12 files changed, 225 insertions, 91 deletions

diff --git a/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c b/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c
index fc2c905b6c9e..c9d11d57aed6 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c
@@ -117,13 +117,13 @@ reset_set(void *data, u64 val)
 
 	if (a5xx_gpu->pm4_bo) {
 		msm_gem_unpin_iova(a5xx_gpu->pm4_bo, gpu->aspace);
-		drm_gem_object_put_locked(a5xx_gpu->pm4_bo);
+		drm_gem_object_put(a5xx_gpu->pm4_bo);
 		a5xx_gpu->pm4_bo = NULL;
 	}
 
 	if (a5xx_gpu->pfp_bo) {
 		msm_gem_unpin_iova(a5xx_gpu->pfp_bo, gpu->aspace);
-		drm_gem_object_put_locked(a5xx_gpu->pfp_bo);
+		drm_gem_object_put(a5xx_gpu->pfp_bo);
 		a5xx_gpu->pfp_bo = NULL;
 	}
 
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 7a271de9a212..5e2750eb3810 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -18,6 +18,18 @@ static void a5xx_dump(struct msm_gpu *gpu);
 
 #define GPU_PAS_ID 13
 
+static void update_shadow_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
+
+	if (a5xx_gpu->has_whereami) {
+		OUT_PKT7(ring, CP_WHERE_AM_I, 2);
+		OUT_RING(ring, lower_32_bits(shadowptr(a5xx_gpu, ring)));
+		OUT_RING(ring, upper_32_bits(shadowptr(a5xx_gpu, ring)));
+	}
+}
+
 void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
 		bool sync)
 {
@@ -30,11 +42,8 @@ void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
 	 * Most flush operations need to issue a WHERE_AM_I opcode to sync up
 	 * the rptr shadow
 	 */
-	if (a5xx_gpu->has_whereami && sync) {
-		OUT_PKT7(ring, CP_WHERE_AM_I, 2);
-		OUT_RING(ring, lower_32_bits(shadowptr(a5xx_gpu, ring)));
-		OUT_RING(ring, upper_32_bits(shadowptr(a5xx_gpu, ring)));
-	}
+	if (sync)
+		update_shadow_rptr(gpu, ring);
 
 	spin_lock_irqsave(&ring->preempt_lock, flags);
 
@@ -168,6 +177,16 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 			ibs++;
 			break;
 		}
+
+		/*
+		 * Periodically update shadow-wptr if needed, so that we
+		 * can see partial progress of submits with large # of
+		 * cmds.. otherwise we could needlessly stall waiting for
+		 * ringbuffer state, simply due to looking at a shadow
+		 * rptr value that has not been updated
+		 */
+		if ((ibs % 32) == 0)
+			update_shadow_rptr(gpu, ring);
 	}
 
 	/*
@@ -1415,7 +1434,7 @@ struct a5xx_gpu_state {
 static int a5xx_crashdumper_init(struct msm_gpu *gpu,
 		struct a5xx_crashdumper *dumper)
 {
-	dumper->ptr = msm_gem_kernel_new_locked(gpu->dev,
+	dumper->ptr = msm_gem_kernel_new(gpu->dev,
 		SZ_1M, MSM_BO_WC, gpu->aspace,
 		&dumper->bo, &dumper->iova);
 
@@ -1517,7 +1536,7 @@ static void a5xx_gpu_state_get_hlsq_regs(struct msm_gpu *gpu,
 
 	if (a5xx_crashdumper_run(gpu, &dumper)) {
 		kfree(a5xx_state->hlsqregs);
-		msm_gem_kernel_put(dumper.bo, gpu->aspace, true);
+		msm_gem_kernel_put(dumper.bo, gpu->aspace);
 		return;
 	}
 
@@ -1525,7 +1544,7 @@ static void a5xx_gpu_state_get_hlsq_regs(struct msm_gpu *gpu,
 	memcpy(a5xx_state->hlsqregs, dumper.ptr + (256 * SZ_1K),
 		count * sizeof(u32));
 
-	msm_gem_kernel_put(dumper.bo, gpu->aspace, true);
+	msm_gem_kernel_put(dumper.bo, gpu->aspace);
 }
 
 static struct msm_gpu_state *a5xx_gpu_state_get(struct msm_gpu *gpu)
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_power.c b/drivers/gpu/drm/msm/adreno/a5xx_power.c
index cdb165236a88..0e63a1429189 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_power.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_power.c
@@ -362,7 +362,7 @@ void a5xx_gpmu_ucode_init(struct msm_gpu *gpu)
 	 */
 	bosize = (cmds_size + (cmds_size / TYPE4_MAX_PAYLOAD) + 1) << 2;
 
-	ptr = msm_gem_kernel_new_locked(drm, bosize,
+	ptr = msm_gem_kernel_new(drm, bosize,
 		MSM_BO_WC | MSM_BO_GPU_READONLY, gpu->aspace,
 		&a5xx_gpu->gpmu_bo, &a5xx_gpu->gpmu_iova);
 	if (IS_ERR(ptr))
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
index ee72510ff8ce..8abc9a2b114a 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
@@ -240,7 +240,7 @@ static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu,
 		A5XX_PREEMPT_COUNTER_SIZE,
 		MSM_BO_WC, gpu->aspace, &counters_bo, &counters_iova);
 	if (IS_ERR(counters)) {
-		msm_gem_kernel_put(bo, gpu->aspace, true);
+		msm_gem_kernel_put(bo, gpu->aspace);
 		return PTR_ERR(counters);
 	}
 
@@ -272,9 +272,8 @@ void a5xx_preempt_fini(struct msm_gpu *gpu)
 	int i;
 
 	for (i = 0; i < gpu->nr_rings; i++) {
-		msm_gem_kernel_put(a5xx_gpu->preempt_bo[i], gpu->aspace, true);
-		msm_gem_kernel_put(a5xx_gpu->preempt_counters_bo[i],
-			gpu->aspace, true);
+		msm_gem_kernel_put(a5xx_gpu->preempt_bo[i], gpu->aspace);
+		msm_gem_kernel_put(a5xx_gpu->preempt_counters_bo[i], gpu->aspace);
 	}
 }
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index b349692219b7..a7c58018959f 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -519,9 +519,9 @@ static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu)
 	if (!pdcptr)
 		goto err;
 
-	if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu))
+	if (adreno_is_a650(adreno_gpu) || adreno_is_a660_family(adreno_gpu))
 		pdc_in_aop = true;
-	else if (adreno_is_a618(adreno_gpu) || adreno_is_a640(adreno_gpu))
+	else if (adreno_is_a618(adreno_gpu) || adreno_is_a640_family(adreno_gpu))
 		pdc_address_offset = 0x30090;
 	else
 		pdc_address_offset = 0x30080;
@@ -933,6 +933,7 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 
 	/* Use a known rate to bring up the GMU */
 	clk_set_rate(gmu->core_clk, 200000000);
+	clk_set_rate(gmu->hub_clk, 150000000);
 	ret = clk_bulk_prepare_enable(gmu->nr_clocks, gmu->clocks);
 	if (ret) {
 		pm_runtime_put(gmu->gxpd);
@@ -1129,12 +1130,12 @@ int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu)
 
 static void a6xx_gmu_memory_free(struct a6xx_gmu *gmu)
 {
-	msm_gem_kernel_put(gmu->hfi.obj, gmu->aspace, false);
-	msm_gem_kernel_put(gmu->debug.obj, gmu->aspace, false);
-	msm_gem_kernel_put(gmu->icache.obj, gmu->aspace, false);
-	msm_gem_kernel_put(gmu->dcache.obj, gmu->aspace, false);
-	msm_gem_kernel_put(gmu->dummy.obj, gmu->aspace, false);
-	msm_gem_kernel_put(gmu->log.obj, gmu->aspace, false);
+	msm_gem_kernel_put(gmu->hfi.obj, gmu->aspace);
+	msm_gem_kernel_put(gmu->debug.obj, gmu->aspace);
+	msm_gem_kernel_put(gmu->icache.obj, gmu->aspace);
+	msm_gem_kernel_put(gmu->dcache.obj, gmu->aspace);
+	msm_gem_kernel_put(gmu->dummy.obj, gmu->aspace);
+	msm_gem_kernel_put(gmu->log.obj, gmu->aspace);
 
 	gmu->aspace->mmu->funcs->detach(gmu->aspace->mmu);
 	msm_gem_address_space_put(gmu->aspace);
@@ -1393,6 +1394,9 @@ static int a6xx_gmu_clocks_probe(struct a6xx_gmu *gmu)
 	gmu->core_clk = msm_clk_bulk_get_clock(gmu->clocks,
 		gmu->nr_clocks, "gmu");
 
+	gmu->hub_clk = msm_clk_bulk_get_clock(gmu->clocks,
+		gmu->nr_clocks, "hub");
+
 	return 0;
 }
 
@@ -1504,7 +1508,7 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 	 * are otherwise unused by a660.
 	 */
 	gmu->dummy.size = SZ_4K;
-	if (adreno_is_a660(adreno_gpu)) {
+	if (adreno_is_a660_family(adreno_gpu)) {
 		ret = a6xx_gmu_memory_alloc(gmu, &gmu->debug, SZ_4K * 7, 0x60400000);
 		if (ret)
 			goto err_memory;
@@ -1522,7 +1526,7 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 			SZ_16M - SZ_16K, 0x04000);
 		if (ret)
 			goto err_memory;
-	} else if (adreno_is_a640(adreno_gpu)) {
+	} else if (adreno_is_a640_family(adreno_gpu)) {
 		ret = a6xx_gmu_memory_alloc(gmu, &gmu->icache,
 			SZ_256K - SZ_16K, 0x04000);
 		if (ret)
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
index 71dfa60070cc..3c74f64e3126 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
@@ -66,6 +66,7 @@ struct a6xx_gmu {
 	int nr_clocks;
 	struct clk_bulk_data *clocks;
 	struct clk *core_clk;
+	struct clk *hub_clk;
 
 	/* current performance index set externally */
 	int current_perf_index;
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 9c5e4618aa0a..40c9fef457a4 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -52,21 +52,25 @@ static bool a6xx_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 	return true;
 }
 
-static void a6xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
+static void update_shadow_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
-	uint32_t wptr;
-	unsigned long flags;
 
 	/* Expanded APRIV doesn't need to issue the WHERE_AM_I opcode */
 	if (a6xx_gpu->has_whereami && !adreno_gpu->base.hw_apriv) {
-		struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
-
 		OUT_PKT7(ring, CP_WHERE_AM_I, 2);
 		OUT_RING(ring, lower_32_bits(shadowptr(a6xx_gpu, ring)));
 		OUT_RING(ring, upper_32_bits(shadowptr(a6xx_gpu, ring)));
 	}
+}
+
+static void a6xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
+{
+	uint32_t wptr;
+	unsigned long flags;
+
+	update_shadow_rptr(gpu, ring);
 
 	spin_lock_irqsave(&ring->preempt_lock, flags);
 
@@ -145,7 +149,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 	struct msm_ringbuffer *ring = submit->ring;
-	unsigned int i;
+	unsigned int i, ibs = 0;
 
 	a6xx_set_pagetable(a6xx_gpu, ring, submit->queue->ctx);
 
@@ -181,8 +185,19 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 			OUT_RING(ring, lower_32_bits(submit->cmd[i].iova));
 			OUT_RING(ring, upper_32_bits(submit->cmd[i].iova));
 			OUT_RING(ring, submit->cmd[i].size);
+			ibs++;
 			break;
 		}
+
+		/*
+		 * Periodically update shadow-wptr if needed, so that we
+		 * can see partial progress of submits with large # of
+		 * cmds.. otherwise we could needlessly stall waiting for
+		 * ringbuffer state, simply due to looking at a shadow
+		 * rptr value that has not been updated
+		 */
+		if ((ibs % 32) == 0)
+			update_shadow_rptr(gpu, ring);
 	}
 
 	get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP(0),
@@ -652,7 +667,7 @@ static void a6xx_set_cp_protect(struct msm_gpu *gpu)
 		regs = a650_protect;
 		count = ARRAY_SIZE(a650_protect);
 		count_max = 48;
-	} else if (adreno_is_a660(adreno_gpu)) {
+	} else if (adreno_is_a660_family(adreno_gpu)) {
 		regs = a660_protect;
 		count = ARRAY_SIZE(a660_protect);
 		count_max = 48;
@@ -683,7 +698,7 @@ static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
 	if (adreno_is_a618(adreno_gpu))
 		return;
 
-	if (adreno_is_a640(adreno_gpu))
+	if (adreno_is_a640_family(adreno_gpu))
 		amsbc = 1;
 
 	if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu)) {
@@ -694,6 +709,13 @@ static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
 		uavflagprd_inv = 2;
 	}
 
+	if (adreno_is_7c3(adreno_gpu)) {
+		lower_bit = 1;
+		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);
@@ -740,6 +762,7 @@ static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
 {
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 	struct msm_gpu *gpu = &adreno_gpu->base;
+	const char *sqe_name = adreno_gpu->info->fw[ADRENO_FW_SQE];
 	u32 *buf = msm_gem_get_vaddr(obj);
 	bool ret = false;
 
@@ -756,8 +779,7 @@ static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
 	 *
 	 * 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)) {
+	if (!strcmp(sqe_name, "a630_sqe.fw")) {
 		/*
 		 * If the lowest nibble is 0xa that is an indication that this
 		 * microcode has been patched. The actual version is in dword
@@ -778,7 +800,7 @@ 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 if (adreno_is_a650(adreno_gpu)) {
+	} else if (!strcmp(sqe_name, "a650_sqe.fw")) {
 		if ((buf[0] & 0xfff) >= 0x095) {
 			ret = true;
 			goto out;
@@ -787,7 +809,7 @@ static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
 		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)) {
+	} else if (!strcmp(sqe_name, "a660_sqe.fw")) {
 		ret = true;
 	} else {
 		DRM_DEV_ERROR(&gpu->pdev->dev,
@@ -897,7 +919,8 @@ 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_family(adreno_gpu)) {
+	if (adreno_is_a640_family(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);
@@ -935,13 +958,14 @@ 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_family(adreno_gpu))
+	if (adreno_is_a640_family(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))
+	if (adreno_is_a660_family(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_CP_LPAC_PROG_FIFO_SIZE, 0x00000020);
 
 	/* Setting the mem pool size */
@@ -952,8 +976,10 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	*/
 	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))
+	else if (adreno_is_a640_family(adreno_gpu) || adreno_is_7c3(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00200200);
+	else if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu))
+		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00300200);
 	else
 		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00180000);
 
@@ -990,13 +1016,15 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	/* Protect registers from the CP */
 	a6xx_set_cp_protect(gpu);
 
-	if (adreno_is_a660(adreno_gpu)) {
+	if (adreno_is_a660_family(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);
 	}
 
+	/* Set dualQ + disable afull for A660 GPU */
+	if (adreno_is_a660(adreno_gpu))
+		gpu_write(gpu, REG_A6XX_UCHE_CMDQ_CONFIG, 0x66906);
+
 	/* Enable expanded apriv for targets that support it */
 	if (gpu->hw_apriv) {
 		gpu_write(gpu, REG_A6XX_CP_APRIV_CNTL,
@@ -1035,7 +1063,7 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 
 	if (adreno_gpu->base.hw_apriv || a6xx_gpu->has_whereami) {
 		if (!a6xx_gpu->shadow_bo) {
-			a6xx_gpu->shadow = msm_gem_kernel_new_locked(gpu->dev,
+			a6xx_gpu->shadow = msm_gem_kernel_new(gpu->dev,
 				sizeof(u32) * gpu->nr_rings,
 				MSM_BO_WC | MSM_BO_MAP_PRIV,
 				gpu->aspace, &a6xx_gpu->shadow_bo,
@@ -1383,13 +1411,13 @@ 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;
+	u32 gpu_scid, cntl1_regval = 0;
 
 	if (IS_ERR(a6xx_gpu->llc_mmio))
 		return;
 
 	if (!llcc_slice_activate(a6xx_gpu->llc_slice)) {
-		u32 gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice);
+		gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice);
 
 		gpu_scid &= 0x1f;
 		cntl1_regval = (gpu_scid << 0) | (gpu_scid << 5) | (gpu_scid << 10) |
@@ -1409,26 +1437,34 @@ static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu)
 		}
 	}
 
-	if (cntl1_regval) {
+	if (!cntl1_regval)
+		return;
+
+	/*
+	 * Program the slice IDs for the various GPU blocks and GPU MMU
+	 * pagetables
+	 */
+	if (!a6xx_gpu->have_mmu500) {
+		a6xx_llc_write(a6xx_gpu,
+			REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_1, cntl1_regval);
+
 		/*
-		 * Program the slice IDs for the various GPU blocks and GPU MMU
-		 * pagetables
+		 * Program cacheability overrides to not allocate cache
+		 * lines on a write miss
 		 */
-		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);
-		}
+		a6xx_llc_rmw(a6xx_gpu,
+			REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_0, 0xF, 0x03);
+		return;
 	}
+
+	gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL1, GENMASK(24, 0), cntl1_regval);
+
+	/* On A660, the SCID programming for UCHE traffic is done in
+	 * A6XX_GBIF_SCACHE_CNTL0[14:10]
+	 */
+	if (adreno_is_a660_family(adreno_gpu))
+		gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL0, (0x1f << 10) |
+			(1 << 8), (gpu_scid << 10) | (1 << 8));
 }
 
 static void a6xx_llc_slices_destroy(struct a6xx_gpu *a6xx_gpu)
@@ -1477,7 +1513,7 @@ static int a6xx_pm_resume(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
-	msm_gpu_resume_devfreq(gpu);
+	msm_devfreq_resume(gpu);
 
 	a6xx_llc_activate(a6xx_gpu);
 
@@ -1494,7 +1530,7 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu)
 
 	a6xx_llc_deactivate(a6xx_gpu);
 
-	devfreq_suspend_device(gpu->devfreq.devfreq);
+	msm_devfreq_suspend(gpu);
 
 	ret = a6xx_gmu_stop(a6xx_gpu);
 	if (ret)
@@ -1667,11 +1703,11 @@ static u32 a618_get_speed_bin(u32 fuse)
 	return UINT_MAX;
 }
 
-static u32 fuse_to_supp_hw(struct device *dev, u32 revn, u32 fuse)
+static u32 fuse_to_supp_hw(struct device *dev, struct adreno_rev rev, u32 fuse)
 {
 	u32 val = UINT_MAX;
 
-	if (revn == 618)
+	if (adreno_cmp_rev(ADRENO_REV(6, 1, 8, ANY_ID), rev))
 		val = a618_get_speed_bin(fuse);
 
 	if (val == UINT_MAX) {
@@ -1684,14 +1720,13 @@ static u32 fuse_to_supp_hw(struct device *dev, u32 revn, u32 fuse)
 	return (1 << val);
 }
 
-static int a6xx_set_supported_hw(struct device *dev, struct a6xx_gpu *a6xx_gpu,
-		u32 revn)
+static int a6xx_set_supported_hw(struct device *dev, struct adreno_rev rev)
 {
 	u32 supp_hw = UINT_MAX;
-	u16 speedbin;
+	u32 speedbin;
 	int ret;
 
-	ret = nvmem_cell_read_u16(dev, "speed_bin", &speedbin);
+	ret = nvmem_cell_read_variable_le_u32(dev, "speed_bin", &speedbin);
 	/*
 	 * -ENOENT means that the platform doesn't support speedbin which is
 	 * fine
@@ -1704,9 +1739,8 @@ static int a6xx_set_supported_hw(struct device *dev, struct a6xx_gpu *a6xx_gpu,
 			      ret);
 		goto done;
 	}
-	speedbin = le16_to_cpu(speedbin);
 
-	supp_hw = fuse_to_supp_hw(dev, revn, speedbin);
+	supp_hw = fuse_to_supp_hw(dev, rev, speedbin);
 
 done:
 	ret = devm_pm_opp_set_supported_hw(dev, &supp_hw, 1);
@@ -1772,12 +1806,13 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 	 */
 	info = adreno_info(config->rev);
 
-	if (info && (info->revn == 650 || info->revn == 660))
+	if (info && (info->revn == 650 || info->revn == 660 ||
+			adreno_cmp_rev(ADRENO_REV(6, 3, 5, ANY_ID), info->rev)))
 		adreno_gpu->base.hw_apriv = true;
 
 	a6xx_llc_slices_init(pdev, a6xx_gpu);
 
-	ret = a6xx_set_supported_hw(&pdev->dev, a6xx_gpu, info->revn);
+	ret = a6xx_set_supported_hw(&pdev->dev, config->rev);
 	if (ret) {
 		a6xx_destroy(&(a6xx_gpu->base.base));
 		return ERR_PTR(ret);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index ad4ea0ed5d99..e8f65cd8eca6 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -112,7 +112,7 @@ static void *state_kmemdup(struct a6xx_gpu_state *a6xx_state, void *src,
 static int a6xx_crashdumper_init(struct msm_gpu *gpu,
 		struct a6xx_crashdumper *dumper)
 {
-	dumper->ptr = msm_gem_kernel_new_locked(gpu->dev,
+	dumper->ptr = msm_gem_kernel_new(gpu->dev,
 		SZ_1M, MSM_BO_WC, gpu->aspace,
 		&dumper->bo, &dumper->iova);
 
@@ -961,7 +961,7 @@ struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu)
 		a6xx_get_clusters(gpu, a6xx_state, dumper);
 		a6xx_get_dbgahb_clusters(gpu, a6xx_state, dumper);
 
-		msm_gem_kernel_put(dumper->bo, gpu->aspace, true);
+		msm_gem_kernel_put(dumper->bo, gpu->aspace);
 	}
 
 	if (snapshot_debugbus)
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
index 919433732b43..d4c65bf0a1b7 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
@@ -382,6 +382,36 @@ static void a660_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
 	msg->cnoc_cmds_data[1][0] =  0x60000001;
 }
 
+static void adreno_7c3_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 = 0x07;
+
+	msg->ddr_cmds_addrs[0] = 0x50004;
+	msg->ddr_cmds_addrs[1] = 0x50000;
+	msg->ddr_cmds_addrs[2] = 0x50088;
+
+	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] = 0x5006c;
+	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 */
@@ -428,10 +458,12 @@ 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))
+	else if (adreno_is_a640_family(adreno_gpu))
 		a640_build_bw_table(&msg);
 	else if (adreno_is_a650(adreno_gpu))
 		a650_build_bw_table(&msg);
+	else if (adreno_is_7c3(adreno_gpu))
+		adreno_7c3_build_bw_table(&msg);
 	else if (adreno_is_a660(adreno_gpu))
 		a660_build_bw_table(&msg);
 	else
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 6dad8015c9a1..2a6ce76656aa 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -8,8 +8,6 @@
 
 #include "adreno_gpu.h"
 
-#define ANY_ID 0xff
-
 bool hang_debug = false;
 MODULE_PARM_DESC(hang_debug, "Dump registers when hang is detected (can be slow!)");
 module_param_named(hang_debug, hang_debug, bool, 0600);
@@ -300,6 +298,30 @@ static const struct adreno_info gpulist[] = {
 		.init = a6xx_gpu_init,
 		.zapfw = "a660_zap.mdt",
 		.hwcg = a660_hwcg,
+	}, {
+		.rev = ADRENO_REV(6, 3, 5, ANY_ID),
+		.name = "Adreno 7c Gen 3",
+		.fw = {
+			[ADRENO_FW_SQE] = "a660_sqe.fw",
+			[ADRENO_FW_GMU] = "a660_gmu.bin",
+		},
+		.gmem = SZ_512K,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
+		.init = a6xx_gpu_init,
+		.hwcg = a660_hwcg,
+	}, {
+		.rev = ADRENO_REV(6, 8, 0, ANY_ID),
+		.revn = 680,
+		.name = "A680",
+		.fw = {
+			[ADRENO_FW_SQE] = "a630_sqe.fw",
+			[ADRENO_FW_GMU] = "a640_gmu.bin",
+		},
+		.gmem = SZ_2M,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
+		.init = a6xx_gpu_init,
+		.zapfw = "a640_zap.mdt",
+		.hwcg = a640_hwcg,
 	},
 };
 
@@ -325,6 +347,15 @@ static inline bool _rev_match(uint8_t entry, uint8_t id)
 	return (entry == ANY_ID) || (entry == id);
 }
 
+bool adreno_cmp_rev(struct adreno_rev rev1, struct adreno_rev rev2)
+{
+
+	return _rev_match(rev1.core, rev2.core) &&
+		_rev_match(rev1.major, rev2.major) &&
+		_rev_match(rev1.minor, rev2.minor) &&
+		_rev_match(rev1.patchid, rev2.patchid);
+}
+
 const struct adreno_info *adreno_info(struct adreno_rev rev)
 {
 	int i;
@@ -332,10 +363,7 @@ const struct adreno_info *adreno_info(struct adreno_rev rev)
 	/* identify gpu: */
 	for (i = 0; i < ARRAY_SIZE(gpulist); i++) {
 		const struct adreno_info *info = &gpulist[i];
-		if (_rev_match(info->rev.core, rev.core) &&
-				_rev_match(info->rev.major, rev.major) &&
-				_rev_match(info->rev.minor, rev.minor) &&
-				_rev_match(info->rev.patchid, rev.patchid))
+		if (adreno_cmp_rev(info->rev, rev))
 			return info;
 	}
 
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 9f5a30234b33..748665232d29 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -261,8 +261,8 @@ int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value)
 			return ret;
 		}
 		return -EINVAL;
-	case MSM_PARAM_NR_RINGS:
-		*value = gpu->nr_rings;
+	case MSM_PARAM_PRIORITIES:
+		*value = gpu->nr_rings * NR_SCHED_PRIORITIES;
 		return 0;
 	case MSM_PARAM_PP_PGTABLE:
 		*value = 0;
@@ -390,7 +390,7 @@ struct drm_gem_object *adreno_fw_create_bo(struct msm_gpu *gpu,
 	struct drm_gem_object *bo;
 	void *ptr;
 
-	ptr = msm_gem_kernel_new_locked(gpu->dev, fw->size - 4,
+	ptr = msm_gem_kernel_new(gpu->dev, fw->size - 4,
 		MSM_BO_WC | MSM_BO_GPU_READONLY, gpu->aspace, &bo, iova);
 
 	if (IS_ERR(ptr))
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index 8dbe0d157520..225c277a6223 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -42,6 +42,8 @@ struct adreno_rev {
 	uint8_t  patchid;
 };
 
+#define ANY_ID 0xff
+
 #define ADRENO_REV(core, major, minor, patchid) \
 	((struct adreno_rev){ core, major, minor, patchid })
 
@@ -141,6 +143,8 @@ struct adreno_platform_config {
 	__ret;                                             \
 })
 
+bool adreno_cmp_rev(struct adreno_rev rev1, struct adreno_rev rev2);
+
 static inline bool adreno_is_a2xx(struct adreno_gpu *gpu)
 {
 	return (gpu->revn < 300);
@@ -237,9 +241,9 @@ static inline int adreno_is_a630(struct adreno_gpu *gpu)
        return gpu->revn == 630;
 }
 
-static inline int adreno_is_a640(struct adreno_gpu *gpu)
+static inline int adreno_is_a640_family(struct adreno_gpu *gpu)
 {
-       return gpu->revn == 640;
+	return (gpu->revn == 640) || (gpu->revn == 680);
 }
 
 static inline int adreno_is_a650(struct adreno_gpu *gpu)
@@ -247,15 +251,27 @@ static inline int adreno_is_a650(struct adreno_gpu *gpu)
        return gpu->revn == 650;
 }
 
+static inline int adreno_is_7c3(struct adreno_gpu *gpu)
+{
+	/* The order of args is important here to handle ANY_ID correctly */
+       return adreno_cmp_rev(ADRENO_REV(6, 3, 5, ANY_ID), gpu->rev);
+}
+
 static inline int adreno_is_a660(struct adreno_gpu *gpu)
 {
        return gpu->revn == 660;
 }
 
+static inline int adreno_is_a660_family(struct adreno_gpu *gpu)
+{
+       return adreno_is_a660(gpu) || adreno_is_7c3(gpu);
+}
+
 /* check for a650, a660, or any derivatives */
 static inline int adreno_is_a650_family(struct adreno_gpu *gpu)
 {
-       return gpu->revn == 650 || gpu->revn == 620 || gpu->revn == 660;
+       return gpu->revn == 650 || gpu->revn == 620 ||
+	       adreno_is_a660_family(gpu);
 }
 
 int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value);