diff options
Diffstat (limited to 'drivers/gpu/drm/amd/display/dc/dml')
10 files changed, 55 insertions, 25 deletions
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile index 5b2a65b42403..8df251626e22 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile @@ -24,15 +24,20 @@ # It provides the general basic services required by other DAL # subcomponents. -ifneq ($(call cc-option, -mpreferred-stack-boundary=4),) - cc_stack_align := -mpreferred-stack-boundary=4 -else ifneq ($(call cc-option, -mstack-alignment=16),) - cc_stack_align := -mstack-alignment=16 -endif +dml_ccflags := -mhard-float -msse -dml_ccflags := -mhard-float -msse $(cc_stack_align) +ifdef CONFIG_CC_IS_GCC +ifeq ($(call cc-ifversion, -lt, 0701, y), y) +IS_OLD_GCC = 1 +endif +endif -ifdef CONFIG_CC_IS_CLANG +ifdef IS_OLD_GCC +# Stack alignment mismatch, proceed with caution. +# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 +# (8B stack alignment). +dml_ccflags += -mpreferred-stack-boundary=4 +else dml_ccflags += -msse2 endif diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c index 649883777f62..6c6c486b774a 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c @@ -2577,7 +2577,8 @@ static void dml20_DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPer mode_lib->vba.MinActiveDRAMClockChangeMargin + mode_lib->vba.DRAMClockChangeLatency; - if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 0) { + if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 50) { + mode_lib->vba.DRAMClockChangeWatermark += 25; mode_lib->vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vactive; } else { if (mode_lib->vba.SynchronizedVBlank || mode_lib->vba.NumberOfActivePlanes == 1) { diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c index 0fafd693ffb4..3c70dd577292 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c @@ -38,6 +38,7 @@ #define BPP_INVALID 0 #define BPP_BLENDED_PIPE 0xffffffff +#define DCN20_MAX_DSC_IMAGE_WIDTH 5184 static double adjust_ReturnBW( struct display_mode_lib *mode_lib, @@ -2610,7 +2611,8 @@ static void dml20v2_DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndP mode_lib->vba.MinActiveDRAMClockChangeMargin + mode_lib->vba.DRAMClockChangeLatency; - if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 0) { + if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 50) { + mode_lib->vba.DRAMClockChangeWatermark += 25; mode_lib->vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vactive; } else { if (mode_lib->vba.SynchronizedVBlank || mode_lib->vba.NumberOfActivePlanes == 1) { @@ -3901,6 +3903,10 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode mode_lib->vba.MaximumSwathWidthInLineBuffer); } for (i = 0; i <= mode_lib->vba.soc.num_states; i++) { + double MaxMaxDispclkRoundedDown = RoundToDFSGranularityDown( + mode_lib->vba.MaxDispclk[mode_lib->vba.soc.num_states], + mode_lib->vba.DISPCLKDPPCLKVCOSpeed); + for (j = 0; j < 2; j++) { mode_lib->vba.MaxDispclkRoundedDownToDFSGranularity = RoundToDFSGranularityDown( mode_lib->vba.MaxDispclk[i], @@ -3925,7 +3931,9 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode && i == mode_lib->vba.soc.num_states) mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine = mode_lib->vba.PixelClock[k] / 2 * (1 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0); - if (mode_lib->vba.ODMCapability == false || mode_lib->vba.PlaneRequiredDISPCLKWithoutODMCombine <= mode_lib->vba.MaxDispclkRoundedDownToDFSGranularity) { + if (mode_lib->vba.ODMCapability == false || + (locals->PlaneRequiredDISPCLKWithoutODMCombine <= MaxMaxDispclkRoundedDown + && (!locals->DSCEnabled[k] || locals->HActive[k] <= DCN20_MAX_DSC_IMAGE_WIDTH))) { locals->ODMCombineEnablePerState[i][k] = false; mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithoutODMCombine; } else { diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c index 878bf4782ce6..2c7455e22a65 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c @@ -207,7 +207,7 @@ static void extract_rq_regs(struct display_mode_lib *mode_lib, rq_regs->rq_regs_l.swath_height = dml_log2(rq_param.dlg.rq_l.swath_height); rq_regs->rq_regs_c.swath_height = dml_log2(rq_param.dlg.rq_c.swath_height); - // FIXME: take the max between luma, chroma chunk size? + // TODO: take the max between luma, chroma chunk size? // okay for now, as we are setting chunk_bytes to 8kb anyways if (rq_param.sizing.rq_l.chunk_bytes >= 32 * 1024) { //32kb rq_regs->drq_expansion_mode = 0; @@ -677,7 +677,7 @@ static void get_surf_rq_param(struct display_mode_lib *mode_lib, unsigned int meta_pitch = 0; unsigned int ppe = mode_422 ? 2 : 1; - // FIXME check if ppe apply for both luma and chroma in 422 case + // TODO check if ppe apply for both luma and chroma in 422 case if (is_chroma) { vp_width = pipe_src_param.viewport_width_c / ppe; vp_height = pipe_src_param.viewport_height_c; @@ -959,7 +959,7 @@ static void dml20_rq_dlg_get_dlg_params(struct display_mode_lib *mode_lib, // Source // dcc_en = src.dcc; dual_plane = is_dual_plane((enum source_format_class)(src->source_format)); - mode_422 = 0; // FIXME + mode_422 = 0; // TODO access_dir = (src->source_scan == dm_vert); // vp access direction: horizontal or vertical accessed // bytes_per_element_l = get_bytes_per_element(source_format_class(src.source_format), 0); // bytes_per_element_c = get_bytes_per_element(source_format_class(src.source_format), 1); @@ -1655,7 +1655,7 @@ static void calculate_ttu_cursor(struct display_mode_lib *mode_lib, cur_width_ub = dml_ceil((double) cur_src_width / (double) cur_req_width, 1) * (double) cur_req_width; cur_req_per_width = cur_width_ub / (double) cur_req_width; - hactive_cur = (double) cur_src_width / hscl_ratio; // FIXME: oswin to think about what to do for cursor + hactive_cur = (double) cur_src_width / hscl_ratio; // TODO: oswin to think about what to do for cursor if (vratio_pre_l <= 1.0) { *refcyc_per_req_delivery_pre_cur = hactive_cur * ref_freq_to_pix_freq diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c index ed8bf5f723c9..1e6aeb1bd2bf 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c @@ -207,7 +207,7 @@ static void extract_rq_regs(struct display_mode_lib *mode_lib, rq_regs->rq_regs_l.swath_height = dml_log2(rq_param.dlg.rq_l.swath_height); rq_regs->rq_regs_c.swath_height = dml_log2(rq_param.dlg.rq_c.swath_height); - // FIXME: take the max between luma, chroma chunk size? + // TODO: take the max between luma, chroma chunk size? // okay for now, as we are setting chunk_bytes to 8kb anyways if (rq_param.sizing.rq_l.chunk_bytes >= 32 * 1024) { //32kb rq_regs->drq_expansion_mode = 0; @@ -677,7 +677,7 @@ static void get_surf_rq_param(struct display_mode_lib *mode_lib, unsigned int meta_pitch = 0; unsigned int ppe = mode_422 ? 2 : 1; - // FIXME check if ppe apply for both luma and chroma in 422 case + // TODO check if ppe apply for both luma and chroma in 422 case if (is_chroma) { vp_width = pipe_src_param.viewport_width_c / ppe; vp_height = pipe_src_param.viewport_height_c; @@ -959,7 +959,7 @@ static void dml20v2_rq_dlg_get_dlg_params(struct display_mode_lib *mode_lib, // Source // dcc_en = src.dcc; dual_plane = is_dual_plane((enum source_format_class)(src->source_format)); - mode_422 = 0; // FIXME + mode_422 = 0; // TODO access_dir = (src->source_scan == dm_vert); // vp access direction: horizontal or vertical accessed // bytes_per_element_l = get_bytes_per_element(source_format_class(src.source_format), 0); // bytes_per_element_c = get_bytes_per_element(source_format_class(src.source_format), 1); @@ -1655,7 +1655,7 @@ static void calculate_ttu_cursor(struct display_mode_lib *mode_lib, cur_width_ub = dml_ceil((double) cur_src_width / (double) cur_req_width, 1) * (double) cur_req_width; cur_req_per_width = cur_width_ub / (double) cur_req_width; - hactive_cur = (double) cur_src_width / hscl_ratio; // FIXME: oswin to think about what to do for cursor + hactive_cur = (double) cur_src_width / hscl_ratio; // TODO: oswin to think about what to do for cursor if (vratio_pre_l <= 1.0) { *refcyc_per_req_delivery_pre_cur = hactive_cur * ref_freq_to_pix_freq diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c index 3b6ed60dcd35..ba77957aefe3 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c @@ -65,6 +65,7 @@ typedef struct { #define BPP_INVALID 0 #define BPP_BLENDED_PIPE 0xffffffff +#define DCN21_MAX_DSC_IMAGE_WIDTH 5184 static void DisplayPipeConfiguration(struct display_mode_lib *mode_lib); static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation( @@ -3379,6 +3380,8 @@ static unsigned int TruncToValidBPP( return 30; else if (DecimalBPP >= 24 && (DesiredBPP == 0 || DesiredBPP == 24)) return 24; + else if (DecimalBPP >= 18 && (DesiredBPP == 0 || DesiredBPP == 18)) + return 18; else return BPP_INVALID; } @@ -3936,6 +3939,10 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.MaximumSwathWidthInLineBuffer); } for (i = 0; i <= mode_lib->vba.soc.num_states; i++) { + double MaxMaxDispclkRoundedDown = RoundToDFSGranularityDown( + mode_lib->vba.MaxDispclk[mode_lib->vba.soc.num_states], + mode_lib->vba.DISPCLKDPPCLKVCOSpeed); + for (j = 0; j < 2; j++) { mode_lib->vba.MaxDispclkRoundedDownToDFSGranularity = RoundToDFSGranularityDown( mode_lib->vba.MaxDispclk[i], @@ -3965,7 +3972,9 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l && i == mode_lib->vba.soc.num_states) mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine = mode_lib->vba.PixelClock[k] / 2 * (1 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0); - if (mode_lib->vba.ODMCapability == false || mode_lib->vba.PlaneRequiredDISPCLKWithoutODMCombine <= mode_lib->vba.MaxDispclkRoundedDownToDFSGranularity) { + if (mode_lib->vba.ODMCapability == false || + (locals->PlaneRequiredDISPCLKWithoutODMCombine <= MaxMaxDispclkRoundedDown + && (!locals->DSCEnabled[k] || locals->HActive[k] <= DCN21_MAX_DSC_IMAGE_WIDTH))) { locals->ODMCombineEnablePerState[i][k] = false; mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithoutODMCombine; } else { 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 f4c1ef9046bf..cfacd6027467 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 @@ -269,7 +269,7 @@ struct writeback_st { struct _vcs_dpi_display_output_params_st { int dp_lanes; - int output_bpp; + double output_bpp; int dsc_enable; int wb_enable; int num_active_wb; @@ -318,6 +318,7 @@ struct _vcs_dpi_display_pipe_dest_params_st { unsigned int vupdate_width; unsigned int vready_offset; unsigned char interlaced; + unsigned char embedded; double pixel_rate_mhz; unsigned char synchronized_vblank_all_planes; unsigned char otg_inst; diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c index 65cf4edddaff..7f9a5621922f 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c @@ -375,6 +375,7 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib) mode_lib->vba.pipe_plane[j] = mode_lib->vba.NumberOfActivePlanes; + mode_lib->vba.EmbeddedPanel[mode_lib->vba.NumberOfActivePlanes] = dst->embedded; mode_lib->vba.DPPPerPlane[mode_lib->vba.NumberOfActivePlanes] = 1; mode_lib->vba.SourceScan[mode_lib->vba.NumberOfActivePlanes] = (enum scan_direction_class) (src->source_scan); @@ -432,8 +433,12 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib) dst->recout_width; // TODO: or should this be full_recout_width???...maybe only when in hsplit mode? mode_lib->vba.ODMCombineEnabled[mode_lib->vba.NumberOfActivePlanes] = dst->odm_combine; + mode_lib->vba.ODMCombineTypeEnabled[mode_lib->vba.NumberOfActivePlanes] = + dst->odm_combine; mode_lib->vba.OutputFormat[mode_lib->vba.NumberOfActivePlanes] = (enum output_format_class) (dout->output_format); + mode_lib->vba.OutputBpp[mode_lib->vba.NumberOfActivePlanes] = + dout->output_bpp; mode_lib->vba.Output[mode_lib->vba.NumberOfActivePlanes] = (enum output_encoder_class) (dout->output_type); diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h index 91decac50557..1540ffbe3979 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h @@ -387,6 +387,7 @@ struct vba_vars_st { /* vba mode support */ /*inputs*/ + bool EmbeddedPanel[DC__NUM_DPP__MAX]; bool SupportGFX7CompatibleTilingIn32bppAnd64bpp; double MaxHSCLRatio; double MaxVSCLRatio; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c b/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c index ad8571f5a142..4c3e9cc30167 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c @@ -243,7 +243,7 @@ void dml1_extract_rq_regs( rq_regs->rq_regs_l.swath_height = dml_log2(rq_param.dlg.rq_l.swath_height); rq_regs->rq_regs_c.swath_height = dml_log2(rq_param.dlg.rq_c.swath_height); - /* FIXME: take the max between luma, chroma chunk size? + /* TODO: take the max between luma, chroma chunk size? * okay for now, as we are setting chunk_bytes to 8kb anyways */ if (rq_param.sizing.rq_l.chunk_bytes >= 32 * 1024) { /*32kb */ @@ -602,7 +602,7 @@ static void get_surf_rq_param( unsigned int log2_dpte_group_length; unsigned int func_meta_row_height, func_dpte_row_height; - /* FIXME check if ppe apply for both luma and chroma in 422 case */ + /* TODO check if ppe apply for both luma and chroma in 422 case */ if (is_chroma) { vp_width = pipe_src_param.viewport_width_c / ppe; vp_height = pipe_src_param.viewport_height_c; @@ -1141,7 +1141,7 @@ void dml1_rq_dlg_get_dlg_params( ASSERT(disp_dlg_regs->refcyc_h_blank_end < (unsigned int) dml_pow(2, 13)); disp_dlg_regs->dlg_vblank_end = interlaced ? (vblank_end / 2) : vblank_end; /* 15 bits */ - prefetch_xy_calc_in_dcfclk = 24.0; /* FIXME: ip_param */ + prefetch_xy_calc_in_dcfclk = 24.0; /* TODO: ip_param */ min_dcfclk_mhz = dlg_sys_param.deepsleep_dcfclk_mhz; t_calc_us = prefetch_xy_calc_in_dcfclk / min_dcfclk_mhz; min_ttu_vblank = dlg_sys_param.t_urg_wm_us; @@ -1182,7 +1182,7 @@ void dml1_rq_dlg_get_dlg_params( dcc_en = e2e_pipe_param.pipe.src.dcc; dual_plane = is_dual_plane( (enum source_format_class) e2e_pipe_param.pipe.src.source_format); - mode_422 = 0; /* FIXME */ + mode_422 = 0; /* TODO */ access_dir = (e2e_pipe_param.pipe.src.source_scan == dm_vert); /* vp access direction: horizontal or vertical accessed */ bytes_per_element_l = get_bytes_per_element( (enum source_format_class) e2e_pipe_param.pipe.src.source_format, @@ -1837,7 +1837,7 @@ void dml1_rq_dlg_get_dlg_params( cur0_width_ub = dml_ceil((double) cur0_src_width / (double) cur0_req_width, 1) * (double) cur0_req_width; cur0_req_per_width = cur0_width_ub / (double) cur0_req_width; - hactive_cur0 = (double) cur0_src_width / hratios_cur0; /* FIXME: oswin to think about what to do for cursor */ + hactive_cur0 = (double) cur0_src_width / hratios_cur0; /* TODO: oswin to think about what to do for cursor */ if (vratio_pre_l <= 1.0) { refcyc_per_req_delivery_pre_cur0 = hactive_cur0 * ref_freq_to_pix_freq |