From 1a3408259bfd5a383b3c7aa7c309c9fb81e35ce0 Mon Sep 17 00:00:00 2001 From: Melissa Wen Date: Wed, 20 Jul 2022 18:32:06 -0100 Subject: [PATCH] drm/amd/display: move FPU code on dcn21 clk_mgr The -mno-gnu-attribute option in dcn21 clk mgr makefile hides a soft vs hard fp error for powerpc. After removing this flag, we can see some FPU code remains there: /gcc-11.3.0-nolibc/powerpc64-linux/bin/powerpc64-linux-ld: drivers/gpu/drm/amd/amdgpu/../display/dc/dml/display_mode_lib.o uses hard float, drivers/gpu/drm/amd/amdgpu/../display/dc/clk_mgr/dcn21/rn_clk_mgr.o uses soft float Therefore, remove the -mno-gnu-attribute flag for dcn21/powerpc and move FPU-associated code to DML folder. Signed-off-by: Melissa Wen Reviewed-by: Rodrigo Siqueira Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile | 6 - .../drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c | 234 +------------------- .../drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.h | 7 + .../gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c | 235 +++++++++++++++++++++ .../gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.h | 2 + 5 files changed, 248 insertions(+), 236 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile index a484536..66dc02c 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile @@ -107,12 +107,6 @@ AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCN201) ############################################################################### CLK_MGR_DCN21 = rn_clk_mgr.o rn_clk_mgr_vbios_smu.o -# prevent build errors regarding soft-float vs hard-float FP ABI tags -# this code is currently unused on ppc64, as it applies to Renoir APUs only -ifdef CONFIG_PPC64 -CFLAGS_$(AMDDALPATH)/dc/clk_mgr/dcn21/rn_clk_mgr.o := $(call cc-option,-mno-gnu-attribute) -endif - AMD_DAL_CLK_MGR_DCN21 = $(addprefix $(AMDDALPATH)/dc/clk_mgr/dcn21/,$(CLK_MGR_DCN21)) AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCN21) 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 cf1b5f3..0202dc6 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 @@ -26,10 +26,9 @@ #include "dccg.h" #include "clk_mgr_internal.h" - #include "dcn20/dcn20_clk_mgr.h" #include "rn_clk_mgr.h" - +#include "dml/dcn20/dcn20_fpu.h" #include "dce100/dce_clk_mgr.h" #include "rn_clk_mgr_vbios_smu.h" @@ -45,7 +44,6 @@ /* Constants */ -#define LPDDR_MEM_RETRAIN_LATENCY 4.977 /* Number obtained from LPDDR4 Training Counter Requirement doc */ #define SMU_VER_55_51_0 0x373300 /* SMU Version that is able to set DISPCLK below 100MHz */ /* Macros */ @@ -613,228 +611,6 @@ static struct clk_bw_params rn_bw_params = { }; -static struct wm_table ddr4_wm_table_gs = { - .entries = { - { - .wm_inst = WM_A, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.72, - .sr_exit_time_us = 7.09, - .sr_enter_plus_exit_time_us = 8.14, - .valid = true, - }, - { - .wm_inst = WM_B, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.72, - .sr_exit_time_us = 10.12, - .sr_enter_plus_exit_time_us = 11.48, - .valid = true, - }, - { - .wm_inst = WM_C, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.72, - .sr_exit_time_us = 10.12, - .sr_enter_plus_exit_time_us = 11.48, - .valid = true, - }, - { - .wm_inst = WM_D, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.72, - .sr_exit_time_us = 10.12, - .sr_enter_plus_exit_time_us = 11.48, - .valid = true, - }, - } -}; - -static struct wm_table lpddr4_wm_table_gs = { - .entries = { - { - .wm_inst = WM_A, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.65333, - .sr_exit_time_us = 5.32, - .sr_enter_plus_exit_time_us = 6.38, - .valid = true, - }, - { - .wm_inst = WM_B, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.65333, - .sr_exit_time_us = 9.82, - .sr_enter_plus_exit_time_us = 11.196, - .valid = true, - }, - { - .wm_inst = WM_C, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.65333, - .sr_exit_time_us = 9.89, - .sr_enter_plus_exit_time_us = 11.24, - .valid = true, - }, - { - .wm_inst = WM_D, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.65333, - .sr_exit_time_us = 9.748, - .sr_enter_plus_exit_time_us = 11.102, - .valid = true, - }, - } -}; - -static struct wm_table lpddr4_wm_table_with_disabled_ppt = { - .entries = { - { - .wm_inst = WM_A, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.65333, - .sr_exit_time_us = 8.32, - .sr_enter_plus_exit_time_us = 9.38, - .valid = true, - }, - { - .wm_inst = WM_B, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.65333, - .sr_exit_time_us = 9.82, - .sr_enter_plus_exit_time_us = 11.196, - .valid = true, - }, - { - .wm_inst = WM_C, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.65333, - .sr_exit_time_us = 9.89, - .sr_enter_plus_exit_time_us = 11.24, - .valid = true, - }, - { - .wm_inst = WM_D, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.65333, - .sr_exit_time_us = 9.748, - .sr_enter_plus_exit_time_us = 11.102, - .valid = true, - }, - } -}; - -static struct wm_table ddr4_wm_table_rn = { - .entries = { - { - .wm_inst = WM_A, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.72, - .sr_exit_time_us = 11.90, - .sr_enter_plus_exit_time_us = 12.80, - .valid = true, - }, - { - .wm_inst = WM_B, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.72, - .sr_exit_time_us = 13.18, - .sr_enter_plus_exit_time_us = 14.30, - .valid = true, - }, - { - .wm_inst = WM_C, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.72, - .sr_exit_time_us = 13.18, - .sr_enter_plus_exit_time_us = 14.30, - .valid = true, - }, - { - .wm_inst = WM_D, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.72, - .sr_exit_time_us = 13.18, - .sr_enter_plus_exit_time_us = 14.30, - .valid = true, - }, - } -}; - -static struct wm_table ddr4_1R_wm_table_rn = { - .entries = { - { - .wm_inst = WM_A, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.72, - .sr_exit_time_us = 13.90, - .sr_enter_plus_exit_time_us = 14.80, - .valid = true, - }, - { - .wm_inst = WM_B, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.72, - .sr_exit_time_us = 13.90, - .sr_enter_plus_exit_time_us = 14.80, - .valid = true, - }, - { - .wm_inst = WM_C, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.72, - .sr_exit_time_us = 13.90, - .sr_enter_plus_exit_time_us = 14.80, - .valid = true, - }, - { - .wm_inst = WM_D, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.72, - .sr_exit_time_us = 13.90, - .sr_enter_plus_exit_time_us = 14.80, - .valid = true, - }, - } -}; - -static struct wm_table lpddr4_wm_table_rn = { - .entries = { - { - .wm_inst = WM_A, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.65333, - .sr_exit_time_us = 7.32, - .sr_enter_plus_exit_time_us = 8.38, - .valid = true, - }, - { - .wm_inst = WM_B, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.65333, - .sr_exit_time_us = 9.82, - .sr_enter_plus_exit_time_us = 11.196, - .valid = true, - }, - { - .wm_inst = WM_C, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.65333, - .sr_exit_time_us = 9.89, - .sr_enter_plus_exit_time_us = 11.24, - .valid = true, - }, - { - .wm_inst = WM_D, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.65333, - .sr_exit_time_us = 9.748, - .sr_enter_plus_exit_time_us = 11.102, - .valid = true, - }, - } -}; - static unsigned int find_socclk_for_voltage(struct dpm_clocks *clock_table, unsigned int voltage) { int i; @@ -914,12 +690,10 @@ static void rn_clk_mgr_helper_populate_bw_params(struct clk_bw_params *bw_params /* * WM set D will be re-purposed for memory retraining */ - bw_params->wm_table.entries[WM_D].pstate_latency_us = LPDDR_MEM_RETRAIN_LATENCY; - bw_params->wm_table.entries[WM_D].wm_inst = WM_D; - bw_params->wm_table.entries[WM_D].wm_type = WM_TYPE_RETRAINING; - bw_params->wm_table.entries[WM_D].valid = true; + DC_FP_START(); + dcn21_clk_mgr_set_bw_params_wm_table(bw_params); + DC_FP_END(); } - } void rn_clk_mgr_construct( diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.h index e4322fa..2e088c5 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.h +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.h @@ -29,6 +29,13 @@ #include "clk_mgr.h" #include "dm_pp_smu.h" +extern struct wm_table ddr4_wm_table_gs; +extern struct wm_table lpddr4_wm_table_gs; +extern struct wm_table lpddr4_wm_table_with_disabled_ppt; +extern struct wm_table ddr4_wm_table_rn; +extern struct wm_table ddr4_1R_wm_table_rn; +extern struct wm_table lpddr4_wm_table_rn; + struct rn_clk_registers { uint32_t CLK1_CLK0_CURRENT_CNT; /* DPREFCLK */ }; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c index dc60b83..eeeae52 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c @@ -42,6 +42,9 @@ #define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) #endif +/* Constant */ +#define LPDDR_MEM_RETRAIN_LATENCY 4.977 /* Number obtained from LPDDR4 Training Counter Requirement doc */ + /** * DOC: DCN2x FPU manipulation Overview * @@ -650,6 +653,228 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = { .num_states = 8 }; +struct wm_table ddr4_wm_table_gs = { + .entries = { + { + .wm_inst = WM_A, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 7.09, + .sr_enter_plus_exit_time_us = 8.14, + .valid = true, + }, + { + .wm_inst = WM_B, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 10.12, + .sr_enter_plus_exit_time_us = 11.48, + .valid = true, + }, + { + .wm_inst = WM_C, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 10.12, + .sr_enter_plus_exit_time_us = 11.48, + .valid = true, + }, + { + .wm_inst = WM_D, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 10.12, + .sr_enter_plus_exit_time_us = 11.48, + .valid = true, + }, + } +}; + +struct wm_table lpddr4_wm_table_gs = { + .entries = { + { + .wm_inst = WM_A, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.65333, + .sr_exit_time_us = 5.32, + .sr_enter_plus_exit_time_us = 6.38, + .valid = true, + }, + { + .wm_inst = WM_B, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.65333, + .sr_exit_time_us = 9.82, + .sr_enter_plus_exit_time_us = 11.196, + .valid = true, + }, + { + .wm_inst = WM_C, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.65333, + .sr_exit_time_us = 9.89, + .sr_enter_plus_exit_time_us = 11.24, + .valid = true, + }, + { + .wm_inst = WM_D, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.65333, + .sr_exit_time_us = 9.748, + .sr_enter_plus_exit_time_us = 11.102, + .valid = true, + }, + } +}; + +struct wm_table lpddr4_wm_table_with_disabled_ppt = { + .entries = { + { + .wm_inst = WM_A, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.65333, + .sr_exit_time_us = 8.32, + .sr_enter_plus_exit_time_us = 9.38, + .valid = true, + }, + { + .wm_inst = WM_B, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.65333, + .sr_exit_time_us = 9.82, + .sr_enter_plus_exit_time_us = 11.196, + .valid = true, + }, + { + .wm_inst = WM_C, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.65333, + .sr_exit_time_us = 9.89, + .sr_enter_plus_exit_time_us = 11.24, + .valid = true, + }, + { + .wm_inst = WM_D, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.65333, + .sr_exit_time_us = 9.748, + .sr_enter_plus_exit_time_us = 11.102, + .valid = true, + }, + } +}; + +struct wm_table ddr4_wm_table_rn = { + .entries = { + { + .wm_inst = WM_A, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 11.90, + .sr_enter_plus_exit_time_us = 12.80, + .valid = true, + }, + { + .wm_inst = WM_B, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 13.18, + .sr_enter_plus_exit_time_us = 14.30, + .valid = true, + }, + { + .wm_inst = WM_C, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 13.18, + .sr_enter_plus_exit_time_us = 14.30, + .valid = true, + }, + { + .wm_inst = WM_D, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 13.18, + .sr_enter_plus_exit_time_us = 14.30, + .valid = true, + }, + } +}; + +struct wm_table ddr4_1R_wm_table_rn = { + .entries = { + { + .wm_inst = WM_A, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 13.90, + .sr_enter_plus_exit_time_us = 14.80, + .valid = true, + }, + { + .wm_inst = WM_B, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 13.90, + .sr_enter_plus_exit_time_us = 14.80, + .valid = true, + }, + { + .wm_inst = WM_C, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 13.90, + .sr_enter_plus_exit_time_us = 14.80, + .valid = true, + }, + { + .wm_inst = WM_D, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 13.90, + .sr_enter_plus_exit_time_us = 14.80, + .valid = true, + }, + } +}; + +struct wm_table lpddr4_wm_table_rn = { + .entries = { + { + .wm_inst = WM_A, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.65333, + .sr_exit_time_us = 7.32, + .sr_enter_plus_exit_time_us = 8.38, + .valid = true, + }, + { + .wm_inst = WM_B, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.65333, + .sr_exit_time_us = 9.82, + .sr_enter_plus_exit_time_us = 11.196, + .valid = true, + }, + { + .wm_inst = WM_C, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.65333, + .sr_exit_time_us = 9.89, + .sr_enter_plus_exit_time_us = 11.24, + .valid = true, + }, + { + .wm_inst = WM_D, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.65333, + .sr_exit_time_us = 9.748, + .sr_enter_plus_exit_time_us = 11.102, + .valid = true, + }, + } +}; + void dcn20_populate_dml_writeback_from_context(struct dc *dc, struct resource_context *res_ctx, display_e2e_pipe_params_st *pipes) @@ -2068,3 +2293,13 @@ void dcn21_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params dml_init_instance(&dc->dml, &dcn2_1_soc, &dcn2_1_ip, DML_PROJECT_DCN21); } + +void dcn21_clk_mgr_set_bw_params_wm_table(struct clk_bw_params *bw_params) +{ + dc_assert_fp_enabled(); + + bw_params->wm_table.entries[WM_D].pstate_latency_us = LPDDR_MEM_RETRAIN_LATENCY; + bw_params->wm_table.entries[WM_D].wm_inst = WM_D; + bw_params->wm_table.entries[WM_D].wm_type = WM_TYPE_RETRAINING; + bw_params->wm_table.entries[WM_D].valid = true; +} diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.h index aa89219..a6e1ad0 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.h @@ -82,4 +82,6 @@ bool dcn21_validate_bandwidth_fp(struct dc *dc, bool fast_validate); void dcn21_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params); +void dcn21_clk_mgr_set_bw_params_wm_table(struct clk_bw_params *bw_params); + #endif /* __DCN20_FPU_H__ */ -- 2.7.4