1 files changed, 436 insertions, 956 deletions

diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 85b891152a2c..ba9146f22a2c 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -16,7 +16,10 @@
 #include <linux/posix_acl_xattr.h>
 #include <linux/exportfs.h>
 #include <linux/file.h>
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
 #include "overlayfs.h"
+#include "params.h"
 
 MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
 MODULE_DESCRIPTION("Overlay filesystem");
@@ -25,95 +28,55 @@ MODULE_LICENSE("GPL");
 
 struct ovl_dir_cache;
 
-#define OVL_MAX_STACK 500
-
-static bool ovl_redirect_dir_def = IS_ENABLED(CONFIG_OVERLAY_FS_REDIRECT_DIR);
-module_param_named(redirect_dir, ovl_redirect_dir_def, bool, 0644);
-MODULE_PARM_DESC(redirect_dir,
-		 "Default to on or off for the redirect_dir feature");
-
-static bool ovl_redirect_always_follow =
-	IS_ENABLED(CONFIG_OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW);
-module_param_named(redirect_always_follow, ovl_redirect_always_follow,
-		   bool, 0644);
-MODULE_PARM_DESC(redirect_always_follow,
-		 "Follow redirects even if redirect_dir feature is turned off");
-
-static bool ovl_index_def = IS_ENABLED(CONFIG_OVERLAY_FS_INDEX);
-module_param_named(index, ovl_index_def, bool, 0644);
-MODULE_PARM_DESC(index,
-		 "Default to on or off for the inodes index feature");
-
-static bool ovl_nfs_export_def = IS_ENABLED(CONFIG_OVERLAY_FS_NFS_EXPORT);
-module_param_named(nfs_export, ovl_nfs_export_def, bool, 0644);
-MODULE_PARM_DESC(nfs_export,
-		 "Default to on or off for the NFS export feature");
-
-static bool ovl_xino_auto_def = IS_ENABLED(CONFIG_OVERLAY_FS_XINO_AUTO);
-module_param_named(xino_auto, ovl_xino_auto_def, bool, 0644);
-MODULE_PARM_DESC(xino_auto,
-		 "Auto enable xino feature");
-
-static void ovl_entry_stack_free(struct ovl_entry *oe)
+static struct dentry *ovl_d_real(struct dentry *dentry, enum d_real_type type)
 {
-	unsigned int i;
-
-	for (i = 0; i < oe->numlower; i++)
-		dput(oe->lowerstack[i].dentry);
-}
-
-static bool ovl_metacopy_def = IS_ENABLED(CONFIG_OVERLAY_FS_METACOPY);
-module_param_named(metacopy, ovl_metacopy_def, bool, 0644);
-MODULE_PARM_DESC(metacopy,
-		 "Default to on or off for the metadata only copy up feature");
-
-static void ovl_dentry_release(struct dentry *dentry)
-{
-	struct ovl_entry *oe = dentry->d_fsdata;
+	struct dentry *upper, *lower;
+	int err;
 
-	if (oe) {
-		ovl_entry_stack_free(oe);
-		kfree_rcu(oe, rcu);
+	switch (type) {
+	case D_REAL_DATA:
+	case D_REAL_METADATA:
+		break;
+	default:
+		goto bug;
 	}
-}
-
-static struct dentry *ovl_d_real(struct dentry *dentry,
-				 const struct inode *inode)
-{
-	struct dentry *real = NULL, *lower;
-
-	/* It's an overlay file */
-	if (inode && d_inode(dentry) == inode)
-		return dentry;
 
 	if (!d_is_reg(dentry)) {
-		if (!inode || inode == d_inode(dentry))
-			return dentry;
-		goto bug;
+		/* d_real_inode() is only relevant for regular files */
+		return dentry;
 	}
 
-	real = ovl_dentry_upper(dentry);
-	if (real && (inode == d_inode(real)))
-		return real;
+	upper = ovl_dentry_upper(dentry);
+	if (upper && (type == D_REAL_METADATA ||
+		      ovl_has_upperdata(d_inode(dentry))))
+		return upper;
 
-	if (real && !inode && ovl_has_upperdata(d_inode(dentry)))
-		return real;
+	if (type == D_REAL_METADATA) {
+		lower = ovl_dentry_lower(dentry);
+		goto real_lower;
+	}
 
+	/*
+	 * Best effort lazy lookup of lowerdata for D_REAL_DATA case to return
+	 * the real lowerdata dentry.  The only current caller of d_real() with
+	 * D_REAL_DATA is d_real_inode() from trace_uprobe and this caller is
+	 * likely going to be followed reading from the file, before placing
+	 * uprobes on offset within the file, so lowerdata should be available
+	 * when setting the uprobe.
+	 */
+	err = ovl_verify_lowerdata(dentry);
+	if (err)
+		goto bug;
 	lower = ovl_dentry_lowerdata(dentry);
 	if (!lower)
 		goto bug;
-	real = lower;
 
-	/* Handle recursion */
-	real = d_real(real, inode);
+real_lower:
+	/* Handle recursion into stacked lower fs */
+	return d_real(lower, type);
 
-	if (!inode || inode == d_inode(real))
-		return real;
 bug:
-	WARN(1, "%s(%pd4, %s:%lu): real dentry (%p/%lu) not found\n",
-	     __func__, dentry, inode ? inode->i_sb->s_id : "NULL",
-	     inode ? inode->i_ino : 0, real,
-	     real && d_inode(real) ? d_inode(real)->i_ino : 0);
+	WARN(1, "%s(%pd4, %d): real dentry not found\n", __func__, dentry, type);
 	return dentry;
 }
 
@@ -121,11 +84,31 @@ static int ovl_revalidate_real(struct dentry *d, unsigned int flags, bool weak)
 {
 	int ret = 1;
 
+	if (!d)
+		return 1;
+
 	if (weak) {
 		if (d->d_flags & DCACHE_OP_WEAK_REVALIDATE)
 			ret =  d->d_op->d_weak_revalidate(d, flags);
 	} else if (d->d_flags & DCACHE_OP_REVALIDATE) {
-		ret = d->d_op->d_revalidate(d, flags);
+		struct dentry *parent;
+		struct inode *dir;
+		struct name_snapshot n;
+
+		if (flags & LOOKUP_RCU) {
+			parent = READ_ONCE(d->d_parent);
+			dir = d_inode_rcu(parent);
+			if (!dir)
+				return -ECHILD;
+		} else {
+			parent = dget_parent(d);
+			dir = d_inode(parent);
+		}
+		take_dentry_name_snapshot(&n, d);
+		ret = d->d_op->d_revalidate(dir, &n.name, d, flags);
+		release_dentry_name_snapshot(&n);
+		if (!(flags & LOOKUP_RCU))
+			dput(parent);
 		if (!ret) {
 			if (!(flags & LOOKUP_RCU))
 				d_invalidate(d);
@@ -138,28 +121,39 @@ static int ovl_revalidate_real(struct dentry *d, unsigned int flags, bool weak)
 static int ovl_dentry_revalidate_common(struct dentry *dentry,
 					unsigned int flags, bool weak)
 {
-	struct ovl_entry *oe = dentry->d_fsdata;
+	struct ovl_entry *oe;
+	struct ovl_path *lowerstack;
 	struct inode *inode = d_inode_rcu(dentry);
 	struct dentry *upper;
 	unsigned int i;
 	int ret = 1;
 
-	/* Careful in RCU mode */
-	if (!inode)
+	if (!inode) {
+		/*
+		 * Lookup of negative dentries will call ovl_dentry_init_flags()
+		 * with NULL upperdentry and NULL oe, resulting in the
+		 * DCACHE_OP*_REVALIDATE flags being cleared.  Hence the only
+		 * way to get a negative inode is due to a race with dentry
+		 * destruction.
+		 */
+		WARN_ON(!(flags & LOOKUP_RCU));
 		return -ECHILD;
+	}
 
+	oe = OVL_I_E(inode);
+	lowerstack = ovl_lowerstack(oe);
 	upper = ovl_i_dentry_upper(inode);
 	if (upper)
 		ret = ovl_revalidate_real(upper, flags, weak);
 
-	for (i = 0; ret > 0 && i < oe->numlower; i++) {
-		ret = ovl_revalidate_real(oe->lowerstack[i].dentry, flags,
-					  weak);
-	}
+	for (i = 0; ret > 0 && i < ovl_numlower(oe); i++)
+		ret = ovl_revalidate_real(lowerstack[i].dentry, flags, weak);
+
 	return ret;
 }
 
-static int ovl_dentry_revalidate(struct dentry *dentry, unsigned int flags)
+static int ovl_dentry_revalidate(struct inode *dir, const struct qstr *name,
+				 struct dentry *dentry, unsigned int flags)
 {
 	return ovl_dentry_revalidate_common(dentry, flags, false);
 }
@@ -170,12 +164,21 @@ static int ovl_dentry_weak_revalidate(struct dentry *dentry, unsigned int flags)
 }
 
 static const struct dentry_operations ovl_dentry_operations = {
-	.d_release = ovl_dentry_release,
 	.d_real = ovl_d_real,
 	.d_revalidate = ovl_dentry_revalidate,
 	.d_weak_revalidate = ovl_dentry_weak_revalidate,
 };
 
+#if IS_ENABLED(CONFIG_UNICODE)
+static const struct dentry_operations ovl_dentry_ci_operations = {
+	.d_real = ovl_d_real,
+	.d_revalidate = ovl_dentry_revalidate,
+	.d_weak_revalidate = ovl_dentry_weak_revalidate,
+	.d_hash = generic_ci_d_hash,
+	.d_compare = generic_ci_d_compare,
+};
+#endif
+
 static struct kmem_cache *ovl_inode_cachep;
 
 static struct inode *ovl_alloc_inode(struct super_block *sb)
@@ -190,9 +193,8 @@ static struct inode *ovl_alloc_inode(struct super_block *sb)
 	oi->version = 0;
 	oi->flags = 0;
 	oi->__upperdentry = NULL;
-	oi->lowerpath.dentry = NULL;
-	oi->lowerpath.layer = NULL;
-	oi->lowerdata = NULL;
+	oi->lowerdata_redirect = NULL;
+	oi->oe = NULL;
 	mutex_init(&oi->lock);
 
 	return &oi->vfs_inode;
@@ -203,6 +205,7 @@ static void ovl_free_inode(struct inode *inode)
 	struct ovl_inode *oi = OVL_I(inode);
 
 	kfree(oi->redirect);
+	kfree(oi->oe);
 	mutex_destroy(&oi->lock);
 	kmem_cache_free(ovl_inode_cachep, oi);
 }
@@ -212,75 +215,32 @@ static void ovl_destroy_inode(struct inode *inode)
 	struct ovl_inode *oi = OVL_I(inode);
 
 	dput(oi->__upperdentry);
-	dput(oi->lowerpath.dentry);
+	ovl_stack_put(ovl_lowerstack(oi->oe), ovl_numlower(oi->oe));
 	if (S_ISDIR(inode->i_mode))
 		ovl_dir_cache_free(inode);
 	else
-		iput(oi->lowerdata);
-}
-
-static void ovl_free_fs(struct ovl_fs *ofs)
-{
-	struct vfsmount **mounts;
-	unsigned i;
-
-	iput(ofs->workbasedir_trap);
-	iput(ofs->indexdir_trap);
-	iput(ofs->workdir_trap);
-	dput(ofs->whiteout);
-	dput(ofs->indexdir);
-	dput(ofs->workdir);
-	if (ofs->workdir_locked)
-		ovl_inuse_unlock(ofs->workbasedir);
-	dput(ofs->workbasedir);
-	if (ofs->upperdir_locked)
-		ovl_inuse_unlock(ovl_upper_mnt(ofs)->mnt_root);
-
-	/* Hack!  Reuse ofs->layers as a vfsmount array before freeing it */
-	mounts = (struct vfsmount **) ofs->layers;
-	for (i = 0; i < ofs->numlayer; i++) {
-		iput(ofs->layers[i].trap);
-		mounts[i] = ofs->layers[i].mnt;
-	}
-	kern_unmount_array(mounts, ofs->numlayer);
-	kfree(ofs->layers);
-	for (i = 0; i < ofs->numfs; i++)
-		free_anon_bdev(ofs->fs[i].pseudo_dev);
-	kfree(ofs->fs);
-
-	kfree(ofs->config.lowerdir);
-	kfree(ofs->config.upperdir);
-	kfree(ofs->config.workdir);
-	kfree(ofs->config.redirect_mode);
-	if (ofs->creator_cred)
-		put_cred(ofs->creator_cred);
-	kfree(ofs);
+		kfree(oi->lowerdata_redirect);
 }
 
 static void ovl_put_super(struct super_block *sb)
 {
-	struct ovl_fs *ofs = sb->s_fs_info;
+	struct ovl_fs *ofs = OVL_FS(sb);
 
-	ovl_free_fs(ofs);
+	if (ofs)
+		ovl_free_fs(ofs);
 }
 
 /* Sync real dirty inodes in upper filesystem (if it exists) */
 static int ovl_sync_fs(struct super_block *sb, int wait)
 {
-	struct ovl_fs *ofs = sb->s_fs_info;
+	struct ovl_fs *ofs = OVL_FS(sb);
 	struct super_block *upper_sb;
 	int ret;
 
 	ret = ovl_sync_status(ofs);
-	/*
-	 * We have to always set the err, because the return value isn't
-	 * checked in syncfs, and instead indirectly return an error via
-	 * the sb's writeback errseq, which VFS inspects after this call.
-	 */
-	if (ret < 0) {
-		errseq_set(&sb->s_wb_err, -EIO);
+
+	if (ret < 0)
 		return -EIO;
-	}
 
 	if (!ret)
 		return ret;
@@ -315,8 +275,9 @@ static int ovl_sync_fs(struct super_block *sb, int wait)
  */
 static int ovl_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
-	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
-	struct dentry *root_dentry = dentry->d_sb->s_root;
+	struct super_block *sb = dentry->d_sb;
+	struct ovl_fs *ofs = OVL_FS(sb);
+	struct dentry *root_dentry = sb->s_root;
 	struct path path;
 	int err;
 
@@ -326,436 +287,24 @@ static int ovl_statfs(struct dentry *dentry, struct kstatfs *buf)
 	if (!err) {
 		buf->f_namelen = ofs->namelen;
 		buf->f_type = OVERLAYFS_SUPER_MAGIC;
+		if (ovl_has_fsid(ofs))
+			buf->f_fsid = uuid_to_fsid(sb->s_uuid.b);
 	}
 
 	return err;
 }
 
-/* Will this overlay be forced to mount/remount ro? */
-static bool ovl_force_readonly(struct ovl_fs *ofs)
-{
-	return (!ovl_upper_mnt(ofs) || !ofs->workdir);
-}
-
-static const char *ovl_redirect_mode_def(void)
-{
-	return ovl_redirect_dir_def ? "on" : "off";
-}
-
-static const char * const ovl_xino_str[] = {
-	"off",
-	"auto",
-	"on",
-};
-
-static inline int ovl_xino_def(void)
-{
-	return ovl_xino_auto_def ? OVL_XINO_AUTO : OVL_XINO_OFF;
-}
-
-/**
- * ovl_show_options
- * @m: the seq_file handle
- * @dentry: The dentry to query
- *
- * Prints the mount options for a given superblock.
- * Returns zero; does not fail.
- */
-static int ovl_show_options(struct seq_file *m, struct dentry *dentry)
-{
-	struct super_block *sb = dentry->d_sb;
-	struct ovl_fs *ofs = sb->s_fs_info;
-
-	seq_show_option(m, "lowerdir", ofs->config.lowerdir);
-	if (ofs->config.upperdir) {
-		seq_show_option(m, "upperdir", ofs->config.upperdir);
-		seq_show_option(m, "workdir", ofs->config.workdir);
-	}
-	if (ofs->config.default_permissions)
-		seq_puts(m, ",default_permissions");
-	if (strcmp(ofs->config.redirect_mode, ovl_redirect_mode_def()) != 0)
-		seq_printf(m, ",redirect_dir=%s", ofs->config.redirect_mode);
-	if (ofs->config.index != ovl_index_def)
-		seq_printf(m, ",index=%s", ofs->config.index ? "on" : "off");
-	if (!ofs->config.uuid)
-		seq_puts(m, ",uuid=off");
-	if (ofs->config.nfs_export != ovl_nfs_export_def)
-		seq_printf(m, ",nfs_export=%s", ofs->config.nfs_export ?
-						"on" : "off");
-	if (ofs->config.xino != ovl_xino_def() && !ovl_same_fs(sb))
-		seq_printf(m, ",xino=%s", ovl_xino_str[ofs->config.xino]);
-	if (ofs->config.metacopy != ovl_metacopy_def)
-		seq_printf(m, ",metacopy=%s",
-			   ofs->config.metacopy ? "on" : "off");
-	if (ofs->config.ovl_volatile)
-		seq_puts(m, ",volatile");
-	if (ofs->config.userxattr)
-		seq_puts(m, ",userxattr");
-	return 0;
-}
-
-static int ovl_remount(struct super_block *sb, int *flags, char *data)
-{
-	struct ovl_fs *ofs = sb->s_fs_info;
-	struct super_block *upper_sb;
-	int ret = 0;
-
-	if (!(*flags & SB_RDONLY) && ovl_force_readonly(ofs))
-		return -EROFS;
-
-	if (*flags & SB_RDONLY && !sb_rdonly(sb)) {
-		upper_sb = ovl_upper_mnt(ofs)->mnt_sb;
-		if (ovl_should_sync(ofs)) {
-			down_read(&upper_sb->s_umount);
-			ret = sync_filesystem(upper_sb);
-			up_read(&upper_sb->s_umount);
-		}
-	}
-
-	return ret;
-}
-
 static const struct super_operations ovl_super_operations = {
 	.alloc_inode	= ovl_alloc_inode,
 	.free_inode	= ovl_free_inode,
 	.destroy_inode	= ovl_destroy_inode,
-	.drop_inode	= generic_delete_inode,
+	.drop_inode	= inode_just_drop,
 	.put_super	= ovl_put_super,
 	.sync_fs	= ovl_sync_fs,
 	.statfs		= ovl_statfs,
 	.show_options	= ovl_show_options,
-	.remount_fs	= ovl_remount,
-};
-
-enum {
-	OPT_LOWERDIR,
-	OPT_UPPERDIR,
-	OPT_WORKDIR,
-	OPT_DEFAULT_PERMISSIONS,
-	OPT_REDIRECT_DIR,
-	OPT_INDEX_ON,
-	OPT_INDEX_OFF,
-	OPT_UUID_ON,
-	OPT_UUID_OFF,
-	OPT_NFS_EXPORT_ON,
-	OPT_USERXATTR,
-	OPT_NFS_EXPORT_OFF,
-	OPT_XINO_ON,
-	OPT_XINO_OFF,
-	OPT_XINO_AUTO,
-	OPT_METACOPY_ON,
-	OPT_METACOPY_OFF,
-	OPT_VOLATILE,
-	OPT_ERR,
 };
 
-static const match_table_t ovl_tokens = {
-	{OPT_LOWERDIR,			"lowerdir=%s"},
-	{OPT_UPPERDIR,			"upperdir=%s"},
-	{OPT_WORKDIR,			"workdir=%s"},
-	{OPT_DEFAULT_PERMISSIONS,	"default_permissions"},
-	{OPT_REDIRECT_DIR,		"redirect_dir=%s"},
-	{OPT_INDEX_ON,			"index=on"},
-	{OPT_INDEX_OFF,			"index=off"},
-	{OPT_USERXATTR,			"userxattr"},
-	{OPT_UUID_ON,			"uuid=on"},
-	{OPT_UUID_OFF,			"uuid=off"},
-	{OPT_NFS_EXPORT_ON,		"nfs_export=on"},
-	{OPT_NFS_EXPORT_OFF,		"nfs_export=off"},
-	{OPT_XINO_ON,			"xino=on"},
-	{OPT_XINO_OFF,			"xino=off"},
-	{OPT_XINO_AUTO,			"xino=auto"},
-	{OPT_METACOPY_ON,		"metacopy=on"},
-	{OPT_METACOPY_OFF,		"metacopy=off"},
-	{OPT_VOLATILE,			"volatile"},
-	{OPT_ERR,			NULL}
-};
-
-static char *ovl_next_opt(char **s)
-{
-	char *sbegin = *s;
-	char *p;
-
-	if (sbegin == NULL)
-		return NULL;
-
-	for (p = sbegin; *p; p++) {
-		if (*p == '\\') {
-			p++;
-			if (!*p)
-				break;
-		} else if (*p == ',') {
-			*p = '\0';
-			*s = p + 1;
-			return sbegin;
-		}
-	}
-	*s = NULL;
-	return sbegin;
-}
-
-static int ovl_parse_redirect_mode(struct ovl_config *config, const char *mode)
-{
-	if (strcmp(mode, "on") == 0) {
-		config->redirect_dir = true;
-		/*
-		 * Does not make sense to have redirect creation without
-		 * redirect following.
-		 */
-		config->redirect_follow = true;
-	} else if (strcmp(mode, "follow") == 0) {
-		config->redirect_follow = true;
-	} else if (strcmp(mode, "off") == 0) {
-		if (ovl_redirect_always_follow)
-			config->redirect_follow = true;
-	} else if (strcmp(mode, "nofollow") != 0) {
-		pr_err("bad mount option \"redirect_dir=%s\"\n",
-		       mode);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int ovl_parse_opt(char *opt, struct ovl_config *config)
-{
-	char *p;
-	int err;
-	bool metacopy_opt = false, redirect_opt = false;
-	bool nfs_export_opt = false, index_opt = false;
-
-	config->redirect_mode = kstrdup(ovl_redirect_mode_def(), GFP_KERNEL);
-	if (!config->redirect_mode)
-		return -ENOMEM;
-
-	while ((p = ovl_next_opt(&opt)) != NULL) {
-		int token;
-		substring_t args[MAX_OPT_ARGS];
-
-		if (!*p)
-			continue;
-
-		token = match_token(p, ovl_tokens, args);
-		switch (token) {
-		case OPT_UPPERDIR:
-			kfree(config->upperdir);
-			config->upperdir = match_strdup(&args[0]);
-			if (!config->upperdir)
-				return -ENOMEM;
-			break;
-
-		case OPT_LOWERDIR:
-			kfree(config->lowerdir);
-			config->lowerdir = match_strdup(&args[0]);
-			if (!config->lowerdir)
-				return -ENOMEM;
-			break;
-
-		case OPT_WORKDIR:
-			kfree(config->workdir);
-			config->workdir = match_strdup(&args[0]);
-			if (!config->workdir)
-				return -ENOMEM;
-			break;
-
-		case OPT_DEFAULT_PERMISSIONS:
-			config->default_permissions = true;
-			break;
-
-		case OPT_REDIRECT_DIR:
-			kfree(config->redirect_mode);
-			config->redirect_mode = match_strdup(&args[0]);
-			if (!config->redirect_mode)
-				return -ENOMEM;
-			redirect_opt = true;
-			break;
-
-		case OPT_INDEX_ON:
-			config->index = true;
-			index_opt = true;
-			break;
-
-		case OPT_INDEX_OFF:
-			config->index = false;
-			index_opt = true;
-			break;
-
-		case OPT_UUID_ON:
-			config->uuid = true;
-			break;
-
-		case OPT_UUID_OFF:
-			config->uuid = false;
-			break;
-
-		case OPT_NFS_EXPORT_ON:
-			config->nfs_export = true;
-			nfs_export_opt = true;
-			break;
-
-		case OPT_NFS_EXPORT_OFF:
-			config->nfs_export = false;
-			nfs_export_opt = true;
-			break;
-
-		case OPT_XINO_ON:
-			config->xino = OVL_XINO_ON;
-			break;
-
-		case OPT_XINO_OFF:
-			config->xino = OVL_XINO_OFF;
-			break;
-
-		case OPT_XINO_AUTO:
-			config->xino = OVL_XINO_AUTO;
-			break;
-
-		case OPT_METACOPY_ON:
-			config->metacopy = true;
-			metacopy_opt = true;
-			break;
-
-		case OPT_METACOPY_OFF:
-			config->metacopy = false;
-			metacopy_opt = true;
-			break;
-
-		case OPT_VOLATILE:
-			config->ovl_volatile = true;
-			break;
-
-		case OPT_USERXATTR:
-			config->userxattr = true;
-			break;
-
-		default:
-			pr_err("unrecognized mount option \"%s\" or missing value\n",
-					p);
-			return -EINVAL;
-		}
-	}
-
-	/* Workdir/index are useless in non-upper mount */
-	if (!config->upperdir) {
-		if (config->workdir) {
-			pr_info("option \"workdir=%s\" is useless in a non-upper mount, ignore\n",
-				config->workdir);
-			kfree(config->workdir);
-			config->workdir = NULL;
-		}
-		if (config->index && index_opt) {
-			pr_info("option \"index=on\" is useless in a non-upper mount, ignore\n");
-			index_opt = false;
-		}
-		config->index = false;
-	}
-
-	if (!config->upperdir && config->ovl_volatile) {
-		pr_info("option \"volatile\" is meaningless in a non-upper mount, ignoring it.\n");
-		config->ovl_volatile = false;
-	}
-
-	err = ovl_parse_redirect_mode(config, config->redirect_mode);
-	if (err)
-		return err;
-
-	/*
-	 * This is to make the logic below simpler.  It doesn't make any other
-	 * difference, since config->redirect_dir is only used for upper.
-	 */
-	if (!config->upperdir && config->redirect_follow)
-		config->redirect_dir = true;
-
-	/* Resolve metacopy -> redirect_dir dependency */
-	if (config->metacopy && !config->redirect_dir) {
-		if (metacopy_opt && redirect_opt) {
-			pr_err("conflicting options: metacopy=on,redirect_dir=%s\n",
-			       config->redirect_mode);
-			return -EINVAL;
-		}
-		if (redirect_opt) {
-			/*
-			 * There was an explicit redirect_dir=... that resulted
-			 * in this conflict.
-			 */
-			pr_info("disabling metacopy due to redirect_dir=%s\n",
-				config->redirect_mode);
-			config->metacopy = false;
-		} else {
-			/* Automatically enable redirect otherwise. */
-			config->redirect_follow = config->redirect_dir = true;
-		}
-	}
-
-	/* Resolve nfs_export -> index dependency */
-	if (config->nfs_export && !config->index) {
-		if (!config->upperdir && config->redirect_follow) {
-			pr_info("NFS export requires \"redirect_dir=nofollow\" on non-upper mount, falling back to nfs_export=off.\n");
-			config->nfs_export = false;
-		} else if (nfs_export_opt && index_opt) {
-			pr_err("conflicting options: nfs_export=on,index=off\n");
-			return -EINVAL;
-		} else if (index_opt) {
-			/*
-			 * There was an explicit index=off that resulted
-			 * in this conflict.
-			 */
-			pr_info("disabling nfs_export due to index=off\n");
-			config->nfs_export = false;
-		} else {
-			/* Automatically enable index otherwise. */
-			config->index = true;
-		}
-	}
-
-	/* Resolve nfs_export -> !metacopy dependency */
-	if (config->nfs_export && config->metacopy) {
-		if (nfs_export_opt && metacopy_opt) {
-			pr_err("conflicting options: nfs_export=on,metacopy=on\n");
-			return -EINVAL;
-		}
-		if (metacopy_opt) {
-			/*
-			 * There was an explicit metacopy=on that resulted
-			 * in this conflict.
-			 */
-			pr_info("disabling nfs_export due to metacopy=on\n");
-			config->nfs_export = false;
-		} else {
-			/*
-			 * There was an explicit nfs_export=on that resulted
-			 * in this conflict.
-			 */
-			pr_info("disabling metacopy due to nfs_export=on\n");
-			config->metacopy = false;
-		}
-	}
-
-
-	/* Resolve userxattr -> !redirect && !metacopy dependency */
-	if (config->userxattr) {
-		if (config->redirect_follow && redirect_opt) {
-			pr_err("conflicting options: userxattr,redirect_dir=%s\n",
-			       config->redirect_mode);
-			return -EINVAL;
-		}
-		if (config->metacopy && metacopy_opt) {
-			pr_err("conflicting options: userxattr,metacopy=on\n");
-			return -EINVAL;
-		}
-		/*
-		 * Silently disable default setting of redirect and metacopy.
-		 * This shall be the default in the future as well: these
-		 * options must be explicitly enabled if used together with
-		 * userxattr.
-		 */
-		config->redirect_dir = config->redirect_follow = false;
-		config->metacopy = false;
-	}
-
-	return 0;
-}
-
 #define OVL_WORKDIR_NAME "work"
 #define OVL_INDEXDIR_NAME "index"
 
@@ -768,9 +317,8 @@ static struct dentry *ovl_workdir_create(struct ovl_fs *ofs,
 	int err;
 	bool retried = false;
 
-	inode_lock_nested(dir, I_MUTEX_PARENT);
 retry:
-	work = ovl_lookup_upper(ofs, name, ofs->workbasedir, strlen(name));
+	work = ovl_start_creating_upper(ofs, ofs->workbasedir, &QSTR(name));
 
 	if (!IS_ERR(work)) {
 		struct iattr attr = {
@@ -779,26 +327,26 @@ retry:
 		};
 
 		if (work->d_inode) {
+			end_creating_keep(work);
+			if (persist)
+				return work;
 			err = -EEXIST;
 			if (retried)
 				goto out_dput;
-
-			if (persist)
-				goto out_unlock;
-
 			retried = true;
-			err = ovl_workdir_cleanup(ofs, dir, mnt, work, 0);
+			err = ovl_workdir_cleanup(ofs, ofs->workbasedir, mnt, work, 0);
 			dput(work);
-			if (err == -EINVAL) {
-				work = ERR_PTR(err);
-				goto out_unlock;
-			}
+			if (err == -EINVAL)
+				return ERR_PTR(err);
+
 			goto retry;
 		}
 
-		err = ovl_mkdir_real(ofs, dir, &work, attr.ia_mode);
-		if (err)
-			goto out_dput;
+		work = ovl_do_mkdir(ofs, dir, work, attr.ia_mode);
+		end_creating_keep(work);
+		err = PTR_ERR(work);
+		if (IS_ERR(work))
+			goto out_err;
 
 		/* Weird filesystem returning with hashed negative (kernfs)? */
 		err = -EINVAL;
@@ -836,8 +384,6 @@ retry:
 		err = PTR_ERR(work);
 		goto out_err;
 	}
-out_unlock:
-	inode_unlock(dir);
 	return work;
 
 out_dput:
@@ -845,71 +391,7 @@ out_dput:
 out_err:
 	pr_warn("failed to create directory %s/%s (errno: %i); mounting read-only\n",
 		ofs->config.workdir, name, -err);
-	work = NULL;
-	goto out_unlock;
-}
-
-static void ovl_unescape(char *s)
-{
-	char *d = s;
-
-	for (;; s++, d++) {
-		if (*s == '\\')
-			s++;
-		*d = *s;
-		if (!*s)
-			break;
-	}
-}
-
-static int ovl_mount_dir_noesc(const char *name, struct path *path)
-{
-	int err = -EINVAL;
-
-	if (!*name) {
-		pr_err("empty lowerdir\n");
-		goto out;
-	}
-	err = kern_path(name, LOOKUP_FOLLOW, path);
-	if (err) {
-		pr_err("failed to resolve '%s': %i\n", name, err);
-		goto out;
-	}
-	err = -EINVAL;
-	if (ovl_dentry_weird(path->dentry)) {
-		pr_err("filesystem on '%s' not supported\n", name);
-		goto out_put;
-	}
-	if (!d_is_dir(path->dentry)) {
-		pr_err("'%s' not a directory\n", name);
-		goto out_put;
-	}
-	return 0;
-
-out_put:
-	path_put_init(path);
-out:
-	return err;
-}
-
-static int ovl_mount_dir(const char *name, struct path *path)
-{
-	int err = -ENOMEM;
-	char *tmp = kstrdup(name, GFP_KERNEL);
-
-	if (tmp) {
-		ovl_unescape(tmp);
-		err = ovl_mount_dir_noesc(tmp, path);
-
-		if (!err && path->dentry->d_flags & DCACHE_OP_REAL) {
-			pr_err("filesystem on '%s' not supported as upperdir\n",
-			       tmp);
-			path_put_init(path);
-			err = -EINVAL;
-		}
-		kfree(tmp);
-	}
-	return err;
+	return NULL;
 }
 
 static int ovl_check_namelen(const struct path *path, struct ovl_fs *ofs,
@@ -926,16 +408,12 @@ static int ovl_check_namelen(const struct path *path, struct ovl_fs *ofs,
 	return err;
 }
 
-static int ovl_lower_dir(const char *name, struct path *path,
+static int ovl_lower_dir(const char *name, const struct path *path,
 			 struct ovl_fs *ofs, int *stack_depth)
 {
 	int fh_type;
 	int err;
 
-	err = ovl_mount_dir_noesc(name, path);
-	if (err)
-		return err;
-
 	err = ovl_check_namelen(path, ofs, name);
 	if (err)
 		return err;
@@ -954,6 +432,7 @@ static int ovl_lower_dir(const char *name, struct path *path,
 		pr_warn("fs on '%s' does not support file handles, falling back to index=off,nfs_export=off.\n",
 			name);
 	}
+	ofs->nofh |= !fh_type;
 	/*
 	 * Decoding origin file handle is required for persistent st_ino.
 	 * Without persistent st_ino, xino=auto falls back to xino=off.
@@ -978,102 +457,14 @@ static bool ovl_workdir_ok(struct dentry *workdir, struct dentry *upperdir)
 	bool ok = false;
 
 	if (workdir != upperdir) {
-		ok = (lock_rename(workdir, upperdir) == NULL);
-		unlock_rename(workdir, upperdir);
+		struct dentry *trap = lock_rename(workdir, upperdir);
+		if (!IS_ERR(trap))
+			unlock_rename(workdir, upperdir);
+		ok = (trap == NULL);
 	}
 	return ok;
 }
 
-static unsigned int ovl_split_lowerdirs(char *str)
-{
-	unsigned int ctr = 1;
-	char *s, *d;
-
-	for (s = d = str;; s++, d++) {
-		if (*s == '\\') {
-			s++;
-		} else if (*s == ':') {
-			*d = '\0';
-			ctr++;
-			continue;
-		}
-		*d = *s;
-		if (!*s)
-			break;
-	}
-	return ctr;
-}
-
-static int ovl_own_xattr_get(const struct xattr_handler *handler,
-			     struct dentry *dentry, struct inode *inode,
-			     const char *name, void *buffer, size_t size)
-{
-	return -EOPNOTSUPP;
-}
-
-static int ovl_own_xattr_set(const struct xattr_handler *handler,
-			     struct user_namespace *mnt_userns,
-			     struct dentry *dentry, struct inode *inode,
-			     const char *name, const void *value,
-			     size_t size, int flags)
-{
-	return -EOPNOTSUPP;
-}
-
-static int ovl_other_xattr_get(const struct xattr_handler *handler,
-			       struct dentry *dentry, struct inode *inode,
-			       const char *name, void *buffer, size_t size)
-{
-	return ovl_xattr_get(dentry, inode, name, buffer, size);
-}
-
-static int ovl_other_xattr_set(const struct xattr_handler *handler,
-			       struct user_namespace *mnt_userns,
-			       struct dentry *dentry, struct inode *inode,
-			       const char *name, const void *value,
-			       size_t size, int flags)
-{
-	return ovl_xattr_set(dentry, inode, name, value, size, flags);
-}
-
-static const struct xattr_handler ovl_own_trusted_xattr_handler = {
-	.prefix	= OVL_XATTR_TRUSTED_PREFIX,
-	.get = ovl_own_xattr_get,
-	.set = ovl_own_xattr_set,
-};
-
-static const struct xattr_handler ovl_own_user_xattr_handler = {
-	.prefix	= OVL_XATTR_USER_PREFIX,
-	.get = ovl_own_xattr_get,
-	.set = ovl_own_xattr_set,
-};
-
-static const struct xattr_handler ovl_other_xattr_handler = {
-	.prefix	= "", /* catch all */
-	.get = ovl_other_xattr_get,
-	.set = ovl_other_xattr_set,
-};
-
-static const struct xattr_handler *ovl_trusted_xattr_handlers[] = {
-#ifdef CONFIG_FS_POSIX_ACL
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
-#endif
-	&ovl_own_trusted_xattr_handler,
-	&ovl_other_xattr_handler,
-	NULL
-};
-
-static const struct xattr_handler *ovl_user_xattr_handlers[] = {
-#ifdef CONFIG_FS_POSIX_ACL
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
-#endif
-	&ovl_own_user_xattr_handler,
-	&ovl_other_xattr_handler,
-	NULL
-};
-
 static int ovl_setup_trap(struct super_block *sb, struct dentry *dir,
 			  struct inode **ptrap, const char *name)
 {
@@ -1112,15 +503,12 @@ static int ovl_report_in_use(struct ovl_fs *ofs, const char *name)
 }
 
 static int ovl_get_upper(struct super_block *sb, struct ovl_fs *ofs,
-			 struct ovl_layer *upper_layer, struct path *upperpath)
+			 struct ovl_layer *upper_layer,
+			 const struct path *upperpath)
 {
 	struct vfsmount *upper_mnt;
 	int err;
 
-	err = ovl_mount_dir(ofs->config.upperdir, upperpath);
-	if (err)
-		goto out;
-
 	/* Upperdir path should not be r/o */
 	if (__mnt_is_readonly(upperpath->mnt)) {
 		pr_err("upper fs is r/o, try multi-lower layers mount\n");
@@ -1182,56 +570,56 @@ out:
 static int ovl_check_rename_whiteout(struct ovl_fs *ofs)
 {
 	struct dentry *workdir = ofs->workdir;
-	struct inode *dir = d_inode(workdir);
 	struct dentry *temp;
-	struct dentry *dest;
 	struct dentry *whiteout;
 	struct name_snapshot name;
+	struct renamedata rd = {};
+	char name2[OVL_TEMPNAME_SIZE];
 	int err;
 
-	inode_lock_nested(dir, I_MUTEX_PARENT);
-
 	temp = ovl_create_temp(ofs, workdir, OVL_CATTR(S_IFREG | 0));
 	err = PTR_ERR(temp);
 	if (IS_ERR(temp))
-		goto out_unlock;
+		return err;
 
-	dest = ovl_lookup_temp(ofs, workdir);
-	err = PTR_ERR(dest);
-	if (IS_ERR(dest)) {
+	rd.mnt_idmap = ovl_upper_mnt_idmap(ofs);
+	rd.old_parent = workdir;
+	rd.new_parent = workdir;
+	rd.flags = RENAME_WHITEOUT;
+	ovl_tempname(name2);
+	err = start_renaming_dentry(&rd, 0, temp, &QSTR(name2));
+	if (err) {
 		dput(temp);
-		goto out_unlock;
+		return err;
 	}
 
 	/* Name is inline and stable - using snapshot as a copy helper */
 	take_dentry_name_snapshot(&name, temp);
-	err = ovl_do_rename(ofs, dir, temp, dir, dest, RENAME_WHITEOUT);
+	err = ovl_do_rename_rd(&rd);
+	end_renaming(&rd);
 	if (err) {
 		if (err == -EINVAL)
 			err = 0;
 		goto cleanup_temp;
 	}
 
-	whiteout = ovl_lookup_upper(ofs, name.name.name, workdir, name.name.len);
+	whiteout = ovl_lookup_upper_unlocked(ofs, name.name.name,
+					     workdir, name.name.len);
 	err = PTR_ERR(whiteout);
 	if (IS_ERR(whiteout))
 		goto cleanup_temp;
 
-	err = ovl_is_whiteout(whiteout);
+	err = ovl_upper_is_whiteout(ofs, whiteout);
 
 	/* Best effort cleanup of whiteout and temp file */
 	if (err)
-		ovl_cleanup(ofs, dir, whiteout);
+		ovl_cleanup(ofs, workdir, whiteout);
 	dput(whiteout);
 
 cleanup_temp:
-	ovl_cleanup(ofs, dir, temp);
+	ovl_cleanup(ofs, workdir, temp);
 	release_dentry_name_snapshot(&name);
 	dput(temp);
-	dput(dest);
-
-out_unlock:
-	inode_unlock(dir);
 
 	return err;
 }
@@ -1240,15 +628,15 @@ static struct dentry *ovl_lookup_or_create(struct ovl_fs *ofs,
 					   struct dentry *parent,
 					   const char *name, umode_t mode)
 {
-	size_t len = strlen(name);
 	struct dentry *child;
 
-	inode_lock_nested(parent->d_inode, I_MUTEX_PARENT);
-	child = ovl_lookup_upper(ofs, name, parent, len);
-	if (!IS_ERR(child) && !child->d_inode)
-		child = ovl_create_real(ofs, parent->d_inode, child,
-					OVL_CATTR(mode));
-	inode_unlock(parent->d_inode);
+	child = ovl_start_creating_upper(ofs, parent, &QSTR(name));
+	if (!IS_ERR(child)) {
+		if (!child->d_inode)
+			child = ovl_create_real(ofs, parent, child,
+						OVL_CATTR(mode));
+		end_creating_keep(child);
+	}
 	dput(parent);
 
 	return child;
@@ -1341,10 +729,21 @@ static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs,
 	if (err) {
 		pr_warn("failed to set xattr on upper\n");
 		ofs->noxattr = true;
-		if (ofs->config.index || ofs->config.metacopy) {
-			ofs->config.index = false;
+		if (ovl_redirect_follow(ofs)) {
+			ofs->config.redirect_mode = OVL_REDIRECT_NOFOLLOW;
+			pr_warn("...falling back to redirect_dir=nofollow.\n");
+		}
+		if (ofs->config.metacopy) {
 			ofs->config.metacopy = false;
-			pr_warn("...falling back to index=off,metacopy=off.\n");
+			pr_warn("...falling back to metacopy=off.\n");
+		}
+		if (ofs->config.index) {
+			ofs->config.index = false;
+			pr_warn("...falling back to index=off.\n");
+		}
+		if (ovl_has_fsid(ofs)) {
+			ofs->config.uuid = OVL_UUID_NULL;
+			pr_warn("...falling back to uuid=null.\n");
 		}
 		/*
 		 * xattr support is required for persistent st_ino.
@@ -1391,6 +790,7 @@ static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs,
 		ofs->config.index = false;
 		pr_warn("upper fs does not support file handles, falling back to index=off.\n");
 	}
+	ofs->nofh |= !fh_type;
 
 	/* Check if upper fs has 32bit inode numbers */
 	if (fh_type != FILEID_INO32_GEN)
@@ -1407,46 +807,37 @@ out:
 }
 
 static int ovl_get_workdir(struct super_block *sb, struct ovl_fs *ofs,
-			   const struct path *upperpath)
+			   const struct path *upperpath,
+			   const struct path *workpath)
 {
 	int err;
-	struct path workpath = { };
-
-	err = ovl_mount_dir(ofs->config.workdir, &workpath);
-	if (err)
-		goto out;
 
 	err = -EINVAL;
-	if (upperpath->mnt != workpath.mnt) {
+	if (upperpath->mnt != workpath->mnt) {
 		pr_err("workdir and upperdir must reside under the same mount\n");
-		goto out;
+		return err;
 	}
-	if (!ovl_workdir_ok(workpath.dentry, upperpath->dentry)) {
+	if (!ovl_workdir_ok(workpath->dentry, upperpath->dentry)) {
 		pr_err("workdir and upperdir must be separate subtrees\n");
-		goto out;
+		return err;
 	}
 
-	ofs->workbasedir = dget(workpath.dentry);
+	ofs->workbasedir = dget(workpath->dentry);
 
 	if (ovl_inuse_trylock(ofs->workbasedir)) {
 		ofs->workdir_locked = true;
 	} else {
 		err = ovl_report_in_use(ofs, "workdir");
 		if (err)
-			goto out;
+			return err;
 	}
 
 	err = ovl_setup_trap(sb, ofs->workbasedir, &ofs->workbasedir_trap,
 			     "workdir");
 	if (err)
-		goto out;
-
-	err = ovl_make_workdir(sb, ofs, &workpath);
-
-out:
-	path_put(&workpath);
+		return err;
 
-	return err;
+	return ovl_make_workdir(sb, ofs, workpath);
 }
 
 static int ovl_get_indexdir(struct super_block *sb, struct ovl_fs *ofs,
@@ -1454,15 +845,20 @@ static int ovl_get_indexdir(struct super_block *sb, struct ovl_fs *ofs,
 {
 	struct vfsmount *mnt = ovl_upper_mnt(ofs);
 	struct dentry *indexdir;
+	struct dentry *origin = ovl_lowerstack(oe)->dentry;
+	const struct ovl_fh *fh;
 	int err;
 
+	fh = ovl_get_origin_fh(ofs, origin);
+	if (IS_ERR(fh))
+		return PTR_ERR(fh);
+
 	err = mnt_want_write(mnt);
 	if (err)
-		return err;
+		goto out_free_fh;
 
 	/* Verify lower root is upper root origin */
-	err = ovl_verify_origin(ofs, upperpath->dentry,
-				oe->lowerstack[0].dentry, true);
+	err = ovl_verify_origin_fh(ofs, upperpath->dentry, fh, true);
 	if (err) {
 		pr_err("failed to verify upper root origin\n");
 		goto out;
@@ -1477,10 +873,8 @@ static int ovl_get_indexdir(struct super_block *sb, struct ovl_fs *ofs,
 	if (IS_ERR(indexdir)) {
 		err = PTR_ERR(indexdir);
 	} else if (indexdir) {
-		ofs->indexdir = indexdir;
-		ofs->workdir = dget(indexdir);
-
-		err = ovl_setup_trap(sb, ofs->indexdir, &ofs->indexdir_trap,
+		ofs->workdir = indexdir;
+		err = ovl_setup_trap(sb, indexdir, &ofs->workdir_trap,
 				     "indexdir");
 		if (err)
 			goto out;
@@ -1493,15 +887,15 @@ static int ovl_get_indexdir(struct super_block *sb, struct ovl_fs *ofs,
 		 * ".overlay.upper" to indicate that index may have
 		 * directory entries.
 		 */
-		if (ovl_check_origin_xattr(ofs, ofs->indexdir)) {
-			err = ovl_verify_set_fh(ofs, ofs->indexdir,
-						OVL_XATTR_ORIGIN,
-						upperpath->dentry, true, false);
+		if (ovl_check_origin_xattr(ofs, indexdir)) {
+			err = ovl_verify_origin_xattr(ofs, indexdir,
+						      OVL_XATTR_ORIGIN,
+						      upperpath->dentry, true,
+						      false);
 			if (err)
 				pr_err("failed to verify index dir 'origin' xattr\n");
 		}
-		err = ovl_verify_upper(ofs, ofs->indexdir, upperpath->dentry,
-				       true);
+		err = ovl_verify_upper(ofs, indexdir, upperpath->dentry, true);
 		if (err)
 			pr_err("failed to verify index dir 'upper' xattr\n");
 
@@ -1509,11 +903,13 @@ static int ovl_get_indexdir(struct super_block *sb, struct ovl_fs *ofs,
 		if (!err)
 			err = ovl_indexdir_cleanup(ofs);
 	}
-	if (err || !ofs->indexdir)
+	if (err || !indexdir)
 		pr_warn("try deleting index dir or mounting with '-o index=off' to disable inodes index.\n");
 
 out:
 	mnt_drop_write(mnt);
+out_free_fh:
+	kfree(fh);
 	return err;
 }
 
@@ -1582,7 +978,7 @@ static int ovl_get_fsid(struct ovl_fs *ofs, const struct path *path)
 			pr_warn("%s uuid detected in lower fs '%pd2', falling back to xino=%s,index=off,nfs_export=off.\n",
 				uuid_is_null(&sb->s_uuid) ? "null" :
 							    "conflicting",
-				path->dentry, ovl_xino_str[ofs->config.xino]);
+				path->dentry, ovl_xino_mode(&ofs->config));
 		}
 	}
 
@@ -1599,19 +995,50 @@ static int ovl_get_fsid(struct ovl_fs *ofs, const struct path *path)
 	return ofs->numfs++;
 }
 
+/*
+ * The fsid after the last lower fsid is used for the data layers.
+ * It is a "null fs" with a null sb, null uuid, and no pseudo dev.
+ */
+static int ovl_get_data_fsid(struct ovl_fs *ofs)
+{
+	return ofs->numfs;
+}
+
+/*
+ * Set the ovl sb encoding as the same one used by the first layer
+ */
+static int ovl_set_encoding(struct super_block *sb, struct super_block *fs_sb)
+{
+	if (!sb_has_encoding(fs_sb))
+		return 0;
+
+#if IS_ENABLED(CONFIG_UNICODE)
+	if (sb_has_strict_encoding(fs_sb)) {
+		pr_err("strict encoding not supported\n");
+		return -EINVAL;
+	}
+
+	sb->s_encoding = fs_sb->s_encoding;
+	sb->s_encoding_flags = fs_sb->s_encoding_flags;
+#endif
+	return 0;
+}
+
 static int ovl_get_layers(struct super_block *sb, struct ovl_fs *ofs,
-			  struct path *stack, unsigned int numlower,
-			  struct ovl_layer *layers)
+			  struct ovl_fs_context *ctx, struct ovl_layer *layers)
 {
 	int err;
 	unsigned int i;
+	size_t nr_merged_lower;
 
-	err = -ENOMEM;
-	ofs->fs = kcalloc(numlower + 1, sizeof(struct ovl_sb), GFP_KERNEL);
+	ofs->fs = kcalloc(ctx->nr + 2, sizeof(struct ovl_sb), GFP_KERNEL);
 	if (ofs->fs == NULL)
-		goto out;
+		return -ENOMEM;
 
-	/* idx/fsid 0 are reserved for upper fs even with lower only overlay */
+	/*
+	 * idx/fsid 0 are reserved for upper fs even with lower only overlay
+	 * and the last fsid is reserved for "null fs" of the data layers.
+	 */
 	ofs->numfs++;
 
 	/*
@@ -1623,22 +1050,33 @@ static int ovl_get_layers(struct super_block *sb, struct ovl_fs *ofs,
 	err = get_anon_bdev(&ofs->fs[0].pseudo_dev);
 	if (err) {
 		pr_err("failed to get anonymous bdev for upper fs\n");
-		goto out;
+		return err;
 	}
 
 	if (ovl_upper_mnt(ofs)) {
 		ofs->fs[0].sb = ovl_upper_mnt(ofs)->mnt_sb;
 		ofs->fs[0].is_lower = false;
+
+		if (ofs->casefold) {
+			err = ovl_set_encoding(sb, ofs->fs[0].sb);
+			if (err)
+				return err;
+		}
 	}
 
-	for (i = 0; i < numlower; i++) {
+	nr_merged_lower = ctx->nr - ctx->nr_data;
+	for (i = 0; i < ctx->nr; i++) {
+		struct ovl_fs_context_layer *l = &ctx->lower[i];
 		struct vfsmount *mnt;
 		struct inode *trap;
 		int fsid;
 
-		err = fsid = ovl_get_fsid(ofs, &stack[i]);
-		if (err < 0)
-			goto out;
+		if (i < nr_merged_lower)
+			fsid = ovl_get_fsid(ofs, &l->path);
+		else
+			fsid = ovl_get_data_fsid(ofs);
+		if (fsid < 0)
+			return fsid;
 
 		/*
 		 * Check if lower root conflicts with this overlay layers before
@@ -1647,24 +1085,24 @@ static int ovl_get_layers(struct super_block *sb, struct ovl_fs *ofs,
 		 * the upperdir/workdir is in fact in-use by our
 		 * upperdir/workdir.
 		 */
-		err = ovl_setup_trap(sb, stack[i].dentry, &trap, "lowerdir");
+		err = ovl_setup_trap(sb, l->path.dentry, &trap, "lowerdir");
 		if (err)
-			goto out;
+			return err;
 
-		if (ovl_is_inuse(stack[i].dentry)) {
+		if (ovl_is_inuse(l->path.dentry)) {
 			err = ovl_report_in_use(ofs, "lowerdir");
 			if (err) {
 				iput(trap);
-				goto out;
+				return err;
 			}
 		}
 
-		mnt = clone_private_mount(&stack[i]);
+		mnt = clone_private_mount(&l->path);
 		err = PTR_ERR(mnt);
 		if (IS_ERR(mnt)) {
 			pr_err("failed to clone lowerpath\n");
 			iput(trap);
-			goto out;
+			return err;
 		}
 
 		/*
@@ -1678,8 +1116,24 @@ static int ovl_get_layers(struct super_block *sb, struct ovl_fs *ofs,
 		layers[ofs->numlayer].idx = ofs->numlayer;
 		layers[ofs->numlayer].fsid = fsid;
 		layers[ofs->numlayer].fs = &ofs->fs[fsid];
+		/* Store for printing lowerdir=... in ovl_show_options() */
+		ofs->config.lowerdirs[ofs->numlayer] = l->name;
+		l->name = NULL;
 		ofs->numlayer++;
 		ofs->fs[fsid].is_lower = true;
+
+		if (ofs->casefold) {
+			if (!ovl_upper_mnt(ofs) && !sb_has_encoding(sb)) {
+				err = ovl_set_encoding(sb, ofs->fs[fsid].sb);
+				if (err)
+					return err;
+			}
+
+			if (!sb_same_encoding(sb, mnt->mnt_sb)) {
+				pr_err("all layers must have the same encoding\n");
+				return -EINVAL;
+			}
+		}
 	}
 
 	/*
@@ -1714,69 +1168,68 @@ static int ovl_get_layers(struct super_block *sb, struct ovl_fs *ofs,
 			ofs->xino_mode);
 	}
 
-	err = 0;
-out:
-	return err;
+	return 0;
 }
 
 static struct ovl_entry *ovl_get_lowerstack(struct super_block *sb,
-				const char *lower, unsigned int numlower,
-				struct ovl_fs *ofs, struct ovl_layer *layers)
+					    struct ovl_fs_context *ctx,
+					    struct ovl_fs *ofs,
+					    struct ovl_layer *layers)
 {
 	int err;
-	struct path *stack = NULL;
 	unsigned int i;
+	size_t nr_merged_lower;
 	struct ovl_entry *oe;
+	struct ovl_path *lowerstack;
+
+	struct ovl_fs_context_layer *l;
 
-	if (!ofs->config.upperdir && numlower == 1) {
+	if (!ofs->config.upperdir && ctx->nr == 1) {
 		pr_err("at least 2 lowerdir are needed while upperdir nonexistent\n");
 		return ERR_PTR(-EINVAL);
 	}
 
-	stack = kcalloc(numlower, sizeof(struct path), GFP_KERNEL);
-	if (!stack)
-		return ERR_PTR(-ENOMEM);
+	if (ctx->nr == ctx->nr_data) {
+		pr_err("at least one non-data lowerdir is required\n");
+		return ERR_PTR(-EINVAL);
+	}
 
 	err = -EINVAL;
-	for (i = 0; i < numlower; i++) {
-		err = ovl_lower_dir(lower, &stack[i], ofs, &sb->s_stack_depth);
-		if (err)
-			goto out_err;
+	for (i = 0; i < ctx->nr; i++) {
+		l = &ctx->lower[i];
 
-		lower = strchr(lower, '\0') + 1;
+		err = ovl_lower_dir(l->name, &l->path, ofs, &sb->s_stack_depth);
+		if (err)
+			return ERR_PTR(err);
 	}
 
 	err = -EINVAL;
 	sb->s_stack_depth++;
 	if (sb->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) {
 		pr_err("maximum fs stacking depth exceeded\n");
-		goto out_err;
+		return ERR_PTR(err);
 	}
 
-	err = ovl_get_layers(sb, ofs, stack, numlower, layers);
+	err = ovl_get_layers(sb, ofs, ctx, layers);
 	if (err)
-		goto out_err;
+		return ERR_PTR(err);
 
 	err = -ENOMEM;
-	oe = ovl_alloc_entry(numlower);
+	/* Data-only layers are not merged in root directory */
+	nr_merged_lower = ctx->nr - ctx->nr_data;
+	oe = ovl_alloc_entry(nr_merged_lower);
 	if (!oe)
-		goto out_err;
+		return ERR_PTR(err);
 
-	for (i = 0; i < numlower; i++) {
-		oe->lowerstack[i].dentry = dget(stack[i].dentry);
-		oe->lowerstack[i].layer = &ofs->layers[i+1];
+	lowerstack = ovl_lowerstack(oe);
+	for (i = 0; i < nr_merged_lower; i++) {
+		l = &ctx->lower[i];
+		lowerstack[i].dentry = dget(l->path.dentry);
+		lowerstack[i].layer = &ofs->layers[i + 1];
 	}
-
-out:
-	for (i = 0; i < numlower; i++)
-		path_put(&stack[i]);
-	kfree(stack);
+	ofs->numdatalayer = ctx->nr_data;
 
 	return oe;
-
-out_err:
-	oe = ERR_PTR(err);
-	goto out;
 }
 
 /*
@@ -1857,20 +1310,19 @@ static struct dentry *ovl_get_root(struct super_block *sb,
 				   struct ovl_entry *oe)
 {
 	struct dentry *root;
-	struct ovl_path *lowerpath = &oe->lowerstack[0];
+	struct ovl_fs *ofs = OVL_FS(sb);
+	struct ovl_path *lowerpath = ovl_lowerstack(oe);
 	unsigned long ino = d_inode(lowerpath->dentry)->i_ino;
 	int fsid = lowerpath->layer->fsid;
 	struct ovl_inode_params oip = {
 		.upperdentry = upperdentry,
-		.lowerpath = lowerpath,
+		.oe = oe,
 	};
 
 	root = d_make_root(ovl_new_inode(sb, S_IFDIR, 0));
 	if (!root)
 		return NULL;
 
-	root->d_fsdata = oe;
-
 	if (upperdentry) {
 		/* Root inode uses upper st_ino/i_ino */
 		ino = d_inode(upperdentry)->i_ino;
@@ -1880,83 +1332,84 @@ static struct dentry *ovl_get_root(struct super_block *sb,
 			ovl_set_flag(OVL_IMPURE, d_inode(root));
 	}
 
+	/* Look for xwhiteouts marker except in the lowermost layer */
+	for (int i = 0; i < ovl_numlower(oe) - 1; i++, lowerpath++) {
+		struct path path = {
+			.mnt = lowerpath->layer->mnt,
+			.dentry = lowerpath->dentry,
+		};
+
+		/* overlay.opaque=x means xwhiteouts directory */
+		if (ovl_get_opaquedir_val(ofs, &path) == 'x') {
+			ovl_layer_set_xwhiteouts(ofs, lowerpath->layer);
+			ovl_dentry_set_xwhiteouts(root);
+		}
+	}
+
 	/* Root is always merge -> can have whiteouts */
 	ovl_set_flag(OVL_WHITEOUTS, d_inode(root));
 	ovl_dentry_set_flag(OVL_E_CONNECTED, root);
 	ovl_set_upperdata(d_inode(root));
 	ovl_inode_init(d_inode(root), &oip, ino, fsid);
-	ovl_dentry_update_reval(root, upperdentry, DCACHE_OP_WEAK_REVALIDATE);
+	WARN_ON(!!IS_CASEFOLDED(d_inode(root)) != ofs->casefold);
+	ovl_dentry_init_flags(root, upperdentry, oe, DCACHE_OP_WEAK_REVALIDATE);
+	/* root keeps a reference of upperdentry */
+	dget(upperdentry);
 
 	return root;
 }
 
-static int ovl_fill_super(struct super_block *sb, void *data, int silent)
+static void ovl_set_d_op(struct super_block *sb)
 {
-	struct path upperpath = { };
-	struct dentry *root_dentry;
-	struct ovl_entry *oe;
-	struct ovl_fs *ofs;
-	struct ovl_layer *layers;
-	struct cred *cred;
-	char *splitlower = NULL;
-	unsigned int numlower;
-	int err;
-
-	err = -EIO;
-	if (WARN_ON(sb->s_user_ns != current_user_ns()))
-		goto out;
-
-	sb->s_d_op = &ovl_dentry_operations;
-
-	err = -ENOMEM;
-	ofs = kzalloc(sizeof(struct ovl_fs), GFP_KERNEL);
-	if (!ofs)
-		goto out;
+#if IS_ENABLED(CONFIG_UNICODE)
+	struct ovl_fs *ofs = sb->s_fs_info;
 
-	err = -ENOMEM;
-	ofs->creator_cred = cred = prepare_creds();
-	if (!cred)
-		goto out_err;
+	if (ofs->casefold) {
+		set_default_d_op(sb, &ovl_dentry_ci_operations);
+		return;
+	}
+#endif
+	set_default_d_op(sb, &ovl_dentry_operations);
+}
 
-	/* Is there a reason anyone would want not to share whiteouts? */
-	ofs->share_whiteout = true;
+static int ovl_fill_super_creds(struct fs_context *fc, struct super_block *sb)
+{
+	struct ovl_fs *ofs = sb->s_fs_info;
+	struct cred *creator_cred = (struct cred *)ofs->creator_cred;
+	struct ovl_fs_context *ctx = fc->fs_private;
+	struct ovl_layer *layers;
+	struct ovl_entry *oe = NULL;
+	int err;
 
-	ofs->config.index = ovl_index_def;
-	ofs->config.uuid = true;
-	ofs->config.nfs_export = ovl_nfs_export_def;
-	ofs->config.xino = ovl_xino_def();
-	ofs->config.metacopy = ovl_metacopy_def;
-	err = ovl_parse_opt((char *) data, &ofs->config);
+	err = ovl_fs_params_verify(ctx, &ofs->config);
 	if (err)
-		goto out_err;
+		return err;
 
 	err = -EINVAL;
-	if (!ofs->config.lowerdir) {
-		if (!silent)
+	if (ctx->nr == 0) {
+		if (!(fc->sb_flags & SB_SILENT))
 			pr_err("missing 'lowerdir'\n");
-		goto out_err;
-	}
-
-	err = -ENOMEM;
-	splitlower = kstrdup(ofs->config.lowerdir, GFP_KERNEL);
-	if (!splitlower)
-		goto out_err;
-
-	err = -EINVAL;
-	numlower = ovl_split_lowerdirs(splitlower);
-	if (numlower > OVL_MAX_STACK) {
-		pr_err("too many lower directories, limit is %d\n",
-		       OVL_MAX_STACK);
-		goto out_err;
+		return err;
 	}
 
 	err = -ENOMEM;
-	layers = kcalloc(numlower + 1, sizeof(struct ovl_layer), GFP_KERNEL);
+	layers = kcalloc(ctx->nr + 1, sizeof(struct ovl_layer), GFP_KERNEL);
 	if (!layers)
-		goto out_err;
+		return err;
 
+	ofs->config.lowerdirs = kcalloc(ctx->nr + 1, sizeof(char *), GFP_KERNEL);
+	if (!ofs->config.lowerdirs) {
+		kfree(layers);
+		return err;
+	}
 	ofs->layers = layers;
-	/* Layer 0 is reserved for upper even if there's no upper */
+	/*
+	 * Layer 0 is reserved for upper even if there's no upper.
+	 * config.lowerdirs[0] is used for storing the user provided colon
+	 * separated lowerdir string.
+	 */
+	ofs->config.lowerdirs[0] = ctx->lowerdir_all;
+	ctx->lowerdir_all = NULL;
 	ofs->numlayer = 1;
 
 	sb->s_stack_depth = 0;
@@ -1980,12 +1433,12 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 		err = -EINVAL;
 		if (!ofs->config.workdir) {
 			pr_err("missing 'workdir'\n");
-			goto out_err;
+			return err;
 		}
 
-		err = ovl_get_upper(sb, ofs, &layers[0], &upperpath);
+		err = ovl_get_upper(sb, ofs, &layers[0], &ctx->upper);
 		if (err)
-			goto out_err;
+			return err;
 
 		upper_sb = ovl_upper_mnt(ofs)->mnt_sb;
 		if (!ovl_should_sync(ofs)) {
@@ -1993,13 +1446,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 			if (errseq_check(&upper_sb->s_wb_err, ofs->errseq)) {
 				err = -EIO;
 				pr_err("Cannot mount volatile when upperdir has an unseen error. Sync upperdir fs to clear state.\n");
-				goto out_err;
+				return err;
 			}
 		}
 
-		err = ovl_get_workdir(sb, ofs, &upperpath);
+		err = ovl_get_workdir(sb, ofs, &ctx->upper, &ctx->work);
 		if (err)
-			goto out_err;
+			return err;
 
 		if (!ofs->workdir)
 			sb->s_flags |= SB_RDONLY;
@@ -2007,27 +1460,30 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 		sb->s_stack_depth = upper_sb->s_stack_depth;
 		sb->s_time_gran = upper_sb->s_time_gran;
 	}
-	oe = ovl_get_lowerstack(sb, splitlower, numlower, ofs, layers);
+	oe = ovl_get_lowerstack(sb, ctx, ofs, layers);
 	err = PTR_ERR(oe);
 	if (IS_ERR(oe))
-		goto out_err;
+		return err;
 
 	/* If the upper fs is nonexistent, we mark overlayfs r/o too */
 	if (!ovl_upper_mnt(ofs))
 		sb->s_flags |= SB_RDONLY;
 
-	if (!ofs->config.uuid && ofs->numfs > 1) {
-		pr_warn("The uuid=off requires a single fs for lower and upper, falling back to uuid=on.\n");
-		ofs->config.uuid = true;
+	if (!ovl_origin_uuid(ofs) && ofs->numfs > 1) {
+		pr_warn("The uuid=off requires a single fs for lower and upper, falling back to uuid=null.\n");
+		ofs->config.uuid = OVL_UUID_NULL;
+	} else if (ovl_has_fsid(ofs) && ovl_upper_mnt(ofs)) {
+		/* Use per instance persistent uuid/fsid */
+		ovl_init_uuid_xattr(sb, ofs, &ctx->upper);
 	}
 
 	if (!ovl_force_readonly(ofs) && ofs->config.index) {
-		err = ovl_get_indexdir(sb, ofs, oe, &upperpath);
+		err = ovl_get_indexdir(sb, ofs, oe, &ctx->upper);
 		if (err)
 			goto out_free_oe;
 
 		/* Force r/o mount with no index dir */
-		if (!ofs->indexdir)
+		if (!ofs->workdir)
 			sb->s_flags |= SB_RDONLY;
 	}
 
@@ -2036,7 +1492,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 		goto out_free_oe;
 
 	/* Show index=off in /proc/mounts for forced r/o mount */
-	if (!ofs->indexdir) {
+	if (!ofs->workdir) {
 		ofs->config.index = false;
 		if (ovl_upper_mnt(ofs) && ofs->config.nfs_export) {
 			pr_warn("NFS export requires an index dir, falling back to nfs_export=off.\n");
@@ -2049,54 +1505,83 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 		ofs->config.nfs_export = false;
 	}
 
+	/*
+	 * Support encoding decodable file handles with nfs_export=on
+	 * and encoding non-decodable file handles with nfs_export=off
+	 * if all layers support file handles.
+	 */
 	if (ofs->config.nfs_export)
 		sb->s_export_op = &ovl_export_operations;
+	else if (!ofs->nofh)
+		sb->s_export_op = &ovl_export_fid_operations;
 
 	/* Never override disk quota limits or use reserved space */
-	cap_lower(cred->cap_effective, CAP_SYS_RESOURCE);
+	cap_lower(creator_cred->cap_effective, CAP_SYS_RESOURCE);
 
 	sb->s_magic = OVERLAYFS_SUPER_MAGIC;
-	sb->s_xattr = ofs->config.userxattr ? ovl_user_xattr_handlers :
-		ovl_trusted_xattr_handlers;
+	sb->s_xattr = ovl_xattr_handlers(ofs);
 	sb->s_fs_info = ofs;
+#ifdef CONFIG_FS_POSIX_ACL
 	sb->s_flags |= SB_POSIXACL;
+#endif
 	sb->s_iflags |= SB_I_SKIP_SYNC;
+	/*
+	 * Ensure that umask handling is done by the filesystems used
+	 * for the the upper layer instead of overlayfs as that would
+	 * lead to unexpected results.
+	 */
+	sb->s_iflags |= SB_I_NOUMASK;
+	sb->s_iflags |= SB_I_EVM_HMAC_UNSUPPORTED;
 
 	err = -ENOMEM;
-	root_dentry = ovl_get_root(sb, upperpath.dentry, oe);
-	if (!root_dentry)
+	sb->s_root = ovl_get_root(sb, ctx->upper.dentry, oe);
+	if (!sb->s_root)
 		goto out_free_oe;
 
-	mntput(upperpath.mnt);
-	kfree(splitlower);
-
-	sb->s_root = root_dentry;
-
 	return 0;
 
 out_free_oe:
-	ovl_entry_stack_free(oe);
-	kfree(oe);
-out_err:
-	kfree(splitlower);
-	path_put(&upperpath);
-	ovl_free_fs(ofs);
-out:
+	ovl_free_entry(oe);
 	return err;
 }
 
-static struct dentry *ovl_mount(struct file_system_type *fs_type, int flags,
-				const char *dev_name, void *raw_data)
+int ovl_fill_super(struct super_block *sb, struct fs_context *fc)
 {
-	return mount_nodev(fs_type, flags, raw_data, ovl_fill_super);
+	struct ovl_fs *ofs = sb->s_fs_info;
+	int err;
+
+	err = -EIO;
+	if (WARN_ON(fc->user_ns != current_user_ns()))
+		goto out_err;
+
+	ovl_set_d_op(sb);
+
+	if (!ofs->creator_cred) {
+		err = -ENOMEM;
+		ofs->creator_cred = prepare_creds();
+		if (!ofs->creator_cred)
+			goto out_err;
+	}
+
+	with_ovl_creds(sb)
+		err = ovl_fill_super_creds(fc, sb);
+
+out_err:
+	if (err) {
+		ovl_free_fs(ofs);
+		sb->s_fs_info = NULL;
+	}
+
+	return err;
 }
 
-static struct file_system_type ovl_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "overlay",
-	.fs_flags	= FS_USERNS_MOUNT,
-	.mount		= ovl_mount,
-	.kill_sb	= kill_anon_super,
+struct file_system_type ovl_fs_type = {
+	.owner			= THIS_MODULE,
+	.name			= "overlay",
+	.init_fs_context	= ovl_init_fs_context,
+	.parameters		= ovl_parameter_spec,
+	.fs_flags		= FS_USERNS_MOUNT,
+	.kill_sb		= kill_anon_super,
 };
 MODULE_ALIAS_FS("overlay");
 
@@ -2114,19 +1599,15 @@ static int __init ovl_init(void)
 	ovl_inode_cachep = kmem_cache_create("ovl_inode",
 					     sizeof(struct ovl_inode), 0,
 					     (SLAB_RECLAIM_ACCOUNT|
-					      SLAB_MEM_SPREAD|SLAB_ACCOUNT),
+					      SLAB_ACCOUNT),
 					     ovl_inode_init_once);
 	if (ovl_inode_cachep == NULL)
 		return -ENOMEM;
 
-	err = ovl_aio_request_cache_init();
-	if (!err) {
-		err = register_filesystem(&ovl_fs_type);
-		if (!err)
-			return 0;
+	err = register_filesystem(&ovl_fs_type);
+	if (!err)
+		return 0;
 
-		ovl_aio_request_cache_destroy();
-	}
 	kmem_cache_destroy(ovl_inode_cachep);
 
 	return err;
@@ -2142,7 +1623,6 @@ static void __exit ovl_exit(void)
 	 */
 	rcu_barrier();
 	kmem_cache_destroy(ovl_inode_cachep);
-	ovl_aio_request_cache_destroy();
 }
 
 module_init(ovl_init);