sched.h

包括初始化、进程管理、进程通信、内存管理、设备管理、中断、文件系统、系统调用等精选源码分析。

#ifndef _LINUX_SCHED_H
#define _LINUX_SCHED_H

#include <asm/param.h>	/* for HZ */

extern unsigned long event;

#include <linux/config.h>
#include <linux/binfmts.h>
#include <linux/personality.h>
#include <linux/threads.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/times.h>
#include <linux/timex.h>

#include <asm/system.h>
#include <asm/semaphore.h>
#include <asm/page.h>
#include <asm/ptrace.h>
#include <asm/mmu.h>

#include <linux/smp.h>
#include <linux/tty.h>
#include <linux/sem.h>
#include <linux/signal.h>
#include <linux/securebits.h>
#include <linux/fs_struct.h>

/*
 * cloning flags:
 */
#define CSIGNAL		0x000000ff	/* signal mask to be sent at exit */
#define CLONE_VM	0x00000100	/* set if VM shared between processes */
#define CLONE_FS	0x00000200	/* set if fs info shared between processes */
#define CLONE_FILES	0x00000400	/* set if open files shared between processes */
#define CLONE_SIGHAND	0x00000800	/* set if signal handlers and blocked signals shared */
#define CLONE_PID	0x00001000	/* set if pid shared */
#define CLONE_PTRACE	0x00002000	/* set if we want to let tracing continue on the child too */
#define CLONE_VFORK	0x00004000	/* set if the parent wants the child to wake it up on mm_release */
#define CLONE_PARENT	0x00008000	/* set if we want to have the same parent as the cloner */
#define CLONE_THREAD	0x00010000	/* Same thread group? */

#define CLONE_SIGNAL	(CLONE_SIGHAND | CLONE_THREAD)

/*
 * These are the constant used to fake the fixed-point load-average
 * counting. Some notes:
 *  - 11 bit fractions expand to 22 bits by the multiplies: this gives
 *    a load-average precision of 10 bits integer + 11 bits fractional
 *  - if you want to count load-averages more often, you need more
 *    precision, or rounding will get you. With 2-second counting freq,
 *    the EXP_n values would be 1981, 2034 and 2043 if still using only
 *    11 bit fractions.
 */
extern unsigned long avenrun[];		/* Load averages */

#define FSHIFT		11		/* nr of bits of precision */
#define FIXED_1		(1<<FSHIFT)	/* 1.0 as fixed-point */
#define LOAD_FREQ	(5*HZ)		/* 5 sec intervals */
#define EXP_1		1884		/* 1/exp(5sec/1min) as fixed-point */
#define EXP_5		2014		/* 1/exp(5sec/5min) */
#define EXP_15		2037		/* 1/exp(5sec/15min) */

#define CALC_LOAD(load,exp,n) \
	load *= exp; \
	load += n*(FIXED_1-exp); \
	load >>= FSHIFT;

#define CT_TO_SECS(x)	((x) / HZ)
#define CT_TO_USECS(x)	(((x) % HZ) * 1000000/HZ)

extern int nr_running, nr_threads;
extern int last_pid;

#include <linux/fs.h>
#include <linux/time.h>
#include <linux/param.h>
#include <linux/resource.h>
#include <linux/timer.h>

#include <asm/processor.h>

#define TASK_RUNNING		0
#define TASK_INTERRUPTIBLE	1
#define TASK_UNINTERRUPTIBLE	2
#define TASK_ZOMBIE		4
#define TASK_STOPPED		8

#define __set_task_state(tsk, state_value)		\
	do { (tsk)->state = (state_value); } while (0)
#ifdef CONFIG_SMP
#define set_task_state(tsk, state_value)		\
	set_mb((tsk)->state, (state_value))
#else
#define set_task_state(tsk, state_value)		\
	__set_task_state((tsk), (state_value))
#endif

#define __set_current_state(state_value)			\
	do { current->state = (state_value); } while (0)
#ifdef CONFIG_SMP
#define set_current_state(state_value)		\
	set_mb(current->state, (state_value))
#else
#define set_current_state(state_value)		\
	__set_current_state(state_value)
#endif

/*
 * Scheduling policies
 */
#define SCHED_OTHER		0
#define SCHED_FIFO		1
#define SCHED_RR		2

/*
 * This is an additional bit set when we want to
 * yield the CPU for one re-schedule..
 */
#define SCHED_YIELD		0x10

struct sched_param {
	int sched_priority;
};

#ifdef __KERNEL__

#include <linux/spinlock.h>

/*
 * This serializes "schedule()" and also protects
 * the run-queue from deletions/modifications (but
 * _adding_ to the beginning of the run-queue has
 * a separate lock).
 */
extern rwlock_t tasklist_lock;
extern spinlock_t runqueue_lock;
extern spinlock_t mmlist_lock;

extern void sched_init(void);
extern void init_idle(void);
extern void show_state(void);
extern void cpu_init (void);
extern void trap_init(void);
extern void update_process_times(int user);
extern void update_one_process(struct task_struct *p, unsigned long user,
			       unsigned long system, int cpu);

#define	MAX_SCHEDULE_TIMEOUT	LONG_MAX
extern signed long FASTCALL(schedule_timeout(signed long timeout));
asmlinkage void schedule(void);

extern int schedule_task(struct tq_struct *task);
extern void flush_scheduled_tasks(void);
extern int start_context_thread(void);
extern int current_is_keventd(void);

/*
 * The default fd array needs to be at least BITS_PER_LONG,
 * as this is the granularity returned by copy_fdset().
 */
#define NR_OPEN_DEFAULT BITS_PER_LONG

/*
 * Open file table structure
 */
struct files_struct {
	atomic_t count;
	rwlock_t file_lock;
	int max_fds;
	int max_fdset;
	int next_fd;
	struct file ** fd;	/* current fd array */
	fd_set *close_on_exec;
	fd_set *open_fds;
	fd_set close_on_exec_init;
	fd_set open_fds_init;
	struct file * fd_array[NR_OPEN_DEFAULT];
};

#define INIT_FILES \
{ 							\
	count:		ATOMIC_INIT(1), 		\
	file_lock:	RW_LOCK_UNLOCKED, 		\
	max_fds:	NR_OPEN_DEFAULT, 		\
	max_fdset:	__FD_SETSIZE, 			\
	next_fd:	0, 				\
	fd:		&init_files.fd_array[0], 	\
	close_on_exec:	&init_files.close_on_exec_init, \
	open_fds:	&init_files.open_fds_init, 	\
	close_on_exec_init: { { 0, } }, 		\
	open_fds_init:	{ { 0, } }, 			\
	fd_array:	{ NULL, } 			\
}

/* Maximum number of active map areas.. This is a random (large) number */
#define MAX_MAP_COUNT	(65536)

/* Number of map areas at which the AVL tree is activated. This is arbitrary. */
#define AVL_MIN_MAP_COUNT	32

struct mm_struct {
	struct vm_area_struct * mmap;		/* list of VMAs */
	struct vm_area_struct * mmap_avl;	/* tree of VMAs */
	struct vm_area_struct * mmap_cache;	/* last find_vma result */
	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 semaphore mmap_sem;
	spinlock_t page_table_lock;

	struct list_head mmlist;		/* List of all active mm's */

	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, total_vm, locked_vm;
	unsigned long def_flags;
	unsigned long cpu_vm_mask;
	unsigned long swap_cnt;	/* number of pages to swap on next pass */
	unsigned long swap_address;

	/* Architecture-specific MM context */
	mm_context_t context;
};

#define INIT_MM(name) \
{			 				\
	mmap:		&init_mmap, 			\
	mmap_avl:	NULL, 				\
	mmap_cache:	NULL, 				\
	pgd:		swapper_pg_dir, 		\
	mm_users:	ATOMIC_INIT(2), 		\
	mm_count:	ATOMIC_INIT(1), 		\
	map_count:	1, 				\
	mmap_sem:	__MUTEX_INITIALIZER(name.mmap_sem), \
	page_table_lock: SPIN_LOCK_UNLOCKED, 		\
	mmlist:		LIST_HEAD_INIT(name.mmlist),	\
}

struct signal_struct {
	atomic_t		count;
	struct k_sigaction	action[_NSIG];
	spinlock_t		siglock;
};


#define INIT_SIGNALS {	\
	count:		ATOMIC_INIT(1), 		\
	action:		{ {{0,}}, }, 			\
	siglock:	SPIN_LOCK_UNLOCKED 		\
}

/*
 * 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? */

	/* Hash table maintenance information */
	struct user_struct *next, **pprev;
	uid_t uid;
};

#define get_current_user() ({ 				\
	struct user_struct *__user = current->user;	\
	atomic_inc(&__user->__count);			\
	__user; })

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

struct task_struct {
	/*
	 * offsets of these are hardcoded elsewhere - touch with care
	 */
	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
	unsigned long flags;	/* per process flags, defined below */
	int sigpending;
	mm_segment_t addr_limit;	/* thread address space:
					 	0-0xBFFFFFFF for user-thead
						0-0xFFFFFFFF for kernel-thread
					 */
	struct exec_domain *exec_domain;
	volatile long need_resched;
	unsigned long ptrace;

	int lock_depth;		/* Lock depth */

/*
 * offset 32 begins here on 32-bit platforms. We keep
 * all fields in a single cacheline that are needed for
 * the goodness() loop in schedule().
 */
	long counter;
	long nice;
	unsigned long policy;
	struct mm_struct *mm;
	int has_cpu, processor;
	unsigned long cpus_allowed;
	/*
	 * (only the 'next' pointer fits into the cacheline, but
	 * that's just fine.)
	 */
	struct list_head run_list;
	unsigned long sleep_time;

	struct task_struct *next_task, *prev_task;
	struct mm_struct *active_mm;

/* task state */
	struct linux_binfmt *binfmt;
	int exit_code, exit_signal;
	int pdeath_signal;  /*  The signal sent when the parent dies  */
	/* ??? */
	unsigned long personality;
	int dumpable:1;
	int did_exec:1;
	pid_t pid;
	pid_t pgrp;
	pid_t tty_old_pgrp;
	pid_t session;
	pid_t tgid;
	/* boolean value for session group leader */
	int leader;
	/* 
	 * pointers to (original) parent process, youngest child, younger sibling,
	 * older sibling, respectively.  (p->father can be replaced with 
	 * p->p_pptr->pid)
	 */
	struct task_struct *p_opptr, *p_pptr, *p_cptr, *p_ysptr, *p_osptr;
	struct list_head thread_group;

	/* PID hash table linkage. */
	struct task_struct *pidhash_next;
	struct task_struct **pidhash_pprev;

	wait_queue_head_t wait_chldexit;	/* for wait4() */
	struct semaphore *vfork_sem;		/* for vfork() */
	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;
	struct tms times;
	unsigned long start_time;
	long per_cpu_utime[NR_CPUS], per_cpu_stime[NR_CPUS];
/* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
	unsigned long min_flt, maj_flt, nswap, cmin_flt, cmaj_flt, cnswap;
	int swappable:1;
/* process credentials */
	uid_t uid,euid,suid,fsuid;
	gid_t gid,egid,sgid,fsgid;
	int ngroups;
	gid_t	groups[NGROUPS];
	kernel_cap_t   cap_effective, cap_inheritable, cap_permitted;
	int keep_capabilities:1;
	struct user_struct *user;
/* limits */
	struct rlimit rlim[RLIM_NLIMITS];
	unsigned short used_math;
	char comm[16];
/* file system info */
	int link_count;
	struct tty_struct *tty; /* NULL if no tty */
	unsigned int locks; /* How many file locks are being held */
/* ipc stuff */
	struct sem_undo *semundo;
	struct sem_queue *semsleeping;
/* CPU-specific state of this task */
	struct thread_struct thread;
/* filesystem information */
	struct fs_struct *fs;
/* open file information */
	struct files_struct *files;
/* signal handlers */
	spinlock_t sigmask_lock;	/* Protects signal and blocked */
	struct signal_struct *sig;

	sigset_t blocked;
	struct sigpending pending;

	unsigned long sas_ss_sp;
	size_t sas_ss_size;
	int (*notifier)(void *priv);
	void *notifier_data;
	sigset_t *notifier_mask;
	
/* Thread group tracking */
   	u32 parent_exec_id;
   	u32 self_exec_id;
/* Protection of (de-)allocation: mm, files, fs, tty */
	spinlock_t alloc_lock;
};

/*
 * Per process flags
 */
#define PF_ALIGNWARN	0x00000001	/* Print alignment warning msgs */
					/* Not implemented yet, only for 486*/
#define PF_STARTING	0x00000002	/* being created */
#define PF_EXITING	0x00000004	/* getting shut down */
#define PF_FORKNOEXEC	0x00000040	/* forked but didn't exec */
#define PF_SUPERPRIV	0x00000100	/* used super-user privileges */
#define PF_DUMPCORE	0x00000200	/* dumped core */
#define PF_SIGNALED	0x00000400	/* killed by a signal */
#define PF_MEMALLOC	0x00000800	/* Allocating memory */
#define PF_VFORK	0x00001000	/* Wake up parent in mm_release */

#define PF_USEDFPU	0x00100000	/* task used FPU this quantum (SMP) */

/*
 * Ptrace flags
 */

#define PT_PTRACED	0x00000001
#define PT_TRACESYS	0x00000002
#define PT_DTRACE	0x00000004	/* delayed trace (used on m68k, i386) */
#define PT_TRACESYSGOOD	0x00000008

/*
 * Limit the stack by to some sane default: root can always
 * increase this limit if needed..  8MB seems reasonable.
 */
#define _STK_LIM	(8*1024*1024)

#define DEF_COUNTER	(10*HZ/100)	/* 100 ms time slice */
#define MAX_COUNTER	(20*HZ/100)
#define DEF_NICE	(0)

/*
 *  INIT_TASK is used to set up the first task table, touch at
 * your own risk!. Base=0, limit=0x1fffff (=2MB)
 */
#define INIT_TASK(tsk)	\
{									\
    state:		0,						\
    flags:		0,						\
    sigpending:		0,						\
    addr_limit:		KERNEL_DS,					\