#include <linux/rbtree.h>
#include <linux/thread_info.h>
#include <linux/cpumask.h>
+#include <linux/errno.h>
+#include <linux/nodemask.h>
#include <asm/system.h>
#include <asm/semaphore.h>
#include <asm/page.h>
#include <asm/ptrace.h>
#include <asm/mmu.h>
+#include <asm/cputime.h>
#include <linux/smp.h>
#include <linux/sem.h>
#include <linux/pid.h>
#include <linux/percpu.h>
#include <linux/topology.h>
+#include <linux/seccomp.h>
#include <linux/vs_base.h>
struct exec_domain;
extern int exec_shield;
-extern int exec_shield_randomize;
extern int print_fatal_signals;
/*
load += n*(FIXED_1-exp); \
load >>= FSHIFT;
-#define CT_TO_SECS(x) ((x) / HZ)
-#define CT_TO_USECS(x) (((x) % HZ) * 1000000/HZ)
-
+extern unsigned long total_forks;
extern int nr_threads;
extern int last_pid;
DECLARE_PER_CPU(unsigned long, process_counts);
#define set_current_state(state_value) \
set_mb(current->state, (state_value))
+/* Task command name length */
+#define TASK_COMM_LEN 16
+
/*
* Scheduling policies
*/
extern void cpu_init (void);
extern void trap_init(void);
extern void update_process_times(int user);
-extern void scheduler_tick(int user_tick, int system);
-extern unsigned long cache_decay_ticks;
+extern void scheduler_tick(void);
/* Attach to any functions which should be ignored in wchan output. */
#define __sched __attribute__((__section__(".sched.text")))
extern void arch_unmap_area(struct vm_area_struct *area);
extern void arch_unmap_area_topdown(struct vm_area_struct *area);
+#define __set_mm_counter(mm, member, value) (mm)->_##member = (value)
+#define set_mm_counter(mm, member, value) vx_ ## member ## pages_sub((mm), ((mm)->_##member - value))
+#define get_mm_counter(mm, member) ((mm)->_##member)
+#define add_mm_counter(mm, member, value) vx_ ## member ## pages_add((mm), (value))
+#define inc_mm_counter(mm, member) vx_ ## member ## pages_inc((mm))
+#define dec_mm_counter(mm, member) vx_ ## member ## pages_dec((mm))
+typedef unsigned long mm_counter_t;
struct mm_struct {
struct vm_area_struct * mmap; /* list of VMAs */
atomic_t mm_count; /* How many references to "struct mm_struct" (users count as 1) */
int map_count; /* number of VMAs */
struct rw_semaphore mmap_sem;
- spinlock_t page_table_lock; /* Protects page tables, mm->rss, mm->anon_rss */
+ spinlock_t page_table_lock; /* Protects page tables and some counters */
struct list_head mmlist; /* List of maybe swapped mm's. These are globally strung
* together off init_mm.mmlist, and are protected
unsigned long start_code, end_code, start_data, end_data;
unsigned long start_brk, brk, start_stack;
unsigned long arg_start, arg_end, env_start, env_end;
- unsigned long rss, anon_rss, total_vm, locked_vm, shared_vm;
+ unsigned long total_vm, locked_vm, shared_vm;
unsigned long exec_vm, stack_vm, reserved_vm, def_flags, nr_ptes;
+ /* Special counters protected by the page_table_lock */
+ mm_counter_t _rss;
+ mm_counter_t _anon_rss;
+
unsigned long saved_auxv[42]; /* for /proc/PID/auxv */
- unsigned dumpable:2;
+ unsigned dumpable:1;
cpumask_t cpu_vm_mask;
/* Architecture-specific MM context */
struct kioctx *ioctx_list;
struct kioctx default_kioctx;
+
+ unsigned long hiwater_rss; /* High-water RSS usage */
+ unsigned long hiwater_vm; /* High-water virtual memory usage */
};
struct sighand_struct {
atomic_t count;
atomic_t live;
+ wait_queue_head_t wait_chldexit; /* for wait4() */
+
/* current thread group signal load-balancing target: */
task_t *curr_target;
struct sigpending shared_pending;
/* thread group exit support */
- int group_exit;
int group_exit_code;
/* overloaded:
* - notify group_exit_task when ->count is equal to notify_count
/* thread group stop support, overloads group_exit_code too */
int group_stop_count;
- /* 1 if group stopped since last SIGCONT, -1 if SIGCONT since report */
- int stop_state;
+ unsigned int flags; /* see SIGNAL_* flags below */
/* POSIX.1b Interval Timers */
struct list_head posix_timers;
+ /* ITIMER_REAL timer for the process */
+ struct timer_list real_timer;
+ unsigned long it_real_value, 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 */
pid_t pgrp;
pid_t tty_old_pgrp;
* Live threads maintain their own counters and add to these
* in __exit_signal, except for the group leader.
*/
- unsigned long utime, stime, cutime, cstime;
+ cputime_t utime, stime, cutime, cstime;
unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
+ /*
+ * 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 sched_time;
+
/*
* We don't bother to synchronize most readers of this at all,
* because there is no reader checking a limit that actually needs
* 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
};
+/*
+ * 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 */
+
+
/*
* Priority of a process goes from 0..MAX_PRIO-1, valid RT
* priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL tasks are
/* load_balance() stats */
unsigned long lb_cnt[MAX_IDLE_TYPES];
unsigned long lb_failed[MAX_IDLE_TYPES];
+ unsigned long lb_balanced[MAX_IDLE_TYPES];
unsigned long lb_imbalance[MAX_IDLE_TYPES];
+ unsigned long lb_gained[MAX_IDLE_TYPES];
+ unsigned long lb_hot_gained[MAX_IDLE_TYPES];
unsigned long lb_nobusyg[MAX_IDLE_TYPES];
unsigned long lb_nobusyq[MAX_IDLE_TYPES];
+ /* Active load balancing */
+ unsigned long alb_cnt;
+ unsigned long alb_failed;
+ unsigned long alb_pushed;
+
/* sched_balance_exec() stats */
unsigned long sbe_attempts;
unsigned long sbe_pushed;
/* try_to_wake_up() stats */
- unsigned long ttwu_wake_affine;
- unsigned long ttwu_wake_balance;
+ unsigned long ttwu_wake_remote;
+ unsigned long ttwu_move_affine;
+ unsigned long ttwu_move_balance;
#endif
};
struct io_context; /* See blkdev.h */
void exit_io_context(void);
+struct cpuset;
#define NGROUPS_SMALL 32
#define NGROUPS_PER_BLOCK ((int)(PAGE_SIZE / sizeof(gid_t)))
unsigned long flags; /* per process flags, defined below */
unsigned long ptrace;
- int lock_depth; /* Lock depth */
+ int lock_depth; /* BKL lock depth */
int prio, static_prio;
struct list_head run_list;
prio_array_t *array;
unsigned long sleep_avg;
- long interactive_credit;
unsigned long long timestamp, last_ran;
+ unsigned long long sched_time; /* sched_clock time spent running */
int activated;
unsigned long policy;
/* PID/PID hash table linkage. */
struct pid pids[PIDTYPE_MAX];
- wait_queue_head_t wait_chldexit; /* for wait4() */
struct completion *vfork_done; /* for vfork() */
int __user *set_child_tid; /* CLONE_CHILD_SETTID */
int __user *clear_child_tid; /* CLONE_CHILD_CLEARTID */
unsigned long rt_priority;
- unsigned long it_real_value, it_prof_value, it_virt_value;
- unsigned long it_real_incr, it_prof_incr, it_virt_incr;
- struct timer_list real_timer;
- unsigned long utime, stime;
+ cputime_t utime, stime;
unsigned long nvcsw, nivcsw; /* context switch counts */
struct timespec start_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;
unsigned keep_capabilities:1;
struct user_struct *user;
#ifdef CONFIG_KEYS
- struct key *session_keyring; /* keyring inherited over fork */
- struct key *process_keyring; /* keyring private to this process (CLONE_THREAD) */
struct key *thread_keyring; /* keyring private to this thread */
#endif
- unsigned short used_math;
- char comm[16];
+ int oomkilladj; /* OOM kill score adjustment (bit shift). */
+ 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;
/* ipc stuff */
void *security;
struct audit_context *audit_context;
+ seccomp_t seccomp;
/* vserver context data */
xid_t xid;
* to a stack based synchronous wait) if its doing sync IO.
*/
wait_queue_t *io_wait;
+/* i/o counters(bytes read/written, #syscalls */
+ u64 rchar, wchar, syscr, syscw;
+#if defined(CONFIG_BSD_PROCESS_ACCT)
+ u64 acct_rss_mem1; /* accumulated rss usage */
+ u64 acct_vm_mem1; /* accumulated virtual memory usage */
+ clock_t acct_stimexpd; /* clock_t-converted stime since last update */
+#endif
#ifdef CONFIG_NUMA
struct mempolicy *mempolicy;
- short il_next; /* could be shared with used_math */
+ short il_next;
+#endif
+#ifdef CONFIG_CPUSETS
+ struct cpuset *cpuset;
+ nodemask_t mems_allowed;
+ int cpuset_mems_generation;
#endif
};
#define PF_DUMPCORE 0x00000200 /* dumped core */
#define PF_SIGNALED 0x00000400 /* killed by a signal */
#define PF_MEMALLOC 0x00000800 /* Allocating memory */
-#define PF_MEMDIE 0x00001000 /* Killed for out-of-memory */
-#define PF_FLUSHER 0x00002000 /* responsible for disk writeback */
-
-#define PF_FREEZE 0x00004000 /* this task should be frozen for suspend */
+#define PF_FLUSHER 0x00001000 /* responsible for disk writeback */
+#define PF_USED_MATH 0x00002000 /* if unset the fpu must be initialized before use */
+#define PF_FREEZE 0x00004000 /* this task is being frozen for suspend now */
#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_LESS_THROTTLE 0x00100000 /* Throttle me less: I clean memory */
#define PF_SYNCWRITE 0x00200000 /* I am doing a sync write */
#define PF_BORROWED_MM 0x00400000 /* I am a kthread doing use_mm */
-#define PF_RELOCEXEC 0x00800000 /* relocate shared libraries */
+#define PF_RANDOMIZE 0x00800000 /* randomize virtual address space */
+
+/*
+ * 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(task_t *p, cpumask_t new_mask);
#else
static inline int set_cpus_allowed(task_t *p, cpumask_t new_mask)
{
+ if (!cpus_intersects(new_mask, cpu_online_map))
+ return -EINVAL;
return 0;
}
#endif
extern unsigned long long sched_clock(void);
+extern unsigned long long current_sched_time(const task_t *current_task);
/* sched_exec is called by processes performing an exec */
#ifdef CONFIG_SMP
#define sched_exec() {}
#endif
+#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);
extern void set_user_nice(task_t *p, long nice);
extern int task_prio(const task_t *p);
extern int task_nice(const task_t *p);
+extern int can_nice(const task_t *p, const int nice);
extern int task_curr(const task_t *p);
extern int idle_cpu(int cpu);
+extern int sched_setscheduler(struct task_struct *, int, struct sched_param *);
+extern task_t *idle_task(int cpu);
void yield(void);
extern void flush_thread(void);
extern void exit_thread(void);
-extern void exit_mm(struct task_struct *);
extern void exit_files(struct task_struct *);
extern void exit_signal(struct task_struct *);
extern void __exit_signal(struct task_struct *);
extern NORET_TYPE void do_group_exit(int);
-extern void reparent_to_init(void);
extern void daemonize(const char *, ...);
extern int allow_signal(int);
extern int disallow_signal(int);
return unlikely(test_thread_flag(TIF_NEED_RESCHED));
}
-extern void __cond_resched(void);
-static inline void cond_resched(void)
-{
- if (need_resched())
- __cond_resched();
-}
+/*
+ * cond_resched() and cond_resched_lock(): latency reduction via
+ * explicit rescheduling in places that are safe. The return
+ * value indicates whether a reschedule was done in fact.
+ * cond_resched_lock() will drop the spinlock before scheduling,
+ * cond_resched_softirq() will enable bhs before scheduling.
+ */
+extern int cond_resched(void);
+extern int cond_resched_lock(spinlock_t * lock);
+extern int cond_resched_softirq(void);
/*
- * cond_resched_lock() - if a reschedule is pending, drop the given lock,
- * call schedule, and on return reacquire the lock.
- *
- * This works OK both with and without CONFIG_PREEMPT. We do strange low-level
- * operations here to prevent schedule() from being called twice (once via
- * spin_unlock(), once by hand).
+ * Does a critical section need to be broken due to another
+ * task waiting?:
*/
-static inline void cond_resched_lock(spinlock_t * lock)
+#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)
{
- if (need_resched()) {
- _raw_spin_unlock(lock);
- preempt_enable_no_resched();
- __cond_resched();
- spin_lock(lock);
- }
+ if (need_lockbreak(lock) || need_resched())
+ return 1;
+ return 0;
}
/* Reevaluate whether the task has signals pending delivery.
#endif
+/* try_to_freeze
+ *
+ * Checks whether we need to enter the refrigerator
+ * and returns 1 if we did so.
+ */
+#ifdef CONFIG_PM
+extern void refrigerator(unsigned long);
+extern int freeze_processes(void);
+extern void thaw_processes(void);
+
+static inline int try_to_freeze(unsigned long refrigerator_flags)
+{
+ if (unlikely(current->flags & PF_FREEZE)) {
+ refrigerator(refrigerator_flags);
+ return 1;
+ } else
+ return 0;
+}
+#else
+static inline void refrigerator(unsigned long flag) {}
+static inline int freeze_processes(void) { BUG(); return 0; }
+static inline void thaw_processes(void) {}
+
+static inline int try_to_freeze(unsigned long refrigerator_flags)
+{
+ return 0;
+}
+#endif /* CONFIG_PM */
#endif /* __KERNEL__ */
#endif