linux-sg2042/include/linux/sched.h

2154 lines
63 KiB
C

#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
#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/fs_struct.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/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 <asm/processor.h>
struct mem_cgroup;
struct exec_domain;
struct futex_pi_state;
struct robust_list_head;
struct bio;
/*
* List of flags we want to share for kernel threads,
* if only because they are not used by them anyway.
*/
#define CLONE_KERNEL (CLONE_FS | CLONE_FILES | CLONE_SIGHAND)
/*
* 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 */
#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 weighted_cpuload(const int cpu);
struct seq_file;
struct cfs_rq;
struct task_group;
#ifdef CONFIG_SCHED_DEBUG
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);
#else
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)
{
}
#endif
/*
* 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_INTERRUPTIBLE 1
#define TASK_UNINTERRUPTIBLE 2
#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
/* Convenience macros for the sake of set_task_state */
#define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
#define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED)
#define TASK_TRACED (TASK_WAKEKILL | __TASK_TRACED)
/* Convenience macros for the sake of wake_up */
#define TASK_NORMAL (TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)
#define TASK_ALL (TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED)
/* get_task_state() */
#define TASK_REPORT (TASK_RUNNING | TASK_INTERRUPTIBLE | \
TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \
__TASK_TRACED)
#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)
#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 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_t nohz_cpu_mask;
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
extern int select_nohz_load_balancer(int cpu);
#else
static inline int select_nohz_load_balancer(int cpu)
{
return 0;
}
#endif
extern unsigned long rt_needs_cpu(int cpu);
/*
* Only dump TASK_* tasks. (0 for all tasks)
*/
extern void show_state_filter(unsigned long state_filter);
static inline void show_state(void)
{
show_state_filter(0);
}
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 account_process_tick(struct task_struct *task, int user);
extern void update_process_times(int user);
extern void scheduler_tick(void);
extern void hrtick_resched(void);
extern void sched_show_task(struct task_struct *p);
#ifdef CONFIG_DETECT_SOFTLOCKUP
extern void softlockup_tick(void);
extern void spawn_softlockup_task(void);
extern void touch_softlockup_watchdog(void);
extern void touch_all_softlockup_watchdogs(void);
extern unsigned long softlockup_thresh;
extern unsigned long sysctl_hung_task_check_count;
extern unsigned long sysctl_hung_task_timeout_secs;
extern unsigned long sysctl_hung_task_warnings;
#else
static inline void softlockup_tick(void)
{
}
static inline void spawn_softlockup_task(void)
{
}
static inline void touch_softlockup_watchdog(void)
{
}
static inline void touch_all_softlockup_watchdogs(void)
{
}
#endif
/* 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);
#define MAX_SCHEDULE_TIMEOUT LONG_MAX
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);
struct nsproxy;
struct user_namespace;
/* Maximum number of active map areas.. This is a random (large) number */
#define DEFAULT_MAX_MAP_COUNT 65536
extern int sysctl_max_map_count;
#include <linux/aio.h>
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);
#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS
/*
* The mm counters are not protected by its page_table_lock,
* so must be incremented atomically.
*/
#define set_mm_counter(mm, member, value) atomic_long_set(&(mm)->_##member, value)
#define get_mm_counter(mm, member) ((unsigned long)atomic_long_read(&(mm)->_##member))
#define add_mm_counter(mm, member, value) atomic_long_add(value, &(mm)->_##member)
#define inc_mm_counter(mm, member) atomic_long_inc(&(mm)->_##member)
#define dec_mm_counter(mm, member) atomic_long_dec(&(mm)->_##member)
#else /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
/*
* The mm counters are protected by its page_table_lock,
* so can be incremented directly.
*/
#define set_mm_counter(mm, member, value) (mm)->_##member = (value)
#define get_mm_counter(mm, member) ((mm)->_##member)
#define add_mm_counter(mm, member, value) (mm)->_##member += (value)
#define inc_mm_counter(mm, member) (mm)->_##member++
#define dec_mm_counter(mm, member) (mm)->_##member--
#endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
#define get_mm_rss(mm) \
(get_mm_counter(mm, file_rss) + get_mm_counter(mm, anon_rss))
#define update_hiwater_rss(mm) do { \
unsigned long _rss = get_mm_rss(mm); \
if ((mm)->hiwater_rss < _rss) \
(mm)->hiwater_rss = _rss; \
} while (0)
#define update_hiwater_vm(mm) do { \
if ((mm)->hiwater_vm < (mm)->total_vm) \
(mm)->hiwater_vm = (mm)->total_vm; \
} while (0)
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 */
#define MMF_DUMPABLE_BITS 2
/* coredump filter bits */
#define MMF_DUMP_ANON_PRIVATE 2
#define MMF_DUMP_ANON_SHARED 3
#define MMF_DUMP_MAPPED_PRIVATE 4
#define MMF_DUMP_MAPPED_SHARED 5
#define MMF_DUMP_ELF_HEADERS 6
#define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS
#define MMF_DUMP_FILTER_BITS 5
#define MMF_DUMP_FILTER_MASK \
(((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT)
#define MMF_DUMP_FILTER_DEFAULT \
((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED))
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;
};
/*
* 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 count;
atomic_t live;
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.
*/
struct task_struct *group_exit_task;
int notify_count;
/* 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 */
cputime_t it_prof_expires, it_virt_expires;
cputime_t it_prof_incr, it_virt_incr;
/* job control IDs */
/*
* pgrp and session fields are deprecated.
* use the task_session_Xnr and task_pgrp_Xnr routines below
*/
union {
pid_t pgrp __deprecated;
pid_t __pgrp;
};
struct pid *tty_old_pgrp;
union {
pid_t session __deprecated;
pid_t __session;
};
/* 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;
unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
unsigned long inblock, oublock, cinblock, coublock;
/*
* Cumulative ns of scheduled CPU time for 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 list_head cpu_timers[3];
/* keep the process-shared keyrings here so that they do the right
* thing in threads created with CLONE_THREAD */
#ifdef CONFIG_KEYS
struct key *session_keyring; /* keyring inherited over fork */
struct key *process_keyring; /* keyring private to this process */
#endif
#ifdef CONFIG_BSD_PROCESS_ACCT
struct pacct_struct pacct; /* per-process accounting information */
#endif
#ifdef CONFIG_TASKSTATS
struct taskstats *stats;
#endif
#ifdef CONFIG_AUDIT
unsigned audit_tty;
struct tty_audit_buf *tty_audit_buf;
#endif
};
/* Context switch must be unlocked if interrupts are to be enabled */
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
# define __ARCH_WANT_UNLOCKED_CTXSW
#endif
/*
* 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 */
/* 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? */
#ifdef CONFIG_INOTIFY_USER
atomic_t inotify_watches; /* How many inotify watches does this user have? */
atomic_t inotify_devs; /* How many inotify devs does this user have opened? */
#endif
#ifdef CONFIG_POSIX_MQUEUE
/* protected by mq_lock */
unsigned long mq_bytes; /* How many bytes can be allocated to mqueue? */
#endif
unsigned long locked_shm; /* How many pages of mlocked shm ? */
#ifdef CONFIG_KEYS
struct key *uid_keyring; /* UID specific keyring */
struct key *session_keyring; /* UID's default session keyring */
#endif
/* Hash table maintenance information */
struct hlist_node uidhash_node;
uid_t uid;
#ifdef CONFIG_USER_SCHED
struct task_group *tg;
#ifdef CONFIG_SYSFS
struct kobject kobj;
struct work_struct work;
#endif
#endif
};
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;
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
struct sched_info {
/* cumulative counters */
unsigned long pcount; /* # of times run on this cpu */
unsigned long long cpu_time, /* time spent on the cpu */
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 */
#ifdef CONFIG_SCHEDSTATS
/* BKL stats */
unsigned int bkl_count;
#endif
};
#endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */
#ifdef CONFIG_SCHEDSTATS
extern const struct file_operations proc_schedstat_operations;
#endif /* CONFIG_SCHEDSTATS */
#ifdef 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 */
};
#endif /* CONFIG_TASK_DELAY_ACCT */
static inline int sched_info_on(void)
{
#ifdef CONFIG_SCHEDSTATS
return 1;
#elif defined(CONFIG_TASK_DELAY_ACCT)
extern int delayacct_on;
return delayacct_on;
#else
return 0;
#endif
}
enum cpu_idle_type {
CPU_IDLE,
CPU_NOT_IDLE,
CPU_NEWLY_IDLE,
CPU_MAX_IDLE_TYPES
};
/*
* sched-domains (multiprocessor balancing) declarations:
*/
/*
* Increase resolution of nice-level calculations:
*/
#define SCHED_LOAD_SHIFT 10
#define SCHED_LOAD_SCALE (1L << SCHED_LOAD_SHIFT)
#define SCHED_LOAD_SCALE_FUZZ SCHED_LOAD_SCALE
#ifdef CONFIG_SMP
#define SD_LOAD_BALANCE 1 /* Do load balancing on this domain. */
#define SD_BALANCE_NEWIDLE 2 /* Balance when about to become idle */
#define SD_BALANCE_EXEC 4 /* Balance on exec */
#define SD_BALANCE_FORK 8 /* Balance on fork, clone */
#define SD_WAKE_IDLE 16 /* Wake to idle CPU on task wakeup */
#define SD_WAKE_AFFINE 32 /* Wake task to waking CPU */
#define SD_WAKE_BALANCE 64 /* Perform balancing at task wakeup */
#define SD_SHARE_CPUPOWER 128 /* Domain members share cpu power */
#define SD_POWERSAVINGS_BALANCE 256 /* Balance for power savings */
#define SD_SHARE_PKG_RESOURCES 512 /* Domain members share cpu pkg resources */
#define SD_SERIALIZE 1024 /* Only a single load balancing instance */
#define SD_WAKE_IDLE_FAR 2048 /* Gain latency sacrificing cache hit */
#define BALANCE_FOR_MC_POWER \
(sched_smt_power_savings ? SD_POWERSAVINGS_BALANCE : 0)
#define BALANCE_FOR_PKG_POWER \
((sched_mc_power_savings || sched_smt_power_savings) ? \
SD_POWERSAVINGS_BALANCE : 0)
#define test_sd_parent(sd, flag) ((sd->parent && \
(sd->parent->flags & flag)) ? 1 : 0)
struct sched_group {
struct sched_group *next; /* Must be a circular list */
cpumask_t cpumask;
/*
* CPU power of this group, SCHED_LOAD_SCALE being max power for a
* single CPU. This is read only (except for setup, hotplug CPU).
* Note : Never change cpu_power without recompute its reciprocal
*/
unsigned int __cpu_power;
/*
* reciprocal value of cpu_power to avoid expensive divides
* (see include/linux/reciprocal_div.h)
*/
u32 reciprocal_cpu_power;
};
enum sched_domain_level {
SD_LV_NONE = 0,
SD_LV_SIBLING,
SD_LV_MC,
SD_LV_CPU,
SD_LV_NODE,
SD_LV_ALLNODES,
SD_LV_MAX
};
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 */
cpumask_t span; /* span of all CPUs in this domain */
int first_cpu; /* cache of the first cpu in this 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;
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 */
#ifdef CONFIG_SCHEDSTATS
/* 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;
#endif
};
extern void partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
struct sched_domain_attr *dattr_new);
extern int arch_reinit_sched_domains(void);
#endif /* CONFIG_SMP */
/*
* A runqueue laden with a single nice 0 task scores a weighted_cpuload of
* SCHED_LOAD_SCALE. This function returns 1 if any cpu is laden with a
* task of nice 0 or enough lower priority tasks to bring up the
* weighted_cpuload
*/
static inline int above_background_load(void)
{
unsigned long cpu;
for_each_online_cpu(cpu) {
if (weighted_cpuload(cpu) >= SCHED_LOAD_SCALE)
return 1;
}
return 0;
}
struct io_context; /* See blkdev.h */
#define NGROUPS_SMALL 32
#define NGROUPS_PER_BLOCK ((unsigned int)(PAGE_SIZE / sizeof(gid_t)))
struct group_info {
int ngroups;
atomic_t usage;
gid_t small_block[NGROUPS_SMALL];
int nblocks;
gid_t *blocks[0];
};
/*
* get_group_info() must be called with the owning task locked (via task_lock())
* when task != current. The reason being that the vast majority of callers are
* looking at current->group_info, which can not be changed except by the
* current task. Changing current->group_info requires the task lock, too.
*/
#define get_group_info(group_info) do { \
atomic_inc(&(group_info)->usage); \
} while (0)
#define put_group_info(group_info) do { \
if (atomic_dec_and_test(&(group_info)->usage)) \
groups_free(group_info); \
} while (0)
extern struct group_info *groups_alloc(int gidsetsize);
extern void groups_free(struct group_info *group_info);
extern int set_current_groups(struct group_info *group_info);
extern int groups_search(struct group_info *group_info, gid_t grp);
/* access the groups "array" with this macro */
#define GROUP_AT(gi, i) \
((gi)->blocks[(i)/NGROUPS_PER_BLOCK][(i)%NGROUPS_PER_BLOCK])
#ifdef ARCH_HAS_PREFETCH_SWITCH_STACK
extern void prefetch_stack(struct task_struct *t);
#else
static inline void prefetch_stack(struct task_struct *t) { }
#endif
struct audit_context; /* See audit.c */
struct mempolicy;
struct pipe_inode_info;
struct uts_namespace;
struct rq;
struct sched_domain;
struct sched_class {
const struct sched_class *next;
void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup);
void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep);
void (*yield_task) (struct rq *rq);
int (*select_task_rq)(struct task_struct *p, int sync);
void (*check_preempt_curr) (struct rq *rq, struct task_struct *p);
struct task_struct * (*pick_next_task) (struct rq *rq);
void (*put_prev_task) (struct rq *rq, struct task_struct *p);
#ifdef CONFIG_SMP
unsigned long (*load_balance) (struct rq *this_rq, int this_cpu,
struct rq *busiest, unsigned long max_load_move,
struct sched_domain *sd, enum cpu_idle_type idle,
int *all_pinned, int *this_best_prio);
int (*move_one_task) (struct rq *this_rq, int this_cpu,
struct rq *busiest, struct sched_domain *sd,
enum cpu_idle_type idle);
void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
void (*post_schedule) (struct rq *this_rq);
void (*task_wake_up) (struct rq *this_rq, struct task_struct *task);
#endif
void (*set_curr_task) (struct rq *rq);
void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
void (*task_new) (struct rq *rq, struct task_struct *p);
void (*set_cpus_allowed)(struct task_struct *p,
const cpumask_t *newmask);
void (*join_domain)(struct rq *rq);
void (*leave_domain)(struct rq *rq);
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);
#ifdef CONFIG_FAIR_GROUP_SCHED
void (*moved_group) (struct task_struct *p);
#endif
};
struct load_weight {
unsigned long weight, inv_weight;
};
/*
* CFS stats for a schedulable entity (task, task-group etc)
*
* Current field usage histogram:
*
* 4 se->block_start
* 4 se->run_node
* 4 se->sleep_start
* 6 se->load.weight
*/
struct sched_entity {
struct load_weight load; /* for load-balancing */
struct rb_node run_node;
struct list_head group_node;
unsigned int on_rq;
u64 exec_start;
u64 sum_exec_runtime;
u64 vruntime;
u64 prev_sum_exec_runtime;
u64 last_wakeup;
u64 avg_overlap;
#ifdef CONFIG_SCHEDSTATS
u64 wait_start;
u64 wait_max;
u64 wait_count;
u64 wait_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;
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_forced2_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;
#endif
#ifdef CONFIG_FAIR_GROUP_SCHED
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;
#endif
};
struct sched_rt_entity {
struct list_head run_list;
unsigned int time_slice;
unsigned long timeout;
int nr_cpus_allowed;
struct sched_rt_entity *back;
#ifdef CONFIG_RT_GROUP_SCHED
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;
#endif
};
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 */
#ifdef CONFIG_SMP
#ifdef __ARCH_WANT_UNLOCKED_CTXSW
int oncpu;
#endif
#endif
int prio, static_prio, normal_prio;
const struct sched_class *sched_class;
struct sched_entity se;
struct sched_rt_entity rt;
#ifdef CONFIG_PREEMPT_NOTIFIERS
/* list of struct preempt_notifier: */
struct hlist_head preempt_notifiers;
#endif
/*
* 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;
s8 oomkilladj; /* OOM kill score adjustment (bit shift). */
#ifdef CONFIG_BLK_DEV_IO_TRACE
unsigned int btrace_seq;
#endif
unsigned int policy;
cpumask_t cpus_allowed;
#ifdef CONFIG_PREEMPT_RCU
int rcu_read_lock_nesting;
int rcu_flipctr_idx;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
struct sched_info sched_info;
#endif
struct list_head tasks;
/*
* ptrace_list/ptrace_children forms the list of my children
* that were stolen by a ptracer.
*/
struct list_head ptrace_children;
struct list_head ptrace_list;
struct mm_struct *mm, *active_mm;
/* task state */
struct linux_binfmt *binfmt;
int exit_state;
int exit_code, exit_signal;
int pdeath_signal; /* The signal sent when the parent dies */
/* ??? */
unsigned int personality;
unsigned did_exec:1;
pid_t pid;
pid_t tgid;
#ifdef CONFIG_CC_STACKPROTECTOR
/* Canary value for the -fstack-protector gcc feature */
unsigned long stack_canary;
#endif
/*
* pointers to (original) parent process, youngest child, younger sibling,
* older sibling, respectively. (p->father can be replaced with
* p->parent->pid)
*/
struct task_struct *real_parent; /* real parent process (when being debugged) */
struct task_struct *parent; /* parent process */
/*
* children/sibling forms the list of my children plus the
* tasks I'm ptracing.
*/
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 */
/* 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 */
unsigned int rt_priority;
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;
cputime_t it_prof_expires, it_virt_expires;
unsigned long long it_sched_expires;
struct list_head cpu_timers[3];
/* process credentials */
uid_t uid,euid,suid,fsuid;
gid_t gid,egid,sgid,fsgid;
struct group_info *group_info;
kernel_cap_t cap_effective, cap_inheritable, cap_permitted, cap_bset;
unsigned securebits;
struct user_struct *user;
#ifdef CONFIG_KEYS
struct key *request_key_auth; /* assumed request_key authority */
struct key *thread_keyring; /* keyring private to this thread */
unsigned char jit_keyring; /* default keyring to attach requested keys to */
#endif
char comm[TASK_COMM_LEN]; /* executable name excluding path
- access with [gs]et_task_comm (which lock
it with task_lock())
- initialized normally by flush_old_exec */
/* file system info */
int link_count, total_link_count;
#ifdef CONFIG_SYSVIPC
/* ipc stuff */
struct sysv_sem sysvsem;
#endif
#ifdef CONFIG_DETECT_SOFTLOCKUP
/* hung task detection */
unsigned long last_switch_timestamp;
unsigned long last_switch_count;
#endif
/* 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; /* To be restored with TIF_RESTORE_SIGMASK */
struct sigpending pending;
unsigned long sas_ss_sp;
size_t sas_ss_size;
int (*notifier)(void *priv);
void *notifier_data;
sigset_t *notifier_mask;
#ifdef CONFIG_SECURITY
void *security;
#endif
struct audit_context *audit_context;
#ifdef CONFIG_AUDITSYSCALL
uid_t loginuid;
unsigned int sessionid;
#endif
seccomp_t seccomp;
/* Thread group tracking */
u32 parent_exec_id;
u32 self_exec_id;
/* Protection of (de-)allocation: mm, files, fs, tty, keyrings */
spinlock_t alloc_lock;
/* Protection of the PI data structures: */
spinlock_t pi_lock;
#ifdef CONFIG_RT_MUTEXES
/* 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;
#endif
#ifdef CONFIG_DEBUG_MUTEXES
/* mutex deadlock detection */
struct mutex_waiter *blocked_on;
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
unsigned int irq_events;
int hardirqs_enabled;
unsigned long hardirq_enable_ip;
unsigned int hardirq_enable_event;
unsigned long hardirq_disable_ip;
unsigned int hardirq_disable_event;
int softirqs_enabled;
unsigned long softirq_disable_ip;
unsigned int softirq_disable_event;
unsigned long softirq_enable_ip;
unsigned int softirq_enable_event;
int hardirq_context;
int softirq_context;
#endif
#ifdef CONFIG_LOCKDEP
# define MAX_LOCK_DEPTH 48UL
u64 curr_chain_key;
int lockdep_depth;
struct held_lock held_locks[MAX_LOCK_DEPTH];
unsigned int lockdep_recursion;
#endif
/* journalling filesystem info */
void *journal_info;
/* stacked block device info */
struct bio *bio_list, **bio_tail;
/* 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. */
#ifdef CONFIG_TASK_XACCT
/* i/o counters(bytes read/written, #syscalls */
u64 rchar, wchar, syscr, syscw;
#endif
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_stimexpd;/* stime since last update */
#endif
#ifdef CONFIG_NUMA
struct mempolicy *mempolicy;
short il_next;
#endif
#ifdef CONFIG_CPUSETS
nodemask_t mems_allowed;
int cpuset_mems_generation;
int cpuset_mem_spread_rotor;
#endif
#ifdef CONFIG_CGROUPS
/* 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;
#endif
#ifdef CONFIG_FUTEX
struct robust_list_head __user *robust_list;
#ifdef CONFIG_COMPAT
struct compat_robust_list_head __user *compat_robust_list;
#endif
struct list_head pi_state_list;
struct futex_pi_state *pi_state_cache;
#endif
atomic_t fs_excl; /* holding fs exclusive resources */
struct rcu_head rcu;
/*
* cache last used pipe for splice
*/
struct pipe_inode_info *splice_pipe;
#ifdef CONFIG_TASK_DELAY_ACCT
struct task_delay_info *delays;
#endif
#ifdef CONFIG_FAULT_INJECTION
int make_it_fail;
#endif
struct prop_local_single dirties;
#ifdef CONFIG_LATENCYTOP
int latency_record_count;
struct latency_record latency_record[LT_SAVECOUNT];
#endif
};
/*
* 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_RT_PRIO MAX_USER_RT_PRIO
#define MAX_PRIO (MAX_RT_PRIO + 40)
#define DEFAULT_PRIO (MAX_RT_PRIO + 20)
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 void set_task_session(struct task_struct *tsk, pid_t session)
{
tsk->signal->__session = session;
}
static inline void set_task_pgrp(struct task_struct *tsk, pid_t pgrp)
{
tsk->signal->__pgrp = pgrp;
}
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;
}
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
*/
static inline pid_t task_pid_nr(struct task_struct *tsk)
{
return tsk->pid;
}
pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
static inline pid_t task_pid_vnr(struct task_struct *tsk)
{
return pid_vnr(task_pid(tsk));
}
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(struct task_struct *tsk)
{
return tsk->signal->__pgrp;
}
pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
static inline pid_t task_pgrp_vnr(struct task_struct *tsk)
{
return pid_vnr(task_pgrp(tsk));
}
static inline pid_t task_session_nr(struct task_struct *tsk)
{
return tsk->signal->__session;
}
pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
static inline pid_t task_session_vnr(struct task_struct *tsk)
{
return pid_vnr(task_session(tsk));
}
/**
* 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);
#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))
__put_task_struct(t);
}
/*
* Per process flags
*/
#define PF_ALIGNWARN 0x00000001 /* Print alignment warning msgs */
/* Not implemented yet, only for 486*/
#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_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_NOFREEZE 0x00008000 /* this thread should not be frozen */
#define PF_FROZEN 0x00010000 /* frozen for system suspend */
#define PF_FSTRANS 0x00020000 /* inside a filesystem transaction */
#define PF_KSWAPD 0x00040000 /* I am kswapd */
#define PF_SWAPOFF 0x00080000 /* I am in swapoff */
#define PF_LESS_THROTTLE 0x00100000 /* Throttle me less: I clean memory */
#define PF_BORROWED_MM 0x00200000 /* I am a kthread doing use_mm */
#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_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 */
/*
* 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)
#ifdef CONFIG_SMP
extern int set_cpus_allowed_ptr(struct task_struct *p,
const cpumask_t *new_mask);
#else
static inline int set_cpus_allowed_ptr(struct task_struct *p,
const cpumask_t *new_mask)
{
if (!cpu_isset(0, *new_mask))
return -EINVAL;
return 0;
}
#endif
static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
{
return set_cpus_allowed_ptr(p, &new_mask);
}
extern unsigned long long sched_clock(void);
/*
* For kernel-internal use: high-speed (but slightly incorrect) per-cpu
* clock constructed from sched_clock():
*/
extern unsigned long long cpu_clock(int cpu);
extern unsigned long long
task_sched_runtime(struct task_struct *task);
/* sched_exec is called by processes performing an exec */
#ifdef CONFIG_SMP
extern void sched_exec(void);
#else
#define sched_exec() {}
#endif
extern void sched_clock_idle_sleep_event(void);
extern void sched_clock_idle_wakeup_event(u64 delta_ns);
#ifdef CONFIG_HOTPLUG_CPU
extern void idle_task_exit(void);
#else
static inline void idle_task_exit(void) {}
#endif
extern void sched_idle_next(void);
#if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP)
extern void wake_up_idle_cpu(int cpu);
#else
static inline void wake_up_idle_cpu(int cpu) { }
#endif
#ifdef CONFIG_SCHED_DEBUG
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_child_runs_first;
extern unsigned int sysctl_sched_features;
extern unsigned int sysctl_sched_migration_cost;
extern unsigned int sysctl_sched_nr_migrate;
int sched_nr_latency_handler(struct ctl_table *table, int write,
struct file *file, void __user *buffer, size_t *length,
loff_t *ppos);
#endif
extern unsigned int sysctl_sched_rt_period;
extern int sysctl_sched_rt_runtime;
int sched_rt_handler(struct ctl_table *table, int write,
struct file *filp, void __user *buffer, size_t *lenp,
loff_t *ppos);
extern unsigned int sysctl_sched_compat_yield;
#ifdef CONFIG_RT_MUTEXES
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);
#else
static inline int rt_mutex_getprio(struct task_struct *p)
{
return p->normal_prio;
}
# define rt_mutex_adjust_pi(p) do { } while (0)
#endif
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 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)];
};
#ifndef __HAVE_ARCH_KSTACK_END
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*)));
}
#endif
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_type_ns():
* it is the most generic call - it finds a task by all id,
* type and namespace specified
* find_task_by_pid_ns():
* finds a task by its pid in the specified namespace
* find_task_by_vpid():
* finds a task by its virtual pid
* find_task_by_pid():
* finds a task by its global pid
*
* see also find_pid() etc in include/linux/pid.h
*/
extern struct task_struct *find_task_by_pid_type_ns(int type, int pid,
struct pid_namespace *ns);
extern struct task_struct *find_task_by_pid(pid_t nr);
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)
{
atomic_inc(&u->__count);
return u;
}
extern void free_uid(struct user_struct *);
extern void switch_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);
#ifdef CONFIG_SMP
extern void kick_process(struct task_struct *tsk);
#else
static inline void kick_process(struct task_struct *tsk) { }
#endif
extern void sched_fork(struct task_struct *p, int clone_flags);
extern void sched_dead(struct task_struct *p);
extern int in_group_p(gid_t);
extern int in_egroup_p(gid_t);
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 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 void do_notify_parent(struct task_struct *, int);
extern void force_sig(int, struct task_struct *);
extern void force_sig_specific(int, struct task_struct *);
extern int send_sig(int, struct task_struct *, int);
extern void zap_other_threads(struct task_struct *p);
extern int kill_proc(pid_t, int, int);
extern struct sigqueue *sigqueue_alloc(void);
extern void sigqueue_free(struct sigqueue *);
extern int send_sigqueue(int, struct sigqueue *, struct task_struct *);
extern int send_group_sigqueue(int, struct sigqueue *, struct task_struct *);
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)
static inline int is_si_special(const struct siginfo *info)
{
return info <= SEND_SIG_FORCED;
}
/* True if we are on the alternate signal stack. */
static inline int on_sig_stack(unsigned long sp)
{
return (sp - current->sas_ss_sp < current->sas_ss_size);
}
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)))
__mmdrop(mm);
}
/* 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(int, 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_signal(struct signal_struct *);
extern void __cleanup_sighand(struct sighand_struct *);
extern void exit_itimers(struct signal_struct *);
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);
#ifdef CONFIG_SMP
extern void wait_task_inactive(struct task_struct * p);
#else
#define wait_task_inactive(p) do { } while (0)
#endif
#define remove_parent(p) list_del_init(&(p)->sibling)
#define add_parent(p) list_add_tail(&(p)->sibling,&(p)->parent->children)
#define next_task(p) list_entry(rcu_dereference((p)->tasks.next), struct task_struct, tasks)
#define for_each_process(p) \
for (p = &init_task ; (p = next_task(p)) != &init_task ; )
/*
* 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)
/* 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_dereference(p->thread_group.next),
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[].
*
* 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)
{
spin_lock(&p->alloc_lock);
}
static inline void task_unlock(struct task_struct *p)
{
spin_unlock(&p->alloc_lock);
}
extern struct sighand_struct *lock_task_sighand(struct task_struct *tsk,
unsigned long *flags);
static inline void unlock_task_sighand(struct task_struct *tsk,
unsigned long *flags)
{
spin_unlock_irqrestore(&tsk->sighand->siglock, *flags);
}
#ifndef __HAVE_THREAD_FUNCTIONS
#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;
}
static inline unsigned long *end_of_stack(struct task_struct *p)
{
return (unsigned long *)(task_thread_info(p) + 1);
}
#endif
extern void thread_info_cache_init(void);
/* 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)
{
set_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
}
static inline void clear_tsk_need_resched(struct task_struct *tsk)
{
clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
}
static inline int signal_pending(struct task_struct *p)
{
return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
}
extern int __fatal_signal_pending(struct task_struct *p);
static inline int fatal_signal_pending(struct task_struct *p)
{
return signal_pending(p) && __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.
*/
#ifdef CONFIG_PREEMPT
static inline int cond_resched(void)
{
return 0;
}
#else
extern int _cond_resched(void);
static inline int cond_resched(void)
{
return _cond_resched();
}
#endif
extern int cond_resched_lock(spinlock_t * lock);
extern int cond_resched_softirq(void);
/*
* 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)
{
#ifdef CONFIG_PREEMPT
return spin_is_contended(lock);
#else
return 0;
#endif
}
/*
* 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.
*/
#ifdef CONFIG_SMP
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);
#else
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 */
#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT
extern void arch_pick_mmap_layout(struct mm_struct *mm);
#else
static inline void arch_pick_mmap_layout(struct mm_struct *mm)
{
mm->mmap_base = TASK_UNMAPPED_BASE;
mm->get_unmapped_area = arch_get_unmapped_area;
mm->unmap_area = arch_unmap_area;
}
#endif
extern long sched_setaffinity(pid_t pid, const cpumask_t *new_mask);
extern long sched_getaffinity(pid_t pid, cpumask_t *mask);
extern int sched_mc_power_savings, sched_smt_power_savings;
extern void normalize_rt_tasks(void);
#ifdef CONFIG_GROUP_SCHED
extern struct task_group init_task_group;
#ifdef CONFIG_USER_SCHED
extern struct task_group root_task_group;
#endif
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);
#ifdef CONFIG_FAIR_GROUP_SCHED
extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
extern unsigned long sched_group_shares(struct task_group *tg);
#endif
#ifdef CONFIG_RT_GROUP_SCHED
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);
#endif
#endif
#ifdef CONFIG_TASK_XACCT
static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
{
tsk->rchar += amt;
}
static inline void add_wchar(struct task_struct *tsk, ssize_t amt)
{
tsk->wchar += amt;
}
static inline void inc_syscr(struct task_struct *tsk)
{
tsk->syscr++;
}
static inline void inc_syscw(struct task_struct *tsk)
{
tsk->syscw++;
}
#else
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)
{
}
#endif
#ifdef CONFIG_SMP
void migration_init(void);
#else
static inline void migration_init(void)
{
}
#endif
#ifndef TASK_SIZE_OF
#define TASK_SIZE_OF(tsk) TASK_SIZE
#endif
#endif /* __KERNEL__ */
#endif