[GIT PULL -mm] 0/4 Unionfs updates/fixes/cleanups

[GIT PULL -mm] 0/4 Unionfs updates/fixes/cleanups

[Erez Zadok]

The following is a series of patchsets related to Unionfs.  This is the
fifth set of patchsets resulting from an lkml review of the entire unionfs
code base, in preparation for a merge into mainline.  The most significant
changes here are a few locking related fixes, and a correction to broken
logic which didn't allow writing to the first available writable branch.

These patches were tested (where appropriate) on 2.6.24, MM, as well as the
backports to 2.6.{23,22,21,20,19,18,9} on ext2/3/4, xfs, reiserfs, nfs2/3/4,
jffs2, ramfs, tmpfs, cramfs, and squashfs (where available).  Also tested
with LTP-full and with a continuous parallel kernel compile (while forcing
cache flushing, manipulating lower branches, etc.).  See
http://unionfs.filesystems.org/ to download back-ported unionfs code.

Please pull from the 'master' branch of
git://git.kernel.org/pub/scm/linux/kernel/git/ezk/unionfs.git

to receive the following:

Erez Zadok (4):
      Unionfs: use first writable branch (fix/cleanup)
      Unionfs: remove unnecessary call to d_iput
      Unionfs: d_parent related locking fixes
      Unionfs: lock_rename related locking fixes

 copyup.c |   16 --
 inode.c  |  395 ++++++++++++++++++++++++---------------------------------------
 rename.c |   16 ++
 union.h  |    4 
 4 files changed, 174 insertions(+), 257 deletions(-)

---
Erez Zadok
ezk@cs.sunysb.edu

[PATCH 1/4] Unionfs: use first writable branch (fix/cleanup)

[Erez Zadok]

Cleanup code in ->create, ->symlink, and ->mknod: refactor common code into
helper functions.  Also, this allows writing to multiple branches again,
which was broken by an earlier patch.

Signed-off-by: Erez Zadok <ezk@cs.sunysb.edu>
---
 fs/unionfs/inode.c |  395 +++++++++++++++++++++-------------------------------
 1 files changed, 156 insertions(+), 239 deletions(-)

diff --git a/fs/unionfs/inode.c b/fs/unionfs/inode.c
index e15ddb9..0b92da2 100644
--- a/fs/unionfs/inode.c
+++ b/fs/unionfs/inode.c
@@ -18,14 +18,159 @@
 
 #include "union.h"
 
+/*
+ * Helper function when creating new objects (create, symlink, and mknod).
+ * Checks to see if there's a whiteout in @lower_dentry's parent directory,
+ * whose name is taken from @dentry.  Then tries to remove that whiteout, if
+ * found.
+ *
+ * Return 0 if no whiteout was found, or if one was found and successfully
+ * removed (a zero tells the caller that @lower_dentry belongs to a good
+ * branch to create the new object in).  Return -ERRNO if an error occurred
+ * during whiteout lookup or in trying to unlink the whiteout.
+ */
+static int check_for_whiteout(struct dentry *dentry,
+			      struct dentry *lower_dentry)
+{
+	int err = 0;
+	struct dentry *wh_dentry = NULL;
+	struct dentry *lower_dir_dentry;
+	char *name = NULL;
+
+	/*
+	 * check if whiteout exists in this branch, i.e. lookup .wh.foo
+	 * first.
+	 */
+	name = alloc_whname(dentry->d_name.name, dentry->d_name.len);
+	if (unlikely(IS_ERR(name))) {
+		err = PTR_ERR(name);
+		goto out;
+	}
+
+	wh_dentry = lookup_one_len(name, lower_dentry->d_parent,
+				   dentry->d_name.len + UNIONFS_WHLEN);
+	if (IS_ERR(wh_dentry)) {
+		err = PTR_ERR(wh_dentry);
+		wh_dentry = NULL;
+		goto out;
+	}
+
+	if (!wh_dentry->d_inode) /* no whiteout exists */
+		goto out;
+
+	/* .wh.foo has been found, so let's unlink it */
+	lower_dir_dentry = lock_parent_wh(wh_dentry);
+	/* see Documentation/filesystems/unionfs/issues.txt */
+	lockdep_off();
+	err = vfs_unlink(lower_dir_dentry->d_inode, wh_dentry);
+	lockdep_on();
+	unlock_dir(lower_dir_dentry);
+
+	/*
+	 * Whiteouts are special files and should be deleted no matter what
+	 * (as if they never existed), in order to allow this create
+	 * operation to succeed.  This is especially important in sticky
+	 * directories: a whiteout may have been created by one user, but
+	 * the newly created file may be created by another user.
+	 * Therefore, in order to maintain Unix semantics, if the vfs_unlink
+	 * above failed, then we have to try to directly unlink the
+	 * whiteout.  Note: in the ODF version of unionfs, whiteout are
+	 * handled much more cleanly.
+	 */
+	if (err == -EPERM) {
+		struct inode *inode = lower_dir_dentry->d_inode;
+		err = inode->i_op->unlink(inode, wh_dentry);
+	}
+	if (err)
+		printk(KERN_ERR "unionfs: could not "
+		       "unlink whiteout, err = %d\n", err);
+
+out:
+	dput(wh_dentry);
+	kfree(name);
+	return err;
+}
+
+/*
+ * Find a writeable branch to create new object in.  Checks all writeble
+ * branches of the parent inode, from istart to iend order; if none are
+ * suitable, also tries branch 0 (which may require a copyup).
+ *
+ * Return a lower_dentry we can use to create object in, or ERR_PTR.
+ */
+static struct dentry *find_writeable_branch(struct inode *parent,
+					    struct dentry *dentry)
+{
+	int err = -EINVAL;
+	int bindex, istart, iend;
+	struct dentry *lower_dentry = NULL;
+
+	istart = ibstart(parent);
+	iend = ibend(parent);
+	if (istart < 0)
+		goto out;
+
+begin:
+	for (bindex = istart; bindex <= iend; bindex++) {
+		/* skip non-writeable branches */
+		err = is_robranch_super(dentry->d_sb, bindex);
+		if (err) {
+			err = -EROFS;
+			continue;
+		}
+		lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
+		if (!lower_dentry)
+			continue;
+		/*
+		 * check for whiteouts in writeable branch, and remove them
+		 * if necessary.
+		 */
+		err = check_for_whiteout(dentry, lower_dentry);
+		if (err)
+			continue;
+	}
+	/*
+	 * If istart wasn't already branch 0, and we got any error, then try
+	 * branch 0 (which may require copyup)
+	 */
+	if (err && istart > 0) {
+		istart = iend = 0;
+		goto begin;
+	}
+
+	/*
+	 * If we tried even branch 0, and still got an error, abort.  But if
+	 * the error was an EROFS, then we should try to copyup.
+	 */
+	if (err && err != -EROFS)
+		goto out;
+
+	/*
+	 * If we get here, then check if copyup needed.  If lower_dentry is
+	 * NULL, create the entire dentry directory structure in branch 0.
+	 */
+	if (!lower_dentry) {
+		bindex = 0;
+		lower_dentry = create_parents(parent, dentry,
+					      dentry->d_name.name, bindex);
+		if (IS_ERR(lower_dentry)) {
+			err = PTR_ERR(lower_dentry);
+			goto out;
+		}
+	}
+	err = 0;		/* all's well */
+out:
+	if (err)
+		return ERR_PTR(err);
+	return lower_dentry;
+}
+
 static int unionfs_create(struct inode *parent, struct dentry *dentry,
 			  int mode, struct nameidata *nd)
 {
 	int err = 0;
 	struct dentry *lower_dentry = NULL;
-	struct dentry *wh_dentry = NULL;
 	struct dentry *lower_parent_dentry = NULL;
-	char *name = NULL;
 	int valid = 0;
 	struct nameidata lower_nd;
 
@@ -46,89 +191,12 @@ static int unionfs_create(struct inode *parent, struct dentry *dentry,
 	 */
 	BUG_ON(!valid && dentry->d_inode);
 
-	/*
-	 * We shouldn't create things in a read-only branch; this check is a
-	 * bit redundant as we don't allow branch 0 to be read-only at the
-	 * moment
-	 */
-	err = is_robranch_super(dentry->d_sb, 0);
-	if (err) {
-		err = -EROFS;
+	lower_dentry = find_writeable_branch(parent, dentry);
+	if (IS_ERR(lower_dentry)) {
+		err = PTR_ERR(lower_dentry);
 		goto out;
 	}
 
-	/*
-	 * We _always_ create on branch 0
-	 */
-	lower_dentry = unionfs_lower_dentry_idx(dentry, 0);
-	if (lower_dentry) {
-		/*
-		 * check if whiteout exists in this branch, i.e. lookup .wh.foo
-		 * first.
-		 */
-		name = alloc_whname(dentry->d_name.name, dentry->d_name.len);
-		if (unlikely(IS_ERR(name))) {
-			err = PTR_ERR(name);
-			goto out;
-		}
-
-		wh_dentry = lookup_one_len(name, lower_dentry->d_parent,
-					   dentry->d_name.len + UNIONFS_WHLEN);
-		if (IS_ERR(wh_dentry)) {
-			err = PTR_ERR(wh_dentry);
-			wh_dentry = NULL;
-			goto out;
-		}
-
-		if (wh_dentry->d_inode) {
-			/*
-			 * .wh.foo has been found, so let's unlink it
-			 */
-			struct dentry *lower_dir_dentry;
-
-			lower_dir_dentry = lock_parent_wh(wh_dentry);
-			/* see Documentation/filesystems/unionfs/issues.txt */
-			lockdep_off();
-			err = vfs_unlink(lower_dir_dentry->d_inode, wh_dentry);
-			lockdep_on();
-			unlock_dir(lower_dir_dentry);
-
-			/*
-			 * Whiteouts are special files and should be deleted
-			 * no matter what (as if they never existed), in
-			 * order to allow this create operation to succeed.
-			 * This is especially important in sticky
-			 * directories: a whiteout may have been created by
-			 * one user, but the newly created file may be
-			 * created by another user.  Therefore, in order to
-			 * maintain Unix semantics, if the vfs_unlink above
-			 * ailed, then we have to try to directly unlink the
-			 * whiteout.  Note: in the ODF version of unionfs,
-			 * whiteout are handled much more cleanly.
-			 */
-			if (err == -EPERM) {
-				struct inode *inode = lower_dir_dentry->d_inode;
-				err = inode->i_op->unlink(inode, wh_dentry);
-			}
-			if (err) {
-				printk(KERN_ERR "unionfs: create: could not "
-				       "unlink whiteout, err = %d\n", err);
-				goto out;
-			}
-		}
-	} else {
-		/*
-		 * if lower_dentry is NULL, create the entire
-		 * dentry directory structure in branch 0.
-		 */
-		lower_dentry = create_parents(parent, dentry,
-					      dentry->d_name.name, 0);
-		if (IS_ERR(lower_dentry)) {
-			err = PTR_ERR(lower_dentry);
-			goto out;
-		}
-	}
-
 	lower_parent_dentry = lock_parent(lower_dentry);
 	if (IS_ERR(lower_parent_dentry)) {
 		err = PTR_ERR(lower_parent_dentry);
@@ -156,9 +224,6 @@ static int unionfs_create(struct inode *parent, struct dentry *dentry,
 	unlock_dir(lower_parent_dentry);
 
 out:
-	dput(wh_dentry);
-	kfree(name);
-
 	if (!err)
 		unionfs_postcopyup_setmnt(dentry);
 
@@ -417,86 +482,12 @@ static int unionfs_symlink(struct inode *parent, struct dentry *dentry,
 	 */
 	BUG_ON(!valid && dentry->d_inode);
 
-	/*
-	 * We shouldn't create things in a read-only branch; this check is a
-	 * bit redundant as we don't allow branch 0 to be read-only at the
-	 * moment
-	 */
-	err = is_robranch_super(dentry->d_sb, 0);
-	if (err) {
-		err = -EROFS;
+	lower_dentry = find_writeable_branch(parent, dentry);
+	if (IS_ERR(lower_dentry)) {
+		err = PTR_ERR(lower_dentry);
 		goto out;
 	}
 
-	/*
-	 * We _always_ create on branch 0
-	 */
-	lower_dentry = unionfs_lower_dentry_idx(dentry, 0);
-	if (lower_dentry) {
-		/*
-		 * check if whiteout exists in this branch, i.e. lookup .wh.foo
-		 * first.
-		 */
-		name = alloc_whname(dentry->d_name.name, dentry->d_name.len);
-		if (unlikely(IS_ERR(name))) {
-			err = PTR_ERR(name);
-			goto out;
-		}
-
-		wh_dentry = lookup_one_len(name, lower_dentry->d_parent,
-					   dentry->d_name.len + UNIONFS_WHLEN);
-		if (IS_ERR(wh_dentry)) {
-			err = PTR_ERR(wh_dentry);
-			wh_dentry = NULL;
-			goto out;
-		}
-
-		if (wh_dentry->d_inode) {
-			/*
-			 * .wh.foo has been found, so let's unlink it
-			 */
-			struct dentry *lower_dir_dentry;
-
-			lower_dir_dentry = lock_parent_wh(wh_dentry);
-			err = vfs_unlink(lower_dir_dentry->d_inode, wh_dentry);
-			unlock_dir(lower_dir_dentry);
-
-			/*
-			 * Whiteouts are special files and should be deleted
-			 * no matter what (as if they never existed), in
-			 * order to allow this create operation to succeed.
-			 * This is especially important in sticky
-			 * directories: a whiteout may have been created by
-			 * one user, but the newly created file may be
-			 * created by another user.  Therefore, in order to
-			 * maintain Unix semantics, if the vfs_unlink above
-			 * ailed, then we have to try to directly unlink the
-			 * whiteout.  Note: in the ODF version of unionfs,
-			 * whiteout are handled much more cleanly.
-			 */
-			if (err == -EPERM) {
-				struct inode *inode = lower_dir_dentry->d_inode;
-				err = inode->i_op->unlink(inode, wh_dentry);
-			}
-			if (err) {
-				printk(KERN_ERR "unionfs: symlink: could not "
-				       "unlink whiteout, err = %d\n", err);
-				goto out;
-			}
-		}
-	} else {
-		/*
-		 * if lower_dentry is NULL, create the entire
-		 * dentry directory structure in branch 0.
-		 */
-		lower_dentry = create_parents(parent, dentry,
-					      dentry->d_name.name, 0);
-		if (IS_ERR(lower_dentry)) {
-			err = PTR_ERR(lower_dentry);
-			goto out;
-		}
-	}
-
 	lower_parent_dentry = lock_parent(lower_dentry);
 	if (IS_ERR(lower_parent_dentry)) {
 		err = PTR_ERR(lower_parent_dentry);
@@ -713,86 +704,12 @@ static int unionfs_mknod(struct inode *parent, struct dentry *dentry, int mode,
 	 */
 	BUG_ON(!valid && dentry->d_inode);
 
-	/*
-	 * We shouldn't create things in a read-only branch; this check is a
-	 * bit redundant as we don't allow branch 0 to be read-only at the
-	 * moment
-	 */
-	err = is_robranch_super(dentry->d_sb, 0);
-	if (err) {
-		err = -EROFS;
+	lower_dentry = find_writeable_branch(parent, dentry);
+	if (IS_ERR(lower_dentry)) {
+		err = PTR_ERR(lower_dentry);
 		goto out;
 	}
 
-	/*
-	 * We _always_ create on branch 0
-	 */
-	lower_dentry = unionfs_lower_dentry_idx(dentry, 0);
-	if (lower_dentry) {
-		/*
-		 * check if whiteout exists in this branch, i.e. lookup .wh.foo
-		 * first.
-		 */
-		name = alloc_whname(dentry->d_name.name, dentry->d_name.len);
-		if (unlikely(IS_ERR(name))) {
-			err = PTR_ERR(name);
-			goto out;
-		}
-
-		wh_dentry = lookup_one_len(name, lower_dentry->d_parent,
-					   dentry->d_name.len + UNIONFS_WHLEN);
-		if (IS_ERR(wh_dentry)) {
-			err = PTR_ERR(wh_dentry);
-			wh_dentry = NULL;
-			goto out;
-		}
-
-		if (wh_dentry->d_inode) {
-			/*
-			 * .wh.foo has been found, so let's unlink it
-			 */
-			struct dentry *lower_dir_dentry;
-
-			lower_dir_dentry = lock_parent_wh(wh_dentry);
-			err = vfs_unlink(lower_dir_dentry->d_inode, wh_dentry);
-			unlock_dir(lower_dir_dentry);
-
-			/*
-			 * Whiteouts are special files and should be deleted
-			 * no matter what (as if they never existed), in
-			 * order to allow this create operation to succeed.
-			 * This is especially important in sticky
-			 * directories: a whiteout may have been created by
-			 * one user, but the newly created file may be
-			 * created by another user.  Therefore, in order to
-			 * maintain Unix semantics, if the vfs_unlink above
-			 * ailed, then we have to try to directly unlink the
-			 * whiteout.  Note: in the ODF version of unionfs,
-			 * whiteout are handled much more cleanly.
-			 */
-			if (err == -EPERM) {
-				struct inode *inode = lower_dir_dentry->d_inode;
-				err = inode->i_op->unlink(inode, wh_dentry);
-			}
-			if (err) {
-				printk(KERN_ERR "unionfs: mknod: could not "
-				       "unlink whiteout, err = %d\n", err);
-				goto out;
-			}
-		}
-	} else {
-		/*
-		 * if lower_dentry is NULL, create the entire
-		 * dentry directory structure in branch 0.
-		 */
-		lower_dentry = create_parents(parent, dentry,
-					      dentry->d_name.name, 0);
-		if (IS_ERR(lower_dentry)) {
-			err = PTR_ERR(lower_dentry);
-			goto out;
-		}
-	}
-
 	lower_parent_dentry = lock_parent(lower_dentry);
 	if (IS_ERR(lower_parent_dentry)) {
 		err = PTR_ERR(lower_parent_dentry);
-- 
1.5.2.2

[PATCH 2/4] Unionfs: remove unnecessary call to d_iput

[Erez Zadok]

This old code was to fix a bug which has long since been fixed in our
copyup_permission and unionfs_d_iput.

Signed-off-by: Erez Zadok <ezk@cs.sunysb.edu>
---
 fs/unionfs/copyup.c |   13 -------------
 1 files changed, 0 insertions(+), 13 deletions(-)

diff --git a/fs/unionfs/copyup.c b/fs/unionfs/copyup.c
index 16b2c7c..8663224 100644
--- a/fs/unionfs/copyup.c
+++ b/fs/unionfs/copyup.c
@@ -807,19 +807,6 @@ begin:
 						 lower_dentry);
 		unlock_dir(lower_parent_dentry);
 		if (err) {
-			struct inode *inode = lower_dentry->d_inode;
-			/*
-			 * If we get here, it means that we created a new
-			 * dentry+inode, but copying permissions failed.
-			 * Therefore, we should delete this inode and dput
-			 * the dentry so as not to leave cruft behind.
-			 */
-			if (lower_dentry->d_op && lower_dentry->d_op->d_iput)
-				lower_dentry->d_op->d_iput(lower_dentry,
-							   inode);
-			else
-				iput(inode);
-			lower_dentry->d_inode = NULL;
 			dput(lower_dentry);
 			lower_dentry = ERR_PTR(err);
 			goto out;
-- 
1.5.2.2

[PATCH 3/4] Unionfs: d_parent related locking fixes

[Erez Zadok]

Signed-off-by: Erez Zadok <ezk@cs.sunysb.edu>
---
 fs/unionfs/copyup.c |    3 +--
 fs/unionfs/union.h  |    4 ++--
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/fs/unionfs/copyup.c b/fs/unionfs/copyup.c
index 8663224..9beac01 100644
--- a/fs/unionfs/copyup.c
+++ b/fs/unionfs/copyup.c
@@ -716,8 +716,7 @@ struct dentry *create_parents(struct inode *dir, struct dentry *dentry,
 		child_dentry = parent_dentry;
 
 		/* find the parent directory dentry in unionfs */
-		parent_dentry = child_dentry->d_parent;
-		dget(parent_dentry);
+		parent_dentry = dget_parent(child_dentry);
 
 		/* find out the lower_parent_dentry in the given branch */
 		lower_parent_dentry =
diff --git a/fs/unionfs/union.h b/fs/unionfs/union.h
index d324f83..4b4d6c9 100644
--- a/fs/unionfs/union.h
+++ b/fs/unionfs/union.h
@@ -487,13 +487,13 @@ extern int parse_branch_mode(const char *name, int *perms);
 /* locking helpers */
 static inline struct dentry *lock_parent(struct dentry *dentry)
 {
-	struct dentry *dir = dget(dentry->d_parent);
+	struct dentry *dir = dget_parent(dentry);
 	mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);
 	return dir;
 }
 static inline struct dentry *lock_parent_wh(struct dentry *dentry)
 {
-	struct dentry *dir = dget(dentry->d_parent);
+	struct dentry *dir = dget_parent(dentry);
 
 	mutex_lock_nested(&dir->d_inode->i_mutex, UNIONFS_DMUTEX_WHITEOUT);
 	return dir;
-- 
1.5.2.2

[PATCH 4/4] Unionfs: lock_rename related locking fixes

[Erez Zadok]

CC: Mike Halcrow <mhalcrow@us.ibm.com>

Signed-off-by: Erez Zadok <ezk@cs.sunysb.edu>
---
 fs/unionfs/rename.c |   16 +++++++++++++++-
 1 files changed, 15 insertions(+), 1 deletions(-)

diff --git a/fs/unionfs/rename.c b/fs/unionfs/rename.c
index 9306a2b..5ab13f9 100644
--- a/fs/unionfs/rename.c
+++ b/fs/unionfs/rename.c
@@ -29,6 +29,7 @@ static int __unionfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct dentry *lower_new_dir_dentry;
 	struct dentry *lower_wh_dentry;
 	struct dentry *lower_wh_dir_dentry;
+	struct dentry *trap;
 	char *wh_name = NULL;
 
 	lower_new_dentry = unionfs_lower_dentry_idx(new_dentry, bindex);
@@ -95,6 +96,7 @@ static int __unionfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		goto out;
 
 	dget(lower_old_dentry);
+	dget(lower_new_dentry);
 	lower_old_dir_dentry = dget_parent(lower_old_dentry);
 	lower_new_dir_dentry = dget_parent(lower_new_dentry);
 
@@ -122,9 +124,20 @@ static int __unionfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	/* see Documentation/filesystems/unionfs/issues.txt */
 	lockdep_off();
-	lock_rename(lower_old_dir_dentry, lower_new_dir_dentry);
+	trap = lock_rename(lower_old_dir_dentry, lower_new_dir_dentry);
+	/* source should not be ancenstor of target */
+	if (trap == lower_old_dentry) {
+		err = -EINVAL;
+		goto out_err_unlock;
+	}
+	/* target should not be ancenstor of source */
+	if (trap == lower_new_dentry) {
+		err = -ENOTEMPTY;
+		goto out_err_unlock;
+	}
 	err = vfs_rename(lower_old_dir_dentry->d_inode, lower_old_dentry,
 			 lower_new_dir_dentry->d_inode, lower_new_dentry);
+out_err_unlock:
 	unlock_rename(lower_old_dir_dentry, lower_new_dir_dentry);
 	lockdep_on();
 
@@ -132,6 +145,7 @@ out_dput:
 	dput(lower_old_dir_dentry);
 	dput(lower_new_dir_dentry);
 	dput(lower_old_dentry);
+	dput(lower_new_dentry);
 
 out:
 	if (!err) {
-- 
1.5.2.2