kernel-ark/kernel/sched/sched.h
Linus Torvalds d57d394319 Power management material for v4.7-rc1
- New cpufreq "schedutil" governor (making decisions based on CPU
    utilization information provided by the scheduler and capable of
    switching CPU frequencies right away if the underlying driver
    supports that) and support for fast frequency switching in the
    acpi-cpufreq driver (Rafael Wysocki).
 
  - Consolidation of CPU frequency management on ARM platforms allowing
    them to get rid of some platform-specific boilerplate code if they
    are going to use the cpufreq-dt driver (Viresh Kumar, Finley Xiao,
    Marc Gonzalez).
 
  - Support for ACPI _PPC and CPU frequency limits in the intel_pstate
    driver (Srinivas Pandruvada).
 
  - Fixes and cleanups in the cpufreq core and generic governor code
    (Rafael Wysocki, Sai Gurrappadi).
 
  - intel_pstate driver optimizations and cleanups (Rafael Wysocki,
    Philippe Longepe, Chen Yu, Joe Perches).
 
  - cpufreq powernv driver fixes and cleanups (Akshay Adiga, Shilpasri
    Bhat).
 
  - cpufreq qoriq driver fixes and cleanups (Jia Hongtao).
 
  - ACPI cpufreq driver cleanups (Viresh Kumar).
 
  - Assorted cpufreq driver updates (Ashwin Chaugule, Geliang Tang,
    Javier Martinez Canillas, Paul Gortmaker, Sudeep Holla).
 
  - Assorted cpufreq fixes and cleanups (Joe Perches, Arnd Bergmann).
 
  - Fixes and cleanups in the OPP (Operating Performance Points)
    framework, mostly related to OPP sharing, and reorganization of
    OF-dependent code in it (Viresh Kumar, Arnd Bergmann, Sudeep Holla).
 
  - New "passive" governor for devfreq (for SoC subsystems that will
    rely on someone else for the management of their power resources)
    and consolidation of devfreq support for Exynos platforms, coding
    style and typo fixes for devfreq (Chanwoo Choi, MyungJoo Ham).
 
  - PM core fixes and cleanups, mostly to make it work better with the
    generic power domains (genpd) framework, and updates for that
    framework (Ulf Hansson, Thierry Reding, Colin Ian King).
 
  - Intel Broxton support for the intel_idle driver (Len Brown).
 
  - cpuidle core optimization and fix (Daniel Lezcano, Dave Gerlach).
 
  - ARM cpuidle cleanups (Jisheng Zhang).
 
  - Intel Kabylake support for the RAPL power capping driver (Jacob Pan).
 
  - AVS (Adaptive Voltage Switching) rockchip-io driver update (Heiko
    Stuebner).
 
  - Updates for the cpupower tool (Arjun Sreedharan, Colin Ian King,
    Mattia Dongili, Thomas Renninger).
 
 /
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.22 (GNU/Linux)
 
 iQIcBAABCAAGBQJXOjLgAAoJEILEb/54YlRxfn0P/RbSPpNlUNBIE8DFrdD9jRdJ
 TIpZ7uiHi9tU1ZF17UBbb/SwuWfYVnVmiorZGRfFOtGaoqh0HFZ/nplDz99rK0ku
 vW2OnbojMQEUMU3IcUT1y4BsSl0H23f7ZOKrdprALeWxDQmbgnYjrE6vkX6hRtld
 A8eeZvIEJ5CzV8S+9aOOOpojW2yXk5dYGdZ7gpQdoM0n7zVLyPnNucJoha3BYmOG
 FwKEIe05RpIhfLfGT0CXIRcOzwAZ6ZWKgOrXUrx/AadPbvu/TP9zkI0djYI8ukyv
 z2oiO/GExoeGVuUzvy8vY5SiH4NQvViftFzMZepcsmjxmVglohMPRL8VLjZIBckk
 DDcqH9e0OQI20jjYT1vIf5+JWBvLxuQfGtyzI0S+sE/elB1zI/3O8p+8N2CuF5n+
 my2dawIewnHI/0AdSpJ+K7DVrfwPHAX19axtPX3dJSLh2OuHCPNlAtbxRGAriBfH
 Zv9NETxlrch69o2AD4K54DErWV1FsYLznzK5Zms6MC2Ispbb+oiYpacTlZblznvb
 H5U2SSNlA5Niir3vVJ01nKRtzxlWoi67CQxbYrGhlaR0nTTxf9HqWgcSiTZrn7Pv
 hs+LA2aUfMf3JGjStdORS7S8biQSid5vypfkglpWLZBKHNC9BqqZd9gSM+jF3FVh
 ps4mMM4UXY4hnoFDkMBI
 =WM89
 -----END PGP SIGNATURE-----

Merge tag 'pm-4.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "The majority of changes go into the cpufreq subsystem this time.

  To me, quite obviously, the biggest ticket item is the new "schedutil"
  governor.  Interestingly enough, it's the first new cpufreq governor
  since the beginning of the git era (except for some out-of-the-tree
  ones).

  There are two main differences between it and the existing governors.
  First, it uses the information provided by the scheduler directly for
  making its decisions, so it doesn't have to track anything by itself.
  Second, it can invoke drivers (supporting that feature) to adjust CPU
  performance right away without having to spawn work items to be
  executed in process context or similar.  Currently, the acpi-cpufreq
  driver is the only one supporting that mode of operation, but then it
  is used on a large number of systems.

  The "schedutil" governor as included here is very simple and mostly
  regarded as a foundation for future work on the integration of the
  scheduler with CPU power management (in fact, there is work in
  progress on top of it already).  Nevertheless it works and the
  preliminary results obtained with it are encouraging.

  There also is some consolidation of CPU frequency management for ARM
  platforms that can add their machine IDs the the new stub dt-platdev
  driver now and that will take care of creating the requisite platform
  device for cpufreq-dt, so it is not necessary to do that in platform
  code any more.  Several ARM platforms are switched over to using this
  generic mechanism.

  In addition to that, the intel_pstate driver is now going to respect
  CPU frequency limits set by the platform firmware (or a BMC) and
  provided via the ACPI _PPC object.

  The devfreq subsystem is getting a new "passive" governor for SoCs
  subsystems that will depend on somebody else to manage their voltage
  rails and its support for Samsung Exynos SoCs is consolidated.

  The rest is support for new hardware (Intel Broxton support in
  intel_idle for one example), bug fixes, optimizations and cleanups in
  a number of places.

  Specifics:

   - New cpufreq "schedutil" governor (making decisions based on CPU
     utilization information provided by the scheduler and capable of
     switching CPU frequencies right away if the underlying driver
     supports that) and support for fast frequency switching in the
     acpi-cpufreq driver (Rafael Wysocki)

   - Consolidation of CPU frequency management on ARM platforms allowing
     them to get rid of some platform-specific boilerplate code if they
     are going to use the cpufreq-dt driver (Viresh Kumar, Finley Xiao,
     Marc Gonzalez)

   - Support for ACPI _PPC and CPU frequency limits in the intel_pstate
     driver (Srinivas Pandruvada)

   - Fixes and cleanups in the cpufreq core and generic governor code
     (Rafael Wysocki, Sai Gurrappadi)

   - intel_pstate driver optimizations and cleanups (Rafael Wysocki,
     Philippe Longepe, Chen Yu, Joe Perches)

   - cpufreq powernv driver fixes and cleanups (Akshay Adiga, Shilpasri
     Bhat)

   - cpufreq qoriq driver fixes and cleanups (Jia Hongtao)

   - ACPI cpufreq driver cleanups (Viresh Kumar)

   - Assorted cpufreq driver updates (Ashwin Chaugule, Geliang Tang,
     Javier Martinez Canillas, Paul Gortmaker, Sudeep Holla)

   - Assorted cpufreq fixes and cleanups (Joe Perches, Arnd Bergmann)

   - Fixes and cleanups in the OPP (Operating Performance Points)
     framework, mostly related to OPP sharing, and reorganization of
     OF-dependent code in it (Viresh Kumar, Arnd Bergmann, Sudeep Holla)

   - New "passive" governor for devfreq (for SoC subsystems that will
     rely on someone else for the management of their power resources)
     and consolidation of devfreq support for Exynos platforms, coding
     style and typo fixes for devfreq (Chanwoo Choi, MyungJoo Ham)

   - PM core fixes and cleanups, mostly to make it work better with the
     generic power domains (genpd) framework, and updates for that
     framework (Ulf Hansson, Thierry Reding, Colin Ian King)

   - Intel Broxton support for the intel_idle driver (Len Brown)

   - cpuidle core optimization and fix (Daniel Lezcano, Dave Gerlach)

   - ARM cpuidle cleanups (Jisheng Zhang)

   - Intel Kabylake support for the RAPL power capping driver (Jacob
     Pan)

   - AVS (Adaptive Voltage Switching) rockchip-io driver update (Heiko
     Stuebner)

   - Updates for the cpupower tool (Arjun Sreedharan, Colin Ian King,
     Mattia Dongili, Thomas Renninger)"

* tag 'pm-4.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (112 commits)
  intel_pstate: Clean up get_target_pstate_use_performance()
  intel_pstate: Use sample.core_avg_perf in get_avg_pstate()
  intel_pstate: Clarify average performance computation
  intel_pstate: Avoid unnecessary synchronize_sched() during initialization
  cpufreq: schedutil: Make default depend on CONFIG_SMP
  cpufreq: powernv: del_timer_sync when global and local pstate are equal
  cpufreq: powernv: Move smp_call_function_any() out of irq safe block
  intel_pstate: Clean up intel_pstate_get()
  cpufreq: schedutil: Make it depend on CONFIG_SMP
  cpufreq: governor: Fix handling of special cases in dbs_update()
  PM / OPP: Move CONFIG_OF dependent code in a separate file
  cpufreq: intel_pstate: Ignore _PPC processing under HWP
  cpufreq: arm_big_little: use generic OPP functions for {init, free}_opp_table
  PM / OPP: add non-OF versions of dev_pm_opp_{cpumask_, }remove_table
  cpufreq: tango: Use generic platdev driver
  PM / OPP: pass cpumask by reference
  cpufreq: Fix GOV_LIMITS handling for the userspace governor
  cpupower: fix potential memory leak
  PM / devfreq: style/typo fixes
  PM / devfreq: exynos: Add the detailed correlation for Exynos5422 bus
  ..
2016-05-16 19:17:22 -07:00

1825 lines
46 KiB
C

#include <linux/sched.h>
#include <linux/sched/sysctl.h>
#include <linux/sched/rt.h>
#include <linux/sched/deadline.h>
#include <linux/binfmts.h>
#include <linux/mutex.h>
#include <linux/spinlock.h>
#include <linux/stop_machine.h>
#include <linux/irq_work.h>
#include <linux/tick.h>
#include <linux/slab.h>
#include "cpupri.h"
#include "cpudeadline.h"
#include "cpuacct.h"
struct rq;
struct cpuidle_state;
/* task_struct::on_rq states: */
#define TASK_ON_RQ_QUEUED 1
#define TASK_ON_RQ_MIGRATING 2
extern __read_mostly int scheduler_running;
extern unsigned long calc_load_update;
extern atomic_long_t calc_load_tasks;
extern void calc_global_load_tick(struct rq *this_rq);
extern long calc_load_fold_active(struct rq *this_rq);
#ifdef CONFIG_SMP
extern void cpu_load_update_active(struct rq *this_rq);
#else
static inline void cpu_load_update_active(struct rq *this_rq) { }
#endif
/*
* Helpers for converting nanosecond timing to jiffy resolution
*/
#define NS_TO_JIFFIES(TIME) ((unsigned long)(TIME) / (NSEC_PER_SEC / HZ))
/*
* Increase resolution of nice-level calculations for 64-bit architectures.
* The extra resolution improves shares distribution and load balancing of
* low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup
* hierarchies, especially on larger systems. This is not a user-visible change
* and does not change the user-interface for setting shares/weights.
*
* We increase resolution only if we have enough bits to allow this increased
* resolution (i.e. 64bit). The costs for increasing resolution when 32bit are
* pretty high and the returns do not justify the increased costs.
*
* Really only required when CONFIG_FAIR_GROUP_SCHED is also set, but to
* increase coverage and consistency always enable it on 64bit platforms.
*/
#ifdef CONFIG_64BIT
# define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT + SCHED_FIXEDPOINT_SHIFT)
# define scale_load(w) ((w) << SCHED_FIXEDPOINT_SHIFT)
# define scale_load_down(w) ((w) >> SCHED_FIXEDPOINT_SHIFT)
#else
# define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT)
# define scale_load(w) (w)
# define scale_load_down(w) (w)
#endif
/*
* Task weight (visible to users) and its load (invisible to users) have
* independent resolution, but they should be well calibrated. We use
* scale_load() and scale_load_down(w) to convert between them. The
* following must be true:
*
* scale_load(sched_prio_to_weight[USER_PRIO(NICE_TO_PRIO(0))]) == NICE_0_LOAD
*
*/
#define NICE_0_LOAD (1L << NICE_0_LOAD_SHIFT)
/*
* Single value that decides SCHED_DEADLINE internal math precision.
* 10 -> just above 1us
* 9 -> just above 0.5us
*/
#define DL_SCALE (10)
/*
* 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 idle_policy(int policy)
{
return policy == SCHED_IDLE;
}
static inline int fair_policy(int policy)
{
return policy == SCHED_NORMAL || policy == SCHED_BATCH;
}
static inline int rt_policy(int policy)
{
return policy == SCHED_FIFO || policy == SCHED_RR;
}
static inline int dl_policy(int policy)
{
return policy == SCHED_DEADLINE;
}
static inline bool valid_policy(int policy)
{
return idle_policy(policy) || fair_policy(policy) ||
rt_policy(policy) || dl_policy(policy);
}
static inline int task_has_rt_policy(struct task_struct *p)
{
return rt_policy(p->policy);
}
static inline int task_has_dl_policy(struct task_struct *p)
{
return dl_policy(p->policy);
}
/*
* Tells if entity @a should preempt entity @b.
*/
static inline bool
dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b)
{
return dl_time_before(a->deadline, b->deadline);
}
/*
* 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;
unsigned int rt_period_active;
};
void __dl_clear_params(struct task_struct *p);
/*
* To keep the bandwidth of -deadline tasks and groups under control
* we need some place where:
* - store the maximum -deadline bandwidth of the system (the group);
* - cache the fraction of that bandwidth that is currently allocated.
*
* This is all done in the data structure below. It is similar to the
* one used for RT-throttling (rt_bandwidth), with the main difference
* that, since here we are only interested in admission control, we
* do not decrease any runtime while the group "executes", neither we
* need a timer to replenish it.
*
* With respect to SMP, the bandwidth is given on a per-CPU basis,
* meaning that:
* - dl_bw (< 100%) is the bandwidth of the system (group) on each CPU;
* - dl_total_bw array contains, in the i-eth element, the currently
* allocated bandwidth on the i-eth CPU.
* Moreover, groups consume bandwidth on each CPU, while tasks only
* consume bandwidth on the CPU they're running on.
* Finally, dl_total_bw_cpu is used to cache the index of dl_total_bw
* that will be shown the next time the proc or cgroup controls will
* be red. It on its turn can be changed by writing on its own
* control.
*/
struct dl_bandwidth {
raw_spinlock_t dl_runtime_lock;
u64 dl_runtime;
u64 dl_period;
};
static inline int dl_bandwidth_enabled(void)
{
return sysctl_sched_rt_runtime >= 0;
}
extern struct dl_bw *dl_bw_of(int i);
struct dl_bw {
raw_spinlock_t lock;
u64 bw, total_bw;
};
static inline
void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw)
{
dl_b->total_bw -= tsk_bw;
}
static inline
void __dl_add(struct dl_bw *dl_b, u64 tsk_bw)
{
dl_b->total_bw += tsk_bw;
}
static inline
bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw)
{
return dl_b->bw != -1 &&
dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
}
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 hierarchical_quota;
u64 runtime_expires;
int idle, period_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;
#ifdef CONFIG_SMP
/*
* load_avg can be heavily contended at clock tick time, so put
* it in its own cacheline separated from the fields above which
* will also be accessed at each tick.
*/
atomic_long_t load_avg ____cacheline_aligned;
#endif
#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
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);
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 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);
extern struct task_group *sched_create_group(struct task_group *parent);
extern void sched_online_group(struct task_group *tg,
struct task_group *parent);
extern void sched_destroy_group(struct task_group *tg);
extern void sched_offline_group(struct task_group *tg);
extern void sched_move_task(struct task_struct *tsk);
#ifdef CONFIG_FAIR_GROUP_SCHED
extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
#ifdef CONFIG_SMP
extern void set_task_rq_fair(struct sched_entity *se,
struct cfs_rq *prev, struct cfs_rq *next);
#else /* !CONFIG_SMP */
static inline void set_task_rq_fair(struct sched_entity *se,
struct cfs_rq *prev, struct cfs_rq *next) { }
#endif /* CONFIG_SMP */
#endif /* CONFIG_FAIR_GROUP_SCHED */
#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
/*
* CFS load tracking
*/
struct sched_avg avg;
u64 runnable_load_sum;
unsigned long runnable_load_avg;
#ifdef CONFIG_FAIR_GROUP_SCHED
unsigned long tg_load_avg_contrib;
#endif
atomic_long_t removed_load_avg, removed_util_avg;
#ifndef CONFIG_64BIT
u64 load_last_update_time_copy;
#endif
#ifdef 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;
u64 last_h_load_update;
struct sched_entity *h_load_next;
#endif /* CONFIG_FAIR_GROUP_SCHED */
#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;
}
/* RT IPI pull logic requires IRQ_WORK */
#ifdef CONFIG_IRQ_WORK
# define HAVE_RT_PUSH_IPI
#endif
/* Real-Time classes' related field in a runqueue: */
struct rt_rq {
struct rt_prio_array active;
unsigned int rt_nr_running;
unsigned int rr_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;
#ifdef HAVE_RT_PUSH_IPI
int push_flags;
int push_cpu;
struct irq_work push_work;
raw_spinlock_t push_lock;
#endif
#endif /* CONFIG_SMP */
int rt_queued;
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 task_group *tg;
#endif
};
/* Deadline class' related fields in a runqueue */
struct dl_rq {
/* runqueue is an rbtree, ordered by deadline */
struct rb_root rb_root;
struct rb_node *rb_leftmost;
unsigned long dl_nr_running;
#ifdef CONFIG_SMP
/*
* Deadline values of the currently executing and the
* earliest ready task on this rq. Caching these facilitates
* the decision wether or not a ready but not running task
* should migrate somewhere else.
*/
struct {
u64 curr;
u64 next;
} earliest_dl;
unsigned long dl_nr_migratory;
int overloaded;
/*
* Tasks on this rq that can be pushed away. They are kept in
* an rb-tree, ordered by tasks' deadlines, with caching
* of the leftmost (earliest deadline) element.
*/
struct rb_root pushable_dl_tasks_root;
struct rb_node *pushable_dl_tasks_leftmost;
#else
struct dl_bw dl_bw;
#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;
/* Indicate more than one runnable task for any CPU */
bool overload;
/*
* The bit corresponding to a CPU gets set here if such CPU has more
* than one runnable -deadline task (as it is below for RT tasks).
*/
cpumask_var_t dlo_mask;
atomic_t dlo_count;
struct dl_bw dl_bw;
struct cpudl cpudl;
/*
* 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;
#ifdef CONFIG_NUMA_BALANCING
unsigned int nr_numa_running;
unsigned int nr_preferred_running;
#endif
#define CPU_LOAD_IDX_MAX 5
unsigned long cpu_load[CPU_LOAD_IDX_MAX];
#ifdef CONFIG_NO_HZ_COMMON
#ifdef CONFIG_SMP
unsigned long last_load_update_tick;
#endif /* CONFIG_SMP */
u64 nohz_stamp;
unsigned long nohz_flags;
#endif /* CONFIG_NO_HZ_COMMON */
#ifdef CONFIG_NO_HZ_FULL
unsigned long last_sched_tick;
#endif
/* 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;
struct dl_rq dl;
#ifdef CONFIG_FAIR_GROUP_SCHED
/* list of leaf cfs_rq on this cpu: */
struct list_head leaf_cfs_rq_list;
#endif /* CONFIG_FAIR_GROUP_SCHED */
/*
* 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;
unsigned int clock_skip_update;
u64 clock;
u64 clock_task;
atomic_t nr_iowait;
#ifdef CONFIG_SMP
struct root_domain *rd;
struct sched_domain *sd;
unsigned long cpu_capacity;
unsigned long cpu_capacity_orig;
struct callback_head *balance_callback;
unsigned char idle_balance;
/* For active balancing */
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;
/* This is used to determine avg_idle's max value */
u64 max_idle_balance_cost;
#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
#ifdef CONFIG_CPU_IDLE
/* Must be inspected within a rcu lock section */
struct cpuidle_state *idle_state;
#endif
};
static inline int cpu_of(struct rq *rq)
{
#ifdef CONFIG_SMP
return rq->cpu;
#else
return 0;
#endif
}
DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu)))
#define this_rq() this_cpu_ptr(&runqueues)
#define task_rq(p) cpu_rq(task_cpu(p))
#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
#define raw_rq() raw_cpu_ptr(&runqueues)
static inline u64 __rq_clock_broken(struct rq *rq)
{
return READ_ONCE(rq->clock);
}
static inline u64 rq_clock(struct rq *rq)
{
lockdep_assert_held(&rq->lock);
return rq->clock;
}
static inline u64 rq_clock_task(struct rq *rq)
{
lockdep_assert_held(&rq->lock);
return rq->clock_task;
}
#define RQCF_REQ_SKIP 0x01
#define RQCF_ACT_SKIP 0x02
static inline void rq_clock_skip_update(struct rq *rq, bool skip)
{
lockdep_assert_held(&rq->lock);
if (skip)
rq->clock_skip_update |= RQCF_REQ_SKIP;
else
rq->clock_skip_update &= ~RQCF_REQ_SKIP;
}
#ifdef CONFIG_NUMA
enum numa_topology_type {
NUMA_DIRECT,
NUMA_GLUELESS_MESH,
NUMA_BACKPLANE,
};
extern enum numa_topology_type sched_numa_topology_type;
extern int sched_max_numa_distance;
extern bool find_numa_distance(int distance);
#endif
#ifdef CONFIG_NUMA_BALANCING
/* The regions in numa_faults array from task_struct */
enum numa_faults_stats {
NUMA_MEM = 0,
NUMA_CPU,
NUMA_MEMBUF,
NUMA_CPUBUF
};
extern void sched_setnuma(struct task_struct *p, int node);
extern int migrate_task_to(struct task_struct *p, int cpu);
extern int migrate_swap(struct task_struct *, struct task_struct *);
#endif /* CONFIG_NUMA_BALANCING */
#ifdef CONFIG_SMP
static inline void
queue_balance_callback(struct rq *rq,
struct callback_head *head,
void (*func)(struct rq *rq))
{
lockdep_assert_held(&rq->lock);
if (unlikely(head->next))
return;
head->func = (void (*)(struct callback_head *))func;
head->next = rq->balance_callback;
rq->balance_callback = head;
}
extern void sched_ttwu_pending(void);
#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;
}
static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
{
struct sched_domain *sd;
for_each_domain(cpu, sd) {
if (sd->flags & flag)
break;
}
return sd;
}
DECLARE_PER_CPU(struct sched_domain *, sd_llc);
DECLARE_PER_CPU(int, sd_llc_size);
DECLARE_PER_CPU(int, sd_llc_id);
DECLARE_PER_CPU(struct sched_domain *, sd_numa);
DECLARE_PER_CPU(struct sched_domain *, sd_busy);
DECLARE_PER_CPU(struct sched_domain *, sd_asym);
struct sched_group_capacity {
atomic_t ref;
/*
* CPU capacity of this group, SCHED_CAPACITY_SCALE being max capacity
* for a single CPU.
*/
unsigned int capacity;
unsigned long next_update;
int imbalance; /* XXX unrelated to capacity but shared group state */
/*
* Number of busy cpus in this group.
*/
atomic_t nr_busy_cpus;
unsigned long cpumask[0]; /* iteration mask */
};
struct sched_group {
struct sched_group *next; /* Must be a circular list */
atomic_t ref;
unsigned int group_weight;
struct sched_group_capacity *sgc;
/*
* The CPUs this group covers.
*
* NOTE: this field is variable length. (Allocated dynamically
* by attaching extra space to the end of the structure,
* depending on how many CPUs the kernel has booted up with)
*/
unsigned long cpumask[0];
};
static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
{
return to_cpumask(sg->cpumask);
}
/*
* cpumask masking which cpus in the group are allowed to iterate up the domain
* tree.
*/
static inline struct cpumask *sched_group_mask(struct sched_group *sg)
{
return to_cpumask(sg->sgc->cpumask);
}
/**
* group_first_cpu - Returns the first cpu in the cpumask of a sched_group.
* @group: The group whose first cpu is to be returned.
*/
static inline unsigned int group_first_cpu(struct sched_group *group)
{
return cpumask_first(sched_group_cpus(group));
}
extern int group_balance_cpu(struct sched_group *sg);
#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
void register_sched_domain_sysctl(void);
void unregister_sched_domain_sysctl(void);
#else
static inline void register_sched_domain_sysctl(void)
{
}
static inline void unregister_sched_domain_sysctl(void)
{
}
#endif
#else
static inline void sched_ttwu_pending(void) { }
#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_css() 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
set_task_rq_fair(&p->se, p->se.cfs_rq, tg->cfs_rq[cpu]);
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;
p->wake_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)
#define SCHED_FEAT(name, enabled) \
static __always_inline bool static_branch_##name(struct static_key *key) \
{ \
return static_key_##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 */
extern struct static_key_false sched_numa_balancing;
extern struct static_key_false sched_schedstats;
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
}
static inline int task_on_rq_queued(struct task_struct *p)
{
return p->on_rq == TASK_ON_RQ_QUEUED;
}
static inline int task_on_rq_migrating(struct task_struct *p)
{
return p->on_rq == TASK_ON_RQ_MIGRATING;
}
#ifndef prepare_arch_switch
# define prepare_arch_switch(next) do { } while (0)
#endif
#ifndef finish_arch_post_lock_switch
# define finish_arch_post_lock_switch() do { } while (0)
#endif
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.
*
* In particular, the load of prev->state in finish_task_switch() must
* happen before this.
*
* Pairs with the smp_cond_acquire() in try_to_wake_up().
*/
smp_store_release(&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);
}
/*
* wake flags
*/
#define WF_SYNC 0x01 /* waker goes to sleep after wakeup */
#define WF_FORK 0x02 /* child wakeup after fork */
#define WF_MIGRATED 0x4 /* internal use, task got migrated */
/*
* 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
extern const int sched_prio_to_weight[40];
extern const u32 sched_prio_to_wmult[40];
/*
* {de,en}queue flags:
*
* DEQUEUE_SLEEP - task is no longer runnable
* ENQUEUE_WAKEUP - task just became runnable
*
* SAVE/RESTORE - an otherwise spurious dequeue/enqueue, done to ensure tasks
* are in a known state which allows modification. Such pairs
* should preserve as much state as possible.
*
* MOVE - paired with SAVE/RESTORE, explicitly does not preserve the location
* in the runqueue.
*
* ENQUEUE_HEAD - place at front of runqueue (tail if not specified)
* ENQUEUE_REPLENISH - CBS (replenish runtime and postpone deadline)
* ENQUEUE_MIGRATED - the task was migrated during wakeup
*
*/
#define DEQUEUE_SLEEP 0x01
#define DEQUEUE_SAVE 0x02 /* matches ENQUEUE_RESTORE */
#define DEQUEUE_MOVE 0x04 /* matches ENQUEUE_MOVE */
#define ENQUEUE_WAKEUP 0x01
#define ENQUEUE_RESTORE 0x02
#define ENQUEUE_MOVE 0x04
#define ENQUEUE_HEAD 0x08
#define ENQUEUE_REPLENISH 0x10
#ifdef CONFIG_SMP
#define ENQUEUE_MIGRATED 0x20
#else
#define ENQUEUE_MIGRATED 0x00
#endif
#define RETRY_TASK ((void *)-1UL)
struct sched_class {
const struct sched_class *next;
void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
void (*yield_task) (struct rq *rq);
bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt);
void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
/*
* It is the responsibility of the pick_next_task() method that will
* return the next task to call put_prev_task() on the @prev task or
* something equivalent.
*
* May return RETRY_TASK when it finds a higher prio class has runnable
* tasks.
*/
struct task_struct * (*pick_next_task) (struct rq *rq,
struct task_struct *prev,
struct pin_cookie cookie);
void (*put_prev_task) (struct rq *rq, struct task_struct *p);
#ifdef CONFIG_SMP
int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
void (*migrate_task_rq)(struct task_struct *p);
void (*task_woken) (struct rq *this_rq, struct task_struct *task);
void (*set_cpus_allowed)(struct task_struct *p,
const struct cpumask *newmask);
void (*rq_online)(struct rq *rq);
void (*rq_offline)(struct rq *rq);
#endif
void (*set_curr_task) (struct rq *rq);
void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
void (*task_fork) (struct task_struct *p);
void (*task_dead) (struct task_struct *p);
/*
* The switched_from() call is allowed to drop rq->lock, therefore we
* cannot assume the switched_from/switched_to pair is serliazed by
* rq->lock. They are however serialized by p->pi_lock.
*/
void (*switched_from) (struct rq *this_rq, struct task_struct *task);
void (*switched_to) (struct rq *this_rq, struct task_struct *task);
void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
int oldprio);
unsigned int (*get_rr_interval) (struct rq *rq,
struct task_struct *task);
void (*update_curr) (struct rq *rq);
#ifdef CONFIG_FAIR_GROUP_SCHED
void (*task_move_group) (struct task_struct *p);
#endif
};
static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
{
prev->sched_class->put_prev_task(rq, prev);
}
#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 dl_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 update_group_capacity(struct sched_domain *sd, int cpu);
extern void trigger_load_balance(struct rq *rq);
extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask);
#endif
#ifdef CONFIG_CPU_IDLE
static inline void idle_set_state(struct rq *rq,
struct cpuidle_state *idle_state)
{
rq->idle_state = idle_state;
}
static inline struct cpuidle_state *idle_get_state(struct rq *rq)
{
WARN_ON(!rcu_read_lock_held());
return rq->idle_state;
}
#else
static inline void idle_set_state(struct rq *rq,
struct cpuidle_state *idle_state)
{
}
static inline struct cpuidle_state *idle_get_state(struct rq *rq)
{
return NULL;
}
#endif
extern void sysrq_sched_debug_show(void);
extern void sched_init_granularity(void);
extern void update_max_interval(void);
extern void init_sched_dl_class(void);
extern void init_sched_rt_class(void);
extern void init_sched_fair_class(void);
extern void resched_curr(struct rq *rq);
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 struct dl_bandwidth def_dl_bandwidth;
extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime);
extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
unsigned long to_ratio(u64 period, u64 runtime);
extern void init_entity_runnable_average(struct sched_entity *se);
extern void post_init_entity_util_avg(struct sched_entity *se);
#ifdef CONFIG_NO_HZ_FULL
extern bool sched_can_stop_tick(struct rq *rq);
/*
* Tick may be needed by tasks in the runqueue depending on their policy and
* requirements. If tick is needed, lets send the target an IPI to kick it out of
* nohz mode if necessary.
*/
static inline void sched_update_tick_dependency(struct rq *rq)
{
int cpu;
if (!tick_nohz_full_enabled())
return;
cpu = cpu_of(rq);
if (!tick_nohz_full_cpu(cpu))
return;
if (sched_can_stop_tick(rq))
tick_nohz_dep_clear_cpu(cpu, TICK_DEP_BIT_SCHED);
else
tick_nohz_dep_set_cpu(cpu, TICK_DEP_BIT_SCHED);
}
#else
static inline void sched_update_tick_dependency(struct rq *rq) { }
#endif
static inline void add_nr_running(struct rq *rq, unsigned count)
{
unsigned prev_nr = rq->nr_running;
rq->nr_running = prev_nr + count;
if (prev_nr < 2 && rq->nr_running >= 2) {
#ifdef CONFIG_SMP
if (!rq->rd->overload)
rq->rd->overload = true;
#endif
}
sched_update_tick_dependency(rq);
}
static inline void sub_nr_running(struct rq *rq, unsigned count)
{
rq->nr_running -= count;
/* Check if we still need preemption */
sched_update_tick_dependency(rq);
}
static inline void rq_last_tick_reset(struct rq *rq)
{
#ifdef CONFIG_NO_HZ_FULL
rq->last_sched_tick = jiffies;
#endif
}
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);
#ifndef arch_scale_freq_capacity
static __always_inline
unsigned long arch_scale_freq_capacity(struct sched_domain *sd, int cpu)
{
return SCHED_CAPACITY_SCALE;
}
#endif
#ifndef arch_scale_cpu_capacity
static __always_inline
unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
{
if (sd && (sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1))
return sd->smt_gain / sd->span_weight;
return SCHED_CAPACITY_SCALE;
}
#endif
static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
{
rq->rt_avg += rt_delta * arch_scale_freq_capacity(NULL, cpu_of(rq));
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
struct rq_flags {
unsigned long flags;
struct pin_cookie cookie;
};
struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
__acquires(rq->lock);
struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
__acquires(p->pi_lock)
__acquires(rq->lock);
static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf)
__releases(rq->lock)
{
lockdep_unpin_lock(&rq->lock, rf->cookie);
raw_spin_unlock(&rq->lock);
}
static inline void
task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
__releases(rq->lock)
__releases(p->pi_lock)
{
lockdep_unpin_lock(&rq->lock, rf->cookie);
raw_spin_unlock(&rq->lock);
raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
}
#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_);
}
static inline void double_lock(spinlock_t *l1, spinlock_t *l2)
{
if (l1 > l2)
swap(l1, l2);
spin_lock(l1);
spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
}
static inline void double_lock_irq(spinlock_t *l1, spinlock_t *l2)
{
if (l1 > l2)
swap(l1, l2);
spin_lock_irq(l1);
spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
}
static inline void double_raw_lock(raw_spinlock_t *l1, raw_spinlock_t *l2)
{
if (l1 > l2)
swap(l1, l2);
raw_spin_lock(l1);
raw_spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
}
/*
* 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);
#ifdef CONFIG_SCHED_DEBUG
extern void print_cfs_stats(struct seq_file *m, int cpu);
extern void print_rt_stats(struct seq_file *m, int cpu);
extern void print_dl_stats(struct seq_file *m, int cpu);
extern void
print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
#ifdef CONFIG_NUMA_BALANCING
extern void
show_numa_stats(struct task_struct *p, struct seq_file *m);
extern void
print_numa_stats(struct seq_file *m, int node, unsigned long tsf,
unsigned long tpf, unsigned long gsf, unsigned long gpf);
#endif /* CONFIG_NUMA_BALANCING */
#endif /* CONFIG_SCHED_DEBUG */
extern void init_cfs_rq(struct cfs_rq *cfs_rq);
extern void init_rt_rq(struct rt_rq *rt_rq);
extern void init_dl_rq(struct dl_rq *dl_rq);
extern void cfs_bandwidth_usage_inc(void);
extern void cfs_bandwidth_usage_dec(void);
#ifdef CONFIG_NO_HZ_COMMON
enum rq_nohz_flag_bits {
NOHZ_TICK_STOPPED,
NOHZ_BALANCE_KICK,
};
#define nohz_flags(cpu) (&cpu_rq(cpu)->nohz_flags)
extern void nohz_balance_exit_idle(unsigned int cpu);
#else
static inline void nohz_balance_exit_idle(unsigned int cpu) { }
#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 */
#ifdef CONFIG_CPU_FREQ
DECLARE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
/**
* cpufreq_update_util - Take a note about CPU utilization changes.
* @time: Current time.
* @util: Current utilization.
* @max: Utilization ceiling.
*
* This function is called by the scheduler on every invocation of
* update_load_avg() on the CPU whose utilization is being updated.
*
* It can only be called from RCU-sched read-side critical sections.
*/
static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max)
{
struct update_util_data *data;
data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data));
if (data)
data->func(data, time, util, max);
}
/**
* cpufreq_trigger_update - Trigger CPU performance state evaluation if needed.
* @time: Current time.
*
* The way cpufreq is currently arranged requires it to evaluate the CPU
* performance state (frequency/voltage) on a regular basis to prevent it from
* being stuck in a completely inadequate performance level for too long.
* That is not guaranteed to happen if the updates are only triggered from CFS,
* though, because they may not be coming in if RT or deadline tasks are active
* all the time (or there are RT and DL tasks only).
*
* As a workaround for that issue, this function is called by the RT and DL
* sched classes to trigger extra cpufreq updates to prevent it from stalling,
* but that really is a band-aid. Going forward it should be replaced with
* solutions targeted more specifically at RT and DL tasks.
*/
static inline void cpufreq_trigger_update(u64 time)
{
cpufreq_update_util(time, ULONG_MAX, 0);
}
#else
static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max) {}
static inline void cpufreq_trigger_update(u64 time) {}
#endif /* CONFIG_CPU_FREQ */
#ifdef arch_scale_freq_capacity
#ifndef arch_scale_freq_invariant
#define arch_scale_freq_invariant() (true)
#endif
#else /* arch_scale_freq_capacity */
#define arch_scale_freq_invariant() (false)
#endif
static inline void account_reset_rq(struct rq *rq)
{
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
rq->prev_irq_time = 0;
#endif
#ifdef CONFIG_PARAVIRT
rq->prev_steal_time = 0;
#endif
#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
rq->prev_steal_time_rq = 0;
#endif
}