blob: 0802277e6b80f7dd96e6eb161cddea13eda527eb [file] [log] [blame]
#ifndef _LINUX_SCHED_H
#define _LINUX_SCHED_H
* cloning flags:
#define CSIGNAL 0x000000ff /* signal mask to be sent at exit */
#define CLONE_VM 0x00000100 /* set if VM shared between processes */
#define CLONE_FS 0x00000200 /* set if fs info shared between processes */
#define CLONE_FILES 0x00000400 /* set if open files shared between processes */
#define CLONE_SIGHAND 0x00000800 /* set if signal handlers and blocked signals shared */
#define CLONE_PTRACE 0x00002000 /* set if we want to let tracing continue on the child too */
#define CLONE_VFORK 0x00004000 /* set if the parent wants the child to wake it up on mm_release */
#define CLONE_PARENT 0x00008000 /* set if we want to have the same parent as the cloner */
#define CLONE_THREAD 0x00010000 /* Same thread group? */
#define CLONE_NEWNS 0x00020000 /* New namespace group? */
#define CLONE_SYSVSEM 0x00040000 /* share system V SEM_UNDO semantics */
#define CLONE_SETTLS 0x00080000 /* create a new TLS for the child */
#define CLONE_PARENT_SETTID 0x00100000 /* set the TID in the parent */
#define CLONE_CHILD_CLEARTID 0x00200000 /* clear the TID in the child */
#define CLONE_DETACHED 0x00400000 /* Unused, ignored */
#define CLONE_UNTRACED 0x00800000 /* set if the tracing process can't force CLONE_PTRACE on this clone */
#define CLONE_CHILD_SETTID 0x01000000 /* set the TID in the child */
#define CLONE_STOPPED 0x02000000 /* Start in stopped state */
#define CLONE_NEWUTS 0x04000000 /* New utsname group? */
#define CLONE_NEWIPC 0x08000000 /* New ipcs */
#define CLONE_NEWUSER 0x10000000 /* New user namespace */
#define CLONE_NEWPID 0x20000000 /* New pid namespace */
#define CLONE_NEWNET 0x40000000 /* New network namespace */
#define CLONE_IO 0x80000000 /* Clone io context */
* Scheduling policies
#define SCHED_NORMAL 0
#define SCHED_FIFO 1
#define SCHED_RR 2
#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__
struct sched_param {
int sched_priority;
#include <asm/param.h> /* for HZ */
#include <linux/capability.h>
#include <linux/threads.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/timex.h>
#include <linux/jiffies.h>
#include <linux/rbtree.h>
#include <linux/thread_info.h>
#include <linux/cpumask.h>
#include <linux/errno.h>
#include <linux/nodemask.h>
#include <linux/mm_types.h>
#include <asm/system.h>
#include <asm/page.h>
#include <asm/ptrace.h>
#include <asm/cputime.h>
#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>
#include <linux/percpu.h>
#include <linux/topology.h>
#include <linux/proportions.h>
#include <linux/seccomp.h>
#include <linux/rcupdate.h>
#include <linux/rculist.h>
#include <linux/rtmutex.h>
#include <linux/time.h>
#include <linux/param.h>
#include <linux/resource.h>
#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>
#include <linux/gfp.h>
#include <asm/processor.h>
struct exec_domain;
struct futex_pi_state;
struct robust_list_head;
struct bio_list;
struct fs_struct;
struct perf_event_context;
* List of flags we want to share for kernel threads,
* if only because they are not used by them anyway.
* These are the constant used to fake the fixed-point load-average
* counting. Some notes:
* - 11 bit fractions expand to 22 bits by the multiplies: this gives
* a load-average precision of 10 bits integer + 11 bits fractional
* - if you want to count load-averages more often, you need more
* precision, or rounding will get you. With 2-second counting freq,
* the EXP_n values would be 1981, 2034 and 2043 if still using only
* 11 bit fractions.
extern unsigned long avenrun[]; /* Load averages */
extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift);
#define FSHIFT 11 /* nr of bits of precision */
#define FIXED_1 (1<<FSHIFT) /* 1.0 as fixed-point */
#define LOAD_FREQ (5*HZ+1) /* 5 sec intervals */
#define EXP_1 1884 /* 1/exp(5sec/1min) as fixed-point */
#define EXP_5 2014 /* 1/exp(5sec/5min) */
#define EXP_15 2037 /* 1/exp(5sec/15min) */
#define CALC_LOAD(load,exp,n) \
load *= exp; \
load += n*(FIXED_1-exp); \
load >>= FSHIFT;
extern unsigned long total_forks;
extern int nr_threads;
DECLARE_PER_CPU(unsigned long, process_counts);
extern int nr_processes(void);
extern unsigned long nr_running(void);
extern unsigned long nr_uninterruptible(void);
extern unsigned long nr_active(void);
extern unsigned long nr_iowait(void);
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);
struct seq_file;
struct cfs_rq;
struct task_group;
extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m);
extern void proc_sched_set_task(struct task_struct *p);
extern void
print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
static inline void
proc_sched_show_task(struct task_struct *p, struct seq_file *m)
static inline void proc_sched_set_task(struct task_struct *p)
static inline void
print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
* Task state bitmask. NOTE! These bits are also
* encoded in fs/proc/array.c: get_task_state().
* We have two separate sets of flags: task->state
* is about runnability, while task->exit_state are
* about the task exiting. Confusing, but this way
* modifying one set can't modify the other one by
* mistake.
#define TASK_RUNNING 0
#define __TASK_STOPPED 4
#define __TASK_TRACED 8
/* in tsk->exit_state */
#define EXIT_ZOMBIE 16
#define EXIT_DEAD 32
/* in tsk->state again */
#define TASK_DEAD 64
#define TASK_WAKEKILL 128
#define TASK_WAKING 256
#define TASK_STATE_MAX 512
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 */
/* Convenience macros for the sake of wake_up */
/* get_task_state() */
#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_FREEZING) == 0)
#define __set_task_state(tsk, state_value) \
do { (tsk)->state = (state_value); } while (0)
#define set_task_state(tsk, state_value) \
set_mb((tsk)->state, (state_value))
* 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->state = (state_value); } while (0)
#define set_current_state(state_value) \
set_mb(current->state, (state_value))
/* Task command name length */
#define TASK_COMM_LEN 16
#include <linux/spinlock.h>
* This serializes "schedule()" and also protects
* the run-queue from deletions/modifications (but
* _adding_ to the beginning of the run-queue has
* a separate lock).
extern rwlock_t tasklist_lock;
extern spinlock_t mmlist_lock;
struct task_struct;
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(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);
static inline int select_nohz_load_balancer(int cpu)
return 0;
* Only dump TASK_* tasks. (0 for all tasks)
extern void show_state_filter(unsigned long state_filter);
static inline void show_state(void)
extern void show_regs(struct pt_regs *);
* TASK is a pointer to the task whose backtrace we want to see (or NULL for current
* task), SP is the stack pointer of the first frame that should be shown in the back
* trace (or NULL if the entire call-chain of the task should be shown).
extern void show_stack(struct task_struct *task, unsigned long *sp);
void io_schedule(void);
long io_schedule_timeout(long timeout);
extern void cpu_init (void);
extern void trap_init(void);
extern void update_process_times(int user);
extern void scheduler_tick(void);
extern void sched_show_task(struct task_struct *p);
extern void softlockup_tick(void);
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,
void __user *buffer,
size_t *lenp, loff_t *ppos);
extern unsigned int softlockup_panic;
extern int softlockup_thresh;
static inline void softlockup_tick(void)
static inline void touch_softlockup_watchdog(void)
static inline void touch_softlockup_watchdog_sync(void)
static inline void touch_all_softlockup_watchdogs(void)
extern unsigned int sysctl_hung_task_panic;
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,
void __user *buffer,
size_t *lenp, loff_t *ppos);
/* Attach to any functions which should be ignored in wchan output. */
#define __sched __attribute__((__section__(".sched.text")))
/* Linker adds these: start and end of __sched functions */
extern char __sched_text_start[], __sched_text_end[];
/* Is this address in the __sched functions? */
extern int in_sched_functions(unsigned long addr);
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);
extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner);
struct nsproxy;
struct user_namespace;
* 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.
extern int sysctl_max_map_count;
#include <linux/aio.h>
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);
extern unsigned long
arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff,
unsigned long flags);
extern void arch_unmap_area(struct mm_struct *, unsigned long);
extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
extern void set_dumpable(struct mm_struct *mm, int value);
extern int get_dumpable(struct mm_struct *mm);
/* mm flags */
/* dumpable bits */
#define MMF_DUMPABLE 0 /* core dump is permitted */
#define MMF_DUMP_SECURELY 1 /* core file is readable only by root */
/* coredump filter bits */
/* leave room for more dump flags */
#define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */
struct sighand_struct {
atomic_t count;
struct k_sigaction action[_NSIG];
spinlock_t siglock;
wait_queue_head_t signalfd_wqh;
struct pacct_struct {
int ac_flag;
long ac_exitcode;
unsigned long ac_mem;
cputime_t ac_utime, ac_stime;
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
* @stime: time spent in kernel mode, in &cputime_t units
* @sum_exec_runtime: total time spent on the CPU, in nanoseconds
* This structure groups together three kinds of CPU time that are
* tracked for threads and thread groups. Most things considering
* CPU time want to group these counts together and treat all three
* of them in parallel.
struct task_cputime {
cputime_t utime;
cputime_t stime;
unsigned long long sum_exec_runtime;
/* Alternate field names when used to cache expirations. */
#define prof_exp stime
#define virt_exp utime
#define sched_exp sum_exec_runtime
#define INIT_CPUTIME \
(struct task_cputime) { \
.utime = cputime_zero, \
.stime = cputime_zero, \
.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().
* struct thread_group_cputimer - thread group interval timer counts
* @cputime: thread group interval timers.
* @running: non-zero when there are timers running and
* @cputime receives updates.
* @lock: lock for fields in this struct.
* This structure contains the version of task_cputime, above, that is
* used for thread group CPU timer calculations.
struct thread_group_cputimer {
struct task_cputime cputime;
int running;
spinlock_t lock;
* NOTE! "signal_struct" does not have it's own
* locking, because a shared signal_struct always
* implies a shared sighand_struct, so locking
* sighand_struct is always a proper superset of
* the locking of signal_struct.
struct signal_struct {
atomic_t sigcnt;
atomic_t live;
int nr_threads;
wait_queue_head_t wait_chldexit; /* for wait4() */
/* current thread group signal load-balancing target: */
struct task_struct *curr_target;
/* shared signal handling: */
struct sigpending shared_pending;
/* thread group exit support */
int group_exit_code;
/* overloaded:
* - notify group_exit_task when ->count is equal to notify_count
* - everyone except group_exit_task is stopped during signal delivery
* of fatal signals, group_exit_task processes the signal.
int notify_count;
struct task_struct *group_exit_task;
/* thread group stop support, overloads group_exit_code too */
int group_stop_count;
unsigned int flags; /* see SIGNAL_* flags below */
/* POSIX.1b Interval Timers */
struct list_head posix_timers;
/* ITIMER_REAL timer for the process */
struct hrtimer real_timer;
struct pid *leader_pid;
ktime_t it_real_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.
* See thread_group_cputimer(), et al, for details.
struct thread_group_cputimer cputimer;
/* Earliest-expiration cache. */
struct task_cputime cputime_expires;
struct list_head cpu_timers[3];
struct pid *tty_old_pgrp;
/* boolean value for session group leader */
int leader;
struct tty_struct *tty; /* NULL if no tty */
* Cumulative resource counters for dead threads in the group,
* and for reaped dead child processes forked by this group.
* Live threads maintain their own counters and add to these
* in __exit_signal, except for the group leader.
cputime_t utime, stime, cutime, cstime;
cputime_t gtime;
cputime_t cgtime;
cputime_t prev_utime, prev_stime;
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;
* Cumulative ns of schedule CPU time fo dead threads in the
* group, not including a zombie group leader, (This only differs
* from jiffies_to_ns(utime + stime) if sched_clock uses something
* other than jiffies.)
unsigned long long sum_sched_runtime;
* We don't bother to synchronize most readers of this at all,
* because there is no reader checking a limit that actually needs
* to get both rlim_cur and rlim_max atomically, and either one
* alone is a single word that can safely be read normally.
* getrlimit/setrlimit use task_lock(current->group_leader) to
* protect this instead of the siglock, because they really
* have no need to disable irqs.
struct rlimit rlim[RLIM_NLIMITS];
struct pacct_struct pacct; /* per-process accounting information */
struct taskstats *stats;
unsigned audit_tty;
struct tty_audit_buf *tty_audit_buf;
int oom_adj; /* OOM kill score adjustment (bit shift) */
/* Context switch must be unlocked if interrupts are to be enabled */
* Bits in flags field of signal_struct.
#define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */
#define SIGNAL_STOP_DEQUEUED 0x00000002 /* stop signal dequeued */
#define SIGNAL_STOP_CONTINUED 0x00000004 /* SIGCONT since WCONTINUED reap */
#define SIGNAL_GROUP_EXIT 0x00000008 /* group exit in progress */
* Pending notifications to parent.
#define SIGNAL_CLD_STOPPED 0x00000010
#define SIGNAL_CLD_CONTINUED 0x00000020
#define SIGNAL_UNKILLABLE 0x00000040 /* for init: ignore fatal signals */
/* If true, all threads except ->group_exit_task have pending SIGKILL */
static inline int signal_group_exit(const struct signal_struct *sig)
return (sig->flags & SIGNAL_GROUP_EXIT) ||
(sig->group_exit_task != NULL);
* Some day this will be a full-fledged user tracking system..
struct user_struct {
atomic_t __count; /* reference count */
atomic_t processes; /* How many processes does this user have? */
atomic_t files; /* How many open files does this user have? */
atomic_t sigpending; /* How many pending signals does this user have? */
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? */
atomic_t epoll_watches; /* The number of file descriptors currently watched */
/* protected by mq_lock */
unsigned long mq_bytes; /* How many bytes can be allocated to mqueue? */
unsigned long locked_shm; /* How many pages of mlocked shm ? */
struct key *uid_keyring; /* UID specific keyring */
struct key *session_keyring; /* UID's default session keyring */
/* Hash table maintenance information */
struct hlist_node uidhash_node;
uid_t uid;
struct user_namespace *user_ns;
atomic_long_t locked_vm;
extern int uids_sysfs_init(void);
extern struct user_struct *find_user(uid_t);
extern struct user_struct root_user;
#define INIT_USER (&root_user)
struct backing_dev_info;
struct reclaim_state;
struct sched_info {
/* cumulative counters */
unsigned long pcount; /* # of times run on this cpu */
unsigned long long run_delay; /* time spent waiting on a runqueue */
/* timestamps */
unsigned long long last_arrival,/* when we last ran on a cpu */
last_queued; /* when we were last queued to run */
/* BKL stats */
unsigned int bkl_count;
#endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */
struct task_delay_info {
spinlock_t lock;
unsigned int flags; /* Private per-task flags */
/* For each stat XXX, add following, aligned appropriately
* struct timespec XXX_start, XXX_end;
* u64 XXX_delay;
* u32 XXX_count;
* Atomicity of updates to XXX_delay, XXX_count protected by
* single lock above (split into XXX_lock if contention is an issue).
* XXX_count is incremented on every XXX operation, the delay
* associated with the operation is added to XXX_delay.
* XXX_delay contains the accumulated delay time in nanoseconds.
struct timespec blkio_start, blkio_end; /* Shared by blkio, swapin */
u64 blkio_delay; /* wait for sync block io completion */
u64 swapin_delay; /* wait for swapin block io completion */
u32 blkio_count; /* total count of the number of sync block */
/* io operations performed */
u32 swapin_count; /* total count of the number of swapin block */
/* io operations performed */
struct timespec freepages_start, freepages_end;
u64 freepages_delay; /* wait for memory reclaim */
u32 freepages_count; /* total count of memory reclaim */
static inline int sched_info_on(void)
return 1;
extern int delayacct_on;
return delayacct_on;
return 0;
enum cpu_idle_type {
* sched-domains (multiprocessor balancing) declarations:
* Increase resolution of nice-level calculations:
#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 */
POWERSAVINGS_BALANCE_BASIC, /* Fill one thread/core/package
* first for long running threads
POWERSAVINGS_BALANCE_WAKEUP, /* Also bias task wakeups to semi-idle
* cpu package for power savings
extern int sched_mc_power_savings, sched_smt_power_savings;
static inline int sd_balance_for_mc_power(void)
if (sched_smt_power_savings)
if (!sched_mc_power_savings)
return 0;
static inline int sd_balance_for_package_power(void)
if (sched_mc_power_savings | sched_smt_power_savings)
* Optimise SD flags for power savings:
* SD_BALANCE_NEWIDLE helps agressive task consolidation and power savings.
* Keep default SD flags if sched_{smt,mc}_power_saving=0
static inline int sd_power_saving_flags(void)
if (sched_mc_power_savings | sched_smt_power_savings)
return 0;
struct sched_group {
struct sched_group *next; /* Must be a circular list */
* CPU power of this group, SCHED_LOAD_SCALE being max power for a
* single CPU.
unsigned int cpu_power;
unsigned int group_weight;
* The CPUs this group covers.
* NOTE: this field is variable length. (Allocated dynamically
* by attaching extra space to the end of the structure,
* depending on how many CPUs the kernel has booted up with)
* It is also be embedded into static data structures at build
* time. (See 'struct static_sched_group' in kernel/sched.c)
unsigned long cpumask[0];
static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
return to_cpumask(sg->cpumask);
enum sched_domain_level {
struct sched_domain_attr {
int relax_domain_level;
#define SD_ATTR_INIT (struct sched_domain_attr) { \
.relax_domain_level = -1, \
struct sched_domain {
/* These fields must be setup */
struct sched_domain *parent; /* top domain must be null terminated */
struct sched_domain *child; /* bottom domain must be null terminated */
struct sched_group *groups; /* the balancing groups of the domain */
unsigned long min_interval; /* Minimum balance interval ms */
unsigned long max_interval; /* Maximum balance interval ms */
unsigned int busy_factor; /* less balancing by factor if busy */
unsigned int imbalance_pct; /* No balance until over watermark */
unsigned int cache_nice_tries; /* Leave cache hot tasks for # tries */
unsigned int busy_idx;
unsigned int idle_idx;
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;
/* Runtime fields. */
unsigned long last_balance; /* init to jiffies. units in jiffies */
unsigned int balance_interval; /* initialise to 1. units in ms. */
unsigned int nr_balance_failed; /* initialise to 0 */
u64 last_update;
/* load_balance() stats */
unsigned int lb_count[CPU_MAX_IDLE_TYPES];
unsigned int lb_failed[CPU_MAX_IDLE_TYPES];
unsigned int lb_balanced[CPU_MAX_IDLE_TYPES];
unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES];
unsigned int lb_gained[CPU_MAX_IDLE_TYPES];
unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES];
unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES];
unsigned int lb_nobusyq[CPU_MAX_IDLE_TYPES];
/* Active load balancing */
unsigned int alb_count;
unsigned int alb_failed;
unsigned int alb_pushed;
/* SD_BALANCE_EXEC stats */
unsigned int sbe_count;
unsigned int sbe_balanced;
unsigned int sbe_pushed;
/* SD_BALANCE_FORK stats */
unsigned int sbf_count;
unsigned int sbf_balanced;
unsigned int sbf_pushed;
/* try_to_wake_up() stats */
unsigned int ttwu_wake_remote;
unsigned int ttwu_move_affine;
unsigned int ttwu_move_balance;
char *name;
unsigned int span_weight;
* Span of all CPUs in this domain.
* NOTE: this field is variable length. (Allocated dynamically
* by attaching extra space to the end of the structure,
* depending on how many CPUs the kernel has booted up with)
* It is also be embedded into static data structures at build
* time. (See 'struct static_sched_domain' in kernel/sched.c)
unsigned long span[0];
static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
return to_cpumask(sd->span);
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)
if (sd->parent && (sd->parent->flags & flag))
return 1;
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, cpumask_var_t doms_new[],
struct sched_domain_attr *dattr_new)
#endif /* !CONFIG_SMP */
struct io_context; /* See blkdev.h */
extern void prefetch_stack(struct task_struct *t);
static inline void prefetch_stack(struct task_struct *t) { }
struct audit_context; /* See audit.c */
struct mempolicy;
struct pipe_inode_info;
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_HEAD 4
struct sched_class {
const struct sched_class *next;
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 flags);
struct task_struct * (*pick_next_task) (struct rq *rq);
void (*put_prev_task) (struct rq *rq, struct task_struct *p);
int (*select_task_rq)(struct rq *rq, struct task_struct *p,
int sd_flag, int flags);
void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
void (*post_schedule) (struct rq *this_rq);
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);
void (*rq_online)(struct rq *rq);
void (*rq_offline)(struct rq *rq);
void (*set_curr_task) (struct rq *rq);
void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
void (*task_fork) (struct task_struct *p);
void (*switched_from) (struct rq *this_rq, struct task_struct *task,
int running);
void (*switched_to) (struct rq *this_rq, struct task_struct *task,
int running);
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);
void (*task_move_group) (struct task_struct *p, int on_rq);
struct load_weight {
unsigned long weight, inv_weight;
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;
s64 sum_sleep_runtime;
u64 block_start;
u64 block_max;
u64 exec_max;
u64 slice_max;
u64 nr_migrations_cold;
u64 nr_failed_migrations_affine;
u64 nr_failed_migrations_running;
u64 nr_failed_migrations_hot;
u64 nr_forced_migrations;
u64 nr_wakeups;
u64 nr_wakeups_sync;
u64 nr_wakeups_migrate;
u64 nr_wakeups_local;
u64 nr_wakeups_remote;
u64 nr_wakeups_affine;
u64 nr_wakeups_affine_attempts;
u64 nr_wakeups_passive;
u64 nr_wakeups_idle;
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;
struct sched_statistics statistics;
struct sched_entity *parent;
/* rq on which this entity is (to be) queued: */
struct cfs_rq *cfs_rq;
/* rq "owned" by this entity/group: */
struct cfs_rq *my_q;
struct sched_rt_entity {
struct list_head run_list;
unsigned long timeout;
unsigned int time_slice;
int nr_cpus_allowed;
struct sched_rt_entity *back;
struct sched_rt_entity *parent;
/* rq on which this entity is (to be) queued: */
struct rt_rq *rt_rq;
/* rq "owned" by this entity/group: */
struct rt_rq *my_q;
struct rcu_node;
struct task_struct {
volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */
void *stack;
atomic_t usage;
unsigned int flags; /* per process flags, defined below */
unsigned int ptrace;
int lock_depth; /* BKL lock depth */
int oncpu;
int prio, static_prio, normal_prio;
unsigned int rt_priority;
const struct sched_class *sched_class;
struct sched_entity se;
struct sched_rt_entity rt;
/* list of struct preempt_notifier: */
struct hlist_head preempt_notifiers;
* fpu_counter contains the number of consecutive context switches
* that the FPU is used. If this is over a threshold, the lazy fpu
* saving becomes unlazy to save the trap. This is an unsigned char
* so that after 256 times the counter wraps and the behavior turns
* lazy again; this to deal with bursty apps that only use FPU for
* a short time
unsigned char fpu_counter;
unsigned int btrace_seq;
unsigned int policy;
cpumask_t cpus_allowed;
int rcu_read_lock_nesting;
char rcu_read_unlock_special;
struct rcu_node *rcu_blocked_node;
struct list_head rcu_node_entry;
#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
struct sched_info sched_info;
struct list_head tasks;
struct plist_node pushable_tasks;
struct mm_struct *mm, *active_mm;
struct task_rss_stat rss_stat;
/* task state */
int exit_state;
int exit_code, exit_signal;
int pdeath_signal; /* The signal sent when the parent dies */
/* ??? */
unsigned int personality;
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;
/* Canary value for the -fstack-protector gcc feature */
unsigned long stack_canary;
* pointers to (original) parent process, youngest child, younger sibling,
* older sibling, respectively. (p->father can be replaced with
* p->real_parent->pid)
struct task_struct *real_parent; /* real parent process */
struct task_struct *parent; /* recipient of SIGCHLD, wait4() reports */
* children/sibling forms the list of my natural children
struct list_head children; /* list of my children */
struct list_head sibling; /* linkage in my parent's children list */
struct task_struct *group_leader; /* threadgroup leader */
* ptraced is the list of tasks this task is using ptrace on.
* This includes both natural children and PTRACE_ATTACH targets.
* p->ptrace_entry is p's link on the p->parent->ptraced list.
struct list_head ptraced;
struct list_head ptrace_entry;
/* PID/PID hash table linkage. */
struct pid_link pids[PIDTYPE_MAX];
struct list_head thread_group;
struct completion *vfork_done; /* for vfork() */
int __user *set_child_tid; /* CLONE_CHILD_SETTID */
int __user *clear_child_tid; /* CLONE_CHILD_CLEARTID */
cputime_t utime, stime, utimescaled, stimescaled;
cputime_t gtime;
cputime_t prev_utime, prev_stime;
unsigned long nvcsw, nivcsw; /* context switch counts */
struct timespec start_time; /* monotonic time */
struct timespec real_start_time; /* boot based time */
/* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
unsigned long min_flt, maj_flt;
struct task_cputime cputime_expires;
struct list_head cpu_timers[3];
/* process credentials */
const struct cred *real_cred; /* objective and real subjective task
* credentials (COW) */
const struct cred *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 setup_new_exec */
/* file system info */
int link_count, total_link_count;
/* ipc stuff */
struct sysv_sem sysvsem;
/* hung task detection */
unsigned long last_switch_count;
/* CPU-specific state of this task */
struct thread_struct thread;
/* filesystem information */
struct fs_struct *fs;
/* open file information */
struct files_struct *files;
/* namespaces */
struct nsproxy *nsproxy;
/* signal handlers */
struct signal_struct *signal;
struct sighand_struct *sighand;
sigset_t blocked, real_blocked;
sigset_t saved_sigmask; /* restored if set_restore_sigmask() was used */
struct sigpending pending;
unsigned long sas_ss_sp;
size_t sas_ss_size;
int (*notifier)(void *priv);
void *notifier_data;
sigset_t *notifier_mask;
struct audit_context *audit_context;
uid_t loginuid;
unsigned int sessionid;
seccomp_t seccomp;
/* Thread group tracking */
u32 parent_exec_id;
u32 self_exec_id;
/* Protection of (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed,
* mempolicy */
spinlock_t alloc_lock;
/* IRQ handler threads */
struct irqaction *irqaction;
/* Protection of the PI data structures: */
raw_spinlock_t pi_lock;
/* PI waiters blocked on a rt_mutex held by this task */
struct plist_head pi_waiters;
/* Deadlock detection and priority inheritance handling */
struct rt_mutex_waiter *pi_blocked_on;
/* mutex deadlock detection */
struct mutex_waiter *blocked_on;
unsigned int irq_events;
unsigned long hardirq_enable_ip;
unsigned long hardirq_disable_ip;
unsigned int hardirq_enable_event;
unsigned int hardirq_disable_event;
int hardirqs_enabled;
int hardirq_context;
unsigned long softirq_disable_ip;
unsigned long softirq_enable_ip;
unsigned int softirq_disable_event;
unsigned int softirq_enable_event;
int softirqs_enabled;
int softirq_context;
# define MAX_LOCK_DEPTH 48UL
u64 curr_chain_key;
int lockdep_depth;
unsigned int lockdep_recursion;
struct held_lock held_locks[MAX_LOCK_DEPTH];
gfp_t lockdep_reclaim_gfp;
/* journalling filesystem info */
void *journal_info;
/* stacked block device info */
struct bio_list *bio_list;
/* VM state */
struct reclaim_state *reclaim_state;
struct backing_dev_info *backing_dev_info;
struct io_context *io_context;
unsigned long ptrace_message;
siginfo_t *last_siginfo; /* For ptrace use. */
struct task_io_accounting ioac;
#if defined(CONFIG_TASK_XACCT)
u64 acct_rss_mem1; /* accumulated rss usage */
u64 acct_vm_mem1; /* accumulated virtual memory usage */
cputime_t acct_timexpd; /* stime + utime since last update */
nodemask_t mems_allowed; /* Protected by alloc_lock */
int mems_allowed_change_disable;
int cpuset_mem_spread_rotor;
int cpuset_slab_spread_rotor;
/* Control Group info protected by css_set_lock */
struct css_set *cgroups;
/* cg_list protected by css_set_lock and tsk->alloc_lock */
struct list_head cg_list;
struct robust_list_head __user *robust_list;
struct compat_robust_list_head __user *compat_robust_list;
struct list_head pi_state_list;
struct futex_pi_state *pi_state_cache;
struct perf_event_context *perf_event_ctxp;
struct mutex perf_event_mutex;
struct list_head perf_event_list;
struct mempolicy *mempolicy; /* Protected by alloc_lock */
short il_next;
atomic_t fs_excl; /* holding fs exclusive resources */
struct rcu_head rcu;
* cache last used pipe for splice
struct pipe_inode_info *splice_pipe;
struct task_delay_info *delays;
int make_it_fail;
struct prop_local_single dirties;
int latency_record_count;
struct latency_record latency_record[LT_SAVECOUNT];
* time slack values; these are used to round up poll() and
* select() etc timeout values. These are in nanoseconds.
unsigned long timer_slack_ns;
unsigned long default_timer_slack_ns;
struct list_head *scm_work_list;
/* 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;
/* time stamp for last schedule */
unsigned long long ftrace_timestamp;
* Number of functions that haven't been traced
* because of depth overrun.
atomic_t trace_overrun;
/* Pause for the tracing */
atomic_t tracing_graph_pause;
/* state flags for use by tracers */
unsigned long trace;
/* 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;
/* Future-safe accessor for struct task_struct's cpus_allowed. */
#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
* Priority of a process goes from 0..MAX_PRIO-1, valid RT
* priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
* tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority
* values are inverted: lower p->prio value means higher priority.
* The MAX_USER_RT_PRIO value allows the actual maximum
* RT priority to be separate from the value exported to
* user-space. This allows kernel threads to set their
* priority to a value higher than any user task. Note:
* MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO.
#define MAX_USER_RT_PRIO 100
#define MAX_PRIO (MAX_RT_PRIO + 40)
static inline int rt_prio(int prio)
if (unlikely(prio < MAX_RT_PRIO))
return 1;
return 0;
static inline int rt_task(struct task_struct *p)
return rt_prio(p->prio);
static inline struct pid *task_pid(struct task_struct *task)
return task->pids[PIDTYPE_PID].pid;
static inline struct pid *task_tgid(struct task_struct *task)
return task->group_leader->pids[PIDTYPE_PID].pid;
* Without tasklist or rcu lock it is not safe to dereference
* the result of task_pgrp/task_session even if task == current,
* we can race with another thread doing sys_setsid/sys_setpgid.
static inline struct pid *task_pgrp(struct task_struct *task)
return task->group_leader->pids[PIDTYPE_PGID].pid;
static inline struct pid *task_session(struct task_struct *task)
return task->group_leader->pids[PIDTYPE_SID].pid;
struct pid_namespace;
* the helpers to get the task's different pids as they are seen
* from various namespaces
* task_xid_nr() : global id, i.e. the id seen from the init namespace;
* task_xid_vnr() : virtual id, i.e. the id seen from the pid namespace of
* current.
* task_xid_nr_ns() : id seen from the ns specified;
* set_task_vxid() : assigns a virtual id to a task;
* see also pid_nr() etc in include/linux/pid.h
pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
struct pid_namespace *ns);
static inline pid_t task_pid_nr(struct task_struct *tsk)
return tsk->pid;
static inline pid_t task_pid_nr_ns(struct task_struct *tsk,
struct pid_namespace *ns)
return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns);
static inline pid_t task_pid_vnr(struct task_struct *tsk)
return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL);
static inline pid_t task_tgid_nr(struct task_struct *tsk)
return tsk->tgid;
pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
static inline pid_t task_tgid_vnr(struct task_struct *tsk)
return pid_vnr(task_tgid(tsk));
static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk,
struct pid_namespace *ns)
return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns);
static inline pid_t task_pgrp_vnr(struct task_struct *tsk)
return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL);
static inline pid_t task_session_nr_ns(struct task_struct *tsk,
struct pid_namespace *ns)
return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns);
static inline pid_t task_session_vnr(struct task_struct *tsk)
return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL);
/* obsolete, do not use */
static inline pid_t task_pgrp_nr(struct task_struct *tsk)
return task_pgrp_nr_ns(tsk, &init_pid_ns);
* pid_alive - check that a task structure is not stale
* @p: Task structure to be checked.
* Test if a process is not yet dead (at most zombie state)
* If pid_alive fails, then pointers within the task structure
* can be stale and must not be dereferenced.
static inline int pid_alive(struct task_struct *p)
return p->pids[PIDTYPE_PID].pid != NULL;
* is_global_init - check if a task structure is init
* @tsk: Task structure to be checked.
* Check if a task structure is the first user space task the kernel created.
static inline int is_global_init(struct task_struct *tsk)
return tsk->pid == 1;
* is_container_init:
* check whether in the task is init in its own pid namespace.
extern int is_container_init(struct task_struct *tsk);
extern struct pid *cad_pid;
extern void free_task(struct task_struct *tsk);
static inline void free_thread_info(struct thread_info *ti)
if (!test_ti_thread_flag(ti, TIF_STACK_REPLACED))
free_pages((unsigned long)ti, THREAD_SIZE_ORDER);
#define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0)
extern void __put_task_struct(struct task_struct *t);
static inline void put_task_struct(struct task_struct *t)
if (atomic_dec_and_test(&t->usage))
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_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_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_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 */
#define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */
#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 */
#define PF_FREEZER_NOSIG 0x80000000 /* Freezer won't send signals to it */
* Only the _current_ task can read/write to tsk->flags, but other
* tasks can access tsk->flags in readonly mode for example
* with tsk_used_math (like during threaded core dumping).
* There is however an exception to this rule during ptrace
* or during fork: the ptracer task is allowed to write to the
* child->flags of its traced child (same goes for fork, the parent
* can write to the child->flags), because we're guaranteed the
* child is not running and in turn not changing child->flags
* at the same time the parent does it.
#define clear_stopped_child_used_math(child) do { (child)->flags &= ~PF_USED_MATH; } while (0)
#define set_stopped_child_used_math(child) do { (child)->flags |= PF_USED_MATH; } while (0)
#define clear_used_math() clear_stopped_child_used_math(current)
#define set_used_math() set_stopped_child_used_math(current)
#define conditional_stopped_child_used_math(condition, child) \
do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= (condition) ? PF_USED_MATH : 0; } while (0)
#define conditional_used_math(condition) \
conditional_stopped_child_used_math(condition, current)
#define copy_to_stopped_child_used_math(child) \
do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= current->flags & PF_USED_MATH; } while (0)
/* NOTE: this will return 0 or PF_USED_MATH, it will never return 1 */
#define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
#define used_math() tsk_used_math(current)
#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;
static inline void rcu_copy_process(struct task_struct *p)
extern int set_cpus_allowed_ptr(struct task_struct *p,
const struct cpumask *new_mask);
static inline int set_cpus_allowed_ptr(struct task_struct *p,
const struct cpumask *new_mask)
if (!cpumask_test_cpu(0, new_mask))
return -EINVAL;
return 0;
static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
return set_cpus_allowed_ptr(p, &new_mask);
* Architectures can set this to 1 if they have specified
* but then during bootup it turns out that sched_clock()
* is reliable after all:
extern int sched_clock_stable;
/* 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);
static inline void sched_clock_tick(void)
static inline void sched_clock_idle_sleep_event(void)
static inline void sched_clock_idle_wakeup_event(u64 delta_ns)
extern void sched_clock_tick(void);
extern void sched_clock_idle_sleep_event(void);
extern void sched_clock_idle_wakeup_event(u64 delta_ns);
* For kernel-internal use: high-speed (but slightly incorrect) per-cpu
* clock constructed from sched_clock():
extern unsigned long long cpu_clock(int cpu);
* 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 void enable_sched_clock_irqtime(void);
extern void disable_sched_clock_irqtime(void);
static inline void enable_sched_clock_irqtime(void) {}
static inline void disable_sched_clock_irqtime(void) {}
extern unsigned long long
task_sched_runtime(struct task_struct *task);
extern unsigned long long thread_group_sched_runtime(struct task_struct *task);
/* sched_exec is called by processes performing an exec */
extern void sched_exec(void);
#define sched_exec() {}
extern void sched_clock_idle_sleep_event(void);
extern void sched_clock_idle_wakeup_event(u64 delta_ns);
extern void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p);
extern void idle_task_exit(void);
static inline void idle_task_exit(void) {}
extern void sched_idle_next(void);
#if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP)
extern void wake_up_idle_cpu(int cpu);
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;
extern unsigned int sysctl_sched_child_runs_first;
enum sched_tunable_scaling {
extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;
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_proc_update_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length,
loff_t *ppos);
static inline unsigned int get_sysctl_timer_migration(void)
return sysctl_timer_migration;
static inline unsigned int get_sysctl_timer_migration(void)
return 1;
extern unsigned int sysctl_sched_rt_period;
extern int sysctl_sched_rt_runtime;
int sched_rt_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
extern unsigned int sysctl_sched_compat_yield;
extern int rt_mutex_getprio(struct task_struct *p);
extern void rt_mutex_setprio(struct task_struct *p, int prio);
extern void rt_mutex_adjust_pi(struct task_struct *p);
static inline int rt_mutex_getprio(struct task_struct *p)
return p->normal_prio;
# define rt_mutex_adjust_pi(p) do { } while (0)
extern void set_user_nice(struct task_struct *p, long nice);
extern int task_prio(const struct task_struct *p);
extern int task_nice(const struct task_struct *p);
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_nocheck(struct task_struct *, int,
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);
void yield(void);
* The default (Linux) execution domain.
extern struct exec_domain default_exec_domain;
union thread_union {
struct thread_info thread_info;
unsigned long stack[THREAD_SIZE/sizeof(long)];
static inline int kstack_end(void *addr)
/* Reliable end of stack detection:
* Some APM bios versions misalign the stack
return !(((unsigned long)addr+sizeof(void*)-1) & (THREAD_SIZE-sizeof(void*)));
extern union thread_union init_thread_union;
extern struct task_struct init_task;
extern struct mm_struct init_mm;
extern struct pid_namespace init_pid_ns;
* find a task by one of its numerical ids
* find_task_by_pid_ns():
* finds a task by its pid in the specified namespace
* find_task_by_vpid():
* finds a task by its virtual pid
* see also find_vpid() etc in include/linux/pid.h
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);
extern void __set_special_pids(struct pid *pid);
/* per-UID process charging. */
extern struct user_struct * alloc_uid(struct user_namespace *, uid_t);
static inline struct user_struct *get_uid(struct user_struct *u)
return u;
extern void free_uid(struct user_struct *);
extern void release_uids(struct user_namespace *ns);
#include <asm/current.h>
extern void do_timer(unsigned long ticks);
extern int wake_up_state(struct task_struct *tsk, unsigned int state);
extern int wake_up_process(struct task_struct *tsk);
extern void wake_up_new_task(struct task_struct *tsk,
unsigned long clone_flags);
extern void kick_process(struct task_struct *tsk);
static inline void kick_process(struct task_struct *tsk) { }
extern void sched_fork(struct task_struct *p, int clone_flags);
extern void sched_dead(struct task_struct *p);
extern void proc_caches_init(void);
extern void flush_signals(struct task_struct *);
extern void __flush_signals(struct task_struct *);
extern void ignore_signals(struct task_struct *);
extern void flush_signal_handlers(struct task_struct *, int force_default);
extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info);
static inline int dequeue_signal_lock(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
unsigned long flags;
int ret;
spin_lock_irqsave(&tsk->sighand->siglock, flags);
ret = dequeue_signal(tsk, mask, info);
spin_unlock_irqrestore(&tsk->sighand->siglock, flags);
return ret;
extern void block_all_signals(int (*notifier)(void *priv), void *priv,
sigset_t *mask);
extern void unblock_all_signals(void);
extern void release_task(struct task_struct * p);
extern int send_sig_info(int, struct siginfo *, struct task_struct *);
extern int force_sigsegv(int, struct task_struct *);
extern int force_sig_info(int, struct siginfo *, struct task_struct *);
extern int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp);
extern int kill_pid_info(int sig, struct siginfo *info, struct pid *pid);
extern int kill_pid_info_as_uid(int, struct siginfo *, struct pid *, uid_t, uid_t, u32);
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 int send_sig(int, struct task_struct *, int);
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);
extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
extern int do_sigaltstack(const stack_t __user *, stack_t __user *, unsigned long);
static inline int kill_cad_pid(int sig, int priv)
return kill_pid(cad_pid, sig, priv);
/* These can be the second arg to send_sig_info/send_group_sig_info. */
#define SEND_SIG_NOINFO ((struct siginfo *) 0)
#define SEND_SIG_PRIV ((struct siginfo *) 1)
#define SEND_SIG_FORCED ((struct siginfo *) 2)
* True if we are on the alternate signal stack.
static inline int on_sig_stack(unsigned long sp)
return sp >= current->sas_ss_sp &&
sp - current->sas_ss_sp < current->sas_ss_size;
return sp > current->sas_ss_sp &&
sp - current->sas_ss_sp <= current->sas_ss_size;
static inline int sas_ss_flags(unsigned long sp)
return (current->sas_ss_size == 0 ? SS_DISABLE
: on_sig_stack(sp) ? SS_ONSTACK : 0);
* Routines for handling mm_structs
extern struct mm_struct * mm_alloc(void);
/* mmdrop drops the mm and the page tables */
extern void __mmdrop(struct mm_struct *);
static inline void mmdrop(struct mm_struct * mm)
if (unlikely(atomic_dec_and_test(&mm->mm_count)))
/* mmput gets rid of the mappings and all user-space */
extern void mmput(struct mm_struct *);
/* Grab a reference to a task's mm, if it is not already going away */
extern struct mm_struct *get_task_mm(struct task_struct *task);
/* Remove the current tasks stale references to the old mm_struct */
extern void mm_release(struct task_struct *, struct mm_struct *);
/* Allocate a new mm structure and copy contents from tsk->mm */
extern struct mm_struct *dup_mm(struct task_struct *tsk);
extern int copy_thread(unsigned long, unsigned long, unsigned long,
struct task_struct *, struct pt_regs *);
extern void flush_thread(void);
extern void exit_thread(void);
extern void exit_files(struct task_struct *);
extern void __cleanup_sighand(struct sighand_struct *);
extern void exit_itimers(struct signal_struct *);
extern void flush_itimer_signals(void);
extern NORET_TYPE void do_group_exit(int);
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 long do_fork(unsigned long, unsigned long, struct pt_regs *, unsigned long, int __user *, int __user *);
struct task_struct *fork_idle(int);
extern void set_task_comm(struct task_struct *tsk, char *from);
extern char *get_task_comm(char *to, struct task_struct *tsk);
extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
static inline unsigned long wait_task_inactive(struct task_struct *p,
long match_state)
return 1;
#define next_task(p) \
list_entry_rcu((p)->, struct task_struct, tasks)
#define for_each_process(p) \
for (p = &init_task ; (p = next_task(p)) != &init_task ; )
extern bool current_is_single_threaded(void);
* Careful: do_each_thread/while_each_thread is a double loop so
* 'break' will not work as expected - use goto instead.
#define do_each_thread(g, t) \
for (g = t = &init_task ; (g = t = next_task(g)) != &init_task ; ) do
#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)
/* Do to the insanities of de_thread it is possible for a process
* to have the pid of the thread group leader without actually being
* the thread group leader. For iteration through the pids in proc
* all we care about is that we have a task with the appropriate
* pid, we don't actually care if we have the right task.
static inline int has_group_leader_pid(struct task_struct *p)
return p->pid == p->tgid;
static inline
int same_thread_group(struct task_struct *p1, struct task_struct *p2)
return p1->tgid == p2->tgid;
static inline struct task_struct *next_thread(const struct task_struct *p)
return list_entry_rcu(p->,
struct task_struct, thread_group);
static inline int thread_group_empty(struct task_struct *p)
return list_empty(&p->thread_group);
#define delay_group_leader(p) \
(thread_group_leader(p) && !thread_group_empty(p))
static inline int task_detached(struct task_struct *p)
return p->exit_signal == -1;
* Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
* subscriptions and synchronises with wait4(). Also used in procfs. Also
* pins the final release of task.io_context. Also protects ->cpuset and
* ->cgroup.subsys[].
* Nests both inside and outside of read_lock(&tasklist_lock).
* It must not be nested with write_lock_irq(&tasklist_lock),
* neither inside nor outside.
static inline void task_lock(struct task_struct *p)
static inline void task_unlock(struct task_struct *p)
extern struct sighand_struct *lock_task_sighand(struct task_struct *tsk,
unsigned long *flags);
static inline void unlock_task_sighand(struct task_struct *tsk,
unsigned long *flags)
spin_unlock_irqrestore(&tsk->sighand->siglock, *flags);
#define task_thread_info(task) ((struct thread_info *)(task)->stack)
#define task_stack_page(task) ((task)->stack)
* Replace the stack of 'task' with a new stack, freeing the old stack.
* This should only be called before a task has started executing. The new
* stack will not be freed when the task quits; it is the responsibility of
* the calling code to free the new stack once the task has completed.
void replace_stack(struct task_struct *task, void *new_stack);
static inline void setup_thread_stack(struct task_struct *p, struct task_struct *org)
*task_thread_info(p) = *task_thread_info(org);
task_thread_info(p)->task = p;
static inline unsigned long *end_of_stack(struct task_struct *p)
return (unsigned long *)(task_thread_info(p) + 1);
static inline int object_is_on_stack(void *obj)
void *stack = task_stack_page(current);
return (obj >= stack) && (obj < (stack + THREAD_SIZE));
extern void thread_info_cache_init(void);
static inline unsigned long stack_not_used(struct task_struct *p)
unsigned long *n = end_of_stack(p);
do { /* Skip over canary */
} while (!*n);
return (unsigned long)n - (unsigned long)end_of_stack(p);
/* set thread flags in other task's structures
* - see asm/thread_info.h for TIF_xxxx flags available
static inline void set_tsk_thread_flag(struct task_struct *tsk, int flag)
set_ti_thread_flag(task_thread_info(tsk), flag);
static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag)
clear_ti_thread_flag(task_thread_info(tsk), flag);
static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag)
return test_and_set_ti_thread_flag(task_thread_info(tsk), flag);
static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag)
return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag);
static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag)
return test_ti_thread_flag(task_thread_info(tsk), flag);
static inline void set_tsk_need_resched(struct task_struct *tsk)
static inline void clear_tsk_need_resched(struct task_struct *tsk)
static inline int test_tsk_need_resched(struct task_struct *tsk)
return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED));
static inline int restart_syscall(void)
set_tsk_thread_flag(current, TIF_SIGPENDING);
static inline int signal_pending(struct task_struct *p)
return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
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)
return signal_pending(p) && __fatal_signal_pending(p);
static inline int signal_pending_state(long state, struct task_struct *p)
return 0;
if (!signal_pending(p))
return 0;
return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p);
static inline int need_resched(void)
return unlikely(test_thread_flag(TIF_NEED_RESCHED));
* cond_resched() and cond_resched_lock(): latency reduction via
* explicit rescheduling in places that are safe. The return
* value indicates whether a reschedule was done in fact.
* cond_resched_lock() will drop the spinlock before scheduling,
* cond_resched_softirq() will enable bhs before scheduling.
extern int _cond_resched(void);
#define cond_resched() ({ \
__might_sleep(__FILE__, __LINE__, 0); \
_cond_resched(); \
extern int __cond_resched_lock(spinlock_t *lock);
#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
* task waiting?: (technically does not depend on CONFIG_PREEMPT,
* but a general need for low latency)
static inline int spin_needbreak(spinlock_t *lock)
return spin_is_contended(lock);
return 0;
* Thread group CPU time accounting.
void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times);
void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
static inline void thread_group_cputime_init(struct signal_struct *sig)
* Reevaluate whether the task has signals pending delivery.
* Wake the task if so.
* This is required every time the blocked sigset_t changes.
* callers must hold sighand->siglock.
extern void recalc_sigpending_and_wake(struct task_struct *t);
extern void recalc_sigpending(void);
extern void signal_wake_up(struct task_struct *t, int resume_stopped);
* Wrappers for p->thread_info->cpu access. No-op on UP.
static inline unsigned int task_cpu(const struct task_struct *p)
return task_thread_info(p)->cpu;
extern void set_task_cpu(struct task_struct *p, unsigned int cpu);
static inline unsigned int task_cpu(const struct task_struct *p)
return 0;
static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
#endif /* CONFIG_SMP */
extern void
__trace_special(void *__tr, void *__data,
unsigned long arg1, unsigned long arg2, unsigned long arg3);
static inline void
__trace_special(void *__tr, void *__data,
unsigned long arg1, unsigned long arg2, unsigned long arg3)
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);
extern struct task_group init_task_group;
extern struct task_group *sched_create_group(struct task_group *parent);
extern void sched_destroy_group(struct task_group *tg);
extern void sched_move_task(struct task_struct *tsk);
extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
extern unsigned long sched_group_shares(struct task_group *tg);
extern int sched_group_set_rt_runtime(struct task_group *tg,
long rt_runtime_us);
extern long sched_group_rt_runtime(struct task_group *tg);
extern int sched_group_set_rt_period(struct task_group *tg,
long rt_period_us);
extern long sched_group_rt_period(struct task_group *tg);
extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk);
extern int task_can_switch_user(struct user_struct *up,
struct task_struct *tsk);
static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
tsk->ioac.rchar += amt;
static inline void add_wchar(struct task_struct *tsk, ssize_t amt)
tsk->ioac.wchar += amt;
static inline void inc_syscr(struct task_struct *tsk)
static inline void inc_syscw(struct task_struct *tsk)
static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
static inline void add_wchar(struct task_struct *tsk, ssize_t amt)
static inline void inc_syscr(struct task_struct *tsk)
static inline void inc_syscw(struct task_struct *tsk)
#ifndef TASK_SIZE_OF
* Call the function if the target task is executing on a CPU right now:
extern void task_oncpu_function_call(struct task_struct *p,
void (*func) (void *info), void *info);
extern void mm_update_next_owner(struct mm_struct *mm);
extern void mm_init_owner(struct mm_struct *mm, struct task_struct *p);
static inline void mm_update_next_owner(struct mm_struct *mm)
static inline void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
#endif /* CONFIG_MM_OWNER */
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__ */