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
  ...

7 files changed, 31 insertions, 30 deletions

diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 1457f59f447a..995cb2c90b1a 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -113,11 +113,11 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp)
 
 	inode_lock(inode);
 
-	error = set_posix_acl(&init_user_ns, fh->fh_dentry, ACL_TYPE_ACCESS,
+	error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_ACCESS,
 			      argp->acl_access);
 	if (error)
 		goto out_drop_lock;
-	error = set_posix_acl(&init_user_ns, fh->fh_dentry, ACL_TYPE_DEFAULT,
+	error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_DEFAULT,
 			      argp->acl_default);
 	if (error)
 		goto out_drop_lock;
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 647108138e8a..887803735e2a 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -103,11 +103,11 @@ static __be32 nfsd3_proc_setacl(struct svc_rqst *rqstp)
 
 	inode_lock(inode);
 
-	error = set_posix_acl(&init_user_ns, fh->fh_dentry, ACL_TYPE_ACCESS,
+	error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_ACCESS,
 			      argp->acl_access);
 	if (error)
 		goto out_drop_lock;
-	error = set_posix_acl(&init_user_ns, fh->fh_dentry, ACL_TYPE_DEFAULT,
+	error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_DEFAULT,
 			      argp->acl_default);
 
 out_drop_lock:
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index d01b29aba662..f41992ecd0d7 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -320,7 +320,7 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		iap->ia_mode &= ~current_umask();
 
 	fh_fill_pre_attrs(fhp);
-	host_err = vfs_create(&init_user_ns, inode, child, iap->ia_mode, true);
+	host_err = vfs_create(&nop_mnt_idmap, inode, child, iap->ia_mode, true);
 	if (host_err < 0) {
 		status = nfserrno(host_err);
 		goto out;
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 78b8cd9651d5..3509e73abe1f 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -233,7 +233,7 @@ nfsd4_create_clid_dir(struct nfs4_client *clp)
 		 * as well be forgiving and just succeed silently.
 		 */
 		goto out_put;
-	status = vfs_mkdir(&init_user_ns, d_inode(dir), dentry, S_IRWXU);
+	status = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), dentry, S_IRWXU);
 out_put:
 	dput(dentry);
 out_unlock:
@@ -353,7 +353,7 @@ nfsd4_unlink_clid_dir(char *name, int namlen, struct nfsd_net *nn)
 	status = -ENOENT;
 	if (d_really_is_negative(dentry))
 		goto out;
-	status = vfs_rmdir(&init_user_ns, d_inode(dir), dentry);
+	status = vfs_rmdir(&nop_mnt_idmap, d_inode(dir), dentry);
 out:
 	dput(dentry);
 out_unlock:
@@ -443,7 +443,7 @@ purge_old(struct dentry *parent, struct dentry *child, struct nfsd_net *nn)
 	if (nfs4_has_reclaimed_state(name, nn))
 		goto out_free;
 
-	status = vfs_rmdir(&init_user_ns, d_inode(parent), child);
+	status = vfs_rmdir(&nop_mnt_idmap, d_inode(parent), child);
 	if (status)
 		printk("failed to remove client recovery directory %pd\n",
 				child);
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 76ea268dc420..ccd8485fee04 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -40,7 +40,7 @@ static int nfsd_acceptable(void *expv, struct dentry *dentry)
 		/* make sure parents give x permission to user */
 		int err;
 		parent = dget_parent(tdentry);
-		err = inode_permission(&init_user_ns,
+		err = inode_permission(&nop_mnt_idmap,
 				       d_inode(parent), MAY_EXEC);
 		if (err < 0) {
 			dput(parent);
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 9744443c3965..a82d91afdc9c 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -93,7 +93,7 @@ nfsd_proc_setattr(struct svc_rqst *rqstp)
 		if (delta < 0)
 			delta = -delta;
 		if (delta < MAX_TOUCH_TIME_ERROR &&
-		    setattr_prepare(&init_user_ns, fhp->fh_dentry, iap) != 0) {
+		    setattr_prepare(&nop_mnt_idmap, fhp->fh_dentry, iap) != 0) {
 			/*
 			 * Turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME.
 			 * This will cause notify_change to set these times
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 4c3a0d84043c..ab4ee3509ce3 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -426,7 +426,7 @@ static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap)
 		if (iap->ia_size < 0)
 			return -EFBIG;
 
-		host_err = notify_change(&init_user_ns, dentry, &size_attr, NULL);
+		host_err = notify_change(&nop_mnt_idmap, dentry, &size_attr, NULL);
 		if (host_err)
 			return host_err;
 		iap->ia_valid &= ~ATTR_SIZE;
@@ -444,7 +444,7 @@ static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap)
 		return 0;
 
 	iap->ia_valid |= ATTR_CTIME;
-	return notify_change(&init_user_ns, dentry, iap, NULL);
+	return notify_change(&nop_mnt_idmap, dentry, iap, NULL);
 }
 
 /**
@@ -542,12 +542,12 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		attr->na_labelerr = security_inode_setsecctx(dentry,
 			attr->na_seclabel->data, attr->na_seclabel->len);
 	if (IS_ENABLED(CONFIG_FS_POSIX_ACL) && attr->na_pacl)
-		attr->na_aclerr = set_posix_acl(&init_user_ns,
+		attr->na_aclerr = set_posix_acl(&nop_mnt_idmap,
 						dentry, ACL_TYPE_ACCESS,
 						attr->na_pacl);
 	if (IS_ENABLED(CONFIG_FS_POSIX_ACL) &&
 	    !attr->na_aclerr && attr->na_dpacl && S_ISDIR(inode->i_mode))
-		attr->na_aclerr = set_posix_acl(&init_user_ns,
+		attr->na_aclerr = set_posix_acl(&nop_mnt_idmap,
 						dentry, ACL_TYPE_DEFAULT,
 						attr->na_dpacl);
 	inode_unlock(inode);
@@ -583,7 +583,7 @@ int nfsd4_is_junction(struct dentry *dentry)
 		return 0;
 	if (!(inode->i_mode & S_ISVTX))
 		return 0;
-	if (vfs_getxattr(&init_user_ns, dentry, NFSD_JUNCTION_XATTR_NAME,
+	if (vfs_getxattr(&nop_mnt_idmap, dentry, NFSD_JUNCTION_XATTR_NAME,
 			 NULL, 0) <= 0)
 		return 0;
 	return 1;
@@ -1363,12 +1363,13 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	err = 0;
 	switch (type) {
 	case S_IFREG:
-		host_err = vfs_create(&init_user_ns, dirp, dchild, iap->ia_mode, true);
+		host_err = vfs_create(&nop_mnt_idmap, dirp, dchild,
+				      iap->ia_mode, true);
 		if (!host_err)
 			nfsd_check_ignore_resizing(iap);
 		break;
 	case S_IFDIR:
-		host_err = vfs_mkdir(&init_user_ns, dirp, dchild, iap->ia_mode);
+		host_err = vfs_mkdir(&nop_mnt_idmap, dirp, dchild, iap->ia_mode);
 		if (!host_err && unlikely(d_unhashed(dchild))) {
 			struct dentry *d;
 			d = lookup_one_len(dchild->d_name.name,
@@ -1396,7 +1397,7 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	case S_IFBLK:
 	case S_IFIFO:
 	case S_IFSOCK:
-		host_err = vfs_mknod(&init_user_ns, dirp, dchild,
+		host_err = vfs_mknod(&nop_mnt_idmap, dirp, dchild,
 				     iap->ia_mode, rdev);
 		break;
 	default:
@@ -1557,7 +1558,7 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		goto out_drop_write;
 	}
 	fh_fill_pre_attrs(fhp);
-	host_err = vfs_symlink(&init_user_ns, d_inode(dentry), dnew, path);
+	host_err = vfs_symlink(&nop_mnt_idmap, d_inode(dentry), dnew, path);
 	err = nfserrno(host_err);
 	cerr = fh_compose(resfhp, fhp->fh_export, dnew, fhp);
 	if (!err)
@@ -1625,7 +1626,7 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
 	if (d_really_is_negative(dold))
 		goto out_dput;
 	fh_fill_pre_attrs(ffhp);
-	host_err = vfs_link(dold, &init_user_ns, dirp, dnew, NULL);
+	host_err = vfs_link(dold, &nop_mnt_idmap, dirp, dnew, NULL);
 	fh_fill_post_attrs(ffhp);
 	inode_unlock(dirp);
 	if (!host_err) {
@@ -1745,10 +1746,10 @@ retry:
 		goto out_dput_old;
 	} else {
 		struct renamedata rd = {
-			.old_mnt_userns	= &init_user_ns,
+			.old_mnt_idmap	= &nop_mnt_idmap,
 			.old_dir	= fdir,
 			.old_dentry	= odentry,
-			.new_mnt_userns	= &init_user_ns,
+			.new_mnt_idmap	= &nop_mnt_idmap,
 			.new_dir	= tdir,
 			.new_dentry	= ndentry,
 		};
@@ -1850,14 +1851,14 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 			nfsd_close_cached_files(rdentry);
 
 		for (retries = 1;;) {
-			host_err = vfs_unlink(&init_user_ns, dirp, rdentry, NULL);
+			host_err = vfs_unlink(&nop_mnt_idmap, dirp, rdentry, NULL);
 			if (host_err != -EAGAIN || !retries--)
 				break;
 			if (!nfsd_wait_for_delegreturn(rqstp, rinode))
 				break;
 		}
 	} else {
-		host_err = vfs_rmdir(&init_user_ns, dirp, rdentry);
+		host_err = vfs_rmdir(&nop_mnt_idmap, dirp, rdentry);
 	}
 	fh_fill_post_attrs(fhp);
 
@@ -2129,7 +2130,7 @@ nfsd_getxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name,
 
 	inode_lock_shared(inode);
 
-	len = vfs_getxattr(&init_user_ns, dentry, name, NULL, 0);
+	len = vfs_getxattr(&nop_mnt_idmap, dentry, name, NULL, 0);
 
 	/*
 	 * Zero-length attribute, just return.
@@ -2156,7 +2157,7 @@ nfsd_getxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name,
 		goto out;
 	}
 
-	len = vfs_getxattr(&init_user_ns, dentry, name, buf, len);
+	len = vfs_getxattr(&nop_mnt_idmap, dentry, name, buf, len);
 	if (len <= 0) {
 		kvfree(buf);
 		buf = NULL;
@@ -2267,7 +2268,7 @@ nfsd_removexattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name)
 	inode_lock(fhp->fh_dentry->d_inode);
 	fh_fill_pre_attrs(fhp);
 
-	ret = __vfs_removexattr_locked(&init_user_ns, fhp->fh_dentry,
+	ret = __vfs_removexattr_locked(&nop_mnt_idmap, fhp->fh_dentry,
 				       name, NULL);
 
 	fh_fill_post_attrs(fhp);
@@ -2294,7 +2295,7 @@ nfsd_setxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name,
 	inode_lock(fhp->fh_dentry->d_inode);
 	fh_fill_pre_attrs(fhp);
 
-	ret = __vfs_setxattr_locked(&init_user_ns, fhp->fh_dentry, name, buf,
+	ret = __vfs_setxattr_locked(&nop_mnt_idmap, fhp->fh_dentry, name, buf,
 				    len, flags, NULL);
 	fh_fill_post_attrs(fhp);
 	inode_unlock(fhp->fh_dentry->d_inode);
@@ -2378,14 +2379,14 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
 		return 0;
 
 	/* This assumes  NFSD_MAY_{READ,WRITE,EXEC} == MAY_{READ,WRITE,EXEC} */
-	err = inode_permission(&init_user_ns, inode,
+	err = inode_permission(&nop_mnt_idmap, inode,
 			       acc & (MAY_READ | MAY_WRITE | MAY_EXEC));
 
 	/* Allow read access to binaries even when mode 111 */
 	if (err == -EACCES && S_ISREG(inode->i_mode) &&
 	     (acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE) ||
 	      acc == (NFSD_MAY_READ | NFSD_MAY_READ_IF_EXEC)))
-		err = inode_permission(&init_user_ns, inode, MAY_EXEC);
+		err = inode_permission(&nop_mnt_idmap, inode, MAY_EXEC);
 
 	return err? nfserrno(err) : 0;
 }