drm/msm: Add priv->mm_lock to protect active/inactive lists

Rather than relying on the big dev->struct_mutex hammer, introduce a
more specific lock for protecting the bo lists.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Signed-off-by: Rob Clark <robdclark@chromium.org>

6 files changed, 58 insertions, 14 deletions

diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c
index ee2e270f464c..64afbed89821 100644
--- a/drivers/gpu/drm/msm/msm_debugfs.c
+++ b/drivers/gpu/drm/msm/msm_debugfs.c
@@ -112,6 +112,11 @@ 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);
+	if (ret)
+		return ret;
 
 	if (gpu) {
 		seq_printf(m, "Active Objects (%s):\n", gpu->name);
@@ -121,6 +126,8 @@ static int msm_gem_show(struct drm_device *dev, struct seq_file *m)
 	seq_printf(m, "Inactive Objects:\n");
 	msm_gem_describe_objects(&priv->inactive_list, m);
 
+	mutex_unlock(&priv->mm_lock);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 49685571dc0e..81cb2cecc829 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -7,6 +7,7 @@
 
 #include <linux/dma-mapping.h>
 #include <linux/kthread.h>
+#include <linux/sched/mm.h>
 #include <linux/uaccess.h>
 #include <uapi/linux/sched/types.h>
 
@@ -441,6 +442,12 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 	init_llist_head(&priv->free_list);
 
 	INIT_LIST_HEAD(&priv->inactive_list);
+	mutex_init(&priv->mm_lock);
+
+	/* Teach lockdep about lock ordering wrt. shrinker: */
+	fs_reclaim_acquire(GFP_KERNEL);
+	might_lock(&priv->mm_lock);
+	fs_reclaim_release(GFP_KERNEL);
 
 	drm_mode_config_init(ddev);
 
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index 0749aeaa7f92..e3a8fae8c9f6 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -174,8 +174,19 @@ struct msm_drm_private {
 	struct msm_rd_state *hangrd;   /* debugfs to dump hanging submits */
 	struct msm_perf_state *perf;
 
-	/* list of GEM objects: */
+	/*
+	 * List of inactive GEM objects.  Every bo is either in the inactive_list
+	 * or gpu->active_list (for the gpu it is active on[1])
+	 *
+	 * These lists are protected by mm_lock.  If struct_mutex is involved, it
+	 * should be aquired prior to mm_lock.  One should *not* hold mm_lock in
+	 * get_pages()/vmap()/etc paths, as they can trigger the shrinker.
+	 *
+	 * [1] if someone ever added support for the old 2d cores, there could be
+	 *     more than one gpu object
+	 */
 	struct list_head inactive_list;
+	struct mutex mm_lock;
 
 	/* worker for delayed free of objects: */
 	struct work_struct free_work;
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index a0baea2e96c8..084131db89d2 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -767,13 +767,17 @@ int msm_gem_sync_object(struct drm_gem_object *obj,
 void msm_gem_active_get(struct drm_gem_object *obj, struct msm_gpu *gpu)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
-	WARN_ON(!mutex_is_locked(&obj->dev->struct_mutex));
+	struct msm_drm_private *priv = obj->dev->dev_private;
+
+	might_sleep();
 	WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED);
 
 	if (!atomic_fetch_inc(&msm_obj->active_count)) {
+		mutex_lock(&priv->mm_lock);
 		msm_obj->gpu = gpu;
 		list_del_init(&msm_obj->mm_list);
 		list_add_tail(&msm_obj->mm_list, &gpu->active_list);
+		mutex_unlock(&priv->mm_lock);
 	}
 }
 
@@ -782,12 +786,14 @@ void msm_gem_active_put(struct drm_gem_object *obj)
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
 	struct msm_drm_private *priv = obj->dev->dev_private;
 
-	WARN_ON(!mutex_is_locked(&obj->dev->struct_mutex));
+	might_sleep();
 
 	if (!atomic_dec_return(&msm_obj->active_count)) {
+		mutex_lock(&priv->mm_lock);
 		msm_obj->gpu = NULL;
 		list_del_init(&msm_obj->mm_list);
 		list_add_tail(&msm_obj->mm_list, &priv->inactive_list);
+		mutex_unlock(&priv->mm_lock);
 	}
 }
 
@@ -942,13 +948,16 @@ static void free_object(struct msm_gem_object *msm_obj)
 {
 	struct drm_gem_object *obj = &msm_obj->base;
 	struct drm_device *dev = obj->dev;
+	struct msm_drm_private *priv = dev->dev_private;
 
 	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
 
 	/* object should not be on active list: */
 	WARN_ON(is_active(msm_obj));
 
+	mutex_lock(&priv->mm_lock);
 	list_del(&msm_obj->mm_list);
+	mutex_unlock(&priv->mm_lock);
 
 	msm_gem_lock(obj);
 
@@ -1127,14 +1136,9 @@ static struct drm_gem_object *_msm_gem_new(struct drm_device *dev,
 		mapping_set_gfp_mask(obj->filp->f_mapping, GFP_HIGHUSER);
 	}
 
-	if (struct_mutex_locked) {
-		WARN_ON(!mutex_is_locked(&dev->struct_mutex));
-		list_add_tail(&msm_obj->mm_list, &priv->inactive_list);
-	} else {
-		mutex_lock(&dev->struct_mutex);
-		list_add_tail(&msm_obj->mm_list, &priv->inactive_list);
-		mutex_unlock(&dev->struct_mutex);
-	}
+	mutex_lock(&priv->mm_lock);
+	list_add_tail(&msm_obj->mm_list, &priv->inactive_list);
+	mutex_unlock(&priv->mm_lock);
 
 	return obj;
 
@@ -1202,9 +1206,9 @@ struct drm_gem_object *msm_gem_import(struct drm_device *dev,
 
 	msm_gem_unlock(obj);
 
-	mutex_lock(&dev->struct_mutex);
+	mutex_lock(&priv->mm_lock);
 	list_add_tail(&msm_obj->mm_list, &priv->inactive_list);
-	mutex_unlock(&dev->struct_mutex);
+	mutex_unlock(&priv->mm_lock);
 
 	return obj;
 
diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c
index 2dc0ffa925b4..6be073b8ca08 100644
--- a/drivers/gpu/drm/msm/msm_gem_shrinker.c
+++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c
@@ -51,6 +51,8 @@ msm_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
 	if (!msm_gem_shrinker_lock(dev, &unlock))
 		return 0;
 
+	mutex_lock(&priv->mm_lock);
+
 	list_for_each_entry(msm_obj, &priv->inactive_list, mm_list) {
 		if (!msm_gem_trylock(&msm_obj->base))
 			continue;
@@ -59,6 +61,8 @@ msm_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
 		msm_gem_unlock(&msm_obj->base);
 	}
 
+	mutex_unlock(&priv->mm_lock);
+
 	if (unlock)
 		mutex_unlock(&dev->struct_mutex);
 
@@ -78,6 +82,8 @@ msm_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 	if (!msm_gem_shrinker_lock(dev, &unlock))
 		return SHRINK_STOP;
 
+	mutex_lock(&priv->mm_lock);
+
 	list_for_each_entry(msm_obj, &priv->inactive_list, mm_list) {
 		if (freed >= sc->nr_to_scan)
 			break;
@@ -90,6 +96,8 @@ msm_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 		msm_gem_unlock(&msm_obj->base);
 	}
 
+	mutex_unlock(&priv->mm_lock);
+
 	if (unlock)
 		mutex_unlock(&dev->struct_mutex);
 
@@ -112,6 +120,8 @@ msm_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr)
 	if (!msm_gem_shrinker_lock(dev, &unlock))
 		return NOTIFY_DONE;
 
+	mutex_lock(&priv->mm_lock);
+
 	list_for_each_entry(msm_obj, &priv->inactive_list, mm_list) {
 		if (!msm_gem_trylock(&msm_obj->base))
 			continue;
@@ -129,6 +139,8 @@ msm_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr)
 			break;
 	}
 
+	mutex_unlock(&priv->mm_lock);
+
 	if (unlock)
 		mutex_unlock(&dev->struct_mutex);
 
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index b937e1d3af01..09938ae114ec 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -94,7 +94,10 @@ struct msm_gpu {
 	struct msm_ringbuffer *rb[MSM_GPU_MAX_RINGS];
 	int nr_rings;
 
-	/* list of GEM active objects: */
+	/*
+	 * List of GEM active objects on this gpu.  Protected by
+	 * msm_drm_private::mm_lock
+	 */
 	struct list_head active_list;
 
 	/* does gpu need hw_init? */