overlayfs updates for 6.12

-----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEE9zuTYTs0RXF+Ke33EVvVyTe/1WoFAmbodTUACgkQEVvVyTe/
 1Wp5Jw/+LN99lGoKXKZ7zB8gta4hMm2O+wd3//IdfTi6u59uff0QvVNbczC6SRlJ
 sW6czIgjKpR1xt6Orp0Rof0VZK09PMqq3Iw7Tt3xEkJtjKxppfMCQHeoi03CH9kF
 gOHPW+Ad4jlCk+TYFEuHk5lQIgVtJ11JDtGjr5tNa03MbrLIa0pFpTdz65bg9uTn
 JdPqA+fiJ/mVoXlFQEZkQPeT8CgMfTbKtQDGfcmKzrNo0ZyQdW30u5lP3MGROptn
 X/QX5n77UrE9Du+UHPSaVDRUd8iA/ZcZe/7RAlKXWElHpKvAiqv84Sz0Mc1fczHx
 nQHaUfQixGs/vakkPXxVqKn/Xvnj4GDwUqyM9mG8kN1x4QpdyFRqM66zZxtWsSi5
 /PL0zwAY950a5fY4VsyRsSf6Zl/SlDdB+PVVajk6BKqMxWgvxyuVbFRUqfesHsfA
 V5GHil7F03sPzO12SvAJg8HuresCiafLdAPJgGXuGoeprmeSP9eYx0EqcUzLpHd7
 ORUF4qEylYFp8vZBJdBnZpSGRUv/mmjDDowsKeKyfgKyVR99lLKLCtqMJ0e0eGaE
 mpGNg+eq//snJldvBUHrMYQvyVm18/bbOzT0ZdGPp2bMUxLjSbiab7D3S9GKRxRt
 8GRg/bJfZw5tz2i1bxbe5IWfNij5pDilLeAQUsoO8pUwu/SrCy8=
 =wnbj
 -----END PGP SIGNATURE-----

Merge tag 'ovl-update-6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/overlayfs/vfs

Pull overlayfs updates from Amir Goldstein:

 - Increase robustness of overlayfs to crashes in the case of underlying
   filesystems that to not guarantee metadata ordering to persistent
   storage (problem was reported with ubifs).

 - Deny mount inside container with features that require root
   privileges to work properly, instead of failing operations later.

 - Some clarifications to overlayfs documentation.

* tag 'ovl-update-6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/overlayfs/vfs:
  ovl: fail if trusted xattrs are needed but caller lacks permission
  overlayfs.rst: update metacopy section in overlayfs documentation
  ovl: fsync after metadata copy-up
  ovl: don't set the superblock's errseq_t manually

Documentation/filesystems/overlayfs.rst

@@ -367,8 +367,11 @@ Metadata only copy up
 
 When the "metacopy" feature is enabled, overlayfs will only copy
 up metadata (as opposed to whole file), when a metadata specific operation
-like chown/chmod is performed. Full file will be copied up later when
-file is opened for WRITE operation.
+like chown/chmod is performed. An upper file in this state is marked with
+"trusted.overlayfs.metacopy" xattr which indicates that the upper file
+contains no data.  The data will be copied up later when file is opened for
+WRITE operation.  After the lower file's data is copied up,
+the "trusted.overlayfs.metacopy" xattr is removed from the upper file.
 
 In other words, this is delayed data copy up operation and data is copied
 up when there is a need to actually modify data.

fs/overlayfs/copy_up.c

@@ -243,8 +243,24 @@ static int ovl_verify_area(loff_t pos, loff_t pos2, loff_t len, loff_t totlen)
 	return 0;
 }
 
+static int ovl_sync_file(struct path *path)
+{
+	struct file *new_file;
+	int err;
+
+	new_file = ovl_path_open(path, O_LARGEFILE | O_RDONLY);
+	if (IS_ERR(new_file))
+		return PTR_ERR(new_file);
+
+	err = vfs_fsync(new_file, 0);
+	fput(new_file);
+
+	return err;
+}
+
 static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry,
-			    struct file *new_file, loff_t len)
+			    struct file *new_file, loff_t len,
+			    bool datasync)
 {
 	struct path datapath;
 	struct file *old_file;
@@ -342,7 +358,8 @@ static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry,
 
 		len -= bytes;
 	}
-	if (!error && ovl_should_sync(ofs))
+	/* call fsync once, either now or later along with metadata */
+	if (!error && ovl_should_sync(ofs) && datasync)
 		error = vfs_fsync(new_file, 0);
 out_fput:
 	fput(old_file);
@@ -574,6 +591,7 @@ struct ovl_copy_up_ctx {
 	bool indexed;
 	bool metacopy;
 	bool metacopy_digest;
+	bool metadata_fsync;
 };
 
 static int ovl_link_up(struct ovl_copy_up_ctx *c)
@@ -634,7 +652,8 @@ static int ovl_copy_up_data(struct ovl_copy_up_ctx *c, const struct path *temp)
 	if (IS_ERR(new_file))
 		return PTR_ERR(new_file);
 
-	err = ovl_copy_up_file(ofs, c->dentry, new_file, c->stat.size);
+	err = ovl_copy_up_file(ofs, c->dentry, new_file, c->stat.size,
+			       !c->metadata_fsync);
 	fput(new_file);
 
 	return err;
@@ -701,6 +720,10 @@ static int ovl_copy_up_metadata(struct ovl_copy_up_ctx *c, struct dentry *temp)
 		err = ovl_set_attr(ofs, temp, &c->stat);
 	inode_unlock(temp->d_inode);
 
+	/* fsync metadata before moving it into upper dir */
+	if (!err && ovl_should_sync(ofs) && c->metadata_fsync)
+		err = ovl_sync_file(&upperpath);
+
 	return err;
 }
 
@@ -860,7 +883,8 @@ static int ovl_copy_up_tmpfile(struct ovl_copy_up_ctx *c)
 
 	temp = tmpfile->f_path.dentry;
 	if (!c->metacopy && c->stat.size) {
-		err = ovl_copy_up_file(ofs, c->dentry, tmpfile, c->stat.size);
+		err = ovl_copy_up_file(ofs, c->dentry, tmpfile, c->stat.size,
+				       !c->metadata_fsync);
 		if (err)
 			goto out_fput;
 	}
@@ -1135,6 +1159,17 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 	    !kgid_has_mapping(current_user_ns(), ctx.stat.gid))
 		return -EOVERFLOW;
 
+	/*
+	 * With metacopy disabled, we fsync after final metadata copyup, for
+	 * both regular files and directories to get atomic copyup semantics
+	 * on filesystems that do not use strict metadata ordering (e.g. ubifs).
+	 *
+	 * With metacopy enabled we want to avoid fsync on all meta copyup
+	 * that will hurt performance of workloads such as chown -R, so we
+	 * only fsync on data copyup as legacy behavior.
+	 */
+	ctx.metadata_fsync = !OVL_FS(dentry->d_sb)->config.metacopy &&
+			     (S_ISREG(ctx.stat.mode) || S_ISDIR(ctx.stat.mode));
 	ctx.metacopy = ovl_need_meta_copy_up(dentry, ctx.stat.mode, flags);
 
 	if (parent) {

fs/overlayfs/params.c

@@ -755,11 +755,6 @@ int ovl_fs_params_verify(const struct ovl_fs_context *ctx,
 {
 	struct ovl_opt_set set = ctx->set;
 
-	if (ctx->nr_data > 0 && !config->metacopy) {
-		pr_err("lower data-only dirs require metacopy support.\n");
-		return -EINVAL;
-	}
-
 	/* Workdir/index are useless in non-upper mount */
 	if (!config->upperdir) {
 		if (config->workdir) {
@@ -911,6 +906,39 @@ int ovl_fs_params_verify(const struct ovl_fs_context *ctx,
 		config->metacopy = false;
 	}
 
+	/*
+	 * Fail if we don't have trusted xattr capability and a feature was
+	 * explicitly requested that requires them.
+	 */
+	if (!config->userxattr && !capable(CAP_SYS_ADMIN)) {
+		if (set.redirect &&
+		    config->redirect_mode != OVL_REDIRECT_NOFOLLOW) {
+			pr_err("redirect_dir requires permission to access trusted xattrs\n");
+			return -EPERM;
+		}
+		if (config->metacopy && set.metacopy) {
+			pr_err("metacopy requires permission to access trusted xattrs\n");
+			return -EPERM;
+		}
+		if (config->verity_mode) {
+			pr_err("verity requires permission to access trusted xattrs\n");
+			return -EPERM;
+		}
+		if (ctx->nr_data > 0) {
+			pr_err("lower data-only dirs require permission to access trusted xattrs\n");
+			return -EPERM;
+		}
+		/*
+		 * Other xattr-dependent features should be disabled without
+		 * great disturbance to the user in ovl_make_workdir().
+		 */
+	}
+
+	if (ctx->nr_data > 0 && !config->metacopy) {
+		pr_err("lower data-only dirs require metacopy support.\n");
+		return -EINVAL;
+	}
+
 	return 0;
 }
 

fs/overlayfs/super.c

@@ -202,15 +202,9 @@ static int ovl_sync_fs(struct super_block *sb, int wait)
 	int ret;
 
 	ret = ovl_sync_status(ofs);
-	/*
-	 * We have to always set the err, because the return value isn't
-	 * checked in syncfs, and instead indirectly return an error via
-	 * the sb's writeback errseq, which VFS inspects after this call.
-	 */
-	if (ret < 0) {
-		errseq_set(&sb->s_wb_err, -EIO);
+
+	if (ret < 0)
 		return -EIO;
-	}
 
 	if (!ret)
 		return ret;