Merge tag 'fs.idmapped.mnt_idmap.v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping

Pull idmapping updates from Christian Brauner:
 "Last cycle we've already made the interaction with idmapped mounts
  more robust and type safe by introducing the vfs{g,u}id_t type. This
  cycle we concluded the conversion and removed the legacy helpers.

  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
  filesystem developers without detailed knowledge in this area this can
  be a potential source for bugs.

  Instead of passing the plain namespace we introduce a dedicated type
  struct mnt_idmap and replace the pointer with a pointer to a struct
  mnt_idmap. There are no semantic or size changes for the mount struct
  caused by this.

  We then start converting all places aware of idmapped mounts to rely
  on struct mnt_idmap. Once the conversion is done all helpers down to
  the really low-level make_vfs{g,u}id() and from_vfs{g,u}id() will take
  a struct mnt_idmap argument instead of two namespace arguments. This
  way it becomes impossible to conflate the two removing and thus
  eliminating the possibility of any bugs. Fwiw, I fixed some issues in
  that area a while ago in ntfs3 and ksmbd in the past. Afterwards only
  low-level code can ultimately use the associated namespace for any
  permission checks. Even most of the vfs can be completely obivious
  about this ultimately and filesystems will never interact with it in
  any form in the future.

  A struct mnt_idmap currently encompasses a simple refcount and pointer
  to the relevant namespace the mount is idmapped to. If a mount isn't
  idmapped then it will point to a static nop_mnt_idmap and if it
  doesn't that it is idmapped. As usual there are no allocations or
  anything happening for non-idmapped mounts. Everthing is carefully
  written to be a nop for non-idmapped mounts as has always been the
  case.

  If an idmapped mount is created a struct mnt_idmap is allocated and a
  reference taken on the relevant namespace. Each mount that gets
  idmapped or inherits the idmap simply bumps the reference count on
  struct mnt_idmap. Just a reminder that we only allow a mount to change
  it's idmapping a single time and only if it hasn't already been
  attached to the filesystems and has no active writers.

  The actual changes are fairly straightforward but this will have huge
  benefits for maintenance and security in the long run even if it
  causes some churn.

  Note that this also makes it possible to extend struct mount_idmap in
  the future. For example, it would be possible to place the namespace
  pointer in an anonymous union together with an idmapping struct. This
  would allow us to expose an api to userspace that would let it specify
  idmappings directly instead of having to go through the detour of
  setting up namespaces at all"

* tag 'fs.idmapped.mnt_idmap.v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping:
  acl: conver higher-level helpers to rely on mnt_idmap
  fs: introduce dedicated idmap type for mounts

1 files changed, 9 insertions, 7 deletions

diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index e6643db35cce..d7bc81fc0840 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -871,7 +871,7 @@ EXPORT_SYMBOL (posix_acl_to_xattr);
 
 /**
  * vfs_posix_acl_to_xattr - convert from kernel to userspace representation
- * @mnt_userns: user namespace of the mount
+ * @idmap: idmap of the mount
  * @inode: inode the posix acls are set on
  * @acl: the posix acls as represented by the vfs
  * @buffer: the buffer into which to convert @acl
@@ -884,7 +884,7 @@ EXPORT_SYMBOL (posix_acl_to_xattr);
  * Return: On success, the size of the stored uapi posix acls, on error a
  * negative errno.
  */
-static ssize_t vfs_posix_acl_to_xattr(struct user_namespace *mnt_userns,
+static ssize_t vfs_posix_acl_to_xattr(struct mnt_idmap *idmap,
 				      struct inode *inode,
 				      const struct posix_acl *acl, void *buffer,
 				      size_t size)
@@ -893,6 +893,7 @@ static ssize_t vfs_posix_acl_to_xattr(struct user_namespace *mnt_userns,
 	struct posix_acl_xattr_header *ext_acl = buffer;
 	struct posix_acl_xattr_entry *ext_entry;
 	struct user_namespace *fs_userns, *caller_userns;
+	struct user_namespace *mnt_userns;
 	ssize_t real_size, n;
 	vfsuid_t vfsuid;
 	vfsgid_t vfsgid;
@@ -908,6 +909,7 @@ static ssize_t vfs_posix_acl_to_xattr(struct user_namespace *mnt_userns,
 
 	fs_userns = i_user_ns(inode);
 	caller_userns = current_user_ns();
+	mnt_userns = mnt_idmap_owner(idmap);
 	for (n=0; n < acl->a_count; n++, ext_entry++) {
 		const struct posix_acl_entry *acl_e = &acl->a_entries[n];
 		ext_entry->e_tag  = cpu_to_le16(acl_e->e_tag);
@@ -1227,7 +1229,7 @@ out_inode_unlock:
 }
 EXPORT_SYMBOL_GPL(vfs_remove_acl);
 
-int do_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
+int do_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 	       const char *acl_name, const void *kvalue, size_t size)
 {
 	int error;
@@ -1243,22 +1245,22 @@ int do_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
 			return PTR_ERR(acl);
 	}
 
-	error = vfs_set_acl(mnt_userns, dentry, acl_name, acl);
+	error = vfs_set_acl(mnt_idmap_owner(idmap), dentry, acl_name, acl);
 	posix_acl_release(acl);
 	return error;
 }
 
-ssize_t do_get_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
+ssize_t do_get_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 		   const char *acl_name, void *kvalue, size_t size)
 {
 	ssize_t error;
 	struct posix_acl *acl;
 
-	acl = vfs_get_acl(mnt_userns, dentry, acl_name);
+	acl = vfs_get_acl(mnt_idmap_owner(idmap), dentry, acl_name);
 	if (IS_ERR(acl))
 		return PTR_ERR(acl);
 
-	error = vfs_posix_acl_to_xattr(mnt_userns, d_inode(dentry),
+	error = vfs_posix_acl_to_xattr(idmap, d_inode(dentry),
 				       acl, kvalue, size);
 	posix_acl_release(acl);
 	return error;