diff --git a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
index adc60b25f8e6c61e51c7db37805fa24a89378fae..0af01a0ec601686254f62b1e445d1ee7f3644403 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
@@ -205,7 +205,8 @@ nvkm_firmware_dtor(struct nvkm_firmware *fw)
 		break;
 	case NVKM_FIRMWARE_IMG_DMA:
 		nvkm_memory_unref(&memory);
-		dma_free_coherent(fw->device->dev, sg_dma_len(&fw->mem.sgl), fw->img, fw->phys);
+		dma_free_noncoherent(fw->device->dev, sg_dma_len(&fw->mem.sgl),
+				     fw->img, fw->phys, DMA_TO_DEVICE);
 		break;
 	case NVKM_FIRMWARE_IMG_SGT:
 		nvkm_memory_unref(&memory);
@@ -236,10 +237,12 @@ nvkm_firmware_ctor(const struct nvkm_firmware_func *func, const char *name,
 		break;
 	case NVKM_FIRMWARE_IMG_DMA: {
 		dma_addr_t addr;
-
 		len = ALIGN(fw->len, PAGE_SIZE);
 
-		fw->img = dma_alloc_coherent(fw->device->dev, len, &addr, GFP_KERNEL);
+		fw->img = dma_alloc_noncoherent(fw->device->dev,
+						len, &addr,
+						DMA_TO_DEVICE,
+						GFP_KERNEL);
 		if (fw->img) {
 			memcpy(fw->img, src, fw->len);
 			fw->phys = addr;
diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c
index 80a480b12174680b859cd0468eb087c9ffba8055..a1c8545f1249a1ac669ea95b1dfe2afc4dd5a8eb 100644
--- a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c
+++ b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c
@@ -89,6 +89,12 @@ nvkm_falcon_fw_boot(struct nvkm_falcon_fw *fw, struct nvkm_subdev *user,
 		nvkm_falcon_fw_dtor_sigs(fw);
 	}
 
+	/* after last write to the img, sync dma mappings */
+	dma_sync_single_for_device(fw->fw.device->dev,
+				   fw->fw.phys,
+				   sg_dma_len(&fw->fw.mem.sgl),
+				   DMA_TO_DEVICE);
+
 	FLCNFW_DBG(fw, "resetting");
 	fw->func->reset(fw);