1 files changed, 438 insertions, 233 deletions

diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index b193d08a3dc3..758611ee4475 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -16,7 +16,6 @@
 #include <linux/sched/signal.h>
 #include <linux/cred.h>
 #include <linux/namei.h>
-#include <linux/fdtable.h>
 #include <linux/ratelimit.h>
 #include <linux/exportfs.h>
 #include "overlayfs.h"
@@ -44,16 +43,44 @@ static bool ovl_must_copy_xattr(const char *name)
 	       !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN);
 }
 
-int ovl_copy_xattr(struct super_block *sb, struct dentry *old,
-		   struct dentry *new)
+static int ovl_copy_acl(struct ovl_fs *ofs, const struct path *path,
+			struct dentry *dentry, const char *acl_name)
 {
+	int err;
+	struct posix_acl *clone, *real_acl = NULL;
+
+	real_acl = ovl_get_acl_path(path, acl_name, false);
+	if (!real_acl)
+		return 0;
+
+	if (IS_ERR(real_acl)) {
+		err = PTR_ERR(real_acl);
+		if (err == -ENODATA || err == -EOPNOTSUPP)
+			return 0;
+		return err;
+	}
+
+	clone = posix_acl_clone(real_acl, GFP_KERNEL);
+	posix_acl_release(real_acl); /* release original acl */
+	if (!clone)
+		return -ENOMEM;
+
+	err = ovl_do_set_acl(ofs, dentry, acl_name, clone);
+
+	/* release cloned acl */
+	posix_acl_release(clone);
+	return err;
+}
+
+int ovl_copy_xattr(struct super_block *sb, const struct path *oldpath, struct dentry *new)
+{
+	struct dentry *old = oldpath->dentry;
 	ssize_t list_size, size, value_size = 0;
 	char *buf, *name, *value = NULL;
 	int error = 0;
 	size_t slen;
 
-	if (!(old->d_inode->i_opflags & IOP_XATTR) ||
-	    !(new->d_inode->i_opflags & IOP_XATTR))
+	if (!old->d_inode->i_op->listxattr || !new->d_inode->i_op->listxattr)
 		return 0;
 
 	list_size = vfs_listxattr(old, NULL, 0);
@@ -86,17 +113,26 @@ int ovl_copy_xattr(struct super_block *sb, struct dentry *old,
 		if (ovl_is_private_xattr(sb, name))
 			continue;
 
-		error = security_inode_copy_up_xattr(name);
-		if (error < 0 && error != -EOPNOTSUPP)
-			break;
-		if (error == 1) {
+		error = security_inode_copy_up_xattr(old, name);
+		if (error == -ECANCELED) {
 			error = 0;
 			continue; /* Discard */
 		}
+		if (error < 0 && error != -EOPNOTSUPP)
+			break;
+
+		if (is_posix_acl_xattr(name)) {
+			error = ovl_copy_acl(OVL_FS(sb), oldpath, new, name);
+			if (!error)
+				continue;
+			/* POSIX ACLs must be copied. */
+			break;
+		}
+
 retry:
-		size = vfs_getxattr(&init_user_ns, old, name, value, value_size);
+		size = ovl_do_getxattr(oldpath, name, value, value_size);
 		if (size == -ERANGE)
-			size = vfs_getxattr(&init_user_ns, old, name, NULL, 0);
+			size = ovl_do_getxattr(oldpath, name, NULL, 0);
 
 		if (size < 0) {
 			error = size;
@@ -117,7 +153,7 @@ retry:
 			goto retry;
 		}
 
-		error = vfs_setxattr(&init_user_ns, new, name, value, size, 0);
+		error = ovl_do_setxattr(OVL_FS(sb), new, name, value, size, 0);
 		if (error) {
 			if (error != -EOPNOTSUPP || ovl_must_copy_xattr(name))
 				break;
@@ -132,11 +168,11 @@ out:
 	return error;
 }
 
-static int ovl_copy_fileattr(struct inode *inode, struct path *old,
-			     struct path *new)
+static int ovl_copy_fileattr(struct inode *inode, const struct path *old,
+			     const struct path *new)
 {
-	struct fileattr oldfa = { .flags_valid = true };
-	struct fileattr newfa = { .flags_valid = true };
+	struct file_kattr oldfa = { .flags_valid = true };
+	struct file_kattr newfa = { .flags_valid = true };
 	int err;
 
 	err = ovl_real_fileattr_get(old, &oldfa);
@@ -145,7 +181,7 @@ static int ovl_copy_fileattr(struct inode *inode, struct path *old,
 		if (err == -ENOTTY || err == -EINVAL)
 			return 0;
 		pr_warn("failed to retrieve lower fileattr (%pd2, err=%i)\n",
-			old, err);
+			old->dentry, err);
 		return err;
 	}
 
@@ -157,7 +193,9 @@ static int ovl_copy_fileattr(struct inode *inode, struct path *old,
 	 */
 	if (oldfa.flags & OVL_PROT_FS_FLAGS_MASK) {
 		err = ovl_set_protattr(inode, new->dentry, &oldfa);
-		if (err)
+		if (err == -EPERM)
+			pr_warn_once("copying fileattr: no xattr on upper\n");
+		else if (err)
 			return err;
 	}
 
@@ -167,8 +205,16 @@ static int ovl_copy_fileattr(struct inode *inode, struct path *old,
 
 	err = ovl_real_fileattr_get(new, &newfa);
 	if (err) {
+		/*
+		 * Returning an error if upper doesn't support fileattr will
+		 * result in a regression, so revert to the old behavior.
+		 */
+		if (err == -ENOTTY || err == -EINVAL) {
+			pr_warn_once("copying fileattr: no support on upper\n");
+			return 0;
+		}
 		pr_warn("failed to retrieve upper fileattr (%pd2, err=%i)\n",
-			new, err);
+			new->dentry, err);
 		return err;
 	}
 
@@ -183,11 +229,40 @@ static int ovl_copy_fileattr(struct inode *inode, struct path *old,
 	return ovl_real_fileattr_set(new, &newfa);
 }
 
-static int ovl_copy_up_data(struct ovl_fs *ofs, struct path *old,
-			    struct path *new, loff_t len)
+static int ovl_verify_area(loff_t pos, loff_t pos2, loff_t len, loff_t totlen)
+{
+	loff_t tmp;
+
+	if (pos != pos2)
+		return -EIO;
+	if (pos < 0 || len < 0 || totlen < 0)
+		return -EIO;
+	if (check_add_overflow(pos, len, &tmp))
+		return -EIO;
+	return 0;
+}
+
+static int ovl_sync_file(const struct path *path)
 {
-	struct file *old_file;
 	struct file *new_file;
+	int err;
+
+	new_file = ovl_path_open(path, O_LARGEFILE | O_RDONLY);
+	if (IS_ERR(new_file))
+		return PTR_ERR(new_file);
+
+	err = vfs_fsync(new_file, 0);
+	fput(new_file);
+
+	return err;
+}
+
+static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry,
+			    struct file *new_file, loff_t len,
+			    bool datasync)
+{
+	struct path datapath;
+	struct file *old_file;
 	loff_t old_pos = 0;
 	loff_t new_pos = 0;
 	loff_t cloned;
@@ -196,33 +271,34 @@ static int ovl_copy_up_data(struct ovl_fs *ofs, struct path *old,
 	bool skip_hole = false;
 	int error = 0;
 
-	if (len == 0)
-		return 0;
+	ovl_path_lowerdata(dentry, &datapath);
+	if (WARN_ON_ONCE(datapath.dentry == NULL) ||
+	    WARN_ON_ONCE(len < 0))
+		return -EIO;
 
-	old_file = ovl_path_open(old, O_LARGEFILE | O_RDONLY);
+	old_file = ovl_path_open(&datapath, O_LARGEFILE | O_RDONLY);
 	if (IS_ERR(old_file))
 		return PTR_ERR(old_file);
 
-	new_file = ovl_path_open(new, O_LARGEFILE | O_WRONLY);
-	if (IS_ERR(new_file)) {
-		error = PTR_ERR(new_file);
-		goto out_fput;
-	}
-
 	/* Try to use clone_file_range to clone up within the same fs */
-	cloned = do_clone_file_range(old_file, 0, new_file, 0, len, 0);
+	cloned = vfs_clone_file_range(old_file, 0, new_file, 0, len, 0);
 	if (cloned == len)
-		goto out;
+		goto out_fput;
+
 	/* Couldn't clone, so now we try to copy the data */
+	error = rw_verify_area(READ, old_file, &old_pos, len);
+	if (!error)
+		error = rw_verify_area(WRITE, new_file, &new_pos, len);
+	if (error)
+		goto out_fput;
 
 	/* Check if lower fs supports seek operation */
-	if (old_file->f_mode & FMODE_LSEEK &&
-	    old_file->f_op->llseek)
+	if (old_file->f_mode & FMODE_LSEEK)
 		skip_hole = true;
 
 	while (len) {
 		size_t this_len = OVL_COPY_UP_CHUNK_SIZE;
-		long bytes;
+		ssize_t bytes;
 
 		if (len < this_len)
 			this_len = len;
@@ -246,8 +322,12 @@ static int ovl_copy_up_data(struct ovl_fs *ofs, struct path *old,
 		 * it may not recognize all kind of holes and sometimes
 		 * only skips partial of hole area. However, it will be
 		 * enough for most of the use cases.
+		 *
+		 * We do not hold upper sb_writers throughout the loop to avert
+		 * lockdep warning with llseek of lower file in nested overlay:
+		 * - upper sb_writers
+		 * -- lower ovl_inode_lock (ovl_llseek)
 		 */
-
 		if (skip_hole && data_pos < old_pos) {
 			data_pos = vfs_llseek(old_file, old_pos, SEEK_DATA);
 			if (data_pos > old_pos) {
@@ -262,6 +342,10 @@ static int ovl_copy_up_data(struct ovl_fs *ofs, struct path *old,
 			}
 		}
 
+		error = ovl_verify_area(old_pos, new_pos, this_len, len);
+		if (error)
+			break;
+
 		bytes = do_splice_direct(old_file, &old_pos,
 					 new_file, &new_pos,
 					 this_len, SPLICE_F_MOVE);
@@ -273,38 +357,40 @@ static int ovl_copy_up_data(struct ovl_fs *ofs, struct path *old,
 
 		len -= bytes;
 	}
-out:
-	if (!error && ovl_should_sync(ofs))
+	/* call fsync once, either now or later along with metadata */
+	if (!error && ovl_should_sync(ofs) && datasync)
 		error = vfs_fsync(new_file, 0);
-	fput(new_file);
 out_fput:
 	fput(old_file);
 	return error;
 }
 
-static int ovl_set_size(struct dentry *upperdentry, struct kstat *stat)
+static int ovl_set_size(struct ovl_fs *ofs,
+			struct dentry *upperdentry, struct kstat *stat)
 {
 	struct iattr attr = {
 		.ia_valid = ATTR_SIZE,
 		.ia_size = stat->size,
 	};
 
-	return notify_change(&init_user_ns, upperdentry, &attr, NULL);
+	return ovl_do_notify_change(ofs, upperdentry, &attr);
 }
 
-static int ovl_set_timestamps(struct dentry *upperdentry, struct kstat *stat)
+static int ovl_set_timestamps(struct ovl_fs *ofs, struct dentry *upperdentry,
+			      struct kstat *stat)
 {
 	struct iattr attr = {
 		.ia_valid =
-		     ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET,
+		     ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_CTIME,
 		.ia_atime = stat->atime,
 		.ia_mtime = stat->mtime,
 	};
 
-	return notify_change(&init_user_ns, upperdentry, &attr, NULL);
+	return ovl_do_notify_change(ofs, upperdentry, &attr);
 }
 
-int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat)
+int ovl_set_attr(struct ovl_fs *ofs, struct dentry *upperdentry,
+		 struct kstat *stat)
 {
 	int err = 0;
 
@@ -313,29 +399,29 @@ int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat)
 			.ia_valid = ATTR_MODE,
 			.ia_mode = stat->mode,
 		};
-		err = notify_change(&init_user_ns, upperdentry, &attr, NULL);
+		err = ovl_do_notify_change(ofs, upperdentry, &attr);
 	}
 	if (!err) {
 		struct iattr attr = {
 			.ia_valid = ATTR_UID | ATTR_GID,
-			.ia_uid = stat->uid,
-			.ia_gid = stat->gid,
+			.ia_vfsuid = VFSUIDT_INIT(stat->uid),
+			.ia_vfsgid = VFSGIDT_INIT(stat->gid),
 		};
-		err = notify_change(&init_user_ns, upperdentry, &attr, NULL);
+		err = ovl_do_notify_change(ofs, upperdentry, &attr);
 	}
 	if (!err)
-		ovl_set_timestamps(upperdentry, stat);
+		ovl_set_timestamps(ofs, upperdentry, stat);
 
 	return err;
 }
 
-struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real,
+struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct inode *realinode,
 				  bool is_upper)
 {
 	struct ovl_fh *fh;
 	int fh_type, dwords;
 	int buflen = MAX_HANDLE_SZ;
-	uuid_t *uuid = &real->d_sb->s_uuid;
+	uuid_t *uuid = &realinode->i_sb->s_uuid;
 	int err;
 
 	/* Make sure the real fid stays 32bit aligned */
@@ -352,13 +438,13 @@ struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real,
 	 * the price or reconnecting the dentry.
 	 */
 	dwords = buflen >> 2;
-	fh_type = exportfs_encode_fh(real, (void *)fh->fb.fid, &dwords, 0);
+	fh_type = exportfs_encode_inode_fh(realinode, (void *)fh->fb.fid,
+					   &dwords, NULL, 0);
 	buflen = (dwords << 2);
 
 	err = -EIO;
-	if (WARN_ON(fh_type < 0) ||
-	    WARN_ON(buflen > MAX_HANDLE_SZ) ||
-	    WARN_ON(fh_type == FILEID_INVALID))
+	if (fh_type < 0 || fh_type == FILEID_INVALID ||
+	    WARN_ON(buflen > MAX_HANDLE_SZ))
 		goto out_err;
 
 	fh->fb.version = OVL_FH_VERSION;
@@ -374,7 +460,7 @@ struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real,
 	if (is_upper)
 		fh->fb.flags |= OVL_FH_FLAG_PATH_UPPER;
 	fh->fb.len = sizeof(fh->fb) + buflen;
-	if (ofs->config.uuid)
+	if (ovl_origin_uuid(ofs))
 		fh->fb.uuid = *uuid;
 
 	return fh;
@@ -384,29 +470,29 @@ out_err:
 	return ERR_PTR(err);
 }
 
-int ovl_set_origin(struct ovl_fs *ofs, struct dentry *lower,
-		   struct dentry *upper)
+struct ovl_fh *ovl_get_origin_fh(struct ovl_fs *ofs, struct dentry *origin)
 {
-	const struct ovl_fh *fh = NULL;
-	int err;
-
 	/*
 	 * When lower layer doesn't support export operations store a 'null' fh,
 	 * so we can use the overlay.origin xattr to distignuish between a copy
 	 * up and a pure upper inode.
 	 */
-	if (ovl_can_decode_fh(lower->d_sb)) {
-		fh = ovl_encode_real_fh(ofs, lower, false);
-		if (IS_ERR(fh))
-			return PTR_ERR(fh);
-	}
+	if (!ovl_can_decode_fh(origin->d_sb))
+		return NULL;
+
+	return ovl_encode_real_fh(ofs, d_inode(origin), false);
+}
+
+int ovl_set_origin_fh(struct ovl_fs *ofs, const struct ovl_fh *fh,
+		      struct dentry *upper)
+{
+	int err;
 
 	/*
 	 * Do not fail when upper doesn't support xattrs.
 	 */
 	err = ovl_check_setxattr(ofs, upper, OVL_XATTR_ORIGIN, fh->buf,
 				 fh ? fh->fb.len : 0, 0);
-	kfree(fh);
 
 	/* Ignore -EPERM from setting "user.*" on symlink/special */
 	return err == -EPERM ? 0 : err;
@@ -419,11 +505,11 @@ static int ovl_set_upper_fh(struct ovl_fs *ofs, struct dentry *upper,
 	const struct ovl_fh *fh;
 	int err;
 
-	fh = ovl_encode_real_fh(ofs, upper, true);
+	fh = ovl_encode_real_fh(ofs, d_inode(upper), true);
 	if (IS_ERR(fh))
 		return PTR_ERR(fh);
 
-	err = ovl_do_setxattr(ofs, index, OVL_XATTR_UPPER, fh->buf, fh->fb.len);
+	err = ovl_setxattr(ofs, index, OVL_XATTR_UPPER, fh->buf, fh->fb.len);
 
 	kfree(fh);
 	return err;
@@ -431,17 +517,14 @@ static int ovl_set_upper_fh(struct ovl_fs *ofs, struct dentry *upper,
 
 /*
  * Create and install index entry.
- *
- * Caller must hold i_mutex on indexdir.
  */
-static int ovl_create_index(struct dentry *dentry, struct dentry *origin,
+static int ovl_create_index(struct dentry *dentry, const struct ovl_fh *fh,
 			    struct dentry *upper)
 {
 	struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
 	struct dentry *indexdir = ovl_indexdir(dentry->d_sb);
-	struct inode *dir = d_inode(indexdir);
-	struct dentry *index = NULL;
 	struct dentry *temp = NULL;
+	struct renamedata rd = {};
 	struct qstr name = { };
 	int err;
 
@@ -460,11 +543,11 @@ static int ovl_create_index(struct dentry *dentry, struct dentry *origin,
 	if (WARN_ON(ovl_test_flag(OVL_INDEX, d_inode(dentry))))
 		return -EIO;
 
-	err = ovl_get_index_name(ofs, origin, &name);
+	err = ovl_get_index_name_fh(fh, &name);
 	if (err)
 		return err;
 
-	temp = ovl_create_temp(indexdir, OVL_CATTR(S_IFDIR | 0));
+	temp = ovl_create_temp(ofs, indexdir, OVL_CATTR(S_IFDIR | 0));
 	err = PTR_ERR(temp);
 	if (IS_ERR(temp))
 		goto free_name;
@@ -473,16 +556,18 @@ static int ovl_create_index(struct dentry *dentry, struct dentry *origin,
 	if (err)
 		goto out;
 
-	index = lookup_one_len(name.name, indexdir, name.len);
-	if (IS_ERR(index)) {
-		err = PTR_ERR(index);
-	} else {
-		err = ovl_do_rename(dir, temp, dir, index, 0);
-		dput(index);
-	}
+	rd.mnt_idmap = ovl_upper_mnt_idmap(ofs);
+	rd.old_parent = indexdir;
+	rd.new_parent = indexdir;
+	err = start_renaming_dentry(&rd, 0, temp, &name);
+	if (err)
+		goto out;
+
+	err = ovl_do_rename_rd(&rd);
+	end_renaming(&rd);
 out:
 	if (err)
-		ovl_cleanup(dir, temp);
+		ovl_cleanup(ofs, indexdir, temp);
 	dput(temp);
 free_name:
 	kfree(name.name);
@@ -499,9 +584,12 @@ struct ovl_copy_up_ctx {
 	struct dentry *destdir;
 	struct qstr destname;
 	struct dentry *workdir;
+	const struct ovl_fh *origin_fh;
 	bool origin;
 	bool indexed;
 	bool metacopy;
+	bool metacopy_digest;
+	bool metadata_fsync;
 };
 
 static int ovl_link_up(struct ovl_copy_up_ctx *c)
@@ -509,70 +597,78 @@ static int ovl_link_up(struct ovl_copy_up_ctx *c)
 	int err;
 	struct dentry *upper;
 	struct dentry *upperdir = ovl_dentry_upper(c->parent);
+	struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb);
 	struct inode *udir = d_inode(upperdir);
 
+	ovl_start_write(c->dentry);
+
 	/* Mark parent "impure" because it may now contain non-pure upper */
 	err = ovl_set_impure(c->parent, upperdir);
 	if (err)
-		return err;
+		goto out;
 
 	err = ovl_set_nlink_lower(c->dentry);
 	if (err)
-		return err;
+		goto out;
 
-	inode_lock_nested(udir, I_MUTEX_PARENT);
-	upper = lookup_one_len(c->dentry->d_name.name, upperdir,
-			       c->dentry->d_name.len);
+	upper = ovl_start_creating_upper(ofs, upperdir,
+					 &QSTR_LEN(c->dentry->d_name.name,
+						   c->dentry->d_name.len));
 	err = PTR_ERR(upper);
 	if (!IS_ERR(upper)) {
-		err = ovl_do_link(ovl_dentry_upper(c->dentry), udir, upper);
-		dput(upper);
+		err = ovl_do_link(ofs, ovl_dentry_upper(c->dentry), udir, upper);
 
 		if (!err) {
 			/* Restore timestamps on parent (best effort) */
-			ovl_set_timestamps(upperdir, &c->pstat);
+			ovl_set_timestamps(ofs, upperdir, &c->pstat);
 			ovl_dentry_set_upper_alias(c->dentry);
+			ovl_dentry_update_reval(c->dentry, upper);
 		}
+		end_creating(upper);
 	}
-	inode_unlock(udir);
 	if (err)
-		return err;
+		goto out;
 
 	err = ovl_set_nlink_upper(c->dentry);
 
+out:
+	ovl_end_write(c->dentry);
 	return err;
 }
 
-static int ovl_copy_up_inode(struct ovl_copy_up_ctx *c, struct dentry *temp)
+static int ovl_copy_up_data(struct ovl_copy_up_ctx *c, const struct path *temp)
 {
 	struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb);
-	struct inode *inode = d_inode(c->dentry);
-	struct path upperpath, datapath;
+	struct file *new_file;
 	int err;
 
-	ovl_path_upper(c->dentry, &upperpath);
-	if (WARN_ON(upperpath.dentry != NULL))
-		return -EIO;
+	if (!S_ISREG(c->stat.mode) || c->metacopy || !c->stat.size)
+		return 0;
 
-	upperpath.dentry = temp;
+	new_file = ovl_path_open(temp, O_LARGEFILE | O_WRONLY);
+	if (IS_ERR(new_file))
+		return PTR_ERR(new_file);
 
-	/*
-	 * Copy up data first and then xattrs. Writing data after
-	 * xattrs will remove security.capability xattr automatically.
-	 */
-	if (S_ISREG(c->stat.mode) && !c->metacopy) {
-		ovl_path_lowerdata(c->dentry, &datapath);
-		err = ovl_copy_up_data(ofs, &datapath, &upperpath,
-				       c->stat.size);
-		if (err)
-			return err;
-	}
+	err = ovl_copy_up_file(ofs, c->dentry, new_file, c->stat.size,
+			       !c->metadata_fsync);
+	fput(new_file);
+
+	return err;
+}
 
-	err = ovl_copy_xattr(c->dentry->d_sb, c->lowerpath.dentry, temp);
+static int ovl_copy_up_metadata(struct ovl_copy_up_ctx *c, struct dentry *temp)
+{
+	struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb);
+	struct inode *inode = d_inode(c->dentry);
+	struct path upperpath = { .mnt = ovl_upper_mnt(ofs), .dentry = temp };
+	int err;
+
+	err = ovl_copy_xattr(c->dentry->d_sb, &c->lowerpath, temp);
 	if (err)
 		return err;
 
-	if (inode->i_flags & OVL_COPY_I_FLAGS_MASK) {
+	if (inode->i_flags & OVL_FATTR_I_FLAGS_MASK &&
+	    (S_ISREG(c->stat.mode) || S_ISDIR(c->stat.mode))) {
 		/*
 		 * Copy the fileattr inode flags that are the source of already
 		 * copied i_flags
@@ -590,66 +686,82 @@ static int ovl_copy_up_inode(struct ovl_copy_up_ctx *c, struct dentry *temp)
 	 * hard link.
 	 */
 	if (c->origin) {
-		err = ovl_set_origin(ofs, c->lowerpath.dentry, temp);
+		err = ovl_set_origin_fh(ofs, c->origin_fh, temp);
 		if (err)
 			return err;
 	}
 
 	if (c->metacopy) {
-		err = ovl_check_setxattr(ofs, temp, OVL_XATTR_METACOPY,
-					 NULL, 0, -EOPNOTSUPP);
+		struct path lowerdatapath;
+		struct ovl_metacopy metacopy_data = OVL_METACOPY_INIT;
+
+		ovl_path_lowerdata(c->dentry, &lowerdatapath);
+		if (WARN_ON_ONCE(lowerdatapath.dentry == NULL))
+			return -EIO;
+		err = ovl_get_verity_digest(ofs, &lowerdatapath, &metacopy_data);
+		if (err)
+			return err;
+
+		if (metacopy_data.digest_algo)
+			c->metacopy_digest = true;
+
+		err = ovl_set_metacopy_xattr(ofs, temp, &metacopy_data);
 		if (err)
 			return err;
 	}
 
 	inode_lock(temp->d_inode);
 	if (S_ISREG(c->stat.mode))
-		err = ovl_set_size(temp, &c->stat);
+		err = ovl_set_size(ofs, temp, &c->stat);
 	if (!err)
-		err = ovl_set_attr(temp, &c->stat);
+		err = ovl_set_attr(ofs, temp, &c->stat);
 	inode_unlock(temp->d_inode);
 
+	/* fsync metadata before moving it into upper dir */
+	if (!err && ovl_should_sync(ofs) && c->metadata_fsync)
+		err = ovl_sync_file(&upperpath);
+
 	return err;
 }
 
-struct ovl_cu_creds {
-	const struct cred *old;
-	struct cred *new;
-};
-
-static int ovl_prep_cu_creds(struct dentry *dentry, struct ovl_cu_creds *cc)
+static const struct cred *ovl_prepare_copy_up_creds(struct dentry *dentry)
 {
+	struct cred *copy_up_cred = NULL;
 	int err;
 
-	cc->old = cc->new = NULL;
-	err = security_inode_copy_up(dentry, &cc->new);
+	err = security_inode_copy_up(dentry, &copy_up_cred);
 	if (err < 0)
-		return err;
+		return ERR_PTR(err);
 
-	if (cc->new)
-		cc->old = override_creds(cc->new);
+	if (!copy_up_cred)
+		return NULL;
 
-	return 0;
+	return override_creds(copy_up_cred);
 }
 
-static void ovl_revert_cu_creds(struct ovl_cu_creds *cc)
+static void ovl_revert_copy_up_creds(const struct cred *orig_cred)
 {
-	if (cc->new) {
-		revert_creds(cc->old);
-		put_cred(cc->new);
-	}
+	const struct cred *copy_up_cred;
+
+	copy_up_cred = revert_creds(orig_cred);
+	put_cred(copy_up_cred);
 }
 
+DEFINE_CLASS(copy_up_creds, const struct cred *,
+	     if (!IS_ERR_OR_NULL(_T)) ovl_revert_copy_up_creds(_T),
+	     ovl_prepare_copy_up_creds(dentry), struct dentry *dentry)
+
 /*
  * Copyup using workdir to prepare temp file.  Used when copying up directories,
  * special files or when upper fs doesn't support O_TMPFILE.
  */
 static int ovl_copy_up_workdir(struct ovl_copy_up_ctx *c)
 {
+	struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb);
 	struct inode *inode;
-	struct inode *udir = d_inode(c->destdir), *wdir = d_inode(c->workdir);
-	struct dentry *temp, *upper;
-	struct ovl_cu_creds cc;
+	struct path path = { .mnt = ovl_upper_mnt(ofs) };
+	struct renamedata rd = {};
+	struct dentry *temp;
 	int err;
 	struct ovl_cattr cattr = {
 		/* Can't properly set mode on creation because of the umask */
@@ -658,102 +770,145 @@ static int ovl_copy_up_workdir(struct ovl_copy_up_ctx *c)
 		.link = c->link
 	};
 
-	/* workdir and destdir could be the same when copying up to indexdir */
-	err = -EIO;
-	if (lock_rename(c->workdir, c->destdir) != NULL)
-		goto unlock;
-
-	err = ovl_prep_cu_creds(c->dentry, &cc);
-	if (err)
-		goto unlock;
+	scoped_class(copy_up_creds, copy_up_creds, c->dentry) {
+		if (IS_ERR(copy_up_creds))
+			return PTR_ERR(copy_up_creds);
 
-	temp = ovl_create_temp(c->workdir, &cattr);
-	ovl_revert_cu_creds(&cc);
+		ovl_start_write(c->dentry);
+		temp = ovl_create_temp(ofs, c->workdir, &cattr);
+		ovl_end_write(c->dentry);
+	}
 
-	err = PTR_ERR(temp);
 	if (IS_ERR(temp))
-		goto unlock;
+		return PTR_ERR(temp);
 
-	err = ovl_copy_up_inode(c, temp);
+	/*
+	 * Copy up data first and then xattrs. Writing data after
+	 * xattrs will remove security.capability xattr automatically.
+	 */
+	path.dentry = temp;
+	err = ovl_copy_up_data(c, &path);
+	ovl_start_write(c->dentry);
 	if (err)
-		goto cleanup;
+		goto cleanup_unlocked;
 
 	if (S_ISDIR(c->stat.mode) && c->indexed) {
-		err = ovl_create_index(c->dentry, c->lowerpath.dentry, temp);
+		err = ovl_create_index(c->dentry, c->origin_fh, temp);
 		if (err)
-			goto cleanup;
+			goto cleanup_unlocked;
 	}
 
-	upper = lookup_one_len(c->destname.name, c->destdir, c->destname.len);
-	err = PTR_ERR(upper);
-	if (IS_ERR(upper))
-		goto cleanup;
+	/*
+	 * We cannot hold lock_rename() throughout this helper, because of
+	 * lock ordering with sb_writers, which shouldn't be held when calling
+	 * ovl_copy_up_data(), so lock workdir and destdir and make sure that
+	 * temp wasn't moved before copy up completion or cleanup.
+	 */
+	rd.mnt_idmap = ovl_upper_mnt_idmap(ofs);
+	rd.old_parent = c->workdir;
+	rd.new_parent = c->destdir;
+	rd.flags = 0;
+	err = start_renaming_dentry(&rd, 0, temp,
+				    &QSTR_LEN(c->destname.name, c->destname.len));
+	if (err) {
+		/* temp or workdir moved underneath us? map to -EIO */
+		err = -EIO;
+	}
+	if (err)
+		goto cleanup_unlocked;
+
+	err = ovl_copy_up_metadata(c, temp);
+	if (!err)
+		err = ovl_do_rename_rd(&rd);
+	end_renaming(&rd);
 
-	err = ovl_do_rename(wdir, temp, udir, upper, 0);
-	dput(upper);
 	if (err)
-		goto cleanup;
+		goto cleanup_unlocked;
 
-	if (!c->metacopy)
-		ovl_set_upperdata(d_inode(c->dentry));
 	inode = d_inode(c->dentry);
+	if (c->metacopy_digest)
+		ovl_set_flag(OVL_HAS_DIGEST, inode);
+	else
+		ovl_clear_flag(OVL_HAS_DIGEST, inode);
+	ovl_clear_flag(OVL_VERIFIED_DIGEST, inode);
+
+	if (!c->metacopy)
+		ovl_set_upperdata(inode);
 	ovl_inode_update(inode, temp);
 	if (S_ISDIR(inode->i_mode))
 		ovl_set_flag(OVL_WHITEOUTS, inode);
-unlock:
-	unlock_rename(c->workdir, c->destdir);
+out:
+	ovl_end_write(c->dentry);
 
 	return err;
 
-cleanup:
-	ovl_cleanup(wdir, temp);
+cleanup_unlocked:
+	ovl_cleanup(ofs, c->workdir, temp);
 	dput(temp);
-	goto unlock;
+	goto out;
 }
 
 /* Copyup using O_TMPFILE which does not require cross dir locking */
 static int ovl_copy_up_tmpfile(struct ovl_copy_up_ctx *c)
 {
+	struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb);
 	struct inode *udir = d_inode(c->destdir);
 	struct dentry *temp, *upper;
-	struct ovl_cu_creds cc;
+	struct file *tmpfile;
 	int err;
 
-	err = ovl_prep_cu_creds(c->dentry, &cc);
-	if (err)
-		return err;
+	scoped_class(copy_up_creds, copy_up_creds, c->dentry) {
+		if (IS_ERR(copy_up_creds))
+			return PTR_ERR(copy_up_creds);
 
-	temp = ovl_do_tmpfile(c->workdir, c->stat.mode);
-	ovl_revert_cu_creds(&cc);
+		ovl_start_write(c->dentry);
+		tmpfile = ovl_do_tmpfile(ofs, c->workdir, c->stat.mode);
+		ovl_end_write(c->dentry);
+	}
 
-	if (IS_ERR(temp))
-		return PTR_ERR(temp);
+	if (IS_ERR(tmpfile))
+		return PTR_ERR(tmpfile);
 
-	err = ovl_copy_up_inode(c, temp);
-	if (err)
-		goto out_dput;
+	temp = tmpfile->f_path.dentry;
+	if (!c->metacopy && c->stat.size) {
+		err = ovl_copy_up_file(ofs, c->dentry, tmpfile, c->stat.size,
+				       !c->metadata_fsync);
+		if (err)
+			goto out_fput;
+	}
 
-	inode_lock_nested(udir, I_MUTEX_PARENT);
+	ovl_start_write(c->dentry);
 
-	upper = lookup_one_len(c->destname.name, c->destdir, c->destname.len);
+	err = ovl_copy_up_metadata(c, temp);
+	if (err)
+		goto out;
+
+	upper = ovl_start_creating_upper(ofs, c->destdir,
+					 &QSTR_LEN(c->destname.name,
+						   c->destname.len));
 	err = PTR_ERR(upper);
 	if (!IS_ERR(upper)) {
-		err = ovl_do_link(temp, udir, upper);
-		dput(upper);
+		err = ovl_do_link(ofs, temp, udir, upper);
+		end_creating(upper);
 	}
-	inode_unlock(udir);
 
 	if (err)
-		goto out_dput;
+		goto out;
+
+	if (c->metacopy_digest)
+		ovl_set_flag(OVL_HAS_DIGEST, d_inode(c->dentry));
+	else
+		ovl_clear_flag(OVL_HAS_DIGEST, d_inode(c->dentry));
+	ovl_clear_flag(OVL_VERIFIED_DIGEST, d_inode(c->dentry));
 
 	if (!c->metacopy)
 		ovl_set_upperdata(d_inode(c->dentry));
-	ovl_inode_update(d_inode(c->dentry), temp);
-
-	return 0;
+	ovl_inode_update(d_inode(c->dentry), dget(temp));
 
-out_dput:
-	dput(temp);
+out:
+	ovl_end_write(c->dentry);
+out_fput:
+	fput(tmpfile);
 	return err;
 }
 
@@ -770,6 +925,8 @@ static int ovl_do_copy_up(struct ovl_copy_up_ctx *c)
 {
 	int err;
 	struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb);
+	struct dentry *origin = c->lowerpath.dentry;
+	struct ovl_fh *fh = NULL;
 	bool to_index = false;
 
 	/*
@@ -786,25 +943,42 @@ static int ovl_do_copy_up(struct ovl_copy_up_ctx *c)
 			to_index = true;
 	}
 
-	if (S_ISDIR(c->stat.mode) || c->stat.nlink == 1 || to_index)
+	if (S_ISDIR(c->stat.mode) || c->stat.nlink == 1 || to_index) {
+		fh = ovl_get_origin_fh(ofs, origin);
+		if (IS_ERR(fh))
+			return PTR_ERR(fh);
+
+		/* origin_fh may be NULL */
+		c->origin_fh = fh;
 		c->origin = true;
+	}
 
 	if (to_index) {
 		c->destdir = ovl_indexdir(c->dentry->d_sb);
-		err = ovl_get_index_name(ofs, c->lowerpath.dentry, &c->destname);
+		err = ovl_get_index_name(ofs, origin, &c->destname);
 		if (err)
-			return err;
+			goto out_free_fh;
 	} else if (WARN_ON(!c->parent)) {
 		/* Disconnected dentry must be copied up to index dir */
-		return -EIO;
+		err = -EIO;
+		goto out_free_fh;
 	} else {
 		/*
+		 * c->dentry->d_name is stabilzed by ovl_copy_up_start(),
+		 * because if we got here, it means that c->dentry has no upper
+		 * alias and changing ->d_name means going through ovl_rename()
+		 * that will call ovl_copy_up() on source and target dentry.
+		 */
+		c->destname = c->dentry->d_name;
+		/*
 		 * Mark parent "impure" because it may now contain non-pure
 		 * upper
 		 */
+		ovl_start_write(c->dentry);
 		err = ovl_set_impure(c->parent, c->destdir);
+		ovl_end_write(c->dentry);
 		if (err)
-			return err;
+			goto out_free_fh;
 	}
 
 	/* Should we copyup with O_TMPFILE or with workdir? */
@@ -818,6 +992,7 @@ static int ovl_do_copy_up(struct ovl_copy_up_ctx *c)
 	if (c->indexed)
 		ovl_set_flag(OVL_INDEX, d_inode(c->dentry));
 
+	ovl_start_write(c->dentry);
 	if (to_index) {
 		/* Initialize nlink for copy up of disconnected dentry */
 		err = ovl_set_nlink_upper(c->dentry);
@@ -826,22 +1001,26 @@ static int ovl_do_copy_up(struct ovl_copy_up_ctx *c)
 
 		/* Restore timestamps on parent (best effort) */
 		inode_lock(udir);
-		ovl_set_timestamps(c->destdir, &c->pstat);
+		ovl_set_timestamps(ofs, c->destdir, &c->pstat);
 		inode_unlock(udir);
 
 		ovl_dentry_set_upper_alias(c->dentry);
+		ovl_dentry_update_reval(c->dentry, ovl_dentry_upper(c->dentry));
 	}
+	ovl_end_write(c->dentry);
 
 out:
 	if (to_index)
 		kfree(c->destname.name);
+out_free_fh:
+	kfree(fh);
 	return err;
 }
 
 static bool ovl_need_meta_copy_up(struct dentry *dentry, umode_t mode,
 				  int flags)
 {
-	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+	struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
 
 	if (!ofs->config.metacopy)
 		return false;
@@ -852,15 +1031,28 @@ static bool ovl_need_meta_copy_up(struct dentry *dentry, umode_t mode,
 	if (flags && ((OPEN_FMODE(flags) & FMODE_WRITE) || (flags & O_TRUNC)))
 		return false;
 
+	/* Fall back to full copy if no fsverity on source data and we require verity */
+	if (ofs->config.verity_mode == OVL_VERITY_REQUIRE) {
+		struct path lowerdata;
+
+		ovl_path_lowerdata(dentry, &lowerdata);
+
+		if (WARN_ON_ONCE(lowerdata.dentry == NULL) ||
+		    ovl_ensure_verity_loaded(&lowerdata) ||
+		    !fsverity_active(d_inode(lowerdata.dentry))) {
+			return false;
+		}
+	}
+
 	return true;
 }
 
-static ssize_t ovl_getxattr(struct dentry *dentry, char *name, char **value)
+static ssize_t ovl_getxattr_value(const struct path *path, char *name, char **value)
 {
 	ssize_t res;
 	char *buf;
 
-	res = vfs_getxattr(&init_user_ns, dentry, name, NULL, 0);
+	res = ovl_do_getxattr(path, name, NULL, 0);
 	if (res == -ENODATA || res == -EOPNOTSUPP)
 		res = 0;
 
@@ -869,7 +1061,7 @@ static ssize_t ovl_getxattr(struct dentry *dentry, char *name, char **value)
 		if (!buf)
 			return -ENOMEM;
 
-		res = vfs_getxattr(&init_user_ns, dentry, name, buf, res);
+		res = ovl_do_getxattr(path, name, buf, res);
 		if (res < 0)
 			kfree(buf);
 		else
@@ -882,7 +1074,7 @@ static ssize_t ovl_getxattr(struct dentry *dentry, char *name, char **value)
 static int ovl_copy_up_meta_inode_data(struct ovl_copy_up_ctx *c)
 {
 	struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb);
-	struct path upperpath, datapath;
+	struct path upperpath;
 	int err;
 	char *capability = NULL;
 	ssize_t cap_size;
@@ -891,18 +1083,14 @@ static int ovl_copy_up_meta_inode_data(struct ovl_copy_up_ctx *c)
 	if (WARN_ON(upperpath.dentry == NULL))
 		return -EIO;
 
-	ovl_path_lowerdata(c->dentry, &datapath);
-	if (WARN_ON(datapath.dentry == NULL))
-		return -EIO;
-
 	if (c->stat.size) {
-		err = cap_size = ovl_getxattr(upperpath.dentry, XATTR_NAME_CAPS,
-					      &capability);
+		err = cap_size = ovl_getxattr_value(&upperpath, XATTR_NAME_CAPS,
+						    &capability);
 		if (cap_size < 0)
 			goto out;
 	}
 
-	err = ovl_copy_up_data(ofs, &datapath, &upperpath, c->stat.size);
+	err = ovl_copy_up_data(c, &upperpath);
 	if (err)
 		goto out_free;
 
@@ -910,18 +1098,21 @@ static int ovl_copy_up_meta_inode_data(struct ovl_copy_up_ctx *c)
 	 * Writing to upper file will clear security.capability xattr. We
 	 * don't want that to happen for normal copy-up operation.
 	 */
+	ovl_start_write(c->dentry);
 	if (capability) {
-		err = vfs_setxattr(&init_user_ns, upperpath.dentry,
-				   XATTR_NAME_CAPS, capability, cap_size, 0);
-		if (err)
-			goto out_free;
+		err = ovl_do_setxattr(ofs, upperpath.dentry, XATTR_NAME_CAPS,
+				      capability, cap_size, 0);
 	}
-
-
-	err = ovl_do_removexattr(ofs, upperpath.dentry, OVL_XATTR_METACOPY);
+	if (!err) {
+		err = ovl_removexattr(ofs, upperpath.dentry,
+				      OVL_XATTR_METACOPY);
+	}
+	ovl_end_write(c->dentry);
 	if (err)
 		goto out_free;
 
+	ovl_clear_flag(OVL_HAS_DIGEST, d_inode(c->dentry));
+	ovl_clear_flag(OVL_VERIFIED_DIGEST, d_inode(c->dentry));
 	ovl_set_upperdata(d_inode(c->dentry));
 out_free:
 	kfree(capability);
@@ -950,12 +1141,26 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 	if (err)
 		return err;
 
+	if (!kuid_has_mapping(current_user_ns(), ctx.stat.uid) ||
+	    !kgid_has_mapping(current_user_ns(), ctx.stat.gid))
+		return -EOVERFLOW;
+
+	/*
+	 * With metacopy disabled, we fsync after final metadata copyup, for
+	 * both regular files and directories to get atomic copyup semantics
+	 * on filesystems that do not use strict metadata ordering (e.g. ubifs).
+	 *
+	 * With metacopy enabled we want to avoid fsync on all meta copyup
+	 * that will hurt performance of workloads such as chown -R, so we
+	 * only fsync on data copyup as legacy behavior.
+	 */
+	ctx.metadata_fsync = !OVL_FS(dentry->d_sb)->config.metacopy &&
+			     (S_ISREG(ctx.stat.mode) || S_ISDIR(ctx.stat.mode));
 	ctx.metacopy = ovl_need_meta_copy_up(dentry, ctx.stat.mode, flags);
 
 	if (parent) {
 		ovl_path_upper(parent, &parentpath);
 		ctx.destdir = parentpath.dentry;
-		ctx.destname = dentry->d_name;
 
 		err = vfs_getattr(&parentpath, &ctx.pstat,
 				  STATX_ATIME | STATX_MTIME,
@@ -996,7 +1201,6 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 static int ovl_copy_up_flags(struct dentry *dentry, int flags)
 {
 	int err = 0;
-	const struct cred *old_cred;
 	bool disconnected = (dentry->d_flags & DCACHE_DISCONNECTED);
 
 	/*
@@ -1007,7 +1211,15 @@ static int ovl_copy_up_flags(struct dentry *dentry, int flags)
 	if (WARN_ON(disconnected && d_is_dir(dentry)))
 		return -EIO;
 
-	old_cred = ovl_override_creds(dentry->d_sb);
+	/*
+	 * We may not need lowerdata if we are only doing metacopy up, but it is
+	 * not very important to optimize this case, so do lazy lowerdata lookup
+	 * before any copy up, so we can do it before taking ovl_inode_lock().
+	 */
+	err = ovl_verify_lowerdata(dentry);
+	if (err)
+		return err;
+
 	while (!err) {
 		struct dentry *next;
 		struct dentry *parent = NULL;
@@ -1027,12 +1239,12 @@ static int ovl_copy_up_flags(struct dentry *dentry, int flags)
 			next = parent;
 		}
 
-		err = ovl_copy_up_one(parent, next, flags);
+		with_ovl_creds(dentry->d_sb)
+			err = ovl_copy_up_one(parent, next, flags);
 
 		dput(parent);
 		dput(next);
 	}
-	revert_creds(old_cred);
 
 	return err;
 }
@@ -1054,17 +1266,10 @@ static bool ovl_open_need_copy_up(struct dentry *dentry, int flags)
 
 int ovl_maybe_copy_up(struct dentry *dentry, int flags)
 {
-	int err = 0;
-
-	if (ovl_open_need_copy_up(dentry, flags)) {
-		err = ovl_want_write(dentry);
-		if (!err) {
-			err = ovl_copy_up_flags(dentry, flags);
-			ovl_drop_write(dentry);
-		}
-	}
+	if (!ovl_open_need_copy_up(dentry, flags))
+		return 0;
 
-	return err;
+	return ovl_copy_up_flags(dentry, flags);
 }
 
 int ovl_copy_up_with_data(struct dentry *dentry)