Merge tag 'pull-persistency' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull persistent dentry infrastructure and conversion from Al Viro:
 "Some filesystems use a kinda-sorta controlled dentry refcount leak to
  pin dentries of created objects in dcache (and undo it when removing
  those). A reference is grabbed and not released, but it's not actually
  _stored_ anywhere.

  That works, but it's hard to follow and verify; among other things, we
  have no way to tell _which_ of the increments is intended to be an
  unpaired one. Worse, on removal we need to decide whether the
  reference had already been dropped, which can be non-trivial if that
  removal is on umount and we need to figure out if this dentry is
  pinned due to e.g. unlink() not done. Usually that is handled by using
  kill_litter_super() as ->kill_sb(), but there are open-coded special
  cases of the same (consider e.g. /proc/self).

  Things get simpler if we introduce a new dentry flag
  (DCACHE_PERSISTENT) marking those "leaked" dentries. Having it set
  claims responsibility for +1 in refcount.

  The end result this series is aiming for:

   - get these unbalanced dget() and dput() replaced with new primitives
     that would, in addition to adjusting refcount, set and clear
     persistency flag.

   - instead of having kill_litter_super() mess with removing the
     remaining "leaked" references (e.g. for all tmpfs files that hadn't
     been removed prior to umount), have the regular
     shrink_dcache_for_umount() strip DCACHE_PERSISTENT of all dentries,
     dropping the corresponding reference if it had been set. After that
     kill_litter_super() becomes an equivalent of kill_anon_super().

  Doing that in a single step is not feasible - it would affect too many
  places in too many filesystems. It has to be split into a series.

  This work has really started early in 2024; quite a few preliminary
  pieces have already gone into mainline. This chunk is finally getting
  to the meat of that stuff - infrastructure and most of the conversions
  to it.

  Some pieces are still sitting in the local branches, but the bulk of
  that stuff is here"

* tag 'pull-persistency' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (54 commits)
  d_make_discardable(): warn if given a non-persistent dentry
  kill securityfs_recursive_remove()
  convert securityfs
  get rid of kill_litter_super()
  convert rust_binderfs
  convert nfsctl
  convert rpc_pipefs
  convert hypfs
  hypfs: swich hypfs_create_u64() to returning int
  hypfs: switch hypfs_create_str() to returning int
  hypfs: don't pin dentries twice
  convert gadgetfs
  gadgetfs: switch to simple_remove_by_name()
  convert functionfs
  functionfs: switch to simple_remove_by_name()
  functionfs: fix the open/removal races
  functionfs: need to cancel ->reset_work in ->kill_sb()
  functionfs: don't bother with ffs->ref in ffs_data_{opened,closed}()
  functionfs: don't abuse ffs_data_closed() on fs shutdown
  convert selinuxfs
  ...

1 files changed, 19 insertions, 63 deletions

diff --git a/drivers/android/binderfs.c b/drivers/android/binderfs.c
index be8e64eb39ec..a28d0511960e 100644
--- a/drivers/android/binderfs.c
+++ b/drivers/android/binderfs.c
@@ -183,28 +183,15 @@ static int binderfs_binder_device_create(struct inode *ref_inode,
 	}
 
 	root = sb->s_root;
-	inode_lock(d_inode(root));
-
-	/* look it up */
-	dentry = lookup_noperm(&QSTR(name), root);
+	dentry = simple_start_creating(root, name);
 	if (IS_ERR(dentry)) {
-		inode_unlock(d_inode(root));
 		ret = PTR_ERR(dentry);
 		goto err;
 	}
-
-	if (d_really_is_positive(dentry)) {
-		/* already exists */
-		dput(dentry);
-		inode_unlock(d_inode(root));
-		ret = -EEXIST;
-		goto err;
-	}
-
 	inode->i_private = device;
-	d_instantiate(dentry, inode);
+	d_make_persistent(dentry, inode);
 	fsnotify_create(root->d_inode, dentry);
-	inode_unlock(d_inode(root));
+	simple_done_creating(dentry);
 
 	binder_add_device(device);
 
@@ -410,12 +397,6 @@ static int binderfs_binder_ctl_create(struct super_block *sb)
 	if (!device)
 		return -ENOMEM;
 
-	/* If we have already created a binder-control node, return. */
-	if (info->control_dentry) {
-		ret = 0;
-		goto out;
-	}
-
 	ret = -ENOMEM;
 	inode = new_inode(sb);
 	if (!inode)
@@ -451,7 +432,8 @@ static int binderfs_binder_ctl_create(struct super_block *sb)
 
 	inode->i_private = device;
 	info->control_dentry = dentry;
-	d_add(dentry, inode);
+	d_make_persistent(dentry, inode);
+	dput(dentry);
 
 	return 0;
 
@@ -481,24 +463,6 @@ static struct inode *binderfs_make_inode(struct super_block *sb, int mode)
 	return ret;
 }
 
-static struct dentry *binderfs_create_dentry(struct dentry *parent,
-					     const char *name)
-{
-	struct dentry *dentry;
-
-	dentry = lookup_noperm(&QSTR(name), parent);
-	if (IS_ERR(dentry))
-		return dentry;
-
-	/* Return error if the file/dir already exists. */
-	if (d_really_is_positive(dentry)) {
-		dput(dentry);
-		return ERR_PTR(-EEXIST);
-	}
-
-	return dentry;
-}
-
 struct dentry *binderfs_create_file(struct dentry *parent, const char *name,
 				    const struct file_operations *fops,
 				    void *data)
@@ -508,28 +472,24 @@ struct dentry *binderfs_create_file(struct dentry *parent, const char *name,
 	struct super_block *sb;
 
 	parent_inode = d_inode(parent);
-	inode_lock(parent_inode);
 
-	dentry = binderfs_create_dentry(parent, name);
+	dentry = simple_start_creating(parent, name);
 	if (IS_ERR(dentry))
-		goto out;
+		return dentry;
 
 	sb = parent_inode->i_sb;
 	new_inode = binderfs_make_inode(sb, S_IFREG | 0444);
 	if (!new_inode) {
-		dput(dentry);
-		dentry = ERR_PTR(-ENOMEM);
-		goto out;
+		simple_done_creating(dentry);
+		return ERR_PTR(-ENOMEM);
 	}
 
 	new_inode->i_fop = fops;
 	new_inode->i_private = data;
-	d_instantiate(dentry, new_inode);
+	d_make_persistent(dentry, new_inode);
 	fsnotify_create(parent_inode, dentry);
-
-out:
-	inode_unlock(parent_inode);
-	return dentry;
+	simple_done_creating(dentry);
+	return dentry; // borrowed
 }
 
 static struct dentry *binderfs_create_dir(struct dentry *parent,
@@ -540,30 +500,26 @@ static struct dentry *binderfs_create_dir(struct dentry *parent,
 	struct super_block *sb;
 
 	parent_inode = d_inode(parent);
-	inode_lock(parent_inode);
 
-	dentry = binderfs_create_dentry(parent, name);
+	dentry = simple_start_creating(parent, name);
 	if (IS_ERR(dentry))
-		goto out;
+		return dentry;
 
 	sb = parent_inode->i_sb;
 	new_inode = binderfs_make_inode(sb, S_IFDIR | 0755);
 	if (!new_inode) {
-		dput(dentry);
-		dentry = ERR_PTR(-ENOMEM);
-		goto out;
+		simple_done_creating(dentry);
+		return ERR_PTR(-ENOMEM);
 	}
 
 	new_inode->i_fop = &simple_dir_operations;
 	new_inode->i_op = &simple_dir_inode_operations;
 
 	set_nlink(new_inode, 2);
-	d_instantiate(dentry, new_inode);
+	d_make_persistent(dentry, new_inode);
 	inc_nlink(parent_inode);
 	fsnotify_mkdir(parent_inode, dentry);
-
-out:
-	inode_unlock(parent_inode);
+	simple_done_creating(dentry);
 	return dentry;
 }
 
@@ -779,7 +735,7 @@ static void binderfs_kill_super(struct super_block *sb)
 	 * During inode eviction struct binderfs_info is needed.
 	 * So first wipe the super_block then free struct binderfs_info.
 	 */
-	kill_litter_super(sb);
+	kill_anon_super(sb);
 
 	if (info && info->ipc_ns)
 		put_ipc_ns(info->ipc_ns);