diff options
Diffstat (limited to 'include/linux/sched.h')
-rw-r--r-- | include/linux/sched.h | 274 |
1 files changed, 264 insertions, 10 deletions
diff --git a/include/linux/sched.h b/include/linux/sched.h index 315df144c156..f415b2452ed8 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -51,6 +51,7 @@ struct sched_param { #include <linux/resource.h> #include <linux/timer.h> #include <linux/hrtimer.h> +#include <linux/kcov.h> #include <linux/task_io_accounting.h> #include <linux/latencytop.h> #include <linux/cred.h> @@ -173,6 +174,9 @@ extern bool single_task_running(void); extern unsigned long nr_iowait(void); extern unsigned long nr_iowait_cpu(int cpu); extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load); +#ifdef CONFIG_CPU_QUIET +extern u64 nr_running_integral(unsigned int cpu); +#endif extern void calc_global_load(unsigned long ticks); @@ -219,9 +223,10 @@ extern void proc_sched_set_task(struct task_struct *p); #define TASK_WAKING 256 #define TASK_PARKED 512 #define TASK_NOLOAD 1024 -#define TASK_STATE_MAX 2048 +#define TASK_NEW 2048 +#define TASK_STATE_MAX 4096 -#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPN" +#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPNn" extern char ___assert_task_state[1 - 2*!!( sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)]; @@ -314,6 +319,15 @@ extern char ___assert_task_state[1 - 2*!!( /* Task command name length */ #define TASK_COMM_LEN 16 +enum task_event { + PUT_PREV_TASK = 0, + PICK_NEXT_TASK = 1, + TASK_WAKE = 2, + TASK_MIGRATE = 3, + TASK_UPDATE = 4, + IRQ_UPDATE = 5, +}; + #include <linux/spinlock.h> /* @@ -939,6 +953,14 @@ enum cpu_idle_type { #define SCHED_CAPACITY_SHIFT 10 #define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT) +struct sched_capacity_reqs { + unsigned long cfs; + unsigned long rt; + unsigned long dl; + + unsigned long total; +}; + /* * Wake-queues are lists of tasks with a pending wakeup, whose * callers have already marked the task as woken internally, @@ -972,12 +994,13 @@ struct wake_q_node { struct wake_q_head { struct wake_q_node *first; struct wake_q_node **lastp; + int count; }; #define WAKE_Q_TAIL ((struct wake_q_node *) 0x01) #define WAKE_Q(name) \ - struct wake_q_head name = { WAKE_Q_TAIL, &name.first } + struct wake_q_head name = { WAKE_Q_TAIL, &name.first, 0 } extern void wake_q_add(struct wake_q_head *head, struct task_struct *task); @@ -993,7 +1016,8 @@ extern void wake_up_q(struct wake_q_head *head); #define SD_BALANCE_FORK 0x0008 /* Balance on fork, clone */ #define SD_BALANCE_WAKE 0x0010 /* Balance on wakeup */ #define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */ -#define SD_SHARE_CPUCAPACITY 0x0080 /* Domain members share cpu power */ +#define SD_ASYM_CPUCAPACITY 0x0040 /* Groups have different max cpu capacities */ +#define SD_SHARE_CPUCAPACITY 0x0080 /* Domain members share cpu capacity */ #define SD_SHARE_POWERDOMAIN 0x0100 /* Domain members share power domain */ #define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share cpu pkg resources */ #define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */ @@ -1001,6 +1025,7 @@ extern void wake_up_q(struct wake_q_head *head); #define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */ #define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */ #define SD_NUMA 0x4000 /* cross-node balancing */ +#define SD_SHARE_CAP_STATES 0x8000 /* Domain members share capacity state */ #ifdef CONFIG_SCHED_SMT static inline int cpu_smt_flags(void) @@ -1033,8 +1058,57 @@ struct sched_domain_attr { extern int sched_domain_level_max; +struct capacity_state { + unsigned long cap; /* compute capacity */ + unsigned long power; /* power consumption at this compute capacity */ +}; + +struct idle_state { + unsigned long power; /* power consumption in this idle state */ +}; + +struct sched_group_energy { + unsigned int nr_idle_states; /* number of idle states */ + struct idle_state *idle_states; /* ptr to idle state array */ + unsigned int nr_cap_states; /* number of capacity states */ + struct capacity_state *cap_states; /* ptr to capacity state array */ +}; + +unsigned long capacity_curr_of(int cpu); + struct sched_group; +struct eas_stats { + /* select_idle_sibling() stats */ + u64 sis_attempts; + u64 sis_idle; + u64 sis_cache_affine; + u64 sis_suff_cap; + u64 sis_idle_cpu; + u64 sis_count; + + /* select_energy_cpu_brute() stats */ + u64 secb_attempts; + u64 secb_sync; + u64 secb_idle_bt; + u64 secb_insuff_cap; + u64 secb_no_nrg_sav; + u64 secb_nrg_sav; + u64 secb_count; + + /* find_best_target() stats */ + u64 fbt_attempts; + u64 fbt_no_cpu; + u64 fbt_no_sd; + u64 fbt_pref_idle; + u64 fbt_count; + + /* cas */ + /* select_task_rq_fair() stats */ + u64 cas_attempts; + u64 cas_count; +}; + struct sched_domain { /* These fields must be setup */ struct sched_domain *parent; /* top domain must be null terminated */ @@ -1095,6 +1169,8 @@ struct sched_domain { unsigned int ttwu_wake_remote; unsigned int ttwu_move_affine; unsigned int ttwu_move_balance; + + struct eas_stats eas_stats; #endif #ifdef CONFIG_SCHED_DEBUG char *name; @@ -1131,6 +1207,8 @@ bool cpus_share_cache(int this_cpu, int that_cpu); typedef const struct cpumask *(*sched_domain_mask_f)(int cpu); typedef int (*sched_domain_flags_f)(void); +typedef +const struct sched_group_energy * const(*sched_domain_energy_f)(int cpu); #define SDTL_OVERLAP 0x01 @@ -1143,6 +1221,7 @@ struct sd_data { struct sched_domain_topology_level { sched_domain_mask_f mask; sched_domain_flags_f sd_flags; + sched_domain_energy_f energy; int flags; int numa_level; struct sd_data data; @@ -1250,6 +1329,70 @@ struct sched_statistics { u64 nr_wakeups_affine_attempts; u64 nr_wakeups_passive; u64 nr_wakeups_idle; + + /* select_idle_sibling() */ + u64 nr_wakeups_sis_attempts; + u64 nr_wakeups_sis_idle; + u64 nr_wakeups_sis_cache_affine; + u64 nr_wakeups_sis_suff_cap; + u64 nr_wakeups_sis_idle_cpu; + u64 nr_wakeups_sis_count; + + /* energy_aware_wake_cpu() */ + u64 nr_wakeups_secb_attempts; + u64 nr_wakeups_secb_sync; + u64 nr_wakeups_secb_idle_bt; + u64 nr_wakeups_secb_insuff_cap; + u64 nr_wakeups_secb_no_nrg_sav; + u64 nr_wakeups_secb_nrg_sav; + u64 nr_wakeups_secb_count; + + /* find_best_target() */ + u64 nr_wakeups_fbt_attempts; + u64 nr_wakeups_fbt_no_cpu; + u64 nr_wakeups_fbt_no_sd; + u64 nr_wakeups_fbt_pref_idle; + u64 nr_wakeups_fbt_count; + + /* cas */ + /* select_task_rq_fair() */ + u64 nr_wakeups_cas_attempts; + u64 nr_wakeups_cas_count; +}; +#endif + +#ifdef CONFIG_SCHED_WALT +#define RAVG_HIST_SIZE_MAX 5 + +/* ravg represents frequency scaled cpu-demand of tasks */ +struct ravg { + /* + * 'mark_start' marks the beginning of an event (task waking up, task + * starting to execute, task being preempted) within a window + * + * 'sum' represents how runnable a task has been within current + * window. It incorporates both running time and wait time and is + * frequency scaled. + * + * 'sum_history' keeps track of history of 'sum' seen over previous + * RAVG_HIST_SIZE windows. Windows where task was entirely sleeping are + * ignored. + * + * 'demand' represents maximum sum seen over previous + * sysctl_sched_ravg_hist_size windows. 'demand' could drive frequency + * demand for tasks. + * + * 'curr_window' represents task's contribution to cpu busy time + * statistics (rq->curr_runnable_sum) in current window + * + * 'prev_window' represents task's contribution to cpu busy time + * statistics (rq->prev_runnable_sum) in previous window + */ + u64 mark_start; + u32 sum, demand; + u32 sum_history[RAVG_HIST_SIZE_MAX]; + u32 curr_window, prev_window; + u16 active_windows; }; #endif @@ -1291,6 +1434,10 @@ struct sched_rt_entity { unsigned long watchdog_stamp; unsigned int time_slice; + /* Accesses for these must be guarded by rq->lock of the task's rq */ + bool schedtune_enqueued; + struct hrtimer schedtune_timer; + struct sched_rt_entity *back; #ifdef CONFIG_RT_GROUP_SCHED struct sched_rt_entity *parent; @@ -1389,6 +1536,13 @@ struct tlbflush_unmap_batch { }; struct task_struct { +#ifdef CONFIG_THREAD_INFO_IN_TASK + /* + * For reasons of header soup (see current_thread_info()), this + * must be the first element of task_struct. + */ + struct thread_info thread_info; +#endif volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */ void *stack; atomic_t usage; @@ -1398,6 +1552,9 @@ struct task_struct { #ifdef CONFIG_SMP struct llist_node wake_entry; int on_cpu; +#ifdef CONFIG_THREAD_INFO_IN_TASK + unsigned int cpu; /* current CPU */ +#endif unsigned int wakee_flips; unsigned long wakee_flip_decay_ts; struct task_struct *last_wakee; @@ -1411,6 +1568,16 @@ struct task_struct { const struct sched_class *sched_class; struct sched_entity se; struct sched_rt_entity rt; +#ifdef CONFIG_SCHED_WALT + struct ravg ravg; + /* + * 'init_load_pct' represents the initial task load assigned to children + * of this task + */ + u32 init_load_pct; + u64 last_sleep_ts; +#endif + #ifdef CONFIG_CGROUP_SCHED struct task_group *sched_task_group; #endif @@ -1535,6 +1702,10 @@ struct task_struct { cputime_t utime, stime, utimescaled, stimescaled; cputime_t gtime; +#ifdef CONFIG_CPU_FREQ_TIMES + u64 *time_in_state; + unsigned int max_state; +#endif struct prev_cputime prev_cputime; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN seqlock_t vtime_seqlock; @@ -1785,8 +1956,8 @@ struct task_struct { * time slack values; these are used to round up poll() and * select() etc timeout values. These are in nanoseconds. */ - unsigned long timer_slack_ns; - unsigned long default_timer_slack_ns; + u64 timer_slack_ns; + u64 default_timer_slack_ns; #ifdef CONFIG_KASAN unsigned int kasan_depth; @@ -1812,6 +1983,16 @@ struct task_struct { /* bitmask and counter of trace recursion */ unsigned long trace_recursion; #endif /* CONFIG_TRACING */ +#ifdef CONFIG_KCOV + /* Coverage collection mode enabled for this task (0 if disabled). */ + enum kcov_mode kcov_mode; + /* Size of the kcov_area. */ + unsigned kcov_size; + /* Buffer for coverage collection. */ + void *kcov_area; + /* kcov desciptor wired with this task or NULL. */ + struct kcov *kcov; +#endif #ifdef CONFIG_MEMCG struct mem_cgroup *memcg_in_oom; gfp_t memcg_oom_gfp_mask; @@ -2440,7 +2621,9 @@ extern void set_curr_task(int cpu, struct task_struct *p); void yield(void); union thread_union { +#ifndef CONFIG_THREAD_INFO_IN_TASK struct thread_info thread_info; +#endif unsigned long stack[THREAD_SIZE/sizeof(long)]; }; @@ -2627,6 +2810,11 @@ static inline bool mmget_not_zero(struct mm_struct *mm) /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); +/* same as above but performs the slow path from the async kontext. Can + * be called from the atomic context as well + */ +extern void mmput_async(struct mm_struct *); + /* Grab a reference to a task's mm, if it is not already going away */ extern struct mm_struct *get_task_mm(struct task_struct *task); /* @@ -2655,7 +2843,14 @@ static inline int copy_thread_tls( } #endif extern void flush_thread(void); -extern void exit_thread(void); + +#ifdef CONFIG_HAVE_EXIT_THREAD +extern void exit_thread(struct task_struct *tsk); +#else +static inline void exit_thread(struct task_struct *tsk) +{ +} +#endif extern void exit_files(struct task_struct *); extern void __cleanup_sighand(struct sighand_struct *); @@ -2840,10 +3035,34 @@ static inline void threadgroup_change_end(struct task_struct *tsk) cgroup_threadgroup_change_end(tsk); } -#ifndef __HAVE_THREAD_FUNCTIONS +#ifdef CONFIG_THREAD_INFO_IN_TASK + +static inline struct thread_info *task_thread_info(struct task_struct *task) +{ + return &task->thread_info; +} + +/* + * When accessing the stack of a non-current task that might exit, use + * try_get_task_stack() instead. task_stack_page will return a pointer + * that could get freed out from under you. + */ +static inline void *task_stack_page(const struct task_struct *task) +{ + return task->stack; +} + +#define setup_thread_stack(new,old) do { } while(0) + +static inline unsigned long *end_of_stack(const struct task_struct *task) +{ + return task->stack; +} + +#elif !defined(__HAVE_THREAD_FUNCTIONS) #define task_thread_info(task) ((struct thread_info *)(task)->stack) -#define task_stack_page(task) ((task)->stack) +#define task_stack_page(task) ((void *)(task)->stack) static inline void setup_thread_stack(struct task_struct *p, struct task_struct *org) { @@ -2870,6 +3089,14 @@ static inline unsigned long *end_of_stack(struct task_struct *p) } #endif + +static inline void *try_get_task_stack(struct task_struct *tsk) +{ + return task_stack_page(tsk); +} + +static inline void put_task_stack(struct task_struct *tsk) {} + #define task_stack_end_corrupted(task) \ (*(end_of_stack(task)) != STACK_END_MAGIC) @@ -2880,7 +3107,7 @@ static inline int object_is_on_stack(void *obj) return (obj >= stack) && (obj < (stack + THREAD_SIZE)); } -extern void thread_info_cache_init(void); +extern void thread_stack_cache_init(void); #ifdef CONFIG_DEBUG_STACK_USAGE static inline unsigned long stack_not_used(struct task_struct *p) @@ -3135,7 +3362,11 @@ static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume) static inline unsigned int task_cpu(const struct task_struct *p) { +#ifdef CONFIG_THREAD_INFO_IN_TASK + return p->cpu; +#else return task_thread_info(p)->cpu; +#endif } static inline int task_node(const struct task_struct *p) @@ -3188,6 +3419,11 @@ static inline void inc_syscw(struct task_struct *tsk) { tsk->ioac.syscw++; } + +static inline void inc_syscfs(struct task_struct *tsk) +{ + tsk->ioac.syscfs++; +} #else static inline void add_rchar(struct task_struct *tsk, ssize_t amt) { @@ -3204,6 +3440,9 @@ static inline void inc_syscr(struct task_struct *tsk) static inline void inc_syscw(struct task_struct *tsk) { } +static inline void inc_syscfs(struct task_struct *tsk) +{ +} #endif #ifndef TASK_SIZE_OF @@ -3240,4 +3479,19 @@ static inline unsigned long rlimit_max(unsigned int limit) return task_rlimit_max(current, limit); } +#define SCHED_CPUFREQ_RT (1U << 0) +#define SCHED_CPUFREQ_DL (1U << 1) +#define SCHED_CPUFREQ_IOWAIT (1U << 2) + +#ifdef CONFIG_CPU_FREQ +struct update_util_data { + void (*func)(struct update_util_data *data, u64 time, unsigned int flags); +}; + +void cpufreq_add_update_util_hook(int cpu, struct update_util_data *data, + void (*func)(struct update_util_data *data, u64 time, + unsigned int flags)); +void cpufreq_remove_update_util_hook(int cpu); +#endif /* CONFIG_CPU_FREQ */ + #endif |