file.c

FUSE文件系统开发工具,将内核层面的文件系统开发过程平移到应用层面上来。

	inarg.offset = pos;
	inarg.size = count;
	req->in.h.opcode = FUSE_WRITE;
	req->in.h.nodeid = get_node_id(inode);
	req->in.argpages = 1;
	req->in.numargs = 2;
	req->in.args[0].size = sizeof(struct fuse_write_in);
	req->in.args[0].value = &inarg;
	req->in.args[1].size = count;
	req->out.numargs = 1;
	req->out.args[0].size = sizeof(struct fuse_write_out);
	req->out.args[0].value = &outarg;
	request_send(fc, req);
	return outarg.size;
}

static int fuse_prepare_write(struct file *file, struct page *page,
			      unsigned offset, unsigned to)
{
	/* No op */
	return 0;
}

static int fuse_commit_write(struct file *file, struct page *page,
			     unsigned offset, unsigned to)
{
	int err;
	size_t nres;
	unsigned count = to - offset;
	struct inode *inode = page->mapping->host;
	struct fuse_conn *fc = get_fuse_conn(inode);
	loff_t pos = page_offset(page) + offset;
	struct fuse_req *req;

	if (is_bad_inode(inode))
		return -EIO;

	req = fuse_get_req(fc);
	if (IS_ERR(req))
		return PTR_ERR(req);

	req->num_pages = 1;
	req->pages[0] = page;
	req->page_offset = offset;
	nres = fuse_send_write(req, file, inode, pos, count);
	err = req->out.h.error;
	fuse_put_request(fc, req);
	if (!err && nres != count)
		err = -EIO;
	if (!err) {
		pos += count;
		spin_lock(&fc->lock);
		if (pos > inode->i_size)
			i_size_write(inode, pos);
		spin_unlock(&fc->lock);

		if (offset == 0 && to == PAGE_CACHE_SIZE)
			SetPageUptodate(page);
	}
	fuse_invalidate_attr(inode);
	return err;
}

static void fuse_release_user_pages(struct fuse_req *req, int write)
{
	unsigned i;

	for (i = 0; i < req->num_pages; i++) {
		struct page *page = req->pages[i];
		if (write)
			set_page_dirty_lock(page);
		put_page(page);
	}
}

static int fuse_get_user_pages(struct fuse_req *req, const char __user *buf,
			       unsigned nbytes, int write)
{
	unsigned long user_addr = (unsigned long) buf;
	unsigned offset = user_addr & ~PAGE_MASK;
	int npages;

	/* This doesn't work with nfsd */
	if (!current->mm)
		return -EPERM;

	nbytes = min(nbytes, (unsigned) FUSE_MAX_PAGES_PER_REQ << PAGE_SHIFT);
	npages = (nbytes + offset + PAGE_SIZE - 1) >> PAGE_SHIFT;
	npages = max(npages, 1);
	npages = min(npages, FUSE_MAX_PAGES_PER_REQ);
	down_read(&current->mm->mmap_sem);
	npages = get_user_pages(current, current->mm, user_addr, npages, write,
				0, req->pages, NULL);
	up_read(&current->mm->mmap_sem);
	if (npages < 0)
		return npages;

	req->num_pages = npages;
	req->page_offset = offset;
	return 0;
}

static ssize_t fuse_direct_io(struct file *file, const char __user *buf,
			      size_t count, loff_t *ppos, int write)
{
	struct inode *inode = file->f_dentry->d_inode;
	struct fuse_conn *fc = get_fuse_conn(inode);
	size_t nmax = write ? fc->max_write : fc->max_read;
	loff_t pos = *ppos;
	ssize_t res = 0;
	struct fuse_req *req;

	if (is_bad_inode(inode))
		return -EIO;

	req = fuse_get_req(fc);
	if (IS_ERR(req))
		return PTR_ERR(req);

	while (count) {
		size_t nres;
		size_t nbytes = min(count, nmax);
		int err = fuse_get_user_pages(req, buf, nbytes, !write);
		if (err) {
			res = err;
			break;
		}
		nbytes = (req->num_pages << PAGE_SHIFT) - req->page_offset;
		nbytes = min(count, nbytes);
		if (write)
			nres = fuse_send_write(req, file, inode, pos, nbytes);
		else
			nres = fuse_send_read(req, file, inode, pos, nbytes);
		fuse_release_user_pages(req, !write);
		if (req->out.h.error) {
			if (!res)
				res = req->out.h.error;
			break;
		} else if (nres > nbytes) {
			res = -EIO;
			break;
		}
		count -= nres;
		res += nres;
		pos += nres;
		buf += nres;
		if (nres != nbytes)
			break;
		if (count) {
			fuse_put_request(fc, req);
			req = fuse_get_req(fc);
			if (IS_ERR(req))
				break;
		}
	}
	fuse_put_request(fc, req);
	if (res > 0) {
		if (write) {
			spin_lock(&fc->lock);
			if (pos > inode->i_size)
				i_size_write(inode, pos);
			spin_unlock(&fc->lock);
		}
		*ppos = pos;
	}
	fuse_invalidate_attr(inode);

	return res;
}

static ssize_t fuse_direct_read(struct file *file, char __user *buf,
				     size_t count, loff_t *ppos)
{
	return fuse_direct_io(file, buf, count, ppos, 0);
}

static ssize_t fuse_direct_write(struct file *file, const char __user *buf,
				 size_t count, loff_t *ppos)
{
	struct inode *inode = file->f_dentry->d_inode;
	ssize_t res;
	/* Don't allow parallel writes to the same file */
	mutex_lock(&inode->i_mutex);
	res = generic_write_checks(file, ppos, &count, 0);
	if (!res)
		res = fuse_direct_io(file, buf, count, ppos, 1);
	mutex_unlock(&inode->i_mutex);
	return res;
}

static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	if ((vma->vm_flags & VM_SHARED)) {
		if ((vma->vm_flags & VM_WRITE))
			return -ENODEV;
		else
			vma->vm_flags &= ~VM_MAYWRITE;
	}
	return generic_file_mmap(file, vma);
}

static int fuse_set_page_dirty(struct page *page)
{
	printk("fuse_set_page_dirty: should not happen\n");
	dump_stack();
	return 0;
}

static int convert_fuse_file_lock(const struct fuse_file_lock *ffl,
				  struct file_lock *fl)
{
	switch (ffl->type) {
	case F_UNLCK:
		break;

	case F_RDLCK:
	case F_WRLCK:
		if (ffl->start > OFFSET_MAX || ffl->end > OFFSET_MAX ||
		    ffl->end < ffl->start)
			return -EIO;

		fl->fl_start = ffl->start;
		fl->fl_end = ffl->end;
		fl->fl_pid = ffl->pid;
		break;

	default:
		return -EIO;
	}
	fl->fl_type = ffl->type;
	return 0;
}

static void fuse_lk_fill(struct fuse_req *req, struct file *file,
			 const struct file_lock *fl, int opcode, pid_t pid)
{
	struct inode *inode = file->f_dentry->d_inode;
	struct fuse_conn *fc = get_fuse_conn(inode);
	struct fuse_file *ff = file->private_data;
	struct fuse_lk_in *arg = &req->misc.lk_in;

	arg->fh = ff->fh;
	arg->owner = fuse_lock_owner_id(fc, fl->fl_owner);
	arg->lk.start = fl->fl_start;
	arg->lk.end = fl->fl_end;
	arg->lk.type = fl->fl_type;
	arg->lk.pid = pid;
	req->in.h.opcode = opcode;
	req->in.h.nodeid = get_node_id(inode);
	req->in.numargs = 1;
	req->in.args[0].size = sizeof(*arg);
	req->in.args[0].value = arg;
}

static int fuse_getlk(struct file *file, struct file_lock *fl)
{
	struct inode *inode = file->f_dentry->d_inode;
	struct fuse_conn *fc = get_fuse_conn(inode);
	struct fuse_req *req;
	struct fuse_lk_out outarg;
	int err;

	req = fuse_get_req(fc);
	if (IS_ERR(req))
		return PTR_ERR(req);

	fuse_lk_fill(req, file, fl, FUSE_GETLK, 0);
	req->out.numargs = 1;
	req->out.args[0].size = sizeof(outarg);
	req->out.args[0].value = &outarg;
	request_send(fc, req);
	err = req->out.h.error;
	fuse_put_request(fc, req);
	if (!err)
		err = convert_fuse_file_lock(&outarg.lk, fl);

	return err;
}

static int fuse_setlk(struct file *file, struct file_lock *fl)
{
	struct inode *inode = file->f_dentry->d_inode;
	struct fuse_conn *fc = get_fuse_conn(inode);
	struct fuse_req *req;
	int opcode = (fl->fl_flags & FL_SLEEP) ? FUSE_SETLKW : FUSE_SETLK;
	pid_t pid = fl->fl_type != F_UNLCK ? current->tgid : 0;
	int err;

#ifdef KERNEL_2_6_18_PLUS
	/* Unlock on close is handled by the flush method */
	if (fl->fl_flags & FL_CLOSE)
		return 0;

	req = fuse_get_req(fc);
#else
	/* If it's (possibly) unlock on close, don't fail the allocation */
	if (fl->fl_type == F_UNLCK && fl->fl_start == 0 &&
	    fl->fl_end == OFFSET_MAX)
		req = fuse_get_req_nofail(fc, file);
	else {
		/* Hack: add dummy lock, otherwise unlock on close is
		   optimized away */
		struct file_lock **flp;
		for (flp = &inode->i_flock;
		     *flp && !((*flp)->fl_flags & FL_POSIX);
		     flp = &(*flp)->fl_next);
		if (!*flp) {
			struct file_lock *dummy =
				kmalloc(sizeof(struct file_lock), GFP_KERNEL);
			if (!dummy)
				return -ENOLCK;
			locks_init_lock(dummy);
			dummy->fl_flags |= FL_POSIX;
			*flp = dummy;
		}
		req = fuse_get_req(fc);
	}
#endif
	if (IS_ERR(req))
		return PTR_ERR(req);

	fuse_lk_fill(req, file, fl, opcode, pid);
	request_send(fc, req);
	err = req->out.h.error;
	/* locking is restartable */
	if (err == -EINTR)
		err = -ERESTARTSYS;
	fuse_put_request(fc, req);
	return err;
}

static int fuse_file_lock(struct file *file, int cmd, struct file_lock *fl)
{
	struct inode *inode = file->f_dentry->d_inode;
	struct fuse_conn *fc = get_fuse_conn(inode);
	int err;

	if (cmd == F_GETLK) {
		if (fc->no_lock) {
#ifdef KERNEL_2_6_22_PLUS
			posix_test_lock(file, fl);
#elif defined(KERNEL_2_6_17_PLUS)
			if (!posix_test_lock(file, fl, fl))
				fl->fl_type = F_UNLCK;
#else
			struct file_lock *cfl = posix_test_lock(file, fl);
			if (!cfl)
				fl->fl_type = F_UNLCK;
			else
				*fl = *cfl;
#endif
			err = 0;
		} else
			err = fuse_getlk(file, fl);
	} else {
		if (fc->no_lock)
			err = posix_lock_file_wait(file, fl);
		else
			err = fuse_setlk(file, fl);
	}
	return err;
}

static sector_t fuse_bmap(struct address_space *mapping, sector_t block)
{
	struct inode *inode = mapping->host;
	struct fuse_conn *fc = get_fuse_conn(inode);
	struct fuse_req *req;
	struct fuse_bmap_in inarg;
	struct fuse_bmap_out outarg;
	int err;

	if (!inode->i_sb->s_bdev || fc->no_bmap)
		return 0;

	req = fuse_get_req(fc);
	if (IS_ERR(req))
		return 0;

	memset(&inarg, 0, sizeof(inarg));
	inarg.block = block;
	inarg.blocksize = inode->i_sb->s_blocksize;
	req->in.h.opcode = FUSE_BMAP;
	req->in.h.nodeid = get_node_id(inode);
	req->in.numargs = 1;
	req->in.args[0].size = sizeof(inarg);
	req->in.args[0].value = &inarg;
	req->out.numargs = 1;
	req->out.args[0].size = sizeof(outarg);
	req->out.args[0].value = &outarg;
	request_send(fc, req);
	err = req->out.h.error;
	fuse_put_request(fc, req);
	if (err == -ENOSYS)
		fc->no_bmap = 1;

	return err ? 0 : outarg.block;
}

static struct file_operations fuse_file_operations = {
	.llseek		= generic_file_llseek,
#ifndef KERNEL_2_6_19_PLUS
	.read		= generic_file_read,
	.write		= generic_file_write,
#else
	.read		= do_sync_read,
	.aio_read	= generic_file_aio_read,
	.write		= do_sync_write,
	.aio_write	= generic_file_aio_write,
#endif
	.mmap		= fuse_file_mmap,
	.open		= fuse_open,
	.flush		= fuse_flush,
	.release	= fuse_release,
	.fsync		= fuse_fsync,
	.lock		= fuse_file_lock,
#ifdef KERNEL_2_6_23_PLUS
	.splice_read	= generic_file_splice_read,
#else
	.sendfile	= generic_file_sendfile,
#endif
};

static struct file_operations fuse_direct_io_file_operations = {
	.llseek		= generic_file_llseek,
	.read		= fuse_direct_read,
	.write		= fuse_direct_write,
	.open		= fuse_open,
	.flush		= fuse_flush,
	.release	= fuse_release,
	.fsync		= fuse_fsync,
	.lock		= fuse_file_lock,
	/* no mmap and sendfile */
};

static struct address_space_operations fuse_file_aops  = {
	.readpage	= fuse_readpage,
	.prepare_write	= fuse_prepare_write,
	.commit_write	= fuse_commit_write,
	.readpages	= fuse_readpages,
	.set_page_dirty	= fuse_set_page_dirty,
	.bmap		= fuse_bmap,
};

void fuse_init_file_inode(struct inode *inode)
{
	inode->i_fop = &fuse_file_operations;
	inode->i_data.a_ops = &fuse_file_aops;
}