#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/task_io_accounting.h>
#include <linux/latencytop.h>
#include <linux/cred.h>
+#include <linux/llist.h>
#include <asm/processor.h>
((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
#define task_contributes_to_load(task) \
((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
- (task->flags & PF_FREEZING) == 0)
+ (task->flags & PF_FROZEN) == 0)
#define __set_task_state(tsk, state_value) \
do { (tsk)->state = (state_value); } while (0)
extern int runqueue_is_locked(int cpu);
-extern cpumask_var_t nohz_cpu_mask;
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
extern void select_nohz_load_balancer(int stop_tick);
+extern void set_cpu_sd_state_idle(void);
extern int get_nohz_timer_target(void);
#else
static inline void select_nohz_load_balancer(int stop_tick) { }
+static inline void set_cpu_sd_state_idle(void) { }
#endif
/*
extern signed long schedule_timeout_killable(signed long timeout);
extern signed long schedule_timeout_uninterruptible(signed long timeout);
asmlinkage void schedule(void);
+extern void schedule_preempt_disabled(void);
extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner);
struct nsproxy;
#define INIT_CPUTIME \
(struct task_cputime) { \
- .utime = cputime_zero, \
- .stime = cputime_zero, \
+ .utime = 0, \
+ .stime = 0, \
.sum_exec_runtime = 0, \
}
struct thread_group_cputimer {
struct task_cputime cputime;
int running;
- spinlock_t lock;
+ raw_spinlock_t lock;
};
#include <linux/rwsem.h>
int group_stop_count;
unsigned int flags; /* see SIGNAL_* flags below */
+ /*
+ * PR_SET_CHILD_SUBREAPER marks a process, like a service
+ * manager, to re-parent orphan (double-forking) child processes
+ * to this process instead of 'init'. The service manager is
+ * able to receive SIGCHLD signals and is able to investigate
+ * the process until it calls wait(). All children of this
+ * process will inherit a flag if they should look for a
+ * child_subreaper process at exit.
+ */
+ unsigned int is_child_subreaper:1;
+ unsigned int has_child_subreaper:1;
+
/* POSIX.1b Interval Timers */
struct list_head posix_timers;
#endif
#ifdef CONFIG_CGROUPS
/*
- * The threadgroup_fork_lock prevents threads from forking with
- * CLONE_THREAD while held for writing. Use this for fork-sensitive
- * threadgroup-wide operations. It's taken for reading in fork.c in
- * copy_process().
- * Currently only needed write-side by cgroups.
+ * group_rwsem prevents new tasks from entering the threadgroup and
+ * member tasks from exiting,a more specifically, setting of
+ * PF_EXITING. fork and exit paths are protected with this rwsem
+ * using threadgroup_change_begin/end(). Users which require
+ * threadgroup to remain stable should use threadgroup_[un]lock()
+ * which also takes care of exec path. Currently, cgroup is the
+ * only user.
*/
- struct rw_semaphore threadgroup_fork_lock;
+ struct rw_semaphore group_rwsem;
#endif
int oom_adj; /* OOM kill score adjustment (bit shift) */
* when BITS_PER_LONG <= 32 are pretty high and the returns do not justify the
* increased costs.
*/
-#if BITS_PER_LONG > 32
+#if 0 /* BITS_PER_LONG > 32 -- currently broken: it increases power usage under light load */
# define SCHED_LOAD_RESOLUTION 10
# define scale_load(w) ((w) << SCHED_LOAD_RESOLUTION)
# define scale_load_down(w) ((w) >> SCHED_LOAD_RESOLUTION)
#define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */
#define SD_ASYM_PACKING 0x0800 /* Place busy groups earlier in the domain */
#define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */
+#define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */
enum powersavings_balance_level {
POWERSAVINGS_BALANCE_NONE = 0, /* No power saving load balance */
return 0;
}
-struct sched_group {
- struct sched_group *next; /* Must be a circular list */
+struct sched_group_power {
atomic_t ref;
-
/*
* CPU power of this group, SCHED_LOAD_SCALE being max power for a
* single CPU.
*/
- unsigned int cpu_power, cpu_power_orig;
+ unsigned int power, power_orig;
+ unsigned long next_update;
+ /*
+ * Number of busy cpus in this group.
+ */
+ atomic_t nr_busy_cpus;
+};
+
+struct sched_group {
+ struct sched_group *next; /* Must be a circular list */
+ atomic_t ref;
+
unsigned int group_weight;
+ struct sched_group_power *sgp;
/*
* The CPUs this group covers.
return to_cpumask(sg->cpumask);
}
+/**
+ * group_first_cpu - Returns the first cpu in the cpumask of a sched_group.
+ * @group: The group whose first cpu is to be returned.
+ */
+static inline unsigned int group_first_cpu(struct sched_group *group)
+{
+ return cpumask_first(sched_group_cpus(group));
+}
+
struct sched_domain_attr {
int relax_domain_level;
};
unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu);
unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu);
+bool cpus_share_cache(int this_cpu, int that_cpu);
+
#else /* CONFIG_SMP */
struct sched_domain_attr;
struct sched_domain_attr *dattr_new)
{
}
+
+static inline bool cpus_share_cache(int this_cpu, int that_cpu)
+{
+ return true;
+}
+
#endif /* !CONFIG_SMP */
*/
#define WF_SYNC 0x01 /* waker goes to sleep after wakup */
#define WF_FORK 0x02 /* child wakeup after fork */
+#define WF_MIGRATED 0x04 /* internal use, task got migrated */
#define ENQUEUE_WAKEUP 1
#define ENQUEUE_HEAD 2
#endif
};
+/*
+ * default timeslice is 100 msecs (used only for SCHED_RR tasks).
+ * Timeslices get refilled after they expire.
+ */
+#define RR_TIMESLICE (100 * HZ / 1000)
+
struct rcu_node;
enum perf_event_task_context {
unsigned int ptrace;
#ifdef CONFIG_SMP
- struct task_struct *wake_entry;
+ struct llist_node wake_entry;
int on_cpu;
#endif
int on_rq;
unsigned sched_reset_on_fork:1;
unsigned sched_contributes_to_load:1;
+#ifdef CONFIG_GENERIC_HARDIRQS
+ /* IRQ handler threads */
+ unsigned irq_thread:1;
+#endif
+
pid_t pid;
pid_t tgid;
* older sibling, respectively. (p->father can be replaced with
* p->real_parent->pid)
*/
- struct task_struct *real_parent; /* real parent process */
- struct task_struct *parent; /* recipient of SIGCHLD, wait4() reports */
+ struct task_struct __rcu *real_parent; /* real parent process */
+ struct task_struct __rcu *parent; /* recipient of SIGCHLD, wait4() reports */
/*
* children/sibling forms the list of my natural children
*/
* mempolicy */
spinlock_t alloc_lock;
-#ifdef CONFIG_GENERIC_HARDIRQS
- /* IRQ handler threads */
- struct irqaction *irqaction;
-#endif
-
/* Protection of the PI data structures: */
raw_spinlock_t pi_lock;
#endif
#ifdef CONFIG_CPUSETS
nodemask_t mems_allowed; /* Protected by alloc_lock */
- int mems_allowed_change_disable;
+ seqcount_t mems_allowed_seq; /* Seqence no to catch updates */
int cpuset_mem_spread_rotor;
int cpuset_slab_spread_rotor;
#endif
short il_next;
short pref_node_fork;
#endif
- atomic_t fs_excl; /* holding fs exclusive resources */
struct rcu_head rcu;
/*
#ifdef CONFIG_FAULT_INJECTION
int make_it_fail;
#endif
- struct prop_local_single dirties;
+ /*
+ * when (nr_dirtied >= nr_dirtied_pause), it's time to call
+ * balance_dirty_pages() for some dirty throttling pause
+ */
+ int nr_dirtied;
+ int nr_dirtied_pause;
+ unsigned long dirty_paused_when; /* start of a write-and-pause period */
+
#ifdef CONFIG_LATENCYTOP
int latency_record_count;
struct latency_record latency_record[LT_SAVECOUNT];
/*
* Per process flags
*/
-#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_DUMPCORE 0x00000200 /* dumped core */
#define PF_SIGNALED 0x00000400 /* killed by a signal */
#define PF_MEMALLOC 0x00000800 /* Allocating memory */
+#define PF_NPROC_EXCEEDED 0x00001000 /* set_user noticed that RLIMIT_NPROC was exceeded */
#define PF_USED_MATH 0x00002000 /* if unset the fpu must be initialized before use */
-#define PF_FREEZING 0x00004000 /* freeze in progress. do not account to load */
#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_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 freezable */
-#define PF_FREEZER_NOSIG 0x80000000 /* Freezer won't send signals to it */
/*
* Only the _current_ task can read/write to tsk->flags, but other
#define JOBCTL_STOP_DEQUEUED_BIT 16 /* stop signal dequeued */
#define JOBCTL_STOP_PENDING_BIT 17 /* task should stop for group stop */
#define JOBCTL_STOP_CONSUME_BIT 18 /* consume group stop count */
+#define JOBCTL_TRAP_STOP_BIT 19 /* trap for STOP */
+#define JOBCTL_TRAP_NOTIFY_BIT 20 /* trap for NOTIFY */
#define JOBCTL_TRAPPING_BIT 21 /* switching to TRACED */
+#define JOBCTL_LISTENING_BIT 22 /* ptracer is listening for events */
#define JOBCTL_STOP_DEQUEUED (1 << JOBCTL_STOP_DEQUEUED_BIT)
#define JOBCTL_STOP_PENDING (1 << JOBCTL_STOP_PENDING_BIT)
#define JOBCTL_STOP_CONSUME (1 << JOBCTL_STOP_CONSUME_BIT)
+#define JOBCTL_TRAP_STOP (1 << JOBCTL_TRAP_STOP_BIT)
+#define JOBCTL_TRAP_NOTIFY (1 << JOBCTL_TRAP_NOTIFY_BIT)
#define JOBCTL_TRAPPING (1 << JOBCTL_TRAPPING_BIT)
+#define JOBCTL_LISTENING (1 << JOBCTL_LISTENING_BIT)
-#define JOBCTL_PENDING_MASK JOBCTL_STOP_PENDING
+#define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
+#define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
+extern bool task_set_jobctl_pending(struct task_struct *task,
+ unsigned int mask);
+extern void task_clear_jobctl_trapping(struct task_struct *task);
extern void task_clear_jobctl_pending(struct task_struct *task,
unsigned int mask);
#ifdef CONFIG_PREEMPT_RCU
#define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */
-#define RCU_READ_UNLOCK_BOOSTED (1 << 1) /* boosted while in RCU read-side. */
-#define RCU_READ_UNLOCK_NEED_QS (1 << 2) /* RCU core needs CPU response. */
+#define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */
static inline void rcu_copy_process(struct task_struct *p)
{
extern unsigned long long
task_sched_runtime(struct task_struct *task);
-extern unsigned long long thread_group_sched_runtime(struct task_struct *task);
/* sched_exec is called by processes performing an exec */
#ifdef CONFIG_SMP
extern void sched_autogroup_exit(struct signal_struct *sig);
#ifdef CONFIG_PROC_FS
extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m);
-extern int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice);
+extern int proc_sched_autogroup_set_nice(struct task_struct *p, int nice);
#endif
#else
static inline void sched_autogroup_create_attach(struct task_struct *p) { }
static inline void sched_autogroup_exit(struct signal_struct *sig) { }
#endif
+#ifdef CONFIG_CFS_BANDWIDTH
+extern unsigned int sysctl_sched_cfs_bandwidth_slice;
+#endif
+
#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);
+static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
+{
+ return tsk->pi_blocked_on != NULL;
+}
#else
static inline int rt_mutex_getprio(struct task_struct *p)
{
return p->normal_prio;
}
# define rt_mutex_adjust_pi(p) do { } while (0)
+static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
+{
+ return false;
+}
#endif
extern bool yield_to(struct task_struct *p, bool preempt);
extern int sched_setscheduler_nocheck(struct task_struct *, int,
const struct sched_param *);
extern struct task_struct *idle_task(int cpu);
+/**
+ * is_idle_task - is the specified task an idle task?
+ * @p: the task in question.
+ */
+static inline bool is_idle_task(const struct task_struct *p)
+{
+ return p->pid == 0;
+}
extern struct task_struct *curr_task(int cpu);
extern void set_curr_task(int cpu, struct task_struct *p);
spin_unlock_irqrestore(&tsk->sighand->siglock, flags);
return ret;
-}
+}
extern void block_all_signals(int (*notifier)(void *priv), void *priv,
sigset_t *mask);
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_pid_info_as_cred(int, struct siginfo *, struct pid *,
+ const struct cred *, u32);
extern int kill_pgrp(struct pid *pid, int sig, int priv);
extern int kill_pid(struct pid *pid, int sig, int priv);
extern int kill_proc_info(int, struct siginfo *, pid_t);
-extern int do_notify_parent(struct task_struct *, int);
+extern __must_check bool do_notify_parent(struct task_struct *, int);
extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent);
extern void force_sig(int, struct task_struct *);
extern int send_sig(int, struct task_struct *, int);
extern 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);
+/*
+ * Grab a reference to a task's mm, if it is not already going away
+ * and ptrace_may_access with the mode parameter passed to it
+ * succeeds.
+ */
+extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode);
/* Remove the current tasks stale references to the old mm_struct */
extern void mm_release(struct task_struct *, struct mm_struct *);
/* Allocate a new mm structure and copy contents from tsk->mm */
extern void exit_itimers(struct signal_struct *);
extern void flush_itimer_signals(void);
-extern NORET_TYPE void do_group_exit(int);
+extern void do_group_exit(int);
extern void daemonize(const char *, ...);
extern int allow_signal(int);
return tsk->signal->nr_threads;
}
-/* de_thread depends on thread_group_leader not being a pid based check */
-#define thread_group_leader(p) (p == p->group_leader)
+static inline bool thread_group_leader(struct task_struct *p)
+{
+ return p->exit_signal >= 0;
+}
/* Do to the insanities of de_thread it is possible for a process
* to have the pid of the thread group leader without actually being
#define delay_group_leader(p) \
(thread_group_leader(p) && !thread_group_empty(p))
-static inline int task_detached(struct task_struct *p)
-{
- return p->exit_signal == -1;
-}
-
/*
* 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[].
+ * ->cgroup.subsys[]. And ->vfork_done.
*
* Nests both inside and outside of read_lock(&tasklist_lock).
* It must not be nested with write_lock_irq(&tasklist_lock),
extern struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
unsigned long *flags);
-#define lock_task_sighand(tsk, flags) \
-({ struct sighand_struct *__ss; \
- __cond_lock(&(tsk)->sighand->siglock, \
- (__ss = __lock_task_sighand(tsk, flags))); \
- __ss; \
-}) \
+static inline struct sighand_struct *lock_task_sighand(struct task_struct *tsk,
+ unsigned long *flags)
+{
+ struct sighand_struct *ret;
+
+ ret = __lock_task_sighand(tsk, flags);
+ (void)__cond_lock(&tsk->sighand->siglock, ret);
+ return ret;
+}
static inline void unlock_task_sighand(struct task_struct *tsk,
unsigned long *flags)
spin_unlock_irqrestore(&tsk->sighand->siglock, *flags);
}
-/* See the declaration of threadgroup_fork_lock in signal_struct. */
#ifdef CONFIG_CGROUPS
-static inline void threadgroup_fork_read_lock(struct task_struct *tsk)
+static inline void threadgroup_change_begin(struct task_struct *tsk)
{
- down_read(&tsk->signal->threadgroup_fork_lock);
+ down_read(&tsk->signal->group_rwsem);
}
-static inline void threadgroup_fork_read_unlock(struct task_struct *tsk)
+static inline void threadgroup_change_end(struct task_struct *tsk)
{
- up_read(&tsk->signal->threadgroup_fork_lock);
+ up_read(&tsk->signal->group_rwsem);
}
-static inline void threadgroup_fork_write_lock(struct task_struct *tsk)
+
+/**
+ * threadgroup_lock - lock threadgroup
+ * @tsk: member task of the threadgroup to lock
+ *
+ * Lock the threadgroup @tsk belongs to. No new task is allowed to enter
+ * and member tasks aren't allowed to exit (as indicated by PF_EXITING) or
+ * perform exec. This is useful for cases where the threadgroup needs to
+ * stay stable across blockable operations.
+ *
+ * fork and exit paths explicitly call threadgroup_change_{begin|end}() for
+ * synchronization. While held, no new task will be added to threadgroup
+ * and no existing live task will have its PF_EXITING set.
+ *
+ * During exec, a task goes and puts its thread group through unusual
+ * changes. After de-threading, exclusive access is assumed to resources
+ * which are usually shared by tasks in the same group - e.g. sighand may
+ * be replaced with a new one. Also, the exec'ing task takes over group
+ * leader role including its pid. Exclude these changes while locked by
+ * grabbing cred_guard_mutex which is used to synchronize exec path.
+ */
+static inline void threadgroup_lock(struct task_struct *tsk)
{
- down_write(&tsk->signal->threadgroup_fork_lock);
+ /*
+ * exec uses exit for de-threading nesting group_rwsem inside
+ * cred_guard_mutex. Grab cred_guard_mutex first.
+ */
+ mutex_lock(&tsk->signal->cred_guard_mutex);
+ down_write(&tsk->signal->group_rwsem);
}
-static inline void threadgroup_fork_write_unlock(struct task_struct *tsk)
+
+/**
+ * threadgroup_unlock - unlock threadgroup
+ * @tsk: member task of the threadgroup to unlock
+ *
+ * Reverse threadgroup_lock().
+ */
+static inline void threadgroup_unlock(struct task_struct *tsk)
{
- up_write(&tsk->signal->threadgroup_fork_lock);
+ up_write(&tsk->signal->group_rwsem);
+ mutex_unlock(&tsk->signal->cred_guard_mutex);
}
#else
-static inline void threadgroup_fork_read_lock(struct task_struct *tsk) {}
-static inline void threadgroup_fork_read_unlock(struct task_struct *tsk) {}
-static inline void threadgroup_fork_write_lock(struct task_struct *tsk) {}
-static inline void threadgroup_fork_write_unlock(struct task_struct *tsk) {}
+static inline void threadgroup_change_begin(struct task_struct *tsk) {}
+static inline void threadgroup_change_end(struct task_struct *tsk) {}
+static inline void threadgroup_lock(struct task_struct *tsk) {}
+static inline void threadgroup_unlock(struct task_struct *tsk) {}
#endif
#ifndef __HAVE_THREAD_FUNCTIONS
extern int __cond_resched_lock(spinlock_t *lock);
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPT_COUNT
#define PREEMPT_LOCK_OFFSET PREEMPT_OFFSET
#else
#define PREEMPT_LOCK_OFFSET 0
static inline void thread_group_cputime_init(struct signal_struct *sig)
{
- spin_lock_init(&sig->cputimer.lock);
+ raw_spin_lock_init(&sig->cputimer.lock);
}
/*