窥探 kernel，just for fun --- task_struct

本系列文章由张同浩编写，转载请注明出处：http://blog.csdn.net/muge0913/article/details/7477083

邮箱：[email protected]

程序和进程：

程序是存放在磁盘上的一系列代码和数据的可执行镜像，是一个静态的实体；

进程是一个执行的程序，它是动态的实体，它除了包含指令段，数据段等静态数据外（数据是可以是动态变化的），还包括当前的状态信息，如临时数据堆栈信息，当前处理器的寄存器信息等动态信息。这些动态信息通常称为进程上下文。

从内核角度来看，进程是操作系统分配内存，cpu时间片等资源的最小单位。其中它用到的数据和信息大部分都是在动态变化的。在linux内核中进程上下文通常用task_struct来描述，进程切换负责保存当前进程的上下文，恢复合适进程的上下文到cpu和寄存器中。

进程和线程：

 随着计算机产业的发展，计算机的应用范围越来越广，计算机要解决的范围从处理器密集型的科学计算向IO密集型的用户交互式程序。为了解决日益复杂的问题。人们提出了分而治之（divide and comquer）的思想，也就是提出了进程。随着计算机的发展和对此技术的研究，人们发现，进程间的切换带来了相当大的系统开销（overload），人们又提出了线程的概念。线程是对进程的进一步抽象。一个进程有两部分组成：线程集合和资源集合。线程是进程中的一个动态对象，一组动态的指令流。进程中的所有线程将共享进程的中的资源，但每个线程又有独立的程序计数器，堆栈和寄存器。

linux中线程、进程都是用struct task_struct来描述。进程描述符task_struct用来刻画进程的状态属性，是内核操作和维护进程状态的唯一手段,其定义在linux 2.6.xx/include/linux/sched.h中。这个结构体相当的大

truct task_struct {
    /*这个是进程的运行时状态，-1代表不可运行，0代表可运行，>0代表已停止*/
    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;
    /*表示此进程的运行优先级*/
    unsigned int rt_priority;
    const struct sched_class *sched_class;
    struct sched_entity se;
    struct sched_rt_entity rt;

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

    /*
     * 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;
#ifdef CONFIG_BLK_DEV_IO_TRACE
    unsigned int btrace_seq;
#endif

    unsigned int policy;
    cpumask_t cpus_allowed;

#ifdef CONFIG_PREEMPT_RCU
    int rcu_read_lock_nesting;
    char rcu_read_unlock_special;
    struct list_head rcu_node_entry;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_TREE_PREEMPT_RCU
    struct rcu_node *rcu_blocked_node;
#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */

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

    struct list_head tasks;
    struct plist_node pushable_tasks;
    /*该结构体记录了进程内存使用的相关情况*/
    struct mm_struct *mm, *active_mm;
#if defined(SPLIT_RSS_COUNTING)
    struct task_rss_stat    rss_stat;
#endif
/* task state */
    /*进程退出时的状态*/
    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;
    unsigned in_execve:1;   /* Tell the LSMs that the process is doing an
                 * execve */
    unsigned in_iowait:1;


    /* Revert to default priority/policy when forking */
    unsigned sched_reset_on_fork:1;

    /*进程号*/
    pid_t pid;
    /*组进程号*/
    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->real_parent->pid)
     */
     /*创建该进程的父进程*/
    struct task_struct *real_parent; /* real parent process */
    /*parent是该进程现在的父进程，有可能是”继父“*/
    struct task_struct *parent; /* recipient of SIGCHLD, wait4() reports */
    /*
     * children/sibling forms the list of my natural children
     */
     /*这里children指的是该进程孩子的链表，可以得到所有孩子的进程描述符*/
    struct list_head children;  /* list of my children */
    /*sibling该进程兄弟的链表，也就是其父亲的所有孩子的链表*/
    struct list_head sibling;   /* linkage in my parent's children list */
    /*这个是主线程的进程描述符，linux并没有单独实现线程的相关结构体，只是用一个进程来代替线程，然后对其做一些特殊的处理*/
    struct task_struct *group_leader;   /* threadgroup leader */

    /*
     * ptraced is the list of tasks this task is using ptrace on.
     * This includes both natural children and PTRACE_ATTACH targets.
     * p->ptrace_entry is p's link on the p->parent->ptraced list.
     */
    struct list_head ptraced;
    struct list_head ptrace_entry;

    /* PID/PID hash table linkage. */
    struct pid_link pids[PIDTYPE_MAX];
    /*该进程所有线程的链表*/
    struct list_head thread_group;

    struct completion *vfork_done;      /* for vfork() */
    int __user *set_child_tid;      /* CLONE_CHILD_SETTID */
    int __user *clear_child_tid;        /* CLONE_CHILD_CLEARTID */

    /*这个是该进程使用cpu时间的信息，utime是在用户态下执行的时间，stime是在内核态下执行的时间*/
    cputime_t utime, stime, utimescaled, stimescaled;
    cputime_t gtime;
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
    cputime_t prev_utime, prev_stime;
#endif
    unsigned long nvcsw, nivcsw; /* context switch counts */
    /*启动的时间，只是时间基准不一样*/
    struct timespec start_time;         /* monotonic time */
    struct timespec real_start_time;    /* boot based time */
/* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
    unsigned long min_flt, maj_flt;

    struct task_cputime cputime_expires;
    struct list_head cpu_timers[3];

/* process credentials */
    const struct cred __rcu *real_cred; /* objective and real subjective task
                     * credentials (COW) */
    const struct cred __rcu *cred;  /* effective (overridable) subjective task
                     * credentials (COW) */
    struct cred *replacement_session_keyring; /* for KEYCTL_SESSION_TO_PARENT */

    /*保存该进程名字的字符数组*/
    char comm[TASK_COMM_LEN]; /* executable name excluding path
                     - access with [gs]et_task_comm (which lock
                       it with task_lock())
                     - initialized normally by setup_new_exec */
/* file system info */
/* 文件系统信息计数*/
    int link_count, total_link_count;
#ifdef CONFIG_SYSVIPC
/* ipc stuff */
    struct sysv_sem sysvsem;
#endif
#ifdef CONFIG_DETECT_HUNG_TASK
/* hung task detection */
    unsigned long last_switch_count;
#endif
/* CPU-specific state of this task */
/*该进程在特定CPU下的状态*/
    struct thread_struct thread;
/* filesystem information */
/* 文件系统相关信息结构体*/
    struct fs_struct *fs;
/* open file information */
/* 打开的文件相关信息结构体,对驱动开发者来说此结构会常见到*/
    struct files_struct *files;
/* namespaces */
    struct nsproxy *nsproxy;
/* signal handlers */
/* 信号相关信息的句柄*/
    struct signal_struct *signal;
    struct sighand_struct *sighand;

    sigset_t blocked, real_blocked;
    sigset_t saved_sigmask; /* restored if set_restore_sigmask() was used */
    struct sigpending pending;

    unsigned long sas_ss_sp;
    size_t sas_ss_size;
    int (*notifier)(void *priv);
    void *notifier_data;
    sigset_t *notifier_mask;
    struct audit_context *audit_context;
#ifdef CONFIG_AUDITSYSCALL
    uid_t loginuid;
    unsigned int sessionid;
#endif
    seccomp_t seccomp;

/* Thread group tracking */
    u32 parent_exec_id;
    u32 self_exec_id;
/* Protection of (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed,
 * mempolicy */
    spinlock_t alloc_lock;

#ifdef CONFIG_GENERIC_HARDIRQS
    /* IRQ handler threads */
    struct irqaction *irqaction;
#endif

    /* Protection of the PI data structures: */
    raw_spinlock_t pi_lock;

#ifdef CONFIG_RT_MUTEXES
    /* PI waiters blocked on a rt_mutex held by this task */
    struct plist_head pi_waiters;
    /* Deadlock detection and priority inheritance handling */
    struct rt_mutex_waiter *pi_blocked_on;
#endif

#ifdef CONFIG_DEBUG_MUTEXES
    /* mutex deadlock detection */
    struct mutex_waiter *blocked_on;
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
    unsigned int irq_events;
    unsigned long hardirq_enable_ip;
    unsigned long hardirq_disable_ip;
    unsigned int hardirq_enable_event;
    unsigned int hardirq_disable_event;
    int hardirqs_enabled;
    int hardirq_context;
    unsigned long softirq_disable_ip;
    unsigned long softirq_enable_ip;
    unsigned int softirq_disable_event;
    unsigned int softirq_enable_event;
    int softirqs_enabled;
    int softirq_context;
#endif
#ifdef CONFIG_LOCKDEP
# define MAX_LOCK_DEPTH 48UL
    u64 curr_chain_key;
    int lockdep_depth;
    unsigned int lockdep_recursion;
    struct held_lock held_locks[MAX_LOCK_DEPTH];
    gfp_t lockdep_reclaim_gfp;
#endif

/* journalling filesystem info */
    void *journal_info;

/* stacked block device info */
    struct bio_list *bio_list;

/* VM state */
    struct reclaim_state *reclaim_state;

    struct backing_dev_info *backing_dev_info;

    struct io_context *io_context;

    unsigned long ptrace_message;
    siginfo_t *last_siginfo; /* For ptrace use.  */
    struct task_io_accounting ioac;
#if defined(CONFIG_TASK_XACCT)
    u64 acct_rss_mem1;  /* accumulated rss usage */
    u64 acct_vm_mem1;   /* accumulated virtual memory usage */
    cputime_t acct_timexpd; /* stime + utime since last update */
#endif
#ifdef CONFIG_CPUSETS
    nodemask_t mems_allowed;    /* Protected by alloc_lock */
    int mems_allowed_change_disable;
    int cpuset_mem_spread_rotor;
    int cpuset_slab_spread_rotor;
#endif
#ifdef CONFIG_CGROUPS
    /* Control Group info protected by css_set_lock */
    struct css_set __rcu *cgroups;
    /* cg_list protected by css_set_lock and tsk->alloc_lock */
    struct list_head cg_list;
#endif
#ifdef CONFIG_FUTEX
    struct robust_list_head __user *robust_list;
#ifdef CONFIG_COMPAT
    struct compat_robust_list_head __user *compat_robust_list;
#endif
    struct list_head pi_state_list;
    struct futex_pi_state *pi_state_cache;
#endif
#ifdef CONFIG_PERF_EVENTS
    struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts];
    struct mutex perf_event_mutex;
    struct list_head perf_event_list;
#endif
#ifdef CONFIG_NUMA
    struct mempolicy *mempolicy;    /* Protected by alloc_lock */
    short il_next;
#endif
    atomic_t fs_excl;   /* holding fs exclusive resources */
    struct rcu_head rcu;

    /*
     * cache last used pipe for splice
     */
    struct pipe_inode_info *splice_pipe;
#ifdef  CONFIG_TASK_DELAY_ACCT
    struct task_delay_info *delays;
#endif
#ifdef CONFIG_FAULT_INJECTION
    int make_it_fail;
#endif
    struct prop_local_single dirties;
#ifdef CONFIG_LATENCYTOP
    int latency_record_count;
    struct latency_record latency_record[LT_SAVECOUNT];
#endif
    /*
     * time slack values; these are used to round up poll() and
     * select() etc timeout values. These are in nanoseconds.
     */
     /*这些是松弛时间值，用来规定select()和poll()的超时时间，单位是纳秒nanoseconds  */
    unsigned long timer_slack_ns;
    unsigned long default_timer_slack_ns;

    struct list_head    *scm_work_list;
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
    /* Index of current stored address in ret_stack */
    int curr_ret_stack;
    /* Stack of return addresses for return function tracing */
    struct ftrace_ret_stack *ret_stack;
    /* time stamp for last schedule */
    unsigned long long ftrace_timestamp;
    /*
     * Number of functions that haven't been traced
     * because of depth overrun.
     */
    atomic_t trace_overrun;
    /* Pause for the tracing */
    atomic_t tracing_graph_pause;
#endif
#ifdef CONFIG_TRACING
    /* state flags for use by tracers */
    unsigned long trace;
    /* bitmask of trace recursion */
    unsigned long trace_recursion;
#endif /* CONFIG_TRACING */
#ifdef CONFIG_CGROUP_MEM_RES_CTLR /* memcg uses this to do batch job */
    struct memcg_batch_info {
        int do_batch;   /* incremented when batch uncharge started */
        struct mem_cgroup *memcg; /* target memcg of uncharge */
        unsigned long bytes;        /* uncharged usage */
        unsigned long memsw_bytes; /* uncharged mem+swap usage */
    } memcg_batch;
#endif
};

上面只是一些简单注释，后面会重点介绍某些重要的结构体，和它们的相关操作和用途。