diff options
Diffstat (limited to 'include/linux/sched.h')
| -rw-r--r-- | include/linux/sched.h | 280 |
1 files changed, 235 insertions, 45 deletions
diff --git a/include/linux/sched.h b/include/linux/sched.h index 62c68e513e39..ad3ec9ec61f7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -262,20 +262,9 @@ extern char ___assert_task_state[1 - 2*!!( #define set_task_state(tsk, state_value) \ do { \ (tsk)->task_state_change = _THIS_IP_; \ - smp_store_mb((tsk)->state, (state_value)); \ + smp_store_mb((tsk)->state, (state_value)); \ } while (0) -/* - * set_current_state() includes a barrier so that the write of current->state - * is correctly serialised wrt the caller's subsequent test of whether to - * actually sleep: - * - * set_current_state(TASK_UNINTERRUPTIBLE); - * if (do_i_need_to_sleep()) - * schedule(); - * - * If the caller does not need such serialisation then use __set_current_state() - */ #define __set_current_state(state_value) \ do { \ current->task_state_change = _THIS_IP_; \ @@ -284,11 +273,19 @@ extern char ___assert_task_state[1 - 2*!!( #define set_current_state(state_value) \ do { \ current->task_state_change = _THIS_IP_; \ - smp_store_mb(current->state, (state_value)); \ + smp_store_mb(current->state, (state_value)); \ } while (0) #else +/* + * @tsk had better be current, or you get to keep the pieces. + * + * The only reason is that computing current can be more expensive than + * using a pointer that's already available. + * + * Therefore, see set_current_state(). + */ #define __set_task_state(tsk, state_value) \ do { (tsk)->state = (state_value); } while (0) #define set_task_state(tsk, state_value) \ @@ -299,11 +296,34 @@ extern char ___assert_task_state[1 - 2*!!( * is correctly serialised wrt the caller's subsequent test of whether to * actually sleep: * + * for (;;) { * set_current_state(TASK_UNINTERRUPTIBLE); - * if (do_i_need_to_sleep()) - * schedule(); + * if (!need_sleep) + * break; + * + * schedule(); + * } + * __set_current_state(TASK_RUNNING); + * + * If the caller does not need such serialisation (because, for instance, the + * condition test and condition change and wakeup are under the same lock) then + * use __set_current_state(). * - * If the caller does not need such serialisation then use __set_current_state() + * The above is typically ordered against the wakeup, which does: + * + * need_sleep = false; + * wake_up_state(p, TASK_UNINTERRUPTIBLE); + * + * Where wake_up_state() (and all other wakeup primitives) imply enough + * barriers to order the store of the variable against wakeup. + * + * Wakeup will do: if (@state & p->state) p->state = TASK_RUNNING, that is, + * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a + * TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING). + * + * This is obviously fine, since they both store the exact same value. + * + * Also see the comments of try_to_wake_up(). */ #define __set_current_state(state_value) \ do { current->state = (state_value); } while (0) @@ -448,6 +468,8 @@ static inline void io_schedule(void) io_schedule_timeout(MAX_SCHEDULE_TIMEOUT); } +void __noreturn do_task_dead(void); + struct nsproxy; struct user_namespace; @@ -518,12 +540,17 @@ static inline int get_dumpable(struct mm_struct *mm) /* leave room for more dump flags */ #define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */ #define MMF_VM_HUGEPAGE 17 /* set when VM_HUGEPAGE is set on vma */ -#define MMF_EXE_FILE_CHANGED 18 /* see prctl_set_mm_exe_file() */ +/* + * This one-shot flag is dropped due to necessity of changing exe once again + * on NFS restore + */ +//#define MMF_EXE_FILE_CHANGED 18 /* see prctl_set_mm_exe_file() */ #define MMF_HAS_UPROBES 19 /* has uprobes */ #define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */ -#define MMF_OOM_REAPED 21 /* mm has been already reaped */ -#define MMF_OOM_NOT_REAPABLE 22 /* mm couldn't be reaped */ +#define MMF_OOM_SKIP 21 /* mm is of no interest for the OOM killer */ +#define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ +#define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK) @@ -671,7 +698,6 @@ struct signal_struct { atomic_t sigcnt; atomic_t live; int nr_threads; - atomic_t oom_victims; /* # of TIF_MEDIE threads in this thread group */ struct list_head thread_head; wait_queue_head_t wait_chldexit; /* for wait4() */ @@ -804,6 +830,8 @@ struct signal_struct { short oom_score_adj; /* OOM kill score adjustment */ short oom_score_adj_min; /* OOM kill score adjustment min value. * Only settable by CAP_SYS_RESOURCE. */ + struct mm_struct *oom_mm; /* recorded mm when the thread group got + * killed by the oom killer */ struct mutex cred_guard_mutex; /* guard against foreign influences on * credential calculations @@ -826,6 +854,16 @@ struct signal_struct { #define SIGNAL_UNKILLABLE 0x00000040 /* for init: ignore fatal signals */ +#define SIGNAL_STOP_MASK (SIGNAL_CLD_MASK | SIGNAL_STOP_STOPPED | \ + SIGNAL_STOP_CONTINUED) + +static inline void signal_set_stop_flags(struct signal_struct *sig, + unsigned int flags) +{ + WARN_ON(sig->flags & (SIGNAL_GROUP_EXIT|SIGNAL_GROUP_COREDUMP)); + sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags; +} + /* If true, all threads except ->group_exit_task have pending SIGKILL */ static inline int signal_group_exit(const struct signal_struct *sig) { @@ -985,7 +1023,7 @@ enum cpu_idle_type { * already in a wake queue, the wakeup will happen soon and the second * waker can just skip it. * - * The WAKE_Q macro declares and initializes the list head. + * The DEFINE_WAKE_Q macro declares and initializes the list head. * wake_up_q() does NOT reinitialize the list; it's expected to be * called near the end of a function, where the fact that the queue is * not used again will be easy to see by inspection. @@ -1005,7 +1043,7 @@ struct wake_q_head { #define WAKE_Q_TAIL ((struct wake_q_node *) 0x01) -#define WAKE_Q(name) \ +#define DEFINE_WAKE_Q(name) \ struct wake_q_head name = { WAKE_Q_TAIL, &name.first } extern void wake_q_add(struct wake_q_head *head, @@ -1022,7 +1060,8 @@ 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 */ @@ -1052,6 +1091,8 @@ static inline int cpu_numa_flags(void) } #endif +extern int arch_asym_cpu_priority(int cpu); + struct sched_domain_attr { int relax_domain_level; }; @@ -1064,6 +1105,12 @@ extern int sched_domain_level_max; struct sched_group; +struct sched_domain_shared { + atomic_t ref; + atomic_t nr_busy_cpus; + int has_idle_cores; +}; + struct sched_domain { /* These fields must be setup */ struct sched_domain *parent; /* top domain must be null terminated */ @@ -1094,6 +1141,8 @@ struct sched_domain { u64 max_newidle_lb_cost; unsigned long next_decay_max_lb_cost; + u64 avg_scan_cost; /* select_idle_sibling */ + #ifdef CONFIG_SCHEDSTATS /* load_balance() stats */ unsigned int lb_count[CPU_MAX_IDLE_TYPES]; @@ -1132,6 +1181,7 @@ struct sched_domain { void *private; /* used during construction */ struct rcu_head rcu; /* used during destruction */ }; + struct sched_domain_shared *shared; unsigned int span_weight; /* @@ -1165,6 +1215,7 @@ typedef int (*sched_domain_flags_f)(void); struct sd_data { struct sched_domain **__percpu sd; + struct sched_domain_shared **__percpu sds; struct sched_group **__percpu sg; struct sched_group_capacity **__percpu sgc; }; @@ -1458,6 +1509,13 @@ 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; @@ -1467,6 +1525,9 @@ 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; @@ -1602,7 +1663,10 @@ struct task_struct { int __user *set_child_tid; /* CLONE_CHILD_SETTID */ int __user *clear_child_tid; /* CLONE_CHILD_CLEARTID */ - cputime_t utime, stime, utimescaled, stimescaled; + cputime_t utime, stime; +#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME + cputime_t utimescaled, stimescaled; +#endif cputime_t gtime; struct prev_cputime prev_cputime; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN @@ -1631,6 +1695,7 @@ struct task_struct { struct list_head cpu_timers[3]; /* process credentials */ + const struct cred __rcu *ptracer_cred; /* Tracer's credentials at attach */ const struct cred __rcu *real_cred; /* objective and real subjective task * credentials (COW) */ const struct cred __rcu *cred; /* effective (overridable) subjective task @@ -1766,6 +1831,9 @@ struct task_struct { /* cg_list protected by css_set_lock and tsk->alloc_lock */ struct list_head cg_list; #endif +#ifdef CONFIG_INTEL_RDT_A + int closid; +#endif #ifdef CONFIG_FUTEX struct robust_list_head __user *robust_list; #ifdef CONFIG_COMPAT @@ -1923,6 +1991,13 @@ struct task_struct { #ifdef CONFIG_MMU struct task_struct *oom_reaper_list; #endif +#ifdef CONFIG_VMAP_STACK + struct vm_struct *stack_vm_area; +#endif +#ifdef CONFIG_THREAD_INFO_IN_TASK + /* A live task holds one reference. */ + atomic_t stack_refcount; +#endif /* CPU-specific state of this task */ struct thread_struct thread; /* @@ -1939,6 +2014,18 @@ extern int arch_task_struct_size __read_mostly; # define arch_task_struct_size (sizeof(struct task_struct)) #endif +#ifdef CONFIG_VMAP_STACK +static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) +{ + return t->stack_vm_area; +} +#else +static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) +{ + return NULL; +} +#endif + /* Future-safe accessor for struct task_struct's cpus_allowed. */ #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed) @@ -2176,40 +2263,45 @@ struct task_struct *try_get_task_struct(struct task_struct **ptask); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN extern void task_cputime(struct task_struct *t, cputime_t *utime, cputime_t *stime); -extern void task_cputime_scaled(struct task_struct *t, - cputime_t *utimescaled, cputime_t *stimescaled); extern cputime_t task_gtime(struct task_struct *t); #else static inline void task_cputime(struct task_struct *t, cputime_t *utime, cputime_t *stime) { - if (utime) - *utime = t->utime; - if (stime) - *stime = t->stime; + *utime = t->utime; + *stime = t->stime; +} + +static inline cputime_t task_gtime(struct task_struct *t) +{ + return t->gtime; } +#endif +#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME static inline void task_cputime_scaled(struct task_struct *t, cputime_t *utimescaled, cputime_t *stimescaled) { - if (utimescaled) - *utimescaled = t->utimescaled; - if (stimescaled) - *stimescaled = t->stimescaled; + *utimescaled = t->utimescaled; + *stimescaled = t->stimescaled; } - -static inline cputime_t task_gtime(struct task_struct *t) +#else +static inline void task_cputime_scaled(struct task_struct *t, + cputime_t *utimescaled, + cputime_t *stimescaled) { - return t->gtime; + task_cputime(t, utimescaled, stimescaled); } #endif + extern void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st); extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st); /* * Per process flags */ +#define PF_IDLE 0x00000002 /* I am an IDLE thread */ #define PF_EXITING 0x00000004 /* getting shut down */ #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ #define PF_VCPU 0x00000010 /* I'm a virtual CPU */ @@ -2400,6 +2492,10 @@ static inline void calc_load_enter_idle(void) { } static inline void calc_load_exit_idle(void) { } #endif /* CONFIG_NO_HZ_COMMON */ +#ifndef cpu_relax_yield +#define cpu_relax_yield() cpu_relax() +#endif + /* * Do not use outside of architecture code which knows its limitations. * @@ -2523,6 +2619,7 @@ extern void sched_autogroup_create_attach(struct task_struct *p); extern void sched_autogroup_detach(struct task_struct *p); extern void sched_autogroup_fork(struct signal_struct *sig); extern void sched_autogroup_exit(struct signal_struct *sig); +extern void sched_autogroup_exit_task(struct task_struct *p); #ifdef CONFIG_PROC_FS extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m); extern int proc_sched_autogroup_set_nice(struct task_struct *p, int nice); @@ -2532,6 +2629,7 @@ static inline void sched_autogroup_create_attach(struct task_struct *p) { } static inline void sched_autogroup_detach(struct task_struct *p) { } static inline void sched_autogroup_fork(struct signal_struct *sig) { } static inline void sched_autogroup_exit(struct signal_struct *sig) { } +static inline void sched_autogroup_exit_task(struct task_struct *p) { } #endif extern int yield_to(struct task_struct *p, bool preempt); @@ -2565,15 +2663,17 @@ extern struct task_struct *idle_task(int cpu); */ static inline bool is_idle_task(const struct task_struct *p) { - return p->pid == 0; + return !!(p->flags & PF_IDLE); } extern struct task_struct *curr_task(int cpu); -extern void set_curr_task(int cpu, struct task_struct *p); +extern void ia64_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)]; }; @@ -2832,6 +2932,20 @@ static inline void mmdrop(struct mm_struct *mm) __mmdrop(mm); } +static inline void mmdrop_async_fn(struct work_struct *work) +{ + struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work); + __mmdrop(mm); +} + +static inline void mmdrop_async(struct mm_struct *mm) +{ + if (unlikely(atomic_dec_and_test(&mm->mm_count))) { + INIT_WORK(&mm->async_put_work, mmdrop_async_fn); + schedule_work(&mm->async_put_work); + } +} + static inline bool mmget_not_zero(struct mm_struct *mm) { return atomic_inc_not_zero(&mm->mm_users); @@ -3061,10 +3175,34 @@ 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) { @@ -3091,6 +3229,24 @@ static inline unsigned long *end_of_stack(struct task_struct *p) } #endif + +#ifdef CONFIG_THREAD_INFO_IN_TASK +static inline void *try_get_task_stack(struct task_struct *tsk) +{ + return atomic_inc_not_zero(&tsk->stack_refcount) ? + task_stack_page(tsk) : NULL; +} + +extern void put_task_stack(struct task_struct *tsk); +#else +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) {} +#endif + #define task_stack_end_corrupted(task) \ (*(end_of_stack(task)) != STACK_END_MAGIC) @@ -3206,7 +3362,11 @@ static inline int signal_pending_state(long state, struct task_struct *p) * cond_resched_lock() will drop the spinlock before scheduling, * cond_resched_softirq() will enable bhs before scheduling. */ +#ifndef CONFIG_PREEMPT extern int _cond_resched(void); +#else +static inline int _cond_resched(void) { return 0; } +#endif #define cond_resched() ({ \ ___might_sleep(__FILE__, __LINE__, 0); \ @@ -3236,6 +3396,15 @@ static inline void cond_resched_rcu(void) #endif } +static inline unsigned long get_preempt_disable_ip(struct task_struct *p) +{ +#ifdef CONFIG_DEBUG_PREEMPT + return p->preempt_disable_ip; +#else + return 0; +#endif +} + /* * Does a critical section need to be broken due to another * task waiting?: (technically does not depend on CONFIG_PREEMPT, @@ -3364,7 +3533,11 @@ 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) @@ -3387,6 +3560,18 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) #endif /* CONFIG_SMP */ +/* + * In order to reduce various lock holder preemption latencies provide an + * interface to see if a vCPU is currently running or not. + * + * This allows us to terminate optimistic spin loops and block, analogous to + * the native optimistic spin heuristic of testing if the lock owner task is + * running or not. + */ +#ifndef vcpu_is_preempted +# define vcpu_is_preempted(cpu) false +#endif + extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask); extern long sched_getaffinity(pid_t pid, struct cpumask *mask); @@ -3469,15 +3654,20 @@ 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) + +#define SCHED_CPUFREQ_RT_DL (SCHED_CPUFREQ_RT | SCHED_CPUFREQ_DL) + #ifdef CONFIG_CPU_FREQ struct update_util_data { - void (*func)(struct update_util_data *data, - u64 time, unsigned long util, unsigned long max); + 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 long util, unsigned long max)); + void (*func)(struct update_util_data *data, u64 time, + unsigned int flags)); void cpufreq_remove_update_util_hook(int cpu); #endif /* CONFIG_CPU_FREQ */ |