fork.c

实现创建进程的fork函数的源代码

 * 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.
 */
struct task_struct *copy_process(unsigned long clone_flags,
				 unsigned long stack_start,
				 struct pt_regs *regs,
				 unsigned long stack_size,
				 int __user *parent_tidptr,
				 int __user *child_tidptr)
{
	int retval;
	struct task_struct *p = NULL;

	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);

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

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

	retval = -EAGAIN;
	if (atomic_read(&p->user->processes) >=
			p->rlim[RLIMIT_NPROC].rlim_cur) {
		if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
				p->user != &root_user)
			goto bad_fork_free;
	}

	atomic_inc(&p->user->__count);
	atomic_inc(&p->user->processes);
	get_group_info(p->group_info);

	/*
	 * 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.
	 */
	if (nr_threads >= max_threads)
		goto bad_fork_cleanup_count;

	if (!try_module_get(p->thread_info->exec_domain->module))
		goto bad_fork_cleanup_count;

	if (p->binfmt && !try_module_get(p->binfmt->module))
		goto bad_fork_cleanup_put_domain;

	p->did_exec = 0;
	copy_flags(clone_flags, p);
	if (clone_flags & CLONE_IDLETASK)
		p->pid = 0;
	else {
		p->pid = alloc_pidmap();
		if (p->pid == -1)
			goto bad_fork_cleanup;
	}
	retval = -EFAULT;
	if (clone_flags & CLONE_PARENT_SETTID)
		if (put_user(p->pid, parent_tidptr))
			goto bad_fork_cleanup;

	p->proc_dentry = NULL;

	INIT_LIST_HEAD(&p->children);
	INIT_LIST_HEAD(&p->sibling);
	init_waitqueue_head(&p->wait_chldexit);
	p->vfork_done = NULL;
	spin_lock_init(&p->alloc_lock);
	spin_lock_init(&p->proc_lock);

	clear_tsk_thread_flag(p, TIF_SIGPENDING);
	init_sigpending(&p->pending);

	p->it_real_value = p->it_virt_value = p->it_prof_value = 0;
	p->it_real_incr = p->it_virt_incr = p->it_prof_incr = 0;
	init_timer(&p->real_timer);
	p->real_timer.data = (unsigned long) p;

	p->utime = p->stime = 0;
	p->cutime = p->cstime = 0;
	p->lock_depth = -1;		/* -1 = no lock */
	p->start_time = get_jiffies_64();
	p->security = NULL;
	p->io_context = NULL;
	p->audit_context = NULL;
#ifdef CONFIG_NUMA
 	p->mempolicy = mpol_copy(p->mempolicy);
 	if (IS_ERR(p->mempolicy)) {
 		retval = PTR_ERR(p->mempolicy);
 		p->mempolicy = NULL;
 		goto bad_fork_cleanup;
 	}
#endif

	if ((retval = security_task_alloc(p)))
		goto bad_fork_cleanup_policy;
	if ((retval = audit_alloc(p)))
		goto bad_fork_cleanup_security;
	/* 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_namespace(clone_flags, p)))
		goto bad_fork_cleanup_mm;
	retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
	if (retval)
		goto bad_fork_cleanup_namespace;

	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;

	/*
	 * Syscall tracing should be turned off in the child regardless
	 * of CLONE_PTRACE.
	 */
	clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);

	/* Our parent execution domain becomes current domain
	   These must match for thread signalling to apply */
	   
	p->parent_exec_id = p->self_exec_id;

	/* ok, now we should be set up.. */
	p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL);
	p->pdeath_signal = 0;

	/* Perform scheduler related setup */
	sched_fork(p);

	/*
	 * Ok, make it visible to the rest of the system.
	 * We dont wake it up yet.
	 */
	p->tgid = p->pid;
	p->group_leader = p;
	INIT_LIST_HEAD(&p->ptrace_children);
	INIT_LIST_HEAD(&p->ptrace_list);

	/* Need tasklist lock for parent etc handling! */
	write_lock_irq(&tasklist_lock);
	/*
	 * Check for pending SIGKILL! The new thread should not be allowed
	 * to slip out of an OOM kill. (or normal SIGKILL.)
	 */
	if (sigismember(&current->pending.signal, SIGKILL)) {
		write_unlock_irq(&tasklist_lock);
		retval = -EINTR;
		goto bad_fork_cleanup_namespace;
	}

	/* CLONE_PARENT re-uses the old parent */
	if (clone_flags & CLONE_PARENT)
		p->real_parent = current->real_parent;
	else
		p->real_parent = current;
	p->parent = p->real_parent;

	if (clone_flags & CLONE_THREAD) {
		spin_lock(&current->sighand->siglock);
		/*
		 * Important: if an exit-all has been started then
		 * do not create this new thread - the whole thread
		 * group is supposed to exit anyway.
		 */
		if (current->signal->group_exit) {
			spin_unlock(&current->sighand->siglock);
			write_unlock_irq(&tasklist_lock);
			retval = -EAGAIN;
			goto bad_fork_cleanup_namespace;
		}
		p->tgid = current->tgid;
		p->group_leader = current->group_leader;

		if (current->signal->group_stop_count > 0) {
			/*
			 * There is an all-stop in progress for the group.
			 * We ourselves will stop as soon as we check signals.
			 * Make the new thread part of that group stop too.
			 */
			current->signal->group_stop_count++;
			set_tsk_thread_flag(p, TIF_SIGPENDING);
		}

		spin_unlock(&current->sighand->siglock);
	}

	SET_LINKS(p);
	if (p->ptrace & PT_PTRACED)
		__ptrace_link(p, current->parent);

	attach_pid(p, PIDTYPE_PID, p->pid);
	if (thread_group_leader(p)) {
		attach_pid(p, PIDTYPE_TGID, p->tgid);
		attach_pid(p, PIDTYPE_PGID, process_group(p));
		attach_pid(p, PIDTYPE_SID, p->signal->session);
		if (p->pid)
			__get_cpu_var(process_counts)++;
	} else
		link_pid(p, p->pids + PIDTYPE_TGID, &p->group_leader->pids[PIDTYPE_TGID].pid);

	nr_threads++;
	write_unlock_irq(&tasklist_lock);
	retval = 0;

fork_out:
	if (retval)
		return ERR_PTR(retval);
	return p;

bad_fork_cleanup_namespace:
	exit_namespace(p);
bad_fork_cleanup_mm:
	exit_mm(p);
	if (p->active_mm)
		mmdrop(p->active_mm);
bad_fork_cleanup_signal:
	exit_signal(p);
bad_fork_cleanup_sighand:
	exit_sighand(p);
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_security:
	security_task_free(p);
bad_fork_cleanup_policy:
#ifdef CONFIG_NUMA
	mpol_free(p->mempolicy);
#endif
bad_fork_cleanup:
	if (p->pid > 0)
		free_pidmap(p->pid);
	if (p->binfmt)
		module_put(p->binfmt->module);
bad_fork_cleanup_put_domain:
	module_put(p->thread_info->exec_domain->module);
bad_fork_cleanup_count:
	put_group_info(p->group_info);
	atomic_dec(&p->user->processes);
	free_uid(p->user);
bad_fork_free:
	free_task(p);
	goto fork_out;
}

static inline int fork_traceflag (unsigned clone_flags)
{
	if (clone_flags & (CLONE_UNTRACED | CLONE_IDLETASK))
		return 0;
	else if (clone_flags & CLONE_VFORK) {
		if (current->ptrace & PT_TRACE_VFORK)
			return PTRACE_EVENT_VFORK;
	} else if ((clone_flags & CSIGNAL) != SIGCHLD) {
		if (current->ptrace & PT_TRACE_CLONE)
			return PTRACE_EVENT_CLONE;
	} else if (current->ptrace & PT_TRACE_FORK)
		return PTRACE_EVENT_FORK;

	return 0;
}

/*
 *  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.
 */
long do_fork(unsigned long clone_flags,
	      unsigned long stack_start,
	      struct pt_regs *regs,
	      unsigned long stack_size,
	      int __user *parent_tidptr,
	      int __user *child_tidptr)
{
	struct task_struct *p;
	int trace = 0;
	long pid;

	if (unlikely(current->ptrace)) {
		trace = fork_traceflag (clone_flags);
		if (trace)
			clone_flags |= CLONE_PTRACE;
	}

	p = copy_process(clone_flags, stack_start, regs, stack_size, parent_tidptr, child_tidptr);
	/*
	 * Do this prior waking up the new thread - the thread pointer
	 * might get invalid after that point, if the thread exits quickly.
	 */
	pid = IS_ERR(p) ? PTR_ERR(p) : p->pid;

	if (!IS_ERR(p)) {
		struct completion vfork;

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

		if ((p->ptrace & PT_PTRACED) || (clone_flags & CLONE_STOPPED)) {
			/*
			 * We'll start up with an immediate SIGSTOP.
			 */
			sigaddset(&p->pending.signal, SIGSTOP);
			set_tsk_thread_flag(p, TIF_SIGPENDING);
		}

		if (!(clone_flags & CLONE_STOPPED)) {
			/*
			 * Do the wakeup last. On SMP we treat fork() and
			 * CLONE_VM separately, because fork() has already
			 * created cache footprint on this CPU (due to
			 * copying the pagetables), hence migration would
			 * probably be costy. Threads on the other hand
			 * have less traction to the current CPU, and if
			 * there's an imbalance then the scheduler can
			 * migrate this fresh thread now, before it
			 * accumulates a larger cache footprint:
			 */
			if (clone_flags & CLONE_VM)
				wake_up_forked_thread(p);
			else
				wake_up_forked_process(p);
		} else {
			int cpu = get_cpu();

			p->state = TASK_STOPPED;
			if (cpu_is_offline(task_cpu(p)))
				set_task_cpu(p, cpu);

			put_cpu();
		}
		++total_forks;

		if (unlikely (trace)) {
			current->ptrace_message = pid;
			ptrace_notify ((trace << 8) | SIGTRAP);
		}

		if (clone_flags & CLONE_VFORK) {
			wait_for_completion(&vfork);
			if (unlikely (current->ptrace & PT_TRACE_VFORK_DONE))
				ptrace_notify ((PTRACE_EVENT_VFORK_DONE << 8) | SIGTRAP);
		} else
			/*
			 * Let the child process run first, to avoid most of the
			 * COW overhead when the child exec()s afterwards.
			 */
			set_need_resched();
	}
	return pid;
}

/* SLAB cache for signal_struct structures (tsk->signal) */
kmem_cache_t *signal_cachep;

/* SLAB cache for sighand_struct structures (tsk->sighand) */
kmem_cache_t *sighand_cachep;

/* SLAB cache for files_struct structures (tsk->files) */
kmem_cache_t *files_cachep;

/* SLAB cache for fs_struct structures (tsk->fs) */
kmem_cache_t *fs_cachep;

/* SLAB cache for vm_area_struct structures */
kmem_cache_t *vm_area_cachep;

/* SLAB cache for mm_struct structures (tsk->mm) */
kmem_cache_t *mm_cachep;

void __init proc_caches_init(void)
{
	sighand_cachep = kmem_cache_create("sighand_cache",
			sizeof(struct sighand_struct), 0,
			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
	signal_cachep = kmem_cache_create("signal_cache",
			sizeof(struct signal_struct), 0,
			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
	files_cachep = kmem_cache_create("files_cache", 
			sizeof(struct files_struct), 0,
			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
	fs_cachep = kmem_cache_create("fs_cache", 
			sizeof(struct fs_struct), 0,
			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
	vm_area_cachep = kmem_cache_create("vm_area_struct",
			sizeof(struct vm_area_struct), 0,
			SLAB_PANIC, NULL, NULL);
	mm_cachep = kmem_cache_create("mm_struct",
			sizeof(struct mm_struct), 0,
			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
}