1 files changed, 145 insertions, 65 deletions

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 65d38b25c070..28e6705c6da6 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -28,7 +28,7 @@ static void a6xx_gmu_fault(struct a6xx_gmu *gmu)
 	gmu->hung = true;
 
 	/* Turn off the hangcheck timer while we are resetting */
-	del_timer(&gpu->hangcheck_timer);
+	timer_delete(&gpu->hangcheck_timer);
 
 	/* Queue the GPU handler because we need to treat this as a recovery */
 	kthread_queue_work(gpu->worker, &gpu->recover_work);
@@ -813,10 +813,10 @@ static int a6xx_gmu_fw_load(struct a6xx_gmu *gmu)
 	}
 
 	ver = gmu_read(gmu, REG_A6XX_GMU_CORE_FW_VERSION);
-	DRM_INFO("Loaded GMU firmware v%u.%u.%u\n",
-		 FIELD_GET(A6XX_GMU_CORE_FW_VERSION_MAJOR__MASK, ver),
-		 FIELD_GET(A6XX_GMU_CORE_FW_VERSION_MINOR__MASK, ver),
-		 FIELD_GET(A6XX_GMU_CORE_FW_VERSION_STEP__MASK, ver));
+	DRM_INFO_ONCE("Loaded GMU firmware v%u.%u.%u\n",
+		      FIELD_GET(A6XX_GMU_CORE_FW_VERSION_MAJOR__MASK, ver),
+		      FIELD_GET(A6XX_GMU_CORE_FW_VERSION_MINOR__MASK, ver),
+		      FIELD_GET(A6XX_GMU_CORE_FW_VERSION_STEP__MASK, ver));
 
 	return 0;
 }
@@ -1064,14 +1064,6 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 
 	gmu->hung = false;
 
-	/* Notify AOSS about the ACD state (unimplemented for now => disable it) */
-	if (!IS_ERR(gmu->qmp)) {
-		ret = qmp_send(gmu->qmp, "{class: gpu, res: acd, val: %d}",
-			       0 /* Hardcode ACD to be disabled for now */);
-		if (ret)
-			dev_err(gmu->dev, "failed to send GPU ACD state\n");
-	}
-
 	/* Turn on the resources */
 	pm_runtime_get_sync(gmu->dev);
 
@@ -1169,49 +1161,50 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu)
 	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 	u32 val;
+	int ret;
 
 	/*
-	 * The GMU may still be in slumber unless the GPU started so check and
-	 * skip putting it back into slumber if so
+	 * GMU firmware's internal power state gets messed up if we send "prepare_slumber" hfi when
+	 * oob_gpu handshake wasn't done after the last wake up. So do a dummy handshake here when
+	 * required
 	 */
-	val = gmu_read(gmu, REG_A6XX_GPU_GMU_CX_GMU_RPMH_POWER_STATE);
+	if (adreno_gpu->base.needs_hw_init) {
+		if (a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET))
+			goto force_off;
 
-	if (val != 0xf) {
-		int ret = a6xx_gmu_wait_for_idle(gmu);
+		a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET);
+	}
 
-		/* If the GMU isn't responding assume it is hung */
-		if (ret) {
-			a6xx_gmu_force_off(gmu);
-			return;
-		}
+	ret = a6xx_gmu_wait_for_idle(gmu);
 
-		a6xx_bus_clear_pending_transactions(adreno_gpu, a6xx_gpu->hung);
+	/* If the GMU isn't responding assume it is hung */
+	if (ret)
+		goto force_off;
 
-		/* tell the GMU we want to slumber */
-		ret = a6xx_gmu_notify_slumber(gmu);
-		if (ret) {
-			a6xx_gmu_force_off(gmu);
-			return;
-		}
+	a6xx_bus_clear_pending_transactions(adreno_gpu, a6xx_gpu->hung);
 
-		ret = gmu_poll_timeout(gmu,
-			REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS, val,
-			!(val & A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS_GPUBUSYIGNAHB),
-			100, 10000);
+	/* tell the GMU we want to slumber */
+	ret = a6xx_gmu_notify_slumber(gmu);
+	if (ret)
+		goto force_off;
 
-		/*
-		 * Let the user know we failed to slumber but don't worry too
-		 * much because we are powering down anyway
-		 */
+	ret = gmu_poll_timeout(gmu,
+		REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS, val,
+		!(val & A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS_GPUBUSYIGNAHB),
+		100, 10000);
 
-		if (ret)
-			DRM_DEV_ERROR(gmu->dev,
-				"Unable to slumber GMU: status = 0%x/0%x\n",
-				gmu_read(gmu,
-					REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS),
-				gmu_read(gmu,
-					REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS2));
-	}
+	/*
+	 * Let the user know we failed to slumber but don't worry too
+	 * much because we are powering down anyway
+	 */
+
+	if (ret)
+		DRM_DEV_ERROR(gmu->dev,
+			"Unable to slumber GMU: status = 0%x/0%x\n",
+			gmu_read(gmu,
+				REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS),
+			gmu_read(gmu,
+				REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS2));
 
 	/* Turn off HFI */
 	a6xx_hfi_stop(gmu);
@@ -1221,6 +1214,11 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu)
 
 	/* Tell RPMh to power off the GPU */
 	a6xx_rpmh_stop(gmu);
+
+	return;
+
+force_off:
+	a6xx_gmu_force_off(gmu);
 }
 
 
@@ -1261,15 +1259,17 @@ 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);
-	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);
+	struct msm_mmu *mmu = to_msm_vm(gmu->vm)->mmu;
+
+	msm_gem_kernel_put(gmu->hfi.obj, gmu->vm);
+	msm_gem_kernel_put(gmu->debug.obj, gmu->vm);
+	msm_gem_kernel_put(gmu->icache.obj, gmu->vm);
+	msm_gem_kernel_put(gmu->dcache.obj, gmu->vm);
+	msm_gem_kernel_put(gmu->dummy.obj, gmu->vm);
+	msm_gem_kernel_put(gmu->log.obj, gmu->vm);
+
+	mmu->funcs->detach(mmu);
+	drm_gpuvm_put(gmu->vm);
 }
 
 static int a6xx_gmu_memory_alloc(struct a6xx_gmu *gmu, struct a6xx_gmu_bo *bo,
@@ -1298,7 +1298,7 @@ static int a6xx_gmu_memory_alloc(struct a6xx_gmu *gmu, struct a6xx_gmu_bo *bo,
 	if (IS_ERR(bo->obj))
 		return PTR_ERR(bo->obj);
 
-	ret = msm_gem_get_and_pin_iova_range(bo->obj, gmu->aspace, &bo->iova,
+	ret = msm_gem_get_and_pin_iova_range(bo->obj, gmu->vm, &bo->iova,
 					     range_start, range_end);
 	if (ret) {
 		drm_gem_object_put(bo->obj);
@@ -1313,7 +1313,7 @@ static int a6xx_gmu_memory_alloc(struct a6xx_gmu *gmu, struct a6xx_gmu_bo *bo,
 	return 0;
 }
 
-static int a6xx_gmu_memory_probe(struct a6xx_gmu *gmu)
+static int a6xx_gmu_memory_probe(struct drm_device *drm, struct a6xx_gmu *gmu)
 {
 	struct msm_mmu *mmu;
 
@@ -1323,9 +1323,9 @@ static int a6xx_gmu_memory_probe(struct a6xx_gmu *gmu)
 	if (IS_ERR(mmu))
 		return PTR_ERR(mmu);
 
-	gmu->aspace = msm_gem_address_space_create(mmu, "gmu", 0x0, 0x80000000);
-	if (IS_ERR(gmu->aspace))
-		return PTR_ERR(gmu->aspace);
+	gmu->vm = msm_gem_vm_create(drm, mmu, "gmu", 0x0, 0x80000000, true);
+	if (IS_ERR(gmu->vm))
+		return PTR_ERR(gmu->vm);
 
 	return 0;
 }
@@ -1665,6 +1665,75 @@ static int a6xx_gmu_pwrlevels_probe(struct a6xx_gmu *gmu)
 	return a6xx_gmu_rpmh_votes_init(gmu);
 }
 
+static int a6xx_gmu_acd_probe(struct a6xx_gmu *gmu)
+{
+	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
+	struct a6xx_hfi_acd_table *cmd = &gmu->acd_table;
+	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
+	struct msm_gpu *gpu = &adreno_gpu->base;
+	int ret, i, cmd_idx = 0;
+	extern bool disable_acd;
+
+	/* Skip ACD probe if requested via module param */
+	if (disable_acd) {
+		DRM_DEV_ERROR(gmu->dev, "Skipping GPU ACD probe\n");
+		return 0;
+	}
+
+	cmd->version = 1;
+	cmd->stride = 1;
+	cmd->enable_by_level = 0;
+
+	/* Skip freq = 0 and parse acd-level for rest of the OPPs */
+	for (i = 1; i < gmu->nr_gpu_freqs; i++) {
+		struct dev_pm_opp *opp;
+		struct device_node *np;
+		unsigned long freq;
+		u32 val;
+
+		freq = gmu->gpu_freqs[i];
+		opp = dev_pm_opp_find_freq_exact(&gpu->pdev->dev, freq, true);
+		np = dev_pm_opp_get_of_node(opp);
+
+		ret = of_property_read_u32(np, "qcom,opp-acd-level", &val);
+		of_node_put(np);
+		dev_pm_opp_put(opp);
+		if (ret == -EINVAL)
+			continue;
+		else if (ret) {
+			DRM_DEV_ERROR(gmu->dev, "Unable to read acd level for freq %lu\n", freq);
+			return ret;
+		}
+
+		cmd->enable_by_level |= BIT(i);
+		cmd->data[cmd_idx++] = val;
+	}
+
+	cmd->num_levels = cmd_idx;
+
+	/* It is a problem if qmp node is unavailable when ACD is required */
+	if (cmd->enable_by_level && IS_ERR_OR_NULL(gmu->qmp)) {
+		DRM_DEV_ERROR(gmu->dev, "Unable to send ACD state to AOSS\n");
+		return -EINVAL;
+	}
+
+	/* Otherwise, nothing to do if qmp is unavailable */
+	if (IS_ERR_OR_NULL(gmu->qmp))
+		return 0;
+
+	/*
+	 * Notify AOSS about the ACD state. AOSS is supposed to assume that ACD is disabled on
+	 * system reset. So it is harmless if we couldn't notify 'OFF' state
+	 */
+	ret = qmp_send(gmu->qmp, "{class: gpu, res: acd, val: %d}", !!cmd->enable_by_level);
+	if (ret && cmd->enable_by_level) {
+		DRM_DEV_ERROR(gmu->dev, "Failed to send ACD state to AOSS\n");
+		return ret;
+	}
+
+	return 0;
+}
+
 static int a6xx_gmu_clocks_probe(struct a6xx_gmu *gmu)
 {
 	int ret = devm_clk_bulk_get_all(gmu->dev, &gmu->clocks);
@@ -1873,7 +1942,7 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 	if (ret)
 		goto err_put_device;
 
-	ret = a6xx_gmu_memory_probe(gmu);
+	ret = a6xx_gmu_memory_probe(adreno_gpu->base.dev, gmu);
 	if (ret)
 		goto err_put_device;
 
@@ -1983,10 +2052,11 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 		goto detach_cxpd;
 	}
 
+	/* Other errors are handled during GPU ACD probe */
 	gmu->qmp = qmp_get(gmu->dev);
-	if (IS_ERR(gmu->qmp) && adreno_is_a7xx(adreno_gpu)) {
-		ret = PTR_ERR(gmu->qmp);
-		goto remove_device_link;
+	if (PTR_ERR_OR_ZERO(gmu->qmp) == -EPROBE_DEFER) {
+		ret = -EPROBE_DEFER;
+		goto detach_gxpd;
 	}
 
 	init_completion(&gmu->pd_gate);
@@ -2002,6 +2072,10 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 	/* Get the power levels for the GMU and GPU */
 	a6xx_gmu_pwrlevels_probe(gmu);
 
+	ret = a6xx_gmu_acd_probe(gmu);
+	if (ret)
+		goto detach_gxpd;
+
 	/* Set up the HFI queues */
 	a6xx_hfi_init(gmu);
 
@@ -2012,7 +2086,13 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 
 	return 0;
 
-remove_device_link:
+detach_gxpd:
+	if (!IS_ERR_OR_NULL(gmu->gxpd))
+		dev_pm_domain_detach(gmu->gxpd, false);
+
+	if (!IS_ERR_OR_NULL(gmu->qmp))
+		qmp_put(gmu->qmp);
+
 	device_link_del(link);
 
 detach_cxpd: