}
#endif
-#ifdef CONFIG_DETECT_HUNG_TASK
-extern unsigned int sysctl_hung_task_panic;
-extern unsigned long sysctl_hung_task_check_count;
-extern unsigned long sysctl_hung_task_timeout_secs;
-extern unsigned long sysctl_hung_task_warnings;
-extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
- void __user *buffer,
- size_t *lenp, loff_t *ppos);
-#else
-/* Avoid need for ifdefs elsewhere in the code */
-enum { sysctl_hung_task_timeout_secs = 0 };
-#endif
-
/* Attach to any functions which should be ignored in wchan output. */
#define __sched __attribute__((__section__(".sched.text")))
struct nsproxy;
struct user_namespace;
-/*
- * Default maximum number of active map areas, this limits the number of vmas
- * per mm struct. Users can overwrite this number by sysctl but there is a
- * problem.
- *
- * When a program's coredump is generated as ELF format, a section is created
- * per a vma. In ELF, the number of sections is represented in unsigned short.
- * This means the number of sections should be smaller than 65535 at coredump.
- * Because the kernel adds some informative sections to a image of program at
- * generating coredump, we need some margin. The number of extra sections is
- * 1-3 now and depends on arch. We use "5" as safe margin, here.
- */
-#define MAPCOUNT_ELF_CORE_MARGIN (5)
-#define DEFAULT_MAX_MAP_COUNT (USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN)
-
-extern int sysctl_max_map_count;
-
#include <linux/aio.h>
#ifdef CONFIG_MMU
/* rq "owned" by this entity/group: */
struct cfs_rq *my_q;
#endif
+
/*
* Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
* removed when useful for applications beyond shares distribution (e.g.
struct sched_rt_entity {
struct list_head run_list;
unsigned long timeout;
+ unsigned long watchdog_stamp;
unsigned int time_slice;
struct sched_rt_entity *back;
#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;
cputime_t gtime;
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
struct cputime prev_cputime;
+#endif
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+ seqlock_t vtime_seqlock;
+ unsigned long long vtime_snap;
+ enum {
+ VTIME_SLEEPING = 0,
+ VTIME_USER,
+ VTIME_SYS,
+ } vtime_snap_whence;
#endif
unsigned long nvcsw, nivcsw; /* context switch counts */
struct timespec start_time; /* monotonic time */
}
#endif
-/*
- * Priority of a process goes from 0..MAX_PRIO-1, valid RT
- * 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
- * user-space. This allows kernel threads to set their
- * priority to a value higher than any user task. Note:
- * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO.
- */
-
-#define MAX_USER_RT_PRIO 100
-#define MAX_RT_PRIO MAX_USER_RT_PRIO
-
-#define MAX_PRIO (MAX_RT_PRIO + 40)
-#define DEFAULT_PRIO (MAX_RT_PRIO + 20)
-
-static inline int rt_prio(int prio)
-{
- if (unlikely(prio < MAX_RT_PRIO))
- return 1;
- return 0;
-}
-
-static inline int rt_task(struct task_struct *p)
-{
- return rt_prio(p->prio);
-}
-
static inline struct pid *task_pid(struct task_struct *task)
{
return task->pids[PIDTYPE_PID].pid;
__put_task_struct(t);
}
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+extern void task_cputime(struct task_struct *t,
+ cputime_t *utime, cputime_t *stime);
+extern void task_cputime_scaled(struct task_struct *t,
+ cputime_t *utimescaled, cputime_t *stimescaled);
+extern cputime_t task_gtime(struct task_struct *t);
+#else
+static inline void task_cputime(struct task_struct *t,
+ cputime_t *utime, cputime_t *stime)
+{
+ if (utime)
+ *utime = t->utime;
+ if (stime)
+ *stime = t->stime;
+}
+
+static inline void task_cputime_scaled(struct task_struct *t,
+ cputime_t *utimescaled,
+ cputime_t *stimescaled)
+{
+ if (utimescaled)
+ *utimescaled = t->utimescaled;
+ if (stimescaled)
+ *stimescaled = t->stimescaled;
+}
+
+static inline cputime_t task_gtime(struct task_struct *t)
+{
+ return t->gtime;
+}
+#endif
extern void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
#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_USED_ASYNC 0x00004000 /* used async_schedule*(), used by module init */
#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 */
static inline void wake_up_idle_cpu(int cpu) { }
#endif
-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_child_runs_first;
-
-enum sched_tunable_scaling {
- SCHED_TUNABLESCALING_NONE,
- SCHED_TUNABLESCALING_LOG,
- SCHED_TUNABLESCALING_LINEAR,
- SCHED_TUNABLESCALING_END,
-};
-extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;
-
-extern unsigned int sysctl_numa_balancing_scan_delay;
-extern unsigned int sysctl_numa_balancing_scan_period_min;
-extern unsigned int sysctl_numa_balancing_scan_period_max;
-extern unsigned int sysctl_numa_balancing_scan_period_reset;
-extern unsigned int sysctl_numa_balancing_scan_size;
-extern unsigned int sysctl_numa_balancing_settle_count;
-
-#ifdef CONFIG_SCHED_DEBUG
-extern unsigned int sysctl_sched_migration_cost;
-extern unsigned int sysctl_sched_nr_migrate;
-extern unsigned int sysctl_sched_time_avg;
-extern unsigned int sysctl_timer_migration;
-extern unsigned int sysctl_sched_shares_window;
-
-int sched_proc_update_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *length,
- loff_t *ppos);
-#endif
-#ifdef CONFIG_SCHED_DEBUG
-static inline unsigned int get_sysctl_timer_migration(void)
-{
- return sysctl_timer_migration;
-}
-#else
-static inline unsigned int get_sysctl_timer_migration(void)
-{
- return 1;
-}
-#endif
-extern unsigned int sysctl_sched_rt_period;
-extern int sysctl_sched_rt_runtime;
-
-int sched_rt_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *lenp,
- loff_t *ppos);
-
#ifdef CONFIG_SCHED_AUTOGROUP
-extern unsigned int sysctl_sched_autogroup_enabled;
-
extern void sched_autogroup_create_attach(struct task_struct *p);
extern void sched_autogroup_detach(struct task_struct *p);
extern 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);
-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 void set_user_nice(struct task_struct *p, long nice);
extern int task_prio(const struct task_struct *p);
extern void recalc_sigpending_and_wake(struct task_struct *t);
extern void recalc_sigpending(void);
-extern void signal_wake_up(struct task_struct *t, int resume_stopped);
+extern void signal_wake_up_state(struct task_struct *t, unsigned int state);
+
+static inline void signal_wake_up(struct task_struct *t, bool resume)
+{
+ signal_wake_up_state(t, resume ? TASK_WAKEKILL : 0);
+}
+static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume)
+{
+ signal_wake_up_state(t, resume ? __TASK_TRACED : 0);
+}
/*
* Wrappers for p->thread_info->cpu access. No-op on UP.
extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
-extern void normalize_rt_tasks(void);
-
#ifdef CONFIG_CGROUP_SCHED
extern struct task_group root_task_group;
extern struct task_group *sched_create_group(struct task_group *parent);
+ extern void sched_online_group(struct task_group *tg,
+ struct task_group *parent);
extern void sched_destroy_group(struct task_group *tg);
+ extern void sched_offline_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);
#endif
#include "sched.h"
-#include "../workqueue_sched.h"
+#include "../workqueue_internal.h"
#include "../smpboot.h"
#define CREATE_TRACE_POINTS
*/
int wake_up_process(struct task_struct *p)
{
- return try_to_wake_up(p, TASK_ALL, 0);
+ WARN_ON(task_is_stopped_or_traced(p));
+ return try_to_wake_up(p, TASK_NORMAL, 0);
}
EXPORT_SYMBOL(wake_up_process);
struct task_struct *curr = current;
struct rq *rq, *p_rq;
unsigned long flags;
- bool yielded = 0;
+ int yielded = 0;
local_irq_save(flags);
rq = this_rq();
*/
idle->sched_class = &idle_sched_class;
ftrace_graph_init_idle_task(idle, cpu);
+ vtime_init_idle(idle);
#if defined(CONFIG_SMP)
sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
#endif
struct task_group *sched_create_group(struct task_group *parent)
{
struct task_group *tg;
- unsigned long flags;
tg = kzalloc(sizeof(*tg), GFP_KERNEL);
if (!tg)
if (!alloc_rt_sched_group(tg, parent))
goto err;
+ return tg;
+
+ err:
+ free_sched_group(tg);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ void sched_online_group(struct task_group *tg, struct task_group *parent)
+ {
+ unsigned long flags;
+
spin_lock_irqsave(&task_group_lock, flags);
list_add_rcu(&tg->list, &task_groups);
INIT_LIST_HEAD(&tg->children);
list_add_rcu(&tg->siblings, &parent->children);
spin_unlock_irqrestore(&task_group_lock, flags);
-
- return tg;
-
- err:
- free_sched_group(tg);
- return ERR_PTR(-ENOMEM);
}
/* rcu callback to free various structures associated with a task group */
/* Destroy runqueue etc associated with a task group */
void sched_destroy_group(struct task_group *tg)
+ {
+ /* wait for possible concurrent references to cfs_rqs complete */
+ call_rcu(&tg->rcu, free_sched_group_rcu);
+ }
+
+ void sched_offline_group(struct task_group *tg)
{
unsigned long flags;
int i;
list_del_rcu(&tg->list);
list_del_rcu(&tg->siblings);
spin_unlock_irqrestore(&task_group_lock, flags);
-
- /* wait for possible concurrent references to cfs_rqs complete */
- call_rcu(&tg->rcu, free_sched_group_rcu);
}
/* change task's runqueue when it moves between groups.
}
#endif /* CONFIG_RT_GROUP_SCHED */
+int sched_rr_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ int ret;
+ static DEFINE_MUTEX(mutex);
+
+ mutex_lock(&mutex);
+ ret = proc_dointvec(table, write, buffer, lenp, ppos);
+ /* make sure that internally we keep jiffies */
+ /* also, writing zero resets timeslice to default */
+ if (!ret && write) {
+ sched_rr_timeslice = sched_rr_timeslice <= 0 ?
+ RR_TIMESLICE : msecs_to_jiffies(sched_rr_timeslice);
+ }
+ mutex_unlock(&mutex);
+ return ret;
+}
+
int sched_rt_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
return &tg->css;
}
+ static int cpu_cgroup_css_online(struct cgroup *cgrp)
+ {
+ struct task_group *tg = cgroup_tg(cgrp);
+ struct task_group *parent;
+
+ if (!cgrp->parent)
+ return 0;
+
+ parent = cgroup_tg(cgrp->parent);
+ sched_online_group(tg, parent);
+ return 0;
+ }
+
static void cpu_cgroup_css_free(struct cgroup *cgrp)
{
struct task_group *tg = cgroup_tg(cgrp);
sched_destroy_group(tg);
}
+ static void cpu_cgroup_css_offline(struct cgroup *cgrp)
+ {
+ struct task_group *tg = cgroup_tg(cgrp);
+
+ sched_offline_group(tg);
+ }
+
static int cpu_cgroup_can_attach(struct cgroup *cgrp,
struct cgroup_taskset *tset)
{
.name = "cpu",
.css_alloc = cpu_cgroup_css_alloc,
.css_free = cpu_cgroup_css_free,
+ .css_online = cpu_cgroup_css_online,
+ .css_offline = cpu_cgroup_css_offline,
.can_attach = cpu_cgroup_can_attach,
.attach = cpu_cgroup_attach,
.exit = cpu_cgroup_exit,
help:
@echo 'Possible targets:'
@echo ''
+ @echo ' cgroup - cgroup tools'
@echo ' cpupower - a tool for all things x86 CPU power'
@echo ' firewire - the userspace part of nosy, an IEEE-1394 traffic sniffer'
@echo ' lguest - a minimal 32-bit x86 hypervisor'
@echo ' x86_energy_perf_policy - Intel energy policy tool'
@echo ''
@echo 'You can do:'
- @echo ' $$ make -C tools/<tool>_install'
+ @echo ' $$ make -C tools/ <tool>_install'
@echo ''
@echo ' from the kernel command line to build and install one of'
@echo ' the tools above'
cpupower: FORCE
$(call descend,power/$@)
- firewire lguest perf usb virtio vm: FORCE
+ cgroup firewire lguest perf usb virtio vm: FORCE
$(call descend,$@)
selftests: FORCE
cpupower_install:
$(call descend,power/$(@:_install=),install)
- firewire_install lguest_install perf_install usb_install virtio_install vm_install:
+ cgroup_install firewire_install lguest_install perf_install usb_install virtio_install vm_install:
$(call descend,$(@:_install=),install)
selftests_install:
turbostat_install x86_energy_perf_policy_install:
$(call descend,power/x86/$(@:_install=),install)
- install: cpupower_install firewire_install lguest_install perf_install \
- selftests_install turbostat_install usb_install virtio_install \
- vm_install x86_energy_perf_policy_install
+ install: cgroup_install cpupower_install firewire_install lguest_install \
+ perf_install selftests_install turbostat_install usb_install \
+ virtio_install vm_install x86_energy_perf_policy_install
cpupower_clean:
$(call descend,power/cpupower,clean)
- firewire_clean lguest_clean perf_clean usb_clean virtio_clean vm_clean:
+ cgroup_clean firewire_clean lguest_clean perf_clean usb_clean virtio_clean vm_clean:
$(call descend,$(@:_clean=),clean)
selftests_clean:
turbostat_clean x86_energy_perf_policy_clean:
$(call descend,power/x86/$(@:_clean=),clean)
- clean: cpupower_clean firewire_clean lguest_clean perf_clean selftests_clean \
- turbostat_clean usb_clean virtio_clean vm_clean \
- x86_energy_perf_policy_clean
+ clean: cgroup_clean cpupower_clean firewire_clean lguest_clean perf_clean \
+ selftests_clean turbostat_clean usb_clean virtio_clean \
+ vm_clean x86_energy_perf_policy_clean
.PHONY: FORCE