aufs: writable branch select policy 1/2, core

Aufs can have multiple writable branches, and there are several
policies to select one among them.
This commit implements default "top-down-parent" for both of
creating-policy and copyup-policy.

See also the document in this commit.
Signed-off-by: J. R. Okajima <hooanon05g@gmail.com>

Documentation/filesystems/aufs/design/05wbr_policy.txt

+
+# Copyright (C) 2005-2019 Junjiro R. Okajima
+
+Policies to Select One among Multiple Writable Branches
+----------------------------------------------------------------------
+When the number of writable branch is more than one, aufs has to decide
+the target branch for file creation or copy-up. By default, the highest
+writable branch which has the parent (or ancestor) dir of the target
+file is chosen (top-down-parent policy).
+By user's request, aufs implements some other policies to select the
+writable branch, for file creation several policies, round-robin,
+most-free-space, and other policies. For copy-up, top-down-parent,
+bottom-up-parent, bottom-up and others.
+
+As expected, the round-robin policy selects the branch in circular. When
+you have two writable branches and creates 10 new files, 5 files will be
+created for each branch. mkdir(2) systemcall is an exception. When you
+create 10 new directories, all will be created on the same branch.
+And the most-free-space policy selects the one which has most free
+space among the writable branches. The amount of free space will be
+checked by aufs internally, and users can specify its time interval.
+
+The policies for copy-up is more simple,
+top-down-parent is equivalent to the same named on in create policy,
+bottom-up-parent selects the writable branch where the parent dir
+exists and the nearest upper one from the copyup-source,
+bottom-up selects the nearest upper writable branch from the
+copyup-source, regardless the existence of the parent dir.
+
+There are some rules or exceptions to apply these policies.
+- If there is a readonly branch above the policy-selected branch and
+  the parent dir is marked as opaque (a variation of whiteout), or the
+  target (creating) file is whiteout-ed on the upper readonly branch,
+  then the result of the policy is ignored and the target file will be
+  created on the nearest upper writable branch than the readonly branch.
+- If there is a writable branch above the policy-selected branch and
+  the parent dir is marked as opaque or the target file is whiteouted
+  on the branch, then the result of the policy is ignored and the target
+  file will be created on the highest one among the upper writable
+  branches who has diropq or whiteout. In case of whiteout, aufs removes
+  it as usual.
+- link(2) and rename(2) systemcalls are exceptions in every policy.
+  They try selecting the branch where the source exists as possible
+  since copyup a large file will take long time. If it can't be,
+  ie. the branch where the source exists is readonly, then they will
+  follow the copyup policy.
+- There is an exception for rename(2) when the target exists.
+  If the rename target exists, aufs compares the index of the branches
+  where the source and the target exists and selects the higher
+  one. If the selected branch is readonly, then aufs follows the
+  copyup policy.

fs/aufs/Makefile

@@ -12,7 +12,7 @@ ccflags-y += -include ${srctree}/include/uapi/linux/aufs_type.h
 obj-$(CONFIG_AUFS_FS) += aufs.o
 aufs-y := module.o sbinfo.o super.o branch.o xino.o sysaufs.o opts.o \
 	wkq.o vfsub.o dcsub.o \
-	cpup.o whout.o \
+	cpup.o whout.o wbr_policy.o \
 	dinfo.o dentry.o \
 	file.o \
 	dir.o \

fs/aufs/opts.c

@@ -22,6 +22,7 @@ enum {
 	Opt_trunc_xino_path, Opt_itrunc_xino,
 	Opt_trunc_xib, Opt_notrunc_xib,
 	Opt_plink, Opt_noplink, Opt_list_plink,
+	Opt_wbr_copyup, Opt_wbr_create,
 	Opt_tail, Opt_ignore, Opt_ignore_silent, Opt_err
 };
 
@@ -52,6 +53,12 @@ static match_table_t options = {
 	{Opt_list_plink, "list_plink"},
 #endif
 
+	{Opt_wbr_create, "create=%s"},
+	{Opt_wbr_create, "create_policy=%s"},
+	{Opt_wbr_copyup, "cpup=%s"},
+	{Opt_wbr_copyup, "copyup=%s"},
+	{Opt_wbr_copyup, "copyup_policy=%s"},
+
 	/* internal use for the scripts */
 	{Opt_ignore_silent, "si=%s"},
 
@@ -63,6 +70,20 @@ static match_table_t options = {
 
 /* ---------------------------------------------------------------------- */
 
+static const char *au_parser_pattern(int val, match_table_t tbl)
+{
+	struct match_token *p;
+
+	p = tbl;
+	while (p->pattern) {
+		if (p->token == val)
+			return p->pattern;
+		p++;
+	}
+	BUG();
+	return "??";
+}
+
 static const char *au_optstr(int *val, match_table_t tbl)
 {
 	struct match_token *p;
@@ -231,6 +252,51 @@ void au_optstr_br_perm(au_br_perm_str_t *str, int perm)
 
 /* ---------------------------------------------------------------------- */
 
+static match_table_t au_wbr_create_policy = {
+	{AuWbrCreate_TDP, "tdp"},
+	{AuWbrCreate_TDP, "top-down-parent"},
+
+	/* add more later */
+	{-1, NULL}
+};
+
+static int noinline_for_stack
+au_wbr_create_val(char *str, struct au_opt_wbr_create *create)
+{
+	int err;
+	substring_t args[MAX_OPT_ARGS];
+
+	err = match_token(str, au_wbr_create_policy, args);
+	create->wbr_create = err;
+
+	return err;
+}
+
+const char *au_optstr_wbr_create(int wbr_create)
+{
+	return au_parser_pattern(wbr_create, au_wbr_create_policy);
+}
+
+static match_table_t au_wbr_copyup_policy = {
+	{AuWbrCopyup_TDP, "tdp"},
+	{AuWbrCopyup_TDP, "top-down-parent"},
+	{-1, NULL}
+};
+
+static int noinline_for_stack au_wbr_copyup_val(char *str)
+{
+	substring_t args[MAX_OPT_ARGS];
+
+	return match_token(str, au_wbr_copyup_policy, args);
+}
+
+const char *au_optstr_wbr_copyup(int wbr_copyup)
+{
+	return au_parser_pattern(wbr_copyup, au_wbr_copyup_policy);
+}
+
+/* ---------------------------------------------------------------------- */
+
 static const int lkup_dirflags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
 
 static void dump_opts(struct au_opts *opts)
@@ -241,6 +307,7 @@ static void dump_opts(struct au_opts *opts)
 		struct au_opt_add *add;
 		struct au_opt_xino *xino;
 		struct au_opt_xino_itrunc *xino_itrunc;
+		struct au_opt_wbr_create *create;
 	} u;
 	struct au_opt *opt;
 
@@ -286,6 +353,15 @@ static void dump_opts(struct au_opts *opts)
 		case Opt_list_plink:
 			AuLabel(list_plink);
 			break;
+		case Opt_wbr_create:
+			u.create = &opt->wbr_create;
+			AuDbg("create %d, %s\n", u.create->wbr_create,
+				  au_optstr_wbr_create(u.create->wbr_create));
+			break;
+		case Opt_wbr_copyup:
+			AuDbg("copyup %d, %s\n", opt->wbr_copyup,
+				  au_optstr_wbr_copyup(opt->wbr_copyup));
+			break;
 		default:
 			BUG();
 		}
@@ -520,6 +596,25 @@ int au_opts_parse(struct super_block *sb, char *str, struct au_opts *opts)
 			opt->type = token;
 			break;
 
+		case Opt_wbr_create:
+			u.create = &opt->wbr_create;
+			u.create->wbr_create
+				= au_wbr_create_val(a->args[0].from, u.create);
+			if (u.create->wbr_create >= 0) {
+				err = 0;
+				opt->type = token;
+			} else
+				pr_err("wrong value, %s\n", opt_str);
+			break;
+		case Opt_wbr_copyup:
+			opt->wbr_copyup = au_wbr_copyup_val(a->args[0].from);
+			if (opt->wbr_copyup >= 0) {
+				err = 0;
+				opt->type = token;
+			} else
+				pr_err("wrong value, %s\n", opt_str);
+			break;
+
 		case Opt_ignore:
 			pr_warn("ignored %s\n", opt_str);
 			/*FALLTHROUGH*/
@@ -552,6 +647,31 @@ out:
 	return err;
 }
 
+static int au_opt_wbr_create(struct super_block *sb,
+			     struct au_opt_wbr_create *create)
+{
+	int err;
+	struct au_sbinfo *sbinfo;
+
+	SiMustWriteLock(sb);
+
+	err = 1; /* handled */
+	sbinfo = au_sbi(sb);
+	if (sbinfo->si_wbr_create_ops->fin) {
+		err = sbinfo->si_wbr_create_ops->fin(sb);
+		if (!err)
+			err = 1;
+	}
+
+	sbinfo->si_wbr_create = create->wbr_create;
+	sbinfo->si_wbr_create_ops = au_wbr_create_ops + create->wbr_create;
+
+	if (sbinfo->si_wbr_create_ops->init)
+		sbinfo->si_wbr_create_ops->init(sb); /* ignore */
+
+	return err;
+}
+
 /*
  * returns,
  * plus: processed without an error
@@ -581,6 +701,14 @@ static int au_opt_simple(struct super_block *sb, struct au_opt *opt,
 			au_plink_list(sb);
 		break;
 
+	case Opt_wbr_create:
+		err = au_opt_wbr_create(sb, &opt->wbr_create);
+		break;
+	case Opt_wbr_copyup:
+		sbinfo->si_wbr_copyup = opt->wbr_copyup;
+		sbinfo->si_wbr_copyup_ops = au_wbr_copyup_ops + opt->wbr_copyup;
+		break;
+
 	case Opt_trunc_xino:
 		au_opt_set(sbinfo->si_mntflags, TRUNC_XINO);
 		break;

fs/aufs/opts.h

@@ -46,6 +46,23 @@ static inline unsigned int au_opts_plink(unsigned int mntflags)
 
 /* ---------------------------------------------------------------------- */
 
+/* policies to select one among multiple writable branches */
+enum {
+	AuWbrCreate_TDP,	/* top down parent */
+	/* add more later */
+
+	AuWbrCreate_Def = AuWbrCreate_TDP
+};
+
+enum {
+	AuWbrCopyup_TDP,	/* top down parent */
+	/* add more later */
+
+	AuWbrCopyup_Def = AuWbrCopyup_TDP
+};
+
+/* ---------------------------------------------------------------------- */
+
 struct au_opt_add {
 	aufs_bindex_t	bindex;
 	char		*pathname;
@@ -62,12 +79,19 @@ struct au_opt_xino_itrunc {
 	aufs_bindex_t	bindex;
 };
 
+struct au_opt_wbr_create {
+	int			wbr_create;
+	/* add more later */
+};
+
 struct au_opt {
 	int type;
 	union {
 		struct au_opt_xino	xino;
 		struct au_opt_xino_itrunc xino_itrunc;
 		struct au_opt_add	add;
+		struct au_opt_wbr_create wbr_create;
+		int			wbr_copyup;
 		/* add more later */
 	};
 };
@@ -92,6 +116,8 @@ struct au_opts {
 
 /* opts.c */
 void au_optstr_br_perm(au_br_perm_str_t *str, int perm);
+const char *au_optstr_wbr_copyup(int wbr_copyup);
+const char *au_optstr_wbr_create(int wbr_create);
 
 void au_opts_free(struct au_opts *opts);
 struct super_block;

fs/aufs/sbinfo.c

@@ -60,6 +60,11 @@ int au_si_alloc(struct super_block *sb)
 	sbinfo->si_bbot = -1;
 	sbinfo->si_last_br_id = AUFS_BRANCH_MAX / 2;
 
+	sbinfo->si_wbr_copyup = AuWbrCopyup_Def;
+	sbinfo->si_wbr_create = AuWbrCreate_Def;
+	sbinfo->si_wbr_copyup_ops = au_wbr_copyup_ops + sbinfo->si_wbr_copyup;
+	sbinfo->si_wbr_create_ops = au_wbr_create_ops + sbinfo->si_wbr_create;
+
 	sbinfo->si_mntflags = au_opts_plink(AuOpt_Def);
 
 	sbinfo->si_xino_jiffy = jiffies;

fs/aufs/super.c

@@ -103,6 +103,24 @@ static int au_show_brs(struct seq_file *seq, struct super_block *sb)
 	return err;
 }
 
+/* re-commit later */ __maybe_unused
+static void au_show_wbr_create(struct seq_file *m, int v,
+			       struct au_sbinfo *sbinfo)
+{
+	const char *pat;
+
+	AuRwMustAnyLock(&sbinfo->si_rwsem);
+
+	seq_puts(m, ",create=");
+	pat = au_optstr_wbr_create(v);
+	switch (v) {
+	case AuWbrCreate_TDP:
+		seq_puts(m, pat);
+		break;
+		break;
+	}
+}
+
 /* re-commit later */ __maybe_unused
 static int au_show_xino(struct seq_file *seq, struct super_block *sb)
 {

fs/aufs/super.h

@@ -18,6 +18,24 @@
 #include "rwsem.h"
 #include "wkq.h"
 
+/* policies to select one among multiple writable branches */
+struct au_wbr_copyup_operations {
+	int (*copyup)(struct dentry *dentry);
+};
+
+#define AuWbr_DIR	1		/* target is a dir */
+#define AuWbr_PARENT	(1 << 1)	/* always require a parent */
+
+#define au_ftest_wbr(flags, name)	((flags) & AuWbr_##name)
+#define au_fset_wbr(flags, name)	{ (flags) |= AuWbr_##name; }
+#define au_fclr_wbr(flags, name)	{ (flags) &= ~AuWbr_##name; }
+
+struct au_wbr_create_operations {
+	int (*create)(struct dentry *dentry, unsigned int flags);
+	int (*init)(struct super_block *sb);
+	int (*fin)(struct super_block *sb);
+};
+
 #define AuPlink_NHASH 100
 static inline int au_plink_hash(ino_t ino)
 {
@@ -45,6 +63,12 @@ struct au_sbinfo {
 				sizeof(aufs_bindex_t) * BITS_PER_BYTE - 1;
 	struct au_branch	**si_branch;
 
+	/* policy to select a writable branch */
+	unsigned char		si_wbr_copyup;
+	unsigned char		si_wbr_create;
+	struct au_wbr_copyup_operations *si_wbr_copyup_ops;
+	struct au_wbr_create_operations *si_wbr_create_ops;
+
 	/* mount flags */
 	/* include/asm-ia64/siginfo.h defines a macro named si_flags */
 	unsigned int		si_mntflags;
@@ -89,6 +113,12 @@ struct au_sbinfo {
 
 /* ---------------------------------------------------------------------- */
 
+/* policy to select one among writable branches */
+#define AuWbrCopyup(sbinfo, ...) \
+	((sbinfo)->si_wbr_copyup_ops->copyup(__VA_ARGS__))
+#define AuWbrCreate(sbinfo, ...) \
+	((sbinfo)->si_wbr_create_ops->create(__VA_ARGS__))
+
 /* flags for si_read_lock()/aufs_read_lock()/di_read_lock() */
 #define AuLock_DW		1		/* write-lock dentry */
 #define AuLock_IR		(1 << 1)	/* read-lock inode */
@@ -118,6 +148,13 @@ aufs_bindex_t au_new_br_id(struct super_block *sb);
 int si_read_lock(struct super_block *sb, int flags);
 int si_write_lock(struct super_block *sb, int flags);
 
+/* wbr_policy.c */
+extern struct au_wbr_copyup_operations au_wbr_copyup_ops[];
+extern struct au_wbr_create_operations au_wbr_create_ops[];
+int au_cpdown_dirs(struct dentry *dentry, aufs_bindex_t bdst);
+int au_wbr_nonopq(struct dentry *dentry, aufs_bindex_t bindex);
+int au_wbr_do_copyup_bu(struct dentry *dentry, aufs_bindex_t btop);
+
 /* ---------------------------------------------------------------------- */
 
 static inline struct au_sbinfo *au_sbi(struct super_block *sb)

fs/aufs/vfsub.c

@@ -316,6 +316,80 @@ ssize_t vfsub_write_k(struct file *file, void *kbuf, size_t count, loff_t *ppos)
 
 /* ---------------------------------------------------------------------- */
 
+struct au_vfsub_mkdir_args {
+	int *errp;
+	struct inode *dir;
+	struct path *path;
+	int mode;
+};
+
+static void au_call_vfsub_mkdir(void *args)
+{
+	struct au_vfsub_mkdir_args *a = args;
+	*a->errp = vfsub_mkdir(a->dir, a->path, a->mode);
+}
+
+int vfsub_sio_mkdir(struct inode *dir, struct path *path, int mode)
+{
+	int err, do_sio, wkq_err;
+
+	do_sio = au_test_h_perm_sio(dir, MAY_EXEC | MAY_WRITE);
+	if (!do_sio) {
+		lockdep_off();
+		err = vfsub_mkdir(dir, path, mode);
+		lockdep_on();
+	} else {
+		struct au_vfsub_mkdir_args args = {
+			.errp	= &err,
+			.dir	= dir,
+			.path	= path,
+			.mode	= mode
+		};
+		wkq_err = au_wkq_wait(au_call_vfsub_mkdir, &args);
+		if (unlikely(wkq_err))
+			err = wkq_err;
+	}
+
+	return err;
+}
+
+struct au_vfsub_rmdir_args {
+	int *errp;
+	struct inode *dir;
+	struct path *path;
+};
+
+static void au_call_vfsub_rmdir(void *args)
+{
+	struct au_vfsub_rmdir_args *a = args;
+	*a->errp = vfsub_rmdir(a->dir, a->path);
+}
+
+int vfsub_sio_rmdir(struct inode *dir, struct path *path)
+{
+	int err, do_sio, wkq_err;
+
+	do_sio = au_test_h_perm_sio(dir, MAY_EXEC | MAY_WRITE);
+	if (!do_sio) {
+		lockdep_off();
+		err = vfsub_rmdir(dir, path);
+		lockdep_on();
+	} else {
+		struct au_vfsub_rmdir_args args = {
+			.errp	= &err,
+			.dir	= dir,
+			.path	= path
+		};
+		wkq_err = au_wkq_wait(au_call_vfsub_rmdir, &args);
+		if (unlikely(wkq_err))
+			err = wkq_err;
+	}
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
 struct notify_change_args {
 	int *errp;
 	struct path *path;

fs/aufs/vfsub.h

@@ -138,6 +138,8 @@ static inline loff_t vfsub_llseek(struct file *file, loff_t offset, int origin)
 
 /* ---------------------------------------------------------------------- */
 
+int vfsub_sio_mkdir(struct inode *dir, struct path *path, int mode);
+int vfsub_sio_rmdir(struct inode *dir, struct path *path);
 int vfsub_sio_notify_change(struct path *path, struct iattr *ia,
 			    struct inode **delegated_inode);
 int vfsub_notify_change(struct path *path, struct iattr *ia,

fs/aufs/wbr_policy.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2005-2019 Junjiro R. Okajima
+ */
+
+/*
+ * policies for selecting one among multiple writable branches
+ */
+
+#include "aufs.h"
+
+/* subset of cpup_attr() */
+static noinline_for_stack
+int au_cpdown_attr(struct path *h_path, struct dentry *h_src)
+{
+	int err, sbits;
+	struct iattr ia;
+	struct inode *h_isrc;
+
+	h_isrc = d_inode(h_src);
+	ia.ia_valid = ATTR_FORCE | ATTR_MODE | ATTR_UID | ATTR_GID;
+	ia.ia_mode = h_isrc->i_mode;
+	ia.ia_uid = h_isrc->i_uid;
+	ia.ia_gid = h_isrc->i_gid;
+	sbits = !!(ia.ia_mode & (S_ISUID | S_ISGID));
+	au_cpup_attr_flags(d_inode(h_path->dentry), h_isrc->i_flags);
+	/* no delegation since it is just created */
+	err = vfsub_sio_notify_change(h_path, &ia, /*delegated*/NULL);
+
+	/* is this nfs only? */
+	if (!err && sbits && au_test_nfs(h_path->dentry->d_sb)) {
+		ia.ia_valid = ATTR_FORCE | ATTR_MODE;
+		ia.ia_mode = h_isrc->i_mode;
+		err = vfsub_sio_notify_change(h_path, &ia, /*delegated*/NULL);
+	}
+
+	return err;
+}
+
+#define AuCpdown_PARENT_OPQ	1
+#define AuCpdown_WHED		(1 << 1)
+#define AuCpdown_MADE_DIR	(1 << 2)
+#define AuCpdown_DIROPQ		(1 << 3)
+#define au_ftest_cpdown(flags, name)	((flags) & AuCpdown_##name)
+#define au_fset_cpdown(flags, name) \
+	do { (flags) |= AuCpdown_##name; } while (0)
+#define au_fclr_cpdown(flags, name) \
+	do { (flags) &= ~AuCpdown_##name; } while (0)
+
+static int au_cpdown_dir_opq(struct dentry *dentry, aufs_bindex_t bdst,
+			     unsigned int *flags)
+{
+	int err;
+	struct dentry *opq_dentry;
+
+	opq_dentry = au_diropq_create(dentry, bdst);
+	err = PTR_ERR(opq_dentry);
+	if (IS_ERR(opq_dentry))
+		goto out;
+	dput(opq_dentry);
+	au_fset_cpdown(*flags, DIROPQ);
+
+out:
+	return err;
+}
+
+static int au_cpdown_dir_wh(struct dentry *dentry, struct dentry *h_parent,
+			    struct inode *dir, aufs_bindex_t bdst)
+{
+	int err;
+	struct path h_path;
+	struct au_branch *br;
+
+	br = au_sbr(dentry->d_sb, bdst);
+	h_path.dentry = au_wh_lkup(h_parent, &dentry->d_name, br);
+	err = PTR_ERR(h_path.dentry);
+	if (IS_ERR(h_path.dentry))
+		goto out;
+
+	err = 0;
+	if (d_is_positive(h_path.dentry)) {
+		h_path.mnt = au_br_mnt(br);
+		err = au_wh_unlink_dentry(au_h_iptr(dir, bdst), &h_path,
+					  dentry);
+	}
+	dput(h_path.dentry);
+
+out:
+	return err;
+}
+
+static int au_cpdown_dir(struct dentry *dentry, aufs_bindex_t bdst,
+			 struct au_pin *pin,
+			 struct dentry *h_parent, void *arg)
+{
+	int err, rerr;
+	aufs_bindex_t bopq, btop;
+	struct path h_path;
+	struct dentry *parent;
+	struct inode *h_dir, *h_inode, *inode, *dir;
+	unsigned int *flags = arg;
+
+	btop = au_dbtop(dentry);
+	/* dentry is di-locked */
+	parent = dget_parent(dentry);
+	dir = d_inode(parent);
+	h_dir = d_inode(h_parent);
+	AuDebugOn(h_dir != au_h_iptr(dir, bdst));
+	IMustLock(h_dir);
+
+	err = au_lkup_neg(dentry, bdst, /*wh*/0);
+	if (unlikely(err < 0))
+		goto out;
+	h_path.dentry = au_h_dptr(dentry, bdst);
+	h_path.mnt = au_sbr_mnt(dentry->d_sb, bdst);
+	err = vfsub_sio_mkdir(au_h_iptr(dir, bdst), &h_path, 0755);
+	if (unlikely(err))
+		goto out_put;
+	au_fset_cpdown(*flags, MADE_DIR);
+
+	bopq = au_dbdiropq(dentry);
+	au_fclr_cpdown(*flags, WHED);
+	au_fclr_cpdown(*flags, DIROPQ);
+	if (au_dbwh(dentry) == bdst)
+		au_fset_cpdown(*flags, WHED);
+	if (!au_ftest_cpdown(*flags, PARENT_OPQ) && bopq <= bdst)
+		au_fset_cpdown(*flags, PARENT_OPQ);
+	h_inode = d_inode(h_path.dentry);
+	inode_lock_nested(h_inode, AuLsc_I_CHILD);
+	if (au_ftest_cpdown(*flags, WHED)) {
+		err = au_cpdown_dir_opq(dentry, bdst, flags);
+		if (unlikely(err)) {
+			inode_unlock(h_inode);
+			goto out_dir;
+		}
+	}
+
+	err = au_cpdown_attr(&h_path, au_h_dptr(dentry, btop));
+	inode_unlock(h_inode);
+	if (unlikely(err))
+		goto out_opq;
+
+	if (au_ftest_cpdown(*flags, WHED)) {
+		err = au_cpdown_dir_wh(dentry, h_parent, dir, bdst);
+		if (unlikely(err))
+			goto out_opq;
+	}
+
+	inode = d_inode(dentry);
+	if (au_ibbot(inode) < bdst)
+		au_set_ibbot(inode, bdst);
+	au_set_h_iptr(inode, bdst, au_igrab(h_inode),
+		      au_hi_flags(inode, /*isdir*/1));
+	goto out; /* success */
+
+	/* revert */
+out_opq:
+	if (au_ftest_cpdown(*flags, DIROPQ)) {
+		inode_lock_nested(h_inode, AuLsc_I_CHILD);
+		rerr = au_diropq_remove(dentry, bdst);
+		inode_unlock(h_inode);
+		if (unlikely(rerr)) {
+			AuIOErr("failed removing diropq for %pd b%d (%d)\n",
+				dentry, bdst, rerr);
+			err = -EIO;
+			goto out;
+		}
+	}
+out_dir:
+	if (au_ftest_cpdown(*flags, MADE_DIR)) {
+		rerr = vfsub_sio_rmdir(au_h_iptr(dir, bdst), &h_path);
+		if (unlikely(rerr)) {
+			AuIOErr("failed removing %pd b%d (%d)\n",
+				dentry, bdst, rerr);
+			err = -EIO;
+		}
+	}
+out_put:
+	au_set_h_dptr(dentry, bdst, NULL);
+	if (au_dbbot(dentry) == bdst)
+		au_update_dbbot(dentry);
+out:
+	dput(parent);
+	return err;
+}
+
+int au_cpdown_dirs(struct dentry *dentry, aufs_bindex_t bdst)
+{
+	int err;
+	unsigned int flags;
+
+	flags = 0;
+	err = au_cp_dirs(dentry, bdst, au_cpdown_dir, &flags);
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* policies for create */
+
+int au_wbr_nonopq(struct dentry *dentry, aufs_bindex_t bindex)
+{
+	int err, i, j, ndentry;
+	aufs_bindex_t bopq;
+	struct au_dcsub_pages dpages;
+	struct au_dpage *dpage;
+	struct dentry **dentries, *parent, *d;
+
+	err = au_dpages_init(&dpages, GFP_NOFS);
+	if (unlikely(err))
+		goto out;
+	parent = dget_parent(dentry);
+	err = au_dcsub_pages_rev_aufs(&dpages, parent, /*do_include*/0);
+	if (unlikely(err))
+		goto out_free;
+
+	err = bindex;
+	for (i = 0; i < dpages.ndpage; i++) {
+		dpage = dpages.dpages + i;
+		dentries = dpage->dentries;
+		ndentry = dpage->ndentry;
+		for (j = 0; j < ndentry; j++) {
+			d = dentries[j];
+			di_read_lock_parent2(d, !AuLock_IR);
+			bopq = au_dbdiropq(d);
+			di_read_unlock(d, !AuLock_IR);
+			if (bopq >= 0 && bopq < err)
+				err = bopq;
+		}
+	}
+
+out_free:
+	dput(parent);
+	au_dpages_free(&dpages);
+out:
+	return err;
+}
+
+static int au_wbr_bu(struct super_block *sb, aufs_bindex_t bindex)
+{
+	for (; bindex >= 0; bindex--)
+		if (!au_br_rdonly(au_sbr(sb, bindex)))
+			return bindex;
+	return -EROFS;
+}
+
+/* top down parent */
+static int au_wbr_create_tdp(struct dentry *dentry,
+			     unsigned int flags __maybe_unused)
+{
+	int err;
+	aufs_bindex_t btop, bindex;
+	struct super_block *sb;
+	struct dentry *parent, *h_parent;
+
+	sb = dentry->d_sb;
+	btop = au_dbtop(dentry);
+	err = btop;
+	if (!au_br_rdonly(au_sbr(sb, btop)))
+		goto out;
+
+	err = -EROFS;
+	parent = dget_parent(dentry);
+	for (bindex = au_dbtop(parent); bindex < btop; bindex++) {
+		h_parent = au_h_dptr(parent, bindex);
+		if (!h_parent || d_is_negative(h_parent))
+			continue;
+
+		if (!au_br_rdonly(au_sbr(sb, bindex))) {
+			err = bindex;
+			break;
+		}
+	}
+	dput(parent);
+
+	/* bottom up here */
+	if (unlikely(err < 0)) {
+		err = au_wbr_bu(sb, btop - 1);
+		if (err >= 0)
+			err = au_wbr_nonopq(dentry, err);
+	}
+
+out:
+	AuDbg("b%d\n", err);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* policies for copyup */
+
+/* top down parent */
+static int au_wbr_copyup_tdp(struct dentry *dentry)
+{
+	return au_wbr_create_tdp(dentry, /*flags, anything is ok*/0);
+}
+
+/* ---------------------------------------------------------------------- */
+
+struct au_wbr_copyup_operations au_wbr_copyup_ops[] = {
+	[AuWbrCopyup_TDP] = {
+		.copyup	= au_wbr_copyup_tdp
+	}
+};
+
+struct au_wbr_create_operations au_wbr_create_ops[] = {
+	[AuWbrCreate_TDP] = {
+		.create	= au_wbr_create_tdp
+	}
+};