
 }
 
@@ -332,11 +291,7 @@ static const char *get_constraint_name(struct powercap_zone *pcz, int cid)
 
 static int get_max_power_uw(struct powercap_zone *pcz, int id, u64 *max_power)
 {
-	struct dtpm *dtpm = to_dtpm(pcz);
-
-	mutex_lock(&dtpm_lock);
-	*max_power = dtpm->power_max;
-	mutex_unlock(&dtpm_lock);
+	*max_power = to_dtpm(pcz)->power_max;
 
 	return 0;
 }
@@ -439,8 +394,6 @@ int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent)
 	if (IS_ERR(pcz))
 		return PTR_ERR(pcz);
 
-	mutex_lock(&dtpm_lock);
-
 	if (parent) {
 		list_add_tail(&dtpm->sibling, &parent->children);
 		dtpm->parent = parent;
@@ -456,19 +409,253 @@ int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent)
 	pr_debug("Registered dtpm node '%s' / %llu-%llu uW, \n",
 		 dtpm->zone.name, dtpm->power_min, dtpm->power_max);
 
-	mutex_unlock(&dtpm_lock);
+	return 0;
+}
+
+static struct dtpm *dtpm_setup_virtual(const struct dtpm_node *hierarchy,
+				       struct dtpm *parent)
+{
+	struct dtpm *dtpm;
+	int ret;
+
+	dtpm = kzalloc(sizeof(*dtpm), GFP_KERNEL);
+	if (!dtpm)
+		return ERR_PTR(-ENOMEM);
+	dtpm_init(dtpm, NULL);
+
+	ret = dtpm_register(hierarchy->name, dtpm, parent);
+	if (ret) {
+		pr_err("Failed to register dtpm node '%s': %d\n",
+		       hierarchy->name, ret);
+		kfree(dtpm);
+		return ERR_PTR(ret);
+	}
+
+	return dtpm;
+}
+
+static struct dtpm *dtpm_setup_dt(const struct dtpm_node *hierarchy,
+				  struct dtpm *parent)
+{
+	struct device_node *np;
+	int i, ret;
+
+	np = of_find_node_by_path(hierarchy->name);
+	if (!np) {
+		pr_err("Failed to find '%s'\n", hierarchy->name);
+		return ERR_PTR(-ENXIO);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(dtpm_subsys); i++) {
+
+		if (!dtpm_subsys[i]->setup)
+			continue;
+
+		ret = dtpm_subsys[i]->setup(parent, np);
+		if (ret) {
+			pr_err("Failed to setup '%s': %d\n", dtpm_subsys[i]->name, ret);
+			of_node_put(np);
+			return ERR_PTR(ret);
+		}
+	}
+
+	of_node_put(np);
+
+	/*
+	 * By returning a NULL pointer, we let know the caller there
+	 * is no child for us as we are a leaf of the tree
+	 */
+	return NULL;
+}
+
+typedef struct dtpm * (*dtpm_node_callback_t)(const struct dtpm_node *, struct dtpm *);
+
+static dtpm_node_callback_t dtpm_node_callback[] = {
+	[DTPM_NODE_VIRTUAL] = dtpm_setup_virtual,
+	[DTPM_NODE_DT] = dtpm_setup_dt,
+};
+
+static int dtpm_for_each_child(const struct dtpm_node *hierarchy,
+			       const struct dtpm_node *it, struct dtpm *parent)
+{
+	struct dtpm *dtpm;
+	int i, ret;
+
+	for (i = 0; hierarchy[i].name; i++) {
+
+		if (hierarchy[i].parent != it)
+			continue;
+
+		dtpm = dtpm_node_callback[hierarchy[i].type](&hierarchy[i], parent);
+
+		/*
+		 * A NULL pointer means there is no children, hence we
+		 * continue without going deeper in the recursivity.
+		 */
+		if (!dtpm)
+			continue;
+
+		/*
+		 * There are multiple reasons why the callback could
+		 * fail. The generic glue is abstracting the backend
+		 * and therefore it is not possible to report back or
+		 * take a decision based on the error.  In any case,
+		 * if this call fails, it is not critical in the
+		 * hierarchy creation, we can assume the underlying
+		 * service is not found, so we continue without this
+		 * branch in the tree but with a warning to log the
+		 * information the node was not created.
+		 */
+		if (IS_ERR(dtpm)) {
+			pr_warn("Failed to create '%s' in the hierarchy\n",
+				hierarchy[i].name);
+			continue;
+		}
+
+		ret = dtpm_for_each_child(hierarchy, &hierarchy[i], dtpm);
+		if (ret)
+			return ret;
+	}
 
 	return 0;
 }
 
-static int __init init_dtpm(void)
+/**
+ * dtpm_create_hierarchy - Create the dtpm hierarchy
+ * @hierarchy: An array of struct dtpm_node describing the hierarchy
+ *
+ * The function is called by the platform specific code with the
+ * description of the different node in the hierarchy. It creates the
+ * tree in the sysfs filesystem under the powercap dtpm entry.
+ *
+ * The expected tree has the format:
+ *
+ * struct dtpm_node hierarchy[] = {
+ *	[0] { .name = "topmost", type =  DTPM_NODE_VIRTUAL },
+ *	[1] { .name = "package", .type = DTPM_NODE_VIRTUAL, .parent = &hierarchy[0] },
+ *	[2] { .name = "/cpus/cpu0", .type = DTPM_NODE_DT, .parent = &hierarchy[1] },
+ *	[3] { .name = "/cpus/cpu1", .type = DTPM_NODE_DT, .parent = &hierarchy[1] },
+ *	[4] { .name = "/cpus/cpu2", .type = DTPM_NODE_DT, .parent = &hierarchy[1] },
+ *	[5] { .name = "/cpus/cpu3", .type = DTPM_NODE_DT, .parent = &hierarchy[1] },
+ *	[6] { }
+ * };
+ *
+ * The last element is always an empty one and marks the end of the
+ * array.
+ *
+ * Return: zero on success, a negative value in case of error. Errors
+ * are reported back from the underlying functions.
+ */
+int dtpm_create_hierarchy(struct of_device_id *dtpm_match_table)
 {
+	const struct of_device_id *match;
+	const struct dtpm_node *hierarchy;
+	struct device_node *np;
+	int i, ret;
+
+	mutex_lock(&dtpm_lock);
+
+	if (pct) {
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+
 	pct = powercap_register_control_type(NULL, "dtpm", NULL);
 	if (IS_ERR(pct)) {
 		pr_err("Failed to register control type\n");
-		return PTR_ERR(pct);
+		ret = PTR_ERR(pct);
+		goto out_pct;
 	}
 
+	ret = -ENODEV;
+	np = of_find_node_by_path("/");
+	if (!np)
+		goto out_err;
+
+	match = of_match_node(dtpm_match_table, np);
+
+	of_node_put(np);
+
+	if (!match)
+		goto out_err;
+
+	hierarchy = match->data;
+	if (!hierarchy) {
+		ret = -EFAULT;
+		goto out_err;
+	}
+
+	ret = dtpm_for_each_child(hierarchy, NULL, NULL);
+	if (ret)
+		goto out_err;
+	
+	for (i = 0; i < ARRAY_SIZE(dtpm_subsys); i++) {
+
+		if (!dtpm_subsys[i]->init)
+			continue;
+
+		ret = dtpm_subsys[i]->init();
+		if (ret)
+			pr_info("Failed to initialize '%s': %d",
+				dtpm_subsys[i]->name, ret);
+	}
+
+	mutex_unlock(&dtpm_lock);
+
 	return 0;
+
+out_err:
+	powercap_unregister_control_type(pct);
+out_pct:
+	pct = NULL;
+out_unlock:
+	mutex_unlock(&dtpm_lock);
+	
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dtpm_create_hierarchy);
+
+static void __dtpm_destroy_hierarchy(struct dtpm *dtpm)
+{
+	struct dtpm *child, *aux;
+
+	list_for_each_entry_safe(child, aux, &dtpm->children, sibling)
+		__dtpm_destroy_hierarchy(child);
+
+	/*
+	 * At this point, we know all children were removed from the
+	 * recursive call before
+	 */
+	dtpm_unregister(dtpm);
+}
+
+void dtpm_destroy_hierarchy(void)
+{
+	int i;
+
+	mutex_lock(&dtpm_lock);
+
+	if (!pct)
+		goto out_unlock;
+
+	__dtpm_destroy_hierarchy(root);
+	
+
+	for (i = 0; i < ARRAY_SIZE(dtpm_subsys); i++) {
+
+		if (!dtpm_subsys[i]->exit)
+			continue;
+
+		dtpm_subsys[i]->exit();
+	}
+
+	powercap_unregister_control_type(pct);
+
+	pct = NULL;
+
+	root = NULL;
+
+out_unlock:
+	mutex_unlock(&dtpm_lock);
 }
-late_initcall(init_dtpm);
+EXPORT_SYMBOL_GPL(dtpm_destroy_hierarchy);