diff options
Diffstat (limited to 'include/linux/sched.h')
| -rw-r--r-- | include/linux/sched.h | 218 |
1 files changed, 138 insertions, 80 deletions
diff --git a/include/linux/sched.h b/include/linux/sched.h index a781dec1cd0..ea74596014a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -3,6 +3,8 @@ #include <uapi/linux/sched.h> +#include <linux/sched/prio.h> + struct sched_param { int sched_priority; @@ -27,7 +29,7 @@ struct sched_param { #include <asm/page.h> #include <asm/ptrace.h> -#include <asm/cputime.h> +#include <linux/cputime.h> #include <linux/smp.h> #include <linux/sem.h> @@ -130,11 +132,9 @@ struct perf_event_context; struct blk_plug; struct filename; -/* - * List of flags we want to share for kernel threads, - * if only because they are not used by them anyway. - */ -#define CLONE_KERNEL (CLONE_FS | CLONE_FILES | CLONE_SIGHAND) +#define VMACACHE_BITS 2 +#define VMACACHE_SIZE (1U << VMACACHE_BITS) +#define VMACACHE_MASK (VMACACHE_SIZE - 1) /* * These are the constant used to fake the fixed-point load-average @@ -204,8 +204,9 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq); #define __TASK_STOPPED 4 #define __TASK_TRACED 8 /* in tsk->exit_state */ -#define EXIT_ZOMBIE 16 -#define EXIT_DEAD 32 +#define EXIT_DEAD 16 +#define EXIT_ZOMBIE 32 +#define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD) /* in tsk->state again */ #define TASK_DEAD 64 #define TASK_WAKEKILL 128 @@ -213,7 +214,7 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq); #define TASK_PARKED 512 #define TASK_STATE_MAX 1024 -#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP" +#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWP" extern char ___assert_task_state[1 - 2*!!( sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)]; @@ -292,10 +293,14 @@ extern int runqueue_is_locked(int cpu); #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) extern void nohz_balance_enter_idle(int cpu); extern void set_cpu_sd_state_idle(void); -extern int get_nohz_timer_target(void); +extern int get_nohz_timer_target(int pinned); #else static inline void nohz_balance_enter_idle(int cpu) { } static inline void set_cpu_sd_state_idle(void) { } +static inline int get_nohz_timer_target(int pinned) +{ + return smp_processor_id(); +} #endif /* @@ -734,7 +739,6 @@ static inline int signal_group_exit(const struct signal_struct *sig) struct user_struct { atomic_t __count; /* reference count */ atomic_t processes; /* How many processes does this user have? */ - atomic_t files; /* How many open files does this user have? */ atomic_t sigpending; /* How many pending signals does this user have? */ #ifdef CONFIG_INOTIFY_USER atomic_t inotify_watches; /* How many inotify watches does this user have? */ @@ -859,6 +863,7 @@ enum cpu_idle_type { #define SD_BALANCE_WAKE 0x0010 /* Balance on wakeup */ #define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */ #define SD_SHARE_CPUPOWER 0x0080 /* Domain members share cpu power */ +#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 */ #define SD_ASYM_PACKING 0x0800 /* Place busy groups earlier in the domain */ @@ -866,7 +871,26 @@ enum cpu_idle_type { #define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */ #define SD_NUMA 0x4000 /* cross-node balancing */ -extern int __weak arch_sd_sibiling_asym_packing(void); +#ifdef CONFIG_SCHED_SMT +static inline const int cpu_smt_flags(void) +{ + return SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES; +} +#endif + +#ifdef CONFIG_SCHED_MC +static inline const int cpu_core_flags(void) +{ + return SD_SHARE_PKG_RESOURCES; +} +#endif + +#ifdef CONFIG_NUMA +static inline const int cpu_numa_flags(void) +{ + return SD_NUMA; +} +#endif struct sched_domain_attr { int relax_domain_level; @@ -974,6 +998,38 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms); bool cpus_share_cache(int this_cpu, int that_cpu); +typedef const struct cpumask *(*sched_domain_mask_f)(int cpu); +typedef const int (*sched_domain_flags_f)(void); + +#define SDTL_OVERLAP 0x01 + +struct sd_data { + struct sched_domain **__percpu sd; + struct sched_group **__percpu sg; + struct sched_group_power **__percpu sgp; +}; + +struct sched_domain_topology_level { + sched_domain_mask_f mask; + sched_domain_flags_f sd_flags; + int flags; + int numa_level; + struct sd_data data; +#ifdef CONFIG_SCHED_DEBUG + char *name; +#endif +}; + +extern struct sched_domain_topology_level *sched_domain_topology; + +extern void set_sched_topology(struct sched_domain_topology_level *tl); + +#ifdef CONFIG_SCHED_DEBUG +# define SD_INIT_NAME(type) .name = #type +#else +# define SD_INIT_NAME(type) +#endif + #else /* CONFIG_SMP */ struct sched_domain_attr; @@ -1077,6 +1133,7 @@ struct sched_entity { #endif #ifdef CONFIG_FAIR_GROUP_SCHED + int depth; struct sched_entity *parent; /* rq on which this entity is (to be) queued: */ struct cfs_rq *cfs_rq; @@ -1111,8 +1168,8 @@ struct sched_dl_entity { /* * Original scheduling parameters. Copied here from sched_attr - * during sched_setscheduler2(), they will remain the same until - * the next sched_setscheduler2(). + * during sched_setattr(), they will remain the same until + * the next sched_setattr(). */ u64 dl_runtime; /* maximum runtime for each instance */ u64 dl_deadline; /* relative deadline of each instance */ @@ -1141,9 +1198,12 @@ struct sched_dl_entity { * * @dl_boosted tells if we are boosted due to DI. If so we are * outside bandwidth enforcement mechanism (but only until we - * exit the critical section). + * exit the critical section); + * + * @dl_yielded tells if task gave up the cpu before consuming + * all its available runtime during the last job. */ - int dl_throttled, dl_new, dl_boosted; + int dl_throttled, dl_new, dl_boosted, dl_yielded; /* * Bandwidth enforcement timer. Each -deadline task has its @@ -1228,6 +1288,9 @@ struct task_struct { #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; #endif + /* per-thread vma caching */ + u32 vmacache_seqnum; + struct vm_area_struct *vmacache[VMACACHE_SIZE]; #if defined(SPLIT_RSS_COUNTING) struct task_rss_stat rss_stat; #endif @@ -1460,6 +1523,9 @@ struct task_struct { struct mutex perf_event_mutex; struct list_head perf_event_list; #endif +#ifdef CONFIG_DEBUG_PREEMPT + unsigned long preempt_disable_ip; +#endif #ifdef CONFIG_NUMA struct mempolicy *mempolicy; /* Protected by alloc_lock */ short il_next; @@ -1470,9 +1536,10 @@ struct task_struct { unsigned int numa_scan_period; unsigned int numa_scan_period_max; int numa_preferred_nid; - int numa_migrate_deferred; unsigned long numa_migrate_retry; u64 node_stamp; /* migration stamp */ + u64 last_task_numa_placement; + u64 last_sum_exec_runtime; struct callback_head numa_work; struct list_head numa_entry; @@ -1483,15 +1550,22 @@ struct task_struct { * Scheduling placement decisions are made based on the these counts. * The values remain static for the duration of a PTE scan */ - unsigned long *numa_faults; + unsigned long *numa_faults_memory; unsigned long total_numa_faults; /* * numa_faults_buffer records faults per node during the current - * scan window. When the scan completes, the counts in numa_faults - * decay and these values are copied. + * scan window. When the scan completes, the counts in + * numa_faults_memory decay and these values are copied. */ - unsigned long *numa_faults_buffer; + unsigned long *numa_faults_buffer_memory; + + /* + * Track the nodes the process was running on when a NUMA hinting + * fault was incurred. + */ + unsigned long *numa_faults_cpu; + unsigned long *numa_faults_buffer_cpu; /* * numa_faults_locality tracks if faults recorded during the last @@ -1596,8 +1670,8 @@ extern void task_numa_fault(int last_node, int node, int pages, int flags); extern pid_t task_numa_group_id(struct task_struct *p); extern void set_numabalancing_state(bool enabled); extern void task_numa_free(struct task_struct *p); - -extern unsigned int sysctl_numa_balancing_migrate_deferred; +extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page, + int src_nid, int dst_cpu); #else static inline void task_numa_fault(int last_node, int node, int pages, int flags) @@ -1613,6 +1687,11 @@ static inline void set_numabalancing_state(bool enabled) static inline void task_numa_free(struct task_struct *p) { } +static inline bool should_numa_migrate_memory(struct task_struct *p, + struct page *page, int src_nid, int dst_cpu) +{ + return true; +} #endif static inline struct pid *task_pid(struct task_struct *task) @@ -1688,6 +1767,24 @@ static inline pid_t task_tgid_vnr(struct task_struct *tsk) } +static inline int pid_alive(const struct task_struct *p); +static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns) +{ + pid_t pid = 0; + + rcu_read_lock(); + if (pid_alive(tsk)) + pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns); + rcu_read_unlock(); + + return pid; +} + +static inline pid_t task_ppid_nr(const struct task_struct *tsk) +{ + return task_ppid_nr_ns(tsk, &init_pid_ns); +} + static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { @@ -1727,7 +1824,7 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) * * Return: 1 if the process is alive. 0 otherwise. */ -static inline int pid_alive(struct task_struct *p) +static inline int pid_alive(const struct task_struct *p) { return p->pids[PIDTYPE_PID].pid != NULL; } @@ -1821,7 +1918,6 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, #define PF_SPREAD_SLAB 0x02000000 /* Spread some slab caches over cpuset */ #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ -#define PF_MEMPOLICY 0x10000000 /* Non-default NUMA mempolicy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ #define PF_SUSPEND_TASK 0x80000000 /* this thread called freeze_processes and should not be frozen */ @@ -2080,7 +2176,16 @@ static inline void sched_autogroup_exit(struct signal_struct *sig) { } extern bool yield_to(struct task_struct *p, bool preempt); extern void set_user_nice(struct task_struct *p, long nice); extern int task_prio(const struct task_struct *p); -extern int task_nice(const struct task_struct *p); +/** + * task_nice - return the nice value of a given task. + * @p: the task in question. + * + * Return: The nice value [ -20 ... 0 ... 19 ]. + */ +static inline int task_nice(const struct task_struct *p) +{ + return PRIO_TO_NICE((p)->static_prio); +} extern int can_nice(const struct task_struct *p, const int nice); extern int task_curr(const struct task_struct *p); extern int idle_cpu(int cpu); @@ -2309,9 +2414,6 @@ extern void flush_itimer_signals(void); extern void do_group_exit(int); -extern int allow_signal(int); -extern int disallow_signal(int); - extern int do_execve(struct filename *, const char __user * const __user *, const char __user * const __user *); @@ -2319,7 +2421,7 @@ extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, i struct task_struct *fork_idle(int); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); -extern void set_task_comm(struct task_struct *tsk, char *from); +extern void set_task_comm(struct task_struct *tsk, const char *from); extern char *get_task_comm(char *to, struct task_struct *tsk); #ifdef CONFIG_SMP @@ -2663,51 +2765,9 @@ static inline int spin_needbreak(spinlock_t *lock) /* * Idle thread specific functions to determine the need_resched - * polling state. We have two versions, one based on TS_POLLING in - * thread_info.status and one based on TIF_POLLING_NRFLAG in - * thread_info.flags + * polling state. */ -#ifdef TS_POLLING -static inline int tsk_is_polling(struct task_struct *p) -{ - return task_thread_info(p)->status & TS_POLLING; -} -static inline void __current_set_polling(void) -{ - current_thread_info()->status |= TS_POLLING; -} - -static inline bool __must_check current_set_polling_and_test(void) -{ - __current_set_polling(); - - /* - * Polling state must be visible before we test NEED_RESCHED, - * paired by resched_task() - */ - smp_mb(); - - return unlikely(tif_need_resched()); -} - -static inline void __current_clr_polling(void) -{ - current_thread_info()->status &= ~TS_POLLING; -} - -static inline bool __must_check current_clr_polling_and_test(void) -{ - __current_clr_polling(); - - /* - * Polling state must be visible before we test NEED_RESCHED, - * paired by resched_task() - */ - smp_mb(); - - return unlikely(tif_need_resched()); -} -#elif defined(TIF_POLLING_NRFLAG) +#ifdef TIF_POLLING_NRFLAG static inline int tsk_is_polling(struct task_struct *p) { return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG); @@ -2725,10 +2785,8 @@ static inline bool __must_check current_set_polling_and_test(void) /* * Polling state must be visible before we test NEED_RESCHED, * paired by resched_task() - * - * XXX: assumes set/clear bit are identical barrier wise. */ - smp_mb__after_clear_bit(); + smp_mb__after_atomic(); return unlikely(tif_need_resched()); } @@ -2746,7 +2804,7 @@ static inline bool __must_check current_clr_polling_and_test(void) * Polling state must be visible before we test NEED_RESCHED, * paired by resched_task() */ - smp_mb__after_clear_bit(); + smp_mb__after_atomic(); return unlikely(tif_need_resched()); } @@ -2899,7 +2957,7 @@ static inline void inc_syscw(struct task_struct *tsk) #define TASK_SIZE_OF(tsk) TASK_SIZE #endif -#ifdef CONFIG_MM_OWNER +#ifdef CONFIG_MEMCG extern void mm_update_next_owner(struct mm_struct *mm); extern void mm_init_owner(struct mm_struct *mm, struct task_struct *p); #else @@ -2910,7 +2968,7 @@ static inline void mm_update_next_owner(struct mm_struct *mm) static inline void mm_init_owner(struct mm_struct *mm, struct task_struct *p) { } -#endif /* CONFIG_MM_OWNER */ +#endif /* CONFIG_MEMCG */ static inline unsigned long task_rlimit(const struct task_struct *tsk, unsigned int limit) |