1 files changed, 181 insertions, 79 deletions

diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index fe511192f83c..ba9146f22a2c 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -91,7 +91,24 @@ static int ovl_revalidate_real(struct dentry *d, unsigned int flags, bool weak)
 		if (d->d_flags & DCACHE_OP_WEAK_REVALIDATE)
 			ret =  d->d_op->d_weak_revalidate(d, flags);
 	} else if (d->d_flags & DCACHE_OP_REVALIDATE) {
-		ret = d->d_op->d_revalidate(d, flags);
+		struct dentry *parent;
+		struct inode *dir;
+		struct name_snapshot n;
+
+		if (flags & LOOKUP_RCU) {
+			parent = READ_ONCE(d->d_parent);
+			dir = d_inode_rcu(parent);
+			if (!dir)
+				return -ECHILD;
+		} else {
+			parent = dget_parent(d);
+			dir = d_inode(parent);
+		}
+		take_dentry_name_snapshot(&n, d);
+		ret = d->d_op->d_revalidate(dir, &n.name, d, flags);
+		release_dentry_name_snapshot(&n);
+		if (!(flags & LOOKUP_RCU))
+			dput(parent);
 		if (!ret) {
 			if (!(flags & LOOKUP_RCU))
 				d_invalidate(d);
@@ -111,9 +128,17 @@ static int ovl_dentry_revalidate_common(struct dentry *dentry,
 	unsigned int i;
 	int ret = 1;
 
-	/* Careful in RCU mode */
-	if (!inode)
+	if (!inode) {
+		/*
+		 * Lookup of negative dentries will call ovl_dentry_init_flags()
+		 * with NULL upperdentry and NULL oe, resulting in the
+		 * DCACHE_OP*_REVALIDATE flags being cleared.  Hence the only
+		 * way to get a negative inode is due to a race with dentry
+		 * destruction.
+		 */
+		WARN_ON(!(flags & LOOKUP_RCU));
 		return -ECHILD;
+	}
 
 	oe = OVL_I_E(inode);
 	lowerstack = ovl_lowerstack(oe);
@@ -127,7 +152,8 @@ static int ovl_dentry_revalidate_common(struct dentry *dentry,
 	return ret;
 }
 
-static int ovl_dentry_revalidate(struct dentry *dentry, unsigned int flags)
+static int ovl_dentry_revalidate(struct inode *dir, const struct qstr *name,
+				 struct dentry *dentry, unsigned int flags)
 {
 	return ovl_dentry_revalidate_common(dentry, flags, false);
 }
@@ -143,6 +169,16 @@ static const struct dentry_operations ovl_dentry_operations = {
 	.d_weak_revalidate = ovl_dentry_weak_revalidate,
 };
 
+#if IS_ENABLED(CONFIG_UNICODE)
+static const struct dentry_operations ovl_dentry_ci_operations = {
+	.d_real = ovl_d_real,
+	.d_revalidate = ovl_dentry_revalidate,
+	.d_weak_revalidate = ovl_dentry_weak_revalidate,
+	.d_hash = generic_ci_d_hash,
+	.d_compare = generic_ci_d_compare,
+};
+#endif
+
 static struct kmem_cache *ovl_inode_cachep;
 
 static struct inode *ovl_alloc_inode(struct super_block *sb)
@@ -262,7 +298,7 @@ static const struct super_operations ovl_super_operations = {
 	.alloc_inode	= ovl_alloc_inode,
 	.free_inode	= ovl_free_inode,
 	.destroy_inode	= ovl_destroy_inode,
-	.drop_inode	= generic_delete_inode,
+	.drop_inode	= inode_just_drop,
 	.put_super	= ovl_put_super,
 	.sync_fs	= ovl_sync_fs,
 	.statfs		= ovl_statfs,
@@ -281,9 +317,8 @@ static struct dentry *ovl_workdir_create(struct ovl_fs *ofs,
 	int err;
 	bool retried = false;
 
-	inode_lock_nested(dir, I_MUTEX_PARENT);
 retry:
-	work = ovl_lookup_upper(ofs, name, ofs->workbasedir, strlen(name));
+	work = ovl_start_creating_upper(ofs, ofs->workbasedir, &QSTR(name));
 
 	if (!IS_ERR(work)) {
 		struct iattr attr = {
@@ -292,26 +327,26 @@ retry:
 		};
 
 		if (work->d_inode) {
+			end_creating_keep(work);
+			if (persist)
+				return work;
 			err = -EEXIST;
 			if (retried)
 				goto out_dput;
-
-			if (persist)
-				goto out_unlock;
-
 			retried = true;
-			err = ovl_workdir_cleanup(ofs, dir, mnt, work, 0);
+			err = ovl_workdir_cleanup(ofs, ofs->workbasedir, mnt, work, 0);
 			dput(work);
-			if (err == -EINVAL) {
-				work = ERR_PTR(err);
-				goto out_unlock;
-			}
+			if (err == -EINVAL)
+				return ERR_PTR(err);
+
 			goto retry;
 		}
 
-		err = ovl_mkdir_real(ofs, dir, &work, attr.ia_mode);
-		if (err)
-			goto out_dput;
+		work = ovl_do_mkdir(ofs, dir, work, attr.ia_mode);
+		end_creating_keep(work);
+		err = PTR_ERR(work);
+		if (IS_ERR(work))
+			goto out_err;
 
 		/* Weird filesystem returning with hashed negative (kernfs)? */
 		err = -EINVAL;
@@ -349,8 +384,6 @@ retry:
 		err = PTR_ERR(work);
 		goto out_err;
 	}
-out_unlock:
-	inode_unlock(dir);
 	return work;
 
 out_dput:
@@ -358,8 +391,7 @@ out_dput:
 out_err:
 	pr_warn("failed to create directory %s/%s (errno: %i); mounting read-only\n",
 		ofs->config.workdir, name, -err);
-	work = NULL;
-	goto out_unlock;
+	return NULL;
 }
 
 static int ovl_check_namelen(const struct path *path, struct ovl_fs *ofs,
@@ -376,7 +408,7 @@ static int ovl_check_namelen(const struct path *path, struct ovl_fs *ofs,
 	return err;
 }
 
-static int ovl_lower_dir(const char *name, struct path *path,
+static int ovl_lower_dir(const char *name, const struct path *path,
 			 struct ovl_fs *ofs, int *stack_depth)
 {
 	int fh_type;
@@ -538,37 +570,41 @@ out:
 static int ovl_check_rename_whiteout(struct ovl_fs *ofs)
 {
 	struct dentry *workdir = ofs->workdir;
-	struct inode *dir = d_inode(workdir);
 	struct dentry *temp;
-	struct dentry *dest;
 	struct dentry *whiteout;
 	struct name_snapshot name;
+	struct renamedata rd = {};
+	char name2[OVL_TEMPNAME_SIZE];
 	int err;
 
-	inode_lock_nested(dir, I_MUTEX_PARENT);
-
 	temp = ovl_create_temp(ofs, workdir, OVL_CATTR(S_IFREG | 0));
 	err = PTR_ERR(temp);
 	if (IS_ERR(temp))
-		goto out_unlock;
+		return err;
 
-	dest = ovl_lookup_temp(ofs, workdir);
-	err = PTR_ERR(dest);
-	if (IS_ERR(dest)) {
+	rd.mnt_idmap = ovl_upper_mnt_idmap(ofs);
+	rd.old_parent = workdir;
+	rd.new_parent = workdir;
+	rd.flags = RENAME_WHITEOUT;
+	ovl_tempname(name2);
+	err = start_renaming_dentry(&rd, 0, temp, &QSTR(name2));
+	if (err) {
 		dput(temp);
-		goto out_unlock;
+		return err;
 	}
 
 	/* Name is inline and stable - using snapshot as a copy helper */
 	take_dentry_name_snapshot(&name, temp);
-	err = ovl_do_rename(ofs, dir, temp, dir, dest, RENAME_WHITEOUT);
+	err = ovl_do_rename_rd(&rd);
+	end_renaming(&rd);
 	if (err) {
 		if (err == -EINVAL)
 			err = 0;
 		goto cleanup_temp;
 	}
 
-	whiteout = ovl_lookup_upper(ofs, name.name.name, workdir, name.name.len);
+	whiteout = ovl_lookup_upper_unlocked(ofs, name.name.name,
+					     workdir, name.name.len);
 	err = PTR_ERR(whiteout);
 	if (IS_ERR(whiteout))
 		goto cleanup_temp;
@@ -577,17 +613,13 @@ static int ovl_check_rename_whiteout(struct ovl_fs *ofs)
 
 	/* Best effort cleanup of whiteout and temp file */
 	if (err)
-		ovl_cleanup(ofs, dir, whiteout);
+		ovl_cleanup(ofs, workdir, whiteout);
 	dput(whiteout);
 
 cleanup_temp:
-	ovl_cleanup(ofs, dir, temp);
+	ovl_cleanup(ofs, workdir, temp);
 	release_dentry_name_snapshot(&name);
 	dput(temp);
-	dput(dest);
-
-out_unlock:
-	inode_unlock(dir);
 
 	return err;
 }
@@ -596,15 +628,15 @@ static struct dentry *ovl_lookup_or_create(struct ovl_fs *ofs,
 					   struct dentry *parent,
 					   const char *name, umode_t mode)
 {
-	size_t len = strlen(name);
 	struct dentry *child;
 
-	inode_lock_nested(parent->d_inode, I_MUTEX_PARENT);
-	child = ovl_lookup_upper(ofs, name, parent, len);
-	if (!IS_ERR(child) && !child->d_inode)
-		child = ovl_create_real(ofs, parent->d_inode, child,
-					OVL_CATTR(mode));
-	inode_unlock(parent->d_inode);
+	child = ovl_start_creating_upper(ofs, parent, &QSTR(name));
+	if (!IS_ERR(child)) {
+		if (!child->d_inode)
+			child = ovl_create_real(ofs, parent, child,
+						OVL_CATTR(mode));
+		end_creating_keep(child);
+	}
 	dput(parent);
 
 	return child;
@@ -972,6 +1004,25 @@ static int ovl_get_data_fsid(struct ovl_fs *ofs)
 	return ofs->numfs;
 }
 
+/*
+ * Set the ovl sb encoding as the same one used by the first layer
+ */
+static int ovl_set_encoding(struct super_block *sb, struct super_block *fs_sb)
+{
+	if (!sb_has_encoding(fs_sb))
+		return 0;
+
+#if IS_ENABLED(CONFIG_UNICODE)
+	if (sb_has_strict_encoding(fs_sb)) {
+		pr_err("strict encoding not supported\n");
+		return -EINVAL;
+	}
+
+	sb->s_encoding = fs_sb->s_encoding;
+	sb->s_encoding_flags = fs_sb->s_encoding_flags;
+#endif
+	return 0;
+}
 
 static int ovl_get_layers(struct super_block *sb, struct ovl_fs *ofs,
 			  struct ovl_fs_context *ctx, struct ovl_layer *layers)
@@ -1005,6 +1056,12 @@ static int ovl_get_layers(struct super_block *sb, struct ovl_fs *ofs,
 	if (ovl_upper_mnt(ofs)) {
 		ofs->fs[0].sb = ovl_upper_mnt(ofs)->mnt_sb;
 		ofs->fs[0].is_lower = false;
+
+		if (ofs->casefold) {
+			err = ovl_set_encoding(sb, ofs->fs[0].sb);
+			if (err)
+				return err;
+		}
 	}
 
 	nr_merged_lower = ctx->nr - ctx->nr_data;
@@ -1064,6 +1121,19 @@ static int ovl_get_layers(struct super_block *sb, struct ovl_fs *ofs,
 		l->name = NULL;
 		ofs->numlayer++;
 		ofs->fs[fsid].is_lower = true;
+
+		if (ofs->casefold) {
+			if (!ovl_upper_mnt(ofs) && !sb_has_encoding(sb)) {
+				err = ovl_set_encoding(sb, ofs->fs[fsid].sb);
+				if (err)
+					return err;
+			}
+
+			if (!sb_same_encoding(sb, mnt->mnt_sb)) {
+				pr_err("all layers must have the same encoding\n");
+				return -EINVAL;
+			}
+		}
 	}
 
 	/*
@@ -1119,6 +1189,11 @@ static struct ovl_entry *ovl_get_lowerstack(struct super_block *sb,
 		return ERR_PTR(-EINVAL);
 	}
 
+	if (ctx->nr == ctx->nr_data) {
+		pr_err("at least one non-data lowerdir is required\n");
+		return ERR_PTR(-EINVAL);
+	}
+
 	err = -EINVAL;
 	for (i = 0; i < ctx->nr; i++) {
 		l = &ctx->lower[i];
@@ -1276,6 +1351,7 @@ static struct dentry *ovl_get_root(struct super_block *sb,
 	ovl_dentry_set_flag(OVL_E_CONNECTED, root);
 	ovl_set_upperdata(d_inode(root));
 	ovl_inode_init(d_inode(root), &oip, ino, fsid);
+	WARN_ON(!!IS_CASEFOLDED(d_inode(root)) != ofs->casefold);
 	ovl_dentry_init_flags(root, upperdentry, oe, DCACHE_OP_WEAK_REVALIDATE);
 	/* root keeps a reference of upperdentry */
 	dget(upperdentry);
@@ -1283,47 +1359,48 @@ static struct dentry *ovl_get_root(struct super_block *sb,
 	return root;
 }
 
-int ovl_fill_super(struct super_block *sb, struct fs_context *fc)
+static void ovl_set_d_op(struct super_block *sb)
+{
+#if IS_ENABLED(CONFIG_UNICODE)
+	struct ovl_fs *ofs = sb->s_fs_info;
+
+	if (ofs->casefold) {
+		set_default_d_op(sb, &ovl_dentry_ci_operations);
+		return;
+	}
+#endif
+	set_default_d_op(sb, &ovl_dentry_operations);
+}
+
+static int ovl_fill_super_creds(struct fs_context *fc, struct super_block *sb)
 {
 	struct ovl_fs *ofs = sb->s_fs_info;
+	struct cred *creator_cred = (struct cred *)ofs->creator_cred;
 	struct ovl_fs_context *ctx = fc->fs_private;
-	struct dentry *root_dentry;
-	struct ovl_entry *oe;
 	struct ovl_layer *layers;
-	struct cred *cred;
+	struct ovl_entry *oe = NULL;
 	int err;
 
-	err = -EIO;
-	if (WARN_ON(fc->user_ns != current_user_ns()))
-		goto out_err;
-
-	sb->s_d_op = &ovl_dentry_operations;
-
-	err = -ENOMEM;
-	ofs->creator_cred = cred = prepare_creds();
-	if (!cred)
-		goto out_err;
-
 	err = ovl_fs_params_verify(ctx, &ofs->config);
 	if (err)
-		goto out_err;
+		return err;
 
 	err = -EINVAL;
 	if (ctx->nr == 0) {
 		if (!(fc->sb_flags & SB_SILENT))
 			pr_err("missing 'lowerdir'\n");
-		goto out_err;
+		return err;
 	}
 
 	err = -ENOMEM;
 	layers = kcalloc(ctx->nr + 1, sizeof(struct ovl_layer), GFP_KERNEL);
 	if (!layers)
-		goto out_err;
+		return err;
 
 	ofs->config.lowerdirs = kcalloc(ctx->nr + 1, sizeof(char *), GFP_KERNEL);
 	if (!ofs->config.lowerdirs) {
 		kfree(layers);
-		goto out_err;
+		return err;
 	}
 	ofs->layers = layers;
 	/*
@@ -1356,12 +1433,12 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc)
 		err = -EINVAL;
 		if (!ofs->config.workdir) {
 			pr_err("missing 'workdir'\n");
-			goto out_err;
+			return err;
 		}
 
 		err = ovl_get_upper(sb, ofs, &layers[0], &ctx->upper);
 		if (err)
-			goto out_err;
+			return err;
 
 		upper_sb = ovl_upper_mnt(ofs)->mnt_sb;
 		if (!ovl_should_sync(ofs)) {
@@ -1369,13 +1446,13 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc)
 			if (errseq_check(&upper_sb->s_wb_err, ofs->errseq)) {
 				err = -EIO;
 				pr_err("Cannot mount volatile when upperdir has an unseen error. Sync upperdir fs to clear state.\n");
-				goto out_err;
+				return err;
 			}
 		}
 
 		err = ovl_get_workdir(sb, ofs, &ctx->upper, &ctx->work);
 		if (err)
-			goto out_err;
+			return err;
 
 		if (!ofs->workdir)
 			sb->s_flags |= SB_RDONLY;
@@ -1386,7 +1463,7 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc)
 	oe = ovl_get_lowerstack(sb, ctx, ofs, layers);
 	err = PTR_ERR(oe);
 	if (IS_ERR(oe))
-		goto out_err;
+		return err;
 
 	/* If the upper fs is nonexistent, we mark overlayfs r/o too */
 	if (!ovl_upper_mnt(ofs))
@@ -1439,7 +1516,7 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc)
 		sb->s_export_op = &ovl_export_fid_operations;
 
 	/* Never override disk quota limits or use reserved space */
-	cap_lower(cred->cap_effective, CAP_SYS_RESOURCE);
+	cap_lower(creator_cred->cap_effective, CAP_SYS_RESOURCE);
 
 	sb->s_magic = OVERLAYFS_SUPER_MAGIC;
 	sb->s_xattr = ovl_xattr_handlers(ofs);
@@ -1457,19 +1534,44 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_iflags |= SB_I_EVM_HMAC_UNSUPPORTED;
 
 	err = -ENOMEM;
-	root_dentry = ovl_get_root(sb, ctx->upper.dentry, oe);
-	if (!root_dentry)
+	sb->s_root = ovl_get_root(sb, ctx->upper.dentry, oe);
+	if (!sb->s_root)
 		goto out_free_oe;
 
-	sb->s_root = root_dentry;
-
 	return 0;
 
 out_free_oe:
 	ovl_free_entry(oe);
+	return err;
+}
+
+int ovl_fill_super(struct super_block *sb, struct fs_context *fc)
+{
+	struct ovl_fs *ofs = sb->s_fs_info;
+	int err;
+
+	err = -EIO;
+	if (WARN_ON(fc->user_ns != current_user_ns()))
+		goto out_err;
+
+	ovl_set_d_op(sb);
+
+	if (!ofs->creator_cred) {
+		err = -ENOMEM;
+		ofs->creator_cred = prepare_creds();
+		if (!ofs->creator_cred)
+			goto out_err;
+	}
+
+	with_ovl_creds(sb)
+		err = ovl_fill_super_creds(fc, sb);
+
 out_err:
-	ovl_free_fs(ofs);
-	sb->s_fs_info = NULL;
+	if (err) {
+		ovl_free_fs(ofs);
+		sb->s_fs_info = NULL;
+	}
+
 	return err;
 }