Merge tag 'amd-drm-fixes-6.18-2025-11-06' of https://gitlab.freedesktop.org/agd5f/linux into drm-fixes

airlied · airlied · commit b57b47741ec1 · 2025-11-07T09:20:48.000+10:00
amd-drm-fixes-6.18-2025-11-06: amdgpu: - Reset fixes - Misc fixes - Panel scaling fixes - HDMI fix - S0ix fixes - Hibernation fix - Secure display fix - Suspend fix - MST fix amdkfd: - Process cleanup fix Signed-off-by: Dave Airlie <airlied@redhat.com> From: Alex Deucher <alexander.deucher@amd.com> Link: https://patch.msgid.link/20251106201326.807230-1-alexander.deucher@amd.com
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1267,6 +1267,10 @@ static int unmap_bo_from_gpuvm(struct kgd_mem *mem,
 
 	(void)amdgpu_vm_bo_unmap(adev, bo_va, entry->va);
 
+	/* VM entity stopped if process killed, don't clear freed pt bo */
+	if (!amdgpu_vm_ready(vm))
+		return 0;
+
 	(void)amdgpu_vm_clear_freed(adev, vm, &bo_va->last_pt_update);
 
 	(void)amdgpu_sync_fence(sync, bo_va->last_pt_update, GFP_KERNEL);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5243,10 +5243,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool notify_clients)
 	if (amdgpu_sriov_vf(adev))
 		amdgpu_virt_release_full_gpu(adev, false);
 
-	r = amdgpu_dpm_notify_rlc_state(adev, false);
-	if (r)
-		return r;
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2632,9 +2632,14 @@ static int amdgpu_pmops_suspend_noirq(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
+	int r;
 
-	if (amdgpu_acpi_should_gpu_reset(adev))
-		return amdgpu_asic_reset(adev);
+	if (amdgpu_acpi_should_gpu_reset(adev)) {
+		amdgpu_device_lock_reset_domain(adev->reset_domain);
+		r = amdgpu_asic_reset(adev);
+		amdgpu_device_unlock_reset_domain(adev->reset_domain);
+		return r;
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -2355,8 +2355,11 @@ static int psp_securedisplay_initialize(struct psp_context *psp)
 	if (!ret && !psp->securedisplay_context.context.resp_status) {
 		psp->securedisplay_context.context.initialized = true;
 		mutex_init(&psp->securedisplay_context.mutex);
-	} else
+	} else {
+		/* don't try again */
+		psp->securedisplay_context.context.bin_desc.size_bytes = 0;
 		return ret;
+	}
 
 	mutex_lock(&psp->securedisplay_context.mutex);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
@@ -407,7 +407,8 @@ static int aqua_vanjaram_switch_partition_mode(struct amdgpu_xcp_mgr *xcp_mgr,
 		return -EINVAL;
 	}
 
-	if (adev->kfd.init_complete && !amdgpu_in_reset(adev))
+	if (adev->kfd.init_complete && !amdgpu_in_reset(adev) &&
+		!adev->in_suspend)
 		flags |= AMDGPU_XCP_OPS_KFD;
 
 	if (flags & AMDGPU_XCP_OPS_KFD) {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
@@ -3102,6 +3102,11 @@ static int gfx_v6_0_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
+	adev->gfx.gfx_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.gfx_ring[0]);
+	adev->gfx.compute_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.compute_ring[0]);
+
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -4399,6 +4399,11 @@ static int gfx_v7_0_sw_init(struct amdgpu_ip_block *ip_block)
 
 	gfx_v7_0_gpu_early_init(adev);
 
+	adev->gfx.gfx_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.gfx_ring[0]);
+	adev->gfx.compute_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.compute_ring[0]);
+
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -2023,6 +2023,11 @@ static int gfx_v8_0_sw_init(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
+	adev->gfx.gfx_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.gfx_ring[0]);
+	adev->gfx.compute_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.compute_ring[0]);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -2292,7 +2292,9 @@ static int gfx_v9_4_3_cp_resume(struct amdgpu_device *adev)
 		r = amdgpu_xcp_init(adev->xcp_mgr, num_xcp, mode);
 
 	} else {
-		if (amdgpu_xcp_query_partition_mode(adev->xcp_mgr,
+		if (adev->in_suspend)
+			amdgpu_xcp_restore_partition_mode(adev->xcp_mgr);
+		else if (amdgpu_xcp_query_partition_mode(adev->xcp_mgr,
 						    AMDGPU_XCP_FL_NONE) ==
 		    AMDGPU_UNKNOWN_COMPUTE_PARTITION_MODE)
 			r = amdgpu_xcp_switch_partition_mode(
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -142,13 +142,37 @@ static int psp_v11_0_init_microcode(struct psp_context *psp)
 	return err;
 }
 
-static int psp_v11_0_wait_for_bootloader(struct psp_context *psp)
+static int psp_v11_wait_for_tos_unload(struct psp_context *psp)
 {
 	struct amdgpu_device *adev = psp->adev;
+	uint32_t sol_reg1, sol_reg2;
+	int retry_loop;
 
+	/* Wait for the TOS to be unloaded */
+	for (retry_loop = 0; retry_loop < 20; retry_loop++) {
+		sol_reg1 = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
+		usleep_range(1000, 2000);
+		sol_reg2 = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
+		if (sol_reg1 == sol_reg2)
+			return 0;
+	}
+	dev_err(adev->dev, "TOS unload failed, C2PMSG_33: %x C2PMSG_81: %x",
+		RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_33),
+		RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81));
+
+	return -ETIME;
+}
+
+static int psp_v11_0_wait_for_bootloader(struct psp_context *psp)
+{
+	struct amdgpu_device *adev = psp->adev;
 	int ret;
 	int retry_loop;
 
+	/* For a reset done at the end of S3, only wait for TOS to be unloaded */
+	if (adev->in_s3 && !(adev->flags & AMD_IS_APU) && amdgpu_in_reset(adev))
+		return psp_v11_wait_for_tos_unload(psp);
+
 	for (retry_loop = 0; retry_loop < 20; retry_loop++) {
 		/* Wait for bootloader to signify that is
 		    ready having bit 31 of C2PMSG_35 set to 1 */
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3563,6 +3563,7 @@ static int dm_resume(struct amdgpu_ip_block *ip_block)
 	/* Do mst topology probing after resuming cached state*/
 	drm_connector_list_iter_begin(ddev, &iter);
 	drm_for_each_connector_iter(connector, &iter) {
+		bool init = false;
 
 		if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK)
 			continue;
@@ -3572,7 +3573,14 @@ static int dm_resume(struct amdgpu_ip_block *ip_block)
 		    aconnector->mst_root)
 			continue;
 
-		drm_dp_mst_topology_queue_probe(&aconnector->mst_mgr);
+		scoped_guard(mutex, &aconnector->mst_mgr.lock) {
+			init = !aconnector->mst_mgr.mst_primary;
+		}
+		if (init)
+			dm_helpers_dp_mst_start_top_mgr(aconnector->dc_link->ctx,
+				aconnector->dc_link, false);
+		else
+			drm_dp_mst_topology_queue_probe(&aconnector->mst_mgr);
 	}
 	drm_connector_list_iter_end(&iter);
 
@@ -8030,7 +8038,7 @@ static int dm_encoder_helper_atomic_check(struct drm_encoder *encoder,
 				       "mode %dx%d@%dHz is not native, enabling scaling\n",
 				       adjusted_mode->hdisplay, adjusted_mode->vdisplay,
 				       drm_mode_vrefresh(adjusted_mode));
-			dm_new_connector_state->scaling = RMX_FULL;
+			dm_new_connector_state->scaling = RMX_ASPECT;
 		}
 		return 0;
 	}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -1302,7 +1302,8 @@ static int odm_combine_segments_show(struct seq_file *m, void *unused)
 	if (connector->status != connector_status_connected)
 		return -ENODEV;
 
-	if (pipe_ctx != NULL && pipe_ctx->stream_res.tg->funcs->get_odm_combine_segments)
+	if (pipe_ctx && pipe_ctx->stream_res.tg &&
+	    pipe_ctx->stream_res.tg->funcs->get_odm_combine_segments)
 		pipe_ctx->stream_res.tg->funcs->get_odm_combine_segments(pipe_ctx->stream_res.tg, &segments);
 
 	seq_printf(m, "%d\n", segments);
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c
@@ -1141,6 +1141,7 @@ static bool detect_link_and_local_sink(struct dc_link *link,
 		    !sink->edid_caps.edid_hdmi)
 			sink->sink_signal = SIGNAL_TYPE_DVI_SINGLE_LINK;
 		else if (dc_is_dvi_signal(sink->sink_signal) &&
+			 dc_is_dvi_signal(link->connector_signal) &&
 			 aud_support->hdmi_audio_native &&
 			 sink->edid_caps.edid_hdmi)
 			sink->sink_signal = SIGNAL_TYPE_HDMI_TYPE_A;
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
@@ -195,24 +195,6 @@ int amdgpu_dpm_set_mp1_state(struct amdgpu_device *adev,
 	return ret;
 }
 
-int amdgpu_dpm_notify_rlc_state(struct amdgpu_device *adev, bool en)
-{
-	int ret = 0;
-	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
-
-	if (pp_funcs && pp_funcs->notify_rlc_state) {
-		mutex_lock(&adev->pm.mutex);
-
-		ret = pp_funcs->notify_rlc_state(
-				adev->powerplay.pp_handle,
-				en);
-
-		mutex_unlock(&adev->pm.mutex);
-	}
-
-	return ret;
-}
-
 int amdgpu_dpm_is_baco_supported(struct amdgpu_device *adev)
 {
 	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -4724,14 +4724,14 @@ int amdgpu_pm_sysfs_init(struct amdgpu_device *adev)
 		ret = devm_device_add_group(adev->dev,
 					    &amdgpu_pm_policy_attr_group);
 		if (ret)
-			goto err_out0;
+			goto err_out1;
 	}
 
 	if (amdgpu_dpm_is_temp_metrics_supported(adev, SMU_TEMP_METRIC_GPUBOARD)) {
 		ret = devm_device_add_group(adev->dev,
 					    &amdgpu_board_attr_group);
 		if (ret)
-			goto err_out0;
+			goto err_out1;
 		if (amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_MAXNODEPOWERLIMIT,
 						 (void *)&tmp) != -EOPNOTSUPP) {
 			sysfs_add_file_to_group(&adev->dev->kobj,
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
@@ -424,8 +424,6 @@ int amdgpu_dpm_mode1_reset(struct amdgpu_device *adev);
 int amdgpu_dpm_set_mp1_state(struct amdgpu_device *adev,
 			     enum pp_mp1_state mp1_state);
 
-int amdgpu_dpm_notify_rlc_state(struct amdgpu_device *adev, bool en);
-
 int amdgpu_dpm_set_gfx_power_up_by_imu(struct amdgpu_device *adev);
 
 int amdgpu_dpm_baco_exit(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -2040,6 +2040,12 @@ static int smu_disable_dpms(struct smu_context *smu)
 	    smu->is_apu && (amdgpu_in_reset(adev) || adev->in_s0ix))
 		return 0;
 
+	/* vangogh s0ix */
+	if ((amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(11, 5, 0) ||
+	     amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(11, 5, 2)) &&
+	    adev->in_s0ix)
+		return 0;
+
 	/*
 	 * For gpu reset, runpm and hibernation through BACO,
 	 * BACO feature has to be kept enabled.
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
@@ -2217,6 +2217,9 @@ static int vangogh_post_smu_init(struct smu_context *smu)
 	uint32_t total_cu = adev->gfx.config.max_cu_per_sh *
 		adev->gfx.config.max_sh_per_se * adev->gfx.config.max_shader_engines;
 
+	if (adev->in_s0ix)
+		return 0;
+
 	/* allow message will be sent after enable message on Vangogh*/
 	if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_DPM_GFXCLK_BIT) &&
 			(adev->pg_flags & AMD_PG_SUPPORT_GFX_PG)) {

Original file line number	Diff line number	Diff line change
`@@ -5243,10 +5243,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool notify_clients)`
`5243`	`5243`	`if (amdgpu_sriov_vf(adev))`
`5244`	`5244`	`amdgpu_virt_release_full_gpu(adev, false);`
`5245`	`5245`
`5246`		`- r = amdgpu_dpm_notify_rlc_state(adev, false);`
`5247`		`- if (r)`
`5248`		`- return r;`
`5249`		`-`
`5250`	`5246`	`return 0;`
`5251`	`5247`	`}`
`5252`	`5248`
Original file line number	Diff line number	Diff line change
`@@ -407,7 +407,8 @@ static int aqua_vanjaram_switch_partition_mode(struct amdgpu_xcp_mgr *xcp_mgr,`
`407`	`407`	`return -EINVAL;`
`408`	`408`	`}`
`409`	`409`
`410`		`- if (adev->kfd.init_complete && !amdgpu_in_reset(adev))`
	`410`	`+ if (adev->kfd.init_complete && !amdgpu_in_reset(adev) &&`
	`411`	`+ !adev->in_suspend)`
`411`	`412`	`flags \|= AMDGPU_XCP_OPS_KFD;`
`412`	`413`
`413`	`414`	`if (flags & AMDGPU_XCP_OPS_KFD) {`
Original file line number	Diff line number	Diff line change
`@@ -3102,6 +3102,11 @@ static int gfx_v6_0_sw_init(struct amdgpu_ip_block *ip_block)`
`3102`	`3102`	`return r;`
`3103`	`3103`	`}`
`3104`	`3104`
	`3105`	`+ adev->gfx.gfx_supported_reset =`
	`3106`	`+ amdgpu_get_soft_full_reset_mask(&adev->gfx.gfx_ring[0]);`
	`3107`	`+ adev->gfx.compute_supported_reset =`
	`3108`	`+ amdgpu_get_soft_full_reset_mask(&adev->gfx.compute_ring[0]);`
	`3109`	`+`
`3105`	`3110`	`return r;`
`3106`	`3111`	`}`
`3107`	`3112`
Original file line number	Diff line number	Diff line change
`@@ -4399,6 +4399,11 @@ static int gfx_v7_0_sw_init(struct amdgpu_ip_block *ip_block)`
`4399`	`4399`
`4400`	`4400`	`gfx_v7_0_gpu_early_init(adev);`
`4401`	`4401`
	`4402`	`+ adev->gfx.gfx_supported_reset =`
	`4403`	`+ amdgpu_get_soft_full_reset_mask(&adev->gfx.gfx_ring[0]);`
	`4404`	`+ adev->gfx.compute_supported_reset =`
	`4405`	`+ amdgpu_get_soft_full_reset_mask(&adev->gfx.compute_ring[0]);`
	`4406`	`+`
`4402`	`4407`	`return r;`
`4403`	`4408`	`}`
`4404`	`4409`