drm/tegra: Acquire a reference to the IOVA cache

The IOVA API uses a memory cache to allocate IOVA nodes from. To make
sure that this cache is available, obtain a reference to it and release
the reference when the cache is no longer needed.

On 64-bit ARM this is hidden by the fact that the DMA mapping API gets
that reference and never releases it. On 32-bit ARM, however, the DMA
mapping API doesn't do that, so allocation of IOVA nodes fails.

Fixes: ad92601 ("drm/tegra: Add Tegra DRM allocation API")
Reviewed-by: Dmitry Osipenko <digetx@gmail.com>
Tested-by: Dmitry Osipenko <digetx@gmail.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>

drivers/gpu/drm/tegra/drm.c

@@ -113,6 +113,10 @@ static int tegra_drm_load(struct drm_device *drm, unsigned long flags)
 			goto free;
 		}
 
+		err = iova_cache_get();
+		if (err < 0)
+			goto domain;
+
 		geometry = &tegra->domain->geometry;
 		gem_start = geometry->aperture_start;
 		gem_end = geometry->aperture_end - CARVEOUT_SZ;
@@ -207,8 +211,11 @@ static int tegra_drm_load(struct drm_device *drm, unsigned long flags)
 		mutex_destroy(&tegra->mm_lock);
 		drm_mm_takedown(&tegra->mm);
 		put_iova_domain(&tegra->carveout.domain);
-		iommu_domain_free(tegra->domain);
+		iova_cache_put();
 	}
+domain:
+	if (tegra->domain)
+		iommu_domain_free(tegra->domain);
 free:
 	kfree(tegra);
 	return err;
@@ -233,6 +240,7 @@ static void tegra_drm_unload(struct drm_device *drm)
 		mutex_destroy(&tegra->mm_lock);
 		drm_mm_takedown(&tegra->mm);
 		put_iova_domain(&tegra->carveout.domain);
+		iova_cache_put();
 		iommu_domain_free(tegra->domain);
 	}