drm/msm: Fix debugfs deadlock

In normal cases the gem obj lock is acquired first before mm_lock.  The
exception is iterating the various object lists.  In the shrinker path,
deadlock is avoided by using msm_gem_trylock() and skipping over objects
that cannot be locked.  But for debugfs the straightforward thing is to
split things out into a separate list of all objects protected by it's
own lock.

Fixes: d984457b31 ("drm/msm: Add priv->mm_lock to protect active/inactive lists")
Signed-off-by: Rob Clark <robdclark@chromium.org>
Tested-by: Douglas Anderson <dianders@chromium.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Link: https://lore.kernel.org/r/20210401012722.527712-4-robdclark@gmail.com
Signed-off-by: Rob Clark <robdclark@chromium.org>

drivers/gpu/drm/msm/msm_debugfs.c

@@ -111,23 +111,15 @@ static const struct file_operations msm_gpu_fops = {
 static int msm_gem_show(struct drm_device *dev, struct seq_file *m)
 {
 	struct msm_drm_private *priv = dev->dev_private;
-	struct msm_gpu *gpu = priv->gpu;
 	int ret;
 
-	ret = mutex_lock_interruptible(&priv->mm_lock);
+	ret = mutex_lock_interruptible(&priv->obj_lock);
 	if (ret)
 		return ret;
 
-	if (gpu) {
+	msm_gem_describe_objects(&priv->objects, m);
-		seq_printf(m, "Active Objects (%s):\n", gpu->name);
-		msm_gem_describe_objects(&gpu->active_list, m);
-	}
 
-	seq_printf(m, "Inactive Objects:\n");
+	mutex_unlock(&priv->obj_lock);
-	msm_gem_describe_objects(&priv->inactive_dontneed, m);
-	msm_gem_describe_objects(&priv->inactive_willneed, m);
-
-	mutex_unlock(&priv->mm_lock);
 
 	return 0;
 }

drivers/gpu/drm/msm/msm_drv.c

@@ -446,6 +446,9 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv)
 
 	priv->wq = alloc_ordered_workqueue("msm", 0);
 
+	INIT_LIST_HEAD(&priv->objects);
+	mutex_init(&priv->obj_lock);
+
 	INIT_LIST_HEAD(&priv->inactive_willneed);
 	INIT_LIST_HEAD(&priv->inactive_dontneed);
 	INIT_LIST_HEAD(&priv->inactive_purged);

drivers/gpu/drm/msm/msm_drv.h

@@ -174,7 +174,14 @@ struct msm_drm_private {
 	struct msm_rd_state *hangrd;   /* debugfs to dump hanging submits */
 	struct msm_perf_state *perf;
 
-	/*
+	/**
+	 * List of all GEM objects (mainly for debugfs, protected by obj_lock
+	 * (acquire before per GEM object lock)
+	 */
+	struct list_head objects;
+	struct mutex obj_lock;
+
+	/**
 	 * Lists of inactive GEM objects.  Every bo is either in one of the
 	 * inactive lists (depending on whether or not it is shrinkable) or
 	 * gpu->active_list (for the gpu it is active on[1])

drivers/gpu/drm/msm/msm_gem.c

@@ -961,7 +961,7 @@ void msm_gem_describe_objects(struct list_head *list, struct seq_file *m)
 	size_t size = 0;
 
 	seq_puts(m, "   flags       id ref  offset   kaddr            size     madv      name\n");
-	list_for_each_entry(msm_obj, list, mm_list) {
+	list_for_each_entry(msm_obj, list, node) {
 		struct drm_gem_object *obj = &msm_obj->base;
 		seq_puts(m, "   ");
 		msm_gem_describe(obj, m);
@@ -980,6 +980,10 @@ void msm_gem_free_object(struct drm_gem_object *obj)
 	struct drm_device *dev = obj->dev;
 	struct msm_drm_private *priv = dev->dev_private;
 
+	mutex_lock(&priv->obj_lock);
+	list_del(&msm_obj->node);
+	mutex_unlock(&priv->obj_lock);
+
 	mutex_lock(&priv->mm_lock);
 	if (msm_obj->dontneed)
 		mark_unpurgable(msm_obj);
@@ -1169,6 +1173,10 @@ static struct drm_gem_object *_msm_gem_new(struct drm_device *dev,
 	list_add_tail(&msm_obj->mm_list, &priv->inactive_willneed);
 	mutex_unlock(&priv->mm_lock);
 
+	mutex_lock(&priv->obj_lock);
+	list_add_tail(&msm_obj->node, &priv->objects);
+	mutex_unlock(&priv->obj_lock);
+
 	return obj;
 
 fail:
@@ -1239,6 +1247,10 @@ struct drm_gem_object *msm_gem_import(struct drm_device *dev,
 	list_add_tail(&msm_obj->mm_list, &priv->inactive_willneed);
 	mutex_unlock(&priv->mm_lock);
 
+	mutex_lock(&priv->obj_lock);
+	list_add_tail(&msm_obj->node, &priv->objects);
+	mutex_unlock(&priv->obj_lock);
+
 	return obj;
 
 fail:

drivers/gpu/drm/msm/msm_gem.h

@@ -60,10 +60,16 @@ struct msm_gem_object {
 	 */
 	uint8_t vmap_count;
 
+	/**
+	 * Node in list of all objects (mainly for debugfs, protected by
+	 * priv->obj_lock
+	 */
+	struct list_head node;
+
 	/**
 	 * An object is either:
-	 *  inactive - on priv->inactive_dontneed/willneed/purged depending
+	 *  inactive - on priv->inactive_dontneed or priv->inactive_willneed
-	 *     on status
+	 *     (depending on purgability status)
 	 *  active   - on one one of the gpu's active_list..  well, at
 	 *     least for now we don't have (I don't think) hw sync between
 	 *     2d and 3d one devices which have both, meaning we need to