* 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>
*
* This idea comes from the SD scheduler of Con Kolivas:
*/
-static int get_update_sysctl_factor(void)
+static unsigned int get_update_sysctl_factor(void)
{
- unsigned int cpus = min_t(int, num_online_cpus(), 8);
+ unsigned int cpus = min_t(unsigned int, num_online_cpus(), 8);
unsigned int factor;
switch (sysctl_sched_tunable_scaling) {
return grp->my_q;
}
-static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq,
- int force_update);
-
static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
{
if (!cfs_rq->on_list) {
}
cfs_rq->on_list = 1;
- /* We should have no load, but we need to update last_decay. */
- update_cfs_rq_blocked_load(cfs_rq, 0);
}
}
loff_t *ppos)
{
int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
- int factor = get_update_sysctl_factor();
+ unsigned int factor = get_update_sysctl_factor();
if (ret || !write)
return ret;
*/
static u64 __sched_period(unsigned long nr_running)
{
- u64 period = sysctl_sched_latency;
- unsigned long nr_latency = sched_nr_latency;
-
- if (unlikely(nr_running > nr_latency)) {
- period = sysctl_sched_min_granularity;
- period *= nr_running;
- }
-
- return period;
+ if (unlikely(nr_running > sched_nr_latency))
+ return nr_running * sysctl_sched_min_granularity;
+ else
+ return sysctl_sched_latency;
}
/*
static int select_idle_sibling(struct task_struct *p, int cpu);
static unsigned long task_h_load(struct task_struct *p);
-static inline void __update_task_entity_contrib(struct sched_entity *se);
-static inline void __update_task_entity_utilization(struct sched_entity *se);
+/*
+ * 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 task start runnable values to heavy its load in infant time */
-void init_task_runnable_average(struct task_struct *p)
+/* Give new sched_entity start runnable values to heavy its load in infant time */
+void init_entity_runnable_average(struct sched_entity *se)
{
- u32 slice;
+ struct sched_avg *sa = &se->avg;
- slice = sched_slice(task_cfs_rq(p), &p->se) >> 10;
- p->se.avg.runnable_avg_sum = p->se.avg.running_avg_sum = slice;
- p->se.avg.avg_period = slice;
- __update_task_entity_contrib(&p->se);
- __update_task_entity_utilization(&p->se);
+ sa->last_update_time = 0;
+ /*
+ * sched_avg's period_contrib should be strictly less then 1024, so
+ * we give it 1023 to make sure it is almost a period (1024us), and
+ * will definitely be update (after enqueue).
+ */
+ sa->period_contrib = 1023;
+ 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 = sa->util_avg * LOAD_AVG_MAX;
+ /* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
}
+
+static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq);
+static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq);
#else
-void init_task_runnable_average(struct task_struct *p)
+void init_entity_runnable_average(struct sched_entity *se)
{
}
#endif
static unsigned int task_scan_min(struct task_struct *p)
{
- unsigned int scan_size = ACCESS_ONCE(sysctl_numa_balancing_scan_size);
+ unsigned int scan_size = READ_ONCE(sysctl_numa_balancing_scan_size);
unsigned int scan, floor;
unsigned int windows = 1;
static bool load_too_imbalanced(long src_load, long dst_load,
struct task_numa_env *env)
{
+ long imb, old_imb;
+ long orig_src_load, orig_dst_load;
long src_capacity, dst_capacity;
- long orig_src_load;
- long load_a, load_b;
- long moved_load;
- long imb;
/*
* The load is corrected for the CPU capacity available on each node.
dst_capacity = env->dst_stats.compute_capacity;
/* We care about the slope of the imbalance, not the direction. */
- load_a = dst_load;
- load_b = src_load;
- if (load_a < load_b)
- swap(load_a, load_b);
+ if (dst_load < src_load)
+ swap(dst_load, src_load);
/* Is the difference below the threshold? */
- imb = load_a * src_capacity * 100 -
- load_b * dst_capacity * env->imbalance_pct;
+ imb = dst_load * src_capacity * 100 -
+ src_load * dst_capacity * env->imbalance_pct;
if (imb <= 0)
return false;
/*
* The imbalance is above the allowed threshold.
- * Allow a move that brings us closer to a balanced situation,
- * without moving things past the point of balance.
+ * Compare it with the old imbalance.
*/
orig_src_load = env->src_stats.load;
+ orig_dst_load = env->dst_stats.load;
- /*
- * In a task swap, there will be one load moving from src to dst,
- * and another moving back. This is the net sum of both moves.
- * A simple task move will always have a positive value.
- * Allow the move if it brings the system closer to a balanced
- * situation, without crossing over the balance point.
- */
- moved_load = orig_src_load - src_load;
+ if (orig_dst_load < orig_src_load)
+ swap(orig_dst_load, orig_src_load);
- if (moved_load > 0)
- /* Moving src -> dst. Did we overshoot balance? */
- return src_load * dst_capacity < dst_load * src_capacity;
- else
- /* Moving dst -> src. Did we overshoot balance? */
- return dst_load * src_capacity < src_load * dst_capacity;
+ old_imb = orig_dst_load * src_capacity * 100 -
+ orig_src_load * dst_capacity * env->imbalance_pct;
+
+ /* Would this change make things worse? */
+ return (imb > old_imb);
}
/*
}
}
+/* Only move tasks to a NUMA node less busy than the current node. */
+static bool numa_has_capacity(struct task_numa_env *env)
+{
+ struct numa_stats *src = &env->src_stats;
+ struct numa_stats *dst = &env->dst_stats;
+
+ if (src->has_free_capacity && !dst->has_free_capacity)
+ return false;
+
+ /*
+ * Only consider a task move if the source has a higher load
+ * than the destination, corrected for CPU capacity on each node.
+ *
+ * src->load dst->load
+ * --------------------- vs ---------------------
+ * src->compute_capacity dst->compute_capacity
+ */
+ if (src->load * dst->compute_capacity * env->imbalance_pct >
+
+ dst->load * src->compute_capacity * 100)
+ return true;
+
+ return false;
+}
+
static int task_numa_migrate(struct task_struct *p)
{
struct task_numa_env env = {
update_numa_stats(&env.dst_stats, env.dst_nid);
/* Try to find a spot on the preferred nid. */
- task_numa_find_cpu(&env, taskimp, groupimp);
+ if (numa_has_capacity(&env))
+ task_numa_find_cpu(&env, taskimp, groupimp);
/*
* Look at other nodes in these cases:
env.dist = dist;
env.dst_nid = nid;
update_numa_stats(&env.dst_stats, env.dst_nid);
- task_numa_find_cpu(&env, taskimp, groupimp);
+ if (numa_has_capacity(&env))
+ task_numa_find_cpu(&env, taskimp, groupimp);
}
}
delta = runtime - p->last_sum_exec_runtime;
*period = now - p->last_task_numa_placement;
} else {
- delta = p->se.avg.runnable_avg_sum;
- *period = p->se.avg.avg_period;
+ delta = p->se.avg.load_sum / p->se.load.weight;
+ *period = LOAD_AVG_MAX;
}
p->last_sum_exec_runtime = runtime;
u64 runtime, period;
spinlock_t *group_lock = NULL;
- seq = ACCESS_ONCE(p->mm->numa_scan_seq);
+ /*
+ * The p->mm->numa_scan_seq field gets updated without
+ * exclusive access. Use READ_ONCE() here to ensure
+ * that the field is read in a single access:
+ */
+ seq = READ_ONCE(p->mm->numa_scan_seq);
if (p->numa_scan_seq == seq)
return;
p->numa_scan_seq = seq;
}
rcu_read_lock();
- tsk = ACCESS_ONCE(cpu_rq(cpu)->curr);
+ tsk = READ_ONCE(cpu_rq(cpu)->curr);
if (!cpupid_match_pid(tsk, cpupid))
goto no_join;
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 */
static void reset_ptenuma_scan(struct task_struct *p)
{
- ACCESS_ONCE(p->mm->numa_scan_seq)++;
+ /*
+ * We only did a read acquisition of the mmap sem, so
+ * p->mm->numa_scan_seq is written to without exclusive access
+ * and the update is not guaranteed to be atomic. That's not
+ * much of an issue though, since this is just used for
+ * statistical sampling. Use READ_ONCE/WRITE_ONCE, which are not
+ * expensive, to avoid any form of compiler optimizations:
+ */
+ WRITE_ONCE(p->mm->numa_scan_seq, READ_ONCE(p->mm->numa_scan_seq) + 1);
p->mm->numa_scan_offset = 0;
}
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));
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) {
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();
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;
long tg_weight;
/*
- * Use this CPU's actual weight instead of the last load_contribution
- * to gain a more accurate current total weight. See
- * update_cfs_rq_load_contribution().
+ * Use this CPU's real-time load instead of the last load contribution
+ * as the updating of the contribution is delayed, and we will use the
+ * the real-time load to calc the share. See update_tg_load_avg().
*/
tg_weight = atomic_long_read(&tg->load_avg);
- tg_weight -= cfs_rq->tg_load_contrib;
+ tg_weight -= cfs_rq->tg_load_avg_contrib;
tg_weight += cfs_rq->load.weight;
return tg_weight;
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_SMP
-/*
- * We choose a half-life close to 1 scheduling period.
- * Note: The tables below 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 */
-
/* Precomputed fixed inverse multiplies for multiplication by y^n */
static const u32 runnable_avg_yN_inv[] = {
0xffffffff, 0xfa83b2da, 0xf5257d14, 0xefe4b99a, 0xeac0c6e6, 0xe5b906e6,
local_n %= LOAD_AVG_PERIOD;
}
- val *= runnable_avg_yN_inv[local_n];
- /* We don't use SRR here since we always want to round down. */
- return val >> 32;
+ val = mul_u64_u32_shr(val, runnable_avg_yN_inv[local_n], 32);
+ return val;
}
/*
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
* load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... )
* = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
*/
-static __always_inline int __update_entity_runnable_avg(u64 now, int cpu,
- struct sched_avg *sa,
- int runnable,
- int running)
+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;
- u32 runnable_contrib;
- int delta_w, decayed = 0;
- unsigned long scale_freq = arch_scale_freq_capacity(NULL, cpu);
+ u64 delta, scaled_delta, periods;
+ u32 contrib;
+ unsigned int delta_w, scaled_delta_w, decayed = 0;
+ unsigned long scale_freq, scale_cpu;
- delta = now - sa->last_runnable_update;
+ delta = now - sa->last_update_time;
/*
* This should only happen when time goes backwards, which it
* unfortunately does during sched clock init when we swap over to TSC.
*/
if ((s64)delta < 0) {
- sa->last_runnable_update = now;
+ sa->last_update_time = now;
return 0;
}
delta >>= 10;
if (!delta)
return 0;
- sa->last_runnable_update = now;
+ 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->avg_period % 1024;
+ delta_w = sa->period_contrib;
if (delta + delta_w >= 1024) {
- /* period roll-over */
decayed = 1;
+ /* how much left for next period will start over, we don't know yet */
+ sa->period_contrib = 0;
+
/*
* Now that we know we're crossing a period boundary, figure
* out how much from delta we need to complete the current
* period and accrue it.
*/
delta_w = 1024 - delta_w;
- if (runnable)
- sa->runnable_avg_sum += delta_w;
+ scaled_delta_w = cap_scale(delta_w, scale_freq);
+ if (weight) {
+ sa->load_sum += weight * scaled_delta_w;
+ if (cfs_rq) {
+ cfs_rq->runnable_load_sum +=
+ weight * scaled_delta_w;
+ }
+ }
if (running)
- sa->running_avg_sum += delta_w * scale_freq
- >> SCHED_CAPACITY_SHIFT;
- sa->avg_period += delta_w;
+ sa->util_sum += scaled_delta_w * scale_cpu;
delta -= delta_w;
periods = delta / 1024;
delta %= 1024;
- sa->runnable_avg_sum = decay_load(sa->runnable_avg_sum,
- periods + 1);
- sa->running_avg_sum = decay_load(sa->running_avg_sum,
- periods + 1);
- sa->avg_period = decay_load(sa->avg_period,
- periods + 1);
+ sa->load_sum = decay_load(sa->load_sum, periods + 1);
+ if (cfs_rq) {
+ cfs_rq->runnable_load_sum =
+ decay_load(cfs_rq->runnable_load_sum, periods + 1);
+ }
+ sa->util_sum = decay_load((u64)(sa->util_sum), periods + 1);
/* Efficiently calculate \sum (1..n_period) 1024*y^i */
- runnable_contrib = __compute_runnable_contrib(periods);
- if (runnable)
- sa->runnable_avg_sum += runnable_contrib;
+ 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->running_avg_sum += runnable_contrib * scale_freq
- >> SCHED_CAPACITY_SHIFT;
- sa->avg_period += runnable_contrib;
+ sa->util_sum += contrib * scale_cpu;
}
/* Remainder of delta accrued against u_0` */
- if (runnable)
- sa->runnable_avg_sum += delta;
+ scaled_delta = cap_scale(delta, scale_freq);
+ if (weight) {
+ sa->load_sum += weight * scaled_delta;
+ if (cfs_rq)
+ cfs_rq->runnable_load_sum += weight * scaled_delta;
+ }
if (running)
- sa->running_avg_sum += delta * scale_freq
- >> SCHED_CAPACITY_SHIFT;
- sa->avg_period += delta;
-
- return decayed;
-}
+ sa->util_sum += scaled_delta * scale_cpu;
-/* Synchronize an entity's decay with its parenting cfs_rq.*/
-static inline u64 __synchronize_entity_decay(struct sched_entity *se)
-{
- struct cfs_rq *cfs_rq = cfs_rq_of(se);
- u64 decays = atomic64_read(&cfs_rq->decay_counter);
-
- decays -= se->avg.decay_count;
- se->avg.decay_count = 0;
- if (!decays)
- return 0;
+ sa->period_contrib += delta;
- se->avg.load_avg_contrib = decay_load(se->avg.load_avg_contrib, decays);
- se->avg.utilization_avg_contrib =
- decay_load(se->avg.utilization_avg_contrib, decays);
+ if (decayed) {
+ sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX);
+ if (cfs_rq) {
+ cfs_rq->runnable_load_avg =
+ div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX);
+ }
+ sa->util_avg = sa->util_sum / LOAD_AVG_MAX;
+ }
- return decays;
+ return decayed;
}
#ifdef CONFIG_FAIR_GROUP_SCHED
-static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq,
- int force_update)
-{
- struct task_group *tg = cfs_rq->tg;
- long tg_contrib;
-
- tg_contrib = cfs_rq->runnable_load_avg + cfs_rq->blocked_load_avg;
- tg_contrib -= cfs_rq->tg_load_contrib;
-
- if (!tg_contrib)
- return;
-
- if (force_update || abs(tg_contrib) > cfs_rq->tg_load_contrib / 8) {
- atomic_long_add(tg_contrib, &tg->load_avg);
- cfs_rq->tg_load_contrib += tg_contrib;
- }
-}
-
/*
- * Aggregate cfs_rq runnable averages into an equivalent task_group
- * representation for computing load contributions.
+ * Updating tg's load_avg is necessary before update_cfs_share (which is done)
+ * and effective_load (which is not done because it is too costly).
*/
-static inline void __update_tg_runnable_avg(struct sched_avg *sa,
- struct cfs_rq *cfs_rq)
+static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
{
- struct task_group *tg = cfs_rq->tg;
- long contrib;
-
- /* The fraction of a cpu used by this cfs_rq */
- contrib = div_u64((u64)sa->runnable_avg_sum << NICE_0_SHIFT,
- sa->avg_period + 1);
- contrib -= cfs_rq->tg_runnable_contrib;
-
- if (abs(contrib) > cfs_rq->tg_runnable_contrib / 64) {
- atomic_add(contrib, &tg->runnable_avg);
- cfs_rq->tg_runnable_contrib += contrib;
- }
-}
+ long delta = cfs_rq->avg.load_avg - cfs_rq->tg_load_avg_contrib;
-static inline void __update_group_entity_contrib(struct sched_entity *se)
-{
- struct cfs_rq *cfs_rq = group_cfs_rq(se);
- struct task_group *tg = cfs_rq->tg;
- int runnable_avg;
-
- u64 contrib;
-
- contrib = cfs_rq->tg_load_contrib * tg->shares;
- se->avg.load_avg_contrib = div_u64(contrib,
- atomic_long_read(&tg->load_avg) + 1);
-
- /*
- * For group entities we need to compute a correction term in the case
- * that they are consuming <1 cpu so that we would contribute the same
- * load as a task of equal weight.
- *
- * Explicitly co-ordinating this measurement would be expensive, but
- * fortunately the sum of each cpus contribution forms a usable
- * lower-bound on the true value.
- *
- * Consider the aggregate of 2 contributions. Either they are disjoint
- * (and the sum represents true value) or they are disjoint and we are
- * understating by the aggregate of their overlap.
- *
- * Extending this to N cpus, for a given overlap, the maximum amount we
- * understand is then n_i(n_i+1)/2 * w_i where n_i is the number of
- * cpus that overlap for this interval and w_i is the interval width.
- *
- * On a small machine; the first term is well-bounded which bounds the
- * total error since w_i is a subset of the period. Whereas on a
- * larger machine, while this first term can be larger, if w_i is the
- * of consequential size guaranteed to see n_i*w_i quickly converge to
- * our upper bound of 1-cpu.
- */
- runnable_avg = atomic_read(&tg->runnable_avg);
- if (runnable_avg < NICE_0_LOAD) {
- se->avg.load_avg_contrib *= runnable_avg;
- se->avg.load_avg_contrib >>= NICE_0_SHIFT;
+ if (force || abs(delta) > cfs_rq->tg_load_avg_contrib / 64) {
+ atomic_long_add(delta, &cfs_rq->tg->load_avg);
+ cfs_rq->tg_load_avg_contrib = cfs_rq->avg.load_avg;
}
}
-static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
-{
- __update_entity_runnable_avg(rq_clock_task(rq), cpu_of(rq), &rq->avg,
- runnable, runnable);
- __update_tg_runnable_avg(&rq->avg, &rq->cfs);
-}
#else /* CONFIG_FAIR_GROUP_SCHED */
-static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq,
- int force_update) {}
-static inline void __update_tg_runnable_avg(struct sched_avg *sa,
- struct cfs_rq *cfs_rq) {}
-static inline void __update_group_entity_contrib(struct sched_entity *se) {}
-static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {}
+static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
#endif /* CONFIG_FAIR_GROUP_SCHED */
-static inline void __update_task_entity_contrib(struct sched_entity *se)
-{
- u32 contrib;
-
- /* avoid overflowing a 32-bit type w/ SCHED_LOAD_SCALE */
- contrib = se->avg.runnable_avg_sum * scale_load_down(se->load.weight);
- contrib /= (se->avg.avg_period + 1);
- se->avg.load_avg_contrib = scale_load(contrib);
-}
+static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
-/* Compute the current contribution to load_avg by se, return any delta */
-static long __update_entity_load_avg_contrib(struct sched_entity *se)
+/* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */
+static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
{
- long old_contrib = se->avg.load_avg_contrib;
+ struct sched_avg *sa = &cfs_rq->avg;
+ int decayed, removed = 0;
- if (entity_is_task(se)) {
- __update_task_entity_contrib(se);
- } else {
- __update_tg_runnable_avg(&se->avg, group_cfs_rq(se));
- __update_group_entity_contrib(se);
+ if (atomic_long_read(&cfs_rq->removed_load_avg)) {
+ 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;
}
- return se->avg.load_avg_contrib - old_contrib;
-}
+ 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, 0);
+ }
+ decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
+ scale_load_down(cfs_rq->load.weight), cfs_rq->curr != NULL, cfs_rq);
-static inline void __update_task_entity_utilization(struct sched_entity *se)
-{
- u32 contrib;
+#ifndef CONFIG_64BIT
+ smp_wmb();
+ cfs_rq->load_last_update_time_copy = sa->last_update_time;
+#endif
- /* avoid overflowing a 32-bit type w/ SCHED_LOAD_SCALE */
- contrib = se->avg.running_avg_sum * scale_load_down(SCHED_LOAD_SCALE);
- contrib /= (se->avg.avg_period + 1);
- se->avg.utilization_avg_contrib = scale_load(contrib);
+ return decayed || removed;
}
-static long __update_entity_utilization_avg_contrib(struct sched_entity *se)
+/* Update task and its cfs_rq load average */
+static inline void update_load_avg(struct sched_entity *se, int update_tg)
{
- long old_contrib = se->avg.utilization_avg_contrib;
-
- if (entity_is_task(se))
- __update_task_entity_utilization(se);
- else
- se->avg.utilization_avg_contrib =
- group_cfs_rq(se)->utilization_load_avg;
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ u64 now = cfs_rq_clock_task(cfs_rq);
+ int cpu = cpu_of(rq_of(cfs_rq));
- return se->avg.utilization_avg_contrib - old_contrib;
-}
+ /*
+ * 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);
-static inline void subtract_blocked_load_contrib(struct cfs_rq *cfs_rq,
- long load_contrib)
-{
- if (likely(load_contrib < cfs_rq->blocked_load_avg))
- cfs_rq->blocked_load_avg -= load_contrib;
- else
- cfs_rq->blocked_load_avg = 0;
+ if (update_cfs_rq_load_avg(now, cfs_rq) && update_tg)
+ update_tg_load_avg(cfs_rq, 0);
}
-static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
-
-/* Update a sched_entity's runnable average */
-static inline void update_entity_load_avg(struct sched_entity *se,
- int update_cfs_rq)
+static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- struct cfs_rq *cfs_rq = cfs_rq_of(se);
- long contrib_delta, utilization_delta;
- int cpu = cpu_of(rq_of(cfs_rq));
- u64 now;
+ if (!sched_feat(ATTACH_AGE_LOAD))
+ goto skip_aging;
/*
- * For a group entity we need to use their owned cfs_rq_clock_task() in
- * case they are the parent of a throttled hierarchy.
+ * If we got migrated (either between CPUs or between cgroups) we'll
+ * have aged the average right before clearing @last_update_time.
*/
- if (entity_is_task(se))
- now = cfs_rq_clock_task(cfs_rq);
- else
- now = cfs_rq_clock_task(group_cfs_rq(se));
+ 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);
- if (!__update_entity_runnable_avg(now, cpu, &se->avg, se->on_rq,
- cfs_rq->curr == se))
- return;
+ /*
+ * XXX: we could have just aged the entire load away if we've been
+ * absent from the fair class for too long.
+ */
+ }
- contrib_delta = __update_entity_load_avg_contrib(se);
- utilization_delta = __update_entity_utilization_avg_contrib(se);
+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;
+}
- if (!update_cfs_rq)
- return;
+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);
- if (se->on_rq) {
- cfs_rq->runnable_load_avg += contrib_delta;
- cfs_rq->utilization_load_avg += utilization_delta;
- } else {
- subtract_blocked_load_contrib(cfs_rq, -contrib_delta);
- }
+ 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);
}
-/*
- * Decay the load contributed by all blocked children and account this so that
- * their contribution may appropriately discounted when they wake up.
- */
-static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update)
+/* 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)
{
- u64 now = cfs_rq_clock_task(cfs_rq) >> 20;
- u64 decays;
-
- decays = now - cfs_rq->last_decay;
- if (!decays && !force_update)
- return;
+ struct sched_avg *sa = &se->avg;
+ u64 now = cfs_rq_clock_task(cfs_rq);
+ int migrated, decayed;
- if (atomic_long_read(&cfs_rq->removed_load)) {
- unsigned long removed_load;
- removed_load = atomic_long_xchg(&cfs_rq->removed_load, 0);
- subtract_blocked_load_contrib(cfs_rq, removed_load);
+ 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);
}
- if (decays) {
- cfs_rq->blocked_load_avg = decay_load(cfs_rq->blocked_load_avg,
- decays);
- atomic64_add(decays, &cfs_rq->decay_counter);
- cfs_rq->last_decay = now;
- }
+ decayed = update_cfs_rq_load_avg(now, cfs_rq);
+
+ cfs_rq->runnable_load_avg += sa->load_avg;
+ cfs_rq->runnable_load_sum += sa->load_sum;
- __update_cfs_rq_tg_load_contrib(cfs_rq, force_update);
+ if (migrated)
+ attach_entity_load_avg(cfs_rq, se);
+
+ if (decayed || migrated)
+ update_tg_load_avg(cfs_rq, 0);
}
-/* Add the load generated by se into cfs_rq's child load-average */
-static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
- struct sched_entity *se,
- int wakeup)
+/* Remove the runnable load generated by se from cfs_rq's runnable load average */
+static inline void
+dequeue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- /*
- * We track migrations using entity decay_count <= 0, on a wake-up
- * migration we use a negative decay count to track the remote decays
- * accumulated while sleeping.
- *
- * Newly forked tasks are enqueued with se->avg.decay_count == 0, they
- * are seen by enqueue_entity_load_avg() as a migration with an already
- * constructed load_avg_contrib.
- */
- if (unlikely(se->avg.decay_count <= 0)) {
- se->avg.last_runnable_update = rq_clock_task(rq_of(cfs_rq));
- if (se->avg.decay_count) {
- /*
- * In a wake-up migration we have to approximate the
- * time sleeping. This is because we can't synchronize
- * clock_task between the two cpus, and it is not
- * guaranteed to be read-safe. Instead, we can
- * approximate this using our carried decays, which are
- * explicitly atomically readable.
- */
- se->avg.last_runnable_update -= (-se->avg.decay_count)
- << 20;
- update_entity_load_avg(se, 0);
- /* Indicate that we're now synchronized and on-rq */
- se->avg.decay_count = 0;
- }
- wakeup = 0;
- } else {
- __synchronize_entity_decay(se);
- }
+ update_load_avg(se, 1);
- /* migrated tasks did not contribute to our blocked load */
- if (wakeup) {
- subtract_blocked_load_contrib(cfs_rq, se->avg.load_avg_contrib);
- update_entity_load_avg(se, 0);
- }
-
- cfs_rq->runnable_load_avg += se->avg.load_avg_contrib;
- cfs_rq->utilization_load_avg += se->avg.utilization_avg_contrib;
- /* we force update consideration on load-balancer moves */
- update_cfs_rq_blocked_load(cfs_rq, !wakeup);
+ 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);
}
/*
- * Remove se's load from this cfs_rq child load-average, if the entity is
- * transitioning to a blocked state we track its projected decay using
- * blocked_load_avg.
+ * Task first catches up with cfs_rq, and then subtract
+ * itself from the cfs_rq (task must be off the queue now).
*/
-static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq,
- struct sched_entity *se,
- int sleep)
+void remove_entity_load_avg(struct sched_entity *se)
{
- update_entity_load_avg(se, 1);
- /* we force update consideration on load-balancer moves */
- update_cfs_rq_blocked_load(cfs_rq, !sleep);
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ u64 last_update_time;
+
+#ifndef CONFIG_64BIT
+ u64 last_update_time_copy;
- cfs_rq->runnable_load_avg -= se->avg.load_avg_contrib;
- cfs_rq->utilization_load_avg -= se->avg.utilization_avg_contrib;
- if (sleep) {
- cfs_rq->blocked_load_avg += se->avg.load_avg_contrib;
- se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
- } /* migrations, e.g. sleep=0 leave decay_count == 0 */
+ do {
+ last_update_time_copy = cfs_rq->load_last_update_time_copy;
+ smp_rmb();
+ last_update_time = cfs_rq->avg.last_update_time;
+ } while (last_update_time != last_update_time_copy);
+#else
+ last_update_time = cfs_rq->avg.last_update_time;
+#endif
+
+ __update_load_avg(last_update_time, cpu_of(rq_of(cfs_rq)), &se->avg, 0, 0, NULL);
+ atomic_long_add(se->avg.load_avg, &cfs_rq->removed_load_avg);
+ atomic_long_add(se->avg.util_avg, &cfs_rq->removed_util_avg);
}
/*
*/
void idle_enter_fair(struct rq *this_rq)
{
- update_rq_runnable_avg(this_rq, 1);
}
/*
*/
void idle_exit_fair(struct rq *this_rq)
{
- update_rq_runnable_avg(this_rq, 0);
+}
+
+static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq)
+{
+ return cfs_rq->runnable_load_avg;
+}
+
+static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq)
+{
+ return cfs_rq->avg.load_avg;
}
static int idle_balance(struct rq *this_rq);
#else /* CONFIG_SMP */
-static inline void update_entity_load_avg(struct sched_entity *se,
- int update_cfs_rq) {}
-static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {}
-static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
- struct sched_entity *se,
- int wakeup) {}
-static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq,
- struct sched_entity *se,
- int sleep) {}
-static inline void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq,
- int force_update) {}
+static inline void update_load_avg(struct sched_entity *se, int update_tg) {}
+static inline void
+enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
+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)
{
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
- enqueue_entity_load_avg(cfs_rq, se, flags & ENQUEUE_WAKEUP);
+ enqueue_entity_load_avg(cfs_rq, se);
account_entity_enqueue(cfs_rq, se);
update_cfs_shares(cfs_rq);
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
- dequeue_entity_load_avg(cfs_rq, se, flags & DEQUEUE_SLEEP);
+ dequeue_entity_load_avg(cfs_rq, se);
update_stats_dequeue(cfs_rq, se);
if (flags & DEQUEUE_SLEEP) {
*/
update_stats_wait_end(cfs_rq, se);
__dequeue_entity(cfs_rq, se);
- update_entity_load_avg(se, 1);
+ update_load_avg(se, 1);
}
update_stats_curr_start(cfs_rq, se);
/* Put 'current' back into the tree. */
__enqueue_entity(cfs_rq, prev);
/* in !on_rq case, update occurred at dequeue */
- update_entity_load_avg(prev, 1);
+ update_load_avg(prev, 0);
}
cfs_rq->curr = NULL;
}
/*
* Ensure that runnable average is periodically updated.
*/
- update_entity_load_avg(curr, 1);
- update_cfs_rq_blocked_load(cfs_rq, 1);
+ update_load_avg(curr, 1);
update_cfs_shares(cfs_rq);
#ifdef CONFIG_SCHED_HRTICK
if (cfs_b->quota == RUNTIME_INF)
amount = min_amount;
else {
- /*
- * If the bandwidth pool has become inactive, then at least one
- * period must have elapsed since the last consumption.
- * Refresh the global state and ensure bandwidth timer becomes
- * active.
- */
- if (!cfs_b->timer_active) {
- __refill_cfs_bandwidth_runtime(cfs_b);
- __start_cfs_bandwidth(cfs_b, false);
- }
+ start_cfs_bandwidth(cfs_b);
if (cfs_b->runtime > 0) {
amount = min(cfs_b->runtime, min_amount);
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
struct sched_entity *se;
long task_delta, dequeue = 1;
+ bool empty;
se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))];
cfs_rq->throttled = 1;
cfs_rq->throttled_clock = rq_clock(rq);
raw_spin_lock(&cfs_b->lock);
+ empty = list_empty(&cfs_b->throttled_cfs_rq);
+
/*
* Add to the _head_ of the list, so that an already-started
* distribute_cfs_runtime will not see us
*/
list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
- if (!cfs_b->timer_active)
- __start_cfs_bandwidth(cfs_b, false);
+
+ /*
+ * If we're the first throttled task, make sure the bandwidth
+ * timer is running.
+ */
+ if (empty)
+ start_cfs_bandwidth(cfs_b);
+
raw_spin_unlock(&cfs_b->lock);
}
if (cfs_b->idle && !throttled)
goto out_deactivate;
- /*
- * if we have relooped after returning idle once, we need to update our
- * status as actually running, so that other cpus doing
- * __start_cfs_bandwidth will stop trying to cancel us.
- */
- cfs_b->timer_active = 1;
-
__refill_cfs_bandwidth_runtime(cfs_b);
if (!throttled) {
return 0;
out_deactivate:
- cfs_b->timer_active = 0;
return 1;
}
* Are we near the end of the current quota period?
*
* Requires cfs_b->lock for hrtimer_expires_remaining to be safe against the
- * hrtimer base being cleared by __hrtimer_start_range_ns. In the case of
+ * hrtimer base being cleared by hrtimer_start. In the case of
* migrate_hrtimers, base is never cleared, so we are fine.
*/
static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire)
if (runtime_refresh_within(cfs_b, min_left))
return;
- start_bandwidth_timer(&cfs_b->slack_timer,
- ns_to_ktime(cfs_bandwidth_slack_period));
+ hrtimer_start(&cfs_b->slack_timer,
+ ns_to_ktime(cfs_bandwidth_slack_period),
+ HRTIMER_MODE_REL);
}
/* we know any runtime found here is valid as update_curr() precedes return */
{
struct cfs_bandwidth *cfs_b =
container_of(timer, struct cfs_bandwidth, slack_timer);
+
do_sched_cfs_slack_timer(cfs_b);
return HRTIMER_NORESTART;
{
struct cfs_bandwidth *cfs_b =
container_of(timer, struct cfs_bandwidth, period_timer);
- ktime_t now;
int overrun;
int idle = 0;
raw_spin_lock(&cfs_b->lock);
for (;;) {
- now = hrtimer_cb_get_time(timer);
- overrun = hrtimer_forward(timer, now, cfs_b->period);
-
+ overrun = hrtimer_forward_now(timer, cfs_b->period);
if (!overrun)
break;
idle = do_sched_cfs_period_timer(cfs_b, overrun);
}
+ if (idle)
+ cfs_b->period_active = 0;
raw_spin_unlock(&cfs_b->lock);
return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
cfs_b->period = ns_to_ktime(default_cfs_period());
INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
- hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
cfs_b->period_timer.function = sched_cfs_period_timer;
hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
cfs_b->slack_timer.function = sched_cfs_slack_timer;
INIT_LIST_HEAD(&cfs_rq->throttled_list);
}
-/* requires cfs_b->lock, may release to reprogram timer */
-void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force)
+void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
{
- /*
- * The timer may be active because we're trying to set a new bandwidth
- * period or because we're racing with the tear-down path
- * (timer_active==0 becomes visible before the hrtimer call-back
- * terminates). In either case we ensure that it's re-programmed
- */
- while (unlikely(hrtimer_active(&cfs_b->period_timer)) &&
- hrtimer_try_to_cancel(&cfs_b->period_timer) < 0) {
- /* bounce the lock to allow do_sched_cfs_period_timer to run */
- raw_spin_unlock(&cfs_b->lock);
- cpu_relax();
- raw_spin_lock(&cfs_b->lock);
- /* if someone else restarted the timer then we're done */
- if (!force && cfs_b->timer_active)
- return;
- }
+ lockdep_assert_held(&cfs_b->lock);
- cfs_b->timer_active = 1;
- start_bandwidth_timer(&cfs_b->period_timer, cfs_b->period);
+ if (!cfs_b->period_active) {
+ cfs_b->period_active = 1;
+ hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
+ hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
+ }
}
static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
if (cfs_rq_throttled(cfs_rq))
break;
+ update_load_avg(se, 1);
update_cfs_shares(cfs_rq);
- update_entity_load_avg(se, 1);
}
- if (!se) {
- update_rq_runnable_avg(rq, rq->nr_running);
+ if (!se)
add_nr_running(rq, 1);
- }
+
hrtick_update(rq);
}
if (cfs_rq_throttled(cfs_rq))
break;
+ update_load_avg(se, 1);
update_cfs_shares(cfs_rq);
- update_entity_load_avg(se, 1);
}
- if (!se) {
+ if (!se)
sub_nr_running(rq, 1);
- update_rq_runnable_avg(rq, 1);
- }
+
hrtick_update(rq);
}
-#ifdef CONFIG_SMP
-/* Used instead of source_load when we know the type == 0 */
-static unsigned long weighted_cpuload(const int cpu)
+#ifdef CONFIG_SMP
+
+/*
+ * per rq 'load' arrray crap; XXX kill this.
+ */
+
+/*
+ * The exact cpuload at various idx values, calculated at every tick would be
+ * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load
+ *
+ * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called
+ * on nth tick when cpu may be busy, then we have:
+ * load = ((2^idx - 1) / 2^idx)^(n-1) * load
+ * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load
+ *
+ * decay_load_missed() below does efficient calculation of
+ * load = ((2^idx - 1) / 2^idx)^(n-1) * load
+ * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load
+ *
+ * The calculation is approximated on a 128 point scale.
+ * degrade_zero_ticks is the number of ticks after which load at any
+ * particular idx is approximated to be zero.
+ * degrade_factor is a precomputed table, a row for each load idx.
+ * Each column corresponds to degradation factor for a power of two ticks,
+ * based on 128 point scale.
+ * Example:
+ * row 2, col 3 (=12) says that the degradation at load idx 2 after
+ * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8).
+ *
+ * With this power of 2 load factors, we can degrade the load n times
+ * by looking at 1 bits in n and doing as many mult/shift instead of
+ * n mult/shifts needed by the exact degradation.
+ */
+#define DEGRADE_SHIFT 7
+static const unsigned char
+ degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128};
+static const unsigned char
+ 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},
+ {112, 98, 75, 43, 15, 1, 0},
+ {120, 112, 98, 76, 45, 16, 2} };
+
+/*
+ * 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;
+}
+
+/*
+ * Update rq->cpu_load[] statistics. This function is usually called every
+ * scheduler tick (TICK_NSEC). With tickless idle this will not be called
+ * every tick. We fix it up based on jiffies.
+ */
+static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
+ unsigned long pending_updates)
+{
+ 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];
+ old_load = decay_load_missed(old_load, pending_updates - 1, i);
+ 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;
+ }
+
+ sched_avg_update(this_rq);
+}
+
+/* Used instead of source_load when we know the type == 0 */
+static unsigned long weighted_cpuload(const int cpu)
+{
+ return cfs_rq_runnable_load_avg(&cpu_rq(cpu)->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 cannot use the delta approach from the regular tick since that
+ * would seriously skew the load calculation. However we'll make do for those
+ * updates happening while idle (nohz_idle_balance) or coming out of idle
+ * (tick_nohz_idle_exit).
+ *
+ * This means we might still be one tick off for nohz periods.
+ */
+
+/*
+ * Called from nohz_idle_balance() to update the load ratings before doing the
+ * idle balance.
+ */
+static void update_idle_cpu_load(struct rq *this_rq)
+{
+ unsigned long curr_jiffies = READ_ONCE(jiffies);
+ unsigned long load = weighted_cpuload(cpu_of(this_rq));
+ unsigned long pending_updates;
+
+ /*
+ * bail if there's load or we're actually up-to-date.
+ */
+ if (load || curr_jiffies == this_rq->last_load_update_tick)
+ return;
+
+ pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+ this_rq->last_load_update_tick = curr_jiffies;
+
+ __update_cpu_load(this_rq, load, pending_updates);
+}
+
+/*
+ * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed.
+ */
+void update_cpu_load_nohz(void)
+{
+ struct rq *this_rq = this_rq();
+ unsigned long curr_jiffies = READ_ONCE(jiffies);
+ unsigned long pending_updates;
+
+ if (curr_jiffies == this_rq->last_load_update_tick)
+ return;
+
+ raw_spin_lock(&this_rq->lock);
+ pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+ if (pending_updates) {
+ this_rq->last_load_update_tick = curr_jiffies;
+ /*
+ * We were idle, this means load 0, the current load might be
+ * !0 due to remote wakeups and the sort.
+ */
+ __update_cpu_load(this_rq, 0, pending_updates);
+ }
+ raw_spin_unlock(&this_rq->lock);
+}
+#endif /* CONFIG_NO_HZ */
+
+/*
+ * Called from scheduler_tick()
+ */
+void update_cpu_load_active(struct rq *this_rq)
{
- return cpu_rq(cpu)->cfs.runnable_load_avg;
+ unsigned long load = weighted_cpuload(cpu_of(this_rq));
+ /*
+ * See the mess around update_idle_cpu_load() / update_cpu_load_nohz().
+ */
+ this_rq->last_load_update_tick = jiffies;
+ __update_cpu_load(this_rq, load, 1);
}
/*
static unsigned long cpu_avg_load_per_task(int cpu)
{
struct rq *rq = cpu_rq(cpu);
- unsigned long nr_running = ACCESS_ONCE(rq->cfs.h_nr_running);
- unsigned long load_avg = rq->cfs.runnable_load_avg;
+ unsigned long nr_running = READ_ONCE(rq->cfs.h_nr_running);
+ unsigned long load_avg = weighted_cpuload(cpu);
if (nr_running)
return load_avg / nr_running;
/*
* w = rw_i + @wl
*/
- w = se->my_q->load.weight + wl;
+ w = cfs_rq_load_avg(se->my_q) + wl;
/*
* wl = S * s'_i; see (2)
/*
* wl = dw_i = S * (s'_i - s_i); see (3)
*/
- wl -= se->load.weight;
+ wl -= se->avg.load_avg;
/*
* Recursively apply this logic to all parent groups to compute
#endif
+/*
+ * Detect M:N waker/wakee relationships via a switching-frequency heuristic.
+ * A waker of many should wake a different task than the one last awakened
+ * at a frequency roughly N times higher than one of its wakees. In order
+ * to determine whether we should let the load spread vs consolodating to
+ * shared cache, we look for a minimum 'flip' frequency of llc_size in one
+ * partner, and a factor of lls_size higher frequency in the other. With
+ * both conditions met, we can be relatively sure that the relationship is
+ * non-monogamous, with partner count exceeding socket size. Waker/wakee
+ * being client/server, worker/dispatcher, interrupt source or whatever is
+ * irrelevant, spread criteria is apparent partner count exceeds socket size.
+ */
static int wake_wide(struct task_struct *p)
{
+ unsigned int master = current->wakee_flips;
+ unsigned int slave = p->wakee_flips;
int factor = this_cpu_read(sd_llc_size);
- /*
- * Yeah, it's the switching-frequency, could means many wakee or
- * rapidly switch, use factor here will just help to automatically
- * adjust the loose-degree, so bigger node will lead to more pull.
- */
- if (p->wakee_flips > factor) {
- /*
- * wakee is somewhat hot, it needs certain amount of cpu
- * resource, so if waker is far more hot, prefer to leave
- * it alone.
- */
- if (current->wakee_flips > (factor * p->wakee_flips))
- return 1;
- }
-
- return 0;
+ if (master < slave)
+ swap(master, slave);
+ if (slave < factor || master < slave * factor)
+ return 0;
+ return 1;
}
static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
unsigned long weight;
int balanced;
- /*
- * If we wake multiple tasks be careful to not bounce
- * ourselves around too much.
- */
- if (wake_wide(p))
- return 0;
-
idx = sd->wake_idx;
this_cpu = smp_processor_id();
prev_cpu = task_cpu(p);
*/
if (sync) {
tg = task_group(current);
- weight = current->se.load.weight;
+ weight = current->se.avg.load_avg;
this_load += effective_load(tg, this_cpu, -weight, -weight);
load += effective_load(tg, prev_cpu, 0, -weight);
}
tg = task_group(p);
- weight = p->se.load.weight;
+ weight = p->se.avg.load_avg;
/*
* In low-load situations, where prev_cpu is idle and this_cpu is idle
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.utilization_load_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.utilization_load_avg can be higher than SCHED_LOAD_SCALE
- * because of unfortunate rounding in avg_period and running_load_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.utilization_load_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;
}
/*
{
struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
int cpu = smp_processor_id();
- int new_cpu = cpu;
+ int new_cpu = prev_cpu;
int want_affine = 0;
int sync = wake_flags & WF_SYNC;
if (sd_flag & SD_BALANCE_WAKE)
- want_affine = cpumask_test_cpu(cpu, tsk_cpus_allowed(p));
+ want_affine = !wake_wide(p) && cpumask_test_cpu(cpu, tsk_cpus_allowed(p));
rcu_read_lock();
for_each_domain(cpu, tmp) {
if (!(tmp->flags & SD_LOAD_BALANCE))
- continue;
+ break;
/*
* If both cpu and prev_cpu are part of this domain,
if (tmp->flags & sd_flag)
sd = tmp;
+ else if (!want_affine)
+ break;
}
- if (affine_sd && cpu != prev_cpu && wake_affine(affine_sd, p, sync))
- prev_cpu = cpu;
-
- if (sd_flag & SD_BALANCE_WAKE) {
- new_cpu = select_idle_sibling(p, prev_cpu);
- goto unlock;
+ if (affine_sd) {
+ sd = NULL; /* Prefer wake_affine over balance flags */
+ if (cpu != prev_cpu && wake_affine(affine_sd, p, sync))
+ new_cpu = cpu;
}
- while (sd) {
+ if (!sd) {
+ if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */
+ new_cpu = select_idle_sibling(p, new_cpu);
+
+ } else while (sd) {
struct sched_group *group;
int weight;
}
/* while loop will break here if sd == NULL */
}
-unlock:
rcu_read_unlock();
return new_cpu;
* 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)
{
- struct sched_entity *se = &p->se;
- struct cfs_rq *cfs_rq = cfs_rq_of(se);
-
/*
- * Load tracking: accumulate removed load so that it can be processed
- * when we next update owning cfs_rq under rq->lock. Tasks contribute
- * to blocked load iff they have a positive decay-count. It can never
- * be negative here since on-rq tasks have decay-count == 0.
+ * We are supposed to update the task to "current" time, then its up to date
+ * and ready to go to new CPU/cfs_rq. But we have difficulty in getting
+ * what current time is, so simply throw away the out-of-date time. This
+ * will result in the wakee task is less decayed, but giving the wakee more
+ * load sounds not bad.
*/
- if (se->avg.decay_count) {
- se->avg.decay_count = -__synchronize_entity_decay(se);
- atomic_long_add(se->avg.load_avg_contrib,
- &cfs_rq->removed_load);
- }
+ remove_entity_load_avg(&p->se);
+
+ /* Tell new CPU we are migrated */
+ p->se.avg.last_update_time = 0;
/* We have migrated, no longer consider this task hot */
- se->exec_start = 0;
+ p->se.exec_start = 0;
+}
+
+static void task_dead_fair(struct task_struct *p)
+{
+ remove_entity_load_avg(&p->se);
}
#endif /* CONFIG_SMP */
* entity, update_curr() will update its vruntime, otherwise
* forget we've ever seen it.
*/
- if (curr && curr->on_rq)
- update_curr(cfs_rq);
- else
- curr = NULL;
+ if (curr) {
+ if (curr->on_rq)
+ update_curr(cfs_rq);
+ else
+ curr = NULL;
- /*
- * This call to check_cfs_rq_runtime() will do the throttle and
- * dequeue its entity in the parent(s). Therefore the 'simple'
- * nr_running test will indeed be correct.
- */
- if (unlikely(check_cfs_rq_runtime(cfs_rq)))
- goto simple;
+ /*
+ * This call to check_cfs_rq_runtime() will do the
+ * throttle and dequeue its entity in the parent(s).
+ * Therefore the 'simple' nr_running test will indeed
+ * be correct.
+ */
+ if (unlikely(check_cfs_rq_runtime(cfs_rq)))
+ goto simple;
+ }
se = pick_next_entity(cfs_rq, curr);
cfs_rq = group_cfs_rq(se);
return p;
idle:
+ /*
+ * This is OK, because current is on_cpu, which avoids it being picked
+ * for load-balance and preemption/IRQs are still disabled avoiding
+ * further scheduler activity on it and we're being very careful to
+ * re-start the picking loop.
+ */
+ lockdep_unpin_lock(&rq->lock);
new_tasks = idle_balance(rq);
+ lockdep_pin_lock(&rq->lock);
/*
* Because idle_balance() releases (and re-acquires) rq->lock, it is
* possible for any higher priority task to appear. In that case we
}
#ifdef CONFIG_NUMA_BALANCING
-/* Returns true if the destination node has incurred more faults */
-static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env)
+/*
+ * Returns 1, if task migration degrades locality
+ * Returns 0, if task migration improves locality i.e migration preferred.
+ * Returns -1, if task migration is not affected by locality.
+ */
+static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
{
struct numa_group *numa_group = rcu_dereference(p->numa_group);
+ unsigned long src_faults, dst_faults;
int src_nid, dst_nid;
- if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults ||
- !(env->sd->flags & SD_NUMA)) {
- return false;
- }
+ if (!static_branch_likely(&sched_numa_balancing))
+ return -1;
+
+ if (!p->numa_faults || !(env->sd->flags & SD_NUMA))
+ return -1;
src_nid = cpu_to_node(env->src_cpu);
dst_nid = cpu_to_node(env->dst_cpu);
if (src_nid == dst_nid)
- return false;
-
- if (numa_group) {
- /* Task is already in the group's interleave set. */
- if (node_isset(src_nid, numa_group->active_nodes))
- return false;
-
- /* Task is moving into the group's interleave set. */
- if (node_isset(dst_nid, numa_group->active_nodes))
- return true;
+ return -1;
- return group_faults(p, dst_nid) > group_faults(p, src_nid);
+ /* Migrating away from the preferred node is always bad. */
+ if (src_nid == p->numa_preferred_nid) {
+ if (env->src_rq->nr_running > env->src_rq->nr_preferred_running)
+ return 1;
+ else
+ return -1;
}
/* Encourage migration to the preferred node. */
if (dst_nid == p->numa_preferred_nid)
- return true;
-
- return task_faults(p, dst_nid) > task_faults(p, src_nid);
-}
-
-
-static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
-{
- struct numa_group *numa_group = rcu_dereference(p->numa_group);
- int src_nid, dst_nid;
-
- if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER))
- return false;
-
- if (!p->numa_faults || !(env->sd->flags & SD_NUMA))
- return false;
-
- src_nid = cpu_to_node(env->src_cpu);
- dst_nid = cpu_to_node(env->dst_cpu);
-
- if (src_nid == dst_nid)
- return false;
+ return 0;
if (numa_group) {
- /* Task is moving within/into the group's interleave set. */
- if (node_isset(dst_nid, numa_group->active_nodes))
- return false;
-
- /* Task is moving out of the group's interleave set. */
- if (node_isset(src_nid, numa_group->active_nodes))
- return true;
-
- return group_faults(p, dst_nid) < group_faults(p, src_nid);
+ src_faults = group_faults(p, src_nid);
+ dst_faults = group_faults(p, dst_nid);
+ } else {
+ src_faults = task_faults(p, src_nid);
+ dst_faults = task_faults(p, dst_nid);
}
- /* Migrating away from the preferred node is always bad. */
- if (src_nid == p->numa_preferred_nid)
- return true;
-
- return task_faults(p, dst_nid) < task_faults(p, src_nid);
+ return dst_faults < src_faults;
}
#else
-static inline bool migrate_improves_locality(struct task_struct *p,
- struct lb_env *env)
-{
- return false;
-}
-
-static inline bool migrate_degrades_locality(struct task_struct *p,
+static inline int migrate_degrades_locality(struct task_struct *p,
struct lb_env *env)
{
- return false;
+ return -1;
}
#endif
static
int can_migrate_task(struct task_struct *p, struct lb_env *env)
{
- int tsk_cache_hot = 0;
+ int tsk_cache_hot;
lockdep_assert_held(&env->src_rq->lock);
* 2) task is cache cold, or
* 3) too many balance attempts have failed.
*/
- tsk_cache_hot = task_hot(p, env);
- if (!tsk_cache_hot)
- tsk_cache_hot = migrate_degrades_locality(p, env);
+ tsk_cache_hot = migrate_degrades_locality(p, env);
+ if (tsk_cache_hot == -1)
+ tsk_cache_hot = task_hot(p, env);
- if (migrate_improves_locality(p, env) || !tsk_cache_hot ||
+ if (tsk_cache_hot <= 0 ||
env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
- if (tsk_cache_hot) {
+ if (tsk_cache_hot == 1) {
schedstat_inc(env->sd, lb_hot_gained[env->idle]);
schedstat_inc(p, se.statistics.nr_forced_migrations);
}
return 0;
while (!list_empty(tasks)) {
+ /*
+ * We don't want to steal all, otherwise we may be treated likewise,
+ * which could at worst lead to a livelock crash.
+ */
+ if (env->idle != CPU_NOT_IDLE && env->src_rq->nr_running <= 1)
+ break;
+
p = list_first_entry(tasks, struct task_struct, se.group_node);
env->loop++;
}
#ifdef CONFIG_FAIR_GROUP_SCHED
-/*
- * update tg->load_weight by folding this cpu's load_avg
- */
-static void __update_blocked_averages_cpu(struct task_group *tg, int cpu)
-{
- struct sched_entity *se = tg->se[cpu];
- struct cfs_rq *cfs_rq = tg->cfs_rq[cpu];
-
- /* throttled entities do not contribute to load */
- if (throttled_hierarchy(cfs_rq))
- return;
-
- update_cfs_rq_blocked_load(cfs_rq, 1);
-
- if (se) {
- update_entity_load_avg(se, 1);
- /*
- * We pivot on our runnable average having decayed to zero for
- * list removal. This generally implies that all our children
- * have also been removed (modulo rounding error or bandwidth
- * control); however, such cases are rare and we can fix these
- * at enqueue.
- *
- * TODO: fix up out-of-order children on enqueue.
- */
- if (!se->avg.runnable_avg_sum && !cfs_rq->nr_running)
- list_del_leaf_cfs_rq(cfs_rq);
- } else {
- struct rq *rq = rq_of(cfs_rq);
- update_rq_runnable_avg(rq, rq->nr_running);
- }
-}
-
static void update_blocked_averages(int cpu)
{
struct rq *rq = cpu_rq(cpu);
raw_spin_lock_irqsave(&rq->lock, flags);
update_rq_clock(rq);
+
/*
* Iterates the task_group tree in a bottom up fashion, see
* list_add_leaf_cfs_rq() for details.
*/
for_each_leaf_cfs_rq(rq, cfs_rq) {
- /*
- * Note: We may want to consider periodically releasing
- * rq->lock about these updates so that creating many task
- * groups does not result in continually extending hold time.
- */
- __update_blocked_averages_cpu(cfs_rq->tg, rq->cpu);
- }
+ /* throttled entities do not contribute to load */
+ if (throttled_hierarchy(cfs_rq))
+ continue;
+ if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq))
+ update_tg_load_avg(cfs_rq, 0);
+ }
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
}
if (!se) {
- cfs_rq->h_load = cfs_rq->runnable_load_avg;
+ cfs_rq->h_load = cfs_rq_load_avg(cfs_rq);
cfs_rq->last_h_load_update = now;
}
while ((se = cfs_rq->h_load_next) != NULL) {
load = cfs_rq->h_load;
- load = div64_ul(load * se->avg.load_avg_contrib,
- cfs_rq->runnable_load_avg + 1);
+ load = div64_ul(load * se->avg.load_avg,
+ cfs_rq_load_avg(cfs_rq) + 1);
cfs_rq = group_cfs_rq(se);
cfs_rq->h_load = load;
cfs_rq->last_h_load_update = now;
struct cfs_rq *cfs_rq = task_cfs_rq(p);
update_cfs_rq_h_load(cfs_rq);
- return div64_ul(p->se.avg.load_avg_contrib * cfs_rq->h_load,
- cfs_rq->runnable_load_avg + 1);
+ return div64_ul(p->se.avg.load_avg * cfs_rq->h_load,
+ cfs_rq_load_avg(cfs_rq) + 1);
}
#else
static inline void update_blocked_averages(int cpu)
{
+ struct rq *rq = cpu_rq(cpu);
+ struct cfs_rq *cfs_rq = &rq->cfs;
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&rq->lock, flags);
+ update_rq_clock(rq);
+ update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
}
static unsigned long task_h_load(struct task_struct *p)
{
- return p->se.avg.load_avg_contrib;
+ return p->se.avg.load_avg;
}
#endif
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;
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);
* Since we're reading these variables without serialization make sure
* we read them once before doing sanity checks on them.
*/
- age_stamp = ACCESS_ONCE(rq->age_stamp);
- avg = ACCESS_ONCE(rq->rt_avg);
+ age_stamp = READ_ONCE(rq->age_stamp);
+ avg = READ_ONCE(rq->rt_avg);
delta = __rq_clock_broken(rq) - age_stamp;
if (unlikely(delta < 0))
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);
* 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.
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;
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;
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)
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);
}
/**
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)) {
goto out;
}
- /*
- * Drop the rq->lock, but keep IRQ/preempt disabled.
- */
raw_spin_unlock(&this_rq->lock);
update_blocked_averages(this_cpu);
* 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
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)))
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));
}
entity_tick(cfs_rq, se, queued);
}
- if (numabalancing_enabled)
+ if (static_branch_unlikely(&sched_numa_balancing))
task_tick_numa(rq, curr);
-
- update_rq_runnable_avg(rq, 1);
}
/*
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.
se->vruntime -= cfs_rq->min_vruntime;
}
-#ifdef CONFIG_SMP
- /*
- * Remove our load from contribution when we leave sched_fair
- * and ensure we don't carry in an old decay_count if we
- * switch back.
- */
- if (se->avg.decay_count) {
- __synchronize_entity_decay(se);
- subtract_blocked_load_contrib(cfs_rq, se->avg.load_avg_contrib);
- }
-#endif
+ /* Catch up with the cfs_rq and remove our load when we leave */
+ 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)
{
-#ifdef CONFIG_FAIR_GROUP_SCHED
struct sched_entity *se = &p->se;
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
/*
* Since the real-depth could have been changed (only FAIR
* class maintain depth value), reset depth properly.
*/
se->depth = se->parent ? se->parent->depth + 1 : 0;
#endif
- if (!task_on_rq_queued(p))
- return;
- /*
- * 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);
+ /* 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)) {
+ /*
+ * 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.
cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
#endif
#ifdef CONFIG_SMP
- atomic64_set(&cfs_rq->decay_counter, 1);
- atomic_long_set(&cfs_rq->removed_load, 0);
+ atomic_long_set(&cfs_rq->removed_load_avg, 0);
+ atomic_long_set(&cfs_rq->removed_util_avg, 0);
#endif
}
#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
- /*
- * migrate_task_rq_fair() will have removed our previous
- * contribution, but we must synchronize for ongoing future
- * decay.
- */
- se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
- cfs_rq->blocked_load_avg += se->avg.load_avg_contrib;
+ /* 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)
for_each_possible_cpu(i) {
if (tg->cfs_rq)
kfree(tg->cfs_rq[i]);
- if (tg->se)
+ if (tg->se) {
+ if (tg->se[i])
+ remove_entity_load_avg(tg->se[i]);
kfree(tg->se[i]);
+ }
}
kfree(tg->cfs_rq);
init_cfs_rq(cfs_rq);
init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
+ init_entity_runnable_average(se);
}
return 1;
.rq_offline = rq_offline_fair,
.task_waking = task_waking_fair,
+ .task_dead = task_dead_fair,
+ .set_cpus_allowed = set_cpus_allowed_common,
#endif
.set_curr_task = set_curr_task_fair,
print_cfs_rq(m, cpu, cfs_rq);
rcu_read_unlock();
}
-#endif
+
+#ifdef CONFIG_NUMA_BALANCING
+void show_numa_stats(struct task_struct *p, struct seq_file *m)
+{
+ int node;
+ unsigned long tsf = 0, tpf = 0, gsf = 0, gpf = 0;
+
+ for_each_online_node(node) {
+ if (p->numa_faults) {
+ tsf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 0)];
+ tpf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 1)];
+ }
+ if (p->numa_group) {
+ gsf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 0)],
+ gpf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 1)];
+ }
+ print_numa_stats(m, node, tsf, tpf, gsf, gpf);
+ }
+}
+#endif /* CONFIG_NUMA_BALANCING */
+#endif /* CONFIG_SCHED_DEBUG */
__init void init_sched_fair_class(void)
{