[PATCH 07/30] Unionfs: create new special files only in first branch

[Erez Zadok]

When creating a new special file, always create it in the first branch,
which is always writeable, not in the branch which may have a whiteout in
it.  This makes the policy for the creation of new special files consistent
with that of new files/directories, as well as improves efficiency a bit.

Signed-off-by: Erez Zadok <ezk@xxxxxxxxxxxxx>
---
 fs/unionfs/inode.c |  174 +++++++++++++++++++++++++++------------------------
 1 files changed, 92 insertions(+), 82 deletions(-)

diff --git a/fs/unionfs/inode.c b/fs/unionfs/inode.c
index 63ff3d3..8076d0b 100644
--- a/fs/unionfs/inode.c
+++ b/fs/unionfs/inode.c
@@ -686,15 +686,15 @@ out:
 	return err;
 }
 
-static int unionfs_mknod(struct inode *dir, struct dentry *dentry, int mode,
+static int unionfs_mknod(struct inode *parent, struct dentry *dentry, int mode,
 			 dev_t dev)
 {
 	int err = 0;
-	struct dentry *lower_dentry = NULL, *whiteout_dentry = NULL;
+	struct dentry *lower_dentry = NULL;
+	struct dentry *wh_dentry = NULL;
 	struct dentry *lower_parent_dentry = NULL;
-	int bindex = 0, bstart;
 	char *name = NULL;
-	int whiteout_unlinked = 0;
+	int valid = 0;
 
 	unionfs_read_lock(dentry->d_sb);
 	unionfs_lock_dentry(dentry);
@@ -705,115 +705,125 @@ static int unionfs_mknod(struct inode *dir, struct dentry *dentry, int mode,
 		goto out;
 	}
 
-	bstart = dbstart(dentry);
-
-	lower_dentry = unionfs_lower_dentry(dentry);
+	/*
+	 * It's only a bug if this dentry was not negative and couldn't be
+	 * revalidated (shouldn't happen).
+	 */
+	BUG_ON(!valid && dentry->d_inode);
 
 	/*
-	 * check if whiteout exists in this branch, i.e. lookup .wh.foo
-	 * first.
+	 * 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
 	 */
-	name = alloc_whname(dentry->d_name.name, dentry->d_name.len);
-	if (unlikely(IS_ERR(name))) {
-		err = PTR_ERR(name);
+	err = is_robranch_super(dentry->d_sb, 0);
+	if (err) {
+		err = -EROFS;
 		goto out;
 	}
 
-	whiteout_dentry = lookup_one_len(name, lower_dentry->d_parent,
-					 dentry->d_name.len + UNIONFS_WHLEN);
-	if (IS_ERR(whiteout_dentry)) {
-		err = PTR_ERR(whiteout_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;
+		}
 
-	if (!whiteout_dentry->d_inode) {
-		dput(whiteout_dentry);
-		whiteout_dentry = NULL;
-	} else {
-		/* found .wh.foo, unlink it */
-		lower_parent_dentry = lock_parent(whiteout_dentry);
+		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;
+		}
 
-		/* found a.wh.foo entry, remove it then do vfs_mkdir */
-		err = is_robranch_super(dentry->d_sb, bstart);
-		if (!err)
-			err = vfs_unlink(lower_parent_dentry->d_inode,
-					 whiteout_dentry);
-		dput(whiteout_dentry);
+		if (wh_dentry->d_inode) {
+			/*
+			 * .wh.foo has been found, so let's unlink it
+			 */
+			struct dentry *lower_dir_dentry;
 
-		unlock_dir(lower_parent_dentry);
+			lower_dir_dentry = lock_parent(wh_dentry);
+			err = vfs_unlink(lower_dir_dentry->d_inode, wh_dentry);
+			unlock_dir(lower_dir_dentry);
 
-		if (err) {
-			if (!IS_COPYUP_ERR(err))
+			/*
+			 * 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;
-			bstart--;
-		} else {
-			whiteout_unlinked = 1;
-		}
-	}
-
-	for (bindex = bstart; bindex >= 0; bindex--) {
-		if (is_robranch_super(dentry->d_sb, bindex))
-			continue;
-
-		lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
-		if (!lower_dentry) {
-			lower_dentry = create_parents(dir, dentry,
-						      dentry->d_name.name,
-						      bindex);
-			if (IS_ERR(lower_dentry)) {
-				printk(KERN_ERR "unionfs: failed to create "
-				       "parents on %d, err = %ld\n",
-				       bindex, PTR_ERR(lower_dentry));
-				continue;
 			}
 		}
-
-		lower_parent_dentry = lock_parent(lower_dentry);
-		if (IS_ERR(lower_parent_dentry)) {
-			err = PTR_ERR(lower_parent_dentry);
+	} 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;
 		}
+	}
 
-		err = vfs_mknod(lower_parent_dentry->d_inode,
-				lower_dentry, mode, dev);
-
-		if (err) {
-			unlock_dir(lower_parent_dentry);
-			break;
-		}
+	lower_parent_dentry = lock_parent(lower_dentry);
+	if (IS_ERR(lower_parent_dentry)) {
+		err = PTR_ERR(lower_parent_dentry);
+		goto out;
+	}
 
-		/*
-		 * Only INTERPOSE_LOOKUP can return a value other than 0 on
-		 * err.
-		 */
-		err = PTR_ERR(unionfs_interpose(dentry, dir->i_sb, 0));
+	err = vfs_mknod(lower_parent_dentry->d_inode, lower_dentry, mode, dev);
+	if (!err) {
+		err = PTR_ERR(unionfs_interpose(dentry, parent->i_sb, 0));
 		if (!err) {
-			fsstack_copy_attr_times(dir,
-						lower_parent_dentry->d_inode);
-			fsstack_copy_inode_size(dir,
+			unionfs_copy_attr_times(parent);
+			fsstack_copy_inode_size(parent,
 						lower_parent_dentry->d_inode);
-			/* update number of links on parent directory */
-			dir->i_nlink = unionfs_get_nlinks(dir);
+			/* update no. of links on parent directory */
+			parent->i_nlink = unionfs_get_nlinks(parent);
 		}
-		unlock_dir(lower_parent_dentry);
-
-		break;
 	}
 
-out:
-	if (!dentry->d_inode)
-		d_drop(dentry);
+	unlock_dir(lower_parent_dentry);
 
+out:
+	dput(wh_dentry);
 	kfree(name);
 
 	if (!err)
 		unionfs_postcopyup_setmnt(dentry);
 
-	unionfs_check_inode(dir);
+	unionfs_check_inode(parent);
+	if (!err)
+		unionfs_check_dentry(dentry->d_parent);
 	unionfs_check_dentry(dentry);
 	unionfs_unlock_dentry(dentry);
 	unionfs_read_unlock(dentry->d_sb);
-
 	return err;
 }
 
-- 
1.5.2.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/