blob: 253538f29ade890dcd48d1708fcd15ae362653be [file] [log] [blame]
#ifndef _LINUX_SCHED_H
#define _LINUX_SCHED_H
#include <uapi/linux/sched.h>
#include <linux/sched/prio.h>
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/plist.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 <linux/preempt.h>
#include <asm/page.h>
#include <asm/ptrace.h>
#include <linux/cputime.h>
#include <linux/smp.h>
#include <linux/sem.h>
#include <linux/shm.h>
#include <linux/signal.h>
#include <linux/compiler.h>
#include <linux/completion.h>
#include <linux/pid.h>
#include <linux/percpu.h>
#include <linux/topology.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/kcov.h>
#include <linux/task_io_accounting.h>
#include <linux/latencytop.h>
#include <linux/cred.h>
#include <linux/llist.h>
#include <linux/uidgid.h>
#include <linux/gfp.h>
#include <linux/magic.h>
#include <linux/cgroup-defs.h>
#include <asm/processor.h>
#define SCHED_ATTR_SIZE_VER0 48 /* sizeof first published struct */
* Extended scheduling parameters data structure.
* This is needed because the original struct sched_param can not be
* altered without introducing ABI issues with legacy applications
* (e.g., in sched_getparam()).
* However, the possibility of specifying more than just a priority for
* the tasks may be useful for a wide variety of application fields, e.g.,
* multimedia, streaming, automation and control, and many others.
* This variant (sched_attr) is meant at describing a so-called
* sporadic time-constrained task. In such model a task is specified by:
* - the activation period or minimum instance inter-arrival time;
* - the maximum (or average, depending on the actual scheduling
* discipline) computation time of all instances, a.k.a. runtime;
* - the deadline (relative to the actual activation time) of each
* instance.
* Very briefly, a periodic (sporadic) task asks for the execution of
* some specific computation --which is typically called an instance--
* (at most) every period. Moreover, each instance typically lasts no more
* than the runtime and must be completed by time instant t equal to
* the instance activation time + the deadline.
* This is reflected by the actual fields of the sched_attr structure:
* @size size of the structure, for fwd/bwd compat.
* @sched_policy task's scheduling policy
* @sched_flags for customizing the scheduler behaviour
* @sched_nice task's nice value (SCHED_NORMAL/BATCH)
* @sched_priority task's static priority (SCHED_FIFO/RR)
* @sched_deadline representative of the task's deadline
* @sched_runtime representative of the task's runtime
* @sched_period representative of the task's period
* Given this task model, there are a multiplicity of scheduling algorithms
* and policies, that can be used to ensure all the tasks will make their
* timing constraints.
* As of now, the SCHED_DEADLINE policy (sched_dl scheduling class) is the
* only user of this new interface. More information about the algorithm
* available in the scheduling class file or in Documentation/.
struct sched_attr {
u32 size;
u32 sched_policy;
u64 sched_flags;
s32 sched_nice;
u32 sched_priority;
u64 sched_runtime;
u64 sched_deadline;
u64 sched_period;
struct futex_pi_state;
struct robust_list_head;
struct bio_list;
struct fs_struct;
struct perf_event_context;
struct blk_plug;
struct filename;
struct nameidata;
* 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 bool single_task_running(void);
extern unsigned long nr_iowait(void);
extern unsigned long nr_iowait_cpu(int cpu);
extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load);
extern void calc_global_load(unsigned long ticks);
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
extern void cpu_load_update_nohz_start(void);
extern void cpu_load_update_nohz_stop(void);
static inline void cpu_load_update_nohz_start(void) { }
static inline void cpu_load_update_nohz_stop(void) { }
extern void dump_cpu_task(int cpu);
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);
* 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_DEAD 16
#define EXIT_ZOMBIE 32
/* in tsk->state again */
#define TASK_DEAD 64
#define TASK_WAKEKILL 128
#define TASK_WAKING 256
#define TASK_PARKED 512
#define TASK_NOLOAD 1024
#define TASK_STATE_MAX 2048
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_stopped_or_traced(task) \
((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
#define task_contributes_to_load(task) \
((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
(task->flags & PF_FROZEN) == 0 && \
(task->state & TASK_NOLOAD) == 0)
#define __set_task_state(tsk, state_value) \
do { \
(tsk)->task_state_change = _THIS_IP_; \
(tsk)->state = (state_value); \
} while (0)
#define set_task_state(tsk, state_value) \
do { \
(tsk)->task_state_change = _THIS_IP_; \
smp_store_mb((tsk)->state, (state_value)); \
} while (0)
* set_current_state() includes a barrier so that the write of current->state
* is correctly serialised wrt the caller's subsequent test of whether to
* actually sleep:
* set_current_state(TASK_UNINTERRUPTIBLE);
* if (do_i_need_to_sleep())
* schedule();
* If the caller does not need such serialisation then use __set_current_state()
#define __set_current_state(state_value) \
do { \
current->task_state_change = _THIS_IP_; \
current->state = (state_value); \
} while (0)
#define set_current_state(state_value) \
do { \
current->task_state_change = _THIS_IP_; \
smp_store_mb(current->state, (state_value)); \
} while (0)
#define __set_task_state(tsk, state_value) \
do { (tsk)->state = (state_value); } while (0)
#define set_task_state(tsk, state_value) \
smp_store_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) \
smp_store_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 cpumask_var_t cpu_isolated_map;
extern int runqueue_is_locked(int cpu);
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
extern void nohz_balance_enter_idle(int cpu);
extern void set_cpu_sd_state_idle(void);
extern int get_nohz_timer_target(void);
static inline void nohz_balance_enter_idle(int cpu) { }
static inline void set_cpu_sd_state_idle(void) { }
* 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);
extern void cpu_init (void);
extern void trap_init(void);
extern void update_process_times(int user);
extern void scheduler_tick(void);
extern int sched_cpu_starting(unsigned int cpu);
extern int sched_cpu_activate(unsigned int cpu);
extern int sched_cpu_deactivate(unsigned int cpu);
extern int sched_cpu_dying(unsigned int cpu);
# define sched_cpu_dying NULL
extern void sched_show_task(struct task_struct *p);
extern void touch_softlockup_watchdog_sched(void);
extern void touch_softlockup_watchdog(void);
extern void touch_softlockup_watchdog_sync(void);
extern void touch_all_softlockup_watchdogs(void);
extern int proc_dowatchdog_thresh(struct ctl_table *table, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos);
extern unsigned int softlockup_panic;
extern unsigned int hardlockup_panic;
void lockup_detector_init(void);
static inline void touch_softlockup_watchdog_sched(void)
static inline void touch_softlockup_watchdog(void)
static inline void touch_softlockup_watchdog_sync(void)
static inline void touch_all_softlockup_watchdogs(void)
static inline void lockup_detector_init(void)
void reset_hung_task_detector(void);
static inline void reset_hung_task_detector(void)
/* 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);
extern signed long schedule_timeout_idle(signed long timeout);
asmlinkage void schedule(void);
extern void schedule_preempt_disabled(void);
extern long io_schedule_timeout(long timeout);
static inline void io_schedule(void)
struct nsproxy;
struct user_namespace;
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);
static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
#define SUID_DUMP_DISABLE 0 /* No setuid dumping */
#define SUID_DUMP_USER 1 /* Dump as user of process */
#define SUID_DUMP_ROOT 2 /* Dump as root */
/* mm flags */
/* for SUID_DUMP_* above */
extern void set_dumpable(struct mm_struct *mm, int value);
* This returns the actual value of the suid_dumpable flag. For things
* that are using this for checking for privilege transitions, it must
* test against SUID_DUMP_USER rather than treating it as a boolean
* value.
static inline int __get_dumpable(unsigned long mm_flags)
return mm_flags & MMF_DUMPABLE_MASK;
static inline int get_dumpable(struct mm_struct *mm)
return __get_dumpable(mm->flags);
/* coredump filter bits */
/* leave room for more dump flags */
#define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */
#define MMF_VM_HUGEPAGE 17 /* set when VM_HUGEPAGE is set on vma */
#define MMF_EXE_FILE_CHANGED 18 /* see prctl_set_mm_exe_file() */
#define MMF_HAS_UPROBES 19 /* has uprobes */
#define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */
#define MMF_OOM_REAPED 21 /* mm has been already reaped */
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 prev_cputime - snaphsot of system and user cputime
* @utime: time spent in user mode
* @stime: time spent in system mode
* @lock: protects the above two fields
* Stores previous user/system time values such that we can guarantee
* monotonicity.
struct prev_cputime {
cputime_t utime;
cputime_t stime;
raw_spinlock_t lock;
static inline void prev_cputime_init(struct prev_cputime *prev)
prev->utime = prev->stime = 0;
* 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 virt_exp utime
#define prof_exp stime
#define sched_exp sum_exec_runtime
#define INIT_CPUTIME \
(struct task_cputime) { \
.utime = 0, \
.stime = 0, \
.sum_exec_runtime = 0, \
* This is the atomic variant of task_cputime, which can be used for
* storing and updating task_cputime statistics without locking.
struct task_cputime_atomic {
atomic64_t utime;
atomic64_t stime;
atomic64_t sum_exec_runtime;
(struct task_cputime_atomic) { \
.utime = ATOMIC64_INIT(0), \
.stime = ATOMIC64_INIT(0), \
.sum_exec_runtime = ATOMIC64_INIT(0), \
* Disable preemption until the scheduler is running -- use an unconditional
* value so that it also works on !PREEMPT_COUNT kernels.
* Reset by start_kernel()->sched_init()->init_idle()->init_idle_preempt_count().
* Initial preempt_count value; reflects the preempt_count schedule invariant
* which states that during context switches:
* preempt_count() == 2*PREEMPT_DISABLE_OFFSET
* Note: See finish_task_switch().
* struct thread_group_cputimer - thread group interval timer counts
* @cputime_atomic: atomic thread group interval timers.
* @running: true when there are timers running and
* @cputime_atomic receives updates.
* @checking_timer: true when a thread in the group is in the
* process of checking for thread group timers.
* 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_atomic cputime_atomic;
bool running;
bool checking_timer;
#include <linux/rwsem.h>
struct autogroup;
* NOTE! "signal_struct" does not have its 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;
atomic_t oom_victims; /* # of TIF_MEDIE threads in this thread group */
struct list_head thread_head;
wait_queue_head_t wait_chldexit; /* for wait4() */
/* 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 */
* PR_SET_CHILD_SUBREAPER marks a process, like a service
* manager, to re-parent orphan (double-forking) child processes
* to this process instead of 'init'. The service manager is
* able to receive SIGCHLD signals and is able to investigate
* the process until it calls wait(). All children of this
* process will inherit a flag if they should look for a
* child_subreaper process at exit.
unsigned int is_child_subreaper:1;
unsigned int has_child_subreaper:1;
/* POSIX.1b Interval Timers */
int posix_timer_id;
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;
atomic_t tick_dep_mask;
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 */
struct autogroup *autogroup;
* 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.
seqlock_t stats_lock;
cputime_t utime, stime, cutime, cstime;
cputime_t gtime;
cputime_t cgtime;
struct prev_cputime prev_cputime;
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;
* Thread is the potential origin of an oom condition; kill first on
* oom
bool oom_flag_origin;
short oom_score_adj; /* OOM kill score adjustment */
short oom_score_adj_min; /* OOM kill score adjustment min value.
* Only settable by CAP_SYS_RESOURCE. */
struct mutex cred_guard_mutex; /* guard against foreign influences on
* credential calculations
* (notably. ptrace) */
* Bits in flags field of signal_struct.
#define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */
#define SIGNAL_STOP_CONTINUED 0x00000002 /* SIGCONT since WCONTINUED reap */
#define SIGNAL_GROUP_EXIT 0x00000004 /* group exit in progress */
#define SIGNAL_GROUP_COREDUMP 0x00000008 /* coredump 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 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 fanotify_listeners;
atomic_long_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 ? */
unsigned long unix_inflight; /* How many files in flight in unix sockets */
atomic_long_t pipe_bufs; /* how many pages are allocated in pipe buffers */
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;
kuid_t uid;
atomic_long_t locked_vm;
extern int uids_sysfs_init(void);
extern struct user_struct *find_user(kuid_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 */
#endif /* CONFIG_SCHED_INFO */
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.
u64 blkio_start; /* 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 */
u64 freepages_start;
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;
void force_schedstat_enabled(void);
enum cpu_idle_type {
* Integer metrics need fixed point arithmetic, e.g., sched/fair
* has a few: load, load_avg, util_avg, freq, and capacity.
* We define a basic fixed point arithmetic range, and then formalize
* all these metrics based on that basic range.
* Increase resolution of cpu_capacity calculations
* Wake-queues are lists of tasks with a pending wakeup, whose
* callers have already marked the task as woken internally,
* and can thus carry on. A common use case is being able to
* do the wakeups once the corresponding user lock as been
* released.
* We hold reference to each task in the list across the wakeup,
* thus guaranteeing that the memory is still valid by the time
* the actual wakeups are performed in wake_up_q().
* One per task suffices, because there's never a need for a task to be
* in two wake queues simultaneously; it is forbidden to abandon a task
* in a wake queue (a call to wake_up_q() _must_ follow), so if a task is
* already in a wake queue, the wakeup will happen soon and the second
* waker can just skip it.
* The WAKE_Q macro declares and initializes the list head.
* wake_up_q() does NOT reinitialize the list; it's expected to be
* called near the end of a function, where the fact that the queue is
* not used again will be easy to see by inspection.
* Note that this can cause spurious wakeups. schedule() callers
* must ensure the call is done inside a loop, confirming that the
* wakeup condition has in fact occurred.
struct wake_q_node {
struct wake_q_node *next;
struct wake_q_head {
struct wake_q_node *first;
struct wake_q_node **lastp;
#define WAKE_Q_TAIL ((struct wake_q_node *) 0x01)
#define WAKE_Q(name) \
struct wake_q_head name = { WAKE_Q_TAIL, &name.first }
extern void wake_q_add(struct wake_q_head *head,
struct task_struct *task);
extern void wake_up_q(struct wake_q_head *head);
* sched-domains (multiprocessor balancing) declarations:
#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_SHARE_CPUCAPACITY 0x0080 /* Domain members share cpu power */
#define SD_SHARE_POWERDOMAIN 0x0100 /* Domain members share power domain */
#define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share cpu pkg resources */
#define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */
#define SD_ASYM_PACKING 0x0800 /* Place busy groups earlier in the domain */
#define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */
#define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */
#define SD_NUMA 0x4000 /* cross-node balancing */
static inline int cpu_smt_flags(void)
static inline int cpu_core_flags(void)
static inline int cpu_numa_flags(void)
return SD_NUMA;
struct sched_domain_attr {
int relax_domain_level;
#define SD_ATTR_INIT (struct sched_domain_attr) { \
.relax_domain_level = -1, \
extern int sched_domain_level_max;
struct sched_group;
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 nohz_idle; /* NOHZ IDLE status */
int flags; /* See SD_* */
int 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 */
/* idle_balance() stats */
u64 max_newidle_lb_cost;
unsigned long next_decay_max_lb_cost;
/* 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;
union {
void *private; /* used during construction */
struct rcu_head rcu; /* used during destruction */
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)
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);
bool cpus_share_cache(int this_cpu, int that_cpu);
typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
typedef int (*sched_domain_flags_f)(void);
#define SDTL_OVERLAP 0x01
struct sd_data {
struct sched_domain **__percpu sd;
struct sched_group **__percpu sg;
struct sched_group_capacity **__percpu sgc;
struct sched_domain_topology_level {
sched_domain_mask_f mask;
sched_domain_flags_f sd_flags;
int flags;
int numa_level;
struct sd_data data;
char *name;
extern void set_sched_topology(struct sched_domain_topology_level *tl);
extern void wake_up_if_idle(int cpu);
# define SD_INIT_NAME(type) .name = #type
# define SD_INIT_NAME(type)
#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)
static inline bool cpus_share_cache(int this_cpu, int that_cpu)
return true;
#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 load_weight {
unsigned long weight;
u32 inv_weight;
* The load_avg/util_avg accumulates an infinite geometric series
* (see __update_load_avg() in kernel/sched/fair.c).
* [load_avg definition]
* load_avg = runnable% * scale_load_down(load)
* where runnable% is the time ratio that a sched_entity is runnable.
* For cfs_rq, it is the aggregated load_avg of all runnable and
* blocked sched_entities.
* load_avg may also take frequency scaling into account:
* load_avg = runnable% * scale_load_down(load) * freq%
* where freq% is the CPU frequency normalized to the highest frequency.
* [util_avg definition]
* util_avg = running% * SCHED_CAPACITY_SCALE
* where running% is the time ratio that a sched_entity is running on
* a CPU. For cfs_rq, it is the aggregated util_avg of all runnable
* and blocked sched_entities.
* util_avg may also factor frequency scaling and CPU capacity scaling:
* util_avg = running% * SCHED_CAPACITY_SCALE * freq% * capacity%
* where freq% is the same as above, and capacity% is the CPU capacity
* normalized to the greatest capacity (due to uarch differences, etc).
* N.B., the above ratios (runnable%, running%, freq%, and capacity%)
* themselves are in the range of [0, 1]. To do fixed point arithmetics,
* we therefore scale them to as large a range as necessary. This is for
* example reflected by util_avg's SCHED_CAPACITY_SCALE.
* [Overflow issue]
* The 64-bit load_sum can have 4353082796 (=2^64/47742/88761) entities
* with the highest load (=88761), always runnable on a single cfs_rq,
* and should not overflow as the number already hits PID_MAX_LIMIT.
* For all other cases (including 32-bit kernels), struct load_weight's
* weight will overflow first before we do, because:
* Max(load_avg) <= Max(load.weight)
* Then it is the load_weight's responsibility to consider overflow
* issues.
struct sched_avg {
u64 last_update_time, load_sum;
u32 util_sum, period_contrib;
unsigned long load_avg, util_avg;
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;
int depth;
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;
* Per entity load average tracking.
* Put into separate cache line so it does not
* collide with read-mostly values above.
struct sched_avg avg ____cacheline_aligned_in_smp;
struct sched_rt_entity {
struct list_head run_list;
unsigned long timeout;
unsigned long watchdog_stamp;
unsigned int time_slice;
unsigned short on_rq;
unsigned short on_list;
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 sched_dl_entity {
struct rb_node rb_node;
* Original scheduling parameters. Copied here from sched_attr
* during sched_setattr(), they will remain the same until
* the next sched_setattr().
u64 dl_runtime; /* maximum runtime for each instance */
u64 dl_deadline; /* relative deadline of each instance */
u64 dl_period; /* separation of two instances (period) */
u64 dl_bw; /* dl_runtime / dl_deadline */
* Actual scheduling parameters. Initialized with the values above,
* they are continously updated during task execution. Note that
* the remaining runtime could be < 0 in case we are in overrun.
s64 runtime; /* remaining runtime for this instance */
u64 deadline; /* absolute deadline for this instance */
unsigned int flags; /* specifying the scheduler behaviour */
* Some bool flags:
* @dl_throttled tells if we exhausted the runtime. If so, the
* task has to wait for a replenishment to be performed at the
* next firing of dl_timer.
* @dl_boosted tells if we are boosted due to DI. If so we are
* outside bandwidth enforcement mechanism (but only until we
* exit the critical section);
* @dl_yielded tells if task gave up the cpu before consuming
* all its available runtime during the last job.
int dl_throttled, dl_boosted, dl_yielded;
* Bandwidth enforcement timer. Each -deadline task has its
* own bandwidth to be enforced, thus we need one timer per task.
struct hrtimer dl_timer;
union rcu_special {
struct {
u8 blocked;
u8 need_qs;
u8 exp_need_qs;
u8 pad; /* Otherwise the compiler can store garbage here. */
} b; /* Bits. */
u32 s; /* Set of bits. */
struct rcu_node;
enum perf_event_task_context {
perf_invalid_context = -1,
perf_hw_context = 0,
/* Track pages that require TLB flushes */
struct tlbflush_unmap_batch {
* Each bit set is a CPU that potentially has a TLB entry for one of
* the PFNs being flushed. See set_tlb_ubc_flush_pending().
struct cpumask cpumask;
/* True if any bit in cpumask is set */
bool flush_required;
* If true then the PTE was dirty when unmapped. The entry must be
* flushed before IO is initiated or a stale TLB entry potentially
* allows an update without redirtying the page.
bool writable;
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;
struct llist_node wake_entry;
int on_cpu;
unsigned int wakee_flips;
unsigned long wakee_flip_decay_ts;
struct task_struct *last_wakee;
int wake_cpu;
int on_rq;
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;
struct task_group *sched_task_group;
struct sched_dl_entity dl;
/* list of struct preempt_notifier: */
struct hlist_head preempt_notifiers;
unsigned int btrace_seq;
unsigned int policy;
int nr_cpus_allowed;
cpumask_t cpus_allowed;
int rcu_read_lock_nesting;
union rcu_special rcu_read_unlock_special;
struct list_head rcu_node_entry;
struct rcu_node *rcu_blocked_node;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
unsigned long rcu_tasks_nvcsw;
bool rcu_tasks_holdout;
struct list_head rcu_tasks_holdout_list;
int rcu_tasks_idle_cpu;
#endif /* #ifdef CONFIG_TASKS_RCU */
struct sched_info sched_info;
struct list_head tasks;
struct plist_node pushable_tasks;
struct rb_node pushable_dl_tasks;
struct mm_struct *mm, *active_mm;
/* per-thread vma caching */
u32 vmacache_seqnum;
struct vm_area_struct *vmacache[VMACACHE_SIZE];
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 long jobctl; /* JOBCTL_*, siglock protected */
/* Used for emulating ABI behavior of previous Linux versions */
unsigned int personality;
/* scheduler bits, serialized by scheduler locks */
unsigned sched_reset_on_fork:1;
unsigned sched_contributes_to_load:1;
unsigned sched_migrated:1;
unsigned sched_remote_wakeup:1;
unsigned :0; /* force alignment to the next boundary */
/* unserialized, strictly 'current' */
unsigned in_execve:1; /* bit to tell LSMs we're in execve */
unsigned in_iowait:1;
unsigned memcg_may_oom:1;
unsigned memcg_kmem_skip_account:1;
unsigned brk_randomized:1;
unsigned long atomic_flags; /* Flags needing atomic access. */
struct restart_block restart_block;
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 __rcu *real_parent; /* real parent process */
struct task_struct __rcu *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 list_head thread_node;
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;
struct prev_cputime prev_cputime;
seqcount_t vtime_seqcount;
unsigned long long vtime_snap;
enum {
/* Task is sleeping or running in a CPU with VTIME inactive */
/* Task runs in userspace in a CPU with VTIME active */
/* Task runs in kernelspace in a CPU with VTIME active */
} vtime_snap_whence;
atomic_t tick_dep_mask;
unsigned long nvcsw, nivcsw; /* context switch counts */
u64 start_time; /* monotonic time in nsec */
u64 real_start_time; /* boot based time in nsec */
/* 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 __rcu *real_cred; /* objective and real subjective task
* credentials (COW) */
const struct cred __rcu *cred; /* effective (overridable) subjective task
* credentials (COW) */
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 */
struct nameidata *nameidata;
/* ipc stuff */
struct sysv_sem sysvsem;
struct sysv_shm sysvshm;
/* hung task detection */
unsigned long last_switch_count;
/* 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;
unsigned sas_ss_flags;
struct callback_head *task_works;
struct audit_context *audit_context;
kuid_t loginuid;
unsigned int sessionid;
struct seccomp 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;
/* Protection of the PI data structures: */
raw_spinlock_t pi_lock;
struct wake_q_node wake_q;
/* PI waiters blocked on a rt_mutex held by this task */
struct rb_root pi_waiters;
struct rb_node *pi_waiters_leftmost;
/* 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;
unsigned int in_ubsan;
/* journalling filesystem info */
void *journal_info;
/* stacked block device info */
struct bio_list *bio_list;
/* stack plugging */
struct blk_plug *plug;
/* 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 */
seqcount_t mems_allowed_seq; /* Seqence no to catch updates */
int cpuset_mem_spread_rotor;
int cpuset_slab_spread_rotor;
/* Control Group info protected by css_set_lock */
struct css_set __rcu *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[perf_nr_task_contexts];
struct mutex perf_event_mutex;
struct list_head perf_event_list;
unsigned long preempt_disable_ip;
struct mempolicy *mempolicy; /* Protected by alloc_lock */
short il_next;
short pref_node_fork;
int numa_scan_seq;
unsigned int numa_scan_period;
unsigned int numa_scan_period_max;
int numa_preferred_nid;
unsigned long numa_migrate_retry;
u64 node_stamp; /* migration stamp */
u64 last_task_numa_placement;
u64 last_sum_exec_runtime;
struct callback_head numa_work;
struct list_head numa_entry;
struct numa_group *numa_group;
* numa_faults is an array split into four regions:
* faults_memory, faults_cpu, faults_memory_buffer, faults_cpu_buffer
* in this precise order.
* faults_memory: Exponential decaying average of faults on a per-node
* basis. Scheduling placement decisions are made based on these
* counts. The values remain static for the duration of a PTE scan.
* faults_cpu: Track the nodes the process was running on when a NUMA
* hinting fault was incurred.
* faults_memory_buffer and faults_cpu_buffer: Record faults per node
* during the current scan window. When the scan completes, the counts
* in faults_memory and faults_cpu decay and these values are copied.
unsigned long *numa_faults;
unsigned long total_numa_faults;
* numa_faults_locality tracks if faults recorded during the last
* scan window were remote/local or failed to migrate. The task scan
* period is adapted based on the locality of the faults with different
* weights depending on whether they were shared or private faults
unsigned long numa_faults_locality[3];
unsigned long numa_pages_migrated;
struct tlbflush_unmap_batch tlb_ubc;
struct rcu_head rcu;
* cache last used pipe for splice
struct pipe_inode_info *splice_pipe;
struct page_frag task_frag;
struct task_delay_info *delays;
int make_it_fail;
* when (nr_dirtied >= nr_dirtied_pause), it's time to call
* balance_dirty_pages() for some dirty throttling pause
int nr_dirtied;
int nr_dirtied_pause;
unsigned long dirty_paused_when; /* start of a write-and-pause period */
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.
u64 timer_slack_ns;
u64 default_timer_slack_ns;
unsigned int kasan_depth;
/* 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 and counter of trace recursion */
unsigned long trace_recursion;
#endif /* CONFIG_TRACING */
/* Coverage collection mode enabled for this task (0 if disabled). */
enum kcov_mode kcov_mode;
/* Size of the kcov_area. */
unsigned kcov_size;
/* Buffer for coverage collection. */
void *kcov_area;
/* kcov desciptor wired with this task or NULL. */
struct kcov *kcov;
struct mem_cgroup *memcg_in_oom;
gfp_t memcg_oom_gfp_mask;
int memcg_oom_order;
/* number of pages to reclaim on returning to userland */
unsigned int memcg_nr_pages_over_high;
struct uprobe_task *utask;
unsigned int sequential_io;
unsigned int sequential_io_avg;
unsigned long task_state_change;
int pagefault_disabled;
struct task_struct *oom_reaper_list;
/* CPU-specific state of this task */
struct thread_struct thread;
* WARNING: on x86, 'thread_struct' contains a variable-sized
* structure. It *MUST* be at the end of 'task_struct'.
* Do not put anything below here!
extern int arch_task_struct_size __read_mostly;
# define arch_task_struct_size (sizeof(struct task_struct))
/* Future-safe accessor for struct task_struct's cpus_allowed. */
#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
static inline int tsk_nr_cpus_allowed(struct task_struct *p)
return p->nr_cpus_allowed;
#define TNF_MIGRATED 0x01
#define TNF_NO_GROUP 0x02
#define TNF_SHARED 0x04
#define TNF_FAULT_LOCAL 0x08
#define TNF_MIGRATE_FAIL 0x10
extern void task_numa_fault(int last_node, int node, int pages, int flags);
extern pid_t task_numa_group_id(struct task_struct *p);
extern void set_numabalancing_state(bool enabled);
extern void task_numa_free(struct task_struct *p);
extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page,
int src_nid, int dst_cpu);
static inline void task_numa_fault(int last_node, int node, int pages,
int flags)
static inline pid_t task_numa_group_id(struct task_struct *p)
return 0;
static inline void set_numabalancing_state(bool enabled)
static inline void task_numa_free(struct task_struct *p)
static inline bool should_numa_migrate_memory(struct task_struct *p,
struct page *page, int src_nid, int dst_cpu)
return true;
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 int pid_alive(const struct task_struct *p);
static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns)
pid_t pid = 0;
if (pid_alive(tsk))
pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns);
return pid;
static inline pid_t task_ppid_nr(const struct task_struct *tsk)
return task_ppid_nr_ns(tsk, &init_pid_ns);
static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk,
struct pid_namespace *ns)
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.
* Return: 1 if the process is alive. 0 otherwise.
static inline int pid_alive(const struct task_struct *p)
return p->pids[PIDTYPE_PID].pid != NULL;
* is_global_init - check if a task structure is init. Since init
* is free to have sub-threads we need to check tgid.
* @tsk: Task structure to be checked.
* Check if a task structure is the first user space task the kernel created.
* Return: 1 if the task structure is init. 0 otherwise.
static inline int is_global_init(struct task_struct *tsk)
return task_tgid_nr(tsk) == 1;
extern struct pid *cad_pid;
extern void free_task(struct task_struct *tsk);
#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_cputime(struct task_struct *t,
cputime_t *utime, cputime_t *stime);
extern void task_cputime_scaled(struct task_struct *t,
cputime_t *utimescaled, cputime_t *stimescaled);
extern cputime_t task_gtime(struct task_struct *t);
static inline void task_cputime(struct task_struct *t,
cputime_t *utime, cputime_t *stime)
if (utime)
*utime = t->utime;
if (stime)
*stime = t->stime;
static inline void task_cputime_scaled(struct task_struct *t,
cputime_t *utimescaled,
cputime_t *stimescaled)
if (utimescaled)
*utimescaled = t->utimescaled;
if (stimescaled)
*stimescaled = t->stimescaled;
static inline cputime_t task_gtime(struct task_struct *t)
return t->gtime;
extern void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
* Per process flags
#define PF_EXITING 0x00000004 /* getting shut down */
#define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */
#define PF_VCPU 0x00000010 /* I'm a virtual CPU */
#define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */
#define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */
#define PF_MCE_PROCESS 0x00000080 /* process policy on mce errors */
#define PF_SUPERPRIV 0x00000100 /* used super-user privileges */
#define PF_DUMPCORE 0x00000200 /* dumped core */
#define PF_SIGNALED 0x00000400 /* killed by a signal */
#define PF_MEMALLOC 0x00000800 /* Allocating memory */
#define PF_NPROC_EXCEEDED 0x00001000 /* set_user noticed that RLIMIT_NPROC was exceeded */
#define PF_USED_MATH 0x00002000 /* if unset the fpu must be initialized before use */
#define PF_USED_ASYNC 0x00004000 /* used async_schedule*(), used by module init */
#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_MEMALLOC_NOIO 0x00080000 /* Allocating memory without IO involved */
#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_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */
#define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */
#define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */
#define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */
#define PF_SUSPEND_TASK 0x80000000 /* this thread called freeze_processes and should not be frozen */
* 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)
/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags
* __GFP_FS is also cleared as it implies __GFP_IO.
static inline gfp_t memalloc_noio_flags(gfp_t flags)
if (unlikely(current->flags & PF_MEMALLOC_NOIO))
flags &= ~(__GFP_IO | __GFP_FS);
return flags;
static inline unsigned int memalloc_noio_save(void)
unsigned int flags = current->flags & PF_MEMALLOC_NOIO;
current->flags |= PF_MEMALLOC_NOIO;
return flags;
static inline void memalloc_noio_restore(unsigned int flags)
current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags;
/* Per-process atomic flags. */
#define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */
#define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */
#define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */
#define PFA_LMK_WAITING 3 /* Lowmemorykiller is waiting */
#define TASK_PFA_TEST(name, func) \
static inline bool task_##func(struct task_struct *p) \
{ return test_bit(PFA_##name, &p->atomic_flags); }
#define TASK_PFA_SET(name, func) \
static inline void task_set_##func(struct task_struct *p) \
{ set_bit(PFA_##name, &p->atomic_flags); }
#define TASK_PFA_CLEAR(name, func) \
static inline void task_clear_##func(struct task_struct *p) \
{ clear_bit(PFA_##name, &p->atomic_flags); }
TASK_PFA_SET(NO_NEW_PRIVS, no_new_privs)
* task->jobctl flags
#define JOBCTL_STOP_SIGMASK 0xffff /* signr of the last group stop */
#define JOBCTL_STOP_DEQUEUED_BIT 16 /* stop signal dequeued */
#define JOBCTL_STOP_PENDING_BIT 17 /* task should stop for group stop */
#define JOBCTL_STOP_CONSUME_BIT 18 /* consume group stop count */
#define JOBCTL_TRAP_STOP_BIT 19 /* trap for STOP */
#define JOBCTL_TRAP_NOTIFY_BIT 20 /* trap for NOTIFY */
#define JOBCTL_TRAPPING_BIT 21 /* switching to TRACED */
#define JOBCTL_LISTENING_BIT 22 /* ptracer is listening for events */
extern bool task_set_jobctl_pending(struct task_struct *task,
unsigned long mask);
extern void task_clear_jobctl_trapping(struct task_struct *task);
extern void task_clear_jobctl_pending(struct task_struct *task,
unsigned long mask);
static inline void rcu_copy_process(struct task_struct *p)
p->rcu_read_lock_nesting = 0;
p->rcu_read_unlock_special.s = 0;
p->rcu_blocked_node = NULL;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
p->rcu_tasks_holdout = false;
p->rcu_tasks_idle_cpu = -1;
#endif /* #ifdef CONFIG_TASKS_RCU */
static inline void tsk_restore_flags(struct task_struct *task,
unsigned long orig_flags, unsigned long flags)
task->flags &= ~flags;
task->flags |= orig_flags & flags;
extern int cpuset_cpumask_can_shrink(const struct cpumask *cur,
const struct cpumask *trial);
extern int task_can_attach(struct task_struct *p,
const struct cpumask *cs_cpus_allowed);
extern void do_set_cpus_allowed(struct task_struct *p,
const struct cpumask *new_mask);
extern int set_cpus_allowed_ptr(struct task_struct *p,
const struct cpumask *new_mask);
static inline void do_set_cpus_allowed(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;
void calc_load_enter_idle(void);
void calc_load_exit_idle(void);
static inline void calc_load_enter_idle(void) { }
static inline void calc_load_exit_idle(void) { }
#endif /* CONFIG_NO_HZ_COMMON */
* Do not use outside of architecture code which knows its limitations.
* sched_clock() has no promise of monotonicity or bounded drift between
* CPUs, use (which you should not) requires disabling IRQs.
* Please use one of the three interfaces below.
extern unsigned long long notrace sched_clock(void);
* See the comment in kernel/sched/clock.c
extern u64 running_clock(void);
extern u64 sched_clock_cpu(int cpu);
extern void sched_clock_init(void);
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)
static inline u64 cpu_clock(int cpu)
return sched_clock();
static inline u64 local_clock(void)
return sched_clock();
* 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(void);
extern void set_sched_clock_stable(void);
extern void clear_sched_clock_stable(void);
extern void sched_clock_tick(void);
extern void sched_clock_idle_sleep_event(void);
extern void sched_clock_idle_wakeup_event(u64 delta_ns);
* As outlined in clock.c, provides a fast, high resolution, nanosecond
* time source that is monotonic per cpu argument and has bounded drift
* between cpus.
* ######################### BIG FAT WARNING ##########################
* # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can #
* # go backwards !! #
* ####################################################################
static inline u64 cpu_clock(int cpu)
return sched_clock_cpu(cpu);
static inline u64 local_clock(void)
return sched_clock_cpu(raw_smp_processor_id());
* 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);
/* 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 idle_task_exit(void);
static inline void idle_task_exit(void) {}
#if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP)
extern void wake_up_nohz_cpu(int cpu);
static inline void wake_up_nohz_cpu(int cpu) { }
extern u64 scheduler_tick_max_deferment(void);
extern void sched_autogroup_create_attach(struct task_struct *p);
extern void sched_autogroup_detach(struct task_struct *p);
extern void sched_autogroup_fork(struct signal_struct *sig);
extern void sched_autogroup_exit(struct signal_struct *sig);
extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m);
extern int proc_sched_autogroup_set_nice(struct task_struct *p, int nice);
static inline void sched_autogroup_create_attach(struct task_struct *p) { }
static inline void sched_autogroup_detach(struct task_struct *p) { }
static inline void sched_autogroup_fork(struct signal_struct *sig) { }
static inline void sched_autogroup_exit(struct signal_struct *sig) { }
extern int yield_to(struct task_struct *p, bool preempt);
extern void set_user_nice(struct task_struct *p, long nice);
extern int task_prio(const struct task_struct *p);
* task_nice - return the nice value of a given task.
* @p: the task in question.
* Return: The nice value [ -20 ... 0 ... 19 ].
static inline int task_nice(const struct task_struct *p)
return PRIO_TO_NICE((p)->static_prio);
extern int can_nice(const struct task_struct *p, const int nice);
extern int task_curr(const struct task_struct *p);
extern int idle_cpu(int cpu);
extern int sched_setscheduler(struct task_struct *, int,
const struct sched_param *);
extern int sched_setscheduler_nocheck(struct task_struct *, int,
const struct sched_param *);
extern int sched_setattr(struct task_struct *,
const struct sched_attr *);
extern struct task_struct *idle_task(int cpu);
* is_idle_task - is the specified task an idle task?
* @p: the task in question.
* Return: 1 if @p is an idle task. 0 otherwise.
static inline bool is_idle_task(const struct task_struct *p)
return p->pid == 0;
extern struct task_struct *curr_task(int cpu);
extern void set_curr_task(int cpu, struct task_struct *p);
void yield(void);
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);
/* per-UID process charging. */
extern struct user_struct * alloc_uid(kuid_t);
static inline struct user_struct *get_uid(struct user_struct *u)
return u;
extern void free_uid(struct user_struct *);
#include <asm/current.h>
extern void xtime_update(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);
extern void kick_process(struct task_struct *tsk);
static inline void kick_process(struct task_struct *tsk) { }
extern int sched_fork(unsigned long clone_flags, struct task_struct *p);
extern void sched_dead(struct task_struct *p);
extern void proc_caches_init(void);
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 kernel_dequeue_signal(siginfo_t *info)
struct task_struct *tsk = current;
siginfo_t __info;
int ret;
ret = dequeue_signal(tsk, &tsk->blocked, info ?: &__info);
return ret;
static inline void kernel_signal_stop(void)
if (current->jobctl & JOBCTL_STOP_DEQUEUED)
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_cred(int, struct siginfo *, struct pid *,
const struct cred *, 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 __must_check bool 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 *);
static inline void restore_saved_sigmask(void)
if (test_and_clear_restore_sigmask())
static inline sigset_t *sigmask_to_save(void)
sigset_t *res = &current->blocked;
if (unlikely(test_restore_sigmask()))
res = &current->saved_sigmask;
return res;
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)
* If the signal stack is SS_AUTODISARM then, by construction, we
* can't be on the signal stack unless user code deliberately set
* SS_AUTODISARM when we were already on it.
* This improves reliability: if user state gets corrupted such that
* the stack pointer points very close to the end of the signal stack,
* then this check will enable the signal to be handled anyway.
if (current->sas_ss_flags & SS_AUTODISARM)
return 0;
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)
if (!current->sas_ss_size)
return SS_DISABLE;
return on_sig_stack(sp) ? SS_ONSTACK : 0;
static inline void sas_ss_reset(struct task_struct *p)
p->sas_ss_sp = 0;
p->sas_ss_size = 0;
p->sas_ss_flags = SS_DISABLE;
static inline unsigned long sigsp(unsigned long sp, struct ksignal *ksig)
if (unlikely((ksig-> & SA_ONSTACK)) && ! sas_ss_flags(sp))
return current->sas_ss_sp;
return current->sas_ss_sp + current->sas_ss_size;
return sp;
* 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)))
static inline bool mmget_not_zero(struct mm_struct *mm)
return atomic_inc_not_zero(&mm->mm_users);
/* mmput gets rid of the mappings and all user-space */
extern void mmput(struct mm_struct *);
/* same as above but performs the slow path from the async context. Can
* be called from the atomic context as well
extern void mmput_async(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);
* Grab a reference to a task's mm, if it is not already going away
* and ptrace_may_access with the mode parameter passed to it
* succeeds.
extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode);
/* Remove the current tasks stale references to the old mm_struct */
extern void mm_release(struct task_struct *, struct mm_struct *);
extern int copy_thread_tls(unsigned long, unsigned long, unsigned long,
struct task_struct *, unsigned long);
extern int copy_thread(unsigned long, unsigned long, unsigned long,
struct task_struct *);
/* Architectures that haven't opted into copy_thread_tls get the tls argument
* via pt_regs, so ignore the tls argument passed via C. */
static inline int copy_thread_tls(
unsigned long clone_flags, unsigned long sp, unsigned long arg,
struct task_struct *p, unsigned long tls)
return copy_thread(clone_flags, sp, arg, p);
extern void flush_thread(void);
extern void exit_thread(struct task_struct *tsk);
static inline void exit_thread(struct task_struct *tsk)
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 void do_group_exit(int);
extern int do_execve(struct filename *,
const char __user * const __user *,
const char __user * const __user *);
extern int do_execveat(int, struct filename *,
const char __user * const __user *,
const char __user * const __user *,
extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *, unsigned long);
extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
struct task_struct *fork_idle(int);
extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec);
static inline void set_task_comm(struct task_struct *tsk, const char *from)
__set_task_comm(tsk, from, false);
extern char *get_task_comm(char *to, struct task_struct *tsk);
void scheduler_ipi(void);
extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
static inline void scheduler_ipi(void) { }
static inline unsigned long wait_task_inactive(struct task_struct *p,
long match_state)
return 1;
#define tasklist_empty() \
#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)
#define __for_each_thread(signal, t) \
list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node)
#define for_each_thread(p, t) \
__for_each_thread((p)->signal, t)
/* Careful: this is a double loop, 'break' won't work as expected. */
#define for_each_process_thread(p, t) \
for_each_process(p) for_each_thread(p, t)
static inline int get_nr_threads(struct task_struct *tsk)
return tsk->signal->nr_threads;
static inline bool thread_group_leader(struct task_struct *p)
return p->exit_signal >= 0;
/* 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 bool has_group_leader_pid(struct task_struct *p)
return task_pid(p) == p->signal->leader_pid;
static inline
bool same_thread_group(struct task_struct *p1, struct task_struct *p2)
return p1->signal == p2->signal;
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))
* 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[]. And ->vfork_done.
* 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 struct sighand_struct *lock_task_sighand(struct task_struct *tsk,
unsigned long *flags)
struct sighand_struct *ret;
ret = __lock_task_sighand(tsk, flags);
(void)__cond_lock(&tsk->sighand->siglock, ret);
return ret;
static inline void unlock_task_sighand(struct task_struct *tsk,
unsigned long *flags)
spin_unlock_irqrestore(&tsk->sighand->siglock, *flags);
* threadgroup_change_begin - mark the beginning of changes to a threadgroup
* @tsk: task causing the changes
* All operations which modify a threadgroup - a new thread joining the
* group, death of a member thread (the assertion of PF_EXITING) and
* exec(2) dethreading the process and replacing the leader - are wrapped
* by threadgroup_change_{begin|end}(). This is to provide a place which
* subsystems needing threadgroup stability can hook into for
* synchronization.
static inline void threadgroup_change_begin(struct task_struct *tsk)
* threadgroup_change_end - mark the end of changes to a threadgroup
* @tsk: task causing the changes
* See threadgroup_change_begin().
static inline void threadgroup_change_end(struct task_struct *tsk)
#define task_thread_info(task) ((struct thread_info *)(task)->stack)
#define task_stack_page(task) ((task)->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;
* Return the address of the last usable long on the stack.
* When the stack grows down, this is just above the thread
* info struct. Going any lower will corrupt the threadinfo.
* When the stack grows up, this is the highest address.
* Beyond that position, we corrupt data on the next page.
static inline unsigned long