Merge branch 'overlayfs-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs

Pull overlayfs updates from Miklos Szeredi:

 - Report constant st_ino values across copy-up even if underlying
   layers are on different filesystems, but using different st_dev
   values for each layer.

   Ideally we'd report the same st_dev across the overlay, and it's
   possible to do for filesystems that use only 32bits for st_ino by
   unifying the inum space. It would be nice if it wasn't a choice of 32
   or 64, rather filesystems could report their current maximum (that
   could change on resize, so it wouldn't be set in stone).

 - miscellaneus fixes and a cleanup of ovl_fill_super(), that was long
   overdue.

 - created a path_put_init() helper that clears out the pointers after
   putting the ref.

   I think this could be useful elsewhere, so added it to <linux/path.h>

* 'overlayfs-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs: (30 commits)
  ovl: remove unneeded arg from ovl_verify_origin()
  ovl: Put upperdentry if ovl_check_origin() fails
  ovl: rename ufs to ofs
  ovl: clean up getting lower layers
  ovl: clean up workdir creation
  ovl: clean up getting upper layer
  ovl: move ovl_get_workdir() and ovl_get_lower_layers()
  ovl: reduce the number of arguments for ovl_workdir_create()
  ovl: change order of setup in ovl_fill_super()
  ovl: factor out ovl_free_fs() helper
  ovl: grab reference to workbasedir early
  ovl: split out ovl_get_indexdir() from ovl_fill_super()
  ovl: split out ovl_get_lower_layers() from ovl_fill_super()
  ovl: split out ovl_get_workdir() from ovl_fill_super()
  ovl: split out ovl_get_upper() from ovl_fill_super()
  ovl: split out ovl_get_lowerstack() from ovl_fill_super()
  ovl: split out ovl_get_workpath() from ovl_fill_super()
  ovl: split out ovl_get_upperpath() from ovl_fill_super()
  ovl: use path_put_init() in error paths for ovl_fill_super()
  vfs: add path_put_init()
  ...

10 files changed, 576 insertions, 376 deletions

diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index c441f9387a1b..eb3b8d39fb61 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -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)
 
@@ -486,6 +485,7 @@ static int ovl_copy_up_inode(struct ovl_copy_up_ctx *c, struct dentry *temp)
 static int ovl_copy_up_locked(struct ovl_copy_up_ctx *c)
 {
 	struct inode *udir = c->destdir->d_inode;
+	struct inode *inode;
 	struct dentry *newdentry = NULL;
 	struct dentry *temp = NULL;
 	int err;
@@ -508,7 +508,11 @@ static int ovl_copy_up_locked(struct ovl_copy_up_ctx *c)
 	if (err)
 		goto out_cleanup;
 
-	ovl_inode_update(d_inode(c->dentry), newdentry);
+	inode = d_inode(c->dentry);
+	ovl_inode_update(inode, newdentry);
+	if (S_ISDIR(inode->i_mode))
+		ovl_set_flag(OVL_WHITEOUTS, inode);
+
 out:
 	dput(temp);
 	return err;
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index cc961a3bd3bd..e13921824c70 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -181,6 +181,11 @@ static bool ovl_type_origin(struct dentry *dentry)
 	return OVL_TYPE_ORIGIN(ovl_path_type(dentry));
 }
 
+static bool ovl_may_have_whiteouts(struct dentry *dentry)
+{
+	return ovl_test_flag(OVL_WHITEOUTS, d_inode(dentry));
+}
+
 static int ovl_create_upper(struct dentry *dentry, struct inode *inode,
 			    struct cattr *attr, struct dentry *hardlink)
 {
@@ -300,7 +305,6 @@ static struct dentry *ovl_check_empty_and_clear(struct dentry *dentry)
 {
 	int err;
 	struct dentry *ret = NULL;
-	enum ovl_path_type type = ovl_path_type(dentry);
 	LIST_HEAD(list);
 
 	err = ovl_check_empty_dir(dentry, &list);
@@ -313,13 +317,13 @@ static struct dentry *ovl_check_empty_and_clear(struct dentry *dentry)
 	 * When removing an empty opaque directory, then it makes no sense to
 	 * replace it with an exact replica of itself.
 	 *
-	 * If no upperdentry then skip clearing whiteouts.
+	 * If upperdentry has whiteouts, clear them.
 	 *
 	 * Can race with copy-up, since we don't hold the upperdir mutex.
 	 * Doesn't matter, since copy-up can't create a non-empty directory
 	 * from an empty one.
 	 */
-	if (OVL_TYPE_UPPER(type) && OVL_TYPE_MERGE(type))
+	if (!list_empty(&list))
 		ret = ovl_clear_empty(dentry, &list);
 
 out_free:
@@ -698,8 +702,9 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir)
 	struct dentry *opaquedir = NULL;
 	int err;
 
-	/* Redirect dir can be !ovl_lower_positive && OVL_TYPE_MERGE */
-	if (is_dir && ovl_dentry_get_redirect(dentry)) {
+	/* Redirect/origin dir can be !ovl_lower_positive && not clean */
+	if (is_dir && (ovl_dentry_get_redirect(dentry) ||
+		       ovl_may_have_whiteouts(dentry))) {
 		opaquedir = ovl_check_empty_and_clear(dentry);
 		err = PTR_ERR(opaquedir);
 		if (IS_ERR(opaquedir))
@@ -946,7 +951,8 @@ static int ovl_rename(struct inode *olddir, struct dentry *old,
 
 	old_cred = ovl_override_creds(old->d_sb);
 
-	if (overwrite && new_is_dir && ovl_type_merge_or_lower(new)) {
+	if (overwrite && new_is_dir && (ovl_type_merge_or_lower(new) ||
+					ovl_may_have_whiteouts(new))) {
 		opaquedir = ovl_check_empty_and_clear(new);
 		err = PTR_ERR(opaquedir);
 		if (IS_ERR(opaquedir)) {
@@ -1069,9 +1075,10 @@ static int ovl_rename(struct inode *olddir, struct dentry *old,
 			drop_nlink(d_inode(new));
 	}
 
-	ovl_dentry_version_inc(old->d_parent,
-			       !overwrite && ovl_type_origin(new));
-	ovl_dentry_version_inc(new->d_parent, ovl_type_origin(old));
+	ovl_dentry_version_inc(old->d_parent, ovl_type_origin(old) ||
+			       (!overwrite && ovl_type_origin(new)));
+	ovl_dentry_version_inc(new->d_parent, ovl_type_origin(old) ||
+			       (d_inode(new) && ovl_type_origin(new)));
 
 out_dput:
 	dput(newdentry);
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 321511ed8c42..00b6b294272a 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -15,6 +15,14 @@
 #include <linux/ratelimit.h>
 #include "overlayfs.h"
 
+
+static dev_t ovl_get_pseudo_dev(struct dentry *dentry)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	return oe->lowerstack[0].layer->pseudo_dev;
+}
+
 int ovl_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	int err;
@@ -66,6 +74,7 @@ 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);
@@ -75,16 +84,13 @@ 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.
-	 * This guaranties constant st_dev/st_ino across copy up.
+	 * For non-dir or same fs, we use st_ino of the copy up origin, if we
+	 * know it. This guaranties constant st_dev/st_ino across copy up.
 	 *
 	 * If filesystem supports NFS export ops, 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);
@@ -95,7 +101,6 @@ int ovl_getattr(const struct path *path, struct kstat *stat,
 			if (err)
 				goto out;
 
-			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
@@ -107,17 +112,36 @@ int ovl_getattr(const struct path *path, struct kstat *stat,
 			if (is_dir || lowerstat.nlink == 1 ||
 			    ovl_test_flag(OVL_INDEX, d_inode(dentry)))
 				stat->ino = lowerstat.ino;
+
+			if (samefs)
+				WARN_ON_ONCE(stat->dev != lowerstat.dev);
+			else
+				stat->dev = ovl_get_pseudo_dev(dentry);
 		}
-		stat->dev = dentry->d_sb->s_dev;
-	} else if (is_dir) {
+		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 (!OVL_TYPE_UPPER(type)) {
+			/*
+			 * For non-samefs setup, to make sure that st_dev/st_ino
+			 * pair is unique across the system, we use a unique
+			 * anonymous st_dev for lower layer inode.
+			 */
+			stat->dev = ovl_get_pseudo_dev(dentry);
+		}
+	} else {
 		/*
-		 * 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.
+		 *
+		 * 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;
@@ -409,6 +433,7 @@ static inline void ovl_lockdep_annotate_inode_mutex_key(struct inode *inode)
 #ifdef CONFIG_LOCKDEP
 	static struct lock_class_key ovl_i_mutex_key[OVL_MAX_NESTING];
 	static struct lock_class_key ovl_i_mutex_dir_key[OVL_MAX_NESTING];
+	static struct lock_class_key ovl_i_lock_key[OVL_MAX_NESTING];
 
 	int depth = inode->i_sb->s_stack_depth - 1;
 
@@ -419,6 +444,8 @@ static inline void ovl_lockdep_annotate_inode_mutex_key(struct inode *inode)
 		lockdep_set_class(&inode->i_rwsem, &ovl_i_mutex_dir_key[depth]);
 	else
 		lockdep_set_class(&inode->i_rwsem, &ovl_i_mutex_key[depth]);
+
+	lockdep_set_class(&OVL_I(inode)->lock, &ovl_i_lock_key[depth]);
 #endif
 }
 
@@ -657,6 +684,16 @@ struct inode *ovl_get_inode(struct dentry *dentry, struct dentry *upperdentry,
 	if (upperdentry && ovl_is_impuredir(upperdentry))
 		ovl_set_flag(OVL_IMPURE, inode);
 
+	/* Check for non-merge dir that may have whiteouts */
+	if (S_ISDIR(realinode->i_mode)) {
+		struct ovl_entry *oe = dentry->d_fsdata;
+
+		if (((upperdentry && lowerdentry) || oe->numlower > 1) ||
+		    ovl_check_origin_xattr(upperdentry ?: lowerdentry)) {
+			ovl_set_flag(OVL_WHITEOUTS, inode);
+		}
+	}
+
 	if (inode->i_state & I_NEW)
 		unlock_new_inode(inode);
 out:
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index a12dc10bf726..625ed8066570 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -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;
@@ -286,16 +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);
@@ -309,12 +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;
@@ -350,8 +348,8 @@ static int ovl_verify_origin_fh(struct dentry *dentry, const struct ovl_fh *fh)
  *
  * Return 0 on match, -ESTALE on mismatch, < 0 on error.
  */
-int ovl_verify_origin(struct dentry *dentry, struct vfsmount *mnt,
-		      struct dentry *origin, bool is_upper, bool set)
+int ovl_verify_origin(struct dentry *dentry, struct dentry *origin,
+		      bool is_upper, bool set)
 {
 	struct inode *inode;
 	struct ovl_fh *fh;
@@ -384,13 +382,13 @@ fail:
  * 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;
 
@@ -429,7 +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)
@@ -568,11 +566,24 @@ 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;
 }
 
+static int ovl_find_layer(struct ovl_fs *ofs, struct ovl_path *path)
+{
+	int i;
+
+	for (i = 0; i < ofs->numlower; i++) {
+		if (ofs->lower_layers[i].mnt == path->layer->mnt)
+			break;
+	}
+
+	return i;
+}
+
 struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 			  unsigned int flags)
 {
@@ -581,7 +592,7 @@ 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;
@@ -630,7 +641,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 			err = ovl_check_origin(upperdentry, roe->lowerstack,
 					       roe->numlower, &stack, &ctr);
 			if (err)
-				goto out;
+				goto out_put_upper;
 		}
 
 		if (d.redirect) {
@@ -646,17 +657,17 @@ 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;
 
@@ -664,7 +675,7 @@ 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)
@@ -674,10 +685,8 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 			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))
+			i = ovl_find_layer(ofs, &lower);
+			if (WARN_ON(i == ofs->numlower))
 				break;
 		}
 	}
@@ -700,7 +709,7 @@ 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)
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index d9a0edd4e57e..13eab09a6b6f 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -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),
@@ -28,7 +29,10 @@ enum ovl_path_type {
 #define OVL_XATTR_NLINK OVL_XATTR_PREFIX "nlink"
 
 enum ovl_flag {
+	/* Pure upper dir that may contain non pure upper entries */
 	OVL_IMPURE,
+	/* Non-merge dir that may contain whiteout entries */
+	OVL_WHITEOUTS,
 	OVL_INDEX,
 };
 
@@ -223,6 +227,7 @@ bool ovl_is_whiteout(struct dentry *dentry);
 struct file *ovl_path_open(struct path *path, int flags);
 int ovl_copy_up_start(struct dentry *dentry);
 void ovl_copy_up_end(struct dentry *dentry);
+bool ovl_check_origin_xattr(struct dentry *dentry);
 bool ovl_check_dir_xattr(struct dentry *dentry, const char *name);
 int ovl_check_setxattr(struct dentry *dentry, struct dentry *upperdentry,
 		       const char *name, const void *value, size_t size,
@@ -244,9 +249,9 @@ 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_origin(struct dentry *dentry, struct dentry *origin,
+		      bool is_upper, bool set);
+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);
@@ -263,7 +268,7 @@ 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);
diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
index 36b49bd09264..752bab645879 100644
--- a/fs/overlayfs/ovl_entry.h
+++ b/fs/overlayfs/ovl_entry.h
@@ -17,11 +17,21 @@ struct ovl_config {
 	bool index;
 };
 
+struct ovl_layer {
+	struct vfsmount *mnt;
+	dev_t pseudo_dev;
+};
+
+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 +62,7 @@ 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);
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index c310e3ff7f3f..0daa4354fec4 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -26,6 +26,7 @@ struct ovl_cache_entry {
 	struct list_head l_node;
 	struct rb_node node;
 	struct ovl_cache_entry *next_maybe_whiteout;
+	bool is_upper;
 	bool is_whiteout;
 	char name[];
 };
@@ -158,6 +159,7 @@ static struct ovl_cache_entry *ovl_cache_entry_new(struct ovl_readdir_data *rdd,
 	/* Defer setting d_ino for upper entry to ovl_iterate() */
 	if (ovl_calc_d_ino(rdd, p))
 		p->ino = 0;
+	p->is_upper = rdd->is_upper;
 	p->is_whiteout = false;
 
 	if (d_type == DT_CHR) {
@@ -316,21 +318,37 @@ static inline int ovl_dir_read(struct path *realpath,
 	return err;
 }
 
+/*
+ * Can we iterate real dir directly?
+ *
+ * Non-merge dir may contain whiteouts from a time it was a merge upper, before
+ * lower dir was removed under it and possibly before it was rotated from upper
+ * to lower layer.
+ */
+static bool ovl_dir_is_real(struct dentry *dir)
+{
+	return !ovl_test_flag(OVL_WHITEOUTS, d_inode(dir));
+}
+
 static void ovl_dir_reset(struct file *file)
 {
 	struct ovl_dir_file *od = file->private_data;
 	struct ovl_dir_cache *cache = od->cache;
 	struct dentry *dentry = file->f_path.dentry;
-	enum ovl_path_type type = ovl_path_type(dentry);
+	bool is_real;
 
 	if (cache && ovl_dentry_version_get(dentry) != cache->version) {
 		ovl_cache_put(od, dentry);
 		od->cache = NULL;
 		od->cursor = NULL;
 	}
-	WARN_ON(!od->is_real && !OVL_TYPE_MERGE(type));
-	if (od->is_real && OVL_TYPE_MERGE(type))
+	is_real = ovl_dir_is_real(dentry);
+	if (od->is_real != is_real) {
+		/* is_real can only become false when dir is copied up */
+		if (WARN_ON(is_real))
+			return;
 		od->is_real = false;
+	}
 }
 
 static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list,
@@ -816,7 +834,7 @@ static int ovl_dir_open(struct inode *inode, struct file *file)
 		return PTR_ERR(realfile);
 	}
 	od->realfile = realfile;
-	od->is_real = !OVL_TYPE_MERGE(type);
+	od->is_real = ovl_dir_is_real(file->f_path.dentry);
 	od->is_upper = OVL_TYPE_UPPER(type);
 	file->private_data = od;
 
@@ -835,7 +853,7 @@ const struct file_operations ovl_dir_operations = {
 int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list)
 {
 	int err;
-	struct ovl_cache_entry *p;
+	struct ovl_cache_entry *p, *n;
 	struct rb_root root = RB_ROOT;
 
 	err = ovl_dir_read_merged(dentry, list, &root);
@@ -844,18 +862,29 @@ int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list)
 
 	err = 0;
 
-	list_for_each_entry(p, list, l_node) {
-		if (p->is_whiteout)
-			continue;
+	list_for_each_entry_safe(p, n, list, l_node) {
+		/*
+		 * Select whiteouts in upperdir, they should
+		 * be cleared when deleting this directory.
+		 */
+		if (p->is_whiteout) {
+			if (p->is_upper)
+				continue;
+			goto del_entry;
+		}
 
 		if (p->name[0] == '.') {
 			if (p->len == 1)
-				continue;
+				goto del_entry;
 			if (p->len == 2 && p->name[1] == '.')
-				continue;
+				goto del_entry;
 		}
 		err = -ENOTEMPTY;
 		break;
+
+del_entry:
+		list_del(&p->l_node);
+		kfree(p);
 	}
 
 	return err;
@@ -869,7 +898,7 @@ void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list)
 	list_for_each_entry(p, list, l_node) {
 		struct dentry *dentry;
 
-		if (!p->is_whiteout)
+		if (WARN_ON(!p->is_whiteout || !p->is_upper))
 			continue;
 
 		dentry = lookup_one_len(p->name, upper, p->len);
@@ -985,7 +1014,7 @@ 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;
@@ -1020,7 +1049,7 @@ 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);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index f5738e96a052..be03578181d2 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -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 <miklos@szeredi.hu>");
 MODULE_DESCRIPTION("Overlay filesystem");
@@ -39,15 +38,20 @@ module_param_named(index, ovl_index_def, bool, 0644);
 MODULE_PARM_DESC(ovl_index_def,
 		 "Default to on or off for the inodes index feature");
 
+static void ovl_entry_stack_free(struct ovl_entry *oe)
+{
+	unsigned int i;
+
+	for (i = 0; i < oe->numlower; i++)
+		dput(oe->lowerstack[i].dentry);
+}
+
 static void ovl_dentry_release(struct dentry *dentry)
 {
 	struct ovl_entry *oe = dentry->d_fsdata;
 
 	if (oe) {
-		unsigned int i;
-
-		for (i = 0; i < oe->numlower; i++)
-			dput(oe->lowerstack[i].dentry);
+		ovl_entry_stack_free(oe);
 		kfree_rcu(oe, rcu);
 	}
 }
@@ -207,39 +211,48 @@ static void ovl_destroy_inode(struct inode *inode)
 	call_rcu(&inode->i_rcu, ovl_i_callback);
 }
 
-static void ovl_put_super(struct super_block *sb)
+static void ovl_free_fs(struct ovl_fs *ofs)
 {
-	struct ovl_fs *ufs = sb->s_fs_info;
 	unsigned i;
 
-	dput(ufs->indexdir);
-	dput(ufs->workdir);
-	if (ufs->workdir_locked)
-		ovl_inuse_unlock(ufs->workbasedir);
-	dput(ufs->workbasedir);
-	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++)
-		mntput(ufs->lower_mnt[i]);
-	kfree(ufs->lower_mnt);
-
-	kfree(ufs->config.lowerdir);
-	kfree(ufs->config.upperdir);
-	kfree(ufs->config.workdir);
-	put_cred(ufs->creator_cred);
-	kfree(ufs);
+	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(ofs->upper_mnt->mnt_root);
+	mntput(ofs->upper_mnt);
+	for (i = 0; i < ofs->numlower; i++) {
+		mntput(ofs->lower_layers[i].mnt);
+		free_anon_bdev(ofs->lower_layers[i].pseudo_dev);
+	}
+	kfree(ofs->lower_layers);
+
+	kfree(ofs->config.lowerdir);
+	kfree(ofs->config.upperdir);
+	kfree(ofs->config.workdir);
+	if (ofs->creator_cred)
+		put_cred(ofs->creator_cred);
+	kfree(ofs);
+}
+
+static void ovl_put_super(struct super_block *sb)
+{
+	struct ovl_fs *ofs = sb->s_fs_info;
+
+	ovl_free_fs(ofs);
 }
 
 static int ovl_sync_fs(struct super_block *sb, int wait)
 {
-	struct ovl_fs *ufs = sb->s_fs_info;
+	struct ovl_fs *ofs = sb->s_fs_info;
 	struct super_block *upper_sb;
 	int ret;
 
-	if (!ufs->upper_mnt)
+	if (!ofs->upper_mnt)
 		return 0;
-	upper_sb = ufs->upper_mnt->mnt_sb;
+	upper_sb = ofs->upper_mnt->mnt_sb;
 	if (!upper_sb->s_op->sync_fs)
 		return 0;
 
@@ -277,9 +290,9 @@ static int ovl_statfs(struct dentry *dentry, struct kstatfs *buf)
 }
 
 /* Will this overlay be forced to mount/remount ro? */
-static bool ovl_force_readonly(struct ovl_fs *ufs)
+static bool ovl_force_readonly(struct ovl_fs *ofs)
 {
-	return (!ufs->upper_mnt || !ufs->workdir);
+	return (!ofs->upper_mnt || !ofs->workdir);
 }
 
 /**
@@ -291,29 +304,29 @@ static bool ovl_force_readonly(struct ovl_fs *ufs)
 static int ovl_show_options(struct seq_file *m, struct dentry *dentry)
 {
 	struct super_block *sb = dentry->d_sb;
-	struct ovl_fs *ufs = sb->s_fs_info;
+	struct ovl_fs *ofs = sb->s_fs_info;
 
-	seq_show_option(m, "lowerdir", ufs->config.lowerdir);
-	if (ufs->config.upperdir) {
-		seq_show_option(m, "upperdir", ufs->config.upperdir);
-		seq_show_option(m, "workdir", ufs->config.workdir);
+	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 (ufs->config.default_permissions)
+	if (ofs->config.default_permissions)
 		seq_puts(m, ",default_permissions");
-	if (ufs->config.redirect_dir != ovl_redirect_dir_def)
+	if (ofs->config.redirect_dir != ovl_redirect_dir_def)
 		seq_printf(m, ",redirect_dir=%s",
-			   ufs->config.redirect_dir ? "on" : "off");
-	if (ufs->config.index != ovl_index_def)
+			   ofs->config.redirect_dir ? "on" : "off");
+	if (ofs->config.index != ovl_index_def)
 		seq_printf(m, ",index=%s",
-			   ufs->config.index ? "on" : "off");
+			   ofs->config.index ? "on" : "off");
 	return 0;
 }
 
 static int ovl_remount(struct super_block *sb, int *flags, char *data)
 {
-	struct ovl_fs *ufs = sb->s_fs_info;
+	struct ovl_fs *ofs = sb->s_fs_info;
 
-	if (!(*flags & MS_RDONLY) && ovl_force_readonly(ufs))
+	if (!(*flags & MS_RDONLY) && ovl_force_readonly(ofs))
 		return -EROFS;
 
 	return 0;
@@ -451,13 +464,11 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config)
 #define OVL_WORKDIR_NAME "work"
 #define OVL_INDEXDIR_NAME "index"
 
-static struct dentry *ovl_workdir_create(struct super_block *sb,
-					 struct ovl_fs *ufs,
-					 struct dentry *dentry,
+static struct dentry *ovl_workdir_create(struct ovl_fs *ofs,
 					 const char *name, bool persist)
 {
-	struct inode *dir = dentry->d_inode;
-	struct vfsmount *mnt = ufs->upper_mnt;
+	struct inode *dir =  ofs->workbasedir->d_inode;
+	struct vfsmount *mnt = ofs->upper_mnt;
 	struct dentry *work;
 	int err;
 	bool retried = false;
@@ -471,7 +482,7 @@ static struct dentry *ovl_workdir_create(struct super_block *sb,
 	locked = true;
 
 retry:
-	work = lookup_one_len(name, dentry, strlen(name));
+	work = lookup_one_len(name, ofs->workbasedir, strlen(name));
 
 	if (!IS_ERR(work)) {
 		struct iattr attr = {
@@ -541,8 +552,7 @@ out_dput:
 	dput(work);
 out_err:
 	pr_warn("overlayfs: failed to create directory %s/%s (errno: %i); mounting read-only\n",
-		ufs->config.workdir, name, -err);
-	sb->s_flags |= MS_RDONLY;
+		ofs->config.workdir, name, -err);
 	work = NULL;
 	goto out_unlock;
 }
@@ -585,7 +595,7 @@ static int ovl_mount_dir_noesc(const char *name, struct path *path)
 	return 0;
 
 out_put:
-	path_put(path);
+	path_put_init(path);
 out:
 	return err;
 }
@@ -603,7 +613,7 @@ static int ovl_mount_dir(const char *name, struct path *path)
 			if (ovl_dentry_remote(path->dentry)) {
 				pr_err("overlayfs: filesystem on '%s' not supported as upperdir\n",
 				       tmp);
-				path_put(path);
+				path_put_init(path);
 				err = -EINVAL;
 			}
 		kfree(tmp);
@@ -655,7 +665,7 @@ static int ovl_lower_dir(const char *name, struct path *path,
 	return 0;
 
 out_put:
-	path_put(path);
+	path_put_init(path);
 out:
 	return err;
 }
@@ -826,129 +836,269 @@ static const struct xattr_handler *ovl_xattr_handlers[] = {
 	NULL
 };
 
-static int ovl_fill_super(struct super_block *sb, void *data, int silent)
+static int ovl_get_upper(struct ovl_fs *ofs, struct path *upperpath)
 {
-	struct path upperpath = { };
-	struct path workpath = { };
-	struct dentry *root_dentry;
-	struct ovl_entry *oe;
-	struct ovl_fs *ufs;
-	struct path *stack = NULL;
-	char *lowertmp;
-	char *lower;
-	unsigned int numlower;
-	unsigned int stacklen = 0;
-	unsigned int i;
-	bool remote = false;
-	struct cred *cred;
+	struct vfsmount *upper_mnt;
 	int err;
 
-	err = -ENOMEM;
-	ufs = kzalloc(sizeof(struct ovl_fs), GFP_KERNEL);
-	if (!ufs)
+	err = ovl_mount_dir(ofs->config.upperdir, upperpath);
+	if (err)
 		goto out;
 
-	ufs->config.redirect_dir = ovl_redirect_dir_def;
-	ufs->config.index = ovl_index_def;
-	err = ovl_parse_opt((char *) data, &ufs->config);
+	/* Upper fs should not be r/o */
+	if (sb_rdonly(upperpath->mnt->mnt_sb)) {
+		pr_err("overlayfs: upper fs is r/o, try multi-lower layers mount\n");
+		err = -EINVAL;
+		goto out;
+	}
+
+	err = ovl_check_namelen(upperpath, ofs, ofs->config.upperdir);
 	if (err)
-		goto out_free_config;
+		goto out;
+
+	err = -EBUSY;
+	if (ovl_inuse_trylock(upperpath->dentry)) {
+		ofs->upperdir_locked = true;
+	} else if (ofs->config.index) {
+		pr_err("overlayfs: upperdir is in-use by another mount, mount with '-o index=off' to override exclusive upperdir protection.\n");
+		goto out;
+	} else {