sched.h

来自「linux 内核源代码」· C头文件 代码 · 共 1,993 行 · 第 1/4 页

#ifdef CONFIG_BSD_PROCESS_ACCT
	struct pacct_struct pacct;	/* per-process accounting information */
#endif
#ifdef CONFIG_TASKSTATS
	struct taskstats *stats;
#endif
#ifdef CONFIG_AUDIT
	unsigned audit_tty;
	struct tty_audit_buf *tty_audit_buf;
#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 */

/*
 * Some day this will be a full-fledged user tracking system..
 */
struct user_struct {
	atomic_t __count;	/* reference count */
	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_USER
	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
#ifdef CONFIG_POSIX_MQUEUE
	/* protected by mq_lock	*/
	unsigned long mq_bytes;	/* How many bytes can be allocated to mqueue? */
#endif
	unsigned long locked_shm; /* How many pages of mlocked shm ? */

#ifdef CONFIG_KEYS
	struct key *uid_keyring;	/* UID specific keyring */
	struct key *session_keyring;	/* UID's default session keyring */
#endif

	/* Hash table maintenance information */
	struct hlist_node uidhash_node;
	uid_t uid;

#ifdef CONFIG_FAIR_USER_SCHED
	struct task_group *tg;
#ifdef CONFIG_SYSFS
	struct kset kset;
	struct subsys_attribute user_attr;
	struct work_struct work;
#endif
#endif
};

#ifdef CONFIG_FAIR_USER_SCHED
extern int uids_kobject_init(void);
#else
static inline int uids_kobject_init(void) { return 0; }
#endif

extern struct user_struct *find_user(uid_t);

extern struct user_struct root_user;
#define INIT_USER (&root_user)

struct backing_dev_info;
struct reclaim_state;

#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
struct sched_info {
	/* cumulative counters */
	unsigned long pcount;	      /* # of times run on this cpu */
	unsigned long long cpu_time,  /* time spent on the cpu */
			   run_delay; /* time spent waiting on a runqueue */

	/* timestamps */
	unsigned long long last_arrival,/* when we last ran on a cpu */
			   last_queued;	/* when we were last queued to run */
#ifdef CONFIG_SCHEDSTATS
	/* BKL stats */
	unsigned int bkl_count;
#endif
};
#endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */

#ifdef CONFIG_SCHEDSTATS
extern const struct file_operations proc_schedstat_operations;
#endif /* CONFIG_SCHEDSTATS */

#ifdef CONFIG_TASK_DELAY_ACCT
struct task_delay_info {
	spinlock_t	lock;
	unsigned int	flags;	/* Private per-task flags */

	/* For each stat XXX, add following, aligned appropriately
	 *
	 * struct timespec XXX_start, XXX_end;
	 * u64 XXX_delay;
	 * u32 XXX_count;
	 *
	 * Atomicity of updates to XXX_delay, XXX_count protected by
	 * single lock above (split into XXX_lock if contention is an issue).
	 */

	/*
	 * XXX_count is incremented on every XXX operation, the delay
	 * associated with the operation is added to XXX_delay.
	 * XXX_delay contains the accumulated delay time in nanoseconds.
	 */
	struct timespec blkio_start, blkio_end;	/* Shared by blkio, swapin */
	u64 blkio_delay;	/* wait for sync block io completion */
	u64 swapin_delay;	/* wait for swapin block io completion */
	u32 blkio_count;	/* total count of the number of sync block */
				/* io operations performed */
	u32 swapin_count;	/* total count of the number of swapin block */
				/* io operations performed */
};
#endif	/* CONFIG_TASK_DELAY_ACCT */

static inline int sched_info_on(void)
{
#ifdef CONFIG_SCHEDSTATS
	return 1;
#elif defined(CONFIG_TASK_DELAY_ACCT)
	extern int delayacct_on;
	return delayacct_on;
#else
	return 0;
#endif
}

enum cpu_idle_type {
	CPU_IDLE,
	CPU_NOT_IDLE,
	CPU_NEWLY_IDLE,
	CPU_MAX_IDLE_TYPES
};

/*
 * sched-domains (multiprocessor balancing) declarations:
 */

/*
 * Increase resolution of nice-level calculations:
 */
#define SCHED_LOAD_SHIFT	10
#define SCHED_LOAD_SCALE	(1L << SCHED_LOAD_SHIFT)

#define SCHED_LOAD_SCALE_FUZZ	SCHED_LOAD_SCALE

#ifdef CONFIG_SMP
#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_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 */
#define SD_POWERSAVINGS_BALANCE	256	/* Balance for power savings */
#define SD_SHARE_PKG_RESOURCES	512	/* Domain members share cpu pkg resources */
#define SD_SERIALIZE		1024	/* Only a single load balancing instance */

#define BALANCE_FOR_MC_POWER	\
	(sched_smt_power_savings ? SD_POWERSAVINGS_BALANCE : 0)

#define BALANCE_FOR_PKG_POWER	\
	((sched_mc_power_savings || sched_smt_power_savings) ?	\
	 SD_POWERSAVINGS_BALANCE : 0)

#define test_sd_parent(sd, flag)	((sd->parent &&		\
					 (sd->parent->flags & flag)) ? 1 : 0)


struct sched_group {
	struct sched_group *next;	/* Must be a circular list */
	cpumask_t cpumask;

	/*
	 * CPU power of this group, SCHED_LOAD_SCALE being max power for a
	 * single CPU. This is read only (except for setup, hotplug CPU).
	 * Note : Never change cpu_power without recompute its reciprocal
	 */
	unsigned int __cpu_power;
	/*
	 * reciprocal value of cpu_power to avoid expensive divides
	 * (see include/linux/reciprocal_div.h)
	 */
	u32 reciprocal_cpu_power;
};

struct sched_domain {
	/* These fields must be setup */
	struct sched_domain *parent;	/* top domain must be null terminated */
	struct sched_domain *child;	/* bottom domain must be null terminated */
	struct sched_group *groups;	/* the balancing groups of the domain */
	cpumask_t span;			/* span of all CPUs in this domain */
	unsigned long min_interval;	/* Minimum balance interval ms */
	unsigned long max_interval;	/* Maximum balance interval ms */
	unsigned int busy_factor;	/* less balancing by factor if busy */
	unsigned int imbalance_pct;	/* No balance until over watermark */
	unsigned int cache_nice_tries;	/* Leave cache hot tasks for # tries */
	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. */
	unsigned long last_balance;	/* init to jiffies. units in jiffies */
	unsigned int balance_interval;	/* initialise to 1. units in ms. */
	unsigned int nr_balance_failed; /* initialise to 0 */

#ifdef CONFIG_SCHEDSTATS
	/* load_balance() stats */
	unsigned int lb_count[CPU_MAX_IDLE_TYPES];
	unsigned int lb_failed[CPU_MAX_IDLE_TYPES];
	unsigned int lb_balanced[CPU_MAX_IDLE_TYPES];
	unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES];
	unsigned int lb_gained[CPU_MAX_IDLE_TYPES];
	unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES];
	unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES];
	unsigned int lb_nobusyq[CPU_MAX_IDLE_TYPES];

	/* Active load balancing */
	unsigned int alb_count;
	unsigned int alb_failed;
	unsigned int alb_pushed;

	/* SD_BALANCE_EXEC stats */
	unsigned int sbe_count;
	unsigned int sbe_balanced;
	unsigned int sbe_pushed;

	/* SD_BALANCE_FORK stats */
	unsigned int sbf_count;
	unsigned int sbf_balanced;
	unsigned int sbf_pushed;

	/* try_to_wake_up() stats */
	unsigned int ttwu_wake_remote;
	unsigned int ttwu_move_affine;
	unsigned int ttwu_move_balance;
#endif
};

extern void partition_sched_domains(int ndoms_new, cpumask_t *doms_new);

#endif	/* CONFIG_SMP */

/*
 * A runqueue laden with a single nice 0 task scores a weighted_cpuload of
 * SCHED_LOAD_SCALE. This function returns 1 if any cpu is laden with a
 * task of nice 0 or enough lower priority tasks to bring up the
 * weighted_cpuload
 */
static inline int above_background_load(void)
{
	unsigned long cpu;

	for_each_online_cpu(cpu) {
		if (weighted_cpuload(cpu) >= SCHED_LOAD_SCALE)
			return 1;
	}
	return 0;
}

struct io_context;			/* See blkdev.h */
#define NGROUPS_SMALL		32
#define NGROUPS_PER_BLOCK	((int)(PAGE_SIZE / sizeof(gid_t)))
struct group_info {
	int ngroups;
	atomic_t usage;
	gid_t small_block[NGROUPS_SMALL];
	int nblocks;
	gid_t *blocks[0];
};

/*
 * get_group_info() must be called with the owning task locked (via task_lock())
 * when task != current.  The reason being that the vast majority of callers are
 * looking at current->group_info, which can not be changed except by the
 * current task.  Changing current->group_info requires the task lock, too.
 */
#define get_group_info(group_info) do { \
	atomic_inc(&(group_info)->usage); \
} while (0)

#define put_group_info(group_info) do { \
	if (atomic_dec_and_test(&(group_info)->usage)) \
		groups_free(group_info); \
} while (0)

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 *t);
#else
static inline void prefetch_stack(struct task_struct *t) { }
#endif

struct audit_context;		/* See audit.c */
struct mempolicy;
struct pipe_inode_info;
struct uts_namespace;

struct rq;
struct sched_domain;

struct sched_class {
	const struct sched_class *next;

	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup);
	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep);
	void (*yield_task) (struct rq *rq);

	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p);

	struct task_struct * (*pick_next_task) (struct rq *rq);
	void (*put_prev_task) (struct rq *rq, struct task_struct *p);

#ifdef CONFIG_SMP
	unsigned long (*load_balance) (struct rq *this_rq, int this_cpu,
			struct rq *busiest, unsigned long max_load_move,
			struct sched_domain *sd, enum cpu_idle_type idle,
			int *all_pinned, int *this_best_prio);

	int (*move_one_task) (struct rq *this_rq, int this_cpu,
			      struct rq *busiest, struct sched_domain *sd,
			      enum cpu_idle_type idle);
#endif

	void (*set_curr_task) (struct rq *rq);
	void (*task_tick) (struct rq *rq, struct task_struct *p);
	void (*task_new) (struct rq *rq, struct task_struct *p);
};

struct load_weight {
	unsigned long weight, inv_weight;
};

/*
 * CFS stats for a schedulable entity (task, task-group etc)
 *
 * Current field usage histogram:
 *
 *     4 se->block_start
 *     4 se->run_node
 *     4 se->sleep_start
 *     6 se->load.weight
 */
struct sched_entity {
	struct load_weight	load;		/* for load-balancing */
	struct rb_node		run_node;
	unsigned int		on_rq;

	u64			exec_start;
	u64			sum_exec_runtime;
	u64			vruntime;
	u64			prev_sum_exec_runtime;

#ifdef CONFIG_SCHEDSTATS
	u64			wait_start;
	u64			wait_max;

	u64			sleep_start;
	u64			sleep_max;
	s64			sum_sleep_runtime;

	u64			block_start;
	u64			block_max;
	u64			exec_max;
	u64			slice_max;

	u64			nr_migrations;
	u64			nr_migrations_cold;
	u64			nr_failed_migrations_affine;
	u64			nr_failed_migrations_running;
	u64			nr_failed_migrations_hot;
	u64			nr_forced_migrations;
	u64			nr_forced2_migrations;

	u64			nr_wakeups;
	u64			nr_wakeups_sync;
	u64			nr_wakeups_migrate;
	u64			nr_wakeups_local;
	u64			nr_wakeups_remote;
	u64			nr_wakeups_affine;
	u64			nr_wakeups_affine_attempts;
	u64			nr_wakeups_passive;
	u64			nr_wakeups_idle;
#endif

#ifdef CONFIG_FAIR_GROUP_SCHED
	struct sched_entity	*parent;
	/* rq on which this entity is (to be) queued: */
	struct cfs_rq		*cfs_rq;
	/* rq "owned" by this entity/group: */
	struct cfs_rq		*my_q;
#endif
};

struct task_struct {
	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
	void *stack;
	atomic_t usage;
	unsigned int flags;	/* per process flags, defined below */
	unsigned int ptrace;

	int lock_depth;		/* BKL lock depth */

#ifdef CONFIG_SMP
#ifdef __ARCH_WANT_UNLOCKED_CTXSW
	int oncpu;
#endif
#endif

	int prio, static_prio, normal_prio;
	struct list_head run_list;
	const struct sched_class *sched_class;
	struct sched_entity se;

#ifdef CONFIG_PREEMPT_NOTIFIERS
	/* list of struct preempt_notifier: */
	struct hlist_head preempt_notifiers;
#endif

	unsigned short ioprio;
	/*
	 * fpu_counter contains the number of consecutive context switches
	 * that the FPU is used. If this is over a threshold, the lazy fpu
	 * saving becomes unlazy to save the trap. This is an unsigned char
	 * so that after 256 times the counter wraps and the behavior turns
	 * lazy again; this to deal with bursty apps that only use FPU for
	 * a short time
	 */
	unsigned char fpu_counter;
	s8 oomkilladj; /* OOM kill score adjustment (bit shift). */
#ifdef CONFIG_BLK_DEV_IO_TRACE
	unsigned int btrace_seq;
#endif

	unsigned int policy;
	cpumask_t cpus_allowed;
	unsigned int time_slice;

#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
	struct sched_info sched_info;
#endif

	struct list_head tasks;
	/*
	 * ptrace_list/ptrace_children forms the list of my children
	 * that were stolen by a ptracer.
	 */
	struct list_head ptrace_children;
	struct list_head ptrace_list;

	struct mm_struct *mm, *active_mm;

/* task state */
	struct linux_binfmt *binfmt;
	int exit_state;
	int exit_code, exit_signal;
	int pdeath_signal;  /*  The signal sent when the parent dies  */
	/* ??? */
	unsigned int personality;
	unsigned did_exec:1;
	pid_t pid;
	pid_t tgid;

#ifdef CONFIG_CC_STACKPROTECTOR
	/* Canary value for the -fstack-protector gcc feature */
	unsigned long stack_canary;
#endif
	/* 
	 * pointers to (original) parent process, youngest child, younger sibling,
	 * older sibling, respectively.  (p->father can be replaced with 
	 * p->parent->pid)
	 */
	struct task_struct *real_parent; /* real parent process (when being debugged) */
	struct task_struct *parent;	/* parent process */
	/*
	 * children/sibling forms the list of my children plus the