《Linux内核深度解析》 进程调度和多线程管理

beyond_笑谈

《Linux内核深度解析》 进程调度和多线程管理 [复制链接]

在Linux内核中，3个系统调用可以用来创建新的进程。

1. fork（分叉）：子进程是父进程的一个副本，采用了写时复制的技术
2. vfork：用于创建子进程，之后子进程立即调用execve以装载新程序的情况。为了避免复制物理页，父进程会睡眠等待子进程装载新程序。现在fork采用了写时复制的技术，vfork失去了速度优势，已经被废弃。
3. clone（克隆）：可以精确地控制子进程和父进程共享哪些资源。这个系统调用的主要用处是可供pthread库用来创建线程。其中clone是功能最齐全的函数，参数多，使用复杂，fork是clone的简化函数。
4. 函数_do_fork，代码如下

long _do_fork(unsigned long clone_flags,	//克隆标志
	      unsigned long stack_start,	//用作指定新线程的用户栈的起始地址
	      unsigned long stack_size,		//指定新线程的用户栈的长度
	      int __user *parent_tidptr,		//新线程保存进程标识符的位置
	      int __user *child_tidptr,		//存放新线程保存进程标识符的位置
	      unsigned long tls)			//指定新线程本地存储的位置

     5. 函数copy_process

    创建新进程的主要工作由函数copy_process完成，代码如下

static __latent_entropy struct task_struct *copy_process(
					unsigned long clone_flags,
					unsigned long stack_start,
					unsigned long stack_size,
					int __user *child_tidptr,
					struct pid *pid,
					int trace,
					unsigned long tls,
					int node)
{
	int retval;
	struct task_struct *p;

	if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
		return ERR_PTR(-EINVAL);

	if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|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);

	/*
	 * If the new process will be in a different pid or user namespace
	 * do not allow it to share a thread group with the forking task.
	 */
	if (clone_flags & CLONE_THREAD) {
		if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) ||
		    (task_active_pid_ns(current) !=
				current->nsproxy->pid_ns_for_children))
			return ERR_PTR(-EINVAL);
	}

	retval = security_task_create(clone_flags);
	if (retval)
		goto fork_out;

	retval = -ENOMEM;
	p = dup_task_struct(current, node);
	if (!p)
		goto fork_out;

	/*
	 * This _must_ happen before we call free_task(), i.e. before we jump
	 * to any of the bad_fork_* labels. This is to avoid freeing
	 * p->set_child_tid which is (ab)used as a kthread's data pointer for
	 * kernel threads (PF_KTHREAD).
	 */
	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;

	ftrace_graph_init_task(p);

	rt_mutex_init_task(p);

#ifdef CONFIG_PROVE_LOCKING
	DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
	DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
#endif
	retval = -EAGAIN;
	if (atomic_read(&p->real_cred->user->processes) >=
			task_rlimit(p, RLIMIT_NPROC)) {
		if (p->real_cred->user != INIT_USER &&
		    !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN))
			goto bad_fork_free;
	}
	current->flags &= ~PF_NPROC_EXCEEDED;

	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;

	delayacct_tsk_init(p);	/* Must remain after dup_task_struct() */
	p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE);
	p->flags |= PF_FORKNOEXEC;
	INIT_LIST_HEAD(&p->children);
	INIT_LIST_HEAD(&p->sibling);
	rcu_copy_process(p);
	p->vfork_done = NULL;
	spin_lock_init(&p->alloc_lock);

	init_sigpending(&p->pending);

	p->utime = p->stime = p->gtime = 0;
#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
	p->utimescaled = p->stimescaled = 0;
#endif
	prev_cputime_init(&p->prev_cputime);

#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
	seqcount_init(&p->vtime_seqcount);
	p->vtime_snap = 0;
	p->vtime_snap_whence = VTIME_INACTIVE;
#endif

#if defined(SPLIT_RSS_COUNTING)
	memset(&p->rss_stat, 0, sizeof(p->rss_stat));
#endif

	p->default_timer_slack_ns = current->timer_slack_ns;

	task_io_accounting_init(&p->ioac);
	acct_clear_integrals(p);

	posix_cpu_timers_init(p);

	p->start_time = ktime_get_ns();
	p->real_start_time = ktime_get_boot_ns();
	p->io_context = NULL;
	p->audit_context = NULL;
	cgroup_fork(p);
#ifdef CONFIG_NUMA
	p->mempolicy = mpol_dup(p->mempolicy);
	if (IS_ERR(p->mempolicy)) {
		retval = PTR_ERR(p->mempolicy);
		p->mempolicy = NULL;
		goto bad_fork_cleanup_threadgroup_lock;
	}
#endif
#ifdef CONFIG_CPUSETS
	p->cpuset_mem_spread_rotor = NUMA_NO_NODE;
	p->cpuset_slab_spread_rotor = NUMA_NO_NODE;
	seqcount_init(&p->mems_allowed_seq);
#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

	p->pagefault_disabled = 0;

#ifdef CONFIG_LOCKDEP
	p->lockdep_depth = 0; /* no locks held yet */
	p->curr_chain_key = 0;
	p->lockdep_recursion = 0;
#endif

#ifdef CONFIG_DEBUG_MUTEXES
	p->blocked_on = NULL; /* not blocked yet */
#endif
#ifdef CONFIG_BCACHE
	p->sequential_io	= 0;
	p->sequential_io_avg	= 0;
#endif

	/* Perform scheduler related setup. Assign this task to a CPU. */
	retval = sched_fork(clone_flags, p);
	if (retval)
		goto bad_fork_cleanup_policy;

	retval = perf_event_init_task(p);
	if (retval)
		goto bad_fork_cleanup_policy;
	retval = audit_alloc(p);
	if (retval)
		goto bad_fork_cleanup_perf;
	/* copy all the process information */
	shm_init_task(p);
	retval = security_task_alloc(p, clone_flags);
	if (retval)
		goto bad_fork_cleanup_audit;
	retval = copy_semundo(clone_flags, p);
	if (retval)
		goto bad_fork_cleanup_security;
	retval = copy_files(clone_flags, p);
	if (retval)
		goto bad_fork_cleanup_semundo;
	retval = copy_fs(clone_flags, p);
	if (retval)
		goto bad_fork_cleanup_files;
	retval = copy_sighand(clone_flags, p);
	if (retval)
		goto bad_fork_cleanup_fs;
	retval = copy_signal(clone_flags, p);
	if (retval)
		goto bad_fork_cleanup_sighand;
	retval = copy_mm(clone_flags, p);
	if (retval)
		goto bad_fork_cleanup_signal;
	retval = copy_namespaces(clone_flags, p);
	if (retval)
		goto bad_fork_cleanup_mm;
	retval = copy_io(clone_flags, p);
	if (retval)
		goto bad_fork_cleanup_namespaces;
	retval = copy_thread_tls(clone_flags, stack_start, stack_size, p, tls);
	if (retval)
		goto bad_fork_cleanup_io;

	if (pid != &init_struct_pid) {
		pid = alloc_pid(p->nsproxy->pid_ns_for_children);
		if (IS_ERR(pid)) {
			retval = PTR_ERR(pid);
			goto bad_fork_cleanup_thread;
		}
	}

#ifdef CONFIG_BLOCK
	p->plug = NULL;
#endif
#ifdef CONFIG_FUTEX
	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;
#endif
	/*
	 * sigaltstack should be cleared when sharing the same VM
	 */
	if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM)
		sas_ss_reset(p);

	/*
	 * Syscall tracing and stepping should be turned off in the
	 * child regardless of CLONE_PTRACE.
	 */
	user_disable_single_step(p);
	clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
#ifdef TIF_SYSCALL_EMU
	clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
#endif
	clear_all_latency_tracing(p);

	/* ok, now we should be set up.. */
	p->pid = pid_nr(pid);
	if (clone_flags & CLONE_THREAD) {
		p->exit_signal = -1;
		p->group_leader = current->group_leader;
		p->tgid = current->tgid;
	} else {
		if (clone_flags & CLONE_PARENT)
			p->exit_signal = current->group_leader->exit_signal;
		else
			p->exit_signal = (clone_flags & CSIGNAL);
		p->group_leader = p;
		p->tgid = p->pid;
	}

	p->nr_dirtied = 0;
	p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10);
	p->dirty_paused_when = 0;

	p->pdeath_signal = 0;
	INIT_LIST_HEAD(&p->thread_group);
	p->task_works = NULL;

	cgroup_threadgroup_change_begin(current);
	/*
	 * Ensure that the cgroup subsystem policies allow the new process to be
	 * forked. It should be noted the the new process's css_set can be changed
	 * between here and cgroup_post_fork() if an organisation operation is in
	 * progress.
	 */
	retval = cgroup_can_fork(p);
	if (retval)
		goto bad_fork_free_pid;

	/*
	 * Make it visible to the rest of the system, but dont wake it up yet.
	 * Need tasklist lock for parent etc handling!
	 */
	write_lock_irq(&tasklist_lock);

	/* 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;
	}

	klp_copy_process(p);

	spin_lock(¤t->sighand->siglock);

	/*
	 * Copy seccomp details explicitly here, in case they were changed
	 * before holding sighand lock.
	 */
	copy_seccomp(p);

	/*
	 * 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)) {
		retval = -ERESTARTNOINTR;
		goto bad_fork_cancel_cgroup;
	}
	if (unlikely(!(ns_of_pid(pid)->nr_hashed & PIDNS_HASH_ADDING))) {
		retval = -ENOMEM;
		goto bad_fork_cancel_cgroup;
	}

	if (likely(p->pid)) {
		ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);

		init_task_pid(p, PIDTYPE_PID, pid);
		if (thread_group_leader(p)) {
			init_task_pid(p, PIDTYPE_PGID, task_pgrp(current));
			init_task_pid(p, PIDTYPE_SID, task_session(current));

			if (is_child_reaper(pid)) {
				ns_of_pid(pid)->child_reaper = p;
				p->signal->flags |= SIGNAL_UNKILLABLE;
			}

			p->signal->leader_pid = pid;
			p->signal->tty = tty_kref_get(current->signal->tty);
			/*
			 * Inherit has_child_subreaper flag under the same
			 * tasklist_lock with adding child to the process tree
			 * for propagate_has_child_subreaper optimization.
			 */
			p->signal->has_child_subreaper = p->real_parent->signal->has_child_subreaper ||
							 p->real_parent->signal->is_child_subreaper;
			list_add_tail(&p->sibling, &p->real_parent->children);
			list_add_tail_rcu(&p->tasks, &init_task.tasks);
			attach_pid(p, PIDTYPE_PGID);
			attach_pid(p, PIDTYPE_SID);
			__this_cpu_inc(process_counts);
		} else {
			current->signal->nr_threads++;
			atomic_inc(¤t->signal->live);
			atomic_inc(¤t->signal->sigcnt);
			list_add_tail_rcu(&p->thread_group,
					  &p->group_leader->thread_group);
			list_add_tail_rcu(&p->thread_node,
					  &p->signal->thread_head);
		}
		attach_pid(p, PIDTYPE_PID);
		nr_threads++;
	}

	total_forks++;
	spin_unlock(¤t->sighand->siglock);
	syscall_tracepoint_update(p);
	write_unlock_irq(&tasklist_lock);

	proc_fork_connector(p);
	cgroup_post_fork(p);
	cgroup_threadgroup_change_end(current);
	perf_event_fork(p);

	trace_task_newtask(p, clone_flags);
	uprobe_copy_process(p, clone_flags);

	return p;

bad_fork_cancel_cgroup:
	spin_unlock(¤t->sighand->siglock);
	write_unlock_irq(&tasklist_lock);
	cgroup_cancel_fork(p);
bad_fork_free_pid:
	cgroup_threadgroup_change_end(current);
	if (pid != &init_struct_pid)
		free_pid(pid);
bad_fork_cleanup_thread:
	exit_thread(p);
bad_fork_cleanup_io:
	if (p->io_context)
		exit_io_context(p);
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))
		free_signal_struct(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_security:
	security_task_free(p);
bad_fork_cleanup_audit:
	audit_free(p);
bad_fork_cleanup_perf:
	perf_event_free_task(p);
bad_fork_cleanup_policy:
#ifdef CONFIG_NUMA
	mpol_put(p->mempolicy);
bad_fork_cleanup_threadgroup_lock:
#endif
	delayacct_tsk_free(p);
bad_fork_cleanup_count:
	atomic_dec(&p->cred->user->processes);
	exit_creds(p);
bad_fork_free:
	p->state = TASK_DEAD;
	put_task_stack(p);
	free_task(p);
fork_out:
	return ERR_PTR(retval);
} 
//end copy_process

    

        6.    唤醒新进程

        函数wake_up_new_task负责唤醒刚刚创建的新进程，代码如下

        

void wake_up_new_task(struct task_struct *p)
{
	struct rq_flags rf;
	struct rq *rq;

	raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
	p->state = TASK_RUNNING;
#ifdef CONFIG_SMP
	/*
	 * Fork balancing, do it here and not earlier because:
	 *  - cpus_allowed can change in the fork path
	 *  - any previously selected CPU might disappear through hotplug
	 *
	 * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
	 * as we're not fully set-up yet.
	 */
	__set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
#endif
	rq = __task_rq_lock(p, &rf);
	update_rq_clock(rq);
	post_init_entity_util_avg(&p->se);

	activate_task(rq, p, ENQUEUE_NOCLOCK);
	p->on_rq = TASK_ON_RQ_QUEUED;
	trace_sched_wakeup_new(p);
	check_preempt_curr(rq, p, WF_FORK);
#ifdef CONFIG_SMP
	if (p->sched_class->task_woken) {
		/*
		 * Nothing relies on rq->lock after this, so its fine to
		 * drop it.
		 */
		rq_unpin_lock(rq, &rf);
		p->sched_class->task_woken(rq, p);
		rq_repin_lock(rq, &rf);
	}
#endif
	task_rq_unlock(rq, p, &rf);
}
// end of wake_up_new_task

 

        7.   新进程第一次运行

        新进程第一次运行是从函数ret_from_fork开始执行，函数ret_from_fork是由各种处理器架构自定义的函数，ARM64架构定义的函数ret_from_fork代码如下

tsk	.req	x28		// current thread_info

ENTRY(ret_from_fork)
	bl	schedule_tail
	cbz	x19, 1f				// not a kernel thread
	mov	x0, x20
	blr	x19
1:	get_thread_info tsk
	b	ret_to_user
ENDPROC(ret_from_fork)