diff options
Diffstat (limited to 'drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c')
| -rw-r--r-- | drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c | 102 |
1 files changed, 91 insertions, 11 deletions
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c index f0683fd9d3f0..b26fcf86014c 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c @@ -207,24 +207,20 @@ static float calculate_net_bw_in_kbytes_sec(struct _vcs_dpi_voltage_scaling_st * return limiting_bw_kbytes_sec; } -void dcn321_insert_entry_into_table_sorted(struct _vcs_dpi_voltage_scaling_st *table, +static void dcn321_insert_entry_into_table_sorted(struct _vcs_dpi_voltage_scaling_st *table, unsigned int *num_entries, struct _vcs_dpi_voltage_scaling_st *entry) { int i = 0; int index = 0; - float net_bw_of_new_state = 0; dc_assert_fp_enabled(); - get_optimal_ntuple(entry); - if (*num_entries == 0) { table[0] = *entry; (*num_entries)++; } else { - net_bw_of_new_state = calculate_net_bw_in_kbytes_sec(entry); - while (net_bw_of_new_state > calculate_net_bw_in_kbytes_sec(&table[index])) { + while (entry->net_bw_in_kbytes_sec > table[index].net_bw_in_kbytes_sec) { index++; if (index >= *num_entries) break; @@ -252,6 +248,63 @@ static void remove_entry_from_table_at_index(struct _vcs_dpi_voltage_scaling_st memset(&table[--(*num_entries)], 0, sizeof(struct _vcs_dpi_voltage_scaling_st)); } +static void swap_table_entries(struct _vcs_dpi_voltage_scaling_st *first_entry, + struct _vcs_dpi_voltage_scaling_st *second_entry) +{ + struct _vcs_dpi_voltage_scaling_st temp_entry = *first_entry; + *first_entry = *second_entry; + *second_entry = temp_entry; +} + +/* + * sort_entries_with_same_bw - Sort entries sharing the same bandwidth by DCFCLK + */ +static void sort_entries_with_same_bw(struct _vcs_dpi_voltage_scaling_st *table, unsigned int *num_entries) +{ + unsigned int start_index = 0; + unsigned int end_index = 0; + unsigned int current_bw = 0; + + for (int i = 0; i < (*num_entries - 1); i++) { + if (table[i].net_bw_in_kbytes_sec == table[i+1].net_bw_in_kbytes_sec) { + current_bw = table[i].net_bw_in_kbytes_sec; + start_index = i; + end_index = ++i; + + while ((i < (*num_entries - 1)) && (table[i+1].net_bw_in_kbytes_sec == current_bw)) + end_index = ++i; + } + + if (start_index != end_index) { + for (int j = start_index; j < end_index; j++) { + for (int k = start_index; k < end_index; k++) { + if (table[k].dcfclk_mhz > table[k+1].dcfclk_mhz) + swap_table_entries(&table[k], &table[k+1]); + } + } + } + + start_index = 0; + end_index = 0; + + } +} + +/* + * remove_inconsistent_entries - Ensure entries with the same bandwidth have MEMCLK and FCLK monotonically increasing + * and remove entries that do not follow this order + */ +static void remove_inconsistent_entries(struct _vcs_dpi_voltage_scaling_st *table, unsigned int *num_entries) +{ + for (int i = 0; i < (*num_entries - 1); i++) { + if (table[i].net_bw_in_kbytes_sec == table[i+1].net_bw_in_kbytes_sec) { + if ((table[i].dram_speed_mts > table[i+1].dram_speed_mts) || + (table[i].fabricclk_mhz > table[i+1].fabricclk_mhz)) + remove_entry_from_table_at_index(table, num_entries, i); + } + } +} + /* * override_max_clk_values - Overwrite the max clock frequencies with the max DC mode timings * Input: @@ -362,11 +415,11 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk if (max_clk_data.fclk_mhz == 0) max_clk_data.fclk_mhz = max_clk_data.dcfclk_mhz * - dcn3_2_soc.pct_ideal_sdp_bw_after_urgent / - dcn3_2_soc.pct_ideal_fabric_bw_after_urgent; + dcn3_21_soc.pct_ideal_sdp_bw_after_urgent / + dcn3_21_soc.pct_ideal_fabric_bw_after_urgent; if (max_clk_data.phyclk_mhz == 0) - max_clk_data.phyclk_mhz = dcn3_2_soc.clock_limits[0].phyclk_mhz; + max_clk_data.phyclk_mhz = dcn3_21_soc.clock_limits[0].phyclk_mhz; *num_entries = 0; entry.dispclk_mhz = max_clk_data.dispclk_mhz; @@ -374,8 +427,8 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk entry.dppclk_mhz = max_clk_data.dppclk_mhz; entry.dtbclk_mhz = max_clk_data.dtbclk_mhz; entry.phyclk_mhz = max_clk_data.phyclk_mhz; - entry.phyclk_d18_mhz = dcn3_2_soc.clock_limits[0].phyclk_d18_mhz; - entry.phyclk_d32_mhz = dcn3_2_soc.clock_limits[0].phyclk_d32_mhz; + entry.phyclk_d18_mhz = dcn3_21_soc.clock_limits[0].phyclk_d18_mhz; + entry.phyclk_d32_mhz = dcn3_21_soc.clock_limits[0].phyclk_d32_mhz; // Insert all the DCFCLK STAs for (i = 0; i < num_dcfclk_stas; i++) { @@ -383,6 +436,8 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk entry.fabricclk_mhz = 0; entry.dram_speed_mts = 0; + get_optimal_ntuple(&entry); + entry.net_bw_in_kbytes_sec = calculate_net_bw_in_kbytes_sec(&entry); dcn321_insert_entry_into_table_sorted(table, num_entries, &entry); } @@ -391,6 +446,8 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk entry.fabricclk_mhz = 0; entry.dram_speed_mts = 0; + get_optimal_ntuple(&entry); + entry.net_bw_in_kbytes_sec = calculate_net_bw_in_kbytes_sec(&entry); dcn321_insert_entry_into_table_sorted(table, num_entries, &entry); // Insert the UCLK DPMS @@ -399,6 +456,8 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk entry.fabricclk_mhz = 0; entry.dram_speed_mts = bw_params->clk_table.entries[i].memclk_mhz * 16; + get_optimal_ntuple(&entry); + entry.net_bw_in_kbytes_sec = calculate_net_bw_in_kbytes_sec(&entry); dcn321_insert_entry_into_table_sorted(table, num_entries, &entry); } @@ -409,6 +468,8 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk entry.fabricclk_mhz = bw_params->clk_table.entries[i].fclk_mhz; entry.dram_speed_mts = 0; + get_optimal_ntuple(&entry); + entry.net_bw_in_kbytes_sec = calculate_net_bw_in_kbytes_sec(&entry); dcn321_insert_entry_into_table_sorted(table, num_entries, &entry); } } @@ -418,6 +479,8 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk entry.fabricclk_mhz = max_clk_data.fclk_mhz; entry.dram_speed_mts = 0; + get_optimal_ntuple(&entry); + entry.net_bw_in_kbytes_sec = calculate_net_bw_in_kbytes_sec(&entry); dcn321_insert_entry_into_table_sorted(table, num_entries, &entry); } @@ -433,6 +496,23 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk remove_entry_from_table_at_index(table, num_entries, i); } + // Insert entry with all max dc limits without bandwitch matching + if (!disable_dc_mode_overwrite) { + struct _vcs_dpi_voltage_scaling_st max_dc_limits_entry = entry; + + max_dc_limits_entry.dcfclk_mhz = max_clk_data.dcfclk_mhz; + max_dc_limits_entry.fabricclk_mhz = max_clk_data.fclk_mhz; + max_dc_limits_entry.dram_speed_mts = max_clk_data.memclk_mhz * 16; + + max_dc_limits_entry.net_bw_in_kbytes_sec = calculate_net_bw_in_kbytes_sec(&max_dc_limits_entry); + dcn321_insert_entry_into_table_sorted(table, num_entries, &max_dc_limits_entry); + + sort_entries_with_same_bw(table, num_entries); + remove_inconsistent_entries(table, num_entries); + } + + + // At this point, the table only contains supported points of interest // it could be used as is, but some states may be redundant due to // coarse grained nature of some clocks, so we want to round up to |