drm: locking&new iterators for connector_list

The requirements for connector_list locking are a bit tricky:
- We need to be able to jump over zombie conectors (i.e. with refcount
  == 0, but not yet removed from the list). If instead we require that
  there's no zombies on the list then the final kref_put must happen
  under the list protection lock, which means that locking context
  leaks all over the place. Not pretty - better to deal with zombies
  and wrap the locking just around the list_del in the destructor.

- When we walk the list we must _not_ hold the connector list lock. We
  walk the connector list at an absolutely massive amounts of places,
  if all those places can't ever call drm_connector_unreference the
  code would get unecessarily complicated.

- connector_list needs it own lock, again too many places that walk it
  that we could reuse e.g. mode_config.mutex without resulting in
  inversions.

- Lots of code uses these loops to look-up a connector, i.e. they want
  to be able to call drm_connector_reference. But on the other hand we
  want connectors to stay on that list until they're dead (i.e.
  connector_list can't hold a full reference), which means despite the
  "can't hold lock for the loop body" rule we need to make sure a
  connector doesn't suddenly become a zombie.

At first Dave&I discussed various horror-show approaches using srcu,
but turns out it's fairly easy:

- For the loop body we always hold an additional reference to the
  current connector. That means it can't zombify, and it also means
  it'll stay on the list, which means we can use it as our iterator to
  find the next connector.

- When we try to find the next connector we only have to jump over
  zombies. To make sure we don't chase bad pointers that entire loop
  is protected with the new connect_list_lock spinlock. And because we
  know that we're starting out with a non-zombie (need to drop our
  reference for the old connector only after we have our new one),
  we're guranteed to still be on the connector_list and either find
  the next non-zombie or complete the iteration.

- Only downside is that we need to make sure that the temporary
  reference for the loop body doesn't leak. iter_get/put() functions +
  lockdep make sure that's the case.

- To avoid a flag day the new iterator macro has an _iter postfix. We
  can rename it back once all the users of the unsafe version are gone
  (there's about 100 list walkers for the connector_list).

For now this patch only converts all the list walking in the core,
leaving helpers and drivers for later patches. The nice thing is that
we can now finally remove 2 FIXME comments from the
register/unregister functions.

v2:
- use irqsafe spinlocks, so that we can use this in drm_state_dump
  too.
- nuke drm_modeset_lock_all from drm_connector_init, now entirely
  cargo-culted nonsense.

v3:
- do {} while (!kref_get_unless_zero), makes for a tidier loop (Dave).
- pretty kerneldoc
- add EXPORT_SYMBOL, helpers&drivers are supposed to use this.

v4: Change lockdep annotations to only check whether we release the
iter fake lock again (i.e. make sure that iter_put is called), but
not check any locking dependecies itself. That seams to require a
recursive read lock in trylock mode.

Cc: Dave Airlie <airlied@gmail.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161213230814.19598-6-daniel.vetter@ffwll.ch

1 files changed, 98 insertions, 18 deletions

diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index 40f8126a9738..020225809ff4 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -190,13 +190,11 @@ int drm_connector_init(struct drm_device *dev,
 	struct ida *connector_ida =
 		&drm_connector_enum_list[connector_type].ida;
 
-	drm_modeset_lock_all(dev);
-
 	ret = drm_mode_object_get_reg(dev, &connector->base,
 				      DRM_MODE_OBJECT_CONNECTOR,
 				      false, drm_connector_free);
 	if (ret)
-		goto out_unlock;
+		return ret;
 
 	connector->base.properties = &connector->properties;
 	connector->dev = dev;
@@ -233,8 +231,10 @@ int drm_connector_init(struct drm_device *dev,
 
 	/* We should add connectors at the end to avoid upsetting the connector
 	 * index too much. */
+	spin_lock_irq(&config->connector_list_lock);
 	list_add_tail(&connector->head, &config->connector_list);
 	config->num_connector++;
+	spin_unlock_irq(&config->connector_list_lock);
 
 	if (connector_type != DRM_MODE_CONNECTOR_VIRTUAL)
 		drm_object_attach_property(&connector->base,
@@ -259,9 +259,6 @@ out_put:
 	if (ret)
 		drm_mode_object_unregister(dev, &connector->base);
 
-out_unlock:
-	drm_modeset_unlock_all(dev);
-
 	return ret;
 }
 EXPORT_SYMBOL(drm_connector_init);
@@ -352,8 +349,10 @@ void drm_connector_cleanup(struct drm_connector *connector)
 	drm_mode_object_unregister(dev, &connector->base);
 	kfree(connector->name);
 	connector->name = NULL;
+	spin_lock_irq(&dev->mode_config.connector_list_lock);
 	list_del(&connector->head);
 	dev->mode_config.num_connector--;
+	spin_unlock_irq(&dev->mode_config.connector_list_lock);
 
 	WARN_ON(connector->state && !connector->funcs->atomic_destroy_state);
 	if (connector->state && connector->funcs->atomic_destroy_state)
@@ -432,30 +431,30 @@ EXPORT_SYMBOL(drm_connector_unregister);
 void drm_connector_unregister_all(struct drm_device *dev)
 {
 	struct drm_connector *connector;
+	struct drm_connector_list_iter conn_iter;
 
-	/* FIXME: taking the mode config mutex ends up in a clash with sysfs */
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head)
+	drm_connector_list_iter_get(dev, &conn_iter);
+	drm_for_each_connector_iter(connector, &conn_iter)
 		drm_connector_unregister(connector);
+	drm_connector_list_iter_put(&conn_iter);
 }
 
 int drm_connector_register_all(struct drm_device *dev)
 {
 	struct drm_connector *connector;
-	int ret;
+	struct drm_connector_list_iter conn_iter;
+	int ret = 0;
 
-	/* FIXME: taking the mode config mutex ends up in a clash with
-	 * fbcon/backlight registration */
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_get(dev, &conn_iter);
+	drm_for_each_connector_iter(connector, &conn_iter) {
 		ret = drm_connector_register(connector);
 		if (ret)
-			goto err;
+			break;
 	}
+	drm_connector_list_iter_put(&conn_iter);
 
-	return 0;
-
-err:
-	mutex_unlock(&dev->mode_config.mutex);
-	drm_connector_unregister_all(dev);
+	if (ret)
+		drm_connector_unregister_all(dev);
 	return ret;
 }
 
@@ -477,6 +476,87 @@ const char *drm_get_connector_status_name(enum drm_connector_status status)
 }
 EXPORT_SYMBOL(drm_get_connector_status_name);
 
+#ifdef CONFIG_LOCKDEP
+static struct lockdep_map connector_list_iter_dep_map = {
+	.name = "drm_connector_list_iter"
+};
+#endif
+
+/**
+ * drm_connector_list_iter_get - initialize a connector_list iterator
+ * @dev: DRM device
+ * @iter: connector_list iterator
+ *
+ * Sets @iter up to walk the connector list in &drm_mode_config of @dev. @iter
+ * must always be cleaned up again by calling drm_connector_list_iter_put().
+ * Iteration itself happens using drm_connector_list_iter_next() or
+ * drm_for_each_connector_iter().
+ */
+void drm_connector_list_iter_get(struct drm_device *dev,
+				 struct drm_connector_list_iter *iter)
+{
+	iter->dev = dev;
+	iter->conn = NULL;
+	lock_acquire_shared_recursive(&connector_list_iter_dep_map, 0, 1, NULL, _RET_IP_);
+}
+EXPORT_SYMBOL(drm_connector_list_iter_get);
+
+/**
+ * drm_connector_list_iter_next - return next connector
+ * @iter: connectr_list iterator
+ *
+ * Returns the next connector for @iter, or NULL when the list walk has
+ * completed.
+ */
+struct drm_connector *
+drm_connector_list_iter_next(struct drm_connector_list_iter *iter)
+{
+	struct drm_connector *old_conn = iter->conn;
+	struct drm_mode_config *config = &iter->dev->mode_config;
+	struct list_head *lhead;
+	unsigned long flags;
+
+	spin_lock_irqsave(&config->connector_list_lock, flags);
+	lhead = old_conn ? &old_conn->head : &config->connector_list;
+
+	do {
+		if (lhead->next == &config->connector_list) {
+			iter->conn = NULL;
+			break;
+		}
+
+		lhead = lhead->next;
+		iter->conn = list_entry(lhead, struct drm_connector, head);
+
+		/* loop until it's not a zombie connector */
+	} while (!kref_get_unless_zero(&iter->conn->base.refcount));
+	spin_unlock_irqrestore(&config->connector_list_lock, flags);
+
+	if (old_conn)
+		drm_connector_unreference(old_conn);
+
+	return iter->conn;
+}
+EXPORT_SYMBOL(drm_connector_list_iter_next);
+
+/**
+ * drm_connector_list_iter_put - tear down a connector_list iterator
+ * @iter: connector_list iterator
+ *
+ * Tears down @iter and releases any resources (like &drm_connector references)
+ * acquired while walking the list. This must always be called, both when the
+ * iteration completes fully or when it was aborted without walking the entire
+ * list.
+ */
+void drm_connector_list_iter_put(struct drm_connector_list_iter *iter)
+{
+	iter->dev = NULL;
+	if (iter->conn)
+		drm_connector_unreference(iter->conn);
+	lock_release(&connector_list_iter_dep_map, 0, _RET_IP_);
+}
+EXPORT_SYMBOL(drm_connector_list_iter_put);
+
 static const struct drm_prop_enum_list drm_subpixel_enum_list[] = {
 	{ SubPixelUnknown, "Unknown" },
 	{ SubPixelHorizontalRGB, "Horizontal RGB" },