aufs5.7-20200622.patch

+	static struct {
+		char *name;
+		struct lock_class_key *key;
+	} a[] = {
+		{ .name = "&sbinfo->si_rwsem" },
+		{ .name = "&finfo->fi_rwsem" },
+		{ .name = "&dinfo->di_rwsem" },
+		{ .name = "&iinfo->ii_rwsem" }
+	};
+	static int set;
+	int i;
+
+	/* lockless read from 'set.' see below */
+	if (set == ARRAY_SIZE(a)) {
+		for (i = 0; i < ARRAY_SIZE(a); i++)
+			if (a[i].key == key)
+				goto match;
+		goto unmatch;
+	}
+
+	spin_lock(&spin);
+	if (set)
+		for (i = 0; i < ARRAY_SIZE(a); i++)
+			if (a[i].key == key) {
+				spin_unlock(&spin);
+				goto match;
+			}
+	for (i = 0; i < ARRAY_SIZE(a); i++) {
+		if (a[i].key) {
+			if (unlikely(a[i].key == key)) { /* rare but possible */
+				spin_unlock(&spin);
+				goto match;
+			} else
+				continue;
+		}
+		if (strstr(a[i].name, name)) {
+			/*
+			 * the order of these three lines is important for the
+			 * lockless read above.
+			 */
+			a[i].key = key;
+			spin_unlock(&spin);
+			set++;
+			/* AuDbg("%d, %s\n", set, name); */
+			goto match;
+		}
+	}
+	spin_unlock(&spin);
+	goto unmatch;
+
+match:
+	return 1;
+unmatch:
+	return 0;
+}
+
+static int au_wkq_lockdep_alloc(struct au_wkinfo *wkinfo)
+{
+	int err, n;
+	struct task_struct *curr;
+	struct held_lock **hl, *held_locks, *p;
+
+	err = 0;
+	curr = current;
+	wkinfo->dont_check = lockdep_recursing(curr);
+	if (wkinfo->dont_check)
+		goto out;
+	n = curr->lockdep_depth;
+	if (!n)
+		goto out;
+
+	err = -ENOMEM;
+	wkinfo->hlock = kmalloc_array(n + 1, sizeof(*wkinfo->hlock), GFP_NOFS);
+	if (unlikely(!wkinfo->hlock))
+		goto out;
+
+	err = 0;
+#if 0 /* left for debugging */
+	if (0 && au_debug_test())
+		lockdep_print_held_locks(curr);
+#endif
+	held_locks = curr->held_locks;
+	hl = wkinfo->hlock;
+	while (n--) {
+		p = held_locks++;
+		if (au_wkq_lockdep_test(p->instance->key, p->instance->name))
+			*hl++ = p;
+	}
+	*hl = NULL;
+
+out:
+	return err;
+}
+
+static void au_wkq_lockdep_free(struct au_wkinfo *wkinfo)
+{
+	au_kfree_try_rcu(wkinfo->hlock);
+}
+
+static void au_wkq_lockdep_pre(struct au_wkinfo *wkinfo)
+{
+	struct held_lock *p, **hl = wkinfo->hlock;
+	int subclass;
+
+	if (wkinfo->dont_check)
+		lockdep_off();
+	if (!hl)
+		return;
+	while ((p = *hl++)) { /* assignment */
+		subclass = lockdep_hlock_class(p)->subclass;
+		/* AuDbg("%s, %d\n", p->instance->name, subclass); */
+		if (p->read)
+			rwsem_acquire_read(p->instance, subclass, 0,
+					   /*p->acquire_ip*/_RET_IP_);
+		else
+			rwsem_acquire(p->instance, subclass, 0,
+				      /*p->acquire_ip*/_RET_IP_);
+	}
+}
+
+static void au_wkq_lockdep_post(struct au_wkinfo *wkinfo)
+{
+	struct held_lock *p, **hl = wkinfo->hlock;
+
+	if (wkinfo->dont_check)
+		lockdep_on();
+	if (!hl)
+		return;
+	while ((p = *hl++)) /* assignment */
+		rwsem_release(p->instance, /*p->acquire_ip*/_RET_IP_);
+}
+#endif
+
+static void wkq_func(struct work_struct *wk)
+{
+	struct au_wkinfo *wkinfo = container_of(wk, struct au_wkinfo, wk);
+
+	AuDebugOn(!uid_eq(current_fsuid(), GLOBAL_ROOT_UID));
+	AuDebugOn(rlimit(RLIMIT_FSIZE) != RLIM_INFINITY);
+
+	au_wkq_lockdep_pre(wkinfo);
+	wkinfo->func(wkinfo->args);
+	au_wkq_lockdep_post(wkinfo);
+	if (au_ftest_wkq(wkinfo->flags, WAIT))
+		complete(wkinfo->comp);
+	else {
+		kobject_put(wkinfo->kobj);
+		module_put(THIS_MODULE); /* todo: ?? */
+		au_kfree_rcu(wkinfo);
+	}
+}
+
+/*
+ * Since struct completion is large, try allocating it dynamically.
+ */
+#define AuWkqCompDeclare(name)	struct completion *comp = NULL
+
+static int au_wkq_comp_alloc(struct au_wkinfo *wkinfo, struct completion **comp)
+{
+	*comp = kmalloc(sizeof(**comp), GFP_NOFS);
+	if (*comp) {
+		init_completion(*comp);
+		wkinfo->comp = *comp;
+		return 0;
+	}
+	return -ENOMEM;
+}
+
+static void au_wkq_comp_free(struct completion *comp)
+{
+	au_kfree_rcu(comp);
+}
+
+static void au_wkq_run(struct au_wkinfo *wkinfo)
+{
+	if (au_ftest_wkq(wkinfo->flags, NEST)) {
+		if (au_wkq_test()) {
+			AuWarn1("wkq from wkq, unless silly-rename on NFS,"
+				" due to a dead dir by UDBA,"
+				" or async xino write?\n");
+			AuDebugOn(au_ftest_wkq(wkinfo->flags, WAIT));
+		}
+	} else
+		au_dbg_verify_kthread();
+
+	if (au_ftest_wkq(wkinfo->flags, WAIT)) {
+		INIT_WORK_ONSTACK(&wkinfo->wk, wkq_func);
+		queue_work(au_wkq, &wkinfo->wk);
+	} else {
+		INIT_WORK(&wkinfo->wk, wkq_func);
+		schedule_work(&wkinfo->wk);
+	}
+}
+
+/*
+ * Be careful. It is easy to make deadlock happen.
+ * processA: lock, wkq and wait
+ * processB: wkq and wait, lock in wkq
+ * --> deadlock
+ */
+int au_wkq_do_wait(unsigned int flags, au_wkq_func_t func, void *args)
+{
+	int err;
+	AuWkqCompDeclare(comp);
+	struct au_wkinfo wkinfo = {
+		.flags	= flags,
+		.func	= func,
+		.args	= args
+	};
+
+	err = au_wkq_comp_alloc(&wkinfo, &comp);
+	if (unlikely(err))
+		goto out;
+	err = au_wkq_lockdep_alloc(&wkinfo);
+	if (unlikely(err))
+		goto out_comp;
+	if (!err) {
+		au_wkq_run(&wkinfo);
+		/* no timeout, no interrupt */
+		wait_for_completion(wkinfo.comp);
+	}
+	au_wkq_lockdep_free(&wkinfo);
+
+out_comp:
+	au_wkq_comp_free(comp);
+out:
+	destroy_work_on_stack(&wkinfo.wk);
+	return err;
+}
+
+/*
+ * Note: dget/dput() in func for aufs dentries are not supported. It will be a
+ * problem in a concurrent umounting.
+ */
+int au_wkq_nowait(au_wkq_func_t func, void *args, struct super_block *sb,
+		  unsigned int flags)
+{
+	int err;
+	struct au_wkinfo *wkinfo;
+
+	atomic_inc(&au_sbi(sb)->si_nowait.nw_len);
+
+	/*
+	 * wkq_func() must free this wkinfo.
+	 * it highly depends upon the implementation of workqueue.
+	 */
+	err = 0;
+	wkinfo = kmalloc(sizeof(*wkinfo), GFP_NOFS);
+	if (wkinfo) {
+		wkinfo->kobj = &au_sbi(sb)->si_kobj;
+		wkinfo->flags = flags & ~AuWkq_WAIT;
+		wkinfo->func = func;
+		wkinfo->args = args;
+		wkinfo->comp = NULL;
+		au_wkq_lockdep_init(wkinfo);
+		kobject_get(wkinfo->kobj);
+		__module_get(THIS_MODULE); /* todo: ?? */
+
+		au_wkq_run(wkinfo);
+	} else {
+		err = -ENOMEM;
+		au_nwt_done(&au_sbi(sb)->si_nowait);
+	}
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+void au_nwt_init(struct au_nowait_tasks *nwt)
+{
+	atomic_set(&nwt->nw_len, 0);
+	/* smp_mb(); */ /* atomic_set */
+	init_waitqueue_head(&nwt->nw_wq);
+}
+
+void au_wkq_fin(void)
+{
+	destroy_workqueue(au_wkq);
+}
+
+int __init au_wkq_init(void)
+{
+	int err;
+
+	err = 0;
+	au_wkq = alloc_workqueue(AUFS_WKQ_NAME, 0, WQ_DFL_ACTIVE);
+	if (IS_ERR(au_wkq))
+		err = PTR_ERR(au_wkq);
+	else if (!au_wkq)
+		err = -ENOMEM;
+
+	return err;
+}
diff -Naur null/fs/aufs/wkq.h linux-5.7/fs/aufs/wkq.h
--- /dev/null
+++ linux-5.7/fs/aufs/wkq.h	2020-08-22 11:57:41.475116229 +0200
@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2005-2020 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * workqueue for asynchronous/super-io operations
+ * todo: try new credentials management scheme
+ */
+
+#ifndef __AUFS_WKQ_H__
+#define __AUFS_WKQ_H__
+
+#ifdef __KERNEL__
+
+#include <linux/wait.h>
+
+struct super_block;
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * in the next operation, wait for the 'nowait' tasks in system-wide workqueue
+ */
+struct au_nowait_tasks {
+	atomic_t		nw_len;
+	wait_queue_head_t	nw_wq;
+};
+
+/* ---------------------------------------------------------------------- */
+
+typedef void (*au_wkq_func_t)(void *args);
+
+/* wkq flags */
+#define AuWkq_WAIT	1
+#define AuWkq_NEST	(1 << 1)
+#define au_ftest_wkq(flags, name)	((flags) & AuWkq_##name)
+#define au_fset_wkq(flags, name) \
+	do { (flags) |= AuWkq_##name; } while (0)
+#define au_fclr_wkq(flags, name) \
+	do { (flags) &= ~AuWkq_##name; } while (0)
+
+/* wkq.c */
+int au_wkq_do_wait(unsigned int flags, au_wkq_func_t func, void *args);
+int au_wkq_nowait(au_wkq_func_t func, void *args, struct super_block *sb,
+		  unsigned int flags);
+void au_nwt_init(struct au_nowait_tasks *nwt);
+int __init au_wkq_init(void);
+void au_wkq_fin(void);
+
+/* ---------------------------------------------------------------------- */
+
+static inline int au_wkq_test(void)
+{
+	return current->flags & PF_WQ_WORKER;
+}
+
+static inline int au_wkq_wait(au_wkq_func_t func, void *args)
+{
+	return au_wkq_do_wait(AuWkq_WAIT, func, args);
+}
+
+static inline void au_nwt_done(struct au_nowait_tasks *nwt)
+{
+	if (atomic_dec_and_test(&nwt->nw_len))
+		wake_up_all(&nwt->nw_wq);
+}
+
+static inline int au_nwt_flush(struct au_nowait_tasks *nwt)
+{
+	wait_event(nwt->nw_wq, !atomic_read(&nwt->nw_len));
+	return 0;
+}
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_WKQ_H__ */
diff -Naur null/fs/aufs/xattr.c linux-5.7/fs/aufs/xattr.c
--- /dev/null
+++ linux-5.7/fs/aufs/xattr.c	2020-08-22 11:57:41.475116229 +0200
@@ -0,0 +1,356 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2014-2020 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * handling xattr functions
+ */
+
+#include <linux/fs.h>
+#include <linux/posix_acl_xattr.h>
+#include <linux/xattr.h>
+#include "aufs.h"
+
+static int au_xattr_ignore(int err, char *name, unsigned int ignore_flags)
+{
+	if (!ignore_flags)
+		goto out;
+	switch (err) {
+	case -ENOMEM:
+	case -EDQUOT:
+		goto out;
+	}
+
+	if ((ignore_flags & AuBrAttr_ICEX) == AuBrAttr_ICEX) {
+		err = 0;
+		goto out;
+	}
+
+#define cmp(brattr, prefix) do {					\
+		if (!strncmp(name, XATTR_##prefix##_PREFIX,		\
+			     XATTR_##prefix##_PREFIX_LEN)) {		\
+			if (ignore_flags & AuBrAttr_ICEX_##brattr)	\
+				err = 0;				\
+			goto out;					\
+		}							\
+	} while (0)
+
+	cmp(SEC, SECURITY);
+	cmp(SYS, SYSTEM);
+	cmp(TR, TRUSTED);
+	cmp(USR, USER);
+#undef cmp
+
+	if (ignore_flags & AuBrAttr_ICEX_OTH)
+		err = 0;
+
+out:
+	return err;
+}
+
+static const int au_xattr_out_of_list = AuBrAttr_ICEX_OTH << 1;
+
+static int au_do_cpup_xattr(struct dentry *h_dst, struct dentry *h_src,
+			    char *name, char **buf, unsigned int ignore_flags,
+			    unsigned int verbose)
+{
+	int err;
+	ssize_t ssz;
+	struct inode *h_idst;
+
+	ssz = vfs_getxattr_alloc(h_src, name, buf, 0, GFP_NOFS);
+	err = ssz;
+	if (unlikely(err <= 0)) {
+		if (err == -ENODATA
+		    || (err == -EOPNOTSUPP
+			&& ((ignore_flags & au_xattr_out_of_list)
+			    || (au_test_nfs_noacl(d_inode(h_src))
+				&& (!strcmp(name, XATTR_NAME_POSIX_ACL_ACCESS)
+				    || !strcmp(name,
+					       XATTR_NAME_POSIX_ACL_DEFAULT))))
+			    ))
+			err = 0;
+		if (err && (verbose || au_debug_test()))
+			pr_err("%s, err %d\n", name, err);
+		goto out;
+	}
+
+	/* unlock it temporary */
+	h_idst = d_inode(h_dst);
+	inode_unlock(h_idst);
+	err = vfsub_setxattr(h_dst, name, *buf, ssz, /*flags*/0);
+	inode_lock_nested(h_idst, AuLsc_I_CHILD2);
+	if (unlikely(err)) {
+		if (verbose || au_debug_test())
+			pr_err("%s, err %d\n", name, err);
+		err = au_xattr_ignore(err, name, ignore_flags);
+	}
+
+out:
+	return err;
+}
+
+int au_cpup_xattr(struct dentry *h_dst, struct dentry *h_src, int ignore_flags,
+		  unsigned int verbose)
+{
+	int err, unlocked, acl_access, acl_default;
+	ssize_t ssz;
+	struct inode *h_isrc, *h_idst;
+	char *value, *p, *o, *e;
+
+	/* try stopping to update the source inode while we are referencing */
+	/* there should not be the parent-child relationship between them */
+	h_isrc = d_inode(h_src);
+	h_idst = d_inode(h_dst);
+	inode_unlock(h_idst);
+	inode_lock_shared_nested(h_isrc, AuLsc_I_CHILD);
+	inode_lock_nested(h_idst, AuLsc_I_CHILD2);
+	unlocked = 0;
+
+	/* some filesystems don't list POSIX ACL, for example tmpfs */
+	ssz = vfs_listxattr(h_src, NULL, 0);
+	err = ssz;
+	if (unlikely(err < 0)) {
+		AuTraceErr(err);
+		if (err == -ENODATA
+		    || err == -EOPNOTSUPP)
+			err = 0;	/* ignore */
+		goto out;
+	}
+
+	err = 0;
+	p = NULL;
+	o = NULL;
+	if (ssz) {
+		err = -ENOMEM;
+		p = kmalloc(ssz, GFP_NOFS);
+		o = p;
+		if (unlikely(!p))
+			goto out;
+		err = vfs_listxattr(h_src, p, ssz);
+	}
+	inode_unlock_shared(h_isrc);
+	unlocked = 1;
+	AuDbg("err %d, ssz %zd\n", err, ssz);
+	if (unlikely(err < 0))
+		goto out_free;
+
+	err = 0;
+	e = p + ssz;
+	value = NULL;
+	acl_access = 0;
+	acl_default = 0;
+	while (!err && p < e) {
+		acl_access |= !strncmp(p, XATTR_NAME_POSIX_ACL_ACCESS,
+				       sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1);
+		acl_default |= !strncmp(p, XATTR_NAME_POSIX_ACL_DEFAULT,
+					sizeof(XATTR_NAME_POSIX_ACL_DEFAULT)
+					- 1);
+		err = au_do_cpup_xattr(h_dst, h_src, p, &value, ignore_flags,
+				       verbose);
+		p += strlen(p) + 1;
+	}
+	AuTraceErr(err);
+	ignore_flags |= au_xattr_out_of_list;
+	if (!err && !acl_access) {
+		err = au_do_cpup_xattr(h_dst, h_src,
+				       XATTR_NAME_POSIX_ACL_ACCESS, &value,
+				       ignore_flags, verbose);
+		AuTraceErr(err);
+	}
+	if (!err && !acl_default) {
+		err = au_do_cpup_xattr(h_dst, h_src,
+				       XATTR_NAME_POSIX_ACL_DEFAULT, &value,
+				       ignore_flags, verbose);
+		AuTraceErr(err);
+	}
+
+	au_kfree_try_rcu(value);
+
+out_free:
+	au_kfree_try_rcu(o);
+out:
+	if (!unlocked)
+		inode_unlock_shared(h_isrc);
+	AuTraceErr(err);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_smack_reentering(struct super_block *sb)
+{
+#if IS_ENABLED(CONFIG_SECURITY_SMACK) || IS_ENABLED(CONFIG_SECURITY_SELINUX)
+	/*
+	 * as a part of lookup, smack_d_instantiate() is called, and it calls
+	 * i_op->getxattr(). ouch.
+	 */
+	return si_pid_test(sb);
+#else
+	return 0;
+#endif
+}
+
+enum {
+	AU_XATTR_LIST,
+	AU_XATTR_GET
+};
+
+struct au_lgxattr {
+	int type;
+	union {
+		struct {
+			char	*list;
+			size_t	size;
+		} list;
+		struct {
+			const char	*name;
+			void		*value;
+			size_t		size;
+		} get;
+	} u;
+};
+
+static ssize_t au_lgxattr(struct dentry *dentry, struct inode *inode,
+			  struct au_lgxattr *arg)
+{
+	ssize_t err;
+	int reenter;
+	struct path h_path;
+	struct super_block *sb;
+
+	sb = dentry->d_sb;
+	reenter = au_smack_reentering(sb);
+	if (!reenter) {
+		err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
+		if (unlikely(err))
+			goto out;
+	}
+	err = au_h_path_getattr(dentry, inode, /*force*/1, &h_path, reenter);
+	if (unlikely(err))
+		goto out_si;
+	if (unlikely(!h_path.dentry))
+		/* illegally overlapped or something */
+		goto out_di; /* pretending success */
+
+	/* always topmost entry only */
+	switch (arg->type) {
+	case AU_XATTR_LIST:
+		err = vfs_listxattr(h_path.dentry,
+				    arg->u.list.list, arg->u.list.size);
+		break;
+	case AU_XATTR_GET:
+		AuDebugOn(d_is_negative(h_path.dentry));
+		err = vfs_getxattr(h_path.dentry,
+				   arg->u.get.name, arg->u.get.value,
+				   arg->u.get.size);
+		break;
+	}
+
+out_di:
+	if (!reenter)
+		di_read_unlock(dentry, AuLock_IR);
+out_si:
+	if (!reenter)
+		si_read_unlock(sb);
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+ssize_t aufs_listxattr(struct dentry *dentry, char *list, size_t size)
+{
+	struct au_lgxattr arg = {
+		.type = AU_XATTR_LIST,
+		.u.list = {
+			.list	= list,
+			.size	= size
+		},
+	};
+
+	return au_lgxattr(dentry, /*inode*/NULL, &arg);
+}
+
+static ssize_t au_getxattr(struct dentry *dentry, struct inode *inode,
+			   const char *name, void *value, size_t size)
+{
+	struct au_lgxattr arg = {
+		.type = AU_XATTR_GET,
+		.u.get = {
+			.name	= name,
+			.value	= value,
+			.size	= size
+		},
+	};
+
+	return au_lgxattr(dentry, inode, &arg);
+}
+
+static int au_setxattr(struct dentry *dentry, struct inode *inode,
+		       const char *name, const void *value, size_t size,
+		       int flags)
+{
+	struct au_sxattr arg = {
+		.type = AU_XATTR_SET,
+		.u.set = {
+			.name	= name,
+			.value	= value,
+			.size	= size,
+			.flags	= flags
+		},
+	};
+
+	return au_sxattr(dentry, inode, &arg);
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_xattr_get(const struct xattr_handler *handler,
+			struct dentry *dentry, struct inode *inode,
+			const char *name, void *buffer, size_t size)
+{
+	return au_getxattr(dentry, inode, name, buffer, size);
+}
+
+static int au_xattr_set(const struct xattr_handler *handler,
+			struct dentry *dentry, struct inode *inode,
+			const char *name, const void *value, size_t size,
+			int flags)
+{
+	return au_setxattr(dentry, inode, name, value, size, flags);
+}
+
+static const struct xattr_handler au_xattr_handler = {
+	.name	= "",
+	.prefix	= "",
+	.get	= au_xattr_get,
+	.set	= au_xattr_set
+};
+
+static const struct xattr_handler *au_xattr_handlers[] = {
+#ifdef CONFIG_FS_POSIX_ACL
+	&posix_acl_access_xattr_handler,
+	&posix_acl_default_xattr_handler,
+#endif
+	&au_xattr_handler, /* must be last */
+	NULL
+};
+
+void au_xattr_init(struct super_block *sb)
+{
+	sb->s_xattr = au_xattr_handlers;
+}
diff -Naur null/fs/aufs/xino.c linux-5.7/fs/aufs/xino.c
--- /dev/null
+++ linux-5.7/fs/aufs/xino.c	2020-08-22 11:57:41.475116229 +0200
@@ -0,0 +1,1966 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2005-2020 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * external inode number translation table and bitmap
+ *
+ * things to consider
+ * - the lifetime
+ *   + au_xino object
+ *   + XINO files (xino, xib, xigen)
+ *   + dynamic debugfs entries (xiN)
+ *   + static debugfs entries (xib, xigen)
+ *   + static sysfs entry (xi_path)
+ * - several entry points to handle them.
+ *   + mount(2) without xino option (default)
+ *   + mount(2) with xino option
+ *   + mount(2) with noxino option
+ *   + umount(2)
+ *   + remount with add/del branches
+ *   + remount with xino/noxino options
+ */
+
+#include <linux/seq_file.h>
+#include <linux/statfs.h>
+#include "aufs.h"
+
+static aufs_bindex_t sbr_find_shared(struct super_block *sb, aufs_bindex_t btop,
+				     aufs_bindex_t bbot,
+				     struct super_block *h_sb)
+{
+	/* todo: try binary-search if the branches are many */
+	for (; btop <= bbot; btop++)
+		if (h_sb == au_sbr_sb(sb, btop))
+			return btop;
+	return -1;
+}
+
+/*
+ * find another branch who is on the same filesystem of the specified
+ * branch{@btgt}. search until @bbot.
+ */
+static aufs_bindex_t is_sb_shared(struct super_block *sb, aufs_bindex_t btgt,
+				  aufs_bindex_t bbot)
+{
+	aufs_bindex_t bindex;
+	struct super_block *tgt_sb;
+
+	tgt_sb = au_sbr_sb(sb, btgt);
+	bindex = sbr_find_shared(sb, /*btop*/0, btgt - 1, tgt_sb);
+	if (bindex < 0)
+		bindex = sbr_find_shared(sb, btgt + 1, bbot, tgt_sb);
+
+	return bindex;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * stop unnecessary notify events at creating xino files
+ */
+
+aufs_bindex_t au_xi_root(struct super_block *sb, struct dentry *dentry)
+{
+	aufs_bindex_t bfound, bindex, bbot;
+	struct dentry *parent;
+	struct au_branch *br;
+
+	bfound = -1;
+	parent = dentry->d_parent; /* safe d_parent access */
+	bbot = au_sbbot(sb);
+	for (bindex = 0; bindex <= bbot; bindex++) {
+		br = au_sbr(sb, bindex);
+		if (au_br_dentry(br) == parent) {
+			bfound = bindex;
+			break;
+		}
+	}
+
+	AuDbg("bfound b%d\n", bfound);
+	return bfound;
+}
+
+struct au_xino_lock_dir {
+	struct au_hinode *hdir;
+	struct dentry *parent;
+	struct inode *dir;
+};
+
+static struct dentry *au_dget_parent_lock(struct dentry *dentry,
+					  unsigned int lsc)
+{
+	struct dentry *parent;
+	struct inode *dir;
+
+	parent = dget_parent(dentry);
+	dir = d_inode(parent);
+	inode_lock_nested(dir, lsc);
+#if 0 /* it should not happen */
+	spin_lock(&dentry->d_lock);
+	if (unlikely(dentry->d_parent != parent)) {
+		spin_unlock(&dentry->d_lock);
+		inode_unlock(dir);
+		dput(parent);
+		parent = NULL;
+		goto out;
+	}
+	spin_unlock(&dentry->d_lock);
+
+out:
+#endif
+	return parent;
+}
+
+static void au_xino_lock_dir(struct super_block *sb, struct path *xipath,
+			     struct au_xino_lock_dir *ldir)
+{
+	aufs_bindex_t bindex;
+
+	ldir->hdir = NULL;
+	bindex = au_xi_root(sb, xipath->dentry);
+	if (bindex >= 0) {
+		/* rw branch root */
+		ldir->hdir = au_hi(d_inode(sb->s_root), bindex);
+		au_hn_inode_lock_nested(ldir->hdir, AuLsc_I_PARENT);
+	} else {
+		/* other */
+		ldir->parent = au_dget_parent_lock(xipath->dentry,
+						   AuLsc_I_PARENT);
+		ldir->dir = d_inode(ldir->parent);
+	}
+}
+
+static void au_xino_unlock_dir(struct au_xino_lock_dir *ldir)
+{
+	if (ldir->hdir)
+		au_hn_inode_unlock(ldir->hdir);
+	else {
+		inode_unlock(ldir->dir);
+		dput(ldir->parent);
+	}
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * create and set a new xino file
+ */
+struct file *au_xino_create(struct super_block *sb, char *fpath, int silent,
+			    int wbrtop)
+{
+	struct file *file;
+	struct dentry *h_parent, *d;
+	struct inode *h_dir, *inode;
+	int err;
+	static DEFINE_MUTEX(mtx);
+
+	/*
+	 * at mount-time, and the xino file is the default path,
+	 * hnotify is disabled so we have no notify events to ignore.
+	 * when a user specified the xino, we cannot get au_hdir to be ignored.
+	 */
+	if (!wbrtop)
+		mutex_lock(&mtx);
+	file = vfsub_filp_open(fpath, O_RDWR | O_CREAT | O_EXCL | O_LARGEFILE
+			       /* | __FMODE_NONOTIFY */,
+			       0666);
+	if (IS_ERR(file)) {
+		if (!wbrtop)
+			mutex_unlock(&mtx);
+		if (!silent)
+			pr_err("open %s(%ld)\n", fpath, PTR_ERR(file));
+		return file;
+	}
+
+	/* keep file count */
+	err = 0;
+	d = file->f_path.dentry;
+	h_parent = au_dget_parent_lock(d, AuLsc_I_PARENT);
+	if (!wbrtop)
+		mutex_unlock(&mtx);
+	/* mnt_want_write() is unnecessary here */
+	h_dir = d_inode(h_parent);
+	inode = file_inode(file);
+	/* no delegation since it is just created */
+	if (inode->i_nlink)
+		err = vfsub_unlink(h_dir, &file->f_path, /*delegated*/NULL,
+				   /*force*/0);
+	inode_unlock(h_dir);
+	dput(h_parent);
+	if (unlikely(err)) {
+		if (!silent)
+			pr_err("unlink %s(%d)\n", fpath, err);
+		goto out;
+	}
+
+	err = -EINVAL;
+	if (unlikely(sb == d->d_sb)) {
+		if (!silent)
+			pr_err("%s must be outside\n", fpath);
+		goto out;
+	}
+	if (unlikely(au_test_fs_bad_xino(d->d_sb))) {
+		if (!silent)
+			pr_err("xino doesn't support %s(%s)\n",
+			       fpath, au_sbtype(d->d_sb));
+		goto out;
+	}
+	return file; /* success */
+
+out:
+	fput(file);
+	file = ERR_PTR(err);
+	return file;
+}
+
+/*
+ * create a new xinofile at the same place/path as @base.
+ */
+struct file *au_xino_create2(struct super_block *sb, struct path *base,
+			     struct file *copy_src)
+{
+	struct file *file;
+	struct dentry *dentry, *parent;
+	struct inode *dir, *delegated;
+	struct qstr *name;
+	struct path path;
+	int err, do_unlock;
+	struct au_xino_lock_dir ldir;
+
+	do_unlock = 1;
+	au_xino_lock_dir(sb, base, &ldir);
+	dentry = base->dentry;
+	parent = dentry->d_parent; /* dir inode is locked */
+	dir = d_inode(parent);