inode.c

linux 内核源代码

 */

struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
			   unsigned int mode, dev_t dev)
{
	struct inode *inode = NULL;
	struct gfs2_inode *dip = ghs->gh_gl->gl_object;
	struct inode *dir = &dip->i_inode;
	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
	struct gfs2_inum_host inum = { .no_addr = 0, .no_formal_ino = 0 };
	int error;
	u64 generation;
	struct buffer_head *bh=NULL;

	if (!name->len || name->len > GFS2_FNAMESIZE)
		return ERR_PTR(-ENAMETOOLONG);

	gfs2_holder_reinit(LM_ST_EXCLUSIVE, 0, ghs);
	error = gfs2_glock_nq(ghs);
	if (error)
		goto fail;

	error = create_ok(dip, name, mode);
	if (error)
		goto fail_gunlock;

	error = pick_formal_ino(sdp, &inum.no_formal_ino);
	if (error)
		goto fail_gunlock;

	error = alloc_dinode(dip, &inum.no_addr, &generation);
	if (error)
		goto fail_gunlock;

	error = gfs2_glock_nq_num(sdp, inum.no_addr, &gfs2_inode_glops,
				  LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1);
	if (error)
		goto fail_gunlock;

	error = make_dinode(dip, ghs[1].gh_gl, mode, &inum, &generation, dev, &bh);
	if (error)
		goto fail_gunlock2;

	inode = gfs2_inode_lookup(dir->i_sb, IF2DT(mode),
					inum.no_addr,
					inum.no_formal_ino, 0);
	if (IS_ERR(inode))
		goto fail_gunlock2;

	gfs2_inode_bh(GFS2_I(inode), bh);

	error = gfs2_inode_refresh(GFS2_I(inode));
	if (error)
		goto fail_gunlock2;

	error = gfs2_acl_create(dip, GFS2_I(inode));
	if (error)
		goto fail_gunlock2;

	error = gfs2_security_init(dip, GFS2_I(inode));
	if (error)
		goto fail_gunlock2;

	error = link_dinode(dip, name, GFS2_I(inode));
	if (error)
		goto fail_gunlock2;

	if (!inode)
		return ERR_PTR(-ENOMEM);
	return inode;

fail_gunlock2:
	gfs2_glock_dq_uninit(ghs + 1);
	if (inode)
		iput(inode);
fail_gunlock:
	gfs2_glock_dq(ghs);
fail:
	return ERR_PTR(error);
}

/**
 * gfs2_rmdiri - Remove a directory
 * @dip: The parent directory of the directory to be removed
 * @name: The name of the directory to be removed
 * @ip: The GFS2 inode of the directory to be removed
 *
 * Assumes Glocks on dip and ip are held
 *
 * Returns: errno
 */

int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name,
		struct gfs2_inode *ip)
{
	struct qstr dotname;
	int error;

	if (ip->i_di.di_entries != 2) {
		if (gfs2_consist_inode(ip))
			gfs2_dinode_print(ip);
		return -EIO;
	}

	error = gfs2_dir_del(dip, name);
	if (error)
		return error;

	error = gfs2_change_nlink(dip, -1);
	if (error)
		return error;

	gfs2_str2qstr(&dotname, ".");
	error = gfs2_dir_del(ip, &dotname);
	if (error)
		return error;

	gfs2_str2qstr(&dotname, "..");
	error = gfs2_dir_del(ip, &dotname);
	if (error)
		return error;

	/* It looks odd, but it really should be done twice */
	error = gfs2_change_nlink(ip, -1);
	if (error)
		return error;

	error = gfs2_change_nlink(ip, -1);
	if (error)
		return error;

	return error;
}

/*
 * gfs2_unlink_ok - check to see that a inode is still in a directory
 * @dip: the directory
 * @name: the name of the file
 * @ip: the inode
 *
 * Assumes that the lock on (at least) @dip is held.
 *
 * Returns: 0 if the parent/child relationship is correct, errno if it isn't
 */

int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
		   const struct gfs2_inode *ip)
{
	int error;

	if (IS_IMMUTABLE(&ip->i_inode) || IS_APPEND(&ip->i_inode))
		return -EPERM;

	if ((dip->i_inode.i_mode & S_ISVTX) &&
	    dip->i_inode.i_uid != current->fsuid &&
	    ip->i_inode.i_uid != current->fsuid && !capable(CAP_FOWNER))
		return -EPERM;

	if (IS_APPEND(&dip->i_inode))
		return -EPERM;

	error = permission(&dip->i_inode, MAY_WRITE | MAY_EXEC, NULL);
	if (error)
		return error;

	error = gfs2_dir_check(&dip->i_inode, name, ip);
	if (error)
		return error;

	return 0;
}

/*
 * gfs2_ok_to_move - check if it's ok to move a directory to another directory
 * @this: move this
 * @to: to here
 *
 * Follow @to back to the root and make sure we don't encounter @this
 * Assumes we already hold the rename lock.
 *
 * Returns: errno
 */

int gfs2_ok_to_move(struct gfs2_inode *this, struct gfs2_inode *to)
{
	struct inode *dir = &to->i_inode;
	struct super_block *sb = dir->i_sb;
	struct inode *tmp;
	struct qstr dotdot;
	int error = 0;

	gfs2_str2qstr(&dotdot, "..");

	igrab(dir);

	for (;;) {
		if (dir == &this->i_inode) {
			error = -EINVAL;
			break;
		}
		if (dir == sb->s_root->d_inode) {
			error = 0;
			break;
		}

		tmp = gfs2_lookupi(dir, &dotdot, 1, NULL);
		if (IS_ERR(tmp)) {
			error = PTR_ERR(tmp);
			break;
		}

		iput(dir);
		dir = tmp;
	}

	iput(dir);

	return error;
}

/**
 * gfs2_readlinki - return the contents of a symlink
 * @ip: the symlink's inode
 * @buf: a pointer to the buffer to be filled
 * @len: a pointer to the length of @buf
 *
 * If @buf is too small, a piece of memory is kmalloc()ed and needs
 * to be freed by the caller.
 *
 * Returns: errno
 */

int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len)
{
	struct gfs2_holder i_gh;
	struct buffer_head *dibh;
	unsigned int x;
	int error;

	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &i_gh);
	error = gfs2_glock_nq_atime(&i_gh);
	if (error) {
		gfs2_holder_uninit(&i_gh);
		return error;
	}

	if (!ip->i_di.di_size) {
		gfs2_consist_inode(ip);
		error = -EIO;
		goto out;
	}

	error = gfs2_meta_inode_buffer(ip, &dibh);
	if (error)
		goto out;

	x = ip->i_di.di_size + 1;
	if (x > *len) {
		*buf = kmalloc(x, GFP_KERNEL);
		if (!*buf) {
			error = -ENOMEM;
			goto out_brelse;
		}
	}

	memcpy(*buf, dibh->b_data + sizeof(struct gfs2_dinode), x);
	*len = x;

out_brelse:
	brelse(dibh);
out:
	gfs2_glock_dq_uninit(&i_gh);
	return error;
}

/**
 * gfs2_glock_nq_atime - Acquire a hold on an inode's glock, and
 *       conditionally update the inode's atime
 * @gh: the holder to acquire
 *
 * Tests atime (access time) for gfs2_read, gfs2_readdir and gfs2_mmap
 * Update if the difference between the current time and the inode's current
 * atime is greater than an interval specified at mount.
 *
 * Returns: errno
 */

int gfs2_glock_nq_atime(struct gfs2_holder *gh)
{
	struct gfs2_glock *gl = gh->gh_gl;
	struct gfs2_sbd *sdp = gl->gl_sbd;
	struct gfs2_inode *ip = gl->gl_object;
	s64 quantum = gfs2_tune_get(sdp, gt_atime_quantum);
	unsigned int state;
	int flags;
	int error;
	struct timespec tv = CURRENT_TIME;

	if (gfs2_assert_warn(sdp, gh->gh_flags & GL_ATIME) ||
	    gfs2_assert_warn(sdp, !(gh->gh_flags & GL_ASYNC)) ||
	    gfs2_assert_warn(sdp, gl->gl_ops == &gfs2_inode_glops))
		return -EINVAL;

	state = gh->gh_state;
	flags = gh->gh_flags;

	error = gfs2_glock_nq(gh);
	if (error)
		return error;

	if (test_bit(SDF_NOATIME, &sdp->sd_flags) ||
	    (sdp->sd_vfs->s_flags & MS_RDONLY))
		return 0;

	if (tv.tv_sec - ip->i_inode.i_atime.tv_sec >= quantum) {
		gfs2_glock_dq(gh);
		gfs2_holder_reinit(LM_ST_EXCLUSIVE, gh->gh_flags & ~LM_FLAG_ANY,
				   gh);
		error = gfs2_glock_nq(gh);
		if (error)
			return error;

		/* Verify that atime hasn't been updated while we were
		   trying to get exclusive lock. */

		tv = CURRENT_TIME;
		if (tv.tv_sec - ip->i_inode.i_atime.tv_sec >= quantum) {
			struct buffer_head *dibh;
			struct gfs2_dinode *di;

			error = gfs2_trans_begin(sdp, RES_DINODE, 0);
			if (error == -EROFS)
				return 0;
			if (error)
				goto fail;

			error = gfs2_meta_inode_buffer(ip, &dibh);
			if (error)
				goto fail_end_trans;

			ip->i_inode.i_atime = tv;

			gfs2_trans_add_bh(ip->i_gl, dibh, 1);
			di = (struct gfs2_dinode *)dibh->b_data;
			di->di_atime = cpu_to_be64(ip->i_inode.i_atime.tv_sec);
			di->di_atime_nsec = cpu_to_be32(ip->i_inode.i_atime.tv_nsec);
			brelse(dibh);

			gfs2_trans_end(sdp);
		}

		/* If someone else has asked for the glock,
		   unlock and let them have it. Then reacquire
		   in the original state. */
		if (gfs2_glock_is_blocking(gl)) {
			gfs2_glock_dq(gh);
			gfs2_holder_reinit(state, flags, gh);
			return gfs2_glock_nq(gh);
		}
	}

	return 0;

fail_end_trans:
	gfs2_trans_end(sdp);
fail:
	gfs2_glock_dq(gh);
	return error;
}

static int
__gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
{
	struct buffer_head *dibh;
	int error;

	error = gfs2_meta_inode_buffer(ip, &dibh);
	if (!error) {
		error = inode_setattr(&ip->i_inode, attr);
		gfs2_assert_warn(GFS2_SB(&ip->i_inode), !error);
		gfs2_trans_add_bh(ip->i_gl, dibh, 1);
		gfs2_dinode_out(ip, dibh->b_data);
		brelse(dibh);
	}
	return error;
}

/**
 * gfs2_setattr_simple -
 * @ip:
 * @attr:
 *
 * Called with a reference on the vnode.
 *
 * Returns: errno
 */

int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
{
	int error;

	if (current->journal_info)
		return __gfs2_setattr_simple(ip, attr);

	error = gfs2_trans_begin(GFS2_SB(&ip->i_inode), RES_DINODE, 0);
	if (error)
		return error;

	error = __gfs2_setattr_simple(ip, attr);
	gfs2_trans_end(GFS2_SB(&ip->i_inode));
	return error;
}

void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf)
{
	const struct gfs2_dinode_host *di = &ip->i_di;
	struct gfs2_dinode *str = buf;

	str->di_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
	str->di_header.mh_type = cpu_to_be32(GFS2_METATYPE_DI);
	str->di_header.__pad0 = 0;
	str->di_header.mh_format = cpu_to_be32(GFS2_FORMAT_DI);
	str->di_header.__pad1 = 0;
	str->di_num.no_addr = cpu_to_be64(ip->i_no_addr);
	str->di_num.no_formal_ino = cpu_to_be64(ip->i_no_formal_ino);
	str->di_mode = cpu_to_be32(ip->i_inode.i_mode);
	str->di_uid = cpu_to_be32(ip->i_inode.i_uid);
	str->di_gid = cpu_to_be32(ip->i_inode.i_gid);
	str->di_nlink = cpu_to_be32(ip->i_inode.i_nlink);
	str->di_size = cpu_to_be64(di->di_size);
	str->di_blocks = cpu_to_be64(di->di_blocks);
	str->di_atime = cpu_to_be64(ip->i_inode.i_atime.tv_sec);
	str->di_mtime = cpu_to_be64(ip->i_inode.i_mtime.tv_sec);
	str->di_ctime = cpu_to_be64(ip->i_inode.i_ctime.tv_sec);

	str->di_goal_meta = cpu_to_be64(di->di_goal_meta);
	str->di_goal_data = cpu_to_be64(di->di_goal_data);
	str->di_generation = cpu_to_be64(di->di_generation);

	str->di_flags = cpu_to_be32(di->di_flags);
	str->di_height = cpu_to_be16(di->di_height);
	str->di_payload_format = cpu_to_be32(S_ISDIR(ip->i_inode.i_mode) &&
					     !(ip->i_di.di_flags & GFS2_DIF_EXHASH) ?
					     GFS2_FORMAT_DE : 0);
	str->di_depth = cpu_to_be16(di->di_depth);
	str->di_entries = cpu_to_be32(di->di_entries);

	str->di_eattr = cpu_to_be64(di->di_eattr);
	str->di_atime_nsec = cpu_to_be32(ip->i_inode.i_atime.tv_nsec);
	str->di_mtime_nsec = cpu_to_be32(ip->i_inode.i_mtime.tv_nsec);
	str->di_ctime_nsec = cpu_to_be32(ip->i_inode.i_ctime.tv_nsec);
}

void gfs2_dinode_print(const struct gfs2_inode *ip)
{
	const struct gfs2_dinode_host *di = &ip->i_di;

	printk(KERN_INFO "  no_formal_ino = %llu\n",
	       (unsigned long long)ip->i_no_formal_ino);
	printk(KERN_INFO "  no_addr = %llu\n",
	       (unsigned long long)ip->i_no_addr);
	printk(KERN_INFO "  di_size = %llu\n", (unsigned long long)di->di_size);
	printk(KERN_INFO "  di_blocks = %llu\n",
	       (unsigned long long)di->di_blocks);
	printk(KERN_INFO "  di_goal_meta = %llu\n",
	       (unsigned long long)di->di_goal_meta);
	printk(KERN_INFO "  di_goal_data = %llu\n",
	       (unsigned long long)di->di_goal_data);
	printk(KERN_INFO "  di_flags = 0x%.8X\n", di->di_flags);
	printk(KERN_INFO "  di_height = %u\n", di->di_height);
	printk(KERN_INFO "  di_depth = %u\n", di->di_depth);
	printk(KERN_INFO "  di_entries = %u\n", di->di_entries);
	printk(KERN_INFO "  di_eattr = %llu\n",
	       (unsigned long long)di->di_eattr);
}