Merge branch 'thermal-intel'

Merge thermal control changes related to Intel platforms for 6.3-rc1: - Rework ACPI helper functions for thermal control to retrieve a trip point temperature instead of initializing a trip point objetc (Rafael Wysocki). - Clean up and improve the int340x thermal driver ((Rafael Wysocki). - Simplify and clean up the intel_pch thermal driver ((Rafael Wysocki). - Fix the Intel powerclamp thermal driver and make it use the common idle injection framework (Srinivas Pandruvada). - Add two module parameters, cpumask and max_idle, to the Intel powerclamp thermal driver to allow it to affect only a specific subset of CPUs instead of all of them (Srinivas Pandruvada). - Make the Intel quark_dts thermal driver Use generic trip point objects instead of its own trip point representation (Daniel Lezcano). - Add toctree entry for thermal documents and fix two issues in the Intel powerclamp driver documentation (Bagas Sanjaya). * thermal-intel: (25 commits) Documentation: powerclamp: Fix numbered lists formatting Documentation: powerclamp: Escape wildcard in cpumask description Documentation: admin-guide: Add toctree entry for thermal docs thermal: intel: powerclamp: Add two module parameters Documentation: admin-guide: Move intel_powerclamp documentation thermal: intel: powerclamp: Fix duration module parameter thermal: intel: powerclamp: Return last requested state as cur_state thermal: intel: quark_dts: Use generic trip points thermal: intel: powerclamp: Use powercap idle-inject feature powercap: idle_inject: Add update callback powercap: idle_inject: Export symbols thermal: intel: powerclamp: Fix cur_state for multi package system thermal: intel: intel_pch: Drop struct board_info thermal: intel: intel_pch: Rename board ID symbols thermal: intel: intel_pch: Fold suspend and resume routines into their callers thermal: intel: intel_pch: Fold two functions into their callers thermal: intel: intel_pch: Eliminate device operations object thermal: intel: intel_pch: Rename device operations callbacks thermal: intel: intel_pch: Eliminate redundant return pointers thermal: intel: intel_pch: Make pch_wpt_add_acpi_psv_trip() return int ...
author: Rafael J. Wysocki <rafael.j.wysocki@intel.com> 2023-02-15 17:18:08 +0100
committer: Rafael J. Wysocki <rafael.j.wysocki@intel.com> 2023-02-15 17:18:08 +0100
commit: badf1f90502d3fc627a18880dfafd8c636699baf (patch)
tree: d069f30768766fa721b6f311351de2e0df53f8c1 /drivers/thermal/intel/intel_powerclamp.c
parent: c3bd6d539f34784b235c7070edba978f67516372 (diff)
parent: fef1f0be10c61dd16fd370964c316c399483448f (diff)
download: lwn-badf1f90502d3fc627a18880dfafd8c636699baf.tar.gz
lwn-badf1f90502d3fc627a18880dfafd8c636699baf.zip
1 files changed, 314 insertions, 231 deletions
diff --git a/drivers/thermal/intel/intel_powerclamp.c b/drivers/thermal/intel/intel_powerclamp.c
index b80e25ec1261..c7ba5680cd48 100644
--- a/drivers/thermal/intel/intel_powerclamp.c
+++ b/drivers/thermal/intel/intel_powerclamp.c
@@ -2,7 +2,7 @@
 /*
  * intel_powerclamp.c - package c-state idle injection
  *
- * Copyright (c) 2012, Intel Corporation.
+ * Copyright (c) 2012-2023, Intel Corporation.
  *
  * Authors:
  *     Arjan van de Ven <arjan@linux.intel.com>
@@ -27,23 +27,17 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/delay.h>
-#include <linux/kthread.h>
 #include <linux/cpu.h>
 #include <linux/thermal.h>
-#include <linux/slab.h>
-#include <linux/tick.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
-#include <linux/sched/rt.h>
-#include <uapi/linux/sched/types.h>
+#include <linux/idle_inject.h>
 
-#include <asm/nmi.h>
 #include <asm/msr.h>
 #include <asm/mwait.h>
 #include <asm/cpu_device_id.h>
-#include <asm/hardirq.h>
 
-#define MAX_TARGET_RATIO (50U)
+#define MAX_TARGET_RATIO (100U)
 /* For each undisturbed clamping period (no extra wake ups during idle time),
  * we increment the confidence counter for the given target ratio.
  * CONFIDENCE_OK defines the level where runtime calibration results are
@@ -57,37 +51,30 @@
 
 static unsigned int target_mwait;
 static struct dentry *debug_dir;
+static bool poll_pkg_cstate_enable;
 
-/* user selected target */
-static unsigned int set_target_ratio;
+/* Idle ratio observed using package C-state counters */
 static unsigned int current_ratio;
-static bool should_skip;
 
-static unsigned int control_cpu; /* The cpu assigned to collect stat and update
-				  * control parameters. default to BSP but BSP
-				  * can be offlined.
-				  */
-static bool clamping;
+/* Skip the idle injection till set to true */
+static bool should_skip;
 
-struct powerclamp_worker_data {
-	struct kthread_worker *worker;
-	struct kthread_work balancing_work;
-	struct kthread_delayed_work idle_injection_work;
+struct powerclamp_data {
 	unsigned int cpu;
 	unsigned int count;
 	unsigned int guard;
 	unsigned int window_size_now;
 	unsigned int target_ratio;
-	unsigned int duration_jiffies;
 	bool clamping;
 };
 
-static struct powerclamp_worker_data __percpu *worker_data;
+static struct powerclamp_data powerclamp_data;
+
 static struct thermal_cooling_device *cooling_dev;
-static unsigned long *cpu_clamping_mask;  /* bit map for tracking per cpu
-					   * clamping kthread worker
-					   */
 
+static DEFINE_MUTEX(powerclamp_lock);
+
+/* This duration is in microseconds */
 static unsigned int duration;
 static unsigned int pkg_cstate_ratio_cur;
 static unsigned int window_size;
@@ -104,25 +91,171 @@ static int duration_set(const char *arg, const struct kernel_param *kp)
 		pr_err("Out of recommended range %lu, between 6-25ms\n",
 			new_duration);
 		ret = -EINVAL;
+		goto exit;
 	}
 
-	duration = clamp(new_duration, 6ul, 25ul);
-	smp_mb();
-
+	mutex_lock(&powerclamp_lock);
+	duration = clamp(new_duration, 6ul, 25ul) * 1000;
+	mutex_unlock(&powerclamp_lock);
 exit:
 
 	return ret;
 }
 
+static int duration_get(char *buf, const struct kernel_param *kp)
+{
+	int ret;
+
+	mutex_lock(&powerclamp_lock);
+	ret = sysfs_emit(buf, "%d\n", duration / 1000);
+	mutex_unlock(&powerclamp_lock);
+
+	return ret;
+}
+
 static const struct kernel_param_ops duration_ops = {
 	.set = duration_set,
-	.get = param_get_int,
+	.get = duration_get,
 };
 
-
-module_param_cb(duration, &duration_ops, &duration, 0644);
+module_param_cb(duration, &duration_ops, NULL, 0644);
 MODULE_PARM_DESC(duration, "forced idle time for each attempt in msec.");
 
+#define DEFAULT_MAX_IDLE	50
+#define MAX_ALL_CPU_IDLE	75
+
+static u8 max_idle = DEFAULT_MAX_IDLE;
+
+static cpumask_var_t idle_injection_cpu_mask;
+
+static int allocate_copy_idle_injection_mask(const struct cpumask *copy_mask)
+{
+	if (cpumask_available(idle_injection_cpu_mask))
+		goto copy_mask;
+
+	/* This mask is allocated only one time and freed during module exit */
+	if (!alloc_cpumask_var(&idle_injection_cpu_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+copy_mask:
+	cpumask_copy(idle_injection_cpu_mask, copy_mask);
+
+	return 0;
+}
+
+/* Return true if the cpumask and idle percent combination is invalid */
+static bool check_invalid(cpumask_var_t mask, u8 idle)
+{
+	if (cpumask_equal(cpu_present_mask, mask) && idle > MAX_ALL_CPU_IDLE)
+		return true;
+
+	return false;
+}
+
+static int cpumask_set(const char *arg, const struct kernel_param *kp)
+{
+	cpumask_var_t new_mask;
+	int ret;
+
+	mutex_lock(&powerclamp_lock);
+
+	/* Can't set mask when cooling device is in use */
+	if (powerclamp_data.clamping) {
+		ret = -EAGAIN;
+		goto skip_cpumask_set;
+	}
+
+	ret = alloc_cpumask_var(&new_mask, GFP_KERNEL);
+	if (!ret)
+		goto skip_cpumask_set;
+
+	ret = bitmap_parse(arg, strlen(arg), cpumask_bits(new_mask),
+			   nr_cpumask_bits);
+	if (ret)
+		goto free_cpumask_set;
+
+	if (cpumask_empty(new_mask) || check_invalid(new_mask, max_idle)) {
+		ret = -EINVAL;
+		goto free_cpumask_set;
+	}
+
+	/*
+	 * When module parameters are passed from kernel command line
+	 * during insmod, the module parameter callback is called
+	 * before powerclamp_init(), so we can't assume that some
+	 * cpumask can be allocated and copied before here. Also
+	 * in this case this cpumask is used as the default mask.
+	 */
+	ret = allocate_copy_idle_injection_mask(new_mask);
+
+free_cpumask_set:
+	free_cpumask_var(new_mask);
+skip_cpumask_set:
+	mutex_unlock(&powerclamp_lock);
+
+	return ret;
+}
+
+static int cpumask_get(char *buf, const struct kernel_param *kp)
+{
+	if (!cpumask_available(idle_injection_cpu_mask))
+		return -ENODEV;
+
+	return bitmap_print_to_pagebuf(false, buf, cpumask_bits(idle_injection_cpu_mask),
+				       nr_cpumask_bits);
+}
+
+static const struct kernel_param_ops cpumask_ops = {
+	.set = cpumask_set,
+	.get = cpumask_get,
+};
+
+module_param_cb(cpumask, &cpumask_ops, NULL, 0644);
+MODULE_PARM_DESC(cpumask, "Mask of CPUs to use for idle injection.");
+
+static int max_idle_set(const char *arg, const struct kernel_param *kp)
+{
+	u8 new_max_idle;
+	int ret = 0;
+
+	mutex_lock(&powerclamp_lock);
+
+	/* Can't set mask when cooling device is in use */
+	if (powerclamp_data.clamping) {
+		ret = -EAGAIN;
+		goto skip_limit_set;
+	}
+
+	ret = kstrtou8(arg, 10, &new_max_idle);
+	if (ret)
+		goto skip_limit_set;
+
+	if (new_max_idle > MAX_TARGET_RATIO) {
+		ret = -EINVAL;
+		goto skip_limit_set;
+	}
+
+	if (check_invalid(idle_injection_cpu_mask, new_max_idle)) {
+		ret = -EINVAL;
+		goto skip_limit_set;
+	}
+
+	max_idle = new_max_idle;
+
+skip_limit_set:
+	mutex_unlock(&powerclamp_lock);
+
+	return ret;
+}
+
+static const struct kernel_param_ops max_idle_ops = {
+	.set = max_idle_set,
+	.get = param_get_int,
+};
+
+module_param_cb(max_idle, &max_idle_ops, &max_idle, 0644);
+MODULE_PARM_DESC(max_idle, "maximum injected idle time to the total CPU time ratio in percent range:1-100");
+
 struct powerclamp_calibration_data {
 	unsigned long confidence;  /* used for calibration, basically a counter
 				    * gets incremented each time a clamping
@@ -261,6 +394,9 @@ static unsigned int get_compensation(int ratio)
 {
 	unsigned int comp = 0;
 
+	if (!poll_pkg_cstate_enable)
+		return 0;
+
 	/* we only use compensation if all adjacent ones are good */
 	if (ratio == 1 &&
 		cal_data[ratio].confidence >= CONFIDENCE_OK &&
@@ -302,7 +438,7 @@ static void adjust_compensation(int target_ratio, unsigned int win)
 	if (d->confidence >= CONFIDENCE_OK)
 		return;
 
-	delta = set_target_ratio - current_ratio;
+	delta = powerclamp_data.target_ratio - current_ratio;
 	/* filter out bad data */
 	if (delta >= 0 && delta <= (1+target_ratio/10)) {
 		if (d->steady_comp)
@@ -341,82 +477,39 @@ static bool powerclamp_adjust_controls(unsigned int target_ratio,
 	adjust_compensation(target_ratio, win);
 
 	/* if we are above target+guard, skip */
-	return set_target_ratio + guard <= current_ratio;
+	return powerclamp_data.target_ratio + guard <= current_ratio;
 }
 
-static void clamp_balancing_func(struct kthread_work *work)
+/*
+ * This function calculates runtime from the current target ratio.
+ * This function gets called under powerclamp_lock.
+ */
+static unsigned int get_run_time(void)
 {
-	struct powerclamp_worker_data *w_data;
-	int sleeptime;
-	unsigned long target_jiffies;
 	unsigned int compensated_ratio;
-	int interval; /* jiffies to sleep for each attempt */
-
-	w_data = container_of(work, struct powerclamp_worker_data,
-			      balancing_work);
+	unsigned int runtime;
 
 	/*
 	 * make sure user selected ratio does not take effect until
 	 * the next round. adjust target_ratio if user has changed
 	 * target such that we can converge quickly.
 	 */
-	w_data->target_ratio = READ_ONCE(set_target_ratio);
-	w_data->guard = 1 + w_data->target_ratio / 20;
-	w_data->window_size_now = window_size;
-	w_data->duration_jiffies = msecs_to_jiffies(duration);
-	w_data->count++;
+	powerclamp_data.guard = 1 + powerclamp_data.target_ratio / 20;
+	powerclamp_data.window_size_now = window_size;
 
 	/*
 	 * systems may have different ability to enter package level
 	 * c-states, thus we need to compensate the injected idle ratio
 	 * to achieve the actual target reported by the HW.
 	 */
-	compensated_ratio = w_data->target_ratio +
-		get_compensation(w_data->target_ratio);
+	compensated_ratio = powerclamp_data.target_ratio +
+		get_compensation(powerclamp_data.target_ratio);
 	if (compensated_ratio <= 0)
 		compensated_ratio = 1;
-	interval = w_data->duration_jiffies * 100 / compensated_ratio;
-
-	/* align idle time */
-	target_jiffies = roundup(jiffies, interval);
-	sleeptime = target_jiffies - jiffies;
-	if (sleeptime <= 0)
-		sleeptime = 1;
-
-	if (clamping && w_data->clamping && cpu_online(w_data->cpu))
-		kthread_queue_delayed_work(w_data->worker,
-					   &w_data->idle_injection_work,
-					   sleeptime);
-}
 
-static void clamp_idle_injection_func(struct kthread_work *work)
-{
-	struct powerclamp_worker_data *w_data;
-
-	w_data = container_of(work, struct powerclamp_worker_data,
-			      idle_injection_work.work);
-
-	/*
-	 * only elected controlling cpu can collect stats and update
-	 * control parameters.
-	 */
-	if (w_data->cpu == control_cpu &&
-	    !(w_data->count % w_data->window_size_now)) {
-		should_skip =
-			powerclamp_adjust_controls(w_data->target_ratio,
-						   w_data->guard,
-						   w_data->window_size_now);
-		smp_mb();
-	}
+	runtime = duration * 100 / compensated_ratio - duration;
 
-	if (should_skip)
-		goto balance;
-
-	play_idle(jiffies_to_usecs(w_data->duration_jiffies));
-
-balance:
-	if (clamping && w_data->clamping && cpu_online(w_data->cpu))
-		kthread_queue_work(w_data->worker, &w_data->balancing_work);
+	return runtime;
 }
 
 /*
@@ -452,126 +545,129 @@ static void poll_pkg_cstate(struct work_struct *dummy)
 	msr_last = msr_now;
 	tsc_last = tsc_now;
 
-	if (true == clamping)
+	mutex_lock(&powerclamp_lock);
+	if (powerclamp_data.clamping)
 		schedule_delayed_work(&poll_pkg_cstate_work, HZ);
+	mutex_unlock(&powerclamp_lock);
 }
 
-static void start_power_clamp_worker(unsigned long cpu)
+static struct idle_inject_device *ii_dev;
+
+/*
+ * This function is called from idle injection core on timer expiry
+ * for the run duration. This allows powerclamp to readjust or skip
+ * injecting idle for this cycle.
+ */
+static bool idle_inject_update(void)
 {
-	struct powerclamp_worker_data *w_data = per_cpu_ptr(worker_data, cpu);
-	struct kthread_worker *worker;
+	bool update = false;
 
-	worker = kthread_create_worker_on_cpu(cpu, 0, "kidle_inj/%ld", cpu);
-	if (IS_ERR(worker))
-		return;
+	/* We can't sleep in this callback */
+	if (!mutex_trylock(&powerclamp_lock))
+		return true;
 
-	w_data->worker = worker;
-	w_data->count = 0;
-	w_data->cpu = cpu;
-	w_data->clamping = true;
-	set_bit(cpu, cpu_clamping_mask);
-	sched_set_fifo(worker->task);
-	kthread_init_work(&w_data->balancing_work, clamp_balancing_func);
-	kthread_init_delayed_work(&w_data->idle_injection_work,
-				  clamp_idle_injection_func);
-	kthread_queue_work(w_data->worker, &w_data->balancing_work);
-}
+	if (!(powerclamp_data.count % powerclamp_data.window_size_now)) {
 
-static void stop_power_clamp_worker(unsigned long cpu)
-{
-	struct powerclamp_worker_data *w_data = per_cpu_ptr(worker_data, cpu);
+		should_skip = powerclamp_adjust_controls(powerclamp_data.target_ratio,
+							 powerclamp_data.guard,
+							 powerclamp_data.window_size_now);
+		update = true;
+	}
 
-	if (!w_data->worker)
-		return;
+	if (update) {
+		unsigned int runtime = get_run_time();
 
-	w_data->clamping = false;
-	/*
-	 * Make sure that all works that get queued after this point see
-	 * the clamping disabled. The counter part is not needed because
-	 * there is an implicit memory barrier when the queued work
-	 * is proceed.
-	 */
-	smp_wmb();
-	kthread_cancel_work_sync(&w_data->balancing_work);
-	kthread_cancel_delayed_work_sync(&w_data->idle_injection_work);
-	/*
-	 * The balancing work still might be queued here because
-	 * the handling of the "clapming" variable, cancel, and queue
-	 * operations are not synchronized via a lock. But it is not
-	 * a big deal. The balancing work is fast and destroy kthread
-	 * will wait for it.
-	 */
-	clear_bit(w_data->cpu, cpu_clamping_mask);
-	kthread_destroy_worker(w_data->worker);
+		idle_inject_set_duration(ii_dev, runtime, duration);
+	}
+
+	powerclamp_data.count++;
+
+	mutex_unlock(&powerclamp_lock);
+
+	if (should_skip)
+		return false;
 
-	w_data->worker = NULL;
+	return true;
 }
 
-static int start_power_clamp(void)
+/* This function starts idle injection by calling idle_inject_start() */
+static void trigger_idle_injection(void)
 {
-	unsigned long cpu;
-
-	set_target_ratio = clamp(set_target_ratio, 0U, MAX_TARGET_RATIO - 1);
-	/* prevent cpu hotplug */
-	cpus_read_lock();
+	unsigned int runtime = get_run_time();
 
-	/* prefer BSP */
-	control_cpu = cpumask_first(cpu_online_mask);
+	idle_inject_set_duration(ii_dev, runtime, duration);
+	idle_inject_start(ii_dev);
+	powerclamp_data.clamping = true;
+}
 
-	clamping = true;
-	schedule_delayed_work(&poll_pkg_cstate_work, 0);
+/*
+ * This function is called from start_power_clamp() to register
+ * CPUS with powercap idle injection register and set default
+ * idle duration and latency.
+ */
+static int powerclamp_idle_injection_register(void)
+{
+	poll_pkg_cstate_enable = false;
+	if (cpumask_equal(cpu_present_mask, idle_injection_cpu_mask)) {
+		ii_dev = idle_inject_register_full(idle_injection_cpu_mask, idle_inject_update);
+		if (topology_max_packages() == 1 && topology_max_die_per_package() == 1)
+			poll_pkg_cstate_enable = true;
+	} else {
+		ii_dev = idle_inject_register(idle_injection_cpu_mask);
+	}
 
-	/* start one kthread worker per online cpu */
-	for_each_online_cpu(cpu) {
-		start_power_clamp_worker(cpu);
+	if (!ii_dev) {
+		pr_err("powerclamp: idle_inject_register failed\n");
+		return -EAGAIN;
 	}
-	cpus_read_unlock();
+
+	idle_inject_set_duration(ii_dev, TICK_USEC, duration);
+	idle_inject_set_latency(ii_dev, UINT_MAX);
 
 	return 0;
 }
 
-static void end_power_clamp(void)
+/*
+ * This function is called from end_power_clamp() to stop idle injection
+ * and unregister CPUS from powercap idle injection core.
+ */
+static void remove_idle_injection(void)
 {
-	int i;
+	if (!powerclamp_data.clamping)
+		return;
 
-	/*
-	 * Block requeuing in all the kthread workers. They will flush and
-	 * stop faster.
-	 */
-	clamping = false;
-	for_each_set_bit(i, cpu_clamping_mask, num_possible_cpus()) {
-		pr_debug("clamping worker for cpu %d alive, destroy\n", i);
-		stop_power_clamp_worker(i);
-	}
+	powerclamp_data.clamping = false;
+	idle_inject_stop(ii_dev);
 }
 
-static int powerclamp_cpu_online(unsigned int cpu)
+/*
+ * This function is called when user change the cooling device
+ * state from zero to some other value.
+ */
+static int start_power_clamp(void)
 {
-	if (clamping == false)
-		return 0;
-	start_power_clamp_worker(cpu);
-	/* prefer BSP as controlling CPU */
-	if (cpu == 0) {
-		control_cpu = 0;
-		smp_mb();
+	int ret;
+
+	ret = powerclamp_idle_injection_register();
+	if (!ret) {
+		trigger_idle_injection();
+		if (poll_pkg_cstate_enable)
+			schedule_delayed_work(&poll_pkg_cstate_work, 0);
 	}
-	return 0;
+
+	return ret;
 }
 
-static int powerclamp_cpu_predown(unsigned int cpu)
+/*
+ * This function is called when user change the cooling device
+ * state from non zero value zero.
+ */
+static void end_power_clamp(void)
 {
-	if (clamping == false)
-		return 0;
-
-	stop_power_clamp_worker(cpu);
-	if (cpu != control_cpu)
-		return 0;
-
-	control_cpu = cpumask_first(cpu_online_mask);
-	if (control_cpu == cpu)
-		control_cpu = cpumask_next(cpu, cpu_online_mask);
-	smp_mb();
-	return 0;
+	if (powerclamp_data.clamping) {
+		remove_idle_injection();
+		idle_inject_unregister(ii_dev);
+	}
 }
 
 static int powerclamp_get_max_state(struct thermal_cooling_device *cdev,
@@ -585,11 +681,9 @@ static int powerclamp_get_max_state(struct thermal_cooling_device *cdev,
 static int powerclamp_get_cur_state(struct thermal_cooling_device *cdev,
 				 unsigned long *state)
 {
-	if (true == clamping)
-		*state = pkg_cstate_ratio_cur;
-	else
-		/* to save power, do not poll idle ratio while not clamping */
-		*state = -1; /* indicates invalid state */
+	mutex_lock(&powerclamp_lock);
+	*state = powerclamp_data.target_ratio;
+	mutex_unlock(&powerclamp_lock);
 
 	return 0;
 }
@@ -599,24 +693,32 @@ static int powerclamp_set_cur_state(struct thermal_cooling_device *cdev,
 {
 	int ret = 0;
 
+	mutex_lock(&powerclamp_lock);
+
 	new_target_ratio = clamp(new_target_ratio, 0UL,
-				(unsigned long) (MAX_TARGET_RATIO-1));
-	if (set_target_ratio == 0 && new_target_ratio > 0) {
+				(unsigned long) (max_idle - 1));
+	if (!powerclamp_data.target_ratio && new_target_ratio > 0) {
 		pr_info("Start idle injection to reduce power\n");
-		set_target_ratio = new_target_ratio;
+		powerclamp_data.target_ratio = new_target_ratio;
 		ret = start_power_clamp();
+		if (ret)
+			powerclamp_data.target_ratio = 0;
 		goto exit_set;
-	} else	if (set_target_ratio > 0 && new_target_ratio == 0) {
+	} else	if (powerclamp_data.target_ratio > 0 && new_target_ratio == 0) {
 		pr_info("Stop forced idle injection\n");
 		end_power_clamp();
-		set_target_ratio = 0;
+		powerclamp_data.target_ratio = 0;
 	} else	/* adjust currently running */ {
-		set_target_ratio = new_target_ratio;
-		/* make new set_target_ratio visible to other cpus */
-		smp_mb();
+		unsigned int runtime;
+
+		powerclamp_data.target_ratio = new_target_ratio;
+		runtime = get_run_time();
+		idle_inject_set_duration(ii_dev, runtime, duration);
 	}
 
 exit_set:
+	mutex_unlock(&powerclamp_lock);
+
 	return ret;
 }
 
@@ -657,7 +759,6 @@ static int powerclamp_debug_show(struct seq_file *m, void *unused)
 {
 	int i = 0;
 
-	seq_printf(m, "controlling cpu: %d\n", control_cpu);
 	seq_printf(m, "pct confidence steady dynamic (compensation)\n");
 	for (i = 0; i < MAX_TARGET_RATIO; i++) {
 		seq_printf(m, "%d\t%lu\t%lu\t%lu\n",
@@ -680,75 +781,57 @@ static inline void powerclamp_create_debug_files(void)
 			    &powerclamp_debug_fops);
 }
 
-static enum cpuhp_state hp_state;
-
 static int __init powerclamp_init(void)
 {
 	int retval;
 
-	cpu_clamping_mask = bitmap_zalloc(num_possible_cpus(), GFP_KERNEL);
-	if (!cpu_clamping_mask)
-		return -ENOMEM;
-
 	/* probe cpu features and ids here */
 	retval = powerclamp_probe();
 	if (retval)
-		goto exit_free;
+		return retval;
+
+	mutex_lock(&powerclamp_lock);
+	retval = allocate_copy_idle_injection_mask(cpu_present_mask);
+	mutex_unlock(&powerclamp_lock);
+
+	if (retval)
+		return retval;
 
 	/* set default limit, maybe adjusted during runtime based on feedback */
 	window_size = 2;
-	retval = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-					   "thermal/intel_powerclamp:online",
-					   powerclamp_cpu_online,
-					   powerclamp_cpu_predown);
-	if (retval < 0)
-		goto exit_free;
-
-	hp_state = retval;
-
-	worker_data = alloc_percpu(struct powerclamp_worker_data);
-	if (!worker_data) {
-		retval = -ENOMEM;
-		goto exit_unregister;
-	}
 
 	cooling_dev = thermal_cooling_device_register("intel_powerclamp", NULL,
-						&powerclamp_cooling_ops);
-	if (IS_ERR(cooling_dev)) {
-		retval = -ENODEV;
-		goto exit_free_thread;
-	}
+						      &powerclamp_cooling_ops);
+	if (IS_ERR(cooling_dev))
+		return -ENODEV;
 
 	if (!duration)
-		duration = jiffies_to_msecs(DEFAULT_DURATION_JIFFIES);
+		duration = jiffies_to_usecs(DEFAULT_DURATION_JIFFIES);
 
 	powerclamp_create_debug_files();
 
 	return 0;
-
-exit_free_thread:
-	free_percpu(worker_data);
-exit_unregister:
-	cpuhp_remove_state_nocalls(hp_state);
-exit_free:
-	bitmap_free(cpu_clamping_mask);
-	return retval;
 }
 module_init(powerclamp_init);
 
 static void __exit powerclamp_exit(void)
 {
+	mutex_lock(&powerclamp_lock);
 	end_power_clamp();
-	cpuhp_remove_state_nocalls(hp_state);
-	free_percpu(worker_data);
+	mutex_unlock(&powerclamp_lock);
+
 	thermal_cooling_device_unregister(cooling_dev);
-	bitmap_free(cpu_clamping_mask);
 
 	cancel_delayed_work_sync(&poll_pkg_cstate_work);
 	debugfs_remove_recursive(debug_dir);
+
+	if (cpumask_available(idle_injection_cpu_mask))
+		free_cpumask_var(idle_injection_cpu_mask);
 }
 module_exit(powerclamp_exit);
 
+MODULE_IMPORT_NS(IDLE_INJECT);
+
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>");
 MODULE_AUTHOR("Jacob Pan <jacob.jun.pan@linux.intel.com>");
author	Rafael J. Wysocki <rafael.j.wysocki@intel.com>	2023-02-15 17:18:08 +0100
committer	Rafael J. Wysocki <rafael.j.wysocki@intel.com>	2023-02-15 17:18:08 +0100
commit	badf1f90502d3fc627a18880dfafd8c636699baf (patch)
tree	d069f30768766fa721b6f311351de2e0df53f8c1 /drivers/thermal/intel/intel_powerclamp.c
parent	c3bd6d539f34784b235c7070edba978f67516372 (diff)
parent	fef1f0be10c61dd16fd370964c316c399483448f (diff)
download	lwn-badf1f90502d3fc627a18880dfafd8c636699baf.tar.gz lwn-badf1f90502d3fc627a18880dfafd8c636699baf.zip