blob: f21398b43673a3a3eb88e004acc8d8adaebd07d3 [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0
/*
* 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 "sched.h"
#include <trace/events/sched.h>
#include <trace/hooks/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;
static 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;
static 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;
static 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;
}
/*
* The margin used when comparing utilization with CPU capacity.
*
* (default: ~20%)
*/
#define fits_capacity(cap, max) ((cap) * 1280 < (max) * 1024)
#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
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
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 cfs_rq_tg_path(struct cfs_rq *cfs_rq, char *path, int len)
{
if (!path)
return;
if (cfs_rq && task_group_is_autogroup(cfs_rq->tg))
autogroup_path(cfs_rq->tg, path, len);
else if (cfs_rq && cfs_rq->tg->css.cgroup)
cgroup_path(cfs_rq->tg->css.cgroup, path, len);
else
strlcpy(path, "(null)", len);
}
static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
{
struct rq *rq = rq_of(cfs_rq);
int cpu = cpu_of(rq);
if (cfs_rq->on_list)
return rq->tmp_alone_branch == &rq->leaf_cfs_rq_list;
cfs_rq->on_list = 1;
/*
* 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 top 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;
return true;
}
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 top 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;
return true;
}
/*
* 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 begin 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 begin
* of the branch
*/
rq->tmp_alone_branch = &cfs_rq->leaf_cfs_rq_list;
return false;
}
static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
{
if (cfs_rq->on_list) {
struct rq *rq = rq_of(cfs_rq);
/*
* With cfs_rq being unthrottled/throttled during an enqueue,
* it can happen the tmp_alone_branch points the a leaf that
* we finally want to del. In this case, tmp_alone_branch moves
* to the prev element but it will point to rq->leaf_cfs_rq_list
* at the end of the enqueue.
*/
if (rq->tmp_alone_branch == &cfs_rq->leaf_cfs_rq_list)
rq->tmp_alone_branch = cfs_rq->leaf_cfs_rq_list.prev;
list_del_rcu(&cfs_rq->leaf_cfs_rq_list);
cfs_rq->on_list = 0;
}
}
static inline void assert_list_leaf_cfs_rq(struct rq *rq)
{
SCHED_WARN_ON(rq->tmp_alone_branch != &rq->leaf_cfs_rq_list);
}
/* 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);
}
#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 cfs_rq_tg_path(struct cfs_rq *cfs_rq, char *path, int len)
{
if (path)
strlcpy(path, "(null)", len);
}
static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
{
return true;
}
static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
{
}
static inline void assert_list_leaf_cfs_rq(struct rq *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;
struct rb_node *leftmost = rb_first_cached(&cfs_rq->tasks_timeline);
u64 vruntime = cfs_rq->min_vruntime;
if (curr) {
if (curr->on_rq)
vruntime = curr->vruntime;
else
curr = NULL;
}
if (leftmost) { /* non-empty tree */
struct sched_entity *se;
se = rb_entry(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_root.rb_node;
struct rb_node *parent = NULL;
struct sched_entity *entry;
bool leftmost = true;
/*
* 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 = false;
}
}
rb_link_node(&se->run_node, parent, link);
rb_insert_color_cached(&se->run_node,
&cfs_rq->tasks_timeline, leftmost);
}
static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
rb_erase_cached(&se->run_node, &cfs_rq->tasks_timeline);
}
struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
{
struct rb_node *left = rb_first_cached(&cfs_rq->tasks_timeline);
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.rb_root);
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);
}
#include "pelt.h"
#ifdef CONFIG_SMP
static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu);
static unsigned long task_h_load(struct task_struct *p);
static unsigned long capacity_of(int cpu);
/* 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;
memset(sa, 0, sizeof(*sa));
/*
* Tasks are initialized with full load to be seen as heavy tasks until
* they get a chance to stabilize to their real load level.
* Group entities are initialized with zero load to reflect the fact that
* nothing has been attached to the task group yet.
*/
if (entity_is_task(se))
sa->runnable_load_avg = sa->load_avg = scale_load_down(se->load.weight);
se->runnable_weight = se->load.weight;
/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
}
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 = (cpu_scale - cfs_rq->avg.util_avg) / 2^n
*
* where n denotes the nth task and cpu_scale the CPU capacity.
*
* For example, for a CPU with 1024 of capacity, 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 task_struct *p)
{
struct sched_entity *se = &p->se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
struct sched_avg *sa = &se->avg;
long cpu_scale = arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq)));
long cap = (long)(cpu_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;
}
}
if (p->sched_class != &fair_sched_class) {
/*
* For !fair tasks do:
*
update_cfs_rq_load_avg(now, cfs_rq);
attach_entity_load_avg(cfs_rq, se, 0);
switched_from_fair(rq, p);
*
* such that the next switched_to_fair() has the
* expected state.
*/
se->avg.last_update_time = cfs_rq_clock_pelt(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 task_struct *p)
{
}
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);
cgroup_account_cputime(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);
trace_sched_blocked_reason(tsk);
/*
* 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;
struct numa_group {
refcount_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];
};
/*
* For functions that can be called in multiple contexts that permit reading
* ->numa_group (see struct task_struct for locking rules).
*/
static struct numa_group *deref_task_numa_group(struct task_struct *p)
{
return rcu_dereference_check(p->numa_group, p == current ||
(lockdep_is_held(&task_rq(p)->lock) && !READ_ONCE(p->on_cpu)));
}
static struct numa_group *deref_curr_numa_group(struct task_struct *p)
{
return rcu_dereference_protected(p->numa_group, p == current);
}
static inline unsigned long group_faults_priv(struct numa_group *ng);
static inline unsigned long group_faults_shared(struct numa_group *ng);
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_start(struct task_struct *p)
{
unsigned long smin = task_scan_min(p);
unsigned long period = smin;
struct numa_group *ng;
/* Scale the maximum scan period with the amount of shared memory. */
rcu_read_lock();
ng = rcu_dereference(p->numa_group);
if (ng) {
unsigned long shared = group_faults_shared(ng);
unsigned long private = group_faults_priv(ng);
period *= refcount_read(&ng->refcount);
period *= shared + 1;
period /= private + shared + 1;
}
rcu_read_unlock();
return max(smin, period);
}
static unsigned int task_scan_max(struct task_struct *p)
{
unsigned long smin = task_scan_min(p);
unsigned long smax;
struct numa_group *ng;
/* Watch for min being lower than max due to floor calculations */
smax = sysctl_numa_balancing_scan_period_max / task_nr_scan_windows(p);
/* Scale the maximum scan period with the amount of shared memory. */
ng = deref_curr_numa_group(p);
if (ng) {
unsigned long shared = group_faults_shared(ng);
unsigned long private = group_faults_priv(ng);
unsigned long period = smax;
period *= refcount_read(&ng->refcount);
period *= shared + 1;
period /= private + shared + 1;
smax = max(smax, period);
}
return max(smin, smax);
}
static void account_numa_enqueue(struct rq *rq, struct task_struct *p)
{
rq->nr_numa_running += (p->numa_preferred_nid != NUMA_NO_NODE);
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 != NUMA_NO_NODE);
rq->nr_preferred_running -= (p->numa_preferred_nid == task_node(p));
}
/* 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)
{
struct numa_group *ng;
pid_t gid = 0;
rcu_read_lock();
ng = rcu_dereference(p->numa_group);
if (ng)
gid = ng->gid;
rcu_read_unlock();
return gid;
}
/*
* 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)
{
struct numa_group *ng = deref_task_numa_group(p);
if (!ng)
return 0;
return ng->faults[task_faults_idx(NUMA_MEM, nid, 0)] +
ng->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)];
}
static inline unsigned long group_faults_priv(struct numa_group *ng)
{
unsigned long faults = 0;
int node;
for_each_online_node(node) {
faults += ng->faults[task_faults_idx(NUMA_MEM, node, 1)];
}
return faults;
}
static inline unsigned long group_faults_shared(struct numa_group *ng)
{
unsigned long faults = 0;
int node;
for_each_online_node(node) {
faults += ng->faults[task_faults_idx(NUMA_MEM, node, 0)];
}
return faults;
}
/*
* 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)
{
struct numa_group *ng = deref_task_numa_group(p);
unsigned long faults, total_faults;
if (!ng)
return 0;
total_faults = ng->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 = deref_curr_numa_group(p);
int dst_nid = cpu_to_node(dst_cpu);
int last_cpupid, this_cpupid;
this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid);
last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
/*
* Allow first faults or private faults to migrate immediately early in
* the lifetime of a task. The magic number 4 is based on waiting for
* two full passes of the "multi-stage node selection" test that is
* executed below.
*/
if ((p->numa_preferred_nid == NUMA_NO_NODE || p->numa_scan_seq <= 4) &&
(cpupid_pid_unset(last_cpupid) || cpupid_match_pid(p, last_cpupid)))
return true;
/*
* 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.
*/
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 cpu_runnable_load(struct rq *rq);
/* Cached statistics for all CPUs within a node */
struct numa_stats {
unsigned long load;
/* Total compute capacity of CPUs on a node */
unsigned long compute_capacity;
};
/*
* XXX borrowed from update_sg_lb_stats
*/
static void update_numa_stats(struct numa_stats *ns, int nid)
{
int cpu;
memset(ns, 0, sizeof(*ns));
for_each_cpu(cpu, cpumask_of_node(nid)) {
struct rq *rq = cpu_rq(cpu);
ns->load += cpu_runnable_load(rq);
ns->compute_capacity += capacity_of(cpu);
}
}
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)
{
struct rq *rq = cpu_rq(env->dst_cpu);
/* Bail out if run-queue part of active NUMA balance. */
if (xchg(&rq->numa_migrate_on, 1))
return;
/*
* Clear previous best_cpu/rq numa-migrate flag, since task now
* found a better CPU to move/swap.
*/
if (env->best_cpu != -1) {
rq = cpu_rq(env->best_cpu);
WRITE_ONCE(rq->numa_migrate_on, 0);
}
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;
imb = abs(dst_load * src_capacity - src_load * dst_capacity);
orig_src_load = env->src_stats.load;
orig_dst_load = env->dst_stats.load;
old_imb = abs(orig_dst_load * src_capacity - orig_src_load * dst_capacity);
/* Would this change make things worse? */
return (imb > old_imb);
}
/*
* Maximum NUMA importance can be 1998 (2*999);
* SMALLIMP @ 30 would be close to 1998/64.
* Used to deter task migration.
*/
#define SMALLIMP 30
/*
* 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, bool maymove)
{
struct numa_group *cur_ng, *p_ng = deref_curr_numa_group(env->p);
struct rq *dst_rq = cpu_rq(env->dst_cpu);
long imp = p_ng ? groupimp : taskimp;
struct task_struct *cur;
long src_load, dst_load;
int dist = env->dist;
long moveimp = imp;
long load;
if (READ_ONCE(dst_rq->numa_migrate_on))
return;
rcu_read_lock();
cur = 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;
if (!cur) {
if (maymove && moveimp >= env->best_imp)
goto assign;
else
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 remote accesses that would be expected to
* be incurred if the tasks were swapped.
*/
/* Skip this swap candidate if cannot move to the source cpu */
if (!cpumask_test_cpu(env->src_cpu, cur->cpus_ptr))
goto unlock;
/*
* If dst and source tasks are in the same NUMA group, or not
* in any group then look only at task weights.
*/
cur_ng = rcu_dereference(cur->numa_group);
if (cur_ng == p_ng) {
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_ng)
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_ng && p_ng)
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 (maymove && moveimp > imp && moveimp > env->best_imp) {
imp = moveimp;
cur = NULL;
goto assign;
}
/*
* If the NUMA importance is less than SMALLIMP,
* task migration might only result in ping pong
* of tasks and also hurt performance due to cache
* misses.
*/
if (imp < SMALLIMP || imp <= env->best_imp + SMALLIMP / 2)
goto unlock;
/*
* In the overloaded case, try and keep the load balanced.
*/
load = task_h_load(env->p) - task_h_load(cur);
if (!load)
goto assign;
dst_load = env->dst_stats.load + load;
src_load = env->src_stats.load - load;
if (load_too_imbalanced(src_load, dst_load, env))
goto unlock;
assign:
/*
* 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();
}
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)
{
long src_load, dst_load, load;
bool maymove = false;
int cpu;
load = task_h_load(env->p);
dst_load = env->dst_stats.load + load;
src_load = env->src_stats.load - load;
/*
* If the improvement from just moving env->p direction is better
* than swapping tasks around, check if a move is possible.
*/
maymove = !load_too_imbalanced(src_load, dst_load, env);
for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) {
/* Skip this CPU if the source task cannot migrate */
if (!cpumask_test_cpu(cpu, env->p->cpus_ptr))
continue;
env->dst_cpu = cpu;
task_numa_compare(env, taskimp, groupimp, maymove);
}
}
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,
};
unsigned long taskweight, groupweight;
struct sched_domain *sd;
long taskimp, groupimp;
struct numa_group *ng;
struct rq *best_rq;
int nid, ret, dist;
/*
* 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)) {
sched_setnuma(p, 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. */
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.
*/
ng = deref_curr_numa_group(p);
if (env.best_cpu == -1 || (ng && ng->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);
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 (ng) {
if (env.best_cpu == -1)
nid = env.src_nid;
else
nid = cpu_to_node(env.best_cpu);
if (nid != p->numa_preferred_nid)
sched_setnuma(p, nid);
}
/* No better CPU than the current one was found. */
if (env.best_cpu == -1)
return -EAGAIN;
best_rq = cpu_rq(env.best_cpu);
if (env.best_task == NULL) {
ret = migrate_task_to(p, env.best_cpu);
WRITE_ONCE(best_rq->numa_migrate_on, 0);
if (ret != 0)
trace_sched_stick_numa(p, env.src_cpu, env.best_cpu);
return ret;
}
ret = migrate_swap(p, env.best_task, env.best_cpu, env.src_cpu);
WRITE_ONCE(best_rq->numa_migrate_on, 0);
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 == NUMA_NO_NODE || !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 lr_ratio, ps_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);
lr_ratio = (local * NUMA_PERIOD_SLOTS) / (local + remote);
ps_ratio = (private * NUMA_PERIOD_SLOTS) / (private + shared);
if (ps_ratio >= NUMA_PERIOD_THRESHOLD) {
/*
* Most memory accesses are local. There is no need to
* do fast NUMA scanning, since memory is already local.
*/
int slot = ps_ratio - NUMA_PERIOD_THRESHOLD;
if (!slot)
slot = 1;
diff = slot * period_slot;
} else if (lr_ratio >= NUMA_PERIOD_THRESHOLD) {
/*
* Most memory accesses are shared with other tasks.
* There is no point in continuing fast NUMA scanning,
* since other tasks may just move the memory elsewhere.
*/
int slot = lr_ratio - NUMA_PERIOD_THRESHOLD;
if (!slot)
slot = 1;
diff = slot * period_slot;
} else {
/*
* Private memory faults exceed (SLOTS-THRESHOLD)/SLOTS,
* yet they are not on the local NUMA node. Speed up
* NUMA scanning to get the memory moved over.
*/
int ratio = max(lr_ratio, ps_ratio);
diff = -(NUMA_PERIOD_THRESHOLD - ratio) * period_slot;
}
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;
/* Avoid time going backwards, prevent potential divide error: */
if (unlikely((s64)*period < 0))
*period = 0;
} else {
delta = p->se.avg.load_sum;
*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 = NUMA_NO_NODE;
unsigned long max_faults = 0;
unsigned long fault_types[2] = { 0, 0 };
unsigned long total_faults;
u64 runtime, period;
spinlock_t *group_lock = NULL;
struct numa_group *ng;
/*
* 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 */
ng = deref_curr_numa_group(p);
if (ng) {
group_lock = &ng->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 (ng) {
/*
* 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.
*/
ng->faults[mem_idx] += diff;
ng->faults_cpu[mem_idx] += f_diff;
ng->total_faults += diff;
group_faults += ng->faults[mem_idx];
}
}
if (!ng) {
if (faults > max_faults) {
max_faults = faults;
max_nid = nid;
}
} else if (group_faults > max_faults) {
max_faults = group_faults;
max_nid = nid;
}
}
if (ng) {
numa_group_count_active_nodes(ng);
spin_unlock_irq(group_lock);
max_nid = preferred_group_nid(p, max_nid);
}
if (max_faults) {
/* Set the new preferred node */
if (max_nid != p->numa_preferred_nid)
sched_setnuma(p, max_nid);
}
update_task_scan_period(p, fault_types[0], fault_types[1]);
}
static inline int get_numa_group(struct numa_group *grp)
{
return refcount_inc_not_zero(&grp->refcount);
}
static inline void put_numa_group(struct numa_group *grp)
{
if (refcount_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(!deref_curr_numa_group(p))) {
unsigned int size = sizeof(struct numa_group) +
4*nr_node_ids*sizeof(unsigned long);
grp = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
if (!grp)
return;
refcount_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 = deref_curr_numa_group(p);
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;
}
/*
* Get rid of NUMA staticstics associated with a task (either current or dead).
* If @final is set, the task is dead and has reached refcount zero, so we can
* safely free all relevant data structures. Otherwise, there might be
* concurrent reads from places like load balancing and procfs, and we should
* reset the data back to default state without freeing ->numa_faults.
*/
void task_numa_free(struct task_struct *p, bool final)
{
/* safe: p either is current or is being freed by current */
struct numa_group *grp = rcu_dereference_raw(p->numa_group);
unsigned long *numa_faults = p->numa_faults;
unsigned long flags;
int i;
if (!numa_faults)
return;
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);
}
if (final) {
p->numa_faults = NULL;
kfree(numa_faults);
} else {
p->total_numa_faults = 0;
for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
numa_faults[i] = 0;
}
}
/*
* 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 = deref_curr_numa_group(p);
if (!priv && !local && ng && ng->active_nodes > 1 &&
numa_is_active_node(cpu_node, ng) &&
numa_is_active_node(mem_node, ng))
local = 1;
/*
* Retry to migrate task to preferred node periodically, in case it
* previously failed, or the scheduler moved us.
*/
if (time_after(jiffies, p->numa_migrate_retry)) {
task_numa_placement(p);
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().
*/
static 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;
/*
* 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_start(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;
}
}
void init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
{
int mm_users = 0;
struct mm_struct *mm = p->mm;
if (mm) {
mm_users = atomic_read(&mm->mm_users);
if (mm_users == 1) {
mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
mm->numa_scan_seq = 0;
}
}
p->node_stamp = 0;
p->numa_scan_seq = mm ? mm->numa_scan_seq : 0;
p->numa_scan_period = sysctl_numa_balancing_scan_delay;
/* Protect against double add, see task_tick_numa and task_numa_work */
p->numa_work.next = &p->numa_work;
p->numa_faults = NULL;
RCU_INIT_POINTER(p->numa_group, NULL);
p->last_task_numa_placement = 0;
p->last_sum_exec_runtime = 0;
init_task_work(&p->numa_work, task_numa_work);
/* New address space, reset the preferred nid */
if (!(clone_flags & CLONE_VM)) {
p->numa_preferred_nid = NUMA_NO_NODE;
return;
}
/*
* New thread, keep existing numa_preferred_nid which should be copied
* already by arch_dup_task_struct but stagger when scans start.
*/
if (mm) {
unsigned int delay;
delay = min_t(unsigned int, task_scan_max(current),
current->numa_scan_period * mm_users * NSEC_PER_MSEC);
delay += 2 * TICK_NSEC;
p->node_stamp = delay;
}
}
/*
* Drive the periodic memory faults..
*/
static 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->flags & (PF_EXITING | PF_KTHREAD)) || 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_start(curr);
curr->node_stamp += period;
if (!time_before(jiffies, curr->mm->numa_next_scan))
task_work_add(curr, work, true);
}
}
static void update_scan_period(struct task_struct *p, int new_cpu)
{
int src_nid = cpu_to_node(task_cpu(p));
int dst_nid = cpu_to_node(new_cpu);
if (!static_branch_likely(&sched_numa_balancing))
return;
if (!p->mm || !p->numa_faults || (p->flags & PF_EXITING))
return;
if (src_nid == dst_nid)
return;
/*
* Allow resets if faults have been trapped before one scan
* has completed. This is most likely due to a new task that
* is pulled cross-node due to wakeups or load balancing.
*/
if (p->numa_scan_seq) {
/*
* Avoid scan adjustments if moving to the preferred
* node or if the task was not previously running on
* the preferred node.
*/
if (dst_nid == p->numa_preferred_nid ||
(p->numa_preferred_nid != NUMA_NO_NODE &&
src_nid != p->numa_preferred_nid))
return;
}
p->numa_scan_period = task_scan_start(p);
}
#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)
{
}
static inline void update_scan_period(struct task_struct *p, int new_cpu)
{
}
#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);
#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);
#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--;
}
/*
* 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)
/*
* 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)
/*
* Remove and clamp on negative, from a local variable.
*
* A variant of sub_positive(), which does not use explicit load-store
* and is thus optimized for local variable updates.
*/
#define lsub_positive(_ptr, _val) do { \
typeof(_ptr) ptr = (_ptr); \
*ptr -= min_t(typeof(*ptr), *ptr, _val); \
} while (0)
#ifdef CONFIG_SMP
static inline void
enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
cfs_rq->runnable_weight += se->runnable_weight;
cfs_rq->avg.runnable_load_avg += se->avg.runnable_load_avg;
cfs_rq->avg.runnable_load_sum += se_runnable(se) * se->avg.runnable_load_sum;
}
static inline void
dequeue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
cfs_rq->runnable_weight -= se->runnable_weight;
sub_positive(&cfs_rq->avg.runnable_load_avg, se->avg.runnable_load_avg);
sub_positive(&cfs_rq->avg.runnable_load_sum,
se_runnable(se) * se->avg.runnable_load_sum);
}
static inline void
enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
cfs_rq->avg.load_avg += se->avg.load_avg;
cfs_rq->avg.load_sum += se_weight(se) * se->avg.load_sum;
}
static inline void
dequeue_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_weight(se) * se->avg.load_sum);
}
#else
static inline void
enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
static inline void
dequeue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
static inline void
enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
static inline void
dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
#endif
static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
unsigned long weight, unsigned long runnable)
{
if (se->on_rq) {
/* commit outstanding execution time */
if (cfs_rq->curr == se)
update_curr(cfs_rq);
account_entity_dequeue(cfs_rq, se);
dequeue_runnable_load_avg(cfs_rq, se);
}
dequeue_load_avg(cfs_rq, se);
se->runnable_weight = runnable;
update_load_set(&se->load, weight);
#ifdef CONFIG_SMP
do {
u32 divider = LOAD_AVG_MAX - 1024 + se->avg.period_contrib;
se->avg.load_avg = div_u64(se_weight(se) * se->avg.load_sum, divider);
se->avg.runnable_load_avg =
div_u64(se_runnable(se) * se->avg.runnable_load_sum, divider);
} while (0);
#endif
enqueue_load_avg(cfs_rq, se);
if (se->on_rq) {
account_entity_enqueue(cfs_rq, se);
enqueue_runnable_load_avg(cfs_rq, se);
}
}
void reweight_task(struct task_struct *p, int prio)
{
struct sched_entity *se = &p->se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
struct load_weight *load = &se->load;
unsigned long weight = scale_load(sched_prio_to_weight[prio]);
reweight_entity(cfs_rq, se, weight, weight);
load->inv_weight = sched_prio_to_wmult[prio];
}
#ifdef CONFIG_FAIR_GROUP_SCHED
#ifdef CONFIG_SMP
/*
* All this does is approximate the hierarchical proportion which includes that
* global sum we all love to hate.
*
* That is, the weight of a group entity, is the proportional share of the
* group weight based on the group runqueue weights. That is:
*
* tg->weight * grq->load.weight
* ge->load.weight = ----------------------------- (1)
* \Sum grq->load.weight
*
* Now, because computing that sum is prohibitively expensive to compute (been
* there, done that) we approximate it with this average stuff. The average
* moves slower and therefore the approximation is cheaper and more stable.
*
* So instead of the above, we substitute:
*
* grq->load.weight -> grq->avg.load_avg (2)
*
* which yields the following:
*
* tg->weight * grq->avg.load_avg
* ge->load.weight = ------------------------------ (3)
* tg->load_avg
*
* Where: tg->load_avg ~= \Sum grq->avg.load_avg
*
* That is shares_avg, and it is right (given the approximation (2)).
*
* The problem with it is that because the average is slow -- it was designed
* to be exactly that of course -- this leads to transients in boundary
* conditions. In specific, the case where the group was idle and we start the
* one task. It takes time for our CPU's grq->avg.load_avg to build up,
* yielding bad latency etc..
*
* Now, in that special case (1) reduces to:
*
* tg->weight * grq->load.weight
* ge->load.weight = ----------------------------- = tg->weight (4)
* grp->load.weight
*
* That is, the sum collapses because all other CPUs are idle; the UP scenario.
*
* So what we do is modify our approximation (3) to approach (4) in the (near)
* UP case, like:
*
* ge->load.weight =
*
* tg->weight * grq->load.weight
* --------------------------------------------------- (5)
* tg->load_avg - grq->avg.load_avg + grq->load.weight
*
* But because grq->load.weight can drop to 0, resulting in a divide by zero,
* we need to use grq->avg.load_avg as its lower bound, which then gives:
*
*
* tg->weight * grq->load.weight
* ge->load.weight = ----------------------------- (6)
* tg_load_avg'
*
* Where:
*
* tg_load_avg' = tg->load_avg - grq->avg.load_avg +
* max(grq->load.weight, grq->avg.load_avg)
*
* And that is shares_weight and is icky. In the (near) UP case it approaches
* (4) while in the normal case it approaches (3). It consistently
* overestimates the ge->load.weight and therefore:
*
* \Sum ge->load.weight >= tg->weight
*
* hence icky!
*/
static long calc_group_shares(struct cfs_rq *cfs_rq)
{
long tg_weight, tg_shares, load, shares;
struct task_group *tg = cfs_rq->tg;
tg_shares = READ_ONCE(tg->shares);
load = max(scale_load_down(cfs_rq->load.weight), cfs_rq->avg.load_avg);
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.
*/
return clamp_t(long, shares, MIN_SHARES, tg_shares);
}
/*
* This calculates the effective runnable weight for a group entity based on
* the group entity weight calculated above.
*
* Because of the above approximation (2), our group entity weight is
* an load_avg based ratio (3). This means that it includes blocked load and
* does not represent the runnable weight.
*
* Approximate the group entity's runnable weight per ratio from the group
* runqueue:
*
* grq->avg.runnable_load_avg
* ge->runnable_weight = ge->load.weight * -------------------------- (7)
* grq->avg.load_avg
*
* However, analogous to above, since the avg numbers are slow, this leads to
* transients in the from-idle case. Instead we use:
*
* ge->runnable_weight = ge->load.weight *
*
* max(grq->avg.runnable_load_avg, grq->runnable_weight)
* ----------------------------------------------------- (8)
* max(grq->avg.load_avg, grq->load.weight)
*
* Where these max() serve both to use the 'instant' values to fix the slow
* from-idle and avoid the /0 on to-idle, similar to (6).
*/
static long calc_group_runnable(struct cfs_rq *cfs_rq, long shares)
{
long runnable, load_avg;
load_avg = max(cfs_rq->avg.load_avg,
scale_load_down(cfs_rq->load.weight));
runnable = max(cfs_rq->avg.runnable_load_avg,
scale_load_down(cfs_rq->runnable_weight));
runnable *= shares;
if (load_avg)
runnable /= load_avg;
return clamp_t(long, runnable, MIN_SHARES, shares);
}
#endif /* CONFIG_SMP */
static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
/*
* Recomputes the group entity based on the current state of its group
* runqueue.
*/
static void update_cfs_group(struct sched_entity *se)
{
struct cfs_rq *gcfs_rq = group_cfs_rq(se);
long shares, runnable;
if (!gcfs_rq)
return;
if (throttled_hierarchy(gcfs_rq))
return;
#ifndef CONFIG_SMP
runnable = shares = READ_ONCE(gcfs_rq->tg->shares);
if (likely(se->load.weight == shares))
return;
#else
shares = calc_group_shares(gcfs_rq);
runnable = calc_group_runnable(gcfs_rq, shares);
#endif
reweight_entity(cfs_rq_of(se), se, shares, runnable);
}
#else /* CONFIG_FAIR_GROUP_SCHED */
static inline void update_cfs_group(struct sched_entity *se)
{
}
#endif /* CONFIG_FAIR_GROUP_SCHED */
static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags)
{
struct rq *rq = rq_of(cfs_rq);
if (&rq->cfs == cfs_rq || (flags & SCHED_CPUFREQ_MIGRATION)) {
/*
* 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.
*
* 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, flags);
}
}
#ifdef CONFIG_SMP
#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, se);
se->avg.last_update_time = n_last_update_time;
}
/*
* When on migration a sched_entity joins/leaves the PELT hierarchy, we need to
* propagate its contribution. The key to this propagation is the invariant
* that for each group:
*
* ge->avg == grq->avg (1)
*
* _IFF_ we look at the pure running and runnable sums. Because they
* represent the very same entity, just at different points in the hierarchy.
*
* Per the above update_tg_cfs_util() is trivial and simply copies the running
* sum over (but still wrong, because the group entity and group rq do not have
* their PELT windows aligned).
*
* However, update_tg_cfs_runnable() is more complex. So we have:
*
* ge->avg.load_avg = ge->load.weight * ge->avg.runnable_avg (2)
*
* And since, like util, the runnable part should be directly transferable,
* the following would _appear_ to be the straight forward approach:
*
* grq->avg.load_avg = grq->load.weight * grq->avg.runnable_avg (3)
*
* And per (1) we have:
*
* ge->avg.runnable_avg == grq->avg.runnable_avg
*
* Which gives:
*
* ge->load.weight * grq->avg.load_avg
* ge->avg.load_avg = ----------------------------------- (4)
* grq->load.weight
*
* Except that is wrong!
*
* Because while for entities historical weight is not important and we