Merge tag 'fs.idmapped.v6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping

Pull vfs idmapping updates from Christian Brauner:

 - Last cycle we introduced the dedicated struct mnt_idmap type for
   mount idmapping and the required infrastucture in 256c8aed2b42 ("fs:
   introduce dedicated idmap type for mounts"). As promised in last
   cycle's pull request message this converts everything to rely on
   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 relevant on the mount level. Especially for
   non-vfs developers without detailed knowledge in this area this was a
   potential source for bugs.

   This finishes the conversion. Instead of passing the plain namespace
   around this updates all places that currently take a pointer to a
   mnt_userns with a pointer to struct mnt_idmap.

   Now that the conversion is done all helpers down to the really
   low-level helpers only accept a struct mnt_idmap argument instead of
   two namespace arguments.

   Conflating mount and other idmappings will now cause the compiler to
   complain loudly thus eliminating the possibility of any bugs. This
   makes it impossible for filesystem developers to mix up mount and
   filesystem idmappings as they are two distinct types and require
   distinct helpers that cannot be used interchangeably.

   Everything associated with struct mnt_idmap is moved into a single
   separate file. With that change no code can poke around in struct
   mnt_idmap. It can only be interacted with through dedicated helpers.
   That means all filesystems are and all of the vfs is completely
   oblivious to the actual implementation of idmappings.

   We are now also able to extend struct mnt_idmap as we see fit. For
   example, we can decouple it completely from namespaces for users that
   don't require or don't want to use them at all. We can also extend
   the concept of idmappings so we can cover filesystem specific
   requirements.

   In combination with the vfs{g,u}id_t work we finished in v6.2 this
   makes this feature substantially more robust and thus difficult to
   implement wrong by a given filesystem and also protects the vfs.

 - Enable idmapped mounts for tmpfs and fulfill a longstanding request.

   A long-standing request from users had been to make it possible to
   create idmapped mounts for tmpfs. For example, to share the host's
   tmpfs mount between multiple sandboxes. This is a prerequisite for
   some advanced Kubernetes cases. Systemd also has a range of use-cases
   to increase service isolation. And there are more users of this.

   However, with all of the other work going on this was way down on the
   priority list but luckily someone other than ourselves picked this
   up.

   As usual the patch is tiny as all the infrastructure work had been
   done multiple kernel releases ago. In addition to all the tests that
   we already have I requested that Rodrigo add a dedicated tmpfs
   testsuite for idmapped mounts to xfstests. It is to be included into
   xfstests during the v6.3 development cycle. This should add a slew of
   additional tests.

* tag 'fs.idmapped.v6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping: (26 commits)
  shmem: support idmapped mounts for tmpfs
  fs: move mnt_idmap
  fs: port vfs{g,u}id helpers to mnt_idmap
  fs: port fs{g,u}id helpers to mnt_idmap
  fs: port i_{g,u}id_into_vfs{g,u}id() to mnt_idmap
  fs: port i_{g,u}id_{needs_}update() to mnt_idmap
  quota: port to mnt_idmap
  fs: port privilege checking helpers to mnt_idmap
  fs: port inode_owner_or_capable() to mnt_idmap
  fs: port inode_init_owner() to mnt_idmap
  fs: port acl to mnt_idmap
  fs: port xattr to mnt_idmap
  fs: port ->permission() to pass mnt_idmap
  fs: port ->fileattr_set() to pass mnt_idmap
  fs: port ->set_acl() to pass mnt_idmap
  fs: port ->get_acl() to pass mnt_idmap
  fs: port ->tmpfile() to pass mnt_idmap
  fs: port ->rename() to pass mnt_idmap
  fs: port ->mknod() to pass mnt_idmap
  fs: port ->mkdir() to pass mnt_idmap
  ...

8 files changed, 33 insertions, 33 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 9e479d7d202b..5e0e0ccd47aa 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -685,7 +685,7 @@ static bool proc_fd_access_allowed(struct inode *inode)
 	return allowed;
 }
 
-int proc_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+int proc_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		 struct iattr *attr)
 {
 	int error;
@@ -694,11 +694,11 @@ int proc_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 	if (attr->ia_valid & ATTR_MODE)
 		return -EPERM;
 
-	error = setattr_prepare(&init_user_ns, dentry, attr);
+	error = setattr_prepare(&nop_mnt_idmap, dentry, attr);
 	if (error)
 		return error;
 
-	setattr_copy(&init_user_ns, inode, attr);
+	setattr_copy(&nop_mnt_idmap, inode, attr);
 	mark_inode_dirty(inode);
 	return 0;
 }
@@ -727,7 +727,7 @@ static bool has_pid_permissions(struct proc_fs_info *fs_info,
 }
 
 
-static int proc_pid_permission(struct user_namespace *mnt_userns,
+static int proc_pid_permission(struct mnt_idmap *idmap,
 			       struct inode *inode, int mask)
 {
 	struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb);
@@ -753,7 +753,7 @@ static int proc_pid_permission(struct user_namespace *mnt_userns,
 
 		return -EPERM;
 	}
-	return generic_permission(&init_user_ns, inode, mask);
+	return generic_permission(&nop_mnt_idmap, inode, mask);
 }
 
 
@@ -1959,14 +1959,14 @@ static struct inode *proc_pid_make_base_inode(struct super_block *sb,
 	return inode;
 }
 
-int pid_getattr(struct user_namespace *mnt_userns, const struct path *path,
+int pid_getattr(struct mnt_idmap *idmap, const struct path *path,
 		struct kstat *stat, u32 request_mask, unsigned int query_flags)
 {
 	struct inode *inode = d_inode(path->dentry);
 	struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb);
 	struct task_struct *task;
 
-	generic_fillattr(&init_user_ns, inode, stat);
+	generic_fillattr(&nop_mnt_idmap, inode, stat);
 
 	stat->uid = GLOBAL_ROOT_UID;
 	stat->gid = GLOBAL_ROOT_GID;
@@ -3557,7 +3557,7 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx)
  * This function makes sure that the node is always accessible for members of
  * same thread group.
  */
-static int proc_tid_comm_permission(struct user_namespace *mnt_userns,
+static int proc_tid_comm_permission(struct mnt_idmap *idmap,
 				    struct inode *inode, int mask)
 {
 	bool is_same_tgroup;
@@ -3577,7 +3577,7 @@ static int proc_tid_comm_permission(struct user_namespace *mnt_userns,
 		return 0;
 	}
 
-	return generic_permission(&init_user_ns, inode, mask);
+	return generic_permission(&nop_mnt_idmap, inode, mask);
 }
 
 static const struct inode_operations proc_tid_comm_inode_operations = {
@@ -3891,13 +3891,13 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx)
 	return 0;
 }
 
-static int proc_task_getattr(struct user_namespace *mnt_userns,
+static int proc_task_getattr(struct mnt_idmap *idmap,
 			     const struct path *path, struct kstat *stat,
 			     u32 request_mask, unsigned int query_flags)
 {
 	struct inode *inode = d_inode(path->dentry);
 	struct task_struct *p = get_proc_task(inode);
-	generic_fillattr(&init_user_ns, inode, stat);
+	generic_fillattr(&nop_mnt_idmap, inode, stat);
 
 	if (p) {
 		stat->nlink += get_nr_threads(p);
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 53e4919ef860..b3140deebbbf 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -326,13 +326,13 @@ static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry,
  * /proc/pid/fd needs a special permission handler so that a process can still
  * access /proc/self/fd after it has executed a setuid().
  */
-int proc_fd_permission(struct user_namespace *mnt_userns,
+int proc_fd_permission(struct mnt_idmap *idmap,
 		       struct inode *inode, int mask)
 {
 	struct task_struct *p;
 	int rv;
 
-	rv = generic_permission(&init_user_ns, inode, mask);
+	rv = generic_permission(&nop_mnt_idmap, inode, mask);
 	if (rv == 0)
 		return rv;
 
@@ -345,14 +345,14 @@ int proc_fd_permission(struct user_namespace *mnt_userns,
 	return rv;
 }
 
-static int proc_fd_getattr(struct user_namespace *mnt_userns,
+static int proc_fd_getattr(struct mnt_idmap *idmap,
 			const struct path *path, struct kstat *stat,
 			u32 request_mask, unsigned int query_flags)
 {
 	struct inode *inode = d_inode(path->dentry);
 	int rv = 0;
 
-	generic_fillattr(&init_user_ns, inode, stat);
+	generic_fillattr(&nop_mnt_idmap, inode, stat);
 
 	/* If it's a directory, put the number of open fds there */
 	if (S_ISDIR(inode->i_mode)) {
diff --git a/fs/proc/fd.h b/fs/proc/fd.h
index c5a921a06a0b..7e7265f7e06f 100644
--- a/fs/proc/fd.h
+++ b/fs/proc/fd.h
@@ -10,7 +10,7 @@ extern const struct inode_operations proc_fd_inode_operations;
 extern const struct file_operations proc_fdinfo_operations;
 extern const struct inode_operations proc_fdinfo_inode_operations;
 
-extern int proc_fd_permission(struct user_namespace *mnt_userns,
+extern int proc_fd_permission(struct mnt_idmap *idmap,
 			      struct inode *inode, int mask);
 
 static inline unsigned int proc_fd(struct inode *inode)
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 587b91d9d998..8379593fa4bb 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -115,18 +115,18 @@ static bool pde_subdir_insert(struct proc_dir_entry *dir,
 	return true;
 }
 
-static int proc_notify_change(struct user_namespace *mnt_userns,
+static int proc_notify_change(struct mnt_idmap *idmap,
 			      struct dentry *dentry, struct iattr *iattr)
 {
 	struct inode *inode = d_inode(dentry);
 	struct proc_dir_entry *de = PDE(inode);
 	int error;
 
-	error = setattr_prepare(&init_user_ns, dentry, iattr);
+	error = setattr_prepare(&nop_mnt_idmap, dentry, iattr);
 	if (error)
 		return error;
 
-	setattr_copy(&init_user_ns, inode, iattr);
+	setattr_copy(&nop_mnt_idmap, inode, iattr);
 	mark_inode_dirty(inode);
 
 	proc_set_user(de, inode->i_uid, inode->i_gid);
@@ -134,7 +134,7 @@ static int proc_notify_change(struct user_namespace *mnt_userns,
 	return 0;
 }
 
-static int proc_getattr(struct user_namespace *mnt_userns,
+static int proc_getattr(struct mnt_idmap *idmap,
 			const struct path *path, struct kstat *stat,
 			u32 request_mask, unsigned int query_flags)
 {
@@ -147,7 +147,7 @@ static int proc_getattr(struct user_namespace *mnt_userns,
 		}
 	}
 
-	generic_fillattr(&init_user_ns, inode, stat);
+	generic_fillattr(&nop_mnt_idmap, inode, stat);
 	return 0;
 }
 
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index b701d0207edf..9dda7e54b2d0 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -162,9 +162,9 @@ extern int proc_pid_statm(struct seq_file *, struct pid_namespace *,
  * base.c
  */
 extern const struct dentry_operations pid_dentry_operations;
-extern int pid_getattr(struct user_namespace *, const struct path *,
+extern int pid_getattr(struct mnt_idmap *, const struct path *,
 		       struct kstat *, u32, unsigned int);
-extern int proc_setattr(struct user_namespace *, struct dentry *,
+extern int proc_setattr(struct mnt_idmap *, struct dentry *,
 			struct iattr *);
 extern void proc_pid_evict_inode(struct proc_inode *);
 extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struct *, umode_t);
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 856839b8ae8b..a0c0419872e3 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -299,7 +299,7 @@ static struct dentry *proc_tgid_net_lookup(struct inode *dir,
 	return de;
 }
 
-static int proc_tgid_net_getattr(struct user_namespace *mnt_userns,
+static int proc_tgid_net_getattr(struct mnt_idmap *idmap,
 				 const struct path *path, struct kstat *stat,
 				 u32 request_mask, unsigned int query_flags)
 {
@@ -308,7 +308,7 @@ static int proc_tgid_net_getattr(struct user_namespace *mnt_userns,
 
 	net = get_proc_task_net(inode);
 
-	generic_fillattr(&init_user_ns, inode, stat);
+	generic_fillattr(&nop_mnt_idmap, inode, stat);
 
 	if (net != NULL) {
 		stat->nlink = net->proc_net->nlink;
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 48f2d60bd78a..e89bd8f1368b 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -798,7 +798,7 @@ out:
 	return 0;
 }
 
-static int proc_sys_permission(struct user_namespace *mnt_userns,
+static int proc_sys_permission(struct mnt_idmap *idmap,
 			       struct inode *inode, int mask)
 {
 	/*
@@ -827,7 +827,7 @@ static int proc_sys_permission(struct user_namespace *mnt_userns,
 	return error;
 }
 
-static int proc_sys_setattr(struct user_namespace *mnt_userns,
+static int proc_sys_setattr(struct mnt_idmap *idmap,
 			    struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = d_inode(dentry);
@@ -836,16 +836,16 @@ static int proc_sys_setattr(struct user_namespace *mnt_userns,
 	if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))
 		return -EPERM;
 
-	error = setattr_prepare(&init_user_ns, dentry, attr);
+	error = setattr_prepare(&nop_mnt_idmap, dentry, attr);
 	if (error)
 		return error;
 
-	setattr_copy(&init_user_ns, inode, attr);
+	setattr_copy(&nop_mnt_idmap, inode, attr);
 	mark_inode_dirty(inode);
 	return 0;
 }
 
-static int proc_sys_getattr(struct user_namespace *mnt_userns,
+static int proc_sys_getattr(struct mnt_idmap *idmap,
 			    const struct path *path, struct kstat *stat,
 			    u32 request_mask, unsigned int query_flags)
 {
@@ -856,7 +856,7 @@ static int proc_sys_getattr(struct user_namespace *mnt_userns,
 	if (IS_ERR(head))
 		return PTR_ERR(head);
 
-	generic_fillattr(&init_user_ns, inode, stat);
+	generic_fillattr(&nop_mnt_idmap, inode, stat);
 	if (table)
 		stat->mode = (stat->mode & S_IFMT) | table->mode;
 
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 3c2ee3eb1138..a86e65a608da 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -310,11 +310,11 @@ void __init proc_root_init(void)
 	register_filesystem(&proc_fs_type);
 }
 
-static int proc_root_getattr(struct user_namespace *mnt_userns,
+static int proc_root_getattr(struct mnt_idmap *idmap,
 			     const struct path *path, struct kstat *stat,
 			     u32 request_mask, unsigned int query_flags)
 {
-	generic_fillattr(&init_user_ns, d_inode(path->dentry), stat);
+	generic_fillattr(&nop_mnt_idmap, d_inode(path->dentry), stat);
 	stat->nlink = proc_root.nlink + nr_processes();
 	return 0;
 }