3 files changed, 70 insertions, 8 deletions

diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c
index f814eb4941c0..c273a4476f23 100644
--- a/drivers/gpu/host1x/bus.c
+++ b/drivers/gpu/host1x/bus.c
@@ -485,7 +485,7 @@ static int host1x_device_add(struct host1x *host1x,
 
 	err = host1x_device_parse_dt(device, driver);
 	if (err < 0) {
-		kfree(device);
+		put_device(&device->dev);
 		return err;
 	}
 
@@ -887,6 +887,20 @@ unlock:
 }
 EXPORT_SYMBOL(host1x_client_resume);
 
+/**
+ * host1x_bo_pin() - Create a DMA mapping for the buffer object
+ * @dev: Device onto which DMA map to
+ * @bo: Buffer object to map
+ * @dir: DMA direction
+ * @cache: Cache in which to store mapping, or NULL
+ *
+ * Creates a DMA mapping pointing to @bo for @dev. The refcount of @bo is incremented
+ * until host1x_bo_unpin is called.
+ *
+ * If @cache is specified, the mapping is also stored in the cache and not released
+ * until @bo is freed (refcount drops to zero). This improves performance when a buffer
+ * is pinned and unpinned frequently as in the case of display use.
+ */
 struct host1x_bo_mapping *host1x_bo_pin(struct device *dev, struct host1x_bo *bo,
 					enum dma_data_direction dir,
 					struct host1x_bo_cache *cache)
@@ -899,6 +913,7 @@ struct host1x_bo_mapping *host1x_bo_pin(struct device *dev, struct host1x_bo *bo
 		list_for_each_entry(mapping, &cache->mappings, entry) {
 			if (mapping->bo == bo && mapping->direction == dir) {
 				kref_get(&mapping->ref);
+				host1x_bo_get(bo);
 				goto unlock;
 			}
 		}
@@ -908,6 +923,8 @@ struct host1x_bo_mapping *host1x_bo_pin(struct device *dev, struct host1x_bo *bo
 	if (IS_ERR(mapping))
 		goto unlock;
 
+	host1x_bo_get(bo);
+
 	spin_lock(&mapping->bo->lock);
 	list_add_tail(&mapping->list, &bo->mappings);
 	spin_unlock(&mapping->bo->lock);
@@ -918,7 +935,12 @@ struct host1x_bo_mapping *host1x_bo_pin(struct device *dev, struct host1x_bo *bo
 
 		list_add_tail(&mapping->entry, &cache->mappings);
 
-		/* bump reference count to track the copy in the cache */
+		/*
+		 * Bump the mapping reference count to track the mapping in the cache,
+		 * but do not bump the BO's refcount. This allows the BO to still get freed,
+		 * triggering the release of the cache mapping through
+		 * host1x_bo_clear_cached_mappings.
+		 */
 		kref_get(&mapping->ref);
 	}
 
@@ -948,9 +970,17 @@ static void __host1x_bo_unpin(struct kref *ref)
 	mapping->bo->ops->unpin(mapping);
 }
 
+/**
+ * host1x_bo_unpin() - Release an established DMA mapping of a buffer object
+ * @mapping: Mapping to release
+ *
+ * Unmaps the given @mapping, unless it is cached. Decreases the refcount on
+ * the underlying buffer object.
+ */
 void host1x_bo_unpin(struct host1x_bo_mapping *mapping)
 {
 	struct host1x_bo_cache *cache = mapping->cache;
+	struct host1x_bo *bo = mapping->bo;
 
 	if (cache)
 		mutex_lock(&cache->lock);
@@ -959,5 +989,33 @@ void host1x_bo_unpin(struct host1x_bo_mapping *mapping)
 
 	if (cache)
 		mutex_unlock(&cache->lock);
+
+	host1x_bo_put(bo);
 }
 EXPORT_SYMBOL(host1x_bo_unpin);
+
+/**
+ * host1x_bo_clear_cached_mappings() - Remove all cached mappings pointing at a bo
+ * @bo: Buffer object to release mappings of
+ *
+ * Drops references to any mappings pointing to @bo left in any caches. This must
+ * be called by any host1x_bo implementers that may be pinned with caching enabled
+ * before freeing the bo.
+ */
+void host1x_bo_clear_cached_mappings(struct host1x_bo *bo)
+{
+	struct host1x_bo_mapping *mapping, *tmp;
+	struct host1x_bo_cache *cache;
+
+	list_for_each_entry_safe(mapping, tmp, &bo->mappings, list) {
+		cache = mapping->cache;
+		if (WARN_ON(!cache))
+			continue;
+
+		mutex_lock(&mapping->cache->lock);
+		WARN_ON(kref_read(&mapping->ref) != 1);
+		__host1x_bo_unpin(&mapping->ref);
+		mutex_unlock(&mapping->cache->lock);
+	}
+}
+EXPORT_SYMBOL(host1x_bo_clear_cached_mappings);
diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c
index 3ed49e1fd933..70bda32f1ff4 100644
--- a/drivers/gpu/host1x/job.c
+++ b/drivers/gpu/host1x/job.c
@@ -235,6 +235,8 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job)
 		}
 
 		if (host->domain) {
+			ssize_t map_err;
+
 			for_each_sgtable_sg(map->sgt, sg, j)
 				gather_size += sg->length;
 
@@ -248,11 +250,11 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job)
 				goto put;
 			}
 
-			err = iommu_map_sgtable(host->domain, iova_dma_addr(&host->iova, alloc),
-						map->sgt, IOMMU_READ);
-			if (err == 0) {
+			map_err = iommu_map_sgtable(host->domain, iova_dma_addr(&host->iova, alloc),
+						    map->sgt, IOMMU_READ);
+			if (map_err < 0) {
 				__free_iova(&host->iova, alloc);
-				err = -EINVAL;
+				err = map_err;
 				goto put;
 			}
 
diff --git a/drivers/gpu/host1x/mipi.c b/drivers/gpu/host1x/mipi.c
index 01513b775d89..988681423981 100644
--- a/drivers/gpu/host1x/mipi.c
+++ b/drivers/gpu/host1x/mipi.c
@@ -114,8 +114,10 @@ struct tegra_mipi_device *tegra_mipi_request(struct device *device,
 	if (err < 0)
 		return ERR_PTR(err);
 
-	if (provider.np != args.np)
-		return ERR_PTR(-ENODEV);
+	if (provider.np != args.np) {
+		err = -ENODEV;
+		goto out;
+	}
 
 	mipidev = kzalloc_obj(*mipidev);
 	if (!mipidev) {