9486 lines
229 KiB
C
9486 lines
229 KiB
C
/*
|
|
* kernel/sched.c
|
|
*
|
|
* Kernel scheduler and related syscalls
|
|
*
|
|
* Copyright (C) 1991-2002 Linus Torvalds
|
|
*
|
|
* 1996-12-23 Modified by Dave Grothe to fix bugs in semaphores and
|
|
* make semaphores SMP safe
|
|
* 1998-11-19 Implemented schedule_timeout() and related stuff
|
|
* by Andrea Arcangeli
|
|
* 2002-01-04 New ultra-scalable O(1) scheduler by Ingo Molnar:
|
|
* hybrid priority-list and round-robin design with
|
|
* an array-switch method of distributing timeslices
|
|
* and per-CPU runqueues. Cleanups and useful suggestions
|
|
* by Davide Libenzi, preemptible kernel bits by Robert Love.
|
|
* 2003-09-03 Interactivity tuning by Con Kolivas.
|
|
* 2004-04-02 Scheduler domains code by Nick Piggin
|
|
* 2007-04-15 Work begun on replacing all interactivity tuning with a
|
|
* fair scheduling design by Con Kolivas.
|
|
* 2007-05-05 Load balancing (smp-nice) and other improvements
|
|
* by Peter Williams
|
|
* 2007-05-06 Interactivity improvements to CFS by Mike Galbraith
|
|
* 2007-07-01 Group scheduling enhancements by Srivatsa Vaddagiri
|
|
* 2007-11-29 RT balancing improvements by Steven Rostedt, Gregory Haskins,
|
|
* Thomas Gleixner, Mike Kravetz
|
|
*/
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/module.h>
|
|
#include <linux/nmi.h>
|
|
#include <linux/init.h>
|
|
#include <linux/uaccess.h>
|
|
#include <linux/highmem.h>
|
|
#include <asm/mmu_context.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/capability.h>
|
|
#include <linux/completion.h>
|
|
#include <linux/kernel_stat.h>
|
|
#include <linux/debug_locks.h>
|
|
#include <linux/perf_event.h>
|
|
#include <linux/security.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/profile.h>
|
|
#include <linux/freezer.h>
|
|
#include <linux/vmalloc.h>
|
|
#include <linux/blkdev.h>
|
|
#include <linux/delay.h>
|
|
#include <linux/pid_namespace.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/threads.h>
|
|
#include <linux/timer.h>
|
|
#include <linux/rcupdate.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/cpuset.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/proc_fs.h>
|
|
#include <linux/seq_file.h>
|
|
#include <linux/stop_machine.h>
|
|
#include <linux/sysctl.h>
|
|
#include <linux/syscalls.h>
|
|
#include <linux/times.h>
|
|
#include <linux/tsacct_kern.h>
|
|
#include <linux/kprobes.h>
|
|
#include <linux/delayacct.h>
|
|
#include <linux/unistd.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/hrtimer.h>
|
|
#include <linux/tick.h>
|
|
#include <linux/debugfs.h>
|
|
#include <linux/ctype.h>
|
|
#include <linux/ftrace.h>
|
|
#include <linux/slab.h>
|
|
|
|
#include <asm/tlb.h>
|
|
#include <asm/irq_regs.h>
|
|
#include <asm/mutex.h>
|
|
|
|
#include "sched_cpupri.h"
|
|
#include "workqueue_sched.h"
|
|
#include "sched_autogroup.h"
|
|
|
|
#define CREATE_TRACE_POINTS
|
|
#include <trace/events/sched.h>
|
|
|
|
/*
|
|
* 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:
|
|
*
|
|
* default timeslice is 100 msecs (used only for SCHED_RR tasks).
|
|
* Timeslices get refilled after they expire.
|
|
*/
|
|
#define DEF_TIMESLICE (100 * HZ / 1000)
|
|
|
|
/*
|
|
* single value that denotes runtime == period, ie unlimited time.
|
|
*/
|
|
#define RUNTIME_INF ((u64)~0ULL)
|
|
|
|
static inline int rt_policy(int policy)
|
|
{
|
|
if (unlikely(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;
|
|
};
|
|
|
|
static struct rt_bandwidth def_rt_bandwidth;
|
|
|
|
static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);
|
|
|
|
static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer)
|
|
{
|
|
struct rt_bandwidth *rt_b =
|
|
container_of(timer, struct rt_bandwidth, rt_period_timer);
|
|
ktime_t now;
|
|
int overrun;
|
|
int idle = 0;
|
|
|
|
for (;;) {
|
|
now = hrtimer_cb_get_time(timer);
|
|
overrun = hrtimer_forward(timer, now, rt_b->rt_period);
|
|
|
|
if (!overrun)
|
|
break;
|
|
|
|
idle = do_sched_rt_period_timer(rt_b, overrun);
|
|
}
|
|
|
|
return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
|
|
}
|
|
|
|
static
|
|
void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime)
|
|
{
|
|
rt_b->rt_period = ns_to_ktime(period);
|
|
rt_b->rt_runtime = runtime;
|
|
|
|
raw_spin_lock_init(&rt_b->rt_runtime_lock);
|
|
|
|
hrtimer_init(&rt_b->rt_period_timer,
|
|
CLOCK_MONOTONIC, HRTIMER_MODE_REL);
|
|
rt_b->rt_period_timer.function = sched_rt_period_timer;
|
|
}
|
|
|
|
static inline int rt_bandwidth_enabled(void)
|
|
{
|
|
return sysctl_sched_rt_runtime >= 0;
|
|
}
|
|
|
|
static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
|
|
{
|
|
ktime_t now;
|
|
|
|
if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
|
|
return;
|
|
|
|
if (hrtimer_active(&rt_b->rt_period_timer))
|
|
return;
|
|
|
|
raw_spin_lock(&rt_b->rt_runtime_lock);
|
|
for (;;) {
|
|
unsigned long delta;
|
|
ktime_t soft, hard;
|
|
|
|
if (hrtimer_active(&rt_b->rt_period_timer))
|
|
break;
|
|
|
|
now = hrtimer_cb_get_time(&rt_b->rt_period_timer);
|
|
hrtimer_forward(&rt_b->rt_period_timer, now, rt_b->rt_period);
|
|
|
|
soft = hrtimer_get_softexpires(&rt_b->rt_period_timer);
|
|
hard = hrtimer_get_expires(&rt_b->rt_period_timer);
|
|
delta = ktime_to_ns(ktime_sub(hard, soft));
|
|
__hrtimer_start_range_ns(&rt_b->rt_period_timer, soft, delta,
|
|
HRTIMER_MODE_ABS_PINNED, 0);
|
|
}
|
|
raw_spin_unlock(&rt_b->rt_runtime_lock);
|
|
}
|
|
|
|
#ifdef CONFIG_RT_GROUP_SCHED
|
|
static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b)
|
|
{
|
|
hrtimer_cancel(&rt_b->rt_period_timer);
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* sched_domains_mutex serializes calls to arch_init_sched_domains,
|
|
* detach_destroy_domains and partition_sched_domains.
|
|
*/
|
|
static DEFINE_MUTEX(sched_domains_mutex);
|
|
|
|
#ifdef CONFIG_CGROUP_SCHED
|
|
|
|
#include <linux/cgroup.h>
|
|
|
|
struct cfs_rq;
|
|
|
|
static LIST_HEAD(task_groups);
|
|
|
|
/* 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;
|
|
#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
|
|
};
|
|
|
|
/* task_group_lock serializes the addition/removal of task groups */
|
|
static DEFINE_SPINLOCK(task_group_lock);
|
|
|
|
#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 2
|
|
#define MAX_SHARES (1UL << 18)
|
|
|
|
static int root_task_group_load = ROOT_TASK_GROUP_LOAD;
|
|
#endif
|
|
|
|
/* Default task group.
|
|
* Every task in system belong to this group at bootup.
|
|
*/
|
|
struct task_group root_task_group;
|
|
|
|
#endif /* CONFIG_CGROUP_SCHED */
|
|
|
|
/* CFS-related fields in a runqueue */
|
|
struct cfs_rq {
|
|
struct load_weight load;
|
|
unsigned long nr_running;
|
|
|
|
u64 exec_clock;
|
|
u64 min_vruntime;
|
|
|
|
struct rb_root tasks_timeline;
|
|
struct rb_node *rb_leftmost;
|
|
|
|
struct list_head tasks;
|
|
struct list_head *balance_iterator;
|
|
|
|
/*
|
|
* '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;
|
|
|
|
unsigned int nr_spread_over;
|
|
|
|
#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_SMP
|
|
/*
|
|
* the part of load.weight contributed by tasks
|
|
*/
|
|
unsigned long task_weight;
|
|
|
|
/*
|
|
* h_load = weight * f(tg)
|
|
*
|
|
* Where f(tg) is the recursive weight fraction assigned to
|
|
* this group.
|
|
*/
|
|
unsigned long h_load;
|
|
|
|
/*
|
|
* Maintaining per-cpu shares distribution for group scheduling
|
|
*
|
|
* load_stamp is the last time we updated the load average
|
|
* load_last is the last time we updated the load average and saw load
|
|
* load_unacc_exec_time is currently unaccounted execution time
|
|
*/
|
|
u64 load_avg;
|
|
u64 load_period;
|
|
u64 load_stamp, load_last, load_unacc_exec_time;
|
|
|
|
unsigned long load_contribution;
|
|
#endif
|
|
#endif
|
|
};
|
|
|
|
/* Real-Time classes' related field in a runqueue: */
|
|
struct rt_rq {
|
|
struct rt_prio_array active;
|
|
unsigned long 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;
|
|
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;
|
|
atomic_t rto_count;
|
|
struct cpupri cpupri;
|
|
};
|
|
|
|
/*
|
|
* By default the system creates a single root-domain with all cpus as
|
|
* members (mimicking the global state we have today).
|
|
*/
|
|
static 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 long 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 char nohz_balance_kick;
|
|
#endif
|
|
unsigned 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;
|
|
#endif
|
|
#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_at_tick;
|
|
/* 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;
|
|
|
|
unsigned long avg_load_per_task;
|
|
|
|
u64 rt_avg;
|
|
u64 age_stamp;
|
|
u64 idle_stamp;
|
|
u64 avg_idle;
|
|
#endif
|
|
|
|
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
|
|
u64 prev_irq_time;
|
|
#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_switch;
|
|
unsigned int sched_count;
|
|
unsigned int sched_goidle;
|
|
|
|
/* try_to_wake_up() stats */
|
|
unsigned int ttwu_count;
|
|
unsigned int ttwu_local;
|
|
#endif
|
|
};
|
|
|
|
static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
|
|
|
|
|
|
static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
|
|
|
|
static inline int cpu_of(struct rq *rq)
|
|
{
|
|
#ifdef CONFIG_SMP
|
|
return rq->cpu;
|
|
#else
|
|
return 0;
|
|
#endif
|
|
}
|
|
|
|
#define rcu_dereference_check_sched_domain(p) \
|
|
rcu_dereference_check((p), \
|
|
rcu_read_lock_sched_held() || \
|
|
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 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_CGROUP_SCHED
|
|
|
|
/*
|
|
* Return the group to which this tasks belongs.
|
|
*
|
|
* We use task_subsys_state_check() and extend the RCU verification
|
|
* with lockdep_is_held(&task_rq(p)->lock) because cpu_cgroup_attach()
|
|
* holds that lock for each task it moves into the cgroup. Therefore
|
|
* by holding that lock, we pin the task to the current cgroup.
|
|
*/
|
|
static inline struct task_group *task_group(struct task_struct *p)
|
|
{
|
|
struct task_group *tg;
|
|
struct cgroup_subsys_state *css;
|
|
|
|
css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
|
|
lockdep_is_held(&task_rq(p)->lock));
|
|
tg = container_of(css, struct task_group, css);
|
|
|
|
return autogroup_task_group(p, tg);
|
|
}
|
|
|
|
/* 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)
|
|
{
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
p->se.cfs_rq = task_group(p)->cfs_rq[cpu];
|
|
p->se.parent = task_group(p)->se[cpu];
|
|
#endif
|
|
|
|
#ifdef CONFIG_RT_GROUP_SCHED
|
|
p->rt.rt_rq = task_group(p)->rt_rq[cpu];
|
|
p->rt.parent = task_group(p)->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 void update_rq_clock_task(struct rq *rq, s64 delta);
|
|
|
|
static void update_rq_clock(struct rq *rq)
|
|
{
|
|
s64 delta;
|
|
|
|
if (rq->skip_clock_update)
|
|
return;
|
|
|
|
delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
|
|
rq->clock += delta;
|
|
update_rq_clock_task(rq, delta);
|
|
}
|
|
|
|
/*
|
|
* Tunables that become constants when CONFIG_SCHED_DEBUG is off:
|
|
*/
|
|
#ifdef CONFIG_SCHED_DEBUG
|
|
# define const_debug __read_mostly
|
|
#else
|
|
# define const_debug static const
|
|
#endif
|
|
|
|
/**
|
|
* runqueue_is_locked - Returns true if the current cpu runqueue is locked
|
|
* @cpu: the processor in question.
|
|
*
|
|
* This interface allows printk to be called with the runqueue lock
|
|
* held and know whether or not it is OK to wake up the klogd.
|
|
*/
|
|
int runqueue_is_locked(int cpu)
|
|
{
|
|
return raw_spin_is_locked(&cpu_rq(cpu)->lock);
|
|
}
|
|
|
|
/*
|
|
* Debugging: various feature bits
|
|
*/
|
|
|
|
#define SCHED_FEAT(name, enabled) \
|
|
__SCHED_FEAT_##name ,
|
|
|
|
enum {
|
|
#include "sched_features.h"
|
|
};
|
|
|
|
#undef SCHED_FEAT
|
|
|
|
#define SCHED_FEAT(name, enabled) \
|
|
(1UL << __SCHED_FEAT_##name) * enabled |
|
|
|
|
const_debug unsigned int sysctl_sched_features =
|
|
#include "sched_features.h"
|
|
0;
|
|
|
|
#undef SCHED_FEAT
|
|
|
|
#ifdef CONFIG_SCHED_DEBUG
|
|
#define SCHED_FEAT(name, enabled) \
|
|
#name ,
|
|
|
|
static __read_mostly char *sched_feat_names[] = {
|
|
#include "sched_features.h"
|
|
NULL
|
|
};
|
|
|
|
#undef SCHED_FEAT
|
|
|
|
static int sched_feat_show(struct seq_file *m, void *v)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; sched_feat_names[i]; i++) {
|
|
if (!(sysctl_sched_features & (1UL << i)))
|
|
seq_puts(m, "NO_");
|
|
seq_printf(m, "%s ", sched_feat_names[i]);
|
|
}
|
|
seq_puts(m, "\n");
|
|
|
|
return 0;
|
|
}
|
|
|
|
static ssize_t
|
|
sched_feat_write(struct file *filp, const char __user *ubuf,
|
|
size_t cnt, loff_t *ppos)
|
|
{
|
|
char buf[64];
|
|
char *cmp;
|
|
int neg = 0;
|
|
int i;
|
|
|
|
if (cnt > 63)
|
|
cnt = 63;
|
|
|
|
if (copy_from_user(&buf, ubuf, cnt))
|
|
return -EFAULT;
|
|
|
|
buf[cnt] = 0;
|
|
cmp = strstrip(buf);
|
|
|
|
if (strncmp(cmp, "NO_", 3) == 0) {
|
|
neg = 1;
|
|
cmp += 3;
|
|
}
|
|
|
|
for (i = 0; sched_feat_names[i]; i++) {
|
|
if (strcmp(cmp, sched_feat_names[i]) == 0) {
|
|
if (neg)
|
|
sysctl_sched_features &= ~(1UL << i);
|
|
else
|
|
sysctl_sched_features |= (1UL << i);
|
|
break;
|
|
}
|
|
}
|
|
|
|
if (!sched_feat_names[i])
|
|
return -EINVAL;
|
|
|
|
*ppos += cnt;
|
|
|
|
return cnt;
|
|
}
|
|
|
|
static int sched_feat_open(struct inode *inode, struct file *filp)
|
|
{
|
|
return single_open(filp, sched_feat_show, NULL);
|
|
}
|
|
|
|
static const struct file_operations sched_feat_fops = {
|
|
.open = sched_feat_open,
|
|
.write = sched_feat_write,
|
|
.read = seq_read,
|
|
.llseek = seq_lseek,
|
|
.release = single_release,
|
|
};
|
|
|
|
static __init int sched_init_debug(void)
|
|
{
|
|
debugfs_create_file("sched_features", 0644, NULL, NULL,
|
|
&sched_feat_fops);
|
|
|
|
return 0;
|
|
}
|
|
late_initcall(sched_init_debug);
|
|
|
|
#endif
|
|
|
|
#define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
|
|
|
|
/*
|
|
* Number of tasks to iterate in a single balance run.
|
|
* Limited because this is done with IRQs disabled.
|
|
*/
|
|
const_debug unsigned int sysctl_sched_nr_migrate = 32;
|
|
|
|
/*
|
|
* period over which we average the RT time consumption, measured
|
|
* in ms.
|
|
*
|
|
* default: 1s
|
|
*/
|
|
const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC;
|
|
|
|
/*
|
|
* period over which we measure -rt task cpu usage in us.
|
|
* default: 1s
|
|
*/
|
|
unsigned int sysctl_sched_rt_period = 1000000;
|
|
|
|
static __read_mostly int scheduler_running;
|
|
|
|
/*
|
|
* part of the period that we allow rt tasks to run in us.
|
|
* default: 0.95s
|
|
*/
|
|
int sysctl_sched_rt_runtime = 950000;
|
|
|
|
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;
|
|
}
|
|
|
|
#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
|
|
|
|
static inline int task_current(struct rq *rq, struct task_struct *p)
|
|
{
|
|
return rq->curr == p;
|
|
}
|
|
|
|
#ifndef __ARCH_WANT_UNLOCKED_CTXSW
|
|
static inline int task_running(struct rq *rq, struct task_struct *p)
|
|
{
|
|
return task_current(rq, p);
|
|
}
|
|
|
|
static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
|
|
{
|
|
}
|
|
|
|
static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
|
|
{
|
|
#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 int task_running(struct rq *rq, struct task_struct *p)
|
|
{
|
|
#ifdef CONFIG_SMP
|
|
return p->oncpu;
|
|
#else
|
|
return task_current(rq, p);
|
|
#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->oncpu = 1;
|
|
#endif
|
|
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
|
|
raw_spin_unlock_irq(&rq->lock);
|
|
#else
|
|
raw_spin_unlock(&rq->lock);
|
|
#endif
|
|
}
|
|
|
|
static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
|
|
{
|
|
#ifdef CONFIG_SMP
|
|
/*
|
|
* After ->oncpu 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->oncpu = 0;
|
|
#endif
|
|
#ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW
|
|
local_irq_enable();
|
|
#endif
|
|
}
|
|
#endif /* __ARCH_WANT_UNLOCKED_CTXSW */
|
|
|
|
/*
|
|
* Check whether the task is waking, we use this to synchronize ->cpus_allowed
|
|
* against ttwu().
|
|
*/
|
|
static inline int task_is_waking(struct task_struct *p)
|
|
{
|
|
return unlikely(p->state == TASK_WAKING);
|
|
}
|
|
|
|
/*
|
|
* __task_rq_lock - lock the runqueue a given task resides on.
|
|
* Must be called interrupts disabled.
|
|
*/
|
|
static inline struct rq *__task_rq_lock(struct task_struct *p)
|
|
__acquires(rq->lock)
|
|
{
|
|
struct rq *rq;
|
|
|
|
for (;;) {
|
|
rq = task_rq(p);
|
|
raw_spin_lock(&rq->lock);
|
|
if (likely(rq == task_rq(p)))
|
|
return rq;
|
|
raw_spin_unlock(&rq->lock);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* task_rq_lock - lock the runqueue a given task resides on and disable
|
|
* interrupts. Note the ordering: we can safely lookup the task_rq without
|
|
* explicitly disabling preemption.
|
|
*/
|
|
static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
|
|
__acquires(rq->lock)
|
|
{
|
|
struct rq *rq;
|
|
|
|
for (;;) {
|
|
local_irq_save(*flags);
|
|
rq = task_rq(p);
|
|
raw_spin_lock(&rq->lock);
|
|
if (likely(rq == task_rq(p)))
|
|
return rq;
|
|
raw_spin_unlock_irqrestore(&rq->lock, *flags);
|
|
}
|
|
}
|
|
|
|
static void __task_rq_unlock(struct rq *rq)
|
|
__releases(rq->lock)
|
|
{
|
|
raw_spin_unlock(&rq->lock);
|
|
}
|
|
|
|
static inline void task_rq_unlock(struct rq *rq, unsigned long *flags)
|
|
__releases(rq->lock)
|
|
{
|
|
raw_spin_unlock_irqrestore(&rq->lock, *flags);
|
|
}
|
|
|
|
/*
|
|
* this_rq_lock - lock this runqueue and disable interrupts.
|
|
*/
|
|
static struct rq *this_rq_lock(void)
|
|
__acquires(rq->lock)
|
|
{
|
|
struct rq *rq;
|
|
|
|
local_irq_disable();
|
|
rq = this_rq();
|
|
raw_spin_lock(&rq->lock);
|
|
|
|
return rq;
|
|
}
|
|
|
|
#ifdef CONFIG_SCHED_HRTICK
|
|
/*
|
|
* Use HR-timers to deliver accurate preemption points.
|
|
*
|
|
* Its all a bit involved since we cannot program an hrt while holding the
|
|
* rq->lock. So what we do is store a state in in rq->hrtick_* and ask for a
|
|
* reschedule event.
|
|
*
|
|
* When we get rescheduled we reprogram the hrtick_timer outside of the
|
|
* rq->lock.
|
|
*/
|
|
|
|
/*
|
|
* 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);
|
|
}
|
|
|
|
static void hrtick_clear(struct rq *rq)
|
|
{
|
|
if (hrtimer_active(&rq->hrtick_timer))
|
|
hrtimer_cancel(&rq->hrtick_timer);
|
|
}
|
|
|
|
/*
|
|
* High-resolution timer tick.
|
|
* Runs from hardirq context with interrupts disabled.
|
|
*/
|
|
static enum hrtimer_restart hrtick(struct hrtimer *timer)
|
|
{
|
|
struct rq *rq = container_of(timer, struct rq, hrtick_timer);
|
|
|
|
WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
|
|
|
|
raw_spin_lock(&rq->lock);
|
|
update_rq_clock(rq);
|
|
rq->curr->sched_class->task_tick(rq, rq->curr, 1);
|
|
raw_spin_unlock(&rq->lock);
|
|
|
|
return HRTIMER_NORESTART;
|
|
}
|
|
|
|
#ifdef CONFIG_SMP
|
|
/*
|
|
* called from hardirq (IPI) context
|
|
*/
|
|
static void __hrtick_start(void *arg)
|
|
{
|
|
struct rq *rq = arg;
|
|
|
|
raw_spin_lock(&rq->lock);
|
|
hrtimer_restart(&rq->hrtick_timer);
|
|
rq->hrtick_csd_pending = 0;
|
|
raw_spin_unlock(&rq->lock);
|
|
}
|
|
|
|
/*
|
|
* Called to set the hrtick timer state.
|
|
*
|
|
* called with rq->lock held and irqs disabled
|
|
*/
|
|
static void hrtick_start(struct rq *rq, u64 delay)
|
|
{
|
|
struct hrtimer *timer = &rq->hrtick_timer;
|
|
ktime_t time = ktime_add_ns(timer->base->get_time(), delay);
|
|
|
|
hrtimer_set_expires(timer, time);
|
|
|
|
if (rq == this_rq()) {
|
|
hrtimer_restart(timer);
|
|
} else if (!rq->hrtick_csd_pending) {
|
|
__smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0);
|
|
rq->hrtick_csd_pending = 1;
|
|
}
|
|
}
|
|
|
|
static int
|
|
hotplug_hrtick(struct notifier_block *nfb, unsigned long action, void *hcpu)
|
|
{
|
|
int cpu = (int)(long)hcpu;
|
|
|
|
switch (action) {
|
|
case CPU_UP_CANCELED:
|
|
case CPU_UP_CANCELED_FROZEN:
|
|
case CPU_DOWN_PREPARE:
|
|
case CPU_DOWN_PREPARE_FROZEN:
|
|
case CPU_DEAD:
|
|
case CPU_DEAD_FROZEN:
|
|
hrtick_clear(cpu_rq(cpu));
|
|
return NOTIFY_OK;
|
|
}
|
|
|
|
return NOTIFY_DONE;
|
|
}
|
|
|
|
static __init void init_hrtick(void)
|
|
{
|
|
hotcpu_notifier(hotplug_hrtick, 0);
|
|
}
|
|
#else
|
|
/*
|
|
* Called to set the hrtick timer state.
|
|
*
|
|
* called with rq->lock held and irqs disabled
|
|
*/
|
|
static void hrtick_start(struct rq *rq, u64 delay)
|
|
{
|
|
__hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0,
|
|
HRTIMER_MODE_REL_PINNED, 0);
|
|
}
|
|
|
|
static inline void init_hrtick(void)
|
|
{
|
|
}
|
|
#endif /* CONFIG_SMP */
|
|
|
|
static void init_rq_hrtick(struct rq *rq)
|
|
{
|
|
#ifdef CONFIG_SMP
|
|
rq->hrtick_csd_pending = 0;
|
|
|
|
rq->hrtick_csd.flags = 0;
|
|
rq->hrtick_csd.func = __hrtick_start;
|
|
rq->hrtick_csd.info = rq;
|
|
#endif
|
|
|
|
hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
|
|
rq->hrtick_timer.function = hrtick;
|
|
}
|
|
#else /* CONFIG_SCHED_HRTICK */
|
|
static inline void hrtick_clear(struct rq *rq)
|
|
{
|
|
}
|
|
|
|
static inline void init_rq_hrtick(struct rq *rq)
|
|
{
|
|
}
|
|
|
|
static inline void init_hrtick(void)
|
|
{
|
|
}
|
|
#endif /* CONFIG_SCHED_HRTICK */
|
|
|
|
/*
|
|
* resched_task - mark a task 'to be rescheduled now'.
|
|
*
|
|
* On UP this means the setting of the need_resched flag, on SMP it
|
|
* might also involve a cross-CPU call to trigger the scheduler on
|
|
* the target CPU.
|
|
*/
|
|
#ifdef CONFIG_SMP
|
|
|
|
#ifndef tsk_is_polling
|
|
#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
|
|
#endif
|
|
|
|
static void resched_task(struct task_struct *p)
|
|
{
|
|
int cpu;
|
|
|
|
assert_raw_spin_locked(&task_rq(p)->lock);
|
|
|
|
if (test_tsk_need_resched(p))
|
|
return;
|
|
|
|
set_tsk_need_resched(p);
|
|
|
|
cpu = task_cpu(p);
|
|
if (cpu == smp_processor_id())
|
|
return;
|
|
|
|
/* NEED_RESCHED must be visible before we test polling */
|
|
smp_mb();
|
|
if (!tsk_is_polling(p))
|
|
smp_send_reschedule(cpu);
|
|
}
|
|
|
|
static void resched_cpu(int cpu)
|
|
{
|
|
struct rq *rq = cpu_rq(cpu);
|
|
unsigned long flags;
|
|
|
|
if (!raw_spin_trylock_irqsave(&rq->lock, flags))
|
|
return;
|
|
resched_task(cpu_curr(cpu));
|
|
raw_spin_unlock_irqrestore(&rq->lock, flags);
|
|
}
|
|
|
|
#ifdef CONFIG_NO_HZ
|
|
/*
|
|
* In the semi idle case, use the nearest busy cpu for migrating timers
|
|
* from an idle cpu. This is good for power-savings.
|
|
*
|
|
* We don't do similar optimization for completely idle system, as
|
|
* selecting an idle cpu will add more delays to the timers than intended
|
|
* (as that cpu's timer base may not be uptodate wrt jiffies etc).
|
|
*/
|
|
int get_nohz_timer_target(void)
|
|
{
|
|
int cpu = smp_processor_id();
|
|
int i;
|
|
struct sched_domain *sd;
|
|
|
|
for_each_domain(cpu, sd) {
|
|
for_each_cpu(i, sched_domain_span(sd))
|
|
if (!idle_cpu(i))
|
|
return i;
|
|
}
|
|
return cpu;
|
|
}
|
|
/*
|
|
* When add_timer_on() enqueues a timer into the timer wheel of an
|
|
* idle CPU then this timer might expire before the next timer event
|
|
* which is scheduled to wake up that CPU. In case of a completely
|
|
* idle system the next event might even be infinite time into the
|
|
* future. wake_up_idle_cpu() ensures that the CPU is woken up and
|
|
* leaves the inner idle loop so the newly added timer is taken into
|
|
* account when the CPU goes back to idle and evaluates the timer
|
|
* wheel for the next timer event.
|
|
*/
|
|
void wake_up_idle_cpu(int cpu)
|
|
{
|
|
struct rq *rq = cpu_rq(cpu);
|
|
|
|
if (cpu == smp_processor_id())
|
|
return;
|
|
|
|
/*
|
|
* This is safe, as this function is called with the timer
|
|
* wheel base lock of (cpu) held. When the CPU is on the way
|
|
* to idle and has not yet set rq->curr to idle then it will
|
|
* be serialized on the timer wheel base lock and take the new
|
|
* timer into account automatically.
|
|
*/
|
|
if (rq->curr != rq->idle)
|
|
return;
|
|
|
|
/*
|
|
* We can set TIF_RESCHED on the idle task of the other CPU
|
|
* lockless. The worst case is that the other CPU runs the
|
|
* idle task through an additional NOOP schedule()
|
|
*/
|
|
set_tsk_need_resched(rq->idle);
|
|
|
|
/* NEED_RESCHED must be visible before we test polling */
|
|
smp_mb();
|
|
if (!tsk_is_polling(rq->idle))
|
|
smp_send_reschedule(cpu);
|
|
}
|
|
|
|
#endif /* CONFIG_NO_HZ */
|
|
|
|
static u64 sched_avg_period(void)
|
|
{
|
|
return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2;
|
|
}
|
|
|
|
static void sched_avg_update(struct rq *rq)
|
|
{
|
|
s64 period = sched_avg_period();
|
|
|
|
while ((s64)(rq->clock - rq->age_stamp) > period) {
|
|
/*
|
|
* Inline assembly required to prevent the compiler
|
|
* optimising this loop into a divmod call.
|
|
* See __iter_div_u64_rem() for another example of this.
|
|
*/
|
|
asm("" : "+rm" (rq->age_stamp));
|
|
rq->age_stamp += period;
|
|
rq->rt_avg /= 2;
|
|
}
|
|
}
|
|
|
|
static void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
|
|
{
|
|
rq->rt_avg += rt_delta;
|
|
sched_avg_update(rq);
|
|
}
|
|
|
|
#else /* !CONFIG_SMP */
|
|
static void resched_task(struct task_struct *p)
|
|
{
|
|
assert_raw_spin_locked(&task_rq(p)->lock);
|
|
set_tsk_need_resched(p);
|
|
}
|
|
|
|
static void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
|
|
{
|
|
}
|
|
|
|
static void sched_avg_update(struct rq *rq)
|
|
{
|
|
}
|
|
#endif /* CONFIG_SMP */
|
|
|
|
#if BITS_PER_LONG == 32
|
|
# define WMULT_CONST (~0UL)
|
|
#else
|
|
# define WMULT_CONST (1UL << 32)
|
|
#endif
|
|
|
|
#define WMULT_SHIFT 32
|
|
|
|
/*
|
|
* Shift right and round:
|
|
*/
|
|
#define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y))
|
|
|
|
/*
|
|
* delta *= weight / lw
|
|
*/
|
|
static unsigned long
|
|
calc_delta_mine(unsigned long delta_exec, unsigned long weight,
|
|
struct load_weight *lw)
|
|
{
|
|
u64 tmp;
|
|
|
|
if (!lw->inv_weight) {
|
|
if (BITS_PER_LONG > 32 && unlikely(lw->weight >= WMULT_CONST))
|
|
lw->inv_weight = 1;
|
|
else
|
|
lw->inv_weight = 1 + (WMULT_CONST-lw->weight/2)
|
|
/ (lw->weight+1);
|
|
}
|
|
|
|
tmp = (u64)delta_exec * weight;
|
|
/*
|
|
* Check whether we'd overflow the 64-bit multiplication:
|
|
*/
|
|
if (unlikely(tmp > WMULT_CONST))
|
|
tmp = SRR(SRR(tmp, WMULT_SHIFT/2) * lw->inv_weight,
|
|
WMULT_SHIFT/2);
|
|
else
|
|
tmp = SRR(tmp * lw->inv_weight, WMULT_SHIFT);
|
|
|
|
return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX);
|
|
}
|
|
|
|
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,
|
|
};
|
|
|
|
#ifdef CONFIG_CGROUP_CPUACCT
|
|
static void cpuacct_charge(struct task_struct *tsk, u64 cputime);
|
|
static void cpuacct_update_stats(struct task_struct *tsk,
|
|
enum cpuacct_stat_index idx, cputime_t val);
|
|
#else
|
|
static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
|
|
static inline void cpuacct_update_stats(struct task_struct *tsk,
|
|
enum cpuacct_stat_index idx, cputime_t val) {}
|
|
#endif
|
|
|
|
static inline void inc_cpu_load(struct rq *rq, unsigned long load)
|
|
{
|
|
update_load_add(&rq->load, load);
|
|
}
|
|
|
|
static inline void dec_cpu_load(struct rq *rq, unsigned long load)
|
|
{
|
|
update_load_sub(&rq->load, load);
|
|
}
|
|
|
|
#if (defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)) || defined(CONFIG_RT_GROUP_SCHED)
|
|
typedef int (*tg_visitor)(struct task_group *, void *);
|
|
|
|
/*
|
|
* Iterate the full tree, calling @down when first entering a node and @up when
|
|
* leaving it for the final time.
|
|
*/
|
|
static int walk_tg_tree(tg_visitor down, tg_visitor up, void *data)
|
|
{
|
|
struct task_group *parent, *child;
|
|
int ret;
|
|
|
|
rcu_read_lock();
|
|
parent = &root_task_group;
|
|
down:
|
|
ret = (*down)(parent, data);
|
|
if (ret)
|
|
goto out_unlock;
|
|
list_for_each_entry_rcu(child, &parent->children, siblings) {
|
|
parent = child;
|
|
goto down;
|
|
|
|
up:
|
|
continue;
|
|
}
|
|
ret = (*up)(parent, data);
|
|
if (ret)
|
|
goto out_unlock;
|
|
|
|
child = parent;
|
|
parent = parent->parent;
|
|
if (parent)
|
|
goto up;
|
|
out_unlock:
|
|
rcu_read_unlock();
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int tg_nop(struct task_group *tg, void *data)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_SMP
|
|
/* Used instead of source_load when we know the type == 0 */
|
|
static unsigned long weighted_cpuload(const int cpu)
|
|
{
|
|
return cpu_rq(cpu)->load.weight;
|
|
}
|
|
|
|
/*
|
|
* Return a low guess at the load of a migration-source cpu weighted
|
|
* according to the scheduling class and "nice" value.
|
|
*
|
|
* We want to under-estimate the load of migration sources, to
|
|
* balance conservatively.
|
|
*/
|
|
static unsigned long source_load(int cpu, int type)
|
|
{
|
|
struct rq *rq = cpu_rq(cpu);
|
|
unsigned long total = weighted_cpuload(cpu);
|
|
|
|
if (type == 0 || !sched_feat(LB_BIAS))
|
|
return total;
|
|
|
|
return min(rq->cpu_load[type-1], total);
|
|
}
|
|
|
|
/*
|
|
* Return a high guess at the load of a migration-target cpu weighted
|
|
* according to the scheduling class and "nice" value.
|
|
*/
|
|
static unsigned long target_load(int cpu, int type)
|
|
{
|
|
struct rq *rq = cpu_rq(cpu);
|
|
unsigned long total = weighted_cpuload(cpu);
|
|
|
|
if (type == 0 || !sched_feat(LB_BIAS))
|
|
return total;
|
|
|
|
return max(rq->cpu_load[type-1], total);
|
|
}
|
|
|
|
static unsigned long power_of(int cpu)
|
|
{
|
|
return cpu_rq(cpu)->cpu_power;
|
|
}
|
|
|
|
static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);
|
|
|
|
static unsigned long cpu_avg_load_per_task(int cpu)
|
|
{
|
|
struct rq *rq = cpu_rq(cpu);
|
|
unsigned long nr_running = ACCESS_ONCE(rq->nr_running);
|
|
|
|
if (nr_running)
|
|
rq->avg_load_per_task = rq->load.weight / nr_running;
|
|
else
|
|
rq->avg_load_per_task = 0;
|
|
|
|
return rq->avg_load_per_task;
|
|
}
|
|
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
|
|
/*
|
|
* Compute the cpu's hierarchical load factor for each task group.
|
|
* This needs to be done in a top-down fashion because the load of a child
|
|
* group is a fraction of its parents load.
|
|
*/
|
|
static int tg_load_down(struct task_group *tg, void *data)
|
|
{
|
|
unsigned long load;
|
|
long cpu = (long)data;
|
|
|
|
if (!tg->parent) {
|
|
load = cpu_rq(cpu)->load.weight;
|
|
} else {
|
|
load = tg->parent->cfs_rq[cpu]->h_load;
|
|
load *= tg->se[cpu]->load.weight;
|
|
load /= tg->parent->cfs_rq[cpu]->load.weight + 1;
|
|
}
|
|
|
|
tg->cfs_rq[cpu]->h_load = load;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void update_h_load(long cpu)
|
|
{
|
|
walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
|
|
}
|
|
|
|
#endif
|
|
|
|
#ifdef CONFIG_PREEMPT
|
|
|
|
static 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 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 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 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 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 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 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
|
|
|
|
static void calc_load_account_idle(struct rq *this_rq);
|
|
static void update_sysctl(void);
|
|
static int get_update_sysctl_factor(void);
|
|
static void update_cpu_load(struct rq *this_rq);
|
|
|
|
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
|
|
}
|
|
|
|
static const struct sched_class rt_sched_class;
|
|
|
|
#define sched_class_highest (&stop_sched_class)
|
|
#define for_each_class(class) \
|
|
for (class = sched_class_highest; class; class = class->next)
|
|
|
|
#include "sched_stats.h"
|
|
|
|
static void inc_nr_running(struct rq *rq)
|
|
{
|
|
rq->nr_running++;
|
|
}
|
|
|
|
static void dec_nr_running(struct rq *rq)
|
|
{
|
|
rq->nr_running--;
|
|
}
|
|
|
|
static void set_load_weight(struct task_struct *p)
|
|
{
|
|
/*
|
|
* SCHED_IDLE tasks get minimal weight:
|
|
*/
|
|
if (p->policy == SCHED_IDLE) {
|
|
p->se.load.weight = WEIGHT_IDLEPRIO;
|
|
p->se.load.inv_weight = WMULT_IDLEPRIO;
|
|
return;
|
|
}
|
|
|
|
p->se.load.weight = prio_to_weight[p->static_prio - MAX_RT_PRIO];
|
|
p->se.load.inv_weight = prio_to_wmult[p->static_prio - MAX_RT_PRIO];
|
|
}
|
|
|
|
static void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
|
|
{
|
|
update_rq_clock(rq);
|
|
sched_info_queued(p);
|
|
p->sched_class->enqueue_task(rq, p, flags);
|
|
p->se.on_rq = 1;
|
|
}
|
|
|
|
static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
|
|
{
|
|
update_rq_clock(rq);
|
|
sched_info_dequeued(p);
|
|
p->sched_class->dequeue_task(rq, p, flags);
|
|
p->se.on_rq = 0;
|
|
}
|
|
|
|
/*
|
|
* activate_task - move a task to the runqueue.
|
|
*/
|
|
static void activate_task(struct rq *rq, struct task_struct *p, int flags)
|
|
{
|
|
if (task_contributes_to_load(p))
|
|
rq->nr_uninterruptible--;
|
|
|
|
enqueue_task(rq, p, flags);
|
|
inc_nr_running(rq);
|
|
}
|
|
|
|
/*
|
|
* deactivate_task - remove a task from the runqueue.
|
|
*/
|
|
static void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
|
|
{
|
|
if (task_contributes_to_load(p))
|
|
rq->nr_uninterruptible++;
|
|
|
|
dequeue_task(rq, p, flags);
|
|
dec_nr_running(rq);
|
|
}
|
|
|
|
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
|
|
|
|
/*
|
|
* There are no locks covering percpu hardirq/softirq time.
|
|
* They are only modified in account_system_vtime, on corresponding CPU
|
|
* with interrupts disabled. So, writes are safe.
|
|
* They are read and saved off onto struct rq in update_rq_clock().
|
|
* This may result in other CPU reading this CPU's irq time and can
|
|
* race with irq/account_system_vtime on this CPU. We would either get old
|
|
* or new value with a side effect of accounting a slice of irq time to wrong
|
|
* task when irq is in progress while we read rq->clock. That is a worthy
|
|
* compromise in place of having locks on each irq in account_system_time.
|
|
*/
|
|
static DEFINE_PER_CPU(u64, cpu_hardirq_time);
|
|
static DEFINE_PER_CPU(u64, cpu_softirq_time);
|
|
|
|
static DEFINE_PER_CPU(u64, irq_start_time);
|
|
static int sched_clock_irqtime;
|
|
|
|
void enable_sched_clock_irqtime(void)
|
|
{
|
|
sched_clock_irqtime = 1;
|
|
}
|
|
|
|
void disable_sched_clock_irqtime(void)
|
|
{
|
|
sched_clock_irqtime = 0;
|
|
}
|
|
|
|
#ifndef CONFIG_64BIT
|
|
static DEFINE_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 */
|
|
|
|
/*
|
|
* Called before incrementing preempt_count on {soft,}irq_enter
|
|
* and before decrementing preempt_count on {soft,}irq_exit.
|
|
*/
|
|
void account_system_vtime(struct task_struct *curr)
|
|
{
|
|
unsigned long flags;
|
|
s64 delta;
|
|
int cpu;
|
|
|
|
if (!sched_clock_irqtime)
|
|
return;
|
|
|
|
local_irq_save(flags);
|
|
|
|
cpu = smp_processor_id();
|
|
delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time);
|
|
__this_cpu_add(irq_start_time, delta);
|
|
|
|
irq_time_write_begin();
|
|
/*
|
|
* We do not account for softirq time from ksoftirqd here.
|
|
* We want to continue accounting softirq time to ksoftirqd thread
|
|
* in that case, so as not to confuse scheduler with a special task
|
|
* that do not consume any time, but still wants to run.
|
|
*/
|
|
if (hardirq_count())
|
|
__this_cpu_add(cpu_hardirq_time, delta);
|
|
else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
|
|
__this_cpu_add(cpu_softirq_time, delta);
|
|
|
|
irq_time_write_end();
|
|
local_irq_restore(flags);
|
|
}
|
|
EXPORT_SYMBOL_GPL(account_system_vtime);
|
|
|
|
static void update_rq_clock_task(struct rq *rq, s64 delta)
|
|
{
|
|
s64 irq_delta;
|
|
|
|
irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
|
|
|
|
/*
|
|
* Since irq_time is only updated on {soft,}irq_exit, we might run into
|
|
* this case when a previous update_rq_clock() happened inside a
|
|
* {soft,}irq region.
|
|
*
|
|
* When this happens, we stop ->clock_task and only update the
|
|
* prev_irq_time stamp to account for the part that fit, so that a next
|
|
* update will consume the rest. This ensures ->clock_task is
|
|
* monotonic.
|
|
*
|
|
* It does however cause some slight miss-attribution of {soft,}irq
|
|
* time, a more accurate solution would be to update the irq_time using
|
|
* the current rq->clock timestamp, except that would require using
|
|
* atomic ops.
|
|
*/
|
|
if (irq_delta > delta)
|
|
irq_delta = delta;
|
|
|
|
rq->prev_irq_time += irq_delta;
|
|
delta -= irq_delta;
|
|
rq->clock_task += delta;
|
|
|
|
if (irq_delta && sched_feat(NONIRQ_POWER))
|
|
sched_rt_avg_update(rq, irq_delta);
|
|
}
|
|
|
|
static int irqtime_account_hi_update(void)
|
|
{
|
|
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
|
|
unsigned long flags;
|
|
u64 latest_ns;
|
|
int ret = 0;
|
|
|
|
local_irq_save(flags);
|
|
latest_ns = this_cpu_read(cpu_hardirq_time);
|
|
if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->irq))
|
|
ret = 1;
|
|
local_irq_restore(flags);
|
|
return ret;
|
|
}
|
|
|
|
static int irqtime_account_si_update(void)
|
|
{
|
|
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
|
|
unsigned long flags;
|
|
u64 latest_ns;
|
|
int ret = 0;
|
|
|
|
local_irq_save(flags);
|
|
latest_ns = this_cpu_read(cpu_softirq_time);
|
|
if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->softirq))
|
|
ret = 1;
|
|
local_irq_restore(flags);
|
|
return ret;
|
|
}
|
|
|
|
#else /* CONFIG_IRQ_TIME_ACCOUNTING */
|
|
|
|
#define sched_clock_irqtime (0)
|
|
|
|
static void update_rq_clock_task(struct rq *rq, s64 delta)
|
|
{
|
|
rq->clock_task += delta;
|
|
}
|
|
|
|
#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
|
|
|
|
#include "sched_idletask.c"
|
|
#include "sched_fair.c"
|
|
#include "sched_rt.c"
|
|
#include "sched_autogroup.c"
|
|
#include "sched_stoptask.c"
|
|
#ifdef CONFIG_SCHED_DEBUG
|
|
# include "sched_debug.c"
|
|
#endif
|
|
|
|
void sched_set_stop_task(int cpu, struct task_struct *stop)
|
|
{
|
|
struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
|
|
struct task_struct *old_stop = cpu_rq(cpu)->stop;
|
|
|
|
if (stop) {
|
|
/*
|
|
* Make it appear like a SCHED_FIFO task, its something
|
|
* userspace knows about and won't get confused about.
|
|
*
|
|
* Also, it will make PI more or less work without too
|
|
* much confusion -- but then, stop work should not
|
|
* rely on PI working anyway.
|
|
*/
|
|
sched_setscheduler_nocheck(stop, SCHED_FIFO, ¶m);
|
|
|
|
stop->sched_class = &stop_sched_class;
|
|
}
|
|
|
|
cpu_rq(cpu)->stop = stop;
|
|
|
|
if (old_stop) {
|
|
/*
|
|
* Reset it back to a normal scheduling class so that
|
|
* it can die in pieces.
|
|
*/
|
|
old_stop->sched_class = &rt_sched_class;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* __normal_prio - return the priority that is based on the static prio
|
|
*/
|
|
static inline int __normal_prio(struct task_struct *p)
|
|
{
|
|
return p->static_prio;
|
|
}
|
|
|
|
/*
|
|
* Calculate the expected normal priority: i.e. priority
|
|
* without taking RT-inheritance into account. Might be
|
|
* boosted by interactivity modifiers. Changes upon fork,
|
|
* setprio syscalls, and whenever the interactivity
|
|
* estimator recalculates.
|
|
*/
|
|
static inline int normal_prio(struct task_struct *p)
|
|
{
|
|
int prio;
|
|
|
|
if (task_has_rt_policy(p))
|
|
prio = MAX_RT_PRIO-1 - p->rt_priority;
|
|
else
|
|
prio = __normal_prio(p);
|
|
return prio;
|
|
}
|
|
|
|
/*
|
|
* Calculate the current priority, i.e. the priority
|
|
* taken into account by the scheduler. This value might
|
|
* be boosted by RT tasks, or might be boosted by
|
|
* interactivity modifiers. Will be RT if the task got
|
|
* RT-boosted. If not then it returns p->normal_prio.
|
|
*/
|
|
static int effective_prio(struct task_struct *p)
|
|
{
|
|
p->normal_prio = normal_prio(p);
|
|
/*
|
|
* If we are RT tasks or we were boosted to RT priority,
|
|
* keep the priority unchanged. Otherwise, update priority
|
|
* to the normal priority:
|
|
*/
|
|
if (!rt_prio(p->prio))
|
|
return p->normal_prio;
|
|
return p->prio;
|
|
}
|
|
|
|
/**
|
|
* task_curr - is this task currently executing on a CPU?
|
|
* @p: the task in question.
|
|
*/
|
|
inline int task_curr(const struct task_struct *p)
|
|
{
|
|
return cpu_curr(task_cpu(p)) == p;
|
|
}
|
|
|
|
static inline void check_class_changed(struct rq *rq, struct task_struct *p,
|
|
const struct sched_class *prev_class,
|
|
int oldprio)
|
|
{
|
|
if (prev_class != p->sched_class) {
|
|
if (prev_class->switched_from)
|
|
prev_class->switched_from(rq, p);
|
|
p->sched_class->switched_to(rq, p);
|
|
} else if (oldprio != p->prio)
|
|
p->sched_class->prio_changed(rq, p, oldprio);
|
|
}
|
|
|
|
static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
|
|
{
|
|
const struct sched_class *class;
|
|
|
|
if (p->sched_class == rq->curr->sched_class) {
|
|
rq->curr->sched_class->check_preempt_curr(rq, p, flags);
|
|
} else {
|
|
for_each_class(class) {
|
|
if (class == rq->curr->sched_class)
|
|
break;
|
|
if (class == p->sched_class) {
|
|
resched_task(rq->curr);
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
|
|
/*
|
|
* A queue event has occurred, and we're going to schedule. In
|
|
* this case, we can save a useless back to back clock update.
|
|
*/
|
|
if (rq->curr->se.on_rq && test_tsk_need_resched(rq->curr))
|
|
rq->skip_clock_update = 1;
|
|
}
|
|
|
|
#ifdef CONFIG_SMP
|
|
/*
|
|
* Is this task likely cache-hot:
|
|
*/
|
|
static int
|
|
task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
|
|
{
|
|
s64 delta;
|
|
|
|
if (p->sched_class != &fair_sched_class)
|
|
return 0;
|
|
|
|
if (unlikely(p->policy == SCHED_IDLE))
|
|
return 0;
|
|
|
|
/*
|
|
* Buddy candidates are cache hot:
|
|
*/
|
|
if (sched_feat(CACHE_HOT_BUDDY) && this_rq()->nr_running &&
|
|
(&p->se == cfs_rq_of(&p->se)->next ||
|
|
&p->se == cfs_rq_of(&p->se)->last))
|
|
return 1;
|
|
|
|
if (sysctl_sched_migration_cost == -1)
|
|
return 1;
|
|
if (sysctl_sched_migration_cost == 0)
|
|
return 0;
|
|
|
|
delta = now - p->se.exec_start;
|
|
|
|
return delta < (s64)sysctl_sched_migration_cost;
|
|
}
|
|
|
|
void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
|
|
{
|
|
#ifdef CONFIG_SCHED_DEBUG
|
|
/*
|
|
* We should never call set_task_cpu() on a blocked task,
|
|
* ttwu() will sort out the placement.
|
|
*/
|
|
WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING &&
|
|
!(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE));
|
|
#endif
|
|
|
|
trace_sched_migrate_task(p, new_cpu);
|
|
|
|
if (task_cpu(p) != new_cpu) {
|
|
p->se.nr_migrations++;
|
|
perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 1, NULL, 0);
|
|
}
|
|
|
|
__set_task_cpu(p, new_cpu);
|
|
}
|
|
|
|
struct migration_arg {
|
|
struct task_struct *task;
|
|
int dest_cpu;
|
|
};
|
|
|
|
static int migration_cpu_stop(void *data);
|
|
|
|
/*
|
|
* The task's runqueue lock must be held.
|
|
* Returns true if you have to wait for migration thread.
|
|
*/
|
|
static bool migrate_task(struct task_struct *p, struct rq *rq)
|
|
{
|
|
/*
|
|
* If the task is not on a runqueue (and not running), then
|
|
* the next wake-up will properly place the task.
|
|
*/
|
|
return p->se.on_rq || task_running(rq, p);
|
|
}
|
|
|
|
/*
|
|
* wait_task_inactive - wait for a thread to unschedule.
|
|
*
|
|
* If @match_state is nonzero, it's the @p->state value just checked and
|
|
* not expected to change. If it changes, i.e. @p might have woken up,
|
|
* then return zero. When we succeed in waiting for @p to be off its CPU,
|
|
* we return a positive number (its total switch count). If a second call
|
|
* a short while later returns the same number, the caller can be sure that
|
|
* @p has remained unscheduled the whole time.
|
|
*
|
|
* The caller must ensure that the task *will* unschedule sometime soon,
|
|
* else this function might spin for a *long* time. This function can't
|
|
* be called with interrupts off, or it may introduce deadlock with
|
|
* smp_call_function() if an IPI is sent by the same process we are
|
|
* waiting to become inactive.
|
|
*/
|
|
unsigned long wait_task_inactive(struct task_struct *p, long match_state)
|
|
{
|
|
unsigned long flags;
|
|
int running, on_rq;
|
|
unsigned long ncsw;
|
|
struct rq *rq;
|
|
|
|
for (;;) {
|
|
/*
|
|
* We do the initial early heuristics without holding
|
|
* any task-queue locks at all. We'll only try to get
|
|
* the runqueue lock when things look like they will
|
|
* work out!
|
|
*/
|
|
rq = task_rq(p);
|
|
|
|
/*
|
|
* If the task is actively running on another CPU
|
|
* still, just relax and busy-wait without holding
|
|
* any locks.
|
|
*
|
|
* NOTE! Since we don't hold any locks, it's not
|
|
* even sure that "rq" stays as the right runqueue!
|
|
* But we don't care, since "task_running()" will
|
|
* return false if the runqueue has changed and p
|
|
* is actually now running somewhere else!
|
|
*/
|
|
while (task_running(rq, p)) {
|
|
if (match_state && unlikely(p->state != match_state))
|
|
return 0;
|
|
cpu_relax();
|
|
}
|
|
|
|
/*
|
|
* Ok, time to look more closely! We need the rq
|
|
* lock now, to be *sure*. If we're wrong, we'll
|
|
* just go back and repeat.
|
|
*/
|
|
rq = task_rq_lock(p, &flags);
|
|
trace_sched_wait_task(p);
|
|
running = task_running(rq, p);
|
|
on_rq = p->se.on_rq;
|
|
ncsw = 0;
|
|
if (!match_state || p->state == match_state)
|
|
ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
|
|
task_rq_unlock(rq, &flags);
|
|
|
|
/*
|
|
* If it changed from the expected state, bail out now.
|
|
*/
|
|
if (unlikely(!ncsw))
|
|
break;
|
|
|
|
/*
|
|
* Was it really running after all now that we
|
|
* checked with the proper locks actually held?
|
|
*
|
|
* Oops. Go back and try again..
|
|
*/
|
|
if (unlikely(running)) {
|
|
cpu_relax();
|
|
continue;
|
|
}
|
|
|
|
/*
|
|
* It's not enough that it's not actively running,
|
|
* it must be off the runqueue _entirely_, and not
|
|
* preempted!
|
|
*
|
|
* So if it was still runnable (but just not actively
|
|
* running right now), it's preempted, and we should
|
|
* yield - it could be a while.
|
|
*/
|
|
if (unlikely(on_rq)) {
|
|
ktime_t to = ktime_set(0, NSEC_PER_SEC/HZ);
|
|
|
|
set_current_state(TASK_UNINTERRUPTIBLE);
|
|
schedule_hrtimeout(&to, HRTIMER_MODE_REL);
|
|
continue;
|
|
}
|
|
|
|
/*
|
|
* Ahh, all good. It wasn't running, and it wasn't
|
|
* runnable, which means that it will never become
|
|
* running in the future either. We're all done!
|
|
*/
|
|
break;
|
|
}
|
|
|
|
return ncsw;
|
|
}
|
|
|
|
/***
|
|
* kick_process - kick a running thread to enter/exit the kernel
|
|
* @p: the to-be-kicked thread
|
|
*
|
|
* Cause a process which is running on another CPU to enter
|
|
* kernel-mode, without any delay. (to get signals handled.)
|
|
*
|
|
* NOTE: this function doesn't have to take the runqueue lock,
|
|
* because all it wants to ensure is that the remote task enters
|
|
* the kernel. If the IPI races and the task has been migrated
|
|
* to another CPU then no harm is done and the purpose has been
|
|
* achieved as well.
|
|
*/
|
|
void kick_process(struct task_struct *p)
|
|
{
|
|
int cpu;
|
|
|
|
preempt_disable();
|
|
cpu = task_cpu(p);
|
|
if ((cpu != smp_processor_id()) && task_curr(p))
|
|
smp_send_reschedule(cpu);
|
|
preempt_enable();
|
|
}
|
|
EXPORT_SYMBOL_GPL(kick_process);
|
|
#endif /* CONFIG_SMP */
|
|
|
|
#ifdef CONFIG_SMP
|
|
/*
|
|
* ->cpus_allowed is protected by either TASK_WAKING or rq->lock held.
|
|
*/
|
|
static int select_fallback_rq(int cpu, struct task_struct *p)
|
|
{
|
|
int dest_cpu;
|
|
const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(cpu));
|
|
|
|
/* Look for allowed, online CPU in same node. */
|
|
for_each_cpu_and(dest_cpu, nodemask, cpu_active_mask)
|
|
if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
|
|
return dest_cpu;
|
|
|
|
/* Any allowed, online CPU? */
|
|
dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_active_mask);
|
|
if (dest_cpu < nr_cpu_ids)
|
|
return dest_cpu;
|
|
|
|
/* No more Mr. Nice Guy. */
|
|
dest_cpu = cpuset_cpus_allowed_fallback(p);
|
|
/*
|
|
* Don't tell them about moving exiting tasks or
|
|
* kernel threads (both mm NULL), since they never
|
|
* leave kernel.
|
|
*/
|
|
if (p->mm && printk_ratelimit()) {
|
|
printk(KERN_INFO "process %d (%s) no longer affine to cpu%d\n",
|
|
task_pid_nr(p), p->comm, cpu);
|
|
}
|
|
|
|
return dest_cpu;
|
|
}
|
|
|
|
/*
|
|
* The caller (fork, wakeup) owns TASK_WAKING, ->cpus_allowed is stable.
|
|
*/
|
|
static inline
|
|
int select_task_rq(struct rq *rq, struct task_struct *p, int sd_flags, int wake_flags)
|
|
{
|
|
int cpu = p->sched_class->select_task_rq(rq, p, sd_flags, wake_flags);
|
|
|
|
/*
|
|
* In order not to call set_task_cpu() on a blocking task we need
|
|
* to rely on ttwu() to place the task on a valid ->cpus_allowed
|
|
* cpu.
|
|
*
|
|
* Since this is common to all placement strategies, this lives here.
|
|
*
|
|
* [ this allows ->select_task() to simply return task_cpu(p) and
|
|
* not worry about this generic constraint ]
|
|
*/
|
|
if (unlikely(!cpumask_test_cpu(cpu, &p->cpus_allowed) ||
|
|
!cpu_online(cpu)))
|
|
cpu = select_fallback_rq(task_cpu(p), p);
|
|
|
|
return cpu;
|
|
}
|
|
|
|
static void update_avg(u64 *avg, u64 sample)
|
|
{
|
|
s64 diff = sample - *avg;
|
|
*avg += diff >> 3;
|
|
}
|
|
#endif
|
|
|
|
static inline void ttwu_activate(struct task_struct *p, struct rq *rq,
|
|
bool is_sync, bool is_migrate, bool is_local,
|
|
unsigned long en_flags)
|
|
{
|
|
schedstat_inc(p, se.statistics.nr_wakeups);
|
|
if (is_sync)
|
|
schedstat_inc(p, se.statistics.nr_wakeups_sync);
|
|
if (is_migrate)
|
|
schedstat_inc(p, se.statistics.nr_wakeups_migrate);
|
|
if (is_local)
|
|
schedstat_inc(p, se.statistics.nr_wakeups_local);
|
|
else
|
|
schedstat_inc(p, se.statistics.nr_wakeups_remote);
|
|
|
|
activate_task(rq, p, en_flags);
|
|
}
|
|
|
|
static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq,
|
|
int wake_flags, bool success)
|
|
{
|
|
trace_sched_wakeup(p, success);
|
|
check_preempt_curr(rq, p, wake_flags);
|
|
|
|
p->state = TASK_RUNNING;
|
|
#ifdef CONFIG_SMP
|
|
if (p->sched_class->task_woken)
|
|
p->sched_class->task_woken(rq, p);
|
|
|
|
if (unlikely(rq->idle_stamp)) {
|
|
u64 delta = rq->clock - rq->idle_stamp;
|
|
u64 max = 2*sysctl_sched_migration_cost;
|
|
|
|
if (delta > max)
|
|
rq->avg_idle = max;
|
|
else
|
|
update_avg(&rq->avg_idle, delta);
|
|
rq->idle_stamp = 0;
|
|
}
|
|
#endif
|
|
/* if a worker is waking up, notify workqueue */
|
|
if ((p->flags & PF_WQ_WORKER) && success)
|
|
wq_worker_waking_up(p, cpu_of(rq));
|
|
}
|
|
|
|
/**
|
|
* try_to_wake_up - wake up a thread
|
|
* @p: the thread to be awakened
|
|
* @state: the mask of task states that can be woken
|
|
* @wake_flags: wake modifier flags (WF_*)
|
|
*
|
|
* Put it on the run-queue if it's not already there. The "current"
|
|
* thread is always on the run-queue (except when the actual
|
|
* re-schedule is in progress), and as such you're allowed to do
|
|
* the simpler "current->state = TASK_RUNNING" to mark yourself
|
|
* runnable without the overhead of this.
|
|
*
|
|
* Returns %true if @p was woken up, %false if it was already running
|
|
* or @state didn't match @p's state.
|
|
*/
|
|
static int try_to_wake_up(struct task_struct *p, unsigned int state,
|
|
int wake_flags)
|
|
{
|
|
int cpu, orig_cpu, this_cpu, success = 0;
|
|
unsigned long flags;
|
|
unsigned long en_flags = ENQUEUE_WAKEUP;
|
|
struct rq *rq;
|
|
|
|
this_cpu = get_cpu();
|
|
|
|
smp_wmb();
|
|
rq = task_rq_lock(p, &flags);
|
|
if (!(p->state & state))
|
|
goto out;
|
|
|
|
if (p->se.on_rq)
|
|
goto out_running;
|
|
|
|
cpu = task_cpu(p);
|
|
orig_cpu = cpu;
|
|
|
|
#ifdef CONFIG_SMP
|
|
if (unlikely(task_running(rq, p)))
|
|
goto out_activate;
|
|
|
|
/*
|
|
* In order to handle concurrent wakeups and release the rq->lock
|
|
* we put the task in TASK_WAKING state.
|
|
*
|
|
* First fix up the nr_uninterruptible count:
|
|
*/
|
|
if (task_contributes_to_load(p)) {
|
|
if (likely(cpu_online(orig_cpu)))
|
|
rq->nr_uninterruptible--;
|
|
else
|
|
this_rq()->nr_uninterruptible--;
|
|
}
|
|
p->state = TASK_WAKING;
|
|
|
|
if (p->sched_class->task_waking) {
|
|
p->sched_class->task_waking(rq, p);
|
|
en_flags |= ENQUEUE_WAKING;
|
|
}
|
|
|
|
cpu = select_task_rq(rq, p, SD_BALANCE_WAKE, wake_flags);
|
|
if (cpu != orig_cpu)
|
|
set_task_cpu(p, cpu);
|
|
__task_rq_unlock(rq);
|
|
|
|
rq = cpu_rq(cpu);
|
|
raw_spin_lock(&rq->lock);
|
|
|
|
/*
|
|
* We migrated the task without holding either rq->lock, however
|
|
* since the task is not on the task list itself, nobody else
|
|
* will try and migrate the task, hence the rq should match the
|
|
* cpu we just moved it to.
|
|
*/
|
|
WARN_ON(task_cpu(p) != cpu);
|
|
WARN_ON(p->state != TASK_WAKING);
|
|
|
|
#ifdef CONFIG_SCHEDSTATS
|
|
schedstat_inc(rq, ttwu_count);
|
|
if (cpu == this_cpu)
|
|
schedstat_inc(rq, ttwu_local);
|
|
else {
|
|
struct sched_domain *sd;
|
|
for_each_domain(this_cpu, sd) {
|
|
if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
|
|
schedstat_inc(sd, ttwu_wake_remote);
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
#endif /* CONFIG_SCHEDSTATS */
|
|
|
|
out_activate:
|
|
#endif /* CONFIG_SMP */
|
|
ttwu_activate(p, rq, wake_flags & WF_SYNC, orig_cpu != cpu,
|
|
cpu == this_cpu, en_flags);
|
|
success = 1;
|
|
out_running:
|
|
ttwu_post_activation(p, rq, wake_flags, success);
|
|
out:
|
|
task_rq_unlock(rq, &flags);
|
|
put_cpu();
|
|
|
|
return success;
|
|
}
|
|
|
|
/**
|
|
* try_to_wake_up_local - try to wake up a local task with rq lock held
|
|
* @p: the thread to be awakened
|
|
*
|
|
* Put @p on the run-queue if it's not already there. The caller must
|
|
* ensure that this_rq() is locked, @p is bound to this_rq() and not
|
|
* the current task. this_rq() stays locked over invocation.
|
|
*/
|
|
static void try_to_wake_up_local(struct task_struct *p)
|
|
{
|
|
struct rq *rq = task_rq(p);
|
|
bool success = false;
|
|
|
|
BUG_ON(rq != this_rq());
|
|
BUG_ON(p == current);
|
|
lockdep_assert_held(&rq->lock);
|
|
|
|
if (!(p->state & TASK_NORMAL))
|
|
return;
|
|
|
|
if (!p->se.on_rq) {
|
|
if (likely(!task_running(rq, p))) {
|
|
schedstat_inc(rq, ttwu_count);
|
|
schedstat_inc(rq, ttwu_local);
|
|
}
|
|
ttwu_activate(p, rq, false, false, true, ENQUEUE_WAKEUP);
|
|
success = true;
|
|
}
|
|
ttwu_post_activation(p, rq, 0, success);
|
|
}
|
|
|
|
/**
|
|
* wake_up_process - Wake up a specific process
|
|
* @p: The process to be woken up.
|
|
*
|
|
* Attempt to wake up the nominated process and move it to the set of runnable
|
|
* processes. Returns 1 if the process was woken up, 0 if it was already
|
|
* running.
|
|
*
|
|
* It may be assumed that this function implies a write memory barrier before
|
|
* changing the task state if and only if any tasks are woken up.
|
|
*/
|
|
int wake_up_process(struct task_struct *p)
|
|
{
|
|
return try_to_wake_up(p, TASK_ALL, 0);
|
|
}
|
|
EXPORT_SYMBOL(wake_up_process);
|
|
|
|
int wake_up_state(struct task_struct *p, unsigned int state)
|
|
{
|
|
return try_to_wake_up(p, state, 0);
|
|
}
|
|
|
|
/*
|
|
* Perform scheduler related setup for a newly forked process p.
|
|
* p is forked by current.
|
|
*
|
|
* __sched_fork() is basic setup used by init_idle() too:
|
|
*/
|
|
static void __sched_fork(struct task_struct *p)
|
|
{
|
|
p->se.exec_start = 0;
|
|
p->se.sum_exec_runtime = 0;
|
|
p->se.prev_sum_exec_runtime = 0;
|
|
p->se.nr_migrations = 0;
|
|
p->se.vruntime = 0;
|
|
|
|
#ifdef CONFIG_SCHEDSTATS
|
|
memset(&p->se.statistics, 0, sizeof(p->se.statistics));
|
|
#endif
|
|
|
|
INIT_LIST_HEAD(&p->rt.run_list);
|
|
p->se.on_rq = 0;
|
|
INIT_LIST_HEAD(&p->se.group_node);
|
|
|
|
#ifdef CONFIG_PREEMPT_NOTIFIERS
|
|
INIT_HLIST_HEAD(&p->preempt_notifiers);
|
|
#endif
|
|
}
|
|
|
|
/*
|
|
* fork()/clone()-time setup:
|
|
*/
|
|
void sched_fork(struct task_struct *p, int clone_flags)
|
|
{
|
|
int cpu = get_cpu();
|
|
|
|
__sched_fork(p);
|
|
/*
|
|
* We mark the process as running here. This guarantees that
|
|
* nobody will actually run it, and a signal or other external
|
|
* event cannot wake it up and insert it on the runqueue either.
|
|
*/
|
|
p->state = TASK_RUNNING;
|
|
|
|
/*
|
|
* Revert to default priority/policy on fork if requested.
|
|
*/
|
|
if (unlikely(p->sched_reset_on_fork)) {
|
|
if (p->policy == SCHED_FIFO || p->policy == SCHED_RR) {
|
|
p->policy = SCHED_NORMAL;
|
|
p->normal_prio = p->static_prio;
|
|
}
|
|
|
|
if (PRIO_TO_NICE(p->static_prio) < 0) {
|
|
p->static_prio = NICE_TO_PRIO(0);
|
|
p->normal_prio = p->static_prio;
|
|
set_load_weight(p);
|
|
}
|
|
|
|
/*
|
|
* We don't need the reset flag anymore after the fork. It has
|
|
* fulfilled its duty:
|
|
*/
|
|
p->sched_reset_on_fork = 0;
|
|
}
|
|
|
|
/*
|
|
* Make sure we do not leak PI boosting priority to the child.
|
|
*/
|
|
p->prio = current->normal_prio;
|
|
|
|
if (!rt_prio(p->prio))
|
|
p->sched_class = &fair_sched_class;
|
|
|
|
if (p->sched_class->task_fork)
|
|
p->sched_class->task_fork(p);
|
|
|
|
/*
|
|
* The child is not yet in the pid-hash so no cgroup attach races,
|
|
* and the cgroup is pinned to this child due to cgroup_fork()
|
|
* is ran before sched_fork().
|
|
*
|
|
* Silence PROVE_RCU.
|
|
*/
|
|
rcu_read_lock();
|
|
set_task_cpu(p, cpu);
|
|
rcu_read_unlock();
|
|
|
|
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
|
|
if (likely(sched_info_on()))
|
|
memset(&p->sched_info, 0, sizeof(p->sched_info));
|
|
#endif
|
|
#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
|
|
p->oncpu = 0;
|
|
#endif
|
|
#ifdef CONFIG_PREEMPT
|
|
/* Want to start with kernel preemption disabled. */
|
|
task_thread_info(p)->preempt_count = 1;
|
|
#endif
|
|
#ifdef CONFIG_SMP
|
|
plist_node_init(&p->pushable_tasks, MAX_PRIO);
|
|
#endif
|
|
|
|
put_cpu();
|
|
}
|
|
|
|
/*
|
|
* wake_up_new_task - wake up a newly created task for the first time.
|
|
*
|
|
* This function will do some initial scheduler statistics housekeeping
|
|
* that must be done for every newly created context, then puts the task
|
|
* on the runqueue and wakes it.
|
|
*/
|
|
void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
|
|
{
|
|
unsigned long flags;
|
|
struct rq *rq;
|
|
int cpu __maybe_unused = get_cpu();
|
|
|
|
#ifdef CONFIG_SMP
|
|
rq = task_rq_lock(p, &flags);
|
|
p->state = TASK_WAKING;
|
|
|
|
/*
|
|
* Fork balancing, do it here and not earlier because:
|
|
* - cpus_allowed can change in the fork path
|
|
* - any previously selected cpu might disappear through hotplug
|
|
*
|
|
* We set TASK_WAKING so that select_task_rq() can drop rq->lock
|
|
* without people poking at ->cpus_allowed.
|
|
*/
|
|
cpu = select_task_rq(rq, p, SD_BALANCE_FORK, 0);
|
|
set_task_cpu(p, cpu);
|
|
|
|
p->state = TASK_RUNNING;
|
|
task_rq_unlock(rq, &flags);
|
|
#endif
|
|
|
|
rq = task_rq_lock(p, &flags);
|
|
activate_task(rq, p, 0);
|
|
trace_sched_wakeup_new(p, 1);
|
|
check_preempt_curr(rq, p, WF_FORK);
|
|
#ifdef CONFIG_SMP
|
|
if (p->sched_class->task_woken)
|
|
p->sched_class->task_woken(rq, p);
|
|
#endif
|
|
task_rq_unlock(rq, &flags);
|
|
put_cpu();
|
|
}
|
|
|
|
#ifdef CONFIG_PREEMPT_NOTIFIERS
|
|
|
|
/**
|
|
* preempt_notifier_register - tell me when current is being preempted & rescheduled
|
|
* @notifier: notifier struct to register
|
|
*/
|
|
void preempt_notifier_register(struct preempt_notifier *notifier)
|
|
{
|
|
hlist_add_head(¬ifier->link, ¤t->preempt_notifiers);
|
|
}
|
|
EXPORT_SYMBOL_GPL(preempt_notifier_register);
|
|
|
|
/**
|
|
* preempt_notifier_unregister - no longer interested in preemption notifications
|
|
* @notifier: notifier struct to unregister
|
|
*
|
|
* This is safe to call from within a preemption notifier.
|
|
*/
|
|
void preempt_notifier_unregister(struct preempt_notifier *notifier)
|
|
{
|
|
hlist_del(¬ifier->link);
|
|
}
|
|
EXPORT_SYMBOL_GPL(preempt_notifier_unregister);
|
|
|
|
static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
|
|
{
|
|
struct preempt_notifier *notifier;
|
|
struct hlist_node *node;
|
|
|
|
hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)
|
|
notifier->ops->sched_in(notifier, raw_smp_processor_id());
|
|
}
|
|
|
|
static void
|
|
fire_sched_out_preempt_notifiers(struct task_struct *curr,
|
|
struct task_struct *next)
|
|
{
|
|
struct preempt_notifier *notifier;
|
|
struct hlist_node *node;
|
|
|
|
hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)
|
|
notifier->ops->sched_out(notifier, next);
|
|
}
|
|
|
|
#else /* !CONFIG_PREEMPT_NOTIFIERS */
|
|
|
|
static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
|
|
{
|
|
}
|
|
|
|
static void
|
|
fire_sched_out_preempt_notifiers(struct task_struct *curr,
|
|
struct task_struct *next)
|
|
{
|
|
}
|
|
|
|
#endif /* CONFIG_PREEMPT_NOTIFIERS */
|
|
|
|
/**
|
|
* prepare_task_switch - prepare to switch tasks
|
|
* @rq: the runqueue preparing to switch
|
|
* @prev: the current task that is being switched out
|
|
* @next: the task we are going to switch to.
|
|
*
|
|
* This is called with the rq lock held and interrupts off. It must
|
|
* be paired with a subsequent finish_task_switch after the context
|
|
* switch.
|
|
*
|
|
* prepare_task_switch sets up locking and calls architecture specific
|
|
* hooks.
|
|
*/
|
|
static inline void
|
|
prepare_task_switch(struct rq *rq, struct task_struct *prev,
|
|
struct task_struct *next)
|
|
{
|
|
sched_info_switch(prev, next);
|
|
perf_event_task_sched_out(prev, next);
|
|
fire_sched_out_preempt_notifiers(prev, next);
|
|
prepare_lock_switch(rq, next);
|
|
prepare_arch_switch(next);
|
|
trace_sched_switch(prev, next);
|
|
}
|
|
|
|
/**
|
|
* finish_task_switch - clean up after a task-switch
|
|
* @rq: runqueue associated with task-switch
|
|
* @prev: the thread we just switched away from.
|
|
*
|
|
* finish_task_switch must be called after the context switch, paired
|
|
* with a prepare_task_switch call before the context switch.
|
|
* finish_task_switch will reconcile locking set up by prepare_task_switch,
|
|
* and do any other architecture-specific cleanup actions.
|
|
*
|
|
* Note that we may have delayed dropping an mm in context_switch(). If
|
|
* so, we finish that here outside of the runqueue lock. (Doing it
|
|
* with the lock held can cause deadlocks; see schedule() for
|
|
* details.)
|
|
*/
|
|
static void finish_task_switch(struct rq *rq, struct task_struct *prev)
|
|
__releases(rq->lock)
|
|
{
|
|
struct mm_struct *mm = rq->prev_mm;
|
|
long prev_state;
|
|
|
|
rq->prev_mm = NULL;
|
|
|
|
/*
|
|
* A task struct has one reference for the use as "current".
|
|
* If a task dies, then it sets TASK_DEAD in tsk->state and calls
|
|
* schedule one last time. The schedule call will never return, and
|
|
* the scheduled task must drop that reference.
|
|
* The test for TASK_DEAD must occur while the runqueue locks are
|
|
* still held, otherwise prev could be scheduled on another cpu, die
|
|
* there before we look at prev->state, and then the reference would
|
|
* be dropped twice.
|
|
* Manfred Spraul <manfred@colorfullife.com>
|
|
*/
|
|
prev_state = prev->state;
|
|
finish_arch_switch(prev);
|
|
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
|
|
local_irq_disable();
|
|
#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
|
|
perf_event_task_sched_in(current);
|
|
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
|
|
local_irq_enable();
|
|
#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
|
|
finish_lock_switch(rq, prev);
|
|
|
|
fire_sched_in_preempt_notifiers(current);
|
|
if (mm)
|
|
mmdrop(mm);
|
|
if (unlikely(prev_state == TASK_DEAD)) {
|
|
/*
|
|
* Remove function-return probe instances associated with this
|
|
* task and put them back on the free list.
|
|
*/
|
|
kprobe_flush_task(prev);
|
|
put_task_struct(prev);
|
|
}
|
|
}
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
/* assumes rq->lock is held */
|
|
static inline void pre_schedule(struct rq *rq, struct task_struct *prev)
|
|
{
|
|
if (prev->sched_class->pre_schedule)
|
|
prev->sched_class->pre_schedule(rq, prev);
|
|
}
|
|
|
|
/* rq->lock is NOT held, but preemption is disabled */
|
|
static inline void post_schedule(struct rq *rq)
|
|
{
|
|
if (rq->post_schedule) {
|
|
unsigned long flags;
|
|
|
|
raw_spin_lock_irqsave(&rq->lock, flags);
|
|
if (rq->curr->sched_class->post_schedule)
|
|
rq->curr->sched_class->post_schedule(rq);
|
|
raw_spin_unlock_irqrestore(&rq->lock, flags);
|
|
|
|
rq->post_schedule = 0;
|
|
}
|
|
}
|
|
|
|
#else
|
|
|
|
static inline void pre_schedule(struct rq *rq, struct task_struct *p)
|
|
{
|
|
}
|
|
|
|
static inline void post_schedule(struct rq *rq)
|
|
{
|
|
}
|
|
|
|
#endif
|
|
|
|
/**
|
|
* schedule_tail - first thing a freshly forked thread must call.
|
|
* @prev: the thread we just switched away from.
|
|
*/
|
|
asmlinkage void schedule_tail(struct task_struct *prev)
|
|
__releases(rq->lock)
|
|
{
|
|
struct rq *rq = this_rq();
|
|
|
|
finish_task_switch(rq, prev);
|
|
|
|
/*
|
|
* FIXME: do we need to worry about rq being invalidated by the
|
|
* task_switch?
|
|
*/
|
|
post_schedule(rq);
|
|
|
|
#ifdef __ARCH_WANT_UNLOCKED_CTXSW
|
|
/* In this case, finish_task_switch does not reenable preemption */
|
|
preempt_enable();
|
|
#endif
|
|
if (current->set_child_tid)
|
|
put_user(task_pid_vnr(current), current->set_child_tid);
|
|
}
|
|
|
|
/*
|
|
* context_switch - switch to the new MM and the new
|
|
* thread's register state.
|
|
*/
|
|
static inline void
|
|
context_switch(struct rq *rq, struct task_struct *prev,
|
|
struct task_struct *next)
|
|
{
|
|
struct mm_struct *mm, *oldmm;
|
|
|
|
prepare_task_switch(rq, prev, next);
|
|
|
|
mm = next->mm;
|
|
oldmm = prev->active_mm;
|
|
/*
|
|
* For paravirt, this is coupled with an exit in switch_to to
|
|
* combine the page table reload and the switch backend into
|
|
* one hypercall.
|
|
*/
|
|
arch_start_context_switch(prev);
|
|
|
|
if (!mm) {
|
|
next->active_mm = oldmm;
|
|
atomic_inc(&oldmm->mm_count);
|
|
enter_lazy_tlb(oldmm, next);
|
|
} else
|
|
switch_mm(oldmm, mm, next);
|
|
|
|
if (!prev->mm) {
|
|
prev->active_mm = NULL;
|
|
rq->prev_mm = oldmm;
|
|
}
|
|
/*
|
|
* Since the runqueue lock will be released by the next
|
|
* task (which is an invalid locking op but in the case
|
|
* of the scheduler it's an obvious special-case), so we
|
|
* do an early lockdep release here:
|
|
*/
|
|
#ifndef __ARCH_WANT_UNLOCKED_CTXSW
|
|
spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
|
|
#endif
|
|
|
|
/* Here we just switch the register state and the stack. */
|
|
switch_to(prev, next, prev);
|
|
|
|
barrier();
|
|
/*
|
|
* this_rq must be evaluated again because prev may have moved
|
|
* CPUs since it called schedule(), thus the 'rq' on its stack
|
|
* frame will be invalid.
|
|
*/
|
|
finish_task_switch(this_rq(), prev);
|
|
}
|
|
|
|
/*
|
|
* nr_running, nr_uninterruptible and nr_context_switches:
|
|
*
|
|
* externally visible scheduler statistics: current number of runnable
|
|
* threads, current number of uninterruptible-sleeping threads, total
|
|
* number of context switches performed since bootup.
|
|
*/
|
|
unsigned long nr_running(void)
|
|
{
|
|
unsigned long i, sum = 0;
|
|
|
|
for_each_online_cpu(i)
|
|
sum += cpu_rq(i)->nr_running;
|
|
|
|
return sum;
|
|
}
|
|
|
|
unsigned long nr_uninterruptible(void)
|
|
{
|
|
unsigned long i, sum = 0;
|
|
|
|
for_each_possible_cpu(i)
|
|
sum += cpu_rq(i)->nr_uninterruptible;
|
|
|
|
/*
|
|
* Since we read the counters lockless, it might be slightly
|
|
* inaccurate. Do not allow it to go below zero though:
|
|
*/
|
|
if (unlikely((long)sum < 0))
|
|
sum = 0;
|
|
|
|
return sum;
|
|
}
|
|
|
|
unsigned long long nr_context_switches(void)
|
|
{
|
|
int i;
|
|
unsigned long long sum = 0;
|
|
|
|
for_each_possible_cpu(i)
|
|
sum += cpu_rq(i)->nr_switches;
|
|
|
|
return sum;
|
|
}
|
|
|
|
unsigned long nr_iowait(void)
|
|
{
|
|
unsigned long i, sum = 0;
|
|
|
|
for_each_possible_cpu(i)
|
|
sum += atomic_read(&cpu_rq(i)->nr_iowait);
|
|
|
|
return sum;
|
|
}
|
|
|
|
unsigned long nr_iowait_cpu(int cpu)
|
|
{
|
|
struct rq *this = cpu_rq(cpu);
|
|
return atomic_read(&this->nr_iowait);
|
|
}
|
|
|
|
unsigned long this_cpu_load(void)
|
|
{
|
|
struct rq *this = this_rq();
|
|
return this->cpu_load[0];
|
|
}
|
|
|
|
|
|
/* Variables and functions for calc_load */
|
|
static atomic_long_t calc_load_tasks;
|
|
static unsigned long calc_load_update;
|
|
unsigned long avenrun[3];
|
|
EXPORT_SYMBOL(avenrun);
|
|
|
|
static long calc_load_fold_active(struct rq *this_rq)
|
|
{
|
|
long nr_active, delta = 0;
|
|
|
|
nr_active = this_rq->nr_running;
|
|
nr_active += (long) this_rq->nr_uninterruptible;
|
|
|
|
if (nr_active != this_rq->calc_load_active) {
|
|
delta = nr_active - this_rq->calc_load_active;
|
|
this_rq->calc_load_active = nr_active;
|
|
}
|
|
|
|
return delta;
|
|
}
|
|
|
|
static unsigned long
|
|
calc_load(unsigned long load, unsigned long exp, unsigned long active)
|
|
{
|
|
load *= exp;
|
|
load += active * (FIXED_1 - exp);
|
|
load += 1UL << (FSHIFT - 1);
|
|
return load >> FSHIFT;
|
|
}
|
|
|
|
#ifdef CONFIG_NO_HZ
|
|
/*
|
|
* For NO_HZ we delay the active fold to the next LOAD_FREQ update.
|
|
*
|
|
* When making the ILB scale, we should try to pull this in as well.
|
|
*/
|
|
static atomic_long_t calc_load_tasks_idle;
|
|
|
|
static void calc_load_account_idle(struct rq *this_rq)
|
|
{
|
|
long delta;
|
|
|
|
delta = calc_load_fold_active(this_rq);
|
|
if (delta)
|
|
atomic_long_add(delta, &calc_load_tasks_idle);
|
|
}
|
|
|
|
static long calc_load_fold_idle(void)
|
|
{
|
|
long delta = 0;
|
|
|
|
/*
|
|
* Its got a race, we don't care...
|
|
*/
|
|
if (atomic_long_read(&calc_load_tasks_idle))
|
|
delta = atomic_long_xchg(&calc_load_tasks_idle, 0);
|
|
|
|
return delta;
|
|
}
|
|
|
|
/**
|
|
* fixed_power_int - compute: x^n, in O(log n) time
|
|
*
|
|
* @x: base of the power
|
|
* @frac_bits: fractional bits of @x
|
|
* @n: power to raise @x to.
|
|
*
|
|
* By exploiting the relation between the definition of the natural power
|
|
* function: x^n := x*x*...*x (x multiplied by itself for n times), and
|
|
* the binary encoding of numbers used by computers: n := \Sum n_i * 2^i,
|
|
* (where: n_i \elem {0, 1}, the binary vector representing n),
|
|
* we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is
|
|
* of course trivially computable in O(log_2 n), the length of our binary
|
|
* vector.
|
|
*/
|
|
static unsigned long
|
|
fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n)
|
|
{
|
|
unsigned long result = 1UL << frac_bits;
|
|
|
|
if (n) for (;;) {
|
|
if (n & 1) {
|
|
result *= x;
|
|
result += 1UL << (frac_bits - 1);
|
|
result >>= frac_bits;
|
|
}
|
|
n >>= 1;
|
|
if (!n)
|
|
break;
|
|
x *= x;
|
|
x += 1UL << (frac_bits - 1);
|
|
x >>= frac_bits;
|
|
}
|
|
|
|
return result;
|
|
}
|
|
|
|
/*
|
|
* a1 = a0 * e + a * (1 - e)
|
|
*
|
|
* a2 = a1 * e + a * (1 - e)
|
|
* = (a0 * e + a * (1 - e)) * e + a * (1 - e)
|
|
* = a0 * e^2 + a * (1 - e) * (1 + e)
|
|
*
|
|
* a3 = a2 * e + a * (1 - e)
|
|
* = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e)
|
|
* = a0 * e^3 + a * (1 - e) * (1 + e + e^2)
|
|
*
|
|
* ...
|
|
*
|
|
* an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1]
|
|
* = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e)
|
|
* = a0 * e^n + a * (1 - e^n)
|
|
*
|
|
* [1] application of the geometric series:
|
|
*
|
|
* n 1 - x^(n+1)
|
|
* S_n := \Sum x^i = -------------
|
|
* i=0 1 - x
|
|
*/
|
|
static unsigned long
|
|
calc_load_n(unsigned long load, unsigned long exp,
|
|
unsigned long active, unsigned int n)
|
|
{
|
|
|
|
return calc_load(load, fixed_power_int(exp, FSHIFT, n), active);
|
|
}
|
|
|
|
/*
|
|
* NO_HZ can leave us missing all per-cpu ticks calling
|
|
* calc_load_account_active(), but since an idle CPU folds its delta into
|
|
* calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold
|
|
* in the pending idle delta if our idle period crossed a load cycle boundary.
|
|
*
|
|
* Once we've updated the global active value, we need to apply the exponential
|
|
* weights adjusted to the number of cycles missed.
|
|
*/
|
|
static void calc_global_nohz(unsigned long ticks)
|
|
{
|
|
long delta, active, n;
|
|
|
|
if (time_before(jiffies, calc_load_update))
|
|
return;
|
|
|
|
/*
|
|
* If we crossed a calc_load_update boundary, make sure to fold
|
|
* any pending idle changes, the respective CPUs might have
|
|
* missed the tick driven calc_load_account_active() update
|
|
* due to NO_HZ.
|
|
*/
|
|
delta = calc_load_fold_idle();
|
|
if (delta)
|
|
atomic_long_add(delta, &calc_load_tasks);
|
|
|
|
/*
|
|
* If we were idle for multiple load cycles, apply them.
|
|
*/
|
|
if (ticks >= LOAD_FREQ) {
|
|
n = ticks / LOAD_FREQ;
|
|
|
|
active = atomic_long_read(&calc_load_tasks);
|
|
active = active > 0 ? active * FIXED_1 : 0;
|
|
|
|
avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n);
|
|
avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
|
|
avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
|
|
|
|
calc_load_update += n * LOAD_FREQ;
|
|
}
|
|
|
|
/*
|
|
* Its possible the remainder of the above division also crosses
|
|
* a LOAD_FREQ period, the regular check in calc_global_load()
|
|
* which comes after this will take care of that.
|
|
*
|
|
* Consider us being 11 ticks before a cycle completion, and us
|
|
* sleeping for 4*LOAD_FREQ + 22 ticks, then the above code will
|
|
* age us 4 cycles, and the test in calc_global_load() will
|
|
* pick up the final one.
|
|
*/
|
|
}
|
|
#else
|
|
static void calc_load_account_idle(struct rq *this_rq)
|
|
{
|
|
}
|
|
|
|
static inline long calc_load_fold_idle(void)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static void calc_global_nohz(unsigned long ticks)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
/**
|
|
* get_avenrun - get the load average array
|
|
* @loads: pointer to dest load array
|
|
* @offset: offset to add
|
|
* @shift: shift count to shift the result left
|
|
*
|
|
* These values are estimates at best, so no need for locking.
|
|
*/
|
|
void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
|
|
{
|
|
loads[0] = (avenrun[0] + offset) << shift;
|
|
loads[1] = (avenrun[1] + offset) << shift;
|
|
loads[2] = (avenrun[2] + offset) << shift;
|
|
}
|
|
|
|
/*
|
|
* calc_load - update the avenrun load estimates 10 ticks after the
|
|
* CPUs have updated calc_load_tasks.
|
|
*/
|
|
void calc_global_load(unsigned long ticks)
|
|
{
|
|
long active;
|
|
|
|
calc_global_nohz(ticks);
|
|
|
|
if (time_before(jiffies, calc_load_update + 10))
|
|
return;
|
|
|
|
active = atomic_long_read(&calc_load_tasks);
|
|
active = active > 0 ? active * FIXED_1 : 0;
|
|
|
|
avenrun[0] = calc_load(avenrun[0], EXP_1, active);
|
|
avenrun[1] = calc_load(avenrun[1], EXP_5, active);
|
|
avenrun[2] = calc_load(avenrun[2], EXP_15, active);
|
|
|
|
calc_load_update += LOAD_FREQ;
|
|
}
|
|
|
|
/*
|
|
* Called from update_cpu_load() to periodically update this CPU's
|
|
* active count.
|
|
*/
|
|
static void calc_load_account_active(struct rq *this_rq)
|
|
{
|
|
long delta;
|
|
|
|
if (time_before(jiffies, this_rq->calc_load_update))
|
|
return;
|
|
|
|
delta = calc_load_fold_active(this_rq);
|
|
delta += calc_load_fold_idle();
|
|
if (delta)
|
|
atomic_long_add(delta, &calc_load_tasks);
|
|
|
|
this_rq->calc_load_update += LOAD_FREQ;
|
|
}
|
|
|
|
/*
|
|
* The exact cpuload at various idx values, calculated at every tick would be
|
|
* load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load
|
|
*
|
|
* If a cpu misses updates for n-1 ticks (as it was idle) and update gets called
|
|
* on nth tick when cpu may be busy, then we have:
|
|
* load = ((2^idx - 1) / 2^idx)^(n-1) * load
|
|
* load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load
|
|
*
|
|
* decay_load_missed() below does efficient calculation of
|
|
* load = ((2^idx - 1) / 2^idx)^(n-1) * load
|
|
* avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load
|
|
*
|
|
* The calculation is approximated on a 128 point scale.
|
|
* degrade_zero_ticks is the number of ticks after which load at any
|
|
* particular idx is approximated to be zero.
|
|
* degrade_factor is a precomputed table, a row for each load idx.
|
|
* Each column corresponds to degradation factor for a power of two ticks,
|
|
* based on 128 point scale.
|
|
* Example:
|
|
* row 2, col 3 (=12) says that the degradation at load idx 2 after
|
|
* 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8).
|
|
*
|
|
* With this power of 2 load factors, we can degrade the load n times
|
|
* by looking at 1 bits in n and doing as many mult/shift instead of
|
|
* n mult/shifts needed by the exact degradation.
|
|
*/
|
|
#define DEGRADE_SHIFT 7
|
|
static const unsigned char
|
|
degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128};
|
|
static const unsigned char
|
|
degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = {
|
|
{0, 0, 0, 0, 0, 0, 0, 0},
|
|
{64, 32, 8, 0, 0, 0, 0, 0},
|
|
{96, 72, 40, 12, 1, 0, 0},
|
|
{112, 98, 75, 43, 15, 1, 0},
|
|
{120, 112, 98, 76, 45, 16, 2} };
|
|
|
|
/*
|
|
* Update cpu_load for any missed ticks, due to tickless idle. The backlog
|
|
* would be when CPU is idle and so we just decay the old load without
|
|
* adding any new load.
|
|
*/
|
|
static unsigned long
|
|
decay_load_missed(unsigned long load, unsigned long missed_updates, int idx)
|
|
{
|
|
int j = 0;
|
|
|
|
if (!missed_updates)
|
|
return load;
|
|
|
|
if (missed_updates >= degrade_zero_ticks[idx])
|
|
return 0;
|
|
|
|
if (idx == 1)
|
|
return load >> missed_updates;
|
|
|
|
while (missed_updates) {
|
|
if (missed_updates % 2)
|
|
load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT;
|
|
|
|
missed_updates >>= 1;
|
|
j++;
|
|
}
|
|
return load;
|
|
}
|
|
|
|
/*
|
|
* Update rq->cpu_load[] statistics. This function is usually called every
|
|
* scheduler tick (TICK_NSEC). With tickless idle this will not be called
|
|
* every tick. We fix it up based on jiffies.
|
|
*/
|
|
static void update_cpu_load(struct rq *this_rq)
|
|
{
|
|
unsigned long this_load = this_rq->load.weight;
|
|
unsigned long curr_jiffies = jiffies;
|
|
unsigned long pending_updates;
|
|
int i, scale;
|
|
|
|
this_rq->nr_load_updates++;
|
|
|
|
/* Avoid repeated calls on same jiffy, when moving in and out of idle */
|
|
if (curr_jiffies == this_rq->last_load_update_tick)
|
|
return;
|
|
|
|
pending_updates = curr_jiffies - this_rq->last_load_update_tick;
|
|
this_rq->last_load_update_tick = curr_jiffies;
|
|
|
|
/* Update our load: */
|
|
this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */
|
|
for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) {
|
|
unsigned long old_load, new_load;
|
|
|
|
/* scale is effectively 1 << i now, and >> i divides by scale */
|
|
|
|
old_load = this_rq->cpu_load[i];
|
|
old_load = decay_load_missed(old_load, pending_updates - 1, i);
|
|
new_load = this_load;
|
|
/*
|
|
* Round up the averaging division if load is increasing. This
|
|
* prevents us from getting stuck on 9 if the load is 10, for
|
|
* example.
|
|
*/
|
|
if (new_load > old_load)
|
|
new_load += scale - 1;
|
|
|
|
this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i;
|
|
}
|
|
|
|
sched_avg_update(this_rq);
|
|
}
|
|
|
|
static void update_cpu_load_active(struct rq *this_rq)
|
|
{
|
|
update_cpu_load(this_rq);
|
|
|
|
calc_load_account_active(this_rq);
|
|
}
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
/*
|
|
* sched_exec - execve() is a valuable balancing opportunity, because at
|
|
* this point the task has the smallest effective memory and cache footprint.
|
|
*/
|
|
void sched_exec(void)
|
|
{
|
|
struct task_struct *p = current;
|
|
unsigned long flags;
|
|
struct rq *rq;
|
|
int dest_cpu;
|
|
|
|
rq = task_rq_lock(p, &flags);
|
|
dest_cpu = p->sched_class->select_task_rq(rq, p, SD_BALANCE_EXEC, 0);
|
|
if (dest_cpu == smp_processor_id())
|
|
goto unlock;
|
|
|
|
/*
|
|
* select_task_rq() can race against ->cpus_allowed
|
|
*/
|
|
if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) &&
|
|
likely(cpu_active(dest_cpu)) && migrate_task(p, rq)) {
|
|
struct migration_arg arg = { p, dest_cpu };
|
|
|
|
task_rq_unlock(rq, &flags);
|
|
stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
|
|
return;
|
|
}
|
|
unlock:
|
|
task_rq_unlock(rq, &flags);
|
|
}
|
|
|
|
#endif
|
|
|
|
DEFINE_PER_CPU(struct kernel_stat, kstat);
|
|
|
|
EXPORT_PER_CPU_SYMBOL(kstat);
|
|
|
|
/*
|
|
* Return any ns on the sched_clock that have not yet been accounted in
|
|
* @p in case that task is currently running.
|
|
*
|
|
* Called with task_rq_lock() held on @rq.
|
|
*/
|
|
static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq)
|
|
{
|
|
u64 ns = 0;
|
|
|
|
if (task_current(rq, p)) {
|
|
update_rq_clock(rq);
|
|
ns = rq->clock_task - p->se.exec_start;
|
|
if ((s64)ns < 0)
|
|
ns = 0;
|
|
}
|
|
|
|
return ns;
|
|
}
|
|
|
|
unsigned long long task_delta_exec(struct task_struct *p)
|
|
{
|
|
unsigned long flags;
|
|
struct rq *rq;
|
|
u64 ns = 0;
|
|
|
|
rq = task_rq_lock(p, &flags);
|
|
ns = do_task_delta_exec(p, rq);
|
|
task_rq_unlock(rq, &flags);
|
|
|
|
return ns;
|
|
}
|
|
|
|
/*
|
|
* Return accounted runtime for the task.
|
|
* In case the task is currently running, return the runtime plus current's
|
|
* pending runtime that have not been accounted yet.
|
|
*/
|
|
unsigned long long task_sched_runtime(struct task_struct *p)
|
|
{
|
|
unsigned long flags;
|
|
struct rq *rq;
|
|
u64 ns = 0;
|
|
|
|
rq = task_rq_lock(p, &flags);
|
|
ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq);
|
|
task_rq_unlock(rq, &flags);
|
|
|
|
return ns;
|
|
}
|
|
|
|
/*
|
|
* Return sum_exec_runtime for the thread group.
|
|
* In case the task is currently running, return the sum plus current's
|
|
* pending runtime that have not been accounted yet.
|
|
*
|
|
* Note that the thread group might have other running tasks as well,
|
|
* so the return value not includes other pending runtime that other
|
|
* running tasks might have.
|
|
*/
|
|
unsigned long long thread_group_sched_runtime(struct task_struct *p)
|
|
{
|
|
struct task_cputime totals;
|
|
unsigned long flags;
|
|
struct rq *rq;
|
|
u64 ns;
|
|
|
|
rq = task_rq_lock(p, &flags);
|
|
thread_group_cputime(p, &totals);
|
|
ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq);
|
|
task_rq_unlock(rq, &flags);
|
|
|
|
return ns;
|
|
}
|
|
|
|
/*
|
|
* Account user cpu time to a process.
|
|
* @p: the process that the cpu time gets accounted to
|
|
* @cputime: the cpu time spent in user space since the last update
|
|
* @cputime_scaled: cputime scaled by cpu frequency
|
|
*/
|
|
void account_user_time(struct task_struct *p, cputime_t cputime,
|
|
cputime_t cputime_scaled)
|
|
{
|
|
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
|
|
cputime64_t tmp;
|
|
|
|
/* Add user time to process. */
|
|
p->utime = cputime_add(p->utime, cputime);
|
|
p->utimescaled = cputime_add(p->utimescaled, cputime_scaled);
|
|
account_group_user_time(p, cputime);
|
|
|
|
/* Add user time to cpustat. */
|
|
tmp = cputime_to_cputime64(cputime);
|
|
if (TASK_NICE(p) > 0)
|
|
cpustat->nice = cputime64_add(cpustat->nice, tmp);
|
|
else
|
|
cpustat->user = cputime64_add(cpustat->user, tmp);
|
|
|
|
cpuacct_update_stats(p, CPUACCT_STAT_USER, cputime);
|
|
/* Account for user time used */
|
|
acct_update_integrals(p);
|
|
}
|
|
|
|
/*
|
|
* Account guest cpu time to a process.
|
|
* @p: the process that the cpu time gets accounted to
|
|
* @cputime: the cpu time spent in virtual machine since the last update
|
|
* @cputime_scaled: cputime scaled by cpu frequency
|
|
*/
|
|
static void account_guest_time(struct task_struct *p, cputime_t cputime,
|
|
cputime_t cputime_scaled)
|
|
{
|
|
cputime64_t tmp;
|
|
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
|
|
|
|
tmp = cputime_to_cputime64(cputime);
|
|
|
|
/* Add guest time to process. */
|
|
p->utime = cputime_add(p->utime, cputime);
|
|
p->utimescaled = cputime_add(p->utimescaled, cputime_scaled);
|
|
account_group_user_time(p, cputime);
|
|
p->gtime = cputime_add(p->gtime, cputime);
|
|
|
|
/* Add guest time to cpustat. */
|
|
if (TASK_NICE(p) > 0) {
|
|
cpustat->nice = cputime64_add(cpustat->nice, tmp);
|
|
cpustat->guest_nice = cputime64_add(cpustat->guest_nice, tmp);
|
|
} else {
|
|
cpustat->user = cputime64_add(cpustat->user, tmp);
|
|
cpustat->guest = cputime64_add(cpustat->guest, tmp);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Account system cpu time to a process and desired cpustat field
|
|
* @p: the process that the cpu time gets accounted to
|
|
* @cputime: the cpu time spent in kernel space since the last update
|
|
* @cputime_scaled: cputime scaled by cpu frequency
|
|
* @target_cputime64: pointer to cpustat field that has to be updated
|
|
*/
|
|
static inline
|
|
void __account_system_time(struct task_struct *p, cputime_t cputime,
|
|
cputime_t cputime_scaled, cputime64_t *target_cputime64)
|
|
{
|
|
cputime64_t tmp = cputime_to_cputime64(cputime);
|
|
|
|
/* Add system time to process. */
|
|
p->stime = cputime_add(p->stime, cputime);
|
|
p->stimescaled = cputime_add(p->stimescaled, cputime_scaled);
|
|
account_group_system_time(p, cputime);
|
|
|
|
/* Add system time to cpustat. */
|
|
*target_cputime64 = cputime64_add(*target_cputime64, tmp);
|
|
cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime);
|
|
|
|
/* Account for system time used */
|
|
acct_update_integrals(p);
|
|
}
|
|
|
|
/*
|
|
* Account system cpu time to a process.
|
|
* @p: the process that the cpu time gets accounted to
|
|
* @hardirq_offset: the offset to subtract from hardirq_count()
|
|
* @cputime: the cpu time spent in kernel space since the last update
|
|
* @cputime_scaled: cputime scaled by cpu frequency
|
|
*/
|
|
void account_system_time(struct task_struct *p, int hardirq_offset,
|
|
cputime_t cputime, cputime_t cputime_scaled)
|
|
{
|
|
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
|
|
cputime64_t *target_cputime64;
|
|
|
|
if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
|
|
account_guest_time(p, cputime, cputime_scaled);
|
|
return;
|
|
}
|
|
|
|
if (hardirq_count() - hardirq_offset)
|
|
target_cputime64 = &cpustat->irq;
|
|
else if (in_serving_softirq())
|
|
target_cputime64 = &cpustat->softirq;
|
|
else
|
|
target_cputime64 = &cpustat->system;
|
|
|
|
__account_system_time(p, cputime, cputime_scaled, target_cputime64);
|
|
}
|
|
|
|
/*
|
|
* Account for involuntary wait time.
|
|
* @cputime: the cpu time spent in involuntary wait
|
|
*/
|
|
void account_steal_time(cputime_t cputime)
|
|
{
|
|
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
|
|
cputime64_t cputime64 = cputime_to_cputime64(cputime);
|
|
|
|
cpustat->steal = cputime64_add(cpustat->steal, cputime64);
|
|
}
|
|
|
|
/*
|
|
* Account for idle time.
|
|
* @cputime: the cpu time spent in idle wait
|
|
*/
|
|
void account_idle_time(cputime_t cputime)
|
|
{
|
|
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
|
|
cputime64_t cputime64 = cputime_to_cputime64(cputime);
|
|
struct rq *rq = this_rq();
|
|
|
|
if (atomic_read(&rq->nr_iowait) > 0)
|
|
cpustat->iowait = cputime64_add(cpustat->iowait, cputime64);
|
|
else
|
|
cpustat->idle = cputime64_add(cpustat->idle, cputime64);
|
|
}
|
|
|
|
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
|
|
|
|
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
|
|
/*
|
|
* Account a tick to a process and cpustat
|
|
* @p: the process that the cpu time gets accounted to
|
|
* @user_tick: is the tick from userspace
|
|
* @rq: the pointer to rq
|
|
*
|
|
* Tick demultiplexing follows the order
|
|
* - pending hardirq update
|
|
* - pending softirq update
|
|
* - user_time
|
|
* - idle_time
|
|
* - system time
|
|
* - check for guest_time
|
|
* - else account as system_time
|
|
*
|
|
* Check for hardirq is done both for system and user time as there is
|
|
* no timer going off while we are on hardirq and hence we may never get an
|
|
* opportunity to update it solely in system time.
|
|
* p->stime and friends are only updated on system time and not on irq
|
|
* softirq as those do not count in task exec_runtime any more.
|
|
*/
|
|
static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
|
|
struct rq *rq)
|
|
{
|
|
cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
|
|
cputime64_t tmp = cputime_to_cputime64(cputime_one_jiffy);
|
|
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
|
|
|
|
if (irqtime_account_hi_update()) {
|
|
cpustat->irq = cputime64_add(cpustat->irq, tmp);
|
|
} else if (irqtime_account_si_update()) {
|
|
cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
|
|
} else if (this_cpu_ksoftirqd() == p) {
|
|
/*
|
|
* ksoftirqd time do not get accounted in cpu_softirq_time.
|
|
* So, we have to handle it separately here.
|
|
* Also, p->stime needs to be updated for ksoftirqd.
|
|
*/
|
|
__account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
|
|
&cpustat->softirq);
|
|
} else if (user_tick) {
|
|
account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
|
|
} else if (p == rq->idle) {
|
|
account_idle_time(cputime_one_jiffy);
|
|
} else if (p->flags & PF_VCPU) { /* System time or guest time */
|
|
account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled);
|
|
} else {
|
|
__account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
|
|
&cpustat->system);
|
|
}
|
|
}
|
|
|
|
static void irqtime_account_idle_ticks(int ticks)
|
|
{
|
|
int i;
|
|
struct rq *rq = this_rq();
|
|
|
|
for (i = 0; i < ticks; i++)
|
|
irqtime_account_process_tick(current, 0, rq);
|
|
}
|
|
#else /* CONFIG_IRQ_TIME_ACCOUNTING */
|
|
static void irqtime_account_idle_ticks(int ticks) {}
|
|
static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
|
|
struct rq *rq) {}
|
|
#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
|
|
|
|
/*
|
|
* Account a single tick of cpu time.
|
|
* @p: the process that the cpu time gets accounted to
|
|
* @user_tick: indicates if the tick is a user or a system tick
|
|
*/
|
|
void account_process_tick(struct task_struct *p, int user_tick)
|
|
{
|
|
cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
|
|
struct rq *rq = this_rq();
|
|
|
|
if (sched_clock_irqtime) {
|
|
irqtime_account_process_tick(p, user_tick, rq);
|
|
return;
|
|
}
|
|
|
|
if (user_tick)
|
|
account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
|
|
else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
|
|
account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy,
|
|
one_jiffy_scaled);
|
|
else
|
|
account_idle_time(cputime_one_jiffy);
|
|
}
|
|
|
|
/*
|
|
* Account multiple ticks of steal time.
|
|
* @p: the process from which the cpu time has been stolen
|
|
* @ticks: number of stolen ticks
|
|
*/
|
|
void account_steal_ticks(unsigned long ticks)
|
|
{
|
|
account_steal_time(jiffies_to_cputime(ticks));
|
|
}
|
|
|
|
/*
|
|
* Account multiple ticks of idle time.
|
|
* @ticks: number of stolen ticks
|
|
*/
|
|
void account_idle_ticks(unsigned long ticks)
|
|
{
|
|
|
|
if (sched_clock_irqtime) {
|
|
irqtime_account_idle_ticks(ticks);
|
|
return;
|
|
}
|
|
|
|
account_idle_time(jiffies_to_cputime(ticks));
|
|
}
|
|
|
|
#endif
|
|
|
|
/*
|
|
* Use precise platform statistics if available:
|
|
*/
|
|
#ifdef CONFIG_VIRT_CPU_ACCOUNTING
|
|
void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
|
|
{
|
|
*ut = p->utime;
|
|
*st = p->stime;
|
|
}
|
|
|
|
void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
|
|
{
|
|
struct task_cputime cputime;
|
|
|
|
thread_group_cputime(p, &cputime);
|
|
|
|
*ut = cputime.utime;
|
|
*st = cputime.stime;
|
|
}
|
|
#else
|
|
|
|
#ifndef nsecs_to_cputime
|
|
# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs)
|
|
#endif
|
|
|
|
void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
|
|
{
|
|
cputime_t rtime, utime = p->utime, total = cputime_add(utime, p->stime);
|
|
|
|
/*
|
|
* Use CFS's precise accounting:
|
|
*/
|
|
rtime = nsecs_to_cputime(p->se.sum_exec_runtime);
|
|
|
|
if (total) {
|
|
u64 temp = rtime;
|
|
|
|
temp *= utime;
|
|
do_div(temp, total);
|
|
utime = (cputime_t)temp;
|
|
} else
|
|
utime = rtime;
|
|
|
|
/*
|
|
* Compare with previous values, to keep monotonicity:
|
|
*/
|
|
p->prev_utime = max(p->prev_utime, utime);
|
|
p->prev_stime = max(p->prev_stime, cputime_sub(rtime, p->prev_utime));
|
|
|
|
*ut = p->prev_utime;
|
|
*st = p->prev_stime;
|
|
}
|
|
|
|
/*
|
|
* Must be called with siglock held.
|
|
*/
|
|
void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
|
|
{
|
|
struct signal_struct *sig = p->signal;
|
|
struct task_cputime cputime;
|
|
cputime_t rtime, utime, total;
|
|
|
|
thread_group_cputime(p, &cputime);
|
|
|
|
total = cputime_add(cputime.utime, cputime.stime);
|
|
rtime = nsecs_to_cputime(cputime.sum_exec_runtime);
|
|
|
|
if (total) {
|
|
u64 temp = rtime;
|
|
|
|
temp *= cputime.utime;
|
|
do_div(temp, total);
|
|
utime = (cputime_t)temp;
|
|
} else
|
|
utime = rtime;
|
|
|
|
sig->prev_utime = max(sig->prev_utime, utime);
|
|
sig->prev_stime = max(sig->prev_stime,
|
|
cputime_sub(rtime, sig->prev_utime));
|
|
|
|
*ut = sig->prev_utime;
|
|
*st = sig->prev_stime;
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* This function gets called by the timer code, with HZ frequency.
|
|
* We call it with interrupts disabled.
|
|
*
|
|
* It also gets called by the fork code, when changing the parent's
|
|
* timeslices.
|
|
*/
|
|
void scheduler_tick(void)
|
|
{
|
|
int cpu = smp_processor_id();
|
|
struct rq *rq = cpu_rq(cpu);
|
|
struct task_struct *curr = rq->curr;
|
|
|
|
sched_clock_tick();
|
|
|
|
raw_spin_lock(&rq->lock);
|
|
update_rq_clock(rq);
|
|
update_cpu_load_active(rq);
|
|
curr->sched_class->task_tick(rq, curr, 0);
|
|
raw_spin_unlock(&rq->lock);
|
|
|
|
perf_event_task_tick();
|
|
|
|
#ifdef CONFIG_SMP
|
|
rq->idle_at_tick = idle_cpu(cpu);
|
|
trigger_load_balance(rq, cpu);
|
|
#endif
|
|
}
|
|
|
|
notrace unsigned long get_parent_ip(unsigned long addr)
|
|
{
|
|
if (in_lock_functions(addr)) {
|
|
addr = CALLER_ADDR2;
|
|
if (in_lock_functions(addr))
|
|
addr = CALLER_ADDR3;
|
|
}
|
|
return addr;
|
|
}
|
|
|
|
#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
|
|
defined(CONFIG_PREEMPT_TRACER))
|
|
|
|
void __kprobes add_preempt_count(int val)
|
|
{
|
|
#ifdef CONFIG_DEBUG_PREEMPT
|
|
/*
|
|
* Underflow?
|
|
*/
|
|
if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
|
|
return;
|
|
#endif
|
|
preempt_count() += val;
|
|
#ifdef CONFIG_DEBUG_PREEMPT
|
|
/*
|
|
* Spinlock count overflowing soon?
|
|
*/
|
|
DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
|
|
PREEMPT_MASK - 10);
|
|
#endif
|
|
if (preempt_count() == val)
|
|
trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
|
|
}
|
|
EXPORT_SYMBOL(add_preempt_count);
|
|
|
|
void __kprobes sub_preempt_count(int val)
|
|
{
|
|
#ifdef CONFIG_DEBUG_PREEMPT
|
|
/*
|
|
* Underflow?
|
|
*/
|
|
if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
|
|
return;
|
|
/*
|
|
* Is the spinlock portion underflowing?
|
|
*/
|
|
if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) &&
|
|
!(preempt_count() & PREEMPT_MASK)))
|
|
return;
|
|
#endif
|
|
|
|
if (preempt_count() == val)
|
|
trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
|
|
preempt_count() -= val;
|
|
}
|
|
EXPORT_SYMBOL(sub_preempt_count);
|
|
|
|
#endif
|
|
|
|
/*
|
|
* Print scheduling while atomic bug:
|
|
*/
|
|
static noinline void __schedule_bug(struct task_struct *prev)
|
|
{
|
|
struct pt_regs *regs = get_irq_regs();
|
|
|
|
printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n",
|
|
prev->comm, prev->pid, preempt_count());
|
|
|
|
debug_show_held_locks(prev);
|
|
print_modules();
|
|
if (irqs_disabled())
|
|
print_irqtrace_events(prev);
|
|
|
|
if (regs)
|
|
show_regs(regs);
|
|
else
|
|
dump_stack();
|
|
}
|
|
|
|
/*
|
|
* Various schedule()-time debugging checks and statistics:
|
|
*/
|
|
static inline void schedule_debug(struct task_struct *prev)
|
|
{
|
|
/*
|
|
* Test if we are atomic. Since do_exit() needs to call into
|
|
* schedule() atomically, we ignore that path for now.
|
|
* Otherwise, whine if we are scheduling when we should not be.
|
|
*/
|
|
if (unlikely(in_atomic_preempt_off() && !prev->exit_state))
|
|
__schedule_bug(prev);
|
|
|
|
profile_hit(SCHED_PROFILING, __builtin_return_address(0));
|
|
|
|
schedstat_inc(this_rq(), sched_count);
|
|
#ifdef CONFIG_SCHEDSTATS
|
|
if (unlikely(prev->lock_depth >= 0)) {
|
|
schedstat_inc(this_rq(), rq_sched_info.bkl_count);
|
|
schedstat_inc(prev, sched_info.bkl_count);
|
|
}
|
|
#endif
|
|
}
|
|
|
|
static void put_prev_task(struct rq *rq, struct task_struct *prev)
|
|
{
|
|
if (prev->se.on_rq)
|
|
update_rq_clock(rq);
|
|
prev->sched_class->put_prev_task(rq, prev);
|
|
}
|
|
|
|
/*
|
|
* Pick up the highest-prio task:
|
|
*/
|
|
static inline struct task_struct *
|
|
pick_next_task(struct rq *rq)
|
|
{
|
|
const struct sched_class *class;
|
|
struct task_struct *p;
|
|
|
|
/*
|
|
* Optimization: we know that if all tasks are in
|
|
* the fair class we can call that function directly:
|
|
*/
|
|
if (likely(rq->nr_running == rq->cfs.nr_running)) {
|
|
p = fair_sched_class.pick_next_task(rq);
|
|
if (likely(p))
|
|
return p;
|
|
}
|
|
|
|
for_each_class(class) {
|
|
p = class->pick_next_task(rq);
|
|
if (p)
|
|
return p;
|
|
}
|
|
|
|
BUG(); /* the idle class will always have a runnable task */
|
|
}
|
|
|
|
/*
|
|
* schedule() is the main scheduler function.
|
|
*/
|
|
asmlinkage void __sched schedule(void)
|
|
{
|
|
struct task_struct *prev, *next;
|
|
unsigned long *switch_count;
|
|
struct rq *rq;
|
|
int cpu;
|
|
|
|
need_resched:
|
|
preempt_disable();
|
|
cpu = smp_processor_id();
|
|
rq = cpu_rq(cpu);
|
|
rcu_note_context_switch(cpu);
|
|
prev = rq->curr;
|
|
|
|
schedule_debug(prev);
|
|
|
|
if (sched_feat(HRTICK))
|
|
hrtick_clear(rq);
|
|
|
|
raw_spin_lock_irq(&rq->lock);
|
|
|
|
switch_count = &prev->nivcsw;
|
|
if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
|
|
if (unlikely(signal_pending_state(prev->state, prev))) {
|
|
prev->state = TASK_RUNNING;
|
|
} else {
|
|
/*
|
|
* If a worker is going to sleep, notify and
|
|
* ask workqueue whether it wants to wake up a
|
|
* task to maintain concurrency. If so, wake
|
|
* up the task.
|
|
*/
|
|
if (prev->flags & PF_WQ_WORKER) {
|
|
struct task_struct *to_wakeup;
|
|
|
|
to_wakeup = wq_worker_sleeping(prev, cpu);
|
|
if (to_wakeup)
|
|
try_to_wake_up_local(to_wakeup);
|
|
}
|
|
deactivate_task(rq, prev, DEQUEUE_SLEEP);
|
|
}
|
|
switch_count = &prev->nvcsw;
|
|
}
|
|
|
|
/*
|
|
* If we are going to sleep and we have plugged IO queued, make
|
|
* sure to submit it to avoid deadlocks.
|
|
*/
|
|
if (prev->state != TASK_RUNNING && blk_needs_flush_plug(prev)) {
|
|
raw_spin_unlock(&rq->lock);
|
|
blk_flush_plug(prev);
|
|
raw_spin_lock(&rq->lock);
|
|
}
|
|
|
|
pre_schedule(rq, prev);
|
|
|
|
if (unlikely(!rq->nr_running))
|
|
idle_balance(cpu, rq);
|
|
|
|
put_prev_task(rq, prev);
|
|
next = pick_next_task(rq);
|
|
clear_tsk_need_resched(prev);
|
|
rq->skip_clock_update = 0;
|
|
|
|
if (likely(prev != next)) {
|
|
rq->nr_switches++;
|
|
rq->curr = next;
|
|
++*switch_count;
|
|
|
|
context_switch(rq, prev, next); /* unlocks the rq */
|
|
/*
|
|
* The context switch have flipped the stack from under us
|
|
* and restored the local variables which were saved when
|
|
* this task called schedule() in the past. prev == current
|
|
* is still correct, but it can be moved to another cpu/rq.
|
|
*/
|
|
cpu = smp_processor_id();
|
|
rq = cpu_rq(cpu);
|
|
} else
|
|
raw_spin_unlock_irq(&rq->lock);
|
|
|
|
post_schedule(rq);
|
|
|
|
preempt_enable_no_resched();
|
|
if (need_resched())
|
|
goto need_resched;
|
|
}
|
|
EXPORT_SYMBOL(schedule);
|
|
|
|
#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
|
|
/*
|
|
* Look out! "owner" is an entirely speculative pointer
|
|
* access and not reliable.
|
|
*/
|
|
int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
|
|
{
|
|
unsigned int cpu;
|
|
struct rq *rq;
|
|
|
|
if (!sched_feat(OWNER_SPIN))
|
|
return 0;
|
|
|
|
#ifdef CONFIG_DEBUG_PAGEALLOC
|
|
/*
|
|
* Need to access the cpu field knowing that
|
|
* DEBUG_PAGEALLOC could have unmapped it if
|
|
* the mutex owner just released it and exited.
|
|
*/
|
|
if (probe_kernel_address(&owner->cpu, cpu))
|
|
return 0;
|
|
#else
|
|
cpu = owner->cpu;
|
|
#endif
|
|
|
|
/*
|
|
* Even if the access succeeded (likely case),
|
|
* the cpu field may no longer be valid.
|
|
*/
|
|
if (cpu >= nr_cpumask_bits)
|
|
return 0;
|
|
|
|
/*
|
|
* We need to validate that we can do a
|
|
* get_cpu() and that we have the percpu area.
|
|
*/
|
|
if (!cpu_online(cpu))
|
|
return 0;
|
|
|
|
rq = cpu_rq(cpu);
|
|
|
|
for (;;) {
|
|
/*
|
|
* Owner changed, break to re-assess state.
|
|
*/
|
|
if (lock->owner != owner) {
|
|
/*
|
|
* If the lock has switched to a different owner,
|
|
* we likely have heavy contention. Return 0 to quit
|
|
* optimistic spinning and not contend further:
|
|
*/
|
|
if (lock->owner)
|
|
return 0;
|
|
break;
|
|
}
|
|
|
|
/*
|
|
* Is that owner really running on that cpu?
|
|
*/
|
|
if (task_thread_info(rq->curr) != owner || need_resched())
|
|
return 0;
|
|
|
|
arch_mutex_cpu_relax();
|
|
}
|
|
|
|
return 1;
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_PREEMPT
|
|
/*
|
|
* this is the entry point to schedule() from in-kernel preemption
|
|
* off of preempt_enable. Kernel preemptions off return from interrupt
|
|
* occur there and call schedule directly.
|
|
*/
|
|
asmlinkage void __sched notrace preempt_schedule(void)
|
|
{
|
|
struct thread_info *ti = current_thread_info();
|
|
|
|
/*
|
|
* If there is a non-zero preempt_count or interrupts are disabled,
|
|
* we do not want to preempt the current task. Just return..
|
|
*/
|
|
if (likely(ti->preempt_count || irqs_disabled()))
|
|
return;
|
|
|
|
do {
|
|
add_preempt_count_notrace(PREEMPT_ACTIVE);
|
|
schedule();
|
|
sub_preempt_count_notrace(PREEMPT_ACTIVE);
|
|
|
|
/*
|
|
* Check again in case we missed a preemption opportunity
|
|
* between schedule and now.
|
|
*/
|
|
barrier();
|
|
} while (need_resched());
|
|
}
|
|
EXPORT_SYMBOL(preempt_schedule);
|
|
|
|
/*
|
|
* this is the entry point to schedule() from kernel preemption
|
|
* off of irq context.
|
|
* Note, that this is called and return with irqs disabled. This will
|
|
* protect us against recursive calling from irq.
|
|
*/
|
|
asmlinkage void __sched preempt_schedule_irq(void)
|
|
{
|
|
struct thread_info *ti = current_thread_info();
|
|
|
|
/* Catch callers which need to be fixed */
|
|
BUG_ON(ti->preempt_count || !irqs_disabled());
|
|
|
|
do {
|
|
add_preempt_count(PREEMPT_ACTIVE);
|
|
local_irq_enable();
|
|
schedule();
|
|
local_irq_disable();
|
|
sub_preempt_count(PREEMPT_ACTIVE);
|
|
|
|
/*
|
|
* Check again in case we missed a preemption opportunity
|
|
* between schedule and now.
|
|
*/
|
|
barrier();
|
|
} while (need_resched());
|
|
}
|
|
|
|
#endif /* CONFIG_PREEMPT */
|
|
|
|
int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags,
|
|
void *key)
|
|
{
|
|
return try_to_wake_up(curr->private, mode, wake_flags);
|
|
}
|
|
EXPORT_SYMBOL(default_wake_function);
|
|
|
|
/*
|
|
* The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just
|
|
* wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve
|
|
* number) then we wake all the non-exclusive tasks and one exclusive task.
|
|
*
|
|
* There are circumstances in which we can try to wake a task which has already
|
|
* started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
|
|
* zero in this (rare) case, and we handle it by continuing to scan the queue.
|
|
*/
|
|
static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
|
|
int nr_exclusive, int wake_flags, void *key)
|
|
{
|
|
wait_queue_t *curr, *next;
|
|
|
|
list_for_each_entry_safe(curr, next, &q->task_list, task_list) {
|
|
unsigned flags = curr->flags;
|
|
|
|
if (curr->func(curr, mode, wake_flags, key) &&
|
|
(flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
|
|
break;
|
|
}
|
|
}
|
|
|
|
/**
|
|
* __wake_up - wake up threads blocked on a waitqueue.
|
|
* @q: the waitqueue
|
|
* @mode: which threads
|
|
* @nr_exclusive: how many wake-one or wake-many threads to wake up
|
|
* @key: is directly passed to the wakeup function
|
|
*
|
|
* It may be assumed that this function implies a write memory barrier before
|
|
* changing the task state if and only if any tasks are woken up.
|
|
*/
|
|
void __wake_up(wait_queue_head_t *q, unsigned int mode,
|
|
int nr_exclusive, void *key)
|
|
{
|
|
unsigned long flags;
|
|
|
|
spin_lock_irqsave(&q->lock, flags);
|
|
__wake_up_common(q, mode, nr_exclusive, 0, key);
|
|
spin_unlock_irqrestore(&q->lock, flags);
|
|
}
|
|
EXPORT_SYMBOL(__wake_up);
|
|
|
|
/*
|
|
* Same as __wake_up but called with the spinlock in wait_queue_head_t held.
|
|
*/
|
|
void __wake_up_locked(wait_queue_head_t *q, unsigned int mode)
|
|
{
|
|
__wake_up_common(q, mode, 1, 0, NULL);
|
|
}
|
|
EXPORT_SYMBOL_GPL(__wake_up_locked);
|
|
|
|
void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
|
|
{
|
|
__wake_up_common(q, mode, 1, 0, key);
|
|
}
|
|
EXPORT_SYMBOL_GPL(__wake_up_locked_key);
|
|
|
|
/**
|
|
* __wake_up_sync_key - wake up threads blocked on a waitqueue.
|
|
* @q: the waitqueue
|
|
* @mode: which threads
|
|
* @nr_exclusive: how many wake-one or wake-many threads to wake up
|
|
* @key: opaque value to be passed to wakeup targets
|
|
*
|
|
* The sync wakeup differs that the waker knows that it will schedule
|
|
* away soon, so while the target thread will be woken up, it will not
|
|
* be migrated to another CPU - ie. the two threads are 'synchronized'
|
|
* with each other. This can prevent needless bouncing between CPUs.
|
|
*
|
|
* On UP it can prevent extra preemption.
|
|
*
|
|
* It may be assumed that this function implies a write memory barrier before
|
|
* changing the task state if and only if any tasks are woken up.
|
|
*/
|
|
void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
|
|
int nr_exclusive, void *key)
|
|
{
|
|
unsigned long flags;
|
|
int wake_flags = WF_SYNC;
|
|
|
|
if (unlikely(!q))
|
|
return;
|
|
|
|
if (unlikely(!nr_exclusive))
|
|
wake_flags = 0;
|
|
|
|
spin_lock_irqsave(&q->lock, flags);
|
|
__wake_up_common(q, mode, nr_exclusive, wake_flags, key);
|
|
spin_unlock_irqrestore(&q->lock, flags);
|
|
}
|
|
EXPORT_SYMBOL_GPL(__wake_up_sync_key);
|
|
|
|
/*
|
|
* __wake_up_sync - see __wake_up_sync_key()
|
|
*/
|
|
void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
|
|
{
|
|
__wake_up_sync_key(q, mode, nr_exclusive, NULL);
|
|
}
|
|
EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */
|
|
|
|
/**
|
|
* complete: - signals a single thread waiting on this completion
|
|
* @x: holds the state of this particular completion
|
|
*
|
|
* This will wake up a single thread waiting on this completion. Threads will be
|
|
* awakened in the same order in which they were queued.
|
|
*
|
|
* See also complete_all(), wait_for_completion() and related routines.
|
|
*
|
|
* It may be assumed that this function implies a write memory barrier before
|
|
* changing the task state if and only if any tasks are woken up.
|
|
*/
|
|
void complete(struct completion *x)
|
|
{
|
|
unsigned long flags;
|
|
|
|
spin_lock_irqsave(&x->wait.lock, flags);
|
|
x->done++;
|
|
__wake_up_common(&x->wait, TASK_NORMAL, 1, 0, NULL);
|
|
spin_unlock_irqrestore(&x->wait.lock, flags);
|
|
}
|
|
EXPORT_SYMBOL(complete);
|
|
|
|
/**
|
|
* complete_all: - signals all threads waiting on this completion
|
|
* @x: holds the state of this particular completion
|
|
*
|
|
* This will wake up all threads waiting on this particular completion event.
|
|
*
|
|
* It may be assumed that this function implies a write memory barrier before
|
|
* changing the task state if and only if any tasks are woken up.
|
|
*/
|
|
void complete_all(struct completion *x)
|
|
{
|
|
unsigned long flags;
|
|
|
|
spin_lock_irqsave(&x->wait.lock, flags);
|
|
x->done += UINT_MAX/2;
|
|
__wake_up_common(&x->wait, TASK_NORMAL, 0, 0, NULL);
|
|
spin_unlock_irqrestore(&x->wait.lock, flags);
|
|
}
|
|
EXPORT_SYMBOL(complete_all);
|
|
|
|
static inline long __sched
|
|
do_wait_for_common(struct completion *x, long timeout, int state)
|
|
{
|
|
if (!x->done) {
|
|
DECLARE_WAITQUEUE(wait, current);
|
|
|
|
__add_wait_queue_tail_exclusive(&x->wait, &wait);
|
|
do {
|
|
if (signal_pending_state(state, current)) {
|
|
timeout = -ERESTARTSYS;
|
|
break;
|
|
}
|
|
__set_current_state(state);
|
|
spin_unlock_irq(&x->wait.lock);
|
|
timeout = schedule_timeout(timeout);
|
|
spin_lock_irq(&x->wait.lock);
|
|
} while (!x->done && timeout);
|
|
__remove_wait_queue(&x->wait, &wait);
|
|
if (!x->done)
|
|
return timeout;
|
|
}
|
|
x->done--;
|
|
return timeout ?: 1;
|
|
}
|
|
|
|
static long __sched
|
|
wait_for_common(struct completion *x, long timeout, int state)
|
|
{
|
|
might_sleep();
|
|
|
|
spin_lock_irq(&x->wait.lock);
|
|
timeout = do_wait_for_common(x, timeout, state);
|
|
spin_unlock_irq(&x->wait.lock);
|
|
return timeout;
|
|
}
|
|
|
|
/**
|
|
* wait_for_completion: - waits for completion of a task
|
|
* @x: holds the state of this particular completion
|
|
*
|
|
* This waits to be signaled for completion of a specific task. It is NOT
|
|
* interruptible and there is no timeout.
|
|
*
|
|
* See also similar routines (i.e. wait_for_completion_timeout()) with timeout
|
|
* and interrupt capability. Also see complete().
|
|
*/
|
|
void __sched wait_for_completion(struct completion *x)
|
|
{
|
|
wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
|
|
}
|
|
EXPORT_SYMBOL(wait_for_completion);
|
|
|
|
/**
|
|
* wait_for_completion_timeout: - waits for completion of a task (w/timeout)
|
|
* @x: holds the state of this particular completion
|
|
* @timeout: timeout value in jiffies
|
|
*
|
|
* This waits for either a completion of a specific task to be signaled or for a
|
|
* specified timeout to expire. The timeout is in jiffies. It is not
|
|
* interruptible.
|
|
*/
|
|
unsigned long __sched
|
|
wait_for_completion_timeout(struct completion *x, unsigned long timeout)
|
|
{
|
|
return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE);
|
|
}
|
|
EXPORT_SYMBOL(wait_for_completion_timeout);
|
|
|
|
/**
|
|
* wait_for_completion_interruptible: - waits for completion of a task (w/intr)
|
|
* @x: holds the state of this particular completion
|
|
*
|
|
* This waits for completion of a specific task to be signaled. It is
|
|
* interruptible.
|
|
*/
|
|
int __sched wait_for_completion_interruptible(struct completion *x)
|
|
{
|
|
long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE);
|
|
if (t == -ERESTARTSYS)
|
|
return t;
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(wait_for_completion_interruptible);
|
|
|
|
/**
|
|
* wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr))
|
|
* @x: holds the state of this particular completion
|
|
* @timeout: timeout value in jiffies
|
|
*
|
|
* This waits for either a completion of a specific task to be signaled or for a
|
|
* specified timeout to expire. It is interruptible. The timeout is in jiffies.
|
|
*/
|
|
long __sched
|
|
wait_for_completion_interruptible_timeout(struct completion *x,
|
|
unsigned long timeout)
|
|
{
|
|
return wait_for_common(x, timeout, TASK_INTERRUPTIBLE);
|
|
}
|
|
EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
|
|
|
|
/**
|
|
* wait_for_completion_killable: - waits for completion of a task (killable)
|
|
* @x: holds the state of this particular completion
|
|
*
|
|
* This waits to be signaled for completion of a specific task. It can be
|
|
* interrupted by a kill signal.
|
|
*/
|
|
int __sched wait_for_completion_killable(struct completion *x)
|
|
{
|
|
long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE);
|
|
if (t == -ERESTARTSYS)
|
|
return t;
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(wait_for_completion_killable);
|
|
|
|
/**
|
|
* wait_for_completion_killable_timeout: - waits for completion of a task (w/(to,killable))
|
|
* @x: holds the state of this particular completion
|
|
* @timeout: timeout value in jiffies
|
|
*
|
|
* This waits for either a completion of a specific task to be
|
|
* signaled or for a specified timeout to expire. It can be
|
|
* interrupted by a kill signal. The timeout is in jiffies.
|
|
*/
|
|
long __sched
|
|
wait_for_completion_killable_timeout(struct completion *x,
|
|
unsigned long timeout)
|
|
{
|
|
return wait_for_common(x, timeout, TASK_KILLABLE);
|
|
}
|
|
EXPORT_SYMBOL(wait_for_completion_killable_timeout);
|
|
|
|
/**
|
|
* try_wait_for_completion - try to decrement a completion without blocking
|
|
* @x: completion structure
|
|
*
|
|
* Returns: 0 if a decrement cannot be done without blocking
|
|
* 1 if a decrement succeeded.
|
|
*
|
|
* If a completion is being used as a counting completion,
|
|
* attempt to decrement the counter without blocking. This
|
|
* enables us to avoid waiting if the resource the completion
|
|
* is protecting is not available.
|
|
*/
|
|
bool try_wait_for_completion(struct completion *x)
|
|
{
|
|
unsigned long flags;
|
|
int ret = 1;
|
|
|
|
spin_lock_irqsave(&x->wait.lock, flags);
|
|
if (!x->done)
|
|
ret = 0;
|
|
else
|
|
x->done--;
|
|
spin_unlock_irqrestore(&x->wait.lock, flags);
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(try_wait_for_completion);
|
|
|
|
/**
|
|
* completion_done - Test to see if a completion has any waiters
|
|
* @x: completion structure
|
|
*
|
|
* Returns: 0 if there are waiters (wait_for_completion() in progress)
|
|
* 1 if there are no waiters.
|
|
*
|
|
*/
|
|
bool completion_done(struct completion *x)
|
|
{
|
|
unsigned long flags;
|
|
int ret = 1;
|
|
|
|
spin_lock_irqsave(&x->wait.lock, flags);
|
|
if (!x->done)
|
|
ret = 0;
|
|
spin_unlock_irqrestore(&x->wait.lock, flags);
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(completion_done);
|
|
|
|
static long __sched
|
|
sleep_on_common(wait_queue_head_t *q, int state, long timeout)
|
|
{
|
|
unsigned long flags;
|
|
wait_queue_t wait;
|
|
|
|
init_waitqueue_entry(&wait, current);
|
|
|
|
__set_current_state(state);
|
|
|
|
spin_lock_irqsave(&q->lock, flags);
|
|
__add_wait_queue(q, &wait);
|
|
spin_unlock(&q->lock);
|
|
timeout = schedule_timeout(timeout);
|
|
spin_lock_irq(&q->lock);
|
|
__remove_wait_queue(q, &wait);
|
|
spin_unlock_irqrestore(&q->lock, flags);
|
|
|
|
return timeout;
|
|
}
|
|
|
|
void __sched interruptible_sleep_on(wait_queue_head_t *q)
|
|
{
|
|
sleep_on_common(q, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
|
|
}
|
|
EXPORT_SYMBOL(interruptible_sleep_on);
|
|
|
|
long __sched
|
|
interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout)
|
|
{
|
|
return sleep_on_common(q, TASK_INTERRUPTIBLE, timeout);
|
|
}
|
|
EXPORT_SYMBOL(interruptible_sleep_on_timeout);
|
|
|
|
void __sched sleep_on(wait_queue_head_t *q)
|
|
{
|
|
sleep_on_common(q, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
|
|
}
|
|
EXPORT_SYMBOL(sleep_on);
|
|
|
|
long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout)
|
|
{
|
|
return sleep_on_common(q, TASK_UNINTERRUPTIBLE, timeout);
|
|
}
|
|
EXPORT_SYMBOL(sleep_on_timeout);
|
|
|
|
#ifdef CONFIG_RT_MUTEXES
|
|
|
|
/*
|
|
* rt_mutex_setprio - set the current priority of a task
|
|
* @p: task
|
|
* @prio: prio value (kernel-internal form)
|
|
*
|
|
* This function changes the 'effective' priority of a task. It does
|
|
* not touch ->normal_prio like __setscheduler().
|
|
*
|
|
* Used by the rt_mutex code to implement priority inheritance logic.
|
|
*/
|
|
void rt_mutex_setprio(struct task_struct *p, int prio)
|
|
{
|
|
unsigned long flags;
|
|
int oldprio, on_rq, running;
|
|
struct rq *rq;
|
|
const struct sched_class *prev_class;
|
|
|
|
BUG_ON(prio < 0 || prio > MAX_PRIO);
|
|
|
|
rq = task_rq_lock(p, &flags);
|
|
|
|
trace_sched_pi_setprio(p, prio);
|
|
oldprio = p->prio;
|
|
prev_class = p->sched_class;
|
|
on_rq = p->se.on_rq;
|
|
running = task_current(rq, p);
|
|
if (on_rq)
|
|
dequeue_task(rq, p, 0);
|
|
if (running)
|
|
p->sched_class->put_prev_task(rq, p);
|
|
|
|
if (rt_prio(prio))
|
|
p->sched_class = &rt_sched_class;
|
|
else
|
|
p->sched_class = &fair_sched_class;
|
|
|
|
p->prio = prio;
|
|
|
|
if (running)
|
|
p->sched_class->set_curr_task(rq);
|
|
if (on_rq)
|
|
enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
|
|
|
|
check_class_changed(rq, p, prev_class, oldprio);
|
|
task_rq_unlock(rq, &flags);
|
|
}
|
|
|
|
#endif
|
|
|
|
void set_user_nice(struct task_struct *p, long nice)
|
|
{
|
|
int old_prio, delta, on_rq;
|
|
unsigned long flags;
|
|
struct rq *rq;
|
|
|
|
if (TASK_NICE(p) == nice || nice < -20 || nice > 19)
|
|
return;
|
|
/*
|
|
* We have to be careful, if called from sys_setpriority(),
|
|
* the task might be in the middle of scheduling on another CPU.
|
|
*/
|
|
rq = task_rq_lock(p, &flags);
|
|
/*
|
|
* The RT priorities are set via sched_setscheduler(), but we still
|
|
* allow the 'normal' nice value to be set - but as expected
|
|
* it wont have any effect on scheduling until the task is
|
|
* SCHED_FIFO/SCHED_RR:
|
|
*/
|
|
if (task_has_rt_policy(p)) {
|
|
p->static_prio = NICE_TO_PRIO(nice);
|
|
goto out_unlock;
|
|
}
|
|
on_rq = p->se.on_rq;
|
|
if (on_rq)
|
|
dequeue_task(rq, p, 0);
|
|
|
|
p->static_prio = NICE_TO_PRIO(nice);
|
|
set_load_weight(p);
|
|
old_prio = p->prio;
|
|
p->prio = effective_prio(p);
|
|
delta = p->prio - old_prio;
|
|
|
|
if (on_rq) {
|
|
enqueue_task(rq, p, 0);
|
|
/*
|
|
* If the task increased its priority or is running and
|
|
* lowered its priority, then reschedule its CPU:
|
|
*/
|
|
if (delta < 0 || (delta > 0 && task_running(rq, p)))
|
|
resched_task(rq->curr);
|
|
}
|
|
out_unlock:
|
|
task_rq_unlock(rq, &flags);
|
|
}
|
|
EXPORT_SYMBOL(set_user_nice);
|
|
|
|
/*
|
|
* can_nice - check if a task can reduce its nice value
|
|
* @p: task
|
|
* @nice: nice value
|
|
*/
|
|
int can_nice(const struct task_struct *p, const int nice)
|
|
{
|
|
/* convert nice value [19,-20] to rlimit style value [1,40] */
|
|
int nice_rlim = 20 - nice;
|
|
|
|
return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) ||
|
|
capable(CAP_SYS_NICE));
|
|
}
|
|
|
|
#ifdef __ARCH_WANT_SYS_NICE
|
|
|
|
/*
|
|
* sys_nice - change the priority of the current process.
|
|
* @increment: priority increment
|
|
*
|
|
* sys_setpriority is a more generic, but much slower function that
|
|
* does similar things.
|
|
*/
|
|
SYSCALL_DEFINE1(nice, int, increment)
|
|
{
|
|
long nice, retval;
|
|
|
|
/*
|
|
* Setpriority might change our priority at the same moment.
|
|
* We don't have to worry. Conceptually one call occurs first
|
|
* and we have a single winner.
|
|
*/
|
|
if (increment < -40)
|
|
increment = -40;
|
|
if (increment > 40)
|
|
increment = 40;
|
|
|
|
nice = TASK_NICE(current) + increment;
|
|
if (nice < -20)
|
|
nice = -20;
|
|
if (nice > 19)
|
|
nice = 19;
|
|
|
|
if (increment < 0 && !can_nice(current, nice))
|
|
return -EPERM;
|
|
|
|
retval = security_task_setnice(current, nice);
|
|
if (retval)
|
|
return retval;
|
|
|
|
set_user_nice(current, nice);
|
|
return 0;
|
|
}
|
|
|
|
#endif
|
|
|
|
/**
|
|
* task_prio - return the priority value of a given task.
|
|
* @p: the task in question.
|
|
*
|
|
* This is the priority value as seen by users in /proc.
|
|
* RT tasks are offset by -200. Normal tasks are centered
|
|
* around 0, value goes from -16 to +15.
|
|
*/
|
|
int task_prio(const struct task_struct *p)
|
|
{
|
|
return p->prio - MAX_RT_PRIO;
|
|
}
|
|
|
|
/**
|
|
* task_nice - return the nice value of a given task.
|
|
* @p: the task in question.
|
|
*/
|
|
int task_nice(const struct task_struct *p)
|
|
{
|
|
return TASK_NICE(p);
|
|
}
|
|
EXPORT_SYMBOL(task_nice);
|
|
|
|
/**
|
|
* idle_cpu - is a given cpu idle currently?
|
|
* @cpu: the processor in question.
|
|
*/
|
|
int idle_cpu(int cpu)
|
|
{
|
|
return cpu_curr(cpu) == cpu_rq(cpu)->idle;
|
|
}
|
|
|
|
/**
|
|
* idle_task - return the idle task for a given cpu.
|
|
* @cpu: the processor in question.
|
|
*/
|
|
struct task_struct *idle_task(int cpu)
|
|
{
|
|
return cpu_rq(cpu)->idle;
|
|
}
|
|
|
|
/**
|
|
* find_process_by_pid - find a process with a matching PID value.
|
|
* @pid: the pid in question.
|
|
*/
|
|
static struct task_struct *find_process_by_pid(pid_t pid)
|
|
{
|
|
return pid ? find_task_by_vpid(pid) : current;
|
|
}
|
|
|
|
/* Actually do priority change: must hold rq lock. */
|
|
static void
|
|
__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
|
|
{
|
|
BUG_ON(p->se.on_rq);
|
|
|
|
p->policy = policy;
|
|
p->rt_priority = prio;
|
|
p->normal_prio = normal_prio(p);
|
|
/* we are holding p->pi_lock already */
|
|
p->prio = rt_mutex_getprio(p);
|
|
if (rt_prio(p->prio))
|
|
p->sched_class = &rt_sched_class;
|
|
else
|
|
p->sched_class = &fair_sched_class;
|
|
set_load_weight(p);
|
|
}
|
|
|
|
/*
|
|
* check the target process has a UID that matches the current process's
|
|
*/
|
|
static bool check_same_owner(struct task_struct *p)
|
|
{
|
|
const struct cred *cred = current_cred(), *pcred;
|
|
bool match;
|
|
|
|
rcu_read_lock();
|
|
pcred = __task_cred(p);
|
|
if (cred->user->user_ns == pcred->user->user_ns)
|
|
match = (cred->euid == pcred->euid ||
|
|
cred->euid == pcred->uid);
|
|
else
|
|
match = false;
|
|
rcu_read_unlock();
|
|
return match;
|
|
}
|
|
|
|
static int __sched_setscheduler(struct task_struct *p, int policy,
|
|
const struct sched_param *param, bool user)
|
|
{
|
|
int retval, oldprio, oldpolicy = -1, on_rq, running;
|
|
unsigned long flags;
|
|
const struct sched_class *prev_class;
|
|
struct rq *rq;
|
|
int reset_on_fork;
|
|
|
|
/* may grab non-irq protected spin_locks */
|
|
BUG_ON(in_interrupt());
|
|
recheck:
|
|
/* double check policy once rq lock held */
|
|
if (policy < 0) {
|
|
reset_on_fork = p->sched_reset_on_fork;
|
|
policy = oldpolicy = p->policy;
|
|
} else {
|
|
reset_on_fork = !!(policy & SCHED_RESET_ON_FORK);
|
|
policy &= ~SCHED_RESET_ON_FORK;
|
|
|
|
if (policy != SCHED_FIFO && policy != SCHED_RR &&
|
|
policy != SCHED_NORMAL && policy != SCHED_BATCH &&
|
|
policy != SCHED_IDLE)
|
|
return -EINVAL;
|
|
}
|
|
|
|
/*
|
|
* Valid priorities for SCHED_FIFO and SCHED_RR are
|
|
* 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL,
|
|
* SCHED_BATCH and SCHED_IDLE is 0.
|
|
*/
|
|
if (param->sched_priority < 0 ||
|
|
(p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) ||
|
|
(!p->mm && param->sched_priority > MAX_RT_PRIO-1))
|
|
return -EINVAL;
|
|
if (rt_policy(policy) != (param->sched_priority != 0))
|
|
return -EINVAL;
|
|
|
|
/*
|
|
* Allow unprivileged RT tasks to decrease priority:
|
|
*/
|
|
if (user && !capable(CAP_SYS_NICE)) {
|
|
if (rt_policy(policy)) {
|
|
unsigned long rlim_rtprio =
|
|
task_rlimit(p, RLIMIT_RTPRIO);
|
|
|
|
/* can't set/change the rt policy */
|
|
if (policy != p->policy && !rlim_rtprio)
|
|
return -EPERM;
|
|
|
|
/* can't increase priority */
|
|
if (param->sched_priority > p->rt_priority &&
|
|
param->sched_priority > rlim_rtprio)
|
|
return -EPERM;
|
|
}
|
|
|
|
/*
|
|
* Treat SCHED_IDLE as nice 20. Only allow a switch to
|
|
* SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
|
|
*/
|
|
if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) {
|
|
if (!can_nice(p, TASK_NICE(p)))
|
|
return -EPERM;
|
|
}
|
|
|
|
/* can't change other user's priorities */
|
|
if (!check_same_owner(p))
|
|
return -EPERM;
|
|
|
|
/* Normal users shall not reset the sched_reset_on_fork flag */
|
|
if (p->sched_reset_on_fork && !reset_on_fork)
|
|
return -EPERM;
|
|
}
|
|
|
|
if (user) {
|
|
retval = security_task_setscheduler(p);
|
|
if (retval)
|
|
return retval;
|
|
}
|
|
|
|
/*
|
|
* make sure no PI-waiters arrive (or leave) while we are
|
|
* changing the priority of the task:
|
|
*/
|
|
raw_spin_lock_irqsave(&p->pi_lock, flags);
|
|
/*
|
|
* To be able to change p->policy safely, the appropriate
|
|
* runqueue lock must be held.
|
|
*/
|
|
rq = __task_rq_lock(p);
|
|
|
|
/*
|
|
* Changing the policy of the stop threads its a very bad idea
|
|
*/
|
|
if (p == rq->stop) {
|
|
__task_rq_unlock(rq);
|
|
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
|
|
return -EINVAL;
|
|
}
|
|
|
|
/*
|
|
* If not changing anything there's no need to proceed further:
|
|
*/
|
|
if (unlikely(policy == p->policy && (!rt_policy(policy) ||
|
|
param->sched_priority == p->rt_priority))) {
|
|
|
|
__task_rq_unlock(rq);
|
|
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
|
|
return 0;
|
|
}
|
|
|
|
#ifdef CONFIG_RT_GROUP_SCHED
|
|
if (user) {
|
|
/*
|
|
* Do not allow realtime tasks into groups that have no runtime
|
|
* assigned.
|
|
*/
|
|
if (rt_bandwidth_enabled() && rt_policy(policy) &&
|
|
task_group(p)->rt_bandwidth.rt_runtime == 0 &&
|
|
!task_group_is_autogroup(task_group(p))) {
|
|
__task_rq_unlock(rq);
|
|
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
|
|
return -EPERM;
|
|
}
|
|
}
|
|
#endif
|
|
|
|
/* recheck policy now with rq lock held */
|
|
if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
|
|
policy = oldpolicy = -1;
|
|
__task_rq_unlock(rq);
|
|
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
|
|
goto recheck;
|
|
}
|
|
on_rq = p->se.on_rq;
|
|
running = task_current(rq, p);
|
|
if (on_rq)
|
|
deactivate_task(rq, p, 0);
|
|
if (running)
|
|
p->sched_class->put_prev_task(rq, p);
|
|
|
|
p->sched_reset_on_fork = reset_on_fork;
|
|
|
|
oldprio = p->prio;
|
|
prev_class = p->sched_class;
|
|
__setscheduler(rq, p, policy, param->sched_priority);
|
|
|
|
if (running)
|
|
p->sched_class->set_curr_task(rq);
|
|
if (on_rq)
|
|
activate_task(rq, p, 0);
|
|
|
|
check_class_changed(rq, p, prev_class, oldprio);
|
|
__task_rq_unlock(rq);
|
|
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
|
|
|
|
rt_mutex_adjust_pi(p);
|
|
|
|
return 0;
|
|
}
|
|
|
|
/**
|
|
* sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
|
|
* @p: the task in question.
|
|
* @policy: new policy.
|
|
* @param: structure containing the new RT priority.
|
|
*
|
|
* NOTE that the task may be already dead.
|
|
*/
|
|
int sched_setscheduler(struct task_struct *p, int policy,
|
|
const struct sched_param *param)
|
|
{
|
|
return __sched_setscheduler(p, policy, param, true);
|
|
}
|
|
EXPORT_SYMBOL_GPL(sched_setscheduler);
|
|
|
|
/**
|
|
* sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
|
|
* @p: the task in question.
|
|
* @policy: new policy.
|
|
* @param: structure containing the new RT priority.
|
|
*
|
|
* Just like sched_setscheduler, only don't bother checking if the
|
|
* current context has permission. For example, this is needed in
|
|
* stop_machine(): we create temporary high priority worker threads,
|
|
* but our caller might not have that capability.
|
|
*/
|
|
int sched_setscheduler_nocheck(struct task_struct *p, int policy,
|
|
const struct sched_param *param)
|
|
{
|
|
return __sched_setscheduler(p, policy, param, false);
|
|
}
|
|
|
|
static int
|
|
do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
|
|
{
|
|
struct sched_param lparam;
|
|
struct task_struct *p;
|
|
int retval;
|
|
|
|
if (!param || pid < 0)
|
|
return -EINVAL;
|
|
if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
|
|
return -EFAULT;
|
|
|
|
rcu_read_lock();
|
|
retval = -ESRCH;
|
|
p = find_process_by_pid(pid);
|
|
if (p != NULL)
|
|
retval = sched_setscheduler(p, policy, &lparam);
|
|
rcu_read_unlock();
|
|
|
|
return retval;
|
|
}
|
|
|
|
/**
|
|
* sys_sched_setscheduler - set/change the scheduler policy and RT priority
|
|
* @pid: the pid in question.
|
|
* @policy: new policy.
|
|
* @param: structure containing the new RT priority.
|
|
*/
|
|
SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy,
|
|
struct sched_param __user *, param)
|
|
{
|
|
/* negative values for policy are not valid */
|
|
if (policy < 0)
|
|
return -EINVAL;
|
|
|
|
return do_sched_setscheduler(pid, policy, param);
|
|
}
|
|
|
|
/**
|
|
* sys_sched_setparam - set/change the RT priority of a thread
|
|
* @pid: the pid in question.
|
|
* @param: structure containing the new RT priority.
|
|
*/
|
|
SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
|
|
{
|
|
return do_sched_setscheduler(pid, -1, param);
|
|
}
|
|
|
|
/**
|
|
* sys_sched_getscheduler - get the policy (scheduling class) of a thread
|
|
* @pid: the pid in question.
|
|
*/
|
|
SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
|
|
{
|
|
struct task_struct *p;
|
|
int retval;
|
|
|
|
if (pid < 0)
|
|
return -EINVAL;
|
|
|
|
retval = -ESRCH;
|
|
rcu_read_lock();
|
|
p = find_process_by_pid(pid);
|
|
if (p) {
|
|
retval = security_task_getscheduler(p);
|
|
if (!retval)
|
|
retval = p->policy
|
|
| (p->sched_reset_on_fork ? SCHED_RESET_ON_FORK : 0);
|
|
}
|
|
rcu_read_unlock();
|
|
return retval;
|
|
}
|
|
|
|
/**
|
|
* sys_sched_getparam - get the RT priority of a thread
|
|
* @pid: the pid in question.
|
|
* @param: structure containing the RT priority.
|
|
*/
|
|
SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
|
|
{
|
|
struct sched_param lp;
|
|
struct task_struct *p;
|
|
int retval;
|
|
|
|
if (!param || pid < 0)
|
|
return -EINVAL;
|
|
|
|
rcu_read_lock();
|
|
p = find_process_by_pid(pid);
|
|
retval = -ESRCH;
|
|
if (!p)
|
|
goto out_unlock;
|
|
|
|
retval = security_task_getscheduler(p);
|
|
if (retval)
|
|
goto out_unlock;
|
|
|
|
lp.sched_priority = p->rt_priority;
|
|
rcu_read_unlock();
|
|
|
|
/*
|
|
* This one might sleep, we cannot do it with a spinlock held ...
|
|
*/
|
|
retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
|
|
|
|
return retval;
|
|
|
|
out_unlock:
|
|
rcu_read_unlock();
|
|
return retval;
|
|
}
|
|
|
|
long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
|
|
{
|
|
cpumask_var_t cpus_allowed, new_mask;
|
|
struct task_struct *p;
|
|
int retval;
|
|
|
|
get_online_cpus();
|
|
rcu_read_lock();
|
|
|
|
p = find_process_by_pid(pid);
|
|
if (!p) {
|
|
rcu_read_unlock();
|
|
put_online_cpus();
|
|
return -ESRCH;
|
|
}
|
|
|
|
/* Prevent p going away */
|
|
get_task_struct(p);
|
|
rcu_read_unlock();
|
|
|
|
if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
|
|
retval = -ENOMEM;
|
|
goto out_put_task;
|
|
}
|
|
if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
|
|
retval = -ENOMEM;
|
|
goto out_free_cpus_allowed;
|
|
}
|
|
retval = -EPERM;
|
|
if (!check_same_owner(p) && !task_ns_capable(p, CAP_SYS_NICE))
|
|
goto out_unlock;
|
|
|
|
retval = security_task_setscheduler(p);
|
|
if (retval)
|
|
goto out_unlock;
|
|
|
|
cpuset_cpus_allowed(p, cpus_allowed);
|
|
cpumask_and(new_mask, in_mask, cpus_allowed);
|
|
again:
|
|
retval = set_cpus_allowed_ptr(p, new_mask);
|
|
|
|
if (!retval) {
|
|
cpuset_cpus_allowed(p, cpus_allowed);
|
|
if (!cpumask_subset(new_mask, cpus_allowed)) {
|
|
/*
|
|
* We must have raced with a concurrent cpuset
|
|
* update. Just reset the cpus_allowed to the
|
|
* cpuset's cpus_allowed
|
|
*/
|
|
cpumask_copy(new_mask, cpus_allowed);
|
|
goto again;
|
|
}
|
|
}
|
|
out_unlock:
|
|
free_cpumask_var(new_mask);
|
|
out_free_cpus_allowed:
|
|
free_cpumask_var(cpus_allowed);
|
|
out_put_task:
|
|
put_task_struct(p);
|
|
put_online_cpus();
|
|
return retval;
|
|
}
|
|
|
|
static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
|
|
struct cpumask *new_mask)
|
|
{
|
|
if (len < cpumask_size())
|
|
cpumask_clear(new_mask);
|
|
else if (len > cpumask_size())
|
|
len = cpumask_size();
|
|
|
|
return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0;
|
|
}
|
|
|
|
/**
|
|
* sys_sched_setaffinity - set the cpu affinity of a process
|
|
* @pid: pid of the process
|
|
* @len: length in bytes of the bitmask pointed to by user_mask_ptr
|
|
* @user_mask_ptr: user-space pointer to the new cpu mask
|
|
*/
|
|
SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
|
|
unsigned long __user *, user_mask_ptr)
|
|
{
|
|
cpumask_var_t new_mask;
|
|
int retval;
|
|
|
|
if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
|
|
return -ENOMEM;
|
|
|
|
retval = get_user_cpu_mask(user_mask_ptr, len, new_mask);
|
|
if (retval == 0)
|
|
retval = sched_setaffinity(pid, new_mask);
|
|
free_cpumask_var(new_mask);
|
|
return retval;
|
|
}
|
|
|
|
long sched_getaffinity(pid_t pid, struct cpumask *mask)
|
|
{
|
|
struct task_struct *p;
|
|
unsigned long flags;
|
|
struct rq *rq;
|
|
int retval;
|
|
|
|
get_online_cpus();
|
|
rcu_read_lock();
|
|
|
|
retval = -ESRCH;
|
|
p = find_process_by_pid(pid);
|
|
if (!p)
|
|
goto out_unlock;
|
|
|
|
retval = security_task_getscheduler(p);
|
|
if (retval)
|
|
goto out_unlock;
|
|
|
|
rq = task_rq_lock(p, &flags);
|
|
cpumask_and(mask, &p->cpus_allowed, cpu_online_mask);
|
|
task_rq_unlock(rq, &flags);
|
|
|
|
out_unlock:
|
|
rcu_read_unlock();
|
|
put_online_cpus();
|
|
|
|
return retval;
|
|
}
|
|
|
|
/**
|
|
* sys_sched_getaffinity - get the cpu affinity of a process
|
|
* @pid: pid of the process
|
|
* @len: length in bytes of the bitmask pointed to by user_mask_ptr
|
|
* @user_mask_ptr: user-space pointer to hold the current cpu mask
|
|
*/
|
|
SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
|
|
unsigned long __user *, user_mask_ptr)
|
|
{
|
|
int ret;
|
|
cpumask_var_t mask;
|
|
|
|
if ((len * BITS_PER_BYTE) < nr_cpu_ids)
|
|
return -EINVAL;
|
|
if (len & (sizeof(unsigned long)-1))
|
|
return -EINVAL;
|
|
|
|
if (!alloc_cpumask_var(&mask, GFP_KERNEL))
|
|
return -ENOMEM;
|
|
|
|
ret = sched_getaffinity(pid, mask);
|
|
if (ret == 0) {
|
|
size_t retlen = min_t(size_t, len, cpumask_size());
|
|
|
|
if (copy_to_user(user_mask_ptr, mask, retlen))
|
|
ret = -EFAULT;
|
|
else
|
|
ret = retlen;
|
|
}
|
|
free_cpumask_var(mask);
|
|
|
|
return ret;
|
|
}
|
|
|
|
/**
|
|
* sys_sched_yield - yield the current processor to other threads.
|
|
*
|
|
* This function yields the current CPU to other tasks. If there are no
|
|
* other threads running on this CPU then this function will return.
|
|
*/
|
|
SYSCALL_DEFINE0(sched_yield)
|
|
{
|
|
struct rq *rq = this_rq_lock();
|
|
|
|
schedstat_inc(rq, yld_count);
|
|
current->sched_class->yield_task(rq);
|
|
|
|
/*
|
|
* Since we are going to call schedule() anyway, there's
|
|
* no need to preempt or enable interrupts:
|
|
*/
|
|
__release(rq->lock);
|
|
spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
|
|
do_raw_spin_unlock(&rq->lock);
|
|
preempt_enable_no_resched();
|
|
|
|
schedule();
|
|
|
|
return 0;
|
|
}
|
|
|
|
static inline int should_resched(void)
|
|
{
|
|
return need_resched() && !(preempt_count() & PREEMPT_ACTIVE);
|
|
}
|
|
|
|
static void __cond_resched(void)
|
|
{
|
|
add_preempt_count(PREEMPT_ACTIVE);
|
|
schedule();
|
|
sub_preempt_count(PREEMPT_ACTIVE);
|
|
}
|
|
|
|
int __sched _cond_resched(void)
|
|
{
|
|
if (should_resched()) {
|
|
__cond_resched();
|
|
return 1;
|
|
}
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(_cond_resched);
|
|
|
|
/*
|
|
* __cond_resched_lock() - if a reschedule is pending, drop the given lock,
|
|
* call schedule, and on return reacquire the lock.
|
|
*
|
|
* This works OK both with and without CONFIG_PREEMPT. We do strange low-level
|
|
* operations here to prevent schedule() from being called twice (once via
|
|
* spin_unlock(), once by hand).
|
|
*/
|
|
int __cond_resched_lock(spinlock_t *lock)
|
|
{
|
|
int resched = should_resched();
|
|
int ret = 0;
|
|
|
|
lockdep_assert_held(lock);
|
|
|
|
if (spin_needbreak(lock) || resched) {
|
|
spin_unlock(lock);
|
|
if (resched)
|
|
__cond_resched();
|
|
else
|
|
cpu_relax();
|
|
ret = 1;
|
|
spin_lock(lock);
|
|
}
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(__cond_resched_lock);
|
|
|
|
int __sched __cond_resched_softirq(void)
|
|
{
|
|
BUG_ON(!in_softirq());
|
|
|
|
if (should_resched()) {
|
|
local_bh_enable();
|
|
__cond_resched();
|
|
local_bh_disable();
|
|
return 1;
|
|
}
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(__cond_resched_softirq);
|
|
|
|
/**
|
|
* yield - yield the current processor to other threads.
|
|
*
|
|
* This is a shortcut for kernel-space yielding - it marks the
|
|
* thread runnable and calls sys_sched_yield().
|
|
*/
|
|
void __sched yield(void)
|
|
{
|
|
set_current_state(TASK_RUNNING);
|
|
sys_sched_yield();
|
|
}
|
|
EXPORT_SYMBOL(yield);
|
|
|
|
/**
|
|
* yield_to - yield the current processor to another thread in
|
|
* your thread group, or accelerate that thread toward the
|
|
* processor it's on.
|
|
* @p: target task
|
|
* @preempt: whether task preemption is allowed or not
|
|
*
|
|
* It's the caller's job to ensure that the target task struct
|
|
* can't go away on us before we can do any checks.
|
|
*
|
|
* Returns true if we indeed boosted the target task.
|
|
*/
|
|
bool __sched yield_to(struct task_struct *p, bool preempt)
|
|
{
|
|
struct task_struct *curr = current;
|
|
struct rq *rq, *p_rq;
|
|
unsigned long flags;
|
|
bool yielded = 0;
|
|
|
|
local_irq_save(flags);
|
|
rq = this_rq();
|
|
|
|
again:
|
|
p_rq = task_rq(p);
|
|
double_rq_lock(rq, p_rq);
|
|
while (task_rq(p) != p_rq) {
|
|
double_rq_unlock(rq, p_rq);
|
|
goto again;
|
|
}
|
|
|
|
if (!curr->sched_class->yield_to_task)
|
|
goto out;
|
|
|
|
if (curr->sched_class != p->sched_class)
|
|
goto out;
|
|
|
|
if (task_running(p_rq, p) || p->state)
|
|
goto out;
|
|
|
|
yielded = curr->sched_class->yield_to_task(rq, p, preempt);
|
|
if (yielded) {
|
|
schedstat_inc(rq, yld_count);
|
|
/*
|
|
* Make p's CPU reschedule; pick_next_entity takes care of
|
|
* fairness.
|
|
*/
|
|
if (preempt && rq != p_rq)
|
|
resched_task(p_rq->curr);
|
|
}
|
|
|
|
out:
|
|
double_rq_unlock(rq, p_rq);
|
|
local_irq_restore(flags);
|
|
|
|
if (yielded)
|
|
schedule();
|
|
|
|
return yielded;
|
|
}
|
|
EXPORT_SYMBOL_GPL(yield_to);
|
|
|
|
/*
|
|
* This task is about to go to sleep on IO. Increment rq->nr_iowait so
|
|
* that process accounting knows that this is a task in IO wait state.
|
|
*/
|
|
void __sched io_schedule(void)
|
|
{
|
|
struct rq *rq = raw_rq();
|
|
|
|
delayacct_blkio_start();
|
|
atomic_inc(&rq->nr_iowait);
|
|
blk_flush_plug(current);
|
|
current->in_iowait = 1;
|
|
schedule();
|
|
current->in_iowait = 0;
|
|
atomic_dec(&rq->nr_iowait);
|
|
delayacct_blkio_end();
|
|
}
|
|
EXPORT_SYMBOL(io_schedule);
|
|
|
|
long __sched io_schedule_timeout(long timeout)
|
|
{
|
|
struct rq *rq = raw_rq();
|
|
long ret;
|
|
|
|
delayacct_blkio_start();
|
|
atomic_inc(&rq->nr_iowait);
|
|
blk_flush_plug(current);
|
|
current->in_iowait = 1;
|
|
ret = schedule_timeout(timeout);
|
|
current->in_iowait = 0;
|
|
atomic_dec(&rq->nr_iowait);
|
|
delayacct_blkio_end();
|
|
return ret;
|
|
}
|
|
|
|
/**
|
|
* sys_sched_get_priority_max - return maximum RT priority.
|
|
* @policy: scheduling class.
|
|
*
|
|
* this syscall returns the maximum rt_priority that can be used
|
|
* by a given scheduling class.
|
|
*/
|
|
SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
|
|
{
|
|
int ret = -EINVAL;
|
|
|
|
switch (policy) {
|
|
case SCHED_FIFO:
|
|
case SCHED_RR:
|
|
ret = MAX_USER_RT_PRIO-1;
|
|
break;
|
|
case SCHED_NORMAL:
|
|
case SCHED_BATCH:
|
|
case SCHED_IDLE:
|
|
ret = 0;
|
|
break;
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
/**
|
|
* sys_sched_get_priority_min - return minimum RT priority.
|
|
* @policy: scheduling class.
|
|
*
|
|
* this syscall returns the minimum rt_priority that can be used
|
|
* by a given scheduling class.
|
|
*/
|
|
SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
|
|
{
|
|
int ret = -EINVAL;
|
|
|
|
switch (policy) {
|
|
case SCHED_FIFO:
|
|
case SCHED_RR:
|
|
ret = 1;
|
|
break;
|
|
case SCHED_NORMAL:
|
|
case SCHED_BATCH:
|
|
case SCHED_IDLE:
|
|
ret = 0;
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
/**
|
|
* sys_sched_rr_get_interval - return the default timeslice of a process.
|
|
* @pid: pid of the process.
|
|
* @interval: userspace pointer to the timeslice value.
|
|
*
|
|
* this syscall writes the default timeslice value of a given process
|
|
* into the user-space timespec buffer. A value of '0' means infinity.
|
|
*/
|
|
SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
|
|
struct timespec __user *, interval)
|
|
{
|
|
struct task_struct *p;
|
|
unsigned int time_slice;
|
|
unsigned long flags;
|
|
struct rq *rq;
|
|
int retval;
|
|
struct timespec t;
|
|
|
|
if (pid < 0)
|
|
return -EINVAL;
|
|
|
|
retval = -ESRCH;
|
|
rcu_read_lock();
|
|
p = find_process_by_pid(pid);
|
|
if (!p)
|
|
goto out_unlock;
|
|
|
|
retval = security_task_getscheduler(p);
|
|
if (retval)
|
|
goto out_unlock;
|
|
|
|
rq = task_rq_lock(p, &flags);
|
|
time_slice = p->sched_class->get_rr_interval(rq, p);
|
|
task_rq_unlock(rq, &flags);
|
|
|
|
rcu_read_unlock();
|
|
jiffies_to_timespec(time_slice, &t);
|
|
retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
|
|
return retval;
|
|
|
|
out_unlock:
|
|
rcu_read_unlock();
|
|
return retval;
|
|
}
|
|
|
|
static const char stat_nam[] = TASK_STATE_TO_CHAR_STR;
|
|
|
|
void sched_show_task(struct task_struct *p)
|
|
{
|
|
unsigned long free = 0;
|
|
unsigned state;
|
|
|
|
state = p->state ? __ffs(p->state) + 1 : 0;
|
|
printk(KERN_INFO "%-15.15s %c", p->comm,
|
|
state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?');
|
|
#if BITS_PER_LONG == 32
|
|
if (state == TASK_RUNNING)
|
|
printk(KERN_CONT " running ");
|
|
else
|
|
printk(KERN_CONT " %08lx ", thread_saved_pc(p));
|
|
#else
|
|
if (state == TASK_RUNNING)
|
|
printk(KERN_CONT " running task ");
|
|
else
|
|
printk(KERN_CONT " %016lx ", thread_saved_pc(p));
|
|
#endif
|
|
#ifdef CONFIG_DEBUG_STACK_USAGE
|
|
free = stack_not_used(p);
|
|
#endif
|
|
printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free,
|
|
task_pid_nr(p), task_pid_nr(p->real_parent),
|
|
(unsigned long)task_thread_info(p)->flags);
|
|
|
|
show_stack(p, NULL);
|
|
}
|
|
|
|
void show_state_filter(unsigned long state_filter)
|
|
{
|
|
struct task_struct *g, *p;
|
|
|
|
#if BITS_PER_LONG == 32
|
|
printk(KERN_INFO
|
|
" task PC stack pid father\n");
|
|
#else
|
|
printk(KERN_INFO
|
|
" task PC stack pid father\n");
|
|
#endif
|
|
read_lock(&tasklist_lock);
|
|
do_each_thread(g, p) {
|
|
/*
|
|
* reset the NMI-timeout, listing all files on a slow
|
|
* console might take a lot of time:
|
|
*/
|
|
touch_nmi_watchdog();
|
|
if (!state_filter || (p->state & state_filter))
|
|
sched_show_task(p);
|
|
} while_each_thread(g, p);
|
|
|
|
touch_all_softlockup_watchdogs();
|
|
|
|
#ifdef CONFIG_SCHED_DEBUG
|
|
sysrq_sched_debug_show();
|
|
#endif
|
|
read_unlock(&tasklist_lock);
|
|
/*
|
|
* Only show locks if all tasks are dumped:
|
|
*/
|
|
if (!state_filter)
|
|
debug_show_all_locks();
|
|
}
|
|
|
|
void __cpuinit init_idle_bootup_task(struct task_struct *idle)
|
|
{
|
|
idle->sched_class = &idle_sched_class;
|
|
}
|
|
|
|
/**
|
|
* init_idle - set up an idle thread for a given CPU
|
|
* @idle: task in question
|
|
* @cpu: cpu the idle task belongs to
|
|
*
|
|
* NOTE: this function does not set the idle thread's NEED_RESCHED
|
|
* flag, to make booting more robust.
|
|
*/
|
|
void __cpuinit init_idle(struct task_struct *idle, int cpu)
|
|
{
|
|
struct rq *rq = cpu_rq(cpu);
|
|
unsigned long flags;
|
|
|
|
raw_spin_lock_irqsave(&rq->lock, flags);
|
|
|
|
__sched_fork(idle);
|
|
idle->state = TASK_RUNNING;
|
|
idle->se.exec_start = sched_clock();
|
|
|
|
cpumask_copy(&idle->cpus_allowed, cpumask_of(cpu));
|
|
/*
|
|
* We're having a chicken and egg problem, even though we are
|
|
* holding rq->lock, the cpu isn't yet set to this cpu so the
|
|
* lockdep check in task_group() will fail.
|
|
*
|
|
* Similar case to sched_fork(). / Alternatively we could
|
|
* use task_rq_lock() here and obtain the other rq->lock.
|
|
*
|
|
* Silence PROVE_RCU
|
|
*/
|
|
rcu_read_lock();
|
|
__set_task_cpu(idle, cpu);
|
|
rcu_read_unlock();
|
|
|
|
rq->curr = rq->idle = idle;
|
|
#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
|
|
idle->oncpu = 1;
|
|
#endif
|
|
raw_spin_unlock_irqrestore(&rq->lock, flags);
|
|
|
|
/* Set the preempt count _outside_ the spinlocks! */
|
|
#if defined(CONFIG_PREEMPT)
|
|
task_thread_info(idle)->preempt_count = (idle->lock_depth >= 0);
|
|
#else
|
|
task_thread_info(idle)->preempt_count = 0;
|
|
#endif
|
|
/*
|
|
* The idle tasks have their own, simple scheduling class:
|
|
*/
|
|
idle->sched_class = &idle_sched_class;
|
|
ftrace_graph_init_idle_task(idle, cpu);
|
|
}
|
|
|
|
/*
|
|
* In a system that switches off the HZ timer nohz_cpu_mask
|
|
* indicates which cpus entered this state. This is used
|
|
* in the rcu update to wait only for active cpus. For system
|
|
* which do not switch off the HZ timer nohz_cpu_mask should
|
|
* always be CPU_BITS_NONE.
|
|
*/
|
|
cpumask_var_t nohz_cpu_mask;
|
|
|
|
/*
|
|
* 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 int get_update_sysctl_factor(void)
|
|
{
|
|
unsigned int cpus = min_t(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
|
|
}
|
|
|
|
static inline void sched_init_granularity(void)
|
|
{
|
|
update_sysctl();
|
|
}
|
|
|
|
#ifdef CONFIG_SMP
|
|
/*
|
|
* This is how migration works:
|
|
*
|
|
* 1) we invoke migration_cpu_stop() on the target CPU using
|
|
* stop_one_cpu().
|
|
* 2) stopper starts to run (implicitly forcing the migrated thread
|
|
* off the CPU)
|
|
* 3) it checks whether the migrated task is still in the wrong runqueue.
|
|
* 4) if it's in the wrong runqueue then the migration thread removes
|
|
* it and puts it into the right queue.
|
|
* 5) stopper completes and stop_one_cpu() returns and the migration
|
|
* is done.
|
|
*/
|
|
|
|
/*
|
|
* Change a given task's CPU affinity. Migrate the thread to a
|
|
* proper CPU and schedule it away if the CPU it's executing on
|
|
* is removed from the allowed bitmask.
|
|
*
|
|
* NOTE: the caller must have a valid reference to the task, the
|
|
* task must not exit() & deallocate itself prematurely. The
|
|
* call is not atomic; no spinlocks may be held.
|
|
*/
|
|
int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
|
|
{
|
|
unsigned long flags;
|
|
struct rq *rq;
|
|
unsigned int dest_cpu;
|
|
int ret = 0;
|
|
|
|
/*
|
|
* Serialize against TASK_WAKING so that ttwu() and wunt() can
|
|
* drop the rq->lock and still rely on ->cpus_allowed.
|
|
*/
|
|
again:
|
|
while (task_is_waking(p))
|
|
cpu_relax();
|
|
rq = task_rq_lock(p, &flags);
|
|
if (task_is_waking(p)) {
|
|
task_rq_unlock(rq, &flags);
|
|
goto again;
|
|
}
|
|
|
|
if (!cpumask_intersects(new_mask, cpu_active_mask)) {
|
|
ret = -EINVAL;
|
|
goto out;
|
|
}
|
|
|
|
if (unlikely((p->flags & PF_THREAD_BOUND) && p != current &&
|
|
!cpumask_equal(&p->cpus_allowed, new_mask))) {
|
|
ret = -EINVAL;
|
|
goto out;
|
|
}
|
|
|
|
if (p->sched_class->set_cpus_allowed)
|
|
p->sched_class->set_cpus_allowed(p, new_mask);
|
|
else {
|
|
cpumask_copy(&p->cpus_allowed, new_mask);
|
|
p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
|
|
}
|
|
|
|
/* Can the task run on the task's current CPU? If so, we're done */
|
|
if (cpumask_test_cpu(task_cpu(p), new_mask))
|
|
goto out;
|
|
|
|
dest_cpu = cpumask_any_and(cpu_active_mask, new_mask);
|
|
if (migrate_task(p, rq)) {
|
|
struct migration_arg arg = { p, dest_cpu };
|
|
/* Need help from migration thread: drop lock and wait. */
|
|
task_rq_unlock(rq, &flags);
|
|
stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
|
|
tlb_migrate_finish(p->mm);
|
|
return 0;
|
|
}
|
|
out:
|
|
task_rq_unlock(rq, &flags);
|
|
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
|
|
|
|
/*
|
|
* Move (not current) task off this cpu, onto dest cpu. We're doing
|
|
* this because either it can't run here any more (set_cpus_allowed()
|
|
* away from this CPU, or CPU going down), or because we're
|
|
* attempting to rebalance this task on exec (sched_exec).
|
|
*
|
|
* So we race with normal scheduler movements, but that's OK, as long
|
|
* as the task is no longer on this CPU.
|
|
*
|
|
* Returns non-zero if task was successfully migrated.
|
|
*/
|
|
static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
|
|
{
|
|
struct rq *rq_dest, *rq_src;
|
|
int ret = 0;
|
|
|
|
if (unlikely(!cpu_active(dest_cpu)))
|
|
return ret;
|
|
|
|
rq_src = cpu_rq(src_cpu);
|
|
rq_dest = cpu_rq(dest_cpu);
|
|
|
|
double_rq_lock(rq_src, rq_dest);
|
|
/* Already moved. */
|
|
if (task_cpu(p) != src_cpu)
|
|
goto done;
|
|
/* Affinity changed (again). */
|
|
if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
|
|
goto fail;
|
|
|
|
/*
|
|
* If we're not on a rq, the next wake-up will ensure we're
|
|
* placed properly.
|
|
*/
|
|
if (p->se.on_rq) {
|
|
deactivate_task(rq_src, p, 0);
|
|
set_task_cpu(p, dest_cpu);
|
|
activate_task(rq_dest, p, 0);
|
|
check_preempt_curr(rq_dest, p, 0);
|
|
}
|
|
done:
|
|
ret = 1;
|
|
fail:
|
|
double_rq_unlock(rq_src, rq_dest);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* migration_cpu_stop - this will be executed by a highprio stopper thread
|
|
* and performs thread migration by bumping thread off CPU then
|
|
* 'pushing' onto another runqueue.
|
|
*/
|
|
static int migration_cpu_stop(void *data)
|
|
{
|
|
struct migration_arg *arg = data;
|
|
|
|
/*
|
|
* The original target cpu might have gone down and we might
|
|
* be on another cpu but it doesn't matter.
|
|
*/
|
|
local_irq_disable();
|
|
__migrate_task(arg->task, raw_smp_processor_id(), arg->dest_cpu);
|
|
local_irq_enable();
|
|
return 0;
|
|
}
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
|
|
/*
|
|
* Ensures that the idle task is using init_mm right before its cpu goes
|
|
* offline.
|
|
*/
|
|
void idle_task_exit(void)
|
|
{
|
|
struct mm_struct *mm = current->active_mm;
|
|
|
|
BUG_ON(cpu_online(smp_processor_id()));
|
|
|
|
if (mm != &init_mm)
|
|
switch_mm(mm, &init_mm, current);
|
|
mmdrop(mm);
|
|
}
|
|
|
|
/*
|
|
* While a dead CPU has no uninterruptible tasks queued at this point,
|
|
* it might still have a nonzero ->nr_uninterruptible counter, because
|
|
* for performance reasons the counter is not stricly tracking tasks to
|
|
* their home CPUs. So we just add the counter to another CPU's counter,
|
|
* to keep the global sum constant after CPU-down:
|
|
*/
|
|
static void migrate_nr_uninterruptible(struct rq *rq_src)
|
|
{
|
|
struct rq *rq_dest = cpu_rq(cpumask_any(cpu_active_mask));
|
|
|
|
rq_dest->nr_uninterruptible += rq_src->nr_uninterruptible;
|
|
rq_src->nr_uninterruptible = 0;
|
|
}
|
|
|
|
/*
|
|
* remove the tasks which were accounted by rq from calc_load_tasks.
|
|
*/
|
|
static void calc_global_load_remove(struct rq *rq)
|
|
{
|
|
atomic_long_sub(rq->calc_load_active, &calc_load_tasks);
|
|
rq->calc_load_active = 0;
|
|
}
|
|
|
|
/*
|
|
* Migrate all tasks from the rq, sleeping tasks will be migrated by
|
|
* try_to_wake_up()->select_task_rq().
|
|
*
|
|
* Called with rq->lock held even though we'er in stop_machine() and
|
|
* there's no concurrency possible, we hold the required locks anyway
|
|
* because of lock validation efforts.
|
|
*/
|
|
static void migrate_tasks(unsigned int dead_cpu)
|
|
{
|
|
struct rq *rq = cpu_rq(dead_cpu);
|
|
struct task_struct *next, *stop = rq->stop;
|
|
int dest_cpu;
|
|
|
|
/*
|
|
* Fudge the rq selection such that the below task selection loop
|
|
* doesn't get stuck on the currently eligible stop task.
|
|
*
|
|
* We're currently inside stop_machine() and the rq is either stuck
|
|
* in the stop_machine_cpu_stop() loop, or we're executing this code,
|
|
* either way we should never end up calling schedule() until we're
|
|
* done here.
|
|
*/
|
|
rq->stop = NULL;
|
|
|
|
for ( ; ; ) {
|
|
/*
|
|
* There's this thread running, bail when that's the only
|
|
* remaining thread.
|
|
*/
|
|
if (rq->nr_running == 1)
|
|
break;
|
|
|
|
next = pick_next_task(rq);
|
|
BUG_ON(!next);
|
|
next->sched_class->put_prev_task(rq, next);
|
|
|
|
/* Find suitable destination for @next, with force if needed. */
|
|
dest_cpu = select_fallback_rq(dead_cpu, next);
|
|
raw_spin_unlock(&rq->lock);
|
|
|
|
__migrate_task(next, dead_cpu, dest_cpu);
|
|
|
|
raw_spin_lock(&rq->lock);
|
|
}
|
|
|
|
rq->stop = stop;
|
|
}
|
|
|
|
#endif /* CONFIG_HOTPLUG_CPU */
|
|
|
|
#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
|
|
|
|
static struct ctl_table sd_ctl_dir[] = {
|
|
{
|
|
.procname = "sched_domain",
|
|
.mode = 0555,
|
|
},
|
|
{}
|
|
};
|
|
|
|
static struct ctl_table sd_ctl_root[] = {
|
|
{
|
|
.procname = "kernel",
|
|
.mode = 0555,
|
|
.child = sd_ctl_dir,
|
|
},
|
|
{}
|
|
};
|
|
|
|
static struct ctl_table *sd_alloc_ctl_entry(int n)
|
|
{
|
|
struct ctl_table *entry =
|
|
kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL);
|
|
|
|
return entry;
|
|
}
|
|
|
|
static void sd_free_ctl_entry(struct ctl_table **tablep)
|
|
{
|
|
struct ctl_table *entry;
|
|
|
|
/*
|
|
* In the intermediate directories, both the child directory and
|
|
* procname are dynamically allocated and could fail but the mode
|
|
* will always be set. In the lowest directory the names are
|
|
* static strings and all have proc handlers.
|
|
*/
|
|
for (entry = *tablep; entry->mode; entry++) {
|
|
if (entry->child)
|
|
sd_free_ctl_entry(&entry->child);
|
|
if (entry->proc_handler == NULL)
|
|
kfree(entry->procname);
|
|
}
|
|
|
|
kfree(*tablep);
|
|
*tablep = NULL;
|
|
}
|
|
|
|
static void
|
|
set_table_entry(struct ctl_table *entry,
|
|
const char *procname, void *data, int maxlen,
|
|
mode_t mode, proc_handler *proc_handler)
|
|
{
|
|
entry->procname = procname;
|
|
entry->data = data;
|
|
entry->maxlen = maxlen;
|
|
entry->mode = mode;
|
|
entry->proc_handler = proc_handler;
|
|
}
|
|
|
|
static struct ctl_table *
|
|
sd_alloc_ctl_domain_table(struct sched_domain *sd)
|
|
{
|
|
struct ctl_table *table = sd_alloc_ctl_entry(13);
|
|
|
|
if (table == NULL)
|
|
return NULL;
|
|
|
|
set_table_entry(&table[0], "min_interval", &sd->min_interval,
|
|
sizeof(long), 0644, proc_doulongvec_minmax);
|
|
set_table_entry(&table[1], "max_interval", &sd->max_interval,
|
|
sizeof(long), 0644, proc_doulongvec_minmax);
|
|
set_table_entry(&table[2], "busy_idx", &sd->busy_idx,
|
|
sizeof(int), 0644, proc_dointvec_minmax);
|
|
set_table_entry(&table[3], "idle_idx", &sd->idle_idx,
|
|
sizeof(int), 0644, proc_dointvec_minmax);
|
|
set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx,
|
|
sizeof(int), 0644, proc_dointvec_minmax);
|
|
set_table_entry(&table[5], "wake_idx", &sd->wake_idx,
|
|
sizeof(int), 0644, proc_dointvec_minmax);
|
|
set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx,
|
|
sizeof(int), 0644, proc_dointvec_minmax);
|
|
set_table_entry(&table[7], "busy_factor", &sd->busy_factor,
|
|
sizeof(int), 0644, proc_dointvec_minmax);
|
|
set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct,
|
|
sizeof(int), 0644, proc_dointvec_minmax);
|
|
set_table_entry(&table[9], "cache_nice_tries",
|
|
&sd->cache_nice_tries,
|
|
sizeof(int), 0644, proc_dointvec_minmax);
|
|
set_table_entry(&table[10], "flags", &sd->flags,
|
|
sizeof(int), 0644, proc_dointvec_minmax);
|
|
set_table_entry(&table[11], "name", sd->name,
|
|
CORENAME_MAX_SIZE, 0444, proc_dostring);
|
|
/* &table[12] is terminator */
|
|
|
|
return table;
|
|
}
|
|
|
|
static ctl_table *sd_alloc_ctl_cpu_table(int cpu)
|
|
{
|
|
struct ctl_table *entry, *table;
|
|
struct sched_domain *sd;
|
|
int domain_num = 0, i;
|
|
char buf[32];
|
|
|
|
for_each_domain(cpu, sd)
|
|
domain_num++;
|
|
entry = table = sd_alloc_ctl_entry(domain_num + 1);
|
|
if (table == NULL)
|
|
return NULL;
|
|
|
|
i = 0;
|
|
for_each_domain(cpu, sd) {
|
|
snprintf(buf, 32, "domain%d", i);
|
|
entry->procname = kstrdup(buf, GFP_KERNEL);
|
|
entry->mode = 0555;
|
|
entry->child = sd_alloc_ctl_domain_table(sd);
|
|
entry++;
|
|
i++;
|
|
}
|
|
return table;
|
|
}
|
|
|
|
static struct ctl_table_header *sd_sysctl_header;
|
|
static void register_sched_domain_sysctl(void)
|
|
{
|
|
int i, cpu_num = num_possible_cpus();
|
|
struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
|
|
char buf[32];
|
|
|
|
WARN_ON(sd_ctl_dir[0].child);
|
|
sd_ctl_dir[0].child = entry;
|
|
|
|
if (entry == NULL)
|
|
return;
|
|
|
|
for_each_possible_cpu(i) {
|
|
snprintf(buf, 32, "cpu%d", i);
|
|
entry->procname = kstrdup(buf, GFP_KERNEL);
|
|
entry->mode = 0555;
|
|
entry->child = sd_alloc_ctl_cpu_table(i);
|
|
entry++;
|
|
}
|
|
|
|
WARN_ON(sd_sysctl_header);
|
|
sd_sysctl_header = register_sysctl_table(sd_ctl_root);
|
|
}
|
|
|
|
/* may be called multiple times per register */
|
|
static void unregister_sched_domain_sysctl(void)
|
|
{
|
|
if (sd_sysctl_header)
|
|
unregister_sysctl_table(sd_sysctl_header);
|
|
sd_sysctl_header = NULL;
|
|
if (sd_ctl_dir[0].child)
|
|
sd_free_ctl_entry(&sd_ctl_dir[0].child);
|
|
}
|
|
#else
|
|
static void register_sched_domain_sysctl(void)
|
|
{
|
|
}
|
|
static void unregister_sched_domain_sysctl(void)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
static void set_rq_online(struct rq *rq)
|
|
{
|
|
if (!rq->online) {
|
|
const struct sched_class *class;
|
|
|
|
cpumask_set_cpu(rq->cpu, rq->rd->online);
|
|
rq->online = 1;
|
|
|
|
for_each_class(class) {
|
|
if (class->rq_online)
|
|
class->rq_online(rq);
|
|
}
|
|
}
|
|
}
|
|
|
|
static void set_rq_offline(struct rq *rq)
|
|
{
|
|
if (rq->online) {
|
|
const struct sched_class *class;
|
|
|
|
for_each_class(class) {
|
|
if (class->rq_offline)
|
|
class->rq_offline(rq);
|
|
}
|
|
|
|
cpumask_clear_cpu(rq->cpu, rq->rd->online);
|
|
rq->online = 0;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* migration_call - callback that gets triggered when a CPU is added.
|
|
* Here we can start up the necessary migration thread for the new CPU.
|
|
*/
|
|
static int __cpuinit
|
|
migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
|
|
{
|
|
int cpu = (long)hcpu;
|
|
unsigned long flags;
|
|
struct rq *rq = cpu_rq(cpu);
|
|
|
|
switch (action & ~CPU_TASKS_FROZEN) {
|
|
|
|
case CPU_UP_PREPARE:
|
|
rq->calc_load_update = calc_load_update;
|
|
break;
|
|
|
|
case CPU_ONLINE:
|
|
/* Update our root-domain */
|
|
raw_spin_lock_irqsave(&rq->lock, flags);
|
|
if (rq->rd) {
|
|
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
|
|
|
|
set_rq_online(rq);
|
|
}
|
|
raw_spin_unlock_irqrestore(&rq->lock, flags);
|
|
break;
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
case CPU_DYING:
|
|
/* Update our root-domain */
|
|
raw_spin_lock_irqsave(&rq->lock, flags);
|
|
if (rq->rd) {
|
|
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
|
|
set_rq_offline(rq);
|
|
}
|
|
migrate_tasks(cpu);
|
|
BUG_ON(rq->nr_running != 1); /* the migration thread */
|
|
raw_spin_unlock_irqrestore(&rq->lock, flags);
|
|
|
|
migrate_nr_uninterruptible(rq);
|
|
calc_global_load_remove(rq);
|
|
break;
|
|
#endif
|
|
}
|
|
|
|
update_max_interval();
|
|
|
|
return NOTIFY_OK;
|
|
}
|
|
|
|
/*
|
|
* Register at high priority so that task migration (migrate_all_tasks)
|
|
* happens before everything else. This has to be lower priority than
|
|
* the notifier in the perf_event subsystem, though.
|
|
*/
|
|
static struct notifier_block __cpuinitdata migration_notifier = {
|
|
.notifier_call = migration_call,
|
|
.priority = CPU_PRI_MIGRATION,
|
|
};
|
|
|
|
static int __cpuinit sched_cpu_active(struct notifier_block *nfb,
|
|
unsigned long action, void *hcpu)
|
|
{
|
|
switch (action & ~CPU_TASKS_FROZEN) {
|
|
case CPU_ONLINE:
|
|
case CPU_DOWN_FAILED:
|
|
set_cpu_active((long)hcpu, true);
|
|
return NOTIFY_OK;
|
|
default:
|
|
return NOTIFY_DONE;
|
|
}
|
|
}
|
|
|
|
static int __cpuinit sched_cpu_inactive(struct notifier_block *nfb,
|
|
unsigned long action, void *hcpu)
|
|
{
|
|
switch (action & ~CPU_TASKS_FROZEN) {
|
|
case CPU_DOWN_PREPARE:
|
|
set_cpu_active((long)hcpu, false);
|
|
return NOTIFY_OK;
|
|
default:
|
|
return NOTIFY_DONE;
|
|
}
|
|
}
|
|
|
|
static int __init migration_init(void)
|
|
{
|
|
void *cpu = (void *)(long)smp_processor_id();
|
|
int err;
|
|
|
|
/* Initialize migration for the boot CPU */
|
|
err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
|
|
BUG_ON(err == NOTIFY_BAD);
|
|
migration_call(&migration_notifier, CPU_ONLINE, cpu);
|
|
register_cpu_notifier(&migration_notifier);
|
|
|
|
/* Register cpu active notifiers */
|
|
cpu_notifier(sched_cpu_active, CPU_PRI_SCHED_ACTIVE);
|
|
cpu_notifier(sched_cpu_inactive, CPU_PRI_SCHED_INACTIVE);
|
|
|
|
return 0;
|
|
}
|
|
early_initcall(migration_init);
|
|
#endif
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
#ifdef CONFIG_SCHED_DEBUG
|
|
|
|
static __read_mostly int sched_domain_debug_enabled;
|
|
|
|
static int __init sched_domain_debug_setup(char *str)
|
|
{
|
|
sched_domain_debug_enabled = 1;
|
|
|
|
return 0;
|
|
}
|
|
early_param("sched_debug", sched_domain_debug_setup);
|
|
|
|
static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
|
|
struct cpumask *groupmask)
|
|
{
|
|
struct sched_group *group = sd->groups;
|
|
char str[256];
|
|
|
|
cpulist_scnprintf(str, sizeof(str), sched_domain_span(sd));
|
|
cpumask_clear(groupmask);
|
|
|
|
printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
|
|
|
|
if (!(sd->flags & SD_LOAD_BALANCE)) {
|
|
printk("does not load-balance\n");
|
|
if (sd->parent)
|
|
printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain"
|
|
" has parent");
|
|
return -1;
|
|
}
|
|
|
|
printk(KERN_CONT "span %s level %s\n", str, sd->name);
|
|
|
|
if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
|
|
printk(KERN_ERR "ERROR: domain->span does not contain "
|
|
"CPU%d\n", cpu);
|
|
}
|
|
if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) {
|
|
printk(KERN_ERR "ERROR: domain->groups does not contain"
|
|
" CPU%d\n", cpu);
|
|
}
|
|
|
|
printk(KERN_DEBUG "%*s groups:", level + 1, "");
|
|
do {
|
|
if (!group) {
|
|
printk("\n");
|
|
printk(KERN_ERR "ERROR: group is NULL\n");
|
|
break;
|
|
}
|
|
|
|
if (!group->cpu_power) {
|
|
printk(KERN_CONT "\n");
|
|
printk(KERN_ERR "ERROR: domain->cpu_power not "
|
|
"set\n");
|
|
break;
|
|
}
|
|
|
|
if (!cpumask_weight(sched_group_cpus(group))) {
|
|
printk(KERN_CONT "\n");
|
|
printk(KERN_ERR "ERROR: empty group\n");
|
|
break;
|
|
}
|
|
|
|
if (cpumask_intersects(groupmask, sched_group_cpus(group))) {
|
|
printk(KERN_CONT "\n");
|
|
printk(KERN_ERR "ERROR: repeated CPUs\n");
|
|
break;
|
|
}
|
|
|
|
cpumask_or(groupmask, groupmask, sched_group_cpus(group));
|
|
|
|
cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
|
|
|
|
printk(KERN_CONT " %s", str);
|
|
if (group->cpu_power != SCHED_LOAD_SCALE) {
|
|
printk(KERN_CONT " (cpu_power = %d)",
|
|
group->cpu_power);
|
|
}
|
|
|
|
group = group->next;
|
|
} while (group != sd->groups);
|
|
printk(KERN_CONT "\n");
|
|
|
|
if (!cpumask_equal(sched_domain_span(sd), groupmask))
|
|
printk(KERN_ERR "ERROR: groups don't span domain->span\n");
|
|
|
|
if (sd->parent &&
|
|
!cpumask_subset(groupmask, sched_domain_span(sd->parent)))
|
|
printk(KERN_ERR "ERROR: parent span is not a superset "
|
|
"of domain->span\n");
|
|
return 0;
|
|
}
|
|
|
|
static void sched_domain_debug(struct sched_domain *sd, int cpu)
|
|
{
|
|
cpumask_var_t groupmask;
|
|
int level = 0;
|
|
|
|
if (!sched_domain_debug_enabled)
|
|
return;
|
|
|
|
if (!sd) {
|
|
printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
|
|
return;
|
|
}
|
|
|
|
printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
|
|
|
|
if (!alloc_cpumask_var(&groupmask, GFP_KERNEL)) {
|
|
printk(KERN_DEBUG "Cannot load-balance (out of memory)\n");
|
|
return;
|
|
}
|
|
|
|
for (;;) {
|
|
if (sched_domain_debug_one(sd, cpu, level, groupmask))
|
|
break;
|
|
level++;
|
|
sd = sd->parent;
|
|
if (!sd)
|
|
break;
|
|
}
|
|
free_cpumask_var(groupmask);
|
|
}
|
|
#else /* !CONFIG_SCHED_DEBUG */
|
|
# define sched_domain_debug(sd, cpu) do { } while (0)
|
|
#endif /* CONFIG_SCHED_DEBUG */
|
|
|
|
static int sd_degenerate(struct sched_domain *sd)
|
|
{
|
|
if (cpumask_weight(sched_domain_span(sd)) == 1)
|
|
return 1;
|
|
|
|
/* Following flags need at least 2 groups */
|
|
if (sd->flags & (SD_LOAD_BALANCE |
|
|
SD_BALANCE_NEWIDLE |
|
|
SD_BALANCE_FORK |
|
|
SD_BALANCE_EXEC |
|
|
SD_SHARE_CPUPOWER |
|
|
SD_SHARE_PKG_RESOURCES)) {
|
|
if (sd->groups != sd->groups->next)
|
|
return 0;
|
|
}
|
|
|
|
/* Following flags don't use groups */
|
|
if (sd->flags & (SD_WAKE_AFFINE))
|
|
return 0;
|
|
|
|
return 1;
|
|
}
|
|
|
|
static int
|
|
sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
|
|
{
|
|
unsigned long cflags = sd->flags, pflags = parent->flags;
|
|
|
|
if (sd_degenerate(parent))
|
|
return 1;
|
|
|
|
if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent)))
|
|
return 0;
|
|
|
|
/* Flags needing groups don't count if only 1 group in parent */
|
|
if (parent->groups == parent->groups->next) {
|
|
pflags &= ~(SD_LOAD_BALANCE |
|
|
SD_BALANCE_NEWIDLE |
|
|
SD_BALANCE_FORK |
|
|
SD_BALANCE_EXEC |
|
|
SD_SHARE_CPUPOWER |
|
|
SD_SHARE_PKG_RESOURCES);
|
|
if (nr_node_ids == 1)
|
|
pflags &= ~SD_SERIALIZE;
|
|
}
|
|
if (~cflags & pflags)
|
|
return 0;
|
|
|
|
return 1;
|
|
}
|
|
|
|
static void free_rootdomain(struct root_domain *rd)
|
|
{
|
|
synchronize_sched();
|
|
|
|
cpupri_cleanup(&rd->cpupri);
|
|
|
|
free_cpumask_var(rd->rto_mask);
|
|
free_cpumask_var(rd->online);
|
|
free_cpumask_var(rd->span);
|
|
kfree(rd);
|
|
}
|
|
|
|
static void rq_attach_root(struct rq *rq, struct root_domain *rd)
|
|
{
|
|
struct root_domain *old_rd = NULL;
|
|
unsigned long flags;
|
|
|
|
raw_spin_lock_irqsave(&rq->lock, flags);
|
|
|
|
if (rq->rd) {
|
|
old_rd = rq->rd;
|
|
|
|
if (cpumask_test_cpu(rq->cpu, old_rd->online))
|
|
set_rq_offline(rq);
|
|
|
|
cpumask_clear_cpu(rq->cpu, old_rd->span);
|
|
|
|
/*
|
|
* If we dont want to free the old_rt yet then
|
|
* set old_rd to NULL to skip the freeing later
|
|
* in this function:
|
|
*/
|
|
if (!atomic_dec_and_test(&old_rd->refcount))
|
|
old_rd = NULL;
|
|
}
|
|
|
|
atomic_inc(&rd->refcount);
|
|
rq->rd = rd;
|
|
|
|
cpumask_set_cpu(rq->cpu, rd->span);
|
|
if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
|
|
set_rq_online(rq);
|
|
|
|
raw_spin_unlock_irqrestore(&rq->lock, flags);
|
|
|
|
if (old_rd)
|
|
free_rootdomain(old_rd);
|
|
}
|
|
|
|
static int init_rootdomain(struct root_domain *rd)
|
|
{
|
|
memset(rd, 0, sizeof(*rd));
|
|
|
|
if (!alloc_cpumask_var(&rd->span, GFP_KERNEL))
|
|
goto out;
|
|
if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
|
|
goto free_span;
|
|
if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
|
|
goto free_online;
|
|
|
|
if (cpupri_init(&rd->cpupri) != 0)
|
|
goto free_rto_mask;
|
|
return 0;
|
|
|
|
free_rto_mask:
|
|
free_cpumask_var(rd->rto_mask);
|
|
free_online:
|
|
free_cpumask_var(rd->online);
|
|
free_span:
|
|
free_cpumask_var(rd->span);
|
|
out:
|
|
return -ENOMEM;
|
|
}
|
|
|
|
static void init_defrootdomain(void)
|
|
{
|
|
init_rootdomain(&def_root_domain);
|
|
|
|
atomic_set(&def_root_domain.refcount, 1);
|
|
}
|
|
|
|
static struct root_domain *alloc_rootdomain(void)
|
|
{
|
|
struct root_domain *rd;
|
|
|
|
rd = kmalloc(sizeof(*rd), GFP_KERNEL);
|
|
if (!rd)
|
|
return NULL;
|
|
|
|
if (init_rootdomain(rd) != 0) {
|
|
kfree(rd);
|
|
return NULL;
|
|
}
|
|
|
|
return rd;
|
|
}
|
|
|
|
/*
|
|
* Attach the domain 'sd' to 'cpu' as its base domain. Callers must
|
|
* hold the hotplug lock.
|
|
*/
|
|
static void
|
|
cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
|
|
{
|
|
struct rq *rq = cpu_rq(cpu);
|
|
struct sched_domain *tmp;
|
|
|
|
for (tmp = sd; tmp; tmp = tmp->parent)
|
|
tmp->span_weight = cpumask_weight(sched_domain_span(tmp));
|
|
|
|
/* Remove the sched domains which do not contribute to scheduling. */
|
|
for (tmp = sd; tmp; ) {
|
|
struct sched_domain *parent = tmp->parent;
|
|
if (!parent)
|
|
break;
|
|
|
|
if (sd_parent_degenerate(tmp, parent)) {
|
|
tmp->parent = parent->parent;
|
|
if (parent->parent)
|
|
parent->parent->child = tmp;
|
|
} else
|
|
tmp = tmp->parent;
|
|
}
|
|
|
|
if (sd && sd_degenerate(sd)) {
|
|
sd = sd->parent;
|
|
if (sd)
|
|
sd->child = NULL;
|
|
}
|
|
|
|
sched_domain_debug(sd, cpu);
|
|
|
|
rq_attach_root(rq, rd);
|
|
rcu_assign_pointer(rq->sd, sd);
|
|
}
|
|
|
|
/* cpus with isolated domains */
|
|
static cpumask_var_t cpu_isolated_map;
|
|
|
|
/* Setup the mask of cpus configured for isolated domains */
|
|
static int __init isolated_cpu_setup(char *str)
|
|
{
|
|
alloc_bootmem_cpumask_var(&cpu_isolated_map);
|
|
cpulist_parse(str, cpu_isolated_map);
|
|
return 1;
|
|
}
|
|
|
|
__setup("isolcpus=", isolated_cpu_setup);
|
|
|
|
/*
|
|
* init_sched_build_groups takes the cpumask we wish to span, and a pointer
|
|
* to a function which identifies what group(along with sched group) a CPU
|
|
* belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids
|
|
* (due to the fact that we keep track of groups covered with a struct cpumask).
|
|
*
|
|
* init_sched_build_groups will build a circular linked list of the groups
|
|
* covered by the given span, and will set each group's ->cpumask correctly,
|
|
* and ->cpu_power to 0.
|
|
*/
|
|
static void
|
|
init_sched_build_groups(const struct cpumask *span,
|
|
const struct cpumask *cpu_map,
|
|
int (*group_fn)(int cpu, const struct cpumask *cpu_map,
|
|
struct sched_group **sg,
|
|
struct cpumask *tmpmask),
|
|
struct cpumask *covered, struct cpumask *tmpmask)
|
|
{
|
|
struct sched_group *first = NULL, *last = NULL;
|
|
int i;
|
|
|
|
cpumask_clear(covered);
|
|
|
|
for_each_cpu(i, span) {
|
|
struct sched_group *sg;
|
|
int group = group_fn(i, cpu_map, &sg, tmpmask);
|
|
int j;
|
|
|
|
if (cpumask_test_cpu(i, covered))
|
|
continue;
|
|
|
|
cpumask_clear(sched_group_cpus(sg));
|
|
sg->cpu_power = 0;
|
|
|
|
for_each_cpu(j, span) {
|
|
if (group_fn(j, cpu_map, NULL, tmpmask) != group)
|
|
continue;
|
|
|
|
cpumask_set_cpu(j, covered);
|
|
cpumask_set_cpu(j, sched_group_cpus(sg));
|
|
}
|
|
if (!first)
|
|
first = sg;
|
|
if (last)
|
|
last->next = sg;
|
|
last = sg;
|
|
}
|
|
last->next = first;
|
|
}
|
|
|
|
#define SD_NODES_PER_DOMAIN 16
|
|
|
|
#ifdef CONFIG_NUMA
|
|
|
|
/**
|
|
* find_next_best_node - find the next node to include in a sched_domain
|
|
* @node: node whose sched_domain we're building
|
|
* @used_nodes: nodes already in the sched_domain
|
|
*
|
|
* Find the next node to include in a given scheduling domain. Simply
|
|
* finds the closest node not already in the @used_nodes map.
|
|
*
|
|
* Should use nodemask_t.
|
|
*/
|
|
static int find_next_best_node(int node, nodemask_t *used_nodes)
|
|
{
|
|
int i, n, val, min_val, best_node = 0;
|
|
|
|
min_val = INT_MAX;
|
|
|
|
for (i = 0; i < nr_node_ids; i++) {
|
|
/* Start at @node */
|
|
n = (node + i) % nr_node_ids;
|
|
|
|
if (!nr_cpus_node(n))
|
|
continue;
|
|
|
|
/* Skip already used nodes */
|
|
if (node_isset(n, *used_nodes))
|
|
continue;
|
|
|
|
/* Simple min distance search */
|
|
val = node_distance(node, n);
|
|
|
|
if (val < min_val) {
|
|
min_val = val;
|
|
best_node = n;
|
|
}
|
|
}
|
|
|
|
node_set(best_node, *used_nodes);
|
|
return best_node;
|
|
}
|
|
|
|
/**
|
|
* sched_domain_node_span - get a cpumask for a node's sched_domain
|
|
* @node: node whose cpumask we're constructing
|
|
* @span: resulting cpumask
|
|
*
|
|
* Given a node, construct a good cpumask for its sched_domain to span. It
|
|
* should be one that prevents unnecessary balancing, but also spreads tasks
|
|
* out optimally.
|
|
*/
|
|
static void sched_domain_node_span(int node, struct cpumask *span)
|
|
{
|
|
nodemask_t used_nodes;
|
|
int i;
|
|
|
|
cpumask_clear(span);
|
|
nodes_clear(used_nodes);
|
|
|
|
cpumask_or(span, span, cpumask_of_node(node));
|
|
node_set(node, used_nodes);
|
|
|
|
for (i = 1; i < SD_NODES_PER_DOMAIN; i++) {
|
|
int next_node = find_next_best_node(node, &used_nodes);
|
|
|
|
cpumask_or(span, span, cpumask_of_node(next_node));
|
|
}
|
|
}
|
|
#endif /* CONFIG_NUMA */
|
|
|
|
int sched_smt_power_savings = 0, sched_mc_power_savings = 0;
|
|
|
|
/*
|
|
* The cpus mask in sched_group and sched_domain hangs off the end.
|
|
*
|
|
* ( See the the comments in include/linux/sched.h:struct sched_group
|
|
* and struct sched_domain. )
|
|
*/
|
|
struct static_sched_group {
|
|
struct sched_group sg;
|
|
DECLARE_BITMAP(cpus, CONFIG_NR_CPUS);
|
|
};
|
|
|
|
struct static_sched_domain {
|
|
struct sched_domain sd;
|
|
DECLARE_BITMAP(span, CONFIG_NR_CPUS);
|
|
};
|
|
|
|
struct s_data {
|
|
#ifdef CONFIG_NUMA
|
|
int sd_allnodes;
|
|
cpumask_var_t domainspan;
|
|
cpumask_var_t covered;
|
|
cpumask_var_t notcovered;
|
|
#endif
|
|
cpumask_var_t nodemask;
|
|
cpumask_var_t this_sibling_map;
|
|
cpumask_var_t this_core_map;
|
|
cpumask_var_t this_book_map;
|
|
cpumask_var_t send_covered;
|
|
cpumask_var_t tmpmask;
|
|
struct sched_group **sched_group_nodes;
|
|
struct root_domain *rd;
|
|
};
|
|
|
|
enum s_alloc {
|
|
sa_sched_groups = 0,
|
|
sa_rootdomain,
|
|
sa_tmpmask,
|
|
sa_send_covered,
|
|
sa_this_book_map,
|
|
sa_this_core_map,
|
|
sa_this_sibling_map,
|
|
sa_nodemask,
|
|
sa_sched_group_nodes,
|
|
#ifdef CONFIG_NUMA
|
|
sa_notcovered,
|
|
sa_covered,
|
|
sa_domainspan,
|
|
#endif
|
|
sa_none,
|
|
};
|
|
|
|
/*
|
|
* SMT sched-domains:
|
|
*/
|
|
#ifdef CONFIG_SCHED_SMT
|
|
static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains);
|
|
static DEFINE_PER_CPU(struct static_sched_group, sched_groups);
|
|
|
|
static int
|
|
cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map,
|
|
struct sched_group **sg, struct cpumask *unused)
|
|
{
|
|
if (sg)
|
|
*sg = &per_cpu(sched_groups, cpu).sg;
|
|
return cpu;
|
|
}
|
|
#endif /* CONFIG_SCHED_SMT */
|
|
|
|
/*
|
|
* multi-core sched-domains:
|
|
*/
|
|
#ifdef CONFIG_SCHED_MC
|
|
static DEFINE_PER_CPU(struct static_sched_domain, core_domains);
|
|
static DEFINE_PER_CPU(struct static_sched_group, sched_group_core);
|
|
|
|
static int
|
|
cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
|
|
struct sched_group **sg, struct cpumask *mask)
|
|
{
|
|
int group;
|
|
#ifdef CONFIG_SCHED_SMT
|
|
cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
|
|
group = cpumask_first(mask);
|
|
#else
|
|
group = cpu;
|
|
#endif
|
|
if (sg)
|
|
*sg = &per_cpu(sched_group_core, group).sg;
|
|
return group;
|
|
}
|
|
#endif /* CONFIG_SCHED_MC */
|
|
|
|
/*
|
|
* book sched-domains:
|
|
*/
|
|
#ifdef CONFIG_SCHED_BOOK
|
|
static DEFINE_PER_CPU(struct static_sched_domain, book_domains);
|
|
static DEFINE_PER_CPU(struct static_sched_group, sched_group_book);
|
|
|
|
static int
|
|
cpu_to_book_group(int cpu, const struct cpumask *cpu_map,
|
|
struct sched_group **sg, struct cpumask *mask)
|
|
{
|
|
int group = cpu;
|
|
#ifdef CONFIG_SCHED_MC
|
|
cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
|
|
group = cpumask_first(mask);
|
|
#elif defined(CONFIG_SCHED_SMT)
|
|
cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
|
|
group = cpumask_first(mask);
|
|
#endif
|
|
if (sg)
|
|
*sg = &per_cpu(sched_group_book, group).sg;
|
|
return group;
|
|
}
|
|
#endif /* CONFIG_SCHED_BOOK */
|
|
|
|
static DEFINE_PER_CPU(struct static_sched_domain, phys_domains);
|
|
static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys);
|
|
|
|
static int
|
|
cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,
|
|
struct sched_group **sg, struct cpumask *mask)
|
|
{
|
|
int group;
|
|
#ifdef CONFIG_SCHED_BOOK
|
|
cpumask_and(mask, cpu_book_mask(cpu), cpu_map);
|
|
group = cpumask_first(mask);
|
|
#elif defined(CONFIG_SCHED_MC)
|
|
cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
|
|
group = cpumask_first(mask);
|
|
#elif defined(CONFIG_SCHED_SMT)
|
|
cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
|
|
group = cpumask_first(mask);
|
|
#else
|
|
group = cpu;
|
|
#endif
|
|
if (sg)
|
|
*sg = &per_cpu(sched_group_phys, group).sg;
|
|
return group;
|
|
}
|
|
|
|
#ifdef CONFIG_NUMA
|
|
/*
|
|
* The init_sched_build_groups can't handle what we want to do with node
|
|
* groups, so roll our own. Now each node has its own list of groups which
|
|
* gets dynamically allocated.
|
|
*/
|
|
static DEFINE_PER_CPU(struct static_sched_domain, node_domains);
|
|
static struct sched_group ***sched_group_nodes_bycpu;
|
|
|
|
static DEFINE_PER_CPU(struct static_sched_domain, allnodes_domains);
|
|
static DEFINE_PER_CPU(struct static_sched_group, sched_group_allnodes);
|
|
|
|
static int cpu_to_allnodes_group(int cpu, const struct cpumask *cpu_map,
|
|
struct sched_group **sg,
|
|
struct cpumask *nodemask)
|
|
{
|
|
int group;
|
|
|
|
cpumask_and(nodemask, cpumask_of_node(cpu_to_node(cpu)), cpu_map);
|
|
group = cpumask_first(nodemask);
|
|
|
|
if (sg)
|
|
*sg = &per_cpu(sched_group_allnodes, group).sg;
|
|
return group;
|
|
}
|
|
|
|
static void init_numa_sched_groups_power(struct sched_group *group_head)
|
|
{
|
|
struct sched_group *sg = group_head;
|
|
int j;
|
|
|
|
if (!sg)
|
|
return;
|
|
do {
|
|
for_each_cpu(j, sched_group_cpus(sg)) {
|
|
struct sched_domain *sd;
|
|
|
|
sd = &per_cpu(phys_domains, j).sd;
|
|
if (j != group_first_cpu(sd->groups)) {
|
|
/*
|
|
* Only add "power" once for each
|
|
* physical package.
|
|
*/
|
|
continue;
|
|
}
|
|
|
|
sg->cpu_power += sd->groups->cpu_power;
|
|
}
|
|
sg = sg->next;
|
|
} while (sg != group_head);
|
|
}
|
|
|
|
static int build_numa_sched_groups(struct s_data *d,
|
|
const struct cpumask *cpu_map, int num)
|
|
{
|
|
struct sched_domain *sd;
|
|
struct sched_group *sg, *prev;
|
|
int n, j;
|
|
|
|
cpumask_clear(d->covered);
|
|
cpumask_and(d->nodemask, cpumask_of_node(num), cpu_map);
|
|
if (cpumask_empty(d->nodemask)) {
|
|
d->sched_group_nodes[num] = NULL;
|
|
goto out;
|
|
}
|
|
|
|
sched_domain_node_span(num, d->domainspan);
|
|
cpumask_and(d->domainspan, d->domainspan, cpu_map);
|
|
|
|
sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
|
|
GFP_KERNEL, num);
|
|
if (!sg) {
|
|
printk(KERN_WARNING "Can not alloc domain group for node %d\n",
|
|
num);
|
|
return -ENOMEM;
|
|
}
|
|
d->sched_group_nodes[num] = sg;
|
|
|
|
for_each_cpu(j, d->nodemask) {
|
|
sd = &per_cpu(node_domains, j).sd;
|
|
sd->groups = sg;
|
|
}
|
|
|
|
sg->cpu_power = 0;
|
|
cpumask_copy(sched_group_cpus(sg), d->nodemask);
|
|
sg->next = sg;
|
|
cpumask_or(d->covered, d->covered, d->nodemask);
|
|
|
|
prev = sg;
|
|
for (j = 0; j < nr_node_ids; j++) {
|
|
n = (num + j) % nr_node_ids;
|
|
cpumask_complement(d->notcovered, d->covered);
|
|
cpumask_and(d->tmpmask, d->notcovered, cpu_map);
|
|
cpumask_and(d->tmpmask, d->tmpmask, d->domainspan);
|
|
if (cpumask_empty(d->tmpmask))
|
|
break;
|
|
cpumask_and(d->tmpmask, d->tmpmask, cpumask_of_node(n));
|
|
if (cpumask_empty(d->tmpmask))
|
|
continue;
|
|
sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
|
|
GFP_KERNEL, num);
|
|
if (!sg) {
|
|
printk(KERN_WARNING
|
|
"Can not alloc domain group for node %d\n", j);
|
|
return -ENOMEM;
|
|
}
|
|
sg->cpu_power = 0;
|
|
cpumask_copy(sched_group_cpus(sg), d->tmpmask);
|
|
sg->next = prev->next;
|
|
cpumask_or(d->covered, d->covered, d->tmpmask);
|
|
prev->next = sg;
|
|
prev = sg;
|
|
}
|
|
out:
|
|
return 0;
|
|
}
|
|
#endif /* CONFIG_NUMA */
|
|
|
|
#ifdef CONFIG_NUMA
|
|
/* Free memory allocated for various sched_group structures */
|
|
static void free_sched_groups(const struct cpumask *cpu_map,
|
|
struct cpumask *nodemask)
|
|
{
|
|
int cpu, i;
|
|
|
|
for_each_cpu(cpu, cpu_map) {
|
|
struct sched_group **sched_group_nodes
|
|
= sched_group_nodes_bycpu[cpu];
|
|
|
|
if (!sched_group_nodes)
|
|
continue;
|
|
|
|
for (i = 0; i < nr_node_ids; i++) {
|
|
struct sched_group *oldsg, *sg = sched_group_nodes[i];
|
|
|
|
cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
|
|
if (cpumask_empty(nodemask))
|
|
continue;
|
|
|
|
if (sg == NULL)
|
|
continue;
|
|
sg = sg->next;
|
|
next_sg:
|
|
oldsg = sg;
|
|
sg = sg->next;
|
|
kfree(oldsg);
|
|
if (oldsg != sched_group_nodes[i])
|
|
goto next_sg;
|
|
}
|
|
kfree(sched_group_nodes);
|
|
sched_group_nodes_bycpu[cpu] = NULL;
|
|
}
|
|
}
|
|
#else /* !CONFIG_NUMA */
|
|
static void free_sched_groups(const struct cpumask *cpu_map,
|
|
struct cpumask *nodemask)
|
|
{
|
|
}
|
|
#endif /* CONFIG_NUMA */
|
|
|
|
/*
|
|
* Initialize sched groups cpu_power.
|
|
*
|
|
* cpu_power indicates the capacity of sched group, which is used while
|
|
* distributing the load between different sched groups in a sched domain.
|
|
* Typically cpu_power for all the groups in a sched domain will be same unless
|
|
* there are asymmetries in the topology. If there are asymmetries, group
|
|
* having more cpu_power will pickup more load compared to the group having
|
|
* less cpu_power.
|
|
*/
|
|
static void init_sched_groups_power(int cpu, struct sched_domain *sd)
|
|
{
|
|
struct sched_domain *child;
|
|
struct sched_group *group;
|
|
long power;
|
|
int weight;
|
|
|
|
WARN_ON(!sd || !sd->groups);
|
|
|
|
if (cpu != group_first_cpu(sd->groups))
|
|
return;
|
|
|
|
sd->groups->group_weight = cpumask_weight(sched_group_cpus(sd->groups));
|
|
|
|
child = sd->child;
|
|
|
|
sd->groups->cpu_power = 0;
|
|
|
|
if (!child) {
|
|
power = SCHED_LOAD_SCALE;
|
|
weight = cpumask_weight(sched_domain_span(sd));
|
|
/*
|
|
* SMT siblings share the power of a single core.
|
|
* Usually multiple threads get a better yield out of
|
|
* that one core than a single thread would have,
|
|
* reflect that in sd->smt_gain.
|
|
*/
|
|
if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
|
|
power *= sd->smt_gain;
|
|
power /= weight;
|
|
power >>= SCHED_LOAD_SHIFT;
|
|
}
|
|
sd->groups->cpu_power += power;
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* Add cpu_power of each child group to this groups cpu_power.
|
|
*/
|
|
group = child->groups;
|
|
do {
|
|
sd->groups->cpu_power += group->cpu_power;
|
|
group = group->next;
|
|
} while (group != child->groups);
|
|
}
|
|
|
|
/*
|
|
* Initializers for schedule domains
|
|
* Non-inlined to reduce accumulated stack pressure in build_sched_domains()
|
|
*/
|
|
|
|
#ifdef CONFIG_SCHED_DEBUG
|
|
# define SD_INIT_NAME(sd, type) sd->name = #type
|
|
#else
|
|
# define SD_INIT_NAME(sd, type) do { } while (0)
|
|
#endif
|
|
|
|
#define SD_INIT(sd, type) sd_init_##type(sd)
|
|
|
|
#define SD_INIT_FUNC(type) \
|
|
static noinline void sd_init_##type(struct sched_domain *sd) \
|
|
{ \
|
|
memset(sd, 0, sizeof(*sd)); \
|
|
*sd = SD_##type##_INIT; \
|
|
sd->level = SD_LV_##type; \
|
|
SD_INIT_NAME(sd, type); \
|
|
}
|
|
|
|
SD_INIT_FUNC(CPU)
|
|
#ifdef CONFIG_NUMA
|
|
SD_INIT_FUNC(ALLNODES)
|
|
SD_INIT_FUNC(NODE)
|
|
#endif
|
|
#ifdef CONFIG_SCHED_SMT
|
|
SD_INIT_FUNC(SIBLING)
|
|
#endif
|
|
#ifdef CONFIG_SCHED_MC
|
|
SD_INIT_FUNC(MC)
|
|
#endif
|
|
#ifdef CONFIG_SCHED_BOOK
|
|
SD_INIT_FUNC(BOOK)
|
|
#endif
|
|
|
|
static int default_relax_domain_level = -1;
|
|
|
|
static int __init setup_relax_domain_level(char *str)
|
|
{
|
|
unsigned long val;
|
|
|
|
val = simple_strtoul(str, NULL, 0);
|
|
if (val < SD_LV_MAX)
|
|
default_relax_domain_level = val;
|
|
|
|
return 1;
|
|
}
|
|
__setup("relax_domain_level=", setup_relax_domain_level);
|
|
|
|
static void set_domain_attribute(struct sched_domain *sd,
|
|
struct sched_domain_attr *attr)
|
|
{
|
|
int request;
|
|
|
|
if (!attr || attr->relax_domain_level < 0) {
|
|
if (default_relax_domain_level < 0)
|
|
return;
|
|
else
|
|
request = default_relax_domain_level;
|
|
} else
|
|
request = attr->relax_domain_level;
|
|
if (request < sd->level) {
|
|
/* turn off idle balance on this domain */
|
|
sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
|
|
} else {
|
|
/* turn on idle balance on this domain */
|
|
sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
|
|
}
|
|
}
|
|
|
|
static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
|
|
const struct cpumask *cpu_map)
|
|
{
|
|
switch (what) {
|
|
case sa_sched_groups:
|
|
free_sched_groups(cpu_map, d->tmpmask); /* fall through */
|
|
d->sched_group_nodes = NULL;
|
|
case sa_rootdomain:
|
|
free_rootdomain(d->rd); /* fall through */
|
|
case sa_tmpmask:
|
|
free_cpumask_var(d->tmpmask); /* fall through */
|
|
case sa_send_covered:
|
|
free_cpumask_var(d->send_covered); /* fall through */
|
|
case sa_this_book_map:
|
|
free_cpumask_var(d->this_book_map); /* fall through */
|
|
case sa_this_core_map:
|
|
free_cpumask_var(d->this_core_map); /* fall through */
|
|
case sa_this_sibling_map:
|
|
free_cpumask_var(d->this_sibling_map); /* fall through */
|
|
case sa_nodemask:
|
|
free_cpumask_var(d->nodemask); /* fall through */
|
|
case sa_sched_group_nodes:
|
|
#ifdef CONFIG_NUMA
|
|
kfree(d->sched_group_nodes); /* fall through */
|
|
case sa_notcovered:
|
|
free_cpumask_var(d->notcovered); /* fall through */
|
|
case sa_covered:
|
|
free_cpumask_var(d->covered); /* fall through */
|
|
case sa_domainspan:
|
|
free_cpumask_var(d->domainspan); /* fall through */
|
|
#endif
|
|
case sa_none:
|
|
break;
|
|
}
|
|
}
|
|
|
|
static enum s_alloc __visit_domain_allocation_hell(struct s_data *d,
|
|
const struct cpumask *cpu_map)
|
|
{
|
|
#ifdef CONFIG_NUMA
|
|
if (!alloc_cpumask_var(&d->domainspan, GFP_KERNEL))
|
|
return sa_none;
|
|
if (!alloc_cpumask_var(&d->covered, GFP_KERNEL))
|
|
return sa_domainspan;
|
|
if (!alloc_cpumask_var(&d->notcovered, GFP_KERNEL))
|
|
return sa_covered;
|
|
/* Allocate the per-node list of sched groups */
|
|
d->sched_group_nodes = kcalloc(nr_node_ids,
|
|
sizeof(struct sched_group *), GFP_KERNEL);
|
|
if (!d->sched_group_nodes) {
|
|
printk(KERN_WARNING "Can not alloc sched group node list\n");
|
|
return sa_notcovered;
|
|
}
|
|
sched_group_nodes_bycpu[cpumask_first(cpu_map)] = d->sched_group_nodes;
|
|
#endif
|
|
if (!alloc_cpumask_var(&d->nodemask, GFP_KERNEL))
|
|
return sa_sched_group_nodes;
|
|
if (!alloc_cpumask_var(&d->this_sibling_map, GFP_KERNEL))
|
|
return sa_nodemask;
|
|
if (!alloc_cpumask_var(&d->this_core_map, GFP_KERNEL))
|
|
return sa_this_sibling_map;
|
|
if (!alloc_cpumask_var(&d->this_book_map, GFP_KERNEL))
|
|
return sa_this_core_map;
|
|
if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL))
|
|
return sa_this_book_map;
|
|
if (!alloc_cpumask_var(&d->tmpmask, GFP_KERNEL))
|
|
return sa_send_covered;
|
|
d->rd = alloc_rootdomain();
|
|
if (!d->rd) {
|
|
printk(KERN_WARNING "Cannot alloc root domain\n");
|
|
return sa_tmpmask;
|
|
}
|
|
return sa_rootdomain;
|
|
}
|
|
|
|
static struct sched_domain *__build_numa_sched_domains(struct s_data *d,
|
|
const struct cpumask *cpu_map, struct sched_domain_attr *attr, int i)
|
|
{
|
|
struct sched_domain *sd = NULL;
|
|
#ifdef CONFIG_NUMA
|
|
struct sched_domain *parent;
|
|
|
|
d->sd_allnodes = 0;
|
|
if (cpumask_weight(cpu_map) >
|
|
SD_NODES_PER_DOMAIN * cpumask_weight(d->nodemask)) {
|
|
sd = &per_cpu(allnodes_domains, i).sd;
|
|
SD_INIT(sd, ALLNODES);
|
|
set_domain_attribute(sd, attr);
|
|
cpumask_copy(sched_domain_span(sd), cpu_map);
|
|
cpu_to_allnodes_group(i, cpu_map, &sd->groups, d->tmpmask);
|
|
d->sd_allnodes = 1;
|
|
}
|
|
parent = sd;
|
|
|
|
sd = &per_cpu(node_domains, i).sd;
|
|
SD_INIT(sd, NODE);
|
|
set_domain_attribute(sd, attr);
|
|
sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd));
|
|
sd->parent = parent;
|
|
if (parent)
|
|
parent->child = sd;
|
|
cpumask_and(sched_domain_span(sd), sched_domain_span(sd), cpu_map);
|
|
#endif
|
|
return sd;
|
|
}
|
|
|
|
static struct sched_domain *__build_cpu_sched_domain(struct s_data *d,
|
|
const struct cpumask *cpu_map, struct sched_domain_attr *attr,
|
|
struct sched_domain *parent, int i)
|
|
{
|
|
struct sched_domain *sd;
|
|
sd = &per_cpu(phys_domains, i).sd;
|
|
SD_INIT(sd, CPU);
|
|
set_domain_attribute(sd, attr);
|
|
cpumask_copy(sched_domain_span(sd), d->nodemask);
|
|
sd->parent = parent;
|
|
if (parent)
|
|
parent->child = sd;
|
|
cpu_to_phys_group(i, cpu_map, &sd->groups, d->tmpmask);
|
|
return sd;
|
|
}
|
|
|
|
static struct sched_domain *__build_book_sched_domain(struct s_data *d,
|
|
const struct cpumask *cpu_map, struct sched_domain_attr *attr,
|
|
struct sched_domain *parent, int i)
|
|
{
|
|
struct sched_domain *sd = parent;
|
|
#ifdef CONFIG_SCHED_BOOK
|
|
sd = &per_cpu(book_domains, i).sd;
|
|
SD_INIT(sd, BOOK);
|
|
set_domain_attribute(sd, attr);
|
|
cpumask_and(sched_domain_span(sd), cpu_map, cpu_book_mask(i));
|
|
sd->parent = parent;
|
|
parent->child = sd;
|
|
cpu_to_book_group(i, cpu_map, &sd->groups, d->tmpmask);
|
|
#endif
|
|
return sd;
|
|
}
|
|
|
|
static struct sched_domain *__build_mc_sched_domain(struct s_data *d,
|
|
const struct cpumask *cpu_map, struct sched_domain_attr *attr,
|
|
struct sched_domain *parent, int i)
|
|
{
|
|
struct sched_domain *sd = parent;
|
|
#ifdef CONFIG_SCHED_MC
|
|
sd = &per_cpu(core_domains, i).sd;
|
|
SD_INIT(sd, MC);
|
|
set_domain_attribute(sd, attr);
|
|
cpumask_and(sched_domain_span(sd), cpu_map, cpu_coregroup_mask(i));
|
|
sd->parent = parent;
|
|
parent->child = sd;
|
|
cpu_to_core_group(i, cpu_map, &sd->groups, d->tmpmask);
|
|
#endif
|
|
return sd;
|
|
}
|
|
|
|
static struct sched_domain *__build_smt_sched_domain(struct s_data *d,
|
|
const struct cpumask *cpu_map, struct sched_domain_attr *attr,
|
|
struct sched_domain *parent, int i)
|
|
{
|
|
struct sched_domain *sd = parent;
|
|
#ifdef CONFIG_SCHED_SMT
|
|
sd = &per_cpu(cpu_domains, i).sd;
|
|
SD_INIT(sd, SIBLING);
|
|
set_domain_attribute(sd, attr);
|
|
cpumask_and(sched_domain_span(sd), cpu_map, topology_thread_cpumask(i));
|
|
sd->parent = parent;
|
|
parent->child = sd;
|
|
cpu_to_cpu_group(i, cpu_map, &sd->groups, d->tmpmask);
|
|
#endif
|
|
return sd;
|
|
}
|
|
|
|
static void build_sched_groups(struct s_data *d, enum sched_domain_level l,
|
|
const struct cpumask *cpu_map, int cpu)
|
|
{
|
|
switch (l) {
|
|
#ifdef CONFIG_SCHED_SMT
|
|
case SD_LV_SIBLING: /* set up CPU (sibling) groups */
|
|
cpumask_and(d->this_sibling_map, cpu_map,
|
|
topology_thread_cpumask(cpu));
|
|
if (cpu == cpumask_first(d->this_sibling_map))
|
|
init_sched_build_groups(d->this_sibling_map, cpu_map,
|
|
&cpu_to_cpu_group,
|
|
d->send_covered, d->tmpmask);
|
|
break;
|
|
#endif
|
|
#ifdef CONFIG_SCHED_MC
|
|
case SD_LV_MC: /* set up multi-core groups */
|
|
cpumask_and(d->this_core_map, cpu_map, cpu_coregroup_mask(cpu));
|
|
if (cpu == cpumask_first(d->this_core_map))
|
|
init_sched_build_groups(d->this_core_map, cpu_map,
|
|
&cpu_to_core_group,
|
|
d->send_covered, d->tmpmask);
|
|
break;
|
|
#endif
|
|
#ifdef CONFIG_SCHED_BOOK
|
|
case SD_LV_BOOK: /* set up book groups */
|
|
cpumask_and(d->this_book_map, cpu_map, cpu_book_mask(cpu));
|
|
if (cpu == cpumask_first(d->this_book_map))
|
|
init_sched_build_groups(d->this_book_map, cpu_map,
|
|
&cpu_to_book_group,
|
|
d->send_covered, d->tmpmask);
|
|
break;
|
|
#endif
|
|
case SD_LV_CPU: /* set up physical groups */
|
|
cpumask_and(d->nodemask, cpumask_of_node(cpu), cpu_map);
|
|
if (!cpumask_empty(d->nodemask))
|
|
init_sched_build_groups(d->nodemask, cpu_map,
|
|
&cpu_to_phys_group,
|
|
d->send_covered, d->tmpmask);
|
|
break;
|
|
#ifdef CONFIG_NUMA
|
|
case SD_LV_ALLNODES:
|
|
init_sched_build_groups(cpu_map, cpu_map, &cpu_to_allnodes_group,
|
|
d->send_covered, d->tmpmask);
|
|
break;
|
|
#endif
|
|
default:
|
|
break;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Build sched domains for a given set of cpus and attach the sched domains
|
|
* to the individual cpus
|
|
*/
|
|
static int __build_sched_domains(const struct cpumask *cpu_map,
|
|
struct sched_domain_attr *attr)
|
|
{
|
|
enum s_alloc alloc_state = sa_none;
|
|
struct s_data d;
|
|
struct sched_domain *sd;
|
|
int i;
|
|
#ifdef CONFIG_NUMA
|
|
d.sd_allnodes = 0;
|
|
#endif
|
|
|
|
alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
|
|
if (alloc_state != sa_rootdomain)
|
|
goto error;
|
|
alloc_state = sa_sched_groups;
|
|
|
|
/*
|
|
* Set up domains for cpus specified by the cpu_map.
|
|
*/
|
|
for_each_cpu(i, cpu_map) {
|
|
cpumask_and(d.nodemask, cpumask_of_node(cpu_to_node(i)),
|
|
cpu_map);
|
|
|
|
sd = __build_numa_sched_domains(&d, cpu_map, attr, i);
|
|
sd = __build_cpu_sched_domain(&d, cpu_map, attr, sd, i);
|
|
sd = __build_book_sched_domain(&d, cpu_map, attr, sd, i);
|
|
sd = __build_mc_sched_domain(&d, cpu_map, attr, sd, i);
|
|
sd = __build_smt_sched_domain(&d, cpu_map, attr, sd, i);
|
|
}
|
|
|
|
for_each_cpu(i, cpu_map) {
|
|
build_sched_groups(&d, SD_LV_SIBLING, cpu_map, i);
|
|
build_sched_groups(&d, SD_LV_BOOK, cpu_map, i);
|
|
build_sched_groups(&d, SD_LV_MC, cpu_map, i);
|
|
}
|
|
|
|
/* Set up physical groups */
|
|
for (i = 0; i < nr_node_ids; i++)
|
|
build_sched_groups(&d, SD_LV_CPU, cpu_map, i);
|
|
|
|
#ifdef CONFIG_NUMA
|
|
/* Set up node groups */
|
|
if (d.sd_allnodes)
|
|
build_sched_groups(&d, SD_LV_ALLNODES, cpu_map, 0);
|
|
|
|
for (i = 0; i < nr_node_ids; i++)
|
|
if (build_numa_sched_groups(&d, cpu_map, i))
|
|
goto error;
|
|
#endif
|
|
|
|
/* Calculate CPU power for physical packages and nodes */
|
|
#ifdef CONFIG_SCHED_SMT
|
|
for_each_cpu(i, cpu_map) {
|
|
sd = &per_cpu(cpu_domains, i).sd;
|
|
init_sched_groups_power(i, sd);
|
|
}
|
|
#endif
|
|
#ifdef CONFIG_SCHED_MC
|
|
for_each_cpu(i, cpu_map) {
|
|
sd = &per_cpu(core_domains, i).sd;
|
|
init_sched_groups_power(i, sd);
|
|
}
|
|
#endif
|
|
#ifdef CONFIG_SCHED_BOOK
|
|
for_each_cpu(i, cpu_map) {
|
|
sd = &per_cpu(book_domains, i).sd;
|
|
init_sched_groups_power(i, sd);
|
|
}
|
|
#endif
|
|
|
|
for_each_cpu(i, cpu_map) {
|
|
sd = &per_cpu(phys_domains, i).sd;
|
|
init_sched_groups_power(i, sd);
|
|
}
|
|
|
|
#ifdef CONFIG_NUMA
|
|
for (i = 0; i < nr_node_ids; i++)
|
|
init_numa_sched_groups_power(d.sched_group_nodes[i]);
|
|
|
|
if (d.sd_allnodes) {
|
|
struct sched_group *sg;
|
|
|
|
cpu_to_allnodes_group(cpumask_first(cpu_map), cpu_map, &sg,
|
|
d.tmpmask);
|
|
init_numa_sched_groups_power(sg);
|
|
}
|
|
#endif
|
|
|
|
/* Attach the domains */
|
|
for_each_cpu(i, cpu_map) {
|
|
#ifdef CONFIG_SCHED_SMT
|
|
sd = &per_cpu(cpu_domains, i).sd;
|
|
#elif defined(CONFIG_SCHED_MC)
|
|
sd = &per_cpu(core_domains, i).sd;
|
|
#elif defined(CONFIG_SCHED_BOOK)
|
|
sd = &per_cpu(book_domains, i).sd;
|
|
#else
|
|
sd = &per_cpu(phys_domains, i).sd;
|
|
#endif
|
|
cpu_attach_domain(sd, d.rd, i);
|
|
}
|
|
|
|
d.sched_group_nodes = NULL; /* don't free this we still need it */
|
|
__free_domain_allocs(&d, sa_tmpmask, cpu_map);
|
|
return 0;
|
|
|
|
error:
|
|
__free_domain_allocs(&d, alloc_state, cpu_map);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
static int build_sched_domains(const struct cpumask *cpu_map)
|
|
{
|
|
return __build_sched_domains(cpu_map, NULL);
|
|
}
|
|
|
|
static cpumask_var_t *doms_cur; /* current sched domains */
|
|
static int ndoms_cur; /* number of sched domains in 'doms_cur' */
|
|
static struct sched_domain_attr *dattr_cur;
|
|
/* attribues of custom domains in 'doms_cur' */
|
|
|
|
/*
|
|
* Special case: If a kmalloc of a doms_cur partition (array of
|
|
* cpumask) fails, then fallback to a single sched domain,
|
|
* as determined by the single cpumask fallback_doms.
|
|
*/
|
|
static cpumask_var_t fallback_doms;
|
|
|
|
/*
|
|
* arch_update_cpu_topology lets virtualized architectures update the
|
|
* cpu core maps. It is supposed to return 1 if the topology changed
|
|
* or 0 if it stayed the same.
|
|
*/
|
|
int __attribute__((weak)) arch_update_cpu_topology(void)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
cpumask_var_t *alloc_sched_domains(unsigned int ndoms)
|
|
{
|
|
int i;
|
|
cpumask_var_t *doms;
|
|
|
|
doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL);
|
|
if (!doms)
|
|
return NULL;
|
|
for (i = 0; i < ndoms; i++) {
|
|
if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) {
|
|
free_sched_domains(doms, i);
|
|
return NULL;
|
|
}
|
|
}
|
|
return doms;
|
|
}
|
|
|
|
void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
|
|
{
|
|
unsigned int i;
|
|
for (i = 0; i < ndoms; i++)
|
|
free_cpumask_var(doms[i]);
|
|
kfree(doms);
|
|
}
|
|
|
|
/*
|
|
* Set up scheduler domains and groups. Callers must hold the hotplug lock.
|
|
* For now this just excludes isolated cpus, but could be used to
|
|
* exclude other special cases in the future.
|
|
*/
|
|
static int arch_init_sched_domains(const struct cpumask *cpu_map)
|
|
{
|
|
int err;
|
|
|
|
arch_update_cpu_topology();
|
|
ndoms_cur = 1;
|
|
doms_cur = alloc_sched_domains(ndoms_cur);
|
|
if (!doms_cur)
|
|
doms_cur = &fallback_doms;
|
|
cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
|
|
dattr_cur = NULL;
|
|
err = build_sched_domains(doms_cur[0]);
|
|
register_sched_domain_sysctl();
|
|
|
|
return err;
|
|
}
|
|
|
|
static void arch_destroy_sched_domains(const struct cpumask *cpu_map,
|
|
struct cpumask *tmpmask)
|
|
{
|
|
free_sched_groups(cpu_map, tmpmask);
|
|
}
|
|
|
|
/*
|
|
* Detach sched domains from a group of cpus specified in cpu_map
|
|
* These cpus will now be attached to the NULL domain
|
|
*/
|
|
static void detach_destroy_domains(const struct cpumask *cpu_map)
|
|
{
|
|
/* Save because hotplug lock held. */
|
|
static DECLARE_BITMAP(tmpmask, CONFIG_NR_CPUS);
|
|
int i;
|
|
|
|
for_each_cpu(i, cpu_map)
|
|
cpu_attach_domain(NULL, &def_root_domain, i);
|
|
synchronize_sched();
|
|
arch_destroy_sched_domains(cpu_map, to_cpumask(tmpmask));
|
|
}
|
|
|
|
/* handle null as "default" */
|
|
static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
|
|
struct sched_domain_attr *new, int idx_new)
|
|
{
|
|
struct sched_domain_attr tmp;
|
|
|
|
/* fast path */
|
|
if (!new && !cur)
|
|
return 1;
|
|
|
|
tmp = SD_ATTR_INIT;
|
|
return !memcmp(cur ? (cur + idx_cur) : &tmp,
|
|
new ? (new + idx_new) : &tmp,
|
|
sizeof(struct sched_domain_attr));
|
|
}
|
|
|
|
/*
|
|
* Partition sched domains as specified by the 'ndoms_new'
|
|
* cpumasks in the array doms_new[] of cpumasks. This compares
|
|
* doms_new[] to the current sched domain partitioning, doms_cur[].
|
|
* It destroys each deleted domain and builds each new domain.
|
|
*
|
|
* 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'.
|
|
* The masks don't intersect (don't overlap.) We should setup one
|
|
* sched domain for each mask. CPUs not in any of the cpumasks will
|
|
* not be load balanced. If the same cpumask appears both in the
|
|
* current 'doms_cur' domains and in the new 'doms_new', we can leave
|
|
* it as it is.
|
|
*
|
|
* The passed in 'doms_new' should be allocated using
|
|
* alloc_sched_domains. This routine takes ownership of it and will
|
|
* free_sched_domains it when done with it. If the caller failed the
|
|
* alloc call, then it can pass in doms_new == NULL && ndoms_new == 1,
|
|
* and partition_sched_domains() will fallback to the single partition
|
|
* 'fallback_doms', it also forces the domains to be rebuilt.
|
|
*
|
|
* If doms_new == NULL it will be replaced with cpu_online_mask.
|
|
* ndoms_new == 0 is a special case for destroying existing domains,
|
|
* and it will not create the default domain.
|
|
*
|
|
* Call with hotplug lock held
|
|
*/
|
|
void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
|
|
struct sched_domain_attr *dattr_new)
|
|
{
|
|
int i, j, n;
|
|
int new_topology;
|
|
|
|
mutex_lock(&sched_domains_mutex);
|
|
|
|
/* always unregister in case we don't destroy any domains */
|
|
unregister_sched_domain_sysctl();
|
|
|
|
/* Let architecture update cpu core mappings. */
|
|
new_topology = arch_update_cpu_topology();
|
|
|
|
n = doms_new ? ndoms_new : 0;
|
|
|
|
/* Destroy deleted domains */
|
|
for (i = 0; i < ndoms_cur; i++) {
|
|
for (j = 0; j < n && !new_topology; j++) {
|
|
if (cpumask_equal(doms_cur[i], doms_new[j])
|
|
&& dattrs_equal(dattr_cur, i, dattr_new, j))
|
|
goto match1;
|
|
}
|
|
/* no match - a current sched domain not in new doms_new[] */
|
|
detach_destroy_domains(doms_cur[i]);
|
|
match1:
|
|
;
|
|
}
|
|
|
|
if (doms_new == NULL) {
|
|
ndoms_cur = 0;
|
|
doms_new = &fallback_doms;
|
|
cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map);
|
|
WARN_ON_ONCE(dattr_new);
|
|
}
|
|
|
|
/* Build new domains */
|
|
for (i = 0; i < ndoms_new; i++) {
|
|
for (j = 0; j < ndoms_cur && !new_topology; j++) {
|
|
if (cpumask_equal(doms_new[i], doms_cur[j])
|
|
&& dattrs_equal(dattr_new, i, dattr_cur, j))
|
|
goto match2;
|
|
}
|
|
/* no match - add a new doms_new */
|
|
__build_sched_domains(doms_new[i],
|
|
dattr_new ? dattr_new + i : NULL);
|
|
match2:
|
|
;
|
|
}
|
|
|
|
/* Remember the new sched domains */
|
|
if (doms_cur != &fallback_doms)
|
|
free_sched_domains(doms_cur, ndoms_cur);
|
|
kfree(dattr_cur); /* kfree(NULL) is safe */
|
|
doms_cur = doms_new;
|
|
dattr_cur = dattr_new;
|
|
ndoms_cur = ndoms_new;
|
|
|
|
register_sched_domain_sysctl();
|
|
|
|
mutex_unlock(&sched_domains_mutex);
|
|
}
|
|
|
|
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
|
|
static void arch_reinit_sched_domains(void)
|
|
{
|
|
get_online_cpus();
|
|
|
|
/* Destroy domains first to force the rebuild */
|
|
partition_sched_domains(0, NULL, NULL);
|
|
|
|
rebuild_sched_domains();
|
|
put_online_cpus();
|
|
}
|
|
|
|
static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt)
|
|
{
|
|
unsigned int level = 0;
|
|
|
|
if (sscanf(buf, "%u", &level) != 1)
|
|
return -EINVAL;
|
|
|
|
/*
|
|
* level is always be positive so don't check for
|
|
* level < POWERSAVINGS_BALANCE_NONE which is 0
|
|
* What happens on 0 or 1 byte write,
|
|
* need to check for count as well?
|
|
*/
|
|
|
|
if (level >= MAX_POWERSAVINGS_BALANCE_LEVELS)
|
|
return -EINVAL;
|
|
|
|
if (smt)
|
|
sched_smt_power_savings = level;
|
|
else
|
|
sched_mc_power_savings = level;
|
|
|
|
arch_reinit_sched_domains();
|
|
|
|
return count;
|
|
}
|
|
|
|
#ifdef CONFIG_SCHED_MC
|
|
static ssize_t sched_mc_power_savings_show(struct sysdev_class *class,
|
|
struct sysdev_class_attribute *attr,
|
|
char *page)
|
|
{
|
|
return sprintf(page, "%u\n", sched_mc_power_savings);
|
|
}
|
|
static ssize_t sched_mc_power_savings_store(struct sysdev_class *class,
|
|
struct sysdev_class_attribute *attr,
|
|
const char *buf, size_t count)
|
|
{
|
|
return sched_power_savings_store(buf, count, 0);
|
|
}
|
|
static SYSDEV_CLASS_ATTR(sched_mc_power_savings, 0644,
|
|
sched_mc_power_savings_show,
|
|
sched_mc_power_savings_store);
|
|
#endif
|
|
|
|
#ifdef CONFIG_SCHED_SMT
|
|
static ssize_t sched_smt_power_savings_show(struct sysdev_class *dev,
|
|
struct sysdev_class_attribute *attr,
|
|
char *page)
|
|
{
|
|
return sprintf(page, "%u\n", sched_smt_power_savings);
|
|
}
|
|
static ssize_t sched_smt_power_savings_store(struct sysdev_class *dev,
|
|
struct sysdev_class_attribute *attr,
|
|
const char *buf, size_t count)
|
|
{
|
|
return sched_power_savings_store(buf, count, 1);
|
|
}
|
|
static SYSDEV_CLASS_ATTR(sched_smt_power_savings, 0644,
|
|
sched_smt_power_savings_show,
|
|
sched_smt_power_savings_store);
|
|
#endif
|
|
|
|
int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls)
|
|
{
|
|
int err = 0;
|
|
|
|
#ifdef CONFIG_SCHED_SMT
|
|
if (smt_capable())
|
|
err = sysfs_create_file(&cls->kset.kobj,
|
|
&attr_sched_smt_power_savings.attr);
|
|
#endif
|
|
#ifdef CONFIG_SCHED_MC
|
|
if (!err && mc_capable())
|
|
err = sysfs_create_file(&cls->kset.kobj,
|
|
&attr_sched_mc_power_savings.attr);
|
|
#endif
|
|
return err;
|
|
}
|
|
#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
|
|
|
|
/*
|
|
* Update cpusets according to cpu_active mask. If cpusets are
|
|
* disabled, cpuset_update_active_cpus() becomes a simple wrapper
|
|
* around partition_sched_domains().
|
|
*/
|
|
static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action,
|
|
void *hcpu)
|
|
{
|
|
switch (action & ~CPU_TASKS_FROZEN) {
|
|
case CPU_ONLINE:
|
|
case CPU_DOWN_FAILED:
|
|
cpuset_update_active_cpus();
|
|
return NOTIFY_OK;
|
|
default:
|
|
return NOTIFY_DONE;
|
|
}
|
|
}
|
|
|
|
static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action,
|
|
void *hcpu)
|
|
{
|
|
switch (action & ~CPU_TASKS_FROZEN) {
|
|
case CPU_DOWN_PREPARE:
|
|
cpuset_update_active_cpus();
|
|
return NOTIFY_OK;
|
|
default:
|
|
return NOTIFY_DONE;
|
|
}
|
|
}
|
|
|
|
static int update_runtime(struct notifier_block *nfb,
|
|
unsigned long action, void *hcpu)
|
|
{
|
|
int cpu = (int)(long)hcpu;
|
|
|
|
switch (action) {
|
|
case CPU_DOWN_PREPARE:
|
|
case CPU_DOWN_PREPARE_FROZEN:
|
|
disable_runtime(cpu_rq(cpu));
|
|
return NOTIFY_OK;
|
|
|
|
case CPU_DOWN_FAILED:
|
|
case CPU_DOWN_FAILED_FROZEN:
|
|
case CPU_ONLINE:
|
|
case CPU_ONLINE_FROZEN:
|
|
enable_runtime(cpu_rq(cpu));
|
|
return NOTIFY_OK;
|
|
|
|
default:
|
|
return NOTIFY_DONE;
|
|
}
|
|
}
|
|
|
|
void __init sched_init_smp(void)
|
|
{
|
|
cpumask_var_t non_isolated_cpus;
|
|
|
|
alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);
|
|
alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
|
|
|
|
#if defined(CONFIG_NUMA)
|
|
sched_group_nodes_bycpu = kzalloc(nr_cpu_ids * sizeof(void **),
|
|
GFP_KERNEL);
|
|
BUG_ON(sched_group_nodes_bycpu == NULL);
|
|
#endif
|
|
get_online_cpus();
|
|
mutex_lock(&sched_domains_mutex);
|
|
arch_init_sched_domains(cpu_active_mask);
|
|
cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
|
|
if (cpumask_empty(non_isolated_cpus))
|
|
cpumask_set_cpu(smp_processor_id(), non_isolated_cpus);
|
|
mutex_unlock(&sched_domains_mutex);
|
|
put_online_cpus();
|
|
|
|
hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE);
|
|
hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE);
|
|
|
|
/* RT runtime code needs to handle some hotplug events */
|
|
hotcpu_notifier(update_runtime, 0);
|
|
|
|
init_hrtick();
|
|
|
|
/* Move init over to a non-isolated CPU */
|
|
if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0)
|
|
BUG();
|
|
sched_init_granularity();
|
|
free_cpumask_var(non_isolated_cpus);
|
|
|
|
init_sched_rt_class();
|
|
}
|
|
#else
|
|
void __init sched_init_smp(void)
|
|
{
|
|
sched_init_granularity();
|
|
}
|
|
#endif /* CONFIG_SMP */
|
|
|
|
const_debug unsigned int sysctl_timer_migration = 1;
|
|
|
|
int in_sched_functions(unsigned long addr)
|
|
{
|
|
return in_lock_functions(addr) ||
|
|
(addr >= (unsigned long)__sched_text_start
|
|
&& addr < (unsigned long)__sched_text_end);
|
|
}
|
|
|
|
static void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq)
|
|
{
|
|
cfs_rq->tasks_timeline = RB_ROOT;
|
|
INIT_LIST_HEAD(&cfs_rq->tasks);
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
cfs_rq->rq = rq;
|
|
/* allow initial update_cfs_load() to truncate */
|
|
#ifdef CONFIG_SMP
|
|
cfs_rq->load_stamp = 1;
|
|
#endif
|
|
#endif
|
|
cfs_rq->min_vruntime = (u64)(-(1LL << 20));
|
|
}
|
|
|
|
static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
|
|
{
|
|
struct rt_prio_array *array;
|
|
int i;
|
|
|
|
array = &rt_rq->active;
|
|
for (i = 0; i < MAX_RT_PRIO; i++) {
|
|
INIT_LIST_HEAD(array->queue + i);
|
|
__clear_bit(i, array->bitmap);
|
|
}
|
|
/* delimiter for bitsearch: */
|
|
__set_bit(MAX_RT_PRIO, array->bitmap);
|
|
|
|
#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
|
|
rt_rq->highest_prio.curr = MAX_RT_PRIO;
|
|
#ifdef CONFIG_SMP
|
|
rt_rq->highest_prio.next = MAX_RT_PRIO;
|
|
#endif
|
|
#endif
|
|
#ifdef CONFIG_SMP
|
|
rt_rq->rt_nr_migratory = 0;
|
|
rt_rq->overloaded = 0;
|
|
plist_head_init_raw(&rt_rq->pushable_tasks, &rq->lock);
|
|
#endif
|
|
|
|
rt_rq->rt_time = 0;
|
|
rt_rq->rt_throttled = 0;
|
|
rt_rq->rt_runtime = 0;
|
|
raw_spin_lock_init(&rt_rq->rt_runtime_lock);
|
|
|
|
#ifdef CONFIG_RT_GROUP_SCHED
|
|
rt_rq->rt_nr_boosted = 0;
|
|
rt_rq->rq = rq;
|
|
#endif
|
|
}
|
|
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
|
|
struct sched_entity *se, int cpu,
|
|
struct sched_entity *parent)
|
|
{
|
|
struct rq *rq = cpu_rq(cpu);
|
|
tg->cfs_rq[cpu] = cfs_rq;
|
|
init_cfs_rq(cfs_rq, rq);
|
|
cfs_rq->tg = tg;
|
|
|
|
tg->se[cpu] = se;
|
|
/* se could be NULL for root_task_group */
|
|
if (!se)
|
|
return;
|
|
|
|
if (!parent)
|
|
se->cfs_rq = &rq->cfs;
|
|
else
|
|
se->cfs_rq = parent->my_q;
|
|
|
|
se->my_q = cfs_rq;
|
|
update_load_set(&se->load, 0);
|
|
se->parent = parent;
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_RT_GROUP_SCHED
|
|
static 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)
|
|
{
|
|
struct rq *rq = cpu_rq(cpu);
|
|
|
|
tg->rt_rq[cpu] = rt_rq;
|
|
init_rt_rq(rt_rq, rq);
|
|
rt_rq->tg = tg;
|
|
rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime;
|
|
|
|
tg->rt_se[cpu] = rt_se;
|
|
if (!rt_se)
|
|
return;
|
|
|
|
if (!parent)
|
|
rt_se->rt_rq = &rq->rt;
|
|
else
|
|
rt_se->rt_rq = parent->my_q;
|
|
|
|
rt_se->my_q = rt_rq;
|
|
rt_se->parent = parent;
|
|
INIT_LIST_HEAD(&rt_se->run_list);
|
|
}
|
|
#endif
|
|
|
|
void __init sched_init(void)
|
|
{
|
|
int i, j;
|
|
unsigned long alloc_size = 0, ptr;
|
|
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
alloc_size += 2 * nr_cpu_ids * sizeof(void **);
|
|
#endif
|
|
#ifdef CONFIG_RT_GROUP_SCHED
|
|
alloc_size += 2 * nr_cpu_ids * sizeof(void **);
|
|
#endif
|
|
#ifdef CONFIG_CPUMASK_OFFSTACK
|
|
alloc_size += num_possible_cpus() * cpumask_size();
|
|
#endif
|
|
if (alloc_size) {
|
|
ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);
|
|
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
root_task_group.se = (struct sched_entity **)ptr;
|
|
ptr += nr_cpu_ids * sizeof(void **);
|
|
|
|
root_task_group.cfs_rq = (struct cfs_rq **)ptr;
|
|
ptr += nr_cpu_ids * sizeof(void **);
|
|
|
|
#endif /* CONFIG_FAIR_GROUP_SCHED */
|
|
#ifdef CONFIG_RT_GROUP_SCHED
|
|
root_task_group.rt_se = (struct sched_rt_entity **)ptr;
|
|
ptr += nr_cpu_ids * sizeof(void **);
|
|
|
|
root_task_group.rt_rq = (struct rt_rq **)ptr;
|
|
ptr += nr_cpu_ids * sizeof(void **);
|
|
|
|
#endif /* CONFIG_RT_GROUP_SCHED */
|
|
#ifdef CONFIG_CPUMASK_OFFSTACK
|
|
for_each_possible_cpu(i) {
|
|
per_cpu(load_balance_tmpmask, i) = (void *)ptr;
|
|
ptr += cpumask_size();
|
|
}
|
|
#endif /* CONFIG_CPUMASK_OFFSTACK */
|
|
}
|
|
|
|
#ifdef CONFIG_SMP
|
|
init_defrootdomain();
|
|
#endif
|
|
|
|
init_rt_bandwidth(&def_rt_bandwidth,
|
|
global_rt_period(), global_rt_runtime());
|
|
|
|
#ifdef CONFIG_RT_GROUP_SCHED
|
|
init_rt_bandwidth(&root_task_group.rt_bandwidth,
|
|
global_rt_period(), global_rt_runtime());
|
|
#endif /* CONFIG_RT_GROUP_SCHED */
|
|
|
|
#ifdef CONFIG_CGROUP_SCHED
|
|
list_add(&root_task_group.list, &task_groups);
|
|
INIT_LIST_HEAD(&root_task_group.children);
|
|
autogroup_init(&init_task);
|
|
#endif /* CONFIG_CGROUP_SCHED */
|
|
|
|
for_each_possible_cpu(i) {
|
|
struct rq *rq;
|
|
|
|
rq = cpu_rq(i);
|
|
raw_spin_lock_init(&rq->lock);
|
|
rq->nr_running = 0;
|
|
rq->calc_load_active = 0;
|
|
rq->calc_load_update = jiffies + LOAD_FREQ;
|
|
init_cfs_rq(&rq->cfs, rq);
|
|
init_rt_rq(&rq->rt, rq);
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
root_task_group.shares = root_task_group_load;
|
|
INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
|
|
/*
|
|
* How much cpu bandwidth does root_task_group get?
|
|
*
|
|
* In case of task-groups formed thr' the cgroup filesystem, it
|
|
* gets 100% of the cpu resources in the system. This overall
|
|
* system cpu resource is divided among the tasks of
|
|
* root_task_group and its child task-groups in a fair manner,
|
|
* based on each entity's (task or task-group's) weight
|
|
* (se->load.weight).
|
|
*
|
|
* In other words, if root_task_group has 10 tasks of weight
|
|
* 1024) and two child groups A0 and A1 (of weight 1024 each),
|
|
* then A0's share of the cpu resource is:
|
|
*
|
|
* A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33%
|
|
*
|
|
* We achieve this by letting root_task_group's tasks sit
|
|
* directly in rq->cfs (i.e root_task_group->se[] = NULL).
|
|
*/
|
|
init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, NULL);
|
|
#endif /* CONFIG_FAIR_GROUP_SCHED */
|
|
|
|
rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime;
|
|
#ifdef CONFIG_RT_GROUP_SCHED
|
|
INIT_LIST_HEAD(&rq->leaf_rt_rq_list);
|
|
init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL);
|
|
#endif
|
|
|
|
for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
|
|
rq->cpu_load[j] = 0;
|
|
|
|
rq->last_load_update_tick = jiffies;
|
|
|
|
#ifdef CONFIG_SMP
|
|
rq->sd = NULL;
|
|
rq->rd = NULL;
|
|
rq->cpu_power = SCHED_LOAD_SCALE;
|
|
rq->post_schedule = 0;
|
|
rq->active_balance = 0;
|
|
rq->next_balance = jiffies;
|
|
rq->push_cpu = 0;
|
|
rq->cpu = i;
|
|
rq->online = 0;
|
|
rq->idle_stamp = 0;
|
|
rq->avg_idle = 2*sysctl_sched_migration_cost;
|
|
rq_attach_root(rq, &def_root_domain);
|
|
#ifdef CONFIG_NO_HZ
|
|
rq->nohz_balance_kick = 0;
|
|
init_sched_softirq_csd(&per_cpu(remote_sched_softirq_cb, i));
|
|
#endif
|
|
#endif
|
|
init_rq_hrtick(rq);
|
|
atomic_set(&rq->nr_iowait, 0);
|
|
}
|
|
|
|
set_load_weight(&init_task);
|
|
|
|
#ifdef CONFIG_PREEMPT_NOTIFIERS
|
|
INIT_HLIST_HEAD(&init_task.preempt_notifiers);
|
|
#endif
|
|
|
|
#ifdef CONFIG_SMP
|
|
open_softirq(SCHED_SOFTIRQ, run_rebalance_domains);
|
|
#endif
|
|
|
|
#ifdef CONFIG_RT_MUTEXES
|
|
plist_head_init_raw(&init_task.pi_waiters, &init_task.pi_lock);
|
|
#endif
|
|
|
|
/*
|
|
* The boot idle thread does lazy MMU switching as well:
|
|
*/
|
|
atomic_inc(&init_mm.mm_count);
|
|
enter_lazy_tlb(&init_mm, current);
|
|
|
|
/*
|
|
* Make us the idle thread. Technically, schedule() should not be
|
|
* called from this thread, however somewhere below it might be,
|
|
* but because we are the idle thread, we just pick up running again
|
|
* when this runqueue becomes "idle".
|
|
*/
|
|
init_idle(current, smp_processor_id());
|
|
|
|
calc_load_update = jiffies + LOAD_FREQ;
|
|
|
|
/*
|
|
* During early bootup we pretend to be a normal task:
|
|
*/
|
|
current->sched_class = &fair_sched_class;
|
|
|
|
/* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
|
|
zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
|
|
#ifdef CONFIG_SMP
|
|
#ifdef CONFIG_NO_HZ
|
|
zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT);
|
|
alloc_cpumask_var(&nohz.grp_idle_mask, GFP_NOWAIT);
|
|
atomic_set(&nohz.load_balancer, nr_cpu_ids);
|
|
atomic_set(&nohz.first_pick_cpu, nr_cpu_ids);
|
|
atomic_set(&nohz.second_pick_cpu, nr_cpu_ids);
|
|
#endif
|
|
/* May be allocated at isolcpus cmdline parse time */
|
|
if (cpu_isolated_map == NULL)
|
|
zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
|
|
#endif /* SMP */
|
|
|
|
scheduler_running = 1;
|
|
}
|
|
|
|
#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
|
|
static inline int preempt_count_equals(int preempt_offset)
|
|
{
|
|
int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth();
|
|
|
|
return (nested == preempt_offset);
|
|
}
|
|
|
|
void __might_sleep(const char *file, int line, int preempt_offset)
|
|
{
|
|
#ifdef in_atomic
|
|
static unsigned long prev_jiffy; /* ratelimiting */
|
|
|
|
if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) ||
|
|
system_state != SYSTEM_RUNNING || oops_in_progress)
|
|
return;
|
|
if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
|
|
return;
|
|
prev_jiffy = jiffies;
|
|
|
|
printk(KERN_ERR
|
|
"BUG: sleeping function called from invalid context at %s:%d\n",
|
|
file, line);
|
|
printk(KERN_ERR
|
|
"in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n",
|
|
in_atomic(), irqs_disabled(),
|
|
current->pid, current->comm);
|
|
|
|
debug_show_held_locks(current);
|
|
if (irqs_disabled())
|
|
print_irqtrace_events(current);
|
|
dump_stack();
|
|
#endif
|
|
}
|
|
EXPORT_SYMBOL(__might_sleep);
|
|
#endif
|
|
|
|
#ifdef CONFIG_MAGIC_SYSRQ
|
|
static void normalize_task(struct rq *rq, struct task_struct *p)
|
|
{
|
|
const struct sched_class *prev_class = p->sched_class;
|
|
int old_prio = p->prio;
|
|
int on_rq;
|
|
|
|
on_rq = p->se.on_rq;
|
|
if (on_rq)
|
|
deactivate_task(rq, p, 0);
|
|
__setscheduler(rq, p, SCHED_NORMAL, 0);
|
|
if (on_rq) {
|
|
activate_task(rq, p, 0);
|
|
resched_task(rq->curr);
|
|
}
|
|
|
|
check_class_changed(rq, p, prev_class, old_prio);
|
|
}
|
|
|
|
void normalize_rt_tasks(void)
|
|
{
|
|
struct task_struct *g, *p;
|
|
unsigned long flags;
|
|
struct rq *rq;
|
|
|
|
read_lock_irqsave(&tasklist_lock, flags);
|
|
do_each_thread(g, p) {
|
|
/*
|
|
* Only normalize user tasks:
|
|
*/
|
|
if (!p->mm)
|
|
continue;
|
|
|
|
p->se.exec_start = 0;
|
|
#ifdef CONFIG_SCHEDSTATS
|
|
p->se.statistics.wait_start = 0;
|
|
p->se.statistics.sleep_start = 0;
|
|
p->se.statistics.block_start = 0;
|
|
#endif
|
|
|
|
if (!rt_task(p)) {
|
|
/*
|
|
* Renice negative nice level userspace
|
|
* tasks back to 0:
|
|
*/
|
|
if (TASK_NICE(p) < 0 && p->mm)
|
|
set_user_nice(p, 0);
|
|
continue;
|
|
}
|
|
|
|
raw_spin_lock(&p->pi_lock);
|
|
rq = __task_rq_lock(p);
|
|
|
|
normalize_task(rq, p);
|
|
|
|
__task_rq_unlock(rq);
|
|
raw_spin_unlock(&p->pi_lock);
|
|
} while_each_thread(g, p);
|
|
|
|
read_unlock_irqrestore(&tasklist_lock, flags);
|
|
}
|
|
|
|
#endif /* CONFIG_MAGIC_SYSRQ */
|
|
|
|
#if defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB)
|
|
/*
|
|
* These functions are only useful for the IA64 MCA handling, or kdb.
|
|
*
|
|
* They can only be called when the whole system has been
|
|
* stopped - every CPU needs to be quiescent, and no scheduling
|
|
* activity can take place. Using them for anything else would
|
|
* be a serious bug, and as a result, they aren't even visible
|
|
* under any other configuration.
|
|
*/
|
|
|
|
/**
|
|
* curr_task - return the current task for a given cpu.
|
|
* @cpu: the processor in question.
|
|
*
|
|
* ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
|
|
*/
|
|
struct task_struct *curr_task(int cpu)
|
|
{
|
|
return cpu_curr(cpu);
|
|
}
|
|
|
|
#endif /* defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) */
|
|
|
|
#ifdef CONFIG_IA64
|
|
/**
|
|
* set_curr_task - set the current task for a given cpu.
|
|
* @cpu: the processor in question.
|
|
* @p: the task pointer to set.
|
|
*
|
|
* Description: This function must only be used when non-maskable interrupts
|
|
* are serviced on a separate stack. It allows the architecture to switch the
|
|
* notion of the current task on a cpu in a non-blocking manner. This function
|
|
* must be called with all CPU's synchronized, and interrupts disabled, the
|
|
* and caller must save the original value of the current task (see
|
|
* curr_task() above) and restore that value before reenabling interrupts and
|
|
* re-starting the system.
|
|
*
|
|
* ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
|
|
*/
|
|
void set_curr_task(int cpu, struct task_struct *p)
|
|
{
|
|
cpu_curr(cpu) = p;
|
|
}
|
|
|
|
#endif
|
|
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
static void free_fair_sched_group(struct task_group *tg)
|
|
{
|
|
int i;
|
|
|
|
for_each_possible_cpu(i) {
|
|
if (tg->cfs_rq)
|
|
kfree(tg->cfs_rq[i]);
|
|
if (tg->se)
|
|
kfree(tg->se[i]);
|
|
}
|
|
|
|
kfree(tg->cfs_rq);
|
|
kfree(tg->se);
|
|
}
|
|
|
|
static
|
|
int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
|
|
{
|
|
struct cfs_rq *cfs_rq;
|
|
struct sched_entity *se;
|
|
int i;
|
|
|
|
tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL);
|
|
if (!tg->cfs_rq)
|
|
goto err;
|
|
tg->se = kzalloc(sizeof(se) * nr_cpu_ids, GFP_KERNEL);
|
|
if (!tg->se)
|
|
goto err;
|
|
|
|
tg->shares = NICE_0_LOAD;
|
|
|
|
for_each_possible_cpu(i) {
|
|
cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
|
|
GFP_KERNEL, cpu_to_node(i));
|
|
if (!cfs_rq)
|
|
goto err;
|
|
|
|
se = kzalloc_node(sizeof(struct sched_entity),
|
|
GFP_KERNEL, cpu_to_node(i));
|
|
if (!se)
|
|
goto err_free_rq;
|
|
|
|
init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
|
|
}
|
|
|
|
return 1;
|
|
|
|
err_free_rq:
|
|
kfree(cfs_rq);
|
|
err:
|
|
return 0;
|
|
}
|
|
|
|
static inline void unregister_fair_sched_group(struct task_group *tg, int cpu)
|
|
{
|
|
struct rq *rq = cpu_rq(cpu);
|
|
unsigned long flags;
|
|
|
|
/*
|
|
* Only empty task groups can be destroyed; so we can speculatively
|
|
* check on_list without danger of it being re-added.
|
|
*/
|
|
if (!tg->cfs_rq[cpu]->on_list)
|
|
return;
|
|
|
|
raw_spin_lock_irqsave(&rq->lock, flags);
|
|
list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
|
|
raw_spin_unlock_irqrestore(&rq->lock, flags);
|
|
}
|
|
#else /* !CONFG_FAIR_GROUP_SCHED */
|
|
static inline void free_fair_sched_group(struct task_group *tg)
|
|
{
|
|
}
|
|
|
|
static inline
|
|
int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
static inline void unregister_fair_sched_group(struct task_group *tg, int cpu)
|
|
{
|
|
}
|
|
#endif /* CONFIG_FAIR_GROUP_SCHED */
|
|
|
|
#ifdef CONFIG_RT_GROUP_SCHED
|
|
static void free_rt_sched_group(struct task_group *tg)
|
|
{
|
|
int i;
|
|
|
|
destroy_rt_bandwidth(&tg->rt_bandwidth);
|
|
|
|
for_each_possible_cpu(i) {
|
|
if (tg->rt_rq)
|
|
kfree(tg->rt_rq[i]);
|
|
if (tg->rt_se)
|
|
kfree(tg->rt_se[i]);
|
|
}
|
|
|
|
kfree(tg->rt_rq);
|
|
kfree(tg->rt_se);
|
|
}
|
|
|
|
static
|
|
int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
|
|
{
|
|
struct rt_rq *rt_rq;
|
|
struct sched_rt_entity *rt_se;
|
|
struct rq *rq;
|
|
int i;
|
|
|
|
tg->rt_rq = kzalloc(sizeof(rt_rq) * nr_cpu_ids, GFP_KERNEL);
|
|
if (!tg->rt_rq)
|
|
goto err;
|
|
tg->rt_se = kzalloc(sizeof(rt_se) * nr_cpu_ids, GFP_KERNEL);
|
|
if (!tg->rt_se)
|
|
goto err;
|
|
|
|
init_rt_bandwidth(&tg->rt_bandwidth,
|
|
ktime_to_ns(def_rt_bandwidth.rt_period), 0);
|
|
|
|
for_each_possible_cpu(i) {
|
|
rq = cpu_rq(i);
|
|
|
|
rt_rq = kzalloc_node(sizeof(struct rt_rq),
|
|
GFP_KERNEL, cpu_to_node(i));
|
|
if (!rt_rq)
|
|
goto err;
|
|
|
|
rt_se = kzalloc_node(sizeof(struct sched_rt_entity),
|
|
GFP_KERNEL, cpu_to_node(i));
|
|
if (!rt_se)
|
|
goto err_free_rq;
|
|
|
|
init_tg_rt_entry(tg, rt_rq, rt_se, i, parent->rt_se[i]);
|
|
}
|
|
|
|
return 1;
|
|
|
|
err_free_rq:
|
|
kfree(rt_rq);
|
|
err:
|
|
return 0;
|
|
}
|
|
#else /* !CONFIG_RT_GROUP_SCHED */
|
|
static inline void free_rt_sched_group(struct task_group *tg)
|
|
{
|
|
}
|
|
|
|
static inline
|
|
int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
|
|
{
|
|
return 1;
|
|
}
|
|
#endif /* CONFIG_RT_GROUP_SCHED */
|
|
|
|
#ifdef CONFIG_CGROUP_SCHED
|
|
static void free_sched_group(struct task_group *tg)
|
|
{
|
|
free_fair_sched_group(tg);
|
|
free_rt_sched_group(tg);
|
|
autogroup_free(tg);
|
|
kfree(tg);
|
|
}
|
|
|
|
/* allocate runqueue etc for a new task group */
|
|
struct task_group *sched_create_group(struct task_group *parent)
|
|
{
|
|
struct task_group *tg;
|
|
unsigned long flags;
|
|
|
|
tg = kzalloc(sizeof(*tg), GFP_KERNEL);
|
|
if (!tg)
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
if (!alloc_fair_sched_group(tg, parent))
|
|
goto err;
|
|
|
|
if (!alloc_rt_sched_group(tg, parent))
|
|
goto err;
|
|
|
|
spin_lock_irqsave(&task_group_lock, flags);
|
|
list_add_rcu(&tg->list, &task_groups);
|
|
|
|
WARN_ON(!parent); /* root should already exist */
|
|
|
|
tg->parent = parent;
|
|
INIT_LIST_HEAD(&tg->children);
|
|
list_add_rcu(&tg->siblings, &parent->children);
|
|
spin_unlock_irqrestore(&task_group_lock, flags);
|
|
|
|
return tg;
|
|
|
|
err:
|
|
free_sched_group(tg);
|
|
return ERR_PTR(-ENOMEM);
|
|
}
|
|
|
|
/* rcu callback to free various structures associated with a task group */
|
|
static void free_sched_group_rcu(struct rcu_head *rhp)
|
|
{
|
|
/* now it should be safe to free those cfs_rqs */
|
|
free_sched_group(container_of(rhp, struct task_group, rcu));
|
|
}
|
|
|
|
/* Destroy runqueue etc associated with a task group */
|
|
void sched_destroy_group(struct task_group *tg)
|
|
{
|
|
unsigned long flags;
|
|
int i;
|
|
|
|
/* end participation in shares distribution */
|
|
for_each_possible_cpu(i)
|
|
unregister_fair_sched_group(tg, i);
|
|
|
|
spin_lock_irqsave(&task_group_lock, flags);
|
|
list_del_rcu(&tg->list);
|
|
list_del_rcu(&tg->siblings);
|
|
spin_unlock_irqrestore(&task_group_lock, flags);
|
|
|
|
/* wait for possible concurrent references to cfs_rqs complete */
|
|
call_rcu(&tg->rcu, free_sched_group_rcu);
|
|
}
|
|
|
|
/* change task's runqueue when it moves between groups.
|
|
* The caller of this function should have put the task in its new group
|
|
* by now. This function just updates tsk->se.cfs_rq and tsk->se.parent to
|
|
* reflect its new group.
|
|
*/
|
|
void sched_move_task(struct task_struct *tsk)
|
|
{
|
|
int on_rq, running;
|
|
unsigned long flags;
|
|
struct rq *rq;
|
|
|
|
rq = task_rq_lock(tsk, &flags);
|
|
|
|
running = task_current(rq, tsk);
|
|
on_rq = tsk->se.on_rq;
|
|
|
|
if (on_rq)
|
|
dequeue_task(rq, tsk, 0);
|
|
if (unlikely(running))
|
|
tsk->sched_class->put_prev_task(rq, tsk);
|
|
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
if (tsk->sched_class->task_move_group)
|
|
tsk->sched_class->task_move_group(tsk, on_rq);
|
|
else
|
|
#endif
|
|
set_task_rq(tsk, task_cpu(tsk));
|
|
|
|
if (unlikely(running))
|
|
tsk->sched_class->set_curr_task(rq);
|
|
if (on_rq)
|
|
enqueue_task(rq, tsk, 0);
|
|
|
|
task_rq_unlock(rq, &flags);
|
|
}
|
|
#endif /* CONFIG_CGROUP_SCHED */
|
|
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
static DEFINE_MUTEX(shares_mutex);
|
|
|
|
int sched_group_set_shares(struct task_group *tg, unsigned long shares)
|
|
{
|
|
int i;
|
|
unsigned long flags;
|
|
|
|
/*
|
|
* We can't change the weight of the root cgroup.
|
|
*/
|
|
if (!tg->se[0])
|
|
return -EINVAL;
|
|
|
|
if (shares < MIN_SHARES)
|
|
shares = MIN_SHARES;
|
|
else if (shares > MAX_SHARES)
|
|
shares = MAX_SHARES;
|
|
|
|
mutex_lock(&shares_mutex);
|
|
if (tg->shares == shares)
|
|
goto done;
|
|
|
|
tg->shares = shares;
|
|
for_each_possible_cpu(i) {
|
|
struct rq *rq = cpu_rq(i);
|
|
struct sched_entity *se;
|
|
|
|
se = tg->se[i];
|
|
/* Propagate contribution to hierarchy */
|
|
raw_spin_lock_irqsave(&rq->lock, flags);
|
|
for_each_sched_entity(se)
|
|
update_cfs_shares(group_cfs_rq(se));
|
|
raw_spin_unlock_irqrestore(&rq->lock, flags);
|
|
}
|
|
|
|
done:
|
|
mutex_unlock(&shares_mutex);
|
|
return 0;
|
|
}
|
|
|
|
unsigned long sched_group_shares(struct task_group *tg)
|
|
{
|
|
return tg->shares;
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_RT_GROUP_SCHED
|
|
/*
|
|
* Ensure that the real time constraints are schedulable.
|
|
*/
|
|
static DEFINE_MUTEX(rt_constraints_mutex);
|
|
|
|
static unsigned long to_ratio(u64 period, u64 runtime)
|
|
{
|
|
if (runtime == RUNTIME_INF)
|
|
return 1ULL << 20;
|
|
|
|
return div64_u64(runtime << 20, period);
|
|
}
|
|
|
|
/* Must be called with tasklist_lock held */
|
|
static inline int tg_has_rt_tasks(struct task_group *tg)
|
|
{
|
|
struct task_struct *g, *p;
|
|
|
|
do_each_thread(g, p) {
|
|
if (rt_task(p) && rt_rq_of_se(&p->rt)->tg == tg)
|
|
return 1;
|
|
} while_each_thread(g, p);
|
|
|
|
return 0;
|
|
}
|
|
|
|
struct rt_schedulable_data {
|
|
struct task_group *tg;
|
|
u64 rt_period;
|
|
u64 rt_runtime;
|
|
};
|
|
|
|
static int tg_schedulable(struct task_group *tg, void *data)
|
|
{
|
|
struct rt_schedulable_data *d = data;
|
|
struct task_group *child;
|
|
unsigned long total, sum = 0;
|
|
u64 period, runtime;
|
|
|
|
period = ktime_to_ns(tg->rt_bandwidth.rt_period);
|
|
runtime = tg->rt_bandwidth.rt_runtime;
|
|
|
|
if (tg == d->tg) {
|
|
period = d->rt_period;
|
|
runtime = d->rt_runtime;
|
|
}
|
|
|
|
/*
|
|
* Cannot have more runtime than the period.
|
|
*/
|
|
if (runtime > period && runtime != RUNTIME_INF)
|
|
return -EINVAL;
|
|
|
|
/*
|
|
* Ensure we don't starve existing RT tasks.
|
|
*/
|
|
if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg))
|
|
return -EBUSY;
|
|
|
|
total = to_ratio(period, runtime);
|
|
|
|
/*
|
|
* Nobody can have more than the global setting allows.
|
|
*/
|
|
if (total > to_ratio(global_rt_period(), global_rt_runtime()))
|
|
return -EINVAL;
|
|
|
|
/*
|
|
* The sum of our children's runtime should not exceed our own.
|
|
*/
|
|
list_for_each_entry_rcu(child, &tg->children, siblings) {
|
|
period = ktime_to_ns(child->rt_bandwidth.rt_period);
|
|
runtime = child->rt_bandwidth.rt_runtime;
|
|
|
|
if (child == d->tg) {
|
|
period = d->rt_period;
|
|
runtime = d->rt_runtime;
|
|
}
|
|
|
|
sum += to_ratio(period, runtime);
|
|
}
|
|
|
|
if (sum > total)
|
|
return -EINVAL;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
|
|
{
|
|
struct rt_schedulable_data data = {
|
|
.tg = tg,
|
|
.rt_period = period,
|
|
.rt_runtime = runtime,
|
|
};
|
|
|
|
return walk_tg_tree(tg_schedulable, tg_nop, &data);
|
|
}
|
|
|
|
static int tg_set_bandwidth(struct task_group *tg,
|
|
u64 rt_period, u64 rt_runtime)
|
|
{
|
|
int i, err = 0;
|
|
|
|
mutex_lock(&rt_constraints_mutex);
|
|
read_lock(&tasklist_lock);
|
|
err = __rt_schedulable(tg, rt_period, rt_runtime);
|
|
if (err)
|
|
goto unlock;
|
|
|
|
raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
|
|
tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period);
|
|
tg->rt_bandwidth.rt_runtime = rt_runtime;
|
|
|
|
for_each_possible_cpu(i) {
|
|
struct rt_rq *rt_rq = tg->rt_rq[i];
|
|
|
|
raw_spin_lock(&rt_rq->rt_runtime_lock);
|
|
rt_rq->rt_runtime = rt_runtime;
|
|
raw_spin_unlock(&rt_rq->rt_runtime_lock);
|
|
}
|
|
raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
|
|
unlock:
|
|
read_unlock(&tasklist_lock);
|
|
mutex_unlock(&rt_constraints_mutex);
|
|
|
|
return err;
|
|
}
|
|
|
|
int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
|
|
{
|
|
u64 rt_runtime, rt_period;
|
|
|
|
rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period);
|
|
rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
|
|
if (rt_runtime_us < 0)
|
|
rt_runtime = RUNTIME_INF;
|
|
|
|
return tg_set_bandwidth(tg, rt_period, rt_runtime);
|
|
}
|
|
|
|
long sched_group_rt_runtime(struct task_group *tg)
|
|
{
|
|
u64 rt_runtime_us;
|
|
|
|
if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF)
|
|
return -1;
|
|
|
|
rt_runtime_us = tg->rt_bandwidth.rt_runtime;
|
|
do_div(rt_runtime_us, NSEC_PER_USEC);
|
|
return rt_runtime_us;
|
|
}
|
|
|
|
int sched_group_set_rt_period(struct task_group *tg, long rt_period_us)
|
|
{
|
|
u64 rt_runtime, rt_period;
|
|
|
|
rt_period = (u64)rt_period_us * NSEC_PER_USEC;
|
|
rt_runtime = tg->rt_bandwidth.rt_runtime;
|
|
|
|
if (rt_period == 0)
|
|
return -EINVAL;
|
|
|
|
return tg_set_bandwidth(tg, rt_period, rt_runtime);
|
|
}
|
|
|
|
long sched_group_rt_period(struct task_group *tg)
|
|
{
|
|
u64 rt_period_us;
|
|
|
|
rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period);
|
|
do_div(rt_period_us, NSEC_PER_USEC);
|
|
return rt_period_us;
|
|
}
|
|
|
|
static int sched_rt_global_constraints(void)
|
|
{
|
|
u64 runtime, period;
|
|
int ret = 0;
|
|
|
|
if (sysctl_sched_rt_period <= 0)
|
|
return -EINVAL;
|
|
|
|
runtime = global_rt_runtime();
|
|
period = global_rt_period();
|
|
|
|
/*
|
|
* Sanity check on the sysctl variables.
|
|
*/
|
|
if (runtime > period && runtime != RUNTIME_INF)
|
|
return -EINVAL;
|
|
|
|
mutex_lock(&rt_constraints_mutex);
|
|
read_lock(&tasklist_lock);
|
|
ret = __rt_schedulable(NULL, 0, 0);
|
|
read_unlock(&tasklist_lock);
|
|
mutex_unlock(&rt_constraints_mutex);
|
|
|
|
return ret;
|
|
}
|
|
|
|
int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
|
|
{
|
|
/* Don't accept realtime tasks when there is no way for them to run */
|
|
if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
|
|
return 0;
|
|
|
|
return 1;
|
|
}
|
|
|
|
#else /* !CONFIG_RT_GROUP_SCHED */
|
|
static int sched_rt_global_constraints(void)
|
|
{
|
|
unsigned long flags;
|
|
int i;
|
|
|
|
if (sysctl_sched_rt_period <= 0)
|
|
return -EINVAL;
|
|
|
|
/*
|
|
* There's always some RT tasks in the root group
|
|
* -- migration, kstopmachine etc..
|
|
*/
|
|
if (sysctl_sched_rt_runtime == 0)
|
|
return -EBUSY;
|
|
|
|
raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
|
|
for_each_possible_cpu(i) {
|
|
struct rt_rq *rt_rq = &cpu_rq(i)->rt;
|
|
|
|
raw_spin_lock(&rt_rq->rt_runtime_lock);
|
|
rt_rq->rt_runtime = global_rt_runtime();
|
|
raw_spin_unlock(&rt_rq->rt_runtime_lock);
|
|
}
|
|
raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
|
|
|
|
return 0;
|
|
}
|
|
#endif /* CONFIG_RT_GROUP_SCHED */
|
|
|
|
int sched_rt_handler(struct ctl_table *table, int write,
|
|
void __user *buffer, size_t *lenp,
|
|
loff_t *ppos)
|
|
{
|
|
int ret;
|
|
int old_period, old_runtime;
|
|
static DEFINE_MUTEX(mutex);
|
|
|
|
mutex_lock(&mutex);
|
|
old_period = sysctl_sched_rt_period;
|
|
old_runtime = sysctl_sched_rt_runtime;
|
|
|
|
ret = proc_dointvec(table, write, buffer, lenp, ppos);
|
|
|
|
if (!ret && write) {
|
|
ret = sched_rt_global_constraints();
|
|
if (ret) {
|
|
sysctl_sched_rt_period = old_period;
|
|
sysctl_sched_rt_runtime = old_runtime;
|
|
} else {
|
|
def_rt_bandwidth.rt_runtime = global_rt_runtime();
|
|
def_rt_bandwidth.rt_period =
|
|
ns_to_ktime(global_rt_period());
|
|
}
|
|
}
|
|
mutex_unlock(&mutex);
|
|
|
|
return ret;
|
|
}
|
|
|
|
#ifdef CONFIG_CGROUP_SCHED
|
|
|
|
/* return corresponding task_group object of a cgroup */
|
|
static inline struct task_group *cgroup_tg(struct cgroup *cgrp)
|
|
{
|
|
return container_of(cgroup_subsys_state(cgrp, cpu_cgroup_subsys_id),
|
|
struct task_group, css);
|
|
}
|
|
|
|
static struct cgroup_subsys_state *
|
|
cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp)
|
|
{
|
|
struct task_group *tg, *parent;
|
|
|
|
if (!cgrp->parent) {
|
|
/* This is early initialization for the top cgroup */
|
|
return &root_task_group.css;
|
|
}
|
|
|
|
parent = cgroup_tg(cgrp->parent);
|
|
tg = sched_create_group(parent);
|
|
if (IS_ERR(tg))
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
return &tg->css;
|
|
}
|
|
|
|
static void
|
|
cpu_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
|
|
{
|
|
struct task_group *tg = cgroup_tg(cgrp);
|
|
|
|
sched_destroy_group(tg);
|
|
}
|
|
|
|
static int
|
|
cpu_cgroup_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
|
|
{
|
|
#ifdef CONFIG_RT_GROUP_SCHED
|
|
if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk))
|
|
return -EINVAL;
|
|
#else
|
|
/* We don't support RT-tasks being in separate groups */
|
|
if (tsk->sched_class != &fair_sched_class)
|
|
return -EINVAL;
|
|
#endif
|
|
return 0;
|
|
}
|
|
|
|
static int
|
|
cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
|
|
struct task_struct *tsk, bool threadgroup)
|
|
{
|
|
int retval = cpu_cgroup_can_attach_task(cgrp, tsk);
|
|
if (retval)
|
|
return retval;
|
|
if (threadgroup) {
|
|
struct task_struct *c;
|
|
rcu_read_lock();
|
|
list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
|
|
retval = cpu_cgroup_can_attach_task(cgrp, c);
|
|
if (retval) {
|
|
rcu_read_unlock();
|
|
return retval;
|
|
}
|
|
}
|
|
rcu_read_unlock();
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static void
|
|
cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
|
|
struct cgroup *old_cont, struct task_struct *tsk,
|
|
bool threadgroup)
|
|
{
|
|
sched_move_task(tsk);
|
|
if (threadgroup) {
|
|
struct task_struct *c;
|
|
rcu_read_lock();
|
|
list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
|
|
sched_move_task(c);
|
|
}
|
|
rcu_read_unlock();
|
|
}
|
|
}
|
|
|
|
static void
|
|
cpu_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
|
|
struct cgroup *old_cgrp, struct task_struct *task)
|
|
{
|
|
/*
|
|
* cgroup_exit() is called in the copy_process() failure path.
|
|
* Ignore this case since the task hasn't ran yet, this avoids
|
|
* trying to poke a half freed task state from generic code.
|
|
*/
|
|
if (!(task->flags & PF_EXITING))
|
|
return;
|
|
|
|
sched_move_task(task);
|
|
}
|
|
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
static int cpu_shares_write_u64(struct cgroup *cgrp, struct cftype *cftype,
|
|
u64 shareval)
|
|
{
|
|
return sched_group_set_shares(cgroup_tg(cgrp), shareval);
|
|
}
|
|
|
|
static u64 cpu_shares_read_u64(struct cgroup *cgrp, struct cftype *cft)
|
|
{
|
|
struct task_group *tg = cgroup_tg(cgrp);
|
|
|
|
return (u64) tg->shares;
|
|
}
|
|
#endif /* CONFIG_FAIR_GROUP_SCHED */
|
|
|
|
#ifdef CONFIG_RT_GROUP_SCHED
|
|
static int cpu_rt_runtime_write(struct cgroup *cgrp, struct cftype *cft,
|
|
s64 val)
|
|
{
|
|
return sched_group_set_rt_runtime(cgroup_tg(cgrp), val);
|
|
}
|
|
|
|
static s64 cpu_rt_runtime_read(struct cgroup *cgrp, struct cftype *cft)
|
|
{
|
|
return sched_group_rt_runtime(cgroup_tg(cgrp));
|
|
}
|
|
|
|
static int cpu_rt_period_write_uint(struct cgroup *cgrp, struct cftype *cftype,
|
|
u64 rt_period_us)
|
|
{
|
|
return sched_group_set_rt_period(cgroup_tg(cgrp), rt_period_us);
|
|
}
|
|
|
|
static u64 cpu_rt_period_read_uint(struct cgroup *cgrp, struct cftype *cft)
|
|
{
|
|
return sched_group_rt_period(cgroup_tg(cgrp));
|
|
}
|
|
#endif /* CONFIG_RT_GROUP_SCHED */
|
|
|
|
static struct cftype cpu_files[] = {
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
{
|
|
.name = "shares",
|
|
.read_u64 = cpu_shares_read_u64,
|
|
.write_u64 = cpu_shares_write_u64,
|
|
},
|
|
#endif
|
|
#ifdef CONFIG_RT_GROUP_SCHED
|
|
{
|
|
.name = "rt_runtime_us",
|
|
.read_s64 = cpu_rt_runtime_read,
|
|
.write_s64 = cpu_rt_runtime_write,
|
|
},
|
|
{
|
|
.name = "rt_period_us",
|
|
.read_u64 = cpu_rt_period_read_uint,
|
|
.write_u64 = cpu_rt_period_write_uint,
|
|
},
|
|
#endif
|
|
};
|
|
|
|
static int cpu_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cont)
|
|
{
|
|
return cgroup_add_files(cont, ss, cpu_files, ARRAY_SIZE(cpu_files));
|
|
}
|
|
|
|
struct cgroup_subsys cpu_cgroup_subsys = {
|
|
.name = "cpu",
|
|
.create = cpu_cgroup_create,
|
|
.destroy = cpu_cgroup_destroy,
|
|
.can_attach = cpu_cgroup_can_attach,
|
|
.attach = cpu_cgroup_attach,
|
|
.exit = cpu_cgroup_exit,
|
|
.populate = cpu_cgroup_populate,
|
|
.subsys_id = cpu_cgroup_subsys_id,
|
|
.early_init = 1,
|
|
};
|
|
|
|
#endif /* CONFIG_CGROUP_SCHED */
|
|
|
|
#ifdef CONFIG_CGROUP_CPUACCT
|
|
|
|
/*
|
|
* CPU accounting code for task groups.
|
|
*
|
|
* Based on the work by Paul Menage (menage@google.com) and Balbir Singh
|
|
* (balbir@in.ibm.com).
|
|
*/
|
|
|
|
/* 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 percpu_counter cpustat[CPUACCT_STAT_NSTATS];
|
|
struct cpuacct *parent;
|
|
};
|
|
|
|
struct cgroup_subsys cpuacct_subsys;
|
|
|
|
/* 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);
|
|
}
|
|
|
|
/* create a new cpu accounting group */
|
|
static struct cgroup_subsys_state *cpuacct_create(
|
|
struct cgroup_subsys *ss, struct cgroup *cgrp)
|
|
{
|
|
struct cpuacct *ca = kzalloc(sizeof(*ca), GFP_KERNEL);
|
|
int i;
|
|
|
|
if (!ca)
|
|
goto out;
|
|
|
|
ca->cpuusage = alloc_percpu(u64);
|
|
if (!ca->cpuusage)
|
|
goto out_free_ca;
|
|
|
|
for (i = 0; i < CPUACCT_STAT_NSTATS; i++)
|
|
if (percpu_counter_init(&ca->cpustat[i], 0))
|
|
goto out_free_counters;
|
|
|
|
if (cgrp->parent)
|
|
ca->parent = cgroup_ca(cgrp->parent);
|
|
|
|
return &ca->css;
|
|
|
|
out_free_counters:
|
|
while (--i >= 0)
|
|
percpu_counter_destroy(&ca->cpustat[i]);
|
|
free_percpu(ca->cpuusage);
|
|
out_free_ca:
|
|
kfree(ca);
|
|
out:
|
|
return ERR_PTR(-ENOMEM);
|
|
}
|
|
|
|
/* destroy an existing cpu accounting group */
|
|
static void
|
|
cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
|
|
{
|
|
struct cpuacct *ca = cgroup_ca(cgrp);
|
|
int i;
|
|
|
|
for (i = 0; i < CPUACCT_STAT_NSTATS; i++)
|
|
percpu_counter_destroy(&ca->cpustat[i]);
|
|
free_percpu(ca->cpuusage);
|
|
kfree(ca);
|
|
}
|
|
|
|
static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
|
|
{
|
|
u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
|
|
u64 data;
|
|
|
|
#ifndef CONFIG_64BIT
|
|
/*
|
|
* Take rq->lock to make 64-bit read safe on 32-bit platforms.
|
|
*/
|
|
raw_spin_lock_irq(&cpu_rq(cpu)->lock);
|
|
data = *cpuusage;
|
|
raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
|
|
#else
|
|
data = *cpuusage;
|
|
#endif
|
|
|
|
return data;
|
|
}
|
|
|
|
static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
|
|
{
|
|
u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
|
|
|
|
#ifndef CONFIG_64BIT
|
|
/*
|
|
* Take rq->lock to make 64-bit write safe on 32-bit platforms.
|
|
*/
|
|
raw_spin_lock_irq(&cpu_rq(cpu)->lock);
|
|
*cpuusage = val;
|
|
raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
|
|
#else
|
|
*cpuusage = val;
|
|
#endif
|
|
}
|
|
|
|
/* return total cpu usage (in nanoseconds) of a group */
|
|
static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft)
|
|
{
|
|
struct cpuacct *ca = cgroup_ca(cgrp);
|
|
u64 totalcpuusage = 0;
|
|
int i;
|
|
|
|
for_each_present_cpu(i)
|
|
totalcpuusage += cpuacct_cpuusage_read(ca, i);
|
|
|
|
return totalcpuusage;
|
|
}
|
|
|
|
static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype,
|
|
u64 reset)
|
|
{
|
|
struct cpuacct *ca = cgroup_ca(cgrp);
|
|
int err = 0;
|
|
int i;
|
|
|
|
if (reset) {
|
|
err = -EINVAL;
|
|
goto out;
|
|
}
|
|
|
|
for_each_present_cpu(i)
|
|
cpuacct_cpuusage_write(ca, i, 0);
|
|
|
|
out:
|
|
return err;
|
|
}
|
|
|
|
static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft,
|
|
struct seq_file *m)
|
|
{
|
|
struct cpuacct *ca = cgroup_ca(cgroup);
|
|
u64 percpu;
|
|
int i;
|
|
|
|
for_each_present_cpu(i) {
|
|
percpu = cpuacct_cpuusage_read(ca, i);
|
|
seq_printf(m, "%llu ", (unsigned long long) percpu);
|
|
}
|
|
seq_printf(m, "\n");
|
|
return 0;
|
|
}
|
|
|
|
static const char *cpuacct_stat_desc[] = {
|
|
[CPUACCT_STAT_USER] = "user",
|
|
[CPUACCT_STAT_SYSTEM] = "system",
|
|
};
|
|
|
|
static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft,
|
|
struct cgroup_map_cb *cb)
|
|
{
|
|
struct cpuacct *ca = cgroup_ca(cgrp);
|
|
int i;
|
|
|
|
for (i = 0; i < CPUACCT_STAT_NSTATS; i++) {
|
|
s64 val = percpu_counter_read(&ca->cpustat[i]);
|
|
val = cputime64_to_clock_t(val);
|
|
cb->fill(cb, cpuacct_stat_desc[i], val);
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static struct cftype files[] = {
|
|
{
|
|
.name = "usage",
|
|
.read_u64 = cpuusage_read,
|
|
.write_u64 = cpuusage_write,
|
|
},
|
|
{
|
|
.name = "usage_percpu",
|
|
.read_seq_string = cpuacct_percpu_seq_read,
|
|
},
|
|
{
|
|
.name = "stat",
|
|
.read_map = cpuacct_stats_show,
|
|
},
|
|
};
|
|
|
|
static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
|
|
{
|
|
return cgroup_add_files(cgrp, ss, files, ARRAY_SIZE(files));
|
|
}
|
|
|
|
/*
|
|
* charge this task's execution time to its accounting group.
|
|
*
|
|
* called with rq->lock held.
|
|
*/
|
|
static void cpuacct_charge(struct task_struct *tsk, u64 cputime)
|
|
{
|
|
struct cpuacct *ca;
|
|
int cpu;
|
|
|
|
if (unlikely(!cpuacct_subsys.active))
|
|
return;
|
|
|
|
cpu = task_cpu(tsk);
|
|
|
|
rcu_read_lock();
|
|
|
|
ca = task_ca(tsk);
|
|
|
|
for (; ca; ca = ca->parent) {
|
|
u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
|
|
*cpuusage += cputime;
|
|
}
|
|
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
/*
|
|
* When CONFIG_VIRT_CPU_ACCOUNTING is enabled one jiffy can be very large
|
|
* in cputime_t units. As a result, cpuacct_update_stats calls
|
|
* percpu_counter_add with values large enough to always overflow the
|
|
* per cpu batch limit causing bad SMP scalability.
|
|
*
|
|
* To fix this we scale percpu_counter_batch by cputime_one_jiffy so we
|
|
* batch the same amount of time with CONFIG_VIRT_CPU_ACCOUNTING disabled
|
|
* and enabled. We cap it at INT_MAX which is the largest allowed batch value.
|
|
*/
|
|
#ifdef CONFIG_SMP
|
|
#define CPUACCT_BATCH \
|
|
min_t(long, percpu_counter_batch * cputime_one_jiffy, INT_MAX)
|
|
#else
|
|
#define CPUACCT_BATCH 0
|
|
#endif
|
|
|
|
/*
|
|
* Charge the system/user time to the task's accounting group.
|
|
*/
|
|
static void cpuacct_update_stats(struct task_struct *tsk,
|
|
enum cpuacct_stat_index idx, cputime_t val)
|
|
{
|
|
struct cpuacct *ca;
|
|
int batch = CPUACCT_BATCH;
|
|
|
|
if (unlikely(!cpuacct_subsys.active))
|
|
return;
|
|
|
|
rcu_read_lock();
|
|
ca = task_ca(tsk);
|
|
|
|
do {
|
|
__percpu_counter_add(&ca->cpustat[idx], val, batch);
|
|
ca = ca->parent;
|
|
} while (ca);
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
struct cgroup_subsys cpuacct_subsys = {
|
|
.name = "cpuacct",
|
|
.create = cpuacct_create,
|
|
.destroy = cpuacct_destroy,
|
|
.populate = cpuacct_populate,
|
|
.subsys_id = cpuacct_subsys_id,
|
|
};
|
|
#endif /* CONFIG_CGROUP_CPUACCT */
|
|
|