vfs.c

linux 内核源代码

}

int
nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry, struct nfs4_acl **acl)
{
	struct inode *inode = dentry->d_inode;
	int error = 0;
	struct posix_acl *pacl = NULL, *dpacl = NULL;
	unsigned int flags = 0;

	pacl = _get_posix_acl(dentry, POSIX_ACL_XATTR_ACCESS);
	if (IS_ERR(pacl) && PTR_ERR(pacl) == -ENODATA)
		pacl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
	if (IS_ERR(pacl)) {
		error = PTR_ERR(pacl);
		pacl = NULL;
		goto out;
	}

	if (S_ISDIR(inode->i_mode)) {
		dpacl = _get_posix_acl(dentry, POSIX_ACL_XATTR_DEFAULT);
		if (IS_ERR(dpacl) && PTR_ERR(dpacl) == -ENODATA)
			dpacl = NULL;
		else if (IS_ERR(dpacl)) {
			error = PTR_ERR(dpacl);
			dpacl = NULL;
			goto out;
		}
		flags = NFS4_ACL_DIR;
	}

	*acl = nfs4_acl_posix_to_nfsv4(pacl, dpacl, flags);
	if (IS_ERR(*acl)) {
		error = PTR_ERR(*acl);
		*acl = NULL;
	}
 out:
	posix_acl_release(pacl);
	posix_acl_release(dpacl);
	return error;
}

#endif /* defined(CONFIG_NFS_V4) */

#ifdef CONFIG_NFSD_V3
/*
 * Check server access rights to a file system object
 */
struct accessmap {
	u32		access;
	int		how;
};
static struct accessmap	nfs3_regaccess[] = {
    {	NFS3_ACCESS_READ,	MAY_READ			},
    {	NFS3_ACCESS_EXECUTE,	MAY_EXEC			},
    {	NFS3_ACCESS_MODIFY,	MAY_WRITE|MAY_TRUNC		},
    {	NFS3_ACCESS_EXTEND,	MAY_WRITE			},

    {	0,			0				}
};

static struct accessmap	nfs3_diraccess[] = {
    {	NFS3_ACCESS_READ,	MAY_READ			},
    {	NFS3_ACCESS_LOOKUP,	MAY_EXEC			},
    {	NFS3_ACCESS_MODIFY,	MAY_EXEC|MAY_WRITE|MAY_TRUNC	},
    {	NFS3_ACCESS_EXTEND,	MAY_EXEC|MAY_WRITE		},
    {	NFS3_ACCESS_DELETE,	MAY_REMOVE			},

    {	0,			0				}
};

static struct accessmap	nfs3_anyaccess[] = {
	/* Some clients - Solaris 2.6 at least, make an access call
	 * to the server to check for access for things like /dev/null
	 * (which really, the server doesn't care about).  So
	 * We provide simple access checking for them, looking
	 * mainly at mode bits, and we make sure to ignore read-only
	 * filesystem checks
	 */
    {	NFS3_ACCESS_READ,	MAY_READ			},
    {	NFS3_ACCESS_EXECUTE,	MAY_EXEC			},
    {	NFS3_ACCESS_MODIFY,	MAY_WRITE|MAY_LOCAL_ACCESS	},
    {	NFS3_ACCESS_EXTEND,	MAY_WRITE|MAY_LOCAL_ACCESS	},

    {	0,			0				}
};

__be32
nfsd_access(struct svc_rqst *rqstp, struct svc_fh *fhp, u32 *access, u32 *supported)
{
	struct accessmap	*map;
	struct svc_export	*export;
	struct dentry		*dentry;
	u32			query, result = 0, sresult = 0;
	__be32			error;

	error = fh_verify(rqstp, fhp, 0, MAY_NOP);
	if (error)
		goto out;

	export = fhp->fh_export;
	dentry = fhp->fh_dentry;

	if (S_ISREG(dentry->d_inode->i_mode))
		map = nfs3_regaccess;
	else if (S_ISDIR(dentry->d_inode->i_mode))
		map = nfs3_diraccess;
	else
		map = nfs3_anyaccess;


	query = *access;
	for  (; map->access; map++) {
		if (map->access & query) {
			__be32 err2;

			sresult |= map->access;

			err2 = nfsd_permission(rqstp, export, dentry, map->how);
			switch (err2) {
			case nfs_ok:
				result |= map->access;
				break;
				
			/* the following error codes just mean the access was not allowed,
			 * rather than an error occurred */
			case nfserr_rofs:
			case nfserr_acces:
			case nfserr_perm:
				/* simply don't "or" in the access bit. */
				break;
			default:
				error = err2;
				goto out;
			}
		}
	}
	*access = result;
	if (supported)
		*supported = sresult;

 out:
	return error;
}
#endif /* CONFIG_NFSD_V3 */



/*
 * Open an existing file or directory.
 * The access argument indicates the type of open (read/write/lock)
 * N.B. After this call fhp needs an fh_put
 */
__be32
nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
			int access, struct file **filp)
{
	struct dentry	*dentry;
	struct inode	*inode;
	int		flags = O_RDONLY|O_LARGEFILE;
	__be32		err;
	int		host_err;

	/*
	 * If we get here, then the client has already done an "open",
	 * and (hopefully) checked permission - so allow OWNER_OVERRIDE
	 * in case a chmod has now revoked permission.
	 */
	err = fh_verify(rqstp, fhp, type, access | MAY_OWNER_OVERRIDE);
	if (err)
		goto out;

	dentry = fhp->fh_dentry;
	inode = dentry->d_inode;

	/* Disallow write access to files with the append-only bit set
	 * or any access when mandatory locking enabled
	 */
	err = nfserr_perm;
	if (IS_APPEND(inode) && (access & MAY_WRITE))
		goto out;
	/*
	 * We must ignore files (but only files) which might have mandatory
	 * locks on them because there is no way to know if the accesser has
	 * the lock.
	 */
	if (S_ISREG((inode)->i_mode) && mandatory_lock(inode))
		goto out;

	if (!inode->i_fop)
		goto out;

	/*
	 * Check to see if there are any leases on this file.
	 * This may block while leases are broken.
	 */
	host_err = break_lease(inode, O_NONBLOCK | ((access & MAY_WRITE) ? FMODE_WRITE : 0));
	if (host_err == -EWOULDBLOCK)
		host_err = -ETIMEDOUT;
	if (host_err) /* NOMEM or WOULDBLOCK */
		goto out_nfserr;

	if (access & MAY_WRITE) {
		if (access & MAY_READ)
			flags = O_RDWR|O_LARGEFILE;
		else
			flags = O_WRONLY|O_LARGEFILE;

		DQUOT_INIT(inode);
	}
	*filp = dentry_open(dget(dentry), mntget(fhp->fh_export->ex_mnt), flags);
	if (IS_ERR(*filp))
		host_err = PTR_ERR(*filp);
out_nfserr:
	err = nfserrno(host_err);
out:
	return err;
}

/*
 * Close a file.
 */
void
nfsd_close(struct file *filp)
{
	fput(filp);
}

/*
 * Sync a file
 * As this calls fsync (not fdatasync) there is no need for a write_inode
 * after it.
 */
static inline int nfsd_dosync(struct file *filp, struct dentry *dp,
			      const struct file_operations *fop)
{
	struct inode *inode = dp->d_inode;
	int (*fsync) (struct file *, struct dentry *, int);
	int err;

	err = filemap_fdatawrite(inode->i_mapping);
	if (err == 0 && fop && (fsync = fop->fsync))
		err = fsync(filp, dp, 0);
	if (err == 0)
		err = filemap_fdatawait(inode->i_mapping);

	return err;
}
	

static int
nfsd_sync(struct file *filp)
{
        int err;
	struct inode *inode = filp->f_path.dentry->d_inode;
	dprintk("nfsd: sync file %s\n", filp->f_path.dentry->d_name.name);
	mutex_lock(&inode->i_mutex);
	err=nfsd_dosync(filp, filp->f_path.dentry, filp->f_op);
	mutex_unlock(&inode->i_mutex);

	return err;
}

int
nfsd_sync_dir(struct dentry *dp)
{
	return nfsd_dosync(NULL, dp, dp->d_inode->i_fop);
}

/*
 * Obtain the readahead parameters for the file
 * specified by (dev, ino).
 */

static inline struct raparms *
nfsd_get_raparms(dev_t dev, ino_t ino)
{
	struct raparms	*ra, **rap, **frap = NULL;
	int depth = 0;
	unsigned int hash;
	struct raparm_hbucket *rab;

	hash = jhash_2words(dev, ino, 0xfeedbeef) & RAPARM_HASH_MASK;
	rab = &raparm_hash[hash];

	spin_lock(&rab->pb_lock);
	for (rap = &rab->pb_head; (ra = *rap); rap = &ra->p_next) {
		if (ra->p_ino == ino && ra->p_dev == dev)
			goto found;
		depth++;
		if (ra->p_count == 0)
			frap = rap;
	}
	depth = nfsdstats.ra_size*11/10;
	if (!frap) {	
		spin_unlock(&rab->pb_lock);
		return NULL;
	}
	rap = frap;
	ra = *frap;
	ra->p_dev = dev;
	ra->p_ino = ino;
	ra->p_set = 0;
	ra->p_hindex = hash;
found:
	if (rap != &rab->pb_head) {
		*rap = ra->p_next;
		ra->p_next   = rab->pb_head;
		rab->pb_head = ra;
	}
	ra->p_count++;
	nfsdstats.ra_depth[depth*10/nfsdstats.ra_size]++;
	spin_unlock(&rab->pb_lock);
	return ra;
}

/*
 * Grab and keep cached pages associated with a file in the svc_rqst
 * so that they can be passed to the network sendmsg/sendpage routines
 * directly. They will be released after the sending has completed.
 */
static int
nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
		  struct splice_desc *sd)
{
	struct svc_rqst *rqstp = sd->u.data;
	struct page **pp = rqstp->rq_respages + rqstp->rq_resused;
	struct page *page = buf->page;
	size_t size;
	int ret;

	ret = buf->ops->confirm(pipe, buf);
	if (unlikely(ret))
		return ret;

	size = sd->len;

	if (rqstp->rq_res.page_len == 0) {
		get_page(page);
		put_page(*pp);
		*pp = page;
		rqstp->rq_resused++;
		rqstp->rq_res.page_base = buf->offset;
		rqstp->rq_res.page_len = size;
	} else if (page != pp[-1]) {
		get_page(page);
		if (*pp)
			put_page(*pp);
		*pp = page;
		rqstp->rq_resused++;
		rqstp->rq_res.page_len += size;
	} else
		rqstp->rq_res.page_len += size;

	return size;
}

static int nfsd_direct_splice_actor(struct pipe_inode_info *pipe,
				    struct splice_desc *sd)
{
	return __splice_from_pipe(pipe, sd, nfsd_splice_actor);
}

static inline int svc_msnfs(struct svc_fh *ffhp)
{
#ifdef MSNFS
	return (ffhp->fh_export->ex_flags & NFSEXP_MSNFS);
#else
	return 0;
#endif
}

static __be32
nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
              loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
{
	struct inode *inode;
	struct raparms	*ra;
	mm_segment_t	oldfs;
	__be32		err;
	int		host_err;

	err = nfserr_perm;
	inode = file->f_path.dentry->d_inode;

	if (svc_msnfs(fhp) && !lock_may_read(inode, offset, *count))
		goto out;

	/* Get readahead parameters */
	ra = nfsd_get_raparms(inode->i_sb->s_dev, inode->i_ino);

	if (ra && ra->p_set)
		file->f_ra = ra->p_ra;

	if (file->f_op->splice_read && rqstp->rq_splice_ok) {
		struct splice_desc sd = {
			.len		= 0,
			.total_len	= *count,
			.pos		= offset,
			.u.data		= rqstp,
		};

		rqstp->rq_resused = 1;
		host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor);
	} else {
		oldfs = get_fs();
		set_fs(KERNEL_DS);
		host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset);
		set_fs(oldfs);
	}

	/* Write back readahead params */
	if (ra) {
		struct raparm_hbucket *rab = &raparm_hash[ra->p_hindex];
		spin_lock(&rab->pb_lock);
		ra->p_ra = file->f_ra;
		ra->p_set = 1;
		ra->p_count--;
		spin_unlock(&rab->pb_lock);
	}

	if (host_err >= 0) {
		nfsdstats.io_read += host_err;
		*count = host_err;
		err = 0;
		fsnotify_access(file->f_path.dentry);
	} else 
		err = nfserrno(host_err);
out:
	return err;
}

static void kill_suid(struct dentry *dentry)
{
	struct iattr	ia;
	ia.ia_valid = ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;

	mutex_lock(&dentry->d_inode->i_mutex);
	notify_change(dentry, &ia);
	mutex_unlock(&dentry->d_inode->i_mutex);
}

static __be32
nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
				loff_t offset, struct kvec *vec, int vlen,
	   			unsigned long cnt, int *stablep)
{
	struct svc_export	*exp;
	struct dentry		*dentry;
	struct inode		*inode;
	mm_segment_t		oldfs;
	__be32			err = 0;
	int			host_err;
	int			stable = *stablep;

#ifdef MSNFS
	err = nfserr_perm;

	if ((fhp->fh_export->ex_flags & NFSEXP_MSNFS) &&
		(!lock_may_write(file->f_path.dentry->d_inode, offset, cnt)))
		goto out;
#endif

	dentry = file->f_path.dentry;
	inode = dentry->d_inode;
	exp   = fhp->fh_export;

	/*
	 * Request sync writes if
	 *  -	the sync export option has been set, or
	 *  -	the client requested O_SYNC behavior (NFSv3 feature).
	 *  -   The file system doesn't support fsync().
	 * When gathered writes have been configured for this volume,
	 * flushing the data to disk is handled separately below.
	 */

	if (file->f_op->fsync == 0) {/* COMMIT3 cannot work */
	       stable = 2;
	       *stablep = 2; /* FILE_SYNC */
	}

	if (!EX_ISSYNC(exp))
		stable = 0;
	if (stable && !EX_WGATHER(exp))
		file->f_flags |= O_SYNC;

	/* Write the data. */
	oldfs = get_fs(); set_fs(KERNEL_DS);
	host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &offset);
	set_fs(oldfs);
	if (host_err >= 0) {
		nfsdstats.io_write += cnt;
		fsnotify_modify(file->f_path.dentry);
	}

	/* clear setuid/setgid flag after write */
	if (host_err >= 0 && (inode->i_mode & (S_ISUID | S_ISGID)))
		kill_suid(dentry);

	if (host_err >= 0 && stable) {
		static ino_t	last_ino;
		static dev_t	last_dev;

		/*
		 * Gathered writes: If another process is currently
		 * writing to the file, there's a high chance
		 * this is another nfsd (triggered by a bulk write
		 * from a client's biod). Rather than syncing the
		 * file with each write request, we sleep for 10 msec.
		 *
		 * I don't know if this roughly approximates
		 * C. Juszak's idea of gathered writes, but it's a
		 * nice and simple solution (IMHO), and it seems to