drm/msm/a6xx: Add support for using system cache on MMU500 based targets

GPU targets with an MMU-500 attached have a slightly different process for
enabling system cache. Use the compatible string on the IOMMU phandle
to see if an MMU-500 is attached and modify the programming sequence
accordingly.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>

drivers/gpu/drm/msm/adreno/a6xx_gpu.c

@@ -1040,6 +1040,8 @@ static void a6xx_llc_deactivate(struct a6xx_gpu *a6xx_gpu)
 
 static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu)
 {
+	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
+	struct msm_gpu *gpu = &adreno_gpu->base;
 	u32 cntl1_regval = 0;
 
 	if (IS_ERR(a6xx_gpu->llc_mmio))
@@ -1053,11 +1055,17 @@ static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu)
 			       (gpu_scid << 15) | (gpu_scid << 20);
 	}
 
+	/*
+	 * For targets with a MMU500, activate the slice but don't program the
+	 * register.  The XBL will take care of that.
+	 */
 	if (!llcc_slice_activate(a6xx_gpu->htw_llc_slice)) {
-		u32 gpuhtw_scid = llcc_get_slice_id(a6xx_gpu->htw_llc_slice);
+		if (!a6xx_gpu->have_mmu500) {
+			u32 gpuhtw_scid = llcc_get_slice_id(a6xx_gpu->htw_llc_slice);
 
-		gpuhtw_scid &= 0x1f;
-		cntl1_regval |= FIELD_PREP(GENMASK(29, 25), gpuhtw_scid);
+			gpuhtw_scid &= 0x1f;
+			cntl1_regval |= FIELD_PREP(GENMASK(29, 25), gpuhtw_scid);
+		}
 	}
 
 	if (cntl1_regval) {
@@ -1065,13 +1073,20 @@ static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu)
 		 * Program the slice IDs for the various GPU blocks and GPU MMU
 		 * pagetables
 		 */
-		a6xx_llc_write(a6xx_gpu, REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_1, cntl1_regval);
-
-		/*
-		 * Program cacheability overrides to not allocate cache lines on
-		 * a write miss
-		 */
-		a6xx_llc_rmw(a6xx_gpu, REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_0, 0xF, 0x03);
+		if (a6xx_gpu->have_mmu500)
+			gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL1, GENMASK(24, 0),
+				cntl1_regval);
+		else {
+			a6xx_llc_write(a6xx_gpu,
+				REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_1, cntl1_regval);
+
+			/*
+			 * Program cacheability overrides to not allocate cache
+			 * lines on a write miss
+			 */
+			a6xx_llc_rmw(a6xx_gpu,
+				REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_0, 0xF, 0x03);
+		}
 	}
 }
 
@@ -1084,10 +1099,21 @@ static void a6xx_llc_slices_destroy(struct a6xx_gpu *a6xx_gpu)
 static void a6xx_llc_slices_init(struct platform_device *pdev,
 		struct a6xx_gpu *a6xx_gpu)
 {
+	struct device_node *phandle;
+
 	a6xx_gpu->llc_mmio = msm_ioremap(pdev, "cx_mem", "gpu_cx");
 	if (IS_ERR(a6xx_gpu->llc_mmio))
 		return;
 
+	/*
+	 * There is a different programming path for targets with an mmu500
+	 * attached, so detect if that is the case
+	 */
+	phandle = of_parse_phandle(pdev->dev.of_node, "iommus", 0);
+	a6xx_gpu->have_mmu500 = (phandle &&
+		of_device_is_compatible(phandle, "arm,mmu-500"));
+	of_node_put(phandle);
+
 	a6xx_gpu->llc_slice = llcc_slice_getd(LLCC_GPU);
 	a6xx_gpu->htw_llc_slice = llcc_slice_getd(LLCC_GPUHTW);
 

drivers/gpu/drm/msm/adreno/a6xx_gpu.h

@@ -32,6 +32,7 @@ struct a6xx_gpu {
 	void __iomem *llc_mmio;
 	void *llc_slice;
 	void *htw_llc_slice;
+	bool have_mmu500;
 };
 
 #define to_a6xx_gpu(x) container_of(x, struct a6xx_gpu, base)