diff options
Diffstat (limited to 'drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c')
| -rw-r--r-- | drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c | 260 |
1 files changed, 256 insertions, 4 deletions
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c index 0cbab81..4ee3c26 100644 --- a/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c +++ b/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c @@ -28,6 +28,7 @@ #include "dc.h" #include "core_types.h" #include "dal_asic_id.h" +#include "calcs_logger.h" /* * NOTE: @@ -52,11 +53,16 @@ static enum bw_calcs_version bw_calcs_version_from_asic_id(struct hw_asic_id asi return BW_CALCS_VERSION_CARRIZO; case FAMILY_VI: + if (ASIC_REV_IS_POLARIS12_V(asic_id.hw_internal_rev)) + return BW_CALCS_VERSION_POLARIS12; if (ASIC_REV_IS_POLARIS10_P(asic_id.hw_internal_rev)) return BW_CALCS_VERSION_POLARIS10; - if (ASIC_REV_IS_POLARIS11_M(asic_id.hw_internal_rev) || - ASIC_REV_IS_POLARIS12_V(asic_id.hw_internal_rev)) + if (ASIC_REV_IS_POLARIS11_M(asic_id.hw_internal_rev)) return BW_CALCS_VERSION_POLARIS11; +#if defined(CONFIG_DRM_AMD_DC_VEGAM) + if (ASIC_REV_IS_VEGAM(asic_id.hw_internal_rev)) + return BW_CALCS_VERSION_VEGAM; +#endif return BW_CALCS_VERSION_INVALID; case FAMILY_AI: @@ -2145,6 +2151,11 @@ void bw_calcs_init(struct bw_calcs_dceip *bw_dceip, dceip.mcifwr_all_surfaces_burst_time = bw_int_to_fixed(0); /* todo: this is a bug*/ break; case BW_CALCS_VERSION_POLARIS10: +#if defined(CONFIG_DRM_AMD_DC_VEGAM) + /* TODO: Treat VEGAM the same as P10 for now + * Need to tune the para for VEGAM if needed */ + case BW_CALCS_VERSION_VEGAM: +#endif vbios.memory_type = bw_def_gddr5; vbios.dram_channel_width_in_bits = 32; vbios.number_of_dram_channels = asic_id.vram_width / vbios.dram_channel_width_in_bits; @@ -2373,6 +2384,122 @@ void bw_calcs_init(struct bw_calcs_dceip *bw_dceip, dceip.scatter_gather_pte_request_rows_in_tiling_mode = 2; dceip.mcifwr_all_surfaces_burst_time = bw_int_to_fixed(0); break; + case BW_CALCS_VERSION_POLARIS12: + vbios.memory_type = bw_def_gddr5; + vbios.dram_channel_width_in_bits = 32; + vbios.number_of_dram_channels = asic_id.vram_width / vbios.dram_channel_width_in_bits; + vbios.number_of_dram_banks = 8; + vbios.high_yclk = bw_int_to_fixed(6000); + vbios.mid_yclk = bw_int_to_fixed(3200); + vbios.low_yclk = bw_int_to_fixed(1000); + vbios.low_sclk = bw_int_to_fixed(678); + vbios.mid1_sclk = bw_int_to_fixed(864); + vbios.mid2_sclk = bw_int_to_fixed(900); + vbios.mid3_sclk = bw_int_to_fixed(920); + vbios.mid4_sclk = bw_int_to_fixed(940); + vbios.mid5_sclk = bw_int_to_fixed(960); + vbios.mid6_sclk = bw_int_to_fixed(980); + vbios.high_sclk = bw_int_to_fixed(1049); + vbios.low_voltage_max_dispclk = bw_int_to_fixed(459); + vbios.mid_voltage_max_dispclk = bw_int_to_fixed(654); + vbios.high_voltage_max_dispclk = bw_int_to_fixed(1108); + vbios.low_voltage_max_phyclk = bw_int_to_fixed(540); + vbios.mid_voltage_max_phyclk = bw_int_to_fixed(810); + vbios.high_voltage_max_phyclk = bw_int_to_fixed(810); + vbios.data_return_bus_width = bw_int_to_fixed(32); + vbios.trc = bw_int_to_fixed(48); + if (vbios.number_of_dram_channels == 2) // 64-bit + vbios.dmifmc_urgent_latency = bw_int_to_fixed(4); + else + vbios.dmifmc_urgent_latency = bw_int_to_fixed(3); + vbios.stutter_self_refresh_exit_latency = bw_int_to_fixed(5); + vbios.stutter_self_refresh_entry_latency = bw_int_to_fixed(0); + vbios.nbp_state_change_latency = bw_int_to_fixed(250); + vbios.mcifwrmc_urgent_latency = bw_int_to_fixed(10); + vbios.scatter_gather_enable = false; + vbios.down_spread_percentage = bw_frc_to_fixed(5, 10); + vbios.cursor_width = 32; + vbios.average_compression_rate = 4; + vbios.number_of_request_slots_gmc_reserves_for_dmif_per_channel = 256; + vbios.blackout_duration = bw_int_to_fixed(0); /* us */ + vbios.maximum_blackout_recovery_time = bw_int_to_fixed(0); + + dceip.max_average_percent_of_ideal_port_bw_display_can_use_in_normal_system_operation = 100; + dceip.max_average_percent_of_ideal_drambw_display_can_use_in_normal_system_operation = 100; + dceip.percent_of_ideal_port_bw_received_after_urgent_latency = 100; + dceip.large_cursor = false; + dceip.dmif_request_buffer_size = bw_int_to_fixed(768); + dceip.dmif_pipe_en_fbc_chunk_tracker = false; + dceip.cursor_max_outstanding_group_num = 1; + dceip.lines_interleaved_into_lb = 2; + dceip.chunk_width = 256; + dceip.number_of_graphics_pipes = 5; + dceip.number_of_underlay_pipes = 0; + dceip.low_power_tiling_mode = 0; + dceip.display_write_back_supported = true; + dceip.argb_compression_support = true; + dceip.underlay_vscaler_efficiency6_bit_per_component = + bw_frc_to_fixed(35556, 10000); + dceip.underlay_vscaler_efficiency8_bit_per_component = + bw_frc_to_fixed(34286, 10000); + dceip.underlay_vscaler_efficiency10_bit_per_component = + bw_frc_to_fixed(32, 10); + dceip.underlay_vscaler_efficiency12_bit_per_component = + bw_int_to_fixed(3); + dceip.graphics_vscaler_efficiency6_bit_per_component = + bw_frc_to_fixed(35, 10); + dceip.graphics_vscaler_efficiency8_bit_per_component = + bw_frc_to_fixed(34286, 10000); + dceip.graphics_vscaler_efficiency10_bit_per_component = + bw_frc_to_fixed(32, 10); + dceip.graphics_vscaler_efficiency12_bit_per_component = + bw_int_to_fixed(3); + dceip.alpha_vscaler_efficiency = bw_int_to_fixed(3); + dceip.max_dmif_buffer_allocated = 4; + dceip.graphics_dmif_size = 12288; + dceip.underlay_luma_dmif_size = 19456; + dceip.underlay_chroma_dmif_size = 23552; + dceip.pre_downscaler_enabled = true; + dceip.underlay_downscale_prefetch_enabled = true; + dceip.lb_write_pixels_per_dispclk = bw_int_to_fixed(1); + dceip.lb_size_per_component444 = bw_int_to_fixed(245952); + dceip.graphics_lb_nodownscaling_multi_line_prefetching = true; + dceip.stutter_and_dram_clock_state_change_gated_before_cursor = + bw_int_to_fixed(1); + dceip.underlay420_luma_lb_size_per_component = bw_int_to_fixed( + 82176); + dceip.underlay420_chroma_lb_size_per_component = + bw_int_to_fixed(164352); + dceip.underlay422_lb_size_per_component = bw_int_to_fixed( + 82176); + dceip.cursor_chunk_width = bw_int_to_fixed(64); + dceip.cursor_dcp_buffer_lines = bw_int_to_fixed(4); + dceip.underlay_maximum_width_efficient_for_tiling = + bw_int_to_fixed(1920); + dceip.underlay_maximum_height_efficient_for_tiling = + bw_int_to_fixed(1080); + dceip.peak_pte_request_to_eviction_ratio_limiting_multiple_displays_or_single_rotated_display = + bw_frc_to_fixed(3, 10); + dceip.peak_pte_request_to_eviction_ratio_limiting_single_display_no_rotation = + bw_int_to_fixed(25); + dceip.minimum_outstanding_pte_request_limit = bw_int_to_fixed( + 2); + dceip.maximum_total_outstanding_pte_requests_allowed_by_saw = + bw_int_to_fixed(128); + dceip.limit_excessive_outstanding_dmif_requests = true; + dceip.linear_mode_line_request_alternation_slice = + bw_int_to_fixed(64); + dceip.scatter_gather_lines_of_pte_prefetching_in_linear_mode = + 32; + dceip.display_write_back420_luma_mcifwr_buffer_size = 12288; + dceip.display_write_back420_chroma_mcifwr_buffer_size = 8192; + dceip.request_efficiency = bw_frc_to_fixed(8, 10); + dceip.dispclk_per_request = bw_int_to_fixed(2); + dceip.dispclk_ramping_factor = bw_frc_to_fixed(105, 100); + dceip.display_pipe_throughput_factor = bw_frc_to_fixed(105, 100); + dceip.scatter_gather_pte_request_rows_in_tiling_mode = 2; + dceip.mcifwr_all_surfaces_burst_time = bw_int_to_fixed(0); + break; case BW_CALCS_VERSION_STONEY: vbios.memory_type = bw_def_gddr5; vbios.dram_channel_width_in_bits = 64; @@ -2815,6 +2942,19 @@ static void populate_initial_data( data->bytes_per_pixel[num_displays + 4] = 4; break; } + } else if (pipe[i].stream->dst.width != 0 && + pipe[i].stream->dst.height != 0 && + pipe[i].stream->src.width != 0 && + pipe[i].stream->src.height != 0) { + data->src_width[num_displays + 4] = bw_int_to_fixed(pipe[i].stream->src.width); + data->pitch_in_pixels[num_displays + 4] = data->src_width[num_displays + 4]; + data->src_height[num_displays + 4] = bw_int_to_fixed(pipe[i].stream->src.height); + data->h_taps[num_displays + 4] = pipe[i].stream->src.width == pipe[i].stream->dst.width ? bw_int_to_fixed(1) : bw_int_to_fixed(2); + data->v_taps[num_displays + 4] = pipe[i].stream->src.height == pipe[i].stream->dst.height ? bw_int_to_fixed(1) : bw_int_to_fixed(2); + data->h_scale_ratio[num_displays + 4] = bw_frc_to_fixed(pipe[i].stream->src.width, pipe[i].stream->dst.width); + data->v_scale_ratio[num_displays + 4] = bw_frc_to_fixed(pipe[i].stream->src.height, pipe[i].stream->dst.height); + data->rotation_angle[num_displays + 4] = bw_int_to_fixed(0); + data->bytes_per_pixel[num_displays + 4] = 4; } else { data->src_width[num_displays + 4] = bw_int_to_fixed(pipe[i].stream->timing.h_addressable); data->pitch_in_pixels[num_displays + 4] = data->src_width[num_displays + 4]; @@ -2873,6 +3013,11 @@ bool bw_calcs(struct dc_context *ctx, struct bw_fixed mid_yclk = vbios->mid_yclk; struct bw_fixed low_yclk = vbios->low_yclk; + if (ctx->dc->debug.bandwidth_calcs_trace) { + print_bw_calcs_dceip(ctx->logger, dceip); + print_bw_calcs_vbios(ctx->logger, vbios); + print_bw_calcs_data(ctx->logger, data); + } calculate_bandwidth(dceip, vbios, data); yclk_lvl = data->y_clk_level; @@ -2968,7 +3113,33 @@ bool bw_calcs(struct dc_context *ctx, bw_fixed_to_int(bw_mul(data-> stutter_exit_watermark[9], bw_int_to_fixed(1000))); - + calcs_output->stutter_entry_wm_ns[0].a_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[4], bw_int_to_fixed(1000))); + calcs_output->stutter_entry_wm_ns[1].a_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[5], bw_int_to_fixed(1000))); + calcs_output->stutter_entry_wm_ns[2].a_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[6], bw_int_to_fixed(1000))); + if (ctx->dc->caps.max_slave_planes) { + calcs_output->stutter_entry_wm_ns[3].a_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[0], bw_int_to_fixed(1000))); + calcs_output->stutter_entry_wm_ns[4].a_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[1], bw_int_to_fixed(1000))); + } else { + calcs_output->stutter_entry_wm_ns[3].a_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[7], bw_int_to_fixed(1000))); + calcs_output->stutter_entry_wm_ns[4].a_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[8], bw_int_to_fixed(1000))); + } + calcs_output->stutter_entry_wm_ns[5].a_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[9], bw_int_to_fixed(1000))); calcs_output->urgent_wm_ns[0].a_mark = bw_fixed_to_int(bw_mul(data-> @@ -3063,7 +3234,33 @@ bool bw_calcs(struct dc_context *ctx, bw_fixed_to_int(bw_mul(data-> stutter_exit_watermark[9], bw_int_to_fixed(1000))); - + calcs_output->stutter_entry_wm_ns[0].b_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[4], bw_int_to_fixed(1000))); + calcs_output->stutter_entry_wm_ns[1].b_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[5], bw_int_to_fixed(1000))); + calcs_output->stutter_entry_wm_ns[2].b_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[6], bw_int_to_fixed(1000))); + if (ctx->dc->caps.max_slave_planes) { + calcs_output->stutter_entry_wm_ns[3].b_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[0], bw_int_to_fixed(1000))); + calcs_output->stutter_entry_wm_ns[4].b_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[1], bw_int_to_fixed(1000))); + } else { + calcs_output->stutter_entry_wm_ns[3].b_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[7], bw_int_to_fixed(1000))); + calcs_output->stutter_entry_wm_ns[4].b_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[8], bw_int_to_fixed(1000))); + } + calcs_output->stutter_entry_wm_ns[5].b_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[9], bw_int_to_fixed(1000))); calcs_output->urgent_wm_ns[0].b_mark = bw_fixed_to_int(bw_mul(data-> @@ -3156,6 +3353,34 @@ bool bw_calcs(struct dc_context *ctx, bw_fixed_to_int(bw_mul(data-> stutter_exit_watermark[9], bw_int_to_fixed(1000))); + calcs_output->stutter_entry_wm_ns[0].c_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[4], bw_int_to_fixed(1000))); + calcs_output->stutter_entry_wm_ns[1].c_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[5], bw_int_to_fixed(1000))); + calcs_output->stutter_entry_wm_ns[2].c_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[6], bw_int_to_fixed(1000))); + if (ctx->dc->caps.max_slave_planes) { + calcs_output->stutter_entry_wm_ns[3].c_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[0], bw_int_to_fixed(1000))); + calcs_output->stutter_entry_wm_ns[4].c_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[1], bw_int_to_fixed(1000))); + } else { + calcs_output->stutter_entry_wm_ns[3].c_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[7], bw_int_to_fixed(1000))); + calcs_output->stutter_entry_wm_ns[4].c_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[8], bw_int_to_fixed(1000))); + } + calcs_output->stutter_entry_wm_ns[5].c_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[9], bw_int_to_fixed(1000))); + calcs_output->urgent_wm_ns[0].c_mark = bw_fixed_to_int(bw_mul(data-> urgent_watermark[4], bw_int_to_fixed(1000))); @@ -3260,6 +3485,33 @@ bool bw_calcs(struct dc_context *ctx, bw_fixed_to_int(bw_mul(data-> stutter_exit_watermark[9], bw_int_to_fixed(1000))); + calcs_output->stutter_entry_wm_ns[0].d_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[4], bw_int_to_fixed(1000))); + calcs_output->stutter_entry_wm_ns[1].d_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[5], bw_int_to_fixed(1000))); + calcs_output->stutter_entry_wm_ns[2].d_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[6], bw_int_to_fixed(1000))); + if (ctx->dc->caps.max_slave_planes) { + calcs_output->stutter_entry_wm_ns[3].d_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[0], bw_int_to_fixed(1000))); + calcs_output->stutter_entry_wm_ns[4].d_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[1], bw_int_to_fixed(1000))); + } else { + calcs_output->stutter_entry_wm_ns[3].d_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[7], bw_int_to_fixed(1000))); + calcs_output->stutter_entry_wm_ns[4].d_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[8], bw_int_to_fixed(1000))); + } + calcs_output->stutter_entry_wm_ns[5].d_mark = + bw_fixed_to_int(bw_mul(data-> + stutter_entry_watermark[9], bw_int_to_fixed(1000))); calcs_output->urgent_wm_ns[0].d_mark = bw_fixed_to_int(bw_mul(data-> |
