aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/sched/sched.h
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sched/sched.h')
-rw-r--r--kernel/sched/sched.h1440
1 files changed, 1066 insertions, 374 deletions
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 9ea647835fd6..a4a20046e586 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2,83 +2,99 @@
/*
* Scheduler internal types and methods:
*/
-#include <linux/sched.h>
+#ifndef _KERNEL_SCHED_SCHED_H
+#define _KERNEL_SCHED_SCHED_H
+#include <linux/sched/affinity.h>
#include <linux/sched/autogroup.h>
-#include <linux/sched/clock.h>
-#include <linux/sched/coredump.h>
#include <linux/sched/cpufreq.h>
-#include <linux/sched/cputime.h>
#include <linux/sched/deadline.h>
-#include <linux/sched/debug.h>
-#include <linux/sched/hotplug.h>
-#include <linux/sched/idle.h>
-#include <linux/sched/init.h>
-#include <linux/sched/isolation.h>
-#include <linux/sched/jobctl.h>
+#include <linux/sched.h>
#include <linux/sched/loadavg.h>
#include <linux/sched/mm.h>
-#include <linux/sched/nohz.h>
-#include <linux/sched/numa_balancing.h>
-#include <linux/sched/prio.h>
-#include <linux/sched/rt.h>
+#include <linux/sched/rseq_api.h>
#include <linux/sched/signal.h>
#include <linux/sched/smt.h>
#include <linux/sched/stat.h>
#include <linux/sched/sysctl.h>
+#include <linux/sched/task_flags.h>
#include <linux/sched/task.h>
-#include <linux/sched/task_stack.h>
#include <linux/sched/topology.h>
-#include <linux/sched/user.h>
-#include <linux/sched/wake_q.h>
-#include <linux/sched/xacct.h>
-
-#include <uapi/linux/sched/types.h>
-#include <linux/binfmts.h>
-#include <linux/blkdev.h>
-#include <linux/compat.h>
+#include <linux/atomic.h>
+#include <linux/bitmap.h>
+#include <linux/bug.h>
+#include <linux/capability.h>
+#include <linux/cgroup_api.h>
+#include <linux/cgroup.h>
#include <linux/context_tracking.h>
#include <linux/cpufreq.h>
-#include <linux/cpuidle.h>
-#include <linux/cpuset.h>
+#include <linux/cpumask_api.h>
#include <linux/ctype.h>
-#include <linux/debugfs.h>
-#include <linux/delayacct.h>
-#include <linux/energy_model.h>
-#include <linux/init_task.h>
-#include <linux/kprobes.h>
+#include <linux/file.h>
+#include <linux/fs_api.h>
+#include <linux/hrtimer_api.h>
+#include <linux/interrupt.h>
+#include <linux/irq_work.h>
+#include <linux/jiffies.h>
+#include <linux/kref_api.h>
#include <linux/kthread.h>
-#include <linux/membarrier.h>
-#include <linux/migrate.h>
-#include <linux/mmu_context.h>
-#include <linux/nmi.h>
+#include <linux/ktime_api.h>
+#include <linux/lockdep_api.h>
+#include <linux/lockdep.h>
+#include <linux/minmax.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/mutex_api.h>
+#include <linux/plist.h>
+#include <linux/poll.h>
#include <linux/proc_fs.h>
-#include <linux/prefetch.h>
#include <linux/profile.h>
#include <linux/psi.h>
-#include <linux/rcupdate_wait.h>
-#include <linux/security.h>
+#include <linux/rcupdate.h>
+#include <linux/seq_file.h>
+#include <linux/seqlock.h>
+#include <linux/softirq.h>
+#include <linux/spinlock_api.h>
+#include <linux/static_key.h>
#include <linux/stop_machine.h>
-#include <linux/suspend.h>
-#include <linux/swait.h>
+#include <linux/syscalls_api.h>
#include <linux/syscalls.h>
-#include <linux/task_work.h>
-#include <linux/tsacct_kern.h>
+#include <linux/tick.h>
+#include <linux/topology.h>
+#include <linux/types.h>
+#include <linux/u64_stats_sync_api.h>
+#include <linux/uaccess.h>
+#include <linux/wait_api.h>
+#include <linux/wait_bit.h>
+#include <linux/workqueue_api.h>
+
+#include <trace/events/power.h>
+#include <trace/events/sched.h>
+
+#include "../workqueue_internal.h"
+
+#ifdef CONFIG_CGROUP_SCHED
+#include <linux/cgroup.h>
+#include <linux/psi.h>
+#endif
-#include <asm/tlb.h>
+#ifdef CONFIG_SCHED_DEBUG
+# include <linux/static_key.h>
+#endif
#ifdef CONFIG_PARAVIRT
# include <asm/paravirt.h>
+# include <asm/paravirt_api_clock.h>
#endif
#include "cpupri.h"
#include "cpudeadline.h"
#ifdef CONFIG_SCHED_DEBUG
-# define SCHED_WARN_ON(x) WARN_ONCE(x, #x)
+# define SCHED_WARN_ON(x) WARN_ONCE(x, #x)
#else
-# define SCHED_WARN_ON(x) ({ (void)(x), 0; })
+# define SCHED_WARN_ON(x) ({ (void)(x), 0; })
#endif
struct rq;
@@ -93,9 +109,17 @@ extern __read_mostly int scheduler_running;
extern unsigned long calc_load_update;
extern atomic_long_t calc_load_tasks;
+extern unsigned int sysctl_sched_child_runs_first;
+
extern void calc_global_load_tick(struct rq *this_rq);
extern long calc_load_fold_active(struct rq *this_rq, long adjust);
+extern void call_trace_sched_update_nr_running(struct rq *rq, int count);
+
+extern unsigned int sysctl_sched_rt_period;
+extern int sysctl_sched_rt_runtime;
+extern int sched_rr_timeslice;
+
/*
* Helpers for converting nanosecond timing to jiffy resolution
*/
@@ -118,7 +142,13 @@ extern long calc_load_fold_active(struct rq *this_rq, long adjust);
#ifdef CONFIG_64BIT
# define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT + SCHED_FIXEDPOINT_SHIFT)
# define scale_load(w) ((w) << SCHED_FIXEDPOINT_SHIFT)
-# define scale_load_down(w) ((w) >> SCHED_FIXEDPOINT_SHIFT)
+# define scale_load_down(w) \
+({ \
+ unsigned long __w = (w); \
+ if (__w) \
+ __w = max(2UL, __w >> SCHED_FIXEDPOINT_SHIFT); \
+ __w; \
+})
#else
# define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT)
# define scale_load(w) (w)
@@ -131,7 +161,7 @@ extern long calc_load_fold_active(struct rq *this_rq, long adjust);
* scale_load() and scale_load_down(w) to convert between them. The
* following must be true:
*
- * scale_load(sched_prio_to_weight[USER_PRIO(NICE_TO_PRIO(0))]) == NICE_0_LOAD
+ * scale_load(sched_prio_to_weight[NICE_TO_PRIO(0)-MAX_RT_PRIO]) == NICE_0_LOAD
*
*/
#define NICE_0_LOAD (1L << NICE_0_LOAD_SHIFT)
@@ -189,6 +219,19 @@ static inline int task_has_dl_policy(struct task_struct *p)
#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
+static inline void update_avg(u64 *avg, u64 sample)
+{
+ s64 diff = sample - *avg;
+ *avg += diff / 8;
+}
+
+/*
+ * Shifting a value by an exponent greater *or equal* to the size of said value
+ * is UB; cap at size-1.
+ */
+#define shr_bound(val, shift) \
+ (val >> min_t(typeof(shift), shift, BITS_PER_TYPE(typeof(val)) - 1))
+
/*
* !! For sched_setattr_nocheck() (kernel) only !!
*
@@ -203,6 +246,8 @@ static inline int task_has_dl_policy(struct task_struct *p)
*/
#define SCHED_FLAG_SUGOV 0x10000000
+#define SCHED_DL_FLAGS (SCHED_FLAG_RECLAIM | SCHED_FLAG_DL_OVERRUN | SCHED_FLAG_SUGOV)
+
static inline bool dl_entity_is_special(struct sched_dl_entity *dl_se)
{
#ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
@@ -241,30 +286,6 @@ struct rt_bandwidth {
void __dl_clear_params(struct task_struct *p);
-/*
- * To keep the bandwidth of -deadline tasks and groups under control
- * we need some place where:
- * - store the maximum -deadline bandwidth of the system (the group);
- * - cache the fraction of that bandwidth that is currently allocated.
- *
- * This is all done in the data structure below. It is similar to the
- * one used for RT-throttling (rt_bandwidth), with the main difference
- * that, since here we are only interested in admission control, we
- * do not decrease any runtime while the group "executes", neither we
- * need a timer to replenish it.
- *
- * With respect to SMP, the bandwidth is given on a per-CPU basis,
- * meaning that:
- * - dl_bw (< 100%) is the bandwidth of the system (group) on each CPU;
- * - dl_total_bw array contains, in the i-eth element, the currently
- * allocated bandwidth on the i-eth CPU.
- * Moreover, groups consume bandwidth on each CPU, while tasks only
- * consume bandwidth on the CPU they're running on.
- * Finally, dl_total_bw_cpu is used to cache the index of dl_total_bw
- * that will be shown the next time the proc or cgroup controls will
- * be red. It on its turn can be changed by writing on its own
- * control.
- */
struct dl_bandwidth {
raw_spinlock_t dl_runtime_lock;
u64 dl_runtime;
@@ -276,36 +297,30 @@ static inline int dl_bandwidth_enabled(void)
return sysctl_sched_rt_runtime >= 0;
}
+/*
+ * To keep the bandwidth of -deadline tasks under control
+ * we need some place where:
+ * - store the maximum -deadline bandwidth of each cpu;
+ * - cache the fraction of bandwidth that is currently allocated in
+ * each root domain;
+ *
+ * This is all done in the data structure below. It is similar to the
+ * one used for RT-throttling (rt_bandwidth), with the main difference
+ * that, since here we are only interested in admission control, we
+ * do not decrease any runtime while the group "executes", neither we
+ * need a timer to replenish it.
+ *
+ * With respect to SMP, bandwidth is given on a per root domain basis,
+ * meaning that:
+ * - bw (< 100%) is the deadline bandwidth of each CPU;
+ * - total_bw is the currently allocated bandwidth in each root domain;
+ */
struct dl_bw {
raw_spinlock_t lock;
u64 bw;
u64 total_bw;
};
-static inline void __dl_update(struct dl_bw *dl_b, s64 bw);
-
-static inline
-void __dl_sub(struct dl_bw *dl_b, u64 tsk_bw, int cpus)
-{
- dl_b->total_bw -= tsk_bw;
- __dl_update(dl_b, (s32)tsk_bw / cpus);
-}
-
-static inline
-void __dl_add(struct dl_bw *dl_b, u64 tsk_bw, int cpus)
-{
- dl_b->total_bw += tsk_bw;
- __dl_update(dl_b, -((s32)tsk_bw / cpus));
-}
-
-static inline
-bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw)
-{
- return dl_b->bw != -1 &&
- dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
-}
-
-extern void dl_change_utilization(struct task_struct *p, u64 new_bw);
extern void init_dl_bw(struct dl_bw *dl_b);
extern int sched_dl_global_validate(void);
extern void sched_dl_do_global(void);
@@ -314,15 +329,11 @@ extern void __setparam_dl(struct task_struct *p, const struct sched_attr *attr);
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_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed);
extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
-extern bool dl_cpu_busy(unsigned int cpu);
+extern int dl_cpu_busy(int cpu, struct task_struct *p);
#ifdef CONFIG_CGROUP_SCHED
-#include <linux/cgroup.h>
-#include <linux/psi.h>
-
struct cfs_rq;
struct rt_rq;
@@ -334,11 +345,12 @@ struct cfs_bandwidth {
ktime_t period;
u64 quota;
u64 runtime;
+ u64 burst;
+ u64 runtime_snap;
s64 hierarchical_quota;
u8 idle;
u8 period_active;
- u8 distribute_running;
u8 slack_started;
struct hrtimer period_timer;
struct hrtimer slack_timer;
@@ -347,7 +359,9 @@ struct cfs_bandwidth {
/* Statistics: */
int nr_periods;
int nr_throttled;
+ int nr_burst;
u64 throttled_time;
+ u64 burst_time;
#endif
};
@@ -362,6 +376,9 @@ struct task_group {
struct cfs_rq **cfs_rq;
unsigned long shares;
+ /* A positive value indicates that this is a SCHED_IDLE group. */
+ int idle;
+
#ifdef CONFIG_SMP
/*
* load_avg can be heavily contended at clock tick time, so put
@@ -449,8 +466,6 @@ 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);
@@ -464,13 +479,15 @@ 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_release_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);
+extern int sched_group_set_idle(struct task_group *tg, long idle);
+
#ifdef CONFIG_SMP
extern void set_task_rq_fair(struct sched_entity *se,
struct cfs_rq *prev, struct cfs_rq *next);
@@ -486,16 +503,64 @@ struct cfs_bandwidth { };
#endif /* CONFIG_CGROUP_SCHED */
+extern void unregister_rt_sched_group(struct task_group *tg);
+extern void free_rt_sched_group(struct task_group *tg);
+extern int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent);
+
+/*
+ * u64_u32_load/u64_u32_store
+ *
+ * Use a copy of a u64 value to protect against data race. This is only
+ * applicable for 32-bits architectures.
+ */
+#ifdef CONFIG_64BIT
+# define u64_u32_load_copy(var, copy) var
+# define u64_u32_store_copy(var, copy, val) (var = val)
+#else
+# define u64_u32_load_copy(var, copy) \
+({ \
+ u64 __val, __val_copy; \
+ do { \
+ __val_copy = copy; \
+ /* \
+ * paired with u64_u32_store_copy(), ordering access \
+ * to var and copy. \
+ */ \
+ smp_rmb(); \
+ __val = var; \
+ } while (__val != __val_copy); \
+ __val; \
+})
+# define u64_u32_store_copy(var, copy, val) \
+do { \
+ typeof(val) __val = (val); \
+ var = __val; \
+ /* \
+ * paired with u64_u32_load_copy(), ordering access to var and \
+ * copy. \
+ */ \
+ smp_wmb(); \
+ copy = __val; \
+} while (0)
+#endif
+# define u64_u32_load(var) u64_u32_load_copy(var, var##_copy)
+# define u64_u32_store(var, val) u64_u32_store_copy(var, var##_copy, val)
+
/* CFS-related fields in a runqueue */
struct cfs_rq {
struct load_weight load;
- unsigned long runnable_weight;
unsigned int nr_running;
unsigned int h_nr_running; /* SCHED_{NORMAL,BATCH,IDLE} */
+ unsigned int idle_nr_running; /* SCHED_IDLE */
unsigned int idle_h_nr_running; /* SCHED_IDLE */
u64 exec_clock;
u64 min_vruntime;
+#ifdef CONFIG_SCHED_CORE
+ unsigned int forceidle_seq;
+ u64 min_vruntime_fi;
+#endif
+
#ifndef CONFIG_64BIT
u64 min_vruntime_copy;
#endif
@@ -521,14 +586,14 @@ struct cfs_rq {
*/
struct sched_avg avg;
#ifndef CONFIG_64BIT
- u64 load_last_update_time_copy;
+ u64 last_update_time_copy;
#endif
struct {
raw_spinlock_t lock ____cacheline_aligned;
int nr;
unsigned long load_avg;
unsigned long util_avg;
- unsigned long runnable_sum;
+ unsigned long runnable_avg;
} removed;
#ifdef CONFIG_FAIR_GROUP_SCHED
@@ -563,13 +628,20 @@ struct cfs_rq {
struct list_head leaf_cfs_rq_list;
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
int runtime_enabled;
s64 runtime_remaining;
+ u64 throttled_pelt_idle;
+#ifndef CONFIG_64BIT
+ u64 throttled_pelt_idle_copy;
+#endif
u64 throttled_clock;
- u64 throttled_clock_task;
- u64 throttled_clock_task_time;
+ u64 throttled_clock_pelt;
+ u64 throttled_clock_pelt_time;
int throttled;
int throttle_count;
struct list_head throttled_list;
@@ -601,8 +673,8 @@ struct rt_rq {
} highest_prio;
#endif
#ifdef CONFIG_SMP
- unsigned long rt_nr_migratory;
- unsigned long rt_nr_total;
+ unsigned int rt_nr_migratory;
+ unsigned int rt_nr_total;
int overloaded;
struct plist_head pushable_tasks;
@@ -616,7 +688,7 @@ struct rt_rq {
raw_spinlock_t rt_runtime_lock;
#ifdef CONFIG_RT_GROUP_SCHED
- unsigned long rt_nr_boosted;
+ unsigned int rt_nr_boosted;
struct rq *rq;
struct task_group *tg;
@@ -633,7 +705,7 @@ struct dl_rq {
/* runqueue is an rbtree, ordered by deadline */
struct rb_root_cached root;
- unsigned long dl_nr_running;
+ unsigned int dl_nr_running;
#ifdef CONFIG_SMP
/*
@@ -647,7 +719,7 @@ struct dl_rq {
u64 next;
} earliest_dl;
- unsigned long dl_nr_migratory;
+ unsigned int dl_nr_migratory;
int overloaded;
/*
@@ -688,8 +760,30 @@ struct dl_rq {
#ifdef CONFIG_FAIR_GROUP_SCHED
/* An entity is a task if it doesn't "own" a runqueue */
#define entity_is_task(se) (!se->my_q)
+
+static inline void se_update_runnable(struct sched_entity *se)
+{
+ if (!entity_is_task(se))
+ se->runnable_weight = se->my_q->h_nr_running;
+}
+
+static inline long se_runnable(struct sched_entity *se)
+{
+ if (entity_is_task(se))
+ return !!se->on_rq;
+ else
+ return se->runnable_weight;
+}
+
#else
#define entity_is_task(se) 1
+
+static inline void se_update_runnable(struct sched_entity *se) {}
+
+static inline long se_runnable(struct sched_entity *se)
+{
+ return !!se->on_rq;
+}
#endif
#ifdef CONFIG_SMP
@@ -701,10 +795,6 @@ static inline long se_weight(struct sched_entity *se)
return scale_load_down(se->load.weight);
}
-static inline long se_runnable(struct sched_entity *se)
-{
- return scale_load_down(se->runnable_weight);
-}
static inline bool sched_asym_prefer(int a, int b)
{
@@ -755,6 +845,15 @@ struct root_domain {
struct dl_bw dl_bw;
struct cpudl cpudl;
+ /*
+ * Indicate whether a root_domain's dl_bw has been checked or
+ * updated. It's monotonously increasing value.
+ *
+ * Also, some corner cases, like 'wrap around' is dangerous, but given
+ * that u64 is 'big enough'. So that shouldn't be a concern.
+ */
+ u64 visit_gen;
+
#ifdef HAVE_RT_PUSH_IPI
/*
* For IPI pull requests, loop across the rto_mask.
@@ -835,8 +934,16 @@ struct uclamp_rq {
unsigned int value;
struct uclamp_bucket bucket[UCLAMP_BUCKETS];
};
+
+DECLARE_STATIC_KEY_FALSE(sched_uclamp_used);
#endif /* CONFIG_UCLAMP_TASK */
+struct rq;
+struct balance_callback {
+ struct balance_callback *next;
+ void (*func)(struct rq *rq);
+};
+
/*
* This is the main, per-CPU runqueue data structure.
*
@@ -846,7 +953,7 @@ struct uclamp_rq {
*/
struct rq {
/* runqueue lock: */
- raw_spinlock_t lock;
+ raw_spinlock_t __lock;
/*
* nr_running and cpu_load should be in the same cacheline because
@@ -860,15 +967,17 @@ struct rq {
#endif
#ifdef CONFIG_NO_HZ_COMMON
#ifdef CONFIG_SMP
- unsigned long last_load_update_tick;
unsigned long last_blocked_load_update_tick;
unsigned int has_blocked_load;
+ call_single_data_t nohz_csd;
#endif /* CONFIG_SMP */
unsigned int nohz_tick_stopped;
- atomic_t nohz_flags;
+ atomic_t nohz_flags;
#endif /* CONFIG_NO_HZ_COMMON */
- unsigned long nr_load_updates;
+#ifdef CONFIG_SMP
+ unsigned int ttwu_pending;
+#endif
u64 nr_switches;
#ifdef CONFIG_UCLAMP_TASK
@@ -894,7 +1003,7 @@ struct rq {
* 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;
+ unsigned int nr_uninterruptible;
struct task_struct __rcu *curr;
struct task_struct *idle;
@@ -908,9 +1017,20 @@ struct rq {
u64 clock_task ____cacheline_aligned;
u64 clock_pelt;
unsigned long lost_idle_time;
+ u64 clock_pelt_idle;
+ u64 clock_idle;
+#ifndef CONFIG_64BIT
+ u64 clock_pelt_idle_copy;
+ u64 clock_idle_copy;
+#endif
atomic_t nr_iowait;
+#ifdef CONFIG_SCHED_DEBUG
+ u64 last_seen_need_resched_ns;
+ int ticks_without_resched;
+#endif
+
#ifdef CONFIG_MEMBARRIER
int membarrier_state;
#endif
@@ -922,8 +1042,9 @@ struct rq {
unsigned long cpu_capacity;
unsigned long cpu_capacity_orig;
- struct callback_head *balance_callback;
+ struct balance_callback *balance_callback;
+ unsigned char nohz_idle_balance;
unsigned char idle_balance;
unsigned long misfit_task_load;
@@ -944,12 +1065,22 @@ struct rq {
#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
struct sched_avg avg_irq;
#endif
+#ifdef CONFIG_SCHED_THERMAL_PRESSURE
+ struct sched_avg avg_thermal;
+#endif
u64 idle_stamp;
u64 avg_idle;
+ unsigned long wake_stamp;
+ u64 wake_avg_idle;
+
/* This is used to determine avg_idle's max value */
u64 max_idle_balance_cost;
+
+#ifdef CONFIG_HOTPLUG_CPU
+ struct rcuwait hotplug_wait;
#endif
+#endif /* CONFIG_SMP */
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
u64 prev_irq_time;
@@ -967,10 +1098,10 @@ struct rq {
#ifdef CONFIG_SCHED_HRTICK
#ifdef CONFIG_SMP
- int hrtick_csd_pending;
call_single_data_t hrtick_csd;
#endif
struct hrtimer hrtick_timer;
+ ktime_t hrtick_time;
#endif
#ifdef CONFIG_SCHEDSTATS
@@ -991,14 +1122,34 @@ struct rq {
unsigned int ttwu_local;
#endif
-#ifdef CONFIG_SMP
- struct llist_head wake_list;
-#endif
-
#ifdef CONFIG_CPU_IDLE
/* Must be inspected within a rcu lock section */
struct cpuidle_state *idle_state;
#endif
+
+#ifdef CONFIG_SMP
+ unsigned int nr_pinned;
+#endif
+ unsigned int push_busy;
+ struct cpu_stop_work push_work;
+
+#ifdef CONFIG_SCHED_CORE
+ /* per rq */
+ struct rq *core;
+ struct task_struct *core_pick;
+ unsigned int core_enabled;
+ unsigned int core_sched_seq;
+ struct rb_root core_tree;
+
+ /* shared state -- careful with sched_core_cpu_deactivate() */
+ unsigned int core_task_seq;
+ unsigned int core_pick_seq;
+ unsigned long core_cookie;
+ unsigned int core_forceidle_count;
+ unsigned int core_forceidle_seq;
+ unsigned int core_forceidle_occupation;
+ u64 core_forceidle_start;
+#endif
};
#ifdef CONFIG_FAIR_GROUP_SCHED
@@ -1026,6 +1177,213 @@ static inline int cpu_of(struct rq *rq)
#endif
}
+#define MDF_PUSH 0x01
+
+static inline bool is_migration_disabled(struct task_struct *p)
+{
+#ifdef CONFIG_SMP
+ return p->migration_disabled;
+#else
+ return false;
+#endif
+}
+
+DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
+
+#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu)))
+#define this_rq() this_cpu_ptr(&runqueues)
+#define task_rq(p) cpu_rq(task_cpu(p))
+#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
+#define raw_rq() raw_cpu_ptr(&runqueues)
+
+struct sched_group;
+#ifdef CONFIG_SCHED_CORE
+static inline struct cpumask *sched_group_span(struct sched_group *sg);
+
+DECLARE_STATIC_KEY_FALSE(__sched_core_enabled);
+
+static inline bool sched_core_enabled(struct rq *rq)
+{
+ return static_branch_unlikely(&__sched_core_enabled) && rq->core_enabled;
+}
+
+static inline bool sched_core_disabled(void)
+{
+ return !static_branch_unlikely(&__sched_core_enabled);
+}
+
+/*
+ * Be careful with this function; not for general use. The return value isn't
+ * stable unless you actually hold a relevant rq->__lock.
+ */
+static inline raw_spinlock_t *rq_lockp(struct rq *rq)
+{
+ if (sched_core_enabled(rq))
+ return &rq->core->__lock;
+
+ return &rq->__lock;
+}
+
+static inline raw_spinlock_t *__rq_lockp(struct rq *rq)
+{
+ if (rq->core_enabled)
+ return &rq->core->__lock;
+
+ return &rq->__lock;
+}
+
+bool cfs_prio_less(struct task_struct *a, struct task_struct *b, bool fi);
+
+/*
+ * Helpers to check if the CPU's core cookie matches with the task's cookie
+ * when core scheduling is enabled.
+ * A special case is that the task's cookie always matches with CPU's core
+ * cookie if the CPU is in an idle core.
+ */
+static inline bool sched_cpu_cookie_match(struct rq *rq, struct task_struct *p)
+{
+ /* Ignore cookie match if core scheduler is not enabled on the CPU. */
+ if (!sched_core_enabled(rq))
+ return true;
+
+ return rq->core->core_cookie == p->core_cookie;
+}
+
+static inline bool sched_core_cookie_match(struct rq *rq, struct task_struct *p)
+{
+ bool idle_core = true;
+ int cpu;
+
+ /* Ignore cookie match if core scheduler is not enabled on the CPU. */
+ if (!sched_core_enabled(rq))
+ return true;
+
+ for_each_cpu(cpu, cpu_smt_mask(cpu_of(rq))) {
+ if (!available_idle_cpu(cpu)) {
+ idle_core = false;
+ break;
+ }
+ }
+
+ /*
+ * A CPU in an idle core is always the best choice for tasks with
+ * cookies.
+ */
+ return idle_core || rq->core->core_cookie == p->core_cookie;
+}
+
+static inline bool sched_group_cookie_match(struct rq *rq,
+ struct task_struct *p,
+ struct sched_group *group)
+{
+ int cpu;
+
+ /* Ignore cookie match if core scheduler is not enabled on the CPU. */
+ if (!sched_core_enabled(rq))
+ return true;
+
+ for_each_cpu_and(cpu, sched_group_span(group), p->cpus_ptr) {
+ if (sched_core_cookie_match(cpu_rq(cpu), p))
+ return true;
+ }
+ return false;
+}
+
+static inline bool sched_core_enqueued(struct task_struct *p)
+{
+ return !RB_EMPTY_NODE(&p->core_node);
+}
+
+extern void sched_core_enqueue(struct rq *rq, struct task_struct *p);
+extern void sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags);
+
+extern void sched_core_get(void);
+extern void sched_core_put(void);
+
+#else /* !CONFIG_SCHED_CORE */
+
+static inline bool sched_core_enabled(struct rq *rq)
+{
+ return false;
+}
+
+static inline bool sched_core_disabled(void)
+{
+ return true;
+}
+
+static inline raw_spinlock_t *rq_lockp(struct rq *rq)
+{
+ return &rq->__lock;
+}
+
+static inline raw_spinlock_t *__rq_lockp(struct rq *rq)
+{
+ return &rq->__lock;
+}
+
+static inline bool sched_cpu_cookie_match(struct rq *rq, struct task_struct *p)
+{
+ return true;
+}
+
+static inline bool sched_core_cookie_match(struct rq *rq, struct task_struct *p)
+{
+ return true;
+}
+
+static inline bool sched_group_cookie_match(struct rq *rq,
+ struct task_struct *p,
+ struct sched_group *group)
+{
+ return true;
+}
+#endif /* CONFIG_SCHED_CORE */
+
+static inline void lockdep_assert_rq_held(struct rq *rq)
+{
+ lockdep_assert_held(__rq_lockp(rq));
+}
+
+extern void raw_spin_rq_lock_nested(struct rq *rq, int subclass);
+extern bool raw_spin_rq_trylock(struct rq *rq);
+extern void raw_spin_rq_unlock(struct rq *rq);
+
+static inline void raw_spin_rq_lock(struct rq *rq)
+{
+ raw_spin_rq_lock_nested(rq, 0);
+}
+
+static inline void raw_spin_rq_lock_irq(struct rq *rq)
+{
+ local_irq_disable();
+ raw_spin_rq_lock(rq);
+}
+
+static inline void raw_spin_rq_unlock_irq(struct rq *rq)
+{
+ raw_spin_rq_unlock(rq);
+ local_irq_enable();
+}
+
+static inline unsigned long _raw_spin_rq_lock_irqsave(struct rq *rq)
+{
+ unsigned long flags;
+ local_irq_save(flags);
+ raw_spin_rq_lock(rq);
+ return flags;
+}
+
+static inline void raw_spin_rq_unlock_irqrestore(struct rq *rq, unsigned long flags)
+{
+ raw_spin_rq_unlock(rq);
+ local_irq_restore(flags);
+}
+
+#define raw_spin_rq_lock_irqsave(rq, flags) \
+do { \
+ flags = _raw_spin_rq_lock_irqsave(rq); \
+} while (0)
#ifdef CONFIG_SCHED_SMT
extern void __update_idle_core(struct rq *rq);
@@ -1040,21 +1398,59 @@ static inline void update_idle_core(struct rq *rq)
static inline void update_idle_core(struct rq *rq) { }
#endif
-DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static inline struct task_struct *task_of(struct sched_entity *se)
+{
+ SCHED_WARN_ON(!entity_is_task(se));
+ return container_of(se, struct task_struct, se);
+}
-#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu)))
-#define this_rq() this_cpu_ptr(&runqueues)
-#define task_rq(p) cpu_rq(task_cpu(p))
-#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
-#define raw_rq() raw_cpu_ptr(&runqueues)
+static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
+{
+ return p->se.cfs_rq;
+}
-extern void update_rq_clock(struct rq *rq);
+/* runqueue on which this entity is (to be) queued */
+static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
+{
+ return se->cfs_rq;
+}
-static inline u64 __rq_clock_broken(struct rq *rq)
+/* runqueue "owned" by this group */
+static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
{
- return READ_ONCE(rq->clock);
+ return grp->my_q;
}
+#else
+
+static inline struct task_struct *task_of(struct sched_entity *se)
+{
+ return container_of(se, struct task_struct, se);
+}
+
+static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
+{
+ return &task_rq(p)->cfs;
+}
+
+static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
+{
+ struct task_struct *p = task_of(se);
+ struct rq *rq = task_rq(p);
+
+ return &rq->cfs;
+}
+
+/* runqueue "owned" by this group */
+static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
+{
+ return NULL;
+}
+#endif
+
+extern void update_rq_clock(struct rq *rq);
+
/*
* rq::clock_update_flags bits
*
@@ -1074,7 +1470,7 @@ static inline u64 __rq_clock_broken(struct rq *rq)
*
* if (rq-clock_update_flags >= RQCF_UPDATED)
*
- * to check if %RQCF_UPADTED is set. It'll never be shifted more than
+ * to check if %RQCF_UPDATED is set. It'll never be shifted more than
* one position though, because the next rq_unpin_lock() will shift it
* back.
*/
@@ -1093,7 +1489,7 @@ static inline void assert_clock_updated(struct rq *rq)
static inline u64 rq_clock(struct rq *rq)
{
- lockdep_assert_held(&rq->lock);
+ lockdep_assert_rq_held(rq);
assert_clock_updated(rq);
return rq->clock;
@@ -1101,25 +1497,43 @@ static inline u64 rq_clock(struct rq *rq)
static inline u64 rq_clock_task(struct rq *rq)
{
- lockdep_assert_held(&rq->lock);
+ lockdep_assert_rq_held(rq);
assert_clock_updated(rq);
return rq->clock_task;
}
+/**
+ * By default the decay is the default pelt decay period.
+ * The decay shift can change the decay period in
+ * multiples of 32.
+ * Decay shift Decay period(ms)
+ * 0 32
+ * 1 64
+ * 2 128
+ * 3 256
+ * 4 512
+ */
+extern int sched_thermal_decay_shift;
+
+static inline u64 rq_clock_thermal(struct rq *rq)
+{
+ return rq_clock_task(rq) >> sched_thermal_decay_shift;
+}
+
static inline void rq_clock_skip_update(struct rq *rq)
{
- lockdep_assert_held(&rq->lock);
+ lockdep_assert_rq_held(rq);
rq->clock_update_flags |= RQCF_REQ_SKIP;
}
/*
* See rt task throttling, which is the only time a skip
- * request is cancelled.
+ * request is canceled.
*/
static inline void rq_clock_cancel_skipupdate(struct rq *rq)
{
- lockdep_assert_held(&rq->lock);
+ lockdep_assert_rq_held(rq);
rq->clock_update_flags &= ~RQCF_REQ_SKIP;
}
@@ -1136,13 +1550,28 @@ struct rq_flags {
#endif
};
+extern struct balance_callback balance_push_callback;
+
+/*
+ * Lockdep annotation that avoids accidental unlocks; it's like a
+ * sticky/continuous lockdep_assert_held().
+ *
+ * This avoids code that has access to 'struct rq *rq' (basically everything in
+ * the scheduler) from accidentally unlocking the rq if they do not also have a
+ * copy of the (on-stack) 'struct rq_flags rf'.
+ *
+ * Also see Documentation/locking/lockdep-design.rst.
+ */
static inline void rq_pin_lock(struct rq *rq, struct rq_flags *rf)
{
- rf->cookie = lockdep_pin_lock(&rq->lock);
+ rf->cookie = lockdep_pin_lock(__rq_lockp(rq));
#ifdef CONFIG_SCHED_DEBUG
rq->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
rf->clock_update_flags = 0;
+#ifdef CONFIG_SMP
+ SCHED_WARN_ON(rq->balance_callback && rq->balance_callback != &balance_push_callback);
+#endif
#endif
}
@@ -1153,12 +1582,12 @@ static inline void rq_unpin_lock(struct rq *rq, struct rq_flags *rf)
rf->clock_update_flags = RQCF_UPDATED;
#endif
- lockdep_unpin_lock(&rq->lock, rf->cookie);
+ lockdep_unpin_lock(__rq_lockp(rq), rf->cookie);
}
static inline void rq_repin_lock(struct rq *rq, struct rq_flags *rf)
{
- lockdep_repin_lock(&rq->lock, rf->cookie);
+ lockdep_repin_lock(__rq_lockp(rq), rf->cookie);
#ifdef CONFIG_SCHED_DEBUG
/*
@@ -1179,7 +1608,7 @@ static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf)
__releases(rq->lock)
{
rq_unpin_lock(rq, rf);
- raw_spin_unlock(&rq->lock);
+ raw_spin_rq_unlock(rq);
}
static inline void
@@ -1188,7 +1617,7 @@ task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
__releases(p->pi_lock)
{
rq_unpin_lock(rq, rf);
- raw_spin_unlock(&rq->lock);
+ raw_spin_rq_unlock(rq);
raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
}
@@ -1196,7 +1625,7 @@ static inline void
rq_lock_irqsave(struct rq *rq, struct rq_flags *rf)
__acquires(rq->lock)
{
- raw_spin_lock_irqsave(&rq->lock, rf->flags);
+ raw_spin_rq_lock_irqsave(rq, rf->flags);
rq_pin_lock(rq, rf);
}
@@ -1204,7 +1633,7 @@ static inline void
rq_lock_irq(struct rq *rq, struct rq_flags *rf)
__acquires(rq->lock)
{
- raw_spin_lock_irq(&rq->lock);
+ raw_spin_rq_lock_irq(rq);
rq_pin_lock(rq, rf);
}
@@ -1212,24 +1641,16 @@ static inline void
rq_lock(struct rq *rq, struct rq_flags *rf)
__acquires(rq->lock)
{
- raw_spin_lock(&rq->lock);
+ raw_spin_rq_lock(rq);
rq_pin_lock(rq, rf);
}
static inline void
-rq_relock(struct rq *rq, struct rq_flags *rf)
- __acquires(rq->lock)
-{
- raw_spin_lock(&rq->lock);
- rq_repin_lock(rq, rf);
-}
-
-static inline void
rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf)
__releases(rq->lock)
{
rq_unpin_lock(rq, rf);
- raw_spin_unlock_irqrestore(&rq->lock, rf->flags);
+ raw_spin_rq_unlock_irqrestore(rq, rf->flags);
}
static inline void
@@ -1237,7 +1658,7 @@ rq_unlock_irq(struct rq *rq, struct rq_flags *rf)
__releases(rq->lock)
{
rq_unpin_lock(rq, rf);
- raw_spin_unlock_irq(&rq->lock);
+ raw_spin_rq_unlock_irq(rq);
}
static inline void
@@ -1245,7 +1666,7 @@ rq_unlock(struct rq *rq, struct rq_flags *rf)
__releases(rq->lock)
{
rq_unpin_lock(rq, rf);
- raw_spin_unlock(&rq->lock);
+ raw_spin_rq_unlock(rq);
}
static inline struct rq *
@@ -1269,12 +1690,14 @@ enum numa_topology_type {
extern enum numa_topology_type sched_numa_topology_type;
extern int sched_max_numa_distance;
extern bool find_numa_distance(int distance);
-extern void sched_init_numa(void);
+extern void sched_init_numa(int offline_node);
+extern void sched_update_numa(int cpu, bool online);
extern void sched_domains_numa_masks_set(unsigned int cpu);
extern void sched_domains_numa_masks_clear(unsigned int cpu);
extern int sched_numa_find_closest(const struct cpumask *cpus, int cpu);
#else
-static inline void sched_init_numa(void) { }
+static inline void sched_init_numa(int offline_node) { }
+static inline void sched_update_numa(int cpu, bool online) { }
static inline void sched_domains_numa_masks_set(unsigned int cpu) { }
static inline void sched_domains_numa_masks_clear(unsigned int cpu) { }
static inline int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
@@ -1307,21 +1730,24 @@ init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
static inline void
queue_balance_callback(struct rq *rq,
- struct callback_head *head,
+ struct balance_callback *head,
void (*func)(struct rq *rq))
{
- lockdep_assert_held(&rq->lock);
+ lockdep_assert_rq_held(rq);
- if (unlikely(head->next))
+ /*
+ * Don't (re)queue an already queued item; nor queue anything when
+ * balance_push() is active, see the comment with
+ * balance_push_callback.
+ */
+ if (unlikely(head->next || rq->balance_callback == &balance_push_callback))
return;
- head->func = (void (*)(struct callback_head *))func;
+ head->func = func;
head->next = rq->balance_callback;
rq->balance_callback = head;
}
-extern void sched_ttwu_pending(void);
-
#define rcu_dereference_check_sched_domain(p) \
rcu_dereference_check((p), \
lockdep_is_held(&sched_domains_mutex))
@@ -1337,8 +1763,6 @@ extern void sched_ttwu_pending(void);
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
@@ -1382,6 +1806,11 @@ DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
extern struct static_key_false sched_asym_cpucapacity;
+static __always_inline bool sched_asym_cpucap_active(void)
+{
+ return static_branch_unlikely(&sched_asym_cpucapacity);
+}
+
struct sched_group_capacity {
atomic_t ref;
/*
@@ -1398,7 +1827,7 @@ struct sched_group_capacity {
int id;
#endif
- unsigned long cpumask[0]; /* Balance mask */
+ unsigned long cpumask[]; /* Balance mask */
};
struct sched_group {
@@ -1408,6 +1837,7 @@ struct sched_group {
unsigned int group_weight;
struct sched_group_capacity *sgc;
int asym_prefer_cpu; /* CPU of highest priority in group */
+ int flags;
/*
* The CPUs this group covers.
@@ -1416,7 +1846,7 @@ struct sched_group {
* 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];
+ unsigned long cpumask[];
};
static inline struct cpumask *sched_group_span(struct sched_group *sg)
@@ -1432,45 +1862,50 @@ static inline struct cpumask *group_balance_mask(struct sched_group *sg)
return to_cpumask(sg->sgc->cpumask);
}
-/**
- * group_first_cpu - Returns the first CPU in the cpumask of a sched_group.
- * @group: The group whose first CPU is to be returned.
- */
-static inline unsigned int group_first_cpu(struct sched_group *group)
-{
- return cpumask_first(sched_group_span(group));
-}
-
extern int group_balance_cpu(struct sched_group *sg);
-#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
-void register_sched_domain_sysctl(void);
+#ifdef CONFIG_SCHED_DEBUG
+void update_sched_domain_debugfs(void);
void dirty_sched_domain_sysctl(int cpu);
-void unregister_sched_domain_sysctl(void);
#else
-static inline void register_sched_domain_sysctl(void)
+static inline void update_sched_domain_debugfs(void)
{
}
static inline void dirty_sched_domain_sysctl(int cpu)
{
}
-static inline void unregister_sched_domain_sysctl(void)
+#endif
+
+extern int sched_update_scaling(void);
+#endif /* CONFIG_SMP */
+
+#include "stats.h"
+
+#if defined(CONFIG_SCHED_CORE) && defined(CONFIG_SCHEDSTATS)
+
+extern void __sched_core_account_forceidle(struct rq *rq);
+
+static inline void sched_core_account_forceidle(struct rq *rq)
{
+ if (schedstat_enabled())
+ __sched_core_account_forceidle(rq);
}
-#endif
-extern int newidle_balance(struct rq *this_rq, struct rq_flags *rf);
+extern void __sched_core_tick(struct rq *rq);
-#else
+static inline void sched_core_tick(struct rq *rq)
+{
+ if (sched_core_enabled(rq) && schedstat_enabled())
+ __sched_core_tick(rq);
+}
-static inline void sched_ttwu_pending(void) { }
+#else
-static inline int newidle_balance(struct rq *this_rq, struct rq_flags *rf) { return 0; }
+static inline void sched_core_account_forceidle(struct rq *rq) {}
-#endif /* CONFIG_SMP */
+static inline void sched_core_tick(struct rq *rq) {}
-#include "stats.h"
-#include "autogroup.h"
+#endif /* CONFIG_SCHED_CORE && CONFIG_SCHEDSTATS */
#ifdef CONFIG_CGROUP_SCHED
@@ -1503,6 +1938,7 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
set_task_rq_fair(&p->se, p->se.cfs_rq, tg->cfs_rq[cpu]);
p->se.cfs_rq = tg->cfs_rq[cpu];
p->se.parent = tg->se[cpu];
+ p->se.depth = tg->se[cpu] ? tg->se[cpu]->depth + 1 : 0;
#endif
#ifdef CONFIG_RT_GROUP_SCHED
@@ -1531,11 +1967,7 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
* per-task data have been completed by this moment.
*/
smp_wmb();
-#ifdef CONFIG_THREAD_INFO_IN_TASK
- WRITE_ONCE(p->cpu, cpu);
-#else
WRITE_ONCE(task_thread_info(p)->cpu, cpu);
-#endif
p->wake_cpu = cpu;
#endif
}
@@ -1544,7 +1976,6 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
* Tunables that become constants when CONFIG_SCHED_DEBUG is off:
*/
#ifdef CONFIG_SCHED_DEBUG
-# include <linux/static_key.h>
# define const_debug __read_mostly
#else
# define const_debug const
@@ -1560,7 +1991,7 @@ enum {
#undef SCHED_FEAT
-#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_JUMP_LABEL)
+#ifdef CONFIG_SCHED_DEBUG
/*
* To support run-time toggling of sched features, all the translation units
@@ -1568,6 +1999,7 @@ enum {
*/
extern const_debug unsigned int sysctl_sched_features;
+#ifdef CONFIG_JUMP_LABEL
#define SCHED_FEAT(name, enabled) \
static __always_inline bool static_branch_##name(struct static_key *key) \
{ \
@@ -1580,7 +2012,13 @@ static __always_inline bool static_branch_##name(struct static_key *key) \
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 && CONFIG_JUMP_LABEL) */
+#else /* !CONFIG_JUMP_LABEL */
+
+#define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
+
+#endif /* CONFIG_JUMP_LABEL */
+
+#else /* !SCHED_DEBUG */
/*
* Each translation unit has its own copy of sysctl_sched_features to allow
@@ -1596,7 +2034,7 @@ static const_debug __maybe_unused unsigned int sysctl_sched_features =
#define sched_feat(x) !!(sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
-#endif /* SCHED_DEBUG && CONFIG_JUMP_LABEL */
+#endif /* SCHED_DEBUG */
extern struct static_key_false sched_numa_balancing;
extern struct static_key_false sched_schedstats;
@@ -1619,7 +2057,7 @@ 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)
+static inline int task_on_cpu(struct rq *rq, struct task_struct *p)
{
#ifdef CONFIG_SMP
return p->on_cpu;
@@ -1638,12 +2076,19 @@ static inline int task_on_rq_migrating(struct task_struct *p)
return READ_ONCE(p->on_rq) == TASK_ON_RQ_MIGRATING;
}
-/*
- * 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 */
+/* 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_SYNC 0x10 /* Waker goes to sleep after wakeup */
+#define WF_MIGRATED 0x20 /* Internal use, task got migrated */
+
+#ifdef CONFIG_SMP
+static_assert(WF_EXEC == SD_BALANCE_EXEC);
+static_assert(WF_FORK == SD_BALANCE_FORK);
+static_assert(WF_TTWU == SD_BALANCE_WAKE);
+#endif
/*
* To aid in avoiding the subversion of "niceness" due to uneven distribution
@@ -1700,7 +2145,6 @@ extern const u32 sched_prio_to_wmult[40];
#define RETRY_TASK ((void *)-1UL)
struct sched_class {
- const struct sched_class *next;
#ifdef CONFIG_UCLAMP_TASK
int uclamp_enabled;
@@ -1709,7 +2153,7 @@ struct sched_class {
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);
+ bool (*yield_to_task)(struct rq *rq, struct task_struct *p);
void (*check_preempt_curr)(struct rq *rq, struct task_struct *p, int flags);
@@ -1720,16 +2164,22 @@ struct sched_class {
#ifdef CONFIG_SMP
int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
- int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
+ int (*select_task_rq)(struct task_struct *p, int task_cpu, int flags);
+
+ struct task_struct * (*pick_task)(struct rq *rq);
+
void (*migrate_task_rq)(struct task_struct *p, int new_cpu);
void (*task_woken)(struct rq *this_rq, struct task_struct *task);
void (*set_cpus_allowed)(struct task_struct *p,
- const struct cpumask *newmask);
+ const struct cpumask *newmask,
+ u32 flags);
void (*rq_online)(struct rq *rq);
void (*rq_offline)(struct rq *rq);
+
+ struct rq *(*find_lock_rq)(struct task_struct *p, struct rq *rq);
#endif
void (*task_tick)(struct rq *rq, struct task_struct *p, int queued);
@@ -1738,7 +2188,7 @@ struct sched_class {
/*
* The switched_from() call is allowed to drop rq->lock, therefore we
- * cannot assume the switched_from/switched_to pair is serliazed by
+ * cannot assume the switched_from/switched_to pair is serialized by
* rq->lock. They are however serialized by p->pi_lock.
*/
void (*switched_from)(struct rq *this_rq, struct task_struct *task);
@@ -1751,11 +2201,8 @@ struct sched_class {
void (*update_curr)(struct rq *rq);
-#define TASK_SET_GROUP 0
-#define TASK_MOVE_GROUP 1
-
#ifdef CONFIG_FAIR_GROUP_SCHED
- void (*task_change_group)(struct task_struct *p, int type);
+ void (*task_change_group)(struct task_struct *p);
#endif
};
@@ -1767,21 +2214,36 @@ static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
static inline void set_next_task(struct rq *rq, struct task_struct *next)
{
- WARN_ON_ONCE(rq->curr != next);
next->sched_class->set_next_task(rq, next, false);
}
-#ifdef CONFIG_SMP
-#define sched_class_highest (&stop_sched_class)
-#else
-#define sched_class_highest (&dl_sched_class)
-#endif
+
+/*
+ * Helper to define a sched_class instance; each one is placed in a separate
+ * section which is ordered by the linker script:
+ *
+ * include/asm-generic/vmlinux.lds.h
+ *
+ * *CAREFUL* they are laid out in *REVERSE* order!!!
+ *
+ * Also enforce alignment on the instance, not the type, to guarantee layout.
+ */
+#define DEFINE_SCHED_CLASS(name) \
+const struct sched_class name##_sched_class \
+ __aligned(__alignof__(struct sched_class)) \
+ __section("__" #name "_sched_class")
+
+/* Defined in include/asm-generic/vmlinux.lds.h */
+extern struct sched_class __sched_class_highest[];
+extern struct sched_class __sched_class_lowest[];
#define for_class_range(class, _from, _to) \
- for (class = (_from); class != (_to); class = class->next)
+ for (class = (_from); class < (_to); class++)
#define for_each_class(class) \
- for_class_range(class, sched_class_highest, NULL)
+ for_class_range(class, __sched_class_highest, __sched_class_lowest)
+
+#define sched_class_above(_a, _b) ((_a) < (_b))
extern const struct sched_class stop_sched_class;
extern const struct sched_class dl_sched_class;
@@ -1812,13 +2274,39 @@ static inline bool sched_fair_runnable(struct rq *rq)
extern struct task_struct *pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
extern struct task_struct *pick_next_task_idle(struct rq *rq);
+#define SCA_CHECK 0x01
+#define SCA_MIGRATE_DISABLE 0x02
+#define SCA_MIGRATE_ENABLE 0x04
+#define SCA_USER 0x08
+
#ifdef CONFIG_SMP
extern void update_group_capacity(struct sched_domain *sd, int cpu);
extern void trigger_load_balance(struct rq *rq);
-extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask);
+extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask, u32 flags);
+
+static inline struct task_struct *get_push_task(struct rq *rq)
+{
+ struct task_struct *p = rq->curr;
+
+ lockdep_assert_rq_held(rq);
+
+ if (rq->push_busy)
+ return NULL;
+
+ if (p->nr_cpus_allowed == 1)
+ return NULL;
+
+ if (p->migration_disabled)
+ return NULL;
+
+ rq->push_busy = true;
+ return get_task_struct(p);
+}
+
+extern int push_cpu_stop(void *arg);
#endif
@@ -1864,16 +2352,17 @@ 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 bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
-extern struct dl_bandwidth def_dl_bandwidth;
extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime);
extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
extern void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se);
-extern void init_dl_rq_bw_ratio(struct dl_rq *dl_rq);
#define BW_SHIFT 20
#define BW_UNIT (1 << BW_SHIFT)
#define RATIO_SHIFT 8
+#define MAX_BW_BITS (64 - BW_SHIFT)
+#define MAX_BW ((1ULL << MAX_BW_BITS) - 1)
unsigned long to_ratio(u64 period, u64 runtime);
extern void init_entity_runnable_average(struct sched_entity *se);
@@ -1890,12 +2379,7 @@ extern int __init sched_tick_offload_init(void);
*/
static inline void sched_update_tick_dependency(struct rq *rq)
{
- int cpu;
-
- if (!tick_nohz_full_enabled())
- return;
-
- cpu = cpu_of(rq);
+ int cpu = cpu_of(rq);
if (!tick_nohz_full_cpu(cpu))
return;
@@ -1915,6 +2399,9 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
unsigned prev_nr = rq->nr_running;
rq->nr_running = prev_nr + count;
+ if (trace_sched_update_nr_running_tp_enabled()) {
+ call_trace_sched_update_nr_running(rq, count);
+ }
#ifdef CONFIG_SMP
if (prev_nr < 2 && rq->nr_running >= 2) {
@@ -1929,6 +2416,10 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
static inline void sub_nr_running(struct rq *rq, unsigned count)
{
rq->nr_running -= count;
+ if (trace_sched_update_nr_running_tp_enabled()) {
+ call_trace_sched_update_nr_running(rq, -count);
+ }
+
/* Check if we still need preemption */
sched_update_tick_dependency(rq);
}
@@ -1938,9 +2429,32 @@ 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);
+#ifdef CONFIG_PREEMPT_RT
+#define SCHED_NR_MIGRATE_BREAK 8
+#else
+#define SCHED_NR_MIGRATE_BREAK 32
+#endif
+
extern const_debug unsigned int sysctl_sched_nr_migrate;
extern const_debug unsigned int sysctl_sched_migration_cost;
+#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;
+
+extern unsigned int sysctl_sched_tunable_scaling;
+
+extern unsigned int sysctl_numa_balancing_scan_delay;
+extern unsigned int sysctl_numa_balancing_scan_period_min;
+extern unsigned int sysctl_numa_balancing_scan_period_max;
+extern unsigned int sysctl_numa_balancing_scan_size;
+extern unsigned int sysctl_numa_balancing_hot_threshold;
+#endif
+
#ifdef CONFIG_SCHED_HRTICK
/*
@@ -1950,17 +2464,39 @@ extern const_debug unsigned int sysctl_sched_migration_cost;
*/
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 inline int hrtick_enabled_fair(struct rq *rq)
+{
+ if (!sched_feat(HRTICK))
+ return 0;
+ return hrtick_enabled(rq);
+}
+
+static inline int hrtick_enabled_dl(struct rq *rq)
+{
+ if (!sched_feat(HRTICK_DL))
+ return 0;
+ return hrtick_enabled(rq);
+}
+
void hrtick_start(struct rq *rq, u64 delay);
#else
+static inline int hrtick_enabled_fair(struct rq *rq)
+{
+ return 0;
+}
+
+static inline int hrtick_enabled_dl(struct rq *rq)
+{
+ return 0;
+}
+
static inline int hrtick_enabled(struct rq *rq)
{
return 0;
@@ -1968,7 +2504,24 @@ static inline int hrtick_enabled(struct rq *rq)
#endif /* CONFIG_SCHED_HRTICK */
+#ifndef arch_scale_freq_tick
+static __always_inline
+void arch_scale_freq_tick(void)
+{
+}
+#endif
+
#ifndef arch_scale_freq_capacity
+/**
+ * arch_scale_freq_capacity - get the frequency scale factor of a given CPU.
+ * @cpu: the CPU in question.
+ *
+ * Return: the frequency scale factor normalized against SCHED_CAPACITY_SCALE, i.e.
+ *
+ * f_curr
+ * ------ * SCHED_CAPACITY_SCALE
+ * f_max
+ */
static __always_inline
unsigned long arch_scale_freq_capacity(int cpu)
{
@@ -1976,10 +2529,56 @@ unsigned long arch_scale_freq_capacity(int cpu)
}
#endif
+#ifdef CONFIG_SCHED_DEBUG
+/*
+ * In double_lock_balance()/double_rq_lock(), we use raw_spin_rq_lock() to
+ * acquire rq lock instead of rq_lock(). So at the end of these two functions
+ * we need to call double_rq_clock_clear_update() to clear RQCF_UPDATED of
+ * rq->clock_update_flags to avoid the WARN_DOUBLE_CLOCK warning.
+ */
+static inline void double_rq_clock_clear_update(struct rq *rq1, struct rq *rq2)
+{
+ rq1->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
+ /* rq1 == rq2 for !CONFIG_SMP, so just clear RQCF_UPDATED once. */
#ifdef CONFIG_SMP
-#ifdef CONFIG_PREEMPTION
+ rq2->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
+#endif
+}
+#else
+static inline void double_rq_clock_clear_update(struct rq *rq1, struct rq *rq2) {}
+#endif
-static inline void double_rq_lock(struct rq *rq1, struct rq *rq2);
+#ifdef CONFIG_SMP
+
+static inline bool rq_order_less(struct rq *rq1, struct rq *rq2)
+{
+#ifdef CONFIG_SCHED_CORE
+ /*
+ * In order to not have {0,2},{1,3} turn into into an AB-BA,
+ * order by core-id first and cpu-id second.
+ *
+ * Notably:
+ *
+ * double_rq_lock(0,3); will take core-0, core-1 lock
+ * double_rq_lock(1,2); will take core-1, core-0 lock
+ *
+ * when only cpu-id is considered.
+ */
+ if (rq1->core->cpu < rq2->core->cpu)
+ return true;
+ if (rq1->core->cpu > rq2->core->cpu)
+ return false;
+
+ /*
+ * __sched_core_flip() relies on SMT having cpu-id lock order.
+ */
+#endif
+ return rq1->cpu < rq2->cpu;
+}
+
+extern void double_rq_lock(struct rq *rq1, struct rq *rq2);
+
+#ifdef CONFIG_PREEMPTION
/*
* fair double_lock_balance: Safely acquires both rq->locks in a fair
@@ -1994,7 +2593,7 @@ static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
__acquires(busiest->lock)
__acquires(this_rq->lock)
{
- raw_spin_unlock(&this_rq->lock);
+ raw_spin_rq_unlock(this_rq);
double_rq_lock(this_rq, busiest);
return 1;
@@ -2013,20 +2612,22 @@ static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
__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);
+ if (__rq_lockp(this_rq) == __rq_lockp(busiest) ||
+ likely(raw_spin_rq_trylock(busiest))) {
+ double_rq_clock_clear_update(this_rq, busiest);
+ return 0;
+ }
+
+ if (rq_order_less(this_rq, busiest)) {
+ raw_spin_rq_lock_nested(busiest, SINGLE_DEPTH_NESTING);
+ double_rq_clock_clear_update(this_rq, busiest);
+ return 0;
}
- return ret;
+
+ raw_spin_rq_unlock(this_rq);
+ double_rq_lock(this_rq, busiest);
+
+ return 1;
}
#endif /* CONFIG_PREEMPTION */
@@ -2036,11 +2637,7 @@ static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
*/
static inline int double_lock_balance(struct rq *this_rq, struct rq *busiest)
{
- if (unlikely(!irqs_disabled())) {
- /* printk() doesn't work well under rq->lock */
- raw_spin_unlock(&this_rq->lock);
- BUG_ON(1);
- }
+ lockdep_assert_irqs_disabled();
return _double_lock_balance(this_rq, busiest);
}
@@ -2048,8 +2645,9 @@ static inline int double_lock_balance(struct rq *this_rq, struct 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_);
+ if (__rq_lockp(this_rq) != __rq_lockp(busiest))
+ raw_spin_rq_unlock(busiest);
+ lock_set_subclass(&__rq_lockp(this_rq)->dep_map, 0, _RET_IP_);
}
static inline void double_lock(spinlock_t *l1, spinlock_t *l2)
@@ -2080,31 +2678,6 @@ static inline void double_raw_lock(raw_spinlock_t *l1, raw_spinlock_t *l2)
}
/*
- * 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,
@@ -2114,11 +2687,11 @@ 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);
+ if (__rq_lockp(rq1) != __rq_lockp(rq2))
+ raw_spin_rq_unlock(rq2);
else
__release(rq2->lock);
+ raw_spin_rq_unlock(rq1);
}
extern void set_rq_online (struct rq *rq);
@@ -2137,10 +2710,11 @@ 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);
+ WARN_ON_ONCE(!irqs_disabled());
+ WARN_ON_ONCE(rq1 != rq2);
+ raw_spin_rq_lock(rq1);
__acquire(rq2->lock); /* Fake it out ;) */
+ double_rq_clock_clear_update(rq1, rq2);
}
/*
@@ -2153,8 +2727,8 @@ 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);
+ WARN_ON_ONCE(rq1 != rq2);
+ raw_spin_rq_unlock(rq1);
__release(rq2->lock);
}
@@ -2164,7 +2738,7 @@ extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq);
extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq);
#ifdef CONFIG_SCHED_DEBUG
-extern bool sched_debug_enabled;
+extern bool sched_debug_verbose;
extern void print_cfs_stats(struct seq_file *m, int cpu);
extern void print_rt_stats(struct seq_file *m, int cpu);
@@ -2172,6 +2746,8 @@ extern void print_dl_stats(struct seq_file *m, int cpu);
extern void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq);
+
+extern void resched_latency_warn(int cpu, u64 latency);
#ifdef CONFIG_NUMA_BALANCING
extern void
show_numa_stats(struct task_struct *p, struct seq_file *m);
@@ -2179,6 +2755,8 @@ extern void
print_numa_stats(struct seq_file *m, int node, unsigned long tsf,
unsigned long tpf, unsigned long gsf, unsigned long gpf);
#endif /* CONFIG_NUMA_BALANCING */
+#else
+static inline void resched_latency_warn(int cpu, u64 latency) {}
#endif /* CONFIG_SCHED_DEBUG */
extern void init_cfs_rq(struct cfs_rq *cfs_rq);
@@ -2191,11 +2769,19 @@ extern void cfs_bandwidth_usage_dec(void);
#ifdef CONFIG_NO_HZ_COMMON
#define NOHZ_BALANCE_KICK_BIT 0
#define NOHZ_STATS_KICK_BIT 1
+#define NOHZ_NEWILB_KICK_BIT 2
+#define NOHZ_NEXT_KICK_BIT 3
+/* Run rebalance_domains() */
#define NOHZ_BALANCE_KICK BIT(NOHZ_BALANCE_KICK_BIT)
+/* Update blocked load */
#define NOHZ_STATS_KICK BIT(NOHZ_STATS_KICK_BIT)
+/* Update blocked load when entering idle */
+#define NOHZ_NEWILB_KICK BIT(NOHZ_NEWILB_KICK_BIT)
+/* Update nohz.next_balance */
+#define NOHZ_NEXT_KICK BIT(NOHZ_NEXT_KICK_BIT)
-#define NOHZ_KICK_MASK (NOHZ_BALANCE_KICK | NOHZ_STATS_KICK)
+#define NOHZ_KICK_MASK (NOHZ_BALANCE_KICK | NOHZ_STATS_KICK | NOHZ_NEXT_KICK)
#define nohz_flags(cpu) (&cpu_rq(cpu)->nohz_flags)
@@ -2204,33 +2790,12 @@ extern void nohz_balance_exit_idle(struct rq *rq);
static inline void nohz_balance_exit_idle(struct rq *rq) { }
#endif
-
-#ifdef CONFIG_SMP
-static inline
-void __dl_update(struct dl_bw *dl_b, s64 bw)
-{
- struct root_domain *rd = container_of(dl_b, struct root_domain, dl_bw);
- int i;
-
- RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
- "sched RCU must be held");
- for_each_cpu_and(i, rd->span, cpu_active_mask) {
- struct rq *rq = cpu_rq(i);
-
- rq->dl.extra_bw += bw;
- }
-}
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+extern void nohz_run_idle_balance(int cpu);
#else
-static inline
-void __dl_update(struct dl_bw *dl_b, s64 bw)
-{
- struct dl_rq *dl = container_of(dl_b, struct dl_rq, dl_bw);
-
- dl->extra_bw += bw;
-}
+static inline void nohz_run_idle_balance(int cpu) { }
#endif
-
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
struct irqtime {
u64 total;
@@ -2243,7 +2808,7 @@ DECLARE_PER_CPU(struct irqtime, cpu_irqtime);
/*
* Returns the irqtime minus the softirq time computed by ksoftirqd.
- * Otherwise ksoftirqd's sum_exec_runtime is substracted its own runtime
+ * Otherwise ksoftirqd's sum_exec_runtime is subtracted its own runtime
* and never move forward.
*/
static inline u64 irq_time_read(int cpu)
@@ -2299,40 +2864,6 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
#endif /* CONFIG_CPU_FREQ */
-#ifdef CONFIG_UCLAMP_TASK
-unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
-
-static __always_inline
-unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
- struct task_struct *p)
-{
- unsigned long min_util = READ_ONCE(rq->uclamp[UCLAMP_MIN].value);
- unsigned long max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value);
-
- if (p) {
- min_util = max(min_util, uclamp_eff_value(p, UCLAMP_MIN));
- max_util = max(max_util, uclamp_eff_value(p, UCLAMP_MAX));
- }
-
- /*
- * Since CPU's {min,max}_util clamps are MAX aggregated considering
- * RUNNABLE tasks with _different_ clamps, we can end up with an
- * inversion. Fix it now when the clamps are applied.
- */
- if (unlikely(min_util >= max_util))
- return min_util;
-
- return clamp(util, min_util, max_util);
-}
-#else /* CONFIG_UCLAMP_TASK */
-static inline
-unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
- struct task_struct *p)
-{
- return util;
-}
-#endif /* CONFIG_UCLAMP_TASK */
-
#ifdef arch_scale_freq_capacity
# ifndef arch_scale_freq_invariant
# define arch_scale_freq_invariant() true
@@ -2346,29 +2877,41 @@ static inline unsigned long capacity_orig_of(int cpu)
{
return cpu_rq(cpu)->cpu_capacity_orig;
}
-#endif
/**
- * enum schedutil_type - CPU utilization type
+ * enum cpu_util_type - CPU utilization type
* @FREQUENCY_UTIL: Utilization used to select frequency
* @ENERGY_UTIL: Utilization used during energy calculation
*
* The utilization signals of all scheduling classes (CFS/RT/DL) and IRQ time
* need to be aggregated differently depending on the usage made of them. This
- * enum is used within schedutil_freq_util() to differentiate the types of
+ * enum is used within effective_cpu_util() to differentiate the types of
* utilization expected by the callers, and adjust the aggregation accordingly.
*/
-enum schedutil_type {
+enum cpu_util_type {
FREQUENCY_UTIL,
ENERGY_UTIL,
};
-#ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
-
-unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs,
- unsigned long max, enum schedutil_type type,
+unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
+ enum cpu_util_type type,
struct task_struct *p);
+/*
+ * Verify the fitness of task @p to run on @cpu taking into account the
+ * CPU original capacity and the runtime/deadline ratio of the task.
+ *
+ * The function will return true if the original capacity of @cpu is
+ * greater than or equal to task's deadline density right shifted by
+ * (BW_SHIFT - SCHED_CAPACITY_SHIFT) and false otherwise.
+ */
+static inline bool dl_task_fits_capacity(struct task_struct *p, int cpu)
+{
+ unsigned long cap = arch_scale_cpu_capacity(cpu);
+
+ return cap >= p->dl.dl_density >> (BW_SHIFT - SCHED_CAPACITY_SHIFT);
+}
+
static inline unsigned long cpu_bw_dl(struct rq *rq)
{
return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT;
@@ -2379,30 +2922,158 @@ static inline unsigned long cpu_util_dl(struct rq *rq)
return READ_ONCE(rq->avg_dl.util_avg);
}
-static inline unsigned long cpu_util_cfs(struct rq *rq)
+/**
+ * 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)
{
- unsigned long util = READ_ONCE(rq->cfs.avg.util_avg);
+ 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(rq->cfs.avg.util_est.enqueued));
+ READ_ONCE(cfs_rq->avg.util_est.enqueued));
}
- return util;
+ return min(util, capacity_orig_of(cpu));
}
static inline unsigned long cpu_util_rt(struct rq *rq)
{
return READ_ONCE(rq->avg_rt.util_avg);
}
-#else /* CONFIG_CPU_FREQ_GOV_SCHEDUTIL */
-static inline unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs,
- unsigned long max, enum schedutil_type type,
- struct task_struct *p)
+#endif
+
+#ifdef CONFIG_UCLAMP_TASK
+unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
+
+/**
+ * uclamp_rq_util_with - clamp @util with @rq and @p effective uclamp values.
+ * @rq: The rq to clamp against. Must not be NULL.
+ * @util: The util value to clamp.
+ * @p: The task to clamp against. Can be NULL if you want to clamp
+ * against @rq only.
+ *
+ * Clamps the passed @util to the max(@rq, @p) effective uclamp values.
+ *
+ * If sched_uclamp_used static key is disabled, then just return the util
+ * without any clamping since uclamp aggregation at the rq level in the fast
+ * path is disabled, rendering this operation a NOP.
+ *
+ * Use uclamp_eff_value() if you don't care about uclamp values at rq level. It
+ * will return the correct effective uclamp value of the task even if the
+ * static key is disabled.
+ */
+static __always_inline
+unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
+ struct task_struct *p)
{
- return 0;
+ unsigned long min_util = 0;
+ unsigned long max_util = 0;
+
+ if (!static_branch_likely(&sched_uclamp_used))
+ return util;
+
+ if (p) {
+ min_util = uclamp_eff_value(p, UCLAMP_MIN);
+ max_util = uclamp_eff_value(p, UCLAMP_MAX);
+
+ /*
+ * Ignore last runnable task's max clamp, as this task will
+ * reset it. Similarly, no need to read the rq's min clamp.
+ */
+ if (rq->uclamp_flags & UCLAMP_FLAG_IDLE)
+ goto out;
+ }
+
+ min_util = max_t(unsigned long, min_util, READ_ONCE(rq->uclamp[UCLAMP_MIN].value));
+ max_util = max_t(unsigned long, max_util, READ_ONCE(rq->uclamp[UCLAMP_MAX].value));
+out:
+ /*
+ * Since CPU's {min,max}_util clamps are MAX aggregated considering
+ * RUNNABLE tasks with _different_ clamps, we can end up with an
+ * inversion. Fix it now when the clamps are applied.
+ */
+ if (unlikely(min_util >= max_util))
+ return min_util;
+
+ return clamp(util, min_util, max_util);
}
-#endif /* CONFIG_CPU_FREQ_GOV_SCHEDUTIL */
+
+/* Is the rq being capped/throttled by uclamp_max? */
+static inline bool uclamp_rq_is_capped(struct rq *rq)
+{
+ unsigned long rq_util;
+ unsigned long max_util;
+
+ if (!static_branch_likely(&sched_uclamp_used))
+ return false;
+
+ rq_util = cpu_util_cfs(cpu_of(rq)) + cpu_util_rt(rq);
+ max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value);
+
+ return max_util != SCHED_CAPACITY_SCALE && rq_util >= max_util;
+}
+
+/*
+ * When uclamp is compiled in, the aggregation at rq level is 'turned off'
+ * by default in the fast path and only gets turned on once userspace performs
+ * an operation that requires it.
+ *
+ * Returns true if userspace opted-in to use uclamp and aggregation at rq level
+ * hence is active.
+ */
+static inline bool uclamp_is_used(void)
+{
+ return static_branch_likely(&sched_uclamp_used);
+}
+#else /* CONFIG_UCLAMP_TASK */
+static inline
+unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
+ struct task_struct *p)
+{
+ return util;
+}
+
+static inline bool uclamp_rq_is_capped(struct rq *rq) { return false; }
+
+static inline bool uclamp_is_used(void)
+{
+ return false;
+}
+#endif /* CONFIG_UCLAMP_TASK */
#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
static inline unsigned long cpu_util_irq(struct rq *rq)
@@ -2492,3 +3163,24 @@ static inline bool is_per_cpu_kthread(struct task_struct *p)
return true;
}
#endif
+
+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);
+
+#ifdef CONFIG_PREEMPT_DYNAMIC
+extern int preempt_dynamic_mode;
+extern int sched_dynamic_mode(const char *str);
+extern void sched_dynamic_update(int mode);
+#endif
+
+static inline void update_current_exec_runtime(struct task_struct *curr,
+ u64 now, u64 delta_exec)
+{
+ curr->se.sum_exec_runtime += delta_exec;
+ account_group_exec_runtime(curr, delta_exec);
+
+ curr->se.exec_start = now;
+ cgroup_account_cputime(curr, delta_exec);
+}
+
+#endif /* _KERNEL_SCHED_SCHED_H */