#include <linux/rbtree.h>
#include <linux/thread_info.h>
#include <linux/cpumask.h>
+#include <linux/errno.h>
+#include <linux/nodemask.h>
+#include <linux/vs_base.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/rcupdate.h>
+
+#include <linux/auxvec.h> /* For AT_VECTOR_SIZE */
struct exec_domain;
-extern int exec_shield;
-extern int exec_shield_randomize;
-extern int print_fatal_signals;
/*
* cloning flags:
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);
-// DECLARE_PER_CPU(struct runqueue, runqueues); -- removed after ckrm cpu v7 merge
extern int nr_processes(void);
extern unsigned long nr_running(void);
extern unsigned long nr_uninterruptible(void);
#include <linux/param.h>
#include <linux/resource.h>
#include <linux/timer.h>
+#include <linux/hrtimer.h>
#include <asm/processor.h>
+/*
+ * 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
-#define TASK_ONHOLD 64
+/* in tsk->state again */
+#define TASK_NONINTERACTIVE 64
+#define TASK_ONHOLD 128
#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
+
/*
* Scheduling policies
*/
#define SCHED_NORMAL 0
#define SCHED_FIFO 1
#define SCHED_RR 2
+#define SCHED_BATCH 3
struct sched_param {
int sched_priority;
#ifdef __KERNEL__
-#include <linux/taskdelays.h>
#include <linux/spinlock.h>
/*
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);
+
+#ifdef CONFIG_DETECT_SOFTLOCKUP
+extern void softlockup_tick(struct pt_regs *regs);
+extern void spawn_softlockup_task(void);
+extern void touch_softlockup_watchdog(void);
+#else
+static inline void softlockup_tick(struct pt_regs *regs)
+{
+}
+static inline void spawn_softlockup_task(void)
+{
+}
+static inline void touch_softlockup_watchdog(void)
+{
+}
+#endif
+
/* Attach to any functions which should be ignored in wchan output. */
#define __sched __attribute__((__section__(".sched.text")))
#define MAX_SCHEDULE_TIMEOUT LONG_MAX
extern signed long FASTCALL(schedule_timeout(signed long timeout));
+extern signed long schedule_timeout_interruptible(signed long timeout);
+extern signed long schedule_timeout_uninterruptible(signed long timeout);
asmlinkage void schedule(void);
struct namespace;
extern unsigned long
arch_get_unmapped_area(struct file *, unsigned long, unsigned long,
unsigned long, unsigned long);
-
-extern unsigned long
-arch_get_unmapped_exec_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 vm_area_struct *area);
-extern void arch_unmap_area_topdown(struct vm_area_struct *area);
+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.
+ */
+typedef atomic_long_t mm_counter_t;
+#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))
+
+#else /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
+/*
+ * The mm counters are protected by its page_table_lock,
+ * so can be incremented directly.
+ */
+typedef unsigned long mm_counter_t;
+#define __set_mm_counter(mm, member, value) (mm)->_##member = (value)
+#define get_mm_counter(mm, member) ((mm)->_##member)
+
+#endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
+
+#define set_mm_counter(mm, member, value) \
+ vx_ ## member ## pages_sub((mm), (get_mm_counter(mm, member) - value))
+#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))
+
+#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)
struct mm_struct {
struct vm_area_struct * mmap; /* list of VMAs */
unsigned long (*get_unmapped_area) (struct file *filp,
unsigned long addr, unsigned long len,
unsigned long pgoff, unsigned long flags);
- unsigned long (*get_unmapped_exec_area) (struct file *filp,
- unsigned long addr, unsigned long len,
- unsigned long pgoff, unsigned long flags);
- void (*unmap_area) (struct vm_area_struct *area);
+ void (*unmap_area) (struct mm_struct *mm, unsigned long addr);
unsigned long mmap_base; /* base of mmap area */
- unsigned long free_area_cache; /* first hole */
+ unsigned long task_size; /* size of task vm space */
+ unsigned long cached_hole_size; /* if non-zero, the largest hole below free_area_cache */
+ unsigned long free_area_cache; /* first hole of size cached_hole_size or larger */
pgd_t * pgd;
atomic_t mm_users; /* How many users with user space? */
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
* by mmlist_lock
*/
+ /* Special counters, in some configurations protected by the
+ * page_table_lock, in other configurations by being atomic.
+ */
+ mm_counter_t _file_rss;
+ mm_counter_t _anon_rss;
+
+ unsigned long hiwater_rss; /* High-watermark of RSS usage */
+ unsigned long hiwater_vm; /* High-water virtual memory usage */
+
+ unsigned long total_vm, locked_vm, shared_vm, exec_vm;
+ unsigned long stack_vm, reserved_vm, def_flags, nr_ptes;
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 exec_vm, stack_vm, reserved_vm, def_flags, nr_ptes;
- unsigned long saved_auxv[42]; /* for /proc/PID/auxv */
+ unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */
unsigned dumpable:2;
cpumask_t cpu_vm_mask;
/* aio bits */
rwlock_t ioctx_list_lock;
struct kioctx *ioctx_list;
-
- struct kioctx default_kioctx;
-#ifdef CONFIG_CKRM_RES_MEM
- struct ckrm_mem_res *memclass;
- struct list_head tasklist; /* list of all tasks sharing this address space */
- spinlock_t peertask_lock; /* protect above tasklist */
-#endif
};
struct sighand_struct {
atomic_t count;
struct k_sigaction action[_NSIG];
spinlock_t siglock;
+ struct rcu_head rcu;
};
+extern void sighand_free_cb(struct rcu_head *rhp);
+
+static inline void sighand_free(struct sighand_struct *sp)
+{
+ call_rcu(&sp->rcu, sighand_free_cb);
+}
+
/*
* NOTE! "signal_struct" does not have it's own
* locking, because a shared signal_struct always
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 hrtimer real_timer;
+ 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 */
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
};
+/* 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 */
+
+
/*
* Priority of a process goes from 0..MAX_PRIO-1, valid RT
- * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL tasks are
- * in the range MAX_RT_PRIO..MAX_PRIO-1. Priority values
- * are inverted: lower p->prio value means higher priority.
+ * 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
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
+ 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
/* protected by mq_lock */
unsigned long mq_bytes; /* How many bytes can be allocated to mqueue? */
unsigned long locked_shm; /* How many pages of mlocked shm ? */
#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_WAKE_IDLE 8 /* Wake to idle CPU on task wakeup */
-#define SD_WAKE_AFFINE 16 /* Wake task to waking CPU */
-#define SD_WAKE_BALANCE 32 /* Perform balancing at task wakeup */
-#define SD_SHARE_CPUPOWER 64 /* Domain members share cpu power */
+#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 */
struct sched_group {
struct sched_group *next; /* Must be a circular list */
unsigned long long cache_hot_time; /* Task considered cache hot (ns) */
unsigned int cache_nice_tries; /* Leave cache hot tasks for # tries */
unsigned int per_cpu_gain; /* CPU % gained by adding domain cpus */
+ unsigned int busy_idx;
+ unsigned int idle_idx;
+ unsigned int newidle_idx;
+ unsigned int wake_idx;
+ unsigned int forkexec_idx;
int flags; /* See SD_* */
/* Runtime fields. */
/* 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];
- /* sched_balance_exec() stats */
- unsigned long sbe_attempts;
+ /* Active load balancing */
+ unsigned long alb_cnt;
+ unsigned long alb_failed;
+ unsigned long alb_pushed;
+
+ /* SD_BALANCE_EXEC stats */
+ unsigned long sbe_cnt;
+ unsigned long sbe_balanced;
unsigned long sbe_pushed;
+ /* SD_BALANCE_FORK stats */
+ unsigned long sbf_cnt;
+ unsigned long sbf_balanced;
+ unsigned long sbf_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
};
-#ifdef ARCH_HAS_SCHED_DOMAIN
-/* Useful helpers that arch setup code may use. Defined in kernel/sched.c */
-extern cpumask_t cpu_isolated_map;
-extern void init_sched_build_groups(struct sched_group groups[],
- cpumask_t span, int (*group_fn)(int cpu));
-extern void cpu_attach_domain(struct sched_domain *sd, int cpu);
-#endif /* ARCH_HAS_SCHED_DOMAIN */
-#endif /* CONFIG_SMP */
+extern void partition_sched_domains(cpumask_t *partition1,
+ cpumask_t *partition2);
+
+/*
+ * Maximum cache size the migration-costs auto-tuning code will
+ * search from:
+ */
+extern unsigned int max_cache_size;
+
+#endif /* CONFIG_SMP */
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)))
groups_free(group_info); \
} while (0)
-struct group_info *groups_alloc(int gidsetsize);
-void groups_free(struct group_info *group_info);
-int set_current_groups(struct group_info *group_info);
+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*);
+#else
+static inline void prefetch_stack(struct task_struct *t) { }
+#endif
struct audit_context; /* See audit.c */
struct mempolicy;
-#ifdef CONFIG_CKRM_CPU_SCHEDULE
-/**
- * ckrm_cpu_demand_stat - used to track the cpu demand of a task/class
- * @run: how much time it has been running since the counter started
- * @total: total time since the counter started
- * @last_sleep: the last time it sleeps, last_sleep = 0 when not sleeping
- * @recalc_interval: how often do we recalculate the cpu_demand
- * @cpu_demand: moving average of run/total
- */
-struct ckrm_cpu_demand_stat {
- unsigned long long run;
- unsigned long long total;
- unsigned long long last_sleep;
- unsigned long long recalc_interval;
- unsigned long cpu_demand; /*estimated cpu demand */
-};
-#endif
-
-
struct task_struct {
volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */
struct thread_info *thread_info;
unsigned long flags; /* per process flags, defined below */
unsigned long ptrace;
- int lock_depth; /* Lock depth */
+ int lock_depth; /* BKL lock depth */
+#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
+ int oncpu;
+#endif
int prio, static_prio;
struct list_head run_list;
prio_array_t *array;
+ unsigned short ioprio;
+
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 *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
- 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 */
/* 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;
int (*notifier)(void *priv);
void *notifier_data;
sigset_t *notifier_mask;
-
- /* TUX state */
- void *tux_info;
- void (*tux_exit)(void);
-
void *security;
struct audit_context *audit_context;
/* vserver context data */
- xid_t xid;
struct vx_info *vx_info;
+ struct nx_info *nx_info;
-/* vserver network data */
+ xid_t xid;
nid_t nid;
- struct nx_info *nx_info;
+
+ seccomp_t seccomp;
/* Thread group tracking */
u32 parent_exec_id;
spinlock_t alloc_lock;
/* Protection of proc_dentry: nesting proc_lock, dcache_lock, write_lock_irq(&tasklist_lock); */
spinlock_t proc_lock;
-/* context-switch lock */
- spinlock_t switch_lock;
+
+#ifdef CONFIG_DEBUG_MUTEXES
+ /* mutex deadlock detection */
+ struct mutex_waiter *blocked_on;
+#endif
/* journalling filesystem info */
void *journal_info;
struct io_context *io_context;
- int ioprio;
-
unsigned long ptrace_message;
siginfo_t *last_siginfo; /* For ptrace use. */
/*
* 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_CKRM
- spinlock_t ckrm_tsklock;
- void *ce_data;
-#ifdef CONFIG_CKRM_TYPE_TASKCLASS
- // .. Hubertus should change to CONFIG_CKRM_TYPE_TASKCLASS
- struct ckrm_task_class *taskclass;
- struct list_head taskclass_link;
-#ifdef CONFIG_CKRM_CPU_SCHEDULE
- struct ckrm_cpu_class *cpu_class;
- //track cpu demand of this task
- struct ckrm_cpu_demand_stat demand_stat;
-#endif //CONFIG_CKRM_CPU_SCHEDULE
-#endif // CONFIG_CKRM_TYPE_TASKCLASS
-#ifdef CONFIG_CKRM_RES_MEM
- struct list_head mm_peers; // list of tasks using same mm_struct
-#endif // CONFIG_CKRM_RES_MEM
-#endif // CONFIG_CKRM
- struct task_delay_info delays;
+#ifdef CONFIG_CPUSETS
+ struct cpuset *cpuset;
+ nodemask_t mems_allowed;
+ int cpuset_mems_generation;
+#endif
+ atomic_t fs_excl; /* holding fs exclusive resources */
+ struct rcu_head rcu;
};
static inline pid_t process_group(struct task_struct *tsk)
}
extern void free_task(struct task_struct *tsk);
-extern void __put_task_struct(struct task_struct *tsk);
#define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0)
-#define put_task_struct(tsk) \
-do { if (atomic_dec_and_test(&(tsk)->usage)) __put_task_struct(tsk); } while(0)
+
+extern void __put_task_struct_cb(struct rcu_head *rhp);
+
+static inline void put_task_struct(struct task_struct *t)
+{
+ if (atomic_dec_and_test(&t->usage))
+ call_rcu(&t->rcu, __put_task_struct_cb);
+}
/*
* Per process flags
#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_MEMIO 0x01000000 /* I am potentially doing I/O for mem */
-#define PF_IOWAIT 0x02000000 /* I am waiting on disk I/O */
+#define PF_RANDOMIZE 0x00800000 /* randomize virtual address space */
+#define PF_SWAPWRITE 0x01000000 /* Allowed to write to swap */
+
+/*
+ * 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 (!cpu_isset(0, new_mask))
+ 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);
+extern task_t *curr_task(int cpu);
+extern void set_curr_task(int cpu, task_t *p);
void yield(void);
#define find_task_by_real_pid(nr) \
- find_task_by_pid_type(PIDTYPE_PID, nr)
+ find_task_by_pid_type(PIDTYPE_REALPID, nr)
#define find_task_by_pid(nr) \
- find_task_by_pid_type(PIDTYPE_PID, \
- vx_rmap_pid(nr))
+ find_task_by_pid_type(PIDTYPE_PID, nr)
extern struct task_struct *find_task_by_pid_type(int type, int pid);
extern void set_special_pids(pid_t session, pid_t pgrp);
atomic_inc(&u->__count);
return u;
}
-
extern void free_uid(struct user_struct *);
extern void switch_uid(struct user_struct *);
#else
static inline void kick_process(struct task_struct *tsk) { }
#endif
-extern void FASTCALL(sched_fork(task_t * p));
+extern void FASTCALL(sched_fork(task_t * p, int clone_flags));
extern void FASTCALL(sched_exit(task_t * p));
extern int in_group_p(gid_t);
extern int __kill_pg_info(int sig, struct siginfo *info, pid_t pgrp);
extern int kill_pg_info(int, struct siginfo *, pid_t);
extern int kill_proc_info(int, struct siginfo *, pid_t);
+extern int kill_proc_info_as_uid(int, struct siginfo *, pid_t, uid_t, uid_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 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, const struct k_sigaction *, struct k_sigaction *);
+extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
extern int do_sigaltstack(const stack_t __user *, stack_t __user *, unsigned long);
/* These can be the second arg to send_sig_info/send_group_sig_info. */
#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)
: on_sig_stack(sp) ? SS_ONSTACK : 0);
}
-
-#ifdef CONFIG_SECURITY
-/* code is in security.c */
-extern int capable(int cap);
-#else
-static inline int capable(int cap)
-{
- if (cap_raised(current->cap_effective, cap)) {
- current->flags |= PF_SUPERPRIV;
- return 1;
- }
- return 0;
-}
-#endif
-
-
/*
* Routines for handling mm_structs
*/
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);
/*
* Protects ->fs, ->files, ->mm, ->ptrace, ->group_info, ->comm, keyring
- * subscriptions and synchronises with wait4(). Also used in procfs.
+ * subscriptions and synchronises with wait4(). Also used in procfs. Also
+ * pins the final release of task.io_context. Also protects ->cpuset.
*
* Nests both inside and outside of read_lock(&tasklist_lock).
* It must not be nested with write_lock_irq(&tasklist_lock),
spin_unlock(&p->alloc_lock);
}
+#ifndef __HAVE_THREAD_FUNCTIONS
+
+#define task_thread_info(task) (task)->thread_info
+#define task_stack_page(task) ((void*)((task)->thread_info))
+
+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 *)(p->thread_info + 1);
+}
+
+#endif
+
/* 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(tsk->thread_info,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(tsk->thread_info,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(tsk->thread_info,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(tsk->thread_info,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(tsk->thread_info,flag);
+ return test_ti_thread_flag(task_thread_info(tsk), flag);
}
static inline void set_tsk_need_resched(struct task_struct *tsk)
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?:
+ */
+#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 void cond_resched_lock(spinlock_t * lock)
+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.
static inline unsigned int task_cpu(const struct task_struct *p)
{
- return p->thread_info->cpu;
+ return task_thread_info(p)->cpu;
}
static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
{
- p->thread_info->cpu = cpu;
+ task_thread_info(p)->cpu = cpu;
}
#else
#endif /* CONFIG_SMP */
-/* API for registering delay info */
-#ifdef CONFIG_DELAY_ACCT
-
-#define test_delay_flag(tsk,flg) ((tsk)->flags & (flg))
-#define set_delay_flag(tsk,flg) ((tsk)->flags |= (flg))
-#define clear_delay_flag(tsk,flg) ((tsk)->flags &= ~(flg))
-
-#define def_delay_var(var) unsigned long long var
-#define get_delay(tsk,field) ((tsk)->delays.field)
-
-#define start_delay(var) ((var) = sched_clock())
-#define start_delay_set(var,flg) (set_delay_flag(current,flg),(var) = sched_clock())
-
-#define inc_delay(tsk,field) (((tsk)->delays.field)++)
-
-/* because of hardware timer drifts in SMPs and task continue on different cpu
- * then where the start_ts was taken there is a possibility that
- * end_ts < start_ts by some usecs. In this case we ignore the diff
- * and add nothing to the total.
- */
-#ifdef CONFIG_SMP
-#define test_ts_integrity(start_ts,end_ts) (likely((end_ts) > (start_ts)))
+#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT
+extern void arch_pick_mmap_layout(struct mm_struct *mm);
#else
-#define test_ts_integrity(start_ts,end_ts) (1)
+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
-#define add_delay_ts(tsk,field,start_ts,end_ts) \
- do { if (test_ts_integrity(start_ts,end_ts)) (tsk)->delays.field += ((end_ts)-(start_ts)); } while (0)
+extern long sched_setaffinity(pid_t pid, cpumask_t new_mask);
+extern long sched_getaffinity(pid_t pid, cpumask_t *mask);
-#define add_delay_clear(tsk,field,start_ts,flg) \
- do { \
- unsigned long long now = sched_clock();\
- add_delay_ts(tsk,field,start_ts,now); \
- clear_delay_flag(tsk,flg); \
- } while (0)
+extern void normalize_rt_tasks(void);
-static inline void add_io_delay(unsigned long long dstart)
+#ifdef CONFIG_PM
+/*
+ * Check if a process has been frozen
+ */
+static inline int frozen(struct task_struct *p)
{
- struct task_struct * tsk = current;
- unsigned long long now = sched_clock();
- unsigned long long val;
-
- if (test_ts_integrity(dstart,now))
- val = now - dstart;
- else
- val = 0;
- if (test_delay_flag(tsk,PF_MEMIO)) {
- tsk->delays.mem_iowait_total += val;
- tsk->delays.num_memwaits++;
- } else {
- tsk->delays.iowait_total += val;
- tsk->delays.num_iowaits++;
- }
- clear_delay_flag(tsk,PF_IOWAIT);
+ return p->flags & PF_FROZEN;
}
-inline static void init_delays(struct task_struct *tsk)
+/*
+ * Check if there is a request to freeze a process
+ */
+static inline int freezing(struct task_struct *p)
{
- memset((void*)&tsk->delays,0,sizeof(tsk->delays));
+ return p->flags & PF_FREEZE;
}
-#else
-
-#define test_delay_flag(tsk,flg) (0)
-#define set_delay_flag(tsk,flg) do { } while (0)
-#define clear_delay_flag(tsk,flg) do { } while (0)
-
-#define def_delay_var(var)
-#define get_delay(tsk,field) (0)
-
-#define start_delay(var) do { } while (0)
-#define start_delay_set(var,flg) do { } while (0)
-
-#define inc_delay(tsk,field) do { } while (0)
-#define add_delay_ts(tsk,field,start_ts,now) do { } while (0)
-#define add_delay_clear(tsk,field,start_ts,flg) do { } while (0)
-#define add_io_delay(dstart) do { } while (0)
-#define init_delays(tsk) do { } while (0)
-#endif
-
+/*
+ * Request that a process be frozen
+ * FIXME: SMP problem. We may not modify other process' flags!
+ */
+static inline void freeze(struct task_struct *p)
+{
+ p->flags |= PF_FREEZE;
+}
+/*
+ * Wake up a frozen process
+ */
+static inline int thaw_process(struct task_struct *p)
+{
+ if (frozen(p)) {
+ p->flags &= ~PF_FROZEN;
+ wake_up_process(p);
+ return 1;
+ }
+ return 0;
+}
-#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)
+/*
+ * freezing is complete, mark process as frozen
+ */
+static inline void frozen_process(struct task_struct *p)
{
- mm->mmap_base = TASK_UNMAPPED_BASE;
- mm->get_unmapped_area = arch_get_unmapped_area;
- mm->unmap_area = arch_unmap_area;
+ p->flags = (p->flags & ~PF_FREEZE) | PF_FROZEN;
}
-#endif
-extern long sched_setaffinity(pid_t pid, cpumask_t new_mask);
-extern long sched_getaffinity(pid_t pid, cpumask_t *mask);
+extern void refrigerator(void);
+extern int freeze_processes(void);
+extern void thaw_processes(void);
-#ifdef CONFIG_MAGIC_SYSRQ
+static inline int try_to_freeze(void)
+{
+ if (freezing(current)) {
+ refrigerator();
+ return 1;
+ } else
+ return 0;
+}
+#else
+static inline int frozen(struct task_struct *p) { return 0; }
+static inline int freezing(struct task_struct *p) { return 0; }
+static inline void freeze(struct task_struct *p) { BUG(); }
+static inline int thaw_process(struct task_struct *p) { return 1; }
+static inline void frozen_process(struct task_struct *p) { BUG(); }
-extern void normalize_rt_tasks(void);
+static inline void refrigerator(void) {}
+static inline int freeze_processes(void) { BUG(); return 0; }
+static inline void thaw_processes(void) {}
-#endif
+static inline int try_to_freeze(void) { return 0; }
+#endif /* CONFIG_PM */
#endif /* __KERNEL__ */
#endif