进程管理（三）

（一）：进程创建

linux不同于其他操作系统，linux在进程的创建的时候，将进程的创建和执行程序分成了两个函数，fork()和exec()。进程在创建的过程中，首先通过fork()函数拷贝一份当前进程来创建一个子进程。子进程和父进程的区别仅仅在于PID,PPID(父进程的进程号，子进程将其设置为被拷贝进程的进程号)和某些资源以及统计量（被挂起的信号等）。exec()函数负责执行负责执行可执行文件并将其载入地址空间开始运行。

1：写时拷贝

在传统的fotk()函数中，直接将进程的所有的资源复制给新创建的进程，这样有一些不好的地方，首先，这样会使得进程创建缓慢，其次就是有很多没有必要继承的数据被无辜继承下来，后来还需要修改，这样就会造成效率低下。

现在有了写时拷贝（copy-on-write），这是一种推迟甚至免除拷贝数据的技术，在进程被创建的时候，内核并不是复制整个进程地址空间，而是让父进程和子进程共享同一个拷贝。只有在需要写入的时候，数据才会被复制。

2：fork()

Linux通过clone()系统调用实现fork()。这个调用通过一系列的参数标志来指明父，子进程需要共享的资源。其中fork(),vfork(),_clone()都根据各自需要的参数标志去调用clone(),然后clone()在去调用dk_fork()。最后do_fork()调用copy_process()让进程开始运行。下面我们来看一下该调用过程。其中基本上大部分定义在 kernel/fork.c中。

我们首先看一下copy_process()函数：

/*
 * This creates a new process as a copy of the old one,
 * but does not actually start it yet.
 *
 * 该方法会创建一个旧进程的拷贝，但是他并没有真实运行
 *
 * It copies the registers, and all the appropriate
 * parts of the process environment (as per the clone
 * flags). The actual kick-off is left to the caller.
 *
 * 他会复制寄存器的内容，以及进程环境所有可能的部分。
 *
 */
static struct task_struct *copy_process(unsigned long clone_flags,
                    unsigned long stack_start,
                    struct pt_regs *regs,
                    unsigned long stack_size,
                    int __user *parent_tidptr,
                    int __user *child_tidptr,
                    int pid)
{
    int retval;
    struct task_struct *p = NULL;
    if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
        return ERR_PTR(-EINVAL);
    /*
     * Thread groups must share signals as well, and detached threads
     * can only be started up within the thread group.
     *
     * 线程组一定要共享信号，并且分离的线程也仅仅能在线程组中运行。
     *
     */
    if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND))
        return ERR_PTR(-EINVAL);
    /*
     * Shared signal handlers imply shared VM. By way of the above,
     * thread groups also imply shared VM. Blocking this case allows
     * for various simplifications in other code.
     */
    if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM))
        return ERR_PTR(-EINVAL);
    retval = security_task_create(clone_flags);
    if (retval)
        goto fork_out;
    retval = -ENOMEM;
    /*
     * 使用dump_task_struct()为新进程创建一个内核栈，thread_info结构和task_struct，这些值
     * 与当前进程相同，此时，子进程和父进程的描述符是完全一样的。
     *
     */
    p = dup_task_struct(current);
    /*
     * 创建完成之后，检查新创建进程的正确性，以及当前拥有的进程数目没有
     * 超过给他分配的资源的限制。
     *
     * 子进程开始着手将自己与父进程区别开来，进程描述符中的很多成员需要被清0
     * 或被设置为初始值。
     */
    if (!p)
        goto fork_out;
#ifdef CONFIG_TRACE_IRQFLAGS
    DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
    DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
#endif
    retval = -EAGAIN;
    if (atomic_read(&p->user->processes) >=
            p->signal->rlim[RLIMIT_NPROC].rlim_cur) {
        if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
                p->user != &root_user)
            goto bad_fork_free;
    }
    atomic_inc(&p->user->__count);
    atomic_inc(&p->user->processes);
    get_group_info(p->group_info);
    /*
     * If multiple threads are within copy_process(), then this check
     * triggers too late. This doesn‘t hurt, the check is only there
     * to stop root fork bombs.
     */
    if (nr_threads >= max_threads)
        goto bad_fork_cleanup_count;
    if (!try_module_get(task_thread_info(p)->exec_domain->module))
        goto bad_fork_cleanup_count;
    if (p->binfmt && !try_module_get(p->binfmt->module))
        goto bad_fork_cleanup_put_domain;
    p->did_exec = 0;
    delayacct_tsk_init(p);  /* Must remain after dup_task_struct() */
    /*
     * copy_flags()函数被调用，来更新task_struct的flags成员。表明进程
     * 是否拥有超级权限的PF_SUPERPRIV标志被清0,表明进程还没有调用exec()
     * 函数的PF_FORKNOEXEC标志被设置
     */
    copy_flags(clone_flags, p);
    /*
     * 由于之前函数刚开始的时候，调用函数alloc_pid()函数已经为该进程
     * 分配了pid，在这里只需设置新创建进程的pid即可。
     *
     */
    p->pid = pid;
    retval = -EFAULT;
    // 根据传递的参数标志，copy_process()拷贝或共享打开的文件，文件系统信息，
    // 信号处理函数，进程地址空间和命名空间等。
    if (clone_flags & CLONE_PARENT_SETTID)
        if (put_user(p->pid, parent_tidptr))
            goto bad_fork_cleanup_delays_binfmt;
    INIT_LIST_HEAD(&p->children);
    INIT_LIST_HEAD(&p->sibling);
    p->vfork_done = NULL;
    spin_lock_init(&p->alloc_lock);
    clear_tsk_thread_flag(p, TIF_SIGPENDING);
    init_sigpending(&p->pending);
    p->utime = cputime_zero;
    p->stime = cputime_zero;
    p->sched_time = 0;
    p->rchar = 0;       /* I/O counter: bytes read */
    p->wchar = 0;       /* I/O counter: bytes written */
    p->syscr = 0;       /* I/O counter: read syscalls */
    p->syscw = 0;       /* I/O counter: write syscalls */
    acct_clear_integrals(p);
    p->it_virt_expires = cputime_zero;
    p->it_prof_expires = cputime_zero;
    p->it_sched_expires = 0;
    INIT_LIST_HEAD(&p->cpu_timers[0]);
    INIT_LIST_HEAD(&p->cpu_timers[1]);
    INIT_LIST_HEAD(&p->cpu_timers[2]);
    p->lock_depth = -1;     /* -1 = no lock */
    do_posix_clock_monotonic_gettime(&p->start_time);
    p->security = NULL;
    p->io_context = NULL;
    p->io_wait = NULL;
    p->audit_context = NULL;
    cpuset_fork(p);
#ifdef CONFIG_NUMA
    p->mempolicy = mpol_copy(p->mempolicy);
    if (IS_ERR(p->mempolicy)) {
        retval = PTR_ERR(p->mempolicy);
        p->mempolicy = NULL;
        goto bad_fork_cleanup_cpuset;
    }
    mpol_fix_fork_child_flag(p);
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
    p->irq_events = 0;
    p->hardirqs_enabled = 0;
    p->hardirq_enable_ip = 0;
    p->hardirq_enable_event = 0;
    p->hardirq_disable_ip = _THIS_IP_;
    p->hardirq_disable_event = 0;
    p->softirqs_enabled = 1;
    p->softirq_enable_ip = _THIS_IP_;
    p->softirq_enable_event = 0;
    p->softirq_disable_ip = 0;
    p->softirq_disable_event = 0;
    p->hardirq_context = 0;
    p->softirq_context = 0;
#endif
#ifdef CONFIG_LOCKDEP
    p->lockdep_depth = 0; /* no locks held yet */
    p->curr_chain_key = 0;
    p->lockdep_recursion = 0;
#endif
    rt_mutex_init_task(p);
#ifdef CONFIG_DEBUG_MUTEXES
    p->blocked_on = NULL; /* not blocked yet */
#endif
    p->tgid = p->pid;
    if (clone_flags & CLONE_THREAD)
        p->tgid = current->tgid;
    if ((retval = security_task_alloc(p)))
        goto bad_fork_cleanup_policy;
    if ((retval = audit_alloc(p)))
        goto bad_fork_cleanup_security;
    /* copy all the process information */
    if ((retval = copy_semundo(clone_flags, p)))
        goto bad_fork_cleanup_audit;
    if ((retval = copy_files(clone_flags, p)))
        goto bad_fork_cleanup_semundo;
    if ((retval = copy_fs(clone_flags, p)))
        goto bad_fork_cleanup_files;
    if ((retval = copy_sighand(clone_flags, p)))
        goto bad_fork_cleanup_fs;
    if ((retval = copy_signal(clone_flags, p)))
        goto bad_fork_cleanup_sighand;
    if ((retval = copy_mm(clone_flags, p)))
        goto bad_fork_cleanup_signal;
    if ((retval = copy_keys(clone_flags, p)))
        goto bad_fork_cleanup_mm;
    if ((retval = copy_namespace(clone_flags, p)))
        goto bad_fork_cleanup_keys;
    retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
    if (retval)
        goto bad_fork_cleanup_namespace;
    p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
    /*
     * Clear TID on mm_release()?
     */
    p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL;
    p->robust_list = NULL;
#ifdef CONFIG_COMPAT
    p->compat_robust_list = NULL;
#endif
    INIT_LIST_HEAD(&p->pi_state_list);
    p->pi_state_cache = NULL;
    /*
     * sigaltstack should be cleared when sharing the same VM
     */
    if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM)
        p->sas_ss_sp = p->sas_ss_size = 0;
    /*
     * Syscall tracing should be turned off in the child regardless
     * of CLONE_PTRACE.
     */
    clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
#ifdef TIF_SYSCALL_EMU
    clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
#endif
    /* Our parent execution domain becomes current domain
       These must match for thread signalling to apply */

    p->parent_exec_id = p->self_exec_id;
    /* ok, now we should be set up.. */
    p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL);
    p->pdeath_signal = 0;
    p->exit_state = 0;
    /*
     * Ok, make it visible to the rest of the system.
     * We dont wake it up yet.
     */
    p->group_leader = p;
    INIT_LIST_HEAD(&p->thread_group);
    INIT_LIST_HEAD(&p->ptrace_children);
    INIT_LIST_HEAD(&p->ptrace_list);
    /* Perform scheduler related setup. Assign this task to a CPU. */
    sched_fork(p, clone_flags);
    /* Need tasklist lock for parent etc handling! */
    write_lock_irq(&tasklist_lock);
    /*
     * The task hasn‘t been attached yet, so its cpus_allowed mask will
     * not be changed, nor will its assigned CPU.
     *
     * The cpus_allowed mask of the parent may have changed after it was
     * copied first time - so re-copy it here, then check the child‘s CPU
     * to ensure it is on a valid CPU (and if not, just force it back to
     * parent‘s CPU). This avoids alot of nasty races.
     */
    p->cpus_allowed = current->cpus_allowed;
    if (unlikely(!cpu_isset(task_cpu(p), p->cpus_allowed) ||
            !cpu_online(task_cpu(p))))
        set_task_cpu(p, smp_processor_id());
    /* CLONE_PARENT re-uses the old parent */
    if (clone_flags & (CLONE_PARENT|CLONE_THREAD))
        p->real_parent = current->real_parent;
    else
        p->real_parent = current;
    p->parent = p->real_parent;
    spin_lock(¤t->sighand->siglock);
    /*
     * Process group and session signals need to be delivered to just the
     * parent before the fork or both the parent and the child after the
     * fork. Restart if a signal comes in before we add the new process to
     * it‘s process group.
     * A fatal signal pending means that current will exit, so the new
     * thread can‘t slip out of an OOM kill (or normal SIGKILL).
     */
    recalc_sigpending();
    if (signal_pending(current)) {
        spin_unlock(¤t->sighand->siglock);
        write_unlock_irq(&tasklist_lock);
        retval = -ERESTARTNOINTR;
        goto bad_fork_cleanup_namespace;
    }
    if (clone_flags & CLONE_THREAD) {
        p->group_leader = current->group_leader;
        list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
        if (!cputime_eq(current->signal->it_virt_expires,
                cputime_zero) ||
            !cputime_eq(current->signal->it_prof_expires,
                cputime_zero) ||
            current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY ||
            !list_empty(¤t->signal->cpu_timers[0]) ||
            !list_empty(¤t->signal->cpu_timers[1]) ||
            !list_empty(¤t->signal->cpu_timers[2])) {
            /*
             * Have child wake up on its first tick to check
             * for process CPU timers.
             */
            p->it_prof_expires = jiffies_to_cputime(1);
        }
    }
    /*
     * inherit ioprioretval
     */
    p->ioprio = current->ioprio;
    if (likely(p->pid)) {
        add_parent(p);
        if (unlikely(p->ptrace & PT_PTRACED))
            __ptrace_link(p, current->parent);
        if (thread_group_leader(p)) {
            p->signal->tty = current->signal->tty;
            p->signal->pgrp = process_group(current);
            p->signal->session = current->signal->session;
            attach_pid(p, PIDTYPE_PGID, process_group(p));
            attach_pid(p, PIDTYPE_SID, p->signal->session);
            list_add_tail_rcu(&p->tasks, &init_task.tasks);
            __get_cpu_var(process_counts)++;
        }
        attach_pid(p, PIDTYPE_PID, p->pid);
        nr_threads++;
    }
    total_forks++;
    spin_unlock(¤t->sighand->siglock);
    write_unlock_irq(&tasklist_lock);
    proc_fork_connector(p);
    //最后返回新创建进程描述符的指针
    return p;
bad_fork_cleanup_namespace:
    exit_namespace(p);
bad_fork_cleanup_keys:
    exit_keys(p);
bad_fork_cleanup_mm:
    if (p->mm)
        mmput(p->mm);
bad_fork_cleanup_signal:
    cleanup_signal(p);
bad_fork_cleanup_sighand:
    __cleanup_sighand(p->sighand);
bad_fork_cleanup_fs:
    exit_fs(p); /* blocking */
bad_fork_cleanup_files:
    exit_files(p); /* blocking */
bad_fork_cleanup_semundo:
    exit_sem(p);
bad_fork_cleanup_audit:
    audit_free(p);
bad_fork_cleanup_security:
    security_task_free(p);
bad_fork_cleanup_policy:
#ifdef CONFIG_NUMA
    mpol_free(p->mempolicy);
bad_fork_cleanup_cpuset:
#endif
    cpuset_exit(p);
bad_fork_cleanup_delays_binfmt:
    delayacct_tsk_free(p);
    if (p->binfmt)
        module_put(p->binfmt->module);
bad_fork_cleanup_put_domain:
    module_put(task_thread_info(p)->exec_domain->module);
bad_fork_cleanup_count:
    put_group_info(p->group_info);
    atomic_dec(&p->user->processes);
    free_uid(p->user);
bad_fork_free:
    free_task(p);
fork_out:
    return ERR_PTR(retval);
}

这样，我们来梳理一下copy_process()的工作流程。

根据代码，当该函数被调用的时候，首先会调用alloc_pid()函数分配一个新的pid。接着进程下面的操作：

1：调用dump_task_struct()函数为为新进程创建一个内核栈，thread_info结构和task_struct，这些值和当前进程的值相同。此时，子进程和父进程的进程描述符是完全一样的。

2：接着，程序会检查新创建的子进程的正确性，并且检查当前用户所拥有的进程数目没有超过给他分配的资源限制。

3：子进程着手将自己与父进程去被开来。进程描述符内的很多成员都要被清0或者是设置为初始值。    

4：子进程的状态被设置为TASK_UNINTERRUPTIBLE，来保证不会投入运行

5：调用copy_flags()来更新task_struct的flags成员。表示用户是否拥有超级权限的标志PF_SUPERPRIV被清0.

6：设置新进程的pid

7：根据clone()传递的参数标志，copy_process()拷贝或共享打开的文件，文件系统信息，信号处理函数，进程地址空间和命名空间等。

8：最后，返回一个指向子进程的指针。