X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=include%2Flinux%2Fsched.h;h=244c287a5ac12f4b0c10068322b3daac493ba29e;hb=ad09750b51150ca87531b8790a379214a974c167;hp=1bc6fae0c1351b96ffd7e7f1e88dda544891f73c;hpb=2ff05b2b4eac2e63d345fc731ea151a060247f53;p=safe%2Fjmp%2Flinux-2.6 diff --git a/include/linux/sched.h b/include/linux/sched.h index 1bc6fae..244c287 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__ @@ -92,14 +94,13 @@ struct sched_param { #include -struct mem_cgroup; struct exec_domain; struct futex_pi_state; struct robust_list_head; struct bio; struct fs_struct; struct bts_context; -struct perf_counter_context; +struct perf_event_context; /* * List of flags we want to share for kernel threads, @@ -139,8 +140,11 @@ extern int nr_processes(void); extern unsigned long nr_running(void); extern unsigned long nr_uninterruptible(void); extern unsigned long nr_iowait(void); +extern unsigned long nr_iowait_cpu(void); +extern unsigned long this_cpu_load(void); + + extern void calc_global_load(void); -extern u64 cpu_nr_migrations(int cpu); extern unsigned long get_parent_ip(unsigned long addr); @@ -166,8 +170,6 @@ 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(). @@ -189,6 +191,7 @@ extern unsigned long long time_sync_thresh; /* in tsk->state again */ #define TASK_DEAD 64 #define TASK_WAKEKILL 128 +#define TASK_WAKING 256 /* Convenience macros for the sake of set_task_state */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) @@ -210,7 +213,7 @@ extern unsigned long long time_sync_thresh; ((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) @@ -255,7 +258,7 @@ 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 int runqueue_is_locked(int cpu); extern void task_rq_unlock_wait(struct task_struct *p); extern cpumask_var_t nohz_cpu_mask; @@ -303,7 +306,7 @@ extern void softlockup_tick(void); extern void touch_softlockup_watchdog(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, + void __user *buffer, size_t *lenp, loff_t *ppos); extern unsigned int softlockup_panic; extern int softlockup_thresh; @@ -325,7 +328,7 @@ 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); #endif @@ -343,15 +346,26 @@ 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 (USHORT_MAX - MAPCOUNT_ELF_CORE_MARGIN) extern int sysctl_max_map_count; @@ -408,6 +422,15 @@ static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm) return max(mm->hiwater_rss, get_mm_rss(mm)); } +static inline void setmax_mm_hiwater_rss(unsigned long *maxrss, + struct mm_struct *mm) +{ + unsigned long hiwater_rss = get_mm_hiwater_rss(mm); + + if (*maxrss < hiwater_rss) + *maxrss = hiwater_rss; +} + static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm) { return max(mm->hiwater_vm, mm->total_vm); @@ -420,7 +443,9 @@ 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 @@ -430,6 +455,7 @@ 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 \ @@ -443,6 +469,10 @@ 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; @@ -459,6 +489,13 @@ 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 @@ -487,6 +524,15 @@ 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. @@ -544,9 +590,12 @@ 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. @@ -575,9 +624,13 @@ 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; /* @@ -609,6 +662,8 @@ struct signal_struct { unsigned audit_tty; struct tty_audit_buf *tty_audit_buf; #endif + + int oom_adj; /* OOM kill score adjustment (bit shift) */ }; /* Context switch must be unlocked if interrupts are to be enabled */ @@ -674,11 +729,11 @@ struct user_struct { struct task_group *tg; #ifdef CONFIG_SYSFS struct kobject kobj; - struct work_struct work; + struct delayed_work work; #endif #endif -#ifdef CONFIG_PERF_COUNTERS +#ifdef CONFIG_PERF_EVENTS atomic_long_t locked_vm; #endif }; @@ -776,18 +831,19 @@ 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_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */ enum powersavings_balance_level { POWERSAVINGS_BALANCE_NONE = 0, /* No power saving load balance */ @@ -807,7 +863,7 @@ static inline int sd_balance_for_mc_power(void) if (sched_smt_power_savings) return SD_POWERSAVINGS_BALANCE; - return 0; + return SD_PREFER_SIBLING; } static inline int sd_balance_for_package_power(void) @@ -815,7 +871,7 @@ 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; } /* @@ -837,15 +893,9 @@ 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; /* * The CPUs this group covers. @@ -898,6 +948,7 @@ 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; @@ -961,9 +1012,13 @@ 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) { @@ -973,17 +1028,21 @@ 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 */ @@ -1001,6 +1060,12 @@ 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 */ + struct sched_class { const struct sched_class *next; @@ -1008,13 +1073,13 @@ struct sched_class { void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep); 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); + int (*select_task_rq)(struct task_struct *p, int sd_flag, int flags); unsigned long (*load_balance) (struct rq *this_rq, int this_cpu, struct rq *busiest, unsigned long max_load_move, @@ -1025,7 +1090,6 @@ struct sched_class { 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); @@ -1038,7 +1102,7 @@ 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); @@ -1047,6 +1111,9 @@ 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); #endif @@ -1090,6 +1157,8 @@ struct sched_entity { u64 wait_max; u64 wait_count; u64 wait_sum; + u64 iowait_count; + u64 iowait_sum; u64 sleep_start; u64 sleep_max; @@ -1105,7 +1174,6 @@ 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; @@ -1143,6 +1211,8 @@ struct sched_rt_entity { #endif }; +struct rcu_node; + struct task_struct { volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */ void *stack; @@ -1185,10 +1255,12 @@ struct task_struct { unsigned int policy; cpumask_t cpus_allowed; -#ifdef CONFIG_PREEMPT_RCU +#ifdef CONFIG_TREE_PREEMPT_RCU int rcu_read_lock_nesting; - int rcu_flipctr_idx; -#endif /* #ifdef CONFIG_PREEMPT_RCU */ + char rcu_read_unlock_special; + struct rcu_node *rcu_blocked_node; + struct list_head rcu_node_entry; +#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) struct sched_info sched_info; @@ -1200,7 +1272,6 @@ struct task_struct { struct mm_struct *mm, *active_mm; /* task state */ - struct linux_binfmt *binfmt; int exit_state; int exit_code, exit_signal; int pdeath_signal; /* The signal sent when the parent dies */ @@ -1209,11 +1280,19 @@ 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, @@ -1253,7 +1332,9 @@ 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 */ @@ -1271,6 +1352,7 @@ struct task_struct { 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 @@ -1327,7 +1409,7 @@ 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 */ @@ -1342,17 +1424,17 @@ 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 @@ -1364,8 +1446,10 @@ struct task_struct { gfp_t lockdep_reclaim_gfp; #endif +#ifdef CONFIG_FS_JOURNAL_INFO /* journalling filesystem info */ void *journal_info; +#endif /* stacked block device info */ struct bio *bio_list, **bio_tail; @@ -1403,10 +1487,10 @@ 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; + struct mutex perf_event_mutex; + struct list_head perf_event_list; #endif #ifdef CONFIG_NUMA struct mempolicy *mempolicy; /* Protected by alloc_lock */ @@ -1459,6 +1543,15 @@ struct task_struct { /* bitmask of trace recursion */ unsigned long trace_recursion; #endif /* CONFIG_TRACING */ + unsigned long stack_start; +#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. */ @@ -1640,9 +1733,8 @@ 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 @@ -1654,17 +1746,19 @@ extern cputime_t task_gtime(struct task_struct *p); #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ #define PF_VCPU 0x00000010 /* I'm a virtual CPU */ #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 */ @@ -1672,6 +1766,7 @@ 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 */ @@ -1702,6 +1797,27 @@ 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_TREE_PREEMPT_RCU + +#define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */ +#define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* 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; + p->rcu_blocked_node = NULL; + 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); @@ -1714,10 +1830,13 @@ 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 @@ -1729,7 +1848,8 @@ static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask) extern int sched_clock_stable; #endif -extern unsigned long long sched_clock(void); +/* ftrace calls sched_clock() directly */ +extern unsigned long long notrace sched_clock(void); extern void sched_clock_init(void); extern u64 sched_clock_cpu(int cpu); @@ -1791,15 +1911,24 @@ 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; -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 @@ -1817,7 +1946,7 @@ 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; @@ -1879,9 +2008,6 @@ extern struct pid_namespace init_pid_ns; /* * find a task by one of its numerical ids * - * find_task_by_pid_type_ns(): - * it is the most generic call - it finds a task by all id, - * type and namespace specified * find_task_by_pid_ns(): * finds a task by its pid in the specified namespace * find_task_by_vpid(): @@ -1890,9 +2016,6 @@ extern struct pid_namespace init_pid_ns; * see also find_vpid() etc in include/linux/pid.h */ -extern struct task_struct *find_task_by_pid_type_ns(int type, int pid, - struct pid_namespace *ns); - extern struct task_struct *find_task_by_vpid(pid_t nr); extern struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns); @@ -1958,8 +2081,8 @@ 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 struct sigqueue *sigqueue_alloc(void); @@ -1978,16 +2101,18 @@ 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) @@ -2061,7 +2186,7 @@ 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 @@ -2235,7 +2360,10 @@ 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) { @@ -2265,23 +2393,31 @@ 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_OFFSET); \ + __cond_resched_softirq(); \ +}) /* * Does a critical section need to be broken due to another