Merge tag 'drm-msm-next-2020-07-30' of https://gitlab.freedesktop.org/drm/msm into drm-next

Take 2 of msm-next pull, this version drops the OPP patch due to [1],
so I'll send the gpu opp/bw scaling patch after the OPP patch lands.
Since I had to force-push I took the opportunity to rebase on
drm-next, and since you already merged in 5.8-rc6 a few fixes from the
last cycle dropped out.

This time around:

* A bunch more a650/a640 (sm8150/sm8250) display and GPU enablement
  and fixes
* Enable dpu dither block for 6bpc panels
* dpu suspend fixes
* dpu fix for cursor on 2nd display
* dsi/mdp5 enablement for sdm630/sdm636/sdm660

I also regenerated the register headers, which accounts for a good
bit of the size this time, because we hadn't re-synced the register
headers since the early days of a6xx bringup.
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Rob Clark <robdclark@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/ <CAF6AEGs_eswoX-E0Ddg5DoEQy35x3GG+6SDXUAjPMrtAWFkqng@mail.gmail.com

Documentation/devicetree/bindings/display/msm/dsi.txt

@@ -87,6 +87,7 @@ Required properties:
   * "qcom,dsi-phy-20nm"
   * "qcom,dsi-phy-28nm-8960"
   * "qcom,dsi-phy-14nm"
+  * "qcom,dsi-phy-14nm-660"
   * "qcom,dsi-phy-10nm"
   * "qcom,dsi-phy-10nm-8998"
 - reg: Physical base address and length of the registers of PLL, PHY. Some

Documentation/devicetree/bindings/display/msm/gpu.txt

@@ -112,6 +112,34 @@ Example a6xx (with GMU):
 		interconnects = <&rsc_hlos MASTER_GFX3D &rsc_hlos SLAVE_EBI1>;
 		interconnect-names = "gfx-mem";
 
+		gpu_opp_table: opp-table {
+			compatible = "operating-points-v2";
+
+			opp-430000000 {
+				opp-hz = /bits/ 64 <430000000>;
+				opp-level = <RPMH_REGULATOR_LEVEL_SVS_L1>;
+				opp-peak-kBps = <5412000>;
+			};
+
+			opp-355000000 {
+				opp-hz = /bits/ 64 <355000000>;
+				opp-level = <RPMH_REGULATOR_LEVEL_SVS>;
+				opp-peak-kBps = <3072000>;
+			};
+
+			opp-267000000 {
+				opp-hz = /bits/ 64 <267000000>;
+				opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS>;
+				opp-peak-kBps = <3072000>;
+			};
+
+			opp-180000000 {
+				opp-hz = /bits/ 64 <180000000>;
+				opp-level = <RPMH_REGULATOR_LEVEL_MIN_SVS>;
+				opp-peak-kBps = <1804000>;
+			};
+		};
+
 		qcom,gmu = <&gmu>;
 
 		zap-shader {

drivers/gpu/drm/msm/adreno/a3xx.xml.h

@@ -8,19 +8,21 @@ This file was generated by the rules-ng-ng headergen tool in this git repository
 git clone https://github.com/freedreno/envytools.git
 
 The rules-ng-ng source files this header was generated from are:
-- /home/robclark/src/envytools/rnndb/adreno.xml               (    501 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml          (  42463 bytes, from 2018-11-19 13:44:03)
-- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml (  14201 bytes, from 2018-12-02 17:29:54)
-- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml    (  43052 bytes, from 2018-12-02 17:29:54)
-- /home/robclark/src/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a4xx.xml          ( 112086 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml          ( 147240 bytes, from 2018-12-02 17:29:54)
-- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml          ( 140790 bytes, from 2018-12-02 17:29:54)
-- /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml      (  10431 bytes, from 2018-09-14 13:03:07)
-- /home/robclark/src/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2018-07-03 19:37:13)
-
-Copyright (C) 2013-2018 by the following authors:
+- /home/robclark/src/envytools/rnndb/adreno.xml                     (    594 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/freedreno_copyright.xml        (   1572 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml                (  90159 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml       (  14386 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml          (  65048 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/adreno/a3xx.xml                (  84226 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/adreno/a4xx.xml                ( 112556 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml                ( 149461 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml                ( 184695 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml            (  11218 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/adreno/ocmem.xml               (   1773 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_control_regs.xml (   4559 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_pipe_regs.xml    (   2872 bytes, from 2020-07-23 21:58:14)
+
+Copyright (C) 2013-2020 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
 - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin)
 
@@ -48,7 +50,9 @@ WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
 enum a3xx_tile_mode {
 	LINEAR = 0,
+	TILE_4X4 = 1,
 	TILE_32X32 = 2,
+	TILE_4X2 = 3,
 };
 
 enum a3xx_state_block_id {
@@ -123,6 +127,7 @@ enum a3xx_vtx_fmt {
 	VFMT_2_10_10_10_UNORM = 61,
 	VFMT_2_10_10_10_SINT = 62,
 	VFMT_2_10_10_10_SNORM = 63,
+	VFMT_NONE = 255,
 };
 
 enum a3xx_tex_fmt {
@@ -206,15 +211,7 @@ enum a3xx_tex_fmt {
 	TFMT_ETC2_RGBA8 = 116,
 	TFMT_ETC2_RGB8A1 = 117,
 	TFMT_ETC2_RGB8 = 118,
-};
-
-enum a3xx_tex_fetchsize {
-	TFETCH_DISABLE = 0,
-	TFETCH_1_BYTE = 1,
-	TFETCH_2_BYTE = 2,
-	TFETCH_4_BYTE = 3,
-	TFETCH_8_BYTE = 4,
-	TFETCH_16_BYTE = 5,
+	TFMT_NONE = 255,
 };
 
 enum a3xx_color_fmt {
@@ -228,8 +225,8 @@ enum a3xx_color_fmt {
 	RB_R8G8B8A8_SINT = 11,
 	RB_R8G8_UNORM = 12,
 	RB_R8G8_SNORM = 13,
-	RB_R8_UINT = 14,
-	RB_R8_SINT = 15,
+	RB_R8G8_UINT = 14,
+	RB_R8G8_SINT = 15,
 	RB_R10G10B10A2_UNORM = 16,
 	RB_A2R10G10B10_UNORM = 17,
 	RB_R10G10B10A2_UINT = 18,
@@ -261,6 +258,7 @@ enum a3xx_color_fmt {
 	RB_R32_UINT = 56,
 	RB_R32G32_UINT = 57,
 	RB_R32G32B32A32_UINT = 59,
+	RB_NONE = 255,
 };
 
 enum a3xx_cp_perfcounter_select {
@@ -932,6 +930,9 @@ static inline uint32_t REG_A3XX_CP_PROTECT_REG(uint32_t i0) { return 0x00000460
 
 #define REG_A3XX_GRAS_CL_CLIP_CNTL				0x00002040
 #define A3XX_GRAS_CL_CLIP_CNTL_IJ_PERSP_CENTER			0x00001000
+#define A3XX_GRAS_CL_CLIP_CNTL_IJ_NON_PERSP_CENTER		0x00002000
+#define A3XX_GRAS_CL_CLIP_CNTL_IJ_PERSP_CENTROID		0x00004000
+#define A3XX_GRAS_CL_CLIP_CNTL_IJ_NON_PERSP_CENTROID		0x00008000
 #define A3XX_GRAS_CL_CLIP_CNTL_CLIP_DISABLE			0x00010000
 #define A3XX_GRAS_CL_CLIP_CNTL_ZFAR_CLIP_DISABLE		0x00020000
 #define A3XX_GRAS_CL_CLIP_CNTL_VP_CLIP_CODE_IGNORE		0x00080000
@@ -1170,10 +1171,12 @@ static inline uint32_t A3XX_RB_RENDER_CONTROL_BIN_WIDTH(uint32_t val)
 }
 #define A3XX_RB_RENDER_CONTROL_DISABLE_COLOR_PIPE		0x00001000
 #define A3XX_RB_RENDER_CONTROL_ENABLE_GMEM			0x00002000
-#define A3XX_RB_RENDER_CONTROL_XCOORD				0x00004000
-#define A3XX_RB_RENDER_CONTROL_YCOORD				0x00008000
-#define A3XX_RB_RENDER_CONTROL_ZCOORD				0x00010000
-#define A3XX_RB_RENDER_CONTROL_WCOORD				0x00020000
+#define A3XX_RB_RENDER_CONTROL_COORD_MASK__MASK			0x0003c000
+#define A3XX_RB_RENDER_CONTROL_COORD_MASK__SHIFT		14
+static inline uint32_t A3XX_RB_RENDER_CONTROL_COORD_MASK(uint32_t val)
+{
+	return ((val) << A3XX_RB_RENDER_CONTROL_COORD_MASK__SHIFT) & A3XX_RB_RENDER_CONTROL_COORD_MASK__MASK;
+}
 #define A3XX_RB_RENDER_CONTROL_I_CLAMP_ENABLE			0x00080000
 #define A3XX_RB_RENDER_CONTROL_COV_VALUE_OUTPUT_ENABLE		0x00100000
 #define A3XX_RB_RENDER_CONTROL_ALPHA_TEST			0x00400000
@@ -1755,11 +1758,29 @@ static inline uint32_t A3XX_HLSQ_CONTROL_2_REG_PRIMALLOCTHRESHOLD(uint32_t val)
 }
 
 #define REG_A3XX_HLSQ_CONTROL_3_REG				0x00002203
-#define A3XX_HLSQ_CONTROL_3_REG_REGID__MASK			0x000000ff
-#define A3XX_HLSQ_CONTROL_3_REG_REGID__SHIFT			0
-static inline uint32_t A3XX_HLSQ_CONTROL_3_REG_REGID(uint32_t val)
+#define A3XX_HLSQ_CONTROL_3_REG_IJPERSPCENTERREGID__MASK	0x000000ff
+#define A3XX_HLSQ_CONTROL_3_REG_IJPERSPCENTERREGID__SHIFT	0
+static inline uint32_t A3XX_HLSQ_CONTROL_3_REG_IJPERSPCENTERREGID(uint32_t val)
+{
+	return ((val) << A3XX_HLSQ_CONTROL_3_REG_IJPERSPCENTERREGID__SHIFT) & A3XX_HLSQ_CONTROL_3_REG_IJPERSPCENTERREGID__MASK;
+}
+#define A3XX_HLSQ_CONTROL_3_REG_IJNONPERSPCENTERREGID__MASK	0x0000ff00
+#define A3XX_HLSQ_CONTROL_3_REG_IJNONPERSPCENTERREGID__SHIFT	8
+static inline uint32_t A3XX_HLSQ_CONTROL_3_REG_IJNONPERSPCENTERREGID(uint32_t val)
+{
+	return ((val) << A3XX_HLSQ_CONTROL_3_REG_IJNONPERSPCENTERREGID__SHIFT) & A3XX_HLSQ_CONTROL_3_REG_IJNONPERSPCENTERREGID__MASK;
+}
+#define A3XX_HLSQ_CONTROL_3_REG_IJPERSPCENTROIDREGID__MASK	0x00ff0000
+#define A3XX_HLSQ_CONTROL_3_REG_IJPERSPCENTROIDREGID__SHIFT	16
+static inline uint32_t A3XX_HLSQ_CONTROL_3_REG_IJPERSPCENTROIDREGID(uint32_t val)
+{
+	return ((val) << A3XX_HLSQ_CONTROL_3_REG_IJPERSPCENTROIDREGID__SHIFT) & A3XX_HLSQ_CONTROL_3_REG_IJPERSPCENTROIDREGID__MASK;
+}
+#define A3XX_HLSQ_CONTROL_3_REG_IJNONPERSPCENTROIDREGID__MASK	0xff000000
+#define A3XX_HLSQ_CONTROL_3_REG_IJNONPERSPCENTROIDREGID__SHIFT	24
+static inline uint32_t A3XX_HLSQ_CONTROL_3_REG_IJNONPERSPCENTROIDREGID(uint32_t val)
 {
-	return ((val) << A3XX_HLSQ_CONTROL_3_REG_REGID__SHIFT) & A3XX_HLSQ_CONTROL_3_REG_REGID__MASK;
+	return ((val) << A3XX_HLSQ_CONTROL_3_REG_IJNONPERSPCENTROIDREGID__SHIFT) & A3XX_HLSQ_CONTROL_3_REG_IJNONPERSPCENTROIDREGID__MASK;
 }
 
 #define REG_A3XX_HLSQ_VS_CONTROL_REG				0x00002204
@@ -1944,8 +1965,6 @@ static inline uint32_t A3XX_VFD_CONTROL_1_REGID4INST(uint32_t val)
 
 #define REG_A3XX_VFD_INDEX_OFFSET				0x00002245
 
-#define REG_A3XX_VFD_INDEX_OFFSET				0x00002245
-
 static inline uint32_t REG_A3XX_VFD_FETCH(uint32_t i0) { return 0x00002246 + 0x2*i0; }
 
 static inline uint32_t REG_A3XX_VFD_FETCH_INSTR_0(uint32_t i0) { return 0x00002246 + 0x2*i0; }
@@ -3107,7 +3126,12 @@ static inline uint32_t A3XX_TEX_SAMP_1_MIN_LOD(float val)
 }
 
 #define REG_A3XX_TEX_CONST_0					0x00000000
-#define A3XX_TEX_CONST_0_TILED					0x00000001
+#define A3XX_TEX_CONST_0_TILE_MODE__MASK			0x00000003
+#define A3XX_TEX_CONST_0_TILE_MODE__SHIFT			0
+static inline uint32_t A3XX_TEX_CONST_0_TILE_MODE(enum a3xx_tile_mode val)
+{
+	return ((val) << A3XX_TEX_CONST_0_TILE_MODE__SHIFT) & A3XX_TEX_CONST_0_TILE_MODE__MASK;
+}
 #define A3XX_TEX_CONST_0_SRGB					0x00000004
 #define A3XX_TEX_CONST_0_SWIZ_X__MASK				0x00000070
 #define A3XX_TEX_CONST_0_SWIZ_X__SHIFT				4
@@ -3172,11 +3196,11 @@ static inline uint32_t A3XX_TEX_CONST_1_WIDTH(uint32_t val)
 {
 	return ((val) << A3XX_TEX_CONST_1_WIDTH__SHIFT) & A3XX_TEX_CONST_1_WIDTH__MASK;
 }
-#define A3XX_TEX_CONST_1_FETCHSIZE__MASK			0xf0000000
-#define A3XX_TEX_CONST_1_FETCHSIZE__SHIFT			28
-static inline uint32_t A3XX_TEX_CONST_1_FETCHSIZE(enum a3xx_tex_fetchsize val)
+#define A3XX_TEX_CONST_1_PITCHALIGN__MASK			0xf0000000
+#define A3XX_TEX_CONST_1_PITCHALIGN__SHIFT			28
+static inline uint32_t A3XX_TEX_CONST_1_PITCHALIGN(uint32_t val)
 {
-	return ((val) << A3XX_TEX_CONST_1_FETCHSIZE__SHIFT) & A3XX_TEX_CONST_1_FETCHSIZE__MASK;
+	return ((val) << A3XX_TEX_CONST_1_PITCHALIGN__SHIFT) & A3XX_TEX_CONST_1_PITCHALIGN__MASK;
 }
 
 #define REG_A3XX_TEX_CONST_2					0x00000002

drivers/gpu/drm/msm/adreno/a5xx_gpu.c

@@ -186,7 +186,8 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 	 * timestamp is written to the memory and then triggers the interrupt
 	 */
 	OUT_PKT7(ring, CP_EVENT_WRITE, 4);
-	OUT_RING(ring, CACHE_FLUSH_TS | (1 << 31));
+	OUT_RING(ring, CP_EVENT_WRITE_0_EVENT(CACHE_FLUSH_TS) |
+		CP_EVENT_WRITE_0_IRQ);
 	OUT_RING(ring, lower_32_bits(rbmemptr(ring, fence)));
 	OUT_RING(ring, upper_32_bits(rbmemptr(ring, fence)));
 	OUT_RING(ring, submit->seqno);
@@ -730,7 +731,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	 */
 	if (adreno_is_a530(adreno_gpu)) {
 		OUT_PKT7(gpu->rb[0], CP_EVENT_WRITE, 1);
-		OUT_RING(gpu->rb[0], 0x0F);
+		OUT_RING(gpu->rb[0], CP_EVENT_WRITE_0_EVENT(STAT_EVENT));
 
 		gpu->funcs->flush(gpu, gpu->rb[0]);
 		if (!a5xx_idle(gpu, gpu->rb[0]))

drivers/gpu/drm/msm/adreno/a6xx_gmu.c

@@ -103,17 +103,45 @@ bool a6xx_gmu_gx_is_on(struct a6xx_gmu *gmu)
 		A6XX_GMU_SPTPRAC_PWR_CLK_STATUS_GX_HM_CLK_OFF));
 }
 
-static void __a6xx_gmu_set_freq(struct a6xx_gmu *gmu, int index)
+void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
 {
-	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
-	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
-	struct msm_gpu *gpu = &adreno_gpu->base;
-	int ret;
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
+	struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
+	u32 perf_index;
+	unsigned long gpu_freq;
+	int ret = 0;
+
+	gpu_freq = dev_pm_opp_get_freq(opp);
+
+	if (gpu_freq == gmu->freq)
+		return;
+
+	for (perf_index = 0; perf_index < gmu->nr_gpu_freqs - 1; perf_index++)
+		if (gpu_freq == gmu->gpu_freqs[perf_index])
+			break;
+
+	gmu->current_perf_index = perf_index;
+	gmu->freq = gmu->gpu_freqs[perf_index];
+
+	/*
+	 * This can get called from devfreq while the hardware is idle. Don't
+	 * bring up the power if it isn't already active
+	 */
+	if (pm_runtime_get_if_in_use(gmu->dev) == 0)
+		return;
+
+	if (!gmu->legacy) {
+		a6xx_hfi_set_freq(gmu, perf_index);
+		icc_set_bw(gpu->icc_path, 0, MBps_to_icc(7216));
+		pm_runtime_put(gmu->dev);
+		return;
+	}
 
 	gmu_write(gmu, REG_A6XX_GMU_DCVS_ACK_OPTION, 0);
 
 	gmu_write(gmu, REG_A6XX_GMU_DCVS_PERF_SETTING,
-		((3 & 0xf) << 28) | index);
+			((3 & 0xf) << 28) | perf_index);
 
 	/*
 	 * Send an invalid index as a vote for the bus bandwidth and let the
@@ -134,37 +162,6 @@ static void __a6xx_gmu_set_freq(struct a6xx_gmu *gmu, int index)
 	 * for now leave it at max so that the performance is nominal.
 	 */
 	icc_set_bw(gpu->icc_path, 0, MBps_to_icc(7216));
-}
-
-void a6xx_gmu_set_freq(struct msm_gpu *gpu, unsigned long freq)
-{
-	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
-	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
-	struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
-	u32 perf_index = 0;
-
-	if (freq == gmu->freq)
-		return;
-
-	for (perf_index = 0; perf_index < gmu->nr_gpu_freqs - 1; perf_index++)
-		if (freq == gmu->gpu_freqs[perf_index])
-			break;
-
-	gmu->current_perf_index = perf_index;
-	gmu->freq = gmu->gpu_freqs[perf_index];
-
-	/*
-	 * This can get called from devfreq while the hardware is idle. Don't
-	 * bring up the power if it isn't already active
-	 */
-	if (pm_runtime_get_if_in_use(gmu->dev) == 0)
-		return;
-
-	if (gmu->legacy)
-		__a6xx_gmu_set_freq(gmu, perf_index);
-	else
-		a6xx_hfi_set_freq(gmu, perf_index);
-
 	pm_runtime_put(gmu->dev);
 }
 
@@ -839,6 +836,19 @@ static void a6xx_gmu_force_off(struct a6xx_gmu *gmu)
 	a6xx_gmu_rpmh_off(gmu);
 }
 
+static void a6xx_gmu_set_initial_freq(struct msm_gpu *gpu, struct a6xx_gmu *gmu)
+{
+	struct dev_pm_opp *gpu_opp;
+	unsigned long gpu_freq = gmu->gpu_freqs[gmu->current_perf_index];
+
+	gpu_opp = dev_pm_opp_find_freq_exact(&gpu->pdev->dev, gpu_freq, true);
+	if (IS_ERR_OR_NULL(gpu_opp))
+		return;
+
+	a6xx_gmu_set_freq(gpu, gpu_opp);
+	dev_pm_opp_put(gpu_opp);
+}
+
 int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 {
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
@@ -854,10 +864,19 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 	/* Turn on the resources */
 	pm_runtime_get_sync(gmu->dev);
 
+	/*
+	 * "enable" the GX power domain which won't actually do anything but it
+	 * will make sure that the refcounting is correct in case we need to
+	 * bring down the GX after a GMU failure
+	 */
+	if (!IS_ERR_OR_NULL(gmu->gxpd))
+		pm_runtime_get_sync(gmu->gxpd);
+
 	/* Use a known rate to bring up the GMU */
 	clk_set_rate(gmu->core_clk, 200000000);
 	ret = clk_bulk_prepare_enable(gmu->nr_clocks, gmu->clocks);
 	if (ret) {
+		pm_runtime_put(gmu->gxpd);
 		pm_runtime_put(gmu->dev);
 		return ret;
 	}
@@ -898,24 +917,14 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 	enable_irq(gmu->hfi_irq);
 
 	/* Set the GPU to the current freq */
-	if (gmu->legacy)
-		__a6xx_gmu_set_freq(gmu, gmu->current_perf_index);
-	else
-		a6xx_hfi_set_freq(gmu, gmu->current_perf_index);
-
-	/*
-	 * "enable" the GX power domain which won't actually do anything but it
-	 * will make sure that the refcounting is correct in case we need to
-	 * bring down the GX after a GMU failure
-	 */
-	if (!IS_ERR_OR_NULL(gmu->gxpd))
-		pm_runtime_get(gmu->gxpd);
+	a6xx_gmu_set_initial_freq(gpu, gmu);
 
 out:
 	/* On failure, shut down the GMU to leave it in a good state */
 	if (ret) {
 		disable_irq(gmu->gmu_irq);
 		a6xx_rpmh_stop(gmu);
+		pm_runtime_put(gmu->gxpd);
 		pm_runtime_put(gmu->dev);
 	}
 

drivers/gpu/drm/msm/adreno/a6xx_gmu.h

@@ -127,6 +127,11 @@ static inline u64 gmu_read64(struct a6xx_gmu *gmu, u32 lo, u32 hi)
 	readl_poll_timeout((gmu)->mmio + ((addr) << 2), val, cond, \
 		interval, timeout)
 
+static inline u32 gmu_read_rscc(struct a6xx_gmu *gmu, u32 offset)
+{
+	return msm_readl(gmu->rscc + (offset << 2));
+}
+
 static inline void gmu_write_rscc(struct a6xx_gmu *gmu, u32 offset, u32 value)
 {
 	return msm_writel(value, gmu->rscc + (offset << 2));

drivers/gpu/drm/msm/adreno/a6xx_gmu.xml.h

@@ -8,19 +8,21 @@ This file was generated by the rules-ng-ng headergen tool in this git repository
 git clone https://github.com/freedreno/envytools.git
 
 The rules-ng-ng source files this header was generated from are:
-- /home/robclark/src/envytools/rnndb/adreno.xml               (    501 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml          (  42463 bytes, from 2018-11-19 13:44:03)
-- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml (  14201 bytes, from 2018-12-02 17:29:54)
-- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml    (  43052 bytes, from 2018-12-02 17:29:54)
-- /home/robclark/src/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a4xx.xml          ( 112086 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml          ( 147240 bytes, from 2018-12-02 17:29:54)
-- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml          ( 140790 bytes, from 2018-12-02 17:29:54)
-- /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml      (  10431 bytes, from 2018-09-14 13:03:07)
-- /home/robclark/src/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2018-07-03 19:37:13)
-
-Copyright (C) 2013-2018 by the following authors:
+- /home/robclark/src/envytools/rnndb/adreno.xml                     (    594 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/freedreno_copyright.xml        (   1572 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml                (  90159 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml       (  14386 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml          (  65048 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/adreno/a3xx.xml                (  84226 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/adreno/a4xx.xml                ( 112556 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml                ( 149461 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml                ( 184695 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml            (  11218 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/adreno/ocmem.xml               (   1773 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_control_regs.xml (   4559 bytes, from 2020-07-23 21:58:14)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_pipe_regs.xml    (   2872 bytes, from 2020-07-23 21:58:14)
+
+Copyright (C) 2013-2020 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
 - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin)
 
@@ -46,24 +48,109 @@ WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 */
 
 
-#define A6XX_GMU_GPU_IDLE_STATUS_BUSY_IGN_AHB			0x00800000
-#define A6XX_GMU_GPU_IDLE_STATUS_CX_GX_CPU_BUSY_IGN_AHB		0x40000000
-#define A6XX_GMU_OOB_BOOT_SLUMBER_SET_MASK			0x00400000
-#define A6XX_GMU_OOB_BOOT_SLUMBER_CHECK_MASK			0x40000000
-#define A6XX_GMU_OOB_BOOT_SLUMBER_CLEAR_MASK			0x40000000
-#define A6XX_GMU_OOB_DCVS_SET_MASK				0x00800000
-#define A6XX_GMU_OOB_DCVS_CHECK_MASK				0x80000000
-#define A6XX_GMU_OOB_DCVS_CLEAR_MASK				0x80000000
-#define A6XX_GMU_OOB_GPU_SET_MASK				0x00040000
-#define A6XX_GMU_OOB_GPU_CHECK_MASK				0x04000000
-#define A6XX_GMU_OOB_GPU_CLEAR_MASK				0x04000000
-#define A6XX_GMU_OOB_PERFCNTR_SET_MASK				0x00020000
-#define A6XX_GMU_OOB_PERFCNTR_CHECK_MASK			0x02000000
-#define A6XX_GMU_OOB_PERFCNTR_CLEAR_MASK			0x02000000
+#define A6XX_GMU_GPU_IDLE_STATUS_BUSY_IGN_AHB__MASK		0x00800000
+#define A6XX_GMU_GPU_IDLE_STATUS_BUSY_IGN_AHB__SHIFT		23
+static inline uint32_t A6XX_GMU_GPU_IDLE_STATUS_BUSY_IGN_AHB(uint32_t val)
+{
+	return ((val) << A6XX_GMU_GPU_IDLE_STATUS_BUSY_IGN_AHB__SHIFT) & A6XX_GMU_GPU_IDLE_STATUS_BUSY_IGN_AHB__MASK;
+}
+#define A6XX_GMU_GPU_IDLE_STATUS_CX_GX_CPU_BUSY_IGN_AHB__MASK	0x40000000
+#define A6XX_GMU_GPU_IDLE_STATUS_CX_GX_CPU_BUSY_IGN_AHB__SHIFT	30
+static inline uint32_t A6XX_GMU_GPU_IDLE_STATUS_CX_GX_CPU_BUSY_IGN_AHB(uint32_t val)
+{
+	return ((val) << A6XX_GMU_GPU_IDLE_STATUS_CX_GX_CPU_BUSY_IGN_AHB__SHIFT) & A6XX_GMU_GPU_IDLE_STATUS_CX_GX_CPU_BUSY_IGN_AHB__MASK;
+}
+#define A6XX_GMU_OOB_BOOT_SLUMBER_SET_MASK__MASK		0x00400000
+#define A6XX_GMU_OOB_BOOT_SLUMBER_SET_MASK__SHIFT		22
+static inline uint32_t A6XX_GMU_OOB_BOOT_SLUMBER_SET_MASK(uint32_t val)
+{
+	return ((val) << A6XX_GMU_OOB_BOOT_SLUMBER_SET_MASK__SHIFT) & A6XX_GMU_OOB_BOOT_SLUMBER_SET_MASK__MASK;
+}
+#define A6XX_GMU_OOB_BOOT_SLUMBER_CHECK_MASK__MASK		0x40000000
+#define A6XX_GMU_OOB_BOOT_SLUMBER_CHECK_MASK__SHIFT		30
+static inline uint32_t A6XX_GMU_OOB_BOOT_SLUMBER_CHECK_MASK(uint32_t val)
+{
+	return ((val) << A6XX_GMU_OOB_BOOT_SLUMBER_CHECK_MASK__SHIFT) & A6XX_GMU_OOB_BOOT_SLUMBER_CHECK_MASK__MASK;
+}
+#define A6XX_GMU_OOB_BOOT_SLUMBER_CLEAR_MASK__MASK		0x40000000
+#define A6XX_GMU_OOB_BOOT_SLUMBER_CLEAR_MASK__SHIFT		30
+static inline uint32_t A6XX_GMU_OOB_BOOT_SLUMBER_CLEAR_MASK(uint32_t val)
+{
+	return ((val) << A6XX_GMU_OOB_BOOT_SLUMBER_CLEAR_MASK__SHIFT) & A6XX_GMU_OOB_BOOT_SLUMBER_CLEAR_MASK__MASK;
+}
+#define A6XX_GMU_OOB_DCVS_SET_MASK__MASK			0x00800000
+#define A6XX_GMU_OOB_DCVS_SET_MASK__SHIFT			23
+static inline uint32_t A6XX_GMU_OOB_DCVS_SET_MASK(uint32_t val)
+{
+	return ((val) << A6XX_GMU_OOB_DCVS_SET_MASK__SHIFT) & A6XX_GMU_OOB_DCVS_SET_MASK__MASK;
+}
+#define A6XX_GMU_OOB_DCVS_CHECK_MASK__MASK			0x80000000
+#define A6XX_GMU_OOB_DCVS_CHECK_MASK__SHIFT			31
+static inline uint32_t A6XX_GMU_OOB_DCVS_CHECK_MASK(uint32_t val)
+{
+	return ((val) << A6XX_GMU_OOB_DCVS_CHECK_MASK__SHIFT) & A6XX_GMU_OOB_DCVS_CHECK_MASK__MASK;
+}
+#define A6XX_GMU_OOB_DCVS_CLEAR_MASK__MASK			0x80000000
+#define A6XX_GMU_OOB_DCVS_CLEAR_MASK__SHIFT			31
+static inline uint32_t A6XX_GMU_OOB_DCVS_CLEAR_MASK(uint32_t val)
+{
+	return ((val) << A6XX_GMU_OOB_DCVS_CLEAR_MASK__SHIFT) & A6XX_GMU_OOB_DCVS_CLEAR_MASK__MASK;
+}
+#define A6XX_GMU_OOB_GPU_SET_MASK__MASK				0x00040000
+#define A6XX_GMU_OOB_GPU_SET_MASK__SHIFT			18
+static inline uint32_t A6XX_GMU_OOB_GPU_SET_MASK(uint32_t val)
+{
+	return ((val) << A6XX_GMU_OOB_GPU_SET_MASK__SHIFT) & A6XX_GMU_OOB_GPU_SET_MASK__MASK;
+}
+#define A6XX_GMU_OOB_GPU_CHECK_MASK__MASK			0x04000000
+#define A6XX_GMU_OOB_GPU_CHECK_MASK__SHIFT			26
+static inline uint32_t A6XX_GMU_OOB_GPU_CHECK_MASK(uint32_t val)
+{
+	return ((val) << A6XX_GMU_OOB_GPU_CHECK_MASK__SHIFT) & A6XX_GMU_OOB_GPU_CHECK_MASK__MASK;
+}
+#define A6XX_GMU_OOB_GPU_CLEAR_MASK__MASK			0x04000000
+#define A6XX_GMU_OOB_GPU_CLEAR_MASK__SHIFT			26
+static inline uint32_t A6XX_GMU_OOB_GPU_CLEAR_MASK(uint32_t val)
+{
+	return ((val) << A6XX_GMU_OOB_GPU_CLEAR_MASK__SHIFT) & A6XX_GMU_OOB_GPU_CLEAR_MASK__MASK;
+}
+#define A6XX_GMU_OOB_PERFCNTR_SET_MASK__MASK			0x00020000
+#define A6XX_GMU_OOB_PERFCNTR_SET_MASK__SHIFT			17
+static inline uint32_t A6XX_GMU_OOB_PERFCNTR_SET_MASK(uint32_t val)
+{
+	return ((val) << A6XX_GMU_OOB_PERFCNTR_SET_MASK__SHIFT) & A6XX_GMU_OOB_PERFCNTR_SET_MASK__MASK;
+}
+#define A6XX_GMU_OOB_PERFCNTR_CHECK_MASK__MASK			0x02000000
+#define A6XX_GMU_OOB_PERFCNTR_CHECK_MASK__SHIFT			25
+static inline uint32_t A6XX_GMU_OOB_PERFCNTR_CHECK_MASK(uint32_t val)
+{
+	return ((val) << A6XX_GMU_OOB_PERFCNTR_CHECK_MASK__SHIFT) & A6XX_GMU_OOB_PERFCNTR_CHECK_MASK__MASK;
+}
+#define A6XX_GMU_OOB_PERFCNTR_CLEAR_MASK__MASK			0x02000000
+#define A6XX_GMU_OOB_PERFCNTR_CLEAR_MASK__SHIFT			25
+static inline uint32_t A6XX_GMU_OOB_PERFCNTR_CLEAR_MASK(uint32_t val)
+{
+	return ((val) << A6XX_GMU_OOB_PERFCNTR_CLEAR_MASK__SHIFT) & A6XX_GMU_OOB_PERFCNTR_CLEAR_MASK__MASK;
+}
 #define A6XX_HFI_IRQ_MSGQ_MASK					0x00000001
-#define A6XX_HFI_IRQ_DSGQ_MASK					0x00000002
-#define A6XX_HFI_IRQ_BLOCKED_MSG_MASK				0x00000004
-#define A6XX_HFI_IRQ_CM3_FAULT_MASK				0x00800000
+#define A6XX_HFI_IRQ_DSGQ_MASK__MASK				0x00000002
+#define A6XX_HFI_IRQ_DSGQ_MASK__SHIFT				1
+static inline uint32_t A6XX_HFI_IRQ_DSGQ_MASK(uint32_t val)
+{
+	return ((val) << A6XX_HFI_IRQ_DSGQ_MASK__SHIFT) & A6XX_HFI_IRQ_DSGQ_MASK__MASK;
+}
+#define A6XX_HFI_IRQ_BLOCKED_MSG_MASK__MASK			0x00000004
+#define A6XX_HFI_IRQ_BLOCKED_MSG_MASK__SHIFT			2
+static inline uint32_t A6XX_HFI_IRQ_BLOCKED_MSG_MASK(uint32_t val)
+{
+	return ((val) << A6XX_HFI_IRQ_BLOCKED_MSG_MASK__SHIFT) & A6XX_HFI_IRQ_BLOCKED_MSG_MASK__MASK;
+}
+#define A6XX_HFI_IRQ_CM3_FAULT_MASK__MASK			0x00800000
+#define A6XX_HFI_IRQ_CM3_FAULT_MASK__SHIFT			23
+static inline uint32_t A6XX_HFI_IRQ_CM3_FAULT_MASK(uint32_t val)
+{
+	return ((val) << A6XX_HFI_IRQ_CM3_FAULT_MASK__SHIFT) & A6XX_HFI_IRQ_CM3_FAULT_MASK__MASK;
+}
 #define A6XX_HFI_IRQ_GMU_ERR_MASK__MASK				0x007f0000
 #define A6XX_HFI_IRQ_GMU_ERR_MASK__SHIFT			16
 static inline uint32_t A6XX_HFI_IRQ_GMU_ERR_MASK(uint32_t val)

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

@@ -74,7 +74,9 @@ static void get_stats_counter(struct msm_ringbuffer *ring, u32 counter,
 		u64 iova)
 {
 	OUT_PKT7(ring, CP_REG_TO_MEM, 3);
-	OUT_RING(ring, counter | (1 << 30) | (2 << 18));
+	OUT_RING(ring, CP_REG_TO_MEM_0_REG(counter) |
+		CP_REG_TO_MEM_0_CNT(2) |
+		CP_REG_TO_MEM_0_64B);
 	OUT_RING(ring, lower_32_bits(iova));
 	OUT_RING(ring, upper_32_bits(iova));
 }
@@ -102,10 +104,10 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 
 	/* Invalidate CCU depth and color */
 	OUT_PKT7(ring, CP_EVENT_WRITE, 1);
-	OUT_RING(ring, PC_CCU_INVALIDATE_DEPTH);
+	OUT_RING(ring, CP_EVENT_WRITE_0_EVENT(PC_CCU_INVALIDATE_DEPTH));
 
 	OUT_PKT7(ring, CP_EVENT_WRITE, 1);
-	OUT_RING(ring, PC_CCU_INVALIDATE_COLOR);
+	OUT_RING(ring, CP_EVENT_WRITE_0_EVENT(PC_CCU_INVALIDATE_COLOR));
 
 	/* Submit the commands */
 	for (i = 0; i < submit->nr_cmds; i++) {
@@ -139,7 +141,8 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 	 * timestamp is written to the memory and then triggers the interrupt
 	 */
 	OUT_PKT7(ring, CP_EVENT_WRITE, 4);
-	OUT_RING(ring, CACHE_FLUSH_TS | (1 << 31));
+	OUT_RING(ring, CP_EVENT_WRITE_0_EVENT(CACHE_FLUSH_TS) |
+		CP_EVENT_WRITE_0_IRQ);
 	OUT_RING(ring, lower_32_bits(rbmemptr(ring, fence)));
 	OUT_RING(ring, upper_32_bits(rbmemptr(ring, fence)));
 	OUT_RING(ring, submit->seqno);
@@ -151,10 +154,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 	a6xx_flush(gpu, ring);
 }
 
-static const struct {
-	u32 offset;
-	u32 value;
-} a6xx_hwcg[] = {
+const struct adreno_reglist a630_hwcg[] = {
 	{REG_A6XX_RBBM_CLOCK_CNTL_SP0, 0x22222222},
 	{REG_A6XX_RBBM_CLOCK_CNTL_SP1, 0x22222222},
 	{REG_A6XX_RBBM_CLOCK_CNTL_SP2, 0x22222222},
@@ -259,7 +259,114 @@ static const struct {
 	{REG_A6XX_RBBM_CLOCK_MODE_HLSQ, 0x00002222},
 	{REG_A6XX_RBBM_CLOCK_CNTL_GMU_GX, 0x00000222},
 	{REG_A6XX_RBBM_CLOCK_DELAY_GMU_GX, 0x00000111},
-	{REG_A6XX_RBBM_CLOCK_HYST_GMU_GX, 0x00000555}
+	{REG_A6XX_RBBM_CLOCK_HYST_GMU_GX, 0x00000555},
+	{},
+};
+
+const struct adreno_reglist a640_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, 0x02222222},
+	{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, 0x05222022},
+	{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},
+	{},
+};
+
+const struct adreno_reglist a650_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, 0x02222222},
+	{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, 0x00000777},
+	{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)
@@ -267,26 +374,65 @@ static void a6xx_set_hwcg(struct msm_gpu *gpu, bool state)
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 	struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
+	const struct adreno_reglist *reg;
 	unsigned int i;
-	u32 val;
+	u32 val, clock_cntl_on;
+
+	if (!adreno_gpu->info->hwcg)
+		return;
+
+	if (adreno_is_a630(adreno_gpu))
+		clock_cntl_on = 0x8aa8aa02;
+	else
+		clock_cntl_on = 0x8aa8aa82;
 
 	val = gpu_read(gpu, REG_A6XX_RBBM_CLOCK_CNTL);
 
 	/* Don't re-program the registers if they are already correct */
-	if ((!state && !val) || (state && (val == 0x8aa8aa02)))
+	if ((!state && !val) || (state && (val == clock_cntl_on)))
 		return;
 
 	/* Disable SP clock before programming HWCG registers */
 	gmu_rmw(gmu, REG_A6XX_GPU_GMU_GX_SPTPRAC_CLOCK_CONTROL, 1, 0);
 
-	for (i = 0; i < ARRAY_SIZE(a6xx_hwcg); i++)
-		gpu_write(gpu, a6xx_hwcg[i].offset,
-			state ? a6xx_hwcg[i].value : 0);
+	for (i = 0; (reg = &adreno_gpu->info->hwcg[i], reg->offset); i++)
+		gpu_write(gpu, reg->offset, state ? reg->value : 0);
 
 	/* Enable SP clock */
 	gmu_rmw(gmu, REG_A6XX_GPU_GMU_GX_SPTPRAC_CLOCK_CONTROL, 0, 1);
 
-	gpu_write(gpu, REG_A6XX_RBBM_CLOCK_CNTL, state ? 0x8aa8aa02 : 0);
+	gpu_write(gpu, REG_A6XX_RBBM_CLOCK_CNTL, state ? clock_cntl_on : 0);
+}
+
+static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	u32 lower_bit = 2;
+	u32 amsbc = 0;
+	u32 rgb565_predicator = 0;
+	u32 uavflagprd_inv = 0;
+
+	/* a618 is using the hw default values */
+	if (adreno_is_a618(adreno_gpu))
+		return;
+
+	if (adreno_is_a640(adreno_gpu))
+		amsbc = 1;
+
+	if (adreno_is_a650(adreno_gpu)) {
+		/* TODO: get ddr type from bootloader and use 2 for LPDDR4 */
+		lower_bit = 3;
+		amsbc = 1;
+		rgb565_predicator = 1;
+		uavflagprd_inv = 2;
+	}
+
+	gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL,
+		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);
+	gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL, lower_bit << 21);
 }
 
 static int a6xx_cp_init(struct msm_gpu *gpu)
@@ -406,12 +552,8 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	gpu_write(gpu, REG_A6XX_TPL1_ADDR_MODE_CNTL, 0x1);
 	gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_ADDR_MODE_CNTL, 0x1);
 
-	/*
-	 * enable hardware clockgating
-	 * For now enable clock gating only for a630
-	 */
-	if (adreno_is_a630(adreno_gpu))
-		a6xx_set_hwcg(gpu, true);
+	/* enable hardware clockgating */
+	a6xx_set_hwcg(gpu, true);
 
 	/* VBIF/GBIF start*/
 	if (adreno_is_a640(adreno_gpu) || adreno_is_a650(adreno_gpu)) {
@@ -478,12 +620,7 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	/* Select CP0 to always count cycles */
 	gpu_write(gpu, REG_A6XX_CP_PERFCTR_CP_SEL_0, PERF_CP_ALWAYS_COUNT);
 
-	if (adreno_is_a630(adreno_gpu)) {
-		gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL, 2 << 1);
-		gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, 2 << 1);
-		gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL, 2 << 1);
-		gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL, 2 << 21);
-	}
+	a6xx_set_ubwc_config(gpu);
 
 	/* Enable fault detection */
 	gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL,

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

@@ -63,7 +63,7 @@ void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state);
 int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node);
 void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu);
 
-void a6xx_gmu_set_freq(struct msm_gpu *gpu, unsigned long freq);
+void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp);
 unsigned long a6xx_gmu_get_freq(struct msm_gpu *gpu);
 
 void a6xx_show(struct msm_gpu *gpu, struct msm_gpu_state *state,

drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c

@@ -736,7 +736,8 @@ static void a6xx_get_ahb_gpu_registers(struct msm_gpu *gpu,
 static void _a6xx_get_gmu_registers(struct msm_gpu *gpu,
 		struct a6xx_gpu_state *a6xx_state,
 		const struct a6xx_registers *regs,
-		struct a6xx_gpu_state_obj *obj)
+		struct a6xx_gpu_state_obj *obj,
+		bool rscc)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
@@ -755,9 +756,17 @@ static void _a6xx_get_gmu_registers(struct msm_gpu *gpu,
 		u32 count = RANGE(regs->registers, i);
 		int j;
 
-		for (j = 0; j < count; j++)
-			obj->data[index++] = gmu_read(gmu,
-				regs->registers[i] + j);
+		for (j = 0; j < count; j++) {
+			u32 offset = regs->registers[i] + j;
+			u32 val;
+
+			if (rscc)
+				val = gmu_read_rscc(gmu, offset);
+			else
+				val = gmu_read(gmu, offset);
+
+			obj->data[index++] = val;
+		}
 	}
 }
 
@@ -777,7 +786,9 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu,
 
 	/* Get the CX GMU registers from AHB */
 	_a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[0],
-		&a6xx_state->gmu_registers[0]);
+		&a6xx_state->gmu_registers[0], false);
+	_a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[1],
+		&a6xx_state->gmu_registers[1], true);
 
 	if (!a6xx_gmu_gx_is_on(&a6xx_gpu->gmu))
 		return;
@@ -785,8 +796,8 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu,
 	/* Set the fence to ALLOW mode so we can access the registers */
 	gpu_write(gpu, REG_A6XX_GMU_AO_AHB_FENCE_CTRL, 0);
 
-	_a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[1],
-		&a6xx_state->gmu_registers[1]);
+	_a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[2],
+		&a6xx_state->gmu_registers[2], false);
 }
 
 #define A6XX_GBIF_REGLIST_SIZE   1

drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h

@@ -341,10 +341,6 @@ static const u32 a6xx_gmu_cx_registers[] = {
 	0x5157, 0x5158, 0x515d, 0x515d, 0x5162, 0x5162, 0x5164, 0x5165,
 	0x5180, 0x5186, 0x5190, 0x519e, 0x51c0, 0x51c0, 0x51c5, 0x51cc,
 	0x51e0, 0x51e2, 0x51f0, 0x51f0, 0x5200, 0x5201,
-	/* GPU RSCC */
-	0x8c8c, 0x8c8c, 0x8d01, 0x8d02, 0x8f40, 0x8f42, 0x8f44, 0x8f47,
-	0x8f4c, 0x8f87, 0x8fec, 0x8fef, 0x8ff4, 0x902f, 0x9094, 0x9097,
-	0x909c, 0x90d7, 0x913c, 0x913f, 0x9144, 0x917f,
 	/* GMU AO */
 	0x9300, 0x9316, 0x9400, 0x9400,
 	/* GPU CC */
@@ -357,8 +353,16 @@ static const u32 a6xx_gmu_cx_registers[] = {
 	0xbc00, 0xbc16, 0xbc20, 0xbc27,
 };
 
+static const u32 a6xx_gmu_cx_rscc_registers[] = {
+	/* GPU RSCC */
+	0x008c, 0x008c, 0x0101, 0x0102, 0x0340, 0x0342, 0x0344, 0x0347,
+	0x034c, 0x0387, 0x03ec, 0x03ef, 0x03f4, 0x042f, 0x0494, 0x0497,
+	0x049c, 0x04d7, 0x053c, 0x053f, 0x0544, 0x057f,
+};
+
 static const struct a6xx_registers a6xx_gmu_reglist[] = {
 	REGS(a6xx_gmu_cx_registers, 0, 0),
+	REGS(a6xx_gmu_cx_rscc_registers, 0, 0),
 	REGS(a6xx_gmu_gx_registers, 0, 0),
 };
 

drivers/gpu/drm/msm/adreno/a6xx_hfi.c

@@ -281,6 +281,76 @@ static void a618_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
 	msg->cnoc_cmds_data[1][0] =  0x60000001;
 }
 
+static void a640_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
+{
+	/*
+	 * Send a single "off" entry just to get things running
+	 * TODO: bus scaling
+	 */
+	msg->bw_level_num = 1;
+
+	msg->ddr_cmds_num = 3;
+	msg->ddr_wait_bitmask = 0x01;
+
+	msg->ddr_cmds_addrs[0] = 0x50000;
+	msg->ddr_cmds_addrs[1] = 0x5003c;
+	msg->ddr_cmds_addrs[2] = 0x5000c;
+
+	msg->ddr_cmds_data[0][0] =  0x40000000;
+	msg->ddr_cmds_data[0][1] =  0x40000000;
+	msg->ddr_cmds_data[0][2] =  0x40000000;
+
+	/*
+	 * These are the CX (CNOC) votes - these are used by the GMU but the
+	 * votes are known and fixed for the target
+	 */
+	msg->cnoc_cmds_num = 3;
+	msg->cnoc_wait_bitmask = 0x01;
+
+	msg->cnoc_cmds_addrs[0] = 0x50034;
+	msg->cnoc_cmds_addrs[1] = 0x5007c;
+	msg->cnoc_cmds_addrs[2] = 0x5004c;
+
+	msg->cnoc_cmds_data[0][0] =  0x40000000;
+	msg->cnoc_cmds_data[0][1] =  0x00000000;
+	msg->cnoc_cmds_data[0][2] =  0x40000000;
+
+	msg->cnoc_cmds_data[1][0] =  0x60000001;
+	msg->cnoc_cmds_data[1][1] =  0x20000001;
+	msg->cnoc_cmds_data[1][2] =  0x60000001;
+}
+
+static void a650_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
+{
+	/*
+	 * Send a single "off" entry just to get things running
+	 * TODO: bus scaling
+	 */
+	msg->bw_level_num = 1;
+
+	msg->ddr_cmds_num = 3;
+	msg->ddr_wait_bitmask = 0x01;
+
+	msg->ddr_cmds_addrs[0] = 0x50000;
+	msg->ddr_cmds_addrs[1] = 0x50004;
+	msg->ddr_cmds_addrs[2] = 0x5007c;
+
+	msg->ddr_cmds_data[0][0] =  0x40000000;
+	msg->ddr_cmds_data[0][1] =  0x40000000;
+	msg->ddr_cmds_data[0][2] =  0x40000000;
+
+	/*
+	 * These are the CX (CNOC) votes - these are used by the GMU but the
+	 * votes are known and fixed for the target
+	 */
+	msg->cnoc_cmds_num = 1;
+	msg->cnoc_wait_bitmask = 0x01;
+
+	msg->cnoc_cmds_addrs[0] = 0x500a4;
+	msg->cnoc_cmds_data[0][0] =  0x40000000;
+	msg->cnoc_cmds_data[1][0] =  0x60000001;
+}
+
 static void a6xx_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
 {
 	/* Send a single "off" entry since the 630 GMU doesn't do bus scaling */
@@ -327,6 +397,10 @@ static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu)
 
 	if (adreno_is_a618(adreno_gpu))
 		a618_build_bw_table(&msg);
+	else if (adreno_is_a640(adreno_gpu))
+		a640_build_bw_table(&msg);
+	else if (adreno_is_a650(adreno_gpu))
+		a650_build_bw_table(&msg);
 	else
 		a6xx_build_bw_table(&msg);
 

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

@@ -200,6 +200,7 @@ static const struct adreno_info gpulist[] = {
 		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init = a6xx_gpu_init,
 		.zapfw = "a630_zap.mdt",
+		.hwcg = a630_hwcg,
 	}, {
 		.rev = ADRENO_REV(6, 4, 0, ANY_ID),
 		.revn = 640,
@@ -212,6 +213,7 @@ static const struct adreno_info gpulist[] = {
 		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init = a6xx_gpu_init,
 		.zapfw = "a640_zap.mdt",
+		.hwcg = a640_hwcg,
 	}, {
 		.rev = ADRENO_REV(6, 5, 0, ANY_ID),
 		.revn = 650,
@@ -224,6 +226,7 @@ static const struct adreno_info gpulist[] = {
 		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init = a6xx_gpu_init,
 		.zapfw = "a650_zap.mdt",
+		.hwcg = a650_hwcg,
 	},
 };
 

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

@@ -895,7 +895,7 @@ static int adreno_get_legacy_pwrlevels(struct device *dev)
 	return 0;
 }
 
-static int adreno_get_pwrlevels(struct device *dev,
+static void adreno_get_pwrlevels(struct device *dev,
 		struct msm_gpu *gpu)
 {
 	unsigned long freq = ULONG_MAX;
@@ -930,24 +930,6 @@ static int adreno_get_pwrlevels(struct device *dev,
 	}
 
 	DBG("fast_rate=%u, slow_rate=27000000", gpu->fast_rate);
-
-	/* Check for an interconnect path for the bus */
-	gpu->icc_path = of_icc_get(dev, "gfx-mem");
-	if (!gpu->icc_path) {
-		/*
-		 * Keep compatbility with device trees that don't have an
-		 * interconnect-names property.
-		 */
-		gpu->icc_path = of_icc_get(dev, NULL);
-	}
-	if (IS_ERR(gpu->icc_path))
-		gpu->icc_path = NULL;
-
-	gpu->ocmem_icc_path = of_icc_get(dev, "ocmem");
-	if (IS_ERR(gpu->ocmem_icc_path))
-		gpu->ocmem_icc_path = NULL;
-
-	return 0;
 }
 
 int adreno_gpu_ocmem_init(struct device *dev, struct adreno_gpu *adreno_gpu,
@@ -993,9 +975,11 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 		struct adreno_gpu *adreno_gpu,
 		const struct adreno_gpu_funcs *funcs, int nr_rings)
 {
-	struct adreno_platform_config *config = pdev->dev.platform_data;
+	struct device *dev = &pdev->dev;
+	struct adreno_platform_config *config = dev->platform_data;
 	struct msm_gpu_config adreno_gpu_config  = { 0 };
 	struct msm_gpu *gpu = &adreno_gpu->base;
+	int ret;
 
 	adreno_gpu->funcs = funcs;
 	adreno_gpu->info = adreno_info(config->rev);
@@ -1007,27 +991,59 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 
 	adreno_gpu_config.nr_rings = nr_rings;
 
-	adreno_get_pwrlevels(&pdev->dev, gpu);
+	adreno_get_pwrlevels(dev, gpu);
 
-	pm_runtime_set_autosuspend_delay(&pdev->dev,
+	pm_runtime_set_autosuspend_delay(dev,
 		adreno_gpu->info->inactive_period);
-	pm_runtime_use_autosuspend(&pdev->dev);
-	pm_runtime_enable(&pdev->dev);
+	pm_runtime_use_autosuspend(dev);
+	pm_runtime_enable(dev);
 
-	return msm_gpu_init(drm, pdev, &adreno_gpu->base, &funcs->base,
+	ret = msm_gpu_init(drm, pdev, &adreno_gpu->base, &funcs->base,
 			adreno_gpu->info->name, &adreno_gpu_config);
+	if (ret)
+		return ret;
+
+	/*
+	 * The legacy case, before "interconnect-names", only has a
+	 * single interconnect path which is equivalent to "gfx-mem"
+	 */
+	if (!of_find_property(dev->of_node, "interconnect-names", NULL)) {
+		gpu->icc_path = of_icc_get(dev, NULL);
+	} else {
+		gpu->icc_path = of_icc_get(dev, "gfx-mem");
+		gpu->ocmem_icc_path = of_icc_get(dev, "ocmem");
+	}
+
+	if (IS_ERR(gpu->icc_path)) {
+		ret = PTR_ERR(gpu->icc_path);
+		gpu->icc_path = NULL;
+		return ret;
+	}
+
+	if (IS_ERR(gpu->ocmem_icc_path)) {
+		ret = PTR_ERR(gpu->ocmem_icc_path);
+		gpu->ocmem_icc_path = NULL;
+		/* allow -ENODATA, ocmem icc is optional */
+		if (ret != -ENODATA)
+			return ret;
+	}
+
+	return 0;
 }
 
 void adreno_gpu_cleanup(struct adreno_gpu *adreno_gpu)
 {
 	struct msm_gpu *gpu = &adreno_gpu->base;
+	struct msm_drm_private *priv = gpu->dev->dev_private;
 	unsigned int i;
 
 	for (i = 0; i < ARRAY_SIZE(adreno_gpu->info->fw); i++)
 		release_firmware(adreno_gpu->fw[i]);
 
-	icc_put(gpu->icc_path);
-	icc_put(gpu->ocmem_icc_path);
+	pm_runtime_disable(&priv->gpu_pdev->dev);
 
 	msm_gpu_cleanup(&adreno_gpu->base);
+
+	icc_put(gpu->icc_path);
+	icc_put(gpu->ocmem_icc_path);
 }

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

@@ -68,6 +68,13 @@ struct adreno_gpu_funcs {
 	int (*get_timestamp)(struct msm_gpu *gpu, uint64_t *value);
 };
 
+struct adreno_reglist {
+	u32 offset;
+	u32 value;
+};
+
+extern const struct adreno_reglist a630_hwcg[], a640_hwcg[], a650_hwcg[];
+
 struct adreno_info {
 	struct adreno_rev rev;
 	uint32_t revn;
@@ -78,6 +85,7 @@ struct adreno_info {
 	struct msm_gpu *(*init)(struct drm_device *dev);
 	const char *zapfw;
 	u32 inactive_period;
+	const struct adreno_reglist *hwcg;
 };
 
 const struct adreno_info *adreno_info(struct adreno_rev rev);

drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c

@@ -7,6 +7,7 @@
 #include <linux/debugfs.h>
 #include <linux/errno.h>
 #include <linux/mutex.h>
+#include <linux/pm_opp.h>
 #include <linux/sort.h>
 #include <linux/clk.h>
 #include <linux/bitmap.h>
@@ -218,7 +219,7 @@ static int _dpu_core_perf_set_core_clk_rate(struct dpu_kms *kms, u64 rate)
 		rate = core_clk->max_rate;
 
 	core_clk->rate = rate;
-	return msm_dss_clk_set_rate(core_clk, 1);
+	return dev_pm_opp_set_rate(&kms->pdev->dev, core_clk->rate);
 }
 
 static u64 _dpu_core_perf_get_core_clk_rate(struct dpu_kms *kms)

drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c

@@ -389,14 +389,14 @@ static void dpu_crtc_frame_event_cb(void *data, u32 event)
 	spin_unlock_irqrestore(&dpu_crtc->spin_lock, flags);
 
 	if (!fevent) {
-		DRM_ERROR("crtc%d event %d overflow\n", crtc->base.id, event);
+		DRM_ERROR_RATELIMITED("crtc%d event %d overflow\n", crtc->base.id, event);
 		return;
 	}
 
 	fevent->event = event;
 	fevent->crtc = crtc;
 	fevent->ts = ktime_get();
-	kthread_queue_work(&priv->event_thread[crtc_id].worker, &fevent->work);
+	kthread_queue_work(priv->event_thread[crtc_id].worker, &fevent->work);
 }
 
 void dpu_crtc_complete_commit(struct drm_crtc *crtc)

drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c

@@ -208,6 +208,36 @@ struct dpu_encoder_virt {
 
 #define to_dpu_encoder_virt(x) container_of(x, struct dpu_encoder_virt, base)
 
+static u32 dither_matrix[DITHER_MATRIX_SZ] = {
+	15, 7, 13, 5, 3, 11, 1, 9, 12, 4, 14, 6, 0, 8, 2, 10
+};
+
+static void _dpu_encoder_setup_dither(struct dpu_hw_pingpong *hw_pp, unsigned bpc)
+{
+	struct dpu_hw_dither_cfg dither_cfg = { 0 };
+
+	if (!hw_pp->ops.setup_dither)
+		return;
+
+	switch (bpc) {
+	case 6:
+		dither_cfg.c0_bitdepth = 6;
+		dither_cfg.c1_bitdepth = 6;
+		dither_cfg.c2_bitdepth = 6;
+		dither_cfg.c3_bitdepth = 6;
+		dither_cfg.temporal_en = 0;
+		break;
+	default:
+		hw_pp->ops.setup_dither(hw_pp, NULL);
+		return;
+	}
+
+	memcpy(&dither_cfg.matrix, dither_matrix,
+			sizeof(u32) * DITHER_MATRIX_SZ);
+
+	hw_pp->ops.setup_dither(hw_pp, &dither_cfg);
+}
+
 void dpu_encoder_helper_report_irq_timeout(struct dpu_encoder_phys *phys_enc,
 		enum dpu_intr_idx intr_idx)
 {
@@ -1058,7 +1088,7 @@ static void _dpu_encoder_virt_enable_helper(struct drm_encoder *drm_enc)
 {
 	struct dpu_encoder_virt *dpu_enc = NULL;
 	struct msm_drm_private *priv;
-	struct dpu_kms *dpu_kms;
+	int i;
 
 	if (!drm_enc || !drm_enc->dev) {
 		DPU_ERROR("invalid parameters\n");
@@ -1066,7 +1096,6 @@ static void _dpu_encoder_virt_enable_helper(struct drm_encoder *drm_enc)
 	}
 
 	priv = drm_enc->dev->dev_private;
-	dpu_kms = to_dpu_kms(priv->kms);
 
 	dpu_enc = to_dpu_encoder_virt(drm_enc);
 	if (!dpu_enc || !dpu_enc->cur_master) {
@@ -1074,13 +1103,17 @@ static void _dpu_encoder_virt_enable_helper(struct drm_encoder *drm_enc)
 		return;
 	}
 
-	if (dpu_enc->cur_master->hw_mdptop &&
-			dpu_enc->cur_master->hw_mdptop->ops.reset_ubwc)
-		dpu_enc->cur_master->hw_mdptop->ops.reset_ubwc(
-				dpu_enc->cur_master->hw_mdptop,
-				dpu_kms->catalog);
-
 	_dpu_encoder_update_vsync_source(dpu_enc, &dpu_enc->disp_info);
+
+	if (dpu_enc->disp_info.intf_type == DRM_MODE_ENCODER_DSI &&
+			!WARN_ON(dpu_enc->num_phys_encs == 0)) {
+		unsigned bpc = dpu_enc->phys_encs[0]->connector->display_info.bpc;
+		for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) {
+			if (!dpu_enc->hw_pp[i])
+				continue;
+			_dpu_encoder_setup_dither(dpu_enc->hw_pp[i], bpc);
+		}
+	}
 }
 
 void dpu_encoder_virt_runtime_resume(struct drm_encoder *drm_enc)

drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c

@@ -245,30 +245,14 @@ static int dpu_hw_ctl_get_bitmask_intf(struct dpu_hw_ctl *ctx,
 static int dpu_hw_ctl_get_bitmask_intf_v1(struct dpu_hw_ctl *ctx,
 		u32 *flushbits, enum dpu_intf intf)
 {
-	switch (intf) {
-	case INTF_0:
-	case INTF_1:
-		*flushbits |= BIT(31);
-		break;
-	default:
-		return 0;
-	}
+	*flushbits |= BIT(31);
 	return 0;
 }
 
 static int dpu_hw_ctl_active_get_bitmask_intf(struct dpu_hw_ctl *ctx,
 		u32 *flushbits, enum dpu_intf intf)
 {
-	switch (intf) {
-	case INTF_0:
-		*flushbits |= BIT(0);
-		break;
-	case INTF_1:
-		*flushbits |= BIT(1);
-		break;
-	default:
-		return 0;
-	}
+	*flushbits |= BIT(intf - INTF_0);
 	return 0;
 }
 

drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h

@@ -171,6 +171,7 @@ enum dpu_ctl {
 	CTL_2,
 	CTL_3,
 	CTL_4,
+	CTL_5,
 	CTL_MAX
 };
 
@@ -180,6 +181,7 @@ enum dpu_pingpong {
 	PINGPONG_2,
 	PINGPONG_3,
 	PINGPONG_4,
+	PINGPONG_5,
 	PINGPONG_S0,
 	PINGPONG_MAX
 };