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.c623
1 files changed, 219 insertions, 404 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8591529e1753..036be95a87e9 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -275,6 +275,19 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
return grp->my_q;
}
+static inline void cfs_rq_tg_path(struct cfs_rq *cfs_rq, char *path, int len)
+{
+ if (!path)
+ return;
+
+ if (cfs_rq && task_group_is_autogroup(cfs_rq->tg))
+ autogroup_path(cfs_rq->tg, path, len);
+ else if (cfs_rq && cfs_rq->tg->css.cgroup)
+ cgroup_path(cfs_rq->tg->css.cgroup, path, len);
+ else
+ strlcpy(path, "(null)", len);
+}
+
static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
{
struct rq *rq = rq_of(cfs_rq);
@@ -449,6 +462,12 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
return NULL;
}
+static inline void cfs_rq_tg_path(struct cfs_rq *cfs_rq, char *path, int len)
+{
+ if (path)
+ strlcpy(path, "(null)", len);
+}
+
static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
{
return true;
@@ -764,7 +783,7 @@ void post_init_entity_util_avg(struct task_struct *p)
struct sched_entity *se = &p->se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
struct sched_avg *sa = &se->avg;
- long cpu_scale = arch_scale_cpu_capacity(NULL, cpu_of(rq_of(cfs_rq)));
+ long cpu_scale = arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq)));
long cap = (long)(cpu_scale - cfs_rq->avg.util_avg) / 2;
if (cap > 0) {
@@ -1466,9 +1485,7 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
group_faults_cpu(ng, src_nid) * group_faults(p, dst_nid) * 4;
}
-static unsigned long weighted_cpuload(struct rq *rq);
-static unsigned long source_load(int cpu, int type);
-static unsigned long target_load(int cpu, int type);
+static unsigned long cpu_runnable_load(struct rq *rq);
/* Cached statistics for all CPUs within a node */
struct numa_stats {
@@ -1489,7 +1506,7 @@ static void update_numa_stats(struct numa_stats *ns, int nid)
for_each_cpu(cpu, cpumask_of_node(nid)) {
struct rq *rq = cpu_rq(cpu);
- ns->load += weighted_cpuload(rq);
+ ns->load += cpu_runnable_load(rq);
ns->compute_capacity += capacity_of(cpu);
}
@@ -1621,7 +1638,7 @@ static void task_numa_compare(struct task_numa_env *env,
* be incurred if the tasks were swapped.
*/
/* Skip this swap candidate if cannot move to the source cpu */
- if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed))
+ if (!cpumask_test_cpu(env->src_cpu, cur->cpus_ptr))
goto unlock;
/*
@@ -1718,7 +1735,7 @@ static void task_numa_find_cpu(struct task_numa_env *env,
for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) {
/* Skip this CPU if the source task cannot migrate */
- if (!cpumask_test_cpu(cpu, &env->p->cpus_allowed))
+ if (!cpumask_test_cpu(cpu, env->p->cpus_ptr))
continue;
env->dst_cpu = cpu;
@@ -2686,8 +2703,6 @@ static void
account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
update_load_add(&cfs_rq->load, se->load.weight);
- if (!parent_entity(se))
- update_load_add(&rq_of(cfs_rq)->load, se->load.weight);
#ifdef CONFIG_SMP
if (entity_is_task(se)) {
struct rq *rq = rq_of(cfs_rq);
@@ -2703,8 +2718,6 @@ static void
account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
update_load_sub(&cfs_rq->load, se->load.weight);
- if (!parent_entity(se))
- update_load_sub(&rq_of(cfs_rq)->load, se->load.weight);
#ifdef CONFIG_SMP
if (entity_is_task(se)) {
account_numa_dequeue(rq_of(cfs_rq), task_of(se));
@@ -3334,6 +3347,9 @@ static inline int propagate_entity_load_avg(struct sched_entity *se)
update_tg_cfs_util(cfs_rq, se, gcfs_rq);
update_tg_cfs_runnable(cfs_rq, se, gcfs_rq);
+ trace_pelt_cfs_tp(cfs_rq);
+ trace_pelt_se_tp(se);
+
return 1;
}
@@ -3486,6 +3502,8 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
add_tg_cfs_propagate(cfs_rq, se->avg.load_sum);
cfs_rq_util_change(cfs_rq, flags);
+
+ trace_pelt_cfs_tp(cfs_rq);
}
/**
@@ -3505,6 +3523,8 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
add_tg_cfs_propagate(cfs_rq, -se->avg.load_sum);
cfs_rq_util_change(cfs_rq, 0);
+
+ trace_pelt_cfs_tp(cfs_rq);
}
/*
@@ -4100,7 +4120,8 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
* least twice that of our own weight (i.e. dont track it
* when there are only lesser-weight tasks around):
*/
- if (schedstat_enabled() && rq_of(cfs_rq)->load.weight >= 2*se->load.weight) {
+ if (schedstat_enabled() &&
+ rq_of(cfs_rq)->cfs.load.weight >= 2*se->load.weight) {
schedstat_set(se->statistics.slice_max,
max((u64)schedstat_val(se->statistics.slice_max),
se->sum_exec_runtime - se->prev_sum_exec_runtime));
@@ -4734,6 +4755,11 @@ static void start_cfs_slack_bandwidth(struct cfs_bandwidth *cfs_b)
if (runtime_refresh_within(cfs_b, min_left))
return;
+ /* don't push forwards an existing deferred unthrottle */
+ if (cfs_b->slack_started)
+ return;
+ cfs_b->slack_started = true;
+
hrtimer_start(&cfs_b->slack_timer,
ns_to_ktime(cfs_bandwidth_slack_period),
HRTIMER_MODE_REL);
@@ -4787,6 +4813,7 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
/* confirm we're still not at a refresh boundary */
raw_spin_lock_irqsave(&cfs_b->lock, flags);
+ cfs_b->slack_started = false;
if (cfs_b->distribute_running) {
raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
return;
@@ -4950,6 +4977,7 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
cfs_b->slack_timer.function = sched_cfs_slack_timer;
cfs_b->distribute_running = 0;
+ cfs_b->slack_started = false;
}
static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
@@ -5153,8 +5181,10 @@ static inline bool cpu_overutilized(int cpu)
static inline void update_overutilized_status(struct rq *rq)
{
- if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu))
+ if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu)) {
WRITE_ONCE(rq->rd->overutilized, SG_OVERUTILIZED);
+ trace_sched_overutilized_tp(rq->rd, SG_OVERUTILIZED);
+ }
}
#else
static inline void update_overutilized_status(struct rq *rq) { }
@@ -5325,71 +5355,6 @@ DEFINE_PER_CPU(cpumask_var_t, load_balance_mask);
DEFINE_PER_CPU(cpumask_var_t, select_idle_mask);
#ifdef CONFIG_NO_HZ_COMMON
-/*
- * per rq 'load' arrray crap; XXX kill this.
- */
-
-/*
- * The exact cpuload calculated at every tick would be:
- *
- * load' = (1 - 1/2^i) * load + (1/2^i) * cur_load
- *
- * If a CPU misses updates for n ticks (as it was idle) and update gets
- * called on the n+1-th tick when CPU may be busy, then we have:
- *
- * load_n = (1 - 1/2^i)^n * load_0
- * load_n+1 = (1 - 1/2^i) * load_n + (1/2^i) * cur_load
- *
- * decay_load_missed() below does efficient calculation of
- *
- * load' = (1 - 1/2^i)^n * load
- *
- * Because x^(n+m) := x^n * x^m we can decompose any x^n in power-of-2 factors.
- * This allows us to precompute the above in said factors, thereby allowing the
- * reduction of an arbitrary n in O(log_2 n) steps. (See also
- * fixed_power_int())
- *
- * The calculation is approximated on a 128 point scale.
- */
-#define DEGRADE_SHIFT 7
-
-static const u8 degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128};
-static const u8 degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = {
- { 0, 0, 0, 0, 0, 0, 0, 0 },
- { 64, 32, 8, 0, 0, 0, 0, 0 },
- { 96, 72, 40, 12, 1, 0, 0, 0 },
- { 112, 98, 75, 43, 15, 1, 0, 0 },
- { 120, 112, 98, 76, 45, 16, 2, 0 }
-};
-
-/*
- * Update cpu_load for any missed ticks, due to tickless idle. The backlog
- * would be when CPU is idle and so we just decay the old load without
- * adding any new load.
- */
-static unsigned long
-decay_load_missed(unsigned long load, unsigned long missed_updates, int idx)
-{
- int j = 0;
-
- if (!missed_updates)
- return load;
-
- if (missed_updates >= degrade_zero_ticks[idx])
- return 0;
-
- if (idx == 1)
- return load >> missed_updates;
-
- while (missed_updates) {
- if (missed_updates % 2)
- load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT;
-
- missed_updates >>= 1;
- j++;
- }
- return load;
-}
static struct {
cpumask_var_t idle_cpus_mask;
@@ -5401,234 +5366,11 @@ static struct {
#endif /* CONFIG_NO_HZ_COMMON */
-/**
- * __cpu_load_update - update the rq->cpu_load[] statistics
- * @this_rq: The rq to update statistics for
- * @this_load: The current load
- * @pending_updates: The number of missed updates
- *
- * Update rq->cpu_load[] statistics. This function is usually called every
- * scheduler tick (TICK_NSEC).
- *
- * This function computes a decaying average:
- *
- * load[i]' = (1 - 1/2^i) * load[i] + (1/2^i) * load
- *
- * Because of NOHZ it might not get called on every tick which gives need for
- * the @pending_updates argument.
- *
- * load[i]_n = (1 - 1/2^i) * load[i]_n-1 + (1/2^i) * load_n-1
- * = A * load[i]_n-1 + B ; A := (1 - 1/2^i), B := (1/2^i) * load
- * = A * (A * load[i]_n-2 + B) + B
- * = A * (A * (A * load[i]_n-3 + B) + B) + B
- * = A^3 * load[i]_n-3 + (A^2 + A + 1) * B
- * = A^n * load[i]_0 + (A^(n-1) + A^(n-2) + ... + 1) * B
- * = A^n * load[i]_0 + ((1 - A^n) / (1 - A)) * B
- * = (1 - 1/2^i)^n * (load[i]_0 - load) + load
- *
- * In the above we've assumed load_n := load, which is true for NOHZ_FULL as
- * any change in load would have resulted in the tick being turned back on.
- *
- * For regular NOHZ, this reduces to:
- *
- * load[i]_n = (1 - 1/2^i)^n * load[i]_0
- *
- * see decay_load_misses(). For NOHZ_FULL we get to subtract and add the extra
- * term.
- */
-static void cpu_load_update(struct rq *this_rq, unsigned long this_load,
- unsigned long pending_updates)
-{
- unsigned long __maybe_unused tickless_load = this_rq->cpu_load[0];
- int i, scale;
-
- this_rq->nr_load_updates++;
-
- /* Update our load: */
- this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */
- for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) {
- unsigned long old_load, new_load;
-
- /* scale is effectively 1 << i now, and >> i divides by scale */
-
- old_load = this_rq->cpu_load[i];
-#ifdef CONFIG_NO_HZ_COMMON
- old_load = decay_load_missed(old_load, pending_updates - 1, i);
- if (tickless_load) {
- old_load -= decay_load_missed(tickless_load, pending_updates - 1, i);
- /*
- * old_load can never be a negative value because a
- * decayed tickless_load cannot be greater than the
- * original tickless_load.
- */
- old_load += tickless_load;
- }
-#endif
- new_load = this_load;
- /*
- * Round up the averaging division if load is increasing. This
- * prevents us from getting stuck on 9 if the load is 10, for
- * example.
- */
- if (new_load > old_load)
- new_load += scale - 1;
-
- this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i;
- }
-}
-
-/* Used instead of source_load when we know the type == 0 */
-static unsigned long weighted_cpuload(struct rq *rq)
+static unsigned long cpu_runnable_load(struct rq *rq)
{
return cfs_rq_runnable_load_avg(&rq->cfs);
}
-#ifdef CONFIG_NO_HZ_COMMON
-/*
- * There is no sane way to deal with nohz on smp when using jiffies because the
- * CPU doing the jiffies update might drift wrt the CPU doing the jiffy reading
- * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}.
- *
- * Therefore we need to avoid the delta approach from the regular tick when
- * possible since that would seriously skew the load calculation. This is why we
- * use cpu_load_update_periodic() for CPUs out of nohz. However we'll rely on
- * jiffies deltas for updates happening while in nohz mode (idle ticks, idle
- * loop exit, nohz_idle_balance, nohz full exit...)
- *
- * This means we might still be one tick off for nohz periods.
- */
-
-static void cpu_load_update_nohz(struct rq *this_rq,
- unsigned long curr_jiffies,
- unsigned long load)
-{
- unsigned long pending_updates;
-
- pending_updates = curr_jiffies - this_rq->last_load_update_tick;
- if (pending_updates) {
- this_rq->last_load_update_tick = curr_jiffies;
- /*
- * In the regular NOHZ case, we were idle, this means load 0.
- * In the NOHZ_FULL case, we were non-idle, we should consider
- * its weighted load.
- */
- cpu_load_update(this_rq, load, pending_updates);
- }
-}
-
-/*
- * Called from nohz_idle_balance() to update the load ratings before doing the
- * idle balance.
- */
-static void cpu_load_update_idle(struct rq *this_rq)
-{
- /*
- * bail if there's load or we're actually up-to-date.
- */
- if (weighted_cpuload(this_rq))
- return;
-
- cpu_load_update_nohz(this_rq, READ_ONCE(jiffies), 0);
-}
-
-/*
- * Record CPU load on nohz entry so we know the tickless load to account
- * on nohz exit. cpu_load[0] happens then to be updated more frequently
- * than other cpu_load[idx] but it should be fine as cpu_load readers
- * shouldn't rely into synchronized cpu_load[*] updates.
- */
-void cpu_load_update_nohz_start(void)
-{
- struct rq *this_rq = this_rq();
-
- /*
- * This is all lockless but should be fine. If weighted_cpuload changes
- * concurrently we'll exit nohz. And cpu_load write can race with
- * cpu_load_update_idle() but both updater would be writing the same.
- */
- this_rq->cpu_load[0] = weighted_cpuload(this_rq);
-}
-
-/*
- * Account the tickless load in the end of a nohz frame.
- */
-void cpu_load_update_nohz_stop(void)
-{
- unsigned long curr_jiffies = READ_ONCE(jiffies);
- struct rq *this_rq = this_rq();
- unsigned long load;
- struct rq_flags rf;
-
- if (curr_jiffies == this_rq->last_load_update_tick)
- return;
-
- load = weighted_cpuload(this_rq);
- rq_lock(this_rq, &rf);
- update_rq_clock(this_rq);
- cpu_load_update_nohz(this_rq, curr_jiffies, load);
- rq_unlock(this_rq, &rf);
-}
-#else /* !CONFIG_NO_HZ_COMMON */
-static inline void cpu_load_update_nohz(struct rq *this_rq,
- unsigned long curr_jiffies,
- unsigned long load) { }
-#endif /* CONFIG_NO_HZ_COMMON */
-
-static void cpu_load_update_periodic(struct rq *this_rq, unsigned long load)
-{
-#ifdef CONFIG_NO_HZ_COMMON
- /* See the mess around cpu_load_update_nohz(). */
- this_rq->last_load_update_tick = READ_ONCE(jiffies);
-#endif
- cpu_load_update(this_rq, load, 1);
-}
-
-/*
- * Called from scheduler_tick()
- */
-void cpu_load_update_active(struct rq *this_rq)
-{
- unsigned long load = weighted_cpuload(this_rq);
-
- if (tick_nohz_tick_stopped())
- cpu_load_update_nohz(this_rq, READ_ONCE(jiffies), load);
- else
- cpu_load_update_periodic(this_rq, load);
-}
-
-/*
- * Return a low guess at the load of a migration-source CPU weighted
- * according to the scheduling class and "nice" value.
- *
- * We want to under-estimate the load of migration sources, to
- * balance conservatively.
- */
-static unsigned long source_load(int cpu, int type)
-{
- struct rq *rq = cpu_rq(cpu);
- unsigned long total = weighted_cpuload(rq);
-
- if (type == 0 || !sched_feat(LB_BIAS))
- return total;
-
- return min(rq->cpu_load[type-1], total);
-}
-
-/*
- * Return a high guess at the load of a migration-target CPU weighted
- * according to the scheduling class and "nice" value.
- */
-static unsigned long target_load(int cpu, int type)
-{
- struct rq *rq = cpu_rq(cpu);
- unsigned long total = weighted_cpuload(rq);
-
- if (type == 0 || !sched_feat(LB_BIAS))
- return total;
-
- return max(rq->cpu_load[type-1], total);
-}
-
static unsigned long capacity_of(int cpu)
{
return cpu_rq(cpu)->cpu_capacity;
@@ -5638,7 +5380,7 @@ static unsigned long cpu_avg_load_per_task(int cpu)
{
struct rq *rq = cpu_rq(cpu);
unsigned long nr_running = READ_ONCE(rq->cfs.h_nr_running);
- unsigned long load_avg = weighted_cpuload(rq);
+ unsigned long load_avg = cpu_runnable_load(rq);
if (nr_running)
return load_avg / nr_running;
@@ -5736,7 +5478,7 @@ wake_affine_weight(struct sched_domain *sd, struct task_struct *p,
s64 this_eff_load, prev_eff_load;
unsigned long task_load;
- this_eff_load = target_load(this_cpu, sd->wake_idx);
+ this_eff_load = cpu_runnable_load(cpu_rq(this_cpu));
if (sync) {
unsigned long current_load = task_h_load(current);
@@ -5754,7 +5496,7 @@ wake_affine_weight(struct sched_domain *sd, struct task_struct *p,
this_eff_load *= 100;
this_eff_load *= capacity_of(prev_cpu);
- prev_eff_load = source_load(prev_cpu, sd->wake_idx);
+ prev_eff_load = cpu_runnable_load(cpu_rq(prev_cpu));
prev_eff_load -= task_load;
if (sched_feat(WA_BIAS))
prev_eff_load *= 100 + (sd->imbalance_pct - 100) / 2;
@@ -5815,14 +5557,10 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
unsigned long this_runnable_load = ULONG_MAX;
unsigned long min_avg_load = ULONG_MAX, this_avg_load = ULONG_MAX;
unsigned long most_spare = 0, this_spare = 0;
- int load_idx = sd->forkexec_idx;
int imbalance_scale = 100 + (sd->imbalance_pct-100)/2;
unsigned long imbalance = scale_load_down(NICE_0_LOAD) *
(sd->imbalance_pct-100) / 100;
- if (sd_flag & SD_BALANCE_WAKE)
- load_idx = sd->wake_idx;
-
do {
unsigned long load, avg_load, runnable_load;
unsigned long spare_cap, max_spare_cap;
@@ -5831,7 +5569,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
/* Skip over this group if it has no CPUs allowed */
if (!cpumask_intersects(sched_group_span(group),
- &p->cpus_allowed))
+ p->cpus_ptr))
continue;
local_group = cpumask_test_cpu(this_cpu,
@@ -5846,12 +5584,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
max_spare_cap = 0;
for_each_cpu(i, sched_group_span(group)) {
- /* Bias balancing toward CPUs of our domain */
- if (local_group)
- load = source_load(i, load_idx);
- else
- load = target_load(i, load_idx);
-
+ load = cpu_runnable_load(cpu_rq(i));
runnable_load += load;
avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs);
@@ -5963,7 +5696,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this
return cpumask_first(sched_group_span(group));
/* Traverse only the allowed CPUs */
- for_each_cpu_and(i, sched_group_span(group), &p->cpus_allowed) {
+ for_each_cpu_and(i, sched_group_span(group), p->cpus_ptr) {
if (available_idle_cpu(i)) {
struct rq *rq = cpu_rq(i);
struct cpuidle_state *idle = idle_get_state(rq);
@@ -5987,7 +5720,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this
shallowest_idle_cpu = i;
}
} else if (shallowest_idle_cpu == -1) {
- load = weighted_cpuload(cpu_rq(i));
+ load = cpu_runnable_load(cpu_rq(i));
if (load < min_load) {
min_load = load;
least_loaded_cpu = i;
@@ -6003,7 +5736,7 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p
{
int new_cpu = cpu;
- if (!cpumask_intersects(sched_domain_span(sd), &p->cpus_allowed))
+ if (!cpumask_intersects(sched_domain_span(sd), p->cpus_ptr))
return prev_cpu;
/*
@@ -6120,7 +5853,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
if (!test_idle_cores(target, false))
return -1;
- cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed);
+ cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
for_each_cpu_wrap(core, cpus, target) {
bool idle = true;
@@ -6154,7 +5887,7 @@ static int select_idle_smt(struct task_struct *p, int target)
return -1;
for_each_cpu(cpu, cpu_smt_mask(target)) {
- if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
+ if (!cpumask_test_cpu(cpu, p->cpus_ptr))
continue;
if (available_idle_cpu(cpu))
return cpu;
@@ -6218,7 +5951,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
for_each_cpu_wrap(cpu, sched_domain_span(sd), target) {
if (!--nr)
return -1;
- if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
+ if (!cpumask_test_cpu(cpu, p->cpus_ptr))
continue;
if (available_idle_cpu(cpu))
break;
@@ -6255,7 +5988,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
recent_used_cpu != target &&
cpus_share_cache(recent_used_cpu, target) &&
available_idle_cpu(recent_used_cpu) &&
- cpumask_test_cpu(p->recent_used_cpu, &p->cpus_allowed)) {
+ cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr)) {
/*
* Replace recent_used_cpu with prev as it is a potential
* candidate for the next wake:
@@ -6499,11 +6232,21 @@ static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu)
static long
compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd)
{
- long util, max_util, sum_util, energy = 0;
+ unsigned int max_util, util_cfs, cpu_util, cpu_cap;
+ unsigned long sum_util, energy = 0;
+ struct task_struct *tsk;
int cpu;
for (; pd; pd = pd->next) {
+ struct cpumask *pd_mask = perf_domain_span(pd);
+
+ /*
+ * The energy model mandates all the CPUs of a performance
+ * domain have the same capacity.
+ */
+ cpu_cap = arch_scale_cpu_capacity(cpumask_first(pd_mask));
max_util = sum_util = 0;
+
/*
* The capacity state of CPUs of the current rd can be driven by
* CPUs of another rd if they belong to the same performance
@@ -6514,11 +6257,29 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd)
* it will not appear in its pd list and will not be accounted
* by compute_energy().
*/
- for_each_cpu_and(cpu, perf_domain_span(pd), cpu_online_mask) {
- util = cpu_util_next(cpu, p, dst_cpu);
- util = schedutil_energy_util(cpu, util);
- max_util = max(util, max_util);
- sum_util += util;
+ for_each_cpu_and(cpu, pd_mask, cpu_online_mask) {
+ util_cfs = cpu_util_next(cpu, p, dst_cpu);
+
+ /*
+ * Busy time computation: utilization clamping is not
+ * required since the ratio (sum_util / cpu_capacity)
+ * is already enough to scale the EM reported power
+ * consumption at the (eventually clamped) cpu_capacity.
+ */
+ sum_util += schedutil_cpu_util(cpu, util_cfs, cpu_cap,
+ ENERGY_UTIL, NULL);
+
+ /*
+ * Performance domain frequency: utilization clamping
+ * must be considered since it affects the selection
+ * of the performance domain frequency.
+ * NOTE: in case RT tasks are running, by default the
+ * FREQUENCY_UTIL's utilization can be max OPP.
+ */
+ tsk = cpu == dst_cpu ? p : NULL;
+ cpu_util = schedutil_cpu_util(cpu, util_cfs, cpu_cap,
+ FREQUENCY_UTIL, tsk);
+ max_util = max(max_util, cpu_util);
}
energy += em_pd_energy(pd->em_pd, max_util, sum_util);
@@ -6601,7 +6362,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
int max_spare_cap_cpu = -1;
for_each_cpu_and(cpu, perf_domain_span(pd), sched_domain_span(sd)) {
- if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
+ if (!cpumask_test_cpu(cpu, p->cpus_ptr))
continue;
/* Skip CPUs that will be overutilized. */
@@ -6690,7 +6451,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
}
want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu) &&
- cpumask_test_cpu(cpu, &p->cpus_allowed);
+ cpumask_test_cpu(cpu, p->cpus_ptr);
}
rcu_read_lock();
@@ -7446,14 +7207,14 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
/*
* We do not migrate tasks that are:
* 1) throttled_lb_pair, or
- * 2) cannot be migrated to this CPU due to cpus_allowed, or
+ * 2) cannot be migrated to this CPU due to cpus_ptr, or
* 3) running (obviously), or
* 4) are cache-hot on their current CPU.
*/
if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu))
return 0;
- if (!cpumask_test_cpu(env->dst_cpu, &p->cpus_allowed)) {
+ if (!cpumask_test_cpu(env->dst_cpu, p->cpus_ptr)) {
int cpu;
schedstat_inc(p->se.statistics.nr_failed_migrations_affine);
@@ -7473,7 +7234,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
/* Prevent to re-select dst_cpu via env's CPUs: */
for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) {
- if (cpumask_test_cpu(cpu, &p->cpus_allowed)) {
+ if (cpumask_test_cpu(cpu, p->cpus_ptr)) {
env->flags |= LBF_DST_PINNED;
env->new_dst_cpu = cpu;
break;
@@ -7559,7 +7320,7 @@ static struct task_struct *detach_one_task(struct lb_env *env)
static const unsigned int sched_nr_migrate_break = 32;
/*
- * detach_tasks() -- tries to detach up to imbalance weighted load from
+ * detach_tasks() -- tries to detach up to imbalance runnable load from
* busiest_rq, as part of a balancing operation within domain "sd".
*
* Returns number of detached tasks if successful and 0 otherwise.
@@ -7627,7 +7388,7 @@ static int detach_tasks(struct lb_env *env)
/*
* We only want to steal up to the prescribed amount of
- * weighted load.
+ * runnable load.
*/
if (env->imbalance <= 0)
break;
@@ -7696,6 +7457,7 @@ static void attach_tasks(struct lb_env *env)
rq_unlock(env->dst_rq, &rf);
}
+#ifdef CONFIG_NO_HZ_COMMON
static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq)
{
if (cfs_rq->avg.load_avg)
@@ -7723,6 +7485,19 @@ static inline bool others_have_blocked(struct rq *rq)
return false;
}
+static inline void update_blocked_load_status(struct rq *rq, bool has_blocked)
+{
+ rq->last_blocked_load_update_tick = jiffies;
+
+ if (!has_blocked)
+ rq->has_blocked_load = 0;
+}
+#else
+static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq) { return false; }
+static inline bool others_have_blocked(struct rq *rq) { return false; }
+static inline void update_blocked_load_status(struct rq *rq, bool has_blocked) {}
+#endif
+
#ifdef CONFIG_FAIR_GROUP_SCHED
static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
@@ -7788,11 +7563,7 @@ static void update_blocked_averages(int cpu)
if (others_have_blocked(rq))
done = false;
-#ifdef CONFIG_NO_HZ_COMMON
- rq->last_blocked_load_update_tick = jiffies;
- if (done)
- rq->has_blocked_load = 0;
-#endif
+ update_blocked_load_status(rq, !done);
rq_unlock_irqrestore(rq, &rf);
}
@@ -7858,11 +7629,7 @@ static inline void update_blocked_averages(int cpu)
update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
update_irq_load_avg(rq, 0);
-#ifdef CONFIG_NO_HZ_COMMON
- rq->last_blocked_load_update_tick = jiffies;
- if (!cfs_rq_has_blocked(cfs_rq) && !others_have_blocked(rq))
- rq->has_blocked_load = 0;
-#endif
+ update_blocked_load_status(rq, cfs_rq_has_blocked(cfs_rq) || others_have_blocked(rq));
rq_unlock_irqrestore(rq, &rf);
}
@@ -7880,7 +7647,6 @@ static unsigned long task_h_load(struct task_struct *p)
struct sg_lb_stats {
unsigned long avg_load; /*Avg load across the CPUs of the group */
unsigned long group_load; /* Total load over the CPUs of the group */
- unsigned long sum_weighted_load; /* Weighted load of group's tasks */
unsigned long load_per_task;
unsigned long group_capacity;
unsigned long group_util; /* Total utilization of the group */
@@ -7934,38 +7700,10 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds)
};
}
-/**
- * get_sd_load_idx - Obtain the load index for a given sched domain.
- * @sd: The sched_domain whose load_idx is to be obtained.
- * @idle: The idle status of the CPU for whose sd load_idx is obtained.
- *
- * Return: The load index.
- */
-static inline int get_sd_load_idx(struct sched_domain *sd,
- enum cpu_idle_type idle)
-{
- int load_idx;
-
- switch (idle) {
- case CPU_NOT_IDLE:
- load_idx = sd->busy_idx;
- break;
-
- case CPU_NEWLY_IDLE:
- load_idx = sd->newidle_idx;
- break;
- default:
- load_idx = sd->idle_idx;
- break;
- }
-
- return load_idx;
-}
-
static unsigned long scale_rt_capacity(struct sched_domain *sd, int cpu)
{
struct rq *rq = cpu_rq(cpu);
- unsigned long max = arch_scale_cpu_capacity(sd, cpu);
+ unsigned long max = arch_scale_cpu_capacity(cpu);
unsigned long used, free;
unsigned long irq;
@@ -7990,7 +7728,7 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
unsigned long capacity = scale_rt_capacity(sd, cpu);
struct sched_group *sdg = sd->groups;
- cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(sd, cpu);
+ cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(cpu);
if (!capacity)
capacity = 1;
@@ -8100,7 +7838,7 @@ static inline int check_misfit_status(struct rq *rq, struct sched_domain *sd)
/*
* Group imbalance indicates (and tries to solve) the problem where balancing
- * groups is inadequate due to ->cpus_allowed constraints.
+ * groups is inadequate due to ->cpus_ptr constraints.
*
* Imagine a situation of two groups of 4 CPUs each and 4 tasks each with a
* cpumask covering 1 CPU of the first group and 3 CPUs of the second group.
@@ -8250,9 +7988,6 @@ static inline void update_sg_lb_stats(struct lb_env *env,
struct sg_lb_stats *sgs,
int *sg_status)
{
- int local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(group));
- int load_idx = get_sd_load_idx(env->sd, env->idle);
- unsigned long load;
int i, nr_running;
memset(sgs, 0, sizeof(*sgs));
@@ -8263,13 +7998,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
if ((env->flags & LBF_NOHZ_STATS) && update_nohz_stats(rq, false))
env->flags |= LBF_NOHZ_AGAIN;
- /* Bias balancing toward CPUs of our domain: */
- if (local_group)
- load = target_load(i, load_idx);
- else
- load = source_load(i, load_idx);
-
- sgs->group_load += load;
+ sgs->group_load += cpu_runnable_load(rq);
sgs->group_util += cpu_util(i);
sgs->sum_nr_running += rq->cfs.h_nr_running;
@@ -8284,7 +8013,6 @@ static inline void update_sg_lb_stats(struct lb_env *env,
sgs->nr_numa_running += rq->nr_numa_running;
sgs->nr_preferred_running += rq->nr_preferred_running;
#endif
- sgs->sum_weighted_load += weighted_cpuload(rq);
/*
* No need to call idle_cpu() if nr_running is not 0
*/
@@ -8303,7 +8031,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
sgs->avg_load = (sgs->group_load*SCHED_CAPACITY_SCALE) / sgs->group_capacity;
if (sgs->sum_nr_running)
- sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
+ sgs->load_per_task = sgs->group_load / sgs->sum_nr_running;
sgs->group_weight = group->group_weight;
@@ -8517,8 +8245,12 @@ next_group:
/* Update over-utilization (tipping point, U >= 0) indicator */
WRITE_ONCE(rd->overutilized, sg_status & SG_OVERUTILIZED);
+ trace_sched_overutilized_tp(rd, sg_status & SG_OVERUTILIZED);
} else if (sg_status & SG_OVERUTILIZED) {
- WRITE_ONCE(env->dst_rq->rd->overutilized, SG_OVERUTILIZED);
+ struct root_domain *rd = env->dst_rq->rd;
+
+ WRITE_ONCE(rd->overutilized, SG_OVERUTILIZED);
+ trace_sched_overutilized_tp(rd, SG_OVERUTILIZED);
}
}
@@ -8724,7 +8456,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
* find_busiest_group - Returns the busiest group within the sched_domain
* if there is an imbalance.
*
- * Also calculates the amount of weighted load which should be moved
+ * Also calculates the amount of runnable load which should be moved
* to restore balance.
*
* @env: The load balancing environment.
@@ -8769,7 +8501,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
/*
* If the busiest group is imbalanced the below checks don't
* work because they assume all things are equal, which typically
- * isn't true due to cpus_allowed constraints and the like.
+ * isn't true due to cpus_ptr constraints and the like.
*/
if (busiest->group_type == group_imbalanced)
goto force_balance;
@@ -8843,7 +8575,7 @@ static struct rq *find_busiest_queue(struct lb_env *env,
int i;
for_each_cpu_and(i, sched_group_span(group), env->cpus) {
- unsigned long capacity, wl;
+ unsigned long capacity, load;
enum fbq_type rt;
rq = cpu_rq(i);
@@ -8897,30 +8629,30 @@ static struct rq *find_busiest_queue(struct lb_env *env,
rq->nr_running == 1)
continue;
- wl = weighted_cpuload(rq);
+ load = cpu_runnable_load(rq);
/*
- * When comparing with imbalance, use weighted_cpuload()
+ * When comparing with imbalance, use cpu_runnable_load()
* which is not scaled with the CPU capacity.
*/
- if (rq->nr_running == 1 && wl > env->imbalance &&
+ if (rq->nr_running == 1 && load > env->imbalance &&
!check_cpu_capacity(rq, env->sd))
continue;
/*
* For the load comparisons with the other CPU's, consider
- * the weighted_cpuload() scaled with the CPU capacity, so
+ * the cpu_runnable_load() scaled with the CPU capacity, so
* that the load can be moved away from the CPU that is
* potentially running at a lower capacity.
*
- * Thus we're looking for max(wl_i / capacity_i), crosswise
+ * Thus we're looking for max(load_i / capacity_i), crosswise
* multiplication to rid ourselves of the division works out
- * to: wl_i * capacity_j > wl_j * capacity_i; where j is
+ * to: load_i * capacity_j > load_j * capacity_i; where j is
* our previous maximum.
*/
- if (wl * busiest_capacity > busiest_load * capacity) {
- busiest_load = wl;
+ if (load * busiest_capacity > busiest_load * capacity) {
+ busiest_load = load;
busiest_capacity = capacity;
busiest = rq;
}
@@ -9211,7 +8943,7 @@ more_balance:
* if the curr task on busiest CPU can't be
* moved to this_cpu:
*/
- if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) {
+ if (!cpumask_test_cpu(this_cpu, busiest->curr->cpus_ptr)) {
raw_spin_unlock_irqrestore(&busiest->lock,
flags);
env.flags |= LBF_ALL_PINNED;
@@ -9880,7 +9612,6 @@ static bool _nohz_idle_balance(struct rq *this_rq, unsigned int flags,
rq_lock_irqsave(rq, &rf);
update_rq_clock(rq);
- cpu_load_update_idle(rq);
rq_unlock_irqrestore(rq, &rf);
if (flags & NOHZ_BALANCE_KICK)
@@ -10691,6 +10422,10 @@ const struct sched_class fair_sched_class = {
#ifdef CONFIG_FAIR_GROUP_SCHED
.task_change_group = task_change_group_fair,
#endif
+
+#ifdef CONFIG_UCLAMP_TASK
+ .uclamp_enabled = 1,
+#endif
};
#ifdef CONFIG_SCHED_DEBUG
@@ -10738,3 +10473,83 @@ __init void init_sched_fair_class(void)
#endif /* SMP */
}
+
+/*
+ * Helper functions to facilitate extracting info from tracepoints.
+ */
+
+const struct sched_avg *sched_trace_cfs_rq_avg(struct cfs_rq *cfs_rq)
+{
+#ifdef CONFIG_SMP
+ return cfs_rq ? &cfs_rq->avg : NULL;
+#else
+ return NULL;
+#endif
+}
+EXPORT_SYMBOL_GPL(sched_trace_cfs_rq_avg);
+
+char *sched_trace_cfs_rq_path(struct cfs_rq *cfs_rq, char *str, int len)
+{
+ if (!cfs_rq) {
+ if (str)
+ strlcpy(str, "(null)", len);
+ else
+ return NULL;
+ }
+
+ cfs_rq_tg_path(cfs_rq, str, len);
+ return str;
+}
+EXPORT_SYMBOL_GPL(sched_trace_cfs_rq_path);
+
+int sched_trace_cfs_rq_cpu(struct cfs_rq *cfs_rq)
+{
+ return cfs_rq ? cpu_of(rq_of(cfs_rq)) : -1;
+}
+EXPORT_SYMBOL_GPL(sched_trace_cfs_rq_cpu);
+
+const struct sched_avg *sched_trace_rq_avg_rt(struct rq *rq)
+{
+#ifdef CONFIG_SMP
+ return rq ? &rq->avg_rt : NULL;
+#else
+ return NULL;
+#endif
+}
+EXPORT_SYMBOL_GPL(sched_trace_rq_avg_rt);
+
+const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq)
+{
+#ifdef CONFIG_SMP
+ return rq ? &rq->avg_dl : NULL;
+#else
+ return NULL;
+#endif
+}
+EXPORT_SYMBOL_GPL(sched_trace_rq_avg_dl);
+
+const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq)
+{
+#if defined(CONFIG_SMP) && defined(CONFIG_HAVE_SCHED_AVG_IRQ)
+ return rq ? &rq->avg_irq : NULL;
+#else
+ return NULL;
+#endif
+}
+EXPORT_SYMBOL_GPL(sched_trace_rq_avg_irq);
+
+int sched_trace_rq_cpu(struct rq *rq)
+{
+ return rq ? cpu_of(rq) : -1;
+}
+EXPORT_SYMBOL_GPL(sched_trace_rq_cpu);
+
+const struct cpumask *sched_trace_rd_span(struct root_domain *rd)
+{
+#ifdef CONFIG_SMP
+ return rd ? rd->span : NULL;
+#else
+ return NULL;
+#endif
+}
+EXPORT_SYMBOL_GPL(sched_trace_rd_span);