#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
#include <linux/mm_types.h>
#include <asm/system.h>
-#include <asm/semaphore.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/securebits.h>
#include <linux/fs_struct.h>
#include <linux/compiler.h>
#include <linux/completion.h>
#include <linux/proportions.h>
#include <linux/seccomp.h>
#include <linux/rcupdate.h>
-#include <linux/futex.h>
#include <linux/rtmutex.h>
#include <linux/time.h>
#include <asm/processor.h>
+struct mem_cgroup;
struct exec_domain;
struct futex_pi_state;
+struct robust_list_head;
struct bio;
/*
}
#endif
+extern unsigned long long time_sync_thresh;
+
/*
* Task state bitmask. NOTE! These bits are also
* encoded in fs/proc/array.c: get_task_state().
#define TASK_RUNNING 0
#define TASK_INTERRUPTIBLE 1
#define TASK_UNINTERRUPTIBLE 2
-#define TASK_STOPPED 4
-#define TASK_TRACED 8
+#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)
extern void sched_init(void);
extern void sched_init_smp(void);
+extern asmlinkage void schedule_tail(struct task_struct *prev);
extern void init_idle(struct task_struct *idle, int cpu);
extern void init_idle_bootup_task(struct task_struct *idle);
extern int in_sched_functions(unsigned long addr);
#define MAX_SCHEDULE_TIMEOUT LONG_MAX
-extern signed long FASTCALL(schedule_timeout(signed long timeout));
+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);
/* ITIMER_REAL timer for the process */
struct hrtimer real_timer;
- struct task_struct *tsk;
+ struct pid *leader_pid;
ktime_t it_real_incr;
/* ITIMER_PROF and ITIMER_VIRTUAL timers for the process */
#define SIGNAL_STOP_DEQUEUED 0x00000002 /* stop signal dequeued */
#define SIGNAL_STOP_CONTINUED 0x00000004 /* SIGCONT since WCONTINUED reap */
#define SIGNAL_GROUP_EXIT 0x00000008 /* group exit in progress */
+/*
+ * Pending notifications to parent.
+ */
+#define SIGNAL_CLD_STOPPED 0x00000010
+#define SIGNAL_CLD_CONTINUED 0x00000020
+#define SIGNAL_CLD_MASK (SIGNAL_CLD_STOPPED|SIGNAL_CLD_CONTINUED)
+
+#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 hlist_node uidhash_node;
uid_t uid;
-#ifdef CONFIG_FAIR_USER_SCHED
+#ifdef CONFIG_USER_SCHED
struct task_group *tg;
#ifdef CONFIG_SYSFS
struct kobject kobj;
#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)
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 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 */
#endif
};
-extern void partition_sched_domains(int ndoms_new, cpumask_t *doms_new);
+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 */
struct io_context; /* See blkdev.h */
#define NGROUPS_SMALL 32
-#define NGROUPS_PER_BLOCK ((int)(PAGE_SIZE / sizeof(gid_t)))
+#define NGROUPS_PER_BLOCK ((unsigned int)(PAGE_SIZE / sizeof(gid_t)))
struct group_info {
int ngroups;
atomic_t usage;
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, cpumask_t *newmask);
+ void (*set_cpus_allowed)(struct task_struct *p,
+ const cpumask_t *newmask);
void (*join_domain)(struct rq *rq);
void (*leave_domain)(struct rq *rq);
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 {
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 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;
unsigned long timeout;
int nr_cpus_allowed;
-#ifdef CONFIG_FAIR_GROUP_SCHED
+ 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;
struct hlist_head preempt_notifiers;
#endif
- unsigned short ioprio;
/*
* fpu_counter contains the number of consecutive context switches
* that the FPU is used. If this is over a threshold, the lazy fpu
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;
- unsigned keep_capabilities:1;
+ 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 sighand_struct *sighand;
sigset_t blocked, real_blocked;
- sigset_t saved_sigmask; /* To be restored with TIF_RESTORE_SIGMASK */
+ sigset_t saved_sigmask; /* restored if set_restore_sigmask() was used */
struct sigpending pending;
unsigned long sas_ss_sp;
void *security;
#endif
struct audit_context *audit_context;
+#ifdef CONFIG_AUDITSYSCALL
+ uid_t loginuid;
+ unsigned int sessionid;
+#endif
seccomp_t seccomp;
/* Thread group tracking */
int softirq_context;
#endif
#ifdef CONFIG_LOCKDEP
-# define MAX_LOCK_DEPTH 30UL
+# define MAX_LOCK_DEPTH 48UL
u64 curr_chain_key;
int lockdep_depth;
struct held_lock held_locks[MAX_LOCK_DEPTH];
* 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 namespace the task
- * belongs to. this only makes sence when called in the
- * context of the task that belongs to the same 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;
#define used_math() tsk_used_math(current)
#ifdef CONFIG_SMP
-extern int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask);
+extern int set_cpus_allowed_ptr(struct task_struct *p,
+ const cpumask_t *new_mask);
#else
-static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
+static inline int set_cpus_allowed_ptr(struct task_struct *p,
+ const cpumask_t *new_mask)
{
- if (!cpu_isset(0, 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);
+#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+static inline void sched_clock_init(void)
+{
+}
+
+static inline u64 sched_clock_cpu(int cpu)
+{
+ return sched_clock();
+}
+
+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)
+{
+}
+#else
+extern void sched_clock_init(void);
+extern u64 sched_clock_cpu(int cpu);
+extern void sched_clock_tick(void);
+extern void sched_clock_idle_sleep_event(void);
+extern void sched_clock_idle_wakeup_event(u64 delta_ns);
+#endif
+
/*
* For kernel-internal use: high-speed (but slightly incorrect) per-cpu
* clock constructed from sched_clock():
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_batch_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;
-extern unsigned int sysctl_sched_rt_period;
-extern unsigned int sysctl_sched_rt_ratio;
-#if defined(CONFIG_FAIR_GROUP_SCHED) && defined(CONFIG_SMP)
-extern unsigned int sysctl_sched_min_bal_int_shares;
-extern unsigned int sysctl_sched_max_bal_int_shares;
-#endif
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;
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);
+static inline struct task_struct *__deprecated find_task_by_pid(pid_t nr)
+{
+ return find_task_by_pid_type_ns(PIDTYPE_PID, nr, &init_pid_ns);
+}
extern struct task_struct *find_task_by_vpid(pid_t nr);
extern struct task_struct *find_task_by_pid_ns(pid_t nr,
struct pid_namespace *ns);
-extern void __set_special_pids(pid_t session, pid_t pgrp);
+extern void __set_special_pids(struct pid *pid);
/* per-UID process charging. */
extern struct user_struct * alloc_uid(struct user_namespace *, uid_t);
extern void do_timer(unsigned long ticks);
-extern int FASTCALL(wake_up_state(struct task_struct * tsk, unsigned int state));
-extern int FASTCALL(wake_up_process(struct task_struct * tsk));
-extern void FASTCALL(wake_up_new_task(struct task_struct * tsk,
- unsigned long clone_flags));
+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
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 send_group_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_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_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 send_sigqueue(struct sigqueue *, struct task_struct *, int group);
extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
extern int do_sigaltstack(const stack_t __user *, stack_t __user *, unsigned long);
extern struct mm_struct * mm_alloc(void);
/* mmdrop drops the mm and the page tables */
-extern void FASTCALL(__mmdrop(struct mm_struct *));
+extern void __mmdrop(struct mm_struct *);
static inline void mmdrop(struct mm_struct * mm)
{
if (unlikely(atomic_dec_and_test(&mm->mm_count)))
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);
struct task_struct *fork_idle(int);
extern void set_task_comm(struct task_struct *tsk, char *from);
-extern void get_task_comm(char *to, struct task_struct *tsk);
+extern char *get_task_comm(char *to, struct task_struct *tsk);
#ifdef CONFIG_SMP
extern void wait_task_inactive(struct task_struct * p);
#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
*/
clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
}
+static inline int test_tsk_need_resched(struct task_struct *tsk)
+{
+ return unlikely(test_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));
+ return unlikely(test_tsk_need_resched(current));
}
/*
/*
* Does a critical section need to be broken due to another
- * task waiting?:
+ * task waiting?: (technically does not depend on CONFIG_PREEMPT,
+ * but a general need for low latency)
*/
-#if defined(CONFIG_PREEMPT) && defined(CONFIG_SMP)
-# define need_lockbreak(lock) ((lock)->break_lock)
-#else
-# define need_lockbreak(lock) 0
-#endif
-
-/*
- * Does a critical section need to be broken due to another
- * task waiting or preemption being signalled:
- */
-static inline int lock_need_resched(spinlock_t *lock)
+static inline int spin_needbreak(spinlock_t *lock)
{
- if (need_lockbreak(lock) || need_resched())
- return 1;
+#ifdef CONFIG_PREEMPT
+ return spin_is_contended(lock);
+#else
return 0;
+#endif
}
/*
}
#endif
-extern long sched_setaffinity(pid_t pid, cpumask_t new_mask);
+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_FAIR_GROUP_SCHED
+#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(void);
+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
}
#endif
+#ifndef TASK_SIZE_OF
+#define TASK_SIZE_OF(tsk) TASK_SIZE
+#endif
+
+#ifdef CONFIG_MM_OWNER
+extern void mm_update_next_owner(struct mm_struct *mm);
+extern void mm_init_owner(struct mm_struct *mm, struct task_struct *p);
+#else
+static inline void mm_update_next_owner(struct mm_struct *mm)
+{
+}
+
+static inline void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
+{
+}
+#endif /* CONFIG_MM_OWNER */
+
#endif /* __KERNEL__ */
#endif