Linux内核创建一个新进程的过程

骑猪看日落 2022-07-25 16:58 163阅读 0赞

作者：王鹤楼  
原创作品转载请注明出处 《Linux内核分析》MOOC课程  
[http://mooc.study.163.com/course/USTC-1000029000][http_mooc.study.163.com_course_USTC-1000029000]

## 操作系统的三大功能 ##

进程管理  
内存管理  
文件系统

## task\_struct ##

用来描述进程的数据结构，可以理解为进程的属性。进程状态、进程调度信息、各种标识符、进程通信有关信息、时间和定时器信息、进程链接信息、文件系统信息、虚拟内存信息、页面管理信息、对称多处理器和处理器相关的环境等，该数据结构被定义为task\_struct

## 进程控制块 PCB ##

是操作系统核心中一种数据结构，主要表示进程状态。

## 进程状态 ##

![这里写图片描述][20160403164725382]

在实验楼里进行如下操作，由于进行到一半环境太卡，没有充分截图  
执行操作：  
rm -rf menu  
然后克隆一份新的代码：  
git clone [https://github.com/mengning/menu.git][https_github.com_mengning_menu.git]  
cd menu  
mv fork\_test.c test.c  
make rootfs  
出现菜单后执行fork命令，可以看出打印信息，已经创建了子进程

qemu -kernel linux-3.18.6/arch/x86/boot/bzImage -initrd rootfs.img -s -S

gdb  
target remote:1234  
file linux-3.18.6/vmlinux  
b sys\_clone  
b do\_fork  
b dup\_task\_struct  
b copy\_process  
b copy\_thread  
b ret\_from\_fork  
c //开始执行

## fork函数 ##

调用一次返回两次，父进程中返加子进程的pid,子进程中返回0

//fork
    #ifdef __ARCH_WANT_SYS_FORK
    SYSCALL_DEFINE0(fork)
    {
    #ifdef CONFIG_MMU
        return do_fork(SIGCHLD, 0, 0, NULL, NULL);
    #else
        /* can not support in nommu mode */
        return -EINVAL;
    #endif
    }
    #endif
    
    //vfork
    #ifdef __ARCH_WANT_SYS_VFORK
    SYSCALL_DEFINE0(vfork)
    {
        return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0,
                0, NULL, NULL);
    }
    #endif
    
    //clone
    #ifdef __ARCH_WANT_SYS_CLONE
    #ifdef CONFIG_CLONE_BACKWARDS
    SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
             int __user *, parent_tidptr,
             int, tls_val,
             int __user *, child_tidptr)
    #elif defined(CONFIG_CLONE_BACKWARDS2)
    SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags,
             int __user *, parent_tidptr,
             int __user *, child_tidptr,
             int, tls_val)
    #elif defined(CONFIG_CLONE_BACKWARDS3)
    SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp,
            int, stack_size,
            int __user *, parent_tidptr,
            int __user *, child_tidptr,
            int, tls_val)
    #else
    SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
             int __user *, parent_tidptr,
             int __user *, child_tidptr,
             int, tls_val)
    #endif
    {
        return do_fork(clone_flags, newsp, 0, parent_tidptr, child_tidptr);
    }
    #endif

从以上代码中可以看出fork,vfork,clone最终都是调用 do\_fork来创建新进程

do\_fork

long do_fork(unsigned long clone_flags,
              unsigned long stack_start,
              unsigned long stack_size,
              int __user *parent_tidptr,
              int __user *child_tidptr)
    {
            //创建进程描述符指针
            struct task_struct *p;
    
            //……
    
            //复制进程描述符，copy_process()的返回值是一个 task_struct 指针。
            p = copy_process(clone_flags, stack_start, stack_size,
                 child_tidptr, NULL, trace);
    
            if (!IS_ERR(p)) {
                struct completion vfork;
                struct pid *pid;
    
                trace_sched_process_fork(current, p);
    
                //得到新创建的进程描述符中的pid
                pid = get_task_pid(p, PIDTYPE_PID);
                nr = pid_vnr(pid);
    
                if (clone_flags & CLONE_PARENT_SETTID)
                    put_user(nr, parent_tidptr);
    
                //如果调用的 vfork()方法，初始化 vfork 完成处理信息。
                if (clone_flags & CLONE_VFORK) {
                    p->vfork_done = &vfork;
                    init_completion(&vfork);
                    get_task_struct(p);
                }
    
                //将子进程加入到调度器中，为其分配 CPU，准备执行
                wake_up_new_task(p);
    
                //fork 完成，子进程即将开始运行
                if (unlikely(trace))
                    ptrace_event_pid(trace, pid);
    
                //如果是 vfork，将父进程加入至等待队列，等待子进程完成
                if (clone_flags & CLONE_VFORK) {
                    if (!wait_for_vfork_done(p, &vfork))
                        ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid);
                }
    
                put_pid(pid);
            } else {
                nr = PTR_ERR(p);
            }
            return nr;
    }

do\_fork 流程

调用 copy\_process 为子进程复制出一份进程信息  
如果是 vfork 初始化完成处理信息  
调用 wake\_up\_new\_task 将子进程加入调度器，为之分配 CPU  
如果是 vfork，父进程等待子进程完成 exec 替换自己的地址空间

进入到copy\_process函数

static 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)
    {
        int retval;
        //创建进程描述符指针
        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 namespace
         * don't allow the creation of threads.
         */
        if ((clone_flags & (CLONE_VM|CLONE_NEWPID)) &&
            (task_active_pid_ns(current) != current->nsproxy->pid_ns))
            return ERR_PTR(-EINVAL);
    
        retval = security_task_create(clone_flags);
        if (retval)
            goto fork_out;
    
        retval = -ENOMEM;
        //复制当前的 task_struct
        p = dup_task_struct(current);
        if (!p)
            goto fork_out;
    
        ftrace_graph_init_task(p);
        get_seccomp_filter(p);
    
         //初始化互斥变量 
        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;
        //检查进程数是否超过限制，由操作系统定义
        if (atomic_read(&p->real_cred->user->processes) >=
                task_rlimit(p, RLIMIT_NPROC)) {
            if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
                p->real_cred->user != INIT_USER)
                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;
        //检查进程数是否超过 max_threads 由内存大小决定
        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() */
        copy_flags(clone_flags, p);
        INIT_LIST_HEAD(&p->children);
        INIT_LIST_HEAD(&p->sibling);
        rcu_copy_process(p);
        p->vfork_done = NULL;
        //初始化自旋锁
        spin_lock_init(&p->alloc_lock);
        //初始化挂起信号
        init_sigpending(&p->pending);
    
        p->utime = p->stime = p->gtime = 0;
        p->utimescaled = p->stimescaled = 0;
    #ifndef CONFIG_VIRT_CPU_ACCOUNTING
        p->prev_cputime.utime = p->prev_cputime.stime = 0;
    #endif
    #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
        seqlock_init(&p->vtime_seqlock);
        p->vtime_snap = 0;
        p->vtime_snap_whence = VTIME_SLEEPING;
    #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);
    
        //初始化CPU定时器
        posix_cpu_timers_init(p);
    
        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;
        if (clone_flags & CLONE_THREAD)
            threadgroup_change_begin(current);
        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_cgroup;
        }
        mpol_fix_fork_child_flag(p);
    #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
    #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_MEMCG
        p->memcg_batch.do_batch = 0;
        p->memcg_batch.memcg = NULL;
    #endif
    
        /* Perform scheduler related setup. Assign this task to a CPU. */
         //初始化进程数据结构，并把进程状态设置为 TASK_RUNNING
        sched_fork(p);
    
        retval = perf_event_init_task(p);
         //复制所有进程信息，包括文件系统、信号处理函数、信号、内存管理等
        if (retval)
            goto bad_fork_cleanup_policy;
        retval = audit_alloc(p);
        if (retval)
            goto bad_fork_cleanup_policy;
        /* copy all the process information */
        retval = copy_semundo(clone_flags, p);
        if (retval)
            goto bad_fork_cleanup_audit;
        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;
        //初始化子进程内核栈
        retval = copy_thread(clone_flags, stack_start, stack_size, p);
        if (retval)
            goto bad_fork_cleanup_io;
    
        if (pid != &init_struct_pid) {
            retval = -ENOMEM;
             //为新进程分配新的 pid
            pid = alloc_pid(p->nsproxy->pid_ns);
            if (!pid)
                goto bad_fork_cleanup_io;
        }
    
         //设置子进程 pid 
        p->pid = pid_nr(pid);
        p->tgid = p->pid;
        if (clone_flags & CLONE_THREAD)
            p->tgid = current->tgid;
    
        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_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
        uprobe_copy_process(p);
        /*
         * 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 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.. */
        if (clone_flags & CLONE_THREAD)
            p->exit_signal = -1;
        else if (clone_flags & CLONE_PARENT)
            p->exit_signal = current->group_leader->exit_signal;
        else
            p->exit_signal = (clone_flags & CSIGNAL);
    
        p->pdeath_signal = 0;
        p->exit_state = 0;
    
        p->nr_dirtied = 0;
        p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10);
        p->dirty_paused_when = 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);
        p->task_works = NULL;
    
        /* 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;
        }
    
        spin_lock(&current->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(&current->sighand->siglock);
            write_unlock_irq(&tasklist_lock);
            retval = -ERESTARTNOINTR;
            goto bad_fork_free_pid;
        }
    
        if (clone_flags & CLONE_THREAD) {
            current->signal->nr_threads++;
            atomic_inc(&current->signal->live);
            atomic_inc(&current->signal->sigcnt);
            p->group_leader = current->group_leader;
            list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
        }
    
        if (likely(p->pid)) {
            ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
    
            if (thread_group_leader(p)) {
                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);
                attach_pid(p, PIDTYPE_PGID, task_pgrp(current));
                attach_pid(p, PIDTYPE_SID, task_session(current));
                list_add_tail(&p->sibling, &p->real_parent->children);
                list_add_tail_rcu(&p->tasks, &init_task.tasks);
                __this_cpu_inc(process_counts);
            }
            attach_pid(p, PIDTYPE_PID, pid);
            nr_threads++;
        }
    
        total_forks++;
        spin_unlock(&current->sighand->siglock);
        write_unlock_irq(&tasklist_lock);
        proc_fork_connector(p);
        cgroup_post_fork(p);
        if (clone_flags & CLONE_THREAD)
            threadgroup_change_end(current);
        perf_event_fork(p);
    
        trace_task_newtask(p, clone_flags);
    
        return p;
    
    bad_fork_free_pid:
        if (pid != &init_struct_pid)
            free_pid(pid);
    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_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
        if (clone_flags & CLONE_THREAD)
            threadgroup_change_end(current);
        cgroup_exit(p, 0);
        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);
    }

## copy\_thread函数 ##

int copy_thread(unsigned long clone_flags, unsigned long sp,
        unsigned long arg, struct task_struct *p)
    {
        //获取寄存器信息
        struct pt_regs *childregs = task_pt_regs(p);
        struct task_struct *tsk;
        int err;
    
        p->thread.sp = (unsigned long) childregs;
        p->thread.sp0 = (unsigned long) (childregs+1);
        memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
    
        if (unlikely(p->flags & PF_KTHREAD)) {
            //内核线程
            memset(childregs, 0, sizeof(struct pt_regs));
            p->thread.ip = (unsigned long) ret_from_kernel_thread;
            task_user_gs(p) = __KERNEL_STACK_CANARY;
            childregs->ds = __USER_DS;
            childregs->es = __USER_DS;
            childregs->fs = __KERNEL_PERCPU;
            childregs->bx = sp; /* function */
            childregs->bp = arg;
            childregs->orig_ax = -1;
            childregs->cs = __KERNEL_CS | get_kernel_rpl();
            childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED;
            p->thread.io_bitmap_ptr = NULL;
            return 0;
        }
    
        //将当前寄存器信息复制给子进程
        *childregs = *current_pt_regs();
    
        //子进程 eax 置 0，因此fork 在子进程返回0
        childregs->ax = 0;
        if (sp)
            childregs->sp = sp;
    
        //子进程ip 设置为ret_from_fork，因此子进程从ret_from_fork开始执行
        p->thread.ip = (unsigned long) ret_from_fork;
    
        //……
    
        return err;
    }

## ret\_from\_fork ##

ENTRY(ret_from_fork)
        CFI_STARTPROC
        pushl_cfi %eax
        call schedule_tail
        GET_THREAD_INFO(%ebp)
        popl_cfi %eax
        pushl_cfi $0x0202       # Reset kernel eflags
        popfl_cfi
        jmp syscall_exit
        CFI_ENDPROC
    END(ret_from_fork)

## 总结 ##

dup\_task\_struct中为子进程分配了新的堆栈  
调用了sched\_fork，将其置为TASK\_RUNNING  
copy\_thread中将父进程的寄存器上下文复制给子进程，保证了父子进程的堆栈信息是一致的  
将ret\_from\_fork的地址设置为eip寄存器的值  
最终子进程从ret\_from\_fork开始执行

[http_mooc.study.163.com_course_USTC-1000029000]: http://mooc.study.163.com/course/USTC-1000029000
[20160403164725382]: /images/20220724/6cbf2819350c4797a8088eebdea82482.png
[https_github.com_mengning_menu.git]: https://github.com/mengning/menu.git