diff options
Diffstat (limited to 'include/linux/sched.h')
-rw-r--r-- | include/linux/sched.h | 707 |
1 files changed, 434 insertions, 273 deletions
diff --git a/include/linux/sched.h b/include/linux/sched.h index 4d0754269884..abc527aa8550 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -38,6 +38,8 @@ #define SCHED_BATCH 3 /* SCHED_ISO: reserved but not implemented yet */ #define SCHED_IDLE 5 +/* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */ +#define SCHED_RESET_ON_FORK 0x40000000 #ifdef __KERNEL__ @@ -68,7 +70,6 @@ struct sched_param { #include <linux/smp.h> #include <linux/sem.h> #include <linux/signal.h> -#include <linux/path.h> #include <linux/compiler.h> #include <linux/completion.h> #include <linux/pid.h> @@ -86,7 +87,6 @@ struct sched_param { #include <linux/timer.h> #include <linux/hrtimer.h> #include <linux/task_io_accounting.h> -#include <linux/kobject.h> #include <linux/latencytop.h> #include <linux/cred.h> @@ -95,10 +95,9 @@ struct sched_param { struct exec_domain; struct futex_pi_state; struct robust_list_head; -struct bio; +struct bio_list; struct fs_struct; -struct bts_context; -struct perf_counter_context; +struct perf_event_context; /* * List of flags we want to share for kernel threads, @@ -138,8 +137,11 @@ extern int nr_processes(void); extern unsigned long nr_running(void); extern unsigned long nr_uninterruptible(void); extern unsigned long nr_iowait(void); -extern void calc_global_load(void); -extern u64 cpu_nr_migrations(int cpu); +extern unsigned long nr_iowait_cpu(int cpu); +extern unsigned long this_cpu_load(void); + + +extern void calc_global_load(unsigned long ticks); extern unsigned long get_parent_ip(unsigned long addr); @@ -165,8 +167,6 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) } #endif -extern unsigned long long time_sync_thresh; - /* * Task state bitmask. NOTE! These bits are also * encoded in fs/proc/array.c: get_task_state(). @@ -188,6 +188,13 @@ extern unsigned long long time_sync_thresh; /* in tsk->state again */ #define TASK_DEAD 64 #define TASK_WAKEKILL 128 +#define TASK_WAKING 256 +#define TASK_STATE_MAX 512 + +#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKW" + +extern char ___assert_task_state[1 - 2*!!( + sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)]; /* Convenience macros for the sake of set_task_state */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) @@ -205,11 +212,12 @@ extern unsigned long long time_sync_thresh; #define task_is_traced(task) ((task->state & __TASK_TRACED) != 0) #define task_is_stopped(task) ((task->state & __TASK_STOPPED) != 0) +#define task_is_dead(task) ((task)->exit_state != 0) #define task_is_stopped_or_traced(task) \ ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0) #define task_contributes_to_load(task) \ ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \ - (task->flags & PF_FROZEN) == 0) + (task->flags & PF_FREEZING) == 0) #define __set_task_state(tsk, state_value) \ do { (tsk)->state = (state_value); } while (0) @@ -248,24 +256,24 @@ extern spinlock_t mmlist_lock; struct task_struct; +#ifdef CONFIG_PROVE_RCU +extern int lockdep_tasklist_lock_is_held(void); +#endif /* #ifdef CONFIG_PROVE_RCU */ + extern void sched_init(void); extern void sched_init_smp(void); extern asmlinkage void schedule_tail(struct task_struct *prev); extern void init_idle(struct task_struct *idle, int cpu); extern void init_idle_bootup_task(struct task_struct *idle); -extern int runqueue_is_locked(void); -extern void task_rq_unlock_wait(struct task_struct *p); +extern int runqueue_is_locked(int cpu); extern cpumask_var_t nohz_cpu_mask; #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ) -extern int select_nohz_load_balancer(int cpu); -extern int get_nohz_load_balancer(void); +extern void select_nohz_load_balancer(int stop_tick); +extern int get_nohz_timer_target(void); #else -static inline int select_nohz_load_balancer(int cpu) -{ - return 0; -} +static inline void select_nohz_load_balancer(int stop_tick) { } #endif /* @@ -297,25 +305,29 @@ extern void scheduler_tick(void); extern void sched_show_task(struct task_struct *p); -#ifdef CONFIG_DETECT_SOFTLOCKUP -extern void softlockup_tick(void); +#ifdef CONFIG_LOCKUP_DETECTOR extern void touch_softlockup_watchdog(void); +extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); -extern int proc_dosoftlockup_thresh(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, - size_t *lenp, loff_t *ppos); +extern int proc_dowatchdog_thresh(struct ctl_table *table, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos); extern unsigned int softlockup_panic; extern int softlockup_thresh; +void lockup_detector_init(void); #else -static inline void softlockup_tick(void) +static inline void touch_softlockup_watchdog(void) { } -static inline void touch_softlockup_watchdog(void) +static inline void touch_softlockup_watchdog_sync(void) { } static inline void touch_all_softlockup_watchdogs(void) { } +static inline void lockup_detector_init(void) +{ +} #endif #ifdef CONFIG_DETECT_HUNG_TASK @@ -324,8 +336,11 @@ extern unsigned long sysctl_hung_task_check_count; extern unsigned long sysctl_hung_task_timeout_secs; extern unsigned long sysctl_hung_task_warnings; extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos); +#else +/* Avoid need for ifdefs elsewhere in the code */ +enum { sysctl_hung_task_timeout_secs = 0 }; #endif /* Attach to any functions which should be ignored in wchan output. */ @@ -342,20 +357,33 @@ extern signed long schedule_timeout(signed long timeout); extern signed long schedule_timeout_interruptible(signed long timeout); extern signed long schedule_timeout_killable(signed long timeout); extern signed long schedule_timeout_uninterruptible(signed long timeout); -asmlinkage void __schedule(void); asmlinkage void schedule(void); extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner); struct nsproxy; struct user_namespace; -/* Maximum number of active map areas.. This is a random (large) number */ -#define DEFAULT_MAX_MAP_COUNT 65536 +/* + * Default maximum number of active map areas, this limits the number of vmas + * per mm struct. Users can overwrite this number by sysctl but there is a + * problem. + * + * When a program's coredump is generated as ELF format, a section is created + * per a vma. In ELF, the number of sections is represented in unsigned short. + * This means the number of sections should be smaller than 65535 at coredump. + * Because the kernel adds some informative sections to a image of program at + * generating coredump, we need some margin. The number of extra sections is + * 1-3 now and depends on arch. We use "5" as safe margin, here. + */ +#define MAPCOUNT_ELF_CORE_MARGIN (5) +#define DEFAULT_MAX_MAP_COUNT (USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN) extern int sysctl_max_map_count; #include <linux/aio.h> +#ifdef CONFIG_MMU +extern void arch_pick_mmap_layout(struct mm_struct *mm); extern unsigned long arch_get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); @@ -365,52 +393,10 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long flags); extern void arch_unmap_area(struct mm_struct *, unsigned long); extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long); +#else +static inline void arch_pick_mmap_layout(struct mm_struct *mm) {} +#endif -#if USE_SPLIT_PTLOCKS -/* - * The mm counters are not protected by its page_table_lock, - * so must be incremented atomically. - */ -#define set_mm_counter(mm, member, value) atomic_long_set(&(mm)->_##member, value) -#define get_mm_counter(mm, member) ((unsigned long)atomic_long_read(&(mm)->_##member)) -#define add_mm_counter(mm, member, value) atomic_long_add(value, &(mm)->_##member) -#define inc_mm_counter(mm, member) atomic_long_inc(&(mm)->_##member) -#define dec_mm_counter(mm, member) atomic_long_dec(&(mm)->_##member) - -#else /* !USE_SPLIT_PTLOCKS */ -/* - * The mm counters are protected by its page_table_lock, - * so can be incremented directly. - */ -#define set_mm_counter(mm, member, value) (mm)->_##member = (value) -#define get_mm_counter(mm, member) ((mm)->_##member) -#define add_mm_counter(mm, member, value) (mm)->_##member += (value) -#define inc_mm_counter(mm, member) (mm)->_##member++ -#define dec_mm_counter(mm, member) (mm)->_##member-- - -#endif /* !USE_SPLIT_PTLOCKS */ - -#define get_mm_rss(mm) \ - (get_mm_counter(mm, file_rss) + get_mm_counter(mm, anon_rss)) -#define update_hiwater_rss(mm) do { \ - unsigned long _rss = get_mm_rss(mm); \ - if ((mm)->hiwater_rss < _rss) \ - (mm)->hiwater_rss = _rss; \ -} while (0) -#define update_hiwater_vm(mm) do { \ - if ((mm)->hiwater_vm < (mm)->total_vm) \ - (mm)->hiwater_vm = (mm)->total_vm; \ -} while (0) - -static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm) -{ - return max(mm->hiwater_rss, get_mm_rss(mm)); -} - -static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm) -{ - return max(mm->hiwater_vm, mm->total_vm); -} extern void set_dumpable(struct mm_struct *mm, int value); extern int get_dumpable(struct mm_struct *mm); @@ -419,7 +405,9 @@ extern int get_dumpable(struct mm_struct *mm); /* dumpable bits */ #define MMF_DUMPABLE 0 /* core dump is permitted */ #define MMF_DUMP_SECURELY 1 /* core file is readable only by root */ + #define MMF_DUMPABLE_BITS 2 +#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1) /* coredump filter bits */ #define MMF_DUMP_ANON_PRIVATE 2 @@ -429,6 +417,7 @@ extern int get_dumpable(struct mm_struct *mm); #define MMF_DUMP_ELF_HEADERS 6 #define MMF_DUMP_HUGETLB_PRIVATE 7 #define MMF_DUMP_HUGETLB_SHARED 8 + #define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS #define MMF_DUMP_FILTER_BITS 7 #define MMF_DUMP_FILTER_MASK \ @@ -442,6 +431,10 @@ extern int get_dumpable(struct mm_struct *mm); #else # define MMF_DUMP_MASK_DEFAULT_ELF 0 #endif + /* leave room for more dump flags */ +#define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */ + +#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK) struct sighand_struct { atomic_t count; @@ -458,6 +451,13 @@ struct pacct_struct { unsigned long ac_minflt, ac_majflt; }; +struct cpu_itimer { + cputime_t expires; + cputime_t incr; + u32 error; + u32 incr_error; +}; + /** * struct task_cputime - collected CPU time counts * @utime: time spent in user mode, in &cputime_t units @@ -486,6 +486,15 @@ struct task_cputime { .sum_exec_runtime = 0, \ } +/* + * Disable preemption until the scheduler is running. + * Reset by start_kernel()->sched_init()->init_idle(). + * + * We include PREEMPT_ACTIVE to avoid cond_resched() from working + * before the scheduler is active -- see should_resched(). + */ +#define INIT_PREEMPT_COUNT (1 + PREEMPT_ACTIVE) + /** * struct thread_group_cputimer - thread group interval timer counts * @cputime: thread group interval timers. @@ -502,6 +511,8 @@ struct thread_group_cputimer { spinlock_t lock; }; +struct autogroup; + /* * NOTE! "signal_struct" does not have it's own * locking, because a shared signal_struct always @@ -510,8 +521,9 @@ struct thread_group_cputimer { * the locking of signal_struct. */ struct signal_struct { - atomic_t count; + atomic_t sigcnt; atomic_t live; + int nr_threads; wait_queue_head_t wait_chldexit; /* for wait4() */ @@ -543,9 +555,12 @@ struct signal_struct { struct pid *leader_pid; ktime_t it_real_incr; - /* ITIMER_PROF and ITIMER_VIRTUAL timers for the process */ - cputime_t it_prof_expires, it_virt_expires; - cputime_t it_prof_incr, it_virt_incr; + /* + * ITIMER_PROF and ITIMER_VIRTUAL timers for the process, we use + * CPUCLOCK_PROF and CPUCLOCK_VIRT for indexing array as these + * values are defined to 0 and 1 respectively + */ + struct cpu_itimer it[2]; /* * Thread group totals for process CPU timers. @@ -565,6 +580,9 @@ struct signal_struct { struct tty_struct *tty; /* NULL if no tty */ +#ifdef CONFIG_SCHED_AUTOGROUP + struct autogroup *autogroup; +#endif /* * Cumulative resource counters for dead threads in the group, * and for reaped dead child processes forked by this group. @@ -574,9 +592,13 @@ struct signal_struct { cputime_t utime, stime, cutime, cstime; cputime_t gtime; cputime_t cgtime; +#ifndef CONFIG_VIRT_CPU_ACCOUNTING + cputime_t prev_utime, prev_stime; +#endif unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; unsigned long inblock, oublock, cinblock, coublock; + unsigned long maxrss, cmaxrss; struct task_io_accounting ioac; /* @@ -608,6 +630,13 @@ struct signal_struct { unsigned audit_tty; struct tty_audit_buf *tty_audit_buf; #endif + + int oom_adj; /* OOM kill score adjustment (bit shift) */ + int oom_score_adj; /* OOM kill score adjustment */ + + struct mutex cred_guard_mutex; /* guard against foreign influences on + * credential calculations + * (notably. ptrace) */ }; /* Context switch must be unlocked if interrupts are to be enabled */ @@ -650,6 +679,9 @@ struct user_struct { atomic_t inotify_watches; /* How many inotify watches does this user have? */ atomic_t inotify_devs; /* How many inotify devs does this user have opened? */ #endif +#ifdef CONFIG_FANOTIFY + atomic_t fanotify_listeners; +#endif #ifdef CONFIG_EPOLL atomic_t epoll_watches; /* The number of file descriptors currently watched */ #endif @@ -669,15 +701,7 @@ struct user_struct { uid_t uid; struct user_namespace *user_ns; -#ifdef CONFIG_USER_SCHED - struct task_group *tg; -#ifdef CONFIG_SYSFS - struct kobject kobj; - struct delayed_work work; -#endif -#endif - -#ifdef CONFIG_PERF_COUNTERS +#ifdef CONFIG_PERF_EVENTS atomic_long_t locked_vm; #endif }; @@ -775,18 +799,19 @@ enum cpu_idle_type { #define SCHED_LOAD_SCALE_FUZZ SCHED_LOAD_SCALE #ifdef CONFIG_SMP -#define SD_LOAD_BALANCE 1 /* Do load balancing on this domain. */ -#define SD_BALANCE_NEWIDLE 2 /* Balance when about to become idle */ -#define SD_BALANCE_EXEC 4 /* Balance on exec */ -#define SD_BALANCE_FORK 8 /* Balance on fork, clone */ -#define SD_WAKE_IDLE 16 /* Wake to idle CPU on task wakeup */ -#define SD_WAKE_AFFINE 32 /* Wake task to waking CPU */ -#define SD_WAKE_BALANCE 64 /* Perform balancing at task wakeup */ -#define SD_SHARE_CPUPOWER 128 /* Domain members share cpu power */ -#define SD_POWERSAVINGS_BALANCE 256 /* Balance for power savings */ -#define SD_SHARE_PKG_RESOURCES 512 /* Domain members share cpu pkg resources */ -#define SD_SERIALIZE 1024 /* Only a single load balancing instance */ -#define SD_WAKE_IDLE_FAR 2048 /* Gain latency sacrificing cache hit */ +#define SD_LOAD_BALANCE 0x0001 /* Do load balancing on this domain. */ +#define SD_BALANCE_NEWIDLE 0x0002 /* Balance when about to become idle */ +#define SD_BALANCE_EXEC 0x0004 /* Balance on exec */ +#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_PREFER_LOCAL 0x0040 /* Prefer to keep tasks local to this domain */ +#define SD_SHARE_CPUPOWER 0x0080 /* Domain members share cpu power */ +#define SD_POWERSAVINGS_BALANCE 0x0100 /* Balance for power savings */ +#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 */ +#define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */ enum powersavings_balance_level { POWERSAVINGS_BALANCE_NONE = 0, /* No power saving load balance */ @@ -806,6 +831,9 @@ static inline int sd_balance_for_mc_power(void) if (sched_smt_power_savings) return SD_POWERSAVINGS_BALANCE; + if (!sched_mc_power_savings) + return SD_PREFER_SIBLING; + return 0; } @@ -814,9 +842,11 @@ static inline int sd_balance_for_package_power(void) if (sched_mc_power_savings | sched_smt_power_savings) return SD_POWERSAVINGS_BALANCE; - return 0; + return SD_PREFER_SIBLING; } +extern int __weak arch_sd_sibiling_asym_packing(void); + /* * Optimise SD flags for power savings: * SD_BALANCE_NEWIDLE helps agressive task consolidation and power savings. @@ -836,15 +866,10 @@ struct sched_group { /* * CPU power of this group, SCHED_LOAD_SCALE being max power for a - * single CPU. This is read only (except for setup, hotplug CPU). - * Note : Never change cpu_power without recompute its reciprocal - */ - unsigned int __cpu_power; - /* - * reciprocal value of cpu_power to avoid expensive divides - * (see include/linux/reciprocal_div.h) + * single CPU. */ - u32 reciprocal_cpu_power; + unsigned int cpu_power, cpu_power_orig; + unsigned int group_weight; /* * The CPUs this group covers. @@ -868,6 +893,7 @@ enum sched_domain_level { SD_LV_NONE = 0, SD_LV_SIBLING, SD_LV_MC, + SD_LV_BOOK, SD_LV_CPU, SD_LV_NODE, SD_LV_ALLNODES, @@ -897,6 +923,7 @@ struct sched_domain { unsigned int newidle_idx; unsigned int wake_idx; unsigned int forkexec_idx; + unsigned int smt_gain; int flags; /* See SD_* */ enum sched_domain_level level; @@ -942,6 +969,7 @@ struct sched_domain { char *name; #endif + unsigned int span_weight; /* * Span of all CPUs in this domain. * @@ -960,9 +988,13 @@ static inline struct cpumask *sched_domain_span(struct sched_domain *sd) return to_cpumask(sd->span); } -extern void partition_sched_domains(int ndoms_new, struct cpumask *doms_new, +extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new); +/* Allocate an array of sched domains, for partition_sched_domains(). */ +cpumask_var_t *alloc_sched_domains(unsigned int ndoms); +void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms); + /* Test a flag in parent sched domain */ static inline int test_sd_parent(struct sched_domain *sd, int flag) { @@ -972,17 +1004,21 @@ static inline int test_sd_parent(struct sched_domain *sd, int flag) return 0; } +unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu); +unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu); + #else /* CONFIG_SMP */ struct sched_domain_attr; static inline void -partition_sched_domains(int ndoms_new, struct cpumask *doms_new, +partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new) { } #endif /* !CONFIG_SMP */ + struct io_context; /* See blkdev.h */ @@ -1000,33 +1036,38 @@ struct uts_namespace; struct rq; struct sched_domain; +/* + * wake flags + */ +#define WF_SYNC 0x01 /* waker goes to sleep after wakup */ +#define WF_FORK 0x02 /* child wakeup after fork */ + +#define ENQUEUE_WAKEUP 1 +#define ENQUEUE_WAKING 2 +#define ENQUEUE_HEAD 4 + +#define DEQUEUE_SLEEP 1 + struct sched_class { const struct sched_class *next; - void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup); - void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep); + 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); - void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int sync); + void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags); struct task_struct * (*pick_next_task) (struct rq *rq); void (*put_prev_task) (struct rq *rq, struct task_struct *p); #ifdef CONFIG_SMP - int (*select_task_rq)(struct task_struct *p, int sync); - - unsigned long (*load_balance) (struct rq *this_rq, int this_cpu, - struct rq *busiest, unsigned long max_load_move, - struct sched_domain *sd, enum cpu_idle_type idle, - int *all_pinned, int *this_best_prio); + int (*select_task_rq)(struct rq *rq, struct task_struct *p, + int sd_flag, int flags); - int (*move_one_task) (struct rq *this_rq, int this_cpu, - struct rq *busiest, struct sched_domain *sd, - enum cpu_idle_type idle); void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); - int (*needs_post_schedule) (struct rq *this_rq); void (*post_schedule) (struct rq *this_rq); - void (*task_wake_up) (struct rq *this_rq, struct task_struct *task); + void (*task_waking) (struct rq *this_rq, struct task_struct *task); + void (*task_woken) (struct rq *this_rq, struct task_struct *task); void (*set_cpus_allowed)(struct task_struct *p, const struct cpumask *newmask); @@ -1037,7 +1078,7 @@ struct sched_class { void (*set_curr_task) (struct rq *rq); void (*task_tick) (struct rq *rq, struct task_struct *p, int queued); - void (*task_new) (struct rq *rq, struct task_struct *p); + void (*task_fork) (struct task_struct *p); void (*switched_from) (struct rq *this_rq, struct task_struct *task, int running); @@ -1046,8 +1087,11 @@ struct sched_class { void (*prio_changed) (struct rq *this_rq, struct task_struct *task, int oldprio, int running); + unsigned int (*get_rr_interval) (struct rq *rq, + struct task_struct *task); + #ifdef CONFIG_FAIR_GROUP_SCHED - void (*moved_group) (struct task_struct *p); + void (*task_move_group) (struct task_struct *p, int on_rq); #endif }; @@ -1055,40 +1099,14 @@ struct load_weight { unsigned long weight, inv_weight; }; -/* - * CFS stats for a schedulable entity (task, task-group etc) - * - * Current field usage histogram: - * - * 4 se->block_start - * 4 se->run_node - * 4 se->sleep_start - * 6 se->load.weight - */ -struct sched_entity { - struct load_weight load; /* for load-balancing */ - struct rb_node run_node; - struct list_head group_node; - unsigned int on_rq; - - u64 exec_start; - u64 sum_exec_runtime; - u64 vruntime; - u64 prev_sum_exec_runtime; - - u64 last_wakeup; - u64 avg_overlap; - - u64 nr_migrations; - - u64 start_runtime; - u64 avg_wakeup; - #ifdef CONFIG_SCHEDSTATS +struct sched_statistics { u64 wait_start; u64 wait_max; u64 wait_count; u64 wait_sum; + u64 iowait_count; + u64 iowait_sum; u64 sleep_start; u64 sleep_max; @@ -1104,7 +1122,6 @@ struct sched_entity { u64 nr_failed_migrations_running; u64 nr_failed_migrations_hot; u64 nr_forced_migrations; - u64 nr_forced2_migrations; u64 nr_wakeups; u64 nr_wakeups_sync; @@ -1115,6 +1132,24 @@ struct sched_entity { u64 nr_wakeups_affine_attempts; u64 nr_wakeups_passive; u64 nr_wakeups_idle; +}; +#endif + +struct sched_entity { + struct load_weight load; /* for load-balancing */ + struct rb_node run_node; + struct list_head group_node; + unsigned int on_rq; + + u64 exec_start; + u64 sum_exec_runtime; + u64 vruntime; + u64 prev_sum_exec_runtime; + + u64 nr_migrations; + +#ifdef CONFIG_SCHEDSTATS + struct sched_statistics statistics; #endif #ifdef CONFIG_FAIR_GROUP_SCHED @@ -1142,6 +1177,15 @@ struct sched_rt_entity { #endif }; +struct rcu_node; + +enum perf_event_task_context { + perf_invalid_context = -1, + perf_hw_context = 0, + perf_sw_context, + perf_nr_task_contexts, +}; + struct task_struct { volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */ void *stack; @@ -1186,20 +1230,30 @@ struct task_struct { #ifdef CONFIG_PREEMPT_RCU int rcu_read_lock_nesting; - int rcu_flipctr_idx; + char rcu_read_unlock_special; + struct list_head rcu_node_entry; #endif /* #ifdef CONFIG_PREEMPT_RCU */ +#ifdef CONFIG_TREE_PREEMPT_RCU + struct rcu_node *rcu_blocked_node; +#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ +#ifdef CONFIG_RCU_BOOST + struct rt_mutex *rcu_boost_mutex; +#endif /* #ifdef CONFIG_RCU_BOOST */ #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) struct sched_info sched_info; #endif struct list_head tasks; +#ifdef CONFIG_SMP struct plist_node pushable_tasks; +#endif struct mm_struct *mm, *active_mm; - +#if defined(SPLIT_RSS_COUNTING) + struct task_rss_stat rss_stat; +#endif /* task state */ - struct linux_binfmt *binfmt; int exit_state; int exit_code, exit_signal; int pdeath_signal; /* The signal sent when the parent dies */ @@ -1208,11 +1262,19 @@ struct task_struct { unsigned did_exec:1; unsigned in_execve:1; /* Tell the LSMs that the process is doing an * execve */ + unsigned in_iowait:1; + + + /* Revert to default priority/policy when forking */ + unsigned sched_reset_on_fork:1; + pid_t pid; pid_t tgid; +#ifdef CONFIG_CC_STACKPROTECTOR /* Canary value for the -fstack-protector gcc feature */ unsigned long stack_canary; +#endif /* * pointers to (original) parent process, youngest child, younger sibling, @@ -1236,12 +1298,6 @@ struct task_struct { struct list_head ptraced; struct list_head ptrace_entry; - /* - * This is the tracer handle for the ptrace BTS extension. - * This field actually belongs to the ptracer task. - */ - struct bts_context *bts; - /* PID/PID hash table linkage. */ struct pid_link pids[PIDTYPE_MAX]; struct list_head thread_group; @@ -1252,7 +1308,9 @@ struct task_struct { cputime_t utime, stime, utimescaled, stimescaled; cputime_t gtime; +#ifndef CONFIG_VIRT_CPU_ACCOUNTING cputime_t prev_utime, prev_stime; +#endif unsigned long nvcsw, nivcsw; /* context switch counts */ struct timespec start_time; /* monotonic time */ struct timespec real_start_time; /* boot based time */ @@ -1263,18 +1321,16 @@ struct task_struct { struct list_head cpu_timers[3]; /* process credentials */ - const struct cred *real_cred; /* objective and real subjective task + const struct cred __rcu *real_cred; /* objective and real subjective task * credentials (COW) */ - const struct cred *cred; /* effective (overridable) subjective task + const struct cred __rcu *cred; /* effective (overridable) subjective task * credentials (COW) */ - struct mutex cred_guard_mutex; /* guard against foreign influences on - * credential calculations - * (notably. ptrace) */ + struct cred *replacement_session_keyring; /* for KEYCTL_SESSION_TO_PARENT */ char comm[TASK_COMM_LEN]; /* executable name excluding path - access with [gs]et_task_comm (which lock it with task_lock()) - - initialized normally by flush_old_exec */ + - initialized normally by setup_new_exec */ /* file system info */ int link_count, total_link_count; #ifdef CONFIG_SYSVIPC @@ -1326,7 +1382,7 @@ struct task_struct { #endif /* Protection of the PI data structures: */ - spinlock_t pi_lock; + raw_spinlock_t pi_lock; #ifdef CONFIG_RT_MUTEXES /* PI waiters blocked on a rt_mutex held by this task */ @@ -1341,17 +1397,17 @@ struct task_struct { #endif #ifdef CONFIG_TRACE_IRQFLAGS unsigned int irq_events; - int hardirqs_enabled; unsigned long hardirq_enable_ip; - unsigned int hardirq_enable_event; unsigned long hardirq_disable_ip; + unsigned int hardirq_enable_event; unsigned int hardirq_disable_event; - int softirqs_enabled; + int hardirqs_enabled; + int hardirq_context; unsigned long softirq_disable_ip; - unsigned int softirq_disable_event; unsigned long softirq_enable_ip; + unsigned int softirq_disable_event; unsigned int softirq_enable_event; - int hardirq_context; + int softirqs_enabled; int softirq_context; #endif #ifdef CONFIG_LOCKDEP @@ -1367,7 +1423,7 @@ struct task_struct { void *journal_info; /* stacked block device info */ - struct bio *bio_list, **bio_tail; + struct bio_list *bio_list; /* VM state */ struct reclaim_state *reclaim_state; @@ -1386,11 +1442,13 @@ struct task_struct { #endif #ifdef CONFIG_CPUSETS nodemask_t mems_allowed; /* Protected by alloc_lock */ + int mems_allowed_change_disable; int cpuset_mem_spread_rotor; + int cpuset_slab_spread_rotor; #endif #ifdef CONFIG_CGROUPS /* Control Group info protected by css_set_lock */ - struct css_set *cgroups; + struct css_set __rcu *cgroups; /* cg_list protected by css_set_lock and tsk->alloc_lock */ struct list_head cg_list; #endif @@ -1402,10 +1460,10 @@ struct task_struct { struct list_head pi_state_list; struct futex_pi_state *pi_state_cache; #endif -#ifdef CONFIG_PERF_COUNTERS - struct perf_counter_context *perf_counter_ctxp; - struct mutex perf_counter_mutex; - struct list_head perf_counter_list; +#ifdef CONFIG_PERF_EVENTS + struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts]; + struct mutex perf_event_mutex; + struct list_head perf_event_list; #endif #ifdef CONFIG_NUMA struct mempolicy *mempolicy; /* Protected by alloc_lock */ @@ -1438,7 +1496,7 @@ struct task_struct { struct list_head *scm_work_list; #ifdef CONFIG_FUNCTION_GRAPH_TRACER - /* Index of current stored adress in ret_stack */ + /* Index of current stored address in ret_stack */ int curr_ret_stack; /* Stack of return addresses for return function tracing */ struct ftrace_ret_stack *ret_stack; @@ -1458,10 +1516,18 @@ struct task_struct { /* bitmask of trace recursion */ unsigned long trace_recursion; #endif /* CONFIG_TRACING */ +#ifdef CONFIG_CGROUP_MEM_RES_CTLR /* memcg uses this to do batch job */ + struct memcg_batch_info { + int do_batch; /* incremented when batch uncharge started */ + struct mem_cgroup *memcg; /* target memcg of uncharge */ + unsigned long bytes; /* uncharged usage */ + unsigned long memsw_bytes; /* uncharged mem+swap usage */ + } memcg_batch; +#endif }; /* Future-safe accessor for struct task_struct's cpus_allowed. */ -#define tsk_cpumask(tsk) (&(tsk)->cpus_allowed) +#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed) /* * Priority of a process goes from 0..MAX_PRIO-1, valid RT @@ -1639,31 +1705,31 @@ static inline void put_task_struct(struct task_struct *t) __put_task_struct(t); } -extern cputime_t task_utime(struct task_struct *p); -extern cputime_t task_stime(struct task_struct *p); -extern cputime_t task_gtime(struct task_struct *p); +extern void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st); +extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st); /* * Per process flags */ -#define PF_ALIGNWARN 0x00000001 /* Print alignment warning msgs */ - /* Not implemented yet, only for 486*/ +#define PF_KSOFTIRQD 0x00000001 /* I am ksoftirqd */ #define PF_STARTING 0x00000002 /* being created */ #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 */ +#define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */ #define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */ +#define PF_MCE_PROCESS 0x00000080 /* process policy on mce errors */ #define PF_SUPERPRIV 0x00000100 /* used super-user privileges */ #define PF_DUMPCORE 0x00000200 /* dumped core */ #define PF_SIGNALED 0x00000400 /* killed by a signal */ #define PF_MEMALLOC 0x00000800 /* Allocating memory */ -#define PF_FLUSHER 0x00001000 /* responsible for disk writeback */ #define PF_USED_MATH 0x00002000 /* if unset the fpu must be initialized before use */ +#define PF_FREEZING 0x00004000 /* freeze in progress. do not account to load */ #define PF_NOFREEZE 0x00008000 /* this thread should not be frozen */ #define PF_FROZEN 0x00010000 /* frozen for system suspend */ #define PF_FSTRANS 0x00020000 /* inside a filesystem transaction */ #define PF_KSWAPD 0x00040000 /* I am kswapd */ -#define PF_SWAPOFF 0x00080000 /* I am in swapoff */ +#define PF_OOM_ORIGIN 0x00080000 /* Allocating much memory to others */ #define PF_LESS_THROTTLE 0x00100000 /* Throttle me less: I clean memory */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* randomize virtual address space */ @@ -1671,6 +1737,7 @@ extern cputime_t task_gtime(struct task_struct *p); #define PF_SPREAD_PAGE 0x01000000 /* Spread page cache over cpuset */ #define PF_SPREAD_SLAB 0x02000000 /* Spread some slab caches over cpuset */ #define PF_THREAD_BOUND 0x04000000 /* Thread bound to specific cpu */ +#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 freezeable */ @@ -1701,6 +1768,33 @@ extern cputime_t task_gtime(struct task_struct *p); #define tsk_used_math(p) ((p)->flags & PF_USED_MATH) #define used_math() tsk_used_math(current) +#ifdef CONFIG_PREEMPT_RCU + +#define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */ +#define RCU_READ_UNLOCK_BOOSTED (1 << 1) /* boosted while in RCU read-side. */ +#define RCU_READ_UNLOCK_NEED_QS (1 << 2) /* RCU core needs CPU response. */ + +static inline void rcu_copy_process(struct task_struct *p) +{ + p->rcu_read_lock_nesting = 0; + p->rcu_read_unlock_special = 0; +#ifdef CONFIG_TREE_PREEMPT_RCU + p->rcu_blocked_node = NULL; +#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ +#ifdef CONFIG_RCU_BOOST + p->rcu_boost_mutex = NULL; +#endif /* #ifdef CONFIG_RCU_BOOST */ + INIT_LIST_HEAD(&p->rcu_node_entry); +} + +#else + +static inline void rcu_copy_process(struct task_struct *p) +{ +} + +#endif + #ifdef CONFIG_SMP extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask); @@ -1713,25 +1807,32 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p, return 0; } #endif + +#ifndef CONFIG_CPUMASK_OFFSTACK static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask) { return set_cpus_allowed_ptr(p, &new_mask); } +#endif /* - * Architectures can set this to 1 if they have specified - * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig, - * but then during bootup it turns out that sched_clock() - * is reliable after all: + * Do not use outside of architecture code which knows its limitations. + * + * sched_clock() has no promise of monotonicity or bounded drift between + * CPUs, use (which you should not) requires disabling IRQs. + * + * Please use one of the three interfaces below. */ -#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK -extern int sched_clock_stable; -#endif +extern unsigned long long notrace sched_clock(void); +/* + * See the comment in kernel/sched_clock.c + */ +extern u64 cpu_clock(int cpu); +extern u64 local_clock(void); +extern u64 sched_clock_cpu(int cpu); -extern unsigned long long sched_clock(void); extern void sched_clock_init(void); -extern u64 sched_clock_cpu(int cpu); #ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK static inline void sched_clock_tick(void) @@ -1746,16 +1847,31 @@ static inline void sched_clock_idle_wakeup_event(u64 delta_ns) { } #else +/* + * Architectures can set this to 1 if they have specified + * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig, + * but then during bootup it turns out that sched_clock() + * is reliable after all: + */ +extern int sched_clock_stable; + extern void sched_clock_tick(void); extern void sched_clock_idle_sleep_event(void); extern void sched_clock_idle_wakeup_event(u64 delta_ns); #endif +#ifdef CONFIG_IRQ_TIME_ACCOUNTING /* - * For kernel-internal use: high-speed (but slightly incorrect) per-cpu - * clock constructed from sched_clock(): + * An i/f to runtime opt-in for irq time accounting based off of sched_clock. + * The reason for this explicit opt-in is not to have perf penalty with + * slow sched_clocks. */ -extern unsigned long long cpu_clock(int cpu); +extern void enable_sched_clock_irqtime(void); +extern void disable_sched_clock_irqtime(void); +#else +static inline void enable_sched_clock_irqtime(void) {} +static inline void disable_sched_clock_irqtime(void) {} +#endif extern unsigned long long task_sched_runtime(struct task_struct *task); @@ -1777,8 +1893,6 @@ extern void idle_task_exit(void); static inline void idle_task_exit(void) {} #endif -extern void sched_idle_next(void); - #if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP) extern void wake_up_idle_cpu(int cpu); #else @@ -1788,17 +1902,25 @@ static inline void wake_up_idle_cpu(int cpu) { } extern unsigned int sysctl_sched_latency; extern unsigned int sysctl_sched_min_granularity; extern unsigned int sysctl_sched_wakeup_granularity; -extern unsigned int sysctl_sched_shares_ratelimit; -extern unsigned int sysctl_sched_shares_thresh; -#ifdef CONFIG_SCHED_DEBUG extern unsigned int sysctl_sched_child_runs_first; -extern unsigned int sysctl_sched_features; + +enum sched_tunable_scaling { + SCHED_TUNABLESCALING_NONE, + SCHED_TUNABLESCALING_LOG, + SCHED_TUNABLESCALING_LINEAR, + SCHED_TUNABLESCALING_END, +}; +extern enum sched_tunable_scaling sysctl_sched_tunable_scaling; + +#ifdef CONFIG_SCHED_DEBUG extern unsigned int sysctl_sched_migration_cost; extern unsigned int sysctl_sched_nr_migrate; +extern unsigned int sysctl_sched_time_avg; extern unsigned int sysctl_timer_migration; +extern unsigned int sysctl_sched_shares_window; -int sched_nr_latency_handler(struct ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *length, +int sched_proc_update_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos); #endif #ifdef CONFIG_SCHED_DEBUG @@ -1816,11 +1938,29 @@ extern unsigned int sysctl_sched_rt_period; extern int sysctl_sched_rt_runtime; int sched_rt_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos); extern unsigned int sysctl_sched_compat_yield; +#ifdef CONFIG_SCHED_AUTOGROUP +extern unsigned int sysctl_sched_autogroup_enabled; + +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); +#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); +#endif +#else +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) { } +#endif + #ifdef CONFIG_RT_MUTEXES extern int rt_mutex_getprio(struct task_struct *p); extern void rt_mutex_setprio(struct task_struct *p, int prio); @@ -1839,9 +1979,10 @@ extern int task_nice(const struct task_struct *p); 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); -extern int sched_setscheduler(struct task_struct *, int, struct sched_param *); +extern int sched_setscheduler(struct task_struct *, int, + const struct sched_param *); extern int sched_setscheduler_nocheck(struct task_struct *, int, - struct sched_param *); + const struct sched_param *); extern struct task_struct *idle_task(int cpu); extern struct task_struct *curr_task(int cpu); extern void set_curr_task(int cpu, struct task_struct *p); @@ -1951,10 +2092,10 @@ extern int kill_pgrp(struct pid *pid, int sig, int priv); extern int kill_pid(struct pid *pid, int sig, int priv); extern int kill_proc_info(int, struct siginfo *, pid_t); extern int do_notify_parent(struct task_struct *, int); +extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent); extern void force_sig(int, struct task_struct *); -extern void force_sig_specific(int, struct task_struct *); extern int send_sig(int, struct task_struct *, int); -extern void zap_other_threads(struct task_struct *p); +extern int zap_other_threads(struct task_struct *p); extern struct sigqueue *sigqueue_alloc(void); extern void sigqueue_free(struct sigqueue *); extern int send_sigqueue(struct sigqueue *, struct task_struct *, int group); @@ -1971,16 +2112,18 @@ static inline int kill_cad_pid(int sig, int priv) #define SEND_SIG_PRIV ((struct siginfo *) 1) #define SEND_SIG_FORCED ((struct siginfo *) 2) -static inline int is_si_special(const struct siginfo *info) -{ - return info <= SEND_SIG_FORCED; -} - -/* True if we are on the alternate signal stack. */ - +/* + * True if we are on the alternate signal stack. + */ static inline int on_sig_stack(unsigned long sp) { - return (sp - current->sas_ss_sp < current->sas_ss_size); +#ifdef CONFIG_STACK_GROWSUP + return sp >= current->sas_ss_sp && + sp - current->sas_ss_sp < current->sas_ss_size; +#else + return sp > current->sas_ss_sp && + sp - current->sas_ss_sp <= current->sas_ss_size; +#endif } static inline int sas_ss_flags(unsigned long sp) @@ -2017,7 +2160,6 @@ extern void flush_thread(void); extern void exit_thread(void); extern void exit_files(struct task_struct *); -extern void __cleanup_signal(struct signal_struct *); extern void __cleanup_sighand(struct sighand_struct *); extern void exit_itimers(struct signal_struct *); @@ -2029,7 +2171,9 @@ extern void daemonize(const char *, ...); extern int allow_signal(int); extern int disallow_signal(int); -extern int do_execve(char *, char __user * __user *, char __user * __user *, struct pt_regs *); +extern int do_execve(const char *, + const char __user * const __user *, + const char __user * const __user *, struct pt_regs *); extern long do_fork(unsigned long, unsigned long, struct pt_regs *, unsigned long, int __user *, int __user *); struct task_struct *fork_idle(int); @@ -2037,10 +2181,8 @@ extern void set_task_comm(struct task_struct *tsk, char *from); extern char *get_task_comm(char *to, struct task_struct *tsk); #ifdef CONFIG_SMP -extern void wait_task_context_switch(struct task_struct *p); extern unsigned long wait_task_inactive(struct task_struct *, long match_state); #else -static inline void wait_task_context_switch(struct task_struct *p) {} static inline unsigned long wait_task_inactive(struct task_struct *p, long match_state) { @@ -2054,7 +2196,7 @@ static inline unsigned long wait_task_inactive(struct task_struct *p, #define for_each_process(p) \ for (p = &init_task ; (p = next_task(p)) != &init_task ; ) -extern bool is_single_threaded(struct task_struct *); +extern bool current_is_single_threaded(void); /* * Careful: do_each_thread/while_each_thread is a double loop so @@ -2066,6 +2208,11 @@ extern bool is_single_threaded(struct task_struct *); #define while_each_thread(g, t) \ while ((t = next_thread(t)) != g) +static inline int get_nr_threads(struct task_struct *tsk) +{ + return tsk->signal->nr_threads; +} + /* de_thread depends on thread_group_leader not being a pid based check */ #define thread_group_leader(p) (p == p->group_leader) @@ -2125,9 +2272,16 @@ static inline void task_unlock(struct task_struct *p) spin_unlock(&p->alloc_lock); } -extern struct sighand_struct *lock_task_sighand(struct task_struct *tsk, +extern struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, unsigned long *flags); +#define lock_task_sighand(tsk, flags) \ +({ struct sighand_struct *__ss; \ + __cond_lock(&(tsk)->sighand->siglock, \ + (__ss = __lock_task_sighand(tsk, flags))); \ + __ss; \ +}) \ + static inline void unlock_task_sighand(struct task_struct *tsk, unsigned long *flags) { @@ -2228,7 +2382,10 @@ static inline int signal_pending(struct task_struct *p) return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING)); } -extern int __fatal_signal_pending(struct task_struct *p); +static inline int __fatal_signal_pending(struct task_struct *p) +{ + return unlikely(sigismember(&p->pending.signal, SIGKILL)); +} static inline int fatal_signal_pending(struct task_struct *p) { @@ -2258,23 +2415,31 @@ static inline int need_resched(void) * cond_resched_softirq() will enable bhs before scheduling. */ extern int _cond_resched(void); -#ifdef CONFIG_PREEMPT_BKL -static inline int cond_resched(void) -{ - return 0; -} + +#define cond_resched() ({ \ + __might_sleep(__FILE__, __LINE__, 0); \ + _cond_resched(); \ +}) + +extern int __cond_resched_lock(spinlock_t *lock); + +#ifdef CONFIG_PREEMPT +#define PREEMPT_LOCK_OFFSET PREEMPT_OFFSET #else -static inline int cond_resched(void) -{ - return _cond_resched(); -} +#define PREEMPT_LOCK_OFFSET 0 #endif -extern int cond_resched_lock(spinlock_t * lock); -extern int cond_resched_softirq(void); -static inline int cond_resched_bkl(void) -{ - return _cond_resched(); -} + +#define cond_resched_lock(lock) ({ \ + __might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET); \ + __cond_resched_lock(lock); \ +}) + +extern int __cond_resched_softirq(void); + +#define cond_resched_softirq() ({ \ + __might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET); \ + __cond_resched_softirq(); \ +}) /* * Does a critical section need to be broken due to another @@ -2298,13 +2463,7 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times); static inline void thread_group_cputime_init(struct signal_struct *sig) { - sig->cputimer.cputime = INIT_CPUTIME; spin_lock_init(&sig->cputimer.lock); - sig->cputimer.running = 0; -} - -static inline void thread_group_cputime_free(struct signal_struct *sig) -{ } /* @@ -2343,32 +2502,14 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) #endif /* CONFIG_SMP */ -extern void arch_pick_mmap_layout(struct mm_struct *mm); - -#ifdef CONFIG_TRACING -extern void -__trace_special(void *__tr, void *__data, - unsigned long arg1, unsigned long arg2, unsigned long arg3); -#else -static inline void -__trace_special(void *__tr, void *__data, - unsigned long arg1, unsigned long arg2, unsigned long arg3) -{ -} -#endif - extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask); extern long sched_getaffinity(pid_t pid, struct cpumask *mask); extern void normalize_rt_tasks(void); -#ifdef CONFIG_GROUP_SCHED +#ifdef CONFIG_CGROUP_SCHED -extern struct task_group init_task_group; -#ifdef CONFIG_USER_SCHED extern struct task_group root_task_group; -extern void set_tg_uid(struct user_struct *user); -#endif extern struct task_group *sched_create_group(struct task_group *parent); extern void sched_destroy_group(struct task_group *tg); @@ -2453,7 +2594,27 @@ static inline void mm_init_owner(struct mm_struct *mm, struct task_struct *p) } #endif /* CONFIG_MM_OWNER */ -#define TASK_STATE_TO_CHAR_STR "RSDTtZX" +static inline unsigned long task_rlimit(const struct task_struct *tsk, + unsigned int limit) +{ + return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_cur); +} + +static inline unsigned long task_rlimit_max(const struct task_struct *tsk, + unsigned int limit) +{ + return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_max); +} + +static inline unsigned long rlimit(unsigned int limit) +{ + return task_rlimit(current, limit); +} + +static inline unsigned long rlimit_max(unsigned int limit) +{ + return task_rlimit_max(current, limit); +} #endif /* __KERNEL__ */ |