프로 세 스 생 성 copy프로 세 스 함수

copy_프로 세 스 함수 가 프로 세 스에 서 만 든 dofork 함수 에서 호출 되 었 습 니 다. 주로 프로 세 스 데이터 구 조 를 완 료 했 고 각종 자원 의 초기 화 를 완 료 했 습 니 다.초기 화 방식 은 재배 치 할 수도 있 고 부모 프로 세 스 자원 을 공유 할 수도 있 습 니 다. 주로 CLONE 인자 에 따라 확 정 됩 니 다.

/*
 * This creates a new process as a copy of the old one,
 * but does not actually start it yet.
 *
 * 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.
 */
static struct task_struct *copy_process(unsigned long clone_flags,
					unsigned long stack_start,
					struct pt_regs *regs,
					unsigned long stack_size,
					int __user *child_tidptr,
					struct pid *pid,
					int trace)
{
	int retval;
	struct task_struct *p;
	int cgroup_callbacks_done = 0;
	/*          */
	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.
	 */
	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);

	/*
	 * Siblings of global init remain as zombies on exit since they are
	 * not reaped by their parent (swapper). To solve this and to avoid
	 * multi-rooted process trees, prevent global and container-inits
	 * from creating siblings.
	 */
	if ((clone_flags & CLONE_PARENT) &&
				current->signal->flags & SIGNAL_UNKILLABLE)
		return ERR_PTR(-EINVAL);
	/*Check permission before creating a child process.  See the clone(2)
 *	manual page for definitions of the @clone_flags.
 *	@clone_flags contains the flags indicating what should be shared.
 *	Return 0 if permission is granted.*/
	retval = security_task_create(clone_flags);
	if (retval)
		goto fork_out;

	retval = -ENOMEM;
	/*           、thread_iofo task_struct,
	    copy      ，       ，
	               。,    
	    ，                
	     */
	p = dup_task_struct(current);
	if (!p)
		goto fork_out;
	/*task   ftrace_ret_stack        ，   
	     */
	ftrace_graph_init_task(p);
	/*task         */
	rt_mutex_init_task(p);

#ifdef CONFIG_PROVE_LOCKING/*not set*/
	DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
	DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
#endif
	retval = -EAGAIN;
	/*        if，   if   rlim     task_sturct   。
	             ，rlim[RLIMIT_NPROC]        
	          ，                 
	           ，       goto bad_fork_free 。
	 2 if   capable（）          ，      
	          ，     0       。*/
	if (atomic_read(&p->real_cred->user->processes) >=
			p->signal->rlim[RLIMIT_NPROC].rlim_cur) {
		if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
		    p->real_cred->user != INIT_USER)
			goto bad_fork_free;
	}
	/*Copy credentials for the new process*/
	retval = copy_creds(p, clone_flags);
	if (retval < 0)
		goto bad_fork_free;

	/*
	 * 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.
	 */
	retval = -EAGAIN;
	/*                  */
	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;

	p->did_exec = 0;
	delayacct_tsk_init(p);	/* Must remain after dup_task_struct() */
	/*  task_struct   flags  */
	copy_flags(clone_flags, p);
	INIT_LIST_HEAD(&p->children);
	INIT_LIST_HEAD(&p->sibling);
	rcu_copy_process(p);/*rcu        */
	p->vfork_done = NULL;
	spin_lock_init(&p->alloc_lock);

	init_sigpending(&p->pending);

	p->utime = cputime_zero;
	p->stime = cputime_zero;
	p->gtime = cputime_zero;
	p->utimescaled = cputime_zero;
	p->stimescaled = cputime_zero;
	p->prev_utime = cputime_zero;
	p->prev_stime = cputime_zero;

	p->default_timer_slack_ns = current->timer_slack_ns;

	task_io_accounting_init(&p->ioac);/*task io        */
	acct_clear_integrals(p);/*clear the mm integral fields in task_struct*/

	posix_cpu_timers_init(p);/*timer   */

	p->lock_depth = -1;		/* -1 = no lock */
	do_posix_clock_monotonic_gettime(&p->start_time);
	p->real_start_time = p->start_time;
	monotonic_to_bootbased(&p->real_start_time);
	p->io_context = NULL;
	p->audit_context = NULL;
	cgroup_fork(p);/*attach newly forked task to its parents cgroup.*/
#ifdef CONFIG_NUMA/*not set*/
	p->mempolicy = mpol_dup(p->mempolicy);
 	if (IS_ERR(p->mempolicy)) {
 		retval = PTR_ERR(p->mempolicy);
 		p->mempolicy = NULL;
 		goto bad_fork_cleanup_cgroup;
 	}
	mpol_fix_fork_child_flag(p);
#endif
#ifdef CONFIG_TRACE_IRQFLAGS/*yes*/
	p->irq_events = 0;
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW/*not found*/
	p->hardirqs_enabled = 1;
#else
	p->hardirqs_enabled = 0;
#endif
	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/*yes*/
	p->lockdep_depth = 0; /* no locks held yet */
	p->curr_chain_key = 0;
	p->lockdep_recursion = 0;
#endif

#ifdef CONFIG_DEBUG_MUTEXES/*not set */
	p->blocked_on = NULL; /* not blocked yet */
#endif

	p->bts = NULL;

	p->stack_start = stack_start;

	/* Perform scheduler related setup. Assign this task to a CPU. */
	sched_fork(p, clone_flags);/*       */
	/*
 	* Initialize the perf_event context in task_struct
 	*/
	retval = perf_event_init_task(p);
	if (retval)
		goto bad_fork_cleanup_policy;

	if ((retval = audit_alloc(p)))
		goto bad_fork_cleanup_policy;

	/*      ，  flag          
	                */
	/* 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_namespaces(clone_flags, p)))
		goto bad_fork_cleanup_mm;
	if ((retval = copy_io(clone_flags, p)))
		goto bad_fork_cleanup_namespaces;
	retval = copy_thread(clone_flags, stack_start, stack_size, p, regs);
	if (retval)
		goto bad_fork_cleanup_io;

	if (pid != &init_struct_pid) {
		retval = -ENOMEM;
		pid = alloc_pid(p->nsproxy->pid_ns);
		if (!pid)
			goto bad_fork_cleanup_io;

		if (clone_flags & CLONE_NEWPID) {
			retval = pid_ns_prepare_proc(p->nsproxy->pid_ns);
			if (retval < 0)
				goto bad_fork_free_pid;
		}
	}

	p->pid = pid_nr(pid);
	p->tgid = p->pid;
	/*               TGID。
	        TGID PID  ，
	      ，            TGID   ，
	              getpid()     PID。*/
	if (clone_flags & CLONE_THREAD)
		p->tgid = current->tgid;
	/*         ，clone the cgroup the given subsystem is attached to*/
	if (current->nsproxy != p->nsproxy) {
		retval = ns_cgroup_clone(p, pid);
		if (retval)
			goto bad_fork_free_pid;
	}
	/*     CLONE_CHILD_SETTID,        */
	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;
#ifdef CONFIG_FUTEX/*yes*/
	p->robust_list = NULL;
#ifdef CONFIG_COMPAT/*not found*/
	p->compat_robust_list = NULL;
#endif
	INIT_LIST_HEAD(&p->pi_state_list);
	p->pi_state_cache = NULL;
#endif
	/*
	 * 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/*not found*/
	clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
#endif
	clear_all_latency_tracing(p);

	/* 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);

	/* Now that the task is set up, run cgroup callbacks if
	 * necessary. We need to run them before the task is visible
	 * on the tasklist. */
	cgroup_fork_callbacks(p);
	cgroup_callbacks_done = 1;

	/* 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;
	p->rt.nr_cpus_allowed = current->rt.nr_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;
		p->parent_exec_id = current->parent_exec_id;
	} else {/*         */
		p->real_parent = current;
		p->parent_exec_id = current->self_exec_id;
	}

	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_free_pid;
	}
	/*             */
	if (clone_flags & CLONE_THREAD) {
		atomic_inc(¤t->signal->count);
		atomic_inc(¤t->signal->live);
		p->group_leader = current->group_leader;/*          */
		/*      leader     */
		list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
	}

	if (likely(p->pid)) {
		/*         */
		list_add_tail(&p->sibling, &p->real_parent->children);
		/*ptrace      */
		tracehook_finish_clone(p, clone_flags, trace);

		if (thread_group_leader(p)) {/*    p    leader*/
			if (clone_flags & CLONE_NEWPID)
				/*       pid    ，   
				     child_reaper    p,     
				               */
				p->nsproxy->pid_ns->child_reaper = p;

			p->signal->leader_pid = pid;
			tty_kref_put(p->signal->tty);/*  tty  */
			p->signal->tty = tty_kref_get(current->signal->tty);/*  tty  */
			/*          pid   ，  pid
			          */
			attach_pid(p, PIDTYPE_PGID, task_pgrp(current));
			attach_pid(p, PIDTYPE_SID, task_session(current));
			list_add_tail_rcu(&p->tasks, &init_task.tasks);/*    */
			__get_cpu_var(process_counts)++;/* per cpu    */
		}
		attach_pid(p, PIDTYPE_PID, pid);/*  pid  */
		nr_threads++;/*     */
	}

	total_forks++;
	spin_unlock(¤t->sighand->siglock);
	write_unlock_irq(&tasklist_lock);
	proc_fork_connector(p);
	/*Adds the task to the list running through its css_set if necessary.*/
	cgroup_post_fork(p);
	perf_event_fork(p);
	return p;

bad_fork_free_pid:
	if (pid != &init_struct_pid)
		free_pid(pid);
bad_fork_cleanup_io:
	put_io_context(p->io_context);
bad_fork_cleanup_namespaces:
	exit_task_namespaces(p);
bad_fork_cleanup_mm:
	if (p->mm)
		mmput(p->mm);
bad_fork_cleanup_signal:
	if (!(clone_flags & CLONE_THREAD))
		__cleanup_signal(p->signal);
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_policy:
	perf_event_free_task(p);
#ifdef CONFIG_NUMA
	mpol_put(p->mempolicy);
bad_fork_cleanup_cgroup:
#endif
	cgroup_exit(p, cgroup_callbacks_done);
	delayacct_tsk_free(p);
	module_put(task_thread_info(p)->exec_domain->module);
bad_fork_cleanup_count:
	atomic_dec(&p->cred->user->processes);
	exit_creds(p);
bad_fork_free:
	free_task(p);
fork_out:
	return ERR_PTR(retval);
}

static struct task_struct *dup_task_struct(struct task_struct *orig)
{
	struct task_struct *tsk;
	struct thread_info *ti;
	unsigned long *stackend;

	int err;
	/*fpu    */
	prepare_to_copy(orig);
	/*  alloc_task_struct()    task_struct    */
	tsk = alloc_task_struct();
	if (!tsk)
		return NULL;
	/*  thread_info    ,    order 1，       */
	ti = alloc_thread_info(tsk);
	if (!ti) {/*  thread info      ，  tsk*/
		free_task_struct(tsk);
		return NULL;
	}
	/*         */
 	err = arch_dup_task_struct(tsk, orig);
	if (err)
		goto out;

	tsk->stack = ti;/*task    */
	/*   prop_local_single  */
	err = prop_local_init_single(&tsk->dirties);
	if (err)
		goto out;
	/*   thread info  */
	setup_thread_stack(tsk, orig);
	stackend = end_of_stack(tsk);/*          */
	/*               */
	*stackend = STACK_END_MAGIC;	/* for overflow detection */

#ifdef CONFIG_CC_STACKPROTECTOR/*yes*/
	tsk->stack_canary = get_random_int();/*   stack_canary  */
#endif

	/* One for us, one for whoever does the "release_task()" (usually parent) */
	atomic_set(&tsk->usage,2);
	atomic_set(&tsk->fs_excl, 0);/*   fs  */
#ifdef CONFIG_BLK_DEV_IO_TRACE/*yes*/
	tsk->btrace_seq = 0;
#endif
	tsk->splice_pipe = NULL;

	account_kernel_stack(ti, 1);

	return tsk;

out:
	free_thread_info(ti);
	free_task_struct(tsk);
	return NULL;
}

/*
 * fork()/clone()-time setup:
 */
void sched_fork(struct task_struct *p, int clone_flags)
{
	int cpu = get_cpu();/*  cpu id*/

	__sched_fork(p);

	/*
	 * Revert to default priority/policy on fork if requested.
	 */
	if (unlikely(p->sched_reset_on_fork)) {
		if (p->policy == SCHED_FIFO || p->policy == SCHED_RR) {
			p->policy = SCHED_NORMAL;
			p->normal_prio = p->static_prio;
		}

		if (PRIO_TO_NICE(p->static_prio) < 0) {
			p->static_prio = NICE_TO_PRIO(0);
			p->normal_prio = p->static_prio;
			set_load_weight(p);
		}

		/*
		 * We don't need the reset flag anymore after the fork. It has
		 * fulfilled its duty:
		 */
		p->sched_reset_on_fork = 0;
	}

	/*
	 * Make sure we do not leak PI boosting priority to the child.
	 */
	p->prio = current->normal_prio;

	if (!rt_prio(p->prio))
		p->sched_class = &fair_sched_class;

#ifdef CONFIG_SMP
	cpu = p->sched_class->select_task_rq(p, SD_BALANCE_FORK, 0);
#endif
	set_task_cpu(p, cpu);/*        cpu   */

#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)/*yes*/
	if (likely(sched_info_on()))
		memset(&p->sched_info, 0, sizeof(p->sched_info));
#endif
#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
	p->oncpu = 0;
#endif
#ifdef CONFIG_PREEMPT/*not set*/
	/* Want to start with kernel preemption disabled. */
	task_thread_info(p)->preempt_count = 1;
#endif
	plist_node_init(&p->pushable_tasks, MAX_PRIO);

	put_cpu();
}

주요 호출sched_fork

/*
 * Perform scheduler related setup for a newly forked process p.
 * p is forked by current.
 *
 * __sched_fork() is basic setup used by init_idle() too:
 */
static void __sched_fork(struct task_struct *p)
{	/*       */
	p->se.exec_start		= 0;
	p->se.sum_exec_runtime		= 0;
	...

	p->se.nr_wakeups_idle			= 0;

#endif

	INIT_LIST_HEAD(&p->rt.run_list);/*           */
	p->se.on_rq = 0;
	INIT_LIST_HEAD(&p->se.group_node);

#ifdef CONFIG_PREEMPT_NOTIFIERS/*yes*/
	INIT_HLIST_HEAD(&p->preempt_notifiers);
#endif

	/*
	 * We mark the process as running here, but have not actually
	 * inserted it onto the runqueue yet. This guarantees that
	 * nobody will actually run it, and a signal or other external
	 * event cannot wake it up and insert it on the runqueue either.
	 *//*          */
	p->state = TASK_RUNNING;
}

주석 이 대부분 달 려 있어 쉽게 알 아 볼 수 있 는 곳 이 많다.또한 프로 세 스 생 성에 있어 서 버 전 을 사용 하지 않 는 커 널 의 차이 가 매우 크 므 로 이 를 보 려 면 구체 적 인 버 전 을 확인 하 는 것 이 좋 습 니 다. 새 버 전에 새로운 것 이 많이 추 가 될 수 있 습 니 다.이렇게 하려 면 다른 메커니즘 과 결합 하여 이해 해 야 한다.