diff options
Diffstat (limited to 'drivers/gpu')
37 files changed, 460 insertions, 146 deletions
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index e392a90ca687..85b79a7fee63 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -228,6 +228,7 @@ source "drivers/gpu/drm/arm/Kconfig" config DRM_RADEON tristate "ATI Radeon" depends on DRM && PCI && MMU + depends on AGP || !AGP select FW_LOADER select DRM_KMS_HELPER select DRM_TTM diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index b6879d97c9c9..49267eb64302 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -180,6 +180,7 @@ extern uint amdgpu_smu_memory_pool_size; extern uint amdgpu_dc_feature_mask; extern uint amdgpu_dc_debug_mask; extern uint amdgpu_dm_abm_level; +extern int amdgpu_backlight; extern struct amdgpu_mgpu_info mgpu_info; extern int amdgpu_ras_enable; extern uint amdgpu_ras_mask; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index 36a741d63ddc..2e9b16fb3fcd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -903,7 +903,7 @@ void amdgpu_acpi_fini(struct amdgpu_device *adev) */ bool amdgpu_acpi_is_s0ix_supported(struct amdgpu_device *adev) { -#if defined(CONFIG_AMD_PMC) +#if defined(CONFIG_AMD_PMC) || defined(CONFIG_AMD_PMC_MODULE) if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0) { if (adev->flags & AMD_IS_APU) return true; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 4575192d9b08..b26e2fd1c538 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -781,6 +781,10 @@ uint amdgpu_dm_abm_level; MODULE_PARM_DESC(abmlevel, "ABM level (0 = off (default), 1-4 = backlight reduction level) "); module_param_named(abmlevel, amdgpu_dm_abm_level, uint, 0444); +int amdgpu_backlight = -1; +MODULE_PARM_DESC(backlight, "Backlight control (0 = pwm, 1 = aux, -1 auto (default))"); +module_param_named(backlight, amdgpu_backlight, bint, 0444); + /** * DOC: tmz (int) * Trusted Memory Zone (TMZ) is a method to protect data being written diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c index 51cd49c6f38f..24010cacf7d0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c @@ -146,7 +146,7 @@ static int amdgpufb_create_pinned_object(struct amdgpu_fbdev *rfbdev, size = mode_cmd->pitches[0] * height; aligned_size = ALIGN(size, PAGE_SIZE); ret = amdgpu_gem_object_create(adev, aligned_size, 0, domain, flags, - ttm_bo_type_kernel, NULL, &gobj); + ttm_bo_type_device, NULL, &gobj); if (ret) { pr_err("failed to allocate framebuffer (%d)\n", aligned_size); return -ENOMEM; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 3e1fd1e7d09f..573cf17262da 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2267,6 +2267,11 @@ static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector) caps->ext_caps->bits.hdr_aux_backlight_control == 1) caps->aux_support = true; + if (amdgpu_backlight == 0) + caps->aux_support = false; + else if (amdgpu_backlight == 1) + caps->aux_support = true; + /* From the specification (CTA-861-G), for calculating the maximum * luminance we need to use: * Luminance = 50*2**(CV/32) @@ -3185,19 +3190,6 @@ static void amdgpu_dm_update_backlight_caps(struct amdgpu_display_manager *dm) #endif } -static int set_backlight_via_aux(struct dc_link *link, uint32_t brightness) -{ - bool rc; - - if (!link) - return 1; - - rc = dc_link_set_backlight_level_nits(link, true, brightness, - AUX_BL_DEFAULT_TRANSITION_TIME_MS); - - return rc ? 0 : 1; -} - static int get_brightness_range(const struct amdgpu_dm_backlight_caps *caps, unsigned *min, unsigned *max) { @@ -3260,9 +3252,10 @@ static int amdgpu_dm_backlight_update_status(struct backlight_device *bd) brightness = convert_brightness_from_user(&caps, bd->props.brightness); // Change brightness based on AUX property if (caps.aux_support) - return set_backlight_via_aux(link, brightness); - - rc = dc_link_set_backlight_level(dm->backlight_link, brightness, 0); + rc = dc_link_set_backlight_level_nits(link, true, brightness, + AUX_BL_DEFAULT_TRANSITION_TIME_MS); + else + rc = dc_link_set_backlight_level(dm->backlight_link, brightness, 0); return rc ? 0 : 1; } @@ -3270,11 +3263,27 @@ static int amdgpu_dm_backlight_update_status(struct backlight_device *bd) static int amdgpu_dm_backlight_get_brightness(struct backlight_device *bd) { struct amdgpu_display_manager *dm = bl_get_data(bd); - int ret = dc_link_get_backlight_level(dm->backlight_link); + struct amdgpu_dm_backlight_caps caps; + + amdgpu_dm_update_backlight_caps(dm); + caps = dm->backlight_caps; + + if (caps.aux_support) { + struct dc_link *link = (struct dc_link *)dm->backlight_link; + u32 avg, peak; + bool rc; - if (ret == DC_ERROR_UNEXPECTED) - return bd->props.brightness; - return convert_brightness_to_user(&dm->backlight_caps, ret); + rc = dc_link_get_backlight_level_nits(link, &avg, &peak); + if (!rc) + return bd->props.brightness; + return convert_brightness_to_user(&caps, avg); + } else { + int ret = dc_link_get_backlight_level(dm->backlight_link); + + if (ret == DC_ERROR_UNEXPECTED) + return bd->props.brightness; + return convert_brightness_to_user(&caps, ret); + } } static const struct backlight_ops amdgpu_dm_backlight_ops = { @@ -4716,6 +4725,7 @@ static int fill_dc_plane_attributes(struct amdgpu_device *adev, dc_plane_state->global_alpha_value = plane_info.global_alpha_value; dc_plane_state->dcc = plane_info.dcc; dc_plane_state->layer_index = plane_info.layer_index; // Always returns 0 + dc_plane_state->flip_int_enabled = true; /* * Always set input transfer function, since plane state is refreshed diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index fa5059f71727..bd0101013ec8 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -2602,7 +2602,6 @@ bool dc_link_set_backlight_level(const struct dc_link *link, if (pipe_ctx->plane_state == NULL) frame_ramp = 0; } else { - ASSERT(false); return false; } diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 4eee3a55fa30..18ed0d3f247e 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -887,6 +887,7 @@ struct dc_plane_state { int layer_index; union surface_update_flags update_flags; + bool flip_int_enabled; /* private to DC core */ struct dc_plane_status status; struct dc_context *ctx; diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c index 9e796dfeac20..714c71a5fbde 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c @@ -1257,6 +1257,16 @@ void hubp1_soft_reset(struct hubp *hubp, bool reset) REG_UPDATE(DCHUBP_CNTL, HUBP_DISABLE, reset ? 1 : 0); } +void hubp1_set_flip_int(struct hubp *hubp) +{ + struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp); + + REG_UPDATE(DCSURF_SURFACE_FLIP_INTERRUPT, + SURFACE_FLIP_INT_MASK, 1); + + return; +} + void hubp1_init(struct hubp *hubp) { //do nothing @@ -1290,6 +1300,7 @@ static const struct hubp_funcs dcn10_hubp_funcs = { .dmdata_load = NULL, .hubp_soft_reset = hubp1_soft_reset, .hubp_in_blank = hubp1_in_blank, + .hubp_set_flip_int = hubp1_set_flip_int, }; /*****************************************/ diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h index a9a6ed7f4f99..e2f2f6995935 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h @@ -74,6 +74,7 @@ SRI(DCSURF_SURFACE_EARLIEST_INUSE_C, HUBPREQ, id),\ SRI(DCSURF_SURFACE_EARLIEST_INUSE_HIGH_C, HUBPREQ, id),\ SRI(DCSURF_SURFACE_CONTROL, HUBPREQ, id),\ + SRI(DCSURF_SURFACE_FLIP_INTERRUPT, HUBPREQ, id),\ SRI(HUBPRET_CONTROL, HUBPRET, id),\ SRI(DCN_EXPANSION_MODE, HUBPREQ, id),\ SRI(DCHUBP_REQ_SIZE_CONFIG, HUBP, id),\ @@ -183,6 +184,7 @@ uint32_t DCSURF_SURFACE_EARLIEST_INUSE_C; \ uint32_t DCSURF_SURFACE_EARLIEST_INUSE_HIGH_C; \ uint32_t DCSURF_SURFACE_CONTROL; \ + uint32_t DCSURF_SURFACE_FLIP_INTERRUPT; \ uint32_t HUBPRET_CONTROL; \ uint32_t DCN_EXPANSION_MODE; \ uint32_t DCHUBP_REQ_SIZE_CONFIG; \ @@ -332,6 +334,7 @@ HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_META_SURFACE_TMZ_C, mask_sh),\ HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_EN, mask_sh),\ HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_IND_64B_BLK, mask_sh),\ + HUBP_SF(HUBPREQ0_DCSURF_SURFACE_FLIP_INTERRUPT, SURFACE_FLIP_INT_MASK, mask_sh),\ HUBP_SF(HUBPRET0_HUBPRET_CONTROL, DET_BUF_PLANE1_BASE_ADDRESS, mask_sh),\ HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CB_B, mask_sh),\ HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CR_R, mask_sh),\ @@ -531,6 +534,7 @@ type PRIMARY_SURFACE_DCC_IND_64B_BLK;\ type SECONDARY_SURFACE_DCC_EN;\ type SECONDARY_SURFACE_DCC_IND_64B_BLK;\ + type SURFACE_FLIP_INT_MASK;\ type DET_BUF_PLANE1_BASE_ADDRESS;\ type CROSSBAR_SRC_CB_B;\ type CROSSBAR_SRC_CR_R;\ @@ -777,4 +781,6 @@ void hubp1_read_state_common(struct hubp *hubp); bool hubp1_in_blank(struct hubp *hubp); void hubp1_soft_reset(struct hubp *hubp, bool reset); +void hubp1_set_flip_int(struct hubp *hubp); + #endif diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 89912bb5014f..9ba5c624770d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -2196,6 +2196,13 @@ static void dcn10_enable_plane( if (dc->debug.sanity_checks) { hws->funcs.verify_allow_pstate_change_high(dc); } + + if (!pipe_ctx->top_pipe + && pipe_ctx->plane_state + && pipe_ctx->plane_state->flip_int_enabled + && pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_int) + pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_int(pipe_ctx->plane_res.hubp); + } void dcn10_program_gamut_remap(struct pipe_ctx *pipe_ctx) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c index 0df0da2e6a4d..bec7059f6d5d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c @@ -1597,6 +1597,7 @@ static struct hubp_funcs dcn20_hubp_funcs = { .validate_dml_output = hubp2_validate_dml_output, .hubp_in_blank = hubp1_in_blank, .hubp_soft_reset = hubp1_soft_reset, + .hubp_set_flip_int = hubp1_set_flip_int, }; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 0726fb435e2a..aece1103331d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1146,6 +1146,12 @@ void dcn20_enable_plane( pipe_ctx->plane_res.hubp->funcs->hubp_set_vm_system_aperture_settings(pipe_ctx->plane_res.hubp, &apt); } + if (!pipe_ctx->top_pipe + && pipe_ctx->plane_state + && pipe_ctx->plane_state->flip_int_enabled + && pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_int) + pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_int(pipe_ctx->plane_res.hubp); + // if (dc->debug.sanity_checks) { // dcn10_verify_allow_pstate_change_high(dc); // } @@ -1501,38 +1507,8 @@ static void dcn20_update_dchubp_dpp( if (pipe_ctx->update_flags.bits.enable || pipe_ctx->update_flags.bits.opp_changed || pipe_ctx->stream->update_flags.bits.gamut_remap || pipe_ctx->stream->update_flags.bits.out_csc) { - struct mpc *mpc = pipe_ctx->stream_res.opp->ctx->dc->res_pool->mpc; - - if (mpc->funcs->set_gamut_remap) { - int i; - int mpcc_id = hubp->inst; - struct mpc_grph_gamut_adjustment adjust; - bool enable_remap_dpp = false; - - memset(&adjust, 0, sizeof(adjust)); - adjust.gamut_adjust_type = GRAPHICS_GAMUT_ADJUST_TYPE_BYPASS; - - /* save the enablement of gamut remap for dpp */ - enable_remap_dpp = pipe_ctx->stream->gamut_remap_matrix.enable_remap; - - /* force bypass gamut remap for dpp/cm */ - pipe_ctx->stream->gamut_remap_matrix.enable_remap = false; - dc->hwss.program_gamut_remap(pipe_ctx); - - /* restore gamut remap flag and use this remap into mpc */ - pipe_ctx->stream->gamut_remap_matrix.enable_remap = enable_remap_dpp; - - /* build remap matrix for top plane if enabled */ - if (enable_remap_dpp && pipe_ctx->top_pipe == NULL) { - adjust.gamut_adjust_type = GRAPHICS_GAMUT_ADJUST_TYPE_SW; - for (i = 0; i < CSC_TEMPERATURE_MATRIX_SIZE; i++) - adjust.temperature_matrix[i] = - pipe_ctx->stream->gamut_remap_matrix.matrix[i]; - } - mpc->funcs->set_gamut_remap(mpc, mpcc_id, &adjust); - } else - /* dpp/cm gamut remap*/ - dc->hwss.program_gamut_remap(pipe_ctx); + /* dpp/cm gamut remap*/ + dc->hwss.program_gamut_remap(pipe_ctx); /*call the dcn2 method which uses mpc csc*/ dc->hwss.program_output_csc(dc, diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c index f9045852728f..b0c9180b808f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c @@ -838,6 +838,7 @@ static struct hubp_funcs dcn21_hubp_funcs = { .hubp_set_flip_control_surface_gsl = hubp2_set_flip_control_surface_gsl, .hubp_init = hubp21_init, .validate_dml_output = hubp21_validate_dml_output, + .hubp_set_flip_int = hubp1_set_flip_int, }; bool hubp21_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index 072f8c880924..4a3df13c9e49 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -296,7 +296,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = { .num_banks = 8, .num_chans = 4, .vmm_page_size_bytes = 4096, - .dram_clock_change_latency_us = 11.72, + .dram_clock_change_latency_us = 23.84, .return_bus_width_bytes = 64, .dispclk_dppclk_vco_speed_mhz = 3600, .xfc_bus_transport_time_us = 4, @@ -1062,8 +1062,6 @@ static void patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_s { int i; - DC_FP_START(); - if (dc->bb_overrides.sr_exit_time_ns) { for (i = 0; i < WM_SET_COUNT; i++) { dc->clk_mgr->bw_params->wm_table.entries[i].sr_exit_time_us = @@ -1088,8 +1086,6 @@ static void patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_s dc->bb_overrides.dram_clock_change_latency_ns / 1000.0; } } - - DC_FP_END(); } void dcn21_calculate_wm( @@ -1339,7 +1335,7 @@ static noinline bool dcn21_validate_bandwidth_fp(struct dc *dc, int vlevel = 0; int pipe_split_from[MAX_PIPES]; int pipe_cnt = 0; - display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_KERNEL); + display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_ATOMIC); DC_LOGGER_INIT(dc->ctx->logger); BW_VAL_TRACE_COUNT(); @@ -1599,6 +1595,11 @@ static void update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param dcn2_1_soc.num_chans = bw_params->num_channels; ASSERT(clk_table->num_entries); + /* Copy dcn2_1_soc.clock_limits to clock_limits to avoid copying over null states later */ + for (i = 0; i < dcn2_1_soc.num_states + 1; i++) { + clock_limits[i] = dcn2_1_soc.clock_limits[i]; + } + for (i = 0; i < clk_table->num_entries; i++) { /* loop backwards*/ for (closest_clk_lvl = 0, j = dcn2_1_soc.num_states - 1; j >= 0; j--) { diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c index 41a1d0e9b7e2..e0df9b0065f9 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c @@ -113,6 +113,7 @@ bool cm3_helper_translate_curve_to_hw_format( struct pwl_result_data *rgb_resulted; struct pwl_result_data *rgb; struct pwl_result_data *rgb_plus_1; + struct pwl_result_data *rgb_minus_1; struct fixed31_32 end_value; int32_t region_start, region_end; @@ -140,7 +141,7 @@ bool cm3_helper_translate_curve_to_hw_format( region_start = -MAX_LOW_POINT; region_end = NUMBER_REGIONS - MAX_LOW_POINT; } else { - /* 10 segments + /* 11 segments * segment is from 2^-10 to 2^0 * There are less than 256 points, for optimization */ @@ -154,9 +155,10 @@ bool cm3_helper_translate_curve_to_hw_format( seg_distr[7] = 4; seg_distr[8] = 4; seg_distr[9] = 4; + seg_distr[10] = 1; region_start = -10; - region_end = 0; + region_end = 1; } for (i = region_end - region_start; i < MAX_REGIONS_NUMBER ; i++) @@ -189,6 +191,10 @@ bool cm3_helper_translate_curve_to_hw_format( rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index]; rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index]; + rgb_resulted[hw_points].red = rgb_resulted[hw_points - 1].red; + rgb_resulted[hw_points].green = rgb_resulted[hw_points - 1].green; + rgb_resulted[hw_points].blue = rgb_resulted[hw_points - 1].blue; + // All 3 color channels have same x corner_points[0].red.x = dc_fixpt_pow(dc_fixpt_from_int(2), dc_fixpt_from_int(region_start)); @@ -259,15 +265,18 @@ bool cm3_helper_translate_curve_to_hw_format( rgb = rgb_resulted; rgb_plus_1 = rgb_resulted + 1; + rgb_minus_1 = rgb; i = 1; while (i != hw_points + 1) { - if (dc_fixpt_lt(rgb_plus_1->red, rgb->red)) - rgb_plus_1->red = rgb->red; - if (dc_fixpt_lt(rgb_plus_1->green, rgb->green)) - rgb_plus_1->green = rgb->green; - if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue)) - rgb_plus_1->blue = rgb->blue; + if (i >= hw_points - 1) { + if (dc_fixpt_lt(rgb_plus_1->red, rgb->red)) + rgb_plus_1->red = dc_fixpt_add(rgb->red, rgb_minus_1->delta_red); + if (dc_fixpt_lt(rgb_plus_1->green, rgb->green)) + rgb_plus_1->green = dc_fixpt_add(rgb->green, rgb_minus_1->delta_green); + if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue)) + rgb_plus_1->blue = dc_fixpt_add(rgb->blue, rgb_minus_1->delta_blue); + } rgb->delta_red = dc_fixpt_sub(rgb_plus_1->red, rgb->red); rgb->delta_green = dc_fixpt_sub(rgb_plus_1->green, rgb->green); @@ -283,6 +292,7 @@ bool cm3_helper_translate_curve_to_hw_format( } ++rgb_plus_1; + rgb_minus_1 = rgb; ++rgb; ++i; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c index 88ffa9ff1ed1..f24612523248 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c @@ -511,6 +511,7 @@ static struct hubp_funcs dcn30_hubp_funcs = { .hubp_init = hubp3_init, .hubp_in_blank = hubp1_in_blank, .hubp_soft_reset = hubp1_soft_reset, + .hubp_set_flip_int = hubp1_set_flip_int, }; bool hubp3_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c index 8d0f663489ac..fb7f1dea3c46 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c @@ -2508,6 +2508,19 @@ static const struct resource_funcs dcn30_res_pool_funcs = { .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, }; +#define CTX ctx + +#define REG(reg_name) \ + (DCN_BASE.instance[0].segment[mm ## reg_name ## _BASE_IDX] + mm ## reg_name) + +static uint32_t read_pipe_fuses(struct dc_context *ctx) +{ + uint32_t value = REG_READ(CC_DC_PIPE_DIS); + /* Support for max 6 pipes */ + value = value & 0x3f; + return value; +} + static bool dcn30_resource_construct( uint8_t num_virtual_links, struct dc *dc, @@ -2517,6 +2530,15 @@ static bool dcn30_resource_construct( struct dc_context *ctx = dc->ctx; struct irq_service_init_data init_data; struct ddc_service_init_data ddc_init_data; + uint32_t pipe_fuses = read_pipe_fuses(ctx); + uint32_t num_pipes = 0; + + if (!(pipe_fuses == 0 || pipe_fuses == 0x3e)) { + BREAK_TO_DEBUGGER(); + dm_error("DC: Unexpected fuse recipe for navi2x !\n"); + /* fault to single pipe */ + pipe_fuses = 0x3e; + } DC_FP_START(); @@ -2650,6 +2672,15 @@ static bool dcn30_resource_construct( /* PP Lib and SMU interfaces */ init_soc_bounding_box(dc, pool); + num_pipes = dcn3_0_ip.max_num_dpp; + + for (i = 0; i < dcn3_0_ip.max_num_dpp; i++) + if (pipe_fuses & 1 << i) + num_pipes--; + + dcn3_0_ip.max_num_dpp = num_pipes; + dcn3_0_ip.max_num_otg = num_pipes; + dml_init_instance(&dc->dml, &dcn3_0_soc, &dcn3_0_ip, DML_PROJECT_DCN30); /* IRQ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c index 5d4b2c60192e..c494235016e0 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c @@ -1619,12 +1619,106 @@ static void dcn301_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *b dml_init_instance(&dc->dml, &dcn3_01_soc, &dcn3_01_ip, DML_PROJECT_DCN30); } +static void calculate_wm_set_for_vlevel( + int vlevel, + struct wm_range_table_entry *table_entry, + struct dcn_watermarks *wm_set, + struct display_mode_lib *dml, + display_e2e_pipe_params_st *pipes, + int pipe_cnt) +{ + double dram_clock_change_latency_cached = dml->soc.dram_clock_change_latency_us; + + ASSERT(vlevel < dml->soc.num_states); + /* only pipe 0 is read for voltage and dcf/soc clocks */ + pipes[0].clks_cfg.voltage = vlevel; + pipes[0].clks_cfg.dcfclk_mhz = dml->soc.clock_limits[vlevel].dcfclk_mhz; + pipes[0].clks_cfg.socclk_mhz = dml->soc.clock_limits[vlevel].socclk_mhz; + + dml->soc.dram_clock_change_latency_us = table_entry->pstate_latency_us; + dml->soc.sr_exit_time_us = table_entry->sr_exit_time_us; + dml->soc.sr_enter_plus_exit_time_us = table_entry->sr_enter_plus_exit_time_us; + + wm_set->urgent_ns = get_wm_urgent(dml, pipes, pipe_cnt) * 1000; + wm_set->cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(dml, pipes, pipe_cnt) * 1000; + wm_set->cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(dml, pipes, pipe_cnt) * 1000; + wm_set->cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(dml, pipes, pipe_cnt) * 1000; + wm_set->pte_meta_urgent_ns = get_wm_memory_trip(dml, pipes, pipe_cnt) * 1000; + wm_set->frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(dml, pipes, pipe_cnt) * 1000; + wm_set->frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(dml, pipes, pipe_cnt) * 1000; + wm_set->urgent_latency_ns = get_urgent_latency(dml, pipes, pipe_cnt) * 1000; + dml->soc.dram_clock_change_latency_us = dram_clock_change_latency_cached; + +} + +static void dcn301_calculate_wm_and_dlg( + struct dc *dc, struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int pipe_cnt, + int vlevel_req) +{ + int i, pipe_idx; + int vlevel, vlevel_max; + struct wm_range_table_entry *table_entry; + struct clk_bw_params *bw_params = dc->clk_mgr->bw_params; + + ASSERT(bw_params); + + vlevel_max = bw_params->clk_table.num_entries - 1; + + /* WM Set D */ + table_entry = &bw_params->wm_table.entries[WM_D]; + if (table_entry->wm_type == WM_TYPE_RETRAINING) + vlevel = 0; + else + vlevel = vlevel_max; + calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.d, + &context->bw_ctx.dml, pipes, pipe_cnt); + /* WM Set C */ + table_entry = &bw_params->wm_table.entries[WM_C]; + vlevel = min(max(vlevel_req, 2), vlevel_max); + calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.c, + &context->bw_ctx.dml, pipes, pipe_cnt); + /* WM Set B */ + table_entry = &bw_params->wm_table.entries[WM_B]; + vlevel = min(max(vlevel_req, 1), vlevel_max); + calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.b, + &context->bw_ctx.dml, pipes, pipe_cnt); + + /* WM Set A */ + table_entry = &bw_params->wm_table.entries[WM_A]; + vlevel = min(vlevel_req, vlevel_max); + calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.a, + &context->bw_ctx.dml, pipes, pipe_cnt); + + for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) { + if (!context->res_ctx.pipe_ctx[i].stream) + continue; + + pipes[pipe_idx].clks_cfg.dispclk_mhz = get_dispclk_calculated(&context->bw_ctx.dml, pipes, pipe_cnt); + pipes[pipe_idx].clks_cfg.dppclk_mhz = get_dppclk_calculated(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); + + if (dc->config.forced_clocks) { + pipes[pipe_idx].clks_cfg.dispclk_mhz = context->bw_ctx.dml.soc.clock_limits[0].dispclk_mhz; + pipes[pipe_idx].clks_cfg.dppclk_mhz = context->bw_ctx.dml.soc.clock_limits[0].dppclk_mhz; + } + if (dc->debug.min_disp_clk_khz > pipes[pipe_idx].clks_cfg.dispclk_mhz * 1000) + pipes[pipe_idx].clks_cfg.dispclk_mhz = dc->debug.min_disp_clk_khz / 1000.0; + if (dc->debug.min_dpp_clk_khz > pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000) + pipes[pipe_idx].clks_cfg.dppclk_mhz = dc->debug.min_dpp_clk_khz / 1000.0; + + pipe_idx++; + } + + dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel); +} + static struct resource_funcs dcn301_res_pool_funcs = { .destroy = dcn301_destroy_resource_pool, .link_enc_create = dcn301_link_encoder_create, .panel_cntl_create = dcn301_panel_cntl_create, .validate_bandwidth = dcn30_validate_bandwidth, - .calculate_wm_and_dlg = dcn30_calculate_wm_and_dlg, + .calculate_wm_and_dlg = dcn301_calculate_wm_and_dlg, .populate_dml_pipes = dcn30_populate_dml_pipes_from_context, .acquire_idle_pipe_for_layer = dcn20_acquire_idle_pipe_for_layer, .add_stream_to_ctx = dcn30_add_stream_to_ctx, diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h index 22f3f643ed1b..346dcd87dc10 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h @@ -191,6 +191,8 @@ struct hubp_funcs { bool (*hubp_in_blank)(struct hubp *hubp); void (*hubp_soft_reset)(struct hubp *hubp, bool reset); + void (*hubp_set_flip_int)(struct hubp *hubp); + }; #endif diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index c57dc9ae81f2..a2681fe875ed 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -5216,10 +5216,10 @@ static int smu7_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr, for (j = 0; j < dep_sclk_table->count; j++) { valid_entry = false; for (k = 0; k < watermarks->num_wm_sets; k++) { - if (dep_sclk_table->entries[i].clk / 10 >= watermarks->wm_clk_ranges[k].wm_min_eng_clk_in_khz && - dep_sclk_table->entries[i].clk / 10 < watermarks->wm_clk_ranges[k].wm_max_eng_clk_in_khz && - dep_mclk_table->entries[i].clk / 10 >= watermarks->wm_clk_ranges[k].wm_min_mem_clk_in_khz && - dep_mclk_table->entries[i].clk / 10 < watermarks->wm_clk_ranges[k].wm_max_mem_clk_in_khz) { + if (dep_sclk_table->entries[i].clk >= watermarks->wm_clk_ranges[k].wm_min_eng_clk_in_khz / 10 && + dep_sclk_table->entries[i].clk < watermarks->wm_clk_ranges[k].wm_max_eng_clk_in_khz / 10 && + dep_mclk_table->entries[i].clk >= watermarks->wm_clk_ranges[k].wm_min_mem_clk_in_khz / 10 && + dep_mclk_table->entries[i].clk < watermarks->wm_clk_ranges[k].wm_max_mem_clk_in_khz / 10) { valid_entry = true; table->DisplayWatermark[i][j] = watermarks->wm_clk_ranges[k].wm_set_id; break; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c index 29c99642d22d..22b636e2b89b 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c @@ -1505,6 +1505,48 @@ static int vega10_populate_single_lclk_level(struct pp_hwmgr *hwmgr, return 0; } +static int vega10_override_pcie_parameters(struct pp_hwmgr *hwmgr) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev); + struct vega10_hwmgr *data = + (struct vega10_hwmgr *)(hwmgr->backend); + uint32_t pcie_gen = 0, pcie_width = 0; + PPTable_t *pp_table = &(data->smc_state_table.pp_table); + int i; + + if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4) + pcie_gen = 3; + else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) + pcie_gen = 2; + else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2) + pcie_gen = 1; + else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1) + pcie_gen = 0; + + if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X16) + pcie_width = 6; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X12) + pcie_width = 5; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X8) + pcie_width = 4; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X4) + pcie_width = 3; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X2) + pcie_width = 2; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X1) + pcie_width = 1; + + for (i = 0; i < NUM_LINK_LEVELS; i++) { + if (pp_table->PcieGenSpeed[i] > pcie_gen) + pp_table->PcieGenSpeed[i] = pcie_gen; + + if (pp_table->PcieLaneCount[i] > pcie_width) + pp_table->PcieLaneCount[i] = pcie_width; + } + + return 0; +} + static int vega10_populate_smc_link_levels(struct pp_hwmgr *hwmgr) { int result = -1; @@ -2556,6 +2598,11 @@ static int vega10_init_smc_table(struct pp_hwmgr *hwmgr) "Failed to initialize Link Level!", return result); + result = vega10_override_pcie_parameters(hwmgr); + PP_ASSERT_WITH_CODE(!result, + "Failed to override pcie parameters!", + return result); + result = vega10_populate_all_graphic_levels(hwmgr); PP_ASSERT_WITH_CODE(!result, "Failed to initialize Graphics Level!", @@ -2922,6 +2969,7 @@ static int vega10_start_dpm(struct pp_hwmgr *hwmgr, uint32_t bitmap) return 0; } + static int vega10_enable_disable_PCC_limit_feature(struct pp_hwmgr *hwmgr, bool enable) { struct vega10_hwmgr *data = hwmgr->backend; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c index c0753029a8e2..43e01d880f7c 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c @@ -481,6 +481,67 @@ static void vega12_init_dpm_state(struct vega12_dpm_state *dpm_state) dpm_state->hard_max_level = 0xffff; } +static int vega12_override_pcie_parameters(struct pp_hwmgr *hwmgr) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev); + struct vega12_hwmgr *data = + (struct vega12_hwmgr *)(hwmgr->backend); + uint32_t pcie_gen = 0, pcie_width = 0, smu_pcie_arg, pcie_gen_arg, pcie_width_arg; + PPTable_t *pp_table = &(data->smc_state_table.pp_table); + int i; + int ret; + + if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4) + pcie_gen = 3; + else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) + pcie_gen = 2; + else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2) + pcie_gen = 1; + else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1) + pcie_gen = 0; + + if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X16) + pcie_width = 6; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X12) + pcie_width = 5; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X8) + pcie_width = 4; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X4) + pcie_width = 3; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X2) + pcie_width = 2; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X1) + pcie_width = 1; + + /* Bit 31:16: LCLK DPM level. 0 is DPM0, and 1 is DPM1 + * Bit 15:8: PCIE GEN, 0 to 3 corresponds to GEN1 to GEN4 + * Bit 7:0: PCIE lane width, 1 to 7 corresponds is x1 to x32 + */ + for (i = 0; i < NUM_LINK_LEVELS; i++) { + pcie_gen_arg = (pp_table->PcieGenSpeed[i] > pcie_gen) ? pcie_gen : + pp_table->PcieGenSpeed[i]; + pcie_width_arg = (pp_table->PcieLaneCount[i] > pcie_width) ? pcie_width : + pp_table->PcieLaneCount[i]; + + if (pcie_gen_arg != pp_table->PcieGenSpeed[i] || pcie_width_arg != + pp_table->PcieLaneCount[i]) { + smu_pcie_arg = (i << 16) | (pcie_gen_arg << 8) | pcie_width_arg; + ret = smum_send_msg_to_smc_with_parameter(hwmgr, + PPSMC_MSG_OverridePcieParameters, smu_pcie_arg, + NULL); + PP_ASSERT_WITH_CODE(!ret, + "[OverridePcieParameters] Attempt to override pcie params failed!", + return ret); + } + + /* update the pptable */ + pp_table->PcieGenSpeed[i] = pcie_gen_arg; + pp_table->PcieLaneCount[i] = pcie_width_arg; + } + + return 0; +} + static int vega12_get_number_of_dpm_level(struct pp_hwmgr *hwmgr, PPCLK_e clk_id, uint32_t *num_of_levels) { @@ -968,6 +1029,11 @@ static int vega12_enable_dpm_tasks(struct pp_hwmgr *hwmgr) "Failed to enable all smu features!", return result); + result = vega12_override_pcie_parameters(hwmgr); + PP_ASSERT_WITH_CODE(!result, + "[EnableDPMTasks] Failed to override pcie parameters!", + return result); + tmp_result = vega12_power_control_set_level(hwmgr); PP_ASSERT_WITH_CODE(!tmp_result, "Failed to power control set level!", diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c index 87811b005b85..f19964c69a00 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c @@ -831,7 +831,9 @@ static int vega20_override_pcie_parameters(struct pp_hwmgr *hwmgr) struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev); struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend); - uint32_t pcie_gen = 0, pcie_width = 0, smu_pcie_arg; + uint32_t pcie_gen = 0, pcie_width = 0, smu_pcie_arg, pcie_gen_arg, pcie_width_arg; + PPTable_t *pp_table = &(data->smc_state_table.pp_table); + int i; int ret; if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4) @@ -860,17 +862,27 @@ static int vega20_override_pcie_parameters(struct pp_hwmgr *hwmgr) * Bit 15:8: PCIE GEN, 0 to 3 corresponds to GEN1 to GEN4 * Bit 7:0: PCIE lane width, 1 to 7 corresponds is x1 to x32 */ - smu_pcie_arg = (1 << 16) | (pcie_gen << 8) | pcie_width; - ret = smum_send_msg_to_smc_with_parameter(hwmgr, - PPSMC_MSG_OverridePcieParameters, smu_pcie_arg, - NULL); - PP_ASSERT_WITH_CODE(!ret, - "[OverridePcieParameters] Attempt to override pcie params failed!", - return ret); + for (i = 0; i < NUM_LINK_LEVELS; i++) { + pcie_gen_arg = (pp_table->PcieGenSpeed[i] > pcie_gen) ? pcie_gen : + pp_table->PcieGenSpeed[i]; + pcie_width_arg = (pp_table->PcieLaneCount[i] > pcie_width) ? pcie_width : + pp_table->PcieLaneCount[i]; + + if (pcie_gen_arg != pp_table->PcieGenSpeed[i] || pcie_width_arg != + pp_table->PcieLaneCount[i]) { + smu_pcie_arg = (i << 16) | (pcie_gen_arg << 8) | pcie_width_arg; + ret = smum_send_msg_to_smc_with_parameter(hwmgr, + PPSMC_MSG_OverridePcieParameters, smu_pcie_arg, + NULL); + PP_ASSERT_WITH_CODE(!ret, + "[OverridePcieParameters] Attempt to override pcie params failed!", + return ret); + } - data->pcie_parameters_override = true; - data->pcie_gen_level1 = pcie_gen; - data->pcie_width_level1 = pcie_width; + /* update the pptable */ + pp_table->PcieGenSpeed[i] = pcie_gen_arg; + pp_table->PcieLaneCount[i] = pcie_width_arg; + } return 0; } @@ -3319,9 +3331,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, data->od8_settings.od8_settings_array; OverDriveTable_t *od_table = &(data->smc_state_table.overdrive_table); - struct phm_ppt_v3_information *pptable_information = - (struct phm_ppt_v3_information *)hwmgr->pptable; - PPTable_t *pptable = (PPTable_t *)pptable_information->smc_pptable; + PPTable_t *pptable = &(data->smc_state_table.pp_table); struct pp_clock_levels_with_latency clocks; struct vega20_single_dpm_table *fclk_dpm_table = &(data->dpm_table.fclk_table); @@ -3420,13 +3430,9 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, current_lane_width = vega20_get_current_pcie_link_width_level(hwmgr); for (i = 0; i < NUM_LINK_LEVELS; i++) { - if (i == 1 && data->pcie_parameters_override) { - gen_speed = data->pcie_gen_level1; - lane_width = data->pcie_width_level1; - } else { - gen_speed = pptable->PcieGenSpeed[i]; - lane_width = pptable->PcieLaneCount[i]; - } + gen_speed = pptable->PcieGenSpeed[i]; + lane_width = pptable->PcieLaneCount[i]; + size += sprintf(buf + size, "%d: %s %s %dMhz %s\n", i, (gen_speed == 0) ? "2.5GT/s," : (gen_speed == 1) ? "5.0GT/s," : diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index fb1b1d096975..9cf555d6842b 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -713,9 +713,12 @@ static int engine_setup_common(struct intel_engine_cs *engine) goto err_status; } + err = intel_engine_init_cmd_parser(engine); + if (err) + goto err_cmd_parser; + intel_engine_init_active(engine, ENGINE_PHYSICAL); intel_engine_init_execlists(engine); - intel_engine_init_cmd_parser(engine); intel_engine_init__pm(engine); intel_engine_init_retire(engine); @@ -732,6 +735,8 @@ static int engine_setup_common(struct intel_engine_cs *engine) return 0; +err_cmd_parser: + intel_breadcrumbs_free(engine->breadcrumbs); err_status: cleanup_status_page(engine); return err; diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index ced9a96d7c34..5f86f5b2caf6 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -940,7 +940,7 @@ static void fini_hash_table(struct intel_engine_cs *engine) * struct intel_engine_cs based on whether the platform requires software * command parsing. */ -void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) +int intel_engine_init_cmd_parser(struct intel_engine_cs *engine) { const struct drm_i915_cmd_table *cmd_tables; int cmd_table_count; @@ -948,7 +948,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) if (!IS_GEN(engine->i915, 7) && !(IS_GEN(engine->i915, 9) && engine->class == COPY_ENGINE_CLASS)) - return; + return 0; switch (engine->class) { case RENDER_CLASS: @@ -1013,19 +1013,19 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) break; default: MISSING_CASE(engine->class); - return; + goto out; } if (!validate_cmds_sorted(engine, cmd_tables, cmd_table_count)) { drm_err(&engine->i915->drm, "%s: command descriptions are not sorted\n", engine->name); - return; + goto out; } if (!validate_regs_sorted(engine)) { drm_err(&engine->i915->drm, "%s: registers are not sorted\n", engine->name); - return; + goto out; } ret = init_hash_table(engine, cmd_tables, cmd_table_count); @@ -1033,10 +1033,17 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) drm_err(&engine->i915->drm, "%s: initialised failed!\n", engine->name); fini_hash_table(engine); - return; + goto out; } engine->flags |= I915_ENGINE_USING_CMD_PARSER; + +out: + if (intel_engine_requires_cmd_parser(engine) && + !intel_engine_using_cmd_parser(engine)) + return -EINVAL; + + return 0; } /** diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 26d69d06aa6d..cb62ddba2035 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1952,7 +1952,7 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type); /* i915_cmd_parser.c */ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv); -void intel_engine_init_cmd_parser(struct intel_engine_cs *engine); +int intel_engine_init_cmd_parser(struct intel_engine_cs *engine); void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine); int intel_engine_cmd_parser(struct intel_engine_cs *engine, struct i915_vma *batch, diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 112ba5f2ce90..e62ad69606f6 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -603,7 +603,6 @@ static int append_oa_sample(struct i915_perf_stream *stream, { int report_size = stream->oa_buffer.format_size; struct drm_i915_perf_record_header header; - u32 sample_flags = stream->sample_flags; header.type = DRM_I915_PERF_RECORD_SAMPLE; header.pad = 0; @@ -617,10 +616,8 @@ static int append_oa_sample(struct i915_perf_stream *stream, return -EFAULT; buf += sizeof(header); - if (sample_flags & SAMPLE_OA_REPORT) { - if (copy_to_user(buf, report, report_size)) - return -EFAULT; - } + if (copy_to_user(buf, report, report_size)) + return -EFAULT; (*offset) += header.size; @@ -2682,7 +2679,7 @@ static void i915_oa_stream_enable(struct i915_perf_stream *stream) stream->perf->ops.oa_enable(stream); - if (stream->periodic) + if (stream->sample_flags & SAMPLE_OA_REPORT) hrtimer_start(&stream->poll_check_timer, ns_to_ktime(stream->poll_oa_period), HRTIMER_MODE_REL_PINNED); @@ -2745,7 +2742,7 @@ static void i915_oa_stream_disable(struct i915_perf_stream *stream) { stream->perf->ops.oa_disable(stream); - if (stream->periodic) + if (stream->sample_flags & SAMPLE_OA_REPORT) hrtimer_cancel(&stream->poll_check_timer); } @@ -3028,7 +3025,7 @@ static ssize_t i915_perf_read(struct file *file, * disabled stream as an error. In particular it might otherwise lead * to a deadlock for blocking file descriptors... */ - if (!stream->enabled) + if (!stream->enabled || !(stream->sample_flags & SAMPLE_OA_REPORT)) return -EIO; if (!(file->f_flags & O_NONBLOCK)) { diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 7146cd0f3256..aaf1f0045b16 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -3316,7 +3316,18 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define ILK_DISPLAY_CHICKEN1 _MMIO(0x42000) #define ILK_FBCQ_DIS (1 << 22) -#define ILK_PABSTRETCH_DIS (1 << 21) +#define ILK_PABSTRETCH_DIS REG_BIT(21) +#define ILK_SABSTRETCH_DIS REG_BIT(20) +#define IVB_PRI_STRETCH_MAX_MASK REG_GENMASK(21, 20) +#define IVB_PRI_STRETCH_MAX_X8 REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 0) +#define IVB_PRI_STRETCH_MAX_X4 REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 1) +#define IVB_PRI_STRETCH_MAX_X2 REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 2) +#define IVB_PRI_STRETCH_MAX_X1 REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 3) +#define IVB_SPR_STRETCH_MAX_MASK REG_GENMASK(19, 18) +#define IVB_SPR_STRETCH_MAX_X8 REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 0) +#define IVB_SPR_STRETCH_MAX_X4 REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 1) +#define IVB_SPR_STRETCH_MAX_X2 REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 2) +#define IVB_SPR_STRETCH_MAX_X1 REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 3) /* @@ -8039,6 +8050,16 @@ enum { #define _CHICKEN_PIPESL_1_A 0x420b0 #define _CHICKEN_PIPESL_1_B 0x420b4 +#define HSW_PRI_STRETCH_MAX_MASK REG_GENMASK(28, 27) +#define HSW_PRI_STRETCH_MAX_X8 REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 0) +#define HSW_PRI_STRETCH_MAX_X4 REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 1) +#define HSW_PRI_STRETCH_MAX_X2 REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 2) +#define HSW_PRI_STRETCH_MAX_X1 REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 3) +#define HSW_SPR_STRETCH_MAX_MASK REG_GENMASK(26, 25) +#define HSW_SPR_STRETCH_MAX_X8 REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 0) +#define HSW_SPR_STRETCH_MAX_X4 REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 1) +#define HSW_SPR_STRETCH_MAX_X2 REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 2) +#define HSW_SPR_STRETCH_MAX_X1 REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 3) #define HSW_FBCQ_DIS (1 << 22) #define BDW_DPRS_MASK_VBLANK_SRD (1 << 0) #define CHICKEN_PIPESL_1(pipe) _MMIO_PIPE(pipe, _CHICKEN_PIPESL_1_A, _CHICKEN_PIPESL_1_B) diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 0c3e63f27c29..97b57acc02e2 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -7245,11 +7245,16 @@ static void bdw_init_clock_gating(struct drm_i915_private *dev_priv) intel_uncore_write(&dev_priv->uncore, CHICKEN_PAR1_1, intel_uncore_read(&dev_priv->uncore, CHICKEN_PAR1_1) | DPA_MASK_VBLANK_SRD); - /* WaPsrDPRSUnmaskVBlankInSRD:bdw */ for_each_pipe(dev_priv, pipe) { + /* WaPsrDPRSUnmaskVBlankInSRD:bdw */ intel_uncore_write(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe), intel_uncore_read(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe)) | BDW_DPRS_MASK_VBLANK_SRD); + + /* Undocumented but fixes async flip + VT-d corruption */ + if (intel_vtd_active()) + intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe), + HSW_PRI_STRETCH_MAX_MASK, HSW_PRI_STRETCH_MAX_X1); } /* WaVSRefCountFullforceMissDisable:bdw */ @@ -7285,11 +7290,20 @@ static void bdw_init_clock_gating(struct drm_i915_private *dev_priv) static void hsw_init_clock_gating(struct drm_i915_private *dev_priv) { + enum pipe pipe; + /* WaFbcAsynchFlipDisableFbcQueue:hsw,bdw */ intel_uncore_write(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A), intel_uncore_read(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A)) | HSW_FBCQ_DIS); + for_each_pipe(dev_priv, pipe) { + /* Undocumented but fixes async flip + VT-d corruption */ + if (intel_vtd_active()) + intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe), + HSW_PRI_STRETCH_MAX_MASK, HSW_PRI_STRETCH_MAX_X1); + } + /* This is required by WaCatErrorRejectionIssue:hsw */ intel_uncore_write(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG, intel_uncore_read(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) | diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 2375711877cf..f2720a006199 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -551,12 +551,17 @@ nouveau_bo_sync_for_device(struct nouveau_bo *nvbo) if (!ttm_dma) return; + if (!ttm_dma->pages) { + NV_DEBUG(drm, "ttm_dma 0x%p: pages NULL\n", ttm_dma); + return; + } /* Don't waste time looping if the object is coherent */ if (nvbo->force_coherent) return; - for (i = 0; i < ttm_dma->num_pages; ++i) { + i = 0; + while (i < ttm_dma->num_pages) { struct page *p = ttm_dma->pages[i]; size_t num_pages = 1; @@ -582,12 +587,17 @@ nouveau_bo_sync_for_cpu(struct nouveau_bo *nvbo) if (!ttm_dma) return; + if (!ttm_dma->pages) { + NV_DEBUG(drm, "ttm_dma 0x%p: pages NULL\n", ttm_dma); + return; + } /* Don't waste time looping if the object is coherent */ if (nvbo->force_coherent) return; - for (i = 0; i < ttm_dma->num_pages; ++i) { + i = 0; + while (i < ttm_dma->num_pages) { struct page *p = ttm_dma->pages[i]; size_t num_pages = 1; diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index f09989bdce98..3effc8c71494 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -574,6 +574,8 @@ struct radeon_gem { struct list_head objects; }; +extern const struct drm_gem_object_funcs radeon_gem_object_funcs; + int radeon_gem_init(struct radeon_device *rdev); void radeon_gem_fini(struct radeon_device *rdev); int radeon_gem_object_create(struct radeon_device *rdev, unsigned long size, diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index 941826923247..db14a82a2e4b 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -43,7 +43,7 @@ struct sg_table *radeon_gem_prime_get_sg_table(struct drm_gem_object *obj); int radeon_gem_prime_pin(struct drm_gem_object *obj); void radeon_gem_prime_unpin(struct drm_gem_object *obj); -static const struct drm_gem_object_funcs radeon_gem_object_funcs; +const struct drm_gem_object_funcs radeon_gem_object_funcs; static void radeon_gem_object_free(struct drm_gem_object *gobj) { @@ -227,7 +227,7 @@ static int radeon_gem_handle_lockup(struct radeon_device *rdev, int r) return r; } -static const struct drm_gem_object_funcs radeon_gem_object_funcs = { +const struct drm_gem_object_funcs radeon_gem_object_funcs = { .free = radeon_gem_object_free, .open = radeon_gem_object_open, .close = radeon_gem_object_close, diff --git a/drivers/gpu/drm/radeon/radeon_prime.c b/drivers/gpu/drm/radeon/radeon_prime.c index ab29eb9e8667..42a87948e28c 100644 --- a/drivers/gpu/drm/radeon/radeon_prime.c +++ b/drivers/gpu/drm/radeon/radeon_prime.c @@ -56,6 +56,8 @@ struct drm_gem_object *radeon_gem_prime_import_sg_table(struct drm_device *dev, if (ret) return ERR_PTR(ret); + bo->tbo.base.funcs = &radeon_gem_object_funcs; + mutex_lock(&rdev->gem.mutex); list_add_tail(&bo->list, &rdev->gem.objects); mutex_unlock(&rdev->gem.mutex); diff --git a/drivers/gpu/drm/rcar-du/rcar_du_encoder.c b/drivers/gpu/drm/rcar-du/rcar_du_encoder.c index ba8c6038cd63..ca3761772211 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_encoder.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_encoder.c @@ -48,21 +48,12 @@ static unsigned int rcar_du_encoder_count_ports(struct device_node *node) static const struct drm_encoder_funcs rcar_du_encoder_funcs = { }; -static void rcar_du_encoder_release(struct drm_device *dev, void *res) -{ - struct rcar_du_encoder *renc = res; - - drm_encoder_cleanup(&renc->base); - kfree(renc); -} - int rcar_du_encoder_init(struct rcar_du_device *rcdu, enum rcar_du_output output, struct device_node *enc_node) { struct rcar_du_encoder *renc; struct drm_bridge *bridge; - int ret; /* * Locate the DRM bridge from the DT node. For the DPAD outputs, if the @@ -101,26 +92,16 @@ int rcar_du_encoder_init(struct rcar_du_device *rcdu, return -ENOLINK; } - renc = kzalloc(sizeof(*renc), GFP_KERNEL); - if (renc == NULL) - return -ENOMEM; - - renc->output = output; - dev_dbg(rcdu->dev, "initializing encoder %pOF for output %u\n", enc_node, output); - ret = drm_encoder_init(&rcdu->ddev, &renc->base, &rcar_du_encoder_funcs, - DRM_MODE_ENCODER_NONE, NULL); - if (ret < 0) { - kfree(renc); - return ret; - } + renc = drmm_encoder_alloc(&rcdu->ddev, struct rcar_du_encoder, base, + &rcar_du_encoder_funcs, DRM_MODE_ENCODER_NONE, + NULL); + if (!renc) + return -ENOMEM; - ret = drmm_add_action_or_reset(&rcdu->ddev, rcar_du_encoder_release, - renc); - if (ret) - return ret; + renc->output = output; /* * Attach the bridge to the encoder. The bridge will create the diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c index 0a900afc66ff..45c9c6a7f1d6 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c @@ -500,8 +500,6 @@ vm_fault_t vmw_bo_vm_huge_fault(struct vm_fault *vmf, vm_fault_t ret; pgoff_t fault_page_size; bool write = vmf->flags & FAULT_FLAG_WRITE; - bool is_cow_mapping = - (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; switch (pe_size) { case PE_SIZE_PMD: @@ -518,7 +516,7 @@ vm_fault_t vmw_bo_vm_huge_fault(struct vm_fault *vmf, } /* Always do write dirty-tracking and COW on PTE level. */ - if (write && (READ_ONCE(vbo->dirty) || is_cow_mapping)) + if (write && (READ_ONCE(vbo->dirty) || is_cow_mapping(vma->vm_flags))) return VM_FAULT_FALLBACK; ret = ttm_bo_vm_reserve(bo, vmf); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c index 3c03b1746661..cb9975889e2f 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c @@ -49,7 +49,7 @@ int vmw_mmap(struct file *filp, struct vm_area_struct *vma) vma->vm_ops = &vmw_vm_ops; /* Use VM_PFNMAP rather than VM_MIXEDMAP if not a COW mapping */ - if ((vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) != VM_MAYWRITE) + if (!is_cow_mapping(vma->vm_flags)) vma->vm_flags = (vma->vm_flags & ~VM_MIXEDMAP) | VM_PFNMAP; return 0; |