[PATCH] r/o bind mounts: get callers of vfs_mknod/create/mkdir()

This takes care of all of the direct callers of vfs_mknod().
Since a few of these cases also handle normal file creation
as well, this also covers some calls to vfs_create().

So that we don't have to make three mnt_want/drop_write()
calls inside of the switch statement, we move some of its
logic outside of the switch and into a helper function
suggested by Christoph.

This also encapsulates a fix for mknod(S_IFREG) that Miklos
found.

[AV: merged mkdir handling, added missing nfsd pieces]

Acked-by: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

fs/namei.c

@@ -1984,6 +1984,23 @@ int vfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
 	return error;
 }
 
+static int may_mknod(mode_t mode)
+{
+	switch (mode & S_IFMT) {
+	case S_IFREG:
+	case S_IFCHR:
+	case S_IFBLK:
+	case S_IFIFO:
+	case S_IFSOCK:
+	case 0: /* zero mode translates to S_IFREG */
+		return 0;
+	case S_IFDIR:
+		return -EPERM;
+	default:
+		return -EINVAL;
+	}
+}
+
 asmlinkage long sys_mknodat(int dfd, const char __user *filename, int mode,
 				unsigned dev)
 {
@@ -2002,12 +2019,19 @@ asmlinkage long sys_mknodat(int dfd, const char __user *filename, int mode,
 	if (error)
 		goto out;
 	dentry = lookup_create(&nd, 0);
-	error = PTR_ERR(dentry);
+	if (IS_ERR(dentry)) {
-
+		error = PTR_ERR(dentry);
+		goto out_unlock;
+	}
 	if (!IS_POSIXACL(nd.path.dentry->d_inode))
 		mode &= ~current->fs->umask;
-	if (!IS_ERR(dentry)) {
+	error = may_mknod(mode);
-		switch (mode & S_IFMT) {
+	if (error)
+		goto out_dput;
+	error = mnt_want_write(nd.path.mnt);
+	if (error)
+		goto out_dput;
+	switch (mode & S_IFMT) {
 		case 0: case S_IFREG:
 			error = vfs_create(nd.path.dentry->d_inode,dentry,mode,&nd);
 			break;
@@ -2018,14 +2042,11 @@ asmlinkage long sys_mknodat(int dfd, const char __user *filename, int mode,
 		case S_IFIFO: case S_IFSOCK:
 			error = vfs_mknod(nd.path.dentry->d_inode,dentry,mode,0);
 			break;
-		case S_IFDIR:
-			error = -EPERM;
-			break;
-		default:
-			error = -EINVAL;
-		}
-		dput(dentry);
 	}
+	mnt_drop_write(nd.path.mnt);
+out_dput:
+	dput(dentry);
+out_unlock:
 	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
 	path_put(&nd.path);
 out:
@@ -2083,7 +2104,12 @@ asmlinkage long sys_mkdirat(int dfd, const char __user *pathname, int mode)
 
 	if (!IS_POSIXACL(nd.path.dentry->d_inode))
 		mode &= ~current->fs->umask;
+	error = mnt_want_write(nd.path.mnt);
+	if (error)
+		goto out_dput;
 	error = vfs_mkdir(nd.path.dentry->d_inode, dentry, mode);
+	mnt_drop_write(nd.path.mnt);
+out_dput:
 	dput(dentry);
 out_unlock:
 	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);

fs/nfsd/nfs4recover.c

@@ -155,7 +155,11 @@ nfsd4_create_clid_dir(struct nfs4_client *clp)
 		dprintk("NFSD: nfsd4_create_clid_dir: DIRECTORY EXISTS\n");
 		goto out_put;
 	}
+	status = mnt_want_write(rec_dir.path.mnt);
+	if (status)
+		goto out_put;
 	status = vfs_mkdir(rec_dir.path.dentry->d_inode, dentry, S_IRWXU);
+	mnt_drop_write(rec_dir.path.mnt);
 out_put:
 	dput(dentry);
 out_unlock:

fs/nfsd/vfs.c

@@ -1255,23 +1255,35 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	err = 0;
 	switch (type) {
 	case S_IFREG:
+		host_err = mnt_want_write(fhp->fh_export->ex_path.mnt);
+		if (host_err)
+			goto out_nfserr;
 		host_err = vfs_create(dirp, dchild, iap->ia_mode, NULL);
 		break;
 	case S_IFDIR:
+		host_err = mnt_want_write(fhp->fh_export->ex_path.mnt);
+		if (host_err)
+			goto out_nfserr;
 		host_err = vfs_mkdir(dirp, dchild, iap->ia_mode);
 		break;
 	case S_IFCHR:
 	case S_IFBLK:
 	case S_IFIFO:
 	case S_IFSOCK:
+		host_err = mnt_want_write(fhp->fh_export->ex_path.mnt);
+		if (host_err)
+			goto out_nfserr;
 		host_err = vfs_mknod(dirp, dchild, iap->ia_mode, rdev);
 		break;
 	default:
 	        printk("nfsd: bad file type %o in nfsd_create\n", type);
 		host_err = -EINVAL;
-	}
-	if (host_err < 0)
 		goto out_nfserr;
+	}
+	if (host_err < 0) {
+		mnt_drop_write(fhp->fh_export->ex_path.mnt);
+		goto out_nfserr;
+	}
 
 	if (EX_ISSYNC(fhp->fh_export)) {
 		err = nfserrno(nfsd_sync_dir(dentry));
@@ -1282,6 +1294,7 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	err2 = nfsd_create_setattr(rqstp, resfhp, iap);
 	if (err2)
 		err = err2;
+	mnt_drop_write(fhp->fh_export->ex_path.mnt);
 	/*
 	 * Update the file handle to get the new inode info.
 	 */
@@ -1359,6 +1372,9 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		v_atime = verifier[1]&0x7fffffff;
 	}
 	
+	host_err = mnt_want_write(fhp->fh_export->ex_path.mnt);
+	if (host_err)
+		goto out_nfserr;
 	if (dchild->d_inode) {
 		err = 0;
 
@@ -1390,12 +1406,15 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		case NFS3_CREATE_GUARDED:
 			err = nfserr_exist;
 		}
+		mnt_drop_write(fhp->fh_export->ex_path.mnt);
 		goto out;
 	}
 
 	host_err = vfs_create(dirp, dchild, iap->ia_mode, NULL);
-	if (host_err < 0)
+	if (host_err < 0) {
+		mnt_drop_write(fhp->fh_export->ex_path.mnt);
 		goto out_nfserr;
+	}
 	if (created)
 		*created = 1;
 
@@ -1420,6 +1439,7 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	if (err2)
 		err = err2;
 
+	mnt_drop_write(fhp->fh_export->ex_path.mnt);
 	/*
 	 * Update the filehandle to get the new inode info.
 	 */

net/unix/af_unix.c

@@ -819,7 +819,11 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		 */
 		mode = S_IFSOCK |
 		       (SOCK_INODE(sock)->i_mode & ~current->fs->umask);
+		err = mnt_want_write(nd.path.mnt);
+		if (err)
+			goto out_mknod_dput;
 		err = vfs_mknod(nd.path.dentry->d_inode, dentry, mode, 0);
+		mnt_drop_write(nd.path.mnt);
 		if (err)
 			goto out_mknod_dput;
 		mutex_unlock(&nd.path.dentry->d_inode->i_mutex);