aboutsummaryrefslogtreecommitdiff
path: root/include/linux/sched.h
diff options
context:
space:
mode:
Diffstat (limited to 'include/linux/sched.h')
-rw-r--r--include/linux/sched.h137
1 files changed, 101 insertions, 36 deletions
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 41d0237fd44..4032ec1cf83 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -90,6 +90,7 @@ struct sched_param {
#include <linux/task_io_accounting.h>
#include <linux/latencytop.h>
#include <linux/cred.h>
+#include <linux/llist.h>
#include <asm/processor.h>
@@ -219,7 +220,7 @@ extern char ___assert_task_state[1 - 2*!!(
((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)
@@ -270,12 +271,13 @@ extern void init_idle_bootup_task(struct task_struct *idle);
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
/*
@@ -483,8 +485,8 @@ struct task_cputime {
#define INIT_CPUTIME \
(struct task_cputime) { \
- .utime = cputime_zero, \
- .stime = cputime_zero, \
+ .utime = 0, \
+ .stime = 0, \
.sum_exec_runtime = 0, \
}
@@ -510,7 +512,7 @@ struct task_cputime {
struct thread_group_cputimer {
struct task_cputime cputime;
int running;
- spinlock_t lock;
+ raw_spinlock_t lock;
};
#include <linux/rwsem.h>
@@ -635,13 +637,15 @@ struct signal_struct {
#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) */
@@ -901,6 +905,10 @@ struct sched_group_power {
* single CPU.
*/
unsigned int power, power_orig;
+ /*
+ * Number of busy cpus in this group.
+ */
+ atomic_t nr_busy_cpus;
};
struct sched_group {
@@ -925,6 +933,15 @@ static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
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;
};
@@ -1225,7 +1242,7 @@ struct task_struct {
unsigned int ptrace;
#ifdef CONFIG_SMP
- struct task_struct *wake_entry;
+ struct llist_node wake_entry;
int on_cpu;
#endif
int on_rq;
@@ -1260,9 +1277,6 @@ struct task_struct {
#ifdef CONFIG_PREEMPT_RCU
int rcu_read_lock_nesting;
char rcu_read_unlock_special;
-#if defined(CONFIG_RCU_BOOST) && defined(CONFIG_TREE_PREEMPT_RCU)
- int rcu_boosted;
-#endif /* #if defined(CONFIG_RCU_BOOST) && defined(CONFIG_TREE_PREEMPT_RCU) */
struct list_head rcu_node_entry;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_TREE_PREEMPT_RCU
@@ -1318,8 +1332,8 @@ struct task_struct {
* 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
*/
@@ -1524,7 +1538,14 @@ struct task_struct {
#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];
@@ -1769,7 +1790,6 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
#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 */
@@ -1785,7 +1805,6 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
#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
@@ -2039,6 +2058,10 @@ static inline void sched_autogroup_fork(struct signal_struct *sig) { }
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);
@@ -2063,6 +2086,14 @@ extern int sched_setscheduler(struct task_struct *, int,
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?
+ * @tsk: the task in question.
+ */
+static inline bool is_idle_task(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);
@@ -2165,7 +2196,8 @@ 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_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);
@@ -2243,7 +2275,7 @@ extern void __cleanup_sighand(struct sighand_struct *);
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);
@@ -2365,29 +2397,62 @@ static inline void unlock_task_sighand(struct task_struct *tsk,
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
@@ -2565,7 +2630,7 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
static inline void thread_group_cputime_init(struct signal_struct *sig)
{
- spin_lock_init(&sig->cputimer.lock);
+ raw_spin_lock_init(&sig->cputimer.lock);
}
/*