fs: port ->setattr() to pass mnt_idmap

Convert to struct mnt_idmap.

Last cycle we merged the necessary infrastructure in
256c8aed2b42 ("fs: introduce dedicated idmap type for mounts").
This is just the conversion to struct mnt_idmap.

Currently we still pass around the plain namespace that was attached to a
mount. This is in general pretty convenient but it makes it easy to
conflate namespaces that are relevant on the filesystem with namespaces
that are relevent on the mount level. Especially for non-vfs developers
without detailed knowledge in this area this can be a potential source for
bugs.

Once the conversion to struct mnt_idmap is done all helpers down to the
really low-level helpers will take a struct mnt_idmap argument instead of
two namespace arguments. This way it becomes impossible to conflate the two
eliminating the possibility of any bugs. All of the vfs and all filesystems
only operate on struct mnt_idmap.

Acked-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>

88 files changed, 230 insertions, 218 deletions

diff --git a/fs/9p/acl.c b/fs/9p/acl.c
index c397c51f80d9..9848a245fa6f 100644
--- a/fs/9p/acl.c
+++ b/fs/9p/acl.c
@@ -225,7 +225,7 @@ int v9fs_iop_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
 			 * FIXME should we update ctime ?
 			 * What is the following setxattr update the mode ?
 			 */
-			v9fs_vfs_setattr_dotl(&init_user_ns, dentry, &iattr);
+			v9fs_vfs_setattr_dotl(&nop_mnt_idmap, dentry, &iattr);
 		}
 		break;
 	case ACL_TYPE_DEFAULT:
diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h
index bc417da7e9c1..75106b9f293d 100644
--- a/fs/9p/v9fs_vfs.h
+++ b/fs/9p/v9fs_vfs.h
@@ -60,7 +60,7 @@ void v9fs_inode2stat(struct inode *inode, struct p9_wstat *stat);
 int v9fs_uflags2omode(int uflags, int extended);
 
 void v9fs_blank_wstat(struct p9_wstat *wstat);
-int v9fs_vfs_setattr_dotl(struct user_namespace *mnt_userns,
+int v9fs_vfs_setattr_dotl(struct mnt_idmap *idmap,
 			  struct dentry *dentry, struct iattr *iattr);
 int v9fs_file_fsync_dotl(struct file *filp, loff_t start, loff_t end,
 			 int datasync);
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 27a04a226d97..d8cd3f17bbf3 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -1060,13 +1060,13 @@ v9fs_vfs_getattr(struct user_namespace *mnt_userns, const struct path *path,
 
 /**
  * v9fs_vfs_setattr - set file metadata
- * @mnt_userns: The user namespace of the mount
+ * @idmap: idmap of the mount
  * @dentry: file whose metadata to set
  * @iattr: metadata assignment structure
  *
  */
 
-static int v9fs_vfs_setattr(struct user_namespace *mnt_userns,
+static int v9fs_vfs_setattr(struct mnt_idmap *idmap,
 			    struct dentry *dentry, struct iattr *iattr)
 {
 	int retval, use_dentry = 0;
@@ -1077,7 +1077,7 @@ static int v9fs_vfs_setattr(struct user_namespace *mnt_userns,
 	struct p9_wstat wstat;
 
 	p9_debug(P9_DEBUG_VFS, "\n");
-	retval = setattr_prepare(&init_user_ns, dentry, iattr);
+	retval = setattr_prepare(&nop_mnt_idmap, dentry, iattr);
 	if (retval)
 		return retval;
 
@@ -1135,7 +1135,7 @@ static int v9fs_vfs_setattr(struct user_namespace *mnt_userns,
 
 	v9fs_invalidate_inode_attr(inode);
 
-	setattr_copy(&init_user_ns, inode, iattr);
+	setattr_copy(&nop_mnt_idmap, inode, iattr);
 	mark_inode_dirty(inode);
 	return 0;
 }
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index f806b3f11649..dfe6b4017bd0 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -529,13 +529,13 @@ static int v9fs_mapped_iattr_valid(int iattr_valid)
 
 /**
  * v9fs_vfs_setattr_dotl - set file metadata
- * @mnt_userns: The user namespace of the mount
+ * @idmap: idmap of the mount
  * @dentry: file whose metadata to set
  * @iattr: metadata assignment structure
  *
  */
 
-int v9fs_vfs_setattr_dotl(struct user_namespace *mnt_userns,
+int v9fs_vfs_setattr_dotl(struct mnt_idmap *idmap,
 			  struct dentry *dentry, struct iattr *iattr)
 {
 	int retval, use_dentry = 0;
@@ -548,7 +548,7 @@ int v9fs_vfs_setattr_dotl(struct user_namespace *mnt_userns,
 
 	p9_debug(P9_DEBUG_VFS, "\n");
 
-	retval = setattr_prepare(&init_user_ns, dentry, iattr);
+	retval = setattr_prepare(&nop_mnt_idmap, dentry, iattr);
 	if (retval)
 		return retval;
 
@@ -597,7 +597,7 @@ int v9fs_vfs_setattr_dotl(struct user_namespace *mnt_userns,
 		truncate_setsize(inode, iattr->ia_size);
 
 	v9fs_invalidate_inode_attr(inode);
-	setattr_copy(&init_user_ns, inode, iattr);
+	setattr_copy(&nop_mnt_idmap, inode, iattr);
 	mark_inode_dirty(inode);
 	if (iattr->ia_valid & ATTR_MODE) {
 		/* We also want to update ACL when we update mode bits */
diff --git a/fs/adfs/adfs.h b/fs/adfs/adfs.h
index 06b7c92343ad..223f0283d20f 100644
--- a/fs/adfs/adfs.h
+++ b/fs/adfs/adfs.h
@@ -144,7 +144,7 @@ struct adfs_discmap {
 /* Inode stuff */
 struct inode *adfs_iget(struct super_block *sb, struct object_info *obj);
 int adfs_write_inode(struct inode *inode, struct writeback_control *wbc);
-int adfs_notify_change(struct user_namespace *mnt_userns, struct dentry *dentry,
+int adfs_notify_change(struct mnt_idmap *idmap, struct dentry *dentry,
 		       struct iattr *attr);
 
 /* map.c */
diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c
index ee22278b0cfc..c3ac613d0975 100644
--- a/fs/adfs/inode.c
+++ b/fs/adfs/inode.c
@@ -294,7 +294,7 @@ out:
  * later.
  */
 int
-adfs_notify_change(struct user_namespace *mnt_userns, struct dentry *dentry,
+adfs_notify_change(struct mnt_idmap *idmap, struct dentry *dentry,
 		   struct iattr *attr)
 {
 	struct inode *inode = d_inode(dentry);
@@ -302,7 +302,7 @@ adfs_notify_change(struct user_namespace *mnt_userns, struct dentry *dentry,
 	unsigned int ia_valid = attr->ia_valid;
 	int error;
 	
-	error = setattr_prepare(&init_user_ns, dentry, attr);
+	error = setattr_prepare(&nop_mnt_idmap, dentry, attr);
 
 	/*
 	 * we can't change the UID or GID of any file -
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index bfa89e131ead..8c98e2644a5e 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -185,7 +185,7 @@ extern int	affs_rename2(struct user_namespace *mnt_userns,
 /* inode.c */
 
 extern struct inode		*affs_new_inode(struct inode *dir);
-extern int			 affs_notify_change(struct user_namespace *mnt_userns,
+extern int			 affs_notify_change(struct mnt_idmap *idmap,
 					struct dentry *dentry, struct iattr *attr);
 extern void			 affs_evict_inode(struct inode *inode);
 extern struct inode		*affs_iget(struct super_block *sb,
diff --git a/fs/affs/inode.c b/fs/affs/inode.c
index 2352a75bd9d6..27f77a52c5c8 100644
--- a/fs/affs/inode.c
+++ b/fs/affs/inode.c
@@ -216,7 +216,7 @@ affs_write_inode(struct inode *inode, struct writeback_control *wbc)
 }
 
 int
-affs_notify_change(struct user_namespace *mnt_userns, struct dentry *dentry,
+affs_notify_change(struct mnt_idmap *idmap, struct dentry *dentry,
 		   struct iattr *attr)
 {
 	struct inode *inode = d_inode(dentry);
@@ -224,7 +224,7 @@ affs_notify_change(struct user_namespace *mnt_userns, struct dentry *dentry,
 
 	pr_debug("notify_change(%lu,0x%x)\n", inode->i_ino, attr->ia_valid);
 
-	error = setattr_prepare(&init_user_ns, dentry, attr);
+	error = setattr_prepare(&nop_mnt_idmap, dentry, attr);
 	if (error)
 		goto out;
 
@@ -250,7 +250,7 @@ affs_notify_change(struct user_namespace *mnt_userns, struct dentry *dentry,
 		affs_truncate(inode);
 	}
 
-	setattr_copy(&init_user_ns, inode, attr);
+	setattr_copy(&nop_mnt_idmap, inode, attr);
 	mark_inode_dirty(inode);
 
 	if (attr->ia_valid & ATTR_MODE)
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 6d3a3dbe4928..f001cf1750ec 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -870,7 +870,7 @@ static const struct afs_operation_ops afs_setattr_operation = {
 /*
  * set the attributes of an inode
  */
-int afs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+int afs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		struct iattr *attr)
 {
 	const unsigned int supported =
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index fd8567b98e2b..e2a23efc91b6 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -1172,7 +1172,7 @@ extern bool afs_check_validity(struct afs_vnode *);
 extern int afs_validate(struct afs_vnode *, struct key *);
 extern int afs_getattr(struct user_namespace *mnt_userns, const struct path *,
 		       struct kstat *, u32, unsigned int);
-extern int afs_setattr(struct user_namespace *mnt_userns, struct dentry *, struct iattr *);
+extern int afs_setattr(struct mnt_idmap *idmap, struct dentry *, struct iattr *);
 extern void afs_evict_inode(struct inode *);
 extern int afs_drop_inode(struct inode *);
 
diff --git a/fs/attr.c b/fs/attr.c
index 023a3860568a..39d35621e57b 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -142,7 +142,7 @@ static bool chgrp_ok(struct user_namespace *mnt_userns,
 
 /**
  * setattr_prepare - check if attribute changes to a dentry are allowed
- * @mnt_userns:	user namespace of the mount the inode was found from
+ * @idmap:	idmap of the mount the inode was found from
  * @dentry:	dentry to check
  * @attr:	attributes to change
  *
@@ -152,18 +152,19 @@ static bool chgrp_ok(struct user_namespace *mnt_userns,
  * SGID bit from mode if user is not allowed to set it. Also file capabilities
  * and IMA extended attributes are cleared if ATTR_KILL_PRIV is set.
  *
- * If the inode has been found through an idmapped mount the user namespace of
- * the vfsmount must be passed through @mnt_userns. This function will then
- * take care to map the inode according to @mnt_userns before checking
+ * If the inode has been found through an idmapped mount the idmap of
+ * the vfsmount must be passed through @idmap. This function will then
+ * take care to map the inode according to @idmap before checking
  * permissions. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs init_user_ns.
+ * performed on the raw inode simply passs @nop_mnt_idmap.
  *
  * Should be called as the first thing in ->setattr implementations,
  * possibly after taking additional locks.
  */
-int setattr_prepare(struct user_namespace *mnt_userns, struct dentry *dentry,
+int setattr_prepare(struct mnt_idmap *idmap, struct dentry *dentry,
 		    struct iattr *attr)
 {
+	struct user_namespace *mnt_userns = mnt_idmap_owner(idmap);
 	struct inode *inode = d_inode(dentry);
 	unsigned int ia_valid = attr->ia_valid;
 
@@ -276,7 +277,7 @@ EXPORT_SYMBOL(inode_newsize_ok);
 
 /**
  * setattr_copy - copy simple metadata updates into the generic inode
- * @mnt_userns:	user namespace of the mount the inode was found from
+ * @idmap:	idmap of the mount the inode was found from
  * @inode:	the inode to be updated
  * @attr:	the new attributes
  *
@@ -289,19 +290,20 @@ EXPORT_SYMBOL(inode_newsize_ok);
  * Noticeably missing is inode size update, which is more complex
  * as it requires pagecache updates.
  *
- * If the inode has been found through an idmapped mount the user namespace of
- * the vfsmount must be passed through @mnt_userns. This function will then
- * take care to map the inode according to @mnt_userns before checking
+ * If the inode has been found through an idmapped mount the idmap of
+ * the vfsmount must be passed through @idmap. This function will then
+ * take care to map the inode according to @idmap before checking
  * permissions. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs init_user_ns.
+ * performed on the raw inode simply pass @nop_mnt_idmap.
  *
  * The inode is not marked as dirty after this operation. The rationale is
  * that for "simple" filesystems, the struct inode is the inode storage.
  * The caller is free to mark the inode dirty afterwards if needed.
  */
-void setattr_copy(struct user_namespace *mnt_userns, struct inode *inode,
+void setattr_copy(struct mnt_idmap *idmap, struct inode *inode,
 		  const struct iattr *attr)
 {
+	struct user_namespace *mnt_userns = mnt_idmap_owner(idmap);
 	unsigned int ia_valid = attr->ia_valid;
 
 	i_uid_update(mnt_userns, attr, inode);
@@ -472,7 +474,7 @@ int notify_change(struct mnt_idmap *idmap, struct dentry *dentry,
 	    !vfsgid_valid(i_gid_into_vfsgid(mnt_userns, inode)))
 		return -EOVERFLOW;
 
-	error = security_inode_setattr(mnt_userns, dentry, attr);
+	error = security_inode_setattr(idmap, dentry, attr);
 	if (error)
 		return error;
 	error = try_break_deleg(inode, delegated_inode);
@@ -480,9 +482,9 @@ int notify_change(struct mnt_idmap *idmap, struct dentry *dentry,
 		return error;
 
 	if (inode->i_op->setattr)
-		error = inode->i_op->setattr(mnt_userns, dentry, attr);
+		error = inode->i_op->setattr(idmap, dentry, attr);
 	else
-		error = simple_setattr(mnt_userns, dentry, attr);
+		error = simple_setattr(idmap, dentry, attr);
 
 	if (!error) {
 		fsnotify_change(dentry, ia_valid);
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index 92737166203f..9cb95ff99047 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -102,7 +102,7 @@ static int bad_inode_getattr(struct user_namespace *mnt_userns,
 	return -EIO;
 }
 
-static int bad_inode_setattr(struct user_namespace *mnt_userns,
+static int bad_inode_setattr(struct mnt_idmap *idmap,
 			     struct dentry *direntry, struct iattr *attrs)
 {
 	return -EIO;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 8bcad9940154..36a897e5d8de 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5281,7 +5281,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 	return ret;
 }
 
-static int btrfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+static int btrfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 			 struct iattr *attr)
 {
 	struct inode *inode = d_inode(dentry);
@@ -5291,7 +5291,7 @@ static int btrfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentr
 	if (btrfs_root_readonly(root))
 		return -EROFS;
 
-	err = setattr_prepare(mnt_userns, dentry, attr);
+	err = setattr_prepare(idmap, dentry, attr);
 	if (err)
 		return err;
 
@@ -5302,12 +5302,13 @@ static int btrfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentr
 	}
 
 	if (attr->ia_valid) {
-		setattr_copy(mnt_userns, inode, attr);
+		setattr_copy(idmap, inode, attr);
 		inode_inc_iversion(inode);
 		err = btrfs_dirty_inode(BTRFS_I(inode));
 
 		if (!err && attr->ia_valid & ATTR_MODE)
-			err = posix_acl_chmod(mnt_userns, dentry, inode->i