结合中断上下文切换和进程上下文切换分析Linux内核的一般执行过程

long do_fork(unsigned long clone_flags,
    unsigned long stack_start,
    unsigned long stack_size,
    int __user *parent_tidptr,
    int __user *child_tidptr)
{
    struct task_struct *p;
    int trace = 0;
    long nr;

    /*
    * 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 ((clone_flags & CSIGNAL) != SIGCHLD)
            trace = PTRACE_EVENT_CLONE;
        else
            trace = PTRACE_EVENT_FORK;
    
        if (likely(!ptrace_event_enabled(current, trace)))
            trace = 0;
    }
    
    p = copy_process(clone_flags, stack_start, stack_size,
        child_tidptr, NULL, trace);
    /*
    * Do this prior waking up the new thread - the thread pointer
    * might get invalid after that point, if the thread exits quickly.
    */
    if (!IS_ERR(p)) {
        struct completion vfork;
        struct pid *pid;
    
        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, parent_tidptr);
    
        if (clone_flags & CLONE_VFORK) {
            p->vfork_done = &vfork;
            init_completion(&vfork);
            get_task_struct(p);
        }
    
        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);
    } else {
        nr = PTR_ERR(p);
    }
    return nr;

}

static __latent_entropy struct task_struct *copy_process(
                    struct pid *pid,
                    int trace,
                    int node,
                    struct kernel_clone_args *args)
{
    ...
    p = dup_task_struct(current, node);
    ...
    /* 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, args->stack, args->stack_size, p,
                 args->tls);  
    if (retval)
        goto bad_fork_cleanup_io;
    ...
    return p;
    ...

SYSCALL_DEFINE3(execve,
        const char __user *, filename,
        const char __user *const __user *, argv,
        const char __user *const __user *, envp)
{
    return do_execve(getname(filename), argv, envp);
}

/*
 * sys_execve() executes a new program.
 */
static int __do_execve_file(int fd, struct filename *filename,
                struct user_arg_ptr argv,
                struct user_arg_ptr envp,
                int flags, struct file *file)
{
    char *pathbuf = NULL;
    struct linux_binprm *bprm;
    struct files_struct *displaced;
    int retval;
    // ...
    bprm->file = file;
    // ...
    retval = prepare_binprm(bprm);
    // ...
    retval = copy_strings(bprm->envc, envp, bprm);
    // ...
    retval = exec_binprm(bprm);
    // ...
    return retval;
}

static int exec_binprm(struct linux_binprm *bprm)
{
    pid_t old_pid, old_vpid;
    int ret;
?
    /* Need to fetch pid before load_binary changes it */
    old_pid = current->pid;
    rcu_read_lock();
    old_vpid = task_pid_nr_ns(current, task_active_pid_ns(current->parent));
    rcu_read_unlock();
?
    ret = search_binary_handler(bprm);
    if (ret >= 0) {
        audit_bprm(bprm);
        trace_sched_process_exec(current, old_pid, bprm);
        ptrace_event(PTRACE_EVENT_EXEC, old_vpid);
        proc_exec_connector(current);
    }
?
    return ret;
}