kernel-fxtec-pro1x/kernel/sched/sched.h

1368 lines
35 KiB
C
Raw Normal View History

#include <linux/sched.h>
#include <linux/sched/sysctl.h>
#include <linux/sched/rt.h>
#include <linux/mutex.h>
#include <linux/spinlock.h>
#include <linux/stop_machine.h>
#include <linux/tick.h>
#include "cpupri.h"
#include "cpuacct.h"
struct rq;
extern __read_mostly int scheduler_running;
extern unsigned long calc_load_update;
extern atomic_long_t calc_load_tasks;
extern long calc_load_fold_active(struct rq *this_rq);
extern void update_cpu_load_active(struct rq *this_rq);
/*
* 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))
/*
* Increase resolution of nice-level calculations for 64-bit architectures.
* The extra resolution improves shares distribution and load balancing of
* low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup
* hierarchies, especially on larger systems. This is not a user-visible change
* and does not change the user-interface for setting shares/weights.
*
* We increase resolution only if we have enough bits to allow this increased
* resolution (i.e. BITS_PER_LONG > 32). The costs for increasing resolution
* when BITS_PER_LONG <= 32 are pretty high and the returns do not justify the
* increased costs.
*/
#if 0 /* BITS_PER_LONG > 32 -- currently broken: it increases power usage under light load */
# define SCHED_LOAD_RESOLUTION 10
# define scale_load(w) ((w) << SCHED_LOAD_RESOLUTION)
# define scale_load_down(w) ((w) >> SCHED_LOAD_RESOLUTION)
#else
# define SCHED_LOAD_RESOLUTION 0
# define scale_load(w) (w)
# define scale_load_down(w) (w)
#endif
#define SCHED_LOAD_SHIFT (10 + SCHED_LOAD_RESOLUTION)
#define SCHED_LOAD_SCALE (1L << SCHED_LOAD_SHIFT)
#define NICE_0_LOAD SCHED_LOAD_SCALE
#define NICE_0_SHIFT SCHED_LOAD_SHIFT
/*
* These are the 'tuning knobs' of the scheduler:
*/
/*
* single value that denotes runtime == period, ie unlimited time.
*/
#define RUNTIME_INF ((u64)~0ULL)
static inline int rt_policy(int policy)
{
if (policy == SCHED_FIFO || policy == SCHED_RR)
return 1;
return 0;
}
static inline int task_has_rt_policy(struct task_struct *p)
{
return rt_policy(p->policy);
}
/*
* This is the priority-queue data structure of the RT scheduling class:
*/
struct rt_prio_array {
DECLARE_BITMAP(bitmap, MAX_RT_PRIO+1); /* include 1 bit for delimiter */
struct list_head queue[MAX_RT_PRIO];
};
struct rt_bandwidth {
/* nests inside the rq lock: */
raw_spinlock_t rt_runtime_lock;
ktime_t rt_period;
u64 rt_runtime;
struct hrtimer rt_period_timer;
};
extern struct mutex sched_domains_mutex;
#ifdef CONFIG_CGROUP_SCHED
#include <linux/cgroup.h>
struct cfs_rq;
struct rt_rq;
extern struct list_head task_groups;
struct cfs_bandwidth {
#ifdef CONFIG_CFS_BANDWIDTH
raw_spinlock_t lock;
ktime_t period;
u64 quota, runtime;
s64 hierarchal_quota;
u64 runtime_expires;
int idle, timer_active;
struct hrtimer period_timer, slack_timer;
struct list_head throttled_cfs_rq;
/* statistics */
int nr_periods, nr_throttled;
u64 throttled_time;
#endif
};
/* task group related information */
struct task_group {
struct cgroup_subsys_state css;
#ifdef CONFIG_FAIR_GROUP_SCHED
/* schedulable entities of this group on each cpu */
struct sched_entity **se;
/* runqueue "owned" by this group on each cpu */
struct cfs_rq **cfs_rq;
unsigned long shares;
#ifdef CONFIG_SMP
atomic_long_t load_avg;
atomic_t runnable_avg;
#endif
#endif
#ifdef CONFIG_RT_GROUP_SCHED
struct sched_rt_entity **rt_se;
struct rt_rq **rt_rq;
struct rt_bandwidth rt_bandwidth;
#endif
struct rcu_head rcu;
struct list_head list;
struct task_group *parent;
struct list_head siblings;
struct list_head children;
#ifdef CONFIG_SCHED_AUTOGROUP
struct autogroup *autogroup;
#endif
struct cfs_bandwidth cfs_bandwidth;
};
#ifdef CONFIG_FAIR_GROUP_SCHED
#define ROOT_TASK_GROUP_LOAD NICE_0_LOAD
/*
* A weight of 0 or 1 can cause arithmetics problems.
* A weight of a cfs_rq is the sum of weights of which entities
* are queued on this cfs_rq, so a weight of a entity should not be
* too large, so as the shares value of a task group.
* (The default weight is 1024 - so there's no practical
* limitation from this.)
*/
#define MIN_SHARES (1UL << 1)
#define MAX_SHARES (1UL << 18)
#endif
typedef int (*tg_visitor)(struct task_group *, void *);
extern int walk_tg_tree_from(struct task_group *from,
tg_visitor down, tg_visitor up, void *data);
/*
* Iterate the full tree, calling @down when first entering a node and @up when
* leaving it for the final time.
*
* Caller must hold rcu_lock or sufficient equivalent.
*/
static inline int walk_tg_tree(tg_visitor down, tg_visitor up, void *data)
{
return walk_tg_tree_from(&root_task_group, down, up, data);
}
extern int tg_nop(struct task_group *tg, void *data);
extern void free_fair_sched_group(struct task_group *tg);
extern int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent);
extern void unregister_fair_sched_group(struct task_group *tg, int cpu);
extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
struct sched_entity *se, int cpu,
struct sched_entity *parent);
extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
extern void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq);
extern void free_rt_sched_group(struct task_group *tg);
extern int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent);
extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
struct sched_rt_entity *rt_se, int cpu,
struct sched_rt_entity *parent);
extern struct task_group *sched_create_group(struct task_group *parent);
extern void sched_online_group(struct task_group *tg,
struct task_group *parent);
extern void sched_destroy_group(struct task_group *tg);
extern void sched_offline_group(struct task_group *tg);
extern void sched_move_task(struct task_struct *tsk);
#ifdef CONFIG_FAIR_GROUP_SCHED
extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
#endif
#else /* CONFIG_CGROUP_SCHED */
struct cfs_bandwidth { };
#endif /* CONFIG_CGROUP_SCHED */
/* CFS-related fields in a runqueue */
struct cfs_rq {
struct load_weight load;
unsigned int nr_running, h_nr_running;
u64 exec_clock;
u64 min_vruntime;
#ifndef CONFIG_64BIT
u64 min_vruntime_copy;
#endif
struct rb_root tasks_timeline;
struct rb_node *rb_leftmost;
/*
* 'curr' points to currently running entity on this cfs_rq.
* It is set to NULL otherwise (i.e when none are currently running).
*/
struct sched_entity *curr, *next, *last, *skip;
#ifdef CONFIG_SCHED_DEBUG
unsigned int nr_spread_over;
#endif
#ifdef CONFIG_SMP
/*
* CFS Load tracking
* Under CFS, load is tracked on a per-entity basis and aggregated up.
* This allows for the description of both thread and group usage (in
* the FAIR_GROUP_SCHED case).
*/
unsigned long runnable_load_avg, blocked_load_avg;
atomic64_t decay_counter;
u64 last_decay;
atomic_long_t removed_load;
#ifdef CONFIG_FAIR_GROUP_SCHED
/* Required to track per-cpu representation of a task_group */
u32 tg_runnable_contrib;
unsigned long tg_load_contrib;
/*
* h_load = weight * f(tg)
*
* Where f(tg) is the recursive weight fraction assigned to
* this group.
*/
unsigned long h_load;
sched: Move h_load calculation to task_h_load() The bad thing about update_h_load(), which computes hierarchical load factor for task groups, is that it is called for each task group in the system before every load balancer run, and since rebalance can be triggered very often, this function can eat really a lot of cpu time if there are many cpu cgroups in the system. Although the situation was improved significantly by commit a35b646 ('sched, cgroup: Reduce rq->lock hold times for large cgroup hierarchies'), the problem still can arise under some kinds of loads, e.g. when cpus are switching from idle to busy and back very frequently. For instance, when I start 1000 of processes that wake up every millisecond on my 8 cpus host, 'top' and 'perf top' show: Cpu(s): 17.8%us, 24.3%sy, 0.0%ni, 57.9%id, 0.0%wa, 0.0%hi, 0.0%si Events: 243K cycles 7.57% [kernel] [k] __schedule 7.08% [kernel] [k] timerqueue_add 6.13% libc-2.12.so [.] usleep Then if I create 10000 *idle* cpu cgroups (no processes in them), cpu usage increases significantly although the 'wakers' are still executing in the root cpu cgroup: Cpu(s): 19.1%us, 48.7%sy, 0.0%ni, 31.6%id, 0.0%wa, 0.0%hi, 0.7%si Events: 230K cycles 24.56% [kernel] [k] tg_load_down 5.76% [kernel] [k] __schedule This happens because this particular kind of load triggers 'new idle' rebalance very frequently, which requires calling update_h_load(), which, in turn, calls tg_load_down() for every *idle* cpu cgroup even though it is absolutely useless, because idle cpu cgroups have no tasks to pull. This patch tries to improve the situation by making h_load calculation proceed only when h_load is really necessary. To achieve this, it substitutes update_h_load() with update_cfs_rq_h_load(), which computes h_load only for a given cfs_rq and all its ascendants, and makes the load balancer call this function whenever it considers if a task should be pulled, i.e. it moves h_load calculations directly to task_h_load(). For h_load of the same cfs_rq not to be updated multiple times (in case several tasks in the same cgroup are considered during the same balance run), the patch keeps the time of the last h_load update for each cfs_rq and breaks calculation when it finds h_load to be uptodate. The benefit of it is that h_load is computed only for those cfs_rq's, which really need it, in particular all idle task groups are skipped. Although this, in fact, moves h_load calculation under rq lock, it should not affect latency much, because the amount of work done under rq lock while trying to pull tasks is limited by sched_nr_migrate. After the patch applied with the setup described above (1000 wakers in the root cgroup and 10000 idle cgroups), I get: Cpu(s): 16.9%us, 24.8%sy, 0.0%ni, 58.4%id, 0.0%wa, 0.0%hi, 0.0%si Events: 242K cycles 7.57% [kernel] [k] __schedule 6.70% [kernel] [k] timerqueue_add 5.93% libc-2.12.so [.] usleep Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1373896159-1278-1-git-send-email-vdavydov@parallels.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-07-15 07:49:19 -06:00
u64 last_h_load_update;
struct sched_entity *h_load_next;
#endif /* CONFIG_FAIR_GROUP_SCHED */
#endif /* CONFIG_SMP */
#ifdef CONFIG_FAIR_GROUP_SCHED
struct rq *rq; /* cpu runqueue to which this cfs_rq is attached */
/*
* leaf cfs_rqs are those that hold tasks (lowest schedulable entity in
* a hierarchy). Non-leaf lrqs hold other higher schedulable entities
* (like users, containers etc.)
*
* leaf_cfs_rq_list ties together list of leaf cfs_rq's in a cpu. This
* list is used during load balance.
*/
int on_list;
struct list_head leaf_cfs_rq_list;
struct task_group *tg; /* group that "owns" this runqueue */
#ifdef CONFIG_CFS_BANDWIDTH
int runtime_enabled;
u64 runtime_expires;
s64 runtime_remaining;
u64 throttled_clock, throttled_clock_task;
u64 throttled_clock_task_time;
int throttled, throttle_count;
struct list_head throttled_list;
#endif /* CONFIG_CFS_BANDWIDTH */
#endif /* CONFIG_FAIR_GROUP_SCHED */
};
static inline int rt_bandwidth_enabled(void)
{
return sysctl_sched_rt_runtime >= 0;
}
/* Real-Time classes' related field in a runqueue: */
struct rt_rq {
struct rt_prio_array active;
unsigned int rt_nr_running;
#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
struct {
int curr; /* highest queued rt task prio */
#ifdef CONFIG_SMP
int next; /* next highest */
#endif
} highest_prio;
#endif
#ifdef CONFIG_SMP
unsigned long rt_nr_migratory;
unsigned long rt_nr_total;
int overloaded;
struct plist_head pushable_tasks;
#endif
int rt_throttled;
u64 rt_time;
u64 rt_runtime;
/* Nests inside the rq lock: */
raw_spinlock_t rt_runtime_lock;
#ifdef CONFIG_RT_GROUP_SCHED
unsigned long rt_nr_boosted;
struct rq *rq;
struct task_group *tg;
#endif
};
#ifdef CONFIG_SMP
/*
* We add the notion of a root-domain which will be used to define per-domain
* variables. Each exclusive cpuset essentially defines an island domain by
* fully partitioning the member cpus from any other cpuset. Whenever a new
* exclusive cpuset is created, we also create and attach a new root-domain
* object.
*
*/
struct root_domain {
atomic_t refcount;
atomic_t rto_count;
struct rcu_head rcu;
cpumask_var_t span;
cpumask_var_t online;
/*
* The "RT overload" flag: it gets set if a CPU has more than
* one runnable RT task.
*/
cpumask_var_t rto_mask;
struct cpupri cpupri;
};
extern struct root_domain def_root_domain;
#endif /* CONFIG_SMP */
/*
* This is the main, per-CPU runqueue data structure.
*
* Locking rule: those places that want to lock multiple runqueues
* (such as the load balancing or the thread migration code), lock
* acquire operations must be ordered by ascending &runqueue.
*/
struct rq {
/* runqueue lock: */
raw_spinlock_t lock;
/*
* nr_running and cpu_load should be in the same cacheline because
* remote CPUs use both these fields when doing load calculation.
*/
unsigned int nr_running;
#define CPU_LOAD_IDX_MAX 5
unsigned long cpu_load[CPU_LOAD_IDX_MAX];
unsigned long last_load_update_tick;
nohz: Rename CONFIG_NO_HZ to CONFIG_NO_HZ_COMMON We are planning to convert the dynticks Kconfig options layout into a choice menu. The user must be able to easily pick any of the following implementations: constant periodic tick, idle dynticks, full dynticks. As this implies a mutual exclusion, the two dynticks implementions need to converge on the selection of a common Kconfig option in order to ease the sharing of a common infrastructure. It would thus seem pretty natural to reuse CONFIG_NO_HZ to that end. It already implements all the idle dynticks code and the full dynticks depends on all that code for now. So ideally the choice menu would propose CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED then both would select CONFIG_NO_HZ. On the other hand we want to stay backward compatible: if CONFIG_NO_HZ is set in an older config file, we want to enable CONFIG_NO_HZ_IDLE by default. But we can't afford both at the same time or we run into a circular dependency: 1) CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED both select CONFIG_NO_HZ 2) If CONFIG_NO_HZ is set, we default to CONFIG_NO_HZ_IDLE We might be able to support that from Kconfig/Kbuild but it may not be wise to introduce such a confusing behaviour. So to solve this, create a new CONFIG_NO_HZ_COMMON option which gathers the common code between idle and full dynticks (that common code for now is simply the idle dynticks code) and select it from their referring Kconfig. Then we'll later create CONFIG_NO_HZ_IDLE and map CONFIG_NO_HZ to it for backward compatibility. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Christoph Lameter <cl@linux.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Gilad Ben Yossef <gilad@benyossef.com> Cc: Hakan Akkan <hakanakkan@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de>
2011-08-10 15:21:01 -06:00
#ifdef CONFIG_NO_HZ_COMMON
u64 nohz_stamp;
unsigned long nohz_flags;
#endif
#ifdef CONFIG_NO_HZ_FULL
unsigned long last_sched_tick;
#endif
int skip_clock_update;
/* capture load from *all* tasks on this cpu: */
struct load_weight load;
unsigned long nr_load_updates;
u64 nr_switches;
struct cfs_rq cfs;
struct rt_rq rt;
#ifdef CONFIG_FAIR_GROUP_SCHED
/* list of leaf cfs_rq on this cpu: */
struct list_head leaf_cfs_rq_list;
sched, cgroup: Reduce rq->lock hold times for large cgroup hierarchies Peter Portante reported that for large cgroup hierarchies (and or on large CPU counts) we get immense lock contention on rq->lock and stuff stops working properly. His workload was a ton of processes, each in their own cgroup, everybody idling except for a sporadic wakeup once every so often. It was found that: schedule() idle_balance() load_balance() local_irq_save() double_rq_lock() update_h_load() walk_tg_tree(tg_load_down) tg_load_down() Results in an entire cgroup hierarchy walk under rq->lock for every new-idle balance and since new-idle balance isn't throttled this results in a lot of work while holding the rq->lock. This patch does two things, it removes the work from under rq->lock based on the good principle of race and pray which is widely employed in the load-balancer as a whole. And secondly it throttles the update_h_load() calculation to max once per jiffy. I considered excluding update_h_load() for new-idle balance all-together, but purely relying on regular balance passes to update this data might not work out under some rare circumstances where the new-idle busiest isn't the regular busiest for a while (unlikely, but a nightmare to debug if someone hits it and suffers). Cc: pjt@google.com Cc: Larry Woodman <lwoodman@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Reported-by: Peter Portante <pportant@redhat.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/n/tip-aaarrzfpnaam7pqrekofu8a6@git.kernel.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2012-08-08 13:46:40 -06:00
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
struct list_head leaf_rt_rq_list;
#endif
/*
* This is part of a global counter where only the total sum
* over all CPUs matters. A task can increase this counter on
* one CPU and if it got migrated afterwards it may decrease
* it on another CPU. Always updated under the runqueue lock:
*/
unsigned long nr_uninterruptible;
struct task_struct *curr, *idle, *stop;
unsigned long next_balance;
struct mm_struct *prev_mm;
u64 clock;
u64 clock_task;
atomic_t nr_iowait;
#ifdef CONFIG_SMP
struct root_domain *rd;
struct sched_domain *sd;
unsigned long cpu_power;
unsigned char idle_balance;
/* For active balancing */
int post_schedule;
int active_balance;
int push_cpu;
struct cpu_stop_work active_balance_work;
/* cpu of this runqueue: */
int cpu;
int online;
struct list_head cfs_tasks;
u64 rt_avg;
u64 age_stamp;
u64 idle_stamp;
u64 avg_idle;
#endif
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
u64 prev_irq_time;
#endif
#ifdef CONFIG_PARAVIRT
u64 prev_steal_time;
#endif
#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
u64 prev_steal_time_rq;
#endif
/* calc_load related fields */
unsigned long calc_load_update;
long calc_load_active;
#ifdef CONFIG_SCHED_HRTICK
#ifdef CONFIG_SMP
int hrtick_csd_pending;
struct call_single_data hrtick_csd;
#endif
struct hrtimer hrtick_timer;
#endif
#ifdef CONFIG_SCHEDSTATS
/* latency stats */
struct sched_info rq_sched_info;
unsigned long long rq_cpu_time;
/* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */
/* sys_sched_yield() stats */
unsigned int yld_count;
/* schedule() stats */
unsigned int sched_count;
unsigned int sched_goidle;
/* try_to_wake_up() stats */
unsigned int ttwu_count;
unsigned int ttwu_local;
#endif
#ifdef CONFIG_SMP
struct llist_head wake_list;
#endif
struct sched_avg avg;
};
static inline int cpu_of(struct rq *rq)
{
#ifdef CONFIG_SMP
return rq->cpu;
#else
return 0;
#endif
}
DECLARE_PER_CPU(struct rq, runqueues);
#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu)))
#define this_rq() (&__get_cpu_var(runqueues))
#define task_rq(p) cpu_rq(task_cpu(p))
#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
#define raw_rq() (&__raw_get_cpu_var(runqueues))
static inline u64 rq_clock(struct rq *rq)
{
return rq->clock;
}
static inline u64 rq_clock_task(struct rq *rq)
{
return rq->clock_task;
}
#ifdef CONFIG_SMP
#define rcu_dereference_check_sched_domain(p) \
rcu_dereference_check((p), \
lockdep_is_held(&sched_domains_mutex))
/*
* The domain tree (rq->sd) is protected by RCU's quiescent state transition.
* See detach_destroy_domains: synchronize_sched for details.
*
* The domain tree of any CPU may only be accessed from within
* preempt-disabled sections.
*/
#define for_each_domain(cpu, __sd) \
for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); \
__sd; __sd = __sd->parent)
#define for_each_lower_domain(sd) for (; sd; sd = sd->child)
/**
* highest_flag_domain - Return highest sched_domain containing flag.
* @cpu: The cpu whose highest level of sched domain is to
* be returned.
* @flag: The flag to check for the highest sched_domain
* for the given cpu.
*
* Returns the highest sched_domain of a cpu which contains the given flag.
*/
static inline struct sched_domain *highest_flag_domain(int cpu, int flag)
{
struct sched_domain *sd, *hsd = NULL;
for_each_domain(cpu, sd) {
if (!(sd->flags & flag))
break;
hsd = sd;
}
return hsd;
}
DECLARE_PER_CPU(struct sched_domain *, sd_llc);
DECLARE_PER_CPU(int, sd_llc_size);
DECLARE_PER_CPU(int, sd_llc_id);
struct sched_group_power {
atomic_t ref;
/*
* CPU power of this group, SCHED_LOAD_SCALE being max power for a
* single CPU.
*/
unsigned int power, power_orig;
unsigned long next_update;
int imbalance; /* XXX unrelated to power but shared group state */
/*
* Number of busy cpus in this group.
*/
atomic_t nr_busy_cpus;
unsigned long cpumask[0]; /* iteration mask */
};
struct sched_group {
struct sched_group *next; /* Must be a circular list */
atomic_t ref;
unsigned int group_weight;
struct sched_group_power *sgp;
/*
* The CPUs this group covers.
*
* NOTE: this field is variable length. (Allocated dynamically
* by attaching extra space to the end of the structure,
* depending on how many CPUs the kernel has booted up with)
*/
unsigned long cpumask[0];
};
static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
{
return to_cpumask(sg->cpumask);
}
/*
* cpumask masking which cpus in the group are allowed to iterate up the domain
* tree.
*/
static inline struct cpumask *sched_group_mask(struct sched_group *sg)
{
return to_cpumask(sg->sgp->cpumask);
}
/**
* group_first_cpu - Returns the first cpu in the cpumask of a sched_group.
* @group: The group whose first cpu is to be returned.
*/
static inline unsigned int group_first_cpu(struct sched_group *group)
{
return cpumask_first(sched_group_cpus(group));
}
extern int group_balance_cpu(struct sched_group *sg);
#endif /* CONFIG_SMP */
#include "stats.h"
#include "auto_group.h"
#ifdef CONFIG_CGROUP_SCHED
/*
* Return the group to which this tasks belongs.
*
* We cannot use task_css() and friends because the cgroup subsystem
* changes that value before the cgroup_subsys::attach() method is called,
* therefore we cannot pin it and might observe the wrong value.
*
* The same is true for autogroup's p->signal->autogroup->tg, the autogroup
* core changes this before calling sched_move_task().
*
* Instead we use a 'copy' which is updated from sched_move_task() while
* holding both task_struct::pi_lock and rq::lock.
*/
static inline struct task_group *task_group(struct task_struct *p)
{
return p->sched_task_group;
}
/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
{
#if defined(CONFIG_FAIR_GROUP_SCHED) || defined(CONFIG_RT_GROUP_SCHED)
struct task_group *tg = task_group(p);
#endif
#ifdef CONFIG_FAIR_GROUP_SCHED
p->se.cfs_rq = tg->cfs_rq[cpu];
p->se.parent = tg->se[cpu];
#endif
#ifdef CONFIG_RT_GROUP_SCHED
p->rt.rt_rq = tg->rt_rq[cpu];
p->rt.parent = tg->rt_se[cpu];
#endif
}
#else /* CONFIG_CGROUP_SCHED */
static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { }
static inline struct task_group *task_group(struct task_struct *p)
{
return NULL;
}
#endif /* CONFIG_CGROUP_SCHED */
static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
{
set_task_rq(p, cpu);
#ifdef CONFIG_SMP
/*
* After ->cpu is set up to a new value, task_rq_lock(p, ...) can be
* successfuly executed on another CPU. We must ensure that updates of
* per-task data have been completed by this moment.
*/
smp_wmb();
task_thread_info(p)->cpu = cpu;
#endif
}
/*
* Tunables that become constants when CONFIG_SCHED_DEBUG is off:
*/
#ifdef CONFIG_SCHED_DEBUG
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 00:31:31 -07:00
# include <linux/static_key.h>
# define const_debug __read_mostly
#else
# define const_debug const
#endif
extern const_debug unsigned int sysctl_sched_features;
#define SCHED_FEAT(name, enabled) \
__SCHED_FEAT_##name ,
enum {
#include "features.h"
__SCHED_FEAT_NR,
};
#undef SCHED_FEAT
#if defined(CONFIG_SCHED_DEBUG) && defined(HAVE_JUMP_LABEL)
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 00:31:31 -07:00
static __always_inline bool static_branch__true(struct static_key *key)
{
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 00:31:31 -07:00
return static_key_true(key); /* Not out of line branch. */
}
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 00:31:31 -07:00
static __always_inline bool static_branch__false(struct static_key *key)
{
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 00:31:31 -07:00
return static_key_false(key); /* Out of line branch. */
}
#define SCHED_FEAT(name, enabled) \
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 00:31:31 -07:00
static __always_inline bool static_branch_##name(struct static_key *key) \
{ \
return static_branch__##enabled(key); \
}
#include "features.h"
#undef SCHED_FEAT
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 00:31:31 -07:00
extern struct static_key sched_feat_keys[__SCHED_FEAT_NR];
#define sched_feat(x) (static_branch_##x(&sched_feat_keys[__SCHED_FEAT_##x]))
#else /* !(SCHED_DEBUG && HAVE_JUMP_LABEL) */
#define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
#endif /* SCHED_DEBUG && HAVE_JUMP_LABEL */
#ifdef CONFIG_NUMA_BALANCING
#define sched_feat_numa(x) sched_feat(x)
#ifdef CONFIG_SCHED_DEBUG
#define numabalancing_enabled sched_feat_numa(NUMA)
#else
extern bool numabalancing_enabled;
#endif /* CONFIG_SCHED_DEBUG */
#else
#define sched_feat_numa(x) (0)
#define numabalancing_enabled (0)
#endif /* CONFIG_NUMA_BALANCING */
static inline u64 global_rt_period(void)
{
return (u64)sysctl_sched_rt_period * NSEC_PER_USEC;
}
static inline u64 global_rt_runtime(void)
{
if (sysctl_sched_rt_runtime < 0)
return RUNTIME_INF;
return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
}
static inline int task_current(struct rq *rq, struct task_struct *p)
{
return rq->curr == p;
}
static inline int task_running(struct rq *rq, struct task_struct *p)
{
#ifdef CONFIG_SMP
return p->on_cpu;
#else
return task_current(rq, p);
#endif
}
#ifndef prepare_arch_switch
# define prepare_arch_switch(next) do { } while (0)
#endif
#ifndef finish_arch_switch
# define finish_arch_switch(prev) do { } while (0)
#endif
#ifndef finish_arch_post_lock_switch
# define finish_arch_post_lock_switch() do { } while (0)
#endif
#ifndef __ARCH_WANT_UNLOCKED_CTXSW
static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
{
#ifdef CONFIG_SMP
/*
* We can optimise this out completely for !SMP, because the
* SMP rebalancing from interrupt is the only thing that cares
* here.
*/
next->on_cpu = 1;
#endif
}
static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
{
#ifdef CONFIG_SMP
/*
* After ->on_cpu is cleared, the task can be moved to a different CPU.
* We must ensure this doesn't happen until the switch is completely
* finished.
*/
smp_wmb();
prev->on_cpu = 0;
#endif
#ifdef CONFIG_DEBUG_SPINLOCK
/* this is a valid case when another task releases the spinlock */
rq->lock.owner = current;
#endif
/*
* If we are tracking spinlock dependencies then we have to
* fix up the runqueue lock - which gets 'carried over' from
* prev into current:
*/
spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
raw_spin_unlock_irq(&rq->lock);
}
#else /* __ARCH_WANT_UNLOCKED_CTXSW */
static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
{
#ifdef CONFIG_SMP
/*
* We can optimise this out completely for !SMP, because the
* SMP rebalancing from interrupt is the only thing that cares
* here.
*/
next->on_cpu = 1;
#endif
raw_spin_unlock(&rq->lock);
}
static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
{
#ifdef CONFIG_SMP
/*
* After ->on_cpu is cleared, the task can be moved to a different CPU.
* We must ensure this doesn't happen until the switch is completely
* finished.
*/
smp_wmb();
prev->on_cpu = 0;
#endif
local_irq_enable();
}
#endif /* __ARCH_WANT_UNLOCKED_CTXSW */
/*
* wake flags
*/
#define WF_SYNC 0x01 /* waker goes to sleep after wakeup */
#define WF_FORK 0x02 /* child wakeup after fork */
#define WF_MIGRATED 0x4 /* internal use, task got migrated */
/*
* To aid in avoiding the subversion of "niceness" due to uneven distribution
* of tasks with abnormal "nice" values across CPUs the contribution that
* each task makes to its run queue's load is weighted according to its
* scheduling class and "nice" value. For SCHED_NORMAL tasks this is just a
* scaled version of the new time slice allocation that they receive on time
* slice expiry etc.
*/
#define WEIGHT_IDLEPRIO 3
#define WMULT_IDLEPRIO 1431655765
/*
* 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,
};
#define ENQUEUE_WAKEUP 1
#define ENQUEUE_HEAD 2
#ifdef CONFIG_SMP
#define ENQUEUE_WAKING 4 /* sched_class::task_waking was called */
#else
#define ENQUEUE_WAKING 0
#endif
#define DEQUEUE_SLEEP 1
struct sched_class {
const struct sched_class *next;
void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
void (*yield_task) (struct rq *rq);
bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt);
void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
struct task_struct * (*pick_next_task) (struct rq *rq);
void (*put_prev_task) (struct rq *rq, struct task_struct *p);
#ifdef CONFIG_SMP
int (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
void (*migrate_task_rq)(struct task_struct *p, int next_cpu);
void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
void (*post_schedule) (struct rq *this_rq);
void (*task_waking) (struct task_struct *task);
void (*task_woken) (struct rq *this_rq, struct task_struct *task);
void (*set_cpus_allowed)(struct task_struct *p,
const struct cpumask *newmask);
void (*rq_online)(struct rq *rq);
void (*rq_offline)(struct rq *rq);
#endif
void (*set_curr_task) (struct rq *rq);
void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
void (*task_fork) (struct task_struct *p);
void (*switched_from) (struct rq *this_rq, struct task_struct *task);
void (*switched_to) (struct rq *this_rq, struct task_struct *task);
void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
int oldprio);
unsigned int (*get_rr_interval) (struct rq *rq,
struct task_struct *task);
#ifdef CONFIG_FAIR_GROUP_SCHED
void (*task_move_group) (struct task_struct *p, int on_rq);
#endif
};
#define sched_class_highest (&stop_sched_class)
#define for_each_class(class) \
for (class = sched_class_highest; class; class = class->next)
extern const struct sched_class stop_sched_class;
extern const struct sched_class rt_sched_class;
extern const struct sched_class fair_sched_class;
extern const struct sched_class idle_sched_class;
#ifdef CONFIG_SMP
extern void update_group_power(struct sched_domain *sd, int cpu);
extern void trigger_load_balance(struct rq *rq, int cpu);
extern void idle_balance(int this_cpu, struct rq *this_rq);
sched: Fix wrong rq's runnable_avg update with rt tasks The current update of the rq's load can be erroneous when RT tasks are involved. The update of the load of a rq that becomes idle, is done only if the avg_idle is less than sysctl_sched_migration_cost. If RT tasks and short idle duration alternate, the runnable_avg will not be updated correctly and the time will be accounted as idle time when a CFS task wakes up. A new idle_enter function is called when the next task is the idle function so the elapsed time will be accounted as run time in the load of the rq, whatever the average idle time is. The function update_rq_runnable_avg is removed from idle_balance. When a RT task is scheduled on an idle CPU, the update of the rq's load is not done when the rq exit idle state because CFS's functions are not called. Then, the idle_balance, which is called just before entering the idle function, updates the rq's load and makes the assumption that the elapsed time since the last update, was only running time. As a consequence, the rq's load of a CPU that only runs a periodic RT task, is close to LOAD_AVG_MAX whatever the running duration of the RT task is. A new idle_exit function is called when the prev task is the idle function so the elapsed time will be accounted as idle time in the rq's load. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: linaro-kernel@lists.linaro.org Cc: peterz@infradead.org Cc: pjt@google.com Cc: fweisbec@gmail.com Cc: efault@gmx.de Link: http://lkml.kernel.org/r/1366302867-5055-1-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-04-18 10:34:26 -06:00
extern void idle_enter_fair(struct rq *this_rq);
extern void idle_exit_fair(struct rq *this_rq);
#else /* CONFIG_SMP */
static inline void idle_balance(int cpu, struct rq *rq)
{
}
#endif
extern void sysrq_sched_debug_show(void);
extern void sched_init_granularity(void);
extern void update_max_interval(void);
extern void init_sched_rt_class(void);
extern void init_sched_fair_class(void);
extern void resched_task(struct task_struct *p);
extern void resched_cpu(int cpu);
extern struct rt_bandwidth def_rt_bandwidth;
extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
extern void update_idle_cpu_load(struct rq *this_rq);
sched: Set an initial value of runnable avg for new forked task We need to initialize the se.avg.{decay_count, load_avg_contrib} for a new forked task. Otherwise random values of above variables cause a mess when a new task is enqueued: enqueue_task_fair enqueue_entity enqueue_entity_load_avg and make fork balancing imbalance due to incorrect load_avg_contrib. Further more, Morten Rasmussen notice some tasks were not launched at once after created. So Paul and Peter suggest giving a start value for new task runnable avg time same as sched_slice(). PeterZ said: > So the 'problem' is that our running avg is a 'floating' average; ie. it > decays with time. Now we have to guess about the future of our newly > spawned task -- something that is nigh impossible seeing these CPU > vendors keep refusing to implement the crystal ball instruction. > > So there's two asymptotic cases we want to deal well with; 1) the case > where the newly spawned program will be 'nearly' idle for its lifetime; > and 2) the case where its cpu-bound. > > Since we have to guess, we'll go for worst case and assume its > cpu-bound; now we don't want to make the avg so heavy adjusting to the > near-idle case takes forever. We want to be able to quickly adjust and > lower our running avg. > > Now we also don't want to make our avg too light, such that it gets > decremented just for the new task not having had a chance to run yet -- > even if when it would run, it would be more cpu-bound than not. > > So what we do is we make the initial avg of the same duration as that we > guess it takes to run each task on the system at least once -- aka > sched_slice(). > > Of course we can defeat this with wakeup/fork bombs, but in the 'normal' > case it should be good enough. Paul also contributed most of the code comments in this commit. Signed-off-by: Alex Shi <alex.shi@intel.com> Reviewed-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Reviewed-by: Paul Turner <pjt@google.com> [peterz; added explanation of sched_slice() usage] Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1371694737-29336-4-git-send-email-alex.shi@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-06-19 20:18:47 -06:00
extern void init_task_runnable_average(struct task_struct *p);
#ifdef CONFIG_PARAVIRT
static inline u64 steal_ticks(u64 steal)
{
if (unlikely(steal > NSEC_PER_SEC))
return div_u64(steal, TICK_NSEC);
return __iter_div_u64_rem(steal, TICK_NSEC, &steal);
}
#endif
static inline void inc_nr_running(struct rq *rq)
{
rq->nr_running++;
#ifdef CONFIG_NO_HZ_FULL
if (rq->nr_running == 2) {
if (tick_nohz_full_cpu(rq->cpu)) {
/* Order rq->nr_running write against the IPI */
smp_wmb();
smp_send_reschedule(rq->cpu);
}
}
#endif
}
static inline void dec_nr_running(struct rq *rq)
{
rq->nr_running--;
}
static inline void rq_last_tick_reset(struct rq *rq)
{
#ifdef CONFIG_NO_HZ_FULL
rq->last_sched_tick = jiffies;
#endif
}
extern void update_rq_clock(struct rq *rq);
extern void activate_task(struct rq *rq, struct task_struct *p, int flags);
extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);
extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
extern const_debug unsigned int sysctl_sched_time_avg;
extern const_debug unsigned int sysctl_sched_nr_migrate;
extern const_debug unsigned int sysctl_sched_migration_cost;
static inline u64 sched_avg_period(void)
{
return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2;
}
#ifdef CONFIG_SCHED_HRTICK
/*
* Use hrtick when:
* - enabled by features
* - hrtimer is actually high res
*/
static inline int hrtick_enabled(struct rq *rq)
{
if (!sched_feat(HRTICK))
return 0;
if (!cpu_active(cpu_of(rq)))
return 0;
return hrtimer_is_hres_active(&rq->hrtick_timer);
}
void hrtick_start(struct rq *rq, u64 delay);
sched: Save some hrtick_start_fair cycles hrtick_start_fair() shows up in profiles even when disabled. v3.0.6 taskset -c 3 pipe-test PerfTop: 997 irqs/sec kernel:89.5% exact: 0.0% [1000Hz cycles], (all, CPU: 3) ------------------------------------------------------------------------------------------------ Virgin Patched samples pcnt function samples pcnt function _______ _____ ___________________________ _______ _____ ___________________________ 2880.00 10.2% __schedule 3136.00 11.3% __schedule 1634.00 5.8% pipe_read 1615.00 5.8% pipe_read 1458.00 5.2% system_call 1534.00 5.5% system_call 1382.00 4.9% _raw_spin_lock_irqsave 1412.00 5.1% _raw_spin_lock_irqsave 1202.00 4.3% pipe_write 1255.00 4.5% copy_user_generic_string 1164.00 4.1% copy_user_generic_string 1241.00 4.5% __switch_to 1097.00 3.9% __switch_to 929.00 3.3% mutex_lock 872.00 3.1% mutex_lock 846.00 3.0% mutex_unlock 687.00 2.4% mutex_unlock 804.00 2.9% pipe_write 682.00 2.4% native_sched_clock 713.00 2.6% native_sched_clock 643.00 2.3% system_call_after_swapgs 653.00 2.3% _raw_spin_unlock_irqrestore 617.00 2.2% sched_clock_local 633.00 2.3% fsnotify 612.00 2.2% fsnotify 605.00 2.2% sched_clock_local 596.00 2.1% _raw_spin_unlock_irqrestore 593.00 2.1% system_call_after_swapgs 542.00 1.9% sysret_check 559.00 2.0% sysret_check 467.00 1.7% fget_light 472.00 1.7% fget_light 462.00 1.6% finish_task_switch 461.00 1.7% finish_task_switch 437.00 1.5% vfs_write 442.00 1.6% vfs_write 431.00 1.5% do_sync_write 428.00 1.5% do_sync_write 413.00 1.5% select_task_rq_fair 404.00 1.5% _raw_spin_lock_irq 386.00 1.4% update_curr 402.00 1.4% update_curr 385.00 1.4% rw_verify_area 389.00 1.4% do_sync_read 377.00 1.3% _raw_spin_lock_irq 378.00 1.4% vfs_read 369.00 1.3% do_sync_read 340.00 1.2% pipe_iov_copy_from_user 360.00 1.3% vfs_read 316.00 1.1% __wake_up_sync_key * 342.00 1.2% hrtick_start_fair 313.00 1.1% __wake_up_common Signed-off-by: Mike Galbraith <efault@gmx.de> [ fixed !CONFIG_SCHED_HRTICK borkage ] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1321971607.6855.17.camel@marge.simson.net Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-11-22 07:20:07 -07:00
#else
static inline int hrtick_enabled(struct rq *rq)
{
return 0;
}
#endif /* CONFIG_SCHED_HRTICK */
#ifdef CONFIG_SMP
extern void sched_avg_update(struct rq *rq);
static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
{
rq->rt_avg += rt_delta;
sched_avg_update(rq);
}
#else
static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { }
static inline void sched_avg_update(struct rq *rq) { }
#endif
extern void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period);
#ifdef CONFIG_SMP
#ifdef CONFIG_PREEMPT
static inline void double_rq_lock(struct rq *rq1, struct rq *rq2);
/*
* fair double_lock_balance: Safely acquires both rq->locks in a fair
* way at the expense of forcing extra atomic operations in all
* invocations. This assures that the double_lock is acquired using the
* same underlying policy as the spinlock_t on this architecture, which
* reduces latency compared to the unfair variant below. However, it
* also adds more overhead and therefore may reduce throughput.
*/
static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
__releases(this_rq->lock)
__acquires(busiest->lock)
__acquires(this_rq->lock)
{
raw_spin_unlock(&this_rq->lock);
double_rq_lock(this_rq, busiest);
return 1;
}
#else
/*
* Unfair double_lock_balance: Optimizes throughput at the expense of
* latency by eliminating extra atomic operations when the locks are
* already in proper order on entry. This favors lower cpu-ids and will
* grant the double lock to lower cpus over higher ids under contention,
* regardless of entry order into the function.
*/
static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
__releases(this_rq->lock)
__acquires(busiest->lock)
__acquires(this_rq->lock)
{
int ret = 0;
if (unlikely(!raw_spin_trylock(&busiest->lock))) {
if (busiest < this_rq) {
raw_spin_unlock(&this_rq->lock);
raw_spin_lock(&busiest->lock);
raw_spin_lock_nested(&this_rq->lock,
SINGLE_DEPTH_NESTING);
ret = 1;
} else
raw_spin_lock_nested(&busiest->lock,
SINGLE_DEPTH_NESTING);
}
return ret;
}
#endif /* CONFIG_PREEMPT */
/*
* double_lock_balance - lock the busiest runqueue, this_rq is locked already.
*/
static inline int double_lock_balance(struct rq *this_rq, struct rq *busiest)
{
if (unlikely(!irqs_disabled())) {
/* printk() doesn't work good under rq->lock */
raw_spin_unlock(&this_rq->lock);
BUG_ON(1);
}
return _double_lock_balance(this_rq, busiest);
}
static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
__releases(busiest->lock)
{
raw_spin_unlock(&busiest->lock);
lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
}
/*
* double_rq_lock - safely lock two runqueues
*
* Note this does not disable interrupts like task_rq_lock,
* you need to do so manually before calling.
*/
static inline void double_rq_lock(struct rq *rq1, struct rq *rq2)
__acquires(rq1->lock)
__acquires(rq2->lock)
{
BUG_ON(!irqs_disabled());
if (rq1 == rq2) {
raw_spin_lock(&rq1->lock);
__acquire(rq2->lock); /* Fake it out ;) */
} else {
if (rq1 < rq2) {
raw_spin_lock(&rq1->lock);
raw_spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING);
} else {
raw_spin_lock(&rq2->lock);
raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
}
}
}
/*
* double_rq_unlock - safely unlock two runqueues
*
* Note this does not restore interrupts like task_rq_unlock,
* you need to do so manually after calling.
*/
static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2)
__releases(rq1->lock)
__releases(rq2->lock)
{
raw_spin_unlock(&rq1->lock);
if (rq1 != rq2)
raw_spin_unlock(&rq2->lock);
else
__release(rq2->lock);
}
#else /* CONFIG_SMP */
/*
* double_rq_lock - safely lock two runqueues
*
* Note this does not disable interrupts like task_rq_lock,
* you need to do so manually before calling.
*/
static inline void double_rq_lock(struct rq *rq1, struct rq *rq2)
__acquires(rq1->lock)
__acquires(rq2->lock)
{
BUG_ON(!irqs_disabled());
BUG_ON(rq1 != rq2);
raw_spin_lock(&rq1->lock);
__acquire(rq2->lock); /* Fake it out ;) */
}
/*
* double_rq_unlock - safely unlock two runqueues
*
* Note this does not restore interrupts like task_rq_unlock,
* you need to do so manually after calling.
*/
static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2)
__releases(rq1->lock)
__releases(rq2->lock)
{
BUG_ON(rq1 != rq2);
raw_spin_unlock(&rq1->lock);
__release(rq2->lock);
}
#endif
extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq);
extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq);
extern void print_cfs_stats(struct seq_file *m, int cpu);
extern void print_rt_stats(struct seq_file *m, int cpu);
extern void init_cfs_rq(struct cfs_rq *cfs_rq);
extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq);
extern void account_cfs_bandwidth_used(int enabled, int was_enabled);
nohz: Rename CONFIG_NO_HZ to CONFIG_NO_HZ_COMMON We are planning to convert the dynticks Kconfig options layout into a choice menu. The user must be able to easily pick any of the following implementations: constant periodic tick, idle dynticks, full dynticks. As this implies a mutual exclusion, the two dynticks implementions need to converge on the selection of a common Kconfig option in order to ease the sharing of a common infrastructure. It would thus seem pretty natural to reuse CONFIG_NO_HZ to that end. It already implements all the idle dynticks code and the full dynticks depends on all that code for now. So ideally the choice menu would propose CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED then both would select CONFIG_NO_HZ. On the other hand we want to stay backward compatible: if CONFIG_NO_HZ is set in an older config file, we want to enable CONFIG_NO_HZ_IDLE by default. But we can't afford both at the same time or we run into a circular dependency: 1) CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED both select CONFIG_NO_HZ 2) If CONFIG_NO_HZ is set, we default to CONFIG_NO_HZ_IDLE We might be able to support that from Kconfig/Kbuild but it may not be wise to introduce such a confusing behaviour. So to solve this, create a new CONFIG_NO_HZ_COMMON option which gathers the common code between idle and full dynticks (that common code for now is simply the idle dynticks code) and select it from their referring Kconfig. Then we'll later create CONFIG_NO_HZ_IDLE and map CONFIG_NO_HZ to it for backward compatibility. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Christoph Lameter <cl@linux.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Gilad Ben Yossef <gilad@benyossef.com> Cc: Hakan Akkan <hakanakkan@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de>
2011-08-10 15:21:01 -06:00
#ifdef CONFIG_NO_HZ_COMMON
enum rq_nohz_flag_bits {
NOHZ_TICK_STOPPED,
NOHZ_BALANCE_KICK,
};
#define nohz_flags(cpu) (&cpu_rq(cpu)->nohz_flags)
#endif
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
DECLARE_PER_CPU(u64, cpu_hardirq_time);
DECLARE_PER_CPU(u64, cpu_softirq_time);
#ifndef CONFIG_64BIT
DECLARE_PER_CPU(seqcount_t, irq_time_seq);
static inline void irq_time_write_begin(void)
{
__this_cpu_inc(irq_time_seq.sequence);
smp_wmb();
}
static inline void irq_time_write_end(void)
{
smp_wmb();
__this_cpu_inc(irq_time_seq.sequence);
}
static inline u64 irq_time_read(int cpu)
{
u64 irq_time;
unsigned seq;
do {
seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu));
irq_time = per_cpu(cpu_softirq_time, cpu) +
per_cpu(cpu_hardirq_time, cpu);
} while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq));
return irq_time;
}
#else /* CONFIG_64BIT */
static inline void irq_time_write_begin(void)
{
}
static inline void irq_time_write_end(void)
{
}
static inline u64 irq_time_read(int cpu)
{
return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
}
#endif /* CONFIG_64BIT */
#endif /* CONFIG_IRQ_TIME_ACCOUNTING */