summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--drivers/cpufreq/cpufreq.c37
-rw-r--r--drivers/cpufreq/cpufreq_conservative.c10
-rw-r--r--drivers/cpufreq/cpufreq_ondemand.c36
-rw-r--r--drivers/cpufreq/cpufreq_performance.c18
-rw-r--r--drivers/cpufreq/cpufreq_powersave.c10
-rw-r--r--drivers/cpufreq/cpufreq_userspace.c10
-rw-r--r--drivers/cpufreq/powernv-cpufreq.c116
-rw-r--r--include/linux/cpufreq.h25
-rw-r--r--include/trace/events/power.h22
-rw-r--r--kernel/trace/power-traces.c1
10 files changed, 162 insertions, 123 deletions
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index e979ec78b695..34b17447e0d1 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -959,6 +959,11 @@ static int cpufreq_add_dev_interface(struct cpufreq_policy *policy)
return cpufreq_add_dev_symlink(policy);
}
+__weak struct cpufreq_governor *cpufreq_default_governor(void)
+{
+ return NULL;
+}
+
static int cpufreq_init_policy(struct cpufreq_policy *policy)
{
struct cpufreq_governor *gov = NULL;
@@ -968,11 +973,14 @@ static int cpufreq_init_policy(struct cpufreq_policy *policy)
/* Update governor of new_policy to the governor used before hotplug */
gov = find_governor(policy->last_governor);
- if (gov)
+ if (gov) {
pr_debug("Restoring governor %s for cpu %d\n",
policy->governor->name, policy->cpu);
- else
- gov = CPUFREQ_DEFAULT_GOVERNOR;
+ } else {
+ gov = cpufreq_default_governor();
+ if (!gov)
+ return -ENODATA;
+ }
new_policy.governor = gov;
@@ -1920,21 +1928,16 @@ int cpufreq_driver_target(struct cpufreq_policy *policy,
}
EXPORT_SYMBOL_GPL(cpufreq_driver_target);
+__weak struct cpufreq_governor *cpufreq_fallback_governor(void)
+{
+ return NULL;
+}
+
static int __cpufreq_governor(struct cpufreq_policy *policy,
unsigned int event)
{
int ret;
- /* Only must be defined when default governor is known to have latency
- restrictions, like e.g. conservative or ondemand.
- That this is the case is already ensured in Kconfig
- */
-#ifdef CONFIG_CPU_FREQ_GOV_PERFORMANCE
- struct cpufreq_governor *gov = &cpufreq_gov_performance;
-#else
- struct cpufreq_governor *gov = NULL;
-#endif
-
/* Don't start any governor operations if we are entering suspend */
if (cpufreq_suspended)
return 0;
@@ -1948,12 +1951,14 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
if (policy->governor->max_transition_latency &&
policy->cpuinfo.transition_latency >
policy->governor->max_transition_latency) {
- if (!gov)
- return -EINVAL;
- else {
+ struct cpufreq_governor *gov = cpufreq_fallback_governor();
+
+ if (gov) {
pr_warn("%s governor failed, too long transition latency of HW, fallback to %s governor\n",
policy->governor->name, gov->name);
policy->governor = gov;
+ } else {
+ return -EINVAL;
}
}
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index 606ad74abe6e..8504a70a4785 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -26,10 +26,7 @@ static DEFINE_PER_CPU(struct cs_cpu_dbs_info_s, cs_cpu_dbs_info);
static int cs_cpufreq_governor_dbs(struct cpufreq_policy *policy,
unsigned int event);
-#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE
-static
-#endif
-struct cpufreq_governor cpufreq_gov_conservative = {
+static struct cpufreq_governor cpufreq_gov_conservative = {
.name = "conservative",
.governor = cs_cpufreq_governor_dbs,
.max_transition_latency = TRANSITION_LATENCY_LIMIT,
@@ -399,6 +396,11 @@ MODULE_DESCRIPTION("'cpufreq_conservative' - A dynamic cpufreq governor for "
MODULE_LICENSE("GPL");
#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE
+struct cpufreq_governor *cpufreq_default_governor(void)
+{
+ return &cpufreq_gov_conservative;
+}
+
fs_initcall(cpufreq_gov_dbs_init);
#else
module_init(cpufreq_gov_dbs_init);
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index eae51070c034..929e193ac1c1 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -31,9 +31,7 @@ static DEFINE_PER_CPU(struct od_cpu_dbs_info_s, od_cpu_dbs_info);
static struct od_ops od_ops;
-#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND
static struct cpufreq_governor cpufreq_gov_ondemand;
-#endif
static unsigned int default_powersave_bias;
@@ -554,6 +552,19 @@ static struct common_dbs_data od_dbs_cdata = {
.mutex = __MUTEX_INITIALIZER(od_dbs_cdata.mutex),
};
+static int od_cpufreq_governor_dbs(struct cpufreq_policy *policy,
+ unsigned int event)
+{
+ return cpufreq_governor_dbs(policy, &od_dbs_cdata, event);
+}
+
+static struct cpufreq_governor cpufreq_gov_ondemand = {
+ .name = "ondemand",
+ .governor = od_cpufreq_governor_dbs,
+ .max_transition_latency = TRANSITION_LATENCY_LIMIT,
+ .owner = THIS_MODULE,
+};
+
static void od_set_powersave_bias(unsigned int powersave_bias)
{
struct cpufreq_policy *policy;
@@ -605,22 +616,6 @@ void od_unregister_powersave_bias_handler(void)
}
EXPORT_SYMBOL_GPL(od_unregister_powersave_bias_handler);
-static int od_cpufreq_governor_dbs(struct cpufreq_policy *policy,
- unsigned int event)
-{
- return cpufreq_governor_dbs(policy, &od_dbs_cdata, event);
-}
-
-#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND
-static
-#endif
-struct cpufreq_governor cpufreq_gov_ondemand = {
- .name = "ondemand",
- .governor = od_cpufreq_governor_dbs,
- .max_transition_latency = TRANSITION_LATENCY_LIMIT,
- .owner = THIS_MODULE,
-};
-
static int __init cpufreq_gov_dbs_init(void)
{
return cpufreq_register_governor(&cpufreq_gov_ondemand);
@@ -638,6 +633,11 @@ MODULE_DESCRIPTION("'cpufreq_ondemand' - A dynamic cpufreq governor for "
MODULE_LICENSE("GPL");
#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND
+struct cpufreq_governor *cpufreq_default_governor(void)
+{
+ return &cpufreq_gov_ondemand;
+}
+
fs_initcall(cpufreq_gov_dbs_init);
#else
module_init(cpufreq_gov_dbs_init);
diff --git a/drivers/cpufreq/cpufreq_performance.c b/drivers/cpufreq/cpufreq_performance.c
index cf117deb39b1..af9f4b96f5a8 100644
--- a/drivers/cpufreq/cpufreq_performance.c
+++ b/drivers/cpufreq/cpufreq_performance.c
@@ -33,10 +33,7 @@ static int cpufreq_governor_performance(struct cpufreq_policy *policy,
return 0;
}
-#ifdef CONFIG_CPU_FREQ_GOV_PERFORMANCE_MODULE
-static
-#endif
-struct cpufreq_governor cpufreq_gov_performance = {
+static struct cpufreq_governor cpufreq_gov_performance = {
.name = "performance",
.governor = cpufreq_governor_performance,
.owner = THIS_MODULE,
@@ -52,6 +49,19 @@ static void __exit cpufreq_gov_performance_exit(void)
cpufreq_unregister_governor(&cpufreq_gov_performance);
}
+#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE
+struct cpufreq_governor *cpufreq_default_governor(void)
+{
+ return &cpufreq_gov_performance;
+}
+#endif
+#ifndef CONFIG_CPU_FREQ_GOV_PERFORMANCE_MODULE
+struct cpufreq_governor *cpufreq_fallback_governor(void)
+{
+ return &cpufreq_gov_performance;
+}
+#endif
+
MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>");
MODULE_DESCRIPTION("CPUfreq policy governor 'performance'");
MODULE_LICENSE("GPL");
diff --git a/drivers/cpufreq/cpufreq_powersave.c b/drivers/cpufreq/cpufreq_powersave.c
index e3b874c235ea..b8b400232a74 100644
--- a/drivers/cpufreq/cpufreq_powersave.c
+++ b/drivers/cpufreq/cpufreq_powersave.c
@@ -33,10 +33,7 @@ static int cpufreq_governor_powersave(struct cpufreq_policy *policy,
return 0;
}
-#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE
-static
-#endif
-struct cpufreq_governor cpufreq_gov_powersave = {
+static struct cpufreq_governor cpufreq_gov_powersave = {
.name = "powersave",
.governor = cpufreq_governor_powersave,
.owner = THIS_MODULE,
@@ -57,6 +54,11 @@ MODULE_DESCRIPTION("CPUfreq policy governor 'powersave'");
MODULE_LICENSE("GPL");
#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE
+struct cpufreq_governor *cpufreq_default_governor(void)
+{
+ return &cpufreq_gov_powersave;
+}
+
fs_initcall(cpufreq_gov_powersave_init);
#else
module_init(cpufreq_gov_powersave_init);
diff --git a/drivers/cpufreq/cpufreq_userspace.c b/drivers/cpufreq/cpufreq_userspace.c
index 4dbf1db16aca..4d16f45ee1da 100644
--- a/drivers/cpufreq/cpufreq_userspace.c
+++ b/drivers/cpufreq/cpufreq_userspace.c
@@ -89,10 +89,7 @@ static int cpufreq_governor_userspace(struct cpufreq_policy *policy,
return rc;
}
-#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE
-static
-#endif
-struct cpufreq_governor cpufreq_gov_userspace = {
+static struct cpufreq_governor cpufreq_gov_userspace = {
.name = "userspace",
.governor = cpufreq_governor_userspace,
.store_setspeed = cpufreq_set,
@@ -116,6 +113,11 @@ MODULE_DESCRIPTION("CPUfreq policy governor 'userspace'");
MODULE_LICENSE("GPL");
#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE
+struct cpufreq_governor *cpufreq_default_governor(void)
+{
+ return &cpufreq_gov_userspace;
+}
+
fs_initcall(cpufreq_gov_userspace_init);
#else
module_init(cpufreq_gov_userspace_init);
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 547890fd9572..1bbc10a54c59 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -28,6 +28,8 @@
#include <linux/of.h>
#include <linux/reboot.h>
#include <linux/slab.h>
+#include <linux/cpu.h>
+#include <trace/events/power.h>
#include <asm/cputhreads.h>
#include <asm/firmware.h>
@@ -42,13 +44,24 @@
static struct cpufreq_frequency_table powernv_freqs[POWERNV_MAX_PSTATES+1];
static bool rebooting, throttled, occ_reset;
+static unsigned int *core_to_chip_map;
+
+static const char * const throttle_reason[] = {
+ "No throttling",
+ "Power Cap",
+ "Processor Over Temperature",
+ "Power Supply Failure",
+ "Over Current",
+ "OCC Reset"
+};
static struct chip {
unsigned int id;
bool throttled;
+ bool restore;
+ u8 throttle_reason;
cpumask_t mask;
struct work_struct throttle;
- bool restore;
} *chips;
static int nr_chips;
@@ -312,13 +325,14 @@ static inline unsigned int get_nominal_index(void)
static void powernv_cpufreq_throttle_check(void *data)
{
unsigned int cpu = smp_processor_id();
+ unsigned int chip_id = core_to_chip_map[cpu_core_index_of_thread(cpu)];
unsigned long pmsr;
int pmsr_pmax, i;
pmsr = get_pmspr(SPRN_PMSR);
for (i = 0; i < nr_chips; i++)
- if (chips[i].id == cpu_to_chip_id(cpu))
+ if (chips[i].id == chip_id)
break;
/* Check for Pmax Capping */
@@ -328,17 +342,17 @@ static void powernv_cpufreq_throttle_check(void *data)
goto next;
chips[i].throttled = true;
if (pmsr_pmax < powernv_pstate_info.nominal)
- pr_crit("CPU %d on Chip %u has Pmax reduced below nominal frequency (%d < %d)\n",
- cpu, chips[i].id, pmsr_pmax,
- powernv_pstate_info.nominal);
- else
- pr_info("CPU %d on Chip %u has Pmax reduced below turbo frequency (%d < %d)\n",
- cpu, chips[i].id, pmsr_pmax,
- powernv_pstate_info.max);
+ pr_warn_once("CPU %d on Chip %u has Pmax reduced below nominal frequency (%d < %d)\n",
+ cpu, chips[i].id, pmsr_pmax,
+ powernv_pstate_info.nominal);
+ trace_powernv_throttle(chips[i].id,
+ throttle_reason[chips[i].throttle_reason],
+ pmsr_pmax);
} else if (chips[i].throttled) {
chips[i].throttled = false;
- pr_info("CPU %d on Chip %u has Pmax restored to %d\n", cpu,
- chips[i].id, pmsr_pmax);
+ trace_powernv_throttle(chips[i].id,
+ throttle_reason[chips[i].throttle_reason],
+ pmsr_pmax);
}
/* Check if Psafe_mode_active is set in PMSR. */
@@ -356,7 +370,7 @@ next:
if (throttled) {
pr_info("PMSR = %16lx\n", pmsr);
- pr_crit("CPU Frequency could be throttled\n");
+ pr_warn("CPU Frequency could be throttled\n");
}
}
@@ -423,18 +437,19 @@ void powernv_cpufreq_work_fn(struct work_struct *work)
{
struct chip *chip = container_of(work, struct chip, throttle);
unsigned int cpu;
- cpumask_var_t mask;
+ cpumask_t mask;
- smp_call_function_any(&chip->mask,
+ get_online_cpus();
+ cpumask_and(&mask, &chip->mask, cpu_online_mask);
+ smp_call_function_any(&mask,
powernv_cpufreq_throttle_check, NULL, 0);
if (!chip->restore)
- return;
+ goto out;
chip->restore = false;
- cpumask_copy(mask, &chip->mask);
- for_each_cpu_and(cpu, mask, cpu_online_mask) {
- int index, tcpu;
+ for_each_cpu(cpu, &mask) {
+ int index;
struct cpufreq_policy policy;
cpufreq_get_policy(&policy, cpu);
@@ -442,20 +457,12 @@ void powernv_cpufreq_work_fn(struct work_struct *work)
policy.cur,
CPUFREQ_RELATION_C, &index);
powernv_cpufreq_target_index(&policy, index);
- for_each_cpu(tcpu, policy.cpus)
- cpumask_clear_cpu(tcpu, mask);
+ cpumask_andnot(&mask, &mask, policy.cpus);
}
+out:
+ put_online_cpus();
}
-static char throttle_reason[][30] = {
- "No throttling",
- "Power Cap",
- "Processor Over Temperature",
- "Power Supply Failure",
- "Over Current",
- "OCC Reset"
- };
-
static int powernv_cpufreq_occ_msg(struct notifier_block *nb,
unsigned long msg_type, void *_msg)
{
@@ -481,7 +488,7 @@ static int powernv_cpufreq_occ_msg(struct notifier_block *nb,
*/
if (!throttled) {
throttled = true;
- pr_crit("CPU frequency is throttled for duration\n");
+ pr_warn("CPU frequency is throttled for duration\n");
}
break;
@@ -505,23 +512,18 @@ static int powernv_cpufreq_occ_msg(struct notifier_block *nb,
return 0;
}
- if (omsg.throttle_status &&
+ for (i = 0; i < nr_chips; i++)
+ if (chips[i].id == omsg.chip)
+ break;
+
+ if (omsg.throttle_status >= 0 &&
omsg.throttle_status <= OCC_MAX_THROTTLE_STATUS)
- pr_info("OCC: Chip %u Pmax reduced due to %s\n",
- (unsigned int)omsg.chip,
- throttle_reason[omsg.throttle_status]);
- else if (!omsg.throttle_status)
- pr_info("OCC: Chip %u %s\n", (unsigned int)omsg.chip,
- throttle_reason[omsg.throttle_status]);
- else
- return 0;
+ chips[i].throttle_reason = omsg.throttle_status;
- for (i = 0; i < nr_chips; i++)
- if (chips[i].id == omsg.chip) {
- if (!omsg.throttle_status)
- chips[i].restore = true;
- schedule_work(&chips[i].throttle);
- }
+ if (!omsg.throttle_status)
+ chips[i].restore = true;
+
+ schedule_work(&chips[i].throttle);
}
return 0;
}
@@ -556,29 +558,41 @@ static int init_chip_info(void)
unsigned int chip[256];
unsigned int cpu, i;
unsigned int prev_chip_id = UINT_MAX;
+ cpumask_t cpu_mask;
+ int ret = -ENOMEM;
+
+ core_to_chip_map = kcalloc(cpu_nr_cores(), sizeof(unsigned int),
+ GFP_KERNEL);
+ if (!core_to_chip_map)
+ goto out;
- for_each_possible_cpu(cpu) {
+ cpumask_copy(&cpu_mask, cpu_possible_mask);
+ for_each_cpu(cpu, &cpu_mask) {
unsigned int id = cpu_to_chip_id(cpu);
if (prev_chip_id != id) {
prev_chip_id = id;
chip[nr_chips++] = id;
}
+ core_to_chip_map[cpu_core_index_of_thread(cpu)] = id;
+ cpumask_andnot(&cpu_mask, &cpu_mask, cpu_sibling_mask(cpu));
}
- chips = kmalloc_array(nr_chips, sizeof(struct chip), GFP_KERNEL);
+ chips = kcalloc(nr_chips, sizeof(struct chip), GFP_KERNEL);
if (!chips)
- return -ENOMEM;
+ goto free_chip_map;
for (i = 0; i < nr_chips; i++) {
chips[i].id = chip[i];
- chips[i].throttled = false;
cpumask_copy(&chips[i].mask, cpumask_of_node(chip[i]));
INIT_WORK(&chips[i].throttle, powernv_cpufreq_work_fn);
- chips[i].restore = false;
}
return 0;
+free_chip_map:
+ kfree(core_to_chip_map);
+out:
+ return ret;
}
static int __init powernv_cpufreq_init(void)
@@ -612,6 +626,8 @@ static void __exit powernv_cpufreq_exit(void)
unregister_reboot_notifier(&powernv_cpufreq_reboot_nb);
opal_message_notifier_unregister(OPAL_MSG_OCC,
&powernv_cpufreq_opal_nb);
+ kfree(chips);
+ kfree(core_to_chip_map);
cpufreq_unregister_driver(&powernv_cpufreq_driver);
}
module_exit(powernv_cpufreq_exit);
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 88a4215125bc..d0bf555b6bbf 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -464,29 +464,8 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
int cpufreq_register_governor(struct cpufreq_governor *governor);
void cpufreq_unregister_governor(struct cpufreq_governor *governor);
-/* CPUFREQ DEFAULT GOVERNOR */
-/*
- * Performance governor is fallback governor if any other gov failed to auto
- * load due latency restrictions
- */
-#ifdef CONFIG_CPU_FREQ_GOV_PERFORMANCE
-extern struct cpufreq_governor cpufreq_gov_performance;
-#endif
-#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE
-#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_performance)
-#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE)
-extern struct cpufreq_governor cpufreq_gov_powersave;
-#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_powersave)
-#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE)
-extern struct cpufreq_governor cpufreq_gov_userspace;
-#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_userspace)
-#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND)
-extern struct cpufreq_governor cpufreq_gov_ondemand;
-#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_ondemand)
-#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE)
-extern struct cpufreq_governor cpufreq_gov_conservative;
-#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_conservative)
-#endif
+struct cpufreq_governor *cpufreq_default_governor(void);
+struct cpufreq_governor *cpufreq_fallback_governor(void);
/*********************************************************************
* FREQUENCY TABLE HELPERS *
diff --git a/include/trace/events/power.h b/include/trace/events/power.h
index 284244ebfe8d..19e50300ce7d 100644
--- a/include/trace/events/power.h
+++ b/include/trace/events/power.h
@@ -38,6 +38,28 @@ DEFINE_EVENT(cpu, cpu_idle,
TP_ARGS(state, cpu_id)
);
+TRACE_EVENT(powernv_throttle,
+
+ TP_PROTO(int chip_id, const char *reason, int pmax),
+
+ TP_ARGS(chip_id, reason, pmax),
+
+ TP_STRUCT__entry(
+ __field(int, chip_id)
+ __string(reason, reason)
+ __field(int, pmax)
+ ),
+
+ TP_fast_assign(
+ __entry->chip_id = chip_id;
+ __assign_str(reason, reason);
+ __entry->pmax = pmax;
+ ),
+
+ TP_printk("Chip %d Pmax %d %s", __entry->chip_id,
+ __entry->pmax, __get_str(reason))
+);
+
TRACE_EVENT(pstate_sample,
TP_PROTO(u32 core_busy,
diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c
index eb4220a132ec..81b87451c0ea 100644
--- a/kernel/trace/power-traces.c
+++ b/kernel/trace/power-traces.c
@@ -15,4 +15,5 @@
EXPORT_TRACEPOINT_SYMBOL_GPL(suspend_resume);
EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle);
+EXPORT_TRACEPOINT_SYMBOL_GPL(powernv_throttle);
generated by cgit v1.2.3 (git 2.46.0) at 2025-07-25 01:51:46 +0000