summaryrefslogtreecommitdiffstats
path: root/kernel/sched
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sched')
-rw-r--r--kernel/sched/core.c4
-rw-r--r--kernel/sched/cpufreq_schedutil.c82
-rw-r--r--kernel/sched/cputime.c27
-rw-r--r--kernel/sched/fair.c115
-rw-r--r--kernel/sched/sched-pelt.h13
-rw-r--r--kernel/sched/sched.h9
6 files changed, 124 insertions, 126 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0c443bb..c51147a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5775,7 +5775,7 @@ static void cpuset_cpu_active(void)
* cpuset configurations.
*/
}
- cpuset_update_active_cpus(true);
+ cpuset_update_active_cpus();
}
static int cpuset_cpu_inactive(unsigned int cpu)
@@ -5798,7 +5798,7 @@ static int cpuset_cpu_inactive(unsigned int cpu)
if (overflow)
return -EBUSY;
- cpuset_update_active_cpus(false);
+ cpuset_update_active_cpus();
} else {
num_cpus_frozen++;
partition_sched_domains(1, NULL, NULL);
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 54c5775..76877a6 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -61,6 +61,11 @@ struct sugov_cpu {
unsigned long util;
unsigned long max;
unsigned int flags;
+
+ /* The field below is for single-CPU policies only. */
+#ifdef CONFIG_NO_HZ_COMMON
+ unsigned long saved_idle_calls;
+#endif
};
static DEFINE_PER_CPU(struct sugov_cpu, sugov_cpu);
@@ -93,22 +98,23 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
{
struct cpufreq_policy *policy = sg_policy->policy;
+ if (sg_policy->next_freq == next_freq)
+ return;
+
+ if (sg_policy->next_freq > next_freq)
+ next_freq = (sg_policy->next_freq + next_freq) >> 1;
+
+ sg_policy->next_freq = next_freq;
sg_policy->last_freq_update_time = time;
if (policy->fast_switch_enabled) {
- if (sg_policy->next_freq == next_freq) {
- trace_cpu_frequency(policy->cur, smp_processor_id());
- return;
- }
- sg_policy->next_freq = next_freq;
next_freq = cpufreq_driver_fast_switch(policy, next_freq);
if (next_freq == CPUFREQ_ENTRY_INVALID)
return;
policy->cur = next_freq;
trace_cpu_frequency(next_freq, smp_processor_id());
- } else if (sg_policy->next_freq != next_freq) {
- sg_policy->next_freq = next_freq;
+ } else {
sg_policy->work_in_progress = true;
irq_work_queue(&sg_policy->irq_work);
}
@@ -192,6 +198,19 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util,
sg_cpu->iowait_boost >>= 1;
}
+#ifdef CONFIG_NO_HZ_COMMON
+static bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu)
+{
+ unsigned long idle_calls = tick_nohz_get_idle_calls();
+ bool ret = idle_calls == sg_cpu->saved_idle_calls;
+
+ sg_cpu->saved_idle_calls = idle_calls;
+ return ret;
+}
+#else
+static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
+#endif /* CONFIG_NO_HZ_COMMON */
+
static void sugov_update_single(struct update_util_data *hook, u64 time,
unsigned int flags)
{
@@ -200,6 +219,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
struct cpufreq_policy *policy = sg_policy->policy;
unsigned long util, max;
unsigned int next_f;
+ bool busy;
sugov_set_iowait_boost(sg_cpu, time, flags);
sg_cpu->last_update = time;
@@ -207,40 +227,37 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
if (!sugov_should_update_freq(sg_policy, time))
return;
+ busy = sugov_cpu_is_busy(sg_cpu);
+
if (flags & SCHED_CPUFREQ_RT_DL) {
next_f = policy->cpuinfo.max_freq;
} else {
sugov_get_util(&util, &max);
sugov_iowait_boost(sg_cpu, &util, &max);
next_f = get_next_freq(sg_policy, util, max);
+ /*
+ * Do not reduce the frequency if the CPU has not been idle
+ * recently, as the reduction is likely to be premature then.
+ */
+ if (busy && next_f < sg_policy->next_freq)
+ next_f = sg_policy->next_freq;
}
sugov_update_commit(sg_policy, time, next_f);
}
-static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
- unsigned long util, unsigned long max,
- unsigned int flags)
+static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu)
{
struct sugov_policy *sg_policy = sg_cpu->sg_policy;
struct cpufreq_policy *policy = sg_policy->policy;
- unsigned int max_f = policy->cpuinfo.max_freq;
u64 last_freq_update_time = sg_policy->last_freq_update_time;
+ unsigned long util = 0, max = 1;
unsigned int j;
- if (flags & SCHED_CPUFREQ_RT_DL)
- return max_f;
-
- sugov_iowait_boost(sg_cpu, &util, &max);
-
for_each_cpu(j, policy->cpus) {
- struct sugov_cpu *j_sg_cpu;
+ struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
unsigned long j_util, j_max;
s64 delta_ns;
- if (j == smp_processor_id())
- continue;
-
- j_sg_cpu = &per_cpu(sugov_cpu, j);
/*
* If the CPU utilization was last updated before the previous
* frequency update and the time elapsed between the last update
@@ -254,7 +271,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
continue;
}
if (j_sg_cpu->flags & SCHED_CPUFREQ_RT_DL)
- return max_f;
+ return policy->cpuinfo.max_freq;
j_util = j_sg_cpu->util;
j_max = j_sg_cpu->max;
@@ -289,7 +306,11 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time,
sg_cpu->last_update = time;
if (sugov_should_update_freq(sg_policy, time)) {
- next_f = sugov_next_freq_shared(sg_cpu, util, max, flags);
+ if (flags & SCHED_CPUFREQ_RT_DL)
+ next_f = sg_policy->policy->cpuinfo.max_freq;
+ else
+ next_f = sugov_next_freq_shared(sg_cpu);
+
sugov_update_commit(sg_policy, time, next_f);
}
@@ -473,7 +494,6 @@ static int sugov_init(struct cpufreq_policy *policy)
{
struct sugov_policy *sg_policy;
struct sugov_tunables *tunables;
- unsigned int lat;
int ret = 0;
/* State should be equivalent to EXIT */
@@ -512,10 +532,16 @@ static int sugov_init(struct cpufreq_policy *policy)
goto stop_kthread;
}
- tunables->rate_limit_us = LATENCY_MULTIPLIER;
- lat = policy->cpuinfo.transition_latency / NSEC_PER_USEC;
- if (lat)
- tunables->rate_limit_us *= lat;
+ if (policy->transition_delay_us) {
+ tunables->rate_limit_us = policy->transition_delay_us;
+ } else {
+ unsigned int lat;
+
+ tunables->rate_limit_us = LATENCY_MULTIPLIER;
+ lat = policy->cpuinfo.transition_latency / NSEC_PER_USEC;
+ if (lat)
+ tunables->rate_limit_us *= lat;
+ }
policy->governor_data = sg_policy;
sg_policy->tunables = tunables;
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index f3778e2b..aea3135 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -34,6 +34,18 @@ void disable_sched_clock_irqtime(void)
sched_clock_irqtime = 0;
}
+static void irqtime_account_delta(struct irqtime *irqtime, u64 delta,
+ enum cpu_usage_stat idx)
+{
+ u64 *cpustat = kcpustat_this_cpu->cpustat;
+
+ u64_stats_update_begin(&irqtime->sync);
+ cpustat[idx] += delta;
+ irqtime->total += delta;
+ irqtime->tick_delta += delta;
+ u64_stats_update_end(&irqtime->sync);
+}
+
/*
* Called before incrementing preempt_count on {soft,}irq_enter
* and before decrementing preempt_count on {soft,}irq_exit.
@@ -41,7 +53,6 @@ void disable_sched_clock_irqtime(void)
void irqtime_account_irq(struct task_struct *curr)
{
struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime);
- u64 *cpustat = kcpustat_this_cpu->cpustat;
s64 delta;
int cpu;
@@ -52,22 +63,16 @@ void irqtime_account_irq(struct task_struct *curr)
delta = sched_clock_cpu(cpu) - irqtime->irq_start_time;
irqtime->irq_start_time += delta;
- u64_stats_update_begin(&irqtime->sync);
/*
* We do not account for softirq time from ksoftirqd here.
* We want to continue accounting softirq time to ksoftirqd thread
* in that case, so as not to confuse scheduler with a special task
* that do not consume any time, but still wants to run.
*/
- if (hardirq_count()) {
- cpustat[CPUTIME_IRQ] += delta;
- irqtime->tick_delta += delta;
- } else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) {
- cpustat[CPUTIME_SOFTIRQ] += delta;
- irqtime->tick_delta += delta;
- }
-
- u64_stats_update_end(&irqtime->sync);
+ if (hardirq_count())
+ irqtime_account_delta(irqtime, delta, CPUTIME_IRQ);
+ else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
+ irqtime_account_delta(irqtime, delta, CPUTIME_SOFTIRQ);
}
EXPORT_SYMBOL_GPL(irqtime_account_irq);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 76f67b3..a903276 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -717,18 +717,12 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
}
#ifdef CONFIG_SMP
+
+#include "sched-pelt.h"
+
static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu);
static unsigned long task_h_load(struct task_struct *p);
-/*
- * We choose a half-life close to 1 scheduling period.
- * Note: The tables runnable_avg_yN_inv and runnable_avg_yN_sum are
- * dependent on this value.
- */
-#define LOAD_AVG_PERIOD 32
-#define LOAD_AVG_MAX 47742 /* maximum possible load avg */
-#define LOAD_AVG_MAX_N 345 /* number of full periods to produce LOAD_AVG_MAX */
-
/* Give new sched_entity start runnable values to heavy its load in infant time */
void init_entity_runnable_average(struct sched_entity *se)
{
@@ -2733,36 +2727,6 @@ static inline void update_cfs_shares(struct sched_entity *se)
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_SMP
-/* Precomputed fixed inverse multiplies for multiplication by y^n */
-static const u32 runnable_avg_yN_inv[] = {
- 0xffffffff, 0xfa83b2da, 0xf5257d14, 0xefe4b99a, 0xeac0c6e6, 0xe5b906e6,
- 0xe0ccdeeb, 0xdbfbb796, 0xd744fcc9, 0xd2a81d91, 0xce248c14, 0xc9b9bd85,
- 0xc5672a10, 0xc12c4cc9, 0xbd08a39e, 0xb8fbaf46, 0xb504f333, 0xb123f581,
- 0xad583ee9, 0xa9a15ab4, 0xa5fed6a9, 0xa2704302, 0x9ef5325f, 0x9b8d39b9,
- 0x9837f050, 0x94f4efa8, 0x91c3d373, 0x8ea4398a, 0x8b95c1e3, 0x88980e80,
- 0x85aac367, 0x82cd8698,
-};
-
-/*
- * Precomputed \Sum y^k { 1<=k<=n }. These are floor(true_value) to prevent
- * over-estimates when re-combining.
- */
-static const u32 runnable_avg_yN_sum[] = {
- 0, 1002, 1982, 2941, 3880, 4798, 5697, 6576, 7437, 8279, 9103,
- 9909,10698,11470,12226,12966,13690,14398,15091,15769,16433,17082,
- 17718,18340,18949,19545,20128,20698,21256,21802,22336,22859,23371,
-};
-
-/*
- * Precomputed \Sum y^k { 1<=k<=n, where n%32=0). Values are rolled down to
- * lower integers. See Documentation/scheduler/sched-avg.txt how these
- * were generated:
- */
-static const u32 __accumulated_sum_N32[] = {
- 0, 23371, 35056, 40899, 43820, 45281,
- 46011, 46376, 46559, 46650, 46696, 46719,
-};
-
/*
* Approximate:
* val * y^n, where y^32 ~= 0.5 (~1 scheduling period)
@@ -2771,9 +2735,7 @@ static u64 decay_load(u64 val, u64 n)
{
unsigned int local_n;
- if (!n)
- return val;
- else if (unlikely(n > LOAD_AVG_PERIOD * 63))
+ if (unlikely(n > LOAD_AVG_PERIOD * 63))
return 0;
/* after bounds checking we can collapse to 32-bit */
@@ -2795,40 +2757,25 @@ static u64 decay_load(u64 val, u64 n)
return val;
}
-static u32 __accumulate_sum(u64 periods, u32 period_contrib, u32 remainder)
+static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3)
{
- u32 c1, c2, c3 = remainder; /* y^0 == 1 */
-
- if (!periods)
- return remainder - period_contrib;
-
- if (unlikely(periods >= LOAD_AVG_MAX_N))
- return LOAD_AVG_MAX;
+ u32 c1, c2, c3 = d3; /* y^0 == 1 */
/*
- * c1 = d1 y^(p+1)
+ * c1 = d1 y^p
*/
- c1 = decay_load((u64)(1024 - period_contrib), periods);
+ c1 = decay_load((u64)d1, periods);
- periods -= 1;
/*
- * For updates fully spanning n periods, the contribution to runnable
- * average will be:
- *
- * c2 = 1024 \Sum y^n
+ * p-1
+ * c2 = 1024 \Sum y^n
+ * n=1
*
- * We can compute this reasonably efficiently by combining:
- *
- * y^PERIOD = 1/2 with precomputed 1024 \Sum y^n {for: n < PERIOD}
+ * inf inf
+ * = 1024 ( \Sum y^n - \Sum y^n - y^0 )
+ * n=0 n=p
*/
- if (likely(periods <= LOAD_AVG_PERIOD)) {
- c2 = runnable_avg_yN_sum[periods];
- } else {
- c2 = __accumulated_sum_N32[periods/LOAD_AVG_PERIOD];
- periods %= LOAD_AVG_PERIOD;
- c2 = decay_load(c2, periods);
- c2 += runnable_avg_yN_sum[periods];
- }
+ c2 = LOAD_AVG_MAX - decay_load(LOAD_AVG_MAX, periods) - 1024;
return c1 + c2 + c3;
}
@@ -2846,23 +2793,23 @@ static u32 __accumulate_sum(u64 periods, u32 period_contrib, u32 remainder)
* |<->|<----------------->|<--->|
* ... |---x---|------| ... |------|-----x (now)
*
- * p
- * u' = (u + d1) y^(p+1) + 1024 \Sum y^n + d3 y^0
- * n=1
+ * p-1
+ * u' = (u + d1) y^p + 1024 \Sum y^n + d3 y^0
+ * n=1
*
- * = u y^(p+1) + (Step 1)
+ * = u y^p + (Step 1)
*
- * p
- * d1 y^(p+1) + 1024 \Sum y^n + d3 y^0 (Step 2)
- * n=1
+ * p-1
+ * d1 y^p + 1024 \Sum y^n + d3 y^0 (Step 2)
+ * n=1
*/
static __always_inline u32
accumulate_sum(u64 delta, int cpu, struct sched_avg *sa,
unsigned long weight, int running, struct cfs_rq *cfs_rq)
{
unsigned long scale_freq, scale_cpu;
+ u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */
u64 periods;
- u32 contrib;
scale_freq = arch_scale_freq_capacity(NULL, cpu);
scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
@@ -2880,13 +2827,14 @@ accumulate_sum(u64 delta, int cpu, struct sched_avg *sa,
decay_load(cfs_rq->runnable_load_sum, periods);
}
sa->util_sum = decay_load((u64)(sa->util_sum), periods);
- }
- /*
- * Step 2
- */
- delta %= 1024;
- contrib = __accumulate_sum(periods, sa->period_contrib, delta);
+ /*
+ * Step 2
+ */
+ delta %= 1024;
+ contrib = __accumulate_pelt_segments(periods,
+ 1024 - sa->period_contrib, delta);
+ }
sa->period_contrib = delta;
contrib = cap_scale(contrib, scale_freq);
@@ -2952,7 +2900,8 @@ ___update_load_avg(u64 now, int cpu, struct sched_avg *sa,
delta >>= 10;
if (!delta)
return 0;
- sa->last_update_time = now;
+
+ sa->last_update_time += delta << 10;
/*
* Now we know we crossed measurement unit boundaries. The *_avg
diff --git a/kernel/sched/sched-pelt.h b/kernel/sched/sched-pelt.h
new file mode 100644
index 0000000..cd200d1
--- /dev/null
+++ b/kernel/sched/sched-pelt.h
@@ -0,0 +1,13 @@
+/* Generated by Documentation/scheduler/sched-pelt; do not modify. */
+
+static const u32 runnable_avg_yN_inv[] = {
+ 0xffffffff, 0xfa83b2da, 0xf5257d14, 0xefe4b99a, 0xeac0c6e6, 0xe5b906e6,
+ 0xe0ccdeeb, 0xdbfbb796, 0xd744fcc9, 0xd2a81d91, 0xce248c14, 0xc9b9bd85,
+ 0xc5672a10, 0xc12c4cc9, 0xbd08a39e, 0xb8fbaf46, 0xb504f333, 0xb123f581,
+ 0xad583ee9, 0xa9a15ab4, 0xa5fed6a9, 0xa2704302, 0x9ef5325f, 0x9b8d39b9,
+ 0x9837f050, 0x94f4efa8, 0x91c3d373, 0x8ea4398a, 0x8b95c1e3, 0x88980e80,
+ 0x85aac367, 0x82cd8698,
+};
+
+#define LOAD_AVG_PERIOD 32
+#define LOAD_AVG_MAX 47742
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index de4b934..7808ab0 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1928,6 +1928,7 @@ static inline void nohz_balance_exit_idle(unsigned int cpu) { }
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
struct irqtime {
+ u64 total;
u64 tick_delta;
u64 irq_start_time;
struct u64_stats_sync sync;
@@ -1935,16 +1936,20 @@ struct irqtime {
DECLARE_PER_CPU(struct irqtime, cpu_irqtime);
+/*
+ * Returns the irqtime minus the softirq time computed by ksoftirqd.
+ * Otherwise ksoftirqd's sum_exec_runtime is substracted its own runtime
+ * and never move forward.
+ */
static inline u64 irq_time_read(int cpu)
{
struct irqtime *irqtime = &per_cpu(cpu_irqtime, cpu);
- u64 *cpustat = kcpustat_cpu(cpu).cpustat;
unsigned int seq;
u64 total;
do {
seq = __u64_stats_fetch_begin(&irqtime->sync);
- total = cpustat[CPUTIME_SOFTIRQ] + cpustat[CPUTIME_IRQ];
+ total = irqtime->total;
} while (__u64_stats_fetch_retry(&irqtime->sync, seq));
return total;
OpenPOWER on IntegriCloud