Linux内核之进程管理

struct task_struct {

#ifdef CONFIG_THREAD_INFO_IN_TASK
  /*
   * For reasons of header soup (see current_thread_info()), this
   * must be the first element of task_struct.
   */
  struct thread_info    thread_info;
#endif
  /* -1 unrunnable, 0 runnable, >0 stopped:  进程状态 */
  volatile long     state;
    
    /* Per task flags (PF_*), defined further below: flags标记 */
  unsigned int      flags;
  
  /* 内存描述符 地址空间 */
  struct mm_struct    *mm;

  /* 进程状态 */
  int       exit_state;
  int       exit_code;

  /* pid 进程标识符 */
  pid_t       pid;

  /* Real parent process: 父进程*/
  struct task_struct __rcu  *real_parent;
  struct task_struct __rcu  *parent;
  /*
   * Children/sibling form the list of natural children:
   * 子进程的链表
   */
  struct list_head    children;

  /* Filesystem information: 文件系统信息*/
  struct fs_struct    *fs;

  /* Open file information:  打开文件信息*/
  struct files_struct   *files;

  /* Namespaces: */
  struct nsproxy      *nsproxy;

  /* Signal handlers:  信号处理*/
  struct signal_struct    *signal;
  struct sighand_struct   *sighand;
  sigset_t      blocked;
  sigset_t      real_blocked;

};

struct thread_info {
  struct task_struct  *task;    /* main task structure */
  unsigned long   flags;    /* low level flags */
  __u32     cpu;    /* current CPU */
  int     preempt_count;  /* 0 => preemptable,
               <0 => BUG */
  mm_segment_t    addr_limit; /* thread address space:
               0-0xBFFFFFFF for user
               0-0xFFFFFFFF for kernel */
  struct thread_info  *real_thread;    /* Points to non-IRQ stack */
  unsigned long aux_fp_regs[FP_SIZE]; /* auxiliary fp_regs to save/restore
               them out-of-band */
};

atomic_read(&p->real_cred->user->processes) >= task_rlimit(p, RLIMIT_NPROC) 

p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER |PF_IDLE);
p->flags |= PF_FORKNOEXEC;

部分代码：
/* copy all the process information */
shm_init_task(p);
retval = security_task_alloc(p, clone_flags);
retval = copy_semundo(clone_flags, p);
// 打开文件
retval = copy_files(clone_flags, p);
// 文件系统
retval = copy_fs(clone_flags, p);
retval = copy_sighand(clone_flags, p);
retval = copy_signal(clone_flags, p);
// 内存描述符（虚拟内存区域）
retval = copy_mm(clone_flags, p);
retval = copy_namespaces(clone_flags, p);
retval = copy_io(clone_flags, p);
retval = copy_thread_tls(clone_flags, stack_start, stack_size, p, tls);
  

static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
{
  struct mm_struct *mm, *oldmm;
  int retval;

  tsk->mm = NULL;
  tsk->active_mm = NULL;
    
  /* initialize the new vmacache entries */
  vmacache_flush(tsk);

    // 如果flags传入CLONE_VM，直接使用父进程的内存地址空间
  if (clone_flags & CLONE_VM) {
    mmget(oldmm);
    mm = oldmm;
    goto good_mm;
  }

  retval = -ENOMEM;
    // 拷贝内存描述符
  mm = dup_mm(tsk, current->mm);
  if (!mm)
    goto fail_nomem;

good_mm:
  tsk->mm = mm;
  tsk->active_mm = mm;
  return 0;

fail_nomem:
  return retval;
}

/**
 * dup_mm() - duplicates an existing mm structure
 * @tsk: the task_struct with which the new mm will be associated.
 * @oldmm: the mm to duplicate.
 *
 * Allocates a new mm structure and duplicates the provided @oldmm structure
 * content into it.
 *
 * Return: the duplicated mm or NULL on failure.
 */
static struct mm_struct *dup_mm(struct task_struct *tsk, struct mm_struct *oldmm)
{
  struct mm_struct *mm;
  int err;

  mm = allocate_mm();
  if (!mm)
    goto fail_nomem;

  memcpy(mm, oldmm, sizeof(*mm));

  if (!mm_init(mm, tsk, mm->user_ns))
    goto fail_nomem;

  err = dup_mmap(mm, oldmm);
  if (err)
    goto free_pt;

  mm->hiwater_rss = get_mm_rss(mm);
  mm->hiwater_vm = mm->total_vm;

  if (mm->binfmt && !try_module_get(mm->binfmt->module))
    goto free_pt;

  return mm;

free_pt:
  /* don't put binfmt in mmput, we haven't got module yet */
  mm->binfmt = NULL;
  mm_init_owner(mm, NULL);
  mmput(mm);

fail_nomem:
  return NULL;
}

void __noreturn do_exit(long code)
{
  struct task_struct *tsk = current;

  exit_signals(tsk);  /* sets PF_EXITING */

    // task_struct的退出code，供父进程检索
  tsk->exit_code = code;

  // 释放占用的内存描述符mm_struct，如果没有共享这个地址空间，则彻底释放
  exit_mm();

  // 退出等待队列
  exit_sem(tsk);
  exit_shm(tsk);
  // 递减文件描述符、文件系统的引用计数。如果引用计数降为0，没有被其他进程使用，则可以释放。
  exit_files(tsk);
  exit_fs(tsk);
  exit_task_namespaces(tsk);
  exit_task_work(tsk);
  exit_thread(tsk);
  exit_umh(tsk);

  // 给父进程发信号
  exit_notify(tsk, group_dead);
}