9510 lines
246 KiB
C
9510 lines
246 KiB
C
/*
|
|
* Completely Fair Scheduling (CFS) Class (SCHED_NORMAL/SCHED_BATCH)
|
|
*
|
|
* Copyright (C) 2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
|
|
*
|
|
* Interactivity improvements by Mike Galbraith
|
|
* (C) 2007 Mike Galbraith <efault@gmx.de>
|
|
*
|
|
* Various enhancements by Dmitry Adamushko.
|
|
* (C) 2007 Dmitry Adamushko <dmitry.adamushko@gmail.com>
|
|
*
|
|
* Group scheduling enhancements by Srivatsa Vaddagiri
|
|
* Copyright IBM Corporation, 2007
|
|
* Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
|
|
*
|
|
* Scaled math optimizations by Thomas Gleixner
|
|
* Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de>
|
|
*
|
|
* Adaptive scheduling granularity, math enhancements by Peter Zijlstra
|
|
* Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
|
|
*/
|
|
|
|
#include <linux/sched/mm.h>
|
|
#include <linux/sched/topology.h>
|
|
|
|
#include <linux/latencytop.h>
|
|
#include <linux/cpumask.h>
|
|
#include <linux/cpuidle.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/profile.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/mempolicy.h>
|
|
#include <linux/migrate.h>
|
|
#include <linux/task_work.h>
|
|
|
|
#include <trace/events/sched.h>
|
|
|
|
#include "sched.h"
|
|
|
|
/*
|
|
* Targeted preemption latency for CPU-bound tasks:
|
|
*
|
|
* NOTE: this latency value is not the same as the concept of
|
|
* 'timeslice length' - timeslices in CFS are of variable length
|
|
* and have no persistent notion like in traditional, time-slice
|
|
* based scheduling concepts.
|
|
*
|
|
* (to see the precise effective timeslice length of your workload,
|
|
* run vmstat and monitor the context-switches (cs) field)
|
|
*
|
|
* (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds)
|
|
*/
|
|
unsigned int sysctl_sched_latency = 6000000ULL;
|
|
unsigned int normalized_sysctl_sched_latency = 6000000ULL;
|
|
|
|
/*
|
|
* The initial- and re-scaling of tunables is configurable
|
|
*
|
|
* Options are:
|
|
*
|
|
* SCHED_TUNABLESCALING_NONE - unscaled, always *1
|
|
* SCHED_TUNABLESCALING_LOG - scaled logarithmical, *1+ilog(ncpus)
|
|
* SCHED_TUNABLESCALING_LINEAR - scaled linear, *ncpus
|
|
*
|
|
* (default SCHED_TUNABLESCALING_LOG = *(1+ilog(ncpus))
|
|
*/
|
|
enum sched_tunable_scaling sysctl_sched_tunable_scaling = SCHED_TUNABLESCALING_LOG;
|
|
|
|
/*
|
|
* Minimal preemption granularity for CPU-bound tasks:
|
|
*
|
|
* (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds)
|
|
*/
|
|
unsigned int sysctl_sched_min_granularity = 750000ULL;
|
|
unsigned int normalized_sysctl_sched_min_granularity = 750000ULL;
|
|
|
|
/*
|
|
* This value is kept at sysctl_sched_latency/sysctl_sched_min_granularity
|
|
*/
|
|
static unsigned int sched_nr_latency = 8;
|
|
|
|
/*
|
|
* After fork, child runs first. If set to 0 (default) then
|
|
* parent will (try to) run first.
|
|
*/
|
|
unsigned int sysctl_sched_child_runs_first __read_mostly;
|
|
|
|
/*
|
|
* SCHED_OTHER wake-up granularity.
|
|
*
|
|
* This option delays the preemption effects of decoupled workloads
|
|
* and reduces their over-scheduling. Synchronous workloads will still
|
|
* have immediate wakeup/sleep latencies.
|
|
*
|
|
* (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
|
|
*/
|
|
unsigned int sysctl_sched_wakeup_granularity = 1000000UL;
|
|
unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL;
|
|
|
|
const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
|
|
|
|
#ifdef CONFIG_SMP
|
|
/*
|
|
* For asym packing, by default the lower numbered cpu has higher priority.
|
|
*/
|
|
int __weak arch_asym_cpu_priority(int cpu)
|
|
{
|
|
return -cpu;
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_CFS_BANDWIDTH
|
|
/*
|
|
* Amount of runtime to allocate from global (tg) to local (per-cfs_rq) pool
|
|
* each time a cfs_rq requests quota.
|
|
*
|
|
* Note: in the case that the slice exceeds the runtime remaining (either due
|
|
* to consumption or the quota being specified to be smaller than the slice)
|
|
* we will always only issue the remaining available time.
|
|
*
|
|
* (default: 5 msec, units: microseconds)
|
|
*/
|
|
unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL;
|
|
#endif
|
|
|
|
/*
|
|
* The margin used when comparing utilization with CPU capacity:
|
|
* util * margin < capacity * 1024
|
|
*
|
|
* (default: ~20%)
|
|
*/
|
|
unsigned int capacity_margin = 1280;
|
|
|
|
static inline void update_load_add(struct load_weight *lw, unsigned long inc)
|
|
{
|
|
lw->weight += inc;
|
|
lw->inv_weight = 0;
|
|
}
|
|
|
|
static inline void update_load_sub(struct load_weight *lw, unsigned long dec)
|
|
{
|
|
lw->weight -= dec;
|
|
lw->inv_weight = 0;
|
|
}
|
|
|
|
static inline void update_load_set(struct load_weight *lw, unsigned long w)
|
|
{
|
|
lw->weight = w;
|
|
lw->inv_weight = 0;
|
|
}
|
|
|
|
/*
|
|
* Increase the granularity value when there are more CPUs,
|
|
* because with more CPUs the 'effective latency' as visible
|
|
* to users decreases. But the relationship is not linear,
|
|
* so pick a second-best guess by going with the log2 of the
|
|
* number of CPUs.
|
|
*
|
|
* This idea comes from the SD scheduler of Con Kolivas:
|
|
*/
|
|
static unsigned int get_update_sysctl_factor(void)
|
|
{
|
|
unsigned int cpus = min_t(unsigned int, num_online_cpus(), 8);
|
|
unsigned int factor;
|
|
|
|
switch (sysctl_sched_tunable_scaling) {
|
|
case SCHED_TUNABLESCALING_NONE:
|
|
factor = 1;
|
|
break;
|
|
case SCHED_TUNABLESCALING_LINEAR:
|
|
factor = cpus;
|
|
break;
|
|
case SCHED_TUNABLESCALING_LOG:
|
|
default:
|
|
factor = 1 + ilog2(cpus);
|
|
break;
|
|
}
|
|
|
|
return factor;
|
|
}
|
|
|
|
static void update_sysctl(void)
|
|
{
|
|
unsigned int factor = get_update_sysctl_factor();
|
|
|
|
#define SET_SYSCTL(name) \
|
|
(sysctl_##name = (factor) * normalized_sysctl_##name)
|
|
SET_SYSCTL(sched_min_granularity);
|
|
SET_SYSCTL(sched_latency);
|
|
SET_SYSCTL(sched_wakeup_granularity);
|
|
#undef SET_SYSCTL
|
|
}
|
|
|
|
void sched_init_granularity(void)
|
|
{
|
|
update_sysctl();
|
|
}
|
|
|
|
#define WMULT_CONST (~0U)
|
|
#define WMULT_SHIFT 32
|
|
|
|
static void __update_inv_weight(struct load_weight *lw)
|
|
{
|
|
unsigned long w;
|
|
|
|
if (likely(lw->inv_weight))
|
|
return;
|
|
|
|
w = scale_load_down(lw->weight);
|
|
|
|
if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST))
|
|
lw->inv_weight = 1;
|
|
else if (unlikely(!w))
|
|
lw->inv_weight = WMULT_CONST;
|
|
else
|
|
lw->inv_weight = WMULT_CONST / w;
|
|
}
|
|
|
|
/*
|
|
* delta_exec * weight / lw.weight
|
|
* OR
|
|
* (delta_exec * (weight * lw->inv_weight)) >> WMULT_SHIFT
|
|
*
|
|
* Either weight := NICE_0_LOAD and lw \e sched_prio_to_wmult[], in which case
|
|
* we're guaranteed shift stays positive because inv_weight is guaranteed to
|
|
* fit 32 bits, and NICE_0_LOAD gives another 10 bits; therefore shift >= 22.
|
|
*
|
|
* Or, weight =< lw.weight (because lw.weight is the runqueue weight), thus
|
|
* weight/lw.weight <= 1, and therefore our shift will also be positive.
|
|
*/
|
|
static u64 __calc_delta(u64 delta_exec, unsigned long weight, struct load_weight *lw)
|
|
{
|
|
u64 fact = scale_load_down(weight);
|
|
int shift = WMULT_SHIFT;
|
|
|
|
__update_inv_weight(lw);
|
|
|
|
if (unlikely(fact >> 32)) {
|
|
while (fact >> 32) {
|
|
fact >>= 1;
|
|
shift--;
|
|
}
|
|
}
|
|
|
|
/* hint to use a 32x32->64 mul */
|
|
fact = (u64)(u32)fact * lw->inv_weight;
|
|
|
|
while (fact >> 32) {
|
|
fact >>= 1;
|
|
shift--;
|
|
}
|
|
|
|
return mul_u64_u32_shr(delta_exec, fact, shift);
|
|
}
|
|
|
|
|
|
const struct sched_class fair_sched_class;
|
|
|
|
/**************************************************************
|
|
* CFS operations on generic schedulable entities:
|
|
*/
|
|
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
|
|
/* cpu runqueue to which this cfs_rq is attached */
|
|
static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
|
|
{
|
|
return cfs_rq->rq;
|
|
}
|
|
|
|
/* An entity is a task if it doesn't "own" a runqueue */
|
|
#define entity_is_task(se) (!se->my_q)
|
|
|
|
static inline struct task_struct *task_of(struct sched_entity *se)
|
|
{
|
|
SCHED_WARN_ON(!entity_is_task(se));
|
|
return container_of(se, struct task_struct, se);
|
|
}
|
|
|
|
/* Walk up scheduling entities hierarchy */
|
|
#define for_each_sched_entity(se) \
|
|
for (; se; se = se->parent)
|
|
|
|
static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
|
|
{
|
|
return p->se.cfs_rq;
|
|
}
|
|
|
|
/* runqueue on which this entity is (to be) queued */
|
|
static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
|
|
{
|
|
return se->cfs_rq;
|
|
}
|
|
|
|
/* runqueue "owned" by this group */
|
|
static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
|
|
{
|
|
return grp->my_q;
|
|
}
|
|
|
|
static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
|
|
{
|
|
if (!cfs_rq->on_list) {
|
|
struct rq *rq = rq_of(cfs_rq);
|
|
int cpu = cpu_of(rq);
|
|
/*
|
|
* Ensure we either appear before our parent (if already
|
|
* enqueued) or force our parent to appear after us when it is
|
|
* enqueued. The fact that we always enqueue bottom-up
|
|
* reduces this to two cases and a special case for the root
|
|
* cfs_rq. Furthermore, it also means that we will always reset
|
|
* tmp_alone_branch either when the branch is connected
|
|
* to a tree or when we reach the beg of the tree
|
|
*/
|
|
if (cfs_rq->tg->parent &&
|
|
cfs_rq->tg->parent->cfs_rq[cpu]->on_list) {
|
|
/*
|
|
* If parent is already on the list, we add the child
|
|
* just before. Thanks to circular linked property of
|
|
* the list, this means to put the child at the tail
|
|
* of the list that starts by parent.
|
|
*/
|
|
list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list,
|
|
&(cfs_rq->tg->parent->cfs_rq[cpu]->leaf_cfs_rq_list));
|
|
/*
|
|
* The branch is now connected to its tree so we can
|
|
* reset tmp_alone_branch to the beginning of the
|
|
* list.
|
|
*/
|
|
rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
|
|
} else if (!cfs_rq->tg->parent) {
|
|
/*
|
|
* cfs rq without parent should be put
|
|
* at the tail of the list.
|
|
*/
|
|
list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list,
|
|
&rq->leaf_cfs_rq_list);
|
|
/*
|
|
* We have reach the beg of a tree so we can reset
|
|
* tmp_alone_branch to the beginning of the list.
|
|
*/
|
|
rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
|
|
} else {
|
|
/*
|
|
* The parent has not already been added so we want to
|
|
* make sure that it will be put after us.
|
|
* tmp_alone_branch points to the beg of the branch
|
|
* where we will add parent.
|
|
*/
|
|
list_add_rcu(&cfs_rq->leaf_cfs_rq_list,
|
|
rq->tmp_alone_branch);
|
|
/*
|
|
* update tmp_alone_branch to points to the new beg
|
|
* of the branch
|
|
*/
|
|
rq->tmp_alone_branch = &cfs_rq->leaf_cfs_rq_list;
|
|
}
|
|
|
|
cfs_rq->on_list = 1;
|
|
}
|
|
}
|
|
|
|
static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
|
|
{
|
|
if (cfs_rq->on_list) {
|
|
list_del_rcu(&cfs_rq->leaf_cfs_rq_list);
|
|
cfs_rq->on_list = 0;
|
|
}
|
|
}
|
|
|
|
/* Iterate thr' all leaf cfs_rq's on a runqueue */
|
|
#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) \
|
|
list_for_each_entry_safe(cfs_rq, pos, &rq->leaf_cfs_rq_list, \
|
|
leaf_cfs_rq_list)
|
|
|
|
/* Do the two (enqueued) entities belong to the same group ? */
|
|
static inline struct cfs_rq *
|
|
is_same_group(struct sched_entity *se, struct sched_entity *pse)
|
|
{
|
|
if (se->cfs_rq == pse->cfs_rq)
|
|
return se->cfs_rq;
|
|
|
|
return NULL;
|
|
}
|
|
|
|
static inline struct sched_entity *parent_entity(struct sched_entity *se)
|
|
{
|
|
return se->parent;
|
|
}
|
|
|
|
static void
|
|
find_matching_se(struct sched_entity **se, struct sched_entity **pse)
|
|
{
|
|
int se_depth, pse_depth;
|
|
|
|
/*
|
|
* preemption test can be made between sibling entities who are in the
|
|
* same cfs_rq i.e who have a common parent. Walk up the hierarchy of
|
|
* both tasks until we find their ancestors who are siblings of common
|
|
* parent.
|
|
*/
|
|
|
|
/* First walk up until both entities are at same depth */
|
|
se_depth = (*se)->depth;
|
|
pse_depth = (*pse)->depth;
|
|
|
|
while (se_depth > pse_depth) {
|
|
se_depth--;
|
|
*se = parent_entity(*se);
|
|
}
|
|
|
|
while (pse_depth > se_depth) {
|
|
pse_depth--;
|
|
*pse = parent_entity(*pse);
|
|
}
|
|
|
|
while (!is_same_group(*se, *pse)) {
|
|
*se = parent_entity(*se);
|
|
*pse = parent_entity(*pse);
|
|
}
|
|
}
|
|
|
|
#else /* !CONFIG_FAIR_GROUP_SCHED */
|
|
|
|
static inline struct task_struct *task_of(struct sched_entity *se)
|
|
{
|
|
return container_of(se, struct task_struct, se);
|
|
}
|
|
|
|
static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
|
|
{
|
|
return container_of(cfs_rq, struct rq, cfs);
|
|
}
|
|
|
|
#define entity_is_task(se) 1
|
|
|
|
#define for_each_sched_entity(se) \
|
|
for (; se; se = NULL)
|
|
|
|
static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
|
|
{
|
|
return &task_rq(p)->cfs;
|
|
}
|
|
|
|
static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
|
|
{
|
|
struct task_struct *p = task_of(se);
|
|
struct rq *rq = task_rq(p);
|
|
|
|
return &rq->cfs;
|
|
}
|
|
|
|
/* runqueue "owned" by this group */
|
|
static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
|
|
{
|
|
}
|
|
|
|
static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
|
|
{
|
|
}
|
|
|
|
#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) \
|
|
for (cfs_rq = &rq->cfs, pos = NULL; cfs_rq; cfs_rq = pos)
|
|
|
|
static inline struct sched_entity *parent_entity(struct sched_entity *se)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline void
|
|
find_matching_se(struct sched_entity **se, struct sched_entity **pse)
|
|
{
|
|
}
|
|
|
|
#endif /* CONFIG_FAIR_GROUP_SCHED */
|
|
|
|
static __always_inline
|
|
void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec);
|
|
|
|
/**************************************************************
|
|
* Scheduling class tree data structure manipulation methods:
|
|
*/
|
|
|
|
static inline u64 max_vruntime(u64 max_vruntime, u64 vruntime)
|
|
{
|
|
s64 delta = (s64)(vruntime - max_vruntime);
|
|
if (delta > 0)
|
|
max_vruntime = vruntime;
|
|
|
|
return max_vruntime;
|
|
}
|
|
|
|
static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime)
|
|
{
|
|
s64 delta = (s64)(vruntime - min_vruntime);
|
|
if (delta < 0)
|
|
min_vruntime = vruntime;
|
|
|
|
return min_vruntime;
|
|
}
|
|
|
|
static inline int entity_before(struct sched_entity *a,
|
|
struct sched_entity *b)
|
|
{
|
|
return (s64)(a->vruntime - b->vruntime) < 0;
|
|
}
|
|
|
|
static void update_min_vruntime(struct cfs_rq *cfs_rq)
|
|
{
|
|
struct sched_entity *curr = cfs_rq->curr;
|
|
|
|
u64 vruntime = cfs_rq->min_vruntime;
|
|
|
|
if (curr) {
|
|
if (curr->on_rq)
|
|
vruntime = curr->vruntime;
|
|
else
|
|
curr = NULL;
|
|
}
|
|
|
|
if (cfs_rq->rb_leftmost) {
|
|
struct sched_entity *se = rb_entry(cfs_rq->rb_leftmost,
|
|
struct sched_entity,
|
|
run_node);
|
|
|
|
if (!curr)
|
|
vruntime = se->vruntime;
|
|
else
|
|
vruntime = min_vruntime(vruntime, se->vruntime);
|
|
}
|
|
|
|
/* ensure we never gain time by being placed backwards. */
|
|
cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime);
|
|
#ifndef CONFIG_64BIT
|
|
smp_wmb();
|
|
cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
|
|
#endif
|
|
}
|
|
|
|
/*
|
|
* Enqueue an entity into the rb-tree:
|
|
*/
|
|
static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|
{
|
|
struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
|
|
struct rb_node *parent = NULL;
|
|
struct sched_entity *entry;
|
|
int leftmost = 1;
|
|
|
|
/*
|
|
* Find the right place in the rbtree:
|
|
*/
|
|
while (*link) {
|
|
parent = *link;
|
|
entry = rb_entry(parent, struct sched_entity, run_node);
|
|
/*
|
|
* We dont care about collisions. Nodes with
|
|
* the same key stay together.
|
|
*/
|
|
if (entity_before(se, entry)) {
|
|
link = &parent->rb_left;
|
|
} else {
|
|
link = &parent->rb_right;
|
|
leftmost = 0;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Maintain a cache of leftmost tree entries (it is frequently
|
|
* used):
|
|
*/
|
|
if (leftmost)
|
|
cfs_rq->rb_leftmost = &se->run_node;
|
|
|
|
rb_link_node(&se->run_node, parent, link);
|
|
rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
|
|
}
|
|
|
|
static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|
{
|
|
if (cfs_rq->rb_leftmost == &se->run_node) {
|
|
struct rb_node *next_node;
|
|
|
|
next_node = rb_next(&se->run_node);
|
|
cfs_rq->rb_leftmost = next_node;
|
|
}
|
|
|
|
rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
|
|
}
|
|
|
|
struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
|
|
{
|
|
struct rb_node *left = cfs_rq->rb_leftmost;
|
|
|
|
if (!left)
|
|
return NULL;
|
|
|
|
return rb_entry(left, struct sched_entity, run_node);
|
|
}
|
|
|
|
static struct sched_entity *__pick_next_entity(struct sched_entity *se)
|
|
{
|
|
struct rb_node *next = rb_next(&se->run_node);
|
|
|
|
if (!next)
|
|
return NULL;
|
|
|
|
return rb_entry(next, struct sched_entity, run_node);
|
|
}
|
|
|
|
#ifdef CONFIG_SCHED_DEBUG
|
|
struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
|
|
{
|
|
struct rb_node *last = rb_last(&cfs_rq->tasks_timeline);
|
|
|
|
if (!last)
|
|
return NULL;
|
|
|
|
return rb_entry(last, struct sched_entity, run_node);
|
|
}
|
|
|
|
/**************************************************************
|
|
* Scheduling class statistics methods:
|
|
*/
|
|
|
|
int sched_proc_update_handler(struct ctl_table *table, int write,
|
|
void __user *buffer, size_t *lenp,
|
|
loff_t *ppos)
|
|
{
|
|
int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
|
|
unsigned int factor = get_update_sysctl_factor();
|
|
|
|
if (ret || !write)
|
|
return ret;
|
|
|
|
sched_nr_latency = DIV_ROUND_UP(sysctl_sched_latency,
|
|
sysctl_sched_min_granularity);
|
|
|
|
#define WRT_SYSCTL(name) \
|
|
(normalized_sysctl_##name = sysctl_##name / (factor))
|
|
WRT_SYSCTL(sched_min_granularity);
|
|
WRT_SYSCTL(sched_latency);
|
|
WRT_SYSCTL(sched_wakeup_granularity);
|
|
#undef WRT_SYSCTL
|
|
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* delta /= w
|
|
*/
|
|
static inline u64 calc_delta_fair(u64 delta, struct sched_entity *se)
|
|
{
|
|
if (unlikely(se->load.weight != NICE_0_LOAD))
|
|
delta = __calc_delta(delta, NICE_0_LOAD, &se->load);
|
|
|
|
return delta;
|
|
}
|
|
|
|
/*
|
|
* The idea is to set a period in which each task runs once.
|
|
*
|
|
* When there are too many tasks (sched_nr_latency) we have to stretch
|
|
* this period because otherwise the slices get too small.
|
|
*
|
|
* p = (nr <= nl) ? l : l*nr/nl
|
|
*/
|
|
static u64 __sched_period(unsigned long nr_running)
|
|
{
|
|
if (unlikely(nr_running > sched_nr_latency))
|
|
return nr_running * sysctl_sched_min_granularity;
|
|
else
|
|
return sysctl_sched_latency;
|
|
}
|
|
|
|
/*
|
|
* We calculate the wall-time slice from the period by taking a part
|
|
* proportional to the weight.
|
|
*
|
|
* s = p*P[w/rw]
|
|
*/
|
|
static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|
{
|
|
u64 slice = __sched_period(cfs_rq->nr_running + !se->on_rq);
|
|
|
|
for_each_sched_entity(se) {
|
|
struct load_weight *load;
|
|
struct load_weight lw;
|
|
|
|
cfs_rq = cfs_rq_of(se);
|
|
load = &cfs_rq->load;
|
|
|
|
if (unlikely(!se->on_rq)) {
|
|
lw = cfs_rq->load;
|
|
|
|
update_load_add(&lw, se->load.weight);
|
|
load = &lw;
|
|
}
|
|
slice = __calc_delta(slice, se->load.weight, load);
|
|
}
|
|
return slice;
|
|
}
|
|
|
|
/*
|
|
* We calculate the vruntime slice of a to-be-inserted task.
|
|
*
|
|
* vs = s/w
|
|
*/
|
|
static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|
{
|
|
return calc_delta_fair(sched_slice(cfs_rq, se), se);
|
|
}
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
#include "sched-pelt.h"
|
|
|
|
static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu);
|
|
static unsigned long task_h_load(struct task_struct *p);
|
|
|
|
/* Give new sched_entity start runnable values to heavy its load in infant time */
|
|
void init_entity_runnable_average(struct sched_entity *se)
|
|
{
|
|
struct sched_avg *sa = &se->avg;
|
|
|
|
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;
|
|
/*
|
|
* Tasks are intialized with full load to be seen as heavy tasks until
|
|
* they get a chance to stabilize to their real load level.
|
|
* Group entities are intialized with zero load to reflect the fact that
|
|
* nothing has been attached to the task group yet.
|
|
*/
|
|
if (entity_is_task(se))
|
|
sa->load_avg = scale_load_down(se->load.weight);
|
|
sa->load_sum = sa->load_avg * LOAD_AVG_MAX;
|
|
/*
|
|
* At this point, util_avg won't be used in select_task_rq_fair anyway
|
|
*/
|
|
sa->util_avg = 0;
|
|
sa->util_sum = 0;
|
|
/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
|
|
}
|
|
|
|
static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
|
|
static void attach_entity_cfs_rq(struct sched_entity *se);
|
|
|
|
/*
|
|
* With new tasks being created, their initial util_avgs are extrapolated
|
|
* based on the cfs_rq's current util_avg:
|
|
*
|
|
* util_avg = cfs_rq->util_avg / (cfs_rq->load_avg + 1) * se.load.weight
|
|
*
|
|
* However, in many cases, the above util_avg does not give a desired
|
|
* value. Moreover, the sum of the util_avgs may be divergent, such
|
|
* as when the series is a harmonic series.
|
|
*
|
|
* To solve this problem, we also cap the util_avg of successive tasks to
|
|
* only 1/2 of the left utilization budget:
|
|
*
|
|
* util_avg_cap = (1024 - cfs_rq->avg.util_avg) / 2^n
|
|
*
|
|
* where n denotes the nth task.
|
|
*
|
|
* For example, a simplest series from the beginning would be like:
|
|
*
|
|
* task util_avg: 512, 256, 128, 64, 32, 16, 8, ...
|
|
* cfs_rq util_avg: 512, 768, 896, 960, 992, 1008, 1016, ...
|
|
*
|
|
* Finally, that extrapolated util_avg is clamped to the cap (util_avg_cap)
|
|
* if util_avg > util_avg_cap.
|
|
*/
|
|
void post_init_entity_util_avg(struct sched_entity *se)
|
|
{
|
|
struct cfs_rq *cfs_rq = cfs_rq_of(se);
|
|
struct sched_avg *sa = &se->avg;
|
|
long cap = (long)(SCHED_CAPACITY_SCALE - cfs_rq->avg.util_avg) / 2;
|
|
|
|
if (cap > 0) {
|
|
if (cfs_rq->avg.util_avg != 0) {
|
|
sa->util_avg = cfs_rq->avg.util_avg * se->load.weight;
|
|
sa->util_avg /= (cfs_rq->avg.load_avg + 1);
|
|
|
|
if (sa->util_avg > cap)
|
|
sa->util_avg = cap;
|
|
} else {
|
|
sa->util_avg = cap;
|
|
}
|
|
sa->util_sum = sa->util_avg * LOAD_AVG_MAX;
|
|
}
|
|
|
|
if (entity_is_task(se)) {
|
|
struct task_struct *p = task_of(se);
|
|
if (p->sched_class != &fair_sched_class) {
|
|
/*
|
|
* For !fair tasks do:
|
|
*
|
|
update_cfs_rq_load_avg(now, cfs_rq, false);
|
|
attach_entity_load_avg(cfs_rq, se);
|
|
switched_from_fair(rq, p);
|
|
*
|
|
* such that the next switched_to_fair() has the
|
|
* expected state.
|
|
*/
|
|
se->avg.last_update_time = cfs_rq_clock_task(cfs_rq);
|
|
return;
|
|
}
|
|
}
|
|
|
|
attach_entity_cfs_rq(se);
|
|
}
|
|
|
|
#else /* !CONFIG_SMP */
|
|
void init_entity_runnable_average(struct sched_entity *se)
|
|
{
|
|
}
|
|
void post_init_entity_util_avg(struct sched_entity *se)
|
|
{
|
|
}
|
|
static void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
|
|
{
|
|
}
|
|
#endif /* CONFIG_SMP */
|
|
|
|
/*
|
|
* Update the current task's runtime statistics.
|
|
*/
|
|
static void update_curr(struct cfs_rq *cfs_rq)
|
|
{
|
|
struct sched_entity *curr = cfs_rq->curr;
|
|
u64 now = rq_clock_task(rq_of(cfs_rq));
|
|
u64 delta_exec;
|
|
|
|
if (unlikely(!curr))
|
|
return;
|
|
|
|
delta_exec = now - curr->exec_start;
|
|
if (unlikely((s64)delta_exec <= 0))
|
|
return;
|
|
|
|
curr->exec_start = now;
|
|
|
|
schedstat_set(curr->statistics.exec_max,
|
|
max(delta_exec, curr->statistics.exec_max));
|
|
|
|
curr->sum_exec_runtime += delta_exec;
|
|
schedstat_add(cfs_rq->exec_clock, delta_exec);
|
|
|
|
curr->vruntime += calc_delta_fair(delta_exec, curr);
|
|
update_min_vruntime(cfs_rq);
|
|
|
|
if (entity_is_task(curr)) {
|
|
struct task_struct *curtask = task_of(curr);
|
|
|
|
trace_sched_stat_runtime(curtask, delta_exec, curr->vruntime);
|
|
cpuacct_charge(curtask, delta_exec);
|
|
account_group_exec_runtime(curtask, delta_exec);
|
|
}
|
|
|
|
account_cfs_rq_runtime(cfs_rq, delta_exec);
|
|
}
|
|
|
|
static void update_curr_fair(struct rq *rq)
|
|
{
|
|
update_curr(cfs_rq_of(&rq->curr->se));
|
|
}
|
|
|
|
static inline void
|
|
update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|
{
|
|
u64 wait_start, prev_wait_start;
|
|
|
|
if (!schedstat_enabled())
|
|
return;
|
|
|
|
wait_start = rq_clock(rq_of(cfs_rq));
|
|
prev_wait_start = schedstat_val(se->statistics.wait_start);
|
|
|
|
if (entity_is_task(se) && task_on_rq_migrating(task_of(se)) &&
|
|
likely(wait_start > prev_wait_start))
|
|
wait_start -= prev_wait_start;
|
|
|
|
schedstat_set(se->statistics.wait_start, wait_start);
|
|
}
|
|
|
|
static inline void
|
|
update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|
{
|
|
struct task_struct *p;
|
|
u64 delta;
|
|
|
|
if (!schedstat_enabled())
|
|
return;
|
|
|
|
delta = rq_clock(rq_of(cfs_rq)) - schedstat_val(se->statistics.wait_start);
|
|
|
|
if (entity_is_task(se)) {
|
|
p = task_of(se);
|
|
if (task_on_rq_migrating(p)) {
|
|
/*
|
|
* Preserve migrating task's wait time so wait_start
|
|
* time stamp can be adjusted to accumulate wait time
|
|
* prior to migration.
|
|
*/
|
|
schedstat_set(se->statistics.wait_start, delta);
|
|
return;
|
|
}
|
|
trace_sched_stat_wait(p, delta);
|
|
}
|
|
|
|
schedstat_set(se->statistics.wait_max,
|
|
max(schedstat_val(se->statistics.wait_max), delta));
|
|
schedstat_inc(se->statistics.wait_count);
|
|
schedstat_add(se->statistics.wait_sum, delta);
|
|
schedstat_set(se->statistics.wait_start, 0);
|
|
}
|
|
|
|
static inline void
|
|
update_stats_enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|
{
|
|
struct task_struct *tsk = NULL;
|
|
u64 sleep_start, block_start;
|
|
|
|
if (!schedstat_enabled())
|
|
return;
|
|
|
|
sleep_start = schedstat_val(se->statistics.sleep_start);
|
|
block_start = schedstat_val(se->statistics.block_start);
|
|
|
|
if (entity_is_task(se))
|
|
tsk = task_of(se);
|
|
|
|
if (sleep_start) {
|
|
u64 delta = rq_clock(rq_of(cfs_rq)) - sleep_start;
|
|
|
|
if ((s64)delta < 0)
|
|
delta = 0;
|
|
|
|
if (unlikely(delta > schedstat_val(se->statistics.sleep_max)))
|
|
schedstat_set(se->statistics.sleep_max, delta);
|
|
|
|
schedstat_set(se->statistics.sleep_start, 0);
|
|
schedstat_add(se->statistics.sum_sleep_runtime, delta);
|
|
|
|
if (tsk) {
|
|
account_scheduler_latency(tsk, delta >> 10, 1);
|
|
trace_sched_stat_sleep(tsk, delta);
|
|
}
|
|
}
|
|
if (block_start) {
|
|
u64 delta = rq_clock(rq_of(cfs_rq)) - block_start;
|
|
|
|
if ((s64)delta < 0)
|
|
delta = 0;
|
|
|
|
if (unlikely(delta > schedstat_val(se->statistics.block_max)))
|
|
schedstat_set(se->statistics.block_max, delta);
|
|
|
|
schedstat_set(se->statistics.block_start, 0);
|
|
schedstat_add(se->statistics.sum_sleep_runtime, delta);
|
|
|
|
if (tsk) {
|
|
if (tsk->in_iowait) {
|
|
schedstat_add(se->statistics.iowait_sum, delta);
|
|
schedstat_inc(se->statistics.iowait_count);
|
|
trace_sched_stat_iowait(tsk, delta);
|
|
}
|
|
|
|
trace_sched_stat_blocked(tsk, delta);
|
|
|
|
/*
|
|
* Blocking time is in units of nanosecs, so shift by
|
|
* 20 to get a milliseconds-range estimation of the
|
|
* amount of time that the task spent sleeping:
|
|
*/
|
|
if (unlikely(prof_on == SLEEP_PROFILING)) {
|
|
profile_hits(SLEEP_PROFILING,
|
|
(void *)get_wchan(tsk),
|
|
delta >> 20);
|
|
}
|
|
account_scheduler_latency(tsk, delta >> 10, 0);
|
|
}
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Task is being enqueued - update stats:
|
|
*/
|
|
static inline void
|
|
update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
|
|
{
|
|
if (!schedstat_enabled())
|
|
return;
|
|
|
|
/*
|
|
* Are we enqueueing a waiting task? (for current tasks
|
|
* a dequeue/enqueue event is a NOP)
|
|
*/
|
|
if (se != cfs_rq->curr)
|
|
update_stats_wait_start(cfs_rq, se);
|
|
|
|
if (flags & ENQUEUE_WAKEUP)
|
|
update_stats_enqueue_sleeper(cfs_rq, se);
|
|
}
|
|
|
|
static inline void
|
|
update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
|
|
{
|
|
|
|
if (!schedstat_enabled())
|
|
return;
|
|
|
|
/*
|
|
* Mark the end of the wait period if dequeueing a
|
|
* waiting task:
|
|
*/
|
|
if (se != cfs_rq->curr)
|
|
update_stats_wait_end(cfs_rq, se);
|
|
|
|
if ((flags & DEQUEUE_SLEEP) && entity_is_task(se)) {
|
|
struct task_struct *tsk = task_of(se);
|
|
|
|
if (tsk->state & TASK_INTERRUPTIBLE)
|
|
schedstat_set(se->statistics.sleep_start,
|
|
rq_clock(rq_of(cfs_rq)));
|
|
if (tsk->state & TASK_UNINTERRUPTIBLE)
|
|
schedstat_set(se->statistics.block_start,
|
|
rq_clock(rq_of(cfs_rq)));
|
|
}
|
|
}
|
|
|
|
/*
|
|
* We are picking a new current task - update its stats:
|
|
*/
|
|
static inline void
|
|
update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|
{
|
|
/*
|
|
* We are starting a new run period:
|
|
*/
|
|
se->exec_start = rq_clock_task(rq_of(cfs_rq));
|
|
}
|
|
|
|
/**************************************************
|
|
* Scheduling class queueing methods:
|
|
*/
|
|
|
|
#ifdef CONFIG_NUMA_BALANCING
|
|
/*
|
|
* Approximate time to scan a full NUMA task in ms. The task scan period is
|
|
* calculated based on the tasks virtual memory size and
|
|
* numa_balancing_scan_size.
|
|
*/
|
|
unsigned int sysctl_numa_balancing_scan_period_min = 1000;
|
|
unsigned int sysctl_numa_balancing_scan_period_max = 60000;
|
|
|
|
/* Portion of address space to scan in MB */
|
|
unsigned int sysctl_numa_balancing_scan_size = 256;
|
|
|
|
/* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */
|
|
unsigned int sysctl_numa_balancing_scan_delay = 1000;
|
|
|
|
static unsigned int task_nr_scan_windows(struct task_struct *p)
|
|
{
|
|
unsigned long rss = 0;
|
|
unsigned long nr_scan_pages;
|
|
|
|
/*
|
|
* Calculations based on RSS as non-present and empty pages are skipped
|
|
* by the PTE scanner and NUMA hinting faults should be trapped based
|
|
* on resident pages
|
|
*/
|
|
nr_scan_pages = sysctl_numa_balancing_scan_size << (20 - PAGE_SHIFT);
|
|
rss = get_mm_rss(p->mm);
|
|
if (!rss)
|
|
rss = nr_scan_pages;
|
|
|
|
rss = round_up(rss, nr_scan_pages);
|
|
return rss / nr_scan_pages;
|
|
}
|
|
|
|
/* For sanitys sake, never scan more PTEs than MAX_SCAN_WINDOW MB/sec. */
|
|
#define MAX_SCAN_WINDOW 2560
|
|
|
|
static unsigned int task_scan_min(struct task_struct *p)
|
|
{
|
|
unsigned int scan_size = READ_ONCE(sysctl_numa_balancing_scan_size);
|
|
unsigned int scan, floor;
|
|
unsigned int windows = 1;
|
|
|
|
if (scan_size < MAX_SCAN_WINDOW)
|
|
windows = MAX_SCAN_WINDOW / scan_size;
|
|
floor = 1000 / windows;
|
|
|
|
scan = sysctl_numa_balancing_scan_period_min / task_nr_scan_windows(p);
|
|
return max_t(unsigned int, floor, scan);
|
|
}
|
|
|
|
static unsigned int task_scan_max(struct task_struct *p)
|
|
{
|
|
unsigned int smin = task_scan_min(p);
|
|
unsigned int smax;
|
|
|
|
/* Watch for min being lower than max due to floor calculations */
|
|
smax = sysctl_numa_balancing_scan_period_max / task_nr_scan_windows(p);
|
|
return max(smin, smax);
|
|
}
|
|
|
|
static void account_numa_enqueue(struct rq *rq, struct task_struct *p)
|
|
{
|
|
rq->nr_numa_running += (p->numa_preferred_nid != -1);
|
|
rq->nr_preferred_running += (p->numa_preferred_nid == task_node(p));
|
|
}
|
|
|
|
static void account_numa_dequeue(struct rq *rq, struct task_struct *p)
|
|
{
|
|
rq->nr_numa_running -= (p->numa_preferred_nid != -1);
|
|
rq->nr_preferred_running -= (p->numa_preferred_nid == task_node(p));
|
|
}
|
|
|
|
struct numa_group {
|
|
atomic_t refcount;
|
|
|
|
spinlock_t lock; /* nr_tasks, tasks */
|
|
int nr_tasks;
|
|
pid_t gid;
|
|
int active_nodes;
|
|
|
|
struct rcu_head rcu;
|
|
unsigned long total_faults;
|
|
unsigned long max_faults_cpu;
|
|
/*
|
|
* Faults_cpu is used to decide whether memory should move
|
|
* towards the CPU. As a consequence, these stats are weighted
|
|
* more by CPU use than by memory faults.
|
|
*/
|
|
unsigned long *faults_cpu;
|
|
unsigned long faults[0];
|
|
};
|
|
|
|
/* Shared or private faults. */
|
|
#define NR_NUMA_HINT_FAULT_TYPES 2
|
|
|
|
/* Memory and CPU locality */
|
|
#define NR_NUMA_HINT_FAULT_STATS (NR_NUMA_HINT_FAULT_TYPES * 2)
|
|
|
|
/* Averaged statistics, and temporary buffers. */
|
|
#define NR_NUMA_HINT_FAULT_BUCKETS (NR_NUMA_HINT_FAULT_STATS * 2)
|
|
|
|
pid_t task_numa_group_id(struct task_struct *p)
|
|
{
|
|
return p->numa_group ? p->numa_group->gid : 0;
|
|
}
|
|
|
|
/*
|
|
* The averaged statistics, shared & private, memory & cpu,
|
|
* occupy the first half of the array. The second half of the
|
|
* array is for current counters, which are averaged into the
|
|
* first set by task_numa_placement.
|
|
*/
|
|
static inline int task_faults_idx(enum numa_faults_stats s, int nid, int priv)
|
|
{
|
|
return NR_NUMA_HINT_FAULT_TYPES * (s * nr_node_ids + nid) + priv;
|
|
}
|
|
|
|
static inline unsigned long task_faults(struct task_struct *p, int nid)
|
|
{
|
|
if (!p->numa_faults)
|
|
return 0;
|
|
|
|
return p->numa_faults[task_faults_idx(NUMA_MEM, nid, 0)] +
|
|
p->numa_faults[task_faults_idx(NUMA_MEM, nid, 1)];
|
|
}
|
|
|
|
static inline unsigned long group_faults(struct task_struct *p, int nid)
|
|
{
|
|
if (!p->numa_group)
|
|
return 0;
|
|
|
|
return p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 0)] +
|
|
p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 1)];
|
|
}
|
|
|
|
static inline unsigned long group_faults_cpu(struct numa_group *group, int nid)
|
|
{
|
|
return group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 0)] +
|
|
group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 1)];
|
|
}
|
|
|
|
/*
|
|
* A node triggering more than 1/3 as many NUMA faults as the maximum is
|
|
* considered part of a numa group's pseudo-interleaving set. Migrations
|
|
* between these nodes are slowed down, to allow things to settle down.
|
|
*/
|
|
#define ACTIVE_NODE_FRACTION 3
|
|
|
|
static bool numa_is_active_node(int nid, struct numa_group *ng)
|
|
{
|
|
return group_faults_cpu(ng, nid) * ACTIVE_NODE_FRACTION > ng->max_faults_cpu;
|
|
}
|
|
|
|
/* Handle placement on systems where not all nodes are directly connected. */
|
|
static unsigned long score_nearby_nodes(struct task_struct *p, int nid,
|
|
int maxdist, bool task)
|
|
{
|
|
unsigned long score = 0;
|
|
int node;
|
|
|
|
/*
|
|
* All nodes are directly connected, and the same distance
|
|
* from each other. No need for fancy placement algorithms.
|
|
*/
|
|
if (sched_numa_topology_type == NUMA_DIRECT)
|
|
return 0;
|
|
|
|
/*
|
|
* This code is called for each node, introducing N^2 complexity,
|
|
* which should be ok given the number of nodes rarely exceeds 8.
|
|
*/
|
|
for_each_online_node(node) {
|
|
unsigned long faults;
|
|
int dist = node_distance(nid, node);
|
|
|
|
/*
|
|
* The furthest away nodes in the system are not interesting
|
|
* for placement; nid was already counted.
|
|
*/
|
|
if (dist == sched_max_numa_distance || node == nid)
|
|
continue;
|
|
|
|
/*
|
|
* On systems with a backplane NUMA topology, compare groups
|
|
* of nodes, and move tasks towards the group with the most
|
|
* memory accesses. When comparing two nodes at distance
|
|
* "hoplimit", only nodes closer by than "hoplimit" are part
|
|
* of each group. Skip other nodes.
|
|
*/
|
|
if (sched_numa_topology_type == NUMA_BACKPLANE &&
|
|
dist > maxdist)
|
|
continue;
|
|
|
|
/* Add up the faults from nearby nodes. */
|
|
if (task)
|
|
faults = task_faults(p, node);
|
|
else
|
|
faults = group_faults(p, node);
|
|
|
|
/*
|
|
* On systems with a glueless mesh NUMA topology, there are
|
|
* no fixed "groups of nodes". Instead, nodes that are not
|
|
* directly connected bounce traffic through intermediate
|
|
* nodes; a numa_group can occupy any set of nodes.
|
|
* The further away a node is, the less the faults count.
|
|
* This seems to result in good task placement.
|
|
*/
|
|
if (sched_numa_topology_type == NUMA_GLUELESS_MESH) {
|
|
faults *= (sched_max_numa_distance - dist);
|
|
faults /= (sched_max_numa_distance - LOCAL_DISTANCE);
|
|
}
|
|
|
|
score += faults;
|
|
}
|
|
|
|
return score;
|
|
}
|
|
|
|
/*
|
|
* These return the fraction of accesses done by a particular task, or
|
|
* task group, on a particular numa node. The group weight is given a
|
|
* larger multiplier, in order to group tasks together that are almost
|
|
* evenly spread out between numa nodes.
|
|
*/
|
|
static inline unsigned long task_weight(struct task_struct *p, int nid,
|
|
int dist)
|
|
{
|
|
unsigned long faults, total_faults;
|
|
|
|
if (!p->numa_faults)
|
|
return 0;
|
|
|
|
total_faults = p->total_numa_faults;
|
|
|
|
if (!total_faults)
|
|
return 0;
|
|
|
|
faults = task_faults(p, nid);
|
|
faults += score_nearby_nodes(p, nid, dist, true);
|
|
|
|
return 1000 * faults / total_faults;
|
|
}
|
|
|
|
static inline unsigned long group_weight(struct task_struct *p, int nid,
|
|
int dist)
|
|
{
|
|
unsigned long faults, total_faults;
|
|
|
|
if (!p->numa_group)
|
|
return 0;
|
|
|
|
total_faults = p->numa_group->total_faults;
|
|
|
|
if (!total_faults)
|
|
return 0;
|
|
|
|
faults = group_faults(p, nid);
|
|
faults += score_nearby_nodes(p, nid, dist, false);
|
|
|
|
return 1000 * faults / total_faults;
|
|
}
|
|
|
|
bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
|
|
int src_nid, int dst_cpu)
|
|
{
|
|
struct numa_group *ng = p->numa_group;
|
|
int dst_nid = cpu_to_node(dst_cpu);
|
|
int last_cpupid, this_cpupid;
|
|
|
|
this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid);
|
|
|
|
/*
|
|
* Multi-stage node selection is used in conjunction with a periodic
|
|
* migration fault to build a temporal task<->page relation. By using
|
|
* a two-stage filter we remove short/unlikely relations.
|
|
*
|
|
* Using P(p) ~ n_p / n_t as per frequentist probability, we can equate
|
|
* a task's usage of a particular page (n_p) per total usage of this
|
|
* page (n_t) (in a given time-span) to a probability.
|
|
*
|
|
* Our periodic faults will sample this probability and getting the
|
|
* same result twice in a row, given these samples are fully
|
|
* independent, is then given by P(n)^2, provided our sample period
|
|
* is sufficiently short compared to the usage pattern.
|
|
*
|
|
* This quadric squishes small probabilities, making it less likely we
|
|
* act on an unlikely task<->page relation.
|
|
*/
|
|
last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
|
|
if (!cpupid_pid_unset(last_cpupid) &&
|
|
cpupid_to_nid(last_cpupid) != dst_nid)
|
|
return false;
|
|
|
|
/* Always allow migrate on private faults */
|
|
if (cpupid_match_pid(p, last_cpupid))
|
|
return true;
|
|
|
|
/* A shared fault, but p->numa_group has not been set up yet. */
|
|
if (!ng)
|
|
return true;
|
|
|
|
/*
|
|
* Destination node is much more heavily used than the source
|
|
* node? Allow migration.
|
|
*/
|
|
if (group_faults_cpu(ng, dst_nid) > group_faults_cpu(ng, src_nid) *
|
|
ACTIVE_NODE_FRACTION)
|
|
return true;
|
|
|
|
/*
|
|
* Distribute memory according to CPU & memory use on each node,
|
|
* with 3/4 hysteresis to avoid unnecessary memory migrations:
|
|
*
|
|
* faults_cpu(dst) 3 faults_cpu(src)
|
|
* --------------- * - > ---------------
|
|
* faults_mem(dst) 4 faults_mem(src)
|
|
*/
|
|
return group_faults_cpu(ng, dst_nid) * group_faults(p, src_nid) * 3 >
|
|
group_faults_cpu(ng, src_nid) * group_faults(p, dst_nid) * 4;
|
|
}
|
|
|
|
static unsigned long weighted_cpuload(const int cpu);
|
|
static unsigned long source_load(int cpu, int type);
|
|
static unsigned long target_load(int cpu, int type);
|
|
static unsigned long capacity_of(int cpu);
|
|
|
|
/* Cached statistics for all CPUs within a node */
|
|
struct numa_stats {
|
|
unsigned long nr_running;
|
|
unsigned long load;
|
|
|
|
/* Total compute capacity of CPUs on a node */
|
|
unsigned long compute_capacity;
|
|
|
|
/* Approximate capacity in terms of runnable tasks on a node */
|
|
unsigned long task_capacity;
|
|
int has_free_capacity;
|
|
};
|
|
|
|
/*
|
|
* XXX borrowed from update_sg_lb_stats
|
|
*/
|
|
static void update_numa_stats(struct numa_stats *ns, int nid)
|
|
{
|
|
int smt, cpu, cpus = 0;
|
|
unsigned long capacity;
|
|
|
|
memset(ns, 0, sizeof(*ns));
|
|
for_each_cpu(cpu, cpumask_of_node(nid)) {
|
|
struct rq *rq = cpu_rq(cpu);
|
|
|
|
ns->nr_running += rq->nr_running;
|
|
ns->load += weighted_cpuload(cpu);
|
|
ns->compute_capacity += capacity_of(cpu);
|
|
|
|
cpus++;
|
|
}
|
|
|
|
/*
|
|
* If we raced with hotplug and there are no CPUs left in our mask
|
|
* the @ns structure is NULL'ed and task_numa_compare() will
|
|
* not find this node attractive.
|
|
*
|
|
* We'll either bail at !has_free_capacity, or we'll detect a huge
|
|
* imbalance and bail there.
|
|
*/
|
|
if (!cpus)
|
|
return;
|
|
|
|
/* smt := ceil(cpus / capacity), assumes: 1 < smt_power < 2 */
|
|
smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, ns->compute_capacity);
|
|
capacity = cpus / smt; /* cores */
|
|
|
|
ns->task_capacity = min_t(unsigned, capacity,
|
|
DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE));
|
|
ns->has_free_capacity = (ns->nr_running < ns->task_capacity);
|
|
}
|
|
|
|
struct task_numa_env {
|
|
struct task_struct *p;
|
|
|
|
int src_cpu, src_nid;
|
|
int dst_cpu, dst_nid;
|
|
|
|
struct numa_stats src_stats, dst_stats;
|
|
|
|
int imbalance_pct;
|
|
int dist;
|
|
|
|
struct task_struct *best_task;
|
|
long best_imp;
|
|
int best_cpu;
|
|
};
|
|
|
|
static void task_numa_assign(struct task_numa_env *env,
|
|
struct task_struct *p, long imp)
|
|
{
|
|
if (env->best_task)
|
|
put_task_struct(env->best_task);
|
|
if (p)
|
|
get_task_struct(p);
|
|
|
|
env->best_task = p;
|
|
env->best_imp = imp;
|
|
env->best_cpu = env->dst_cpu;
|
|
}
|
|
|
|
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;
|
|
|
|
/*
|
|
* The load is corrected for the CPU capacity available on each node.
|
|
*
|
|
* src_load dst_load
|
|
* ------------ vs ---------
|
|
* src_capacity dst_capacity
|
|
*/
|
|
src_capacity = env->src_stats.compute_capacity;
|
|
dst_capacity = env->dst_stats.compute_capacity;
|
|
|
|
/* We care about the slope of the imbalance, not the direction. */
|
|
if (dst_load < src_load)
|
|
swap(dst_load, src_load);
|
|
|
|
/* Is the difference below the threshold? */
|
|
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.
|
|
* Compare it with the old imbalance.
|
|
*/
|
|
orig_src_load = env->src_stats.load;
|
|
orig_dst_load = env->dst_stats.load;
|
|
|
|
if (orig_dst_load < orig_src_load)
|
|
swap(orig_dst_load, orig_src_load);
|
|
|
|
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);
|
|
}
|
|
|
|
/*
|
|
* This checks if the overall compute and NUMA accesses of the system would
|
|
* be improved if the source tasks was migrated to the target dst_cpu taking
|
|
* into account that it might be best if task running on the dst_cpu should
|
|
* be exchanged with the source task
|
|
*/
|
|
static void task_numa_compare(struct task_numa_env *env,
|
|
long taskimp, long groupimp)
|
|
{
|
|
struct rq *src_rq = cpu_rq(env->src_cpu);
|
|
struct rq *dst_rq = cpu_rq(env->dst_cpu);
|
|
struct task_struct *cur;
|
|
long src_load, dst_load;
|
|
long load;
|
|
long imp = env->p->numa_group ? groupimp : taskimp;
|
|
long moveimp = imp;
|
|
int dist = env->dist;
|
|
|
|
rcu_read_lock();
|
|
cur = task_rcu_dereference(&dst_rq->curr);
|
|
if (cur && ((cur->flags & PF_EXITING) || is_idle_task(cur)))
|
|
cur = NULL;
|
|
|
|
/*
|
|
* Because we have preemption enabled we can get migrated around and
|
|
* end try selecting ourselves (current == env->p) as a swap candidate.
|
|
*/
|
|
if (cur == env->p)
|
|
goto unlock;
|
|
|
|
/*
|
|
* "imp" is the fault differential for the source task between the
|
|
* source and destination node. Calculate the total differential for
|
|
* the source task and potential destination task. The more negative
|
|
* the value is, the more rmeote accesses that would be expected to
|
|
* be incurred if the tasks were swapped.
|
|
*/
|
|
if (cur) {
|
|
/* Skip this swap candidate if cannot move to the source cpu */
|
|
if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed))
|
|
goto unlock;
|
|
|
|
/*
|
|
* If dst and source tasks are in the same NUMA group, or not
|
|
* in any group then look only at task weights.
|
|
*/
|
|
if (cur->numa_group == env->p->numa_group) {
|
|
imp = taskimp + task_weight(cur, env->src_nid, dist) -
|
|
task_weight(cur, env->dst_nid, dist);
|
|
/*
|
|
* Add some hysteresis to prevent swapping the
|
|
* tasks within a group over tiny differences.
|
|
*/
|
|
if (cur->numa_group)
|
|
imp -= imp/16;
|
|
} else {
|
|
/*
|
|
* Compare the group weights. If a task is all by
|
|
* itself (not part of a group), use the task weight
|
|
* instead.
|
|
*/
|
|
if (cur->numa_group)
|
|
imp += group_weight(cur, env->src_nid, dist) -
|
|
group_weight(cur, env->dst_nid, dist);
|
|
else
|
|
imp += task_weight(cur, env->src_nid, dist) -
|
|
task_weight(cur, env->dst_nid, dist);
|
|
}
|
|
}
|
|
|
|
if (imp <= env->best_imp && moveimp <= env->best_imp)
|
|
goto unlock;
|
|
|
|
if (!cur) {
|
|
/* Is there capacity at our destination? */
|
|
if (env->src_stats.nr_running <= env->src_stats.task_capacity &&
|
|
!env->dst_stats.has_free_capacity)
|
|
goto unlock;
|
|
|
|
goto balance;
|
|
}
|
|
|
|
/* Balance doesn't matter much if we're running a task per cpu */
|
|
if (imp > env->best_imp && src_rq->nr_running == 1 &&
|
|
dst_rq->nr_running == 1)
|
|
goto assign;
|
|
|
|
/*
|
|
* In the overloaded case, try and keep the load balanced.
|
|
*/
|
|
balance:
|
|
load = task_h_load(env->p);
|
|
dst_load = env->dst_stats.load + load;
|
|
src_load = env->src_stats.load - load;
|
|
|
|
if (moveimp > imp && moveimp > env->best_imp) {
|
|
/*
|
|
* If the improvement from just moving env->p direction is
|
|
* better than swapping tasks around, check if a move is
|
|
* possible. Store a slightly smaller score than moveimp,
|
|
* so an actually idle CPU will win.
|
|
*/
|
|
if (!load_too_imbalanced(src_load, dst_load, env)) {
|
|
imp = moveimp - 1;
|
|
cur = NULL;
|
|
goto assign;
|
|
}
|
|
}
|
|
|
|
if (imp <= env->best_imp)
|
|
goto unlock;
|
|
|
|
if (cur) {
|
|
load = task_h_load(cur);
|
|
dst_load -= load;
|
|
src_load += load;
|
|
}
|
|
|
|
if (load_too_imbalanced(src_load, dst_load, env))
|
|
goto unlock;
|
|
|
|
/*
|
|
* One idle CPU per node is evaluated for a task numa move.
|
|
* Call select_idle_sibling to maybe find a better one.
|
|
*/
|
|
if (!cur) {
|
|
/*
|
|
* select_idle_siblings() uses an per-cpu cpumask that
|
|
* can be used from IRQ context.
|
|
*/
|
|
local_irq_disable();
|
|
env->dst_cpu = select_idle_sibling(env->p, env->src_cpu,
|
|
env->dst_cpu);
|
|
local_irq_enable();
|
|
}
|
|
|
|
assign:
|
|
task_numa_assign(env, cur, imp);
|
|
unlock:
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
static void task_numa_find_cpu(struct task_numa_env *env,
|
|
long taskimp, long groupimp)
|
|
{
|
|
int cpu;
|
|
|
|
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))
|
|
continue;
|
|
|
|
env->dst_cpu = cpu;
|
|
task_numa_compare(env, taskimp, groupimp);
|
|
}
|
|
}
|
|
|
|
/* 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 = {
|
|
.p = p,
|
|
|
|
.src_cpu = task_cpu(p),
|
|
.src_nid = task_node(p),
|
|
|
|
.imbalance_pct = 112,
|
|
|
|
.best_task = NULL,
|
|
.best_imp = 0,
|
|
.best_cpu = -1,
|
|
};
|
|
struct sched_domain *sd;
|
|
unsigned long taskweight, groupweight;
|
|
int nid, ret, dist;
|
|
long taskimp, groupimp;
|
|
|
|
/*
|
|
* Pick the lowest SD_NUMA domain, as that would have the smallest
|
|
* imbalance and would be the first to start moving tasks about.
|
|
*
|
|
* And we want to avoid any moving of tasks about, as that would create
|
|
* random movement of tasks -- counter the numa conditions we're trying
|
|
* to satisfy here.
|
|
*/
|
|
rcu_read_lock();
|
|
sd = rcu_dereference(per_cpu(sd_numa, env.src_cpu));
|
|
if (sd)
|
|
env.imbalance_pct = 100 + (sd->imbalance_pct - 100) / 2;
|
|
rcu_read_unlock();
|
|
|
|
/*
|
|
* Cpusets can break the scheduler domain tree into smaller
|
|
* balance domains, some of which do not cross NUMA boundaries.
|
|
* Tasks that are "trapped" in such domains cannot be migrated
|
|
* elsewhere, so there is no point in (re)trying.
|
|
*/
|
|
if (unlikely(!sd)) {
|
|
p->numa_preferred_nid = task_node(p);
|
|
return -EINVAL;
|
|
}
|
|
|
|
env.dst_nid = p->numa_preferred_nid;
|
|
dist = env.dist = node_distance(env.src_nid, env.dst_nid);
|
|
taskweight = task_weight(p, env.src_nid, dist);
|
|
groupweight = group_weight(p, env.src_nid, dist);
|
|
update_numa_stats(&env.src_stats, env.src_nid);
|
|
taskimp = task_weight(p, env.dst_nid, dist) - taskweight;
|
|
groupimp = group_weight(p, env.dst_nid, dist) - groupweight;
|
|
update_numa_stats(&env.dst_stats, env.dst_nid);
|
|
|
|
/* Try to find a spot on the preferred nid. */
|
|
if (numa_has_capacity(&env))
|
|
task_numa_find_cpu(&env, taskimp, groupimp);
|
|
|
|
/*
|
|
* Look at other nodes in these cases:
|
|
* - there is no space available on the preferred_nid
|
|
* - the task is part of a numa_group that is interleaved across
|
|
* multiple NUMA nodes; in order to better consolidate the group,
|
|
* we need to check other locations.
|
|
*/
|
|
if (env.best_cpu == -1 || (p->numa_group && p->numa_group->active_nodes > 1)) {
|
|
for_each_online_node(nid) {
|
|
if (nid == env.src_nid || nid == p->numa_preferred_nid)
|
|
continue;
|
|
|
|
dist = node_distance(env.src_nid, env.dst_nid);
|
|
if (sched_numa_topology_type == NUMA_BACKPLANE &&
|
|
dist != env.dist) {
|
|
taskweight = task_weight(p, env.src_nid, dist);
|
|
groupweight = group_weight(p, env.src_nid, dist);
|
|
}
|
|
|
|
/* Only consider nodes where both task and groups benefit */
|
|
taskimp = task_weight(p, nid, dist) - taskweight;
|
|
groupimp = group_weight(p, nid, dist) - groupweight;
|
|
if (taskimp < 0 && groupimp < 0)
|
|
continue;
|
|
|
|
env.dist = dist;
|
|
env.dst_nid = nid;
|
|
update_numa_stats(&env.dst_stats, env.dst_nid);
|
|
if (numa_has_capacity(&env))
|
|
task_numa_find_cpu(&env, taskimp, groupimp);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* If the task is part of a workload that spans multiple NUMA nodes,
|
|
* and is migrating into one of the workload's active nodes, remember
|
|
* this node as the task's preferred numa node, so the workload can
|
|
* settle down.
|
|
* A task that migrated to a second choice node will be better off
|
|
* trying for a better one later. Do not set the preferred node here.
|
|
*/
|
|
if (p->numa_group) {
|
|
struct numa_group *ng = p->numa_group;
|
|
|
|
if (env.best_cpu == -1)
|
|
nid = env.src_nid;
|
|
else
|
|
nid = env.dst_nid;
|
|
|
|
if (ng->active_nodes > 1 && numa_is_active_node(env.dst_nid, ng))
|
|
sched_setnuma(p, env.dst_nid);
|
|
}
|
|
|
|
/* No better CPU than the current one was found. */
|
|
if (env.best_cpu == -1)
|
|
return -EAGAIN;
|
|
|
|
/*
|
|
* Reset the scan period if the task is being rescheduled on an
|
|
* alternative node to recheck if the tasks is now properly placed.
|
|
*/
|
|
p->numa_scan_period = task_scan_min(p);
|
|
|
|
if (env.best_task == NULL) {
|
|
ret = migrate_task_to(p, env.best_cpu);
|
|
if (ret != 0)
|
|
trace_sched_stick_numa(p, env.src_cpu, env.best_cpu);
|
|
return ret;
|
|
}
|
|
|
|
ret = migrate_swap(p, env.best_task);
|
|
if (ret != 0)
|
|
trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task));
|
|
put_task_struct(env.best_task);
|
|
return ret;
|
|
}
|
|
|
|
/* Attempt to migrate a task to a CPU on the preferred node. */
|
|
static void numa_migrate_preferred(struct task_struct *p)
|
|
{
|
|
unsigned long interval = HZ;
|
|
|
|
/* This task has no NUMA fault statistics yet */
|
|
if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults))
|
|
return;
|
|
|
|
/* Periodically retry migrating the task to the preferred node */
|
|
interval = min(interval, msecs_to_jiffies(p->numa_scan_period) / 16);
|
|
p->numa_migrate_retry = jiffies + interval;
|
|
|
|
/* Success if task is already running on preferred CPU */
|
|
if (task_node(p) == p->numa_preferred_nid)
|
|
return;
|
|
|
|
/* Otherwise, try migrate to a CPU on the preferred node */
|
|
task_numa_migrate(p);
|
|
}
|
|
|
|
/*
|
|
* Find out how many nodes on the workload is actively running on. Do this by
|
|
* tracking the nodes from which NUMA hinting faults are triggered. This can
|
|
* be different from the set of nodes where the workload's memory is currently
|
|
* located.
|
|
*/
|
|
static void numa_group_count_active_nodes(struct numa_group *numa_group)
|
|
{
|
|
unsigned long faults, max_faults = 0;
|
|
int nid, active_nodes = 0;
|
|
|
|
for_each_online_node(nid) {
|
|
faults = group_faults_cpu(numa_group, nid);
|
|
if (faults > max_faults)
|
|
max_faults = faults;
|
|
}
|
|
|
|
for_each_online_node(nid) {
|
|
faults = group_faults_cpu(numa_group, nid);
|
|
if (faults * ACTIVE_NODE_FRACTION > max_faults)
|
|
active_nodes++;
|
|
}
|
|
|
|
numa_group->max_faults_cpu = max_faults;
|
|
numa_group->active_nodes = active_nodes;
|
|
}
|
|
|
|
/*
|
|
* When adapting the scan rate, the period is divided into NUMA_PERIOD_SLOTS
|
|
* increments. The more local the fault statistics are, the higher the scan
|
|
* period will be for the next scan window. If local/(local+remote) ratio is
|
|
* below NUMA_PERIOD_THRESHOLD (where range of ratio is 1..NUMA_PERIOD_SLOTS)
|
|
* the scan period will decrease. Aim for 70% local accesses.
|
|
*/
|
|
#define NUMA_PERIOD_SLOTS 10
|
|
#define NUMA_PERIOD_THRESHOLD 7
|
|
|
|
/*
|
|
* Increase the scan period (slow down scanning) if the majority of
|
|
* our memory is already on our local node, or if the majority of
|
|
* the page accesses are shared with other processes.
|
|
* Otherwise, decrease the scan period.
|
|
*/
|
|
static void update_task_scan_period(struct task_struct *p,
|
|
unsigned long shared, unsigned long private)
|
|
{
|
|
unsigned int period_slot;
|
|
int ratio;
|
|
int diff;
|
|
|
|
unsigned long remote = p->numa_faults_locality[0];
|
|
unsigned long local = p->numa_faults_locality[1];
|
|
|
|
/*
|
|
* If there were no record hinting faults then either the task is
|
|
* completely idle or all activity is areas that are not of interest
|
|
* to automatic numa balancing. Related to that, if there were failed
|
|
* migration then it implies we are migrating too quickly or the local
|
|
* node is overloaded. In either case, scan slower
|
|
*/
|
|
if (local + shared == 0 || p->numa_faults_locality[2]) {
|
|
p->numa_scan_period = min(p->numa_scan_period_max,
|
|
p->numa_scan_period << 1);
|
|
|
|
p->mm->numa_next_scan = jiffies +
|
|
msecs_to_jiffies(p->numa_scan_period);
|
|
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* Prepare to scale scan period relative to the current period.
|
|
* == NUMA_PERIOD_THRESHOLD scan period stays the same
|
|
* < NUMA_PERIOD_THRESHOLD scan period decreases (scan faster)
|
|
* >= NUMA_PERIOD_THRESHOLD scan period increases (scan slower)
|
|
*/
|
|
period_slot = DIV_ROUND_UP(p->numa_scan_period, NUMA_PERIOD_SLOTS);
|
|
ratio = (local * NUMA_PERIOD_SLOTS) / (local + remote);
|
|
if (ratio >= NUMA_PERIOD_THRESHOLD) {
|
|
int slot = ratio - NUMA_PERIOD_THRESHOLD;
|
|
if (!slot)
|
|
slot = 1;
|
|
diff = slot * period_slot;
|
|
} else {
|
|
diff = -(NUMA_PERIOD_THRESHOLD - ratio) * period_slot;
|
|
|
|
/*
|
|
* Scale scan rate increases based on sharing. There is an
|
|
* inverse relationship between the degree of sharing and
|
|
* the adjustment made to the scanning period. Broadly
|
|
* speaking the intent is that there is little point
|
|
* scanning faster if shared accesses dominate as it may
|
|
* simply bounce migrations uselessly
|
|
*/
|
|
ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared + 1));
|
|
diff = (diff * ratio) / NUMA_PERIOD_SLOTS;
|
|
}
|
|
|
|
p->numa_scan_period = clamp(p->numa_scan_period + diff,
|
|
task_scan_min(p), task_scan_max(p));
|
|
memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
|
|
}
|
|
|
|
/*
|
|
* Get the fraction of time the task has been running since the last
|
|
* NUMA placement cycle. The scheduler keeps similar statistics, but
|
|
* decays those on a 32ms period, which is orders of magnitude off
|
|
* from the dozens-of-seconds NUMA balancing period. Use the scheduler
|
|
* stats only if the task is so new there are no NUMA statistics yet.
|
|
*/
|
|
static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period)
|
|
{
|
|
u64 runtime, delta, now;
|
|
/* Use the start of this time slice to avoid calculations. */
|
|
now = p->se.exec_start;
|
|
runtime = p->se.sum_exec_runtime;
|
|
|
|
if (p->last_task_numa_placement) {
|
|
delta = runtime - p->last_sum_exec_runtime;
|
|
*period = now - p->last_task_numa_placement;
|
|
} else {
|
|
delta = p->se.avg.load_sum / p->se.load.weight;
|
|
*period = LOAD_AVG_MAX;
|
|
}
|
|
|
|
p->last_sum_exec_runtime = runtime;
|
|
p->last_task_numa_placement = now;
|
|
|
|
return delta;
|
|
}
|
|
|
|
/*
|
|
* Determine the preferred nid for a task in a numa_group. This needs to
|
|
* be done in a way that produces consistent results with group_weight,
|
|
* otherwise workloads might not converge.
|
|
*/
|
|
static int preferred_group_nid(struct task_struct *p, int nid)
|
|
{
|
|
nodemask_t nodes;
|
|
int dist;
|
|
|
|
/* Direct connections between all NUMA nodes. */
|
|
if (sched_numa_topology_type == NUMA_DIRECT)
|
|
return nid;
|
|
|
|
/*
|
|
* On a system with glueless mesh NUMA topology, group_weight
|
|
* scores nodes according to the number of NUMA hinting faults on
|
|
* both the node itself, and on nearby nodes.
|
|
*/
|
|
if (sched_numa_topology_type == NUMA_GLUELESS_MESH) {
|
|
unsigned long score, max_score = 0;
|
|
int node, max_node = nid;
|
|
|
|
dist = sched_max_numa_distance;
|
|
|
|
for_each_online_node(node) {
|
|
score = group_weight(p, node, dist);
|
|
if (score > max_score) {
|
|
max_score = score;
|
|
max_node = node;
|
|
}
|
|
}
|
|
return max_node;
|
|
}
|
|
|
|
/*
|
|
* Finding the preferred nid in a system with NUMA backplane
|
|
* interconnect topology is more involved. The goal is to locate
|
|
* tasks from numa_groups near each other in the system, and
|
|
* untangle workloads from different sides of the system. This requires
|
|
* searching down the hierarchy of node groups, recursively searching
|
|
* inside the highest scoring group of nodes. The nodemask tricks
|
|
* keep the complexity of the search down.
|
|
*/
|
|
nodes = node_online_map;
|
|
for (dist = sched_max_numa_distance; dist > LOCAL_DISTANCE; dist--) {
|
|
unsigned long max_faults = 0;
|
|
nodemask_t max_group = NODE_MASK_NONE;
|
|
int a, b;
|
|
|
|
/* Are there nodes at this distance from each other? */
|
|
if (!find_numa_distance(dist))
|
|
continue;
|
|
|
|
for_each_node_mask(a, nodes) {
|
|
unsigned long faults = 0;
|
|
nodemask_t this_group;
|
|
nodes_clear(this_group);
|
|
|
|
/* Sum group's NUMA faults; includes a==b case. */
|
|
for_each_node_mask(b, nodes) {
|
|
if (node_distance(a, b) < dist) {
|
|
faults += group_faults(p, b);
|
|
node_set(b, this_group);
|
|
node_clear(b, nodes);
|
|
}
|
|
}
|
|
|
|
/* Remember the top group. */
|
|
if (faults > max_faults) {
|
|
max_faults = faults;
|
|
max_group = this_group;
|
|
/*
|
|
* subtle: at the smallest distance there is
|
|
* just one node left in each "group", the
|
|
* winner is the preferred nid.
|
|
*/
|
|
nid = a;
|
|
}
|
|
}
|
|
/* Next round, evaluate the nodes within max_group. */
|
|
if (!max_faults)
|
|
break;
|
|
nodes = max_group;
|
|
}
|
|
return nid;
|
|
}
|
|
|
|
static void task_numa_placement(struct task_struct *p)
|
|
{
|
|
int seq, nid, max_nid = -1, max_group_nid = -1;
|
|
unsigned long max_faults = 0, max_group_faults = 0;
|
|
unsigned long fault_types[2] = { 0, 0 };
|
|
unsigned long total_faults;
|
|
u64 runtime, period;
|
|
spinlock_t *group_lock = NULL;
|
|
|
|
/*
|
|
* 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;
|
|
p->numa_scan_period_max = task_scan_max(p);
|
|
|
|
total_faults = p->numa_faults_locality[0] +
|
|
p->numa_faults_locality[1];
|
|
runtime = numa_get_avg_runtime(p, &period);
|
|
|
|
/* If the task is part of a group prevent parallel updates to group stats */
|
|
if (p->numa_group) {
|
|
group_lock = &p->numa_group->lock;
|
|
spin_lock_irq(group_lock);
|
|
}
|
|
|
|
/* Find the node with the highest number of faults */
|
|
for_each_online_node(nid) {
|
|
/* Keep track of the offsets in numa_faults array */
|
|
int mem_idx, membuf_idx, cpu_idx, cpubuf_idx;
|
|
unsigned long faults = 0, group_faults = 0;
|
|
int priv;
|
|
|
|
for (priv = 0; priv < NR_NUMA_HINT_FAULT_TYPES; priv++) {
|
|
long diff, f_diff, f_weight;
|
|
|
|
mem_idx = task_faults_idx(NUMA_MEM, nid, priv);
|
|
membuf_idx = task_faults_idx(NUMA_MEMBUF, nid, priv);
|
|
cpu_idx = task_faults_idx(NUMA_CPU, nid, priv);
|
|
cpubuf_idx = task_faults_idx(NUMA_CPUBUF, nid, priv);
|
|
|
|
/* Decay existing window, copy faults since last scan */
|
|
diff = p->numa_faults[membuf_idx] - p->numa_faults[mem_idx] / 2;
|
|
fault_types[priv] += p->numa_faults[membuf_idx];
|
|
p->numa_faults[membuf_idx] = 0;
|
|
|
|
/*
|
|
* Normalize the faults_from, so all tasks in a group
|
|
* count according to CPU use, instead of by the raw
|
|
* number of faults. Tasks with little runtime have
|
|
* little over-all impact on throughput, and thus their
|
|
* faults are less important.
|
|
*/
|
|
f_weight = div64_u64(runtime << 16, period + 1);
|
|
f_weight = (f_weight * p->numa_faults[cpubuf_idx]) /
|
|
(total_faults + 1);
|
|
f_diff = f_weight - p->numa_faults[cpu_idx] / 2;
|
|
p->numa_faults[cpubuf_idx] = 0;
|
|
|
|
p->numa_faults[mem_idx] += diff;
|
|
p->numa_faults[cpu_idx] += f_diff;
|
|
faults += p->numa_faults[mem_idx];
|
|
p->total_numa_faults += diff;
|
|
if (p->numa_group) {
|
|
/*
|
|
* safe because we can only change our own group
|
|
*
|
|
* mem_idx represents the offset for a given
|
|
* nid and priv in a specific region because it
|
|
* is at the beginning of the numa_faults array.
|
|
*/
|
|
p->numa_group->faults[mem_idx] += diff;
|
|
p->numa_group->faults_cpu[mem_idx] += f_diff;
|
|
p->numa_group->total_faults += diff;
|
|
group_faults += p->numa_group->faults[mem_idx];
|
|
}
|
|
}
|
|
|
|
if (faults > max_faults) {
|
|
max_faults = faults;
|
|
max_nid = nid;
|
|
}
|
|
|
|
if (group_faults > max_group_faults) {
|
|
max_group_faults = group_faults;
|
|
max_group_nid = nid;
|
|
}
|
|
}
|
|
|
|
update_task_scan_period(p, fault_types[0], fault_types[1]);
|
|
|
|
if (p->numa_group) {
|
|
numa_group_count_active_nodes(p->numa_group);
|
|
spin_unlock_irq(group_lock);
|
|
max_nid = preferred_group_nid(p, max_group_nid);
|
|
}
|
|
|
|
if (max_faults) {
|
|
/* Set the new preferred node */
|
|
if (max_nid != p->numa_preferred_nid)
|
|
sched_setnuma(p, max_nid);
|
|
|
|
if (task_node(p) != p->numa_preferred_nid)
|
|
numa_migrate_preferred(p);
|
|
}
|
|
}
|
|
|
|
static inline int get_numa_group(struct numa_group *grp)
|
|
{
|
|
return atomic_inc_not_zero(&grp->refcount);
|
|
}
|
|
|
|
static inline void put_numa_group(struct numa_group *grp)
|
|
{
|
|
if (atomic_dec_and_test(&grp->refcount))
|
|
kfree_rcu(grp, rcu);
|
|
}
|
|
|
|
static void task_numa_group(struct task_struct *p, int cpupid, int flags,
|
|
int *priv)
|
|
{
|
|
struct numa_group *grp, *my_grp;
|
|
struct task_struct *tsk;
|
|
bool join = false;
|
|
int cpu = cpupid_to_cpu(cpupid);
|
|
int i;
|
|
|
|
if (unlikely(!p->numa_group)) {
|
|
unsigned int size = sizeof(struct numa_group) +
|
|
4*nr_node_ids*sizeof(unsigned long);
|
|
|
|
grp = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
|
|
if (!grp)
|
|
return;
|
|
|
|
atomic_set(&grp->refcount, 1);
|
|
grp->active_nodes = 1;
|
|
grp->max_faults_cpu = 0;
|
|
spin_lock_init(&grp->lock);
|
|
grp->gid = p->pid;
|
|
/* Second half of the array tracks nids where faults happen */
|
|
grp->faults_cpu = grp->faults + NR_NUMA_HINT_FAULT_TYPES *
|
|
nr_node_ids;
|
|
|
|
for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
|
|
grp->faults[i] = p->numa_faults[i];
|
|
|
|
grp->total_faults = p->total_numa_faults;
|
|
|
|
grp->nr_tasks++;
|
|
rcu_assign_pointer(p->numa_group, grp);
|
|
}
|
|
|
|
rcu_read_lock();
|
|
tsk = READ_ONCE(cpu_rq(cpu)->curr);
|
|
|
|
if (!cpupid_match_pid(tsk, cpupid))
|
|
goto no_join;
|
|
|
|
grp = rcu_dereference(tsk->numa_group);
|
|
if (!grp)
|
|
goto no_join;
|
|
|
|
my_grp = p->numa_group;
|
|
if (grp == my_grp)
|
|
goto no_join;
|
|
|
|
/*
|
|
* Only join the other group if its bigger; if we're the bigger group,
|
|
* the other task will join us.
|
|
*/
|
|
if (my_grp->nr_tasks > grp->nr_tasks)
|
|
goto no_join;
|
|
|
|
/*
|
|
* Tie-break on the grp address.
|
|
*/
|
|
if (my_grp->nr_tasks == grp->nr_tasks && my_grp > grp)
|
|
goto no_join;
|
|
|
|
/* Always join threads in the same process. */
|
|
if (tsk->mm == current->mm)
|
|
join = true;
|
|
|
|
/* Simple filter to avoid false positives due to PID collisions */
|
|
if (flags & TNF_SHARED)
|
|
join = true;
|
|
|
|
/* Update priv based on whether false sharing was detected */
|
|
*priv = !join;
|
|
|
|
if (join && !get_numa_group(grp))
|
|
goto no_join;
|
|
|
|
rcu_read_unlock();
|
|
|
|
if (!join)
|
|
return;
|
|
|
|
BUG_ON(irqs_disabled());
|
|
double_lock_irq(&my_grp->lock, &grp->lock);
|
|
|
|
for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) {
|
|
my_grp->faults[i] -= p->numa_faults[i];
|
|
grp->faults[i] += p->numa_faults[i];
|
|
}
|
|
my_grp->total_faults -= p->total_numa_faults;
|
|
grp->total_faults += p->total_numa_faults;
|
|
|
|
my_grp->nr_tasks--;
|
|
grp->nr_tasks++;
|
|
|
|
spin_unlock(&my_grp->lock);
|
|
spin_unlock_irq(&grp->lock);
|
|
|
|
rcu_assign_pointer(p->numa_group, grp);
|
|
|
|
put_numa_group(my_grp);
|
|
return;
|
|
|
|
no_join:
|
|
rcu_read_unlock();
|
|
return;
|
|
}
|
|
|
|
void task_numa_free(struct task_struct *p)
|
|
{
|
|
struct numa_group *grp = p->numa_group;
|
|
void *numa_faults = p->numa_faults;
|
|
unsigned long flags;
|
|
int i;
|
|
|
|
if (grp) {
|
|
spin_lock_irqsave(&grp->lock, flags);
|
|
for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
|
|
grp->faults[i] -= p->numa_faults[i];
|
|
grp->total_faults -= p->total_numa_faults;
|
|
|
|
grp->nr_tasks--;
|
|
spin_unlock_irqrestore(&grp->lock, flags);
|
|
RCU_INIT_POINTER(p->numa_group, NULL);
|
|
put_numa_group(grp);
|
|
}
|
|
|
|
p->numa_faults = NULL;
|
|
kfree(numa_faults);
|
|
}
|
|
|
|
/*
|
|
* Got a PROT_NONE fault for a page on @node.
|
|
*/
|
|
void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
|
|
{
|
|
struct task_struct *p = current;
|
|
bool migrated = flags & TNF_MIGRATED;
|
|
int cpu_node = task_node(current);
|
|
int local = !!(flags & TNF_FAULT_LOCAL);
|
|
struct numa_group *ng;
|
|
int priv;
|
|
|
|
if (!static_branch_likely(&sched_numa_balancing))
|
|
return;
|
|
|
|
/* for example, ksmd faulting in a user's mm */
|
|
if (!p->mm)
|
|
return;
|
|
|
|
/* Allocate buffer to track faults on a per-node basis */
|
|
if (unlikely(!p->numa_faults)) {
|
|
int size = sizeof(*p->numa_faults) *
|
|
NR_NUMA_HINT_FAULT_BUCKETS * nr_node_ids;
|
|
|
|
p->numa_faults = kzalloc(size, GFP_KERNEL|__GFP_NOWARN);
|
|
if (!p->numa_faults)
|
|
return;
|
|
|
|
p->total_numa_faults = 0;
|
|
memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
|
|
}
|
|
|
|
/*
|
|
* First accesses are treated as private, otherwise consider accesses
|
|
* to be private if the accessing pid has not changed
|
|
*/
|
|
if (unlikely(last_cpupid == (-1 & LAST_CPUPID_MASK))) {
|
|
priv = 1;
|
|
} else {
|
|
priv = cpupid_match_pid(p, last_cpupid);
|
|
if (!priv && !(flags & TNF_NO_GROUP))
|
|
task_numa_group(p, last_cpupid, flags, &priv);
|
|
}
|
|
|
|
/*
|
|
* If a workload spans multiple NUMA nodes, a shared fault that
|
|
* occurs wholly within the set of nodes that the workload is
|
|
* actively using should be counted as local. This allows the
|
|
* scan rate to slow down when a workload has settled down.
|
|
*/
|
|
ng = p->numa_group;
|
|
if (!priv && !local && ng && ng->active_nodes > 1 &&
|
|
numa_is_active_node(cpu_node, ng) &&
|
|
numa_is_active_node(mem_node, ng))
|
|
local = 1;
|
|
|
|
task_numa_placement(p);
|
|
|
|
/*
|
|
* Retry task to preferred node migration periodically, in case it
|
|
* case it previously failed, or the scheduler moved us.
|
|
*/
|
|
if (time_after(jiffies, p->numa_migrate_retry))
|
|
numa_migrate_preferred(p);
|
|
|
|
if (migrated)
|
|
p->numa_pages_migrated += pages;
|
|
if (flags & TNF_MIGRATE_FAIL)
|
|
p->numa_faults_locality[2] += pages;
|
|
|
|
p->numa_faults[task_faults_idx(NUMA_MEMBUF, mem_node, priv)] += pages;
|
|
p->numa_faults[task_faults_idx(NUMA_CPUBUF, cpu_node, priv)] += pages;
|
|
p->numa_faults_locality[local] += pages;
|
|
}
|
|
|
|
static void reset_ptenuma_scan(struct task_struct *p)
|
|
{
|
|
/*
|
|
* 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;
|
|
}
|
|
|
|
/*
|
|
* The expensive part of numa migration is done from task_work context.
|
|
* Triggered from task_tick_numa().
|
|
*/
|
|
void task_numa_work(struct callback_head *work)
|
|
{
|
|
unsigned long migrate, next_scan, now = jiffies;
|
|
struct task_struct *p = current;
|
|
struct mm_struct *mm = p->mm;
|
|
u64 runtime = p->se.sum_exec_runtime;
|
|
struct vm_area_struct *vma;
|
|
unsigned long start, end;
|
|
unsigned long nr_pte_updates = 0;
|
|
long pages, virtpages;
|
|
|
|
SCHED_WARN_ON(p != container_of(work, struct task_struct, numa_work));
|
|
|
|
work->next = work; /* protect against double add */
|
|
/*
|
|
* Who cares about NUMA placement when they're dying.
|
|
*
|
|
* NOTE: make sure not to dereference p->mm before this check,
|
|
* exit_task_work() happens _after_ exit_mm() so we could be called
|
|
* without p->mm even though we still had it when we enqueued this
|
|
* work.
|
|
*/
|
|
if (p->flags & PF_EXITING)
|
|
return;
|
|
|
|
if (!mm->numa_next_scan) {
|
|
mm->numa_next_scan = now +
|
|
msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
|
|
}
|
|
|
|
/*
|
|
* Enforce maximal scan/migration frequency..
|
|
*/
|
|
migrate = mm->numa_next_scan;
|
|
if (time_before(now, migrate))
|
|
return;
|
|
|
|
if (p->numa_scan_period == 0) {
|
|
p->numa_scan_period_max = task_scan_max(p);
|
|
p->numa_scan_period = task_scan_min(p);
|
|
}
|
|
|
|
next_scan = now + msecs_to_jiffies(p->numa_scan_period);
|
|
if (cmpxchg(&mm->numa_next_scan, migrate, next_scan) != migrate)
|
|
return;
|
|
|
|
/*
|
|
* Delay this task enough that another task of this mm will likely win
|
|
* the next time around.
|
|
*/
|
|
p->node_stamp += 2 * TICK_NSEC;
|
|
|
|
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;
|
|
|
|
|
|
if (!down_read_trylock(&mm->mmap_sem))
|
|
return;
|
|
vma = find_vma(mm, start);
|
|
if (!vma) {
|
|
reset_ptenuma_scan(p);
|
|
start = 0;
|
|
vma = mm->mmap;
|
|
}
|
|
for (; vma; vma = vma->vm_next) {
|
|
if (!vma_migratable(vma) || !vma_policy_mof(vma) ||
|
|
is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_MIXEDMAP)) {
|
|
continue;
|
|
}
|
|
|
|
/*
|
|
* Shared library pages mapped by multiple processes are not
|
|
* migrated as it is expected they are cache replicated. Avoid
|
|
* hinting faults in read-only file-backed mappings or the vdso
|
|
* as migrating the pages will be of marginal benefit.
|
|
*/
|
|
if (!vma->vm_mm ||
|
|
(vma->vm_file && (vma->vm_flags & (VM_READ|VM_WRITE)) == (VM_READ)))
|
|
continue;
|
|
|
|
/*
|
|
* Skip inaccessible VMAs to avoid any confusion between
|
|
* PROT_NONE and NUMA hinting ptes
|
|
*/
|
|
if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
|
|
continue;
|
|
|
|
do {
|
|
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);
|
|
|
|
/*
|
|
* 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 || virtpages <= 0)
|
|
goto out;
|
|
|
|
cond_resched();
|
|
} while (end != vma->vm_end);
|
|
}
|
|
|
|
out:
|
|
/*
|
|
* It is possible to reach the end of the VMA list but the last few
|
|
* VMAs are not guaranteed to the vma_migratable. If they are not, we
|
|
* would find the !migratable VMA on the next scan but not reset the
|
|
* scanner to the start so check it now.
|
|
*/
|
|
if (vma)
|
|
mm->numa_scan_offset = start;
|
|
else
|
|
reset_ptenuma_scan(p);
|
|
up_read(&mm->mmap_sem);
|
|
|
|
/*
|
|
* Make sure tasks use at least 32x as much time to run other code
|
|
* than they used here, to limit NUMA PTE scanning overhead to 3% max.
|
|
* Usually update_task_scan_period slows down scanning enough; on an
|
|
* overloaded system we need to limit overhead on a per task basis.
|
|
*/
|
|
if (unlikely(p->se.sum_exec_runtime != runtime)) {
|
|
u64 diff = p->se.sum_exec_runtime - runtime;
|
|
p->node_stamp += 32 * diff;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Drive the periodic memory faults..
|
|
*/
|
|
void task_tick_numa(struct rq *rq, struct task_struct *curr)
|
|
{
|
|
struct callback_head *work = &curr->numa_work;
|
|
u64 period, now;
|
|
|
|
/*
|
|
* We don't care about NUMA placement if we don't have memory.
|
|
*/
|
|
if (!curr->mm || (curr->flags & PF_EXITING) || work->next != work)
|
|
return;
|
|
|
|
/*
|
|
* Using runtime rather than walltime has the dual advantage that
|
|
* we (mostly) drive the selection from busy threads and that the
|
|
* task needs to have done some actual work before we bother with
|
|
* NUMA placement.
|
|
*/
|
|
now = curr->se.sum_exec_runtime;
|
|
period = (u64)curr->numa_scan_period * NSEC_PER_MSEC;
|
|
|
|
if (now > curr->node_stamp + period) {
|
|
if (!curr->node_stamp)
|
|
curr->numa_scan_period = task_scan_min(curr);
|
|
curr->node_stamp += period;
|
|
|
|
if (!time_before(jiffies, curr->mm->numa_next_scan)) {
|
|
init_task_work(work, task_numa_work); /* TODO: move this into sched_fork() */
|
|
task_work_add(curr, work, true);
|
|
}
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Can a task be moved from prev_cpu to this_cpu without causing a load
|
|
* imbalance that would trigger the load balancer?
|
|
*/
|
|
static inline bool numa_wake_affine(struct sched_domain *sd,
|
|
struct task_struct *p, int this_cpu,
|
|
int prev_cpu, int sync)
|
|
{
|
|
struct numa_stats prev_load, this_load;
|
|
s64 this_eff_load, prev_eff_load;
|
|
|
|
update_numa_stats(&prev_load, cpu_to_node(prev_cpu));
|
|
update_numa_stats(&this_load, cpu_to_node(this_cpu));
|
|
|
|
/*
|
|
* If sync wakeup then subtract the (maximum possible)
|
|
* effect of the currently running task from the load
|
|
* of the current CPU:
|
|
*/
|
|
if (sync) {
|
|
unsigned long current_load = task_h_load(current);
|
|
|
|
if (this_load.load > current_load)
|
|
this_load.load -= current_load;
|
|
else
|
|
this_load.load = 0;
|
|
}
|
|
|
|
/*
|
|
* In low-load situations, where this_cpu's node is idle due to the
|
|
* sync cause above having dropped this_load.load to 0, move the task.
|
|
* Moving to an idle socket will not create a bad imbalance.
|
|
*
|
|
* Otherwise check if the nodes are near enough in load to allow this
|
|
* task to be woken on this_cpu's node.
|
|
*/
|
|
if (this_load.load > 0) {
|
|
unsigned long task_load = task_h_load(p);
|
|
|
|
this_eff_load = 100;
|
|
this_eff_load *= prev_load.compute_capacity;
|
|
|
|
prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2;
|
|
prev_eff_load *= this_load.compute_capacity;
|
|
|
|
this_eff_load *= this_load.load + task_load;
|
|
prev_eff_load *= prev_load.load - task_load;
|
|
|
|
return this_eff_load <= prev_eff_load;
|
|
}
|
|
|
|
return true;
|
|
}
|
|
#else
|
|
static void task_tick_numa(struct rq *rq, struct task_struct *curr)
|
|
{
|
|
}
|
|
|
|
static inline void account_numa_enqueue(struct rq *rq, struct task_struct *p)
|
|
{
|
|
}
|
|
|
|
static inline void account_numa_dequeue(struct rq *rq, struct task_struct *p)
|
|
{
|
|
}
|
|
|
|
#ifdef CONFIG_SMP
|
|
static inline bool numa_wake_affine(struct sched_domain *sd,
|
|
struct task_struct *p, int this_cpu,
|
|
int prev_cpu, int sync)
|
|
{
|
|
return true;
|
|
}
|
|
#endif /* !SMP */
|
|
#endif /* CONFIG_NUMA_BALANCING */
|
|
|
|
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);
|
|
|
|
account_numa_enqueue(rq, task_of(se));
|
|
list_add(&se->group_node, &rq->cfs_tasks);
|
|
}
|
|
#endif
|
|
cfs_rq->nr_running++;
|
|
}
|
|
|
|
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));
|
|
list_del_init(&se->group_node);
|
|
}
|
|
#endif
|
|
cfs_rq->nr_running--;
|
|
}
|
|
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
# ifdef CONFIG_SMP
|
|
static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
|
|
{
|
|
long tg_weight, load, shares;
|
|
|
|
/*
|
|
* This really should be: cfs_rq->avg.load_avg, but instead we use
|
|
* cfs_rq->load.weight, which is its upper bound. This helps ramp up
|
|
* the shares for small weight interactive tasks.
|
|
*/
|
|
load = scale_load_down(cfs_rq->load.weight);
|
|
|
|
tg_weight = atomic_long_read(&tg->load_avg);
|
|
|
|
/* Ensure tg_weight >= load */
|
|
tg_weight -= cfs_rq->tg_load_avg_contrib;
|
|
tg_weight += load;
|
|
|
|
shares = (tg->shares * load);
|
|
if (tg_weight)
|
|
shares /= tg_weight;
|
|
|
|
/*
|
|
* MIN_SHARES has to be unscaled here to support per-CPU partitioning
|
|
* of a group with small tg->shares value. It is a floor value which is
|
|
* assigned as a minimum load.weight to the sched_entity representing
|
|
* the group on a CPU.
|
|
*
|
|
* E.g. on 64-bit for a group with tg->shares of scale_load(15)=15*1024
|
|
* on an 8-core system with 8 tasks each runnable on one CPU shares has
|
|
* to be 15*1024*1/8=1920 instead of scale_load(MIN_SHARES)=2*1024. In
|
|
* case no task is runnable on a CPU MIN_SHARES=2 should be returned
|
|
* instead of 0.
|
|
*/
|
|
if (shares < MIN_SHARES)
|
|
shares = MIN_SHARES;
|
|
if (shares > tg->shares)
|
|
shares = tg->shares;
|
|
|
|
return shares;
|
|
}
|
|
# else /* CONFIG_SMP */
|
|
static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
|
|
{
|
|
return tg->shares;
|
|
}
|
|
# endif /* CONFIG_SMP */
|
|
|
|
static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
|
|
unsigned long weight)
|
|
{
|
|
if (se->on_rq) {
|
|
/* commit outstanding execution time */
|
|
if (cfs_rq->curr == se)
|
|
update_curr(cfs_rq);
|
|
account_entity_dequeue(cfs_rq, se);
|
|
}
|
|
|
|
update_load_set(&se->load, weight);
|
|
|
|
if (se->on_rq)
|
|
account_entity_enqueue(cfs_rq, se);
|
|
}
|
|
|
|
static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
|
|
|
|
static void update_cfs_shares(struct sched_entity *se)
|
|
{
|
|
struct cfs_rq *cfs_rq = group_cfs_rq(se);
|
|
struct task_group *tg;
|
|
long shares;
|
|
|
|
if (!cfs_rq)
|
|
return;
|
|
|
|
if (throttled_hierarchy(cfs_rq))
|
|
return;
|
|
|
|
tg = cfs_rq->tg;
|
|
|
|
#ifndef CONFIG_SMP
|
|
if (likely(se->load.weight == tg->shares))
|
|
return;
|
|
#endif
|
|
shares = calc_cfs_shares(cfs_rq, tg);
|
|
|
|
reweight_entity(cfs_rq_of(se), se, shares);
|
|
}
|
|
|
|
#else /* CONFIG_FAIR_GROUP_SCHED */
|
|
static inline void update_cfs_shares(struct sched_entity *se)
|
|
{
|
|
}
|
|
#endif /* CONFIG_FAIR_GROUP_SCHED */
|
|
|
|
#ifdef CONFIG_SMP
|
|
/*
|
|
* Approximate:
|
|
* val * y^n, where y^32 ~= 0.5 (~1 scheduling period)
|
|
*/
|
|
static u64 decay_load(u64 val, u64 n)
|
|
{
|
|
unsigned int local_n;
|
|
|
|
if (unlikely(n > LOAD_AVG_PERIOD * 63))
|
|
return 0;
|
|
|
|
/* after bounds checking we can collapse to 32-bit */
|
|
local_n = n;
|
|
|
|
/*
|
|
* As y^PERIOD = 1/2, we can combine
|
|
* y^n = 1/2^(n/PERIOD) * y^(n%PERIOD)
|
|
* With a look-up table which covers y^n (n<PERIOD)
|
|
*
|
|
* To achieve constant time decay_load.
|
|
*/
|
|
if (unlikely(local_n >= LOAD_AVG_PERIOD)) {
|
|
val >>= local_n / LOAD_AVG_PERIOD;
|
|
local_n %= LOAD_AVG_PERIOD;
|
|
}
|
|
|
|
val = mul_u64_u32_shr(val, runnable_avg_yN_inv[local_n], 32);
|
|
return val;
|
|
}
|
|
|
|
static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3)
|
|
{
|
|
u32 c1, c2, c3 = d3; /* y^0 == 1 */
|
|
|
|
/*
|
|
* c1 = d1 y^p
|
|
*/
|
|
c1 = decay_load((u64)d1, periods);
|
|
|
|
/*
|
|
* p-1
|
|
* c2 = 1024 \Sum y^n
|
|
* n=1
|
|
*
|
|
* inf inf
|
|
* = 1024 ( \Sum y^n - \Sum y^n - y^0 )
|
|
* n=0 n=p
|
|
*/
|
|
c2 = LOAD_AVG_MAX - decay_load(LOAD_AVG_MAX, periods) - 1024;
|
|
|
|
return c1 + c2 + c3;
|
|
}
|
|
|
|
#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
|
|
|
|
/*
|
|
* Accumulate the three separate parts of the sum; d1 the remainder
|
|
* of the last (incomplete) period, d2 the span of full periods and d3
|
|
* the remainder of the (incomplete) current period.
|
|
*
|
|
* d1 d2 d3
|
|
* ^ ^ ^
|
|
* | | |
|
|
* |<->|<----------------->|<--->|
|
|
* ... |---x---|------| ... |------|-----x (now)
|
|
*
|
|
* p-1
|
|
* u' = (u + d1) y^p + 1024 \Sum y^n + d3 y^0
|
|
* n=1
|
|
*
|
|
* = u y^p + (Step 1)
|
|
*
|
|
* p-1
|
|
* d1 y^p + 1024 \Sum y^n + d3 y^0 (Step 2)
|
|
* n=1
|
|
*/
|
|
static __always_inline u32
|
|
accumulate_sum(u64 delta, int cpu, struct sched_avg *sa,
|
|
unsigned long weight, int running, struct cfs_rq *cfs_rq)
|
|
{
|
|
unsigned long scale_freq, scale_cpu;
|
|
u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */
|
|
u64 periods;
|
|
|
|
scale_freq = arch_scale_freq_capacity(NULL, cpu);
|
|
scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
|
|
|
|
delta += sa->period_contrib;
|
|
periods = delta / 1024; /* A period is 1024us (~1ms) */
|
|
|
|
/*
|
|
* Step 1: decay old *_sum if we crossed period boundaries.
|
|
*/
|
|
if (periods) {
|
|
sa->load_sum = decay_load(sa->load_sum, periods);
|
|
if (cfs_rq) {
|
|
cfs_rq->runnable_load_sum =
|
|
decay_load(cfs_rq->runnable_load_sum, periods);
|
|
}
|
|
sa->util_sum = decay_load((u64)(sa->util_sum), periods);
|
|
|
|
/*
|
|
* Step 2
|
|
*/
|
|
delta %= 1024;
|
|
contrib = __accumulate_pelt_segments(periods,
|
|
1024 - sa->period_contrib, delta);
|
|
}
|
|
sa->period_contrib = delta;
|
|
|
|
contrib = cap_scale(contrib, scale_freq);
|
|
if (weight) {
|
|
sa->load_sum += weight * contrib;
|
|
if (cfs_rq)
|
|
cfs_rq->runnable_load_sum += weight * contrib;
|
|
}
|
|
if (running)
|
|
sa->util_sum += contrib * scale_cpu;
|
|
|
|
return periods;
|
|
}
|
|
|
|
/*
|
|
* We can represent the historical contribution to runnable average as the
|
|
* coefficients of a geometric series. To do this we sub-divide our runnable
|
|
* history into segments of approximately 1ms (1024us); label the segment that
|
|
* occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g.
|
|
*
|
|
* [<- 1024us ->|<- 1024us ->|<- 1024us ->| ...
|
|
* p0 p1 p2
|
|
* (now) (~1ms ago) (~2ms ago)
|
|
*
|
|
* Let u_i denote the fraction of p_i that the entity was runnable.
|
|
*
|
|
* We then designate the fractions u_i as our co-efficients, yielding the
|
|
* following representation of historical load:
|
|
* u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ...
|
|
*
|
|
* We choose y based on the with of a reasonably scheduling period, fixing:
|
|
* y^32 = 0.5
|
|
*
|
|
* This means that the contribution to load ~32ms ago (u_32) will be weighted
|
|
* approximately half as much as the contribution to load within the last ms
|
|
* (u_0).
|
|
*
|
|
* When a period "rolls over" and we have new u_0`, multiplying the previous
|
|
* sum again by y is sufficient to update:
|
|
* 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_load_avg(u64 now, int cpu, struct sched_avg *sa,
|
|
unsigned long weight, int running, struct cfs_rq *cfs_rq)
|
|
{
|
|
u64 delta;
|
|
|
|
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_update_time = now;
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Use 1024ns as the unit of measurement since it's a reasonable
|
|
* approximation of 1us and fast to compute.
|
|
*/
|
|
delta >>= 10;
|
|
if (!delta)
|
|
return 0;
|
|
|
|
sa->last_update_time += delta << 10;
|
|
|
|
/*
|
|
* Now we know we crossed measurement unit boundaries. The *_avg
|
|
* accrues by two steps:
|
|
*
|
|
* Step 1: accumulate *_sum since last_update_time. If we haven't
|
|
* crossed period boundaries, finish.
|
|
*/
|
|
if (!accumulate_sum(delta, cpu, sa, weight, running, cfs_rq))
|
|
return 0;
|
|
|
|
/*
|
|
* Step 2: update *_avg.
|
|
*/
|
|
sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX - 1024 + sa->period_contrib);
|
|
if (cfs_rq) {
|
|
cfs_rq->runnable_load_avg =
|
|
div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX - 1024 + sa->period_contrib);
|
|
}
|
|
sa->util_avg = sa->util_sum / (LOAD_AVG_MAX - 1024 + sa->period_contrib);
|
|
|
|
return 1;
|
|
}
|
|
|
|
static int
|
|
__update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se)
|
|
{
|
|
return ___update_load_avg(now, cpu, &se->avg, 0, 0, NULL);
|
|
}
|
|
|
|
static int
|
|
__update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|
{
|
|
return ___update_load_avg(now, cpu, &se->avg,
|
|
se->on_rq * scale_load_down(se->load.weight),
|
|
cfs_rq->curr == se, NULL);
|
|
}
|
|
|
|
static int
|
|
__update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq)
|
|
{
|
|
return ___update_load_avg(now, cpu, &cfs_rq->avg,
|
|
scale_load_down(cfs_rq->load.weight),
|
|
cfs_rq->curr != NULL, cfs_rq);
|
|
}
|
|
|
|
/*
|
|
* Signed add and clamp on underflow.
|
|
*
|
|
* Explicitly do a load-store to ensure the intermediate value never hits
|
|
* memory. This allows lockless observations without ever seeing the negative
|
|
* values.
|
|
*/
|
|
#define add_positive(_ptr, _val) do { \
|
|
typeof(_ptr) ptr = (_ptr); \
|
|
typeof(_val) val = (_val); \
|
|
typeof(*ptr) res, var = READ_ONCE(*ptr); \
|
|
\
|
|
res = var + val; \
|
|
\
|
|
if (val < 0 && res > var) \
|
|
res = 0; \
|
|
\
|
|
WRITE_ONCE(*ptr, res); \
|
|
} while (0)
|
|
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
/**
|
|
* update_tg_load_avg - update the tg's load avg
|
|
* @cfs_rq: the cfs_rq whose avg changed
|
|
* @force: update regardless of how small the difference
|
|
*
|
|
* This function 'ensures': tg->load_avg := \Sum tg->cfs_rq[]->avg.load.
|
|
* However, because tg->load_avg is a global value there are performance
|
|
* considerations.
|
|
*
|
|
* In order to avoid having to look at the other cfs_rq's, we use a
|
|
* differential update where we store the last value we propagated. This in
|
|
* turn allows skipping updates if the differential is 'small'.
|
|
*
|
|
* Updating tg's load_avg is necessary before update_cfs_share().
|
|
*/
|
|
static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
|
|
{
|
|
long delta = cfs_rq->avg.load_avg - cfs_rq->tg_load_avg_contrib;
|
|
|
|
/*
|
|
* No need to update load_avg for root_task_group as it is not used.
|
|
*/
|
|
if (cfs_rq->tg == &root_task_group)
|
|
return;
|
|
|
|
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;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Called within set_task_rq() right before setting a task's cpu. The
|
|
* caller only guarantees p->pi_lock is held; no other assumptions,
|
|
* including the state of rq->lock, should be made.
|
|
*/
|
|
void set_task_rq_fair(struct sched_entity *se,
|
|
struct cfs_rq *prev, struct cfs_rq *next)
|
|
{
|
|
u64 p_last_update_time;
|
|
u64 n_last_update_time;
|
|
|
|
if (!sched_feat(ATTACH_AGE_LOAD))
|
|
return;
|
|
|
|
/*
|
|
* 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.last_update_time && prev))
|
|
return;
|
|
|
|
#ifndef CONFIG_64BIT
|
|
{
|
|
u64 p_last_update_time_copy;
|
|
u64 n_last_update_time_copy;
|
|
|
|
do {
|
|
p_last_update_time_copy = prev->load_last_update_time_copy;
|
|
n_last_update_time_copy = next->load_last_update_time_copy;
|
|
|
|
smp_rmb();
|
|
|
|
p_last_update_time = prev->avg.last_update_time;
|
|
n_last_update_time = next->avg.last_update_time;
|
|
|
|
} while (p_last_update_time != p_last_update_time_copy ||
|
|
n_last_update_time != n_last_update_time_copy);
|
|
}
|
|
#else
|
|
p_last_update_time = prev->avg.last_update_time;
|
|
n_last_update_time = next->avg.last_update_time;
|
|
#endif
|
|
__update_load_avg_blocked_se(p_last_update_time, cpu_of(rq_of(prev)), se);
|
|
se->avg.last_update_time = n_last_update_time;
|
|
}
|
|
|
|
/* Take into account change of utilization of a child task group */
|
|
static inline void
|
|
update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|
{
|
|
struct cfs_rq *gcfs_rq = group_cfs_rq(se);
|
|
long delta = gcfs_rq->avg.util_avg - se->avg.util_avg;
|
|
|
|
/* Nothing to update */
|
|
if (!delta)
|
|
return;
|
|
|
|
/* Set new sched_entity's utilization */
|
|
se->avg.util_avg = gcfs_rq->avg.util_avg;
|
|
se->avg.util_sum = se->avg.util_avg * LOAD_AVG_MAX;
|
|
|
|
/* Update parent cfs_rq utilization */
|
|
add_positive(&cfs_rq->avg.util_avg, delta);
|
|
cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * LOAD_AVG_MAX;
|
|
}
|
|
|
|
/* Take into account change of load of a child task group */
|
|
static inline void
|
|
update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|
{
|
|
struct cfs_rq *gcfs_rq = group_cfs_rq(se);
|
|
long delta, load = gcfs_rq->avg.load_avg;
|
|
|
|
/*
|
|
* If the load of group cfs_rq is null, the load of the
|
|
* sched_entity will also be null so we can skip the formula
|
|
*/
|
|
if (load) {
|
|
long tg_load;
|
|
|
|
/* Get tg's load and ensure tg_load > 0 */
|
|
tg_load = atomic_long_read(&gcfs_rq->tg->load_avg) + 1;
|
|
|
|
/* Ensure tg_load >= load and updated with current load*/
|
|
tg_load -= gcfs_rq->tg_load_avg_contrib;
|
|
tg_load += load;
|
|
|
|
/*
|
|
* We need to compute a correction term in the case that the
|
|
* task group is consuming more CPU than a task of equal
|
|
* weight. A task with a weight equals to tg->shares will have
|
|
* a load less or equal to scale_load_down(tg->shares).
|
|
* Similarly, the sched_entities that represent the task group
|
|
* at parent level, can't have a load higher than
|
|
* scale_load_down(tg->shares). And the Sum of sched_entities'
|
|
* load must be <= scale_load_down(tg->shares).
|
|
*/
|
|
if (tg_load > scale_load_down(gcfs_rq->tg->shares)) {
|
|
/* scale gcfs_rq's load into tg's shares*/
|
|
load *= scale_load_down(gcfs_rq->tg->shares);
|
|
load /= tg_load;
|
|
}
|
|
}
|
|
|
|
delta = load - se->avg.load_avg;
|
|
|
|
/* Nothing to update */
|
|
if (!delta)
|
|
return;
|
|
|
|
/* Set new sched_entity's load */
|
|
se->avg.load_avg = load;
|
|
se->avg.load_sum = se->avg.load_avg * LOAD_AVG_MAX;
|
|
|
|
/* Update parent cfs_rq load */
|
|
add_positive(&cfs_rq->avg.load_avg, delta);
|
|
cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * LOAD_AVG_MAX;
|
|
|
|
/*
|
|
* If the sched_entity is already enqueued, we also have to update the
|
|
* runnable load avg.
|
|
*/
|
|
if (se->on_rq) {
|
|
/* Update parent cfs_rq runnable_load_avg */
|
|
add_positive(&cfs_rq->runnable_load_avg, delta);
|
|
cfs_rq->runnable_load_sum = cfs_rq->runnable_load_avg * LOAD_AVG_MAX;
|
|
}
|
|
}
|
|
|
|
static inline void set_tg_cfs_propagate(struct cfs_rq *cfs_rq)
|
|
{
|
|
cfs_rq->propagate_avg = 1;
|
|
}
|
|
|
|
static inline int test_and_clear_tg_cfs_propagate(struct sched_entity *se)
|
|
{
|
|
struct cfs_rq *cfs_rq = group_cfs_rq(se);
|
|
|
|
if (!cfs_rq->propagate_avg)
|
|
return 0;
|
|
|
|
cfs_rq->propagate_avg = 0;
|
|
return 1;
|
|
}
|
|
|
|
/* Update task and its cfs_rq load average */
|
|
static inline int propagate_entity_load_avg(struct sched_entity *se)
|
|
{
|
|
struct cfs_rq *cfs_rq;
|
|
|
|
if (entity_is_task(se))
|
|
return 0;
|
|
|
|
if (!test_and_clear_tg_cfs_propagate(se))
|
|
return 0;
|
|
|
|
cfs_rq = cfs_rq_of(se);
|
|
|
|
set_tg_cfs_propagate(cfs_rq);
|
|
|
|
update_tg_cfs_util(cfs_rq, se);
|
|
update_tg_cfs_load(cfs_rq, se);
|
|
|
|
return 1;
|
|
}
|
|
|
|
/*
|
|
* Check if we need to update the load and the utilization of a blocked
|
|
* group_entity:
|
|
*/
|
|
static inline bool skip_blocked_update(struct sched_entity *se)
|
|
{
|
|
struct cfs_rq *gcfs_rq = group_cfs_rq(se);
|
|
|
|
/*
|
|
* If sched_entity still have not zero load or utilization, we have to
|
|
* decay it:
|
|
*/
|
|
if (se->avg.load_avg || se->avg.util_avg)
|
|
return false;
|
|
|
|
/*
|
|
* If there is a pending propagation, we have to update the load and
|
|
* the utilization of the sched_entity:
|
|
*/
|
|
if (gcfs_rq->propagate_avg)
|
|
return false;
|
|
|
|
/*
|
|
* Otherwise, the load and the utilization of the sched_entity is
|
|
* already zero and there is no pending propagation, so it will be a
|
|
* waste of time to try to decay it:
|
|
*/
|
|
return true;
|
|
}
|
|
|
|
#else /* CONFIG_FAIR_GROUP_SCHED */
|
|
|
|
static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
|
|
|
|
static inline int propagate_entity_load_avg(struct sched_entity *se)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void set_tg_cfs_propagate(struct cfs_rq *cfs_rq) {}
|
|
|
|
#endif /* CONFIG_FAIR_GROUP_SCHED */
|
|
|
|
static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
|
|
{
|
|
if (&this_rq()->cfs == cfs_rq) {
|
|
/*
|
|
* There are a few boundary cases this might miss but it should
|
|
* get called often enough that that should (hopefully) not be
|
|
* a real problem -- added to that it only calls on the local
|
|
* CPU, so if we enqueue remotely we'll miss an update, but
|
|
* the next tick/schedule should update.
|
|
*
|
|
* It will not get called when we go idle, because the idle
|
|
* thread is a different class (!fair), nor will the utilization
|
|
* number include things like RT tasks.
|
|
*
|
|
* As is, the util number is not freq-invariant (we'd have to
|
|
* implement arch_scale_freq_capacity() for that).
|
|
*
|
|
* See cpu_util().
|
|
*/
|
|
cpufreq_update_util(rq_of(cfs_rq), 0);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Unsigned subtract and clamp on underflow.
|
|
*
|
|
* Explicitly do a load-store to ensure the intermediate value never hits
|
|
* memory. This allows lockless observations without ever seeing the negative
|
|
* values.
|
|
*/
|
|
#define sub_positive(_ptr, _val) do { \
|
|
typeof(_ptr) ptr = (_ptr); \
|
|
typeof(*ptr) val = (_val); \
|
|
typeof(*ptr) res, var = READ_ONCE(*ptr); \
|
|
res = var - val; \
|
|
if (res > var) \
|
|
res = 0; \
|
|
WRITE_ONCE(*ptr, res); \
|
|
} while (0)
|
|
|
|
/**
|
|
* update_cfs_rq_load_avg - update the cfs_rq's load/util averages
|
|
* @now: current time, as per cfs_rq_clock_task()
|
|
* @cfs_rq: cfs_rq to update
|
|
* @update_freq: should we call cfs_rq_util_change() or will the call do so
|
|
*
|
|
* The cfs_rq avg is the direct sum of all its entities (blocked and runnable)
|
|
* avg. The immediate corollary is that all (fair) tasks must be attached, see
|
|
* post_init_entity_util_avg().
|
|
*
|
|
* cfs_rq->avg is used for task_h_load() and update_cfs_share() for example.
|
|
*
|
|
* Returns true if the load decayed or we removed load.
|
|
*
|
|
* Since both these conditions indicate a changed cfs_rq->avg.load we should
|
|
* call update_tg_load_avg() when this function returns true.
|
|
*/
|
|
static inline int
|
|
update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
|
|
{
|
|
struct sched_avg *sa = &cfs_rq->avg;
|
|
int decayed, removed_load = 0, removed_util = 0;
|
|
|
|
if (atomic_long_read(&cfs_rq->removed_load_avg)) {
|
|
s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
|
|
sub_positive(&sa->load_avg, r);
|
|
sub_positive(&sa->load_sum, r * LOAD_AVG_MAX);
|
|
removed_load = 1;
|
|
set_tg_cfs_propagate(cfs_rq);
|
|
}
|
|
|
|
if (atomic_long_read(&cfs_rq->removed_util_avg)) {
|
|
long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0);
|
|
sub_positive(&sa->util_avg, r);
|
|
sub_positive(&sa->util_sum, r * LOAD_AVG_MAX);
|
|
removed_util = 1;
|
|
set_tg_cfs_propagate(cfs_rq);
|
|
}
|
|
|
|
decayed = __update_load_avg_cfs_rq(now, cpu_of(rq_of(cfs_rq)), cfs_rq);
|
|
|
|
#ifndef CONFIG_64BIT
|
|
smp_wmb();
|
|
cfs_rq->load_last_update_time_copy = sa->last_update_time;
|
|
#endif
|
|
|
|
if (update_freq && (decayed || removed_util))
|
|
cfs_rq_util_change(cfs_rq);
|
|
|
|
return decayed || removed_load;
|
|
}
|
|
|
|
/*
|
|
* Optional action to be done while updating the load average
|
|
*/
|
|
#define UPDATE_TG 0x1
|
|
#define SKIP_AGE_LOAD 0x2
|
|
|
|
/* Update task and its cfs_rq load average */
|
|
static inline void update_load_avg(struct sched_entity *se, int flags)
|
|
{
|
|
struct cfs_rq *cfs_rq = cfs_rq_of(se);
|
|
u64 now = cfs_rq_clock_task(cfs_rq);
|
|
struct rq *rq = rq_of(cfs_rq);
|
|
int cpu = cpu_of(rq);
|
|
int decayed;
|
|
|
|
/*
|
|
* 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
|
|
*/
|
|
if (se->avg.last_update_time && !(flags & SKIP_AGE_LOAD))
|
|
__update_load_avg_se(now, cpu, cfs_rq, se);
|
|
|
|
decayed = update_cfs_rq_load_avg(now, cfs_rq, true);
|
|
decayed |= propagate_entity_load_avg(se);
|
|
|
|
if (decayed && (flags & UPDATE_TG))
|
|
update_tg_load_avg(cfs_rq, 0);
|
|
}
|
|
|
|
/**
|
|
* attach_entity_load_avg - attach this entity to its cfs_rq load avg
|
|
* @cfs_rq: cfs_rq to attach to
|
|
* @se: sched_entity to attach
|
|
*
|
|
* Must call update_cfs_rq_load_avg() before this, since we rely on
|
|
* cfs_rq->avg.last_update_time being current.
|
|
*/
|
|
static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|
{
|
|
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;
|
|
set_tg_cfs_propagate(cfs_rq);
|
|
|
|
cfs_rq_util_change(cfs_rq);
|
|
}
|
|
|
|
/**
|
|
* detach_entity_load_avg - detach this entity from its cfs_rq load avg
|
|
* @cfs_rq: cfs_rq to detach from
|
|
* @se: sched_entity to detach
|
|
*
|
|
* Must call update_cfs_rq_load_avg() before this, since we rely on
|
|
* cfs_rq->avg.last_update_time being current.
|
|
*/
|
|
static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|
{
|
|
|
|
sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg);
|
|
sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum);
|
|
sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
|
|
sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
|
|
set_tg_cfs_propagate(cfs_rq);
|
|
|
|
cfs_rq_util_change(cfs_rq);
|
|
}
|
|
|
|
/* Add the load generated by se into cfs_rq's load average */
|
|
static inline void
|
|
enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|
{
|
|
struct sched_avg *sa = &se->avg;
|
|
|
|
cfs_rq->runnable_load_avg += sa->load_avg;
|
|
cfs_rq->runnable_load_sum += sa->load_sum;
|
|
|
|
if (!sa->last_update_time) {
|
|
attach_entity_load_avg(cfs_rq, se);
|
|
update_tg_load_avg(cfs_rq, 0);
|
|
}
|
|
}
|
|
|
|
/* 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)
|
|
{
|
|
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);
|
|
}
|
|
|
|
#ifndef CONFIG_64BIT
|
|
static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
|
|
{
|
|
u64 last_update_time_copy;
|
|
u64 last_update_time;
|
|
|
|
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);
|
|
|
|
return last_update_time;
|
|
}
|
|
#else
|
|
static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
|
|
{
|
|
return cfs_rq->avg.last_update_time;
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* Synchronize entity load avg of dequeued entity without locking
|
|
* the previous rq.
|
|
*/
|
|
void sync_entity_load_avg(struct sched_entity *se)
|
|
{
|
|
struct cfs_rq *cfs_rq = cfs_rq_of(se);
|
|
u64 last_update_time;
|
|
|
|
last_update_time = cfs_rq_last_update_time(cfs_rq);
|
|
__update_load_avg_blocked_se(last_update_time, cpu_of(rq_of(cfs_rq)), se);
|
|
}
|
|
|
|
/*
|
|
* Task first catches up with cfs_rq, and then subtract
|
|
* itself from the cfs_rq (task must be off the queue now).
|
|
*/
|
|
void remove_entity_load_avg(struct sched_entity *se)
|
|
{
|
|
struct cfs_rq *cfs_rq = cfs_rq_of(se);
|
|
|
|
/*
|
|
* tasks cannot exit without having gone through wake_up_new_task() ->
|
|
* post_init_entity_util_avg() which will have added things to the
|
|
* cfs_rq, so we can remove unconditionally.
|
|
*
|
|
* Similarly for groups, they will have passed through
|
|
* post_init_entity_util_avg() before unregister_sched_fair_group()
|
|
* calls this.
|
|
*/
|
|
|
|
sync_entity_load_avg(se);
|
|
atomic_long_add(se->avg.load_avg, &cfs_rq->removed_load_avg);
|
|
atomic_long_add(se->avg.util_avg, &cfs_rq->removed_util_avg);
|
|
}
|
|
|
|
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, struct rq_flags *rf);
|
|
|
|
#else /* CONFIG_SMP */
|
|
|
|
static inline int
|
|
update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
#define UPDATE_TG 0x0
|
|
#define SKIP_AGE_LOAD 0x0
|
|
|
|
static inline void update_load_avg(struct sched_entity *se, int not_used1)
|
|
{
|
|
cpufreq_update_util(rq_of(cfs_rq_of(se)), 0);
|
|
}
|
|
|
|
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, struct rq_flags *rf)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
#endif /* CONFIG_SMP */
|
|
|
|
static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|
{
|
|
#ifdef CONFIG_SCHED_DEBUG
|
|
s64 d = se->vruntime - cfs_rq->min_vruntime;
|
|
|
|
if (d < 0)
|
|
d = -d;
|
|
|
|
if (d > 3*sysctl_sched_latency)
|
|
schedstat_inc(cfs_rq->nr_spread_over);
|
|
#endif
|
|
}
|
|
|
|
static void
|
|
place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
|
|
{
|
|
u64 vruntime = cfs_rq->min_vruntime;
|
|
|
|
/*
|
|
* The 'current' period is already promised to the current tasks,
|
|
* however the extra weight of the new task will slow them down a
|
|
* little, place the new task so that it fits in the slot that
|
|
* stays open at the end.
|
|
*/
|
|
if (initial && sched_feat(START_DEBIT))
|
|
vruntime += sched_vslice(cfs_rq, se);
|
|
|
|
/* sleeps up to a single latency don't count. */
|
|
if (!initial) {
|
|
unsigned long thresh = sysctl_sched_latency;
|
|
|
|
/*
|
|
* Halve their sleep time's effect, to allow
|
|
* for a gentler effect of sleepers:
|
|
*/
|
|
if (sched_feat(GENTLE_FAIR_SLEEPERS))
|
|
thresh >>= 1;
|
|
|
|
vruntime -= thresh;
|
|
}
|
|
|
|
/* ensure we never gain time by being placed backwards. */
|
|
se->vruntime = max_vruntime(se->vruntime, vruntime);
|
|
}
|
|
|
|
static void check_enqueue_throttle(struct cfs_rq *cfs_rq);
|
|
|
|
static inline void check_schedstat_required(void)
|
|
{
|
|
#ifdef CONFIG_SCHEDSTATS
|
|
if (schedstat_enabled())
|
|
return;
|
|
|
|
/* Force schedstat enabled if a dependent tracepoint is active */
|
|
if (trace_sched_stat_wait_enabled() ||
|
|
trace_sched_stat_sleep_enabled() ||
|
|
trace_sched_stat_iowait_enabled() ||
|
|
trace_sched_stat_blocked_enabled() ||
|
|
trace_sched_stat_runtime_enabled()) {
|
|
printk_deferred_once("Scheduler tracepoints stat_sleep, stat_iowait, "
|
|
"stat_blocked and stat_runtime require the "
|
|
"kernel parameter schedstats=enable or "
|
|
"kernel.sched_schedstats=1\n");
|
|
}
|
|
#endif
|
|
}
|
|
|
|
|
|
/*
|
|
* MIGRATION
|
|
*
|
|
* dequeue
|
|
* update_curr()
|
|
* update_min_vruntime()
|
|
* vruntime -= min_vruntime
|
|
*
|
|
* enqueue
|
|
* update_curr()
|
|
* update_min_vruntime()
|
|
* vruntime += min_vruntime
|
|
*
|
|
* this way the vruntime transition between RQs is done when both
|
|
* min_vruntime are up-to-date.
|
|
*
|
|
* WAKEUP (remote)
|
|
*
|
|
* ->migrate_task_rq_fair() (p->state == TASK_WAKING)
|
|
* vruntime -= min_vruntime
|
|
*
|
|
* enqueue
|
|
* update_curr()
|
|
* update_min_vruntime()
|
|
* vruntime += min_vruntime
|
|
*
|
|
* this way we don't have the most up-to-date min_vruntime on the originating
|
|
* CPU and an up-to-date min_vruntime on the destination CPU.
|
|
*/
|
|
|
|
static void
|
|
enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
|
|
{
|
|
bool renorm = !(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_MIGRATED);
|
|
bool curr = cfs_rq->curr == se;
|
|
|
|
/*
|
|
* If we're the current task, we must renormalise before calling
|
|
* update_curr().
|
|
*/
|
|
if (renorm && curr)
|
|
se->vruntime += cfs_rq->min_vruntime;
|
|
|
|
update_curr(cfs_rq);
|
|
|
|
/*
|
|
* Otherwise, renormalise after, such that we're placed at the current
|
|
* moment in time, instead of some random moment in the past. Being
|
|
* placed in the past could significantly boost this task to the
|
|
* fairness detriment of existing tasks.
|
|
*/
|
|
if (renorm && !curr)
|
|
se->vruntime += cfs_rq->min_vruntime;
|
|
|
|
/*
|
|
* When enqueuing a sched_entity, we must:
|
|
* - Update loads to have both entity and cfs_rq synced with now.
|
|
* - Add its load to cfs_rq->runnable_avg
|
|
* - For group_entity, update its weight to reflect the new share of
|
|
* its group cfs_rq
|
|
* - Add its new weight to cfs_rq->load.weight
|
|
*/
|
|
update_load_avg(se, UPDATE_TG);
|
|
enqueue_entity_load_avg(cfs_rq, se);
|
|
update_cfs_shares(se);
|
|
account_entity_enqueue(cfs_rq, se);
|
|
|
|
if (flags & ENQUEUE_WAKEUP)
|
|
place_entity(cfs_rq, se, 0);
|
|
|
|
check_schedstat_required();
|
|
update_stats_enqueue(cfs_rq, se, flags);
|
|
check_spread(cfs_rq, se);
|
|
if (!curr)
|
|
__enqueue_entity(cfs_rq, se);
|
|
se->on_rq = 1;
|
|
|
|
if (cfs_rq->nr_running == 1) {
|
|
list_add_leaf_cfs_rq(cfs_rq);
|
|
check_enqueue_throttle(cfs_rq);
|
|
}
|
|
}
|
|
|
|
static void __clear_buddies_last(struct sched_entity *se)
|
|
{
|
|
for_each_sched_entity(se) {
|
|
struct cfs_rq *cfs_rq = cfs_rq_of(se);
|
|
if (cfs_rq->last != se)
|
|
break;
|
|
|
|
cfs_rq->last = NULL;
|
|
}
|
|
}
|
|
|
|
static void __clear_buddies_next(struct sched_entity *se)
|
|
{
|
|
for_each_sched_entity(se) {
|
|
struct cfs_rq *cfs_rq = cfs_rq_of(se);
|
|
if (cfs_rq->next != se)
|
|
break;
|
|
|
|
cfs_rq->next = NULL;
|
|
}
|
|
}
|
|
|
|
static void __clear_buddies_skip(struct sched_entity *se)
|
|
{
|
|
for_each_sched_entity(se) {
|
|
struct cfs_rq *cfs_rq = cfs_rq_of(se);
|
|
if (cfs_rq->skip != se)
|
|
break;
|
|
|
|
cfs_rq->skip = NULL;
|
|
}
|
|
}
|
|
|
|
static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|
{
|
|
if (cfs_rq->last == se)
|
|
__clear_buddies_last(se);
|
|
|
|
if (cfs_rq->next == se)
|
|
__clear_buddies_next(se);
|
|
|
|
if (cfs_rq->skip == se)
|
|
__clear_buddies_skip(se);
|
|
}
|
|
|
|
static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq);
|
|
|
|
static void
|
|
dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
|
|
{
|
|
/*
|
|
* Update run-time statistics of the 'current'.
|
|
*/
|
|
update_curr(cfs_rq);
|
|
|
|
/*
|
|
* When dequeuing a sched_entity, we must:
|
|
* - Update loads to have both entity and cfs_rq synced with now.
|
|
* - Substract its load from the cfs_rq->runnable_avg.
|
|
* - Substract its previous weight from cfs_rq->load.weight.
|
|
* - For group entity, update its weight to reflect the new share
|
|
* of its group cfs_rq.
|
|
*/
|
|
update_load_avg(se, UPDATE_TG);
|
|
dequeue_entity_load_avg(cfs_rq, se);
|
|
|
|
update_stats_dequeue(cfs_rq, se, flags);
|
|
|
|
clear_buddies(cfs_rq, se);
|
|
|
|
if (se != cfs_rq->curr)
|
|
__dequeue_entity(cfs_rq, se);
|
|
se->on_rq = 0;
|
|
account_entity_dequeue(cfs_rq, se);
|
|
|
|
/*
|
|
* Normalize after update_curr(); which will also have moved
|
|
* min_vruntime if @se is the one holding it back. But before doing
|
|
* update_min_vruntime() again, which will discount @se's position and
|
|
* can move min_vruntime forward still more.
|
|
*/
|
|
if (!(flags & DEQUEUE_SLEEP))
|
|
se->vruntime -= cfs_rq->min_vruntime;
|
|
|
|
/* return excess runtime on last dequeue */
|
|
return_cfs_rq_runtime(cfs_rq);
|
|
|
|
update_cfs_shares(se);
|
|
|
|
/*
|
|
* Now advance min_vruntime if @se was the entity holding it back,
|
|
* except when: DEQUEUE_SAVE && !DEQUEUE_MOVE, in this case we'll be
|
|
* put back on, and if we advance min_vruntime, we'll be placed back
|
|
* further than we started -- ie. we'll be penalized.
|
|
*/
|
|
if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) == DEQUEUE_SAVE)
|
|
update_min_vruntime(cfs_rq);
|
|
}
|
|
|
|
/*
|
|
* Preempt the current task with a newly woken task if needed:
|
|
*/
|
|
static void
|
|
check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
|
|
{
|
|
unsigned long ideal_runtime, delta_exec;
|
|
struct sched_entity *se;
|
|
s64 delta;
|
|
|
|
ideal_runtime = sched_slice(cfs_rq, curr);
|
|
delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
|
|
if (delta_exec > ideal_runtime) {
|
|
resched_curr(rq_of(cfs_rq));
|
|
/*
|
|
* The current task ran long enough, ensure it doesn't get
|
|
* re-elected due to buddy favours.
|
|
*/
|
|
clear_buddies(cfs_rq, curr);
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* Ensure that a task that missed wakeup preemption by a
|
|
* narrow margin doesn't have to wait for a full slice.
|
|
* This also mitigates buddy induced latencies under load.
|
|
*/
|
|
if (delta_exec < sysctl_sched_min_granularity)
|
|
return;
|
|
|
|
se = __pick_first_entity(cfs_rq);
|
|
delta = curr->vruntime - se->vruntime;
|
|
|
|
if (delta < 0)
|
|
return;
|
|
|
|
if (delta > ideal_runtime)
|
|
resched_curr(rq_of(cfs_rq));
|
|
}
|
|
|
|
static void
|
|
set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|
{
|
|
/* 'current' is not kept within the tree. */
|
|
if (se->on_rq) {
|
|
/*
|
|
* Any task has to be enqueued before it get to execute on
|
|
* a CPU. So account for the time it spent waiting on the
|
|
* runqueue.
|
|
*/
|
|
update_stats_wait_end(cfs_rq, se);
|
|
__dequeue_entity(cfs_rq, se);
|
|
update_load_avg(se, UPDATE_TG);
|
|
}
|
|
|
|
update_stats_curr_start(cfs_rq, se);
|
|
cfs_rq->curr = se;
|
|
|
|
/*
|
|
* Track our maximum slice length, if the CPU's load is at
|
|
* 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) {
|
|
schedstat_set(se->statistics.slice_max,
|
|
max((u64)schedstat_val(se->statistics.slice_max),
|
|
se->sum_exec_runtime - se->prev_sum_exec_runtime));
|
|
}
|
|
|
|
se->prev_sum_exec_runtime = se->sum_exec_runtime;
|
|
}
|
|
|
|
static int
|
|
wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
|
|
|
|
/*
|
|
* Pick the next process, keeping these things in mind, in this order:
|
|
* 1) keep things fair between processes/task groups
|
|
* 2) pick the "next" process, since someone really wants that to run
|
|
* 3) pick the "last" process, for cache locality
|
|
* 4) do not run the "skip" process, if something else is available
|
|
*/
|
|
static struct sched_entity *
|
|
pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr)
|
|
{
|
|
struct sched_entity *left = __pick_first_entity(cfs_rq);
|
|
struct sched_entity *se;
|
|
|
|
/*
|
|
* If curr is set we have to see if its left of the leftmost entity
|
|
* still in the tree, provided there was anything in the tree at all.
|
|
*/
|
|
if (!left || (curr && entity_before(curr, left)))
|
|
left = curr;
|
|
|
|
se = left; /* ideally we run the leftmost entity */
|
|
|
|
/*
|
|
* Avoid running the skip buddy, if running something else can
|
|
* be done without getting too unfair.
|
|
*/
|
|
if (cfs_rq->skip == se) {
|
|
struct sched_entity *second;
|
|
|
|
if (se == curr) {
|
|
second = __pick_first_entity(cfs_rq);
|
|
} else {
|
|
second = __pick_next_entity(se);
|
|
if (!second || (curr && entity_before(curr, second)))
|
|
second = curr;
|
|
}
|
|
|
|
if (second && wakeup_preempt_entity(second, left) < 1)
|
|
se = second;
|
|
}
|
|
|
|
/*
|
|
* Prefer last buddy, try to return the CPU to a preempted task.
|
|
*/
|
|
if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
|
|
se = cfs_rq->last;
|
|
|
|
/*
|
|
* Someone really wants this to run. If it's not unfair, run it.
|
|
*/
|
|
if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
|
|
se = cfs_rq->next;
|
|
|
|
clear_buddies(cfs_rq, se);
|
|
|
|
return se;
|
|
}
|
|
|
|
static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq);
|
|
|
|
static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
|
|
{
|
|
/*
|
|
* If still on the runqueue then deactivate_task()
|
|
* was not called and update_curr() has to be done:
|
|
*/
|
|
if (prev->on_rq)
|
|
update_curr(cfs_rq);
|
|
|
|
/* throttle cfs_rqs exceeding runtime */
|
|
check_cfs_rq_runtime(cfs_rq);
|
|
|
|
check_spread(cfs_rq, prev);
|
|
|
|
if (prev->on_rq) {
|
|
update_stats_wait_start(cfs_rq, prev);
|
|
/* Put 'current' back into the tree. */
|
|
__enqueue_entity(cfs_rq, prev);
|
|
/* in !on_rq case, update occurred at dequeue */
|
|
update_load_avg(prev, 0);
|
|
}
|
|
cfs_rq->curr = NULL;
|
|
}
|
|
|
|
static void
|
|
entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
|
|
{
|
|
/*
|
|
* Update run-time statistics of the 'current'.
|
|
*/
|
|
update_curr(cfs_rq);
|
|
|
|
/*
|
|
* Ensure that runnable average is periodically updated.
|
|
*/
|
|
update_load_avg(curr, UPDATE_TG);
|
|
update_cfs_shares(curr);
|
|
|
|
#ifdef CONFIG_SCHED_HRTICK
|
|
/*
|
|
* queued ticks are scheduled to match the slice, so don't bother
|
|
* validating it and just reschedule.
|
|
*/
|
|
if (queued) {
|
|
resched_curr(rq_of(cfs_rq));
|
|
return;
|
|
}
|
|
/*
|
|
* don't let the period tick interfere with the hrtick preemption
|
|
*/
|
|
if (!sched_feat(DOUBLE_TICK) &&
|
|
hrtimer_active(&rq_of(cfs_rq)->hrtick_timer))
|
|
return;
|
|
#endif
|
|
|
|
if (cfs_rq->nr_running > 1)
|
|
check_preempt_tick(cfs_rq, curr);
|
|
}
|
|
|
|
|
|
/**************************************************
|
|
* CFS bandwidth control machinery
|
|
*/
|
|
|
|
#ifdef CONFIG_CFS_BANDWIDTH
|
|
|
|
#ifdef HAVE_JUMP_LABEL
|
|
static struct static_key __cfs_bandwidth_used;
|
|
|
|
static inline bool cfs_bandwidth_used(void)
|
|
{
|
|
return static_key_false(&__cfs_bandwidth_used);
|
|
}
|
|
|
|
void cfs_bandwidth_usage_inc(void)
|
|
{
|
|
static_key_slow_inc(&__cfs_bandwidth_used);
|
|
}
|
|
|
|
void cfs_bandwidth_usage_dec(void)
|
|
{
|
|
static_key_slow_dec(&__cfs_bandwidth_used);
|
|
}
|
|
#else /* HAVE_JUMP_LABEL */
|
|
static bool cfs_bandwidth_used(void)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
void cfs_bandwidth_usage_inc(void) {}
|
|
void cfs_bandwidth_usage_dec(void) {}
|
|
#endif /* HAVE_JUMP_LABEL */
|
|
|
|
/*
|
|
* default period for cfs group bandwidth.
|
|
* default: 0.1s, units: nanoseconds
|
|
*/
|
|
static inline u64 default_cfs_period(void)
|
|
{
|
|
return 100000000ULL;
|
|
}
|
|
|
|
static inline u64 sched_cfs_bandwidth_slice(void)
|
|
{
|
|
return (u64)sysctl_sched_cfs_bandwidth_slice * NSEC_PER_USEC;
|
|
}
|
|
|
|
/*
|
|
* Replenish runtime according to assigned quota and update expiration time.
|
|
* We use sched_clock_cpu directly instead of rq->clock to avoid adding
|
|
* additional synchronization around rq->lock.
|
|
*
|
|
* requires cfs_b->lock
|
|
*/
|
|
void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b)
|
|
{
|
|
u64 now;
|
|
|
|
if (cfs_b->quota == RUNTIME_INF)
|
|
return;
|
|
|
|
now = sched_clock_cpu(smp_processor_id());
|
|
cfs_b->runtime = cfs_b->quota;
|
|
cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period);
|
|
}
|
|
|
|
static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
|
|
{
|
|
return &tg->cfs_bandwidth;
|
|
}
|
|
|
|
/* rq->task_clock normalized against any time this cfs_rq has spent throttled */
|
|
static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
|
|
{
|
|
if (unlikely(cfs_rq->throttle_count))
|
|
return cfs_rq->throttled_clock_task - cfs_rq->throttled_clock_task_time;
|
|
|
|
return rq_clock_task(rq_of(cfs_rq)) - cfs_rq->throttled_clock_task_time;
|
|
}
|
|
|
|
/* returns 0 on failure to allocate runtime */
|
|
static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
|
|
{
|
|
struct task_group *tg = cfs_rq->tg;
|
|
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
|
|
u64 amount = 0, min_amount, expires;
|
|
|
|
/* note: this is a positive sum as runtime_remaining <= 0 */
|
|
min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining;
|
|
|
|
raw_spin_lock(&cfs_b->lock);
|
|
if (cfs_b->quota == RUNTIME_INF)
|
|
amount = min_amount;
|
|
else {
|
|
start_cfs_bandwidth(cfs_b);
|
|
|
|
if (cfs_b->runtime > 0) {
|
|
amount = min(cfs_b->runtime, min_amount);
|
|
cfs_b->runtime -= amount;
|
|
cfs_b->idle = 0;
|
|
}
|
|
}
|
|
expires = cfs_b->runtime_expires;
|
|
raw_spin_unlock(&cfs_b->lock);
|
|
|
|
cfs_rq->runtime_remaining += amount;
|
|
/*
|
|
* we may have advanced our local expiration to account for allowed
|
|
* spread between our sched_clock and the one on which runtime was
|
|
* issued.
|
|
*/
|
|
if ((s64)(expires - cfs_rq->runtime_expires) > 0)
|
|
cfs_rq->runtime_expires = expires;
|
|
|
|
return cfs_rq->runtime_remaining > 0;
|
|
}
|
|
|
|
/*
|
|
* Note: This depends on the synchronization provided by sched_clock and the
|
|
* fact that rq->clock snapshots this value.
|
|
*/
|
|
static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq)
|
|
{
|
|
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
|
|
|
|
/* if the deadline is ahead of our clock, nothing to do */
|
|
if (likely((s64)(rq_clock(rq_of(cfs_rq)) - cfs_rq->runtime_expires) < 0))
|
|
return;
|
|
|
|
if (cfs_rq->runtime_remaining < 0)
|
|
return;
|
|
|
|
/*
|
|
* If the local deadline has passed we have to consider the
|
|
* possibility that our sched_clock is 'fast' and the global deadline
|
|
* has not truly expired.
|
|
*
|
|
* Fortunately we can check determine whether this the case by checking
|
|
* whether the global deadline has advanced. It is valid to compare
|
|
* cfs_b->runtime_expires without any locks since we only care about
|
|
* exact equality, so a partial write will still work.
|
|
*/
|
|
|
|
if (cfs_rq->runtime_expires != cfs_b->runtime_expires) {
|
|
/* extend local deadline, drift is bounded above by 2 ticks */
|
|
cfs_rq->runtime_expires += TICK_NSEC;
|
|
} else {
|
|
/* global deadline is ahead, expiration has passed */
|
|
cfs_rq->runtime_remaining = 0;
|
|
}
|
|
}
|
|
|
|
static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
|
|
{
|
|
/* dock delta_exec before expiring quota (as it could span periods) */
|
|
cfs_rq->runtime_remaining -= delta_exec;
|
|
expire_cfs_rq_runtime(cfs_rq);
|
|
|
|
if (likely(cfs_rq->runtime_remaining > 0))
|
|
return;
|
|
|
|
/*
|
|
* if we're unable to extend our runtime we resched so that the active
|
|
* hierarchy can be throttled
|
|
*/
|
|
if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr))
|
|
resched_curr(rq_of(cfs_rq));
|
|
}
|
|
|
|
static __always_inline
|
|
void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
|
|
{
|
|
if (!cfs_bandwidth_used() || !cfs_rq->runtime_enabled)
|
|
return;
|
|
|
|
__account_cfs_rq_runtime(cfs_rq, delta_exec);
|
|
}
|
|
|
|
static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq)
|
|
{
|
|
return cfs_bandwidth_used() && cfs_rq->throttled;
|
|
}
|
|
|
|
/* check whether cfs_rq, or any parent, is throttled */
|
|
static inline int throttled_hierarchy(struct cfs_rq *cfs_rq)
|
|
{
|
|
return cfs_bandwidth_used() && cfs_rq->throttle_count;
|
|
}
|
|
|
|
/*
|
|
* Ensure that neither of the group entities corresponding to src_cpu or
|
|
* dest_cpu are members of a throttled hierarchy when performing group
|
|
* load-balance operations.
|
|
*/
|
|
static inline int throttled_lb_pair(struct task_group *tg,
|
|
int src_cpu, int dest_cpu)
|
|
{
|
|
struct cfs_rq *src_cfs_rq, *dest_cfs_rq;
|
|
|
|
src_cfs_rq = tg->cfs_rq[src_cpu];
|
|
dest_cfs_rq = tg->cfs_rq[dest_cpu];
|
|
|
|
return throttled_hierarchy(src_cfs_rq) ||
|
|
throttled_hierarchy(dest_cfs_rq);
|
|
}
|
|
|
|
/* updated child weight may affect parent so we have to do this bottom up */
|
|
static int tg_unthrottle_up(struct task_group *tg, void *data)
|
|
{
|
|
struct rq *rq = data;
|
|
struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
|
|
|
|
cfs_rq->throttle_count--;
|
|
if (!cfs_rq->throttle_count) {
|
|
/* adjust cfs_rq_clock_task() */
|
|
cfs_rq->throttled_clock_task_time += rq_clock_task(rq) -
|
|
cfs_rq->throttled_clock_task;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int tg_throttle_down(struct task_group *tg, void *data)
|
|
{
|
|
struct rq *rq = data;
|
|
struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
|
|
|
|
/* group is entering throttled state, stop time */
|
|
if (!cfs_rq->throttle_count)
|
|
cfs_rq->throttled_clock_task = rq_clock_task(rq);
|
|
cfs_rq->throttle_count++;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
|
|
{
|
|
struct rq *rq = rq_of(cfs_rq);
|
|
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))];
|
|
|
|
/* freeze hierarchy runnable averages while throttled */
|
|
rcu_read_lock();
|
|
walk_tg_tree_from(cfs_rq->tg, tg_throttle_down, tg_nop, (void *)rq);
|
|
rcu_read_unlock();
|
|
|
|
task_delta = cfs_rq->h_nr_running;
|
|
for_each_sched_entity(se) {
|
|
struct cfs_rq *qcfs_rq = cfs_rq_of(se);
|
|
/* throttled entity or throttle-on-deactivate */
|
|
if (!se->on_rq)
|
|
break;
|
|
|
|
if (dequeue)
|
|
dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP);
|
|
qcfs_rq->h_nr_running -= task_delta;
|
|
|
|
if (qcfs_rq->load.weight)
|
|
dequeue = 0;
|
|
}
|
|
|
|
if (!se)
|
|
sub_nr_running(rq, task_delta);
|
|
|
|
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 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);
|
|
}
|
|
|
|
void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
|
|
{
|
|
struct rq *rq = rq_of(cfs_rq);
|
|
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
|
|
struct sched_entity *se;
|
|
int enqueue = 1;
|
|
long task_delta;
|
|
|
|
se = cfs_rq->tg->se[cpu_of(rq)];
|
|
|
|
cfs_rq->throttled = 0;
|
|
|
|
update_rq_clock(rq);
|
|
|
|
raw_spin_lock(&cfs_b->lock);
|
|
cfs_b->throttled_time += rq_clock(rq) - cfs_rq->throttled_clock;
|
|
list_del_rcu(&cfs_rq->throttled_list);
|
|
raw_spin_unlock(&cfs_b->lock);
|
|
|
|
/* update hierarchical throttle state */
|
|
walk_tg_tree_from(cfs_rq->tg, tg_nop, tg_unthrottle_up, (void *)rq);
|
|
|
|
if (!cfs_rq->load.weight)
|
|
return;
|
|
|
|
task_delta = cfs_rq->h_nr_running;
|
|
for_each_sched_entity(se) {
|
|
if (se->on_rq)
|
|
enqueue = 0;
|
|
|
|
cfs_rq = cfs_rq_of(se);
|
|
if (enqueue)
|
|
enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
|
|
cfs_rq->h_nr_running += task_delta;
|
|
|
|
if (cfs_rq_throttled(cfs_rq))
|
|
break;
|
|
}
|
|
|
|
if (!se)
|
|
add_nr_running(rq, task_delta);
|
|
|
|
/* determine whether we need to wake up potentially idle cpu */
|
|
if (rq->curr == rq->idle && rq->cfs.nr_running)
|
|
resched_curr(rq);
|
|
}
|
|
|
|
static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b,
|
|
u64 remaining, u64 expires)
|
|
{
|
|
struct cfs_rq *cfs_rq;
|
|
u64 runtime;
|
|
u64 starting_runtime = remaining;
|
|
|
|
rcu_read_lock();
|
|
list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq,
|
|
throttled_list) {
|
|
struct rq *rq = rq_of(cfs_rq);
|
|
struct rq_flags rf;
|
|
|
|
rq_lock(rq, &rf);
|
|
if (!cfs_rq_throttled(cfs_rq))
|
|
goto next;
|
|
|
|
runtime = -cfs_rq->runtime_remaining + 1;
|
|
if (runtime > remaining)
|
|
runtime = remaining;
|
|
remaining -= runtime;
|
|
|
|
cfs_rq->runtime_remaining += runtime;
|
|
cfs_rq->runtime_expires = expires;
|
|
|
|
/* we check whether we're throttled above */
|
|
if (cfs_rq->runtime_remaining > 0)
|
|
unthrottle_cfs_rq(cfs_rq);
|
|
|
|
next:
|
|
rq_unlock(rq, &rf);
|
|
|
|
if (!remaining)
|
|
break;
|
|
}
|
|
rcu_read_unlock();
|
|
|
|
return starting_runtime - remaining;
|
|
}
|
|
|
|
/*
|
|
* Responsible for refilling a task_group's bandwidth and unthrottling its
|
|
* cfs_rqs as appropriate. If there has been no activity within the last
|
|
* period the timer is deactivated until scheduling resumes; cfs_b->idle is
|
|
* used to track this state.
|
|
*/
|
|
static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
|
|
{
|
|
u64 runtime, runtime_expires;
|
|
int throttled;
|
|
|
|
/* no need to continue the timer with no bandwidth constraint */
|
|
if (cfs_b->quota == RUNTIME_INF)
|
|
goto out_deactivate;
|
|
|
|
throttled = !list_empty(&cfs_b->throttled_cfs_rq);
|
|
cfs_b->nr_periods += overrun;
|
|
|
|
/*
|
|
* idle depends on !throttled (for the case of a large deficit), and if
|
|
* we're going inactive then everything else can be deferred
|
|
*/
|
|
if (cfs_b->idle && !throttled)
|
|
goto out_deactivate;
|
|
|
|
__refill_cfs_bandwidth_runtime(cfs_b);
|
|
|
|
if (!throttled) {
|
|
/* mark as potentially idle for the upcoming period */
|
|
cfs_b->idle = 1;
|
|
return 0;
|
|
}
|
|
|
|
/* account preceding periods in which throttling occurred */
|
|
cfs_b->nr_throttled += overrun;
|
|
|
|
runtime_expires = cfs_b->runtime_expires;
|
|
|
|
/*
|
|
* This check is repeated as we are holding onto the new bandwidth while
|
|
* we unthrottle. This can potentially race with an unthrottled group
|
|
* trying to acquire new bandwidth from the global pool. This can result
|
|
* in us over-using our runtime if it is all used during this loop, but
|
|
* only by limited amounts in that extreme case.
|
|
*/
|
|
while (throttled && cfs_b->runtime > 0) {
|
|
runtime = cfs_b->runtime;
|
|
raw_spin_unlock(&cfs_b->lock);
|
|
/* we can't nest cfs_b->lock while distributing bandwidth */
|
|
runtime = distribute_cfs_runtime(cfs_b, runtime,
|
|
runtime_expires);
|
|
raw_spin_lock(&cfs_b->lock);
|
|
|
|
throttled = !list_empty(&cfs_b->throttled_cfs_rq);
|
|
|
|
cfs_b->runtime -= min(runtime, cfs_b->runtime);
|
|
}
|
|
|
|
/*
|
|
* While we are ensured activity in the period following an
|
|
* unthrottle, this also covers the case in which the new bandwidth is
|
|
* insufficient to cover the existing bandwidth deficit. (Forcing the
|
|
* timer to remain active while there are any throttled entities.)
|
|
*/
|
|
cfs_b->idle = 0;
|
|
|
|
return 0;
|
|
|
|
out_deactivate:
|
|
return 1;
|
|
}
|
|
|
|
/* a cfs_rq won't donate quota below this amount */
|
|
static const u64 min_cfs_rq_runtime = 1 * NSEC_PER_MSEC;
|
|
/* minimum remaining period time to redistribute slack quota */
|
|
static const u64 min_bandwidth_expiration = 2 * NSEC_PER_MSEC;
|
|
/* how long we wait to gather additional slack before distributing */
|
|
static const u64 cfs_bandwidth_slack_period = 5 * NSEC_PER_MSEC;
|
|
|
|
/*
|
|
* 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. 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)
|
|
{
|
|
struct hrtimer *refresh_timer = &cfs_b->period_timer;
|
|
u64 remaining;
|
|
|
|
/* if the call-back is running a quota refresh is already occurring */
|
|
if (hrtimer_callback_running(refresh_timer))
|
|
return 1;
|
|
|
|
/* is a quota refresh about to occur? */
|
|
remaining = ktime_to_ns(hrtimer_expires_remaining(refresh_timer));
|
|
if (remaining < min_expire)
|
|
return 1;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void start_cfs_slack_bandwidth(struct cfs_bandwidth *cfs_b)
|
|
{
|
|
u64 min_left = cfs_bandwidth_slack_period + min_bandwidth_expiration;
|
|
|
|
/* if there's a quota refresh soon don't bother with slack */
|
|
if (runtime_refresh_within(cfs_b, min_left))
|
|
return;
|
|
|
|
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 */
|
|
static void __return_cfs_rq_runtime(struct cfs_rq *cfs_rq)
|
|
{
|
|
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
|
|
s64 slack_runtime = cfs_rq->runtime_remaining - min_cfs_rq_runtime;
|
|
|
|
if (slack_runtime <= 0)
|
|
return;
|
|
|
|
raw_spin_lock(&cfs_b->lock);
|
|
if (cfs_b->quota != RUNTIME_INF &&
|
|
cfs_rq->runtime_expires == cfs_b->runtime_expires) {
|
|
cfs_b->runtime += slack_runtime;
|
|
|
|
/* we are under rq->lock, defer unthrottling using a timer */
|
|
if (cfs_b->runtime > sched_cfs_bandwidth_slice() &&
|
|
!list_empty(&cfs_b->throttled_cfs_rq))
|
|
start_cfs_slack_bandwidth(cfs_b);
|
|
}
|
|
raw_spin_unlock(&cfs_b->lock);
|
|
|
|
/* even if it's not valid for return we don't want to try again */
|
|
cfs_rq->runtime_remaining -= slack_runtime;
|
|
}
|
|
|
|
static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq)
|
|
{
|
|
if (!cfs_bandwidth_used())
|
|
return;
|
|
|
|
if (!cfs_rq->runtime_enabled || cfs_rq->nr_running)
|
|
return;
|
|
|
|
__return_cfs_rq_runtime(cfs_rq);
|
|
}
|
|
|
|
/*
|
|
* This is done with a timer (instead of inline with bandwidth return) since
|
|
* it's necessary to juggle rq->locks to unthrottle their respective cfs_rqs.
|
|
*/
|
|
static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
|
|
{
|
|
u64 runtime = 0, slice = sched_cfs_bandwidth_slice();
|
|
u64 expires;
|
|
|
|
/* confirm we're still not at a refresh boundary */
|
|
raw_spin_lock(&cfs_b->lock);
|
|
if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) {
|
|
raw_spin_unlock(&cfs_b->lock);
|
|
return;
|
|
}
|
|
|
|
if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice)
|
|
runtime = cfs_b->runtime;
|
|
|
|
expires = cfs_b->runtime_expires;
|
|
raw_spin_unlock(&cfs_b->lock);
|
|
|
|
if (!runtime)
|
|
return;
|
|
|
|
runtime = distribute_cfs_runtime(cfs_b, runtime, expires);
|
|
|
|
raw_spin_lock(&cfs_b->lock);
|
|
if (expires == cfs_b->runtime_expires)
|
|
cfs_b->runtime -= min(runtime, cfs_b->runtime);
|
|
raw_spin_unlock(&cfs_b->lock);
|
|
}
|
|
|
|
/*
|
|
* When a group wakes up we want to make sure that its quota is not already
|
|
* expired/exceeded, otherwise it may be allowed to steal additional ticks of
|
|
* runtime as update_curr() throttling can not not trigger until it's on-rq.
|
|
*/
|
|
static void check_enqueue_throttle(struct cfs_rq *cfs_rq)
|
|
{
|
|
if (!cfs_bandwidth_used())
|
|
return;
|
|
|
|
/* an active group must be handled by the update_curr()->put() path */
|
|
if (!cfs_rq->runtime_enabled || cfs_rq->curr)
|
|
return;
|
|
|
|
/* ensure the group is not already throttled */
|
|
if (cfs_rq_throttled(cfs_rq))
|
|
return;
|
|
|
|
/* update runtime allocation */
|
|
account_cfs_rq_runtime(cfs_rq, 0);
|
|
if (cfs_rq->runtime_remaining <= 0)
|
|
throttle_cfs_rq(cfs_rq);
|
|
}
|
|
|
|
static void sync_throttle(struct task_group *tg, int cpu)
|
|
{
|
|
struct cfs_rq *pcfs_rq, *cfs_rq;
|
|
|
|
if (!cfs_bandwidth_used())
|
|
return;
|
|
|
|
if (!tg->parent)
|
|
return;
|
|
|
|
cfs_rq = tg->cfs_rq[cpu];
|
|
pcfs_rq = tg->parent->cfs_rq[cpu];
|
|
|
|
cfs_rq->throttle_count = pcfs_rq->throttle_count;
|
|
cfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu));
|
|
}
|
|
|
|
/* conditionally throttle active cfs_rq's from put_prev_entity() */
|
|
static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq)
|
|
{
|
|
if (!cfs_bandwidth_used())
|
|
return false;
|
|
|
|
if (likely(!cfs_rq->runtime_enabled || cfs_rq->runtime_remaining > 0))
|
|
return false;
|
|
|
|
/*
|
|
* it's possible for a throttled entity to be forced into a running
|
|
* state (e.g. set_curr_task), in this case we're finished.
|
|
*/
|
|
if (cfs_rq_throttled(cfs_rq))
|
|
return true;
|
|
|
|
throttle_cfs_rq(cfs_rq);
|
|
return true;
|
|
}
|
|
|
|
static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
|
|
{
|
|
struct cfs_bandwidth *cfs_b =
|
|
container_of(timer, struct cfs_bandwidth, slack_timer);
|
|
|
|
do_sched_cfs_slack_timer(cfs_b);
|
|
|
|
return HRTIMER_NORESTART;
|
|
}
|
|
|
|
static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
|
|
{
|
|
struct cfs_bandwidth *cfs_b =
|
|
container_of(timer, struct cfs_bandwidth, period_timer);
|
|
int overrun;
|
|
int idle = 0;
|
|
|
|
raw_spin_lock(&cfs_b->lock);
|
|
for (;;) {
|
|
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;
|
|
}
|
|
|
|
void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
|
|
{
|
|
raw_spin_lock_init(&cfs_b->lock);
|
|
cfs_b->runtime = 0;
|
|
cfs_b->quota = RUNTIME_INF;
|
|
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_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;
|
|
}
|
|
|
|
static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
|
|
{
|
|
cfs_rq->runtime_enabled = 0;
|
|
INIT_LIST_HEAD(&cfs_rq->throttled_list);
|
|
}
|
|
|
|
void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
|
|
{
|
|
lockdep_assert_held(&cfs_b->lock);
|
|
|
|
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)
|
|
{
|
|
/* init_cfs_bandwidth() was not called */
|
|
if (!cfs_b->throttled_cfs_rq.next)
|
|
return;
|
|
|
|
hrtimer_cancel(&cfs_b->period_timer);
|
|
hrtimer_cancel(&cfs_b->slack_timer);
|
|
}
|
|
|
|
/*
|
|
* Both these cpu hotplug callbacks race against unregister_fair_sched_group()
|
|
*
|
|
* The race is harmless, since modifying bandwidth settings of unhooked group
|
|
* bits doesn't do much.
|
|
*/
|
|
|
|
/* cpu online calback */
|
|
static void __maybe_unused update_runtime_enabled(struct rq *rq)
|
|
{
|
|
struct task_group *tg;
|
|
|
|
lockdep_assert_held(&rq->lock);
|
|
|
|
rcu_read_lock();
|
|
list_for_each_entry_rcu(tg, &task_groups, list) {
|
|
struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
|
|
struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
|
|
|
|
raw_spin_lock(&cfs_b->lock);
|
|
cfs_rq->runtime_enabled = cfs_b->quota != RUNTIME_INF;
|
|
raw_spin_unlock(&cfs_b->lock);
|
|
}
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
/* cpu offline callback */
|
|
static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
|
|
{
|
|
struct task_group *tg;
|
|
|
|
lockdep_assert_held(&rq->lock);
|
|
|
|
rcu_read_lock();
|
|
list_for_each_entry_rcu(tg, &task_groups, list) {
|
|
struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
|
|
|
|
if (!cfs_rq->runtime_enabled)
|
|
continue;
|
|
|
|
/*
|
|
* clock_task is not advancing so we just need to make sure
|
|
* there's some valid quota amount
|
|
*/
|
|
cfs_rq->runtime_remaining = 1;
|
|
/*
|
|
* Offline rq is schedulable till cpu is completely disabled
|
|
* in take_cpu_down(), so we prevent new cfs throttling here.
|
|
*/
|
|
cfs_rq->runtime_enabled = 0;
|
|
|
|
if (cfs_rq_throttled(cfs_rq))
|
|
unthrottle_cfs_rq(cfs_rq);
|
|
}
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
#else /* CONFIG_CFS_BANDWIDTH */
|
|
static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
|
|
{
|
|
return rq_clock_task(rq_of(cfs_rq));
|
|
}
|
|
|
|
static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) {}
|
|
static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) { return false; }
|
|
static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {}
|
|
static inline void sync_throttle(struct task_group *tg, int cpu) {}
|
|
static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
|
|
|
|
static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline int throttled_hierarchy(struct cfs_rq *cfs_rq)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline int throttled_lb_pair(struct task_group *tg,
|
|
int src_cpu, int dest_cpu)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
|
|
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
|
|
#endif
|
|
|
|
static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
|
|
{
|
|
return NULL;
|
|
}
|
|
static inline void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
|
|
static inline void update_runtime_enabled(struct rq *rq) {}
|
|
static inline void unthrottle_offline_cfs_rqs(struct rq *rq) {}
|
|
|
|
#endif /* CONFIG_CFS_BANDWIDTH */
|
|
|
|
/**************************************************
|
|
* CFS operations on tasks:
|
|
*/
|
|
|
|
#ifdef CONFIG_SCHED_HRTICK
|
|
static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
|
|
{
|
|
struct sched_entity *se = &p->se;
|
|
struct cfs_rq *cfs_rq = cfs_rq_of(se);
|
|
|
|
SCHED_WARN_ON(task_rq(p) != rq);
|
|
|
|
if (rq->cfs.h_nr_running > 1) {
|
|
u64 slice = sched_slice(cfs_rq, se);
|
|
u64 ran = se->sum_exec_runtime - se->prev_sum_exec_runtime;
|
|
s64 delta = slice - ran;
|
|
|
|
if (delta < 0) {
|
|
if (rq->curr == p)
|
|
resched_curr(rq);
|
|
return;
|
|
}
|
|
hrtick_start(rq, delta);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* called from enqueue/dequeue and updates the hrtick when the
|
|
* current task is from our class and nr_running is low enough
|
|
* to matter.
|
|
*/
|
|
static void hrtick_update(struct rq *rq)
|
|
{
|
|
struct task_struct *curr = rq->curr;
|
|
|
|
if (!hrtick_enabled(rq) || curr->sched_class != &fair_sched_class)
|
|
return;
|
|
|
|
if (cfs_rq_of(&curr->se)->nr_running < sched_nr_latency)
|
|
hrtick_start_fair(rq, curr);
|
|
}
|
|
#else /* !CONFIG_SCHED_HRTICK */
|
|
static inline void
|
|
hrtick_start_fair(struct rq *rq, struct task_struct *p)
|
|
{
|
|
}
|
|
|
|
static inline void hrtick_update(struct rq *rq)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* The enqueue_task method is called before nr_running is
|
|
* increased. Here we update the fair scheduling stats and
|
|
* then put the task into the rbtree:
|
|
*/
|
|
static void
|
|
enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
|
|
{
|
|
struct cfs_rq *cfs_rq;
|
|
struct sched_entity *se = &p->se;
|
|
|
|
/*
|
|
* If in_iowait is set, the code below may not trigger any cpufreq
|
|
* utilization updates, so do it here explicitly with the IOWAIT flag
|
|
* passed.
|
|
*/
|
|
if (p->in_iowait)
|
|
cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_IOWAIT);
|
|
|
|
for_each_sched_entity(se) {
|
|
if (se->on_rq)
|
|
break;
|
|
cfs_rq = cfs_rq_of(se);
|
|
enqueue_entity(cfs_rq, se, flags);
|
|
|
|
/*
|
|
* end evaluation on encountering a throttled cfs_rq
|
|
*
|
|
* note: in the case of encountering a throttled cfs_rq we will
|
|
* post the final h_nr_running increment below.
|
|
*/
|
|
if (cfs_rq_throttled(cfs_rq))
|
|
break;
|
|
cfs_rq->h_nr_running++;
|
|
|
|
flags = ENQUEUE_WAKEUP;
|
|
}
|
|
|
|
for_each_sched_entity(se) {
|
|
cfs_rq = cfs_rq_of(se);
|
|
cfs_rq->h_nr_running++;
|
|
|
|
if (cfs_rq_throttled(cfs_rq))
|
|
break;
|
|
|
|
update_load_avg(se, UPDATE_TG);
|
|
update_cfs_shares(se);
|
|
}
|
|
|
|
if (!se)
|
|
add_nr_running(rq, 1);
|
|
|
|
hrtick_update(rq);
|
|
}
|
|
|
|
static void set_next_buddy(struct sched_entity *se);
|
|
|
|
/*
|
|
* The dequeue_task method is called before nr_running is
|
|
* decreased. We remove the task from the rbtree and
|
|
* update the fair scheduling stats:
|
|
*/
|
|
static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
|
|
{
|
|
struct cfs_rq *cfs_rq;
|
|
struct sched_entity *se = &p->se;
|
|
int task_sleep = flags & DEQUEUE_SLEEP;
|
|
|
|
for_each_sched_entity(se) {
|
|
cfs_rq = cfs_rq_of(se);
|
|
dequeue_entity(cfs_rq, se, flags);
|
|
|
|
/*
|
|
* end evaluation on encountering a throttled cfs_rq
|
|
*
|
|
* note: in the case of encountering a throttled cfs_rq we will
|
|
* post the final h_nr_running decrement below.
|
|
*/
|
|
if (cfs_rq_throttled(cfs_rq))
|
|
break;
|
|
cfs_rq->h_nr_running--;
|
|
|
|
/* Don't dequeue parent if it has other entities besides us */
|
|
if (cfs_rq->load.weight) {
|
|
/* Avoid re-evaluating load for this entity: */
|
|
se = parent_entity(se);
|
|
/*
|
|
* Bias pick_next to pick a task from this cfs_rq, as
|
|
* p is sleeping when it is within its sched_slice.
|
|
*/
|
|
if (task_sleep && se && !throttled_hierarchy(cfs_rq))
|
|
set_next_buddy(se);
|
|
break;
|
|
}
|
|
flags |= DEQUEUE_SLEEP;
|
|
}
|
|
|
|
for_each_sched_entity(se) {
|
|
cfs_rq = cfs_rq_of(se);
|
|
cfs_rq->h_nr_running--;
|
|
|
|
if (cfs_rq_throttled(cfs_rq))
|
|
break;
|
|
|
|
update_load_avg(se, UPDATE_TG);
|
|
update_cfs_shares(se);
|
|
}
|
|
|
|
if (!se)
|
|
sub_nr_running(rq, 1);
|
|
|
|
hrtick_update(rq);
|
|
}
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
/* Working cpumask for: load_balance, load_balance_newidle. */
|
|
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;
|
|
}
|
|
#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;
|
|
}
|
|
|
|
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 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(cpu_of(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(cpu_of(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(cpu_of(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(cpu_of(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(cpu);
|
|
|
|
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(cpu);
|
|
|
|
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;
|
|
}
|
|
|
|
static unsigned long capacity_orig_of(int cpu)
|
|
{
|
|
return cpu_rq(cpu)->cpu_capacity_orig;
|
|
}
|
|
|
|
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(cpu);
|
|
|
|
if (nr_running)
|
|
return load_avg / nr_running;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void record_wakee(struct task_struct *p)
|
|
{
|
|
/*
|
|
* Only decay a single time; tasks that have less then 1 wakeup per
|
|
* jiffy will not have built up many flips.
|
|
*/
|
|
if (time_after(jiffies, current->wakee_flip_decay_ts + HZ)) {
|
|
current->wakee_flips >>= 1;
|
|
current->wakee_flip_decay_ts = jiffies;
|
|
}
|
|
|
|
if (current->last_wakee != p) {
|
|
current->last_wakee = p;
|
|
current->wakee_flips++;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* 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 consolidating
|
|
* 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);
|
|
|
|
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 prev_cpu, int sync)
|
|
{
|
|
int this_cpu = smp_processor_id();
|
|
bool affine = false;
|
|
|
|
/*
|
|
* Common case: CPUs are in the same socket, and select_idle_sibling()
|
|
* will do its thing regardless of what we return:
|
|
*/
|
|
if (cpus_share_cache(prev_cpu, this_cpu))
|
|
affine = true;
|
|
else
|
|
affine = numa_wake_affine(sd, p, this_cpu, prev_cpu, sync);
|
|
|
|
schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts);
|
|
if (affine) {
|
|
schedstat_inc(sd->ttwu_move_affine);
|
|
schedstat_inc(p->se.statistics.nr_wakeups_affine);
|
|
}
|
|
|
|
return affine;
|
|
}
|
|
|
|
static inline int task_util(struct task_struct *p);
|
|
static int cpu_util_wake(int cpu, struct task_struct *p);
|
|
|
|
static unsigned long capacity_spare_wake(int cpu, struct task_struct *p)
|
|
{
|
|
return capacity_orig_of(cpu) - cpu_util_wake(cpu, p);
|
|
}
|
|
|
|
/*
|
|
* find_idlest_group finds and returns the least busy CPU group within the
|
|
* domain.
|
|
*/
|
|
static struct sched_group *
|
|
find_idlest_group(struct sched_domain *sd, struct task_struct *p,
|
|
int this_cpu, int sd_flag)
|
|
{
|
|
struct sched_group *idlest = NULL, *group = sd->groups;
|
|
struct sched_group *most_spare_sg = NULL;
|
|
unsigned long min_runnable_load = ULONG_MAX, this_runnable_load = 0;
|
|
unsigned long min_avg_load = ULONG_MAX, this_avg_load = 0;
|
|
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;
|
|
int local_group;
|
|
int i;
|
|
|
|
/* Skip over this group if it has no CPUs allowed */
|
|
if (!cpumask_intersects(sched_group_span(group),
|
|
&p->cpus_allowed))
|
|
continue;
|
|
|
|
local_group = cpumask_test_cpu(this_cpu,
|
|
sched_group_span(group));
|
|
|
|
/*
|
|
* Tally up the load of all CPUs in the group and find
|
|
* the group containing the CPU with most spare capacity.
|
|
*/
|
|
avg_load = 0;
|
|
runnable_load = 0;
|
|
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);
|
|
|
|
runnable_load += load;
|
|
|
|
avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs);
|
|
|
|
spare_cap = capacity_spare_wake(i, p);
|
|
|
|
if (spare_cap > max_spare_cap)
|
|
max_spare_cap = spare_cap;
|
|
}
|
|
|
|
/* Adjust by relative CPU capacity of the group */
|
|
avg_load = (avg_load * SCHED_CAPACITY_SCALE) /
|
|
group->sgc->capacity;
|
|
runnable_load = (runnable_load * SCHED_CAPACITY_SCALE) /
|
|
group->sgc->capacity;
|
|
|
|
if (local_group) {
|
|
this_runnable_load = runnable_load;
|
|
this_avg_load = avg_load;
|
|
this_spare = max_spare_cap;
|
|
} else {
|
|
if (min_runnable_load > (runnable_load + imbalance)) {
|
|
/*
|
|
* The runnable load is significantly smaller
|
|
* so we can pick this new cpu
|
|
*/
|
|
min_runnable_load = runnable_load;
|
|
min_avg_load = avg_load;
|
|
idlest = group;
|
|
} else if ((runnable_load < (min_runnable_load + imbalance)) &&
|
|
(100*min_avg_load > imbalance_scale*avg_load)) {
|
|
/*
|
|
* The runnable loads are close so take the
|
|
* blocked load into account through avg_load.
|
|
*/
|
|
min_avg_load = avg_load;
|
|
idlest = group;
|
|
}
|
|
|
|
if (most_spare < max_spare_cap) {
|
|
most_spare = max_spare_cap;
|
|
most_spare_sg = group;
|
|
}
|
|
}
|
|
} while (group = group->next, group != sd->groups);
|
|
|
|
/*
|
|
* The cross-over point between using spare capacity or least load
|
|
* is too conservative for high utilization tasks on partially
|
|
* utilized systems if we require spare_capacity > task_util(p),
|
|
* so we allow for some task stuffing by using
|
|
* spare_capacity > task_util(p)/2.
|
|
*
|
|
* Spare capacity can't be used for fork because the utilization has
|
|
* not been set yet, we must first select a rq to compute the initial
|
|
* utilization.
|
|
*/
|
|
if (sd_flag & SD_BALANCE_FORK)
|
|
goto skip_spare;
|
|
|
|
if (this_spare > task_util(p) / 2 &&
|
|
imbalance_scale*this_spare > 100*most_spare)
|
|
return NULL;
|
|
|
|
if (most_spare > task_util(p) / 2)
|
|
return most_spare_sg;
|
|
|
|
skip_spare:
|
|
if (!idlest)
|
|
return NULL;
|
|
|
|
if (min_runnable_load > (this_runnable_load + imbalance))
|
|
return NULL;
|
|
|
|
if ((this_runnable_load < (min_runnable_load + imbalance)) &&
|
|
(100*this_avg_load < imbalance_scale*min_avg_load))
|
|
return NULL;
|
|
|
|
return idlest;
|
|
}
|
|
|
|
/*
|
|
* find_idlest_cpu - find the idlest cpu among the cpus in group.
|
|
*/
|
|
static int
|
|
find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
|
|
{
|
|
unsigned long load, min_load = ULONG_MAX;
|
|
unsigned int min_exit_latency = UINT_MAX;
|
|
u64 latest_idle_timestamp = 0;
|
|
int least_loaded_cpu = this_cpu;
|
|
int shallowest_idle_cpu = -1;
|
|
int i;
|
|
|
|
/* Check if we have any choice: */
|
|
if (group->group_weight == 1)
|
|
return cpumask_first(sched_group_span(group));
|
|
|
|
/* Traverse only the allowed CPUs */
|
|
for_each_cpu_and(i, sched_group_span(group), &p->cpus_allowed) {
|
|
if (idle_cpu(i)) {
|
|
struct rq *rq = cpu_rq(i);
|
|
struct cpuidle_state *idle = idle_get_state(rq);
|
|
if (idle && idle->exit_latency < min_exit_latency) {
|
|
/*
|
|
* We give priority to a CPU whose idle state
|
|
* has the smallest exit latency irrespective
|
|
* of any idle timestamp.
|
|
*/
|
|
min_exit_latency = idle->exit_latency;
|
|
latest_idle_timestamp = rq->idle_stamp;
|
|
shallowest_idle_cpu = i;
|
|
} else if ((!idle || idle->exit_latency == min_exit_latency) &&
|
|
rq->idle_stamp > latest_idle_timestamp) {
|
|
/*
|
|
* If equal or no active idle state, then
|
|
* the most recently idled CPU might have
|
|
* a warmer cache.
|
|
*/
|
|
latest_idle_timestamp = rq->idle_stamp;
|
|
shallowest_idle_cpu = i;
|
|
}
|
|
} else if (shallowest_idle_cpu == -1) {
|
|
load = weighted_cpuload(i);
|
|
if (load < min_load || (load == min_load && i == this_cpu)) {
|
|
min_load = load;
|
|
least_loaded_cpu = i;
|
|
}
|
|
}
|
|
}
|
|
|
|
return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu;
|
|
}
|
|
|
|
#ifdef CONFIG_SCHED_SMT
|
|
|
|
static inline void set_idle_cores(int cpu, int val)
|
|
{
|
|
struct sched_domain_shared *sds;
|
|
|
|
sds = rcu_dereference(per_cpu(sd_llc_shared, cpu));
|
|
if (sds)
|
|
WRITE_ONCE(sds->has_idle_cores, val);
|
|
}
|
|
|
|
static inline bool test_idle_cores(int cpu, bool def)
|
|
{
|
|
struct sched_domain_shared *sds;
|
|
|
|
sds = rcu_dereference(per_cpu(sd_llc_shared, cpu));
|
|
if (sds)
|
|
return READ_ONCE(sds->has_idle_cores);
|
|
|
|
return def;
|
|
}
|
|
|
|
/*
|
|
* Scans the local SMT mask to see if the entire core is idle, and records this
|
|
* information in sd_llc_shared->has_idle_cores.
|
|
*
|
|
* Since SMT siblings share all cache levels, inspecting this limited remote
|
|
* state should be fairly cheap.
|
|
*/
|
|
void __update_idle_core(struct rq *rq)
|
|
{
|
|
int core = cpu_of(rq);
|
|
int cpu;
|
|
|
|
rcu_read_lock();
|
|
if (test_idle_cores(core, true))
|
|
goto unlock;
|
|
|
|
for_each_cpu(cpu, cpu_smt_mask(core)) {
|
|
if (cpu == core)
|
|
continue;
|
|
|
|
if (!idle_cpu(cpu))
|
|
goto unlock;
|
|
}
|
|
|
|
set_idle_cores(core, 1);
|
|
unlock:
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
/*
|
|
* Scan the entire LLC domain for idle cores; this dynamically switches off if
|
|
* there are no idle cores left in the system; tracked through
|
|
* sd_llc->shared->has_idle_cores and enabled through update_idle_core() above.
|
|
*/
|
|
static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int target)
|
|
{
|
|
struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
|
|
int core, cpu;
|
|
|
|
if (!static_branch_likely(&sched_smt_present))
|
|
return -1;
|
|
|
|
if (!test_idle_cores(target, false))
|
|
return -1;
|
|
|
|
cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed);
|
|
|
|
for_each_cpu_wrap(core, cpus, target) {
|
|
bool idle = true;
|
|
|
|
for_each_cpu(cpu, cpu_smt_mask(core)) {
|
|
cpumask_clear_cpu(cpu, cpus);
|
|
if (!idle_cpu(cpu))
|
|
idle = false;
|
|
}
|
|
|
|
if (idle)
|
|
return core;
|
|
}
|
|
|
|
/*
|
|
* Failed to find an idle core; stop looking for one.
|
|
*/
|
|
set_idle_cores(target, 0);
|
|
|
|
return -1;
|
|
}
|
|
|
|
/*
|
|
* Scan the local SMT mask for idle CPUs.
|
|
*/
|
|
static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
|
|
{
|
|
int cpu;
|
|
|
|
if (!static_branch_likely(&sched_smt_present))
|
|
return -1;
|
|
|
|
for_each_cpu(cpu, cpu_smt_mask(target)) {
|
|
if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
|
|
continue;
|
|
if (idle_cpu(cpu))
|
|
return cpu;
|
|
}
|
|
|
|
return -1;
|
|
}
|
|
|
|
#else /* CONFIG_SCHED_SMT */
|
|
|
|
static inline int select_idle_core(struct task_struct *p, struct sched_domain *sd, int target)
|
|
{
|
|
return -1;
|
|
}
|
|
|
|
static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
|
|
{
|
|
return -1;
|
|
}
|
|
|
|
#endif /* CONFIG_SCHED_SMT */
|
|
|
|
/*
|
|
* Scan the LLC domain for idle CPUs; this is dynamically regulated by
|
|
* comparing the average scan cost (tracked in sd->avg_scan_cost) against the
|
|
* average idle time for this rq (as found in rq->avg_idle).
|
|
*/
|
|
static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target)
|
|
{
|
|
struct sched_domain *this_sd;
|
|
u64 avg_cost, avg_idle;
|
|
u64 time, cost;
|
|
s64 delta;
|
|
int cpu, nr = INT_MAX;
|
|
|
|
this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
|
|
if (!this_sd)
|
|
return -1;
|
|
|
|
/*
|
|
* Due to large variance we need a large fuzz factor; hackbench in
|
|
* particularly is sensitive here.
|
|
*/
|
|
avg_idle = this_rq()->avg_idle / 512;
|
|
avg_cost = this_sd->avg_scan_cost + 1;
|
|
|
|
if (sched_feat(SIS_AVG_CPU) && avg_idle < avg_cost)
|
|
return -1;
|
|
|
|
if (sched_feat(SIS_PROP)) {
|
|
u64 span_avg = sd->span_weight * avg_idle;
|
|
if (span_avg > 4*avg_cost)
|
|
nr = div_u64(span_avg, avg_cost);
|
|
else
|
|
nr = 4;
|
|
}
|
|
|
|
time = local_clock();
|
|
|
|
for_each_cpu_wrap(cpu, sched_domain_span(sd), target) {
|
|
if (!--nr)
|
|
return -1;
|
|
if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
|
|
continue;
|
|
if (idle_cpu(cpu))
|
|
break;
|
|
}
|
|
|
|
time = local_clock() - time;
|
|
cost = this_sd->avg_scan_cost;
|
|
delta = (s64)(time - cost) / 8;
|
|
this_sd->avg_scan_cost += delta;
|
|
|
|
return cpu;
|
|
}
|
|
|
|
/*
|
|
* Try and locate an idle core/thread in the LLC cache domain.
|
|
*/
|
|
static int select_idle_sibling(struct task_struct *p, int prev, int target)
|
|
{
|
|
struct sched_domain *sd;
|
|
int i;
|
|
|
|
if (idle_cpu(target))
|
|
return target;
|
|
|
|
/*
|
|
* If the previous cpu is cache affine and idle, don't be stupid.
|
|
*/
|
|
if (prev != target && cpus_share_cache(prev, target) && idle_cpu(prev))
|
|
return prev;
|
|
|
|
sd = rcu_dereference(per_cpu(sd_llc, target));
|
|
if (!sd)
|
|
return target;
|
|
|
|
i = select_idle_core(p, sd, target);
|
|
if ((unsigned)i < nr_cpumask_bits)
|
|
return i;
|
|
|
|
i = select_idle_cpu(p, sd, target);
|
|
if ((unsigned)i < nr_cpumask_bits)
|
|
return i;
|
|
|
|
i = select_idle_smt(p, sd, target);
|
|
if ((unsigned)i < nr_cpumask_bits)
|
|
return i;
|
|
|
|
return target;
|
|
}
|
|
|
|
/*
|
|
* 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 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 cpu_util(int cpu)
|
|
{
|
|
unsigned long util = cpu_rq(cpu)->cfs.avg.util_avg;
|
|
unsigned long capacity = capacity_orig_of(cpu);
|
|
|
|
return (util >= capacity) ? capacity : util;
|
|
}
|
|
|
|
static inline int task_util(struct task_struct *p)
|
|
{
|
|
return p->se.avg.util_avg;
|
|
}
|
|
|
|
/*
|
|
* cpu_util_wake: Compute cpu utilization with any contributions from
|
|
* the waking task p removed.
|
|
*/
|
|
static int cpu_util_wake(int cpu, struct task_struct *p)
|
|
{
|
|
unsigned long util, capacity;
|
|
|
|
/* Task has no contribution or is new */
|
|
if (cpu != task_cpu(p) || !p->se.avg.last_update_time)
|
|
return cpu_util(cpu);
|
|
|
|
capacity = capacity_orig_of(cpu);
|
|
util = max_t(long, cpu_rq(cpu)->cfs.avg.util_avg - task_util(p), 0);
|
|
|
|
return (util >= capacity) ? capacity : util;
|
|
}
|
|
|
|
/*
|
|
* Disable WAKE_AFFINE in the case where task @p doesn't fit in the
|
|
* capacity of either the waking CPU @cpu or the previous CPU @prev_cpu.
|
|
*
|
|
* In that case WAKE_AFFINE doesn't make sense and we'll let
|
|
* BALANCE_WAKE sort things out.
|
|
*/
|
|
static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
|
|
{
|
|
long min_cap, max_cap;
|
|
|
|
min_cap = min(capacity_orig_of(prev_cpu), capacity_orig_of(cpu));
|
|
max_cap = cpu_rq(cpu)->rd->max_cpu_capacity;
|
|
|
|
/* Minimum capacity is close to max, no need to abort wake_affine */
|
|
if (max_cap - min_cap < max_cap >> 3)
|
|
return 0;
|
|
|
|
/* Bring task utilization in sync with prev_cpu */
|
|
sync_entity_load_avg(&p->se);
|
|
|
|
return min_cap * 1024 < task_util(p) * capacity_margin;
|
|
}
|
|
|
|
/*
|
|
* select_task_rq_fair: Select target runqueue for the waking task in domains
|
|
* that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
|
|
* SD_BALANCE_FORK, or SD_BALANCE_EXEC.
|
|
*
|
|
* Balances load by selecting the idlest cpu in the idlest group, or under
|
|
* certain conditions an idle sibling cpu if the domain has SD_WAKE_AFFINE set.
|
|
*
|
|
* Returns the target cpu number.
|
|
*
|
|
* preempt must be disabled.
|
|
*/
|
|
static int
|
|
select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags)
|
|
{
|
|
struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
|
|
int cpu = smp_processor_id();
|
|
int new_cpu = prev_cpu;
|
|
int want_affine = 0;
|
|
int sync = wake_flags & WF_SYNC;
|
|
|
|
if (sd_flag & SD_BALANCE_WAKE) {
|
|
record_wakee(p);
|
|
want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu)
|
|
&& cpumask_test_cpu(cpu, &p->cpus_allowed);
|
|
}
|
|
|
|
rcu_read_lock();
|
|
for_each_domain(cpu, tmp) {
|
|
if (!(tmp->flags & SD_LOAD_BALANCE))
|
|
break;
|
|
|
|
/*
|
|
* If both cpu and prev_cpu are part of this domain,
|
|
* cpu is a valid SD_WAKE_AFFINE target.
|
|
*/
|
|
if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
|
|
cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
|
|
affine_sd = tmp;
|
|
break;
|
|
}
|
|
|
|
if (tmp->flags & sd_flag)
|
|
sd = tmp;
|
|
else if (!want_affine)
|
|
break;
|
|
}
|
|
|
|
if (affine_sd) {
|
|
sd = NULL; /* Prefer wake_affine over balance flags */
|
|
if (cpu == prev_cpu)
|
|
goto pick_cpu;
|
|
|
|
if (wake_affine(affine_sd, p, prev_cpu, sync))
|
|
new_cpu = cpu;
|
|
}
|
|
|
|
if (!sd) {
|
|
pick_cpu:
|
|
if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */
|
|
new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
|
|
|
|
} else while (sd) {
|
|
struct sched_group *group;
|
|
int weight;
|
|
|
|
if (!(sd->flags & sd_flag)) {
|
|
sd = sd->child;
|
|
continue;
|
|
}
|
|
|
|
group = find_idlest_group(sd, p, cpu, sd_flag);
|
|
if (!group) {
|
|
sd = sd->child;
|
|
continue;
|
|
}
|
|
|
|
new_cpu = find_idlest_cpu(group, p, cpu);
|
|
if (new_cpu == -1 || new_cpu == cpu) {
|
|
/* Now try balancing at a lower domain level of cpu */
|
|
sd = sd->child;
|
|
continue;
|
|
}
|
|
|
|
/* Now try balancing at a lower domain level of new_cpu */
|
|
cpu = new_cpu;
|
|
weight = sd->span_weight;
|
|
sd = NULL;
|
|
for_each_domain(cpu, tmp) {
|
|
if (weight <= tmp->span_weight)
|
|
break;
|
|
if (tmp->flags & sd_flag)
|
|
sd = tmp;
|
|
}
|
|
/* while loop will break here if sd == NULL */
|
|
}
|
|
rcu_read_unlock();
|
|
|
|
return new_cpu;
|
|
}
|
|
|
|
/*
|
|
* Called immediately before a task is migrated to a new cpu; task_cpu(p) and
|
|
* cfs_rq_of(p) references at time of call are still valid and identify the
|
|
* previous cpu. The caller guarantees p->pi_lock or task_rq(p)->lock is held.
|
|
*/
|
|
static void migrate_task_rq_fair(struct task_struct *p)
|
|
{
|
|
/*
|
|
* As blocked tasks retain absolute vruntime the migration needs to
|
|
* deal with this by subtracting the old and adding the new
|
|
* min_vruntime -- the latter is done by enqueue_entity() when placing
|
|
* the task on the new runqueue.
|
|
*/
|
|
if (p->state == TASK_WAKING) {
|
|
struct sched_entity *se = &p->se;
|
|
struct cfs_rq *cfs_rq = cfs_rq_of(se);
|
|
u64 min_vruntime;
|
|
|
|
#ifndef CONFIG_64BIT
|
|
u64 min_vruntime_copy;
|
|
|
|
do {
|
|
min_vruntime_copy = cfs_rq->min_vruntime_copy;
|
|
smp_rmb();
|
|
min_vruntime = cfs_rq->min_vruntime;
|
|
} while (min_vruntime != min_vruntime_copy);
|
|
#else
|
|
min_vruntime = cfs_rq->min_vruntime;
|
|
#endif
|
|
|
|
se->vruntime -= min_vruntime;
|
|
}
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
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 */
|
|
p->se.exec_start = 0;
|
|
}
|
|
|
|
static void task_dead_fair(struct task_struct *p)
|
|
{
|
|
remove_entity_load_avg(&p->se);
|
|
}
|
|
#endif /* CONFIG_SMP */
|
|
|
|
static unsigned long
|
|
wakeup_gran(struct sched_entity *curr, struct sched_entity *se)
|
|
{
|
|
unsigned long gran = sysctl_sched_wakeup_granularity;
|
|
|
|
/*
|
|
* Since its curr running now, convert the gran from real-time
|
|
* to virtual-time in his units.
|
|
*
|
|
* By using 'se' instead of 'curr' we penalize light tasks, so
|
|
* they get preempted easier. That is, if 'se' < 'curr' then
|
|
* the resulting gran will be larger, therefore penalizing the
|
|
* lighter, if otoh 'se' > 'curr' then the resulting gran will
|
|
* be smaller, again penalizing the lighter task.
|
|
*
|
|
* This is especially important for buddies when the leftmost
|
|
* task is higher priority than the buddy.
|
|
*/
|
|
return calc_delta_fair(gran, se);
|
|
}
|
|
|
|
/*
|
|
* Should 'se' preempt 'curr'.
|
|
*
|
|
* |s1
|
|
* |s2
|
|
* |s3
|
|
* g
|
|
* |<--->|c
|
|
*
|
|
* w(c, s1) = -1
|
|
* w(c, s2) = 0
|
|
* w(c, s3) = 1
|
|
*
|
|
*/
|
|
static int
|
|
wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
|
|
{
|
|
s64 gran, vdiff = curr->vruntime - se->vruntime;
|
|
|
|
if (vdiff <= 0)
|
|
return -1;
|
|
|
|
gran = wakeup_gran(curr, se);
|
|
if (vdiff > gran)
|
|
return 1;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void set_last_buddy(struct sched_entity *se)
|
|
{
|
|
if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
|
|
return;
|
|
|
|
for_each_sched_entity(se) {
|
|
if (SCHED_WARN_ON(!se->on_rq))
|
|
return;
|
|
cfs_rq_of(se)->last = se;
|
|
}
|
|
}
|
|
|
|
static void set_next_buddy(struct sched_entity *se)
|
|
{
|
|
if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
|
|
return;
|
|
|
|
for_each_sched_entity(se) {
|
|
if (SCHED_WARN_ON(!se->on_rq))
|
|
return;
|
|
cfs_rq_of(se)->next = se;
|
|
}
|
|
}
|
|
|
|
static void set_skip_buddy(struct sched_entity *se)
|
|
{
|
|
for_each_sched_entity(se)
|
|
cfs_rq_of(se)->skip = se;
|
|
}
|
|
|
|
/*
|
|
* Preempt the current task with a newly woken task if needed:
|
|
*/
|
|
static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
|
|
{
|
|
struct task_struct *curr = rq->curr;
|
|
struct sched_entity *se = &curr->se, *pse = &p->se;
|
|
struct cfs_rq *cfs_rq = task_cfs_rq(curr);
|
|
int scale = cfs_rq->nr_running >= sched_nr_latency;
|
|
int next_buddy_marked = 0;
|
|
|
|
if (unlikely(se == pse))
|
|
return;
|
|
|
|
/*
|
|
* This is possible from callers such as attach_tasks(), in which we
|
|
* unconditionally check_prempt_curr() after an enqueue (which may have
|
|
* lead to a throttle). This both saves work and prevents false
|
|
* next-buddy nomination below.
|
|
*/
|
|
if (unlikely(throttled_hierarchy(cfs_rq_of(pse))))
|
|
return;
|
|
|
|
if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK)) {
|
|
set_next_buddy(pse);
|
|
next_buddy_marked = 1;
|
|
}
|
|
|
|
/*
|
|
* We can come here with TIF_NEED_RESCHED already set from new task
|
|
* wake up path.
|
|
*
|
|
* Note: this also catches the edge-case of curr being in a throttled
|
|
* group (e.g. via set_curr_task), since update_curr() (in the
|
|
* enqueue of curr) will have resulted in resched being set. This
|
|
* prevents us from potentially nominating it as a false LAST_BUDDY
|
|
* below.
|
|
*/
|
|
if (test_tsk_need_resched(curr))
|
|
return;
|
|
|
|
/* Idle tasks are by definition preempted by non-idle tasks. */
|
|
if (unlikely(curr->policy == SCHED_IDLE) &&
|
|
likely(p->policy != SCHED_IDLE))
|
|
goto preempt;
|
|
|
|
/*
|
|
* Batch and idle tasks do not preempt non-idle tasks (their preemption
|
|
* is driven by the tick):
|
|
*/
|
|
if (unlikely(p->policy != SCHED_NORMAL) || !sched_feat(WAKEUP_PREEMPTION))
|
|
return;
|
|
|
|
find_matching_se(&se, &pse);
|
|
update_curr(cfs_rq_of(se));
|
|
BUG_ON(!pse);
|
|
if (wakeup_preempt_entity(se, pse) == 1) {
|
|
/*
|
|
* Bias pick_next to pick the sched entity that is
|
|
* triggering this preemption.
|
|
*/
|
|
if (!next_buddy_marked)
|
|
set_next_buddy(pse);
|
|
goto preempt;
|
|
}
|
|
|
|
return;
|
|
|
|
preempt:
|
|
resched_curr(rq);
|
|
/*
|
|
* Only set the backward buddy when the current task is still
|
|
* on the rq. This can happen when a wakeup gets interleaved
|
|
* with schedule on the ->pre_schedule() or idle_balance()
|
|
* point, either of which can * drop the rq lock.
|
|
*
|
|
* Also, during early boot the idle thread is in the fair class,
|
|
* for obvious reasons its a bad idea to schedule back to it.
|
|
*/
|
|
if (unlikely(!se->on_rq || curr == rq->idle))
|
|
return;
|
|
|
|
if (sched_feat(LAST_BUDDY) && scale && entity_is_task(se))
|
|
set_last_buddy(se);
|
|
}
|
|
|
|
static struct task_struct *
|
|
pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
|
|
{
|
|
struct cfs_rq *cfs_rq = &rq->cfs;
|
|
struct sched_entity *se;
|
|
struct task_struct *p;
|
|
int new_tasks;
|
|
|
|
again:
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
if (!cfs_rq->nr_running)
|
|
goto idle;
|
|
|
|
if (prev->sched_class != &fair_sched_class)
|
|
goto simple;
|
|
|
|
/*
|
|
* Because of the set_next_buddy() in dequeue_task_fair() it is rather
|
|
* likely that a next task is from the same cgroup as the current.
|
|
*
|
|
* Therefore attempt to avoid putting and setting the entire cgroup
|
|
* hierarchy, only change the part that actually changes.
|
|
*/
|
|
|
|
do {
|
|
struct sched_entity *curr = cfs_rq->curr;
|
|
|
|
/*
|
|
* Since we got here without doing put_prev_entity() we also
|
|
* have to consider cfs_rq->curr. If it is still a runnable
|
|
* entity, update_curr() will update its vruntime, otherwise
|
|
* forget we've ever seen it.
|
|
*/
|
|
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;
|
|
}
|
|
|
|
se = pick_next_entity(cfs_rq, curr);
|
|
cfs_rq = group_cfs_rq(se);
|
|
} while (cfs_rq);
|
|
|
|
p = task_of(se);
|
|
|
|
/*
|
|
* Since we haven't yet done put_prev_entity and if the selected task
|
|
* is a different task than we started out with, try and touch the
|
|
* least amount of cfs_rqs.
|
|
*/
|
|
if (prev != p) {
|
|
struct sched_entity *pse = &prev->se;
|
|
|
|
while (!(cfs_rq = is_same_group(se, pse))) {
|
|
int se_depth = se->depth;
|
|
int pse_depth = pse->depth;
|
|
|
|
if (se_depth <= pse_depth) {
|
|
put_prev_entity(cfs_rq_of(pse), pse);
|
|
pse = parent_entity(pse);
|
|
}
|
|
if (se_depth >= pse_depth) {
|
|
set_next_entity(cfs_rq_of(se), se);
|
|
se = parent_entity(se);
|
|
}
|
|
}
|
|
|
|
put_prev_entity(cfs_rq, pse);
|
|
set_next_entity(cfs_rq, se);
|
|
}
|
|
|
|
if (hrtick_enabled(rq))
|
|
hrtick_start_fair(rq, p);
|
|
|
|
return p;
|
|
simple:
|
|
cfs_rq = &rq->cfs;
|
|
#endif
|
|
|
|
if (!cfs_rq->nr_running)
|
|
goto idle;
|
|
|
|
put_prev_task(rq, prev);
|
|
|
|
do {
|
|
se = pick_next_entity(cfs_rq, NULL);
|
|
set_next_entity(cfs_rq, se);
|
|
cfs_rq = group_cfs_rq(se);
|
|
} while (cfs_rq);
|
|
|
|
p = task_of(se);
|
|
|
|
if (hrtick_enabled(rq))
|
|
hrtick_start_fair(rq, p);
|
|
|
|
return p;
|
|
|
|
idle:
|
|
new_tasks = idle_balance(rq, rf);
|
|
|
|
/*
|
|
* Because idle_balance() releases (and re-acquires) rq->lock, it is
|
|
* possible for any higher priority task to appear. In that case we
|
|
* must re-start the pick_next_entity() loop.
|
|
*/
|
|
if (new_tasks < 0)
|
|
return RETRY_TASK;
|
|
|
|
if (new_tasks > 0)
|
|
goto again;
|
|
|
|
return NULL;
|
|
}
|
|
|
|
/*
|
|
* Account for a descheduled task:
|
|
*/
|
|
static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
|
|
{
|
|
struct sched_entity *se = &prev->se;
|
|
struct cfs_rq *cfs_rq;
|
|
|
|
for_each_sched_entity(se) {
|
|
cfs_rq = cfs_rq_of(se);
|
|
put_prev_entity(cfs_rq, se);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* sched_yield() is very simple
|
|
*
|
|
* The magic of dealing with the ->skip buddy is in pick_next_entity.
|
|
*/
|
|
static void yield_task_fair(struct rq *rq)
|
|
{
|
|
struct task_struct *curr = rq->curr;
|
|
struct cfs_rq *cfs_rq = task_cfs_rq(curr);
|
|
struct sched_entity *se = &curr->se;
|
|
|
|
/*
|
|
* Are we the only task in the tree?
|
|
*/
|
|
if (unlikely(rq->nr_running == 1))
|
|
return;
|
|
|
|
clear_buddies(cfs_rq, se);
|
|
|
|
if (curr->policy != SCHED_BATCH) {
|
|
update_rq_clock(rq);
|
|
/*
|
|
* Update run-time statistics of the 'current'.
|
|
*/
|
|
update_curr(cfs_rq);
|
|
/*
|
|
* Tell update_rq_clock() that we've just updated,
|
|
* so we don't do microscopic update in schedule()
|
|
* and double the fastpath cost.
|
|
*/
|
|
rq_clock_skip_update(rq, true);
|
|
}
|
|
|
|
set_skip_buddy(se);
|
|
}
|
|
|
|
static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preempt)
|
|
{
|
|
struct sched_entity *se = &p->se;
|
|
|
|
/* throttled hierarchies are not runnable */
|
|
if (!se->on_rq || throttled_hierarchy(cfs_rq_of(se)))
|
|
return false;
|
|
|
|
/* Tell the scheduler that we'd really like pse to run next. */
|
|
set_next_buddy(se);
|
|
|
|
yield_task_fair(rq);
|
|
|
|
return true;
|
|
}
|
|
|
|
#ifdef CONFIG_SMP
|
|
/**************************************************
|
|
* Fair scheduling class load-balancing methods.
|
|
*
|
|
* BASICS
|
|
*
|
|
* The purpose of load-balancing is to achieve the same basic fairness the
|
|
* per-cpu scheduler provides, namely provide a proportional amount of compute
|
|
* time to each task. This is expressed in the following equation:
|
|
*
|
|
* W_i,n/P_i == W_j,n/P_j for all i,j (1)
|
|
*
|
|
* Where W_i,n is the n-th weight average for cpu i. The instantaneous weight
|
|
* W_i,0 is defined as:
|
|
*
|
|
* W_i,0 = \Sum_j w_i,j (2)
|
|
*
|
|
* Where w_i,j is the weight of the j-th runnable task on cpu i. This weight
|
|
* is derived from the nice value as per sched_prio_to_weight[].
|
|
*
|
|
* The weight average is an exponential decay average of the instantaneous
|
|
* weight:
|
|
*
|
|
* W'_i,n = (2^n - 1) / 2^n * W_i,n + 1 / 2^n * W_i,0 (3)
|
|
*
|
|
* C_i is the compute capacity of cpu i, typically it is the
|
|
* fraction of 'recent' time available for SCHED_OTHER task execution. But it
|
|
* can also include other factors [XXX].
|
|
*
|
|
* To achieve this balance we define a measure of imbalance which follows
|
|
* directly from (1):
|
|
*
|
|
* imb_i,j = max{ avg(W/C), W_i/C_i } - min{ avg(W/C), W_j/C_j } (4)
|
|
*
|
|
* We them move tasks around to minimize the imbalance. In the continuous
|
|
* function space it is obvious this converges, in the discrete case we get
|
|
* a few fun cases generally called infeasible weight scenarios.
|
|
*
|
|
* [XXX expand on:
|
|
* - infeasible weights;
|
|
* - local vs global optima in the discrete case. ]
|
|
*
|
|
*
|
|
* SCHED DOMAINS
|
|
*
|
|
* In order to solve the imbalance equation (4), and avoid the obvious O(n^2)
|
|
* for all i,j solution, we create a tree of cpus that follows the hardware
|
|
* topology where each level pairs two lower groups (or better). This results
|
|
* in O(log n) layers. Furthermore we reduce the number of cpus going up the
|
|
* tree to only the first of the previous level and we decrease the frequency
|
|
* of load-balance at each level inv. proportional to the number of cpus in
|
|
* the groups.
|
|
*
|
|
* This yields:
|
|
*
|
|
* log_2 n 1 n
|
|
* \Sum { --- * --- * 2^i } = O(n) (5)
|
|
* i = 0 2^i 2^i
|
|
* `- size of each group
|
|
* | | `- number of cpus doing load-balance
|
|
* | `- freq
|
|
* `- sum over all levels
|
|
*
|
|
* Coupled with a limit on how many tasks we can migrate every balance pass,
|
|
* this makes (5) the runtime complexity of the balancer.
|
|
*
|
|
* An important property here is that each CPU is still (indirectly) connected
|
|
* to every other cpu in at most O(log n) steps:
|
|
*
|
|
* The adjacency matrix of the resulting graph is given by:
|
|
*
|
|
* log_2 n
|
|
* A_i,j = \Union (i % 2^k == 0) && i / 2^(k+1) == j / 2^(k+1) (6)
|
|
* k = 0
|
|
*
|
|
* And you'll find that:
|
|
*
|
|
* A^(log_2 n)_i,j != 0 for all i,j (7)
|
|
*
|
|
* Showing there's indeed a path between every cpu in at most O(log n) steps.
|
|
* The task movement gives a factor of O(m), giving a convergence complexity
|
|
* of:
|
|
*
|
|
* O(nm log n), n := nr_cpus, m := nr_tasks (8)
|
|
*
|
|
*
|
|
* WORK CONSERVING
|
|
*
|
|
* In order to avoid CPUs going idle while there's still work to do, new idle
|
|
* balancing is more aggressive and has the newly idle cpu iterate up the domain
|
|
* tree itself instead of relying on other CPUs to bring it work.
|
|
*
|
|
* This adds some complexity to both (5) and (8) but it reduces the total idle
|
|
* time.
|
|
*
|
|
* [XXX more?]
|
|
*
|
|
*
|
|
* CGROUPS
|
|
*
|
|
* Cgroups make a horror show out of (2), instead of a simple sum we get:
|
|
*
|
|
* s_k,i
|
|
* W_i,0 = \Sum_j \Prod_k w_k * ----- (9)
|
|
* S_k
|
|
*
|
|
* Where
|
|
*
|
|
* s_k,i = \Sum_j w_i,j,k and S_k = \Sum_i s_k,i (10)
|
|
*
|
|
* w_i,j,k is the weight of the j-th runnable task in the k-th cgroup on cpu i.
|
|
*
|
|
* The big problem is S_k, its a global sum needed to compute a local (W_i)
|
|
* property.
|
|
*
|
|
* [XXX write more on how we solve this.. _after_ merging pjt's patches that
|
|
* rewrite all of this once again.]
|
|
*/
|
|
|
|
static unsigned long __read_mostly max_load_balance_interval = HZ/10;
|
|
|
|
enum fbq_type { regular, remote, all };
|
|
|
|
#define LBF_ALL_PINNED 0x01
|
|
#define LBF_NEED_BREAK 0x02
|
|
#define LBF_DST_PINNED 0x04
|
|
#define LBF_SOME_PINNED 0x08
|
|
|
|
struct lb_env {
|
|
struct sched_domain *sd;
|
|
|
|
struct rq *src_rq;
|
|
int src_cpu;
|
|
|
|
int dst_cpu;
|
|
struct rq *dst_rq;
|
|
|
|
struct cpumask *dst_grpmask;
|
|
int new_dst_cpu;
|
|
enum cpu_idle_type idle;
|
|
long imbalance;
|
|
/* The set of CPUs under consideration for load-balancing */
|
|
struct cpumask *cpus;
|
|
|
|
unsigned int flags;
|
|
|
|
unsigned int loop;
|
|
unsigned int loop_break;
|
|
unsigned int loop_max;
|
|
|
|
enum fbq_type fbq_type;
|
|
struct list_head tasks;
|
|
};
|
|
|
|
/*
|
|
* Is this task likely cache-hot:
|
|
*/
|
|
static int task_hot(struct task_struct *p, struct lb_env *env)
|
|
{
|
|
s64 delta;
|
|
|
|
lockdep_assert_held(&env->src_rq->lock);
|
|
|
|
if (p->sched_class != &fair_sched_class)
|
|
return 0;
|
|
|
|
if (unlikely(p->policy == SCHED_IDLE))
|
|
return 0;
|
|
|
|
/*
|
|
* Buddy candidates are cache hot:
|
|
*/
|
|
if (sched_feat(CACHE_HOT_BUDDY) && env->dst_rq->nr_running &&
|
|
(&p->se == cfs_rq_of(&p->se)->next ||
|
|
&p->se == cfs_rq_of(&p->se)->last))
|
|
return 1;
|
|
|
|
if (sysctl_sched_migration_cost == -1)
|
|
return 1;
|
|
if (sysctl_sched_migration_cost == 0)
|
|
return 0;
|
|
|
|
delta = rq_clock_task(env->src_rq) - p->se.exec_start;
|
|
|
|
return delta < (s64)sysctl_sched_migration_cost;
|
|
}
|
|
|
|
#ifdef CONFIG_NUMA_BALANCING
|
|
/*
|
|
* 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 (!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 -1;
|
|
|
|
/* 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 0;
|
|
|
|
/* Leaving a core idle is often worse than degrading locality. */
|
|
if (env->idle != CPU_NOT_IDLE)
|
|
return -1;
|
|
|
|
if (numa_group) {
|
|
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);
|
|
}
|
|
|
|
return dst_faults < src_faults;
|
|
}
|
|
|
|
#else
|
|
static inline int migrate_degrades_locality(struct task_struct *p,
|
|
struct lb_env *env)
|
|
{
|
|
return -1;
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
|
|
*/
|
|
static
|
|
int can_migrate_task(struct task_struct *p, struct lb_env *env)
|
|
{
|
|
int tsk_cache_hot;
|
|
|
|
lockdep_assert_held(&env->src_rq->lock);
|
|
|
|
/*
|
|
* We do not migrate tasks that are:
|
|
* 1) throttled_lb_pair, or
|
|
* 2) cannot be migrated to this CPU due to cpus_allowed, 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)) {
|
|
int cpu;
|
|
|
|
schedstat_inc(p->se.statistics.nr_failed_migrations_affine);
|
|
|
|
env->flags |= LBF_SOME_PINNED;
|
|
|
|
/*
|
|
* Remember if this task can be migrated to any other cpu in
|
|
* our sched_group. We may want to revisit it if we couldn't
|
|
* meet load balance goals by pulling other tasks on src_cpu.
|
|
*
|
|
* Avoid computing new_dst_cpu for NEWLY_IDLE or if we have
|
|
* already computed one in current iteration.
|
|
*/
|
|
if (env->idle == CPU_NEWLY_IDLE || (env->flags & LBF_DST_PINNED))
|
|
return 0;
|
|
|
|
/* 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)) {
|
|
env->flags |= LBF_DST_PINNED;
|
|
env->new_dst_cpu = cpu;
|
|
break;
|
|
}
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
/* Record that we found atleast one task that could run on dst_cpu */
|
|
env->flags &= ~LBF_ALL_PINNED;
|
|
|
|
if (task_running(env->src_rq, p)) {
|
|
schedstat_inc(p->se.statistics.nr_failed_migrations_running);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Aggressive migration if:
|
|
* 1) destination numa is preferred
|
|
* 2) task is cache cold, or
|
|
* 3) too many balance attempts have failed.
|
|
*/
|
|
tsk_cache_hot = migrate_degrades_locality(p, env);
|
|
if (tsk_cache_hot == -1)
|
|
tsk_cache_hot = task_hot(p, env);
|
|
|
|
if (tsk_cache_hot <= 0 ||
|
|
env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
|
|
if (tsk_cache_hot == 1) {
|
|
schedstat_inc(env->sd->lb_hot_gained[env->idle]);
|
|
schedstat_inc(p->se.statistics.nr_forced_migrations);
|
|
}
|
|
return 1;
|
|
}
|
|
|
|
schedstat_inc(p->se.statistics.nr_failed_migrations_hot);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* detach_task() -- detach the task for the migration specified in env
|
|
*/
|
|
static void detach_task(struct task_struct *p, struct lb_env *env)
|
|
{
|
|
lockdep_assert_held(&env->src_rq->lock);
|
|
|
|
p->on_rq = TASK_ON_RQ_MIGRATING;
|
|
deactivate_task(env->src_rq, p, DEQUEUE_NOCLOCK);
|
|
set_task_cpu(p, env->dst_cpu);
|
|
}
|
|
|
|
/*
|
|
* detach_one_task() -- tries to dequeue exactly one task from env->src_rq, as
|
|
* part of active balancing operations within "domain".
|
|
*
|
|
* Returns a task if successful and NULL otherwise.
|
|
*/
|
|
static struct task_struct *detach_one_task(struct lb_env *env)
|
|
{
|
|
struct task_struct *p, *n;
|
|
|
|
lockdep_assert_held(&env->src_rq->lock);
|
|
|
|
list_for_each_entry_safe(p, n, &env->src_rq->cfs_tasks, se.group_node) {
|
|
if (!can_migrate_task(p, env))
|
|
continue;
|
|
|
|
detach_task(p, env);
|
|
|
|
/*
|
|
* Right now, this is only the second place where
|
|
* lb_gained[env->idle] is updated (other is detach_tasks)
|
|
* so we can safely collect stats here rather than
|
|
* inside detach_tasks().
|
|
*/
|
|
schedstat_inc(env->sd->lb_gained[env->idle]);
|
|
return p;
|
|
}
|
|
return NULL;
|
|
}
|
|
|
|
static const unsigned int sched_nr_migrate_break = 32;
|
|
|
|
/*
|
|
* detach_tasks() -- tries to detach up to imbalance weighted load from
|
|
* busiest_rq, as part of a balancing operation within domain "sd".
|
|
*
|
|
* Returns number of detached tasks if successful and 0 otherwise.
|
|
*/
|
|
static int detach_tasks(struct lb_env *env)
|
|
{
|
|
struct list_head *tasks = &env->src_rq->cfs_tasks;
|
|
struct task_struct *p;
|
|
unsigned long load;
|
|
int detached = 0;
|
|
|
|
lockdep_assert_held(&env->src_rq->lock);
|
|
|
|
if (env->imbalance <= 0)
|
|
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++;
|
|
/* We've more or less seen every task there is, call it quits */
|
|
if (env->loop > env->loop_max)
|
|
break;
|
|
|
|
/* take a breather every nr_migrate tasks */
|
|
if (env->loop > env->loop_break) {
|
|
env->loop_break += sched_nr_migrate_break;
|
|
env->flags |= LBF_NEED_BREAK;
|
|
break;
|
|
}
|
|
|
|
if (!can_migrate_task(p, env))
|
|
goto next;
|
|
|
|
load = task_h_load(p);
|
|
|
|
if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed)
|
|
goto next;
|
|
|
|
if ((load / 2) > env->imbalance)
|
|
goto next;
|
|
|
|
detach_task(p, env);
|
|
list_add(&p->se.group_node, &env->tasks);
|
|
|
|
detached++;
|
|
env->imbalance -= load;
|
|
|
|
#ifdef CONFIG_PREEMPT
|
|
/*
|
|
* NEWIDLE balancing is a source of latency, so preemptible
|
|
* kernels will stop after the first task is detached to minimize
|
|
* the critical section.
|
|
*/
|
|
if (env->idle == CPU_NEWLY_IDLE)
|
|
break;
|
|
#endif
|
|
|
|
/*
|
|
* We only want to steal up to the prescribed amount of
|
|
* weighted load.
|
|
*/
|
|
if (env->imbalance <= 0)
|
|
break;
|
|
|
|
continue;
|
|
next:
|
|
list_move_tail(&p->se.group_node, tasks);
|
|
}
|
|
|
|
/*
|
|
* Right now, this is one of only two places we collect this stat
|
|
* so we can safely collect detach_one_task() stats here rather
|
|
* than inside detach_one_task().
|
|
*/
|
|
schedstat_add(env->sd->lb_gained[env->idle], detached);
|
|
|
|
return detached;
|
|
}
|
|
|
|
/*
|
|
* attach_task() -- attach the task detached by detach_task() to its new rq.
|
|
*/
|
|
static void attach_task(struct rq *rq, struct task_struct *p)
|
|
{
|
|
lockdep_assert_held(&rq->lock);
|
|
|
|
BUG_ON(task_rq(p) != rq);
|
|
activate_task(rq, p, ENQUEUE_NOCLOCK);
|
|
p->on_rq = TASK_ON_RQ_QUEUED;
|
|
check_preempt_curr(rq, p, 0);
|
|
}
|
|
|
|
/*
|
|
* attach_one_task() -- attaches the task returned from detach_one_task() to
|
|
* its new rq.
|
|
*/
|
|
static void attach_one_task(struct rq *rq, struct task_struct *p)
|
|
{
|
|
struct rq_flags rf;
|
|
|
|
rq_lock(rq, &rf);
|
|
update_rq_clock(rq);
|
|
attach_task(rq, p);
|
|
rq_unlock(rq, &rf);
|
|
}
|
|
|
|
/*
|
|
* attach_tasks() -- attaches all tasks detached by detach_tasks() to their
|
|
* new rq.
|
|
*/
|
|
static void attach_tasks(struct lb_env *env)
|
|
{
|
|
struct list_head *tasks = &env->tasks;
|
|
struct task_struct *p;
|
|
struct rq_flags rf;
|
|
|
|
rq_lock(env->dst_rq, &rf);
|
|
update_rq_clock(env->dst_rq);
|
|
|
|
while (!list_empty(tasks)) {
|
|
p = list_first_entry(tasks, struct task_struct, se.group_node);
|
|
list_del_init(&p->se.group_node);
|
|
|
|
attach_task(env->dst_rq, p);
|
|
}
|
|
|
|
rq_unlock(env->dst_rq, &rf);
|
|
}
|
|
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
|
|
static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
|
|
{
|
|
if (cfs_rq->load.weight)
|
|
return false;
|
|
|
|
if (cfs_rq->avg.load_sum)
|
|
return false;
|
|
|
|
if (cfs_rq->avg.util_sum)
|
|
return false;
|
|
|
|
if (cfs_rq->runnable_load_sum)
|
|
return false;
|
|
|
|
return true;
|
|
}
|
|
|
|
static void update_blocked_averages(int cpu)
|
|
{
|
|
struct rq *rq = cpu_rq(cpu);
|
|
struct cfs_rq *cfs_rq, *pos;
|
|
struct rq_flags rf;
|
|
|
|
rq_lock_irqsave(rq, &rf);
|
|
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_safe(rq, cfs_rq, pos) {
|
|
struct sched_entity *se;
|
|
|
|
/* 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, true))
|
|
update_tg_load_avg(cfs_rq, 0);
|
|
|
|
/* Propagate pending load changes to the parent, if any: */
|
|
se = cfs_rq->tg->se[cpu];
|
|
if (se && !skip_blocked_update(se))
|
|
update_load_avg(se, 0);
|
|
|
|
/*
|
|
* There can be a lot of idle CPU cgroups. Don't let fully
|
|
* decayed cfs_rqs linger on the list.
|
|
*/
|
|
if (cfs_rq_is_decayed(cfs_rq))
|
|
list_del_leaf_cfs_rq(cfs_rq);
|
|
}
|
|
rq_unlock_irqrestore(rq, &rf);
|
|
}
|
|
|
|
/*
|
|
* Compute the hierarchical load factor for cfs_rq and all its ascendants.
|
|
* This needs to be done in a top-down fashion because the load of a child
|
|
* group is a fraction of its parents load.
|
|
*/
|
|
static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
|
|
{
|
|
struct rq *rq = rq_of(cfs_rq);
|
|
struct sched_entity *se = cfs_rq->tg->se[cpu_of(rq)];
|
|
unsigned long now = jiffies;
|
|
unsigned long load;
|
|
|
|
if (cfs_rq->last_h_load_update == now)
|
|
return;
|
|
|
|
cfs_rq->h_load_next = NULL;
|
|
for_each_sched_entity(se) {
|
|
cfs_rq = cfs_rq_of(se);
|
|
cfs_rq->h_load_next = se;
|
|
if (cfs_rq->last_h_load_update == now)
|
|
break;
|
|
}
|
|
|
|
if (!se) {
|
|
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,
|
|
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;
|
|
}
|
|
}
|
|
|
|
static unsigned long task_h_load(struct task_struct *p)
|
|
{
|
|
struct cfs_rq *cfs_rq = task_cfs_rq(p);
|
|
|
|
update_cfs_rq_h_load(cfs_rq);
|
|
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;
|
|
struct rq_flags rf;
|
|
|
|
rq_lock_irqsave(rq, &rf);
|
|
update_rq_clock(rq);
|
|
update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq, true);
|
|
rq_unlock_irqrestore(rq, &rf);
|
|
}
|
|
|
|
static unsigned long task_h_load(struct task_struct *p)
|
|
{
|
|
return p->se.avg.load_avg;
|
|
}
|
|
#endif
|
|
|
|
/********** Helpers for find_busiest_group ************************/
|
|
|
|
enum group_type {
|
|
group_other = 0,
|
|
group_imbalanced,
|
|
group_overloaded,
|
|
};
|
|
|
|
/*
|
|
* sg_lb_stats - stats of a sched_group required for load_balancing
|
|
*/
|
|
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 */
|
|
unsigned int sum_nr_running; /* Nr tasks running in the group */
|
|
unsigned int idle_cpus;
|
|
unsigned int group_weight;
|
|
enum group_type group_type;
|
|
int group_no_capacity;
|
|
#ifdef CONFIG_NUMA_BALANCING
|
|
unsigned int nr_numa_running;
|
|
unsigned int nr_preferred_running;
|
|
#endif
|
|
};
|
|
|
|
/*
|
|
* sd_lb_stats - Structure to store the statistics of a sched_domain
|
|
* during load balancing.
|
|
*/
|
|
struct sd_lb_stats {
|
|
struct sched_group *busiest; /* Busiest group in this sd */
|
|
struct sched_group *local; /* Local group in this sd */
|
|
unsigned long total_load; /* Total load of all groups in sd */
|
|
unsigned long total_capacity; /* Total capacity of all groups in sd */
|
|
unsigned long avg_load; /* Average load across all groups in sd */
|
|
|
|
struct sg_lb_stats busiest_stat;/* Statistics of the busiest group */
|
|
struct sg_lb_stats local_stat; /* Statistics of the local group */
|
|
};
|
|
|
|
static inline void init_sd_lb_stats(struct sd_lb_stats *sds)
|
|
{
|
|
/*
|
|
* Skimp on the clearing to avoid duplicate work. We can avoid clearing
|
|
* local_stat because update_sg_lb_stats() does a full clear/assignment.
|
|
* We must however clear busiest_stat::avg_load because
|
|
* update_sd_pick_busiest() reads this before assignment.
|
|
*/
|
|
*sds = (struct sd_lb_stats){
|
|
.busiest = NULL,
|
|
.local = NULL,
|
|
.total_load = 0UL,
|
|
.total_capacity = 0UL,
|
|
.busiest_stat = {
|
|
.avg_load = 0UL,
|
|
.sum_nr_running = 0,
|
|
.group_type = group_other,
|
|
},
|
|
};
|
|
}
|
|
|
|
/**
|
|
* 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(int cpu)
|
|
{
|
|
struct rq *rq = cpu_rq(cpu);
|
|
u64 total, used, age_stamp, avg;
|
|
s64 delta;
|
|
|
|
/*
|
|
* Since we're reading these variables without serialization make sure
|
|
* we read them once before doing sanity checks on them.
|
|
*/
|
|
age_stamp = READ_ONCE(rq->age_stamp);
|
|
avg = READ_ONCE(rq->rt_avg);
|
|
delta = __rq_clock_broken(rq) - age_stamp;
|
|
|
|
if (unlikely(delta < 0))
|
|
delta = 0;
|
|
|
|
total = sched_avg_period() + delta;
|
|
|
|
used = div_u64(avg, total);
|
|
|
|
if (likely(used < SCHED_CAPACITY_SCALE))
|
|
return SCHED_CAPACITY_SCALE - used;
|
|
|
|
return 1;
|
|
}
|
|
|
|
static void update_cpu_capacity(struct sched_domain *sd, int cpu)
|
|
{
|
|
unsigned long capacity = arch_scale_cpu_capacity(sd, cpu);
|
|
struct sched_group *sdg = sd->groups;
|
|
|
|
cpu_rq(cpu)->cpu_capacity_orig = capacity;
|
|
|
|
capacity *= scale_rt_capacity(cpu);
|
|
capacity >>= SCHED_CAPACITY_SHIFT;
|
|
|
|
if (!capacity)
|
|
capacity = 1;
|
|
|
|
cpu_rq(cpu)->cpu_capacity = capacity;
|
|
sdg->sgc->capacity = capacity;
|
|
sdg->sgc->min_capacity = capacity;
|
|
}
|
|
|
|
void update_group_capacity(struct sched_domain *sd, int cpu)
|
|
{
|
|
struct sched_domain *child = sd->child;
|
|
struct sched_group *group, *sdg = sd->groups;
|
|
unsigned long capacity, min_capacity;
|
|
unsigned long interval;
|
|
|
|
interval = msecs_to_jiffies(sd->balance_interval);
|
|
interval = clamp(interval, 1UL, max_load_balance_interval);
|
|
sdg->sgc->next_update = jiffies + interval;
|
|
|
|
if (!child) {
|
|
update_cpu_capacity(sd, cpu);
|
|
return;
|
|
}
|
|
|
|
capacity = 0;
|
|
min_capacity = ULONG_MAX;
|
|
|
|
if (child->flags & SD_OVERLAP) {
|
|
/*
|
|
* SD_OVERLAP domains cannot assume that child groups
|
|
* span the current group.
|
|
*/
|
|
|
|
for_each_cpu(cpu, sched_group_span(sdg)) {
|
|
struct sched_group_capacity *sgc;
|
|
struct rq *rq = cpu_rq(cpu);
|
|
|
|
/*
|
|
* build_sched_domains() -> init_sched_groups_capacity()
|
|
* gets here before we've attached the domains to the
|
|
* runqueues.
|
|
*
|
|
* Use capacity_of(), which is set irrespective of domains
|
|
* in update_cpu_capacity().
|
|
*
|
|
* This avoids capacity from being 0 and
|
|
* causing divide-by-zero issues on boot.
|
|
*/
|
|
if (unlikely(!rq->sd)) {
|
|
capacity += capacity_of(cpu);
|
|
} else {
|
|
sgc = rq->sd->groups->sgc;
|
|
capacity += sgc->capacity;
|
|
}
|
|
|
|
min_capacity = min(capacity, min_capacity);
|
|
}
|
|
} else {
|
|
/*
|
|
* !SD_OVERLAP domains can assume that child groups
|
|
* span the current group.
|
|
*/
|
|
|
|
group = child->groups;
|
|
do {
|
|
struct sched_group_capacity *sgc = group->sgc;
|
|
|
|
capacity += sgc->capacity;
|
|
min_capacity = min(sgc->min_capacity, min_capacity);
|
|
group = group->next;
|
|
} while (group != child->groups);
|
|
}
|
|
|
|
sdg->sgc->capacity = capacity;
|
|
sdg->sgc->min_capacity = min_capacity;
|
|
}
|
|
|
|
/*
|
|
* Check whether the capacity of the rq has been noticeably reduced by side
|
|
* activity. The imbalance_pct is used for the threshold.
|
|
* Return true is the capacity is reduced
|
|
*/
|
|
static inline int
|
|
check_cpu_capacity(struct rq *rq, struct sched_domain *sd)
|
|
{
|
|
return ((rq->cpu_capacity * sd->imbalance_pct) <
|
|
(rq->cpu_capacity_orig * 100));
|
|
}
|
|
|
|
/*
|
|
* Group imbalance indicates (and tries to solve) the problem where balancing
|
|
* groups is inadequate due to ->cpus_allowed 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.
|
|
* Something like:
|
|
*
|
|
* { 0 1 2 3 } { 4 5 6 7 }
|
|
* * * * *
|
|
*
|
|
* If we were to balance group-wise we'd place two tasks in the first group and
|
|
* two tasks in the second group. Clearly this is undesired as it will overload
|
|
* cpu 3 and leave one of the cpus in the second group unused.
|
|
*
|
|
* The current solution to this issue is detecting the skew in the first group
|
|
* by noticing the lower domain failed to reach balance and had difficulty
|
|
* moving tasks due to affinity constraints.
|
|
*
|
|
* When this is so detected; this group becomes a candidate for busiest; see
|
|
* update_sd_pick_busiest(). And calculate_imbalance() and
|
|
* find_busiest_group() avoid some of the usual balance conditions to allow it
|
|
* to create an effective group imbalance.
|
|
*
|
|
* This is a somewhat tricky proposition since the next run might not find the
|
|
* group imbalance and decide the groups need to be balanced again. A most
|
|
* subtle and fragile situation.
|
|
*/
|
|
|
|
static inline int sg_imbalanced(struct sched_group *group)
|
|
{
|
|
return group->sgc->imbalance;
|
|
}
|
|
|
|
/*
|
|
* 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 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.
|
|
* As an example, an available capacity of 1% can appear but it doesn't make
|
|
* any benefit for the load balance.
|
|
*/
|
|
static inline bool
|
|
group_has_capacity(struct lb_env *env, struct sg_lb_stats *sgs)
|
|
{
|
|
if (sgs->sum_nr_running < sgs->group_weight)
|
|
return true;
|
|
|
|
if ((sgs->group_capacity * 100) >
|
|
(sgs->group_util * env->sd->imbalance_pct))
|
|
return true;
|
|
|
|
return false;
|
|
}
|
|
|
|
/*
|
|
* group_is_overloaded returns true if the group has more tasks than it can
|
|
* handle.
|
|
* group_is_overloaded is not equals to !group_has_capacity because a group
|
|
* with the exact right number of tasks, has no more spare capacity but is not
|
|
* overloaded so both group_has_capacity and group_is_overloaded return
|
|
* false.
|
|
*/
|
|
static inline bool
|
|
group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs)
|
|
{
|
|
if (sgs->sum_nr_running <= sgs->group_weight)
|
|
return false;
|
|
|
|
if ((sgs->group_capacity * 100) <
|
|
(sgs->group_util * env->sd->imbalance_pct))
|
|
return true;
|
|
|
|
return false;
|
|
}
|
|
|
|
/*
|
|
* group_smaller_cpu_capacity: Returns true if sched_group sg has smaller
|
|
* per-CPU capacity than sched_group ref.
|
|
*/
|
|
static inline bool
|
|
group_smaller_cpu_capacity(struct sched_group *sg, struct sched_group *ref)
|
|
{
|
|
return sg->sgc->min_capacity * capacity_margin <
|
|
ref->sgc->min_capacity * 1024;
|
|
}
|
|
|
|
static inline enum
|
|
group_type group_classify(struct sched_group *group,
|
|
struct sg_lb_stats *sgs)
|
|
{
|
|
if (sgs->group_no_capacity)
|
|
return group_overloaded;
|
|
|
|
if (sg_imbalanced(group))
|
|
return group_imbalanced;
|
|
|
|
return group_other;
|
|
}
|
|
|
|
/**
|
|
* update_sg_lb_stats - Update sched_group's statistics for load balancing.
|
|
* @env: The load balancing environment.
|
|
* @group: sched_group whose statistics are to be updated.
|
|
* @load_idx: Load index of sched_domain of this_cpu for load calc.
|
|
* @local_group: Does group contain this_cpu.
|
|
* @sgs: variable to hold the statistics for this group.
|
|
* @overload: Indicate more than one runnable task for any CPU.
|
|
*/
|
|
static inline void update_sg_lb_stats(struct lb_env *env,
|
|
struct sched_group *group, int load_idx,
|
|
int local_group, struct sg_lb_stats *sgs,
|
|
bool *overload)
|
|
{
|
|
unsigned long load;
|
|
int i, nr_running;
|
|
|
|
memset(sgs, 0, sizeof(*sgs));
|
|
|
|
for_each_cpu_and(i, sched_group_span(group), env->cpus) {
|
|
struct rq *rq = cpu_rq(i);
|
|
|
|
/* 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_util += cpu_util(i);
|
|
sgs->sum_nr_running += rq->cfs.h_nr_running;
|
|
|
|
nr_running = rq->nr_running;
|
|
if (nr_running > 1)
|
|
*overload = true;
|
|
|
|
#ifdef CONFIG_NUMA_BALANCING
|
|
sgs->nr_numa_running += rq->nr_numa_running;
|
|
sgs->nr_preferred_running += rq->nr_preferred_running;
|
|
#endif
|
|
sgs->sum_weighted_load += weighted_cpuload(i);
|
|
/*
|
|
* No need to call idle_cpu() if nr_running is not 0
|
|
*/
|
|
if (!nr_running && idle_cpu(i))
|
|
sgs->idle_cpus++;
|
|
}
|
|
|
|
/* Adjust by relative CPU capacity of the group */
|
|
sgs->group_capacity = group->sgc->capacity;
|
|
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->group_weight = group->group_weight;
|
|
|
|
sgs->group_no_capacity = group_is_overloaded(env, sgs);
|
|
sgs->group_type = group_classify(group, sgs);
|
|
}
|
|
|
|
/**
|
|
* update_sd_pick_busiest - return 1 on busiest group
|
|
* @env: The load balancing environment.
|
|
* @sds: sched_domain statistics
|
|
* @sg: sched_group candidate to be checked for being the busiest
|
|
* @sgs: sched_group statistics
|
|
*
|
|
* Determine if @sg is a busier group than the previously selected
|
|
* busiest group.
|
|
*
|
|
* Return: %true if @sg is a busier group than the previously selected
|
|
* busiest group. %false otherwise.
|
|
*/
|
|
static bool update_sd_pick_busiest(struct lb_env *env,
|
|
struct sd_lb_stats *sds,
|
|
struct sched_group *sg,
|
|
struct sg_lb_stats *sgs)
|
|
{
|
|
struct sg_lb_stats *busiest = &sds->busiest_stat;
|
|
|
|
if (sgs->group_type > busiest->group_type)
|
|
return true;
|
|
|
|
if (sgs->group_type < busiest->group_type)
|
|
return false;
|
|
|
|
if (sgs->avg_load <= busiest->avg_load)
|
|
return false;
|
|
|
|
if (!(env->sd->flags & SD_ASYM_CPUCAPACITY))
|
|
goto asym_packing;
|
|
|
|
/*
|
|
* Candidate sg has no more than one task per CPU and
|
|
* has higher per-CPU capacity. Migrating tasks to less
|
|
* capable CPUs may harm throughput. Maximize throughput,
|
|
* power/energy consequences are not considered.
|
|
*/
|
|
if (sgs->sum_nr_running <= sgs->group_weight &&
|
|
group_smaller_cpu_capacity(sds->local, sg))
|
|
return false;
|
|
|
|
asym_packing:
|
|
/* This is the busiest node in its class. */
|
|
if (!(env->sd->flags & SD_ASYM_PACKING))
|
|
return true;
|
|
|
|
/* No ASYM_PACKING if target cpu is already busy */
|
|
if (env->idle == CPU_NOT_IDLE)
|
|
return true;
|
|
/*
|
|
* ASYM_PACKING needs to move all the work to the highest
|
|
* prority CPUs in the group, therefore mark all groups
|
|
* of lower priority than ourself as busy.
|
|
*/
|
|
if (sgs->sum_nr_running &&
|
|
sched_asym_prefer(env->dst_cpu, sg->asym_prefer_cpu)) {
|
|
if (!sds->busiest)
|
|
return true;
|
|
|
|
/* Prefer to move from lowest priority cpu's work */
|
|
if (sched_asym_prefer(sds->busiest->asym_prefer_cpu,
|
|
sg->asym_prefer_cpu))
|
|
return true;
|
|
}
|
|
|
|
return false;
|
|
}
|
|
|
|
#ifdef CONFIG_NUMA_BALANCING
|
|
static inline enum fbq_type fbq_classify_group(struct sg_lb_stats *sgs)
|
|
{
|
|
if (sgs->sum_nr_running > sgs->nr_numa_running)
|
|
return regular;
|
|
if (sgs->sum_nr_running > sgs->nr_preferred_running)
|
|
return remote;
|
|
return all;
|
|
}
|
|
|
|
static inline enum fbq_type fbq_classify_rq(struct rq *rq)
|
|
{
|
|
if (rq->nr_running > rq->nr_numa_running)
|
|
return regular;
|
|
if (rq->nr_running > rq->nr_preferred_running)
|
|
return remote;
|
|
return all;
|
|
}
|
|
#else
|
|
static inline enum fbq_type fbq_classify_group(struct sg_lb_stats *sgs)
|
|
{
|
|
return all;
|
|
}
|
|
|
|
static inline enum fbq_type fbq_classify_rq(struct rq *rq)
|
|
{
|
|
return regular;
|
|
}
|
|
#endif /* CONFIG_NUMA_BALANCING */
|
|
|
|
/**
|
|
* update_sd_lb_stats - Update sched_domain's statistics for load balancing.
|
|
* @env: The load balancing environment.
|
|
* @sds: variable to hold the statistics for this sched_domain.
|
|
*/
|
|
static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sds)
|
|
{
|
|
struct sched_domain *child = env->sd->child;
|
|
struct sched_group *sg = env->sd->groups;
|
|
struct sg_lb_stats *local = &sds->local_stat;
|
|
struct sg_lb_stats tmp_sgs;
|
|
int load_idx, prefer_sibling = 0;
|
|
bool overload = false;
|
|
|
|
if (child && child->flags & SD_PREFER_SIBLING)
|
|
prefer_sibling = 1;
|
|
|
|
load_idx = get_sd_load_idx(env->sd, env->idle);
|
|
|
|
do {
|
|
struct sg_lb_stats *sgs = &tmp_sgs;
|
|
int local_group;
|
|
|
|
local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(sg));
|
|
if (local_group) {
|
|
sds->local = sg;
|
|
sgs = local;
|
|
|
|
if (env->idle != CPU_NEWLY_IDLE ||
|
|
time_after_eq(jiffies, sg->sgc->next_update))
|
|
update_group_capacity(env->sd, env->dst_cpu);
|
|
}
|
|
|
|
update_sg_lb_stats(env, sg, load_idx, local_group, sgs,
|
|
&overload);
|
|
|
|
if (local_group)
|
|
goto next_group;
|
|
|
|
/*
|
|
* In case the child domain prefers tasks go to siblings
|
|
* first, lower the sg capacity so that we'll try
|
|
* and move all the excess tasks away. We lower the capacity
|
|
* of a group only if the local group has the capacity to fit
|
|
* these excess tasks. The extra check prevents the case where
|
|
* you always pull from the heaviest group when it is already
|
|
* under-utilized (possible with a large weight task outweighs
|
|
* the tasks on the system).
|
|
*/
|
|
if (prefer_sibling && sds->local &&
|
|
group_has_capacity(env, local) &&
|
|
(sgs->sum_nr_running > local->sum_nr_running + 1)) {
|
|
sgs->group_no_capacity = 1;
|
|
sgs->group_type = group_classify(sg, sgs);
|
|
}
|
|
|
|
if (update_sd_pick_busiest(env, sds, sg, sgs)) {
|
|
sds->busiest = sg;
|
|
sds->busiest_stat = *sgs;
|
|
}
|
|
|
|
next_group:
|
|
/* Now, start updating sd_lb_stats */
|
|
sds->total_load += sgs->group_load;
|
|
sds->total_capacity += sgs->group_capacity;
|
|
|
|
sg = sg->next;
|
|
} while (sg != env->sd->groups);
|
|
|
|
if (env->sd->flags & SD_NUMA)
|
|
env->fbq_type = fbq_classify_group(&sds->busiest_stat);
|
|
|
|
if (!env->sd->parent) {
|
|
/* update overload indicator if we are at root domain */
|
|
if (env->dst_rq->rd->overload != overload)
|
|
env->dst_rq->rd->overload = overload;
|
|
}
|
|
|
|
}
|
|
|
|
/**
|
|
* check_asym_packing - Check to see if the group is packed into the
|
|
* sched domain.
|
|
*
|
|
* This is primarily intended to used at the sibling level. Some
|
|
* cores like POWER7 prefer to use lower numbered SMT threads. In the
|
|
* case of POWER7, it can move to lower SMT modes only when higher
|
|
* threads are idle. When in lower SMT modes, the threads will
|
|
* perform better since they share less core resources. Hence when we
|
|
* have idle threads, we want them to be the higher ones.
|
|
*
|
|
* This packing function is run on idle threads. It checks to see if
|
|
* the busiest CPU in this domain (core in the P7 case) has a higher
|
|
* CPU number than the packing function is being run on. Here we are
|
|
* assuming lower CPU number will be equivalent to lower a SMT thread
|
|
* number.
|
|
*
|
|
* Return: 1 when packing is required and a task should be moved to
|
|
* this CPU. The amount of the imbalance is returned in *imbalance.
|
|
*
|
|
* @env: The load balancing environment.
|
|
* @sds: Statistics of the sched_domain which is to be packed
|
|
*/
|
|
static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds)
|
|
{
|
|
int busiest_cpu;
|
|
|
|
if (!(env->sd->flags & SD_ASYM_PACKING))
|
|
return 0;
|
|
|
|
if (env->idle == CPU_NOT_IDLE)
|
|
return 0;
|
|
|
|
if (!sds->busiest)
|
|
return 0;
|
|
|
|
busiest_cpu = sds->busiest->asym_prefer_cpu;
|
|
if (sched_asym_prefer(busiest_cpu, env->dst_cpu))
|
|
return 0;
|
|
|
|
env->imbalance = DIV_ROUND_CLOSEST(
|
|
sds->busiest_stat.avg_load * sds->busiest_stat.group_capacity,
|
|
SCHED_CAPACITY_SCALE);
|
|
|
|
return 1;
|
|
}
|
|
|
|
/**
|
|
* fix_small_imbalance - Calculate the minor imbalance that exists
|
|
* amongst the groups of a sched_domain, during
|
|
* load balancing.
|
|
* @env: The load balancing environment.
|
|
* @sds: Statistics of the sched_domain whose imbalance is to be calculated.
|
|
*/
|
|
static inline
|
|
void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
|
|
{
|
|
unsigned long tmp, capa_now = 0, capa_move = 0;
|
|
unsigned int imbn = 2;
|
|
unsigned long scaled_busy_load_per_task;
|
|
struct sg_lb_stats *local, *busiest;
|
|
|
|
local = &sds->local_stat;
|
|
busiest = &sds->busiest_stat;
|
|
|
|
if (!local->sum_nr_running)
|
|
local->load_per_task = cpu_avg_load_per_task(env->dst_cpu);
|
|
else if (busiest->load_per_task > local->load_per_task)
|
|
imbn = 1;
|
|
|
|
scaled_busy_load_per_task =
|
|
(busiest->load_per_task * SCHED_CAPACITY_SCALE) /
|
|
busiest->group_capacity;
|
|
|
|
if (busiest->avg_load + scaled_busy_load_per_task >=
|
|
local->avg_load + (scaled_busy_load_per_task * imbn)) {
|
|
env->imbalance = busiest->load_per_task;
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* OK, we don't have enough imbalance to justify moving tasks,
|
|
* however we may be able to increase total CPU capacity used by
|
|
* moving them.
|
|
*/
|
|
|
|
capa_now += busiest->group_capacity *
|
|
min(busiest->load_per_task, busiest->avg_load);
|
|
capa_now += local->group_capacity *
|
|
min(local->load_per_task, local->avg_load);
|
|
capa_now /= SCHED_CAPACITY_SCALE;
|
|
|
|
/* Amount of load we'd subtract */
|
|
if (busiest->avg_load > scaled_busy_load_per_task) {
|
|
capa_move += busiest->group_capacity *
|
|
min(busiest->load_per_task,
|
|
busiest->avg_load - scaled_busy_load_per_task);
|
|
}
|
|
|
|
/* Amount of load we'd add */
|
|
if (busiest->avg_load * busiest->group_capacity <
|
|
busiest->load_per_task * SCHED_CAPACITY_SCALE) {
|
|
tmp = (busiest->avg_load * busiest->group_capacity) /
|
|
local->group_capacity;
|
|
} else {
|
|
tmp = (busiest->load_per_task * SCHED_CAPACITY_SCALE) /
|
|
local->group_capacity;
|
|
}
|
|
capa_move += local->group_capacity *
|
|
min(local->load_per_task, local->avg_load + tmp);
|
|
capa_move /= SCHED_CAPACITY_SCALE;
|
|
|
|
/* Move if we gain throughput */
|
|
if (capa_move > capa_now)
|
|
env->imbalance = busiest->load_per_task;
|
|
}
|
|
|
|
/**
|
|
* calculate_imbalance - Calculate the amount of imbalance present within the
|
|
* groups of a given sched_domain during load balance.
|
|
* @env: load balance environment
|
|
* @sds: statistics of the sched_domain whose imbalance is to be calculated.
|
|
*/
|
|
static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
|
|
{
|
|
unsigned long max_pull, load_above_capacity = ~0UL;
|
|
struct sg_lb_stats *local, *busiest;
|
|
|
|
local = &sds->local_stat;
|
|
busiest = &sds->busiest_stat;
|
|
|
|
if (busiest->group_type == group_imbalanced) {
|
|
/*
|
|
* In the group_imb case we cannot rely on group-wide averages
|
|
* to ensure cpu-load equilibrium, look at wider averages. XXX
|
|
*/
|
|
busiest->load_per_task =
|
|
min(busiest->load_per_task, sds->avg_load);
|
|
}
|
|
|
|
/*
|
|
* Avg load of busiest sg can be less and avg load of local sg can
|
|
* be greater than avg load across all sgs of sd because avg load
|
|
* factors in sg capacity and sgs with smaller group_type are
|
|
* skipped when updating the busiest sg:
|
|
*/
|
|
if (busiest->avg_load <= sds->avg_load ||
|
|
local->avg_load >= sds->avg_load) {
|
|
env->imbalance = 0;
|
|
return fix_small_imbalance(env, sds);
|
|
}
|
|
|
|
/*
|
|
* If there aren't any idle cpus, avoid creating some.
|
|
*/
|
|
if (busiest->group_type == group_overloaded &&
|
|
local->group_type == group_overloaded) {
|
|
load_above_capacity = busiest->sum_nr_running * SCHED_CAPACITY_SCALE;
|
|
if (load_above_capacity > busiest->group_capacity) {
|
|
load_above_capacity -= busiest->group_capacity;
|
|
load_above_capacity *= scale_load_down(NICE_0_LOAD);
|
|
load_above_capacity /= busiest->group_capacity;
|
|
} else
|
|
load_above_capacity = ~0UL;
|
|
}
|
|
|
|
/*
|
|
* We're trying to get all the cpus to the average_load, so we don't
|
|
* want to push ourselves above the average load, nor do we wish to
|
|
* reduce the max loaded cpu below the average load. At the same time,
|
|
* we also don't want to reduce the group load below the group
|
|
* capacity. Thus we look for the minimum possible imbalance.
|
|
*/
|
|
max_pull = min(busiest->avg_load - sds->avg_load, load_above_capacity);
|
|
|
|
/* How much load to actually move to equalise the imbalance */
|
|
env->imbalance = min(
|
|
max_pull * busiest->group_capacity,
|
|
(sds->avg_load - local->avg_load) * local->group_capacity
|
|
) / SCHED_CAPACITY_SCALE;
|
|
|
|
/*
|
|
* if *imbalance is less than the average load per runnable task
|
|
* there is no guarantee that any tasks will be moved so we'll have
|
|
* a think about bumping its value to force at least one task to be
|
|
* moved
|
|
*/
|
|
if (env->imbalance < busiest->load_per_task)
|
|
return fix_small_imbalance(env, sds);
|
|
}
|
|
|
|
/******* find_busiest_group() helpers end here *********************/
|
|
|
|
/**
|
|
* 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
|
|
* to restore balance.
|
|
*
|
|
* @env: The load balancing environment.
|
|
*
|
|
* Return: - The busiest group if imbalance exists.
|
|
*/
|
|
static struct sched_group *find_busiest_group(struct lb_env *env)
|
|
{
|
|
struct sg_lb_stats *local, *busiest;
|
|
struct sd_lb_stats sds;
|
|
|
|
init_sd_lb_stats(&sds);
|
|
|
|
/*
|
|
* Compute the various statistics relavent for load balancing at
|
|
* this level.
|
|
*/
|
|
update_sd_lb_stats(env, &sds);
|
|
local = &sds.local_stat;
|
|
busiest = &sds.busiest_stat;
|
|
|
|
/* ASYM feature bypasses nice load balance check */
|
|
if (check_asym_packing(env, &sds))
|
|
return sds.busiest;
|
|
|
|
/* There is no busy sibling group to pull tasks from */
|
|
if (!sds.busiest || busiest->sum_nr_running == 0)
|
|
goto out_balanced;
|
|
|
|
sds.avg_load = (SCHED_CAPACITY_SCALE * sds.total_load)
|
|
/ sds.total_capacity;
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
if (busiest->group_type == group_imbalanced)
|
|
goto force_balance;
|
|
|
|
/* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
|
|
if (env->idle == CPU_NEWLY_IDLE && group_has_capacity(env, local) &&
|
|
busiest->group_no_capacity)
|
|
goto force_balance;
|
|
|
|
/*
|
|
* If the local group is busier than the selected busiest group
|
|
* don't try and pull any tasks.
|
|
*/
|
|
if (local->avg_load >= busiest->avg_load)
|
|
goto out_balanced;
|
|
|
|
/*
|
|
* Don't pull any tasks if this group is already above the domain
|
|
* average load.
|
|
*/
|
|
if (local->avg_load >= sds.avg_load)
|
|
goto out_balanced;
|
|
|
|
if (env->idle == CPU_IDLE) {
|
|
/*
|
|
* This cpu is idle. If the busiest group is not overloaded
|
|
* and there is no imbalance between this and busiest group
|
|
* wrt idle cpus, it is balanced. The imbalance becomes
|
|
* significant if the diff is greater than 1 otherwise we
|
|
* might end up to just move the imbalance on another group
|
|
*/
|
|
if ((busiest->group_type != group_overloaded) &&
|
|
(local->idle_cpus <= (busiest->idle_cpus + 1)))
|
|
goto out_balanced;
|
|
} else {
|
|
/*
|
|
* In the CPU_NEWLY_IDLE, CPU_NOT_IDLE cases, use
|
|
* imbalance_pct to be conservative.
|
|
*/
|
|
if (100 * busiest->avg_load <=
|
|
env->sd->imbalance_pct * local->avg_load)
|
|
goto out_balanced;
|
|
}
|
|
|
|
force_balance:
|
|
/* Looks like there is an imbalance. Compute it */
|
|
calculate_imbalance(env, &sds);
|
|
return sds.busiest;
|
|
|
|
out_balanced:
|
|
env->imbalance = 0;
|
|
return NULL;
|
|
}
|
|
|
|
/*
|
|
* find_busiest_queue - find the busiest runqueue among the cpus in group.
|
|
*/
|
|
static struct rq *find_busiest_queue(struct lb_env *env,
|
|
struct sched_group *group)
|
|
{
|
|
struct rq *busiest = NULL, *rq;
|
|
unsigned long busiest_load = 0, busiest_capacity = 1;
|
|
int i;
|
|
|
|
for_each_cpu_and(i, sched_group_span(group), env->cpus) {
|
|
unsigned long capacity, wl;
|
|
enum fbq_type rt;
|
|
|
|
rq = cpu_rq(i);
|
|
rt = fbq_classify_rq(rq);
|
|
|
|
/*
|
|
* We classify groups/runqueues into three groups:
|
|
* - regular: there are !numa tasks
|
|
* - remote: there are numa tasks that run on the 'wrong' node
|
|
* - all: there is no distinction
|
|
*
|
|
* In order to avoid migrating ideally placed numa tasks,
|
|
* ignore those when there's better options.
|
|
*
|
|
* If we ignore the actual busiest queue to migrate another
|
|
* task, the next balance pass can still reduce the busiest
|
|
* queue by moving tasks around inside the node.
|
|
*
|
|
* If we cannot move enough load due to this classification
|
|
* the next pass will adjust the group classification and
|
|
* allow migration of more tasks.
|
|
*
|
|
* Both cases only affect the total convergence complexity.
|
|
*/
|
|
if (rt > env->fbq_type)
|
|
continue;
|
|
|
|
capacity = capacity_of(i);
|
|
|
|
wl = weighted_cpuload(i);
|
|
|
|
/*
|
|
* When comparing with imbalance, use weighted_cpuload()
|
|
* which is not scaled with the cpu capacity.
|
|
*/
|
|
|
|
if (rq->nr_running == 1 && wl > 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
|
|
* 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
|
|
* multiplication to rid ourselves of the division works out
|
|
* to: wl_i * capacity_j > wl_j * capacity_i; where j is
|
|
* our previous maximum.
|
|
*/
|
|
if (wl * busiest_capacity > busiest_load * capacity) {
|
|
busiest_load = wl;
|
|
busiest_capacity = capacity;
|
|
busiest = rq;
|
|
}
|
|
}
|
|
|
|
return busiest;
|
|
}
|
|
|
|
/*
|
|
* Max backoff if we encounter pinned tasks. Pretty arbitrary value, but
|
|
* so long as it is large enough.
|
|
*/
|
|
#define MAX_PINNED_INTERVAL 512
|
|
|
|
static int need_active_balance(struct lb_env *env)
|
|
{
|
|
struct sched_domain *sd = env->sd;
|
|
|
|
if (env->idle == CPU_NEWLY_IDLE) {
|
|
|
|
/*
|
|
* ASYM_PACKING needs to force migrate tasks from busy but
|
|
* lower priority CPUs in order to pack all tasks in the
|
|
* highest priority CPUs.
|
|
*/
|
|
if ((sd->flags & SD_ASYM_PACKING) &&
|
|
sched_asym_prefer(env->dst_cpu, env->src_cpu))
|
|
return 1;
|
|
}
|
|
|
|
/*
|
|
* The dst_cpu is idle and the src_cpu CPU has only 1 CFS task.
|
|
* It's worth migrating the task if the src_cpu's capacity is reduced
|
|
* because of other sched_class or IRQs if more capacity stays
|
|
* available on dst_cpu.
|
|
*/
|
|
if ((env->idle != CPU_NOT_IDLE) &&
|
|
(env->src_rq->cfs.h_nr_running == 1)) {
|
|
if ((check_cpu_capacity(env->src_rq, sd)) &&
|
|
(capacity_of(env->src_cpu)*sd->imbalance_pct < capacity_of(env->dst_cpu)*100))
|
|
return 1;
|
|
}
|
|
|
|
return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2);
|
|
}
|
|
|
|
static int active_load_balance_cpu_stop(void *data);
|
|
|
|
static int should_we_balance(struct lb_env *env)
|
|
{
|
|
struct sched_group *sg = env->sd->groups;
|
|
int cpu, balance_cpu = -1;
|
|
|
|
/*
|
|
* In the newly idle case, we will allow all the cpu's
|
|
* to do the newly idle load balance.
|
|
*/
|
|
if (env->idle == CPU_NEWLY_IDLE)
|
|
return 1;
|
|
|
|
/* Try to find first idle cpu */
|
|
for_each_cpu_and(cpu, group_balance_mask(sg), env->cpus) {
|
|
if (!idle_cpu(cpu))
|
|
continue;
|
|
|
|
balance_cpu = cpu;
|
|
break;
|
|
}
|
|
|
|
if (balance_cpu == -1)
|
|
balance_cpu = group_balance_cpu(sg);
|
|
|
|
/*
|
|
* First idle cpu or the first cpu(busiest) in this sched group
|
|
* is eligible for doing load balancing at this and above domains.
|
|
*/
|
|
return balance_cpu == env->dst_cpu;
|
|
}
|
|
|
|
/*
|
|
* Check this_cpu to ensure it is balanced within domain. Attempt to move
|
|
* tasks if there is an imbalance.
|
|
*/
|
|
static int load_balance(int this_cpu, struct rq *this_rq,
|
|
struct sched_domain *sd, enum cpu_idle_type idle,
|
|
int *continue_balancing)
|
|
{
|
|
int ld_moved, cur_ld_moved, active_balance = 0;
|
|
struct sched_domain *sd_parent = sd->parent;
|
|
struct sched_group *group;
|
|
struct rq *busiest;
|
|
struct rq_flags rf;
|
|
struct cpumask *cpus = this_cpu_cpumask_var_ptr(load_balance_mask);
|
|
|
|
struct lb_env env = {
|
|
.sd = sd,
|
|
.dst_cpu = this_cpu,
|
|
.dst_rq = this_rq,
|
|
.dst_grpmask = sched_group_span(sd->groups),
|
|
.idle = idle,
|
|
.loop_break = sched_nr_migrate_break,
|
|
.cpus = cpus,
|
|
.fbq_type = all,
|
|
.tasks = LIST_HEAD_INIT(env.tasks),
|
|
};
|
|
|
|
cpumask_and(cpus, sched_domain_span(sd), cpu_active_mask);
|
|
|
|
schedstat_inc(sd->lb_count[idle]);
|
|
|
|
redo:
|
|
if (!should_we_balance(&env)) {
|
|
*continue_balancing = 0;
|
|
goto out_balanced;
|
|
}
|
|
|
|
group = find_busiest_group(&env);
|
|
if (!group) {
|
|
schedstat_inc(sd->lb_nobusyg[idle]);
|
|
goto out_balanced;
|
|
}
|
|
|
|
busiest = find_busiest_queue(&env, group);
|
|
if (!busiest) {
|
|
schedstat_inc(sd->lb_nobusyq[idle]);
|
|
goto out_balanced;
|
|
}
|
|
|
|
BUG_ON(busiest == env.dst_rq);
|
|
|
|
schedstat_add(sd->lb_imbalance[idle], env.imbalance);
|
|
|
|
env.src_cpu = busiest->cpu;
|
|
env.src_rq = busiest;
|
|
|
|
ld_moved = 0;
|
|
if (busiest->nr_running > 1) {
|
|
/*
|
|
* Attempt to move tasks. If find_busiest_group has found
|
|
* an imbalance but busiest->nr_running <= 1, the group is
|
|
* still unbalanced. ld_moved simply stays zero, so it is
|
|
* correctly treated as an imbalance.
|
|
*/
|
|
env.flags |= LBF_ALL_PINNED;
|
|
env.loop_max = min(sysctl_sched_nr_migrate, busiest->nr_running);
|
|
|
|
more_balance:
|
|
rq_lock_irqsave(busiest, &rf);
|
|
update_rq_clock(busiest);
|
|
|
|
/*
|
|
* cur_ld_moved - load moved in current iteration
|
|
* ld_moved - cumulative load moved across iterations
|
|
*/
|
|
cur_ld_moved = detach_tasks(&env);
|
|
|
|
/*
|
|
* We've detached some tasks from busiest_rq. Every
|
|
* task is masked "TASK_ON_RQ_MIGRATING", so we can safely
|
|
* unlock busiest->lock, and we are able to be sure
|
|
* that nobody can manipulate the tasks in parallel.
|
|
* See task_rq_lock() family for the details.
|
|
*/
|
|
|
|
rq_unlock(busiest, &rf);
|
|
|
|
if (cur_ld_moved) {
|
|
attach_tasks(&env);
|
|
ld_moved += cur_ld_moved;
|
|
}
|
|
|
|
local_irq_restore(rf.flags);
|
|
|
|
if (env.flags & LBF_NEED_BREAK) {
|
|
env.flags &= ~LBF_NEED_BREAK;
|
|
goto more_balance;
|
|
}
|
|
|
|
/*
|
|
* Revisit (affine) tasks on src_cpu that couldn't be moved to
|
|
* us and move them to an alternate dst_cpu in our sched_group
|
|
* where they can run. The upper limit on how many times we
|
|
* iterate on same src_cpu is dependent on number of cpus in our
|
|
* sched_group.
|
|
*
|
|
* This changes load balance semantics a bit on who can move
|
|
* load to a given_cpu. In addition to the given_cpu itself
|
|
* (or a ilb_cpu acting on its behalf where given_cpu is
|
|
* nohz-idle), we now have balance_cpu in a position to move
|
|
* load to given_cpu. In rare situations, this may cause
|
|
* conflicts (balance_cpu and given_cpu/ilb_cpu deciding
|
|
* _independently_ and at _same_ time to move some load to
|
|
* given_cpu) causing exceess load to be moved to given_cpu.
|
|
* This however should not happen so much in practice and
|
|
* moreover subsequent load balance cycles should correct the
|
|
* excess load moved.
|
|
*/
|
|
if ((env.flags & LBF_DST_PINNED) && env.imbalance > 0) {
|
|
|
|
/* Prevent to re-select dst_cpu via env's cpus */
|
|
cpumask_clear_cpu(env.dst_cpu, env.cpus);
|
|
|
|
env.dst_rq = cpu_rq(env.new_dst_cpu);
|
|
env.dst_cpu = env.new_dst_cpu;
|
|
env.flags &= ~LBF_DST_PINNED;
|
|
env.loop = 0;
|
|
env.loop_break = sched_nr_migrate_break;
|
|
|
|
/*
|
|
* Go back to "more_balance" rather than "redo" since we
|
|
* need to continue with same src_cpu.
|
|
*/
|
|
goto more_balance;
|
|
}
|
|
|
|
/*
|
|
* We failed to reach balance because of affinity.
|
|
*/
|
|
if (sd_parent) {
|
|
int *group_imbalance = &sd_parent->groups->sgc->imbalance;
|
|
|
|
if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0)
|
|
*group_imbalance = 1;
|
|
}
|
|
|
|
/* All tasks on this runqueue were pinned by CPU affinity */
|
|
if (unlikely(env.flags & LBF_ALL_PINNED)) {
|
|
cpumask_clear_cpu(cpu_of(busiest), cpus);
|
|
/*
|
|
* Attempting to continue load balancing at the current
|
|
* sched_domain level only makes sense if there are
|
|
* active CPUs remaining as possible busiest CPUs to
|
|
* pull load from which are not contained within the
|
|
* destination group that is receiving any migrated
|
|
* load.
|
|
*/
|
|
if (!cpumask_subset(cpus, env.dst_grpmask)) {
|
|
env.loop = 0;
|
|
env.loop_break = sched_nr_migrate_break;
|
|
goto redo;
|
|
}
|
|
goto out_all_pinned;
|
|
}
|
|
}
|
|
|
|
if (!ld_moved) {
|
|
schedstat_inc(sd->lb_failed[idle]);
|
|
/*
|
|
* Increment the failure counter only on periodic balance.
|
|
* We do not want newidle balance, which can be very
|
|
* frequent, pollute the failure counter causing
|
|
* excessive cache_hot migrations and active balances.
|
|
*/
|
|
if (idle != CPU_NEWLY_IDLE)
|
|
sd->nr_balance_failed++;
|
|
|
|
if (need_active_balance(&env)) {
|
|
unsigned long flags;
|
|
|
|
raw_spin_lock_irqsave(&busiest->lock, flags);
|
|
|
|
/* don't kick the active_load_balance_cpu_stop,
|
|
* if the curr task on busiest cpu can't be
|
|
* moved to this_cpu
|
|
*/
|
|
if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) {
|
|
raw_spin_unlock_irqrestore(&busiest->lock,
|
|
flags);
|
|
env.flags |= LBF_ALL_PINNED;
|
|
goto out_one_pinned;
|
|
}
|
|
|
|
/*
|
|
* ->active_balance synchronizes accesses to
|
|
* ->active_balance_work. Once set, it's cleared
|
|
* only after active load balance is finished.
|
|
*/
|
|
if (!busiest->active_balance) {
|
|
busiest->active_balance = 1;
|
|
busiest->push_cpu = this_cpu;
|
|
active_balance = 1;
|
|
}
|
|
raw_spin_unlock_irqrestore(&busiest->lock, flags);
|
|
|
|
if (active_balance) {
|
|
stop_one_cpu_nowait(cpu_of(busiest),
|
|
active_load_balance_cpu_stop, busiest,
|
|
&busiest->active_balance_work);
|
|
}
|
|
|
|
/* We've kicked active balancing, force task migration. */
|
|
sd->nr_balance_failed = sd->cache_nice_tries+1;
|
|
}
|
|
} else
|
|
sd->nr_balance_failed = 0;
|
|
|
|
if (likely(!active_balance)) {
|
|
/* We were unbalanced, so reset the balancing interval */
|
|
sd->balance_interval = sd->min_interval;
|
|
} else {
|
|
/*
|
|
* If we've begun active balancing, start to back off. This
|
|
* case may not be covered by the all_pinned logic if there
|
|
* is only 1 task on the busy runqueue (because we don't call
|
|
* detach_tasks).
|
|
*/
|
|
if (sd->balance_interval < sd->max_interval)
|
|
sd->balance_interval *= 2;
|
|
}
|
|
|
|
goto out;
|
|
|
|
out_balanced:
|
|
/*
|
|
* We reach balance although we may have faced some affinity
|
|
* constraints. Clear the imbalance flag if it was set.
|
|
*/
|
|
if (sd_parent) {
|
|
int *group_imbalance = &sd_parent->groups->sgc->imbalance;
|
|
|
|
if (*group_imbalance)
|
|
*group_imbalance = 0;
|
|
}
|
|
|
|
out_all_pinned:
|
|
/*
|
|
* We reach balance because all tasks are pinned at this level so
|
|
* we can't migrate them. Let the imbalance flag set so parent level
|
|
* can try to migrate them.
|
|
*/
|
|
schedstat_inc(sd->lb_balanced[idle]);
|
|
|
|
sd->nr_balance_failed = 0;
|
|
|
|
out_one_pinned:
|
|
/* tune up the balancing interval */
|
|
if (((env.flags & LBF_ALL_PINNED) &&
|
|
sd->balance_interval < MAX_PINNED_INTERVAL) ||
|
|
(sd->balance_interval < sd->max_interval))
|
|
sd->balance_interval *= 2;
|
|
|
|
ld_moved = 0;
|
|
out:
|
|
return ld_moved;
|
|
}
|
|
|
|
static inline unsigned long
|
|
get_sd_balance_interval(struct sched_domain *sd, int cpu_busy)
|
|
{
|
|
unsigned long interval = sd->balance_interval;
|
|
|
|
if (cpu_busy)
|
|
interval *= sd->busy_factor;
|
|
|
|
/* scale ms to jiffies */
|
|
interval = msecs_to_jiffies(interval);
|
|
interval = clamp(interval, 1UL, max_load_balance_interval);
|
|
|
|
return interval;
|
|
}
|
|
|
|
static inline void
|
|
update_next_balance(struct sched_domain *sd, unsigned long *next_balance)
|
|
{
|
|
unsigned long interval, next;
|
|
|
|
/* used by idle balance, so cpu_busy = 0 */
|
|
interval = get_sd_balance_interval(sd, 0);
|
|
next = sd->last_balance + interval;
|
|
|
|
if (time_after(*next_balance, next))
|
|
*next_balance = next;
|
|
}
|
|
|
|
/*
|
|
* idle_balance is called by schedule() if this_cpu is about to become
|
|
* idle. Attempts to pull tasks from other CPUs.
|
|
*/
|
|
static int idle_balance(struct rq *this_rq, struct rq_flags *rf)
|
|
{
|
|
unsigned long next_balance = jiffies + HZ;
|
|
int this_cpu = this_rq->cpu;
|
|
struct sched_domain *sd;
|
|
int pulled_task = 0;
|
|
u64 curr_cost = 0;
|
|
|
|
/*
|
|
* We must set idle_stamp _before_ calling idle_balance(), such that we
|
|
* measure the duration of idle_balance() as idle time.
|
|
*/
|
|
this_rq->idle_stamp = rq_clock(this_rq);
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
rq_unpin_lock(this_rq, rf);
|
|
|
|
if (this_rq->avg_idle < sysctl_sched_migration_cost ||
|
|
!this_rq->rd->overload) {
|
|
rcu_read_lock();
|
|
sd = rcu_dereference_check_sched_domain(this_rq->sd);
|
|
if (sd)
|
|
update_next_balance(sd, &next_balance);
|
|
rcu_read_unlock();
|
|
|
|
goto out;
|
|
}
|
|
|
|
raw_spin_unlock(&this_rq->lock);
|
|
|
|
update_blocked_averages(this_cpu);
|
|
rcu_read_lock();
|
|
for_each_domain(this_cpu, sd) {
|
|
int continue_balancing = 1;
|
|
u64 t0, domain_cost;
|
|
|
|
if (!(sd->flags & SD_LOAD_BALANCE))
|
|
continue;
|
|
|
|
if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) {
|
|
update_next_balance(sd, &next_balance);
|
|
break;
|
|
}
|
|
|
|
if (sd->flags & SD_BALANCE_NEWIDLE) {
|
|
t0 = sched_clock_cpu(this_cpu);
|
|
|
|
pulled_task = load_balance(this_cpu, this_rq,
|
|
sd, CPU_NEWLY_IDLE,
|
|
&continue_balancing);
|
|
|
|
domain_cost = sched_clock_cpu(this_cpu) - t0;
|
|
if (domain_cost > sd->max_newidle_lb_cost)
|
|
sd->max_newidle_lb_cost = domain_cost;
|
|
|
|
curr_cost += domain_cost;
|
|
}
|
|
|
|
update_next_balance(sd, &next_balance);
|
|
|
|
/*
|
|
* Stop searching for tasks to pull if there are
|
|
* now runnable tasks on this rq.
|
|
*/
|
|
if (pulled_task || this_rq->nr_running > 0)
|
|
break;
|
|
}
|
|
rcu_read_unlock();
|
|
|
|
raw_spin_lock(&this_rq->lock);
|
|
|
|
if (curr_cost > this_rq->max_idle_balance_cost)
|
|
this_rq->max_idle_balance_cost = curr_cost;
|
|
|
|
/*
|
|
* While browsing the domains, we released the rq lock, a task could
|
|
* have been enqueued in the meantime. Since we're not going idle,
|
|
* pretend we pulled a task.
|
|
*/
|
|
if (this_rq->cfs.h_nr_running && !pulled_task)
|
|
pulled_task = 1;
|
|
|
|
out:
|
|
/* Move the next balance forward */
|
|
if (time_after(this_rq->next_balance, next_balance))
|
|
this_rq->next_balance = next_balance;
|
|
|
|
/* Is there a task of a high priority class? */
|
|
if (this_rq->nr_running != this_rq->cfs.h_nr_running)
|
|
pulled_task = -1;
|
|
|
|
if (pulled_task)
|
|
this_rq->idle_stamp = 0;
|
|
|
|
rq_repin_lock(this_rq, rf);
|
|
|
|
return pulled_task;
|
|
}
|
|
|
|
/*
|
|
* active_load_balance_cpu_stop is run by cpu stopper. It pushes
|
|
* running tasks off the busiest CPU onto idle CPUs. It requires at
|
|
* least 1 task to be running on each physical CPU where possible, and
|
|
* avoids physical / logical imbalances.
|
|
*/
|
|
static int active_load_balance_cpu_stop(void *data)
|
|
{
|
|
struct rq *busiest_rq = data;
|
|
int busiest_cpu = cpu_of(busiest_rq);
|
|
int target_cpu = busiest_rq->push_cpu;
|
|
struct rq *target_rq = cpu_rq(target_cpu);
|
|
struct sched_domain *sd;
|
|
struct task_struct *p = NULL;
|
|
struct rq_flags rf;
|
|
|
|
rq_lock_irq(busiest_rq, &rf);
|
|
|
|
/* make sure the requested cpu hasn't gone down in the meantime */
|
|
if (unlikely(busiest_cpu != smp_processor_id() ||
|
|
!busiest_rq->active_balance))
|
|
goto out_unlock;
|
|
|
|
/* Is there any task to move? */
|
|
if (busiest_rq->nr_running <= 1)
|
|
goto out_unlock;
|
|
|
|
/*
|
|
* This condition is "impossible", if it occurs
|
|
* we need to fix it. Originally reported by
|
|
* Bjorn Helgaas on a 128-cpu setup.
|
|
*/
|
|
BUG_ON(busiest_rq == target_rq);
|
|
|
|
/* Search for an sd spanning us and the target CPU. */
|
|
rcu_read_lock();
|
|
for_each_domain(target_cpu, sd) {
|
|
if ((sd->flags & SD_LOAD_BALANCE) &&
|
|
cpumask_test_cpu(busiest_cpu, sched_domain_span(sd)))
|
|
break;
|
|
}
|
|
|
|
if (likely(sd)) {
|
|
struct lb_env env = {
|
|
.sd = sd,
|
|
.dst_cpu = target_cpu,
|
|
.dst_rq = target_rq,
|
|
.src_cpu = busiest_rq->cpu,
|
|
.src_rq = busiest_rq,
|
|
.idle = CPU_IDLE,
|
|
/*
|
|
* can_migrate_task() doesn't need to compute new_dst_cpu
|
|
* for active balancing. Since we have CPU_IDLE, but no
|
|
* @dst_grpmask we need to make that test go away with lying
|
|
* about DST_PINNED.
|
|
*/
|
|
.flags = LBF_DST_PINNED,
|
|
};
|
|
|
|
schedstat_inc(sd->alb_count);
|
|
update_rq_clock(busiest_rq);
|
|
|
|
p = detach_one_task(&env);
|
|
if (p) {
|
|
schedstat_inc(sd->alb_pushed);
|
|
/* Active balancing done, reset the failure counter. */
|
|
sd->nr_balance_failed = 0;
|
|
} else {
|
|
schedstat_inc(sd->alb_failed);
|
|
}
|
|
}
|
|
rcu_read_unlock();
|
|
out_unlock:
|
|
busiest_rq->active_balance = 0;
|
|
rq_unlock(busiest_rq, &rf);
|
|
|
|
if (p)
|
|
attach_one_task(target_rq, p);
|
|
|
|
local_irq_enable();
|
|
|
|
return 0;
|
|
}
|
|
|
|
static inline int on_null_domain(struct rq *rq)
|
|
{
|
|
return unlikely(!rcu_dereference_sched(rq->sd));
|
|
}
|
|
|
|
#ifdef CONFIG_NO_HZ_COMMON
|
|
/*
|
|
* idle load balancing details
|
|
* - When one of the busy CPUs notice that there may be an idle rebalancing
|
|
* needed, they will kick the idle load balancer, which then does idle
|
|
* load balancing for all the idle CPUs.
|
|
*/
|
|
static struct {
|
|
cpumask_var_t idle_cpus_mask;
|
|
atomic_t nr_cpus;
|
|
unsigned long next_balance; /* in jiffy units */
|
|
} nohz ____cacheline_aligned;
|
|
|
|
static inline int find_new_ilb(void)
|
|
{
|
|
int ilb = cpumask_first(nohz.idle_cpus_mask);
|
|
|
|
if (ilb < nr_cpu_ids && idle_cpu(ilb))
|
|
return ilb;
|
|
|
|
return nr_cpu_ids;
|
|
}
|
|
|
|
/*
|
|
* Kick a CPU to do the nohz balancing, if it is time for it. We pick the
|
|
* nohz_load_balancer CPU (if there is one) otherwise fallback to any idle
|
|
* CPU (if there is one).
|
|
*/
|
|
static void nohz_balancer_kick(void)
|
|
{
|
|
int ilb_cpu;
|
|
|
|
nohz.next_balance++;
|
|
|
|
ilb_cpu = find_new_ilb();
|
|
|
|
if (ilb_cpu >= nr_cpu_ids)
|
|
return;
|
|
|
|
if (test_and_set_bit(NOHZ_BALANCE_KICK, nohz_flags(ilb_cpu)))
|
|
return;
|
|
/*
|
|
* Use smp_send_reschedule() instead of resched_cpu().
|
|
* This way we generate a sched IPI on the target cpu which
|
|
* is idle. And the softirq performing nohz idle load balance
|
|
* will be run before returning from the IPI.
|
|
*/
|
|
smp_send_reschedule(ilb_cpu);
|
|
return;
|
|
}
|
|
|
|
void nohz_balance_exit_idle(unsigned int cpu)
|
|
{
|
|
if (unlikely(test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))) {
|
|
/*
|
|
* Completely isolated CPUs don't ever set, so we must test.
|
|
*/
|
|
if (likely(cpumask_test_cpu(cpu, nohz.idle_cpus_mask))) {
|
|
cpumask_clear_cpu(cpu, nohz.idle_cpus_mask);
|
|
atomic_dec(&nohz.nr_cpus);
|
|
}
|
|
clear_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
|
|
}
|
|
}
|
|
|
|
static inline void set_cpu_sd_state_busy(void)
|
|
{
|
|
struct sched_domain *sd;
|
|
int cpu = smp_processor_id();
|
|
|
|
rcu_read_lock();
|
|
sd = rcu_dereference(per_cpu(sd_llc, cpu));
|
|
|
|
if (!sd || !sd->nohz_idle)
|
|
goto unlock;
|
|
sd->nohz_idle = 0;
|
|
|
|
atomic_inc(&sd->shared->nr_busy_cpus);
|
|
unlock:
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
void set_cpu_sd_state_idle(void)
|
|
{
|
|
struct sched_domain *sd;
|
|
int cpu = smp_processor_id();
|
|
|
|
rcu_read_lock();
|
|
sd = rcu_dereference(per_cpu(sd_llc, cpu));
|
|
|
|
if (!sd || sd->nohz_idle)
|
|
goto unlock;
|
|
sd->nohz_idle = 1;
|
|
|
|
atomic_dec(&sd->shared->nr_busy_cpus);
|
|
unlock:
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
/*
|
|
* This routine will record that the cpu is going idle with tick stopped.
|
|
* This info will be used in performing idle load balancing in the future.
|
|
*/
|
|
void nohz_balance_enter_idle(int cpu)
|
|
{
|
|
/*
|
|
* If this cpu is going down, then nothing needs to be done.
|
|
*/
|
|
if (!cpu_active(cpu))
|
|
return;
|
|
|
|
/* Spare idle load balancing on CPUs that don't want to be disturbed: */
|
|
if (!is_housekeeping_cpu(cpu))
|
|
return;
|
|
|
|
if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))
|
|
return;
|
|
|
|
/*
|
|
* If we're a completely isolated CPU, we don't play.
|
|
*/
|
|
if (on_null_domain(cpu_rq(cpu)))
|
|
return;
|
|
|
|
cpumask_set_cpu(cpu, nohz.idle_cpus_mask);
|
|
atomic_inc(&nohz.nr_cpus);
|
|
set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
|
|
}
|
|
#endif
|
|
|
|
static DEFINE_SPINLOCK(balancing);
|
|
|
|
/*
|
|
* Scale the max load_balance interval with the number of CPUs in the system.
|
|
* This trades load-balance latency on larger machines for less cross talk.
|
|
*/
|
|
void update_max_interval(void)
|
|
{
|
|
max_load_balance_interval = HZ*num_online_cpus()/10;
|
|
}
|
|
|
|
/*
|
|
* It checks each scheduling domain to see if it is due to be balanced,
|
|
* and initiates a balancing operation if so.
|
|
*
|
|
* Balancing parameters are set up in init_sched_domains.
|
|
*/
|
|
static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
|
|
{
|
|
int continue_balancing = 1;
|
|
int cpu = rq->cpu;
|
|
unsigned long interval;
|
|
struct sched_domain *sd;
|
|
/* Earliest time when we have to do rebalance again */
|
|
unsigned long next_balance = jiffies + 60*HZ;
|
|
int update_next_balance = 0;
|
|
int need_serialize, need_decay = 0;
|
|
u64 max_cost = 0;
|
|
|
|
update_blocked_averages(cpu);
|
|
|
|
rcu_read_lock();
|
|
for_each_domain(cpu, sd) {
|
|
/*
|
|
* Decay the newidle max times here because this is a regular
|
|
* visit to all the domains. Decay ~1% per second.
|
|
*/
|
|
if (time_after(jiffies, sd->next_decay_max_lb_cost)) {
|
|
sd->max_newidle_lb_cost =
|
|
(sd->max_newidle_lb_cost * 253) / 256;
|
|
sd->next_decay_max_lb_cost = jiffies + HZ;
|
|
need_decay = 1;
|
|
}
|
|
max_cost += sd->max_newidle_lb_cost;
|
|
|
|
if (!(sd->flags & SD_LOAD_BALANCE))
|
|
continue;
|
|
|
|
/*
|
|
* Stop the load balance at this level. There is another
|
|
* CPU in our sched group which is doing load balancing more
|
|
* actively.
|
|
*/
|
|
if (!continue_balancing) {
|
|
if (need_decay)
|
|
continue;
|
|
break;
|
|
}
|
|
|
|
interval = get_sd_balance_interval(sd, idle != CPU_IDLE);
|
|
|
|
need_serialize = sd->flags & SD_SERIALIZE;
|
|
if (need_serialize) {
|
|
if (!spin_trylock(&balancing))
|
|
goto out;
|
|
}
|
|
|
|
if (time_after_eq(jiffies, sd->last_balance + interval)) {
|
|
if (load_balance(cpu, rq, sd, idle, &continue_balancing)) {
|
|
/*
|
|
* The LBF_DST_PINNED logic could have changed
|
|
* env->dst_cpu, so we can't know our idle
|
|
* state even if we migrated tasks. Update it.
|
|
*/
|
|
idle = idle_cpu(cpu) ? CPU_IDLE : CPU_NOT_IDLE;
|
|
}
|
|
sd->last_balance = jiffies;
|
|
interval = get_sd_balance_interval(sd, idle != CPU_IDLE);
|
|
}
|
|
if (need_serialize)
|
|
spin_unlock(&balancing);
|
|
out:
|
|
if (time_after(next_balance, sd->last_balance + interval)) {
|
|
next_balance = sd->last_balance + interval;
|
|
update_next_balance = 1;
|
|
}
|
|
}
|
|
if (need_decay) {
|
|
/*
|
|
* Ensure the rq-wide value also decays but keep it at a
|
|
* reasonable floor to avoid funnies with rq->avg_idle.
|
|
*/
|
|
rq->max_idle_balance_cost =
|
|
max((u64)sysctl_sched_migration_cost, max_cost);
|
|
}
|
|
rcu_read_unlock();
|
|
|
|
/*
|
|
* 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)) {
|
|
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
|
|
/*
|
|
* In CONFIG_NO_HZ_COMMON case, the idle balance kickee will do the
|
|
* rebalancing for all the cpus for whom scheduler ticks are stopped.
|
|
*/
|
|
static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
|
|
{
|
|
int this_cpu = this_rq->cpu;
|
|
struct rq *rq;
|
|
int balance_cpu;
|
|
/* Earliest time when we have to do rebalance again */
|
|
unsigned long next_balance = jiffies + 60*HZ;
|
|
int update_next_balance = 0;
|
|
|
|
if (idle != CPU_IDLE ||
|
|
!test_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu)))
|
|
goto end;
|
|
|
|
for_each_cpu(balance_cpu, nohz.idle_cpus_mask) {
|
|
if (balance_cpu == this_cpu || !idle_cpu(balance_cpu))
|
|
continue;
|
|
|
|
/*
|
|
* If this cpu gets work to do, stop the load balancing
|
|
* work being done for other cpus. Next load
|
|
* balancing owner will pick it up.
|
|
*/
|
|
if (need_resched())
|
|
break;
|
|
|
|
rq = cpu_rq(balance_cpu);
|
|
|
|
/*
|
|
* If time for next balance is due,
|
|
* do the balance.
|
|
*/
|
|
if (time_after_eq(jiffies, rq->next_balance)) {
|
|
struct rq_flags rf;
|
|
|
|
rq_lock_irq(rq, &rf);
|
|
update_rq_clock(rq);
|
|
cpu_load_update_idle(rq);
|
|
rq_unlock_irq(rq, &rf);
|
|
|
|
rebalance_domains(rq, CPU_IDLE);
|
|
}
|
|
|
|
if (time_after(next_balance, rq->next_balance)) {
|
|
next_balance = rq->next_balance;
|
|
update_next_balance = 1;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* 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));
|
|
}
|
|
|
|
/*
|
|
* Current heuristic for kicking the idle load balancer in the presence
|
|
* of an idle cpu in the system.
|
|
* - This rq has more than one task.
|
|
* - This rq has at least one CFS task and the capacity of the CPU is
|
|
* significantly reduced because of RT tasks or IRQs.
|
|
* - At parent of LLC scheduler domain level, this cpu's scheduler group has
|
|
* multiple busy cpu.
|
|
* - For SD_ASYM_PACKING, if the lower numbered cpu's in the scheduler
|
|
* domain span are idle.
|
|
*/
|
|
static inline bool nohz_kick_needed(struct rq *rq)
|
|
{
|
|
unsigned long now = jiffies;
|
|
struct sched_domain_shared *sds;
|
|
struct sched_domain *sd;
|
|
int nr_busy, i, cpu = rq->cpu;
|
|
bool kick = false;
|
|
|
|
if (unlikely(rq->idle_balance))
|
|
return false;
|
|
|
|
/*
|
|
* We may be recently in ticked or tickless idle mode. At the first
|
|
* busy tick after returning from idle, we will update the busy stats.
|
|
*/
|
|
set_cpu_sd_state_busy();
|
|
nohz_balance_exit_idle(cpu);
|
|
|
|
/*
|
|
* None are in tickless mode and hence no need for NOHZ idle load
|
|
* balancing.
|
|
*/
|
|
if (likely(!atomic_read(&nohz.nr_cpus)))
|
|
return false;
|
|
|
|
if (time_before(now, nohz.next_balance))
|
|
return false;
|
|
|
|
if (rq->nr_running >= 2)
|
|
return true;
|
|
|
|
rcu_read_lock();
|
|
sds = rcu_dereference(per_cpu(sd_llc_shared, cpu));
|
|
if (sds) {
|
|
/*
|
|
* XXX: write a coherent comment on why we do this.
|
|
* See also: http://lkml.kernel.org/r/20111202010832.602203411@sbsiddha-desk.sc.intel.com
|
|
*/
|
|
nr_busy = atomic_read(&sds->nr_busy_cpus);
|
|
if (nr_busy > 1) {
|
|
kick = true;
|
|
goto unlock;
|
|
}
|
|
|
|
}
|
|
|
|
sd = rcu_dereference(rq->sd);
|
|
if (sd) {
|
|
if ((rq->cfs.h_nr_running >= 1) &&
|
|
check_cpu_capacity(rq, sd)) {
|
|
kick = true;
|
|
goto unlock;
|
|
}
|
|
}
|
|
|
|
sd = rcu_dereference(per_cpu(sd_asym, cpu));
|
|
if (sd) {
|
|
for_each_cpu(i, sched_domain_span(sd)) {
|
|
if (i == cpu ||
|
|
!cpumask_test_cpu(i, nohz.idle_cpus_mask))
|
|
continue;
|
|
|
|
if (sched_asym_prefer(i, cpu)) {
|
|
kick = true;
|
|
goto unlock;
|
|
}
|
|
}
|
|
}
|
|
unlock:
|
|
rcu_read_unlock();
|
|
return kick;
|
|
}
|
|
#else
|
|
static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { }
|
|
#endif
|
|
|
|
/*
|
|
* run_rebalance_domains is triggered when needed from the scheduler tick.
|
|
* Also triggered for nohz idle balancing (with nohz_balancing_kick set).
|
|
*/
|
|
static __latent_entropy void run_rebalance_domains(struct softirq_action *h)
|
|
{
|
|
struct rq *this_rq = this_rq();
|
|
enum cpu_idle_type idle = this_rq->idle_balance ?
|
|
CPU_IDLE : CPU_NOT_IDLE;
|
|
|
|
/*
|
|
* If this cpu has a pending nohz_balance_kick, then do the
|
|
* balancing on behalf of the other idle cpus whose ticks are
|
|
* stopped. Do nohz_idle_balance *before* rebalance_domains to
|
|
* give the idle cpus a chance to load balance. Else we may
|
|
* load balance only within the local sched_domain hierarchy
|
|
* and abort nohz_idle_balance altogether if we pull some load.
|
|
*/
|
|
nohz_idle_balance(this_rq, idle);
|
|
rebalance_domains(this_rq, idle);
|
|
}
|
|
|
|
/*
|
|
* Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
|
|
*/
|
|
void trigger_load_balance(struct rq *rq)
|
|
{
|
|
/* Don't need to rebalance while attached to NULL domain */
|
|
if (unlikely(on_null_domain(rq)))
|
|
return;
|
|
|
|
if (time_after_eq(jiffies, rq->next_balance))
|
|
raise_softirq(SCHED_SOFTIRQ);
|
|
#ifdef CONFIG_NO_HZ_COMMON
|
|
if (nohz_kick_needed(rq))
|
|
nohz_balancer_kick();
|
|
#endif
|
|
}
|
|
|
|
static void rq_online_fair(struct rq *rq)
|
|
{
|
|
update_sysctl();
|
|
|
|
update_runtime_enabled(rq);
|
|
}
|
|
|
|
static void rq_offline_fair(struct rq *rq)
|
|
{
|
|
update_sysctl();
|
|
|
|
/* Ensure any throttled groups are reachable by pick_next_task */
|
|
unthrottle_offline_cfs_rqs(rq);
|
|
}
|
|
|
|
#endif /* CONFIG_SMP */
|
|
|
|
/*
|
|
* scheduler tick hitting a task of our scheduling class:
|
|
*/
|
|
static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
|
|
{
|
|
struct cfs_rq *cfs_rq;
|
|
struct sched_entity *se = &curr->se;
|
|
|
|
for_each_sched_entity(se) {
|
|
cfs_rq = cfs_rq_of(se);
|
|
entity_tick(cfs_rq, se, queued);
|
|
}
|
|
|
|
if (static_branch_unlikely(&sched_numa_balancing))
|
|
task_tick_numa(rq, curr);
|
|
}
|
|
|
|
/*
|
|
* called on fork with the child task as argument from the parent's context
|
|
* - child not yet on the tasklist
|
|
* - preemption disabled
|
|
*/
|
|
static void task_fork_fair(struct task_struct *p)
|
|
{
|
|
struct cfs_rq *cfs_rq;
|
|
struct sched_entity *se = &p->se, *curr;
|
|
struct rq *rq = this_rq();
|
|
struct rq_flags rf;
|
|
|
|
rq_lock(rq, &rf);
|
|
update_rq_clock(rq);
|
|
|
|
cfs_rq = task_cfs_rq(current);
|
|
curr = cfs_rq->curr;
|
|
if (curr) {
|
|
update_curr(cfs_rq);
|
|
se->vruntime = curr->vruntime;
|
|
}
|
|
place_entity(cfs_rq, se, 1);
|
|
|
|
if (sysctl_sched_child_runs_first && curr && entity_before(curr, se)) {
|
|
/*
|
|
* Upon rescheduling, sched_class::put_prev_task() will place
|
|
* 'current' within the tree based on its new key value.
|
|
*/
|
|
swap(curr->vruntime, se->vruntime);
|
|
resched_curr(rq);
|
|
}
|
|
|
|
se->vruntime -= cfs_rq->min_vruntime;
|
|
rq_unlock(rq, &rf);
|
|
}
|
|
|
|
/*
|
|
* Priority of the task has changed. Check to see if we preempt
|
|
* the current task.
|
|
*/
|
|
static void
|
|
prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
|
|
{
|
|
if (!task_on_rq_queued(p))
|
|
return;
|
|
|
|
/*
|
|
* Reschedule if we are currently running on this runqueue and
|
|
* our priority decreased, or if we are not currently running on
|
|
* this runqueue and our priority is higher than the current's
|
|
*/
|
|
if (rq->curr == p) {
|
|
if (p->prio > oldprio)
|
|
resched_curr(rq);
|
|
} else
|
|
check_preempt_curr(rq, p, 0);
|
|
}
|
|
|
|
static inline bool vruntime_normalized(struct task_struct *p)
|
|
{
|
|
struct sched_entity *se = &p->se;
|
|
|
|
/*
|
|
* 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:
|
|
*
|
|
* - 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 (!se->sum_exec_runtime || p->state == TASK_WAKING)
|
|
return true;
|
|
|
|
return false;
|
|
}
|
|
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
/*
|
|
* Propagate the changes of the sched_entity across the tg tree to make it
|
|
* visible to the root
|
|
*/
|
|
static void propagate_entity_cfs_rq(struct sched_entity *se)
|
|
{
|
|
struct cfs_rq *cfs_rq;
|
|
|
|
/* Start to propagate at parent */
|
|
se = se->parent;
|
|
|
|
for_each_sched_entity(se) {
|
|
cfs_rq = cfs_rq_of(se);
|
|
|
|
if (cfs_rq_throttled(cfs_rq))
|
|
break;
|
|
|
|
update_load_avg(se, UPDATE_TG);
|
|
}
|
|
}
|
|
#else
|
|
static void propagate_entity_cfs_rq(struct sched_entity *se) { }
|
|
#endif
|
|
|
|
static void detach_entity_cfs_rq(struct sched_entity *se)
|
|
{
|
|
struct cfs_rq *cfs_rq = cfs_rq_of(se);
|
|
|
|
/* Catch up with the cfs_rq and remove our load when we leave */
|
|
update_load_avg(se, 0);
|
|
detach_entity_load_avg(cfs_rq, se);
|
|
update_tg_load_avg(cfs_rq, false);
|
|
propagate_entity_cfs_rq(se);
|
|
}
|
|
|
|
static void attach_entity_cfs_rq(struct sched_entity *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
|
|
|
|
/* Synchronize entity with its cfs_rq */
|
|
update_load_avg(se, sched_feat(ATTACH_AGE_LOAD) ? 0 : SKIP_AGE_LOAD);
|
|
attach_entity_load_avg(cfs_rq, se);
|
|
update_tg_load_avg(cfs_rq, false);
|
|
propagate_entity_cfs_rq(se);
|
|
}
|
|
|
|
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.
|
|
*/
|
|
place_entity(cfs_rq, se, 0);
|
|
se->vruntime -= cfs_rq->min_vruntime;
|
|
}
|
|
|
|
detach_entity_cfs_rq(se);
|
|
}
|
|
|
|
static void attach_task_cfs_rq(struct task_struct *p)
|
|
{
|
|
struct sched_entity *se = &p->se;
|
|
struct cfs_rq *cfs_rq = cfs_rq_of(se);
|
|
|
|
attach_entity_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.
|
|
*
|
|
* This routine is mostly called to set cfs_rq->curr field when a task
|
|
* migrates between groups/classes.
|
|
*/
|
|
static void set_curr_task_fair(struct rq *rq)
|
|
{
|
|
struct sched_entity *se = &rq->curr->se;
|
|
|
|
for_each_sched_entity(se) {
|
|
struct cfs_rq *cfs_rq = cfs_rq_of(se);
|
|
|
|
set_next_entity(cfs_rq, se);
|
|
/* ensure bandwidth has been allocated on our new cfs_rq */
|
|
account_cfs_rq_runtime(cfs_rq, 0);
|
|
}
|
|
}
|
|
|
|
void init_cfs_rq(struct cfs_rq *cfs_rq)
|
|
{
|
|
cfs_rq->tasks_timeline = RB_ROOT;
|
|
cfs_rq->min_vruntime = (u64)(-(1LL << 20));
|
|
#ifndef CONFIG_64BIT
|
|
cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
|
|
#endif
|
|
#ifdef CONFIG_SMP
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
cfs_rq->propagate_avg = 0;
|
|
#endif
|
|
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_set_group_fair(struct task_struct *p)
|
|
{
|
|
struct sched_entity *se = &p->se;
|
|
|
|
set_task_rq(p, task_cpu(p));
|
|
se->depth = se->parent ? se->parent->depth + 1 : 0;
|
|
}
|
|
|
|
static void task_move_group_fair(struct task_struct *p)
|
|
{
|
|
detach_task_cfs_rq(p);
|
|
set_task_rq(p, task_cpu(p));
|
|
|
|
#ifdef CONFIG_SMP
|
|
/* Tell se's cfs_rq has been changed -- migrated */
|
|
p->se.avg.last_update_time = 0;
|
|
#endif
|
|
attach_task_cfs_rq(p);
|
|
}
|
|
|
|
static void task_change_group_fair(struct task_struct *p, int type)
|
|
{
|
|
switch (type) {
|
|
case TASK_SET_GROUP:
|
|
task_set_group_fair(p);
|
|
break;
|
|
|
|
case TASK_MOVE_GROUP:
|
|
task_move_group_fair(p);
|
|
break;
|
|
}
|
|
}
|
|
|
|
void free_fair_sched_group(struct task_group *tg)
|
|
{
|
|
int i;
|
|
|
|
destroy_cfs_bandwidth(tg_cfs_bandwidth(tg));
|
|
|
|
for_each_possible_cpu(i) {
|
|
if (tg->cfs_rq)
|
|
kfree(tg->cfs_rq[i]);
|
|
if (tg->se)
|
|
kfree(tg->se[i]);
|
|
}
|
|
|
|
kfree(tg->cfs_rq);
|
|
kfree(tg->se);
|
|
}
|
|
|
|
int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
|
|
{
|
|
struct sched_entity *se;
|
|
struct cfs_rq *cfs_rq;
|
|
int i;
|
|
|
|
tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL);
|
|
if (!tg->cfs_rq)
|
|
goto err;
|
|
tg->se = kzalloc(sizeof(se) * nr_cpu_ids, GFP_KERNEL);
|
|
if (!tg->se)
|
|
goto err;
|
|
|
|
tg->shares = NICE_0_LOAD;
|
|
|
|
init_cfs_bandwidth(tg_cfs_bandwidth(tg));
|
|
|
|
for_each_possible_cpu(i) {
|
|
cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
|
|
GFP_KERNEL, cpu_to_node(i));
|
|
if (!cfs_rq)
|
|
goto err;
|
|
|
|
se = kzalloc_node(sizeof(struct sched_entity),
|
|
GFP_KERNEL, cpu_to_node(i));
|
|
if (!se)
|
|
goto err_free_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;
|
|
|
|
err_free_rq:
|
|
kfree(cfs_rq);
|
|
err:
|
|
return 0;
|
|
}
|
|
|
|
void online_fair_sched_group(struct task_group *tg)
|
|
{
|
|
struct sched_entity *se;
|
|
struct rq *rq;
|
|
int i;
|
|
|
|
for_each_possible_cpu(i) {
|
|
rq = cpu_rq(i);
|
|
se = tg->se[i];
|
|
|
|
raw_spin_lock_irq(&rq->lock);
|
|
update_rq_clock(rq);
|
|
attach_entity_cfs_rq(se);
|
|
sync_throttle(tg, i);
|
|
raw_spin_unlock_irq(&rq->lock);
|
|
}
|
|
}
|
|
|
|
void unregister_fair_sched_group(struct task_group *tg)
|
|
{
|
|
unsigned long flags;
|
|
struct rq *rq;
|
|
int cpu;
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
if (tg->se[cpu])
|
|
remove_entity_load_avg(tg->se[cpu]);
|
|
|
|
/*
|
|
* Only empty task groups can be destroyed; so we can speculatively
|
|
* check on_list without danger of it being re-added.
|
|
*/
|
|
if (!tg->cfs_rq[cpu]->on_list)
|
|
continue;
|
|
|
|
rq = cpu_rq(cpu);
|
|
|
|
raw_spin_lock_irqsave(&rq->lock, flags);
|
|
list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
|
|
raw_spin_unlock_irqrestore(&rq->lock, flags);
|
|
}
|
|
}
|
|
|
|
void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
|
|
struct sched_entity *se, int cpu,
|
|
struct sched_entity *parent)
|
|
{
|
|
struct rq *rq = cpu_rq(cpu);
|
|
|
|
cfs_rq->tg = tg;
|
|
cfs_rq->rq = rq;
|
|
init_cfs_rq_runtime(cfs_rq);
|
|
|
|
tg->cfs_rq[cpu] = cfs_rq;
|
|
tg->se[cpu] = se;
|
|
|
|
/* se could be NULL for root_task_group */
|
|
if (!se)
|
|
return;
|
|
|
|
if (!parent) {
|
|
se->cfs_rq = &rq->cfs;
|
|
se->depth = 0;
|
|
} else {
|
|
se->cfs_rq = parent->my_q;
|
|
se->depth = parent->depth + 1;
|
|
}
|
|
|
|
se->my_q = cfs_rq;
|
|
/* guarantee group entities always have weight */
|
|
update_load_set(&se->load, NICE_0_LOAD);
|
|
se->parent = parent;
|
|
}
|
|
|
|
static DEFINE_MUTEX(shares_mutex);
|
|
|
|
int sched_group_set_shares(struct task_group *tg, unsigned long shares)
|
|
{
|
|
int i;
|
|
|
|
/*
|
|
* We can't change the weight of the root cgroup.
|
|
*/
|
|
if (!tg->se[0])
|
|
return -EINVAL;
|
|
|
|
shares = clamp(shares, scale_load(MIN_SHARES), scale_load(MAX_SHARES));
|
|
|
|
mutex_lock(&shares_mutex);
|
|
if (tg->shares == shares)
|
|
goto done;
|
|
|
|
tg->shares = shares;
|
|
for_each_possible_cpu(i) {
|
|
struct rq *rq = cpu_rq(i);
|
|
struct sched_entity *se = tg->se[i];
|
|
struct rq_flags rf;
|
|
|
|
/* Propagate contribution to hierarchy */
|
|
rq_lock_irqsave(rq, &rf);
|
|
update_rq_clock(rq);
|
|
for_each_sched_entity(se) {
|
|
update_load_avg(se, UPDATE_TG);
|
|
update_cfs_shares(se);
|
|
}
|
|
rq_unlock_irqrestore(rq, &rf);
|
|
}
|
|
|
|
done:
|
|
mutex_unlock(&shares_mutex);
|
|
return 0;
|
|
}
|
|
#else /* CONFIG_FAIR_GROUP_SCHED */
|
|
|
|
void free_fair_sched_group(struct task_group *tg) { }
|
|
|
|
int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
void online_fair_sched_group(struct task_group *tg) { }
|
|
|
|
void unregister_fair_sched_group(struct task_group *tg) { }
|
|
|
|
#endif /* CONFIG_FAIR_GROUP_SCHED */
|
|
|
|
|
|
static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task)
|
|
{
|
|
struct sched_entity *se = &task->se;
|
|
unsigned int rr_interval = 0;
|
|
|
|
/*
|
|
* Time slice is 0 for SCHED_OTHER tasks that are on an otherwise
|
|
* idle runqueue:
|
|
*/
|
|
if (rq->cfs.load.weight)
|
|
rr_interval = NS_TO_JIFFIES(sched_slice(cfs_rq_of(se), se));
|
|
|
|
return rr_interval;
|
|
}
|
|
|
|
/*
|
|
* All the scheduling class methods:
|
|
*/
|
|
const struct sched_class fair_sched_class = {
|
|
.next = &idle_sched_class,
|
|
.enqueue_task = enqueue_task_fair,
|
|
.dequeue_task = dequeue_task_fair,
|
|
.yield_task = yield_task_fair,
|
|
.yield_to_task = yield_to_task_fair,
|
|
|
|
.check_preempt_curr = check_preempt_wakeup,
|
|
|
|
.pick_next_task = pick_next_task_fair,
|
|
.put_prev_task = put_prev_task_fair,
|
|
|
|
#ifdef CONFIG_SMP
|
|
.select_task_rq = select_task_rq_fair,
|
|
.migrate_task_rq = migrate_task_rq_fair,
|
|
|
|
.rq_online = rq_online_fair,
|
|
.rq_offline = rq_offline_fair,
|
|
|
|
.task_dead = task_dead_fair,
|
|
.set_cpus_allowed = set_cpus_allowed_common,
|
|
#endif
|
|
|
|
.set_curr_task = set_curr_task_fair,
|
|
.task_tick = task_tick_fair,
|
|
.task_fork = task_fork_fair,
|
|
|
|
.prio_changed = prio_changed_fair,
|
|
.switched_from = switched_from_fair,
|
|
.switched_to = switched_to_fair,
|
|
|
|
.get_rr_interval = get_rr_interval_fair,
|
|
|
|
.update_curr = update_curr_fair,
|
|
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
.task_change_group = task_change_group_fair,
|
|
#endif
|
|
};
|
|
|
|
#ifdef CONFIG_SCHED_DEBUG
|
|
void print_cfs_stats(struct seq_file *m, int cpu)
|
|
{
|
|
struct cfs_rq *cfs_rq, *pos;
|
|
|
|
rcu_read_lock();
|
|
for_each_leaf_cfs_rq_safe(cpu_rq(cpu), cfs_rq, pos)
|
|
print_cfs_rq(m, cpu, cfs_rq);
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
#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)
|
|
{
|
|
#ifdef CONFIG_SMP
|
|
open_softirq(SCHED_SOFTIRQ, run_rebalance_domains);
|
|
|
|
#ifdef CONFIG_NO_HZ_COMMON
|
|
nohz.next_balance = jiffies;
|
|
zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT);
|
|
#endif
|
|
#endif /* SMP */
|
|
|
|
}
|