aufs: copy-up 4/7, body

The functions for
- create the copy-up target file
- copy filedata
- copy metadata

In copying filedata, I had tried splice_direct() instead of repeating
read/write. Surprisingly, I could not see a big difference. So let's
keep this approach for a while. Someday SEEK_DATA/SEEK_HOLE become more
popular, it may help optimizing this read/write.
Signed-off-by: J. R. Okajima <hooanon05g@gmail.com>

fs/aufs/branch.h

@@ -221,6 +221,12 @@ aufs_bindex_t au_sbr_id(struct super_block *sb, aufs_bindex_t bindex)
 	return au_sbr(sb, bindex)->br_id;
 }
 
+static inline
+struct vfsmount *au_sbr_mnt(struct super_block *sb, aufs_bindex_t bindex)
+{
+	return au_br_mnt(au_sbr(sb, bindex));
+}
+
 static inline
 struct super_block *au_sbr_sb(struct super_block *sb, aufs_bindex_t bindex)
 {

fs/aufs/cpup.c

@@ -8,6 +8,9 @@
  */
 
 #include <linux/fs_stack.h>
+#include <linux/mm.h>
+#include <linux/task_work.h>
+#include <linux/uaccess.h>
 #include "aufs.h"
 
 void au_cpup_attr_flags(struct inode *dst, unsigned int iflags)
@@ -138,3 +141,789 @@ void au_dtime_revert(struct au_dtime *dt)
 	if (unlikely(err))
 		pr_warn("restoring timestamps failed(%d). ignored\n", err);
 }
+
+/* ---------------------------------------------------------------------- */
+
+/* internal use only */
+struct au_cpup_reg_attr {
+	int		valid;
+	struct kstat	st;
+	unsigned int	iflags; /* inode->i_flags */
+};
+
+static noinline_for_stack
+int cpup_iattr(struct dentry *dst, aufs_bindex_t bindex, struct dentry *h_src,
+	       struct au_cpup_reg_attr *h_src_attr)
+{
+	int err, sbits;
+	struct iattr ia;
+	struct path h_path;
+	struct inode *h_isrc, *h_idst;
+	struct kstat *h_st;
+
+	h_path.dentry = au_h_dptr(dst, bindex);
+	h_idst = d_inode(h_path.dentry);
+	h_path.mnt = au_sbr_mnt(dst->d_sb, bindex);
+	h_isrc = d_inode(h_src);
+	ia.ia_valid = ATTR_FORCE | ATTR_UID | ATTR_GID
+		| ATTR_ATIME | ATTR_MTIME
+		| ATTR_ATIME_SET | ATTR_MTIME_SET;
+	if (h_src_attr && h_src_attr->valid) {
+		h_st = &h_src_attr->st;
+		ia.ia_uid = h_st->uid;
+		ia.ia_gid = h_st->gid;
+		ia.ia_atime = h_st->atime;
+		ia.ia_mtime = h_st->mtime;
+		if (h_idst->i_mode != h_st->mode
+		    && !S_ISLNK(h_idst->i_mode)) {
+			ia.ia_valid |= ATTR_MODE;
+			ia.ia_mode = h_st->mode;
+		}
+		sbits = !!(h_st->mode & (S_ISUID | S_ISGID));
+		au_cpup_attr_flags(h_idst, h_src_attr->iflags);
+	} else {
+		ia.ia_uid = h_isrc->i_uid;
+		ia.ia_gid = h_isrc->i_gid;
+		ia.ia_atime = h_isrc->i_atime;
+		ia.ia_mtime = h_isrc->i_mtime;
+		if (h_idst->i_mode != h_isrc->i_mode
+		    && !S_ISLNK(h_idst->i_mode)) {
+			ia.ia_valid |= ATTR_MODE;
+			ia.ia_mode = h_isrc->i_mode;
+		}
+		sbits = !!(h_isrc->i_mode & (S_ISUID | S_ISGID));
+		au_cpup_attr_flags(h_idst, h_isrc->i_flags);
+	}
+	/* no delegation since it is just created */
+	err = vfsub_notify_change(&h_path, &ia, /*delegated*/NULL);
+
+	/* is this nfs only? */
+	if (!err && sbits && au_test_nfs(h_path.dentry->d_sb)) {
+		ia.ia_valid = ATTR_FORCE | ATTR_MODE;
+		ia.ia_mode = h_isrc->i_mode;
+		err = vfsub_notify_change(&h_path, &ia, /*delegated*/NULL);
+	}
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_do_copy_file(struct file *dst, struct file *src, loff_t len,
+			   char *buf, unsigned long blksize)
+{
+	int err;
+	size_t sz, rbytes, wbytes;
+	unsigned char all_zero;
+	char *p, *zp;
+	struct inode *h_inode;
+	/* reduce stack usage */
+	struct iattr *ia;
+
+	zp = page_address(ZERO_PAGE(0));
+	if (unlikely(!zp))
+		return -ENOMEM; /* possible? */
+
+	err = 0;
+	all_zero = 0;
+	while (len) {
+		AuDbg("len %lld\n", len);
+		sz = blksize;
+		if (len < blksize)
+			sz = len;
+
+		rbytes = 0;
+		/* todo: signal_pending? */
+		while (!rbytes || err == -EAGAIN || err == -EINTR) {
+			rbytes = vfsub_read_k(src, buf, sz, &src->f_pos);
+			err = rbytes;
+		}
+		if (unlikely(err < 0))
+			break;
+
+		all_zero = 0;
+		if (len >= rbytes && rbytes == blksize)
+			all_zero = !memcmp(buf, zp, rbytes);
+		if (!all_zero) {
+			wbytes = rbytes;
+			p = buf;
+			while (wbytes) {
+				size_t b;
+
+				b = vfsub_write_k(dst, p, wbytes, &dst->f_pos);
+				err = b;
+				/* todo: signal_pending? */
+				if (unlikely(err == -EAGAIN || err == -EINTR))
+					continue;
+				if (unlikely(err < 0))
+					break;
+				wbytes -= b;
+				p += b;
+			}
+			if (unlikely(err < 0))
+				break;
+		} else {
+			loff_t res;
+
+			AuLabel(hole);
+			res = vfsub_llseek(dst, rbytes, SEEK_CUR);
+			err = res;
+			if (unlikely(res < 0))
+				break;
+		}
+		len -= rbytes;
+		err = 0;
+	}
+
+	/* the last block may be a hole */
+	if (!err && all_zero) {
+		AuLabel(last hole);
+
+		err = 1;
+		if (au_test_nfs(dst->f_path.dentry->d_sb)) {
+			/* nfs requires this step to make last hole */
+			/* is this only nfs? */
+			do {
+				/* todo: signal_pending? */
+				err = vfsub_write_k(dst, "\0", 1, &dst->f_pos);
+			} while (err == -EAGAIN || err == -EINTR);
+			if (err == 1)
+				dst->f_pos--;
+		}
+
+		if (err == 1) {
+			ia = (void *)buf;
+			ia->ia_size = dst->f_pos;
+			ia->ia_valid = ATTR_SIZE | ATTR_FILE;
+			ia->ia_file = dst;
+			h_inode = file_inode(dst);
+			inode_lock_nested(h_inode, AuLsc_I_CHILD2);
+			/* no delegation since it is just created */
+			err = vfsub_notify_change(&dst->f_path, ia,
+						  /*delegated*/NULL);
+			inode_unlock(h_inode);
+		}
+	}
+
+	return err;
+}
+
+int au_copy_file(struct file *dst, struct file *src, loff_t len)
+{
+	int err;
+	unsigned long blksize;
+	unsigned char do_kfree;
+	char *buf;
+	struct super_block *h_sb;
+
+	err = -ENOMEM;
+	h_sb = file_inode(dst)->i_sb;
+	blksize = h_sb->s_blocksize;
+	if (!blksize || PAGE_SIZE < blksize)
+		blksize = PAGE_SIZE;
+	AuDbg("blksize %lu\n", blksize);
+	do_kfree = (blksize != PAGE_SIZE && blksize >= sizeof(struct iattr *));
+	if (do_kfree)
+		buf = kmalloc(blksize, GFP_NOFS);
+	else
+		buf = (void *)__get_free_page(GFP_NOFS);
+	if (unlikely(!buf))
+		goto out;
+
+	if (len > (1 << 22))
+		AuDbg("copying a large file %lld\n", (long long)len);
+
+	src->f_pos = 0;
+	dst->f_pos = 0;
+	err = au_do_copy_file(dst, src, len, buf, blksize);
+	if (do_kfree) {
+		AuDebugOn(!au_kfree_do_sz_test(blksize));
+		au_kfree_do_rcu(buf);
+	} else
+		free_page((unsigned long)buf);
+
+out:
+	return err;
+}
+
+static int au_do_copy(struct file *dst, struct file *src, loff_t len)
+{
+	int err;
+	struct super_block *h_src_sb;
+	struct inode *h_src_inode;
+
+	h_src_inode = file_inode(src);
+	h_src_sb = h_src_inode->i_sb;
+
+	/* XFS acquires inode_lock */
+	if (!au_test_xfs(h_src_sb))
+		err = au_copy_file(dst, src, len);
+	else {
+		inode_unlock_shared(h_src_inode);
+		err = au_copy_file(dst, src, len);
+		inode_lock_shared_nested(h_src_inode, AuLsc_I_CHILD);
+	}
+
+	return err;
+}
+
+static int au_clone_or_copy(struct file *dst, struct file *src, loff_t len)
+{
+	int err;
+	loff_t lo;
+	struct super_block *h_src_sb;
+	struct inode *h_src_inode;
+
+	h_src_inode = file_inode(src);
+	h_src_sb = h_src_inode->i_sb;
+	if (h_src_sb != file_inode(dst)->i_sb
+	    || !dst->f_op->remap_file_range) {
+		err = au_do_copy(dst, src, len);
+		goto out;
+	}
+
+	if (!au_test_nfs(h_src_sb)) {
+		inode_unlock_shared(h_src_inode);
+		lo = vfsub_clone_file_range(src, dst, len);
+		inode_lock_shared_nested(h_src_inode, AuLsc_I_CHILD);
+	} else
+		lo = vfsub_clone_file_range(src, dst, len);
+	if (lo == len) {
+		err = 0;
+		goto out; /* success */
+	} else if (lo >= 0)
+		/* todo: possible? */
+		/* paritially succeeded */
+		AuDbg("lo %lld, len %lld. Retrying.\n", lo, len);
+	else if (lo != -EOPNOTSUPP) {
+		/* older XFS has a condition in cloning */
+		err = lo;
+		goto out;
+	}
+
+	/* the backend fs on NFS may not support cloning */
+	err = au_do_copy(dst, src, len);
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+/*
+ * to support a sparse file which is opened with O_APPEND,
+ * we need to close the file.
+ */
+static int au_cp_regular(struct au_cp_generic *cpg)
+{
+	int err, i;
+	enum { SRC, DST };
+	struct {
+		aufs_bindex_t bindex;
+		unsigned int flags;
+		struct dentry *dentry;
+		struct file *file;
+	} *f, file[] = {
+		{
+			.bindex = cpg->bsrc,
+			.flags = O_RDONLY | O_NOATIME | O_LARGEFILE,
+		},
+		{
+			.bindex = cpg->bdst,
+			.flags = O_WRONLY | O_NOATIME | O_LARGEFILE,
+		}
+	};
+	struct au_branch *br;
+	struct super_block *sb, *h_src_sb;
+	struct inode *h_src_inode;
+	struct task_struct *tsk = current;
+
+	/* bsrc branch can be ro/rw. */
+	sb = cpg->dentry->d_sb;
+	f = file;
+	for (i = 0; i < 2; i++, f++) {
+		f->dentry = au_h_dptr(cpg->dentry, f->bindex);
+		f->file = au_h_open(cpg->dentry, f->bindex, f->flags,
+				    /*file*/NULL);
+		if (IS_ERR(f->file)) {
+			err = PTR_ERR(f->file);
+			if (i == SRC)
+				goto out;
+			else
+				goto out_src;
+		}
+	}
+
+	/* try stopping to update while we copyup */
+	h_src_inode = d_inode(file[SRC].dentry);
+	h_src_sb = h_src_inode->i_sb;
+	if (!au_test_nfs(h_src_sb))
+		IMustLock(h_src_inode);
+	err = au_clone_or_copy(file[DST].file, file[SRC].file, cpg->len);
+
+	/* i wonder if we had O_NO_DELAY_FPUT flag */
+	if (tsk->flags & PF_KTHREAD)
+		__fput_sync(file[DST].file);
+	else {
+		/* it happened actually */
+		fput(file[DST].file);
+		/*
+		 * too bad.
+		 * we have to call both since we don't know which place the file
+		 * was added to.
+		 */
+		task_work_run();
+		flush_delayed_fput();
+	}
+	br = au_sbr(sb, file[DST].bindex);
+	au_lcnt_dec(&br->br_nfiles);
+
+out_src:
+	fput(file[SRC].file);
+	br = au_sbr(sb, file[SRC].bindex);
+	au_lcnt_dec(&br->br_nfiles);
+out:
+	return err;
+}
+
+static int au_do_cpup_regular(struct au_cp_generic *cpg,
+			      struct au_cpup_reg_attr *h_src_attr)
+{
+	int err, rerr;
+	loff_t l;
+	struct path h_path;
+	struct inode *h_src_inode, *h_dst_inode;
+
+	err = 0;
+	h_src_inode = au_h_iptr(d_inode(cpg->dentry), cpg->bsrc);
+	l = i_size_read(h_src_inode);
+	if (cpg->len == -1 || l < cpg->len)
+		cpg->len = l;
+	if (cpg->len) {
+		/* try stopping to update while we are referencing */
+		inode_lock_shared_nested(h_src_inode, AuLsc_I_CHILD);
+		au_pin_hdir_unlock(cpg->pin);
+
+		h_path.dentry = au_h_dptr(cpg->dentry, cpg->bsrc);
+		h_path.mnt = au_sbr_mnt(cpg->dentry->d_sb, cpg->bsrc);
+		h_src_attr->iflags = h_src_inode->i_flags;
+		if (!au_test_nfs(h_src_inode->i_sb))
+			err = vfsub_getattr(&h_path, &h_src_attr->st);
+		else {
+			inode_unlock_shared(h_src_inode);
+			err = vfsub_getattr(&h_path, &h_src_attr->st);
+			inode_lock_shared_nested(h_src_inode, AuLsc_I_CHILD);
+		}
+		if (unlikely(err)) {
+			inode_unlock_shared(h_src_inode);
+			goto out;
+		}
+		h_src_attr->valid = 1;
+		if (!au_test_nfs(h_src_inode->i_sb)) {
+			err = au_cp_regular(cpg);
+			inode_unlock_shared(h_src_inode);
+		} else {
+			inode_unlock_shared(h_src_inode);
+			err = au_cp_regular(cpg);
+		}
+		rerr = au_pin_hdir_relock(cpg->pin);
+		if (!err && rerr)
+			err = rerr;
+	}
+	if (!err && (h_src_inode->i_state & I_LINKABLE)) {
+		h_path.dentry = au_h_dptr(cpg->dentry, cpg->bdst);
+		h_dst_inode = d_inode(h_path.dentry);
+		spin_lock(&h_dst_inode->i_lock);
+		h_dst_inode->i_state |= I_LINKABLE;
+		spin_unlock(&h_dst_inode->i_lock);
+	}
+
+out:
+	return err;
+}
+
+static int au_do_cpup_symlink(struct path *h_path, struct dentry *h_src,
+			      struct inode *h_dir)
+{
+	int err, symlen;
+	mm_segment_t old_fs;
+	union {
+		char *k;
+		char __user *u;
+	} sym;
+
+	err = -ENOMEM;
+	sym.k = (void *)__get_free_page(GFP_NOFS);
+	if (unlikely(!sym.k))
+		goto out;
+
+	/* unnecessary to support mmap_sem since symlink is not mmap-able */
+	old_fs = get_fs();
+	set_fs(KERNEL_DS);
+	symlen = vfs_readlink(h_src, sym.u, PATH_MAX);
+	err = symlen;
+	set_fs(old_fs);
+
+	if (symlen > 0) {
+		sym.k[symlen] = 0;
+		err = vfsub_symlink(h_dir, h_path, sym.k);
+	}
+	free_page((unsigned long)sym.k);
+
+out:
+	return err;
+}
+
+static void au_do_cpup_dir(struct au_cp_generic *cpg, struct dentry *dst_parent)
+{
+	struct inode *dir, *inode;
+
+	/*
+	 * strange behaviour from the users view,
+	 * particularly setattr case
+	 */
+	dir = d_inode(dst_parent);
+	if (au_ibtop(dir) == cpg->bdst)
+		au_cpup_attr_nlink(dir, /*force*/1);
+	inode = d_inode(cpg->dentry);
+	au_cpup_attr_nlink(inode, /*force*/1);
+}
+
+static noinline_for_stack
+int cpup_entry(struct au_cp_generic *cpg, struct dentry *dst_parent,
+	       struct au_cpup_reg_attr *h_src_attr)
+{
+	int err;
+	umode_t mode;
+	unsigned int mnt_flags;
+	unsigned char isdir, isreg, force;
+	const unsigned char do_dt = !!au_ftest_cpup(cpg->flags, DTIME);
+	struct au_dtime dt;
+	struct path h_path;
+	struct dentry *h_src, *h_dst, *h_parent;
+	struct inode *h_inode, *h_dir;
+	struct super_block *sb;
+
+	/* bsrc branch can be ro/rw. */
+	h_src = au_h_dptr(cpg->dentry, cpg->bsrc);
+	h_inode = d_inode(h_src);
+	AuDebugOn(h_inode != au_h_iptr(d_inode(cpg->dentry), cpg->bsrc));
+
+	/* try stopping to be referenced while we are creating */
+	h_dst = au_h_dptr(cpg->dentry, cpg->bdst);
+	if (au_ftest_cpup(cpg->flags, RENAME))
+		AuDebugOn(strncmp(h_dst->d_name.name, AUFS_WH_PFX,
+				  AUFS_WH_PFX_LEN));
+	h_parent = h_dst->d_parent; /* dir inode is locked */
+	h_dir = d_inode(h_parent);
+	IMustLock(h_dir);
+	AuDebugOn(h_parent != h_dst->d_parent);
+
+	sb = cpg->dentry->d_sb;
+	h_path.mnt = au_sbr_mnt(sb, cpg->bdst);
+	if (do_dt) {
+		h_path.dentry = h_parent;
+		au_dtime_store(&dt, dst_parent, &h_path);
+	}
+	h_path.dentry = h_dst;
+
+	isreg = 0;
+	isdir = 0;
+	mode = h_inode->i_mode;
+	switch (mode & S_IFMT) {
+	case S_IFREG:
+		isreg = 1;
+		err = vfsub_create(h_dir, &h_path, 0600, /*want_excl*/true);
+		if (!err)
+			err = au_do_cpup_regular(cpg, h_src_attr);
+		break;
+	case S_IFDIR:
+		isdir = 1;
+		err = vfsub_mkdir(h_dir, &h_path, mode);
+		if (!err)
+			au_do_cpup_dir(cpg, dst_parent);
+		break;
+	case S_IFLNK:
+		err = au_do_cpup_symlink(&h_path, h_src, h_dir);
+		break;
+	case S_IFCHR:
+	case S_IFBLK:
+		AuDebugOn(!capable(CAP_MKNOD));
+		/*FALLTHROUGH*/
+	case S_IFIFO:
+	case S_IFSOCK:
+		err = vfsub_mknod(h_dir, &h_path, mode, h_inode->i_rdev);
+		break;
+	default:
+		AuIOErr("Unknown inode type 0%o\n", mode);
+		err = -EIO;
+	}
+
+	mnt_flags = au_mntflags(sb);
+	if (!isdir
+	    && au_opt_test(mnt_flags, XINO)
+	    && (h_inode->i_nlink == 1
+		|| (h_inode->i_state & I_LINKABLE))
+	    /* todo: unnecessary? */
+	    /* && d_inode(cpg->dentry)->i_nlink == 1 */
+	    && cpg->bdst < cpg->bsrc
+	    && !au_ftest_cpup(cpg->flags, KEEPLINO))
+		au_xino_write(sb, cpg->bsrc, h_inode->i_ino, /*ino*/0);
+		/* ignore this error */
+
+	if (!err) {
+		force = 0;
+		if (isreg) {
+			force = !!cpg->len;
+			if (cpg->len == -1)
+				force = !!i_size_read(h_inode);
+		}
+	}
+
+	if (do_dt)
+		au_dtime_revert(&dt);
+	return err;
+}
+
+static int au_do_ren_after_cpup(struct au_cp_generic *cpg, struct path *h_path)
+{
+	int err;
+	struct dentry *dentry, *h_dentry, *h_parent;
+	struct inode *h_dir;
+	aufs_bindex_t bdst;
+
+	dentry = cpg->dentry;
+	bdst = cpg->bdst;
+	h_dentry = au_h_dptr(dentry, bdst);
+	dget(h_dentry);
+	au_set_h_dptr(dentry, bdst, NULL);
+	err = au_lkup_neg(dentry, bdst, /*wh*/0);
+	if (!err)
+		h_path->dentry = dget(au_h_dptr(dentry, bdst));
+	au_set_h_dptr(dentry, bdst, h_dentry);
+	if (unlikely(err))
+		goto out;
+
+	h_parent = h_dentry->d_parent; /* dir inode is locked */
+	h_dir = d_inode(h_parent);
+	IMustLock(h_dir);
+	AuDbg("%pd %pd\n", h_dentry, h_path->dentry);
+	/* no delegation since it is just created */
+	err = vfsub_rename(h_dir, h_dentry, h_dir, h_path, /*delegated*/NULL,
+			   /*flags*/0);
+	dput(h_path->dentry);
+
+out:
+	return err;
+}
+
+/*
+ * copyup the @dentry from @bsrc to @bdst.
+ * the caller must set the both of lower dentries.
+ * @len is for truncating when it is -1 copyup the entire file.
+ * in link/rename cases, @dst_parent may be different from the real one.
+ * basic->bsrc can be larger than basic->bdst.
+ * aufs doesn't touch the credential so
+ * security_inode_copy_up{,_xattr}() are unnecessary.
+ */
+/* re-commit later */ __maybe_unused
+static int au_cpup_single(struct au_cp_generic *cpg, struct dentry *dst_parent)
+{
+	int err, rerr;
+	aufs_bindex_t old_ibtop;
+	unsigned char isdir, plink;
+	struct dentry *h_src, *h_dst, *h_parent;
+	struct inode *dst_inode, *h_dir, *inode, *delegated, *src_inode;
+	struct super_block *sb;
+	struct au_branch *br;
+	/* to reduce stack size */
+	struct {
+		struct au_dtime dt;
+		struct path h_path;
+		struct au_cpup_reg_attr h_src_attr;
+	} *a;
+
+	err = -ENOMEM;
+	a = kmalloc(sizeof(*a), GFP_NOFS);
+	if (unlikely(!a))
+		goto out;
+	a->h_src_attr.valid = 0;
+
+	sb = cpg->dentry->d_sb;
+	br = au_sbr(sb, cpg->bdst);
+	a->h_path.mnt = au_br_mnt(br);
+	h_dst = au_h_dptr(cpg->dentry, cpg->bdst);
+	h_parent = h_dst->d_parent; /* dir inode is locked */
+	h_dir = d_inode(h_parent);
+	IMustLock(h_dir);
+
+	h_src = au_h_dptr(cpg->dentry, cpg->bsrc);
+	inode = d_inode(cpg->dentry);
+
+	if (!dst_parent)
+		dst_parent = dget_parent(cpg->dentry);
+	else
+		dget(dst_parent);
+
+	plink = !!au_opt_test(au_mntflags(sb), PLINK);
+	dst_inode = au_h_iptr(inode, cpg->bdst);
+	if (dst_inode) {
+		if (unlikely(!plink)) {
+			err = -EIO;
+			AuIOErr("hi%lu(i%lu) exists on b%d "
+				"but plink is disabled\n",
+				dst_inode->i_ino, inode->i_ino, cpg->bdst);
+			goto out_parent;
+		}
+
+		if (dst_inode->i_nlink) {
+			const int do_dt = au_ftest_cpup(cpg->flags, DTIME);
+
+			h_src = au_plink_lkup(inode, cpg->bdst);
+			err = PTR_ERR(h_src);
+			if (IS_ERR(h_src))
+				goto out_parent;
+			if (unlikely(d_is_negative(h_src))) {
+				err = -EIO;
+				AuIOErr("i%lu exists on b%d "
+					"but not pseudo-linked\n",
+					inode->i_ino, cpg->bdst);
+				dput(h_src);
+				goto out_parent;
+			}
+
+			if (do_dt) {
+				a->h_path.dentry = h_parent;
+				au_dtime_store(&a->dt, dst_parent, &a->h_path);
+			}
+
+			a->h_path.dentry = h_dst;
+			delegated = NULL;
+			err = vfsub_link(h_src, h_dir, &a->h_path, &delegated);
+			if (!err && au_ftest_cpup(cpg->flags, RENAME))
+				err = au_do_ren_after_cpup(cpg, &a->h_path);
+			if (do_dt)
+				au_dtime_revert(&a->dt);
+			if (unlikely(err == -EWOULDBLOCK)) {
+				pr_warn("cannot retry for NFSv4 delegation"
+					" for an internal link\n");
+				iput(delegated);
+			}
+			dput(h_src);
+			goto out_parent;
+		} else
+			/* todo: cpup_wh_file? */
+			/* udba work */
+			au_update_ibrange(inode, /*do_put_zero*/1);
+	}
+
+	isdir = S_ISDIR(inode->i_mode);
+	old_ibtop = au_ibtop(inode);
+	err = cpup_entry(cpg, dst_parent, &a->h_src_attr);
+	if (unlikely(err))
+		goto out_rev;
+	dst_inode = d_inode(h_dst);
+	inode_lock_nested(dst_inode, AuLsc_I_CHILD2);
+	/* todo: necessary? */
+	/* au_pin_hdir_unlock(cpg->pin); */
+
+	err = cpup_iattr(cpg->dentry, cpg->bdst, h_src, &a->h_src_attr);
+	if (unlikely(err)) {
+		/* todo: necessary? */
+		/* au_pin_hdir_relock(cpg->pin); */ /* ignore an error */
+		inode_unlock(dst_inode);
+		goto out_rev;
+	}
+
+	if (cpg->bdst < old_ibtop) {
+		au_set_ibtop(inode, cpg->bdst);
+	} else
+		au_set_ibbot(inode, cpg->bdst);
+	au_set_h_iptr(inode, cpg->bdst, au_igrab(dst_inode),
+		      au_hi_flags(inode, isdir));
+
+	/* todo: necessary? */
+	/* err = au_pin_hdir_relock(cpg->pin); */
+	inode_unlock(dst_inode);
+	if (unlikely(err))
+		goto out_rev;
+
+	src_inode = d_inode(h_src);
+	if (!isdir
+	    && (src_inode->i_nlink > 1
+		|| src_inode->i_state & I_LINKABLE)
+	    && plink)
+		au_plink_append(inode, cpg->bdst, h_dst);
+
+	if (au_ftest_cpup(cpg->flags, RENAME)) {
+		a->h_path.dentry = h_dst;
+		err = au_do_ren_after_cpup(cpg, &a->h_path);
+	}
+	if (!err)
+		goto out_parent; /* success */
+
+	/* revert */
+out_rev:
+	a->h_path.dentry = h_parent;
+	au_dtime_store(&a->dt, dst_parent, &a->h_path);
+	a->h_path.dentry = h_dst;
+	rerr = 0;
+	if (d_is_positive(h_dst)) {
+		if (!isdir) {
+			/* no delegation since it is just created */
+			rerr = vfsub_unlink(h_dir, &a->h_path,
+					    /*delegated*/NULL, /*force*/0);
+		} else
+			rerr = vfsub_rmdir(h_dir, &a->h_path);
+	}
+	au_dtime_revert(&a->dt);
+	if (rerr) {
+		AuIOErr("failed removing broken entry(%d, %d)\n", err, rerr);
+		err = -EIO;
+	}
+out_parent:
+	dput(dst_parent);
+	au_kfree_rcu(a);
+out:
+	return err;
+}
+
+#if 0 /* reserved */
+struct au_cpup_single_args {
+	int *errp;
+	struct au_cp_generic *cpg;
+	struct dentry *dst_parent;
+};
+
+static void au_call_cpup_single(void *args)
+{
+	struct au_cpup_single_args *a = args;
+
+	au_pin_hdir_acquire_nest(a->cpg->pin);
+	*a->errp = au_cpup_single(a->cpg, a->dst_parent);
+	au_pin_hdir_release(a->cpg->pin);
+}
+#endif
+
+#if 0 /* reserved */
+int au_sio_cpup_single(struct au_cp_generic *cpg, struct dentry *dst_parent)
+{
+	int err, wkq_err;
+	struct dentry *h_dentry;
+
+	h_dentry = au_h_dptr(cpg->dentry, cpg->bsrc);
+	if (!au_cpup_sio_test(pin, d_inode(h_dentry)->i_mode))
+		err = au_cpup_single(cpg, dst_parent);
+	else {
+		struct au_cpup_single_args args = {
+			.errp		= &err,
+			.cpg		= cpg,
+			.dst_parent	= dst_parent
+		};
+		wkq_err = au_wkq_wait(au_call_cpup_single, &args);
+		if (unlikely(wkq_err))
+			err = wkq_err;
+	}
+
+	return err;
+}
+#endif

fs/aufs/cpup.h

@@ -15,6 +15,7 @@
 #include <linux/path.h>
 
 struct inode;
+struct au_pin;
 
 void au_cpup_attr_flags(struct inode *dst, unsigned int iflags);
 void au_cpup_attr_timesizes(struct inode *inode);
@@ -25,6 +26,30 @@ void au_cpup_attr_all(struct inode *inode, int force);
 
 /* ---------------------------------------------------------------------- */
 
+struct au_cp_generic {
+	struct dentry	*dentry;
+	aufs_bindex_t	bdst, bsrc;
+	loff_t		len;
+	struct au_pin	*pin;
+	unsigned int	flags;
+};
+
+/* cpup flags */
+#define AuCpup_DTIME		1		/* do dtime_store/revert */
+#define AuCpup_KEEPLINO		(1 << 1)	/* do not clear the lower xino,
+						   for link(2) */
+#define AuCpup_RENAME		(1 << 2)	/* rename after cpup */
+
+#define au_ftest_cpup(flags, name)	((flags) & AuCpup_##name)
+#define au_fset_cpup(flags, name) \
+	do { (flags) |= AuCpup_##name; } while (0)
+#define au_fclr_cpup(flags, name) \
+	do { (flags) &= ~AuCpup_##name; } while (0)
+
+int au_copy_file(struct file *dst, struct file *src, loff_t len);
+
+/* ---------------------------------------------------------------------- */
+
 /* keep timestamps when copyup */
 struct au_dtime {
 	struct dentry *dt_dentry;

fs/aufs/iinfo.c

@@ -90,6 +90,46 @@ void au_update_iigen(struct inode *inode, int half)
 	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;
+
+			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);
+		}
+	}
+
+	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);
+}
+
 /* ---------------------------------------------------------------------- */
 
 void au_icntnr_init_once(void *_c)

fs/aufs/inode.h

@@ -120,6 +120,7 @@ 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);
 
 void au_icntnr_init_once(void *_c);
 void au_hinode_init(struct au_hinode *hinode);

fs/aufs/vfsub.c

@@ -97,6 +97,50 @@ out:
 	return err;
 }
 
+int vfsub_symlink(struct inode *dir, struct path *path, const char *symname)
+{
+	int err;
+	struct dentry *d;
+
+	IMustLock(dir);
+
+	d = path->dentry;
+	path->dentry = d->d_parent;
+	err = security_path_symlink(path, d, symname);
+	path->dentry = d;
+	if (unlikely(err))
+		goto out;
+
+	lockdep_off();
+	err = vfs_symlink(dir, path->dentry, symname);
+	lockdep_on();
+
+out:
+	return err;
+}
+
+int vfsub_mknod(struct inode *dir, struct path *path, int mode, dev_t dev)
+{
+	int err;
+	struct dentry *d;
+
+	IMustLock(dir);
+
+	d = path->dentry;
+	path->dentry = d->d_parent;
+	err = security_path_mknod(path, d, mode, new_encode_dev(dev));
+	path->dentry = d;
+	if (unlikely(err))
+		goto out;
+
+	lockdep_off();
+	err = vfs_mknod(dir, path->dentry, mode, dev);
+	lockdep_on();
+
+out:
+	return err;
+}
+
 static int au_test_nlink(struct inode *inode)
 {
 	const unsigned int link_max = UINT_MAX >> 1; /* rough margin */
@@ -135,6 +179,36 @@ out:
 	return err;
 }
 
+int vfsub_rename(struct inode *src_dir, struct dentry *src_dentry,
+		 struct inode *dir, struct path *path,
+		 struct inode **delegated_inode, unsigned int flags)
+{
+	int err;
+	struct path tmp = {
+		.mnt	= path->mnt
+	};
+	struct dentry *d;
+
+	IMustLock(dir);
+	IMustLock(src_dir);
+
+	d = path->dentry;
+	path->dentry = d->d_parent;
+	tmp.dentry = src_dentry->d_parent;
+	err = security_path_rename(&tmp, src_dentry, path, d, /*flags*/0);
+	path->dentry = d;
+	if (unlikely(err))
+		goto out;
+
+	lockdep_off();
+	err = vfs_rename(src_dir, src_dentry, dir, path->dentry,
+			 delegated_inode, flags);
+	lockdep_on();
+
+out:
+	return err;
+}
+
 int vfsub_mkdir(struct inode *dir, struct path *path, int mode)
 {
 	int err;

fs/aufs/vfsub.h

@@ -81,8 +81,14 @@ static inline void vfsub_mnt_drop_write(struct vfsmount *mnt)
 
 int vfsub_create(struct inode *dir, struct path *path, int mode,
 		 bool want_excl);
+int vfsub_symlink(struct inode *dir, struct path *path,
+		  const char *symname);
+int vfsub_mknod(struct inode *dir, struct path *path, int mode, dev_t dev);
 int vfsub_link(struct dentry *src_dentry, struct inode *dir,
 	       struct path *path, struct inode **delegated_inode);
+int vfsub_rename(struct inode *src_hdir, struct dentry *src_dentry,
+		 struct inode *hdir, struct path *path,
+		 struct inode **delegated_inode, unsigned int flags);
 int vfsub_mkdir(struct inode *dir, struct path *path, int mode);
 int vfsub_rmdir(struct inode *dir, struct path *path);
 
@@ -102,6 +108,34 @@ static inline loff_t vfsub_f_size_read(struct file *file)
 	return i_size_read(file_inode(file));
 }
 
+/*
+ * re-use branch fs's ioctl(FICLONE) while aufs itself doesn't support such
+ * ioctl.
+ */
+static inline loff_t vfsub_clone_file_range(struct file *src, struct file *dst,
+					    loff_t len)
+{
+	loff_t err;
+
+	lockdep_off();
+	err = vfs_clone_file_range(src, 0, dst, 0, len, /*remap_flags*/0);
+	lockdep_on();
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static inline loff_t vfsub_llseek(struct file *file, loff_t offset, int origin)
+{
+	loff_t err;
+
+	lockdep_off();
+	err = vfs_llseek(file, offset, origin);
+	lockdep_on();
+	return err;
+}
+
 /* ---------------------------------------------------------------------- */
 
 int vfsub_sio_notify_change(struct path *path, struct iattr *ia,
@@ -111,5 +145,10 @@ int vfsub_notify_change(struct path *path, struct iattr *ia,
 int vfsub_unlink(struct inode *dir, struct path *path,
 		 struct inode **delegated_inode, int force);
 
+static inline int vfsub_getattr(const struct path *path, struct kstat *st)
+{
+	return vfs_getattr(path, st, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT);
+}
+
 #endif /* __KERNEL__ */
 #endif /* __AUFS_VFSUB_H__ */

fs/aufs/xino.c

@@ -271,7 +271,7 @@ struct file *au_xino_create2(struct super_block *sb, struct path *base,
 
 	if (copy_src) {
 		/* no one can touch copy_src xino */
-		//err = au_copy_file(file, copy_src, vfsub_f_size_read(copy_src));
+		err = au_copy_file(file, copy_src, vfsub_f_size_read(copy_src));
 		if (unlikely(err)) {
 			pr_err("%pd copy err %d\n", dentry, err);
 			goto out_fput;