linux/kernel/sched/sched.h
Linus Torvalds 3d59eebc5e Automatic NUMA Balancing V11
-----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.18 (GNU/Linux)
 
 iQIcBAABAgAGBQJQx0kQAAoJEHzG/DNEskfi4fQP/R5PRovayroZALBMLnVJDaLD
 Ttr9p40VNXbiJ+MfRgatJjSSJZ4Jl+fC3NEqBhcwVZhckZZb9R2s0WtrSQo5+ZbB
 vdRfiuKoCaKM4cSZ08C12uTvsF6xjhjd27CTUlMkyOcDoKxMEFKelv0hocSxe4Wo
 xqlv3eF+VsY7kE1BNbgBP06SX4tDpIHRxXfqJPMHaSKQmre+cU0xG2GcEu3QGbHT
 DEDTI788YSaWLmBfMC+kWoaQl1+bV/FYvavIAS8/o4K9IKvgR42VzrXmaFaqrbgb
 72ksa6xfAi57yTmZHqyGmts06qYeBbPpKI+yIhCMInxA9CY3lPbvHppRf0RQOyzj
 YOi4hovGEMJKE+BCILukhJcZ9jCTtS3zut6v1rdvR88f4y7uhR9RfmRfsxuW7PNj
 3Rmh191+n0lVWDmhOs2psXuCLJr3LEiA0dFffN1z8REUTtTAZMsj8Rz+SvBNAZDR
 hsJhERVeXB6X5uQ5rkLDzbn1Zic60LjVw7LIp6SF2OYf/YKaF8vhyWOA8dyCEu8W
 CGo7AoG0BO8tIIr8+LvFe8CweypysZImx4AjCfIs4u9pu/v11zmBvO9NO5yfuObF
 BreEERYgTes/UITxn1qdIW4/q+Nr0iKO3CTqsmu6L1GfCz3/XzPGs3U26fUhllqi
 Ka0JKgnWvsa6ez6FSzKI
 =ivQa
 -----END PGP SIGNATURE-----

Merge tag 'balancenuma-v11' of git://git.kernel.org/pub/scm/linux/kernel/git/mel/linux-balancenuma

Pull Automatic NUMA Balancing bare-bones from Mel Gorman:
 "There are three implementations for NUMA balancing, this tree
  (balancenuma), numacore which has been developed in tip/master and
  autonuma which is in aa.git.

  In almost all respects balancenuma is the dumbest of the three because
  its main impact is on the VM side with no attempt to be smart about
  scheduling.  In the interest of getting the ball rolling, it would be
  desirable to see this much merged for 3.8 with the view to building
  scheduler smarts on top and adapting the VM where required for 3.9.

  The most recent set of comparisons available from different people are

    mel:    https://lkml.org/lkml/2012/12/9/108
    mingo:  https://lkml.org/lkml/2012/12/7/331
    tglx:   https://lkml.org/lkml/2012/12/10/437
    srikar: https://lkml.org/lkml/2012/12/10/397

  The results are a mixed bag.  In my own tests, balancenuma does
  reasonably well.  It's dumb as rocks and does not regress against
  mainline.  On the other hand, Ingo's tests shows that balancenuma is
  incapable of converging for this workloads driven by perf which is bad
  but is potentially explained by the lack of scheduler smarts.  Thomas'
  results show balancenuma improves on mainline but falls far short of
  numacore or autonuma.  Srikar's results indicate we all suffer on a
  large machine with imbalanced node sizes.

  My own testing showed that recent numacore results have improved
  dramatically, particularly in the last week but not universally.
  We've butted heads heavily on system CPU usage and high levels of
  migration even when it shows that overall performance is better.
  There are also cases where it regresses.  Of interest is that for
  specjbb in some configurations it will regress for lower numbers of
  warehouses and show gains for higher numbers which is not reported by
  the tool by default and sometimes missed in treports.  Recently I
  reported for numacore that the JVM was crashing with
  NullPointerExceptions but currently it's unclear what the source of
  this problem is.  Initially I thought it was in how numacore batch
  handles PTEs but I'm no longer think this is the case.  It's possible
  numacore is just able to trigger it due to higher rates of migration.

  These reports were quite late in the cycle so I/we would like to start
  with this tree as it contains much of the code we can agree on and has
  not changed significantly over the last 2-3 weeks."

* tag 'balancenuma-v11' of git://git.kernel.org/pub/scm/linux/kernel/git/mel/linux-balancenuma: (50 commits)
  mm/rmap, migration: Make rmap_walk_anon() and try_to_unmap_anon() more scalable
  mm/rmap: Convert the struct anon_vma::mutex to an rwsem
  mm: migrate: Account a transhuge page properly when rate limiting
  mm: numa: Account for failed allocations and isolations as migration failures
  mm: numa: Add THP migration for the NUMA working set scanning fault case build fix
  mm: numa: Add THP migration for the NUMA working set scanning fault case.
  mm: sched: numa: Delay PTE scanning until a task is scheduled on a new node
  mm: sched: numa: Control enabling and disabling of NUMA balancing if !SCHED_DEBUG
  mm: sched: numa: Control enabling and disabling of NUMA balancing
  mm: sched: Adapt the scanning rate if a NUMA hinting fault does not migrate
  mm: numa: Use a two-stage filter to restrict pages being migrated for unlikely task<->node relationships
  mm: numa: migrate: Set last_nid on newly allocated page
  mm: numa: split_huge_page: Transfer last_nid on tail page
  mm: numa: Introduce last_nid to the page frame
  sched: numa: Slowly increase the scanning period as NUMA faults are handled
  mm: numa: Rate limit setting of pte_numa if node is saturated
  mm: numa: Rate limit the amount of memory that is migrated between nodes
  mm: numa: Structures for Migrate On Fault per NUMA migration rate limiting
  mm: numa: Migrate pages handled during a pmd_numa hinting fault
  mm: numa: Migrate on reference policy
  ...
2012-12-16 15:18:08 -08:00

1242 lines
31 KiB
C

#include <linux/sched.h>
#include <linux/mutex.h>
#include <linux/spinlock.h>
#include <linux/stop_machine.h>
#include "cpupri.h"
extern __read_mostly int scheduler_running;
/*
* Convert user-nice values [ -20 ... 0 ... 19 ]
* to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
* and back.
*/
#define NICE_TO_PRIO(nice) (MAX_RT_PRIO + (nice) + 20)
#define PRIO_TO_NICE(prio) ((prio) - MAX_RT_PRIO - 20)
#define TASK_NICE(p) PRIO_TO_NICE((p)->static_prio)
/*
* 'User priority' is the nice value converted to something we
* can work with better when scaling various scheduler parameters,
* it's a [ 0 ... 39 ] range.
*/
#define USER_PRIO(p) ((p)-MAX_RT_PRIO)
#define TASK_USER_PRIO(p) USER_PRIO((p)->static_prio)
#define MAX_USER_PRIO (USER_PRIO(MAX_PRIO))
/*
* Helpers for converting nanosecond timing to jiffy resolution
*/
#define NS_TO_JIFFIES(TIME) ((unsigned long)(TIME) / (NSEC_PER_SEC / HZ))
#define NICE_0_LOAD SCHED_LOAD_SCALE
#define NICE_0_SHIFT SCHED_LOAD_SHIFT
/*
* These are the 'tuning knobs' of the scheduler:
*/
/*
* single value that denotes runtime == period, ie unlimited time.
*/
#define RUNTIME_INF ((u64)~0ULL)
static inline int rt_policy(int policy)
{
if (policy == SCHED_FIFO || policy == SCHED_RR)
return 1;
return 0;
}
static inline int task_has_rt_policy(struct task_struct *p)
{
return rt_policy(p->policy);
}
/*
* This is the priority-queue data structure of the RT scheduling class:
*/
struct rt_prio_array {
DECLARE_BITMAP(bitmap, MAX_RT_PRIO+1); /* include 1 bit for delimiter */
struct list_head queue[MAX_RT_PRIO];
};
struct rt_bandwidth {
/* nests inside the rq lock: */
raw_spinlock_t rt_runtime_lock;
ktime_t rt_period;
u64 rt_runtime;
struct hrtimer rt_period_timer;
};
extern struct mutex sched_domains_mutex;
#ifdef CONFIG_CGROUP_SCHED
#include <linux/cgroup.h>
struct cfs_rq;
struct rt_rq;
extern struct list_head task_groups;
struct cfs_bandwidth {
#ifdef CONFIG_CFS_BANDWIDTH
raw_spinlock_t lock;
ktime_t period;
u64 quota, runtime;
s64 hierarchal_quota;
u64 runtime_expires;
int idle, timer_active;
struct hrtimer period_timer, slack_timer;
struct list_head throttled_cfs_rq;
/* statistics */
int nr_periods, nr_throttled;
u64 throttled_time;
#endif
};
/* task group related information */
struct task_group {
struct cgroup_subsys_state css;
#ifdef CONFIG_FAIR_GROUP_SCHED
/* schedulable entities of this group on each cpu */
struct sched_entity **se;
/* runqueue "owned" by this group on each cpu */
struct cfs_rq **cfs_rq;
unsigned long shares;
atomic_t load_weight;
atomic64_t load_avg;
atomic_t runnable_avg;
#endif
#ifdef CONFIG_RT_GROUP_SCHED
struct sched_rt_entity **rt_se;
struct rt_rq **rt_rq;
struct rt_bandwidth rt_bandwidth;
#endif
struct rcu_head rcu;
struct list_head list;
struct task_group *parent;
struct list_head siblings;
struct list_head children;
#ifdef CONFIG_SCHED_AUTOGROUP
struct autogroup *autogroup;
#endif
struct cfs_bandwidth cfs_bandwidth;
};
#ifdef CONFIG_FAIR_GROUP_SCHED
#define ROOT_TASK_GROUP_LOAD NICE_0_LOAD
/*
* A weight of 0 or 1 can cause arithmetics problems.
* A weight of a cfs_rq is the sum of weights of which entities
* are queued on this cfs_rq, so a weight of a entity should not be
* too large, so as the shares value of a task group.
* (The default weight is 1024 - so there's no practical
* limitation from this.)
*/
#define MIN_SHARES (1UL << 1)
#define MAX_SHARES (1UL << 18)
#endif
/* Default task group.
* Every task in system belong to this group at bootup.
*/
extern struct task_group root_task_group;
typedef int (*tg_visitor)(struct task_group *, void *);
extern int walk_tg_tree_from(struct task_group *from,
tg_visitor down, tg_visitor up, void *data);
/*
* Iterate the full tree, calling @down when first entering a node and @up when
* leaving it for the final time.
*
* Caller must hold rcu_lock or sufficient equivalent.
*/
static inline int walk_tg_tree(tg_visitor down, tg_visitor up, void *data)
{
return walk_tg_tree_from(&root_task_group, down, up, data);
}
extern int tg_nop(struct task_group *tg, void *data);
extern void free_fair_sched_group(struct task_group *tg);
extern int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent);
extern void unregister_fair_sched_group(struct task_group *tg, int cpu);
extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
struct sched_entity *se, int cpu,
struct sched_entity *parent);
extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
extern void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq);
extern void free_rt_sched_group(struct task_group *tg);
extern int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent);
extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
struct sched_rt_entity *rt_se, int cpu,
struct sched_rt_entity *parent);
#else /* CONFIG_CGROUP_SCHED */
struct cfs_bandwidth { };
#endif /* CONFIG_CGROUP_SCHED */
/* CFS-related fields in a runqueue */
struct cfs_rq {
struct load_weight load;
unsigned int nr_running, h_nr_running;
u64 exec_clock;
u64 min_vruntime;
#ifndef CONFIG_64BIT
u64 min_vruntime_copy;
#endif
struct rb_root tasks_timeline;
struct rb_node *rb_leftmost;
/*
* 'curr' points to currently running entity on this cfs_rq.
* It is set to NULL otherwise (i.e when none are currently running).
*/
struct sched_entity *curr, *next, *last, *skip;
#ifdef CONFIG_SCHED_DEBUG
unsigned int nr_spread_over;
#endif
#ifdef CONFIG_SMP
/*
* Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
* removed when useful for applications beyond shares distribution (e.g.
* load-balance).
*/
#ifdef CONFIG_FAIR_GROUP_SCHED
/*
* CFS Load tracking
* Under CFS, load is tracked on a per-entity basis and aggregated up.
* This allows for the description of both thread and group usage (in
* the FAIR_GROUP_SCHED case).
*/
u64 runnable_load_avg, blocked_load_avg;
atomic64_t decay_counter, removed_load;
u64 last_decay;
#endif /* CONFIG_FAIR_GROUP_SCHED */
/* These always depend on CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_FAIR_GROUP_SCHED
u32 tg_runnable_contrib;
u64 tg_load_contrib;
#endif /* CONFIG_FAIR_GROUP_SCHED */
/*
* h_load = weight * f(tg)
*
* Where f(tg) is the recursive weight fraction assigned to
* this group.
*/
unsigned long h_load;
#endif /* CONFIG_SMP */
#ifdef CONFIG_FAIR_GROUP_SCHED
struct rq *rq; /* cpu runqueue to which this cfs_rq is attached */
/*
* leaf cfs_rqs are those that hold tasks (lowest schedulable entity in
* a hierarchy). Non-leaf lrqs hold other higher schedulable entities
* (like users, containers etc.)
*
* leaf_cfs_rq_list ties together list of leaf cfs_rq's in a cpu. This
* list is used during load balance.
*/
int on_list;
struct list_head leaf_cfs_rq_list;
struct task_group *tg; /* group that "owns" this runqueue */
#ifdef CONFIG_CFS_BANDWIDTH
int runtime_enabled;
u64 runtime_expires;
s64 runtime_remaining;
u64 throttled_clock, throttled_clock_task;
u64 throttled_clock_task_time;
int throttled, throttle_count;
struct list_head throttled_list;
#endif /* CONFIG_CFS_BANDWIDTH */
#endif /* CONFIG_FAIR_GROUP_SCHED */
};
static inline int rt_bandwidth_enabled(void)
{
return sysctl_sched_rt_runtime >= 0;
}
/* Real-Time classes' related field in a runqueue: */
struct rt_rq {
struct rt_prio_array active;
unsigned int rt_nr_running;
#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
struct {
int curr; /* highest queued rt task prio */
#ifdef CONFIG_SMP
int next; /* next highest */
#endif
} highest_prio;
#endif
#ifdef CONFIG_SMP
unsigned long rt_nr_migratory;
unsigned long rt_nr_total;
int overloaded;
struct plist_head pushable_tasks;
#endif
int rt_throttled;
u64 rt_time;
u64 rt_runtime;
/* Nests inside the rq lock: */
raw_spinlock_t rt_runtime_lock;
#ifdef CONFIG_RT_GROUP_SCHED
unsigned long rt_nr_boosted;
struct rq *rq;
struct list_head leaf_rt_rq_list;
struct task_group *tg;
#endif
};
#ifdef CONFIG_SMP
/*
* We add the notion of a root-domain which will be used to define per-domain
* variables. Each exclusive cpuset essentially defines an island domain by
* fully partitioning the member cpus from any other cpuset. Whenever a new
* exclusive cpuset is created, we also create and attach a new root-domain
* object.
*
*/
struct root_domain {
atomic_t refcount;
atomic_t rto_count;
struct rcu_head rcu;
cpumask_var_t span;
cpumask_var_t online;
/*
* The "RT overload" flag: it gets set if a CPU has more than
* one runnable RT task.
*/
cpumask_var_t rto_mask;
struct cpupri cpupri;
};
extern struct root_domain def_root_domain;
#endif /* CONFIG_SMP */
/*
* This is the main, per-CPU runqueue data structure.
*
* Locking rule: those places that want to lock multiple runqueues
* (such as the load balancing or the thread migration code), lock
* acquire operations must be ordered by ascending &runqueue.
*/
struct rq {
/* runqueue lock: */
raw_spinlock_t lock;
/*
* nr_running and cpu_load should be in the same cacheline because
* remote CPUs use both these fields when doing load calculation.
*/
unsigned int nr_running;
#define CPU_LOAD_IDX_MAX 5
unsigned long cpu_load[CPU_LOAD_IDX_MAX];
unsigned long last_load_update_tick;
#ifdef CONFIG_NO_HZ
u64 nohz_stamp;
unsigned long nohz_flags;
#endif
int skip_clock_update;
/* capture load from *all* tasks on this cpu: */
struct load_weight load;
unsigned long nr_load_updates;
u64 nr_switches;
struct cfs_rq cfs;
struct rt_rq rt;
#ifdef CONFIG_FAIR_GROUP_SCHED
/* list of leaf cfs_rq on this cpu: */
struct list_head leaf_cfs_rq_list;
#ifdef CONFIG_SMP
unsigned long h_load_throttle;
#endif /* CONFIG_SMP */
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
struct list_head leaf_rt_rq_list;
#endif
/*
* This is part of a global counter where only the total sum
* over all CPUs matters. A task can increase this counter on
* one CPU and if it got migrated afterwards it may decrease
* it on another CPU. Always updated under the runqueue lock:
*/
unsigned long nr_uninterruptible;
struct task_struct *curr, *idle, *stop;
unsigned long next_balance;
struct mm_struct *prev_mm;
u64 clock;
u64 clock_task;
atomic_t nr_iowait;
#ifdef CONFIG_SMP
struct root_domain *rd;
struct sched_domain *sd;
unsigned long cpu_power;
unsigned char idle_balance;
/* For active balancing */
int post_schedule;
int active_balance;
int push_cpu;
struct cpu_stop_work active_balance_work;
/* cpu of this runqueue: */
int cpu;
int online;
struct list_head cfs_tasks;
u64 rt_avg;
u64 age_stamp;
u64 idle_stamp;
u64 avg_idle;
#endif
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
u64 prev_irq_time;
#endif
#ifdef CONFIG_PARAVIRT
u64 prev_steal_time;
#endif
#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
u64 prev_steal_time_rq;
#endif
/* calc_load related fields */
unsigned long calc_load_update;
long calc_load_active;
#ifdef CONFIG_SCHED_HRTICK
#ifdef CONFIG_SMP
int hrtick_csd_pending;
struct call_single_data hrtick_csd;
#endif
struct hrtimer hrtick_timer;
#endif
#ifdef CONFIG_SCHEDSTATS
/* latency stats */
struct sched_info rq_sched_info;
unsigned long long rq_cpu_time;
/* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */
/* sys_sched_yield() stats */
unsigned int yld_count;
/* schedule() stats */
unsigned int sched_count;
unsigned int sched_goidle;
/* try_to_wake_up() stats */
unsigned int ttwu_count;
unsigned int ttwu_local;
#endif
#ifdef CONFIG_SMP
struct llist_head wake_list;
#endif
struct sched_avg avg;
};
static inline int cpu_of(struct rq *rq)
{
#ifdef CONFIG_SMP
return rq->cpu;
#else
return 0;
#endif
}
DECLARE_PER_CPU(struct rq, runqueues);
#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu)))
#define this_rq() (&__get_cpu_var(runqueues))
#define task_rq(p) cpu_rq(task_cpu(p))
#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
#define raw_rq() (&__raw_get_cpu_var(runqueues))
#ifdef CONFIG_SMP
#define rcu_dereference_check_sched_domain(p) \
rcu_dereference_check((p), \
lockdep_is_held(&sched_domains_mutex))
/*
* The domain tree (rq->sd) is protected by RCU's quiescent state transition.
* See detach_destroy_domains: synchronize_sched for details.
*
* The domain tree of any CPU may only be accessed from within
* preempt-disabled sections.
*/
#define for_each_domain(cpu, __sd) \
for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); \
__sd; __sd = __sd->parent)
#define for_each_lower_domain(sd) for (; sd; sd = sd->child)
/**
* highest_flag_domain - Return highest sched_domain containing flag.
* @cpu: The cpu whose highest level of sched domain is to
* be returned.
* @flag: The flag to check for the highest sched_domain
* for the given cpu.
*
* Returns the highest sched_domain of a cpu which contains the given flag.
*/
static inline struct sched_domain *highest_flag_domain(int cpu, int flag)
{
struct sched_domain *sd, *hsd = NULL;
for_each_domain(cpu, sd) {
if (!(sd->flags & flag))
break;
hsd = sd;
}
return hsd;
}
DECLARE_PER_CPU(struct sched_domain *, sd_llc);
DECLARE_PER_CPU(int, sd_llc_id);
extern int group_balance_cpu(struct sched_group *sg);
#endif /* CONFIG_SMP */
#include "stats.h"
#include "auto_group.h"
#ifdef CONFIG_CGROUP_SCHED
/*
* Return the group to which this tasks belongs.
*
* We cannot use task_subsys_state() and friends because the cgroup
* subsystem changes that value before the cgroup_subsys::attach() method
* is called, therefore we cannot pin it and might observe the wrong value.
*
* The same is true for autogroup's p->signal->autogroup->tg, the autogroup
* core changes this before calling sched_move_task().
*
* Instead we use a 'copy' which is updated from sched_move_task() while
* holding both task_struct::pi_lock and rq::lock.
*/
static inline struct task_group *task_group(struct task_struct *p)
{
return p->sched_task_group;
}
/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
{
#if defined(CONFIG_FAIR_GROUP_SCHED) || defined(CONFIG_RT_GROUP_SCHED)
struct task_group *tg = task_group(p);
#endif
#ifdef CONFIG_FAIR_GROUP_SCHED
p->se.cfs_rq = tg->cfs_rq[cpu];
p->se.parent = tg->se[cpu];
#endif
#ifdef CONFIG_RT_GROUP_SCHED
p->rt.rt_rq = tg->rt_rq[cpu];
p->rt.parent = tg->rt_se[cpu];
#endif
}
#else /* CONFIG_CGROUP_SCHED */
static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { }
static inline struct task_group *task_group(struct task_struct *p)
{
return NULL;
}
#endif /* CONFIG_CGROUP_SCHED */
static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
{
set_task_rq(p, cpu);
#ifdef CONFIG_SMP
/*
* After ->cpu is set up to a new value, task_rq_lock(p, ...) can be
* successfuly executed on another CPU. We must ensure that updates of
* per-task data have been completed by this moment.
*/
smp_wmb();
task_thread_info(p)->cpu = cpu;
#endif
}
/*
* Tunables that become constants when CONFIG_SCHED_DEBUG is off:
*/
#ifdef CONFIG_SCHED_DEBUG
# include <linux/static_key.h>
# define const_debug __read_mostly
#else
# define const_debug const
#endif
extern const_debug unsigned int sysctl_sched_features;
#define SCHED_FEAT(name, enabled) \
__SCHED_FEAT_##name ,
enum {
#include "features.h"
__SCHED_FEAT_NR,
};
#undef SCHED_FEAT
#if defined(CONFIG_SCHED_DEBUG) && defined(HAVE_JUMP_LABEL)
static __always_inline bool static_branch__true(struct static_key *key)
{
return static_key_true(key); /* Not out of line branch. */
}
static __always_inline bool static_branch__false(struct static_key *key)
{
return static_key_false(key); /* Out of line branch. */
}
#define SCHED_FEAT(name, enabled) \
static __always_inline bool static_branch_##name(struct static_key *key) \
{ \
return static_branch__##enabled(key); \
}
#include "features.h"
#undef SCHED_FEAT
extern struct static_key sched_feat_keys[__SCHED_FEAT_NR];
#define sched_feat(x) (static_branch_##x(&sched_feat_keys[__SCHED_FEAT_##x]))
#else /* !(SCHED_DEBUG && HAVE_JUMP_LABEL) */
#define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
#endif /* SCHED_DEBUG && HAVE_JUMP_LABEL */
#ifdef CONFIG_NUMA_BALANCING
#define sched_feat_numa(x) sched_feat(x)
#ifdef CONFIG_SCHED_DEBUG
#define numabalancing_enabled sched_feat_numa(NUMA)
#else
extern bool numabalancing_enabled;
#endif /* CONFIG_SCHED_DEBUG */
#else
#define sched_feat_numa(x) (0)
#define numabalancing_enabled (0)
#endif /* CONFIG_NUMA_BALANCING */
static inline u64 global_rt_period(void)
{
return (u64)sysctl_sched_rt_period * NSEC_PER_USEC;
}
static inline u64 global_rt_runtime(void)
{
if (sysctl_sched_rt_runtime < 0)
return RUNTIME_INF;
return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
}
static inline int task_current(struct rq *rq, struct task_struct *p)
{
return rq->curr == p;
}
static inline int task_running(struct rq *rq, struct task_struct *p)
{
#ifdef CONFIG_SMP
return p->on_cpu;
#else
return task_current(rq, p);
#endif
}
#ifndef prepare_arch_switch
# define prepare_arch_switch(next) do { } while (0)
#endif
#ifndef finish_arch_switch
# define finish_arch_switch(prev) do { } while (0)
#endif
#ifndef finish_arch_post_lock_switch
# define finish_arch_post_lock_switch() do { } while (0)
#endif
#ifndef __ARCH_WANT_UNLOCKED_CTXSW
static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
{
#ifdef CONFIG_SMP
/*
* We can optimise this out completely for !SMP, because the
* SMP rebalancing from interrupt is the only thing that cares
* here.
*/
next->on_cpu = 1;
#endif
}
static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
{
#ifdef CONFIG_SMP
/*
* After ->on_cpu is cleared, the task can be moved to a different CPU.
* We must ensure this doesn't happen until the switch is completely
* finished.
*/
smp_wmb();
prev->on_cpu = 0;
#endif
#ifdef CONFIG_DEBUG_SPINLOCK
/* this is a valid case when another task releases the spinlock */
rq->lock.owner = current;
#endif
/*
* If we are tracking spinlock dependencies then we have to
* fix up the runqueue lock - which gets 'carried over' from
* prev into current:
*/
spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
raw_spin_unlock_irq(&rq->lock);
}
#else /* __ARCH_WANT_UNLOCKED_CTXSW */
static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
{
#ifdef CONFIG_SMP
/*
* We can optimise this out completely for !SMP, because the
* SMP rebalancing from interrupt is the only thing that cares
* here.
*/
next->on_cpu = 1;
#endif
raw_spin_unlock(&rq->lock);
}
static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
{
#ifdef CONFIG_SMP
/*
* After ->on_cpu is cleared, the task can be moved to a different CPU.
* We must ensure this doesn't happen until the switch is completely
* finished.
*/
smp_wmb();
prev->on_cpu = 0;
#endif
local_irq_enable();
}
#endif /* __ARCH_WANT_UNLOCKED_CTXSW */
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;
}
/*
* To aid in avoiding the subversion of "niceness" due to uneven distribution
* of tasks with abnormal "nice" values across CPUs the contribution that
* each task makes to its run queue's load is weighted according to its
* scheduling class and "nice" value. For SCHED_NORMAL tasks this is just a
* scaled version of the new time slice allocation that they receive on time
* slice expiry etc.
*/
#define WEIGHT_IDLEPRIO 3
#define WMULT_IDLEPRIO 1431655765
/*
* Nice levels are multiplicative, with a gentle 10% change for every
* nice level changed. I.e. when a CPU-bound task goes from nice 0 to
* nice 1, it will get ~10% less CPU time than another CPU-bound task
* that remained on nice 0.
*
* The "10% effect" is relative and cumulative: from _any_ nice level,
* if you go up 1 level, it's -10% CPU usage, if you go down 1 level
* it's +10% CPU usage. (to achieve that we use a multiplier of 1.25.
* If a task goes up by ~10% and another task goes down by ~10% then
* the relative distance between them is ~25%.)
*/
static const int prio_to_weight[40] = {
/* -20 */ 88761, 71755, 56483, 46273, 36291,
/* -15 */ 29154, 23254, 18705, 14949, 11916,
/* -10 */ 9548, 7620, 6100, 4904, 3906,
/* -5 */ 3121, 2501, 1991, 1586, 1277,
/* 0 */ 1024, 820, 655, 526, 423,
/* 5 */ 335, 272, 215, 172, 137,
/* 10 */ 110, 87, 70, 56, 45,
/* 15 */ 36, 29, 23, 18, 15,
};
/*
* Inverse (2^32/x) values of the prio_to_weight[] array, precalculated.
*
* In cases where the weight does not change often, we can use the
* precalculated inverse to speed up arithmetics by turning divisions
* into multiplications:
*/
static const u32 prio_to_wmult[40] = {
/* -20 */ 48388, 59856, 76040, 92818, 118348,
/* -15 */ 147320, 184698, 229616, 287308, 360437,
/* -10 */ 449829, 563644, 704093, 875809, 1099582,
/* -5 */ 1376151, 1717300, 2157191, 2708050, 3363326,
/* 0 */ 4194304, 5237765, 6557202, 8165337, 10153587,
/* 5 */ 12820798, 15790321, 19976592, 24970740, 31350126,
/* 10 */ 39045157, 49367440, 61356676, 76695844, 95443717,
/* 15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
};
/* Time spent by the tasks of the cpu accounting group executing in ... */
enum cpuacct_stat_index {
CPUACCT_STAT_USER, /* ... user mode */
CPUACCT_STAT_SYSTEM, /* ... kernel mode */
CPUACCT_STAT_NSTATS,
};
#define sched_class_highest (&stop_sched_class)
#define for_each_class(class) \
for (class = sched_class_highest; class; class = class->next)
extern const struct sched_class stop_sched_class;
extern const struct sched_class rt_sched_class;
extern const struct sched_class fair_sched_class;
extern const struct sched_class idle_sched_class;
#ifdef CONFIG_SMP
extern void trigger_load_balance(struct rq *rq, int cpu);
extern void idle_balance(int this_cpu, struct rq *this_rq);
#else /* CONFIG_SMP */
static inline void idle_balance(int cpu, struct rq *rq)
{
}
#endif
extern void sysrq_sched_debug_show(void);
extern void sched_init_granularity(void);
extern void update_max_interval(void);
extern void update_group_power(struct sched_domain *sd, int cpu);
extern int update_runtime(struct notifier_block *nfb, unsigned long action, void *hcpu);
extern void init_sched_rt_class(void);
extern void init_sched_fair_class(void);
extern void resched_task(struct task_struct *p);
extern void resched_cpu(int cpu);
extern struct rt_bandwidth def_rt_bandwidth;
extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
extern void update_idle_cpu_load(struct rq *this_rq);
#ifdef CONFIG_CGROUP_CPUACCT
#include <linux/cgroup.h>
/* track cpu usage of a group of tasks and its child groups */
struct cpuacct {
struct cgroup_subsys_state css;
/* cpuusage holds pointer to a u64-type object on every cpu */
u64 __percpu *cpuusage;
struct kernel_cpustat __percpu *cpustat;
};
extern struct cgroup_subsys cpuacct_subsys;
extern struct cpuacct root_cpuacct;
/* return cpu accounting group corresponding to this container */
static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp)
{
return container_of(cgroup_subsys_state(cgrp, cpuacct_subsys_id),
struct cpuacct, css);
}
/* return cpu accounting group to which this task belongs */
static inline struct cpuacct *task_ca(struct task_struct *tsk)
{
return container_of(task_subsys_state(tsk, cpuacct_subsys_id),
struct cpuacct, css);
}
static inline struct cpuacct *parent_ca(struct cpuacct *ca)
{
if (!ca || !ca->css.cgroup->parent)
return NULL;
return cgroup_ca(ca->css.cgroup->parent);
}
extern void cpuacct_charge(struct task_struct *tsk, u64 cputime);
#else
static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
#endif
#ifdef CONFIG_PARAVIRT
static inline u64 steal_ticks(u64 steal)
{
if (unlikely(steal > NSEC_PER_SEC))
return div_u64(steal, TICK_NSEC);
return __iter_div_u64_rem(steal, TICK_NSEC, &steal);
}
#endif
static inline void inc_nr_running(struct rq *rq)
{
rq->nr_running++;
}
static inline void dec_nr_running(struct rq *rq)
{
rq->nr_running--;
}
extern void update_rq_clock(struct rq *rq);
extern void activate_task(struct rq *rq, struct task_struct *p, int flags);
extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);
extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
extern const_debug unsigned int sysctl_sched_time_avg;
extern const_debug unsigned int sysctl_sched_nr_migrate;
extern const_debug unsigned int sysctl_sched_migration_cost;
static inline u64 sched_avg_period(void)
{
return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2;
}
#ifdef CONFIG_SCHED_HRTICK
/*
* Use hrtick when:
* - enabled by features
* - hrtimer is actually high res
*/
static inline int hrtick_enabled(struct rq *rq)
{
if (!sched_feat(HRTICK))
return 0;
if (!cpu_active(cpu_of(rq)))
return 0;
return hrtimer_is_hres_active(&rq->hrtick_timer);
}
void hrtick_start(struct rq *rq, u64 delay);
#else
static inline int hrtick_enabled(struct rq *rq)
{
return 0;
}
#endif /* CONFIG_SCHED_HRTICK */
#ifdef CONFIG_SMP
extern void sched_avg_update(struct rq *rq);
static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
{
rq->rt_avg += rt_delta;
sched_avg_update(rq);
}
#else
static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { }
static inline void sched_avg_update(struct rq *rq) { }
#endif
extern void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period);
#ifdef CONFIG_SMP
#ifdef CONFIG_PREEMPT
static inline void double_rq_lock(struct rq *rq1, struct rq *rq2);
/*
* fair double_lock_balance: Safely acquires both rq->locks in a fair
* way at the expense of forcing extra atomic operations in all
* invocations. This assures that the double_lock is acquired using the
* same underlying policy as the spinlock_t on this architecture, which
* reduces latency compared to the unfair variant below. However, it
* also adds more overhead and therefore may reduce throughput.
*/
static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
__releases(this_rq->lock)
__acquires(busiest->lock)
__acquires(this_rq->lock)
{
raw_spin_unlock(&this_rq->lock);
double_rq_lock(this_rq, busiest);
return 1;
}
#else
/*
* Unfair double_lock_balance: Optimizes throughput at the expense of
* latency by eliminating extra atomic operations when the locks are
* already in proper order on entry. This favors lower cpu-ids and will
* grant the double lock to lower cpus over higher ids under contention,
* regardless of entry order into the function.
*/
static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
__releases(this_rq->lock)
__acquires(busiest->lock)
__acquires(this_rq->lock)
{
int ret = 0;
if (unlikely(!raw_spin_trylock(&busiest->lock))) {
if (busiest < this_rq) {
raw_spin_unlock(&this_rq->lock);
raw_spin_lock(&busiest->lock);
raw_spin_lock_nested(&this_rq->lock,
SINGLE_DEPTH_NESTING);
ret = 1;
} else
raw_spin_lock_nested(&busiest->lock,
SINGLE_DEPTH_NESTING);
}
return ret;
}
#endif /* CONFIG_PREEMPT */
/*
* double_lock_balance - lock the busiest runqueue, this_rq is locked already.
*/
static inline int double_lock_balance(struct rq *this_rq, struct rq *busiest)
{
if (unlikely(!irqs_disabled())) {
/* printk() doesn't work good under rq->lock */
raw_spin_unlock(&this_rq->lock);
BUG_ON(1);
}
return _double_lock_balance(this_rq, busiest);
}
static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
__releases(busiest->lock)
{
raw_spin_unlock(&busiest->lock);
lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
}
/*
* double_rq_lock - safely lock two runqueues
*
* Note this does not disable interrupts like task_rq_lock,
* you need to do so manually before calling.
*/
static inline void double_rq_lock(struct rq *rq1, struct rq *rq2)
__acquires(rq1->lock)
__acquires(rq2->lock)
{
BUG_ON(!irqs_disabled());
if (rq1 == rq2) {
raw_spin_lock(&rq1->lock);
__acquire(rq2->lock); /* Fake it out ;) */
} else {
if (rq1 < rq2) {
raw_spin_lock(&rq1->lock);
raw_spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING);
} else {
raw_spin_lock(&rq2->lock);
raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
}
}
}
/*
* double_rq_unlock - safely unlock two runqueues
*
* Note this does not restore interrupts like task_rq_unlock,
* you need to do so manually after calling.
*/
static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2)
__releases(rq1->lock)
__releases(rq2->lock)
{
raw_spin_unlock(&rq1->lock);
if (rq1 != rq2)
raw_spin_unlock(&rq2->lock);
else
__release(rq2->lock);
}
#else /* CONFIG_SMP */
/*
* double_rq_lock - safely lock two runqueues
*
* Note this does not disable interrupts like task_rq_lock,
* you need to do so manually before calling.
*/
static inline void double_rq_lock(struct rq *rq1, struct rq *rq2)
__acquires(rq1->lock)
__acquires(rq2->lock)
{
BUG_ON(!irqs_disabled());
BUG_ON(rq1 != rq2);
raw_spin_lock(&rq1->lock);
__acquire(rq2->lock); /* Fake it out ;) */
}
/*
* double_rq_unlock - safely unlock two runqueues
*
* Note this does not restore interrupts like task_rq_unlock,
* you need to do so manually after calling.
*/
static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2)
__releases(rq1->lock)
__releases(rq2->lock)
{
BUG_ON(rq1 != rq2);
raw_spin_unlock(&rq1->lock);
__release(rq2->lock);
}
#endif
extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq);
extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq);
extern void print_cfs_stats(struct seq_file *m, int cpu);
extern void print_rt_stats(struct seq_file *m, int cpu);
extern void init_cfs_rq(struct cfs_rq *cfs_rq);
extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq);
extern void account_cfs_bandwidth_used(int enabled, int was_enabled);
#ifdef CONFIG_NO_HZ
enum rq_nohz_flag_bits {
NOHZ_TICK_STOPPED,
NOHZ_BALANCE_KICK,
NOHZ_IDLE,
};
#define nohz_flags(cpu) (&cpu_rq(cpu)->nohz_flags)
#endif
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
DECLARE_PER_CPU(u64, cpu_hardirq_time);
DECLARE_PER_CPU(u64, cpu_softirq_time);
#ifndef CONFIG_64BIT
DECLARE_PER_CPU(seqcount_t, irq_time_seq);
static inline void irq_time_write_begin(void)
{
__this_cpu_inc(irq_time_seq.sequence);
smp_wmb();
}
static inline void irq_time_write_end(void)
{
smp_wmb();
__this_cpu_inc(irq_time_seq.sequence);
}
static inline u64 irq_time_read(int cpu)
{
u64 irq_time;
unsigned seq;
do {
seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu));
irq_time = per_cpu(cpu_softirq_time, cpu) +
per_cpu(cpu_hardirq_time, cpu);
} while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq));
return irq_time;
}
#else /* CONFIG_64BIT */
static inline void irq_time_write_begin(void)
{
}
static inline void irq_time_write_end(void)
{
}
static inline u64 irq_time_read(int cpu)
{
return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
}
#endif /* CONFIG_64BIT */
#endif /* CONFIG_IRQ_TIME_ACCOUNTING */