file.c

linux 内核源代码

/*
  FUSE: Filesystem in Userspace
  Copyright (C) 2001-2006  Miklos Szeredi <[e-mail]>

  This program can be distributed under the terms of the GNU GPL.
  See the file COPYING.
*/

#include "fuse_i.h"

#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/sched.h>

static const struct file_operations fuse_direct_io_file_operations;

static int fuse_send_open(struct inode *inode, struct file *file, int isdir,
			  struct fuse_open_out *outargp)
{
	struct fuse_conn *fc = get_fuse_conn(inode);
	struct fuse_open_in inarg;
	struct fuse_req *req;
	int err;

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

	memset(&inarg, 0, sizeof(inarg));
	inarg.flags = file->f_flags & ~(O_CREAT | O_EXCL | O_NOCTTY);
	if (!fc->atomic_o_trunc)
		inarg.flags &= ~O_TRUNC;
	req->in.h.opcode = isdir ? FUSE_OPENDIR : FUSE_OPEN;
	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(*outargp);
	req->out.args[0].value = outargp;
	request_send(fc, req);
	err = req->out.h.error;
	fuse_put_request(fc, req);

	return err;
}

struct fuse_file *fuse_file_alloc(void)
{
	struct fuse_file *ff;
	ff = kmalloc(sizeof(struct fuse_file), GFP_KERNEL);
	if (ff) {
		ff->reserved_req = fuse_request_alloc();
		if (!ff->reserved_req) {
			kfree(ff);
			ff = NULL;
		} else {
			INIT_LIST_HEAD(&ff->write_entry);
			atomic_set(&ff->count, 0);
		}
	}
	return ff;
}

void fuse_file_free(struct fuse_file *ff)
{
	fuse_request_free(ff->reserved_req);
	kfree(ff);
}

static struct fuse_file *fuse_file_get(struct fuse_file *ff)
{
	atomic_inc(&ff->count);
	return ff;
}

static void fuse_release_end(struct fuse_conn *fc, struct fuse_req *req)
{
	dput(req->dentry);
	mntput(req->vfsmount);
	fuse_put_request(fc, req);
}

static void fuse_file_put(struct fuse_file *ff)
{
	if (atomic_dec_and_test(&ff->count)) {
		struct fuse_req *req = ff->reserved_req;
		struct fuse_conn *fc = get_fuse_conn(req->dentry->d_inode);
		req->end = fuse_release_end;
		request_send_background(fc, req);
		kfree(ff);
	}
}

void fuse_finish_open(struct inode *inode, struct file *file,
		      struct fuse_file *ff, struct fuse_open_out *outarg)
{
	if (outarg->open_flags & FOPEN_DIRECT_IO)
		file->f_op = &fuse_direct_io_file_operations;
	if (!(outarg->open_flags & FOPEN_KEEP_CACHE))
		invalidate_inode_pages2(inode->i_mapping);
	ff->fh = outarg->fh;
	file->private_data = fuse_file_get(ff);
}

int fuse_open_common(struct inode *inode, struct file *file, int isdir)
{
	struct fuse_open_out outarg;
	struct fuse_file *ff;
	int err;

	/* VFS checks this, but only _after_ ->open() */
	if (file->f_flags & O_DIRECT)
		return -EINVAL;

	err = generic_file_open(inode, file);
	if (err)
		return err;

	ff = fuse_file_alloc();
	if (!ff)
		return -ENOMEM;

	err = fuse_send_open(inode, file, isdir, &outarg);
	if (err)
		fuse_file_free(ff);
	else {
		if (isdir)
			outarg.open_flags &= ~FOPEN_DIRECT_IO;
		fuse_finish_open(inode, file, ff, &outarg);
	}

	return err;
}

void fuse_release_fill(struct fuse_file *ff, u64 nodeid, int flags, int opcode)
{
	struct fuse_req *req = ff->reserved_req;
	struct fuse_release_in *inarg = &req->misc.release_in;

	inarg->fh = ff->fh;
	inarg->flags = flags;
	req->in.h.opcode = opcode;
	req->in.h.nodeid = nodeid;
	req->in.numargs = 1;
	req->in.args[0].size = sizeof(struct fuse_release_in);
	req->in.args[0].value = inarg;
}

int fuse_release_common(struct inode *inode, struct file *file, int isdir)
{
	struct fuse_file *ff = file->private_data;
	if (ff) {
		struct fuse_conn *fc = get_fuse_conn(inode);

		fuse_release_fill(ff, get_node_id(inode), file->f_flags,
				  isdir ? FUSE_RELEASEDIR : FUSE_RELEASE);

		/* Hold vfsmount and dentry until release is finished */
		ff->reserved_req->vfsmount = mntget(file->f_path.mnt);
		ff->reserved_req->dentry = dget(file->f_path.dentry);

		spin_lock(&fc->lock);
		list_del(&ff->write_entry);
		spin_unlock(&fc->lock);
		/*
		 * Normally this will send the RELEASE request,
		 * however if some asynchronous READ or WRITE requests
		 * are outstanding, the sending will be delayed
		 */
		fuse_file_put(ff);
	}

	/* Return value is ignored by VFS */
	return 0;
}

static int fuse_open(struct inode *inode, struct file *file)
{
	return fuse_open_common(inode, file, 0);
}

static int fuse_release(struct inode *inode, struct file *file)
{
	return fuse_release_common(inode, file, 0);
}

/*
 * Scramble the ID space with XTEA, so that the value of the files_struct
 * pointer is not exposed to userspace.
 */
u64 fuse_lock_owner_id(struct fuse_conn *fc, fl_owner_t id)
{
	u32 *k = fc->scramble_key;
	u64 v = (unsigned long) id;
	u32 v0 = v;
	u32 v1 = v >> 32;
	u32 sum = 0;
	int i;

	for (i = 0; i < 32; i++) {
		v0 += ((v1 << 4 ^ v1 >> 5) + v1) ^ (sum + k[sum & 3]);
		sum += 0x9E3779B9;
		v1 += ((v0 << 4 ^ v0 >> 5) + v0) ^ (sum + k[sum>>11 & 3]);
	}

	return (u64) v0 + ((u64) v1 << 32);
}

static int fuse_flush(struct file *file, fl_owner_t id)
{
	struct inode *inode = file->f_path.dentry->d_inode;
	struct fuse_conn *fc = get_fuse_conn(inode);
	struct fuse_file *ff = file->private_data;
	struct fuse_req *req;
	struct fuse_flush_in inarg;
	int err;

	if (is_bad_inode(inode))
		return -EIO;

	if (fc->no_flush)
		return 0;

	req = fuse_get_req_nofail(fc, file);
	memset(&inarg, 0, sizeof(inarg));
	inarg.fh = ff->fh;
	inarg.lock_owner = fuse_lock_owner_id(fc, id);
	req->in.h.opcode = FUSE_FLUSH;
	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->force = 1;
	request_send(fc, req);
	err = req->out.h.error;
	fuse_put_request(fc, req);
	if (err == -ENOSYS) {
		fc->no_flush = 1;
		err = 0;
	}
	return err;
}

int fuse_fsync_common(struct file *file, struct dentry *de, int datasync,
		      int isdir)
{
	struct inode *inode = de->d_inode;
	struct fuse_conn *fc = get_fuse_conn(inode);
	struct fuse_file *ff = file->private_data;
	struct fuse_req *req;
	struct fuse_fsync_in inarg;
	int err;

	if (is_bad_inode(inode))
		return -EIO;

	if ((!isdir && fc->no_fsync) || (isdir && fc->no_fsyncdir))
		return 0;

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

	memset(&inarg, 0, sizeof(inarg));
	inarg.fh = ff->fh;
	inarg.fsync_flags = datasync ? 1 : 0;
	req->in.h.opcode = isdir ? FUSE_FSYNCDIR : FUSE_FSYNC;
	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;
	request_send(fc, req);
	err = req->out.h.error;
	fuse_put_request(fc, req);
	if (err == -ENOSYS) {
		if (isdir)
			fc->no_fsyncdir = 1;
		else
			fc->no_fsync = 1;
		err = 0;
	}
	return err;
}

static int fuse_fsync(struct file *file, struct dentry *de, int datasync)
{
	return fuse_fsync_common(file, de, datasync, 0);
}

void fuse_read_fill(struct fuse_req *req, struct file *file,
		    struct inode *inode, loff_t pos, size_t count, int opcode)
{
	struct fuse_read_in *inarg = &req->misc.read_in;
	struct fuse_file *ff = file->private_data;

	inarg->fh = ff->fh;
	inarg->offset = pos;
	inarg->size = count;
	inarg->flags = file->f_flags;
	req->in.h.opcode = opcode;
	req->in.h.nodeid = get_node_id(inode);
	req->in.numargs = 1;
	req->in.args[0].size = sizeof(struct fuse_read_in);
	req->in.args[0].value = inarg;
	req->out.argpages = 1;
	req->out.argvar = 1;
	req->out.numargs = 1;
	req->out.args[0].size = count;
}

static size_t fuse_send_read(struct fuse_req *req, struct file *file,
			     struct inode *inode, loff_t pos, size_t count,
			     fl_owner_t owner)
{
	struct fuse_conn *fc = get_fuse_conn(inode);

	fuse_read_fill(req, file, inode, pos, count, FUSE_READ);
	if (owner != NULL) {
		struct fuse_read_in *inarg = &req->misc.read_in;

		inarg->read_flags |= FUSE_READ_LOCKOWNER;
		inarg->lock_owner = fuse_lock_owner_id(fc, owner);
	}
	request_send(fc, req);
	return req->out.args[0].size;
}

static int fuse_readpage(struct file *file, struct page *page)
{
	struct inode *inode = page->mapping->host;
	struct fuse_conn *fc = get_fuse_conn(inode);
	struct fuse_req *req;
	int err;

	err = -EIO;
	if (is_bad_inode(inode))
		goto out;

	req = fuse_get_req(fc);
	err = PTR_ERR(req);
	if (IS_ERR(req))
		goto out;

	req->out.page_zeroing = 1;
	req->num_pages = 1;
	req->pages[0] = page;
	fuse_send_read(req, file, inode, page_offset(page), PAGE_CACHE_SIZE,
		       NULL);
	err = req->out.h.error;
	fuse_put_request(fc, req);
	if (!err)
		SetPageUptodate(page);
	fuse_invalidate_attr(inode); /* atime changed */
 out:
	unlock_page(page);
	return err;
}

static void fuse_readpages_end(struct fuse_conn *fc, struct fuse_req *req)
{
	int i;

	fuse_invalidate_attr(req->pages[0]->mapping->host); /* atime changed */

	for (i = 0; i < req->num_pages; i++) {
		struct page *page = req->pages[i];
		if (!req->out.h.error)
			SetPageUptodate(page);
		else
			SetPageError(page);
		unlock_page(page);
	}
	if (req->ff)
		fuse_file_put(req->ff);
	fuse_put_request(fc, req);
}

static void fuse_send_readpages(struct fuse_req *req, struct file *file,
				struct inode *inode)
{
	struct fuse_conn *fc = get_fuse_conn(inode);
	loff_t pos = page_offset(req->pages[0]);
	size_t count = req->num_pages << PAGE_CACHE_SHIFT;
	req->out.page_zeroing = 1;
	fuse_read_fill(req, file, inode, pos, count, FUSE_READ);
	if (fc->async_read) {
		struct fuse_file *ff = file->private_data;
		req->ff = fuse_file_get(ff);
		req->end = fuse_readpages_end;
		request_send_background(fc, req);
	} else {
		request_send(fc, req);
		fuse_readpages_end(fc, req);
	}
}

struct fuse_fill_data {
	struct fuse_req *req;
	struct file *file;
	struct inode *inode;
};

static int fuse_readpages_fill(void *_data, struct page *page)
{
	struct fuse_fill_data *data = _data;
	struct fuse_req *req = data->req;
	struct inode *inode = data->inode;
	struct fuse_conn *fc = get_fuse_conn(inode);

	if (req->num_pages &&
	    (req->num_pages == FUSE_MAX_PAGES_PER_REQ ||
	     (req->num_pages + 1) * PAGE_CACHE_SIZE > fc->max_read ||
	     req->pages[req->num_pages - 1]->index + 1 != page->index)) {
		fuse_send_readpages(req, data->file, inode);
		data->req = req = fuse_get_req(fc);
		if (IS_ERR(req)) {
			unlock_page(page);
			return PTR_ERR(req);
		}
	}
	req->pages[req->num_pages] = page;
	req->num_pages ++;
	return 0;
}

static int fuse_readpages(struct file *file, struct address_space *mapping,
			  struct list_head *pages, unsigned nr_pages)
{
	struct inode *inode = mapping->host;
	struct fuse_conn *fc = get_fuse_conn(inode);
	struct fuse_fill_data data;
	int err;

	err = -EIO;
	if (is_bad_inode(inode))
		goto out;

	data.file = file;
	data.inode = inode;
	data.req = fuse_get_req(fc);
	err = PTR_ERR(data.req);
	if (IS_ERR(data.req))
		goto out;

	err = read_cache_pages(mapping, pages, fuse_readpages_fill, &data);
	if (!err) {
		if (data.req->num_pages)
			fuse_send_readpages(data.req, file, inode);
		else
			fuse_put_request(fc, data.req);
	}
out:
	return err;
}

static ssize_t fuse_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
				  unsigned long nr_segs, loff_t pos)
{
	struct inode *inode = iocb->ki_filp->f_mapping->host;

	if (pos + iov_length(iov, nr_segs) > i_size_read(inode)) {
		int err;
		/*
		 * If trying to read past EOF, make sure the i_size
		 * attribute is up-to-date.
		 */
		err = fuse_update_attributes(inode, NULL, iocb->ki_filp, NULL);
		if (err)
			return err;
	}

	return generic_file_aio_read(iocb, iov, nr_segs, pos);
}

static void fuse_write_fill(struct fuse_req *req, struct file *file,