1 files changed, 372 insertions, 88 deletions

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index b4d8e1b01ee4..9c5e4618aa0a 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -149,7 +149,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 
 	a6xx_set_pagetable(a6xx_gpu, ring, submit->queue->ctx);
 
-	get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP_0_LO,
+	get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP(0),
 		rbmemptr_stats(ring, index, cpcycles_start));
 
 	/*
@@ -157,7 +157,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	 * GPU registers so we need to add 0x1a800 to the register value on A630
 	 * to get the right value from PM4.
 	 */
-	get_stats_counter(ring, REG_A6XX_GMU_ALWAYS_ON_COUNTER_L + 0x1a800,
+	get_stats_counter(ring, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO,
 		rbmemptr_stats(ring, index, alwayson_start));
 
 	/* Invalidate CCU depth and color */
@@ -185,9 +185,9 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 		}
 	}
 
-	get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP_0_LO,
+	get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP(0),
 		rbmemptr_stats(ring, index, cpcycles_end));
-	get_stats_counter(ring, REG_A6XX_GMU_ALWAYS_ON_COUNTER_L + 0x1a800,
+	get_stats_counter(ring, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO,
 		rbmemptr_stats(ring, index, alwayson_end));
 
 	/* Write the fence to the scratch register */
@@ -206,8 +206,8 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	OUT_RING(ring, submit->seqno);
 
 	trace_msm_gpu_submit_flush(submit,
-		gmu_read64(&a6xx_gpu->gmu, REG_A6XX_GMU_ALWAYS_ON_COUNTER_L,
-			REG_A6XX_GMU_ALWAYS_ON_COUNTER_H));
+		gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO,
+			REG_A6XX_CP_ALWAYS_ON_COUNTER_HI));
 
 	a6xx_flush(gpu, ring);
 }
@@ -427,6 +427,59 @@ const struct adreno_reglist a650_hwcg[] = {
 	{},
 };
 
+const struct adreno_reglist a660_hwcg[] = {
+	{REG_A6XX_RBBM_CLOCK_CNTL_SP0, 0x02222222},
+	{REG_A6XX_RBBM_CLOCK_CNTL2_SP0, 0x02222220},
+	{REG_A6XX_RBBM_CLOCK_DELAY_SP0, 0x00000080},
+	{REG_A6XX_RBBM_CLOCK_HYST_SP0, 0x0000F3CF},
+	{REG_A6XX_RBBM_CLOCK_CNTL_TP0, 0x22222222},
+	{REG_A6XX_RBBM_CLOCK_CNTL2_TP0, 0x22222222},
+	{REG_A6XX_RBBM_CLOCK_CNTL3_TP0, 0x22222222},
+	{REG_A6XX_RBBM_CLOCK_CNTL4_TP0, 0x00022222},
+	{REG_A6XX_RBBM_CLOCK_DELAY_TP0, 0x11111111},
+	{REG_A6XX_RBBM_CLOCK_DELAY2_TP0, 0x11111111},
+	{REG_A6XX_RBBM_CLOCK_DELAY3_TP0, 0x11111111},
+	{REG_A6XX_RBBM_CLOCK_DELAY4_TP0, 0x00011111},
+	{REG_A6XX_RBBM_CLOCK_HYST_TP0, 0x77777777},
+	{REG_A6XX_RBBM_CLOCK_HYST2_TP0, 0x77777777},
+	{REG_A6XX_RBBM_CLOCK_HYST3_TP0, 0x77777777},
+	{REG_A6XX_RBBM_CLOCK_HYST4_TP0, 0x00077777},
+	{REG_A6XX_RBBM_CLOCK_CNTL_RB0, 0x22222222},
+	{REG_A6XX_RBBM_CLOCK_CNTL2_RB0, 0x01002222},
+	{REG_A6XX_RBBM_CLOCK_CNTL_CCU0, 0x00002220},
+	{REG_A6XX_RBBM_CLOCK_HYST_RB_CCU0, 0x00040F00},
+	{REG_A6XX_RBBM_CLOCK_CNTL_RAC, 0x25222022},
+	{REG_A6XX_RBBM_CLOCK_CNTL2_RAC, 0x00005555},
+	{REG_A6XX_RBBM_CLOCK_DELAY_RAC, 0x00000011},
+	{REG_A6XX_RBBM_CLOCK_HYST_RAC, 0x00445044},
+	{REG_A6XX_RBBM_CLOCK_CNTL_TSE_RAS_RBBM, 0x04222222},
+	{REG_A6XX_RBBM_CLOCK_MODE_VFD, 0x00002222},
+	{REG_A6XX_RBBM_CLOCK_MODE_GPC, 0x00222222},
+	{REG_A6XX_RBBM_CLOCK_DELAY_HLSQ_2, 0x00000002},
+	{REG_A6XX_RBBM_CLOCK_MODE_HLSQ, 0x00002222},
+	{REG_A6XX_RBBM_CLOCK_DELAY_TSE_RAS_RBBM, 0x00004000},
+	{REG_A6XX_RBBM_CLOCK_DELAY_VFD, 0x00002222},
+	{REG_A6XX_RBBM_CLOCK_DELAY_GPC, 0x00000200},
+	{REG_A6XX_RBBM_CLOCK_DELAY_HLSQ, 0x00000000},
+	{REG_A6XX_RBBM_CLOCK_HYST_TSE_RAS_RBBM, 0x00000000},
+	{REG_A6XX_RBBM_CLOCK_HYST_VFD, 0x00000000},
+	{REG_A6XX_RBBM_CLOCK_HYST_GPC, 0x04104004},
+	{REG_A6XX_RBBM_CLOCK_HYST_HLSQ, 0x00000000},
+	{REG_A6XX_RBBM_CLOCK_CNTL_TEX_FCHE, 0x00000222},
+	{REG_A6XX_RBBM_CLOCK_DELAY_TEX_FCHE, 0x00000111},
+	{REG_A6XX_RBBM_CLOCK_HYST_TEX_FCHE, 0x00000000},
+	{REG_A6XX_RBBM_CLOCK_CNTL_UCHE, 0x22222222},
+	{REG_A6XX_RBBM_CLOCK_HYST_UCHE, 0x00000004},
+	{REG_A6XX_RBBM_CLOCK_DELAY_UCHE, 0x00000002},
+	{REG_A6XX_RBBM_ISDB_CNT, 0x00000182},
+	{REG_A6XX_RBBM_RAC_THRESHOLD_CNT, 0x00000000},
+	{REG_A6XX_RBBM_SP_HYST_CNT, 0x00000000},
+	{REG_A6XX_RBBM_CLOCK_CNTL_GMU_GX, 0x00000222},
+	{REG_A6XX_RBBM_CLOCK_DELAY_GMU_GX, 0x00000111},
+	{REG_A6XX_RBBM_CLOCK_HYST_GMU_GX, 0x00000555},
+	{},
+};
+
 static void a6xx_set_hwcg(struct msm_gpu *gpu, bool state)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
@@ -462,6 +515,162 @@ static void a6xx_set_hwcg(struct msm_gpu *gpu, bool state)
 	gpu_write(gpu, REG_A6XX_RBBM_CLOCK_CNTL, state ? clock_cntl_on : 0);
 }
 
+/* For a615, a616, a618, A619, a630, a640 and a680 */
+static const u32 a6xx_protect[] = {
+	A6XX_PROTECT_RDONLY(0x00000, 0x04ff),
+	A6XX_PROTECT_RDONLY(0x00501, 0x0005),
+	A6XX_PROTECT_RDONLY(0x0050b, 0x02f4),
+	A6XX_PROTECT_NORDWR(0x0050e, 0x0000),
+	A6XX_PROTECT_NORDWR(0x00510, 0x0000),
+	A6XX_PROTECT_NORDWR(0x00534, 0x0000),
+	A6XX_PROTECT_NORDWR(0x00800, 0x0082),
+	A6XX_PROTECT_NORDWR(0x008a0, 0x0008),
+	A6XX_PROTECT_NORDWR(0x008ab, 0x0024),
+	A6XX_PROTECT_RDONLY(0x008de, 0x00ae),
+	A6XX_PROTECT_NORDWR(0x00900, 0x004d),
+	A6XX_PROTECT_NORDWR(0x0098d, 0x0272),
+	A6XX_PROTECT_NORDWR(0x00e00, 0x0001),
+	A6XX_PROTECT_NORDWR(0x00e03, 0x000c),
+	A6XX_PROTECT_NORDWR(0x03c00, 0x00c3),
+	A6XX_PROTECT_RDONLY(0x03cc4, 0x1fff),
+	A6XX_PROTECT_NORDWR(0x08630, 0x01cf),
+	A6XX_PROTECT_NORDWR(0x08e00, 0x0000),
+	A6XX_PROTECT_NORDWR(0x08e08, 0x0000),
+	A6XX_PROTECT_NORDWR(0x08e50, 0x001f),
+	A6XX_PROTECT_NORDWR(0x09624, 0x01db),
+	A6XX_PROTECT_NORDWR(0x09e70, 0x0001),
+	A6XX_PROTECT_NORDWR(0x09e78, 0x0187),
+	A6XX_PROTECT_NORDWR(0x0a630, 0x01cf),
+	A6XX_PROTECT_NORDWR(0x0ae02, 0x0000),
+	A6XX_PROTECT_NORDWR(0x0ae50, 0x032f),
+	A6XX_PROTECT_NORDWR(0x0b604, 0x0000),
+	A6XX_PROTECT_NORDWR(0x0be02, 0x0001),
+	A6XX_PROTECT_NORDWR(0x0be20, 0x17df),
+	A6XX_PROTECT_NORDWR(0x0f000, 0x0bff),
+	A6XX_PROTECT_RDONLY(0x0fc00, 0x1fff),
+	A6XX_PROTECT_NORDWR(0x11c00, 0x0000), /* note: infinite range */
+};
+
+/* These are for a620 and a650 */
+static const u32 a650_protect[] = {
+	A6XX_PROTECT_RDONLY(0x00000, 0x04ff),
+	A6XX_PROTECT_RDONLY(0x00501, 0x0005),
+	A6XX_PROTECT_RDONLY(0x0050b, 0x02f4),
+	A6XX_PROTECT_NORDWR(0x0050e, 0x0000),
+	A6XX_PROTECT_NORDWR(0x00510, 0x0000),
+	A6XX_PROTECT_NORDWR(0x00534, 0x0000),
+	A6XX_PROTECT_NORDWR(0x00800, 0x0082),
+	A6XX_PROTECT_NORDWR(0x008a0, 0x0008),
+	A6XX_PROTECT_NORDWR(0x008ab, 0x0024),
+	A6XX_PROTECT_RDONLY(0x008de, 0x00ae),
+	A6XX_PROTECT_NORDWR(0x00900, 0x004d),
+	A6XX_PROTECT_NORDWR(0x0098d, 0x0272),
+	A6XX_PROTECT_NORDWR(0x00e00, 0x0001),
+	A6XX_PROTECT_NORDWR(0x00e03, 0x000c),
+	A6XX_PROTECT_NORDWR(0x03c00, 0x00c3),
+	A6XX_PROTECT_RDONLY(0x03cc4, 0x1fff),
+	A6XX_PROTECT_NORDWR(0x08630, 0x01cf),
+	A6XX_PROTECT_NORDWR(0x08e00, 0x0000),
+	A6XX_PROTECT_NORDWR(0x08e08, 0x0000),
+	A6XX_PROTECT_NORDWR(0x08e50, 0x001f),
+	A6XX_PROTECT_NORDWR(0x08e80, 0x027f),
+	A6XX_PROTECT_NORDWR(0x09624, 0x01db),
+	A6XX_PROTECT_NORDWR(0x09e60, 0x0011),
+	A6XX_PROTECT_NORDWR(0x09e78, 0x0187),
+	A6XX_PROTECT_NORDWR(0x0a630, 0x01cf),
+	A6XX_PROTECT_NORDWR(0x0ae02, 0x0000),
+	A6XX_PROTECT_NORDWR(0x0ae50, 0x032f),
+	A6XX_PROTECT_NORDWR(0x0b604, 0x0000),
+	A6XX_PROTECT_NORDWR(0x0b608, 0x0007),
+	A6XX_PROTECT_NORDWR(0x0be02, 0x0001),
+	A6XX_PROTECT_NORDWR(0x0be20, 0x17df),
+	A6XX_PROTECT_NORDWR(0x0f000, 0x0bff),
+	A6XX_PROTECT_RDONLY(0x0fc00, 0x1fff),
+	A6XX_PROTECT_NORDWR(0x18400, 0x1fff),
+	A6XX_PROTECT_NORDWR(0x1a800, 0x1fff),
+	A6XX_PROTECT_NORDWR(0x1f400, 0x0443),
+	A6XX_PROTECT_RDONLY(0x1f844, 0x007b),
+	A6XX_PROTECT_NORDWR(0x1f887, 0x001b),
+	A6XX_PROTECT_NORDWR(0x1f8c0, 0x0000), /* note: infinite range */
+};
+
+/* These are for a635 and a660 */
+static const u32 a660_protect[] = {
+	A6XX_PROTECT_RDONLY(0x00000, 0x04ff),
+	A6XX_PROTECT_RDONLY(0x00501, 0x0005),
+	A6XX_PROTECT_RDONLY(0x0050b, 0x02f4),
+	A6XX_PROTECT_NORDWR(0x0050e, 0x0000),
+	A6XX_PROTECT_NORDWR(0x00510, 0x0000),
+	A6XX_PROTECT_NORDWR(0x00534, 0x0000),
+	A6XX_PROTECT_NORDWR(0x00800, 0x0082),
+	A6XX_PROTECT_NORDWR(0x008a0, 0x0008),
+	A6XX_PROTECT_NORDWR(0x008ab, 0x0024),
+	A6XX_PROTECT_RDONLY(0x008de, 0x00ae),
+	A6XX_PROTECT_NORDWR(0x00900, 0x004d),
+	A6XX_PROTECT_NORDWR(0x0098d, 0x0272),
+	A6XX_PROTECT_NORDWR(0x00e00, 0x0001),
+	A6XX_PROTECT_NORDWR(0x00e03, 0x000c),
+	A6XX_PROTECT_NORDWR(0x03c00, 0x00c3),
+	A6XX_PROTECT_RDONLY(0x03cc4, 0x1fff),
+	A6XX_PROTECT_NORDWR(0x08630, 0x01cf),
+	A6XX_PROTECT_NORDWR(0x08e00, 0x0000),
+	A6XX_PROTECT_NORDWR(0x08e08, 0x0000),
+	A6XX_PROTECT_NORDWR(0x08e50, 0x001f),
+	A6XX_PROTECT_NORDWR(0x08e80, 0x027f),
+	A6XX_PROTECT_NORDWR(0x09624, 0x01db),
+	A6XX_PROTECT_NORDWR(0x09e60, 0x0011),
+	A6XX_PROTECT_NORDWR(0x09e78, 0x0187),
+	A6XX_PROTECT_NORDWR(0x0a630, 0x01cf),
+	A6XX_PROTECT_NORDWR(0x0ae02, 0x0000),
+	A6XX_PROTECT_NORDWR(0x0ae50, 0x012f),
+	A6XX_PROTECT_NORDWR(0x0b604, 0x0000),
+	A6XX_PROTECT_NORDWR(0x0b608, 0x0006),
+	A6XX_PROTECT_NORDWR(0x0be02, 0x0001),
+	A6XX_PROTECT_NORDWR(0x0be20, 0x015f),
+	A6XX_PROTECT_NORDWR(0x0d000, 0x05ff),
+	A6XX_PROTECT_NORDWR(0x0f000, 0x0bff),
+	A6XX_PROTECT_RDONLY(0x0fc00, 0x1fff),
+	A6XX_PROTECT_NORDWR(0x18400, 0x1fff),
+	A6XX_PROTECT_NORDWR(0x1a400, 0x1fff),
+	A6XX_PROTECT_NORDWR(0x1f400, 0x0443),
+	A6XX_PROTECT_RDONLY(0x1f844, 0x007b),
+	A6XX_PROTECT_NORDWR(0x1f860, 0x0000),
+	A6XX_PROTECT_NORDWR(0x1f887, 0x001b),
+	A6XX_PROTECT_NORDWR(0x1f8c0, 0x0000), /* note: infinite range */
+};
+
+static void a6xx_set_cp_protect(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	const u32 *regs = a6xx_protect;
+	unsigned i, count = ARRAY_SIZE(a6xx_protect), count_max = 32;
+
+	BUILD_BUG_ON(ARRAY_SIZE(a6xx_protect) > 32);
+	BUILD_BUG_ON(ARRAY_SIZE(a650_protect) > 48);
+
+	if (adreno_is_a650(adreno_gpu)) {
+		regs = a650_protect;
+		count = ARRAY_SIZE(a650_protect);
+		count_max = 48;
+	} else if (adreno_is_a660(adreno_gpu)) {
+		regs = a660_protect;
+		count = ARRAY_SIZE(a660_protect);
+		count_max = 48;
+	}
+
+	/*
+	 * Enable access protection to privileged registers, fault on an access
+	 * protect violation and select the last span to protect from the start
+	 * address all the way to the end of the register address space
+	 */
+	gpu_write(gpu, REG_A6XX_CP_PROTECT_CNTL, BIT(0) | BIT(1) | BIT(3));
+
+	for (i = 0; i < count - 1; i++)
+		gpu_write(gpu, REG_A6XX_CP_PROTECT(i), regs[i]);
+	/* last CP_PROTECT to have "infinite" length on the last entry */
+	gpu_write(gpu, REG_A6XX_CP_PROTECT(count_max - 1), regs[i]);
+}
+
 static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
@@ -477,7 +686,7 @@ static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
 	if (adreno_is_a640(adreno_gpu))
 		amsbc = 1;
 
-	if (adreno_is_a650(adreno_gpu)) {
+	if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu)) {
 		/* TODO: get ddr type from bootloader and use 2 for LPDDR4 */
 		lower_bit = 3;
 		amsbc = 1;
@@ -489,7 +698,7 @@ static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
 		rgb565_predicator << 11 | amsbc << 4 | lower_bit << 1);
 	gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, lower_bit << 1);
 	gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL,
-		uavflagprd_inv >> 4 | lower_bit << 1);
+		uavflagprd_inv << 4 | lower_bit << 1);
 	gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL, lower_bit << 21);
 }
 
@@ -541,6 +750,11 @@ static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
 	 * Targets up to a640 (a618, a630 and a640) need to check for a
 	 * microcode version that is patched to support the whereami opcode or
 	 * one that is new enough to include it by default.
+	 *
+	 * a650 tier targets don't need whereami but still need to be
+	 * equal to or newer than 0.95 for other security fixes
+	 *
+	 * a660 targets have all the critical security fixes from the start
 	 */
 	if (adreno_is_a618(adreno_gpu) || adreno_is_a630(adreno_gpu) ||
 		adreno_is_a640(adreno_gpu)) {
@@ -564,27 +778,20 @@ static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
 		DRM_DEV_ERROR(&gpu->pdev->dev,
 			"a630 SQE ucode is too old. Have version %x need at least %x\n",
 			buf[0] & 0xfff, 0x190);
-	}  else {
-		/*
-		 * a650 tier targets don't need whereami but still need to be
-		 * equal to or newer than 0.95 for other security fixes
-		 */
-		if (adreno_is_a650(adreno_gpu)) {
-			if ((buf[0] & 0xfff) >= 0x095) {
-				ret = true;
-				goto out;
-			}
-
-			DRM_DEV_ERROR(&gpu->pdev->dev,
-				"a650 SQE ucode is too old. Have version %x need at least %x\n",
-				buf[0] & 0xfff, 0x095);
+	} else if (adreno_is_a650(adreno_gpu)) {
+		if ((buf[0] & 0xfff) >= 0x095) {
+			ret = true;
+			goto out;
 		}
 
-		/*
-		 * When a660 is added those targets should return true here
-		 * since those have all the critical security fixes built in
-		 * from the start
-		 */
+		DRM_DEV_ERROR(&gpu->pdev->dev,
+			"a650 SQE ucode is too old. Have version %x need at least %x\n",
+			buf[0] & 0xfff, 0x095);
+	} else if (adreno_is_a660(adreno_gpu)) {
+		ret = true;
+	} else {
+		DRM_DEV_ERROR(&gpu->pdev->dev,
+			"unknown GPU, add it to a6xx_ucode_check_version()!!\n");
 	}
 out:
 	msm_gem_put_vaddr(obj);
@@ -620,8 +827,8 @@ static int a6xx_ucode_init(struct msm_gpu *gpu)
 		}
 	}
 
-	gpu_write64(gpu, REG_A6XX_CP_SQE_INSTR_BASE_LO,
-		REG_A6XX_CP_SQE_INSTR_BASE_HI, a6xx_gpu->sqe_iova);
+	gpu_write64(gpu, REG_A6XX_CP_SQE_INSTR_BASE,
+		REG_A6XX_CP_SQE_INSTR_BASE+1, a6xx_gpu->sqe_iova);
 
 	return 0;
 }
@@ -690,7 +897,7 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	a6xx_set_hwcg(gpu, true);
 
 	/* VBIF/GBIF start*/
-	if (adreno_is_a640(adreno_gpu) || adreno_is_a650(adreno_gpu)) {
+	if (adreno_is_a640(adreno_gpu) || adreno_is_a650_family(adreno_gpu)) {
 		gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE0, 0x00071620);
 		gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE1, 0x00071620);
 		gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE2, 0x00071620);
@@ -715,7 +922,7 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	gpu_write(gpu, REG_A6XX_UCHE_WRITE_THRU_BASE_LO, 0xfffff000);
 	gpu_write(gpu, REG_A6XX_UCHE_WRITE_THRU_BASE_HI, 0x0001ffff);
 
-	if (!adreno_is_a650(adreno_gpu)) {
+	if (!adreno_is_a650_family(adreno_gpu)) {
 		/* Set the GMEM VA range [0x100000:0x100000 + gpu->gmem - 1] */
 		gpu_write64(gpu, REG_A6XX_UCHE_GMEM_RANGE_MIN_LO,
 			REG_A6XX_UCHE_GMEM_RANGE_MIN_HI, 0x00100000);
@@ -728,22 +935,27 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	gpu_write(gpu, REG_A6XX_UCHE_FILTER_CNTL, 0x804);
 	gpu_write(gpu, REG_A6XX_UCHE_CACHE_WAYS, 0x4);
 
-	if (adreno_is_a640(adreno_gpu) || adreno_is_a650(adreno_gpu))
+	if (adreno_is_a640(adreno_gpu) || adreno_is_a650_family(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_2, 0x02000140);
 	else
 		gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_2, 0x010000c0);
 	gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_1, 0x8040362c);
 
+	if (adreno_is_a660(adreno_gpu))
+		gpu_write(gpu, REG_A6XX_CP_LPAC_PROG_FIFO_SIZE, 0x00000020);
+
 	/* Setting the mem pool size */
 	gpu_write(gpu, REG_A6XX_CP_MEM_POOL_SIZE, 128);
 
-	/* Setting the primFifo thresholds default values */
-	if (adreno_is_a650(adreno_gpu))
-		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00300000);
+	/* Setting the primFifo thresholds default values,
+	 * and vccCacheSkipDis=1 bit (0x200) for A640 and newer
+	*/
+	if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu))
+		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00300200);
 	else if (adreno_is_a640(adreno_gpu))
-		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00200000);
+		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00200200);
 	else
-		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, (0x300 << 11));
+		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00180000);
 
 	/* Set the AHB default slave response to "ERROR" */
 	gpu_write(gpu, REG_A6XX_CP_AHB_CNTL, 0x1);
@@ -752,7 +964,7 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	gpu_write(gpu, REG_A6XX_RBBM_PERFCTR_CNTL, 0x1);
 
 	/* Select CP0 to always count cycles */
-	gpu_write(gpu, REG_A6XX_CP_PERFCTR_CP_SEL_0, PERF_CP_ALWAYS_COUNT);
+	gpu_write(gpu, REG_A6XX_CP_PERFCTR_CP_SEL(0), PERF_CP_ALWAYS_COUNT);
 
 	a6xx_set_ubwc_config(gpu);
 
@@ -763,7 +975,7 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	gpu_write(gpu, REG_A6XX_UCHE_CLIENT_PF, 1);
 
 	/* Set weights for bicubic filtering */
-	if (adreno_is_a650(adreno_gpu)) {
+	if (adreno_is_a650_family(adreno_gpu)) {
 		gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE_0, 0);
 		gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE_1,
 			0x3fe05ff4);
@@ -776,41 +988,14 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	}
 
 	/* Protect registers from the CP */
-	gpu_write(gpu, REG_A6XX_CP_PROTECT_CNTL, 0x00000003);
-
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(0),
-		A6XX_PROTECT_RDONLY(0x600, 0x51));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(1), A6XX_PROTECT_RW(0xae50, 0x2));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(2), A6XX_PROTECT_RW(0x9624, 0x13));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(3), A6XX_PROTECT_RW(0x8630, 0x8));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(4), A6XX_PROTECT_RW(0x9e70, 0x1));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(5), A6XX_PROTECT_RW(0x9e78, 0x187));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(6), A6XX_PROTECT_RW(0xf000, 0x810));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(7),
-		A6XX_PROTECT_RDONLY(0xfc00, 0x3));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(8), A6XX_PROTECT_RW(0x50e, 0x0));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(9), A6XX_PROTECT_RDONLY(0x50f, 0x0));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(10), A6XX_PROTECT_RW(0x510, 0x0));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(11),
-		A6XX_PROTECT_RDONLY(0x0, 0x4f9));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(12),
-		A6XX_PROTECT_RDONLY(0x501, 0xa));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(13),
-		A6XX_PROTECT_RDONLY(0x511, 0x44));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(14), A6XX_PROTECT_RW(0xe00, 0xe));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(15), A6XX_PROTECT_RW(0x8e00, 0x0));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(16), A6XX_PROTECT_RW(0x8e50, 0xf));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(17), A6XX_PROTECT_RW(0xbe02, 0x0));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(18),
-		A6XX_PROTECT_RW(0xbe20, 0x11f3));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(19), A6XX_PROTECT_RW(0x800, 0x82));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(20), A6XX_PROTECT_RW(0x8a0, 0x8));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(21), A6XX_PROTECT_RW(0x8ab, 0x19));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(22), A6XX_PROTECT_RW(0x900, 0x4d));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(23), A6XX_PROTECT_RW(0x98d, 0x76));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(24),
-			A6XX_PROTECT_RDONLY(0x980, 0x4));
-	gpu_write(gpu, REG_A6XX_CP_PROTECT(25), A6XX_PROTECT_RW(0xa630, 0x0));
+	a6xx_set_cp_protect(gpu);
+
+	if (adreno_is_a660(adreno_gpu)) {
+		gpu_write(gpu, REG_A6XX_CP_CHICKEN_DBG, 0x1);
+		gpu_write(gpu, REG_A6XX_RBBM_GBIF_CLIENT_QOS_CNTL, 0x0);
+		/* Set dualQ + disable afull for A660 GPU but not for A635 */
+		gpu_write(gpu, REG_A6XX_UCHE_CMDQ_CONFIG, 0x66906);
+	}
 
 	/* Enable expanded apriv for targets that support it */
 	if (gpu->hw_apriv) {
@@ -852,7 +1037,7 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 		if (!a6xx_gpu->shadow_bo) {
 			a6xx_gpu->shadow = msm_gem_kernel_new_locked(gpu->dev,
 				sizeof(u32) * gpu->nr_rings,
-				MSM_BO_UNCACHED | MSM_BO_MAP_PRIV,
+				MSM_BO_WC | MSM_BO_MAP_PRIV,
 				gpu->aspace, &a6xx_gpu->shadow_bo,
 				&a6xx_gpu->shadow_iova);
 
@@ -959,18 +1144,113 @@ static void a6xx_recover(struct msm_gpu *gpu)
 	msm_gpu_hw_init(gpu);
 }
 
-static int a6xx_fault_handler(void *arg, unsigned long iova, int flags)
+static const char *a6xx_uche_fault_block(struct msm_gpu *gpu, u32 mid)
+{
+	static const char *uche_clients[7] = {
+		"VFD", "SP", "VSC", "VPC", "HLSQ", "PC", "LRZ",
+	};
+	u32 val;
+
+	if (mid < 1 || mid > 3)
+		return "UNKNOWN";
+
+	/*
+	 * The source of the data depends on the mid ID read from FSYNR1.
+	 * and the client ID read from the UCHE block
+	 */
+	val = gpu_read(gpu, REG_A6XX_UCHE_CLIENT_PF);
+
+	/* mid = 3 is most precise and refers to only one block per client */
+	if (mid == 3)
+		return uche_clients[val & 7];
+
+	/* For mid=2 the source is TP or VFD except when the client id is 0 */
+	if (mid == 2)
+		return ((val & 7) == 0) ? "TP" : "TP|VFD";
+
+	/* For mid=1 just return "UCHE" as a catchall for everything else */
+	return "UCHE";
+}
+
+static const char *a6xx_fault_block(struct msm_gpu *gpu, u32 id)
+{
+	if (id == 0)
+		return "CP";
+	else if (id == 4)
+		return "CCU";
+	else if (id == 6)
+		return "CDP Prefetch";
+
+	return a6xx_uche_fault_block(gpu, id);
+}
+
+#define ARM_SMMU_FSR_TF                 BIT(1)
+#define ARM_SMMU_FSR_PF			BIT(3)
+#define ARM_SMMU_FSR_EF			BIT(4)
+
+static int a6xx_fault_handler(void *arg, unsigned long iova, int flags, void *data)
 {
 	struct msm_gpu *gpu = arg;
+	struct adreno_smmu_fault_info *info = data;
+	const char *type = "UNKNOWN";
+	const char *block;
+	bool do_devcoredump = info && !READ_ONCE(gpu->crashstate);
+
+	/*
+	 * If we aren't going to be resuming later from fault_worker, then do
+	 * it now.
+	 */
+	if (!do_devcoredump) {
+		gpu->aspace->mmu->funcs->resume_translation(gpu->aspace->mmu);
+	}
 
-	pr_warn_ratelimited("*** gpu fault: iova=%08lx, flags=%d (%u,%u,%u,%u)\n",
+	/*
+	 * Print a default message if we couldn't get the data from the
+	 * adreno-smmu-priv
+	 */
+	if (!info) {
+		pr_warn_ratelimited("*** gpu fault: iova=%.16lx flags=%d (%u,%u,%u,%u)\n",
 			iova, flags,
 			gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(4)),
 			gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(5)),
 			gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(6)),
 			gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(7)));
 
-	return -EFAULT;
+		return 0;
+	}
+
+	if (info->fsr & ARM_SMMU_FSR_TF)
+		type = "TRANSLATION";
+	else if (info->fsr & ARM_SMMU_FSR_PF)
+		type = "PERMISSION";
+	else if (info->fsr & ARM_SMMU_FSR_EF)
+		type = "EXTERNAL";
+
+	block = a6xx_fault_block(gpu, info->fsynr1 & 0xff);
+
+	pr_warn_ratelimited("*** gpu fault: ttbr0=%.16llx iova=%.16lx dir=%s type=%s source=%s (%u,%u,%u,%u)\n",
+			info->ttbr0, iova,
+			flags & IOMMU_FAULT_WRITE ? "WRITE" : "READ",
+			type, block,
+			gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(4)),
+			gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(5)),
+			gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(6)),
+			gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(7)));
+
+	if (do_devcoredump) {
+		/* Turn off the hangcheck timer to keep it from bothering us */
+		del_timer(&gpu->hangcheck_timer);
+
+		gpu->fault_info.ttbr0 = info->ttbr0;
+		gpu->fault_info.iova  = iova;
+		gpu->fault_info.flags = flags;
+		gpu->fault_info.type  = type;
+		gpu->fault_info.block = block;
+
+		kthread_queue_work(gpu->worker, &gpu->fault_work);
+	}
+
+	return 0;
 }
 
 static void a6xx_cp_hw_err_irq(struct msm_gpu *gpu)
@@ -1022,6 +1302,15 @@ static void a6xx_fault_detect_irq(struct msm_gpu *gpu)
 	struct msm_ringbuffer *ring = gpu->funcs->active_ring(gpu);
 
 	/*
+	 * If stalled on SMMU fault, we could trip the GPU's hang detection,
+	 * but the fault handler will trigger the devcore dump, and we want
+	 * to otherwise resume normally rather than killing the submit, so
+	 * just bail.
+	 */
+	if (gpu_read(gpu, REG_A6XX_RBBM_STATUS3) & A6XX_RBBM_STATUS3_SMMU_STALLED_ON_FAULT)
+		return;
+
+	/*
 	 * Force the GPU to stay on until after we finish
 	 * collecting information
 	 */
@@ -1211,7 +1500,7 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
-	if (adreno_gpu->base.hw_apriv || a6xx_gpu->has_whereami)
+	if (a6xx_gpu->shadow_bo)
 		for (i = 0; i < gpu->nr_rings; i++)
 			a6xx_gpu->shadow[i] = 0;
 
@@ -1266,9 +1555,6 @@ static void a6xx_destroy(struct msm_gpu *gpu)
 
 	adreno_gpu_cleanup(adreno_gpu);
 
-	if (a6xx_gpu->opp_table)
-		dev_pm_opp_put_supported_hw(a6xx_gpu->opp_table);
-
 	kfree(a6xx_gpu);
 }
 
@@ -1401,7 +1687,6 @@ static u32 fuse_to_supp_hw(struct device *dev, u32 revn, u32 fuse)
 static int a6xx_set_supported_hw(struct device *dev, struct a6xx_gpu *a6xx_gpu,
 		u32 revn)
 {
-	struct opp_table *opp_table;
 	u32 supp_hw = UINT_MAX;
 	u16 speedbin;
 	int ret;
@@ -1424,11 +1709,10 @@ static int a6xx_set_supported_hw(struct device *dev, struct a6xx_gpu *a6xx_gpu,
 	supp_hw = fuse_to_supp_hw(dev, revn, speedbin);
 
 done:
-	opp_table = dev_pm_opp_set_supported_hw(dev, &supp_hw, 1);
-	if (IS_ERR(opp_table))
-		return PTR_ERR(opp_table);
+	ret = devm_pm_opp_set_supported_hw(dev, &supp_hw, 1);
+	if (ret)
+		return ret;
 
-	a6xx_gpu->opp_table = opp_table;
 	return 0;
 }
 
@@ -1488,7 +1772,7 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 	 */
 	info = adreno_info(config->rev);
 
-	if (info && info->revn == 650)
+	if (info && (info->revn == 650 || info->revn == 660))
 		adreno_gpu->base.hw_apriv = true;
 
 	a6xx_llc_slices_init(pdev, a6xx_gpu);