Linux中的task_struct
进程：程序的执行过程；即把二进制文件（程序）从磁盘加载到内存之后的操作；
同时操作系统给这个文件创建了一个描述它的结构体，称为PCB。
每个进程都有一个PCB。
Linux下的PCB结构：task_struct
进程在操作系统中都有一个户口，用于表示这个进程。这个户口操作系统被称为PCB（进程控制块），在linux中具体实现是 task_struct数据结构，它记录了一下几个类型的信息：
1.状态信息，例如这个进程处于可执行状态，休眠，挂起等。
2.性质，由于unix有很多变种，进程有自己独特的性质。
3.资源，资源的链接比如内存，还有资源的限制和权限等。
4.组织，例如按照家族关系建立起来的树（父进程，子进程等）。
下面是这一个数据结构
struct task_struct {
/*
* offsets of these are hardcoded elsewhere - touch with care
*/
volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */ //进程当前的状态
unsigned long flags; /* per process flags, defined below */ //反应进程状态的信息，但不是运行状态，定义见下
int sigpending; //进程收到了信号，但尚未处理
mm_segment_t addr_limit; /* thread address space: //虚存地址上限
0-0xBFFFFFFF for user-thead
0-0xFFFFFFFF for kernel-thread
*/
struct exec_domain *exec_domain;
volatile long need_resched; //与进程调度有关表示用户从系统空间按返回用户空间要执行的一次调度
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; //与进程调度相关
long nice;
unsigned long policy; //实用于本进程的调度政策
struct mm_struct *mm;
int processor;
/*
* cpus_runnable is ~0 if the process is not running on any
* CPU. It's (1 << cpu) if it's running on a CPU. This mask
* is updated under the runqueue lock.
*
* To determine whether a process might run on a CPU, this
* mask is AND-ed with cpus_allowed.
*/
unsigned long cpus_runnable, 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; //内核会对每一个进程做点什么事情的时候，常常需要将其连成一个队列，这2个指针用于这个目的
struct mm_struct *active_mm;
struct list_head local_pages;
unsigned int allocation_order, nr_local_pages;
/* task state */
struct linux_binfmt *binfmt;//应用文件格式
int exit_code, exit_signal;
int pdeath_signal; /* The signal sent when the parent dies */
/* ??? */
unsigned long personality; //进程的个性化信息，详细见下
int did_exec:1;
unsigned task_dumpable:1;
pid_t pid; //进程号
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; //用于族谱信息的，例如p_opptr指向父进程
struct list_head thread_group;
/* PID hash table linkage. */
struct task_struct *pidhash_next;
struct task_struct **pidhash_pprev; //pid是随机分配的，我们常常使用kill pid想进程发送信号（大部分人认为是杀死进程，其实这是个发送信号的指令，默认的参数为杀死。如果想暂停某进程，只需kill STOP 进程的PID），这里可以看到根据pid寻找进程的操作是经常被使用的，而pid又是随机分配，于是这里边用这2个指针指向一个杂凑数组，数组是按照杂凑的算法，以pid为关键字建立，方便根据pid来寻找task_struct
wait_queue_head_t wait_chldexit; /* for wait4() */
struct completion *vfork_done; /* for vfork() */
unsigned long rt_priority; //优先级
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; //运行时间的总汇
unsigned long start_time;
long per_cpu_utime[NR_CPUS], per_cpu_stime[NR_CPUS]; //在多个处理器上运行于系统空间和用户空间的时间
/* 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;//发生页面异常的次数和换入换出的次数
int swappable:1;
/* process credentials */
uid_t uid,euid,suid,fsuid;
gid_t gid,egid,sgid,fsgid; //与文件权限有关的
int ngroups;
gid_t groups[NGROUPS];
kernel_cap_t cap_effective, cap_inheritable, cap_permitted; //权限，比如该进程是否有权限从新引导系统，这里是大概介绍
int keep_capabilities:1;
struct user_struct *user; //指向该进程拥有的用户
/* limits */
struct rlimit rlim[RLIM_NLIMITS]; //进程对各种资源使用数量的限制，详细见下
unsigned short used_math;
char comm[16];
/* file system info */
int link_count, total_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;
/* namespace */
struct namespace *namespace;
/* 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;
/* journalling filesystem info */
void *journal_info;
};
#define TASK_RUNNING 0 //不是表示正在运行，而是表示可以被调用
#define TASK_INTERRUPTIBLE 1
#define TASK_UNINTERRUPTIBLE 2
#define TASK_ZOMBIE 4
#define TASK_STOPPED 8 //对应于task_struct中的state，进程运行状态
//对应task_struct的flag
#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_MEMDIE 0x00001000 /* Killed for out-of-memory */
#define PF_FREE_PAGES 0x00002000 /* per process page freeing */
#define PF_NOIO 0x00004000 /* avoid generating further I/O */
#define PF_FSTRANS 0x00008000 /* inside a filesystem transaction */
#define PF_USEDFPU 0x00100000 /* task used FPU this quantum (SMP) */
//进程的个性化信息
enum {
MMAP_PAGE_ZERO = 0x0100000,
ADDR_LIMIT_32BIT = 0x0800000,
SHORT_INODE = 0x1000000,
WHOLE_SECONDS = 0x2000000,
STICKY_TIMEOUTS = 0x4000000,
ADDR_LIMIT_3GB = 0x8000000,
};
/*
* Personality types.
*
* These go in the low byte. Avoid using the top bit, it will
* conflict with error returns.
*/
enum {
PER_LINUX = 0x0000,
PER_LINUX_32BIT = 0x0000 | ADDR_LIMIT_32BIT,
PER_SVR4 = 0x0001 | STICKY_TIMEOUTS | MMAP_PAGE_ZERO,
PER_SVR3 = 0x0002 | STICKY_TIMEOUTS | SHORT_INODE,
PER_SCOSVR3 = 0x0003 | STICKY_TIMEOUTS |
WHOLE_SECONDS | SHORT_INODE,
PER_OSR5 = 0x0003 | STICKY_TIMEOUTS | WHOLE_SECONDS,
PER_WYSEV386 = 0x0004 | STICKY_TIMEOUTS | SHORT_INODE,
PER_ISCR4 = 0x0005 | STICKY_TIMEOUTS,
PER_BSD = 0x0006,
PER_SUNOS = 0x0006 | STICKY_TIMEOUTS,
PER_XENIX = 0x0007 | STICKY_TIMEOUTS | SHORT_INODE,
PER_LINUX32 = 0x0008,
PER_LINUX32_3GB = 0x0008 | ADDR_LIMIT_3GB,
PER_IRIX32 = 0x0009 | STICKY_TIMEOUTS,/* IRIX5 32-bit */
PER_IRIXN32 = 0x000a | STICKY_TIMEOUTS,/* IRIX6 new 32-bit */
PER_IRIX64 = 0x000b | STICKY_TIMEOUTS,/* IRIX6 64-bit */
PER_RISCOS = 0x000c,
PER_SOLARIS = 0x000d | STICKY_TIMEOUTS,
PER_UW7 = 0x000e | STICKY_TIMEOUTS | MMAP_PAGE_ZERO,
PER_HPUX = 0x000f,
PER_OSF4 = 0x0010, /* OSF/1 v4 */
PER_MASK = 0x00ff,
};
//进程资源的限制，对应task_struct中的struct rlimit rlim[RLIM_NLIMITS],RLIM_NLIMITS的值是11，代表11项资源，分别是
#define RLIMIT_CPU 0 /* CPU time in ms */
#define RLIMIT_FSIZE 1 /* Maximum filesize */
#define RLIMIT_DATA 2 /* max data size */
#define RLIMIT_STACK 3 /* max stack size */
#define RLIMIT_CORE 4 /* max core file size */
#define RLIMIT_RSS 5 /* max resident set size */
#define RLIMIT_NPROC 6 /* max number of processes */
#define RLIMIT_NOFILE 7 /* max number of open files */
#define RLIMIT_MEMLOCK 8 /* max locked-in-memory address space */
#define RLIMIT_AS 9 /* address space limit */
#define RLIMIT_LOCKS 10 /* maximum file locks held */
struct task_struct { volatilelong state; //进程状态（可执行、可中断等） #1unsignedlong flags; //Flage 是进程号,在调用fork()时给出int sigpending; //进程上是否有待处理的信号 mm_segment_t addr_limit; //进程地址空间,区分内核进程与普通进程在内存存放的位置不同//0-0xBFFFFFFF for user//0-0xFFFFFFFF for kernelvolatilelong need_resched;//调度标志,表示该进程是否需要重新调度,若非0,则当从内核态返回到用户态,会发生调度 #2int lock_depth; //锁深度long nice; //进程的基本时间片//进程的调度策略,有三种,实时进程:SCHED_FIFO,SCHED_RR, 分时进程:SCHED_OTHERunsignedlong policy; struct mm_struct *mm; //进程内存管理信息int processor; //若进程不在任何CPU上运行, cpus_runnable 的值是0，否则是1 这个值在运行队列被锁时更新unsignedlong cpus_runnable, cpus_allowed; struct list_head run_list; //指向运行队列的指针unsignedlong sleep_time; //进程的睡眠时间//用于将系统中所有的进程连成一个双向循环链表, 其根是init_taskstruct task_struct *next_task, *prev_task; struct mm_struct *active_mm; struct list_head local_pages; //指向本地页面 unsignedint allocation_order, nr_local_pages; struct linux_binfmt *binfmt; //进程所运行的可执行文件的格式int exit_code, exit_signal; int pdeath_signal; //父进程终止时向子进程发送的信号unsignedlong personality; //Linux可以运行由其他UNIX操作系统生成的符合iBCS2标准的程序int did_exec:1; pid_t pid; //进程标识符,用来代表一个进程 pid_t pgrp; //进程组标识,表示进程所属的进程组 pid_t tty_old_pgrp; //进程控制终端所在的组标识 pid_t session; //进程的会话标识 pid_t tgid; int leader; //表示进程是否为会话主管struct task_struct *p_opptr,*p_pptr,*p_cptr,*p_ysptr,*p_osptr; struct list_head thread_group; //线程链表struct task_struct *pidhash_next; //用于将进程链入HASH表struct task_struct **pidhash_pprev; wait_queue_head_t wait_chldexit; //供wait4()使用struct completion *vfork_done; //供vfork() 使用unsignedlong rt_priority; //实时优先级，用它计算实时进程调度时的weight值//it_real_value，it_real_incr用于REAL定时器，单位为jiffies, 系统根据it_real_value//设置定时器的第一个终止时间. 在定时器到期时，向进程发送SIGALRM信号，同时根据//it_real_incr重置终止时间，it_prof_value，it_prof_incr用于Profile定时器，单位为jiffies。//当进程运行时，不管在何种状态下，每个tick都使it_prof_value值减一，当减到0时，向进程发送//信号SIGPROF，并根据it_prof_incr重置时间.//it_virt_value，it_virt_value用于Virtual定时器，单位为jiffies。当进程运行时，不管在何种//状态下，每个tick都使it_virt_value值减一当减到0时，向进程发送信号SIGVTALRM，根据//it_virt_incr重置初值。unsignedlong it_real_value, it_prof_value, it_virt_value; unsignedlong it_real_incr, it_prof_incr, it_virt_value; struct timer_list real_timer; //指向实时定时器的指针struct tms times; //记录进程消耗的时间unsignedlong start_time; //进程创建的时间//记录进程在每个CPU上所消耗的用户态时间和核心态时间long per_cpu_utime[NR_CPUS], per_cpu_stime[NR_CPUS]; //内存缺页和交换信息://min_flt, maj_flt累计进程的次缺页数（Copy on Write页和匿名页）和主缺页数（从映射文件或交换//设备读入的页面数）； nswap记录进程累计换出的页面数，即写到交换设备上的页面数。//cmin_flt, cmaj_flt, cnswap记录本进程为祖先的所有子孙进程的累计次缺页数，主缺页数和换出页面数。//在父进程回收终止的子进程时，父进程会将子进程的这些信息累计到自己结构的这些域中unsignedlong min_flt, maj_flt, nswap, cmin_flt, cmaj_flt, cnswap; int swappable:1; //表示进程的虚拟地址空间是否允许换出//进程认证信息//uid,gid为运行该进程的用户的用户标识符和组标识符，通常是进程创建者的uid，gid//euid，egid为有效uid,gid//fsuid，fsgid为文件系统uid,gid，这两个ID号通常与有效uid,gid相等，在检查对于文件//系统的访问权限时使用他们。//suid，sgid为备份uid,gid uid_t uid,euid,suid,fsuid; gid_t gid,egid,sgid,fsgid; int ngroups; //记录进程在多少个用户组中 gid_t groups[NGROUPS]; //记录进程所在的组//进程的权能，分别是有效位集合，继承位集合，允许位集合 kernel_cap_t cap_effective, cap_inheritable, cap_permitted; int keep_capabilities:1; struct user_struct *user; struct rlimit rlim[RLIM_NLIMITS]; //与进程相关的资源限制信息unsignedshort used_math; //是否使用FPUchar comm[16]; //进程正在运行的可执行文件名//文件系统信息int link_count, total_link_count; //NULL if no tty 进程所在的控制终端，如果不需要控制终端，则该指针为空struct tty_struct *tty; unsignedint locks; //进程间通信信息struct sem_undo *semundo; //进程在信号灯上的所有undo操作struct sem_queue *semsleeping; //当进程因为信号灯操作而挂起时，他在该队列中记录等待的操作//进程的CPU状态，切换时，要保存到停止进程的task_struct中struct thread_struct thread; //文件系统信息struct fs_struct *fs; //打开文件信息struct files_struct *files; //信号处理函数 spinlock_t sigmask_lock; struct signal_struct *sig; //信号处理函数 sigset_t blocked; //进程当前要阻塞的信号，每个信号对应一位struct sigpending pending; //进程上是否有待处理的信号unsignedlong sas_ss_sp; size_t sas_ss_size; int (*notifier)(void *priv); void *notifier_data; sigset_t *notifier_mask; u32 parent_exec_id; u32 self_exec_id; spinlock_t alloc_lock; void *journal_info; };
浙公网安备 33010602011771号