diff options
Diffstat (limited to 'kernel/sched/sched.h')
| -rw-r--r-- | kernel/sched/sched.h | 142 |
1 files changed, 70 insertions, 72 deletions
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 275370854481..62f9278b1663 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -418,6 +418,7 @@ extern void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq, extern void sched_init_dl_servers(void); extern void fair_server_init(struct rq *rq); +extern void ext_server_init(struct rq *rq); extern void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq); extern int dl_server_apply_params(struct sched_dl_entity *dl_se, u64 runtime, u64 period, bool init); @@ -674,16 +675,16 @@ struct balance_callback { void (*func)(struct rq *rq); }; -/* CFS-related fields in a runqueue */ +/* Fair scheduling SCHED_{NORMAL,BATCH,IDLE} related fields in a runqueue: */ struct cfs_rq { struct load_weight load; unsigned int nr_queued; - unsigned int h_nr_queued; /* SCHED_{NORMAL,BATCH,IDLE} */ - unsigned int h_nr_runnable; /* SCHED_{NORMAL,BATCH,IDLE} */ - unsigned int h_nr_idle; /* SCHED_IDLE */ + unsigned int h_nr_queued; /* SCHED_{NORMAL,BATCH,IDLE} */ + unsigned int h_nr_runnable; /* SCHED_{NORMAL,BATCH,IDLE} */ + unsigned int h_nr_idle; /* SCHED_IDLE */ - s64 avg_vruntime; - u64 avg_load; + s64 sum_w_vruntime; + u64 sum_weight; u64 zero_vruntime; #ifdef CONFIG_SCHED_CORE @@ -694,7 +695,7 @@ struct cfs_rq { struct rb_root_cached tasks_timeline; /* - * 'curr' points to currently running entity on this cfs_rq. + * 'curr' points to the currently running entity on this cfs_rq. * It is set to NULL otherwise (i.e when none are currently running). */ struct sched_entity *curr; @@ -730,9 +731,7 @@ struct cfs_rq { unsigned long h_load; u64 last_h_load_update; struct sched_entity *h_load_next; -#endif /* CONFIG_FAIR_GROUP_SCHED */ -#ifdef CONFIG_FAIR_GROUP_SCHED struct rq *rq; /* CPU runqueue to which this cfs_rq is attached */ /* @@ -745,19 +744,19 @@ struct cfs_rq { */ int on_list; struct list_head leaf_cfs_rq_list; - struct task_group *tg; /* group that "owns" this runqueue */ + struct task_group *tg; /* Group that "owns" this runqueue */ /* Locally cached copy of our task_group's idle value */ int idle; -#ifdef CONFIG_CFS_BANDWIDTH +# ifdef CONFIG_CFS_BANDWIDTH int runtime_enabled; s64 runtime_remaining; u64 throttled_pelt_idle; -#ifndef CONFIG_64BIT +# ifndef CONFIG_64BIT u64 throttled_pelt_idle_copy; -#endif +# endif u64 throttled_clock; u64 throttled_clock_pelt; u64 throttled_clock_pelt_time; @@ -769,7 +768,7 @@ struct cfs_rq { struct list_head throttled_list; struct list_head throttled_csd_list; struct list_head throttled_limbo_list; -#endif /* CONFIG_CFS_BANDWIDTH */ +# endif /* CONFIG_CFS_BANDWIDTH */ #endif /* CONFIG_FAIR_GROUP_SCHED */ }; @@ -1121,28 +1120,50 @@ DECLARE_STATIC_KEY_FALSE(sched_uclamp_used); * acquire operations must be ordered by ascending &runqueue. */ struct rq { - /* runqueue lock: */ - raw_spinlock_t __lock; - - /* Per class runqueue modification mask; bits in class order. */ - unsigned int queue_mask; + /* + * The following members are loaded together, without holding the + * rq->lock, in an extremely hot loop in update_sg_lb_stats() + * (called from pick_next_task()). To reduce cache pollution from + * this operation, they are placed together on this dedicated cache + * line. Even though some of them are frequently modified, they are + * loaded much more frequently than they are stored. + */ unsigned int nr_running; #ifdef CONFIG_NUMA_BALANCING unsigned int nr_numa_running; unsigned int nr_preferred_running; - unsigned int numa_migrate_on; #endif + unsigned int ttwu_pending; + unsigned long cpu_capacity; +#ifdef CONFIG_SCHED_PROXY_EXEC + struct task_struct __rcu *donor; /* Scheduling context */ + struct task_struct __rcu *curr; /* Execution context */ +#else + union { + struct task_struct __rcu *donor; /* Scheduler context */ + struct task_struct __rcu *curr; /* Execution context */ + }; +#endif + struct task_struct *idle; + /* padding left here deliberately */ + + /* + * The next cacheline holds the (hot) runqueue lock, as well as + * some other less performance-critical fields. + */ + u64 nr_switches ____cacheline_aligned; + + /* runqueue lock: */ + raw_spinlock_t __lock; + #ifdef CONFIG_NO_HZ_COMMON - unsigned long last_blocked_load_update_tick; - unsigned int has_blocked_load; - call_single_data_t nohz_csd; unsigned int nohz_tick_stopped; atomic_t nohz_flags; + unsigned int has_blocked_load; + unsigned long last_blocked_load_update_tick; + call_single_data_t nohz_csd; #endif /* CONFIG_NO_HZ_COMMON */ - unsigned int ttwu_pending; - u64 nr_switches; - #ifdef CONFIG_UCLAMP_TASK /* Utilization clamp values based on CPU's RUNNABLE tasks */ struct uclamp_rq uclamp[UCLAMP_CNT] ____cacheline_aligned; @@ -1155,6 +1176,7 @@ struct rq { struct dl_rq dl; #ifdef CONFIG_SCHED_CLASS_EXT struct scx_rq scx; + struct sched_dl_entity ext_server; #endif struct sched_dl_entity fair_server; @@ -1165,6 +1187,9 @@ struct rq { struct list_head *tmp_alone_branch; #endif /* CONFIG_FAIR_GROUP_SCHED */ +#ifdef CONFIG_NUMA_BALANCING + unsigned int numa_migrate_on; +#endif /* * This is part of a global counter where only the total sum * over all CPUs matters. A task can increase this counter on @@ -1173,36 +1198,29 @@ struct rq { */ unsigned long nr_uninterruptible; -#ifdef CONFIG_SCHED_PROXY_EXEC - struct task_struct __rcu *donor; /* Scheduling context */ - struct task_struct __rcu *curr; /* Execution context */ -#else - union { - struct task_struct __rcu *donor; /* Scheduler context */ - struct task_struct __rcu *curr; /* Execution context */ - }; -#endif struct sched_dl_entity *dl_server; - struct task_struct *idle; struct task_struct *stop; + const struct sched_class *next_class; unsigned long next_balance; struct mm_struct *prev_mm; - unsigned int clock_update_flags; - u64 clock; - /* Ensure that all clocks are in the same cache line */ + /* + * The following fields of clock data are frequently referenced + * and updated together, and should go on their own cache line. + */ u64 clock_task ____cacheline_aligned; u64 clock_pelt; + u64 clock; unsigned long lost_idle_time; + unsigned int clock_update_flags; u64 clock_pelt_idle; u64 clock_idle; + #ifndef CONFIG_64BIT u64 clock_pelt_idle_copy; u64 clock_idle_copy; #endif - atomic_t nr_iowait; - u64 last_seen_need_resched_ns; int ticks_without_resched; @@ -1213,8 +1231,6 @@ struct rq { struct root_domain *rd; struct sched_domain __rcu *sd; - unsigned long cpu_capacity; - struct balance_callback *balance_callback; unsigned char nohz_idle_balance; @@ -1324,7 +1340,9 @@ struct rq { call_single_data_t cfsb_csd; struct list_head cfsb_csd_list; #endif -}; + + atomic_t nr_iowait; +} __no_randomize_layout; #ifdef CONFIG_FAIR_GROUP_SCHED @@ -1698,6 +1716,7 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp) #endif /* !CONFIG_FAIR_GROUP_SCHED */ +extern void update_rq_avg_idle(struct rq *rq); extern void update_rq_clock(struct rq *rq); /* @@ -2062,8 +2081,8 @@ queue_balance_callback(struct rq *rq, rq->balance_callback = head; } -#define rcu_dereference_check_sched_domain(p) \ - rcu_dereference_check((p), lockdep_is_held(&sched_domains_mutex)) +#define rcu_dereference_sched_domain(p) \ + rcu_dereference_all_check((p), lockdep_is_held(&sched_domains_mutex)) /* * The domain tree (rq->sd) is protected by RCU's quiescent state transition. @@ -2073,7 +2092,7 @@ queue_balance_callback(struct rq *rq, * preempt-disabled sections. */ #define for_each_domain(cpu, __sd) \ - for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); \ + for (__sd = rcu_dereference_sched_domain(cpu_rq(cpu)->sd); \ __sd; __sd = __sd->parent) /* A mask of all the SD flags that have the SDF_SHARED_CHILD metaflag */ @@ -2481,15 +2500,6 @@ struct sched_class { #ifdef CONFIG_UCLAMP_TASK int uclamp_enabled; #endif - /* - * idle: 0 - * ext: 1 - * fair: 2 - * rt: 4 - * dl: 8 - * stop: 16 - */ - unsigned int queue_mask; /* * move_queued_task/activate_task/enqueue_task: rq->lock @@ -2648,20 +2658,6 @@ struct sched_class { #endif }; -/* - * Does not nest; only used around sched_class::pick_task() rq-lock-breaks. - */ -static inline void rq_modified_clear(struct rq *rq) -{ - rq->queue_mask = 0; -} - -static inline bool rq_modified_above(struct rq *rq, const struct sched_class * class) -{ - unsigned int mask = class->queue_mask; - return rq->queue_mask & ~((mask << 1) - 1); -} - static inline void put_prev_task(struct rq *rq, struct task_struct *prev) { WARN_ON_ONCE(rq->donor != prev); @@ -3397,11 +3393,11 @@ struct irqtime { }; DECLARE_PER_CPU(struct irqtime, cpu_irqtime); -extern int sched_clock_irqtime; +DECLARE_STATIC_KEY_FALSE(sched_clock_irqtime); static inline int irqtime_enabled(void) { - return sched_clock_irqtime; + return static_branch_likely(&sched_clock_irqtime); } /* @@ -4010,6 +4006,7 @@ void move_queued_task_locked(struct rq *src_rq, struct rq *dst_rq, struct task_s deactivate_task(src_rq, task, 0); set_task_cpu(task, dst_rq->cpu); activate_task(dst_rq, task, 0); + wakeup_preempt(dst_rq, task, 0); } static inline @@ -4079,6 +4076,7 @@ extern void balance_callbacks(struct rq *rq, struct balance_callback *head); struct sched_change_ctx { u64 prio; struct task_struct *p; + const struct sched_class *class; int flags; bool queued; bool running; |