Linux fork()系统调用流程解析

1. fork()函数介绍（百度百科）

fork系统调用用于创建一个新进程，称为子进程，它与进程（称为系统调用fork的进程）同时运行，此进程称为父进程。创建新的子进程后，两个进程将执行fork（）系统调用之后的下一条指令。子进程使用相同的pc（程序计数器），相同的CPU寄存器，在父进程中使用的相同打开文件。
它不需要参数并返回一个整数值。下面是fork（）返回的不同值。
负值：创建子进程失败。
零：返回到新创建的子进程。
正值：返回父进程或调用者。该值包含新创建的子进程的进程ID。

2. fork()使用示例（百度百科）

#include
#include
#include
 
int main(int argc,char *argv[]){
    pid_t pid=fork();
    if ( pid < 0 ) {
        fprintf(stderr,"错误！");
    } else if( pid == 0 ) {
        printf("子进程空间");
        exit(0);
    } else {
        printf("父进程空间，子进程pid为%d",pid);
    }
    // 可以使用wait或waitpid函数等待子进程的结束并获取结束状态
    exit(0);
}

3. Linux中fork()代码实现分析

3.1 fork()系统调用定义

#ifdef __ARCH_WANT_SYS_FORK
SYSCALL_DEFINE0(fork)
{
#ifdef CONFIG_MMU
	struct kernel_clone_args args = {
		.exit_signal = SIGCHLD,
	};

	return kernel_clone(&args);
#else
	/* can not support in nommu mode */
	return -EINVAL;
#endif
}
#endif

fork()函数不需要传递任何参数，因此他的系统调用声明为DEFINE0。我们继续跟踪fork()系统调用的实现，这里发现是直接调用kernel_clone()函数进行后续处理。

3.2 跟踪kernel_clone()函数实现

/*
 *  Ok, this is the main fork-routine.
 *
 * It copies the process, and if successful kick-starts
 * it and waits for it to finish using the VM if required.
 *
 * args->exit_signal is expected to be checked for sanity by the caller.
 */
pid_t kernel_clone(struct kernel_clone_args *args)
{
	u64 clone_flags = args->flags;
	struct completion vfork;
	struct pid *pid;
	struct task_struct *p;
	int trace = 0;
	pid_t nr;

	/*
	 * For legacy clone() calls, CLONE_PIDFD uses the parent_tid argument
	 * to return the pidfd. Hence, CLONE_PIDFD and CLONE_PARENT_SETTID are
	 * mutually exclusive. With clone3() CLONE_PIDFD has grown a separate
	 * field in struct clone_args and it still doesn't make sense to have
	 * them both point at the same memory location. Performing this check
	 * here has the advantage that we don't need to have a separate helper
	 * to check for legacy clone().
	 */
	if ((args->flags & CLONE_PIDFD) &&
	    (args->flags & CLONE_PARENT_SETTID) &&
	    (args->pidfd == args->parent_tid))
		return -EINVAL;

	/*
	 * Determine whether and which event to report to ptracer.  When
	 * called from kernel_thread or CLONE_UNTRACED is explicitly
	 * requested, no event is reported; otherwise, report if the event
	 * for the type of forking is enabled.
	 */
	if (!(clone_flags & CLONE_UNTRACED)) {
		if (clone_flags & CLONE_VFORK)
			trace = PTRACE_EVENT_VFORK;
		else if (args->exit_signal != SIGCHLD)
			trace = PTRACE_EVENT_CLONE;
		else
			trace = PTRACE_EVENT_FORK;

		if (likely(!ptrace_event_enabled(current, trace)))
			trace = 0;
	}

	/* 通过copy_process()函数创建一个新的进程 */
	p = copy_process(NULL, trace, NUMA_NO_NODE, args);
	add_latent_entropy();

	if (IS_ERR(p))
		return PTR_ERR(p);

	/*
	 * Do this prior waking up the new thread - the thread pointer
	 * might get invalid after that point, if the thread exits quickly.
	 */
	trace_sched_process_fork(current, p);

	pid = get_task_pid(p, PIDTYPE_PID);
	nr = pid_vnr(pid);

	if (clone_flags & CLONE_PARENT_SETTID)
		put_user(nr, args->parent_tid);

	if (clone_flags & CLONE_VFORK) {
		p->vfork_done = &vfork;
		init_completion(&vfork);
		get_task_struct(p);
	}

	if (IS_ENABLED(CONFIG_LRU_GEN) && !(clone_flags & CLONE_VM)) {
		/* lock the task to synchronize with memcg migration */
		task_lock(p);
		lru_gen_add_mm(p->mm);
		task_unlock(p);
	}

	/* 唤醒新创建的进程 */
	wake_up_new_task(p);

	/* forking complete and child started to run, tell ptracer */
	if (unlikely(trace))
		ptrace_event_pid(trace, pid);

	if (clone_flags & CLONE_VFORK) {
		if (!wait_for_vfork_done(p, &vfork))
			ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid);
	}

	put_pid(pid);
	return nr;
}

从kernel_clone()函数定义可以看出，新进程的创建是通过拷贝父进程来实现的，通过copy_process()完成拷贝动作；而新进程的调度运行是通过wake_up_new_task()函数进行处理的。

3.3 跟踪copy_process()函数实现

/*
 * 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 __latent_entropy struct task_struct *copy_process(
					struct pid *pid,
					int trace,
					int node,
					struct kernel_clone_args *args)
{
	int pidfd = -1, retval;
	struct task_struct *p;
	struct multiprocess_signals delayed;
	struct file *pidfile = NULL;
	const u64 clone_flags = args->flags;
	struct nsproxy *nsp = current->nsproxy;

	/*
	 * Don't allow sharing the root directory with processes in a different
	 * namespace
	 */
	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) != nsp->pid_ns_for_children))
			return ERR_PTR(-EINVAL);
	}

	/*
	 * If the new process will be in a different time namespace
	 * do not allow it to share VM or a thread group with the forking task.
	 */
	if (clone_flags & (CLONE_THREAD | CLONE_VM)) {
		if (nsp->time_ns != nsp->time_ns_for_children)
			return ERR_PTR(-EINVAL);
	}

	if (clone_flags & CLONE_PIDFD) {
		/*
		 * - CLONE_DETACHED is blocked so that we can potentially
		 *   reuse it later for CLONE_PIDFD.
		 * - CLONE_THREAD is blocked until someone really needs it.
		 */
		if (clone_flags & (CLONE_DETACHED | CLONE_THREAD))
			return ERR_PTR(-EINVAL);
	}

	/*
	 * Force any signals received before this point to be delivered
	 * before the fork happens.  Collect up signals sent to multiple
	 * processes that happen during the fork and delay them so that
	 * they appear to happen after the fork.
	 */
	sigemptyset(&delayed.signal);
	INIT_HLIST_NODE(&delayed.node);

	spin_lock_irq(&current->sighand->siglock);
	if (!(clone_flags & CLONE_THREAD))
		hlist_add_head(&delayed.node, &current->signal->multiprocess);
	recalc_sigpending();
	spin_unlock_irq(&current->sighand->siglock);
	retval = -ERESTARTNOINTR;
	if (task_sigpending(current))
		goto fork_out;

	retval = -ENOMEM;
	/* 复制父进程的task_struct到新创建的进程，新进程的内核栈也在这个函数中分配 */
	p = dup_task_struct(current, node);
	if (!p)
		goto fork_out;
	p->flags &= ~PF_KTHREAD;
	if (args->kthread)
		p->flags |= PF_KTHREAD;
	if (args->io_thread) {
		/*
		 * Mark us an IO worker, and block any signal that isn't
		 * fatal or STOP
		 */
		p->flags |= PF_IO_WORKER;
		siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP));
	}

	p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? args->child_tid : NULL;
	/*
	 * Clear TID on mm_release()?
	 */
	p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? args->child_tid : NULL;

	ftrace_graph_init_task(p);

	rt_mutex_init_task(p);

	lockdep_assert_irqs_enabled();
#ifdef CONFIG_PROVE_LOCKING
	DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
#endif
	retval = copy_creds(p, clone_flags);
	if (retval < 0)
		goto bad_fork_free;

	retval = -EAGAIN;
	if (is_rlimit_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) {
		if (p->real_cred->user != INIT_USER &&
		    !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN))
			goto bad_fork_cleanup_count;
	}
	current->flags &= ~PF_NPROC_EXCEEDED;

	/*
	 * 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 (data_race(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 | PF_NO_SETAFFINITY);
	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.starttime = 0;
	p->vtime.state = VTIME_INACTIVE;
#endif

#ifdef CONFIG_IO_URING
	p->io_uring = NULL;
#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;

#ifdef CONFIG_PSI
	p->psi_flags = 0;
#endif

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

	posix_cputimers_init(&p->posix_cputimers);

	p->io_context = NULL;
	audit_set_context(p, NULL);
	cgroup_fork(p);
	if (args->kthread) {
		if (!set_kthread_struct(p))
			goto bad_fork_cleanup_delayacct;
	}
#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_delayacct;
	}
#endif
#ifdef CONFIG_CPUSETS
	p->cpuset_mem_spread_rotor = NUMA_NO_NODE;
	p->cpuset_slab_spread_rotor = NUMA_NO_NODE;
	seqcount_spinlock_init(&p->mems_allowed_seq, &p->alloc_lock);
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
	memset(&p->irqtrace, 0, sizeof(p->irqtrace));
	p->irqtrace.hardirq_disable_ip	= _THIS_IP_;
	p->irqtrace.softirq_enable_ip	= _THIS_IP_;
	p->softirqs_enabled		= 1;
	p->softirq_context		= 0;
#endif

	p->pagefault_disabled = 0;

#ifdef CONFIG_LOCKDEP
	lockdep_init_task(p);
#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
#ifdef CONFIG_BPF_SYSCALL
	RCU_INIT_POINTER(p->bpf_storage, NULL);
	p->bpf_ctx = NULL;
#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, clone_flags);
	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;
	/* 将父进程的所有打开文件描述符表都复制到新创建的进程中 */
	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;
	/* 将父进程的内存空间拷贝到新进程中，其实就是为新进程创建页表，把父进程的页表项拷贝到新进程中 */
	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(p, args);
	if (retval)
		goto bad_fork_cleanup_io;

	stackleak_task_init(p);

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

	/*
	 * This has to happen after we've potentially unshared the file
	 * descriptor table (so that the pidfd doesn't leak into the child
	 * if the fd table isn't shared).
	 */
	if (clone_flags & CLONE_PIDFD) {
		retval = get_unused_fd_flags(O_RDWR | O_CLOEXEC);
		if (retval < 0)
			goto bad_fork_free_pid;

		pidfd = retval;

		pidfile = anon_inode_getfile("[pidfd]", &pidfd_fops, pid,
					      O_RDWR | O_CLOEXEC);
		if (IS_ERR(pidfile)) {
			put_unused_fd(pidfd);
			retval = PTR_ERR(pidfile);
			goto bad_fork_free_pid;
		}
		get_pid(pid);	/* held by pidfile now */

		retval = put_user(pidfd, args->pidfd);
		if (retval)
			goto bad_fork_put_pidfd;
	}

#ifdef CONFIG_BLOCK
	p->plug = NULL;
#endif
	futex_init_task(p);

	/*
	 * 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_task_syscall_work(p, SYSCALL_TRACE);
#if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU)
	clear_task_syscall_work(p, SYSCALL_EMU);
#endif
	clear_tsk_latency_tracing(p);

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

#ifdef CONFIG_KRETPROBES
	p->kretprobe_instances.first = NULL;
#endif
#ifdef CONFIG_RETHOOK
	p->rethooks.first = NULL;
#endif

	/*
	 * Ensure that the cgroup subsystem policies allow the new process to be
	 * forked. It should be noted that 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, args);
	if (retval)
		goto bad_fork_put_pidfd;

	/*
	 * Now that the cgroups are pinned, re-clone the parent cgroup and put
	 * the new task on the correct runqueue. All this *before* the task
	 * becomes visible.
	 *
	 * This isn't part of ->can_fork() because while the re-cloning is
	 * cgroup specific, it unconditionally needs to place the task on a
	 * runqueue.
	 */
	sched_cgroup_fork(p, args);

	/*
	 * From this point on we must avoid any synchronous user-space
	 * communication until we take the tasklist-lock. In particular, we do
	 * not want user-space to be able to predict the process start-time by
	 * stalling fork(2) after we recorded the start_time but before it is
	 * visible to the system.
	 */

	p->start_time = ktime_get_ns();
	p->start_boottime = ktime_get_boottime_ns();

	/*
	 * 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;
		if (clone_flags & CLONE_THREAD)
			p->exit_signal = -1;
		else
			p->exit_signal = current->group_leader->exit_signal;
	} else {
		p->real_parent = current;
		p->parent_exec_id = current->self_exec_id;
		p->exit_signal = args->exit_signal;
	}

	klp_copy_process(p);

	sched_core_fork(p);

	spin_lock(&current->sighand->siglock);

	rv_task_fork(p);

	rseq_fork(p, clone_flags);

	/* Don't start children in a dying pid namespace */
	if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) {
		retval = -ENOMEM;
		goto bad_fork_cancel_cgroup;
	}

	/* Let kill terminate clone/fork in the middle */
	if (fatal_signal_pending(current)) {
		retval = -EINTR;
		goto bad_fork_cancel_cgroup;
	}

	/* No more failure paths after this point. */

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

	init_task_pid_links(p);
	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_TGID, pid);
			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->shared_pending.signal = delayed.signal;
			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_TGID);
			attach_pid(p, PIDTYPE_PGID);
			attach_pid(p, PIDTYPE_SID);
			__this_cpu_inc(process_counts);
		} else {
			current->signal->nr_threads++;
			current->signal->quick_threads++;
			atomic_inc(&current->signal->live);
			refcount_inc(&current->signal->sigcnt);
			task_join_group_stop(p);
			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++;
	hlist_del_init(&delayed.node);
	spin_unlock(&current->sighand->siglock);
	syscall_tracepoint_update(p);
	write_unlock_irq(&tasklist_lock);

	if (pidfile)
		fd_install(pidfd, pidfile);

	proc_fork_connector(p);
	sched_post_fork(p);
	cgroup_post_fork(p, args);
	perf_event_fork(p);

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

	copy_oom_score_adj(clone_flags, p);

	return p;

bad_fork_cancel_cgroup:
	sched_core_free(p);
	spin_unlock(&current->sighand->siglock);
	write_unlock_irq(&tasklist_lock);
	cgroup_cancel_fork(p, args);
bad_fork_put_pidfd:
	if (clone_flags & CLONE_PIDFD) {
		fput(pidfile);
		put_unused_fd(pidfd);
	}
bad_fork_free_pid:
	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) {
		mm_clear_owner(p->mm, p);
		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:
	lockdep_free_task(p);
#ifdef CONFIG_NUMA
	mpol_put(p->mempolicy);
#endif
bad_fork_cleanup_delayacct:
	delayacct_tsk_free(p);
bad_fork_cleanup_count:
	dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
	exit_creds(p);
bad_fork_free:
	WRITE_ONCE(p->__state, TASK_DEAD);
	exit_task_stack_account(p);
	put_task_stack(p);
	delayed_free_task(p);
fork_out:
	spin_lock_irq(&current->sighand->siglock);
	hlist_del_init(&delayed.node);
	spin_unlock_irq(&current->sighand->siglock);
	return ERR_PTR(retval);
}

copy_process()函数内容较多，博主只介绍跟内存空间相关的复制动作，因此下面介绍copy_mm()的实现。

3.4 跟踪copy_mm()函数实现

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

	tsk->min_flt = tsk->maj_flt = 0;
	tsk->nvcsw = tsk->nivcsw = 0;
#ifdef CONFIG_DETECT_HUNG_TASK
	tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw;
	tsk->last_switch_time = 0;
#endif

	tsk->mm = NULL;
	tsk->active_mm = NULL;

	/*
	 * Are we cloning a kernel thread?
	 *
	 * We need to steal a active VM for that..
	 */
	oldmm = current->mm;
	if (!oldmm)
		return 0;

	/* 如果是线程的创建则不需要为新的线程task_struct创建新的mm_struct结构，和父线程共享即可，其实这也就是人们常说的多进程间是共享同一内存的原因（或者是多进程之间通信简单） */
	if (clone_flags & CLONE_VM) {
		mmget(oldmm);
		mm = oldmm;
	} else { /* 如果是需要创建新的进程，则需要去分配新的mm_struct */
		mm = dup_mm(tsk, current->mm);
		if (!mm)
			return -ENOMEM;
	}

	tsk->mm = mm;
	tsk->active_mm = mm;
	return 0;
}

对于多线程的copy_mm()到这里就结束了，子线程共享父线程的地址空间，但是对于创建新的进程来说，还需要去创建新的mm_struct，因此还需要跟踪dup_mm()的实现。

3.5 跟踪dup_mm()函数实现

/**
 * 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;

	/* 分配一个新的mm_struct */
	mm = allocate_mm();
	if (!mm)
		goto fail_nomem;

	/* 拷贝父进程mm_struct的内容到子进程中 */
	memcpy(mm, oldmm, sizeof(*mm));

	/* 新进程的mm_struct初始化操作 */
	if (!mm_init(mm, tsk, mm->user_ns))
		goto fail_nomem;

	/* 拷贝父进程的所有vma到子进程，子进程的页表也是在此创建 */
	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;
}

在dup_mm()函数内部，通过调用dup_mmap()函数来将父进程的所有vma拷贝到新创建的子进程的mm_struct中。

3.6 跟踪dup_mmap()函数实现

#ifdef CONFIG_MMU
static __latent_entropy int dup_mmap(struct mm_struct *mm,
					struct mm_struct *oldmm)
{
	struct vm_area_struct *mpnt, *tmp;
	int retval;
	unsigned long charge = 0;
	LIST_HEAD(uf);
	MA_STATE(old_mas, &oldmm->mm_mt, 0, 0);
	MA_STATE(mas, &mm->mm_mt, 0, 0);

	uprobe_start_dup_mmap();
	if (mmap_write_lock_killable(oldmm)) {
		retval = -EINTR;
		goto fail_uprobe_end;
	}
	flush_cache_dup_mm(oldmm);
	uprobe_dup_mmap(oldmm, mm);
	/*
	 * Not linked in yet - no deadlock potential:
	 */
	mmap_write_lock_nested(mm, SINGLE_DEPTH_NESTING);

	/* No ordering required: file already has been exposed. */
	dup_mm_exe_file(mm, oldmm);

	mm->total_vm = oldmm->total_vm;
	mm->data_vm = oldmm->data_vm;
	mm->exec_vm = oldmm->exec_vm;
	mm->stack_vm = oldmm->stack_vm;

	retval = ksm_fork(mm, oldmm);
	if (retval)
		goto out;
	khugepaged_fork(mm, oldmm);

	retval = mas_expected_entries(&mas, oldmm->map_count);
	if (retval)
		goto out;

	/* 遍历父进程的所有vma */
	mas_for_each(&old_mas, mpnt, ULONG_MAX) {
		struct file *file;

		if (mpnt->vm_flags & VM_DONTCOPY) {
			vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt));
			continue;
		}
		charge = 0;
		/*
		 * Don't duplicate many vmas if we've been oom-killed (for
		 * example)
		 */
		if (fatal_signal_pending(current)) {
			retval = -EINTR;
			goto loop_out;
		}
		if (mpnt->vm_flags & VM_ACCOUNT) {
			unsigned long len = vma_pages(mpnt);

			if (security_vm_enough_memory_mm(oldmm, len)) /* sic */
				goto fail_nomem;
			charge = len;
		}
		/* 为新进程创建vma，并拷贝父进程的vma内容到新创建的vma中 */
		tmp = vm_area_dup(mpnt);
		if (!tmp)
			goto fail_nomem;
		retval = vma_dup_policy(mpnt, tmp);
		if (retval)
			goto fail_nomem_policy;
		tmp->vm_mm = mm;
		retval = dup_userfaultfd(tmp, &uf);
		if (retval)
			goto fail_nomem_anon_vma_fork;
		if (tmp->vm_flags & VM_WIPEONFORK) {
			/*
			 * VM_WIPEONFORK gets a clean slate in the child.
			 * Don't prepare anon_vma until fault since we don't
			 * copy page for current vma.
			 */
			tmp->anon_vma = NULL;
		} else if (anon_vma_fork(tmp, mpnt))
			goto fail_nomem_anon_vma_fork;
		tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT);
		file = tmp->vm_file;
		if (file) { /* 如果是文件页映射的vma，则会对新创建的vma做如下操作 */
			struct address_space *mapping = file->f_mapping;

			get_file(file);
			i_mmap_lock_write(mapping);
			if (tmp->vm_flags & VM_SHARED)
				mapping_allow_writable(mapping);
			flush_dcache_mmap_lock(mapping);
			/* insert tmp into the share list, just after mpnt */
			vma_interval_tree_insert_after(tmp, mpnt,
					&mapping->i_mmap);
			flush_dcache_mmap_unlock(mapping);
			i_mmap_unlock_write(mapping);
		}

		/*
		 * Copy/update hugetlb private vma information.
		 */
		if (is_vm_hugetlb_page(tmp))
			hugetlb_dup_vma_private(tmp);

		/* Link the vma into the MT */
		mas.index = tmp->vm_start;
		mas.last = tmp->vm_end - 1;
		mas_store(&mas, tmp);
		if (mas_is_err(&mas))
			goto fail_nomem_mas_store;

		mm->map_count++;
		if (!(tmp->vm_flags & VM_WIPEONFORK))
			/* 将父进程vma的页表信息拷贝到子进程中 */
			retval = copy_page_range(tmp, mpnt);

		if (tmp->vm_ops && tmp->vm_ops->open)
			tmp->vm_ops->open(tmp);

		if (retval)
			goto loop_out;
	}
	/* a new mm has just been created */
	retval = arch_dup_mmap(oldmm, mm);
loop_out:
	mas_destroy(&mas);
out:
	mmap_write_unlock(mm);
	flush_tlb_mm(oldmm);
	mmap_write_unlock(oldmm);
	dup_userfaultfd_complete(&uf);
fail_uprobe_end:
	uprobe_end_dup_mmap();
	return retval;

fail_nomem_mas_store:
	unlink_anon_vmas(tmp);
fail_nomem_anon_vma_fork:
	mpol_put(vma_policy(tmp));
fail_nomem_policy:
	vm_area_free(tmp);
fail_nomem:
	retval = -ENOMEM;
	vm_unacct_memory(charge);
	goto loop_out;
}

这里就是fork()系统调用的实现全部内容了，细节并没有全部展开，读者可自行阅读源码。