[PATCH 1/7] VFS/xfs/ntfs: drop parent lock across d_alloc_parallel() in d_add_ci()

[NeilBrown <neilb@ownmail.net>]

From: NeilBrown <neil@brown.name>

A proposed change will invert the lock ordering between
d_alloc_parallel() and inode_lock() on the parent.
When that happens it will not be safe to call d_alloc_parallel() while
holding the parent lock - even shared.

We don't need to keep the parent lock held when d_add_ci() is run - the
VFS doesn't need it as dentry is exclusively held due to
DCACHE_PAR_LOOKUP and the filesystem has finished its work.

So drop and reclaim the lock (shared or exclusive as determined by
LOOKUP_SHARED) to avoid future deadlock.

Signed-off-by: NeilBrown <neil@brown.name>
---
 Documentation/filesystems/porting.rst |  7 ++++++
 fs/dcache.c                           | 32 +++++++++++++++++++++++----
 fs/ntfs/namei.c                       |  2 +-
 fs/xfs/xfs_iops.c                     |  2 +-
 include/linux/dcache.h                |  3 ++-
 5 files changed, 39 insertions(+), 7 deletions(-)

diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst
index 4e015f1bf1f8..f6a38bd9c68e 100644
--- a/Documentation/filesystems/porting.rst
+++ b/Documentation/filesystems/porting.rst
@@ -1409,3 +1409,10 @@ use only if you have no alternative.
 The .create inode_operation no longer receives the 'excl' arg.  It must
 always assume the file does not already exist.  If the filesystem needs
 to be involved in non-exclusive create, it should provide atomic_open.
+
+---
+
+**mandatory**
+
+d_add_ci() must now be passed the flags arguemnt that was given to ->lookup
+
diff --git a/fs/dcache.c b/fs/dcache.c
index 83790c7a4dee..61e0896dc077 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2383,6 +2383,7 @@ EXPORT_SYMBOL(d_obtain_root);
  * @dentry: the negative dentry that was passed to the parent's lookup func
  * @inode:  the inode case-insensitive lookup has found
  * @name:   the case-exact name to be associated with the returned dentry
+ * @lookup_flags: flags passed to ->lookup
  *
  * This is to avoid filling the dcache with case-insensitive names to the
  * same inode, only the actual correct case is stored in the dcache for
@@ -2395,9 +2396,10 @@ EXPORT_SYMBOL(d_obtain_root);
  * the exact case, and return the spliced entry.
  */
 struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode,
-			struct qstr *name)
+			struct qstr *name, unsigned int lookup_flags)
 {
 	struct dentry *found, *res;
+	bool must_unlock = false;
 
 	/*
 	 * First check if a dentry matching the name already exists,
@@ -2409,24 +2411,46 @@ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode,
 		return found;
 	}
 	if (d_in_lookup(dentry)) {
+		/*
+		 * We are holding parent lock and so don't want to wait
+		 * for a d_in_lookup() dentry.  We can safely drop the
+		 * parent lock and reclaim it as we have exclusive
+		 * access to dentry as it is d_in_lookup() (so
+		 * ->d_parent is stable) and we are near the end
+		 * ->lookup() and will shortly drop the lock anyway.
+		 * We cannot retake the lock while the new dentry is in-lookup
+		 */
+		if (lookup_flags & LOOKUP_SHARED)
+			inode_unlock_shared(d_inode(dentry->d_parent));
+		else
+			inode_unlock(d_inode(dentry->d_parent));
+		must_unlock = true;
 		found = d_alloc_parallel(dentry->d_parent, name);
 		if (IS_ERR(found) || !d_in_lookup(found)) {
 			iput(inode);
-			return found;
+			goto out_unlock;
 		}
 	} else {
 		found = d_alloc(dentry->d_parent, name);
 		if (!found) {
 			iput(inode);
 			return ERR_PTR(-ENOMEM);
-		} 
+		}
 	}
 	res = d_splice_alias(inode, found);
 	if (res) {
 		d_lookup_done(found);
 		dput(found);
-		return res;
+		found = res;
 	}
+	if (!must_unlock)
+		return found;
+out_unlock:
+	d_lookup_done(dentry);
+	if (lookup_flags & LOOKUP_SHARED)
+		inode_lock_shared(d_inode(dentry->d_parent));
+	else
+		inode_lock_nested(d_inode(dentry->d_parent), I_MUTEX_PARENT);
 	return found;
 }
 EXPORT_SYMBOL(d_add_ci);
diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c
index 7091b2496fac..61cfa4e16586 100644
--- a/fs/ntfs/namei.c
+++ b/fs/ntfs/namei.c
@@ -309,7 +309,7 @@ static struct dentry *ntfs_lookup(struct inode *dir_ino, struct dentry *dent,
 		}
 		nls_name.hash = full_name_hash(dent, nls_name.name, nls_name.len);
 
-		dent = d_add_ci(dent, dent_inode, &nls_name);
+		dent = d_add_ci(dent, dent_inode, &nls_name, flags);
 		kfree(nls_name.name);
 		return dent;
 
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 4a3299abf774..fd480c0e4147 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -368,7 +368,7 @@ xfs_vn_ci_lookup(
 	/* else case-insensitive match... */
 	dname.name = ci_name.name;
 	dname.len = ci_name.len;
-	dentry = d_add_ci(dentry, VFS_I(ip), &dname);
+	dentry = d_add_ci(dentry, VFS_I(ip), &dname, flags);
 	kfree(ci_name.name);
 	return dentry;
 }
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index adf239f8205f..97d11f5e6a7b 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -267,7 +267,8 @@ struct dentry *d_duplicate(struct dentry *dentry);
 /* weird procfs mess; *NOT* exported */
 extern struct dentry * d_splice_alias_ops(struct inode *, struct dentry *,
 					  const struct dentry_operations *);
-extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *);
+extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *,
+				unsigned int);
 extern bool d_same_name(const struct dentry *dentry, const struct dentry *parent,
 			const struct qstr *name);
 extern struct dentry *d_find_any_alias(struct inode *inode);

base-commit: 3879f51857325da9bf3cfb073280257cd16ae067
-- 
2.50.0.107.gf914562f5916.dirty