diff options
Diffstat (limited to 'drivers/gpu/drm/amd')
42 files changed, 440 insertions, 162 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index faa3e7102156..559dc24ef436 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2340,8 +2340,6 @@ static int amdgpu_device_ip_suspend_phase1(struct amdgpu_device *adev) { int i, r; - amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE); - amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE); for (i = adev->num_ip_blocks - 1; i >= 0; i--) { if (!adev->ip_blocks[i].status.valid) @@ -3356,6 +3354,9 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) } } + amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE); + amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE); + amdgpu_amdkfd_suspend(adev, !fbcon); amdgpu_ras_suspend(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index f197f1be0969..abe94a55ecad 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -89,7 +89,8 @@ void amdgpu_pm_acpi_event_handler(struct amdgpu_device *adev) adev->pm.ac_power = true; else adev->pm.ac_power = false; - if (adev->powerplay.pp_funcs->enable_bapm) + if (adev->powerplay.pp_funcs && + adev->powerplay.pp_funcs->enable_bapm) amdgpu_dpm_enable_bapm(adev, adev->pm.ac_power); mutex_unlock(&adev->pm.mutex); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index be50867ea644..deaa26808841 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -818,7 +818,7 @@ static int psp_ras_initialize(struct psp_context *psp) if (!psp->adev->psp.ta_ras_ucode_size || !psp->adev->psp.ta_ras_start_addr) { - dev_warn(psp->adev->dev, "RAS: ras ta ucode is not available\n"); + dev_info(psp->adev->dev, "RAS: optional ras ta ucode is not available\n"); return 0; } @@ -902,7 +902,7 @@ static int psp_hdcp_initialize(struct psp_context *psp) if (!psp->adev->psp.ta_hdcp_ucode_size || !psp->adev->psp.ta_hdcp_start_addr) { - dev_warn(psp->adev->dev, "HDCP: hdcp ta ucode is not available\n"); + dev_info(psp->adev->dev, "HDCP: optional hdcp ta ucode is not available\n"); return 0; } @@ -1048,7 +1048,7 @@ static int psp_dtm_initialize(struct psp_context *psp) if (!psp->adev->psp.ta_dtm_ucode_size || !psp->adev->psp.ta_dtm_start_addr) { - dev_warn(psp->adev->dev, "DTM: dtm ta ucode is not available\n"); + dev_info(psp->adev->dev, "DTM: optional dtm ta ucode is not available\n"); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 3c32a94d2424..ab379b44679c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1424,12 +1424,22 @@ static void amdgpu_ras_do_recovery(struct work_struct *work) { struct amdgpu_ras *ras = container_of(work, struct amdgpu_ras, recovery_work); + struct amdgpu_device *remote_adev = NULL; + struct amdgpu_device *adev = ras->adev; + struct list_head device_list, *device_list_handle = NULL; + struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev, false); + + /* Build list of devices to query RAS related errors */ + if (hive && adev->gmc.xgmi.num_physical_nodes > 1) { + device_list_handle = &hive->device_list; + } else { + list_add_tail(&adev->gmc.xgmi.head, &device_list); + device_list_handle = &device_list; + } - /* - * Query and print non zero error counter per IP block for - * awareness before recovering GPU. - */ - amdgpu_ras_log_on_err_counter(ras->adev); + list_for_each_entry(remote_adev, device_list_handle, gmc.xgmi.head) { + amdgpu_ras_log_on_err_counter(remote_adev); + } if (amdgpu_device_should_recover_gpu(ras->adev)) amdgpu_device_gpu_recover(ras->adev, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index c8f2aa1db13b..d78059fd2c72 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -279,7 +279,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_2_nv12[] = #define DEFAULT_SH_MEM_CONFIG \ ((SH_MEM_ADDRESS_MODE_64 << SH_MEM_CONFIG__ADDRESS_MODE__SHIFT) | \ - (SH_MEM_ALIGNMENT_MODE_UNALIGNED << SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | \ + (SH_MEM_ALIGNMENT_MODE_DWORD << SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | \ (SH_MEM_RETRY_MODE_ALL << SH_MEM_CONFIG__RETRY_MODE__SHIFT) | \ (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT)) @@ -1113,7 +1113,7 @@ static int gfx_v10_0_mec_init(struct amdgpu_device *adev) return r; } - memset(hpd, 0, adev->gfx.mec.hpd_eop_obj->tbo.mem.size); + memset(hpd, 0, mec_hpd_size); amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj); amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj); @@ -4104,6 +4104,12 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade /* It is disabled by HW by default */ if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGCG)) { + /* 0 - Disable some blocks' MGCG */ + WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX, 0xe0000000); + WREG32_SOC15(GC, 0, mmCGTT_WD_CLK_CTRL, 0xff000000); + WREG32_SOC15(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xff000000); + WREG32_SOC15(GC, 0, mmCGTT_IA_CLK_CTRL, 0xff000000); + /* 1 - RLC_CGTT_MGCG_OVERRIDE */ def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE); data &= ~(RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK | @@ -4143,19 +4149,20 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade if (def != data) WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data); - /* 2 - disable MGLS in RLC */ + /* 2 - disable MGLS in CP */ + data = RREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL); + if (data & CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK) { + data &= ~CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK; + WREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL, data); + } + + /* 3 - disable MGLS in RLC */ data = RREG32_SOC15(GC, 0, mmRLC_MEM_SLP_CNTL); if (data & RLC_MEM_SLP_CNTL__RLC_MEM_LS_EN_MASK) { data &= ~RLC_MEM_SLP_CNTL__RLC_MEM_LS_EN_MASK; WREG32_SOC15(GC, 0, mmRLC_MEM_SLP_CNTL, data); } - /* 3 - disable MGLS in CP */ - data = RREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL); - if (data & CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK) { - data &= ~CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK; - WREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL, data); - } } } @@ -4266,7 +4273,7 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev, /* === CGCG /CGLS for GFX 3D Only === */ gfx_v10_0_update_3d_clock_gating(adev, enable); /* === MGCG + MGLS === */ - gfx_v10_0_update_medium_grain_clock_gating(adev, enable); + /* gfx_v10_0_update_medium_grain_clock_gating(adev, enable); */ } if (adev->cg_flags & diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 37c8231f1407..e6b113ed2f40 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1217,6 +1217,8 @@ static void gfx_v9_0_check_fw_write_wait(struct amdgpu_device *adev) adev->gfx.mec_fw_write_wait = true; break; default: + adev->gfx.me_fw_write_wait = true; + adev->gfx.mec_fw_write_wait = true; break; } } @@ -1946,7 +1948,7 @@ static int gfx_v9_0_mec_init(struct amdgpu_device *adev) return r; } - memset(hpd, 0, adev->gfx.mec.hpd_eop_obj->tbo.mem.size); + memset(hpd, 0, mec_hpd_size); amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj); amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c index cceb46faf212..dce945ef21a5 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c @@ -710,14 +710,16 @@ static int gfx_v9_4_query_utc_edc_status(struct amdgpu_device *adev, sec_count = REG_GET_FIELD(data, VML2_MEM_ECC_CNTL, SEC_COUNT); if (sec_count) { - DRM_INFO("Instance[%d]: SubBlock %s, SEC %d\n", i, + dev_info(adev->dev, + "Instance[%d]: SubBlock %s, SEC %d\n", i, vml2_mems[i], sec_count); err_data->ce_count += sec_count; } ded_count = REG_GET_FIELD(data, VML2_MEM_ECC_CNTL, DED_COUNT); if (ded_count) { - DRM_INFO("Instance[%d]: SubBlock %s, DED %d\n", i, + dev_info(adev->dev, + "Instance[%d]: SubBlock %s, DED %d\n", i, vml2_mems[i], ded_count); err_data->ue_count += ded_count; } diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c index 0d413fabd015..c0e3efcb09bf 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c @@ -1539,8 +1539,11 @@ static const struct soc15_reg_entry mmhub_v9_4_edc_cnt_regs[] = { { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA7_EDC_CNT3), 0, 0, 0 }, }; -static int mmhub_v9_4_get_ras_error_count(const struct soc15_reg_entry *reg, - uint32_t value, uint32_t *sec_count, uint32_t *ded_count) +static int mmhub_v9_4_get_ras_error_count(struct amdgpu_device *adev, + const struct soc15_reg_entry *reg, + uint32_t value, + uint32_t *sec_count, + uint32_t *ded_count) { uint32_t i; uint32_t sec_cnt, ded_cnt; @@ -1553,7 +1556,7 @@ static int mmhub_v9_4_get_ras_error_count(const struct soc15_reg_entry *reg, mmhub_v9_4_ras_fields[i].sec_count_mask) >> mmhub_v9_4_ras_fields[i].sec_count_shift; if (sec_cnt) { - DRM_INFO("MMHUB SubBlock %s, SEC %d\n", + dev_info(adev->dev, "MMHUB SubBlock %s, SEC %d\n", mmhub_v9_4_ras_fields[i].name, sec_cnt); *sec_count += sec_cnt; @@ -1563,7 +1566,7 @@ static int mmhub_v9_4_get_ras_error_count(const struct soc15_reg_entry *reg, mmhub_v9_4_ras_fields[i].ded_count_mask) >> mmhub_v9_4_ras_fields[i].ded_count_shift; if (ded_cnt) { - DRM_INFO("MMHUB SubBlock %s, DED %d\n", + dev_info(adev->dev, "MMHUB SubBlock %s, DED %d\n", mmhub_v9_4_ras_fields[i].name, ded_cnt); *ded_count += ded_cnt; @@ -1588,7 +1591,7 @@ static void mmhub_v9_4_query_ras_error_count(struct amdgpu_device *adev, reg_value = RREG32(SOC15_REG_ENTRY_OFFSET(mmhub_v9_4_edc_cnt_regs[i])); if (reg_value) - mmhub_v9_4_get_ras_error_count(&mmhub_v9_4_edc_cnt_regs[i], + mmhub_v9_4_get_ras_error_count(adev, &mmhub_v9_4_edc_cnt_regs[i], reg_value, &sec_count, &ded_count); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index d5386f15c4a5..05bc6d96ec52 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -1112,9 +1112,9 @@ kfd_gtt_out: return 0; kfd_gtt_no_free_chunk: - pr_debug("Allocation failed with mem_obj = %p\n", mem_obj); + pr_debug("Allocation failed with mem_obj = %p\n", *mem_obj); mutex_unlock(&kfd->gtt_sa_lock); - kfree(mem_obj); + kfree(*mem_obj); return -ENOMEM; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index d3674d805a0a..f7c5cdc10a70 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -3639,6 +3639,9 @@ fill_dc_plane_info_and_addr(struct amdgpu_device *adev, case DRM_FORMAT_NV12: plane_info->format = SURFACE_PIXEL_FORMAT_VIDEO_420_YCrCb; break; + case DRM_FORMAT_P010: + plane_info->format = SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCrCb; + break; default: DRM_ERROR( "Unsupported screen format %s\n", @@ -4720,10 +4723,10 @@ amdgpu_dm_connector_atomic_duplicate_state(struct drm_connector *connector) static int amdgpu_dm_connector_late_register(struct drm_connector *connector) { +#if defined(CONFIG_DEBUG_FS) struct amdgpu_dm_connector *amdgpu_dm_connector = to_amdgpu_dm_connector(connector); -#if defined(CONFIG_DEBUG_FS) connector_debugfs_init(amdgpu_dm_connector); #endif @@ -5535,6 +5538,8 @@ static int get_plane_formats(const struct drm_plane *plane, if (plane_cap && plane_cap->pixel_format_support.nv12) formats[num_formats++] = DRM_FORMAT_NV12; + if (plane_cap && plane_cap->pixel_format_support.p010) + formats[num_formats++] = DRM_FORMAT_P010; break; case DRM_PLANE_TYPE_OVERLAY: @@ -5587,12 +5592,15 @@ static int amdgpu_dm_plane_init(struct amdgpu_display_manager *dm, } if (plane->type == DRM_PLANE_TYPE_PRIMARY && - plane_cap && plane_cap->pixel_format_support.nv12) { + plane_cap && + (plane_cap->pixel_format_support.nv12 || + plane_cap->pixel_format_support.p010)) { /* This only affects YUV formats. */ drm_plane_create_color_properties( plane, BIT(DRM_COLOR_YCBCR_BT601) | - BIT(DRM_COLOR_YCBCR_BT709), + BIT(DRM_COLOR_YCBCR_BT709) | + BIT(DRM_COLOR_YCBCR_BT2020), BIT(DRM_COLOR_YCBCR_LIMITED_RANGE) | BIT(DRM_COLOR_YCBCR_FULL_RANGE), DRM_COLOR_YCBCR_BT709, DRM_COLOR_YCBCR_LIMITED_RANGE); @@ -5921,7 +5929,8 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm, adev->mode_info.underscan_vborder_property, 0); - drm_connector_attach_max_bpc_property(&aconnector->base, 8, 16); + if (!aconnector->mst_port) + drm_connector_attach_max_bpc_property(&aconnector->base, 8, 16); /* This defaults to the max in the range, but we want 8bpc for non-edp. */ aconnector->base.state->max_bpc = (connector_type == DRM_MODE_CONNECTOR_eDP) ? 16 : 8; @@ -5940,8 +5949,9 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm, &aconnector->base.base, dm->ddev->mode_config.hdr_output_metadata_property, 0); - drm_connector_attach_vrr_capable_property( - &aconnector->base); + if (!aconnector->mst_port) + drm_connector_attach_vrr_capable_property(&aconnector->base); + #ifdef CONFIG_DRM_AMD_DC_HDCP if (adev->dm.hdcp_workqueue) drm_connector_attach_content_protection_property(&aconnector->base, true); @@ -6264,12 +6274,6 @@ static int get_cursor_position(struct drm_plane *plane, struct drm_crtc *crtc, y <= -amdgpu_crtc->max_cursor_height) return 0; - if (crtc->primary->state) { - /* avivo cursor are offset into the total surface */ - x += crtc->primary->state->src_x >> 16; - y += crtc->primary->state->src_y >> 16; - } - if (x < 0) { xorigin = min(-x, amdgpu_crtc->max_cursor_width - 1); x = 0; @@ -6279,6 +6283,7 @@ static int get_cursor_position(struct drm_plane *plane, struct drm_crtc *crtc, y = 0; } position->enable = true; + position->translate_by_source = true; position->x = x; position->y = y; position->x_hotspot = xorigin; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c index 5b70ed3cdb88..78e1c11d4ae5 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c @@ -192,10 +192,13 @@ void hdcp_update_display(struct hdcp_workqueue *hdcp_work, &hdcp_work->srm_version); display->adjust.disable = 0; - if (content_type == DRM_MODE_HDCP_CONTENT_TYPE0) + if (content_type == DRM_MODE_HDCP_CONTENT_TYPE0) { + hdcp_w->link.adjust.hdcp1.disable = 0; hdcp_w->link.adjust.hdcp2.force_type = MOD_HDCP_FORCE_TYPE_0; - else if (content_type == DRM_MODE_HDCP_CONTENT_TYPE1) + } else if (content_type == DRM_MODE_HDCP_CONTENT_TYPE1) { + hdcp_w->link.adjust.hdcp1.disable = 1; hdcp_w->link.adjust.hdcp2.force_type = MOD_HDCP_FORCE_TYPE_1; + } schedule_delayed_work(&hdcp_w->property_validate_dwork, msecs_to_jiffies(DRM_HDCP_CHECK_PERIOD_MS)); @@ -263,7 +266,7 @@ static void event_callback(struct work_struct *work) mutex_lock(&hdcp_work->mutex); - cancel_delayed_work(&hdcp_work->watchdog_timer_dwork); + cancel_delayed_work(&hdcp_work->callback_dwork); mod_hdcp_process_event(&hdcp_work->hdcp, MOD_HDCP_EVENT_CALLBACK, &hdcp_work->output); @@ -344,6 +347,8 @@ static void event_watchdog_timer(struct work_struct *work) mutex_lock(&hdcp_work->mutex); + cancel_delayed_work(&hdcp_work->watchdog_timer_dwork); + mod_hdcp_process_event(&hdcp_work->hdcp, MOD_HDCP_EVENT_WATCHDOG_TIMEOUT, &hdcp_work->output); @@ -414,7 +419,8 @@ static void update_config(void *handle, struct cp_psp_stream_config *config) link->dp.rev = aconnector->dc_link->dpcd_caps.dpcd_rev.raw; link->dp.mst_supported = config->mst_supported; display->adjust.disable = 1; - link->adjust.auth_delay = 2; + link->adjust.auth_delay = 3; + link->adjust.hdcp1.disable = 0; hdcp_update_display(hdcp_work, link_index, aconnector, DRM_MODE_HDCP_CONTENT_TYPE0, false); } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index e8208df420d9..fabbe78d5aef 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -410,6 +410,14 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, drm_connector_attach_encoder(&aconnector->base, &aconnector->mst_encoder->base); + connector->max_bpc_property = master->base.max_bpc_property; + if (connector->max_bpc_property) + drm_connector_attach_max_bpc_property(connector, 8, 16); + + connector->vrr_capable_property = master->base.vrr_capable_property; + if (connector->vrr_capable_property) + drm_connector_attach_vrr_capable_property(connector); + drm_object_attach_property( &connector->base, dev->mode_config.path_property, diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c index ab267ddd4abe..24c5765890fa 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c @@ -643,7 +643,7 @@ static void rn_clk_mgr_helper_populate_bw_params(struct clk_bw_params *bw_params /* Find lowest DPM, FCLK is filled in reverse order*/ for (i = PP_SMU_NUM_FCLK_DPM_LEVELS - 1; i >= 0; i--) { - if (clock_table->FClocks[i].Freq != 0) { + if (clock_table->FClocks[i].Freq != 0 && clock_table->FClocks[i].Vol != 0) { j = i; break; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 2ffb22177df9..8489f1e56892 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -283,6 +283,8 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc, int i = 0; bool ret = false; + stream->adjust = *adjust; + for (i = 0; i < MAX_PIPES; i++) { struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i]; @@ -1360,6 +1362,26 @@ bool dc_commit_state(struct dc *dc, struct dc_state *context) return (result == DC_OK); } +static bool is_flip_pending_in_pipes(struct dc *dc, struct dc_state *context) +{ + int i; + struct pipe_ctx *pipe; + + for (i = 0; i < MAX_PIPES; i++) { + pipe = &context->res_ctx.pipe_ctx[i]; + + if (!pipe->plane_state) + continue; + + /* Must set to false to start with, due to OR in update function */ + pipe->plane_state->status.is_flip_pending = false; + dc->hwss.update_pending_status(pipe); + if (pipe->plane_state->status.is_flip_pending) + return true; + } + return false; +} + bool dc_post_update_surfaces_to_stream(struct dc *dc) { int i; @@ -1370,6 +1392,9 @@ bool dc_post_update_surfaces_to_stream(struct dc *dc) post_surface_trace(dc); + if (is_flip_pending_in_pipes(dc, context)) + return true; + for (i = 0; i < dc->res_pool->pipe_count; i++) if (context->res_ctx.pipe_ctx[i].stream == NULL || context->res_ctx.pipe_ctx[i].plane_state == NULL) { @@ -1703,6 +1728,9 @@ static enum surface_update_type det_surface_update(const struct dc *dc, if (u->coeff_reduction_factor) update_flags->bits.coeff_reduction_change = 1; + if (u->gamut_remap_matrix) + update_flags->bits.gamut_remap_change = 1; + if (u->gamma) { enum surface_pixel_format format = SURFACE_PIXEL_FORMAT_GRPH_BEGIN; @@ -1728,7 +1756,8 @@ static enum surface_update_type det_surface_update(const struct dc *dc, if (update_flags->bits.input_csc_change || update_flags->bits.coeff_reduction_change - || update_flags->bits.gamma_change) { + || update_flags->bits.gamma_change + || update_flags->bits.gamut_remap_change) { type = UPDATE_TYPE_FULL; elevate_update_type(&overall_type, type); } @@ -1832,8 +1861,9 @@ enum surface_update_type dc_check_update_surfaces_for_stream( // Else we fallback to mem compare. } else if (memcmp(&dc->current_state->bw_ctx.bw.dcn.clk, &dc->clk_mgr->clks, offsetof(struct dc_clocks, prev_p_state_change_support)) != 0) { dc->optimized_required = true; - } else if (dc->wm_optimized_required) - dc->optimized_required = true; + } + + dc->optimized_required |= dc->wm_optimized_required; } return type; @@ -1973,6 +2003,10 @@ static void copy_surface_update_to_plane( if (srf_update->coeff_reduction_factor) surface->coeff_reduction_factor = *srf_update->coeff_reduction_factor; + + if (srf_update->gamut_remap_matrix) + surface->gamut_remap_matrix = + *srf_update->gamut_remap_matrix; } static void copy_stream_update_to_stream(struct dc *dc, @@ -2431,7 +2465,7 @@ void dc_commit_updates_for_stream(struct dc *dc, enum surface_update_type update_type; struct dc_state *context; struct dc_context *dc_ctx = dc->ctx; - int i; + int i, j; stream_status = dc_stream_get_status(stream); context = dc->current_state; @@ -2469,6 +2503,17 @@ void dc_commit_updates_for_stream(struct dc *dc, copy_surface_update_to_plane(surface, &srf_updates[i]); + if (update_type >= UPDATE_TYPE_MED) { + for (j = 0; j < dc->res_pool->pipe_count; j++) { + struct pipe_ctx *pipe_ctx = + &context->res_ctx.pipe_ctx[j]; + + if (pipe_ctx->plane_state != surface) + continue; + + resource_build_scaling_params(pipe_ctx); + } + } } copy_stream_update_to_stream(dc, context, stream, stream_update); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 75c7ce4c7581..f4bcc71b2920 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1077,6 +1077,7 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx) * on certain displays, such as the Sharp 4k */ pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_30BPP; + pipe_ctx->plane_res.scl_data.lb_params.alpha_en = plane_state->per_pixel_alpha; pipe_ctx->plane_res.scl_data.recout.x += timing->h_border_left; pipe_ctx->plane_res.scl_data.recout.y += timing->v_border_top; diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index d3ceb39e428e..1935cf6601eb 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -726,6 +726,7 @@ union surface_update_flags { uint32_t output_tf_change:1; uint32_t pixel_format_change:1; uint32_t plane_size_change:1; + uint32_t gamut_remap_change:1; /* Full updates */ uint32_t new_plane:1; @@ -760,6 +761,7 @@ struct dc_plane_state { struct dc_csc_transform input_csc_color_matrix; struct fixed31_32 coeff_reduction_factor; struct fixed31_32 hdr_mult; + struct colorspace_transform gamut_remap_matrix; // TODO: No longer used, remove struct dc_hdr_static_metadata hdr_static_ctx; @@ -839,6 +841,7 @@ struct dc_surface_update { const struct dc_transfer_func *func_shaper; const struct dc_3dlut *lut3d_func; const struct dc_transfer_func *blend_tf; + const struct colorspace_transform *gamut_remap_matrix; }; /* diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h index 25c50bcab9e9..a8dc3082e3e1 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h @@ -385,6 +385,8 @@ struct dc_cursor_position { */ bool enable; + /* Translate cursor x/y by the source rectangle for each plane. */ + bool translate_by_source; }; struct dc_cursor_mi_param { diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 0976e378659f..c279982947e1 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -2685,6 +2685,23 @@ void dce110_set_cursor_position(struct pipe_ctx *pipe_ctx) .mirror = pipe_ctx->plane_state->horizontal_mirror }; + /** + * If the cursor's source viewport is clipped then we need to + * translate the cursor to appear in the correct position on + * the screen. + * + * This translation isn't affected by scaling so it needs to be + * done *after* we adjust the position for the scale factor. + * + * This is only done by opt-in for now since there are still + * some usecases like tiled display that might enable the + * cursor on both streams while expecting dc to clip it. + */ + if (pos_cpy.translate_by_source) { + pos_cpy.x += pipe_ctx->plane_state->src_rect.x; + pos_cpy.y += pipe_ctx->plane_state->src_rect.y; + } + if (pipe_ctx->plane_state->address.type == PLN_ADDR_TYPE_VIDEO_PROGRESSIVE) pos_cpy.enable = false; diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 9cc3314966bd..b0357546471b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -2004,6 +2004,12 @@ void dcn10_program_gamut_remap(struct pipe_ctx *pipe_ctx) for (i = 0; i < CSC_TEMPERATURE_MATRIX_SIZE; i++) adjust.temperature_matrix[i] = pipe_ctx->stream->gamut_remap_matrix.matrix[i]; + } else if (pipe_ctx->plane_state && + pipe_ctx->plane_state->gamut_remap_matrix.enable_remap == true) { + adjust.gamut_adjust_type = GRAPHICS_GAMUT_ADJUST_TYPE_SW; + for (i = 0; i < CSC_TEMPERATURE_MATRIX_SIZE; i++) + adjust.temperature_matrix[i] = + pipe_ctx->plane_state->gamut_remap_matrix.matrix[i]; } pipe_ctx->plane_res.dpp->funcs->dpp_set_gamut_remap(pipe_ctx->plane_res.dpp, &adjust); @@ -3015,12 +3021,50 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) int x_pos = pos_cpy.x; int y_pos = pos_cpy.y; - // translate cursor from stream space to plane space + /** + * DC cursor is stream space, HW cursor is plane space and drawn + * as part of the framebuffer. + * + * Cursor position can't be negative, but hotspot can be used to + * shift cursor out of the plane bounds. Hotspot must be smaller + * than the cursor size. + */ + + /** + * Translate cursor from stream space to plane space. + * + * If the cursor is scaled then we need to scale the position + * to be in the approximately correct place. We can't do anything + * about the actual size being incorrect, that's a limitation of + * the hardware. + */ x_pos = (x_pos - x_plane) * pipe_ctx->plane_state->src_rect.width / pipe_ctx->plane_state->dst_rect.width; y_pos = (y_pos - y_plane) * pipe_ctx->plane_state->src_rect.height / pipe_ctx->plane_state->dst_rect.height; + /** + * If the cursor's source viewport is clipped then we need to + * translate the cursor to appear in the correct position on + * the screen. + * + * This translation isn't affected by scaling so it needs to be + * done *after* we adjust the position for the scale factor. + * + * This is only done by opt-in for now since there are still + * some usecases like tiled display that might enable the + * cursor on both streams while expecting dc to clip it. + */ + if (pos_cpy.translate_by_source) { + x_pos += pipe_ctx->plane_state->src_rect.x; + y_pos += pipe_ctx->plane_state->src_rect.y; + } + + /** + * If the position is negative then we need to add to the hotspot + * to shift the cursor outside the plane. + */ + if (x_pos < 0) { pos_cpy.x_hotspot -= x_pos; x_pos = 0; diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c index 63acb8ff7462..17d96ec6acd8 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c @@ -343,6 +343,23 @@ void optc1_set_blank_data_double_buffer(struct timing_generator *optc, bool enab } /** + * optc1_set_timing_double_buffer() - DRR double buffering control + * + * Sets double buffer point for V_TOTAL, H_TOTAL, VTOTAL_MIN, + * VTOTAL_MAX, VTOTAL_MIN_SEL and VTOTAL_MAX_SEL registers. + * + * Options: any time, start of frame, dp start of frame (range timing) + */ +void optc1_set_timing_double_buffer(struct timing_generator *optc, bool enable) +{ + struct optc *optc1 = DCN10TG_FROM_TG(optc); + uint32_t mode = enable ? 2 : 0; + + REG_UPDATE(OTG_DOUBLE_BUFFER_CONTROL, + OTG_RANGE_TIMING_DBUF_UPDATE_MODE, mode); +} + +/** * unblank_crtc * Call ASIC Control Object to UnBlank CRTC. */ @@ -1353,6 +1370,7 @@ void optc1_clear_optc_underflow(struct timing_generator *optc) void optc1_tg_init(struct timing_generator *optc) { optc1_set_blank_data_double_buffer(optc, true); + optc1_set_timing_double_buffer(optc, true); optc1_clear_optc_underflow(optc); } diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h index f277656d5464..9a459a8fe8a0 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h @@ -185,6 +185,7 @@ struct dcn_optc_registers { SF(OTG0_OTG_GLOBAL_CONTROL0, OTG_MASTER_UPDATE_LOCK_SEL, mask_sh),\ SF(OTG0_OTG_DOUBLE_BUFFER_CONTROL, OTG_UPDATE_PENDING, mask_sh),\ SF(OTG0_OTG_DOUBLE_BUFFER_CONTROL, OTG_BLANK_DATA_DOUBLE_BUFFER_EN, mask_sh),\ + SF(OTG0_OTG_DOUBLE_BUFFER_CONTROL, OTG_RANGE_TIMING_DBUF_UPDATE_MODE, mask_sh),\ SF(OTG0_OTG_H_TOTAL, OTG_H_TOTAL, mask_sh),\ SF(OTG0_OTG_H_BLANK_START_END, OTG_H_BLANK_START, mask_sh),\ SF(OTG0_OTG_H_BLANK_START_END, OTG_H_BLANK_END, mask_sh),\ @@ -643,6 +644,8 @@ bool optc1_is_optc_underflow_occurred(struct timing_generator *optc); void optc1_set_blank_data_double_buffer(struct timing_generator *optc, bool enable); +void optc1_set_timing_double_buffer(struct timing_generator *optc, bool enable); + bool optc1_get_otg_active_size(struct timing_generator *optc, uint32_t *otg_active_width, uint32_t *otg_active_height); diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c index 261bdc3a8218..07265ca7d28c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c @@ -552,7 +552,8 @@ static const struct dc_plane_cap plane_cap = { .pixel_format_support = { .argb8888 = true, .nv12 = true, - .fp16 = true + .fp16 = true, + .p010 = true }, .max_upscale_factor = { @@ -584,7 +585,7 @@ static const struct dc_debug_options debug_defaults_drv = { .disable_pplib_clock_request = false, .disable_pplib_wm_range = false, .pplib_wm_report_mode = WM_REPORT_DEFAULT, - .pipe_split_policy = MPC_SPLIT_AVOID_MULT_DISP, + .pipe_split_policy = MPC_SPLIT_DYNAMIC, .force_single_disp_pipe_split = true, .disable_dcc = DCC_ENABLE, .voltage_align_fclk = true, diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 233318260da4..22f421e82733 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1373,6 +1373,7 @@ static void dcn20_update_dchubp_dpp( } if (pipe_ctx->update_flags.bits.viewport || + (context == dc->current_state && plane_state->update_flags.bits.position_change) || (context == dc->current_state && plane_state->update_flags.bits.scaling_change) || (context == dc->current_state && pipe_ctx->stream->update_flags.bits.scaling)) { diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index a67395208991..5cdbba0cd873 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -1012,7 +1012,8 @@ static const struct dc_plane_cap plane_cap = { .pixel_format_support = { .argb8888 = true, .nv12 = true, - .fp16 = true + .fp16 = true, + .p010 = true }, .max_upscale_factor = { @@ -3342,7 +3343,7 @@ void dcn20_cap_soc_clocks( void dcn20_update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb, struct pp_smu_nv_clock_table *max_clocks, unsigned int *uclk_states, unsigned int num_states) { - struct _vcs_dpi_voltage_scaling_st calculated_states[MAX_CLOCK_LIMIT_STATES]; + struct _vcs_dpi_voltage_scaling_st calculated_states[DC__VOLTAGE_STATES]; int i; int num_calculated_states = 0; int min_dcfclk = 0; diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index 51b5910cd05f..b25484aa8222 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -300,7 +300,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = { .xfc_bus_transport_time_us = 4, .xfc_xbuf_latency_tolerance_us = 4, .use_urgent_burst_bw = 1, - .num_states = 9 + .num_states = 8 }; #ifndef MAX @@ -838,7 +838,8 @@ static const struct dc_plane_cap plane_cap = { .pixel_format_support = { .argb8888 = true, .nv12 = true, - .fp16 = true + .fp16 = true, + .p010 = true }, .max_upscale_factor = { @@ -1376,21 +1377,8 @@ static void update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param unsigned int i, j, k; int closest_clk_lvl; - // diags does not retrieve proper values from SMU - // cap states to 5 and make state 5 the max state - if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment) || IS_DIAG_DC(dc->ctx->dce_environment)) { - dcn2_1_soc.num_states = 5; - - dcn2_1_soc.clock_limits[5].state = 5; - dcn2_1_soc.clock_limits[5].dcfclk_mhz = 810.0; - dcn2_1_soc.clock_limits[5].fabricclk_mhz = 1600.0; - dcn2_1_soc.clock_limits[5].dispclk_mhz = 1395.0; - dcn2_1_soc.clock_limits[5].dppclk_mhz = 1285.0; - dcn2_1_soc.clock_limits[5].phyclk_mhz = 1325.0; - dcn2_1_soc.clock_limits[5].socclk_mhz = 953.0; - dcn2_1_soc.clock_limits[5].dscclk_mhz = 489.0; - dcn2_1_soc.clock_limits[5].dram_speed_mts = 4266.0; - } else { + // Default clock levels are used for diags, which may lead to overclocking. + if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment) && !IS_DIAG_DC(dc->ctx->dce_environment)) { dcn2_1_ip.max_num_otg = pool->base.res_cap->num_timing_generator; dcn2_1_ip.max_num_dpp = pool->base.pipe_count; dcn2_1_soc.num_chans = bw_params->num_channels; @@ -1403,16 +1391,16 @@ static void update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param dcn2_1_soc.clock_limits[0].dram_speed_mts = clk_table->entries[0].memclk_mhz * 2; /* - * Other levels: find cloest DCN clocks that fit the given clock limit using dcfclk - * as indicater + * Other levels: find closest DCN clocks that fit the given clock limit using dcfclk + * as indicator */ closest_clk_lvl = -1; /* index currently being filled */ k = 1; for (i = 1; i < clk_table->num_entries; i++) { - /* loop backwards, skip duplicate state, +1 because SMU has precision issue */ - for (j = dcn2_1_soc.num_states - 2; j >= k; j--) { + /* loop backwards, skip duplicate state*/ + for (j = dcn2_1_soc.num_states - 1; j >= k; j--) { if ((unsigned int) dcn2_1_soc.clock_limits[j].dcfclk_mhz <= clk_table->entries[i].dcfclk_mhz) { closest_clk_lvl = j; break; @@ -1437,13 +1425,13 @@ static void update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param k++; } } - - /* duplicate last level */ - dcn2_1_soc.clock_limits[k] = dcn2_1_soc.clock_limits[k - 1]; - dcn2_1_soc.clock_limits[k].state = k; - dcn2_1_soc.num_states = k + 1; + dcn2_1_soc.num_states = k; } + /* duplicate last level */ + dcn2_1_soc.clock_limits[dcn2_1_soc.num_states] = dcn2_1_soc.clock_limits[dcn2_1_soc.num_states - 1]; + dcn2_1_soc.clock_limits[dcn2_1_soc.num_states].state = dcn2_1_soc.num_states; + dml_init_instance(&dc->dml, &dcn2_1_soc, &dcn2_1_ip, DML_PROJECT_DCN21); } diff --git a/drivers/gpu/drm/amd/display/dc/dml/dc_features.h b/drivers/gpu/drm/amd/display/dc/dml/dc_features.h index ea4cde952f4f..2a1983324629 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dc_features.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dc_features.h @@ -29,7 +29,7 @@ #define DC__PRESENT 1 #define DC__PRESENT__1 1 #define DC__NUM_DPP 4 -#define DC__VOLTAGE_STATES 7 +#define DC__VOLTAGE_STATES 9 #define DC__NUM_DPP__4 1 #define DC__NUM_DPP__0_PRESENT 1 #define DC__NUM_DPP__1_PRESENT 1 diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h index dfd3be452766..687010c17324 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h @@ -22,11 +22,12 @@ * Authors: AMD * */ + +#include "dc_features.h" + #ifndef __DISPLAY_MODE_STRUCTS_H__ #define __DISPLAY_MODE_STRUCTS_H__ -#define MAX_CLOCK_LIMIT_STATES 9 - typedef struct _vcs_dpi_voltage_scaling_st voltage_scaling_st; typedef struct _vcs_dpi_soc_bounding_box_st soc_bounding_box_st; typedef struct _vcs_dpi_ip_params_st ip_params_st; @@ -68,7 +69,7 @@ struct _vcs_dpi_voltage_scaling_st { }; struct _vcs_dpi_soc_bounding_box_st { - struct _vcs_dpi_voltage_scaling_st clock_limits[MAX_CLOCK_LIMIT_STATES]; + struct _vcs_dpi_voltage_scaling_st clock_limits[DC__VOLTAGE_STATES]; unsigned int num_states; double sr_exit_time_us; double sr_enter_plus_exit_time_us; diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h index 8a87d0ed90ae..2359e88d6029 100644 --- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h +++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h @@ -136,6 +136,7 @@ #define RAVEN2_A0 0x81 #define RAVEN1_F0 0xF0 #define RAVEN_UNKNOWN 0xFF +#define RENOIR_A0 0x91 #ifndef ASICREV_IS_RAVEN #define ASICREV_IS_RAVEN(eChipRev) ((eChipRev >= RAVEN_A0) && eChipRev < RAVEN_UNKNOWN) #endif @@ -171,8 +172,6 @@ enum { #define ASICREV_IS_NAVI10_P(eChipRev) (eChipRev < NV_NAVI12_P_A0) #define ASICREV_IS_NAVI12_P(eChipRev) ((eChipRev >= NV_NAVI12_P_A0) && (eChipRev < NV_NAVI14_M_A0)) #define ASICREV_IS_NAVI14_M(eChipRev) ((eChipRev >= NV_NAVI14_M_A0) && (eChipRev < NV_UNKNOWN)) -#define RENOIR_A0 0x91 -#define DEVICE_ID_RENOIR_1636 0x1636 // Renoir #define ASICREV_IS_RENOIR(eChipRev) ((eChipRev >= RENOIR_A0) && (eChipRev < RAVEN1_F0)) /* @@ -183,6 +182,9 @@ enum { #define DEVICE_ID_TEMASH_9839 0x9839 #define DEVICE_ID_TEMASH_983D 0x983D +/* RENOIR */ +#define DEVICE_ID_RENOIR_1636 0x1636 + /* Asic Family IDs for different asic family. */ #define FAMILY_CI 120 /* Sea Islands: Hawaii (P), Bonaire (M) */ #define FAMILY_KV 125 /* Fusion => Kaveri: Spectre, Spooky; Kabini: Kalindi */ diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c index 4e542826cd26..c33454a9e0b4 100644 --- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c +++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c @@ -734,6 +734,7 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync, { struct core_freesync *core_freesync = NULL; unsigned long long nominal_field_rate_in_uhz = 0; + unsigned long long rounded_nominal_in_uhz = 0; unsigned int refresh_range = 0; unsigned long long min_refresh_in_uhz = 0; unsigned long long max_refresh_in_uhz = 0; @@ -750,17 +751,20 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync, min_refresh_in_uhz = in_config->min_refresh_in_uhz; max_refresh_in_uhz = in_config->max_refresh_in_uhz; - // Don't allow min > max - if (min_refresh_in_uhz > max_refresh_in_uhz) - min_refresh_in_uhz = max_refresh_in_uhz; - // Full range may be larger than current video timing, so cap at nominal if (max_refresh_in_uhz > nominal_field_rate_in_uhz) max_refresh_in_uhz = nominal_field_rate_in_uhz; // Full range may be larger than current video timing, so cap at nominal - if (min_refresh_in_uhz > nominal_field_rate_in_uhz) - min_refresh_in_uhz = nominal_field_rate_in_uhz; + if (min_refresh_in_uhz > max_refresh_in_uhz) + min_refresh_in_uhz = max_refresh_in_uhz; + + // If a monitor reports exactly max refresh of 2x of min, enforce it on nominal + rounded_nominal_in_uhz = + div_u64(nominal_field_rate_in_uhz + 50000, 100000) * 100000; + if (in_config->max_refresh_in_uhz == (2 * in_config->min_refresh_in_uhz) && + in_config->max_refresh_in_uhz == rounded_nominal_in_uhz) + min_refresh_in_uhz = div_u64(nominal_field_rate_in_uhz, 2); if (!vrr_settings_require_update(core_freesync, in_config, (unsigned int)min_refresh_in_uhz, (unsigned int)max_refresh_in_uhz, @@ -792,11 +796,6 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync, refresh_range = in_out_vrr->max_refresh_in_uhz - in_out_vrr->min_refresh_in_uhz; - in_out_vrr->btr.margin_in_us = in_out_vrr->max_duration_in_us - - 2 * in_out_vrr->min_duration_in_us; - if (in_out_vrr->btr.margin_in_us > BTR_MAX_MARGIN) - in_out_vrr->btr.margin_in_us = BTR_MAX_MARGIN; - in_out_vrr->supported = true; } @@ -804,9 +803,14 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync, in_out_vrr->btr.btr_enabled = in_config->btr; - if (in_out_vrr->max_refresh_in_uhz < - 2 * in_out_vrr->min_refresh_in_uhz) + if (in_out_vrr->max_refresh_in_uhz < (2 * in_out_vrr->min_refresh_in_uhz)) in_out_vrr->btr.btr_enabled = false; + else { + in_out_vrr->btr.margin_in_us = in_out_vrr->max_duration_in_us - + 2 * in_out_vrr->min_duration_in_us; + if (in_out_vrr->btr.margin_in_us > BTR_MAX_MARGIN) + in_out_vrr->btr.margin_in_us = BTR_MAX_MARGIN; + } in_out_vrr->btr.btr_active = false; in_out_vrr->btr.inserted_duration_in_us = 0; @@ -1008,8 +1012,8 @@ unsigned long long mod_freesync_calc_nominal_field_rate( unsigned int total = stream->timing.h_total * stream->timing.v_total; /* Calculate nominal field rate for stream, rounded up to nearest integer */ - nominal_field_rate_in_uhz = stream->timing.pix_clk_100hz / 10; - nominal_field_rate_in_uhz *= 1000ULL * 1000ULL * 1000ULL; + nominal_field_rate_in_uhz = stream->timing.pix_clk_100hz; + nominal_field_rate_in_uhz *= 100000000ULL; nominal_field_rate_in_uhz = div_u64(nominal_field_rate_in_uhz, total); diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c index e9fbd94f8635..cc1d3f470b99 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c @@ -328,8 +328,7 @@ enum mod_hdcp_status mod_hdcp_add_display(struct mod_hdcp *hdcp, /* add display to connection */ hdcp->connection.link = *link; *display_container = *display; - status = mod_hdcp_add_display_to_topology(hdcp, display_container); - + status = mod_hdcp_add_display_to_topology(hdcp, display->index); if (status != MOD_HDCP_STATUS_SUCCESS) goto out; @@ -375,7 +374,7 @@ enum mod_hdcp_status mod_hdcp_remove_display(struct mod_hdcp *hdcp, status = mod_hdcp_remove_display_from_topology(hdcp, index); if (status != MOD_HDCP_STATUS_SUCCESS) goto out; - memset(display, 0, sizeof(struct mod_hdcp_display)); + display->state = MOD_HDCP_DISPLAY_INACTIVE; /* request authentication when connection is not reset */ if (current_state(hdcp) != HDCP_UNINITIALIZED) diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h index 60ff1a0028ac..5cb4546be0ef 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h @@ -328,7 +328,7 @@ void mod_hdcp_dump_binary_message(uint8_t *msg, uint32_t msg_size, /* psp functions */ enum mod_hdcp_status mod_hdcp_add_display_to_topology( - struct mod_hdcp *hdcp, struct mod_hdcp_display *display); + struct mod_hdcp *hdcp, uint8_t index); enum mod_hdcp_status mod_hdcp_remove_display_from_topology( struct mod_hdcp *hdcp, uint8_t index); enum mod_hdcp_status mod_hdcp_hdcp1_create_session(struct mod_hdcp *hdcp); @@ -503,6 +503,11 @@ static inline uint8_t is_display_active(struct mod_hdcp_display *display) return display->state >= MOD_HDCP_DISPLAY_ACTIVE; } +static inline uint8_t is_display_added(struct mod_hdcp_display *display) +{ + return display->state >= MOD_HDCP_DISPLAY_ACTIVE_AND_ADDED; +} + static inline uint8_t is_display_encryption_enabled(struct mod_hdcp_display *display) { return display->state >= MOD_HDCP_DISPLAY_ENCRYPTION_ENABLED; @@ -510,23 +515,34 @@ static inline uint8_t is_display_encryption_enabled(struct mod_hdcp_display *dis static inline uint8_t get_active_display_count(struct mod_hdcp *hdcp) { - uint8_t active_count = 0; + uint8_t added_count = 0; uint8_t i; for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) if (is_display_active(&hdcp->displays[i])) - active_count++; - return active_count; + added_count++; + return added_count; +} + +static inline uint8_t get_added_display_count(struct mod_hdcp *hdcp) +{ + uint8_t added_count = 0; + uint8_t i; + + for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) + if (is_display_added(&hdcp->displays[i])) + added_count++; + return added_count; } -static inline struct mod_hdcp_display *get_first_active_display( +static inline struct mod_hdcp_display *get_first_added_display( struct mod_hdcp *hdcp) { uint8_t i; struct mod_hdcp_display *display = NULL; for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) - if (is_display_active(&hdcp->displays[i])) { + if (is_display_added(&hdcp->displays[i])) { display = &hdcp->displays[i]; break; } diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c index f244b72e74e0..37c8c05497d6 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c @@ -129,7 +129,7 @@ static inline uint8_t get_device_count(struct mod_hdcp *hdcp) static inline enum mod_hdcp_status check_device_count(struct mod_hdcp *hdcp) { /* device count must be greater than or equal to tracked hdcp displays */ - return (get_device_count(hdcp) < get_active_display_count(hdcp)) ? + return (get_device_count(hdcp) < get_added_display_count(hdcp)) ? MOD_HDCP_STATUS_HDCP1_DEVICE_COUNT_MISMATCH_FAILURE : MOD_HDCP_STATUS_SUCCESS; } diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c index 549c113abcf7..491c00f48026 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c @@ -208,7 +208,7 @@ static inline uint8_t get_device_count(struct mod_hdcp *hdcp) static enum mod_hdcp_status check_device_count(struct mod_hdcp *hdcp) { /* device count must be greater than or equal to tracked hdcp displays */ - return (get_device_count(hdcp) < get_active_display_count(hdcp)) ? + return (get_device_count(hdcp) < get_added_display_count(hdcp)) ? MOD_HDCP_STATUS_HDCP2_DEVICE_COUNT_MISMATCH_FAILURE : MOD_HDCP_STATUS_SUCCESS; } diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c index 836e47954938..c2929815c3ee 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c @@ -54,7 +54,7 @@ enum mod_hdcp_status mod_hdcp_remove_display_from_topology( dtm_cmd = (struct ta_dtm_shared_memory *)psp->dtm_context.dtm_shared_buf; - if (!display || !is_display_active(display)) + if (!display || !is_display_added(display)) return MOD_HDCP_STATUS_DISPLAY_NOT_FOUND; memset(dtm_cmd, 0, sizeof(struct ta_dtm_shared_memory)); @@ -73,21 +73,25 @@ enum mod_hdcp_status mod_hdcp_remove_display_from_topology( HDCP_TOP_REMOVE_DISPLAY_TRACE(hdcp, display->index); return MOD_HDCP_STATUS_SUCCESS; - } - -enum mod_hdcp_status mod_hdcp_add_display_to_topology( - struct mod_hdcp *hdcp, struct mod_hdcp_display *display) + +} +enum mod_hdcp_status mod_hdcp_add_display_to_topology(struct mod_hdcp *hdcp, + uint8_t index) { struct psp_context *psp = hdcp->config.psp.handle; struct ta_dtm_shared_memory *dtm_cmd; + struct mod_hdcp_display *display = + get_active_display_at_index(hdcp, index); struct mod_hdcp_link *link = &hdcp->connection.link; if (!psp->dtm_context.dtm_initialized) { DRM_ERROR("Failed to add display topology, DTM TA is not initialized."); - display->state = MOD_HDCP_DISPLAY_INACTIVE; return MOD_HDCP_STATUS_FAILURE; } + if (!display || is_display_added(display)) + return MOD_HDCP_STATUS_UPDATE_TOPOLOGY_FAILURE; + dtm_cmd = (struct ta_dtm_shared_memory *)psp->dtm_context.dtm_shared_buf; memset(dtm_cmd, 0, sizeof(struct ta_dtm_shared_memory)); @@ -109,11 +113,10 @@ enum mod_hdcp_status mod_hdcp_add_display_to_topology( psp_dtm_invoke(psp, dtm_cmd->cmd_id); - if (dtm_cmd->dtm_status != TA_DTM_STATUS__SUCCESS) { - display->state = MOD_HDCP_DISPLAY_INACTIVE; + if (dtm_cmd->dtm_status != TA_DTM_STATUS__SUCCESS) return MOD_HDCP_STATUS_UPDATE_TOPOLOGY_FAILURE; - } + display->state = MOD_HDCP_DISPLAY_ACTIVE_AND_ADDED; HDCP_TOP_ADD_DISPLAY_TRACE(hdcp, display->index); return MOD_HDCP_STATUS_SUCCESS; @@ -123,7 +126,7 @@ enum mod_hdcp_status mod_hdcp_hdcp1_create_session(struct mod_hdcp *hdcp) { struct psp_context *psp = hdcp->config.psp.handle; - struct mod_hdcp_display *display = get_first_active_display(hdcp); + struct mod_hdcp_display *display = get_first_added_display(hdcp); struct ta_hdcp_shared_memory *hdcp_cmd; if (!psp->hdcp_context.hdcp_initialized) { @@ -176,7 +179,7 @@ enum mod_hdcp_status mod_hdcp_hdcp1_destroy_session(struct mod_hdcp *hdcp) if (is_display_encryption_enabled( &hdcp->displays[i])) { hdcp->displays[i].state = - MOD_HDCP_DISPLAY_ACTIVE; + MOD_HDCP_DISPLAY_ACTIVE_AND_ADDED; HDCP_HDCP1_DISABLED_TRACE(hdcp, hdcp->displays[i].index); } @@ -228,7 +231,7 @@ enum mod_hdcp_status mod_hdcp_hdcp1_enable_encryption(struct mod_hdcp *hdcp) { struct psp_context *psp = hdcp->config.psp.handle; struct ta_hdcp_shared_memory *hdcp_cmd; - struct mod_hdcp_display *display = get_first_active_display(hdcp); + struct mod_hdcp_display *display = get_first_added_display(hdcp); hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf; memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory)); @@ -298,7 +301,8 @@ enum mod_hdcp_status mod_hdcp_hdcp1_enable_dp_stream_encryption(struct mod_hdcp for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) { - if (hdcp->displays[i].adjust.disable) + if (hdcp->displays[i].state != MOD_HDCP_DISPLAY_ACTIVE_AND_ADDED || + hdcp->displays[i].adjust.disable) continue; memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory)); @@ -360,7 +364,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_create_session(struct mod_hdcp *hdcp) { struct psp_context *psp = hdcp->config.psp.handle; struct ta_hdcp_shared_memory *hdcp_cmd; - struct mod_hdcp_display *display = get_first_active_display(hdcp); + struct mod_hdcp_display *display = get_first_added_display(hdcp); if (!psp->hdcp_context.hdcp_initialized) { DRM_ERROR("Failed to create hdcp session, HDCP TA is not initialized"); @@ -419,7 +423,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_destroy_session(struct mod_hdcp *hdcp) if (is_display_encryption_enabled( &hdcp->displays[i])) { hdcp->displays[i].state = - MOD_HDCP_DISPLAY_ACTIVE; + MOD_HDCP_DISPLAY_ACTIVE_AND_ADDED; HDCP_HDCP2_DISABLED_TRACE(hdcp, hdcp->displays[i].index); } @@ -658,7 +662,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_enable_encryption(struct mod_hdcp *hdcp) { struct psp_context *psp = hdcp->config.psp.handle; struct ta_hdcp_shared_memory *hdcp_cmd; - struct mod_hdcp_display *display = get_first_active_display(hdcp); + struct mod_hdcp_display *display = get_first_added_display(hdcp); hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf; memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory)); @@ -743,7 +747,8 @@ enum mod_hdcp_status mod_hdcp_hdcp2_enable_dp_stream_encryption(struct mod_hdcp for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) { - if (hdcp->displays[i].adjust.disable) + if (hdcp->displays[i].state != MOD_HDCP_DISPLAY_ACTIVE_AND_ADDED || + hdcp->displays[i].adjust.disable) continue; hdcp_cmd->in_msg.hdcp2_enable_dp_stream_encryption.display_handle = hdcp->displays[i].index; hdcp_cmd->in_msg.hdcp2_enable_dp_stream_encryption.session_handle = hdcp->auth.id; diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h index eae9309cfb24..c088602bc1a0 100644 --- a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h +++ b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h @@ -117,6 +117,7 @@ enum mod_hdcp_operation_mode { enum mod_hdcp_display_state { MOD_HDCP_DISPLAY_INACTIVE = 0, MOD_HDCP_DISPLAY_ACTIVE, + MOD_HDCP_DISPLAY_ACTIVE_AND_ADDED, MOD_HDCP_DISPLAY_ENCRYPTION_ENABLED }; diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c index c195575366a3..2a12614a12c2 100644 --- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c @@ -1452,7 +1452,8 @@ static int pp_get_asic_baco_state(void *handle, int *state) if (!hwmgr) return -EINVAL; - if (!hwmgr->pm_en || !hwmgr->hwmgr_func->get_asic_baco_state) + if (!(hwmgr->not_vf && amdgpu_dpm) || + !hwmgr->hwmgr_func->get_asic_baco_state) return 0; mutex_lock(&hwmgr->smu_lock); diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c index c6d3bef15320..1ef0923f7190 100644 --- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c @@ -35,6 +35,7 @@ #include "arcturus_ppt.h" #include "smu_v11_0_pptable.h" #include "arcturus_ppsmc.h" +#include "nbio/nbio_7_4_offset.h" #include "nbio/nbio_7_4_sh_mask.h" #include "amdgpu_xgmi.h" #include <linux/i2c.h> @@ -793,8 +794,21 @@ static int arcturus_force_clk_levels(struct smu_context *smu, struct arcturus_dpm_table *dpm_table; struct arcturus_single_dpm_table *single_dpm_table; uint32_t soft_min_level, soft_max_level; + uint32_t smu_version; int ret = 0; + ret = smu_get_smc_version(smu, NULL, &smu_version); + if (ret) { + pr_err("Failed to get smu version!\n"); + return ret; + } + + if (smu_version >= 0x361200) { + pr_err("Forcing clock level is not supported with " + "54.18 and onwards SMU firmwares\n"); + return -EOPNOTSUPP; + } + soft_min_level = mask ? (ffs(mask) - 1) : 0; soft_max_level = mask ? (fls(mask) - 1) : 0; @@ -1511,6 +1525,38 @@ static int arcturus_set_power_profile_mode(struct smu_context *smu, return 0; } +static int arcturus_set_performance_level(struct smu_context *smu, + enum amd_dpm_forced_level level) +{ + uint32_t smu_version; + int ret; + + ret = smu_get_smc_version(smu, NULL, &smu_version); + if (ret) { + pr_err("Failed to get smu version!\n"); + return ret; + } + + switch (level) { + case AMD_DPM_FORCED_LEVEL_HIGH: + case AMD_DPM_FORCED_LEVEL_LOW: + case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD: + case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK: + case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK: + case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK: + if (smu_version >= 0x361200) { + pr_err("Forcing clock level is not supported with " + "54.18 and onwards SMU firmwares\n"); + return -EOPNOTSUPP; + } + break; + default: + break; + } + + return smu_v11_0_set_performance_level(smu, level); +} + static void arcturus_dump_pptable(struct smu_context *smu) { struct smu_table_context *table_context = &smu->smu_table; @@ -2210,6 +2256,18 @@ static void arcturus_i2c_eeprom_control_fini(struct i2c_adapter *control) i2c_del_adapter(control); } +static bool arcturus_is_baco_supported(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + uint32_t val; + + if (!smu_v11_0_baco_is_support(smu)) + return false; + + val = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP0); + return (val & RCC_BIF_STRAP0__STRAP_PX_CAPABLE_MASK) ? true : false; +} + static uint32_t arcturus_get_pptable_power_limit(struct smu_context *smu) { PPTable_t *pptable = smu->smu_table.driver_pptable; @@ -2272,7 +2330,7 @@ static const struct pptable_funcs arcturus_ppt_funcs = { .get_profiling_clk_mask = arcturus_get_profiling_clk_mask, .get_power_profile_mode = arcturus_get_power_profile_mode, .set_power_profile_mode = arcturus_set_power_profile_mode, - .set_performance_level = smu_v11_0_set_performance_level, + .set_performance_level = arcturus_set_performance_level, /* debug (internal used) */ .dump_pptable = arcturus_dump_pptable, .get_power_limit = arcturus_get_power_limit, @@ -2321,7 +2379,7 @@ static const struct pptable_funcs arcturus_ppt_funcs = { .register_irq_handler = smu_v11_0_register_irq_handler, .set_azalia_d3_pme = smu_v11_0_set_azalia_d3_pme, .get_max_sustainable_clocks_by_dc = smu_v11_0_get_max_sustainable_clocks_by_dc, - .baco_is_support= smu_v11_0_baco_is_support, + .baco_is_support= arcturus_is_baco_supported, .baco_get_state = smu_v11_0_baco_get_state, .baco_set_state = smu_v11_0_baco_set_state, .baco_enter = smu_v11_0_baco_enter, diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c index 9c60b38ab53a..15030284b444 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c @@ -28,13 +28,15 @@ #include "smu_internal.h" #include "atomfirmware.h" #include "amdgpu_atomfirmware.h" +#include "soc15_common.h" #include "smu_v11_0.h" #include "smu11_driver_if_navi10.h" #include "atom.h" #include "navi10_ppt.h" #include "smu_v11_0_pptable.h" #include "smu_v11_0_ppsmc.h" -#include "nbio/nbio_7_4_sh_mask.h" +#include "nbio/nbio_2_3_offset.h" +#include "nbio/nbio_2_3_sh_mask.h" #include "asic_reg/mp/mp_11_0_sh_mask.h" @@ -1985,6 +1987,18 @@ static int navi10_setup_od_limits(struct smu_context *smu) { return 0; } +static bool navi10_is_baco_supported(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + uint32_t val; + + if (!smu_v11_0_baco_is_support(smu)) + return false; + + val = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP0); + return (val & RCC_BIF_STRAP0__STRAP_PX_CAPABLE_MASK) ? true : false; +} + static int navi10_set_default_od_settings(struct smu_context *smu, bool initialize) { OverDriveTable_t *od_table, *boot_od_table; int ret = 0; @@ -2361,7 +2375,7 @@ static const struct pptable_funcs navi10_ppt_funcs = { .register_irq_handler = smu_v11_0_register_irq_handler, .set_azalia_d3_pme = smu_v11_0_set_azalia_d3_pme, .get_max_sustainable_clocks_by_dc = smu_v11_0_get_max_sustainable_clocks_by_dc, - .baco_is_support= smu_v11_0_baco_is_support, + .baco_is_support= navi10_is_baco_supported, .baco_get_state = smu_v11_0_baco_get_state, .baco_set_state = smu_v11_0_baco_set_state, .baco_enter = smu_v11_0_baco_enter, diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c index 7bf52ecba01d..ff73a735b888 100644 --- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c @@ -239,6 +239,7 @@ static int renoir_print_clk_levels(struct smu_context *smu, uint32_t cur_value = 0, value = 0, count = 0, min = 0, max = 0; DpmClocks_t *clk_table = smu->smu_table.clocks_table; SmuMetrics_t metrics; + bool cur_value_match_level = false; if (!clk_table || clk_type >= SMU_CLK_COUNT) return -EINVAL; @@ -297,8 +298,13 @@ static int renoir_print_clk_levels(struct smu_context *smu, GET_DPM_CUR_FREQ(clk_table, clk_type, i, value); size += sprintf(buf + size, "%d: %uMhz %s\n", i, value, cur_value == value ? "*" : ""); + if (cur_value == value) + cur_value_match_level = true; } + if (!cur_value_match_level) + size += sprintf(buf + size, " %uMhz *\n", cur_value); + return size; } @@ -887,6 +893,17 @@ static int renoir_read_sensor(struct smu_context *smu, return ret; } +static bool renoir_is_dpm_running(struct smu_context *smu) +{ + /* + * Util now, the pmfw hasn't exported the interface of SMU + * feature mask to APU SKU so just force on all the feature + * at early initial stage. + */ + return true; + +} + static const struct pptable_funcs renoir_ppt_funcs = { .get_smu_msg_index = renoir_get_smu_msg_index, .get_smu_clk_index = renoir_get_smu_clk_index, @@ -927,6 +944,7 @@ static const struct pptable_funcs renoir_ppt_funcs = { .mode2_reset = smu_v12_0_mode2_reset, .set_soft_freq_limited_range = smu_v12_0_set_soft_freq_limited_range, .set_driver_table_location = smu_v12_0_set_driver_table_location, + .is_dpm_running = renoir_is_dpm_running, }; void renoir_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.h b/drivers/gpu/drm/amd/powerplay/renoir_ppt.h index 2a390ddd37dd..89cd6da118a3 100644 --- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.h +++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.h @@ -37,7 +37,7 @@ extern void renoir_set_ppt_funcs(struct smu_context *smu); freq = table->SocClocks[dpm_level].Freq; \ break; \ case SMU_MCLK: \ - freq = table->MemClocks[dpm_level].Freq; \ + freq = table->FClocks[dpm_level].Freq; \ break; \ case SMU_DCEFCLK: \ freq = table->DcfClocks[dpm_level].Freq; \ diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c index d19e1d0d56c0..541c932a6005 100644 --- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c +++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c @@ -42,8 +42,6 @@ #include "asic_reg/thm/thm_11_0_2_sh_mask.h" #include "asic_reg/mp/mp_11_0_offset.h" #include "asic_reg/mp/mp_11_0_sh_mask.h" -#include "asic_reg/nbio/nbio_7_4_offset.h" -#include "asic_reg/nbio/nbio_7_4_sh_mask.h" #include "asic_reg/smuio/smuio_11_0_0_offset.h" #include "asic_reg/smuio/smuio_11_0_0_sh_mask.h" @@ -1662,9 +1660,7 @@ static int smu_v11_0_baco_set_armd3_sequence(struct smu_context *smu, enum smu_v bool smu_v11_0_baco_is_support(struct smu_context *smu) { - struct amdgpu_device *adev = smu->adev; struct smu_baco_context *smu_baco = &smu->smu_baco; - uint32_t val; bool baco_support; mutex_lock(&smu_baco->mutex); @@ -1679,11 +1675,7 @@ bool smu_v11_0_baco_is_support(struct smu_context *smu) !smu_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT)) return false; - val = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP0); - if (val & RCC_BIF_STRAP0__STRAP_PX_CAPABLE_MASK) - return true; - - return false; + return true; } enum smu_baco_state smu_v11_0_baco_get_state(struct smu_context *smu) @@ -1700,11 +1692,9 @@ enum smu_baco_state smu_v11_0_baco_get_state(struct smu_context *smu) int smu_v11_0_baco_set_state(struct smu_context *smu, enum smu_baco_state state) { - struct smu_baco_context *smu_baco = &smu->smu_baco; struct amdgpu_device *adev = smu->adev; struct amdgpu_ras *ras = amdgpu_ras_get_context(adev); - uint32_t bif_doorbell_intr_cntl; uint32_t data; int ret = 0; @@ -1713,14 +1703,7 @@ int smu_v11_0_baco_set_state(struct smu_context *smu, enum smu_baco_state state) mutex_lock(&smu_baco->mutex); - bif_doorbell_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL); - if (state == SMU_BACO_STATE_ENTER) { - bif_doorbell_intr_cntl = REG_SET_FIELD(bif_doorbell_intr_cntl, - BIF_DOORBELL_INT_CNTL, - DOORBELL_INTERRUPT_DISABLE, 1); - WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl); - if (!ras || !ras->supported) { data = RREG32_SOC15(THM, 0, mmTHM_BACO_CNTL); data |= 0x80000000; @@ -1735,11 +1718,6 @@ int smu_v11_0_baco_set_state(struct smu_context *smu, enum smu_baco_state state) if (ret) goto out; - bif_doorbell_intr_cntl = REG_SET_FIELD(bif_doorbell_intr_cntl, - BIF_DOORBELL_INT_CNTL, - DOORBELL_INTERRUPT_DISABLE, 0); - WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl); - /* clear vbios scratch 6 and 7 for coming asic reinit */ WREG32(adev->bios_scratch_reg_offset + 6, 0); WREG32(adev->bios_scratch_reg_offset + 7, 0); diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c index 49ff3756bd9f..3f1044326dcb 100644 --- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c @@ -35,6 +35,7 @@ #include "vega20_ppt.h" #include "vega20_pptable.h" #include "vega20_ppsmc.h" +#include "nbio/nbio_7_4_offset.h" #include "nbio/nbio_7_4_sh_mask.h" #include "asic_reg/thm/thm_11_0_2_offset.h" #include "asic_reg/thm/thm_11_0_2_sh_mask.h" @@ -3174,6 +3175,17 @@ static int vega20_update_pcie_parameters(struct smu_context *smu, return ret; } +static bool vega20_is_baco_supported(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + uint32_t val; + + if (!smu_v11_0_baco_is_support(smu)) + return false; + + val = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP0); + return (val & RCC_BIF_STRAP0__STRAP_PX_CAPABLE_MASK) ? true : false; +} static const struct pptable_funcs vega20_ppt_funcs = { .tables_init = vega20_tables_init, @@ -3262,7 +3274,7 @@ static const struct pptable_funcs vega20_ppt_funcs = { .register_irq_handler = smu_v11_0_register_irq_handler, .set_azalia_d3_pme = smu_v11_0_set_azalia_d3_pme, .get_max_sustainable_clocks_by_dc = smu_v11_0_get_max_sustainable_clocks_by_dc, - .baco_is_support= smu_v11_0_baco_is_support, + .baco_is_support= vega20_is_baco_supported, .baco_get_state = smu_v11_0_baco_get_state, .baco_set_state = smu_v11_0_baco_set_state, .baco_enter = smu_v11_0_baco_enter, |