diff options
Diffstat (limited to 'drivers/gpu/drm/amd/display/dc/calcs')
| -rw-r--r-- | drivers/gpu/drm/amd/display/dc/calcs/Makefile | 36 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c | 59 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/display/dc/calcs/dcn_calc_math.h | 43 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c | 79 |
4 files changed, 121 insertions, 96 deletions
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/Makefile b/drivers/gpu/drm/amd/display/dc/calcs/Makefile index 95f332ee3e7e..4674aca8f206 100644 --- a/drivers/gpu/drm/amd/display/dc/calcs/Makefile +++ b/drivers/gpu/drm/amd/display/dc/calcs/Makefile @@ -1,5 +1,6 @@ # # Copyright 2017 Advanced Micro Devices, Inc. +# Copyright 2019 Raptor Engineering, LLC # # Permission is hereby granted, free of charge, to any person obtaining a # copy of this software and associated documentation files (the "Software"), @@ -24,21 +25,38 @@ # It calculates Bandwidth and Watermarks values for HW programming # -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 +ifdef CONFIG_X86 +calcs_ccflags := -mhard-float -msse endif -calcs_ccflags := -mhard-float -msse $(cc_stack_align) +ifdef CONFIG_PPC64 +calcs_ccflags := -mhard-float -maltivec +endif + +ifdef CONFIG_CC_IS_GCC +ifeq ($(call cc-ifversion, -lt, 0701, y), y) +IS_OLD_GCC = 1 +endif +endif + +ifdef CONFIG_X86 +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). +calcs_ccflags += -mpreferred-stack-boundary=4 +else +calcs_ccflags += -msse2 +endif +endif -CFLAGS_dcn_calcs.o := $(calcs_ccflags) -CFLAGS_dcn_calc_auto.o := $(calcs_ccflags) -CFLAGS_dcn_calc_math.o := $(calcs_ccflags) -Wno-tautological-compare +CFLAGS_$(AMDDALPATH)/dc/calcs/dcn_calcs.o := $(calcs_ccflags) +CFLAGS_$(AMDDALPATH)/dc/calcs/dcn_calc_auto.o := $(calcs_ccflags) +CFLAGS_$(AMDDALPATH)/dc/calcs/dcn_calc_math.o := $(calcs_ccflags) -Wno-tautological-compare BW_CALCS = dce_calcs.o bw_fixed.o custom_float.o -ifdef CONFIG_DRM_AMD_DC_DCN1_0 +ifdef CONFIG_DRM_AMD_DC_DCN BW_CALCS += dcn_calcs.o dcn_calc_math.o dcn_calc_auto.o endif 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 7108d51a9c5b..5d081c42e81b 100644 --- a/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c +++ b/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c @@ -25,6 +25,7 @@ #include <linux/slab.h> +#include "resource.h" #include "dm_services.h" #include "dce_calcs.h" #include "dc.h" @@ -153,14 +154,14 @@ static void calculate_bandwidth( - if (data->d0_underlay_mode == bw_def_none) { d0_underlay_enable = 0; } - else { - d0_underlay_enable = 1; - } - if (data->d1_underlay_mode == bw_def_none) { d1_underlay_enable = 0; } - else { - d1_underlay_enable = 1; - } + if (data->d0_underlay_mode == bw_def_none) + d0_underlay_enable = false; + else + d0_underlay_enable = true; + if (data->d1_underlay_mode == bw_def_none) + d1_underlay_enable = false; + else + d1_underlay_enable = true; data->number_of_underlay_surfaces = d0_underlay_enable + d1_underlay_enable; switch (data->underlay_surface_type) { case bw_def_420: @@ -285,8 +286,8 @@ static void calculate_bandwidth( data->cursor_width_pixels[2] = bw_int_to_fixed(0); data->cursor_width_pixels[3] = bw_int_to_fixed(0); /* graphics surface parameters from spreadsheet*/ - fbc_enabled = 0; - lpt_enabled = 0; + fbc_enabled = false; + lpt_enabled = false; for (i = 4; i <= maximum_number_of_surfaces - 3; i++) { if (i < data->number_of_displays + 4) { if (i == 4 && data->d0_underlay_mode == bw_def_underlay_only) { @@ -337,9 +338,9 @@ static void calculate_bandwidth( data->access_one_channel_only[i] = 0; } if (data->fbc_en[i] == 1) { - fbc_enabled = 1; + fbc_enabled = true; if (data->lpt_en[i] == 1) { - lpt_enabled = 1; + lpt_enabled = true; } } data->cursor_width_pixels[i] = bw_int_to_fixed(vbios->cursor_width); @@ -2852,7 +2853,7 @@ static void populate_initial_data( data->src_height[num_displays * 2 + j] = bw_int_to_fixed(pipe[i].bottom_pipe->plane_res.scl_data.viewport.height); data->src_width[num_displays * 2 + j] = bw_int_to_fixed(pipe[i].bottom_pipe->plane_res.scl_data.viewport.width); data->pitch_in_pixels[num_displays * 2 + j] = bw_int_to_fixed( - pipe[i].bottom_pipe->plane_state->plane_size.grph.surface_pitch); + pipe[i].bottom_pipe->plane_state->plane_size.surface_pitch); data->h_taps[num_displays * 2 + j] = bw_int_to_fixed(pipe[i].bottom_pipe->plane_res.scl_data.taps.h_taps); data->v_taps[num_displays * 2 + j] = bw_int_to_fixed(pipe[i].bottom_pipe->plane_res.scl_data.taps.v_taps); data->h_scale_ratio[num_displays * 2 + j] = fixed31_32_to_bw_fixed( @@ -2977,6 +2978,32 @@ static void populate_initial_data( data->number_of_displays = num_displays; } +static bool all_displays_in_sync(const struct pipe_ctx pipe[], + int pipe_count) +{ + const struct pipe_ctx *active_pipes[MAX_PIPES]; + int i, num_active_pipes = 0; + + for (i = 0; i < pipe_count; i++) { + if (!pipe[i].stream || pipe[i].top_pipe) + continue; + + active_pipes[num_active_pipes++] = &pipe[i]; + } + + if (!num_active_pipes) + return false; + + for (i = 1; i < num_active_pipes; ++i) { + if (!resource_are_streams_timing_synchronizable( + active_pipes[0]->stream, active_pipes[i]->stream)) { + return false; + } + } + + return true; +} + /** * Return: * true - Display(s) configuration supported. @@ -2998,8 +3025,10 @@ bool bw_calcs(struct dc_context *ctx, populate_initial_data(pipe, pipe_count, data); - /*TODO: this should be taken out calcs output and assigned during timing sync for pplib use*/ - calcs_output->all_displays_in_sync = false; + if (ctx->dc->config.multi_mon_pp_mclk_switch) + calcs_output->all_displays_in_sync = all_displays_in_sync(pipe, pipe_count); + else + calcs_output->all_displays_in_sync = false; if (data->number_of_displays != 0) { uint8_t yclk_lvl, sclk_lvl; diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calc_math.h b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calc_math.h deleted file mode 100644 index 45a07eeffbb6..000000000000 --- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calc_math.h +++ /dev/null @@ -1,43 +0,0 @@ -/* - * Copyright 2017 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - * - * Authors: AMD - * - */ - -#ifndef _DCN_CALC_MATH_H_ -#define _DCN_CALC_MATH_H_ - -float dcn_bw_mod(const float arg1, const float arg2); -float dcn_bw_min2(const float arg1, const float arg2); -unsigned int dcn_bw_max(const unsigned int arg1, const unsigned int arg2); -float dcn_bw_max2(const float arg1, const float arg2); -float dcn_bw_floor2(const float arg, const float significance); -float dcn_bw_floor(const float arg); -float dcn_bw_ceil2(const float arg, const float significance); -float dcn_bw_ceil(const float arg); -float dcn_bw_max3(float v1, float v2, float v3); -float dcn_bw_max5(float v1, float v2, float v3, float v4, float v5); -float dcn_bw_pow(float a, float exp); -float dcn_bw_log(float a, float b); -double dcn_bw_fabs(double a); - -#endif /* _DCN_CALC_MATH_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c index 38365dd911a3..1a37550731de 100644 --- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c +++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c @@ -1,5 +1,6 @@ /* * Copyright 2017 Advanced Micro Devices, Inc. + * Copyright 2019 Raptor Engineering, LLC * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), @@ -53,13 +54,9 @@ * remain as-is as it provides us with a guarantee from HW that it is correct. */ -#ifdef CONFIG_DRM_AMD_DC_DCN2_0 /* Defaults from spreadsheet rev#247. * RV2 delta: dram_clock_change_latency, max_num_dpp */ -#else -/* Defaults from spreadsheet rev#247 */ -#endif const struct dcn_soc_bounding_box dcn10_soc_defaults = { /* latencies */ .sr_exit_time = 17, /*us*/ @@ -329,7 +326,7 @@ static void pipe_ctx_to_e2e_pipe_params ( dcc_support_pixel_format(pipe->plane_state->format, &bpe) ? 1 : 0; } input->src.dcc_rate = 1; - input->src.meta_pitch = pipe->plane_state->dcc.grph.meta_pitch; + input->src.meta_pitch = pipe->plane_state->dcc.meta_pitch; input->src.source_scan = dm_horz; input->src.sw_mode = pipe->plane_state->tiling_info.gfx9.swizzle; @@ -626,7 +623,7 @@ static bool dcn_bw_apply_registry_override(struct dc *dc) { bool updated = false; - kernel_fpu_begin(); + DC_FP_START(); if ((int)(dc->dcn_soc->sr_exit_time * 1000) != dc->debug.sr_exit_time_ns && dc->debug.sr_exit_time_ns) { updated = true; @@ -662,7 +659,7 @@ static bool dcn_bw_apply_registry_override(struct dc *dc) dc->dcn_soc->dram_clock_change_latency = dc->debug.dram_clock_change_latency_ns / 1000.0; } - kernel_fpu_end(); + DC_FP_END(); return updated; } @@ -705,6 +702,17 @@ static void hack_bounding_box(struct dcn_bw_internal_vars *v, hack_force_pipe_split(v, context->streams[0]->timing.pix_clk_100hz); } + +unsigned int get_highest_allowed_voltage_level(uint32_t hw_internal_rev) +{ + /* for dali & pollock, the highest voltage level we want is 0 */ + if (ASICREV_IS_POLLOCK(hw_internal_rev) || ASICREV_IS_DALI(hw_internal_rev)) + return 0; + + /* we are ok with all levels */ + return 4; +} + bool dcn_validate_bandwidth( struct dc *dc, struct dc_state *context, @@ -731,7 +739,8 @@ bool dcn_validate_bandwidth( dcn_bw_sync_calcs_and_dml(dc); memset(v, 0, sizeof(*v)); - kernel_fpu_begin(); + DC_FP_START(); + v->sr_exit_time = dc->dcn_soc->sr_exit_time; v->sr_enter_plus_exit_time = dc->dcn_soc->sr_enter_plus_exit_time; v->urgent_latency = dc->dcn_soc->urgent_latency; @@ -1263,12 +1272,12 @@ bool dcn_validate_bandwidth( bw_limit = dc->dcn_soc->percent_disp_bw_limit * v->fabric_and_dram_bandwidth_vmax0p9; bw_limit_pass = (v->total_data_read_bandwidth / 1000.0) < bw_limit; - kernel_fpu_end(); + DC_FP_END(); PERFORMANCE_TRACE_END(); BW_VAL_TRACE_FINISH(); - if (bw_limit_pass && v->voltage_level != 5) + if (bw_limit_pass && v->voltage_level <= get_highest_allowed_voltage_level(dc->ctx->asic_id.hw_internal_rev)) return true; else return false; @@ -1426,37 +1435,49 @@ void dcn_bw_update_from_pplib(struct dc *dc) struct dc_context *ctx = dc->ctx; struct dm_pp_clock_levels_with_voltage fclks = {0}, dcfclks = {0}; bool res; + unsigned vmin0p65_idx, vmid0p72_idx, vnom0p8_idx, vmax0p9_idx; /* TODO: This is not the proper way to obtain fabric_and_dram_bandwidth, should be min(fclk, memclk) */ res = dm_pp_get_clock_levels_by_type_with_voltage( ctx, DM_PP_CLOCK_TYPE_FCLK, &fclks); - kernel_fpu_begin(); + DC_FP_START(); if (res) res = verify_clock_values(&fclks); if (res) { - ASSERT(fclks.num_levels >= 3); - dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 = 32 * (fclks.data[0].clocks_in_khz / 1000.0) / 1000.0; - dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72 = dc->dcn_soc->number_of_channels * - (fclks.data[fclks.num_levels - (fclks.num_levels > 2 ? 3 : 2)].clocks_in_khz / 1000.0) - * ddr4_dram_factor_single_Channel / 1000.0; - dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8 = dc->dcn_soc->number_of_channels * - (fclks.data[fclks.num_levels - 2].clocks_in_khz / 1000.0) - * ddr4_dram_factor_single_Channel / 1000.0; - dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = dc->dcn_soc->number_of_channels * - (fclks.data[fclks.num_levels - 1].clocks_in_khz / 1000.0) - * ddr4_dram_factor_single_Channel / 1000.0; + ASSERT(fclks.num_levels); + + vmin0p65_idx = 0; + vmid0p72_idx = fclks.num_levels - + (fclks.num_levels > 2 ? 3 : (fclks.num_levels > 1 ? 2 : 1)); + vnom0p8_idx = fclks.num_levels - (fclks.num_levels > 1 ? 2 : 1); + vmax0p9_idx = fclks.num_levels - 1; + + dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 = + 32 * (fclks.data[vmin0p65_idx].clocks_in_khz / 1000.0) / 1000.0; + dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72 = + dc->dcn_soc->number_of_channels * + (fclks.data[vmid0p72_idx].clocks_in_khz / 1000.0) + * ddr4_dram_factor_single_Channel / 1000.0; + dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8 = + dc->dcn_soc->number_of_channels * + (fclks.data[vnom0p8_idx].clocks_in_khz / 1000.0) + * ddr4_dram_factor_single_Channel / 1000.0; + dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = + dc->dcn_soc->number_of_channels * + (fclks.data[vmax0p9_idx].clocks_in_khz / 1000.0) + * ddr4_dram_factor_single_Channel / 1000.0; } else BREAK_TO_DEBUGGER(); - kernel_fpu_end(); + DC_FP_END(); res = dm_pp_get_clock_levels_by_type_with_voltage( ctx, DM_PP_CLOCK_TYPE_DCFCLK, &dcfclks); - kernel_fpu_begin(); + DC_FP_START(); if (res) res = verify_clock_values(&dcfclks); @@ -1469,7 +1490,7 @@ void dcn_bw_update_from_pplib(struct dc *dc) } else BREAK_TO_DEBUGGER(); - kernel_fpu_end(); + DC_FP_END(); } void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc) @@ -1484,11 +1505,11 @@ void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc) if (!pp || !pp->set_wm_ranges) return; - kernel_fpu_begin(); + DC_FP_START(); min_fclk_khz = dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 * 1000000 / 32; min_dcfclk_khz = dc->dcn_soc->dcfclkv_min0p65 * 1000; socclk_khz = dc->dcn_soc->socclk * 1000; - kernel_fpu_end(); + DC_FP_END(); /* Now notify PPLib/SMU about which Watermarks sets they should select * depending on DPM state they are in. And update BW MGR GFX Engine and @@ -1539,7 +1560,7 @@ void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc) void dcn_bw_sync_calcs_and_dml(struct dc *dc) { - kernel_fpu_begin(); + DC_FP_START(); DC_LOG_BANDWIDTH_CALCS("sr_exit_time: %f ns\n" "sr_enter_plus_exit_time: %f ns\n" "urgent_latency: %f ns\n" @@ -1728,5 +1749,5 @@ void dcn_bw_sync_calcs_and_dml(struct dc *dc) dc->dml.ip.bug_forcing_LC_req_same_size_fixed = dc->dcn_ip->bug_forcing_luma_and_chroma_request_to_same_size_fixed == dcn_bw_yes; dc->dml.ip.dcfclk_cstate_latency = dc->dcn_ip->dcfclk_cstate_latency; - kernel_fpu_end(); + DC_FP_END(); } |
