summaryrefslogtreecommitdiff
path: root/kernel/sched/fair.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sched/fair.c')
-rw-r--r--kernel/sched/fair.c425
1 files changed, 231 insertions, 194 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index acba2736f..82e905862 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -17,7 +17,7 @@
* Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de>
*
* Adaptive scheduling granularity, math enhancements by Peter Zijlstra
- * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
*/
#include <linux/latencytop.h>
@@ -686,11 +686,12 @@ static unsigned long task_h_load(struct task_struct *p);
/*
* We choose a half-life close to 1 scheduling period.
- * Note: The tables below are dependent on this value.
+ * 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_MAX_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)
@@ -707,7 +708,7 @@ void init_entity_runnable_average(struct sched_entity *se)
sa->load_avg = scale_load_down(se->load.weight);
sa->load_sum = sa->load_avg * LOAD_AVG_MAX;
sa->util_avg = scale_load_down(SCHED_LOAD_SCALE);
- sa->util_sum = LOAD_AVG_MAX;
+ sa->util_sum = sa->util_avg * LOAD_AVG_MAX;
/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
}
@@ -2094,7 +2095,7 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
int local = !!(flags & TNF_FAULT_LOCAL);
int priv;
- if (!numabalancing_enabled)
+ if (!static_branch_likely(&sched_numa_balancing))
return;
/* for example, ksmd faulting in a user's mm */
@@ -2182,7 +2183,7 @@ void task_numa_work(struct callback_head *work)
struct vm_area_struct *vma;
unsigned long start, end;
unsigned long nr_pte_updates = 0;
- long pages;
+ long pages, virtpages;
WARN_ON_ONCE(p != container_of(work, struct task_struct, numa_work));
@@ -2228,9 +2229,11 @@ void task_numa_work(struct callback_head *work)
start = mm->numa_scan_offset;
pages = sysctl_numa_balancing_scan_size;
pages <<= 20 - PAGE_SHIFT; /* MB in pages */
+ virtpages = pages * 8; /* Scan up to this much virtual space */
if (!pages)
return;
+
down_read(&mm->mmap_sem);
vma = find_vma(mm, start);
if (!vma) {
@@ -2265,18 +2268,22 @@ void task_numa_work(struct callback_head *work)
start = max(start, vma->vm_start);
end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE);
end = min(end, vma->vm_end);
- nr_pte_updates += change_prot_numa(vma, start, end);
+ nr_pte_updates = change_prot_numa(vma, start, end);
/*
- * Scan sysctl_numa_balancing_scan_size but ensure that
- * at least one PTE is updated so that unused virtual
- * address space is quickly skipped.
+ * Try to scan sysctl_numa_balancing_size worth of
+ * hpages that have at least one present PTE that
+ * is not already pte-numa. If the VMA contains
+ * areas that are unused or already full of prot_numa
+ * PTEs, scan up to virtpages, to skip through those
+ * areas faster.
*/
if (nr_pte_updates)
pages -= (end - start) >> PAGE_SHIFT;
+ virtpages -= (end - start) >> PAGE_SHIFT;
start = end;
- if (pages <= 0)
+ if (pages <= 0 || virtpages <= 0)
goto out;
cond_resched();
@@ -2320,7 +2327,7 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr)
now = curr->se.sum_exec_runtime;
period = (u64)curr->numa_scan_period * NSEC_PER_MSEC;
- if (now - curr->node_stamp > period) {
+ if (now > curr->node_stamp + period) {
if (!curr->node_stamp)
curr->numa_scan_period = task_scan_min(curr);
curr->node_stamp += period;
@@ -2540,6 +2547,12 @@ static u32 __compute_runnable_contrib(u64 n)
return contrib + runnable_avg_yN_sum[n];
}
+#if (SCHED_LOAD_SHIFT - SCHED_LOAD_RESOLUTION) != 10 || SCHED_CAPACITY_SHIFT != 10
+#error "load tracking assumes 2^10 as unit"
+#endif
+
+#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
+
/*
* We can represent the historical contribution to runnable average as the
* coefficients of a geometric series. To do this we sub-divide our runnable
@@ -2572,10 +2585,10 @@ static __always_inline int
__update_load_avg(u64 now, int cpu, struct sched_avg *sa,
unsigned long weight, int running, struct cfs_rq *cfs_rq)
{
- u64 delta, periods;
+ u64 delta, scaled_delta, periods;
u32 contrib;
- int delta_w, decayed = 0;
- unsigned long scale_freq = arch_scale_freq_capacity(NULL, cpu);
+ unsigned int delta_w, scaled_delta_w, decayed = 0;
+ unsigned long scale_freq, scale_cpu;
delta = now - sa->last_update_time;
/*
@@ -2596,6 +2609,9 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
return 0;
sa->last_update_time = now;
+ scale_freq = arch_scale_freq_capacity(NULL, cpu);
+ scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
+
/* delta_w is the amount already accumulated against our next period */
delta_w = sa->period_contrib;
if (delta + delta_w >= 1024) {
@@ -2610,13 +2626,16 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
* period and accrue it.
*/
delta_w = 1024 - delta_w;
+ scaled_delta_w = cap_scale(delta_w, scale_freq);
if (weight) {
- sa->load_sum += weight * delta_w;
- if (cfs_rq)
- cfs_rq->runnable_load_sum += weight * delta_w;
+ sa->load_sum += weight * scaled_delta_w;
+ if (cfs_rq) {
+ cfs_rq->runnable_load_sum +=
+ weight * scaled_delta_w;
+ }
}
if (running)
- sa->util_sum += delta_w * scale_freq >> SCHED_CAPACITY_SHIFT;
+ sa->util_sum += scaled_delta_w * scale_cpu;
delta -= delta_w;
@@ -2633,23 +2652,25 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
/* Efficiently calculate \sum (1..n_period) 1024*y^i */
contrib = __compute_runnable_contrib(periods);
+ contrib = cap_scale(contrib, scale_freq);
if (weight) {
sa->load_sum += weight * contrib;
if (cfs_rq)
cfs_rq->runnable_load_sum += weight * contrib;
}
if (running)
- sa->util_sum += contrib * scale_freq >> SCHED_CAPACITY_SHIFT;
+ sa->util_sum += contrib * scale_cpu;
}
/* Remainder of delta accrued against u_0` */
+ scaled_delta = cap_scale(delta, scale_freq);
if (weight) {
- sa->load_sum += weight * delta;
+ sa->load_sum += weight * scaled_delta;
if (cfs_rq)
- cfs_rq->runnable_load_sum += weight * delta;
+ cfs_rq->runnable_load_sum += weight * scaled_delta;
}
if (running)
- sa->util_sum += delta * scale_freq >> SCHED_CAPACITY_SHIFT;
+ sa->util_sum += scaled_delta * scale_cpu;
sa->period_contrib += delta;
@@ -2659,7 +2680,7 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
cfs_rq->runnable_load_avg =
div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX);
}
- sa->util_avg = (sa->util_sum << SCHED_LOAD_SHIFT) / LOAD_AVG_MAX;
+ sa->util_avg = sa->util_sum / LOAD_AVG_MAX;
}
return decayed;
@@ -2693,7 +2714,7 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
int decayed, removed = 0;
if (atomic_long_read(&cfs_rq->removed_load_avg)) {
- long r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
+ s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
sa->load_avg = max_t(long, sa->load_avg - r, 0);
sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0);
removed = 1;
@@ -2702,8 +2723,7 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
if (atomic_long_read(&cfs_rq->removed_util_avg)) {
long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0);
sa->util_avg = max_t(long, sa->util_avg - r, 0);
- sa->util_sum = max_t(s32, sa->util_sum -
- ((r * LOAD_AVG_MAX) >> SCHED_LOAD_SHIFT), 0);
+ sa->util_sum = max_t(s32, sa->util_sum - r * LOAD_AVG_MAX, 0);
}
decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
@@ -2721,33 +2741,70 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
static inline void update_load_avg(struct sched_entity *se, int update_tg)
{
struct cfs_rq *cfs_rq = cfs_rq_of(se);
- int cpu = cpu_of(rq_of(cfs_rq));
u64 now = cfs_rq_clock_task(cfs_rq);
+ int cpu = cpu_of(rq_of(cfs_rq));
/*
* Track task load average for carrying it to new CPU after migrated, and
* track group sched_entity load average for task_h_load calc in migration
*/
__update_load_avg(now, cpu, &se->avg,
- se->on_rq * scale_load_down(se->load.weight), cfs_rq->curr == se, NULL);
+ se->on_rq * scale_load_down(se->load.weight),
+ cfs_rq->curr == se, NULL);
if (update_cfs_rq_load_avg(now, cfs_rq) && update_tg)
update_tg_load_avg(cfs_rq, 0);
}
+static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ if (!sched_feat(ATTACH_AGE_LOAD))
+ goto skip_aging;
+
+ /*
+ * If we got migrated (either between CPUs or between cgroups) we'll
+ * have aged the average right before clearing @last_update_time.
+ */
+ if (se->avg.last_update_time) {
+ __update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)),
+ &se->avg, 0, 0, NULL);
+
+ /*
+ * XXX: we could have just aged the entire load away if we've been
+ * absent from the fair class for too long.
+ */
+ }
+
+skip_aging:
+ se->avg.last_update_time = cfs_rq->avg.last_update_time;
+ cfs_rq->avg.load_avg += se->avg.load_avg;
+ cfs_rq->avg.load_sum += se->avg.load_sum;
+ cfs_rq->avg.util_avg += se->avg.util_avg;
+ cfs_rq->avg.util_sum += se->avg.util_sum;
+}
+
+static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ __update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)),
+ &se->avg, se->on_rq * scale_load_down(se->load.weight),
+ cfs_rq->curr == se, NULL);
+
+ cfs_rq->avg.load_avg = max_t(long, cfs_rq->avg.load_avg - se->avg.load_avg, 0);
+ cfs_rq->avg.load_sum = max_t(s64, cfs_rq->avg.load_sum - se->avg.load_sum, 0);
+ cfs_rq->avg.util_avg = max_t(long, cfs_rq->avg.util_avg - se->avg.util_avg, 0);
+ cfs_rq->avg.util_sum = max_t(s32, cfs_rq->avg.util_sum - se->avg.util_sum, 0);
+}
+
/* Add the load generated by se into cfs_rq's load average */
static inline void
enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
struct sched_avg *sa = &se->avg;
u64 now = cfs_rq_clock_task(cfs_rq);
- int migrated = 0, decayed;
+ int migrated, decayed;
- if (sa->last_update_time == 0) {
- sa->last_update_time = now;
- migrated = 1;
- }
- else {
+ migrated = !sa->last_update_time;
+ if (!migrated) {
__update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
se->on_rq * scale_load_down(se->load.weight),
cfs_rq->curr == se, NULL);
@@ -2758,12 +2815,8 @@ enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
cfs_rq->runnable_load_avg += sa->load_avg;
cfs_rq->runnable_load_sum += sa->load_sum;
- if (migrated) {
- cfs_rq->avg.load_avg += sa->load_avg;
- cfs_rq->avg.load_sum += sa->load_sum;
- cfs_rq->avg.util_avg += sa->util_avg;
- cfs_rq->avg.util_sum += sa->util_sum;
- }
+ if (migrated)
+ attach_entity_load_avg(cfs_rq, se);
if (decayed || migrated)
update_tg_load_avg(cfs_rq, 0);
@@ -2778,7 +2831,7 @@ dequeue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
cfs_rq->runnable_load_avg =
max_t(long, cfs_rq->runnable_load_avg - se->avg.load_avg, 0);
cfs_rq->runnable_load_sum =
- max_t(s64, cfs_rq->runnable_load_sum - se->avg.load_sum, 0);
+ max_t(s64, cfs_rq->runnable_load_sum - se->avg.load_sum, 0);
}
/*
@@ -2846,6 +2899,11 @@ static inline void
dequeue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
static inline void remove_entity_load_avg(struct sched_entity *se) {}
+static inline void
+attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
+static inline void
+detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
+
static inline int idle_balance(struct rq *rq)
{
return 0;
@@ -4842,32 +4900,39 @@ next:
done:
return target;
}
+
/*
- * get_cpu_usage returns the amount of capacity of a CPU that is used by CFS
+ * cpu_util returns the amount of capacity of a CPU that is used by CFS
* tasks. The unit of the return value must be the one of capacity so we can
- * compare the usage with the capacity of the CPU that is available for CFS
- * task (ie cpu_capacity).
- * cfs.avg.util_avg is the sum of running time of runnable tasks on a
- * CPU. It represents the amount of utilization of a CPU in the range
- * [0..SCHED_LOAD_SCALE]. The usage of a CPU can't be higher than the full
- * capacity of the CPU because it's about the running time on this CPU.
- * Nevertheless, cfs.avg.util_avg can be higher than SCHED_LOAD_SCALE
- * because of unfortunate rounding in util_avg or just
- * after migrating tasks until the average stabilizes with the new running
- * time. So we need to check that the usage stays into the range
- * [0..cpu_capacity_orig] and cap if necessary.
- * Without capping the usage, a group could be seen as overloaded (CPU0 usage
- * at 121% + CPU1 usage at 80%) whereas CPU1 has 20% of available capacity
+ * compare the utilization with the capacity of the CPU that is available for
+ * CFS task (ie cpu_capacity).
+ *
+ * cfs_rq.avg.util_avg is the sum of running time of runnable tasks plus the
+ * recent utilization of currently non-runnable tasks on a CPU. It represents
+ * the amount of utilization of a CPU in the range [0..capacity_orig] where
+ * capacity_orig is the cpu_capacity available at the highest frequency
+ * (arch_scale_freq_capacity()).
+ * The utilization of a CPU converges towards a sum equal to or less than the
+ * current capacity (capacity_curr <= capacity_orig) of the CPU because it is
+ * the running time on this CPU scaled by capacity_curr.
+ *
+ * Nevertheless, cfs_rq.avg.util_avg can be higher than capacity_curr or even
+ * higher than capacity_orig because of unfortunate rounding in
+ * cfs.avg.util_avg or just after migrating tasks and new task wakeups until
+ * the average stabilizes with the new running time. We need to check that the
+ * utilization stays within the range of [0..capacity_orig] and cap it if
+ * necessary. Without utilization capping, a group could be seen as overloaded
+ * (CPU0 utilization at 121% + CPU1 utilization at 80%) whereas CPU1 has 20% of
+ * available capacity. We allow utilization to overshoot capacity_curr (but not
+ * capacity_orig) as it useful for predicting the capacity required after task
+ * migrations (scheduler-driven DVFS).
*/
-static int get_cpu_usage(int cpu)
+static int cpu_util(int cpu)
{
- unsigned long usage = cpu_rq(cpu)->cfs.avg.util_avg;
+ unsigned long util = cpu_rq(cpu)->cfs.avg.util_avg;
unsigned long capacity = capacity_orig_of(cpu);
- if (usage >= SCHED_LOAD_SCALE)
- return capacity;
-
- return (usage * capacity) >> SCHED_LOAD_SHIFT;
+ return (util >= capacity) ? capacity : util;
}
/*
@@ -4970,7 +5035,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
* previous cpu. However, the caller only guarantees p->pi_lock is held; no
* other assumptions, including the state of rq->lock, should be made.
*/
-static void migrate_task_rq_fair(struct task_struct *p, int next_cpu)
+static void migrate_task_rq_fair(struct task_struct *p)
{
/*
* We are supposed to update the task to "current" time, then its up to date
@@ -5550,10 +5615,10 @@ static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
unsigned long src_faults, dst_faults;
int src_nid, dst_nid;
- if (!p->numa_faults || !(env->sd->flags & SD_NUMA))
+ if (!static_branch_likely(&sched_numa_balancing))
return -1;
- if (!sched_feat(NUMA))
+ if (!p->numa_faults || !(env->sd->flags & SD_NUMA))
return -1;
src_nid = cpu_to_node(env->src_cpu);
@@ -5959,7 +6024,7 @@ struct sg_lb_stats {
unsigned long sum_weighted_load; /* Weighted load of group's tasks */
unsigned long load_per_task;
unsigned long group_capacity;
- unsigned long group_usage; /* Total usage of the group */
+ unsigned long group_util; /* Total utilization of the group */
unsigned int sum_nr_running; /* Nr tasks running in the group */
unsigned int idle_cpus;
unsigned int group_weight;
@@ -6035,19 +6100,6 @@ static inline int get_sd_load_idx(struct sched_domain *sd,
return load_idx;
}
-static unsigned long default_scale_cpu_capacity(struct sched_domain *sd, int cpu)
-{
- if ((sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1))
- return sd->smt_gain / sd->span_weight;
-
- return SCHED_CAPACITY_SCALE;
-}
-
-unsigned long __weak arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
-{
- return default_scale_cpu_capacity(sd, cpu);
-}
-
static unsigned long scale_rt_capacity(int cpu)
{
struct rq *rq = cpu_rq(cpu);
@@ -6077,16 +6129,9 @@ static unsigned long scale_rt_capacity(int cpu)
static void update_cpu_capacity(struct sched_domain *sd, int cpu)
{
- unsigned long capacity = SCHED_CAPACITY_SCALE;
+ unsigned long capacity = arch_scale_cpu_capacity(sd, cpu);
struct sched_group *sdg = sd->groups;
- if (sched_feat(ARCH_CAPACITY))
- capacity *= arch_scale_cpu_capacity(sd, cpu);
- else
- capacity *= default_scale_cpu_capacity(sd, cpu);
-
- capacity >>= SCHED_CAPACITY_SHIFT;
-
cpu_rq(cpu)->cpu_capacity_orig = capacity;
capacity *= scale_rt_capacity(cpu);
@@ -6212,8 +6257,8 @@ static inline int sg_imbalanced(struct sched_group *group)
* group_has_capacity returns true if the group has spare capacity that could
* be used by some tasks.
* We consider that a group has spare capacity if the * number of task is
- * smaller than the number of CPUs or if the usage is lower than the available
- * capacity for CFS tasks.
+ * smaller than the number of CPUs or if the utilization is lower than the
+ * available capacity for CFS tasks.
* For the latter, we use a threshold to stabilize the state, to take into
* account the variance of the tasks' load and to return true if the available
* capacity in meaningful for the load balancer.
@@ -6227,7 +6272,7 @@ group_has_capacity(struct lb_env *env, struct sg_lb_stats *sgs)
return true;
if ((sgs->group_capacity * 100) >
- (sgs->group_usage * env->sd->imbalance_pct))
+ (sgs->group_util * env->sd->imbalance_pct))
return true;
return false;
@@ -6248,15 +6293,15 @@ group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs)
return false;
if ((sgs->group_capacity * 100) <
- (sgs->group_usage * env->sd->imbalance_pct))
+ (sgs->group_util * env->sd->imbalance_pct))
return true;
return false;
}
-static enum group_type group_classify(struct lb_env *env,
- struct sched_group *group,
- struct sg_lb_stats *sgs)
+static inline enum
+group_type group_classify(struct sched_group *group,
+ struct sg_lb_stats *sgs)
{
if (sgs->group_no_capacity)
return group_overloaded;
@@ -6296,7 +6341,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
load = source_load(i, load_idx);
sgs->group_load += load;
- sgs->group_usage += get_cpu_usage(i);
+ sgs->group_util += cpu_util(i);
sgs->sum_nr_running += rq->cfs.h_nr_running;
if (rq->nr_running > 1)
@@ -6321,7 +6366,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
sgs->group_weight = group->group_weight;
sgs->group_no_capacity = group_is_overloaded(env, sgs);
- sgs->group_type = group_classify(env, group, sgs);
+ sgs->group_type = group_classify(group, sgs);
}
/**
@@ -6455,7 +6500,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
group_has_capacity(env, &sds->local_stat) &&
(sgs->sum_nr_running > 1)) {
sgs->group_no_capacity = 1;
- sgs->group_type = group_overloaded;
+ sgs->group_type = group_classify(sg, sgs);
}
if (update_sd_pick_busiest(env, sds, sg, sgs)) {
@@ -7635,8 +7680,22 @@ out:
* When the cpu is attached to null domain for ex, it will not be
* updated.
*/
- if (likely(update_next_balance))
+ if (likely(update_next_balance)) {
rq->next_balance = next_balance;
+
+#ifdef CONFIG_NO_HZ_COMMON
+ /*
+ * If this CPU has been elected to perform the nohz idle
+ * balance. Other idle CPUs have already rebalanced with
+ * nohz_idle_balance() and nohz.next_balance has been
+ * updated accordingly. This CPU is now running the idle load
+ * balance for itself and we need to update the
+ * nohz.next_balance accordingly.
+ */
+ if ((idle == CPU_IDLE) && time_after(nohz.next_balance, rq->next_balance))
+ nohz.next_balance = rq->next_balance;
+#endif
+ }
}
#ifdef CONFIG_NO_HZ_COMMON
@@ -7649,6 +7708,9 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
int this_cpu = this_rq->cpu;
struct rq *rq;
int balance_cpu;
+ /* Earliest time when we have to do rebalance again */
+ unsigned long next_balance = jiffies + 60*HZ;
+ int update_next_balance = 0;
if (idle != CPU_IDLE ||
!test_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu)))
@@ -7680,10 +7742,19 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
rebalance_domains(rq, CPU_IDLE);
}
- if (time_after(this_rq->next_balance, rq->next_balance))
- this_rq->next_balance = rq->next_balance;
+ if (time_after(next_balance, rq->next_balance)) {
+ next_balance = rq->next_balance;
+ update_next_balance = 1;
+ }
}
- nohz.next_balance = this_rq->next_balance;
+
+ /*
+ * next_balance will be updated only when there is a need.
+ * When the CPU is attached to null domain for ex, it will not be
+ * updated.
+ */
+ if (likely(update_next_balance))
+ nohz.next_balance = next_balance;
end:
clear_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu));
}
@@ -7836,7 +7907,7 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
entity_tick(cfs_rq, se, queued);
}
- if (numabalancing_enabled)
+ if (static_branch_unlikely(&sched_numa_balancing))
task_tick_numa(rq, curr);
}
@@ -7912,21 +7983,39 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
check_preempt_curr(rq, p, 0);
}
-static void switched_from_fair(struct rq *rq, struct task_struct *p)
+static inline bool vruntime_normalized(struct task_struct *p)
{
struct sched_entity *se = &p->se;
- struct cfs_rq *cfs_rq = cfs_rq_of(se);
/*
- * Ensure the task's vruntime is normalized, so that when it's
- * switched back to the fair class the enqueue_entity(.flags=0) will
- * do the right thing.
+ * In both the TASK_ON_RQ_QUEUED and TASK_ON_RQ_MIGRATING cases,
+ * the dequeue_entity(.flags=0) will already have normalized the
+ * vruntime.
+ */
+ if (p->on_rq)
+ return true;
+
+ /*
+ * When !on_rq, vruntime of the task has usually NOT been normalized.
+ * But there are some cases where it has already been normalized:
*
- * If it's queued, then the dequeue_entity(.flags=0) will already
- * have normalized the vruntime, if it's !queued, then only when
- * the task is sleeping will it still have non-normalized vruntime.
+ * - A forked child which is waiting for being woken up by
+ * wake_up_new_task().
+ * - A task which has been woken up by try_to_wake_up() and
+ * waiting for actually being woken up by sched_ttwu_pending().
*/
- if (!task_on_rq_queued(p) && p->state != TASK_RUNNING) {
+ if (!se->sum_exec_runtime || p->state == TASK_WAKING)
+ return true;
+
+ return false;
+}
+
+static void detach_task_cfs_rq(struct task_struct *p)
+{
+ struct sched_entity *se = &p->se;
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+ if (!vruntime_normalized(p)) {
/*
* Fix up our vruntime so that the current sleep doesn't
* cause 'unlimited' sleep bonus.
@@ -7935,28 +8024,14 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p)
se->vruntime -= cfs_rq->min_vruntime;
}
-#ifdef CONFIG_SMP
/* Catch up with the cfs_rq and remove our load when we leave */
- __update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq), &se->avg,
- se->on_rq * scale_load_down(se->load.weight), cfs_rq->curr == se, NULL);
-
- cfs_rq->avg.load_avg =
- max_t(long, cfs_rq->avg.load_avg - se->avg.load_avg, 0);
- cfs_rq->avg.load_sum =
- max_t(s64, cfs_rq->avg.load_sum - se->avg.load_sum, 0);
- cfs_rq->avg.util_avg =
- max_t(long, cfs_rq->avg.util_avg - se->avg.util_avg, 0);
- cfs_rq->avg.util_sum =
- max_t(s32, cfs_rq->avg.util_sum - se->avg.util_sum, 0);
-#endif
+ detach_entity_load_avg(cfs_rq, se);
}
-/*
- * We switched to the sched_fair class.
- */
-static void switched_to_fair(struct rq *rq, struct task_struct *p)
+static void attach_task_cfs_rq(struct task_struct *p)
{
struct sched_entity *se = &p->se;
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
#ifdef CONFIG_FAIR_GROUP_SCHED
/*
@@ -7966,31 +8041,33 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p)
se->depth = se->parent ? se->parent->depth + 1 : 0;
#endif
- if (!task_on_rq_queued(p)) {
+ /* Synchronize task with its cfs_rq */
+ attach_entity_load_avg(cfs_rq, se);
+ if (!vruntime_normalized(p))
+ se->vruntime += cfs_rq->min_vruntime;
+}
+
+static void switched_from_fair(struct rq *rq, struct task_struct *p)
+{
+ detach_task_cfs_rq(p);
+}
+
+static void switched_to_fair(struct rq *rq, struct task_struct *p)
+{
+ attach_task_cfs_rq(p);
+
+ if (task_on_rq_queued(p)) {
/*
- * Ensure the task has a non-normalized vruntime when it is switched
- * back to the fair class with !queued, so that enqueue_entity() at
- * wake-up time will do the right thing.
- *
- * If it's queued, then the enqueue_entity(.flags=0) makes the task
- * has non-normalized vruntime, if it's !queued, then it still has
- * normalized vruntime.
+ * We were most likely switched from sched_rt, so
+ * kick off the schedule if running, otherwise just see
+ * if we can still preempt the current task.
*/
- if (p->state != TASK_RUNNING)
- se->vruntime += cfs_rq_of(se)->min_vruntime;
- return;
+ if (rq->curr == p)
+ resched_curr(rq);
+ else
+ check_preempt_curr(rq, p, 0);
}
-
- /*
- * We were most likely switched from sched_rt, so
- * kick off the schedule if running, otherwise just see
- * if we can still preempt the current task.
- */
- if (rq->curr == p)
- resched_curr(rq);
- else
- check_preempt_curr(rq, p, 0);
}
/* Account for a task changing its policy or group.
@@ -8025,56 +8102,16 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
}
#ifdef CONFIG_FAIR_GROUP_SCHED
-static void task_move_group_fair(struct task_struct *p, int queued)
+static void task_move_group_fair(struct task_struct *p)
{
- struct sched_entity *se = &p->se;
- struct cfs_rq *cfs_rq;
-
- /*
- * If the task was not on the rq at the time of this cgroup movement
- * it must have been asleep, sleeping tasks keep their ->vruntime
- * absolute on their old rq until wakeup (needed for the fair sleeper
- * bonus in place_entity()).
- *
- * If it was on the rq, we've just 'preempted' it, which does convert
- * ->vruntime to a relative base.
- *
- * Make sure both cases convert their relative position when migrating
- * to another cgroup's rq. This does somewhat interfere with the
- * fair sleeper stuff for the first placement, but who cares.
- */
- /*
- * When !queued, vruntime of the task has usually NOT been normalized.
- * But there are some cases where it has already been normalized:
- *
- * - Moving a forked child which is waiting for being woken up by
- * wake_up_new_task().
- * - Moving a task which has been woken up by try_to_wake_up() and
- * waiting for actually being woken up by sched_ttwu_pending().
- *
- * To prevent boost or penalty in the new cfs_rq caused by delta
- * min_vruntime between the two cfs_rqs, we skip vruntime adjustment.
- */
- if (!queued && (!se->sum_exec_runtime || p->state == TASK_WAKING))
- queued = 1;
-
- if (!queued)
- se->vruntime -= cfs_rq_of(se)->min_vruntime;
+ detach_task_cfs_rq(p);
set_task_rq(p, task_cpu(p));
- se->depth = se->parent ? se->parent->depth + 1 : 0;
- if (!queued) {
- cfs_rq = cfs_rq_of(se);
- se->vruntime += cfs_rq->min_vruntime;
#ifdef CONFIG_SMP
- /* Virtually synchronize task with its new cfs_rq */
- p->se.avg.last_update_time = cfs_rq->avg.last_update_time;
- cfs_rq->avg.load_avg += p->se.avg.load_avg;
- cfs_rq->avg.load_sum += p->se.avg.load_sum;
- cfs_rq->avg.util_avg += p->se.avg.util_avg;
- cfs_rq->avg.util_sum += p->se.avg.util_sum;
+ /* Tell se's cfs_rq has been changed -- migrated */
+ p->se.avg.last_update_time = 0;
#endif
- }
+ attach_task_cfs_rq(p);
}
void free_fair_sched_group(struct task_group *tg)