fork.c

中科院徐志伟老师一书《操作系统 原理·技术与编程》的源代码和习题接

static int count_open_files(struct files_struct *files, int size)
{
	int i;
	
	/* Find the last open fd */
	for (i = size/(8*sizeof(long)); i > 0; ) {
		if (files->open_fds->fds_bits[--i])
			break;
	}
	i = (i+1) * 8 * sizeof(long);
	return i;
}

static int copy_files(unsigned long clone_flags, struct task_struct * tsk)
{
	struct files_struct *oldf, *newf;
	struct file **old_fds, **new_fds;
	int open_files, nfds, size, i, error = 0;

	/*
	 * A background process may not have any files ...
	 */
	oldf = current->files;
	if (!oldf)
		goto out;

	if (clone_flags & CLONE_FILES) {
		atomic_inc(&oldf->count);
		goto out;
	}

	tsk->files = NULL;
	error = -ENOMEM;
	newf = kmem_cache_alloc(files_cachep, SLAB_KERNEL);
	if (!newf) 
		goto out;

	atomic_set(&newf->count, 1);

	newf->file_lock	    = RW_LOCK_UNLOCKED;
	newf->next_fd	    = 0;
	newf->max_fds	    = NR_OPEN_DEFAULT;
	newf->max_fdset	    = __FD_SETSIZE;
	newf->close_on_exec = &newf->close_on_exec_init;
	newf->open_fds	    = &newf->open_fds_init;
	newf->fd	    = &newf->fd_array[0];

	/* We don't yet have the oldf readlock, but even if the old
           fdset gets grown now, we'll only copy up to "size" fds */
	size = oldf->max_fdset;
	if (size > __FD_SETSIZE) {
		newf->max_fdset = 0;
		write_lock(&newf->file_lock);
		error = expand_fdset(newf, size-1);
		write_unlock(&newf->file_lock);
		if (error)
			goto out_release;
	}
	read_lock(&oldf->file_lock);

	open_files = count_open_files(oldf, size);

	/*
	 * Check whether we need to allocate a larger fd array.
	 * Note: we're not a clone task, so the open count won't
	 * change.
	 */
	nfds = NR_OPEN_DEFAULT;
	if (open_files > nfds) {
		read_unlock(&oldf->file_lock);
		newf->max_fds = 0;
		write_lock(&newf->file_lock);
		error = expand_fd_array(newf, open_files-1);
		write_unlock(&newf->file_lock);
		if (error) 
			goto out_release;
		nfds = newf->max_fds;
		read_lock(&oldf->file_lock);
	}

	old_fds = oldf->fd;
	new_fds = newf->fd;

	memcpy(newf->open_fds->fds_bits, oldf->open_fds->fds_bits, open_files/8);
	memcpy(newf->close_on_exec->fds_bits, oldf->close_on_exec->fds_bits, open_files/8);

	for (i = open_files; i != 0; i--) {
		struct file *f = *old_fds++;
		if (f)
			get_file(f);
		*new_fds++ = f;
	}
	read_unlock(&oldf->file_lock);

	/* compute the remainder to be cleared */
	size = (newf->max_fds - open_files) * sizeof(struct file *);

	/* This is long word aligned thus could use a optimized version */ 
	memset(new_fds, 0, size); 

	if (newf->max_fdset > open_files) {
		int left = (newf->max_fdset-open_files)/8;
		int start = open_files / (8 * sizeof(unsigned long));
		
		memset(&newf->open_fds->fds_bits[start], 0, left);
		memset(&newf->close_on_exec->fds_bits[start], 0, left);
	}

	tsk->files = newf;
	error = 0;
out:
	return error;

out_release:
	free_fdset (newf->close_on_exec, newf->max_fdset);
	free_fdset (newf->open_fds, newf->max_fdset);
	kmem_cache_free(files_cachep, newf);
	goto out;
}

static inline int copy_sighand(unsigned long clone_flags, struct task_struct * tsk)
{
	struct signal_struct *sig;

	if (clone_flags & CLONE_SIGHAND) {
		atomic_inc(&current->sig->count);
		return 0;
	}
	sig = kmem_cache_alloc(sigact_cachep, GFP_KERNEL);
	tsk->sig = sig;
	if (!sig)
		return -1;
	spin_lock_init(&sig->siglock);
	atomic_set(&sig->count, 1);
	memcpy(tsk->sig->action, current->sig->action, sizeof(tsk->sig->action));
	return 0;
}

static inline void copy_flags(unsigned long clone_flags, struct task_struct *p)
{
	unsigned long new_flags = p->flags;

	new_flags &= ~(PF_SUPERPRIV | PF_USEDFPU);
	new_flags |= PF_FORKNOEXEC;
	if (!(clone_flags & CLONE_PTRACE))
		p->ptrace = 0;
	p->flags = new_flags;
}

/*
 *  Ok, this is the main fork-routine. It copies the system process
 * information (task[nr]) and sets up the necessary registers. It also
 * copies the data segment in its entirety.  The "stack_start" and
 * "stack_top" arguments are simply passed along to the platform
 * specific copy_thread() routine.  Most platforms ignore stack_top.
 * For an example that's using stack_top, see
 * arch/ia64/kernel/process.c.
 */
int do_fork(unsigned long clone_flags, unsigned long stack_start,
	    struct pt_regs *regs, unsigned long stack_size)
{
	int retval;
	struct task_struct *p;
	struct completion vfork;

	retval = -EPERM;

	/* 
	 * CLONE_PID is only allowed for the initial SMP swapper
	 * calls
	 */
	if (clone_flags & CLONE_PID) {
		if (current->pid)
			goto fork_out;
	}

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

	*p = *current;

	retval = -EAGAIN;
	/*
	 * Check if we are over our maximum process limit, but be sure to
	 * exclude root. This is needed to make it possible for login and
	 * friends to set the per-user process limit to something lower
	 * than the amount of processes root is running. -- Rik
	 */
	if (atomic_read(&p->user->processes) >= p->rlim[RLIMIT_NPROC].rlim_cur
	              && !capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE))
		goto bad_fork_free;

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

	/*
	 * Counter increases are protected by
	 * the kernel lock so nr_threads can't
	 * increase under us (but it may decrease).
	 */
	if (nr_threads >= max_threads)
		goto bad_fork_cleanup_count;
	
	get_exec_domain(p->exec_domain);

	if (p->binfmt && p->binfmt->module)
		__MOD_INC_USE_COUNT(p->binfmt->module);

	p->did_exec = 0;
	p->swappable = 0;
	p->state = TASK_UNINTERRUPTIBLE;

	copy_flags(clone_flags, p);
	p->pid = get_pid(clone_flags);

	p->run_list.next = NULL;
	p->run_list.prev = NULL;

	p->p_cptr = NULL;
	init_waitqueue_head(&p->wait_chldexit);
	p->vfork_done = NULL;
	if (clone_flags & CLONE_VFORK) {
		p->vfork_done = &vfork;
		init_completion(&vfork);
	}
	spin_lock_init(&p->alloc_lock);

	p->sigpending = 0;
	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->leader = 0;		/* session leadership doesn't inherit */
	p->tty_old_pgrp = 0;
	p->times.tms_utime = p->times.tms_stime = 0;
	p->times.tms_cutime = p->times.tms_cstime = 0;
#ifdef CONFIG_SMP
	{
		int i;
		p->cpus_runnable = ~0UL;
		p->processor = current->processor;
		/* ?? should we just memset this ?? */
		for(i = 0; i < smp_num_cpus; i++)
			p->per_cpu_utime[i] = p->per_cpu_stime[i] = 0;
		spin_lock_init(&p->sigmask_lock);
	}
#endif
	p->lock_depth = -1;		/* -1 = no lock */
	p->start_time = jiffies;

	INIT_LIST_HEAD(&p->local_pages);

	retval = -ENOMEM;
	/* copy all the process information */
	if (copy_files(clone_flags, p))
		goto bad_fork_cleanup;
	if (copy_fs(clone_flags, p))
		goto bad_fork_cleanup_files;
	if (copy_sighand(clone_flags, p))
		goto bad_fork_cleanup_fs;
	if (copy_mm(clone_flags, p))
		goto bad_fork_cleanup_sighand;
	retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
	if (retval)
		goto bad_fork_cleanup_mm;
	p->semundo = NULL;
	
	/* 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->swappable = 1;
	p->exit_signal = clone_flags & CSIGNAL;
	p->pdeath_signal = 0;

	/*
	 * "share" dynamic priority between parent and child, thus the
	 * total amount of dynamic priorities in the system doesnt change,
	 * more scheduling fairness. This is only important in the first
	 * timeslice, on the long run the scheduling behaviour is unchanged.
	 */
	p->counter = (current->counter + 1) >> 1;
	current->counter >>= 1;
	if (!current->counter)
		current->need_resched = 1;

	p->fb=1;
	/*
	 * Ok, add it to the run-queues and make it
	 * visible to the rest of the system.
	 *
	 * Let it rip!
	 */
	retval = p->pid;
	p->tgid = retval;
	INIT_LIST_HEAD(&p->thread_group);

	/* Need tasklist lock for parent etc handling! */
	write_lock_irq(&tasklist_lock);

	/* CLONE_PARENT and CLONE_THREAD re-use the old parent */
	p->p_opptr = current->p_opptr;
	p->p_pptr = current->p_pptr;
	if (!(clone_flags & (CLONE_PARENT | CLONE_THREAD))) {
		p->p_opptr = current;
		if (!(p->ptrace & PT_PTRACED))
			p->p_pptr = current;
	}

	if (clone_flags & CLONE_THREAD) {
		p->tgid = current->tgid;
		list_add(&p->thread_group, &current->thread_group);
	}

	SET_LINKS(p);
	hash_pid(p);
	nr_threads++;
	write_unlock_irq(&tasklist_lock);

	if (p->ptrace & PT_PTRACED)
		send_sig(SIGSTOP, p, 1);

	wake_up_process(p);		/* do this last */
	++total_forks;
	if (clone_flags & CLONE_VFORK)
		wait_for_completion(&vfork);

fork_out:
	return retval;

bad_fork_cleanup_mm:
	exit_mm(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:
	put_exec_domain(p->exec_domain);
	if (p->binfmt && p->binfmt->module)
		__MOD_DEC_USE_COUNT(p->binfmt->module);
bad_fork_cleanup_count:
	atomic_dec(&p->user->processes);
	free_uid(p->user);
bad_fork_free:
	free_task_struct(p);
	goto fork_out;
}

/* SLAB cache for signal_struct structures (tsk->sig) */
kmem_cache_t *sigact_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)
{
	sigact_cachep = kmem_cache_create("signal_act",
			sizeof(struct signal_struct), 0,
			SLAB_HWCACHE_ALIGN, NULL, NULL);
	if (!sigact_cachep)
		panic("Cannot create signal action SLAB cache");

	files_cachep = kmem_cache_create("files_cache", 
			 sizeof(struct files_struct), 0, 
			 SLAB_HWCACHE_ALIGN, NULL, NULL);
	if (!files_cachep) 
		panic("Cannot create files SLAB cache");

	fs_cachep = kmem_cache_create("fs_cache", 
			 sizeof(struct fs_struct), 0, 
			 SLAB_HWCACHE_ALIGN, NULL, NULL);
	if (!fs_cachep) 
		panic("Cannot create fs_struct SLAB cache");
 
	vm_area_cachep = kmem_cache_create("vm_area_struct",
			sizeof(struct vm_area_struct), 0,
			SLAB_HWCACHE_ALIGN, NULL, NULL);
	if(!vm_area_cachep)
		panic("vma_init: Cannot alloc vm_area_struct SLAB cache");

	mm_cachep = kmem_cache_create("mm_struct",
			sizeof(struct mm_struct), 0,
			SLAB_HWCACHE_ALIGN, NULL, NULL);
	if(!mm_cachep)
		panic("vma_init: Cannot alloc mm_struct SLAB cache");
}