aboutsummaryrefslogtreecommitdiff
path: root/kernel/sched/sched.h
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sched/sched.h')
-rw-r--r--kernel/sched/sched.h179
1 files changed, 110 insertions, 69 deletions
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ec7b3e0a2b20..04846272409c 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -286,12 +286,6 @@ struct rt_bandwidth {
void __dl_clear_params(struct task_struct *p);
-struct dl_bandwidth {
- raw_spinlock_t dl_runtime_lock;
- u64 dl_runtime;
- u64 dl_period;
-};
-
static inline int dl_bandwidth_enabled(void)
{
return sysctl_sched_rt_runtime >= 0;
@@ -330,7 +324,7 @@ extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr);
extern bool __checkparam_dl(const struct sched_attr *attr);
extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr);
extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
-extern int dl_cpu_busy(int cpu, struct task_struct *p);
+extern int dl_bw_check_overflow(int cpu);
#ifdef CONFIG_CGROUP_SCHED
@@ -460,11 +454,12 @@ extern void unregister_fair_sched_group(struct task_group *tg);
extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
struct sched_entity *se, int cpu,
struct sched_entity *parent);
-extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
+extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth *parent);
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 bool cfs_task_bw_constrained(struct task_struct *p);
extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
struct sched_rt_entity *rt_se, int cpu,
@@ -500,6 +495,7 @@ static inline void set_task_rq_fair(struct sched_entity *se,
#else /* CONFIG_CGROUP_SCHED */
struct cfs_bandwidth { };
+static inline bool cfs_task_bw_constrained(struct task_struct *p) { return false; }
#endif /* CONFIG_CGROUP_SCHED */
@@ -554,6 +550,9 @@ struct cfs_rq {
unsigned int idle_nr_running; /* SCHED_IDLE */
unsigned int idle_h_nr_running; /* SCHED_IDLE */
+ s64 avg_vruntime;
+ u64 avg_load;
+
u64 exec_clock;
u64 min_vruntime;
#ifdef CONFIG_SCHED_CORE
@@ -573,8 +572,6 @@ struct cfs_rq {
*/
struct sched_entity *curr;
struct sched_entity *next;
- struct sched_entity *last;
- struct sched_entity *skip;
#ifdef CONFIG_SCHED_DEBUG
unsigned int nr_spread_over;
@@ -642,6 +639,8 @@ struct cfs_rq {
u64 throttled_clock;
u64 throttled_clock_pelt;
u64 throttled_clock_pelt_time;
+ u64 throttled_clock_self;
+ u64 throttled_clock_self_time;
int throttled;
int throttle_count;
struct list_head throttled_list;
@@ -754,6 +753,12 @@ struct dl_rq {
u64 extra_bw;
/*
+ * Maximum available bandwidth for reclaiming by SCHED_FLAG_RECLAIM
+ * tasks of this rq. Used in calculation of reclaimable bandwidth(GRUB).
+ */
+ u64 max_bw;
+
+ /*
* Inverse of the fraction of CPU utilization that can be reclaimed
* by the GRUB algorithm.
*/
@@ -1245,6 +1250,7 @@ static inline raw_spinlock_t *__rq_lockp(struct rq *rq)
bool cfs_prio_less(const struct task_struct *a, const struct task_struct *b,
bool fi);
+void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_fi);
/*
* Helpers to check if the CPU's core cookie matches with the task's cookie
@@ -1546,6 +1552,28 @@ static inline void rq_clock_cancel_skipupdate(struct rq *rq)
rq->clock_update_flags &= ~RQCF_REQ_SKIP;
}
+/*
+ * During cpu offlining and rq wide unthrottling, we can trigger
+ * an update_rq_clock() for several cfs and rt runqueues (Typically
+ * when using list_for_each_entry_*)
+ * rq_clock_start_loop_update() can be called after updating the clock
+ * once and before iterating over the list to prevent multiple update.
+ * After the iterative traversal, we need to call rq_clock_stop_loop_update()
+ * to clear RQCF_ACT_SKIP of rq->clock_update_flags.
+ */
+static inline void rq_clock_start_loop_update(struct rq *rq)
+{
+ lockdep_assert_rq_held(rq);
+ SCHED_WARN_ON(rq->clock_update_flags & RQCF_ACT_SKIP);
+ rq->clock_update_flags |= RQCF_ACT_SKIP;
+}
+
+static inline void rq_clock_stop_loop_update(struct rq *rq)
+{
+ lockdep_assert_rq_held(rq);
+ rq->clock_update_flags &= ~RQCF_ACT_SKIP;
+}
+
struct rq_flags {
unsigned long flags;
struct pin_cookie cookie;
@@ -1678,6 +1706,21 @@ rq_unlock(struct rq *rq, struct rq_flags *rf)
raw_spin_rq_unlock(rq);
}
+DEFINE_LOCK_GUARD_1(rq_lock, struct rq,
+ rq_lock(_T->lock, &_T->rf),
+ rq_unlock(_T->lock, &_T->rf),
+ struct rq_flags rf)
+
+DEFINE_LOCK_GUARD_1(rq_lock_irq, struct rq,
+ rq_lock_irq(_T->lock, &_T->rf),
+ rq_unlock_irq(_T->lock, &_T->rf),
+ struct rq_flags rf)
+
+DEFINE_LOCK_GUARD_1(rq_lock_irqsave, struct rq,
+ rq_lock_irqsave(_T->lock, &_T->rf),
+ rq_unlock_irqrestore(_T->lock, &_T->rf),
+ struct rq_flags rf)
+
static inline struct rq *
this_rq_lock_irq(struct rq_flags *rf)
__acquires(rq->lock)
@@ -1772,6 +1815,13 @@ queue_balance_callback(struct rq *rq,
for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); \
__sd; __sd = __sd->parent)
+/* A mask of all the SD flags that have the SDF_SHARED_CHILD metaflag */
+#define SD_FLAG(name, mflags) (name * !!((mflags) & SDF_SHARED_CHILD)) |
+static const unsigned int SD_SHARED_CHILD_MASK =
+#include <linux/sched/sd_flags.h>
+0;
+#undef SD_FLAG
+
/**
* highest_flag_domain - Return highest sched_domain containing flag.
* @cpu: The CPU whose highest level of sched domain is to
@@ -1779,16 +1829,25 @@ queue_balance_callback(struct rq *rq,
* @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.
+ * Returns the highest sched_domain of a CPU which contains @flag. If @flag has
+ * the SDF_SHARED_CHILD metaflag, all the children domains also have @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))
+ if (sd->flags & flag) {
+ hsd = sd;
+ continue;
+ }
+
+ /*
+ * Stop the search if @flag is known to be shared at lower
+ * levels. It will not be found further up.
+ */
+ if (flag & SD_SHARED_CHILD_MASK)
break;
- hsd = sd;
}
return hsd;
@@ -1844,6 +1903,7 @@ struct sched_group {
atomic_t ref;
unsigned int group_weight;
+ unsigned int cores;
struct sched_group_capacity *sgc;
int asym_prefer_cpu; /* CPU of highest priority in group */
int flags;
@@ -2093,12 +2153,13 @@ static inline int task_on_rq_migrating(struct task_struct *p)
}
/* Wake flags. The first three directly map to some SD flag value */
-#define WF_EXEC 0x02 /* Wakeup after exec; maps to SD_BALANCE_EXEC */
-#define WF_FORK 0x04 /* Wakeup after fork; maps to SD_BALANCE_FORK */
-#define WF_TTWU 0x08 /* Wakeup; maps to SD_BALANCE_WAKE */
+#define WF_EXEC 0x02 /* Wakeup after exec; maps to SD_BALANCE_EXEC */
+#define WF_FORK 0x04 /* Wakeup after fork; maps to SD_BALANCE_FORK */
+#define WF_TTWU 0x08 /* Wakeup; maps to SD_BALANCE_WAKE */
-#define WF_SYNC 0x10 /* Waker goes to sleep after wakeup */
-#define WF_MIGRATED 0x20 /* Internal use, task got migrated */
+#define WF_SYNC 0x10 /* Waker goes to sleep after wakeup */
+#define WF_MIGRATED 0x20 /* Internal use, task got migrated */
+#define WF_CURRENT_CPU 0x40 /* Prefer to move the wakee to the current CPU. */
#ifdef CONFIG_SMP
static_assert(WF_EXEC == SD_BALANCE_EXEC);
@@ -2157,6 +2218,7 @@ extern const u32 sched_prio_to_wmult[40];
#else
#define ENQUEUE_MIGRATED 0x00
#endif
+#define ENQUEUE_INITIAL 0x80
#define RETRY_TASK ((void *)-1UL)
@@ -2360,6 +2422,7 @@ static inline struct cpuidle_state *idle_get_state(struct rq *rq)
#endif
extern void schedule_idle(void);
+asmlinkage void schedule_user(void);
extern void sysrq_sched_debug_show(void);
extern void sched_init_granularity(void);
@@ -2378,7 +2441,6 @@ extern struct rt_bandwidth def_rt_bandwidth;
extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
-extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime);
extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
extern void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se);
@@ -2462,11 +2524,9 @@ extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
extern const_debug unsigned int sysctl_sched_nr_migrate;
extern const_debug unsigned int sysctl_sched_migration_cost;
+extern unsigned int sysctl_sched_base_slice;
+
#ifdef CONFIG_SCHED_DEBUG
-extern unsigned int sysctl_sched_latency;
-extern unsigned int sysctl_sched_min_granularity;
-extern unsigned int sysctl_sched_idle_min_granularity;
-extern unsigned int sysctl_sched_wakeup_granularity;
extern int sysctl_resched_latency_warn_ms;
extern int sysctl_resched_latency_warn_once;
@@ -2572,6 +2632,12 @@ static inline void double_rq_clock_clear_update(struct rq *rq1, struct rq *rq2)
static inline void double_rq_clock_clear_update(struct rq *rq1, struct rq *rq2) {}
#endif
+#define DEFINE_LOCK_GUARD_2(name, type, _lock, _unlock, ...) \
+__DEFINE_UNLOCK_GUARD(name, type, _unlock, type *lock2; __VA_ARGS__) \
+static inline class_##name##_t class_##name##_constructor(type *lock, type *lock2) \
+{ class_##name##_t _t = { .lock = lock, .lock2 = lock2 }, *_T = &_t; \
+ _lock; return _t; }
+
#ifdef CONFIG_SMP
static inline bool rq_order_less(struct rq *rq1, struct rq *rq2)
@@ -2701,6 +2767,16 @@ static inline void double_raw_lock(raw_spinlock_t *l1, raw_spinlock_t *l2)
raw_spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
}
+static inline void double_raw_unlock(raw_spinlock_t *l1, raw_spinlock_t *l2)
+{
+ raw_spin_unlock(l1);
+ raw_spin_unlock(l2);
+}
+
+DEFINE_LOCK_GUARD_2(double_raw_spinlock, raw_spinlock_t,
+ double_raw_lock(_T->lock, _T->lock2),
+ double_raw_unlock(_T->lock, _T->lock2))
+
/*
* double_rq_unlock - safely unlock two runqueues
*
@@ -2758,6 +2834,10 @@ static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2)
#endif
+DEFINE_LOCK_GUARD_2(double_rq_lock, struct rq,
+ double_rq_lock(_T->lock, _T->lock2),
+ double_rq_unlock(_T->lock, _T->lock2))
+
extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq);
extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq);
@@ -2946,53 +3026,9 @@ static inline unsigned long cpu_util_dl(struct rq *rq)
return READ_ONCE(rq->avg_dl.util_avg);
}
-/**
- * cpu_util_cfs() - Estimates the amount of CPU capacity used by CFS tasks.
- * @cpu: the CPU to get the utilization for.
- *
- * The unit of the return value must be the same as the one of CPU capacity
- * so that CPU utilization can be compared with CPU capacity.
- *
- * CPU utilization is the sum of running time of runnable tasks plus the
- * recent utilization of currently non-runnable tasks on that CPU.
- * It represents the amount of CPU capacity currently used by CFS tasks in
- * the range [0..max CPU capacity] with max CPU capacity being the CPU
- * capacity at f_max.
- *
- * The estimated CPU utilization is defined as the maximum between CPU
- * utilization and sum of the estimated utilization of the currently
- * runnable tasks on that CPU. It preserves a utilization "snapshot" of
- * previously-executed tasks, which helps better deduce how busy a CPU will
- * be when a long-sleeping task wakes up. The contribution to CPU utilization
- * of such a task would be significantly decayed at this point of time.
- *
- * CPU utilization can be higher than the current CPU capacity
- * (f_curr/f_max * max CPU capacity) or even the max CPU capacity because
- * of rounding errors as well as task migrations or wakeups of new tasks.
- * CPU utilization has to be capped to fit into the [0..max CPU capacity]
- * range. Otherwise a group of CPUs (CPU0 util = 121% + CPU1 util = 80%)
- * could be seen as over-utilized even though CPU1 has 20% of spare CPU
- * capacity. CPU utilization is allowed to overshoot current CPU capacity
- * though since this is useful for predicting the CPU capacity required
- * after task migrations (scheduler-driven DVFS).
- *
- * Return: (Estimated) utilization for the specified CPU.
- */
-static inline unsigned long cpu_util_cfs(int cpu)
-{
- struct cfs_rq *cfs_rq;
- unsigned long util;
-
- cfs_rq = &cpu_rq(cpu)->cfs;
- util = READ_ONCE(cfs_rq->avg.util_avg);
- if (sched_feat(UTIL_EST)) {
- util = max_t(unsigned long, util,
- READ_ONCE(cfs_rq->avg.util_est.enqueued));
- }
-
- return min(util, capacity_orig_of(cpu));
-}
+extern unsigned long cpu_util_cfs(int cpu);
+extern unsigned long cpu_util_cfs_boost(int cpu);
static inline unsigned long cpu_util_rt(struct rq *rq)
{
@@ -3236,6 +3272,8 @@ static inline bool is_per_cpu_kthread(struct task_struct *p)
extern void swake_up_all_locked(struct swait_queue_head *q);
extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
+extern int try_to_wake_up(struct task_struct *tsk, unsigned int state, int wake_flags);
+
#ifdef CONFIG_PREEMPT_DYNAMIC
extern int preempt_dynamic_mode;
extern int sched_dynamic_mode(const char *str);
@@ -3487,4 +3525,7 @@ static inline void task_tick_mm_cid(struct rq *rq, struct task_struct *curr) { }
static inline void init_sched_mm_cid(struct task_struct *t) { }
#endif
+extern u64 avg_vruntime(struct cfs_rq *cfs_rq);
+extern int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se);
+
#endif /* _KERNEL_SCHED_SCHED_H */