-SPDX-License-Identifier: GPL-2.0
-aufs6.x-rcN kbuild patch
+From 8dcf5b3ed788c0909dc1248a00a8997cdeefde1e Mon Sep 17 00:00:00 2001
+From: Tom Briden <tom@decompile.me.uk>
+Date: Thu, 11 Jan 2024 11:05:05 +0000
+Subject: [PATCH] Make AUFS friendly (aufs6.x-rcN 20231106)
-diff --git a/fs/Kconfig b/fs/Kconfig
-index aa7e03cc1941..bf780967b6c4 100644
---- a/fs/Kconfig
-+++ b/fs/Kconfig
-@@ -331,6 +331,7 @@ source "fs/sysv/Kconfig"
- source "fs/ufs/Kconfig"
- source "fs/erofs/Kconfig"
- source "fs/vboxsf/Kconfig"
-+source "fs/aufs/Kconfig"
-
- endif # MISC_FILESYSTEMS
-
-diff --git a/fs/Makefile b/fs/Makefile
-index f9541f40be4e..3a0e13ee39e7 100644
---- a/fs/Makefile
-+++ b/fs/Makefile
-@@ -129,3 +129,4 @@ obj-$(CONFIG_EFIVAR_FS) += efivarfs/
- obj-$(CONFIG_EROFS_FS) += erofs/
- obj-$(CONFIG_VBOXSF_FS) += vboxsf/
- obj-$(CONFIG_ZONEFS_FS) += zonefs/
-+obj-$(CONFIG_AUFS_FS) += aufs/
-SPDX-License-Identifier: GPL-2.0
-aufs6.x-rcN base patch
+Patches applied from sfjro/aufs5-standalone
+---
+ Documentation/ABI/testing/debugfs-aufs | 55 +
+ Documentation/ABI/testing/sysfs-aufs | 31 +
+ Documentation/filesystems/aufs/README | 409 ++++
+ .../filesystems/aufs/design/01intro.txt | 171 ++
+ .../filesystems/aufs/design/02struct.txt | 258 +++
+ .../filesystems/aufs/design/03atomic_open.txt | 85 +
+ .../filesystems/aufs/design/03lookup.txt | 113 +
+ .../filesystems/aufs/design/04branch.txt | 74 +
+ .../filesystems/aufs/design/05wbr_policy.txt | 64 +
+ .../filesystems/aufs/design/06dirren.dot | 44 +
+ .../filesystems/aufs/design/06dirren.txt | 102 +
+ .../filesystems/aufs/design/06fhsm.txt | 118 +
+ .../filesystems/aufs/design/06mmap.txt | 72 +
+ .../filesystems/aufs/design/06xattr.txt | 94 +
+ .../filesystems/aufs/design/07export.txt | 58 +
+ .../filesystems/aufs/design/08shwh.txt | 52 +
+ .../filesystems/aufs/design/10dynop.txt | 47 +
+ MAINTAINERS | 13 +
+ drivers/block/loop.c | 18 +
+ fs/Kconfig | 1 +
+ fs/Makefile | 1 +
+ fs/aufs/Kconfig | 199 ++
+ fs/aufs/Makefile | 46 +
+ fs/aufs/aufs.h | 62 +
+ fs/aufs/branch.c | 1427 ++++++++++++
+ fs/aufs/branch.h | 375 ++++
+ fs/aufs/conf.mk | 40 +
+ fs/aufs/cpup.c | 1459 +++++++++++++
+ fs/aufs/cpup.h | 100 +
+ fs/aufs/dbgaufs.c | 526 +++++
+ fs/aufs/dbgaufs.h | 53 +
+ fs/aufs/dcsub.c | 225 ++
+ fs/aufs/dcsub.h | 137 ++
+ fs/aufs/debug.c | 448 ++++
+ fs/aufs/debug.h | 226 ++
+ fs/aufs/dentry.c | 1168 ++++++++++
+ fs/aufs/dentry.h | 270 +++
+ fs/aufs/dinfo.c | 555 +++++
+ fs/aufs/dir.c | 765 +++++++
+ fs/aufs/dir.h | 134 ++
+ fs/aufs/dirren.c | 1315 +++++++++++
+ fs/aufs/dirren.h | 140 ++
+ fs/aufs/dynop.c | 366 ++++
+ fs/aufs/dynop.h | 77 +
+ fs/aufs/export.c | 830 +++++++
+ fs/aufs/f_op.c | 771 +++++++
+ fs/aufs/fhsm.c | 426 ++++
+ fs/aufs/file.c | 865 ++++++++
+ fs/aufs/file.h | 342 +++
+ fs/aufs/finfo.c | 149 ++
+ fs/aufs/fsctx.c | 1242 +++++++++++
+ fs/aufs/fstype.h | 401 ++++
+ fs/aufs/hbl.h | 65 +
+ fs/aufs/hfsnotify.c | 290 +++
+ fs/aufs/hfsplus.c | 60 +
+ fs/aufs/hnotify.c | 715 ++++++
+ fs/aufs/i_op.c | 1516 +++++++++++++
+ fs/aufs/i_op_add.c | 972 +++++++++
+ fs/aufs/i_op_del.c | 523 +++++
+ fs/aufs/i_op_ren.c | 1260 +++++++++++
+ fs/aufs/iinfo.c | 286 +++
+ fs/aufs/inode.c | 531 +++++
+ fs/aufs/inode.h | 707 ++++++
+ fs/aufs/ioctl.c | 220 ++
+ fs/aufs/lcnt.h | 186 ++
+ fs/aufs/loop.c | 148 ++
+ fs/aufs/loop.h | 55 +
+ fs/aufs/magic.mk | 31 +
+ fs/aufs/module.c | 273 +++
+ fs/aufs/module.h | 180 ++
+ fs/aufs/mvdown.c | 706 ++++++
+ fs/aufs/opts.c | 1032 +++++++++
+ fs/aufs/opts.h | 263 +++
+ fs/aufs/plink.c | 516 +++++
+ fs/aufs/poll.c | 51 +
+ fs/aufs/posix_acl.c | 108 +
+ fs/aufs/procfs.c | 170 ++
+ fs/aufs/rdu.c | 384 ++++
+ fs/aufs/rwsem.h | 85 +
+ fs/aufs/sbinfo.c | 316 +++
+ fs/aufs/super.c | 871 ++++++++
+ fs/aufs/super.h | 592 +++++
+ fs/aufs/sysaufs.c | 94 +
+ fs/aufs/sysaufs.h | 102 +
+ fs/aufs/sysfs.c | 374 ++++
+ fs/aufs/sysrq.c | 149 ++
+ fs/aufs/vdir.c | 896 ++++++++
+ fs/aufs/vfsub.c | 918 ++++++++
+ fs/aufs/vfsub.h | 403 ++++
+ fs/aufs/wbr_policy.c | 830 +++++++
+ fs/aufs/whout.c | 1072 +++++++++
+ fs/aufs/whout.h | 87 +
+ fs/aufs/wkq.c | 372 ++++
+ fs/aufs/wkq.h | 89 +
+ fs/aufs/xattr.c | 360 +++
+ fs/aufs/xino.c | 1926 +++++++++++++++++
+ fs/dcache.c | 4 +-
+ fs/exec.c | 1 +
+ fs/fcntl.c | 5 +-
+ fs/file_table.c | 1 +
+ fs/namespace.c | 9 +
+ fs/notify/group.c | 1 +
+ fs/open.c | 1 +
+ fs/proc/nommu.c | 5 +-
+ fs/proc/task_mmu.c | 7 +-
+ fs/proc/task_nommu.c | 5 +-
+ fs/read_write.c | 2 +
+ fs/splice.c | 5 +-
+ fs/xattr.c | 1 +
+ include/linux/fs.h | 2 +
+ include/linux/lockdep.h | 2 +
+ include/linux/mm.h | 37 +
+ include/linux/mm_types.h | 6 +
+ include/linux/mnt_namespace.h | 3 +
+ include/linux/splice.h | 6 +
+ include/uapi/linux/aufs_type.h | 452 ++++
+ kernel/fork.c | 2 +-
+ kernel/locking/lockdep.c | 4 +-
+ kernel/task_work.c | 1 +
+ mm/Makefile | 1 +
+ mm/filemap.c | 2 +-
+ mm/mmap.c | 41 +-
+ mm/nommu.c | 10 +-
+ mm/prfile.c | 86 +
+ security/security.c | 8 +
+ 125 files changed, 38490 insertions(+), 23 deletions(-)
+ create mode 100644 Documentation/ABI/testing/debugfs-aufs
+ create mode 100644 Documentation/ABI/testing/sysfs-aufs
+ create mode 100644 Documentation/filesystems/aufs/README
+ create mode 100644 Documentation/filesystems/aufs/design/01intro.txt
+ create mode 100644 Documentation/filesystems/aufs/design/02struct.txt
+ create mode 100644 Documentation/filesystems/aufs/design/03atomic_open.txt
+ create mode 100644 Documentation/filesystems/aufs/design/03lookup.txt
+ create mode 100644 Documentation/filesystems/aufs/design/04branch.txt
+ create mode 100644 Documentation/filesystems/aufs/design/05wbr_policy.txt
+ create mode 100644 Documentation/filesystems/aufs/design/06dirren.dot
+ create mode 100644 Documentation/filesystems/aufs/design/06dirren.txt
+ create mode 100644 Documentation/filesystems/aufs/design/06fhsm.txt
+ create mode 100644 Documentation/filesystems/aufs/design/06mmap.txt
+ create mode 100644 Documentation/filesystems/aufs/design/06xattr.txt
+ create mode 100644 Documentation/filesystems/aufs/design/07export.txt
+ create mode 100644 Documentation/filesystems/aufs/design/08shwh.txt
+ create mode 100644 Documentation/filesystems/aufs/design/10dynop.txt
+ create mode 100644 fs/aufs/Kconfig
+ create mode 100644 fs/aufs/Makefile
+ create mode 100644 fs/aufs/aufs.h
+ create mode 100644 fs/aufs/branch.c
+ create mode 100644 fs/aufs/branch.h
+ create mode 100644 fs/aufs/conf.mk
+ create mode 100644 fs/aufs/cpup.c
+ create mode 100644 fs/aufs/cpup.h
+ create mode 100644 fs/aufs/dbgaufs.c
+ create mode 100644 fs/aufs/dbgaufs.h
+ create mode 100644 fs/aufs/dcsub.c
+ create mode 100644 fs/aufs/dcsub.h
+ create mode 100644 fs/aufs/debug.c
+ create mode 100644 fs/aufs/debug.h
+ create mode 100644 fs/aufs/dentry.c
+ create mode 100644 fs/aufs/dentry.h
+ create mode 100644 fs/aufs/dinfo.c
+ create mode 100644 fs/aufs/dir.c
+ create mode 100644 fs/aufs/dir.h
+ create mode 100644 fs/aufs/dirren.c
+ create mode 100644 fs/aufs/dirren.h
+ create mode 100644 fs/aufs/dynop.c
+ create mode 100644 fs/aufs/dynop.h
+ create mode 100644 fs/aufs/export.c
+ create mode 100644 fs/aufs/f_op.c
+ create mode 100644 fs/aufs/fhsm.c
+ create mode 100644 fs/aufs/file.c
+ create mode 100644 fs/aufs/file.h
+ create mode 100644 fs/aufs/finfo.c
+ create mode 100644 fs/aufs/fsctx.c
+ create mode 100644 fs/aufs/fstype.h
+ create mode 100644 fs/aufs/hbl.h
+ create mode 100644 fs/aufs/hfsnotify.c
+ create mode 100644 fs/aufs/hfsplus.c
+ create mode 100644 fs/aufs/hnotify.c
+ create mode 100644 fs/aufs/i_op.c
+ create mode 100644 fs/aufs/i_op_add.c
+ create mode 100644 fs/aufs/i_op_del.c
+ create mode 100644 fs/aufs/i_op_ren.c
+ create mode 100644 fs/aufs/iinfo.c
+ create mode 100644 fs/aufs/inode.c
+ create mode 100644 fs/aufs/inode.h
+ create mode 100644 fs/aufs/ioctl.c
+ create mode 100644 fs/aufs/lcnt.h
+ create mode 100644 fs/aufs/loop.c
+ create mode 100644 fs/aufs/loop.h
+ create mode 100644 fs/aufs/magic.mk
+ create mode 100644 fs/aufs/module.c
+ create mode 100644 fs/aufs/module.h
+ create mode 100644 fs/aufs/mvdown.c
+ create mode 100644 fs/aufs/opts.c
+ create mode 100644 fs/aufs/opts.h
+ create mode 100644 fs/aufs/plink.c
+ create mode 100644 fs/aufs/poll.c
+ create mode 100644 fs/aufs/posix_acl.c
+ create mode 100644 fs/aufs/procfs.c
+ create mode 100644 fs/aufs/rdu.c
+ create mode 100644 fs/aufs/rwsem.h
+ create mode 100644 fs/aufs/sbinfo.c
+ create mode 100644 fs/aufs/super.c
+ create mode 100644 fs/aufs/super.h
+ create mode 100644 fs/aufs/sysaufs.c
+ create mode 100644 fs/aufs/sysaufs.h
+ create mode 100644 fs/aufs/sysfs.c
+ create mode 100644 fs/aufs/sysrq.c
+ create mode 100644 fs/aufs/vdir.c
+ create mode 100644 fs/aufs/vfsub.c
+ create mode 100644 fs/aufs/vfsub.h
+ create mode 100644 fs/aufs/wbr_policy.c
+ create mode 100644 fs/aufs/whout.c
+ create mode 100644 fs/aufs/whout.h
+ create mode 100644 fs/aufs/wkq.c
+ create mode 100644 fs/aufs/wkq.h
+ create mode 100644 fs/aufs/xattr.c
+ create mode 100644 fs/aufs/xino.c
+ create mode 100644 include/uapi/linux/aufs_type.h
+ create mode 100644 mm/prfile.c
-diff --git a/MAINTAINERS b/MAINTAINERS
-index bf0f54c24f81..39b1844bce57 100644
---- a/MAINTAINERS
-+++ b/MAINTAINERS
-@@ -3316,6 +3316,19 @@ F: include/uapi/linux/audit.h
- F: kernel/audit*
- F: lib/*audit.c
-
-+AUFS (advanced multi layered unification filesystem) FILESYSTEM
-+M: "J. R. Okajima" <hooanon05g@gmail.com>
-+L: aufs-users@lists.sourceforge.net (members only)
-+L: linux-unionfs@vger.kernel.org
-+S: Supported
-+W: http://aufs.sourceforge.net
-+T: git://github.com/sfjro/aufs4-linux.git
-+F: Documentation/ABI/testing/debugfs-aufs
-+F: Documentation/ABI/testing/sysfs-aufs
-+F: Documentation/filesystems/aufs/
-+F: fs/aufs/
-+F: include/uapi/linux/aufs_type.h
+diff --git a/Documentation/ABI/testing/debugfs-aufs b/Documentation/ABI/testing/debugfs-aufs
+new file mode 100644
+index 00000000000000..45b739879d7696
+--- /dev/null
++++ b/Documentation/ABI/testing/debugfs-aufs
+@@ -0,0 +1,55 @@
++What: /debug/aufs/si_<id>/
++Date: March 2009
++Contact: J. R. Okajima <hooanon05g@gmail.com>
++Description:
++ Under /debug/aufs, a directory named si_<id> is created
++ per aufs mount, where <id> is a unique id generated
++ internally.
+
- AUXILIARY BUS DRIVER
- M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
- R: Dave Ertman <david.m.ertman@intel.com>
-diff --git a/drivers/block/loop.c b/drivers/block/loop.c
-index 9f2d412fc560..1fefc6a8d049 100644
---- a/drivers/block/loop.c
-+++ b/drivers/block/loop.c
-@@ -645,6 +645,24 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
- goto done;
- }
-
-+/*
-+ * for AUFS
-+ * no get/put for file.
-+ */
-+struct file *loop_backing_file(struct super_block *sb)
-+{
-+ struct file *ret;
-+ struct loop_device *l;
++What: /debug/aufs/si_<id>/plink
++Date: Apr 2013
++Contact: J. R. Okajima <hooanon05g@gmail.com>
++Description:
++ It has three lines and shows the information about the
++ pseudo-link. The first line is a single number
++ representing a number of buckets. The second line is a
++ number of pseudo-links per buckets (separated by a
++ blank). The last line is a single number representing a
++ total number of psedo-links.
++ When the aufs mount option 'noplink' is specified, it
++ will show "1\n0\n0\n".
+
-+ ret = NULL;
-+ if (MAJOR(sb->s_dev) == LOOP_MAJOR) {
-+ l = sb->s_bdev->bd_disk->private_data;
-+ ret = l->lo_backing_file;
-+ }
-+ return ret;
-+}
-+EXPORT_SYMBOL_GPL(loop_backing_file);
++What: /debug/aufs/si_<id>/xib
++Date: March 2009
++Contact: J. R. Okajima <hooanon05g@gmail.com>
++Description:
++ It shows the consumed blocks by xib (External Inode Number
++ Bitmap), its block size and file size.
++ When the aufs mount option 'noxino' is specified, it
++ will be empty. About XINO files, see the aufs manual.
+
- /* loop sysfs attributes */
-
- static ssize_t loop_attr_show(struct device *dev, char *page,
-diff --git a/fs/dcache.c b/fs/dcache.c
-index 25ac74d30bff..6c930ceed526 100644
---- a/fs/dcache.c
-+++ b/fs/dcache.c
-@@ -1345,7 +1345,7 @@ enum d_walk_ret {
- *
- * The @enter() callbacks are called with d_lock held.
- */
--static void d_walk(struct dentry *parent, void *data,
-+void d_walk(struct dentry *parent, void *data,
- enum d_walk_ret (*enter)(void *, struct dentry *))
- {
- struct dentry *this_parent;
-diff --git a/fs/fcntl.c b/fs/fcntl.c
-index e871009f6c88..d62e114c1b1a 100644
---- a/fs/fcntl.c
-+++ b/fs/fcntl.c
-@@ -34,7 +34,7 @@
-
- #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME)
-
--static int setfl(int fd, struct file * filp, unsigned int arg)
-+int setfl(int fd, struct file * filp, unsigned int arg)
- {
- struct inode * inode = file_inode(filp);
- int error = 0;
-@@ -64,6 +64,8 @@ static int setfl(int fd, struct file * filp, unsigned int arg)
-
- if (filp->f_op->check_flags)
- error = filp->f_op->check_flags(arg);
-+ if (!error && filp->f_op->setfl)
-+ error = filp->f_op->setfl(filp, arg);
- if (error)
- return error;
-
-diff --git a/fs/namespace.c b/fs/namespace.c
-index e157efc54023..6c57487f126b 100644
---- a/fs/namespace.c
-+++ b/fs/namespace.c
-@@ -872,6 +872,12 @@ static inline int check_mnt(struct mount *mnt)
- return mnt->mnt_ns == current->nsproxy->mnt_ns;
- }
-
-+/* for aufs, CONFIG_AUFS_BR_FUSE */
-+int is_current_mnt_ns(struct vfsmount *mnt)
-+{
-+ return check_mnt(real_mount(mnt));
-+}
++What: /debug/aufs/si_<id>/xi<branch-index>
++Date: March 2009
++Contact: J. R. Okajima <hooanon05g@gmail.com>
++Description:
++ It shows the consumed blocks by xino (External Inode Number
++ Translation Table), its link count, block size and file
++ size.
++ Due to the file size limit, there may exist multiple
++ xino files per branch. In this case, "-N" is added to
++ the filename and it corresponds to the index of the
++ internal xino array. "-0" is omitted.
++ When the aufs mount option 'noxino' is specified, Those
++ entries won't exist. About XINO files, see the aufs
++ manual.
+
- /*
- * vfsmount lock must be held for write
- */
-diff --git a/fs/splice.c b/fs/splice.c
-index d983d375ff11..7216ef993b5f 100644
---- a/fs/splice.c
-+++ b/fs/splice.c
-@@ -925,8 +925,8 @@ static int warn_unsupported(struct file *file, const char *op)
- /*
- * Attempt to initiate a splice from pipe to file.
- */
--static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
-- loff_t *ppos, size_t len, unsigned int flags)
-+long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
-+ loff_t *ppos, size_t len, unsigned int flags)
- {
- if (unlikely(!out->f_op->splice_write))
- return warn_unsupported(out, "write");
-diff --git a/include/linux/fs.h b/include/linux/fs.h
-index 4aeb3fa11927..dd5871d0c429 100644
---- a/include/linux/fs.h
-+++ b/include/linux/fs.h
-@@ -1099,6 +1099,7 @@ extern void fasync_free(struct fasync_struct *);
- /* can be called from interrupts */
- extern void kill_fasync(struct fasync_struct **, int, int);
-
-+extern int setfl(int fd, struct file *filp, unsigned int arg);
- extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
- extern int f_setown(struct file *filp, int who, int force);
- extern void f_delown(struct file *filp);
-@@ -1901,6 +1902,7 @@ struct file_operations {
- int (*lock) (struct file *, int, struct file_lock *);
- unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
- int (*check_flags)(int);
-+ int (*setfl)(struct file *, unsigned long);
- int (*flock) (struct file *, int, struct file_lock *);
- ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
- ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
-diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
-index dc2844b071c2..069ffb776c2c 100644
---- a/include/linux/lockdep.h
-+++ b/include/linux/lockdep.h
-@@ -249,6 +249,8 @@ static inline int lockdep_match_key(struct lockdep_map *lock,
- return lock->key == key;
- }
-
-+struct lock_class *lockdep_hlock_class(struct held_lock *hlock);
++What: /debug/aufs/si_<id>/xigen
++Date: March 2009
++Contact: J. R. Okajima <hooanon05g@gmail.com>
++Description:
++ It shows the consumed blocks by xigen (External Inode
++ Generation Table), its block size and file size.
++ If CONFIG_AUFS_EXPORT is disabled, this entry will not
++ be created.
++ When the aufs mount option 'noxino' is specified, it
++ will be empty. About XINO files, see the aufs manual.
+diff --git a/Documentation/ABI/testing/sysfs-aufs b/Documentation/ABI/testing/sysfs-aufs
+new file mode 100644
+index 00000000000000..48500c0569e658
+--- /dev/null
++++ b/Documentation/ABI/testing/sysfs-aufs
+@@ -0,0 +1,31 @@
++What: /sys/fs/aufs/si_<id>/
++Date: March 2009
++Contact: J. R. Okajima <hooanon05g@gmail.com>
++Description:
++ Under /sys/fs/aufs, a directory named si_<id> is created
++ per aufs mount, where <id> is a unique id generated
++ internally.
+
- /*
- * Acquire a lock.
- *
-diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h
-index 8f882f5881e8..6b9808f09843 100644
---- a/include/linux/mnt_namespace.h
-+++ b/include/linux/mnt_namespace.h
-@@ -7,12 +7,15 @@ struct mnt_namespace;
- struct fs_struct;
- struct user_namespace;
- struct ns_common;
-+struct vfsmount;
-
- extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *,
- struct user_namespace *, struct fs_struct *);
- extern void put_mnt_ns(struct mnt_namespace *ns);
- extern struct ns_common *from_mnt_ns(struct mnt_namespace *);
-
-+extern int is_current_mnt_ns(struct vfsmount *mnt);
++What: /sys/fs/aufs/si_<id>/br<idx>
++Date: March 2009
++Contact: J. R. Okajima <hooanon05g@gmail.com>
++Description:
++ It shows the abolute path of a member directory (which
++ is called branch) in aufs, and its permission.
+
- extern const struct file_operations proc_mounts_operations;
- extern const struct file_operations proc_mountinfo_operations;
- extern const struct file_operations proc_mountstats_operations;
-diff --git a/include/linux/splice.h b/include/linux/splice.h
-index 6c461573434d..7416cf375ad1 100644
---- a/include/linux/splice.h
-+++ b/include/linux/splice.h
-@@ -99,4 +99,10 @@ extern void splice_shrink_spd(struct splice_pipe_desc *);
-
- extern const struct pipe_buf_operations page_cache_pipe_buf_ops;
- extern const struct pipe_buf_operations default_pipe_buf_ops;
++What: /sys/fs/aufs/si_<id>/brid<idx>
++Date: July 2013
++Contact: J. R. Okajima <hooanon05g@gmail.com>
++Description:
++ It shows the id of a member directory (which is called
++ branch) in aufs.
+
-+extern long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
-+ loff_t *ppos, size_t len, unsigned int flags);
-+extern long do_splice_to(struct file *in, loff_t *ppos,
-+ struct pipe_inode_info *pipe, size_t len,
-+ unsigned int flags);
- #endif
-diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
-index e85b5ad3e206..db4297f60bd3 100644
---- a/kernel/locking/lockdep.c
-+++ b/kernel/locking/lockdep.c
-@@ -218,7 +218,7 @@ unsigned long max_lock_class_idx;
- struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
- DECLARE_BITMAP(lock_classes_in_use, MAX_LOCKDEP_KEYS);
-
--static inline struct lock_class *hlock_class(struct held_lock *hlock)
-+inline struct lock_class *lockdep_hlock_class(struct held_lock *hlock)
- {
- unsigned int class_idx = hlock->class_idx;
-
-@@ -239,6 +239,7 @@ static inline struct lock_class *hlock_class(struct held_lock *hlock)
- */
- return lock_classes + class_idx;
- }
-+#define hlock_class(hlock) lockdep_hlock_class(hlock)
-
- #ifdef CONFIG_LOCK_STAT
- static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], cpu_lock_stats);
-SPDX-License-Identifier: GPL-2.0
-aufs6.x-rcN mmap patch
-
-diff --git a/fs/proc/base.c b/fs/proc/base.c
-index ffd54617c354..29ec720c8038 100644
---- a/fs/proc/base.c
-+++ b/fs/proc/base.c
-@@ -2218,7 +2218,7 @@ static int map_files_get_link(struct dentry *dentry, struct path *path)
- rc = -ENOENT;
- vma = find_exact_vma(mm, vm_start, vm_end);
- if (vma && vma->vm_file) {
-- *path = vma->vm_file->f_path;
-+ *path = vma_pr_or_file(vma)->f_path;
- path_get(path);
- rc = 0;
- }
-diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c
-index 4d3493579458..42edd9a42c78 100644
---- a/fs/proc/nommu.c
-+++ b/fs/proc/nommu.c
-@@ -39,7 +39,10 @@ static int nommu_region_show(struct seq_file *m, struct vm_region *region)
- file = region->vm_file;
-
- if (file) {
-- struct inode *inode = file_inode(region->vm_file);
-+ struct inode *inode;
++What: /sys/fs/aufs/si_<id>/xi_path
++Date: March 2009
++Contact: J. R. Okajima <hooanon05g@gmail.com>
++Description:
++ It shows the abolute path of XINO (External Inode Number
++ Bitmap, Translation Table and Generation Table) file
++ even if it is the default path.
++ When the aufs mount option 'noxino' is specified, it
++ will be empty. About XINO files, see the aufs manual.
+diff --git a/Documentation/filesystems/aufs/README b/Documentation/filesystems/aufs/README
+new file mode 100644
+index 00000000000000..04a4d069bb52a0
+--- /dev/null
++++ b/Documentation/filesystems/aufs/README
+@@ -0,0 +1,409 @@
+
-+ file = vmr_pr_or_file(region);
-+ inode = file_inode(file);
- dev = inode->i_sb->s_dev;
- ino = inode->i_ino;
- }
-diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
-index 3dd5be96691b..40d9d970b308 100644
---- a/fs/proc/task_mmu.c
-+++ b/fs/proc/task_mmu.c
-@@ -271,7 +271,10 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
- const char *name = NULL;
-
- if (file) {
-- struct inode *inode = file_inode(vma->vm_file);
-+ struct inode *inode;
++Aufs6 -- advanced multi layered unification filesystem version 6.x
++http://aufs.sf.net
++Junjiro R. Okajima
+
-+ file = vma_pr_or_file(vma);
-+ inode = file_inode(file);
- dev = inode->i_sb->s_dev;
- ino = inode->i_ino;
- pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT;
-@@ -1943,7 +1946,7 @@ static int show_numa_map(struct seq_file *m, void *v)
- struct proc_maps_private *proc_priv = &numa_priv->proc_maps;
- struct vm_area_struct *vma = v;
- struct numa_maps *md = &numa_priv->md;
-- struct file *file = vma->vm_file;
-+ struct file *file = vma_pr_or_file(vma);
- struct mm_struct *mm = vma->vm_mm;
- struct mempolicy *pol;
- char buffer[64];
-diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
-index a8ac0dd8041e..9fca456e2259 100644
---- a/fs/proc/task_nommu.c
-+++ b/fs/proc/task_nommu.c
-@@ -137,7 +137,10 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
- file = vma->vm_file;
-
- if (file) {
-- struct inode *inode = file_inode(vma->vm_file);
-+ struct inode *inode;
+
-+ file = vma_pr_or_file(vma);
-+ inode = file_inode(file);
- dev = inode->i_sb->s_dev;
- ino = inode->i_ino;
- pgoff = (loff_t)vma->vm_pgoff << PAGE_SHIFT;
-diff --git a/include/linux/mm.h b/include/linux/mm.h
-index bf5d0b1b16f4..94b956eff452 100644
---- a/include/linux/mm.h
-+++ b/include/linux/mm.h
-@@ -2409,6 +2409,43 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping,
- static inline struct vm_area_struct *vma_lookup(struct mm_struct *mm,
- unsigned long addr);
-
-+#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
-+extern void vma_do_file_update_time(struct vm_area_struct *, const char[], int);
-+extern struct file *vma_do_pr_or_file(struct vm_area_struct *, const char[],
-+ int);
-+extern void vma_do_get_file(struct vm_area_struct *, const char[], int);
-+extern void vma_do_fput(struct vm_area_struct *, const char[], int);
++0. Introduction
++----------------------------------------
++In the early days, aufs was entirely re-designed and re-implemented
++Unionfs Version 1.x series. Adding many original ideas, approaches,
++improvements and implementations, it became totally different from
++Unionfs while keeping the basic features.
++Later, Unionfs Version 2.x series began taking some of the same
++approaches to aufs1's.
++Unionfs was being developed by Professor Erez Zadok at Stony Brook
++University and his team.
+
-+#define vma_file_update_time(vma) vma_do_file_update_time(vma, __func__, \
-+ __LINE__)
-+#define vma_pr_or_file(vma) vma_do_pr_or_file(vma, __func__, \
-+ __LINE__)
-+#define vma_get_file(vma) vma_do_get_file(vma, __func__, __LINE__)
-+#define vma_fput(vma) vma_do_fput(vma, __func__, __LINE__)
++Aufs6 supports linux-v6.0 and later, try aufs6.0 branch in
++aufs-linux.git or aufs-standalone.git.
++If you want older kernel version support,
++- for linux-v5.x series, try aufs-linux.git or aufs-standalone.git
++- for linux-v4.x series, try aufs4-linux.git or aufs4-standalone.git
++- for linux-v3.x series, try aufs3-linux.git or aufs3-standalone.git
++- for linux-v2.6.16 and later, try aufs2-2.6.git, aufs2-standalone.git
++ or aufs1 from CVS on SourceForge.
+
-+#ifndef CONFIG_MMU
-+extern struct file *vmr_do_pr_or_file(struct vm_region *, const char[], int);
-+extern void vmr_do_fput(struct vm_region *, const char[], int);
++Note: the name of aufs5-linux.git and aufs5-standalone.git on github
++ were changed. Now they are aufs-linux.git and
++ aufs-standalone.git and they contain aufs5 and later branches.
+
-+#define vmr_pr_or_file(region) vmr_do_pr_or_file(region, __func__, \
-+ __LINE__)
-+#define vmr_fput(region) vmr_do_fput(region, __func__, __LINE__)
-+#endif /* !CONFIG_MMU */
++Note: it becomes clear that "Aufs was rejected. Let's give it up."
++ According to Christoph Hellwig, linux rejects all union-type
++ filesystems but UnionMount.
++<http://marc.info/?l=linux-kernel&m=123938533724484&w=2>
+
-+#else
++PS. Al Viro seems have a plan to merge aufs as well as overlayfs and
++ UnionMount, and he pointed out an issue around a directory mutex
++ lock and aufs addressed it. But it is still unsure whether aufs will
++ be merged (or any other union solution).
++<http://marc.info/?l=linux-kernel&m=136312705029295&w=1>
+
-+#define vma_file_update_time(vma) file_update_time((vma)->vm_file)
-+#define vma_pr_or_file(vma) (vma)->vm_file
-+#define vma_get_file(vma) get_file((vma)->vm_file)
-+#define vma_fput(vma) fput((vma)->vm_file)
+
-+#ifndef CONFIG_MMU
-+#define vmr_pr_or_file(region) (region)->vm_file
-+#define vmr_fput(region) fput((region)->vm_file)
-+#endif /* !CONFIG_MMU */
++1. Features
++----------------------------------------
++- unite several directories into a single virtual filesystem. The member
++ directory is called as a branch.
++- you can specify the permission flags to the branch, which are 'readonly',
++ 'readwrite' and 'whiteout-able.'
++- by upper writable branch, internal copyup and whiteout, files/dirs on
++ readonly branch are modifiable logically.
++- dynamic branch manipulation, add, del.
++- etc...
+
-+#endif /* CONFIG_AUFS_FS */
++Also there are many enhancements in aufs, such as:
++- test only the highest one for the directory permission (dirperm1)
++- copyup on open (coo=)
++- 'move' policy for copy-up between two writable branches, after
++ checking free space.
++- xattr, acl
++- readdir(3) in userspace.
++- keep inode number by external inode number table
++- keep the timestamps of file/dir in internal copyup operation
++- seekable directory, supporting NFS readdir.
++- whiteout is hardlinked in order to reduce the consumption of inodes
++ on branch
++- do not copyup, nor create a whiteout when it is unnecessary
++- revert a single systemcall when an error occurs in aufs
++- remount interface instead of ioctl
++- maintain /etc/mtab by an external command, /sbin/mount.aufs.
++- loopback mounted filesystem as a branch
++- kernel thread for removing the dir who has a plenty of whiteouts
++- support copyup sparse file (a file which has a 'hole' in it)
++- default permission flags for branches
++- selectable permission flags for ro branch, whether whiteout can
++ exist or not
++- export via NFS.
++- support <sysfs>/fs/aufs and <debugfs>/aufs.
++- support multiple writable branches, some policies to select one
++ among multiple writable branches.
++- a new semantics for link(2) and rename(2) to support multiple
++ writable branches.
++- no glibc changes are required.
++- pseudo hardlink (hardlink over branches)
++- allow a direct access manually to a file on branch, e.g. bypassing aufs.
++ including NFS or remote filesystem branch.
++- userspace wrapper for pathconf(3)/fpathconf(3) with _PC_LINK_MAX.
++- and more...
+
- extern int access_process_vm(struct task_struct *tsk, unsigned long addr,
- void *buf, int len, unsigned int gup_flags);
- extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
-diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
-index 36c5b43999e6..ce93e97f76a6 100644
---- a/include/linux/mm_types.h
-+++ b/include/linux/mm_types.h
-@@ -524,6 +524,9 @@ struct vm_region {
- unsigned long vm_top; /* region allocated to here */
- unsigned long vm_pgoff; /* the offset in vm_file corresponding to vm_start */
- struct file *vm_file; /* the backing file or NULL */
-+#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
-+ struct file *vm_prfile; /* the virtual backing file or NULL */
-+#endif
-
- int vm_usage; /* region usage count (access under nommu_region_sem) */
- bool vm_icache_flushed : 1; /* true if the icache has been flushed for
-@@ -637,6 +640,9 @@ struct vm_area_struct {
- unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE
- units */
- struct file * vm_file; /* File we map to (can be NULL). */
-+#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
-+ struct file *vm_prfile; /* shadow of vm_file */
-+#endif
- void * vm_private_data; /* was vm_pte (shared mem) */
-
- #ifdef CONFIG_ANON_VMA_NAME
-diff --git a/kernel/fork.c b/kernel/fork.c
-index 3b6d20dfb9a8..ccad0325cfa9 100644
---- a/kernel/fork.c
-+++ b/kernel/fork.c
-@@ -731,7 +731,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
- if (file) {
- struct address_space *mapping = file->f_mapping;
-
-- get_file(file);
-+ vma_get_file(tmp);
- i_mmap_lock_write(mapping);
- if (tmp->vm_flags & VM_SHARED)
- mapping_allow_writable(mapping);
-diff --git a/mm/Makefile b/mm/Makefile
-index ec65984e2ade..d59461647ccd 100644
---- a/mm/Makefile
-+++ b/mm/Makefile
-@@ -138,3 +138,4 @@ obj-$(CONFIG_IO_MAPPING) += io-mapping.o
- obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o
- obj-$(CONFIG_GENERIC_IOREMAP) += ioremap.o
- obj-$(CONFIG_SHRINKER_DEBUG) += shrinker_debug.o
-+obj-y += prfile.o
-diff --git a/mm/filemap.c b/mm/filemap.c
-index 582f5317ff71..c024ebb30073 100644
---- a/mm/filemap.c
-+++ b/mm/filemap.c
-@@ -3599,7 +3599,7 @@ vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf)
- vm_fault_t ret = VM_FAULT_LOCKED;
-
- sb_start_pagefault(mapping->host->i_sb);
-- file_update_time(vmf->vma->vm_file);
-+ vma_file_update_time(vmf->vma);
- folio_lock(folio);
- if (folio->mapping != mapping) {
- folio_unlock(folio);
-diff --git a/mm/mmap.c b/mm/mmap.c
-index b56a7f0c9f85..5eb114409e07 100644
---- a/mm/mmap.c
-+++ b/mm/mmap.c
-@@ -140,7 +140,7 @@ static void remove_vma(struct vm_area_struct *vma, bool unreachable)
- if (vma->vm_ops && vma->vm_ops->close)
- vma->vm_ops->close(vma);
- if (vma->vm_file)
-- fput(vma->vm_file);
-+ vma_fput(vma);
- mpol_put(vma_policy(vma));
- if (unreachable)
- __vm_area_free(vma);
-@@ -554,7 +554,7 @@ static inline void vma_complete(struct vma_prepare *vp,
- if (vp->file) {
- uprobe_munmap(vp->remove, vp->remove->vm_start,
- vp->remove->vm_end);
-- fput(vp->file);
-+ vma_fput(vp->vma);
- }
- if (vp->remove->anon_vma)
- anon_vma_merge(vp->vma, vp->remove);
-@@ -2364,7 +2364,7 @@ int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
- goto out_free_mpol;
-
- if (new->vm_file)
-- get_file(new->vm_file);
-+ vma_get_file(new);
-
- if (new->vm_ops && new->vm_ops->open)
- new->vm_ops->open(new);
-@@ -2781,7 +2781,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
- * and cause general protection fault
- * ultimately.
- */
-- fput(vma->vm_file);
-+ vma_fput(vma);
- vm_area_free(vma);
- vma = merge;
- /* Update vm_flags to pick up the change. */
-@@ -2876,7 +2876,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
-
- if (file || vma->vm_file) {
- unmap_and_free_vma:
-- fput(vma->vm_file);
-+ vma_fput(vma);
- vma->vm_file = NULL;
-
- vma_iter_set(&vmi, vma->vm_end);
-@@ -2938,6 +2938,9 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
- unsigned long populate = 0;
- unsigned long ret = -EINVAL;
- struct file *file;
-+#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
-+ struct file *prfile;
-+#endif
-
- pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/mm/remap_file_pages.rst.\n",
- current->comm, current->pid);
-@@ -2996,10 +2999,34 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
- if (vma->vm_flags & VM_LOCKED)
- flags |= MAP_LOCKED;
-
-+#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
-+ vma_get_file(vma);
-+ file = vma->vm_file;
-+ prfile = vma->vm_prfile;
-+ ret = do_mmap(vma->vm_file, start, size,
-+ prot, flags, /*vm_flags*/0, pgoff, &populate, NULL);
-+ if (!IS_ERR_VALUE(ret) && file && prfile) {
-+ struct vm_area_struct *new_vma;
++Currently these features are dropped temporary from aufs6.
++See design/08plan.txt in detail.
++- nested mount, i.e. aufs as readonly no-whiteout branch of another aufs
++ (robr)
++- statistics of aufs thread (/sys/fs/aufs/stat)
+
-+ new_vma = find_vma(mm, ret);
-+ if (!new_vma->vm_prfile)
-+ new_vma->vm_prfile = prfile;
-+ if (prfile)
-+ get_file(prfile);
-+ }
-+ /*
-+ * two fput()s instead of vma_fput(vma),
-+ * coz vma may not be available anymore.
-+ */
-+ fput(file);
-+ if (prfile)
-+ fput(prfile);
-+#else
- file = get_file(vma->vm_file);
- ret = do_mmap(vma->vm_file, start, size,
- prot, flags, 0, pgoff, &populate, NULL);
- fput(file);
-+#endif /* CONFIG_AUFS_FS */
- out:
- mmap_write_unlock(mm);
- if (populate)
-@@ -3350,7 +3377,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
- if (anon_vma_clone(new_vma, vma))
- goto out_free_mempol;
- if (new_vma->vm_file)
-- get_file(new_vma->vm_file);
-+ vma_get_file(new_vma);
- if (new_vma->vm_ops && new_vma->vm_ops->open)
- new_vma->vm_ops->open(new_vma);
- if (vma_link(mm, new_vma))
-@@ -3364,7 +3391,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
- new_vma->vm_ops->close(new_vma);
-
- if (new_vma->vm_file)
-- fput(new_vma->vm_file);
-+ vma_fput(new_vma);
-
- unlink_anon_vmas(new_vma);
- out_free_mempol:
-diff --git a/mm/nommu.c b/mm/nommu.c
-index 7f9e9e5a0e12..69663f2bd4c4 100644
---- a/mm/nommu.c
-+++ b/mm/nommu.c
-@@ -523,7 +523,7 @@ static void __put_nommu_region(struct vm_region *region)
- up_write(&nommu_region_sem);
-
- if (region->vm_file)
-- fput(region->vm_file);
-+ vmr_fput(region);
-
- /* IO memory and memory shared directly out of the pagecache
- * from ramfs/tmpfs mustn't be released here */
-@@ -603,7 +603,7 @@ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma)
- if (vma->vm_ops && vma->vm_ops->close)
- vma->vm_ops->close(vma);
- if (vma->vm_file)
-- fput(vma->vm_file);
-+ vma_fput(vma);
- put_nommu_region(vma->vm_region);
- vm_area_free(vma);
- }
-@@ -1135,7 +1135,7 @@ unsigned long do_mmap(struct file *file,
- goto error_just_free;
- }
- }
-- fput(region->vm_file);
-+ vmr_fput(region);
- kmem_cache_free(vm_region_jar, region);
- region = pregion;
- result = start;
-@@ -1221,10 +1221,10 @@ unsigned long do_mmap(struct file *file,
- error:
- vma_iter_free(&vmi);
- if (region->vm_file)
-- fput(region->vm_file);
-+ vmr_fput(region);
- kmem_cache_free(vm_region_jar, region);
- if (vma->vm_file)
-- fput(vma->vm_file);
-+ vma_fput(vma);
- vm_area_free(vma);
- return ret;
-
-diff --git a/mm/prfile.c b/mm/prfile.c
-new file mode 100644
-index 000000000000..8f820a235364
---- /dev/null
-+++ b/mm/prfile.c
-@@ -0,0 +1,86 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Mainly for aufs which mmap(2) different file and wants to print different
-+ * path in /proc/PID/maps.
-+ * Call these functions via macros defined in linux/mm.h.
-+ *
-+ * See Documentation/filesystems/aufs/design/06mmap.txt
-+ *
-+ * Copyright (c) 2014-2022 Junjro R. Okajima
-+ * Copyright (c) 2014 Ian Campbell
-+ */
++Features or just an idea in the future (see also design/*.txt),
++- reorder the branch index without del/re-add.
++- permanent xino files for NFSD
++- an option for refreshing the opened files after add/del branches
++- light version, without branch manipulation. (unnecessary?)
++- copyup in userspace
++- inotify in userspace
++- readv/writev
+
-+#include <linux/mm.h>
-+#include <linux/file.h>
-+#include <linux/fs.h>
+
-+/* #define PRFILE_TRACE */
-+static inline void prfile_trace(struct file *f, struct file *pr,
-+ const char func[], int line, const char func2[])
-+{
-+#ifdef PRFILE_TRACE
-+ if (pr)
-+ pr_info("%s:%d: %s, %pD2\n", func, line, func2, f);
-+#endif
-+}
++2. Download
++----------------------------------------
++There are three GIT trees for aufs6, aufs-linux.git,
++aufs-standalone.git, and aufs-util.git.
++While the aufs-util is always necessary, you need either of aufs-linux
++or aufs-standalone.
+
-+void vma_do_file_update_time(struct vm_area_struct *vma, const char func[],
-+ int line)
-+{
-+ struct file *f = vma->vm_file, *pr = vma->vm_prfile;
++The aufs-linux tree includes the whole linux mainline GIT tree,
++git://git.kernel.org/.../torvalds/linux.git.
++And you cannot select CONFIG_AUFS_FS=m for this version, eg. you cannot
++build aufs6 as an external kernel module.
++Several extra patches are not included in this tree. Only
++aufs-standalone tree contains them. They are described in the later
++section "Configuration and Compilation."
+
-+ prfile_trace(f, pr, func, line, __func__);
-+ file_update_time(f);
-+ if (f && pr)
-+ file_update_time(pr);
-+}
++On the other hand, the aufs-standalone tree has only aufs source files
++and necessary patches, and you can select CONFIG_AUFS_FS=m.
++But you need to apply all aufs patches manually.
+
-+struct file *vma_do_pr_or_file(struct vm_area_struct *vma, const char func[],
-+ int line)
-+{
-+ struct file *f = vma->vm_file, *pr = vma->vm_prfile;
++You will find GIT branches whose name is in form of "aufs6.x" where "x"
++represents the linux kernel version, "linux-6.x". For instance,
++"aufs6.0" is for linux-6.0. For latest "linux-6.x-rcN", use
++"aufs6.x-rcN" branch.
+
-+ prfile_trace(f, pr, func, line, __func__);
-+ return (f && pr) ? pr : f;
-+}
++o aufs-linux tree
++$ git clone --reference /your/linux/git/tree \
++ git://github.com/sfjro/aufs-linux.git aufs-linux.git
++- if you don't have linux GIT tree, then remove "--reference ..."
++$ cd aufs-linux.git
++$ git checkout origin/aufs6.0
+
-+void vma_do_get_file(struct vm_area_struct *vma, const char func[], int line)
-+{
-+ struct file *f = vma->vm_file, *pr = vma->vm_prfile;
++Or You may want to directly git-pull aufs into your linux GIT tree, and
++leave the patch-work to GIT.
++$ cd /your/linux/git/tree
++$ git remote add aufs git://github.com/sfjro/aufs-linux.git
++$ git fetch aufs
++$ git checkout -b my6.0 v6.0
++$ (add your local change...)
++$ git pull aufs aufs6.0
++- now you have v6.0 + your_changes + aufs6.0 in you my6.0 branch.
++- you may need to solve some conflicts between your_changes and
++ aufs6.0. in this case, git-rerere is recommended so that you can
++ solve the similar conflicts automatically when you upgrade to 6.1 or
++ later in the future.
+
-+ prfile_trace(f, pr, func, line, __func__);
-+ get_file(f);
-+ if (f && pr)
-+ get_file(pr);
-+}
++o aufs-standalone tree
++$ git clone git://github.com/sfjro/aufs-standalone.git aufs-standalone.git
++$ cd aufs-standalone.git
++$ git checkout origin/aufs6.0
+
-+void vma_do_fput(struct vm_area_struct *vma, const char func[], int line)
-+{
-+ struct file *f = vma->vm_file, *pr = vma->vm_prfile;
++o aufs-util tree
++$ git clone git://git.code.sf.net/p/aufs/aufs-util aufs-util.git
++- note that the public aufs-util.git is on SourceForge instead of
++ GitHUB.
++$ cd aufs-util.git
++$ git checkout origin/aufs6.0
+
-+ prfile_trace(f, pr, func, line, __func__);
-+ fput(f);
-+ if (f && pr)
-+ fput(pr);
-+}
++Note: The 6.x-rcN branch is to be used with `rc' kernel versions ONLY.
++The minor version number, 'x' in '6.x', of aufs may not always
++follow the minor version number of the kernel.
++Because changes in the kernel that cause the use of a new
++minor version number do not always require changes to aufs-util.
+
-+#ifndef CONFIG_MMU
-+struct file *vmr_do_pr_or_file(struct vm_region *region, const char func[],
-+ int line)
-+{
-+ struct file *f = region->vm_file, *pr = region->vm_prfile;
++Since aufs-util has its own minor version number, you may not be
++able to find a GIT branch in aufs-util for your kernel's
++exact minor version number.
++In this case, you should git-checkout the branch for the
++nearest lower number.
+
-+ prfile_trace(f, pr, func, line, __func__);
-+ return (f && pr) ? pr : f;
-+}
++For (an unreleased) example:
++If you are using "linux-6.10" and the "aufs6.10" branch
++does not exist in aufs-util repository, then "aufs6.9", "aufs6.8"
++or something numerically smaller is the branch for your kernel.
+
-+void vmr_do_fput(struct vm_region *region, const char func[], int line)
-+{
-+ struct file *f = region->vm_file, *pr = region->vm_prfile;
++Also you can view all branches by
++ $ git branch -a
+
-+ prfile_trace(f, pr, func, line, __func__);
-+ fput(f);
-+ if (f && pr)
-+ fput(pr);
-+}
-+#endif /* !CONFIG_MMU */
-SPDX-License-Identifier: GPL-2.0
-aufs6.x-rcN standalone patch
-
-diff --git a/fs/dcache.c b/fs/dcache.c
-index 6c930ceed526..576ad162cdec 100644
---- a/fs/dcache.c
-+++ b/fs/dcache.c
-@@ -1450,6 +1450,7 @@ void d_walk(struct dentry *parent, void *data,
- seq = 1;
- goto again;
- }
-+EXPORT_SYMBOL_GPL(d_walk);
-
- struct check_mount {
- struct vfsmount *mnt;
-@@ -3051,6 +3052,7 @@ void d_exchange(struct dentry *dentry1, struct dentry *dentry2)
-
- write_sequnlock(&rename_lock);
- }
-+EXPORT_SYMBOL_GPL(d_exchange);
-
- /**
- * d_ancestor - search for an ancestor
-diff --git a/fs/exec.c b/fs/exec.c
-index 6518e33ea813..b67efac6a1ad 100644
---- a/fs/exec.c
-+++ b/fs/exec.c
-@@ -112,6 +112,7 @@ bool path_noexec(const struct path *path)
- return (path->mnt->mnt_flags & MNT_NOEXEC) ||
- (path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC);
- }
-+EXPORT_SYMBOL_GPL(path_noexec);
-
- #ifdef CONFIG_USELIB
- /*
-diff --git a/fs/fcntl.c b/fs/fcntl.c
-index d62e114c1b1a..ceef001775bd 100644
---- a/fs/fcntl.c
-+++ b/fs/fcntl.c
-@@ -87,6 +87,7 @@ int setfl(int fd, struct file * filp, unsigned int arg)
- out:
- return error;
- }
-+EXPORT_SYMBOL_GPL(setfl);
-
- static void f_modown(struct file *filp, struct pid *pid, enum pid_type type,
- int force)
-diff --git a/fs/file_table.c b/fs/file_table.c
-index ee21b3da9d08..c45ac36795dd 100644
---- a/fs/file_table.c
-+++ b/fs/file_table.c
-@@ -225,6 +225,7 @@ struct file *alloc_empty_file(int flags, const struct cred *cred)
- }
- return ERR_PTR(-ENFILE);
- }
-+EXPORT_SYMBOL_GPL(alloc_empty_file);
-
- /*
- * Variant of alloc_empty_file() that doesn't check and modify nr_files.
-diff --git a/fs/namespace.c b/fs/namespace.c
-index 6c57487f126b..16be9ac1c734 100644
---- a/fs/namespace.c
-+++ b/fs/namespace.c
-@@ -466,6 +466,7 @@ void __mnt_drop_write(struct vfsmount *mnt)
- mnt_dec_writers(real_mount(mnt));
- preempt_enable();
- }
-+EXPORT_SYMBOL_GPL(__mnt_drop_write);
-
- /**
- * mnt_drop_write - give up write access to a mount
-@@ -877,6 +878,7 @@ int is_current_mnt_ns(struct vfsmount *mnt)
- {
- return check_mnt(real_mount(mnt));
- }
-+EXPORT_SYMBOL_GPL(is_current_mnt_ns);
-
- /*
- * vfsmount lock must be held for write
-@@ -2152,6 +2154,7 @@ int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg,
- }
- return 0;
- }
-+EXPORT_SYMBOL_GPL(iterate_mounts);
-
- static void lock_mnt_tree(struct mount *mnt)
- {
-diff --git a/fs/notify/group.c b/fs/notify/group.c
-index 1de6631a3925..3008eb37a18d 100644
---- a/fs/notify/group.c
-+++ b/fs/notify/group.c
-@@ -100,6 +100,7 @@ void fsnotify_get_group(struct fsnotify_group *group)
- {
- refcount_inc(&group->refcnt);
- }
-+EXPORT_SYMBOL_GPL(fsnotify_get_group);
-
- /*
- * Drop a reference to a group. Free it if it's through.
-diff --git a/fs/open.c b/fs/open.c
-index 98f6601fbac6..8624e4ffa15b 100644
---- a/fs/open.c
-+++ b/fs/open.c
-@@ -67,6 +67,7 @@ int do_truncate(struct mnt_idmap *idmap, struct dentry *dentry,
- inode_unlock(dentry->d_inode);
- return ret;
- }
-+EXPORT_SYMBOL_GPL(do_truncate);
-
- long vfs_truncate(const struct path *path, loff_t length)
- {
-diff --git a/fs/read_write.c b/fs/read_write.c
-index 4771701c896b..c79270aba792 100644
---- a/fs/read_write.c
-+++ b/fs/read_write.c
-@@ -477,6 +477,7 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
- inc_syscr(current);
- return ret;
- }
-+EXPORT_SYMBOL_GPL(vfs_read);
-
- static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos)
- {
-@@ -592,6 +593,7 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_
- file_end_write(file);
- return ret;
- }
-+EXPORT_SYMBOL_GPL(vfs_write);
-
- /* file_ppos returns &file->f_pos or NULL if file is stream */
- static inline loff_t *file_ppos(struct file *file)
-diff --git a/fs/splice.c b/fs/splice.c
-index 7216ef993b5f..7ce1f1bc4268 100644
---- a/fs/splice.c
-+++ b/fs/splice.c
-@@ -932,6 +932,7 @@ long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
- return warn_unsupported(out, "write");
- return out->f_op->splice_write(pipe, out, ppos, len, flags);
- }
-+EXPORT_SYMBOL_GPL(do_splice_from);
-
- /*
- * Indicate to the caller that there was a premature EOF when reading from the
-diff --git a/fs/xattr.c b/fs/xattr.c
-index efd4736bc94b..ce1a2c39ab23 100644
---- a/fs/xattr.c
-+++ b/fs/xattr.c
-@@ -406,6 +406,7 @@ vfs_getxattr_alloc(struct mnt_idmap *idmap, struct dentry *dentry,
- *xattr_value = value;
- return error;
- }
-+EXPORT_SYMBOL_GPL(vfs_getxattr_alloc);
-
- ssize_t
- __vfs_getxattr(struct dentry *dentry, struct inode *inode, const char *name,
-diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
-index db4297f60bd3..9aca18312afb 100644
---- a/kernel/locking/lockdep.c
-+++ b/kernel/locking/lockdep.c
-@@ -239,6 +239,7 @@ inline struct lock_class *lockdep_hlock_class(struct held_lock *hlock)
- */
- return lock_classes + class_idx;
- }
-+EXPORT_SYMBOL_GPL(lockdep_hlock_class);
- #define hlock_class(hlock) lockdep_hlock_class(hlock)
-
- #ifdef CONFIG_LOCK_STAT
-diff --git a/kernel/task_work.c b/kernel/task_work.c
-index 065e1ef8fc8d..c623c6f0c645 100644
---- a/kernel/task_work.c
-+++ b/kernel/task_work.c
-@@ -182,3 +182,4 @@ void task_work_run(void)
- } while (work);
- }
- }
-+EXPORT_SYMBOL_GPL(task_work_run);
-diff --git a/security/security.c b/security/security.c
-index 23b129d482a7..fca4c5707a1c 100644
---- a/security/security.c
-+++ b/security/security.c
-@@ -1750,6 +1750,7 @@ int security_path_rmdir(const struct path *dir, struct dentry *dentry)
- return 0;
- return call_int_hook(path_rmdir, 0, dir, dentry);
- }
-+EXPORT_SYMBOL_GPL(security_path_rmdir);
-
- /**
- * security_path_unlink() - Check if removing a hard link is allowed
-@@ -1785,6 +1786,7 @@ int security_path_symlink(const struct path *dir, struct dentry *dentry,
- return 0;
- return call_int_hook(path_symlink, 0, dir, dentry, old_name);
- }
-+EXPORT_SYMBOL_GPL(security_path_symlink);
-
- /**
- * security_path_link - Check if creating a hard link is allowed
-@@ -1803,6 +1805,7 @@ int security_path_link(struct dentry *old_dentry, const struct path *new_dir,
- return 0;
- return call_int_hook(path_link, 0, old_dentry, new_dir, new_dentry);
- }
-+EXPORT_SYMBOL_GPL(security_path_link);
-
- /**
- * security_path_rename() - Check if renaming a file is allowed
-@@ -1864,6 +1867,7 @@ int security_path_chmod(const struct path *path, umode_t mode)
- return 0;
- return call_int_hook(path_chmod, 0, path, mode);
- }
-+EXPORT_SYMBOL_GPL(security_path_chmod);
-
- /**
- * security_path_chown() - Check if changing the file's owner/group is allowed
-@@ -1881,6 +1885,7 @@ int security_path_chown(const struct path *path, kuid_t uid, kgid_t gid)
- return 0;
- return call_int_hook(path_chown, 0, path, uid, gid);
- }
-+EXPORT_SYMBOL_GPL(security_path_chown);
-
- /**
- * security_path_chroot() - Check if changing the root directory is allowed
-@@ -2110,6 +2115,7 @@ int security_inode_permission(struct inode *inode, int mask)
- return 0;
- return call_int_hook(inode_permission, 0, inode, mask);
- }
-+EXPORT_SYMBOL_GPL(security_inode_permission);
-
- /**
- * security_inode_setattr() - Check if setting file attributes is allowed
-@@ -2588,6 +2594,7 @@ int security_file_permission(struct file *file, int mask)
-
- return fsnotify_perm(file, mask);
- }
-+EXPORT_SYMBOL_GPL(security_file_permission);
-
- /**
- * security_file_alloc() - Allocate and init a file's LSM blob
-@@ -2854,6 +2861,7 @@ int security_file_truncate(struct file *file)
- {
- return call_int_hook(file_truncate, 0, file);
- }
-+EXPORT_SYMBOL_GPL(security_file_truncate);
-
- /**
- * security_task_alloc() - Allocate a task's LSM blob
-diff -urN /usr/share/empty/Documentation/ABI/testing/debugfs-aufs linux/Documentation/ABI/testing/debugfs-aufs
---- /usr/share/empty/Documentation/ABI/testing/debugfs-aufs 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/ABI/testing/debugfs-aufs 2022-11-05 23:02:18.955889283 +0100
-@@ -0,0 +1,55 @@
-+What: /debug/aufs/si_<id>/
-+Date: March 2009
-+Contact: J. R. Okajima <hooanon05g@gmail.com>
-+Description:
-+ Under /debug/aufs, a directory named si_<id> is created
-+ per aufs mount, where <id> is a unique id generated
-+ internally.
+
-+What: /debug/aufs/si_<id>/plink
-+Date: Apr 2013
-+Contact: J. R. Okajima <hooanon05g@gmail.com>
-+Description:
-+ It has three lines and shows the information about the
-+ pseudo-link. The first line is a single number
-+ representing a number of buckets. The second line is a
-+ number of pseudo-links per buckets (separated by a
-+ blank). The last line is a single number representing a
-+ total number of psedo-links.
-+ When the aufs mount option 'noplink' is specified, it
-+ will show "1\n0\n0\n".
++3. Configuration and Compilation
++----------------------------------------
++Make sure you have git-checkout'ed the correct branch.
++
++For aufs-linux tree,
++- enable CONFIG_AUFS_FS.
++- set other aufs configurations if necessary.
++- for aufs5.13 and later
++ Because aufs is not only an ordinary filesystem (callee of VFS), but
++ also a caller of VFS functions for branch filesystems, subclassing of
++ the internal locks for LOCKDEP is necessary. LOCKDEP is a debugging
++ feature of linux kernel. If you enable CONFIG_LOCKDEP, then you will
++ need to customize some LOCKDEP numbers. Here are what I use on my
++ test environment.
++ CONFIG_LOCKDEP_BITS=21
++ CONFIG_LOCKDEP_CHAINS_BITS=21
++ CONFIG_LOCKDEP_STACK_TRACE_BITS=24
++ Also you will need to expand some constant values in LOCKDEP. Refer
++ to lockdep-debug.patch in aufs-standalone.git.
++
++For aufs-standalone tree,
++There are several ways to build.
+
-+What: /debug/aufs/si_<id>/xib
-+Date: March 2009
-+Contact: J. R. Okajima <hooanon05g@gmail.com>
-+Description:
-+ It shows the consumed blocks by xib (External Inode Number
-+ Bitmap), its block size and file size.
-+ When the aufs mount option 'noxino' is specified, it
-+ will be empty. About XINO files, see the aufs manual.
++1.
++- apply ./aufs6-kbuild.patch to your kernel source files.
++- apply ./aufs6-base.patch too.
++- apply ./aufs6-mmap.patch too.
++- apply ./aufs6-standalone.patch too, if you have a plan to set
++ CONFIG_AUFS_FS=m. otherwise you don't need ./aufs-standalone.patch.
++- copy ./{Documentation,fs,include/uapi/linux/aufs_type.h} files to your
++ kernel source tree. Never copy $PWD/include/uapi/linux/Kbuild.
++- enable CONFIG_AUFS_FS, you can select either
++ =m or =y.
++- and build your kernel as usual.
++- install the built kernel.
++- install the header files too by "make headers_install" to the
++ directory where you specify. By default, it is $PWD/usr.
++ "make help" shows a brief note for headers_install.
++- and reboot your system.
+
-+What: /debug/aufs/si_<id>/xi<branch-index>
-+Date: March 2009
-+Contact: J. R. Okajima <hooanon05g@gmail.com>
-+Description:
-+ It shows the consumed blocks by xino (External Inode Number
-+ Translation Table), its link count, block size and file
-+ size.
-+ Due to the file size limit, there may exist multiple
-+ xino files per branch. In this case, "-N" is added to
-+ the filename and it corresponds to the index of the
-+ internal xino array. "-0" is omitted.
-+ When the aufs mount option 'noxino' is specified, Those
-+ entries won't exist. About XINO files, see the aufs
-+ manual.
++2.
++- module only (CONFIG_AUFS_FS=m).
++- apply ./aufs6-base.patch to your kernel source files.
++- apply ./aufs6-mmap.patch too.
++- apply ./aufs6-standalone.patch too.
++- build your kernel, don't forget "make headers_install", and reboot.
++- edit ./config.mk and set other aufs configurations if necessary.
++ Note: You should read $PWD/fs/aufs/Kconfig carefully which describes
++ every aufs configurations.
++- build the module by simple "make".
++- you can specify ${KDIR} make variable which points to your kernel
++ source tree.
++- install the files
++ + run "make install" to install the aufs module, or copy the built
++ $PWD/aufs.ko to /lib/modules/... and run depmod -a (or reboot simply).
++ + run "make install_headers" (instead of headers_install) to install
++ the modified aufs header file (you can specify DESTDIR which is
++ available in aufs standalone version's Makefile only), or copy
++ $PWD/usr/include/linux/aufs_type.h to /usr/include/linux or wherever
++ you like manually. By default, the target directory is $PWD/usr.
++- no need to apply aufs6-kbuild.patch, nor copying source files to your
++ kernel source tree.
+
-+What: /debug/aufs/si_<id>/xigen
-+Date: March 2009
-+Contact: J. R. Okajima <hooanon05g@gmail.com>
-+Description:
-+ It shows the consumed blocks by xigen (External Inode
-+ Generation Table), its block size and file size.
-+ If CONFIG_AUFS_EXPORT is disabled, this entry will not
-+ be created.
-+ When the aufs mount option 'noxino' is specified, it
-+ will be empty. About XINO files, see the aufs manual.
-diff -urN /usr/share/empty/Documentation/ABI/testing/sysfs-aufs linux/Documentation/ABI/testing/sysfs-aufs
---- /usr/share/empty/Documentation/ABI/testing/sysfs-aufs 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/ABI/testing/sysfs-aufs 2022-11-05 23:02:18.955889283 +0100
-@@ -0,0 +1,31 @@
-+What: /sys/fs/aufs/si_<id>/
-+Date: March 2009
-+Contact: J. R. Okajima <hooanon05g@gmail.com>
-+Description:
-+ Under /sys/fs/aufs, a directory named si_<id> is created
-+ per aufs mount, where <id> is a unique id generated
-+ internally.
++Note: The header file aufs_type.h is necessary to build aufs-util
++ as well as "make headers_install" in the kernel source tree.
++ headers_install is subject to be forgotten, but it is essentially
++ necessary, not only for building aufs-util.
++ You may not meet problems without headers_install in some older
++ version though.
+
-+What: /sys/fs/aufs/si_<id>/br<idx>
-+Date: March 2009
-+Contact: J. R. Okajima <hooanon05g@gmail.com>
-+Description:
-+ It shows the abolute path of a member directory (which
-+ is called branch) in aufs, and its permission.
++And then,
++- read README in aufs-util, build and install it
++- note that your distribution may contain an obsoleted version of
++ aufs_type.h in /usr/include/linux or something. When you build aufs
++ utilities, make sure that your compiler refers the correct aufs header
++ file which is built by "make headers_install."
++- if you want to use readdir(3) in userspace or pathconf(3) wrapper,
++ then run "make install_ulib" too. And refer to the aufs manual in
++ detail.
+
-+What: /sys/fs/aufs/si_<id>/brid<idx>
-+Date: July 2013
-+Contact: J. R. Okajima <hooanon05g@gmail.com>
-+Description:
-+ It shows the id of a member directory (which is called
-+ branch) in aufs.
++There several other patches in aufs-standalone.git. They are all
++optional. When you meet some problems, they will help you.
++- aufs6-loopback.patch
++ Supports a nested loopback mount in a branch-fs. This patch is
++ unnecessary until aufs produces a message like "you may want to try
++ another patch for loopback file".
++- vfs-ino.patch
++ Modifies a system global kernel internal function get_next_ino() in
++ order to stop assigning 0 for an inode-number. Not directly related to
++ aufs, but recommended generally.
++- tmpfs-idr.patch
++ Keeps the tmpfs inode number as the lowest value. Effective to reduce
++ the size of aufs XINO files for tmpfs branch. Also it prevents the
++ duplication of inode number, which is important for backup tools and
++ other utilities. When you find aufs XINO files for tmpfs branch
++ growing too much, try this patch.
++- lockdep-debug.patch
++ Similar to some kernel configurations for LOCKDEP (see the top of
++ this section), you will need expand some constants in LOCKDEP for
++ aufs if you enable CONFIG_LOCKDEP.
+
-+What: /sys/fs/aufs/si_<id>/xi_path
-+Date: March 2009
-+Contact: J. R. Okajima <hooanon05g@gmail.com>
-+Description:
-+ It shows the abolute path of XINO (External Inode Number
-+ Bitmap, Translation Table and Generation Table) file
-+ even if it is the default path.
-+ When the aufs mount option 'noxino' is specified, it
-+ will be empty. About XINO files, see the aufs manual.
-diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/01intro.txt linux/Documentation/filesystems/aufs/design/01intro.txt
---- /usr/share/empty/Documentation/filesystems/aufs/design/01intro.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/01intro.txt 2022-11-05 23:02:18.955889283 +0100
++
++4. Usage
++----------------------------------------
++At first, make sure aufs-util are installed, and please read the aufs
++manual, aufs.5 in aufs-util.git tree.
++$ man -l aufs.5
++
++And then,
++$ mkdir /tmp/rw /tmp/aufs
++# mount -t aufs -o br=/tmp/rw:${HOME} none /tmp/aufs
++
++Here is another example. The result is equivalent.
++# mount -t aufs -o br=/tmp/rw=rw:${HOME}=ro none /tmp/aufs
++ Or
++# mount -t aufs -o br:/tmp/rw none /tmp/aufs
++# mount -o remount,append:${HOME} /tmp/aufs
++
++Then, you can see whole tree of your home dir through /tmp/aufs. If
++you modify a file under /tmp/aufs, the one on your home directory is
++not affected, instead the same named file will be newly created under
++/tmp/rw. And all of your modification to a file will be applied to
++the one under /tmp/rw. This is called the file based Copy on Write
++(COW) method.
++Aufs mount options are described in aufs.5.
++If you run chroot or something and make your aufs as a root directory,
++then you need to customize the shutdown script. See the aufs manual in
++detail.
++
++Additionally, there are some sample usages of aufs which are a
++diskless system with network booting, and LiveCD over NFS.
++See sample dir in CVS tree on SourceForge.
++
++
++5. Contact
++----------------------------------------
++When you have any problems or strange behaviour in aufs, please let me
++know with:
++- /proc/mounts (instead of the output of mount(8))
++- /sys/module/aufs/*
++- /sys/fs/aufs/* (if you have them)
++- /debug/aufs/* (if you have them)
++- linux kernel version
++ if your kernel is not plain, for example modified by distributor,
++ the url where i can download its source is necessary too.
++- aufs version which was printed at loading the module or booting the
++ system, instead of the date you downloaded.
++- configuration (define/undefine CONFIG_AUFS_xxx)
++- kernel configuration or /proc/config.gz (if you have it)
++- LSM (linux security module, if you are using)
++- behaviour which you think to be incorrect
++- actual operation, reproducible one is better
++- mailto: aufs-users at lists.sourceforge.net
++
++Usually, I don't watch the Public Areas(Bugs, Support Requests, Patches,
++and Feature Requests) on SourceForge. Please join and write to
++aufs-users ML.
++
++
++6. Acknowledgements
++----------------------------------------
++Thanks to everyone who have tried and are using aufs, whoever
++have reported a bug or any feedback.
++
++Especially donators:
++Tomas Matejicek(slax.org) made a donation (much more than once).
++ Since Apr 2010, Tomas M (the author of Slax and Linux Live
++ scripts) is making "doubling" donations.
++ Unfortunately I cannot list all of the donators, but I really
++ appreciate.
++ It ends Aug 2010, but the ordinary donation URL is still available.
++ <http://sourceforge.net/donate/index.php?group_id=167503>
++Dai Itasaka made a donation (2007/8).
++Chuck Smith made a donation (2008/4, 10 and 12).
++Henk Schoneveld made a donation (2008/9).
++Chih-Wei Huang, ASUS, CTC donated Eee PC 4G (2008/10).
++Francois Dupoux made a donation (2008/11).
++Bruno Cesar Ribas and Luis Carlos Erpen de Bona, C3SL serves public
++ aufs2 GIT tree (2009/2).
++William Grant made a donation (2009/3).
++Patrick Lane made a donation (2009/4).
++The Mail Archive (mail-archive.com) made donations (2009/5).
++Nippy Networks (Ed Wildgoose) made a donation (2009/7).
++New Dream Network, LLC (www.dreamhost.com) made a donation (2009/11).
++Pavel Pronskiy made a donation (2011/2).
++Iridium and Inmarsat satellite phone retailer (www.mailasail.com), Nippy
++ Networks (Ed Wildgoose) made a donation for hardware (2011/3).
++Max Lekomcev (DOM-TV project) made a donation (2011/7, 12, 2012/3, 6 and
++11).
++Sam Liddicott made a donation (2011/9).
++Era Scarecrow made a donation (2013/4).
++Bor Ratajc made a donation (2013/4).
++Alessandro Gorreta made a donation (2013/4).
++POIRETTE Marc made a donation (2013/4).
++Alessandro Gorreta made a donation (2013/4).
++lauri kasvandik made a donation (2013/5).
++"pemasu from Finland" made a donation (2013/7).
++The Parted Magic Project made a donation (2013/9 and 11).
++Pavel Barta made a donation (2013/10).
++Nikolay Pertsev made a donation (2014/5).
++James B made a donation (2014/7, 2015/7, and 2021/12).
++Stefano Di Biase made a donation (2014/8).
++Daniel Epellei made a donation (2015/1).
++OmegaPhil made a donation (2016/1, 2018/4).
++Tomasz Szewczyk made a donation (2016/4).
++James Burry made a donation (2016/12).
++Carsten Rose made a donation (2018/9).
++Porteus Kiosk made a donation (2018/10).
++huronOS team: Enya Quetzalli made donations (2022/5, 2023/5 and 8).
++Vasily Mikhaylichenko made a donation (2023/5).
++
++Thank you very much.
++Donations are always, including future donations, very important and
++helpful for me to keep on developing aufs.
++
++
++7.
++----------------------------------------
++If you are an experienced user, no explanation is needed. Aufs is
++just a linux filesystem.
++
++
++Enjoy!
++
++# Local variables: ;
++# mode: text;
++# End: ;
+diff --git a/Documentation/filesystems/aufs/design/01intro.txt b/Documentation/filesystems/aufs/design/01intro.txt
+new file mode 100644
+index 00000000000000..4c468b3264b56b
+--- /dev/null
++++ b/Documentation/filesystems/aufs/design/01intro.txt
@@ -0,0 +1,171 @@
+
+# Copyright (C) 2005-2022 Junjiro R. Okajima
+Some people may think it is better to pass such work to user space
+helper, instead of doing in kernel space. Actually I am still thinking
+about it. But currently I have implemented it in kernel space.
-diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/02struct.txt linux/Documentation/filesystems/aufs/design/02struct.txt
---- /usr/share/empty/Documentation/filesystems/aufs/design/02struct.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/02struct.txt 2022-11-05 23:02:18.955889283 +0100
+diff --git a/Documentation/filesystems/aufs/design/02struct.txt b/Documentation/filesystems/aufs/design/02struct.txt
+new file mode 100644
+index 00000000000000..83be46121ae26f
+--- /dev/null
++++ b/Documentation/filesystems/aufs/design/02struct.txt
@@ -0,0 +1,258 @@
+
+# Copyright (C) 2005-2022 Junjiro R. Okajima
+- etc.
+
+For this purpose, use "aumvdown" command in aufs-util.git.
-diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/03atomic_open.txt linux/Documentation/filesystems/aufs/design/03atomic_open.txt
---- /usr/share/empty/Documentation/filesystems/aufs/design/03atomic_open.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/03atomic_open.txt 2022-11-05 23:02:18.955889283 +0100
+diff --git a/Documentation/filesystems/aufs/design/03atomic_open.txt b/Documentation/filesystems/aufs/design/03atomic_open.txt
+new file mode 100644
+index 00000000000000..4811f243246545
+--- /dev/null
++++ b/Documentation/filesystems/aufs/design/03atomic_open.txt
@@ -0,0 +1,85 @@
+
+# Copyright (C) 2015-2022 Junjiro R. Okajima
+ ->atomic_open() are lost. in the ordinary case, the checks are
+ done by VFS:do_last(), lookup_open() and atomic_open(). some can
+ be implemented in aufs, but not all I am afraid.
-diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/03lookup.txt linux/Documentation/filesystems/aufs/design/03lookup.txt
---- /usr/share/empty/Documentation/filesystems/aufs/design/03lookup.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/03lookup.txt 2022-11-05 23:02:18.959222617 +0100
+diff --git a/Documentation/filesystems/aufs/design/03lookup.txt b/Documentation/filesystems/aufs/design/03lookup.txt
+new file mode 100644
+index 00000000000000..766a28be02637a
+--- /dev/null
++++ b/Documentation/filesystems/aufs/design/03lookup.txt
@@ -0,0 +1,113 @@
+
+# Copyright (C) 2005-2022 Junjiro R. Okajima
+ test, and skip the revalidation in step 4. It is useful and improves
+ aufs performance when system surely hide the aufs branches from user,
+ by over-mounting something (or another method).
-diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/04branch.txt linux/Documentation/filesystems/aufs/design/04branch.txt
---- /usr/share/empty/Documentation/filesystems/aufs/design/04branch.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/04branch.txt 2022-11-05 23:02:18.959222617 +0100
+diff --git a/Documentation/filesystems/aufs/design/04branch.txt b/Documentation/filesystems/aufs/design/04branch.txt
+new file mode 100644
+index 00000000000000..ffeb97dcaff350
+--- /dev/null
++++ b/Documentation/filesystems/aufs/design/04branch.txt
@@ -0,0 +1,74 @@
+
+# Copyright (C) 2005-2022 Junjiro R. Okajima
+ - a file on the branch is mmap-ed.
+ - a regular file on the branch is opened for write and there is no
+ same named entry on the upper branch.
-diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/05wbr_policy.txt linux/Documentation/filesystems/aufs/design/05wbr_policy.txt
---- /usr/share/empty/Documentation/filesystems/aufs/design/05wbr_policy.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/05wbr_policy.txt 2022-11-05 23:02:18.959222617 +0100
+diff --git a/Documentation/filesystems/aufs/design/05wbr_policy.txt b/Documentation/filesystems/aufs/design/05wbr_policy.txt
+new file mode 100644
+index 00000000000000..a2143bfe6efc87
+--- /dev/null
++++ b/Documentation/filesystems/aufs/design/05wbr_policy.txt
@@ -0,0 +1,64 @@
+
+# Copyright (C) 2005-2022 Junjiro R. Okajima
+ where the source and the target exists and selects the higher
+ one. If the selected branch is readonly, then aufs follows the
+ copyup policy.
-diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/06dirren.dot linux/Documentation/filesystems/aufs/design/06dirren.dot
---- /usr/share/empty/Documentation/filesystems/aufs/design/06dirren.dot 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/06dirren.dot 2022-11-05 23:02:18.959222617 +0100
+diff --git a/Documentation/filesystems/aufs/design/06dirren.dot b/Documentation/filesystems/aufs/design/06dirren.dot
+new file mode 100644
+index 00000000000000..4e6c7e7c20ef13
+--- /dev/null
++++ b/Documentation/filesystems/aufs/design/06dirren.dot
@@ -0,0 +1,44 @@
+
+// to view this graph, run dot(1) command in GRAPHVIZ.
+
+aufs_lookup -> whinfo [label="load/remove"];
+}
-diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/06dirren.txt linux/Documentation/filesystems/aufs/design/06dirren.txt
---- /usr/share/empty/Documentation/filesystems/aufs/design/06dirren.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/06dirren.txt 2022-11-05 23:02:18.959222617 +0100
+diff --git a/Documentation/filesystems/aufs/design/06dirren.txt b/Documentation/filesystems/aufs/design/06dirren.txt
+new file mode 100644
+index 00000000000000..58ec5e22fe3d00
+--- /dev/null
++++ b/Documentation/filesystems/aufs/design/06dirren.txt
@@ -0,0 +1,102 @@
+
+# Copyright (C) 2017-2022 Junjiro R. Okajima
+contains two names, before- and after-rename, the name comparision in
+UDBA handler may not work correctly. In this case, the behaviour will be
+equivalen to udba=reval case.
-diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/06fhsm.txt linux/Documentation/filesystems/aufs/design/06fhsm.txt
---- /usr/share/empty/Documentation/filesystems/aufs/design/06fhsm.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/06fhsm.txt 2022-11-05 23:02:18.959222617 +0100
+diff --git a/Documentation/filesystems/aufs/design/06fhsm.txt b/Documentation/filesystems/aufs/design/06fhsm.txt
+new file mode 100644
+index 00000000000000..d3b56325ff87ad
+--- /dev/null
++++ b/Documentation/filesystems/aufs/design/06fhsm.txt
@@ -0,0 +1,118 @@
+
+# Copyright (C) 2011-2022 Junjiro R. Okajima
+
+And of course, in every step, an error may happen. So the operation
+should restore the original file state after an error happens.
-diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/06mmap.txt linux/Documentation/filesystems/aufs/design/06mmap.txt
---- /usr/share/empty/Documentation/filesystems/aufs/design/06mmap.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/06mmap.txt 2022-11-05 23:02:18.959222617 +0100
+diff --git a/Documentation/filesystems/aufs/design/06mmap.txt b/Documentation/filesystems/aufs/design/06mmap.txt
+new file mode 100644
+index 00000000000000..ddc65ce97fa3e8
+--- /dev/null
++++ b/Documentation/filesystems/aufs/design/06mmap.txt
@@ -0,0 +1,72 @@
+
+# Copyright (C) 2005-2022 Junjiro R. Okajima
+ equivalent to vm_prfile described above.
+
+I have to give up this "looks-smater" approach.
-diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/06xattr.txt linux/Documentation/filesystems/aufs/design/06xattr.txt
---- /usr/share/empty/Documentation/filesystems/aufs/design/06xattr.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/06xattr.txt 2022-11-05 23:02:18.959222617 +0100
+diff --git a/Documentation/filesystems/aufs/design/06xattr.txt b/Documentation/filesystems/aufs/design/06xattr.txt
+new file mode 100644
+index 00000000000000..4e5ead3ad74194
+--- /dev/null
++++ b/Documentation/filesystems/aufs/design/06xattr.txt
@@ -0,0 +1,94 @@
+
+# Copyright (C) 2014-2022 Junjiro R. Okajima
+Some contradiction may happen I am afraid.
+Do we need another attribute to stop copying XATTR? I am unsure. For
+now, aufs implements the branch attributes to ignore the error.
-diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/07export.txt linux/Documentation/filesystems/aufs/design/07export.txt
---- /usr/share/empty/Documentation/filesystems/aufs/design/07export.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/07export.txt 2022-11-05 23:02:18.959222617 +0100
+diff --git a/Documentation/filesystems/aufs/design/07export.txt b/Documentation/filesystems/aufs/design/07export.txt
+new file mode 100644
+index 00000000000000..40b2f1f1204932
+--- /dev/null
++++ b/Documentation/filesystems/aufs/design/07export.txt
@@ -0,0 +1,58 @@
+
+# Copyright (C) 2005-2022 Junjiro R. Okajima
+ convert it into ESTALE for NFSD.
+- readdir(): call lockdep_on/off() because filldir in NFSD calls
+ lookup_one_len(), vfs_getattr(), encode_fh() and others.
-diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/08shwh.txt linux/Documentation/filesystems/aufs/design/08shwh.txt
---- /usr/share/empty/Documentation/filesystems/aufs/design/08shwh.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/08shwh.txt 2022-11-05 23:02:18.959222617 +0100
+diff --git a/Documentation/filesystems/aufs/design/08shwh.txt b/Documentation/filesystems/aufs/design/08shwh.txt
+new file mode 100644
+index 00000000000000..67245e98e6b472
+--- /dev/null
++++ b/Documentation/filesystems/aufs/design/08shwh.txt
@@ -0,0 +1,52 @@
+
+# Copyright (C) 2005-2022 Junjiro R. Okajima
+
+This new squashfs archive can be stored on the boot device and the
+initramfs will use it to replace the old one at the next boot.
-diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/10dynop.txt linux/Documentation/filesystems/aufs/design/10dynop.txt
---- /usr/share/empty/Documentation/filesystems/aufs/design/10dynop.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/10dynop.txt 2022-11-05 23:02:18.959222617 +0100
+diff --git a/Documentation/filesystems/aufs/design/10dynop.txt b/Documentation/filesystems/aufs/design/10dynop.txt
+new file mode 100644
+index 00000000000000..da382ec2dc05d6
+--- /dev/null
++++ b/Documentation/filesystems/aufs/design/10dynop.txt
@@ -0,0 +1,47 @@
+
+# Copyright (C) 2010-2022 Junjiro R. Okajima
+XIP (DAX) mainly.
+Currently this approach is applied to address_space_operations for
+regular files only.
-diff -urN /usr/share/empty/Documentation/filesystems/aufs/README linux/Documentation/filesystems/aufs/README
---- /usr/share/empty/Documentation/filesystems/aufs/README 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/README 2023-09-02 12:00:06.376642958 +0200
-@@ -0,0 +1,409 @@
-+
-+Aufs6 -- advanced multi layered unification filesystem version 6.x
-+http://aufs.sf.net
-+Junjiro R. Okajima
-+
-+
-+0. Introduction
-+----------------------------------------
-+In the early days, aufs was entirely re-designed and re-implemented
-+Unionfs Version 1.x series. Adding many original ideas, approaches,
-+improvements and implementations, it became totally different from
-+Unionfs while keeping the basic features.
-+Later, Unionfs Version 2.x series began taking some of the same
-+approaches to aufs1's.
-+Unionfs was being developed by Professor Erez Zadok at Stony Brook
-+University and his team.
-+
-+Aufs6 supports linux-v6.0 and later, try aufs6.0 branch in
-+aufs-linux.git or aufs-standalone.git.
-+If you want older kernel version support,
-+- for linux-v5.x series, try aufs-linux.git or aufs-standalone.git
-+- for linux-v4.x series, try aufs4-linux.git or aufs4-standalone.git
-+- for linux-v3.x series, try aufs3-linux.git or aufs3-standalone.git
-+- for linux-v2.6.16 and later, try aufs2-2.6.git, aufs2-standalone.git
-+ or aufs1 from CVS on SourceForge.
-+
-+Note: the name of aufs5-linux.git and aufs5-standalone.git on github
-+ were changed. Now they are aufs-linux.git and
-+ aufs-standalone.git and they contain aufs5 and later branches.
-+
-+Note: it becomes clear that "Aufs was rejected. Let's give it up."
-+ According to Christoph Hellwig, linux rejects all union-type
-+ filesystems but UnionMount.
-+<http://marc.info/?l=linux-kernel&m=123938533724484&w=2>
-+
-+PS. Al Viro seems have a plan to merge aufs as well as overlayfs and
-+ UnionMount, and he pointed out an issue around a directory mutex
-+ lock and aufs addressed it. But it is still unsure whether aufs will
-+ be merged (or any other union solution).
-+<http://marc.info/?l=linux-kernel&m=136312705029295&w=1>
-+
-+
-+1. Features
-+----------------------------------------
-+- unite several directories into a single virtual filesystem. The member
-+ directory is called as a branch.
-+- you can specify the permission flags to the branch, which are 'readonly',
-+ 'readwrite' and 'whiteout-able.'
-+- by upper writable branch, internal copyup and whiteout, files/dirs on
-+ readonly branch are modifiable logically.
-+- dynamic branch manipulation, add, del.
-+- etc...
-+
-+Also there are many enhancements in aufs, such as:
-+- test only the highest one for the directory permission (dirperm1)
-+- copyup on open (coo=)
-+- 'move' policy for copy-up between two writable branches, after
-+ checking free space.
-+- xattr, acl
-+- readdir(3) in userspace.
-+- keep inode number by external inode number table
-+- keep the timestamps of file/dir in internal copyup operation
-+- seekable directory, supporting NFS readdir.
-+- whiteout is hardlinked in order to reduce the consumption of inodes
-+ on branch
-+- do not copyup, nor create a whiteout when it is unnecessary
-+- revert a single systemcall when an error occurs in aufs
-+- remount interface instead of ioctl
-+- maintain /etc/mtab by an external command, /sbin/mount.aufs.
-+- loopback mounted filesystem as a branch
-+- kernel thread for removing the dir who has a plenty of whiteouts
-+- support copyup sparse file (a file which has a 'hole' in it)
-+- default permission flags for branches
-+- selectable permission flags for ro branch, whether whiteout can
-+ exist or not
-+- export via NFS.
-+- support <sysfs>/fs/aufs and <debugfs>/aufs.
-+- support multiple writable branches, some policies to select one
-+ among multiple writable branches.
-+- a new semantics for link(2) and rename(2) to support multiple
-+ writable branches.
-+- no glibc changes are required.
-+- pseudo hardlink (hardlink over branches)
-+- allow a direct access manually to a file on branch, e.g. bypassing aufs.
-+ including NFS or remote filesystem branch.
-+- userspace wrapper for pathconf(3)/fpathconf(3) with _PC_LINK_MAX.
-+- and more...
-+
-+Currently these features are dropped temporary from aufs6.
-+See design/08plan.txt in detail.
-+- nested mount, i.e. aufs as readonly no-whiteout branch of another aufs
-+ (robr)
-+- statistics of aufs thread (/sys/fs/aufs/stat)
-+
-+Features or just an idea in the future (see also design/*.txt),
-+- reorder the branch index without del/re-add.
-+- permanent xino files for NFSD
-+- an option for refreshing the opened files after add/del branches
-+- light version, without branch manipulation. (unnecessary?)
-+- copyup in userspace
-+- inotify in userspace
-+- readv/writev
-+
-+
-+2. Download
-+----------------------------------------
-+There are three GIT trees for aufs6, aufs-linux.git,
-+aufs-standalone.git, and aufs-util.git.
-+While the aufs-util is always necessary, you need either of aufs-linux
-+or aufs-standalone.
-+
-+The aufs-linux tree includes the whole linux mainline GIT tree,
-+git://git.kernel.org/.../torvalds/linux.git.
-+And you cannot select CONFIG_AUFS_FS=m for this version, eg. you cannot
-+build aufs6 as an external kernel module.
-+Several extra patches are not included in this tree. Only
-+aufs-standalone tree contains them. They are described in the later
-+section "Configuration and Compilation."
-+
-+On the other hand, the aufs-standalone tree has only aufs source files
-+and necessary patches, and you can select CONFIG_AUFS_FS=m.
-+But you need to apply all aufs patches manually.
-+
-+You will find GIT branches whose name is in form of "aufs6.x" where "x"
-+represents the linux kernel version, "linux-6.x". For instance,
-+"aufs6.0" is for linux-6.0. For latest "linux-6.x-rcN", use
-+"aufs6.x-rcN" branch.
-+
-+o aufs-linux tree
-+$ git clone --reference /your/linux/git/tree \
-+ git://github.com/sfjro/aufs-linux.git aufs-linux.git
-+- if you don't have linux GIT tree, then remove "--reference ..."
-+$ cd aufs-linux.git
-+$ git checkout origin/aufs6.0
-+
-+Or You may want to directly git-pull aufs into your linux GIT tree, and
-+leave the patch-work to GIT.
-+$ cd /your/linux/git/tree
-+$ git remote add aufs git://github.com/sfjro/aufs-linux.git
-+$ git fetch aufs
-+$ git checkout -b my6.0 v6.0
-+$ (add your local change...)
-+$ git pull aufs aufs6.0
-+- now you have v6.0 + your_changes + aufs6.0 in you my6.0 branch.
-+- you may need to solve some conflicts between your_changes and
-+ aufs6.0. in this case, git-rerere is recommended so that you can
-+ solve the similar conflicts automatically when you upgrade to 6.1 or
-+ later in the future.
-+
-+o aufs-standalone tree
-+$ git clone git://github.com/sfjro/aufs-standalone.git aufs-standalone.git
-+$ cd aufs-standalone.git
-+$ git checkout origin/aufs6.0
-+
-+o aufs-util tree
-+$ git clone git://git.code.sf.net/p/aufs/aufs-util aufs-util.git
-+- note that the public aufs-util.git is on SourceForge instead of
-+ GitHUB.
-+$ cd aufs-util.git
-+$ git checkout origin/aufs6.0
-+
-+Note: The 6.x-rcN branch is to be used with `rc' kernel versions ONLY.
-+The minor version number, 'x' in '6.x', of aufs may not always
-+follow the minor version number of the kernel.
-+Because changes in the kernel that cause the use of a new
-+minor version number do not always require changes to aufs-util.
-+
-+Since aufs-util has its own minor version number, you may not be
-+able to find a GIT branch in aufs-util for your kernel's
-+exact minor version number.
-+In this case, you should git-checkout the branch for the
-+nearest lower number.
-+
-+For (an unreleased) example:
-+If you are using "linux-6.10" and the "aufs6.10" branch
-+does not exist in aufs-util repository, then "aufs6.9", "aufs6.8"
-+or something numerically smaller is the branch for your kernel.
-+
-+Also you can view all branches by
-+ $ git branch -a
-+
-+
-+3. Configuration and Compilation
-+----------------------------------------
-+Make sure you have git-checkout'ed the correct branch.
+diff --git a/MAINTAINERS b/MAINTAINERS
+index a7c4cf8201e012..5b377eebc87952 100644
+--- a/MAINTAINERS
++++ b/MAINTAINERS
+@@ -3347,6 +3347,19 @@ F: include/uapi/linux/audit.h
+ F: kernel/audit*
+ F: lib/*audit.c
+
++AUFS (advanced multi layered unification filesystem) FILESYSTEM
++M: "J. R. Okajima" <hooanon05g@gmail.com>
++L: aufs-users@lists.sourceforge.net (members only)
++L: linux-unionfs@vger.kernel.org
++S: Supported
++W: http://aufs.sourceforge.net
++T: git://github.com/sfjro/aufs4-linux.git
++F: Documentation/ABI/testing/debugfs-aufs
++F: Documentation/ABI/testing/sysfs-aufs
++F: Documentation/filesystems/aufs/
++F: fs/aufs/
++F: include/uapi/linux/aufs_type.h
+
-+For aufs-linux tree,
-+- enable CONFIG_AUFS_FS.
-+- set other aufs configurations if necessary.
-+- for aufs5.13 and later
-+ Because aufs is not only an ordinary filesystem (callee of VFS), but
-+ also a caller of VFS functions for branch filesystems, subclassing of
-+ the internal locks for LOCKDEP is necessary. LOCKDEP is a debugging
-+ feature of linux kernel. If you enable CONFIG_LOCKDEP, then you will
-+ need to customize some LOCKDEP numbers. Here are what I use on my
-+ test environment.
-+ CONFIG_LOCKDEP_BITS=21
-+ CONFIG_LOCKDEP_CHAINS_BITS=21
-+ CONFIG_LOCKDEP_STACK_TRACE_BITS=24
-+ Also you will need to expand some constant values in LOCKDEP. Refer
-+ to lockdep-debug.patch in aufs-standalone.git.
+ AUXILIARY BUS DRIVER
+ M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+ R: Dave Ertman <david.m.ertman@intel.com>
+diff --git a/drivers/block/loop.c b/drivers/block/loop.c
+index 9f2d412fc560e1..1fefc6a8d049c7 100644
+--- a/drivers/block/loop.c
++++ b/drivers/block/loop.c
+@@ -645,6 +645,24 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
+ goto done;
+ }
+
++/*
++ * for AUFS
++ * no get/put for file.
++ */
++struct file *loop_backing_file(struct super_block *sb)
++{
++ struct file *ret;
++ struct loop_device *l;
+
-+For aufs-standalone tree,
-+There are several ways to build.
++ ret = NULL;
++ if (MAJOR(sb->s_dev) == LOOP_MAJOR) {
++ l = sb->s_bdev->bd_disk->private_data;
++ ret = l->lo_backing_file;
++ }
++ return ret;
++}
++EXPORT_SYMBOL_GPL(loop_backing_file);
+
-+1.
-+- apply ./aufs6-kbuild.patch to your kernel source files.
-+- apply ./aufs6-base.patch too.
-+- apply ./aufs6-mmap.patch too.
-+- apply ./aufs6-standalone.patch too, if you have a plan to set
-+ CONFIG_AUFS_FS=m. otherwise you don't need ./aufs-standalone.patch.
-+- copy ./{Documentation,fs,include/uapi/linux/aufs_type.h} files to your
-+ kernel source tree. Never copy $PWD/include/uapi/linux/Kbuild.
-+- enable CONFIG_AUFS_FS, you can select either
-+ =m or =y.
-+- and build your kernel as usual.
-+- install the built kernel.
-+- install the header files too by "make headers_install" to the
-+ directory where you specify. By default, it is $PWD/usr.
-+ "make help" shows a brief note for headers_install.
-+- and reboot your system.
+ /* loop sysfs attributes */
+
+ static ssize_t loop_attr_show(struct device *dev, char *page,
+diff --git a/fs/Kconfig b/fs/Kconfig
+index 42837617a55b54..6eaf5cde00fde8 100644
+--- a/fs/Kconfig
++++ b/fs/Kconfig
+@@ -333,6 +333,7 @@ source "fs/sysv/Kconfig"
+ source "fs/ufs/Kconfig"
+ source "fs/erofs/Kconfig"
+ source "fs/vboxsf/Kconfig"
++source "fs/aufs/Kconfig"
+
+ endif # MISC_FILESYSTEMS
+
+diff --git a/fs/Makefile b/fs/Makefile
+index 75522f88e76367..8743be00607ec7 100644
+--- a/fs/Makefile
++++ b/fs/Makefile
+@@ -130,3 +130,4 @@ obj-$(CONFIG_EFIVAR_FS) += efivarfs/
+ obj-$(CONFIG_EROFS_FS) += erofs/
+ obj-$(CONFIG_VBOXSF_FS) += vboxsf/
+ obj-$(CONFIG_ZONEFS_FS) += zonefs/
++obj-$(CONFIG_AUFS_FS) += aufs/
+diff --git a/fs/aufs/Kconfig b/fs/aufs/Kconfig
+new file mode 100644
+index 00000000000000..a5008b87a55f1f
+--- /dev/null
++++ b/fs/aufs/Kconfig
+@@ -0,0 +1,199 @@
++# SPDX-License-Identifier: GPL-2.0
++config AUFS_FS
++ tristate "Aufs (Advanced multi layered unification filesystem) support"
++ help
++ Aufs is a stackable unification filesystem such as Unionfs,
++ which unifies several directories and provides a merged single
++ directory.
++ In the early days, aufs was entirely re-designed and
++ re-implemented Unionfs Version 1.x series. Introducing many
++ original ideas, approaches and improvements, it becomes totally
++ different from Unionfs while keeping the basic features.
+
-+2.
-+- module only (CONFIG_AUFS_FS=m).
-+- apply ./aufs6-base.patch to your kernel source files.
-+- apply ./aufs6-mmap.patch too.
-+- apply ./aufs6-standalone.patch too.
-+- build your kernel, don't forget "make headers_install", and reboot.
-+- edit ./config.mk and set other aufs configurations if necessary.
-+ Note: You should read $PWD/fs/aufs/Kconfig carefully which describes
-+ every aufs configurations.
-+- build the module by simple "make".
-+- you can specify ${KDIR} make variable which points to your kernel
-+ source tree.
-+- install the files
-+ + run "make install" to install the aufs module, or copy the built
-+ $PWD/aufs.ko to /lib/modules/... and run depmod -a (or reboot simply).
-+ + run "make install_headers" (instead of headers_install) to install
-+ the modified aufs header file (you can specify DESTDIR which is
-+ available in aufs standalone version's Makefile only), or copy
-+ $PWD/usr/include/linux/aufs_type.h to /usr/include/linux or wherever
-+ you like manually. By default, the target directory is $PWD/usr.
-+- no need to apply aufs6-kbuild.patch, nor copying source files to your
-+ kernel source tree.
++if AUFS_FS
++choice
++ prompt "Maximum number of branches"
++ default AUFS_BRANCH_MAX_127
++ help
++ Specifies the maximum number of branches (or member directories)
++ in a single aufs. The larger value consumes more system
++ resources and has a minor impact to performance.
++config AUFS_BRANCH_MAX_127
++ bool "127"
++ help
++ Specifies the maximum number of branches (or member directories)
++ in a single aufs. The larger value consumes more system
++ resources and has a minor impact to performance.
++config AUFS_BRANCH_MAX_511
++ bool "511"
++ help
++ Specifies the maximum number of branches (or member directories)
++ in a single aufs. The larger value consumes more system
++ resources and has a minor impact to performance.
++config AUFS_BRANCH_MAX_1023
++ bool "1023"
++ help
++ Specifies the maximum number of branches (or member directories)
++ in a single aufs. The larger value consumes more system
++ resources and has a minor impact to performance.
++config AUFS_BRANCH_MAX_32767
++ bool "32767"
++ help
++ Specifies the maximum number of branches (or member directories)
++ in a single aufs. The larger value consumes more system
++ resources and has a minor impact to performance.
++endchoice
+
-+Note: The header file aufs_type.h is necessary to build aufs-util
-+ as well as "make headers_install" in the kernel source tree.
-+ headers_install is subject to be forgotten, but it is essentially
-+ necessary, not only for building aufs-util.
-+ You may not meet problems without headers_install in some older
-+ version though.
++config AUFS_SBILIST
++ bool
++ depends on AUFS_MAGIC_SYSRQ || PROC_FS
++ default y
++ help
++ Automatic configuration for internal use.
++ When aufs supports Magic SysRq or /proc, enabled automatically.
+
-+And then,
-+- read README in aufs-util, build and install it
-+- note that your distribution may contain an obsoleted version of
-+ aufs_type.h in /usr/include/linux or something. When you build aufs
-+ utilities, make sure that your compiler refers the correct aufs header
-+ file which is built by "make headers_install."
-+- if you want to use readdir(3) in userspace or pathconf(3) wrapper,
-+ then run "make install_ulib" too. And refer to the aufs manual in
-+ detail.
++config AUFS_HNOTIFY
++ bool "Detect direct branch access (bypassing aufs)"
++ help
++ If you want to modify files on branches directly, eg. bypassing aufs,
++ and want aufs to detect the changes of them fully, then enable this
++ option and use 'udba=notify' mount option.
++ Currently there is only one available configuration, "fsnotify".
++ It will have a negative impact to the performance.
++ See detail in aufs.5.
+
-+There several other patches in aufs-standalone.git. They are all
-+optional. When you meet some problems, they will help you.
-+- aufs6-loopback.patch
-+ Supports a nested loopback mount in a branch-fs. This patch is
-+ unnecessary until aufs produces a message like "you may want to try
-+ another patch for loopback file".
-+- vfs-ino.patch
-+ Modifies a system global kernel internal function get_next_ino() in
-+ order to stop assigning 0 for an inode-number. Not directly related to
-+ aufs, but recommended generally.
-+- tmpfs-idr.patch
-+ Keeps the tmpfs inode number as the lowest value. Effective to reduce
-+ the size of aufs XINO files for tmpfs branch. Also it prevents the
-+ duplication of inode number, which is important for backup tools and
-+ other utilities. When you find aufs XINO files for tmpfs branch
-+ growing too much, try this patch.
-+- lockdep-debug.patch
-+ Similar to some kernel configurations for LOCKDEP (see the top of
-+ this section), you will need expand some constants in LOCKDEP for
-+ aufs if you enable CONFIG_LOCKDEP.
++choice
++ prompt "method" if AUFS_HNOTIFY
++ default AUFS_HFSNOTIFY
++config AUFS_HFSNOTIFY
++ bool "fsnotify"
++ select FSNOTIFY
++endchoice
+
++config AUFS_EXPORT
++ bool "NFS-exportable aufs"
++ depends on EXPORTFS
++ help
++ If you want to export your mounted aufs via NFS, then enable this
++ option. There are several requirements for this configuration.
++ See detail in aufs.5.
+
-+4. Usage
-+----------------------------------------
-+At first, make sure aufs-util are installed, and please read the aufs
-+manual, aufs.5 in aufs-util.git tree.
-+$ man -l aufs.5
++config AUFS_INO_T_64
++ bool
++ depends on AUFS_EXPORT
++ depends on 64BIT && !(ALPHA || S390)
++ default y
++ help
++ Automatic configuration for internal use.
++ /* typedef unsigned long/int __kernel_ino_t */
++ /* alpha and s390x are int */
+
-+And then,
-+$ mkdir /tmp/rw /tmp/aufs
-+# mount -t aufs -o br=/tmp/rw:${HOME} none /tmp/aufs
++config AUFS_XATTR
++ bool "support for XATTR/EA (including Security Labels)"
++ help
++ If your branch fs supports XATTR/EA and you want to make them
++ available in aufs too, then enable this opsion and specify the
++ branch attributes for EA.
++ See detail in aufs.5.
+
-+Here is another example. The result is equivalent.
-+# mount -t aufs -o br=/tmp/rw=rw:${HOME}=ro none /tmp/aufs
-+ Or
-+# mount -t aufs -o br:/tmp/rw none /tmp/aufs
-+# mount -o remount,append:${HOME} /tmp/aufs
++config AUFS_FHSM
++ bool "File-based Hierarchical Storage Management"
++ help
++ Hierarchical Storage Management (or HSM) is a well-known feature
++ in the storage world. Aufs provides this feature as file-based.
++ with multiple branches.
++ These multiple branches are prioritized, ie. the topmost one
++ should be the fastest drive and be used heavily.
+
-+Then, you can see whole tree of your home dir through /tmp/aufs. If
-+you modify a file under /tmp/aufs, the one on your home directory is
-+not affected, instead the same named file will be newly created under
-+/tmp/rw. And all of your modification to a file will be applied to
-+the one under /tmp/rw. This is called the file based Copy on Write
-+(COW) method.
-+Aufs mount options are described in aufs.5.
-+If you run chroot or something and make your aufs as a root directory,
-+then you need to customize the shutdown script. See the aufs manual in
-+detail.
++config AUFS_RDU
++ bool "Readdir in userspace"
++ help
++ Aufs has two methods to provide a merged view for a directory,
++ by a user-space library and by kernel-space natively. The latter
++ is always enabled but sometimes large and slow.
++ If you enable this option, install the library in aufs2-util
++ package, and set some environment variables for your readdir(3),
++ then the work will be handled in user-space which generally
++ shows better performance in most cases.
++ See detail in aufs.5.
+
-+Additionally, there are some sample usages of aufs which are a
-+diskless system with network booting, and LiveCD over NFS.
-+See sample dir in CVS tree on SourceForge.
++config AUFS_DIRREN
++ bool "Workaround for rename(2)-ing a directory"
++ help
++ By default, aufs returns EXDEV error in renameing a dir who has
++ his child on the lower branch, since it is a bad idea to issue
++ rename(2) internally for every lower branch. But user may not
++ accept this behaviour. So here is a workaround to allow such
++ rename(2) and store some extra information on the writable
++ branch. Obviously this costs high (and I don't like it).
++ To use this feature, you need to enable this configuration AND
++ to specify the mount option `dirren.'
++ See details in aufs.5 and the design documents.
+
++config AUFS_SHWH
++ bool "Show whiteouts"
++ help
++ If you want to make the whiteouts in aufs visible, then enable
++ this option and specify 'shwh' mount option. Although it may
++ sounds like philosophy or something, but in technically it
++ simply shows the name of whiteout with keeping its behaviour.
+
-+5. Contact
-+----------------------------------------
-+When you have any problems or strange behaviour in aufs, please let me
-+know with:
-+- /proc/mounts (instead of the output of mount(8))
-+- /sys/module/aufs/*
-+- /sys/fs/aufs/* (if you have them)
-+- /debug/aufs/* (if you have them)
-+- linux kernel version
-+ if your kernel is not plain, for example modified by distributor,
-+ the url where i can download its source is necessary too.
-+- aufs version which was printed at loading the module or booting the
-+ system, instead of the date you downloaded.
-+- configuration (define/undefine CONFIG_AUFS_xxx)
-+- kernel configuration or /proc/config.gz (if you have it)
-+- LSM (linux security module, if you are using)
-+- behaviour which you think to be incorrect
-+- actual operation, reproducible one is better
-+- mailto: aufs-users at lists.sourceforge.net
++config AUFS_BR_RAMFS
++ bool "Ramfs (initramfs/rootfs) as an aufs branch"
++ help
++ If you want to use ramfs as an aufs branch fs, then enable this
++ option. Generally tmpfs is recommended.
++ Aufs prohibited them to be a branch fs by default, because
++ initramfs becomes unusable after switch_root or something
++ generally. If you sets initramfs as an aufs branch and boot your
++ system by switch_root, you will meet a problem easily since the
++ files in initramfs may be inaccessible.
++ Unless you are going to use ramfs as an aufs branch fs without
++ switch_root or something, leave it N.
+
-+Usually, I don't watch the Public Areas(Bugs, Support Requests, Patches,
-+and Feature Requests) on SourceForge. Please join and write to
-+aufs-users ML.
++config AUFS_BR_FUSE
++ bool "Fuse fs as an aufs branch"
++ depends on FUSE_FS
++ select AUFS_POLL
++ help
++ If you want to use fuse-based userspace filesystem as an aufs
++ branch fs, then enable this option.
++ It implements the internal poll(2) operation which is
++ implemented by fuse only (curretnly).
+
++config AUFS_POLL
++ bool
++ help
++ Automatic configuration for internal use.
+
-+6. Acknowledgements
-+----------------------------------------
-+Thanks to everyone who have tried and are using aufs, whoever
-+have reported a bug or any feedback.
++config AUFS_BR_HFSPLUS
++ bool "Hfsplus as an aufs branch"
++ depends on HFSPLUS_FS
++ default y
++ help
++ If you want to use hfsplus fs as an aufs branch fs, then enable
++ this option. This option introduces a small overhead at
++ copying-up a file on hfsplus.
+
-+Especially donators:
-+Tomas Matejicek(slax.org) made a donation (much more than once).
-+ Since Apr 2010, Tomas M (the author of Slax and Linux Live
-+ scripts) is making "doubling" donations.
-+ Unfortunately I cannot list all of the donators, but I really
-+ appreciate.
-+ It ends Aug 2010, but the ordinary donation URL is still available.
-+ <http://sourceforge.net/donate/index.php?group_id=167503>
-+Dai Itasaka made a donation (2007/8).
-+Chuck Smith made a donation (2008/4, 10 and 12).
-+Henk Schoneveld made a donation (2008/9).
-+Chih-Wei Huang, ASUS, CTC donated Eee PC 4G (2008/10).
-+Francois Dupoux made a donation (2008/11).
-+Bruno Cesar Ribas and Luis Carlos Erpen de Bona, C3SL serves public
-+ aufs2 GIT tree (2009/2).
-+William Grant made a donation (2009/3).
-+Patrick Lane made a donation (2009/4).
-+The Mail Archive (mail-archive.com) made donations (2009/5).
-+Nippy Networks (Ed Wildgoose) made a donation (2009/7).
-+New Dream Network, LLC (www.dreamhost.com) made a donation (2009/11).
-+Pavel Pronskiy made a donation (2011/2).
-+Iridium and Inmarsat satellite phone retailer (www.mailasail.com), Nippy
-+ Networks (Ed Wildgoose) made a donation for hardware (2011/3).
-+Max Lekomcev (DOM-TV project) made a donation (2011/7, 12, 2012/3, 6 and
-+11).
-+Sam Liddicott made a donation (2011/9).
-+Era Scarecrow made a donation (2013/4).
-+Bor Ratajc made a donation (2013/4).
-+Alessandro Gorreta made a donation (2013/4).
-+POIRETTE Marc made a donation (2013/4).
-+Alessandro Gorreta made a donation (2013/4).
-+lauri kasvandik made a donation (2013/5).
-+"pemasu from Finland" made a donation (2013/7).
-+The Parted Magic Project made a donation (2013/9 and 11).
-+Pavel Barta made a donation (2013/10).
-+Nikolay Pertsev made a donation (2014/5).
-+James B made a donation (2014/7, 2015/7, and 2021/12).
-+Stefano Di Biase made a donation (2014/8).
-+Daniel Epellei made a donation (2015/1).
-+OmegaPhil made a donation (2016/1, 2018/4).
-+Tomasz Szewczyk made a donation (2016/4).
-+James Burry made a donation (2016/12).
-+Carsten Rose made a donation (2018/9).
-+Porteus Kiosk made a donation (2018/10).
-+huronOS team: Enya Quetzalli made donations (2022/5, 2023/5 and 8).
-+Vasily Mikhaylichenko made a donation (2023/5).
++config AUFS_BDEV_LOOP
++ bool
++ depends on BLK_DEV_LOOP
++ default y
++ help
++ Automatic configuration for internal use.
++ Convert =[ym] into =y.
+
-+Thank you very much.
-+Donations are always, including future donations, very important and
-+helpful for me to keep on developing aufs.
++config AUFS_DEBUG
++ bool "Debug aufs"
++ help
++ Enable this to compile aufs internal debug code.
++ It will have a negative impact to the performance.
+
++config AUFS_MAGIC_SYSRQ
++ bool
++ depends on AUFS_DEBUG && MAGIC_SYSRQ
++ default y
++ help
++ Automatic configuration for internal use.
++ When aufs supports Magic SysRq, enabled automatically.
++endif
+diff --git a/fs/aufs/Makefile b/fs/aufs/Makefile
+new file mode 100644
+index 00000000000000..4af8ecde3e3fad
+--- /dev/null
++++ b/fs/aufs/Makefile
+@@ -0,0 +1,46 @@
++# SPDX-License-Identifier: GPL-2.0
+
-+7.
-+----------------------------------------
-+If you are an experienced user, no explanation is needed. Aufs is
-+just a linux filesystem.
++include ${src}/magic.mk
++ifeq (${CONFIG_AUFS_FS},m)
++include ${src}/conf.mk
++endif
++-include ${src}/priv_def.mk
+
++# cf. include/linux/kernel.h
++# enable pr_debug
++ccflags-y += -DDEBUG
++# sparse requires the full pathname
++ifdef M
++ccflags-y += -include ${M}/../../include/uapi/linux/aufs_type.h
++else
++ccflags-y += -include ${srctree}/include/uapi/linux/aufs_type.h
++endif
+
-+Enjoy!
++obj-$(CONFIG_AUFS_FS) += aufs.o
++aufs-y := module.o sbinfo.o super.o branch.o xino.o sysaufs.o opts.o fsctx.o \
++ wkq.o vfsub.o dcsub.o \
++ cpup.o whout.o wbr_policy.o \
++ dinfo.o dentry.o \
++ dynop.o \
++ finfo.o file.o f_op.o \
++ dir.o vdir.o \
++ iinfo.o inode.o i_op.o i_op_add.o i_op_del.o i_op_ren.o \
++ mvdown.o ioctl.o
+
-+# Local variables: ;
-+# mode: text;
-+# End: ;
-diff -urN /usr/share/empty/fs/aufs/aufs.h linux/fs/aufs/aufs.h
---- /usr/share/empty/fs/aufs/aufs.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/aufs.h 2022-11-05 23:02:18.959222617 +0100
++# all are boolean
++aufs-$(CONFIG_PROC_FS) += procfs.o plink.o
++aufs-$(CONFIG_SYSFS) += sysfs.o
++aufs-$(CONFIG_DEBUG_FS) += dbgaufs.o
++aufs-$(CONFIG_AUFS_BDEV_LOOP) += loop.o
++aufs-$(CONFIG_AUFS_HNOTIFY) += hnotify.o
++aufs-$(CONFIG_AUFS_HFSNOTIFY) += hfsnotify.o
++aufs-$(CONFIG_AUFS_EXPORT) += export.o
++aufs-$(CONFIG_AUFS_XATTR) += xattr.o
++aufs-$(CONFIG_FS_POSIX_ACL) += posix_acl.o
++aufs-$(CONFIG_AUFS_DIRREN) += dirren.o
++aufs-$(CONFIG_AUFS_FHSM) += fhsm.o
++aufs-$(CONFIG_AUFS_POLL) += poll.o
++aufs-$(CONFIG_AUFS_RDU) += rdu.o
++aufs-$(CONFIG_AUFS_BR_HFSPLUS) += hfsplus.o
++aufs-$(CONFIG_AUFS_DEBUG) += debug.o
++aufs-$(CONFIG_AUFS_MAGIC_SYSRQ) += sysrq.o
+diff --git a/fs/aufs/aufs.h b/fs/aufs/aufs.h
+new file mode 100644
+index 00000000000000..20430cf7904263
+--- /dev/null
++++ b/fs/aufs/aufs.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_H__ */
-diff -urN /usr/share/empty/fs/aufs/branch.c linux/fs/aufs/branch.c
---- /usr/share/empty/fs/aufs/branch.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/branch.c 2022-11-05 23:02:18.959222617 +0100
+diff --git a/fs/aufs/branch.c b/fs/aufs/branch.c
+new file mode 100644
+index 00000000000000..2a85d744d2b5f7
+--- /dev/null
++++ b/fs/aufs/branch.c
@@ -0,0 +1,1427 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+
+ return err;
+}
-diff -urN /usr/share/empty/fs/aufs/branch.h linux/fs/aufs/branch.h
---- /usr/share/empty/fs/aufs/branch.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/branch.h 2023-10-31 09:31:04.196547417 +0100
+diff --git a/fs/aufs/branch.h b/fs/aufs/branch.h
+new file mode 100644
+index 00000000000000..6818ba8df8a24f
+--- /dev/null
++++ b/fs/aufs/branch.h
@@ -0,0 +1,375 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_BRANCH_H__ */
-diff -urN /usr/share/empty/fs/aufs/conf.mk linux/fs/aufs/conf.mk
---- /usr/share/empty/fs/aufs/conf.mk 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/conf.mk 2022-11-05 23:02:18.959222617 +0100
+diff --git a/fs/aufs/conf.mk b/fs/aufs/conf.mk
+new file mode 100644
+index 00000000000000..12782f8e0f3819
+--- /dev/null
++++ b/fs/aufs/conf.mk
@@ -0,0 +1,40 @@
+# SPDX-License-Identifier: GPL-2.0
+
+${obj}/sysfs.o: ${AuConfName}
+
+-include ${srctree}/${src}/conf_priv.mk
-diff -urN /usr/share/empty/fs/aufs/cpup.c linux/fs/aufs/cpup.c
---- /usr/share/empty/fs/aufs/cpup.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/cpup.c 2023-10-31 09:31:04.196547417 +0100
+diff --git a/fs/aufs/cpup.c b/fs/aufs/cpup.c
+new file mode 100644
+index 00000000000000..8c8bd5f7b28d81
+--- /dev/null
++++ b/fs/aufs/cpup.c
@@ -0,0 +1,1459 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ dput(parent);
+ return err;
+}
-diff -urN /usr/share/empty/fs/aufs/cpup.h linux/fs/aufs/cpup.h
---- /usr/share/empty/fs/aufs/cpup.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/cpup.h 2022-11-05 23:02:18.962555950 +0100
+diff --git a/fs/aufs/cpup.h b/fs/aufs/cpup.h
+new file mode 100644
+index 00000000000000..decd8f01425a05
+--- /dev/null
++++ b/fs/aufs/cpup.h
@@ -0,0 +1,100 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_CPUP_H__ */
-diff -urN /usr/share/empty/fs/aufs/dbgaufs.c linux/fs/aufs/dbgaufs.c
---- /usr/share/empty/fs/aufs/dbgaufs.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dbgaufs.c 2023-10-10 22:51:18.033248030 +0200
+diff --git a/fs/aufs/dbgaufs.c b/fs/aufs/dbgaufs.c
+new file mode 100644
+index 00000000000000..d5811df890b5f5
+--- /dev/null
++++ b/fs/aufs/dbgaufs.c
@@ -0,0 +1,526 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ err = 0;
+ return err;
+}
-diff -urN /usr/share/empty/fs/aufs/dbgaufs.h linux/fs/aufs/dbgaufs.h
---- /usr/share/empty/fs/aufs/dbgaufs.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dbgaufs.h 2022-11-05 23:02:18.962555950 +0100
+diff --git a/fs/aufs/dbgaufs.h b/fs/aufs/dbgaufs.h
+new file mode 100644
+index 00000000000000..30f1694224e004
+--- /dev/null
++++ b/fs/aufs/dbgaufs.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __DBGAUFS_H__ */
-diff -urN /usr/share/empty/fs/aufs/dcsub.c linux/fs/aufs/dcsub.c
---- /usr/share/empty/fs/aufs/dcsub.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dcsub.c 2022-11-05 23:02:18.962555950 +0100
+diff --git a/fs/aufs/dcsub.c b/fs/aufs/dcsub.c
+new file mode 100644
+index 00000000000000..fa2a9ad2b49b61
+--- /dev/null
++++ b/fs/aufs/dcsub.c
@@ -0,0 +1,225 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+
+ return path_is_under(path + 0, path + 1);
+}
-diff -urN /usr/share/empty/fs/aufs/dcsub.h linux/fs/aufs/dcsub.h
---- /usr/share/empty/fs/aufs/dcsub.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dcsub.h 2022-11-05 23:02:18.962555950 +0100
+diff --git a/fs/aufs/dcsub.h b/fs/aufs/dcsub.h
+new file mode 100644
+index 00000000000000..7e4f4eba0343b2
+--- /dev/null
++++ b/fs/aufs/dcsub.h
@@ -0,0 +1,137 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_DCSUB_H__ */
-diff -urN /usr/share/empty/fs/aufs/debug.c linux/fs/aufs/debug.c
---- /usr/share/empty/fs/aufs/debug.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/debug.c 2023-10-31 09:31:04.196547417 +0100
+diff --git a/fs/aufs/debug.c b/fs/aufs/debug.c
+new file mode 100644
+index 00000000000000..e503bb357984ec
+--- /dev/null
++++ b/fs/aufs/debug.c
@@ -0,0 +1,448 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+
+ return 0;
+}
-diff -urN /usr/share/empty/fs/aufs/debug.h linux/fs/aufs/debug.h
---- /usr/share/empty/fs/aufs/debug.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/debug.h 2022-11-05 23:02:18.962555950 +0100
+diff --git a/fs/aufs/debug.h b/fs/aufs/debug.h
+new file mode 100644
+index 00000000000000..f757588e5000ac
+--- /dev/null
++++ b/fs/aufs/debug.h
@@ -0,0 +1,226 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_DEBUG_H__ */
-diff -urN /usr/share/empty/fs/aufs/dentry.c linux/fs/aufs/dentry.c
---- /usr/share/empty/fs/aufs/dentry.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dentry.c 2023-10-31 09:31:04.196547417 +0100
+diff --git a/fs/aufs/dentry.c b/fs/aufs/dentry.c
+new file mode 100644
+index 00000000000000..ed7ce8f6d1a1bf
+--- /dev/null
++++ b/fs/aufs/dentry.c
@@ -0,0 +1,1168 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+const struct dentry_operations aufs_dop_noreval = {
+ .d_release = aufs_d_release
+};
-diff -urN /usr/share/empty/fs/aufs/dentry.h linux/fs/aufs/dentry.h
---- /usr/share/empty/fs/aufs/dentry.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dentry.h 2023-10-31 09:31:04.196547417 +0100
+diff --git a/fs/aufs/dentry.h b/fs/aufs/dentry.h
+new file mode 100644
+index 00000000000000..da4c9063d7e1c8
+--- /dev/null
++++ b/fs/aufs/dentry.h
@@ -0,0 +1,270 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_DENTRY_H__ */
-diff -urN /usr/share/empty/fs/aufs/dinfo.c linux/fs/aufs/dinfo.c
---- /usr/share/empty/fs/aufs/dinfo.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dinfo.c 2022-12-17 09:21:34.796521861 +0100
+diff --git a/fs/aufs/dinfo.c b/fs/aufs/dinfo.c
+new file mode 100644
+index 00000000000000..bf4a94414309dc
+--- /dev/null
++++ b/fs/aufs/dinfo.c
@@ -0,0 +1,555 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ return bindex;
+ return -1;
+}
-diff -urN /usr/share/empty/fs/aufs/dir.c linux/fs/aufs/dir.c
---- /usr/share/empty/fs/aufs/dir.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dir.c 2023-10-31 09:31:04.196547417 +0100
+diff --git a/fs/aufs/dir.c b/fs/aufs/dir.c
+new file mode 100644
+index 00000000000000..ee900ea3264b22
+--- /dev/null
++++ b/fs/aufs/dir.c
@@ -0,0 +1,765 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ .flush = aufs_flush_dir,
+ .fsync = aufs_fsync_dir
+};
-diff -urN /usr/share/empty/fs/aufs/dir.h linux/fs/aufs/dir.h
---- /usr/share/empty/fs/aufs/dir.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dir.h 2022-11-05 23:02:18.962555950 +0100
+diff --git a/fs/aufs/dir.h b/fs/aufs/dir.h
+new file mode 100644
+index 00000000000000..382342bd6ecff3
+--- /dev/null
++++ b/fs/aufs/dir.h
@@ -0,0 +1,134 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_DIR_H__ */
-diff -urN /usr/share/empty/fs/aufs/dirren.c linux/fs/aufs/dirren.c
---- /usr/share/empty/fs/aufs/dirren.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dirren.c 2023-10-10 22:51:18.033248030 +0200
+diff --git a/fs/aufs/dirren.c b/fs/aufs/dirren.c
+new file mode 100644
+index 00000000000000..2a6295ab6576b8
+--- /dev/null
++++ b/fs/aufs/dirren.c
@@ -0,0 +1,1315 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ return err;
+}
+
-+int au_dr_lkup_h_ino(struct au_do_lookup_args *lkup, aufs_bindex_t bindex,
-+ ino_t h_ino)
++int au_dr_lkup_h_ino(struct au_do_lookup_args *lkup, aufs_bindex_t bindex,
++ ino_t h_ino)
++{
++ int match;
++ struct au_drinfo *drinfo;
++
++ match = 1;
++ if (!lkup->dirren.drinfo)
++ goto out;
++ AuDebugOn(lkup->dirren.ninfo <= bindex);
++ drinfo = lkup->dirren.drinfo[bindex];
++ if (!drinfo)
++ goto out;
++
++ match = (drinfo->ino == h_ino);
++ AuDbg("match %d\n", match);
++
++out:
++ return match;
++}
++
++/* ---------------------------------------------------------------------- */
++
++int au_dr_opt_set(struct super_block *sb)
++{
++ int err;
++ aufs_bindex_t bindex, bbot;
++ struct au_branch *br;
++
++ err = 0;
++ bbot = au_sbbot(sb);
++ for (bindex = 0; !err && bindex <= bbot; bindex++) {
++ br = au_sbr(sb, bindex);
++ err = au_dr_hino(sb, bindex, /*br*/NULL, &br->br_path);
++ }
++
++ return err;
++}
++
++int au_dr_opt_flush(struct super_block *sb)
++{
++ int err;
++ aufs_bindex_t bindex, bbot;
++ struct au_branch *br;
++
++ err = 0;
++ bbot = au_sbbot(sb);
++ for (bindex = 0; !err && bindex <= bbot; bindex++) {
++ br = au_sbr(sb, bindex);
++ if (au_br_writable(br->br_perm))
++ err = au_dr_hino(sb, bindex, /*br*/NULL, /*path*/NULL);
++ }
++
++ return err;
++}
++
++int au_dr_opt_clr(struct super_block *sb, int no_flush)
++{
++ int err;
++ aufs_bindex_t bindex, bbot;
++ struct au_branch *br;
++
++ err = 0;
++ if (!no_flush) {
++ err = au_dr_opt_flush(sb);
++ if (unlikely(err))
++ goto out;
++ }
++
++ bbot = au_sbbot(sb);
++ for (bindex = 0; bindex <= bbot; bindex++) {
++ br = au_sbr(sb, bindex);
++ au_dr_hino_free(&br->br_dirren);
++ }
++
++out:
++ return err;
++}
+diff --git a/fs/aufs/dirren.h b/fs/aufs/dirren.h
+new file mode 100644
+index 00000000000000..d2d57d95a77ecc
+--- /dev/null
++++ b/fs/aufs/dirren.h
+@@ -0,0 +1,140 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * Copyright (C) 2017-2022 Junjiro R. Okajima
++ *
++ * This program 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/>.
++ */
++
++/*
++ * renamed dir info
++ */
++
++#ifndef __AUFS_DIRREN_H__
++#define __AUFS_DIRREN_H__
++
++#ifdef __KERNEL__
++
++#include <linux/dcache.h>
++#include <linux/statfs.h>
++#include <linux/uuid.h>
++#include "hbl.h"
++
++#define AuDirren_NHASH 100
++
++#ifdef CONFIG_AUFS_DIRREN
++enum au_brid_type {
++ AuBrid_Unset,
++ AuBrid_UUID,
++ AuBrid_FSID,
++ AuBrid_DEV
++};
++
++struct au_dr_brid {
++ enum au_brid_type type;
++ union {
++ uuid_t uuid; /* unimplemented yet */
++ fsid_t fsid;
++ dev_t dev;
++ };
++};
++
++/* 20 is the max digits length of ulong 64 */
++/* brid-type "_" uuid "_" inum */
++#define AUFS_DIRREN_FNAME_SZ (1 + 1 + UUID_STRING_LEN + 20)
++#define AUFS_DIRREN_ENV_VAL_SZ (AUFS_DIRREN_FNAME_SZ + 1 + 20)
++
++struct au_dr_hino {
++ struct hlist_bl_node dr_hnode;
++ ino_t dr_h_ino;
++};
++
++struct au_dr_br {
++ struct hlist_bl_head dr_h_ino[AuDirren_NHASH];
++ struct au_dr_brid dr_brid;
++};
++
++struct au_dr_lookup {
++ /* dr_name is pointed by struct au_do_lookup_args.name */
++ struct qstr dr_name; /* subset of dr_info */
++ aufs_bindex_t ninfo;
++ struct au_drinfo **drinfo;
++};
++#else
++struct au_dr_hino;
++/* empty */
++struct au_dr_br { };
++struct au_dr_lookup { };
++#endif
++
++/* ---------------------------------------------------------------------- */
++
++struct au_branch;
++struct au_do_lookup_args;
++struct au_hinode;
++#ifdef CONFIG_AUFS_DIRREN
++int au_dr_hino_test_add(struct au_dr_br *dr, ino_t h_ino,
++ struct au_dr_hino *add_ent);
++void au_dr_hino_free(struct au_dr_br *dr);
++int au_dr_br_init(struct super_block *sb, struct au_branch *br,
++ const struct path *path);
++int au_dr_br_fin(struct super_block *sb, struct au_branch *br);
++int au_dr_rename(struct dentry *src, aufs_bindex_t bindex,
++ struct qstr *dst_name, void *_rev);
++void au_dr_rename_fin(struct dentry *src, aufs_bindex_t btgt, void *rev);
++void au_dr_rename_rev(struct dentry *src, aufs_bindex_t bindex, void *rev);
++int au_dr_lkup(struct au_do_lookup_args *lkup, struct dentry *dentry,
++ aufs_bindex_t bindex);
++int au_dr_lkup_name(struct au_do_lookup_args *lkup, aufs_bindex_t btgt);
++int au_dr_lkup_h_ino(struct au_do_lookup_args *lkup, aufs_bindex_t bindex,
++ ino_t h_ino);
++void au_dr_lkup_fin(struct au_do_lookup_args *lkup);
++int au_dr_opt_set(struct super_block *sb);
++int au_dr_opt_flush(struct super_block *sb);
++int au_dr_opt_clr(struct super_block *sb, int no_flush);
++#else
++AuStubInt0(au_dr_hino_test_add, struct au_dr_br *dr, ino_t h_ino,
++ struct au_dr_hino *add_ent);
++AuStubVoid(au_dr_hino_free, struct au_dr_br *dr);
++AuStubInt0(au_dr_br_init, struct super_block *sb, struct au_branch *br,
++ const struct path *path);
++AuStubInt0(au_dr_br_fin, struct super_block *sb, struct au_branch *br);
++AuStubInt0(au_dr_rename, struct dentry *src, aufs_bindex_t bindex,
++ struct qstr *dst_name, void *_rev);
++AuStubVoid(au_dr_rename_fin, struct dentry *src, aufs_bindex_t btgt, void *rev);
++AuStubVoid(au_dr_rename_rev, struct dentry *src, aufs_bindex_t bindex,
++ void *rev);
++AuStubInt0(au_dr_lkup, struct au_do_lookup_args *lkup, struct dentry *dentry,
++ aufs_bindex_t bindex);
++AuStubInt0(au_dr_lkup_name, struct au_do_lookup_args *lkup, aufs_bindex_t btgt);
++AuStubInt0(au_dr_lkup_h_ino, struct au_do_lookup_args *lkup,
++ aufs_bindex_t bindex, ino_t h_ino);
++AuStubVoid(au_dr_lkup_fin, struct au_do_lookup_args *lkup);
++AuStubInt0(au_dr_opt_set, struct super_block *sb);
++AuStubInt0(au_dr_opt_flush, struct super_block *sb);
++AuStubInt0(au_dr_opt_clr, struct super_block *sb, int no_flush);
++#endif
++
++/* ---------------------------------------------------------------------- */
++
++#ifdef CONFIG_AUFS_DIRREN
++static inline int au_dr_ihash(ino_t h_ino)
++{
++ return h_ino % AuDirren_NHASH;
++}
++#else
++AuStubInt0(au_dr_ihash, ino_t h_ino);
++#endif
++
++#endif /* __KERNEL__ */
++#endif /* __AUFS_DIRREN_H__ */
+diff --git a/fs/aufs/dynop.c b/fs/aufs/dynop.c
+new file mode 100644
+index 00000000000000..54fd16ecb6d340
+--- /dev/null
++++ b/fs/aufs/dynop.c
+@@ -0,0 +1,366 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2010-2022 Junjiro R. Okajima
++ *
++ * This program 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/>.
++ */
++
++/*
++ * dynamically customizable operations for regular files
++ */
++
++#include "aufs.h"
++
++#define DyPrSym(key) AuDbgSym(key->dk_op.dy_hop)
++
++/*
++ * How large will these lists be?
++ * Usually just a few elements, 20-30 at most for each, I guess.
++ */
++static struct hlist_bl_head dynop[AuDyLast];
++
++static struct au_dykey *dy_gfind_get(struct hlist_bl_head *hbl,
++ const void *h_op)
++{
++ struct au_dykey *key, *tmp;
++ struct hlist_bl_node *pos;
++
++ key = NULL;
++ hlist_bl_lock(hbl);
++ hlist_bl_for_each_entry(tmp, pos, hbl, dk_hnode)
++ if (tmp->dk_op.dy_hop == h_op) {
++ if (kref_get_unless_zero(&tmp->dk_kref))
++ key = tmp;
++ break;
++ }
++ hlist_bl_unlock(hbl);
++
++ return key;
++}
++
++static struct au_dykey *dy_bradd(struct au_branch *br, struct au_dykey *key)
++{
++ struct au_dykey **k, *found;
++ const void *h_op = key->dk_op.dy_hop;
++ int i;
++
++ found = NULL;
++ k = br->br_dykey;
++ for (i = 0; i < AuBrDynOp; i++)
++ if (k[i]) {
++ if (k[i]->dk_op.dy_hop == h_op) {
++ found = k[i];
++ break;
++ }
++ } else
++ break;
++ if (!found) {
++ spin_lock(&br->br_dykey_lock);
++ for (; i < AuBrDynOp; i++)
++ if (k[i]) {
++ if (k[i]->dk_op.dy_hop == h_op) {
++ found = k[i];
++ break;
++ }
++ } else {
++ k[i] = key;
++ break;
++ }
++ spin_unlock(&br->br_dykey_lock);
++ BUG_ON(i == AuBrDynOp); /* expand the array */
++ }
++
++ return found;
++}
++
++/* kref_get() if @key is already added */
++static struct au_dykey *dy_gadd(struct hlist_bl_head *hbl, struct au_dykey *key)
++{
++ struct au_dykey *tmp, *found;
++ struct hlist_bl_node *pos;
++ const void *h_op = key->dk_op.dy_hop;
++
++ found = NULL;
++ hlist_bl_lock(hbl);
++ hlist_bl_for_each_entry(tmp, pos, hbl, dk_hnode)
++ if (tmp->dk_op.dy_hop == h_op) {
++ if (kref_get_unless_zero(&tmp->dk_kref))
++ found = tmp;
++ break;
++ }
++ if (!found)
++ hlist_bl_add_head(&key->dk_hnode, hbl);
++ hlist_bl_unlock(hbl);
++
++ if (!found)
++ DyPrSym(key);
++ return found;
++}
++
++static void dy_free_rcu(struct rcu_head *rcu)
++{
++ struct au_dykey *key;
++
++ key = container_of(rcu, struct au_dykey, dk_rcu);
++ DyPrSym(key);
++ kfree(key);
++}
++
++static void dy_free(struct kref *kref)
++{
++ struct au_dykey *key;
++ struct hlist_bl_head *hbl;
++
++ key = container_of(kref, struct au_dykey, dk_kref);
++ hbl = dynop + key->dk_op.dy_type;
++ au_hbl_del(&key->dk_hnode, hbl);
++ call_rcu(&key->dk_rcu, dy_free_rcu);
++}
++
++void au_dy_put(struct au_dykey *key)
++{
++ kref_put(&key->dk_kref, dy_free);
++}
++
++/* ---------------------------------------------------------------------- */
++
++#define DyDbgSize(cnt, op) AuDebugOn(cnt != sizeof(op)/sizeof(void *))
++
++#ifdef CONFIG_AUFS_DEBUG
++#define DyDbgDeclare(cnt) unsigned int cnt = 0
++#define DyDbgInc(cnt) do { cnt++; } while (0)
++#else
++#define DyDbgDeclare(cnt) do {} while (0)
++#define DyDbgInc(cnt) do {} while (0)
++#endif
++
++#define DySet(func, dst, src, h_op, h_sb) do { \
++ DyDbgInc(cnt); \
++ if (h_op->func) { \
++ if (src.func) \
++ dst.func = src.func; \
++ else \
++ AuDbg("%s %s\n", au_sbtype(h_sb), #func); \
++ } \
++} while (0)
++
++#define DySetForce(func, dst, src) do { \
++ AuDebugOn(!src.func); \
++ DyDbgInc(cnt); \
++ dst.func = src.func; \
++} while (0)
++
++#define DySetAop(func) \
++ DySet(func, dyaop->da_op, aufs_aop, h_aop, h_sb)
++#define DySetAopForce(func) \
++ DySetForce(func, dyaop->da_op, aufs_aop)
++
++static void dy_aop(struct au_dykey *key, const void *h_op,
++ struct super_block *h_sb __maybe_unused)
++{
++ struct au_dyaop *dyaop = (void *)key;
++ const struct address_space_operations *h_aop = h_op;
++ DyDbgDeclare(cnt);
++
++ AuDbg("%s\n", au_sbtype(h_sb));
++
++ DySetAop(writepage);
++ DySetAopForce(read_folio); /* force */
++ DySetAop(writepages);
++ DySetAop(dirty_folio);
++ DySetAop(invalidate_folio);
++ DySetAop(readahead);
++ DySetAop(write_begin);
++ DySetAop(write_end);
++ DySetAop(bmap);
++ DySetAop(release_folio);
++ DySetAop(free_folio);
++ /* this one will be changed according to an aufs mount option */
++ DySetAop(direct_IO);
++ DySetAop(migrate_folio);
++ DySetAop(launder_folio);
++ DySetAop(is_partially_uptodate);
++ DySetAop(is_dirty_writeback);
++ DySetAop(error_remove_page);
++ DySetAop(swap_activate);
++ DySetAop(swap_deactivate);
++ DySetAop(swap_rw);
++
++ DyDbgSize(cnt, *h_aop);
++}
++
++/* ---------------------------------------------------------------------- */
++
++static void dy_bug(struct kref *kref)
++{
++ BUG();
++}
++
++static struct au_dykey *dy_get(struct au_dynop *op, struct au_branch *br)
++{
++ struct au_dykey *key, *old;
++ struct hlist_bl_head *hbl;
++ struct op {
++ unsigned int sz;
++ void (*set)(struct au_dykey *key, const void *h_op,
++ struct super_block *h_sb __maybe_unused);
++ };
++ static const struct op a[] = {
++ [AuDy_AOP] = {
++ .sz = sizeof(struct au_dyaop),
++ .set = dy_aop
++ }
++ };
++ const struct op *p;
++
++ hbl = dynop + op->dy_type;
++ key = dy_gfind_get(hbl, op->dy_hop);
++ if (key)
++ goto out_add; /* success */
++
++ p = a + op->dy_type;
++ key = kzalloc(p->sz, GFP_NOFS);
++ if (unlikely(!key)) {
++ key = ERR_PTR(-ENOMEM);
++ goto out;
++ }
++
++ key->dk_op.dy_hop = op->dy_hop;
++ kref_init(&key->dk_kref);
++ p->set(key, op->dy_hop, au_br_sb(br));
++ old = dy_gadd(hbl, key);
++ if (old) {
++ au_kfree_rcu(key);
++ key = old;
++ }
++
++out_add:
++ old = dy_bradd(br, key);
++ if (old)
++ /* its ref-count should never be zero here */
++ kref_put(&key->dk_kref, dy_bug);
++out:
++ return key;
++}
++
++/* ---------------------------------------------------------------------- */
++/*
++ * Aufs prohibits O_DIRECT by default even if the branch supports it.
++ * This behaviour is necessary to return an error from open(O_DIRECT) instead
++ * of the succeeding I/O. The dio mount option enables O_DIRECT and makes
++ * open(O_DIRECT) always succeed, but the succeeding I/O may return an error.
++ * See the aufs manual in detail.
++ */
++static void dy_adx(struct au_dyaop *dyaop, int do_dx)
++{
++ if (!do_dx)
++ dyaop->da_op.direct_IO = NULL;
++ else
++ dyaop->da_op.direct_IO = aufs_aop.direct_IO;
++}
++
++static struct au_dyaop *dy_aget(struct au_branch *br,
++ const struct address_space_operations *h_aop,
++ int do_dx)
+{
-+ int match;
-+ struct au_drinfo *drinfo;
++ struct au_dyaop *dyaop;
++ struct au_dynop op;
+
-+ match = 1;
-+ if (!lkup->dirren.drinfo)
-+ goto out;
-+ AuDebugOn(lkup->dirren.ninfo <= bindex);
-+ drinfo = lkup->dirren.drinfo[bindex];
-+ if (!drinfo)
++ op.dy_type = AuDy_AOP;
++ op.dy_haop = h_aop;
++ dyaop = (void *)dy_get(&op, br);
++ if (IS_ERR(dyaop))
+ goto out;
-+
-+ match = (drinfo->ino == h_ino);
-+ AuDbg("match %d\n", match);
++ dy_adx(dyaop, do_dx);
+
+out:
-+ return match;
++ return dyaop;
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+int au_dr_opt_set(struct super_block *sb)
++int au_dy_iaop(struct inode *inode, aufs_bindex_t bindex,
++ struct inode *h_inode)
+{
-+ int err;
-+ aufs_bindex_t bindex, bbot;
++ int err, do_dx;
++ struct super_block *sb;
+ struct au_branch *br;
++ struct au_dyaop *dyaop;
++
++ AuDebugOn(!S_ISREG(h_inode->i_mode));
++ IiMustWriteLock(inode);
++
++ sb = inode->i_sb;
++ br = au_sbr(sb, bindex);
++ do_dx = !!au_opt_test(au_mntflags(sb), DIO);
++ dyaop = dy_aget(br, h_inode->i_mapping->a_ops, do_dx);
++ err = PTR_ERR(dyaop);
++ if (IS_ERR(dyaop))
++ /* unnecessary to call dy_fput() */
++ goto out;
+
+ err = 0;
-+ bbot = au_sbbot(sb);
-+ for (bindex = 0; !err && bindex <= bbot; bindex++) {
-+ br = au_sbr(sb, bindex);
-+ err = au_dr_hino(sb, bindex, /*br*/NULL, &br->br_path);
-+ }
++ inode->i_mapping->a_ops = &dyaop->da_op;
+
++out:
+ return err;
+}
+
-+int au_dr_opt_flush(struct super_block *sb)
++/*
++ * Is it safe to replace a_ops during the inode/file is in operation?
++ * Yes, I hope so.
++ */
++int au_dy_irefresh(struct inode *inode)
+{
+ int err;
-+ aufs_bindex_t bindex, bbot;
-+ struct au_branch *br;
++ aufs_bindex_t btop;
++ struct inode *h_inode;
+
+ err = 0;
-+ bbot = au_sbbot(sb);
-+ for (bindex = 0; !err && bindex <= bbot; bindex++) {
-+ br = au_sbr(sb, bindex);
-+ if (au_br_writable(br->br_perm))
-+ err = au_dr_hino(sb, bindex, /*br*/NULL, /*path*/NULL);
++ if (S_ISREG(inode->i_mode)) {
++ btop = au_ibtop(inode);
++ h_inode = au_h_iptr(inode, btop);
++ err = au_dy_iaop(inode, btop, h_inode);
+ }
-+
+ return err;
+}
+
-+int au_dr_opt_clr(struct super_block *sb, int no_flush)
++void au_dy_arefresh(int do_dx)
+{
-+ int err;
-+ aufs_bindex_t bindex, bbot;
-+ struct au_branch *br;
++ struct hlist_bl_head *hbl;
++ struct hlist_bl_node *pos;
++ struct au_dykey *key;
+
-+ err = 0;
-+ if (!no_flush) {
-+ err = au_dr_opt_flush(sb);
-+ if (unlikely(err))
-+ goto out;
-+ }
++ hbl = dynop + AuDy_AOP;
++ hlist_bl_lock(hbl);
++ hlist_bl_for_each_entry(key, pos, hbl, dk_hnode)
++ dy_adx((void *)key, do_dx);
++ hlist_bl_unlock(hbl);
++}
+
-+ bbot = au_sbbot(sb);
-+ for (bindex = 0; bindex <= bbot; bindex++) {
-+ br = au_sbr(sb, bindex);
-+ au_dr_hino_free(&br->br_dirren);
-+ }
++/* ---------------------------------------------------------------------- */
+
-+out:
-+ return err;
++void __init au_dy_init(void)
++{
++ int i;
++
++ for (i = 0; i < AuDyLast; i++)
++ INIT_HLIST_BL_HEAD(dynop + i);
+}
-diff -urN /usr/share/empty/fs/aufs/dirren.h linux/fs/aufs/dirren.h
---- /usr/share/empty/fs/aufs/dirren.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dirren.h 2022-11-05 23:02:18.962555950 +0100
-@@ -0,0 +1,140 @@
++
++void au_dy_fin(void)
++{
++ int i;
++
++ for (i = 0; i < AuDyLast; i++)
++ WARN_ON(!hlist_bl_empty(dynop + i));
++}
+diff --git a/fs/aufs/dynop.h b/fs/aufs/dynop.h
+new file mode 100644
+index 00000000000000..60d89364b67600
+--- /dev/null
++++ b/fs/aufs/dynop.h
+@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
-+ * Copyright (C) 2017-2022 Junjiro R. Okajima
++ * Copyright (C) 2010-2022 Junjiro R. Okajima
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ */
+
+/*
-+ * renamed dir info
++ * dynamically customizable operations (for regular files only)
+ */
+
-+#ifndef __AUFS_DIRREN_H__
-+#define __AUFS_DIRREN_H__
++#ifndef __AUFS_DYNOP_H__
++#define __AUFS_DYNOP_H__
+
+#ifdef __KERNEL__
+
-+#include <linux/dcache.h>
-+#include <linux/statfs.h>
-+#include <linux/uuid.h>
-+#include "hbl.h"
-+
-+#define AuDirren_NHASH 100
++#include <linux/fs.h>
++#include <linux/kref.h>
+
-+#ifdef CONFIG_AUFS_DIRREN
-+enum au_brid_type {
-+ AuBrid_Unset,
-+ AuBrid_UUID,
-+ AuBrid_FSID,
-+ AuBrid_DEV
-+};
++enum {AuDy_AOP, AuDyLast};
+
-+struct au_dr_brid {
-+ enum au_brid_type type;
++struct au_dynop {
++ int dy_type;
+ union {
-+ uuid_t uuid; /* unimplemented yet */
-+ fsid_t fsid;
-+ dev_t dev;
++ const void *dy_hop;
++ const struct address_space_operations *dy_haop;
+ };
+};
+
-+/* 20 is the max digits length of ulong 64 */
-+/* brid-type "_" uuid "_" inum */
-+#define AUFS_DIRREN_FNAME_SZ (1 + 1 + UUID_STRING_LEN + 20)
-+#define AUFS_DIRREN_ENV_VAL_SZ (AUFS_DIRREN_FNAME_SZ + 1 + 20)
++struct au_dykey {
++ union {
++ struct hlist_bl_node dk_hnode;
++ struct rcu_head dk_rcu;
++ };
++ struct au_dynop dk_op;
+
-+struct au_dr_hino {
-+ struct hlist_bl_node dr_hnode;
-+ ino_t dr_h_ino;
++ /*
++ * during I am in the branch local array, kref is gotten. when the
++ * branch is removed, kref is put.
++ */
++ struct kref dk_kref;
+};
+
-+struct au_dr_br {
-+ struct hlist_bl_head dr_h_ino[AuDirren_NHASH];
-+ struct au_dr_brid dr_brid;
++/* stop unioning since their sizes are very different from each other */
++struct au_dyaop {
++ struct au_dykey da_key;
++ struct address_space_operations da_op; /* not const */
+};
++/* make sure that 'struct au_dykey *' can be any type */
++static_assert(!offsetof(struct au_dyaop, da_key));
+
-+struct au_dr_lookup {
-+ /* dr_name is pointed by struct au_do_lookup_args.name */
-+ struct qstr dr_name; /* subset of dr_info */
-+ aufs_bindex_t ninfo;
-+ struct au_drinfo **drinfo;
-+};
++/* ---------------------------------------------------------------------- */
++
++/* dynop.c */
++struct au_branch;
++void au_dy_put(struct au_dykey *key);
++int au_dy_iaop(struct inode *inode, aufs_bindex_t bindex,
++ struct inode *h_inode);
++int au_dy_irefresh(struct inode *inode);
++void au_dy_arefresh(int do_dio);
++
++void __init au_dy_init(void);
++void au_dy_fin(void);
++
++#endif /* __KERNEL__ */
++#endif /* __AUFS_DYNOP_H__ */
+diff --git a/fs/aufs/export.c b/fs/aufs/export.c
+new file mode 100644
+index 00000000000000..4c639e5d40f6bf
+--- /dev/null
++++ b/fs/aufs/export.c
+@@ -0,0 +1,830 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2005-2022 Junjiro R. Okajima
++ *
++ * This program 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/>.
++ */
++
++/*
++ * export via nfs
++ */
++
++#include <linux/exportfs.h>
++#include <linux/fs_struct.h>
++#include <linux/nsproxy.h>
++#include <linux/random.h>
++#include <linux/writeback.h>
++#include "aufs.h"
++
++union conv {
++#ifdef CONFIG_AUFS_INO_T_64
++ __u32 a[2];
+#else
-+struct au_dr_hino;
-+/* empty */
-+struct au_dr_br { };
-+struct au_dr_lookup { };
++ __u32 a[1];
+#endif
++ ino_t ino;
++};
+
-+/* ---------------------------------------------------------------------- */
++static ino_t decode_ino(__u32 *a)
++{
++ union conv u;
+
-+struct au_branch;
-+struct au_do_lookup_args;
-+struct au_hinode;
-+#ifdef CONFIG_AUFS_DIRREN
-+int au_dr_hino_test_add(struct au_dr_br *dr, ino_t h_ino,
-+ struct au_dr_hino *add_ent);
-+void au_dr_hino_free(struct au_dr_br *dr);
-+int au_dr_br_init(struct super_block *sb, struct au_branch *br,
-+ const struct path *path);
-+int au_dr_br_fin(struct super_block *sb, struct au_branch *br);
-+int au_dr_rename(struct dentry *src, aufs_bindex_t bindex,
-+ struct qstr *dst_name, void *_rev);
-+void au_dr_rename_fin(struct dentry *src, aufs_bindex_t btgt, void *rev);
-+void au_dr_rename_rev(struct dentry *src, aufs_bindex_t bindex, void *rev);
-+int au_dr_lkup(struct au_do_lookup_args *lkup, struct dentry *dentry,
-+ aufs_bindex_t bindex);
-+int au_dr_lkup_name(struct au_do_lookup_args *lkup, aufs_bindex_t btgt);
-+int au_dr_lkup_h_ino(struct au_do_lookup_args *lkup, aufs_bindex_t bindex,
-+ ino_t h_ino);
-+void au_dr_lkup_fin(struct au_do_lookup_args *lkup);
-+int au_dr_opt_set(struct super_block *sb);
-+int au_dr_opt_flush(struct super_block *sb);
-+int au_dr_opt_clr(struct super_block *sb, int no_flush);
++ BUILD_BUG_ON(sizeof(u.ino) != sizeof(u.a));
++ u.a[0] = a[0];
++#ifdef CONFIG_AUFS_INO_T_64
++ u.a[1] = a[1];
++#endif
++ return u.ino;
++}
++
++static void encode_ino(__u32 *a, ino_t ino)
++{
++ union conv u;
++
++ u.ino = ino;
++ a[0] = u.a[0];
++#ifdef CONFIG_AUFS_INO_T_64
++ a[1] = u.a[1];
++#endif
++}
++
++/* NFS file handle */
++enum {
++ Fh_br_id,
++ Fh_sigen,
++#ifdef CONFIG_AUFS_INO_T_64
++ /* support 64bit inode number */
++ Fh_ino1,
++ Fh_ino2,
++ Fh_dir_ino1,
++ Fh_dir_ino2,
+#else
-+AuStubInt0(au_dr_hino_test_add, struct au_dr_br *dr, ino_t h_ino,
-+ struct au_dr_hino *add_ent);
-+AuStubVoid(au_dr_hino_free, struct au_dr_br *dr);
-+AuStubInt0(au_dr_br_init, struct super_block *sb, struct au_branch *br,
-+ const struct path *path);
-+AuStubInt0(au_dr_br_fin, struct super_block *sb, struct au_branch *br);
-+AuStubInt0(au_dr_rename, struct dentry *src, aufs_bindex_t bindex,
-+ struct qstr *dst_name, void *_rev);
-+AuStubVoid(au_dr_rename_fin, struct dentry *src, aufs_bindex_t btgt, void *rev);
-+AuStubVoid(au_dr_rename_rev, struct dentry *src, aufs_bindex_t bindex,
-+ void *rev);
-+AuStubInt0(au_dr_lkup, struct au_do_lookup_args *lkup, struct dentry *dentry,
-+ aufs_bindex_t bindex);
-+AuStubInt0(au_dr_lkup_name, struct au_do_lookup_args *lkup, aufs_bindex_t btgt);
-+AuStubInt0(au_dr_lkup_h_ino, struct au_do_lookup_args *lkup,
-+ aufs_bindex_t bindex, ino_t h_ino);
-+AuStubVoid(au_dr_lkup_fin, struct au_do_lookup_args *lkup);
-+AuStubInt0(au_dr_opt_set, struct super_block *sb);
-+AuStubInt0(au_dr_opt_flush, struct super_block *sb);
-+AuStubInt0(au_dr_opt_clr, struct super_block *sb, int no_flush);
++ Fh_ino1,
++ Fh_dir_ino1,
+#endif
++ Fh_igen,
++ Fh_h_type,
++ Fh_tail,
++
++ Fh_ino = Fh_ino1,
++ Fh_dir_ino = Fh_dir_ino1
++};
++
++static int au_test_anon(struct dentry *dentry)
++{
++ /* note: read d_flags without d_lock */
++ return !!(dentry->d_flags & DCACHE_DISCONNECTED);
++}
++
++int au_test_nfsd(void)
++{
++ int ret;
++ struct task_struct *tsk = current;
++ char comm[sizeof(tsk->comm)];
++
++ ret = 0;
++ if (tsk->flags & PF_KTHREAD) {
++ get_task_comm(comm, tsk);
++ ret = !strcmp(comm, "nfsd");
++ }
++
++ return ret;
++}
++
++/* ---------------------------------------------------------------------- */
++/* inode generation external table */
++
++void au_xigen_inc(struct inode *inode)
++{
++ loff_t pos;
++ ssize_t sz;
++ __u32 igen;
++ struct super_block *sb;
++ struct au_sbinfo *sbinfo;
++
++ sb = inode->i_sb;
++ AuDebugOn(!au_opt_test(au_mntflags(sb), XINO));
++
++ sbinfo = au_sbi(sb);
++ pos = inode->i_ino;
++ pos *= sizeof(igen);
++ igen = inode->i_generation + 1;
++ sz = xino_fwrite(sbinfo->si_xigen, &igen, sizeof(igen), &pos);
++ if (sz == sizeof(igen))
++ return; /* success */
++
++ if (unlikely(sz >= 0))
++ AuIOErr("xigen error (%zd)\n", sz);
++}
++
++int au_xigen_new(struct inode *inode)
++{
++ int err;
++ loff_t pos;
++ ssize_t sz;
++ struct super_block *sb;
++ struct au_sbinfo *sbinfo;
++ struct file *file;
++
++ err = 0;
++ /* todo: dirty, at mount time */
++ if (inode->i_ino == AUFS_ROOT_INO)
++ goto out;
++ sb = inode->i_sb;
++ SiMustAnyLock(sb);
++ if (unlikely(!au_opt_test(au_mntflags(sb), XINO)))
++ goto out;
++
++ err = -EFBIG;
++ pos = inode->i_ino;
++ if (unlikely(au_loff_max / sizeof(inode->i_generation) - 1 < pos)) {
++ AuIOErr1("too large i%lld\n", pos);
++ goto out;
++ }
++ pos *= sizeof(inode->i_generation);
++
++ err = 0;
++ sbinfo = au_sbi(sb);
++ file = sbinfo->si_xigen;
++ BUG_ON(!file);
++
++ if (vfsub_f_size_read(file)
++ < pos + sizeof(inode->i_generation)) {
++ inode->i_generation = atomic_inc_return(&sbinfo->si_xigen_next);
++ sz = xino_fwrite(file, &inode->i_generation,
++ sizeof(inode->i_generation), &pos);
++ } else
++ sz = xino_fread(file, &inode->i_generation,
++ sizeof(inode->i_generation), &pos);
++ if (sz == sizeof(inode->i_generation))
++ goto out; /* success */
++
++ err = sz;
++ if (unlikely(sz >= 0)) {
++ err = -EIO;
++ AuIOErr("xigen error (%zd)\n", sz);
++ }
++
++out:
++ return err;
++}
++
++int au_xigen_set(struct super_block *sb, struct path *path)
++{
++ int err;
++ struct au_sbinfo *sbinfo;
++ struct file *file;
++
++ SiMustWriteLock(sb);
++
++ sbinfo = au_sbi(sb);
++ file = au_xino_create2(sb, path, sbinfo->si_xigen);
++ err = PTR_ERR(file);
++ if (IS_ERR(file))
++ goto out;
++ err = 0;
++ if (sbinfo->si_xigen)
++ fput(sbinfo->si_xigen);
++ sbinfo->si_xigen = file;
++
++out:
++ AuTraceErr(err);
++ return err;
++}
++
++void au_xigen_clr(struct super_block *sb)
++{
++ struct au_sbinfo *sbinfo;
++
++ SiMustWriteLock(sb);
++
++ sbinfo = au_sbi(sb);
++ if (sbinfo->si_xigen) {
++ fput(sbinfo->si_xigen);
++ sbinfo->si_xigen = NULL;
++ }
++}
++
++/* ---------------------------------------------------------------------- */
++
++static struct dentry *decode_by_ino(struct super_block *sb, ino_t ino,
++ ino_t dir_ino)
++{
++ struct dentry *dentry, *d;
++ struct inode *inode;
++ unsigned int sigen;
++
++ dentry = NULL;
++ inode = ilookup(sb, ino);
++ if (!inode)
++ goto out;
++
++ dentry = ERR_PTR(-ESTALE);
++ sigen = au_sigen(sb);
++ if (unlikely(au_is_bad_inode(inode)
++ || IS_DEADDIR(inode)
++ || sigen != au_iigen(inode, NULL)))
++ goto out_iput;
++
++ dentry = NULL;
++ if (!dir_ino || S_ISDIR(inode->i_mode))
++ dentry = d_find_alias(inode);
++ else {
++ spin_lock(&inode->i_lock);
++ hlist_for_each_entry(d, &inode->i_dentry, d_u.d_alias) {
++ spin_lock(&d->d_lock);
++ if (!au_test_anon(d)
++ && d_inode(d->d_parent)->i_ino == dir_ino) {
++ dentry = dget_dlock(d);
++ spin_unlock(&d->d_lock);
++ break;
++ }
++ spin_unlock(&d->d_lock);
++ }
++ spin_unlock(&inode->i_lock);
++ }
++ if (unlikely(dentry && au_digen_test(dentry, sigen))) {
++ /* need to refresh */
++ dput(dentry);
++ dentry = NULL;
++ }
++
++out_iput:
++ iput(inode);
++out:
++ AuTraceErrPtr(dentry);
++ return dentry;
++}
+
+/* ---------------------------------------------------------------------- */
+
-+#ifdef CONFIG_AUFS_DIRREN
-+static inline int au_dr_ihash(ino_t h_ino)
++/* todo: dirty? */
++/* if exportfs_decode_fh() passed vfsmount*, we could be happy */
++
++struct au_compare_mnt_args {
++ /* input */
++ struct super_block *sb;
++
++ /* output */
++ struct vfsmount *mnt;
++};
++
++static int au_compare_mnt(struct vfsmount *mnt, void *arg)
+{
-+ return h_ino % AuDirren_NHASH;
++ struct au_compare_mnt_args *a = arg;
++
++ if (mnt->mnt_sb != a->sb)
++ return 0;
++ a->mnt = mntget(mnt);
++ return 1;
+}
-+#else
-+AuStubInt0(au_dr_ihash, ino_t h_ino);
-+#endif
+
-+#endif /* __KERNEL__ */
-+#endif /* __AUFS_DIRREN_H__ */
-diff -urN /usr/share/empty/fs/aufs/dynop.c linux/fs/aufs/dynop.c
---- /usr/share/empty/fs/aufs/dynop.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dynop.c 2022-11-05 23:02:18.962555950 +0100
-@@ -0,0 +1,366 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2010-2022 Junjiro R. Okajima
-+ *
-+ * This program 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/>.
-+ */
++static struct vfsmount *au_mnt_get(struct super_block *sb)
++{
++ int err;
++ struct path root;
++ struct au_compare_mnt_args args = {
++ .sb = sb
++ };
+
-+/*
-+ * dynamically customizable operations for regular files
-+ */
++ get_fs_root(current->fs, &root);
++ rcu_read_lock();
++ err = iterate_mounts(au_compare_mnt, &args, root.mnt);
++ rcu_read_unlock();
++ path_put(&root);
++ AuDebugOn(!err);
++ AuDebugOn(!args.mnt);
++ return args.mnt;
++}
+
-+#include "aufs.h"
++struct au_nfsd_si_lock {
++ unsigned int sigen;
++ aufs_bindex_t bindex, br_id;
++ unsigned char force_lock;
++};
+
-+#define DyPrSym(key) AuDbgSym(key->dk_op.dy_hop)
++static int si_nfsd_read_lock(struct super_block *sb,
++ struct au_nfsd_si_lock *nsi_lock)
++{
++ int err;
++ aufs_bindex_t bindex;
+
-+/*
-+ * How large will these lists be?
-+ * Usually just a few elements, 20-30 at most for each, I guess.
-+ */
-+static struct hlist_bl_head dynop[AuDyLast];
++ si_read_lock(sb, AuLock_FLUSH);
+
-+static struct au_dykey *dy_gfind_get(struct hlist_bl_head *hbl,
-+ const void *h_op)
-+{
-+ struct au_dykey *key, *tmp;
-+ struct hlist_bl_node *pos;
++ /* branch id may be wrapped around */
++ err = 0;
++ bindex = au_br_index(sb, nsi_lock->br_id);
++ if (bindex >= 0 && nsi_lock->sigen + AUFS_BRANCH_MAX > au_sigen(sb))
++ goto out; /* success */
+
-+ key = NULL;
-+ hlist_bl_lock(hbl);
-+ hlist_bl_for_each_entry(tmp, pos, hbl, dk_hnode)
-+ if (tmp->dk_op.dy_hop == h_op) {
-+ if (kref_get_unless_zero(&tmp->dk_kref))
-+ key = tmp;
-+ break;
-+ }
-+ hlist_bl_unlock(hbl);
++ err = -ESTALE;
++ bindex = -1;
++ if (!nsi_lock->force_lock)
++ si_read_unlock(sb);
+
-+ return key;
++out:
++ nsi_lock->bindex = bindex;
++ return err;
+}
+
-+static struct au_dykey *dy_bradd(struct au_branch *br, struct au_dykey *key)
++struct find_name_by_ino {
++ struct dir_context ctx;
++ int called, found;
++ ino_t ino;
++ char *name;
++ int namelen;
++};
++
++static bool
++find_name_by_ino(struct dir_context *ctx, const char *name, int namelen,
++ loff_t offset, u64 ino, unsigned int d_type)
+{
-+ struct au_dykey **k, *found;
-+ const void *h_op = key->dk_op.dy_hop;
-+ int i;
++ struct find_name_by_ino *a = container_of(ctx, struct find_name_by_ino,
++ ctx);
+
-+ found = NULL;
-+ k = br->br_dykey;
-+ for (i = 0; i < AuBrDynOp; i++)
-+ if (k[i]) {
-+ if (k[i]->dk_op.dy_hop == h_op) {
-+ found = k[i];
-+ break;
-+ }
-+ } else
-+ break;
-+ if (!found) {
-+ spin_lock(&br->br_dykey_lock);
-+ for (; i < AuBrDynOp; i++)
-+ if (k[i]) {
-+ if (k[i]->dk_op.dy_hop == h_op) {
-+ found = k[i];
-+ break;
-+ }
-+ } else {
-+ k[i] = key;
-+ break;
-+ }
-+ spin_unlock(&br->br_dykey_lock);
-+ BUG_ON(i == AuBrDynOp); /* expand the array */
-+ }
++ a->called++;
++ if (a->ino != ino)
++ return true;
+
-+ return found;
++ memcpy(a->name, name, namelen);
++ a->namelen = namelen;
++ a->found = 1;
++ return false;
+}
+
-+/* kref_get() if @key is already added */
-+static struct au_dykey *dy_gadd(struct hlist_bl_head *hbl, struct au_dykey *key)
++static struct dentry *au_lkup_by_ino(struct path *path, ino_t ino,
++ struct au_nfsd_si_lock *nsi_lock)
+{
-+ struct au_dykey *tmp, *found;
-+ struct hlist_bl_node *pos;
-+ const void *h_op = key->dk_op.dy_hop;
-+
-+ found = NULL;
-+ hlist_bl_lock(hbl);
-+ hlist_bl_for_each_entry(tmp, pos, hbl, dk_hnode)
-+ if (tmp->dk_op.dy_hop == h_op) {
-+ if (kref_get_unless_zero(&tmp->dk_kref))
-+ found = tmp;
-+ break;
++ struct dentry *dentry, *parent;
++ struct file *file;
++ struct inode *dir;
++ struct find_name_by_ino arg = {
++ .ctx = {
++ .actor = find_name_by_ino
+ }
-+ if (!found)
-+ hlist_bl_add_head(&key->dk_hnode, hbl);
-+ hlist_bl_unlock(hbl);
++ };
++ int err;
+
-+ if (!found)
-+ DyPrSym(key);
-+ return found;
-+}
++ parent = path->dentry;
++ if (nsi_lock)
++ si_read_unlock(parent->d_sb);
++ file = vfsub_dentry_open(path, au_dir_roflags);
++ dentry = (void *)file;
++ if (IS_ERR(file))
++ goto out;
+
-+static void dy_free_rcu(struct rcu_head *rcu)
-+{
-+ struct au_dykey *key;
++ dentry = ERR_PTR(-ENOMEM);
++ arg.name = (void *)__get_free_page(GFP_NOFS);
++ if (unlikely(!arg.name))
++ goto out_file;
++ arg.ino = ino;
++ arg.found = 0;
++ do {
++ arg.called = 0;
++ /* smp_mb(); */
++ err = vfsub_iterate_dir(file, &arg.ctx);
++ } while (!err && !arg.found && arg.called);
++ dentry = ERR_PTR(err);
++ if (unlikely(err))
++ goto out_name;
++ /* instead of ENOENT */
++ dentry = ERR_PTR(-ESTALE);
++ if (!arg.found)
++ goto out_name;
+
-+ key = container_of(rcu, struct au_dykey, dk_rcu);
-+ DyPrSym(key);
-+ kfree(key);
++ /* do not call vfsub_lkup_one() */
++ dir = d_inode(parent);
++ dentry = vfsub_lookup_one_len_unlocked(arg.name, path, arg.namelen);
++ AuTraceErrPtr(dentry);
++ if (IS_ERR(dentry))
++ goto out_name;
++ AuDebugOn(au_test_anon(dentry));
++ if (unlikely(d_really_is_negative(dentry))) {
++ dput(dentry);
++ dentry = ERR_PTR(-ENOENT);
++ }
++
++out_name:
++ free_page((unsigned long)arg.name);
++out_file:
++ fput(file);
++out:
++ if (unlikely(nsi_lock
++ && si_nfsd_read_lock(parent->d_sb, nsi_lock) < 0))
++ if (!IS_ERR(dentry)) {
++ dput(dentry);
++ dentry = ERR_PTR(-ESTALE);
++ }
++ AuTraceErrPtr(dentry);
++ return dentry;
+}
+
-+static void dy_free(struct kref *kref)
++static struct dentry *decode_by_dir_ino(struct super_block *sb, ino_t ino,
++ ino_t dir_ino,
++ struct au_nfsd_si_lock *nsi_lock)
+{
-+ struct au_dykey *key;
-+ struct hlist_bl_head *hbl;
++ struct dentry *dentry;
++ struct path path;
+
-+ key = container_of(kref, struct au_dykey, dk_kref);
-+ hbl = dynop + key->dk_op.dy_type;
-+ au_hbl_del(&key->dk_hnode, hbl);
-+ call_rcu(&key->dk_rcu, dy_free_rcu);
-+}
++ if (dir_ino != AUFS_ROOT_INO) {
++ path.dentry = decode_by_ino(sb, dir_ino, 0);
++ dentry = path.dentry;
++ if (!path.dentry || IS_ERR(path.dentry))
++ goto out;
++ AuDebugOn(au_test_anon(path.dentry));
++ } else
++ path.dentry = dget(sb->s_root);
+
-+void au_dy_put(struct au_dykey *key)
-+{
-+ kref_put(&key->dk_kref, dy_free);
++ path.mnt = au_mnt_get(sb);
++ dentry = au_lkup_by_ino(&path, ino, nsi_lock);
++ path_put(&path);
++
++out:
++ AuTraceErrPtr(dentry);
++ return dentry;
+}
+
+/* ---------------------------------------------------------------------- */
+
-+#define DyDbgSize(cnt, op) AuDebugOn(cnt != sizeof(op)/sizeof(void *))
++static int h_acceptable(void *expv, struct dentry *dentry)
++{
++ return 1;
++}
+
-+#ifdef CONFIG_AUFS_DEBUG
-+#define DyDbgDeclare(cnt) unsigned int cnt = 0
-+#define DyDbgInc(cnt) do { cnt++; } while (0)
-+#else
-+#define DyDbgDeclare(cnt) do {} while (0)
-+#define DyDbgInc(cnt) do {} while (0)
-+#endif
++static char *au_build_path(struct dentry *h_parent, struct path *h_rootpath,
++ char *buf, int len, struct super_block *sb)
++{
++ char *p;
++ int n;
++ struct path path;
+
-+#define DySet(func, dst, src, h_op, h_sb) do { \
-+ DyDbgInc(cnt); \
-+ if (h_op->func) { \
-+ if (src.func) \
-+ dst.func = src.func; \
-+ else \
-+ AuDbg("%s %s\n", au_sbtype(h_sb), #func); \
-+ } \
-+} while (0)
++ p = d_path(h_rootpath, buf, len);
++ if (IS_ERR(p))
++ goto out;
++ n = strlen(p);
+
-+#define DySetForce(func, dst, src) do { \
-+ AuDebugOn(!src.func); \
-+ DyDbgInc(cnt); \
-+ dst.func = src.func; \
-+} while (0)
++ path.mnt = h_rootpath->mnt;
++ path.dentry = h_parent;
++ p = d_path(&path, buf, len);
++ if (IS_ERR(p))
++ goto out;
++ if (n != 1)
++ p += n;
+
-+#define DySetAop(func) \
-+ DySet(func, dyaop->da_op, aufs_aop, h_aop, h_sb)
-+#define DySetAopForce(func) \
-+ DySetForce(func, dyaop->da_op, aufs_aop)
++ path.mnt = au_mnt_get(sb);
++ path.dentry = sb->s_root;
++ p = d_path(&path, buf, len - strlen(p));
++ mntput(path.mnt);
++ if (IS_ERR(p))
++ goto out;
++ if (n != 1)
++ p[strlen(p)] = '/';
+
-+static void dy_aop(struct au_dykey *key, const void *h_op,
-+ struct super_block *h_sb __maybe_unused)
++out:
++ AuTraceErrPtr(p);
++ return p;
++}
++
++static
++struct dentry *decode_by_path(struct super_block *sb, ino_t ino, __u32 *fh,
++ int fh_len, struct au_nfsd_si_lock *nsi_lock)
+{
-+ struct au_dyaop *dyaop = (void *)key;
-+ const struct address_space_operations *h_aop = h_op;
-+ DyDbgDeclare(cnt);
++ struct dentry *dentry, *h_parent, *root;
++ struct super_block *h_sb;
++ char *pathname, *p;
++ struct vfsmount *h_mnt;
++ struct au_branch *br;
++ int err;
++ struct path path;
+
-+ AuDbg("%s\n", au_sbtype(h_sb));
++ br = au_sbr(sb, nsi_lock->bindex);
++ h_mnt = au_br_mnt(br);
++ h_sb = h_mnt->mnt_sb;
++ /* todo: call lower fh_to_dentry()? fh_to_parent()? */
++ lockdep_off();
++ h_parent = exportfs_decode_fh(h_mnt, (void *)(fh + Fh_tail),
++ fh_len - Fh_tail, fh[Fh_h_type],
++ h_acceptable, /*context*/NULL);
++ lockdep_on();
++ dentry = h_parent;
++ if (unlikely(!h_parent || IS_ERR(h_parent))) {
++ AuWarn1("%s decode_fh failed, %ld\n",
++ au_sbtype(h_sb), PTR_ERR(h_parent));
++ goto out;
++ }
++ dentry = NULL;
++ if (unlikely(au_test_anon(h_parent))) {
++ AuWarn1("%s decode_fh returned a disconnected dentry\n",
++ au_sbtype(h_sb));
++ goto out_h_parent;
++ }
+
-+ DySetAop(writepage);
-+ DySetAopForce(read_folio); /* force */
-+ DySetAop(writepages);
-+ DySetAop(dirty_folio);
-+ DySetAop(invalidate_folio);
-+ DySetAop(readahead);
-+ DySetAop(write_begin);
-+ DySetAop(write_end);
-+ DySetAop(bmap);
-+ DySetAop(release_folio);
-+ DySetAop(free_folio);
-+ /* this one will be changed according to an aufs mount option */
-+ DySetAop(direct_IO);
-+ DySetAop(migrate_folio);
-+ DySetAop(launder_folio);
-+ DySetAop(is_partially_uptodate);
-+ DySetAop(is_dirty_writeback);
-+ DySetAop(error_remove_page);
-+ DySetAop(swap_activate);
-+ DySetAop(swap_deactivate);
-+ DySetAop(swap_rw);
++ dentry = ERR_PTR(-ENOMEM);
++ pathname = (void *)__get_free_page(GFP_NOFS);
++ if (unlikely(!pathname))
++ goto out_h_parent;
+
-+ DyDbgSize(cnt, *h_aop);
-+}
++ root = sb->s_root;
++ path.mnt = h_mnt;
++ di_read_lock_parent(root, !AuLock_IR);
++ path.dentry = au_h_dptr(root, nsi_lock->bindex);
++ di_read_unlock(root, !AuLock_IR);
++ p = au_build_path(h_parent, &path, pathname, PAGE_SIZE, sb);
++ dentry = (void *)p;
++ if (IS_ERR(p))
++ goto out_pathname;
+
-+/* ---------------------------------------------------------------------- */
++ si_read_unlock(sb);
++ err = vfsub_kern_path(p, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path);
++ dentry = ERR_PTR(err);
++ if (unlikely(err))
++ goto out_relock;
+
-+static void dy_bug(struct kref *kref)
-+{
-+ BUG();
++ dentry = ERR_PTR(-ENOENT);
++ AuDebugOn(au_test_anon(path.dentry));
++ if (unlikely(d_really_is_negative(path.dentry)))
++ goto out_path;
++
++ if (ino != d_inode(path.dentry)->i_ino)
++ dentry = au_lkup_by_ino(&path, ino, /*nsi_lock*/NULL);
++ else
++ dentry = dget(path.dentry);
++
++out_path:
++ path_put(&path);
++out_relock:
++ if (unlikely(si_nfsd_read_lock(sb, nsi_lock) < 0))
++ if (!IS_ERR(dentry)) {
++ dput(dentry);
++ dentry = ERR_PTR(-ESTALE);
++ }
++out_pathname:
++ free_page((unsigned long)pathname);
++out_h_parent:
++ dput(h_parent);
++out:
++ AuTraceErrPtr(dentry);
++ return dentry;
+}
+
-+static struct au_dykey *dy_get(struct au_dynop *op, struct au_branch *br)
++/* ---------------------------------------------------------------------- */
++
++static struct dentry *
++aufs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len,
++ int fh_type)
+{
-+ struct au_dykey *key, *old;
-+ struct hlist_bl_head *hbl;
-+ struct op {
-+ unsigned int sz;
-+ void (*set)(struct au_dykey *key, const void *h_op,
-+ struct super_block *h_sb __maybe_unused);
-+ };
-+ static const struct op a[] = {
-+ [AuDy_AOP] = {
-+ .sz = sizeof(struct au_dyaop),
-+ .set = dy_aop
-+ }
++ struct dentry *dentry;
++ __u32 *fh = fid->raw;
++ struct au_branch *br;
++ ino_t ino, dir_ino;
++ struct au_nfsd_si_lock nsi_lock = {
++ .force_lock = 0
+ };
-+ const struct op *p;
+
-+ hbl = dynop + op->dy_type;
-+ key = dy_gfind_get(hbl, op->dy_hop);
-+ if (key)
-+ goto out_add; /* success */
++ dentry = ERR_PTR(-ESTALE);
++ /* it should never happen, but the file handle is unreliable */
++ if (unlikely(fh_len < Fh_tail))
++ goto out;
++ nsi_lock.sigen = fh[Fh_sigen];
++ nsi_lock.br_id = fh[Fh_br_id];
+
-+ p = a + op->dy_type;
-+ key = kzalloc(p->sz, GFP_NOFS);
-+ if (unlikely(!key)) {
-+ key = ERR_PTR(-ENOMEM);
++ /* branch id may be wrapped around */
++ br = NULL;
++ if (unlikely(si_nfsd_read_lock(sb, &nsi_lock)))
+ goto out;
-+ }
++ nsi_lock.force_lock = 1;
++
++ /* is this inode still cached? */
++ ino = decode_ino(fh + Fh_ino);
++ /* it should never happen */
++ if (unlikely(ino == AUFS_ROOT_INO))
++ goto out_unlock;
++
++ dir_ino = decode_ino(fh + Fh_dir_ino);
++ dentry = decode_by_ino(sb, ino, dir_ino);
++ if (IS_ERR(dentry))
++ goto out_unlock;
++ if (dentry)
++ goto accept;
++
++ /* is the parent dir cached? */
++ br = au_sbr(sb, nsi_lock.bindex);
++ au_lcnt_inc(&br->br_nfiles);
++ dentry = decode_by_dir_ino(sb, ino, dir_ino, &nsi_lock);
++ if (IS_ERR(dentry))
++ goto out_unlock;
++ if (dentry)
++ goto accept;
+
-+ key->dk_op.dy_hop = op->dy_hop;
-+ kref_init(&key->dk_kref);
-+ p->set(key, op->dy_hop, au_br_sb(br));
-+ old = dy_gadd(hbl, key);
-+ if (old) {
-+ au_kfree_rcu(key);
-+ key = old;
-+ }
++ /* lookup path */
++ dentry = decode_by_path(sb, ino, fh, fh_len, &nsi_lock);
++ if (IS_ERR(dentry))
++ goto out_unlock;
++ if (unlikely(!dentry))
++ /* todo?: make it ESTALE */
++ goto out_unlock;
+
-+out_add:
-+ old = dy_bradd(br, key);
-+ if (old)
-+ /* its ref-count should never be zero here */
-+ kref_put(&key->dk_kref, dy_bug);
-+out:
-+ return key;
-+}
++accept:
++ if (!au_digen_test(dentry, au_sigen(sb))
++ && d_inode(dentry)->i_generation == fh[Fh_igen])
++ goto out_unlock; /* success */
+
-+/* ---------------------------------------------------------------------- */
-+/*
-+ * Aufs prohibits O_DIRECT by default even if the branch supports it.
-+ * This behaviour is necessary to return an error from open(O_DIRECT) instead
-+ * of the succeeding I/O. The dio mount option enables O_DIRECT and makes
-+ * open(O_DIRECT) always succeed, but the succeeding I/O may return an error.
-+ * See the aufs manual in detail.
-+ */
-+static void dy_adx(struct au_dyaop *dyaop, int do_dx)
-+{
-+ if (!do_dx)
-+ dyaop->da_op.direct_IO = NULL;
-+ else
-+ dyaop->da_op.direct_IO = aufs_aop.direct_IO;
++ dput(dentry);
++ dentry = ERR_PTR(-ESTALE);
++out_unlock:
++ if (br)
++ au_lcnt_dec(&br->br_nfiles);
++ si_read_unlock(sb);
++out:
++ AuTraceErrPtr(dentry);
++ return dentry;
+}
+
-+static struct au_dyaop *dy_aget(struct au_branch *br,
-+ const struct address_space_operations *h_aop,
-+ int do_dx)
++#if 0 /* reserved for future use */
++/* support subtreecheck option */
++static struct dentry *aufs_fh_to_parent(struct super_block *sb, struct fid *fid,
++ int fh_len, int fh_type)
+{
-+ struct au_dyaop *dyaop;
-+ struct au_dynop op;
++ struct dentry *parent;
++ __u32 *fh = fid->raw;
++ ino_t dir_ino;
+
-+ op.dy_type = AuDy_AOP;
-+ op.dy_haop = h_aop;
-+ dyaop = (void *)dy_get(&op, br);
-+ if (IS_ERR(dyaop))
++ dir_ino = decode_ino(fh + Fh_dir_ino);
++ parent = decode_by_ino(sb, dir_ino, 0);
++ if (IS_ERR(parent))
+ goto out;
-+ dy_adx(dyaop, do_dx);
++ if (!parent)
++ parent = decode_by_path(sb, au_br_index(sb, fh[Fh_br_id]),
++ dir_ino, fh, fh_len);
+
+out:
-+ return dyaop;
++ AuTraceErrPtr(parent);
++ return parent;
+}
++#endif
+
-+int au_dy_iaop(struct inode *inode, aufs_bindex_t bindex,
-+ struct inode *h_inode)
++/* ---------------------------------------------------------------------- */
++
++static int aufs_encode_fh(struct inode *inode, __u32 *fh, int *max_len,
++ struct inode *dir)
+{
-+ int err, do_dx;
-+ struct super_block *sb;
++ int err;
++ aufs_bindex_t bindex;
++ struct super_block *sb, *h_sb;
++ struct dentry *dentry, *parent, *h_parent;
++ struct inode *h_dir;
+ struct au_branch *br;
-+ struct au_dyaop *dyaop;
+
-+ AuDebugOn(!S_ISREG(h_inode->i_mode));
-+ IiMustWriteLock(inode);
++ err = -ENOSPC;
++ if (unlikely(*max_len <= Fh_tail)) {
++ AuWarn1("NFSv2 client (max_len %d)?\n", *max_len);
++ goto out;
++ }
+
-+ sb = inode->i_sb;
-+ br = au_sbr(sb, bindex);
-+ do_dx = !!au_opt_test(au_mntflags(sb), DIO);
-+ dyaop = dy_aget(br, h_inode->i_mapping->a_ops, do_dx);
-+ err = PTR_ERR(dyaop);
-+ if (IS_ERR(dyaop))
-+ /* unnecessary to call dy_fput() */
++ err = FILEID_ROOT;
++ if (inode->i_ino == AUFS_ROOT_INO) {
++ AuDebugOn(inode->i_ino != AUFS_ROOT_INO);
+ goto out;
++ }
+
-+ err = 0;
-+ inode->i_mapping->a_ops = &dyaop->da_op;
++ h_parent = NULL;
++ sb = inode->i_sb;
++ err = si_read_lock(sb, AuLock_FLUSH);
++ if (unlikely(err))
++ goto out;
+
-+out:
-+ return err;
-+}
++#ifdef CONFIG_AUFS_DEBUG
++ if (unlikely(!au_opt_test(au_mntflags(sb), XINO)))
++ AuWarn1("NFS-exporting requires xino\n");
++#endif
++ err = -EIO;
++ parent = NULL;
++ ii_read_lock_child(inode);
++ bindex = au_ibtop(inode);
++ if (!dir) {
++ dentry = d_find_any_alias(inode);
++ if (unlikely(!dentry))
++ goto out_unlock;
++ AuDebugOn(au_test_anon(dentry));
++ parent = dget_parent(dentry);
++ dput(dentry);
++ if (unlikely(!parent))
++ goto out_unlock;
++ if (d_really_is_positive(parent))
++ dir = d_inode(parent);
++ }
+
-+/*
-+ * Is it safe to replace a_ops during the inode/file is in operation?
-+ * Yes, I hope so.
-+ */
-+int au_dy_irefresh(struct inode *inode)
-+{
-+ int err;
-+ aufs_bindex_t btop;
-+ struct inode *h_inode;
++ ii_read_lock_parent(dir);
++ h_dir = au_h_iptr(dir, bindex);
++ ii_read_unlock(dir);
++ if (unlikely(!h_dir))
++ goto out_parent;
++ h_parent = d_find_any_alias(h_dir);
++ if (unlikely(!h_parent))
++ goto out_hparent;
+
-+ err = 0;
-+ if (S_ISREG(inode->i_mode)) {
-+ btop = au_ibtop(inode);
-+ h_inode = au_h_iptr(inode, btop);
-+ err = au_dy_iaop(inode, btop, h_inode);
++ err = -EPERM;
++ br = au_sbr(sb, bindex);
++ h_sb = au_br_sb(br);
++ if (unlikely(!h_sb->s_export_op)) {
++ AuErr1("%s branch is not exportable\n", au_sbtype(h_sb));
++ goto out_hparent;
+ }
-+ return err;
-+}
+
-+void au_dy_arefresh(int do_dx)
-+{
-+ struct hlist_bl_head *hbl;
-+ struct hlist_bl_node *pos;
-+ struct au_dykey *key;
++ fh[Fh_br_id] = br->br_id;
++ fh[Fh_sigen] = au_sigen(sb);
++ encode_ino(fh + Fh_ino, inode->i_ino);
++ encode_ino(fh + Fh_dir_ino, dir->i_ino);
++ fh[Fh_igen] = inode->i_generation;
+
-+ hbl = dynop + AuDy_AOP;
-+ hlist_bl_lock(hbl);
-+ hlist_bl_for_each_entry(key, pos, hbl, dk_hnode)
-+ dy_adx((void *)key, do_dx);
-+ hlist_bl_unlock(hbl);
++ *max_len -= Fh_tail;
++ fh[Fh_h_type] = exportfs_encode_fh(h_parent, (void *)(fh + Fh_tail),
++ max_len,
++ /*connectable or subtreecheck*/0);
++ err = fh[Fh_h_type];
++ *max_len += Fh_tail;
++ /* todo: macros? */
++ if (err != FILEID_INVALID)
++ err = 99;
++ else
++ AuWarn1("%s encode_fh failed\n", au_sbtype(h_sb));
++
++out_hparent:
++ dput(h_parent);
++out_parent:
++ dput(parent);
++out_unlock:
++ ii_read_unlock(inode);
++ si_read_unlock(sb);
++out:
++ if (unlikely(err < 0))
++ err = FILEID_INVALID;
++ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
-+void __init au_dy_init(void)
++static int aufs_commit_metadata(struct inode *inode)
+{
-+ int i;
++ int err;
++ aufs_bindex_t bindex;
++ struct super_block *sb;
++ struct inode *h_inode;
++ int (*f)(struct inode *inode);
+
-+ for (i = 0; i < AuDyLast; i++)
-+ INIT_HLIST_BL_HEAD(dynop + i);
-+}
++ sb = inode->i_sb;
++ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
++ ii_write_lock_child(inode);
++ bindex = au_ibtop(inode);
++ AuDebugOn(bindex < 0);
++ h_inode = au_h_iptr(inode, bindex);
+
-+void au_dy_fin(void)
-+{
-+ int i;
++ f = h_inode->i_sb->s_export_op->commit_metadata;
++ if (f)
++ err = f(h_inode);
++ else
++ err = sync_inode_metadata(h_inode, /*wait*/1);
+
-+ for (i = 0; i < AuDyLast; i++)
-+ WARN_ON(!hlist_bl_empty(dynop + i));
++ au_cpup_attr_timesizes(inode);
++ ii_write_unlock(inode);
++ si_read_unlock(sb);
++ return err;
+}
-diff -urN /usr/share/empty/fs/aufs/dynop.h linux/fs/aufs/dynop.h
---- /usr/share/empty/fs/aufs/dynop.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dynop.h 2022-11-05 23:02:18.962555950 +0100
-@@ -0,0 +1,77 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2010-2022 Junjiro R. Okajima
-+ *
-+ * This program 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/>.
-+ */
+
-+/*
-+ * dynamically customizable operations (for regular files only)
-+ */
-+
-+#ifndef __AUFS_DYNOP_H__
-+#define __AUFS_DYNOP_H__
-+
-+#ifdef __KERNEL__
-+
-+#include <linux/fs.h>
-+#include <linux/kref.h>
-+
-+enum {AuDy_AOP, AuDyLast};
-+
-+struct au_dynop {
-+ int dy_type;
-+ union {
-+ const void *dy_hop;
-+ const struct address_space_operations *dy_haop;
-+ };
-+};
-+
-+struct au_dykey {
-+ union {
-+ struct hlist_bl_node dk_hnode;
-+ struct rcu_head dk_rcu;
-+ };
-+ struct au_dynop dk_op;
-+
-+ /*
-+ * during I am in the branch local array, kref is gotten. when the
-+ * branch is removed, kref is put.
-+ */
-+ struct kref dk_kref;
-+};
++/* ---------------------------------------------------------------------- */
+
-+/* stop unioning since their sizes are very different from each other */
-+struct au_dyaop {
-+ struct au_dykey da_key;
-+ struct address_space_operations da_op; /* not const */
++static struct export_operations aufs_export_op = {
++ .fh_to_dentry = aufs_fh_to_dentry,
++ /* .fh_to_parent = aufs_fh_to_parent, */
++ .encode_fh = aufs_encode_fh,
++ .commit_metadata = aufs_commit_metadata
+};
-+/* make sure that 'struct au_dykey *' can be any type */
-+static_assert(!offsetof(struct au_dyaop, da_key));
-+
-+/* ---------------------------------------------------------------------- */
+
-+/* dynop.c */
-+struct au_branch;
-+void au_dy_put(struct au_dykey *key);
-+int au_dy_iaop(struct inode *inode, aufs_bindex_t bindex,
-+ struct inode *h_inode);
-+int au_dy_irefresh(struct inode *inode);
-+void au_dy_arefresh(int do_dio);
++void au_export_init(struct super_block *sb)
++{
++ struct au_sbinfo *sbinfo;
++ __u32 u;
+
-+void __init au_dy_init(void);
-+void au_dy_fin(void);
++ BUILD_BUG_ON_MSG(IS_BUILTIN(CONFIG_AUFS_FS)
++ && IS_MODULE(CONFIG_EXPORTFS),
++ AUFS_NAME ": unsupported configuration "
++ "CONFIG_EXPORTFS=m and CONFIG_AUFS_FS=y");
+
-+#endif /* __KERNEL__ */
-+#endif /* __AUFS_DYNOP_H__ */
-diff -urN /usr/share/empty/fs/aufs/export.c linux/fs/aufs/export.c
---- /usr/share/empty/fs/aufs/export.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/export.c 2022-12-17 09:21:34.796521861 +0100
-@@ -0,0 +1,830 @@
++ sb->s_export_op = &aufs_export_op;
++ sbinfo = au_sbi(sb);
++ sbinfo->si_xigen = NULL;
++ get_random_bytes(&u, sizeof(u));
++ BUILD_BUG_ON(sizeof(u) != sizeof(int));
++ atomic_set(&sbinfo->si_xigen_next, u);
++}
+diff --git a/fs/aufs/f_op.c b/fs/aufs/f_op.c
+new file mode 100644
+index 00000000000000..320ad8a9334d30
+--- /dev/null
++++ b/fs/aufs/f_op.c
+@@ -0,0 +1,771 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2005-2022 Junjiro R. Okajima
+ */
+
+/*
-+ * export via nfs
++ * file and vm operations
+ */
+
-+#include <linux/exportfs.h>
-+#include <linux/fs_struct.h>
-+#include <linux/nsproxy.h>
-+#include <linux/random.h>
-+#include <linux/writeback.h>
++#include <linux/aio.h>
++#include <linux/fs_stack.h>
++#include <linux/mman.h>
++#include <linux/security.h>
+#include "aufs.h"
+
-+union conv {
-+#ifdef CONFIG_AUFS_INO_T_64
-+ __u32 a[2];
-+#else
-+ __u32 a[1];
-+#endif
-+ ino_t ino;
-+};
-+
-+static ino_t decode_ino(__u32 *a)
-+{
-+ union conv u;
-+
-+ BUILD_BUG_ON(sizeof(u.ino) != sizeof(u.a));
-+ u.a[0] = a[0];
-+#ifdef CONFIG_AUFS_INO_T_64
-+ u.a[1] = a[1];
-+#endif
-+ return u.ino;
-+}
-+
-+static void encode_ino(__u32 *a, ino_t ino)
-+{
-+ union conv u;
-+
-+ u.ino = ino;
-+ a[0] = u.a[0];
-+#ifdef CONFIG_AUFS_INO_T_64
-+ a[1] = u.a[1];
-+#endif
-+}
-+
-+/* NFS file handle */
-+enum {
-+ Fh_br_id,
-+ Fh_sigen,
-+#ifdef CONFIG_AUFS_INO_T_64
-+ /* support 64bit inode number */
-+ Fh_ino1,
-+ Fh_ino2,
-+ Fh_dir_ino1,
-+ Fh_dir_ino2,
-+#else
-+ Fh_ino1,
-+ Fh_dir_ino1,
-+#endif
-+ Fh_igen,
-+ Fh_h_type,
-+ Fh_tail,
-+
-+ Fh_ino = Fh_ino1,
-+ Fh_dir_ino = Fh_dir_ino1
-+};
-+
-+static int au_test_anon(struct dentry *dentry)
-+{
-+ /* note: read d_flags without d_lock */
-+ return !!(dentry->d_flags & DCACHE_DISCONNECTED);
-+}
-+
-+int au_test_nfsd(void)
-+{
-+ int ret;
-+ struct task_struct *tsk = current;
-+ char comm[sizeof(tsk->comm)];
-+
-+ ret = 0;
-+ if (tsk->flags & PF_KTHREAD) {
-+ get_task_comm(comm, tsk);
-+ ret = !strcmp(comm, "nfsd");
-+ }
-+
-+ return ret;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+/* inode generation external table */
-+
-+void au_xigen_inc(struct inode *inode)
-+{
-+ loff_t pos;
-+ ssize_t sz;
-+ __u32 igen;
-+ struct super_block *sb;
-+ struct au_sbinfo *sbinfo;
-+
-+ sb = inode->i_sb;
-+ AuDebugOn(!au_opt_test(au_mntflags(sb), XINO));
-+
-+ sbinfo = au_sbi(sb);
-+ pos = inode->i_ino;
-+ pos *= sizeof(igen);
-+ igen = inode->i_generation + 1;
-+ sz = xino_fwrite(sbinfo->si_xigen, &igen, sizeof(igen), &pos);
-+ if (sz == sizeof(igen))
-+ return; /* success */
-+
-+ if (unlikely(sz >= 0))
-+ AuIOErr("xigen error (%zd)\n", sz);
-+}
-+
-+int au_xigen_new(struct inode *inode)
++int au_do_open_nondir(struct file *file, int flags, struct file *h_file)
+{
+ int err;
-+ loff_t pos;
-+ ssize_t sz;
-+ struct super_block *sb;
-+ struct au_sbinfo *sbinfo;
-+ struct file *file;
-+
-+ err = 0;
-+ /* todo: dirty, at mount time */
-+ if (inode->i_ino == AUFS_ROOT_INO)
-+ goto out;
-+ sb = inode->i_sb;
-+ SiMustAnyLock(sb);
-+ if (unlikely(!au_opt_test(au_mntflags(sb), XINO)))
-+ goto out;
++ aufs_bindex_t bindex;
++ struct dentry *dentry, *h_dentry;
++ struct au_finfo *finfo;
++ struct inode *h_inode;
+
-+ err = -EFBIG;
-+ pos = inode->i_ino;
-+ if (unlikely(au_loff_max / sizeof(inode->i_generation) - 1 < pos)) {
-+ AuIOErr1("too large i%lld\n", pos);
-+ goto out;
-+ }
-+ pos *= sizeof(inode->i_generation);
++ FiMustWriteLock(file);
+
+ err = 0;
-+ sbinfo = au_sbi(sb);
-+ file = sbinfo->si_xigen;
-+ BUG_ON(!file);
-+
-+ if (vfsub_f_size_read(file)
-+ < pos + sizeof(inode->i_generation)) {
-+ inode->i_generation = atomic_inc_return(&sbinfo->si_xigen_next);
-+ sz = xino_fwrite(file, &inode->i_generation,
-+ sizeof(inode->i_generation), &pos);
-+ } else
-+ sz = xino_fread(file, &inode->i_generation,
-+ sizeof(inode->i_generation), &pos);
-+ if (sz == sizeof(inode->i_generation))
-+ goto out; /* success */
++ dentry = file->f_path.dentry;
++ AuDebugOn(IS_ERR_OR_NULL(dentry));
++ finfo = au_fi(file);
++ memset(&finfo->fi_htop, 0, sizeof(finfo->fi_htop));
++ atomic_set(&finfo->fi_mmapped, 0);
++ bindex = au_dbtop(dentry);
++ if (!h_file) {
++ h_dentry = au_h_dptr(dentry, bindex);
++ err = vfsub_test_mntns(file->f_path.mnt, h_dentry->d_sb);
++ if (unlikely(err))
++ goto out;
++ h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0);
++ if (IS_ERR(h_file)) {
++ err = PTR_ERR(h_file);
++ goto out;
++ }
++ } else {
++ h_dentry = h_file->f_path.dentry;
++ err = vfsub_test_mntns(file->f_path.mnt, h_dentry->d_sb);
++ if (unlikely(err))
++ goto out;
++ /* br ref is already inc-ed */
++ }
+
-+ err = sz;
-+ if (unlikely(sz >= 0)) {
-+ err = -EIO;
-+ AuIOErr("xigen error (%zd)\n", sz);
++ if (flags & __O_TMPFILE) {
++ AuDebugOn(!h_file);
++ AuDebugOn(h_file != au_di(dentry)->di_htmpfile);
++ au_di(dentry)->di_htmpfile = NULL;
++
++ if (!(flags & O_EXCL)) {
++ h_inode = file_inode(h_file);
++ spin_lock(&h_inode->i_lock);
++ h_inode->i_state |= I_LINKABLE;
++ spin_unlock(&h_inode->i_lock);
++ }
+ }
++ au_set_fbtop(file, bindex);
++ au_set_h_fptr(file, bindex, h_file);
++ au_update_figen(file);
++ /* todo: necessary? */
++ /* file->f_ra = h_file->f_ra; */
+
+out:
+ return err;
+}
+
-+int au_xigen_set(struct super_block *sb, struct path *path)
++static int aufs_open_nondir(struct inode *inode __maybe_unused,
++ struct file *file)
+{
+ int err;
-+ struct au_sbinfo *sbinfo;
-+ struct file *file;
-+
-+ SiMustWriteLock(sb);
++ struct super_block *sb;
++ struct au_do_open_args args = {
++ .open = au_do_open_nondir
++ };
+
-+ sbinfo = au_sbi(sb);
-+ file = au_xino_create2(sb, path, sbinfo->si_xigen);
-+ err = PTR_ERR(file);
-+ if (IS_ERR(file))
-+ goto out;
-+ err = 0;
-+ if (sbinfo->si_xigen)
-+ fput(sbinfo->si_xigen);
-+ sbinfo->si_xigen = file;
++ AuDbg("%pD, f_flags 0x%x, f_mode 0x%x\n",
++ file, vfsub_file_flags(file), file->f_mode);
+
-+out:
-+ AuTraceErr(err);
++ sb = file->f_path.dentry->d_sb;
++ si_read_lock(sb, AuLock_FLUSH);
++ err = au_do_open(file, &args);
++ si_read_unlock(sb);
+ return err;
+}
+
-+void au_xigen_clr(struct super_block *sb)
++int aufs_release_nondir(struct inode *inode __maybe_unused, struct file *file)
+{
-+ struct au_sbinfo *sbinfo;
++ struct au_finfo *finfo;
++ aufs_bindex_t bindex;
+
-+ SiMustWriteLock(sb);
++ finfo = au_fi(file);
++ au_hbl_del(&finfo->fi_hlist,
++ &au_sbi(file->f_path.dentry->d_sb)->si_files);
++ bindex = finfo->fi_btop;
++ if (bindex >= 0)
++ au_set_h_fptr(file, bindex, NULL);
+
-+ sbinfo = au_sbi(sb);
-+ if (sbinfo->si_xigen) {
-+ fput(sbinfo->si_xigen);
-+ sbinfo->si_xigen = NULL;
-+ }
++ au_finfo_fin(file);
++ return 0;
+}
+
+/* ---------------------------------------------------------------------- */
+
-+static struct dentry *decode_by_ino(struct super_block *sb, ino_t ino,
-+ ino_t dir_ino)
++static int au_do_flush_nondir(struct file *file, fl_owner_t id)
+{
-+ struct dentry *dentry, *d;
-+ struct inode *inode;
-+ unsigned int sigen;
-+
-+ dentry = NULL;
-+ inode = ilookup(sb, ino);
-+ if (!inode)
-+ goto out;
-+
-+ dentry = ERR_PTR(-ESTALE);
-+ sigen = au_sigen(sb);
-+ if (unlikely(au_is_bad_inode(inode)
-+ || IS_DEADDIR(inode)
-+ || sigen != au_iigen(inode, NULL)))
-+ goto out_iput;
++ int err;
++ struct file *h_file;
+
-+ dentry = NULL;
-+ if (!dir_ino || S_ISDIR(inode->i_mode))
-+ dentry = d_find_alias(inode);
-+ else {
-+ spin_lock(&inode->i_lock);
-+ hlist_for_each_entry(d, &inode->i_dentry, d_u.d_alias) {
-+ spin_lock(&d->d_lock);
-+ if (!au_test_anon(d)
-+ && d_inode(d->d_parent)->i_ino == dir_ino) {
-+ dentry = dget_dlock(d);
-+ spin_unlock(&d->d_lock);
-+ break;
-+ }
-+ spin_unlock(&d->d_lock);
-+ }
-+ spin_unlock(&inode->i_lock);
-+ }
-+ if (unlikely(dentry && au_digen_test(dentry, sigen))) {
-+ /* need to refresh */
-+ dput(dentry);
-+ dentry = NULL;
-+ }
++ err = 0;
++ h_file = au_hf_top(file);
++ if (h_file)
++ err = vfsub_flush(h_file, id);
++ return err;
++}
+
-+out_iput:
-+ iput(inode);
-+out:
-+ AuTraceErrPtr(dentry);
-+ return dentry;
++static int aufs_flush_nondir(struct file *file, fl_owner_t id)
++{
++ return au_do_flush(file, id, au_do_flush_nondir);
+}
+
+/* ---------------------------------------------------------------------- */
++/*
++ * read and write functions acquire [fdi]_rwsem once, but release before
++ * mmap_sem. This is because to stop a race condition between mmap(2).
++ * Releasing these aufs-rwsem should be safe, no branch-management (by keeping
++ * si_rwsem), no harmful copy-up should happen. Actually copy-up may happen in
++ * read functions after [fdi]_rwsem are released, but it should be harmless.
++ */
+
-+/* todo: dirty? */
-+/* if exportfs_decode_fh() passed vfsmount*, we could be happy */
++/* Callers should call au_read_post() or fput() in the end */
++struct file *au_read_pre(struct file *file, int keep_fi, unsigned int lsc)
++{
++ struct file *h_file;
++ int err;
+
-+struct au_compare_mnt_args {
++ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/0, lsc);
++ if (!err) {
++ di_read_unlock(file->f_path.dentry, AuLock_IR);
++ h_file = au_hf_top(file);
++ get_file(h_file);
++ if (!keep_fi)
++ fi_read_unlock(file);
++ } else
++ h_file = ERR_PTR(err);
++
++ return h_file;
++}
++
++static void au_read_post(struct inode *inode, struct file *h_file)
++{
++ /* update without lock, I don't think it a problem */
++ fsstack_copy_attr_atime(inode, file_inode(h_file));
++ fput(h_file);
++}
++
++struct au_write_pre {
+ /* input */
-+ struct super_block *sb;
++ unsigned int lsc;
+
+ /* output */
-+ struct vfsmount *mnt;
++ blkcnt_t blks;
++ aufs_bindex_t btop;
+};
+
-+static int au_compare_mnt(struct vfsmount *mnt, void *arg)
++/*
++ * return with iinfo is write-locked
++ * callers should call au_write_post() or iinfo_write_unlock() + fput() in the
++ * end
++ */
++static struct file *au_write_pre(struct file *file, int do_ready,
++ struct au_write_pre *wpre)
+{
-+ struct au_compare_mnt_args *a = arg;
++ struct file *h_file;
++ struct dentry *dentry;
++ int err;
++ unsigned int lsc;
++ struct au_pin pin;
+
-+ if (mnt->mnt_sb != a->sb)
-+ return 0;
-+ a->mnt = mntget(mnt);
-+ return 1;
++ lsc = 0;
++ if (wpre)
++ lsc = wpre->lsc;
++ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1, lsc);
++ h_file = ERR_PTR(err);
++ if (unlikely(err))
++ goto out;
++
++ dentry = file->f_path.dentry;
++ if (do_ready) {
++ err = au_ready_to_write(file, -1, &pin);
++ if (unlikely(err)) {
++ h_file = ERR_PTR(err);
++ di_write_unlock(dentry);
++ goto out_fi;
++ }
++ }
++
++ di_downgrade_lock(dentry, /*flags*/0);
++ if (wpre)
++ wpre->btop = au_fbtop(file);
++ h_file = au_hf_top(file);
++ get_file(h_file);
++ if (wpre)
++ wpre->blks = file_inode(h_file)->i_blocks;
++ if (do_ready)
++ au_unpin(&pin);
++ di_read_unlock(dentry, /*flags*/0);
++ vfsub_file_start_write(h_file);
++
++out_fi:
++ fi_write_unlock(file);
++out:
++ return h_file;
+}
+
-+static struct vfsmount *au_mnt_get(struct super_block *sb)
++static void au_write_post(struct inode *inode, struct file *h_file,
++ struct au_write_pre *wpre, ssize_t written)
+{
-+ int err;
-+ struct path root;
-+ struct au_compare_mnt_args args = {
-+ .sb = sb
-+ };
++ struct inode *h_inode;
+
-+ get_fs_root(current->fs, &root);
-+ rcu_read_lock();
-+ err = iterate_mounts(au_compare_mnt, &args, root.mnt);
-+ rcu_read_unlock();
-+ path_put(&root);
-+ AuDebugOn(!err);
-+ AuDebugOn(!args.mnt);
-+ return args.mnt;
++ vfsub_file_end_write(h_file);
++ au_cpup_attr_timesizes(inode);
++ AuDebugOn(au_ibtop(inode) != wpre->btop);
++ h_inode = file_inode(h_file);
++ inode->i_mode = h_inode->i_mode;
++ ii_write_unlock(inode);
++ /* AuDbg("blks %llu, %llu\n", (u64)blks, (u64)h_inode->i_blocks); */
++ if (written > 0)
++ au_fhsm_wrote(inode->i_sb, wpre->btop,
++ /*force*/h_inode->i_blocks > wpre->blks);
++ fput(h_file);
+}
+
-+struct au_nfsd_si_lock {
-+ unsigned int sigen;
-+ aufs_bindex_t bindex, br_id;
-+ unsigned char force_lock;
-+};
-+
-+static int si_nfsd_read_lock(struct super_block *sb,
-+ struct au_nfsd_si_lock *nsi_lock)
++/*
++ * todo: very ugly
++ * it locks both of i_mutex and si_rwsem for read in safe.
++ * if the plink maintenance mode continues forever (that is the problem),
++ * may loop forever.
++ */
++static void au_mtx_and_read_lock(struct inode *inode)
+{
+ int err;
-+ aufs_bindex_t bindex;
++ struct super_block *sb = inode->i_sb;
+
-+ si_read_lock(sb, AuLock_FLUSH);
++ while (1) {
++ inode_lock(inode);
++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
++ if (!err)
++ break;
++ inode_unlock(inode);
++ si_read_lock(sb, AuLock_NOPLMW);
++ si_read_unlock(sb);
++ }
++}
+
-+ /* branch id may be wrapped around */
-+ err = 0;
-+ bindex = au_br_index(sb, nsi_lock->br_id);
-+ if (bindex >= 0 && nsi_lock->sigen + AUFS_BRANCH_MAX > au_sigen(sb))
-+ goto out; /* success */
++static ssize_t au_do_iter(struct file *h_file, int rw, struct kiocb *kio,
++ struct iov_iter *iov_iter)
++{
++ ssize_t err;
++ struct file *file;
++ ssize_t (*iter)(struct kiocb *, struct iov_iter *);
+
-+ err = -ESTALE;
-+ bindex = -1;
-+ if (!nsi_lock->force_lock)
-+ si_read_unlock(sb);
++ err = security_file_permission(h_file, rw);
++ if (unlikely(err))
++ goto out;
++
++ err = -ENOSYS; /* the branch doesn't have its ->(read|write)_iter() */
++ iter = NULL;
++ if (rw == MAY_READ)
++ iter = h_file->f_op->read_iter;
++ else if (rw == MAY_WRITE)
++ iter = h_file->f_op->write_iter;
++
++ file = kio->ki_filp;
++ kio->ki_filp = h_file;
++ if (iter) {
++ lockdep_off();
++ err = iter(kio, iov_iter);
++ lockdep_on();
++ } else
++ /* currently there is no such fs */
++ WARN_ON_ONCE(1);
++ kio->ki_filp = file;
+
+out:
-+ nsi_lock->bindex = bindex;
+ return err;
+}
+
-+struct find_name_by_ino {
-+ struct dir_context ctx;
-+ int called, found;
-+ ino_t ino;
-+ char *name;
-+ int namelen;
-+};
-+
-+static bool
-+find_name_by_ino(struct dir_context *ctx, const char *name, int namelen,
-+ loff_t offset, u64 ino, unsigned int d_type)
++static ssize_t aufs_read_iter(struct kiocb *kio, struct iov_iter *iov_iter)
+{
-+ struct find_name_by_ino *a = container_of(ctx, struct find_name_by_ino,
-+ ctx);
++ ssize_t err;
++ struct file *file, *h_file;
++ struct inode *inode;
++ struct super_block *sb;
+
-+ a->called++;
-+ if (a->ino != ino)
-+ return true;
++ file = kio->ki_filp;
++ inode = file_inode(file);
++ sb = inode->i_sb;
++ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
+
-+ memcpy(a->name, name, namelen);
-+ a->namelen = namelen;
-+ a->found = 1;
-+ return false;
++ h_file = au_read_pre(file, /*keep_fi*/1, /*lsc*/0);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
++ goto out;
++
++ if (au_test_loopback_kthread()) {
++ au_warn_loopback(h_file->f_path.dentry->d_sb);
++ if (file->f_mapping != h_file->f_mapping) {
++ file->f_mapping = h_file->f_mapping;
++ smp_mb(); /* unnecessary? */
++ }
++ }
++ fi_read_unlock(file);
++
++ err = au_do_iter(h_file, MAY_READ, kio, iov_iter);
++ /* todo: necessary? */
++ /* file->f_ra = h_file->f_ra; */
++ au_read_post(inode, h_file);
++
++out:
++ si_read_unlock(sb);
++ return err;
+}
+
-+static struct dentry *au_lkup_by_ino(struct path *path, ino_t ino,
-+ struct au_nfsd_si_lock *nsi_lock)
++static ssize_t aufs_write_iter(struct kiocb *kio, struct iov_iter *iov_iter)
+{
-+ struct dentry *dentry, *parent;
-+ struct file *file;
-+ struct inode *dir;
-+ struct find_name_by_ino arg = {
-+ .ctx = {
-+ .actor = find_name_by_ino
-+ }
-+ };
-+ int err;
++ ssize_t err;
++ struct au_write_pre wpre;
++ struct inode *inode;
++ struct file *file, *h_file;
+
-+ parent = path->dentry;
-+ if (nsi_lock)
-+ si_read_unlock(parent->d_sb);
-+ file = vfsub_dentry_open(path, au_dir_roflags);
-+ dentry = (void *)file;
-+ if (IS_ERR(file))
-+ goto out;
++ file = kio->ki_filp;
++ inode = file_inode(file);
++ au_mtx_and_read_lock(inode);
+
-+ dentry = ERR_PTR(-ENOMEM);
-+ arg.name = (void *)__get_free_page(GFP_NOFS);
-+ if (unlikely(!arg.name))
-+ goto out_file;
-+ arg.ino = ino;
-+ arg.found = 0;
-+ do {
-+ arg.called = 0;
-+ /* smp_mb(); */
-+ err = vfsub_iterate_dir(file, &arg.ctx);
-+ } while (!err && !arg.found && arg.called);
-+ dentry = ERR_PTR(err);
-+ if (unlikely(err))
-+ goto out_name;
-+ /* instead of ENOENT */
-+ dentry = ERR_PTR(-ESTALE);
-+ if (!arg.found)
-+ goto out_name;
++ wpre.lsc = 0;
++ h_file = au_write_pre(file, /*do_ready*/1, &wpre);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
++ goto out;
+
-+ /* do not call vfsub_lkup_one() */
-+ dir = d_inode(parent);
-+ dentry = vfsub_lookup_one_len_unlocked(arg.name, path, arg.namelen);
-+ AuTraceErrPtr(dentry);
-+ if (IS_ERR(dentry))
-+ goto out_name;
-+ AuDebugOn(au_test_anon(dentry));
-+ if (unlikely(d_really_is_negative(dentry))) {
-+ dput(dentry);
-+ dentry = ERR_PTR(-ENOENT);
-+ }
++ err = au_do_iter(h_file, MAY_WRITE, kio, iov_iter);
++ au_write_post(inode, h_file, &wpre, err);
+
-+out_name:
-+ free_page((unsigned long)arg.name);
-+out_file:
-+ fput(file);
+out:
-+ if (unlikely(nsi_lock
-+ && si_nfsd_read_lock(parent->d_sb, nsi_lock) < 0))
-+ if (!IS_ERR(dentry)) {
-+ dput(dentry);
-+ dentry = ERR_PTR(-ESTALE);
-+ }
-+ AuTraceErrPtr(dentry);
-+ return dentry;
++ si_read_unlock(inode->i_sb);
++ inode_unlock(inode);
++ return err;
+}
+
-+static struct dentry *decode_by_dir_ino(struct super_block *sb, ino_t ino,
-+ ino_t dir_ino,
-+ struct au_nfsd_si_lock *nsi_lock)
++/*
++ * We may be able to remove aufs_splice_{read,write}() since almost all FSes
++ * don't have their own .splice_{read,write} implimentations, and they use
++ * generic_file_splice_read() and iter_file_splice_write() who can act like the
++ * simple converters to f_op->iter_read() and ->iter_write().
++ * But we keep our own implementations because some non-mainlined FSes may have
++ * their own .splice_{read,write} implimentations and aufs doesn't want to take
++ * away an opportunity to co-work with aufs from them.
++ */
++static ssize_t aufs_splice_read(struct file *file, loff_t *ppos,
++ struct pipe_inode_info *pipe, size_t len,
++ unsigned int flags)
+{
-+ struct dentry *dentry;
-+ struct path path;
++ ssize_t err;
++ struct file *h_file;
++ struct inode *inode;
++ struct super_block *sb;
+
-+ if (dir_ino != AUFS_ROOT_INO) {
-+ path.dentry = decode_by_ino(sb, dir_ino, 0);
-+ dentry = path.dentry;
-+ if (!path.dentry || IS_ERR(path.dentry))
-+ goto out;
-+ AuDebugOn(au_test_anon(path.dentry));
-+ } else
-+ path.dentry = dget(sb->s_root);
++ inode = file_inode(file);
++ sb = inode->i_sb;
++ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
+
-+ path.mnt = au_mnt_get(sb);
-+ dentry = au_lkup_by_ino(&path, ino, nsi_lock);
-+ path_put(&path);
++ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
++ goto out;
++
++ err = vfsub_splice_read(h_file, ppos, pipe, len, flags);
++ /* todo: necessary? */
++ /* file->f_ra = h_file->f_ra; */
++ au_read_post(inode, h_file);
+
+out:
-+ AuTraceErrPtr(dentry);
-+ return dentry;
++ si_read_unlock(sb);
++ return err;
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+static int h_acceptable(void *expv, struct dentry *dentry)
++static ssize_t
++aufs_splice_write(struct pipe_inode_info *pipe, struct file *file, loff_t *ppos,
++ size_t len, unsigned int flags)
+{
-+ return 1;
++ ssize_t err;
++ struct au_write_pre wpre;
++ struct inode *inode;
++ struct file *h_file;
++
++ inode = file_inode(file);
++ au_mtx_and_read_lock(inode);
++
++ wpre.lsc = 0;
++ h_file = au_write_pre(file, /*do_ready*/1, &wpre);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
++ goto out;
++
++ err = vfsub_splice_from(pipe, h_file, ppos, len, flags);
++ au_write_post(inode, h_file, &wpre, err);
++
++out:
++ si_read_unlock(inode->i_sb);
++ inode_unlock(inode);
++ return err;
+}
+
-+static char *au_build_path(struct dentry *h_parent, struct path *h_rootpath,
-+ char *buf, int len, struct super_block *sb)
++static long aufs_fallocate(struct file *file, int mode, loff_t offset,
++ loff_t len)
+{
-+ char *p;
-+ int n;
-+ struct path path;
++ long err;
++ struct au_write_pre wpre;
++ struct inode *inode;
++ struct file *h_file;
+
-+ p = d_path(h_rootpath, buf, len);
-+ if (IS_ERR(p))
-+ goto out;
-+ n = strlen(p);
++ inode = file_inode(file);
++ au_mtx_and_read_lock(inode);
+
-+ path.mnt = h_rootpath->mnt;
-+ path.dentry = h_parent;
-+ p = d_path(&path, buf, len);
-+ if (IS_ERR(p))
++ wpre.lsc = 0;
++ h_file = au_write_pre(file, /*do_ready*/1, &wpre);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
+ goto out;
-+ if (n != 1)
-+ p += n;
+
-+ path.mnt = au_mnt_get(sb);
-+ path.dentry = sb->s_root;
-+ p = d_path(&path, buf, len - strlen(p));
-+ mntput(path.mnt);
-+ if (IS_ERR(p))
-+ goto out;
-+ if (n != 1)
-+ p[strlen(p)] = '/';
++ lockdep_off();
++ err = vfs_fallocate(h_file, mode, offset, len);
++ lockdep_on();
++ /*
++ * we don't need to call file_modifed() here since au_write_post()
++ * is equivalent and copies-up all timestamps and permission bits.
++ */
++ au_write_post(inode, h_file, &wpre, /*written*/1);
+
+out:
-+ AuTraceErrPtr(p);
-+ return p;
++ si_read_unlock(inode->i_sb);
++ inode_unlock(inode);
++ return err;
+}
+
-+static
-+struct dentry *decode_by_path(struct super_block *sb, ino_t ino, __u32 *fh,
-+ int fh_len, struct au_nfsd_si_lock *nsi_lock)
++static ssize_t aufs_copy_file_range(struct file *src, loff_t src_pos,
++ struct file *dst, loff_t dst_pos,
++ size_t len, unsigned int flags)
+{
-+ struct dentry *dentry, *h_parent, *root;
-+ struct super_block *h_sb;
-+ char *pathname, *p;
-+ struct vfsmount *h_mnt;
-+ struct au_branch *br;
-+ int err;
-+ struct path path;
++ ssize_t err;
++ struct au_write_pre wpre;
++ enum { SRC, DST };
++ struct {
++ struct inode *inode;
++ struct file *h_file;
++ struct super_block *h_sb;
++ } a[2];
++#define a_src a[SRC]
++#define a_dst a[DST]
+
-+ br = au_sbr(sb, nsi_lock->bindex);
-+ h_mnt = au_br_mnt(br);
-+ h_sb = h_mnt->mnt_sb;
-+ /* todo: call lower fh_to_dentry()? fh_to_parent()? */
-+ lockdep_off();
-+ h_parent = exportfs_decode_fh(h_mnt, (void *)(fh + Fh_tail),
-+ fh_len - Fh_tail, fh[Fh_h_type],
-+ h_acceptable, /*context*/NULL);
-+ lockdep_on();
-+ dentry = h_parent;
-+ if (unlikely(!h_parent || IS_ERR(h_parent))) {
-+ AuWarn1("%s decode_fh failed, %ld\n",
-+ au_sbtype(h_sb), PTR_ERR(h_parent));
++ err = -EINVAL;
++ a_src.inode = file_inode(src);
++ if (unlikely(!S_ISREG(a_src.inode->i_mode)))
++ goto out;
++ a_dst.inode = file_inode(dst);
++ if (unlikely(!S_ISREG(a_dst.inode->i_mode)))
+ goto out;
-+ }
-+ dentry = NULL;
-+ if (unlikely(au_test_anon(h_parent))) {
-+ AuWarn1("%s decode_fh returned a disconnected dentry\n",
-+ au_sbtype(h_sb));
-+ goto out_h_parent;
-+ }
+
-+ dentry = ERR_PTR(-ENOMEM);
-+ pathname = (void *)__get_free_page(GFP_NOFS);
-+ if (unlikely(!pathname))
-+ goto out_h_parent;
++ au_mtx_and_read_lock(a_dst.inode);
++ /*
++ * in order to match the order in di_write_lock2_{child,parent}(),
++ * use f_path.dentry for this comparison.
++ */
++ if (src->f_path.dentry < dst->f_path.dentry) {
++ a_src.h_file = au_read_pre(src, /*keep_fi*/1, AuLsc_FI_1);
++ err = PTR_ERR(a_src.h_file);
++ if (IS_ERR(a_src.h_file))
++ goto out_si;
+
-+ root = sb->s_root;
-+ path.mnt = h_mnt;
-+ di_read_lock_parent(root, !AuLock_IR);
-+ path.dentry = au_h_dptr(root, nsi_lock->bindex);
-+ di_read_unlock(root, !AuLock_IR);
-+ p = au_build_path(h_parent, &path, pathname, PAGE_SIZE, sb);
-+ dentry = (void *)p;
-+ if (IS_ERR(p))
-+ goto out_pathname;
++ wpre.lsc = AuLsc_FI_2;
++ a_dst.h_file = au_write_pre(dst, /*do_ready*/1, &wpre);
++ err = PTR_ERR(a_dst.h_file);
++ if (IS_ERR(a_dst.h_file)) {
++ au_read_post(a_src.inode, a_src.h_file);
++ goto out_si;
++ }
++ } else {
++ wpre.lsc = AuLsc_FI_1;
++ a_dst.h_file = au_write_pre(dst, /*do_ready*/1, &wpre);
++ err = PTR_ERR(a_dst.h_file);
++ if (IS_ERR(a_dst.h_file))
++ goto out_si;
+
-+ si_read_unlock(sb);
-+ err = vfsub_kern_path(p, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path);
-+ dentry = ERR_PTR(err);
-+ if (unlikely(err))
-+ goto out_relock;
++ a_src.h_file = au_read_pre(src, /*keep_fi*/1, AuLsc_FI_2);
++ err = PTR_ERR(a_src.h_file);
++ if (IS_ERR(a_src.h_file)) {
++ au_write_post(a_dst.inode, a_dst.h_file, &wpre,
++ /*written*/0);
++ goto out_si;
++ }
++ }
+
-+ dentry = ERR_PTR(-ENOENT);
-+ AuDebugOn(au_test_anon(path.dentry));
-+ if (unlikely(d_really_is_negative(path.dentry)))
-+ goto out_path;
++ err = -EXDEV;
++ a_src.h_sb = file_inode(a_src.h_file)->i_sb;
++ a_dst.h_sb = file_inode(a_dst.h_file)->i_sb;
++ if (unlikely(a_src.h_sb != a_dst.h_sb)) {
++ AuDbgFile(src);
++ AuDbgFile(dst);
++ goto out_file;
++ }
+
-+ if (ino != d_inode(path.dentry)->i_ino)
-+ dentry = au_lkup_by_ino(&path, ino, /*nsi_lock*/NULL);
-+ else
-+ dentry = dget(path.dentry);
++ err = vfsub_copy_file_range(a_src.h_file, src_pos, a_dst.h_file,
++ dst_pos, len, flags);
+
-+out_path:
-+ path_put(&path);
-+out_relock:
-+ if (unlikely(si_nfsd_read_lock(sb, nsi_lock) < 0))
-+ if (!IS_ERR(dentry)) {
-+ dput(dentry);
-+ dentry = ERR_PTR(-ESTALE);
-+ }
-+out_pathname:
-+ free_page((unsigned long)pathname);
-+out_h_parent:
-+ dput(h_parent);
++out_file:
++ au_write_post(a_dst.inode, a_dst.h_file, &wpre, err);
++ fi_read_unlock(src);
++ au_read_post(a_src.inode, a_src.h_file);
++out_si:
++ si_read_unlock(a_dst.inode->i_sb);
++ inode_unlock(a_dst.inode);
+out:
-+ AuTraceErrPtr(dentry);
-+ return dentry;
++ return err;
++#undef a_src
++#undef a_dst
+}
+
+/* ---------------------------------------------------------------------- */
+
-+static struct dentry *
-+aufs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len,
-+ int fh_type)
-+{
-+ struct dentry *dentry;
-+ __u32 *fh = fid->raw;
-+ struct au_branch *br;
-+ ino_t ino, dir_ino;
-+ struct au_nfsd_si_lock nsi_lock = {
-+ .force_lock = 0
-+ };
-+
-+ dentry = ERR_PTR(-ESTALE);
-+ /* it should never happen, but the file handle is unreliable */
-+ if (unlikely(fh_len < Fh_tail))
-+ goto out;
-+ nsi_lock.sigen = fh[Fh_sigen];
-+ nsi_lock.br_id = fh[Fh_br_id];
-+
-+ /* branch id may be wrapped around */
-+ br = NULL;
-+ if (unlikely(si_nfsd_read_lock(sb, &nsi_lock)))
-+ goto out;
-+ nsi_lock.force_lock = 1;
-+
-+ /* is this inode still cached? */
-+ ino = decode_ino(fh + Fh_ino);
-+ /* it should never happen */
-+ if (unlikely(ino == AUFS_ROOT_INO))
-+ goto out_unlock;
++/*
++ * The locking order around current->mmap_sem.
++ * - in most and regular cases
++ * file I/O syscall -- aufs_read() or something
++ * -- si_rwsem for read -- mmap_sem
++ * (Note that [fdi]i_rwsem are released before mmap_sem).
++ * - in mmap case
++ * mmap(2) -- mmap_sem -- aufs_mmap() -- si_rwsem for read -- [fdi]i_rwsem
++ * This AB-BA order is definitely bad, but is not a problem since "si_rwsem for
++ * read" allows multiple processes to acquire it and [fdi]i_rwsem are not held
++ * in file I/O. Aufs needs to stop lockdep in aufs_mmap() though.
++ * It means that when aufs acquires si_rwsem for write, the process should never
++ * acquire mmap_sem.
++ *
++ * Actually aufs_iterate() holds [fdi]i_rwsem before mmap_sem, but this is not a
++ * problem either since any directory is not able to be mmap-ed.
++ * The similar scenario is applied to aufs_readlink() too.
++ */
+
-+ dir_ino = decode_ino(fh + Fh_dir_ino);
-+ dentry = decode_by_ino(sb, ino, dir_ino);
-+ if (IS_ERR(dentry))
-+ goto out_unlock;
-+ if (dentry)
-+ goto accept;
++#if 0 /* stop calling security_file_mmap() */
++/* cf. linux/include/linux/mman.h: calc_vm_prot_bits() */
++#define AuConv_VM_PROT(f, b) _calc_vm_trans(f, VM_##b, PROT_##b)
+
-+ /* is the parent dir cached? */
-+ br = au_sbr(sb, nsi_lock.bindex);
-+ au_lcnt_inc(&br->br_nfiles);
-+ dentry = decode_by_dir_ino(sb, ino, dir_ino, &nsi_lock);
-+ if (IS_ERR(dentry))
-+ goto out_unlock;
-+ if (dentry)
-+ goto accept;
++static unsigned long au_arch_prot_conv(unsigned long flags)
++{
++ /* currently ppc64 only */
++#ifdef CONFIG_PPC64
++ /* cf. linux/arch/powerpc/include/asm/mman.h */
++ AuDebugOn(arch_calc_vm_prot_bits(-1) != VM_SAO);
++ return AuConv_VM_PROT(flags, SAO);
++#else
++ AuDebugOn(arch_calc_vm_prot_bits(-1));
++ return 0;
++#endif
++}
+
-+ /* lookup path */
-+ dentry = decode_by_path(sb, ino, fh, fh_len, &nsi_lock);
-+ if (IS_ERR(dentry))
-+ goto out_unlock;
-+ if (unlikely(!dentry))
-+ /* todo?: make it ESTALE */
-+ goto out_unlock;
++static unsigned long au_prot_conv(unsigned long flags)
++{
++ return AuConv_VM_PROT(flags, READ)
++ | AuConv_VM_PROT(flags, WRITE)
++ | AuConv_VM_PROT(flags, EXEC)
++ | au_arch_prot_conv(flags);
++}
+
-+accept:
-+ if (!au_digen_test(dentry, au_sigen(sb))
-+ && d_inode(dentry)->i_generation == fh[Fh_igen])
-+ goto out_unlock; /* success */
++/* cf. linux/include/linux/mman.h: calc_vm_flag_bits() */
++#define AuConv_VM_MAP(f, b) _calc_vm_trans(f, VM_##b, MAP_##b)
+
-+ dput(dentry);
-+ dentry = ERR_PTR(-ESTALE);
-+out_unlock:
-+ if (br)
-+ au_lcnt_dec(&br->br_nfiles);
-+ si_read_unlock(sb);
-+out:
-+ AuTraceErrPtr(dentry);
-+ return dentry;
++static unsigned long au_flag_conv(unsigned long flags)
++{
++ return AuConv_VM_MAP(flags, GROWSDOWN)
++ | AuConv_VM_MAP(flags, DENYWRITE)
++ | AuConv_VM_MAP(flags, LOCKED);
+}
++#endif
+
-+#if 0 /* reserved for future use */
-+/* support subtreecheck option */
-+static struct dentry *aufs_fh_to_parent(struct super_block *sb, struct fid *fid,
-+ int fh_len, int fh_type)
++static int aufs_mmap(struct file *file, struct vm_area_struct *vma)
+{
-+ struct dentry *parent;
-+ __u32 *fh = fid->raw;
-+ ino_t dir_ino;
++ int err;
++ const unsigned char wlock
++ = (file->f_mode & FMODE_WRITE) && (vma->vm_flags & VM_SHARED);
++ struct super_block *sb;
++ struct file *h_file;
++ struct inode *inode;
+
-+ dir_ino = decode_ino(fh + Fh_dir_ino);
-+ parent = decode_by_ino(sb, dir_ino, 0);
-+ if (IS_ERR(parent))
++ AuDbgVmRegion(file, vma);
++
++ inode = file_inode(file);
++ sb = inode->i_sb;
++ lockdep_off();
++ si_read_lock(sb, AuLock_NOPLMW);
++
++ h_file = au_write_pre(file, wlock, /*wpre*/NULL);
++ lockdep_on();
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
+ goto out;
-+ if (!parent)
-+ parent = decode_by_path(sb, au_br_index(sb, fh[Fh_br_id]),
-+ dir_ino, fh, fh_len);
+
++ err = 0;
++ au_set_mmapped(file);
++ au_vm_file_reset(vma, h_file);
++ /*
++ * we cannot call security_mmap_file() here since it may acquire
++ * mmap_sem or i_mutex.
++ *
++ * err = security_mmap_file(h_file, au_prot_conv(vma->vm_flags),
++ * au_flag_conv(vma->vm_flags));
++ */
++ if (!err)
++ err = call_mmap(h_file, vma);
++ if (!err) {
++ au_vm_prfile_set(vma, file);
++ fsstack_copy_attr_atime(inode, file_inode(h_file));
++ goto out_fput; /* success */
++ }
++ au_unset_mmapped(file);
++ au_vm_file_reset(vma, file);
++
++out_fput:
++ lockdep_off();
++ ii_write_unlock(inode);
++ lockdep_on();
++ fput(h_file);
+out:
-+ AuTraceErrPtr(parent);
-+ return parent;
++ lockdep_off();
++ si_read_unlock(sb);
++ lockdep_on();
++ AuTraceErr(err);
++ return err;
+}
-+#endif
+
+/* ---------------------------------------------------------------------- */
+
-+static int aufs_encode_fh(struct inode *inode, __u32 *fh, int *max_len,
-+ struct inode *dir)
++static int aufs_fsync_nondir(struct file *file, loff_t start, loff_t end,
++ int datasync)
+{
+ int err;
-+ aufs_bindex_t bindex;
-+ struct super_block *sb, *h_sb;
-+ struct dentry *dentry, *parent, *h_parent;
-+ struct inode *h_dir;
-+ struct au_branch *br;
++ struct au_write_pre wpre;
++ struct inode *inode;
++ struct file *h_file;
+
-+ err = -ENOSPC;
-+ if (unlikely(*max_len <= Fh_tail)) {
-+ AuWarn1("NFSv2 client (max_len %d)?\n", *max_len);
++ err = 0; /* -EBADF; */ /* posix? */
++ if (unlikely(!(file->f_mode & FMODE_WRITE)))
+ goto out;
-+ }
+
-+ err = FILEID_ROOT;
-+ if (inode->i_ino == AUFS_ROOT_INO) {
-+ AuDebugOn(inode->i_ino != AUFS_ROOT_INO);
-+ goto out;
-+ }
++ inode = file_inode(file);
++ au_mtx_and_read_lock(inode);
+
-+ h_parent = NULL;
-+ sb = inode->i_sb;
-+ err = si_read_lock(sb, AuLock_FLUSH);
-+ if (unlikely(err))
-+ goto out;
++ wpre.lsc = 0;
++ h_file = au_write_pre(file, /*do_ready*/1, &wpre);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
++ goto out_unlock;
+
-+#ifdef CONFIG_AUFS_DEBUG
-+ if (unlikely(!au_opt_test(au_mntflags(sb), XINO)))
-+ AuWarn1("NFS-exporting requires xino\n");
-+#endif
-+ err = -EIO;
-+ parent = NULL;
-+ ii_read_lock_child(inode);
-+ bindex = au_ibtop(inode);
-+ if (!dir) {
-+ dentry = d_find_any_alias(inode);
-+ if (unlikely(!dentry))
-+ goto out_unlock;
-+ AuDebugOn(au_test_anon(dentry));
-+ parent = dget_parent(dentry);
-+ dput(dentry);
-+ if (unlikely(!parent))
-+ goto out_unlock;
-+ if (d_really_is_positive(parent))
-+ dir = d_inode(parent);
-+ }
++ err = vfsub_fsync(h_file, &h_file->f_path, datasync);
++ au_write_post(inode, h_file, &wpre, /*written*/0);
+
-+ ii_read_lock_parent(dir);
-+ h_dir = au_h_iptr(dir, bindex);
-+ ii_read_unlock(dir);
-+ if (unlikely(!h_dir))
-+ goto out_parent;
-+ h_parent = d_find_any_alias(h_dir);
-+ if (unlikely(!h_parent))
-+ goto out_hparent;
++out_unlock:
++ si_read_unlock(inode->i_sb);
++ inode_unlock(inode);
++out:
++ return err;
++}
+
-+ err = -EPERM;
-+ br = au_sbr(sb, bindex);
-+ h_sb = au_br_sb(br);
-+ if (unlikely(!h_sb->s_export_op)) {
-+ AuErr1("%s branch is not exportable\n", au_sbtype(h_sb));
-+ goto out_hparent;
-+ }
++static int aufs_fasync(int fd, struct file *file, int flag)
++{
++ int err;
++ struct file *h_file;
++ struct super_block *sb;
+
-+ fh[Fh_br_id] = br->br_id;
-+ fh[Fh_sigen] = au_sigen(sb);
-+ encode_ino(fh + Fh_ino, inode->i_ino);
-+ encode_ino(fh + Fh_dir_ino, dir->i_ino);
-+ fh[Fh_igen] = inode->i_generation;
++ sb = file->f_path.dentry->d_sb;
++ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
+
-+ *max_len -= Fh_tail;
-+ fh[Fh_h_type] = exportfs_encode_fh(h_parent, (void *)(fh + Fh_tail),
-+ max_len,
-+ /*connectable or subtreecheck*/0);
-+ err = fh[Fh_h_type];
-+ *max_len += Fh_tail;
-+ /* todo: macros? */
-+ if (err != FILEID_INVALID)
-+ err = 99;
-+ else
-+ AuWarn1("%s encode_fh failed\n", au_sbtype(h_sb));
++ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
++ goto out;
++
++ if (h_file->f_op->fasync)
++ err = h_file->f_op->fasync(fd, h_file, flag);
++ fput(h_file); /* instead of au_read_post() */
+
-+out_hparent:
-+ dput(h_parent);
-+out_parent:
-+ dput(parent);
-+out_unlock:
-+ ii_read_unlock(inode);
-+ si_read_unlock(sb);
+out:
-+ if (unlikely(err < 0))
-+ err = FILEID_INVALID;
++ si_read_unlock(sb);
+ return err;
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+static int aufs_commit_metadata(struct inode *inode)
++static int aufs_setfl(struct file *file, unsigned long arg)
+{
+ int err;
-+ aufs_bindex_t bindex;
++ struct file *h_file;
+ struct super_block *sb;
-+ struct inode *h_inode;
-+ int (*f)(struct inode *inode);
+
-+ sb = inode->i_sb;
++ sb = file->f_path.dentry->d_sb;
+ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
-+ ii_write_lock_child(inode);
-+ bindex = au_ibtop(inode);
-+ AuDebugOn(bindex < 0);
-+ h_inode = au_h_iptr(inode, bindex);
+
-+ f = h_inode->i_sb->s_export_op->commit_metadata;
-+ if (f)
-+ err = f(h_inode);
-+ else
-+ err = sync_inode_metadata(h_inode, /*wait*/1);
++ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
++ goto out;
++
++ /* stop calling h_file->fasync */
++ arg |= vfsub_file_flags(file) & FASYNC;
++ err = setfl(/*unused fd*/-1, h_file, arg);
++ fput(h_file); /* instead of au_read_post() */
+
-+ au_cpup_attr_timesizes(inode);
-+ ii_write_unlock(inode);
++out:
+ si_read_unlock(sb);
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
-+static struct export_operations aufs_export_op = {
-+ .fh_to_dentry = aufs_fh_to_dentry,
-+ /* .fh_to_parent = aufs_fh_to_parent, */
-+ .encode_fh = aufs_encode_fh,
-+ .commit_metadata = aufs_commit_metadata
-+};
++const struct file_operations aufs_file_fop = {
++ .owner = THIS_MODULE,
+
-+void au_export_init(struct super_block *sb)
-+{
-+ struct au_sbinfo *sbinfo;
-+ __u32 u;
++ .llseek = default_llseek,
+
-+ BUILD_BUG_ON_MSG(IS_BUILTIN(CONFIG_AUFS_FS)
-+ && IS_MODULE(CONFIG_EXPORTFS),
-+ AUFS_NAME ": unsupported configuration "
-+ "CONFIG_EXPORTFS=m and CONFIG_AUFS_FS=y");
++ .read_iter = aufs_read_iter,
++ .write_iter = aufs_write_iter,
+
-+ sb->s_export_op = &aufs_export_op;
-+ sbinfo = au_sbi(sb);
-+ sbinfo->si_xigen = NULL;
-+ get_random_bytes(&u, sizeof(u));
-+ BUILD_BUG_ON(sizeof(u) != sizeof(int));
-+ atomic_set(&sbinfo->si_xigen_next, u);
-+}
-diff -urN /usr/share/empty/fs/aufs/fhsm.c linux/fs/aufs/fhsm.c
---- /usr/share/empty/fs/aufs/fhsm.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/fhsm.c 2022-11-05 23:02:18.962555950 +0100
++#ifdef CONFIG_AUFS_POLL
++ .poll = aufs_poll,
++#endif
++ .unlocked_ioctl = aufs_ioctl_nondir,
++#ifdef CONFIG_COMPAT
++ .compat_ioctl = aufs_compat_ioctl_nondir,
++#endif
++ .mmap = aufs_mmap,
++ .open = aufs_open_nondir,
++ .flush = aufs_flush_nondir,
++ .release = aufs_release_nondir,
++ .fsync = aufs_fsync_nondir,
++ .fasync = aufs_fasync,
++ .setfl = aufs_setfl,
++ .splice_write = aufs_splice_write,
++ .splice_read = aufs_splice_read,
++#if 0 /* reserved for future use */
++ .aio_splice_write = aufs_aio_splice_write,
++ .aio_splice_read = aufs_aio_splice_read,
++#endif
++ .fallocate = aufs_fallocate,
++ .copy_file_range = aufs_copy_file_range
++};
+diff --git a/fs/aufs/fhsm.c b/fs/aufs/fhsm.c
+new file mode 100644
+index 00000000000000..91262fbbbfaed0
+--- /dev/null
++++ b/fs/aufs/fhsm.c
@@ -0,0 +1,426 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ if (u != AUFS_FHSM_CACHE_DEF_SEC)
+ seq_printf(seq, ",fhsm_sec=%u", u);
+}
-diff -urN /usr/share/empty/fs/aufs/file.c linux/fs/aufs/file.c
---- /usr/share/empty/fs/aufs/file.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/file.c 2023-10-31 09:31:04.199880750 +0100
+diff --git a/fs/aufs/file.c b/fs/aufs/file.c
+new file mode 100644
+index 00000000000000..76ad444328db50
+--- /dev/null
++++ b/fs/aufs/file.c
@@ -0,0 +1,865 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ args->h_file);
+ lockdep_on();
+ di_read_unlock(dentry, AuLock_IR);
-+ }
-+ }
-+
-+ finfo = au_fi(file);
-+ if (!err) {
-+ finfo->fi_file = file;
-+ au_hbl_add(&finfo->fi_hlist,
-+ &au_sbi(file->f_path.dentry->d_sb)->si_files);
-+ }
-+ if (!aopen)
-+ fi_write_unlock(file);
-+ else {
-+ lockdep_off();
-+ fi_write_unlock(file);
-+ lockdep_on();
-+ }
-+ if (unlikely(err)) {
-+ finfo->fi_hdir = NULL;
-+ au_finfo_fin(file);
-+ }
-+
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+int au_reopen_nondir(struct file *file)
-+{
-+ int err;
-+ aufs_bindex_t btop;
-+ struct dentry *dentry;
-+ struct au_branch *br;
-+ struct file *h_file, *h_file_tmp;
-+
-+ dentry = file->f_path.dentry;
-+ btop = au_dbtop(dentry);
-+ br = au_sbr(dentry->d_sb, btop);
-+ h_file_tmp = NULL;
-+ if (au_fbtop(file) == btop) {
-+ h_file = au_hf_top(file);
-+ if (file->f_mode == h_file->f_mode)
-+ return 0; /* success */
-+ h_file_tmp = h_file;
-+ get_file(h_file_tmp);
-+ au_lcnt_inc(&br->br_nfiles);
-+ au_set_h_fptr(file, btop, NULL);
-+ }
-+ AuDebugOn(au_fi(file)->fi_hdir);
-+ /*
-+ * it can happen
-+ * file exists on both of rw and ro
-+ * open --> dbtop and fbtop are both 0
-+ * prepend a branch as rw, "rw" become ro
-+ * remove rw/file
-+ * delete the top branch, "rw" becomes rw again
-+ * --> dbtop is 1, fbtop is still 0
-+ * write --> fbtop is 0 but dbtop is 1
-+ */
-+ /* AuDebugOn(au_fbtop(file) < btop); */
-+
-+ h_file = au_h_open(dentry, btop, vfsub_file_flags(file) & ~O_TRUNC,
-+ file, /*force_wr*/0);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file)) {
-+ if (h_file_tmp) {
-+ /* revert */
-+ au_set_h_fptr(file, btop, h_file_tmp);
-+ h_file_tmp = NULL;
-+ }
-+ goto out; /* todo: close all? */
-+ }
-+
-+ err = 0;
-+ au_set_fbtop(file, btop);
-+ au_set_h_fptr(file, btop, h_file);
-+ au_update_figen(file);
-+ /* todo: necessary? */
-+ /* file->f_ra = h_file->f_ra; */
-+
-+out:
-+ if (h_file_tmp) {
-+ fput(h_file_tmp);
-+ au_lcnt_dec(&br->br_nfiles);
-+ }
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int au_reopen_wh(struct file *file, aufs_bindex_t btgt,
-+ struct dentry *hi_wh)
-+{
-+ int err;
-+ aufs_bindex_t btop;
-+ struct au_dinfo *dinfo;
-+ struct dentry *h_dentry;
-+ struct au_hdentry *hdp;
-+
-+ dinfo = au_di(file->f_path.dentry);
-+ AuRwMustWriteLock(&dinfo->di_rwsem);
-+
-+ btop = dinfo->di_btop;
-+ dinfo->di_btop = btgt;
-+ hdp = au_hdentry(dinfo, btgt);
-+ h_dentry = hdp->hd_dentry;
-+ hdp->hd_dentry = hi_wh;
-+ err = au_reopen_nondir(file);
-+ hdp->hd_dentry = h_dentry;
-+ dinfo->di_btop = btop;
-+
-+ return err;
-+}
-+
-+static int au_ready_to_write_wh(struct file *file, loff_t len,
-+ aufs_bindex_t bcpup, struct au_pin *pin)
-+{
-+ int err;
-+ struct inode *inode, *h_inode;
-+ struct dentry *h_dentry, *hi_wh;
-+ struct au_cp_generic cpg = {
-+ .dentry = file->f_path.dentry,
-+ .bdst = bcpup,
-+ .bsrc = -1,
-+ .len = len,
-+ .pin = pin
-+ };
-+
-+ au_update_dbtop(cpg.dentry);
-+ inode = d_inode(cpg.dentry);
-+ h_inode = NULL;
-+ if (au_dbtop(cpg.dentry) <= bcpup
-+ && au_dbbot(cpg.dentry) >= bcpup) {
-+ h_dentry = au_h_dptr(cpg.dentry, bcpup);
-+ if (h_dentry && d_is_positive(h_dentry))
-+ h_inode = d_inode(h_dentry);
-+ }
-+ hi_wh = au_hi_wh(inode, bcpup);
-+ if (!hi_wh && !h_inode)
-+ err = au_sio_cpup_wh(&cpg, file);
-+ else
-+ /* already copied-up after unlink */
-+ err = au_reopen_wh(file, bcpup, hi_wh);
-+
-+ if (!err
-+ && (inode->i_nlink > 1
-+ || (inode->i_state & I_LINKABLE))
-+ && au_opt_test(au_mntflags(cpg.dentry->d_sb), PLINK))
-+ au_plink_append(inode, bcpup, au_h_dptr(cpg.dentry, bcpup));
-+
-+ return err;
-+}
-+
-+/*
-+ * prepare the @file for writing.
-+ */
-+int au_ready_to_write(struct file *file, loff_t len, struct au_pin *pin)
-+{
-+ int err;
-+ aufs_bindex_t dbtop;
-+ struct dentry *parent;
-+ struct inode *inode;
-+ struct super_block *sb;
-+ struct file *h_file;
-+ struct au_cp_generic cpg = {
-+ .dentry = file->f_path.dentry,
-+ .bdst = -1,
-+ .bsrc = -1,
-+ .len = len,
-+ .pin = pin,
-+ .flags = AuCpup_DTIME
-+ };
-+
-+ sb = cpg.dentry->d_sb;
-+ inode = d_inode(cpg.dentry);
-+ cpg.bsrc = au_fbtop(file);
-+ err = au_test_ro(sb, cpg.bsrc, inode);
-+ if (!err && (au_hf_top(file)->f_mode & FMODE_WRITE)) {
-+ err = au_pin(pin, cpg.dentry, cpg.bsrc, AuOpt_UDBA_NONE,
-+ /*flags*/0);
-+ goto out;
-+ }
-+
-+ /* need to cpup or reopen */
-+ parent = dget_parent(cpg.dentry);
-+ di_write_lock_parent(parent);
-+ err = AuWbrCopyup(au_sbi(sb), cpg.dentry);
-+ cpg.bdst = err;
-+ if (unlikely(err < 0))
-+ goto out_dgrade;
-+ err = 0;
-+
-+ if (!d_unhashed(cpg.dentry) && !au_h_dptr(parent, cpg.bdst)) {
-+ err = au_cpup_dirs(cpg.dentry, cpg.bdst);
-+ if (unlikely(err))
-+ goto out_dgrade;
-+ }
-+
-+ err = au_pin(pin, cpg.dentry, cpg.bdst, AuOpt_UDBA_NONE,
-+ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
-+ if (unlikely(err))
-+ goto out_dgrade;
-+
-+ dbtop = au_dbtop(cpg.dentry);
-+ if (dbtop <= cpg.bdst)
-+ cpg.bsrc = cpg.bdst;
-+
-+ if (dbtop <= cpg.bdst /* just reopen */
-+ || !d_unhashed(cpg.dentry) /* copyup and reopen */
-+ ) {
-+ h_file = au_h_open_pre(cpg.dentry, cpg.bsrc, /*force_wr*/0);
-+ if (IS_ERR(h_file))
-+ err = PTR_ERR(h_file);
-+ else {
-+ di_downgrade_lock(parent, AuLock_IR);
-+ if (dbtop > cpg.bdst)
-+ err = au_sio_cpup_simple(&cpg);
-+ if (!err)
-+ err = au_reopen_nondir(file);
-+ au_h_open_post(cpg.dentry, cpg.bsrc, h_file);
-+ }
-+ } else { /* copyup as wh and reopen */
-+ /*
-+ * since writable hfsplus branch is not supported,
-+ * h_open_pre/post() are unnecessary.
-+ */
-+ err = au_ready_to_write_wh(file, len, cpg.bdst, pin);
-+ di_downgrade_lock(parent, AuLock_IR);
-+ }
-+
-+ if (!err) {
-+ au_pin_set_parent_lflag(pin, /*lflag*/0);
-+ goto out_dput; /* success */
-+ }
-+ au_unpin(pin);
-+ goto out_unlock;
-+
-+out_dgrade:
-+ di_downgrade_lock(parent, AuLock_IR);
-+out_unlock:
-+ di_read_unlock(parent, AuLock_IR);
-+out_dput:
-+ dput(parent);
-+out:
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+int au_do_flush(struct file *file, fl_owner_t id,
-+ int (*flush)(struct file *file, fl_owner_t id))
-+{
-+ int err;
-+ struct super_block *sb;
-+ struct inode *inode;
-+
-+ inode = file_inode(file);
-+ sb = inode->i_sb;
-+ si_noflush_read_lock(sb);
-+ fi_read_lock(file);
-+ ii_read_lock_child(inode);
-+
-+ err = flush(file, id);
-+ au_cpup_attr_timesizes(inode);
-+
-+ ii_read_unlock(inode);
-+ fi_read_unlock(file);
-+ si_read_unlock(sb);
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int au_file_refresh_by_inode(struct file *file, int *need_reopen)
-+{
-+ int err;
-+ struct au_pin pin;
-+ struct au_finfo *finfo;
-+ struct dentry *parent, *hi_wh;
-+ struct inode *inode;
-+ struct super_block *sb;
-+ struct au_cp_generic cpg = {
-+ .dentry = file->f_path.dentry,
-+ .bdst = -1,
-+ .bsrc = -1,
-+ .len = -1,
-+ .pin = &pin,
-+ .flags = AuCpup_DTIME
-+ };
-+
-+ FiMustWriteLock(file);
-+
-+ err = 0;
-+ finfo = au_fi(file);
-+ sb = cpg.dentry->d_sb;
-+ inode = d_inode(cpg.dentry);
-+ cpg.bdst = au_ibtop(inode);
-+ if (cpg.bdst == finfo->fi_btop || IS_ROOT(cpg.dentry))
-+ goto out;
-+
-+ parent = dget_parent(cpg.dentry);
-+ if (au_test_ro(sb, cpg.bdst, inode)) {
-+ di_read_lock_parent(parent, !AuLock_IR);
-+ err = AuWbrCopyup(au_sbi(sb), cpg.dentry);
-+ cpg.bdst = err;
-+ di_read_unlock(parent, !AuLock_IR);
-+ if (unlikely(err < 0))
-+ goto out_parent;
-+ err = 0;
-+ }
-+
-+ di_read_lock_parent(parent, AuLock_IR);
-+ hi_wh = au_hi_wh(inode, cpg.bdst);
-+ if (!S_ISDIR(inode->i_mode)
-+ && au_opt_test(au_mntflags(sb), PLINK)
-+ && au_plink_test(inode)
-+ && !d_unhashed(cpg.dentry)
-+ && cpg.bdst < au_dbtop(cpg.dentry)) {
-+ err = au_test_and_cpup_dirs(cpg.dentry, cpg.bdst);
-+ if (unlikely(err))
-+ goto out_unlock;
-+
-+ /* always superio. */
-+ err = au_pin(&pin, cpg.dentry, cpg.bdst, AuOpt_UDBA_NONE,
-+ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
-+ if (!err) {
-+ err = au_sio_cpup_simple(&cpg);
-+ au_unpin(&pin);
-+ }
-+ } else if (hi_wh) {
-+ /* already copied-up after unlink */
-+ err = au_reopen_wh(file, cpg.bdst, hi_wh);
-+ *need_reopen = 0;
-+ }
-+
-+out_unlock:
-+ di_read_unlock(parent, AuLock_IR);
-+out_parent:
-+ dput(parent);
-+out:
-+ return err;
-+}
-+
-+static void au_do_refresh_dir(struct file *file)
-+{
-+ aufs_bindex_t bindex, bbot, new_bindex, brid;
-+ struct au_hfile *p, tmp, *q;
-+ struct au_finfo *finfo;
-+ struct super_block *sb;
-+ struct au_fidir *fidir;
-+
-+ FiMustWriteLock(file);
-+
-+ sb = file->f_path.dentry->d_sb;
-+ finfo = au_fi(file);
-+ fidir = finfo->fi_hdir;
-+ AuDebugOn(!fidir);
-+ p = fidir->fd_hfile + finfo->fi_btop;
-+ brid = p->hf_br->br_id;
-+ bbot = fidir->fd_bbot;
-+ for (bindex = finfo->fi_btop; bindex <= bbot; bindex++, p++) {
-+ if (!p->hf_file)
-+ continue;
-+
-+ new_bindex = au_br_index(sb, p->hf_br->br_id);
-+ if (new_bindex == bindex)
-+ continue;
-+ if (new_bindex < 0) {
-+ au_set_h_fptr(file, bindex, NULL);
-+ continue;
-+ }
-+
-+ /* swap two lower inode, and loop again */
-+ q = fidir->fd_hfile + new_bindex;
-+ tmp = *q;
-+ *q = *p;
-+ *p = tmp;
-+ if (tmp.hf_file) {
-+ bindex--;
-+ p--;
-+ }
-+ }
-+
-+ p = fidir->fd_hfile;
-+ if (!au_test_mmapped(file) && !d_unlinked(file->f_path.dentry)) {
-+ bbot = au_sbbot(sb);
-+ for (finfo->fi_btop = 0; finfo->fi_btop <= bbot;
-+ finfo->fi_btop++, p++)
-+ if (p->hf_file) {
-+ if (file_inode(p->hf_file))
-+ break;
-+ au_hfput(p, /*execed*/0);
-+ }
-+ } else {
-+ bbot = au_br_index(sb, brid);
-+ for (finfo->fi_btop = 0; finfo->fi_btop < bbot;
-+ finfo->fi_btop++, p++)
-+ if (p->hf_file)
-+ au_hfput(p, /*execed*/0);
-+ bbot = au_sbbot(sb);
-+ }
-+
-+ p = fidir->fd_hfile + bbot;
-+ for (fidir->fd_bbot = bbot; fidir->fd_bbot >= finfo->fi_btop;
-+ fidir->fd_bbot--, p--)
-+ if (p->hf_file) {
-+ if (file_inode(p->hf_file))
-+ break;
-+ au_hfput(p, /*execed*/0);
-+ }
-+ AuDebugOn(fidir->fd_bbot < finfo->fi_btop);
-+}
-+
-+/*
-+ * after branch manipulating, refresh the file.
-+ */
-+static int refresh_file(struct file *file, int (*reopen)(struct file *file))
-+{
-+ int err, need_reopen, nbr;
-+ aufs_bindex_t bbot, bindex;
-+ struct dentry *dentry;
-+ struct super_block *sb;
-+ struct au_finfo *finfo;
-+ struct au_hfile *hfile;
-+
-+ dentry = file->f_path.dentry;
-+ sb = dentry->d_sb;
-+ nbr = au_sbbot(sb) + 1;
-+ finfo = au_fi(file);
-+ if (!finfo->fi_hdir) {
-+ hfile = &finfo->fi_htop;
-+ AuDebugOn(!hfile->hf_file);
-+ bindex = au_br_index(sb, hfile->hf_br->br_id);
-+ AuDebugOn(bindex < 0);
-+ if (bindex != finfo->fi_btop)
-+ au_set_fbtop(file, bindex);
-+ } else {
-+ err = au_fidir_realloc(finfo, nbr, /*may_shrink*/0);
-+ if (unlikely(err))
-+ goto out;
-+ au_do_refresh_dir(file);
-+ }
-+
-+ err = 0;
-+ need_reopen = 1;
-+ if (!au_test_mmapped(file))
-+ err = au_file_refresh_by_inode(file, &need_reopen);
-+ if (finfo->fi_hdir)
-+ /* harmless if err */
-+ au_fidir_realloc(finfo, nbr, /*may_shrink*/1);
-+ if (!err && need_reopen && !d_unlinked(dentry))
-+ err = reopen(file);
-+ if (!err) {
-+ au_update_figen(file);
-+ goto out; /* success */
++ }
+ }
+
-+ /* error, close all lower files */
-+ if (finfo->fi_hdir) {
-+ bbot = au_fbbot_dir(file);
-+ for (bindex = au_fbtop(file); bindex <= bbot; bindex++)
-+ au_set_h_fptr(file, bindex, NULL);
++ finfo = au_fi(file);
++ if (!err) {
++ finfo->fi_file = file;
++ au_hbl_add(&finfo->fi_hlist,
++ &au_sbi(file->f_path.dentry->d_sb)->si_files);
++ }
++ if (!aopen)
++ fi_write_unlock(file);
++ else {
++ lockdep_off();
++ fi_write_unlock(file);
++ lockdep_on();
++ }
++ if (unlikely(err)) {
++ finfo->fi_hdir = NULL;
++ au_finfo_fin(file);
+ }
+
+out:
++ AuTraceErr(err);
+ return err;
+}
+
-+/* common function to regular file and dir */
-+int au_reval_and_lock_fdi(struct file *file, int (*reopen)(struct file *file),
-+ int wlock, unsigned int fi_lsc)
++int au_reopen_nondir(struct file *file)
+{
+ int err;
-+ unsigned int sigen, figen;
+ aufs_bindex_t btop;
-+ unsigned char pseudo_link;
+ struct dentry *dentry;
-+ struct inode *inode;
++ struct au_branch *br;
++ struct file *h_file, *h_file_tmp;
+
-+ err = 0;
+ dentry = file->f_path.dentry;
-+ inode = d_inode(dentry);
-+ sigen = au_sigen(dentry->d_sb);
-+ fi_write_lock_nested(file, fi_lsc);
-+ figen = au_figen(file);
-+ if (!fi_lsc)
-+ di_write_lock_child(dentry);
-+ else
-+ di_write_lock_child2(dentry);
+ btop = au_dbtop(dentry);
-+ pseudo_link = (btop != au_ibtop(inode));
-+ if (sigen == figen && !pseudo_link && au_fbtop(file) == btop) {
-+ if (!wlock) {
-+ di_downgrade_lock(dentry, AuLock_IR);
-+ fi_downgrade_lock(file);
-+ }
-+ goto out; /* success */
-+ }
-+
-+ AuDbg("sigen %d, figen %d\n", sigen, figen);
-+ if (au_digen_test(dentry, sigen)) {
-+ err = au_reval_dpath(dentry, sigen);
-+ AuDebugOn(!err && au_digen_test(dentry, sigen));
++ br = au_sbr(dentry->d_sb, btop);
++ h_file_tmp = NULL;
++ if (au_fbtop(file) == btop) {
++ h_file = au_hf_top(file);
++ if (file->f_mode == h_file->f_mode)
++ return 0; /* success */
++ h_file_tmp = h_file;
++ get_file(h_file_tmp);
++ au_lcnt_inc(&br->br_nfiles);
++ au_set_h_fptr(file, btop, NULL);
+ }
++ AuDebugOn(au_fi(file)->fi_hdir);
++ /*
++ * it can happen
++ * file exists on both of rw and ro
++ * open --> dbtop and fbtop are both 0
++ * prepend a branch as rw, "rw" become ro
++ * remove rw/file
++ * delete the top branch, "rw" becomes rw again
++ * --> dbtop is 1, fbtop is still 0
++ * write --> fbtop is 0 but dbtop is 1
++ */
++ /* AuDebugOn(au_fbtop(file) < btop); */
+
-+ if (!err)
-+ err = refresh_file(file, reopen);
-+ if (!err) {
-+ if (!wlock) {
-+ di_downgrade_lock(dentry, AuLock_IR);
-+ fi_downgrade_lock(file);
++ h_file = au_h_open(dentry, btop, vfsub_file_flags(file) & ~O_TRUNC,
++ file, /*force_wr*/0);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file)) {
++ if (h_file_tmp) {
++ /* revert */
++ au_set_h_fptr(file, btop, h_file_tmp);
++ h_file_tmp = NULL;
+ }
-+ } else {
-+ di_write_unlock(dentry);
-+ fi_write_unlock(file);
++ goto out; /* todo: close all? */
+ }
+
++ err = 0;
++ au_set_fbtop(file, btop);
++ au_set_h_fptr(file, btop, h_file);
++ au_update_figen(file);
++ /* todo: necessary? */
++ /* file->f_ra = h_file->f_ra; */
++
+out:
++ if (h_file_tmp) {
++ fput(h_file_tmp);
++ au_lcnt_dec(&br->br_nfiles);
++ }
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
-+/* cf. aufs_nopage() */
-+/* for madvise(2) */
-+static int aufs_read_folio(struct file *file __maybe_unused, struct folio *folio)
++static int au_reopen_wh(struct file *file, aufs_bindex_t btgt,
++ struct dentry *hi_wh)
+{
-+ folio_unlock(folio);
-+ return 0;
-+}
-+
-+/* it will never be called, but necessary to support O_DIRECT */
-+static ssize_t aufs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
-+{ BUG(); return 0; }
-+
-+/* they will never be called. */
-+#ifdef CONFIG_AUFS_DEBUG
-+static int aufs_write_begin(struct file *file, struct address_space *mapping,
-+ loff_t pos, unsigned len,
-+ struct page **pagep, void **fsdata)
-+{ AuUnsupport(); return 0; }
-+static int aufs_write_end(struct file *file, struct address_space *mapping,
-+ loff_t pos, unsigned len, unsigned copied,
-+ struct page *page, void *fsdata)
-+{ AuUnsupport(); return 0; }
-+static int aufs_writepage(struct page *page, struct writeback_control *wbc)
-+{ AuUnsupport(); return 0; }
-+
-+static bool aufs_dirty_folio(struct address_space *mapping, struct folio *folio)
-+{ AuUnsupport(); return true; }
-+static void aufs_invalidate_folio(struct folio *folio, size_t offset, size_t len)
-+{ AuUnsupport(); }
-+static bool aufs_release_folio(struct folio *folio, gfp_t gfp)
-+{ AuUnsupport(); return true; }
-+#if 0 /* called by memory compaction regardless file */
-+static int aufs_migrate_folio(struct address_space *mapping, struct folio *dst,
-+ struct folio *src, enum migrate_mode mode)
-+{ AuUnsupport(); return 0; }
-+#endif
-+static int aufs_launder_folio(struct folio *folio)
-+{ AuUnsupport(); return 0; }
-+static bool aufs_is_partially_uptodate(struct folio *folio, size_t from,
-+ size_t count)
-+{ AuUnsupport(); return true; }
-+static void aufs_is_dirty_writeback(struct folio *folio, bool *dirty,
-+ bool *writeback)
-+{ AuUnsupport(); }
-+static int aufs_error_remove_page(struct address_space *mapping,
-+ struct page *page)
-+{ AuUnsupport(); return 0; }
-+static int aufs_swap_activate(struct swap_info_struct *sis, struct file *file,
-+ sector_t *span)
-+{ AuUnsupport(); return 0; }
-+static void aufs_swap_deactivate(struct file *file)
-+{ AuUnsupport(); }
-+static int aufs_swap_rw(struct kiocb *iocb, struct iov_iter *iter)
-+{ AuUnsupport(); return 0; }
-+#endif /* CONFIG_AUFS_DEBUG */
-+
-+const struct address_space_operations aufs_aop = {
-+ .read_folio = aufs_read_folio,
-+ .direct_IO = aufs_direct_IO,
-+#ifdef CONFIG_AUFS_DEBUG
-+ .writepage = aufs_writepage,
-+ /* no writepages, because of writepage */
-+ .dirty_folio = aufs_dirty_folio,
-+ /* no readpages, because of readpage */
-+ .write_begin = aufs_write_begin,
-+ .write_end = aufs_write_end,
-+ /* no bmap, no block device */
-+ .invalidate_folio = aufs_invalidate_folio,
-+ .release_folio = aufs_release_folio,
-+ /* is fallback_migrate_page ok? */
-+ /* .migrate_folio = aufs_migrate_folio, */
-+ .launder_folio = aufs_launder_folio,
-+ .is_partially_uptodate = aufs_is_partially_uptodate,
-+ .is_dirty_writeback = aufs_is_dirty_writeback,
-+ .error_remove_page = aufs_error_remove_page,
-+ .swap_activate = aufs_swap_activate,
-+ .swap_deactivate = aufs_swap_deactivate,
-+ .swap_rw = aufs_swap_rw
-+#endif /* CONFIG_AUFS_DEBUG */
-+};
-diff -urN /usr/share/empty/fs/aufs/file.h linux/fs/aufs/file.h
---- /usr/share/empty/fs/aufs/file.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/file.h 2022-11-05 23:02:18.965889284 +0100
-@@ -0,0 +1,342 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2005-2022 Junjiro R. Okajima
-+ *
-+ * This program 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/>.
-+ */
-+
-+/*
-+ * file operations
-+ */
-+
-+#ifndef __AUFS_FILE_H__
-+#define __AUFS_FILE_H__
-+
-+#ifdef __KERNEL__
-+
-+#include <linux/file.h>
-+#include <linux/fs.h>
-+#include <linux/mm_types.h>
-+#include <linux/poll.h>
-+#include "rwsem.h"
++ int err;
++ aufs_bindex_t btop;
++ struct au_dinfo *dinfo;
++ struct dentry *h_dentry;
++ struct au_hdentry *hdp;
+
-+struct au_branch;
-+struct au_hfile {
-+ struct file *hf_file;
-+ struct au_branch *hf_br;
-+};
++ dinfo = au_di(file->f_path.dentry);
++ AuRwMustWriteLock(&dinfo->di_rwsem);
+
-+struct au_vdir;
-+struct au_fidir {
-+ aufs_bindex_t fd_bbot;
-+ aufs_bindex_t fd_nent;
-+ struct au_vdir *fd_vdir_cache;
-+ struct au_hfile fd_hfile[];
-+};
++ btop = dinfo->di_btop;
++ dinfo->di_btop = btgt;
++ hdp = au_hdentry(dinfo, btgt);
++ h_dentry = hdp->hd_dentry;
++ hdp->hd_dentry = hi_wh;
++ err = au_reopen_nondir(file);
++ hdp->hd_dentry = h_dentry;
++ dinfo->di_btop = btop;
+
-+static inline int au_fidir_sz(int nent)
-+{
-+ AuDebugOn(nent < 0);
-+ return sizeof(struct au_fidir) + sizeof(struct au_hfile) * nent;
++ return err;
+}
+
-+struct au_finfo {
-+ atomic_t fi_generation;
-+
-+ struct au_rwsem fi_rwsem;
-+ aufs_bindex_t fi_btop;
-+
-+ /* do not union them */
-+ struct { /* for non-dir */
-+ struct au_hfile fi_htop;
-+ atomic_t fi_mmapped;
-+ };
-+ struct au_fidir *fi_hdir; /* for dir only */
-+
-+ struct hlist_bl_node fi_hlist;
-+ struct file *fi_file; /* very ugly */
-+ struct rcu_head rcu;
-+} ____cacheline_aligned_in_smp;
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* file.c */
-+extern const struct address_space_operations aufs_aop;
-+unsigned int au_file_roflags(unsigned int flags);
-+struct file *au_h_open(struct dentry *dentry, aufs_bindex_t bindex, int flags,
-+ struct file *file, int force_wr);
-+struct au_do_open_args {
-+ int aopen;
-+ int (*open)(struct file *file, int flags,
-+ struct file *h_file);
-+ struct au_fidir *fidir;
-+ struct file *h_file;
-+};
-+int au_do_open(struct file *file, struct au_do_open_args *args);
-+int au_reopen_nondir(struct file *file);
-+struct au_pin;
-+int au_ready_to_write(struct file *file, loff_t len, struct au_pin *pin);
-+int au_reval_and_lock_fdi(struct file *file, int (*reopen)(struct file *file),
-+ int wlock, unsigned int fi_lsc);
-+int au_do_flush(struct file *file, fl_owner_t id,
-+ int (*flush)(struct file *file, fl_owner_t id));
-+
-+/* poll.c */
-+#ifdef CONFIG_AUFS_POLL
-+__poll_t aufs_poll(struct file *file, struct poll_table_struct *pt);
-+#endif
-+
-+#ifdef CONFIG_AUFS_BR_HFSPLUS
-+/* hfsplus.c */
-+struct file *au_h_open_pre(struct dentry *dentry, aufs_bindex_t bindex,
-+ int force_wr);
-+void au_h_open_post(struct dentry *dentry, aufs_bindex_t bindex,
-+ struct file *h_file);
-+#else
-+AuStub(struct file *, au_h_open_pre, return NULL, struct dentry *dentry,
-+ aufs_bindex_t bindex, int force_wr)
-+AuStubVoid(au_h_open_post, struct dentry *dentry, aufs_bindex_t bindex,
-+ struct file *h_file);
-+#endif
-+
-+/* f_op.c */
-+extern const struct file_operations aufs_file_fop;
-+int au_do_open_nondir(struct file *file, int flags, struct file *h_file);
-+int aufs_release_nondir(struct inode *inode __maybe_unused, struct file *file);
-+struct file *au_read_pre(struct file *file, int keep_fi, unsigned int lsc);
-+
-+/* finfo.c */
-+void au_hfput(struct au_hfile *hf, int execed);
-+void au_set_h_fptr(struct file *file, aufs_bindex_t bindex,
-+ struct file *h_file);
-+
-+void au_update_figen(struct file *file);
-+struct au_fidir *au_fidir_alloc(struct super_block *sb);
-+int au_fidir_realloc(struct au_finfo *finfo, int nbr, int may_shrink);
-+
-+void au_fi_init_once(void *_fi);
-+void au_finfo_fin(struct file *file);
-+int au_finfo_init(struct file *file, struct au_fidir *fidir);
-+
-+/* ioctl.c */
-+long aufs_ioctl_nondir(struct file *file, unsigned int cmd, unsigned long arg);
-+#ifdef CONFIG_COMPAT
-+long aufs_compat_ioctl_dir(struct file *file, unsigned int cmd,
-+ unsigned long arg);
-+long aufs_compat_ioctl_nondir(struct file *file, unsigned int cmd,
-+ unsigned long arg);
-+#endif
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static inline struct au_finfo *au_fi(struct file *file)
++static int au_ready_to_write_wh(struct file *file, loff_t len,
++ aufs_bindex_t bcpup, struct au_pin *pin)
+{
-+ return file->private_data;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+#define fi_read_lock(f) au_rw_read_lock(&au_fi(f)->fi_rwsem)
-+#define fi_write_lock(f) au_rw_write_lock(&au_fi(f)->fi_rwsem)
-+#define fi_read_trylock(f) au_rw_read_trylock(&au_fi(f)->fi_rwsem)
-+#define fi_write_trylock(f) au_rw_write_trylock(&au_fi(f)->fi_rwsem)
-+/*
-+#define fi_read_trylock_nested(f) \
-+ au_rw_read_trylock_nested(&au_fi(f)->fi_rwsem)
-+#define fi_write_trylock_nested(f) \
-+ au_rw_write_trylock_nested(&au_fi(f)->fi_rwsem)
-+*/
-+
-+#define fi_read_unlock(f) au_rw_read_unlock(&au_fi(f)->fi_rwsem)
-+#define fi_write_unlock(f) au_rw_write_unlock(&au_fi(f)->fi_rwsem)
-+#define fi_downgrade_lock(f) au_rw_dgrade_lock(&au_fi(f)->fi_rwsem)
++ int err;
++ struct inode *inode, *h_inode;
++ struct dentry *h_dentry, *hi_wh;
++ struct au_cp_generic cpg = {
++ .dentry = file->f_path.dentry,
++ .bdst = bcpup,
++ .bsrc = -1,
++ .len = len,
++ .pin = pin
++ };
+
-+/* lock subclass for finfo */
-+enum {
-+ AuLsc_FI_1,
-+ AuLsc_FI_2
-+};
++ au_update_dbtop(cpg.dentry);
++ inode = d_inode(cpg.dentry);
++ h_inode = NULL;
++ if (au_dbtop(cpg.dentry) <= bcpup
++ && au_dbbot(cpg.dentry) >= bcpup) {
++ h_dentry = au_h_dptr(cpg.dentry, bcpup);
++ if (h_dentry && d_is_positive(h_dentry))
++ h_inode = d_inode(h_dentry);
++ }
++ hi_wh = au_hi_wh(inode, bcpup);
++ if (!hi_wh && !h_inode)
++ err = au_sio_cpup_wh(&cpg, file);
++ else
++ /* already copied-up after unlink */
++ err = au_reopen_wh(file, bcpup, hi_wh);
+
-+static inline void fi_read_lock_nested(struct file *f, unsigned int lsc)
-+{
-+ au_rw_read_lock_nested(&au_fi(f)->fi_rwsem, lsc);
-+}
++ if (!err
++ && (inode->i_nlink > 1
++ || (inode->i_state & I_LINKABLE))
++ && au_opt_test(au_mntflags(cpg.dentry->d_sb), PLINK))
++ au_plink_append(inode, bcpup, au_h_dptr(cpg.dentry, bcpup));
+
-+static inline void fi_write_lock_nested(struct file *f, unsigned int lsc)
-+{
-+ au_rw_write_lock_nested(&au_fi(f)->fi_rwsem, lsc);
++ return err;
+}
+
+/*
-+ * fi_read_lock_1, fi_write_lock_1,
-+ * fi_read_lock_2, fi_write_lock_2
++ * prepare the @file for writing.
+ */
-+#define AuReadLockFunc(name) \
-+static inline void fi_read_lock_##name(struct file *f) \
-+{ fi_read_lock_nested(f, AuLsc_FI_##name); }
-+
-+#define AuWriteLockFunc(name) \
-+static inline void fi_write_lock_##name(struct file *f) \
-+{ fi_write_lock_nested(f, AuLsc_FI_##name); }
-+
-+#define AuRWLockFuncs(name) \
-+ AuReadLockFunc(name) \
-+ AuWriteLockFunc(name)
-+
-+AuRWLockFuncs(1);
-+AuRWLockFuncs(2);
-+
-+#undef AuReadLockFunc
-+#undef AuWriteLockFunc
-+#undef AuRWLockFuncs
-+
-+#define FiMustNoWaiters(f) AuRwMustNoWaiters(&au_fi(f)->fi_rwsem)
-+#define FiMustAnyLock(f) AuRwMustAnyLock(&au_fi(f)->fi_rwsem)
-+#define FiMustWriteLock(f) AuRwMustWriteLock(&au_fi(f)->fi_rwsem)
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* todo: hard/soft set? */
-+static inline aufs_bindex_t au_fbtop(struct file *file)
-+{
-+ FiMustAnyLock(file);
-+ return au_fi(file)->fi_btop;
-+}
-+
-+static inline aufs_bindex_t au_fbbot_dir(struct file *file)
-+{
-+ FiMustAnyLock(file);
-+ AuDebugOn(!au_fi(file)->fi_hdir);
-+ return au_fi(file)->fi_hdir->fd_bbot;
-+}
-+
-+static inline struct au_vdir *au_fvdir_cache(struct file *file)
-+{
-+ FiMustAnyLock(file);
-+ AuDebugOn(!au_fi(file)->fi_hdir);
-+ return au_fi(file)->fi_hdir->fd_vdir_cache;
-+}
-+
-+static inline void au_set_fbtop(struct file *file, aufs_bindex_t bindex)
++int au_ready_to_write(struct file *file, loff_t len, struct au_pin *pin)
+{
-+ FiMustWriteLock(file);
-+ au_fi(file)->fi_btop = bindex;
-+}
++ int err;
++ aufs_bindex_t dbtop;
++ struct dentry *parent;
++ struct inode *inode;
++ struct super_block *sb;
++ struct file *h_file;
++ struct au_cp_generic cpg = {
++ .dentry = file->f_path.dentry,
++ .bdst = -1,
++ .bsrc = -1,
++ .len = len,
++ .pin = pin,
++ .flags = AuCpup_DTIME
++ };
+
-+static inline void au_set_fbbot_dir(struct file *file, aufs_bindex_t bindex)
-+{
-+ FiMustWriteLock(file);
-+ AuDebugOn(!au_fi(file)->fi_hdir);
-+ au_fi(file)->fi_hdir->fd_bbot = bindex;
-+}
++ sb = cpg.dentry->d_sb;
++ inode = d_inode(cpg.dentry);
++ cpg.bsrc = au_fbtop(file);
++ err = au_test_ro(sb, cpg.bsrc, inode);
++ if (!err && (au_hf_top(file)->f_mode & FMODE_WRITE)) {
++ err = au_pin(pin, cpg.dentry, cpg.bsrc, AuOpt_UDBA_NONE,
++ /*flags*/0);
++ goto out;
++ }
+
-+static inline void au_set_fvdir_cache(struct file *file,
-+ struct au_vdir *vdir_cache)
-+{
-+ FiMustWriteLock(file);
-+ AuDebugOn(!au_fi(file)->fi_hdir);
-+ au_fi(file)->fi_hdir->fd_vdir_cache = vdir_cache;
-+}
++ /* need to cpup or reopen */
++ parent = dget_parent(cpg.dentry);
++ di_write_lock_parent(parent);
++ err = AuWbrCopyup(au_sbi(sb), cpg.dentry);
++ cpg.bdst = err;
++ if (unlikely(err < 0))
++ goto out_dgrade;
++ err = 0;
+
-+static inline struct file *au_hf_top(struct file *file)
-+{
-+ FiMustAnyLock(file);
-+ AuDebugOn(au_fi(file)->fi_hdir);
-+ return au_fi(file)->fi_htop.hf_file;
-+}
++ if (!d_unhashed(cpg.dentry) && !au_h_dptr(parent, cpg.bdst)) {
++ err = au_cpup_dirs(cpg.dentry, cpg.bdst);
++ if (unlikely(err))
++ goto out_dgrade;
++ }
+
-+static inline struct file *au_hf_dir(struct file *file, aufs_bindex_t bindex)
-+{
-+ FiMustAnyLock(file);
-+ AuDebugOn(!au_fi(file)->fi_hdir);
-+ return au_fi(file)->fi_hdir->fd_hfile[0 + bindex].hf_file;
-+}
++ err = au_pin(pin, cpg.dentry, cpg.bdst, AuOpt_UDBA_NONE,
++ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
++ if (unlikely(err))
++ goto out_dgrade;
+
-+/* todo: memory barrier? */
-+static inline unsigned int au_figen(struct file *f)
-+{
-+ return atomic_read(&au_fi(f)->fi_generation);
-+}
++ dbtop = au_dbtop(cpg.dentry);
++ if (dbtop <= cpg.bdst)
++ cpg.bsrc = cpg.bdst;
+
-+static inline void au_set_mmapped(struct file *f)
-+{
-+ if (atomic_inc_return(&au_fi(f)->fi_mmapped))
-+ return;
-+ pr_warn("fi_mmapped wrapped around\n");
-+ while (!atomic_inc_return(&au_fi(f)->fi_mmapped))
-+ ;
-+}
++ if (dbtop <= cpg.bdst /* just reopen */
++ || !d_unhashed(cpg.dentry) /* copyup and reopen */
++ ) {
++ h_file = au_h_open_pre(cpg.dentry, cpg.bsrc, /*force_wr*/0);
++ if (IS_ERR(h_file))
++ err = PTR_ERR(h_file);
++ else {
++ di_downgrade_lock(parent, AuLock_IR);
++ if (dbtop > cpg.bdst)
++ err = au_sio_cpup_simple(&cpg);
++ if (!err)
++ err = au_reopen_nondir(file);
++ au_h_open_post(cpg.dentry, cpg.bsrc, h_file);
++ }
++ } else { /* copyup as wh and reopen */
++ /*
++ * since writable hfsplus branch is not supported,
++ * h_open_pre/post() are unnecessary.
++ */
++ err = au_ready_to_write_wh(file, len, cpg.bdst, pin);
++ di_downgrade_lock(parent, AuLock_IR);
++ }
+
-+static inline void au_unset_mmapped(struct file *f)
-+{
-+ atomic_dec(&au_fi(f)->fi_mmapped);
-+}
++ if (!err) {
++ au_pin_set_parent_lflag(pin, /*lflag*/0);
++ goto out_dput; /* success */
++ }
++ au_unpin(pin);
++ goto out_unlock;
+
-+static inline int au_test_mmapped(struct file *f)
-+{
-+ return atomic_read(&au_fi(f)->fi_mmapped);
++out_dgrade:
++ di_downgrade_lock(parent, AuLock_IR);
++out_unlock:
++ di_read_unlock(parent, AuLock_IR);
++out_dput:
++ dput(parent);
++out:
++ return err;
+}
+
-+/* customize vma->vm_file */
++/* ---------------------------------------------------------------------- */
+
-+static inline void au_do_vm_file_reset(struct vm_area_struct *vma,
-+ struct file *file)
++int au_do_flush(struct file *file, fl_owner_t id,
++ int (*flush)(struct file *file, fl_owner_t id))
+{
-+ struct file *f;
++ int err;
++ struct super_block *sb;
++ struct inode *inode;
+
-+ f = vma->vm_file;
-+ get_file(file);
-+ vma->vm_file = file;
-+ fput(f);
-+}
++ inode = file_inode(file);
++ sb = inode->i_sb;
++ si_noflush_read_lock(sb);
++ fi_read_lock(file);
++ ii_read_lock_child(inode);
+
-+#ifdef CONFIG_MMU
-+#define AuDbgVmRegion(file, vma) do {} while (0)
++ err = flush(file, id);
++ au_cpup_attr_timesizes(inode);
+
-+static inline void au_vm_file_reset(struct vm_area_struct *vma,
-+ struct file *file)
-+{
-+ au_do_vm_file_reset(vma, file);
++ ii_read_unlock(inode);
++ fi_read_unlock(file);
++ si_read_unlock(sb);
++ return err;
+}
-+#else
-+#define AuDbgVmRegion(file, vma) \
-+ AuDebugOn((vma)->vm_region && (vma)->vm_region->vm_file != (file))
+
-+static inline void au_vm_file_reset(struct vm_area_struct *vma,
-+ struct file *file)
++/* ---------------------------------------------------------------------- */
++
++static int au_file_refresh_by_inode(struct file *file, int *need_reopen)
+{
-+ struct file *f;
++ int err;
++ struct au_pin pin;
++ struct au_finfo *finfo;
++ struct dentry *parent, *hi_wh;
++ struct inode *inode;
++ struct super_block *sb;
++ struct au_cp_generic cpg = {
++ .dentry = file->f_path.dentry,
++ .bdst = -1,
++ .bsrc = -1,
++ .len = -1,
++ .pin = &pin,
++ .flags = AuCpup_DTIME
++ };
+
-+ au_do_vm_file_reset(vma, file);
-+ f = vma->vm_region->vm_file;
-+ get_file(file);
-+ vma->vm_region->vm_file = file;
-+ fput(f);
-+}
-+#endif /* CONFIG_MMU */
++ FiMustWriteLock(file);
+
-+/* handle vma->vm_prfile */
-+static inline void au_vm_prfile_set(struct vm_area_struct *vma,
-+ struct file *file)
-+{
-+ get_file(file);
-+ vma->vm_prfile = file;
-+#ifndef CONFIG_MMU
-+ get_file(file);
-+ vma->vm_region->vm_prfile = file;
-+#endif
-+}
++ err = 0;
++ finfo = au_fi(file);
++ sb = cpg.dentry->d_sb;
++ inode = d_inode(cpg.dentry);
++ cpg.bdst = au_ibtop(inode);
++ if (cpg.bdst == finfo->fi_btop || IS_ROOT(cpg.dentry))
++ goto out;
+
-+#endif /* __KERNEL__ */
-+#endif /* __AUFS_FILE_H__ */
-diff -urN /usr/share/empty/fs/aufs/finfo.c linux/fs/aufs/finfo.c
---- /usr/share/empty/fs/aufs/finfo.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/finfo.c 2022-11-05 23:02:18.965889284 +0100
-@@ -0,0 +1,149 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2022 Junjiro R. Okajima
-+ *
-+ * This program 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/>.
-+ */
++ parent = dget_parent(cpg.dentry);
++ if (au_test_ro(sb, cpg.bdst, inode)) {
++ di_read_lock_parent(parent, !AuLock_IR);
++ err = AuWbrCopyup(au_sbi(sb), cpg.dentry);
++ cpg.bdst = err;
++ di_read_unlock(parent, !AuLock_IR);
++ if (unlikely(err < 0))
++ goto out_parent;
++ err = 0;
++ }
+
-+/*
-+ * file private data
-+ */
++ di_read_lock_parent(parent, AuLock_IR);
++ hi_wh = au_hi_wh(inode, cpg.bdst);
++ if (!S_ISDIR(inode->i_mode)
++ && au_opt_test(au_mntflags(sb), PLINK)
++ && au_plink_test(inode)
++ && !d_unhashed(cpg.dentry)
++ && cpg.bdst < au_dbtop(cpg.dentry)) {
++ err = au_test_and_cpup_dirs(cpg.dentry, cpg.bdst);
++ if (unlikely(err))
++ goto out_unlock;
+
-+#include "aufs.h"
++ /* always superio. */
++ err = au_pin(&pin, cpg.dentry, cpg.bdst, AuOpt_UDBA_NONE,
++ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
++ if (!err) {
++ err = au_sio_cpup_simple(&cpg);
++ au_unpin(&pin);
++ }
++ } else if (hi_wh) {
++ /* already copied-up after unlink */
++ err = au_reopen_wh(file, cpg.bdst, hi_wh);
++ *need_reopen = 0;
++ }
+
-+void au_hfput(struct au_hfile *hf, int execed)
-+{
-+ if (execed)
-+ allow_write_access(hf->hf_file);
-+ fput(hf->hf_file);
-+ hf->hf_file = NULL;
-+ au_lcnt_dec(&hf->hf_br->br_nfiles);
-+ hf->hf_br = NULL;
++out_unlock:
++ di_read_unlock(parent, AuLock_IR);
++out_parent:
++ dput(parent);
++out:
++ return err;
+}
+
-+void au_set_h_fptr(struct file *file, aufs_bindex_t bindex, struct file *val)
++static void au_do_refresh_dir(struct file *file)
+{
-+ struct au_finfo *finfo = au_fi(file);
-+ struct au_hfile *hf;
++ aufs_bindex_t bindex, bbot, new_bindex, brid;
++ struct au_hfile *p, tmp, *q;
++ struct au_finfo *finfo;
++ struct super_block *sb;
+ struct au_fidir *fidir;
+
++ FiMustWriteLock(file);
++
++ sb = file->f_path.dentry->d_sb;
++ finfo = au_fi(file);
+ fidir = finfo->fi_hdir;
-+ if (!fidir) {
-+ AuDebugOn(finfo->fi_btop != bindex);
-+ hf = &finfo->fi_htop;
-+ } else
-+ hf = fidir->fd_hfile + bindex;
++ AuDebugOn(!fidir);
++ p = fidir->fd_hfile + finfo->fi_btop;
++ brid = p->hf_br->br_id;
++ bbot = fidir->fd_bbot;
++ for (bindex = finfo->fi_btop; bindex <= bbot; bindex++, p++) {
++ if (!p->hf_file)
++ continue;
+
-+ if (hf && hf->hf_file)
-+ au_hfput(hf, vfsub_file_execed(file));
-+ if (val) {
-+ FiMustWriteLock(file);
-+ AuDebugOn(IS_ERR_OR_NULL(file->f_path.dentry));
-+ hf->hf_file = val;
-+ hf->hf_br = au_sbr(file->f_path.dentry->d_sb, bindex);
++ new_bindex = au_br_index(sb, p->hf_br->br_id);
++ if (new_bindex == bindex)
++ continue;
++ if (new_bindex < 0) {
++ au_set_h_fptr(file, bindex, NULL);
++ continue;
++ }
++
++ /* swap two lower inode, and loop again */
++ q = fidir->fd_hfile + new_bindex;
++ tmp = *q;
++ *q = *p;
++ *p = tmp;
++ if (tmp.hf_file) {
++ bindex--;
++ p--;
++ }
+ }
-+}
+
-+void au_update_figen(struct file *file)
-+{
-+ atomic_set(&au_fi(file)->fi_generation, au_digen(file->f_path.dentry));
-+ /* smp_mb(); */ /* atomic_set */
-+}
++ p = fidir->fd_hfile;
++ if (!au_test_mmapped(file) && !d_unlinked(file->f_path.dentry)) {
++ bbot = au_sbbot(sb);
++ for (finfo->fi_btop = 0; finfo->fi_btop <= bbot;
++ finfo->fi_btop++, p++)
++ if (p->hf_file) {
++ if (file_inode(p->hf_file))
++ break;
++ au_hfput(p, /*execed*/0);
++ }
++ } else {
++ bbot = au_br_index(sb, brid);
++ for (finfo->fi_btop = 0; finfo->fi_btop < bbot;
++ finfo->fi_btop++, p++)
++ if (p->hf_file)
++ au_hfput(p, /*execed*/0);
++ bbot = au_sbbot(sb);
++ }
+
-+/* ---------------------------------------------------------------------- */
++ p = fidir->fd_hfile + bbot;
++ for (fidir->fd_bbot = bbot; fidir->fd_bbot >= finfo->fi_btop;
++ fidir->fd_bbot--, p--)
++ if (p->hf_file) {
++ if (file_inode(p->hf_file))
++ break;
++ au_hfput(p, /*execed*/0);
++ }
++ AuDebugOn(fidir->fd_bbot < finfo->fi_btop);
++}
+
-+struct au_fidir *au_fidir_alloc(struct super_block *sb)
++/*
++ * after branch manipulating, refresh the file.
++ */
++static int refresh_file(struct file *file, int (*reopen)(struct file *file))
+{
-+ struct au_fidir *fidir;
-+ int nbr;
++ int err, need_reopen, nbr;
++ aufs_bindex_t bbot, bindex;
++ struct dentry *dentry;
++ struct super_block *sb;
++ struct au_finfo *finfo;
++ struct au_hfile *hfile;
+
++ dentry = file->f_path.dentry;
++ sb = dentry->d_sb;
+ nbr = au_sbbot(sb) + 1;
-+ if (nbr < 2)
-+ nbr = 2; /* initial allocate for 2 branches */
-+ fidir = kzalloc(au_fidir_sz(nbr), GFP_NOFS);
-+ if (fidir) {
-+ fidir->fd_bbot = -1;
-+ fidir->fd_nent = nbr;
++ finfo = au_fi(file);
++ if (!finfo->fi_hdir) {
++ hfile = &finfo->fi_htop;
++ AuDebugOn(!hfile->hf_file);
++ bindex = au_br_index(sb, hfile->hf_br->br_id);
++ AuDebugOn(bindex < 0);
++ if (bindex != finfo->fi_btop)
++ au_set_fbtop(file, bindex);
++ } else {
++ err = au_fidir_realloc(finfo, nbr, /*may_shrink*/0);
++ if (unlikely(err))
++ goto out;
++ au_do_refresh_dir(file);
+ }
+
-+ return fidir;
++ err = 0;
++ need_reopen = 1;
++ if (!au_test_mmapped(file))
++ err = au_file_refresh_by_inode(file, &need_reopen);
++ if (finfo->fi_hdir)
++ /* harmless if err */
++ au_fidir_realloc(finfo, nbr, /*may_shrink*/1);
++ if (!err && need_reopen && !d_unlinked(dentry))
++ err = reopen(file);
++ if (!err) {
++ au_update_figen(file);
++ goto out; /* success */
++ }
++
++ /* error, close all lower files */
++ if (finfo->fi_hdir) {
++ bbot = au_fbbot_dir(file);
++ for (bindex = au_fbtop(file); bindex <= bbot; bindex++)
++ au_set_h_fptr(file, bindex, NULL);
++ }
++
++out:
++ return err;
+}
+
-+int au_fidir_realloc(struct au_finfo *finfo, int nbr, int may_shrink)
++/* common function to regular file and dir */
++int au_reval_and_lock_fdi(struct file *file, int (*reopen)(struct file *file),
++ int wlock, unsigned int fi_lsc)
+{
+ int err;
-+ struct au_fidir *fidir, *p;
++ unsigned int sigen, figen;
++ aufs_bindex_t btop;
++ unsigned char pseudo_link;
++ struct dentry *dentry;
++ struct inode *inode;
+
-+ AuRwMustWriteLock(&finfo->fi_rwsem);
-+ fidir = finfo->fi_hdir;
-+ AuDebugOn(!fidir);
++ err = 0;
++ dentry = file->f_path.dentry;
++ inode = d_inode(dentry);
++ sigen = au_sigen(dentry->d_sb);
++ fi_write_lock_nested(file, fi_lsc);
++ figen = au_figen(file);
++ if (!fi_lsc)
++ di_write_lock_child(dentry);
++ else
++ di_write_lock_child2(dentry);
++ btop = au_dbtop(dentry);
++ pseudo_link = (btop != au_ibtop(inode));
++ if (sigen == figen && !pseudo_link && au_fbtop(file) == btop) {
++ if (!wlock) {
++ di_downgrade_lock(dentry, AuLock_IR);
++ fi_downgrade_lock(file);
++ }
++ goto out; /* success */
++ }
+
-+ err = -ENOMEM;
-+ p = au_kzrealloc(fidir, au_fidir_sz(fidir->fd_nent), au_fidir_sz(nbr),
-+ GFP_NOFS, may_shrink);
-+ if (p) {
-+ p->fd_nent = nbr;
-+ finfo->fi_hdir = p;
-+ err = 0;
++ AuDbg("sigen %d, figen %d\n", sigen, figen);
++ if (au_digen_test(dentry, sigen)) {
++ err = au_reval_dpath(dentry, sigen);
++ AuDebugOn(!err && au_digen_test(dentry, sigen));
++ }
++
++ if (!err)
++ err = refresh_file(file, reopen);
++ if (!err) {
++ if (!wlock) {
++ di_downgrade_lock(dentry, AuLock_IR);
++ fi_downgrade_lock(file);
++ }
++ } else {
++ di_write_unlock(dentry);
++ fi_write_unlock(file);
+ }
+
++out:
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
-+void au_finfo_fin(struct file *file)
-+{
-+ struct au_finfo *finfo;
-+
-+ au_lcnt_dec(&au_sbi(file->f_path.dentry->d_sb)->si_nfiles);
-+
-+ finfo = au_fi(file);
-+ AuDebugOn(finfo->fi_hdir);
-+ AuRwDestroy(&finfo->fi_rwsem);
-+ au_cache_free_finfo(finfo);
-+}
-+
-+void au_fi_init_once(void *_finfo)
++/* cf. aufs_nopage() */
++/* for madvise(2) */
++static int aufs_read_folio(struct file *file __maybe_unused, struct folio *folio)
+{
-+ struct au_finfo *finfo = _finfo;
-+
-+ au_rw_init(&finfo->fi_rwsem);
++ folio_unlock(folio);
++ return 0;
+}
+
-+int au_finfo_init(struct file *file, struct au_fidir *fidir)
-+{
-+ int err;
-+ struct au_finfo *finfo;
-+ struct dentry *dentry;
-+
-+ err = -ENOMEM;
-+ dentry = file->f_path.dentry;
-+ finfo = au_cache_alloc_finfo();
-+ if (unlikely(!finfo))
-+ goto out;
++/* it will never be called, but necessary to support O_DIRECT */
++static ssize_t aufs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
++{ BUG(); return 0; }
+
-+ err = 0;
-+ au_lcnt_inc(&au_sbi(dentry->d_sb)->si_nfiles);
-+ au_rw_write_lock(&finfo->fi_rwsem);
-+ finfo->fi_btop = -1;
-+ finfo->fi_hdir = fidir;
-+ atomic_set(&finfo->fi_generation, au_digen(dentry));
-+ /* smp_mb(); */ /* atomic_set */
++/* they will never be called. */
++#ifdef CONFIG_AUFS_DEBUG
++static int aufs_write_begin(struct file *file, struct address_space *mapping,
++ loff_t pos, unsigned len,
++ struct page **pagep, void **fsdata)
++{ AuUnsupport(); return 0; }
++static int aufs_write_end(struct file *file, struct address_space *mapping,
++ loff_t pos, unsigned len, unsigned copied,
++ struct page *page, void *fsdata)
++{ AuUnsupport(); return 0; }
++static int aufs_writepage(struct page *page, struct writeback_control *wbc)
++{ AuUnsupport(); return 0; }
+
-+ file->private_data = finfo;
++static bool aufs_dirty_folio(struct address_space *mapping, struct folio *folio)
++{ AuUnsupport(); return true; }
++static void aufs_invalidate_folio(struct folio *folio, size_t offset, size_t len)
++{ AuUnsupport(); }
++static bool aufs_release_folio(struct folio *folio, gfp_t gfp)
++{ AuUnsupport(); return true; }
++#if 0 /* called by memory compaction regardless file */
++static int aufs_migrate_folio(struct address_space *mapping, struct folio *dst,
++ struct folio *src, enum migrate_mode mode)
++{ AuUnsupport(); return 0; }
++#endif
++static int aufs_launder_folio(struct folio *folio)
++{ AuUnsupport(); return 0; }
++static bool aufs_is_partially_uptodate(struct folio *folio, size_t from,
++ size_t count)
++{ AuUnsupport(); return true; }
++static void aufs_is_dirty_writeback(struct folio *folio, bool *dirty,
++ bool *writeback)
++{ AuUnsupport(); }
++static int aufs_error_remove_page(struct address_space *mapping,
++ struct page *page)
++{ AuUnsupport(); return 0; }
++static int aufs_swap_activate(struct swap_info_struct *sis, struct file *file,
++ sector_t *span)
++{ AuUnsupport(); return 0; }
++static void aufs_swap_deactivate(struct file *file)
++{ AuUnsupport(); }
++static int aufs_swap_rw(struct kiocb *iocb, struct iov_iter *iter)
++{ AuUnsupport(); return 0; }
++#endif /* CONFIG_AUFS_DEBUG */
+
-+out:
-+ return err;
-+}
-diff -urN /usr/share/empty/fs/aufs/f_op.c linux/fs/aufs/f_op.c
---- /usr/share/empty/fs/aufs/f_op.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/f_op.c 2023-10-31 09:31:04.196547417 +0100
-@@ -0,0 +1,771 @@
-+// SPDX-License-Identifier: GPL-2.0
++const struct address_space_operations aufs_aop = {
++ .read_folio = aufs_read_folio,
++ .direct_IO = aufs_direct_IO,
++#ifdef CONFIG_AUFS_DEBUG
++ .writepage = aufs_writepage,
++ /* no writepages, because of writepage */
++ .dirty_folio = aufs_dirty_folio,
++ /* no readpages, because of readpage */
++ .write_begin = aufs_write_begin,
++ .write_end = aufs_write_end,
++ /* no bmap, no block device */
++ .invalidate_folio = aufs_invalidate_folio,
++ .release_folio = aufs_release_folio,
++ /* is fallback_migrate_page ok? */
++ /* .migrate_folio = aufs_migrate_folio, */
++ .launder_folio = aufs_launder_folio,
++ .is_partially_uptodate = aufs_is_partially_uptodate,
++ .is_dirty_writeback = aufs_is_dirty_writeback,
++ .error_remove_page = aufs_error_remove_page,
++ .swap_activate = aufs_swap_activate,
++ .swap_deactivate = aufs_swap_deactivate,
++ .swap_rw = aufs_swap_rw
++#endif /* CONFIG_AUFS_DEBUG */
++};
+diff --git a/fs/aufs/file.h b/fs/aufs/file.h
+new file mode 100644
+index 00000000000000..b16f31e364a837
+--- /dev/null
++++ b/fs/aufs/file.h
+@@ -0,0 +1,342 @@
++/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2005-2022 Junjiro R. Okajima
+ *
+ */
+
+/*
-+ * file and vm operations
++ * file operations
+ */
+
-+#include <linux/aio.h>
-+#include <linux/fs_stack.h>
-+#include <linux/mman.h>
-+#include <linux/security.h>
-+#include "aufs.h"
-+
-+int au_do_open_nondir(struct file *file, int flags, struct file *h_file)
-+{
-+ int err;
-+ aufs_bindex_t bindex;
-+ struct dentry *dentry, *h_dentry;
-+ struct au_finfo *finfo;
-+ struct inode *h_inode;
++#ifndef __AUFS_FILE_H__
++#define __AUFS_FILE_H__
+
-+ FiMustWriteLock(file);
++#ifdef __KERNEL__
+
-+ err = 0;
-+ dentry = file->f_path.dentry;
-+ AuDebugOn(IS_ERR_OR_NULL(dentry));
-+ finfo = au_fi(file);
-+ memset(&finfo->fi_htop, 0, sizeof(finfo->fi_htop));
-+ atomic_set(&finfo->fi_mmapped, 0);
-+ bindex = au_dbtop(dentry);
-+ if (!h_file) {
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ err = vfsub_test_mntns(file->f_path.mnt, h_dentry->d_sb);
-+ if (unlikely(err))
-+ goto out;
-+ h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0);
-+ if (IS_ERR(h_file)) {
-+ err = PTR_ERR(h_file);
-+ goto out;
-+ }
-+ } else {
-+ h_dentry = h_file->f_path.dentry;
-+ err = vfsub_test_mntns(file->f_path.mnt, h_dentry->d_sb);
-+ if (unlikely(err))
-+ goto out;
-+ /* br ref is already inc-ed */
-+ }
++#include <linux/file.h>
++#include <linux/fs.h>
++#include <linux/mm_types.h>
++#include <linux/poll.h>
++#include "rwsem.h"
+
-+ if (flags & __O_TMPFILE) {
-+ AuDebugOn(!h_file);
-+ AuDebugOn(h_file != au_di(dentry)->di_htmpfile);
-+ au_di(dentry)->di_htmpfile = NULL;
++struct au_branch;
++struct au_hfile {
++ struct file *hf_file;
++ struct au_branch *hf_br;
++};
+
-+ if (!(flags & O_EXCL)) {
-+ h_inode = file_inode(h_file);
-+ spin_lock(&h_inode->i_lock);
-+ h_inode->i_state |= I_LINKABLE;
-+ spin_unlock(&h_inode->i_lock);
-+ }
-+ }
-+ au_set_fbtop(file, bindex);
-+ au_set_h_fptr(file, bindex, h_file);
-+ au_update_figen(file);
-+ /* todo: necessary? */
-+ /* file->f_ra = h_file->f_ra; */
++struct au_vdir;
++struct au_fidir {
++ aufs_bindex_t fd_bbot;
++ aufs_bindex_t fd_nent;
++ struct au_vdir *fd_vdir_cache;
++ struct au_hfile fd_hfile[];
++};
+
-+out:
-+ return err;
++static inline int au_fidir_sz(int nent)
++{
++ AuDebugOn(nent < 0);
++ return sizeof(struct au_fidir) + sizeof(struct au_hfile) * nent;
+}
+
-+static int aufs_open_nondir(struct inode *inode __maybe_unused,
-+ struct file *file)
-+{
-+ int err;
-+ struct super_block *sb;
-+ struct au_do_open_args args = {
-+ .open = au_do_open_nondir
-+ };
++struct au_finfo {
++ atomic_t fi_generation;
+
-+ AuDbg("%pD, f_flags 0x%x, f_mode 0x%x\n",
-+ file, vfsub_file_flags(file), file->f_mode);
++ struct au_rwsem fi_rwsem;
++ aufs_bindex_t fi_btop;
+
-+ sb = file->f_path.dentry->d_sb;
-+ si_read_lock(sb, AuLock_FLUSH);
-+ err = au_do_open(file, &args);
-+ si_read_unlock(sb);
-+ return err;
-+}
++ /* do not union them */
++ struct { /* for non-dir */
++ struct au_hfile fi_htop;
++ atomic_t fi_mmapped;
++ };
++ struct au_fidir *fi_hdir; /* for dir only */
+
-+int aufs_release_nondir(struct inode *inode __maybe_unused, struct file *file)
-+{
-+ struct au_finfo *finfo;
-+ aufs_bindex_t bindex;
++ struct hlist_bl_node fi_hlist;
++ struct file *fi_file; /* very ugly */
++ struct rcu_head rcu;
++} ____cacheline_aligned_in_smp;
+
-+ finfo = au_fi(file);
-+ au_hbl_del(&finfo->fi_hlist,
-+ &au_sbi(file->f_path.dentry->d_sb)->si_files);
-+ bindex = finfo->fi_btop;
-+ if (bindex >= 0)
-+ au_set_h_fptr(file, bindex, NULL);
++/* ---------------------------------------------------------------------- */
+
-+ au_finfo_fin(file);
-+ return 0;
-+}
++/* file.c */
++extern const struct address_space_operations aufs_aop;
++unsigned int au_file_roflags(unsigned int flags);
++struct file *au_h_open(struct dentry *dentry, aufs_bindex_t bindex, int flags,
++ struct file *file, int force_wr);
++struct au_do_open_args {
++ int aopen;
++ int (*open)(struct file *file, int flags,
++ struct file *h_file);
++ struct au_fidir *fidir;
++ struct file *h_file;
++};
++int au_do_open(struct file *file, struct au_do_open_args *args);
++int au_reopen_nondir(struct file *file);
++struct au_pin;
++int au_ready_to_write(struct file *file, loff_t len, struct au_pin *pin);
++int au_reval_and_lock_fdi(struct file *file, int (*reopen)(struct file *file),
++ int wlock, unsigned int fi_lsc);
++int au_do_flush(struct file *file, fl_owner_t id,
++ int (*flush)(struct file *file, fl_owner_t id));
+
-+/* ---------------------------------------------------------------------- */
++/* poll.c */
++#ifdef CONFIG_AUFS_POLL
++__poll_t aufs_poll(struct file *file, struct poll_table_struct *pt);
++#endif
+
-+static int au_do_flush_nondir(struct file *file, fl_owner_t id)
-+{
-+ int err;
-+ struct file *h_file;
++#ifdef CONFIG_AUFS_BR_HFSPLUS
++/* hfsplus.c */
++struct file *au_h_open_pre(struct dentry *dentry, aufs_bindex_t bindex,
++ int force_wr);
++void au_h_open_post(struct dentry *dentry, aufs_bindex_t bindex,
++ struct file *h_file);
++#else
++AuStub(struct file *, au_h_open_pre, return NULL, struct dentry *dentry,
++ aufs_bindex_t bindex, int force_wr)
++AuStubVoid(au_h_open_post, struct dentry *dentry, aufs_bindex_t bindex,
++ struct file *h_file);
++#endif
+
-+ err = 0;
-+ h_file = au_hf_top(file);
-+ if (h_file)
-+ err = vfsub_flush(h_file, id);
-+ return err;
-+}
++/* f_op.c */
++extern const struct file_operations aufs_file_fop;
++int au_do_open_nondir(struct file *file, int flags, struct file *h_file);
++int aufs_release_nondir(struct inode *inode __maybe_unused, struct file *file);
++struct file *au_read_pre(struct file *file, int keep_fi, unsigned int lsc);
+
-+static int aufs_flush_nondir(struct file *file, fl_owner_t id)
-+{
-+ return au_do_flush(file, id, au_do_flush_nondir);
-+}
++/* finfo.c */
++void au_hfput(struct au_hfile *hf, int execed);
++void au_set_h_fptr(struct file *file, aufs_bindex_t bindex,
++ struct file *h_file);
+
-+/* ---------------------------------------------------------------------- */
-+/*
-+ * read and write functions acquire [fdi]_rwsem once, but release before
-+ * mmap_sem. This is because to stop a race condition between mmap(2).
-+ * Releasing these aufs-rwsem should be safe, no branch-management (by keeping
-+ * si_rwsem), no harmful copy-up should happen. Actually copy-up may happen in
-+ * read functions after [fdi]_rwsem are released, but it should be harmless.
-+ */
++void au_update_figen(struct file *file);
++struct au_fidir *au_fidir_alloc(struct super_block *sb);
++int au_fidir_realloc(struct au_finfo *finfo, int nbr, int may_shrink);
+
-+/* Callers should call au_read_post() or fput() in the end */
-+struct file *au_read_pre(struct file *file, int keep_fi, unsigned int lsc)
-+{
-+ struct file *h_file;
-+ int err;
++void au_fi_init_once(void *_fi);
++void au_finfo_fin(struct file *file);
++int au_finfo_init(struct file *file, struct au_fidir *fidir);
+
-+ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/0, lsc);
-+ if (!err) {
-+ di_read_unlock(file->f_path.dentry, AuLock_IR);
-+ h_file = au_hf_top(file);
-+ get_file(h_file);
-+ if (!keep_fi)
-+ fi_read_unlock(file);
-+ } else
-+ h_file = ERR_PTR(err);
++/* ioctl.c */
++long aufs_ioctl_nondir(struct file *file, unsigned int cmd, unsigned long arg);
++#ifdef CONFIG_COMPAT
++long aufs_compat_ioctl_dir(struct file *file, unsigned int cmd,
++ unsigned long arg);
++long aufs_compat_ioctl_nondir(struct file *file, unsigned int cmd,
++ unsigned long arg);
++#endif
+
-+ return h_file;
-+}
++/* ---------------------------------------------------------------------- */
+
-+static void au_read_post(struct inode *inode, struct file *h_file)
++static inline struct au_finfo *au_fi(struct file *file)
+{
-+ /* update without lock, I don't think it a problem */
-+ fsstack_copy_attr_atime(inode, file_inode(h_file));
-+ fput(h_file);
++ return file->private_data;
+}
+
-+struct au_write_pre {
-+ /* input */
-+ unsigned int lsc;
-+
-+ /* output */
-+ blkcnt_t blks;
-+ aufs_bindex_t btop;
-+};
++/* ---------------------------------------------------------------------- */
+
++#define fi_read_lock(f) au_rw_read_lock(&au_fi(f)->fi_rwsem)
++#define fi_write_lock(f) au_rw_write_lock(&au_fi(f)->fi_rwsem)
++#define fi_read_trylock(f) au_rw_read_trylock(&au_fi(f)->fi_rwsem)
++#define fi_write_trylock(f) au_rw_write_trylock(&au_fi(f)->fi_rwsem)
+/*
-+ * return with iinfo is write-locked
-+ * callers should call au_write_post() or iinfo_write_unlock() + fput() in the
-+ * end
-+ */
-+static struct file *au_write_pre(struct file *file, int do_ready,
-+ struct au_write_pre *wpre)
-+{
-+ struct file *h_file;
-+ struct dentry *dentry;
-+ int err;
-+ unsigned int lsc;
-+ struct au_pin pin;
-+
-+ lsc = 0;
-+ if (wpre)
-+ lsc = wpre->lsc;
-+ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1, lsc);
-+ h_file = ERR_PTR(err);
-+ if (unlikely(err))
-+ goto out;
++#define fi_read_trylock_nested(f) \
++ au_rw_read_trylock_nested(&au_fi(f)->fi_rwsem)
++#define fi_write_trylock_nested(f) \
++ au_rw_write_trylock_nested(&au_fi(f)->fi_rwsem)
++*/
+
-+ dentry = file->f_path.dentry;
-+ if (do_ready) {
-+ err = au_ready_to_write(file, -1, &pin);
-+ if (unlikely(err)) {
-+ h_file = ERR_PTR(err);
-+ di_write_unlock(dentry);
-+ goto out_fi;
-+ }
-+ }
++#define fi_read_unlock(f) au_rw_read_unlock(&au_fi(f)->fi_rwsem)
++#define fi_write_unlock(f) au_rw_write_unlock(&au_fi(f)->fi_rwsem)
++#define fi_downgrade_lock(f) au_rw_dgrade_lock(&au_fi(f)->fi_rwsem)
+
-+ di_downgrade_lock(dentry, /*flags*/0);
-+ if (wpre)
-+ wpre->btop = au_fbtop(file);
-+ h_file = au_hf_top(file);
-+ get_file(h_file);
-+ if (wpre)
-+ wpre->blks = file_inode(h_file)->i_blocks;
-+ if (do_ready)
-+ au_unpin(&pin);
-+ di_read_unlock(dentry, /*flags*/0);
-+ vfsub_file_start_write(h_file);
++/* lock subclass for finfo */
++enum {
++ AuLsc_FI_1,
++ AuLsc_FI_2
++};
+
-+out_fi:
-+ fi_write_unlock(file);
-+out:
-+ return h_file;
++static inline void fi_read_lock_nested(struct file *f, unsigned int lsc)
++{
++ au_rw_read_lock_nested(&au_fi(f)->fi_rwsem, lsc);
+}
+
-+static void au_write_post(struct inode *inode, struct file *h_file,
-+ struct au_write_pre *wpre, ssize_t written)
++static inline void fi_write_lock_nested(struct file *f, unsigned int lsc)
+{
-+ struct inode *h_inode;
-+
-+ vfsub_file_end_write(h_file);
-+ au_cpup_attr_timesizes(inode);
-+ AuDebugOn(au_ibtop(inode) != wpre->btop);
-+ h_inode = file_inode(h_file);
-+ inode->i_mode = h_inode->i_mode;
-+ ii_write_unlock(inode);
-+ /* AuDbg("blks %llu, %llu\n", (u64)blks, (u64)h_inode->i_blocks); */
-+ if (written > 0)
-+ au_fhsm_wrote(inode->i_sb, wpre->btop,
-+ /*force*/h_inode->i_blocks > wpre->blks);
-+ fput(h_file);
++ au_rw_write_lock_nested(&au_fi(f)->fi_rwsem, lsc);
+}
+
+/*
-+ * todo: very ugly
-+ * it locks both of i_mutex and si_rwsem for read in safe.
-+ * if the plink maintenance mode continues forever (that is the problem),
-+ * may loop forever.
++ * fi_read_lock_1, fi_write_lock_1,
++ * fi_read_lock_2, fi_write_lock_2
+ */
-+static void au_mtx_and_read_lock(struct inode *inode)
-+{
-+ int err;
-+ struct super_block *sb = inode->i_sb;
-+
-+ while (1) {
-+ inode_lock(inode);
-+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
-+ if (!err)
-+ break;
-+ inode_unlock(inode);
-+ si_read_lock(sb, AuLock_NOPLMW);
-+ si_read_unlock(sb);
-+ }
-+}
-+
-+static ssize_t au_do_iter(struct file *h_file, int rw, struct kiocb *kio,
-+ struct iov_iter *iov_iter)
-+{
-+ ssize_t err;
-+ struct file *file;
-+ ssize_t (*iter)(struct kiocb *, struct iov_iter *);
-+
-+ err = security_file_permission(h_file, rw);
-+ if (unlikely(err))
-+ goto out;
-+
-+ err = -ENOSYS; /* the branch doesn't have its ->(read|write)_iter() */
-+ iter = NULL;
-+ if (rw == MAY_READ)
-+ iter = h_file->f_op->read_iter;
-+ else if (rw == MAY_WRITE)
-+ iter = h_file->f_op->write_iter;
-+
-+ file = kio->ki_filp;
-+ kio->ki_filp = h_file;
-+ if (iter) {
-+ lockdep_off();
-+ err = iter(kio, iov_iter);
-+ lockdep_on();
-+ } else
-+ /* currently there is no such fs */
-+ WARN_ON_ONCE(1);
-+ kio->ki_filp = file;
-+
-+out:
-+ return err;
-+}
++#define AuReadLockFunc(name) \
++static inline void fi_read_lock_##name(struct file *f) \
++{ fi_read_lock_nested(f, AuLsc_FI_##name); }
+
-+static ssize_t aufs_read_iter(struct kiocb *kio, struct iov_iter *iov_iter)
-+{
-+ ssize_t err;
-+ struct file *file, *h_file;
-+ struct inode *inode;
-+ struct super_block *sb;
++#define AuWriteLockFunc(name) \
++static inline void fi_write_lock_##name(struct file *f) \
++{ fi_write_lock_nested(f, AuLsc_FI_##name); }
+
-+ file = kio->ki_filp;
-+ inode = file_inode(file);
-+ sb = inode->i_sb;
-+ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
++#define AuRWLockFuncs(name) \
++ AuReadLockFunc(name) \
++ AuWriteLockFunc(name)
+
-+ h_file = au_read_pre(file, /*keep_fi*/1, /*lsc*/0);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out;
++AuRWLockFuncs(1);
++AuRWLockFuncs(2);
+
-+ if (au_test_loopback_kthread()) {
-+ au_warn_loopback(h_file->f_path.dentry->d_sb);
-+ if (file->f_mapping != h_file->f_mapping) {
-+ file->f_mapping = h_file->f_mapping;
-+ smp_mb(); /* unnecessary? */
-+ }
-+ }
-+ fi_read_unlock(file);
++#undef AuReadLockFunc
++#undef AuWriteLockFunc
++#undef AuRWLockFuncs
+
-+ err = au_do_iter(h_file, MAY_READ, kio, iov_iter);
-+ /* todo: necessary? */
-+ /* file->f_ra = h_file->f_ra; */
-+ au_read_post(inode, h_file);
++#define FiMustNoWaiters(f) AuRwMustNoWaiters(&au_fi(f)->fi_rwsem)
++#define FiMustAnyLock(f) AuRwMustAnyLock(&au_fi(f)->fi_rwsem)
++#define FiMustWriteLock(f) AuRwMustWriteLock(&au_fi(f)->fi_rwsem)
+
-+out:
-+ si_read_unlock(sb);
-+ return err;
-+}
++/* ---------------------------------------------------------------------- */
+
-+static ssize_t aufs_write_iter(struct kiocb *kio, struct iov_iter *iov_iter)
++/* todo: hard/soft set? */
++static inline aufs_bindex_t au_fbtop(struct file *file)
+{
-+ ssize_t err;
-+ struct au_write_pre wpre;
-+ struct inode *inode;
-+ struct file *file, *h_file;
-+
-+ file = kio->ki_filp;
-+ inode = file_inode(file);
-+ au_mtx_and_read_lock(inode);
-+
-+ wpre.lsc = 0;
-+ h_file = au_write_pre(file, /*do_ready*/1, &wpre);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out;
-+
-+ err = au_do_iter(h_file, MAY_WRITE, kio, iov_iter);
-+ au_write_post(inode, h_file, &wpre, err);
-+
-+out:
-+ si_read_unlock(inode->i_sb);
-+ inode_unlock(inode);
-+ return err;
++ FiMustAnyLock(file);
++ return au_fi(file)->fi_btop;
+}
+
-+/*
-+ * We may be able to remove aufs_splice_{read,write}() since almost all FSes
-+ * don't have their own .splice_{read,write} implimentations, and they use
-+ * generic_file_splice_read() and iter_file_splice_write() who can act like the
-+ * simple converters to f_op->iter_read() and ->iter_write().
-+ * But we keep our own implementations because some non-mainlined FSes may have
-+ * their own .splice_{read,write} implimentations and aufs doesn't want to take
-+ * away an opportunity to co-work with aufs from them.
-+ */
-+static ssize_t aufs_splice_read(struct file *file, loff_t *ppos,
-+ struct pipe_inode_info *pipe, size_t len,
-+ unsigned int flags)
++static inline aufs_bindex_t au_fbbot_dir(struct file *file)
+{
-+ ssize_t err;
-+ struct file *h_file;
-+ struct inode *inode;
-+ struct super_block *sb;
-+
-+ inode = file_inode(file);
-+ sb = inode->i_sb;
-+ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
-+
-+ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out;
-+
-+ err = vfsub_splice_read(h_file, ppos, pipe, len, flags);
-+ /* todo: necessary? */
-+ /* file->f_ra = h_file->f_ra; */
-+ au_read_post(inode, h_file);
-+
-+out:
-+ si_read_unlock(sb);
-+ return err;
++ FiMustAnyLock(file);
++ AuDebugOn(!au_fi(file)->fi_hdir);
++ return au_fi(file)->fi_hdir->fd_bbot;
+}
+
-+static ssize_t
-+aufs_splice_write(struct pipe_inode_info *pipe, struct file *file, loff_t *ppos,
-+ size_t len, unsigned int flags)
++static inline struct au_vdir *au_fvdir_cache(struct file *file)
+{
-+ ssize_t err;
-+ struct au_write_pre wpre;
-+ struct inode *inode;
-+ struct file *h_file;
-+
-+ inode = file_inode(file);
-+ au_mtx_and_read_lock(inode);
++ FiMustAnyLock(file);
++ AuDebugOn(!au_fi(file)->fi_hdir);
++ return au_fi(file)->fi_hdir->fd_vdir_cache;
++}
+
-+ wpre.lsc = 0;
-+ h_file = au_write_pre(file, /*do_ready*/1, &wpre);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out;
++static inline void au_set_fbtop(struct file *file, aufs_bindex_t bindex)
++{
++ FiMustWriteLock(file);
++ au_fi(file)->fi_btop = bindex;
++}
+
-+ err = vfsub_splice_from(pipe, h_file, ppos, len, flags);
-+ au_write_post(inode, h_file, &wpre, err);
++static inline void au_set_fbbot_dir(struct file *file, aufs_bindex_t bindex)
++{
++ FiMustWriteLock(file);
++ AuDebugOn(!au_fi(file)->fi_hdir);
++ au_fi(file)->fi_hdir->fd_bbot = bindex;
++}
+
-+out:
-+ si_read_unlock(inode->i_sb);
-+ inode_unlock(inode);
-+ return err;
++static inline void au_set_fvdir_cache(struct file *file,
++ struct au_vdir *vdir_cache)
++{
++ FiMustWriteLock(file);
++ AuDebugOn(!au_fi(file)->fi_hdir);
++ au_fi(file)->fi_hdir->fd_vdir_cache = vdir_cache;
+}
+
-+static long aufs_fallocate(struct file *file, int mode, loff_t offset,
-+ loff_t len)
++static inline struct file *au_hf_top(struct file *file)
+{
-+ long err;
-+ struct au_write_pre wpre;
-+ struct inode *inode;
-+ struct file *h_file;
++ FiMustAnyLock(file);
++ AuDebugOn(au_fi(file)->fi_hdir);
++ return au_fi(file)->fi_htop.hf_file;
++}
+
-+ inode = file_inode(file);
-+ au_mtx_and_read_lock(inode);
++static inline struct file *au_hf_dir(struct file *file, aufs_bindex_t bindex)
++{
++ FiMustAnyLock(file);
++ AuDebugOn(!au_fi(file)->fi_hdir);
++ return au_fi(file)->fi_hdir->fd_hfile[0 + bindex].hf_file;
++}
+
-+ wpre.lsc = 0;
-+ h_file = au_write_pre(file, /*do_ready*/1, &wpre);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out;
++/* todo: memory barrier? */
++static inline unsigned int au_figen(struct file *f)
++{
++ return atomic_read(&au_fi(f)->fi_generation);
++}
+
-+ lockdep_off();
-+ err = vfs_fallocate(h_file, mode, offset, len);
-+ lockdep_on();
-+ /*
-+ * we don't need to call file_modifed() here since au_write_post()
-+ * is equivalent and copies-up all timestamps and permission bits.
-+ */
-+ au_write_post(inode, h_file, &wpre, /*written*/1);
++static inline void au_set_mmapped(struct file *f)
++{
++ if (atomic_inc_return(&au_fi(f)->fi_mmapped))
++ return;
++ pr_warn("fi_mmapped wrapped around\n");
++ while (!atomic_inc_return(&au_fi(f)->fi_mmapped))
++ ;
++}
+
-+out:
-+ si_read_unlock(inode->i_sb);
-+ inode_unlock(inode);
-+ return err;
++static inline void au_unset_mmapped(struct file *f)
++{
++ atomic_dec(&au_fi(f)->fi_mmapped);
+}
+
-+static ssize_t aufs_copy_file_range(struct file *src, loff_t src_pos,
-+ struct file *dst, loff_t dst_pos,
-+ size_t len, unsigned int flags)
++static inline int au_test_mmapped(struct file *f)
+{
-+ ssize_t err;
-+ struct au_write_pre wpre;
-+ enum { SRC, DST };
-+ struct {
-+ struct inode *inode;
-+ struct file *h_file;
-+ struct super_block *h_sb;
-+ } a[2];
-+#define a_src a[SRC]
-+#define a_dst a[DST]
++ return atomic_read(&au_fi(f)->fi_mmapped);
++}
+
-+ err = -EINVAL;
-+ a_src.inode = file_inode(src);
-+ if (unlikely(!S_ISREG(a_src.inode->i_mode)))
-+ goto out;
-+ a_dst.inode = file_inode(dst);
-+ if (unlikely(!S_ISREG(a_dst.inode->i_mode)))
-+ goto out;
++/* customize vma->vm_file */
+
-+ au_mtx_and_read_lock(a_dst.inode);
-+ /*
-+ * in order to match the order in di_write_lock2_{child,parent}(),
-+ * use f_path.dentry for this comparison.
-+ */
-+ if (src->f_path.dentry < dst->f_path.dentry) {
-+ a_src.h_file = au_read_pre(src, /*keep_fi*/1, AuLsc_FI_1);
-+ err = PTR_ERR(a_src.h_file);
-+ if (IS_ERR(a_src.h_file))
-+ goto out_si;
++static inline void au_do_vm_file_reset(struct vm_area_struct *vma,
++ struct file *file)
++{
++ struct file *f;
+
-+ wpre.lsc = AuLsc_FI_2;
-+ a_dst.h_file = au_write_pre(dst, /*do_ready*/1, &wpre);
-+ err = PTR_ERR(a_dst.h_file);
-+ if (IS_ERR(a_dst.h_file)) {
-+ au_read_post(a_src.inode, a_src.h_file);
-+ goto out_si;
-+ }
-+ } else {
-+ wpre.lsc = AuLsc_FI_1;
-+ a_dst.h_file = au_write_pre(dst, /*do_ready*/1, &wpre);
-+ err = PTR_ERR(a_dst.h_file);
-+ if (IS_ERR(a_dst.h_file))
-+ goto out_si;
++ f = vma->vm_file;
++ get_file(file);
++ vma->vm_file = file;
++ fput(f);
++}
+
-+ a_src.h_file = au_read_pre(src, /*keep_fi*/1, AuLsc_FI_2);
-+ err = PTR_ERR(a_src.h_file);
-+ if (IS_ERR(a_src.h_file)) {
-+ au_write_post(a_dst.inode, a_dst.h_file, &wpre,
-+ /*written*/0);
-+ goto out_si;
-+ }
-+ }
++#ifdef CONFIG_MMU
++#define AuDbgVmRegion(file, vma) do {} while (0)
+
-+ err = -EXDEV;
-+ a_src.h_sb = file_inode(a_src.h_file)->i_sb;
-+ a_dst.h_sb = file_inode(a_dst.h_file)->i_sb;
-+ if (unlikely(a_src.h_sb != a_dst.h_sb)) {
-+ AuDbgFile(src);
-+ AuDbgFile(dst);
-+ goto out_file;
-+ }
++static inline void au_vm_file_reset(struct vm_area_struct *vma,
++ struct file *file)
++{
++ au_do_vm_file_reset(vma, file);
++}
++#else
++#define AuDbgVmRegion(file, vma) \
++ AuDebugOn((vma)->vm_region && (vma)->vm_region->vm_file != (file))
+
-+ err = vfsub_copy_file_range(a_src.h_file, src_pos, a_dst.h_file,
-+ dst_pos, len, flags);
++static inline void au_vm_file_reset(struct vm_area_struct *vma,
++ struct file *file)
++{
++ struct file *f;
+
-+out_file:
-+ au_write_post(a_dst.inode, a_dst.h_file, &wpre, err);
-+ fi_read_unlock(src);
-+ au_read_post(a_src.inode, a_src.h_file);
-+out_si:
-+ si_read_unlock(a_dst.inode->i_sb);
-+ inode_unlock(a_dst.inode);
-+out:
-+ return err;
-+#undef a_src
-+#undef a_dst
++ au_do_vm_file_reset(vma, file);
++ f = vma->vm_region->vm_file;
++ get_file(file);
++ vma->vm_region->vm_file = file;
++ fput(f);
+}
++#endif /* CONFIG_MMU */
+
-+/* ---------------------------------------------------------------------- */
++/* handle vma->vm_prfile */
++static inline void au_vm_prfile_set(struct vm_area_struct *vma,
++ struct file *file)
++{
++ get_file(file);
++ vma->vm_prfile = file;
++#ifndef CONFIG_MMU
++ get_file(file);
++ vma->vm_region->vm_prfile = file;
++#endif
++}
+
++#endif /* __KERNEL__ */
++#endif /* __AUFS_FILE_H__ */
+diff --git a/fs/aufs/finfo.c b/fs/aufs/finfo.c
+new file mode 100644
+index 00000000000000..7da7b286c006fc
+--- /dev/null
++++ b/fs/aufs/finfo.c
+@@ -0,0 +1,149 @@
++// SPDX-License-Identifier: GPL-2.0
+/*
-+ * The locking order around current->mmap_sem.
-+ * - in most and regular cases
-+ * file I/O syscall -- aufs_read() or something
-+ * -- si_rwsem for read -- mmap_sem
-+ * (Note that [fdi]i_rwsem are released before mmap_sem).
-+ * - in mmap case
-+ * mmap(2) -- mmap_sem -- aufs_mmap() -- si_rwsem for read -- [fdi]i_rwsem
-+ * This AB-BA order is definitely bad, but is not a problem since "si_rwsem for
-+ * read" allows multiple processes to acquire it and [fdi]i_rwsem are not held
-+ * in file I/O. Aufs needs to stop lockdep in aufs_mmap() though.
-+ * It means that when aufs acquires si_rwsem for write, the process should never
-+ * acquire mmap_sem.
++ * Copyright (C) 2005-2022 Junjiro R. Okajima
+ *
-+ * Actually aufs_iterate() holds [fdi]i_rwsem before mmap_sem, but this is not a
-+ * problem either since any directory is not able to be mmap-ed.
-+ * The similar scenario is applied to aufs_readlink() too.
++ * This program 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/>.
+ */
+
-+#if 0 /* stop calling security_file_mmap() */
-+/* cf. linux/include/linux/mman.h: calc_vm_prot_bits() */
-+#define AuConv_VM_PROT(f, b) _calc_vm_trans(f, VM_##b, PROT_##b)
++/*
++ * file private data
++ */
+
-+static unsigned long au_arch_prot_conv(unsigned long flags)
++#include "aufs.h"
++
++void au_hfput(struct au_hfile *hf, int execed)
+{
-+ /* currently ppc64 only */
-+#ifdef CONFIG_PPC64
-+ /* cf. linux/arch/powerpc/include/asm/mman.h */
-+ AuDebugOn(arch_calc_vm_prot_bits(-1) != VM_SAO);
-+ return AuConv_VM_PROT(flags, SAO);
-+#else
-+ AuDebugOn(arch_calc_vm_prot_bits(-1));
-+ return 0;
-+#endif
++ if (execed)
++ allow_write_access(hf->hf_file);
++ fput(hf->hf_file);
++ hf->hf_file = NULL;
++ au_lcnt_dec(&hf->hf_br->br_nfiles);
++ hf->hf_br = NULL;
+}
+
-+static unsigned long au_prot_conv(unsigned long flags)
++void au_set_h_fptr(struct file *file, aufs_bindex_t bindex, struct file *val)
+{
-+ return AuConv_VM_PROT(flags, READ)
-+ | AuConv_VM_PROT(flags, WRITE)
-+ | AuConv_VM_PROT(flags, EXEC)
-+ | au_arch_prot_conv(flags);
-+}
++ struct au_finfo *finfo = au_fi(file);
++ struct au_hfile *hf;
++ struct au_fidir *fidir;
+
-+/* cf. linux/include/linux/mman.h: calc_vm_flag_bits() */
-+#define AuConv_VM_MAP(f, b) _calc_vm_trans(f, VM_##b, MAP_##b)
++ fidir = finfo->fi_hdir;
++ if (!fidir) {
++ AuDebugOn(finfo->fi_btop != bindex);
++ hf = &finfo->fi_htop;
++ } else
++ hf = fidir->fd_hfile + bindex;
+
-+static unsigned long au_flag_conv(unsigned long flags)
-+{
-+ return AuConv_VM_MAP(flags, GROWSDOWN)
-+ | AuConv_VM_MAP(flags, DENYWRITE)
-+ | AuConv_VM_MAP(flags, LOCKED);
++ if (hf && hf->hf_file)
++ au_hfput(hf, vfsub_file_execed(file));
++ if (val) {
++ FiMustWriteLock(file);
++ AuDebugOn(IS_ERR_OR_NULL(file->f_path.dentry));
++ hf->hf_file = val;
++ hf->hf_br = au_sbr(file->f_path.dentry->d_sb, bindex);
++ }
+}
-+#endif
+
-+static int aufs_mmap(struct file *file, struct vm_area_struct *vma)
++void au_update_figen(struct file *file)
+{
-+ int err;
-+ const unsigned char wlock
-+ = (file->f_mode & FMODE_WRITE) && (vma->vm_flags & VM_SHARED);
-+ struct super_block *sb;
-+ struct file *h_file;
-+ struct inode *inode;
-+
-+ AuDbgVmRegion(file, vma);
++ atomic_set(&au_fi(file)->fi_generation, au_digen(file->f_path.dentry));
++ /* smp_mb(); */ /* atomic_set */
++}
+
-+ inode = file_inode(file);
-+ sb = inode->i_sb;
-+ lockdep_off();
-+ si_read_lock(sb, AuLock_NOPLMW);
++/* ---------------------------------------------------------------------- */
+
-+ h_file = au_write_pre(file, wlock, /*wpre*/NULL);
-+ lockdep_on();
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out;
++struct au_fidir *au_fidir_alloc(struct super_block *sb)
++{
++ struct au_fidir *fidir;
++ int nbr;
+
-+ err = 0;
-+ au_set_mmapped(file);
-+ au_vm_file_reset(vma, h_file);
-+ /*
-+ * we cannot call security_mmap_file() here since it may acquire
-+ * mmap_sem or i_mutex.
-+ *
-+ * err = security_mmap_file(h_file, au_prot_conv(vma->vm_flags),
-+ * au_flag_conv(vma->vm_flags));
-+ */
-+ if (!err)
-+ err = call_mmap(h_file, vma);
-+ if (!err) {
-+ au_vm_prfile_set(vma, file);
-+ fsstack_copy_attr_atime(inode, file_inode(h_file));
-+ goto out_fput; /* success */
++ nbr = au_sbbot(sb) + 1;
++ if (nbr < 2)
++ nbr = 2; /* initial allocate for 2 branches */
++ fidir = kzalloc(au_fidir_sz(nbr), GFP_NOFS);
++ if (fidir) {
++ fidir->fd_bbot = -1;
++ fidir->fd_nent = nbr;
+ }
-+ au_unset_mmapped(file);
-+ au_vm_file_reset(vma, file);
+
-+out_fput:
-+ lockdep_off();
-+ ii_write_unlock(inode);
-+ lockdep_on();
-+ fput(h_file);
-+out:
-+ lockdep_off();
-+ si_read_unlock(sb);
-+ lockdep_on();
-+ AuTraceErr(err);
-+ return err;
++ return fidir;
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+static int aufs_fsync_nondir(struct file *file, loff_t start, loff_t end,
-+ int datasync)
++int au_fidir_realloc(struct au_finfo *finfo, int nbr, int may_shrink)
+{
+ int err;
-+ struct au_write_pre wpre;
-+ struct inode *inode;
-+ struct file *h_file;
-+
-+ err = 0; /* -EBADF; */ /* posix? */
-+ if (unlikely(!(file->f_mode & FMODE_WRITE)))
-+ goto out;
-+
-+ inode = file_inode(file);
-+ au_mtx_and_read_lock(inode);
++ struct au_fidir *fidir, *p;
+
-+ wpre.lsc = 0;
-+ h_file = au_write_pre(file, /*do_ready*/1, &wpre);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out_unlock;
++ AuRwMustWriteLock(&finfo->fi_rwsem);
++ fidir = finfo->fi_hdir;
++ AuDebugOn(!fidir);
+
-+ err = vfsub_fsync(h_file, &h_file->f_path, datasync);
-+ au_write_post(inode, h_file, &wpre, /*written*/0);
++ err = -ENOMEM;
++ p = au_kzrealloc(fidir, au_fidir_sz(fidir->fd_nent), au_fidir_sz(nbr),
++ GFP_NOFS, may_shrink);
++ if (p) {
++ p->fd_nent = nbr;
++ finfo->fi_hdir = p;
++ err = 0;
++ }
+
-+out_unlock:
-+ si_read_unlock(inode->i_sb);
-+ inode_unlock(inode);
-+out:
+ return err;
+}
+
-+static int aufs_fasync(int fd, struct file *file, int flag)
++/* ---------------------------------------------------------------------- */
++
++void au_finfo_fin(struct file *file)
+{
-+ int err;
-+ struct file *h_file;
-+ struct super_block *sb;
++ struct au_finfo *finfo;
+
-+ sb = file->f_path.dentry->d_sb;
-+ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
++ au_lcnt_dec(&au_sbi(file->f_path.dentry->d_sb)->si_nfiles);
+
-+ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out;
++ finfo = au_fi(file);
++ AuDebugOn(finfo->fi_hdir);
++ AuRwDestroy(&finfo->fi_rwsem);
++ au_cache_free_finfo(finfo);
++}
+
-+ if (h_file->f_op->fasync)
-+ err = h_file->f_op->fasync(fd, h_file, flag);
-+ fput(h_file); /* instead of au_read_post() */
++void au_fi_init_once(void *_finfo)
++{
++ struct au_finfo *finfo = _finfo;
+
-+out:
-+ si_read_unlock(sb);
-+ return err;
++ au_rw_init(&finfo->fi_rwsem);
+}
+
-+static int aufs_setfl(struct file *file, unsigned long arg)
++int au_finfo_init(struct file *file, struct au_fidir *fidir)
+{
+ int err;
-+ struct file *h_file;
-+ struct super_block *sb;
-+
-+ sb = file->f_path.dentry->d_sb;
-+ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
++ struct au_finfo *finfo;
++ struct dentry *dentry;
+
-+ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
++ err = -ENOMEM;
++ dentry = file->f_path.dentry;
++ finfo = au_cache_alloc_finfo();
++ if (unlikely(!finfo))
+ goto out;
+
-+ /* stop calling h_file->fasync */
-+ arg |= vfsub_file_flags(file) & FASYNC;
-+ err = setfl(/*unused fd*/-1, h_file, arg);
-+ fput(h_file); /* instead of au_read_post() */
++ err = 0;
++ au_lcnt_inc(&au_sbi(dentry->d_sb)->si_nfiles);
++ au_rw_write_lock(&finfo->fi_rwsem);
++ finfo->fi_btop = -1;
++ finfo->fi_hdir = fidir;
++ atomic_set(&finfo->fi_generation, au_digen(dentry));
++ /* smp_mb(); */ /* atomic_set */
++
++ file->private_data = finfo;
+
+out:
-+ si_read_unlock(sb);
+ return err;
+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+const struct file_operations aufs_file_fop = {
-+ .owner = THIS_MODULE,
-+
-+ .llseek = default_llseek,
-+
-+ .read_iter = aufs_read_iter,
-+ .write_iter = aufs_write_iter,
-+
-+#ifdef CONFIG_AUFS_POLL
-+ .poll = aufs_poll,
-+#endif
-+ .unlocked_ioctl = aufs_ioctl_nondir,
-+#ifdef CONFIG_COMPAT
-+ .compat_ioctl = aufs_compat_ioctl_nondir,
-+#endif
-+ .mmap = aufs_mmap,
-+ .open = aufs_open_nondir,
-+ .flush = aufs_flush_nondir,
-+ .release = aufs_release_nondir,
-+ .fsync = aufs_fsync_nondir,
-+ .fasync = aufs_fasync,
-+ .setfl = aufs_setfl,
-+ .splice_write = aufs_splice_write,
-+ .splice_read = aufs_splice_read,
-+#if 0 /* reserved for future use */
-+ .aio_splice_write = aufs_aio_splice_write,
-+ .aio_splice_read = aufs_aio_splice_read,
-+#endif
-+ .fallocate = aufs_fallocate,
-+ .copy_file_range = aufs_copy_file_range
-+};
-diff -urN /usr/share/empty/fs/aufs/fsctx.c linux/fs/aufs/fsctx.c
---- /usr/share/empty/fs/aufs/fsctx.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/fsctx.c 2022-11-05 23:02:18.965889284 +0100
+diff --git a/fs/aufs/fsctx.c b/fs/aufs/fsctx.c
+new file mode 100644
+index 00000000000000..e14fe4d381c5c9
+--- /dev/null
++++ b/fs/aufs/fsctx.c
@@ -0,0 +1,1242 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ AuTraceErr(err);
+ return err;
+}
-diff -urN /usr/share/empty/fs/aufs/fstype.h linux/fs/aufs/fstype.h
---- /usr/share/empty/fs/aufs/fstype.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/fstype.h 2022-11-05 23:02:18.965889284 +0100
+diff --git a/fs/aufs/fstype.h b/fs/aufs/fstype.h
+new file mode 100644
+index 00000000000000..24ff0d64c219bc
+--- /dev/null
++++ b/fs/aufs/fstype.h
@@ -0,0 +1,401 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_FSTYPE_H__ */
-diff -urN /usr/share/empty/fs/aufs/hbl.h linux/fs/aufs/hbl.h
---- /usr/share/empty/fs/aufs/hbl.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/hbl.h 2022-11-05 23:02:18.965889284 +0100
+diff --git a/fs/aufs/hbl.h b/fs/aufs/hbl.h
+new file mode 100644
+index 00000000000000..7e1e66db0264ba
+--- /dev/null
++++ b/fs/aufs/hbl.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_HBL_H__ */
-diff -urN /usr/share/empty/fs/aufs/hfsnotify.c linux/fs/aufs/hfsnotify.c
---- /usr/share/empty/fs/aufs/hfsnotify.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/hfsnotify.c 2022-11-05 23:02:18.965889284 +0100
+diff --git a/fs/aufs/hfsnotify.c b/fs/aufs/hfsnotify.c
+new file mode 100644
+index 00000000000000..caa900cea3a0c4
+--- /dev/null
++++ b/fs/aufs/hfsnotify.c
@@ -0,0 +1,290 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ .fin_br = au_hfsn_fin_br,
+ .init_br = au_hfsn_init_br
+};
-diff -urN /usr/share/empty/fs/aufs/hfsplus.c linux/fs/aufs/hfsplus.c
---- /usr/share/empty/fs/aufs/hfsplus.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/hfsplus.c 2022-11-05 23:02:18.965889284 +0100
+diff --git a/fs/aufs/hfsplus.c b/fs/aufs/hfsplus.c
+new file mode 100644
+index 00000000000000..c626ff2128c6b3
+--- /dev/null
++++ b/fs/aufs/hfsplus.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ au_lcnt_dec(&br->br_nfiles);
+ }
+}
-diff -urN /usr/share/empty/fs/aufs/hnotify.c linux/fs/aufs/hnotify.c
---- /usr/share/empty/fs/aufs/hnotify.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/hnotify.c 2022-11-05 23:02:18.965889284 +0100
+diff --git a/fs/aufs/hnotify.c b/fs/aufs/hnotify.c
+new file mode 100644
+index 00000000000000..8ca8c98d40a330
+--- /dev/null
++++ b/fs/aufs/hnotify.c
@@ -0,0 +1,715 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ if (au_cache[AuCache_HNOTIFY])
+ au_hn_destroy_cache();
+}
-diff -urN /usr/share/empty/fs/aufs/iinfo.c linux/fs/aufs/iinfo.c
---- /usr/share/empty/fs/aufs/iinfo.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/iinfo.c 2022-11-05 23:02:18.965889284 +0100
-@@ -0,0 +1,286 @@
+diff --git a/fs/aufs/i_op.c b/fs/aufs/i_op.c
+new file mode 100644
+index 00000000000000..a5cc8743c2bca4
+--- /dev/null
++++ b/fs/aufs/i_op.c
+@@ -0,0 +1,1516 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2005-2022 Junjiro R. Okajima
+ */
+
+/*
-+ * inode private data
++ * inode operations (except add/del/rename)
+ */
+
++#include <linux/device_cgroup.h>
++#include <linux/filelock.h>
++#include <linux/fs_stack.h>
++#include <linux/iversion.h>
++#include <linux/security.h>
+#include "aufs.h"
+
-+struct inode *au_h_iptr(struct inode *inode, aufs_bindex_t bindex)
++static int h_permission(struct inode *h_inode, int mask,
++ struct path *h_path, int brperm)
+{
-+ struct inode *h_inode;
-+ struct au_hinode *hinode;
++ int err;
++ const unsigned char write_mask = !!(mask & (MAY_WRITE | MAY_APPEND));
++ struct mnt_idmap *h_idmap;
+
-+ IiMustAnyLock(inode);
++ err = -EPERM;
++ if (write_mask && IS_IMMUTABLE(h_inode))
++ goto out;
+
-+ hinode = au_hinode(au_ii(inode), bindex);
-+ h_inode = hinode->hi_inode;
-+ AuDebugOn(h_inode && atomic_read(&h_inode->i_count) <= 0);
-+ return h_inode;
-+}
++ err = -EACCES;
++ if (((mask & MAY_EXEC)
++ && S_ISREG(h_inode->i_mode)
++ && (path_noexec(h_path)
++ || !(h_inode->i_mode & 0111))))
++ goto out;
+
-+/* todo: hard/soft set? */
-+void au_hiput(struct au_hinode *hinode)
-+{
-+ au_hn_free(hinode);
-+ dput(hinode->hi_whdentry);
-+ iput(hinode->hi_inode);
-+}
++ /*
++ * - skip the lower fs test in the case of write to ro branch.
++ * - nfs dir permission write check is optimized, but a policy for
++ * link/rename requires a real check.
++ * - nfs always sets SB_POSIXACL regardless its mount option 'noacl.'
++ * in this case, generic_permission() returns -EOPNOTSUPP.
++ */
++ h_idmap = mnt_idmap(h_path->mnt);
++ if ((write_mask && !au_br_writable(brperm))
++ || (au_test_nfs(h_inode->i_sb) && S_ISDIR(h_inode->i_mode)
++ && write_mask && !(mask & MAY_READ))
++ || !h_inode->i_op->permission) {
++ /* AuLabel(generic_permission); */
++ /* AuDbg("get_inode_acl %ps\n",
++ h_inode->i_op->get_inode_acl); */
++ err = generic_permission(h_idmap, h_inode, mask);
++ if (err == -EOPNOTSUPP && au_test_nfs_noacl(h_inode))
++ err = h_inode->i_op->permission(h_idmap, h_inode,
++ mask);
++ AuTraceErr(err);
++ } else {
++ /* AuLabel(h_inode->permission); */
++ err = h_inode->i_op->permission(h_idmap, h_inode, mask);
++ AuTraceErr(err);
++ }
+
-+unsigned int au_hi_flags(struct inode *inode, int isdir)
-+{
-+ unsigned int flags;
-+ const unsigned int mnt_flags = au_mntflags(inode->i_sb);
++ if (!err)
++ err = devcgroup_inode_permission(h_inode, mask);
++ if (!err)
++ err = security_inode_permission(h_inode, mask);
+
-+ flags = 0;
-+ if (au_opt_test(mnt_flags, XINO))
-+ au_fset_hi(flags, XINO);
-+ if (isdir && au_opt_test(mnt_flags, UDBA_HNOTIFY))
-+ au_fset_hi(flags, HNOTIFY);
-+ return flags;
++out:
++ return err;
+}
+
-+void au_set_h_iptr(struct inode *inode, aufs_bindex_t bindex,
-+ struct inode *h_inode, unsigned int flags)
++static int aufs_permission(struct mnt_idmap *idmap, struct inode *inode,
++ int mask)
+{
-+ struct au_hinode *hinode;
-+ struct inode *hi;
-+ struct au_iinfo *iinfo = au_ii(inode);
++ int err;
++ aufs_bindex_t bindex, bbot;
++ const unsigned char isdir = !!S_ISDIR(inode->i_mode),
++ write_mask = !!(mask & (MAY_WRITE | MAY_APPEND));
++ struct inode *h_inode;
++ struct super_block *sb;
++ struct au_branch *br;
+
-+ IiMustWriteLock(inode);
++ /* todo: support rcu-walk? */
++ if (mask & MAY_NOT_BLOCK)
++ return -ECHILD;
+
-+ hinode = au_hinode(iinfo, bindex);
-+ hi = hinode->hi_inode;
-+ AuDebugOn(h_inode && atomic_read(&h_inode->i_count) <= 0);
++ sb = inode->i_sb;
++ si_read_lock(sb, AuLock_FLUSH);
++ ii_read_lock_child(inode);
++#if 0 /* reserved for future use */
++ /*
++ * This test may be rather 'too much' since the test is essentially done
++ * in the aufs_lookup(). Theoretically it is possible that the inode
++ * generation doesn't match to the superblock's here. But it isn't a
++ * big deal I suppose.
++ */
++ err = au_iigen_test(inode, au_sigen(sb));
++ if (unlikely(err))
++ goto out;
++#endif
+
-+ if (hi)
-+ au_hiput(hinode);
-+ hinode->hi_inode = h_inode;
-+ if (h_inode) {
-+ int err;
-+ struct super_block *sb = inode->i_sb;
-+ struct au_branch *br;
++ if (!isdir
++ || write_mask
++ || au_opt_test(au_mntflags(sb), DIRPERM1)) {
++ err = au_busy_or_stale();
++ h_inode = au_h_iptr(inode, au_ibtop(inode));
++ if (unlikely(!h_inode
++ || (h_inode->i_mode & S_IFMT)
++ != (inode->i_mode & S_IFMT)))
++ goto out;
+
-+ AuDebugOn(inode->i_mode
-+ && (h_inode->i_mode & S_IFMT)
-+ != (inode->i_mode & S_IFMT));
-+ if (bindex == iinfo->ii_btop)
-+ au_cpup_igen(inode, h_inode);
++ err = 0;
++ bindex = au_ibtop(inode);
+ br = au_sbr(sb, bindex);
-+ hinode->hi_id = br->br_id;
-+ if (au_ftest_hi(flags, XINO)) {
-+ err = au_xino_write(sb, bindex, h_inode->i_ino,
-+ inode->i_ino);
-+ if (unlikely(err))
-+ AuIOErr1("failed au_xino_write() %d\n", err);
-+ }
-+
-+ if (au_ftest_hi(flags, HNOTIFY)
-+ && au_br_hnotifyable(br->br_perm)) {
-+ err = au_hn_alloc(hinode, inode);
-+ if (unlikely(err))
-+ AuIOErr1("au_hn_alloc() %d\n", err);
++ err = h_permission(h_inode, mask, &br->br_path, br->br_perm);
++ if (write_mask
++ && !err
++ && !special_file(h_inode->i_mode)) {
++ /* test whether the upper writable branch exists */
++ err = -EROFS;
++ for (; bindex >= 0; bindex--)
++ if (!au_br_rdonly(au_sbr(sb, bindex))) {
++ err = 0;
++ break;
++ }
+ }
++ goto out;
+ }
-+}
-+
-+void au_set_hi_wh(struct inode *inode, aufs_bindex_t bindex,
-+ struct dentry *h_wh)
-+{
-+ struct au_hinode *hinode;
-+
-+ IiMustWriteLock(inode);
+
-+ hinode = au_hinode(au_ii(inode), bindex);
-+ AuDebugOn(hinode->hi_whdentry);
-+ hinode->hi_whdentry = h_wh;
-+}
-+
-+void au_update_iigen(struct inode *inode, int half)
-+{
-+ struct au_iinfo *iinfo;
-+ struct au_iigen *iigen;
-+ unsigned int sigen;
-+
-+ sigen = au_sigen(inode->i_sb);
-+ iinfo = au_ii(inode);
-+ iigen = &iinfo->ii_generation;
-+ spin_lock(&iigen->ig_spin);
-+ iigen->ig_generation = sigen;
-+ if (half)
-+ au_ig_fset(iigen->ig_flags, HALF_REFRESHED);
-+ else
-+ au_ig_fclr(iigen->ig_flags, HALF_REFRESHED);
-+ spin_unlock(&iigen->ig_spin);
-+}
-+
-+/* it may be called at remount time, too */
-+void au_update_ibrange(struct inode *inode, int do_put_zero)
-+{
-+ struct au_iinfo *iinfo;
-+ aufs_bindex_t bindex, bbot;
-+
-+ AuDebugOn(au_is_bad_inode(inode));
-+ IiMustWriteLock(inode);
-+
-+ iinfo = au_ii(inode);
-+ if (do_put_zero && iinfo->ii_btop >= 0) {
-+ for (bindex = iinfo->ii_btop; bindex <= iinfo->ii_bbot;
-+ bindex++) {
-+ struct inode *h_i;
++ /* non-write to dir */
++ err = 0;
++ bbot = au_ibbot(inode);
++ for (bindex = au_ibtop(inode); !err && bindex <= bbot; bindex++) {
++ h_inode = au_h_iptr(inode, bindex);
++ if (h_inode) {
++ err = au_busy_or_stale();
++ if (unlikely(!S_ISDIR(h_inode->i_mode)))
++ break;
+
-+ h_i = au_hinode(iinfo, bindex)->hi_inode;
-+ if (h_i
-+ && !h_i->i_nlink
-+ && !(h_i->i_state & I_LINKABLE))
-+ au_set_h_iptr(inode, bindex, NULL, 0);
++ br = au_sbr(sb, bindex);
++ err = h_permission(h_inode, mask, &br->br_path,
++ br->br_perm);
+ }
+ }
+
-+ iinfo->ii_btop = -1;
-+ iinfo->ii_bbot = -1;
-+ bbot = au_sbbot(inode->i_sb);
-+ for (bindex = 0; bindex <= bbot; bindex++)
-+ if (au_hinode(iinfo, bindex)->hi_inode) {
-+ iinfo->ii_btop = bindex;
-+ break;
-+ }
-+ if (iinfo->ii_btop >= 0)
-+ for (bindex = bbot; bindex >= iinfo->ii_btop; bindex--)
-+ if (au_hinode(iinfo, bindex)->hi_inode) {
-+ iinfo->ii_bbot = bindex;
-+ break;
-+ }
-+ AuDebugOn(iinfo->ii_btop > iinfo->ii_bbot);
++out:
++ ii_read_unlock(inode);
++ si_read_unlock(sb);
++ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
-+void au_icntnr_init_once(void *_c)
-+{
-+ struct au_icntnr *c = _c;
-+ struct au_iinfo *iinfo = &c->iinfo;
-+
-+ spin_lock_init(&iinfo->ii_generation.ig_spin);
-+ au_rw_init(&iinfo->ii_rwsem);
-+ inode_init_once(&c->vfs_inode);
-+}
-+
-+void au_hinode_init(struct au_hinode *hinode)
-+{
-+ hinode->hi_inode = NULL;
-+ hinode->hi_id = -1;
-+ au_hn_init(hinode);
-+ hinode->hi_whdentry = NULL;
-+}
-+
-+int au_iinfo_init(struct inode *inode)
++static struct dentry *aufs_lookup(struct inode *dir, struct dentry *dentry,
++ unsigned int flags)
+{
-+ struct au_iinfo *iinfo;
++ struct dentry *ret, *parent;
++ struct inode *inode;
+ struct super_block *sb;
-+ struct au_hinode *hi;
-+ int nbr, i;
-+
-+ sb = inode->i_sb;
-+ iinfo = &(container_of(inode, struct au_icntnr, vfs_inode)->iinfo);
-+ nbr = au_sbbot(sb) + 1;
-+ if (unlikely(nbr <= 0))
-+ nbr = 1;
-+ hi = kmalloc_array(nbr, sizeof(*iinfo->ii_hinode), GFP_NOFS);
-+ if (hi) {
-+ au_lcnt_inc(&au_sbi(sb)->si_ninodes);
-+
-+ iinfo->ii_hinode = hi;
-+ for (i = 0; i < nbr; i++, hi++)
-+ au_hinode_init(hi);
-+
-+ iinfo->ii_generation.ig_generation = au_sigen(sb);
-+ iinfo->ii_btop = -1;
-+ iinfo->ii_bbot = -1;
-+ iinfo->ii_vdir = NULL;
-+ return 0;
-+ }
-+ return -ENOMEM;
-+}
-+
-+int au_hinode_realloc(struct au_iinfo *iinfo, int nbr, int may_shrink)
-+{
-+ int err, i;
-+ struct au_hinode *hip;
++ int err, npositive;
+
-+ AuRwMustWriteLock(&iinfo->ii_rwsem);
++ IMustLock(dir);
+
-+ err = -ENOMEM;
-+ hip = au_krealloc(iinfo->ii_hinode, sizeof(*hip) * nbr, GFP_NOFS,
-+ may_shrink);
-+ if (hip) {
-+ iinfo->ii_hinode = hip;
-+ i = iinfo->ii_bbot + 1;
-+ hip += i;
-+ for (; i < nbr; i++, hip++)
-+ au_hinode_init(hip);
-+ err = 0;
-+ }
++ /* todo: support rcu-walk? */
++ ret = ERR_PTR(-ECHILD);
++ if (flags & LOOKUP_RCU)
++ goto out;
+
-+ return err;
-+}
++ ret = ERR_PTR(-ENAMETOOLONG);
++ if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN))
++ goto out;
+
-+void au_iinfo_fin(struct inode *inode)
-+{
-+ struct au_iinfo *iinfo;
-+ struct au_hinode *hi;
-+ struct super_block *sb;
-+ aufs_bindex_t bindex, bbot;
-+ const unsigned char unlinked = !inode->i_nlink;
++ sb = dir->i_sb;
++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
++ ret = ERR_PTR(err);
++ if (unlikely(err))
++ goto out;
+
-+ AuDebugOn(au_is_bad_inode(inode));
++ err = au_di_init(dentry);
++ ret = ERR_PTR(err);
++ if (unlikely(err))
++ goto out_si;
+
-+ sb = inode->i_sb;
-+ au_lcnt_dec(&au_sbi(sb)->si_ninodes);
-+ if (si_pid_test(sb))
-+ au_xino_delete_inode(inode, unlinked);
-+ else {
-+ /*
-+ * it is safe to hide the dependency between sbinfo and
-+ * sb->s_umount.
-+ */
-+ lockdep_off();
-+ si_noflush_read_lock(sb);
-+ au_xino_delete_inode(inode, unlinked);
-+ si_read_unlock(sb);
-+ lockdep_on();
++ inode = NULL;
++ npositive = 0; /* suppress a warning */
++ parent = dentry->d_parent; /* dir inode is locked */
++ di_read_lock_parent(parent, AuLock_IR);
++ err = au_alive_dir(parent);
++ if (!err)
++ err = au_digen_test(parent, au_sigen(sb));
++ if (!err) {
++ /* regardless LOOKUP_CREATE, always ALLOW_NEG */
++ npositive = au_lkup_dentry(dentry, au_dbtop(parent),
++ AuLkup_ALLOW_NEG);
++ err = npositive;
+ }
++ di_read_unlock(parent, AuLock_IR);
++ ret = ERR_PTR(err);
++ if (unlikely(err < 0))
++ goto out_unlock;
+
-+ iinfo = au_ii(inode);
-+ if (iinfo->ii_vdir)
-+ au_vdir_free(iinfo->ii_vdir);
-+
-+ bindex = iinfo->ii_btop;
-+ if (bindex >= 0) {
-+ hi = au_hinode(iinfo, bindex);
-+ bbot = iinfo->ii_bbot;
-+ while (bindex++ <= bbot) {
-+ if (hi->hi_inode)
-+ au_hiput(hi);
-+ hi++;
++ if (npositive) {
++ inode = au_new_inode(dentry, /*must_new*/0);
++ if (IS_ERR(inode)) {
++ ret = (void *)inode;
++ inode = NULL;
++ goto out_unlock;
+ }
+ }
-+ au_kfree_rcu(iinfo->ii_hinode);
-+ AuRwDestroy(&iinfo->ii_rwsem);
-+}
-diff -urN /usr/share/empty/fs/aufs/inode.c linux/fs/aufs/inode.c
---- /usr/share/empty/fs/aufs/inode.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/inode.c 2023-10-31 09:31:04.199880750 +0100
-@@ -0,0 +1,531 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2022 Junjiro R. Okajima
-+ *
-+ * This program 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/>.
-+ */
+
-+/*
-+ * inode functions
-+ */
-+
-+#include <linux/iversion.h>
-+#include "aufs.h"
-+
-+struct inode *au_igrab(struct inode *inode)
-+{
++ if (inode)
++ atomic_inc(&inode->i_count);
++ ret = d_splice_alias(inode, dentry);
++#if 0 /* reserved for future use */
++ if (unlikely(d_need_lookup(dentry))) {
++ spin_lock(&dentry->d_lock);
++ dentry->d_flags &= ~DCACHE_NEED_LOOKUP;
++ spin_unlock(&dentry->d_lock);
++ } else
++#endif
+ if (inode) {
-+ AuDebugOn(!atomic_read(&inode->i_count));
-+ ihold(inode);
++ if (!IS_ERR(ret)) {
++ iput(inode);
++ if (ret && ret != dentry)
++ ii_write_unlock(inode);
++ } else {
++ ii_write_unlock(inode);
++ iput(inode);
++ inode = NULL;
++ }
+ }
-+ return inode;
-+}
+
-+static void au_refresh_hinode_attr(struct inode *inode, int do_version)
-+{
-+ au_cpup_attr_all(inode, /*force*/0);
-+ au_update_iigen(inode, /*half*/1);
-+ if (do_version)
-+ inode_inc_iversion(inode);
++out_unlock:
++ di_write_unlock(dentry);
++out_si:
++ si_read_unlock(sb);
++out:
++ return ret;
+}
+
-+static int au_ii_refresh(struct inode *inode, int *update)
-+{
-+ int err, e, nbr;
-+ umode_t type;
-+ aufs_bindex_t bindex, new_bindex;
-+ struct super_block *sb;
-+ struct au_iinfo *iinfo;
-+ struct au_hinode *p, *q, tmp;
-+
-+ AuDebugOn(au_is_bad_inode(inode));
-+ IiMustWriteLock(inode);
-+
-+ *update = 0;
-+ sb = inode->i_sb;
-+ nbr = au_sbbot(sb) + 1;
-+ type = inode->i_mode & S_IFMT;
-+ iinfo = au_ii(inode);
-+ err = au_hinode_realloc(iinfo, nbr, /*may_shrink*/0);
-+ if (unlikely(err))
-+ goto out;
++/* ---------------------------------------------------------------------- */
+
-+ AuDebugOn(iinfo->ii_btop < 0);
-+ p = au_hinode(iinfo, iinfo->ii_btop);
-+ for (bindex = iinfo->ii_btop; bindex <= iinfo->ii_bbot;
-+ bindex++, p++) {
-+ if (!p->hi_inode)
-+ continue;
++/*
++ * very dirty and complicated aufs ->atomic_open().
++ * aufs_atomic_open()
++ * + au_aopen_or_create()
++ * + add_simple()
++ * + vfsub_atomic_open()
++ * + branch fs ->atomic_open()
++ * may call the actual 'open' for h_file
++ * + inc br_nfiles only if opened
++ * + au_aopen_no_open() or au_aopen_do_open()
++ *
++ * au_aopen_do_open()
++ * + finish_open()
++ * + au_do_aopen()
++ * + au_do_open() the body of all 'open'
++ * + au_do_open_nondir()
++ * set the passed h_file
++ *
++ * au_aopen_no_open()
++ * + finish_no_open()
++ */
+
-+ AuDebugOn(type != (p->hi_inode->i_mode & S_IFMT));
-+ new_bindex = au_br_index(sb, p->hi_id);
-+ if (new_bindex == bindex)
-+ continue;
++struct aopen_node {
++ struct hlist_bl_node hblist;
++ struct file *file, *h_file;
++};
+
-+ if (new_bindex < 0) {
-+ *update = 1;
-+ au_hiput(p);
-+ p->hi_inode = NULL;
-+ continue;
-+ }
++static int au_do_aopen(struct inode *inode, struct file *file)
++{
++ struct hlist_bl_head *aopen;
++ struct hlist_bl_node *pos;
++ struct aopen_node *node;
++ struct au_do_open_args args = {
++ .aopen = 1,
++ .open = au_do_open_nondir
++ };
+
-+ if (new_bindex < iinfo->ii_btop)
-+ iinfo->ii_btop = new_bindex;
-+ if (iinfo->ii_bbot < new_bindex)
-+ iinfo->ii_bbot = new_bindex;
-+ /* swap two lower inode, and loop again */
-+ q = au_hinode(iinfo, new_bindex);
-+ tmp = *q;
-+ *q = *p;
-+ *p = tmp;
-+ if (tmp.hi_inode) {
-+ bindex--;
-+ p--;
++ aopen = &au_sbi(inode->i_sb)->si_aopen;
++ hlist_bl_lock(aopen);
++ hlist_bl_for_each_entry(node, pos, aopen, hblist)
++ if (node->file == file) {
++ args.h_file = node->h_file;
++ break;
+ }
-+ }
-+ au_update_ibrange(inode, /*do_put_zero*/0);
-+ au_hinode_realloc(iinfo, nbr, /*may_shrink*/1); /* harmless if err */
-+ e = au_dy_irefresh(inode);
-+ if (unlikely(e && !err))
-+ err = e;
++ hlist_bl_unlock(aopen);
++ /* AuDebugOn(!args.h_file); */
+
-+out:
-+ AuTraceErr(err);
-+ return err;
++ return au_do_open(file, &args);
+}
+
-+void au_refresh_iop(struct inode *inode, int force_getattr)
++static int au_aopen_do_open(struct file *file, struct dentry *dentry,
++ struct aopen_node *aopen_node)
+{
-+ int type;
-+ struct au_sbinfo *sbi = au_sbi(inode->i_sb);
-+ const struct inode_operations *iop
-+ = force_getattr ? aufs_iop : sbi->si_iop_array;
-+
-+ if (inode->i_op == iop)
-+ return;
++ int err;
++ struct hlist_bl_head *aopen;
+
-+ switch (inode->i_mode & S_IFMT) {
-+ case S_IFDIR:
-+ type = AuIop_DIR;
-+ break;
-+ case S_IFLNK:
-+ type = AuIop_SYMLINK;
-+ break;
-+ default:
-+ type = AuIop_OTHER;
-+ break;
-+ }
++ AuLabel(here);
++ aopen = &au_sbi(dentry->d_sb)->si_aopen;
++ au_hbl_add(&aopen_node->hblist, aopen);
++ err = finish_open(file, dentry, au_do_aopen);
++ au_hbl_del(&aopen_node->hblist, aopen);
++ /* AuDbgFile(file); */
++ AuDbg("%pd%s%s\n", dentry,
++ (file->f_mode & FMODE_CREATED) ? " created" : "",
++ (file->f_mode & FMODE_OPENED) ? " opened" : "");
+
-+ inode->i_op = iop + type;
-+ /* unnecessary smp_wmb() */
++ AuTraceErr(err);
++ return err;
+}
+
-+int au_refresh_hinode_self(struct inode *inode)
++static int au_aopen_no_open(struct file *file, struct dentry *dentry)
+{
-+ int err, update;
++ int err;
+
-+ err = au_ii_refresh(inode, &update);
-+ if (!err)
-+ au_refresh_hinode_attr(inode, update && S_ISDIR(inode->i_mode));
++ AuLabel(here);
++ dget(dentry);
++ err = finish_no_open(file, dentry);
+
+ AuTraceErr(err);
+ return err;
+}
+
-+int au_refresh_hinode(struct inode *inode, struct dentry *dentry)
++static int aufs_atomic_open(struct inode *dir, struct dentry *dentry,
++ struct file *file, unsigned int open_flag,
++ umode_t create_mode)
+{
-+ int err, e, update;
-+ unsigned int flags;
-+ umode_t mode;
-+ aufs_bindex_t bindex, bbot;
-+ unsigned char isdir;
-+ struct au_hinode *p;
-+ struct au_iinfo *iinfo;
++ int err, did_open;
++ unsigned int lkup_flags;
++ aufs_bindex_t bindex;
++ struct super_block *sb;
++ struct dentry *parent, *d;
++ struct vfsub_aopen_args args = {
++ .open_flag = open_flag,
++ .create_mode = create_mode
++ };
++ struct aopen_node aopen_node = {
++ .file = file
++ };
+
-+ err = au_ii_refresh(inode, &update);
++ IMustLock(dir);
++ AuDbg("open_flag 0%o\n", open_flag);
++ AuDbgDentry(dentry);
++
++ err = 0;
++ if (!au_di(dentry)) {
++ lkup_flags = LOOKUP_OPEN;
++ if (open_flag & O_CREAT)
++ lkup_flags |= LOOKUP_CREATE;
++ d = aufs_lookup(dir, dentry, lkup_flags);
++ if (IS_ERR(d)) {
++ err = PTR_ERR(d);
++ AuTraceErr(err);
++ goto out;
++ } else if (d) {
++ /*
++ * obsoleted dentry found.
++ * another error will be returned later.
++ */
++ d_drop(d);
++ AuDbgDentry(d);
++ dput(d);
++ }
++ AuDbgDentry(dentry);
++ }
++
++ if (d_is_positive(dentry)
++ || d_unhashed(dentry)
++ || d_unlinked(dentry)
++ || !(open_flag & O_CREAT)) {
++ err = au_aopen_no_open(file, dentry);
++ goto out; /* success */
++ }
++
++ err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN);
+ if (unlikely(err))
+ goto out;
+
-+ update = 0;
-+ iinfo = au_ii(inode);
-+ p = au_hinode(iinfo, iinfo->ii_btop);
-+ mode = (inode->i_mode & S_IFMT);
-+ isdir = S_ISDIR(mode);
-+ flags = au_hi_flags(inode, isdir);
-+ bbot = au_dbbot(dentry);
-+ for (bindex = au_dbtop(dentry); bindex <= bbot; bindex++) {
-+ struct inode *h_i, *h_inode;
-+ struct dentry *h_d;
++ sb = dentry->d_sb;
++ parent = dentry->d_parent; /* dir is locked */
++ di_write_lock_parent(parent);
++ err = au_lkup_dentry(dentry, /*btop*/0, AuLkup_ALLOW_NEG);
++ if (unlikely(err < 0))
++ goto out_parent;
+
-+ h_d = au_h_dptr(dentry, bindex);
-+ if (!h_d || d_is_negative(h_d))
-+ continue;
++ AuDbgDentry(dentry);
++ if (d_is_positive(dentry)) {
++ err = au_aopen_no_open(file, dentry);
++ goto out_parent; /* success */
++ }
+
-+ h_inode = d_inode(h_d);
-+ AuDebugOn(mode != (h_inode->i_mode & S_IFMT));
-+ if (iinfo->ii_btop <= bindex && bindex <= iinfo->ii_bbot) {
-+ h_i = au_h_iptr(inode, bindex);
-+ if (h_i) {
-+ if (h_i == h_inode)
-+ continue;
-+ err = -EIO;
-+ break;
-+ }
-+ }
-+ if (bindex < iinfo->ii_btop)
-+ iinfo->ii_btop = bindex;
-+ if (iinfo->ii_bbot < bindex)
-+ iinfo->ii_bbot = bindex;
-+ au_set_h_iptr(inode, bindex, au_igrab(h_inode), flags);
-+ update = 1;
++ args.file = alloc_empty_file(file->f_flags, current_cred());
++ err = PTR_ERR(args.file);
++ if (IS_ERR(args.file))
++ goto out_parent;
++
++ bindex = au_dbtop(dentry);
++ err = au_aopen_or_create(dir, dentry, &args);
++ AuTraceErr(err);
++ AuDbgFile(args.file);
++ file->f_mode = args.file->f_mode & ~FMODE_OPENED;
++ did_open = !!(args.file->f_mode & FMODE_OPENED);
++ if (!did_open) {
++ fput(args.file);
++ args.file = NULL;
+ }
-+ au_update_ibrange(inode, /*do_put_zero*/0);
-+ e = au_dy_irefresh(inode);
-+ if (unlikely(e && !err))
-+ err = e;
-+ if (!err)
-+ au_refresh_hinode_attr(inode, update && isdir);
++ di_write_unlock(parent);
++ di_write_unlock(dentry);
++ if (unlikely(err < 0)) {
++ if (args.file)
++ fput(args.file);
++ goto out_sb;
++ }
++
++ if (!did_open)
++ err = au_aopen_no_open(file, dentry);
++ else {
++ aopen_node.h_file = args.file;
++ err = au_aopen_do_open(file, dentry, &aopen_node);
++ }
++ if (unlikely(err < 0)) {
++ if (args.file)
++ fput(args.file);
++ if (did_open)
++ au_lcnt_dec(&args.br->br_nfiles);
++ }
++ goto out_sb; /* success */
+
++out_parent:
++ di_write_unlock(parent);
++ di_write_unlock(dentry);
++out_sb:
++ si_read_unlock(sb);
+out:
+ AuTraceErr(err);
++ AuDbgFile(file);
+ return err;
+}
+
-+static int set_inode(struct inode *inode, struct dentry *dentry)
++
++/* ---------------------------------------------------------------------- */
++
++static int au_wr_dir_cpup(struct dentry *dentry, struct dentry *parent,
++ const unsigned char add_entry, aufs_bindex_t bcpup,
++ aufs_bindex_t btop)
+{
+ int err;
-+ unsigned int flags;
-+ umode_t mode;
-+ aufs_bindex_t bindex, btop, btail;
-+ unsigned char isdir;
-+ struct dentry *h_dentry;
-+ struct inode *h_inode;
-+ struct au_iinfo *iinfo;
-+ const struct inode_operations *iop;
++ struct dentry *h_parent;
++ struct inode *h_dir;
+
-+ IiMustWriteLock(inode);
++ if (add_entry)
++ IMustLock(d_inode(parent));
++ else
++ di_write_lock_parent(parent);
+
+ err = 0;
-+ isdir = 0;
-+ iop = au_sbi(inode->i_sb)->si_iop_array;
-+ btop = au_dbtop(dentry);
-+ h_dentry = au_h_dptr(dentry, btop);
-+ h_inode = d_inode(h_dentry);
-+ mode = h_inode->i_mode;
-+ switch (mode & S_IFMT) {
-+ case S_IFREG:
-+ btail = au_dbtail(dentry);
-+ inode->i_op = iop + AuIop_OTHER;
-+ inode->i_fop = &aufs_file_fop;
-+ err = au_dy_iaop(inode, btop, h_inode);
-+ if (unlikely(err))
-+ goto out;
-+ break;
-+ case S_IFDIR:
-+ isdir = 1;
-+ btail = au_dbtaildir(dentry);
-+ inode->i_op = iop + AuIop_DIR;
-+ inode->i_fop = &aufs_dir_fop;
-+ break;
-+ case S_IFLNK:
-+ btail = au_dbtail(dentry);
-+ inode->i_op = iop + AuIop_SYMLINK;
-+ break;
-+ case S_IFBLK:
-+ case S_IFCHR:
-+ case S_IFIFO:
-+ case S_IFSOCK:
-+ btail = au_dbtail(dentry);
-+ inode->i_op = iop + AuIop_OTHER;
-+ init_special_inode(inode, mode, h_inode->i_rdev);
-+ break;
-+ default:
-+ AuIOErr("Unknown file type 0%o\n", mode);
-+ err = -EIO;
-+ goto out;
++ if (!au_h_dptr(parent, bcpup)) {
++ if (btop > bcpup)
++ err = au_cpup_dirs(dentry, bcpup);
++ else if (btop < bcpup)
++ err = au_cpdown_dirs(dentry, bcpup);
++ else
++ BUG();
+ }
++ if (!err && add_entry && !au_ftest_wrdir(add_entry, TMPFILE)) {
++ h_parent = au_h_dptr(parent, bcpup);
++ h_dir = d_inode(h_parent);
++ inode_lock_shared_nested(h_dir, AuLsc_I_PARENT);
++ err = au_lkup_neg(dentry, bcpup, /*wh*/0);
++ /* todo: no unlock here */
++ inode_unlock_shared(h_dir);
+
-+ /* do not set hnotify for whiteouted dirs (SHWH mode) */
-+ flags = au_hi_flags(inode, isdir);
-+ if (au_opt_test(au_mntflags(dentry->d_sb), SHWH)
-+ && au_ftest_hi(flags, HNOTIFY)
-+ && dentry->d_name.len > AUFS_WH_PFX_LEN
-+ && !memcmp(dentry->d_name.name, AUFS_WH_PFX, AUFS_WH_PFX_LEN))
-+ au_fclr_hi(flags, HNOTIFY);
-+ iinfo = au_ii(inode);
-+ iinfo->ii_btop = btop;
-+ iinfo->ii_bbot = btail;
-+ for (bindex = btop; bindex <= btail; bindex++) {
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (h_dentry)
-+ au_set_h_iptr(inode, bindex,
-+ au_igrab(d_inode(h_dentry)), flags);
++ AuDbg("bcpup %d\n", bcpup);
++ if (!err) {
++ if (d_really_is_negative(dentry))
++ au_set_h_dptr(dentry, btop, NULL);
++ au_update_dbrange(dentry, /*do_put_zero*/0);
++ }
+ }
-+ au_cpup_attr_all(inode, /*force*/1);
-+ /*
-+ * to force calling aufs_get_inode_acl() every time,
-+ * do not call cache_no_acl() for aufs inode.
-+ */
+
-+out:
++ if (!add_entry)
++ di_write_unlock(parent);
++ if (!err)
++ err = bcpup; /* success */
++
++ AuTraceErr(err);
+ return err;
+}
+
+/*
-+ * successful returns with iinfo write_locked
-+ * minus: errno
-+ * zero: success, matched
-+ * plus: no error, but unmatched
++ * decide the branch and the parent dir where we will create a new entry.
++ * returns new bindex or an error.
++ * copyup the parent dir if needed.
+ */
-+static int reval_inode(struct inode *inode, struct dentry *dentry)
++int au_wr_dir(struct dentry *dentry, struct dentry *src_dentry,
++ struct au_wr_dir_args *args)
+{
+ int err;
-+ unsigned int gen, igflags;
-+ aufs_bindex_t bindex, bbot;
-+ struct inode *h_inode, *h_dinode;
-+ struct dentry *h_dentry;
++ unsigned int flags;
++ aufs_bindex_t bcpup, btop, src_btop;
++ const unsigned char add_entry
++ = au_ftest_wrdir(args->flags, ADD_ENTRY)
++ | au_ftest_wrdir(args->flags, TMPFILE);
++ struct super_block *sb;
++ struct dentry *parent;
++ struct au_sbinfo *sbinfo;
+
-+ /*
-+ * before this function, if aufs got any iinfo lock, it must be only
-+ * one, the parent dir.
-+ * it can happen by UDBA and the obsoleted inode number.
-+ */
-+ err = -EIO;
-+ if (unlikely(inode->i_ino == parent_ino(dentry)))
-+ goto out;
++ sb = dentry->d_sb;
++ sbinfo = au_sbi(sb);
++ parent = dget_parent(dentry);
++ btop = au_dbtop(dentry);
++ bcpup = btop;
++ if (args->force_btgt < 0) {
++ if (src_dentry) {
++ src_btop = au_dbtop(src_dentry);
++ if (src_btop < btop)
++ bcpup = src_btop;
++ } else if (add_entry) {
++ flags = 0;
++ if (au_ftest_wrdir(args->flags, ISDIR))
++ au_fset_wbr(flags, DIR);
++ err = AuWbrCreate(sbinfo, dentry, flags);
++ bcpup = err;
++ }
+
-+ err = 1;
-+ ii_write_lock_new_child(inode);
-+ h_dentry = au_h_dptr(dentry, au_dbtop(dentry));
-+ h_dinode = d_inode(h_dentry);
-+ bbot = au_ibbot(inode);
-+ for (bindex = au_ibtop(inode); bindex <= bbot; bindex++) {
-+ h_inode = au_h_iptr(inode, bindex);
-+ if (!h_inode || h_inode != h_dinode)
-+ continue;
++ if (bcpup < 0 || au_test_ro(sb, bcpup, d_inode(dentry))) {
++ if (add_entry)
++ err = AuWbrCopyup(sbinfo, dentry);
++ else {
++ if (!IS_ROOT(dentry)) {
++ di_read_lock_parent(parent, !AuLock_IR);
++ err = AuWbrCopyup(sbinfo, dentry);
++ di_read_unlock(parent, !AuLock_IR);
++ } else
++ err = AuWbrCopyup(sbinfo, dentry);
++ }
++ bcpup = err;
++ if (unlikely(err < 0))
++ goto out;
++ }
++ } else {
++ bcpup = args->force_btgt;
++ AuDebugOn(au_test_ro(sb, bcpup, d_inode(dentry)));
++ }
+
-+ err = 0;
-+ gen = au_iigen(inode, &igflags);
-+ if (gen == au_digen(dentry)
-+ && !au_ig_ftest(igflags, HALF_REFRESHED))
-+ break;
++ AuDbg("btop %d, bcpup %d\n", btop, bcpup);
++ err = bcpup;
++ if (bcpup == btop)
++ goto out; /* success */
+
-+ /* fully refresh inode using dentry */
-+ err = au_refresh_hinode(inode, dentry);
-+ if (!err)
-+ au_update_iigen(inode, /*half*/0);
-+ break;
++ /* copyup the new parent into the branch we process */
++ err = au_wr_dir_cpup(dentry, parent, add_entry, bcpup, btop);
++ if (err >= 0) {
++ if (d_really_is_negative(dentry)) {
++ au_set_h_dptr(dentry, btop, NULL);
++ au_set_dbtop(dentry, bcpup);
++ au_set_dbbot(dentry, bcpup);
++ }
++ AuDebugOn(add_entry
++ && !au_ftest_wrdir(args->flags, TMPFILE)
++ && !au_h_dptr(dentry, bcpup));
+ }
+
-+ if (unlikely(err))
-+ ii_write_unlock(inode);
+out:
++ dput(parent);
+ return err;
+}
+
-+int au_ino(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
-+ unsigned int d_type, ino_t *ino)
++/* ---------------------------------------------------------------------- */
++
++void au_pin_hdir_unlock(struct au_pin *p)
+{
-+ int err, idx;
-+ const int isnondir = d_type != DT_DIR;
++ if (p->hdir)
++ au_hn_inode_unlock(p->hdir);
++}
+
-+ /* prevent hardlinked inode number from race condition */
-+ if (isnondir) {
-+ err = au_xinondir_enter(sb, bindex, h_ino, &idx);
-+ if (unlikely(err))
-+ goto out;
-+ }
++int au_pin_hdir_lock(struct au_pin *p)
++{
++ int err;
+
-+ err = au_xino_read(sb, bindex, h_ino, ino);
-+ if (unlikely(err))
-+ goto out_xinondir;
++ err = 0;
++ if (!p->hdir)
++ goto out;
+
-+ if (!*ino) {
-+ err = -EIO;
-+ *ino = au_xino_new_ino(sb);
-+ if (unlikely(!*ino))
-+ goto out_xinondir;
-+ err = au_xino_write(sb, bindex, h_ino, *ino);
-+ if (unlikely(err))
-+ goto out_xinondir;
-+ }
++ /* even if an error happens later, keep this lock */
++ au_hn_inode_lock_nested(p->hdir, p->lsc_hi);
++
++ err = -EBUSY;
++ if (unlikely(p->hdir->hi_inode != d_inode(p->h_parent)))
++ goto out;
++
++ err = 0;
++ if (p->h_dentry)
++ err = au_h_verify(p->h_dentry, p->udba, p->hdir->hi_inode,
++ p->h_parent, p->br);
+
-+out_xinondir:
-+ if (isnondir && idx >= 0)
-+ au_xinondir_leave(sb, bindex, h_ino, idx);
+out:
+ return err;
+}
+
-+/* successful returns with iinfo write_locked */
-+/* todo: return with unlocked? */
-+struct inode *au_new_inode(struct dentry *dentry, int must_new)
++int au_pin_hdir_relock(struct au_pin *p)
+{
-+ struct inode *inode, *h_inode;
-+ struct dentry *h_dentry;
-+ struct super_block *sb;
-+ ino_t h_ino, ino;
-+ int err, idx, hlinked;
-+ aufs_bindex_t btop;
-+
-+ sb = dentry->d_sb;
-+ btop = au_dbtop(dentry);
-+ h_dentry = au_h_dptr(dentry, btop);
-+ h_inode = d_inode(h_dentry);
-+ h_ino = h_inode->i_ino;
-+ hlinked = !d_is_dir(h_dentry) && h_inode->i_nlink > 1;
-+
-+new_ino:
-+ /*
-+ * stop 'race'-ing between hardlinks under different
-+ * parents.
-+ */
-+ if (hlinked) {
-+ err = au_xinondir_enter(sb, btop, h_ino, &idx);
-+ inode = ERR_PTR(err);
-+ if (unlikely(err))
-+ goto out;
-+ }
++ int err, i;
++ struct inode *h_i;
++ struct dentry *h_d[] = {
++ p->h_dentry,
++ p->h_parent
++ };
+
-+ err = au_xino_read(sb, btop, h_ino, &ino);
-+ inode = ERR_PTR(err);
++ err = au_pin_hdir_lock(p);
+ if (unlikely(err))
-+ goto out_xinondir;
-+
-+ if (!ino) {
-+ ino = au_xino_new_ino(sb);
-+ if (unlikely(!ino)) {
-+ inode = ERR_PTR(-EIO);
-+ goto out_xinondir;
-+ }
-+ }
-+
-+ AuDbg("i%lu\n", (unsigned long)ino);
-+ inode = au_iget_locked(sb, ino);
-+ err = PTR_ERR(inode);
-+ if (IS_ERR(inode))
-+ goto out_xinondir;
-+
-+ AuDbg("%lx, new %d\n", inode->i_state, !!(inode->i_state & I_NEW));
-+ if (inode->i_state & I_NEW) {
-+ ii_write_lock_new_child(inode);
-+ err = set_inode(inode, dentry);
-+ if (!err) {
-+ unlock_new_inode(inode);
-+ goto out_xinondir; /* success */
-+ }
++ goto out;
+
-+ /*
-+ * iget_failed() calls iput(), but we need to call
-+ * ii_write_unlock() after iget_failed(). so dirty hack for
-+ * i_count.
-+ */
-+ atomic_inc(&inode->i_count);
-+ iget_failed(inode);
-+ ii_write_unlock(inode);
-+ au_xino_write(sb, btop, h_ino, /*ino*/0);
-+ /* ignore this error */
-+ goto out_iput;
-+ } else if (!must_new && !IS_DEADDIR(inode) && inode->i_nlink) {
-+ /*
-+ * horrible race condition between lookup, readdir and copyup
-+ * (or something).
-+ */
-+ if (hlinked && idx >= 0)
-+ au_xinondir_leave(sb, btop, h_ino, idx);
-+ err = reval_inode(inode, dentry);
-+ if (unlikely(err < 0)) {
-+ hlinked = 0;
-+ goto out_iput;
-+ }
-+ if (!err)
-+ goto out; /* success */
-+ else if (hlinked && idx >= 0) {
-+ err = au_xinondir_enter(sb, btop, h_ino, &idx);
-+ if (unlikely(err)) {
-+ iput(inode);
-+ inode = ERR_PTR(err);
-+ goto out;
-+ }
++ for (i = 0; !err && i < sizeof(h_d)/sizeof(*h_d); i++) {
++ if (!h_d[i])
++ continue;
++ if (d_is_positive(h_d[i])) {
++ h_i = d_inode(h_d[i]);
++ err = !h_i->i_nlink;
+ }
+ }
+
-+ if (unlikely(au_test_fs_unique_ino(h_inode)))
-+ AuWarn1("Warning: Un-notified UDBA or repeatedly renamed dir,"
-+ " b%d, %s, %pd, hi%lu, i%lu.\n",
-+ btop, au_sbtype(h_dentry->d_sb), dentry,
-+ (unsigned long)h_ino, (unsigned long)ino);
-+ ino = 0;
-+ err = au_xino_write(sb, btop, h_ino, /*ino*/0);
-+ if (!err) {
-+ iput(inode);
-+ if (hlinked && idx >= 0)
-+ au_xinondir_leave(sb, btop, h_ino, idx);
-+ goto new_ino;
-+ }
-+
-+out_iput:
-+ iput(inode);
-+ inode = ERR_PTR(err);
-+out_xinondir:
-+ if (hlinked && idx >= 0)
-+ au_xinondir_leave(sb, btop, h_ino, idx);
+out:
-+ return inode;
++ return err;
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+int au_test_ro(struct super_block *sb, aufs_bindex_t bindex,
-+ struct inode *inode)
++static void au_pin_hdir_set_owner(struct au_pin *p, struct task_struct *task)
+{
-+ int err;
-+ struct inode *hi;
-+
-+ err = au_br_rdonly(au_sbr(sb, bindex));
++ atomic_long_set(&p->hdir->hi_inode->i_rwsem.owner, (long)task);
++}
+
-+ /* pseudo-link after flushed may happen out of bounds */
-+ if (!err
-+ && inode
-+ && au_ibtop(inode) <= bindex
-+ && bindex <= au_ibbot(inode)) {
-+ /*
-+ * permission check is unnecessary since vfsub routine
-+ * will be called later
-+ */
-+ hi = au_h_iptr(inode, bindex);
-+ if (hi)
-+ err = IS_IMMUTABLE(hi) ? -EROFS : 0;
++void au_pin_hdir_acquire_nest(struct au_pin *p)
++{
++ if (p->hdir) {
++ rwsem_acquire_nest(&p->hdir->hi_inode->i_rwsem.dep_map,
++ p->lsc_hi, 0, NULL, _RET_IP_);
++ au_pin_hdir_set_owner(p, current);
+ }
-+
-+ return err;
+}
+
-+int au_test_h_perm(struct mnt_idmap *h_idmap, struct inode *h_inode,
-+ int mask)
++void au_pin_hdir_release(struct au_pin *p)
+{
-+ if (uid_eq(current_fsuid(), GLOBAL_ROOT_UID))
-+ return 0;
-+ return inode_permission(h_idmap, h_inode, mask);
++ if (p->hdir) {
++ au_pin_hdir_set_owner(p, p->task);
++ rwsem_release(&p->hdir->hi_inode->i_rwsem.dep_map, _RET_IP_);
++ }
+}
+
-+int au_test_h_perm_sio(struct mnt_idmap *h_idmap, struct inode *h_inode,
-+ int mask)
++struct dentry *au_pinned_h_parent(struct au_pin *pin)
+{
-+ if (au_test_nfs(h_inode->i_sb)
-+ && (mask & MAY_WRITE)
-+ && S_ISDIR(h_inode->i_mode))
-+ mask |= MAY_READ; /* force permission check */
-+ return au_test_h_perm(h_idmap, h_inode, mask);
++ if (pin && pin->parent)
++ return au_h_dptr(pin->parent, pin->bindex);
++ return NULL;
+}
-diff -urN /usr/share/empty/fs/aufs/inode.h linux/fs/aufs/inode.h
---- /usr/share/empty/fs/aufs/inode.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/inode.h 2023-10-31 09:31:04.199880750 +0100
-@@ -0,0 +1,707 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2005-2022 Junjiro R. Okajima
-+ *
-+ * This program 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/>.
-+ */
-+
-+/*
-+ * inode operations
-+ */
-+
-+#ifndef __AUFS_INODE_H__
-+#define __AUFS_INODE_H__
-+
-+#ifdef __KERNEL__
+
-+#include <linux/fsnotify.h>
-+#include "rwsem.h"
-+
-+struct vfsmount;
++void au_unpin(struct au_pin *p)
++{
++ if (p->hdir)
++ au_pin_hdir_unlock(p);
++ if (p->h_mnt && au_ftest_pin(p->flags, MNT_WRITE))
++ vfsub_mnt_drop_write(p->h_mnt);
++ if (!p->hdir)
++ return;
+
-+struct au_hnotify {
-+#ifdef CONFIG_AUFS_HNOTIFY
-+#ifdef CONFIG_AUFS_HFSNOTIFY
-+ /* never use fsnotify_add_vfsmount_mark() */
-+ struct fsnotify_mark hn_mark;
-+#endif
-+ struct inode *hn_aufs_inode; /* no get/put */
-+ struct rcu_head rcu;
-+#endif
-+} ____cacheline_aligned_in_smp;
++ if (!au_ftest_pin(p->flags, DI_LOCKED))
++ di_read_unlock(p->parent, AuLock_IR);
++ iput(p->hdir->hi_inode);
++ dput(p->parent);
++ p->parent = NULL;
++ p->hdir = NULL;
++ p->h_mnt = NULL;
++ /* do not clear p->task */
++}
+
-+struct au_hinode {
-+ struct inode *hi_inode;
-+ aufs_bindex_t hi_id;
-+#ifdef CONFIG_AUFS_HNOTIFY
-+ struct au_hnotify *hi_notify;
-+#endif
++int au_do_pin(struct au_pin *p)
++{
++ int err;
++ struct super_block *sb;
++ struct inode *h_dir;
+
-+ /* reference to the copied-up whiteout with get/put */
-+ struct dentry *hi_whdentry;
-+};
++ err = 0;
++ sb = p->dentry->d_sb;
++ p->br = au_sbr(sb, p->bindex);
++ if (IS_ROOT(p->dentry)) {
++ if (au_ftest_pin(p->flags, MNT_WRITE)) {
++ p->h_mnt = au_br_mnt(p->br);
++ err = vfsub_mnt_want_write(p->h_mnt);
++ if (unlikely(err)) {
++ au_fclr_pin(p->flags, MNT_WRITE);
++ goto out_err;
++ }
++ }
++ goto out;
++ }
+
-+/* ig_flags */
-+#define AuIG_HALF_REFRESHED 1
-+#define au_ig_ftest(flags, name) ((flags) & AuIG_##name)
-+#define au_ig_fset(flags, name) \
-+ do { (flags) |= AuIG_##name; } while (0)
-+#define au_ig_fclr(flags, name) \
-+ do { (flags) &= ~AuIG_##name; } while (0)
++ p->h_dentry = NULL;
++ if (p->bindex <= au_dbbot(p->dentry))
++ p->h_dentry = au_h_dptr(p->dentry, p->bindex);
+
-+struct au_iigen {
-+ spinlock_t ig_spin;
-+ __u32 ig_generation, ig_flags;
-+};
++ p->parent = dget_parent(p->dentry);
++ if (!au_ftest_pin(p->flags, DI_LOCKED))
++ di_read_lock(p->parent, AuLock_IR, p->lsc_di);
+
-+struct au_vdir;
-+struct au_iinfo {
-+ struct au_iigen ii_generation;
-+ struct super_block *ii_hsb1; /* no get/put */
++ h_dir = NULL;
++ p->h_parent = au_h_dptr(p->parent, p->bindex);
++ p->hdir = au_hi(d_inode(p->parent), p->bindex);
++ if (p->hdir)
++ h_dir = p->hdir->hi_inode;
+
-+ struct au_rwsem ii_rwsem;
-+ aufs_bindex_t ii_btop, ii_bbot;
-+ __u32 ii_higen;
-+ struct au_hinode *ii_hinode;
-+ struct au_vdir *ii_vdir;
-+};
++ /*
++ * udba case, or
++ * if DI_LOCKED is not set, then p->parent may be different
++ * and h_parent can be NULL.
++ */
++ if (unlikely(!p->hdir || !h_dir || !p->h_parent)) {
++ err = -EBUSY;
++ if (!au_ftest_pin(p->flags, DI_LOCKED))
++ di_read_unlock(p->parent, AuLock_IR);
++ dput(p->parent);
++ p->parent = NULL;
++ goto out_err;
++ }
+
-+struct au_icntnr {
-+ struct au_iinfo iinfo;
-+ struct inode vfs_inode;
-+ struct hlist_bl_node plink;
-+ struct rcu_head rcu;
-+} ____cacheline_aligned_in_smp;
++ if (au_ftest_pin(p->flags, MNT_WRITE)) {
++ p->h_mnt = au_br_mnt(p->br);
++ err = vfsub_mnt_want_write(p->h_mnt);
++ if (unlikely(err)) {
++ au_fclr_pin(p->flags, MNT_WRITE);
++ if (!au_ftest_pin(p->flags, DI_LOCKED))
++ di_read_unlock(p->parent, AuLock_IR);
++ dput(p->parent);
++ p->parent = NULL;
++ goto out_err;
++ }
++ }
+
-+/* au_pin flags */
-+#define AuPin_DI_LOCKED 1
-+#define AuPin_MNT_WRITE (1 << 1)
-+#define au_ftest_pin(flags, name) ((flags) & AuPin_##name)
-+#define au_fset_pin(flags, name) \
-+ do { (flags) |= AuPin_##name; } while (0)
-+#define au_fclr_pin(flags, name) \
-+ do { (flags) &= ~AuPin_##name; } while (0)
++ au_igrab(h_dir);
++ err = au_pin_hdir_lock(p);
++ if (!err)
++ goto out; /* success */
+
-+struct au_pin {
-+ /* input */
-+ struct dentry *dentry;
-+ unsigned int udba;
-+ unsigned char lsc_di, lsc_hi, flags;
-+ aufs_bindex_t bindex;
++ au_unpin(p);
+
-+ /* output */
-+ struct dentry *parent;
-+ struct au_hinode *hdir;
-+ struct vfsmount *h_mnt;
++out_err:
++ pr_err("err %d\n", err);
++ err = au_busy_or_stale();
++out:
++ return err;
++}
+
-+ /* temporary unlock/relock for copyup */
-+ struct dentry *h_dentry, *h_parent;
-+ struct au_branch *br;
-+ struct task_struct *task;
-+};
++void au_pin_init(struct au_pin *p, struct dentry *dentry,
++ aufs_bindex_t bindex, int lsc_di, int lsc_hi,
++ unsigned int udba, unsigned char flags)
++{
++ p->dentry = dentry;
++ p->udba = udba;
++ p->lsc_di = lsc_di;
++ p->lsc_hi = lsc_hi;
++ p->flags = flags;
++ p->bindex = bindex;
+
-+void au_pin_hdir_unlock(struct au_pin *p);
-+int au_pin_hdir_lock(struct au_pin *p);
-+int au_pin_hdir_relock(struct au_pin *p);
-+void au_pin_hdir_acquire_nest(struct au_pin *p);
-+void au_pin_hdir_release(struct au_pin *p);
++ p->parent = NULL;
++ p->hdir = NULL;
++ p->h_mnt = NULL;
+
-+/* ---------------------------------------------------------------------- */
++ p->h_dentry = NULL;
++ p->h_parent = NULL;
++ p->br = NULL;
++ p->task = current;
++}
+
-+static inline struct au_iinfo *au_ii(struct inode *inode)
++int au_pin(struct au_pin *pin, struct dentry *dentry, aufs_bindex_t bindex,
++ unsigned int udba, unsigned char flags)
+{
-+ BUG_ON(is_bad_inode(inode));
-+ return &(container_of(inode, struct au_icntnr, vfs_inode)->iinfo);
++ au_pin_init(pin, dentry, bindex, AuLsc_DI_PARENT, AuLsc_I_PARENT2,
++ udba, flags);
++ return au_do_pin(pin);
+}
+
+/* ---------------------------------------------------------------------- */
+
-+/* inode.c */
-+struct inode *au_igrab(struct inode *inode);
-+void au_refresh_iop(struct inode *inode, int force_getattr);
-+int au_refresh_hinode_self(struct inode *inode);
-+int au_refresh_hinode(struct inode *inode, struct dentry *dentry);
-+int au_ino(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
-+ unsigned int d_type, ino_t *ino);
-+struct inode *au_new_inode(struct dentry *dentry, int must_new);
-+int au_test_ro(struct super_block *sb, aufs_bindex_t bindex,
-+ struct inode *inode);
-+int au_test_h_perm(struct mnt_idmap *h_idmap, struct inode *h_inode,
-+ int mask);
-+int au_test_h_perm_sio(struct mnt_idmap *h_idmap, struct inode *h_inode,
-+ int mask);
-+
-+static inline int au_wh_ino(struct super_block *sb, aufs_bindex_t bindex,
-+ ino_t h_ino, unsigned int d_type, ino_t *ino)
++/*
++ * ->setattr() and ->getattr() are called in various cases.
++ * chmod, stat: dentry is revalidated.
++ * fchmod, fstat: file and dentry are not revalidated, additionally they may be
++ * unhashed.
++ * for ->setattr(), ia->ia_file is passed from ftruncate only.
++ */
++/* todo: consolidate with do_refresh() and simple_reval_dpath() */
++int au_reval_for_attr(struct dentry *dentry, unsigned int sigen)
+{
-+#ifdef CONFIG_AUFS_SHWH
-+ return au_ino(sb, bindex, h_ino, d_type, ino);
-+#else
-+ return 0;
-+#endif
-+}
-+
-+/* i_op.c */
-+enum {
-+ AuIop_SYMLINK,
-+ AuIop_DIR,
-+ AuIop_OTHER,
-+ AuIop_Last
-+};
-+extern struct inode_operations aufs_iop[AuIop_Last], /* not const */
-+ aufs_iop_nogetattr[AuIop_Last];
++ int err;
++ struct dentry *parent;
+
-+/* au_wr_dir flags */
-+#define AuWrDir_ADD_ENTRY 1
-+#define AuWrDir_ISDIR (1 << 1)
-+#define AuWrDir_TMPFILE (1 << 2)
-+#define au_ftest_wrdir(flags, name) ((flags) & AuWrDir_##name)
-+#define au_fset_wrdir(flags, name) \
-+ do { (flags) |= AuWrDir_##name; } while (0)
-+#define au_fclr_wrdir(flags, name) \
-+ do { (flags) &= ~AuWrDir_##name; } while (0)
++ err = 0;
++ if (au_digen_test(dentry, sigen)) {
++ parent = dget_parent(dentry);
++ di_read_lock_parent(parent, AuLock_IR);
++ err = au_refresh_dentry(dentry, parent);
++ di_read_unlock(parent, AuLock_IR);
++ dput(parent);
++ }
+
-+struct au_wr_dir_args {
-+ aufs_bindex_t force_btgt;
-+ unsigned char flags;
-+};
-+int au_wr_dir(struct dentry *dentry, struct dentry *src_dentry,
-+ struct au_wr_dir_args *args);
++ AuTraceErr(err);
++ return err;
++}
+
-+struct dentry *au_pinned_h_parent(struct au_pin *pin);
-+void au_pin_init(struct au_pin *pin, struct dentry *dentry,
-+ aufs_bindex_t bindex, int lsc_di, int lsc_hi,
-+ unsigned int udba, unsigned char flags);
-+int au_pin(struct au_pin *pin, struct dentry *dentry, aufs_bindex_t bindex,
-+ unsigned int udba, unsigned char flags) __must_check;
-+int au_do_pin(struct au_pin *pin) __must_check;
-+void au_unpin(struct au_pin *pin);
-+int au_reval_for_attr(struct dentry *dentry, unsigned int sigen);
++int au_pin_and_icpup(struct dentry *dentry, struct iattr *ia,
++ struct au_icpup_args *a)
++{
++ int err;
++ loff_t sz;
++ aufs_bindex_t btop, ibtop;
++ struct dentry *hi_wh, *parent;
++ struct inode *inode;
++ struct au_wr_dir_args wr_dir_args = {
++ .force_btgt = -1,
++ .flags = 0
++ };
+
-+#define AuIcpup_DID_CPUP 1
-+#define au_ftest_icpup(flags, name) ((flags) & AuIcpup_##name)
-+#define au_fset_icpup(flags, name) \
-+ do { (flags) |= AuIcpup_##name; } while (0)
-+#define au_fclr_icpup(flags, name) \
-+ do { (flags) &= ~AuIcpup_##name; } while (0)
++ if (d_is_dir(dentry))
++ au_fset_wrdir(wr_dir_args.flags, ISDIR);
++ /* plink or hi_wh() case */
++ btop = au_dbtop(dentry);
++ inode = d_inode(dentry);
++ ibtop = au_ibtop(inode);
++ if (btop != ibtop && !au_test_ro(inode->i_sb, ibtop, inode))
++ wr_dir_args.force_btgt = ibtop;
++ err = au_wr_dir(dentry, /*src_dentry*/NULL, &wr_dir_args);
++ if (unlikely(err < 0))
++ goto out;
++ a->btgt = err;
++ if (err != btop)
++ au_fset_icpup(a->flags, DID_CPUP);
+
-+struct au_icpup_args {
-+ unsigned char flags;
-+ unsigned char pin_flags;
-+ aufs_bindex_t btgt;
-+ unsigned int udba;
-+ struct au_pin pin;
-+ struct path h_path;
-+ struct inode *h_inode;
-+};
++ err = 0;
++ a->pin_flags = AuPin_MNT_WRITE;
++ parent = NULL;
++ if (!IS_ROOT(dentry)) {
++ au_fset_pin(a->pin_flags, DI_LOCKED);
++ parent = dget_parent(dentry);
++ di_write_lock_parent(parent);
++ }
+
-+int au_pin_and_icpup(struct dentry *dentry, struct iattr *ia,
-+ struct au_icpup_args *a);
++ err = au_pin(&a->pin, dentry, a->btgt, a->udba, a->pin_flags);
++ if (unlikely(err))
++ goto out_parent;
+
-+int au_h_path_getattr(struct dentry *dentry, struct inode *inode, int force,
-+ struct path *h_path, int locked);
++ sz = -1;
++ a->h_path.dentry = au_h_dptr(dentry, btop);
++ a->h_inode = d_inode(a->h_path.dentry);
++ if (ia && (ia->ia_valid & ATTR_SIZE)) {
++ inode_lock_shared_nested(a->h_inode, AuLsc_I_CHILD);
++ if (ia->ia_size < i_size_read(a->h_inode))
++ sz = ia->ia_size;
++ inode_unlock_shared(a->h_inode);
++ }
+
-+/* i_op_add.c */
-+int au_may_add(struct dentry *dentry, aufs_bindex_t bindex,
-+ struct dentry *h_parent, int isdir);
-+int aufs_mknod(struct mnt_idmap *idmap, struct inode *dir,
-+ struct dentry *dentry, umode_t mode, dev_t dev);
-+int aufs_symlink(struct mnt_idmap *idmap, struct inode *dir,
-+ struct dentry *dentry, const char *symname);
-+int aufs_create(struct mnt_idmap *idmap, struct inode *dir,
-+ struct dentry *dentry, umode_t mode, bool want_excl);
-+struct vfsub_aopen_args;
-+int au_aopen_or_create(struct inode *dir, struct dentry *dentry,
-+ struct vfsub_aopen_args *args);
-+int aufs_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
-+ struct file *file, umode_t mode);
-+int aufs_link(struct dentry *src_dentry, struct inode *dir,
-+ struct dentry *dentry);
-+int aufs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
-+ struct dentry *dentry, umode_t mode);
++ hi_wh = NULL;
++ if (au_ftest_icpup(a->flags, DID_CPUP) && d_unlinked(dentry)) {
++ hi_wh = au_hi_wh(inode, a->btgt);
++ if (!hi_wh) {
++ struct au_cp_generic cpg = {
++ .dentry = dentry,
++ .bdst = a->btgt,
++ .bsrc = -1,
++ .len = sz,
++ .pin = &a->pin
++ };
++ err = au_sio_cpup_wh(&cpg, /*file*/NULL);
++ if (unlikely(err))
++ goto out_unlock;
++ hi_wh = au_hi_wh(inode, a->btgt);
++ /* todo: revalidate hi_wh? */
++ }
++ }
+
-+/* i_op_del.c */
-+int au_wr_dir_need_wh(struct dentry *dentry, int isdir, aufs_bindex_t *bcpup);
-+int au_may_del(struct dentry *dentry, aufs_bindex_t bindex,
-+ struct dentry *h_parent, int isdir);
-+int aufs_unlink(struct inode *dir, struct dentry *dentry);
-+int aufs_rmdir(struct inode *dir, struct dentry *dentry);
++ if (parent) {
++ au_pin_set_parent_lflag(&a->pin, /*lflag*/0);
++ di_downgrade_lock(parent, AuLock_IR);
++ dput(parent);
++ parent = NULL;
++ }
++ if (!au_ftest_icpup(a->flags, DID_CPUP))
++ goto out; /* success */
+
-+/* i_op_ren.c */
-+int au_wbr(struct dentry *dentry, aufs_bindex_t btgt);
-+int aufs_rename(struct mnt_idmap *idmap,
-+ struct inode *_src_dir, struct dentry *_src_dentry,
-+ struct inode *_dst_dir, struct dentry *_dst_dentry,
-+ unsigned int _flags);
++ if (!d_unhashed(dentry)) {
++ struct au_cp_generic cpg = {
++ .dentry = dentry,
++ .bdst = a->btgt,
++ .bsrc = btop,
++ .len = sz,
++ .pin = &a->pin,
++ .flags = AuCpup_DTIME | AuCpup_HOPEN
++ };
++ err = au_sio_cpup_simple(&cpg);
++ if (!err)
++ a->h_path.dentry = au_h_dptr(dentry, a->btgt);
++ } else if (!hi_wh)
++ a->h_path.dentry = au_h_dptr(dentry, a->btgt);
++ else
++ a->h_path.dentry = hi_wh; /* do not dget here */
+
-+/* iinfo.c */
-+struct inode *au_h_iptr(struct inode *inode, aufs_bindex_t bindex);
-+void au_hiput(struct au_hinode *hinode);
-+void au_set_hi_wh(struct inode *inode, aufs_bindex_t bindex,
-+ struct dentry *h_wh);
-+unsigned int au_hi_flags(struct inode *inode, int isdir);
++out_unlock:
++ a->h_inode = d_inode(a->h_path.dentry);
++ if (!err)
++ goto out; /* success */
++ au_unpin(&a->pin);
++out_parent:
++ if (parent) {
++ di_write_unlock(parent);
++ dput(parent);
++ }
++out:
++ if (!err)
++ inode_lock_nested(a->h_inode, AuLsc_I_CHILD);
++ return err;
++}
+
-+/* hinode flags */
-+#define AuHi_XINO 1
-+#define AuHi_HNOTIFY (1 << 1)
-+#define au_ftest_hi(flags, name) ((flags) & AuHi_##name)
-+#define au_fset_hi(flags, name) \
-+ do { (flags) |= AuHi_##name; } while (0)
-+#define au_fclr_hi(flags, name) \
-+ do { (flags) &= ~AuHi_##name; } while (0)
++static int aufs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
++ struct iattr *ia)
++{
++ int err;
++ struct inode *inode, *delegated;
++ struct super_block *sb;
++ struct file *file;
++ struct au_icpup_args *a;
++ struct mnt_idmap *h_idmap;
+
-+#ifndef CONFIG_AUFS_HNOTIFY
-+#undef AuHi_HNOTIFY
-+#define AuHi_HNOTIFY 0
-+#endif
++ inode = d_inode(dentry);
++ IMustLock(inode);
+
-+void au_set_h_iptr(struct inode *inode, aufs_bindex_t bindex,
-+ struct inode *h_inode, unsigned int flags);
++ err = setattr_prepare(idmap, dentry, ia);
++ if (unlikely(err))
++ goto out;
+
-+void au_update_iigen(struct inode *inode, int half);
-+void au_update_ibrange(struct inode *inode, int do_put_zero);
++ err = -ENOMEM;
++ a = kzalloc(sizeof(*a), GFP_NOFS);
++ if (unlikely(!a))
++ goto out;
+
-+void au_icntnr_init_once(void *_c);
-+void au_hinode_init(struct au_hinode *hinode);
-+int au_iinfo_init(struct inode *inode);
-+void au_iinfo_fin(struct inode *inode);
-+int au_hinode_realloc(struct au_iinfo *iinfo, int nbr, int may_shrink);
++ if (ia->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID))
++ ia->ia_valid &= ~ATTR_MODE;
+
-+#ifdef CONFIG_PROC_FS
-+/* plink.c */
-+int au_plink_maint(struct super_block *sb, int flags);
-+struct au_sbinfo;
-+void au_plink_maint_leave(struct au_sbinfo *sbinfo);
-+int au_plink_maint_enter(struct super_block *sb);
-+#ifdef CONFIG_AUFS_DEBUG
-+void au_plink_list(struct super_block *sb);
-+#else
-+AuStubVoid(au_plink_list, struct super_block *sb)
-+#endif
-+int au_plink_test(struct inode *inode);
-+struct dentry *au_plink_lkup(struct inode *inode, aufs_bindex_t bindex);
-+void au_plink_append(struct inode *inode, aufs_bindex_t bindex,
-+ struct dentry *h_dentry);
-+void au_plink_put(struct super_block *sb, int verbose);
-+void au_plink_clean(struct super_block *sb, int verbose);
-+void au_plink_half_refresh(struct super_block *sb, aufs_bindex_t br_id);
-+#else
-+AuStubInt0(au_plink_maint, struct super_block *sb, int flags);
-+AuStubVoid(au_plink_maint_leave, struct au_sbinfo *sbinfo);
-+AuStubInt0(au_plink_maint_enter, struct super_block *sb);
-+AuStubVoid(au_plink_list, struct super_block *sb);
-+AuStubInt0(au_plink_test, struct inode *inode);
-+AuStub(struct dentry *, au_plink_lkup, return NULL,
-+ struct inode *inode, aufs_bindex_t bindex);
-+AuStubVoid(au_plink_append, struct inode *inode, aufs_bindex_t bindex,
-+ struct dentry *h_dentry);
-+AuStubVoid(au_plink_put, struct super_block *sb, int verbose);
-+AuStubVoid(au_plink_clean, struct super_block *sb, int verbose);
-+AuStubVoid(au_plink_half_refresh, struct super_block *sb, aufs_bindex_t br_id);
-+#endif /* CONFIG_PROC_FS */
++ file = NULL;
++ sb = dentry->d_sb;
++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
++ if (unlikely(err))
++ goto out_kfree;
+
-+#ifdef CONFIG_AUFS_XATTR
-+/* xattr.c */
-+int au_cpup_xattr(struct path *h_dst, struct path *h_src, int ignore_flags,
-+ unsigned int verbose);
-+ssize_t aufs_listxattr(struct dentry *dentry, char *list, size_t size);
-+void au_xattr_init(struct super_block *sb);
-+#else
-+AuStubInt0(au_cpup_xattr, struct path *h_dst, struct path *h_src,
-+ int ignore_flags, unsigned int verbose);
-+AuStubVoid(au_xattr_init, struct super_block *sb);
-+#endif
++ if (ia->ia_valid & ATTR_FILE) {
++ /* currently ftruncate(2) only */
++ AuDebugOn(!d_is_reg(dentry));
++ file = ia->ia_file;
++ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1,
++ /*fi_lsc*/0);
++ if (unlikely(err))
++ goto out_si;
++ ia->ia_file = au_hf_top(file);
++ a->udba = AuOpt_UDBA_NONE;
++ } else {
++ /* fchmod() doesn't pass ia_file */
++ a->udba = au_opt_udba(sb);
++ di_write_lock_child(dentry);
++ /* no d_unlinked(), to set UDBA_NONE for root */
++ if (d_unhashed(dentry))
++ a->udba = AuOpt_UDBA_NONE;
++ if (a->udba != AuOpt_UDBA_NONE) {
++ AuDebugOn(IS_ROOT(dentry));
++ err = au_reval_for_attr(dentry, au_sigen(sb));
++ if (unlikely(err))
++ goto out_dentry;
++ }
++ }
+
-+#ifdef CONFIG_FS_POSIX_ACL
-+struct posix_acl *aufs_get_inode_acl(struct inode *inode, int type, bool rcu);
-+struct posix_acl *aufs_get_acl(struct mnt_idmap *idmap,
-+ struct dentry *dentry, int type);
-+int aufs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
-+ struct posix_acl *acl, int type);
-+#endif
++ err = au_pin_and_icpup(dentry, ia, a);
++ if (unlikely(err < 0))
++ goto out_dentry;
++ if (au_ftest_icpup(a->flags, DID_CPUP)) {
++ ia->ia_file = NULL;
++ ia->ia_valid &= ~ATTR_FILE;
++ }
+
-+#if IS_ENABLED(CONFIG_AUFS_XATTR) || IS_ENABLED(CONFIG_FS_POSIX_ACL)
-+enum {
-+ AU_XATTR_SET,
-+ AU_ACL_SET
-+};
++ a->h_path.mnt = au_sbr_mnt(sb, a->btgt);
++ if ((ia->ia_valid & (ATTR_MODE | ATTR_CTIME))
++ == (ATTR_MODE | ATTR_CTIME)) {
++ err = security_path_chmod(&a->h_path, ia->ia_mode);
++ if (unlikely(err))
++ goto out_unlock;
++ } else if ((ia->ia_valid & (ATTR_UID | ATTR_GID))
++ && (ia->ia_valid & ATTR_CTIME)) {
++ err = security_path_chown(&a->h_path, ia->ia_uid, ia->ia_gid);
++ if (unlikely(err))
++ goto out_unlock;
++ }
+
-+struct au_sxattr {
-+ int type;
-+ union {
-+ struct {
-+ const char *name;
-+ const void *value;
-+ size_t size;
-+ int flags;
-+ } set;
-+ struct {
-+ struct posix_acl *acl;
-+ int type;
-+ } acl_set;
-+ } u;
-+};
-+ssize_t au_sxattr(struct dentry *dentry, struct inode *inode,
-+ struct au_sxattr *arg);
-+#endif
++ if (ia->ia_valid & ATTR_SIZE) {
++ struct file *f;
+
-+/* ---------------------------------------------------------------------- */
++ if (ia->ia_size < i_size_read(inode))
++ /* unmap only */
++ truncate_setsize(inode, ia->ia_size);
+
-+/* lock subclass for iinfo */
-+enum {
-+ AuLsc_II_CHILD, /* child first */
-+ AuLsc_II_CHILD2, /* rename(2), link(2), and cpup at hnotify */
-+ AuLsc_II_CHILD3, /* copyup dirs */
-+ AuLsc_II_PARENT, /* see AuLsc_I_PARENT in vfsub.h */
-+ AuLsc_II_PARENT2,
-+ AuLsc_II_PARENT3, /* copyup dirs */
-+ AuLsc_II_NEW_CHILD
-+};
++ f = NULL;
++ if (ia->ia_valid & ATTR_FILE)
++ f = ia->ia_file;
++ inode_unlock(a->h_inode);
++ err = vfsub_trunc(&a->h_path, ia->ia_size, ia->ia_valid, f);
++ inode_lock_nested(a->h_inode, AuLsc_I_CHILD);
++ } else {
++ delegated = NULL;
++ while (1) {
++ err = vfsub_notify_change(&a->h_path, ia, &delegated);
++ if (delegated) {
++ err = break_deleg_wait(&delegated);
++ if (!err)
++ continue;
++ }
++ break;
++ }
++ }
++ /*
++ * regardless aufs 'acl' option setting.
++ * why don't all acl-aware fs call this func from their ->setattr()?
++ */
++ if (!err && (ia->ia_valid & ATTR_MODE)) {
++ h_idmap = mnt_idmap(a->h_path.mnt);
++ err = vfsub_acl_chmod(h_idmap, a->h_path.dentry, ia->ia_mode);
++ }
++ if (!err)
++ au_cpup_attr_changeable(inode);
+
-+/*
-+ * ii_read_lock_child, ii_write_lock_child,
-+ * ii_read_lock_child2, ii_write_lock_child2,
-+ * ii_read_lock_child3, ii_write_lock_child3,
-+ * ii_read_lock_parent, ii_write_lock_parent,
-+ * ii_read_lock_parent2, ii_write_lock_parent2,
-+ * ii_read_lock_parent3, ii_write_lock_parent3,
-+ * ii_read_lock_new_child, ii_write_lock_new_child,
-+ */
-+#define AuReadLockFunc(name, lsc) \
-+static inline void ii_read_lock_##name(struct inode *i) \
-+{ \
-+ au_rw_read_lock_nested(&au_ii(i)->ii_rwsem, AuLsc_II_##lsc); \
++out_unlock:
++ inode_unlock(a->h_inode);
++ au_unpin(&a->pin);
++ if (unlikely(err))
++ au_update_dbtop(dentry);
++out_dentry:
++ di_write_unlock(dentry);
++ if (file) {
++ fi_write_unlock(file);
++ ia->ia_file = file;
++ ia->ia_valid |= ATTR_FILE;
++ }
++out_si:
++ si_read_unlock(sb);
++out_kfree:
++ au_kfree_rcu(a);
++out:
++ AuTraceErr(err);
++ return err;
+}
+
-+#define AuWriteLockFunc(name, lsc) \
-+static inline void ii_write_lock_##name(struct inode *i) \
-+{ \
-+ au_rw_write_lock_nested(&au_ii(i)->ii_rwsem, AuLsc_II_##lsc); \
-+}
++#if IS_ENABLED(CONFIG_AUFS_XATTR) || IS_ENABLED(CONFIG_FS_POSIX_ACL)
++static int au_h_path_to_set_attr(struct dentry *dentry,
++ struct au_icpup_args *a, struct path *h_path)
++{
++ int err;
++ struct super_block *sb;
+
-+#define AuRWLockFuncs(name, lsc) \
-+ AuReadLockFunc(name, lsc) \
-+ AuWriteLockFunc(name, lsc)
++ sb = dentry->d_sb;
++ a->udba = au_opt_udba(sb);
++ /* no d_unlinked(), to set UDBA_NONE for root */
++ if (d_unhashed(dentry))
++ a->udba = AuOpt_UDBA_NONE;
++ if (a->udba != AuOpt_UDBA_NONE) {
++ AuDebugOn(IS_ROOT(dentry));
++ err = au_reval_for_attr(dentry, au_sigen(sb));
++ if (unlikely(err))
++ goto out;
++ }
++ err = au_pin_and_icpup(dentry, /*ia*/NULL, a);
++ if (unlikely(err < 0))
++ goto out;
+
-+AuRWLockFuncs(child, CHILD);
-+AuRWLockFuncs(child2, CHILD2);
-+AuRWLockFuncs(child3, CHILD3);
-+AuRWLockFuncs(parent, PARENT);
-+AuRWLockFuncs(parent2, PARENT2);
-+AuRWLockFuncs(parent3, PARENT3);
-+AuRWLockFuncs(new_child, NEW_CHILD);
++ h_path->dentry = a->h_path.dentry;
++ h_path->mnt = au_sbr_mnt(sb, a->btgt);
+
-+#undef AuReadLockFunc
-+#undef AuWriteLockFunc
-+#undef AuRWLockFuncs
++out:
++ return err;
++}
+
-+#define ii_read_unlock(i) au_rw_read_unlock(&au_ii(i)->ii_rwsem)
-+#define ii_write_unlock(i) au_rw_write_unlock(&au_ii(i)->ii_rwsem)
-+#define ii_downgrade_lock(i) au_rw_dgrade_lock(&au_ii(i)->ii_rwsem)
++ssize_t au_sxattr(struct dentry *dentry, struct inode *inode,
++ struct au_sxattr *arg)
++{
++ int err;
++ struct path h_path;
++ struct super_block *sb;
++ struct au_icpup_args *a;
++ struct inode *h_inode;
++ struct mnt_idmap *h_idmap;
+
-+#define IiMustNoWaiters(i) AuRwMustNoWaiters(&au_ii(i)->ii_rwsem)
-+#define IiMustAnyLock(i) AuRwMustAnyLock(&au_ii(i)->ii_rwsem)
-+#define IiMustWriteLock(i) AuRwMustWriteLock(&au_ii(i)->ii_rwsem)
++ IMustLock(inode);
+
-+/* ---------------------------------------------------------------------- */
++ err = -ENOMEM;
++ a = kzalloc(sizeof(*a), GFP_NOFS);
++ if (unlikely(!a))
++ goto out;
+
-+static inline void au_icntnr_init(struct au_icntnr *c)
-+{
-+#ifdef CONFIG_AUFS_DEBUG
-+ c->vfs_inode.i_mode = 0;
-+#endif
-+}
++ sb = dentry->d_sb;
++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
++ if (unlikely(err))
++ goto out_kfree;
+
-+static inline unsigned int au_iigen(struct inode *inode, unsigned int *igflags)
-+{
-+ unsigned int gen;
-+ struct au_iinfo *iinfo;
-+ struct au_iigen *iigen;
++ h_path.dentry = NULL; /* silence gcc */
++ di_write_lock_child(dentry);
++ err = au_h_path_to_set_attr(dentry, a, &h_path);
++ if (unlikely(err))
++ goto out_di;
++ h_idmap = mnt_idmap(h_path.mnt);
++
++ inode_unlock(a->h_inode);
++ switch (arg->type) {
++ case AU_XATTR_SET:
++ AuDebugOn(d_is_negative(h_path.dentry));
++ err = vfsub_setxattr(h_idmap, h_path.dentry,
++ arg->u.set.name, arg->u.set.value,
++ arg->u.set.size, arg->u.set.flags);
++ break;
++ case AU_ACL_SET:
++ err = -EOPNOTSUPP;
++ h_inode = d_inode(h_path.dentry);
++ if (h_inode->i_op->set_acl) {
++ /* this will call posix_acl_update_mode */
++ err = h_inode->i_op->set_acl(h_idmap, h_path.dentry,
++ arg->u.acl_set.acl,
++ arg->u.acl_set.type);
++ }
++ break;
++ }
++ if (!err)
++ au_cpup_attr_timesizes(inode);
+
-+ iinfo = au_ii(inode);
-+ iigen = &iinfo->ii_generation;
-+ spin_lock(&iigen->ig_spin);
-+ if (igflags)
-+ *igflags = iigen->ig_flags;
-+ gen = iigen->ig_generation;
-+ spin_unlock(&iigen->ig_spin);
++ au_unpin(&a->pin);
++ if (unlikely(err))
++ au_update_dbtop(dentry);
+
-+ return gen;
++out_di:
++ di_write_unlock(dentry);
++ si_read_unlock(sb);
++out_kfree:
++ au_kfree_rcu(a);
++out:
++ AuTraceErr(err);
++ return err;
+}
++#endif
+
-+/* tiny test for inode number */
-+/* tmpfs generation is too rough */
-+static inline int au_test_higen(struct inode *inode, struct inode *h_inode)
++static void au_refresh_iattr(struct inode *inode, struct kstat *st,
++ unsigned int nlink)
+{
-+ struct au_iinfo *iinfo;
++ unsigned int n;
+
-+ iinfo = au_ii(inode);
-+ AuRwMustAnyLock(&iinfo->ii_rwsem);
-+ return !(iinfo->ii_hsb1 == h_inode->i_sb
-+ && iinfo->ii_higen == h_inode->i_generation);
-+}
++ inode->i_mode = st->mode;
++ /* don't i_[ug]id_write() here */
++ inode->i_uid = st->uid;
++ inode->i_gid = st->gid;
++ inode->i_atime = st->atime;
++ inode->i_mtime = st->mtime;
++ inode_set_ctime_to_ts(inode, st->ctime);
+
-+static inline void au_iigen_dec(struct inode *inode)
-+{
-+ struct au_iinfo *iinfo;
-+ struct au_iigen *iigen;
++ au_cpup_attr_nlink(inode, /*force*/0);
++ if (S_ISDIR(inode->i_mode)) {
++ n = inode->i_nlink;
++ n -= nlink;
++ n += st->nlink;
++ smp_mb(); /* for i_nlink */
++ /* 0 can happen */
++ set_nlink(inode, n);
++ }
+
-+ iinfo = au_ii(inode);
-+ iigen = &iinfo->ii_generation;
-+ spin_lock(&iigen->ig_spin);
-+ iigen->ig_generation--;
-+ spin_unlock(&iigen->ig_spin);
++ spin_lock(&inode->i_lock);
++ inode->i_blocks = st->blocks;
++ i_size_write(inode, st->size);
++ spin_unlock(&inode->i_lock);
+}
+
-+static inline int au_iigen_test(struct inode *inode, unsigned int sigen)
++/*
++ * common routine for aufs_getattr() and au_getxattr().
++ * returns zero or negative (an error).
++ * @dentry will be read-locked in success.
++ */
++int au_h_path_getattr(struct dentry *dentry, struct inode *inode, int force,
++ struct path *h_path, int locked)
+{
+ int err;
++ unsigned int mnt_flags, sigen;
++ unsigned char udba_none;
++ aufs_bindex_t bindex;
++ struct super_block *sb, *h_sb;
++
++ h_path->mnt = NULL;
++ h_path->dentry = NULL;
+
+ err = 0;
-+ if (unlikely(inode && au_iigen(inode, NULL) != sigen))
-+ err = -EIO;
++ sb = dentry->d_sb;
++ mnt_flags = au_mntflags(sb);
++ udba_none = !!au_opt_test(mnt_flags, UDBA_NONE);
+
-+ return err;
-+}
++ if (unlikely(locked))
++ goto body; /* skip locking dinfo */
+
-+/* ---------------------------------------------------------------------- */
++ /* support fstat(2) */
++ if (!d_unlinked(dentry) && !udba_none) {
++ sigen = au_sigen(sb);
++ err = au_digen_test(dentry, sigen);
++ if (!err) {
++ di_read_lock_child(dentry, AuLock_IR);
++ err = au_dbrange_test(dentry);
++ if (unlikely(err)) {
++ di_read_unlock(dentry, AuLock_IR);
++ goto out;
++ }
++ } else {
++ AuDebugOn(IS_ROOT(dentry));
++ di_write_lock_child(dentry);
++ err = au_dbrange_test(dentry);
++ if (!err)
++ err = au_reval_for_attr(dentry, sigen);
++ if (!err)
++ di_downgrade_lock(dentry, AuLock_IR);
++ else {
++ di_write_unlock(dentry);
++ goto out;
++ }
++ }
++ } else
++ di_read_lock_child(dentry, AuLock_IR);
+
-+static inline struct au_hinode *au_hinode(struct au_iinfo *iinfo,
-+ aufs_bindex_t bindex)
-+{
-+ return iinfo->ii_hinode + bindex;
-+}
++body:
++ if (!inode) {
++ inode = d_inode(dentry);
++ if (unlikely(!inode))
++ goto out;
++ }
++ bindex = au_ibtop(inode);
++ h_path->mnt = au_sbr_mnt(sb, bindex);
++ h_sb = h_path->mnt->mnt_sb;
++ if (!force
++ && !au_test_fs_bad_iattr(h_sb)
++ && udba_none)
++ goto out; /* success */
+
-+static inline int au_is_bad_inode(struct inode *inode)
-+{
-+ return !!(is_bad_inode(inode) || !au_hinode(au_ii(inode), 0));
-+}
++ if (au_dbtop(dentry) == bindex)
++ h_path->dentry = au_h_dptr(dentry, bindex);
++ else if (au_opt_test(mnt_flags, PLINK) && au_plink_test(inode)) {
++ h_path->dentry = au_plink_lkup(inode, bindex);
++ if (IS_ERR(h_path->dentry))
++ /* pretending success */
++ h_path->dentry = NULL;
++ else
++ dput(h_path->dentry);
++ }
+
-+static inline aufs_bindex_t au_ii_br_id(struct inode *inode,
-+ aufs_bindex_t bindex)
-+{
-+ IiMustAnyLock(inode);
-+ return au_hinode(au_ii(inode), bindex)->hi_id;
++out:
++ return err;
+}
+
-+static inline aufs_bindex_t au_ibtop(struct inode *inode)
++static int aufs_getattr(struct mnt_idmap *idmap, const struct path *path,
++ struct kstat *st, u32 request, unsigned int query)
+{
-+ IiMustAnyLock(inode);
-+ return au_ii(inode)->ii_btop;
-+}
++ int err;
++ unsigned char positive;
++ struct path h_path;
++ struct dentry *dentry;
++ struct inode *inode;
++ struct super_block *sb;
+
-+static inline aufs_bindex_t au_ibbot(struct inode *inode)
-+{
-+ IiMustAnyLock(inode);
-+ return au_ii(inode)->ii_bbot;
-+}
++ dentry = path->dentry;
++ inode = d_inode(dentry);
++ sb = dentry->d_sb;
++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
++ if (unlikely(err))
++ goto out;
++ err = au_h_path_getattr(dentry, /*inode*/NULL, /*force*/0, &h_path,
++ /*locked*/0);
++ if (unlikely(err))
++ goto out_si;
++ if (unlikely(!h_path.dentry))
++ /* illegally overlapped or something */
++ goto out_fill; /* pretending success */
+
-+static inline struct au_vdir *au_ivdir(struct inode *inode)
-+{
-+ IiMustAnyLock(inode);
-+ return au_ii(inode)->ii_vdir;
-+}
++ positive = d_is_positive(h_path.dentry);
++ if (positive)
++ /* no vfsub version */
++ err = vfs_getattr(&h_path, st, request, query);
++ if (!err) {
++ if (positive)
++ au_refresh_iattr(inode, st,
++ d_inode(h_path.dentry)->i_nlink);
++ goto out_fill; /* success */
++ }
++ AuTraceErr(err);
++ goto out_di;
+
-+static inline struct dentry *au_hi_wh(struct inode *inode, aufs_bindex_t bindex)
-+{
-+ IiMustAnyLock(inode);
-+ return au_hinode(au_ii(inode), bindex)->hi_whdentry;
++out_fill:
++ generic_fillattr(idmap, request, inode, st);
++out_di:
++ di_read_unlock(dentry, AuLock_IR);
++out_si:
++ si_read_unlock(sb);
++out:
++ AuTraceErr(err);
++ return err;
+}
+
-+static inline void au_set_ibtop(struct inode *inode, aufs_bindex_t bindex)
-+{
-+ IiMustWriteLock(inode);
-+ au_ii(inode)->ii_btop = bindex;
-+}
++/* ---------------------------------------------------------------------- */
+
-+static inline void au_set_ibbot(struct inode *inode, aufs_bindex_t bindex)
++static const char *aufs_get_link(struct dentry *dentry, struct inode *inode,
++ struct delayed_call *done)
+{
-+ IiMustWriteLock(inode);
-+ au_ii(inode)->ii_bbot = bindex;
-+}
++ const char *ret;
++ struct dentry *h_dentry;
++ struct inode *h_inode;
++ int err;
++ aufs_bindex_t bindex;
+
-+static inline void au_set_ivdir(struct inode *inode, struct au_vdir *vdir)
-+{
-+ IiMustWriteLock(inode);
-+ au_ii(inode)->ii_vdir = vdir;
-+}
++ ret = NULL; /* suppress a warning */
++ err = -ECHILD;
++ if (!dentry)
++ goto out;
+
-+static inline struct au_hinode *au_hi(struct inode *inode, aufs_bindex_t bindex)
-+{
-+ IiMustAnyLock(inode);
-+ return au_hinode(au_ii(inode), bindex);
-+}
++ err = aufs_read_lock(dentry, AuLock_IR | AuLock_GEN);
++ if (unlikely(err))
++ goto out;
+
-+/* ---------------------------------------------------------------------- */
++ err = au_d_hashed_positive(dentry);
++ if (unlikely(err))
++ goto out_unlock;
+
-+static inline struct dentry *au_pinned_parent(struct au_pin *pin)
-+{
-+ if (pin)
-+ return pin->parent;
-+ return NULL;
-+}
++ err = -EINVAL;
++ inode = d_inode(dentry);
++ bindex = au_ibtop(inode);
++ h_inode = au_h_iptr(inode, bindex);
++ if (unlikely(!h_inode->i_op->get_link))
++ goto out_unlock;
+
-+static inline struct inode *au_pinned_h_dir(struct au_pin *pin)
-+{
-+ if (pin && pin->hdir)
-+ return pin->hdir->hi_inode;
-+ return NULL;
-+}
++ err = -EBUSY;
++ h_dentry = NULL;
++ if (au_dbtop(dentry) <= bindex) {
++ h_dentry = au_h_dptr(dentry, bindex);
++ if (h_dentry)
++ dget(h_dentry);
++ }
++ if (!h_dentry) {
++ h_dentry = d_find_any_alias(h_inode);
++ if (IS_ERR(h_dentry)) {
++ err = PTR_ERR(h_dentry);
++ goto out_unlock;
++ }
++ }
++ if (unlikely(!h_dentry))
++ goto out_unlock;
+
-+static inline struct au_hinode *au_pinned_hdir(struct au_pin *pin)
-+{
-+ if (pin)
-+ return pin->hdir;
-+ return NULL;
-+}
++ err = 0;
++ AuDbg("%ps\n", h_inode->i_op->get_link);
++ AuDbgDentry(h_dentry);
++ ret = vfs_get_link(h_dentry, done);
++ dput(h_dentry);
++ if (IS_ERR(ret))
++ err = PTR_ERR(ret);
+
-+static inline void au_pin_set_dentry(struct au_pin *pin, struct dentry *dentry)
-+{
-+ if (pin)
-+ pin->dentry = dentry;
++out_unlock:
++ aufs_read_unlock(dentry, AuLock_IR);
++out:
++ if (unlikely(err))
++ ret = ERR_PTR(err);
++ AuTraceErrPtr(ret);
++ return ret;
+}
+
-+static inline void au_pin_set_parent_lflag(struct au_pin *pin,
-+ unsigned char lflag)
++/* ---------------------------------------------------------------------- */
++
++static int au_is_special(struct inode *inode)
+{
-+ if (pin) {
-+ if (lflag)
-+ au_fset_pin(pin->flags, DI_LOCKED);
-+ else
-+ au_fclr_pin(pin->flags, DI_LOCKED);
-+ }
++ return (inode->i_mode & (S_IFBLK | S_IFCHR | S_IFIFO | S_IFSOCK));
+}
+
-+#if 0 /* reserved */
-+static inline void au_pin_set_parent(struct au_pin *pin, struct dentry *parent)
++static int aufs_update_time(struct inode *inode, int flags)
+{
-+ if (pin) {
-+ dput(pin->parent);
-+ pin->parent = dget(parent);
-+ }
-+}
-+#endif
++ int err;
++ aufs_bindex_t bindex;
++ struct super_block *sb;
++ struct inode *h_inode;
++ struct vfsmount *h_mnt;
+
-+/* ---------------------------------------------------------------------- */
++ sb = inode->i_sb;
++ WARN_ONCE((flags & S_ATIME) && !IS_NOATIME(inode),
++ "unexpected s_flags 0x%lx", sb->s_flags);
+
-+struct au_branch;
-+#ifdef CONFIG_AUFS_HNOTIFY
-+struct au_hnotify_op {
-+ void (*ctl)(struct au_hinode *hinode, int do_set);
-+ int (*alloc)(struct au_hinode *hinode);
++ /* mmap_sem might be acquired already, cf. aufs_mmap() */
++ lockdep_off();
++ si_read_lock(sb, AuLock_FLUSH);
++ ii_write_lock_child(inode);
+
-+ /*
-+ * if it returns true, the caller should free hinode->hi_notify,
-+ * otherwise ->free() frees it.
-+ */
-+ int (*free)(struct au_hinode *hinode,
-+ struct au_hnotify *hn) __must_check;
++ err = 0;
++ bindex = au_ibtop(inode);
++ h_inode = au_h_iptr(inode, bindex);
++ if (!au_test_ro(sb, bindex, inode)) {
++ h_mnt = au_sbr_mnt(sb, bindex);
++ err = vfsub_mnt_want_write(h_mnt);
++ if (!err) {
++ err = vfsub_update_time(h_inode, flags);
++ vfsub_mnt_drop_write(h_mnt);
++ }
++ } else if (au_is_special(h_inode)) {
++ /*
++ * Never copy-up here.
++ * These special files may already be opened and used for
++ * communicating. If we copied it up, then the communication
++ * would be corrupted.
++ */
++ AuWarn1("timestamps for i%lu are ignored "
++ "since it is on readonly branch (hi%lu).\n",
++ inode->i_ino, h_inode->i_ino);
++ } else if (flags & ~S_ATIME) {
++ err = -EIO;
++ AuIOErr1("unexpected flags 0x%x\n", flags);
++ AuDebugOn(1);
++ }
+
-+ void (*fin)(void);
-+ int (*init)(void);
++ if (!err)
++ au_cpup_attr_timesizes(inode);
++ ii_write_unlock(inode);
++ si_read_unlock(sb);
++ lockdep_on();
+
-+ int (*reset_br)(unsigned int udba, struct au_branch *br, int perm);
-+ void (*fin_br)(struct au_branch *br);
-+ int (*init_br)(struct au_branch *br, int perm);
-+};
++ if (!err && (flags & S_VERSION))
++ inode_inc_iversion(inode);
+
-+/* hnotify.c */
-+int au_hn_alloc(struct au_hinode *hinode, struct inode *inode);
-+void au_hn_free(struct au_hinode *hinode);
-+void au_hn_ctl(struct au_hinode *hinode, int do_set);
-+void au_hn_reset(struct inode *inode, unsigned int flags);
-+int au_hnotify(struct inode *h_dir, struct au_hnotify *hnotify, u32 mask,
-+ const struct qstr *h_child_qstr, struct inode *h_child_inode);
-+int au_hnotify_reset_br(unsigned int udba, struct au_branch *br, int perm);
-+int au_hnotify_init_br(struct au_branch *br, int perm);
-+void au_hnotify_fin_br(struct au_branch *br);
-+int __init au_hnotify_init(void);
-+void au_hnotify_fin(void);
++ return err;
++}
+
-+/* hfsnotify.c */
-+extern const struct au_hnotify_op au_hnotify_op;
++/* ---------------------------------------------------------------------- */
+
-+static inline
-+void au_hn_init(struct au_hinode *hinode)
-+{
-+ hinode->hi_notify = NULL;
-+}
++/* no getattr version will be set by module.c:aufs_init() */
++struct inode_operations aufs_iop_nogetattr[AuIop_Last],
++ aufs_iop[] = {
++ [AuIop_SYMLINK] = {
++ .permission = aufs_permission,
++#ifdef CONFIG_FS_POSIX_ACL
++ .get_inode_acl = aufs_get_inode_acl,
++ .get_acl = aufs_get_acl,
++ .set_acl = aufs_set_acl, /* unsupport for symlink? */
++#endif
+
-+static inline struct au_hnotify *au_hn(struct au_hinode *hinode)
-+{
-+ return hinode->hi_notify;
-+}
++ .setattr = aufs_setattr,
++ .getattr = aufs_getattr,
+
-+#else
-+AuStub(int, au_hn_alloc, return -EOPNOTSUPP,
-+ struct au_hinode *hinode __maybe_unused,
-+ struct inode *inode __maybe_unused)
-+AuStub(struct au_hnotify *, au_hn, return NULL, struct au_hinode *hinode)
-+AuStubVoid(au_hn_free, struct au_hinode *hinode __maybe_unused)
-+AuStubVoid(au_hn_ctl, struct au_hinode *hinode __maybe_unused,
-+ int do_set __maybe_unused)
-+AuStubVoid(au_hn_reset, struct inode *inode __maybe_unused,
-+ unsigned int flags __maybe_unused)
-+AuStubInt0(au_hnotify_reset_br, unsigned int udba __maybe_unused,
-+ struct au_branch *br __maybe_unused,
-+ int perm __maybe_unused)
-+AuStubInt0(au_hnotify_init_br, struct au_branch *br __maybe_unused,
-+ int perm __maybe_unused)
-+AuStubVoid(au_hnotify_fin_br, struct au_branch *br __maybe_unused)
-+AuStubInt0(__init au_hnotify_init, void)
-+AuStubVoid(au_hnotify_fin, void)
-+AuStubVoid(au_hn_init, struct au_hinode *hinode __maybe_unused)
-+#endif /* CONFIG_AUFS_HNOTIFY */
++#ifdef CONFIG_AUFS_XATTR
++ .listxattr = aufs_listxattr,
++#endif
+
-+static inline void au_hn_suspend(struct au_hinode *hdir)
-+{
-+ au_hn_ctl(hdir, /*do_set*/0);
-+}
++ .get_link = aufs_get_link
+
-+static inline void au_hn_resume(struct au_hinode *hdir)
-+{
-+ au_hn_ctl(hdir, /*do_set*/1);
-+}
++ /* .update_time = aufs_update_time */
++ },
++ [AuIop_DIR] = {
++ .create = aufs_create,
++ .lookup = aufs_lookup,
++ .link = aufs_link,
++ .unlink = aufs_unlink,
++ .symlink = aufs_symlink,
++ .mkdir = aufs_mkdir,
++ .rmdir = aufs_rmdir,
++ .mknod = aufs_mknod,
++ .rename = aufs_rename,
+
-+static inline void au_hn_inode_lock(struct au_hinode *hdir)
-+{
-+ inode_lock(hdir->hi_inode);
-+ au_hn_suspend(hdir);
-+}
++ .permission = aufs_permission,
++#ifdef CONFIG_FS_POSIX_ACL
++ .get_inode_acl = aufs_get_inode_acl,
++ .get_acl = aufs_get_acl,
++ .set_acl = aufs_set_acl,
++#endif
+
-+static inline void au_hn_inode_lock_nested(struct au_hinode *hdir,
-+ unsigned int sc __maybe_unused)
-+{
-+ inode_lock_nested(hdir->hi_inode, sc);
-+ au_hn_suspend(hdir);
-+}
++ .setattr = aufs_setattr,
++ .getattr = aufs_getattr,
+
-+#if 0 /* unused */
-+#include "vfsub.h"
-+static inline void au_hn_inode_lock_shared_nested(struct au_hinode *hdir,
-+ unsigned int sc)
-+{
-+ inode_lock_shared_nested(hdir->hi_inode, sc);
-+ au_hn_suspend(hdir);
-+}
++#ifdef CONFIG_AUFS_XATTR
++ .listxattr = aufs_listxattr,
++#endif
++
++ .update_time = aufs_update_time,
++ .atomic_open = aufs_atomic_open,
++ .tmpfile = aufs_tmpfile
++ },
++ [AuIop_OTHER] = {
++ .permission = aufs_permission,
++#ifdef CONFIG_FS_POSIX_ACL
++ .get_inode_acl = aufs_get_inode_acl,
++ .get_acl = aufs_get_acl,
++ .set_acl = aufs_set_acl,
+#endif
+
-+static inline void au_hn_inode_unlock(struct au_hinode *hdir)
-+{
-+ au_hn_resume(hdir);
-+ inode_unlock(hdir->hi_inode);
-+}
++ .setattr = aufs_setattr,
++ .getattr = aufs_getattr,
+
-+#endif /* __KERNEL__ */
-+#endif /* __AUFS_INODE_H__ */
-diff -urN /usr/share/empty/fs/aufs/ioctl.c linux/fs/aufs/ioctl.c
---- /usr/share/empty/fs/aufs/ioctl.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/ioctl.c 2022-11-05 23:02:18.965889284 +0100
-@@ -0,0 +1,220 @@
++#ifdef CONFIG_AUFS_XATTR
++ .listxattr = aufs_listxattr,
++#endif
++
++ .update_time = aufs_update_time
++ }
++};
+diff --git a/fs/aufs/i_op_add.c b/fs/aufs/i_op_add.c
+new file mode 100644
+index 00000000000000..f238050b802f29
+--- /dev/null
++++ b/fs/aufs/i_op_add.c
+@@ -0,0 +1,972 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2005-2022 Junjiro R. Okajima
+ */
+
+/*
-+ * ioctl
-+ * plink-management and readdir in userspace.
-+ * assist the pathconf(3) wrapper library.
-+ * move-down
-+ * File-based Hierarchical Storage Management.
++ * inode operations (add entry)
+ */
+
-+#include <linux/compat.h>
-+#include <linux/file.h>
++#include <linux/iversion.h>
+#include "aufs.h"
+
-+static int au_wbr_fd(struct path *path, struct aufs_wbr_fd __user *arg)
++/*
++ * final procedure of adding a new entry, except link(2).
++ * remove whiteout, instantiate, copyup the parent dir's times and size
++ * and update version.
++ * if it failed, re-create the removed whiteout.
++ */
++static int epilog(struct inode *dir, aufs_bindex_t bindex,
++ struct dentry *wh_dentry, struct dentry *dentry)
+{
-+ int err, fd;
-+ aufs_bindex_t wbi, bindex, bbot;
-+ struct file *h_file;
++ int err, rerr;
++ aufs_bindex_t bwh;
++ struct path h_path;
+ struct super_block *sb;
-+ struct dentry *root;
-+ struct au_branch *br;
-+ struct aufs_wbr_fd wbrfd = {
-+ .oflags = au_dir_roflags,
-+ .brid = -1
-+ };
-+ const int valid = O_RDONLY | O_NONBLOCK | O_LARGEFILE | O_DIRECTORY
-+ | O_NOATIME | O_CLOEXEC;
-+
-+ AuDebugOn(wbrfd.oflags & ~valid);
++ struct inode *inode, *h_dir;
++ struct dentry *wh;
+
-+ if (arg) {
-+ err = copy_from_user(&wbrfd, arg, sizeof(wbrfd));
-+ if (unlikely(err)) {
-+ err = -EFAULT;
++ bwh = -1;
++ sb = dir->i_sb;
++ if (wh_dentry) {
++ h_dir = d_inode(wh_dentry->d_parent); /* dir inode is locked */
++ IMustLock(h_dir);
++ AuDebugOn(au_h_iptr(dir, bindex) != h_dir);
++ bwh = au_dbwh(dentry);
++ h_path.dentry = wh_dentry;
++ h_path.mnt = au_sbr_mnt(sb, bindex);
++ err = au_wh_unlink_dentry(au_h_iptr(dir, bindex), &h_path,
++ dentry);
++ if (unlikely(err))
+ goto out;
-+ }
++ }
+
-+ err = -EINVAL;
-+ AuDbg("wbrfd{0%o, %d}\n", wbrfd.oflags, wbrfd.brid);
-+ wbrfd.oflags |= au_dir_roflags;
-+ AuDbg("0%o\n", wbrfd.oflags);
-+ if (unlikely(wbrfd.oflags & ~valid))
-+ goto out;
++ inode = au_new_inode(dentry, /*must_new*/1);
++ if (!IS_ERR(inode)) {
++ d_instantiate(dentry, inode);
++ dir = d_inode(dentry->d_parent); /* dir inode is locked */
++ IMustLock(dir);
++ au_dir_ts(dir, bindex);
++ inode_inc_iversion(dir);
++ au_fhsm_wrote(sb, bindex, /*force*/0);
++ return 0; /* success */
+ }
+
-+ fd = get_unused_fd_flags(0);
-+ err = fd;
-+ if (unlikely(fd < 0))
++ err = PTR_ERR(inode);
++ if (!wh_dentry)
+ goto out;
+
-+ h_file = ERR_PTR(-EINVAL);
-+ wbi = 0;
-+ br = NULL;
-+ sb = path->dentry->d_sb;
-+ root = sb->s_root;
-+ aufs_read_lock(root, AuLock_IR);
-+ bbot = au_sbbot(sb);
-+ if (wbrfd.brid >= 0) {
-+ wbi = au_br_index(sb, wbrfd.brid);
-+ if (unlikely(wbi < 0 || wbi > bbot))
-+ goto out_unlock;
-+ }
++ /* revert */
++ /* dir inode is locked */
++ wh = au_wh_create(dentry, bwh, wh_dentry->d_parent);
++ rerr = PTR_ERR(wh);
++ if (IS_ERR(wh)) {
++ AuIOErr("%pd reverting whiteout failed(%d, %d)\n",
++ dentry, err, rerr);
++ err = -EIO;
++ } else
++ dput(wh);
+
-+ h_file = ERR_PTR(-ENOENT);
-+ br = au_sbr(sb, wbi);
-+ if (!au_br_writable(br->br_perm)) {
-+ if (arg)
-+ goto out_unlock;
++out:
++ return err;
++}
+
-+ bindex = wbi + 1;
-+ wbi = -1;
-+ for (; bindex <= bbot; bindex++) {
-+ br = au_sbr(sb, bindex);
-+ if (au_br_writable(br->br_perm)) {
-+ wbi = bindex;
-+ br = au_sbr(sb, wbi);
-+ break;
-+ }
++static int au_d_may_add(struct dentry *dentry)
++{
++ int err;
++
++ err = 0;
++ if (unlikely(d_unhashed(dentry)))
++ err = -ENOENT;
++ if (unlikely(d_really_is_positive(dentry)))
++ err = -EEXIST;
++ return err;
++}
++
++/*
++ * simple tests for the adding inode operations.
++ * following the checks in vfs, plus the parent-child relationship.
++ */
++int au_may_add(struct dentry *dentry, aufs_bindex_t bindex,
++ struct dentry *h_parent, int isdir)
++{
++ int err;
++ umode_t h_mode;
++ struct dentry *h_dentry;
++ struct inode *h_inode;
++
++ err = -ENAMETOOLONG;
++ if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN))
++ goto out;
++
++ h_dentry = au_h_dptr(dentry, bindex);
++ if (d_really_is_negative(dentry)) {
++ err = -EEXIST;
++ if (unlikely(d_is_positive(h_dentry)))
++ goto out;
++ } else {
++ /* rename(2) case */
++ err = -EIO;
++ if (unlikely(d_is_negative(h_dentry)))
++ goto out;
++ h_inode = d_inode(h_dentry);
++ if (unlikely(!h_inode->i_nlink))
++ goto out;
++
++ h_mode = h_inode->i_mode;
++ if (!isdir) {
++ err = -EISDIR;
++ if (unlikely(S_ISDIR(h_mode)))
++ goto out;
++ } else if (unlikely(!S_ISDIR(h_mode))) {
++ err = -ENOTDIR;
++ goto out;
+ }
+ }
-+ AuDbg("wbi %d\n", wbi);
-+ if (wbi >= 0)
-+ h_file = au_h_open(root, wbi, wbrfd.oflags, NULL,
-+ /*force_wr*/0);
-+
-+out_unlock:
-+ aufs_read_unlock(root, AuLock_IR);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out_fd;
+
-+ au_lcnt_dec(&br->br_nfiles); /* cf. au_h_open() */
-+ fd_install(fd, h_file);
-+ err = fd;
-+ goto out; /* success */
++ err = 0;
++ /* expected parent dir is locked */
++ if (unlikely(h_parent != h_dentry->d_parent))
++ err = -EIO;
+
-+out_fd:
-+ put_unused_fd(fd);
+out:
+ AuTraceErr(err);
+ return err;
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long arg)
++/*
++ * initial procedure of adding a new entry.
++ * prepare writable branch and the parent dir, lock it,
++ * and lookup whiteout for the new entry.
++ */
++static struct dentry*
++lock_hdir_lkup_wh(struct dentry *dentry, struct au_dtime *dt,
++ struct dentry *src_dentry, struct au_pin *pin,
++ struct au_wr_dir_args *wr_dir_args)
+{
-+ long err;
-+ struct dentry *dentry;
-+
-+ switch (cmd) {
-+ case AUFS_CTL_RDU:
-+ case AUFS_CTL_RDU_INO:
-+ err = au_rdu_ioctl(file, cmd, arg);
-+ break;
++ struct dentry *wh_dentry, *h_parent;
++ struct super_block *sb;
++ struct au_branch *br;
++ int err;
++ unsigned int udba;
++ aufs_bindex_t bcpup;
+
-+ case AUFS_CTL_WBR_FD:
-+ err = au_wbr_fd(&file->f_path, (void __user *)arg);
-+ break;
++ AuDbg("%pd\n", dentry);
+
-+ case AUFS_CTL_IBUSY:
-+ err = au_ibusy_ioctl(file, arg);
-+ break;
++ err = au_wr_dir(dentry, src_dentry, wr_dir_args);
++ bcpup = err;
++ wh_dentry = ERR_PTR(err);
++ if (unlikely(err < 0))
++ goto out;
+
-+ case AUFS_CTL_BRINFO:
-+ err = au_brinfo_ioctl(file, arg);
-+ break;
++ sb = dentry->d_sb;
++ udba = au_opt_udba(sb);
++ err = au_pin(pin, dentry, bcpup, udba,
++ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
++ wh_dentry = ERR_PTR(err);
++ if (unlikely(err))
++ goto out;
+
-+ case AUFS_CTL_FHSM_FD:
-+ dentry = file->f_path.dentry;
-+ if (IS_ROOT(dentry))
-+ err = au_fhsm_fd(dentry->d_sb, arg);
-+ else
-+ err = -ENOTTY;
-+ break;
++ h_parent = au_pinned_h_parent(pin);
++ if (udba != AuOpt_UDBA_NONE
++ && au_dbtop(dentry) == bcpup)
++ err = au_may_add(dentry, bcpup, h_parent,
++ au_ftest_wrdir(wr_dir_args->flags, ISDIR));
++ else if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN))
++ err = -ENAMETOOLONG;
++ wh_dentry = ERR_PTR(err);
++ if (unlikely(err))
++ goto out_unpin;
+
-+ default:
-+ /* do not call the lower */
-+ AuDbg("0x%x\n", cmd);
-+ err = -ENOTTY;
++ br = au_sbr(sb, bcpup);
++ if (dt) {
++ struct path tmp = {
++ .dentry = h_parent,
++ .mnt = au_br_mnt(br)
++ };
++ au_dtime_store(dt, au_pinned_parent(pin), &tmp);
+ }
+
-+ AuTraceErr(err);
-+ return err;
++ wh_dentry = NULL;
++ if (bcpup != au_dbwh(dentry))
++ goto out; /* success */
++
++ /*
++ * ENAMETOOLONG here means that if we allowed create such name, then it
++ * would not be able to removed in the future. So we don't allow such
++ * name here and we don't handle ENAMETOOLONG differently here.
++ */
++ wh_dentry = au_wh_lkup(h_parent, &dentry->d_name, br);
++
++out_unpin:
++ if (IS_ERR(wh_dentry))
++ au_unpin(pin);
++out:
++ return wh_dentry;
+}
+
-+long aufs_ioctl_nondir(struct file *file, unsigned int cmd, unsigned long arg)
++/* ---------------------------------------------------------------------- */
++
++enum { Mknod, Symlink, Creat };
++struct simple_arg {
++ int type;
++ union {
++ struct {
++ umode_t mode;
++ bool want_excl;
++ bool try_aopen;
++ struct vfsub_aopen_args *aopen;
++ } c;
++ struct {
++ const char *symname;
++ } s;
++ struct {
++ umode_t mode;
++ dev_t dev;
++ } m;
++ } u;
++};
++
++static int add_simple(struct inode *dir, struct dentry *dentry,
++ struct simple_arg *arg)
+{
-+ long err;
++ int err, rerr;
++ aufs_bindex_t btop;
++ unsigned char created;
++ const unsigned char try_aopen
++ = (arg->type == Creat && arg->u.c.try_aopen);
++ struct vfsub_aopen_args *aopen = arg->u.c.aopen;
++ struct dentry *wh_dentry, *parent;
++ struct inode *h_dir;
++ struct super_block *sb;
++ struct au_branch *br;
++ /* to reduce stack size */
++ struct {
++ struct au_dtime dt;
++ struct au_pin pin;
++ struct path h_path;
++ struct au_wr_dir_args wr_dir_args;
++ } *a;
+
-+ switch (cmd) {
-+ case AUFS_CTL_MVDOWN:
-+ err = au_mvdown(file->f_path.dentry, (void __user *)arg);
-+ break;
++ AuDbg("%pd\n", dentry);
++ IMustLock(dir);
+
-+ case AUFS_CTL_WBR_FD:
-+ err = au_wbr_fd(&file->f_path, (void __user *)arg);
-+ break;
++ err = -ENOMEM;
++ a = kmalloc(sizeof(*a), GFP_NOFS);
++ if (unlikely(!a))
++ goto out;
++ a->wr_dir_args.force_btgt = -1;
++ a->wr_dir_args.flags = AuWrDir_ADD_ENTRY;
++
++ parent = dentry->d_parent; /* dir inode is locked */
++ if (!try_aopen) {
++ err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN);
++ if (unlikely(err))
++ goto out_free;
++ }
++ err = au_d_may_add(dentry);
++ if (unlikely(err))
++ goto out_unlock;
++ if (!try_aopen)
++ di_write_lock_parent(parent);
++ wh_dentry = lock_hdir_lkup_wh(dentry, &a->dt, /*src_dentry*/NULL,
++ &a->pin, &a->wr_dir_args);
++ err = PTR_ERR(wh_dentry);
++ if (IS_ERR(wh_dentry))
++ goto out_parent;
+
++ btop = au_dbtop(dentry);
++ sb = dentry->d_sb;
++ br = au_sbr(sb, btop);
++ a->h_path.dentry = au_h_dptr(dentry, btop);
++ a->h_path.mnt = au_br_mnt(br);
++ h_dir = au_pinned_h_dir(&a->pin);
++ switch (arg->type) {
++ case Creat:
++ if (!try_aopen || !h_dir->i_op->atomic_open) {
++ err = vfsub_create(h_dir, &a->h_path, arg->u.c.mode,
++ arg->u.c.want_excl);
++ created = !err;
++ if (!err && try_aopen)
++ aopen->file->f_mode |= FMODE_CREATED;
++ } else {
++ aopen->br = br;
++ err = vfsub_atomic_open(h_dir, a->h_path.dentry, aopen);
++ AuDbg("err %d\n", err);
++ AuDbgFile(aopen->file);
++ created = err >= 0
++ && !!(aopen->file->f_mode & FMODE_CREATED);
++ }
++ break;
++ case Symlink:
++ err = vfsub_symlink(h_dir, &a->h_path, arg->u.s.symname);
++ created = !err;
++ break;
++ case Mknod:
++ err = vfsub_mknod(h_dir, &a->h_path, arg->u.m.mode,
++ arg->u.m.dev);
++ created = !err;
++ break;
+ default:
-+ /* do not call the lower */
-+ AuDbg("0x%x\n", cmd);
-+ err = -ENOTTY;
++ BUG();
+ }
++ if (unlikely(err < 0))
++ goto out_unpin;
+
-+ AuTraceErr(err);
++ err = epilog(dir, btop, wh_dentry, dentry);
++ if (!err)
++ goto out_unpin; /* success */
++
++ /* revert */
++ if (created /* && d_is_positive(a->h_path.dentry) */) {
++ /* no delegation since it is just created */
++ rerr = vfsub_unlink(h_dir, &a->h_path, /*delegated*/NULL,
++ /*force*/0);
++ if (rerr) {
++ AuIOErr("%pd revert failure(%d, %d)\n",
++ dentry, err, rerr);
++ err = -EIO;
++ }
++ au_dtime_revert(&a->dt);
++ }
++ if (try_aopen && h_dir->i_op->atomic_open
++ && (aopen->file->f_mode & FMODE_OPENED))
++ /* aopen->file is still opened */
++ au_lcnt_dec(&aopen->br->br_nfiles);
++
++out_unpin:
++ au_unpin(&a->pin);
++ dput(wh_dentry);
++out_parent:
++ if (!try_aopen)
++ di_write_unlock(parent);
++out_unlock:
++ if (unlikely(err)) {
++ au_update_dbtop(dentry);
++ d_drop(dentry);
++ }
++ if (!try_aopen)
++ aufs_read_unlock(dentry, AuLock_DW);
++out_free:
++ au_kfree_rcu(a);
++out:
+ return err;
+}
+
-+#ifdef CONFIG_COMPAT
-+long aufs_compat_ioctl_dir(struct file *file, unsigned int cmd,
-+ unsigned long arg)
++int aufs_mknod(struct mnt_idmap *idmap, struct inode *dir,
++ struct dentry *dentry, umode_t mode, dev_t dev)
+{
-+ long err;
++ struct simple_arg arg = {
++ .type = Mknod,
++ .u.m = {
++ .mode = mode,
++ .dev = dev
++ }
++ };
++ return add_simple(dir, dentry, &arg);
++}
++
++int aufs_symlink(struct mnt_idmap *idmap, struct inode *dir,
++ struct dentry *dentry, const char *symname)
++{
++ struct simple_arg arg = {
++ .type = Symlink,
++ .u.s.symname = symname
++ };
++ return add_simple(dir, dentry, &arg);
++}
++
++int aufs_create(struct mnt_idmap *idmap, struct inode *dir,
++ struct dentry *dentry, umode_t mode, bool want_excl)
++{
++ struct simple_arg arg = {
++ .type = Creat,
++ .u.c = {
++ .mode = mode,
++ .want_excl = want_excl
++ }
++ };
++ return add_simple(dir, dentry, &arg);
++}
++
++int au_aopen_or_create(struct inode *dir, struct dentry *dentry,
++ struct vfsub_aopen_args *aopen_args)
++{
++ struct simple_arg arg = {
++ .type = Creat,
++ .u.c = {
++ .mode = aopen_args->create_mode,
++ .want_excl = aopen_args->open_flag & O_EXCL,
++ .try_aopen = true,
++ .aopen = aopen_args
++ }
++ };
++ return add_simple(dir, dentry, &arg);
++}
+
-+ switch (cmd) {
-+ case AUFS_CTL_RDU:
-+ case AUFS_CTL_RDU_INO:
-+ err = au_rdu_compat_ioctl(file, cmd, arg);
-+ break;
++int aufs_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
++ struct file *file, umode_t mode)
++{
++ int err;
++ aufs_bindex_t bindex;
++ struct path h_ppath;
++ struct super_block *sb;
++ struct au_branch *br;
++ struct dentry *dentry, *parent, *h_parent, *h_dentry;
++ struct inode *h_dir, *inode;
++ struct vfsmount *h_mnt;
++ struct mnt_idmap *h_idmap;
++ struct file *h_file;
++ struct au_wr_dir_args wr_dir_args = {
++ .force_btgt = -1,
++ .flags = AuWrDir_TMPFILE
++ };
+
-+ case AUFS_CTL_IBUSY:
-+ err = au_ibusy_compat_ioctl(file, arg);
-+ break;
++ /* copy-up may happen */
++ inode_lock(dir);
+
-+ case AUFS_CTL_BRINFO:
-+ err = au_brinfo_compat_ioctl(file, arg);
-+ break;
++ h_file = NULL;
++ sb = dir->i_sb;
++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
++ if (unlikely(err))
++ goto out;
+
-+ default:
-+ err = aufs_ioctl_dir(file, cmd, arg);
-+ }
++ dentry = file->f_path.dentry;
++ err = au_di_init(dentry);
++ if (unlikely(err))
++ goto out_si;
+
-+ AuTraceErr(err);
-+ return err;
-+}
++ err = -EBUSY;
++ parent = d_find_any_alias(dir);
++ AuDebugOn(!parent);
++ di_write_lock_parent(parent);
++ if (unlikely(d_inode(parent) != dir))
++ goto out_parent;
+
-+long aufs_compat_ioctl_nondir(struct file *file, unsigned int cmd,
-+ unsigned long arg)
-+{
-+ return aufs_ioctl_nondir(file, cmd, (unsigned long)compat_ptr(arg));
-+}
-+#endif
-diff -urN /usr/share/empty/fs/aufs/i_op_add.c linux/fs/aufs/i_op_add.c
---- /usr/share/empty/fs/aufs/i_op_add.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/i_op_add.c 2023-10-31 09:31:04.199880750 +0100
-@@ -0,0 +1,972 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2022 Junjiro R. Okajima
-+ *
-+ * This program 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/>.
-+ */
++ err = au_digen_test(parent, au_sigen(sb));
++ if (unlikely(err))
++ goto out_parent;
+
-+/*
-+ * inode operations (add entry)
-+ */
++ bindex = au_dbtop(parent);
++ au_set_dbtop(dentry, bindex);
++ au_set_dbbot(dentry, bindex);
++ err = au_wr_dir(dentry, /*src_dentry*/NULL, &wr_dir_args);
++ bindex = err;
++ if (unlikely(err < 0))
++ goto out_parent;
+
-+#include <linux/iversion.h>
-+#include "aufs.h"
++ err = -EOPNOTSUPP;
++ h_dir = au_h_iptr(dir, bindex);
++ if (unlikely(!h_dir->i_op->tmpfile))
++ goto out_parent;
+
-+/*
-+ * final procedure of adding a new entry, except link(2).
-+ * remove whiteout, instantiate, copyup the parent dir's times and size
-+ * and update version.
-+ * if it failed, re-create the removed whiteout.
-+ */
-+static int epilog(struct inode *dir, aufs_bindex_t bindex,
-+ struct dentry *wh_dentry, struct dentry *dentry)
-+{
-+ int err, rerr;
-+ aufs_bindex_t bwh;
-+ struct path h_path;
-+ struct super_block *sb;
-+ struct inode *inode, *h_dir;
-+ struct dentry *wh;
++ br = au_sbr(sb, bindex);
++ h_mnt = au_br_mnt(br);
++ err = vfsub_mnt_want_write(h_mnt);
++ if (unlikely(err))
++ goto out_parent;
+
-+ bwh = -1;
-+ sb = dir->i_sb;
-+ if (wh_dentry) {
-+ h_dir = d_inode(wh_dentry->d_parent); /* dir inode is locked */
-+ IMustLock(h_dir);
-+ AuDebugOn(au_h_iptr(dir, bindex) != h_dir);
-+ bwh = au_dbwh(dentry);
-+ h_path.dentry = wh_dentry;
-+ h_path.mnt = au_sbr_mnt(sb, bindex);
-+ err = au_wh_unlink_dentry(au_h_iptr(dir, bindex), &h_path,
-+ dentry);
-+ if (unlikely(err))
-+ goto out;
++ h_idmap = mnt_idmap(h_mnt);
++ h_parent = au_h_dptr(parent, bindex);
++ h_ppath.mnt = h_mnt;
++ h_ppath.dentry = h_parent;
++ h_file = kernel_tmpfile_open(h_idmap, &h_ppath, mode, /*open_flag*/0,
++ current_cred());
++ if (IS_ERR(h_file)) {
++ err = PTR_ERR(h_file);
++ h_file = NULL;
++ goto out_mnt;
+ }
+
++ h_dentry = h_file->f_path.dentry;
++ au_set_dbtop(dentry, bindex);
++ au_set_dbbot(dentry, bindex);
++ au_set_h_dptr(dentry, bindex, dget(h_dentry));
+ inode = au_new_inode(dentry, /*must_new*/1);
-+ if (!IS_ERR(inode)) {
-+ d_instantiate(dentry, inode);
-+ dir = d_inode(dentry->d_parent); /* dir inode is locked */
-+ IMustLock(dir);
-+ au_dir_ts(dir, bindex);
-+ inode_inc_iversion(dir);
-+ au_fhsm_wrote(sb, bindex, /*force*/0);
-+ return 0; /* success */
++ if (IS_ERR(inode)) {
++ err = PTR_ERR(inode);
++ au_set_h_dptr(dentry, bindex, NULL);
++ au_set_dbtop(dentry, -1);
++ au_set_dbbot(dentry, -1);
++ goto out_h_file;
+ }
+
-+ err = PTR_ERR(inode);
-+ if (!wh_dentry)
-+ goto out;
++ if (!inode->i_nlink)
++ set_nlink(inode, 1);
++ d_tmpfile(file, inode);
++ au_di(dentry)->di_tmpfile = 1;
++ get_file(h_file);
++ au_di(dentry)->di_htmpfile = h_file;
+
-+ /* revert */
-+ /* dir inode is locked */
-+ wh = au_wh_create(dentry, bwh, wh_dentry->d_parent);
-+ rerr = PTR_ERR(wh);
-+ if (IS_ERR(wh)) {
-+ AuIOErr("%pd reverting whiteout failed(%d, %d)\n",
-+ dentry, err, rerr);
-+ err = -EIO;
-+ } else
-+ dput(wh);
++ /* update without i_mutex */
++ if (au_ibtop(dir) == au_dbtop(dentry))
++ au_cpup_attr_timesizes(dir);
+
++out_h_file:
++ fput(h_file);
++out_mnt:
++ vfsub_mnt_drop_write(h_mnt);
++out_parent:
++ di_write_unlock(parent);
++ dput(parent);
++ di_write_unlock(dentry);
++ if (!err)
++ goto out_si;
++ if (h_file)
++ fput(h_file);
++ au_di(dentry)->di_htmpfile = NULL;
++ au_di_fin(dentry);
++ dentry->d_fsdata = NULL;
++out_si:
++ si_read_unlock(sb);
++ if (!err && h_file) {
++ /* finally... */
++ err = finish_open_simple(file, err);
++ if (!err)
++ au_lcnt_inc(&br->br_nfiles);
++ else {
++ fput(h_file);
++ au_di(dentry)->di_htmpfile = NULL;
++ au_di_fin(dentry);
++ dentry->d_fsdata = NULL;
++ }
++ }
+out:
++ inode_unlock(dir);
++ AuTraceErr(err);
+ return err;
+}
+
-+static int au_d_may_add(struct dentry *dentry)
++/* ---------------------------------------------------------------------- */
++
++struct au_link_args {
++ aufs_bindex_t bdst, bsrc;
++ struct au_pin pin;
++ struct path h_path;
++ struct dentry *src_parent, *parent;
++};
++
++static int au_cpup_before_link(struct dentry *src_dentry,
++ struct au_link_args *a)
+{
+ int err;
++ struct dentry *h_src_dentry;
++ struct au_cp_generic cpg = {
++ .dentry = src_dentry,
++ .bdst = a->bdst,
++ .bsrc = a->bsrc,
++ .len = -1,
++ .pin = &a->pin,
++ .flags = AuCpup_DTIME | AuCpup_HOPEN /* | AuCpup_KEEPLINO */
++ };
+
-+ err = 0;
-+ if (unlikely(d_unhashed(dentry)))
-+ err = -ENOENT;
-+ if (unlikely(d_really_is_positive(dentry)))
-+ err = -EEXIST;
++ di_read_lock_parent(a->src_parent, AuLock_IR);
++ err = au_test_and_cpup_dirs(src_dentry, a->bdst);
++ if (unlikely(err))
++ goto out;
++
++ h_src_dentry = au_h_dptr(src_dentry, a->bsrc);
++ err = au_pin(&a->pin, src_dentry, a->bdst,
++ au_opt_udba(src_dentry->d_sb),
++ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
++ if (unlikely(err))
++ goto out;
++
++ err = au_sio_cpup_simple(&cpg);
++ au_unpin(&a->pin);
++
++out:
++ di_read_unlock(a->src_parent, AuLock_IR);
+ return err;
+}
+
-+/*
-+ * simple tests for the adding inode operations.
-+ * following the checks in vfs, plus the parent-child relationship.
-+ */
-+int au_may_add(struct dentry *dentry, aufs_bindex_t bindex,
-+ struct dentry *h_parent, int isdir)
++static int au_cpup_or_link(struct dentry *src_dentry, struct dentry *dentry,
++ struct au_link_args *a)
+{
+ int err;
-+ umode_t h_mode;
-+ struct dentry *h_dentry;
-+ struct inode *h_inode;
-+
-+ err = -ENAMETOOLONG;
-+ if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN))
-+ goto out;
++ unsigned char plink;
++ aufs_bindex_t bbot;
++ struct dentry *h_src_dentry;
++ struct inode *h_inode, *inode, *delegated;
++ struct super_block *sb;
++ struct file *h_file;
+
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (d_really_is_negative(dentry)) {
-+ err = -EEXIST;
-+ if (unlikely(d_is_positive(h_dentry)))
-+ goto out;
++ plink = 0;
++ h_inode = NULL;
++ sb = src_dentry->d_sb;
++ inode = d_inode(src_dentry);
++ if (au_ibtop(inode) <= a->bdst)
++ h_inode = au_h_iptr(inode, a->bdst);
++ if (!h_inode || !h_inode->i_nlink) {
++ /* copyup src_dentry as the name of dentry. */
++ bbot = au_dbbot(dentry);
++ if (bbot < a->bsrc)
++ au_set_dbbot(dentry, a->bsrc);
++ au_set_h_dptr(dentry, a->bsrc,
++ dget(au_h_dptr(src_dentry, a->bsrc)));
++ dget(a->h_path.dentry);
++ au_set_h_dptr(dentry, a->bdst, NULL);
++ AuDbg("temporary d_inode...\n");
++ spin_lock(&dentry->d_lock);
++ dentry->d_inode = d_inode(src_dentry); /* tmp */
++ spin_unlock(&dentry->d_lock);
++ h_file = au_h_open_pre(dentry, a->bsrc, /*force_wr*/0);
++ if (IS_ERR(h_file))
++ err = PTR_ERR(h_file);
++ else {
++ struct au_cp_generic cpg = {
++ .dentry = dentry,
++ .bdst = a->bdst,
++ .bsrc = -1,
++ .len = -1,
++ .pin = &a->pin,
++ .flags = AuCpup_KEEPLINO
++ };
++ err = au_sio_cpup_simple(&cpg);
++ au_h_open_post(dentry, a->bsrc, h_file);
++ if (!err) {
++ dput(a->h_path.dentry);
++ a->h_path.dentry = au_h_dptr(dentry, a->bdst);
++ } else
++ au_set_h_dptr(dentry, a->bdst,
++ a->h_path.dentry);
++ }
++ spin_lock(&dentry->d_lock);
++ dentry->d_inode = NULL; /* restore */
++ spin_unlock(&dentry->d_lock);
++ AuDbg("temporary d_inode...done\n");
++ au_set_h_dptr(dentry, a->bsrc, NULL);
++ au_set_dbbot(dentry, bbot);
+ } else {
-+ /* rename(2) case */
-+ err = -EIO;
-+ if (unlikely(d_is_negative(h_dentry)))
-+ goto out;
-+ h_inode = d_inode(h_dentry);
-+ if (unlikely(!h_inode->i_nlink))
-+ goto out;
-+
-+ h_mode = h_inode->i_mode;
-+ if (!isdir) {
-+ err = -EISDIR;
-+ if (unlikely(S_ISDIR(h_mode)))
++ /* the inode of src_dentry already exists on a.bdst branch */
++ h_src_dentry = d_find_alias(h_inode);
++ if (!h_src_dentry && au_plink_test(inode)) {
++ plink = 1;
++ h_src_dentry = au_plink_lkup(inode, a->bdst);
++ err = PTR_ERR(h_src_dentry);
++ if (IS_ERR(h_src_dentry))
+ goto out;
-+ } else if (unlikely(!S_ISDIR(h_mode))) {
-+ err = -ENOTDIR;
-+ goto out;
++
++ if (unlikely(d_is_negative(h_src_dentry))) {
++ dput(h_src_dentry);
++ h_src_dentry = NULL;
++ }
++
++ }
++ if (h_src_dentry) {
++ delegated = NULL;
++ err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin),
++ &a->h_path, &delegated);
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal link\n");
++ iput(delegated);
++ }
++ dput(h_src_dentry);
++ } else {
++ AuIOErr("no dentry found for hi%lu on b%d\n",
++ h_inode->i_ino, a->bdst);
++ err = -EIO;
+ }
+ }
+
-+ err = 0;
-+ /* expected parent dir is locked */
-+ if (unlikely(h_parent != h_dentry->d_parent))
-+ err = -EIO;
++ if (!err && !plink)
++ au_plink_append(inode, a->bdst, a->h_path.dentry);
+
+out:
+ AuTraceErr(err);
+ return err;
+}
+
-+/*
-+ * initial procedure of adding a new entry.
-+ * prepare writable branch and the parent dir, lock it,
-+ * and lookup whiteout for the new entry.
-+ */
-+static struct dentry*
-+lock_hdir_lkup_wh(struct dentry *dentry, struct au_dtime *dt,
-+ struct dentry *src_dentry, struct au_pin *pin,
-+ struct au_wr_dir_args *wr_dir_args)
++int aufs_link(struct dentry *src_dentry, struct inode *dir,
++ struct dentry *dentry)
+{
-+ struct dentry *wh_dentry, *h_parent;
++ int err, rerr;
++ struct au_dtime dt;
++ struct au_link_args *a;
++ struct dentry *wh_dentry, *h_src_dentry;
++ struct inode *inode, *delegated;
+ struct super_block *sb;
-+ struct au_branch *br;
-+ int err;
-+ unsigned int udba;
-+ aufs_bindex_t bcpup;
++ struct au_wr_dir_args wr_dir_args = {
++ /* .force_btgt = -1, */
++ .flags = AuWrDir_ADD_ENTRY
++ };
+
-+ AuDbg("%pd\n", dentry);
++ IMustLock(dir);
++ inode = d_inode(src_dentry);
++ IMustLock(inode);
+
-+ err = au_wr_dir(dentry, src_dentry, wr_dir_args);
-+ bcpup = err;
-+ wh_dentry = ERR_PTR(err);
-+ if (unlikely(err < 0))
++ err = -ENOMEM;
++ a = kzalloc(sizeof(*a), GFP_NOFS);
++ if (unlikely(!a))
+ goto out;
+
-+ sb = dentry->d_sb;
-+ udba = au_opt_udba(sb);
-+ err = au_pin(pin, dentry, bcpup, udba,
-+ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
-+ wh_dentry = ERR_PTR(err);
++ a->parent = dentry->d_parent; /* dir inode is locked */
++ err = aufs_read_and_write_lock2(dentry, src_dentry,
++ AuLock_NOPLM | AuLock_GEN);
+ if (unlikely(err))
-+ goto out;
++ goto out_kfree;
++ err = au_d_linkable(src_dentry);
++ if (unlikely(err))
++ goto out_unlock;
++ err = au_d_may_add(dentry);
++ if (unlikely(err))
++ goto out_unlock;
+
-+ h_parent = au_pinned_h_parent(pin);
-+ if (udba != AuOpt_UDBA_NONE
-+ && au_dbtop(dentry) == bcpup)
-+ err = au_may_add(dentry, bcpup, h_parent,
-+ au_ftest_wrdir(wr_dir_args->flags, ISDIR));
-+ else if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN))
-+ err = -ENAMETOOLONG;
-+ wh_dentry = ERR_PTR(err);
++ a->src_parent = dget_parent(src_dentry);
++ wr_dir_args.force_btgt = au_ibtop(inode);
++
++ di_write_lock_parent(a->parent);
++ wr_dir_args.force_btgt = au_wbr(dentry, wr_dir_args.force_btgt);
++ wh_dentry = lock_hdir_lkup_wh(dentry, &dt, src_dentry, &a->pin,
++ &wr_dir_args);
++ err = PTR_ERR(wh_dentry);
++ if (IS_ERR(wh_dentry))
++ goto out_parent;
++
++ err = 0;
++ sb = dentry->d_sb;
++ a->bdst = au_dbtop(dentry);
++ a->h_path.dentry = au_h_dptr(dentry, a->bdst);
++ a->h_path.mnt = au_sbr_mnt(sb, a->bdst);
++ a->bsrc = au_ibtop(inode);
++ h_src_dentry = au_h_d_alias(src_dentry, a->bsrc);
++ if (!h_src_dentry && au_di(src_dentry)->di_tmpfile)
++ h_src_dentry = dget(au_hi_wh(inode, a->bsrc));
++ if (!h_src_dentry) {
++ a->bsrc = au_dbtop(src_dentry);
++ h_src_dentry = au_h_d_alias(src_dentry, a->bsrc);
++ AuDebugOn(!h_src_dentry);
++ } else if (IS_ERR(h_src_dentry)) {
++ err = PTR_ERR(h_src_dentry);
++ goto out_parent;
++ }
++
++ /*
++ * aufs doesn't touch the credential so
++ * security_dentry_create_files_as() is unnecessary.
++ */
++ if (au_opt_test(au_mntflags(sb), PLINK)) {
++ if (a->bdst < a->bsrc
++ /* && h_src_dentry->d_sb != a->h_path.dentry->d_sb */)
++ err = au_cpup_or_link(src_dentry, dentry, a);
++ else {
++ delegated = NULL;
++ err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin),
++ &a->h_path, &delegated);
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal link\n");
++ iput(delegated);
++ }
++ }
++ dput(h_src_dentry);
++ } else {
++ /*
++ * copyup src_dentry to the branch we process,
++ * and then link(2) to it.
++ */
++ dput(h_src_dentry);
++ if (a->bdst < a->bsrc
++ /* && h_src_dentry->d_sb != a->h_path.dentry->d_sb */) {
++ au_unpin(&a->pin);
++ di_write_unlock(a->parent);
++ err = au_cpup_before_link(src_dentry, a);
++ di_write_lock_parent(a->parent);
++ if (!err)
++ err = au_pin(&a->pin, dentry, a->bdst,
++ au_opt_udba(sb),
++ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
++ if (unlikely(err))
++ goto out_wh;
++ }
++ if (!err) {
++ h_src_dentry = au_h_dptr(src_dentry, a->bdst);
++ err = -ENOENT;
++ if (h_src_dentry && d_is_positive(h_src_dentry)) {
++ delegated = NULL;
++ err = vfsub_link(h_src_dentry,
++ au_pinned_h_dir(&a->pin),
++ &a->h_path, &delegated);
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry"
++ " for NFSv4 delegation"
++ " for an internal link\n");
++ iput(delegated);
++ }
++ }
++ }
++ }
+ if (unlikely(err))
+ goto out_unpin;
+
-+ br = au_sbr(sb, bcpup);
-+ if (dt) {
-+ struct path tmp = {
-+ .dentry = h_parent,
-+ .mnt = au_br_mnt(br)
-+ };
-+ au_dtime_store(dt, au_pinned_parent(pin), &tmp);
++ if (wh_dentry) {
++ a->h_path.dentry = wh_dentry;
++ err = au_wh_unlink_dentry(au_pinned_h_dir(&a->pin), &a->h_path,
++ dentry);
++ if (unlikely(err))
++ goto out_revert;
+ }
+
-+ wh_dentry = NULL;
-+ if (bcpup != au_dbwh(dentry))
-+ goto out; /* success */
-+
-+ /*
-+ * ENAMETOOLONG here means that if we allowed create such name, then it
-+ * would not be able to removed in the future. So we don't allow such
-+ * name here and we don't handle ENAMETOOLONG differently here.
-+ */
-+ wh_dentry = au_wh_lkup(h_parent, &dentry->d_name, br);
++ au_dir_ts(dir, a->bdst);
++ inode_inc_iversion(dir);
++ inc_nlink(inode);
++ inode_set_ctime_to_ts(inode, inode_get_ctime(dir));
++ d_instantiate(dentry, au_igrab(inode));
++ if (d_unhashed(a->h_path.dentry))
++ /* some filesystem calls d_drop() */
++ d_drop(dentry);
++ /* some filesystems consume an inode even hardlink */
++ au_fhsm_wrote(sb, a->bdst, /*force*/0);
++ goto out_unpin; /* success */
+
++out_revert:
++ /* no delegation since it is just created */
++ rerr = vfsub_unlink(au_pinned_h_dir(&a->pin), &a->h_path,
++ /*delegated*/NULL, /*force*/0);
++ if (unlikely(rerr)) {
++ AuIOErr("%pd reverting failed(%d, %d)\n", dentry, err, rerr);
++ err = -EIO;
++ }
++ au_dtime_revert(&dt);
+out_unpin:
-+ if (IS_ERR(wh_dentry))
-+ au_unpin(pin);
++ au_unpin(&a->pin);
++out_wh:
++ dput(wh_dentry);
++out_parent:
++ di_write_unlock(a->parent);
++ dput(a->src_parent);
++out_unlock:
++ if (unlikely(err)) {
++ au_update_dbtop(dentry);
++ d_drop(dentry);
++ }
++ aufs_read_and_write_unlock2(dentry, src_dentry);
++out_kfree:
++ au_kfree_rcu(a);
+out:
-+ return wh_dentry;
++ AuTraceErr(err);
++ return err;
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+enum { Mknod, Symlink, Creat };
-+struct simple_arg {
-+ int type;
-+ union {
-+ struct {
-+ umode_t mode;
-+ bool want_excl;
-+ bool try_aopen;
-+ struct vfsub_aopen_args *aopen;
-+ } c;
-+ struct {
-+ const char *symname;
-+ } s;
-+ struct {
-+ umode_t mode;
-+ dev_t dev;
-+ } m;
-+ } u;
-+};
-+
-+static int add_simple(struct inode *dir, struct dentry *dentry,
-+ struct simple_arg *arg)
++int aufs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
++ struct dentry *dentry, umode_t mode)
+{
+ int err, rerr;
-+ aufs_bindex_t btop;
-+ unsigned char created;
-+ const unsigned char try_aopen
-+ = (arg->type == Creat && arg->u.c.try_aopen);
-+ struct vfsub_aopen_args *aopen = arg->u.c.aopen;
-+ struct dentry *wh_dentry, *parent;
-+ struct inode *h_dir;
++ aufs_bindex_t bindex;
++ unsigned char diropq;
++ struct path h_path;
++ struct dentry *wh_dentry, *parent, *opq_dentry;
++ struct inode *h_inode;
+ struct super_block *sb;
-+ struct au_branch *br;
-+ /* to reduce stack size */
+ struct {
-+ struct au_dtime dt;
+ struct au_pin pin;
-+ struct path h_path;
-+ struct au_wr_dir_args wr_dir_args;
-+ } *a;
++ struct au_dtime dt;
++ } *a; /* reduce the stack usage */
++ struct au_wr_dir_args wr_dir_args = {
++ .force_btgt = -1,
++ .flags = AuWrDir_ADD_ENTRY | AuWrDir_ISDIR
++ };
+
-+ AuDbg("%pd\n", dentry);
+ IMustLock(dir);
+
+ err = -ENOMEM;
+ a = kmalloc(sizeof(*a), GFP_NOFS);
+ if (unlikely(!a))
+ goto out;
-+ a->wr_dir_args.force_btgt = -1;
-+ a->wr_dir_args.flags = AuWrDir_ADD_ENTRY;
+
-+ parent = dentry->d_parent; /* dir inode is locked */
-+ if (!try_aopen) {
-+ err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN);
-+ if (unlikely(err))
-+ goto out_free;
-+ }
++ err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN);
++ if (unlikely(err))
++ goto out_free;
+ err = au_d_may_add(dentry);
+ if (unlikely(err))
+ goto out_unlock;
-+ if (!try_aopen)
-+ di_write_lock_parent(parent);
++
++ parent = dentry->d_parent; /* dir inode is locked */
++ di_write_lock_parent(parent);
+ wh_dentry = lock_hdir_lkup_wh(dentry, &a->dt, /*src_dentry*/NULL,
-+ &a->pin, &a->wr_dir_args);
++ &a->pin, &wr_dir_args);
+ err = PTR_ERR(wh_dentry);
+ if (IS_ERR(wh_dentry))
+ goto out_parent;
+
-+ btop = au_dbtop(dentry);
+ sb = dentry->d_sb;
-+ br = au_sbr(sb, btop);
-+ a->h_path.dentry = au_h_dptr(dentry, btop);
-+ a->h_path.mnt = au_br_mnt(br);
-+ h_dir = au_pinned_h_dir(&a->pin);
-+ switch (arg->type) {
-+ case Creat:
-+ if (!try_aopen || !h_dir->i_op->atomic_open) {
-+ err = vfsub_create(h_dir, &a->h_path, arg->u.c.mode,
-+ arg->u.c.want_excl);
-+ created = !err;
-+ if (!err && try_aopen)
-+ aopen->file->f_mode |= FMODE_CREATED;
-+ } else {
-+ aopen->br = br;
-+ err = vfsub_atomic_open(h_dir, a->h_path.dentry, aopen);
-+ AuDbg("err %d\n", err);
-+ AuDbgFile(aopen->file);
-+ created = err >= 0
-+ && !!(aopen->file->f_mode & FMODE_CREATED);
-+ }
-+ break;
-+ case Symlink:
-+ err = vfsub_symlink(h_dir, &a->h_path, arg->u.s.symname);
-+ created = !err;
-+ break;
-+ case Mknod:
-+ err = vfsub_mknod(h_dir, &a->h_path, arg->u.m.mode,
-+ arg->u.m.dev);
-+ created = !err;
-+ break;
-+ default:
-+ BUG();
-+ }
-+ if (unlikely(err < 0))
++ bindex = au_dbtop(dentry);
++ h_path.dentry = au_h_dptr(dentry, bindex);
++ h_path.mnt = au_sbr_mnt(sb, bindex);
++ err = vfsub_mkdir(au_pinned_h_dir(&a->pin), &h_path, mode);
++ if (unlikely(err))
+ goto out_unpin;
+
-+ err = epilog(dir, btop, wh_dentry, dentry);
-+ if (!err)
++ /* make the dir opaque */
++ diropq = 0;
++ h_inode = d_inode(h_path.dentry);
++ if (wh_dentry
++ || au_opt_test(au_mntflags(sb), ALWAYS_DIROPQ)) {
++ inode_lock_nested(h_inode, AuLsc_I_CHILD);
++ opq_dentry = au_diropq_create(dentry, bindex);
++ inode_unlock(h_inode);
++ err = PTR_ERR(opq_dentry);
++ if (IS_ERR(opq_dentry))
++ goto out_dir;
++ dput(opq_dentry);
++ diropq = 1;
++ }
++
++ err = epilog(dir, bindex, wh_dentry, dentry);
++ if (!err) {
++ inc_nlink(dir);
+ goto out_unpin; /* success */
++ }
+
+ /* revert */
-+ if (created /* && d_is_positive(a->h_path.dentry) */) {
-+ /* no delegation since it is just created */
-+ rerr = vfsub_unlink(h_dir, &a->h_path, /*delegated*/NULL,
-+ /*force*/0);
++ if (diropq) {
++ AuLabel(revert opq);
++ inode_lock_nested(h_inode, AuLsc_I_CHILD);
++ rerr = au_diropq_remove(dentry, bindex);
++ inode_unlock(h_inode);
+ if (rerr) {
-+ AuIOErr("%pd revert failure(%d, %d)\n",
++ AuIOErr("%pd reverting diropq failed(%d, %d)\n",
+ dentry, err, rerr);
+ err = -EIO;
+ }
-+ au_dtime_revert(&a->dt);
+ }
-+ if (try_aopen && h_dir->i_op->atomic_open
-+ && (aopen->file->f_mode & FMODE_OPENED))
-+ /* aopen->file is still opened */
-+ au_lcnt_dec(&aopen->br->br_nfiles);
+
++out_dir:
++ AuLabel(revert dir);
++ rerr = vfsub_rmdir(au_pinned_h_dir(&a->pin), &h_path);
++ if (rerr) {
++ AuIOErr("%pd reverting dir failed(%d, %d)\n",
++ dentry, err, rerr);
++ err = -EIO;
++ }
++ au_dtime_revert(&a->dt);
+out_unpin:
+ au_unpin(&a->pin);
+ dput(wh_dentry);
+out_parent:
-+ if (!try_aopen)
-+ di_write_unlock(parent);
++ di_write_unlock(parent);
+out_unlock:
+ if (unlikely(err)) {
+ au_update_dbtop(dentry);
+ d_drop(dentry);
+ }
-+ if (!try_aopen)
-+ aufs_read_unlock(dentry, AuLock_DW);
++ aufs_read_unlock(dentry, AuLock_DW);
+out_free:
+ au_kfree_rcu(a);
+out:
+ return err;
+}
+diff --git a/fs/aufs/i_op_del.c b/fs/aufs/i_op_del.c
+new file mode 100644
+index 00000000000000..8d9631492b930a
+--- /dev/null
++++ b/fs/aufs/i_op_del.c
+@@ -0,0 +1,523 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2005-2022 Junjiro R. Okajima
++ *
++ * This program 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/>.
++ */
+
-+int aufs_mknod(struct mnt_idmap *idmap, struct inode *dir,
-+ struct dentry *dentry, umode_t mode, dev_t dev)
-+{
-+ struct simple_arg arg = {
-+ .type = Mknod,
-+ .u.m = {
-+ .mode = mode,
-+ .dev = dev
-+ }
-+ };
-+ return add_simple(dir, dentry, &arg);
-+}
++/*
++ * inode operations (del entry)
++ */
+
-+int aufs_symlink(struct mnt_idmap *idmap, struct inode *dir,
-+ struct dentry *dentry, const char *symname)
-+{
-+ struct simple_arg arg = {
-+ .type = Symlink,
-+ .u.s.symname = symname
-+ };
-+ return add_simple(dir, dentry, &arg);
-+}
++#include <linux/iversion.h>
++#include "aufs.h"
+
-+int aufs_create(struct mnt_idmap *idmap, struct inode *dir,
-+ struct dentry *dentry, umode_t mode, bool want_excl)
++/*
++ * decide if a new whiteout for @dentry is necessary or not.
++ * when it is necessary, prepare the parent dir for the upper branch whose
++ * branch index is @bcpup for creation. the actual creation of the whiteout will
++ * be done by caller.
++ * return value:
++ * 0: wh is unnecessary
++ * plus: wh is necessary
++ * minus: error
++ */
++int au_wr_dir_need_wh(struct dentry *dentry, int isdir, aufs_bindex_t *bcpup)
+{
-+ struct simple_arg arg = {
-+ .type = Creat,
-+ .u.c = {
-+ .mode = mode,
-+ .want_excl = want_excl
++ int need_wh, err;
++ aufs_bindex_t btop;
++ struct super_block *sb;
++
++ sb = dentry->d_sb;
++ btop = au_dbtop(dentry);
++ if (*bcpup < 0) {
++ *bcpup = btop;
++ if (au_test_ro(sb, btop, d_inode(dentry))) {
++ err = AuWbrCopyup(au_sbi(sb), dentry);
++ *bcpup = err;
++ if (unlikely(err < 0))
++ goto out;
+ }
-+ };
-+ return add_simple(dir, dentry, &arg);
-+}
++ } else
++ AuDebugOn(btop < *bcpup
++ || au_test_ro(sb, *bcpup, d_inode(dentry)));
++ AuDbg("bcpup %d, btop %d\n", *bcpup, btop);
+
-+int au_aopen_or_create(struct inode *dir, struct dentry *dentry,
-+ struct vfsub_aopen_args *aopen_args)
-+{
-+ struct simple_arg arg = {
-+ .type = Creat,
-+ .u.c = {
-+ .mode = aopen_args->create_mode,
-+ .want_excl = aopen_args->open_flag & O_EXCL,
-+ .try_aopen = true,
-+ .aopen = aopen_args
++ if (*bcpup != btop) {
++ err = au_cpup_dirs(dentry, *bcpup);
++ if (unlikely(err))
++ goto out;
++ need_wh = 1;
++ } else {
++ struct au_dinfo *dinfo, *tmp;
++
++ need_wh = -ENOMEM;
++ dinfo = au_di(dentry);
++ tmp = au_di_alloc(sb, AuLsc_DI_TMP);
++ if (tmp) {
++ au_di_cp(tmp, dinfo);
++ au_di_swap(tmp, dinfo);
++ /* returns the number of positive dentries */
++ need_wh = au_lkup_dentry(dentry, btop + 1,
++ /* AuLkup_IGNORE_PERM */ 0);
++ au_di_swap(tmp, dinfo);
++ au_rw_write_unlock(&tmp->di_rwsem);
++ au_di_free(tmp);
+ }
-+ };
-+ return add_simple(dir, dentry, &arg);
++ }
++ AuDbg("need_wh %d\n", need_wh);
++ err = need_wh;
++
++out:
++ return err;
+}
+
-+int aufs_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
-+ struct file *file, umode_t mode)
++/*
++ * simple tests for the del-entry operations.
++ * following the checks in vfs, plus the parent-child relationship.
++ */
++int au_may_del(struct dentry *dentry, aufs_bindex_t bindex,
++ struct dentry *h_parent, int isdir)
+{
+ int err;
-+ aufs_bindex_t bindex;
++ umode_t h_mode;
++ struct dentry *h_dentry, *h_latest;
++ struct inode *h_inode;
+ struct path h_ppath;
+ struct super_block *sb;
+ struct au_branch *br;
-+ struct dentry *dentry, *parent, *h_parent, *h_dentry;
-+ struct inode *h_dir, *inode;
-+ struct vfsmount *h_mnt;
+ struct mnt_idmap *h_idmap;
-+ struct file *h_file;
-+ struct au_wr_dir_args wr_dir_args = {
-+ .force_btgt = -1,
-+ .flags = AuWrDir_TMPFILE
-+ };
-+
-+ /* copy-up may happen */
-+ inode_lock(dir);
-+
-+ h_file = NULL;
-+ sb = dir->i_sb;
-+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
-+ if (unlikely(err))
-+ goto out;
-+
-+ dentry = file->f_path.dentry;
-+ err = au_di_init(dentry);
-+ if (unlikely(err))
-+ goto out_si;
-+
-+ err = -EBUSY;
-+ parent = d_find_any_alias(dir);
-+ AuDebugOn(!parent);
-+ di_write_lock_parent(parent);
-+ if (unlikely(d_inode(parent) != dir))
-+ goto out_parent;
-+
-+ err = au_digen_test(parent, au_sigen(sb));
-+ if (unlikely(err))
-+ goto out_parent;
-+
-+ bindex = au_dbtop(parent);
-+ au_set_dbtop(dentry, bindex);
-+ au_set_dbbot(dentry, bindex);
-+ err = au_wr_dir(dentry, /*src_dentry*/NULL, &wr_dir_args);
-+ bindex = err;
-+ if (unlikely(err < 0))
-+ goto out_parent;
-+
-+ err = -EOPNOTSUPP;
-+ h_dir = au_h_iptr(dir, bindex);
-+ if (unlikely(!h_dir->i_op->tmpfile))
-+ goto out_parent;
-+
-+ br = au_sbr(sb, bindex);
-+ h_mnt = au_br_mnt(br);
-+ err = vfsub_mnt_want_write(h_mnt);
-+ if (unlikely(err))
-+ goto out_parent;
+
-+ h_idmap = mnt_idmap(h_mnt);
-+ h_parent = au_h_dptr(parent, bindex);
-+ h_ppath.mnt = h_mnt;
-+ h_ppath.dentry = h_parent;
-+ h_file = kernel_tmpfile_open(h_idmap, &h_ppath, mode, /*open_flag*/0,
-+ current_cred());
-+ if (IS_ERR(h_file)) {
-+ err = PTR_ERR(h_file);
-+ h_file = NULL;
-+ goto out_mnt;
-+ }
++ h_dentry = au_h_dptr(dentry, bindex);
++ if (d_really_is_positive(dentry)) {
++ err = -ENOENT;
++ if (unlikely(d_is_negative(h_dentry)))
++ goto out;
++ h_inode = d_inode(h_dentry);
++ if (unlikely(!h_inode->i_nlink))
++ goto out;
+
-+ h_dentry = h_file->f_path.dentry;
-+ au_set_dbtop(dentry, bindex);
-+ au_set_dbbot(dentry, bindex);
-+ au_set_h_dptr(dentry, bindex, dget(h_dentry));
-+ inode = au_new_inode(dentry, /*must_new*/1);
-+ if (IS_ERR(inode)) {
-+ err = PTR_ERR(inode);
-+ au_set_h_dptr(dentry, bindex, NULL);
-+ au_set_dbtop(dentry, -1);
-+ au_set_dbbot(dentry, -1);
-+ goto out_h_file;
++ h_mode = h_inode->i_mode;
++ if (!isdir) {
++ err = -EISDIR;
++ if (unlikely(S_ISDIR(h_mode)))
++ goto out;
++ } else if (unlikely(!S_ISDIR(h_mode))) {
++ err = -ENOTDIR;
++ goto out;
++ }
++ } else {
++ /* rename(2) case */
++ err = -EIO;
++ if (unlikely(d_is_positive(h_dentry)))
++ goto out;
+ }
+
-+ if (!inode->i_nlink)
-+ set_nlink(inode, 1);
-+ d_tmpfile(file, inode);
-+ au_di(dentry)->di_tmpfile = 1;
-+ get_file(h_file);
-+ au_di(dentry)->di_htmpfile = h_file;
++ err = -ENOENT;
++ /* expected parent dir is locked */
++ if (unlikely(h_parent != h_dentry->d_parent))
++ goto out;
++ err = 0;
+
-+ /* update without i_mutex */
-+ if (au_ibtop(dir) == au_dbtop(dentry))
-+ au_cpup_attr_timesizes(dir);
++ /*
++ * rmdir a dir may break the consistency on some filesystem.
++ * let's try heavy test.
++ */
++ err = -EACCES;
++ sb = dentry->d_sb;
++ br = au_sbr(sb, bindex);
++ h_idmap = au_br_idmap(br);
++ if (unlikely(!au_opt_test(au_mntflags(sb), DIRPERM1)
++ && au_test_h_perm(h_idmap, d_inode(h_parent),
++ MAY_EXEC | MAY_WRITE)))
++ goto out;
++
++ h_ppath.dentry = h_parent;
++ h_ppath.mnt = au_br_mnt(br);
++ h_latest = au_sio_lkup_one(h_idmap, &dentry->d_name, &h_ppath);
++ err = -EIO;
++ if (IS_ERR(h_latest))
++ goto out;
++ if (h_latest == h_dentry)
++ err = 0;
++ dput(h_latest);
+
-+out_h_file:
-+ fput(h_file);
-+out_mnt:
-+ vfsub_mnt_drop_write(h_mnt);
-+out_parent:
-+ di_write_unlock(parent);
-+ dput(parent);
-+ di_write_unlock(dentry);
-+ if (!err)
-+ goto out_si;
-+ if (h_file)
-+ fput(h_file);
-+ au_di(dentry)->di_htmpfile = NULL;
-+ au_di_fin(dentry);
-+ dentry->d_fsdata = NULL;
-+out_si:
-+ si_read_unlock(sb);
-+ if (!err && h_file) {
-+ /* finally... */
-+ err = finish_open_simple(file, err);
-+ if (!err)
-+ au_lcnt_inc(&br->br_nfiles);
-+ else {
-+ fput(h_file);
-+ au_di(dentry)->di_htmpfile = NULL;
-+ au_di_fin(dentry);
-+ dentry->d_fsdata = NULL;
-+ }
-+ }
+out:
-+ inode_unlock(dir);
-+ AuTraceErr(err);
+ return err;
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+struct au_link_args {
-+ aufs_bindex_t bdst, bsrc;
-+ struct au_pin pin;
-+ struct path h_path;
-+ struct dentry *src_parent, *parent;
-+};
-+
-+static int au_cpup_before_link(struct dentry *src_dentry,
-+ struct au_link_args *a)
++/*
++ * decide the branch where we operate for @dentry. the branch index will be set
++ * @rbcpup. after deciding it, 'pin' it and store the timestamps of the parent
++ * dir for reverting.
++ * when a new whiteout is necessary, create it.
++ */
++static struct dentry*
++lock_hdir_create_wh(struct dentry *dentry, int isdir, aufs_bindex_t *rbcpup,
++ struct au_dtime *dt, struct au_pin *pin)
+{
-+ int err;
-+ struct dentry *h_src_dentry;
-+ struct au_cp_generic cpg = {
-+ .dentry = src_dentry,
-+ .bdst = a->bdst,
-+ .bsrc = a->bsrc,
-+ .len = -1,
-+ .pin = &a->pin,
-+ .flags = AuCpup_DTIME | AuCpup_HOPEN /* | AuCpup_KEEPLINO */
-+ };
++ struct dentry *wh_dentry;
++ struct super_block *sb;
++ struct path h_path;
++ int err, need_wh;
++ unsigned int udba;
++ aufs_bindex_t bcpup;
+
-+ di_read_lock_parent(a->src_parent, AuLock_IR);
-+ err = au_test_and_cpup_dirs(src_dentry, a->bdst);
-+ if (unlikely(err))
++ need_wh = au_wr_dir_need_wh(dentry, isdir, rbcpup);
++ wh_dentry = ERR_PTR(need_wh);
++ if (unlikely(need_wh < 0))
+ goto out;
+
-+ h_src_dentry = au_h_dptr(src_dentry, a->bsrc);
-+ err = au_pin(&a->pin, src_dentry, a->bdst,
-+ au_opt_udba(src_dentry->d_sb),
++ sb = dentry->d_sb;
++ udba = au_opt_udba(sb);
++ bcpup = *rbcpup;
++ err = au_pin(pin, dentry, bcpup, udba,
+ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
++ wh_dentry = ERR_PTR(err);
+ if (unlikely(err))
+ goto out;
+
-+ err = au_sio_cpup_simple(&cpg);
-+ au_unpin(&a->pin);
++ h_path.dentry = au_pinned_h_parent(pin);
++ if (udba != AuOpt_UDBA_NONE
++ && au_dbtop(dentry) == bcpup) {
++ err = au_may_del(dentry, bcpup, h_path.dentry, isdir);
++ wh_dentry = ERR_PTR(err);
++ if (unlikely(err))
++ goto out_unpin;
++ }
++
++ h_path.mnt = au_sbr_mnt(sb, bcpup);
++ au_dtime_store(dt, au_pinned_parent(pin), &h_path);
++ wh_dentry = NULL;
++ if (!need_wh)
++ goto out; /* success, no need to create whiteout */
++
++ wh_dentry = au_wh_create(dentry, bcpup, h_path.dentry);
++ if (IS_ERR(wh_dentry))
++ goto out_unpin;
++
++ /* returns with the parent is locked and wh_dentry is dget-ed */
++ goto out; /* success */
+
++out_unpin:
++ au_unpin(pin);
+out:
-+ di_read_unlock(a->src_parent, AuLock_IR);
-+ return err;
++ return wh_dentry;
+}
+
-+static int au_cpup_or_link(struct dentry *src_dentry, struct dentry *dentry,
-+ struct au_link_args *a)
++/*
++ * when removing a dir, rename it to a unique temporary whiteout-ed name first
++ * in order to be revertible and save time for removing many child whiteouts
++ * under the dir.
++ * returns 1 when there are too many child whiteout and caller should remove
++ * them asynchronously. returns 0 when the number of children is enough small to
++ * remove now or the branch fs is a remote fs.
++ * otherwise return an error.
++ */
++static int renwh_and_rmdir(struct dentry *dentry, aufs_bindex_t bindex,
++ struct au_nhash *whlist, struct inode *dir)
+{
-+ int err;
-+ unsigned char plink;
-+ aufs_bindex_t bbot;
-+ struct dentry *h_src_dentry;
-+ struct inode *h_inode, *inode, *delegated;
++ int rmdir_later, err, dirwh;
++ struct dentry *h_dentry;
+ struct super_block *sb;
-+ struct file *h_file;
++ struct inode *inode;
+
-+ plink = 0;
-+ h_inode = NULL;
-+ sb = src_dentry->d_sb;
-+ inode = d_inode(src_dentry);
-+ if (au_ibtop(inode) <= a->bdst)
-+ h_inode = au_h_iptr(inode, a->bdst);
-+ if (!h_inode || !h_inode->i_nlink) {
-+ /* copyup src_dentry as the name of dentry. */
-+ bbot = au_dbbot(dentry);
-+ if (bbot < a->bsrc)
-+ au_set_dbbot(dentry, a->bsrc);
-+ au_set_h_dptr(dentry, a->bsrc,
-+ dget(au_h_dptr(src_dentry, a->bsrc)));
-+ dget(a->h_path.dentry);
-+ au_set_h_dptr(dentry, a->bdst, NULL);
-+ AuDbg("temporary d_inode...\n");
-+ spin_lock(&dentry->d_lock);
-+ dentry->d_inode = d_inode(src_dentry); /* tmp */
-+ spin_unlock(&dentry->d_lock);
-+ h_file = au_h_open_pre(dentry, a->bsrc, /*force_wr*/0);
-+ if (IS_ERR(h_file))
-+ err = PTR_ERR(h_file);
-+ else {
-+ struct au_cp_generic cpg = {
-+ .dentry = dentry,
-+ .bdst = a->bdst,
-+ .bsrc = -1,
-+ .len = -1,
-+ .pin = &a->pin,
-+ .flags = AuCpup_KEEPLINO
-+ };
-+ err = au_sio_cpup_simple(&cpg);
-+ au_h_open_post(dentry, a->bsrc, h_file);
-+ if (!err) {
-+ dput(a->h_path.dentry);
-+ a->h_path.dentry = au_h_dptr(dentry, a->bdst);
-+ } else
-+ au_set_h_dptr(dentry, a->bdst,
-+ a->h_path.dentry);
-+ }
-+ spin_lock(&dentry->d_lock);
-+ dentry->d_inode = NULL; /* restore */
-+ spin_unlock(&dentry->d_lock);
-+ AuDbg("temporary d_inode...done\n");
-+ au_set_h_dptr(dentry, a->bsrc, NULL);
-+ au_set_dbbot(dentry, bbot);
-+ } else {
-+ /* the inode of src_dentry already exists on a.bdst branch */
-+ h_src_dentry = d_find_alias(h_inode);
-+ if (!h_src_dentry && au_plink_test(inode)) {
-+ plink = 1;
-+ h_src_dentry = au_plink_lkup(inode, a->bdst);
-+ err = PTR_ERR(h_src_dentry);
-+ if (IS_ERR(h_src_dentry))
-+ goto out;
++ sb = dentry->d_sb;
++ SiMustAnyLock(sb);
++ h_dentry = au_h_dptr(dentry, bindex);
++ err = au_whtmp_ren(h_dentry, au_sbr(sb, bindex));
++ if (unlikely(err))
++ goto out;
+
-+ if (unlikely(d_is_negative(h_src_dentry))) {
-+ dput(h_src_dentry);
-+ h_src_dentry = NULL;
-+ }
++ /* stop monitoring */
++ inode = d_inode(dentry);
++ au_hn_free(au_hi(inode, bindex));
+
-+ }
-+ if (h_src_dentry) {
-+ delegated = NULL;
-+ err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin),
-+ &a->h_path, &delegated);
-+ if (unlikely(err == -EWOULDBLOCK)) {
-+ pr_warn("cannot retry for NFSv4 delegation"
-+ " for an internal link\n");
-+ iput(delegated);
-+ }
-+ dput(h_src_dentry);
-+ } else {
-+ AuIOErr("no dentry found for hi%lu on b%d\n",
-+ h_inode->i_ino, a->bdst);
-+ err = -EIO;
-+ }
++ if (!au_test_fs_remote(h_dentry->d_sb)) {
++ dirwh = au_sbi(sb)->si_dirwh;
++ rmdir_later = (dirwh <= 1);
++ if (!rmdir_later)
++ rmdir_later = au_nhash_test_longer_wh(whlist, bindex,
++ dirwh);
++ if (rmdir_later)
++ return rmdir_later;
+ }
+
-+ if (!err && !plink)
-+ au_plink_append(inode, a->bdst, a->h_path.dentry);
++ err = au_whtmp_rmdir(dir, bindex, h_dentry, whlist);
++ if (unlikely(err)) {
++ AuIOErr("rmdir %pd, b%d failed, %d. ignored\n",
++ h_dentry, bindex, err);
++ err = 0;
++ }
+
+out:
+ AuTraceErr(err);
+ return err;
+}
+
-+int aufs_link(struct dentry *src_dentry, struct inode *dir,
-+ struct dentry *dentry)
++/*
++ * final procedure for deleting a entry.
++ * maintain dentry and iattr.
++ */
++static void epilog(struct inode *dir, struct dentry *dentry,
++ aufs_bindex_t bindex)
+{
-+ int err, rerr;
-+ struct au_dtime dt;
-+ struct au_link_args *a;
-+ struct dentry *wh_dentry, *h_src_dentry;
-+ struct inode *inode, *delegated;
-+ struct super_block *sb;
-+ struct au_wr_dir_args wr_dir_args = {
-+ /* .force_btgt = -1, */
-+ .flags = AuWrDir_ADD_ENTRY
++ struct inode *inode;
++
++ inode = d_inode(dentry);
++ d_drop(dentry);
++ inode_set_ctime_to_ts(inode, inode_get_ctime(dir));
++
++ au_dir_ts(dir, bindex);
++ inode_inc_iversion(dir);
++}
++
++/*
++ * when an error happened, remove the created whiteout and revert everything.
++ */
++static int do_revert(int err, struct inode *dir, aufs_bindex_t bindex,
++ aufs_bindex_t bwh, struct dentry *wh_dentry,
++ struct dentry *dentry, struct au_dtime *dt)
++{
++ int rerr;
++ struct path h_path = {
++ .dentry = wh_dentry,
++ .mnt = au_sbr_mnt(dir->i_sb, bindex)
+ };
+
++ rerr = au_wh_unlink_dentry(au_h_iptr(dir, bindex), &h_path, dentry);
++ if (!rerr) {
++ au_set_dbwh(dentry, bwh);
++ au_dtime_revert(dt);
++ return 0;
++ }
++
++ AuIOErr("%pd reverting whiteout failed(%d, %d)\n", dentry, err, rerr);
++ return -EIO;
++}
++
++/* ---------------------------------------------------------------------- */
++
++int aufs_unlink(struct inode *dir, struct dentry *dentry)
++{
++ int err;
++ aufs_bindex_t bwh, bindex, btop;
++ struct inode *inode, *h_dir, *delegated, *h_inode;
++ struct dentry *parent, *wh_dentry;
++ /* to reduce stack size */
++ struct {
++ struct au_dtime dt;
++ struct au_pin pin;
++ struct path h_path;
++ } *a;
++
+ IMustLock(dir);
-+ inode = d_inode(src_dentry);
-+ IMustLock(inode);
+
+ err = -ENOMEM;
-+ a = kzalloc(sizeof(*a), GFP_NOFS);
++ a = kmalloc(sizeof(*a), GFP_NOFS);
+ if (unlikely(!a))
+ goto out;
+
-+ a->parent = dentry->d_parent; /* dir inode is locked */
-+ err = aufs_read_and_write_lock2(dentry, src_dentry,
-+ AuLock_NOPLM | AuLock_GEN);
-+ if (unlikely(err))
-+ goto out_kfree;
-+ err = au_d_linkable(src_dentry);
++ err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN);
+ if (unlikely(err))
-+ goto out_unlock;
-+ err = au_d_may_add(dentry);
++ goto out_free;
++ err = au_d_hashed_positive(dentry);
+ if (unlikely(err))
+ goto out_unlock;
++ inode = d_inode(dentry);
++ IMustLock(inode);
++ err = -EISDIR;
++ if (unlikely(d_is_dir(dentry)))
++ goto out_unlock; /* possible? */
+
-+ a->src_parent = dget_parent(src_dentry);
-+ wr_dir_args.force_btgt = au_ibtop(inode);
-+
-+ di_write_lock_parent(a->parent);
-+ wr_dir_args.force_btgt = au_wbr(dentry, wr_dir_args.force_btgt);
-+ wh_dentry = lock_hdir_lkup_wh(dentry, &dt, src_dentry, &a->pin,
-+ &wr_dir_args);
++ btop = au_dbtop(dentry);
++ bwh = au_dbwh(dentry);
++ bindex = -1;
++ parent = dentry->d_parent; /* dir inode is locked */
++ di_write_lock_parent(parent);
++ wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/0, &bindex, &a->dt,
++ &a->pin);
+ err = PTR_ERR(wh_dentry);
+ if (IS_ERR(wh_dentry))
+ goto out_parent;
+
-+ err = 0;
-+ sb = dentry->d_sb;
-+ a->bdst = au_dbtop(dentry);
-+ a->h_path.dentry = au_h_dptr(dentry, a->bdst);
-+ a->h_path.mnt = au_sbr_mnt(sb, a->bdst);
-+ a->bsrc = au_ibtop(inode);
-+ h_src_dentry = au_h_d_alias(src_dentry, a->bsrc);
-+ if (!h_src_dentry && au_di(src_dentry)->di_tmpfile)
-+ h_src_dentry = dget(au_hi_wh(inode, a->bsrc));
-+ if (!h_src_dentry) {
-+ a->bsrc = au_dbtop(src_dentry);
-+ h_src_dentry = au_h_d_alias(src_dentry, a->bsrc);
-+ AuDebugOn(!h_src_dentry);
-+ } else if (IS_ERR(h_src_dentry)) {
-+ err = PTR_ERR(h_src_dentry);
-+ goto out_parent;
-+ }
-+
-+ /*
-+ * aufs doesn't touch the credential so
-+ * security_dentry_create_files_as() is unnecessary.
-+ */
-+ if (au_opt_test(au_mntflags(sb), PLINK)) {
-+ if (a->bdst < a->bsrc
-+ /* && h_src_dentry->d_sb != a->h_path.dentry->d_sb */)
-+ err = au_cpup_or_link(src_dentry, dentry, a);
-+ else {
-+ delegated = NULL;
-+ err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin),
-+ &a->h_path, &delegated);
-+ if (unlikely(err == -EWOULDBLOCK)) {
-+ pr_warn("cannot retry for NFSv4 delegation"
-+ " for an internal link\n");
-+ iput(delegated);
-+ }
++ a->h_path.mnt = au_sbr_mnt(dentry->d_sb, btop);
++ a->h_path.dentry = au_h_dptr(dentry, btop);
++ dget(a->h_path.dentry);
++ if (bindex == btop) {
++ h_dir = au_pinned_h_dir(&a->pin);
++ delegated = NULL;
++ err = vfsub_unlink(h_dir, &a->h_path, &delegated, /*force*/0);
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal unlink\n");
++ iput(delegated);
+ }
-+ dput(h_src_dentry);
+ } else {
-+ /*
-+ * copyup src_dentry to the branch we process,
-+ * and then link(2) to it.
-+ */
-+ dput(h_src_dentry);
-+ if (a->bdst < a->bsrc
-+ /* && h_src_dentry->d_sb != a->h_path.dentry->d_sb */) {
-+ au_unpin(&a->pin);
-+ di_write_unlock(a->parent);
-+ err = au_cpup_before_link(src_dentry, a);
-+ di_write_lock_parent(a->parent);
-+ if (!err)
-+ err = au_pin(&a->pin, dentry, a->bdst,
-+ au_opt_udba(sb),
-+ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
-+ if (unlikely(err))
-+ goto out_wh;
-+ }
-+ if (!err) {
-+ h_src_dentry = au_h_dptr(src_dentry, a->bdst);
-+ err = -ENOENT;
-+ if (h_src_dentry && d_is_positive(h_src_dentry)) {
-+ delegated = NULL;
-+ err = vfsub_link(h_src_dentry,
-+ au_pinned_h_dir(&a->pin),
-+ &a->h_path, &delegated);
-+ if (unlikely(err == -EWOULDBLOCK)) {
-+ pr_warn("cannot retry"
-+ " for NFSv4 delegation"
-+ " for an internal link\n");
-+ iput(delegated);
-+ }
-+ }
-+ }
++ /* dir inode is locked */
++ h_dir = d_inode(wh_dentry->d_parent);
++ IMustLock(h_dir);
++ err = 0;
+ }
-+ if (unlikely(err))
-+ goto out_unpin;
+
-+ if (wh_dentry) {
-+ a->h_path.dentry = wh_dentry;
-+ err = au_wh_unlink_dentry(au_pinned_h_dir(&a->pin), &a->h_path,
-+ dentry);
-+ if (unlikely(err))
-+ goto out_revert;
++ if (!err) {
++ vfsub_drop_nlink(inode);
++ epilog(dir, dentry, bindex);
++
++ /* update target timestamps */
++ if (bindex == btop) {
++ vfsub_update_h_iattr(&a->h_path, /*did*/NULL);
++ /*ignore*/
++ h_inode = d_inode(a->h_path.dentry);
++ inode_set_ctime_to_ts(inode, inode_get_ctime(h_inode));
++ } else
++ /* todo: this timestamp may be reverted later */
++ inode_set_ctime_to_ts(inode, inode_get_ctime(h_dir));
++ goto out_unpin; /* success */
+ }
+
-+ au_dir_ts(dir, a->bdst);
-+ inode_inc_iversion(dir);
-+ inc_nlink(inode);
-+ inode_set_ctime_to_ts(inode, inode_get_ctime(dir));
-+ d_instantiate(dentry, au_igrab(inode));
-+ if (d_unhashed(a->h_path.dentry))
-+ /* some filesystem calls d_drop() */
-+ d_drop(dentry);
-+ /* some filesystems consume an inode even hardlink */
-+ au_fhsm_wrote(sb, a->bdst, /*force*/0);
-+ goto out_unpin; /* success */
++ /* revert */
++ if (wh_dentry) {
++ int rerr;
+
-+out_revert:
-+ /* no delegation since it is just created */
-+ rerr = vfsub_unlink(au_pinned_h_dir(&a->pin), &a->h_path,
-+ /*delegated*/NULL, /*force*/0);
-+ if (unlikely(rerr)) {
-+ AuIOErr("%pd reverting failed(%d, %d)\n", dentry, err, rerr);
-+ err = -EIO;
++ rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry,
++ &a->dt);
++ if (rerr)
++ err = rerr;
+ }
-+ au_dtime_revert(&dt);
++
+out_unpin:
+ au_unpin(&a->pin);
-+out_wh:
+ dput(wh_dentry);
++ dput(a->h_path.dentry);
+out_parent:
-+ di_write_unlock(a->parent);
-+ dput(a->src_parent);
++ di_write_unlock(parent);
+out_unlock:
-+ if (unlikely(err)) {
-+ au_update_dbtop(dentry);
-+ d_drop(dentry);
-+ }
-+ aufs_read_and_write_unlock2(dentry, src_dentry);
-+out_kfree:
++ aufs_read_unlock(dentry, AuLock_DW);
++out_free:
+ au_kfree_rcu(a);
+out:
-+ AuTraceErr(err);
+ return err;
+}
+
-+int aufs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
-+ struct dentry *dentry, umode_t mode)
++int aufs_rmdir(struct inode *dir, struct dentry *dentry)
+{
-+ int err, rerr;
-+ aufs_bindex_t bindex;
-+ unsigned char diropq;
-+ struct path h_path;
-+ struct dentry *wh_dentry, *parent, *opq_dentry;
-+ struct inode *h_inode;
-+ struct super_block *sb;
++ int err, rmdir_later;
++ aufs_bindex_t bwh, bindex, btop;
++ struct inode *inode;
++ struct dentry *parent, *wh_dentry, *h_dentry;
++ struct au_whtmp_rmdir *args;
++ /* to reduce stack size */
+ struct {
-+ struct au_pin pin;
+ struct au_dtime dt;
-+ } *a; /* reduce the stack usage */
-+ struct au_wr_dir_args wr_dir_args = {
-+ .force_btgt = -1,
-+ .flags = AuWrDir_ADD_ENTRY | AuWrDir_ISDIR
-+ };
++ struct au_pin pin;
++ } *a;
+
+ IMustLock(dir);
+
+ if (unlikely(!a))
+ goto out;
+
-+ err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN);
++ err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN);
+ if (unlikely(err))
+ goto out_free;
-+ err = au_d_may_add(dentry);
++ err = au_alive_dir(dentry);
+ if (unlikely(err))
+ goto out_unlock;
++ inode = d_inode(dentry);
++ IMustLock(inode);
++ err = -ENOTDIR;
++ if (unlikely(!d_is_dir(dentry)))
++ goto out_unlock; /* possible? */
++
++ err = -ENOMEM;
++ args = au_whtmp_rmdir_alloc(dir->i_sb, GFP_NOFS);
++ if (unlikely(!args))
++ goto out_unlock;
+
+ parent = dentry->d_parent; /* dir inode is locked */
+ di_write_lock_parent(parent);
-+ wh_dentry = lock_hdir_lkup_wh(dentry, &a->dt, /*src_dentry*/NULL,
-+ &a->pin, &wr_dir_args);
-+ err = PTR_ERR(wh_dentry);
-+ if (IS_ERR(wh_dentry))
++ err = au_test_empty(dentry, &args->whlist);
++ if (unlikely(err))
+ goto out_parent;
+
-+ sb = dentry->d_sb;
-+ bindex = au_dbtop(dentry);
-+ h_path.dentry = au_h_dptr(dentry, bindex);
-+ h_path.mnt = au_sbr_mnt(sb, bindex);
-+ err = vfsub_mkdir(au_pinned_h_dir(&a->pin), &h_path, mode);
-+ if (unlikely(err))
-+ goto out_unpin;
++ btop = au_dbtop(dentry);
++ bwh = au_dbwh(dentry);
++ bindex = -1;
++ wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/1, &bindex, &a->dt,
++ &a->pin);
++ err = PTR_ERR(wh_dentry);
++ if (IS_ERR(wh_dentry))
++ goto out_parent;
+
-+ /* make the dir opaque */
-+ diropq = 0;
-+ h_inode = d_inode(h_path.dentry);
-+ if (wh_dentry
-+ || au_opt_test(au_mntflags(sb), ALWAYS_DIROPQ)) {
-+ inode_lock_nested(h_inode, AuLsc_I_CHILD);
-+ opq_dentry = au_diropq_create(dentry, bindex);
-+ inode_unlock(h_inode);
-+ err = PTR_ERR(opq_dentry);
-+ if (IS_ERR(opq_dentry))
-+ goto out_dir;
-+ dput(opq_dentry);
-+ diropq = 1;
++ h_dentry = au_h_dptr(dentry, btop);
++ dget(h_dentry);
++ rmdir_later = 0;
++ if (bindex == btop) {
++ err = renwh_and_rmdir(dentry, btop, &args->whlist, dir);
++ if (err > 0) {
++ rmdir_later = err;
++ err = 0;
++ }
++ } else {
++ /* stop monitoring */
++ au_hn_free(au_hi(inode, btop));
++
++ /* dir inode is locked */
++ IMustLock(d_inode(wh_dentry->d_parent));
++ err = 0;
+ }
+
-+ err = epilog(dir, bindex, wh_dentry, dentry);
+ if (!err) {
-+ inc_nlink(dir);
++ vfsub_dead_dir(inode);
++ au_set_dbdiropq(dentry, -1);
++ epilog(dir, dentry, bindex);
++
++ if (rmdir_later) {
++ au_whtmp_kick_rmdir(dir, btop, h_dentry, args);
++ args = NULL;
++ }
++
+ goto out_unpin; /* success */
+ }
+
+ /* revert */
-+ if (diropq) {
-+ AuLabel(revert opq);
-+ inode_lock_nested(h_inode, AuLsc_I_CHILD);
-+ rerr = au_diropq_remove(dentry, bindex);
-+ inode_unlock(h_inode);
-+ if (rerr) {
-+ AuIOErr("%pd reverting diropq failed(%d, %d)\n",
-+ dentry, err, rerr);
-+ err = -EIO;
-+ }
-+ }
++ AuLabel(revert);
++ if (wh_dentry) {
++ int rerr;
+
-+out_dir:
-+ AuLabel(revert dir);
-+ rerr = vfsub_rmdir(au_pinned_h_dir(&a->pin), &h_path);
-+ if (rerr) {
-+ AuIOErr("%pd reverting dir failed(%d, %d)\n",
-+ dentry, err, rerr);
-+ err = -EIO;
++ rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry,
++ &a->dt);
++ if (rerr)
++ err = rerr;
+ }
-+ au_dtime_revert(&a->dt);
++
+out_unpin:
+ au_unpin(&a->pin);
+ dput(wh_dentry);
++ dput(h_dentry);
+out_parent:
+ di_write_unlock(parent);
++ if (args)
++ au_whtmp_rmdir_free(args);
+out_unlock:
-+ if (unlikely(err)) {
-+ au_update_dbtop(dentry);
-+ d_drop(dentry);
-+ }
+ aufs_read_unlock(dentry, AuLock_DW);
+out_free:
+ au_kfree_rcu(a);
+out:
++ AuTraceErr(err);
+ return err;
+}
-diff -urN /usr/share/empty/fs/aufs/i_op.c linux/fs/aufs/i_op.c
---- /usr/share/empty/fs/aufs/i_op.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/i_op.c 2023-10-31 09:31:04.199880750 +0100
-@@ -0,0 +1,1516 @@
+diff --git a/fs/aufs/i_op_ren.c b/fs/aufs/i_op_ren.c
+new file mode 100644
+index 00000000000000..e5a3d5549ac7ae
+--- /dev/null
++++ b/fs/aufs/i_op_ren.c
+@@ -0,0 +1,1260 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2005-2022 Junjiro R. Okajima
+ */
+
+/*
-+ * inode operations (except add/del/rename)
++ * inode operation (rename entry)
++ * todo: this is crazy monster
+ */
+
-+#include <linux/device_cgroup.h>
-+#include <linux/filelock.h>
-+#include <linux/fs_stack.h>
+#include <linux/iversion.h>
-+#include <linux/security.h>
+#include "aufs.h"
+
-+static int h_permission(struct inode *h_inode, int mask,
-+ struct path *h_path, int brperm)
-+{
-+ int err;
-+ const unsigned char write_mask = !!(mask & (MAY_WRITE | MAY_APPEND));
-+ struct mnt_idmap *h_idmap;
-+
-+ err = -EPERM;
-+ if (write_mask && IS_IMMUTABLE(h_inode))
-+ goto out;
-+
-+ err = -EACCES;
-+ if (((mask & MAY_EXEC)
-+ && S_ISREG(h_inode->i_mode)
-+ && (path_noexec(h_path)
-+ || !(h_inode->i_mode & 0111))))
-+ goto out;
-+
-+ /*
-+ * - skip the lower fs test in the case of write to ro branch.
-+ * - nfs dir permission write check is optimized, but a policy for
-+ * link/rename requires a real check.
-+ * - nfs always sets SB_POSIXACL regardless its mount option 'noacl.'
-+ * in this case, generic_permission() returns -EOPNOTSUPP.
-+ */
-+ h_idmap = mnt_idmap(h_path->mnt);
-+ if ((write_mask && !au_br_writable(brperm))
-+ || (au_test_nfs(h_inode->i_sb) && S_ISDIR(h_inode->i_mode)
-+ && write_mask && !(mask & MAY_READ))
-+ || !h_inode->i_op->permission) {
-+ /* AuLabel(generic_permission); */
-+ /* AuDbg("get_inode_acl %ps\n",
-+ h_inode->i_op->get_inode_acl); */
-+ err = generic_permission(h_idmap, h_inode, mask);
-+ if (err == -EOPNOTSUPP && au_test_nfs_noacl(h_inode))
-+ err = h_inode->i_op->permission(h_idmap, h_inode,
-+ mask);
-+ AuTraceErr(err);
-+ } else {
-+ /* AuLabel(h_inode->permission); */
-+ err = h_inode->i_op->permission(h_idmap, h_inode, mask);
-+ AuTraceErr(err);
-+ }
-+
-+ if (!err)
-+ err = devcgroup_inode_permission(h_inode, mask);
-+ if (!err)
-+ err = security_inode_permission(h_inode, mask);
-+
-+out:
-+ return err;
-+}
-+
-+static int aufs_permission(struct mnt_idmap *idmap, struct inode *inode,
-+ int mask)
-+{
-+ int err;
-+ aufs_bindex_t bindex, bbot;
-+ const unsigned char isdir = !!S_ISDIR(inode->i_mode),
-+ write_mask = !!(mask & (MAY_WRITE | MAY_APPEND));
-+ struct inode *h_inode;
-+ struct super_block *sb;
-+ struct au_branch *br;
++enum { AuSRC, AuDST, AuSrcDst };
++enum { AuPARENT, AuCHILD, AuParentChild };
+
-+ /* todo: support rcu-walk? */
-+ if (mask & MAY_NOT_BLOCK)
-+ return -ECHILD;
++#define AuRen_ISDIR_SRC 1
++#define AuRen_ISDIR_DST (1 << 1)
++#define AuRen_ISSAMEDIR (1 << 2)
++#define AuRen_WHSRC (1 << 3)
++#define AuRen_WHDST (1 << 4)
++#define AuRen_MNT_WRITE (1 << 5)
++#define AuRen_DT_DSTDIR (1 << 6)
++#define AuRen_DIROPQ_SRC (1 << 7)
++#define AuRen_DIROPQ_DST (1 << 8)
++#define AuRen_DIRREN (1 << 9)
++#define AuRen_DROPPED_SRC (1 << 10)
++#define AuRen_DROPPED_DST (1 << 11)
++#define au_ftest_ren(flags, name) ((flags) & AuRen_##name)
++#define au_fset_ren(flags, name) \
++ do { (flags) |= AuRen_##name; } while (0)
++#define au_fclr_ren(flags, name) \
++ do { (flags) &= ~AuRen_##name; } while (0)
+
-+ sb = inode->i_sb;
-+ si_read_lock(sb, AuLock_FLUSH);
-+ ii_read_lock_child(inode);
-+#if 0 /* reserved for future use */
-+ /*
-+ * This test may be rather 'too much' since the test is essentially done
-+ * in the aufs_lookup(). Theoretically it is possible that the inode
-+ * generation doesn't match to the superblock's here. But it isn't a
-+ * big deal I suppose.
-+ */
-+ err = au_iigen_test(inode, au_sigen(sb));
-+ if (unlikely(err))
-+ goto out;
++#ifndef CONFIG_AUFS_DIRREN
++#undef AuRen_DIRREN
++#define AuRen_DIRREN 0
+#endif
+
-+ if (!isdir
-+ || write_mask
-+ || au_opt_test(au_mntflags(sb), DIRPERM1)) {
-+ err = au_busy_or_stale();
-+ h_inode = au_h_iptr(inode, au_ibtop(inode));
-+ if (unlikely(!h_inode
-+ || (h_inode->i_mode & S_IFMT)
-+ != (inode->i_mode & S_IFMT)))
-+ goto out;
-+
-+ err = 0;
-+ bindex = au_ibtop(inode);
-+ br = au_sbr(sb, bindex);
-+ err = h_permission(h_inode, mask, &br->br_path, br->br_perm);
-+ if (write_mask
-+ && !err
-+ && !special_file(h_inode->i_mode)) {
-+ /* test whether the upper writable branch exists */
-+ err = -EROFS;
-+ for (; bindex >= 0; bindex--)
-+ if (!au_br_rdonly(au_sbr(sb, bindex))) {
-+ err = 0;
-+ break;
-+ }
-+ }
-+ goto out;
-+ }
-+
-+ /* non-write to dir */
-+ err = 0;
-+ bbot = au_ibbot(inode);
-+ for (bindex = au_ibtop(inode); !err && bindex <= bbot; bindex++) {
-+ h_inode = au_h_iptr(inode, bindex);
-+ if (h_inode) {
-+ err = au_busy_or_stale();
-+ if (unlikely(!S_ISDIR(h_inode->i_mode)))
-+ break;
-+
-+ br = au_sbr(sb, bindex);
-+ err = h_permission(h_inode, mask, &br->br_path,
-+ br->br_perm);
-+ }
-+ }
-+
-+out:
-+ ii_read_unlock(inode);
-+ si_read_unlock(sb);
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static struct dentry *aufs_lookup(struct inode *dir, struct dentry *dentry,
-+ unsigned int flags)
-+{
-+ struct dentry *ret, *parent;
-+ struct inode *inode;
-+ struct super_block *sb;
-+ int err, npositive;
-+
-+ IMustLock(dir);
-+
-+ /* todo: support rcu-walk? */
-+ ret = ERR_PTR(-ECHILD);
-+ if (flags & LOOKUP_RCU)
-+ goto out;
-+
-+ ret = ERR_PTR(-ENAMETOOLONG);
-+ if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN))
-+ goto out;
-+
-+ sb = dir->i_sb;
-+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
-+ ret = ERR_PTR(err);
-+ if (unlikely(err))
-+ goto out;
++struct au_ren_args {
++ struct {
++ struct dentry *dentry, *h_dentry, *parent, *h_parent,
++ *wh_dentry;
++ struct inode *dir, *inode;
++ struct au_hinode *hdir, *hinode;
++ struct au_dtime dt[AuParentChild];
++ aufs_bindex_t btop, bdiropq;
++ } sd[AuSrcDst];
+
-+ err = au_di_init(dentry);
-+ ret = ERR_PTR(err);
-+ if (unlikely(err))
-+ goto out_si;
++#define src_dentry sd[AuSRC].dentry
++#define src_dir sd[AuSRC].dir
++#define src_inode sd[AuSRC].inode
++#define src_h_dentry sd[AuSRC].h_dentry
++#define src_parent sd[AuSRC].parent
++#define src_h_parent sd[AuSRC].h_parent
++#define src_wh_dentry sd[AuSRC].wh_dentry
++#define src_hdir sd[AuSRC].hdir
++#define src_hinode sd[AuSRC].hinode
++#define src_h_dir sd[AuSRC].hdir->hi_inode
++#define src_dt sd[AuSRC].dt
++#define src_btop sd[AuSRC].btop
++#define src_bdiropq sd[AuSRC].bdiropq
+
-+ inode = NULL;
-+ npositive = 0; /* suppress a warning */
-+ parent = dentry->d_parent; /* dir inode is locked */
-+ di_read_lock_parent(parent, AuLock_IR);
-+ err = au_alive_dir(parent);
-+ if (!err)
-+ err = au_digen_test(parent, au_sigen(sb));
-+ if (!err) {
-+ /* regardless LOOKUP_CREATE, always ALLOW_NEG */
-+ npositive = au_lkup_dentry(dentry, au_dbtop(parent),
-+ AuLkup_ALLOW_NEG);
-+ err = npositive;
-+ }
-+ di_read_unlock(parent, AuLock_IR);
-+ ret = ERR_PTR(err);
-+ if (unlikely(err < 0))
-+ goto out_unlock;
++#define dst_dentry sd[AuDST].dentry
++#define dst_dir sd[AuDST].dir
++#define dst_inode sd[AuDST].inode
++#define dst_h_dentry sd[AuDST].h_dentry
++#define dst_parent sd[AuDST].parent
++#define dst_h_parent sd[AuDST].h_parent
++#define dst_wh_dentry sd[AuDST].wh_dentry
++#define dst_hdir sd[AuDST].hdir
++#define dst_hinode sd[AuDST].hinode
++#define dst_h_dir sd[AuDST].hdir->hi_inode
++#define dst_dt sd[AuDST].dt
++#define dst_btop sd[AuDST].btop
++#define dst_bdiropq sd[AuDST].bdiropq
+
-+ if (npositive) {
-+ inode = au_new_inode(dentry, /*must_new*/0);
-+ if (IS_ERR(inode)) {
-+ ret = (void *)inode;
-+ inode = NULL;
-+ goto out_unlock;
-+ }
-+ }
++ struct dentry *h_trap;
++ struct au_branch *br;
++ struct path h_path;
++ struct au_nhash whlist;
++ aufs_bindex_t btgt, src_bwh;
+
-+ if (inode)
-+ atomic_inc(&inode->i_count);
-+ ret = d_splice_alias(inode, dentry);
-+#if 0 /* reserved for future use */
-+ if (unlikely(d_need_lookup(dentry))) {
-+ spin_lock(&dentry->d_lock);
-+ dentry->d_flags &= ~DCACHE_NEED_LOOKUP;
-+ spin_unlock(&dentry->d_lock);
-+ } else
-+#endif
-+ if (inode) {
-+ if (!IS_ERR(ret)) {
-+ iput(inode);
-+ if (ret && ret != dentry)
-+ ii_write_unlock(inode);
-+ } else {
-+ ii_write_unlock(inode);
-+ iput(inode);
-+ inode = NULL;
-+ }
-+ }
++ struct {
++ unsigned short auren_flags;
++ unsigned char flags; /* syscall parameter */
++ unsigned char exchange;
++ } __packed;
+
-+out_unlock:
-+ di_write_unlock(dentry);
-+out_si:
-+ si_read_unlock(sb);
-+out:
-+ return ret;
-+}
++ struct au_whtmp_rmdir *thargs;
++ struct dentry *h_dst;
++ struct au_hinode *h_root;
++};
+
+/* ---------------------------------------------------------------------- */
+
+/*
-+ * very dirty and complicated aufs ->atomic_open().
-+ * aufs_atomic_open()
-+ * + au_aopen_or_create()
-+ * + add_simple()
-+ * + vfsub_atomic_open()
-+ * + branch fs ->atomic_open()
-+ * may call the actual 'open' for h_file
-+ * + inc br_nfiles only if opened
-+ * + au_aopen_no_open() or au_aopen_do_open()
-+ *
-+ * au_aopen_do_open()
-+ * + finish_open()
-+ * + au_do_aopen()
-+ * + au_do_open() the body of all 'open'
-+ * + au_do_open_nondir()
-+ * set the passed h_file
-+ *
-+ * au_aopen_no_open()
-+ * + finish_no_open()
++ * functions for reverting.
++ * when an error happened in a single rename systemcall, we should revert
++ * everything as if nothing happened.
++ * we don't need to revert the copied-up/down the parent dir since they are
++ * harmless.
+ */
+
-+struct aopen_node {
-+ struct hlist_bl_node hblist;
-+ struct file *file, *h_file;
-+};
-+
-+static int au_do_aopen(struct inode *inode, struct file *file)
-+{
-+ struct hlist_bl_head *aopen;
-+ struct hlist_bl_node *pos;
-+ struct aopen_node *node;
-+ struct au_do_open_args args = {
-+ .aopen = 1,
-+ .open = au_do_open_nondir
-+ };
-+
-+ aopen = &au_sbi(inode->i_sb)->si_aopen;
-+ hlist_bl_lock(aopen);
-+ hlist_bl_for_each_entry(node, pos, aopen, hblist)
-+ if (node->file == file) {
-+ args.h_file = node->h_file;
-+ break;
-+ }
-+ hlist_bl_unlock(aopen);
-+ /* AuDebugOn(!args.h_file); */
-+
-+ return au_do_open(file, &args);
-+}
-+
-+static int au_aopen_do_open(struct file *file, struct dentry *dentry,
-+ struct aopen_node *aopen_node)
-+{
-+ int err;
-+ struct hlist_bl_head *aopen;
-+
-+ AuLabel(here);
-+ aopen = &au_sbi(dentry->d_sb)->si_aopen;
-+ au_hbl_add(&aopen_node->hblist, aopen);
-+ err = finish_open(file, dentry, au_do_aopen);
-+ au_hbl_del(&aopen_node->hblist, aopen);
-+ /* AuDbgFile(file); */
-+ AuDbg("%pd%s%s\n", dentry,
-+ (file->f_mode & FMODE_CREATED) ? " created" : "",
-+ (file->f_mode & FMODE_OPENED) ? " opened" : "");
-+
-+ AuTraceErr(err);
-+ return err;
-+}
++#define RevertFailure(fmt, ...) do { \
++ AuIOErr("revert failure: " fmt " (%d, %d)\n", \
++ ##__VA_ARGS__, err, rerr); \
++ err = -EIO; \
++} while (0)
+
-+static int au_aopen_no_open(struct file *file, struct dentry *dentry)
++static void au_ren_do_rev_diropq(int err, struct au_ren_args *a, int idx)
+{
-+ int err;
++ int rerr;
++ struct dentry *d;
++#define src_or_dst(member) a->sd[idx].member
+
-+ AuLabel(here);
-+ dget(dentry);
-+ err = finish_no_open(file, dentry);
++ d = src_or_dst(dentry); /* {src,dst}_dentry */
++ au_hn_inode_lock_nested(src_or_dst(hinode), AuLsc_I_CHILD);
++ rerr = au_diropq_remove(d, a->btgt);
++ au_hn_inode_unlock(src_or_dst(hinode));
++ au_set_dbdiropq(d, src_or_dst(bdiropq));
++ if (rerr)
++ RevertFailure("remove diropq %pd", d);
+
-+ AuTraceErr(err);
-+ return err;
++#undef src_or_dst_
+}
+
-+static int aufs_atomic_open(struct inode *dir, struct dentry *dentry,
-+ struct file *file, unsigned int open_flag,
-+ umode_t create_mode)
-+{
-+ int err, did_open;
-+ unsigned int lkup_flags;
-+ aufs_bindex_t bindex;
-+ struct super_block *sb;
-+ struct dentry *parent, *d;
-+ struct vfsub_aopen_args args = {
-+ .open_flag = open_flag,
-+ .create_mode = create_mode
-+ };
-+ struct aopen_node aopen_node = {
-+ .file = file
-+ };
-+
-+ IMustLock(dir);
-+ AuDbg("open_flag 0%o\n", open_flag);
-+ AuDbgDentry(dentry);
-+
-+ err = 0;
-+ if (!au_di(dentry)) {
-+ lkup_flags = LOOKUP_OPEN;
-+ if (open_flag & O_CREAT)
-+ lkup_flags |= LOOKUP_CREATE;
-+ d = aufs_lookup(dir, dentry, lkup_flags);
-+ if (IS_ERR(d)) {
-+ err = PTR_ERR(d);
-+ AuTraceErr(err);
-+ goto out;
-+ } else if (d) {
-+ /*
-+ * obsoleted dentry found.
-+ * another error will be returned later.
-+ */
-+ d_drop(d);
-+ AuDbgDentry(d);
-+ dput(d);
-+ }
-+ AuDbgDentry(dentry);
-+ }
-+
-+ if (d_is_positive(dentry)
-+ || d_unhashed(dentry)
-+ || d_unlinked(dentry)
-+ || !(open_flag & O_CREAT)) {
-+ err = au_aopen_no_open(file, dentry);
-+ goto out; /* success */
-+ }
++static void au_ren_rev_diropq(int err, struct au_ren_args *a)
++{
++ if (au_ftest_ren(a->auren_flags, DIROPQ_SRC))
++ au_ren_do_rev_diropq(err, a, AuSRC);
++ if (au_ftest_ren(a->auren_flags, DIROPQ_DST))
++ au_ren_do_rev_diropq(err, a, AuDST);
++}
+
-+ err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN);
-+ if (unlikely(err))
-+ goto out;
++static void au_ren_rev_rename(int err, struct au_ren_args *a)
++{
++ int rerr;
++ struct inode *delegated;
++ struct path h_ppath = {
++ .dentry = a->src_h_parent,
++ .mnt = a->h_path.mnt
++ };
+
-+ sb = dentry->d_sb;
-+ parent = dentry->d_parent; /* dir is locked */
-+ di_write_lock_parent(parent);
-+ err = au_lkup_dentry(dentry, /*btop*/0, AuLkup_ALLOW_NEG);
-+ if (unlikely(err < 0))
-+ goto out_parent;
++ a->h_path.dentry = vfsub_lkup_one(&a->src_dentry->d_name, &h_ppath);
++ rerr = PTR_ERR(a->h_path.dentry);
++ if (IS_ERR(a->h_path.dentry)) {
++ RevertFailure("lkup one %pd", a->src_dentry);
++ return;
++ }
+
-+ AuDbgDentry(dentry);
-+ if (d_is_positive(dentry)) {
-+ err = au_aopen_no_open(file, dentry);
-+ goto out_parent; /* success */
++ delegated = NULL;
++ rerr = vfsub_rename(a->dst_h_dir,
++ au_h_dptr(a->src_dentry, a->btgt),
++ a->src_h_dir, &a->h_path, &delegated, a->flags);
++ if (unlikely(rerr == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal rename\n");
++ iput(delegated);
+ }
++ d_drop(a->h_path.dentry);
++ dput(a->h_path.dentry);
++ /* au_set_h_dptr(a->src_dentry, a->btgt, NULL); */
++ if (rerr)
++ RevertFailure("rename %pd", a->src_dentry);
++}
+
-+ args.file = alloc_empty_file(file->f_flags, current_cred());
-+ err = PTR_ERR(args.file);
-+ if (IS_ERR(args.file))
-+ goto out_parent;
++static void au_ren_rev_whtmp(int err, struct au_ren_args *a)
++{
++ int rerr;
++ struct inode *delegated;
++ struct path h_ppath = {
++ .dentry = a->dst_h_parent,
++ .mnt = a->h_path.mnt
++ };
+
-+ bindex = au_dbtop(dentry);
-+ err = au_aopen_or_create(dir, dentry, &args);
-+ AuTraceErr(err);
-+ AuDbgFile(args.file);
-+ file->f_mode = args.file->f_mode & ~FMODE_OPENED;
-+ did_open = !!(args.file->f_mode & FMODE_OPENED);
-+ if (!did_open) {
-+ fput(args.file);
-+ args.file = NULL;
++ a->h_path.dentry = vfsub_lkup_one(&a->dst_dentry->d_name, &h_ppath);
++ rerr = PTR_ERR(a->h_path.dentry);
++ if (IS_ERR(a->h_path.dentry)) {
++ RevertFailure("lkup one %pd", a->dst_dentry);
++ return;
+ }
-+ di_write_unlock(parent);
-+ di_write_unlock(dentry);
-+ if (unlikely(err < 0)) {
-+ if (args.file)
-+ fput(args.file);
-+ goto out_sb;
++ if (d_is_positive(a->h_path.dentry)) {
++ d_drop(a->h_path.dentry);
++ dput(a->h_path.dentry);
++ return;
+ }
+
-+ if (!did_open)
-+ err = au_aopen_no_open(file, dentry);
-+ else {
-+ aopen_node.h_file = args.file;
-+ err = au_aopen_do_open(file, dentry, &aopen_node);
-+ }
-+ if (unlikely(err < 0)) {
-+ if (args.file)
-+ fput(args.file);
-+ if (did_open)
-+ au_lcnt_dec(&args.br->br_nfiles);
++ delegated = NULL;
++ rerr = vfsub_rename(a->dst_h_dir, a->h_dst, a->dst_h_dir, &a->h_path,
++ &delegated, a->flags);
++ if (unlikely(rerr == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal rename\n");
++ iput(delegated);
+ }
-+ goto out_sb; /* success */
-+
-+out_parent:
-+ di_write_unlock(parent);
-+ di_write_unlock(dentry);
-+out_sb:
-+ si_read_unlock(sb);
-+out:
-+ AuTraceErr(err);
-+ AuDbgFile(file);
-+ return err;
++ d_drop(a->h_path.dentry);
++ dput(a->h_path.dentry);
++ if (!rerr)
++ au_set_h_dptr(a->dst_dentry, a->btgt, dget(a->h_dst));
++ else
++ RevertFailure("rename %pd", a->h_dst);
+}
+
++static void au_ren_rev_whsrc(int err, struct au_ren_args *a)
++{
++ int rerr;
++
++ a->h_path.dentry = a->src_wh_dentry;
++ rerr = au_wh_unlink_dentry(a->src_h_dir, &a->h_path, a->src_dentry);
++ au_set_dbwh(a->src_dentry, a->src_bwh);
++ if (rerr)
++ RevertFailure("unlink %pd", a->src_wh_dentry);
++}
++#undef RevertFailure
+
+/* ---------------------------------------------------------------------- */
+
-+static int au_wr_dir_cpup(struct dentry *dentry, struct dentry *parent,
-+ const unsigned char add_entry, aufs_bindex_t bcpup,
-+ aufs_bindex_t btop)
++/*
++ * when we have to copyup the renaming entry, do it with the rename-target name
++ * in order to minimize the cost (the later actual rename is unnecessary).
++ * otherwise rename it on the target branch.
++ */
++static int au_ren_or_cpup(struct au_ren_args *a)
+{
+ int err;
-+ struct dentry *h_parent;
-+ struct inode *h_dir;
-+
-+ if (add_entry)
-+ IMustLock(d_inode(parent));
-+ else
-+ di_write_lock_parent(parent);
-+
-+ err = 0;
-+ if (!au_h_dptr(parent, bcpup)) {
-+ if (btop > bcpup)
-+ err = au_cpup_dirs(dentry, bcpup);
-+ else if (btop < bcpup)
-+ err = au_cpdown_dirs(dentry, bcpup);
-+ else
-+ BUG();
-+ }
-+ if (!err && add_entry && !au_ftest_wrdir(add_entry, TMPFILE)) {
-+ h_parent = au_h_dptr(parent, bcpup);
-+ h_dir = d_inode(h_parent);
-+ inode_lock_shared_nested(h_dir, AuLsc_I_PARENT);
-+ err = au_lkup_neg(dentry, bcpup, /*wh*/0);
-+ /* todo: no unlock here */
-+ inode_unlock_shared(h_dir);
++ struct dentry *d;
++ struct inode *delegated;
+
-+ AuDbg("bcpup %d\n", bcpup);
-+ if (!err) {
-+ if (d_really_is_negative(dentry))
-+ au_set_h_dptr(dentry, btop, NULL);
-+ au_update_dbrange(dentry, /*do_put_zero*/0);
++ d = a->src_dentry;
++ if (au_dbtop(d) == a->btgt) {
++ a->h_path.dentry = a->dst_h_dentry;
++ AuDebugOn(au_dbtop(d) != a->btgt);
++ delegated = NULL;
++ err = vfsub_rename(a->src_h_dir, au_h_dptr(d, a->btgt),
++ a->dst_h_dir, &a->h_path, &delegated,
++ a->flags);
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal rename\n");
++ iput(delegated);
+ }
-+ }
++ } else
++ BUG();
+
-+ if (!add_entry)
-+ di_write_unlock(parent);
-+ if (!err)
-+ err = bcpup; /* success */
++ if (!err && a->h_dst)
++ /* it will be set to dinfo later */
++ dget(a->h_dst);
+
-+ AuTraceErr(err);
+ return err;
+}
+
-+/*
-+ * decide the branch and the parent dir where we will create a new entry.
-+ * returns new bindex or an error.
-+ * copyup the parent dir if needed.
-+ */
-+int au_wr_dir(struct dentry *dentry, struct dentry *src_dentry,
-+ struct au_wr_dir_args *args)
++/* cf. aufs_rmdir() */
++static int au_ren_del_whtmp(struct au_ren_args *a)
+{
+ int err;
-+ unsigned int flags;
-+ aufs_bindex_t bcpup, btop, src_btop;
-+ const unsigned char add_entry
-+ = au_ftest_wrdir(args->flags, ADD_ENTRY)
-+ | au_ftest_wrdir(args->flags, TMPFILE);
-+ struct super_block *sb;
-+ struct dentry *parent;
-+ struct au_sbinfo *sbinfo;
-+
-+ sb = dentry->d_sb;
-+ sbinfo = au_sbi(sb);
-+ parent = dget_parent(dentry);
-+ btop = au_dbtop(dentry);
-+ bcpup = btop;
-+ if (args->force_btgt < 0) {
-+ if (src_dentry) {
-+ src_btop = au_dbtop(src_dentry);
-+ if (src_btop < btop)
-+ bcpup = src_btop;
-+ } else if (add_entry) {
-+ flags = 0;
-+ if (au_ftest_wrdir(args->flags, ISDIR))
-+ au_fset_wbr(flags, DIR);
-+ err = AuWbrCreate(sbinfo, dentry, flags);
-+ bcpup = err;
-+ }
++ struct inode *dir;
+
-+ if (bcpup < 0 || au_test_ro(sb, bcpup, d_inode(dentry))) {
-+ if (add_entry)
-+ err = AuWbrCopyup(sbinfo, dentry);
-+ else {
-+ if (!IS_ROOT(dentry)) {
-+ di_read_lock_parent(parent, !AuLock_IR);
-+ err = AuWbrCopyup(sbinfo, dentry);
-+ di_read_unlock(parent, !AuLock_IR);
-+ } else
-+ err = AuWbrCopyup(sbinfo, dentry);
-+ }
-+ bcpup = err;
-+ if (unlikely(err < 0))
-+ goto out;
-+ }
++ dir = a->dst_dir;
++ SiMustAnyLock(dir->i_sb);
++ if (!au_nhash_test_longer_wh(&a->whlist, a->btgt,
++ au_sbi(dir->i_sb)->si_dirwh)
++ || au_test_fs_remote(a->h_dst->d_sb)) {
++ err = au_whtmp_rmdir(dir, a->btgt, a->h_dst, &a->whlist);
++ if (unlikely(err))
++ pr_warn("failed removing whtmp dir %pd (%d), "
++ "ignored.\n", a->h_dst, err);
+ } else {
-+ bcpup = args->force_btgt;
-+ AuDebugOn(au_test_ro(sb, bcpup, d_inode(dentry)));
-+ }
-+
-+ AuDbg("btop %d, bcpup %d\n", btop, bcpup);
-+ err = bcpup;
-+ if (bcpup == btop)
-+ goto out; /* success */
-+
-+ /* copyup the new parent into the branch we process */
-+ err = au_wr_dir_cpup(dentry, parent, add_entry, bcpup, btop);
-+ if (err >= 0) {
-+ if (d_really_is_negative(dentry)) {
-+ au_set_h_dptr(dentry, btop, NULL);
-+ au_set_dbtop(dentry, bcpup);
-+ au_set_dbbot(dentry, bcpup);
-+ }
-+ AuDebugOn(add_entry
-+ && !au_ftest_wrdir(args->flags, TMPFILE)
-+ && !au_h_dptr(dentry, bcpup));
++ au_nhash_wh_free(&a->thargs->whlist);
++ a->thargs->whlist = a->whlist;
++ a->whlist.nh_num = 0;
++ au_whtmp_kick_rmdir(dir, a->btgt, a->h_dst, a->thargs);
++ dput(a->h_dst);
++ a->thargs = NULL;
+ }
+
-+out:
-+ dput(parent);
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+void au_pin_hdir_unlock(struct au_pin *p)
-+{
-+ if (p->hdir)
-+ au_hn_inode_unlock(p->hdir);
++ return 0;
+}
+
-+int au_pin_hdir_lock(struct au_pin *p)
++/* make it 'opaque' dir. */
++static int au_ren_do_diropq(struct au_ren_args *a, int idx)
+{
+ int err;
++ struct dentry *d, *diropq;
++#define src_or_dst(member) a->sd[idx].member
+
+ err = 0;
-+ if (!p->hdir)
-+ goto out;
-+
-+ /* even if an error happens later, keep this lock */
-+ au_hn_inode_lock_nested(p->hdir, p->lsc_hi);
-+
-+ err = -EBUSY;
-+ if (unlikely(p->hdir->hi_inode != d_inode(p->h_parent)))
-+ goto out;
-+
-+ err = 0;
-+ if (p->h_dentry)
-+ err = au_h_verify(p->h_dentry, p->udba, p->hdir->hi_inode,
-+ p->h_parent, p->br);
++ d = src_or_dst(dentry); /* {src,dst}_dentry */
++ src_or_dst(bdiropq) = au_dbdiropq(d);
++ src_or_dst(hinode) = au_hi(src_or_dst(inode), a->btgt);
++ au_hn_inode_lock_nested(src_or_dst(hinode), AuLsc_I_CHILD);
++ diropq = au_diropq_create(d, a->btgt);
++ au_hn_inode_unlock(src_or_dst(hinode));
++ if (IS_ERR(diropq))
++ err = PTR_ERR(diropq);
++ else
++ dput(diropq);
+
-+out:
++#undef src_or_dst_
+ return err;
+}
+
-+int au_pin_hdir_relock(struct au_pin *p)
++static int au_ren_diropq(struct au_ren_args *a)
+{
-+ int err, i;
-+ struct inode *h_i;
-+ struct dentry *h_d[] = {
-+ p->h_dentry,
-+ p->h_parent
-+ };
++ int err;
++ unsigned char always;
++ struct dentry *d;
+
-+ err = au_pin_hdir_lock(p);
-+ if (unlikely(err))
-+ goto out;
++ err = 0;
++ d = a->dst_dentry; /* already renamed on the branch */
++ always = !!au_opt_test(au_mntflags(d->d_sb), ALWAYS_DIROPQ);
++ if (au_ftest_ren(a->auren_flags, ISDIR_SRC)
++ && !au_ftest_ren(a->auren_flags, DIRREN)
++ && a->btgt != au_dbdiropq(a->src_dentry)
++ && (a->dst_wh_dentry
++ || a->btgt <= au_dbdiropq(d)
++ /* hide the lower to keep xino */
++ /* the lowers may not be a dir, but we hide them anyway */
++ || a->btgt < au_dbbot(d)
++ || always)) {
++ AuDbg("here\n");
++ err = au_ren_do_diropq(a, AuSRC);
++ if (unlikely(err))
++ goto out;
++ au_fset_ren(a->auren_flags, DIROPQ_SRC);
++ }
++ if (!a->exchange)
++ goto out; /* success */
+
-+ for (i = 0; !err && i < sizeof(h_d)/sizeof(*h_d); i++) {
-+ if (!h_d[i])
-+ continue;
-+ if (d_is_positive(h_d[i])) {
-+ h_i = d_inode(h_d[i]);
-+ err = !h_i->i_nlink;
-+ }
++ d = a->src_dentry; /* already renamed on the branch */
++ if (au_ftest_ren(a->auren_flags, ISDIR_DST)
++ && a->btgt != au_dbdiropq(a->dst_dentry)
++ && (a->btgt < au_dbdiropq(d)
++ || a->btgt < au_dbbot(d)
++ || always)) {
++ AuDbgDentry(a->src_dentry);
++ AuDbgDentry(a->dst_dentry);
++ err = au_ren_do_diropq(a, AuDST);
++ if (unlikely(err))
++ goto out_rev_src;
++ au_fset_ren(a->auren_flags, DIROPQ_DST);
+ }
++ goto out; /* success */
+
++out_rev_src:
++ AuDbg("err %d, reverting src\n", err);
++ au_ren_rev_diropq(err, a);
+out:
+ return err;
+}
+
-+static void au_pin_hdir_set_owner(struct au_pin *p, struct task_struct *task)
-+{
-+ atomic_long_set(&p->hdir->hi_inode->i_rwsem.owner, (long)task);
-+}
-+
-+void au_pin_hdir_acquire_nest(struct au_pin *p)
-+{
-+ if (p->hdir) {
-+ rwsem_acquire_nest(&p->hdir->hi_inode->i_rwsem.dep_map,
-+ p->lsc_hi, 0, NULL, _RET_IP_);
-+ au_pin_hdir_set_owner(p, current);
-+ }
-+}
-+
-+void au_pin_hdir_release(struct au_pin *p)
++static int do_rename(struct au_ren_args *a)
+{
-+ if (p->hdir) {
-+ au_pin_hdir_set_owner(p, p->task);
-+ rwsem_release(&p->hdir->hi_inode->i_rwsem.dep_map, _RET_IP_);
-+ }
-+}
++ int err;
++ struct dentry *d, *h_d;
++ struct inode *h_inode;
+
-+struct dentry *au_pinned_h_parent(struct au_pin *pin)
-+{
-+ if (pin && pin->parent)
-+ return au_h_dptr(pin->parent, pin->bindex);
-+ return NULL;
-+}
++ if (!a->exchange) {
++ /* prepare workqueue args for asynchronous rmdir */
++ h_d = a->dst_h_dentry;
++ if (au_ftest_ren(a->auren_flags, ISDIR_DST)
++ /* && !au_ftest_ren(a->auren_flags, DIRREN) */
++ && d_is_positive(h_d)) {
++ err = -ENOMEM;
++ a->thargs = au_whtmp_rmdir_alloc(a->src_dentry->d_sb,
++ GFP_NOFS);
++ if (unlikely(!a->thargs))
++ goto out;
++ a->h_dst = dget(h_d);
++ }
+
-+void au_unpin(struct au_pin *p)
-+{
-+ if (p->hdir)
-+ au_pin_hdir_unlock(p);
-+ if (p->h_mnt && au_ftest_pin(p->flags, MNT_WRITE))
-+ vfsub_mnt_drop_write(p->h_mnt);
-+ if (!p->hdir)
-+ return;
++ /* create whiteout for src_dentry */
++ if (au_ftest_ren(a->auren_flags, WHSRC)) {
++ a->src_bwh = au_dbwh(a->src_dentry);
++ AuDebugOn(a->src_bwh >= 0);
++ a->src_wh_dentry = au_wh_create(a->src_dentry, a->btgt,
++ a->src_h_parent);
++ err = PTR_ERR(a->src_wh_dentry);
++ if (IS_ERR(a->src_wh_dentry))
++ goto out_thargs;
++ }
+
-+ if (!au_ftest_pin(p->flags, DI_LOCKED))
-+ di_read_unlock(p->parent, AuLock_IR);
-+ iput(p->hdir->hi_inode);
-+ dput(p->parent);
-+ p->parent = NULL;
-+ p->hdir = NULL;
-+ p->h_mnt = NULL;
-+ /* do not clear p->task */
-+}
++ /* lookup whiteout for dentry */
++ if (au_ftest_ren(a->auren_flags, WHDST)) {
++ h_d = au_wh_lkup(a->dst_h_parent,
++ &a->dst_dentry->d_name, a->br);
++ err = PTR_ERR(h_d);
++ if (IS_ERR(h_d))
++ goto out_whsrc;
++ if (d_is_negative(h_d))
++ dput(h_d);
++ else
++ a->dst_wh_dentry = h_d;
++ }
+
-+int au_do_pin(struct au_pin *p)
-+{
-+ int err;
-+ struct super_block *sb;
-+ struct inode *h_dir;
++ /* rename dentry to tmpwh */
++ if (a->thargs) {
++ err = au_whtmp_ren(a->dst_h_dentry, a->br);
++ if (unlikely(err))
++ goto out_whdst;
+
-+ err = 0;
-+ sb = p->dentry->d_sb;
-+ p->br = au_sbr(sb, p->bindex);
-+ if (IS_ROOT(p->dentry)) {
-+ if (au_ftest_pin(p->flags, MNT_WRITE)) {
-+ p->h_mnt = au_br_mnt(p->br);
-+ err = vfsub_mnt_want_write(p->h_mnt);
-+ if (unlikely(err)) {
-+ au_fclr_pin(p->flags, MNT_WRITE);
-+ goto out_err;
-+ }
++ d = a->dst_dentry;
++ au_set_h_dptr(d, a->btgt, NULL);
++ err = au_lkup_neg(d, a->btgt, /*wh*/0);
++ if (unlikely(err))
++ goto out_whtmp;
++ a->dst_h_dentry = au_h_dptr(d, a->btgt);
+ }
-+ goto out;
+ }
+
-+ p->h_dentry = NULL;
-+ if (p->bindex <= au_dbbot(p->dentry))
-+ p->h_dentry = au_h_dptr(p->dentry, p->bindex);
++ BUG_ON(d_is_positive(a->dst_h_dentry) && a->src_btop != a->btgt);
++#if 0 /* debugging */
++ BUG_ON(!au_ftest_ren(a->auren_flags, DIRREN)
++ && d_is_positive(a->dst_h_dentry)
++ && a->src_btop != a->btgt);
++#endif
+
-+ p->parent = dget_parent(p->dentry);
-+ if (!au_ftest_pin(p->flags, DI_LOCKED))
-+ di_read_lock(p->parent, AuLock_IR, p->lsc_di);
++ /* rename by vfs_rename or cpup */
++ err = au_ren_or_cpup(a);
++ if (unlikely(err))
++ /* leave the copied-up one */
++ goto out_whtmp;
+
-+ h_dir = NULL;
-+ p->h_parent = au_h_dptr(p->parent, p->bindex);
-+ p->hdir = au_hi(d_inode(p->parent), p->bindex);
-+ if (p->hdir)
-+ h_dir = p->hdir->hi_inode;
++ /* make dir opaque */
++ err = au_ren_diropq(a);
++ if (unlikely(err))
++ goto out_rename;
+
-+ /*
-+ * udba case, or
-+ * if DI_LOCKED is not set, then p->parent may be different
-+ * and h_parent can be NULL.
-+ */
-+ if (unlikely(!p->hdir || !h_dir || !p->h_parent)) {
-+ err = -EBUSY;
-+ if (!au_ftest_pin(p->flags, DI_LOCKED))
-+ di_read_unlock(p->parent, AuLock_IR);
-+ dput(p->parent);
-+ p->parent = NULL;
-+ goto out_err;
++ /* update target timestamps */
++ if (a->exchange) {
++ AuDebugOn(au_dbtop(a->dst_dentry) != a->btgt);
++ a->h_path.dentry = au_h_dptr(a->dst_dentry, a->btgt);
++ vfsub_update_h_iattr(&a->h_path, /*did*/NULL); /*ignore*/
++ h_inode = d_inode(a->h_path.dentry);
++ inode_set_ctime_to_ts(a->dst_inode, inode_get_ctime(h_inode));
+ }
++ AuDebugOn(au_dbtop(a->src_dentry) != a->btgt);
++ a->h_path.dentry = au_h_dptr(a->src_dentry, a->btgt);
++ vfsub_update_h_iattr(&a->h_path, /*did*/NULL); /*ignore*/
++ h_inode = d_inode(a->h_path.dentry);
++ inode_set_ctime_to_ts(a->src_inode, inode_get_ctime(h_inode));
+
-+ if (au_ftest_pin(p->flags, MNT_WRITE)) {
-+ p->h_mnt = au_br_mnt(p->br);
-+ err = vfsub_mnt_want_write(p->h_mnt);
-+ if (unlikely(err)) {
-+ au_fclr_pin(p->flags, MNT_WRITE);
-+ if (!au_ftest_pin(p->flags, DI_LOCKED))
-+ di_read_unlock(p->parent, AuLock_IR);
-+ dput(p->parent);
-+ p->parent = NULL;
-+ goto out_err;
++ if (!a->exchange) {
++ /* remove whiteout for dentry */
++ if (a->dst_wh_dentry) {
++ a->h_path.dentry = a->dst_wh_dentry;
++ err = au_wh_unlink_dentry(a->dst_h_dir, &a->h_path,
++ a->dst_dentry);
++ if (unlikely(err))
++ goto out_diropq;
+ }
-+ }
+
-+ au_igrab(h_dir);
-+ err = au_pin_hdir_lock(p);
-+ if (!err)
-+ goto out; /* success */
++ /* remove whtmp */
++ if (a->thargs)
++ au_ren_del_whtmp(a); /* ignore this error */
+
-+ au_unpin(p);
++ au_fhsm_wrote(a->src_dentry->d_sb, a->btgt, /*force*/0);
++ }
++ err = 0;
++ goto out_success;
+
-+out_err:
-+ pr_err("err %d\n", err);
-+ err = au_busy_or_stale();
++out_diropq:
++ au_ren_rev_diropq(err, a);
++out_rename:
++ au_ren_rev_rename(err, a);
++ dput(a->h_dst);
++out_whtmp:
++ if (a->thargs)
++ au_ren_rev_whtmp(err, a);
++out_whdst:
++ dput(a->dst_wh_dentry);
++ a->dst_wh_dentry = NULL;
++out_whsrc:
++ if (a->src_wh_dentry)
++ au_ren_rev_whsrc(err, a);
++out_success:
++ dput(a->src_wh_dentry);
++ dput(a->dst_wh_dentry);
++out_thargs:
++ if (a->thargs) {
++ dput(a->h_dst);
++ au_whtmp_rmdir_free(a->thargs);
++ a->thargs = NULL;
++ }
+out:
+ return err;
+}
+
-+void au_pin_init(struct au_pin *p, struct dentry *dentry,
-+ aufs_bindex_t bindex, int lsc_di, int lsc_hi,
-+ unsigned int udba, unsigned char flags)
-+{
-+ p->dentry = dentry;
-+ p->udba = udba;
-+ p->lsc_di = lsc_di;
-+ p->lsc_hi = lsc_hi;
-+ p->flags = flags;
-+ p->bindex = bindex;
-+
-+ p->parent = NULL;
-+ p->hdir = NULL;
-+ p->h_mnt = NULL;
-+
-+ p->h_dentry = NULL;
-+ p->h_parent = NULL;
-+ p->br = NULL;
-+ p->task = current;
-+}
++/* ---------------------------------------------------------------------- */
+
-+int au_pin(struct au_pin *pin, struct dentry *dentry, aufs_bindex_t bindex,
-+ unsigned int udba, unsigned char flags)
++/*
++ * test if @dentry dir can be rename destination or not.
++ * success means, it is a logically empty dir.
++ */
++static int may_rename_dstdir(struct dentry *dentry, struct au_nhash *whlist)
+{
-+ au_pin_init(pin, dentry, bindex, AuLsc_DI_PARENT, AuLsc_I_PARENT2,
-+ udba, flags);
-+ return au_do_pin(pin);
++ return au_test_empty(dentry, whlist);
+}
+
-+/* ---------------------------------------------------------------------- */
-+
+/*
-+ * ->setattr() and ->getattr() are called in various cases.
-+ * chmod, stat: dentry is revalidated.
-+ * fchmod, fstat: file and dentry are not revalidated, additionally they may be
-+ * unhashed.
-+ * for ->setattr(), ia->ia_file is passed from ftruncate only.
++ * test if @a->src_dentry dir can be rename source or not.
++ * if it can, return 0.
++ * success means,
++ * - it is a logically empty dir.
++ * - or, it exists on writable branch and has no children including whiteouts
++ * on the lower branch unless DIRREN is on.
+ */
-+/* todo: consolidate with do_refresh() and simple_reval_dpath() */
-+int au_reval_for_attr(struct dentry *dentry, unsigned int sigen)
++static int may_rename_srcdir(struct au_ren_args *a)
+{
+ int err;
-+ struct dentry *parent;
++ unsigned int rdhash;
++ aufs_bindex_t btop, btgt;
++ struct dentry *dentry;
++ struct super_block *sb;
++ struct au_sbinfo *sbinfo;
+
-+ err = 0;
-+ if (au_digen_test(dentry, sigen)) {
-+ parent = dget_parent(dentry);
-+ di_read_lock_parent(parent, AuLock_IR);
-+ err = au_refresh_dentry(dentry, parent);
-+ di_read_unlock(parent, AuLock_IR);
-+ dput(parent);
++ dentry = a->src_dentry;
++ sb = dentry->d_sb;
++ sbinfo = au_sbi(sb);
++ if (au_opt_test(sbinfo->si_mntflags, DIRREN))
++ au_fset_ren(a->auren_flags, DIRREN);
++
++ btgt = a->btgt;
++ btop = au_dbtop(dentry);
++ if (btop != btgt) {
++ struct au_nhash whlist;
++
++ SiMustAnyLock(sb);
++ rdhash = sbinfo->si_rdhash;
++ if (!rdhash)
++ rdhash = au_rdhash_est(au_dir_size(/*file*/NULL,
++ dentry));
++ err = au_nhash_alloc(&whlist, rdhash, GFP_NOFS);
++ if (unlikely(err))
++ goto out;
++ err = au_test_empty(dentry, &whlist);
++ au_nhash_wh_free(&whlist);
++ goto out;
+ }
+
-+ AuTraceErr(err);
++ if (btop == au_dbtaildir(dentry))
++ return 0; /* success */
++
++ err = au_test_empty_lower(dentry);
++
++out:
++ if (err == -ENOTEMPTY) {
++ if (au_ftest_ren(a->auren_flags, DIRREN)) {
++ err = 0;
++ } else {
++ AuWarn1("renaming dir who has child(ren) on multiple "
++ "branches, is not supported\n");
++ err = -EXDEV;
++ }
++ }
+ return err;
+}
+
-+int au_pin_and_icpup(struct dentry *dentry, struct iattr *ia,
-+ struct au_icpup_args *a)
++/* side effect: sets whlist and h_dentry */
++static int au_ren_may_dir(struct au_ren_args *a)
+{
+ int err;
-+ loff_t sz;
-+ aufs_bindex_t btop, ibtop;
-+ struct dentry *hi_wh, *parent;
-+ struct inode *inode;
-+ struct au_wr_dir_args wr_dir_args = {
-+ .force_btgt = -1,
-+ .flags = 0
-+ };
++ unsigned int rdhash;
++ struct dentry *d;
+
-+ if (d_is_dir(dentry))
-+ au_fset_wrdir(wr_dir_args.flags, ISDIR);
-+ /* plink or hi_wh() case */
-+ btop = au_dbtop(dentry);
-+ inode = d_inode(dentry);
-+ ibtop = au_ibtop(inode);
-+ if (btop != ibtop && !au_test_ro(inode->i_sb, ibtop, inode))
-+ wr_dir_args.force_btgt = ibtop;
-+ err = au_wr_dir(dentry, /*src_dentry*/NULL, &wr_dir_args);
-+ if (unlikely(err < 0))
-+ goto out;
-+ a->btgt = err;
-+ if (err != btop)
-+ au_fset_icpup(a->flags, DID_CPUP);
++ d = a->dst_dentry;
++ SiMustAnyLock(d->d_sb);
+
+ err = 0;
-+ a->pin_flags = AuPin_MNT_WRITE;
-+ parent = NULL;
-+ if (!IS_ROOT(dentry)) {
-+ au_fset_pin(a->pin_flags, DI_LOCKED);
-+ parent = dget_parent(dentry);
-+ di_write_lock_parent(parent);
-+ }
-+
-+ err = au_pin(&a->pin, dentry, a->btgt, a->udba, a->pin_flags);
-+ if (unlikely(err))
-+ goto out_parent;
++ if (au_ftest_ren(a->auren_flags, ISDIR_DST) && a->dst_inode) {
++ rdhash = au_sbi(d->d_sb)->si_rdhash;
++ if (!rdhash)
++ rdhash = au_rdhash_est(au_dir_size(/*file*/NULL, d));
++ err = au_nhash_alloc(&a->whlist, rdhash, GFP_NOFS);
++ if (unlikely(err))
++ goto out;
+
-+ sz = -1;
-+ a->h_path.dentry = au_h_dptr(dentry, btop);
-+ a->h_inode = d_inode(a->h_path.dentry);
-+ if (ia && (ia->ia_valid & ATTR_SIZE)) {
-+ inode_lock_shared_nested(a->h_inode, AuLsc_I_CHILD);
-+ if (ia->ia_size < i_size_read(a->h_inode))
-+ sz = ia->ia_size;
-+ inode_unlock_shared(a->h_inode);
++ if (!a->exchange) {
++ au_set_dbtop(d, a->dst_btop);
++ err = may_rename_dstdir(d, &a->whlist);
++ au_set_dbtop(d, a->btgt);
++ } else
++ err = may_rename_srcdir(a);
+ }
++ a->dst_h_dentry = au_h_dptr(d, au_dbtop(d));
++ if (unlikely(err))
++ goto out;
+
-+ hi_wh = NULL;
-+ if (au_ftest_icpup(a->flags, DID_CPUP) && d_unlinked(dentry)) {
-+ hi_wh = au_hi_wh(inode, a->btgt);
-+ if (!hi_wh) {
-+ struct au_cp_generic cpg = {
-+ .dentry = dentry,
-+ .bdst = a->btgt,
-+ .bsrc = -1,
-+ .len = sz,
-+ .pin = &a->pin
-+ };
-+ err = au_sio_cpup_wh(&cpg, /*file*/NULL);
-+ if (unlikely(err))
-+ goto out_unlock;
-+ hi_wh = au_hi_wh(inode, a->btgt);
-+ /* todo: revalidate hi_wh? */
++ d = a->src_dentry;
++ a->src_h_dentry = au_h_dptr(d, au_dbtop(d));
++ if (au_ftest_ren(a->auren_flags, ISDIR_SRC)) {
++ err = may_rename_srcdir(a);
++ if (unlikely(err)) {
++ au_nhash_wh_free(&a->whlist);
++ a->whlist.nh_num = 0;
+ }
+ }
-+
-+ if (parent) {
-+ au_pin_set_parent_lflag(&a->pin, /*lflag*/0);
-+ di_downgrade_lock(parent, AuLock_IR);
-+ dput(parent);
-+ parent = NULL;
-+ }
-+ if (!au_ftest_icpup(a->flags, DID_CPUP))
-+ goto out; /* success */
-+
-+ if (!d_unhashed(dentry)) {
-+ struct au_cp_generic cpg = {
-+ .dentry = dentry,
-+ .bdst = a->btgt,
-+ .bsrc = btop,
-+ .len = sz,
-+ .pin = &a->pin,
-+ .flags = AuCpup_DTIME | AuCpup_HOPEN
-+ };
-+ err = au_sio_cpup_simple(&cpg);
-+ if (!err)
-+ a->h_path.dentry = au_h_dptr(dentry, a->btgt);
-+ } else if (!hi_wh)
-+ a->h_path.dentry = au_h_dptr(dentry, a->btgt);
-+ else
-+ a->h_path.dentry = hi_wh; /* do not dget here */
-+
-+out_unlock:
-+ a->h_inode = d_inode(a->h_path.dentry);
-+ if (!err)
-+ goto out; /* success */
-+ au_unpin(&a->pin);
-+out_parent:
-+ if (parent) {
-+ di_write_unlock(parent);
-+ dput(parent);
-+ }
+out:
-+ if (!err)
-+ inode_lock_nested(a->h_inode, AuLsc_I_CHILD);
+ return err;
+}
+
-+static int aufs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
-+ struct iattr *ia)
++/* ---------------------------------------------------------------------- */
++
++/*
++ * simple tests for rename.
++ * following the checks in vfs, plus the parent-child relationship.
++ */
++static int au_may_ren(struct au_ren_args *a)
+{
-+ int err;
-+ struct inode *inode, *delegated;
-+ struct super_block *sb;
-+ struct file *file;
-+ struct au_icpup_args *a;
-+ struct mnt_idmap *h_idmap;
++ int err, isdir;
++ struct inode *h_inode;
+
-+ inode = d_inode(dentry);
-+ IMustLock(inode);
++ if (a->src_btop == a->btgt) {
++ err = au_may_del(a->src_dentry, a->btgt, a->src_h_parent,
++ au_ftest_ren(a->auren_flags, ISDIR_SRC));
++ if (unlikely(err))
++ goto out;
++ err = -EINVAL;
++ if (unlikely(a->src_h_dentry == a->h_trap))
++ goto out;
++ }
+
-+ err = setattr_prepare(idmap, dentry, ia);
-+ if (unlikely(err))
++ err = 0;
++ if (a->dst_btop != a->btgt)
+ goto out;
+
-+ err = -ENOMEM;
-+ a = kzalloc(sizeof(*a), GFP_NOFS);
-+ if (unlikely(!a))
++ err = -ENOTEMPTY;
++ if (unlikely(a->dst_h_dentry == a->h_trap))
+ goto out;
+
-+ if (ia->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID))
-+ ia->ia_valid &= ~ATTR_MODE;
-+
-+ file = NULL;
-+ sb = dentry->d_sb;
-+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
-+ if (unlikely(err))
-+ goto out_kfree;
-+
-+ if (ia->ia_valid & ATTR_FILE) {
-+ /* currently ftruncate(2) only */
-+ AuDebugOn(!d_is_reg(dentry));
-+ file = ia->ia_file;
-+ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1,
-+ /*fi_lsc*/0);
-+ if (unlikely(err))
-+ goto out_si;
-+ ia->ia_file = au_hf_top(file);
-+ a->udba = AuOpt_UDBA_NONE;
++ err = -EIO;
++ isdir = !!au_ftest_ren(a->auren_flags, ISDIR_DST);
++ if (d_really_is_negative(a->dst_dentry)) {
++ if (d_is_negative(a->dst_h_dentry))
++ err = au_may_add(a->dst_dentry, a->btgt,
++ a->dst_h_parent, isdir);
+ } else {
-+ /* fchmod() doesn't pass ia_file */
-+ a->udba = au_opt_udba(sb);
-+ di_write_lock_child(dentry);
-+ /* no d_unlinked(), to set UDBA_NONE for root */
-+ if (d_unhashed(dentry))
-+ a->udba = AuOpt_UDBA_NONE;
-+ if (a->udba != AuOpt_UDBA_NONE) {
-+ AuDebugOn(IS_ROOT(dentry));
-+ err = au_reval_for_attr(dentry, au_sigen(sb));
-+ if (unlikely(err))
-+ goto out_dentry;
-+ }
++ if (unlikely(d_is_negative(a->dst_h_dentry)))
++ goto out;
++ h_inode = d_inode(a->dst_h_dentry);
++ if (h_inode->i_nlink)
++ err = au_may_del(a->dst_dentry, a->btgt,
++ a->dst_h_parent, isdir);
+ }
+
-+ err = au_pin_and_icpup(dentry, ia, a);
-+ if (unlikely(err < 0))
-+ goto out_dentry;
-+ if (au_ftest_icpup(a->flags, DID_CPUP)) {
-+ ia->ia_file = NULL;
-+ ia->ia_valid &= ~ATTR_FILE;
-+ }
++out:
++ if (unlikely(err == -ENOENT || err == -EEXIST))
++ err = -EIO;
++ AuTraceErr(err);
++ return err;
++}
+
-+ a->h_path.mnt = au_sbr_mnt(sb, a->btgt);
-+ if ((ia->ia_valid & (ATTR_MODE | ATTR_CTIME))
-+ == (ATTR_MODE | ATTR_CTIME)) {
-+ err = security_path_chmod(&a->h_path, ia->ia_mode);
-+ if (unlikely(err))
-+ goto out_unlock;
-+ } else if ((ia->ia_valid & (ATTR_UID | ATTR_GID))
-+ && (ia->ia_valid & ATTR_CTIME)) {
-+ err = security_path_chown(&a->h_path, ia->ia_uid, ia->ia_gid);
-+ if (unlikely(err))
-+ goto out_unlock;
-+ }
++/* ---------------------------------------------------------------------- */
+
-+ if (ia->ia_valid & ATTR_SIZE) {
-+ struct file *f;
++/*
++ * locking order
++ * (VFS)
++ * - src_dir and dir by lock_rename()
++ * - inode if exists
++ * (aufs)
++ * - lock all
++ * + src_dentry and dentry by aufs_read_and_write_lock2() which calls,
++ * + si_read_lock
++ * + di_write_lock2_child()
++ * + di_write_lock_child()
++ * + ii_write_lock_child()
++ * + di_write_lock_child2()
++ * + ii_write_lock_child2()
++ * + src_parent and parent
++ * + di_write_lock_parent()
++ * + ii_write_lock_parent()
++ * + di_write_lock_parent2()
++ * + ii_write_lock_parent2()
++ * + lower src_dir and dir by vfsub_lock_rename()
++ * + verify the every relationships between child and parent. if any
++ * of them failed, unlock all and return -EBUSY.
++ */
++static void au_ren_unlock(struct au_ren_args *a)
++{
++ vfsub_unlock_rename(a->src_h_parent, a->src_hdir,
++ a->dst_h_parent, a->dst_hdir);
++ if (au_ftest_ren(a->auren_flags, DIRREN)
++ && a->h_root)
++ au_hn_inode_unlock(a->h_root);
++ if (au_ftest_ren(a->auren_flags, MNT_WRITE))
++ vfsub_mnt_drop_write(au_br_mnt(a->br));
++}
+
-+ if (ia->ia_size < i_size_read(inode))
-+ /* unmap only */
-+ truncate_setsize(inode, ia->ia_size);
++static int au_ren_lock(struct au_ren_args *a)
++{
++ int err;
++ unsigned int udba;
+
-+ f = NULL;
-+ if (ia->ia_valid & ATTR_FILE)
-+ f = ia->ia_file;
-+ inode_unlock(a->h_inode);
-+ err = vfsub_trunc(&a->h_path, ia->ia_size, ia->ia_valid, f);
-+ inode_lock_nested(a->h_inode, AuLsc_I_CHILD);
-+ } else {
-+ delegated = NULL;
-+ while (1) {
-+ err = vfsub_notify_change(&a->h_path, ia, &delegated);
-+ if (delegated) {
-+ err = break_deleg_wait(&delegated);
-+ if (!err)
-+ continue;
-+ }
-+ break;
-+ }
-+ }
-+ /*
-+ * regardless aufs 'acl' option setting.
-+ * why don't all acl-aware fs call this func from their ->setattr()?
-+ */
-+ if (!err && (ia->ia_valid & ATTR_MODE)) {
-+ h_idmap = mnt_idmap(a->h_path.mnt);
-+ err = vfsub_acl_chmod(h_idmap, a->h_path.dentry, ia->ia_mode);
++ err = 0;
++ a->src_h_parent = au_h_dptr(a->src_parent, a->btgt);
++ a->src_hdir = au_hi(a->src_dir, a->btgt);
++ a->dst_h_parent = au_h_dptr(a->dst_parent, a->btgt);
++ a->dst_hdir = au_hi(a->dst_dir, a->btgt);
++
++ err = vfsub_mnt_want_write(au_br_mnt(a->br));
++ if (unlikely(err))
++ goto out;
++ au_fset_ren(a->auren_flags, MNT_WRITE);
++ if (au_ftest_ren(a->auren_flags, DIRREN)) {
++ struct dentry *root;
++ struct inode *dir;
++
++ /*
++ * sbinfo is already locked, so this ii_read_lock is
++ * unnecessary. but our debugging feature checks it.
++ */
++ root = a->src_inode->i_sb->s_root;
++ if (root != a->src_parent && root != a->dst_parent) {
++ dir = d_inode(root);
++ ii_read_lock_parent3(dir);
++ a->h_root = au_hi(dir, a->btgt);
++ ii_read_unlock(dir);
++ au_hn_inode_lock_nested(a->h_root, AuLsc_I_PARENT3);
++ }
+ }
++ a->h_trap = vfsub_lock_rename(a->src_h_parent, a->src_hdir,
++ a->dst_h_parent, a->dst_hdir);
++ udba = au_opt_udba(a->src_dentry->d_sb);
++ if (unlikely(a->src_hdir->hi_inode != d_inode(a->src_h_parent)
++ || a->dst_hdir->hi_inode != d_inode(a->dst_h_parent)))
++ err = au_busy_or_stale();
++ if (!err && au_dbtop(a->src_dentry) == a->btgt)
++ err = au_h_verify(a->src_h_dentry, udba,
++ d_inode(a->src_h_parent), a->src_h_parent,
++ a->br);
++ if (!err && au_dbtop(a->dst_dentry) == a->btgt)
++ err = au_h_verify(a->dst_h_dentry, udba,
++ d_inode(a->dst_h_parent), a->dst_h_parent,
++ a->br);
+ if (!err)
-+ au_cpup_attr_changeable(inode);
++ goto out; /* success */
++
++ err = au_busy_or_stale();
++ au_ren_unlock(a);
+
-+out_unlock:
-+ inode_unlock(a->h_inode);
-+ au_unpin(&a->pin);
-+ if (unlikely(err))
-+ au_update_dbtop(dentry);
-+out_dentry:
-+ di_write_unlock(dentry);
-+ if (file) {
-+ fi_write_unlock(file);
-+ ia->ia_file = file;
-+ ia->ia_valid |= ATTR_FILE;
-+ }
-+out_si:
-+ si_read_unlock(sb);
-+out_kfree:
-+ au_kfree_rcu(a);
+out:
-+ AuTraceErr(err);
+ return err;
+}
+
-+#if IS_ENABLED(CONFIG_AUFS_XATTR) || IS_ENABLED(CONFIG_FS_POSIX_ACL)
-+static int au_h_path_to_set_attr(struct dentry *dentry,
-+ struct au_icpup_args *a, struct path *h_path)
++/* ---------------------------------------------------------------------- */
++
++static void au_ren_refresh_dir(struct au_ren_args *a)
+{
-+ int err;
-+ struct super_block *sb;
++ struct inode *dir;
+
-+ sb = dentry->d_sb;
-+ a->udba = au_opt_udba(sb);
-+ /* no d_unlinked(), to set UDBA_NONE for root */
-+ if (d_unhashed(dentry))
-+ a->udba = AuOpt_UDBA_NONE;
-+ if (a->udba != AuOpt_UDBA_NONE) {
-+ AuDebugOn(IS_ROOT(dentry));
-+ err = au_reval_for_attr(dentry, au_sigen(sb));
-+ if (unlikely(err))
-+ goto out;
++ dir = a->dst_dir;
++ inode_inc_iversion(dir);
++ if (au_ftest_ren(a->auren_flags, ISDIR_SRC)) {
++ /* is this updating defined in POSIX? */
++ au_cpup_attr_timesizes(a->src_inode);
++ au_cpup_attr_nlink(dir, /*force*/1);
+ }
-+ err = au_pin_and_icpup(dentry, /*ia*/NULL, a);
-+ if (unlikely(err < 0))
-+ goto out;
++ au_dir_ts(dir, a->btgt);
+
-+ h_path->dentry = a->h_path.dentry;
-+ h_path->mnt = au_sbr_mnt(sb, a->btgt);
++ if (a->exchange) {
++ dir = a->src_dir;
++ inode_inc_iversion(dir);
++ if (au_ftest_ren(a->auren_flags, ISDIR_DST)) {
++ /* is this updating defined in POSIX? */
++ au_cpup_attr_timesizes(a->dst_inode);
++ au_cpup_attr_nlink(dir, /*force*/1);
++ }
++ au_dir_ts(dir, a->btgt);
++ }
+
-+out:
-+ return err;
++ if (au_ftest_ren(a->auren_flags, ISSAMEDIR))
++ return;
++
++ dir = a->src_dir;
++ inode_inc_iversion(dir);
++ if (au_ftest_ren(a->auren_flags, ISDIR_SRC))
++ au_cpup_attr_nlink(dir, /*force*/1);
++ au_dir_ts(dir, a->btgt);
+}
+
-+ssize_t au_sxattr(struct dentry *dentry, struct inode *inode,
-+ struct au_sxattr *arg)
++static void au_ren_refresh(struct au_ren_args *a)
+{
-+ int err;
-+ struct path h_path;
++ aufs_bindex_t bbot, bindex;
++ struct dentry *d, *h_d;
++ struct inode *i, *h_i;
+ struct super_block *sb;
-+ struct au_icpup_args *a;
-+ struct inode *h_inode;
-+ struct mnt_idmap *h_idmap;
-+
-+ IMustLock(inode);
+
-+ err = -ENOMEM;
-+ a = kzalloc(sizeof(*a), GFP_NOFS);
-+ if (unlikely(!a))
-+ goto out;
++ d = a->dst_dentry;
++ d_drop(d);
++ if (a->h_dst)
++ /* already dget-ed by au_ren_or_cpup() */
++ au_set_h_dptr(d, a->btgt, a->h_dst);
+
-+ sb = dentry->d_sb;
-+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
-+ if (unlikely(err))
-+ goto out_kfree;
++ i = a->dst_inode;
++ if (i) {
++ if (!a->exchange) {
++ if (!au_ftest_ren(a->auren_flags, ISDIR_DST))
++ vfsub_drop_nlink(i);
++ else {
++ vfsub_dead_dir(i);
++ au_cpup_attr_timesizes(i);
++ }
++ au_update_dbrange(d, /*do_put_zero*/1);
++ } else
++ au_cpup_attr_nlink(i, /*force*/1);
++ } else {
++ bbot = a->btgt;
++ for (bindex = au_dbtop(d); bindex < bbot; bindex++)
++ au_set_h_dptr(d, bindex, NULL);
++ bbot = au_dbbot(d);
++ for (bindex = a->btgt + 1; bindex <= bbot; bindex++)
++ au_set_h_dptr(d, bindex, NULL);
++ au_update_dbrange(d, /*do_put_zero*/0);
++ }
+
-+ h_path.dentry = NULL; /* silence gcc */
-+ di_write_lock_child(dentry);
-+ err = au_h_path_to_set_attr(dentry, a, &h_path);
-+ if (unlikely(err))
-+ goto out_di;
-+ h_idmap = mnt_idmap(h_path.mnt);
++ if (a->exchange
++ || au_ftest_ren(a->auren_flags, DIRREN)) {
++ d_drop(a->src_dentry);
++ if (au_ftest_ren(a->auren_flags, DIRREN))
++ au_set_dbwh(a->src_dentry, -1);
++ return;
++ }
+
-+ inode_unlock(a->h_inode);
-+ switch (arg->type) {
-+ case AU_XATTR_SET:
-+ AuDebugOn(d_is_negative(h_path.dentry));
-+ err = vfsub_setxattr(h_idmap, h_path.dentry,
-+ arg->u.set.name, arg->u.set.value,
-+ arg->u.set.size, arg->u.set.flags);
-+ break;
-+ case AU_ACL_SET:
-+ err = -EOPNOTSUPP;
-+ h_inode = d_inode(h_path.dentry);
-+ if (h_inode->i_op->set_acl) {
-+ /* this will call posix_acl_update_mode */
-+ err = h_inode->i_op->set_acl(h_idmap, h_path.dentry,
-+ arg->u.acl_set.acl,
-+ arg->u.acl_set.type);
-+ }
-+ break;
++ d = a->src_dentry;
++ au_set_dbwh(d, -1);
++ bbot = au_dbbot(d);
++ for (bindex = a->btgt + 1; bindex <= bbot; bindex++) {
++ h_d = au_h_dptr(d, bindex);
++ if (h_d)
++ au_set_h_dptr(d, bindex, NULL);
+ }
-+ if (!err)
-+ au_cpup_attr_timesizes(inode);
++ au_set_dbbot(d, a->btgt);
+
-+ au_unpin(&a->pin);
-+ if (unlikely(err))
-+ au_update_dbtop(dentry);
++ sb = d->d_sb;
++ i = a->src_inode;
++ if (au_opt_test(au_mntflags(sb), PLINK) && au_plink_test(i))
++ return; /* success */
+
-+out_di:
-+ di_write_unlock(dentry);
-+ si_read_unlock(sb);
-+out_kfree:
-+ au_kfree_rcu(a);
-+out:
-+ AuTraceErr(err);
-+ return err;
++ bbot = au_ibbot(i);
++ for (bindex = a->btgt + 1; bindex <= bbot; bindex++) {
++ h_i = au_h_iptr(i, bindex);
++ if (h_i) {
++ au_xino_write(sb, bindex, h_i->i_ino, /*ino*/0);
++ /* ignore this error */
++ au_set_h_iptr(i, bindex, NULL, 0);
++ }
++ }
++ au_set_ibbot(i, a->btgt);
+}
-+#endif
+
-+static void au_refresh_iattr(struct inode *inode, struct kstat *st,
-+ unsigned int nlink)
++/* ---------------------------------------------------------------------- */
++
++/* mainly for link(2) and rename(2) */
++int au_wbr(struct dentry *dentry, aufs_bindex_t btgt)
+{
-+ unsigned int n;
++ aufs_bindex_t bdiropq, bwh;
++ struct dentry *parent;
++ struct au_branch *br;
+
-+ inode->i_mode = st->mode;
-+ /* don't i_[ug]id_write() here */
-+ inode->i_uid = st->uid;
-+ inode->i_gid = st->gid;
-+ inode->i_atime = st->atime;
-+ inode->i_mtime = st->mtime;
-+ inode_set_ctime_to_ts(inode, st->ctime);
++ parent = dentry->d_parent;
++ IMustLock(d_inode(parent)); /* dir is locked */
+
-+ au_cpup_attr_nlink(inode, /*force*/0);
-+ if (S_ISDIR(inode->i_mode)) {
-+ n = inode->i_nlink;
-+ n -= nlink;
-+ n += st->nlink;
-+ smp_mb(); /* for i_nlink */
-+ /* 0 can happen */
-+ set_nlink(inode, n);
-+ }
++ bdiropq = au_dbdiropq(parent);
++ bwh = au_dbwh(dentry);
++ br = au_sbr(dentry->d_sb, btgt);
++ if (au_br_rdonly(br)
++ || (0 <= bdiropq && bdiropq < btgt)
++ || (0 <= bwh && bwh < btgt))
++ btgt = -1;
+
-+ spin_lock(&inode->i_lock);
-+ inode->i_blocks = st->blocks;
-+ i_size_write(inode, st->size);
-+ spin_unlock(&inode->i_lock);
++ AuDbg("btgt %d\n", btgt);
++ return btgt;
+}
+
-+/*
-+ * common routine for aufs_getattr() and au_getxattr().
-+ * returns zero or negative (an error).
-+ * @dentry will be read-locked in success.
-+ */
-+int au_h_path_getattr(struct dentry *dentry, struct inode *inode, int force,
-+ struct path *h_path, int locked)
++/* sets src_btop, dst_btop and btgt */
++static int au_ren_wbr(struct au_ren_args *a)
+{
+ int err;
-+ unsigned int mnt_flags, sigen;
-+ unsigned char udba_none;
-+ aufs_bindex_t bindex;
-+ struct super_block *sb, *h_sb;
-+
-+ h_path->mnt = NULL;
-+ h_path->dentry = NULL;
-+
-+ err = 0;
-+ sb = dentry->d_sb;
-+ mnt_flags = au_mntflags(sb);
-+ udba_none = !!au_opt_test(mnt_flags, UDBA_NONE);
++ struct au_wr_dir_args wr_dir_args = {
++ /* .force_btgt = -1, */
++ .flags = AuWrDir_ADD_ENTRY
++ };
+
-+ if (unlikely(locked))
-+ goto body; /* skip locking dinfo */
++ a->src_btop = au_dbtop(a->src_dentry);
++ a->dst_btop = au_dbtop(a->dst_dentry);
++ if (au_ftest_ren(a->auren_flags, ISDIR_SRC)
++ || au_ftest_ren(a->auren_flags, ISDIR_DST))
++ au_fset_wrdir(wr_dir_args.flags, ISDIR);
++ wr_dir_args.force_btgt = a->src_btop;
++ if (a->dst_inode && a->dst_btop < a->src_btop)
++ wr_dir_args.force_btgt = a->dst_btop;
++ wr_dir_args.force_btgt = au_wbr(a->dst_dentry, wr_dir_args.force_btgt);
++ err = au_wr_dir(a->dst_dentry, a->src_dentry, &wr_dir_args);
++ a->btgt = err;
++ if (a->exchange)
++ au_update_dbtop(a->dst_dentry);
+
-+ /* support fstat(2) */
-+ if (!d_unlinked(dentry) && !udba_none) {
-+ sigen = au_sigen(sb);
-+ err = au_digen_test(dentry, sigen);
-+ if (!err) {
-+ di_read_lock_child(dentry, AuLock_IR);
-+ err = au_dbrange_test(dentry);
-+ if (unlikely(err)) {
-+ di_read_unlock(dentry, AuLock_IR);
-+ goto out;
-+ }
-+ } else {
-+ AuDebugOn(IS_ROOT(dentry));
-+ di_write_lock_child(dentry);
-+ err = au_dbrange_test(dentry);
-+ if (!err)
-+ err = au_reval_for_attr(dentry, sigen);
-+ if (!err)
-+ di_downgrade_lock(dentry, AuLock_IR);
-+ else {
-+ di_write_unlock(dentry);
-+ goto out;
-+ }
-+ }
-+ } else
-+ di_read_lock_child(dentry, AuLock_IR);
++ return err;
++}
+
-+body:
-+ if (!inode) {
-+ inode = d_inode(dentry);
-+ if (unlikely(!inode))
-+ goto out;
++static void au_ren_dt(struct au_ren_args *a)
++{
++ a->h_path.dentry = a->src_h_parent;
++ au_dtime_store(a->src_dt + AuPARENT, a->src_parent, &a->h_path);
++ if (!au_ftest_ren(a->auren_flags, ISSAMEDIR)) {
++ a->h_path.dentry = a->dst_h_parent;
++ au_dtime_store(a->dst_dt + AuPARENT, a->dst_parent, &a->h_path);
+ }
-+ bindex = au_ibtop(inode);
-+ h_path->mnt = au_sbr_mnt(sb, bindex);
-+ h_sb = h_path->mnt->mnt_sb;
-+ if (!force
-+ && !au_test_fs_bad_iattr(h_sb)
-+ && udba_none)
-+ goto out; /* success */
+
-+ if (au_dbtop(dentry) == bindex)
-+ h_path->dentry = au_h_dptr(dentry, bindex);
-+ else if (au_opt_test(mnt_flags, PLINK) && au_plink_test(inode)) {
-+ h_path->dentry = au_plink_lkup(inode, bindex);
-+ if (IS_ERR(h_path->dentry))
-+ /* pretending success */
-+ h_path->dentry = NULL;
-+ else
-+ dput(h_path->dentry);
-+ }
++ au_fclr_ren(a->auren_flags, DT_DSTDIR);
++ if (!au_ftest_ren(a->auren_flags, ISDIR_SRC)
++ && !a->exchange)
++ return;
+
-+out:
-+ return err;
++ a->h_path.dentry = a->src_h_dentry;
++ au_dtime_store(a->src_dt + AuCHILD, a->src_dentry, &a->h_path);
++ if (d_is_positive(a->dst_h_dentry)) {
++ au_fset_ren(a->auren_flags, DT_DSTDIR);
++ a->h_path.dentry = a->dst_h_dentry;
++ au_dtime_store(a->dst_dt + AuCHILD, a->dst_dentry, &a->h_path);
++ }
+}
+
-+static int aufs_getattr(struct mnt_idmap *idmap, const struct path *path,
-+ struct kstat *st, u32 request, unsigned int query)
++static void au_ren_rev_dt(int err, struct au_ren_args *a)
+{
-+ int err;
-+ unsigned char positive;
-+ struct path h_path;
-+ struct dentry *dentry;
-+ struct inode *inode;
-+ struct super_block *sb;
++ struct dentry *h_d;
++ struct inode *h_inode;
+
-+ dentry = path->dentry;
-+ inode = d_inode(dentry);
-+ sb = dentry->d_sb;
-+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
-+ if (unlikely(err))
-+ goto out;
-+ err = au_h_path_getattr(dentry, /*inode*/NULL, /*force*/0, &h_path,
-+ /*locked*/0);
-+ if (unlikely(err))
-+ goto out_si;
-+ if (unlikely(!h_path.dentry))
-+ /* illegally overlapped or something */
-+ goto out_fill; /* pretending success */
++ au_dtime_revert(a->src_dt + AuPARENT);
++ if (!au_ftest_ren(a->auren_flags, ISSAMEDIR))
++ au_dtime_revert(a->dst_dt + AuPARENT);
+
-+ positive = d_is_positive(h_path.dentry);
-+ if (positive)
-+ /* no vfsub version */
-+ err = vfs_getattr(&h_path, st, request, query);
-+ if (!err) {
-+ if (positive)
-+ au_refresh_iattr(inode, st,
-+ d_inode(h_path.dentry)->i_nlink);
-+ goto out_fill; /* success */
-+ }
-+ AuTraceErr(err);
-+ goto out_di;
++ if (au_ftest_ren(a->auren_flags, ISDIR_SRC) && err != -EIO) {
++ h_d = a->src_dt[AuCHILD].dt_h_path.dentry;
++ h_inode = d_inode(h_d);
++ inode_lock_nested(h_inode, AuLsc_I_CHILD);
++ au_dtime_revert(a->src_dt + AuCHILD);
++ inode_unlock(h_inode);
+
-+out_fill:
-+ generic_fillattr(idmap, request, inode, st);
-+out_di:
-+ di_read_unlock(dentry, AuLock_IR);
-+out_si:
-+ si_read_unlock(sb);
-+out:
-+ AuTraceErr(err);
-+ return err;
++ if (au_ftest_ren(a->auren_flags, DT_DSTDIR)) {
++ h_d = a->dst_dt[AuCHILD].dt_h_path.dentry;
++ h_inode = d_inode(h_d);
++ inode_lock_nested(h_inode, AuLsc_I_CHILD);
++ au_dtime_revert(a->dst_dt + AuCHILD);
++ inode_unlock(h_inode);
++ }
++ }
+}
+
+/* ---------------------------------------------------------------------- */
+
-+static const char *aufs_get_link(struct dentry *dentry, struct inode *inode,
-+ struct delayed_call *done)
++int aufs_rename(struct mnt_idmap *idmap,
++ struct inode *_src_dir, struct dentry *_src_dentry,
++ struct inode *_dst_dir, struct dentry *_dst_dentry,
++ unsigned int _flags)
+{
-+ const char *ret;
-+ struct dentry *h_dentry;
-+ struct inode *h_inode;
-+ int err;
-+ aufs_bindex_t bindex;
++ int err, lock_flags;
++ void *rev;
++ /* reduce stack space */
++ struct au_ren_args *a;
++ struct au_pin pin;
+
-+ ret = NULL; /* suppress a warning */
-+ err = -ECHILD;
-+ if (!dentry)
++ AuDbg("%pd, %pd, 0x%x\n", _src_dentry, _dst_dentry, _flags);
++ IMustLock(_src_dir);
++ IMustLock(_dst_dir);
++
++ err = -EINVAL;
++ if (unlikely(_flags & RENAME_WHITEOUT))
+ goto out;
+
-+ err = aufs_read_lock(dentry, AuLock_IR | AuLock_GEN);
-+ if (unlikely(err))
++ err = -ENOMEM;
++ BUILD_BUG_ON(sizeof(*a) > PAGE_SIZE);
++ a = kzalloc(sizeof(*a), GFP_NOFS);
++ if (unlikely(!a))
+ goto out;
+
-+ err = au_d_hashed_positive(dentry);
++ a->flags = _flags;
++ BUILD_BUG_ON(sizeof(a->exchange) == sizeof(u8)
++ && RENAME_EXCHANGE > U8_MAX);
++ a->exchange = _flags & RENAME_EXCHANGE;
++ a->src_dir = _src_dir;
++ a->src_dentry = _src_dentry;
++ a->src_inode = NULL;
++ if (d_really_is_positive(a->src_dentry))
++ a->src_inode = d_inode(a->src_dentry);
++ a->src_parent = a->src_dentry->d_parent; /* dir inode is locked */
++ a->dst_dir = _dst_dir;
++ a->dst_dentry = _dst_dentry;
++ a->dst_inode = NULL;
++ if (d_really_is_positive(a->dst_dentry))
++ a->dst_inode = d_inode(a->dst_dentry);
++ a->dst_parent = a->dst_dentry->d_parent; /* dir inode is locked */
++ if (a->dst_inode) {
++ /*
++ * if EXCHANGE && src is non-dir && dst is dir,
++ * dst is not locked.
++ */
++ /* IMustLock(a->dst_inode); */
++ au_igrab(a->dst_inode);
++ }
++
++ err = -ENOTDIR;
++ lock_flags = AuLock_FLUSH | AuLock_NOPLM | AuLock_GEN;
++ if (d_is_dir(a->src_dentry)) {
++ au_fset_ren(a->auren_flags, ISDIR_SRC);
++ if (unlikely(!a->exchange
++ && d_really_is_positive(a->dst_dentry)
++ && !d_is_dir(a->dst_dentry)))
++ goto out_free;
++ lock_flags |= AuLock_DIRS;
++ }
++ if (a->dst_inode && d_is_dir(a->dst_dentry)) {
++ au_fset_ren(a->auren_flags, ISDIR_DST);
++ if (unlikely(!a->exchange
++ && d_really_is_positive(a->src_dentry)
++ && !d_is_dir(a->src_dentry)))
++ goto out_free;
++ lock_flags |= AuLock_DIRS;
++ }
++ err = aufs_read_and_write_lock2(a->dst_dentry, a->src_dentry,
++ lock_flags);
++ if (unlikely(err))
++ goto out_free;
++
++ err = au_d_hashed_positive(a->src_dentry);
+ if (unlikely(err))
+ goto out_unlock;
++ err = -ENOENT;
++ if (a->dst_inode) {
++ /*
++ * If it is a dir, VFS unhash it before this
++ * function. It means we cannot rely upon d_unhashed().
++ */
++ if (unlikely(!a->dst_inode->i_nlink))
++ goto out_unlock;
++ if (!au_ftest_ren(a->auren_flags, ISDIR_DST)) {
++ err = au_d_hashed_positive(a->dst_dentry);
++ if (unlikely(err && !a->exchange))
++ goto out_unlock;
++ } else if (unlikely(IS_DEADDIR(a->dst_inode)))
++ goto out_unlock;
++ } else if (unlikely(d_unhashed(a->dst_dentry)))
++ goto out_unlock;
+
++ /*
++ * is it possible?
++ * yes, it happened (in linux-3.3-rcN) but I don't know why.
++ * there may exist a problem somewhere else.
++ */
+ err = -EINVAL;
-+ inode = d_inode(dentry);
-+ bindex = au_ibtop(inode);
-+ h_inode = au_h_iptr(inode, bindex);
-+ if (unlikely(!h_inode->i_op->get_link))
++ if (unlikely(d_inode(a->dst_parent) == d_inode(a->src_dentry)))
+ goto out_unlock;
+
-+ err = -EBUSY;
-+ h_dentry = NULL;
-+ if (au_dbtop(dentry) <= bindex) {
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (h_dentry)
-+ dget(h_dentry);
-+ }
-+ if (!h_dentry) {
-+ h_dentry = d_find_any_alias(h_inode);
-+ if (IS_ERR(h_dentry)) {
-+ err = PTR_ERR(h_dentry);
-+ goto out_unlock;
-+ }
-+ }
-+ if (unlikely(!h_dentry))
-+ goto out_unlock;
++ au_fset_ren(a->auren_flags, ISSAMEDIR); /* temporary */
++ di_write_lock_parent(a->dst_parent);
+
-+ err = 0;
-+ AuDbg("%ps\n", h_inode->i_op->get_link);
-+ AuDbgDentry(h_dentry);
-+ ret = vfs_get_link(h_dentry, done);
-+ dput(h_dentry);
-+ if (IS_ERR(ret))
-+ err = PTR_ERR(ret);
++ /* which branch we process */
++ err = au_ren_wbr(a);
++ if (unlikely(err < 0))
++ goto out_parent;
++ a->br = au_sbr(a->dst_dentry->d_sb, a->btgt);
++ a->h_path.mnt = au_br_mnt(a->br);
+
-+out_unlock:
-+ aufs_read_unlock(dentry, AuLock_IR);
-+out:
++ /* are they available to be renamed */
++ err = au_ren_may_dir(a);
+ if (unlikely(err))
-+ ret = ERR_PTR(err);
-+ AuTraceErrPtr(ret);
-+ return ret;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int au_is_special(struct inode *inode)
-+{
-+ return (inode->i_mode & (S_IFBLK | S_IFCHR | S_IFIFO | S_IFSOCK));
-+}
-+
-+static int aufs_update_time(struct inode *inode, int flags)
-+{
-+ int err;
-+ aufs_bindex_t bindex;
-+ struct super_block *sb;
-+ struct inode *h_inode;
-+ struct vfsmount *h_mnt;
-+
-+ sb = inode->i_sb;
-+ WARN_ONCE((flags & S_ATIME) && !IS_NOATIME(inode),
-+ "unexpected s_flags 0x%lx", sb->s_flags);
++ goto out_children;
+
-+ /* mmap_sem might be acquired already, cf. aufs_mmap() */
-+ lockdep_off();
-+ si_read_lock(sb, AuLock_FLUSH);
-+ ii_write_lock_child(inode);
++ /* prepare the writable parent dir on the same branch */
++ if (a->dst_btop == a->btgt) {
++ au_fset_ren(a->auren_flags, WHDST);
++ } else {
++ err = au_cpup_dirs(a->dst_dentry, a->btgt);
++ if (unlikely(err))
++ goto out_children;
++ }
+
+ err = 0;
-+ bindex = au_ibtop(inode);
-+ h_inode = au_h_iptr(inode, bindex);
-+ if (!au_test_ro(sb, bindex, inode)) {
-+ h_mnt = au_sbr_mnt(sb, bindex);
-+ err = vfsub_mnt_want_write(h_mnt);
++ if (!a->exchange) {
++ if (a->src_dir != a->dst_dir) {
++ /*
++ * this temporary unlock is safe,
++ * because both dir->i_mutex are locked.
++ */
++ di_write_unlock(a->dst_parent);
++ di_write_lock_parent(a->src_parent);
++ err = au_wr_dir_need_wh(a->src_dentry,
++ au_ftest_ren(a->auren_flags,
++ ISDIR_SRC),
++ &a->btgt);
++ di_write_unlock(a->src_parent);
++ di_write_lock2_parent(a->src_parent, a->dst_parent,
++ /*isdir*/1);
++ au_fclr_ren(a->auren_flags, ISSAMEDIR);
++ } else
++ err = au_wr_dir_need_wh(a->src_dentry,
++ au_ftest_ren(a->auren_flags,
++ ISDIR_SRC),
++ &a->btgt);
++ }
++ if (unlikely(err < 0))
++ goto out_children;
++ if (err)
++ au_fset_ren(a->auren_flags, WHSRC);
++
++ /* cpup src */
++ if (a->src_btop != a->btgt) {
++ err = au_pin(&pin, a->src_dentry, a->btgt,
++ au_opt_udba(a->src_dentry->d_sb),
++ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
+ if (!err) {
-+ err = vfsub_update_time(h_inode, flags);
-+ vfsub_mnt_drop_write(h_mnt);
++ struct au_cp_generic cpg = {
++ .dentry = a->src_dentry,
++ .bdst = a->btgt,
++ .bsrc = a->src_btop,
++ .len = -1,
++ .pin = &pin,
++ .flags = AuCpup_DTIME | AuCpup_HOPEN
++ };
++ AuDebugOn(au_dbtop(a->src_dentry) != a->src_btop);
++ err = au_sio_cpup_simple(&cpg);
++ au_unpin(&pin);
+ }
-+ } else if (au_is_special(h_inode)) {
-+ /*
-+ * Never copy-up here.
-+ * These special files may already be opened and used for
-+ * communicating. If we copied it up, then the communication
-+ * would be corrupted.
-+ */
-+ AuWarn1("timestamps for i%lu are ignored "
-+ "since it is on readonly branch (hi%lu).\n",
-+ inode->i_ino, h_inode->i_ino);
-+ } else if (flags & ~S_ATIME) {
-+ err = -EIO;
-+ AuIOErr1("unexpected flags 0x%x\n", flags);
-+ AuDebugOn(1);
++ if (unlikely(err))
++ goto out_children;
++ a->src_btop = a->btgt;
++ a->src_h_dentry = au_h_dptr(a->src_dentry, a->btgt);
++ if (!a->exchange)
++ au_fset_ren(a->auren_flags, WHSRC);
+ }
+
-+ if (!err)
-+ au_cpup_attr_timesizes(inode);
-+ ii_write_unlock(inode);
-+ si_read_unlock(sb);
-+ lockdep_on();
-+
-+ if (!err && (flags & S_VERSION))
-+ inode_inc_iversion(inode);
-+
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* no getattr version will be set by module.c:aufs_init() */
-+struct inode_operations aufs_iop_nogetattr[AuIop_Last],
-+ aufs_iop[] = {
-+ [AuIop_SYMLINK] = {
-+ .permission = aufs_permission,
-+#ifdef CONFIG_FS_POSIX_ACL
-+ .get_inode_acl = aufs_get_inode_acl,
-+ .get_acl = aufs_get_acl,
-+ .set_acl = aufs_set_acl, /* unsupport for symlink? */
-+#endif
-+
-+ .setattr = aufs_setattr,
-+ .getattr = aufs_getattr,
++ /* cpup dst */
++ if (a->exchange && a->dst_inode
++ && a->dst_btop != a->btgt) {
++ err = au_pin(&pin, a->dst_dentry, a->btgt,
++ au_opt_udba(a->dst_dentry->d_sb),
++ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
++ if (!err) {
++ struct au_cp_generic cpg = {
++ .dentry = a->dst_dentry,
++ .bdst = a->btgt,
++ .bsrc = a->dst_btop,
++ .len = -1,
++ .pin = &pin,
++ .flags = AuCpup_DTIME | AuCpup_HOPEN
++ };
++ err = au_sio_cpup_simple(&cpg);
++ au_unpin(&pin);
++ }
++ if (unlikely(err))
++ goto out_children;
++ a->dst_btop = a->btgt;
++ a->dst_h_dentry = au_h_dptr(a->dst_dentry, a->btgt);
++ }
+
-+#ifdef CONFIG_AUFS_XATTR
-+ .listxattr = aufs_listxattr,
-+#endif
++ /* lock them all */
++ err = au_ren_lock(a);
++ if (unlikely(err))
++ /* leave the copied-up one */
++ goto out_children;
+
-+ .get_link = aufs_get_link
++ if (!a->exchange) {
++ if (!au_opt_test(au_mntflags(a->dst_dir->i_sb), UDBA_NONE))
++ err = au_may_ren(a);
++ else if (unlikely(a->dst_dentry->d_name.len > AUFS_MAX_NAMELEN))
++ err = -ENAMETOOLONG;
++ if (unlikely(err))
++ goto out_hdir;
++ }
+
-+ /* .update_time = aufs_update_time */
-+ },
-+ [AuIop_DIR] = {
-+ .create = aufs_create,
-+ .lookup = aufs_lookup,
-+ .link = aufs_link,
-+ .unlink = aufs_unlink,
-+ .symlink = aufs_symlink,
-+ .mkdir = aufs_mkdir,
-+ .rmdir = aufs_rmdir,
-+ .mknod = aufs_mknod,
-+ .rename = aufs_rename,
++ /* store timestamps to be revertible */
++ au_ren_dt(a);
+
-+ .permission = aufs_permission,
-+#ifdef CONFIG_FS_POSIX_ACL
-+ .get_inode_acl = aufs_get_inode_acl,
-+ .get_acl = aufs_get_acl,
-+ .set_acl = aufs_set_acl,
-+#endif
++ /* store dirren info */
++ if (au_ftest_ren(a->auren_flags, DIRREN)) {
++ err = au_dr_rename(a->src_dentry, a->btgt,
++ &a->dst_dentry->d_name, &rev);
++ AuTraceErr(err);
++ if (unlikely(err))
++ goto out_dt;
++ }
+
-+ .setattr = aufs_setattr,
-+ .getattr = aufs_getattr,
++ /* here we go */
++ err = do_rename(a);
++ if (unlikely(err))
++ goto out_dirren;
+
-+#ifdef CONFIG_AUFS_XATTR
-+ .listxattr = aufs_listxattr,
-+#endif
++ if (au_ftest_ren(a->auren_flags, DIRREN))
++ au_dr_rename_fin(a->src_dentry, a->btgt, rev);
+
-+ .update_time = aufs_update_time,
-+ .atomic_open = aufs_atomic_open,
-+ .tmpfile = aufs_tmpfile
-+ },
-+ [AuIop_OTHER] = {
-+ .permission = aufs_permission,
-+#ifdef CONFIG_FS_POSIX_ACL
-+ .get_inode_acl = aufs_get_inode_acl,
-+ .get_acl = aufs_get_acl,
-+ .set_acl = aufs_set_acl,
-+#endif
++ /* update dir attributes */
++ au_ren_refresh_dir(a);
+
-+ .setattr = aufs_setattr,
-+ .getattr = aufs_getattr,
++ /* dput/iput all lower dentries */
++ au_ren_refresh(a);
+
-+#ifdef CONFIG_AUFS_XATTR
-+ .listxattr = aufs_listxattr,
-+#endif
++ goto out_hdir; /* success */
+
-+ .update_time = aufs_update_time
++out_dirren:
++ if (au_ftest_ren(a->auren_flags, DIRREN))
++ au_dr_rename_rev(a->src_dentry, a->btgt, rev);
++out_dt:
++ au_ren_rev_dt(err, a);
++out_hdir:
++ au_ren_unlock(a);
++out_children:
++ au_nhash_wh_free(&a->whlist);
++ if (err && a->dst_inode && a->dst_btop != a->btgt) {
++ AuDbg("btop %d, btgt %d\n", a->dst_btop, a->btgt);
++ au_set_h_dptr(a->dst_dentry, a->btgt, NULL);
++ au_set_dbtop(a->dst_dentry, a->dst_btop);
+ }
-+};
-diff -urN /usr/share/empty/fs/aufs/i_op_del.c linux/fs/aufs/i_op_del.c
---- /usr/share/empty/fs/aufs/i_op_del.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/i_op_del.c 2023-10-31 09:31:04.199880750 +0100
-@@ -0,0 +1,523 @@
++out_parent:
++ if (!err) {
++ if (d_unhashed(a->src_dentry))
++ au_fset_ren(a->auren_flags, DROPPED_SRC);
++ if (d_unhashed(a->dst_dentry))
++ au_fset_ren(a->auren_flags, DROPPED_DST);
++ if (!a->exchange)
++ d_move(a->src_dentry, a->dst_dentry);
++ else {
++ d_exchange(a->src_dentry, a->dst_dentry);
++ if (au_ftest_ren(a->auren_flags, DROPPED_DST))
++ d_drop(a->dst_dentry);
++ }
++ if (au_ftest_ren(a->auren_flags, DROPPED_SRC))
++ d_drop(a->src_dentry);
++ } else {
++ au_update_dbtop(a->dst_dentry);
++ if (!a->dst_inode)
++ d_drop(a->dst_dentry);
++ }
++ if (au_ftest_ren(a->auren_flags, ISSAMEDIR))
++ di_write_unlock(a->dst_parent);
++ else
++ di_write_unlock2(a->src_parent, a->dst_parent);
++out_unlock:
++ aufs_read_and_write_unlock2(a->dst_dentry, a->src_dentry);
++out_free:
++ iput(a->dst_inode);
++ if (a->thargs)
++ au_whtmp_rmdir_free(a->thargs);
++ au_kfree_rcu(a);
++out:
++ AuTraceErr(err);
++ return err;
++}
+diff --git a/fs/aufs/iinfo.c b/fs/aufs/iinfo.c
+new file mode 100644
+index 00000000000000..0d3a2487643bdc
+--- /dev/null
++++ b/fs/aufs/iinfo.c
+@@ -0,0 +1,286 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2005-2022 Junjiro R. Okajima
+ */
+
+/*
-+ * inode operations (del entry)
++ * inode private data
+ */
+
-+#include <linux/iversion.h>
+#include "aufs.h"
+
-+/*
-+ * decide if a new whiteout for @dentry is necessary or not.
-+ * when it is necessary, prepare the parent dir for the upper branch whose
-+ * branch index is @bcpup for creation. the actual creation of the whiteout will
-+ * be done by caller.
-+ * return value:
-+ * 0: wh is unnecessary
-+ * plus: wh is necessary
-+ * minus: error
-+ */
-+int au_wr_dir_need_wh(struct dentry *dentry, int isdir, aufs_bindex_t *bcpup)
++struct inode *au_h_iptr(struct inode *inode, aufs_bindex_t bindex)
+{
-+ int need_wh, err;
-+ aufs_bindex_t btop;
-+ struct super_block *sb;
-+
-+ sb = dentry->d_sb;
-+ btop = au_dbtop(dentry);
-+ if (*bcpup < 0) {
-+ *bcpup = btop;
-+ if (au_test_ro(sb, btop, d_inode(dentry))) {
-+ err = AuWbrCopyup(au_sbi(sb), dentry);
-+ *bcpup = err;
-+ if (unlikely(err < 0))
-+ goto out;
-+ }
-+ } else
-+ AuDebugOn(btop < *bcpup
-+ || au_test_ro(sb, *bcpup, d_inode(dentry)));
-+ AuDbg("bcpup %d, btop %d\n", *bcpup, btop);
++ struct inode *h_inode;
++ struct au_hinode *hinode;
+
-+ if (*bcpup != btop) {
-+ err = au_cpup_dirs(dentry, *bcpup);
-+ if (unlikely(err))
-+ goto out;
-+ need_wh = 1;
-+ } else {
-+ struct au_dinfo *dinfo, *tmp;
++ IiMustAnyLock(inode);
+
-+ need_wh = -ENOMEM;
-+ dinfo = au_di(dentry);
-+ tmp = au_di_alloc(sb, AuLsc_DI_TMP);
-+ if (tmp) {
-+ au_di_cp(tmp, dinfo);
-+ au_di_swap(tmp, dinfo);
-+ /* returns the number of positive dentries */
-+ need_wh = au_lkup_dentry(dentry, btop + 1,
-+ /* AuLkup_IGNORE_PERM */ 0);
-+ au_di_swap(tmp, dinfo);
-+ au_rw_write_unlock(&tmp->di_rwsem);
-+ au_di_free(tmp);
-+ }
-+ }
-+ AuDbg("need_wh %d\n", need_wh);
-+ err = need_wh;
++ hinode = au_hinode(au_ii(inode), bindex);
++ h_inode = hinode->hi_inode;
++ AuDebugOn(h_inode && atomic_read(&h_inode->i_count) <= 0);
++ return h_inode;
++}
+
-+out:
-+ return err;
++/* todo: hard/soft set? */
++void au_hiput(struct au_hinode *hinode)
++{
++ au_hn_free(hinode);
++ dput(hinode->hi_whdentry);
++ iput(hinode->hi_inode);
+}
+
-+/*
-+ * simple tests for the del-entry operations.
-+ * following the checks in vfs, plus the parent-child relationship.
-+ */
-+int au_may_del(struct dentry *dentry, aufs_bindex_t bindex,
-+ struct dentry *h_parent, int isdir)
++unsigned int au_hi_flags(struct inode *inode, int isdir)
+{
-+ int err;
-+ umode_t h_mode;
-+ struct dentry *h_dentry, *h_latest;
-+ struct inode *h_inode;
-+ struct path h_ppath;
-+ struct super_block *sb;
-+ struct au_branch *br;
-+ struct mnt_idmap *h_idmap;
++ unsigned int flags;
++ const unsigned int mnt_flags = au_mntflags(inode->i_sb);
+
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (d_really_is_positive(dentry)) {
-+ err = -ENOENT;
-+ if (unlikely(d_is_negative(h_dentry)))
-+ goto out;
-+ h_inode = d_inode(h_dentry);
-+ if (unlikely(!h_inode->i_nlink))
-+ goto out;
++ flags = 0;
++ if (au_opt_test(mnt_flags, XINO))
++ au_fset_hi(flags, XINO);
++ if (isdir && au_opt_test(mnt_flags, UDBA_HNOTIFY))
++ au_fset_hi(flags, HNOTIFY);
++ return flags;
++}
+
-+ h_mode = h_inode->i_mode;
-+ if (!isdir) {
-+ err = -EISDIR;
-+ if (unlikely(S_ISDIR(h_mode)))
-+ goto out;
-+ } else if (unlikely(!S_ISDIR(h_mode))) {
-+ err = -ENOTDIR;
-+ goto out;
-+ }
-+ } else {
-+ /* rename(2) case */
-+ err = -EIO;
-+ if (unlikely(d_is_positive(h_dentry)))
-+ goto out;
-+ }
++void au_set_h_iptr(struct inode *inode, aufs_bindex_t bindex,
++ struct inode *h_inode, unsigned int flags)
++{
++ struct au_hinode *hinode;
++ struct inode *hi;
++ struct au_iinfo *iinfo = au_ii(inode);
+
-+ err = -ENOENT;
-+ /* expected parent dir is locked */
-+ if (unlikely(h_parent != h_dentry->d_parent))
-+ goto out;
-+ err = 0;
++ IiMustWriteLock(inode);
+
-+ /*
-+ * rmdir a dir may break the consistency on some filesystem.
-+ * let's try heavy test.
-+ */
-+ err = -EACCES;
-+ sb = dentry->d_sb;
-+ br = au_sbr(sb, bindex);
-+ h_idmap = au_br_idmap(br);
-+ if (unlikely(!au_opt_test(au_mntflags(sb), DIRPERM1)
-+ && au_test_h_perm(h_idmap, d_inode(h_parent),
-+ MAY_EXEC | MAY_WRITE)))
-+ goto out;
++ hinode = au_hinode(iinfo, bindex);
++ hi = hinode->hi_inode;
++ AuDebugOn(h_inode && atomic_read(&h_inode->i_count) <= 0);
+
-+ h_ppath.dentry = h_parent;
-+ h_ppath.mnt = au_br_mnt(br);
-+ h_latest = au_sio_lkup_one(h_idmap, &dentry->d_name, &h_ppath);
-+ err = -EIO;
-+ if (IS_ERR(h_latest))
-+ goto out;
-+ if (h_latest == h_dentry)
-+ err = 0;
-+ dput(h_latest);
++ if (hi)
++ au_hiput(hinode);
++ hinode->hi_inode = h_inode;
++ if (h_inode) {
++ int err;
++ struct super_block *sb = inode->i_sb;
++ struct au_branch *br;
++
++ AuDebugOn(inode->i_mode
++ && (h_inode->i_mode & S_IFMT)
++ != (inode->i_mode & S_IFMT));
++ if (bindex == iinfo->ii_btop)
++ au_cpup_igen(inode, h_inode);
++ br = au_sbr(sb, bindex);
++ hinode->hi_id = br->br_id;
++ if (au_ftest_hi(flags, XINO)) {
++ err = au_xino_write(sb, bindex, h_inode->i_ino,
++ inode->i_ino);
++ if (unlikely(err))
++ AuIOErr1("failed au_xino_write() %d\n", err);
++ }
+
-+out:
-+ return err;
++ if (au_ftest_hi(flags, HNOTIFY)
++ && au_br_hnotifyable(br->br_perm)) {
++ err = au_hn_alloc(hinode, inode);
++ if (unlikely(err))
++ AuIOErr1("au_hn_alloc() %d\n", err);
++ }
++ }
+}
+
-+/*
-+ * decide the branch where we operate for @dentry. the branch index will be set
-+ * @rbcpup. after deciding it, 'pin' it and store the timestamps of the parent
-+ * dir for reverting.
-+ * when a new whiteout is necessary, create it.
-+ */
-+static struct dentry*
-+lock_hdir_create_wh(struct dentry *dentry, int isdir, aufs_bindex_t *rbcpup,
-+ struct au_dtime *dt, struct au_pin *pin)
++void au_set_hi_wh(struct inode *inode, aufs_bindex_t bindex,
++ struct dentry *h_wh)
+{
-+ struct dentry *wh_dentry;
-+ struct super_block *sb;
-+ struct path h_path;
-+ int err, need_wh;
-+ unsigned int udba;
-+ aufs_bindex_t bcpup;
-+
-+ need_wh = au_wr_dir_need_wh(dentry, isdir, rbcpup);
-+ wh_dentry = ERR_PTR(need_wh);
-+ if (unlikely(need_wh < 0))
-+ goto out;
-+
-+ sb = dentry->d_sb;
-+ udba = au_opt_udba(sb);
-+ bcpup = *rbcpup;
-+ err = au_pin(pin, dentry, bcpup, udba,
-+ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
-+ wh_dentry = ERR_PTR(err);
-+ if (unlikely(err))
-+ goto out;
-+
-+ h_path.dentry = au_pinned_h_parent(pin);
-+ if (udba != AuOpt_UDBA_NONE
-+ && au_dbtop(dentry) == bcpup) {
-+ err = au_may_del(dentry, bcpup, h_path.dentry, isdir);
-+ wh_dentry = ERR_PTR(err);
-+ if (unlikely(err))
-+ goto out_unpin;
-+ }
++ struct au_hinode *hinode;
+
-+ h_path.mnt = au_sbr_mnt(sb, bcpup);
-+ au_dtime_store(dt, au_pinned_parent(pin), &h_path);
-+ wh_dentry = NULL;
-+ if (!need_wh)
-+ goto out; /* success, no need to create whiteout */
++ IiMustWriteLock(inode);
+
-+ wh_dentry = au_wh_create(dentry, bcpup, h_path.dentry);
-+ if (IS_ERR(wh_dentry))
-+ goto out_unpin;
++ hinode = au_hinode(au_ii(inode), bindex);
++ AuDebugOn(hinode->hi_whdentry);
++ hinode->hi_whdentry = h_wh;
++}
+
-+ /* returns with the parent is locked and wh_dentry is dget-ed */
-+ goto out; /* success */
++void au_update_iigen(struct inode *inode, int half)
++{
++ struct au_iinfo *iinfo;
++ struct au_iigen *iigen;
++ unsigned int sigen;
+
-+out_unpin:
-+ au_unpin(pin);
-+out:
-+ return wh_dentry;
++ sigen = au_sigen(inode->i_sb);
++ iinfo = au_ii(inode);
++ iigen = &iinfo->ii_generation;
++ spin_lock(&iigen->ig_spin);
++ iigen->ig_generation = sigen;
++ if (half)
++ au_ig_fset(iigen->ig_flags, HALF_REFRESHED);
++ else
++ au_ig_fclr(iigen->ig_flags, HALF_REFRESHED);
++ spin_unlock(&iigen->ig_spin);
+}
+
-+/*
-+ * when removing a dir, rename it to a unique temporary whiteout-ed name first
-+ * in order to be revertible and save time for removing many child whiteouts
-+ * under the dir.
-+ * returns 1 when there are too many child whiteout and caller should remove
-+ * them asynchronously. returns 0 when the number of children is enough small to
-+ * remove now or the branch fs is a remote fs.
-+ * otherwise return an error.
-+ */
-+static int renwh_and_rmdir(struct dentry *dentry, aufs_bindex_t bindex,
-+ struct au_nhash *whlist, struct inode *dir)
++/* it may be called at remount time, too */
++void au_update_ibrange(struct inode *inode, int do_put_zero)
+{
-+ int rmdir_later, err, dirwh;
-+ struct dentry *h_dentry;
-+ struct super_block *sb;
-+ struct inode *inode;
-+
-+ sb = dentry->d_sb;
-+ SiMustAnyLock(sb);
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ err = au_whtmp_ren(h_dentry, au_sbr(sb, bindex));
-+ if (unlikely(err))
-+ goto out;
++ struct au_iinfo *iinfo;
++ aufs_bindex_t bindex, bbot;
+
-+ /* stop monitoring */
-+ inode = d_inode(dentry);
-+ au_hn_free(au_hi(inode, bindex));
++ AuDebugOn(au_is_bad_inode(inode));
++ IiMustWriteLock(inode);
+
-+ if (!au_test_fs_remote(h_dentry->d_sb)) {
-+ dirwh = au_sbi(sb)->si_dirwh;
-+ rmdir_later = (dirwh <= 1);
-+ if (!rmdir_later)
-+ rmdir_later = au_nhash_test_longer_wh(whlist, bindex,
-+ dirwh);
-+ if (rmdir_later)
-+ return rmdir_later;
-+ }
++ iinfo = au_ii(inode);
++ if (do_put_zero && iinfo->ii_btop >= 0) {
++ for (bindex = iinfo->ii_btop; bindex <= iinfo->ii_bbot;
++ bindex++) {
++ struct inode *h_i;
+
-+ err = au_whtmp_rmdir(dir, bindex, h_dentry, whlist);
-+ if (unlikely(err)) {
-+ AuIOErr("rmdir %pd, b%d failed, %d. ignored\n",
-+ h_dentry, bindex, err);
-+ err = 0;
++ h_i = au_hinode(iinfo, bindex)->hi_inode;
++ if (h_i
++ && !h_i->i_nlink
++ && !(h_i->i_state & I_LINKABLE))
++ au_set_h_iptr(inode, bindex, NULL, 0);
++ }
+ }
+
-+out:
-+ AuTraceErr(err);
-+ return err;
++ iinfo->ii_btop = -1;
++ iinfo->ii_bbot = -1;
++ bbot = au_sbbot(inode->i_sb);
++ for (bindex = 0; bindex <= bbot; bindex++)
++ if (au_hinode(iinfo, bindex)->hi_inode) {
++ iinfo->ii_btop = bindex;
++ break;
++ }
++ if (iinfo->ii_btop >= 0)
++ for (bindex = bbot; bindex >= iinfo->ii_btop; bindex--)
++ if (au_hinode(iinfo, bindex)->hi_inode) {
++ iinfo->ii_bbot = bindex;
++ break;
++ }
++ AuDebugOn(iinfo->ii_btop > iinfo->ii_bbot);
+}
+
-+/*
-+ * final procedure for deleting a entry.
-+ * maintain dentry and iattr.
-+ */
-+static void epilog(struct inode *dir, struct dentry *dentry,
-+ aufs_bindex_t bindex)
++/* ---------------------------------------------------------------------- */
++
++void au_icntnr_init_once(void *_c)
+{
-+ struct inode *inode;
++ struct au_icntnr *c = _c;
++ struct au_iinfo *iinfo = &c->iinfo;
+
-+ inode = d_inode(dentry);
-+ d_drop(dentry);
-+ inode_set_ctime_to_ts(inode, inode_get_ctime(dir));
++ spin_lock_init(&iinfo->ii_generation.ig_spin);
++ au_rw_init(&iinfo->ii_rwsem);
++ inode_init_once(&c->vfs_inode);
++}
+
-+ au_dir_ts(dir, bindex);
-+ inode_inc_iversion(dir);
++void au_hinode_init(struct au_hinode *hinode)
++{
++ hinode->hi_inode = NULL;
++ hinode->hi_id = -1;
++ au_hn_init(hinode);
++ hinode->hi_whdentry = NULL;
+}
+
-+/*
-+ * when an error happened, remove the created whiteout and revert everything.
-+ */
-+static int do_revert(int err, struct inode *dir, aufs_bindex_t bindex,
-+ aufs_bindex_t bwh, struct dentry *wh_dentry,
-+ struct dentry *dentry, struct au_dtime *dt)
++int au_iinfo_init(struct inode *inode)
+{
-+ int rerr;
-+ struct path h_path = {
-+ .dentry = wh_dentry,
-+ .mnt = au_sbr_mnt(dir->i_sb, bindex)
-+ };
++ struct au_iinfo *iinfo;
++ struct super_block *sb;
++ struct au_hinode *hi;
++ int nbr, i;
+
-+ rerr = au_wh_unlink_dentry(au_h_iptr(dir, bindex), &h_path, dentry);
-+ if (!rerr) {
-+ au_set_dbwh(dentry, bwh);
-+ au_dtime_revert(dt);
++ sb = inode->i_sb;
++ iinfo = &(container_of(inode, struct au_icntnr, vfs_inode)->iinfo);
++ nbr = au_sbbot(sb) + 1;
++ if (unlikely(nbr <= 0))
++ nbr = 1;
++ hi = kmalloc_array(nbr, sizeof(*iinfo->ii_hinode), GFP_NOFS);
++ if (hi) {
++ au_lcnt_inc(&au_sbi(sb)->si_ninodes);
++
++ iinfo->ii_hinode = hi;
++ for (i = 0; i < nbr; i++, hi++)
++ au_hinode_init(hi);
++
++ iinfo->ii_generation.ig_generation = au_sigen(sb);
++ iinfo->ii_btop = -1;
++ iinfo->ii_bbot = -1;
++ iinfo->ii_vdir = NULL;
+ return 0;
+ }
-+
-+ AuIOErr("%pd reverting whiteout failed(%d, %d)\n", dentry, err, rerr);
-+ return -EIO;
++ return -ENOMEM;
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+int aufs_unlink(struct inode *dir, struct dentry *dentry)
++int au_hinode_realloc(struct au_iinfo *iinfo, int nbr, int may_shrink)
+{
-+ int err;
-+ aufs_bindex_t bwh, bindex, btop;
-+ struct inode *inode, *h_dir, *delegated, *h_inode;
-+ struct dentry *parent, *wh_dentry;
-+ /* to reduce stack size */
-+ struct {
-+ struct au_dtime dt;
-+ struct au_pin pin;
-+ struct path h_path;
-+ } *a;
++ int err, i;
++ struct au_hinode *hip;
+
-+ IMustLock(dir);
++ AuRwMustWriteLock(&iinfo->ii_rwsem);
+
+ err = -ENOMEM;
-+ a = kmalloc(sizeof(*a), GFP_NOFS);
-+ if (unlikely(!a))
-+ goto out;
++ hip = au_krealloc(iinfo->ii_hinode, sizeof(*hip) * nbr, GFP_NOFS,
++ may_shrink);
++ if (hip) {
++ iinfo->ii_hinode = hip;
++ i = iinfo->ii_bbot + 1;
++ hip += i;
++ for (; i < nbr; i++, hip++)
++ au_hinode_init(hip);
++ err = 0;
++ }
+
-+ err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN);
-+ if (unlikely(err))
-+ goto out_free;
-+ err = au_d_hashed_positive(dentry);
-+ if (unlikely(err))
-+ goto out_unlock;
-+ inode = d_inode(dentry);
-+ IMustLock(inode);
-+ err = -EISDIR;
-+ if (unlikely(d_is_dir(dentry)))
-+ goto out_unlock; /* possible? */
++ return err;
++}
+
-+ btop = au_dbtop(dentry);
-+ bwh = au_dbwh(dentry);
-+ bindex = -1;
-+ parent = dentry->d_parent; /* dir inode is locked */
-+ di_write_lock_parent(parent);
-+ wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/0, &bindex, &a->dt,
-+ &a->pin);
-+ err = PTR_ERR(wh_dentry);
-+ if (IS_ERR(wh_dentry))
-+ goto out_parent;
++void au_iinfo_fin(struct inode *inode)
++{
++ struct au_iinfo *iinfo;
++ struct au_hinode *hi;
++ struct super_block *sb;
++ aufs_bindex_t bindex, bbot;
++ const unsigned char unlinked = !inode->i_nlink;
+
-+ a->h_path.mnt = au_sbr_mnt(dentry->d_sb, btop);
-+ a->h_path.dentry = au_h_dptr(dentry, btop);
-+ dget(a->h_path.dentry);
-+ if (bindex == btop) {
-+ h_dir = au_pinned_h_dir(&a->pin);
-+ delegated = NULL;
-+ err = vfsub_unlink(h_dir, &a->h_path, &delegated, /*force*/0);
-+ if (unlikely(err == -EWOULDBLOCK)) {
-+ pr_warn("cannot retry for NFSv4 delegation"
-+ " for an internal unlink\n");
-+ iput(delegated);
-+ }
-+ } else {
-+ /* dir inode is locked */
-+ h_dir = d_inode(wh_dentry->d_parent);
-+ IMustLock(h_dir);
-+ err = 0;
++ AuDebugOn(au_is_bad_inode(inode));
++
++ sb = inode->i_sb;
++ au_lcnt_dec(&au_sbi(sb)->si_ninodes);
++ if (si_pid_test(sb))
++ au_xino_delete_inode(inode, unlinked);
++ else {
++ /*
++ * it is safe to hide the dependency between sbinfo and
++ * sb->s_umount.
++ */
++ lockdep_off();
++ si_noflush_read_lock(sb);
++ au_xino_delete_inode(inode, unlinked);
++ si_read_unlock(sb);
++ lockdep_on();
+ }
+
-+ if (!err) {
-+ vfsub_drop_nlink(inode);
-+ epilog(dir, dentry, bindex);
++ iinfo = au_ii(inode);
++ if (iinfo->ii_vdir)
++ au_vdir_free(iinfo->ii_vdir);
+
-+ /* update target timestamps */
-+ if (bindex == btop) {
-+ vfsub_update_h_iattr(&a->h_path, /*did*/NULL);
-+ /*ignore*/
-+ h_inode = d_inode(a->h_path.dentry);
-+ inode_set_ctime_to_ts(inode, inode_get_ctime(h_inode));
-+ } else
-+ /* todo: this timestamp may be reverted later */
-+ inode_set_ctime_to_ts(inode, inode_get_ctime(h_dir));
-+ goto out_unpin; /* success */
++ bindex = iinfo->ii_btop;
++ if (bindex >= 0) {
++ hi = au_hinode(iinfo, bindex);
++ bbot = iinfo->ii_bbot;
++ while (bindex++ <= bbot) {
++ if (hi->hi_inode)
++ au_hiput(hi);
++ hi++;
++ }
+ }
++ au_kfree_rcu(iinfo->ii_hinode);
++ AuRwDestroy(&iinfo->ii_rwsem);
++}
+diff --git a/fs/aufs/inode.c b/fs/aufs/inode.c
+new file mode 100644
+index 00000000000000..7dbf6a6f2feec3
+--- /dev/null
++++ b/fs/aufs/inode.c
+@@ -0,0 +1,531 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2005-2022 Junjiro R. Okajima
++ *
++ * This program 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/>.
++ */
+
-+ /* revert */
-+ if (wh_dentry) {
-+ int rerr;
++/*
++ * inode functions
++ */
+
-+ rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry,
-+ &a->dt);
-+ if (rerr)
-+ err = rerr;
-+ }
++#include <linux/iversion.h>
++#include "aufs.h"
+
-+out_unpin:
-+ au_unpin(&a->pin);
-+ dput(wh_dentry);
-+ dput(a->h_path.dentry);
-+out_parent:
-+ di_write_unlock(parent);
-+out_unlock:
-+ aufs_read_unlock(dentry, AuLock_DW);
-+out_free:
-+ au_kfree_rcu(a);
-+out:
-+ return err;
++struct inode *au_igrab(struct inode *inode)
++{
++ if (inode) {
++ AuDebugOn(!atomic_read(&inode->i_count));
++ ihold(inode);
++ }
++ return inode;
+}
+
-+int aufs_rmdir(struct inode *dir, struct dentry *dentry)
++static void au_refresh_hinode_attr(struct inode *inode, int do_version)
+{
-+ int err, rmdir_later;
-+ aufs_bindex_t bwh, bindex, btop;
-+ struct inode *inode;
-+ struct dentry *parent, *wh_dentry, *h_dentry;
-+ struct au_whtmp_rmdir *args;
-+ /* to reduce stack size */
-+ struct {
-+ struct au_dtime dt;
-+ struct au_pin pin;
-+ } *a;
++ au_cpup_attr_all(inode, /*force*/0);
++ au_update_iigen(inode, /*half*/1);
++ if (do_version)
++ inode_inc_iversion(inode);
++}
+
-+ IMustLock(dir);
++static int au_ii_refresh(struct inode *inode, int *update)
++{
++ int err, e, nbr;
++ umode_t type;
++ aufs_bindex_t bindex, new_bindex;
++ struct super_block *sb;
++ struct au_iinfo *iinfo;
++ struct au_hinode *p, *q, tmp;
+
-+ err = -ENOMEM;
-+ a = kmalloc(sizeof(*a), GFP_NOFS);
-+ if (unlikely(!a))
-+ goto out;
++ AuDebugOn(au_is_bad_inode(inode));
++ IiMustWriteLock(inode);
+
-+ err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN);
-+ if (unlikely(err))
-+ goto out_free;
-+ err = au_alive_dir(dentry);
++ *update = 0;
++ sb = inode->i_sb;
++ nbr = au_sbbot(sb) + 1;
++ type = inode->i_mode & S_IFMT;
++ iinfo = au_ii(inode);
++ err = au_hinode_realloc(iinfo, nbr, /*may_shrink*/0);
+ if (unlikely(err))
-+ goto out_unlock;
-+ inode = d_inode(dentry);
-+ IMustLock(inode);
-+ err = -ENOTDIR;
-+ if (unlikely(!d_is_dir(dentry)))
-+ goto out_unlock; /* possible? */
-+
-+ err = -ENOMEM;
-+ args = au_whtmp_rmdir_alloc(dir->i_sb, GFP_NOFS);
-+ if (unlikely(!args))
-+ goto out_unlock;
++ goto out;
+
-+ parent = dentry->d_parent; /* dir inode is locked */
-+ di_write_lock_parent(parent);
-+ err = au_test_empty(dentry, &args->whlist);
-+ if (unlikely(err))
-+ goto out_parent;
++ AuDebugOn(iinfo->ii_btop < 0);
++ p = au_hinode(iinfo, iinfo->ii_btop);
++ for (bindex = iinfo->ii_btop; bindex <= iinfo->ii_bbot;
++ bindex++, p++) {
++ if (!p->hi_inode)
++ continue;
+
-+ btop = au_dbtop(dentry);
-+ bwh = au_dbwh(dentry);
-+ bindex = -1;
-+ wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/1, &bindex, &a->dt,
-+ &a->pin);
-+ err = PTR_ERR(wh_dentry);
-+ if (IS_ERR(wh_dentry))
-+ goto out_parent;
++ AuDebugOn(type != (p->hi_inode->i_mode & S_IFMT));
++ new_bindex = au_br_index(sb, p->hi_id);
++ if (new_bindex == bindex)
++ continue;
+
-+ h_dentry = au_h_dptr(dentry, btop);
-+ dget(h_dentry);
-+ rmdir_later = 0;
-+ if (bindex == btop) {
-+ err = renwh_and_rmdir(dentry, btop, &args->whlist, dir);
-+ if (err > 0) {
-+ rmdir_later = err;
-+ err = 0;
++ if (new_bindex < 0) {
++ *update = 1;
++ au_hiput(p);
++ p->hi_inode = NULL;
++ continue;
+ }
-+ } else {
-+ /* stop monitoring */
-+ au_hn_free(au_hi(inode, btop));
+
-+ /* dir inode is locked */
-+ IMustLock(d_inode(wh_dentry->d_parent));
-+ err = 0;
++ if (new_bindex < iinfo->ii_btop)
++ iinfo->ii_btop = new_bindex;
++ if (iinfo->ii_bbot < new_bindex)
++ iinfo->ii_bbot = new_bindex;
++ /* swap two lower inode, and loop again */
++ q = au_hinode(iinfo, new_bindex);
++ tmp = *q;
++ *q = *p;
++ *p = tmp;
++ if (tmp.hi_inode) {
++ bindex--;
++ p--;
++ }
+ }
++ au_update_ibrange(inode, /*do_put_zero*/0);
++ au_hinode_realloc(iinfo, nbr, /*may_shrink*/1); /* harmless if err */
++ e = au_dy_irefresh(inode);
++ if (unlikely(e && !err))
++ err = e;
+
-+ if (!err) {
-+ vfsub_dead_dir(inode);
-+ au_set_dbdiropq(dentry, -1);
-+ epilog(dir, dentry, bindex);
++out:
++ AuTraceErr(err);
++ return err;
++}
+
-+ if (rmdir_later) {
-+ au_whtmp_kick_rmdir(dir, btop, h_dentry, args);
-+ args = NULL;
-+ }
++void au_refresh_iop(struct inode *inode, int force_getattr)
++{
++ int type;
++ struct au_sbinfo *sbi = au_sbi(inode->i_sb);
++ const struct inode_operations *iop
++ = force_getattr ? aufs_iop : sbi->si_iop_array;
+
-+ goto out_unpin; /* success */
++ if (inode->i_op == iop)
++ return;
++
++ switch (inode->i_mode & S_IFMT) {
++ case S_IFDIR:
++ type = AuIop_DIR;
++ break;
++ case S_IFLNK:
++ type = AuIop_SYMLINK;
++ break;
++ default:
++ type = AuIop_OTHER;
++ break;
+ }
+
-+ /* revert */
-+ AuLabel(revert);
-+ if (wh_dentry) {
-+ int rerr;
++ inode->i_op = iop + type;
++ /* unnecessary smp_wmb() */
++}
+
-+ rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry,
-+ &a->dt);
-+ if (rerr)
-+ err = rerr;
-+ }
++int au_refresh_hinode_self(struct inode *inode)
++{
++ int err, update;
++
++ err = au_ii_refresh(inode, &update);
++ if (!err)
++ au_refresh_hinode_attr(inode, update && S_ISDIR(inode->i_mode));
+
-+out_unpin:
-+ au_unpin(&a->pin);
-+ dput(wh_dentry);
-+ dput(h_dentry);
-+out_parent:
-+ di_write_unlock(parent);
-+ if (args)
-+ au_whtmp_rmdir_free(args);
-+out_unlock:
-+ aufs_read_unlock(dentry, AuLock_DW);
-+out_free:
-+ au_kfree_rcu(a);
-+out:
+ AuTraceErr(err);
+ return err;
+}
-diff -urN /usr/share/empty/fs/aufs/i_op_ren.c linux/fs/aufs/i_op_ren.c
---- /usr/share/empty/fs/aufs/i_op_ren.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/i_op_ren.c 2023-10-31 09:31:04.199880750 +0100
-@@ -0,0 +1,1260 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2022 Junjiro R. Okajima
-+ *
-+ * This program 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/>.
-+ */
-+
-+/*
-+ * inode operation (rename entry)
-+ * todo: this is crazy monster
-+ */
+
-+#include <linux/iversion.h>
-+#include "aufs.h"
++int au_refresh_hinode(struct inode *inode, struct dentry *dentry)
++{
++ int err, e, update;
++ unsigned int flags;
++ umode_t mode;
++ aufs_bindex_t bindex, bbot;
++ unsigned char isdir;
++ struct au_hinode *p;
++ struct au_iinfo *iinfo;
+
-+enum { AuSRC, AuDST, AuSrcDst };
-+enum { AuPARENT, AuCHILD, AuParentChild };
++ err = au_ii_refresh(inode, &update);
++ if (unlikely(err))
++ goto out;
+
-+#define AuRen_ISDIR_SRC 1
-+#define AuRen_ISDIR_DST (1 << 1)
-+#define AuRen_ISSAMEDIR (1 << 2)
-+#define AuRen_WHSRC (1 << 3)
-+#define AuRen_WHDST (1 << 4)
-+#define AuRen_MNT_WRITE (1 << 5)
-+#define AuRen_DT_DSTDIR (1 << 6)
-+#define AuRen_DIROPQ_SRC (1 << 7)
-+#define AuRen_DIROPQ_DST (1 << 8)
-+#define AuRen_DIRREN (1 << 9)
-+#define AuRen_DROPPED_SRC (1 << 10)
-+#define AuRen_DROPPED_DST (1 << 11)
-+#define au_ftest_ren(flags, name) ((flags) & AuRen_##name)
-+#define au_fset_ren(flags, name) \
-+ do { (flags) |= AuRen_##name; } while (0)
-+#define au_fclr_ren(flags, name) \
-+ do { (flags) &= ~AuRen_##name; } while (0)
++ update = 0;
++ iinfo = au_ii(inode);
++ p = au_hinode(iinfo, iinfo->ii_btop);
++ mode = (inode->i_mode & S_IFMT);
++ isdir = S_ISDIR(mode);
++ flags = au_hi_flags(inode, isdir);
++ bbot = au_dbbot(dentry);
++ for (bindex = au_dbtop(dentry); bindex <= bbot; bindex++) {
++ struct inode *h_i, *h_inode;
++ struct dentry *h_d;
+
-+#ifndef CONFIG_AUFS_DIRREN
-+#undef AuRen_DIRREN
-+#define AuRen_DIRREN 0
-+#endif
++ h_d = au_h_dptr(dentry, bindex);
++ if (!h_d || d_is_negative(h_d))
++ continue;
+
-+struct au_ren_args {
-+ struct {
-+ struct dentry *dentry, *h_dentry, *parent, *h_parent,
-+ *wh_dentry;
-+ struct inode *dir, *inode;
-+ struct au_hinode *hdir, *hinode;
-+ struct au_dtime dt[AuParentChild];
-+ aufs_bindex_t btop, bdiropq;
-+ } sd[AuSrcDst];
++ h_inode = d_inode(h_d);
++ AuDebugOn(mode != (h_inode->i_mode & S_IFMT));
++ if (iinfo->ii_btop <= bindex && bindex <= iinfo->ii_bbot) {
++ h_i = au_h_iptr(inode, bindex);
++ if (h_i) {
++ if (h_i == h_inode)
++ continue;
++ err = -EIO;
++ break;
++ }
++ }
++ if (bindex < iinfo->ii_btop)
++ iinfo->ii_btop = bindex;
++ if (iinfo->ii_bbot < bindex)
++ iinfo->ii_bbot = bindex;
++ au_set_h_iptr(inode, bindex, au_igrab(h_inode), flags);
++ update = 1;
++ }
++ au_update_ibrange(inode, /*do_put_zero*/0);
++ e = au_dy_irefresh(inode);
++ if (unlikely(e && !err))
++ err = e;
++ if (!err)
++ au_refresh_hinode_attr(inode, update && isdir);
+
-+#define src_dentry sd[AuSRC].dentry
-+#define src_dir sd[AuSRC].dir
-+#define src_inode sd[AuSRC].inode
-+#define src_h_dentry sd[AuSRC].h_dentry
-+#define src_parent sd[AuSRC].parent
-+#define src_h_parent sd[AuSRC].h_parent
-+#define src_wh_dentry sd[AuSRC].wh_dentry
-+#define src_hdir sd[AuSRC].hdir
-+#define src_hinode sd[AuSRC].hinode
-+#define src_h_dir sd[AuSRC].hdir->hi_inode
-+#define src_dt sd[AuSRC].dt
-+#define src_btop sd[AuSRC].btop
-+#define src_bdiropq sd[AuSRC].bdiropq
++out:
++ AuTraceErr(err);
++ return err;
++}
+
-+#define dst_dentry sd[AuDST].dentry
-+#define dst_dir sd[AuDST].dir
-+#define dst_inode sd[AuDST].inode
-+#define dst_h_dentry sd[AuDST].h_dentry
-+#define dst_parent sd[AuDST].parent
-+#define dst_h_parent sd[AuDST].h_parent
-+#define dst_wh_dentry sd[AuDST].wh_dentry
-+#define dst_hdir sd[AuDST].hdir
-+#define dst_hinode sd[AuDST].hinode
-+#define dst_h_dir sd[AuDST].hdir->hi_inode
-+#define dst_dt sd[AuDST].dt
-+#define dst_btop sd[AuDST].btop
-+#define dst_bdiropq sd[AuDST].bdiropq
++static int set_inode(struct inode *inode, struct dentry *dentry)
++{
++ int err;
++ unsigned int flags;
++ umode_t mode;
++ aufs_bindex_t bindex, btop, btail;
++ unsigned char isdir;
++ struct dentry *h_dentry;
++ struct inode *h_inode;
++ struct au_iinfo *iinfo;
++ const struct inode_operations *iop;
+
-+ struct dentry *h_trap;
-+ struct au_branch *br;
-+ struct path h_path;
-+ struct au_nhash whlist;
-+ aufs_bindex_t btgt, src_bwh;
++ IiMustWriteLock(inode);
+
-+ struct {
-+ unsigned short auren_flags;
-+ unsigned char flags; /* syscall parameter */
-+ unsigned char exchange;
-+ } __packed;
++ err = 0;
++ isdir = 0;
++ iop = au_sbi(inode->i_sb)->si_iop_array;
++ btop = au_dbtop(dentry);
++ h_dentry = au_h_dptr(dentry, btop);
++ h_inode = d_inode(h_dentry);
++ mode = h_inode->i_mode;
++ switch (mode & S_IFMT) {
++ case S_IFREG:
++ btail = au_dbtail(dentry);
++ inode->i_op = iop + AuIop_OTHER;
++ inode->i_fop = &aufs_file_fop;
++ err = au_dy_iaop(inode, btop, h_inode);
++ if (unlikely(err))
++ goto out;
++ break;
++ case S_IFDIR:
++ isdir = 1;
++ btail = au_dbtaildir(dentry);
++ inode->i_op = iop + AuIop_DIR;
++ inode->i_fop = &aufs_dir_fop;
++ break;
++ case S_IFLNK:
++ btail = au_dbtail(dentry);
++ inode->i_op = iop + AuIop_SYMLINK;
++ break;
++ case S_IFBLK:
++ case S_IFCHR:
++ case S_IFIFO:
++ case S_IFSOCK:
++ btail = au_dbtail(dentry);
++ inode->i_op = iop + AuIop_OTHER;
++ init_special_inode(inode, mode, h_inode->i_rdev);
++ break;
++ default:
++ AuIOErr("Unknown file type 0%o\n", mode);
++ err = -EIO;
++ goto out;
++ }
+
-+ struct au_whtmp_rmdir *thargs;
-+ struct dentry *h_dst;
-+ struct au_hinode *h_root;
-+};
++ /* do not set hnotify for whiteouted dirs (SHWH mode) */
++ flags = au_hi_flags(inode, isdir);
++ if (au_opt_test(au_mntflags(dentry->d_sb), SHWH)
++ && au_ftest_hi(flags, HNOTIFY)
++ && dentry->d_name.len > AUFS_WH_PFX_LEN
++ && !memcmp(dentry->d_name.name, AUFS_WH_PFX, AUFS_WH_PFX_LEN))
++ au_fclr_hi(flags, HNOTIFY);
++ iinfo = au_ii(inode);
++ iinfo->ii_btop = btop;
++ iinfo->ii_bbot = btail;
++ for (bindex = btop; bindex <= btail; bindex++) {
++ h_dentry = au_h_dptr(dentry, bindex);
++ if (h_dentry)
++ au_set_h_iptr(inode, bindex,
++ au_igrab(d_inode(h_dentry)), flags);
++ }
++ au_cpup_attr_all(inode, /*force*/1);
++ /*
++ * to force calling aufs_get_inode_acl() every time,
++ * do not call cache_no_acl() for aufs inode.
++ */
+
-+/* ---------------------------------------------------------------------- */
++out:
++ return err;
++}
+
+/*
-+ * functions for reverting.
-+ * when an error happened in a single rename systemcall, we should revert
-+ * everything as if nothing happened.
-+ * we don't need to revert the copied-up/down the parent dir since they are
-+ * harmless.
++ * successful returns with iinfo write_locked
++ * minus: errno
++ * zero: success, matched
++ * plus: no error, but unmatched
+ */
++static int reval_inode(struct inode *inode, struct dentry *dentry)
++{
++ int err;
++ unsigned int gen, igflags;
++ aufs_bindex_t bindex, bbot;
++ struct inode *h_inode, *h_dinode;
++ struct dentry *h_dentry;
+
-+#define RevertFailure(fmt, ...) do { \
-+ AuIOErr("revert failure: " fmt " (%d, %d)\n", \
-+ ##__VA_ARGS__, err, rerr); \
-+ err = -EIO; \
-+} while (0)
++ /*
++ * before this function, if aufs got any iinfo lock, it must be only
++ * one, the parent dir.
++ * it can happen by UDBA and the obsoleted inode number.
++ */
++ err = -EIO;
++ if (unlikely(inode->i_ino == parent_ino(dentry)))
++ goto out;
+
-+static void au_ren_do_rev_diropq(int err, struct au_ren_args *a, int idx)
-+{
-+ int rerr;
-+ struct dentry *d;
-+#define src_or_dst(member) a->sd[idx].member
++ err = 1;
++ ii_write_lock_new_child(inode);
++ h_dentry = au_h_dptr(dentry, au_dbtop(dentry));
++ h_dinode = d_inode(h_dentry);
++ bbot = au_ibbot(inode);
++ for (bindex = au_ibtop(inode); bindex <= bbot; bindex++) {
++ h_inode = au_h_iptr(inode, bindex);
++ if (!h_inode || h_inode != h_dinode)
++ continue;
+
-+ d = src_or_dst(dentry); /* {src,dst}_dentry */
-+ au_hn_inode_lock_nested(src_or_dst(hinode), AuLsc_I_CHILD);
-+ rerr = au_diropq_remove(d, a->btgt);
-+ au_hn_inode_unlock(src_or_dst(hinode));
-+ au_set_dbdiropq(d, src_or_dst(bdiropq));
-+ if (rerr)
-+ RevertFailure("remove diropq %pd", d);
++ err = 0;
++ gen = au_iigen(inode, &igflags);
++ if (gen == au_digen(dentry)
++ && !au_ig_ftest(igflags, HALF_REFRESHED))
++ break;
+
-+#undef src_or_dst_
-+}
++ /* fully refresh inode using dentry */
++ err = au_refresh_hinode(inode, dentry);
++ if (!err)
++ au_update_iigen(inode, /*half*/0);
++ break;
++ }
+
-+static void au_ren_rev_diropq(int err, struct au_ren_args *a)
-+{
-+ if (au_ftest_ren(a->auren_flags, DIROPQ_SRC))
-+ au_ren_do_rev_diropq(err, a, AuSRC);
-+ if (au_ftest_ren(a->auren_flags, DIROPQ_DST))
-+ au_ren_do_rev_diropq(err, a, AuDST);
++ if (unlikely(err))
++ ii_write_unlock(inode);
++out:
++ return err;
+}
+
-+static void au_ren_rev_rename(int err, struct au_ren_args *a)
++int au_ino(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
++ unsigned int d_type, ino_t *ino)
+{
-+ int rerr;
-+ struct inode *delegated;
-+ struct path h_ppath = {
-+ .dentry = a->src_h_parent,
-+ .mnt = a->h_path.mnt
-+ };
++ int err, idx;
++ const int isnondir = d_type != DT_DIR;
+
-+ a->h_path.dentry = vfsub_lkup_one(&a->src_dentry->d_name, &h_ppath);
-+ rerr = PTR_ERR(a->h_path.dentry);
-+ if (IS_ERR(a->h_path.dentry)) {
-+ RevertFailure("lkup one %pd", a->src_dentry);
-+ return;
++ /* prevent hardlinked inode number from race condition */
++ if (isnondir) {
++ err = au_xinondir_enter(sb, bindex, h_ino, &idx);
++ if (unlikely(err))
++ goto out;
+ }
+
-+ delegated = NULL;
-+ rerr = vfsub_rename(a->dst_h_dir,
-+ au_h_dptr(a->src_dentry, a->btgt),
-+ a->src_h_dir, &a->h_path, &delegated, a->flags);
-+ if (unlikely(rerr == -EWOULDBLOCK)) {
-+ pr_warn("cannot retry for NFSv4 delegation"
-+ " for an internal rename\n");
-+ iput(delegated);
++ err = au_xino_read(sb, bindex, h_ino, ino);
++ if (unlikely(err))
++ goto out_xinondir;
++
++ if (!*ino) {
++ err = -EIO;
++ *ino = au_xino_new_ino(sb);
++ if (unlikely(!*ino))
++ goto out_xinondir;
++ err = au_xino_write(sb, bindex, h_ino, *ino);
++ if (unlikely(err))
++ goto out_xinondir;
+ }
-+ d_drop(a->h_path.dentry);
-+ dput(a->h_path.dentry);
-+ /* au_set_h_dptr(a->src_dentry, a->btgt, NULL); */
-+ if (rerr)
-+ RevertFailure("rename %pd", a->src_dentry);
++
++out_xinondir:
++ if (isnondir && idx >= 0)
++ au_xinondir_leave(sb, bindex, h_ino, idx);
++out:
++ return err;
+}
+
-+static void au_ren_rev_whtmp(int err, struct au_ren_args *a)
++/* successful returns with iinfo write_locked */
++/* todo: return with unlocked? */
++struct inode *au_new_inode(struct dentry *dentry, int must_new)
+{
-+ int rerr;
-+ struct inode *delegated;
-+ struct path h_ppath = {
-+ .dentry = a->dst_h_parent,
-+ .mnt = a->h_path.mnt
-+ };
++ struct inode *inode, *h_inode;
++ struct dentry *h_dentry;
++ struct super_block *sb;
++ ino_t h_ino, ino;
++ int err, idx, hlinked;
++ aufs_bindex_t btop;
+
-+ a->h_path.dentry = vfsub_lkup_one(&a->dst_dentry->d_name, &h_ppath);
-+ rerr = PTR_ERR(a->h_path.dentry);
-+ if (IS_ERR(a->h_path.dentry)) {
-+ RevertFailure("lkup one %pd", a->dst_dentry);
-+ return;
++ sb = dentry->d_sb;
++ btop = au_dbtop(dentry);
++ h_dentry = au_h_dptr(dentry, btop);
++ h_inode = d_inode(h_dentry);
++ h_ino = h_inode->i_ino;
++ hlinked = !d_is_dir(h_dentry) && h_inode->i_nlink > 1;
++
++new_ino:
++ /*
++ * stop 'race'-ing between hardlinks under different
++ * parents.
++ */
++ if (hlinked) {
++ err = au_xinondir_enter(sb, btop, h_ino, &idx);
++ inode = ERR_PTR(err);
++ if (unlikely(err))
++ goto out;
+ }
-+ if (d_is_positive(a->h_path.dentry)) {
-+ d_drop(a->h_path.dentry);
-+ dput(a->h_path.dentry);
-+ return;
++
++ err = au_xino_read(sb, btop, h_ino, &ino);
++ inode = ERR_PTR(err);
++ if (unlikely(err))
++ goto out_xinondir;
++
++ if (!ino) {
++ ino = au_xino_new_ino(sb);
++ if (unlikely(!ino)) {
++ inode = ERR_PTR(-EIO);
++ goto out_xinondir;
++ }
++ }
++
++ AuDbg("i%lu\n", (unsigned long)ino);
++ inode = au_iget_locked(sb, ino);
++ err = PTR_ERR(inode);
++ if (IS_ERR(inode))
++ goto out_xinondir;
++
++ AuDbg("%lx, new %d\n", inode->i_state, !!(inode->i_state & I_NEW));
++ if (inode->i_state & I_NEW) {
++ ii_write_lock_new_child(inode);
++ err = set_inode(inode, dentry);
++ if (!err) {
++ unlock_new_inode(inode);
++ goto out_xinondir; /* success */
++ }
++
++ /*
++ * iget_failed() calls iput(), but we need to call
++ * ii_write_unlock() after iget_failed(). so dirty hack for
++ * i_count.
++ */
++ atomic_inc(&inode->i_count);
++ iget_failed(inode);
++ ii_write_unlock(inode);
++ au_xino_write(sb, btop, h_ino, /*ino*/0);
++ /* ignore this error */
++ goto out_iput;
++ } else if (!must_new && !IS_DEADDIR(inode) && inode->i_nlink) {
++ /*
++ * horrible race condition between lookup, readdir and copyup
++ * (or something).
++ */
++ if (hlinked && idx >= 0)
++ au_xinondir_leave(sb, btop, h_ino, idx);
++ err = reval_inode(inode, dentry);
++ if (unlikely(err < 0)) {
++ hlinked = 0;
++ goto out_iput;
++ }
++ if (!err)
++ goto out; /* success */
++ else if (hlinked && idx >= 0) {
++ err = au_xinondir_enter(sb, btop, h_ino, &idx);
++ if (unlikely(err)) {
++ iput(inode);
++ inode = ERR_PTR(err);
++ goto out;
++ }
++ }
+ }
+
-+ delegated = NULL;
-+ rerr = vfsub_rename(a->dst_h_dir, a->h_dst, a->dst_h_dir, &a->h_path,
-+ &delegated, a->flags);
-+ if (unlikely(rerr == -EWOULDBLOCK)) {
-+ pr_warn("cannot retry for NFSv4 delegation"
-+ " for an internal rename\n");
-+ iput(delegated);
++ if (unlikely(au_test_fs_unique_ino(h_inode)))
++ AuWarn1("Warning: Un-notified UDBA or repeatedly renamed dir,"
++ " b%d, %s, %pd, hi%lu, i%lu.\n",
++ btop, au_sbtype(h_dentry->d_sb), dentry,
++ (unsigned long)h_ino, (unsigned long)ino);
++ ino = 0;
++ err = au_xino_write(sb, btop, h_ino, /*ino*/0);
++ if (!err) {
++ iput(inode);
++ if (hlinked && idx >= 0)
++ au_xinondir_leave(sb, btop, h_ino, idx);
++ goto new_ino;
+ }
-+ d_drop(a->h_path.dentry);
-+ dput(a->h_path.dentry);
-+ if (!rerr)
-+ au_set_h_dptr(a->dst_dentry, a->btgt, dget(a->h_dst));
-+ else
-+ RevertFailure("rename %pd", a->h_dst);
-+}
-+
-+static void au_ren_rev_whsrc(int err, struct au_ren_args *a)
-+{
-+ int rerr;
+
-+ a->h_path.dentry = a->src_wh_dentry;
-+ rerr = au_wh_unlink_dentry(a->src_h_dir, &a->h_path, a->src_dentry);
-+ au_set_dbwh(a->src_dentry, a->src_bwh);
-+ if (rerr)
-+ RevertFailure("unlink %pd", a->src_wh_dentry);
++out_iput:
++ iput(inode);
++ inode = ERR_PTR(err);
++out_xinondir:
++ if (hlinked && idx >= 0)
++ au_xinondir_leave(sb, btop, h_ino, idx);
++out:
++ return inode;
+}
-+#undef RevertFailure
+
+/* ---------------------------------------------------------------------- */
+
-+/*
-+ * when we have to copyup the renaming entry, do it with the rename-target name
-+ * in order to minimize the cost (the later actual rename is unnecessary).
-+ * otherwise rename it on the target branch.
-+ */
-+static int au_ren_or_cpup(struct au_ren_args *a)
++int au_test_ro(struct super_block *sb, aufs_bindex_t bindex,
++ struct inode *inode)
+{
+ int err;
-+ struct dentry *d;
-+ struct inode *delegated;
++ struct inode *hi;
+
-+ d = a->src_dentry;
-+ if (au_dbtop(d) == a->btgt) {
-+ a->h_path.dentry = a->dst_h_dentry;
-+ AuDebugOn(au_dbtop(d) != a->btgt);
-+ delegated = NULL;
-+ err = vfsub_rename(a->src_h_dir, au_h_dptr(d, a->btgt),
-+ a->dst_h_dir, &a->h_path, &delegated,
-+ a->flags);
-+ if (unlikely(err == -EWOULDBLOCK)) {
-+ pr_warn("cannot retry for NFSv4 delegation"
-+ " for an internal rename\n");
-+ iput(delegated);
-+ }
-+ } else
-+ BUG();
++ err = au_br_rdonly(au_sbr(sb, bindex));
+
-+ if (!err && a->h_dst)
-+ /* it will be set to dinfo later */
-+ dget(a->h_dst);
++ /* pseudo-link after flushed may happen out of bounds */
++ if (!err
++ && inode
++ && au_ibtop(inode) <= bindex
++ && bindex <= au_ibbot(inode)) {
++ /*
++ * permission check is unnecessary since vfsub routine
++ * will be called later
++ */
++ hi = au_h_iptr(inode, bindex);
++ if (hi)
++ err = IS_IMMUTABLE(hi) ? -EROFS : 0;
++ }
+
+ return err;
+}
+
-+/* cf. aufs_rmdir() */
-+static int au_ren_del_whtmp(struct au_ren_args *a)
++int au_test_h_perm(struct mnt_idmap *h_idmap, struct inode *h_inode,
++ int mask)
+{
-+ int err;
-+ struct inode *dir;
-+
-+ dir = a->dst_dir;
-+ SiMustAnyLock(dir->i_sb);
-+ if (!au_nhash_test_longer_wh(&a->whlist, a->btgt,
-+ au_sbi(dir->i_sb)->si_dirwh)
-+ || au_test_fs_remote(a->h_dst->d_sb)) {
-+ err = au_whtmp_rmdir(dir, a->btgt, a->h_dst, &a->whlist);
-+ if (unlikely(err))
-+ pr_warn("failed removing whtmp dir %pd (%d), "
-+ "ignored.\n", a->h_dst, err);
-+ } else {
-+ au_nhash_wh_free(&a->thargs->whlist);
-+ a->thargs->whlist = a->whlist;
-+ a->whlist.nh_num = 0;
-+ au_whtmp_kick_rmdir(dir, a->btgt, a->h_dst, a->thargs);
-+ dput(a->h_dst);
-+ a->thargs = NULL;
-+ }
-+
-+ return 0;
++ if (uid_eq(current_fsuid(), GLOBAL_ROOT_UID))
++ return 0;
++ return inode_permission(h_idmap, h_inode, mask);
+}
+
-+/* make it 'opaque' dir. */
-+static int au_ren_do_diropq(struct au_ren_args *a, int idx)
++int au_test_h_perm_sio(struct mnt_idmap *h_idmap, struct inode *h_inode,
++ int mask)
+{
-+ int err;
-+ struct dentry *d, *diropq;
-+#define src_or_dst(member) a->sd[idx].member
++ if (au_test_nfs(h_inode->i_sb)
++ && (mask & MAY_WRITE)
++ && S_ISDIR(h_inode->i_mode))
++ mask |= MAY_READ; /* force permission check */
++ return au_test_h_perm(h_idmap, h_inode, mask);
++}
+diff --git a/fs/aufs/inode.h b/fs/aufs/inode.h
+new file mode 100644
+index 00000000000000..76c3bd49674a29
+--- /dev/null
++++ b/fs/aufs/inode.h
+@@ -0,0 +1,707 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * Copyright (C) 2005-2022 Junjiro R. Okajima
++ *
++ * This program 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/>.
++ */
+
-+ err = 0;
-+ d = src_or_dst(dentry); /* {src,dst}_dentry */
-+ src_or_dst(bdiropq) = au_dbdiropq(d);
-+ src_or_dst(hinode) = au_hi(src_or_dst(inode), a->btgt);
-+ au_hn_inode_lock_nested(src_or_dst(hinode), AuLsc_I_CHILD);
-+ diropq = au_diropq_create(d, a->btgt);
-+ au_hn_inode_unlock(src_or_dst(hinode));
-+ if (IS_ERR(diropq))
-+ err = PTR_ERR(diropq);
-+ else
-+ dput(diropq);
++/*
++ * inode operations
++ */
+
-+#undef src_or_dst_
-+ return err;
-+}
++#ifndef __AUFS_INODE_H__
++#define __AUFS_INODE_H__
+
-+static int au_ren_diropq(struct au_ren_args *a)
-+{
-+ int err;
-+ unsigned char always;
-+ struct dentry *d;
++#ifdef __KERNEL__
+
-+ err = 0;
-+ d = a->dst_dentry; /* already renamed on the branch */
-+ always = !!au_opt_test(au_mntflags(d->d_sb), ALWAYS_DIROPQ);
-+ if (au_ftest_ren(a->auren_flags, ISDIR_SRC)
-+ && !au_ftest_ren(a->auren_flags, DIRREN)
-+ && a->btgt != au_dbdiropq(a->src_dentry)
-+ && (a->dst_wh_dentry
-+ || a->btgt <= au_dbdiropq(d)
-+ /* hide the lower to keep xino */
-+ /* the lowers may not be a dir, but we hide them anyway */
-+ || a->btgt < au_dbbot(d)
-+ || always)) {
-+ AuDbg("here\n");
-+ err = au_ren_do_diropq(a, AuSRC);
-+ if (unlikely(err))
-+ goto out;
-+ au_fset_ren(a->auren_flags, DIROPQ_SRC);
-+ }
-+ if (!a->exchange)
-+ goto out; /* success */
++#include <linux/fsnotify.h>
++#include "rwsem.h"
+
-+ d = a->src_dentry; /* already renamed on the branch */
-+ if (au_ftest_ren(a->auren_flags, ISDIR_DST)
-+ && a->btgt != au_dbdiropq(a->dst_dentry)
-+ && (a->btgt < au_dbdiropq(d)
-+ || a->btgt < au_dbbot(d)
-+ || always)) {
-+ AuDbgDentry(a->src_dentry);
-+ AuDbgDentry(a->dst_dentry);
-+ err = au_ren_do_diropq(a, AuDST);
-+ if (unlikely(err))
-+ goto out_rev_src;
-+ au_fset_ren(a->auren_flags, DIROPQ_DST);
-+ }
-+ goto out; /* success */
++struct vfsmount;
+
-+out_rev_src:
-+ AuDbg("err %d, reverting src\n", err);
-+ au_ren_rev_diropq(err, a);
-+out:
-+ return err;
-+}
++struct au_hnotify {
++#ifdef CONFIG_AUFS_HNOTIFY
++#ifdef CONFIG_AUFS_HFSNOTIFY
++ /* never use fsnotify_add_vfsmount_mark() */
++ struct fsnotify_mark hn_mark;
++#endif
++ struct inode *hn_aufs_inode; /* no get/put */
++ struct rcu_head rcu;
++#endif
++} ____cacheline_aligned_in_smp;
+
-+static int do_rename(struct au_ren_args *a)
-+{
-+ int err;
-+ struct dentry *d, *h_d;
-+ struct inode *h_inode;
++struct au_hinode {
++ struct inode *hi_inode;
++ aufs_bindex_t hi_id;
++#ifdef CONFIG_AUFS_HNOTIFY
++ struct au_hnotify *hi_notify;
++#endif
+
-+ if (!a->exchange) {
-+ /* prepare workqueue args for asynchronous rmdir */
-+ h_d = a->dst_h_dentry;
-+ if (au_ftest_ren(a->auren_flags, ISDIR_DST)
-+ /* && !au_ftest_ren(a->auren_flags, DIRREN) */
-+ && d_is_positive(h_d)) {
-+ err = -ENOMEM;
-+ a->thargs = au_whtmp_rmdir_alloc(a->src_dentry->d_sb,
-+ GFP_NOFS);
-+ if (unlikely(!a->thargs))
-+ goto out;
-+ a->h_dst = dget(h_d);
-+ }
++ /* reference to the copied-up whiteout with get/put */
++ struct dentry *hi_whdentry;
++};
+
-+ /* create whiteout for src_dentry */
-+ if (au_ftest_ren(a->auren_flags, WHSRC)) {
-+ a->src_bwh = au_dbwh(a->src_dentry);
-+ AuDebugOn(a->src_bwh >= 0);
-+ a->src_wh_dentry = au_wh_create(a->src_dentry, a->btgt,
-+ a->src_h_parent);
-+ err = PTR_ERR(a->src_wh_dentry);
-+ if (IS_ERR(a->src_wh_dentry))
-+ goto out_thargs;
-+ }
++/* ig_flags */
++#define AuIG_HALF_REFRESHED 1
++#define au_ig_ftest(flags, name) ((flags) & AuIG_##name)
++#define au_ig_fset(flags, name) \
++ do { (flags) |= AuIG_##name; } while (0)
++#define au_ig_fclr(flags, name) \
++ do { (flags) &= ~AuIG_##name; } while (0)
+
-+ /* lookup whiteout for dentry */
-+ if (au_ftest_ren(a->auren_flags, WHDST)) {
-+ h_d = au_wh_lkup(a->dst_h_parent,
-+ &a->dst_dentry->d_name, a->br);
-+ err = PTR_ERR(h_d);
-+ if (IS_ERR(h_d))
-+ goto out_whsrc;
-+ if (d_is_negative(h_d))
-+ dput(h_d);
-+ else
-+ a->dst_wh_dentry = h_d;
-+ }
++struct au_iigen {
++ spinlock_t ig_spin;
++ __u32 ig_generation, ig_flags;
++};
+
-+ /* rename dentry to tmpwh */
-+ if (a->thargs) {
-+ err = au_whtmp_ren(a->dst_h_dentry, a->br);
-+ if (unlikely(err))
-+ goto out_whdst;
++struct au_vdir;
++struct au_iinfo {
++ struct au_iigen ii_generation;
++ struct super_block *ii_hsb1; /* no get/put */
+
-+ d = a->dst_dentry;
-+ au_set_h_dptr(d, a->btgt, NULL);
-+ err = au_lkup_neg(d, a->btgt, /*wh*/0);
-+ if (unlikely(err))
-+ goto out_whtmp;
-+ a->dst_h_dentry = au_h_dptr(d, a->btgt);
-+ }
-+ }
++ struct au_rwsem ii_rwsem;
++ aufs_bindex_t ii_btop, ii_bbot;
++ __u32 ii_higen;
++ struct au_hinode *ii_hinode;
++ struct au_vdir *ii_vdir;
++};
+
-+ BUG_ON(d_is_positive(a->dst_h_dentry) && a->src_btop != a->btgt);
-+#if 0 /* debugging */
-+ BUG_ON(!au_ftest_ren(a->auren_flags, DIRREN)
-+ && d_is_positive(a->dst_h_dentry)
-+ && a->src_btop != a->btgt);
-+#endif
++struct au_icntnr {
++ struct au_iinfo iinfo;
++ struct inode vfs_inode;
++ struct hlist_bl_node plink;
++ struct rcu_head rcu;
++} ____cacheline_aligned_in_smp;
+
-+ /* rename by vfs_rename or cpup */
-+ err = au_ren_or_cpup(a);
-+ if (unlikely(err))
-+ /* leave the copied-up one */
-+ goto out_whtmp;
++/* au_pin flags */
++#define AuPin_DI_LOCKED 1
++#define AuPin_MNT_WRITE (1 << 1)
++#define au_ftest_pin(flags, name) ((flags) & AuPin_##name)
++#define au_fset_pin(flags, name) \
++ do { (flags) |= AuPin_##name; } while (0)
++#define au_fclr_pin(flags, name) \
++ do { (flags) &= ~AuPin_##name; } while (0)
+
-+ /* make dir opaque */
-+ err = au_ren_diropq(a);
-+ if (unlikely(err))
-+ goto out_rename;
++struct au_pin {
++ /* input */
++ struct dentry *dentry;
++ unsigned int udba;
++ unsigned char lsc_di, lsc_hi, flags;
++ aufs_bindex_t bindex;
+
-+ /* update target timestamps */
-+ if (a->exchange) {
-+ AuDebugOn(au_dbtop(a->dst_dentry) != a->btgt);
-+ a->h_path.dentry = au_h_dptr(a->dst_dentry, a->btgt);
-+ vfsub_update_h_iattr(&a->h_path, /*did*/NULL); /*ignore*/
-+ h_inode = d_inode(a->h_path.dentry);
-+ inode_set_ctime_to_ts(a->dst_inode, inode_get_ctime(h_inode));
-+ }
-+ AuDebugOn(au_dbtop(a->src_dentry) != a->btgt);
-+ a->h_path.dentry = au_h_dptr(a->src_dentry, a->btgt);
-+ vfsub_update_h_iattr(&a->h_path, /*did*/NULL); /*ignore*/
-+ h_inode = d_inode(a->h_path.dentry);
-+ inode_set_ctime_to_ts(a->src_inode, inode_get_ctime(h_inode));
++ /* output */
++ struct dentry *parent;
++ struct au_hinode *hdir;
++ struct vfsmount *h_mnt;
+
-+ if (!a->exchange) {
-+ /* remove whiteout for dentry */
-+ if (a->dst_wh_dentry) {
-+ a->h_path.dentry = a->dst_wh_dentry;
-+ err = au_wh_unlink_dentry(a->dst_h_dir, &a->h_path,
-+ a->dst_dentry);
-+ if (unlikely(err))
-+ goto out_diropq;
-+ }
++ /* temporary unlock/relock for copyup */
++ struct dentry *h_dentry, *h_parent;
++ struct au_branch *br;
++ struct task_struct *task;
++};
+
-+ /* remove whtmp */
-+ if (a->thargs)
-+ au_ren_del_whtmp(a); /* ignore this error */
++void au_pin_hdir_unlock(struct au_pin *p);
++int au_pin_hdir_lock(struct au_pin *p);
++int au_pin_hdir_relock(struct au_pin *p);
++void au_pin_hdir_acquire_nest(struct au_pin *p);
++void au_pin_hdir_release(struct au_pin *p);
+
-+ au_fhsm_wrote(a->src_dentry->d_sb, a->btgt, /*force*/0);
-+ }
-+ err = 0;
-+ goto out_success;
++/* ---------------------------------------------------------------------- */
+
-+out_diropq:
-+ au_ren_rev_diropq(err, a);
-+out_rename:
-+ au_ren_rev_rename(err, a);
-+ dput(a->h_dst);
-+out_whtmp:
-+ if (a->thargs)
-+ au_ren_rev_whtmp(err, a);
-+out_whdst:
-+ dput(a->dst_wh_dentry);
-+ a->dst_wh_dentry = NULL;
-+out_whsrc:
-+ if (a->src_wh_dentry)
-+ au_ren_rev_whsrc(err, a);
-+out_success:
-+ dput(a->src_wh_dentry);
-+ dput(a->dst_wh_dentry);
-+out_thargs:
-+ if (a->thargs) {
-+ dput(a->h_dst);
-+ au_whtmp_rmdir_free(a->thargs);
-+ a->thargs = NULL;
-+ }
-+out:
-+ return err;
++static inline struct au_iinfo *au_ii(struct inode *inode)
++{
++ BUG_ON(is_bad_inode(inode));
++ return &(container_of(inode, struct au_icntnr, vfs_inode)->iinfo);
+}
+
+/* ---------------------------------------------------------------------- */
+
-+/*
-+ * test if @dentry dir can be rename destination or not.
-+ * success means, it is a logically empty dir.
-+ */
-+static int may_rename_dstdir(struct dentry *dentry, struct au_nhash *whlist)
++/* inode.c */
++struct inode *au_igrab(struct inode *inode);
++void au_refresh_iop(struct inode *inode, int force_getattr);
++int au_refresh_hinode_self(struct inode *inode);
++int au_refresh_hinode(struct inode *inode, struct dentry *dentry);
++int au_ino(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
++ unsigned int d_type, ino_t *ino);
++struct inode *au_new_inode(struct dentry *dentry, int must_new);
++int au_test_ro(struct super_block *sb, aufs_bindex_t bindex,
++ struct inode *inode);
++int au_test_h_perm(struct mnt_idmap *h_idmap, struct inode *h_inode,
++ int mask);
++int au_test_h_perm_sio(struct mnt_idmap *h_idmap, struct inode *h_inode,
++ int mask);
++
++static inline int au_wh_ino(struct super_block *sb, aufs_bindex_t bindex,
++ ino_t h_ino, unsigned int d_type, ino_t *ino)
+{
-+ return au_test_empty(dentry, whlist);
++#ifdef CONFIG_AUFS_SHWH
++ return au_ino(sb, bindex, h_ino, d_type, ino);
++#else
++ return 0;
++#endif
+}
+
-+/*
-+ * test if @a->src_dentry dir can be rename source or not.
-+ * if it can, return 0.
-+ * success means,
-+ * - it is a logically empty dir.
-+ * - or, it exists on writable branch and has no children including whiteouts
-+ * on the lower branch unless DIRREN is on.
-+ */
-+static int may_rename_srcdir(struct au_ren_args *a)
-+{
-+ int err;
-+ unsigned int rdhash;
-+ aufs_bindex_t btop, btgt;
-+ struct dentry *dentry;
-+ struct super_block *sb;
-+ struct au_sbinfo *sbinfo;
++/* i_op.c */
++enum {
++ AuIop_SYMLINK,
++ AuIop_DIR,
++ AuIop_OTHER,
++ AuIop_Last
++};
++extern struct inode_operations aufs_iop[AuIop_Last], /* not const */
++ aufs_iop_nogetattr[AuIop_Last];
+
-+ dentry = a->src_dentry;
-+ sb = dentry->d_sb;
-+ sbinfo = au_sbi(sb);
-+ if (au_opt_test(sbinfo->si_mntflags, DIRREN))
-+ au_fset_ren(a->auren_flags, DIRREN);
++/* au_wr_dir flags */
++#define AuWrDir_ADD_ENTRY 1
++#define AuWrDir_ISDIR (1 << 1)
++#define AuWrDir_TMPFILE (1 << 2)
++#define au_ftest_wrdir(flags, name) ((flags) & AuWrDir_##name)
++#define au_fset_wrdir(flags, name) \
++ do { (flags) |= AuWrDir_##name; } while (0)
++#define au_fclr_wrdir(flags, name) \
++ do { (flags) &= ~AuWrDir_##name; } while (0)
++
++struct au_wr_dir_args {
++ aufs_bindex_t force_btgt;
++ unsigned char flags;
++};
++int au_wr_dir(struct dentry *dentry, struct dentry *src_dentry,
++ struct au_wr_dir_args *args);
++
++struct dentry *au_pinned_h_parent(struct au_pin *pin);
++void au_pin_init(struct au_pin *pin, struct dentry *dentry,
++ aufs_bindex_t bindex, int lsc_di, int lsc_hi,
++ unsigned int udba, unsigned char flags);
++int au_pin(struct au_pin *pin, struct dentry *dentry, aufs_bindex_t bindex,
++ unsigned int udba, unsigned char flags) __must_check;
++int au_do_pin(struct au_pin *pin) __must_check;
++void au_unpin(struct au_pin *pin);
++int au_reval_for_attr(struct dentry *dentry, unsigned int sigen);
++
++#define AuIcpup_DID_CPUP 1
++#define au_ftest_icpup(flags, name) ((flags) & AuIcpup_##name)
++#define au_fset_icpup(flags, name) \
++ do { (flags) |= AuIcpup_##name; } while (0)
++#define au_fclr_icpup(flags, name) \
++ do { (flags) &= ~AuIcpup_##name; } while (0)
+
-+ btgt = a->btgt;
-+ btop = au_dbtop(dentry);
-+ if (btop != btgt) {
-+ struct au_nhash whlist;
++struct au_icpup_args {
++ unsigned char flags;
++ unsigned char pin_flags;
++ aufs_bindex_t btgt;
++ unsigned int udba;
++ struct au_pin pin;
++ struct path h_path;
++ struct inode *h_inode;
++};
+
-+ SiMustAnyLock(sb);
-+ rdhash = sbinfo->si_rdhash;
-+ if (!rdhash)
-+ rdhash = au_rdhash_est(au_dir_size(/*file*/NULL,
-+ dentry));
-+ err = au_nhash_alloc(&whlist, rdhash, GFP_NOFS);
-+ if (unlikely(err))
-+ goto out;
-+ err = au_test_empty(dentry, &whlist);
-+ au_nhash_wh_free(&whlist);
-+ goto out;
-+ }
++int au_pin_and_icpup(struct dentry *dentry, struct iattr *ia,
++ struct au_icpup_args *a);
+
-+ if (btop == au_dbtaildir(dentry))
-+ return 0; /* success */
++int au_h_path_getattr(struct dentry *dentry, struct inode *inode, int force,
++ struct path *h_path, int locked);
+
-+ err = au_test_empty_lower(dentry);
++/* i_op_add.c */
++int au_may_add(struct dentry *dentry, aufs_bindex_t bindex,
++ struct dentry *h_parent, int isdir);
++int aufs_mknod(struct mnt_idmap *idmap, struct inode *dir,
++ struct dentry *dentry, umode_t mode, dev_t dev);
++int aufs_symlink(struct mnt_idmap *idmap, struct inode *dir,
++ struct dentry *dentry, const char *symname);
++int aufs_create(struct mnt_idmap *idmap, struct inode *dir,
++ struct dentry *dentry, umode_t mode, bool want_excl);
++struct vfsub_aopen_args;
++int au_aopen_or_create(struct inode *dir, struct dentry *dentry,
++ struct vfsub_aopen_args *args);
++int aufs_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
++ struct file *file, umode_t mode);
++int aufs_link(struct dentry *src_dentry, struct inode *dir,
++ struct dentry *dentry);
++int aufs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
++ struct dentry *dentry, umode_t mode);
+
-+out:
-+ if (err == -ENOTEMPTY) {
-+ if (au_ftest_ren(a->auren_flags, DIRREN)) {
-+ err = 0;
-+ } else {
-+ AuWarn1("renaming dir who has child(ren) on multiple "
-+ "branches, is not supported\n");
-+ err = -EXDEV;
-+ }
-+ }
-+ return err;
-+}
++/* i_op_del.c */
++int au_wr_dir_need_wh(struct dentry *dentry, int isdir, aufs_bindex_t *bcpup);
++int au_may_del(struct dentry *dentry, aufs_bindex_t bindex,
++ struct dentry *h_parent, int isdir);
++int aufs_unlink(struct inode *dir, struct dentry *dentry);
++int aufs_rmdir(struct inode *dir, struct dentry *dentry);
+
-+/* side effect: sets whlist and h_dentry */
-+static int au_ren_may_dir(struct au_ren_args *a)
-+{
-+ int err;
-+ unsigned int rdhash;
-+ struct dentry *d;
++/* i_op_ren.c */
++int au_wbr(struct dentry *dentry, aufs_bindex_t btgt);
++int aufs_rename(struct mnt_idmap *idmap,
++ struct inode *_src_dir, struct dentry *_src_dentry,
++ struct inode *_dst_dir, struct dentry *_dst_dentry,
++ unsigned int _flags);
+
-+ d = a->dst_dentry;
-+ SiMustAnyLock(d->d_sb);
++/* iinfo.c */
++struct inode *au_h_iptr(struct inode *inode, aufs_bindex_t bindex);
++void au_hiput(struct au_hinode *hinode);
++void au_set_hi_wh(struct inode *inode, aufs_bindex_t bindex,
++ struct dentry *h_wh);
++unsigned int au_hi_flags(struct inode *inode, int isdir);
+
-+ err = 0;
-+ if (au_ftest_ren(a->auren_flags, ISDIR_DST) && a->dst_inode) {
-+ rdhash = au_sbi(d->d_sb)->si_rdhash;
-+ if (!rdhash)
-+ rdhash = au_rdhash_est(au_dir_size(/*file*/NULL, d));
-+ err = au_nhash_alloc(&a->whlist, rdhash, GFP_NOFS);
-+ if (unlikely(err))
-+ goto out;
++/* hinode flags */
++#define AuHi_XINO 1
++#define AuHi_HNOTIFY (1 << 1)
++#define au_ftest_hi(flags, name) ((flags) & AuHi_##name)
++#define au_fset_hi(flags, name) \
++ do { (flags) |= AuHi_##name; } while (0)
++#define au_fclr_hi(flags, name) \
++ do { (flags) &= ~AuHi_##name; } while (0)
+
-+ if (!a->exchange) {
-+ au_set_dbtop(d, a->dst_btop);
-+ err = may_rename_dstdir(d, &a->whlist);
-+ au_set_dbtop(d, a->btgt);
-+ } else
-+ err = may_rename_srcdir(a);
-+ }
-+ a->dst_h_dentry = au_h_dptr(d, au_dbtop(d));
-+ if (unlikely(err))
-+ goto out;
++#ifndef CONFIG_AUFS_HNOTIFY
++#undef AuHi_HNOTIFY
++#define AuHi_HNOTIFY 0
++#endif
+
-+ d = a->src_dentry;
-+ a->src_h_dentry = au_h_dptr(d, au_dbtop(d));
-+ if (au_ftest_ren(a->auren_flags, ISDIR_SRC)) {
-+ err = may_rename_srcdir(a);
-+ if (unlikely(err)) {
-+ au_nhash_wh_free(&a->whlist);
-+ a->whlist.nh_num = 0;
-+ }
-+ }
-+out:
-+ return err;
-+}
++void au_set_h_iptr(struct inode *inode, aufs_bindex_t bindex,
++ struct inode *h_inode, unsigned int flags);
+
-+/* ---------------------------------------------------------------------- */
++void au_update_iigen(struct inode *inode, int half);
++void au_update_ibrange(struct inode *inode, int do_put_zero);
+
-+/*
-+ * simple tests for rename.
-+ * following the checks in vfs, plus the parent-child relationship.
-+ */
-+static int au_may_ren(struct au_ren_args *a)
-+{
-+ int err, isdir;
-+ struct inode *h_inode;
++void au_icntnr_init_once(void *_c);
++void au_hinode_init(struct au_hinode *hinode);
++int au_iinfo_init(struct inode *inode);
++void au_iinfo_fin(struct inode *inode);
++int au_hinode_realloc(struct au_iinfo *iinfo, int nbr, int may_shrink);
+
-+ if (a->src_btop == a->btgt) {
-+ err = au_may_del(a->src_dentry, a->btgt, a->src_h_parent,
-+ au_ftest_ren(a->auren_flags, ISDIR_SRC));
-+ if (unlikely(err))
-+ goto out;
-+ err = -EINVAL;
-+ if (unlikely(a->src_h_dentry == a->h_trap))
-+ goto out;
-+ }
++#ifdef CONFIG_PROC_FS
++/* plink.c */
++int au_plink_maint(struct super_block *sb, int flags);
++struct au_sbinfo;
++void au_plink_maint_leave(struct au_sbinfo *sbinfo);
++int au_plink_maint_enter(struct super_block *sb);
++#ifdef CONFIG_AUFS_DEBUG
++void au_plink_list(struct super_block *sb);
++#else
++AuStubVoid(au_plink_list, struct super_block *sb)
++#endif
++int au_plink_test(struct inode *inode);
++struct dentry *au_plink_lkup(struct inode *inode, aufs_bindex_t bindex);
++void au_plink_append(struct inode *inode, aufs_bindex_t bindex,
++ struct dentry *h_dentry);
++void au_plink_put(struct super_block *sb, int verbose);
++void au_plink_clean(struct super_block *sb, int verbose);
++void au_plink_half_refresh(struct super_block *sb, aufs_bindex_t br_id);
++#else
++AuStubInt0(au_plink_maint, struct super_block *sb, int flags);
++AuStubVoid(au_plink_maint_leave, struct au_sbinfo *sbinfo);
++AuStubInt0(au_plink_maint_enter, struct super_block *sb);
++AuStubVoid(au_plink_list, struct super_block *sb);
++AuStubInt0(au_plink_test, struct inode *inode);
++AuStub(struct dentry *, au_plink_lkup, return NULL,
++ struct inode *inode, aufs_bindex_t bindex);
++AuStubVoid(au_plink_append, struct inode *inode, aufs_bindex_t bindex,
++ struct dentry *h_dentry);
++AuStubVoid(au_plink_put, struct super_block *sb, int verbose);
++AuStubVoid(au_plink_clean, struct super_block *sb, int verbose);
++AuStubVoid(au_plink_half_refresh, struct super_block *sb, aufs_bindex_t br_id);
++#endif /* CONFIG_PROC_FS */
+
-+ err = 0;
-+ if (a->dst_btop != a->btgt)
-+ goto out;
++#ifdef CONFIG_AUFS_XATTR
++/* xattr.c */
++int au_cpup_xattr(struct path *h_dst, struct path *h_src, int ignore_flags,
++ unsigned int verbose);
++ssize_t aufs_listxattr(struct dentry *dentry, char *list, size_t size);
++void au_xattr_init(struct super_block *sb);
++#else
++AuStubInt0(au_cpup_xattr, struct path *h_dst, struct path *h_src,
++ int ignore_flags, unsigned int verbose);
++AuStubVoid(au_xattr_init, struct super_block *sb);
++#endif
+
-+ err = -ENOTEMPTY;
-+ if (unlikely(a->dst_h_dentry == a->h_trap))
-+ goto out;
++#ifdef CONFIG_FS_POSIX_ACL
++struct posix_acl *aufs_get_inode_acl(struct inode *inode, int type, bool rcu);
++struct posix_acl *aufs_get_acl(struct mnt_idmap *idmap,
++ struct dentry *dentry, int type);
++int aufs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
++ struct posix_acl *acl, int type);
++#endif
+
-+ err = -EIO;
-+ isdir = !!au_ftest_ren(a->auren_flags, ISDIR_DST);
-+ if (d_really_is_negative(a->dst_dentry)) {
-+ if (d_is_negative(a->dst_h_dentry))
-+ err = au_may_add(a->dst_dentry, a->btgt,
-+ a->dst_h_parent, isdir);
-+ } else {
-+ if (unlikely(d_is_negative(a->dst_h_dentry)))
-+ goto out;
-+ h_inode = d_inode(a->dst_h_dentry);
-+ if (h_inode->i_nlink)
-+ err = au_may_del(a->dst_dentry, a->btgt,
-+ a->dst_h_parent, isdir);
-+ }
++#if IS_ENABLED(CONFIG_AUFS_XATTR) || IS_ENABLED(CONFIG_FS_POSIX_ACL)
++enum {
++ AU_XATTR_SET,
++ AU_ACL_SET
++};
+
-+out:
-+ if (unlikely(err == -ENOENT || err == -EEXIST))
-+ err = -EIO;
-+ AuTraceErr(err);
-+ return err;
-+}
++struct au_sxattr {
++ int type;
++ union {
++ struct {
++ const char *name;
++ const void *value;
++ size_t size;
++ int flags;
++ } set;
++ struct {
++ struct posix_acl *acl;
++ int type;
++ } acl_set;
++ } u;
++};
++ssize_t au_sxattr(struct dentry *dentry, struct inode *inode,
++ struct au_sxattr *arg);
++#endif
+
+/* ---------------------------------------------------------------------- */
+
++/* lock subclass for iinfo */
++enum {
++ AuLsc_II_CHILD, /* child first */
++ AuLsc_II_CHILD2, /* rename(2), link(2), and cpup at hnotify */
++ AuLsc_II_CHILD3, /* copyup dirs */
++ AuLsc_II_PARENT, /* see AuLsc_I_PARENT in vfsub.h */
++ AuLsc_II_PARENT2,
++ AuLsc_II_PARENT3, /* copyup dirs */
++ AuLsc_II_NEW_CHILD
++};
++
+/*
-+ * locking order
-+ * (VFS)
-+ * - src_dir and dir by lock_rename()
-+ * - inode if exists
-+ * (aufs)
-+ * - lock all
-+ * + src_dentry and dentry by aufs_read_and_write_lock2() which calls,
-+ * + si_read_lock
-+ * + di_write_lock2_child()
-+ * + di_write_lock_child()
-+ * + ii_write_lock_child()
-+ * + di_write_lock_child2()
-+ * + ii_write_lock_child2()
-+ * + src_parent and parent
-+ * + di_write_lock_parent()
-+ * + ii_write_lock_parent()
-+ * + di_write_lock_parent2()
-+ * + ii_write_lock_parent2()
-+ * + lower src_dir and dir by vfsub_lock_rename()
-+ * + verify the every relationships between child and parent. if any
-+ * of them failed, unlock all and return -EBUSY.
++ * ii_read_lock_child, ii_write_lock_child,
++ * ii_read_lock_child2, ii_write_lock_child2,
++ * ii_read_lock_child3, ii_write_lock_child3,
++ * ii_read_lock_parent, ii_write_lock_parent,
++ * ii_read_lock_parent2, ii_write_lock_parent2,
++ * ii_read_lock_parent3, ii_write_lock_parent3,
++ * ii_read_lock_new_child, ii_write_lock_new_child,
+ */
-+static void au_ren_unlock(struct au_ren_args *a)
-+{
-+ vfsub_unlock_rename(a->src_h_parent, a->src_hdir,
-+ a->dst_h_parent, a->dst_hdir);
-+ if (au_ftest_ren(a->auren_flags, DIRREN)
-+ && a->h_root)
-+ au_hn_inode_unlock(a->h_root);
-+ if (au_ftest_ren(a->auren_flags, MNT_WRITE))
-+ vfsub_mnt_drop_write(au_br_mnt(a->br));
++#define AuReadLockFunc(name, lsc) \
++static inline void ii_read_lock_##name(struct inode *i) \
++{ \
++ au_rw_read_lock_nested(&au_ii(i)->ii_rwsem, AuLsc_II_##lsc); \
+}
+
-+static int au_ren_lock(struct au_ren_args *a)
-+{
-+ int err;
-+ unsigned int udba;
++#define AuWriteLockFunc(name, lsc) \
++static inline void ii_write_lock_##name(struct inode *i) \
++{ \
++ au_rw_write_lock_nested(&au_ii(i)->ii_rwsem, AuLsc_II_##lsc); \
++}
+
-+ err = 0;
-+ a->src_h_parent = au_h_dptr(a->src_parent, a->btgt);
-+ a->src_hdir = au_hi(a->src_dir, a->btgt);
-+ a->dst_h_parent = au_h_dptr(a->dst_parent, a->btgt);
-+ a->dst_hdir = au_hi(a->dst_dir, a->btgt);
++#define AuRWLockFuncs(name, lsc) \
++ AuReadLockFunc(name, lsc) \
++ AuWriteLockFunc(name, lsc)
+
-+ err = vfsub_mnt_want_write(au_br_mnt(a->br));
-+ if (unlikely(err))
-+ goto out;
-+ au_fset_ren(a->auren_flags, MNT_WRITE);
-+ if (au_ftest_ren(a->auren_flags, DIRREN)) {
-+ struct dentry *root;
-+ struct inode *dir;
++AuRWLockFuncs(child, CHILD);
++AuRWLockFuncs(child2, CHILD2);
++AuRWLockFuncs(child3, CHILD3);
++AuRWLockFuncs(parent, PARENT);
++AuRWLockFuncs(parent2, PARENT2);
++AuRWLockFuncs(parent3, PARENT3);
++AuRWLockFuncs(new_child, NEW_CHILD);
+
-+ /*
-+ * sbinfo is already locked, so this ii_read_lock is
-+ * unnecessary. but our debugging feature checks it.
-+ */
-+ root = a->src_inode->i_sb->s_root;
-+ if (root != a->src_parent && root != a->dst_parent) {
-+ dir = d_inode(root);
-+ ii_read_lock_parent3(dir);
-+ a->h_root = au_hi(dir, a->btgt);
-+ ii_read_unlock(dir);
-+ au_hn_inode_lock_nested(a->h_root, AuLsc_I_PARENT3);
-+ }
-+ }
-+ a->h_trap = vfsub_lock_rename(a->src_h_parent, a->src_hdir,
-+ a->dst_h_parent, a->dst_hdir);
-+ udba = au_opt_udba(a->src_dentry->d_sb);
-+ if (unlikely(a->src_hdir->hi_inode != d_inode(a->src_h_parent)
-+ || a->dst_hdir->hi_inode != d_inode(a->dst_h_parent)))
-+ err = au_busy_or_stale();
-+ if (!err && au_dbtop(a->src_dentry) == a->btgt)
-+ err = au_h_verify(a->src_h_dentry, udba,
-+ d_inode(a->src_h_parent), a->src_h_parent,
-+ a->br);
-+ if (!err && au_dbtop(a->dst_dentry) == a->btgt)
-+ err = au_h_verify(a->dst_h_dentry, udba,
-+ d_inode(a->dst_h_parent), a->dst_h_parent,
-+ a->br);
-+ if (!err)
-+ goto out; /* success */
++#undef AuReadLockFunc
++#undef AuWriteLockFunc
++#undef AuRWLockFuncs
+
-+ err = au_busy_or_stale();
-+ au_ren_unlock(a);
++#define ii_read_unlock(i) au_rw_read_unlock(&au_ii(i)->ii_rwsem)
++#define ii_write_unlock(i) au_rw_write_unlock(&au_ii(i)->ii_rwsem)
++#define ii_downgrade_lock(i) au_rw_dgrade_lock(&au_ii(i)->ii_rwsem)
+
-+out:
-+ return err;
-+}
++#define IiMustNoWaiters(i) AuRwMustNoWaiters(&au_ii(i)->ii_rwsem)
++#define IiMustAnyLock(i) AuRwMustAnyLock(&au_ii(i)->ii_rwsem)
++#define IiMustWriteLock(i) AuRwMustWriteLock(&au_ii(i)->ii_rwsem)
+
+/* ---------------------------------------------------------------------- */
+
-+static void au_ren_refresh_dir(struct au_ren_args *a)
++static inline void au_icntnr_init(struct au_icntnr *c)
+{
-+ struct inode *dir;
-+
-+ dir = a->dst_dir;
-+ inode_inc_iversion(dir);
-+ if (au_ftest_ren(a->auren_flags, ISDIR_SRC)) {
-+ /* is this updating defined in POSIX? */
-+ au_cpup_attr_timesizes(a->src_inode);
-+ au_cpup_attr_nlink(dir, /*force*/1);
-+ }
-+ au_dir_ts(dir, a->btgt);
-+
-+ if (a->exchange) {
-+ dir = a->src_dir;
-+ inode_inc_iversion(dir);
-+ if (au_ftest_ren(a->auren_flags, ISDIR_DST)) {
-+ /* is this updating defined in POSIX? */
-+ au_cpup_attr_timesizes(a->dst_inode);
-+ au_cpup_attr_nlink(dir, /*force*/1);
-+ }
-+ au_dir_ts(dir, a->btgt);
-+ }
-+
-+ if (au_ftest_ren(a->auren_flags, ISSAMEDIR))
-+ return;
-+
-+ dir = a->src_dir;
-+ inode_inc_iversion(dir);
-+ if (au_ftest_ren(a->auren_flags, ISDIR_SRC))
-+ au_cpup_attr_nlink(dir, /*force*/1);
-+ au_dir_ts(dir, a->btgt);
++#ifdef CONFIG_AUFS_DEBUG
++ c->vfs_inode.i_mode = 0;
++#endif
+}
+
-+static void au_ren_refresh(struct au_ren_args *a)
++static inline unsigned int au_iigen(struct inode *inode, unsigned int *igflags)
+{
-+ aufs_bindex_t bbot, bindex;
-+ struct dentry *d, *h_d;
-+ struct inode *i, *h_i;
-+ struct super_block *sb;
++ unsigned int gen;
++ struct au_iinfo *iinfo;
++ struct au_iigen *iigen;
+
-+ d = a->dst_dentry;
-+ d_drop(d);
-+ if (a->h_dst)
-+ /* already dget-ed by au_ren_or_cpup() */
-+ au_set_h_dptr(d, a->btgt, a->h_dst);
++ iinfo = au_ii(inode);
++ iigen = &iinfo->ii_generation;
++ spin_lock(&iigen->ig_spin);
++ if (igflags)
++ *igflags = iigen->ig_flags;
++ gen = iigen->ig_generation;
++ spin_unlock(&iigen->ig_spin);
+
-+ i = a->dst_inode;
-+ if (i) {
-+ if (!a->exchange) {
-+ if (!au_ftest_ren(a->auren_flags, ISDIR_DST))
-+ vfsub_drop_nlink(i);
-+ else {
-+ vfsub_dead_dir(i);
-+ au_cpup_attr_timesizes(i);
-+ }
-+ au_update_dbrange(d, /*do_put_zero*/1);
-+ } else
-+ au_cpup_attr_nlink(i, /*force*/1);
-+ } else {
-+ bbot = a->btgt;
-+ for (bindex = au_dbtop(d); bindex < bbot; bindex++)
-+ au_set_h_dptr(d, bindex, NULL);
-+ bbot = au_dbbot(d);
-+ for (bindex = a->btgt + 1; bindex <= bbot; bindex++)
-+ au_set_h_dptr(d, bindex, NULL);
-+ au_update_dbrange(d, /*do_put_zero*/0);
-+ }
++ return gen;
++}
+
-+ if (a->exchange
-+ || au_ftest_ren(a->auren_flags, DIRREN)) {
-+ d_drop(a->src_dentry);
-+ if (au_ftest_ren(a->auren_flags, DIRREN))
-+ au_set_dbwh(a->src_dentry, -1);
-+ return;
-+ }
++/* tiny test for inode number */
++/* tmpfs generation is too rough */
++static inline int au_test_higen(struct inode *inode, struct inode *h_inode)
++{
++ struct au_iinfo *iinfo;
+
-+ d = a->src_dentry;
-+ au_set_dbwh(d, -1);
-+ bbot = au_dbbot(d);
-+ for (bindex = a->btgt + 1; bindex <= bbot; bindex++) {
-+ h_d = au_h_dptr(d, bindex);
-+ if (h_d)
-+ au_set_h_dptr(d, bindex, NULL);
-+ }
-+ au_set_dbbot(d, a->btgt);
++ iinfo = au_ii(inode);
++ AuRwMustAnyLock(&iinfo->ii_rwsem);
++ return !(iinfo->ii_hsb1 == h_inode->i_sb
++ && iinfo->ii_higen == h_inode->i_generation);
++}
+
-+ sb = d->d_sb;
-+ i = a->src_inode;
-+ if (au_opt_test(au_mntflags(sb), PLINK) && au_plink_test(i))
-+ return; /* success */
++static inline void au_iigen_dec(struct inode *inode)
++{
++ struct au_iinfo *iinfo;
++ struct au_iigen *iigen;
+
-+ bbot = au_ibbot(i);
-+ for (bindex = a->btgt + 1; bindex <= bbot; bindex++) {
-+ h_i = au_h_iptr(i, bindex);
-+ if (h_i) {
-+ au_xino_write(sb, bindex, h_i->i_ino, /*ino*/0);
-+ /* ignore this error */
-+ au_set_h_iptr(i, bindex, NULL, 0);
-+ }
-+ }
-+ au_set_ibbot(i, a->btgt);
++ iinfo = au_ii(inode);
++ iigen = &iinfo->ii_generation;
++ spin_lock(&iigen->ig_spin);
++ iigen->ig_generation--;
++ spin_unlock(&iigen->ig_spin);
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+/* mainly for link(2) and rename(2) */
-+int au_wbr(struct dentry *dentry, aufs_bindex_t btgt)
++static inline int au_iigen_test(struct inode *inode, unsigned int sigen)
+{
-+ aufs_bindex_t bdiropq, bwh;
-+ struct dentry *parent;
-+ struct au_branch *br;
++ int err;
+
-+ parent = dentry->d_parent;
-+ IMustLock(d_inode(parent)); /* dir is locked */
++ err = 0;
++ if (unlikely(inode && au_iigen(inode, NULL) != sigen))
++ err = -EIO;
+
-+ bdiropq = au_dbdiropq(parent);
-+ bwh = au_dbwh(dentry);
-+ br = au_sbr(dentry->d_sb, btgt);
-+ if (au_br_rdonly(br)
-+ || (0 <= bdiropq && bdiropq < btgt)
-+ || (0 <= bwh && bwh < btgt))
-+ btgt = -1;
++ return err;
++}
+
-+ AuDbg("btgt %d\n", btgt);
-+ return btgt;
++/* ---------------------------------------------------------------------- */
++
++static inline struct au_hinode *au_hinode(struct au_iinfo *iinfo,
++ aufs_bindex_t bindex)
++{
++ return iinfo->ii_hinode + bindex;
+}
+
-+/* sets src_btop, dst_btop and btgt */
-+static int au_ren_wbr(struct au_ren_args *a)
++static inline int au_is_bad_inode(struct inode *inode)
+{
-+ int err;
-+ struct au_wr_dir_args wr_dir_args = {
-+ /* .force_btgt = -1, */
-+ .flags = AuWrDir_ADD_ENTRY
-+ };
++ return !!(is_bad_inode(inode) || !au_hinode(au_ii(inode), 0));
++}
+
-+ a->src_btop = au_dbtop(a->src_dentry);
-+ a->dst_btop = au_dbtop(a->dst_dentry);
-+ if (au_ftest_ren(a->auren_flags, ISDIR_SRC)
-+ || au_ftest_ren(a->auren_flags, ISDIR_DST))
-+ au_fset_wrdir(wr_dir_args.flags, ISDIR);
-+ wr_dir_args.force_btgt = a->src_btop;
-+ if (a->dst_inode && a->dst_btop < a->src_btop)
-+ wr_dir_args.force_btgt = a->dst_btop;
-+ wr_dir_args.force_btgt = au_wbr(a->dst_dentry, wr_dir_args.force_btgt);
-+ err = au_wr_dir(a->dst_dentry, a->src_dentry, &wr_dir_args);
-+ a->btgt = err;
-+ if (a->exchange)
-+ au_update_dbtop(a->dst_dentry);
++static inline aufs_bindex_t au_ii_br_id(struct inode *inode,
++ aufs_bindex_t bindex)
++{
++ IiMustAnyLock(inode);
++ return au_hinode(au_ii(inode), bindex)->hi_id;
++}
+
-+ return err;
++static inline aufs_bindex_t au_ibtop(struct inode *inode)
++{
++ IiMustAnyLock(inode);
++ return au_ii(inode)->ii_btop;
+}
+
-+static void au_ren_dt(struct au_ren_args *a)
++static inline aufs_bindex_t au_ibbot(struct inode *inode)
+{
-+ a->h_path.dentry = a->src_h_parent;
-+ au_dtime_store(a->src_dt + AuPARENT, a->src_parent, &a->h_path);
-+ if (!au_ftest_ren(a->auren_flags, ISSAMEDIR)) {
-+ a->h_path.dentry = a->dst_h_parent;
-+ au_dtime_store(a->dst_dt + AuPARENT, a->dst_parent, &a->h_path);
-+ }
++ IiMustAnyLock(inode);
++ return au_ii(inode)->ii_bbot;
++}
+
-+ au_fclr_ren(a->auren_flags, DT_DSTDIR);
-+ if (!au_ftest_ren(a->auren_flags, ISDIR_SRC)
-+ && !a->exchange)
-+ return;
++static inline struct au_vdir *au_ivdir(struct inode *inode)
++{
++ IiMustAnyLock(inode);
++ return au_ii(inode)->ii_vdir;
++}
+
-+ a->h_path.dentry = a->src_h_dentry;
-+ au_dtime_store(a->src_dt + AuCHILD, a->src_dentry, &a->h_path);
-+ if (d_is_positive(a->dst_h_dentry)) {
-+ au_fset_ren(a->auren_flags, DT_DSTDIR);
-+ a->h_path.dentry = a->dst_h_dentry;
-+ au_dtime_store(a->dst_dt + AuCHILD, a->dst_dentry, &a->h_path);
-+ }
++static inline struct dentry *au_hi_wh(struct inode *inode, aufs_bindex_t bindex)
++{
++ IiMustAnyLock(inode);
++ return au_hinode(au_ii(inode), bindex)->hi_whdentry;
+}
+
-+static void au_ren_rev_dt(int err, struct au_ren_args *a)
++static inline void au_set_ibtop(struct inode *inode, aufs_bindex_t bindex)
+{
-+ struct dentry *h_d;
-+ struct inode *h_inode;
++ IiMustWriteLock(inode);
++ au_ii(inode)->ii_btop = bindex;
++}
+
-+ au_dtime_revert(a->src_dt + AuPARENT);
-+ if (!au_ftest_ren(a->auren_flags, ISSAMEDIR))
-+ au_dtime_revert(a->dst_dt + AuPARENT);
++static inline void au_set_ibbot(struct inode *inode, aufs_bindex_t bindex)
++{
++ IiMustWriteLock(inode);
++ au_ii(inode)->ii_bbot = bindex;
++}
+
-+ if (au_ftest_ren(a->auren_flags, ISDIR_SRC) && err != -EIO) {
-+ h_d = a->src_dt[AuCHILD].dt_h_path.dentry;
-+ h_inode = d_inode(h_d);
-+ inode_lock_nested(h_inode, AuLsc_I_CHILD);
-+ au_dtime_revert(a->src_dt + AuCHILD);
-+ inode_unlock(h_inode);
++static inline void au_set_ivdir(struct inode *inode, struct au_vdir *vdir)
++{
++ IiMustWriteLock(inode);
++ au_ii(inode)->ii_vdir = vdir;
++}
+
-+ if (au_ftest_ren(a->auren_flags, DT_DSTDIR)) {
-+ h_d = a->dst_dt[AuCHILD].dt_h_path.dentry;
-+ h_inode = d_inode(h_d);
-+ inode_lock_nested(h_inode, AuLsc_I_CHILD);
-+ au_dtime_revert(a->dst_dt + AuCHILD);
-+ inode_unlock(h_inode);
-+ }
-+ }
++static inline struct au_hinode *au_hi(struct inode *inode, aufs_bindex_t bindex)
++{
++ IiMustAnyLock(inode);
++ return au_hinode(au_ii(inode), bindex);
+}
+
+/* ---------------------------------------------------------------------- */
+
-+int aufs_rename(struct mnt_idmap *idmap,
-+ struct inode *_src_dir, struct dentry *_src_dentry,
-+ struct inode *_dst_dir, struct dentry *_dst_dentry,
-+ unsigned int _flags)
++static inline struct dentry *au_pinned_parent(struct au_pin *pin)
+{
-+ int err, lock_flags;
-+ void *rev;
-+ /* reduce stack space */
-+ struct au_ren_args *a;
-+ struct au_pin pin;
++ if (pin)
++ return pin->parent;
++ return NULL;
++}
+
-+ AuDbg("%pd, %pd, 0x%x\n", _src_dentry, _dst_dentry, _flags);
-+ IMustLock(_src_dir);
-+ IMustLock(_dst_dir);
++static inline struct inode *au_pinned_h_dir(struct au_pin *pin)
++{
++ if (pin && pin->hdir)
++ return pin->hdir->hi_inode;
++ return NULL;
++}
+
-+ err = -EINVAL;
-+ if (unlikely(_flags & RENAME_WHITEOUT))
-+ goto out;
++static inline struct au_hinode *au_pinned_hdir(struct au_pin *pin)
++{
++ if (pin)
++ return pin->hdir;
++ return NULL;
++}
+
-+ err = -ENOMEM;
-+ BUILD_BUG_ON(sizeof(*a) > PAGE_SIZE);
-+ a = kzalloc(sizeof(*a), GFP_NOFS);
-+ if (unlikely(!a))
-+ goto out;
++static inline void au_pin_set_dentry(struct au_pin *pin, struct dentry *dentry)
++{
++ if (pin)
++ pin->dentry = dentry;
++}
+
-+ a->flags = _flags;
-+ BUILD_BUG_ON(sizeof(a->exchange) == sizeof(u8)
-+ && RENAME_EXCHANGE > U8_MAX);
-+ a->exchange = _flags & RENAME_EXCHANGE;
-+ a->src_dir = _src_dir;
-+ a->src_dentry = _src_dentry;
-+ a->src_inode = NULL;
-+ if (d_really_is_positive(a->src_dentry))
-+ a->src_inode = d_inode(a->src_dentry);
-+ a->src_parent = a->src_dentry->d_parent; /* dir inode is locked */
-+ a->dst_dir = _dst_dir;
-+ a->dst_dentry = _dst_dentry;
-+ a->dst_inode = NULL;
-+ if (d_really_is_positive(a->dst_dentry))
-+ a->dst_inode = d_inode(a->dst_dentry);
-+ a->dst_parent = a->dst_dentry->d_parent; /* dir inode is locked */
-+ if (a->dst_inode) {
-+ /*
-+ * if EXCHANGE && src is non-dir && dst is dir,
-+ * dst is not locked.
-+ */
-+ /* IMustLock(a->dst_inode); */
-+ au_igrab(a->dst_inode);
++static inline void au_pin_set_parent_lflag(struct au_pin *pin,
++ unsigned char lflag)
++{
++ if (pin) {
++ if (lflag)
++ au_fset_pin(pin->flags, DI_LOCKED);
++ else
++ au_fclr_pin(pin->flags, DI_LOCKED);
+ }
++}
+
-+ err = -ENOTDIR;
-+ lock_flags = AuLock_FLUSH | AuLock_NOPLM | AuLock_GEN;
-+ if (d_is_dir(a->src_dentry)) {
-+ au_fset_ren(a->auren_flags, ISDIR_SRC);
-+ if (unlikely(!a->exchange
-+ && d_really_is_positive(a->dst_dentry)
-+ && !d_is_dir(a->dst_dentry)))
-+ goto out_free;
-+ lock_flags |= AuLock_DIRS;
-+ }
-+ if (a->dst_inode && d_is_dir(a->dst_dentry)) {
-+ au_fset_ren(a->auren_flags, ISDIR_DST);
-+ if (unlikely(!a->exchange
-+ && d_really_is_positive(a->src_dentry)
-+ && !d_is_dir(a->src_dentry)))
-+ goto out_free;
-+ lock_flags |= AuLock_DIRS;
++#if 0 /* reserved */
++static inline void au_pin_set_parent(struct au_pin *pin, struct dentry *parent)
++{
++ if (pin) {
++ dput(pin->parent);
++ pin->parent = dget(parent);
+ }
-+ err = aufs_read_and_write_lock2(a->dst_dentry, a->src_dentry,
-+ lock_flags);
-+ if (unlikely(err))
-+ goto out_free;
++}
++#endif
+
-+ err = au_d_hashed_positive(a->src_dentry);
-+ if (unlikely(err))
-+ goto out_unlock;
-+ err = -ENOENT;
-+ if (a->dst_inode) {
-+ /*
-+ * If it is a dir, VFS unhash it before this
-+ * function. It means we cannot rely upon d_unhashed().
-+ */
-+ if (unlikely(!a->dst_inode->i_nlink))
-+ goto out_unlock;
-+ if (!au_ftest_ren(a->auren_flags, ISDIR_DST)) {
-+ err = au_d_hashed_positive(a->dst_dentry);
-+ if (unlikely(err && !a->exchange))
-+ goto out_unlock;
-+ } else if (unlikely(IS_DEADDIR(a->dst_inode)))
-+ goto out_unlock;
-+ } else if (unlikely(d_unhashed(a->dst_dentry)))
-+ goto out_unlock;
++/* ---------------------------------------------------------------------- */
++
++struct au_branch;
++#ifdef CONFIG_AUFS_HNOTIFY
++struct au_hnotify_op {
++ void (*ctl)(struct au_hinode *hinode, int do_set);
++ int (*alloc)(struct au_hinode *hinode);
+
+ /*
-+ * is it possible?
-+ * yes, it happened (in linux-3.3-rcN) but I don't know why.
-+ * there may exist a problem somewhere else.
++ * if it returns true, the caller should free hinode->hi_notify,
++ * otherwise ->free() frees it.
+ */
-+ err = -EINVAL;
-+ if (unlikely(d_inode(a->dst_parent) == d_inode(a->src_dentry)))
-+ goto out_unlock;
++ int (*free)(struct au_hinode *hinode,
++ struct au_hnotify *hn) __must_check;
+
-+ au_fset_ren(a->auren_flags, ISSAMEDIR); /* temporary */
-+ di_write_lock_parent(a->dst_parent);
++ void (*fin)(void);
++ int (*init)(void);
+
-+ /* which branch we process */
-+ err = au_ren_wbr(a);
-+ if (unlikely(err < 0))
-+ goto out_parent;
-+ a->br = au_sbr(a->dst_dentry->d_sb, a->btgt);
-+ a->h_path.mnt = au_br_mnt(a->br);
++ int (*reset_br)(unsigned int udba, struct au_branch *br, int perm);
++ void (*fin_br)(struct au_branch *br);
++ int (*init_br)(struct au_branch *br, int perm);
++};
+
-+ /* are they available to be renamed */
-+ err = au_ren_may_dir(a);
-+ if (unlikely(err))
-+ goto out_children;
++/* hnotify.c */
++int au_hn_alloc(struct au_hinode *hinode, struct inode *inode);
++void au_hn_free(struct au_hinode *hinode);
++void au_hn_ctl(struct au_hinode *hinode, int do_set);
++void au_hn_reset(struct inode *inode, unsigned int flags);
++int au_hnotify(struct inode *h_dir, struct au_hnotify *hnotify, u32 mask,
++ const struct qstr *h_child_qstr, struct inode *h_child_inode);
++int au_hnotify_reset_br(unsigned int udba, struct au_branch *br, int perm);
++int au_hnotify_init_br(struct au_branch *br, int perm);
++void au_hnotify_fin_br(struct au_branch *br);
++int __init au_hnotify_init(void);
++void au_hnotify_fin(void);
+
-+ /* prepare the writable parent dir on the same branch */
-+ if (a->dst_btop == a->btgt) {
-+ au_fset_ren(a->auren_flags, WHDST);
-+ } else {
-+ err = au_cpup_dirs(a->dst_dentry, a->btgt);
-+ if (unlikely(err))
-+ goto out_children;
-+ }
++/* hfsnotify.c */
++extern const struct au_hnotify_op au_hnotify_op;
+
-+ err = 0;
-+ if (!a->exchange) {
-+ if (a->src_dir != a->dst_dir) {
-+ /*
-+ * this temporary unlock is safe,
-+ * because both dir->i_mutex are locked.
-+ */
-+ di_write_unlock(a->dst_parent);
-+ di_write_lock_parent(a->src_parent);
-+ err = au_wr_dir_need_wh(a->src_dentry,
-+ au_ftest_ren(a->auren_flags,
-+ ISDIR_SRC),
-+ &a->btgt);
-+ di_write_unlock(a->src_parent);
-+ di_write_lock2_parent(a->src_parent, a->dst_parent,
-+ /*isdir*/1);
-+ au_fclr_ren(a->auren_flags, ISSAMEDIR);
-+ } else
-+ err = au_wr_dir_need_wh(a->src_dentry,
-+ au_ftest_ren(a->auren_flags,
-+ ISDIR_SRC),
-+ &a->btgt);
-+ }
-+ if (unlikely(err < 0))
-+ goto out_children;
-+ if (err)
-+ au_fset_ren(a->auren_flags, WHSRC);
++static inline
++void au_hn_init(struct au_hinode *hinode)
++{
++ hinode->hi_notify = NULL;
++}
+
-+ /* cpup src */
-+ if (a->src_btop != a->btgt) {
-+ err = au_pin(&pin, a->src_dentry, a->btgt,
-+ au_opt_udba(a->src_dentry->d_sb),
-+ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
-+ if (!err) {
-+ struct au_cp_generic cpg = {
-+ .dentry = a->src_dentry,
-+ .bdst = a->btgt,
-+ .bsrc = a->src_btop,
-+ .len = -1,
-+ .pin = &pin,
-+ .flags = AuCpup_DTIME | AuCpup_HOPEN
-+ };
-+ AuDebugOn(au_dbtop(a->src_dentry) != a->src_btop);
-+ err = au_sio_cpup_simple(&cpg);
-+ au_unpin(&pin);
-+ }
-+ if (unlikely(err))
-+ goto out_children;
-+ a->src_btop = a->btgt;
-+ a->src_h_dentry = au_h_dptr(a->src_dentry, a->btgt);
-+ if (!a->exchange)
-+ au_fset_ren(a->auren_flags, WHSRC);
-+ }
++static inline struct au_hnotify *au_hn(struct au_hinode *hinode)
++{
++ return hinode->hi_notify;
++}
+
-+ /* cpup dst */
-+ if (a->exchange && a->dst_inode
-+ && a->dst_btop != a->btgt) {
-+ err = au_pin(&pin, a->dst_dentry, a->btgt,
-+ au_opt_udba(a->dst_dentry->d_sb),
-+ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
-+ if (!err) {
-+ struct au_cp_generic cpg = {
-+ .dentry = a->dst_dentry,
-+ .bdst = a->btgt,
-+ .bsrc = a->dst_btop,
-+ .len = -1,
-+ .pin = &pin,
-+ .flags = AuCpup_DTIME | AuCpup_HOPEN
-+ };
-+ err = au_sio_cpup_simple(&cpg);
-+ au_unpin(&pin);
-+ }
-+ if (unlikely(err))
-+ goto out_children;
-+ a->dst_btop = a->btgt;
-+ a->dst_h_dentry = au_h_dptr(a->dst_dentry, a->btgt);
-+ }
++#else
++AuStub(int, au_hn_alloc, return -EOPNOTSUPP,
++ struct au_hinode *hinode __maybe_unused,
++ struct inode *inode __maybe_unused)
++AuStub(struct au_hnotify *, au_hn, return NULL, struct au_hinode *hinode)
++AuStubVoid(au_hn_free, struct au_hinode *hinode __maybe_unused)
++AuStubVoid(au_hn_ctl, struct au_hinode *hinode __maybe_unused,
++ int do_set __maybe_unused)
++AuStubVoid(au_hn_reset, struct inode *inode __maybe_unused,
++ unsigned int flags __maybe_unused)
++AuStubInt0(au_hnotify_reset_br, unsigned int udba __maybe_unused,
++ struct au_branch *br __maybe_unused,
++ int perm __maybe_unused)
++AuStubInt0(au_hnotify_init_br, struct au_branch *br __maybe_unused,
++ int perm __maybe_unused)
++AuStubVoid(au_hnotify_fin_br, struct au_branch *br __maybe_unused)
++AuStubInt0(__init au_hnotify_init, void)
++AuStubVoid(au_hnotify_fin, void)
++AuStubVoid(au_hn_init, struct au_hinode *hinode __maybe_unused)
++#endif /* CONFIG_AUFS_HNOTIFY */
+
-+ /* lock them all */
-+ err = au_ren_lock(a);
-+ if (unlikely(err))
-+ /* leave the copied-up one */
-+ goto out_children;
++static inline void au_hn_suspend(struct au_hinode *hdir)
++{
++ au_hn_ctl(hdir, /*do_set*/0);
++}
+
-+ if (!a->exchange) {
-+ if (!au_opt_test(au_mntflags(a->dst_dir->i_sb), UDBA_NONE))
-+ err = au_may_ren(a);
-+ else if (unlikely(a->dst_dentry->d_name.len > AUFS_MAX_NAMELEN))
-+ err = -ENAMETOOLONG;
-+ if (unlikely(err))
-+ goto out_hdir;
-+ }
++static inline void au_hn_resume(struct au_hinode *hdir)
++{
++ au_hn_ctl(hdir, /*do_set*/1);
++}
+
-+ /* store timestamps to be revertible */
-+ au_ren_dt(a);
++static inline void au_hn_inode_lock(struct au_hinode *hdir)
++{
++ inode_lock(hdir->hi_inode);
++ au_hn_suspend(hdir);
++}
+
-+ /* store dirren info */
-+ if (au_ftest_ren(a->auren_flags, DIRREN)) {
-+ err = au_dr_rename(a->src_dentry, a->btgt,
-+ &a->dst_dentry->d_name, &rev);
-+ AuTraceErr(err);
-+ if (unlikely(err))
-+ goto out_dt;
-+ }
++static inline void au_hn_inode_lock_nested(struct au_hinode *hdir,
++ unsigned int sc __maybe_unused)
++{
++ inode_lock_nested(hdir->hi_inode, sc);
++ au_hn_suspend(hdir);
++}
++
++#if 0 /* unused */
++#include "vfsub.h"
++static inline void au_hn_inode_lock_shared_nested(struct au_hinode *hdir,
++ unsigned int sc)
++{
++ inode_lock_shared_nested(hdir->hi_inode, sc);
++ au_hn_suspend(hdir);
++}
++#endif
++
++static inline void au_hn_inode_unlock(struct au_hinode *hdir)
++{
++ au_hn_resume(hdir);
++ inode_unlock(hdir->hi_inode);
++}
++
++#endif /* __KERNEL__ */
++#endif /* __AUFS_INODE_H__ */
+diff --git a/fs/aufs/ioctl.c b/fs/aufs/ioctl.c
+new file mode 100644
+index 00000000000000..2d8d91084099f9
+--- /dev/null
++++ b/fs/aufs/ioctl.c
+@@ -0,0 +1,220 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2005-2022 Junjiro R. Okajima
++ *
++ * This program 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/>.
++ */
++
++/*
++ * ioctl
++ * plink-management and readdir in userspace.
++ * assist the pathconf(3) wrapper library.
++ * move-down
++ * File-based Hierarchical Storage Management.
++ */
++
++#include <linux/compat.h>
++#include <linux/file.h>
++#include "aufs.h"
+
-+ /* here we go */
-+ err = do_rename(a);
-+ if (unlikely(err))
-+ goto out_dirren;
++static int au_wbr_fd(struct path *path, struct aufs_wbr_fd __user *arg)
++{
++ int err, fd;
++ aufs_bindex_t wbi, bindex, bbot;
++ struct file *h_file;
++ struct super_block *sb;
++ struct dentry *root;
++ struct au_branch *br;
++ struct aufs_wbr_fd wbrfd = {
++ .oflags = au_dir_roflags,
++ .brid = -1
++ };
++ const int valid = O_RDONLY | O_NONBLOCK | O_LARGEFILE | O_DIRECTORY
++ | O_NOATIME | O_CLOEXEC;
+
-+ if (au_ftest_ren(a->auren_flags, DIRREN))
-+ au_dr_rename_fin(a->src_dentry, a->btgt, rev);
++ AuDebugOn(wbrfd.oflags & ~valid);
+
-+ /* update dir attributes */
-+ au_ren_refresh_dir(a);
++ if (arg) {
++ err = copy_from_user(&wbrfd, arg, sizeof(wbrfd));
++ if (unlikely(err)) {
++ err = -EFAULT;
++ goto out;
++ }
+
-+ /* dput/iput all lower dentries */
-+ au_ren_refresh(a);
++ err = -EINVAL;
++ AuDbg("wbrfd{0%o, %d}\n", wbrfd.oflags, wbrfd.brid);
++ wbrfd.oflags |= au_dir_roflags;
++ AuDbg("0%o\n", wbrfd.oflags);
++ if (unlikely(wbrfd.oflags & ~valid))
++ goto out;
++ }
+
-+ goto out_hdir; /* success */
++ fd = get_unused_fd_flags(0);
++ err = fd;
++ if (unlikely(fd < 0))
++ goto out;
+
-+out_dirren:
-+ if (au_ftest_ren(a->auren_flags, DIRREN))
-+ au_dr_rename_rev(a->src_dentry, a->btgt, rev);
-+out_dt:
-+ au_ren_rev_dt(err, a);
-+out_hdir:
-+ au_ren_unlock(a);
-+out_children:
-+ au_nhash_wh_free(&a->whlist);
-+ if (err && a->dst_inode && a->dst_btop != a->btgt) {
-+ AuDbg("btop %d, btgt %d\n", a->dst_btop, a->btgt);
-+ au_set_h_dptr(a->dst_dentry, a->btgt, NULL);
-+ au_set_dbtop(a->dst_dentry, a->dst_btop);
++ h_file = ERR_PTR(-EINVAL);
++ wbi = 0;
++ br = NULL;
++ sb = path->dentry->d_sb;
++ root = sb->s_root;
++ aufs_read_lock(root, AuLock_IR);
++ bbot = au_sbbot(sb);
++ if (wbrfd.brid >= 0) {
++ wbi = au_br_index(sb, wbrfd.brid);
++ if (unlikely(wbi < 0 || wbi > bbot))
++ goto out_unlock;
+ }
-+out_parent:
-+ if (!err) {
-+ if (d_unhashed(a->src_dentry))
-+ au_fset_ren(a->auren_flags, DROPPED_SRC);
-+ if (d_unhashed(a->dst_dentry))
-+ au_fset_ren(a->auren_flags, DROPPED_DST);
-+ if (!a->exchange)
-+ d_move(a->src_dentry, a->dst_dentry);
-+ else {
-+ d_exchange(a->src_dentry, a->dst_dentry);
-+ if (au_ftest_ren(a->auren_flags, DROPPED_DST))
-+ d_drop(a->dst_dentry);
++
++ h_file = ERR_PTR(-ENOENT);
++ br = au_sbr(sb, wbi);
++ if (!au_br_writable(br->br_perm)) {
++ if (arg)
++ goto out_unlock;
++
++ bindex = wbi + 1;
++ wbi = -1;
++ for (; bindex <= bbot; bindex++) {
++ br = au_sbr(sb, bindex);
++ if (au_br_writable(br->br_perm)) {
++ wbi = bindex;
++ br = au_sbr(sb, wbi);
++ break;
++ }
+ }
-+ if (au_ftest_ren(a->auren_flags, DROPPED_SRC))
-+ d_drop(a->src_dentry);
-+ } else {
-+ au_update_dbtop(a->dst_dentry);
-+ if (!a->dst_inode)
-+ d_drop(a->dst_dentry);
+ }
-+ if (au_ftest_ren(a->auren_flags, ISSAMEDIR))
-+ di_write_unlock(a->dst_parent);
-+ else
-+ di_write_unlock2(a->src_parent, a->dst_parent);
++ AuDbg("wbi %d\n", wbi);
++ if (wbi >= 0)
++ h_file = au_h_open(root, wbi, wbrfd.oflags, NULL,
++ /*force_wr*/0);
++
+out_unlock:
-+ aufs_read_and_write_unlock2(a->dst_dentry, a->src_dentry);
-+out_free:
-+ iput(a->dst_inode);
-+ if (a->thargs)
-+ au_whtmp_rmdir_free(a->thargs);
-+ au_kfree_rcu(a);
++ aufs_read_unlock(root, AuLock_IR);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
++ goto out_fd;
++
++ au_lcnt_dec(&br->br_nfiles); /* cf. au_h_open() */
++ fd_install(fd, h_file);
++ err = fd;
++ goto out; /* success */
++
++out_fd:
++ put_unused_fd(fd);
+out:
+ AuTraceErr(err);
+ return err;
+}
-diff -urN /usr/share/empty/fs/aufs/Kconfig linux/fs/aufs/Kconfig
---- /usr/share/empty/fs/aufs/Kconfig 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/Kconfig 2022-11-05 23:02:18.959222617 +0100
-@@ -0,0 +1,199 @@
-+# SPDX-License-Identifier: GPL-2.0
-+config AUFS_FS
-+ tristate "Aufs (Advanced multi layered unification filesystem) support"
-+ help
-+ Aufs is a stackable unification filesystem such as Unionfs,
-+ which unifies several directories and provides a merged single
-+ directory.
-+ In the early days, aufs was entirely re-designed and
-+ re-implemented Unionfs Version 1.x series. Introducing many
-+ original ideas, approaches and improvements, it becomes totally
-+ different from Unionfs while keeping the basic features.
+
-+if AUFS_FS
-+choice
-+ prompt "Maximum number of branches"
-+ default AUFS_BRANCH_MAX_127
-+ help
-+ Specifies the maximum number of branches (or member directories)
-+ in a single aufs. The larger value consumes more system
-+ resources and has a minor impact to performance.
-+config AUFS_BRANCH_MAX_127
-+ bool "127"
-+ help
-+ Specifies the maximum number of branches (or member directories)
-+ in a single aufs. The larger value consumes more system
-+ resources and has a minor impact to performance.
-+config AUFS_BRANCH_MAX_511
-+ bool "511"
-+ help
-+ Specifies the maximum number of branches (or member directories)
-+ in a single aufs. The larger value consumes more system
-+ resources and has a minor impact to performance.
-+config AUFS_BRANCH_MAX_1023
-+ bool "1023"
-+ help
-+ Specifies the maximum number of branches (or member directories)
-+ in a single aufs. The larger value consumes more system
-+ resources and has a minor impact to performance.
-+config AUFS_BRANCH_MAX_32767
-+ bool "32767"
-+ help
-+ Specifies the maximum number of branches (or member directories)
-+ in a single aufs. The larger value consumes more system
-+ resources and has a minor impact to performance.
-+endchoice
++/* ---------------------------------------------------------------------- */
+
-+config AUFS_SBILIST
-+ bool
-+ depends on AUFS_MAGIC_SYSRQ || PROC_FS
-+ default y
-+ help
-+ Automatic configuration for internal use.
-+ When aufs supports Magic SysRq or /proc, enabled automatically.
++long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long arg)
++{
++ long err;
++ struct dentry *dentry;
+
-+config AUFS_HNOTIFY
-+ bool "Detect direct branch access (bypassing aufs)"
-+ help
-+ If you want to modify files on branches directly, eg. bypassing aufs,
-+ and want aufs to detect the changes of them fully, then enable this
-+ option and use 'udba=notify' mount option.
-+ Currently there is only one available configuration, "fsnotify".
-+ It will have a negative impact to the performance.
-+ See detail in aufs.5.
++ switch (cmd) {
++ case AUFS_CTL_RDU:
++ case AUFS_CTL_RDU_INO:
++ err = au_rdu_ioctl(file, cmd, arg);
++ break;
+
-+choice
-+ prompt "method" if AUFS_HNOTIFY
-+ default AUFS_HFSNOTIFY
-+config AUFS_HFSNOTIFY
-+ bool "fsnotify"
-+ select FSNOTIFY
-+endchoice
++ case AUFS_CTL_WBR_FD:
++ err = au_wbr_fd(&file->f_path, (void __user *)arg);
++ break;
+
-+config AUFS_EXPORT
-+ bool "NFS-exportable aufs"
-+ depends on EXPORTFS
-+ help
-+ If you want to export your mounted aufs via NFS, then enable this
-+ option. There are several requirements for this configuration.
-+ See detail in aufs.5.
++ case AUFS_CTL_IBUSY:
++ err = au_ibusy_ioctl(file, arg);
++ break;
+
-+config AUFS_INO_T_64
-+ bool
-+ depends on AUFS_EXPORT
-+ depends on 64BIT && !(ALPHA || S390)
-+ default y
-+ help
-+ Automatic configuration for internal use.
-+ /* typedef unsigned long/int __kernel_ino_t */
-+ /* alpha and s390x are int */
++ case AUFS_CTL_BRINFO:
++ err = au_brinfo_ioctl(file, arg);
++ break;
+
-+config AUFS_XATTR
-+ bool "support for XATTR/EA (including Security Labels)"
-+ help
-+ If your branch fs supports XATTR/EA and you want to make them
-+ available in aufs too, then enable this opsion and specify the
-+ branch attributes for EA.
-+ See detail in aufs.5.
++ case AUFS_CTL_FHSM_FD:
++ dentry = file->f_path.dentry;
++ if (IS_ROOT(dentry))
++ err = au_fhsm_fd(dentry->d_sb, arg);
++ else
++ err = -ENOTTY;
++ break;
+
-+config AUFS_FHSM
-+ bool "File-based Hierarchical Storage Management"
-+ help
-+ Hierarchical Storage Management (or HSM) is a well-known feature
-+ in the storage world. Aufs provides this feature as file-based.
-+ with multiple branches.
-+ These multiple branches are prioritized, ie. the topmost one
-+ should be the fastest drive and be used heavily.
++ default:
++ /* do not call the lower */
++ AuDbg("0x%x\n", cmd);
++ err = -ENOTTY;
++ }
+
-+config AUFS_RDU
-+ bool "Readdir in userspace"
-+ help
-+ Aufs has two methods to provide a merged view for a directory,
-+ by a user-space library and by kernel-space natively. The latter
-+ is always enabled but sometimes large and slow.
-+ If you enable this option, install the library in aufs2-util
-+ package, and set some environment variables for your readdir(3),
-+ then the work will be handled in user-space which generally
-+ shows better performance in most cases.
-+ See detail in aufs.5.
++ AuTraceErr(err);
++ return err;
++}
+
-+config AUFS_DIRREN
-+ bool "Workaround for rename(2)-ing a directory"
-+ help
-+ By default, aufs returns EXDEV error in renameing a dir who has
-+ his child on the lower branch, since it is a bad idea to issue
-+ rename(2) internally for every lower branch. But user may not
-+ accept this behaviour. So here is a workaround to allow such
-+ rename(2) and store some extra information on the writable
-+ branch. Obviously this costs high (and I don't like it).
-+ To use this feature, you need to enable this configuration AND
-+ to specify the mount option `dirren.'
-+ See details in aufs.5 and the design documents.
++long aufs_ioctl_nondir(struct file *file, unsigned int cmd, unsigned long arg)
++{
++ long err;
+
-+config AUFS_SHWH
-+ bool "Show whiteouts"
-+ help
-+ If you want to make the whiteouts in aufs visible, then enable
-+ this option and specify 'shwh' mount option. Although it may
-+ sounds like philosophy or something, but in technically it
-+ simply shows the name of whiteout with keeping its behaviour.
++ switch (cmd) {
++ case AUFS_CTL_MVDOWN:
++ err = au_mvdown(file->f_path.dentry, (void __user *)arg);
++ break;
+
-+config AUFS_BR_RAMFS
-+ bool "Ramfs (initramfs/rootfs) as an aufs branch"
-+ help
-+ If you want to use ramfs as an aufs branch fs, then enable this
-+ option. Generally tmpfs is recommended.
-+ Aufs prohibited them to be a branch fs by default, because
-+ initramfs becomes unusable after switch_root or something
-+ generally. If you sets initramfs as an aufs branch and boot your
-+ system by switch_root, you will meet a problem easily since the
-+ files in initramfs may be inaccessible.
-+ Unless you are going to use ramfs as an aufs branch fs without
-+ switch_root or something, leave it N.
++ case AUFS_CTL_WBR_FD:
++ err = au_wbr_fd(&file->f_path, (void __user *)arg);
++ break;
+
-+config AUFS_BR_FUSE
-+ bool "Fuse fs as an aufs branch"
-+ depends on FUSE_FS
-+ select AUFS_POLL
-+ help
-+ If you want to use fuse-based userspace filesystem as an aufs
-+ branch fs, then enable this option.
-+ It implements the internal poll(2) operation which is
-+ implemented by fuse only (curretnly).
++ default:
++ /* do not call the lower */
++ AuDbg("0x%x\n", cmd);
++ err = -ENOTTY;
++ }
+
-+config AUFS_POLL
-+ bool
-+ help
-+ Automatic configuration for internal use.
++ AuTraceErr(err);
++ return err;
++}
+
-+config AUFS_BR_HFSPLUS
-+ bool "Hfsplus as an aufs branch"
-+ depends on HFSPLUS_FS
-+ default y
-+ help
-+ If you want to use hfsplus fs as an aufs branch fs, then enable
-+ this option. This option introduces a small overhead at
-+ copying-up a file on hfsplus.
++#ifdef CONFIG_COMPAT
++long aufs_compat_ioctl_dir(struct file *file, unsigned int cmd,
++ unsigned long arg)
++{
++ long err;
+
-+config AUFS_BDEV_LOOP
-+ bool
-+ depends on BLK_DEV_LOOP
-+ default y
-+ help
-+ Automatic configuration for internal use.
-+ Convert =[ym] into =y.
++ switch (cmd) {
++ case AUFS_CTL_RDU:
++ case AUFS_CTL_RDU_INO:
++ err = au_rdu_compat_ioctl(file, cmd, arg);
++ break;
+
-+config AUFS_DEBUG
-+ bool "Debug aufs"
-+ help
-+ Enable this to compile aufs internal debug code.
-+ It will have a negative impact to the performance.
++ case AUFS_CTL_IBUSY:
++ err = au_ibusy_compat_ioctl(file, arg);
++ break;
+
-+config AUFS_MAGIC_SYSRQ
-+ bool
-+ depends on AUFS_DEBUG && MAGIC_SYSRQ
-+ default y
-+ help
-+ Automatic configuration for internal use.
-+ When aufs supports Magic SysRq, enabled automatically.
-+endif
-diff -urN /usr/share/empty/fs/aufs/lcnt.h linux/fs/aufs/lcnt.h
---- /usr/share/empty/fs/aufs/lcnt.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/lcnt.h 2022-11-05 23:02:18.965889284 +0100
++ case AUFS_CTL_BRINFO:
++ err = au_brinfo_compat_ioctl(file, arg);
++ break;
++
++ default:
++ err = aufs_ioctl_dir(file, cmd, arg);
++ }
++
++ AuTraceErr(err);
++ return err;
++}
++
++long aufs_compat_ioctl_nondir(struct file *file, unsigned int cmd,
++ unsigned long arg)
++{
++ return aufs_ioctl_nondir(file, cmd, (unsigned long)compat_ptr(arg));
++}
++#endif
+diff --git a/fs/aufs/lcnt.h b/fs/aufs/lcnt.h
+new file mode 100644
+index 00000000000000..6dc37108565fa2
+--- /dev/null
++++ b/fs/aufs/lcnt.h
@@ -0,0 +1,186 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_LCNT_H__ */
-diff -urN /usr/share/empty/fs/aufs/loop.c linux/fs/aufs/loop.c
---- /usr/share/empty/fs/aufs/loop.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/loop.c 2022-11-05 23:02:18.965889284 +0100
+diff --git a/fs/aufs/loop.c b/fs/aufs/loop.c
+new file mode 100644
+index 00000000000000..38319058859501
+--- /dev/null
++++ b/fs/aufs/loop.c
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ symbol_put(loop_backing_file);
+ au_kfree_try_rcu(au_warn_loopback_array);
+}
-diff -urN /usr/share/empty/fs/aufs/loop.h linux/fs/aufs/loop.h
---- /usr/share/empty/fs/aufs/loop.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/loop.h 2022-11-05 23:02:18.965889284 +0100
+diff --git a/fs/aufs/loop.h b/fs/aufs/loop.h
+new file mode 100644
+index 00000000000000..9726b8354e00db
+--- /dev/null
++++ b/fs/aufs/loop.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_LOOP_H__ */
-diff -urN /usr/share/empty/fs/aufs/magic.mk linux/fs/aufs/magic.mk
---- /usr/share/empty/fs/aufs/magic.mk 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/magic.mk 2022-11-05 23:02:18.965889284 +0100
+diff --git a/fs/aufs/magic.mk b/fs/aufs/magic.mk
+new file mode 100644
+index 00000000000000..7bc9eef3ffec55
+--- /dev/null
++++ b/fs/aufs/magic.mk
@@ -0,0 +1,31 @@
+# SPDX-License-Identifier: GPL-2.0
+
+ifdef CONFIG_HFSPLUS_FS
+ccflags-y += -DHFSPLUS_SUPER_MAGIC=0x482b
+endif
-diff -urN /usr/share/empty/fs/aufs/Makefile linux/fs/aufs/Makefile
---- /usr/share/empty/fs/aufs/Makefile 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/Makefile 2022-11-05 23:02:18.959222617 +0100
-@@ -0,0 +1,46 @@
-+# SPDX-License-Identifier: GPL-2.0
-+
-+include ${src}/magic.mk
-+ifeq (${CONFIG_AUFS_FS},m)
-+include ${src}/conf.mk
-+endif
-+-include ${src}/priv_def.mk
-+
-+# cf. include/linux/kernel.h
-+# enable pr_debug
-+ccflags-y += -DDEBUG
-+# sparse requires the full pathname
-+ifdef M
-+ccflags-y += -include ${M}/../../include/uapi/linux/aufs_type.h
-+else
-+ccflags-y += -include ${srctree}/include/uapi/linux/aufs_type.h
-+endif
-+
-+obj-$(CONFIG_AUFS_FS) += aufs.o
-+aufs-y := module.o sbinfo.o super.o branch.o xino.o sysaufs.o opts.o fsctx.o \
-+ wkq.o vfsub.o dcsub.o \
-+ cpup.o whout.o wbr_policy.o \
-+ dinfo.o dentry.o \
-+ dynop.o \
-+ finfo.o file.o f_op.o \
-+ dir.o vdir.o \
-+ iinfo.o inode.o i_op.o i_op_add.o i_op_del.o i_op_ren.o \
-+ mvdown.o ioctl.o
-+
-+# all are boolean
-+aufs-$(CONFIG_PROC_FS) += procfs.o plink.o
-+aufs-$(CONFIG_SYSFS) += sysfs.o
-+aufs-$(CONFIG_DEBUG_FS) += dbgaufs.o
-+aufs-$(CONFIG_AUFS_BDEV_LOOP) += loop.o
-+aufs-$(CONFIG_AUFS_HNOTIFY) += hnotify.o
-+aufs-$(CONFIG_AUFS_HFSNOTIFY) += hfsnotify.o
-+aufs-$(CONFIG_AUFS_EXPORT) += export.o
-+aufs-$(CONFIG_AUFS_XATTR) += xattr.o
-+aufs-$(CONFIG_FS_POSIX_ACL) += posix_acl.o
-+aufs-$(CONFIG_AUFS_DIRREN) += dirren.o
-+aufs-$(CONFIG_AUFS_FHSM) += fhsm.o
-+aufs-$(CONFIG_AUFS_POLL) += poll.o
-+aufs-$(CONFIG_AUFS_RDU) += rdu.o
-+aufs-$(CONFIG_AUFS_BR_HFSPLUS) += hfsplus.o
-+aufs-$(CONFIG_AUFS_DEBUG) += debug.o
-+aufs-$(CONFIG_AUFS_MAGIC_SYSRQ) += sysrq.o
-diff -urN /usr/share/empty/fs/aufs/module.c linux/fs/aufs/module.c
---- /usr/share/empty/fs/aufs/module.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/module.c 2022-11-05 23:02:18.965889284 +0100
+diff --git a/fs/aufs/module.c b/fs/aufs/module.c
+new file mode 100644
+index 00000000000000..c2815fffb5c6ae
+--- /dev/null
++++ b/fs/aufs/module.c
@@ -0,0 +1,273 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+
+module_init(aufs_init);
+module_exit(aufs_exit);
-diff -urN /usr/share/empty/fs/aufs/module.h linux/fs/aufs/module.h
---- /usr/share/empty/fs/aufs/module.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/module.h 2022-11-05 23:02:18.969222617 +0100
+diff --git a/fs/aufs/module.h b/fs/aufs/module.h
+new file mode 100644
+index 00000000000000..a9d21d3e5414ea
+--- /dev/null
++++ b/fs/aufs/module.h
@@ -0,0 +1,180 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_MODULE_H__ */
-diff -urN /usr/share/empty/fs/aufs/mvdown.c linux/fs/aufs/mvdown.c
---- /usr/share/empty/fs/aufs/mvdown.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/mvdown.c 2022-11-05 23:02:18.969222617 +0100
+diff --git a/fs/aufs/mvdown.c b/fs/aufs/mvdown.c
+new file mode 100644
+index 00000000000000..daafc27e64b0aa
+--- /dev/null
++++ b/fs/aufs/mvdown.c
@@ -0,0 +1,706 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ AuTraceErr(err);
+ return err;
+}
-diff -urN /usr/share/empty/fs/aufs/opts.c linux/fs/aufs/opts.c
---- /usr/share/empty/fs/aufs/opts.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/opts.c 2022-11-05 23:02:18.969222617 +0100
+diff --git a/fs/aufs/opts.c b/fs/aufs/opts.c
+new file mode 100644
+index 00000000000000..20421440c00417
+--- /dev/null
++++ b/fs/aufs/opts.c
@@ -0,0 +1,1032 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+{
+ return au_mntflags(sb) & AuOptMask_UDBA;
+}
-diff -urN /usr/share/empty/fs/aufs/opts.h linux/fs/aufs/opts.h
---- /usr/share/empty/fs/aufs/opts.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/opts.h 2022-11-05 23:02:18.969222617 +0100
+diff --git a/fs/aufs/opts.h b/fs/aufs/opts.h
+new file mode 100644
+index 00000000000000..d8bbdbf0560ae9
+--- /dev/null
++++ b/fs/aufs/opts.h
@@ -0,0 +1,263 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_OPTS_H__ */
-diff -urN /usr/share/empty/fs/aufs/plink.c linux/fs/aufs/plink.c
---- /usr/share/empty/fs/aufs/plink.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/plink.c 2022-11-05 23:02:18.969222617 +0100
+diff --git a/fs/aufs/plink.c b/fs/aufs/plink.c
+new file mode 100644
+index 00000000000000..5f9a5b50dcc6ba
+--- /dev/null
++++ b/fs/aufs/plink.c
@@ -0,0 +1,516 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ }
+ }
+}
-diff -urN /usr/share/empty/fs/aufs/poll.c linux/fs/aufs/poll.c
---- /usr/share/empty/fs/aufs/poll.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/poll.c 2022-11-05 23:02:18.969222617 +0100
+diff --git a/fs/aufs/poll.c b/fs/aufs/poll.c
+new file mode 100644
+index 00000000000000..83defa454c8e18
+--- /dev/null
++++ b/fs/aufs/poll.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ AuDbg("mask 0x%x\n", mask);
+ return mask;
+}
-diff -urN /usr/share/empty/fs/aufs/posix_acl.c linux/fs/aufs/posix_acl.c
---- /usr/share/empty/fs/aufs/posix_acl.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/posix_acl.c 2023-10-31 09:31:04.199880750 +0100
+diff --git a/fs/aufs/posix_acl.c b/fs/aufs/posix_acl.c
+new file mode 100644
+index 00000000000000..03742bcc66035e
+--- /dev/null
++++ b/fs/aufs/posix_acl.c
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+
+ return err;
+}
-diff -urN /usr/share/empty/fs/aufs/procfs.c linux/fs/aufs/procfs.c
---- /usr/share/empty/fs/aufs/procfs.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/procfs.c 2022-11-05 23:02:18.969222617 +0100
+diff --git a/fs/aufs/procfs.c b/fs/aufs/procfs.c
+new file mode 100644
+index 00000000000000..0fca104ac554b3
+--- /dev/null
++++ b/fs/aufs/procfs.c
@@ -0,0 +1,170 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+out:
+ return err;
+}
-diff -urN /usr/share/empty/fs/aufs/rdu.c linux/fs/aufs/rdu.c
---- /usr/share/empty/fs/aufs/rdu.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/rdu.c 2023-10-31 09:31:04.199880750 +0100
+diff --git a/fs/aufs/rdu.c b/fs/aufs/rdu.c
+new file mode 100644
+index 00000000000000..144251c02c3f31
+--- /dev/null
++++ b/fs/aufs/rdu.c
@@ -0,0 +1,384 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ return err;
+}
+#endif
-diff -urN /usr/share/empty/fs/aufs/rwsem.h linux/fs/aufs/rwsem.h
---- /usr/share/empty/fs/aufs/rwsem.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/rwsem.h 2022-11-05 23:02:18.969222617 +0100
+diff --git a/fs/aufs/rwsem.h b/fs/aufs/rwsem.h
+new file mode 100644
+index 00000000000000..9d9cd50ef15587
+--- /dev/null
++++ b/fs/aufs/rwsem.h
@@ -0,0 +1,85 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_RWSEM_H__ */
-diff -urN /usr/share/empty/fs/aufs/sbinfo.c linux/fs/aufs/sbinfo.c
---- /usr/share/empty/fs/aufs/sbinfo.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/sbinfo.c 2022-11-05 23:02:18.969222617 +0100
+diff --git a/fs/aufs/sbinfo.c b/fs/aufs/sbinfo.c
+new file mode 100644
+index 00000000000000..dde9f9c17b18db
+--- /dev/null
++++ b/fs/aufs/sbinfo.c
@@ -0,0 +1,316 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ di_write_unlock2(d1, d2);
+ si_read_unlock(d1->d_sb);
+}
-diff -urN /usr/share/empty/fs/aufs/super.c linux/fs/aufs/super.c
---- /usr/share/empty/fs/aufs/super.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/super.c 2023-10-10 22:51:18.033248030 +0200
+diff --git a/fs/aufs/super.c b/fs/aufs/super.c
+new file mode 100644
+index 00000000000000..77c6d90808bb3f
+--- /dev/null
++++ b/fs/aufs/super.c
@@ -0,0 +1,871 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ /* no need to __module_get() and module_put(). */
+ .owner = THIS_MODULE,
+};
-diff -urN /usr/share/empty/fs/aufs/super.h linux/fs/aufs/super.h
---- /usr/share/empty/fs/aufs/super.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/super.h 2022-11-05 23:02:18.969222617 +0100
+diff --git a/fs/aufs/super.h b/fs/aufs/super.h
+new file mode 100644
+index 00000000000000..f1d9aedcbca4f3
+--- /dev/null
++++ b/fs/aufs/super.h
@@ -0,0 +1,592 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_SUPER_H__ */
-diff -urN /usr/share/empty/fs/aufs/sysaufs.c linux/fs/aufs/sysaufs.c
---- /usr/share/empty/fs/aufs/sysaufs.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/sysaufs.c 2023-10-10 22:51:18.033248030 +0200
+diff --git a/fs/aufs/sysaufs.c b/fs/aufs/sysaufs.c
+new file mode 100644
+index 00000000000000..ab109d55040c31
+--- /dev/null
++++ b/fs/aufs/sysaufs.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+out:
+ return err;
+}
-diff -urN /usr/share/empty/fs/aufs/sysaufs.h linux/fs/aufs/sysaufs.h
---- /usr/share/empty/fs/aufs/sysaufs.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/sysaufs.h 2022-11-05 23:02:18.969222617 +0100
+diff --git a/fs/aufs/sysaufs.h b/fs/aufs/sysaufs.h
+new file mode 100644
+index 00000000000000..3f7efd4510be61
+--- /dev/null
++++ b/fs/aufs/sysaufs.h
@@ -0,0 +1,102 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __SYSAUFS_H__ */
-diff -urN /usr/share/empty/fs/aufs/sysfs.c linux/fs/aufs/sysfs.c
---- /usr/share/empty/fs/aufs/sysfs.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/sysfs.c 2022-11-05 23:02:18.969222617 +0100
+diff --git a/fs/aufs/sysfs.c b/fs/aufs/sysfs.c
+new file mode 100644
+index 00000000000000..4e8a4cfa9faa22
+--- /dev/null
++++ b/fs/aufs/sysfs.c
@@ -0,0 +1,374 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ }
+ }
+}
-diff -urN /usr/share/empty/fs/aufs/sysrq.c linux/fs/aufs/sysrq.c
---- /usr/share/empty/fs/aufs/sysrq.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/sysrq.c 2023-10-31 09:31:04.199880750 +0100
+diff --git a/fs/aufs/sysrq.c b/fs/aufs/sysrq.c
+new file mode 100644
+index 00000000000000..c03d87e414c50f
+--- /dev/null
++++ b/fs/aufs/sysrq.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ if (unlikely(err))
+ pr_err("err %d (ignored)\n", err);
+}
-diff -urN /usr/share/empty/fs/aufs/vdir.c linux/fs/aufs/vdir.c
---- /usr/share/empty/fs/aufs/vdir.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/vdir.c 2022-12-17 09:21:34.799855195 +0100
+diff --git a/fs/aufs/vdir.c b/fs/aufs/vdir.c
+new file mode 100644
+index 00000000000000..fdf7644049c5d2
+--- /dev/null
++++ b/fs/aufs/vdir.c
@@ -0,0 +1,896 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ /* smp_mb(); */
+ return 0;
+}
-diff -urN /usr/share/empty/fs/aufs/vfsub.c linux/fs/aufs/vfsub.c
---- /usr/share/empty/fs/aufs/vfsub.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/vfsub.c 2023-10-31 09:31:04.199880750 +0100
+diff --git a/fs/aufs/vfsub.c b/fs/aufs/vfsub.c
+new file mode 100644
+index 00000000000000..2fb5f1ac0b31c6
+--- /dev/null
++++ b/fs/aufs/vfsub.c
@@ -0,0 +1,918 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+
+ return err;
+}
-diff -urN /usr/share/empty/fs/aufs/vfsub.h linux/fs/aufs/vfsub.h
---- /usr/share/empty/fs/aufs/vfsub.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/vfsub.h 2023-10-31 09:31:04.199880750 +0100
+diff --git a/fs/aufs/vfsub.h b/fs/aufs/vfsub.h
+new file mode 100644
+index 00000000000000..ed218d95770d0c
+--- /dev/null
++++ b/fs/aufs/vfsub.h
@@ -0,0 +1,403 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_VFSUB_H__ */
-diff -urN /usr/share/empty/fs/aufs/wbr_policy.c linux/fs/aufs/wbr_policy.c
---- /usr/share/empty/fs/aufs/wbr_policy.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/wbr_policy.c 2022-11-05 23:02:18.969222617 +0100
+diff --git a/fs/aufs/wbr_policy.c b/fs/aufs/wbr_policy.c
+new file mode 100644
+index 00000000000000..c726f96b7bd538
+--- /dev/null
++++ b/fs/aufs/wbr_policy.c
@@ -0,0 +1,830 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ .fin = au_wbr_create_fin_mfs
+ }
+};
-diff -urN /usr/share/empty/fs/aufs/whout.c linux/fs/aufs/whout.c
---- /usr/share/empty/fs/aufs/whout.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/whout.c 2023-10-31 09:31:04.199880750 +0100
+diff --git a/fs/aufs/whout.c b/fs/aufs/whout.c
+new file mode 100644
+index 00000000000000..7bd0392eeb875e
+--- /dev/null
++++ b/fs/aufs/whout.c
@@ -0,0 +1,1072 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ au_whtmp_rmdir_free(args);
+ }
+}
-diff -urN /usr/share/empty/fs/aufs/whout.h linux/fs/aufs/whout.h
---- /usr/share/empty/fs/aufs/whout.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/whout.h 2023-10-31 09:31:04.199880750 +0100
+diff --git a/fs/aufs/whout.h b/fs/aufs/whout.h
+new file mode 100644
+index 00000000000000..a7ae8702e7a5cb
+--- /dev/null
++++ b/fs/aufs/whout.h
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_WHOUT_H__ */
-diff -urN /usr/share/empty/fs/aufs/wkq.c linux/fs/aufs/wkq.c
---- /usr/share/empty/fs/aufs/wkq.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/wkq.c 2022-11-05 23:02:18.972555950 +0100
+diff --git a/fs/aufs/wkq.c b/fs/aufs/wkq.c
+new file mode 100644
+index 00000000000000..cb71ca3bf51b79
+--- /dev/null
++++ b/fs/aufs/wkq.c
@@ -0,0 +1,372 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+
+ return err;
+}
-diff -urN /usr/share/empty/fs/aufs/wkq.h linux/fs/aufs/wkq.h
---- /usr/share/empty/fs/aufs/wkq.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/wkq.h 2022-11-05 23:02:18.972555950 +0100
+diff --git a/fs/aufs/wkq.h b/fs/aufs/wkq.h
+new file mode 100644
+index 00000000000000..f8bb8e12395ed5
+--- /dev/null
++++ b/fs/aufs/wkq.h
@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_WKQ_H__ */
-diff -urN /usr/share/empty/fs/aufs/xattr.c linux/fs/aufs/xattr.c
---- /usr/share/empty/fs/aufs/xattr.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/xattr.c 2023-10-31 09:31:04.203214083 +0100
+diff --git a/fs/aufs/xattr.c b/fs/aufs/xattr.c
+new file mode 100644
+index 00000000000000..9e08665728aeed
+--- /dev/null
++++ b/fs/aufs/xattr.c
@@ -0,0 +1,360 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+{
+ sb->s_xattr = au_xattr_handlers;
+}
-diff -urN /usr/share/empty/fs/aufs/xino.c linux/fs/aufs/xino.c
---- /usr/share/empty/fs/aufs/xino.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/xino.c 2023-10-31 09:31:04.203214083 +0100
+diff --git a/fs/aufs/xino.c b/fs/aufs/xino.c
+new file mode 100644
+index 00000000000000..e1db09b3541d1b
+--- /dev/null
++++ b/fs/aufs/xino.c
@@ -0,0 +1,1926 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ wake_up_all(&xi->xi_nondir.wqh);
+}
+
-+int au_xinondir_enter(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
-+ int *idx)
-+{
-+ int err, found, empty;
-+ struct au_xino *xi;
++int au_xinondir_enter(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
++ int *idx)
++{
++ int err, found, empty;
++ struct au_xino *xi;
++
++ err = 0;
++ *idx = -1;
++ if (!au_opt_test(au_mntflags(sb), XINO))
++ goto out; /* no xino */
++
++ xi = au_sbr(sb, bindex)->br_xino;
++
++again:
++ spin_lock(&xi->xi_nondir.spin);
++ found = au_xinondir_find(xi, h_ino);
++ if (found == -1) {
++ empty = au_xinondir_find(xi, /*h_ino*/0);
++ if (empty == -1) {
++ empty = xi->xi_nondir.total;
++ err = au_xinondir_expand(xi);
++ if (unlikely(err))
++ goto out_unlock;
++ }
++ xi->xi_nondir.array[empty] = h_ino;
++ *idx = empty;
++ } else {
++ spin_unlock(&xi->xi_nondir.spin);
++ wait_event(xi->xi_nondir.wqh,
++ xi->xi_nondir.array[found] != h_ino);
++ goto again;
++ }
++
++out_unlock:
++ spin_unlock(&xi->xi_nondir.spin);
++out:
++ return err;
++}
++
++/* ---------------------------------------------------------------------- */
++
++int au_xino_path(struct seq_file *seq, struct file *file)
++{
++ int err;
++
++ err = au_seq_path(seq, &file->f_path);
++ if (unlikely(err))
++ goto out;
++
++#define Deleted "\\040(deleted)"
++ seq->count -= sizeof(Deleted) - 1;
++ AuDebugOn(memcmp(seq->buf + seq->count, Deleted,
++ sizeof(Deleted) - 1));
++#undef Deleted
++
++out:
++ return err;
++}
+diff --git a/fs/dcache.c b/fs/dcache.c
+index c82ae731df9af7..411c9acbdca754 100644
+--- a/fs/dcache.c
++++ b/fs/dcache.c
+@@ -1345,7 +1345,7 @@ enum d_walk_ret {
+ *
+ * The @enter() callbacks are called with d_lock held.
+ */
+-static void d_walk(struct dentry *parent, void *data,
++void d_walk(struct dentry *parent, void *data,
+ enum d_walk_ret (*enter)(void *, struct dentry *))
+ {
+ struct dentry *this_parent;
+@@ -1450,6 +1450,7 @@ static void d_walk(struct dentry *parent, void *data,
+ seq = 1;
+ goto again;
+ }
++EXPORT_SYMBOL_GPL(d_walk);
+
+ struct check_mount {
+ struct vfsmount *mnt;
+@@ -3051,6 +3052,7 @@ void d_exchange(struct dentry *dentry1, struct dentry *dentry2)
+
+ write_sequnlock(&rename_lock);
+ }
++EXPORT_SYMBOL_GPL(d_exchange);
+
+ /**
+ * d_ancestor - search for an ancestor
+diff --git a/fs/exec.c b/fs/exec.c
+index 4aa19b24f2810a..013bc5896529ca 100644
+--- a/fs/exec.c
++++ b/fs/exec.c
+@@ -112,6 +112,7 @@ bool path_noexec(const struct path *path)
+ return (path->mnt->mnt_flags & MNT_NOEXEC) ||
+ (path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC);
+ }
++EXPORT_SYMBOL_GPL(path_noexec);
+
+ #ifdef CONFIG_USELIB
+ /*
+diff --git a/fs/fcntl.c b/fs/fcntl.c
+index c80a6acad742fb..e21a0fcff53801 100644
+--- a/fs/fcntl.c
++++ b/fs/fcntl.c
+@@ -34,7 +34,7 @@
+
+ #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME)
+
+-static int setfl(int fd, struct file * filp, unsigned int arg)
++int setfl(int fd, struct file * filp, unsigned int arg)
+ {
+ struct inode * inode = file_inode(filp);
+ int error = 0;
+@@ -64,6 +64,8 @@ static int setfl(int fd, struct file * filp, unsigned int arg)
+
+ if (filp->f_op->check_flags)
+ error = filp->f_op->check_flags(arg);
++ if (!error && filp->f_op->setfl)
++ error = filp->f_op->setfl(filp, arg);
+ if (error)
+ return error;
+
+@@ -85,6 +87,7 @@ static int setfl(int fd, struct file * filp, unsigned int arg)
+ out:
+ return error;
+ }
++EXPORT_SYMBOL_GPL(setfl);
+
+ static void f_modown(struct file *filp, struct pid *pid, enum pid_type type,
+ int force)
+diff --git a/fs/file_table.c b/fs/file_table.c
+index de4a2915bfd494..475f3f9c787607 100644
+--- a/fs/file_table.c
++++ b/fs/file_table.c
+@@ -235,6 +235,7 @@ struct file *alloc_empty_file(int flags, const struct cred *cred)
+ }
+ return ERR_PTR(-ENFILE);
+ }
++EXPORT_SYMBOL_GPL(alloc_empty_file);
+
+ /*
+ * Variant of alloc_empty_file() that doesn't check and modify nr_files.
+diff --git a/fs/namespace.c b/fs/namespace.c
+index fbf0e596fcd30c..1b942a6b72fa9f 100644
+--- a/fs/namespace.c
++++ b/fs/namespace.c
+@@ -489,6 +489,7 @@ void mnt_put_write_access_file(struct file *file)
+ if (!(file->f_mode & FMODE_WRITER))
+ mnt_put_write_access(file->f_path.mnt);
+ }
++EXPORT_SYMBOL_GPL(__mnt_drop_write);
+
+ void mnt_drop_write_file(struct file *file)
+ {
+@@ -874,6 +875,13 @@ static inline int check_mnt(struct mount *mnt)
+ return mnt->mnt_ns == current->nsproxy->mnt_ns;
+ }
+
++/* for aufs, CONFIG_AUFS_BR_FUSE */
++int is_current_mnt_ns(struct vfsmount *mnt)
++{
++ return check_mnt(real_mount(mnt));
++}
++EXPORT_SYMBOL_GPL(is_current_mnt_ns);
++
+ /*
+ * vfsmount lock must be held for write
+ */
+@@ -2148,6 +2156,7 @@ int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg,
+ }
+ return 0;
+ }
++EXPORT_SYMBOL_GPL(iterate_mounts);
+
+ static void lock_mnt_tree(struct mount *mnt)
+ {
+diff --git a/fs/notify/group.c b/fs/notify/group.c
+index 1de6631a3925ee..3008eb37a18d46 100644
+--- a/fs/notify/group.c
++++ b/fs/notify/group.c
+@@ -100,6 +100,7 @@ void fsnotify_get_group(struct fsnotify_group *group)
+ {
+ refcount_inc(&group->refcnt);
+ }
++EXPORT_SYMBOL_GPL(fsnotify_get_group);
+
+ /*
+ * Drop a reference to a group. Free it if it's through.
+diff --git a/fs/open.c b/fs/open.c
+index 3494a9cd8046c4..dc6a1779c44d8c 100644
+--- a/fs/open.c
++++ b/fs/open.c
+@@ -67,6 +67,7 @@ int do_truncate(struct mnt_idmap *idmap, struct dentry *dentry,
+ inode_unlock(dentry->d_inode);
+ return ret;
+ }
++EXPORT_SYMBOL_GPL(do_truncate);
+
+ long vfs_truncate(const struct path *path, loff_t length)
+ {
+diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c
+index c6e7ebc637562d..d7ccfd90976464 100644
+--- a/fs/proc/nommu.c
++++ b/fs/proc/nommu.c
+@@ -39,7 +39,10 @@ static int nommu_region_show(struct seq_file *m, struct vm_region *region)
+ file = region->vm_file;
+
+ if (file) {
+- struct inode *inode = file_inode(region->vm_file);
++ struct inode *inode;
++
++ file = vmr_pr_or_file(region);
++ inode = file_inode(file);
+ dev = inode->i_sb->s_dev;
+ ino = inode->i_ino;
+ }
+diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
+index 435b61054b5b9e..e67bb5fc412535 100644
+--- a/fs/proc/task_mmu.c
++++ b/fs/proc/task_mmu.c
+@@ -273,7 +273,10 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
+ const char *name = NULL;
+
+ if (file) {
+- struct inode *inode = file_inode(vma->vm_file);
++ struct inode *inode;
++
++ file = vma_pr_or_file(vma);
++ inode = file_inode(file);
+ dev = inode->i_sb->s_dev;
+ ino = inode->i_ino;
+ pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT;
+@@ -2682,7 +2685,7 @@ static int show_numa_map(struct seq_file *m, void *v)
+ struct proc_maps_private *proc_priv = &numa_priv->proc_maps;
+ struct vm_area_struct *vma = v;
+ struct numa_maps *md = &numa_priv->md;
+- struct file *file = vma->vm_file;
++ struct file *file = vma_pr_or_file(vma);
+ struct mm_struct *mm = vma->vm_mm;
+ char buffer[64];
+ struct mempolicy *pol;
+diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
+index bce67453300031..b12b5a75c799ca 100644
+--- a/fs/proc/task_nommu.c
++++ b/fs/proc/task_nommu.c
+@@ -137,7 +137,10 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
+ file = vma->vm_file;
+
+ if (file) {
+- struct inode *inode = file_inode(vma->vm_file);
++ struct inode *inode;
++
++ file = vma_pr_or_file(vma);
++ inode = file_inode(file);
+ dev = inode->i_sb->s_dev;
+ ino = inode->i_ino;
+ pgoff = (loff_t)vma->vm_pgoff << PAGE_SHIFT;
+diff --git a/fs/read_write.c b/fs/read_write.c
+index 4771701c896bad..c79270aba79246 100644
+--- a/fs/read_write.c
++++ b/fs/read_write.c
+@@ -477,6 +477,7 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
+ inc_syscr(current);
+ return ret;
+ }
++EXPORT_SYMBOL_GPL(vfs_read);
+
+ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos)
+ {
+@@ -592,6 +593,7 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_
+ file_end_write(file);
+ return ret;
+ }
++EXPORT_SYMBOL_GPL(vfs_write);
+
+ /* file_ppos returns &file->f_pos or NULL if file is stream */
+ static inline loff_t *file_ppos(struct file *file)
+diff --git a/fs/splice.c b/fs/splice.c
+index d983d375ff1130..7ce1f1bc42684d 100644
+--- a/fs/splice.c
++++ b/fs/splice.c
+@@ -925,13 +925,14 @@ static int warn_unsupported(struct file *file, const char *op)
+ /*
+ * Attempt to initiate a splice from pipe to file.
+ */
+-static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
+- loff_t *ppos, size_t len, unsigned int flags)
++long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
++ loff_t *ppos, size_t len, unsigned int flags)
+ {
+ if (unlikely(!out->f_op->splice_write))
+ return warn_unsupported(out, "write");
+ return out->f_op->splice_write(pipe, out, ppos, len, flags);
+ }
++EXPORT_SYMBOL_GPL(do_splice_from);
+
+ /*
+ * Indicate to the caller that there was a premature EOF when reading from the
+diff --git a/fs/xattr.c b/fs/xattr.c
+index 09d9276034335f..890daee95a7bf3 100644
+--- a/fs/xattr.c
++++ b/fs/xattr.c
+@@ -406,6 +406,7 @@ vfs_getxattr_alloc(struct mnt_idmap *idmap, struct dentry *dentry,
+ *xattr_value = value;
+ return error;
+ }
++EXPORT_SYMBOL_GPL(vfs_getxattr_alloc);
+
+ ssize_t
+ __vfs_getxattr(struct dentry *dentry, struct inode *inode, const char *name,
+diff --git a/include/linux/fs.h b/include/linux/fs.h
+index 98b7a7a8c42e36..7bf7c5d0b4c9d8 100644
+--- a/include/linux/fs.h
++++ b/include/linux/fs.h
+@@ -1102,6 +1102,7 @@ extern void fasync_free(struct fasync_struct *);
+ /* can be called from interrupts */
+ extern void kill_fasync(struct fasync_struct **, int, int);
+
++extern int setfl(int fd, struct file *filp, unsigned int arg);
+ extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
+ extern int f_setown(struct file *filp, int who, int force);
+ extern void f_delown(struct file *filp);
+@@ -1936,6 +1937,7 @@ struct file_operations {
+ int (*lock) (struct file *, int, struct file_lock *);
+ unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
+ int (*check_flags)(int);
++ int (*setfl)(struct file *, unsigned long);
+ int (*flock) (struct file *, int, struct file_lock *);
+ ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
+ ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
+diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
+index dc2844b071c2c2..069ffb776c2c12 100644
+--- a/include/linux/lockdep.h
++++ b/include/linux/lockdep.h
+@@ -249,6 +249,8 @@ static inline int lockdep_match_key(struct lockdep_map *lock,
+ return lock->key == key;
+ }
+
++struct lock_class *lockdep_hlock_class(struct held_lock *hlock);
++
+ /*
+ * Acquire a lock.
+ *
+diff --git a/include/linux/mm.h b/include/linux/mm.h
+index da5219b48d5229..ba625a96957fed 100644
+--- a/include/linux/mm.h
++++ b/include/linux/mm.h
+@@ -2420,6 +2420,43 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping,
+ static inline struct vm_area_struct *vma_lookup(struct mm_struct *mm,
+ unsigned long addr);
+
++#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
++extern void vma_do_file_update_time(struct vm_area_struct *, const char[], int);
++extern struct file *vma_do_pr_or_file(struct vm_area_struct *, const char[],
++ int);
++extern void vma_do_get_file(struct vm_area_struct *, const char[], int);
++extern void vma_do_fput(struct vm_area_struct *, const char[], int);
++
++#define vma_file_update_time(vma) vma_do_file_update_time(vma, __func__, \
++ __LINE__)
++#define vma_pr_or_file(vma) vma_do_pr_or_file(vma, __func__, \
++ __LINE__)
++#define vma_get_file(vma) vma_do_get_file(vma, __func__, __LINE__)
++#define vma_fput(vma) vma_do_fput(vma, __func__, __LINE__)
+
-+ err = 0;
-+ *idx = -1;
-+ if (!au_opt_test(au_mntflags(sb), XINO))
-+ goto out; /* no xino */
++#ifndef CONFIG_MMU
++extern struct file *vmr_do_pr_or_file(struct vm_region *, const char[], int);
++extern void vmr_do_fput(struct vm_region *, const char[], int);
+
-+ xi = au_sbr(sb, bindex)->br_xino;
++#define vmr_pr_or_file(region) vmr_do_pr_or_file(region, __func__, \
++ __LINE__)
++#define vmr_fput(region) vmr_do_fput(region, __func__, __LINE__)
++#endif /* !CONFIG_MMU */
+
-+again:
-+ spin_lock(&xi->xi_nondir.spin);
-+ found = au_xinondir_find(xi, h_ino);
-+ if (found == -1) {
-+ empty = au_xinondir_find(xi, /*h_ino*/0);
-+ if (empty == -1) {
-+ empty = xi->xi_nondir.total;
-+ err = au_xinondir_expand(xi);
-+ if (unlikely(err))
-+ goto out_unlock;
-+ }
-+ xi->xi_nondir.array[empty] = h_ino;
-+ *idx = empty;
-+ } else {
-+ spin_unlock(&xi->xi_nondir.spin);
-+ wait_event(xi->xi_nondir.wqh,
-+ xi->xi_nondir.array[found] != h_ino);
-+ goto again;
-+ }
++#else
+
-+out_unlock:
-+ spin_unlock(&xi->xi_nondir.spin);
-+out:
-+ return err;
-+}
++#define vma_file_update_time(vma) file_update_time((vma)->vm_file)
++#define vma_pr_or_file(vma) (vma)->vm_file
++#define vma_get_file(vma) get_file((vma)->vm_file)
++#define vma_fput(vma) fput((vma)->vm_file)
+
-+/* ---------------------------------------------------------------------- */
++#ifndef CONFIG_MMU
++#define vmr_pr_or_file(region) (region)->vm_file
++#define vmr_fput(region) fput((region)->vm_file)
++#endif /* !CONFIG_MMU */
+
-+int au_xino_path(struct seq_file *seq, struct file *file)
-+{
-+ int err;
++#endif /* CONFIG_AUFS_FS */
+
-+ err = au_seq_path(seq, &file->f_path);
-+ if (unlikely(err))
-+ goto out;
+ extern int access_process_vm(struct task_struct *tsk, unsigned long addr,
+ void *buf, int len, unsigned int gup_flags);
+ extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
+diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
+index 957ce38768b2a8..cc556e47ea1727 100644
+--- a/include/linux/mm_types.h
++++ b/include/linux/mm_types.h
+@@ -527,6 +527,9 @@ struct vm_region {
+ unsigned long vm_top; /* region allocated to here */
+ unsigned long vm_pgoff; /* the offset in vm_file corresponding to vm_start */
+ struct file *vm_file; /* the backing file or NULL */
++#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
++ struct file *vm_prfile; /* the virtual backing file or NULL */
++#endif
+
+ int vm_usage; /* region usage count (access under nommu_region_sem) */
+ bool vm_icache_flushed : 1; /* true if the icache has been flushed for
+@@ -688,6 +691,9 @@ struct vm_area_struct {
+ unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE
+ units */
+ struct file * vm_file; /* File we map to (can be NULL). */
++#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
++ struct file *vm_prfile; /* shadow of vm_file */
++#endif
+ void * vm_private_data; /* was vm_pte (shared mem) */
+
+ #ifdef CONFIG_ANON_VMA_NAME
+diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h
+index 8f882f5881e879..6b9808f0984351 100644
+--- a/include/linux/mnt_namespace.h
++++ b/include/linux/mnt_namespace.h
+@@ -7,12 +7,15 @@ struct mnt_namespace;
+ struct fs_struct;
+ struct user_namespace;
+ struct ns_common;
++struct vfsmount;
+
+ extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *,
+ struct user_namespace *, struct fs_struct *);
+ extern void put_mnt_ns(struct mnt_namespace *ns);
+ extern struct ns_common *from_mnt_ns(struct mnt_namespace *);
+
++extern int is_current_mnt_ns(struct vfsmount *mnt);
+
-+#define Deleted "\\040(deleted)"
-+ seq->count -= sizeof(Deleted) - 1;
-+ AuDebugOn(memcmp(seq->buf + seq->count, Deleted,
-+ sizeof(Deleted) - 1));
-+#undef Deleted
+ extern const struct file_operations proc_mounts_operations;
+ extern const struct file_operations proc_mountinfo_operations;
+ extern const struct file_operations proc_mountstats_operations;
+diff --git a/include/linux/splice.h b/include/linux/splice.h
+index 6c461573434dde..7416cf375ad126 100644
+--- a/include/linux/splice.h
++++ b/include/linux/splice.h
+@@ -99,4 +99,10 @@ extern void splice_shrink_spd(struct splice_pipe_desc *);
+
+ extern const struct pipe_buf_operations page_cache_pipe_buf_ops;
+ extern const struct pipe_buf_operations default_pipe_buf_ops;
+
-+out:
-+ return err;
-+}
-diff -urN /usr/share/empty/include/uapi/linux/aufs_type.h linux/include/uapi/linux/aufs_type.h
---- /usr/share/empty/include/uapi/linux/aufs_type.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/include/uapi/linux/aufs_type.h 2023-10-31 09:31:04.203214083 +0100
++extern long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
++ loff_t *ppos, size_t len, unsigned int flags);
++extern long do_splice_to(struct file *in, loff_t *ppos,
++ struct pipe_inode_info *pipe, size_t len,
++ unsigned int flags);
+ #endif
+diff --git a/include/uapi/linux/aufs_type.h b/include/uapi/linux/aufs_type.h
+new file mode 100644
+index 00000000000000..207ee8ae216206
+--- /dev/null
++++ b/include/uapi/linux/aufs_type.h
@@ -0,0 +1,452 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+#include <limits.h>
+#endif /* __KERNEL__ */
+
-+#define AUFS_VERSION "6.x-rcN-20230925"
++#define AUFS_VERSION "6.x-rcN-20231106"
+
+/* todo? move this to linux-2.6.19/include/magic.h */
+#define AUFS_SUPER_MAGIC ('a' << 24 | 'u' << 16 | 'f' << 8 | 's')
+#define AUFS_CTL_FHSM_FD _IOW(AuCtlType, AuCtl_FHSM_FD, int)
+
+#endif /* __AUFS_TYPE_H__ */
-SPDX-License-Identifier: GPL-2.0
-aufs6.x-rcN loopback patch
-
-diff --git a/drivers/block/loop.c b/drivers/block/loop.c
-index 1fefc6a8d049..86f1f66305d2 100644
---- a/drivers/block/loop.c
-+++ b/drivers/block/loop.c
-@@ -54,7 +54,7 @@ struct loop_device {
- int lo_flags;
- char lo_file_name[LO_NAME_SIZE];
+diff --git a/kernel/fork.c b/kernel/fork.c
+index 10917c3e1f0366..6018e512fb9c32 100644
+--- a/kernel/fork.c
++++ b/kernel/fork.c
+@@ -731,7 +731,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
+ if (file) {
+ struct address_space *mapping = file->f_mapping;
+
+- get_file(file);
++ vma_get_file(tmp);
+ i_mmap_lock_write(mapping);
+ if (vma_is_shared_maywrite(tmp))
+ mapping_allow_writable(mapping);
+diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
+index 151bd3de59363a..d0ac4fc69a31dc 100644
+--- a/kernel/locking/lockdep.c
++++ b/kernel/locking/lockdep.c
+@@ -218,7 +218,7 @@ unsigned long max_lock_class_idx;
+ struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
+ DECLARE_BITMAP(lock_classes_in_use, MAX_LOCKDEP_KEYS);
-- struct file * lo_backing_file;
-+ struct file *lo_backing_file, *lo_backing_virt_file;
- struct block_device *lo_device;
+-static inline struct lock_class *hlock_class(struct held_lock *hlock)
++inline struct lock_class *lockdep_hlock_class(struct held_lock *hlock)
+ {
+ unsigned int class_idx = hlock->class_idx;
- gfp_t old_gfp_mask;
-@@ -510,6 +510,15 @@ static inline void loop_update_dio(struct loop_device *lo)
- lo->use_dio);
+@@ -239,6 +239,8 @@ static inline struct lock_class *hlock_class(struct held_lock *hlock)
+ */
+ return lock_classes + class_idx;
}
++EXPORT_SYMBOL_GPL(lockdep_hlock_class);
++#define hlock_class(hlock) lockdep_hlock_class(hlock)
-+static struct file *loop_real_file(struct file *file)
-+{
-+ struct file *f = NULL;
-+
-+ if (file->f_path.dentry->d_sb->s_op->real_loop)
-+ f = file->f_path.dentry->d_sb->s_op->real_loop(file);
-+ return f;
-+}
-+
- static void loop_reread_partitions(struct loop_device *lo)
- {
- int rc;
-@@ -567,6 +576,7 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
- {
- struct file *file = fget(arg);
- struct file *old_file;
-+ struct file *f, *virt_file = NULL, *old_virt_file;
- int error;
- bool partscan;
- bool is_loop;
-@@ -590,11 +600,19 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
- if (!(lo->lo_flags & LO_FLAGS_READ_ONLY))
- goto out_err;
+ #ifdef CONFIG_LOCK_STAT
+ static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], cpu_lock_stats);
+diff --git a/kernel/task_work.c b/kernel/task_work.c
+index 95a7e1b7f1dab2..5053670775d3ce 100644
+--- a/kernel/task_work.c
++++ b/kernel/task_work.c
+@@ -183,3 +183,4 @@ void task_work_run(void)
+ } while (work);
+ }
+ }
++EXPORT_SYMBOL_GPL(task_work_run);
+diff --git a/mm/Makefile b/mm/Makefile
+index 33873c8aedb399..ae036592066aa6 100644
+--- a/mm/Makefile
++++ b/mm/Makefile
+@@ -138,3 +138,4 @@ obj-$(CONFIG_IO_MAPPING) += io-mapping.o
+ obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o
+ obj-$(CONFIG_GENERIC_IOREMAP) += ioremap.o
+ obj-$(CONFIG_SHRINKER_DEBUG) += shrinker_debug.o
++obj-y += prfile.o
+diff --git a/mm/filemap.c b/mm/filemap.c
+index ad5b4aa049a380..e855d6c72168fe 100644
+--- a/mm/filemap.c
++++ b/mm/filemap.c
+@@ -3584,7 +3584,7 @@ vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf)
+ vm_fault_t ret = VM_FAULT_LOCKED;
-+ f = loop_real_file(file);
-+ if (f) {
-+ virt_file = file;
-+ file = f;
-+ get_file(file);
-+ }
-+
- error = loop_validate_file(file, bdev);
- if (error)
- goto out_err;
+ sb_start_pagefault(mapping->host->i_sb);
+- file_update_time(vmf->vma->vm_file);
++ vma_file_update_time(vmf->vma);
+ folio_lock(folio);
+ if (folio->mapping != mapping) {
+ folio_unlock(folio);
+diff --git a/mm/mmap.c b/mm/mmap.c
+index aa82eec17489ca..a37484d87ff0b3 100644
+--- a/mm/mmap.c
++++ b/mm/mmap.c
+@@ -140,7 +140,7 @@ static void remove_vma(struct vm_area_struct *vma, bool unreachable)
+ if (vma->vm_ops && vma->vm_ops->close)
+ vma->vm_ops->close(vma);
+ if (vma->vm_file)
+- fput(vma->vm_file);
++ vma_fput(vma);
+ mpol_put(vma_policy(vma));
+ if (unreachable)
+ __vm_area_free(vma);
+@@ -554,7 +554,7 @@ static inline void vma_complete(struct vma_prepare *vp,
+ if (vp->file) {
+ uprobe_munmap(vp->remove, vp->remove->vm_start,
+ vp->remove->vm_end);
+- fput(vp->file);
++ vma_fput(vp->vma);
+ }
+ if (vp->remove->anon_vma)
+ anon_vma_merge(vp->vma, vp->remove);
+@@ -2390,7 +2390,7 @@ static int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
+ goto out_free_mpol;
- old_file = lo->lo_backing_file;
-+ old_virt_file = lo->lo_backing_virt_file;
+ if (new->vm_file)
+- get_file(new->vm_file);
++ vma_get_file(new);
- error = -EINVAL;
+ if (new->vm_ops && new->vm_ops->open)
+ new->vm_ops->open(new);
+@@ -2888,7 +2888,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
+ * and cause general protection fault
+ * ultimately.
+ */
+- fput(vma->vm_file);
++ vma_fput(vma);
+ vm_area_free(vma);
+ vma = merge;
+ /* Update vm_flags to pick up the change. */
+@@ -2983,7 +2983,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
-@@ -607,6 +625,7 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
- blk_mq_freeze_queue(lo->lo_queue);
- mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask);
- lo->lo_backing_file = file;
-+ lo->lo_backing_virt_file = virt_file;
- lo->old_gfp_mask = mapping_gfp_mask(file->f_mapping);
- mapping_set_gfp_mask(file->f_mapping,
- lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
-@@ -629,6 +648,8 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
- * dependency.
- */
- fput(old_file);
-+ if (old_virt_file)
-+ fput(old_virt_file);
- if (partscan)
- loop_reread_partitions(lo);
+ if (file || vma->vm_file) {
+ unmap_and_free_vma:
+- fput(vma->vm_file);
++ vma_fput(vma);
+ vma->vm_file = NULL;
-@@ -642,6 +663,8 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
- loop_global_unlock(lo, is_loop);
- out_putf:
- fput(file);
-+ if (virt_file)
-+ fput(virt_file);
- goto done;
- }
+ vma_iter_set(&vmi, vma->vm_end);
+@@ -3045,6 +3045,9 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
+ unsigned long populate = 0;
+ unsigned long ret = -EINVAL;
+ struct file *file;
++#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
++ struct file *prfile;
++#endif
-@@ -1013,6 +1036,7 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
- const struct loop_config *config)
- {
- struct file *file = fget(config->fd);
-+ struct file *f, *virt_file = NULL;
- struct inode *inode;
- struct address_space *mapping;
- int error;
-@@ -1028,6 +1052,13 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
- /* This is safe, since we have a reference from open(). */
- __module_get(THIS_MODULE);
+ pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/mm/remap_file_pages.rst.\n",
+ current->comm, current->pid);
+@@ -3103,10 +3106,34 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
+ if (vma->vm_flags & VM_LOCKED)
+ flags |= MAP_LOCKED;
-+ f = loop_real_file(file);
-+ if (f) {
-+ virt_file = file;
-+ file = f;
-+ get_file(file);
-+ }
++#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
++ vma_get_file(vma);
++ file = vma->vm_file;
++ prfile = vma->vm_prfile;
++ ret = do_mmap(vma->vm_file, start, size,
++ prot, flags, /*vm_flags*/0, pgoff, &populate, NULL);
++ if (!IS_ERR_VALUE(ret) && file && prfile) {
++ struct vm_area_struct *new_vma;
+
- /*
- * If we don't hold exclusive handle for the device, upgrade to it
- * here to avoid changing device under exclusive owner.
-@@ -1091,6 +1122,7 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
- lo->use_dio = lo->lo_flags & LO_FLAGS_DIRECT_IO;
- lo->lo_device = bdev;
- lo->lo_backing_file = file;
-+ lo->lo_backing_virt_file = virt_file;
- lo->old_gfp_mask = mapping_gfp_mask(mapping);
- mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
-
-@@ -1146,6 +1178,8 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
- bd_abort_claiming(bdev, loop_configure);
- out_putf:
++ new_vma = find_vma(mm, ret);
++ if (!new_vma->vm_prfile)
++ new_vma->vm_prfile = prfile;
++ if (prfile)
++ get_file(prfile);
++ }
++ /*
++ * two fput()s instead of vma_fput(vma),
++ * coz vma may not be available anymore.
++ */
++ fput(file);
++ if (prfile)
++ fput(prfile);
++#else
+ file = get_file(vma->vm_file);
+ ret = do_mmap(vma->vm_file, start, size,
+ prot, flags, 0, pgoff, &populate, NULL);
fput(file);
-+ if (virt_file)
-+ fput(virt_file);
- /* This is safe: open() is still holding a reference. */
- module_put(THIS_MODULE);
- return error;
-@@ -1154,6 +1188,7 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
- static void __loop_clr_fd(struct loop_device *lo, bool release)
- {
- struct file *filp;
-+ struct file *virt_filp = lo->lo_backing_virt_file;
- gfp_t gfp = lo->old_gfp_mask;
++#endif /* CONFIG_AUFS_FS */
+ out:
+ mmap_write_unlock(mm);
+ if (populate)
+@@ -3450,7 +3477,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
+ if (anon_vma_clone(new_vma, vma))
+ goto out_free_mempol;
+ if (new_vma->vm_file)
+- get_file(new_vma->vm_file);
++ vma_get_file(new_vma);
+ if (new_vma->vm_ops && new_vma->vm_ops->open)
+ new_vma->vm_ops->open(new_vma);
+ if (vma_link(mm, new_vma))
+@@ -3464,7 +3491,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
+ new_vma->vm_ops->close(new_vma);
- if (test_bit(QUEUE_FLAG_WC, &lo->lo_queue->queue_flags))
-@@ -1170,6 +1205,7 @@ static void __loop_clr_fd(struct loop_device *lo, bool release)
- spin_lock_irq(&lo->lo_lock);
- filp = lo->lo_backing_file;
- lo->lo_backing_file = NULL;
-+ lo->lo_backing_virt_file = NULL;
- spin_unlock_irq(&lo->lo_lock);
+ if (new_vma->vm_file)
+- fput(new_vma->vm_file);
++ vma_fput(new_vma);
- lo->lo_device = NULL;
-@@ -1232,6 +1268,8 @@ static void __loop_clr_fd(struct loop_device *lo, bool release)
- * fput can take open_mutex which is usually taken before lo_mutex.
- */
- fput(filp);
-+ if (virt_filp)
-+ fput(virt_filp);
- }
+ unlink_anon_vmas(new_vma);
+ out_free_mempol:
+diff --git a/mm/nommu.c b/mm/nommu.c
+index b6dc558d314408..d96655486468e4 100644
+--- a/mm/nommu.c
++++ b/mm/nommu.c
+@@ -523,7 +523,7 @@ static void __put_nommu_region(struct vm_region *region)
+ up_write(&nommu_region_sem);
- static int loop_clr_fd(struct loop_device *lo)
-diff --git a/fs/aufs/f_op.c b/fs/aufs/f_op.c
-index fa8a517ffd0c..c18f7bcef81b 100644
---- a/fs/aufs/f_op.c
-+++ b/fs/aufs/f_op.c
-@@ -311,7 +311,7 @@ static ssize_t aufs_read_iter(struct kiocb *kio, struct iov_iter *iov_iter)
- if (IS_ERR(h_file))
- goto out;
+ if (region->vm_file)
+- fput(region->vm_file);
++ vmr_fput(region);
-- if (au_test_loopback_kthread()) {
-+ if (0 && au_test_loopback_kthread()) {
- au_warn_loopback(h_file->f_path.dentry->d_sb);
- if (file->f_mapping != h_file->f_mapping) {
- file->f_mapping = h_file->f_mapping;
-diff --git a/fs/aufs/loop.c b/fs/aufs/loop.c
-index 58043e31e5f3..e2bfae6f9d59 100644
---- a/fs/aufs/loop.c
-+++ b/fs/aufs/loop.c
-@@ -133,3 +133,19 @@ void au_loopback_fin(void)
- symbol_put(loop_backing_file);
- au_kfree_try_rcu(au_warn_loopback_array);
+ /* IO memory and memory shared directly out of the pagecache
+ * from ramfs/tmpfs mustn't be released here */
+@@ -603,7 +603,7 @@ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma)
+ if (vma->vm_ops && vma->vm_ops->close)
+ vma->vm_ops->close(vma);
+ if (vma->vm_file)
+- fput(vma->vm_file);
++ vma_fput(vma);
+ put_nommu_region(vma->vm_region);
+ vm_area_free(vma);
}
+@@ -1135,7 +1135,7 @@ unsigned long do_mmap(struct file *file,
+ goto error_just_free;
+ }
+ }
+- fput(region->vm_file);
++ vmr_fput(region);
+ kmem_cache_free(vm_region_jar, region);
+ region = pregion;
+ result = start;
+@@ -1221,10 +1221,10 @@ unsigned long do_mmap(struct file *file,
+ error:
+ vma_iter_free(&vmi);
+ if (region->vm_file)
+- fput(region->vm_file);
++ vmr_fput(region);
+ kmem_cache_free(vm_region_jar, region);
+ if (vma->vm_file)
+- fput(vma->vm_file);
++ vma_fput(vma);
+ vm_area_free(vma);
+ return ret;
+
+diff --git a/mm/prfile.c b/mm/prfile.c
+new file mode 100644
+index 00000000000000..8f820a2353646f
+--- /dev/null
++++ b/mm/prfile.c
+@@ -0,0 +1,86 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Mainly for aufs which mmap(2) different file and wants to print different
++ * path in /proc/PID/maps.
++ * Call these functions via macros defined in linux/mm.h.
++ *
++ * See Documentation/filesystems/aufs/design/06mmap.txt
++ *
++ * Copyright (c) 2014-2022 Junjro R. Okajima
++ * Copyright (c) 2014 Ian Campbell
++ */
+
-+/* ---------------------------------------------------------------------- */
++#include <linux/mm.h>
++#include <linux/file.h>
++#include <linux/fs.h>
+
-+/* support the loopback block device insude aufs */
++/* #define PRFILE_TRACE */
++static inline void prfile_trace(struct file *f, struct file *pr,
++ const char func[], int line, const char func2[])
++{
++#ifdef PRFILE_TRACE
++ if (pr)
++ pr_info("%s:%d: %s, %pD2\n", func, line, func2, f);
++#endif
++}
+
-+struct file *aufs_real_loop(struct file *file)
++void vma_do_file_update_time(struct vm_area_struct *vma, const char func[],
++ int line)
+{
-+ struct file *f;
++ struct file *f = vma->vm_file, *pr = vma->vm_prfile;
+
-+ BUG_ON(!au_test_aufs(file->f_path.dentry->d_sb));
-+ fi_read_lock(file);
-+ f = au_hf_top(file);
-+ fi_read_unlock(file);
-+ AuDebugOn(!f);
-+ return f;
++ prfile_trace(f, pr, func, line, __func__);
++ file_update_time(f);
++ if (f && pr)
++ file_update_time(pr);
+}
-diff --git a/fs/aufs/loop.h b/fs/aufs/loop.h
-index 03d4908a6c03..34d356e181d5 100644
---- a/fs/aufs/loop.h
-+++ b/fs/aufs/loop.h
-@@ -26,6 +26,8 @@ void au_warn_loopback(struct super_block *h_sb);
-
- int au_loopback_init(void);
- void au_loopback_fin(void);
+
-+struct file *aufs_real_loop(struct file *file);
- #else
- AuStub(struct file *, loop_backing_file, return NULL, struct super_block *sb)
++struct file *vma_do_pr_or_file(struct vm_area_struct *vma, const char func[],
++ int line)
++{
++ struct file *f = vma->vm_file, *pr = vma->vm_prfile;
++
++ prfile_trace(f, pr, func, line, __func__);
++ return (f && pr) ? pr : f;
++}
++
++void vma_do_get_file(struct vm_area_struct *vma, const char func[], int line)
++{
++ struct file *f = vma->vm_file, *pr = vma->vm_prfile;
++
++ prfile_trace(f, pr, func, line, __func__);
++ get_file(f);
++ if (f && pr)
++ get_file(pr);
++}
++
++void vma_do_fput(struct vm_area_struct *vma, const char func[], int line)
++{
++ struct file *f = vma->vm_file, *pr = vma->vm_prfile;
++
++ prfile_trace(f, pr, func, line, __func__);
++ fput(f);
++ if (f && pr)
++ fput(pr);
++}
++
++#ifndef CONFIG_MMU
++struct file *vmr_do_pr_or_file(struct vm_region *region, const char func[],
++ int line)
++{
++ struct file *f = region->vm_file, *pr = region->vm_prfile;
++
++ prfile_trace(f, pr, func, line, __func__);
++ return (f && pr) ? pr : f;
++}
++
++void vmr_do_fput(struct vm_region *region, const char func[], int line)
++{
++ struct file *f = region->vm_file, *pr = region->vm_prfile;
++
++ prfile_trace(f, pr, func, line, __func__);
++ fput(f);
++ if (f && pr)
++ fput(pr);
++}
++#endif /* !CONFIG_MMU */
+diff --git a/security/security.c b/security/security.c
+index dcb3e7014f9bdd..a7135660dd2c70 100644
+--- a/security/security.c
++++ b/security/security.c
+@@ -1750,6 +1750,7 @@ int security_path_rmdir(const struct path *dir, struct dentry *dentry)
+ return 0;
+ return call_int_hook(path_rmdir, 0, dir, dentry);
+ }
++EXPORT_SYMBOL_GPL(security_path_rmdir);
-@@ -36,6 +38,8 @@ AuStubVoid(au_warn_loopback, struct super_block *h_sb)
+ /**
+ * security_path_unlink() - Check if removing a hard link is allowed
+@@ -1785,6 +1786,7 @@ int security_path_symlink(const struct path *dir, struct dentry *dentry,
+ return 0;
+ return call_int_hook(path_symlink, 0, dir, dentry, old_name);
+ }
++EXPORT_SYMBOL_GPL(security_path_symlink);
- AuStubInt0(au_loopback_init, void)
- AuStubVoid(au_loopback_fin, void)
-+
-+AuStub(struct file *, aufs_real_loop, return NULL, struct file *file)
- #endif /* BLK_DEV_LOOP */
+ /**
+ * security_path_link - Check if creating a hard link is allowed
+@@ -1803,6 +1805,7 @@ int security_path_link(struct dentry *old_dentry, const struct path *new_dir,
+ return 0;
+ return call_int_hook(path_link, 0, old_dentry, new_dir, new_dentry);
+ }
++EXPORT_SYMBOL_GPL(security_path_link);
- #endif /* __KERNEL__ */
-diff --git a/fs/aufs/super.c b/fs/aufs/super.c
-index 07d3412e950f..c4a00f620e57 100644
---- a/fs/aufs/super.c
-+++ b/fs/aufs/super.c
-@@ -758,7 +758,10 @@ const struct super_operations aufs_sop = {
- .show_options = aufs_show_options,
- .statfs = aufs_statfs,
- .put_super = aufs_put_super,
-- .sync_fs = aufs_sync_fs
-+ .sync_fs = aufs_sync_fs,
-+#ifdef CONFIG_AUFS_BDEV_LOOP
-+ .real_loop = aufs_real_loop
-+#endif
- };
+ /**
+ * security_path_rename() - Check if renaming a file is allowed
+@@ -1864,6 +1867,7 @@ int security_path_chmod(const struct path *path, umode_t mode)
+ return 0;
+ return call_int_hook(path_chmod, 0, path, mode);
+ }
++EXPORT_SYMBOL_GPL(security_path_chmod);
- /* ---------------------------------------------------------------------- */
-diff --git a/include/linux/fs.h b/include/linux/fs.h
-index dd5871d0c429..748091221f2d 100644
---- a/include/linux/fs.h
-+++ b/include/linux/fs.h
-@@ -2056,6 +2056,11 @@ struct super_operations {
- long (*free_cached_objects)(struct super_block *,
- struct shrink_control *);
- void (*shutdown)(struct super_block *sb);
-+
-+#if IS_ENABLED(CONFIG_BLK_DEV_LOOP) || IS_ENABLED(CONFIG_BLK_DEV_LOOP_MODULE)
-+ /* and aufs */
-+ struct file *(*real_loop)(struct file *);
-+#endif
- };
+ /**
+ * security_path_chown() - Check if changing the file's owner/group is allowed
+@@ -1881,6 +1885,7 @@ int security_path_chown(const struct path *path, kuid_t uid, kgid_t gid)
+ return 0;
+ return call_int_hook(path_chown, 0, path, uid, gid);
+ }
++EXPORT_SYMBOL_GPL(security_path_chown);
- /*
+ /**
+ * security_path_chroot() - Check if changing the root directory is allowed
+@@ -2110,6 +2115,7 @@ int security_inode_permission(struct inode *inode, int mask)
+ return 0;
+ return call_int_hook(inode_permission, 0, inode, mask);
+ }
++EXPORT_SYMBOL_GPL(security_inode_permission);
+
+ /**
+ * security_inode_setattr() - Check if setting file attributes is allowed
+@@ -2588,6 +2594,7 @@ int security_file_permission(struct file *file, int mask)
+
+ return fsnotify_perm(file, mask);
+ }
++EXPORT_SYMBOL_GPL(security_file_permission);
+
+ /**
+ * security_file_alloc() - Allocate and init a file's LSM blob
+@@ -2854,6 +2861,7 @@ int security_file_truncate(struct file *file)
+ {
+ return call_int_hook(file_truncate, 0, file);
+ }
++EXPORT_SYMBOL_GPL(security_file_truncate);
+
+ /**
+ * security_task_alloc() - Allocate a task's LSM blob