From 31747eda41ef3c30c09c5c096b380bf54013746a Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Sun, 14 Jan 2018 18:35:40 +0200
Subject: ovl: hash directory inodes for fsnotify

fsnotify pins a watched directory inode in cache, but if directory dentry
is released, new lookup will allocate a new dentry and a new inode.
Directory events will be notified on the new inode, while fsnotify listener
is watching the old pinned inode.

Hash all directory inodes to reuse the pinned inode on lookup. Pure upper
dirs are hashes by real upper inode, merge and lower dirs are hashed by
real lower inode.

The reference to lower inode was being held by the lower dentry object
in the overlay dentry (oe->lowerstack[0]). Releasing the overlay dentry
may drop lower inode refcount to zero. Add a refcount on behalf of the
overlay inode to prevent that.

As a by-product, hashing directory inodes also detects multiple
redirected dirs to the same lower dir and uncovered redirected dir
target on and returns -ESTALE on lookup.

The reported issue dates back to initial version of overlayfs, but this
patch depends on ovl_inode code that was introduced in kernel v4.13.

Cc: <stable@vger.kernel.org> #v4.13
Reported-by: Niklas Cassel <niklas.cassel@axis.com>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Tested-by: Niklas Cassel <niklas.cassel@axis.com>
---
 fs/overlayfs/inode.c | 39 ++++++++++++++++++++++++++++-----------
 fs/overlayfs/super.c |  1 +
 fs/overlayfs/util.c  |  4 ++--
 3 files changed, 31 insertions(+), 13 deletions(-)

(limited to 'fs')

diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 00b6b294272a..94d2f8a8b779 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -606,6 +606,16 @@ static int ovl_inode_set(struct inode *inode, void *data)
 static bool ovl_verify_inode(struct inode *inode, struct dentry *lowerdentry,
 			     struct dentry *upperdentry)
 {
+	if (S_ISDIR(inode->i_mode)) {
+		/* Real lower dir moved to upper layer under us? */
+		if (!lowerdentry && ovl_inode_lower(inode))
+			return false;
+
+		/* Lookup of an uncovered redirect origin? */
+		if (!upperdentry && ovl_inode_upper(inode))
+			return false;
+	}
+
 	/*
 	 * Allow non-NULL lower inode in ovl_inode even if lowerdentry is NULL.
 	 * This happens when finding a copied up overlay inode for a renamed
@@ -633,6 +643,8 @@ struct inode *ovl_get_inode(struct dentry *dentry, struct dentry *upperdentry,
 	struct inode *inode;
 	/* Already indexed or could be indexed on copy up? */
 	bool indexed = (index || (ovl_indexdir(dentry->d_sb) && !upperdentry));
+	struct dentry *origin = indexed ? lowerdentry : NULL;
+	bool is_dir;
 
 	if (WARN_ON(upperdentry && indexed && !lowerdentry))
 		return ERR_PTR(-EIO);
@@ -641,15 +653,19 @@ struct inode *ovl_get_inode(struct dentry *dentry, struct dentry *upperdentry,
 		realinode = d_inode(lowerdentry);
 
 	/*
-	 * Copy up origin (lower) may exist for non-indexed upper, but we must
-	 * not use lower as hash key in that case.
-	 * Hash inodes that are or could be indexed by origin inode and
-	 * non-indexed upper inodes that could be hard linked by upper inode.
+	 * Copy up origin (lower) may exist for non-indexed non-dir upper, but
+	 * we must not use lower as hash key in that case.
+	 * Hash non-dir that is or could be indexed by origin inode.
+	 * Hash dir that is or could be merged by origin inode.
+	 * Hash pure upper and non-indexed non-dir by upper inode.
 	 */
-	if (!S_ISDIR(realinode->i_mode) && (upperdentry || indexed)) {
-		struct inode *key = d_inode(indexed ? lowerdentry :
-						      upperdentry);
-		unsigned int nlink;
+	is_dir = S_ISDIR(realinode->i_mode);
+	if (is_dir)
+		origin = lowerdentry;
+
+	if (upperdentry || origin) {
+		struct inode *key = d_inode(origin ?: upperdentry);
+		unsigned int nlink = is_dir ? 1 : realinode->i_nlink;
 
 		inode = iget5_locked(dentry->d_sb, (unsigned long) key,
 				     ovl_inode_test, ovl_inode_set, key);
@@ -670,8 +686,9 @@ struct inode *ovl_get_inode(struct dentry *dentry, struct dentry *upperdentry,
 			goto out;
 		}
 
-		nlink = ovl_get_nlink(lowerdentry, upperdentry,
-				      realinode->i_nlink);
+		/* Recalculate nlink for non-dir due to indexing */
+		if (!is_dir)
+			nlink = ovl_get_nlink(lowerdentry, upperdentry, nlink);
 		set_nlink(inode, nlink);
 	} else {
 		inode = new_inode(dentry->d_sb);
@@ -685,7 +702,7 @@ struct inode *ovl_get_inode(struct dentry *dentry, struct dentry *upperdentry,
 		ovl_set_flag(OVL_IMPURE, inode);
 
 	/* Check for non-merge dir that may have whiteouts */
-	if (S_ISDIR(realinode->i_mode)) {
+	if (is_dir) {
 		struct ovl_entry *oe = dentry->d_fsdata;
 
 		if (((upperdentry && lowerdentry) || oe->numlower > 1) ||
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 76440feb79f6..1a436fa92a04 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -211,6 +211,7 @@ static void ovl_destroy_inode(struct inode *inode)
 	struct ovl_inode *oi = OVL_I(inode);
 
 	dput(oi->__upperdentry);
+	iput(oi->lower);
 	kfree(oi->redirect);
 	ovl_dir_cache_free(inode);
 	mutex_destroy(&oi->lock);
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index d6bb1c9f5e7a..06119f34a69d 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -257,7 +257,7 @@ void ovl_inode_init(struct inode *inode, struct dentry *upperdentry,
 	if (upperdentry)
 		OVL_I(inode)->__upperdentry = upperdentry;
 	if (lowerdentry)
-		OVL_I(inode)->lower = d_inode(lowerdentry);
+		OVL_I(inode)->lower = igrab(d_inode(lowerdentry));
 
 	ovl_copyattr(d_inode(upperdentry ?: lowerdentry), inode);
 }
@@ -273,7 +273,7 @@ void ovl_inode_update(struct inode *inode, struct dentry *upperdentry)
 	 */
 	smp_wmb();
 	OVL_I(inode)->__upperdentry = upperdentry;
-	if (!S_ISDIR(upperinode->i_mode) && inode_unhashed(inode)) {
+	if (inode_unhashed(inode)) {
 		inode->i_private = upperinode;
 		__insert_inode_hash(inode, (unsigned long) upperinode);
 	}
-- 
cgit v1.2.3


From d796e77f1dd541fe34481af2eee6454688d13982 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 8 Nov 2017 09:39:46 +0200
Subject: ovl: fix failure to fsync lower dir
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As a writable mount, it is not expected for overlayfs to return
EINVAL/EROFS for fsync, even if dir/file is not changed.

This commit fixes the case of fsync of directory, which is easier to
address, because overlayfs already implements fsync file operation for
directories.

The problem reported by Raphael is that new PostgreSQL 10.0 with a
database in overlayfs where lower layer in squashfs fails to start.
The failure is due to fsync error, when PostgreSQL does fsync on all
existing db directories on startup and a specific directory exists
lower layer with no changes.

Reported-by: Raphael Hertzog <raphael@ouaza.com>
Cc: <stable@vger.kernel.org> # v3.18
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Tested-by: Raphaël Hertzog <hertzog@debian.org>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/overlayfs/readdir.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 8c98578d27a1..a7e45e6cd732 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -769,10 +769,14 @@ static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end,
 	struct dentry *dentry = file->f_path.dentry;
 	struct file *realfile = od->realfile;
 
+	/* Nothing to sync for lower */
+	if (!OVL_TYPE_UPPER(ovl_path_type(dentry)))
+		return 0;
+
 	/*
 	 * Need to check if we started out being a lower dir, but got copied up
 	 */
-	if (!od->is_upper && OVL_TYPE_UPPER(ovl_path_type(dentry))) {
+	if (!od->is_upper) {
 		struct inode *inode = file_inode(file);
 
 		realfile = READ_ONCE(od->upperfile);
-- 
cgit v1.2.3


From 6d0a8a90a5bbfd6befcb512fad6618608e8c0e86 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Fri, 10 Nov 2017 13:18:07 +0200
Subject: ovl: take lower dir inode mutex outside upper sb_writers lock

The functions ovl_lower_positive() and ovl_check_empty_dir() both take
inode mutex on the real lower dir under ovl_want_write() which takes
the upper_mnt sb_writers lock.

While this is not a clear locking order or layering violation, it creates
an undesired lock dependency between two unrelated layers for no good
reason.

This lock dependency materializes to a false(?) positive lockdep warning
when calling rmdir() on a nested overlayfs, where both nested and
underlying overlayfs both use the same fs type as upper layer.

rmdir() on the nested overlayfs creates the lock chain:
  sb_writers of upper_mnt (e.g. tmpfs) in ovl_do_remove()
  ovl_i_mutex_dir_key[] of lower overlay dir in ovl_lower_positive()

rmdir() on the underlying overlayfs creates the lock chain in
reverse order:
  ovl_i_mutex_dir_key[] of lower overlay dir in vfs_rmdir()
  sb_writers of nested upper_mnt (e.g. tmpfs) in ovl_do_remove()

To rid of the unneeded locking dependency, move both ovl_lower_positive()
and ovl_check_empty_dir() to before ovl_want_write() in rmdir() and
rename() implementation.

This change spreads the pieces of ovl_check_empty_and_clear() directly
inside the rmdir()/rename() implementations so the helper is no longer
needed and removed.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/overlayfs/dir.c     | 117 ++++++++++++++++++++++---------------------------
 fs/overlayfs/namei.c   |   3 ++
 fs/overlayfs/readdir.c |   3 ++
 3 files changed, 58 insertions(+), 65 deletions(-)

(limited to 'fs')

diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index f9788bc116a8..a1a7606d4891 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -181,11 +181,6 @@ 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)
 {
@@ -301,37 +296,6 @@ out:
 	return ERR_PTR(err);
 }
 
-static struct dentry *ovl_check_empty_and_clear(struct dentry *dentry)
-{
-	int err;
-	struct dentry *ret = NULL;
-	LIST_HEAD(list);
-
-	err = ovl_check_empty_dir(dentry, &list);
-	if (err) {
-		ret = ERR_PTR(err);
-		goto out_free;
-	}
-
-	/*
-	 * When removing an empty opaque directory, then it makes no sense to
-	 * replace it with an exact replica of itself.
-	 *
-	 * 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 (!list_empty(&list))
-		ret = ovl_clear_empty(dentry, &list);
-
-out_free:
-	ovl_cache_free(&list);
-
-	return ret;
-}
-
 static int ovl_set_upper_acl(struct dentry *upperdentry, const char *name,
 			     const struct posix_acl *acl)
 {
@@ -623,7 +587,8 @@ static bool ovl_matches_upper(struct dentry *dentry, struct dentry *upper)
 	return d_inode(ovl_dentry_upper(dentry)) == d_inode(upper);
 }
 
-static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir)
+static int ovl_remove_and_whiteout(struct dentry *dentry,
+				   struct list_head *list)
 {
 	struct dentry *workdir = ovl_workdir(dentry);
 	struct inode *wdir = workdir->d_inode;
@@ -638,8 +603,8 @@ static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir)
 	if (WARN_ON(!workdir))
 		return -EROFS;
 
-	if (is_dir) {
-		opaquedir = ovl_check_empty_and_clear(dentry);
+	if (!list_empty(list)) {
+		opaquedir = ovl_clear_empty(dentry, list);
 		err = PTR_ERR(opaquedir);
 		if (IS_ERR(opaquedir))
 			goto out;
@@ -694,7 +659,8 @@ kill_whiteout:
 	goto out_d_drop;
 }
 
-static int ovl_remove_upper(struct dentry *dentry, bool is_dir)
+static int ovl_remove_upper(struct dentry *dentry, bool is_dir,
+			    struct list_head *list)
 {
 	struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
 	struct inode *dir = upperdir->d_inode;
@@ -702,10 +668,8 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir)
 	struct dentry *opaquedir = NULL;
 	int err;
 
-	/* 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);
+	if (!list_empty(list)) {
+		opaquedir = ovl_clear_empty(dentry, list);
 		err = PTR_ERR(opaquedir);
 		if (IS_ERR(opaquedir))
 			goto out;
@@ -746,11 +710,26 @@ out:
 	return err;
 }
 
+static bool ovl_pure_upper(struct dentry *dentry)
+{
+	return !ovl_dentry_lower(dentry) &&
+	       !ovl_test_flag(OVL_WHITEOUTS, d_inode(dentry));
+}
+
 static int ovl_do_remove(struct dentry *dentry, bool is_dir)
 {
 	int err;
 	bool locked = false;
 	const struct cred *old_cred;
+	bool lower_positive = ovl_lower_positive(dentry);
+	LIST_HEAD(list);
+
+	/* No need to clean pure upper removed by vfs_rmdir() */
+	if (is_dir && (lower_positive || !ovl_pure_upper(dentry))) {
+		err = ovl_check_empty_dir(dentry, &list);
+		if (err)
+			goto out;
+	}
 
 	err = ovl_want_write(dentry);
 	if (err)
@@ -765,10 +744,10 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir)
 		goto out_drop_write;
 
 	old_cred = ovl_override_creds(dentry->d_sb);
-	if (!ovl_lower_positive(dentry))
-		err = ovl_remove_upper(dentry, is_dir);
+	if (!lower_positive)
+		err = ovl_remove_upper(dentry, is_dir, &list);
 	else
-		err = ovl_remove_and_whiteout(dentry, is_dir);
+		err = ovl_remove_and_whiteout(dentry, &list);
 	revert_creds(old_cred);
 	if (!err) {
 		if (is_dir)
@@ -780,6 +759,7 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir)
 out_drop_write:
 	ovl_drop_write(dentry);
 out:
+	ovl_cache_free(&list);
 	return err;
 }
 
@@ -915,6 +895,7 @@ static int ovl_rename(struct inode *olddir, struct dentry *old,
 	bool samedir = olddir == newdir;
 	struct dentry *opaquedir = NULL;
 	const struct cred *old_cred = NULL;
+	LIST_HEAD(list);
 
 	err = -EINVAL;
 	if (flags & ~(RENAME_EXCHANGE | RENAME_NOREPLACE))
@@ -929,6 +910,27 @@ static int ovl_rename(struct inode *olddir, struct dentry *old,
 	if (!overwrite && !ovl_can_move(new))
 		goto out;
 
+	if (overwrite && new_is_dir && !ovl_pure_upper(new)) {
+		err = ovl_check_empty_dir(new, &list);
+		if (err)
+			goto out;
+	}
+
+	if (overwrite) {
+		if (ovl_lower_positive(old)) {
+			if (!ovl_dentry_is_whiteout(new)) {
+				/* Whiteout source */
+				flags |= RENAME_WHITEOUT;
+			} else {
+				/* Switch whiteouts */
+				flags |= RENAME_EXCHANGE;
+			}
+		} else if (is_dir && ovl_dentry_is_whiteout(new)) {
+			flags |= RENAME_EXCHANGE;
+			cleanup_whiteout = true;
+		}
+	}
+
 	err = ovl_want_write(old);
 	if (err)
 		goto out;
@@ -952,9 +954,8 @@ 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) ||
-					ovl_may_have_whiteouts(new))) {
-		opaquedir = ovl_check_empty_and_clear(new);
+	if (!list_empty(&list)) {
+		opaquedir = ovl_clear_empty(new, &list);
 		err = PTR_ERR(opaquedir);
 		if (IS_ERR(opaquedir)) {
 			opaquedir = NULL;
@@ -962,21 +963,6 @@ static int ovl_rename(struct inode *olddir, struct dentry *old,
 		}
 	}
 
-	if (overwrite) {
-		if (ovl_lower_positive(old)) {
-			if (!ovl_dentry_is_whiteout(new)) {
-				/* Whiteout source */
-				flags |= RENAME_WHITEOUT;
-			} else {
-				/* Switch whiteouts */
-				flags |= RENAME_EXCHANGE;
-			}
-		} else if (is_dir && ovl_dentry_is_whiteout(new)) {
-			flags |= RENAME_EXCHANGE;
-			cleanup_whiteout = true;
-		}
-	}
-
 	old_upperdir = ovl_dentry_upper(old->d_parent);
 	new_upperdir = ovl_dentry_upper(new->d_parent);
 
@@ -1094,6 +1080,7 @@ out_drop_write:
 	ovl_drop_write(old);
 out:
 	dput(opaquedir);
+	ovl_cache_free(&list);
 	return err;
 }
 
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index beb945e1963c..926248e1de04 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -774,6 +774,7 @@ bool ovl_lower_positive(struct dentry *dentry)
 	struct ovl_entry *oe = dentry->d_fsdata;
 	struct ovl_entry *poe = dentry->d_parent->d_fsdata;
 	const struct qstr *name = &dentry->d_name;
+	const struct cred *old_cred;
 	unsigned int i;
 	bool positive = false;
 	bool done = false;
@@ -789,6 +790,7 @@ bool ovl_lower_positive(struct dentry *dentry)
 	if (!ovl_dentry_upper(dentry))
 		return true;
 
+	old_cred = ovl_override_creds(dentry->d_sb);
 	/* Positive upper -> have to look up lower to see whether it exists */
 	for (i = 0; !done && !positive && i < poe->numlower; i++) {
 		struct dentry *this;
@@ -818,6 +820,7 @@ bool ovl_lower_positive(struct dentry *dentry)
 			dput(this);
 		}
 	}
+	revert_creds(old_cred);
 
 	return positive;
 }
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index a7e45e6cd732..7dfe381c2cd8 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -862,8 +862,11 @@ int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list)
 	int err;
 	struct ovl_cache_entry *p, *n;
 	struct rb_root root = RB_ROOT;
+	const struct cred *old_cred;
 
+	old_cred = ovl_override_creds(dentry->d_sb);
 	err = ovl_dir_read_merged(dentry, list, &root);
+	revert_creds(old_cred);
 	if (err)
 		return err;
 
-- 
cgit v1.2.3


From f81678173ce25a1c7e1570a328dfba50b5d872eb Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Mon, 18 Dec 2017 14:25:56 +0200
Subject: ovl: fix another overlay: warning prefix

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/overlayfs/namei.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index 926248e1de04..69a43ede0a2a 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -693,7 +693,8 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 		 */
 		err = -EPERM;
 		if (d.redirect && !ofs->config.redirect_follow) {
-			pr_warn_ratelimited("overlay: refusing to follow redirect for (%pd2)\n", dentry);
+			pr_warn_ratelimited("overlayfs: refusing to follow redirect for (%pd2)\n",
+					    dentry);
 			goto out_put;
 		}
 
-- 
cgit v1.2.3


From 2ba9d57e65044859f7ff133bcb0a902769bf3bc6 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 3 Jan 2018 18:54:41 +0200
Subject: ovl: take mnt_want_write() for work/index dir setup

There are several write operations on upper fs not covered by
mnt_want_write():

- test set/remove OPAQUE xattr
- test create O_TMPFILE
- set ORIGIN xattr in ovl_verify_origin()
- cleanup of index entries in ovl_indexdir_cleanup()

Some of these go way back, but this patch only applies over the
v4.14 re-factoring of ovl_fill_super().

Cc: <stable@vger.kernel.org> #v4.14
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/overlayfs/super.c | 25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)

(limited to 'fs')

diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 1a436fa92a04..3387e6d639a5 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -521,10 +521,6 @@ static struct dentry *ovl_workdir_create(struct ovl_fs *ofs,
 	bool retried = false;
 	bool locked = false;
 
-	err = mnt_want_write(mnt);
-	if (err)
-		goto out_err;
-
 	inode_lock_nested(dir, I_MUTEX_PARENT);
 	locked = true;
 
@@ -589,7 +585,6 @@ retry:
 		goto out_err;
 	}
 out_unlock:
-	mnt_drop_write(mnt);
 	if (locked)
 		inode_unlock(dir);
 
@@ -930,12 +925,17 @@ out:
 
 static int ovl_make_workdir(struct ovl_fs *ofs, struct path *workpath)
 {
+	struct vfsmount *mnt = ofs->upper_mnt;
 	struct dentry *temp;
 	int err;
 
+	err = mnt_want_write(mnt);
+	if (err)
+		return err;
+
 	ofs->workdir = ovl_workdir_create(ofs, OVL_WORKDIR_NAME, false);
 	if (!ofs->workdir)
-		return 0;
+		goto out;
 
 	/*
 	 * Upper should support d_type, else whiteouts are visible.  Given
@@ -945,7 +945,7 @@ static int ovl_make_workdir(struct ovl_fs *ofs, struct path *workpath)
 	 */
 	err = ovl_check_d_type_supported(workpath);
 	if (err < 0)
-		return err;
+		goto out;
 
 	/*
 	 * We allowed this configuration and don't want to break users over
@@ -969,6 +969,7 @@ static int ovl_make_workdir(struct ovl_fs *ofs, struct path *workpath)
 	if (err) {
 		ofs->noxattr = true;
 		pr_warn("overlayfs: upper fs does not support xattr.\n");
+		err = 0;
 	} else {
 		vfs_removexattr(ofs->workdir, OVL_XATTR_OPAQUE);
 	}
@@ -980,7 +981,9 @@ static int ovl_make_workdir(struct ovl_fs *ofs, struct path *workpath)
 		pr_warn("overlayfs: upper fs does not support file handles, falling back to index=off.\n");
 	}
 
-	return 0;
+out:
+	mnt_drop_write(mnt);
+	return err;
 }
 
 static int ovl_get_workdir(struct ovl_fs *ofs, struct path *upperpath)
@@ -1027,8 +1030,13 @@ out:
 static int ovl_get_indexdir(struct ovl_fs *ofs, struct ovl_entry *oe,
 			    struct path *upperpath)
 {
+	struct vfsmount *mnt = ofs->upper_mnt;
 	int err;
 
+	err = mnt_want_write(mnt);
+	if (err)
+		return err;
+
 	/* Verify lower root is upper root origin */
 	err = ovl_verify_origin(upperpath->dentry, oe->lowerstack[0].dentry,
 				false, true);
@@ -1056,6 +1064,7 @@ static int ovl_get_indexdir(struct ovl_fs *ofs, struct ovl_entry *oe,
 		pr_warn("overlayfs: try deleting index dir or mounting with '-o index=off' to disable inodes index.\n");
 
 out:
+	mnt_drop_write(mnt);
 	return err;
 }
 
-- 
cgit v1.2.3


From a5a927a7c82e28ea76599dee4019c41e372c911f Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 3 Jan 2018 18:54:42 +0200
Subject: ovl: take mnt_want_write() for removing impure xattr

The optimization in ovl_cache_get_impure() that tries to remove an
unneeded "impure" xattr needs to take mnt_want_write() on upper fs.

Fixes: 4edb83bb1041 ("ovl: constant d_ino for non-merge dirs")
Cc: <stable@vger.kernel.org> #v4.14
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/overlayfs/readdir.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

(limited to 'fs')

diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 7dfe381c2cd8..1a8c39887992 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -593,8 +593,15 @@ static struct ovl_dir_cache *ovl_cache_get_impure(struct path *path)
 		return ERR_PTR(res);
 	}
 	if (list_empty(&cache->entries)) {
-		/* Good oportunity to get rid of an unnecessary "impure" flag */
-		ovl_do_removexattr(ovl_dentry_upper(dentry), OVL_XATTR_IMPURE);
+		/*
+		 * A good opportunity to get rid of an unneeded "impure" flag.
+		 * Removing the "impure" xattr is best effort.
+		 */
+		if (!ovl_want_write(dentry)) {
+			ovl_do_removexattr(ovl_dentry_upper(dentry),
+					   OVL_XATTR_IMPURE);
+			ovl_drop_write(dentry);
+		}
 		ovl_clear_flag(OVL_IMPURE, d_inode(dentry));
 		kfree(cache);
 		return NULL;
-- 
cgit v1.2.3


From 9678e630305724487f1fc101d6b83c383ff9cc90 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 3 Jan 2018 19:34:45 +0200
Subject: ovl: fix inconsistent d_ino for legacy merge dir

For a merge dir that was copied up before v4.12 or that was hand crafted
offline (e.g. mkdir {upper/lower}/dir), upper dir does not contain the
'trusted.overlay.origin' xattr.  In that case, stat(2) on the merge dir
returns the lower dir st_ino, but getdents(2) returns the upper dir d_ino.

After this change, on merge dir lookup, missing origin xattr on upper
dir will be fixed and 'impure' xattr will be fixed on parent of the legacy
merge dir.

Suggested-by: zhangyi (F) <yi.zhang@huawei.com>
Reviewed-by: zhangyi (F) <yi.zhang@huawei.com>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/overlayfs/copy_up.c   |  4 ++--
 fs/overlayfs/namei.c     | 33 +++++++++++++++++++++++++++++++++
 fs/overlayfs/overlayfs.h |  2 ++
 3 files changed, 37 insertions(+), 2 deletions(-)

(limited to 'fs')

diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index eb3b8d39fb61..206ececd5ae7 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -288,8 +288,8 @@ out:
 	return fh;
 }
 
-static int ovl_set_origin(struct dentry *dentry, struct dentry *lower,
-			  struct dentry *upper)
+int ovl_set_origin(struct dentry *dentry, struct dentry *lower,
+		   struct dentry *upper)
 {
 	const struct ovl_fh *fh = NULL;
 	int err;
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index 69a43ede0a2a..69f4f19659fc 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -584,6 +584,27 @@ static int ovl_find_layer(struct ovl_fs *ofs, struct ovl_path *path)
 	return i;
 }
 
+/* Fix missing 'origin' xattr */
+static int ovl_fix_origin(struct dentry *dentry, struct dentry *lower,
+			  struct dentry *upper)
+{
+	int err;
+
+	if (ovl_check_origin_xattr(upper))
+		return 0;
+
+	err = ovl_want_write(dentry);
+	if (err)
+		return err;
+
+	err = ovl_set_origin(dentry, lower, upper);
+	if (!err)
+		err = ovl_set_impure(dentry->d_parent, upper->d_parent);
+
+	ovl_drop_write(dentry);
+	return err;
+}
+
 struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 			  unsigned int flags)
 {
@@ -674,6 +695,18 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 		if (!this)
 			continue;
 
+		/*
+		 * If no origin fh is stored in upper of a merge dir, store fh
+		 * of lower dir and set upper parent "impure".
+		 */
+		if (upperdentry && !ctr && !ofs->noxattr) {
+			err = ovl_fix_origin(dentry, this, upperdentry);
+			if (err) {
+				dput(this);
+				goto out_put;
+			}
+		}
+
 		stack[ctr].dentry = this;
 		stack[ctr].layer = lower.layer;
 		ctr++;
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index b489099ccd49..d1cfa69c98b5 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -322,3 +322,5 @@ int ovl_copy_up_flags(struct dentry *dentry, int flags);
 int ovl_copy_xattr(struct dentry *old, struct dentry *new);
 int ovl_set_attr(struct dentry *upper, struct kstat *stat);
 struct ovl_fh *ovl_encode_fh(struct dentry *lower, bool is_upper);
+int ovl_set_origin(struct dentry *dentry, struct dentry *lower,
+		   struct dentry *upper);
-- 
cgit v1.2.3


From a683737ba924cd2985f6e7350520f449915ff8f9 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Tue, 19 Sep 2017 12:14:18 +0300
Subject: ovl: disable index when no xattr support

Overlayfs falls back to index=off if lower/upper fs does not support
file handles. Do the same if upper fs does not support xattr.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/overlayfs/super.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 3387e6d639a5..f3281f0b2388 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -968,7 +968,8 @@ static int ovl_make_workdir(struct ovl_fs *ofs, struct path *workpath)
 	err = ovl_do_setxattr(ofs->workdir, OVL_XATTR_OPAQUE, "0", 1, 0);
 	if (err) {
 		ofs->noxattr = true;
-		pr_warn("overlayfs: upper fs does not support xattr.\n");
+		ofs->config.index = false;
+		pr_warn("overlayfs: upper fs does not support xattr, falling back to index=off.\n");
 		err = 0;
 	} else {
 		vfs_removexattr(ofs->workdir, OVL_XATTR_OPAQUE);
-- 
cgit v1.2.3


From 972d0093c2f7b1bd57e47a1780a552dde528fd16 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Tue, 19 Sep 2017 12:14:18 +0300
Subject: ovl: force r/o mount when index dir creation fails

When work dir creation fails, a warning is emitted and overlay is
mounted r/o. Trying to remount r/w will fail with no work dir.

When index dir creation fails, the same warning is emitted and overlay
is mounted r/o, but trying to remount r/w will succeed. This may cause
unintentional corruption of filesystem consistency.

Adjust the behavior of index dir creation failure to that of work dir
creation failure and do not allow to remount r/w. User needs to state
an explicitly intention to work without an index by mounting with
option 'index=off' to allow r/w mount with no index dir.

When mounting with option 'index=on' and no 'upperdir', index is
implicitly disabled, so do not warn about no file handle support.

The issue was introduced with inodes index feature in v4.13, but this
patch will not apply cleanly before ovl_fill_super() re-factoring in
v4.15.

Fixes: 02bcd1577400 ("ovl: introduce the inodes index dir feature")
Cc: <stable@vger.kernel.org> #v4.13
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/overlayfs/super.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

(limited to 'fs')

diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index f3281f0b2388..9aa5d32af427 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -699,7 +699,8 @@ 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)) {
+	if (ofs->config.index && ofs->config.upperdir &&
+	    !ovl_can_decode_fh(path->dentry->d_sb)) {
 		ofs->config.index = false;
 		pr_warn("overlayfs: fs on '%s' does not support file handles, falling back to index=off.\n", name);
 	}
@@ -1268,11 +1269,16 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 		if (err)
 			goto out_free_oe;
 
-		if (!ofs->indexdir)
+		/* Force r/o mount with no index dir */
+		if (!ofs->indexdir) {
+			dput(ofs->workdir);
+			ofs->workdir = NULL;
 			sb->s_flags |= SB_RDONLY;
+		}
+
 	}
 
-	/* Show index=off/on in /proc/mounts for any of the reasons above */
+	/* Show index=off in /proc/mounts for forced r/o mount */
 	if (!ofs->indexdir)
 		ofs->config.index = false;
 
-- 
cgit v1.2.3


From d583ed7d138825fd9469d5419e23230ad39173e8 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 8 Nov 2017 19:23:36 +0200
Subject: ovl: store layer index in ovl_layer

Store the fs root layer index inside ovl_layer struct, so we can
get the root fs layer index from merge dir lower layer instead of
find it with ovl_find_layer() helper.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/overlayfs/namei.c     | 17 +----------------
 fs/overlayfs/ovl_entry.h |  2 ++
 fs/overlayfs/super.c     |  1 +
 3 files changed, 4 insertions(+), 16 deletions(-)

(limited to 'fs')

diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index 69f4f19659fc..a38db76cbccd 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -572,18 +572,6 @@ int ovl_path_next(int idx, struct dentry *dentry, struct path *path)
 	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;
-}
-
 /* Fix missing 'origin' xattr */
 static int ovl_fix_origin(struct dentry *dentry, struct dentry *lower,
 			  struct dentry *upper)
@@ -733,11 +721,8 @@ 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 */
-			i = ovl_find_layer(ofs, &lower);
-			if (WARN_ON(i == ofs->numlower))
-				break;
+			i = lower.layer->idx - 1;
 		}
 	}
 
diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
index 9d0bc03bf6e4..608e48755070 100644
--- a/fs/overlayfs/ovl_entry.h
+++ b/fs/overlayfs/ovl_entry.h
@@ -22,6 +22,8 @@ struct ovl_config {
 struct ovl_layer {
 	struct vfsmount *mnt;
 	dev_t pseudo_dev;
+	/* Index of this layer in fs root (upper == 0) */
+	int idx;
 };
 
 struct ovl_path {
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 9aa5d32af427..b34a002ab4b5 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1106,6 +1106,7 @@ static int ovl_get_lower_layers(struct ovl_fs *ofs, struct path *stack,
 
 		ofs->lower_layers[ofs->numlower].mnt = mnt;
 		ofs->lower_layers[ofs->numlower].pseudo_dev = dev;
+		ofs->lower_layers[ofs->numlower].idx = i + 1;
 		ofs->numlower++;
 
 		/* Check if all lower layers are on same sb */
-- 
cgit v1.2.3


From 2e1a532883cf77f01031bef4b83d864a46c1bed0 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Tue, 24 Oct 2017 15:12:15 +0300
Subject: ovl: factor out ovl_check_origin_fh()

Re-factor ovl_check_origin() and ovl_get_origin(), so origin fh xattr is
read from upper inode only once during lookup with multiple lower layers
and only once when verifying index entry origin.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/overlayfs/namei.c | 142 +++++++++++++++++++++++++++++++++------------------
 1 file changed, 92 insertions(+), 50 deletions(-)

(limited to 'fs')

diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index a38db76cbccd..a6b9bd2afca1 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -87,9 +87,36 @@ static int ovl_acceptable(void *ctx, struct dentry *dentry)
 	return 1;
 }
 
+/*
+ * Check validity of an overlay file handle buffer.
+ *
+ * Return 0 for a valid file handle.
+ * Return -ENODATA for "origin unknown".
+ * Return <0 for an invalid file handle.
+ */
+static int ovl_check_fh_len(struct ovl_fh *fh, int fh_len)
+{
+	if (fh_len < sizeof(struct ovl_fh) || fh_len < fh->len)
+		return -EINVAL;
+
+	if (fh->magic != OVL_FH_MAGIC)
+		return -EINVAL;
+
+	/* Treat larger version and unknown flags as "origin unknown" */
+	if (fh->version > OVL_FH_VERSION || fh->flags & ~OVL_FH_FLAG_ALL)
+		return -ENODATA;
+
+	/* Treat endianness mismatch as "origin unknown" */
+	if (!(fh->flags & OVL_FH_FLAG_ANY_ENDIAN) &&
+	    (fh->flags & OVL_FH_FLAG_BIG_ENDIAN) != OVL_FH_FLAG_CPU_ENDIAN)
+		return -ENODATA;
+
+	return 0;
+}
+
 static struct ovl_fh *ovl_get_origin_fh(struct dentry *dentry)
 {
-	int res;
+	int res, err;
 	struct ovl_fh *fh = NULL;
 
 	res = vfs_getxattr(dentry, OVL_XATTR_ORIGIN, NULL, 0);
@@ -102,7 +129,7 @@ static struct ovl_fh *ovl_get_origin_fh(struct dentry *dentry)
 	if (res == 0)
 		return NULL;
 
-	fh  = kzalloc(res, GFP_KERNEL);
+	fh = kzalloc(res, GFP_KERNEL);
 	if (!fh)
 		return ERR_PTR(-ENOMEM);
 
@@ -110,20 +137,12 @@ static struct ovl_fh *ovl_get_origin_fh(struct dentry *dentry)
 	if (res < 0)
 		goto fail;
 
-	if (res < sizeof(struct ovl_fh) || res < fh->len)
-		goto invalid;
-
-	if (fh->magic != OVL_FH_MAGIC)
+	err = ovl_check_fh_len(fh, res);
+	if (err < 0) {
+		if (err == -ENODATA)
+			goto out;
 		goto invalid;
-
-	/* Treat larger version and unknown flags as "origin unknown" */
-	if (fh->version > OVL_FH_VERSION || fh->flags & ~OVL_FH_FLAG_ALL)
-		goto out;
-
-	/* Treat endianness mismatch as "origin unknown" */
-	if (!(fh->flags & OVL_FH_FLAG_ANY_ENDIAN) &&
-	    (fh->flags & OVL_FH_FLAG_BIG_ENDIAN) != OVL_FH_FLAG_CPU_ENDIAN)
-		goto out;
+	}
 
 	return fh;
 
@@ -139,22 +158,17 @@ invalid:
 	goto out;
 }
 
-static struct dentry *ovl_get_origin(struct dentry *dentry,
-				     struct vfsmount *mnt)
+static struct dentry *ovl_decode_fh(struct ovl_fh *fh, struct vfsmount *mnt)
 {
-	struct dentry *origin = NULL;
-	struct ovl_fh *fh = ovl_get_origin_fh(dentry);
+	struct dentry *origin;
 	int bytes;
 
-	if (IS_ERR_OR_NULL(fh))
-		return (struct dentry *)fh;
-
 	/*
 	 * Make sure that the stored uuid matches the uuid of the lower
 	 * layer where file handle will be decoded.
 	 */
 	if (!uuid_equal(&fh->uuid, &mnt->mnt_sb->s_uuid))
-		goto out;
+		return NULL;
 
 	bytes = (fh->len - offsetof(struct ovl_fh, fid));
 	origin = exportfs_decode_fh(mnt, (struct fid *)fh->fid,
@@ -164,22 +178,15 @@ static struct dentry *ovl_get_origin(struct dentry *dentry,
 		/* Treat stale file handle as "origin unknown" */
 		if (origin == ERR_PTR(-ESTALE))
 			origin = NULL;
-		goto out;
+		return origin;
 	}
 
-	if (ovl_dentry_weird(origin) ||
-	    ((d_inode(origin)->i_mode ^ d_inode(dentry)->i_mode) & S_IFMT))
-		goto invalid;
+	if (ovl_dentry_weird(origin)) {
+		dput(origin);
+		return NULL;
+	}
 
-out:
-	kfree(fh);
 	return origin;
-
-invalid:
-	pr_warn_ratelimited("overlayfs: invalid origin (%pd2)\n", origin);
-	dput(origin);
-	origin = NULL;
-	goto out;
 }
 
 static bool ovl_is_opaquedir(struct dentry *dentry)
@@ -284,9 +291,9 @@ static int ovl_lookup_layer(struct dentry *base, struct ovl_lookup_data *d,
 }
 
 
-static int ovl_check_origin(struct dentry *upperdentry,
-			    struct ovl_path *lower, unsigned int numlower,
-			    struct ovl_path **stackp, unsigned int *ctrp)
+static int ovl_check_origin_fh(struct ovl_fh *fh, struct dentry *upperdentry,
+			       struct ovl_path *lower, unsigned int numlower,
+			       struct ovl_path **stackp)
 {
 	struct vfsmount *mnt;
 	struct dentry *origin = NULL;
@@ -294,18 +301,20 @@ static int ovl_check_origin(struct dentry *upperdentry,
 
 	for (i = 0; i < numlower; i++) {
 		mnt = lower[i].layer->mnt;
-		origin = ovl_get_origin(upperdentry, mnt);
-		if (IS_ERR(origin))
-			return PTR_ERR(origin);
-
+		origin = ovl_decode_fh(fh, mnt);
 		if (origin)
 			break;
 	}
 
 	if (!origin)
-		return 0;
+		return -ESTALE;
+	else if (IS_ERR(origin))
+		return PTR_ERR(origin);
+
+	if (!ovl_is_whiteout(upperdentry) &&
+	    ((d_inode(origin)->i_mode ^ d_inode(upperdentry)->i_mode) & S_IFMT))
+		goto invalid;
 
-	BUG_ON(*ctrp);
 	if (!*stackp)
 		*stackp = kmalloc(sizeof(struct ovl_path), GFP_KERNEL);
 	if (!*stackp) {
@@ -313,9 +322,41 @@ static int ovl_check_origin(struct dentry *upperdentry,
 		return -ENOMEM;
 	}
 	**stackp = (struct ovl_path){.dentry = origin, .layer = lower[i].layer};
-	*ctrp = 1;
 
 	return 0;
+
+invalid:
+	pr_warn_ratelimited("overlayfs: invalid origin (%pd2, ftype=%x, origin ftype=%x).\n",
+			    upperdentry, d_inode(upperdentry)->i_mode & S_IFMT,
+			    d_inode(origin)->i_mode & S_IFMT);
+	dput(origin);
+	return -EIO;
+}
+
+static int ovl_check_origin(struct dentry *upperdentry,
+			    struct ovl_path *lower, unsigned int numlower,
+			    struct ovl_path **stackp, unsigned int *ctrp)
+{
+	struct ovl_fh *fh = ovl_get_origin_fh(upperdentry);
+	int err;
+
+	if (IS_ERR_OR_NULL(fh))
+		return PTR_ERR(fh);
+
+	err = ovl_check_origin_fh(fh, upperdentry, lower, numlower, stackp);
+	kfree(fh);
+
+	if (err) {
+		if (err == -ESTALE)
+			return 0;
+		return err;
+	}
+
+	if (WARN_ON(*ctrp))
+		return -EIO;
+
+	*ctrp = 1;
+	return 0;
 }
 
 /*
@@ -389,7 +430,6 @@ int ovl_verify_index(struct dentry *index, struct ovl_path *lower,
 	size_t len;
 	struct ovl_path origin = { };
 	struct ovl_path *stack = &origin;
-	unsigned int ctr = 0;
 	int err;
 
 	if (!d_inode(index))
@@ -420,16 +460,18 @@ int ovl_verify_index(struct dentry *index, struct ovl_path *lower,
 		goto fail;
 
 	err = -EINVAL;
-	if (hex2bin((u8 *)fh, index->d_name.name, len) || len != fh->len)
+	if (hex2bin((u8 *)fh, index->d_name.name, len))
+		goto fail;
+
+	err = ovl_check_fh_len(fh, len);
+	if (err)
 		goto fail;
 
 	err = ovl_verify_origin_fh(index, fh);
 	if (err)
 		goto fail;
 
-	err = ovl_check_origin(index, lower, numlower, &stack, &ctr);
-	if (!err && !ctr)
-		err = -ESTALE;
+	err = ovl_check_origin_fh(fh, index, lower, numlower, &stack);
 	if (err)
 		goto fail;
 
-- 
cgit v1.2.3


From 1eff1a1deec727bacead79ec64554c1df190f43c Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Tue, 12 Dec 2017 22:40:46 +0200
Subject: ovl: simplify arguments to ovl_check_origin_fh()

Pass the fs instance with lower_layers array instead of the dentry
lowerstack array to ovl_check_origin_fh(), because the dentry members
of lowerstack play no role in this helper.

This change simplifies the argument list of ovl_check_origin(),
ovl_cleanup_index() and ovl_verify_index().

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/overlayfs/namei.c     | 28 +++++++++++++---------------
 fs/overlayfs/overlayfs.h |  9 ++++-----
 fs/overlayfs/readdir.c   | 12 ++++++------
 fs/overlayfs/super.c     |  5 +----
 4 files changed, 24 insertions(+), 30 deletions(-)

(limited to 'fs')

diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index a6b9bd2afca1..27f25a61f6e4 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -291,17 +291,15 @@ static int ovl_lookup_layer(struct dentry *base, struct ovl_lookup_data *d,
 }
 
 
-static int ovl_check_origin_fh(struct ovl_fh *fh, struct dentry *upperdentry,
-			       struct ovl_path *lower, unsigned int numlower,
+static int ovl_check_origin_fh(struct ovl_fs *ofs, struct ovl_fh *fh,
+			       struct dentry *upperdentry,
 			       struct ovl_path **stackp)
 {
-	struct vfsmount *mnt;
 	struct dentry *origin = NULL;
 	int i;
 
-	for (i = 0; i < numlower; i++) {
-		mnt = lower[i].layer->mnt;
-		origin = ovl_decode_fh(fh, mnt);
+	for (i = 0; i < ofs->numlower; i++) {
+		origin = ovl_decode_fh(fh, ofs->lower_layers[i].mnt);
 		if (origin)
 			break;
 	}
@@ -321,7 +319,10 @@ static int ovl_check_origin_fh(struct ovl_fh *fh, struct dentry *upperdentry,
 		dput(origin);
 		return -ENOMEM;
 	}
-	**stackp = (struct ovl_path){.dentry = origin, .layer = lower[i].layer};
+	**stackp = (struct ovl_path){
+		.dentry = origin,
+		.layer = &ofs->lower_layers[i]
+	};
 
 	return 0;
 
@@ -333,8 +334,7 @@ invalid:
 	return -EIO;
 }
 
-static int ovl_check_origin(struct dentry *upperdentry,
-			    struct ovl_path *lower, unsigned int numlower,
+static int ovl_check_origin(struct ovl_fs *ofs, struct dentry *upperdentry,
 			    struct ovl_path **stackp, unsigned int *ctrp)
 {
 	struct ovl_fh *fh = ovl_get_origin_fh(upperdentry);
@@ -343,7 +343,7 @@ static int ovl_check_origin(struct dentry *upperdentry,
 	if (IS_ERR_OR_NULL(fh))
 		return PTR_ERR(fh);
 
-	err = ovl_check_origin_fh(fh, upperdentry, lower, numlower, stackp);
+	err = ovl_check_origin_fh(ofs, fh, upperdentry, stackp);
 	kfree(fh);
 
 	if (err) {
@@ -423,8 +423,7 @@ 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 ovl_path *lower,
-		     unsigned int numlower)
+int ovl_verify_index(struct ovl_fs *ofs, struct dentry *index)
 {
 	struct ovl_fh *fh = NULL;
 	size_t len;
@@ -471,7 +470,7 @@ int ovl_verify_index(struct dentry *index, struct ovl_path *lower,
 	if (err)
 		goto fail;
 
-	err = ovl_check_origin_fh(fh, index, lower, numlower, &stack);
+	err = ovl_check_origin_fh(ofs, fh, index, &stack);
 	if (err)
 		goto fail;
 
@@ -689,8 +688,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 			 * number - it's the same as if we held a reference
 			 * to a dentry in lower layer that was moved under us.
 			 */
-			err = ovl_check_origin(upperdentry, roe->lowerstack,
-					       roe->numlower, &stack, &ctr);
+			err = ovl_check_origin(ofs, upperdentry, &stack, &ctr);
 			if (err)
 				goto out_put_upper;
 		}
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index d1cfa69c98b5..d55afb6646b0 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -251,11 +251,11 @@ static inline bool ovl_is_impuredir(struct dentry *dentry)
 /* namei.c */
 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_verify_index(struct ovl_fs *ofs, struct dentry *index);
 int ovl_get_index_name(struct dentry *origin, struct qstr *name);
 int ovl_path_next(int idx, struct dentry *dentry, struct path *path);
-struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags);
+struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
+			  unsigned int flags);
 bool ovl_lower_positive(struct dentry *dentry);
 
 /* readdir.c */
@@ -267,8 +267,7 @@ void ovl_dir_cache_free(struct inode *inode);
 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 ovl_path *lower, unsigned int numlower);
+int ovl_indexdir_cleanup(struct ovl_fs *ofs);
 
 /* inode.c */
 int ovl_set_nlink_upper(struct dentry *dentry);
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 1a8c39887992..4c660c7085b7 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -1030,13 +1030,13 @@ void ovl_workdir_cleanup(struct inode *dir, struct vfsmount *mnt,
 	}
 }
 
-int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt,
-			 struct ovl_path *lower, unsigned int numlower)
+int ovl_indexdir_cleanup(struct ovl_fs *ofs)
 {
 	int err;
+	struct dentry *indexdir = ofs->indexdir;
 	struct dentry *index = NULL;
-	struct inode *dir = dentry->d_inode;
-	struct path path = { .mnt = mnt, .dentry = dentry };
+	struct inode *dir = indexdir->d_inode;
+	struct path path = { .mnt = ofs->upper_mnt, .dentry = indexdir };
 	LIST_HEAD(list);
 	struct rb_root root = RB_ROOT;
 	struct ovl_cache_entry *p;
@@ -1060,13 +1060,13 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt,
 			if (p->len == 2 && p->name[1] == '.')
 				continue;
 		}
-		index = lookup_one_len(p->name, dentry, p->len);
+		index = lookup_one_len(p->name, indexdir, p->len);
 		if (IS_ERR(index)) {
 			err = PTR_ERR(index);
 			index = NULL;
 			break;
 		}
-		err = ovl_verify_index(index, lower, numlower);
+		err = ovl_verify_index(ofs, index);
 		/* 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 b34a002ab4b5..4345c3f83fde 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1057,10 +1057,7 @@ static int ovl_get_indexdir(struct ovl_fs *ofs, struct ovl_entry *oe,
 
 		/* Cleanup bad/stale/orphan index entries */
 		if (!err)
-			err = ovl_indexdir_cleanup(ofs->indexdir,
-						   ofs->upper_mnt,
-						   oe->lowerstack,
-						   oe->numlower);
+			err = ovl_indexdir_cleanup(ofs);
 	}
 	if (err || !ofs->indexdir)
 		pr_warn("overlayfs: try deleting index dir or mounting with '-o index=off' to disable inodes index.\n");
-- 
cgit v1.2.3


From 051224438af21047b34160b1e0ad1c5af45fdace Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Thu, 11 Jan 2018 08:25:32 +0200
Subject: ovl: generalize ovl_verify_origin() and helpers

Remove the "origin" language from the functions that handle set, get
and verify of "origin" xattr and pass the xattr name as an argument.

The same helpers are going to be used for NFS export to get, get and
verify the "upper" xattr for directory index entries.

ovl_verify_origin() is now a helper used only to verify non upper
file handle stored in "origin" xattr of upper inode.

The upper root dir file handle is still stored in "origin" xattr on
the index dir for backward compatibility. This is going to be changed
by the patch that adds directory index entries support.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/overlayfs/copy_up.c   |  6 +++---
 fs/overlayfs/namei.c     | 42 ++++++++++++++++++++++--------------------
 fs/overlayfs/overlayfs.h | 12 +++++++++---
 fs/overlayfs/super.c     |  8 ++++----
 4 files changed, 38 insertions(+), 30 deletions(-)

(limited to 'fs')

diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 206ececd5ae7..503c92404095 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -232,13 +232,13 @@ int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat)
 	return err;
 }
 
-struct ovl_fh *ovl_encode_fh(struct dentry *lower, bool is_upper)
+struct ovl_fh *ovl_encode_fh(struct dentry *real, bool is_upper)
 {
 	struct ovl_fh *fh;
 	int fh_type, fh_len, dwords;
 	void *buf;
 	int buflen = MAX_HANDLE_SZ;
-	uuid_t *uuid = &lower->d_sb->s_uuid;
+	uuid_t *uuid = &real->d_sb->s_uuid;
 
 	buf = kmalloc(buflen, GFP_KERNEL);
 	if (!buf)
@@ -250,7 +250,7 @@ struct ovl_fh *ovl_encode_fh(struct dentry *lower, bool is_upper)
 	 * the price or reconnecting the dentry.
 	 */
 	dwords = buflen >> 2;
-	fh_type = exportfs_encode_fh(lower, buf, &dwords, 0);
+	fh_type = exportfs_encode_fh(real, buf, &dwords, 0);
 	buflen = (dwords << 2);
 
 	fh = ERR_PTR(-EIO);
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index 27f25a61f6e4..11e164cb2593 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -114,12 +114,12 @@ static int ovl_check_fh_len(struct ovl_fh *fh, int fh_len)
 	return 0;
 }
 
-static struct ovl_fh *ovl_get_origin_fh(struct dentry *dentry)
+static struct ovl_fh *ovl_get_fh(struct dentry *dentry, const char *name)
 {
 	int res, err;
 	struct ovl_fh *fh = NULL;
 
-	res = vfs_getxattr(dentry, OVL_XATTR_ORIGIN, NULL, 0);
+	res = vfs_getxattr(dentry, name, NULL, 0);
 	if (res < 0) {
 		if (res == -ENODATA || res == -EOPNOTSUPP)
 			return NULL;
@@ -133,7 +133,7 @@ static struct ovl_fh *ovl_get_origin_fh(struct dentry *dentry)
 	if (!fh)
 		return ERR_PTR(-ENOMEM);
 
-	res = vfs_getxattr(dentry, OVL_XATTR_ORIGIN, fh, res);
+	res = vfs_getxattr(dentry, name, fh, res);
 	if (res < 0)
 		goto fail;
 
@@ -337,7 +337,7 @@ invalid:
 static int ovl_check_origin(struct ovl_fs *ofs, struct dentry *upperdentry,
 			    struct ovl_path **stackp, unsigned int *ctrp)
 {
-	struct ovl_fh *fh = ovl_get_origin_fh(upperdentry);
+	struct ovl_fh *fh = ovl_get_fh(upperdentry, OVL_XATTR_ORIGIN);
 	int err;
 
 	if (IS_ERR_OR_NULL(fh))
@@ -360,12 +360,13 @@ static int ovl_check_origin(struct ovl_fs *ofs, struct dentry *upperdentry,
 }
 
 /*
- * Verify that @fh matches the origin file handle stored in OVL_XATTR_ORIGIN.
+ * Verify that @fh matches the file handle stored in xattr @name.
  * Return 0 on match, -ESTALE on mismatch, < 0 on error.
  */
-static int ovl_verify_origin_fh(struct dentry *dentry, const struct ovl_fh *fh)
+static int ovl_verify_fh(struct dentry *dentry, const char *name,
+			 const struct ovl_fh *fh)
 {
-	struct ovl_fh *ofh = ovl_get_origin_fh(dentry);
+	struct ovl_fh *ofh = ovl_get_fh(dentry, name);
 	int err = 0;
 
 	if (!ofh)
@@ -382,28 +383,28 @@ static int ovl_verify_origin_fh(struct dentry *dentry, const struct ovl_fh *fh)
 }
 
 /*
- * Verify that an inode matches the origin file handle stored in upper inode.
+ * Verify that @real dentry matches the file handle stored in xattr @name.
  *
- * If @set is true and there is no stored file handle, encode and store origin
- * file handle in OVL_XATTR_ORIGIN.
+ * If @set is true and there is no stored file handle, encode @real and store
+ * file handle in xattr @name.
  *
- * Return 0 on match, -ESTALE on mismatch, < 0 on error.
+ * Return 0 on match, -ESTALE on mismatch, -ENODATA on no xattr, < 0 on error.
  */
-int ovl_verify_origin(struct dentry *dentry, struct dentry *origin,
-		      bool is_upper, bool set)
+int ovl_verify_set_fh(struct dentry *dentry, const char *name,
+		      struct dentry *real, bool is_upper, bool set)
 {
 	struct inode *inode;
 	struct ovl_fh *fh;
 	int err;
 
-	fh = ovl_encode_fh(origin, is_upper);
+	fh = ovl_encode_fh(real, is_upper);
 	err = PTR_ERR(fh);
 	if (IS_ERR(fh))
 		goto fail;
 
-	err = ovl_verify_origin_fh(dentry, fh);
+	err = ovl_verify_fh(dentry, name, fh);
 	if (set && err == -ENODATA)
-		err = ovl_do_setxattr(dentry, OVL_XATTR_ORIGIN, fh, fh->len, 0);
+		err = ovl_do_setxattr(dentry, name, fh, fh->len, 0);
 	if (err)
 		goto fail;
 
@@ -412,9 +413,10 @@ out:
 	return err;
 
 fail:
-	inode = d_inode(origin);
-	pr_warn_ratelimited("overlayfs: failed to verify origin (%pd2, ino=%lu, err=%i)\n",
-			    origin, inode ? inode->i_ino : 0, err);
+	inode = d_inode(real);
+	pr_warn_ratelimited("overlayfs: failed to verify %s (%pd2, ino=%lu, err=%i)\n",
+			    is_upper ? "upper" : "origin", real,
+			    inode ? inode->i_ino : 0, err);
 	goto out;
 }
 
@@ -466,7 +468,7 @@ int ovl_verify_index(struct ovl_fs *ofs, struct dentry *index)
 	if (err)
 		goto fail;
 
-	err = ovl_verify_origin_fh(index, fh);
+	err = ovl_verify_fh(index, OVL_XATTR_ORIGIN, fh);
 	if (err)
 		goto fail;
 
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index d55afb6646b0..1d62b1e6111a 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -249,8 +249,8 @@ static inline bool ovl_is_impuredir(struct dentry *dentry)
 
 
 /* namei.c */
-int ovl_verify_origin(struct dentry *dentry, struct dentry *origin,
-		      bool is_upper, bool set);
+int ovl_verify_set_fh(struct dentry *dentry, const char *name,
+		      struct dentry *real, bool is_upper, bool set);
 int ovl_verify_index(struct ovl_fs *ofs, struct dentry *index);
 int ovl_get_index_name(struct dentry *origin, struct qstr *name);
 int ovl_path_next(int idx, struct dentry *dentry, struct path *path);
@@ -258,6 +258,12 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 			  unsigned int flags);
 bool ovl_lower_positive(struct dentry *dentry);
 
+static inline int ovl_verify_origin(struct dentry *upper,
+				    struct dentry *origin, bool set)
+{
+	return ovl_verify_set_fh(upper, OVL_XATTR_ORIGIN, origin, false, set);
+}
+
 /* readdir.c */
 extern const struct file_operations ovl_dir_operations;
 int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list);
@@ -320,6 +326,6 @@ int ovl_copy_up(struct dentry *dentry);
 int ovl_copy_up_flags(struct dentry *dentry, int flags);
 int ovl_copy_xattr(struct dentry *old, struct dentry *new);
 int ovl_set_attr(struct dentry *upper, struct kstat *stat);
-struct ovl_fh *ovl_encode_fh(struct dentry *lower, bool is_upper);
+struct ovl_fh *ovl_encode_fh(struct dentry *real, bool is_upper);
 int ovl_set_origin(struct dentry *dentry, struct dentry *lower,
 		   struct dentry *upper);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 4345c3f83fde..4ebbb368fce8 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1041,7 +1041,7 @@ static int ovl_get_indexdir(struct ovl_fs *ofs, struct ovl_entry *oe,
 
 	/* Verify lower root is upper root origin */
 	err = ovl_verify_origin(upperpath->dentry, oe->lowerstack[0].dentry,
-				false, true);
+				true);
 	if (err) {
 		pr_err("overlayfs: failed to verify upper root origin\n");
 		goto out;
@@ -1049,9 +1049,9 @@ static int ovl_get_indexdir(struct ovl_fs *ofs, struct ovl_entry *oe,
 
 	ofs->indexdir = ovl_workdir_create(ofs, OVL_INDEXDIR_NAME, true);
 	if (ofs->indexdir) {
-		/* Verify upper root is index dir origin */
-		err = ovl_verify_origin(ofs->indexdir, upperpath->dentry,
-					true, true);
+		/* Verify upper root is exclusively associated with index dir */
+		err = ovl_verify_set_fh(ofs->indexdir, OVL_XATTR_ORIGIN,
+					upperpath->dentry, true, true);
 		if (err)
 			pr_err("overlayfs: failed to verify index dir origin\n");
 
-- 
cgit v1.2.3


From 60b866420ba7ae0b6a8d338f49be21c601d19064 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 10 Jan 2018 23:15:21 +0200
Subject: ovl: update documentation of inodes index feature

Document that inode index feature solves breaking hard links on
copy up.

Simplify Kconfig backward compatibility disclaimer.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/overlayfs/Kconfig | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

(limited to 'fs')

diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig
index 5ac415466861..9eac01c3e21e 100644
--- a/fs/overlayfs/Kconfig
+++ b/fs/overlayfs/Kconfig
@@ -47,9 +47,6 @@ config OVERLAY_FS_INDEX
 	  The inodes index feature prevents breaking of lower hardlinks on copy
 	  up.
 
-	  Note, that the inodes index feature is read-only backward compatible.
-	  That is, mounting an overlay which has an index dir on a kernel that
-	  doesn't support this feature read-only, will not have any negative
-	  outcomes.  However, mounting the same overlay with an old kernel
-	  read-write and then mounting it again with a new kernel, will have
-	  unexpected results.
+	  Note, that the inodes index feature is not backward compatible.
+	  That is, mounting an overlay which has an inodes index on a kernel
+	  that doesn't support this feature will have unexpected results.
-- 
cgit v1.2.3


From f168f1098dd9038daaf9f7be5f81cdea4985886a Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Fri, 19 Jan 2018 11:26:53 +0200
Subject: ovl: add support for "nfs_export" configuration

Introduce the "nfs_export" config, module and mount options.

The NFS export feature depends on the "index" feature and enables two
implicit overlayfs features: "index_all" and "verify_lower".
The "index_all" feature creates an index on copy up of every file and
directory. The "verify_lower" feature uses the full index to detect
overlay filesystems inconsistencies on lookup, like redirect from
multiple upper dirs to the same lower dir.

NFS export can be enabled for non-upper mount with no index. However,
because lower layer redirects cannot be verified with the index, enabling
NFS export support on an overlay with no upper layer requires turning off
redirect follow (e.g. "redirect_dir=nofollow").

The full index may incur some overhead on mount time, especially when
verifying that lower directory file handles are not stale.

NFS export support, full index and consistency verification will be
implemented by following patches.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/overlayfs/Kconfig     | 22 ++++++++++++++++++++++
 fs/overlayfs/overlayfs.h |  2 ++
 fs/overlayfs/ovl_entry.h |  1 +
 fs/overlayfs/super.c     | 49 +++++++++++++++++++++++++++++++++++++++++++-----
 fs/overlayfs/util.c      | 16 ++++++++++++++++
 5 files changed, 85 insertions(+), 5 deletions(-)

(limited to 'fs')

diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig
index 9eac01c3e21e..406e72de88f6 100644
--- a/fs/overlayfs/Kconfig
+++ b/fs/overlayfs/Kconfig
@@ -50,3 +50,25 @@ config OVERLAY_FS_INDEX
 	  Note, that the inodes index feature is not backward compatible.
 	  That is, mounting an overlay which has an inodes index on a kernel
 	  that doesn't support this feature will have unexpected results.
+
+config OVERLAY_FS_NFS_EXPORT
+	bool "Overlayfs: turn on NFS export feature by default"
+	depends on OVERLAY_FS
+	depends on OVERLAY_FS_INDEX
+	help
+	  If this config option is enabled then overlay filesystems will use
+	  the inodes index dir to decode overlay NFS file handles by default.
+	  In this case, it is still possible to turn off NFS export support
+	  globally with the "nfs_export=off" module option or on a filesystem
+	  instance basis with the "nfs_export=off" mount option.
+
+	  The NFS export feature creates an index on copy up of every file and
+	  directory.  This full index is used to detect overlay filesystems
+	  inconsistencies on lookup, like redirect from multiple upper dirs to
+	  the same lower dir.  The full index may incur some overhead on mount
+	  time, especially when verifying that directory file handles are not
+	  stale.
+
+	  Note, that the NFS export feature is not backward compatible.
+	  That is, mounting an overlay which has a full index on a kernel
+	  that doesn't support this feature will have unexpected results.
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 1d62b1e6111a..db75955f9677 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -194,6 +194,8 @@ 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);
 struct dentry *ovl_indexdir(struct super_block *sb);
+bool ovl_index_all(struct super_block *sb);
+bool ovl_verify_lower(struct super_block *sb);
 struct ovl_entry *ovl_alloc_entry(unsigned int numlower);
 bool ovl_dentry_remote(struct dentry *dentry);
 bool ovl_dentry_weird(struct dentry *dentry);
diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
index 608e48755070..6dd60fcf8cb7 100644
--- a/fs/overlayfs/ovl_entry.h
+++ b/fs/overlayfs/ovl_entry.h
@@ -17,6 +17,7 @@ struct ovl_config {
 	bool redirect_follow;
 	const char *redirect_mode;
 	bool index;
+	bool nfs_export;
 };
 
 struct ovl_layer {
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 4ebbb368fce8..1d538be87fa0 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -45,6 +45,11 @@ 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 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(ovl_nfs_export_def,
+		 "Default to on or off for the NFS export feature");
+
 static void ovl_entry_stack_free(struct ovl_entry *oe)
 {
 	unsigned int i;
@@ -342,6 +347,9 @@ static int ovl_show_options(struct seq_file *m, struct dentry *dentry)
 		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.nfs_export != ovl_nfs_export_def)
+		seq_printf(m, ",nfs_export=%s", ofs->config.nfs_export ?
+						"on" : "off");
 	return 0;
 }
 
@@ -374,6 +382,8 @@ enum {
 	OPT_REDIRECT_DIR,
 	OPT_INDEX_ON,
 	OPT_INDEX_OFF,
+	OPT_NFS_EXPORT_ON,
+	OPT_NFS_EXPORT_OFF,
 	OPT_ERR,
 };
 
@@ -385,6 +395,8 @@ static const match_table_t ovl_tokens = {
 	{OPT_REDIRECT_DIR,		"redirect_dir=%s"},
 	{OPT_INDEX_ON,			"index=on"},
 	{OPT_INDEX_OFF,			"index=off"},
+	{OPT_NFS_EXPORT_ON,		"nfs_export=on"},
+	{OPT_NFS_EXPORT_OFF,		"nfs_export=off"},
 	{OPT_ERR,			NULL}
 };
 
@@ -491,6 +503,14 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config)
 			config->index = false;
 			break;
 
+		case OPT_NFS_EXPORT_ON:
+			config->nfs_export = true;
+			break;
+
+		case OPT_NFS_EXPORT_OFF:
+			config->nfs_export = false;
+			break;
+
 		default:
 			pr_err("overlayfs: unrecognized mount option \"%s\" or missing value\n", p);
 			return -EINVAL;
@@ -696,13 +716,16 @@ static int ovl_lower_dir(const char *name, struct path *path,
 		*remote = true;
 
 	/*
-	 * The inodes index feature needs to encode and decode file
-	 * handles, so it requires that all layers support them.
+	 * The inodes index feature and NFS export need to encode and decode
+	 * file handles, so they require that all layers support them.
 	 */
-	if (ofs->config.index && ofs->config.upperdir &&
+	if ((ofs->config.nfs_export ||
+	     (ofs->config.index && ofs->config.upperdir)) &&
 	    !ovl_can_decode_fh(path->dentry->d_sb)) {
 		ofs->config.index = false;
-		pr_warn("overlayfs: fs on '%s' does not support file handles, falling back to index=off.\n", name);
+		ofs->config.nfs_export = false;
+		pr_warn("overlayfs: fs on '%s' does not support file handles, falling back to index=off,nfs_export=off.\n",
+			name);
 	}
 
 	return 0;
@@ -983,6 +1006,12 @@ static int ovl_make_workdir(struct ovl_fs *ofs, struct path *workpath)
 		pr_warn("overlayfs: upper fs does not support file handles, falling back to index=off.\n");
 	}
 
+	/* NFS export of r/w mount depends on index */
+	if (ofs->config.nfs_export && !ofs->config.index) {
+		pr_warn("overlayfs: NFS export requires \"index=on\", falling back to nfs_export=off.\n");
+		ofs->config.nfs_export = false;
+	}
+
 out:
 	mnt_drop_write(mnt);
 	return err;
@@ -1141,6 +1170,10 @@ static struct ovl_entry *ovl_get_lowerstack(struct super_block *sb,
 	} else if (!ofs->config.upperdir && stacklen == 1) {
 		pr_err("overlayfs: at least 2 lowerdir are needed while upperdir nonexistent\n");
 		goto out_err;
+	} else if (!ofs->config.upperdir && ofs->config.nfs_export &&
+		   ofs->config.redirect_follow) {
+		pr_warn("overlayfs: NFS export requires \"redirect_dir=nofollow\" on non-upper mount, falling back to nfs_export=off.\n");
+		ofs->config.nfs_export = false;
 	}
 
 	err = -ENOMEM;
@@ -1217,6 +1250,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 		goto out_err;
 
 	ofs->config.index = ovl_index_def;
+	ofs->config.nfs_export = ovl_nfs_export_def;
 	err = ovl_parse_opt((char *) data, &ofs->config);
 	if (err)
 		goto out_err;
@@ -1277,8 +1311,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 	/* Show index=off in /proc/mounts for forced r/o mount */
-	if (!ofs->indexdir)
+	if (!ofs->indexdi