aboutsummaryrefslogtreecommitdiff
path: root/kernel/sched/fair.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sched/fair.c')
-rw-r--r--kernel/sched/fair.c563
1 files changed, 552 insertions, 11 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 9d9bab5919b..6baa8c84aa8 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -31,9 +31,20 @@
#include <linux/task_work.h>
#include <trace/events/sched.h>
+#ifdef CONFIG_HMP_VARIABLE_SCALE
+#include <linux/sysfs.h>
+#include <linux/vmalloc.h>
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+/* Include cpufreq header to add a notifier so that cpu frequency
+ * scaling can track the current CPU frequency
+ */
+#include <linux/cpufreq.h>
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
+#endif /* CONFIG_HMP_VARIABLE_SCALE */
#include "sched.h"
+
/*
* Targeted preemption latency for CPU-bound tasks:
* (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds)
@@ -1200,8 +1211,95 @@ static u32 __compute_runnable_contrib(u64 n)
return contrib + runnable_avg_yN_sum[n];
}
-/*
- * We can represent the historical contribution to runnable average as the
+#ifdef CONFIG_HMP_VARIABLE_SCALE
+
+#define HMP_VARIABLE_SCALE_SHIFT 16ULL
+struct hmp_global_attr {
+ struct attribute attr;
+ ssize_t (*show)(struct kobject *kobj,
+ struct attribute *attr, char *buf);
+ ssize_t (*store)(struct kobject *a, struct attribute *b,
+ const char *c, size_t count);
+ int *value;
+ int (*to_sysfs)(int);
+ int (*from_sysfs)(int);
+};
+
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+#define HMP_DATA_SYSFS_MAX 4
+#else
+#define HMP_DATA_SYSFS_MAX 3
+#endif
+
+struct hmp_data_struct {
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+ int freqinvar_load_scale_enabled;
+#endif
+ int multiplier; /* used to scale the time delta */
+ struct attribute_group attr_group;
+ struct attribute *attributes[HMP_DATA_SYSFS_MAX + 1];
+ struct hmp_global_attr attr[HMP_DATA_SYSFS_MAX];
+} hmp_data;
+
+static u64 hmp_variable_scale_convert(u64 delta);
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+/* Frequency-Invariant Load Modification:
+ * Loads are calculated as in PJT's patch however we also scale the current
+ * contribution in line with the frequency of the CPU that the task was
+ * executed on.
+ * In this version, we use a simple linear scale derived from the maximum
+ * frequency reported by CPUFreq. As an example:
+ *
+ * Consider that we ran a task for 100% of the previous interval.
+ *
+ * Our CPU was under asynchronous frequency control through one of the
+ * CPUFreq governors.
+ *
+ * The CPUFreq governor reports that it is able to scale the CPU between
+ * 500MHz and 1GHz.
+ *
+ * During the period, the CPU was running at 1GHz.
+ *
+ * In this case, our load contribution for that period is calculated as
+ * 1 * (number_of_active_microseconds)
+ *
+ * This results in our task being able to accumulate maximum load as normal.
+ *
+ *
+ * Consider now that our CPU was executing at 500MHz.
+ *
+ * We now scale the load contribution such that it is calculated as
+ * 0.5 * (number_of_active_microseconds)
+ *
+ * Our task can only record 50% maximum load during this period.
+ *
+ * This represents the task consuming 50% of the CPU's *possible* compute
+ * capacity. However the task did consume 100% of the CPU's *available*
+ * compute capacity which is the value seen by the CPUFreq governor and
+ * user-side CPU Utilization tools.
+ *
+ * Restricting tracked load to be scaled by the CPU's frequency accurately
+ * represents the consumption of possible compute capacity and allows the
+ * HMP migration's simple threshold migration strategy to interact more
+ * predictably with CPUFreq's asynchronous compute capacity changes.
+ */
+#define SCHED_FREQSCALE_SHIFT 10
+struct cpufreq_extents {
+ u32 curr_scale;
+ u32 min;
+ u32 max;
+ u32 flags;
+};
+/* Flag set when the governor in use only allows one frequency.
+ * Disables scaling.
+ */
+#define SCHED_LOAD_FREQINVAR_SINGLEFREQ 0x01
+
+static struct cpufreq_extents freq_scale[CONFIG_NR_CPUS];
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
+#endif /* CONFIG_HMP_VARIABLE_SCALE */
+
+/* We can represent the historical contribution to runnable average as the
* coefficients of a geometric series. To do this we sub-divide our runnable
* history into segments of approximately 1ms (1024us); label the segment that
* occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g.
@@ -1231,13 +1329,23 @@ static u32 __compute_runnable_contrib(u64 n)
static __always_inline int __update_entity_runnable_avg(u64 now,
struct sched_avg *sa,
int runnable,
- int running)
+ int running,
+ int cpu)
{
u64 delta, periods;
u32 runnable_contrib;
int delta_w, decayed = 0;
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+ u64 scaled_delta;
+ u32 scaled_runnable_contrib;
+ int scaled_delta_w;
+ u32 curr_scale = 1024;
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
delta = now - sa->last_runnable_update;
+#ifdef CONFIG_HMP_VARIABLE_SCALE
+ delta = hmp_variable_scale_convert(delta);
+#endif
/*
* This should only happen when time goes backwards, which it
* unfortunately does during sched clock init when we swap over to TSC.
@@ -1256,6 +1364,12 @@ static __always_inline int __update_entity_runnable_avg(u64 now,
return 0;
sa->last_runnable_update = now;
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+ /* retrieve scale factor for load */
+ if (hmp_data.freqinvar_load_scale_enabled)
+ curr_scale = freq_scale[cpu].curr_scale;
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
+
/* delta_w is the amount already accumulated against our next period */
delta_w = sa->runnable_avg_period % 1024;
if (delta + delta_w >= 1024) {
@@ -1268,10 +1382,20 @@ static __always_inline int __update_entity_runnable_avg(u64 now,
* period and accrue it.
*/
delta_w = 1024 - delta_w;
+ /* scale runnable time if necessary */
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+ scaled_delta_w = (delta_w * curr_scale)
+ >> SCHED_FREQSCALE_SHIFT;
+ if (runnable)
+ sa->runnable_avg_sum += scaled_delta_w;
+ if (running)
+ sa->usage_avg_sum += scaled_delta_w;
+#else
if (runnable)
sa->runnable_avg_sum += delta_w;
if (running)
sa->usage_avg_sum += delta_w;
+#endif /* #ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
sa->runnable_avg_period += delta_w;
delta -= delta_w;
@@ -1279,27 +1403,49 @@ static __always_inline int __update_entity_runnable_avg(u64 now,
/* Figure out how many additional periods this update spans */
periods = delta / 1024;
delta %= 1024;
-
+ /* decay the load we have accumulated so far */
sa->runnable_avg_sum = decay_load(sa->runnable_avg_sum,
periods + 1);
sa->runnable_avg_period = decay_load(sa->runnable_avg_period,
periods + 1);
sa->usage_avg_sum = decay_load(sa->usage_avg_sum, periods + 1);
-
+ /* add the contribution from this period */
/* Efficiently calculate \sum (1..n_period) 1024*y^i */
runnable_contrib = __compute_runnable_contrib(periods);
+ /* Apply load scaling if necessary.
+ * Note that multiplying the whole series is same as
+ * multiplying all terms
+ */
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+ scaled_runnable_contrib = (runnable_contrib * curr_scale)
+ >> SCHED_FREQSCALE_SHIFT;
+ if (runnable)
+ sa->runnable_avg_sum += scaled_runnable_contrib;
+ if (running)
+ sa->usage_avg_sum += scaled_runnable_contrib;
+#else
if (runnable)
sa->runnable_avg_sum += runnable_contrib;
if (running)
sa->usage_avg_sum += runnable_contrib;
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
sa->runnable_avg_period += runnable_contrib;
}
/* Remainder of delta accrued against u_0` */
+ /* scale if necessary */
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+ scaled_delta = ((delta * curr_scale) >> SCHED_FREQSCALE_SHIFT);
+ if (runnable)
+ sa->runnable_avg_sum += scaled_delta;
+ if (running)
+ sa->usage_avg_sum += scaled_delta;
+#else
if (runnable)
sa->runnable_avg_sum += delta;
if (running)
sa->usage_avg_sum += delta;
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
sa->runnable_avg_period += delta;
return decayed;
@@ -1467,7 +1613,11 @@ static inline void update_entity_load_avg(struct sched_entity *se,
struct cfs_rq *cfs_rq = cfs_rq_of(se);
long contrib_delta;
u64 now;
+ int cpu = -1; /* not used in normal case */
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+ cpu = cfs_rq->rq->cpu;
+#endif
/*
* For a group entity we need to use their owned cfs_rq_clock_task() in
* case they are the parent of a throttled hierarchy.
@@ -1478,7 +1628,7 @@ static inline void update_entity_load_avg(struct sched_entity *se,
now = cfs_rq_clock_task(group_cfs_rq(se));
if (!__update_entity_runnable_avg(now, &se->avg, se->on_rq,
- cfs_rq->curr == se))
+ cfs_rq->curr == se, cpu))
return;
contrib_delta = __update_entity_load_avg_contrib(se);
@@ -1523,8 +1673,13 @@ static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update)
static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
{
u32 contrib;
+ int cpu = -1; /* not used in normal case */
+
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+ cpu = rq->cpu;
+#endif
__update_entity_runnable_avg(rq->clock_task, &rq->avg, runnable,
- runnable);
+ runnable, cpu);
__update_tg_runnable_avg(&rq->avg, &rq->cfs);
contrib = rq->avg.runnable_avg_sum * scale_load_down(1024);
contrib /= (rq->avg.runnable_avg_period + 1);
@@ -3475,6 +3630,244 @@ static inline void hmp_next_down_delay(struct sched_entity *se, int cpu)
se->avg.hmp_last_down_migration = cfs_rq_clock_task(cfs_rq);
se->avg.hmp_last_up_migration = 0;
}
+
+#ifdef CONFIG_HMP_VARIABLE_SCALE
+/*
+ * Heterogenous multiprocessor (HMP) optimizations
+ *
+ * These functions allow to change the growing speed of the load_avg_ratio
+ * by default it goes from 0 to 0.5 in LOAD_AVG_PERIOD = 32ms
+ * This can now be changed with /sys/kernel/hmp/load_avg_period_ms.
+ *
+ * These functions also allow to change the up and down threshold of HMP
+ * using /sys/kernel/hmp/{up,down}_threshold.
+ * Both must be between 0 and 1023. The threshold that is compared
+ * to the load_avg_ratio is up_threshold/1024 and down_threshold/1024.
+ *
+ * For instance, if load_avg_period = 64 and up_threshold = 512, an idle
+ * task with a load of 0 will reach the threshold after 64ms of busy loop.
+ *
+ * Changing load_avg_periods_ms has the same effect than changing the
+ * default scaling factor Y=1002/1024 in the load_avg_ratio computation to
+ * (1002/1024.0)^(LOAD_AVG_PERIOD/load_avg_period_ms), but the last one
+ * could trigger overflows.
+ * For instance, with Y = 1023/1024 in __update_task_entity_contrib()
+ * "contrib = se->avg.runnable_avg_sum * scale_load_down(se->load.weight);"
+ * could be overflowed for a weight > 2^12 even is the load_avg_contrib
+ * should still be a 32bits result. This would not happen by multiplicating
+ * delta time by 1/22 and setting load_avg_period_ms = 706.
+ */
+
+/*
+ * By scaling the delta time it end-up increasing or decrease the
+ * growing speed of the per entity load_avg_ratio
+ * The scale factor hmp_data.multiplier is a fixed point
+ * number: (32-HMP_VARIABLE_SCALE_SHIFT).HMP_VARIABLE_SCALE_SHIFT
+ */
+static u64 hmp_variable_scale_convert(u64 delta)
+{
+ u64 high = delta >> 32ULL;
+ u64 low = delta & 0xffffffffULL;
+ low *= hmp_data.multiplier;
+ high *= hmp_data.multiplier;
+ return (low >> HMP_VARIABLE_SCALE_SHIFT)
+ + (high << (32ULL - HMP_VARIABLE_SCALE_SHIFT));
+}
+
+static ssize_t hmp_show(struct kobject *kobj,
+ struct attribute *attr, char *buf)
+{
+ ssize_t ret = 0;
+ struct hmp_global_attr *hmp_attr =
+ container_of(attr, struct hmp_global_attr, attr);
+ int temp = *(hmp_attr->value);
+ if (hmp_attr->to_sysfs != NULL)
+ temp = hmp_attr->to_sysfs(temp);
+ ret = sprintf(buf, "%d\n", temp);
+ return ret;
+}
+
+static ssize_t hmp_store(struct kobject *a, struct attribute *attr,
+ const char *buf, size_t count)
+{
+ int temp;
+ ssize_t ret = count;
+ struct hmp_global_attr *hmp_attr =
+ container_of(attr, struct hmp_global_attr, attr);
+ char *str = vmalloc(count + 1);
+ if (str == NULL)
+ return -ENOMEM;
+ memcpy(str, buf, count);
+ str[count] = 0;
+ if (sscanf(str, "%d", &temp) < 1)
+ ret = -EINVAL;
+ else {
+ if (hmp_attr->from_sysfs != NULL)
+ temp = hmp_attr->from_sysfs(temp);
+ if (temp < 0)
+ ret = -EINVAL;
+ else
+ *(hmp_attr->value) = temp;
+ }
+ vfree(str);
+ return ret;
+}
+
+static int hmp_period_tofrom_sysfs(int value)
+{
+ return (LOAD_AVG_PERIOD << HMP_VARIABLE_SCALE_SHIFT) / value;
+}
+
+/* max value for threshold is 1024 */
+static int hmp_theshold_from_sysfs(int value)
+{
+ if (value > 1024)
+ return -1;
+ return value;
+}
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+/* freqinvar control is only 0,1 off/on */
+static int hmp_freqinvar_from_sysfs(int value)
+{
+ if (value < 0 || value > 1)
+ return -1;
+ return value;
+}
+#endif
+static void hmp_attr_add(
+ const char *name,
+ int *value,
+ int (*to_sysfs)(int),
+ int (*from_sysfs)(int))
+{
+ int i = 0;
+ while (hmp_data.attributes[i] != NULL) {
+ i++;
+ if (i >= HMP_DATA_SYSFS_MAX)
+ return;
+ }
+ hmp_data.attr[i].attr.mode = 0644;
+ hmp_data.attr[i].show = hmp_show;
+ hmp_data.attr[i].store = hmp_store;
+ hmp_data.attr[i].attr.name = name;
+ hmp_data.attr[i].value = value;
+ hmp_data.attr[i].to_sysfs = to_sysfs;
+ hmp_data.attr[i].from_sysfs = from_sysfs;
+ hmp_data.attributes[i] = &hmp_data.attr[i].attr;
+ hmp_data.attributes[i + 1] = NULL;
+}
+
+static int hmp_attr_init(void)
+{
+ int ret;
+ memset(&hmp_data, sizeof(hmp_data), 0);
+ /* by default load_avg_period_ms == LOAD_AVG_PERIOD
+ * meaning no change
+ */
+ hmp_data.multiplier = hmp_period_tofrom_sysfs(LOAD_AVG_PERIOD);
+
+ hmp_attr_add("load_avg_period_ms",
+ &hmp_data.multiplier,
+ hmp_period_tofrom_sysfs,
+ hmp_period_tofrom_sysfs);
+ hmp_attr_add("up_threshold",
+ &hmp_up_threshold,
+ NULL,
+ hmp_theshold_from_sysfs);
+ hmp_attr_add("down_threshold",
+ &hmp_down_threshold,
+ NULL,
+ hmp_theshold_from_sysfs);
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+ /* default frequency-invariant scaling ON */
+ hmp_data.freqinvar_load_scale_enabled = 1;
+ hmp_attr_add("frequency_invariant_load_scale",
+ &hmp_data.freqinvar_load_scale_enabled,
+ NULL,
+ hmp_freqinvar_from_sysfs);
+#endif
+ hmp_data.attr_group.name = "hmp";
+ hmp_data.attr_group.attrs = hmp_data.attributes;
+ ret = sysfs_create_group(kernel_kobj,
+ &hmp_data.attr_group);
+ return 0;
+}
+late_initcall(hmp_attr_init);
+#endif /* CONFIG_HMP_VARIABLE_SCALE */
+
+static inline unsigned int hmp_domain_min_load(struct hmp_domain *hmpd,
+ int *min_cpu)
+{
+ int cpu;
+ int min_load = INT_MAX;
+ int min_cpu_temp = NR_CPUS;
+
+ for_each_cpu_mask(cpu, hmpd->cpus) {
+ if (cpu_rq(cpu)->cfs.tg_load_contrib < min_load) {
+ min_load = cpu_rq(cpu)->cfs.tg_load_contrib;
+ min_cpu_temp = cpu;
+ }
+ }
+
+ if (min_cpu)
+ *min_cpu = min_cpu_temp;
+
+ return min_load;
+}
+
+/*
+ * Calculate the task starvation
+ * This is the ratio of actually running time vs. runnable time.
+ * If the two are equal the task is getting the cpu time it needs or
+ * it is alone on the cpu and the cpu is fully utilized.
+ */
+static inline unsigned int hmp_task_starvation(struct sched_entity *se)
+{
+ u32 starvation;
+
+ starvation = se->avg.usage_avg_sum * scale_load_down(NICE_0_LOAD);
+ starvation /= (se->avg.runnable_avg_sum + 1);
+
+ return scale_load(starvation);
+}
+
+static inline unsigned int hmp_offload_down(int cpu, struct sched_entity *se)
+{
+ int min_usage;
+ int dest_cpu = NR_CPUS;
+
+ if (hmp_cpu_is_slowest(cpu))
+ return NR_CPUS;
+
+ /* Is the current domain fully loaded? */
+ /* load < ~94% */
+ min_usage = hmp_domain_min_load(hmp_cpu_domain(cpu), NULL);
+ if (min_usage < NICE_0_LOAD-64)
+ return NR_CPUS;
+
+ /* Is the cpu oversubscribed? */
+ /* load < ~194% */
+ if (cpu_rq(cpu)->cfs.tg_load_contrib < 2*NICE_0_LOAD-64)
+ return NR_CPUS;
+
+ /* Is the task alone on the cpu? */
+ if (cpu_rq(cpu)->cfs.nr_running < 2)
+ return NR_CPUS;
+
+ /* Is the task actually starving? */
+ if (hmp_task_starvation(se) > 768) /* <25% waiting */
+ return NR_CPUS;
+
+ /* Does the slower domain have spare cycles? */
+ min_usage = hmp_domain_min_load(hmp_slower_domain(cpu), &dest_cpu);
+ /* load > 50% */
+ if (min_usage > NICE_0_LOAD/2)
+ return NR_CPUS;
+
+ if (cpumask_test_cpu(dest_cpu, &hmp_slower_domain(cpu)->cpus))
+ return dest_cpu;
+ return NR_CPUS;
+}
#endif /* CONFIG_SCHED_HMP */
/*
@@ -5875,10 +6268,14 @@ static unsigned int hmp_up_migration(int cpu, struct sched_entity *se)
< hmp_next_up_threshold)
return 0;
- if (cpumask_intersects(&hmp_faster_domain(cpu)->cpus,
- tsk_cpus_allowed(p))
- && se->avg.load_avg_ratio > hmp_up_threshold) {
- return 1;
+ if (se->avg.load_avg_ratio > hmp_up_threshold) {
+ /* Target domain load < ~94% */
+ if (hmp_domain_min_load(hmp_faster_domain(cpu), NULL)
+ > NICE_0_LOAD-64)
+ return 0;
+ if (cpumask_intersects(&hmp_faster_domain(cpu)->cpus,
+ tsk_cpus_allowed(p)))
+ return 1;
}
return 0;
}
@@ -6101,6 +6498,21 @@ static void hmp_force_up_migration(int this_cpu)
hmp_next_up_delay(&p->se, target->push_cpu);
}
}
+ if (!force && !target->active_balance) {
+ /*
+ * For now we just check the currently running task.
+ * Selecting the lightest task for offloading will
+ * require extensive book keeping.
+ */
+ target->push_cpu = hmp_offload_down(cpu, curr);
+ if (target->push_cpu < NR_CPUS) {
+ target->active_balance = 1;
+ target->migrate_task = p;
+ force = 1;
+ trace_sched_hmp_migrate(p, target->push_cpu, 2);
+ hmp_next_down_delay(&p->se, target->push_cpu);
+ }
+ }
raw_spin_unlock_irqrestore(&target->lock, flags);
if (force)
stop_one_cpu_nowait(cpu_of(target),
@@ -6632,3 +7044,132 @@ __init void init_sched_fair_class(void)
#endif /* SMP */
}
+
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+static u32 cpufreq_calc_scale(u32 min, u32 max, u32 curr)
+{
+ u32 result = curr / max;
+ return result;
+}
+
+/* Called when the CPU Frequency is changed.
+ * Once for each CPU.
+ */
+static int cpufreq_callback(struct notifier_block *nb,
+ unsigned long val, void *data)
+{
+ struct cpufreq_freqs *freq = data;
+ int cpu = freq->cpu;
+ struct cpufreq_extents *extents;
+
+ if (freq->flags & CPUFREQ_CONST_LOOPS)
+ return NOTIFY_OK;
+
+ if (val != CPUFREQ_POSTCHANGE)
+ return NOTIFY_OK;
+
+ /* if dynamic load scale is disabled, set the load scale to 1.0 */
+ if (!hmp_data.freqinvar_load_scale_enabled) {
+ freq_scale[cpu].curr_scale = 1024;
+ return NOTIFY_OK;
+ }
+
+ extents = &freq_scale[cpu];
+ if (extents->flags & SCHED_LOAD_FREQINVAR_SINGLEFREQ) {
+ /* If our governor was recognised as a single-freq governor,
+ * use 1.0
+ */
+ extents->curr_scale = 1024;
+ } else {
+ extents->curr_scale = cpufreq_calc_scale(extents->min,
+ extents->max, freq->new);
+ }
+
+ return NOTIFY_OK;
+}
+
+/* Called when the CPUFreq governor is changed.
+ * Only called for the CPUs which are actually changed by the
+ * userspace.
+ */
+static int cpufreq_policy_callback(struct notifier_block *nb,
+ unsigned long event, void *data)
+{
+ struct cpufreq_policy *policy = data;
+ struct cpufreq_extents *extents;
+ int cpu, singleFreq = 0;
+ static const char performance_governor[] = "performance";
+ static const char powersave_governor[] = "powersave";
+
+ if (event == CPUFREQ_START)
+ return 0;
+
+ if (event != CPUFREQ_INCOMPATIBLE)
+ return 0;
+
+ /* CPUFreq governors do not accurately report the range of
+ * CPU Frequencies they will choose from.
+ * We recognise performance and powersave governors as
+ * single-frequency only.
+ */
+ if (!strncmp(policy->governor->name, performance_governor,
+ strlen(performance_governor)) ||
+ !strncmp(policy->governor->name, powersave_governor,
+ strlen(powersave_governor)))
+ singleFreq = 1;
+
+ /* Make sure that all CPUs impacted by this policy are
+ * updated since we will only get a notification when the
+ * user explicitly changes the policy on a CPU.
+ */
+ for_each_cpu(cpu, policy->cpus) {
+ extents = &freq_scale[cpu];
+ extents->max = policy->max >> SCHED_FREQSCALE_SHIFT;
+ extents->min = policy->min >> SCHED_FREQSCALE_SHIFT;
+ if (!hmp_data.freqinvar_load_scale_enabled) {
+ extents->curr_scale = 1024;
+ } else if (singleFreq) {
+ extents->flags |= SCHED_LOAD_FREQINVAR_SINGLEFREQ;
+ extents->curr_scale = 1024;
+ } else {
+ extents->flags &= ~SCHED_LOAD_FREQINVAR_SINGLEFREQ;
+ extents->curr_scale = cpufreq_calc_scale(extents->min,
+ extents->max, policy->cur);
+ }
+ }
+
+ return 0;
+}
+
+static struct notifier_block cpufreq_notifier = {
+ .notifier_call = cpufreq_callback,
+};
+static struct notifier_block cpufreq_policy_notifier = {
+ .notifier_call = cpufreq_policy_callback,
+};
+
+static int __init register_sched_cpufreq_notifier(void)
+{
+ int ret = 0;
+
+ /* init safe defaults since there are no policies at registration */
+ for (ret = 0; ret < CONFIG_NR_CPUS; ret++) {
+ /* safe defaults */
+ freq_scale[ret].max = 1024;
+ freq_scale[ret].min = 1024;
+ freq_scale[ret].curr_scale = 1024;
+ }
+
+ pr_info("sched: registering cpufreq notifiers for scale-invariant loads\n");
+ ret = cpufreq_register_notifier(&cpufreq_policy_notifier,
+ CPUFREQ_POLICY_NOTIFIER);
+
+ if (ret != -EINVAL)
+ ret = cpufreq_register_notifier(&cpufreq_notifier,
+ CPUFREQ_TRANSITION_NOTIFIER);
+
+ return ret;
+}
+
+core_initcall(register_sched_cpufreq_notifier);
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */