dev.c

linux下的用户文件系统fuse-2.5.2

			   unsigned long nr_segs)
{
	memset(cs, 0, sizeof(*cs));
	cs->write = write;
	cs->req = req;
	cs->iov = iov;
	cs->nr_segs = nr_segs;
}

/* Unmap and put previous page of userspace buffer */
static inline void fuse_copy_finish(struct fuse_copy_state *cs)
{
	if (cs->mapaddr) {
		kunmap_atomic(cs->mapaddr, KM_USER0);
		if (cs->write) {
			flush_dcache_page(cs->pg);
			set_page_dirty_lock(cs->pg);
		}
		put_page(cs->pg);
		cs->mapaddr = NULL;
	}
}

/*
 * Get another pagefull of userspace buffer, and map it to kernel
 * address space, and lock request
 */
static int fuse_copy_fill(struct fuse_copy_state *cs)
{
	unsigned long offset;
	int err;

	unlock_request(cs->req);
	fuse_copy_finish(cs);
	if (!cs->seglen) {
		BUG_ON(!cs->nr_segs);
		cs->seglen = cs->iov[0].iov_len;
		cs->addr = (unsigned long) cs->iov[0].iov_base;
		cs->iov ++;
		cs->nr_segs --;
	}
	down_read(&current->mm->mmap_sem);
	err = get_user_pages(current, current->mm, cs->addr, 1, cs->write, 0,
			     &cs->pg, NULL);
	up_read(&current->mm->mmap_sem);
	if (err < 0)
		return err;
	BUG_ON(err != 1);
	offset = cs->addr % PAGE_SIZE;
	cs->mapaddr = kmap_atomic(cs->pg, KM_USER0);
	cs->buf = cs->mapaddr + offset;
	cs->len = min(PAGE_SIZE - offset, cs->seglen);
	cs->seglen -= cs->len;
	cs->addr += cs->len;

	return lock_request(cs->req);
}

/* Do as much copy to/from userspace buffer as we can */
static inline int fuse_copy_do(struct fuse_copy_state *cs, void **val,
			       unsigned *size)
{
	unsigned ncpy = min(*size, cs->len);
	if (val) {
		if (cs->write)
			memcpy(cs->buf, *val, ncpy);
		else
			memcpy(*val, cs->buf, ncpy);
		*val += ncpy;
	}
	*size -= ncpy;
	cs->len -= ncpy;
	cs->buf += ncpy;
	return ncpy;
}

/*
 * Copy a page in the request to/from the userspace buffer.  Must be
 * done atomically
 */
static inline int fuse_copy_page(struct fuse_copy_state *cs, struct page *page,
				 unsigned offset, unsigned count, int zeroing)
{
	if (page && zeroing && count < PAGE_SIZE) {
		void *mapaddr = kmap_atomic(page, KM_USER1);
		memset(mapaddr, 0, PAGE_SIZE);
		kunmap_atomic(mapaddr, KM_USER1);
	}
	while (count) {
		int err;
		if (!cs->len && (err = fuse_copy_fill(cs)))
			return err;
		if (page) {
			void *mapaddr = kmap_atomic(page, KM_USER1);
			void *buf = mapaddr + offset;
			offset += fuse_copy_do(cs, &buf, &count);
			kunmap_atomic(mapaddr, KM_USER1);
		} else
			offset += fuse_copy_do(cs, NULL, &count);
	}
	if (page && !cs->write)
		flush_dcache_page(page);
	return 0;
}

/* Copy pages in the request to/from userspace buffer */
static int fuse_copy_pages(struct fuse_copy_state *cs, unsigned nbytes,
			   int zeroing)
{
	unsigned i;
	struct fuse_req *req = cs->req;
	unsigned offset = req->page_offset;
	unsigned count = min(nbytes, (unsigned) PAGE_SIZE - offset);

	for (i = 0; i < req->num_pages && (nbytes || zeroing); i++) {
		struct page *page = req->pages[i];
		int err = fuse_copy_page(cs, page, offset, count, zeroing);
		if (err)
			return err;

		nbytes -= count;
		count = min(nbytes, (unsigned) PAGE_SIZE);
		offset = 0;
	}
	return 0;
}

/* Copy a single argument in the request to/from userspace buffer */
static int fuse_copy_one(struct fuse_copy_state *cs, void *val, unsigned size)
{
	while (size) {
		int err;
		if (!cs->len && (err = fuse_copy_fill(cs)))
			return err;
		fuse_copy_do(cs, &val, &size);
	}
	return 0;
}

/* Copy request arguments to/from userspace buffer */
static int fuse_copy_args(struct fuse_copy_state *cs, unsigned numargs,
			  unsigned argpages, struct fuse_arg *args,
			  int zeroing)
{
	int err = 0;
	unsigned i;

	for (i = 0; !err && i < numargs; i++)  {
		struct fuse_arg *arg = &args[i];
		if (i == numargs - 1 && argpages)
			err = fuse_copy_pages(cs, arg->size, zeroing);
		else
			err = fuse_copy_one(cs, arg->value, arg->size);
	}
	return err;
}

/* Wait until a request is available on the pending list */
static void request_wait(struct fuse_conn *fc)
{
	DECLARE_WAITQUEUE(wait, current);

	add_wait_queue_exclusive(&fc->waitq, &wait);
	while (fc->mounted && list_empty(&fc->pending)) {
		set_current_state(TASK_INTERRUPTIBLE);
		if (signal_pending(current))
			break;

		spin_unlock(&fuse_lock);
		schedule();
		spin_lock(&fuse_lock);
	}
	set_current_state(TASK_RUNNING);
	remove_wait_queue(&fc->waitq, &wait);
}

#ifndef KERNEL_2_6
static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs)
{
	unsigned long seg;
	size_t ret = 0;

	for (seg = 0; seg < nr_segs; seg++)
		ret += iov[seg].iov_len;
	return ret;
}
#endif
/*
 * Read a single request into the userspace filesystem's buffer.  This
 * function waits until a request is available, then removes it from
 * the pending list and copies request data to userspace buffer.  If
 * no reply is needed (FORGET) or request has been interrupted or
 * there was an error during the copying then it's finished by calling
 * request_end().  Otherwise add it to the processing list, and set
 * the 'sent' flag.
 */
static ssize_t fuse_dev_readv(struct file *file, const struct iovec *iov,
			      unsigned long nr_segs, loff_t *off)
{
	int err;
	struct fuse_conn *fc;
	struct fuse_req *req;
	struct fuse_in *in;
	struct fuse_copy_state cs;
	unsigned reqsize;

 restart:
	spin_lock(&fuse_lock);
	fc = file->private_data;
	err = -EPERM;
	if (!fc)
		goto err_unlock;
	request_wait(fc);
	err = -ENODEV;
	if (!fc->mounted)
		goto err_unlock;
	err = -ERESTARTSYS;
	if (list_empty(&fc->pending))
		goto err_unlock;

	req = list_entry(fc->pending.next, struct fuse_req, list);
	list_del_init(&req->list);

	in = &req->in;
	reqsize = in->h.len;
	/* If request is too large, reply with an error and restart the read */
	if (iov_length(iov, nr_segs) < reqsize) {
		req->out.h.error = -EIO;
		/* SETXATTR is special, since it may contain too large data */
		if (in->h.opcode == FUSE_SETXATTR)
			req->out.h.error = -E2BIG;
		request_end(fc, req);
		goto restart;
	}
	spin_unlock(&fuse_lock);
	fuse_copy_init(&cs, 1, req, iov, nr_segs);
	err = fuse_copy_one(&cs, &in->h, sizeof(in->h));
	if (!err)
		err = fuse_copy_args(&cs, in->numargs, in->argpages,
				     (struct fuse_arg *) in->args, 0);
	fuse_copy_finish(&cs);
	spin_lock(&fuse_lock);
	req->locked = 0;
	if (!err && req->interrupted)
		err = -ENOENT;
	if (err) {
		if (!req->interrupted)
			req->out.h.error = -EIO;
		request_end(fc, req);
		return err;
	}
	if (!req->isreply)
		request_end(fc, req);
	else {
		req->sent = 1;
		list_add_tail(&req->list, &fc->processing);
		spin_unlock(&fuse_lock);
	}
	return reqsize;

 err_unlock:
	spin_unlock(&fuse_lock);
	return err;
}

static ssize_t fuse_dev_read(struct file *file, char __user *buf,
			     size_t nbytes, loff_t *off)
{
	struct iovec iov;
	iov.iov_len = nbytes;
	iov.iov_base = buf;
	return fuse_dev_readv(file, &iov, 1, off);
}

/* Look up request on processing list by unique ID */
static struct fuse_req *request_find(struct fuse_conn *fc, u64 unique)
{
	struct list_head *entry;

	list_for_each(entry, &fc->processing) {
		struct fuse_req *req;
		req = list_entry(entry, struct fuse_req, list);
		if (req->in.h.unique == unique)
			return req;
	}
	return NULL;
}

static int copy_out_args(struct fuse_copy_state *cs, struct fuse_out *out,
			 unsigned nbytes)
{
	unsigned reqsize = sizeof(struct fuse_out_header);

	if (out->h.error)
		return nbytes != reqsize ? -EINVAL : 0;

	reqsize += len_args(out->numargs, out->args);

	if (reqsize < nbytes || (reqsize > nbytes && !out->argvar))
		return -EINVAL;
	else if (reqsize > nbytes) {
		struct fuse_arg *lastarg = &out->args[out->numargs-1];
		unsigned diffsize = reqsize - nbytes;
		if (diffsize > lastarg->size)
			return -EINVAL;
		lastarg->size -= diffsize;
	}
	return fuse_copy_args(cs, out->numargs, out->argpages, out->args,
			      out->page_zeroing);
}

/*
 * Write a single reply to a request.  First the header is copied from
 * the write buffer.  The request is then searched on the processing
 * list by the unique ID found in the header.  If found, then remove
 * it from the list and copy the rest of the buffer to the request.
 * The request is finished by calling request_end()
 */
static ssize_t fuse_dev_writev(struct file *file, const struct iovec *iov,
			       unsigned long nr_segs, loff_t *off)
{
	int err;
	unsigned nbytes = iov_length(iov, nr_segs);
	struct fuse_req *req;
	struct fuse_out_header oh;
	struct fuse_copy_state cs;
	struct fuse_conn *fc = fuse_get_conn(file);
	if (!fc)
		return -ENODEV;

	fuse_copy_init(&cs, 0, NULL, iov, nr_segs);
	if (nbytes < sizeof(struct fuse_out_header))
		return -EINVAL;

	err = fuse_copy_one(&cs, &oh, sizeof(oh));
	if (err)
		goto err_finish;
	err = -EINVAL;
	if (!oh.unique || oh.error <= -1000 || oh.error > 0 ||
	    oh.len != nbytes)
		goto err_finish;

	spin_lock(&fuse_lock);
	req = request_find(fc, oh.unique);
	err = -EINVAL;
	if (!req)
		goto err_unlock;

	list_del_init(&req->list);
	if (req->interrupted) {
		spin_unlock(&fuse_lock);
		fuse_copy_finish(&cs);
		spin_lock(&fuse_lock);
		request_end(fc, req);
		return -ENOENT;
	}
	req->out.h = oh;
	req->locked = 1;
	cs.req = req;
	spin_unlock(&fuse_lock);

	err = copy_out_args(&cs, &req->out, nbytes);
	fuse_copy_finish(&cs);

	spin_lock(&fuse_lock);
	req->locked = 0;
	if (!err) {
		if (req->interrupted)
			err = -ENOENT;
	} else if (!req->interrupted)
		req->out.h.error = -EIO;
	request_end(fc, req);

	return err ? err : nbytes;

 err_unlock:
	spin_unlock(&fuse_lock);
 err_finish:
	fuse_copy_finish(&cs);
	return err;
}

static ssize_t fuse_dev_write(struct file *file, const char __user *buf,
			      size_t nbytes, loff_t *off)
{
	struct iovec iov;
	iov.iov_len = nbytes;
	iov.iov_base = (char __user *) buf;
	return fuse_dev_writev(file, &iov, 1, off);
}

static unsigned fuse_dev_poll(struct file *file, poll_table *wait)
{
	struct fuse_conn *fc = fuse_get_conn(file);
	unsigned mask = POLLOUT | POLLWRNORM;

	if (!fc)
		return -ENODEV;

	poll_wait(file, &fc->waitq, wait);

	spin_lock(&fuse_lock);
	if (!list_empty(&fc->pending))
                mask |= POLLIN | POLLRDNORM;
	spin_unlock(&fuse_lock);

	return mask;
}

/* Abort all requests on the given list (pending or processing) */
static void end_requests(struct fuse_conn *fc, struct list_head *head)
{
	while (!list_empty(head)) {
		struct fuse_req *req;
		req = list_entry(head->next, struct fuse_req, list);
		list_del_init(&req->list);
		req->out.h.error = -ECONNABORTED;
		request_end(fc, req);
		spin_lock(&fuse_lock);
	}
}

static int fuse_dev_release(struct inode *inode, struct file *file)
{
	struct fuse_conn *fc;

	spin_lock(&fuse_lock);
	fc = file->private_data;
	if (fc) {
		fc->connected = 0;
		end_requests(fc, &fc->pending);
		end_requests(fc, &fc->processing);
		fuse_release_conn(fc);
	}
	spin_unlock(&fuse_lock);
	return 0;
}

struct file_operations fuse_dev_operations = {
	.owner		= THIS_MODULE,
	.llseek		= no_llseek,
	.read		= fuse_dev_read,
	.readv		= fuse_dev_readv,
	.write		= fuse_dev_write,
	.writev		= fuse_dev_writev,
	.poll		= fuse_dev_poll,
	.release	= fuse_dev_release,
};

static struct miscdevice fuse_miscdevice = {
	.minor = FUSE_MINOR,
	.name  = "fuse",
	.fops = &fuse_dev_operations,
};

int __init fuse_dev_init(void)
{
	int err = -ENOMEM;
	fuse_req_cachep = kmem_cache_create("fuse_request",
					    sizeof(struct fuse_req),
					    0, 0, NULL, NULL);
	if (!fuse_req_cachep)
		goto out;

	err = misc_register(&fuse_miscdevice);
	if (err)
		goto out_cache_clean;

	return 0;

 out_cache_clean:
	kmem_cache_destroy(fuse_req_cachep);
 out:
	return err;
}

void fuse_dev_cleanup(void)
{
	misc_deregister(&fuse_miscdevice);
	kmem_cache_destroy(fuse_req_cachep);
}