diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index c0b5373e90d7..34827fe807d4 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -1793,5 +1793,9 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev)
 	else
 		adreno_gpu->ubwc_config.highest_bank_bit = 14;
 
+	/* a5xx only supports UBWC 1.0, these are not configurable */
+	adreno_gpu->ubwc_config.macrotile_mode = 0;
+	adreno_gpu->ubwc_config.ubwc_swizzle = 0x7;
+
 	return gpu;
 }
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index bcaec86ac67a..7c2fdd1e7684 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -493,24 +493,17 @@ static void a6xx_set_cp_protect(struct msm_gpu *gpu)
 
 static void a6xx_calc_ubwc_config(struct adreno_gpu *gpu)
 {
-	/* Unknown, introduced with A650 family, related to UBWC mode/ver 4 */
 	gpu->ubwc_config.rgb565_predicator = 0;
-	/* Unknown, introduced with A650 family */
 	gpu->ubwc_config.uavflagprd_inv = 0;
-	/* Whether the minimum access length is 64 bits */
 	gpu->ubwc_config.min_acc_len = 0;
-	/* Entirely magic, per-GPU-gen value */
-	gpu->ubwc_config.ubwc_mode = 0;
-	/*
-	 * The Highest Bank Bit value represents the bit of the highest DDR bank.
-	 * This should ideally use DRAM type detection.
-	 */
+	gpu->ubwc_config.ubwc_swizzle = 0x6;
+	gpu->ubwc_config.macrotile_mode = 0;
 	gpu->ubwc_config.highest_bank_bit = 15;
 
 	if (adreno_is_a610(gpu)) {
 		gpu->ubwc_config.highest_bank_bit = 13;
 		gpu->ubwc_config.min_acc_len = 1;
-		gpu->ubwc_config.ubwc_mode = 1;
+		gpu->ubwc_config.ubwc_swizzle = 0x7;
 	}
 
 	if (adreno_is_a618(gpu))
@@ -536,6 +529,7 @@ static void a6xx_calc_ubwc_config(struct adreno_gpu *gpu)
 		gpu->ubwc_config.amsbc = 1;
 		gpu->ubwc_config.rgb565_predicator = 1;
 		gpu->ubwc_config.uavflagprd_inv = 2;
+		gpu->ubwc_config.macrotile_mode = 1;
 	}
 
 	if (adreno_is_7c3(gpu)) {
@@ -543,12 +537,12 @@ static void a6xx_calc_ubwc_config(struct adreno_gpu *gpu)
 		gpu->ubwc_config.amsbc = 1;
 		gpu->ubwc_config.rgb565_predicator = 1;
 		gpu->ubwc_config.uavflagprd_inv = 2;
+		gpu->ubwc_config.macrotile_mode = 1;
 	}
 
 	if (adreno_is_a702(gpu)) {
 		gpu->ubwc_config.highest_bank_bit = 14;
 		gpu->ubwc_config.min_acc_len = 1;
-		gpu->ubwc_config.ubwc_mode = 0;
 	}
 }
 
@@ -564,21 +558,26 @@ static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
 	u32 hbb = adreno_gpu->ubwc_config.highest_bank_bit - 13;
 	u32 hbb_hi = hbb >> 2;
 	u32 hbb_lo = hbb & 3;
+	u32 ubwc_mode = adreno_gpu->ubwc_config.ubwc_swizzle & 1;
+	u32 level2_swizzling_dis = !(adreno_gpu->ubwc_config.ubwc_swizzle & 2);
 
 	gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL,
+		  level2_swizzling_dis << 12 |
 		  adreno_gpu->ubwc_config.rgb565_predicator << 11 |
 		  hbb_hi << 10 | adreno_gpu->ubwc_config.amsbc << 4 |
 		  adreno_gpu->ubwc_config.min_acc_len << 3 |
-		  hbb_lo << 1 | adreno_gpu->ubwc_config.ubwc_mode);
+		  hbb_lo << 1 | ubwc_mode);
 
-	gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, hbb_hi << 4 |
+	gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL,
+		  level2_swizzling_dis << 6 | hbb_hi << 4 |
 		  adreno_gpu->ubwc_config.min_acc_len << 3 |
-		  hbb_lo << 1 | adreno_gpu->ubwc_config.ubwc_mode);
+		  hbb_lo << 1 | ubwc_mode);
 
-	gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL, hbb_hi << 10 |
+	gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL,
+		  level2_swizzling_dis << 12 | hbb_hi << 10 |
 		  adreno_gpu->ubwc_config.uavflagprd_inv << 4 |
 		  adreno_gpu->ubwc_config.min_acc_len << 3 |
-		  hbb_lo << 1 | adreno_gpu->ubwc_config.ubwc_mode);
+		  hbb_lo << 1 | ubwc_mode);
 
 	if (adreno_is_a7xx(adreno_gpu))
 		gpu_write(gpu, REG_A7XX_GRAS_NC_MODE_CNTL,
@@ -586,6 +585,9 @@ static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
 
 	gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL,
 		  adreno_gpu->ubwc_config.min_acc_len << 23 | hbb_lo << 21);
+
+	gpu_write(gpu, REG_A6XX_RBBM_NC_MODE_CNTL,
+		  adreno_gpu->ubwc_config.macrotile_mode);
 }
 
 static int a6xx_cp_init(struct msm_gpu *gpu)
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index 1ab523a163a0..db42f8af978d 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -191,12 +191,42 @@ struct adreno_gpu {
 	const struct firmware *fw[ADRENO_FW_MAX];
 
 	struct {
+		/**
+		 * @rgb565_predicator: Unknown, introduced with A650 family,
+		 * related to UBWC mode/ver 4
+		 */
 		u32 rgb565_predicator;
+		/** @uavflagprd_inv: Unknown, introduced with A650 family */
 		u32 uavflagprd_inv;
+		/** @min_acc_len: Whether the minimum access length is 64 bits */
 		u32 min_acc_len;
-		u32 ubwc_mode;
+		/**
+		 * @ubwc_swizzle: Whether to enable level 1, 2 & 3 bank swizzling.
+		 *
+		 * UBWC 1.0 always enables all three levels.
+		 * UBWC 2.0 removes level 1 bank swizzling, leaving levels 2 & 3.
+		 * UBWC 4.0 adds the optional ability to disable levels 2 & 3.
+		 *
+		 * This is a bitmask where BIT(0) enables level 1, BIT(1)
+		 * controls level 2, and BIT(2) enables level 3.
+		 */
+		u32 ubwc_swizzle;
+		/**
+		 * @highest_bank_bit: Highest Bank Bit
+		 *
+		 * The Highest Bank Bit value represents the bit of the highest
+		 * DDR bank.  This should ideally use DRAM type detection.
+		 */
 		u32 highest_bank_bit;
 		u32 amsbc;
+		/**
+		 * @macrotile_mode: Macrotile Mode
+		 *
+		 * Whether to use 4-channel macrotiling mode or the newer
+		 * 8-channel macrotiling mode introduced in UBWC 3.1. 0 is
+		 * 4-channel and 1 is 8-channel.
+		 */
+		u32 macrotile_mode;
 	} ubwc_config;
 
 	/*