fs: port ->permission() 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>

84 files changed, 422 insertions, 421 deletions

diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
index fb23ffc0792c..d2750085a1f5 100644
--- a/Documentation/filesystems/locking.rst
+++ b/Documentation/filesystems/locking.rst
@@ -69,7 +69,7 @@ prototypes::
 	int (*readlink) (struct dentry *, char __user *,int);
 	const char *(*get_link) (struct dentry *, struct inode *, struct delayed_call *);
 	void (*truncate) (struct inode *);
-	int (*permission) (struct inode *, int, unsigned int);
+	int (*permission) (struct mnt_idmap *, struct inode *, int, unsigned int);
 	struct posix_acl * (*get_inode_acl)(struct inode *, int, bool);
 	int (*setattr) (struct mnt_idmap *, struct dentry *, struct iattr *);
 	int (*getattr) (struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int);
diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst
index bf5cc9809b65..c53f30251a66 100644
--- a/Documentation/filesystems/vfs.rst
+++ b/Documentation/filesystems/vfs.rst
@@ -434,7 +434,7 @@ As of kernel 2.6.22, the following members are defined:
 		int (*readlink) (struct dentry *, char __user *,int);
 		const char *(*get_link) (struct dentry *, struct inode *,
 					 struct delayed_call *);
-		int (*permission) (struct user_namespace *, struct inode *, int);
+		int (*permission) (struct mnt_idmap *, struct inode *, int);
 		struct posix_acl * (*get_inode_acl)(struct inode *, int, bool);
 		int (*setattr) (struct mnt_idmap *, struct dentry *, struct iattr *);
 		int (*getattr) (struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int);
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index d5e7cd465593..e3375b2a0ff3 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -1387,7 +1387,7 @@ extern void afs_cache_permit(struct afs_vnode *, struct key *, unsigned int,
 extern struct key *afs_request_key(struct afs_cell *);
 extern struct key *afs_request_key_rcu(struct afs_cell *);
 extern int afs_check_permit(struct afs_vnode *, struct key *, afs_access_t *);
-extern int afs_permission(struct user_namespace *, struct inode *, int);
+extern int afs_permission(struct mnt_idmap *, struct inode *, int);
 extern void __exit afs_clean_up_permit_cache(void);
 
 /*
diff --git a/fs/afs/security.c b/fs/afs/security.c
index 7c6a63a30394..6a7744c9e2a2 100644
--- a/fs/afs/security.c
+++ b/fs/afs/security.c
@@ -395,7 +395,7 @@ int afs_check_permit(struct afs_vnode *vnode, struct key *key,
  * - AFS ACLs are attached to directories only, and a file is controlled by its
  *   parent directory's ACL
  */
-int afs_permission(struct user_namespace *mnt_userns, struct inode *inode,
+int afs_permission(struct mnt_idmap *idmap, struct inode *inode,
 		   int mask)
 {
 	struct afs_vnode *vnode = AFS_FS_I(inode);
diff --git a/fs/attr.c b/fs/attr.c
index 39d35621e57b..48897e036ce9 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -324,10 +324,11 @@ void setattr_copy(struct mnt_idmap *idmap, struct inode *inode,
 }
 EXPORT_SYMBOL(setattr_copy);
 
-int may_setattr(struct user_namespace *mnt_userns, struct inode *inode,
+int may_setattr(struct mnt_idmap *idmap, struct inode *inode,
 		unsigned int ia_valid)
 {
 	int error;
+	struct user_namespace *mnt_userns = mnt_idmap_owner(idmap);
 
 	if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) {
 		if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
@@ -343,7 +344,7 @@ int may_setattr(struct user_namespace *mnt_userns, struct inode *inode,
 			return -EPERM;
 
 		if (!inode_owner_or_capable(mnt_userns, inode)) {
-			error = inode_permission(mnt_userns, inode, MAY_WRITE);
+			error = inode_permission(idmap, inode, MAY_WRITE);
 			if (error)
 				return error;
 		}
@@ -391,7 +392,7 @@ int notify_change(struct mnt_idmap *idmap, struct dentry *dentry,
 
 	WARN_ON_ONCE(!inode_is_locked(inode));
 
-	error = may_setattr(mnt_userns, inode, ia_valid);
+	error = may_setattr(idmap, inode, ia_valid);
 	if (error)
 		return error;
 
diff --git a/fs/autofs/root.c b/fs/autofs/root.c
index cbc0da00a3cf..6baf90b08e0e 100644
--- a/fs/autofs/root.c
+++ b/fs/autofs/root.c
@@ -10,7 +10,7 @@
 
 #include "autofs_i.h"
 
-static int autofs_dir_permission(struct user_namespace *, struct inode *, int);
+static int autofs_dir_permission(struct mnt_idmap *, struct inode *, int);
 static int autofs_dir_symlink(struct mnt_idmap *, struct inode *,
 			      struct dentry *, const char *);
 static int autofs_dir_unlink(struct inode *, struct dentry *);
@@ -543,7 +543,7 @@ static struct dentry *autofs_lookup(struct inode *dir,
 	return NULL;
 }
 
-static int autofs_dir_permission(struct user_namespace *mnt_userns,
+static int autofs_dir_permission(struct mnt_idmap *idmap,
 				 struct inode *inode, int mask)
 {
 	if (mask & MAY_WRITE) {
@@ -560,7 +560,7 @@ static int autofs_dir_permission(struct user_namespace *mnt_userns,
 			return -EACCES;
 	}
 
-	return generic_permission(mnt_userns, inode, mask);
+	return generic_permission(idmap, inode, mask);
 }
 
 static int autofs_dir_symlink(struct mnt_idmap *idmap,
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index 350ad3461129..db649487d58c 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -89,7 +89,7 @@ static int bad_inode_readlink(struct dentry *dentry, char __user *buffer,
 	return -EIO;
 }
 
-static int bad_inode_permission(struct user_namespace *mnt_userns,
+static int bad_inode_permission(struct mnt_idmap *idmap,
 				struct inode *inode, int mask)
 {
 	return -EIO;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 6a74767b12cb..5251547fdf0b 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -10078,7 +10078,7 @@ int btrfs_prealloc_file_range_trans(struct inode *inode,
 					   min_size, actual_len, alloc_hint, trans);
 }
 
-static int btrfs_permission(struct user_namespace *mnt_userns,
+static int btrfs_permission(struct mnt_idmap *idmap,
 			    struct inode *inode, int mask)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -10091,7 +10091,7 @@ static int btrfs_permission(struct user_namespace *mnt_userns,
 		if (BTRFS_I(inode)->flags & BTRFS_INODE_READONLY)
 			return -EACCES;
 	}
-	return generic_permission(mnt_userns, inode, mask);
+	return generic_permission(idmap, inode, mask);
 }
 
 static int btrfs_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index f23d0d399b9f..80c7feb30770 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -898,10 +898,11 @@ free_pending:
  *     nfs_async_unlink().
  */
 
-static int btrfs_may_delete(struct user_namespace *mnt_userns,
+static int btrfs_may_delete(struct mnt_idmap *idmap,
 			    struct inode *dir, struct dentry *victim, int isdir)
 {
 	int error;
+	struct user_namespace *mnt_userns = mnt_idmap_owner(idmap);
 
 	if (d_really_is_negative(victim))
 		return -ENOENT;
@@ -909,7 +910,7 @@ static int btrfs_may_delete(struct user_namespace *mnt_userns,
 	BUG_ON(d_inode(victim->d_parent) != dir);
 	audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
 
-	error = inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC);
+	error = inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC);
 	if (error)
 		return error;
 	if (IS_APPEND(dir))
@@ -933,16 +934,16 @@ static int btrfs_may_delete(struct user_namespace *mnt_userns,
 }
 
 /* copy of may_create in fs/namei.c() */
-static inline int btrfs_may_create(struct user_namespace *mnt_userns,
+static inline int btrfs_may_create(struct mnt_idmap *idmap,
 				   struct inode *dir, struct dentry *child)
 {
 	if (d_really_is_positive(child))
 		return -EEXIST;
 	if (IS_DEADDIR(dir))
 		return -ENOENT;
-	if (!fsuidgid_has_mapping(dir->i_sb, mnt_userns))
+	if (!fsuidgid_has_mapping(dir->i_sb, idmap))
 		return -EOVERFLOW;
-	return inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC);
+	return inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC);
 }
 
 /*
@@ -951,7 +952,7 @@ static inline int btrfs_may_create(struct user_namespace *mnt_userns,
  * inside this filesystem so it's quite a bit simpler.
  */
 static noinline int btrfs_mksubvol(const struct path *parent,
-				   struct user_namespace *mnt_userns,
+				   struct mnt_idmap *idmap,
 				   const char *name, int namelen,
 				   struct btrfs_root *snap_src,
 				   bool readonly,
@@ -961,18 +962,19 @@ static noinline int btrfs_mksubvol(const struct path *parent,
 	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
 	struct dentry *dentry;
 	struct fscrypt_str name_str = FSTR_INIT((char *)name, namelen);
+	struct user_namespace *mnt_userns = mnt_idmap_owner(idmap);
 	int error;
 
 	error = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT);
 	if (error == -EINTR)
 		return error;
 
-	dentry = lookup_one(mnt_userns, name, parent->dentry, namelen);
+	dentry = lookup_one(idmap, name, parent->dentry, namelen);
 	error = PTR_ERR(dentry);
 	if (IS_ERR(dentry))
 		goto out_unlock;
 
-	error = btrfs_may_create(mnt_userns, dir, dentry);
+	error = btrfs_may_create(idmap, dir, dentry);
 	if (error)
 		goto out_dput;
 
@@ -1007,7 +1009,7 @@ out_unlock:
 }
 
 static noinline int btrfs_mksnapshot(const struct path *parent,
-				   struct user_namespace *mnt_userns,
+				   struct mnt_idmap *idmap,
 				   const char *name, int namelen,
 				   struct btrfs_root *root,
 				   bool readonly,
@@ -1037,7 +1039,7 @@ static noinline int btrfs_mksnapshot(const struct path *parent,
 
 	btrfs_wait_ordered_extents(root, U64_MAX, 0, (u64)-1);
 
-	ret = btrfs_mksubvol(parent, mnt_userns, name, namelen,
+	ret = btrfs_mksubvol(parent, idmap, name, namelen,
 			     root, readonly, inherit);
 out:
 	if (snapshot_force_cow)
@@ -1240,13 +1242,14 @@ out_drop:
 }
 
 static noinline int __btrfs_ioctl_snap_create(struct file *file,
-				struct user_namespace *mnt_userns,
+				struct mnt_idmap *idmap,
 				const char *name, unsigned long fd, int subvol,
 				bool readonly,
 				struct btrfs_qgroup_inherit *inherit)
 {
 	int namelen;
 	int ret = 0;
+	struct user_namespace *mnt_userns = mnt_idmap_owner(idmap);
 
 	if (!S_ISDIR(file_inode(file)->i_mode))
 		return -ENOTDIR;
@@ -1268,7 +1271,7 @@ static noinline int __btrfs_ioctl_snap_create(struct file *file,
 	}
 
 	if (subvol) {
-		ret = btrfs_mksubvol(&file->f_path, mnt_userns, name,
+		ret = btrfs_mksubvol(&file->f_path, idmap, name,
 				     namelen, NULL, readonly, inherit);
 	} else {
 		struct fd src = fdget(fd);
@@ -1290,7 +1293,7 @@ static noinline int __btrfs_ioctl_snap_create(struct file *file,
 			 */
 			ret = -EPERM;
 		} else {
-			ret = btrfs_mksnapshot(&file->f_path, mnt_userns,
+			ret = btrfs_mksnapshot(&file->f_path, idmap,
 					       name, namelen,
 					       BTRFS_I(src_inode)->root,
 					       readonly, inherit);
@@ -1317,7 +1320,7 @@ static noinline int btrfs_ioctl_snap_create(struct file *file,
 		return PTR_ERR(vol_args);
 	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
 
-	ret = __btrfs_ioctl_snap_create(file, file_mnt_user_ns(file),
+	ret = __btrfs_ioctl_snap_create(file, file_mnt_idmap(file),
 					vol_args->name, vol_args->fd, subvol,
 					false, NULL);
 
@@ -1377,7 +1380,7 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file,
 		}
 	}
 
-	ret = __btrfs_ioctl_snap_create(file, file_mnt_user_ns(file),
+	ret = __btrfs_ioctl_snap_create(file, file_mnt_idmap(file),
 					vol_args->name, vol_args->fd, subvol,
 					readonly, inherit);
 	if (ret)
@@ -1870,7 +1873,7 @@ out:
 	return ret;
 }
 
-static int btrfs_search_path_in_tree_user(struct user_namespace *mnt_userns,
+static int btrfs_search_path_in_tree_user(struct mnt_idmap *idmap,
 				struct inode *inode,
 				struct btrfs_ioctl_ino_lookup_user_args *args)
 {
@@ -1962,7 +1965,7 @@ static int btrfs_search_path_in_tree_user(struct user_namespace *mnt_userns,
 				ret = PTR_ERR(temp_inode);
 				goto out_put;
 			}
-			ret = inode_permission(mnt_userns, temp_inode,
+			ret = inode_permission(idmap, temp_inode,
 					       MAY_READ | MAY_EXEC);
 			iput(temp_inode);
 			if (ret) {
@@ -2101,7 +2104,7 @@ static int btrfs_ioctl_ino_lookup_user(struct file *file, void __user *argp)
 		return -EACCES;
 	}
 
-	ret = btrfs_search_path_in_tree_user(file_mnt_user_ns(file), inode, args);
+	ret = btrfs_search_path_in_tree_user(file_mnt_idmap(file), inode, args);
 
 	if (ret == 0 && copy_to_user(argp, args, sizeof(*args)))
 		ret = -EFAULT;
@@ -2335,7 +2338,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 	struct btrfs_root *dest = NULL;
 	struct btrfs_ioctl_vol_args *vol_args = NULL;
 	struct btrfs_ioctl_vol_args_v2 *vol_args2 = NULL;
-	struct user_namespace *mnt_userns = file_mnt_user_ns(file);
+	struct mnt_idmap *idmap = file_mnt_idmap(file);
 	char *subvol_name, *subvol_name_ptr = NULL;
 	int subvol_namelen;
 	int err = 0;
@@ -2428,7 +2431,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 			 * anywhere in the filesystem the user wouldn't be able
 			 * to delete without an idmapped mount.