Overlayfs: constant st_ino/d_ino for non-samefs

index c441f9387a1b..9311d183b532 100644
@@ -22,7 +22,6 @@
 #include <linux/ratelimit.h>
 #include <linux/exportfs.h>
 #include "overlayfs.h"
-#include "ovl_entry.h"
 
 #define OVL_COPY_UP_CHUNK_SIZE (1 << 20)
 

index 2949448d0c7d..b772e5a2a730 100644
@@ -14,7 +14,6 @@
 #include <linux/posix_acl.h>
 #include <linux/ratelimit.h>
 #include "overlayfs.h"
-#include "ovl_entry.h"
 
 int ovl_setattr(struct dentry *dentry, struct iattr *attr)
 {

index a12dc10bf726..505a4b8902fc 100644
@@ -15,7 +15,6 @@
 #include <linux/mount.h>
 #include <linux/exportfs.h>
 #include "overlayfs.h"
-#include "ovl_entry.h"
 
 struct ovl_lookup_data {
 	struct qstr name;

index d53157ccf0d7..1cf3bdd193a4 100644
@@ -9,6 +9,7 @@
 
 #include <linux/kernel.h>
 #include <linux/uuid.h>
+#include "ovl_entry.h"
 
 enum ovl_path_type {
 	__OVL_PATH_UPPER	= (1 << 0),

index f5738e96a052..8702803ba328 100644
@@ -18,7 +18,6 @@
 #include <linux/seq_file.h>
 #include <linux/posix_acl_xattr.h>
 #include "overlayfs.h"
-#include "ovl_entry.h"
 
 MODULE_AUTHOR("Miklos Szeredi <[email protected]>");
 MODULE_DESCRIPTION("Overlay filesystem");

index 51ca8bd16009..9158d17bb320 100644
@@ -17,7 +17,6 @@
 #include <linux/namei.h>
 #include <linux/ratelimit.h>
 #include "overlayfs.h"
-#include "ovl_entry.h"
 
 int ovl_want_write(struct dentry *dentry)
 {

index 505a4b8902fc..7b89f5944e04 100644
@@ -285,16 +285,15 @@ static int ovl_lookup_layer(struct dentry *base, struct ovl_lookup_data *d,
 
 
 static int ovl_check_origin(struct dentry *upperdentry,
-			    struct path *lowerstack, unsigned int numlower,
-			    struct path **stackp, unsigned int *ctrp)
+			    struct ovl_path *lower, unsigned int numlower,
+			    struct ovl_path **stackp, unsigned int *ctrp)
 {
 	struct vfsmount *mnt;
 	struct dentry *origin = NULL;
 	int i;
 
-
 	for (i = 0; i < numlower; i++) {
-		mnt = lowerstack[i].mnt;
+		mnt = lower[i].layer->mnt;
 		origin = ovl_get_origin(upperdentry, mnt);
 		if (IS_ERR(origin))
 			return PTR_ERR(origin);

@@ -308,12 +307,12 @@ static int ovl_check_origin(struct dentry *upperdentry,
 
 	BUG_ON(*ctrp);
 	if (!*stackp)
-		*stackp = kmalloc(sizeof(struct path), GFP_KERNEL);
+		*stackp = kmalloc(sizeof(struct ovl_path), GFP_KERNEL);
 	if (!*stackp) {
 		dput(origin);
 		return -ENOMEM;
 	}
-	**stackp = (struct path) { .dentry = origin, .mnt = mnt };
+	**stackp = (struct ovl_path){.dentry = origin, .layer = lower[i].layer};
 	*ctrp = 1;
 
 	return 0;

@@ -383,13 +382,13 @@ int ovl_verify_origin(struct dentry *dentry, struct vfsmount *mnt,
  * OVL_XATTR_ORIGIN and that origin file handle can be decoded to lower path.
  * Return 0 on match, -ESTALE on mismatch or stale origin, < 0 on error.
  */
-int ovl_verify_index(struct dentry *index, struct path *lowerstack,
+int ovl_verify_index(struct dentry *index, struct ovl_path *lower,
 		     unsigned int numlower)
 {
 	struct ovl_fh *fh = NULL;
 	size_t len;
-	struct path origin = { };
-	struct path *stack = &origin;
+	struct ovl_path origin = { };
+	struct ovl_path *stack = &origin;
 	unsigned int ctr = 0;
 	int err;
 

@@ -428,7 +427,7 @@ int ovl_verify_index(struct dentry *index, struct path *lowerstack,
 	if (err)
 		goto fail;
 
-	err = ovl_check_origin(index, lowerstack, numlower, &stack, &ctr);
+	err = ovl_check_origin(index, lower, numlower, &stack, &ctr);
 	if (!err && !ctr)
 		err = -ESTALE;
 	if (err)

@@ -567,7 +566,8 @@ int ovl_path_next(int idx, struct dentry *dentry, struct path *path)
 		idx++;
 	}
 	BUG_ON(idx > oe->numlower);
-	*path = oe->lowerstack[idx - 1];
+	path->dentry = oe->lowerstack[idx - 1].dentry;
+	path->mnt = oe->lowerstack[idx - 1].layer->mnt;
 
 	return (idx < oe->numlower) ? idx + 1 : -1;
 }

@@ -580,7 +580,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
 	struct ovl_entry *poe = dentry->d_parent->d_fsdata;
 	struct ovl_entry *roe = dentry->d_sb->s_root->d_fsdata;
-	struct path *stack = NULL;
+	struct ovl_path *stack = NULL;
 	struct dentry *upperdir, *upperdentry = NULL;
 	struct dentry *index = NULL;
 	unsigned int ctr = 0;

@@ -645,17 +645,17 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 
 	if (!d.stop && poe->numlower) {
 		err = -ENOMEM;
-		stack = kcalloc(ofs->numlower, sizeof(struct path),
+		stack = kcalloc(ofs->numlower, sizeof(struct ovl_path),
 				GFP_KERNEL);
 		if (!stack)
 			goto out_put_upper;
 	}
 
 	for (i = 0; !d.stop && i < poe->numlower; i++) {
-		struct path lowerpath = poe->lowerstack[i];
+		struct ovl_path lower = poe->lowerstack[i];
 
 		d.last = i == poe->numlower - 1;
-		err = ovl_lookup_layer(lowerpath.dentry, &d, &this);
+		err = ovl_lookup_layer(lower.dentry, &d, &this);
 		if (err)
 			goto out_put;
 

@@ -663,7 +663,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 			continue;
 
 		stack[ctr].dentry = this;
-		stack[ctr].mnt = lowerpath.mnt;
+		stack[ctr].layer = lower.layer;
 		ctr++;
 
 		if (d.stop)

@@ -671,13 +671,8 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 
 		if (d.redirect && d.redirect[0] == '/' && poe != roe) {
 			poe = roe;
-
 			/* Find the current layer on the root dentry */
-			for (i = 0; i < poe->numlower; i++)
-				if (poe->lowerstack[i].mnt == lowerpath.mnt)
-					break;
-			if (WARN_ON(i == poe->numlower))
-				break;
+			i = lower.layer->idx - 1;
 		}
 	}
 

@@ -699,7 +694,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 		goto out_put;
 
 	oe->opaque = upperopaque;
-	memcpy(oe->lowerstack, stack, sizeof(struct path) * ctr);
+	memcpy(oe->lowerstack, stack, sizeof(struct ovl_path) * ctr);
 	dentry->d_fsdata = oe;
 
 	if (upperdentry)

index 1cf3bdd193a4..6d43e0f3d6f5 100644
@@ -203,6 +203,7 @@ void ovl_path_lower(struct dentry *dentry, struct path *path);
 enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path);
 struct dentry *ovl_dentry_upper(struct dentry *dentry);
 struct dentry *ovl_dentry_lower(struct dentry *dentry);
+struct ovl_layer *ovl_layer_lower(struct dentry *dentry);
 struct dentry *ovl_dentry_real(struct dentry *dentry);
 struct dentry *ovl_i_dentry_upper(struct inode *inode);
 struct inode *ovl_inode_upper(struct inode *inode);

@@ -251,7 +252,7 @@ static inline bool ovl_is_impuredir(struct dentry *dentry)
 /* namei.c */
 int ovl_verify_origin(struct dentry *dentry, struct vfsmount *mnt,
 		      struct dentry *origin, bool is_upper, bool set);
-int ovl_verify_index(struct dentry *index, struct path *lowerstack,
+int ovl_verify_index(struct dentry *index, struct ovl_path *lower,
 		     unsigned int numlower);
 int ovl_get_index_name(struct dentry *origin, struct qstr *name);
 int ovl_path_next(int idx, struct dentry *dentry, struct path *path);

@@ -268,7 +269,7 @@ int ovl_check_d_type_supported(struct path *realpath);
 void ovl_workdir_cleanup(struct inode *dir, struct vfsmount *mnt,
 			 struct dentry *dentry, int level);
 int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt,
-			 struct path *lowerstack, unsigned int numlower);
+			 struct ovl_path *lower, unsigned int numlower);
 
 /* inode.c */
 int ovl_set_nlink_upper(struct dentry *dentry);

index 25d9b5adcd42..7573f98ddec1 100644
@@ -17,11 +17,22 @@ struct ovl_config {
 	bool index;
 };
 
+struct ovl_layer {
+	struct vfsmount *mnt;
+	/* Index of this layer in mount (upper == 0) */
+	int idx;
+};
+
+struct ovl_path {
+	struct ovl_layer *layer;
+	struct dentry *dentry;
+};
+
 /* private information held for overlayfs's superblock */
 struct ovl_fs {
 	struct vfsmount *upper_mnt;
 	unsigned numlower;
-	struct vfsmount **lower_mnt;
+	struct ovl_layer *lower_layers;
 	/* workbasedir is the path at workdir= mount option */
 	struct dentry *workbasedir;
 	/* workdir is the 'work' directory under workbasedir */

@@ -52,7 +63,7 @@ struct ovl_entry {
 		struct rcu_head rcu;
 	};
 	unsigned numlower;
-	struct path lowerstack[];
+	struct ovl_path lowerstack[];
 };
 
 struct ovl_entry *ovl_alloc_entry(unsigned int numlower);

index 333de85d6de4..4f2479b6ef91 100644
@@ -1019,7 +1019,7 @@ void ovl_workdir_cleanup(struct inode *dir, struct vfsmount *mnt,
 }
 
 int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt,
-			 struct path *lowerstack, unsigned int numlower)
+			 struct ovl_path *lower, unsigned int numlower)
 {
 	int err;
 	struct dentry *index = NULL;

@@ -1054,7 +1054,7 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt,
 			index = NULL;
 			break;
 		}
-		err = ovl_verify_index(index, lowerstack, numlower);
+		err = ovl_verify_index(index, lower, numlower);
 		/* Cleanup stale and orphan index entries */
 		if (err && (err == -ESTALE || err == -ENOENT))
 			err = ovl_cleanup(dir, index);

136 lines not on this page · raw message

index 9158d17bb320..3c3b026c189b 100644
@@ -124,7 +124,12 @@ void ovl_path_lower(struct dentry *dentry, struct path *path)
 {
 	struct ovl_entry *oe = dentry->d_fsdata;
 
-	*path = oe->numlower ? oe->lowerstack[0] : (struct path) { };
+	if (oe->numlower) {
+		path->mnt = oe->lowerstack[0].layer->mnt;
+		path->dentry = oe->lowerstack[0].dentry;
+	} else {
+		*path = (struct path) { };
+	}
 }
 
 enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path)

@@ -151,6 +156,13 @@ struct dentry *ovl_dentry_lower(struct dentry *dentry)
 	return oe->numlower ? oe->lowerstack[0].dentry : NULL;
 }
 
+struct ovl_layer *ovl_layer_lower(struct dentry *dentry)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	return oe->numlower ? oe->lowerstack[0].layer : NULL;
+}
+
 struct dentry *ovl_dentry_real(struct dentry *dentry)
 {
 	return ovl_dentry_upper(dentry) ?: ovl_dentry_lower(dentry);

index 7573f98ddec1..63ef5ae9275b 100644
@@ -21,6 +21,7 @@ struct ovl_layer {
 	struct vfsmount *mnt;
 	/* Index of this layer in mount (upper == 0) */
 	int idx;
+	dev_t pseudo_dev;
 };
 
 struct ovl_path {

index ceca3a9ac27f..0b8fe8dca187 100644
@@ -219,8 +219,10 @@ static void ovl_put_super(struct super_block *sb)
 	if (ufs->upper_mnt && ufs->upperdir_locked)
 		ovl_inuse_unlock(ufs->upper_mnt->mnt_root);
 	mntput(ufs->upper_mnt);
-	for (i = 0; i < ufs->numlower; i++)
+	for (i = 0; i < ufs->numlower; i++) {
 		mntput(ufs->lower_layers[i].mnt);
+		free_anon_bdev(ufs->lower_layers[i].pseudo_dev);
+	}
 	kfree(ufs->lower_layers);
 
 	kfree(ufs->config.lowerdir);

@@ -1032,11 +1034,19 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 		goto out_put_workdir;
 	for (i = 0; i < numlower; i++) {
 		struct vfsmount *mnt;
+		dev_t dev;
+
+		err = get_anon_bdev(&dev);
+		if (err) {
+			pr_err("overlayfs: failed to get anonymous bdev for lowerpath\n");
+			goto out_put_lower_layers;
+		}
 
 		mnt = clone_private_mount(&stack[i]);
 		err = PTR_ERR(mnt);
 		if (IS_ERR(mnt)) {
 			pr_err("overlayfs: failed to clone lowerpath\n");
+			free_anon_bdev(dev);
 			goto out_put_lower_layers;
 		}
 		/*

@@ -1047,6 +1057,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 
 		ufs->lower_layers[ufs->numlower].mnt = mnt;
 		ufs->lower_layers[ufs->numlower].idx = i + 1;
+		ufs->lower_layers[ufs->numlower].pseudo_dev = dev;
 		ufs->numlower++;
 
 		/* Check if all lower layers are on same sb */

@@ -1161,8 +1172,11 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 out_free_oe:
 	kfree(oe);
 out_put_lower_layers:
-	for (i = 0; i < ufs->numlower; i++)
+	for (i = 0; i < ufs->numlower; i++) {
+		if (ufs->lower_layers[i].mnt)
+			free_anon_bdev(ufs->lower_layers[i].pseudo_dev);
 		mntput(ufs->lower_layers[i].mnt);
+	}
 	kfree(ufs->lower_layers);
 out_put_workdir:
 	dput(ufs->workdir);

index b772e5a2a730..6c54ecff56ee 100644
@@ -58,6 +58,34 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr)
 	return err;
 }
 
+static int ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat)
+{
+	bool samefs = ovl_same_sb(dentry->d_sb);
+
+	if (samefs) {
+		/*
+		 * When all layers are on the same fs, all real inode
+		 * number are unique, so we use the overlay st_dev,
+		 * which is friendly to du -x.
+		 */
+		stat->dev = dentry->d_sb->s_dev;
+	} else if (S_ISDIR(dentry->d_inode->i_mode)) {
+		/*
+		 * Always use the overlay st_dev for directories, so 'find
+		 * -xdev' will scan the entire overlay mount and won't cross the
+		 * overlay mount boundaries.
+		 *
+		 * If not all layers are on the same fs the pair {real st_ino;
+		 * overlay st_dev} is not unique, so use the non persistent
+		 * overlay st_ino for directories.
+		 */
+		stat->dev = dentry->d_sb->s_dev;
+		stat->ino = dentry->d_inode->i_ino;
+	}
+
+	return 0;
+}
+
 int ovl_getattr(const struct path *path, struct kstat *stat,
 		u32 request_mask, unsigned int flags)
 {

@@ -75,13 +103,10 @@ int ovl_getattr(const struct path *path, struct kstat *stat,
 		goto out;
 
 	/*
-	 * When all layers are on the same fs, all real inode number are
-	 * unique, so we use the overlay st_dev, which is friendly to du -x.
-	 *
-	 * We also use st_ino of the copy up origin, if we know it.
+	 * When all layers are on the same fs, we use st_ino of copy up origin.
 	 * This guaranties constant st_dev/st_ino across copy up.
 	 *
-	 * If filesystem supports NFS export ops, this also guaranties
+	 * If lower filesystem supports NFS file handles, this also guaranties
 	 * persistent st_ino across mount cycle.
 	 */
 	if (ovl_same_sb(dentry->d_sb)) {

@@ -108,21 +133,12 @@ int ovl_getattr(const struct path *path, struct kstat *stat,
 			    ovl_test_flag(OVL_INDEX, d_inode(dentry)))
 				stat->ino = lowerstat.ino;
 		}
-		stat->dev = dentry->d_sb->s_dev;
-	} else if (is_dir) {
-		/*
-		 * If not all layers are on the same fs the pair {real st_ino;
-		 * overlay st_dev} is not unique, so use the non persistent
-		 * overlay st_ino.
-		 *
-		 * Always use the overlay st_dev for directories, so 'find
-		 * -xdev' will scan the entire overlay mount and won't cross the
-		 * overlay mount boundaries.
-		 */
-		stat->dev = dentry->d_sb->s_dev;
-		stat->ino = dentry->d_inode->i_ino;
 	}
 
+	err = ovl_map_dev_ino(dentry, stat);
+	if (err)
+		goto out;
+
 	/*
 	 * It's probably not worth it to count subdirs to get the
 	 * correct link count.  nlink=1 seems to pacify 'find' and

index 6c54ecff56ee..29b0adc77ebe 100644
@@ -15,6 +15,7 @@
 #include <linux/ratelimit.h>
 #include "overlayfs.h"
 
+
 int ovl_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	int err;

@@ -60,6 +61,7 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr)
 
 static int ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat)
 {
+	struct ovl_layer *lower_layer = ovl_layer_lower(dentry);
 	bool samefs = ovl_same_sb(dentry->d_sb);
 
 	if (samefs) {

@@ -81,6 +83,14 @@ static int ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat)
 		 */
 		stat->dev = dentry->d_sb->s_dev;
 		stat->ino = dentry->d_inode->i_ino;
+	} else if (lower_layer) {
+		/*
+		 * For non-samefs setup, if we cannot map all layers st_ino
+		 * to a unified address space, we need to make sure that st_dev
+		 * is unique per layer. Upper layer uses real st_dev and lower
+		 * layers use the unique anonymous bdev.
+		 */
+		stat->dev = lower_layer->pseudo_dev;
 	}
 
 	return 0;

index 29b0adc77ebe..80a4b61a1149 100644
@@ -104,6 +104,7 @@ int ovl_getattr(const struct path *path, struct kstat *stat,
 	struct path realpath;
 	const struct cred *old_cred;
 	bool is_dir = S_ISDIR(dentry->d_inode->i_mode);
+	bool samefs = ovl_same_sb(dentry->d_sb);
 	int err;
 
 	type = ovl_path_real(dentry, &realpath);

@@ -113,13 +114,13 @@ int ovl_getattr(const struct path *path, struct kstat *stat,
 		goto out;
 
 	/*
-	 * When all layers are on the same fs, we use st_ino of copy up origin.
+	 * For non-dir or same fs, we use st_ino of the copy up origin.
 	 * This guaranties constant st_dev/st_ino across copy up.
 	 *
 	 * If lower filesystem supports NFS file handles, this also guaranties
 	 * persistent st_ino across mount cycle.
 	 */
-	if (ovl_same_sb(dentry->d_sb)) {
+	if (!is_dir || samefs) {
 		if (OVL_TYPE_ORIGIN(type)) {
 			struct kstat lowerstat;
 			u32 lowermask = STATX_INO | (!is_dir ? STATX_NLINK : 0);

@@ -130,7 +131,9 @@ int ovl_getattr(const struct path *path, struct kstat *stat,
 			if (err)
 				goto out;
 
-			WARN_ON_ONCE(stat->dev != lowerstat.dev);
+			if (samefs)
+				WARN_ON_ONCE(stat->dev != lowerstat.dev);
+
 			/*
 			 * Lower hardlinks may be broken on copy up to different
 			 * upper files, so we cannot use the lower origin st_ino

index 80a4b61a1149..521c4d21eb7b 100644
@@ -63,6 +63,7 @@ static int ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat)
 {
 	struct ovl_layer *lower_layer = ovl_layer_lower(dentry);
 	bool samefs = ovl_same_sb(dentry->d_sb);
+	int xinobits = ovl_xino_bits(dentry->d_sb);
 
 	if (samefs) {
 		/*

@@ -71,6 +72,24 @@ static int ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat)
 		 * which is friendly to du -x.
 		 */
 		stat->dev = dentry->d_sb->s_dev;
+	} else if (xinobits) {
+		/*
+		 * All inode numbers of underlying fs should not be using the
+		 * high xinobits, so we use high xinobits to partition the
+		 * overlay st_ino address space. The high bits holds the layer
+		 * index (upper is 0). This way overlay inode numbers are unique
+		 * and all inodes use overlay st_dev. Inode numbers are also
+		 * persistent for a given layer configuration.
+		 */
+		if (stat->ino >> (64 - xinobits)) {
+			pr_warn_ratelimited("overlayfs: inode number too big (%pd2, ino=%llu, xinobits=%d)\n",
+					    dentry, stat->ino, xinobits);
+			return -EOVERFLOW;
+		}
+
+		if (lower_layer)
+			stat->ino |= ((u64)lower_layer->idx) << (64 - xinobits);
+		stat->dev = dentry->d_sb->s_dev;
 	} else if (S_ISDIR(dentry->d_inode->i_mode)) {
 		/*
 		 * Always use the overlay st_dev for directories, so 'find

@@ -116,11 +135,13 @@ int ovl_getattr(const struct path *path, struct kstat *stat,
 	/*
 	 * For non-dir or same fs, we use st_ino of the copy up origin.
 	 * This guaranties constant st_dev/st_ino across copy up.
+	 * With xino feature and non-samefs, we use st_ino of the copy up
+	 * origin masked with high bits that represent the layer id.
 	 *
 	 * If lower filesystem supports NFS file handles, this also guaranties
 	 * persistent st_ino across mount cycle.
 	 */
-	if (!is_dir || samefs) {
+	if (!is_dir || samefs || ovl_xino_bits(dentry->d_sb)) {
 		if (OVL_TYPE_ORIGIN(type)) {
 			struct kstat lowerstat;
 			u32 lowermask = STATX_INO | (!is_dir ? STATX_NLINK : 0);

index 6d43e0f3d6f5..29569bf1cc6e 100644
@@ -192,7 +192,8 @@ void ovl_drop_write(struct dentry *dentry);
 struct dentry *ovl_workdir(struct dentry *dentry);
 const struct cred *ovl_override_creds(struct super_block *sb);
 struct super_block *ovl_same_sb(struct super_block *sb);
-bool ovl_can_decode_fh(struct super_block *sb);
+int ovl_xino_bits(struct super_block *sb);
+int ovl_can_decode_fh(struct super_block *sb);
 struct dentry *ovl_indexdir(struct super_block *sb);
 struct ovl_entry *ovl_alloc_entry(unsigned int numlower);
 bool ovl_dentry_remote(struct dentry *dentry);

index 63ef5ae9275b..226cf94838a3 100644
@@ -52,6 +52,8 @@ struct ovl_fs {
 	/* Did we take the inuse lock? */
 	bool upperdir_locked;
 	bool workdir_locked;
+	/* Inode numbers in all layers do not use the high xino_bits */
+	int xino_bits;
 };
 
 /* private information held for every overlayfs dentry */

index 0b8fe8dca187..ddedfca9305c 100644
@@ -17,6 +17,7 @@
 #include <linux/statfs.h>
 #include <linux/seq_file.h>
 #include <linux/posix_acl_xattr.h>
+#include <linux/exportfs.h>
 #include "overlayfs.h"
 
 MODULE_AUTHOR("Miklos Szeredi <[email protected]>");

@@ -629,6 +630,7 @@ static int ovl_check_namelen(struct path *path, struct ovl_fs *ofs,
 static int ovl_lower_dir(const char *name, struct path *path,
 			 struct ovl_fs *ofs, int *stack_depth, bool *remote)
 {
+	int fh_type;
 	int err;
 
 	err = ovl_mount_dir_noesc(name, path);

@@ -648,10 +650,14 @@ static int ovl_lower_dir(const char *name, struct path *path,
 	 * The inodes index feature needs to encode and decode file
 	 * handles, so it requires that all layers support them.
 	 */
-	if (ofs->config.index && !ovl_can_decode_fh(path->dentry->d_sb)) {
+	fh_type = ovl_can_decode_fh(path->dentry->d_sb);
+	if (ofs->config.index && !fh_type) {
 		ofs->config.index = false;
 		pr_warn("overlayfs: fs on '%s' does not support file handles, falling back to index=off.\n", name);
 	}
+	/* Check if lower fs has 32bit inode numbers */
+	if (fh_type != FILEID_INO32_GEN)
+		ofs->xino_bits = 0;
 
 	return 0;
 

@@ -842,6 +848,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	unsigned int i;
 	bool remote = false;
 	struct cred *cred;
+	int fh_type;
 	int err;
 
 	err = -ENOMEM;

@@ -961,6 +968,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 		goto out_put_lowerpath;
 	}
 
+	/* Assume underlaying fs uses 32bit inodes unless proven otherwise */
+	ufs->xino_bits = 32;
 	if (ufs->config.upperdir) {
 		ufs->upper_mnt = clone_private_mount(&upperpath);
 		err = PTR_ERR(ufs->upper_mnt);

@@ -1017,14 +1026,17 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 			} else {
 				vfs_removexattr(ufs->workdir, OVL_XATTR_OPAQUE);
 			}
+		}
 
-			/* Check if upper/work fs supports file handles */
-			if (ufs->config.index &&
-			    !ovl_can_decode_fh(ufs->workdir->d_sb)) {
-				ufs->config.index = false;
-				pr_warn("overlayfs: upper fs does not support file handles, falling back to index=off.\n");
-			}
+		/* Check if upper fs supports file handles */
+		fh_type = ovl_can_decode_fh(ufs->upper_mnt->mnt_sb);
+		if (ufs->config.index && !fh_type) {
+			ufs->config.index = false;
+			pr_warn("overlayfs: upper fs does not support file handles, falling back to index=off.\n");
 		}
+		/* Check if upper fs has 32bit inode numbers */
+		if (fh_type != FILEID_INO32_GEN)
+			ufs->xino_bits = 0;
 	}
 
 	err = -ENOMEM;

@@ -1073,6 +1085,10 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	else if (ufs->upper_mnt->mnt_sb != ufs->same_sb)
 		ufs->same_sb = NULL;
 
+	/* When all layers on same fs, overlay can use real inode numbers */
+	if (ufs->same_sb)
+		ufs->xino_bits = 0;
+
 	err = -ENOMEM;
 	oe = ovl_alloc_entry(numlower);
 	if (!oe)

index 3c3b026c189b..255ae337fc46 100644
@@ -50,10 +50,28 @@ struct super_block *ovl_same_sb(struct super_block *sb)
 	return ofs->same_sb;
 }
 
-bool ovl_can_decode_fh(struct super_block *sb)
+int ovl_xino_bits(struct super_block *sb)
 {
-	return (sb->s_export_op && sb->s_export_op->fh_to_dentry &&
-		!uuid_is_null(&sb->s_uuid));
+	struct ovl_fs *ofs = sb->s_fs_info;
+
+	return ofs->xino_bits;
+}
+
+/*
+ * Check if underlying fs supports file handles and try to determine encoding
+ * type, in order to deduce maximum inode number used by fs.
+ *
+ * Return 0 if file handles are not supported.
+ * Return 1 (FILEID_INO32_GEN) if fs uses the default 32bit inode encoding.
+ * Return -1 if fs uses a non default encoding with unknown inode size.
+ */
+int ovl_can_decode_fh(struct super_block *sb)
+{
+	if (!sb->s_export_op || !sb->s_export_op->fh_to_dentry ||
+	    uuid_is_null(&sb->s_uuid))
+		return 0;
+
+	return sb->s_export_op->encode_fh ? -1 : FILEID_INO32_GEN;
 }
 
 struct dentry *ovl_indexdir(struct super_block *sb)

index 4f2479b6ef91..92a6dcdbdaf7 100644
@@ -120,6 +120,10 @@ static bool ovl_calc_d_ino(struct ovl_readdir_data *rdd,
 	if (!rdd->dentry)
 		return false;
 
+	/* Always recalc d_ino when remapping lower inode numbers */
+	if (ovl_xino_bits(rdd->dentry->d_sb))
+		return true;
+
 	/* Always recalc d_ino for parent */
 	if (strcmp(p->name, "..") == 0)
 		return true;

@@ -440,6 +444,19 @@ static struct ovl_dir_cache *ovl_cache_get(struct dentry *dentry)
 	return cache;
 }
 
+/* Map inode number to lower layer unique range */
+static u64 ovl_remap_lower_ino(u64 ino, int xinobits, int idx,
+			       const char *name, int namelen)
+{
+	if (ino >> (64 - xinobits)) {
+		pr_warn_ratelimited("overlayfs: d_ino too big (%.*s, ino=%llu, xinobits=%d)\n",
+				    namelen, name, ino, xinobits);
+		return ino;
+	}
+
+	return ino | ((u64)idx) << (64 - xinobits);
+}
+
 /*
  * Set d_ino for upper entries. Non-upper entries should always report
  * the uppermost real inode ino and should not call this function.

@@ -457,9 +474,10 @@ static int ovl_cache_update_ino(struct path *path, struct ovl_cache_entry *p)
 	struct dentry *this = NULL;
 	enum ovl_path_type type;
 	u64 ino = p->real_ino;
+	int xinobits = ovl_xino_bits(dir->d_sb);
 	int err = 0;
 
-	if (!ovl_same_sb(dir->d_sb))
+	if (!ovl_same_sb(dir->d_sb) && !xinobits)
 		goto out;
 
 	if (p->name[0] == '.') {

@@ -496,6 +514,10 @@ static int ovl_cache_update_ino(struct path *path, struct ovl_cache_entry *p)
 
 		WARN_ON_ONCE(dir->d_sb->s_dev != stat.dev);
 		ino = stat.ino;
+	} else if (xinobits && !OVL_TYPE_UPPER(type)) {
+		ino = ovl_remap_lower_ino(ino, xinobits,
+					  ovl_layer_lower(this)->idx,
+					  p->name, p->len);
 	}
 
 out:

@@ -616,6 +638,8 @@ struct ovl_readdir_translate {
 	struct ovl_dir_cache *cache;
 	struct dir_context ctx;
 	u64 parent_ino;
+	int layer_idx;
+	int xinobits;
 };
 
 static int ovl_fill_real(struct dir_context *ctx, const char *name,

@@ -626,14 +650,17 @@ static int ovl_fill_real(struct dir_context *ctx, const char *name,
 		container_of(ctx, struct ovl_readdir_translate, ctx);
 	struct dir_context *orig_ctx = rdt->orig_ctx;
 
-	if (rdt->parent_ino && strcmp(name, "..") == 0)
+	if (rdt->parent_ino && strcmp(name, "..") == 0) {
 		ino = rdt->parent_ino;
-	else if (rdt->cache) {
+	} else if (rdt->cache) {
 		struct ovl_cache_entry *p;
 
 		p = ovl_cache_entry_find(&rdt->cache->root, name, namelen);
 		if (p)
 			ino = p->ino;
+	} else if (rdt->xinobits) {
+		ino = ovl_remap_lower_ino(ino, rdt->xinobits, rdt->layer_idx,
+					  name, namelen);
 	}
 
 	return orig_ctx->actor(orig_ctx, name, namelen, offset, ino, d_type);

@@ -644,11 +671,16 @@ static int ovl_iterate_real(struct file *file, struct dir_context *ctx)
 	int err;
 	struct ovl_dir_file *od = file->private_data;
 	struct dentry *dir = file->f_path.dentry;
+	struct ovl_layer *lower_layer = ovl_layer_lower(dir);
 	struct ovl_readdir_translate rdt = {
 		.ctx.actor = ovl_fill_real,
 		.orig_ctx = ctx,
+		.xinobits = ovl_xino_bits(dir->d_sb),
 	};
 
+	if (rdt.xinobits && lower_layer)
+		rdt.layer_idx = lower_layer->idx;
+
 	if (OVL_TYPE_MERGE(ovl_path_type(dir->d_parent))) {
 		struct kstat stat;
 		struct path statpath = file->f_path;

@@ -688,9 +720,10 @@ static int ovl_iterate(struct file *file, struct dir_context *ctx)
 		 * dir is impure then need to adjust d_ino for copied up
 		 * entries.
 		 */
-		if (ovl_same_sb(dentry->d_sb) &&
-		    (ovl_test_flag(OVL_IMPURE, d_inode(dentry)) ||
-		     OVL_TYPE_MERGE(ovl_path_type(dentry->d_parent)))) {
+		if (ovl_xino_bits(dentry->d_sb) ||
+		    (ovl_same_sb(dentry->d_sb) &&
+		     (ovl_test_flag(OVL_IMPURE, d_inode(dentry)) ||
+		      OVL_TYPE_MERGE(ovl_path_type(dentry->d_parent))))) {
 			return ovl_iterate_real(file, ctx);
 		}
 		return iterate_dir(od->realfile, ctx);

index 226cf94838a3..13140028f2bb 100644
@@ -15,6 +15,7 @@ struct ovl_config {
 	bool default_permissions;
 	bool redirect_dir;
 	bool index;
+	bool xino;
 };
 
 struct ovl_layer {

index ddedfca9305c..3f41ddf6bd0d 100644
@@ -308,6 +308,8 @@ static int ovl_show_options(struct seq_file *m, struct dentry *dentry)
 	if (ufs->config.index != ovl_index_def)
 		seq_printf(m, ",index=%s",
 			   ufs->config.index ? "on" : "off");
+	if (ufs->config.xino)
+		seq_puts(m, ",xino");
 	return 0;
 }
 

@@ -341,6 +343,7 @@ enum {
 	OPT_REDIRECT_DIR_OFF,
 	OPT_INDEX_ON,
 	OPT_INDEX_OFF,
+	OPT_XINO,
 	OPT_ERR,
 };
 

@@ -353,6 +356,7 @@ static const match_table_t ovl_tokens = {
 	{OPT_REDIRECT_DIR_OFF,		"redirect_dir=off"},
 	{OPT_INDEX_ON,			"index=on"},
 	{OPT_INDEX_OFF,			"index=off"},
+	{OPT_XINO,			"xino"},
 	{OPT_ERR,			NULL}
 };
 

@@ -433,6 +437,10 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config)
 			config->index = false;
 			break;
 
+		case OPT_XINO:
+			config->xino = true;
+			break;
+
 		default:
 			pr_err("overlayfs: unrecognized mount option \"%s\" or missing value\n", p);
 			return -EINVAL;

@@ -1085,9 +1093,18 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	else if (ufs->upper_mnt->mnt_sb != ufs->same_sb)
 		ufs->same_sb = NULL;
 
-	/* When all layers on same fs, overlay can use real inode numbers */
+	/*
+	 * When all layers on same fs, overlay can use real inode numbers.
+	 * With mount option 'xino', mounter declares that there are enough
+	 * free high bits in underlying fs to hold the layer id.
+	 * If overlayfs does encounter underlying inodes using the high xino
+	 * bits reserved for layer id, stat(2) will return -EOVERLFLOW.
+	 */
+	BUILD_BUG_ON(ilog2(OVL_MAX_STACK) > 31);
 	if (ufs->same_sb)
 		ufs->xino_bits = 0;
+	else if (ufs->config.xino && !ufs->xino_bits)
+		ufs->xino_bits = ilog2(ufs->numlower) + 1;
 
 	err = -ENOMEM;
 	oe = ovl_alloc_entry(numlower);