diff options
Diffstat (limited to 'drivers/gpu/drm/amd/display')
120 files changed, 4463 insertions, 1553 deletions
diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig index 096db863c345..87858bc57e64 100644 --- a/drivers/gpu/drm/amd/display/Kconfig +++ b/drivers/gpu/drm/amd/display/Kconfig @@ -6,7 +6,7 @@ config DRM_AMD_DC bool "AMD DC - Enable new display engine" default y select SND_HDA_COMPONENT if SND_HDA_CORE - select DRM_AMD_DC_DCN if X86 && !(KCOV_INSTRUMENT_ALL && KCOV_ENABLE_COMPARISONS) + select DRM_AMD_DC_DCN if (X86 || PPC64) && !(KCOV_INSTRUMENT_ALL && KCOV_ENABLE_COMPARISONS) help Choose this option if you want to use the new display engine support for AMDGPU. This adds required support for Vega and 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 ea55f4160c80..df1535543fde 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -98,6 +98,12 @@ MODULE_FIRMWARE(FIRMWARE_RENOIR_DMUB); #define FIRMWARE_RAVEN_DMCU "amdgpu/raven_dmcu.bin" MODULE_FIRMWARE(FIRMWARE_RAVEN_DMCU); +/* Number of bytes in PSP header for firmware. */ +#define PSP_HEADER_BYTES 0x100 + +/* Number of bytes in PSP footer for firmware. */ +#define PSP_FOOTER_BYTES 0x100 + /** * DOC: overview * @@ -741,28 +747,27 @@ void amdgpu_dm_audio_eld_notify(struct amdgpu_device *adev, int pin) static int dm_dmub_hw_init(struct amdgpu_device *adev) { - const unsigned int psp_header_bytes = 0x100; - const unsigned int psp_footer_bytes = 0x100; const struct dmcub_firmware_header_v1_0 *hdr; struct dmub_srv *dmub_srv = adev->dm.dmub_srv; + struct dmub_srv_fb_info *fb_info = adev->dm.dmub_fb_info; const struct firmware *dmub_fw = adev->dm.dmub_fw; struct dmcu *dmcu = adev->dm.dc->res_pool->dmcu; struct abm *abm = adev->dm.dc->res_pool->abm; - struct dmub_srv_region_params region_params; - struct dmub_srv_region_info region_info; - struct dmub_srv_fb_params fb_params; - struct dmub_srv_fb_info fb_info; struct dmub_srv_hw_params hw_params; enum dmub_status status; const unsigned char *fw_inst_const, *fw_bss_data; - uint32_t i; - int r; + uint32_t i, fw_inst_const_size, fw_bss_data_size; bool has_hw_support; if (!dmub_srv) /* DMUB isn't supported on the ASIC. */ return 0; + if (!fb_info) { + DRM_ERROR("No framebuffer info for DMUB service.\n"); + return -EINVAL; + } + if (!dmub_fw) { /* Firmware required for DMUB support. */ DRM_ERROR("No firmware provided for DMUB.\n"); @@ -782,60 +787,36 @@ static int dm_dmub_hw_init(struct amdgpu_device *adev) hdr = (const struct dmcub_firmware_header_v1_0 *)dmub_fw->data; - /* Calculate the size of all the regions for the DMUB service. */ - memset(®ion_params, 0, sizeof(region_params)); - - region_params.inst_const_size = le32_to_cpu(hdr->inst_const_bytes) - - psp_header_bytes - psp_footer_bytes; - region_params.bss_data_size = le32_to_cpu(hdr->bss_data_bytes); - region_params.vbios_size = adev->dm.dc->ctx->dc_bios->bios_size; - - status = dmub_srv_calc_region_info(dmub_srv, ®ion_params, - ®ion_info); - - if (status != DMUB_STATUS_OK) { - DRM_ERROR("Error calculating DMUB region info: %d\n", status); - return -EINVAL; - } - - /* - * Allocate a framebuffer based on the total size of all the regions. - * TODO: Move this into GART. - */ - r = amdgpu_bo_create_kernel(adev, region_info.fb_size, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, &adev->dm.dmub_bo, - &adev->dm.dmub_bo_gpu_addr, - &adev->dm.dmub_bo_cpu_addr); - if (r) - return r; - - /* Rebase the regions on the framebuffer address. */ - memset(&fb_params, 0, sizeof(fb_params)); - fb_params.cpu_addr = adev->dm.dmub_bo_cpu_addr; - fb_params.gpu_addr = adev->dm.dmub_bo_gpu_addr; - fb_params.region_info = ®ion_info; - - status = dmub_srv_calc_fb_info(dmub_srv, &fb_params, &fb_info); - if (status != DMUB_STATUS_OK) { - DRM_ERROR("Error calculating DMUB FB info: %d\n", status); - return -EINVAL; - } - fw_inst_const = dmub_fw->data + le32_to_cpu(hdr->header.ucode_array_offset_bytes) + - psp_header_bytes; + PSP_HEADER_BYTES; fw_bss_data = dmub_fw->data + le32_to_cpu(hdr->header.ucode_array_offset_bytes) + le32_to_cpu(hdr->inst_const_bytes); /* Copy firmware and bios info into FB memory. */ - memcpy(fb_info.fb[DMUB_WINDOW_0_INST_CONST].cpu_addr, fw_inst_const, - region_params.inst_const_size); - memcpy(fb_info.fb[DMUB_WINDOW_2_BSS_DATA].cpu_addr, fw_bss_data, - region_params.bss_data_size); - memcpy(fb_info.fb[DMUB_WINDOW_3_VBIOS].cpu_addr, - adev->dm.dc->ctx->dc_bios->bios, region_params.vbios_size); + fw_inst_const_size = le32_to_cpu(hdr->inst_const_bytes) - + PSP_HEADER_BYTES - PSP_FOOTER_BYTES; + + fw_bss_data_size = le32_to_cpu(hdr->bss_data_bytes); + + memcpy(fb_info->fb[DMUB_WINDOW_0_INST_CONST].cpu_addr, fw_inst_const, + fw_inst_const_size); + memcpy(fb_info->fb[DMUB_WINDOW_2_BSS_DATA].cpu_addr, fw_bss_data, + fw_bss_data_size); + memcpy(fb_info->fb[DMUB_WINDOW_3_VBIOS].cpu_addr, adev->bios, + adev->bios_size); + + /* Reset regions that need to be reset. */ + memset(fb_info->fb[DMUB_WINDOW_4_MAILBOX].cpu_addr, 0, + fb_info->fb[DMUB_WINDOW_4_MAILBOX].size); + + memset(fb_info->fb[DMUB_WINDOW_5_TRACEBUFF].cpu_addr, 0, + fb_info->fb[DMUB_WINDOW_5_TRACEBUFF].size); + + memset(fb_info->fb[DMUB_WINDOW_6_FW_STATE].cpu_addr, 0, + fb_info->fb[DMUB_WINDOW_6_FW_STATE].size); /* Initialize hardware. */ memset(&hw_params, 0, sizeof(hw_params)); @@ -845,8 +826,8 @@ static int dm_dmub_hw_init(struct amdgpu_device *adev) if (dmcu) hw_params.psp_version = dmcu->psp_version; - for (i = 0; i < fb_info.num_fb; ++i) - hw_params.fb[i] = &fb_info.fb[i]; + for (i = 0; i < fb_info->num_fb; ++i) + hw_params.fb[i] = &fb_info->fb[i]; status = dmub_srv_hw_init(dmub_srv, &hw_params); if (status != DMUB_STATUS_OK) { @@ -925,13 +906,16 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) init_data.dce_environment = DCE_ENV_PRODUCTION_DRV; - /* - * TODO debug why this doesn't work on Raven - */ - if (adev->flags & AMD_IS_APU && - adev->asic_type >= CHIP_CARRIZO && - adev->asic_type < CHIP_RAVEN) + switch (adev->asic_type) { + case CHIP_CARRIZO: + case CHIP_STONEY: + case CHIP_RAVEN: + case CHIP_RENOIR: init_data.flags.gpu_vm_support = true; + break; + default: + break; + } if (amdgpu_dc_feature_mask & DC_FBC_MASK) init_data.flags.fbc_support = true; @@ -956,14 +940,14 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) goto error; } - dc_hardware_init(adev->dm.dc); - r = dm_dmub_hw_init(adev); if (r) { DRM_ERROR("DMUB interface failed to initialize: status=%d\n", r); goto error; } + dc_hardware_init(adev->dm.dc); + adev->dm.freesync_module = mod_freesync_create(adev->dm.dc); if (!adev->dm.freesync_module) { DRM_ERROR( @@ -1174,6 +1158,11 @@ static void amdgpu_dm_dmub_reg_write(void *ctx, uint32_t address, static int dm_dmub_sw_init(struct amdgpu_device *adev) { struct dmub_srv_create_params create_params; + struct dmub_srv_region_params region_params; + struct dmub_srv_region_info region_info; + struct dmub_srv_fb_params fb_params; + struct dmub_srv_fb_info *fb_info; + struct dmub_srv *dmub_srv; const struct dmcub_firmware_header_v1_0 *hdr; const char *fw_name_dmub; enum dmub_asic dmub_asic; @@ -1191,24 +1180,6 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev) return 0; } - adev->dm.dmub_srv = kzalloc(sizeof(*adev->dm.dmub_srv), GFP_KERNEL); - if (!adev->dm.dmub_srv) { - DRM_ERROR("Failed to allocate DMUB service!\n"); - return -ENOMEM; - } - - memset(&create_params, 0, sizeof(create_params)); - create_params.user_ctx = adev; - create_params.funcs.reg_read = amdgpu_dm_dmub_reg_read; - create_params.funcs.reg_write = amdgpu_dm_dmub_reg_write; - create_params.asic = dmub_asic; - - status = dmub_srv_create(adev->dm.dmub_srv, &create_params); - if (status != DMUB_STATUS_OK) { - DRM_ERROR("Error creating DMUB service: %d\n", status); - return -EINVAL; - } - r = request_firmware_direct(&adev->dm.dmub_fw, fw_name_dmub, adev->dev); if (r) { DRM_ERROR("DMUB firmware loading failed: %d\n", r); @@ -1238,6 +1209,80 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev) DRM_INFO("Loading DMUB firmware via PSP: version=0x%08X\n", adev->dm.dmcub_fw_version); + adev->dm.dmub_srv = kzalloc(sizeof(*adev->dm.dmub_srv), GFP_KERNEL); + dmub_srv = adev->dm.dmub_srv; + + if (!dmub_srv) { + DRM_ERROR("Failed to allocate DMUB service!\n"); + return -ENOMEM; + } + + memset(&create_params, 0, sizeof(create_params)); + create_params.user_ctx = adev; + create_params.funcs.reg_read = amdgpu_dm_dmub_reg_read; + create_params.funcs.reg_write = amdgpu_dm_dmub_reg_write; + create_params.asic = dmub_asic; + + /* Create the DMUB service. */ + status = dmub_srv_create(dmub_srv, &create_params); + if (status != DMUB_STATUS_OK) { + DRM_ERROR("Error creating DMUB service: %d\n", status); + return -EINVAL; + } + + /* Calculate the size of all the regions for the DMUB service. */ + memset(®ion_params, 0, sizeof(region_params)); + + region_params.inst_const_size = le32_to_cpu(hdr->inst_const_bytes) - + PSP_HEADER_BYTES - PSP_FOOTER_BYTES; + region_params.bss_data_size = le32_to_cpu(hdr->bss_data_bytes); + region_params.vbios_size = adev->bios_size; + region_params.fw_bss_data = + adev->dm.dmub_fw->data + + le32_to_cpu(hdr->header.ucode_array_offset_bytes) + + le32_to_cpu(hdr->inst_const_bytes); + + status = dmub_srv_calc_region_info(dmub_srv, ®ion_params, + ®ion_info); + + if (status != DMUB_STATUS_OK) { + DRM_ERROR("Error calculating DMUB region info: %d\n", status); + return -EINVAL; + } + + /* + * Allocate a framebuffer based on the total size of all the regions. + * TODO: Move this into GART. + */ + r = amdgpu_bo_create_kernel(adev, region_info.fb_size, PAGE_SIZE, + AMDGPU_GEM_DOMAIN_VRAM, &adev->dm.dmub_bo, + &adev->dm.dmub_bo_gpu_addr, + &adev->dm.dmub_bo_cpu_addr); + if (r) + return r; + + /* Rebase the regions on the framebuffer address. */ + memset(&fb_params, 0, sizeof(fb_params)); + fb_params.cpu_addr = adev->dm.dmub_bo_cpu_addr; + fb_params.gpu_addr = adev->dm.dmub_bo_gpu_addr; + fb_params.region_info = ®ion_info; + + adev->dm.dmub_fb_info = + kzalloc(sizeof(*adev->dm.dmub_fb_info), GFP_KERNEL); + fb_info = adev->dm.dmub_fb_info; + + if (!fb_info) { + DRM_ERROR( + "Failed to allocate framebuffer info for DMUB service!\n"); + return -ENOMEM; + } + + status = dmub_srv_calc_fb_info(dmub_srv, &fb_params, fb_info); + if (status != DMUB_STATUS_OK) { + DRM_ERROR("Error calculating DMUB FB info: %d\n", status); + return -EINVAL; + } + return 0; } @@ -1257,6 +1302,9 @@ static int dm_sw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + kfree(adev->dm.dmub_fb_info); + adev->dm.dmub_fb_info = NULL; + if (adev->dm.dmub_srv) { dmub_srv_destroy(adev->dm.dmub_srv); adev->dm.dmub_srv = NULL; @@ -1559,7 +1607,7 @@ static int dm_resume(void *handle) struct dm_plane_state *dm_new_plane_state; struct dm_atomic_state *dm_state = to_dm_atomic_state(dm->atomic_obj.state); enum dc_connection_type new_connection_type = dc_connection_none; - int i; + int i, r; /* Recreate dc_state - DC invalidates it when setting power state to S3. */ dc_release_state(dm_state->context); @@ -1567,6 +1615,11 @@ static int dm_resume(void *handle) /* TODO: Remove dc_state->dccg, use dc->dccg directly. */ dc_resource_state_construct(dm->dc, dm_state->context); + /* Before powering on DC we need to re-initialize DMUB. */ + r = dm_dmub_hw_init(adev); + if (r) + DRM_ERROR("DMUB interface failed to initialize: status=%d\n", r); + /* power on hardware */ dc_set_power_state(dm->dc, DC_ACPI_CM_POWER_STATE_D0); @@ -3654,27 +3707,21 @@ get_output_color_space(const struct dc_crtc_timing *dc_crtc_timing) return color_space; } -static void reduce_mode_colour_depth(struct dc_crtc_timing *timing_out) -{ - if (timing_out->display_color_depth <= COLOR_DEPTH_888) - return; - - timing_out->display_color_depth--; -} - -static void adjust_colour_depth_from_display_info(struct dc_crtc_timing *timing_out, - const struct drm_display_info *info) +static bool adjust_colour_depth_from_display_info( + struct dc_crtc_timing *timing_out, + const struct drm_display_info *info) { + enum dc_color_depth depth = timing_out->display_color_depth; int normalized_clk; - if (timing_out->display_color_depth <= COLOR_DEPTH_888) - return; do { normalized_clk = timing_out->pix_clk_100hz / 10; /* YCbCr 4:2:0 requires additional adjustment of 1/2 */ if (timing_out->pixel_encoding == PIXEL_ENCODING_YCBCR420) normalized_clk /= 2; /* Adjusting pix clock following on HDMI spec based on colour depth */ - switch (timing_out->display_color_depth) { + switch (depth) { + case COLOR_DEPTH_888: + break; case COLOR_DEPTH_101010: normalized_clk = (normalized_clk * 30) / 24; break; @@ -3685,14 +3732,15 @@ static void adjust_colour_depth_from_display_info(struct dc_crtc_timing *timing_ normalized_clk = (normalized_clk * 48) / 24; break; default: - return; + /* The above depths are the only ones valid for HDMI. */ + return false; } - if (normalized_clk <= info->max_tmds_clock) - return; - reduce_mode_colour_depth(timing_out); - - } while (timing_out->display_color_depth > COLOR_DEPTH_888); - + if (normalized_clk <= info->max_tmds_clock) { + timing_out->display_color_depth = depth; + return true; + } + } while (--depth > COLOR_DEPTH_666); + return false; } static void fill_stream_properties_from_drm_display_mode( @@ -3773,8 +3821,14 @@ static void fill_stream_properties_from_drm_display_mode( stream->out_transfer_func->type = TF_TYPE_PREDEFINED; stream->out_transfer_func->tf = TRANSFER_FUNCTION_SRGB; - if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A) - adjust_colour_depth_from_display_info(timing_out, info); + if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A) { + if (!adjust_colour_depth_from_display_info(timing_out, info) && + drm_mode_is_420_also(info, mode_in) && + timing_out->pixel_encoding != PIXEL_ENCODING_YCBCR420) { + timing_out->pixel_encoding = PIXEL_ENCODING_YCBCR420; + adjust_colour_depth_from_display_info(timing_out, info); + } + } } static void fill_audio_info(struct audio_info *audio_info, @@ -4025,7 +4079,8 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, if (aconnector->dc_link && sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT) { #if defined(CONFIG_DRM_AMD_DC_DCN) - dc_dsc_parse_dsc_dpcd(aconnector->dc_link->dpcd_caps.dsc_caps.dsc_basic_caps.raw, + dc_dsc_parse_dsc_dpcd(aconnector->dc_link->ctx->dc, + aconnector->dc_link->dpcd_caps.dsc_caps.dsc_basic_caps.raw, aconnector->dc_link->dpcd_caps.dsc_caps.dsc_ext_caps.raw, &dsc_caps); #endif @@ -4884,12 +4939,13 @@ static int dm_encoder_helper_atomic_check(struct drm_encoder *encoder, is_y420); bpp = convert_dc_color_depth_into_bpc(color_depth) * 3; clock = adjusted_mode->clock; - dm_new_connector_state->pbn = drm_dp_calc_pbn_mode(clock, bpp); + dm_new_connector_state->pbn = drm_dp_calc_pbn_mode(clock, bpp, false); } dm_new_connector_state->vcpi_slots = drm_dp_atomic_find_vcpi_slots(state, mst_mgr, mst_port, - dm_new_connector_state->pbn); + dm_new_connector_state->pbn, + 0); if (dm_new_connector_state->vcpi_slots < 0) { DRM_DEBUG_ATOMIC("failed finding vcpi slots: %d\n", (int)dm_new_connector_state->vcpi_slots); return dm_new_connector_state->vcpi_slots; @@ -4902,6 +4958,71 @@ const struct drm_encoder_helper_funcs amdgpu_dm_encoder_helper_funcs = { .atomic_check = dm_encoder_helper_atomic_check }; +#if defined(CONFIG_DRM_AMD_DC_DCN) +static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state, + struct dc_state *dc_state) +{ + struct dc_stream_state *stream = NULL; + struct drm_connector *connector; + struct drm_connector_state *new_con_state, *old_con_state; + struct amdgpu_dm_connector *aconnector; + struct dm_connector_state *dm_conn_state; + int i, j, clock, bpp; + int vcpi, pbn_div, pbn = 0; + + for_each_oldnew_connector_in_state(state, connector, old_con_state, new_con_state, i) { + + aconnector = to_amdgpu_dm_connector(connector); + + if (!aconnector->port) + continue; + + if (!new_con_state || !new_con_state->crtc) + continue; + + dm_conn_state = to_dm_connector_state(new_con_state); + + for (j = 0; j < dc_state->stream_count; j++) { + stream = dc_state->streams[j]; + if (!stream) + continue; + + if ((struct amdgpu_dm_connector*)stream->dm_stream_context == aconnector) + break; + + stream = NULL; + } + + if (!stream) + continue; + + if (stream->timing.flags.DSC != 1) { + drm_dp_mst_atomic_enable_dsc(state, + aconnector->port, + dm_conn_state->pbn, + 0, + false); + continue; + } + + pbn_div = dm_mst_get_pbn_divider(stream->link); + bpp = stream->timing.dsc_cfg.bits_per_pixel; + clock = stream->timing.pix_clk_100hz / 10; + pbn = drm_dp_calc_pbn_mode(clock, bpp, true); + vcpi = drm_dp_mst_atomic_enable_dsc(state, + aconnector->port, + pbn, pbn_div, + true); + if (vcpi < 0) + return vcpi; + + dm_conn_state->pbn = pbn; + dm_conn_state->vcpi_slots = vcpi; + } + return 0; +} +#endif + static void dm_drm_plane_reset(struct drm_plane *plane) { struct dm_plane_state *amdgpu_state = NULL; @@ -5564,9 +5685,9 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm, drm_connector_attach_max_bpc_property(&aconnector->base, 8, 16); - /* This defaults to the max in the range, but we want 8bpc. */ - aconnector->base.state->max_bpc = 8; - aconnector->base.state->max_requested_bpc = 8; + /* This defaults to the max in the range, but we want 8bpc for non-edp. */ + aconnector->base.state->max_bpc = (connector_type == DRM_MODE_CONNECTOR_eDP) ? 16 : 8; + aconnector->base.state->max_requested_bpc = aconnector->base.state->max_bpc; if (connector_type == DRM_MODE_CONNECTOR_eDP && dc_is_dmcu_initialized(adev->dm.dc)) { @@ -7641,24 +7762,27 @@ dm_determine_update_type_for_commit(struct amdgpu_display_manager *dm, struct drm_crtc_state *new_crtc_state, *old_crtc_state; struct dm_crtc_state *new_dm_crtc_state, *old_dm_crtc_state; struct dc_stream_status *status = NULL; - - struct dc_surface_update *updates; enum surface_update_type update_type = UPDATE_TYPE_FAST; + struct surface_info_bundle { + struct dc_surface_update surface_updates[MAX_SURFACES]; + struct dc_plane_info plane_infos[MAX_SURFACES]; + struct dc_scaling_info scaling_infos[MAX_SURFACES]; + struct dc_flip_addrs flip_addrs[MAX_SURFACES]; + struct dc_stream_update stream_update; + } *bundle; - updates = kcalloc(MAX_SURFACES, sizeof(*updates), GFP_KERNEL); + bundle = kzalloc(sizeof(*bundle), GFP_KERNEL); - if (!updates) { - DRM_ERROR("Failed to allocate plane updates\n"); + if (!bundle) { + DRM_ERROR("Failed to allocate update bundle\n"); /* Set type to FULL to avoid crashing in DC*/ update_type = UPDATE_TYPE_FULL; goto cleanup; } for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { - struct dc_scaling_info scaling_info; - struct dc_stream_update stream_update; - memset(&stream_update, 0, sizeof(stream_update)); + memset(bundle, 0, sizeof(struct surface_info_bundle)); new_dm_crtc_state = to_dm_crtc_state(new_crtc_state); old_dm_crtc_state = to_dm_crtc_state(old_crtc_state); @@ -7675,8 +7799,9 @@ dm_determine_update_type_for_commit(struct amdgpu_display_manager *dm, for_each_oldnew_plane_in_state(state, plane, old_plane_state, new_plane_state, j) { const struct amdgpu_framebuffer *amdgpu_fb = to_amdgpu_framebuffer(new_plane_state->fb); - struct dc_plane_info plane_info; - struct dc_flip_addrs flip_addr; + struct dc_plane_info *plane_info = &bundle->plane_infos[num_plane]; + struct dc_flip_addrs *flip_addr = &bundle->flip_addrs[num_plane]; + struct dc_scaling_info *scaling_info = &bundle->scaling_infos[num_plane]; uint64_t tiling_flags; new_plane_crtc = new_plane_state->crtc; @@ -7694,49 +7819,48 @@ dm_determine_update_type_for_commit(struct amdgpu_display_manager *dm, if (crtc != new_plane_crtc) continue; - updates[num_plane].surface = new_dm_plane_state->dc_state; + bundle->surface_updates[num_plane].surface = + new_dm_plane_state->dc_state; if (new_crtc_state->mode_changed) { - stream_update.dst = new_dm_crtc_state->stream->dst; - stream_update.src = new_dm_crtc_state->stream->src; + bundle->stream_update.dst = new_dm_crtc_state->stream->dst; + bundle->stream_update.src = new_dm_crtc_state->stream->src; } if (new_crtc_state->color_mgmt_changed) { - updates[num_plane].gamma = + bundle->surface_updates[num_plane].gamma = new_dm_plane_state->dc_state->gamma_correction; - updates[num_plane].in_transfer_func = + bundle->surface_updates[num_plane].in_transfer_func = new_dm_plane_state->dc_state->in_transfer_func; - stream_update.gamut_remap = + bundle->stream_update.gamut_remap = &new_dm_crtc_state->stream->gamut_remap_matrix; - stream_update.output_csc_transform = + bundle->stream_update.output_csc_transform = &new_dm_crtc_state->stream->csc_color_matrix; - stream_update.out_transfer_func = + bundle->stream_update.out_transfer_func = new_dm_crtc_state->stream->out_transfer_func; } ret = fill_dc_scaling_info(new_plane_state, - &scaling_info); + scaling_info); if (ret) goto cleanup; - updates[num_plane].scaling_info = &scaling_info; + bundle->surface_updates[num_plane].scaling_info = scaling_info; if (amdgpu_fb) { ret = get_fb_info(amdgpu_fb, &tiling_flags); if (ret) goto cleanup; - memset(&flip_addr, 0, sizeof(flip_addr)); - ret = fill_dc_plane_info_and_addr( dm->adev, new_plane_state, tiling_flags, - &plane_info, - &flip_addr.address); + plane_info, + &flip_addr->address); if (ret) goto cleanup; - updates[num_plane].plane_info = &plane_info; - updates[num_plane].flip_addr = &flip_addr; + bundle->surface_updates[num_plane].plane_info = plane_info; + bundle->surface_updates[num_plane].flip_addr = flip_addr; } num_plane++; @@ -7757,14 +7881,15 @@ dm_determine_update_type_for_commit(struct amdgpu_display_manager *dm, status = dc_stream_get_status_from_state(old_dm_state->context, new_dm_crtc_state->stream); - stream_update.stream = new_dm_crtc_state->stream; + bundle->stream_update.stream = new_dm_crtc_state->stream; /* * TODO: DC modifies the surface during this call so we need * to lock here - find a way to do this without locking. */ mutex_lock(&dm->dc_lock); - update_type = dc_check_update_surfaces_for_stream(dc, updates, num_plane, - &stream_update, status); + update_type = dc_check_update_surfaces_for_stream( + dc, bundle->surface_updates, num_plane, + &bundle->stream_update, status); mutex_unlock(&dm->dc_lock); if (update_type > UPDATE_TYPE_MED) { @@ -7774,12 +7899,35 @@ dm_determine_update_type_for_commit(struct amdgpu_display_manager *dm, } cleanup: - kfree(updates); + kfree(bundle); *out_type = update_type; return ret; } +static int add_affected_mst_dsc_crtcs(struct drm_atomic_state *state, struct drm_crtc *crtc) +{ + struct drm_connector *connector; + struct drm_connector_state *conn_state; + struct amdgpu_dm_connector *aconnector = NULL; + int i; + for_each_new_connector_in_state(state, connector, conn_state, i) { + if (conn_state->crtc != crtc) + continue; + + aconnector = to_amdgpu_dm_connector(connector); + if (!aconnector->port || !aconnector->mst_port) + aconnector = NULL; + else + break; + } + + if (!aconnector) + return 0; + + return drm_dp_mst_add_affected_dsc_crtcs(state, &aconnector->mst_port->mst_mgr); +} + /** * amdgpu_dm_atomic_check() - Atomic check implementation for AMDgpu DM. * @dev: The DRM device @@ -7832,6 +7980,16 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, if (ret) goto fail; + if (adev->asic_type >= CHIP_NAVI10) { + for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { + if (drm_atomic_crtc_needs_modeset(new_crtc_state)) { + ret = add_affected_mst_dsc_crtcs(state, crtc); + if (ret) + goto fail; + } + } + } + for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { if (!drm_atomic_crtc_needs_modeset(new_crtc_state) && !new_crtc_state->color_mgmt_changed && @@ -7935,11 +8093,6 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, if (ret) goto fail; - /* Perform validation of MST topology in the state*/ - ret = drm_dp_mst_atomic_check(state); - if (ret) - goto fail; - if (state->legacy_cursor_update) { /* * This is a fast cursor update coming from the plane update @@ -8008,6 +8161,25 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, if (ret) goto fail; +#if defined(CONFIG_DRM_AMD_DC_DCN) + if (!compute_mst_dsc_configs_for_state(state, dm_state->context)) + goto fail; + + ret = dm_update_mst_vcpi_slots_for_dsc(state, dm_state->context); + if (ret) + goto fail; +#endif + + /* + * Perform validation of MST topology in the state: + * We need to perform MST atomic check before calling + * dc_validate_global_state(), or there is a chance + * to get stuck in an infinite loop and hang eventually. + */ + ret = drm_dp_mst_atomic_check(state); + if (ret) + goto fail; + if (dc_validate_global_state(dc, dm_state->context, false) != DC_OK) { ret = -EINVAL; goto fail; @@ -8234,17 +8406,38 @@ static bool amdgpu_dm_link_setup_psr(struct dc_stream_state *stream) bool amdgpu_dm_psr_enable(struct dc_stream_state *stream) { struct dc_link *link = stream->link; - struct dc_static_screen_events triggers = {0}; + unsigned int vsync_rate_hz = 0; + struct dc_static_screen_params params = {0}; + /* Calculate number of static frames before generating interrupt to + * enter PSR. + */ + // Init fail safe of 2 frames static + unsigned int num_frames_static = 2; DRM_DEBUG_DRIVER("Enabling psr...\n"); - triggers.cursor_update = true; - triggers.overlay_update = true; - triggers.surface_update = true; + vsync_rate_hz = div64_u64(div64_u64(( + stream->timing.pix_clk_100hz * 100), + stream->timing.v_total), + stream->timing.h_total); + + /* Round up + * Calculate number of frames such that at least 30 ms of time has + * passed. + */ + if (vsync_rate_hz != 0) { + unsigned int frame_time_microsec = 1000000 / vsync_rate_hz; + num_frames_static = (30000 / frame_time_microsec) + 1; + } + + params.triggers.cursor_update = true; + params.triggers.overlay_update = true; + params.triggers.surface_update = true; + params.num_frames = num_frames_static; - dc_stream_set_static_screen_events(link->ctx->dc, + dc_stream_set_static_screen_params(link->ctx->dc, &stream, 1, - &triggers); + ¶ms); return dc_link_set_psr_allow_active(link, true, false); } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index a8fc90a927d6..7ea9acb0358d 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -133,6 +133,13 @@ struct amdgpu_display_manager { struct dmub_srv *dmub_srv; /** + * @dmub_fb_info: + * + * Framebuffer regions for the DMUB. + */ + struct dmub_srv_fb_info *dmub_fb_info; + + /** * @dmub_fw: * * DMUB firmware, required on hardware that has DMUB support. @@ -323,6 +330,7 @@ struct amdgpu_dm_connector { struct drm_dp_mst_port *port; struct amdgpu_dm_connector *mst_port; struct amdgpu_encoder *mst_encoder; + struct drm_dp_aux *dsc_aux; /* TODO see if we can merge with ddc_bus or make a dm_connector */ struct amdgpu_i2c_adapter *i2c; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c index ae329335dfcc..0acd3409dd6c 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c @@ -135,6 +135,20 @@ void hdcp_update_display(struct hdcp_workqueue *hdcp_work, mutex_unlock(&hdcp_w->mutex); } +static void hdcp_remove_display(struct hdcp_workqueue *hdcp_work, + unsigned int link_index, + struct amdgpu_dm_connector *aconnector) +{ + struct hdcp_workqueue *hdcp_w = &hdcp_work[link_index]; + + mutex_lock(&hdcp_w->mutex); + hdcp_w->aconnector = aconnector; + + mod_hdcp_remove_display(&hdcp_w->hdcp, aconnector->base.index, &hdcp_w->output); + + process_output(hdcp_w); + mutex_unlock(&hdcp_w->mutex); +} void hdcp_reset_display(struct hdcp_workqueue *hdcp_work, unsigned int link_index) { struct hdcp_workqueue *hdcp_w = &hdcp_work[link_index]; @@ -303,6 +317,11 @@ static void update_config(void *handle, struct cp_psp_stream_config *config) memset(link, 0, sizeof(*link)); display->index = aconnector->base.index; + + if (config->dpms_off) { + hdcp_remove_display(hdcp_work, link_index, aconnector); + return; + } display->state = MOD_HDCP_DISPLAY_ACTIVE; if (aconnector->dc_sink != NULL) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index 66f266a5e10b..318b474ff20e 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -37,6 +37,7 @@ #include "dc.h" #include "amdgpu_dm.h" #include "amdgpu_dm_irq.h" +#include "amdgpu_dm_mst_types.h" #include "dm_helpers.h" @@ -215,7 +216,8 @@ bool dm_helpers_dp_mst_write_payload_allocation_table( drm_dp_mst_reset_vcpi_slots(mst_mgr, mst_port); } - ret = drm_dp_update_payload_part1(mst_mgr); + /* It's OK for this to fail */ + drm_dp_update_payload_part1(mst_mgr); /* mst_mgr->->payloads are VC payload notify MST branch using DPCD or * AUX message. The sequence is slot 1-63 allocated sequence for each @@ -224,9 +226,6 @@ bool dm_helpers_dp_mst_write_payload_allocation_table( get_payload_table(aconnector, proposed_table); - if (ret) - return false; - return true; } @@ -284,7 +283,6 @@ bool dm_helpers_dp_mst_send_payload_allocation( struct amdgpu_dm_connector *aconnector; struct drm_dp_mst_topology_mgr *mst_mgr; struct drm_dp_mst_port *mst_port; - int ret; aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context; @@ -298,10 +296,8 @@ bool dm_helpers_dp_mst_send_payload_allocation( if (!mst_mgr->mst_state) return false; - ret = drm_dp_update_payload_part2(mst_mgr); - - if (ret) - return false; + /* It's OK for this to fail */ + drm_dp_update_payload_part2(mst_mgr); if (!enable) drm_dp_mst_deallocate_vcpi(mst_mgr, mst_port); @@ -516,8 +512,24 @@ bool dm_helpers_dp_write_dsc_enable( ) { uint8_t enable_dsc = enable ? 1 : 0; + struct amdgpu_dm_connector *aconnector; + + if (!stream) + return false; + + if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) { + aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context; + + if (!aconnector->dsc_aux) + return false; + + return (drm_dp_dpcd_write(aconnector->dsc_aux, DP_DSC_ENABLE, &enable_dsc, 1) >= 0); + } + + if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT) + return dm_helpers_dp_write_dpcd(ctx, stream->link, DP_DSC_ENABLE, &enable_dsc, 1); - return dm_helpers_dp_write_dpcd(ctx, stream->sink->link, DP_DSC_ENABLE, &enable_dsc, 1); + return false; } bool dm_helpers_is_dp_sink_present(struct dc_link *link) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c index 64445c4cc4c2..cbcf504f73a5 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c @@ -111,17 +111,12 @@ static void init_handler_common_data(struct amdgpu_dm_irq_handler_data *hcd, */ static void dm_irq_work_func(struct work_struct *work) { - struct list_head *entry; struct irq_list_head *irq_list_head = container_of(work, struct irq_list_head, work); struct list_head *handler_list = &irq_list_head->head; struct amdgpu_dm_irq_handler_data *handler_data; - list_for_each(entry, handler_list) { - handler_data = list_entry(entry, - struct amdgpu_dm_irq_handler_data, - list); - + list_for_each_entry(handler_data, handler_list, list) { DRM_DEBUG_KMS("DM_IRQ: work_func: for dal_src=%d\n", handler_data->irq_source); @@ -528,19 +523,13 @@ static void amdgpu_dm_irq_immediate_work(struct amdgpu_device *adev, enum dc_irq_source irq_source) { struct amdgpu_dm_irq_handler_data *handler_data; - struct list_head *entry; unsigned long irq_table_flags; DM_IRQ_TABLE_LOCK(adev, irq_table_flags); - list_for_each( - entry, - &adev->dm.irq_handler_list_high_tab[irq_source]) { - - handler_data = list_entry(entry, - struct amdgpu_dm_irq_handler_data, - list); - + list_for_each_entry(handler_data, + &adev->dm.irq_handler_list_high_tab[irq_source], + list) { /* Call a subcomponent which registered for immediate * interrupt notification */ handler_data->handler(handler_data->handler_arg); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 81367c869134..5672f7765919 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -25,6 +25,7 @@ #include <linux/version.h> #include <drm/drm_atomic_helper.h> +#include <drm/drm_dp_mst_helper.h> #include "dm_services.h" #include "amdgpu.h" #include "amdgpu_dm.h" @@ -39,6 +40,12 @@ #if defined(CONFIG_DEBUG_FS) #include "amdgpu_dm_debugfs.h" #endif + + +#if defined(CONFIG_DRM_AMD_DC_DCN) +#include "dc/dcn20/dcn20_resource.h" +#endif + /* #define TRACE_DPCD */ #ifdef TRACE_DPCD @@ -180,6 +187,30 @@ static const struct drm_connector_funcs dm_dp_mst_connector_funcs = { .early_unregister = amdgpu_dm_mst_connector_early_unregister, }; +#if defined(CONFIG_DRM_AMD_DC_DCN) +static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnector) +{ + struct dc_sink *dc_sink = aconnector->dc_sink; + struct drm_dp_mst_port *port = aconnector->port; + u8 dsc_caps[16] = { 0 }; + + aconnector->dsc_aux = drm_dp_mst_dsc_aux_for_port(port); + + if (!aconnector->dsc_aux) + return false; + + if (drm_dp_dpcd_read(aconnector->dsc_aux, DP_DSC_SUPPORT, dsc_caps, 16) < 0) + return false; + + if (!dc_dsc_parse_dsc_dpcd(aconnector->dc_link->ctx->dc, + dsc_caps, NULL, + &dc_sink->sink_dsc_caps.dsc_dec_caps)) + return false; + + return true; +} +#endif + static int dm_dp_mst_get_modes(struct drm_connector *connector) { struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); @@ -222,10 +253,16 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector) /* dc_link_add_remote_sink returns a new reference */ aconnector->dc_sink = dc_sink; - if (aconnector->dc_sink) + if (aconnector->dc_sink) { amdgpu_dm_update_freesync_caps( connector, aconnector->edid); +#if defined(CONFIG_DRM_AMD_DC_DCN) + if (!validate_dsc_caps_on_connector(aconnector)) + memset(&aconnector->dc_sink->sink_dsc_caps, + 0, sizeof(aconnector->dc_sink->sink_dsc_caps)); +#endif + } } drm_connector_update_edid_property( @@ -466,3 +503,384 @@ void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm, aconnector->connector_id); } +int dm_mst_get_pbn_divider(struct dc_link *link) +{ + if (!link) + return 0; + + return dc_link_bandwidth_kbps(link, + dc_link_get_link_cap(link)) / (8 * 1000 * 54); +} + +#if defined(CONFIG_DRM_AMD_DC_DCN) + +struct dsc_mst_fairness_params { + struct dc_crtc_timing *timing; + struct dc_sink *sink; + struct dc_dsc_bw_range bw_range; + bool compression_possible; + struct drm_dp_mst_port *port; +}; + +struct dsc_mst_fairness_vars { + int pbn; + bool dsc_enabled; + int bpp_x16; +}; + +static int kbps_to_peak_pbn(int kbps) +{ + u64 peak_kbps = kbps; + + peak_kbps *= 1006; + peak_kbps = div_u64(peak_kbps, 1000); + return (int) DIV64_U64_ROUND_UP(peak_kbps * 64, (54 * 8 * 1000)); +} + +static void set_dsc_configs_from_fairness_vars(struct dsc_mst_fairness_params *params, + struct dsc_mst_fairness_vars *vars, + int count) +{ + int i; + + for (i = 0; i < count; i++) { + memset(¶ms[i].timing->dsc_cfg, 0, sizeof(params[i].timing->dsc_cfg)); + if (vars[i].dsc_enabled && dc_dsc_compute_config( + params[i].sink->ctx->dc->res_pool->dscs[0], + ¶ms[i].sink->sink_dsc_caps.dsc_dec_caps, + params[i].sink->ctx->dc->debug.dsc_min_slice_height_override, + 0, + params[i].timing, + ¶ms[i].timing->dsc_cfg)) { + params[i].timing->flags.DSC = 1; + params[i].timing->dsc_cfg.bits_per_pixel = vars[i].bpp_x16; + } else { + params[i].timing->flags.DSC = 0; + } + } +} + +static int bpp_x16_from_pbn(struct dsc_mst_fairness_params param, int pbn) +{ + struct dc_dsc_config dsc_config; + u64 kbps; + + kbps = div_u64((u64)pbn * 994 * 8 * 54, 64); + dc_dsc_compute_config( + param.sink->ctx->dc->res_pool->dscs[0], + ¶m.sink->sink_dsc_caps.dsc_dec_caps, + param.sink->ctx->dc->debug.dsc_min_slice_height_override, + (int) kbps, param.timing, &dsc_config); + + return dsc_config.bits_per_pixel; +} + +static void increase_dsc_bpp(struct drm_atomic_state *state, + struct dc_link *dc_link, + struct dsc_mst_fairness_params *params, + struct dsc_mst_fairness_vars *vars, + int count) +{ + int i; + bool bpp_increased[MAX_PIPES]; + int initial_slack[MAX_PIPES]; + int min_initial_slack; + int next_index; + int remaining_to_increase = 0; + int pbn_per_timeslot; + int link_timeslots_used; + int fair_pbn_alloc; + + for (i = 0; i < count; i++) { + if (vars[i].dsc_enabled) { + initial_slack[i] = kbps_to_peak_pbn(params[i].bw_range.max_kbps) - vars[i].pbn; + bpp_increased[i] = false; + remaining_to_increase += 1; + } else { + initial_slack[i] = 0; + bpp_increased[i] = true; + } + } + + pbn_per_timeslot = dc_link_bandwidth_kbps(dc_link, + dc_link_get_link_cap(dc_link)) / (8 * 1000 * 54); + + while (remaining_to_increase) { + next_index = -1; + min_initial_slack = -1; + for (i = 0; i < count; i++) { + if (!bpp_increased[i]) { + if (min_initial_slack == -1 || min_initial_slack > initial_slack[i]) { + min_initial_slack = initial_slack[i]; + next_index = i; + } + } + } + + if (next_index == -1) + break; + + link_timeslots_used = 0; + + for (i = 0; i < count; i++) + link_timeslots_used += DIV_ROUND_UP(vars[i].pbn, pbn_per_timeslot); + + fair_pbn_alloc = (63 - link_timeslots_used) / remaining_to_increase * pbn_per_timeslot; + + if (initial_slack[next_index] > fair_pbn_alloc) { + vars[next_index].pbn += fair_pbn_alloc; + if (drm_dp_atomic_find_vcpi_slots(state, + params[next_index].port->mgr, + params[next_index].port, + vars[next_index].pbn, + dm_mst_get_pbn_divider(dc_link)) < 0) + return; + if (!drm_dp_mst_atomic_check(state)) { + vars[next_index].bpp_x16 = bpp_x16_from_pbn(params[next_index], vars[next_index].pbn); + } else { + vars[next_index].pbn -= fair_pbn_alloc; + if (drm_dp_atomic_find_vcpi_slots(state, + params[next_index].port->mgr, + params[next_index].port, + vars[next_index].pbn, + dm_mst_get_pbn_divider(dc_link)) < 0) + return; + } + } else { + vars[next_index].pbn += initial_slack[next_index]; + if (drm_dp_atomic_find_vcpi_slots(state, + params[next_index].port->mgr, + params[next_index].port, + vars[next_index].pbn, + dm_mst_get_pbn_divider(dc_link)) < 0) + return; + if (!drm_dp_mst_atomic_check(state)) { + vars[next_index].bpp_x16 = params[next_index].bw_range.max_target_bpp_x16; + } else { + vars[next_index].pbn -= initial_slack[next_index]; + if (drm_dp_atomic_find_vcpi_slots(state, + params[next_index].port->mgr, + params[next_index].port, + vars[next_index].pbn, + dm_mst_get_pbn_divider(dc_link)) < 0) + return; + } + } + + bpp_increased[next_index] = true; + remaining_to_increase--; + } +} + +static void try_disable_dsc(struct drm_atomic_state *state, + struct dc_link *dc_link, + struct dsc_mst_fairness_params *params, + struct dsc_mst_fairness_vars *vars, + int count) +{ + int i; + bool tried[MAX_PIPES]; + int kbps_increase[MAX_PIPES]; + int max_kbps_increase; + int next_index; + int remaining_to_try = 0; + + for (i = 0; i < count; i++) { + if (vars[i].dsc_enabled && vars[i].bpp_x16 == params[i].bw_range.max_target_bpp_x16) { + kbps_increase[i] = params[i].bw_range.stream_kbps - params[i].bw_range.max_kbps; + tried[i] = false; + remaining_to_try += 1; + } else { + kbps_increase[i] = 0; + tried[i] = true; + } + } + + while (remaining_to_try) { + next_index = -1; + max_kbps_increase = -1; + for (i = 0; i < count; i++) { + if (!tried[i]) { + if (max_kbps_increase == -1 || max_kbps_increase < kbps_increase[i]) { + max_kbps_increase = kbps_increase[i]; + next_index = i; + } + } + } + + if (next_index == -1) + break; + + vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.stream_kbps); + if (drm_dp_atomic_find_vcpi_slots(state, + params[next_index].port->mgr, + params[next_index].port, + vars[next_index].pbn, + 0) < 0) + return; + + if (!drm_dp_mst_atomic_check(state)) { + vars[next_index].dsc_enabled = false; + vars[next_index].bpp_x16 = 0; + } else { + vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.max_kbps); + if (drm_dp_atomic_find_vcpi_slots(state, + params[next_index].port->mgr, + params[next_index].port, + vars[next_index].pbn, + dm_mst_get_pbn_divider(dc_link)) < 0) + return; + } + + tried[next_index] = true; + remaining_to_try--; + } +} + +static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, + struct dc_state *dc_state, + struct dc_link *dc_link) +{ + int i; + struct dc_stream_state *stream; + struct dsc_mst_fairness_params params[MAX_PIPES]; + struct dsc_mst_fairness_vars vars[MAX_PIPES]; + struct amdgpu_dm_connector *aconnector; + int count = 0; + + memset(params, 0, sizeof(params)); + + /* Set up params */ + for (i = 0; i < dc_state->stream_count; i++) { + struct dc_dsc_policy dsc_policy = {0}; + + stream = dc_state->streams[i]; + + if (stream->link != dc_link) + continue; + + stream->timing.flags.DSC = 0; + + params[count].timing = &stream->timing; + params[count].sink = stream->sink; + aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context; + params[count].port = aconnector->port; + params[count].compression_possible = stream->sink->sink_dsc_caps.dsc_dec_caps.is_dsc_supported; + dc_dsc_get_policy_for_timing(params[count].timing, &dsc_policy); + if (!dc_dsc_compute_bandwidth_range( + stream->sink->ctx->dc->res_pool->dscs[0], + stream->sink->ctx->dc->debug.dsc_min_slice_height_override, + dsc_policy.min_target_bpp, + dsc_policy.max_target_bpp, + &stream->sink->sink_dsc_caps.dsc_dec_caps, + &stream->timing, ¶ms[count].bw_range)) + params[count].bw_range.stream_kbps = dc_bandwidth_in_kbps_from_timing(&stream->timing); + + count++; + } + /* Try no compression */ + for (i = 0; i < count; i++) { + vars[i].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps); + vars[i].dsc_enabled = false; + vars[i].bpp_x16 = 0; + if (drm_dp_atomic_find_vcpi_slots(state, + params[i].port->mgr, + params[i].port, + vars[i].pbn, + 0) < 0) + return false; + } + if (!drm_dp_mst_atomic_check(state)) { + set_dsc_configs_from_fairness_vars(params, vars, count); + return true; + } + + /* Try max compression */ + for (i = 0; i < count; i++) { + if (params[i].compression_possible) { + vars[i].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps); + vars[i].dsc_enabled = true; + vars[i].bpp_x16 = params[i].bw_range.min_target_bpp_x16; + if (drm_dp_atomic_find_vcpi_slots(state, + params[i].port->mgr, + params[i].port, + vars[i].pbn, + dm_mst_get_pbn_divider(dc_link)) < 0) + return false; + } else { + vars[i].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps); + vars[i].dsc_enabled = false; + vars[i].bpp_x16 = 0; + if (drm_dp_atomic_find_vcpi_slots(state, + params[i].port->mgr, + params[i].port, + vars[i].pbn, + 0) < 0) + return false; + } + } + if (drm_dp_mst_atomic_check(state)) + return false; + + /* Optimize degree of compression */ + increase_dsc_bpp(state, dc_link, params, vars, count); + + try_disable_dsc(state, dc_link, params, vars, count); + + set_dsc_configs_from_fairness_vars(params, vars, count); + + return true; +} + +bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, + struct dc_state *dc_state) +{ + int i, j; + struct dc_stream_state *stream; + bool computed_streams[MAX_PIPES]; + struct amdgpu_dm_connector *aconnector; + + for (i = 0; i < dc_state->stream_count; i++) + computed_streams[i] = false; + + for (i = 0; i < dc_state->stream_count; i++) { + stream = dc_state->streams[i]; + + if (stream->signal != SIGNAL_TYPE_DISPLAY_PORT_MST) + continue; + + aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context; + + if (!aconnector || !aconnector->dc_sink) + continue; + + if (!aconnector->dc_sink->sink_dsc_caps.dsc_dec_caps.is_dsc_supported) + continue; + + if (computed_streams[i]) + continue; + + mutex_lock(&aconnector->mst_mgr.lock); + if (!compute_mst_dsc_configs_for_link(state, dc_state, stream->link)) { + mutex_unlock(&aconnector->mst_mgr.lock); + return false; + } + mutex_unlock(&aconnector->mst_mgr.lock); + + for (j = 0; j < dc_state->stream_count; j++) { + if (dc_state->streams[j]->link == stream->link) + computed_streams[j] = true; + } + } + + for (i = 0; i < dc_state->stream_count; i++) { + stream = dc_state->streams[i]; + + if (stream->timing.flags.DSC == 1) + dcn20_add_dsc_to_stream_resource(stream->ctx->dc, dc_state, stream); + } + + return true; +} + +#endif diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h index 2da851b40042..d6813ce67bbd 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h @@ -29,7 +29,14 @@ struct amdgpu_display_manager; struct amdgpu_dm_connector; +int dm_mst_get_pbn_divider(struct dc_link *link); + void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm, struct amdgpu_dm_connector *aconnector); +#if defined(CONFIG_DRM_AMD_DC_DCN) +bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, + struct dc_state *dc_state); +#endif + #endif diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c index 2cb7a4288cb7..c4ba6e84db65 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c @@ -89,6 +89,10 @@ static enum bp_result encoder_control_digx_v1_5( struct bios_parser *bp, struct bp_encoder_control *cntl); +static enum bp_result encoder_control_fallback( + struct bios_parser *bp, + struct bp_encoder_control *cntl); + static void init_dig_encoder_control(struct bios_parser *bp) { uint32_t version = @@ -100,7 +104,7 @@ static void init_dig_encoder_control(struct bios_parser *bp) break; default: dm_output_to_console("Don't have dig_encoder_control for v%d\n", version); - bp->cmd_tbl.dig_encoder_control = NULL; + bp->cmd_tbl.dig_encoder_control = encoder_control_fallback; break; } } @@ -184,6 +188,18 @@ static enum bp_result encoder_control_digx_v1_5( return result; } +static enum bp_result encoder_control_fallback( + struct bios_parser *bp, + struct bp_encoder_control *cntl) +{ + if (bp->base.ctx->dc->ctx->dmub_srv && + bp->base.ctx->dc->debug.dmub_command_table) { + return encoder_control_digx_v1_5(bp, cntl); + } + + return BP_RESULT_FAILURE; +} + /***************************************************************************** ****************************************************************************** ** @@ -196,6 +212,10 @@ static enum bp_result transmitter_control_v1_6( struct bios_parser *bp, struct bp_transmitter_control *cntl); +static enum bp_result transmitter_control_fallback( + struct bios_parser *bp, + struct bp_transmitter_control *cntl); + static void init_transmitter_control(struct bios_parser *bp) { uint8_t frev; @@ -209,7 +229,7 @@ static void init_transmitter_control(struct bios_parser *bp) break; default: dm_output_to_console("Don't have transmitter_control for v%d\n", crev); - bp->cmd_tbl.transmitter_control = NULL; + bp->cmd_tbl.transmitter_control = transmitter_control_fallback; break; } } @@ -273,6 +293,18 @@ static enum bp_result transmitter_control_v1_6( return result; } +static enum bp_result transmitter_control_fallback( + struct bios_parser *bp, + struct bp_transmitter_control *cntl) +{ + if (bp->base.ctx->dc->ctx->dmub_srv && + bp->base.ctx->dc->debug.dmub_command_table) { + return transmitter_control_v1_6(bp, cntl); + } + + return BP_RESULT_FAILURE; +} + /****************************************************************************** ****************************************************************************** ** @@ -285,6 +317,10 @@ static enum bp_result set_pixel_clock_v7( struct bios_parser *bp, struct bp_pixel_clock_parameters *bp_params); +static enum bp_result set_pixel_clock_fallback( + struct bios_parser *bp, + struct bp_pixel_clock_parameters *bp_params); + static void init_set_pixel_clock(struct bios_parser *bp) { switch (BIOS_CMD_TABLE_PARA_REVISION(setpixelclock)) { @@ -294,7 +330,7 @@ static void init_set_pixel_clock(struct bios_parser *bp) default: dm_output_to_console("Don't have set_pixel_clock for v%d\n", BIOS_CMD_TABLE_PARA_REVISION(setpixelclock)); - bp->cmd_tbl.set_pixel_clock = NULL; + bp->cmd_tbl.set_pixel_clock = set_pixel_clock_fallback; break; } } @@ -400,6 +436,18 @@ static enum bp_result set_pixel_clock_v7( return result; } +static enum bp_result set_pixel_clock_fallback( + struct bios_parser *bp, + struct bp_pixel_clock_parameters *bp_params) +{ + if (bp->base.ctx->dc->ctx->dmub_srv && + bp->base.ctx->dc->debug.dmub_command_table) { + return set_pixel_clock_v7(bp, bp_params); + } + + return BP_RESULT_FAILURE; +} + /****************************************************************************** ****************************************************************************** ** @@ -632,6 +680,11 @@ static enum bp_result enable_disp_power_gating_v2_1( enum controller_id crtc_id, enum bp_pipe_control_action action); +static enum bp_result enable_disp_power_gating_fallback( + struct bios_parser *bp, + enum controller_id crtc_id, + enum bp_pipe_control_action action); + static void init_enable_disp_power_gating( struct bios_parser *bp) { @@ -643,7 +696,7 @@ static void init_enable_disp_power_gating( default: dm_output_to_console("Don't enable_disp_power_gating enable_crtc for v%d\n", BIOS_CMD_TABLE_PARA_REVISION(enabledisppowergating)); - bp->cmd_tbl.enable_disp_power_gating = NULL; + bp->cmd_tbl.enable_disp_power_gating = enable_disp_power_gating_fallback; break; } } @@ -695,6 +748,19 @@ static enum bp_result enable_disp_power_gating_v2_1( return result; } +static enum bp_result enable_disp_power_gating_fallback( + struct bios_parser *bp, + enum controller_id crtc_id, + enum bp_pipe_control_action action) +{ + if (bp->base.ctx->dc->ctx->dmub_srv && + bp->base.ctx->dc->debug.dmub_command_table) { + return enable_disp_power_gating_v2_1(bp, crtc_id, action); + } + + return BP_RESULT_FAILURE; +} + /****************************************************************************** ******************************************************************************* ** diff --git a/drivers/gpu/drm/amd/display/dc/calcs/Makefile b/drivers/gpu/drm/amd/display/dc/calcs/Makefile index d0714a3d63c8..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"), @@ -24,7 +25,13 @@ # It calculates Bandwidth and Watermarks values for HW programming # +ifdef CONFIG_X86 calcs_ccflags := -mhard-float -msse +endif + +ifdef CONFIG_PPC64 +calcs_ccflags := -mhard-float -maltivec +endif ifdef CONFIG_CC_IS_GCC ifeq ($(call cc-ifversion, -lt, 0701, y), y) @@ -32,6 +39,7 @@ IS_OLD_GCC = 1 endif endif +ifdef CONFIG_X86 ifdef IS_OLD_GCC # Stack alignment mismatch, proceed with caution. # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 @@ -40,6 +48,7 @@ calcs_ccflags += -mpreferred-stack-boundary=4 else calcs_ccflags += -msse2 endif +endif CFLAGS_$(AMDDALPATH)/dc/calcs/dcn_calcs.o := $(calcs_ccflags) CFLAGS_$(AMDDALPATH)/dc/calcs/dcn_calc_auto.o := $(calcs_ccflags) 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 a1d49256fab7..5d081c42e81b 100644 --- a/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c +++ b/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c @@ -154,14 +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: @@ -286,8 +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) { @@ -338,9 +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); 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 a4ddd657598f..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"), @@ -622,7 +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; @@ -658,7 +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; } @@ -704,8 +705,8 @@ static void hack_bounding_box(struct dcn_bw_internal_vars *v, unsigned int get_highest_allowed_voltage_level(uint32_t hw_internal_rev) { - /* for dali, the highest voltage level we want is 0 */ - if (ASICREV_IS_DALI(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 */ @@ -738,7 +739,7 @@ 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; @@ -1271,7 +1272,7 @@ 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(); @@ -1434,37 +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); @@ -1477,7 +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) @@ -1492,11 +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 @@ -1547,7 +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" @@ -1736,5 +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(); } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile index 3cd283195091..c0f6a8c7de7d 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile @@ -87,6 +87,12 @@ AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCN20) ############################################################################### CLK_MGR_DCN21 = rn_clk_mgr.o rn_clk_mgr_vbios_smu.o +# prevent build errors regarding soft-float vs hard-float FP ABI tags +# this code is currently unused on ppc64, as it applies to Renoir APUs only +ifdef CONFIG_PPC64 +CFLAGS_$(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/clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c index 6d60ef822619..a78e5c74c79c 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c @@ -134,13 +134,13 @@ struct clk_mgr *dc_clk_mgr_create(struct dc_context *ctx, struct pp_smu_funcs *p #if defined(CONFIG_DRM_AMD_DC_DCN) case FAMILY_RV: - if (ASICREV_IS_DALI(asic_id.hw_internal_rev)) { + if (ASICREV_IS_DALI(asic_id.hw_internal_rev) || + ASICREV_IS_POLLOCK(asic_id.hw_internal_rev)) { /* TEMP: this check has to come before ASICREV_IS_RENOIR */ - /* which also incorrectly returns true for Dali */ + /* which also incorrectly returns true for Dali/Pollock*/ rv2_clk_mgr_construct(ctx, clk_mgr, pp_smu); break; } - if (ASICREV_IS_RENOIR(asic_id.hw_internal_rev)) { rn_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg); break; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c index 25d7b7c6681c..49ce46b543ea 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c @@ -27,6 +27,7 @@ #include "clk_mgr_internal.h" #include "dce100/dce_clk_mgr.h" +#include "dcn20_clk_mgr.h" #include "reg_helper.h" #include "core_types.h" #include "dm_helpers.h" @@ -100,13 +101,13 @@ uint32_t dentist_get_did_from_divider(int divider) } void dcn20_update_clocks_update_dpp_dto(struct clk_mgr_internal *clk_mgr, - struct dc_state *context) + struct dc_state *context, bool safe_to_lower) { int i; clk_mgr->dccg->ref_dppclk = clk_mgr->base.clks.dppclk_khz; for (i = 0; i < clk_mgr->base.ctx->dc->res_pool->pipe_count; i++) { - int dpp_inst, dppclk_khz; + int dpp_inst, dppclk_khz, prev_dppclk_khz; /* Loop index will match dpp->inst if resource exists, * and we want to avoid dependency on dpp object @@ -114,8 +115,12 @@ void dcn20_update_clocks_update_dpp_dto(struct clk_mgr_internal *clk_mgr, dpp_inst = i; dppclk_khz = context->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz; - clk_mgr->dccg->funcs->update_dpp_dto( - clk_mgr->dccg, dpp_inst, dppclk_khz); + prev_dppclk_khz = clk_mgr->base.ctx->dc->current_state->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz; + + if ((prev_dppclk_khz > dppclk_khz && safe_to_lower) || prev_dppclk_khz < dppclk_khz) { + clk_mgr->dccg->funcs->update_dpp_dto( + clk_mgr->dccg, dpp_inst, dppclk_khz); + } } } @@ -161,6 +166,9 @@ void dcn2_update_clocks(struct clk_mgr *clk_mgr_base, dc->debug.force_clock_mode & 0x1) { //this is from resume or boot up, if forced_clock cfg option used, we bypass program dispclk and DPPCLK, but need set them for S3. force_reset = true; + + dcn2_read_clocks_from_hw_dentist(clk_mgr_base); + //force_clock_mode 0x1: force reset the clock even it is the same clock as long as it is in Passive level. } display_count = clk_mgr_helper_get_active_display_cnt(dc, context); @@ -240,7 +248,7 @@ void dcn2_update_clocks(struct clk_mgr *clk_mgr_base, if (dc->config.forced_clocks == false || (force_reset && safe_to_lower)) { if (dpp_clock_lowered) { // if clock is being lowered, increase DTO before lowering refclk - dcn20_update_clocks_update_dpp_dto(clk_mgr, context); + dcn20_update_clocks_update_dpp_dto(clk_mgr, context, safe_to_lower); dcn20_update_clocks_update_dentist(clk_mgr); } else { // if clock is being raised, increase refclk before lowering DTO @@ -248,7 +256,7 @@ void dcn2_update_clocks(struct clk_mgr *clk_mgr_base, dcn20_update_clocks_update_dentist(clk_mgr); // always update dtos unless clock is lowered and not safe to lower if (new_clocks->dppclk_khz >= dc->current_state->bw_ctx.bw.dcn.clk.dppclk_khz) - dcn20_update_clocks_update_dpp_dto(clk_mgr, context); + dcn20_update_clocks_update_dpp_dto(clk_mgr, context, safe_to_lower); } } @@ -339,6 +347,32 @@ void dcn2_enable_pme_wa(struct clk_mgr *clk_mgr_base) } } + +void dcn2_read_clocks_from_hw_dentist(struct clk_mgr *clk_mgr_base) +{ + struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base); + uint32_t dispclk_wdivider; + uint32_t dppclk_wdivider; + int disp_divider; + int dpp_divider; + + REG_GET(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_WDIVIDER, &dispclk_wdivider); + REG_GET(DENTIST_DISPCLK_CNTL, DENTIST_DPPCLK_WDIVIDER, &dppclk_wdivider); + + disp_divider = dentist_get_divider_from_did(dispclk_wdivider); + dpp_divider = dentist_get_divider_from_did(dispclk_wdivider); + + if (disp_divider && dpp_divider) { + /* Calculate the current DFS clock, in kHz.*/ + clk_mgr_base->clks.dispclk_khz = (DENTIST_DIVIDER_RANGE_SCALE_FACTOR + * clk_mgr->base.dentist_vco_freq_khz) / disp_divider; + + clk_mgr_base->clks.dppclk_khz = (DENTIST_DIVIDER_RANGE_SCALE_FACTOR + * clk_mgr->base.dentist_vco_freq_khz) / dpp_divider; + } + +} + void dcn2_get_clock(struct clk_mgr *clk_mgr, struct dc_state *context, enum dc_clock_type clock_type, diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.h index c9fd824f3c23..0b9c045b0c8e 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.h +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.h @@ -34,7 +34,7 @@ void dcn2_update_clocks_fpga(struct clk_mgr *clk_mgr, struct dc_state *context, bool safe_to_lower); void dcn20_update_clocks_update_dpp_dto(struct clk_mgr_internal *clk_mgr, - struct dc_state *context); + struct dc_state *context, bool safe_to_lower); void dcn2_init_clocks(struct clk_mgr *clk_mgr); @@ -51,4 +51,8 @@ void dcn2_get_clock(struct clk_mgr *clk_mgr, struct dc_clock_config *clock_cfg); void dcn20_update_clocks_update_dentist(struct clk_mgr_internal *clk_mgr); + +void dcn2_read_clocks_from_hw_dentist(struct clk_mgr *clk_mgr_base); + + #endif //__DCN20_CLK_MGR_H__ 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 de51ef12e33a..9ef3f7b91a1d 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 @@ -59,14 +59,16 @@ int rn_get_active_display_cnt_wa( struct dc_state *context) { int i, display_count; - bool hdmi_present = false; + bool tmds_present = false; display_count = 0; for (i = 0; i < context->stream_count; i++) { const struct dc_stream_state *stream = context->streams[i]; - if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A) - hdmi_present = true; + if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A || + stream->signal == SIGNAL_TYPE_DVI_SINGLE_LINK || + stream->signal == SIGNAL_TYPE_DVI_DUAL_LINK) + tmds_present = true; } for (i = 0; i < dc->link_count; i++) { @@ -85,7 +87,7 @@ int rn_get_active_display_cnt_wa( } /* WA for hang on HDMI after display off back back on*/ - if (display_count == 0 && hdmi_present) + if (display_count == 0 && tmds_present) display_count = 1; return display_count; @@ -149,6 +151,12 @@ void rn_update_clocks(struct clk_mgr *clk_mgr_base, rn_vbios_smu_set_min_deep_sleep_dcfclk(clk_mgr, clk_mgr_base->clks.dcfclk_deep_sleep_khz); } + // workaround: Limit dppclk to 100Mhz to avoid lower eDP panel switch to plus 4K monitor underflow. + if (!IS_DIAG_DC(dc->ctx->dce_environment)) { + if (new_clocks->dppclk_khz < 100000) + new_clocks->dppclk_khz = 100000; + } + if (should_set_clock(safe_to_lower, new_clocks->dppclk_khz, clk_mgr->base.clks.dppclk_khz)) { if (clk_mgr->base.clks.dppclk_khz > new_clocks->dppclk_khz) dpp_clock_lowered = true; @@ -164,16 +172,16 @@ void rn_update_clocks(struct clk_mgr *clk_mgr_base, } if (dpp_clock_lowered) { - // if clock is being lowered, increase DTO before lowering refclk - dcn20_update_clocks_update_dpp_dto(clk_mgr, context); + // increase per DPP DTO before lowering global dppclk + dcn20_update_clocks_update_dpp_dto(clk_mgr, context, safe_to_lower); rn_vbios_smu_set_dppclk(clk_mgr, clk_mgr_base->clks.dppclk_khz); } else { - // if clock is being raised, increase refclk before lowering DTO + // increase global DPPCLK before lowering per DPP DTO if (update_dppclk || update_dispclk) rn_vbios_smu_set_dppclk(clk_mgr, clk_mgr_base->clks.dppclk_khz); // always update dtos unless clock is lowered and not safe to lower if (new_clocks->dppclk_khz >= dc->current_state->bw_ctx.bw.dcn.clk.dppclk_khz) - dcn20_update_clocks_update_dpp_dto(clk_mgr, context); + dcn20_update_clocks_update_dpp_dto(clk_mgr, context, safe_to_lower); } if (update_dispclk && @@ -409,20 +417,20 @@ void build_watermark_ranges(struct clk_bw_params *bw_params, struct pp_smu_wm_ra continue; ranges->reader_wm_sets[num_valid_sets].wm_inst = bw_params->wm_table.entries[i].wm_inst; - ranges->reader_wm_sets[num_valid_sets].wm_type = bw_params->wm_table.entries[i].wm_type;; - /* We will not select WM based on dcfclk, so leave it as unconstrained */ - ranges->reader_wm_sets[num_valid_sets].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN; - ranges->reader_wm_sets[num_valid_sets].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX; - /* fclk wil be used to select WM*/ + ranges->reader_wm_sets[num_valid_sets].wm_type = bw_params->wm_table.entries[i].wm_type; + /* We will not select WM based on fclk, so leave it as unconstrained */ + ranges->reader_wm_sets[num_valid_sets].min_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN; + ranges->reader_wm_sets[num_valid_sets].max_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX; + /* dcfclk wil be used to select WM*/ if (ranges->reader_wm_sets[num_valid_sets].wm_type == WM_TYPE_PSTATE_CHG) { if (i == 0) - ranges->reader_wm_sets[num_valid_sets].min_fill_clk_mhz = 0; + ranges->reader_wm_sets[num_valid_sets].min_drain_clk_mhz = 0; else { /* add 1 to make it non-overlapping with next lvl */ - ranges->reader_wm_sets[num_valid_sets].min_fill_clk_mhz = bw_params->clk_table.entries[i - 1].fclk_mhz + 1; + ranges->reader_wm_sets[num_valid_sets].min_drain_clk_mhz = bw_params->clk_table.entries[i - 1].dcfclk_mhz + 1; } - ranges->reader_wm_sets[num_valid_sets].max_fill_clk_mhz = bw_params->clk_table.entries[i].fclk_mhz; + ranges->reader_wm_sets[num_valid_sets].max_drain_clk_mhz = bw_params->clk_table.entries[i].dcfclk_mhz; } else { /* unconstrained for memory retraining */ diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 39fe38cb39b6..04441dbcba76 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -66,6 +66,9 @@ #include "dce/dce_i2c.h" +#define CTX \ + dc->ctx + #define DC_LOGGER \ dc->ctx->logger @@ -284,7 +287,6 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc, struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i]; if (pipe->stream == stream && pipe->stream_res.tg) { - pipe->stream->adjust = *adjust; dc->hwss.set_drr(&pipe, 1, adjust->v_total_min, @@ -508,10 +510,10 @@ bool dc_stream_program_csc_matrix(struct dc *dc, struct dc_stream_state *stream) return ret; } -void dc_stream_set_static_screen_events(struct dc *dc, +void dc_stream_set_static_screen_params(struct dc *dc, struct dc_stream_state **streams, int num_streams, - const struct dc_static_screen_events *events) + const struct dc_static_screen_params *params) { int i = 0; int j = 0; @@ -530,7 +532,7 @@ void dc_stream_set_static_screen_events(struct dc *dc, } } - dc->hwss.set_static_screen_control(pipes_affected, num_pipes_affected, events); + dc->hwss.set_static_screen_control(pipes_affected, num_pipes_affected, params); } static void dc_destruct(struct dc *dc) @@ -579,6 +581,40 @@ static void dc_destruct(struct dc *dc) } +static bool dc_construct_ctx(struct dc *dc, + const struct dc_init_data *init_params) +{ + struct dc_context *dc_ctx; + enum dce_version dc_version = DCE_VERSION_UNKNOWN; + + dc_ctx = kzalloc(sizeof(*dc_ctx), GFP_KERNEL); + if (!dc_ctx) + return false; + + dc_ctx->cgs_device = init_params->cgs_device; + dc_ctx->driver_context = init_params->driver; + dc_ctx->dc = dc; + dc_ctx->asic_id = init_params->asic_id; + dc_ctx->dc_sink_id_count = 0; + dc_ctx->dc_stream_id_count = 0; + dc_ctx->dce_environment = init_params->dce_environment; + + /* Create logger */ + + dc_version = resource_parse_asic_id(init_params->asic_id); + dc_ctx->dce_version = dc_version; + + dc_ctx->perf_trace = dc_perf_trace_create(); + if (!dc_ctx->perf_trace) { + ASSERT_CRITICAL(false); + return false; + } + + dc->ctx = dc_ctx; + + return true; +} + static bool dc_construct(struct dc *dc, const struct dc_init_data *init_params) { @@ -590,7 +626,6 @@ static bool dc_construct(struct dc *dc, struct dcn_ip_params *dcn_ip; #endif - enum dce_version dc_version = DCE_VERSION_UNKNOWN; dc->config = init_params->flags; // Allocate memory for the vm_helper @@ -636,26 +671,12 @@ static bool dc_construct(struct dc *dc, dc->soc_bounding_box = init_params->soc_bounding_box; #endif - dc_ctx = kzalloc(sizeof(*dc_ctx), GFP_KERNEL); - if (!dc_ctx) { + if (!dc_construct_ctx(dc, init_params)) { dm_error("%s: failed to create ctx\n", __func__); goto fail; } - dc_ctx->cgs_device = init_params->cgs_device; - dc_ctx->driver_context = init_params->driver; - dc_ctx->dc = dc; - dc_ctx->asic_id = init_params->asic_id; - dc_ctx->dc_sink_id_count = 0; - dc_ctx->dc_stream_id_count = 0; - dc->ctx = dc_ctx; - - /* Create logger */ - - dc_ctx->dce_environment = init_params->dce_environment; - - dc_version = resource_parse_asic_id(init_params->asic_id); - dc_ctx->dce_version = dc_version; + dc_ctx = dc->ctx; /* Resource should construct all asic specific resources. * This should be the only place where we need to parse the asic id @@ -670,7 +691,7 @@ static bool dc_construct(struct dc *dc, bp_init_data.bios = init_params->asic_id.atombios_base_address; dc_ctx->dc_bios = dal_bios_parser_create( - &bp_init_data, dc_version); + &bp_init_data, dc_ctx->dce_version); if (!dc_ctx->dc_bios) { ASSERT_CRITICAL(false); @@ -678,17 +699,13 @@ static bool dc_construct(struct dc *dc, } dc_ctx->created_bios = true; - } - - dc_ctx->perf_trace = dc_perf_trace_create(); - if (!dc_ctx->perf_trace) { - ASSERT_CRITICAL(false); - goto fail; } + + /* Create GPIO service */ dc_ctx->gpio_service = dal_gpio_service_create( - dc_version, + dc_ctx->dce_version, dc_ctx->dce_environment, dc_ctx); @@ -697,7 +714,7 @@ static bool dc_construct(struct dc *dc, goto fail; } - dc->res_pool = dc_create_resource_pool(dc, init_params, dc_version); + dc->res_pool = dc_create_resource_pool(dc, init_params, dc_ctx->dce_version); if (!dc->res_pool) goto fail; @@ -728,8 +745,6 @@ static bool dc_construct(struct dc *dc, return true; fail: - - dc_destruct(dc); return false; } @@ -783,6 +798,33 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context) dc_release_state(current_ctx); } +static void wait_for_no_pipes_pending(struct dc *dc, struct dc_state *context) +{ + int i; + int count = 0; + struct pipe_ctx *pipe; + PERF_TRACE(); + for (i = 0; i < MAX_PIPES; i++) { + pipe = &context->res_ctx.pipe_ctx[i]; + + if (!pipe->plane_state) + continue; + + /* Timeout 100 ms */ + while (count < 100000) { + /* Must set to false to start with, due to OR in update function */ + pipe->plane_state->status.is_flip_pending = false; + dc->hwss.update_pending_status(pipe); + if (!pipe->plane_state->status.is_flip_pending) + break; + udelay(1); + count++; + } + ASSERT(!pipe->plane_state->status.is_flip_pending); + } + PERF_TRACE(); +} + /******************************************************************************* * Public functions ******************************************************************************/ @@ -795,28 +837,38 @@ struct dc *dc_create(const struct dc_init_data *init_params) if (NULL == dc) goto alloc_fail; - if (false == dc_construct(dc, init_params)) - goto construct_fail; + if (init_params->dce_environment == DCE_ENV_VIRTUAL_HW) { + if (false == dc_construct_ctx(dc, init_params)) { + dc_destruct(dc); + goto construct_fail; + } + } else { + if (false == dc_construct(dc, init_params)) { + dc_destruct(dc); + goto construct_fail; + } + + full_pipe_count = dc->res_pool->pipe_count; + if (dc->res_pool->underlay_pipe_index != NO_UNDERLAY_PIPE) + full_pipe_count--; + dc->caps.max_streams = min( + full_pipe_count, + dc->res_pool->stream_enc_count); - full_pipe_count = dc->res_pool->pipe_count; - if (dc->res_pool->underlay_pipe_index != NO_UNDERLAY_PIPE) - full_pipe_count--; - dc->caps.max_streams = min( - full_pipe_count, - dc->res_pool->stream_enc_count); + dc->optimize_seamless_boot_streams = 0; + dc->caps.max_links = dc->link_count; + dc->caps.max_audios = dc->res_pool->audio_count; + dc->caps.linear_pitch_alignment = 64; - dc->caps.max_links = dc->link_count; - dc->caps.max_audios = dc->res_pool->audio_count; - dc->caps.linear_pitch_alignment = 64; + dc->caps.max_dp_protocol_version = DP_VERSION_1_4; - dc->caps.max_dp_protocol_version = DP_VERSION_1_4; + if (dc->res_pool->dmcu != NULL) + dc->versions.dmcu_version = dc->res_pool->dmcu->dmcu_version; + } /* Populate versioning information */ dc->versions.dc_ver = DC_VER; - if (dc->res_pool->dmcu != NULL) - dc->versions.dmcu_version = dc->res_pool->dmcu->dmcu_version; - dc->build_id = DC_BUILD_ID; DC_LOG_DC("Display Core initialized\n"); @@ -834,7 +886,8 @@ alloc_fail: void dc_hardware_init(struct dc *dc) { - dc->hwss.init_hw(dc); + if (dc->ctx->dce_environment != DCE_ENV_VIRTUAL_HW) + dc->hwss.init_hw(dc); } void dc_init_callbacks(struct dc *dc, @@ -1148,10 +1201,10 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c for (i = 0; i < context->stream_count; i++) { if (context->streams[i]->apply_seamless_boot_optimization) - dc->optimize_seamless_boot = true; + dc->optimize_seamless_boot_streams++; } - if (!dc->optimize_seamless_boot) + if (dc->optimize_seamless_boot_streams == 0) dc->hwss.prepare_bandwidth(dc, context); /* re-program planes for existing stream, in case we need to @@ -1224,9 +1277,12 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c dc_enable_stereo(dc, context, dc_streams, context->stream_count); - if (!dc->optimize_seamless_boot) - /* pplib is notified if disp_num changed */ - dc->hwss.optimize_bandwidth(dc, context); + if (dc->optimize_seamless_boot_streams == 0) { + /* Must wait for no flips to be pending before doing optimize bw */ + wait_for_no_pipes_pending(dc, context); + /* pplib is notified if disp_num changed */ + dc->hwss.optimize_bandwidth(dc, context); + } for (i = 0; i < context->stream_count; i++) context->streams[i]->mode_changed = false; @@ -1262,12 +1318,18 @@ bool dc_commit_state(struct dc *dc, struct dc_state *context) return (result == DC_OK); } +bool dc_is_hw_initialized(struct dc *dc) +{ + struct dc_bios *dcb = dc->ctx->dc_bios; + return dcb->funcs->is_accelerated_mode(dcb); +} + bool dc_post_update_surfaces_to_stream(struct dc *dc) { int i; struct dc_state *context = dc->current_state; - if (!dc->optimized_required || dc->optimize_seamless_boot) + if (!dc->optimized_required || dc->optimize_seamless_boot_streams > 0) return true; post_surface_trace(dc); @@ -1543,7 +1605,7 @@ static enum surface_update_type get_scaling_info_update_type( update_flags->bits.scaling_change = 1; if (u->scaling_info->src_rect.width > u->surface->src_rect.width - && u->scaling_info->src_rect.height > u->surface->src_rect.height) + || u->scaling_info->src_rect.height > u->surface->src_rect.height) /* Making src rect bigger requires a bandwidth change */ update_flags->bits.clock_change = 1; } @@ -1557,11 +1619,11 @@ static enum surface_update_type get_scaling_info_update_type( update_flags->bits.position_change = 1; if (update_flags->bits.clock_change - || update_flags->bits.bandwidth_change) + || update_flags->bits.bandwidth_change + || update_flags->bits.scaling_change) return UPDATE_TYPE_FULL; - if (update_flags->bits.scaling_change - || update_flags->bits.position_change) + if (update_flags->bits.position_change) return UPDATE_TYPE_MED; return UPDATE_TYPE_FAST; @@ -2051,7 +2113,7 @@ static void commit_planes_do_stream_update(struct dc *dc, dc->hwss.optimize_bandwidth(dc, dc->current_state); } else { - if (!dc->optimize_seamless_boot) + if (dc->optimize_seamless_boot_streams == 0) dc->hwss.prepare_bandwidth(dc, dc->current_state); core_link_enable_stream(dc->current_state, pipe_ctx); @@ -2092,7 +2154,7 @@ static void commit_planes_for_stream(struct dc *dc, int i, j; struct pipe_ctx *top_pipe_to_program = NULL; - if (dc->optimize_seamless_boot && surface_count > 0) { + if (dc->optimize_seamless_boot_streams > 0 && surface_count > 0) { /* Optimize seamless boot flag keeps clocks and watermarks high until * first flip. After first flip, optimization is required to lower * bandwidth. Important to note that it is expected UEFI will @@ -2101,12 +2163,14 @@ static void commit_planes_for_stream(struct dc *dc, */ if (stream->apply_seamless_boot_optimization) { stream->apply_seamless_boot_optimization = false; - dc->optimize_seamless_boot = false; - dc->optimized_required = true; + dc->optimize_seamless_boot_streams--; + + if (dc->optimize_seamless_boot_streams == 0) + dc->optimized_required = true; } } - if (update_type == UPDATE_TYPE_FULL && !dc->optimize_seamless_boot) { + if (update_type == UPDATE_TYPE_FULL && dc->optimize_seamless_boot_streams == 0) { dc->hwss.prepare_bandwidth(dc, context); context_clock_trace(dc, context); } @@ -2398,12 +2462,7 @@ void dc_set_power_state( enum dc_acpi_cm_power_state power_state) { struct kref refcount; - struct display_mode_lib *dml = kzalloc(sizeof(struct display_mode_lib), - GFP_KERNEL); - - ASSERT(dml); - if (!dml) - return; + struct display_mode_lib *dml; switch (power_state) { case DC_ACPI_CM_POWER_STATE_D0: @@ -2426,6 +2485,12 @@ void dc_set_power_state( * clean state, and dc hw programming optimizations will not * cause any trouble. */ + dml = kzalloc(sizeof(struct display_mode_lib), + GFP_KERNEL); + + ASSERT(dml); + if (!dml) + return; /* Preserve refcount */ refcount = dc->current_state->refcount; @@ -2439,10 +2504,10 @@ void dc_set_power_state( dc->current_state->refcount = refcount; dc->current_state->bw_ctx.dml = *dml; + kfree(dml); + break; } - - kfree(dml); } void dc_resume(struct dc *dc) 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 cef8c1ba9797..a09119c10d7c 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -45,6 +45,7 @@ #include "dpcd_defs.h" #include "dmcu.h" #include "hw/clk_mgr.h" +#include "../dce/dmub_psr.h" #define DC_LOGGER_INIT(logger) @@ -817,8 +818,8 @@ static bool dc_link_detect_helper(struct dc_link *link, } case SIGNAL_TYPE_EDP: { - read_current_link_settings_on_detect(link); detect_edp_sink_caps(link); + read_current_link_settings_on_detect(link); sink_caps.transaction_type = DDC_TRANSACTION_TYPE_I2C_OVER_AUX; sink_caps.signal = SIGNAL_TYPE_EDP; break; @@ -850,18 +851,12 @@ static bool dc_link_detect_helper(struct dc_link *link, if (memcmp(&link->dpcd_caps, &prev_dpcd_caps, sizeof(struct dpcd_caps))) same_dpcd = false; } - /* Active dongle plug in without display or downstream unplug*/ + /* Active dongle downstream unplug*/ if (link->type == dc_connection_active_dongle && link->dpcd_caps.sink_count.bits.SINK_COUNT == 0) { - if (prev_sink != NULL) { + if (prev_sink != NULL) /* Downstream unplug */ dc_sink_release(prev_sink); - } else { - /* Empty dongle plug in */ - dp_verify_link_cap_with_retries(link, - &link->reported_link_cap, - LINK_TRAINING_MAX_VERIFY_RETRY); - } return true; } @@ -968,8 +963,7 @@ static bool dc_link_detect_helper(struct dc_link *link, same_edid = is_same_edid(&prev_sink->dc_edid, &sink->dc_edid); if (link->connector_signal == SIGNAL_TYPE_DISPLAY_PORT && - sink_caps.transaction_type == DDC_TRANSACTION_TYPE_I2C_OVER_AUX && - reason != DETECT_REASON_HPDRX) { + sink_caps.transaction_type == DDC_TRANSACTION_TYPE_I2C_OVER_AUX) { /* * TODO debug why Dell 2413 doesn't like * two link trainings @@ -2404,10 +2398,11 @@ bool dc_link_set_psr_allow_active(struct dc_link *link, bool allow_active, bool { struct dc *dc = link->ctx->dc; struct dmcu *dmcu = dc->res_pool->dmcu; + struct dmub_psr *psr = dc->res_pool->psr; - - - if ((dmcu != NULL && dmcu->funcs->is_dmcu_initialized(dmcu)) && link->psr_feature_enabled) + if ((psr != NULL) && link->psr_feature_enabled) + psr->funcs->set_psr_enable(psr, allow_active); + else if ((dmcu != NULL && dmcu->funcs->is_dmcu_initialized(dmcu)) && link->psr_feature_enabled) dmcu->funcs->set_psr_enable(dmcu, allow_active, wait); link->psr_allow_active = allow_active; @@ -2419,8 +2414,11 @@ bool dc_link_get_psr_state(const struct dc_link *link, uint32_t *psr_state) { struct dc *dc = link->ctx->dc; struct dmcu *dmcu = dc->res_pool->dmcu; + struct dmub_psr *psr = dc->res_pool->psr; - if (dmcu != NULL && link->psr_feature_enabled) + if (psr != NULL && link->psr_feature_enabled) + psr->funcs->get_psr_state(psr_state); + else if (dmcu != NULL && link->psr_feature_enabled) dmcu->funcs->get_psr_state(dmcu, psr_state); return true; @@ -2467,6 +2465,7 @@ bool dc_link_setup_psr(struct dc_link *link, { struct dc *dc; struct dmcu *dmcu; + struct dmub_psr *psr; int i; /* updateSinkPsrDpcdConfig*/ union dpcd_psr_configuration psr_configuration; @@ -2478,8 +2477,9 @@ bool dc_link_setup_psr(struct dc_link *link, dc = link->ctx->dc; dmcu = dc->res_pool->dmcu; + psr = dc->res_pool->psr; - if (!dmcu) + if (!dmcu && !psr) return false; @@ -2535,7 +2535,7 @@ bool dc_link_setup_psr(struct dc_link *link, transmitter_to_phy_id(link->link_enc->transmitter); psr_context->crtcTimingVerticalTotal = stream->timing.v_total; - psr_context->vsyncRateHz = div64_u64(div64_u64((stream-> + psr_context->vsync_rate_hz = div64_u64(div64_u64((stream-> timing.pix_clk_100hz * 100), stream->timing.v_total), stream->timing.h_total); @@ -2588,7 +2588,10 @@ bool dc_link_setup_psr(struct dc_link *link, */ psr_context->frame_delay = 0; - link->psr_feature_enabled = dmcu->funcs->setup_psr(dmcu, link, psr_context); + if (psr) + link->psr_feature_enabled = psr->funcs->setup_psr(psr, link, psr_context); + else + link->psr_feature_enabled = dmcu->funcs->setup_psr(dmcu, link, psr_context); /* psr_enabled == 0 indicates setup_psr did not succeed, but this * should not happen since firmware should be running at this point @@ -2863,6 +2866,52 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx) return DC_OK; } + +enum dc_status dc_link_reallocate_mst_payload(struct dc_link *link) +{ + int i; + struct pipe_ctx *pipe_ctx; + + // Clear all of MST payload then reallocate + for (i = 0; i < MAX_PIPES; i++) { + pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i]; + + /* driver enable split pipe for external monitors + * we have to check pipe_ctx is split pipe or not + * If it's split pipe, driver using top pipe to + * reaallocate. + */ + if (!pipe_ctx || pipe_ctx->top_pipe) + continue; + + if (pipe_ctx->stream && pipe_ctx->stream->link == link && + pipe_ctx->stream->dpms_off == false && + pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) { + deallocate_mst_payload(pipe_ctx); + } + } + + for (i = 0; i < MAX_PIPES; i++) { + pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i]; + + if (!pipe_ctx || pipe_ctx->top_pipe) + continue; + + if (pipe_ctx->stream && pipe_ctx->stream->link == link && + pipe_ctx->stream->dpms_off == false && + pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) { + /* enable/disable PHY will clear connection between BE and FE + * need to restore it. + */ + link->link_enc->funcs->connect_dig_be_to_fe(link->link_enc, + pipe_ctx->stream_res.stream_enc->id, true); + dc_link_allocate_mst_payload(pipe_ctx); + } + } + + return DC_OK; +} + #if defined(CONFIG_DRM_AMD_DC_HDCP) static void update_psp_stream_config(struct pipe_ctx *pipe_ctx, bool dpms_off) { @@ -3361,3 +3410,10 @@ const struct dc_link_settings *dc_link_get_link_cap( return &link->preferred_link_setting; return &link->verified_link_cap; } + +void dc_link_overwrite_extended_receiver_cap( + struct dc_link *link) +{ + dp_overwrite_extended_receiver_cap(link); +} + diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c index c2c136b12184..a49c10d5df26 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c @@ -590,7 +590,7 @@ bool dal_ddc_submit_aux_command(struct ddc_service *ddc, struct aux_payload *payload) { uint32_t retrieved = 0; - bool ret = 0; + bool ret = false; if (!ddc) return false; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 42aa889fd0f5..cb731c1d30b1 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -983,7 +983,7 @@ static enum link_training_result perform_clock_recovery_sequence( offset); /* 2. update DPCD of the receiver*/ - if (!retries_cr) + if (!retry_count) /* EPR #361076 - write as a 5-byte burst, * but only for the 1-st iteration.*/ dpcd_set_lt_pattern_and_lane_settings( @@ -1217,24 +1217,33 @@ static void configure_lttpr_mode(struct dc_link *link) uint8_t repeater_cnt; uint32_t aux_interval_address; uint8_t repeater_id; + enum dc_status result = DC_ERROR_UNEXPECTED; uint8_t repeater_mode = DP_PHY_REPEATER_MODE_TRANSPARENT; DC_LOG_HW_LINK_TRAINING("%s\n Set LTTPR to Transparent Mode\n", __func__); - core_link_write_dpcd(link, + result = core_link_write_dpcd(link, DP_PHY_REPEATER_MODE, (uint8_t *)&repeater_mode, sizeof(repeater_mode)); + if (result == DC_OK) { + link->dpcd_caps.lttpr_caps.mode = repeater_mode; + } + if (!link->is_lttpr_mode_transparent) { DC_LOG_HW_LINK_TRAINING("%s\n Set LTTPR to Non Transparent Mode\n", __func__); repeater_mode = DP_PHY_REPEATER_MODE_NON_TRANSPARENT; - core_link_write_dpcd(link, + result = core_link_write_dpcd(link, DP_PHY_REPEATER_MODE, (uint8_t *)&repeater_mode, sizeof(repeater_mode)); + if (result == DC_OK) { + link->dpcd_caps.lttpr_caps.mode = repeater_mode; + } + repeater_cnt = convert_to_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt); for (repeater_id = repeater_cnt; repeater_id > 0; repeater_id--) { aux_interval_address = DP_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1 + @@ -1883,6 +1892,16 @@ bool dp_verify_link_cap( /* disable PHY done possible by BIOS, will be done by driver itself */ dp_disable_link_phy(link, link->connector_signal); + /* Temporary Renoir-specific workaround for SWDEV-215184; + * PHY will sometimes be in bad state on hotplugging display from certain USB-C dongle, + * so add extra cycle of enabling and disabling the PHY before first link training. + */ + if (link->link_enc->features.flags.bits.DP_IS_USB_C && + link->dc->debug.usbc_combo_phy_reset_wa) { + dp_enable_link_phy(link, link->connector_signal, dp_cs_id, cur); + dp_disable_link_phy(link, link->connector_signal); + } + dp_cs_id = get_clock_source_id(link); /* link training starts with the maximum common settings @@ -2854,10 +2873,12 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd /* For now we only handle 'Downstream port status' case. * If we got sink count changed it means * Downstream port status changed, - * then DM should call DC to do the detection. */ - if (hpd_rx_irq_check_link_loss_status( - link, - &hpd_irq_dpcd_data)) { + * then DM should call DC to do the detection. + * NOTE: Do not handle link loss on eDP since it is internal link*/ + if ((link->connector_signal != SIGNAL_TYPE_EDP) && + hpd_rx_irq_check_link_loss_status( + link, + &hpd_irq_dpcd_data)) { /* Connectivity log: link loss */ CONN_DATA_LINK_LOSS(link, hpd_irq_dpcd_data.raw, @@ -2874,18 +2895,14 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd return false; previous_link_settings = link->cur_link_settings; - dp_disable_link_phy(link, pipe_ctx->stream->signal); perform_link_training_with_retries(&previous_link_settings, true, LINK_TRAINING_ATTEMPTS, pipe_ctx, pipe_ctx->stream->signal); - if (pipe_ctx && pipe_ctx->stream && pipe_ctx->stream->link == link && - pipe_ctx->stream->dpms_off == false && - pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) { - dc_link_allocate_mst_payload(pipe_ctx); - } + if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) + dc_link_reallocate_mst_payload(link); status = false; if (out_link_loss) @@ -3267,7 +3284,7 @@ static bool retrieve_link_cap(struct dc_link *link) dpcd_data[DP_TRAINING_AUX_RD_INTERVAL]; link->dpcd_caps.ext_receiver_cap_field_present = - aux_rd_interval.bits.EXT_RECEIVER_CAP_FIELD_PRESENT == 1 ? true:false; + aux_rd_interval.bits.EXT_RECEIVER_CAP_FIELD_PRESENT == 1; if (aux_rd_interval.bits.EXT_RECEIVER_CAP_FIELD_PRESENT == 1) { uint8_t ext_cap_data[16]; @@ -3426,6 +3443,68 @@ static bool retrieve_link_cap(struct dc_link *link) return true; } +bool dp_overwrite_extended_receiver_cap(struct dc_link *link) +{ + uint8_t dpcd_data[16]; + uint32_t read_dpcd_retry_cnt = 3; + enum dc_status status = DC_ERROR_UNEXPECTED; + union dp_downstream_port_present ds_port = { 0 }; + union down_stream_port_count down_strm_port_count; + union edp_configuration_cap edp_config_cap; + + int i; + + for (i = 0; i < read_dpcd_retry_cnt; i++) { + status = core_link_read_dpcd( + link, + DP_DPCD_REV, + dpcd_data, + sizeof(dpcd_data)); + if (status == DC_OK) + break; + } + + link->dpcd_caps.dpcd_rev.raw = + dpcd_data[DP_DPCD_REV - DP_DPCD_REV]; + + if (dpcd_data[DP_MAX_LANE_COUNT - DP_DPCD_REV] == 0) + return false; + + ds_port.byte = dpcd_data[DP_DOWNSTREAMPORT_PRESENT - + DP_DPCD_REV]; + + get_active_converter_info(ds_port.byte, link); + + down_strm_port_count.raw = dpcd_data[DP_DOWN_STREAM_PORT_COUNT - + DP_DPCD_REV]; + + link->dpcd_caps.allow_invalid_MSA_timing_param = + down_strm_port_count.bits.IGNORE_MSA_TIMING_PARAM; + + link->dpcd_caps.max_ln_count.raw = dpcd_data[ + DP_MAX_LANE_COUNT - DP_DPCD_REV]; + + link->dpcd_caps.max_down_spread.raw = dpcd_data[ + DP_MAX_DOWNSPREAD - DP_DPCD_REV]; + + link->reported_link_cap.lane_count = + link->dpcd_caps.max_ln_count.bits.MAX_LANE_COUNT; + link->reported_link_cap.link_rate = dpcd_data[ + DP_MAX_LINK_RATE - DP_DPCD_REV]; + link->reported_link_cap.link_spread = + link->dpcd_caps.max_down_spread.bits.MAX_DOWN_SPREAD ? + LINK_SPREAD_05_DOWNSPREAD_30KHZ : LINK_SPREAD_DISABLED; + + edp_config_cap.raw = dpcd_data[ + DP_EDP_CONFIGURATION_CAP - DP_DPCD_REV]; + link->dpcd_caps.panel_mode_edp = + edp_config_cap.bits.ALT_SCRAMBLER_RESET; + link->dpcd_caps.dpcd_display_control_capable = + edp_config_cap.bits.DPCD_DISPLAY_CONTROL_CAPABLE; + + return true; +} + bool detect_dp_sink_caps(struct dc_link *link) { return retrieve_link_cap(link); @@ -3601,6 +3680,7 @@ static void set_crtc_test_pattern(struct dc_link *link, struct pipe_ctx *odm_pipe; enum controller_dp_color_space controller_color_space; int opp_cnt = 1; + int count; switch (test_pattern_color_space) { case DP_TEST_PATTERN_COLOR_SPACE_RGB: @@ -3644,6 +3724,12 @@ static void set_crtc_test_pattern(struct dc_link *link, NULL, width, height); + /* wait for dpg to blank pixel data with test pattern */ + for (count = 0; count < 1000; count++) { + if (opp->funcs->dpg_is_blanked(opp)) + break; + udelay(100); + } } } break; @@ -3839,8 +3925,38 @@ bool dc_link_dp_set_test_pattern( sizeof(training_pattern)); } } else { - /* CRTC Patterns */ + enum dc_color_space color_space = COLOR_SPACE_UNKNOWN; + + switch (test_pattern_color_space) { + case DP_TEST_PATTERN_COLOR_SPACE_RGB: + color_space = COLOR_SPACE_SRGB; + if (test_pattern == DP_TEST_PATTERN_COLOR_SQUARES_CEA) + color_space = COLOR_SPACE_SRGB_LIMITED; + break; + + case DP_TEST_PATTERN_COLOR_SPACE_YCBCR601: + color_space = COLOR_SPACE_YCBCR601; + if (test_pattern == DP_TEST_PATTERN_COLOR_SQUARES_CEA) + color_space = COLOR_SPACE_YCBCR601_LIMITED; + break; + case DP_TEST_PATTERN_COLOR_SPACE_YCBCR709: + color_space = COLOR_SPACE_YCBCR709; + if (test_pattern == DP_TEST_PATTERN_COLOR_SQUARES_CEA) + color_space = COLOR_SPACE_YCBCR709_LIMITED; + break; + default: + break; + } + /* update MSA to requested color space */ + pipe_ctx->stream_res.stream_enc->funcs->dp_set_stream_attribute(pipe_ctx->stream_res.stream_enc, + &pipe_ctx->stream->timing, + color_space, + pipe_ctx->stream->use_vsc_sdp_for_colorimetry, + link->dpcd_caps.dprx_feature.bits.SST_SPLIT_SDP_CAP); + + /* CRTC Patterns */ set_crtc_test_pattern(link, pipe_ctx, test_pattern, test_pattern_color_space); + /* Set Test Pattern state */ link->test_pattern_enabled = true; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c index 548aac02ca11..ddb855045767 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c @@ -173,15 +173,20 @@ bool edp_receiver_ready_T9(struct dc_link *link) } bool edp_receiver_ready_T7(struct dc_link *link) { - unsigned int tries = 0; unsigned char sinkstatus = 0; unsigned char edpRev = 0; enum dc_status result = DC_OK; + /* use absolute time stamp to constrain max T7*/ + unsigned long long enter_timestamp = 0; + unsigned long long finish_timestamp = 0; + unsigned long long time_taken_in_ns = 0; + result = core_link_read_dpcd(link, DP_EDP_DPCD_REV, &edpRev, sizeof(edpRev)); if (result == DC_OK && edpRev < DP_EDP_12) return true; /* start from eDP version 1.2, SINK_STAUS indicate the sink is ready.*/ + enter_timestamp = dm_get_timestamp(link->ctx); do { sinkstatus = 0; result = core_link_read_dpcd(link, DP_SINK_STATUS, &sinkstatus, sizeof(sinkstatus)); @@ -189,8 +194,10 @@ bool edp_receiver_ready_T7(struct dc_link *link) break; if (result != DC_OK) break; - udelay(25); //MAx T7 is 50ms - } while (++tries < 300); + udelay(25); + finish_timestamp = dm_get_timestamp(link->ctx); + time_taken_in_ns = dm_get_elapse_time_in_ns(link->ctx, finish_timestamp, enter_timestamp); + } while (time_taken_in_ns < 50 * 1000000); //MAx T7 is 50ms if (link->local_sink->edid_caps.panel_patch.extra_t7_ms > 0) udelay(link->local_sink->edid_caps.panel_patch.extra_t7_ms * 1000); @@ -518,6 +525,9 @@ bool dp_set_dsc_pps_sdp(struct pipe_ctx *pipe_ctx, bool enable) struct dsc_config dsc_cfg; uint8_t dsc_packed_pps[128]; + memset(&dsc_cfg, 0, sizeof(dsc_cfg)); + memset(dsc_packed_pps, 0, 128); + /* Enable DSC hw block */ dsc_cfg.pic_width = stream->timing.h_addressable + stream->timing.h_border_left + stream->timing.h_border_right; dsc_cfg.pic_height = stream->timing.v_addressable + stream->timing.v_border_top + stream->timing.v_border_bottom; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 0c19de678339..a0eb9e533a61 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -940,30 +940,43 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx) } -static void calculate_integer_scaling(struct pipe_ctx *pipe_ctx) +/* + * When handling 270 rotation in mixed SLS mode, we have + * stream->timing.h_border_left that is non zero. If we are doing + * pipe-splitting, this h_border_left value gets added to recout.x and when it + * calls calculate_inits_and_adj_vp() and + * adjust_vp_and_init_for_seamless_clip(), it can cause viewport.height for a + * pipe to be incorrect. + * + * To fix this, instead of using stream->timing.h_border_left, we can use + * stream->dst.x to represent the border instead. So we will set h_border_left + * to 0 and shift the appropriate amount in stream->dst.x. We will then + * perform all calculations in resource_build_scaling_params() based on this + * and then restore the h_border_left and stream->dst.x to their original + * values. + * + * shift_border_left_to_dst() will shift the amount of h_border_left to + * stream->dst.x and set h_border_left to 0. restore_border_left_from_dst() + * will restore h_border_left and stream->dst.x back to their original values + * We also need to make sure pipe_ctx->plane_res.scl_data.h_active uses the + * original h_border_left value in its calculation. + */ +int shift_border_left_to_dst(struct pipe_ctx *pipe_ctx) { - unsigned int integer_multiple = 1; - - if (pipe_ctx->plane_state->scaling_quality.integer_scaling) { - // calculate maximum # of replication of src onto addressable - integer_multiple = min( - pipe_ctx->stream->timing.h_addressable / pipe_ctx->stream->src.width, - pipe_ctx->stream->timing.v_addressable / pipe_ctx->stream->src.height); + int store_h_border_left = pipe_ctx->stream->timing.h_border_left; - //scale dst - pipe_ctx->stream->dst.width = integer_multiple * pipe_ctx->stream->src.width; - pipe_ctx->stream->dst.height = integer_multiple * pipe_ctx->stream->src.height; - - //center dst onto addressable - pipe_ctx->stream->dst.x = (pipe_ctx->stream->timing.h_addressable - pipe_ctx->stream->dst.width)/2; - pipe_ctx->stream->dst.y = (pipe_ctx->stream->timing.v_addressable - pipe_ctx->stream->dst.height)/2; - - //We are guaranteed that we are scaling in integer ratio - pipe_ctx->plane_state->scaling_quality.v_taps = 1; - pipe_ctx->plane_state->scaling_quality.h_taps = 1; - pipe_ctx->plane_state->scaling_quality.v_taps_c = 1; - pipe_ctx->plane_state->scaling_quality.h_taps_c = 1; + if (store_h_border_left) { + pipe_ctx->stream->timing.h_border_left = 0; + pipe_ctx->stream->dst.x += store_h_border_left; } + return store_h_border_left; +} + +void restore_border_left_from_dst(struct pipe_ctx *pipe_ctx, + int store_h_border_left) +{ + pipe_ctx->stream->dst.x -= store_h_border_left; + pipe_ctx->stream->timing.h_border_left = store_h_border_left; } bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx) @@ -971,6 +984,7 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx) const struct dc_plane_state *plane_state = pipe_ctx->plane_state; struct dc_crtc_timing *timing = &pipe_ctx->stream->timing; bool res = false; + int store_h_border_left = shift_border_left_to_dst(pipe_ctx); DC_LOGGER_INIT(pipe_ctx->stream->ctx->logger); /* Important: scaling ratio calculation requires pixel format, * lb depth calculation requires recout and taps require scaling ratios. @@ -979,14 +993,18 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx) pipe_ctx->plane_res.scl_data.format = convert_pixel_format_to_dalsurface( pipe_ctx->plane_state->format); - calculate_integer_scaling(pipe_ctx); - calculate_scaling_ratios(pipe_ctx); calculate_viewport(pipe_ctx); - if (pipe_ctx->plane_res.scl_data.viewport.height < 16 || pipe_ctx->plane_res.scl_data.viewport.width < 16) + if (pipe_ctx->plane_res.scl_data.viewport.height < 16 || + pipe_ctx->plane_res.scl_data.viewport.width < 16) { + if (store_h_border_left) { + restore_border_left_from_dst(pipe_ctx, + store_h_border_left); + } return false; + } calculate_recout(pipe_ctx); @@ -999,8 +1017,10 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx) pipe_ctx->plane_res.scl_data.recout.x += timing->h_border_left; pipe_ctx->plane_res.scl_data.recout.y += timing->v_border_top; - pipe_ctx->plane_res.scl_data.h_active = timing->h_addressable + timing->h_border_left + timing->h_border_right; - pipe_ctx->plane_res.scl_data.v_active = timing->v_addressable + timing->v_border_top + timing->v_border_bottom; + pipe_ctx->plane_res.scl_data.h_active = timing->h_addressable + + store_h_border_left + timing->h_border_right; + pipe_ctx->plane_res.scl_data.v_active = timing->v_addressable + + timing->v_border_top + timing->v_border_bottom; /* Taps calculations */ if (pipe_ctx->plane_res.xfm != NULL) @@ -1047,6 +1067,9 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx) plane_state->dst_rect.x, plane_state->dst_rect.y); + if (store_h_border_left) + restore_border_left_from_dst(pipe_ctx, store_h_border_left); + return res; } @@ -1894,8 +1917,26 @@ static int acquire_resource_from_hw_enabled_state( pipe_ctx->plane_res.dpp = pool->dpps[tg_inst]; pipe_ctx->stream_res.opp = pool->opps[tg_inst]; - if (pool->dpps[tg_inst]) + if (pool->dpps[tg_inst]) { pipe_ctx->plane_res.mpcc_inst = pool->dpps[tg_inst]->inst; + + // Read DPP->MPCC->OPP Pipe from HW State + if (pool->mpc->funcs->read_mpcc_state) { + struct mpcc_state s = {0}; + + pool->mpc->funcs->read_mpcc_state(pool->mpc, pipe_ctx->plane_res.mpcc_inst, &s); + + if (s.dpp_id < MAX_MPCC) + pool->mpc->mpcc_array[pipe_ctx->plane_res.mpcc_inst].dpp_id = s.dpp_id; + + if (s.bot_mpcc_id < MAX_MPCC) + pool->mpc->mpcc_array[pipe_ctx->plane_res.mpcc_inst].mpcc_bot = + &pool->mpc->mpcc_array[s.bot_mpcc_id]; + + if (s.opp_id < MAX_OPP) + pipe_ctx->stream_res.opp->mpc_tree_params.opp_id = s.opp_id; + } + } pipe_ctx->pipe_idx = tg_inst; pipe_ctx->stream = stream; @@ -2025,6 +2066,13 @@ void dc_resource_state_construct( dst_ctx->clk_mgr = dc->clk_mgr; } + +bool dc_resource_is_dsc_encoding_supported(const struct dc *dc) +{ + return dc->res_pool->res_cap->num_dsc > 0; +} + + /** * dc_validate_global_state() - Determine if HW can support a given state * Checks HW resource availability and bandwidth requirement. @@ -2281,7 +2329,7 @@ static void set_avi_info_frame( if (color_space == COLOR_SPACE_SRGB || color_space == COLOR_SPACE_2020_RGB_FULLRANGE) { hdmi_info.bits.Q0_Q1 = RGB_QUANTIZATION_FULL_RANGE; - hdmi_info.bits.YQ0_YQ1 = YYC_QUANTIZATION_FULL_RANGE; + hdmi_info.bits.YQ0_YQ1 = YYC_QUANTIZATION_LIMITED_RANGE; } else if (color_space == COLOR_SPACE_SRGB_LIMITED || color_space == COLOR_SPACE_2020_RGB_LIMITEDRANGE) { hdmi_info.bits.Q0_Q1 = RGB_QUANTIZATION_LIMITED_RANGE; @@ -2811,3 +2859,48 @@ unsigned int resource_pixel_format_to_bpp(enum surface_pixel_format format) return -1; } } +static unsigned int get_max_audio_sample_rate(struct audio_mode *modes) +{ + if (modes) { + if (modes->sample_rates.rate.RATE_192) + return 192000; + if (modes->sample_rates.rate.RATE_176_4) + return 176400; + if (modes->sample_rates.rate.RATE_96) + return 96000; + if (modes->sample_rates.rate.RATE_88_2) + return 88200; + if (modes->sample_rates.rate.RATE_48) + return 48000; + if (modes->sample_rates.rate.RATE_44_1) + return 44100; + if (modes->sample_rates.rate.RATE_32) + return 32000; + } + /*original logic when no audio info*/ + return 441000; +} + +void get_audio_check(struct audio_info *aud_modes, + struct audio_check *audio_chk) +{ + unsigned int i; + unsigned int max_sample_rate = 0; + + if (aud_modes) { + audio_chk->audio_packet_type = 0x2;/*audio sample packet AP = .25 for layout0, 1 for layout1*/ + + audio_chk->max_audiosample_rate = 0; + for (i = 0; i < aud_modes->mode_count; i++) { + max_sample_rate = get_max_audio_sample_rate(&aud_modes->modes[i]); + if (audio_chk->max_audiosample_rate < max_sample_rate) + audio_chk->max_audiosample_rate = max_sample_rate; + /*dts takes the same as type 2: AP = 0.25*/ + } + /*check which one take more bandwidth*/ + if (audio_chk->max_audiosample_rate > 192000) + audio_chk->audio_packet_type = 0x9;/*AP =1*/ + audio_chk->acat = 0;/*not support*/ + } +} + diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index b43a4b115fd8..6ddbb00ed37a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -406,25 +406,30 @@ bool dc_stream_add_writeback(struct dc *dc, stream->writeback_info[stream->num_wb_info++] = *wb_info; } - if (!dc->hwss.update_bandwidth(dc, dc->current_state)) { - dm_error("DC: update_bandwidth failed!\n"); - return false; - } - - /* enable writeback */ if (dc->hwss.enable_writeback) { struct dc_stream_status *stream_status = dc_stream_get_status(stream); struct dwbc *dwb = dc->res_pool->dwbc[wb_info->dwb_pipe_inst]; + dwb->otg_inst = stream_status->primary_otg_inst; + } + if (IS_DIAG_DC(dc->ctx->dce_environment)) { + if (!dc->hwss.update_bandwidth(dc, dc->current_state)) { + dm_error("DC: update_bandwidth failed!\n"); + return false; + } - if (dwb->funcs->is_enabled(dwb)) { - /* writeback pipe already enabled, only need to update */ - dc->hwss.update_writeback(dc, stream_status, wb_info, dc->current_state); - } else { - /* Enable writeback pipe from scratch*/ - dc->hwss.enable_writeback(dc, stream_status, wb_info, dc->current_state); + /* enable writeback */ + if (dc->hwss.enable_writeback) { + struct dwbc *dwb = dc->res_pool->dwbc[wb_info->dwb_pipe_inst]; + + if (dwb->funcs->is_enabled(dwb)) { + /* writeback pipe already enabled, only need to update */ + dc->hwss.update_writeback(dc, wb_info, dc->current_state); + } else { + /* Enable writeback pipe from scratch*/ + dc->hwss.enable_writeback(dc, wb_info, dc->current_state); + } } } - return true; } @@ -463,19 +468,29 @@ bool dc_stream_remove_writeback(struct dc *dc, } stream->num_wb_info = j; - /* recalculate and apply DML parameters */ - if (!dc->hwss.update_bandwidth(dc, dc->current_state)) { - dm_error("DC: update_bandwidth failed!\n"); - return false; - } - - /* disable writeback */ - if (dc->hwss.disable_writeback) - dc->hwss.disable_writeback(dc, dwb_pipe_inst); + if (IS_DIAG_DC(dc->ctx->dce_environment)) { + /* recalculate and apply DML parameters */ + if (!dc->hwss.update_bandwidth(dc, dc->current_state)) { + dm_error("DC: update_bandwidth failed!\n"); + return false; + } + /* disable writeback */ + if (dc->hwss.disable_writeback) + dc->hwss.disable_writeback(dc, dwb_pipe_inst); + } return true; } +bool dc_stream_warmup_writeback(struct dc *dc, + int num_dwb, + struct dc_writeback_info *wb_info) +{ + if (dc->hwss.mmhubbub_warmup) + return dc->hwss.mmhubbub_warmup(dc, num_dwb, wb_info); + else + return false; +} uint32_t dc_stream_get_vblank_counter(const struct dc_stream_state *stream) { uint8_t i; diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index c24639080371..8ff25b5dd2f6 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -39,7 +39,7 @@ #include "inc/hw/dmcu.h" #include "dml/display_mode_lib.h" -#define DC_VER "3.2.62" +#define DC_VER "3.2.69" #define MAX_SURFACES 3 #define MAX_PLANES 6 @@ -157,11 +157,14 @@ struct dc_surface_dcc_cap { bool const_color_support; }; -struct dc_static_screen_events { - bool force_trigger; - bool cursor_update; - bool surface_update; - bool overlay_update; +struct dc_static_screen_params { + struct { + bool force_trigger; + bool cursor_update; + bool surface_update; + bool overlay_update; + } triggers; + unsigned int num_frames; }; @@ -367,6 +370,7 @@ struct dc_debug_options { bool disable_hubp_power_gate; bool disable_dsc_power_gate; int dsc_min_slice_height_override; + int dsc_bpp_increment_div; bool native422_support; bool disable_pplib_wm_range; enum wm_report_mode pplib_wm_report_mode; @@ -419,6 +423,9 @@ struct dc_debug_options { bool nv12_iflip_vm_wa; bool disable_dram_clock_change_vactive_support; bool validate_dml_output; + bool enable_dmcub_surface_flip; + bool usbc_combo_phy_reset_wa; + bool disable_dsc; }; struct dc_debug_data { @@ -513,7 +520,7 @@ struct dc { bool optimized_required; /* Require to maintain clocks and bandwidth for UEFI enabled HW */ - bool optimize_seamless_boot; + int optimize_seamless_boot_streams; /* FBC compressor */ struct compressor *fbc_compressor; @@ -909,6 +916,8 @@ void dc_resource_state_copy_construct_current( void dc_resource_state_destruct(struct dc_state *context); +bool dc_resource_is_dsc_encoding_supported(const struct dc *dc); + /* * TODO update to make it about validation sets * Set up streams and links associated to drive sinks @@ -1066,6 +1075,7 @@ unsigned int dc_get_current_backlight_pwm(struct dc *dc); unsigned int dc_get_target_backlight_pwm(struct dc *dc); bool dc_is_dmcu_initialized(struct dc *dc); +bool dc_is_hw_initialized(struct dc *dc); enum dc_status dc_set_clock(struct dc *dc, enum dc_clock_type clock_type, uint32_t clk_khz, uint32_t stepping); void dc_get_clock(struct dc *dc, enum dc_clock_type clock_type, struct dc_clock_config *clock_cfg); diff --git a/drivers/gpu/drm/amd/display/dc/dc_dsc.h b/drivers/gpu/drm/amd/display/dc/dc_dsc.h index 8ec09813ee17..3800340a5b4f 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dsc.h +++ b/drivers/gpu/drm/amd/display/dc/dc_dsc.h @@ -53,7 +53,8 @@ struct dc_dsc_policy { uint32_t min_target_bpp; }; -bool dc_dsc_parse_dsc_dpcd(const uint8_t *dpcd_dsc_basic_data, +bool dc_dsc_parse_dsc_dpcd(const struct dc *dc, + const uint8_t *dpcd_dsc_basic_data, const uint8_t *dpcd_dsc_ext_data, struct dsc_dec_dpcd_caps *dsc_sink_caps); @@ -77,4 +78,6 @@ bool dc_dsc_compute_config( void dc_dsc_get_policy_for_timing(const struct dc_crtc_timing *timing, struct dc_dsc_policy *policy); +void dc_dsc_policy_set_max_target_bpp_limit(uint32_t limit); + #endif diff --git a/drivers/gpu/drm/amd/display/dc/dc_helper.c b/drivers/gpu/drm/amd/display/dc/dc_helper.c index 02a63e9cb62f..737048d8a96c 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_helper.c +++ b/drivers/gpu/drm/amd/display/dc/dc_helper.c @@ -552,6 +552,36 @@ uint32_t generic_read_indirect_reg(const struct dc_context *ctx, return value; } +uint32_t generic_indirect_reg_get(const struct dc_context *ctx, + uint32_t addr_index, uint32_t addr_data, + uint32_t index, int n, + uint8_t shift1, uint32_t mask1, uint32_t *field_value1, + ...) +{ + uint32_t shift, mask, *field_value; + uint32_t value = 0; + int i = 1; + + va_list ap; + + va_start(ap, field_value1); + + value = generic_read_indirect_reg(ctx, addr_index, addr_data, index); + *field_value1 = get_reg_field_value_ex(value, mask1, shift1); + + while (i < n) { + shift = va_arg(ap, uint32_t); + mask = va_arg(ap, uint32_t); + field_value = va_arg(ap, uint32_t *); + + *field_value = get_reg_field_value_ex(value, mask, shift); + i++; + } + + va_end(ap); + + return value; +} uint32_t generic_indirect_reg_update_ex(const struct dc_context *ctx, uint32_t addr_index, uint32_t addr_data, diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h index 1ff79f703734..d25603128394 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_link.h +++ b/drivers/gpu/drm/amd/display/dc/dc_link.h @@ -133,6 +133,7 @@ struct dc_link { struct link_flags { bool dp_keep_receiver_powered; bool dp_skip_DID2; + bool dp_skip_reset_segment; } wa_flags; struct link_mst_stream_allocation_table mst_stream_alloc_table; @@ -204,6 +205,7 @@ enum dc_detect_reason { bool dc_link_detect(struct dc_link *dc_link, enum dc_detect_reason reason); bool dc_link_get_hpd_state(struct dc_link *dc_link); enum dc_status dc_link_allocate_mst_payload(struct pipe_ctx *pipe_ctx); +enum dc_status dc_link_reallocate_mst_payload(struct dc_link *link); /* Notify DC about DP RX Interrupt (aka Short Pulse Interrupt). * Return: @@ -300,6 +302,9 @@ uint32_t dc_link_bandwidth_kbps( const struct dc_link_settings *dc_link_get_link_cap( const struct dc_link *link); +void dc_link_overwrite_extended_receiver_cap( + struct dc_link *link); + bool dc_submit_i2c( struct dc *dc, uint32_t link_index, diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index 3ea54321b045..92096de79dec 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -344,10 +344,17 @@ bool dc_add_all_planes_for_stream( bool dc_stream_add_writeback(struct dc *dc, struct dc_stream_state *stream, struct dc_writeback_info *wb_info); + bool dc_stream_remove_writeback(struct dc *dc, struct dc_stream_state *stream, uint32_t dwb_pipe_inst); + +bool dc_stream_warmup_writeback(struct dc *dc, + int num_dwb, + struct dc_writeback_info *wb_info); + bool dc_stream_dmdata_status_done(struct dc *dc, struct dc_stream_state *stream); + bool dc_stream_set_dynamic_metadata(struct dc *dc, struct dc_stream_state *stream, struct dc_dmdata_attributes *dmdata_attr); @@ -432,10 +439,10 @@ bool dc_stream_get_crc(struct dc *dc, uint32_t *g_y, uint32_t *b_cb); -void dc_stream_set_static_screen_events(struct dc *dc, +void dc_stream_set_static_screen_params(struct dc *dc, struct dc_stream_state **stream, int num_streams, - const struct dc_static_screen_events *events); + const struct dc_static_screen_params *params); void dc_stream_set_dyn_expansion(struct dc *dc, struct dc_stream_state *stream, enum dc_dynamic_expansion option); diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h index 2b92bfa28bde..e59532d98cb4 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_types.h @@ -60,7 +60,12 @@ enum dce_environment { DCE_ENV_FPGA_MAXIMUS, /* Emulation on real HW or on FPGA. Used by Diagnostics, enforces * requirements of Diagnostics team. */ - DCE_ENV_DIAG + DCE_ENV_DIAG, + /* + * Guest VM system, DC HW may exist but is not virtualized and + * should not be used. SW support for VDI only. + */ + DCE_ENV_VIRTUAL_HW }; /* Note: use these macro definitions instead of direct comparison! */ @@ -224,6 +229,7 @@ struct dc_panel_patch { unsigned int extra_t12_ms; unsigned int extra_delay_backlight_off; unsigned int extra_t7_ms; + unsigned int manage_secondary_link; }; struct dc_edid_caps { @@ -598,7 +604,11 @@ struct audio_info { /* this field must be last in this struct */ struct audio_mode modes[DC_MAX_AUDIO_DESC_COUNT]; }; - +struct audio_check { + unsigned int audio_packet_type; + unsigned int max_audiosample_rate; + unsigned int acat; +}; enum dc_infoframe_type { DC_HDMI_INFOFRAME_TYPE_VENDOR = 0x81, DC_HDMI_INFOFRAME_TYPE_AVI = 0x82, @@ -719,7 +729,7 @@ struct psr_context { /* The VSync rate in Hz used to calculate the * step size for smooth brightness feature */ - unsigned int vsyncRateHz; + unsigned int vsync_rate_hz; unsigned int skipPsrWaitForPllLock; unsigned int numberOfControllers; /* Unused, for future use. To indicate that first changed frame from diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c index f1a5d2c6aa37..68c4049cbc2a 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c @@ -400,7 +400,7 @@ static bool acquire( { enum gpio_result result; - if (!is_engine_available(engine)) + if ((engine == NULL) || !is_engine_available(engine)) return false; result = dal_ddc_open(ddc, GPIO_MODE_HARDWARE, diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c index e619e67e6b51..30d953acd016 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c @@ -537,9 +537,6 @@ static void dcn10_dmcu_set_psr_enable(struct dmcu *dmcu, bool enable, bool wait) if (dmcu->dmcu_state != DMCU_RUNNING) return; - dcn10_get_dmcu_psr_state(dmcu, &psr_state); - if (psr_state == 0 && !enable) - return; /* waitDMCUReadyForCmd */ REG_WAIT(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 0, dmcu_wait_reg_ready_interval, diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.c b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.c index 1cd4d8fc361f..066188ba7949 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.c @@ -100,20 +100,6 @@ static uint32_t get_hw_buffer_available_size( dce_i2c_hw->buffer_used_bytes; } -static uint32_t get_speed( - const struct dce_i2c_hw *dce_i2c_hw) -{ - uint32_t pre_scale = 0; - - REG_GET(SPEED, DC_I2C_DDC1_PRESCALE, &pre_scale); - - /* [anaumov] it seems following is unnecessary */ - /*ASSERT(value.bits.DC_I2C_DDC1_PRESCALE);*/ - return pre_scale ? - dce_i2c_hw->reference_frequency / pre_scale : - dce_i2c_hw->default_speed; -} - static void process_channel_reply( struct dce_i2c_hw *dce_i2c_hw, struct i2c_payload *reply) @@ -278,16 +264,25 @@ static void set_speed( struct dce_i2c_hw *dce_i2c_hw, uint32_t speed) { + uint32_t xtal_ref_div = 0; + uint32_t prescale = 0; + + REG_GET(MICROSECOND_TIME_BASE_DIV, XTAL_REF_DIV, &xtal_ref_div); + + if (xtal_ref_div == 0) + xtal_ref_div = 2; + + prescale = ((dce_i2c_hw->reference_frequency * 2) / xtal_ref_div) / speed; if (speed) { if (dce_i2c_hw->masks->DC_I2C_DDC1_START_STOP_TIMING_CNTL) REG_UPDATE_N(SPEED, 3, - FN(DC_I2C_DDC1_SPEED, DC_I2C_DDC1_PRESCALE), dce_i2c_hw->reference_frequency / speed, + FN(DC_I2C_DDC1_SPEED, DC_I2C_DDC1_PRESCALE), prescale, FN(DC_I2C_DDC1_SPEED, DC_I2C_DDC1_THRESHOLD), 2, FN(DC_I2C_DDC1_SPEED, DC_I2C_DDC1_START_STOP_TIMING_CNTL), speed > 50 ? 2:1); else REG_UPDATE_N(SPEED, 2, - FN(DC_I2C_DDC1_SPEED, DC_I2C_DDC1_PRESCALE), dce_i2c_hw->reference_frequency / speed, + FN(DC_I2C_DDC1_SPEED, DC_I2C_DDC1_PRESCALE), prescale, FN(DC_I2C_DDC1_SPEED, DC_I2C_DDC1_THRESHOLD), 2); } } @@ -344,9 +339,7 @@ static void release_engine( bool safe_to_reset; /* Restore original HW engine speed */ - - set_speed(dce_i2c_hw, dce_i2c_hw->original_speed); - + set_speed(dce_i2c_hw, dce_i2c_hw->default_speed); /* Reset HW engine */ { @@ -378,7 +371,6 @@ struct dce_i2c_hw *acquire_i2c_hw_engine( { uint32_t counter = 0; enum gpio_result result; - uint32_t current_speed; struct dce_i2c_hw *dce_i2c_hw = NULL; if (!ddc) @@ -416,11 +408,6 @@ struct dce_i2c_hw *acquire_i2c_hw_engine( dce_i2c_hw->ddc = ddc; - current_speed = get_speed(dce_i2c_hw); - - if (current_speed) - dce_i2c_hw->original_speed = current_speed; - if (!setup_engine(dce_i2c_hw)) { release_engine(dce_i2c_hw); return NULL; @@ -478,13 +465,9 @@ static void submit_channel_request_hw( static uint32_t get_transaction_timeout_hw( const struct dce_i2c_hw *dce_i2c_hw, - uint32_t length) + uint32_t length, + uint32_t speed) { - - uint32_t speed = get_speed(dce_i2c_hw); - - - uint32_t period_timeout; uint32_t num_of_clock_stretches; @@ -504,7 +487,8 @@ static uint32_t get_transaction_timeout_hw( bool dce_i2c_hw_engine_submit_payload( struct dce_i2c_hw *dce_i2c_hw, struct i2c_payload *payload, - bool middle_of_transaction) + bool middle_of_transaction, + uint32_t speed) { struct i2c_request_transaction_data request; @@ -542,7 +526,7 @@ bool dce_i2c_hw_engine_submit_payload( /* obtain timeout value before submitting request */ transaction_timeout = get_transaction_timeout_hw( - dce_i2c_hw, payload->length + 1); + dce_i2c_hw, payload->length + 1, speed); submit_channel_request_hw( dce_i2c_hw, &request); @@ -588,13 +572,11 @@ bool dce_i2c_submit_command_hw( struct i2c_payload *payload = cmd->payloads + index_of_payload; if (!dce_i2c_hw_engine_submit_payload( - dce_i2c_hw, payload, mot)) { + dce_i2c_hw, payload, mot, cmd->speed)) { result = false; break; } - - ++index_of_payload; } @@ -625,7 +607,6 @@ void dce_i2c_hw_construct( dce_i2c_hw->buffer_used_bytes = 0; dce_i2c_hw->transaction_count = 0; dce_i2c_hw->engine_keep_power_up_count = 1; - dce_i2c_hw->original_speed = DEFAULT_I2C_HW_SPEED; dce_i2c_hw->default_speed = DEFAULT_I2C_HW_SPEED; dce_i2c_hw->send_reset_length = 0; dce_i2c_hw->setup_limit = I2C_SETUP_TIME_LIMIT_DCE; @@ -640,9 +621,6 @@ void dce100_i2c_hw_construct( const struct dce_i2c_shift *shifts, const struct dce_i2c_mask *masks) { - - uint32_t xtal_ref_div = 0; - dce_i2c_hw_construct(dce_i2c_hw, ctx, engine_id, @@ -650,21 +628,6 @@ void dce100_i2c_hw_construct( shifts, masks); dce_i2c_hw->buffer_size = I2C_HW_BUFFER_SIZE_DCE100; - - REG_GET(MICROSECOND_TIME_BASE_DIV, XTAL_REF_DIV, &xtal_ref_div); - - if (xtal_ref_div == 0) - xtal_ref_div = 2; - - /*Calculating Reference Clock by divding original frequency by - * XTAL_REF_DIV. - * At upper level, uint32_t reference_frequency = - * dal_dce_i2c_get_reference_clock(as) >> 1 - * which already divided by 2. So we need x2 to get original - * reference clock from ppll_info - */ - dce_i2c_hw->reference_frequency = - (dce_i2c_hw->reference_frequency * 2) / xtal_ref_div; } void dce112_i2c_hw_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.h b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.h index d4b2037f7d74..fb055e6883c0 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.h @@ -256,7 +256,6 @@ struct i2c_request_transaction_data { struct dce_i2c_hw { struct ddc *ddc; - uint32_t original_speed; uint32_t engine_keep_power_up_count; uint32_t transaction_count; uint32_t buffer_used_bytes; diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c new file mode 100644 index 000000000000..225955ec6d39 --- /dev/null +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c @@ -0,0 +1,220 @@ +/* + * Copyright 2019 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 + * + */ + +#include "dmub_psr.h" +#include "dc.h" +#include "dc_dmub_srv.h" +#include "../../dmub/inc/dmub_srv.h" +#include "dmub_fw_state.h" +#include "core_types.h" +#include "ipp.h" + +#define MAX_PIPES 6 + +/** + * Get PSR state from firmware. + */ +static void dmub_get_psr_state(uint32_t *psr_state) +{ + // Not yet implemented + // Trigger GPINT interrupt from firmware +} + +/** + * Enable/Disable PSR. + */ +static void dmub_set_psr_enable(struct dmub_psr *dmub, bool enable) +{ + union dmub_rb_cmd cmd; + struct dc_context *dc = dmub->ctx; + + cmd.psr_enable.header.type = DMUB_CMD__PSR; + + if (enable) + cmd.psr_enable.header.sub_type = DMUB_CMD__PSR_ENABLE; + else + cmd.psr_enable.header.sub_type = DMUB_CMD__PSR_DISABLE; + + cmd.psr_enable.header.payload_bytes = 0; // Send header only + + dc_dmub_srv_cmd_queue(dc->dmub_srv, &cmd.psr_enable.header); + dc_dmub_srv_cmd_execute(dc->dmub_srv); + dc_dmub_srv_wait_idle(dc->dmub_srv); +} + +/** + * Set PSR level. + */ +static void dmub_set_psr_level(struct dmub_psr *dmub, uint16_t psr_level) +{ + union dmub_rb_cmd cmd; + uint32_t psr_state = 0; + struct dc_context *dc = dmub->ctx; + + dmub_get_psr_state(&psr_state); + + if (psr_state == 0) + return; + + cmd.psr_set_level.header.type = DMUB_CMD__PSR; + cmd.psr_set_level.header.sub_type = DMUB_CMD__PSR_SET_LEVEL; + cmd.psr_set_level.header.payload_bytes = sizeof(struct dmub_cmd_psr_set_level_data); + cmd.psr_set_level.psr_set_level_data.psr_level = psr_level; + + dc_dmub_srv_cmd_queue(dc->dmub_srv, &cmd.psr_set_level.header); + dc_dmub_srv_cmd_execute(dc->dmub_srv); + dc_dmub_srv_wait_idle(dc->dmub_srv); +} + +/** + * Setup PSR by programming phy registers and sending psr hw context values to firmware. + */ +static bool dmub_setup_psr(struct dmub_psr *dmub, + struct dc_link *link, + struct psr_context *psr_context) +{ + union dmub_rb_cmd cmd; + struct dc_context *dc = dmub->ctx; + struct dmub_cmd_psr_copy_settings_data *copy_settings_data + = &cmd.psr_copy_settings.psr_copy_settings_data; + struct pipe_ctx *pipe_ctx = NULL; + struct resource_context *res_ctx = &link->ctx->dc->current_state->res_ctx; + + for (int i = 0; i < MAX_PIPES; i++) { + if (res_ctx && + res_ctx->pipe_ctx[i].stream && + res_ctx->pipe_ctx[i].stream->link && + res_ctx->pipe_ctx[i].stream->link == link && + res_ctx->pipe_ctx[i].stream->link->connector_signal == SIGNAL_TYPE_EDP) { + pipe_ctx = &res_ctx->pipe_ctx[i]; + break; + } + } + + if (!pipe_ctx || + !&pipe_ctx->plane_res || + !&pipe_ctx->stream_res) + return false; + + // Program DP DPHY fast training registers + link->link_enc->funcs->psr_program_dp_dphy_fast_training(link->link_enc, + psr_context->psrExitLinkTrainingRequired); + + // Program DP_SEC_CNTL1 register to set transmission GPS0 line num and priority to high + link->link_enc->funcs->psr_program_secondary_packet(link->link_enc, + psr_context->sdpTransmitLineNumDeadline); + + cmd.psr_copy_settings.header.type = DMUB_CMD__PSR; + cmd.psr_copy_settings.header.sub_type = DMUB_CMD__PSR_COPY_SETTINGS; + cmd.psr_copy_settings.header.payload_bytes = sizeof(struct dmub_cmd_psr_copy_settings_data); + + // Hw insts + copy_settings_data->dpphy_inst = psr_context->phyType; + copy_settings_data->aux_inst = psr_context->channel; + copy_settings_data->digfe_inst = psr_context->engineId; + copy_settings_data->digbe_inst = psr_context->transmitterId; + + copy_settings_data->mpcc_inst = pipe_ctx->plane_res.mpcc_inst; + + if (pipe_ctx->plane_res.hubp) + copy_settings_data->hubp_inst = pipe_ctx->plane_res.hubp->inst; + else + copy_settings_data->hubp_inst = 0; + if (pipe_ctx->plane_res.dpp) + copy_settings_data->dpp_inst = pipe_ctx->plane_res.dpp->inst; + else + copy_settings_data->dpp_inst = 0; + if (pipe_ctx->stream_res.opp) + copy_settings_data->opp_inst = pipe_ctx->stream_res.opp->inst; + else + copy_settings_data->opp_inst = 0; + if (pipe_ctx->stream_res.tg) + copy_settings_data->otg_inst = pipe_ctx->stream_res.tg->inst; + else + copy_settings_data->otg_inst = 0; + + // Misc + copy_settings_data->psr_level = psr_context->psr_level.u32all; + copy_settings_data->hyst_frames = psr_context->timehyst_frames; + copy_settings_data->hyst_lines = psr_context->hyst_lines; + copy_settings_data->phy_type = psr_context->phyType; + copy_settings_data->aux_repeat = psr_context->aux_repeats; + copy_settings_data->smu_optimizations_en = psr_context->allow_smu_optimizations; + copy_settings_data->skip_wait_for_pll_lock = psr_context->skipPsrWaitForPllLock; + copy_settings_data->frame_delay = psr_context->frame_delay; + copy_settings_data->smu_phy_id = psr_context->smuPhyId; + copy_settings_data->num_of_controllers = psr_context->numberOfControllers; + copy_settings_data->frame_cap_ind = psr_context->psrFrameCaptureIndicationReq; + copy_settings_data->phy_num = psr_context->frame_delay & 0x7; + copy_settings_data->link_rate = psr_context->frame_delay & 0xF; + + dc_dmub_srv_cmd_queue(dc->dmub_srv, &cmd.psr_copy_settings.header); + dc_dmub_srv_cmd_execute(dc->dmub_srv); + dc_dmub_srv_wait_idle(dc->dmub_srv); + + return true; +} + +static const struct dmub_psr_funcs psr_funcs = { + .set_psr_enable = dmub_set_psr_enable, + .setup_psr = dmub_setup_psr, + .get_psr_state = dmub_get_psr_state, + .set_psr_level = dmub_set_psr_level, +}; + +/** + * Construct PSR object. + */ +static void dmub_psr_construct(struct dmub_psr *psr, struct dc_context *ctx) +{ + psr->ctx = ctx; + psr->funcs = &psr_funcs; +} + +/** + * Allocate and initialize PSR object. + */ +struct dmub_psr *dmub_psr_create(struct dc_context *ctx) +{ + struct dmub_psr *psr = kzalloc(sizeof(struct dmub_psr), GFP_KERNEL); + + if (psr == NULL) { + BREAK_TO_DEBUGGER(); + return NULL; + } + + dmub_psr_construct(psr, ctx); + + return psr; +} + +/** + * Deallocate PSR object. + */ +void dmub_psr_destroy(struct dmub_psr **dmub) +{ + kfree(dmub); + *dmub = NULL; +} diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_fw_state.h b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.h index c87b1ba7590e..229958de3035 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_fw_state.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.h @@ -1,5 +1,5 @@ /* - * Copyright 2019 Advanced Micro Devices, Inc. + * Copyright 2012-16 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"), @@ -23,51 +23,25 @@ * */ -#ifndef _DMUB_FW_STATE_H_ -#define _DMUB_FW_STATE_H_ +#ifndef _DMUB_PSR_H_ +#define _DMUB_PSR_H_ -#include "dmub_types.h" +#include "os_types.h" -#pragma pack(push, 1) - -struct dmub_fw_state { - /** - * @phy_initialized_during_fw_boot: - * - * Detects if VBIOS/VBL has ran before firmware boot. - * A value of 1 will usually mean S0i3 boot. - */ - uint8_t phy_initialized_during_fw_boot; - - /** - * @intialized_phy: - * - * Bit vector of initialized PHY. - */ - uint8_t initialized_phy; - - /** - * @enabled_phy: - * - * Bit vector of enabled PHY for DP alt mode switch tracking. - */ - uint8_t enabled_phy; - - /** - * @dmcu_fw_loaded: - * - * DMCU auto load state. - */ - uint8_t dmcu_fw_loaded; +struct dmub_psr { + struct dc_context *ctx; + const struct dmub_psr_funcs *funcs; +}; - /** - * @psr_state: - * - * PSR state tracking. - */ - uint8_t psr_state; +struct dmub_psr_funcs { + void (*set_psr_enable)(struct dmub_psr *dmub, bool enable); + bool (*setup_psr)(struct dmub_psr *dmub, struct dc_link *link, struct psr_context *psr_context); + void (*get_psr_state)(uint32_t *psr_state); + void (*set_psr_level)(struct dmub_psr *dmub, uint16_t psr_level); }; -#pragma pack(pop) +struct dmub_psr *dmub_psr_create(struct dc_context *ctx); +void dmub_psr_destroy(struct dmub_psr **dmub); + -#endif /* _DMUB_FW_STATE_H_ */ +#endif /* _DCE_DMUB_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 4939cf3b316f..5b689273ff44 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -1373,9 +1373,13 @@ static enum dc_status apply_single_controller_ctx_to_hw( // DRR should set trigger event to monitor surface update event if (stream->adjust.v_total_min != 0 && stream->adjust.v_total_max != 0) event_triggers = 0x80; + /* Event triggers and num frames initialized for DRR, but can be + * later updated for PSR use. Note DRR trigger events are generated + * regardless of whether num frames met. + */ if (pipe_ctx->stream_res.tg->funcs->set_static_screen_control) pipe_ctx->stream_res.tg->funcs->set_static_screen_control( - pipe_ctx->stream_res.tg, event_triggers); + pipe_ctx->stream_res.tg, event_triggers, 2); if (!dc_is_virtual_signal(pipe_ctx->stream->signal)) pipe_ctx->stream_res.stream_enc->funcs->dig_connect_to_otg( @@ -1706,6 +1710,8 @@ static void set_drr(struct pipe_ctx **pipe_ctx, struct drr_params params = {0}; // DRR should set trigger event to monitor surface update event unsigned int event_triggers = 0x80; + // Note DRR trigger events are generated regardless of whether num frames met. + unsigned int num_frames = 2; params.vertical_total_max = vmax; params.vertical_total_min = vmin; @@ -1721,7 +1727,7 @@ static void set_drr(struct pipe_ctx **pipe_ctx, if (vmax != 0 && vmin != 0) pipe_ctx[i]->stream_res.tg->funcs->set_static_screen_control( pipe_ctx[i]->stream_res.tg, - event_triggers); + event_triggers, num_frames); } } @@ -1738,30 +1744,31 @@ static void get_position(struct pipe_ctx **pipe_ctx, } static void set_static_screen_control(struct pipe_ctx **pipe_ctx, - int num_pipes, const struct dc_static_screen_events *events) + int num_pipes, const struct dc_static_screen_params *params) { unsigned int i; - unsigned int value = 0; + unsigned int triggers = 0; - if (events->overlay_update) - value |= 0x100; - if (events->surface_update) - value |= 0x80; - if (events->cursor_update) - value |= 0x2; - if (events->force_trigger) - value |= 0x1; + if (params->triggers.overlay_update) + triggers |= 0x100; + if (params->triggers.surface_update) + triggers |= 0x80; + if (params->triggers.cursor_update) + triggers |= 0x2; + if (params->triggers.force_trigger) + triggers |= 0x1; if (num_pipes) { struct dc *dc = pipe_ctx[0]->stream->ctx->dc; if (dc->fbc_compressor) - value |= 0x84; + triggers |= 0x84; } for (i = 0; i < num_pipes; i++) pipe_ctx[i]->stream_res.tg->funcs-> - set_static_screen_control(pipe_ctx[i]->stream_res.tg, value); + set_static_screen_control(pipe_ctx[i]->stream_res.tg, + triggers, params->num_frames); } /* diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c index 5f7c2c5641c4..1ea7db8eeb98 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c @@ -469,22 +469,27 @@ void dce110_timing_generator_set_drr( void dce110_timing_generator_set_static_screen_control( struct timing_generator *tg, - uint32_t value) + uint32_t event_triggers, + uint32_t num_frames) { struct dce110_timing_generator *tg110 = DCE110TG_FROM_TG(tg); uint32_t static_screen_cntl = 0; uint32_t addr = 0; + // By register spec, it only takes 8 bit value + if (num_frames > 0xFF) + num_frames = 0xFF; + addr = CRTC_REG(mmCRTC_STATIC_SCREEN_CONTROL); static_screen_cntl = dm_read_reg(tg->ctx, addr); set_reg_field_value(static_screen_cntl, - value, + event_triggers, CRTC_STATIC_SCREEN_CONTROL, CRTC_STATIC_SCREEN_EVENT_MASK); set_reg_field_value(static_screen_cntl, - 2, + num_frames, CRTC_STATIC_SCREEN_CONTROL, CRTC_STATIC_SCREEN_FRAME_COUNT); diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.h b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.h index 768ccf27ada9..d8a5ed7b485d 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.h +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.h @@ -231,7 +231,8 @@ void dce110_timing_generator_set_drr( void dce110_timing_generator_set_static_screen_control( struct timing_generator *tg, - uint32_t value); + uint32_t event_triggers, + uint32_t num_frames); void dce110_timing_generator_get_crtc_scanoutpos( struct timing_generator *tg, diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c index 098e56962f2a..82bc4e192bbf 100644 --- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c +++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c @@ -819,13 +819,18 @@ void dce120_tg_set_colors(struct timing_generator *tg, static void dce120_timing_generator_set_static_screen_control( struct timing_generator *tg, - uint32_t value) + uint32_t event_triggers, + uint32_t num_frames) { struct dce110_timing_generator *tg110 = DCE110TG_FROM_TG(tg); + // By register spec, it only takes 8 bit value + if (num_frames > 0xFF) + num_frames = 0xFF; + CRTC_REG_UPDATE_2(CRTC0_CRTC_STATIC_SCREEN_CONTROL, - CRTC_STATIC_SCREEN_EVENT_MASK, value, - CRTC_STATIC_SCREEN_FRAME_COUNT, 2); + CRTC_STATIC_SCREEN_EVENT_MASK, event_triggers, + CRTC_STATIC_SCREEN_FRAME_COUNT, num_frames); } void dce120_timing_generator_set_test_pattern( diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_cm.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_cm.c index 935c892622a0..4d3f7d5e1473 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_cm.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_cm.c @@ -88,26 +88,6 @@ enum dscl_mode_sel { DSCL_MODE_DSCL_BYPASS = 6 }; -static const struct dpp_input_csc_matrix dpp_input_csc_matrix[] = { - {COLOR_SPACE_SRGB, - {0x2000, 0, 0, 0, 0, 0x2000, 0, 0, 0, 0, 0x2000, 0} }, - {COLOR_SPACE_SRGB_LIMITED, - {0x2000, 0, 0, 0, 0, 0x2000, 0, 0, 0, 0, 0x2000, 0} }, - {COLOR_SPACE_YCBCR601, - {0x2cdd, 0x2000, 0, 0xe991, 0xe926, 0x2000, 0xf4fd, 0x10ef, - 0, 0x2000, 0x38b4, 0xe3a6} }, - {COLOR_SPACE_YCBCR601_LIMITED, - {0x3353, 0x2568, 0, 0xe400, 0xe5dc, 0x2568, 0xf367, 0x1108, - 0, 0x2568, 0x40de, 0xdd3a} }, - {COLOR_SPACE_YCBCR709, - {0x3265, 0x2000, 0, 0xe6ce, 0xf105, 0x2000, 0xfa01, 0xa7d, 0, - 0x2000, 0x3b61, 0xe24f} }, - - {COLOR_SPACE_YCBCR709_LIMITED, - {0x39a6, 0x2568, 0, 0xe0d6, 0xeedd, 0x2568, 0xf925, 0x9a8, 0, - 0x2568, 0x43ee, 0xdbb2} } -}; - static void program_gamut_remap( struct dcn10_dpp *dpp, const uint16_t *regval, diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c index a02c10e23e0d..f36a0d8cedfe 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c @@ -930,6 +930,9 @@ static bool hubbub1_get_dcc_compression_cap(struct hubbub *hubbub, output->grph.rgb.max_compressed_blk_size = 64; output->grph.rgb.independent_64b_blks = true; break; + default: + ASSERT(false); + break; } output->capable = true; 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 4d1301e5eaf5..31b64733d693 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c @@ -810,8 +810,7 @@ static void hubp1_set_vm_context0_settings(struct hubp *hubp, void min_set_viewport( struct hubp *hubp, const struct rect *viewport, - const struct rect *viewport_c, - enum dc_rotation_angle rotation) + const struct rect *viewport_c) { struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp); 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 e44eaae5033b..780af5b3c16f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h @@ -749,9 +749,7 @@ void hubp1_set_blank(struct hubp *hubp, bool blank); void min_set_viewport(struct hubp *hubp, const struct rect *viewport, - const struct rect *viewport_c, - enum dc_rotation_angle rotation); -/* rotation angle added for use by hubp21_set_viewport */ + const struct rect *viewport_c); void hubp1_clk_cntl(struct hubp *hubp, bool enable); void hubp1_vtg_sel(struct hubp *hubp, uint32_t otg_inst); 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 3996fef56948..1008ac8a0f2a 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 @@ -479,10 +479,10 @@ void dcn10_enable_power_gating_plane( struct dce_hwseq *hws, bool enable) { - bool force_on = 1; /* disable power gating */ + bool force_on = true; /* disable power gating */ if (enable) - force_on = 0; + force_on = false; /* DCHUBP0/1/2/3 */ REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN0_POWER_FORCEON, force_on); @@ -860,6 +860,7 @@ static void dcn10_reset_back_end_for_pipe( struct dc_state *context) { int i; + struct dc_link *link; DC_LOGGER_INIT(dc->ctx->logger); if (pipe_ctx->stream_res.stream_enc == NULL) { pipe_ctx->stream = NULL; @@ -867,8 +868,14 @@ static void dcn10_reset_back_end_for_pipe( } if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) { - /* DPMS may already disable */ - if (!pipe_ctx->stream->dpms_off) + link = pipe_ctx->stream->link; + /* DPMS may already disable or */ + /* dpms_off status is incorrect due to fastboot + * feature. When system resume from S4 with second + * screen only, the dpms_off would be true but + * VBIOS lit up eDP, so check link status too. + */ + if (!pipe_ctx->stream->dpms_off || link->link_status.link_active) core_link_disable_stream(pipe_ctx); else if (pipe_ctx->stream_res.audio) dc->hwss.disable_audio_stream(pipe_ctx); @@ -1156,7 +1163,8 @@ void dcn10_init_pipes(struct dc *dc, struct dc_state *context) } } - for (i = 0; i < dc->res_pool->pipe_count; i++) { + /* num_opp will be equal to number of mpcc */ + for (i = 0; i < dc->res_pool->res_cap->num_opp; i++) { struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; /* Cannot reset the MPC mux if seamless boot */ @@ -1180,8 +1188,14 @@ void dcn10_init_pipes(struct dc *dc, struct dc_state *context) if (can_apply_seamless_boot && pipe_ctx->stream != NULL && pipe_ctx->stream_res.tg->funcs->is_tg_enabled( - pipe_ctx->stream_res.tg)) + pipe_ctx->stream_res.tg)) { + // Enable double buffering for OTG_BLANK no matter if + // seamless boot is enabled or not to suppress global sync + // signals when OTG blanked. This is to prevent pipe from + // requesting data while in PSR. + tg->funcs->tg_init(tg); continue; + } /* Disable on the current state so the new one isn't cleared. */ pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i]; @@ -2291,8 +2305,7 @@ static void dcn10_update_dchubp_dpp( hubp->funcs->mem_program_viewport( hubp, &pipe_ctx->plane_res.scl_data.viewport, - &pipe_ctx->plane_res.scl_data.viewport_c, - plane_state->rotation); + &pipe_ctx->plane_res.scl_data.viewport_c); } if (pipe_ctx->stream->cursor_attributes.address.quad_part != 0) { @@ -2697,6 +2710,8 @@ void dcn10_set_drr(struct pipe_ctx **pipe_ctx, struct drr_params params = {0}; // DRR set trigger event mapped to OTG_TRIG_A (bit 11) for manual control flow unsigned int event_triggers = 0x800; + // Note DRR trigger events are generated regardless of whether num frames met. + unsigned int num_frames = 2; params.vertical_total_max = vmax; params.vertical_total_min = vmin; @@ -2713,7 +2728,7 @@ void dcn10_set_drr(struct pipe_ctx **pipe_ctx, if (vmax != 0 && vmin != 0) pipe_ctx[i]->stream_res.tg->funcs->set_static_screen_control( pipe_ctx[i]->stream_res.tg, - event_triggers); + event_triggers, num_frames); } } @@ -2730,21 +2745,22 @@ void dcn10_get_position(struct pipe_ctx **pipe_ctx, } void dcn10_set_static_screen_control(struct pipe_ctx **pipe_ctx, - int num_pipes, const struct dc_static_screen_events *events) + int num_pipes, const struct dc_static_screen_params *params) { unsigned int i; - unsigned int value = 0; + unsigned int triggers = 0; - if (events->surface_update) - value |= 0x80; - if (events->cursor_update) - value |= 0x2; - if (events->force_trigger) - value |= 0x1; + if (params->triggers.surface_update) + triggers |= 0x80; + if (params->triggers.cursor_update) + triggers |= 0x2; + if (params->triggers.force_trigger) + triggers |= 0x1; for (i = 0; i < num_pipes; i++) pipe_ctx[i]->stream_res.tg->funcs-> - set_static_screen_control(pipe_ctx[i]->stream_res.tg, value); + set_static_screen_control(pipe_ctx[i]->stream_res.tg, + triggers, params->num_frames); } static void dcn10_config_stereo_parameters( @@ -2895,6 +2911,33 @@ void dcn10_update_dchub(struct dce_hwseq *hws, struct dchub_init_data *dh_data) hubbub->funcs->update_dchub(hubbub, dh_data); } +static bool dcn10_can_pipe_disable_cursor(struct pipe_ctx *pipe_ctx) +{ + struct pipe_ctx *test_pipe; + const struct rect *r1 = &pipe_ctx->plane_res.scl_data.recout, *r2; + int r1_r = r1->x + r1->width, r1_b = r1->y + r1->height, r2_r, r2_b; + + /** + * Disable the cursor if there's another pipe above this with a + * plane that contains this pipe's viewport to prevent double cursor + * and incorrect scaling artifacts. + */ + for (test_pipe = pipe_ctx->top_pipe; test_pipe; + test_pipe = test_pipe->top_pipe) { + if (!test_pipe->plane_state->visible) + continue; + + r2 = &test_pipe->plane_res.scl_data.recout; + r2_r = r2->x + r2->width; + r2_b = r2->y + r2->height; + + if (r1->x >= r2->x && r1->y >= r2->y && r1_r <= r2_r && r1_b <= r2_b) + return true; + } + + return false; +} + void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) { struct dc_cursor_position pos_cpy = pipe_ctx->stream->cursor_position; @@ -2909,6 +2952,8 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) .rotation = pipe_ctx->plane_state->rotation, .mirror = pipe_ctx->plane_state->horizontal_mirror }; + bool pipe_split_on = (pipe_ctx->top_pipe != NULL) || + (pipe_ctx->bottom_pipe != NULL); int x_plane = pipe_ctx->plane_state->dst_rect.x; int y_plane = pipe_ctx->plane_state->dst_rect.y; @@ -2938,9 +2983,13 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) == PLN_ADDR_TYPE_VIDEO_PROGRESSIVE) pos_cpy.enable = false; + if (pos_cpy.enable && dcn10_can_pipe_disable_cursor(pipe_ctx)) + pos_cpy.enable = false; + // Swap axis and mirror horizontally if (param.rotation == ROTATION_ANGLE_90) { uint32_t temp_x = pos_cpy.x; + pos_cpy.x = pipe_ctx->plane_res.scl_data.viewport.width - (pos_cpy.y - pipe_ctx->plane_res.scl_data.viewport.x) + pipe_ctx->plane_res.scl_data.viewport.x; pos_cpy.y = temp_x; @@ -2948,26 +2997,44 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) // Swap axis and mirror vertically else if (param.rotation == ROTATION_ANGLE_270) { uint32_t temp_y = pos_cpy.y; - if (pos_cpy.x > pipe_ctx->plane_res.scl_data.viewport.height) { - pos_cpy.x = pos_cpy.x - pipe_ctx->plane_res.scl_data.viewport.height; - pos_cpy.y = pipe_ctx->plane_res.scl_data.viewport.height - pos_cpy.x; - } else { - pos_cpy.y = 2 * pipe_ctx->plane_res.scl_data.viewport.height - pos_cpy.x; - } + int viewport_height = + pipe_ctx->plane_res.scl_data.viewport.height; + + if (pipe_split_on) { + if (pos_cpy.x > viewport_height) { + pos_cpy.x = pos_cpy.x - viewport_height; + pos_cpy.y = viewport_height - pos_cpy.x; + } else { + pos_cpy.y = 2 * viewport_height - pos_cpy.x; + } + } else + pos_cpy.y = viewport_height - pos_cpy.x; pos_cpy.x = temp_y; } // Mirror horizontally and vertically else if (param.rotation == ROTATION_ANGLE_180) { - if (pos_cpy.x >= pipe_ctx->plane_res.scl_data.viewport.width + pipe_ctx->plane_res.scl_data.viewport.x) { - pos_cpy.x = 2 * pipe_ctx->plane_res.scl_data.viewport.width - - pos_cpy.x + 2 * pipe_ctx->plane_res.scl_data.viewport.x; - } else { - uint32_t temp_x = pos_cpy.x; - pos_cpy.x = 2 * pipe_ctx->plane_res.scl_data.viewport.x - pos_cpy.x; - if (temp_x >= pipe_ctx->plane_res.scl_data.viewport.x + (int)hubp->curs_attr.width - || pos_cpy.x <= (int)hubp->curs_attr.width + pipe_ctx->plane_state->src_rect.x) { - pos_cpy.x = temp_x + pipe_ctx->plane_res.scl_data.viewport.width; + int viewport_width = + pipe_ctx->plane_res.scl_data.viewport.width; + int viewport_x = + pipe_ctx->plane_res.scl_data.viewport.x; + + if (pipe_split_on) { + if (pos_cpy.x >= viewport_width + viewport_x) { + pos_cpy.x = 2 * viewport_width + - pos_cpy.x + 2 * viewport_x; + } else { + uint32_t temp_x = pos_cpy.x; + + pos_cpy.x = 2 * viewport_x - pos_cpy.x; + if (temp_x >= viewport_x + + (int)hubp->curs_attr.width || pos_cpy.x + <= (int)hubp->curs_attr.width + + pipe_ctx->plane_state->src_rect.x) { + pos_cpy.x = temp_x + viewport_width; + } } + } else { + pos_cpy.x = viewport_width - pos_cpy.x + 2 * viewport_x; } pos_cpy.y = pipe_ctx->plane_res.scl_data.viewport.height - pos_cpy.y; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h index 55b8f3b2fc4e..4d20f6586bb5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h @@ -132,7 +132,7 @@ void dcn10_get_position(struct pipe_ctx **pipe_ctx, int num_pipes, struct crtc_position *position); void dcn10_set_static_screen_control(struct pipe_ctx **pipe_ctx, - int num_pipes, const struct dc_static_screen_events *events); + int num_pipes, const struct dc_static_screen_params *params); void dcn10_setup_stereo(struct pipe_ctx *pipe_ctx, struct dc *dc); void dce110_set_avmute(struct pipe_ctx *pipe_ctx, bool enable); void dcn10_log_hw_state(struct dc *dc, diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h index 7493a630f4dc..eb13589b9a81 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h @@ -124,6 +124,26 @@ struct dcn10_link_enc_registers { uint32_t RDPCSTX_PHY_CNTL13; uint32_t RDPCSTX_PHY_CNTL14; uint32_t RDPCSTX_PHY_CNTL15; + uint32_t RDPCSTX_CNTL; + uint32_t RDPCSTX_CLOCK_CNTL; + uint32_t RDPCSTX_PHY_CNTL0; + uint32_t RDPCSTX_PHY_CNTL2; + uint32_t RDPCSTX_PLL_UPDATE_DATA; + uint32_t RDPCS_TX_CR_ADDR; + uint32_t RDPCS_TX_CR_DATA; + uint32_t DPCSTX_TX_CLOCK_CNTL; + uint32_t DPCSTX_TX_CNTL; + uint32_t RDPCSTX_INTERRUPT_CONTROL; + uint32_t RDPCSTX_PHY_FUSE0; + uint32_t RDPCSTX_PHY_FUSE1; + uint32_t RDPCSTX_PHY_FUSE2; + uint32_t RDPCSTX_PHY_FUSE3; + uint32_t RDPCSTX_PHY_RX_LD_VAL; + uint32_t DPCSTX_DEBUG_CONFIG; + uint32_t RDPCSTX_DEBUG_CONFIG; + uint32_t RDPCSTX0_RDPCSTX_SCRATCH; + uint32_t RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG; + uint32_t DCIO_SOFT_RESET; /* indirect registers */ uint32_t RAWLANE0_DIG_PCS_XF_RX_OVRD_IN_2; uint32_t RAWLANE0_DIG_PCS_XF_RX_OVRD_IN_3; diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c index cd7412dc42d1..a9a43b397db9 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c @@ -789,21 +789,26 @@ void optc1_set_early_control( void optc1_set_static_screen_control( struct timing_generator *optc, - uint32_t value) + uint32_t event_triggers, + uint32_t num_frames) { struct optc *optc1 = DCN10TG_FROM_TG(optc); + // By register spec, it only takes 8 bit value + if (num_frames > 0xFF) + num_frames = 0xFF; + /* Bit 8 is no longer applicable in RV for PSR case, * set bit 8 to 0 if given */ - if ((value & STATIC_SCREEN_EVENT_MASK_RANGETIMING_DOUBLE_BUFFER_UPDATE_EN) + if ((event_triggers & STATIC_SCREEN_EVENT_MASK_RANGETIMING_DOUBLE_BUFFER_UPDATE_EN) != 0) - value = value & + event_triggers = event_triggers & ~STATIC_SCREEN_EVENT_MASK_RANGETIMING_DOUBLE_BUFFER_UPDATE_EN; REG_SET_2(OTG_STATIC_SCREEN_CONTROL, 0, - OTG_STATIC_SCREEN_EVENT_MASK, value, - OTG_STATIC_SCREEN_FRAME_COUNT, 2); + OTG_STATIC_SCREEN_EVENT_MASK, event_triggers, + OTG_STATIC_SCREEN_FRAME_COUNT, num_frames); } void optc1_setup_manual_trigger(struct timing_generator *optc) diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h index 3afeb1a30f21..f277656d5464 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h @@ -625,7 +625,8 @@ void optc1_set_drr( void optc1_set_static_screen_control( struct timing_generator *optc, - uint32_t value); + uint32_t event_triggers, + uint32_t num_frames); void optc1_program_stereo(struct timing_generator *optc, const struct dc_crtc_timing *timing, struct crtc_stereo_flags *flags); diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile index fd52862d6624..5fcaf78334ff 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile @@ -9,7 +9,13 @@ DCN20 = dcn20_resource.o dcn20_init.o dcn20_hwseq.o dcn20_dpp.o dcn20_dpp_cm.o d DCN20 += dcn20_dsc.o +ifdef CONFIG_X86 CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -msse +endif + +ifdef CONFIG_PPC64 +CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -maltivec +endif ifdef CONFIG_CC_IS_GCC ifeq ($(call cc-ifversion, -lt, 0701, y), y) @@ -17,6 +23,7 @@ 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 @@ -25,6 +32,7 @@ CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o += -mpreferred-stack-boundary=4 else CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o += -msse2 endif +endif AMD_DAL_DCN20 = $(addprefix $(AMDDALPATH)/dc/dcn20/,$(DCN20)) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c index 1e1151356e60..50bffbfdd394 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c @@ -50,20 +50,20 @@ void dccg2_update_dpp_dto(struct dccg *dccg, int dpp_inst, int req_dppclk) if (dccg->ref_dppclk && req_dppclk) { int ref_dppclk = dccg->ref_dppclk; + int modulo, phase; - ASSERT(req_dppclk <= ref_dppclk); - /* need to clamp to 8 bits */ - if (ref_dppclk > 0xff) { - int divider = (ref_dppclk + 0xfe) / 0xff; + // phase / modulo = dpp pipe clk / dpp global clk + modulo = 0xff; // use FF at the end + phase = ((modulo * req_dppclk) + ref_dppclk - 1) / ref_dppclk; - ref_dppclk /= divider; - req_dppclk = (req_dppclk + divider - 1) / divider; - if (req_dppclk > ref_dppclk) - req_dppclk = ref_dppclk; + if (phase > 0xff) { + ASSERT(false); + phase = 0xff; } + REG_SET_2(DPPCLK_DTO_PARAM[dpp_inst], 0, - DPPCLK0_DTO_PHASE, req_dppclk, - DPPCLK0_DTO_MODULO, ref_dppclk); + DPPCLK0_DTO_PHASE, phase, + DPPCLK0_DTO_MODULO, modulo); REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_ENABLE[dpp_inst], 1); } else { diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c index 4d7e45892f08..13e057d7ee93 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c @@ -104,7 +104,7 @@ static void dpp2_cnv_setup ( uint32_t pixel_format = 0; uint32_t alpha_en = 1; enum dc_color_space color_space = COLOR_SPACE_SRGB; - enum dcn10_input_csc_select select = INPUT_CSC_SELECT_BYPASS; + enum dcn20_input_csc_select select = DCN2_ICSC_SELECT_BYPASS; bool force_disable_cursor = false; struct out_csc_color_matrix tbl_entry; uint32_t is_2bit = 0; @@ -145,25 +145,25 @@ static void dpp2_cnv_setup ( force_disable_cursor = false; pixel_format = 65; color_space = COLOR_SPACE_YCBCR709; - select = INPUT_CSC_SELECT_ICSC; + select = DCN2_ICSC_SELECT_ICSC_A; break; case SURFACE_PIXEL_FORMAT_VIDEO_420_YCrCb: force_disable_cursor = true; pixel_format = 64; color_space = COLOR_SPACE_YCBCR709; - select = INPUT_CSC_SELECT_ICSC; + select = DCN2_ICSC_SELECT_ICSC_A; break; case SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCbCr: force_disable_cursor = true; pixel_format = 67; color_space = COLOR_SPACE_YCBCR709; - select = INPUT_CSC_SELECT_ICSC; + select = DCN2_ICSC_SELECT_ICSC_A; break; case SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCrCb: force_disable_cursor = true; pixel_format = 66; color_space = COLOR_SPACE_YCBCR709; - select = INPUT_CSC_SELECT_ICSC; + select = DCN2_ICSC_SELECT_ICSC_A; break; case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616: pixel_format = 22; @@ -177,7 +177,7 @@ static void dpp2_cnv_setup ( case SURFACE_PIXEL_FORMAT_VIDEO_AYCrCb8888: pixel_format = 12; color_space = COLOR_SPACE_YCBCR709; - select = INPUT_CSC_SELECT_ICSC; + select = DCN2_ICSC_SELECT_ICSC_A; break; case SURFACE_PIXEL_FORMAT_GRPH_RGB111110_FIX: pixel_format = 112; @@ -188,13 +188,13 @@ static void dpp2_cnv_setup ( case SURFACE_PIXEL_FORMAT_VIDEO_ACrYCb2101010: pixel_format = 114; color_space = COLOR_SPACE_YCBCR709; - select = INPUT_CSC_SELECT_ICSC; + select = DCN2_ICSC_SELECT_ICSC_A; is_2bit = 1; break; case SURFACE_PIXEL_FORMAT_VIDEO_CrYCbA1010102: pixel_format = 115; color_space = COLOR_SPACE_YCBCR709; - select = INPUT_CSC_SELECT_ICSC; + select = DCN2_ICSC_SELECT_ICSC_A; is_2bit = 1; break; case SURFACE_PIXEL_FORMAT_GRPH_RGB111110_FLOAT: @@ -227,13 +227,13 @@ static void dpp2_cnv_setup ( tbl_entry.color_space = input_color_space; if (color_space >= COLOR_SPACE_YCBCR601) - select = INPUT_CSC_SELECT_ICSC; + select = DCN2_ICSC_SELECT_ICSC_A; else - select = INPUT_CSC_SELECT_BYPASS; + select = DCN2_ICSC_SELECT_BYPASS; - dpp1_program_input_csc(dpp_base, color_space, select, &tbl_entry); + dpp2_program_input_csc(dpp_base, color_space, select, &tbl_entry); } else - dpp1_program_input_csc(dpp_base, color_space, select, NULL); + dpp2_program_input_csc(dpp_base, color_space, select, NULL); if (force_disable_cursor) { REG_UPDATE(CURSOR_CONTROL, @@ -458,7 +458,7 @@ static struct dpp_funcs dcn20_dpp_funcs = { .dpp_reset = dpp_reset, .dpp_set_scaler = dpp1_dscl_set_scaler_manual_scale, .dpp_get_optimal_number_of_taps = dpp1_get_optimal_number_of_taps, - .dpp_set_gamut_remap = dpp1_cm_set_gamut_remap, + .dpp_set_gamut_remap = dpp2_cm_set_gamut_remap, .dpp_set_csc_adjustment = NULL, .dpp_set_csc_default = NULL, .dpp_program_regamma_pwl = oppn20_dummy_program_regamma_pwl, diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.h index 5b03b737b1d6..27610251c57f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.h @@ -150,6 +150,16 @@ SRI(CM_SHAPER_RAMA_REGION_32_33, CM, id), \ SRI(CM_SHAPER_LUT_INDEX, CM, id) +#define TF_REG_LIST_DCN20_COMMON_APPEND(id) \ + SRI(CM_GAMUT_REMAP_B_C11_C12, CM, id),\ + SRI(CM_GAMUT_REMAP_B_C13_C14, CM, id),\ + SRI(CM_GAMUT_REMAP_B_C21_C22, CM, id),\ + SRI(CM_GAMUT_REMAP_B_C23_C24, CM, id),\ + SRI(CM_GAMUT_REMAP_B_C31_C32, CM, id),\ + SRI(CM_GAMUT_REMAP_B_C33_C34, CM, id),\ + SRI(CM_ICSC_B_C11_C12, CM, id), \ + SRI(CM_ICSC_B_C33_C34, CM, id) + #define TF_REG_LIST_DCN20(id) \ TF_REG_LIST_DCN(id), \ TF_REG_LIST_DCN20_COMMON(id), \ @@ -572,10 +582,29 @@ TF_SF(DSCL0_OBUF_MEM_PWR_CTRL, OBUF_MEM_PWR_FORCE, mask_sh),\ TF_SF(DSCL0_DSCL_MEM_PWR_CTRL, LUT_MEM_PWR_FORCE, mask_sh) +/* DPP CM debug status register: + * + * Status index including current ICSC, Gamut Remap Mode is 9 + * ICSC Mode: [4..3] + * Gamut Remap Mode: [10..9] + */ +#define CM_TEST_DEBUG_DATA_STATUS_IDX 9 + +#define TF_DEBUG_REG_LIST_SH_DCN20 \ + TF_DEBUG_REG_LIST_SH_DCN10, \ + .CM_TEST_DEBUG_DATA_ICSC_MODE = 3, \ + .CM_TEST_DEBUG_DATA_GAMUT_REMAP_MODE = 9 + +#define TF_DEBUG_REG_LIST_MASK_DCN20 \ + TF_DEBUG_REG_LIST_MASK_DCN10, \ + .CM_TEST_DEBUG_DATA_ICSC_MODE = 0x18, \ + .CM_TEST_DEBUG_DATA_GAMUT_REMAP_MODE = 0x600 #define TF_REG_FIELD_LIST_DCN2_0(type) \ TF_REG_FIELD_LIST(type) \ type CM_BLNDGAM_LUT_DATA; \ + type CM_TEST_DEBUG_DATA_ICSC_MODE; \ + type CM_TEST_DEBUG_DATA_GAMUT_REMAP_MODE; \ type FORMAT_CNV16; \ type CNVC_BYPASS_MSB_ALIGN; \ type CLAMP_POSITIVE; \ @@ -630,11 +659,22 @@ struct dcn2_dpp_mask { uint32_t COLOR_KEYER_RED; \ uint32_t COLOR_KEYER_GREEN; \ uint32_t COLOR_KEYER_BLUE; \ - uint32_t OBUF_MEM_PWR_CTRL;\ + uint32_t OBUF_MEM_PWR_CTRL; \ uint32_t DSCL_MEM_PWR_CTRL +#define DPP_DCN2_REG_VARIABLE_LIST_CM_APPEND \ + uint32_t CM_GAMUT_REMAP_B_C11_C12; \ + uint32_t CM_GAMUT_REMAP_B_C13_C14; \ + uint32_t CM_GAMUT_REMAP_B_C21_C22; \ + uint32_t CM_GAMUT_REMAP_B_C23_C24; \ + uint32_t CM_GAMUT_REMAP_B_C31_C32; \ + uint32_t CM_GAMUT_REMAP_B_C33_C34; \ + uint32_t CM_ICSC_B_C11_C12; \ + uint32_t CM_ICSC_B_C33_C34 + struct dcn2_dpp_registers { DPP_DCN2_REG_VARIABLE_LIST; + DPP_DCN2_REG_VARIABLE_LIST_CM_APPEND; }; struct dcn20_dpp { @@ -656,6 +696,18 @@ struct dcn20_dpp { struct pwl_params pwl_data; }; +enum dcn20_input_csc_select { + DCN2_ICSC_SELECT_BYPASS = 0, + DCN2_ICSC_SELECT_ICSC_A = 1, + DCN2_ICSC_SELECT_ICSC_B = 2 +}; + +enum dcn20_gamut_remap_select { + DCN2_GAMUT_REMAP_BYPASS = 0, + DCN2_GAMUT_REMAP_COEF_A = 1, + DCN2_GAMUT_REMAP_COEF_B = 2 +}; + void dpp20_read_state(struct dpp *dpp_base, struct dcn_dpp_state *s); @@ -667,6 +719,16 @@ void dpp2_set_degamma( struct dpp *dpp_base, enum ipp_degamma_mode mode); +void dpp2_cm_set_gamut_remap( + struct dpp *dpp_base, + const struct dpp_grph_csc_adjustment *adjust); + +void dpp2_program_input_csc( + struct dpp *dpp_base, + enum dc_color_space color_space, + enum dcn20_input_csc_select input_select, + const struct out_csc_color_matrix *tbl_entry); + bool dpp20_program_blnd_lut( struct dpp *dpp_base, const struct pwl_params *params); diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp_cm.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp_cm.c index 05a3e7f97ef0..8dc3d1f73984 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp_cm.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp_cm.c @@ -36,6 +36,9 @@ #define REG(reg)\ dpp->tf_regs->reg +#define IND_REG(index) \ + (index) + #define CTX \ dpp->base.ctx @@ -44,9 +47,6 @@ dpp->tf_shift->field_name, dpp->tf_mask->field_name - - - static void dpp2_enable_cm_block( struct dpp *dpp_base) { @@ -158,6 +158,155 @@ void dpp2_set_degamma( } } +static void program_gamut_remap( + struct dcn20_dpp *dpp, + const uint16_t *regval, + enum dcn20_gamut_remap_select select) +{ + uint32_t cur_select = 0; + struct color_matrices_reg gam_regs; + + if (regval == NULL || select == DCN2_GAMUT_REMAP_BYPASS) { + REG_SET(CM_GAMUT_REMAP_CONTROL, 0, + CM_GAMUT_REMAP_MODE, 0); + return; + } + + /* determine which gamut_remap coefficients (A or B) we are using + * currently. select the alternate set to double buffer + * the update so gamut_remap is updated on frame boundary + */ + IX_REG_GET(CM_TEST_DEBUG_INDEX, CM_TEST_DEBUG_DATA, + CM_TEST_DEBUG_DATA_STATUS_IDX, + CM_TEST_DEBUG_DATA_GAMUT_REMAP_MODE, &cur_select); + + /* value stored in dbg reg will be 1 greater than mode we want */ + if (cur_select != DCN2_GAMUT_REMAP_COEF_A) + select = DCN2_GAMUT_REMAP_COEF_A; + else + select = DCN2_GAMUT_REMAP_COEF_B; + + gam_regs.shifts.csc_c11 = dpp->tf_shift->CM_GAMUT_REMAP_C11; + gam_regs.masks.csc_c11 = dpp->tf_mask->CM_GAMUT_REMAP_C11; + gam_regs.shifts.csc_c12 = dpp->tf_shift->CM_GAMUT_REMAP_C12; + gam_regs.masks.csc_c12 = dpp->tf_mask->CM_GAMUT_REMAP_C12; + + if (select == DCN2_GAMUT_REMAP_COEF_A) { + gam_regs.csc_c11_c12 = REG(CM_GAMUT_REMAP_C11_C12); + gam_regs.csc_c33_c34 = REG(CM_GAMUT_REMAP_C33_C34); + } else { + gam_regs.csc_c11_c12 = REG(CM_GAMUT_REMAP_B_C11_C12); + gam_regs.csc_c33_c34 = REG(CM_GAMUT_REMAP_B_C33_C34); + } + + cm_helper_program_color_matrices( + dpp->base.ctx, + regval, + &gam_regs); + + REG_SET( + CM_GAMUT_REMAP_CONTROL, 0, + CM_GAMUT_REMAP_MODE, select); + +} + +void dpp2_cm_set_gamut_remap( + struct dpp *dpp_base, + const struct dpp_grph_csc_adjustment *adjust) +{ + struct dcn20_dpp *dpp = TO_DCN20_DPP(dpp_base); + int i = 0; + + if (adjust->gamut_adjust_type != GRAPHICS_GAMUT_ADJUST_TYPE_SW) + /* Bypass if type is bypass or hw */ + program_gamut_remap(dpp, NULL, DCN2_GAMUT_REMAP_BYPASS); + else { + struct fixed31_32 arr_matrix[12]; + uint16_t arr_reg_val[12]; + + for (i = 0; i < 12; i++) + arr_matrix[i] = adjust->temperature_matrix[i]; + + convert_float_matrix( + arr_reg_val, arr_matrix, 12); + + program_gamut_remap(dpp, arr_reg_val, DCN2_GAMUT_REMAP_COEF_A); + } +} + +void dpp2_program_input_csc( + struct dpp *dpp_base, + enum dc_color_space color_space, + enum dcn20_input_csc_select input_select, + const struct out_csc_color_matrix *tbl_entry) +{ + struct dcn20_dpp *dpp = TO_DCN20_DPP(dpp_base); + int i; + int arr_size = sizeof(dpp_input_csc_matrix)/sizeof(struct dpp_input_csc_matrix); + const uint16_t *regval = NULL; + uint32_t cur_select = 0; + enum dcn20_input_csc_select select; + struct color_matrices_reg icsc_regs; + + if (input_select == DCN2_ICSC_SELECT_BYPASS) { + REG_SET(CM_ICSC_CONTROL, 0, CM_ICSC_MODE, 0); + return; + } + + if (tbl_entry == NULL) { + for (i = 0; i < arr_size; i++) + if (dpp_input_csc_matrix[i].color_space == color_space) { + regval = dpp_input_csc_matrix[i].regval; + break; + } + + if (regval == NULL) { + BREAK_TO_DEBUGGER(); + return; + } + } else { + regval = tbl_entry->regval; + } + + /* determine which CSC coefficients (A or B) we are using + * currently. select the alternate set to double buffer + * the CSC update so CSC is updated on frame boundary + */ + IX_REG_GET(CM_TEST_DEBUG_INDEX, CM_TEST_DEBUG_DATA, + CM_TEST_DEBUG_DATA_STATUS_IDX, + CM_TEST_DEBUG_DATA_ICSC_MODE, &cur_select); + + if (cur_select != DCN2_ICSC_SELECT_ICSC_A) + select = DCN2_ICSC_SELECT_ICSC_A; + else + select = DCN2_ICSC_SELECT_ICSC_B; + + icsc_regs.shifts.csc_c11 = dpp->tf_shift->CM_ICSC_C11; + icsc_regs.masks.csc_c11 = dpp->tf_mask->CM_ICSC_C11; + icsc_regs.shifts.csc_c12 = dpp->tf_shift->CM_ICSC_C12; + icsc_regs.masks.csc_c12 = dpp->tf_mask->CM_ICSC_C12; + + if (select == DCN2_ICSC_SELECT_ICSC_A) { + + icsc_regs.csc_c11_c12 = REG(CM_ICSC_C11_C12); + icsc_regs.csc_c33_c34 = REG(CM_ICSC_C33_C34); + + } else { + + icsc_regs.csc_c11_c12 = REG(CM_ICSC_B_C11_C12); + icsc_regs.csc_c33_c34 = REG(CM_ICSC_B_C33_C34); + + } + + cm_helper_program_color_matrices( + dpp->base.ctx, + regval, + &icsc_regs); + + REG_SET(CM_ICSC_CONTROL, 0, + CM_ICSC_MODE, select); +} + static void dpp20_power_on_blnd_lut( struct dpp *dpp_base, bool power_on) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c index 0111545dac75..6bdfee20b6a7 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c @@ -206,6 +206,9 @@ static bool dsc2_get_packed_pps(struct display_stream_compressor *dsc, const str struct dsc_reg_values dsc_reg_vals; struct dsc_optc_config dsc_optc_cfg; + memset(&dsc_reg_vals, 0, sizeof(dsc_reg_vals)); + memset(&dsc_optc_cfg, 0, sizeof(dsc_optc_cfg)); + DC_LOG_DSC("Getting packed DSC PPS for DSC Config:"); dsc_config_log(dsc, dsc_cfg); DC_LOG_DSC("DSC Picture Parameter Set (PPS):"); diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c index 8b8438566101..9235f7d29454 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c @@ -293,6 +293,9 @@ bool hubbub2_get_dcc_compression_cap(struct hubbub *hubbub, output->grph.rgb.max_compressed_blk_size = 64; output->grph.rgb.independent_64b_blks = true; break; + default: + ASSERT(false); + break; } output->capable = true; output->const_color_support = true; @@ -601,7 +604,8 @@ static const struct hubbub_funcs hubbub2_funcs = { .wm_read_state = hubbub2_wm_read_state, .get_dchub_ref_freq = hubbub2_get_dchub_ref_freq, .program_watermarks = hubbub2_program_watermarks, - .allow_self_refresh_control = hubbub1_allow_self_refresh_control + .is_allow_self_refresh_enabled = hubbub1_is_allow_self_refresh_enabled, + .allow_self_refresh_control = hubbub1_allow_self_refresh_control, }; void hubbub2_construct(struct dcn20_hubbub *hubbub, 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 32878a65bdd7..a444fed94184 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -183,10 +183,10 @@ void dcn20_enable_power_gating_plane( struct dce_hwseq *hws, bool enable) { - bool force_on = 1; /* disable power gating */ + bool force_on = true; /* disable power gating */ if (enable) - force_on = 0; + force_on = false; /* DCHUBP0/1/2/3/4/5 */ REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN0_POWER_FORCEON, force_on); @@ -572,7 +572,6 @@ void dcn20_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx) dpp->funcs->dpp_dppclk_control(dpp, false, false); hubp->power_gated = true; - dc->optimized_required = false; /* We're powering off, no need to optimize */ hws->funcs.plane_atomic_power_down(dc, pipe_ctx->plane_res.dpp, @@ -686,9 +685,13 @@ enum dc_status dcn20_enable_stream_timing( // DRR should set trigger event to monitor surface update event if (stream->adjust.v_total_min != 0 && stream->adjust.v_total_max != 0) event_triggers = 0x80; + /* Event triggers and num frames initialized for DRR, but can be + * later updated for PSR use. Note DRR trigger events are generated + * regardless of whether num frames met. + */ if (pipe_ctx->stream_res.tg->funcs->set_static_screen_control) pipe_ctx->stream_res.tg->funcs->set_static_screen_control( - pipe_ctx->stream_res.tg, event_triggers); + pipe_ctx->stream_res.tg, event_triggers, 2); /* TODO program crtc source select for non-virtual signal*/ /* TODO program FMT */ @@ -941,6 +944,9 @@ void dcn20_blank_pixel_data( int width = stream->timing.h_addressable + stream->timing.h_border_left + stream->timing.h_border_right; int height = stream->timing.v_addressable + stream->timing.v_border_bottom + stream->timing.v_border_top; + if (stream->link->test_pattern_enabled) + return; + /* get opp dpg blank color */ color_space_to_black_color(dc, color_space, &black_color); @@ -1305,6 +1311,7 @@ static void dcn20_update_dchubp_dpp( struct hubp *hubp = pipe_ctx->plane_res.hubp; struct dpp *dpp = pipe_ctx->plane_res.dpp; struct dc_plane_state *plane_state = pipe_ctx->plane_state; + bool viewport_changed = false; if (pipe_ctx->update_flags.bits.dppclk) dpp->funcs->dpp_dppclk_control(dpp, false, true); @@ -1355,9 +1362,9 @@ static void dcn20_update_dchubp_dpp( || plane_state->update_flags.bits.global_alpha_change || plane_state->update_flags.bits.per_pixel_alpha_change) { // MPCC inst is equal to pipe index in practice - int mpcc_inst = pipe_ctx->pipe_idx; + int mpcc_inst = hubp->inst; int opp_inst; - int opp_count = dc->res_pool->res_cap->num_opp; + int opp_count = dc->res_pool->pipe_count; for (opp_inst = 0; opp_inst < opp_count; opp_inst++) { if (dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst]) { @@ -1383,15 +1390,18 @@ static void dcn20_update_dchubp_dpp( if (pipe_ctx->update_flags.bits.viewport || (context == dc->current_state && plane_state->update_flags.bits.scaling_change) || - (context == dc->current_state && pipe_ctx->stream->update_flags.bits.scaling)) + (context == dc->current_state && pipe_ctx->stream->update_flags.bits.scaling)) { + hubp->funcs->mem_program_viewport( hubp, &pipe_ctx->plane_res.scl_data.viewport, - &pipe_ctx->plane_res.scl_data.viewport_c, - plane_state->rotation); + &pipe_ctx->plane_res.scl_data.viewport_c); + viewport_changed = true; + } /* Any updates are handled in dc interface, just need to apply existing for plane enable */ - if ((pipe_ctx->update_flags.bits.enable || pipe_ctx->update_flags.bits.opp_changed) + if ((pipe_ctx->update_flags.bits.enable || pipe_ctx->update_flags.bits.opp_changed || + pipe_ctx->update_flags.bits.scaler || pipe_ctx->update_flags.bits.viewport) && pipe_ctx->stream->cursor_attributes.address.quad_part != 0) { dc->hwss.set_cursor_position(pipe_ctx); dc->hwss.set_cursor_attribute(pipe_ctx); @@ -1441,9 +1451,14 @@ static void dcn20_update_dchubp_dpp( hubp->power_gated = false; } + if (hubp->funcs->apply_PLAT_54186_wa && viewport_changed) + hubp->funcs->apply_PLAT_54186_wa(hubp, &plane_state->address); + if (pipe_ctx->update_flags.bits.enable || plane_state->update_flags.bits.addr_update) hws->funcs.update_plane_addr(dc, pipe_ctx); + + if (pipe_ctx->update_flags.bits.enable) hubp->funcs->set_blank(hubp, false); } @@ -1629,9 +1644,9 @@ void dcn20_program_front_end_for_ctx( struct hubp *hubp = pipe->plane_res.hubp; int j = 0; - for (j = 0; j < TIMEOUT_FOR_PIPE_ENABLE_MS + for (j = 0; j < TIMEOUT_FOR_PIPE_ENABLE_MS*1000 && hubp->funcs->hubp_is_flip_pending(hubp); j++) - msleep(1); + mdelay(1); } } @@ -1731,7 +1746,6 @@ bool dcn20_update_bandwidth( void dcn20_enable_writeback( struct dc *dc, - const struct dc_stream_status *stream_status, struct dc_writeback_info *wb_info, struct dc_state *context) { @@ -1745,8 +1759,7 @@ void dcn20_enable_writeback( mcif_wb = dc->res_pool->mcif_wb[wb_info->dwb_pipe_inst]; /* set the OPTC source mux */ - ASSERT(stream_status->primary_otg_inst < MAX_PIPES); - optc = dc->res_pool->timing_generators[stream_status->primary_otg_inst]; + optc = dc->res_pool->timing_generators[dwb->otg_inst]; optc->funcs->set_dwb_source(optc, wb_info->dwb_pipe_inst); /* set MCIF_WB buffer and arbitration configuration */ mcif_wb->funcs->config_mcif_buf(mcif_wb, &wb_info->mcif_buf_params, wb_info->dwb_params.dest_height); @@ -1995,6 +2008,7 @@ static void dcn20_reset_back_end_for_pipe( struct dc_state *context) { int i; + struct dc_link *link; DC_LOGGER_INIT(dc->ctx->logger); if (pipe_ctx->stream_res.stream_enc == NULL) { pipe_ctx->stream = NULL; @@ -2002,8 +2016,14 @@ static void dcn20_reset_back_end_for_pipe( } if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) { - /* DPMS may already disable */ - if (!pipe_ctx->stream->dpms_off) + link = pipe_ctx->stream->link; + /* DPMS may already disable or */ + /* dpms_off status is incorrect due to fastboot + * feature. When system resume from S4 with second + * screen only, the dpms_off would be true but + * VBIOS lit up eDP, so check link status too. + */ + if (!pipe_ctx->stream->dpms_off || link->link_status.link_active) core_link_disable_stream(pipe_ctx); else if (pipe_ctx->stream_res.audio) dc->hwss.disable_audio_stream(pipe_ctx); diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.h index eecd7a26ec4c..02c9be5ebd47 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.h @@ -104,7 +104,6 @@ void dcn20_program_triple_buffer( bool enable_triple_buffer); void dcn20_enable_writeback( struct dc *dc, - const struct dc_stream_status *stream_status, struct dc_writeback_info *wb_info, struct dc_state *context); void dcn20_disable_writeback( diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h index 62dfd34c69f1..8cab8107fd94 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h @@ -33,7 +33,142 @@ SRI(AUX_DPHY_TX_CONTROL, DP_AUX, id) #define UNIPHY_MASK_SH_LIST(mask_sh)\ - LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_LINK_ENABLE, mask_sh) + LE_SF(SYMCLKA_CLOCK_ENABLE, SYMCLKA_CLOCK_ENABLE, mask_sh),\ + LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_LINK_ENABLE, mask_sh),\ + LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_CHANNEL0_XBAR_SOURCE, mask_sh),\ + LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_CHANNEL1_XBAR_SOURCE, mask_sh),\ + LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_CHANNEL2_XBAR_SOURCE, mask_sh),\ + LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_CHANNEL3_XBAR_SOURCE, mask_sh) + +#define DPCS_MASK_SH_LIST(mask_sh)\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX0_CLK_RDY, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX0_DATA_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX1_CLK_RDY, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX1_DATA_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX2_CLK_RDY, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX2_DATA_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX3_CLK_RDY, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX3_DATA_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL4, RDPCS_PHY_DP_TX0_TERM_CTRL, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL4, RDPCS_PHY_DP_TX1_TERM_CTRL, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL4, RDPCS_PHY_DP_TX2_TERM_CTRL, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL4, RDPCS_PHY_DP_TX3_TERM_CTRL, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL11, RDPCS_PHY_DP_MPLLB_MULTIPLIER, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX0_WIDTH, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX0_RATE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX1_WIDTH, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX1_RATE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX2_PSTATE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX3_PSTATE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX2_MPLL_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX3_MPLL_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL7, RDPCS_PHY_DP_MPLLB_FRACN_QUOT, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL7, RDPCS_PHY_DP_MPLLB_FRACN_DEN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL8, RDPCS_PHY_DP_MPLLB_SSC_PEAK, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL9, RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL9, RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL10, RDPCS_PHY_DP_MPLLB_FRACN_REM, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL11, RDPCS_PHY_DP_REF_CLK_MPLLB_DIV, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL11, RDPCS_PHY_HDMI_MPLLB_HDMI_DIV, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL12, RDPCS_PHY_DP_MPLLB_SSC_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL12, RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL12, RDPCS_PHY_DP_MPLLB_TX_CLK_DIV, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL12, RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL12, RDPCS_PHY_DP_MPLLB_STATE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL13, RDPCS_PHY_DP_MPLLB_DIV_CLK_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL13, RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL14, RDPCS_PHY_DP_MPLLB_FRACN_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL14, RDPCS_PHY_DP_MPLLB_PMIX_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_CNTL, RDPCS_TX_FIFO_LANE0_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_CNTL, RDPCS_TX_FIFO_LANE1_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_CNTL, RDPCS_TX_FIFO_LANE2_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_CNTL, RDPCS_TX_FIFO_LANE3_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_CNTL, RDPCS_TX_FIFO_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_CNTL, RDPCS_TX_FIFO_RD_START_DELAY, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_EXT_REFCLK_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_SRAMCLK_BYPASS, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_SRAMCLK_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_SRAMCLK_CLOCK_ON, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_SYMCLK_DIV2_CLOCK_ON, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_SYMCLK_DIV2_GATE_DIS, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_SYMCLK_DIV2_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX0_DISABLE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX1_DISABLE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX2_DISABLE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX3_DISABLE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX0_REQ, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX1_REQ, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX2_REQ, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX3_REQ, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX0_ACK, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX1_ACK, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX2_ACK, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX3_ACK, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX0_RESET, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX1_RESET, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX2_RESET, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX3_RESET, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_PHY_RESET, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_PHY_CR_MUX_SEL, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_PHY_REF_RANGE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_SRAM_BYPASS, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_SRAM_EXT_LD_DONE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_PHY_HDMIMODE_ENABLE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_SRAM_INIT_DONE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL2, RDPCS_PHY_DP4_POR, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PLL_UPDATE_DATA, RDPCS_PLL_UPDATE_DATA, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL, RDPCS_REG_FIFO_ERROR_MASK, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL, RDPCS_TX_FIFO_ERROR_MASK, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL, RDPCS_DPALT_DISABLE_TOGGLE_MASK, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL, RDPCS_DPALT_4LANE_TOGGLE_MASK, mask_sh),\ + LE_SF(RDPCSTX0_RDPCS_TX_CR_ADDR, RDPCS_TX_CR_ADDR, mask_sh),\ + LE_SF(RDPCSTX0_RDPCS_TX_CR_DATA, RDPCS_TX_CR_DATA, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_MPLLB_V2I, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_TX0_EQ_MAIN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_TX0_EQ_PRE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_TX0_EQ_POST, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_MPLLB_FREQ_VCO, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_MPLLB_CP_INT, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_MPLLB_CP_PROP, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_TX1_EQ_MAIN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_TX1_EQ_PRE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_TX1_EQ_POST, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE2, RDPCS_PHY_DP_TX2_EQ_MAIN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE2, RDPCS_PHY_DP_TX2_EQ_PRE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE2, RDPCS_PHY_DP_TX2_EQ_POST, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DP_TX3_EQ_MAIN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DCO_FINETUNE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DCO_RANGE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DP_TX3_EQ_PRE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DP_TX3_EQ_POST, mask_sh),\ + LE_SF(DPCSTX0_DPCSTX_TX_CLOCK_CNTL, DPCS_SYMCLK_CLOCK_ON, mask_sh),\ + LE_SF(DPCSTX0_DPCSTX_TX_CLOCK_CNTL, DPCS_SYMCLK_GATE_DIS, mask_sh),\ + LE_SF(DPCSTX0_DPCSTX_TX_CLOCK_CNTL, DPCS_SYMCLK_EN, mask_sh),\ + LE_SF(DPCSTX0_DPCSTX_TX_CNTL, DPCS_TX_DATA_SWAP, mask_sh),\ + LE_SF(DPCSTX0_DPCSTX_TX_CNTL, DPCS_TX_DATA_ORDER_INVERT, mask_sh),\ + LE_SF(DPCSTX0_DPCSTX_TX_CNTL, DPCS_TX_FIFO_EN, mask_sh),\ + LE_SF(DPCSTX0_DPCSTX_TX_CNTL, DPCS_TX_FIFO_RD_START_DELAY, mask_sh),\ + LE_SF(DPCSTX0_DPCSTX_DEBUG_CONFIG, DPCS_DBG_CBUS_DIS, mask_sh) + +#define DPCS_DCN2_MASK_SH_LIST(mask_sh)\ + DPCS_MASK_SH_LIST(mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_RX_LD_VAL, RDPCS_PHY_RX_REF_LD_VAL, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_RX_LD_VAL, RDPCS_PHY_RX_VCO_LD_VAL, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE_ACK, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX0_PSTATE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX1_PSTATE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX0_MPLL_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX1_MPLL_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_REF_CLK_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX2_WIDTH, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX2_RATE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX3_WIDTH, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX3_RATE, mask_sh),\ + LE_SF(DCIO_SOFT_RESET, UNIPHYA_SOFT_RESET, mask_sh),\ + LE_SF(DCIO_SOFT_RESET, UNIPHYB_SOFT_RESET, mask_sh),\ + LE_SF(DCIO_SOFT_RESET, UNIPHYC_SOFT_RESET, mask_sh),\ + LE_SF(DCIO_SOFT_RESET, UNIPHYD_SOFT_RESET, mask_sh),\ + LE_SF(DCIO_SOFT_RESET, UNIPHYE_SOFT_RESET, mask_sh) #define LINK_ENCODER_MASK_SH_LIST_DCN20(mask_sh)\ LINK_ENCODER_MASK_SH_LIST_DCN10(mask_sh),\ @@ -63,6 +198,49 @@ SRI(CLOCK_ENABLE, SYMCLK, id), \ SRI(CHANNEL_XBAR_CNTL, UNIPHY, id) +#define DPCS_DCN2_CMN_REG_LIST(id) \ + SRI(DIG_LANE_ENABLE, DIG, id), \ + SRI(TMDS_CTL_BITS, DIG, id), \ + SRI(RDPCSTX_PHY_CNTL3, RDPCSTX, id), \ + SRI(RDPCSTX_PHY_CNTL4, RDPCSTX, id), \ + SRI(RDPCSTX_PHY_CNTL5, RDPCSTX, id), \ + SRI(RDPCSTX_PHY_CNTL6, RDPCSTX, id), \ + SRI(RDPCSTX_PHY_CNTL7, RDPCSTX, id), \ + SRI(RDPCSTX_PHY_CNTL8, RDPCSTX, id), \ + SRI(RDPCSTX_PHY_CNTL9, RDPCSTX, id), \ + SRI(RDPCSTX_PHY_CNTL10, RDPCSTX, id), \ + SRI(RDPCSTX_PHY_CNTL11, RDPCSTX, id), \ + SRI(RDPCSTX_PHY_CNTL12, RDPCSTX, id), \ + SRI(RDPCSTX_PHY_CNTL13, RDPCSTX, id), \ + SRI(RDPCSTX_PHY_CNTL14, RDPCSTX, id), \ + SRI(RDPCSTX_CNTL, RDPCSTX, id), \ + SRI(RDPCSTX_CLOCK_CNTL, RDPCSTX, id), \ + SRI(RDPCSTX_INTERRUPT_CONTROL, RDPCSTX, id), \ + SRI(RDPCSTX_PHY_CNTL0, RDPCSTX, id), \ + SRI(RDPCSTX_PHY_CNTL2, RDPCSTX, id), \ + SRI(RDPCSTX_PLL_UPDATE_DATA, RDPCSTX, id), \ + SRI(RDPCS_TX_CR_ADDR, RDPCSTX, id), \ + SRI(RDPCS_TX_CR_DATA, RDPCSTX, id), \ + SRI(RDPCSTX_PHY_FUSE0, RDPCSTX, id), \ + SRI(RDPCSTX_PHY_FUSE1, RDPCSTX, id), \ + SRI(RDPCSTX_PHY_FUSE2, RDPCSTX, id), \ + SRI(RDPCSTX_PHY_FUSE3, RDPCSTX, id), \ + SRI(DPCSTX_TX_CLOCK_CNTL, DPCSTX, id), \ + SRI(DPCSTX_TX_CNTL, DPCSTX, id), \ + SRI(DPCSTX_DEBUG_CONFIG, DPCSTX, id), \ + SRI(RDPCSTX_DEBUG_CONFIG, RDPCSTX, id), \ + SR(RDPCSTX0_RDPCSTX_SCRATCH) + + +#define DPCS_DCN2_REG_LIST(id) \ + DPCS_DCN2_CMN_REG_LIST(id), \ + SRI(RDPCSTX_PHY_RX_LD_VAL, RDPCSTX, id),\ + SRI(RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG, RDPCSTX, id) + +#define LE_DCN2_REG_LIST(id) \ + LE_DCN10_REG_LIST(id), \ + SR(DCIO_SOFT_RESET) + struct mpll_cfg { uint32_t mpllb_ana_v2i; uint32_t mpllb_ana_freq_vco; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c index f90031ed58a6..de9c857ab3e9 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c @@ -33,6 +33,9 @@ #define REG(reg)\ mpc20->mpc_regs->reg +#define IND_REG(index) \ + (index) + #define CTX \ mpc20->base.ctx @@ -132,19 +135,33 @@ void mpc2_set_output_csc( const uint16_t *regval, enum mpc_output_csc_mode ocsc_mode) { + uint32_t cur_mode; struct dcn20_mpc *mpc20 = TO_DCN20_MPC(mpc); struct color_matrices_reg ocsc_regs; - REG_SET(CSC_MODE[opp_id], 0, MPC_OCSC_MODE, ocsc_mode); - - if (ocsc_mode == MPC_OUTPUT_CSC_DISABLE) + if (ocsc_mode == MPC_OUTPUT_CSC_DISABLE) { + REG_SET(CSC_MODE[opp_id], 0, MPC_OCSC_MODE, ocsc_mode); return; + } if (regval == NULL) { BREAK_TO_DEBUGGER(); return; } + /* determine which CSC coefficients (A or B) we are using + * currently. select the alternate set to double buffer + * the CSC update so CSC is updated on frame boundary + */ + IX_REG_GET(MPC_OCSC_TEST_DEBUG_INDEX, MPC_OCSC_TEST_DEBUG_DATA, + MPC_OCSC_TEST_DEBUG_DATA_STATUS_IDX, + MPC_OCSC_TEST_DEBUG_DATA_OCSC_MODE, &cur_mode); + + if (cur_mode != MPC_OUTPUT_CSC_COEF_A) + ocsc_mode = MPC_OUTPUT_CSC_COEF_A; + else + ocsc_mode = MPC_OUTPUT_CSC_COEF_B; + ocsc_regs.shifts.csc_c11 = mpc20->mpc_shift->MPC_OCSC_C11_A; ocsc_regs.masks.csc_c11 = mpc20->mpc_mask->MPC_OCSC_C11_A; ocsc_regs.shifts.csc_c12 = mpc20->mpc_shift->MPC_OCSC_C12_A; @@ -157,10 +174,13 @@ void mpc2_set_output_csc( ocsc_regs.csc_c11_c12 = REG(CSC_C11_C12_B[opp_id]); ocsc_regs.csc_c33_c34 = REG(CSC_C33_C34_B[opp_id]); } + cm_helper_program_color_matrices( mpc20->base.ctx, regval, &ocsc_regs); + + REG_SET(CSC_MODE[opp_id], 0, MPC_OCSC_MODE, ocsc_mode); } void mpc2_set_ocsc_default( @@ -169,14 +189,16 @@ void mpc2_set_ocsc_default( enum dc_color_space color_space, enum mpc_output_csc_mode ocsc_mode) { + uint32_t cur_mode; struct dcn20_mpc *mpc20 = TO_DCN20_MPC(mpc); uint32_t arr_size; struct color_matrices_reg ocsc_regs; const uint16_t *regval = NULL; - REG_SET(CSC_MODE[opp_id], 0, MPC_OCSC_MODE, ocsc_mode); - if (ocsc_mode == MPC_OUTPUT_CSC_DISABLE) + if (ocsc_mode == MPC_OUTPUT_CSC_DISABLE) { + REG_SET(CSC_MODE[opp_id], 0, MPC_OCSC_MODE, ocsc_mode); return; + } regval = find_color_matrix(color_space, &arr_size); @@ -185,6 +207,19 @@ void mpc2_set_ocsc_default( return; } + /* determine which CSC coefficients (A or B) we are using + * currently. select the alternate set to double buffer + * the CSC update so CSC is updated on frame boundary + */ + IX_REG_GET(MPC_OCSC_TEST_DEBUG_INDEX, MPC_OCSC_TEST_DEBUG_DATA, + MPC_OCSC_TEST_DEBUG_DATA_STATUS_IDX, + MPC_OCSC_TEST_DEBUG_DATA_OCSC_MODE, &cur_mode); + + if (cur_mode != MPC_OUTPUT_CSC_COEF_A) + ocsc_mode = MPC_OUTPUT_CSC_COEF_A; + else + ocsc_mode = MPC_OUTPUT_CSC_COEF_B; + ocsc_regs.shifts.csc_c11 = mpc20->mpc_shift->MPC_OCSC_C11_A; ocsc_regs.masks.csc_c11 = mpc20->mpc_mask->MPC_OCSC_C11_A; ocsc_regs.shifts.csc_c12 = mpc20->mpc_shift->MPC_OCSC_C12_A; @@ -203,6 +238,8 @@ void mpc2_set_ocsc_default( mpc20->base.ctx, regval, &ocsc_regs); + + REG_SET(CSC_MODE[opp_id], 0, MPC_OCSC_MODE, ocsc_mode); } static void mpc2_ogam_get_reg_field( diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.h index 9f53192da2dc..c78fd5123497 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.h @@ -80,6 +80,10 @@ SRII(DENORM_CLAMP_G_Y, MPC_OUT, inst),\ SRII(DENORM_CLAMP_B_CB, MPC_OUT, inst) +#define MPC_DBG_REG_LIST_DCN2_0() \ + SR(MPC_OCSC_TEST_DEBUG_DATA),\ + SR(MPC_OCSC_TEST_DEBUG_INDEX) + #define MPC_REG_VARIABLE_LIST_DCN2_0 \ MPC_COMMON_REG_VARIABLE_LIST \ uint32_t MPCC_TOP_GAIN[MAX_MPCC]; \ @@ -118,6 +122,8 @@ uint32_t MPCC_OGAM_LUT_RAM_CONTROL[MAX_MPCC];\ uint32_t MPCC_OGAM_LUT_DATA[MAX_MPCC];\ uint32_t MPCC_OGAM_MODE[MAX_MPCC];\ + uint32_t MPC_OCSC_TEST_DEBUG_DATA;\ + uint32_t MPC_OCSC_TEST_DEBUG_INDEX;\ uint32_t CSC_MODE[MAX_OPP]; \ uint32_t CSC_C11_C12_A[MAX_OPP]; \ uint32_t CSC_C33_C34_A[MAX_OPP]; \ @@ -134,6 +140,7 @@ SF(MPCC0_MPCC_TOP_GAIN, MPCC_TOP_GAIN, mask_sh),\ SF(MPCC0_MPCC_BOT_GAIN_INSIDE, MPCC_BOT_GAIN_INSIDE, mask_sh),\ SF(MPCC0_MPCC_BOT_GAIN_OUTSIDE, MPCC_BOT_GAIN_OUTSIDE, mask_sh),\ + SF(MPC_OCSC_TEST_DEBUG_INDEX, MPC_OCSC_TEST_DEBUG_INDEX, mask_sh),\ SF(MPC_OUT0_CSC_MODE, MPC_OCSC_MODE, mask_sh),\ SF(MPC_OUT0_CSC_C11_C12_A, MPC_OCSC_C11_A, mask_sh),\ SF(MPC_OUT0_CSC_C11_C12_A, MPC_OCSC_C12_A, mask_sh),\ @@ -174,6 +181,19 @@ SF(MPC_OUT0_DENORM_CLAMP_B_CB, MPC_OUT_DENORM_CLAMP_MAX_B_CB, mask_sh),\ SF(MPC_OUT0_DENORM_CLAMP_B_CB, MPC_OUT_DENORM_CLAMP_MIN_B_CB, mask_sh) +/* + * DCN2 MPC_OCSC debug status register: + * + * Status index including current OCSC Mode is 1 + * OCSC Mode: [1..0] + */ +#define MPC_OCSC_TEST_DEBUG_DATA_STATUS_IDX 1 + +#define MPC_DEBUG_REG_LIST_SH_DCN20 \ + .MPC_OCSC_TEST_DEBUG_DATA_OCSC_MODE = 0 + +#define MPC_DEBUG_REG_LIST_MASK_DCN20 \ + .MPC_OCSC_TEST_DEBUG_DATA_OCSC_MODE = 0x3 #define MPC_REG_FIELD_LIST_DCN2_0(type) \ MPC_REG_FIELD_LIST(type)\ @@ -182,6 +202,8 @@ type MPCC_TOP_GAIN;\ type MPCC_BOT_GAIN_INSIDE;\ type MPCC_BOT_GAIN_OUTSIDE;\ + type MPC_OCSC_TEST_DEBUG_DATA_OCSC_MODE;\ + type MPC_OCSC_TEST_DEBUG_INDEX;\ type MPC_OCSC_MODE;\ type MPC_OCSC_C11_A;\ type MPC_OCSC_C12_A;\ diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c index 673c83e2afd4..d875b0c38fde 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c @@ -236,12 +236,13 @@ void optc2_set_odm_combine(struct timing_generator *optc, int *opp_id, int opp_c struct dc_crtc_timing *timing) { struct optc *optc1 = DCN10TG_FROM_TG(optc); - /* 2 pieces of memory required for up to 5120 displays, 4 for up to 8192 */ int mpcc_hactive = (timing->h_addressable + timing->h_border_left + timing->h_border_right) / opp_cnt; - int memory_mask = mpcc_hactive <= 2560 ? 0x3 : 0xf; + uint32_t memory_mask; uint32_t data_fmt = 0; + ASSERT(opp_cnt == 2); + /* TODO: In pseudocode but does not affect maximus, delete comment if we dont need on asic * REG_SET(OTG_GLOBAL_CONTROL2, 0, GLOBAL_UPDATE_LOCK_EN, 1); * Program OTG register MASTER_UPDATE_LOCK_DB_X/Y to the position before DP frame start @@ -249,9 +250,17 @@ void optc2_set_odm_combine(struct timing_generator *optc, int *opp_id, int opp_c * MASTER_UPDATE_LOCK_DB_X, 160, * MASTER_UPDATE_LOCK_DB_Y, 240); */ + + /* 2 pieces of memory required for up to 5120 displays, 4 for up to 8192, + * however, for ODM combine we can simplify by always using 4. + * To make sure there's no overlap, each instance "reserves" 2 memories and + * they are uniquely combined here. + */ + memory_mask = 0x3 << (opp_id[0] * 2) | 0x3 << (opp_id[1] * 2); + if (REG(OPTC_MEMORY_CONFIG)) REG_SET(OPTC_MEMORY_CONFIG, 0, - OPTC_MEM_SEL, memory_mask << (optc->inst * 4)); + OPTC_MEM_SEL, memory_mask); if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR422) data_fmt = 1; @@ -260,7 +269,6 @@ void optc2_set_odm_combine(struct timing_generator *optc, int *opp_id, int opp_c REG_UPDATE(OPTC_DATA_FORMAT_CONTROL, OPTC_DATA_FORMAT, data_fmt); - ASSERT(opp_cnt == 2); REG_SET_3(OPTC_DATA_SOURCE_SELECT, 0, OPTC_NUM_OF_INPUT_SEGMENT, 1, OPTC_SEG0_SRC_SEL, opp_id[0], @@ -382,14 +390,8 @@ void optc2_setup_manual_trigger(struct timing_generator *optc) { struct optc *optc1 = DCN10TG_FROM_TG(optc); - REG_SET(OTG_MANUAL_FLOW_CONTROL, 0, - MANUAL_FLOW_CONTROL, 1); - - REG_SET(OTG_GLOBAL_CONTROL2, 0, - MANUAL_FLOW_CONTROL_SEL, optc->inst); - REG_SET_8(OTG_TRIGA_CNTL, 0, - OTG_TRIGA_SOURCE_SELECT, 22, + OTG_TRIGA_SOURCE_SELECT, 21, OTG_TRIGA_SOURCE_PIPE_SELECT, optc->inst, OTG_TRIGA_RISING_EDGE_DETECT_CNTL, 1, OTG_TRIGA_FALLING_EDGE_DETECT_CNTL, 0, diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.h index ac93fbfaee03..239cc40ae474 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.h @@ -106,6 +106,7 @@ void optc2_triplebuffer_lock(struct timing_generator *optc); void optc2_triplebuffer_unlock(struct timing_generator *optc); void optc2_lock_doublebuffer_disable(struct timing_generator *optc); void optc2_lock_doublebuffer_enable(struct timing_generator *optc); +void optc2_setup_manual_trigger(struct timing_generator *optc); void optc2_program_manual_trigger(struct timing_generator *optc); bool optc2_is_two_pixels_per_containter(const struct dc_crtc_timing *timing); #endif /* __DC_OPTC_DCN20_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index cfc69919ef9e..85f90f3e24cb 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -1,5 +1,6 @@ /* * Copyright 2016 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"), @@ -65,6 +66,8 @@ #include "dcn/dcn_2_0_0_offset.h" #include "dcn/dcn_2_0_0_sh_mask.h" +#include "dpcs/dpcs_2_0_0_offset.h" +#include "dpcs/dpcs_2_0_0_sh_mask.h" #include "nbio/nbio_2_3_offset.h" @@ -548,6 +551,7 @@ static const struct dcn10_link_enc_hpd_registers link_enc_hpd_regs[] = { [id] = {\ LE_DCN10_REG_LIST(id), \ UNIPHY_DCN2_REG_LIST(phyid), \ + DPCS_DCN2_REG_LIST(id), \ SRI(DP_DPHY_INTERNAL_CTRL, DP, id) \ } @@ -561,11 +565,13 @@ static const struct dcn10_link_enc_registers link_enc_regs[] = { }; static const struct dcn10_link_enc_shift le_shift = { - LINK_ENCODER_MASK_SH_LIST_DCN20(__SHIFT) + LINK_ENCODER_MASK_SH_LIST_DCN20(__SHIFT),\ + DPCS_DCN2_MASK_SH_LIST(__SHIFT) }; static const struct dcn10_link_enc_mask le_mask = { - LINK_ENCODER_MASK_SH_LIST_DCN20(_MASK) + LINK_ENCODER_MASK_SH_LIST_DCN20(_MASK),\ + DPCS_DCN2_MASK_SH_LIST(_MASK) }; #define ipp_regs(id)\ @@ -632,6 +638,7 @@ static const struct dce110_aux_registers aux_engine_regs[] = { #define tf_regs(id)\ [id] = {\ TF_REG_LIST_DCN20(id),\ + TF_REG_LIST_DCN20_COMMON_APPEND(id),\ } static const struct dcn2_dpp_registers tf_regs[] = { @@ -645,12 +652,12 @@ static const struct dcn2_dpp_registers tf_regs[] = { static const struct dcn2_dpp_shift tf_shift = { TF_REG_LIST_SH_MASK_DCN20(__SHIFT), - TF_DEBUG_REG_LIST_SH_DCN10 + TF_DEBUG_REG_LIST_SH_DCN20 }; static const struct dcn2_dpp_mask tf_mask = { TF_REG_LIST_SH_MASK_DCN20(_MASK), - TF_DEBUG_REG_LIST_MASK_DCN10 + TF_DEBUG_REG_LIST_MASK_DCN20 }; #define dwbc_regs_dcn2(id)\ @@ -700,14 +707,17 @@ static const struct dcn20_mpc_registers mpc_regs = { MPC_OUT_MUX_REG_LIST_DCN2_0(3), MPC_OUT_MUX_REG_LIST_DCN2_0(4), MPC_OUT_MUX_REG_LIST_DCN2_0(5), + MPC_DBG_REG_LIST_DCN2_0() }; static const struct dcn20_mpc_shift mpc_shift = { - MPC_COMMON_MASK_SH_LIST_DCN2_0(__SHIFT) + MPC_COMMON_MASK_SH_LIST_DCN2_0(__SHIFT), + MPC_DEBUG_REG_LIST_SH_DCN20 }; static const struct dcn20_mpc_mask mpc_mask = { - MPC_COMMON_MASK_SH_LIST_DCN2_0(_MASK) + MPC_COMMON_MASK_SH_LIST_DCN2_0(_MASK), + MPC_DEBUG_REG_LIST_MASK_DCN20 }; #define tg_regs(id)\ @@ -1563,7 +1573,7 @@ static void release_dsc(struct resource_context *res_ctx, -static enum dc_status add_dsc_to_stream_resource(struct dc *dc, +enum dc_status dcn20_add_dsc_to_stream_resource(struct dc *dc, struct dc_state *dc_ctx, struct dc_stream_state *dc_stream) { @@ -1578,6 +1588,9 @@ static enum dc_status add_dsc_to_stream_resource(struct dc *dc, if (pipe_ctx->stream != dc_stream) continue; + if (pipe_ctx->stream_res.dsc) + continue; + acquire_dsc(&dc_ctx->res_ctx, pool, &pipe_ctx->stream_res.dsc, i); /* The number of DSCs can be less than the number of pipes */ @@ -1626,7 +1639,7 @@ enum dc_status dcn20_add_stream_to_ctx(struct dc *dc, struct dc_state *new_ctx, /* Get a DSC if required and available */ if (result == DC_OK && dc_stream->timing.flags.DSC) - result = add_dsc_to_stream_resource(dc, new_ctx, dc_stream); + result = dcn20_add_dsc_to_stream_resource(dc, new_ctx, dc_stream); if (result == DC_OK) result = dcn20_build_mapped_resource(dc, new_ctx, dc_stream); @@ -1848,6 +1861,22 @@ void dcn20_populate_dml_writeback_from_context( } +static int get_num_odm_heads(struct pipe_ctx *pipe) +{ + int odm_head_count = 0; + struct pipe_ctx *next_pipe = pipe->next_odm_pipe; + while (next_pipe) { + odm_head_count++; + next_pipe = next_pipe->next_odm_pipe; + } + pipe = pipe->prev_odm_pipe; + while (pipe) { + odm_head_count++; + pipe = pipe->prev_odm_pipe; + } + return odm_head_count ? odm_head_count + 1 : 0; +} + int dcn20_populate_dml_pipes_from_context( struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes) { @@ -1874,17 +1903,21 @@ int dcn20_populate_dml_pipes_from_context( for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) { struct dc_crtc_timing *timing = &res_ctx->pipe_ctx[i].stream->timing; unsigned int v_total; + unsigned int front_porch; int output_bpc; if (!res_ctx->pipe_ctx[i].stream) continue; v_total = timing->v_total; + front_porch = timing->v_front_porch; /* todo: pipes[pipe_cnt].pipe.src.dynamic_metadata_enable = 0; pipes[pipe_cnt].pipe.src.dcc = 0; pipes[pipe_cnt].pipe.src.vm = 0;*/ + pipes[pipe_cnt].clks_cfg.refclk_mhz = dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000.0; + pipes[pipe_cnt].dout.dsc_enable = res_ctx->pipe_ctx[i].stream->timing.flags.DSC; /* todo: rotation?*/ pipes[pipe_cnt].dout.dsc_slices = res_ctx->pipe_ctx[i].stream->timing.dsc_cfg.num_slices_h; @@ -1906,7 +1939,7 @@ int dcn20_populate_dml_pipes_from_context( - timing->h_addressable - timing->h_border_left - timing->h_border_right; - pipes[pipe_cnt].pipe.dest.vblank_start = v_total - timing->v_front_porch; + pipes[pipe_cnt].pipe.dest.vblank_start = v_total - front_porch; pipes[pipe_cnt].pipe.dest.vblank_end = pipes[pipe_cnt].pipe.dest.vblank_start - timing->v_addressable - timing->v_border_top @@ -1923,8 +1956,13 @@ int dcn20_populate_dml_pipes_from_context( pipes[pipe_cnt].dout.dp_lanes = 4; pipes[pipe_cnt].pipe.dest.vtotal_min = res_ctx->pipe_ctx[i].stream->adjust.v_total_min; pipes[pipe_cnt].pipe.dest.vtotal_max = res_ctx->pipe_ctx[i].stream->adjust.v_total_max; - pipes[pipe_cnt].pipe.dest.odm_combine = res_ctx->pipe_ctx[i].prev_odm_pipe - || res_ctx->pipe_ctx[i].next_odm_pipe; + switch (get_num_odm_heads(&res_ctx->pipe_ctx[i])) { + case 2: + pipes[pipe_cnt].pipe.dest.odm_combine = dm_odm_combine_mode_2to1; + break; + default: + pipes[pipe_cnt].pipe.dest.odm_combine = dm_odm_combine_mode_disabled; + } pipes[pipe_cnt].pipe.src.hsplit_grp = res_ctx->pipe_ctx[i].pipe_idx; if (res_ctx->pipe_ctx[i].top_pipe && res_ctx->pipe_ctx[i].top_pipe->plane_state == res_ctx->pipe_ctx[i].plane_state) @@ -2034,6 +2072,9 @@ int dcn20_populate_dml_pipes_from_context( if (pipes[pipe_cnt].pipe.src.viewport_height > 1080) pipes[pipe_cnt].pipe.src.viewport_height = 1080; pipes[pipe_cnt].pipe.src.surface_height_y = pipes[pipe_cnt].pipe.src.viewport_height; + pipes[pipe_cnt].pipe.src.surface_width_y = pipes[pipe_cnt].pipe.src.viewport_width; + pipes[pipe_cnt].pipe.src.surface_height_c = pipes[pipe_cnt].pipe.src.viewport_height; + pipes[pipe_cnt].pipe.src.surface_width_c = pipes[pipe_cnt].pipe.src.viewport_width; pipes[pipe_cnt].pipe.src.data_pitch = ((pipes[pipe_cnt].pipe.src.viewport_width + 63) / 64) * 64; /* linear sw only */ pipes[pipe_cnt].pipe.src.source_format = dm_444_32; pipes[pipe_cnt].pipe.dest.recout_width = pipes[pipe_cnt].pipe.src.viewport_width; /*vp_width/hratio*/ @@ -2067,7 +2108,10 @@ int dcn20_populate_dml_pipes_from_context( pipes[pipe_cnt].pipe.src.viewport_width_c = scl->viewport_c.width; pipes[pipe_cnt].pipe.src.viewport_height = scl->viewport.height; pipes[pipe_cnt].pipe.src.viewport_height_c = scl->viewport_c.height; + pipes[pipe_cnt].pipe.src.surface_width_y = pln->plane_size.surface_size.width; pipes[pipe_cnt].pipe.src.surface_height_y = pln->plane_size.surface_size.height; + pipes[pipe_cnt].pipe.src.surface_width_c = pln->plane_size.chroma_size.width; + pipes[pipe_cnt].pipe.src.surface_height_c = pln->plane_size.chroma_size.height; if (pln->format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN) { pipes[pipe_cnt].pipe.src.data_pitch = pln->plane_size.surface_pitch; pipes[pipe_cnt].pipe.src.data_pitch_c = pln->plane_size.chroma_pitch; @@ -2481,7 +2525,7 @@ int dcn20_validate_apply_pipe_split_flags( split[i] = true; if (dc->debug.force_odm_combine & (1 << pipe->stream_res.tg->inst)) { split[i] = true; - context->bw_ctx.dml.vba.ODMCombineEnablePerState[vlevel][pipe_idx] = true; + context->bw_ctx.dml.vba.ODMCombineEnablePerState[vlevel][pipe_idx] = dm_odm_combine_mode_2to1; } context->bw_ctx.dml.vba.ODMCombineEnabled[pipe_idx] = context->bw_ctx.dml.vba.ODMCombineEnablePerState[vlevel][pipe_idx]; @@ -2886,12 +2930,19 @@ bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context, bool voltage_supported = false; bool full_pstate_supported = false; bool dummy_pstate_supported = false; - double p_state_latency_us = context->bw_ctx.dml.soc.dram_clock_change_latency_us; - context->bw_ctx.dml.soc.disable_dram_clock_change_vactive_support = dc->debug.disable_dram_clock_change_vactive_support; + double p_state_latency_us; - if (fast_validate) - return dcn20_validate_bandwidth_internal(dc, context, true); + DC_FP_START(); + p_state_latency_us = context->bw_ctx.dml.soc.dram_clock_change_latency_us; + context->bw_ctx.dml.soc.disable_dram_clock_change_vactive_support = + dc->debug.disable_dram_clock_change_vactive_support; + if (fast_validate) { + voltage_supported = dcn20_validate_bandwidth_internal(dc, context, true); + + DC_FP_END(); + return voltage_supported; + } // Best case, we support full UCLK switch latency voltage_supported = dcn20_validate_bandwidth_internal(dc, context, false); @@ -2899,7 +2950,7 @@ bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context, if (context->bw_ctx.dml.soc.dummy_pstate_latency_us == 0 || (voltage_supported && full_pstate_supported)) { - context->bw_ctx.bw.dcn.clk.p_state_change_support = true; + context->bw_ctx.bw.dcn.clk.p_state_change_support = full_pstate_supported; goto restore_dml_state; } @@ -2920,6 +2971,7 @@ bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context, restore_dml_state: context->bw_ctx.dml.soc.dram_clock_change_latency_us = p_state_latency_us; + DC_FP_END(); return voltage_supported; } @@ -3211,7 +3263,6 @@ void dcn20_update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_s void dcn20_patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb) { - kernel_fpu_begin(); if ((int)(bb->sr_exit_time_us * 1000) != dc->bb_overrides.sr_exit_time_ns && dc->bb_overrides.sr_exit_time_ns) { bb->sr_exit_time_us = dc->bb_overrides.sr_exit_time_ns / 1000.0; @@ -3235,7 +3286,6 @@ void dcn20_patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st bb->dram_clock_change_latency_us = dc->bb_overrides.dram_clock_change_latency_ns / 1000.0; } - kernel_fpu_end(); } static struct _vcs_dpi_soc_bounding_box_st *get_asic_rev_soc_bb( @@ -3441,6 +3491,8 @@ static bool dcn20_resource_construct( enum dml_project dml_project_version = get_dml_project_version(ctx->asic_id.hw_internal_rev); + DC_FP_START(); + ctx->dc_bios->regs = &bios_regs; pool->base.funcs = &dcn20_res_pool_funcs; @@ -3738,10 +3790,12 @@ static bool dcn20_resource_construct( pool->base.oem_device = NULL; } + DC_FP_END(); return true; create_fail: + DC_FP_END(); dcn20_resource_destruct(pool); return false; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h index 840ca66c34e1..f5893840b79b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h @@ -157,6 +157,7 @@ void dcn20_calculate_dlg_params( enum dc_status dcn20_build_mapped_resource(const struct dc *dc, struct dc_state *context, struct dc_stream_state *stream); enum dc_status dcn20_add_stream_to_ctx(struct dc *dc, struct dc_state *new_ctx, struct dc_stream_state *dc_stream); +enum dc_status dcn20_add_dsc_to_stream_resource(struct dc *dc, struct dc_state *dc_ctx, struct dc_stream_state *dc_stream); enum dc_status dcn20_remove_stream_from_ctx(struct dc *dc, struct dc_state *new_ctx, struct dc_stream_state *dc_stream); enum dc_status dcn20_get_default_swizzle_mode(struct dc_plane_state *plane_state); diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile index 4763721fb1c9..07684d3e375a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile @@ -5,7 +5,13 @@ DCN21 = dcn21_init.o dcn21_hubp.o dcn21_hubbub.o dcn21_resource.o \ dcn21_hwseq.o dcn21_link_encoder.o +ifdef CONFIG_X86 CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse +endif + +ifdef CONFIG_PPC64 +CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -maltivec +endif ifdef CONFIG_CC_IS_GCC ifeq ($(call cc-ifversion, -lt, 0701, y), y) @@ -13,6 +19,7 @@ IS_OLD_GCC = 1 endif endif +ifdef CONFIG_X86 ifdef IS_OLD_GCC # Stack alignment mismatch, proceed with caution. # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 @@ -21,6 +28,7 @@ CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -mpreferred-stack-boundary=4 else CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -msse2 endif +endif AMD_DAL_DCN21 = $(addprefix $(AMDDALPATH)/dc/dcn21/,$(DCN21)) 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 332bf3d3a664..cf09b9335728 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c @@ -29,6 +29,8 @@ #include "dm_services.h" #include "reg_helper.h" +#include "dc_dmub_srv.h" + #define DC_LOGGER_INIT(logger) #define REG(reg)\ @@ -169,12 +171,9 @@ static void hubp21_setup( void hubp21_set_viewport( struct hubp *hubp, const struct rect *viewport, - const struct rect *viewport_c, - enum dc_rotation_angle rotation) + const struct rect *viewport_c) { struct dcn21_hubp *hubp21 = TO_DCN21_HUBP(hubp); - int patched_viewport_height = 0; - struct dc_debug_options *debug = &hubp->ctx->dc->debug; REG_SET_2(DCSURF_PRI_VIEWPORT_DIMENSION, 0, PRI_VIEWPORT_WIDTH, viewport->width, @@ -193,31 +192,10 @@ void hubp21_set_viewport( SEC_VIEWPORT_X_START, viewport->x, SEC_VIEWPORT_Y_START, viewport->y); - /* - * Work around for underflow issue with NV12 + rIOMMU translation - * + immediate flip. This will cause hubp underflow, but will not - * be user visible since underflow is in blank region - * Disable w/a when rotated 180 degrees, causes vertical chroma offset - */ - patched_viewport_height = viewport_c->height; - if (debug->nv12_iflip_vm_wa && viewport_c->height > 512 && - rotation != ROTATION_ANGLE_180) { - int pte_row_height = 0; - int pte_rows = 0; - - REG_GET(DCHUBP_REQ_SIZE_CONFIG_C, - PTE_ROW_HEIGHT_LINEAR_C, &pte_row_height); - - pte_row_height = 1 << (pte_row_height + 3); - pte_rows = (viewport_c->height / pte_row_height) + 1; - patched_viewport_height = pte_rows * pte_row_height + 1; - } - - /* DC supports NV12 only at the moment */ REG_SET_2(DCSURF_PRI_VIEWPORT_DIMENSION_C, 0, PRI_VIEWPORT_WIDTH_C, viewport_c->width, - PRI_VIEWPORT_HEIGHT_C, patched_viewport_height); + PRI_VIEWPORT_HEIGHT_C, viewport_c->height); REG_SET_2(DCSURF_PRI_VIEWPORT_START_C, 0, PRI_VIEWPORT_X_START_C, viewport_c->x, @@ -225,13 +203,123 @@ void hubp21_set_viewport( REG_SET_2(DCSURF_SEC_VIEWPORT_DIMENSION_C, 0, SEC_VIEWPORT_WIDTH_C, viewport_c->width, - SEC_VIEWPORT_HEIGHT_C, patched_viewport_height); + SEC_VIEWPORT_HEIGHT_C, viewport_c->height); REG_SET_2(DCSURF_SEC_VIEWPORT_START_C, 0, SEC_VIEWPORT_X_START_C, viewport_c->x, SEC_VIEWPORT_Y_START_C, viewport_c->y); } +static void hubp21_apply_PLAT_54186_wa( + struct hubp *hubp, + const struct dc_plane_address *address) +{ + struct dcn21_hubp *hubp21 = TO_DCN21_HUBP(hubp); + struct dc_debug_options *debug = &hubp->ctx->dc->debug; + unsigned int chroma_bpe = 2; + unsigned int luma_addr_high_part = 0; + unsigned int row_height = 0; + unsigned int chroma_pitch = 0; + unsigned int viewport_c_height = 0; + unsigned int viewport_c_width = 0; + unsigned int patched_viewport_height = 0; + unsigned int patched_viewport_width = 0; + unsigned int rotation_angle = 0; + unsigned int pix_format = 0; + unsigned int h_mirror_en = 0; + unsigned int tile_blk_size = 64 * 1024; /* 64KB for 64KB SW, 4KB for 4KB SW */ + + + if (!debug->nv12_iflip_vm_wa) + return; + + REG_GET(DCHUBP_REQ_SIZE_CONFIG_C, + PTE_ROW_HEIGHT_LINEAR_C, &row_height); + + REG_GET_2(DCSURF_PRI_VIEWPORT_DIMENSION_C, + PRI_VIEWPORT_WIDTH_C, &viewport_c_width, + PRI_VIEWPORT_HEIGHT_C, &viewport_c_height); + + REG_GET(DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C, + PRIMARY_SURFACE_ADDRESS_HIGH_C, &luma_addr_high_part); + + REG_GET(DCSURF_SURFACE_PITCH_C, + PITCH_C, &chroma_pitch); + + chroma_pitch += 1; + + REG_GET_3(DCSURF_SURFACE_CONFIG, + SURFACE_PIXEL_FORMAT, &pix_format, + ROTATION_ANGLE, &rotation_angle, + H_MIRROR_EN, &h_mirror_en); + + /* reset persistent cached data */ + hubp21->PLAT_54186_wa_chroma_addr_offset = 0; + /* apply wa only for NV12 surface with scatter gather enabled with viewport > 512 along + * the vertical direction*/ + if (address->type != PLN_ADDR_TYPE_VIDEO_PROGRESSIVE || + address->video_progressive.luma_addr.high_part == 0xf4) + return; + + if ((rotation_angle == ROTATION_ANGLE_0 || rotation_angle == ROTATION_ANGLE_180) + && viewport_c_height <= 512) + return; + + if ((rotation_angle == ROTATION_ANGLE_90 || rotation_angle == ROTATION_ANGLE_270) + && viewport_c_width <= 512) + return; + + switch (rotation_angle) { + case ROTATION_ANGLE_0: /* 0 degree rotation */ + row_height = 128; + patched_viewport_height = (viewport_c_height / row_height + 1) * row_height + 1; + patched_viewport_width = viewport_c_width; + hubp21->PLAT_54186_wa_chroma_addr_offset = 0; + break; + case ROTATION_ANGLE_180: /* 180 degree rotation */ + row_height = 128; + patched_viewport_height = viewport_c_height + row_height; + patched_viewport_width = viewport_c_width; + hubp21->PLAT_54186_wa_chroma_addr_offset = 0 - chroma_pitch * row_height * chroma_bpe; + break; + case ROTATION_ANGLE_90: /* 90 degree rotation */ + row_height = 256; + if (h_mirror_en) { + patched_viewport_height = viewport_c_height; + patched_viewport_width = viewport_c_width + row_height; + hubp21->PLAT_54186_wa_chroma_addr_offset = 0; + } else { + patched_viewport_height = viewport_c_height; + patched_viewport_width = viewport_c_width + row_height; + hubp21->PLAT_54186_wa_chroma_addr_offset = 0 - tile_blk_size; + } + break; + case ROTATION_ANGLE_270: /* 270 degree rotation */ + row_height = 256; + if (h_mirror_en) { + patched_viewport_height = viewport_c_height; + patched_viewport_width = viewport_c_width + row_height; + hubp21->PLAT_54186_wa_chroma_addr_offset = 0 - tile_blk_size; + } else { + patched_viewport_height = viewport_c_height; + patched_viewport_width = viewport_c_width + row_height; + hubp21->PLAT_54186_wa_chroma_addr_offset = 0; + } + break; + default: + ASSERT(0); + break; + } + + /* catch cases where viewport keep growing */ + ASSERT(patched_viewport_height && patched_viewport_height < 5000); + ASSERT(patched_viewport_width && patched_viewport_width < 5000); + + REG_UPDATE_2(DCSURF_PRI_VIEWPORT_DIMENSION_C, + PRI_VIEWPORT_WIDTH_C, patched_viewport_width, + PRI_VIEWPORT_HEIGHT_C, patched_viewport_height); +} + void hubp21_set_vm_system_aperture_settings(struct hubp *hubp, struct vm_system_aperture_param *apt) { @@ -602,6 +690,219 @@ void hubp21_validate_dml_output(struct hubp *hubp, dml_dlg_attr->refcyc_per_meta_chunk_flip_l, dlg_attr.refcyc_per_meta_chunk_flip_l); } +static void program_surface_flip_and_addr(struct hubp *hubp, struct surface_flip_registers *flip_regs) +{ + struct dcn21_hubp *hubp21 = TO_DCN21_HUBP(hubp); + + REG_UPDATE_3(DCSURF_FLIP_CONTROL, + SURFACE_FLIP_TYPE, flip_regs->immediate, + SURFACE_FLIP_MODE_FOR_STEREOSYNC, flip_regs->grph_stereo, + SURFACE_FLIP_IN_STEREOSYNC, flip_regs->grph_stereo); + + REG_UPDATE(VMID_SETTINGS_0, + VMID, flip_regs->vmid); + + REG_UPDATE_8(DCSURF_SURFACE_CONTROL, + PRIMARY_SURFACE_TMZ, flip_regs->tmz_surface, + PRIMARY_SURFACE_TMZ_C, flip_regs->tmz_surface, + PRIMARY_META_SURFACE_TMZ, flip_regs->tmz_surface, + PRIMARY_META_SURFACE_TMZ_C, flip_regs->tmz_surface, + SECONDARY_SURFACE_TMZ, flip_regs->tmz_surface, + SECONDARY_SURFACE_TMZ_C, flip_regs->tmz_surface, + SECONDARY_META_SURFACE_TMZ, flip_regs->tmz_surface, + SECONDARY_META_SURFACE_TMZ_C, flip_regs->tmz_surface); + + REG_SET(DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH_C, 0, + PRIMARY_META_SURFACE_ADDRESS_HIGH_C, + flip_regs->DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH_C); + + REG_SET(DCSURF_PRIMARY_META_SURFACE_ADDRESS_C, 0, + PRIMARY_META_SURFACE_ADDRESS_C, + flip_regs->DCSURF_PRIMARY_META_SURFACE_ADDRESS_C); + + REG_SET(DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH, 0, + PRIMARY_META_SURFACE_ADDRESS_HIGH, + flip_regs->DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH); + + REG_SET(DCSURF_PRIMARY_META_SURFACE_ADDRESS, 0, + PRIMARY_META_SURFACE_ADDRESS, + flip_regs->DCSURF_PRIMARY_META_SURFACE_ADDRESS); + + REG_SET(DCSURF_SECONDARY_META_SURFACE_ADDRESS_HIGH, 0, + SECONDARY_META_SURFACE_ADDRESS_HIGH, + flip_regs->DCSURF_SECONDARY_META_SURFACE_ADDRESS_HIGH); + + REG_SET(DCSURF_SECONDARY_META_SURFACE_ADDRESS, 0, + SECONDARY_META_SURFACE_ADDRESS, + flip_regs->DCSURF_SECONDARY_META_SURFACE_ADDRESS); + + + REG_SET(DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH, 0, + SECONDARY_SURFACE_ADDRESS_HIGH, + flip_regs->DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH); + + REG_SET(DCSURF_SECONDARY_SURFACE_ADDRESS, 0, + SECONDARY_SURFACE_ADDRESS, + flip_regs->DCSURF_SECONDARY_SURFACE_ADDRESS); + + + REG_SET(DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C, 0, + PRIMARY_SURFACE_ADDRESS_HIGH_C, + flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C); + + REG_SET(DCSURF_PRIMARY_SURFACE_ADDRESS_C, 0, + PRIMARY_SURFACE_ADDRESS_C, + flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS_C); + + REG_SET(DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH, 0, + PRIMARY_SURFACE_ADDRESS_HIGH, + flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH); + + REG_SET(DCSURF_PRIMARY_SURFACE_ADDRESS, 0, + PRIMARY_SURFACE_ADDRESS, + flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS); +} + +void dmcub_PLAT_54186_wa(struct hubp *hubp, struct surface_flip_registers *flip_regs) +{ + struct dc_dmub_srv *dmcub = hubp->ctx->dmub_srv; + struct dcn21_hubp *hubp21 = TO_DCN21_HUBP(hubp); + struct dmub_rb_cmd_PLAT_54186_wa PLAT_54186_wa = { 0 }; + + PLAT_54186_wa.header.type = DMUB_CMD__PLAT_54186_WA; + PLAT_54186_wa.flip.DCSURF_PRIMARY_SURFACE_ADDRESS = flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS; + PLAT_54186_wa.flip.DCSURF_PRIMARY_SURFACE_ADDRESS_C = flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS_C; + PLAT_54186_wa.flip.DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH = flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH; + PLAT_54186_wa.flip.DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C = flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C; + PLAT_54186_wa.flip.flip_params.grph_stereo = flip_regs->grph_stereo; + PLAT_54186_wa.flip.flip_params.hubp_inst = hubp->inst; + PLAT_54186_wa.flip.flip_params.immediate = flip_regs->immediate; + PLAT_54186_wa.flip.flip_params.tmz_surface = flip_regs->tmz_surface; + PLAT_54186_wa.flip.flip_params.vmid = flip_regs->vmid; + + PERF_TRACE(); // TODO: remove after performance is stable. + dc_dmub_srv_cmd_queue(dmcub, &PLAT_54186_wa.header); + PERF_TRACE(); // TODO: remove after performance is stable. + dc_dmub_srv_cmd_execute(dmcub); + PERF_TRACE(); // TODO: remove after performance is stable. + dc_dmub_srv_wait_idle(dmcub); + PERF_TRACE(); // TODO: remove after performance is stable. +} + +bool hubp21_program_surface_flip_and_addr( + struct hubp *hubp, + const struct dc_plane_address *address, + bool flip_immediate) +{ + struct dc_debug_options *debug = &hubp->ctx->dc->debug; + struct dcn21_hubp *hubp21 = TO_DCN21_HUBP(hubp); + struct surface_flip_registers flip_regs = { 0 }; + + flip_regs.vmid = address->vmid; + + switch (address->type) { + case PLN_ADDR_TYPE_GRAPHICS: + if (address->grph.addr.quad_part == 0) { + BREAK_TO_DEBUGGER(); + break; + } + + if (address->grph.meta_addr.quad_part != 0) { + flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS = + address->grph.meta_addr.low_part; + flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH = + address->grph.meta_addr.high_part; + } + + flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS = + address->grph.addr.low_part; + flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH = + address->grph.addr.high_part; + break; + case PLN_ADDR_TYPE_VIDEO_PROGRESSIVE: + if (address->video_progressive.luma_addr.quad_part == 0 + || address->video_progressive.chroma_addr.quad_part == 0) + break; + + if (address->video_progressive.luma_meta_addr.quad_part != 0) { + flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS = + address->video_progressive.luma_meta_addr.low_part; + flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH = + address->video_progressive.luma_meta_addr.high_part; + + flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS_C = + address->video_progressive.chroma_meta_addr.low_part; + flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH_C = + address->video_progressive.chroma_meta_addr.high_part; + } + + flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS = + address->video_progressive.luma_addr.low_part; + flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH = + address->video_progressive.luma_addr.high_part; + + if (debug->nv12_iflip_vm_wa) { + flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS_C = + address->video_progressive.chroma_addr.low_part + hubp21->PLAT_54186_wa_chroma_addr_offset; + } else + flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS_C = + address->video_progressive.chroma_addr.low_part; + + flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C = + address->video_progressive.chroma_addr.high_part; + + break; + case PLN_ADDR_TYPE_GRPH_STEREO: + if (address->grph_stereo.left_addr.quad_part == 0) + break; + if (address->grph_stereo.right_addr.quad_part == 0) + break; + + flip_regs.grph_stereo = true; + + if (address->grph_stereo.right_meta_addr.quad_part != 0) { + flip_regs.DCSURF_SECONDARY_META_SURFACE_ADDRESS = + address->grph_stereo.right_meta_addr.low_part; + flip_regs.DCSURF_SECONDARY_META_SURFACE_ADDRESS_HIGH = + address->grph_stereo.right_meta_addr.high_part; + } + + if (address->grph_stereo.left_meta_addr.quad_part != 0) { + flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS = + address->grph_stereo.left_meta_addr.low_part; + flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH = + address->grph_stereo.left_meta_addr.high_part; + } + + flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS = + address->grph_stereo.left_addr.low_part; + flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH = + address->grph_stereo.left_addr.high_part; + + flip_regs.DCSURF_SECONDARY_SURFACE_ADDRESS = + address->grph_stereo.right_addr.low_part; + flip_regs.DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH = + address->grph_stereo.right_addr.high_part; + + break; + default: + BREAK_TO_DEBUGGER(); + break; + } + + flip_regs.tmz_surface = address->tmz_surface; + flip_regs.immediate = flip_immediate; + + if (hubp->ctx->dc->debug.enable_dmcub_surface_flip && address->type == PLN_ADDR_TYPE_VIDEO_PROGRESSIVE) + dmcub_PLAT_54186_wa(hubp, &flip_regs); + else + program_surface_flip_and_addr(hubp, &flip_regs); + + hubp->request_address = *address; + + return true; +} + void hubp21_init(struct hubp *hubp) { // DEDCN21-133: Inconsistent row starting line for flip between DPTE and Meta @@ -614,7 +915,7 @@ void hubp21_init(struct hubp *hubp) static struct hubp_funcs dcn21_hubp_funcs = { .hubp_enable_tripleBuffer = hubp2_enable_triplebuffer, .hubp_is_triplebuffer_enabled = hubp2_is_triplebuffer_enabled, - .hubp_program_surface_flip_and_addr = hubp2_program_surface_flip_and_addr, + .hubp_program_surface_flip_and_addr = hubp21_program_surface_flip_and_addr, .hubp_program_surface_config = hubp1_program_surface_config, .hubp_is_flip_pending = hubp1_is_flip_pending, .hubp_setup = hubp21_setup, @@ -623,6 +924,7 @@ static struct hubp_funcs dcn21_hubp_funcs = { .set_blank = hubp1_set_blank, .dcc_control = hubp1_dcc_control, .mem_program_viewport = hubp21_set_viewport, + .apply_PLAT_54186_wa = hubp21_apply_PLAT_54186_wa, .set_cursor_attributes = hubp2_cursor_set_attributes, .set_cursor_position = hubp1_cursor_set_position, .hubp_clk_cntl = hubp1_clk_cntl, diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.h index aeda719a2a13..9873b6cbc5ba 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.h +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.h @@ -108,6 +108,7 @@ struct dcn21_hubp { const struct dcn_hubp2_registers *hubp_regs; const struct dcn_hubp2_shift *hubp_shift; const struct dcn_hubp2_mask *hubp_mask; + int PLAT_54186_wa_chroma_addr_offset; }; bool hubp21_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.h index 1d7a1a51f13d..033d5d76f195 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.h @@ -33,6 +33,45 @@ struct dcn21_link_encoder { struct dpcssys_phy_seq_cfg phy_seq_cfg; }; +#define DPCS_DCN21_MASK_SH_LIST(mask_sh)\ + DPCS_DCN2_MASK_SH_LIST(mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_TX_VBOOST_LVL, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE2, RDPCS_PHY_DP_MPLLB_CP_PROP_GS, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_RX_VREF_CTRL, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_MPLLB_CP_INT_GS, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG, RDPCS_DMCU_DPALT_DIS_BLOCK_REG, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL15, RDPCS_PHY_SUP_PRE_HP, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL15, RDPCS_PHY_DP_TX0_VREGDRV_BYP, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL15, RDPCS_PHY_DP_TX1_VREGDRV_BYP, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL15, RDPCS_PHY_DP_TX2_VREGDRV_BYP, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL15, RDPCS_PHY_DP_TX3_VREGDRV_BYP, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DP4, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_TX0_EQ_MAIN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_TX0_EQ_PRE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_TX0_EQ_POST, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_TX1_EQ_MAIN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_TX1_EQ_PRE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_TX1_EQ_POST, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE2, RDPCS_PHY_DP_TX2_EQ_MAIN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE2, RDPCS_PHY_DP_TX2_EQ_PRE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE2, RDPCS_PHY_DP_TX2_EQ_POST, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DP_TX3_EQ_MAIN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DCO_FINETUNE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DCO_RANGE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DP_TX3_EQ_PRE, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DP_TX3_EQ_POST, mask_sh),\ + LE_SF(DCIO_SOFT_RESET, UNIPHYA_SOFT_RESET, mask_sh),\ + LE_SF(DCIO_SOFT_RESET, UNIPHYB_SOFT_RESET, mask_sh),\ + LE_SF(DCIO_SOFT_RESET, UNIPHYC_SOFT_RESET, mask_sh),\ + LE_SF(DCIO_SOFT_RESET, UNIPHYD_SOFT_RESET, mask_sh),\ + LE_SF(DCIO_SOFT_RESET, UNIPHYE_SOFT_RESET, mask_sh) + +#define DPCS_DCN21_REG_LIST(id) \ + DPCS_DCN2_REG_LIST(id),\ + SRI(RDPCSTX_PHY_CNTL15, RDPCSTX, id),\ + SRI(RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG, RDPCSTX, id) + #define LINK_ENCODER_MASK_SH_LIST_DCN21(mask_sh)\ LINK_ENCODER_MASK_SH_LIST_DCN20(mask_sh),\ LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_CHANNEL0_XBAR_SOURCE, mask_sh),\ 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 c865b95d5c0e..33d0a176841a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -1,5 +1,6 @@ /* * Copyright 2018 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"), @@ -59,9 +60,12 @@ #include "dcn20/dcn20_dccg.h" #include "dcn21_hubbub.h" #include "dcn10/dcn10_resource.h" +#include "dce110/dce110_resource.h" #include "dcn20/dcn20_dwb.h" #include "dcn20/dcn20_mmhubbub.h" +#include "dpcs/dpcs_2_1_0_offset.h" +#include "dpcs/dpcs_2_1_0_sh_mask.h" #include "renoir_ip_offset.h" #include "dcn/dcn_2_1_0_offset.h" @@ -80,6 +84,7 @@ #include "dcn21_resource.h" #include "vm_helper.h" #include "dcn20/dcn20_vmid.h" +#include "../dce/dmub_psr.h" #define SOC_BOUNDING_BOX_VALID false #define DC_LOGGER_INIT(logger) @@ -462,15 +467,18 @@ static const struct dcn20_mpc_registers mpc_regs = { MPC_OUT_MUX_REG_LIST_DCN2_0(0), MPC_OUT_MUX_REG_LIST_DCN2_0(1), MPC_OUT_MUX_REG_LIST_DCN2_0(2), - MPC_OUT_MUX_REG_LIST_DCN2_0(3) + MPC_OUT_MUX_REG_LIST_DCN2_0(3), + MPC_DBG_REG_LIST_DCN2_0() }; static const struct dcn20_mpc_shift mpc_shift = { - MPC_COMMON_MASK_SH_LIST_DCN2_0(__SHIFT) + MPC_COMMON_MASK_SH_LIST_DCN2_0(__SHIFT), + MPC_DEBUG_REG_LIST_SH_DCN20 }; static const struct dcn20_mpc_mask mpc_mask = { - MPC_COMMON_MASK_SH_LIST_DCN2_0(_MASK) + MPC_COMMON_MASK_SH_LIST_DCN2_0(_MASK), + MPC_DEBUG_REG_LIST_MASK_DCN20 }; #define hubp_regs(id)\ @@ -605,6 +613,7 @@ static const struct dce110_aux_registers aux_engine_regs[] = { #define tf_regs(id)\ [id] = {\ TF_REG_LIST_DCN20(id),\ + TF_REG_LIST_DCN20_COMMON_APPEND(id),\ } static const struct dcn2_dpp_registers tf_regs[] = { @@ -615,11 +624,13 @@ static const struct dcn2_dpp_registers tf_regs[] = { }; static const struct dcn2_dpp_shift tf_shift = { - TF_REG_LIST_SH_MASK_DCN20(__SHIFT) + TF_REG_LIST_SH_MASK_DCN20(__SHIFT), + TF_DEBUG_REG_LIST_SH_DCN20 }; static const struct dcn2_dpp_mask tf_mask = { - TF_REG_LIST_SH_MASK_DCN20(_MASK) + TF_REG_LIST_SH_MASK_DCN20(_MASK), + TF_DEBUG_REG_LIST_MASK_DCN20 }; #define stream_enc_regs(id)\ @@ -820,12 +831,13 @@ static const struct dc_debug_options debug_defaults_drv = { .disable_dcc = DCC_ENABLE, .vsr_support = true, .performance_trace = false, - .max_downscale_src_width = 3840, + .max_downscale_src_width = 4096, .disable_pplib_wm_range = false, .scl_reset_length10 = true, .sanity_checks = true, .disable_48mhz_pwrdwn = false, - .nv12_iflip_vm_wa = true + .nv12_iflip_vm_wa = true, + .usbc_combo_phy_reset_wa = true }; static const struct dc_debug_options debug_defaults_diags = { @@ -845,6 +857,7 @@ static const struct dc_debug_options debug_defaults_diags = { enum dcn20_clk_src_array_id { DCN20_CLK_SRC_PLL0, DCN20_CLK_SRC_PLL1, + DCN20_CLK_SRC_PLL2, DCN20_CLK_SRC_TOTAL_DCN21 }; @@ -993,7 +1006,8 @@ static void patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_s { int i; - kernel_fpu_begin(); + 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 = @@ -1019,7 +1033,7 @@ static void patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_s } } - kernel_fpu_end(); + DC_FP_END(); } void dcn21_calculate_wm( @@ -1319,12 +1333,6 @@ struct display_stream_compressor *dcn21_dsc_create( static void update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params) { - /* - TODO: Fix this function to calcualte correct values. - There are known issues with this function currently - that will need to be investigated. Use hardcoded known good values for now. - - struct dcn21_resource_pool *pool = TO_DCN21_RES_POOL(dc->res_pool); struct clk_limit_table *clk_table = &bw_params->clk_table; int i; @@ -1339,11 +1347,14 @@ static void update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param dcn2_1_soc.clock_limits[i].dcfclk_mhz = clk_table->entries[i].dcfclk_mhz; dcn2_1_soc.clock_limits[i].fabricclk_mhz = clk_table->entries[i].fclk_mhz; dcn2_1_soc.clock_limits[i].socclk_mhz = clk_table->entries[i].socclk_mhz; - dcn2_1_soc.clock_limits[i].dram_speed_mts = clk_table->entries[i].memclk_mhz * 16 / 1000; + dcn2_1_soc.clock_limits[i].dram_speed_mts = clk_table->entries[i].memclk_mhz * 2; } - dcn2_1_soc.clock_limits[i] = dcn2_1_soc.clock_limits[i - i]; + dcn2_1_soc.clock_limits[i] = dcn2_1_soc.clock_limits[i - 1]; dcn2_1_soc.num_states = i; - */ + + // diags does not retrieve proper values from SMU, do not update DML instance for diags + if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment) && !IS_DIAG_DC(dc->ctx->dce_environment)) + dml_init_instance(&dc->dml, &dcn2_1_soc, &dcn2_1_ip, DML_PROJECT_DCN21); } /* Temporary Place holder until we can get them from fuse */ @@ -1497,8 +1508,9 @@ static const struct encoder_feature_support link_enc_feature = { #define link_regs(id, phyid)\ [id] = {\ - LE_DCN10_REG_LIST(id), \ + LE_DCN2_REG_LIST(id), \ UNIPHY_DCN2_REG_LIST(phyid), \ + DPCS_DCN21_REG_LIST(id), \ SRI(DP_DPHY_INTERNAL_CTRL, DP, id) \ } @@ -1537,11 +1549,13 @@ static const struct dcn10_link_enc_hpd_registers link_enc_hpd_regs[] = { }; static const struct dcn10_link_enc_shift le_shift = { - LINK_ENCODER_MASK_SH_LIST_DCN20(__SHIFT) + LINK_ENCODER_MASK_SH_LIST_DCN20(__SHIFT),\ + DPCS_DCN21_MASK_SH_LIST(__SHIFT) }; static const struct dcn10_link_enc_mask le_mask = { - LINK_ENCODER_MASK_SH_LIST_DCN20(_MASK) + LINK_ENCODER_MASK_SH_LIST_DCN20(_MASK),\ + DPCS_DCN21_MASK_SH_LIST(_MASK) }; static int map_transmitter_id_to_phy_instance( @@ -1706,6 +1720,10 @@ static bool dcn21_resource_construct( dcn21_clock_source_create(ctx, ctx->dc_bios, CLOCK_SOURCE_COMBO_PHY_PLL1, &clk_src_regs[1], false); + pool->base.clock_sources[DCN20_CLK_SRC_PLL2] = + dcn21_clock_source_create(ctx, ctx->dc_bios, + CLOCK_SOURCE_COMBO_PHY_PLL2, + &clk_src_regs[2], false); pool->base.clk_src_count = DCN20_CLK_SRC_TOTAL_DCN21; @@ -1740,6 +1758,10 @@ static bool dcn21_resource_construct( goto create_fail; } + // Leave as NULL to not affect current dmcu psr programming sequence + // Will be uncommented when functionality is confirmed to be working + pool->base.psr = NULL; + pool->base.abm = dce_abm_create(ctx, &abm_regs, &abm_shift, @@ -1776,41 +1798,41 @@ static bool dcn21_resource_construct( if ((pipe_fuses & (1 << i)) != 0) continue; - pool->base.hubps[i] = dcn21_hubp_create(ctx, i); - if (pool->base.hubps[i] == NULL) { + pool->base.hubps[j] = dcn21_hubp_create(ctx, i); + if (pool->base.hubps[j] == NULL) { BREAK_TO_DEBUGGER(); dm_error( "DC: failed to create memory input!\n"); goto create_fail; } - pool->base.ipps[i] = dcn21_ipp_create(ctx, i); - if (pool->base.ipps[i] == NULL) { + pool->base.ipps[j] = dcn21_ipp_create(ctx, i); + if (pool->base.ipps[j] == NULL) { BREAK_TO_DEBUGGER(); dm_error( "DC: failed to create input pixel processor!\n"); goto create_fail; } - pool->base.dpps[i] = dcn21_dpp_create(ctx, i); - if (pool->base.dpps[i] == NULL) { + pool->base.dpps[j] = dcn21_dpp_create(ctx, i); + if (pool->base.dpps[j] == NULL) { BREAK_TO_DEBUGGER(); dm_error( "DC: failed to create dpps!\n"); goto create_fail; } - pool->base.opps[i] = dcn21_opp_create(ctx, i); - if (pool->base.opps[i] == NULL) { + pool->base.opps[j] = dcn21_opp_create(ctx, i); + if (pool->base.opps[j] == NULL) { BREAK_TO_DEBUGGER(); dm_error( "DC: failed to create output pixel processor!\n"); goto create_fail; } - pool->base.timing_generators[i] = dcn21_timing_generator_create( + pool->base.timing_generators[j] = dcn21_timing_generator_create( ctx, i); - if (pool->base.timing_generators[i] == NULL) { + if (pool->base.timing_generators[j] == NULL) { BREAK_TO_DEBUGGER(); dm_error("DC: failed to create tg!\n"); goto create_fail; diff --git a/drivers/gpu/drm/amd/display/dc/dm_services_types.h b/drivers/gpu/drm/amd/display/dc/dm_services_types.h index a3d1be20dd9d..b52ba6ffabe1 100644 --- a/drivers/gpu/drm/amd/display/dc/dm_services_types.h +++ b/drivers/gpu/drm/amd/display/dc/dm_services_types.h @@ -220,6 +220,7 @@ struct dm_bl_data_point { }; /* Total size of the structure should not exceed 256 bytes */ +#define BL_DATA_POINTS 99 struct dm_acpi_atif_backlight_caps { uint16_t size; /* Bytes 0-1 (2 bytes) */ uint16_t flags; /* Byted 2-3 (2 bytes) */ @@ -229,7 +230,7 @@ struct dm_acpi_atif_backlight_caps { uint8_t min_input_signal; /* Byte 7 */ uint8_t max_input_signal; /* Byte 8 */ uint8_t num_data_points; /* Byte 9 */ - struct dm_bl_data_point data_points[99]; /* Bytes 10-207 (198 bytes)*/ + struct dm_bl_data_point data_points[BL_DATA_POINTS]; /* Bytes 10-207 (198 bytes)*/ }; enum dm_acpi_display_type { diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile index fb6358036be8..7ee8b8460a9b 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml/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"), @@ -24,7 +25,13 @@ # It provides the general basic services required by other DAL # subcomponents. +ifdef CONFIG_X86 dml_ccflags := -mhard-float -msse +endif + +ifdef CONFIG_PPC64 +dml_ccflags := -mhard-float -maltivec +endif ifdef CONFIG_CC_IS_GCC ifeq ($(call cc-ifversion, -lt, 0701, y), y) @@ -32,6 +39,7 @@ IS_OLD_GCC = 1 endif endif +ifdef CONFIG_X86 ifdef IS_OLD_GCC # Stack alignment mismatch, proceed with caution. # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 @@ -40,6 +48,7 @@ dml_ccflags += -mpreferred-stack-boundary=4 else dml_ccflags += -msse2 endif +endif CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c index 3b224b155e8c..45f028986a8d 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c @@ -38,6 +38,7 @@ #define BPP_INVALID 0 #define BPP_BLENDED_PIPE 0xffffffff +#define DCN20_MAX_420_IMAGE_WIDTH 4096 static double adjust_ReturnBW( struct display_mode_lib *mode_lib, @@ -937,7 +938,7 @@ static unsigned int CalculateVMAndRowBytes( *MetaRowByte = 0; } - if (SurfaceTiling == dm_sw_linear || SurfaceTiling == dm_sw_gfx7_2d_thin_gl || SurfaceTiling == dm_sw_gfx7_2d_thin_lvp) { + if (SurfaceTiling == dm_sw_linear || SurfaceTiling == dm_sw_gfx7_2d_thin_gl || SurfaceTiling == dm_sw_gfx7_2d_thin_l_vp) { MacroTileSizeBytes = 256; MacroTileHeight = BlockHeight256Bytes; } else if (SurfaceTiling == dm_sw_4kb_s || SurfaceTiling == dm_sw_4kb_s_x @@ -1335,11 +1336,11 @@ static void dml20_DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPer else mode_lib->vba.SwathWidthSingleDPPY[k] = mode_lib->vba.ViewportHeight[k]; - if (mode_lib->vba.ODMCombineEnabled[k] == true) + if (mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) MainPlaneDoesODMCombine = true; for (j = 0; j < mode_lib->vba.NumberOfActivePlanes; ++j) if (mode_lib->vba.BlendingAndTiming[k] == j - && mode_lib->vba.ODMCombineEnabled[j] == true) + && mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) MainPlaneDoesODMCombine = true; if (MainPlaneDoesODMCombine == true) @@ -2848,12 +2849,12 @@ static void dml20_DisplayPipeConfiguration(struct display_mode_lib *mode_lib) SwathWidth = mode_lib->vba.ViewportHeight[k]; } - if (mode_lib->vba.ODMCombineEnabled[k] == true) { + if (mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) { MainPlaneDoesODMCombine = true; } for (j = 0; j < mode_lib->vba.NumberOfActivePlanes; ++j) { if (mode_lib->vba.BlendingAndTiming[k] == j - && mode_lib->vba.ODMCombineEnabled[j] == true) { + && mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) { MainPlaneDoesODMCombine = true; } } @@ -3348,7 +3349,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l == dm_420_10)) || (((mode_lib->vba.SurfaceTiling[k] == dm_sw_gfx7_2d_thin_gl || mode_lib->vba.SurfaceTiling[k] - == dm_sw_gfx7_2d_thin_lvp) + == dm_sw_gfx7_2d_thin_l_vp) && !((mode_lib->vba.SourcePixelFormat[k] == dm_444_64 || mode_lib->vba.SourcePixelFormat[k] @@ -3446,10 +3447,10 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l locals->FabricAndDRAMBandwidthPerState[i] * 1000) * locals->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelDataOnly / 100; - locals->ReturnBWPerState[i] = locals->ReturnBWToDCNPerState; + locals->ReturnBWPerState[i][0] = locals->ReturnBWToDCNPerState; if (locals->DCCEnabledInAnyPlane == true && locals->ReturnBWToDCNPerState > locals->DCFCLKPerState[i] * locals->ReturnBusWidth / 4) { - locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i], + locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0], locals->ReturnBWToDCNPerState * 4 * (1 - locals->UrgentLatency / ((locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024 / (locals->ReturnBWToDCNPerState - locals->DCFCLKPerState[i] @@ -3460,7 +3461,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l + (locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024); if (locals->DCCEnabledInAnyPlane && locals->CriticalPoint > 1 && locals->CriticalPoint < 4) { - locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i], + locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0], 4 * locals->ReturnBWToDCNPerState * (locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024 * locals->ReturnBusWidth * locals->DCFCLKPerState[i] * locals->UrgentLatency / @@ -3472,7 +3473,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l locals->DCFCLKPerState[i], locals->FabricAndDRAMBandwidthPerState[i] * 1000); if (locals->DCCEnabledInAnyPlane == true && locals->ReturnBWToDCNPerState > locals->DCFCLKPerState[i] * locals->ReturnBusWidth / 4) { - locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i], + locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0], locals->ReturnBWToDCNPerState * 4 * (1 - locals->UrgentLatency / ((locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024 / (locals->ReturnBWToDCNPerState - locals->DCFCLKPerState[i] @@ -3483,7 +3484,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l + (locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024); if (locals->DCCEnabledInAnyPlane && locals->CriticalPoint > 1 && locals->CriticalPoint < 4) { - locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i], + locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0], 4 * locals->ReturnBWToDCNPerState * (locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024 * locals->ReturnBusWidth * locals->DCFCLKPerState[i] * locals->UrgentLatency / @@ -3521,12 +3522,12 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l for (i = 0; i <= mode_lib->vba.soc.num_states; i++) { locals->UrgentRoundTripAndOutOfOrderLatencyPerState[i] = (mode_lib->vba.RoundTripPingLatencyCycles + 32.0) / mode_lib->vba.DCFCLKPerState[i] - + locals->UrgentOutOfOrderReturnPerChannel * mode_lib->vba.NumberOfChannels / locals->ReturnBWPerState[i]; - if ((mode_lib->vba.ROBBufferSizeInKByte - mode_lib->vba.PixelChunkSizeInKByte) * 1024.0 / locals->ReturnBWPerState[i] + + locals->UrgentOutOfOrderReturnPerChannel * mode_lib->vba.NumberOfChannels / locals->ReturnBWPerState[i][0]; + if ((mode_lib->vba.ROBBufferSizeInKByte - mode_lib->vba.PixelChunkSizeInKByte) * 1024.0 / locals->ReturnBWPerState[i][0] > locals->UrgentRoundTripAndOutOfOrderLatencyPerState[i]) { - locals->ROBSupport[i] = true; + locals->ROBSupport[i][0] = true; } else { - locals->ROBSupport[i] = false; + locals->ROBSupport[i][0] = false; } } /*Writeback Mode Support Check*/ @@ -3894,16 +3895,22 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l && i == mode_lib->vba.soc.num_states) mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine = mode_lib->vba.PixelClock[k] / 2 * (1 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0); - if (mode_lib->vba.ODMCapability == false || mode_lib->vba.PlaneRequiredDISPCLKWithoutODMCombine <= mode_lib->vba.MaxDispclkRoundedDownToDFSGranularity) { - locals->ODMCombineEnablePerState[i][k] = false; - mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithoutODMCombine; - } else { - locals->ODMCombineEnablePerState[i][k] = true; - mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine; + + locals->ODMCombineEnablePerState[i][k] = false; + mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithoutODMCombine; + if (mode_lib->vba.ODMCapability) { + if (locals->PlaneRequiredDISPCLKWithoutODMCombine > mode_lib->vba.MaxDispclkRoundedDownToDFSGranularity) { + locals->ODMCombineEnablePerState[i][k] = true; + mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine; + } else if (locals->HActive[k] > DCN20_MAX_420_IMAGE_WIDTH && locals->OutputFormat[k] == dm_420) { + locals->ODMCombineEnablePerState[i][k] = true; + mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine; + } } + if (locals->MinDPPCLKUsingSingleDPP[k] * (1.0 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0) <= mode_lib->vba.MaxDppclkRoundedDownToDFSGranularity && locals->SwathWidthYSingleDPP[k] <= locals->MaximumSwathWidth[k] - && locals->ODMCombineEnablePerState[i][k] == false) { + && locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_disabled) { locals->NoOfDPP[i][j][k] = 1; locals->RequiredDPPCLK[i][j][k] = locals->MinDPPCLKUsingSingleDPP[k] * (1.0 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0); @@ -3992,16 +3999,16 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l /*Viewport Size Check*/ for (i = 0; i <= mode_lib->vba.soc.num_states; i++) { - locals->ViewportSizeSupport[i] = true; + locals->ViewportSizeSupport[i][0] = true; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { - if (locals->ODMCombineEnablePerState[i][k] == true) { + if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) { if (dml_min(locals->SwathWidthYSingleDPP[k], dml_round(mode_lib->vba.HActive[k] / 2.0 * mode_lib->vba.HRatio[k])) > locals->MaximumSwathWidth[k]) { - locals->ViewportSizeSupport[i] = false; + locals->ViewportSizeSupport[i][0] = false; } } else { if (locals->SwathWidthYSingleDPP[k] / 2.0 > locals->MaximumSwathWidth[k]) { - locals->ViewportSizeSupport[i] = false; + locals->ViewportSizeSupport[i][0] = false; } } } @@ -4183,8 +4190,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.DSCFormatFactor = 1; } if (locals->RequiresDSC[i][k] == true) { - if (locals->ODMCombineEnablePerState[i][k] - == true) { + if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) { if (mode_lib->vba.PixelClockBackEnd[k] / 6.0 / mode_lib->vba.DSCFormatFactor > (1.0 - mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0) * mode_lib->vba.MaxDSCCLK[i]) { locals->DSCCLKRequiredMoreThanSupported[i] = @@ -4207,7 +4213,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.TotalDSCUnitsRequired = 0.0; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { if (locals->RequiresDSC[i][k] == true) { - if (locals->ODMCombineEnablePerState[i][k] == true) { + if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) { mode_lib->vba.TotalDSCUnitsRequired = mode_lib->vba.TotalDSCUnitsRequired + 2.0; } else { @@ -4249,7 +4255,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.bpp = locals->OutputBppPerState[i][k]; } if (locals->RequiresDSC[i][k] == true && mode_lib->vba.bpp != 0.0) { - if (locals->ODMCombineEnablePerState[i][k] == false) { + if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_disabled) { locals->DSCDelayPerState[i][k] = dscceComputeDelay( mode_lib->vba.DSCInputBitPerComponent[k], @@ -4292,7 +4298,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l for (i = 0; i <= mode_lib->vba.soc.num_states; i++) { for (j = 0; j < 2; j++) { for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { - if (locals->ODMCombineEnablePerState[i][k] == true) + if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) locals->SwathWidthYPerState[i][j][k] = dml_min(locals->SwathWidthYSingleDPP[k], dml_round(locals->HActive[k] / 2 * locals->HRatio[k])); else locals->SwathWidthYPerState[i][j][k] = locals->SwathWidthYSingleDPP[k] / locals->NoOfDPP[i][j][k]; @@ -4345,28 +4351,28 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l locals->EffectiveDETLBLinesLuma = dml_floor(locals->LinesInDETLuma + dml_min( locals->LinesInDETLuma * locals->RequiredDISPCLK[i][j] * locals->BytePerPixelInDETY[k] * - locals->PSCL_FACTOR[k] / locals->ReturnBWPerState[i], + locals->PSCL_FACTOR[k] / locals->ReturnBWPerState[i][0], locals->EffectiveLBLatencyHidingSourceLinesLuma), locals->SwathHeightYPerState[i][j][k]); locals->EffectiveDETLBLinesChroma = dml_floor(locals->LinesInDETChroma + dml_min( locals->LinesInDETChroma * locals->RequiredDISPCLK[i][j] * locals->BytePerPixelInDETC[k] * - locals->PSCL_FACTOR_CHROMA[k] / locals->ReturnBWPerState[i], + locals->PSCL_FACTOR_CHROMA[k] / locals->ReturnBWPerState[i][0], locals->EffectiveLBLatencyHidingSourceLinesChroma), locals->SwathHeightCPerState[i][j][k]); if (locals->BytePerPixelInDETC[k] == 0) { locals->UrgentLatencySupportUsPerState[i][j][k] = locals->EffectiveDETLBLinesLuma * (locals->HTotal[k] / locals->PixelClock[k]) / locals->VRatio[k] - locals->EffectiveDETLBLinesLuma * locals->SwathWidthYPerState[i][j][k] * - dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i] / locals->NoOfDPP[i][j][k]); + dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i][0] / locals->NoOfDPP[i][j][k]); } else { locals->UrgentLatencySupportUsPerState[i][j][k] = dml_min( locals->EffectiveDETLBLinesLuma * (locals->HTotal[k] / locals->PixelClock[k]) / locals->VRatio[k] - locals->EffectiveDETLBLinesLuma * locals->SwathWidthYPerState[i][j][k] * - dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i] / locals->NoOfDPP[i][j][k]), + dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i][0] / locals->NoOfDPP[i][j][k]), locals->EffectiveDETLBLinesChroma * (locals->HTotal[k] / locals->PixelClock[k]) / (locals->VRatio[k] / 2) - locals->EffectiveDETLBLinesChroma * locals->SwathWidthYPerState[i][j][k] / 2 * - dml_ceil(locals->BytePerPixelInDETC[k], 2) / (locals->ReturnBWPerState[i] / locals->NoOfDPP[i][j][k])); + dml_ceil(locals->BytePerPixelInDETC[k], 2) / (locals->ReturnBWPerState[i][0] / locals->NoOfDPP[i][j][k])); } } } @@ -4406,14 +4412,14 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l locals->SwathHeightYThisState[k] = locals->SwathHeightYPerState[i][j][k]; locals->SwathHeightCThisState[k] = locals->SwathHeightCPerState[i][j][k]; locals->SwathWidthYThisState[k] = locals->SwathWidthYPerState[i][j][k]; - mode_lib->vba.ProjectedDCFCLKDeepSleep = dml_max( - mode_lib->vba.ProjectedDCFCLKDeepSleep, + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] = dml_max( + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0], mode_lib->vba.PixelClock[k] / 16.0); if (mode_lib->vba.BytePerPixelInDETC[k] == 0.0) { if (mode_lib->vba.VRatio[k] <= 1.0) { - mode_lib->vba.ProjectedDCFCLKDeepSleep = + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] = dml_max( - mode_lib->vba.ProjectedDCFCLKDeepSleep, + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0], 1.1 * dml_ceil( mode_lib->vba.BytePerPixelInDETY[k], @@ -4423,9 +4429,9 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l * mode_lib->vba.PixelClock[k] / mode_lib->vba.NoOfDPP[i][j][k]); } else { - mode_lib->vba.ProjectedDCFCLKDeepSleep = + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] = dml_max( - mode_lib->vba.ProjectedDCFCLKDeepSleep, + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0], 1.1 * dml_ceil( mode_lib->vba.BytePerPixelInDETY[k], @@ -4436,9 +4442,9 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l } } else { if (mode_lib->vba.VRatio[k] <= 1.0) { - mode_lib->vba.ProjectedDCFCLKDeepSleep = + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] = dml_max( - mode_lib->vba.ProjectedDCFCLKDeepSleep, + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0], 1.1 * dml_ceil( mode_lib->vba.BytePerPixelInDETY[k], @@ -4448,9 +4454,9 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l * mode_lib->vba.PixelClock[k] / mode_lib->vba.NoOfDPP[i][j][k]); } else { - mode_lib->vba.ProjectedDCFCLKDeepSleep = + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] = dml_max( - mode_lib->vba.ProjectedDCFCLKDeepSleep, + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0], 1.1 * dml_ceil( mode_lib->vba.BytePerPixelInDETY[k], @@ -4460,9 +4466,9 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l * mode_lib->vba.RequiredDPPCLK[i][j][k]); } if (mode_lib->vba.VRatio[k] / 2.0 <= 1.0) { - mode_lib->vba.ProjectedDCFCLKDeepSleep = + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] = dml_max( - mode_lib->vba.ProjectedDCFCLKDeepSleep, + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0], 1.1 * dml_ceil( mode_lib->vba.BytePerPixelInDETC[k], @@ -4473,9 +4479,9 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l * mode_lib->vba.PixelClock[k] / mode_lib->vba.NoOfDPP[i][j][k]); } else { - mode_lib->vba.ProjectedDCFCLKDeepSleep = + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] = dml_max( - mode_lib->vba.ProjectedDCFCLKDeepSleep, + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0], 1.1 * dml_ceil( mode_lib->vba.BytePerPixelInDETC[k], @@ -4511,7 +4517,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l &mode_lib->vba.PTEBufferSizeNotExceededY[i][j][k], &mode_lib->vba.dpte_row_height[k], &mode_lib->vba.meta_row_height[k]); - mode_lib->vba.PrefetchLinesY[k] = CalculatePrefetchSourceLines( + mode_lib->vba.PrefetchLinesY[0][0][k] = CalculatePrefetchSourceLines( mode_lib, mode_lib->vba.VRatio[k], mode_lib->vba.vtaps[k], @@ -4550,7 +4556,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l &mode_lib->vba.PTEBufferSizeNotExceededC[i][j][k], &mode_lib->vba.dpte_row_height_chroma[k], &mode_lib->vba.meta_row_height_chroma[k]); - mode_lib->vba.PrefetchLinesC[k] = CalculatePrefetchSourceLines( + mode_lib->vba.PrefetchLinesC[0][0][k] = CalculatePrefetchSourceLines( mode_lib, mode_lib->vba.VRatio[k] / 2.0, mode_lib->vba.VTAPsChroma[k], @@ -4564,14 +4570,14 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.PDEAndMetaPTEBytesPerFrameC = 0.0; mode_lib->vba.MetaRowBytesC = 0.0; mode_lib->vba.DPTEBytesPerRowC = 0.0; - locals->PrefetchLinesC[k] = 0.0; + locals->PrefetchLinesC[0][0][k] = 0.0; locals->PTEBufferSizeNotExceededC[i][j][k] = true; locals->PTEBufferSizeInRequestsForLuma = mode_lib->vba.PTEBufferSizeInRequestsLuma + mode_lib->vba.PTEBufferSizeInRequestsChroma; } - locals->PDEAndMetaPTEBytesPerFrame[k] = + locals->PDEAndMetaPTEBytesPerFrame[0][0][k] = mode_lib->vba.PDEAndMetaPTEBytesPerFrameY + mode_lib->vba.PDEAndMetaPTEBytesPerFrameC; - locals->MetaRowBytes[k] = mode_lib->vba.MetaRowBytesY + mode_lib->vba.MetaRowBytesC; - locals->DPTEBytesPerRow[k] = mode_lib->vba.DPTEBytesPerRowY + mode_lib->vba.DPTEBytesPerRowC; + locals->MetaRowBytes[0][0][k] = mode_lib->vba.MetaRowBytesY + mode_lib->vba.MetaRowBytesC; + locals->DPTEBytesPerRow[0][0][k] = mode_lib->vba.DPTEBytesPerRowY + mode_lib->vba.DPTEBytesPerRowC; CalculateActiveRowBandwidth( mode_lib->vba.GPUVMEnable, @@ -4598,14 +4604,14 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l + mode_lib->vba.TotalNumberOfDCCActiveDPP[i][j] * mode_lib->vba.MetaChunkSize) * 1024.0 - / mode_lib->vba.ReturnBWPerState[i]; + / mode_lib->vba.ReturnBWPerState[i][0]; if (mode_lib->vba.GPUVMEnable == true) { mode_lib->vba.ExtraLatency = mode_lib->vba.ExtraLatency + mode_lib->vba.TotalNumberOfActiveDPP[i][j] * mode_lib->vba.PTEGroupSize - / mode_lib->vba.ReturnBWPerState[i]; + / mode_lib->vba.ReturnBWPerState[i][0]; } - mode_lib->vba.TimeCalc = 24.0 / mode_lib->vba.ProjectedDCFCLKDeepSleep; + mode_lib->vba.TimeCalc = 24.0 / mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0]; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { if (mode_lib->vba.BlendingAndTiming[k] == k) { @@ -4655,7 +4661,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l } for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { - locals->MaximumVStartup[k] = mode_lib->vba.VTotal[k] - mode_lib->vba.VActive[k] + locals->MaximumVStartup[0][0][k] = mode_lib->vba.VTotal[k] - mode_lib->vba.VActive[k] - dml_max(1.0, dml_ceil(locals->WritebackDelay[i][k] / (mode_lib->vba.HTotal[k] / mode_lib->vba.PixelClock[k]), 1.0)); } @@ -4700,7 +4706,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.RequiredDPPCLK[i][j][k], mode_lib->vba.RequiredDISPCLK[i][j], mode_lib->vba.PixelClock[k], - mode_lib->vba.ProjectedDCFCLKDeepSleep, + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0], mode_lib->vba.DSCDelayPerState[i][k], mode_lib->vba.NoOfDPP[i][j][k], mode_lib->vba.ScalerEnabled[k], @@ -4718,7 +4724,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l - mode_lib->vba.VActive[k], mode_lib->vba.HTotal[k], mode_lib->vba.MaxInterDCNTileRepeaters, - mode_lib->vba.MaximumVStartup[k], + mode_lib->vba.MaximumVStartup[0][0][k], mode_lib->vba.GPUVMMaxPageTableLevels, mode_lib->vba.GPUVMEnable, mode_lib->vba.DynamicMetadataEnable[k], @@ -4728,15 +4734,15 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.UrgentLatencyPixelDataOnly, mode_lib->vba.ExtraLatency, mode_lib->vba.TimeCalc, - mode_lib->vba.PDEAndMetaPTEBytesPerFrame[k], - mode_lib->vba.MetaRowBytes[k], - mode_lib->vba.DPTEBytesPerRow[k], - mode_lib->vba.PrefetchLinesY[k], + mode_lib->vba.PDEAndMetaPTEBytesPerFrame[0][0][k], + mode_lib->vba.MetaRowBytes[0][0][k], + mode_lib->vba.DPTEBytesPerRow[0][0][k], + mode_lib->vba.PrefetchLinesY[0][0][k], mode_lib->vba.SwathWidthYPerState[i][j][k], mode_lib->vba.BytePerPixelInDETY[k], mode_lib->vba.PrefillY[k], mode_lib->vba.MaxNumSwY[k], - mode_lib->vba.PrefetchLinesC[k], + mode_lib->vba.PrefetchLinesC[0][0][k], mode_lib->vba.BytePerPixelInDETC[k], mode_lib->vba.PrefillC[k], mode_lib->vba.MaxNumSwC[k], @@ -4767,19 +4773,19 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l locals->prefetch_vm_bw_valid = true; locals->prefetch_row_bw_valid = true; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { - if (locals->PDEAndMetaPTEBytesPerFrame[k] == 0) + if (locals->PDEAndMetaPTEBytesPerFrame[0][0][k] == 0) locals->prefetch_vm_bw[k] = 0; else if (locals->LinesForMetaPTE[k] > 0) - locals->prefetch_vm_bw[k] = locals->PDEAndMetaPTEBytesPerFrame[k] + locals->prefetch_vm_bw[k] = locals->PDEAndMetaPTEBytesPerFrame[0][0][k] / (locals->LinesForMetaPTE[k] * locals->HTotal[k] / locals->PixelClock[k]); else { locals->prefetch_vm_bw[k] = 0; locals->prefetch_vm_bw_valid = false; } - if (locals->MetaRowBytes[k] + locals->DPTEBytesPerRow[k] == 0) + if (locals->MetaRowBytes[0][0][k] + locals->DPTEBytesPerRow[0][0][k] == 0) locals->prefetch_row_bw[k] = 0; else if (locals->LinesForMetaAndDPTERow[k] > 0) - locals->prefetch_row_bw[k] = (locals->MetaRowBytes[k] + locals->DPTEBytesPerRow[k]) + locals->prefetch_row_bw[k] = (locals->MetaRowBytes[0][0][k] + locals->DPTEBytesPerRow[0][0][k]) / (locals->LinesForMetaAndDPTERow[k] * locals->HTotal[k] / locals->PixelClock[k]); else { locals->prefetch_row_bw[k] = 0; @@ -4798,13 +4804,13 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.RequiredPrefetchPixelDataBWLuma[i][j][k]) + mode_lib->vba.meta_row_bw[k] + mode_lib->vba.dpte_row_bw[k]); } - locals->BandwidthWithoutPrefetchSupported[i] = true; - if (mode_lib->vba.MaximumReadBandwidthWithoutPrefetch > locals->ReturnBWPerState[i]) { - locals->BandwidthWithoutPrefetchSupported[i] = false; + locals->BandwidthWithoutPrefetchSupported[i][0] = true; + if (mode_lib->vba.MaximumReadBandwidthWithoutPrefetch > locals->ReturnBWPerState[i][0]) { + locals->BandwidthWithoutPrefetchSupported[i][0] = false; } locals->PrefetchSupported[i][j] = true; - if (mode_lib->vba.MaximumReadBandwidthWithPrefetch > locals->ReturnBWPerState[i]) { + if (mode_lib->vba.MaximumReadBandwidthWithPrefetch > locals->ReturnBWPerState[i][0]) { locals->PrefetchSupported[i][j] = false; } for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { @@ -4829,7 +4835,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l if (mode_lib->vba.PrefetchSupported[i][j] == true && mode_lib->vba.VRatioInPrefetchSupported[i][j] == true) { mode_lib->vba.BandwidthAvailableForImmediateFlip = - mode_lib->vba.ReturnBWPerState[i]; + mode_lib->vba.ReturnBWPerState[i][0]; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { mode_lib->vba.BandwidthAvailableForImmediateFlip = mode_lib->vba.BandwidthAvailableForImmediateFlip @@ -4843,9 +4849,9 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l if ((mode_lib->vba.SourcePixelFormat[k] != dm_420_8 && mode_lib->vba.SourcePixelFormat[k] != dm_420_10)) { mode_lib->vba.ImmediateFlipBytes[k] = - mode_lib->vba.PDEAndMetaPTEBytesPerFrame[k] - + mode_lib->vba.MetaRowBytes[k] - + mode_lib->vba.DPTEBytesPerRow[k]; + mode_lib->vba.PDEAndMetaPTEBytesPerFrame[0][0][k] + + mode_lib->vba.MetaRowBytes[0][0][k] + + mode_lib->vba.DPTEBytesPerRow[0][0][k]; } } mode_lib->vba.TotImmediateFlipBytes = 0.0; @@ -4873,9 +4879,9 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l / mode_lib->vba.PixelClock[k], mode_lib->vba.VRatio[k], mode_lib->vba.Tno_bw[k], - mode_lib->vba.PDEAndMetaPTEBytesPerFrame[k], - mode_lib->vba.MetaRowBytes[k], - mode_lib->vba.DPTEBytesPerRow[k], + mode_lib->vba.PDEAndMetaPTEBytesPerFrame[0][0][k], + mode_lib->vba.MetaRowBytes[0][0][k], + mode_lib->vba.DPTEBytesPerRow[0][0][k], mode_lib->vba.DCCEnable[k], mode_lib->vba.dpte_row_height[k], mode_lib->vba.meta_row_height[k], @@ -4900,7 +4906,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l } mode_lib->vba.ImmediateFlipSupportedForState[i][j] = true; if (mode_lib->vba.total_dcn_read_bw_with_flip - > mode_lib->vba.ReturnBWPerState[i]) { + > mode_lib->vba.ReturnBWPerState[i][0]) { mode_lib->vba.ImmediateFlipSupportedForState[i][j] = false; } for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { @@ -4919,13 +4925,13 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l for (k = 0; k < mode_lib->vba.NumberOfActivePlanes; k++) mode_lib->vba.MaxTotalVActiveRDBandwidth = mode_lib->vba.MaxTotalVActiveRDBandwidth + mode_lib->vba.ReadBandwidth[k]; for (i = 0; i <= mode_lib->vba.soc.num_states; i++) { - mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i] = dml_min(mode_lib->vba.ReturnBusWidth * + mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i][0] = dml_min(mode_lib->vba.ReturnBusWidth * mode_lib->vba.DCFCLKPerState[i], mode_lib->vba.FabricAndDRAMBandwidthPerState[i] * 1000) * mode_lib->vba.MaxAveragePercentOfIdealDRAMBWDisplayCanUseInNormalSystemOperation / 100; - if (mode_lib->vba.MaxTotalVActiveRDBandwidth <= mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i]) - mode_lib->vba.TotalVerticalActiveBandwidthSupport[i] = true; + if (mode_lib->vba.MaxTotalVActiveRDBandwidth <= mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i][0]) + mode_lib->vba.TotalVerticalActiveBandwidthSupport[i][0] = true; else - mode_lib->vba.TotalVerticalActiveBandwidthSupport[i] = false; + mode_lib->vba.TotalVerticalActiveBandwidthSupport[i][0] = false; } /*PTE Buffer Size Check*/ @@ -5013,7 +5019,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l status = DML_FAIL_SCALE_RATIO_TAP; } else if (mode_lib->vba.SourceFormatPixelAndScanSupport != true) { status = DML_FAIL_SOURCE_PIXEL_FORMAT; - } else if (locals->ViewportSizeSupport[i] != true) { + } else if (locals->ViewportSizeSupport[i][0] != true) { status = DML_FAIL_VIEWPORT_SIZE; } else if (locals->DIOSupport[i] != true) { status = DML_FAIL_DIO_SUPPORT; @@ -5023,7 +5029,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l status = DML_FAIL_DSC_CLK_REQUIRED; } else if (locals->UrgentLatencySupport[i][j] != true) { status = DML_FAIL_URGENT_LATENCY; - } else if (locals->ROBSupport[i] != true) { + } else if (locals->ROBSupport[i][0] != true) { status = DML_FAIL_REORDERING_BUFFER; } else if (locals->DISPCLK_DPPCLK_Support[i][j] != true) { status = DML_FAIL_DISPCLK_DPPCLK; @@ -5043,7 +5049,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l status = DML_FAIL_PITCH_SUPPORT; } else if (locals->PrefetchSupported[i][j] != true) { status = DML_FAIL_PREFETCH_SUPPORT; - } else if (locals->TotalVerticalActiveBandwidthSupport[i] != true) { + } else if (locals->TotalVerticalActiveBandwidthSupport[i][0] != true) { status = DML_FAIL_TOTAL_V_ACTIVE_BW; } else if (locals->VRatioInPrefetchSupported[i][j] != true) { status = DML_FAIL_V_RATIO_PREFETCH; @@ -5089,7 +5095,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.DRAMSpeed = mode_lib->vba.DRAMSpeedPerState[mode_lib->vba.VoltageLevel]; mode_lib->vba.FabricClock = mode_lib->vba.FabricClockPerState[mode_lib->vba.VoltageLevel]; mode_lib->vba.SOCCLK = mode_lib->vba.SOCCLKPerState[mode_lib->vba.VoltageLevel]; - mode_lib->vba.ReturnBW = locals->ReturnBWPerState[mode_lib->vba.VoltageLevel]; + mode_lib->vba.ReturnBW = locals->ReturnBWPerState[mode_lib->vba.VoltageLevel][0]; mode_lib->vba.FabricAndDRAMBandwidth = locals->FabricAndDRAMBandwidthPerState[mode_lib->vba.VoltageLevel]; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { if (mode_lib->vba.BlendingAndTiming[k] == k) { diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c index 6482d7b99bae..485a9c62ec58 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c @@ -39,6 +39,7 @@ #define BPP_INVALID 0 #define BPP_BLENDED_PIPE 0xffffffff #define DCN20_MAX_DSC_IMAGE_WIDTH 5184 +#define DCN20_MAX_420_IMAGE_WIDTH 4096 static double adjust_ReturnBW( struct display_mode_lib *mode_lib, @@ -997,7 +998,7 @@ static unsigned int CalculateVMAndRowBytes( *MetaRowByte = 0; } - if (SurfaceTiling == dm_sw_linear || SurfaceTiling == dm_sw_gfx7_2d_thin_gl || SurfaceTiling == dm_sw_gfx7_2d_thin_lvp) { + if (SurfaceTiling == dm_sw_linear || SurfaceTiling == dm_sw_gfx7_2d_thin_gl || SurfaceTiling == dm_sw_gfx7_2d_thin_l_vp) { MacroTileSizeBytes = 256; MacroTileHeight = BlockHeight256Bytes; } else if (SurfaceTiling == dm_sw_4kb_s || SurfaceTiling == dm_sw_4kb_s_x @@ -1395,11 +1396,11 @@ static void dml20v2_DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndP else mode_lib->vba.SwathWidthSingleDPPY[k] = mode_lib->vba.ViewportHeight[k]; - if (mode_lib->vba.ODMCombineEnabled[k] == true) + if (mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) MainPlaneDoesODMCombine = true; for (j = 0; j < mode_lib->vba.NumberOfActivePlanes; ++j) if (mode_lib->vba.BlendingAndTiming[k] == j - && mode_lib->vba.ODMCombineEnabled[j] == true) + && mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) MainPlaneDoesODMCombine = true; if (MainPlaneDoesODMCombine == true) @@ -2885,12 +2886,12 @@ static void dml20v2_DisplayPipeConfiguration(struct display_mode_lib *mode_lib) SwathWidth = mode_lib->vba.ViewportHeight[k]; } - if (mode_lib->vba.ODMCombineEnabled[k] == true) { + if (mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) { MainPlaneDoesODMCombine = true; } for (j = 0; j < mode_lib->vba.NumberOfActivePlanes; ++j) { if (mode_lib->vba.BlendingAndTiming[k] == j - && mode_lib->vba.ODMCombineEnabled[j] == true) { + && mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) { MainPlaneDoesODMCombine = true; } } @@ -3385,7 +3386,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode == dm_420_10)) || (((mode_lib->vba.SurfaceTiling[k] == dm_sw_gfx7_2d_thin_gl || mode_lib->vba.SurfaceTiling[k] - == dm_sw_gfx7_2d_thin_lvp) + == dm_sw_gfx7_2d_thin_l_vp) && !((mode_lib->vba.SourcePixelFormat[k] == dm_444_64 || mode_lib->vba.SourcePixelFormat[k] @@ -3483,10 +3484,10 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode locals->FabricAndDRAMBandwidthPerState[i] * 1000) * locals->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelDataOnly / 100; - locals->ReturnBWPerState[i] = locals->ReturnBWToDCNPerState; + locals->ReturnBWPerState[i][0] = locals->ReturnBWToDCNPerState; if (locals->DCCEnabledInAnyPlane == true && locals->ReturnBWToDCNPerState > locals->DCFCLKPerState[i] * locals->ReturnBusWidth / 4) { - locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i], + locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0], locals->ReturnBWToDCNPerState * 4 * (1 - locals->UrgentLatency / ((locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024 / (locals->ReturnBWToDCNPerState - locals->DCFCLKPerState[i] @@ -3497,7 +3498,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode + (locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024); if (locals->DCCEnabledInAnyPlane && locals->CriticalPoint > 1 && locals->CriticalPoint < 4) { - locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i], + locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0], 4 * locals->ReturnBWToDCNPerState * (locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024 * locals->ReturnBusWidth * locals->DCFCLKPerState[i] * locals->UrgentLatency / @@ -3509,7 +3510,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode locals->DCFCLKPerState[i], locals->FabricAndDRAMBandwidthPerState[i] * 1000); if (locals->DCCEnabledInAnyPlane == true && locals->ReturnBWToDCNPerState > locals->DCFCLKPerState[i] * locals->ReturnBusWidth / 4) { - locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i], + locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0], locals->ReturnBWToDCNPerState * 4 * (1 - locals->UrgentLatency / ((locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024 / (locals->ReturnBWToDCNPerState - locals->DCFCLKPerState[i] @@ -3520,7 +3521,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode + (locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024); if (locals->DCCEnabledInAnyPlane && locals->CriticalPoint > 1 && locals->CriticalPoint < 4) { - locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i], + locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0], 4 * locals->ReturnBWToDCNPerState * (locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024 * locals->ReturnBusWidth * locals->DCFCLKPerState[i] * locals->UrgentLatency / @@ -3558,12 +3559,12 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode for (i = 0; i <= mode_lib->vba.soc.num_states; i++) { locals->UrgentRoundTripAndOutOfOrderLatencyPerState[i] = (mode_lib->vba.RoundTripPingLatencyCycles + 32.0) / mode_lib->vba.DCFCLKPerState[i] - + locals->UrgentOutOfOrderReturnPerChannel * mode_lib->vba.NumberOfChannels / locals->ReturnBWPerState[i]; - if ((mode_lib->vba.ROBBufferSizeInKByte - mode_lib->vba.PixelChunkSizeInKByte) * 1024.0 / locals->ReturnBWPerState[i] + + locals->UrgentOutOfOrderReturnPerChannel * mode_lib->vba.NumberOfChannels / locals->ReturnBWPerState[i][0]; + if ((mode_lib->vba.ROBBufferSizeInKByte - mode_lib->vba.PixelChunkSizeInKByte) * 1024.0 / locals->ReturnBWPerState[i][0] > locals->UrgentRoundTripAndOutOfOrderLatencyPerState[i]) { - locals->ROBSupport[i] = true; + locals->ROBSupport[i][0] = true; } else { - locals->ROBSupport[i] = false; + locals->ROBSupport[i][0] = false; } } /*Writeback Mode Support Check*/ @@ -3935,18 +3936,25 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode && i == mode_lib->vba.soc.num_states) mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine = mode_lib->vba.PixelClock[k] / 2 * (1 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0); - if (mode_lib->vba.ODMCapability == false || - (locals->PlaneRequiredDISPCLKWithoutODMCombine <= MaxMaxDispclkRoundedDown - && (!locals->DSCEnabled[k] || locals->HActive[k] <= DCN20_MAX_DSC_IMAGE_WIDTH))) { - locals->ODMCombineEnablePerState[i][k] = false; - mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithoutODMCombine; - } else { - locals->ODMCombineEnablePerState[i][k] = true; - mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine; + + locals->ODMCombineEnablePerState[i][k] = false; + mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithoutODMCombine; + if (mode_lib->vba.ODMCapability) { + if (locals->PlaneRequiredDISPCLKWithoutODMCombine > MaxMaxDispclkRoundedDown) { + locals->ODMCombineEnablePerState[i][k] = true; + mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine; + } else if (locals->DSCEnabled[k] && (locals->HActive[k] > DCN20_MAX_DSC_IMAGE_WIDTH)) { + locals->ODMCombineEnablePerState[i][k] = true; + mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine; + } else if (locals->HActive[k] > DCN20_MAX_420_IMAGE_WIDTH && locals->OutputFormat[k] == dm_420) { + locals->ODMCombineEnablePerState[i][k] = true; + mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine; + } } + if (locals->MinDPPCLKUsingSingleDPP[k] * (1.0 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0) <= mode_lib->vba.MaxDppclkRoundedDownToDFSGranularity && locals->SwathWidthYSingleDPP[k] <= locals->MaximumSwathWidth[k] - && locals->ODMCombineEnablePerState[i][k] == false) { + && locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_disabled) { locals->NoOfDPP[i][j][k] = 1; locals->RequiredDPPCLK[i][j][k] = locals->MinDPPCLKUsingSingleDPP[k] * (1.0 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0); @@ -4035,16 +4043,16 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode /*Viewport Size Check*/ for (i = 0; i <= mode_lib->vba.soc.num_states; i++) { - locals->ViewportSizeSupport[i] = true; + locals->ViewportSizeSupport[i][0] = true; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { - if (locals->ODMCombineEnablePerState[i][k] == true) { + if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) { if (dml_min(locals->SwathWidthYSingleDPP[k], dml_round(mode_lib->vba.HActive[k] / 2.0 * mode_lib->vba.HRatio[k])) > locals->MaximumSwathWidth[k]) { - locals->ViewportSizeSupport[i] = false; + locals->ViewportSizeSupport[i][0] = false; } } else { if (locals->SwathWidthYSingleDPP[k] / 2.0 > locals->MaximumSwathWidth[k]) { - locals->ViewportSizeSupport[i] = false; + locals->ViewportSizeSupport[i][0] = false; } } } @@ -4226,8 +4234,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode mode_lib->vba.DSCFormatFactor = 1; } if (locals->RequiresDSC[i][k] == true) { - if (locals->ODMCombineEnablePerState[i][k] - == true) { + if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) { if (mode_lib->vba.PixelClockBackEnd[k] / 6.0 / mode_lib->vba.DSCFormatFactor > (1.0 - mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0) * mode_lib->vba.MaxDSCCLK[i]) { locals->DSCCLKRequiredMoreThanSupported[i] = @@ -4250,7 +4257,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode mode_lib->vba.TotalDSCUnitsRequired = 0.0; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { if (locals->RequiresDSC[i][k] == true) { - if (locals->ODMCombineEnablePerState[i][k] == true) { + if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) { mode_lib->vba.TotalDSCUnitsRequired = mode_lib->vba.TotalDSCUnitsRequired + 2.0; } else { @@ -4292,7 +4299,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode mode_lib->vba.bpp = locals->OutputBppPerState[i][k]; } if (locals->RequiresDSC[i][k] == true && mode_lib->vba.bpp != 0.0) { - if (locals->ODMCombineEnablePerState[i][k] == false) { + if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_disabled) { locals->DSCDelayPerState[i][k] = dscceComputeDelay( mode_lib->vba.DSCInputBitPerComponent[k], @@ -4335,7 +4342,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode for (i = 0; i <= mode_lib->vba.soc.num_states; i++) { for (j = 0; j < 2; j++) { for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { - if (locals->ODMCombineEnablePerState[i][k] == true) + if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) locals->SwathWidthYPerState[i][j][k] = dml_min(locals->SwathWidthYSingleDPP[k], dml_round(locals->HActive[k] / 2 * locals->HRatio[k])); else locals->SwathWidthYPerState[i][j][k] = locals->SwathWidthYSingleDPP[k] / locals->NoOfDPP[i][j][k]; @@ -4388,28 +4395,28 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode locals->EffectiveDETLBLinesLuma = dml_floor(locals->LinesInDETLuma + dml_min( locals->LinesInDETLuma * locals->RequiredDISPCLK[i][j] * locals->BytePerPixelInDETY[k] * - locals->PSCL_FACTOR[k] / locals->ReturnBWPerState[i], + locals->PSCL_FACTOR[k] / locals->ReturnBWPerState[i][0], locals->EffectiveLBLatencyHidingSourceLinesLuma), locals->SwathHeightYPerState[i][j][k]); locals->EffectiveDETLBLinesChroma = dml_floor(locals->LinesInDETChroma + dml_min( locals->LinesInDETChroma * locals->RequiredDISPCLK[i][j] * locals->BytePerPixelInDETC[k] * - locals->PSCL_FACTOR_CHROMA[k] / locals->ReturnBWPerState[i], + locals->PSCL_FACTOR_CHROMA[k] / locals->ReturnBWPerState[i][0], locals->EffectiveLBLatencyHidingSourceLinesChroma), locals->SwathHeightCPerState[i][j][k]); if (locals->BytePerPixelInDETC[k] == 0) { locals->UrgentLatencySupportUsPerState[i][j][k] = locals->EffectiveDETLBLinesLuma * (locals->HTotal[k] / locals->PixelClock[k]) / locals->VRatio[k] - locals->EffectiveDETLBLinesLuma * locals->SwathWidthYPerState[i][j][k] * - dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i] / locals->NoOfDPP[i][j][k]); + dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i][0] / locals->NoOfDPP[i][j][k]); } else { locals->UrgentLatencySupportUsPerState[i][j][k] = dml_min( locals->EffectiveDETLBLinesLuma * (locals->HTotal[k] / locals->PixelClock[k]) / locals->VRatio[k] - locals->EffectiveDETLBLinesLuma * locals->SwathWidthYPerState[i][j][k] * - dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i] / locals->NoOfDPP[i][j][k]), + dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i][0] / locals->NoOfDPP[i][j][k]), locals->EffectiveDETLBLinesChroma * (locals->HTotal[k] / locals->PixelClock[k]) / (locals->VRatio[k] / 2) - locals->EffectiveDETLBLinesChroma * locals->SwathWidthYPerState[i][j][k] / 2 * - dml_ceil(locals->BytePerPixelInDETC[k], 2) / (locals->ReturnBWPerState[i] / locals->NoOfDPP[i][j][k])); + dml_ceil(locals->BytePerPixelInDETC[k], 2) / (locals->ReturnBWPerState[i][0] / locals->NoOfDPP[i][j][k])); } } } @@ -4454,14 +4461,14 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode locals->SwathHeightYThisState[k] = locals->SwathHeightYPerState[i][j][k]; locals->SwathHeightCThisState[k] = locals->SwathHeightCPerState[i][j][k]; locals->SwathWidthYThisState[k] = locals->SwathWidthYPerState[i][j][k]; - mode_lib->vba.ProjectedDCFCLKDeepSleep = dml_max( - mode_lib->vba.ProjectedDCFCLKDeepSleep, + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] = dml_max( + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0], mode_lib->vba.PixelClock[k] / 16.0); if (mode_lib->vba.BytePerPixelInDETC[k] == 0.0) { if (mode_lib->vba.VRatio[k] <= 1.0) { - mode_lib->vba.ProjectedDCFCLKDeepSleep = + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] = dml_max( - mode_lib->vba.ProjectedDCFCLKDeepSleep, + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0], 1.1 * dml_ceil( mode_lib->vba.BytePerPixelInDETY[k], @@ -4471,9 +4478,9 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode * mode_lib->vba.PixelClock[k] / mode_lib->vba.NoOfDPP[i][j][k]); } else { - mode_lib->vba.ProjectedDCFCLKDeepSleep = + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] = dml_max( - mode_lib->vba.ProjectedDCFCLKDeepSleep, + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0], 1.1 * dml_ceil( mode_lib->vba.BytePerPixelInDETY[k], @@ -4484,9 +4491,9 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode } } else { if (mode_lib->vba.VRatio[k] <= 1.0) { - mode_lib->vba.ProjectedDCFCLKDeepSleep = + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] = dml_max( - mode_lib->vba.ProjectedDCFCLKDeepSleep, + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0], 1.1 * dml_ceil( mode_lib->vba.BytePerPixelInDETY[k], @@ -4496,9 +4503,9 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode * mode_lib->vba.PixelClock[k] / mode_lib->vba.NoOfDPP[i][j][k]); } else { - mode_lib->vba.ProjectedDCFCLKDeepSleep = + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] = dml_max( - mode_lib->vba.ProjectedDCFCLKDeepSleep, + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0], 1.1 * dml_ceil( mode_lib->vba.BytePerPixelInDETY[k], @@ -4508,9 +4515,9 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode * mode_lib->vba.RequiredDPPCLK[i][j][k]); } if (mode_lib->vba.VRatio[k] / 2.0 <= 1.0) { - mode_lib->vba.ProjectedDCFCLKDeepSleep = + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] = dml_max( - mode_lib->vba.ProjectedDCFCLKDeepSleep, + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0], 1.1 * dml_ceil( mode_lib->vba.BytePerPixelInDETC[k], @@ -4521,9 +4528,9 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode * mode_lib->vba.PixelClock[k] / mode_lib->vba.NoOfDPP[i][j][k]); } else { - mode_lib->vba.ProjectedDCFCLKDeepSleep = + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] = dml_max( - mode_lib->vba.ProjectedDCFCLKDeepSleep, + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0], 1.1 * dml_ceil( mode_lib->vba.BytePerPixelInDETC[k], @@ -4559,7 +4566,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode &mode_lib->vba.PTEBufferSizeNotExceededY[i][j][k], &mode_lib->vba.dpte_row_height[k], &mode_lib->vba.meta_row_height[k]); - mode_lib->vba.PrefetchLinesY[k] = CalculatePrefetchSourceLines( + mode_lib->vba.PrefetchLinesY[0][0][k] = CalculatePrefetchSourceLines( mode_lib, mode_lib->vba.VRatio[k], mode_lib->vba.vtaps[k], @@ -4598,7 +4605,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode &mode_lib->vba.PTEBufferSizeNotExceededC[i][j][k], &mode_lib->vba.dpte_row_height_chroma[k], &mode_lib->vba.meta_row_height_chroma[k]); - mode_lib->vba.PrefetchLinesC[k] = CalculatePrefetchSourceLines( + mode_lib->vba.PrefetchLinesC[0][0][k] = CalculatePrefetchSourceLines( mode_lib, mode_lib->vba.VRatio[k] / 2.0, mode_lib->vba.VTAPsChroma[k], @@ -4612,14 +4619,14 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode mode_lib->vba.PDEAndMetaPTEBytesPerFrameC = 0.0; mode_lib->vba.MetaRowBytesC = 0.0; mode_lib->vba.DPTEBytesPerRowC = 0.0; - locals->PrefetchLinesC[k] = 0.0; + locals->PrefetchLinesC[0][0][k] = 0.0; locals->PTEBufferSizeNotExceededC[i][j][k] = true; locals->PTEBufferSizeInRequestsForLuma = mode_lib->vba.PTEBufferSizeInRequestsLuma + mode_lib->vba.PTEBufferSizeInRequestsChroma; } - locals->PDEAndMetaPTEBytesPerFrame[k] = + locals->PDEAndMetaPTEBytesPerFrame[0][0][k] = mode_lib->vba.PDEAndMetaPTEBytesPerFrameY + mode_lib->vba.PDEAndMetaPTEBytesPerFrameC; - locals->MetaRowBytes[k] = mode_lib->vba.MetaRowBytesY + mode_lib->vba.MetaRowBytesC; - locals->DPTEBytesPerRow[k] = mode_lib->vba.DPTEBytesPerRowY + mode_lib->vba.DPTEBytesPerRowC; + locals->MetaRowBytes[0][0][k] = mode_lib->vba.MetaRowBytesY + mode_lib->vba.MetaRowBytesC; + locals->DPTEBytesPerRow[0][0][k] = mode_lib->vba.DPTEBytesPerRowY + mode_lib->vba.DPTEBytesPerRowC; CalculateActiveRowBandwidth( mode_lib->vba.GPUVMEnable, @@ -4646,14 +4653,14 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode + mode_lib->vba.TotalNumberOfDCCActiveDPP[i][j] * mode_lib->vba.MetaChunkSize) * 1024.0 - / mode_lib->vba.ReturnBWPerState[i]; + / mode_lib->vba.ReturnBWPerState[i][0]; if (mode_lib->vba.GPUVMEnable == true) { mode_lib->vba.ExtraLatency = mode_lib->vba.ExtraLatency + mode_lib->vba.TotalNumberOfActiveDPP[i][j] * mode_lib->vba.PTEGroupSize - / mode_lib->vba.ReturnBWPerState[i]; + / mode_lib->vba.ReturnBWPerState[i][0]; } - mode_lib->vba.TimeCalc = 24.0 / mode_lib->vba.ProjectedDCFCLKDeepSleep; + mode_lib->vba.TimeCalc = 24.0 / mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0]; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { if (mode_lib->vba.BlendingAndTiming[k] == k) { @@ -4703,7 +4710,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode } for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { - locals->MaximumVStartup[k] = mode_lib->vba.VTotal[k] - mode_lib->vba.VActive[k] + locals->MaximumVStartup[0][0][k] = mode_lib->vba.VTotal[k] - mode_lib->vba.VActive[k] - dml_max(1.0, dml_ceil(locals->WritebackDelay[i][k] / (mode_lib->vba.HTotal[k] / mode_lib->vba.PixelClock[k]), 1.0)); } @@ -4743,7 +4750,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode mode_lib->vba.XFCRemoteSurfaceFlipDelay = 0.0; } - CalculateDelayAfterScaler(mode_lib, mode_lib->vba.ReturnBWPerState[i], mode_lib->vba.ReadBandwidthLuma[k], mode_lib->vba.ReadBandwidthChroma[k], mode_lib->vba.MaxTotalVActiveRDBandwidth, + CalculateDelayAfterScaler(mode_lib, mode_lib->vba.ReturnBWPerState[i][0], mode_lib->vba.ReadBandwidthLuma[k], mode_lib->vba.ReadBandwidthChroma[k], mode_lib->vba.MaxTotalVActiveRDBandwidth, mode_lib->vba.DisplayPipeLineDeliveryTimeLuma[k], mode_lib->vba.DisplayPipeLineDeliveryTimeChroma[k], mode_lib->vba.RequiredDPPCLK[i][j][k], mode_lib->vba.RequiredDISPCLK[i][j], mode_lib->vba.PixelClock[k], mode_lib->vba.DSCDelayPerState[i][k], mode_lib->vba.NoOfDPP[i][j][k], mode_lib->vba.ScalerEnabled[k], mode_lib->vba.NumberOfCursors[k], mode_lib->vba.DPPCLKDelaySubtotal, mode_lib->vba.DPPCLKDelaySCL, mode_lib->vba.DPPCLKDelaySCLLBOnly, mode_lib->vba.DPPCLKDelayCNVCFormater, mode_lib->vba.DPPCLKDelayCNVCCursor, mode_lib->vba.DISPCLKDelaySubtotal, @@ -4757,14 +4764,14 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode mode_lib->vba.RequiredDPPCLK[i][j][k], mode_lib->vba.RequiredDISPCLK[i][j], mode_lib->vba.PixelClock[k], - mode_lib->vba.ProjectedDCFCLKDeepSleep, + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0], mode_lib->vba.NoOfDPP[i][j][k], mode_lib->vba.NumberOfCursors[k], mode_lib->vba.VTotal[k] - mode_lib->vba.VActive[k], mode_lib->vba.HTotal[k], mode_lib->vba.MaxInterDCNTileRepeaters, - mode_lib->vba.MaximumVStartup[k], + mode_lib->vba.MaximumVStartup[0][0][k], mode_lib->vba.GPUVMMaxPageTableLevels, mode_lib->vba.GPUVMEnable, mode_lib->vba.DynamicMetadataEnable[k], @@ -4774,15 +4781,15 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode mode_lib->vba.UrgentLatencyPixelDataOnly, mode_lib->vba.ExtraLatency, mode_lib->vba.TimeCalc, - mode_lib->vba.PDEAndMetaPTEBytesPerFrame[k], - mode_lib->vba.MetaRowBytes[k], - mode_lib->vba.DPTEBytesPerRow[k], - mode_lib->vba.PrefetchLinesY[k], + mode_lib->vba.PDEAndMetaPTEBytesPerFrame[0][0][k], + mode_lib->vba.MetaRowBytes[0][0][k], + mode_lib->vba.DPTEBytesPerRow[0][0][k], + mode_lib->vba.PrefetchLinesY[0][0][k], mode_lib->vba.SwathWidthYPerState[i][j][k], mode_lib->vba.BytePerPixelInDETY[k], mode_lib->vba.PrefillY[k], mode_lib->vba.MaxNumSwY[k], - mode_lib->vba.PrefetchLinesC[k], + mode_lib->vba.PrefetchLinesC[0][0][k], mode_lib->vba.BytePerPixelInDETC[k], mode_lib->vba.PrefillC[k], mode_lib->vba.MaxNumSwC[k], @@ -4812,19 +4819,19 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode locals->prefetch_vm_bw_valid = true; locals->prefetch_row_bw_valid = true; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { - if (locals->PDEAndMetaPTEBytesPerFrame[k] == 0) + if (locals->PDEAndMetaPTEBytesPerFrame[0][0][k] == 0) locals->prefetch_vm_bw[k] = 0; else if (locals->LinesForMetaPTE[k] > 0) - locals->prefetch_vm_bw[k] = locals->PDEAndMetaPTEBytesPerFrame[k] + locals->prefetch_vm_bw[k] = locals->PDEAndMetaPTEBytesPerFrame[0][0][k] / (locals->LinesForMetaPTE[k] * locals->HTotal[k] / locals->PixelClock[k]); else { locals->prefetch_vm_bw[k] = 0; locals->prefetch_vm_bw_valid = false; } - if (locals->MetaRowBytes[k] + locals->DPTEBytesPerRow[k] == 0) + if (locals->MetaRowBytes[0][0][k] + locals->DPTEBytesPerRow[0][0][k] == 0) locals->prefetch_row_bw[k] = 0; else if (locals->LinesForMetaAndDPTERow[k] > 0) - locals->prefetch_row_bw[k] = (locals->MetaRowBytes[k] + locals->DPTEBytesPerRow[k]) + locals->prefetch_row_bw[k] = (locals->MetaRowBytes[0][0][k] + locals->DPTEBytesPerRow[0][0][k]) / (locals->LinesForMetaAndDPTERow[k] * locals->HTotal[k] / locals->PixelClock[k]); else { locals->prefetch_row_bw[k] = 0; @@ -4843,13 +4850,13 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode mode_lib->vba.RequiredPrefetchPixelDataBWLuma[i][j][k]) + mode_lib->vba.meta_row_bw[k] + mode_lib->vba.dpte_row_bw[k]); } - locals->BandwidthWithoutPrefetchSupported[i] = true; - if (mode_lib->vba.MaximumReadBandwidthWithoutPrefetch > locals->ReturnBWPerState[i]) { - locals->BandwidthWithoutPrefetchSupported[i] = false; + locals->BandwidthWithoutPrefetchSupported[i][0] = true; + if (mode_lib->vba.MaximumReadBandwidthWithoutPrefetch > locals->ReturnBWPerState[i][0]) { + locals->BandwidthWithoutPrefetchSupported[i][0] = false; } locals->PrefetchSupported[i][j] = true; - if (mode_lib->vba.MaximumReadBandwidthWithPrefetch > locals->ReturnBWPerState[i]) { + if (mode_lib->vba.MaximumReadBandwidthWithPrefetch > locals->ReturnBWPerState[i][0]) { locals->PrefetchSupported[i][j] = false; } for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { @@ -4874,7 +4881,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode if (mode_lib->vba.PrefetchSupported[i][j] == true && mode_lib->vba.VRatioInPrefetchSupported[i][j] == true) { mode_lib->vba.BandwidthAvailableForImmediateFlip = - mode_lib->vba.ReturnBWPerState[i]; + mode_lib->vba.ReturnBWPerState[i][0]; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { mode_lib->vba.BandwidthAvailableForImmediateFlip = mode_lib->vba.BandwidthAvailableForImmediateFlip @@ -4888,9 +4895,9 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode if ((mode_lib->vba.SourcePixelFormat[k] != dm_420_8 && mode_lib->vba.SourcePixelFormat[k] != dm_420_10)) { mode_lib->vba.ImmediateFlipBytes[k] = - mode_lib->vba.PDEAndMetaPTEBytesPerFrame[k] - + mode_lib->vba.MetaRowBytes[k] - + mode_lib->vba.DPTEBytesPerRow[k]; + mode_lib->vba.PDEAndMetaPTEBytesPerFrame[0][0][k] + + mode_lib->vba.MetaRowBytes[0][0][k] + + mode_lib->vba.DPTEBytesPerRow[0][0][k]; } } mode_lib->vba.TotImmediateFlipBytes = 0.0; @@ -4918,9 +4925,9 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode / mode_lib->vba.PixelClock[k], mode_lib->vba.VRatio[k], mode_lib->vba.Tno_bw[k], - mode_lib->vba.PDEAndMetaPTEBytesPerFrame[k], - mode_lib->vba.MetaRowBytes[k], - mode_lib->vba.DPTEBytesPerRow[k], + mode_lib->vba.PDEAndMetaPTEBytesPerFrame[0][0][k], + mode_lib->vba.MetaRowBytes[0][0][k], + mode_lib->vba.DPTEBytesPerRow[0][0][k], mode_lib->vba.DCCEnable[k], mode_lib->vba.dpte_row_height[k], mode_lib->vba.meta_row_height[k], @@ -4945,7 +4952,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode } mode_lib->vba.ImmediateFlipSupportedForState[i][j] = true; if (mode_lib->vba.total_dcn_read_bw_with_flip - > mode_lib->vba.ReturnBWPerState[i]) { + > mode_lib->vba.ReturnBWPerState[i][0]) { mode_lib->vba.ImmediateFlipSupportedForState[i][j] = false; } for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { @@ -4961,13 +4968,13 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode /*Vertical Active BW support*/ for (i = 0; i <= mode_lib->vba.soc.num_states; i++) { - mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i] = dml_min(mode_lib->vba.ReturnBusWidth * + mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i][0] = dml_min(mode_lib->vba.ReturnBusWidth * mode_lib->vba.DCFCLKPerState[i], mode_lib->vba.FabricAndDRAMBandwidthPerState[i] * 1000) * mode_lib->vba.MaxAveragePercentOfIdealDRAMBWDisplayCanUseInNormalSystemOperation / 100; - if (mode_lib->vba.MaxTotalVActiveRDBandwidth <= mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i]) - mode_lib->vba.TotalVerticalActiveBandwidthSupport[i] = true; + if (mode_lib->vba.MaxTotalVActiveRDBandwidth <= mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i][0]) + mode_lib->vba.TotalVerticalActiveBandwidthSupport[i][0] = true; else - mode_lib->vba.TotalVerticalActiveBandwidthSupport[i] = false; + mode_lib->vba.TotalVerticalActiveBandwidthSupport[i][0] = false; } /*PTE Buffer Size Check*/ @@ -5055,7 +5062,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode status = DML_FAIL_SCALE_RATIO_TAP; } else if (mode_lib->vba.SourceFormatPixelAndScanSupport != true) { status = DML_FAIL_SOURCE_PIXEL_FORMAT; - } else if (locals->ViewportSizeSupport[i] != true) { + } else if (locals->ViewportSizeSupport[i][0] != true) { status = DML_FAIL_VIEWPORT_SIZE; } else if (locals->DIOSupport[i] != true) { status = DML_FAIL_DIO_SUPPORT; @@ -5065,7 +5072,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode status = DML_FAIL_DSC_CLK_REQUIRED; } else if (locals->UrgentLatencySupport[i][j] != true) { status = DML_FAIL_URGENT_LATENCY; - } else if (locals->ROBSupport[i] != true) { + } else if (locals->ROBSupport[i][0] != true) { status = DML_FAIL_REORDERING_BUFFER; } else if (locals->DISPCLK_DPPCLK_Support[i][j] != true) { status = DML_FAIL_DISPCLK_DPPCLK; @@ -5085,7 +5092,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode status = DML_FAIL_PITCH_SUPPORT; } else if (locals->PrefetchSupported[i][j] != true) { status = DML_FAIL_PREFETCH_SUPPORT; - } else if (locals->TotalVerticalActiveBandwidthSupport[i] != true) { + } else if (locals->TotalVerticalActiveBandwidthSupport[i][0] != true) { status = DML_FAIL_TOTAL_V_ACTIVE_BW; } else if (locals->VRatioInPrefetchSupported[i][j] != true) { status = DML_FAIL_V_RATIO_PREFETCH; @@ -5131,7 +5138,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode mode_lib->vba.DRAMSpeed = mode_lib->vba.DRAMSpeedPerState[mode_lib->vba.VoltageLevel]; mode_lib->vba.FabricClock = mode_lib->vba.FabricClockPerState[mode_lib->vba.VoltageLevel]; mode_lib->vba.SOCCLK = mode_lib->vba.SOCCLKPerState[mode_lib->vba.VoltageLevel]; - mode_lib->vba.ReturnBW = locals->ReturnBWPerState[mode_lib->vba.VoltageLevel]; + mode_lib->vba.ReturnBW = locals->ReturnBWPerState[mode_lib->vba.VoltageLevel][0]; mode_lib->vba.FabricAndDRAMBandwidth = locals->FabricAndDRAMBandwidthPerState[mode_lib->vba.VoltageLevel]; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { if (mode_lib->vba.BlendingAndTiming[k] == k) { diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c index 9df24ececcec..ca807846032f 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c @@ -107,10 +107,10 @@ static unsigned int get_bytes_per_element(enum source_format_class source_format static bool is_dual_plane(enum source_format_class source_format) { - bool ret_val = 0; + bool ret_val = false; if ((source_format == dm_420_8) || (source_format == dm_420_10)) - ret_val = 1; + ret_val = true; return ret_val; } @@ -240,8 +240,8 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib, unsigned int swath_bytes_c = 0; unsigned int full_swath_bytes_packed_l = 0; unsigned int full_swath_bytes_packed_c = 0; - bool req128_l = 0; - bool req128_c = 0; + bool req128_l = false; + bool req128_c = false; bool surf_linear = (pipe_src_param.sw_mode == dm_sw_linear); bool surf_vert = (pipe_src_param.source_scan == dm_vert); unsigned int log2_swath_height_l = 0; @@ -264,13 +264,13 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib, total_swath_bytes = 2 * full_swath_bytes_packed_l + 2 * full_swath_bytes_packed_c; if (total_swath_bytes <= detile_buf_size_in_bytes) { //full 256b request - req128_l = 0; - req128_c = 0; + req128_l = false; + req128_c = false; swath_bytes_l = full_swath_bytes_packed_l; swath_bytes_c = full_swath_bytes_packed_c; } else { //128b request (for luma only for yuv420 8bpc) - req128_l = 1; - req128_c = 0; + req128_l = true; + req128_c = false; swath_bytes_l = full_swath_bytes_packed_l / 2; swath_bytes_c = full_swath_bytes_packed_c; } @@ -280,9 +280,9 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib, total_swath_bytes = 2 * full_swath_bytes_packed_l; if (total_swath_bytes <= detile_buf_size_in_bytes) - req128_l = 0; + req128_l = false; else - req128_l = 1; + req128_l = true; swath_bytes_l = total_swath_bytes; swath_bytes_c = 0; @@ -670,7 +670,7 @@ static void get_surf_rq_param(struct display_mode_lib *mode_lib, const display_pipe_source_params_st pipe_src_param, bool is_chroma) { - bool mode_422 = 0; + bool mode_422 = false; unsigned int vp_width = 0; unsigned int vp_height = 0; unsigned int data_pitch = 0; @@ -958,7 +958,7 @@ static void dml20_rq_dlg_get_dlg_params(struct display_mode_lib *mode_lib, // Source // dcc_en = src.dcc; dual_plane = is_dual_plane((enum source_format_class)(src->source_format)); - mode_422 = 0; // TODO + mode_422 = false; // TODO access_dir = (src->source_scan == dm_vert); // vp access direction: horizontal or vertical accessed // bytes_per_element_l = get_bytes_per_element(source_format_class(src.source_format), 0); // bytes_per_element_c = get_bytes_per_element(source_format_class(src.source_format), 1); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c index 1e6aeb1bd2bf..287b7a0ad108 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c @@ -107,10 +107,10 @@ static unsigned int get_bytes_per_element(enum source_format_class source_format static bool is_dual_plane(enum source_format_class source_format) { - bool ret_val = 0; + bool ret_val = false; if ((source_format == dm_420_8) || (source_format == dm_420_10)) - ret_val = 1; + ret_val = true; return ret_val; } @@ -240,8 +240,8 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib, unsigned int swath_bytes_c = 0; unsigned int full_swath_bytes_packed_l = 0; unsigned int full_swath_bytes_packed_c = 0; - bool req128_l = 0; - bool req128_c = 0; + bool req128_l = false; + bool req128_c = false; bool surf_linear = (pipe_src_param.sw_mode == dm_sw_linear); bool surf_vert = (pipe_src_param.source_scan == dm_vert); unsigned int log2_swath_height_l = 0; @@ -264,13 +264,13 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib, total_swath_bytes = 2 * full_swath_bytes_packed_l + 2 * full_swath_bytes_packed_c; if (total_swath_bytes <= detile_buf_size_in_bytes) { //full 256b request - req128_l = 0; - req128_c = 0; + req128_l = false; + req128_c = false; swath_bytes_l = full_swath_bytes_packed_l; swath_bytes_c = full_swath_bytes_packed_c; } else { //128b request (for luma only for yuv420 8bpc) - req128_l = 1; - req128_c = 0; + req128_l = true; + req128_c = false; swath_bytes_l = full_swath_bytes_packed_l / 2; swath_bytes_c = full_swath_bytes_packed_c; } @@ -280,9 +280,9 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib, total_swath_bytes = 2 * full_swath_bytes_packed_l; if (total_swath_bytes <= detile_buf_size_in_bytes) - req128_l = 0; + req128_l = false; else - req128_l = 1; + req128_l = true; swath_bytes_l = total_swath_bytes; swath_bytes_c = 0; @@ -670,7 +670,7 @@ static void get_surf_rq_param(struct display_mode_lib *mode_lib, const display_pipe_source_params_st pipe_src_param, bool is_chroma) { - bool mode_422 = 0; + bool mode_422 = false; unsigned int vp_width = 0; unsigned int vp_height = 0; unsigned int data_pitch = 0; @@ -959,7 +959,7 @@ static void dml20v2_rq_dlg_get_dlg_params(struct display_mode_lib *mode_lib, // Source // dcc_en = src.dcc; dual_plane = is_dual_plane((enum source_format_class)(src->source_format)); - mode_422 = 0; // TODO + mode_422 = false; // TODO access_dir = (src->source_scan == dm_vert); // vp access direction: horizontal or vertical accessed // bytes_per_element_l = get_bytes_per_element(source_format_class(src.source_format), 0); // bytes_per_element_c = get_bytes_per_element(source_format_class(src.source_format), 1); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c index 945291d5ad98..e6617c958bb8 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c @@ -65,6 +65,7 @@ typedef struct { #define BPP_INVALID 0 #define BPP_BLENDED_PIPE 0xffffffff #define DCN21_MAX_DSC_IMAGE_WIDTH 5184 +#define DCN21_MAX_420_IMAGE_WIDTH 4096 static void DisplayPipeConfiguration(struct display_mode_lib *mode_lib); static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation( @@ -197,7 +198,7 @@ static unsigned int CalculateVMAndRowBytes( unsigned int *meta_row_width, unsigned int *meta_row_height, unsigned int *vm_group_bytes, - long *dpte_group_bytes, + unsigned int *dpte_group_bytes, unsigned int *PixelPTEReqWidth, unsigned int *PixelPTEReqHeight, unsigned int *PTERequestSize, @@ -295,7 +296,7 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( double UrgentOutOfOrderReturn, double ReturnBW, bool GPUVMEnable, - long dpte_group_bytes[], + int dpte_group_bytes[], unsigned int MetaChunkSize, double UrgentLatency, double ExtraLatency, @@ -309,13 +310,13 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( int DPPPerPlane[], bool DCCEnable[], double DPPCLK[], - unsigned int SwathWidthSingleDPPY[], + double SwathWidthSingleDPPY[], unsigned int SwathHeightY[], double ReadBandwidthPlaneLuma[], unsigned int SwathHeightC[], double ReadBandwidthPlaneChroma[], unsigned int LBBitPerPixel[], - unsigned int SwathWidthY[], + double SwathWidthY[], double HRatio[], unsigned int vtaps[], unsigned int VTAPsChroma[], @@ -344,7 +345,7 @@ static void CalculateDCFCLKDeepSleep( double BytePerPixelDETY[], double BytePerPixelDETC[], double VRatio[], - unsigned int SwathWidthY[], + double SwathWidthY[], int DPPPerPlane[], double HRatio[], double PixelClock[], @@ -435,7 +436,7 @@ static void CalculateMetaAndPTETimes( unsigned int meta_row_height[], unsigned int meta_req_width[], unsigned int meta_req_height[], - long dpte_group_bytes[], + int dpte_group_bytes[], unsigned int PTERequestSizeY[], unsigned int PTERequestSizeC[], unsigned int PixelPTEReqWidthY[], @@ -477,7 +478,7 @@ static double CalculateExtraLatency( bool HostVMEnable, int NumberOfActivePlanes, int NumberOfDPP[], - long dpte_group_bytes[], + int dpte_group_bytes[], double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData, double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly, int HostVMMaxPageTableLevels, @@ -1280,7 +1281,7 @@ static unsigned int CalculateVMAndRowBytes( unsigned int *meta_row_width, unsigned int *meta_row_height, unsigned int *vm_group_bytes, - long *dpte_group_bytes, + unsigned int *dpte_group_bytes, unsigned int *PixelPTEReqWidth, unsigned int *PixelPTEReqHeight, unsigned int *PTERequestSize, @@ -1338,7 +1339,7 @@ static unsigned int CalculateVMAndRowBytes( *MetaRowByte = 0; } - if (SurfaceTiling == dm_sw_linear || SurfaceTiling == dm_sw_gfx7_2d_thin_gl || SurfaceTiling == dm_sw_gfx7_2d_thin_lvp) { + if (SurfaceTiling == dm_sw_linear || SurfaceTiling == dm_sw_gfx7_2d_thin_gl || SurfaceTiling == dm_sw_gfx7_2d_thin_l_vp) { MacroTileSizeBytes = 256; MacroTileHeight = BlockHeight256Bytes; } else if (SurfaceTiling == dm_sw_4kb_s || SurfaceTiling == dm_sw_4kb_s_x @@ -1683,11 +1684,11 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman else locals->SwathWidthSingleDPPY[k] = mode_lib->vba.ViewportHeight[k]; - if (mode_lib->vba.ODMCombineEnabled[k] == true) + if (mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) MainPlaneDoesODMCombine = true; for (j = 0; j < mode_lib->vba.NumberOfActivePlanes; ++j) if (mode_lib->vba.BlendingAndTiming[k] == j - && mode_lib->vba.ODMCombineEnabled[j] == true) + && mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) MainPlaneDoesODMCombine = true; if (MainPlaneDoesODMCombine == true) @@ -2940,12 +2941,12 @@ static void DisplayPipeConfiguration(struct display_mode_lib *mode_lib) SwathWidth = mode_lib->vba.ViewportHeight[k]; } - if (mode_lib->vba.ODMCombineEnabled[k] == true) { + if (mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) { MainPlaneDoesODMCombine = true; } for (j = 0; j < mode_lib->vba.NumberOfActivePlanes; ++j) { if (mode_lib->vba.BlendingAndTiming[k] == j - && mode_lib->vba.ODMCombineEnabled[j] == true) { + && mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) { MainPlaneDoesODMCombine = true; } } @@ -3453,7 +3454,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l == dm_420_10)) || (((mode_lib->vba.SurfaceTiling[k] == dm_sw_gfx7_2d_thin_gl || mode_lib->vba.SurfaceTiling[k] - == dm_sw_gfx7_2d_thin_lvp) + == dm_sw_gfx7_2d_thin_l_vp) && !((mode_lib->vba.SourcePixelFormat[k] == dm_444_64 || mode_lib->vba.SourcePixelFormat[k] @@ -3542,17 +3543,17 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l } } for (i = 0; i <= mode_lib->vba.soc.num_states; i++) { - locals->IdealSDPPortBandwidthPerState[i] = dml_min3( + locals->IdealSDPPortBandwidthPerState[i][0] = dml_min3( mode_lib->vba.ReturnBusWidth * mode_lib->vba.DCFCLKPerState[i], mode_lib->vba.DRAMSpeedPerState[i] * mode_lib->vba.NumberOfChannels * mode_lib->vba.DRAMChannelWidth, mode_lib->vba.FabricClockPerState[i] * mode_lib->vba.FabricDatapathToDCNDataReturn); if (mode_lib->vba.HostVMEnable == false) { - locals->ReturnBWPerState[i] = locals->IdealSDPPortBandwidthPerState[i] + locals->ReturnBWPerState[i][0] = locals->IdealSDPPortBandwidthPerState[i][0] * mode_lib->vba.PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelDataOnly / 100.0; } else { - locals->ReturnBWPerState[i] = locals->IdealSDPPortBandwidthPerState[i] + locals->ReturnBWPerState[i][0] = locals->IdealSDPPortBandwidthPerState[i][0] * mode_lib->vba.PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData / 100.0; } } @@ -3589,12 +3590,12 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l + dml_max3(mode_lib->vba.UrgentOutOfOrderReturnPerChannelPixelDataOnly, mode_lib->vba.UrgentOutOfOrderReturnPerChannelPixelMixedWithVMData, mode_lib->vba.UrgentOutOfOrderReturnPerChannelVMDataOnly) - * mode_lib->vba.NumberOfChannels / locals->ReturnBWPerState[i]; - if ((mode_lib->vba.ROBBufferSizeInKByte - mode_lib->vba.PixelChunkSizeInKByte) * 1024.0 / locals->ReturnBWPerState[i] + * mode_lib->vba.NumberOfChannels / locals->ReturnBWPerState[i][0]; + if ((mode_lib->vba.ROBBufferSizeInKByte - mode_lib->vba.PixelChunkSizeInKByte) * 1024.0 / locals->ReturnBWPerState[i][0] > locals->UrgentRoundTripAndOutOfOrderLatencyPerState[i]) { - locals->ROBSupport[i] = true; + locals->ROBSupport[i][0] = true; } else { - locals->ROBSupport[i] = false; + locals->ROBSupport[i][0] = false; } } /*Writeback Mode Support Check*/ @@ -3971,18 +3972,25 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l && i == mode_lib->vba.soc.num_states) mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine = mode_lib->vba.PixelClock[k] / 2 * (1 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0); - if (mode_lib->vba.ODMCapability == false || - (locals->PlaneRequiredDISPCLKWithoutODMCombine <= MaxMaxDispclkRoundedDown - && (!locals->DSCEnabled[k] || locals->HActive[k] <= DCN21_MAX_DSC_IMAGE_WIDTH))) { - locals->ODMCombineEnablePerState[i][k] = false; - mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithoutODMCombine; - } else { - locals->ODMCombineEnablePerState[i][k] = true; - mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine; + + locals->ODMCombineEnablePerState[i][k] = false; + mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithoutODMCombine; + if (mode_lib->vba.ODMCapability) { + if (locals->PlaneRequiredDISPCLKWithoutODMCombine > MaxMaxDispclkRoundedDown) { + locals->ODMCombineEnablePerState[i][k] = true; + mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine; + } else if (locals->DSCEnabled[k] && (locals->HActive[k] > DCN21_MAX_DSC_IMAGE_WIDTH)) { + locals->ODMCombineEnablePerState[i][k] = true; + mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine; + } else if (locals->HActive[k] > DCN21_MAX_420_IMAGE_WIDTH && locals->OutputFormat[k] == dm_420) { + locals->ODMCombineEnablePerState[i][k] = true; + mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine; + } } + if (locals->MinDPPCLKUsingSingleDPP[k] * (1.0 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0) <= mode_lib->vba.MaxDppclkRoundedDownToDFSGranularity && locals->SwathWidthYSingleDPP[k] <= locals->MaximumSwathWidth[k] - && locals->ODMCombineEnablePerState[i][k] == false) { + && locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_disabled) { locals->NoOfDPP[i][j][k] = 1; locals->RequiredDPPCLK[i][j][k] = locals->MinDPPCLKUsingSingleDPP[k] * (1.0 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0); @@ -4071,16 +4079,16 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l /*Viewport Size Check*/ for (i = 0; i <= mode_lib->vba.soc.num_states; i++) { - locals->ViewportSizeSupport[i] = true; + locals->ViewportSizeSupport[i][0] = true; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { - if (locals->ODMCombineEnablePerState[i][k] == true) { + if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) { if (dml_min(locals->SwathWidthYSingleDPP[k], dml_round(mode_lib->vba.HActive[k] / 2.0 * mode_lib->vba.HRatio[k])) > locals->MaximumSwathWidth[k]) { - locals->ViewportSizeSupport[i] = false; + locals->ViewportSizeSupport[i][0] = false; } } else { if (locals->SwathWidthYSingleDPP[k] / 2.0 > locals->MaximumSwathWidth[k]) { - locals->ViewportSizeSupport[i] = false; + locals->ViewportSizeSupport[i][0] = false; } } } @@ -4121,11 +4129,11 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l } for (i = 0; i <= mode_lib->vba.soc.num_states; i++) { for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { - locals->RequiresDSC[i][k] = 0; + locals->RequiresDSC[i][k] = false; locals->RequiresFEC[i][k] = 0; if (mode_lib->vba.BlendingAndTiming[k] == k) { if (mode_lib->vba.Output[k] == dm_hdmi) { - locals->RequiresDSC[i][k] = 0; + locals->RequiresDSC[i][k] = false; locals->RequiresFEC[i][k] = 0; locals->OutputBppPerState[i][k] = TruncToValidBPP( dml_min(600.0, mode_lib->vba.PHYCLKPerState[i]) / mode_lib->vba.PixelClockBackEnd[k] * 24, @@ -4269,8 +4277,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.DSCFormatFactor = 1; } if (locals->RequiresDSC[i][k] == true) { - if (locals->ODMCombineEnablePerState[i][k] - == true) { + if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) { if (mode_lib->vba.PixelClockBackEnd[k] / 6.0 / mode_lib->vba.DSCFormatFactor > (1.0 - mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0) * mode_lib->vba.MaxDSCCLK[i]) { locals->DSCCLKRequiredMoreThanSupported[i] = @@ -4293,7 +4300,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.TotalDSCUnitsRequired = 0.0; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { if (locals->RequiresDSC[i][k] == true) { - if (locals->ODMCombineEnablePerState[i][k] == true) { + if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) { mode_lib->vba.TotalDSCUnitsRequired = mode_lib->vba.TotalDSCUnitsRequired + 2.0; } else { @@ -4335,7 +4342,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.bpp = locals->OutputBppPerState[i][k]; } if (locals->RequiresDSC[i][k] == true && mode_lib->vba.bpp != 0.0) { - if (locals->ODMCombineEnablePerState[i][k] == false) { + if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_disabled) { locals->DSCDelayPerState[i][k] = dscceComputeDelay( mode_lib->vba.DSCInputBitPerComponent[k], @@ -4399,7 +4406,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { locals->RequiredDPPCLKThisState[k] = locals->RequiredDPPCLK[i][j][k]; locals->NoOfDPPThisState[k] = locals->NoOfDPP[i][j][k]; - if (locals->ODMCombineEnablePerState[i][k] == true) { + if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) { locals->SwathWidthYThisState[k] = dml_min(locals->SwathWidthYSingleDPP[k], dml_round(mode_lib->vba.HActive[k] / 2.0 * mode_lib->vba.HRatio[k])); } else { @@ -4451,7 +4458,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l locals->PSCL_FACTOR, locals->PSCL_FACTOR_CHROMA, locals->RequiredDPPCLKThisState, - &mode_lib->vba.ProjectedDCFCLKDeepSleep); + &mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0]); for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { if ((mode_lib->vba.SourcePixelFormat[k] != dm_444_64 @@ -4496,7 +4503,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l locals->PTERequestSizeC, locals->dpde0_bytes_per_frame_ub_c, locals->meta_pte_bytes_per_frame_ub_c); - locals->PrefetchLinesC[k] = CalculatePrefetchSourceLines( + locals->PrefetchLinesC[0][0][k] = CalculatePrefetchSourceLines( mode_lib, mode_lib->vba.VRatio[k]/2, mode_lib->vba.VTAPsChroma[k], @@ -4511,7 +4518,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.PDEAndMetaPTEBytesPerFrameC = 0.0; mode_lib->vba.MetaRowBytesC = 0.0; mode_lib->vba.DPTEBytesPerRowC = 0.0; - locals->PrefetchLinesC[k] = 0.0; + locals->PrefetchLinesC[0][0][k] = 0.0; locals->PTEBufferSizeNotExceededC[i][j][k] = true; locals->PTEBufferSizeInRequestsForLuma = mode_lib->vba.PTEBufferSizeInRequestsLuma + mode_lib->vba.PTEBufferSizeInRequestsChroma; } @@ -4552,7 +4559,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l locals->PTERequestSizeY, locals->dpde0_bytes_per_frame_ub_l, locals->meta_pte_bytes_per_frame_ub_l); - locals->PrefetchLinesY[k] = CalculatePrefetchSourceLines( + locals->PrefetchLinesY[0][0][k] = CalculatePrefetchSourceLines( mode_lib, mode_lib->vba.VRatio[k], mode_lib->vba.vtaps[k], @@ -4562,10 +4569,10 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.ViewportYStartY[k], &locals->PrefillY[k], &locals->MaxNumSwY[k]); - locals->PDEAndMetaPTEBytesPerFrame[k] = + locals->PDEAndMetaPTEBytesPerFrame[0][0][k] = mode_lib->vba.PDEAndMetaPTEBytesPerFrameY + mode_lib->vba.PDEAndMetaPTEBytesPerFrameC; - locals->MetaRowBytes[k] = mode_lib->vba.MetaRowBytesY + mode_lib->vba.MetaRowBytesC; - locals->DPTEBytesPerRow[k] = mode_lib->vba.DPTEBytesPerRowY + mode_lib->vba.DPTEBytesPerRowC; + locals->MetaRowBytes[0][0][k] = mode_lib->vba.MetaRowBytesY + mode_lib->vba.MetaRowBytesC; + locals->DPTEBytesPerRow[0][0][k] = mode_lib->vba.DPTEBytesPerRowY + mode_lib->vba.DPTEBytesPerRowC; CalculateActiveRowBandwidth( mode_lib->vba.GPUVMEnable, @@ -4591,7 +4598,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.PixelChunkSizeInKByte, locals->TotalNumberOfDCCActiveDPP[i][j], mode_lib->vba.MetaChunkSize, - locals->ReturnBWPerState[i], + locals->ReturnBWPerState[i][0], mode_lib->vba.GPUVMEnable, mode_lib->vba.HostVMEnable, mode_lib->vba.NumberOfActivePlanes, @@ -4602,7 +4609,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.HostVMMaxPageTableLevels, mode_lib->vba.HostVMCachedPageTableLevels); - mode_lib->vba.TimeCalc = 24.0 / mode_lib->vba.ProjectedDCFCLKDeepSleep; + mode_lib->vba.TimeCalc = 24.0 / mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0]; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { if (mode_lib->vba.BlendingAndTiming[k] == k) { if (mode_lib->vba.WritebackEnable[k] == true) { @@ -4644,15 +4651,15 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l } } } - mode_lib->vba.MaxMaxVStartup = 0; + mode_lib->vba.MaxMaxVStartup[0][0] = 0; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { - locals->MaximumVStartup[k] = mode_lib->vba.VTotal[k] - mode_lib->vba.VActive[k] + locals->MaximumVStartup[0][0][k] = mode_lib->vba.VTotal[k] - mode_lib->vba.VActive[k] - dml_max(1.0, dml_ceil(locals->WritebackDelay[i][k] / (mode_lib->vba.HTotal[k] / mode_lib->vba.PixelClock[k]), 1.0)); - mode_lib->vba.MaxMaxVStartup = dml_max(mode_lib->vba.MaxMaxVStartup, locals->MaximumVStartup[k]); + mode_lib->vba.MaxMaxVStartup[0][0] = dml_max(mode_lib->vba.MaxMaxVStartup[0][0], locals->MaximumVStartup[0][0][k]); } mode_lib->vba.NextPrefetchMode = mode_lib->vba.MinPrefetchMode; - mode_lib->vba.NextMaxVStartup = mode_lib->vba.MaxMaxVStartup; + mode_lib->vba.NextMaxVStartup = mode_lib->vba.MaxMaxVStartup[0][0]; do { mode_lib->vba.PrefetchMode[i][j] = mode_lib->vba.NextPrefetchMode; mode_lib->vba.MaxVStartup = mode_lib->vba.NextMaxVStartup; @@ -4693,7 +4700,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l myPipe.DPPCLK = locals->RequiredDPPCLK[i][j][k]; myPipe.DISPCLK = locals->RequiredDISPCLK[i][j]; myPipe.PixelClock = mode_lib->vba.PixelClock[k]; - myPipe.DCFCLKDeepSleep = mode_lib->vba.ProjectedDCFCLKDeepSleep; + myPipe.DCFCLKDeepSleep = mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0]; myPipe.DPPPerPlane = locals->NoOfDPP[i][j][k]; myPipe.ScalerEnabled = mode_lib->vba.ScalerEnabled[k]; myPipe.SourceScan = mode_lib->vba.SourceScan[k]; @@ -4727,8 +4734,8 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l locals->SwathWidthYThisState[k] / mode_lib->vba.HRatio[k], mode_lib->vba.OutputFormat[k], mode_lib->vba.MaxInterDCNTileRepeaters, - dml_min(mode_lib->vba.MaxVStartup, locals->MaximumVStartup[k]), - locals->MaximumVStartup[k], + dml_min(mode_lib->vba.MaxVStartup, locals->MaximumVStartup[0][0][k]), + locals->MaximumVStartup[0][0][k], mode_lib->vba.GPUVMMaxPageTableLevels, mode_lib->vba.GPUVMEnable, &myHostVM, @@ -4739,15 +4746,15 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.UrgentLatency, mode_lib->vba.ExtraLatency, mode_lib->vba.TimeCalc, - locals->PDEAndMetaPTEBytesPerFrame[k], - locals->MetaRowBytes[k], - locals->DPTEBytesPerRow[k], - locals->PrefetchLinesY[k], + locals->PDEAndMetaPTEBytesPerFrame[0][0][k], + locals->MetaRowBytes[0][0][k], + locals->DPTEBytesPerRow[0][0][k], + locals->PrefetchLinesY[0][0][k], locals->SwathWidthYThisState[k], locals->BytePerPixelInDETY[k], locals->PrefillY[k], locals->MaxNumSwY[k], - locals->PrefetchLinesC[k], + locals->PrefetchLinesC[0][0][k], locals->BytePerPixelInDETC[k], locals->PrefillC[k], locals->MaxNumSwC[k], @@ -4836,14 +4843,14 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l + locals->RequiredPrefetchPixelDataBWChroma[i][j][k] * locals->UrgentBurstFactorChromaPre[k] + locals->cursor_bw_pre[k] * locals->UrgentBurstFactorCursorPre[k]); } - locals->BandwidthWithoutPrefetchSupported[i] = true; - if (mode_lib->vba.MaximumReadBandwidthWithoutPrefetch > locals->ReturnBWPerState[i] + locals->BandwidthWithoutPrefetchSupported[i][0] = true; + if (mode_lib->vba.MaximumReadBandwidthWithoutPrefetch > locals->ReturnBWPerState[i][0] || locals->NotEnoughUrgentLatencyHiding == 1) { - locals->BandwidthWithoutPrefetchSupported[i] = false; + locals->BandwidthWithoutPrefetchSupported[i][0] = false; } locals->PrefetchSupported[i][j] = true; - if (mode_lib->vba.MaximumReadBandwidthWithPrefetch > locals->ReturnBWPerState[i] + if (mode_lib->vba.MaximumReadBandwidthWithPrefetch > locals->ReturnBWPerState[i][0] || locals->NotEnoughUrgentLatencyHiding == 1 || locals->NotEnoughUrgentLatencyHidingPre == 1) { locals->PrefetchSupported[i][j] = false; @@ -4872,17 +4879,17 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l } if (mode_lib->vba.MaxVStartup <= 13 || mode_lib->vba.AnyLinesForVMOrRowTooLarge == false) { - mode_lib->vba.NextMaxVStartup = mode_lib->vba.MaxMaxVStartup; + mode_lib->vba.NextMaxVStartup = mode_lib->vba.MaxMaxVStartup[0][0]; mode_lib->vba.NextPrefetchMode = mode_lib->vba.NextPrefetchMode + 1; } else { mode_lib->vba.NextMaxVStartup = mode_lib->vba.NextMaxVStartup - 1; } } while ((locals->PrefetchSupported[i][j] != true || locals->VRatioInPrefetchSupported[i][j] != true) - && (mode_lib->vba.NextMaxVStartup != mode_lib->vba.MaxMaxVStartup + && (mode_lib->vba.NextMaxVStartup != mode_lib->vba.MaxMaxVStartup[0][0] || mode_lib->vba.NextPrefetchMode < mode_lib->vba.MaxPrefetchMode)); if (locals->PrefetchSupported[i][j] == true && locals->VRatioInPrefetchSupported[i][j] == true) { - mode_lib->vba.BandwidthAvailableForImmediateFlip = locals->ReturnBWPerState[i]; + mode_lib->vba.BandwidthAvailableForImmediateFlip = locals->ReturnBWPerState[i][0]; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { mode_lib->vba.BandwidthAvailableForImmediateFlip = mode_lib->vba.BandwidthAvailableForImmediateFlip - dml_max(locals->ReadBandwidthLuma[k] * locals->UrgentBurstFactorLuma[k] @@ -4895,7 +4902,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.TotImmediateFlipBytes = 0.0; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { mode_lib->vba.TotImmediateFlipBytes = mode_lib->vba.TotImmediateFlipBytes - + locals->PDEAndMetaPTEBytesPerFrame[k] + locals->MetaRowBytes[k] + locals->DPTEBytesPerRow[k]; + + locals->PDEAndMetaPTEBytesPerFrame[0][0][k] + locals->MetaRowBytes[0][0][k] + locals->DPTEBytesPerRow[0][0][k]; } for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { @@ -4910,9 +4917,9 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.HostVMMaxPageTableLevels, mode_lib->vba.HostVMCachedPageTableLevels, mode_lib->vba.GPUVMEnable, - locals->PDEAndMetaPTEBytesPerFrame[k], - locals->MetaRowBytes[k], - locals->DPTEBytesPerRow[k], + locals->PDEAndMetaPTEBytesPerFrame[0][0][k], + locals->MetaRowBytes[0][0][k], + locals->DPTEBytesPerRow[0][0][k], mode_lib->vba.BandwidthAvailableForImmediateFlip, mode_lib->vba.TotImmediateFlipBytes, mode_lib->vba.SourcePixelFormat[k], @@ -4943,7 +4950,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l } locals->ImmediateFlipSupportedForState[i][j] = true; if (mode_lib->vba.total_dcn_read_bw_with_flip - > locals->ReturnBWPerState[i]) { + > locals->ReturnBWPerState[i][0]) { locals->ImmediateFlipSupportedForState[i][j] = false; } for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { @@ -4970,7 +4977,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.WritebackInterfaceChromaBufferSize, mode_lib->vba.DCFCLKPerState[i], mode_lib->vba.UrgentOutOfOrderReturnPerChannel * mode_lib->vba.NumberOfChannels, - locals->ReturnBWPerState[i], + locals->ReturnBWPerState[i][0], mode_lib->vba.GPUVMEnable, locals->dpte_group_bytes, mode_lib->vba.MetaChunkSize, @@ -4982,7 +4989,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.DRAMClockChangeLatency, mode_lib->vba.SRExitTime, mode_lib->vba.SREnterPlusExitTime, - mode_lib->vba.ProjectedDCFCLKDeepSleep, + mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0], locals->NoOfDPPThisState, mode_lib->vba.DCCEnable, locals->RequiredDPPCLKThisState, @@ -5025,8 +5032,8 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l MaxTotalVActiveRDBandwidth = MaxTotalVActiveRDBandwidth + locals->ReadBandwidth[k]; } for (i = 0; i <= mode_lib->vba.soc.num_states; ++i) { - locals->MaxTotalVerticalActiveAvailableBandwidth[i] = dml_min( - locals->IdealSDPPortBandwidthPerState[i] * + locals->MaxTotalVerticalActiveAvailableBandwidth[i][0] = dml_min( + locals->IdealSDPPortBandwidthPerState[i][0] * mode_lib->vba.MaxAveragePercentOfIdealSDPPortBWDisplayCanUseInNormalSystemOperation / 100.0, mode_lib->vba.DRAMSpeedPerState[i] * mode_lib->vba.NumberOfChannels * @@ -5034,10 +5041,10 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.MaxAveragePercentOfIdealDRAMBWDisplayCanUseInNormalSystemOperation / 100.0); - if (MaxTotalVActiveRDBandwidth <= locals->MaxTotalVerticalActiveAvailableBandwidth[i]) { - locals->TotalVerticalActiveBandwidthSupport[i] = true; + if (MaxTotalVActiveRDBandwidth <= locals->MaxTotalVerticalActiveAvailableBandwidth[i][0]) { + locals->TotalVerticalActiveBandwidthSupport[i][0] = true; } else { - locals->TotalVerticalActiveBandwidthSupport[i] = false; + locals->TotalVerticalActiveBandwidthSupport[i][0] = false; } } } @@ -5116,7 +5123,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l status = DML_FAIL_SCALE_RATIO_TAP; } else if (mode_lib->vba.SourceFormatPixelAndScanSupport != true) { status = DML_FAIL_SOURCE_PIXEL_FORMAT; - } else if (locals->ViewportSizeSupport[i] != true) { + } else if (locals->ViewportSizeSupport[i][0] != true) { status = DML_FAIL_VIEWPORT_SIZE; } else if (locals->DIOSupport[i] != true) { status = DML_FAIL_DIO_SUPPORT; @@ -5124,7 +5131,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l status = DML_FAIL_NOT_ENOUGH_DSC; } else if (locals->DSCCLKRequiredMoreThanSupported[i] != false) { status = DML_FAIL_DSC_CLK_REQUIRED; - } else if (locals->ROBSupport[i] != true) { + } else if (locals->ROBSupport[i][0] != true) { status = DML_FAIL_REORDERING_BUFFER; } else if (locals->DISPCLK_DPPCLK_Support[i][j] != true) { status = DML_FAIL_DISPCLK_DPPCLK; @@ -5142,7 +5149,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l status = DML_FAIL_CURSOR_SUPPORT; } else if (mode_lib->vba.PitchSupport != true) { status = DML_FAIL_PITCH_SUPPORT; - } else if (locals->TotalVerticalActiveBandwidthSupport[i] != true) { + } else if (locals->TotalVerticalActiveBandwidthSupport[i][0] != true) { status = DML_FAIL_TOTAL_V_ACTIVE_BW; } else if (locals->PTEBufferSizeNotExceeded[i][j] != true) { status = DML_FAIL_PTE_BUFFER_SIZE; @@ -5198,13 +5205,13 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.DRAMSpeed = mode_lib->vba.DRAMSpeedPerState[mode_lib->vba.VoltageLevel]; mode_lib->vba.FabricClock = mode_lib->vba.FabricClockPerState[mode_lib->vba.VoltageLevel]; mode_lib->vba.SOCCLK = mode_lib->vba.SOCCLKPerState[mode_lib->vba.VoltageLevel]; - mode_lib->vba.ReturnBW = locals->ReturnBWPerState[mode_lib->vba.VoltageLevel]; + mode_lib->vba.ReturnBW = locals->ReturnBWPerState[mode_lib->vba.VoltageLevel][0]; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { if (mode_lib->vba.BlendingAndTiming[k] == k) { mode_lib->vba.ODMCombineEnabled[k] = locals->ODMCombineEnablePerState[mode_lib->vba.VoltageLevel][k]; } else { - mode_lib->vba.ODMCombineEnabled[k] = 0; + mode_lib->vba.ODMCombineEnabled[k] = false; } mode_lib->vba.DSCEnabled[k] = locals->RequiresDSC[mode_lib->vba.VoltageLevel][k]; @@ -5227,7 +5234,7 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( double UrgentOutOfOrderReturn, double ReturnBW, bool GPUVMEnable, - long dpte_group_bytes[], + int dpte_group_bytes[], unsigned int MetaChunkSize, double UrgentLatency, double ExtraLatency, @@ -5241,13 +5248,13 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( int DPPPerPlane[], bool DCCEnable[], double DPPCLK[], - unsigned int SwathWidthSingleDPPY[], + double SwathWidthSingleDPPY[], unsigned int SwathHeightY[], double ReadBandwidthPlaneLuma[], unsigned int SwathHeightC[], double ReadBandwidthPlaneChroma[], unsigned int LBBitPerPixel[], - unsigned int SwathWidthY[], + double SwathWidthY[], double HRatio[], unsigned int vtaps[], unsigned int VTAPsChroma[], @@ -5503,7 +5510,7 @@ static void CalculateDCFCLKDeepSleep( double BytePerPixelDETY[], double BytePerPixelDETC[], double VRatio[], - unsigned int SwathWidthY[], + double SwathWidthY[], int DPPPerPlane[], double HRatio[], double PixelClock[], @@ -5831,7 +5838,7 @@ static void CalculateMetaAndPTETimes( unsigned int meta_row_height[], unsigned int meta_req_width[], unsigned int meta_req_height[], - long dpte_group_bytes[], + int dpte_group_bytes[], unsigned int PTERequestSizeY[], unsigned int PTERequestSizeC[], unsigned int PixelPTEReqWidthY[], @@ -6087,7 +6094,7 @@ static double CalculateExtraLatency( bool HostVMEnable, int NumberOfActivePlanes, int NumberOfDPP[], - long dpte_group_bytes[], + int dpte_group_bytes[], double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData, double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly, int HostVMMaxPageTableLevels, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c index e60af383b4db..a38baa73d484 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c @@ -82,10 +82,10 @@ static unsigned int get_bytes_per_element(enum source_format_class source_format static bool is_dual_plane(enum source_format_class source_format) { - bool ret_val = 0; + bool ret_val = false; if ((source_format == dm_420_8) || (source_format == dm_420_10)) - ret_val = 1; + ret_val = true; return ret_val; } @@ -222,8 +222,8 @@ static void handle_det_buf_split( unsigned int swath_bytes_c = 0; unsigned int full_swath_bytes_packed_l = 0; unsigned int full_swath_bytes_packed_c = 0; - bool req128_l = 0; - bool req128_c = 0; + bool req128_l = false; + bool req128_c = false; bool surf_linear = (pipe_src_param.sw_mode == dm_sw_linear); bool surf_vert = (pipe_src_param.source_scan == dm_vert); unsigned int log2_swath_height_l = 0; @@ -248,13 +248,13 @@ static void handle_det_buf_split( total_swath_bytes = 2 * full_swath_bytes_packed_l + 2 * full_swath_bytes_packed_c; if (total_swath_bytes <= detile_buf_size_in_bytes) { //full 256b request - req128_l = 0; - req128_c = 0; + req128_l = false; + req128_c = false; swath_bytes_l = full_swath_bytes_packed_l; swath_bytes_c = full_swath_bytes_packed_c; } else { //128b request (for luma only for yuv420 8bpc) - req128_l = 1; - req128_c = 0; + req128_l = true; + req128_c = false; swath_bytes_l = full_swath_bytes_packed_l / 2; swath_bytes_c = full_swath_bytes_packed_c; } @@ -264,9 +264,9 @@ static void handle_det_buf_split( total_swath_bytes = 2 * full_swath_bytes_packed_l; if (total_swath_bytes <= detile_buf_size_in_bytes) - req128_l = 0; + req128_l = false; else - req128_l = 1; + req128_l = true; swath_bytes_l = total_swath_bytes; swath_bytes_c = 0; @@ -679,7 +679,7 @@ static void get_surf_rq_param( const display_pipe_params_st pipe_param, bool is_chroma) { - bool mode_422 = 0; + bool mode_422 = false; unsigned int vp_width = 0; unsigned int vp_height = 0; unsigned int data_pitch = 0; @@ -1010,7 +1010,7 @@ static void dml_rq_dlg_get_dlg_params( // Source // dcc_en = src.dcc; dual_plane = is_dual_plane((enum source_format_class) (src->source_format)); - mode_422 = 0; // FIXME + mode_422 = false; // FIXME access_dir = (src->source_scan == dm_vert); // vp access direction: horizontal or vertical accessed // bytes_per_element_l = get_bytes_per_element(source_format_class(src.source_format), 0); // bytes_per_element_c = get_bytes_per_element(source_format_class(src.source_format), 1); diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_enums.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_enums.h index 55d4cb23a073..bfc2f39bd1ef 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_enums.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_enums.h @@ -85,7 +85,7 @@ enum dm_swizzle_mode { dm_sw_var_s_x = 29, dm_sw_var_d_x = 30, dm_sw_64kb_r_x, - dm_sw_gfx7_2d_thin_lvp, + dm_sw_gfx7_2d_thin_l_vp, dm_sw_gfx7_2d_thin_gl, }; enum lb_depth { @@ -119,6 +119,10 @@ enum mpc_combine_affinity { dm_mpc_never }; +enum RequestType { + REQ_256Bytes, REQ_128BytesNonContiguous, REQ_128BytesContiguous, REQ_NA +}; + enum self_refresh_affinity { dm_try_to_allow_self_refresh_and_mclk_switch, dm_allow_self_refresh_and_mclk_switch, @@ -165,4 +169,16 @@ enum odm_combine_mode { dm_odm_combine_mode_4to1, }; +enum odm_combine_policy { + dm_odm_combine_policy_dal, + dm_odm_combine_policy_none, + dm_odm_combine_policy_2to1, + dm_odm_combine_policy_4to1, +}; + +enum immediate_flip_requirement { + dm_immediate_flip_not_required, + dm_immediate_flip_required, +}; + #endif diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h index 220d5e610f1f..658f81e757e9 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h @@ -63,6 +63,7 @@ struct _vcs_dpi_voltage_scaling_st { double dispclk_mhz; double phyclk_mhz; double dppclk_mhz; + double dtbclk_mhz; }; struct _vcs_dpi_soc_bounding_box_st { @@ -214,6 +215,7 @@ struct _vcs_dpi_display_pipe_source_params_st { int source_format; unsigned char dcc; unsigned int dcc_rate; + unsigned int dcc_rate_chroma; unsigned char dcc_use_global; unsigned char vm; bool gpuvm; // gpuvm enabled @@ -225,7 +227,10 @@ struct _vcs_dpi_display_pipe_source_params_st { int source_scan; int sw_mode; int macro_tile_size; + unsigned int surface_width_y; unsigned int surface_height_y; + unsigned int surface_width_c; + unsigned int surface_height_c; unsigned int viewport_width; unsigned int viewport_height; unsigned int viewport_y_y; @@ -278,6 +283,7 @@ struct _vcs_dpi_display_output_params_st { int output_type; int output_format; int dsc_slices; + int max_audio_sample_rate; struct writeback_st wb; }; @@ -323,7 +329,7 @@ struct _vcs_dpi_display_pipe_dest_params_st { double pixel_rate_mhz; unsigned char synchronized_vblank_all_planes; unsigned char otg_inst; - unsigned char odm_combine; + unsigned int odm_combine; unsigned char use_maximum_vstartup; unsigned int vtotal_max; unsigned int vtotal_min; diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c index 15b72a8b5174..b3c96d9b472f 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c @@ -264,7 +264,10 @@ static void fetch_socbb_params(struct display_mode_lib *mode_lib) mode_lib->vba.DRAMSpeedPerState[i] = soc->clock_limits[i].dram_speed_mts; //mode_lib->vba.DRAMSpeedPerState[i] = soc->clock_limits[i].dram_speed_mhz; mode_lib->vba.MaxDispclk[i] = soc->clock_limits[i].dispclk_mhz; + mode_lib->vba.DTBCLKPerState[i] = soc->clock_limits[i].dtbclk_mhz; } + mode_lib->vba.MinVoltageLevel = 0; + mode_lib->vba.MaxVoltageLevel = mode_lib->vba.soc.num_states; mode_lib->vba.DoUrgentLatencyAdjustment = soc->do_urgent_latency_adjustment; @@ -306,8 +309,6 @@ static void fetch_ip_params(struct display_mode_lib *mode_lib) mode_lib->vba.WritebackInterfaceBufferSize = ip->writeback_interface_buffer_size_kbytes; mode_lib->vba.WritebackLineBufferSize = ip->writeback_line_buffer_buffer_size; - mode_lib->vba.MinVoltageLevel = 0; - mode_lib->vba.MaxVoltageLevel = 5; mode_lib->vba.WritebackChromaLineBufferWidth = ip->writeback_chroma_line_buffer_width_pixels; @@ -423,8 +424,8 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib) ip->dcc_supported : src->dcc && ip->dcc_supported; mode_lib->vba.DCCRate[mode_lib->vba.NumberOfActivePlanes] = src->dcc_rate; /* TODO: Needs to be set based on src->dcc_rate_luma/chroma */ - mode_lib->vba.DCCRateLuma[mode_lib->vba.NumberOfActivePlanes] = 0; - mode_lib->vba.DCCRateChroma[mode_lib->vba.NumberOfActivePlanes] = 0; + mode_lib->vba.DCCRateLuma[mode_lib->vba.NumberOfActivePlanes] = src->dcc_rate; + mode_lib->vba.DCCRateChroma[mode_lib->vba.NumberOfActivePlanes] = src->dcc_rate_chroma; mode_lib->vba.SourcePixelFormat[mode_lib->vba.NumberOfActivePlanes] = (enum source_format_class) (src->source_format); @@ -436,8 +437,6 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib) dst->recout_width; // TODO: or should this be full_recout_width???...maybe only when in hsplit mode? mode_lib->vba.ODMCombineEnabled[mode_lib->vba.NumberOfActivePlanes] = dst->odm_combine; - mode_lib->vba.ODMCombineTypeEnabled[mode_lib->vba.NumberOfActivePlanes] = - dst->odm_combine; mode_lib->vba.OutputFormat[mode_lib->vba.NumberOfActivePlanes] = (enum output_format_class) (dout->output_format); mode_lib->vba.OutputBpp[mode_lib->vba.NumberOfActivePlanes] = @@ -454,7 +453,7 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib) dout->dp_lanes; /* TODO: Needs to be set based on dout->audio.audio_sample_rate_khz/sample_layout */ mode_lib->vba.AudioSampleRate[mode_lib->vba.NumberOfActivePlanes] = - 44.1 * 1000; + dout->max_audio_sample_rate; mode_lib->vba.AudioSampleLayout[mode_lib->vba.NumberOfActivePlanes] = 1; mode_lib->vba.DRAMClockChangeLatencyOverride = 0.0; @@ -590,6 +589,7 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib) for (k = j + 1; k < mode_lib->vba.cache_num_pipes; ++k) { display_pipe_source_params_st *src_k = &pipes[k].pipe.src; display_pipe_dest_params_st *dst_k = &pipes[k].pipe.dest; + display_output_params_st *dout_k = &pipes[j].dout; if (src_k->is_hsplit && !visited[k] && src->hsplit_grp == src_k->hsplit_grp) { @@ -600,12 +600,18 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib) == dm_horz) { mode_lib->vba.ViewportWidth[mode_lib->vba.NumberOfActivePlanes] += src_k->viewport_width; + mode_lib->vba.ViewportWidthChroma[mode_lib->vba.NumberOfActivePlanes] += + src_k->viewport_width; mode_lib->vba.ScalerRecoutWidth[mode_lib->vba.NumberOfActivePlanes] += dst_k->recout_width; } else { mode_lib->vba.ViewportHeight[mode_lib->vba.NumberOfActivePlanes] += src_k->viewport_height; + mode_lib->vba.ViewportHeightChroma[mode_lib->vba.NumberOfActivePlanes] += + src_k->viewport_height; } + mode_lib->vba.NumberOfDSCSlices[mode_lib->vba.NumberOfActivePlanes] += + dout_k->dsc_slices; visited[k] = true; } @@ -811,7 +817,9 @@ void ModeSupportAndSystemConfiguration(struct display_mode_lib *mode_lib) unsigned int total_pipes = 0; mode_lib->vba.VoltageLevel = mode_lib->vba.cache_pipes[0].clks_cfg.voltage; - mode_lib->vba.ReturnBW = mode_lib->vba.ReturnBWPerState[mode_lib->vba.VoltageLevel]; + mode_lib->vba.ReturnBW = mode_lib->vba.ReturnBWPerState[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb]; + if (mode_lib->vba.ReturnBW == 0) + mode_lib->vba.ReturnBW = mode_lib->vba.ReturnBWPerState[mode_lib->vba.VoltageLevel][0]; mode_lib->vba.FabricAndDRAMBandwidth = mode_lib->vba.FabricAndDRAMBandwidthPerState[mode_lib->vba.VoltageLevel]; fetch_socbb_params(mode_lib); diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h index 3eb657ed5714..2875efd85467 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h @@ -157,6 +157,7 @@ struct vba_vars_st { bool DummyPStateCheck; bool DRAMClockChangeSupportsVActive; bool PrefetchModeSupported; + bool PrefetchAndImmediateFlipSupported; enum self_refresh_affinity AllowDRAMSelfRefreshOrDRAMClockChangeInVblank; // Mode Support only double XFCRemoteSurfaceFlipDelay; double TInitXFill; @@ -318,8 +319,7 @@ struct vba_vars_st { unsigned int DynamicMetadataTransmittedBytes[DC__NUM_DPP__MAX]; double DCCRate[DC__NUM_DPP__MAX]; double AverageDCCCompressionRate; - bool ODMCombineEnabled[DC__NUM_DPP__MAX]; - enum odm_combine_mode ODMCombineTypeEnabled[DC__NUM_DPP__MAX]; + enum odm_combine_mode ODMCombineEnabled[DC__NUM_DPP__MAX]; double OutputBpp[DC__NUM_DPP__MAX]; bool DSCEnabled[DC__NUM_DPP__MAX]; unsigned int DSCInputBitPerComponent[DC__NUM_DPP__MAX]; @@ -347,6 +347,7 @@ struct vba_vars_st { unsigned int EffectiveLBLatencyHidingSourceLinesChroma; double BandwidthAvailableForImmediateFlip; unsigned int PrefetchMode[DC__VOLTAGE_STATES + 1][2]; + unsigned int PrefetchModePerState[DC__VOLTAGE_STATES + 1][2]; unsigned int MinPrefetchMode; unsigned int MaxPrefetchMode; bool AnyLinesForVMOrRowTooLarge; @@ -396,6 +397,7 @@ struct vba_vars_st { bool WritebackLumaAndChromaScalingSupported; bool Cursor64BppSupport; double DCFCLKPerState[DC__VOLTAGE_STATES + 1]; + double DCFCLKState[DC__VOLTAGE_STATES + 1][2]; double FabricClockPerState[DC__VOLTAGE_STATES + 1]; double SOCCLKPerState[DC__VOLTAGE_STATES + 1]; double PHYCLKPerState[DC__VOLTAGE_STATES + 1]; @@ -444,7 +446,7 @@ struct vba_vars_st { double OutputLinkDPLanes[DC__NUM_DPP__MAX]; double ForcedOutputLinkBPP[DC__NUM_DPP__MAX]; // Mode Support only double ImmediateFlipBW[DC__NUM_DPP__MAX]; - double MaxMaxVStartup; + double MaxMaxVStartup[DC__VOLTAGE_STATES + 1][2]; double WritebackLumaVExtra; double WritebackChromaVExtra; @@ -471,7 +473,7 @@ struct vba_vars_st { double RoundedUpMaxSwathSizeBytesC; double EffectiveDETLBLinesLuma; double EffectiveDETLBLinesChroma; - double ProjectedDCFCLKDeepSleep; + double ProjectedDCFCLKDeepSleep[DC__VOLTAGE_STATES + 1][2]; double PDEAndMetaPTEBytesPerFrameY; double PDEAndMetaPTEBytesPerFrameC; unsigned int MetaRowBytesY; @@ -489,12 +491,11 @@ struct vba_vars_st { double FractionOfUrgentBandwidthImmediateFlip; // Mode Support debugging output /* ms locals */ - double IdealSDPPortBandwidthPerState[DC__VOLTAGE_STATES + 1]; + double IdealSDPPortBandwidthPerState[DC__VOLTAGE_STATES + 1][2]; unsigned int NoOfDPP[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; int NoOfDPPThisState[DC__NUM_DPP__MAX]; - bool ODMCombineEnablePerState[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX]; - enum odm_combine_mode ODMCombineTypeEnablePerState[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX]; - unsigned int SwathWidthYThisState[DC__NUM_DPP__MAX]; + enum odm_combine_mode ODMCombineEnablePerState[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX]; + double SwathWidthYThisState[DC__NUM_DPP__MAX]; unsigned int SwathHeightCPerState[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; unsigned int SwathHeightYThisState[DC__NUM_DPP__MAX]; unsigned int SwathHeightCThisState[DC__NUM_DPP__MAX]; @@ -506,7 +507,7 @@ struct vba_vars_st { double RequiredDPPCLKThisState[DC__NUM_DPP__MAX]; bool PTEBufferSizeNotExceededY[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; bool PTEBufferSizeNotExceededC[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; - bool BandwidthWithoutPrefetchSupported[DC__VOLTAGE_STATES + 1]; + bool BandwidthWithoutPrefetchSupported[DC__VOLTAGE_STATES + 1][2]; bool PrefetchSupported[DC__VOLTAGE_STATES + 1][2]; bool VRatioInPrefetchSupported[DC__VOLTAGE_STATES + 1][2]; double RequiredDISPCLK[DC__VOLTAGE_STATES + 1][2]; @@ -515,22 +516,22 @@ struct vba_vars_st { unsigned int TotalNumberOfActiveDPP[DC__VOLTAGE_STATES + 1][2]; unsigned int TotalNumberOfDCCActiveDPP[DC__VOLTAGE_STATES + 1][2]; bool ModeSupport[DC__VOLTAGE_STATES + 1][2]; - double ReturnBWPerState[DC__VOLTAGE_STATES + 1]; + double ReturnBWPerState[DC__VOLTAGE_STATES + 1][2]; bool DIOSupport[DC__VOLTAGE_STATES + 1]; bool NotEnoughDSCUnits[DC__VOLTAGE_STATES + 1]; bool DSCCLKRequiredMoreThanSupported[DC__VOLTAGE_STATES + 1]; bool DTBCLKRequiredMoreThanSupported[DC__VOLTAGE_STATES + 1]; double UrgentRoundTripAndOutOfOrderLatencyPerState[DC__VOLTAGE_STATES + 1]; - bool ROBSupport[DC__VOLTAGE_STATES + 1]; + bool ROBSupport[DC__VOLTAGE_STATES + 1][2]; bool PTEBufferSizeNotExceeded[DC__VOLTAGE_STATES + 1][2]; - bool TotalVerticalActiveBandwidthSupport[DC__VOLTAGE_STATES + 1]; - double MaxTotalVerticalActiveAvailableBandwidth[DC__VOLTAGE_STATES + 1]; + bool TotalVerticalActiveBandwidthSupport[DC__VOLTAGE_STATES + 1][2]; + double MaxTotalVerticalActiveAvailableBandwidth[DC__VOLTAGE_STATES + 1][2]; double PrefetchBW[DC__NUM_DPP__MAX]; - double PDEAndMetaPTEBytesPerFrame[DC__NUM_DPP__MAX]; - double MetaRowBytes[DC__NUM_DPP__MAX]; - double DPTEBytesPerRow[DC__NUM_DPP__MAX]; - double PrefetchLinesY[DC__NUM_DPP__MAX]; - double PrefetchLinesC[DC__NUM_DPP__MAX]; + double PDEAndMetaPTEBytesPerFrame[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; + double MetaRowBytes[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; + double DPTEBytesPerRow[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; + double PrefetchLinesY[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; + double PrefetchLinesC[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; unsigned int MaxNumSwY[DC__NUM_DPP__MAX]; unsigned int MaxNumSwC[DC__NUM_DPP__MAX]; double PrefillY[DC__NUM_DPP__MAX]; @@ -539,7 +540,7 @@ struct vba_vars_st { double LinesForMetaPTE[DC__NUM_DPP__MAX]; double LinesForMetaAndDPTERow[DC__NUM_DPP__MAX]; double MinDPPCLKUsingSingleDPP[DC__NUM_DPP__MAX]; - unsigned int SwathWidthYSingleDPP[DC__NUM_DPP__MAX]; + double SwathWidthYSingleDPP[DC__NUM_DPP__MAX]; double BytePerPixelInDETY[DC__NUM_DPP__MAX]; double BytePerPixelInDETC[DC__NUM_DPP__MAX]; bool RequiresDSC[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX]; @@ -547,7 +548,7 @@ struct vba_vars_st { double RequiresFEC[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX]; double OutputBppPerState[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX]; double DSCDelayPerState[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX]; - bool ViewportSizeSupport[DC__VOLTAGE_STATES + 1]; + bool ViewportSizeSupport[DC__VOLTAGE_STATES + 1][2]; unsigned int Read256BlockHeightY[DC__NUM_DPP__MAX]; unsigned int Read256BlockWidthY[DC__NUM_DPP__MAX]; unsigned int Read256BlockHeightC[DC__NUM_DPP__MAX]; @@ -562,7 +563,7 @@ struct vba_vars_st { double WriteBandwidth[DC__NUM_DPP__MAX]; double PSCL_FACTOR[DC__NUM_DPP__MAX]; double PSCL_FACTOR_CHROMA[DC__NUM_DPP__MAX]; - double MaximumVStartup[DC__NUM_DPP__MAX]; + double MaximumVStartup[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; unsigned int MacroTileWidthY[DC__NUM_DPP__MAX]; unsigned int MacroTileWidthC[DC__NUM_DPP__MAX]; double AlignedDCCMetaPitch[DC__NUM_DPP__MAX]; @@ -579,7 +580,7 @@ struct vba_vars_st { bool ImmediateFlipSupportedForState[DC__VOLTAGE_STATES + 1][2]; double WritebackDelay[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX]; unsigned int vm_group_bytes[DC__NUM_DPP__MAX]; - long dpte_group_bytes[DC__NUM_DPP__MAX]; + unsigned int dpte_group_bytes[DC__NUM_DPP__MAX]; unsigned int dpte_row_height[DC__NUM_DPP__MAX]; unsigned int meta_req_height[DC__NUM_DPP__MAX]; unsigned int meta_req_width[DC__NUM_DPP__MAX]; @@ -605,14 +606,14 @@ struct vba_vars_st { double UrgentBurstFactorChroma[DC__NUM_DPP__MAX]; double UrgentBurstFactorChromaPre[DC__NUM_DPP__MAX]; + bool MPCCombine[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; double SwathWidthCSingleDPP[DC__NUM_DPP__MAX]; double MaximumSwathWidthInLineBufferLuma; double MaximumSwathWidthInLineBufferChroma; double MaximumSwathWidthLuma[DC__NUM_DPP__MAX]; double MaximumSwathWidthChroma[DC__NUM_DPP__MAX]; - bool odm_combine_dummy[DC__NUM_DPP__MAX]; - enum odm_combine_mode odm_combine_mode_dummy[DC__NUM_DPP__MAX]; + enum odm_combine_mode odm_combine_dummy[DC__NUM_DPP__MAX]; double dummy1[DC__NUM_DPP__MAX]; double dummy2[DC__NUM_DPP__MAX]; double dummy3[DC__NUM_DPP__MAX]; @@ -622,9 +623,9 @@ struct vba_vars_st { double dummy7[DC__NUM_DPP__MAX]; double dummy8[DC__NUM_DPP__MAX]; unsigned int dummyinteger1ms[DC__NUM_DPP__MAX]; - unsigned int dummyinteger2ms[DC__NUM_DPP__MAX]; + double dummyinteger2ms[DC__NUM_DPP__MAX]; unsigned int dummyinteger3[DC__NUM_DPP__MAX]; - unsigned int dummyinteger4; + unsigned int dummyinteger4[DC__NUM_DPP__MAX]; unsigned int dummyinteger5; unsigned int dummyinteger6; unsigned int dummyinteger7; @@ -637,7 +638,6 @@ struct vba_vars_st { unsigned int dummyintegerarr2[DC__NUM_DPP__MAX]; unsigned int dummyintegerarr3[DC__NUM_DPP__MAX]; unsigned int dummyintegerarr4[DC__NUM_DPP__MAX]; - long dummylongarr1[DC__NUM_DPP__MAX]; bool dummysinglestring; bool SingleDPPViewportSizeSupportPerPlane[DC__NUM_DPP__MAX]; double PlaneRequiredDISPCLKWithODMCombine2To1; @@ -645,20 +645,19 @@ struct vba_vars_st { unsigned int TotalNumberOfSingleDPPPlanes[DC__VOLTAGE_STATES + 1][2]; bool LinkDSCEnable; bool ODMCombine4To1SupportCheckOK[DC__VOLTAGE_STATES + 1]; - bool ODMCombineEnableThisState[DC__NUM_DPP__MAX]; - enum odm_combine_mode ODMCombineEnableTypeThisState[DC__NUM_DPP__MAX]; - unsigned int SwathWidthCThisState[DC__NUM_DPP__MAX]; + enum odm_combine_mode ODMCombineEnableThisState[DC__NUM_DPP__MAX]; + double SwathWidthCThisState[DC__NUM_DPP__MAX]; bool ViewportSizeSupportPerPlane[DC__NUM_DPP__MAX]; double AlignedDCCMetaPitchY[DC__NUM_DPP__MAX]; double AlignedDCCMetaPitchC[DC__NUM_DPP__MAX]; unsigned int NotEnoughUrgentLatencyHiding; unsigned int NotEnoughUrgentLatencyHidingPre; - long PTEBufferSizeInRequestsForLuma; - long PTEBufferSizeInRequestsForChroma; + int PTEBufferSizeInRequestsForLuma; + int PTEBufferSizeInRequestsForChroma; // Missing from VBA - long dpte_group_bytes_chroma; + int dpte_group_bytes_chroma; unsigned int vm_group_bytes_chroma; double dst_x_after_scaler; double dst_y_after_scaler; @@ -683,8 +682,8 @@ struct vba_vars_st { double MinTTUVBlank[DC__NUM_DPP__MAX]; double BytePerPixelDETY[DC__NUM_DPP__MAX]; double BytePerPixelDETC[DC__NUM_DPP__MAX]; - unsigned int SwathWidthY[DC__NUM_DPP__MAX]; - unsigned int SwathWidthSingleDPPY[DC__NUM_DPP__MAX]; + double SwathWidthY[DC__NUM_DPP__MAX]; + double SwathWidthSingleDPPY[DC__NUM_DPP__MAX]; double CursorRequestDeliveryTime[DC__NUM_DPP__MAX]; double CursorRequestDeliveryTimePrefetch[DC__NUM_DPP__MAX]; double ReadBandwidthPlaneLuma[DC__NUM_DPP__MAX]; @@ -760,12 +759,12 @@ struct vba_vars_st { double LinesInDETY[DC__NUM_DPP__MAX]; double LinesInDETYRoundedDownToSwath[DC__NUM_DPP__MAX]; - unsigned int SwathWidthSingleDPPC[DC__NUM_DPP__MAX]; - unsigned int SwathWidthC[DC__NUM_DPP__MAX]; + double SwathWidthSingleDPPC[DC__NUM_DPP__MAX]; + double SwathWidthC[DC__NUM_DPP__MAX]; unsigned int BytePerPixelY[DC__NUM_DPP__MAX]; unsigned int BytePerPixelC[DC__NUM_DPP__MAX]; - long dummyinteger1; - long dummyinteger2; + unsigned int dummyinteger1; + unsigned int dummyinteger2; double FinalDRAMClockChangeLatency; double Tdmdl_vm[DC__NUM_DPP__MAX]; double Tdmdl[DC__NUM_DPP__MAX]; @@ -779,6 +778,7 @@ struct vba_vars_st { unsigned int DCCCMaxCompressedBlock[DC__NUM_DPP__MAX]; unsigned int DCCCIndependent64ByteBlock[DC__NUM_DPP__MAX]; double VStartupMargin; + bool NotEnoughTimeForDynamicMetadata; /* Missing from VBA */ unsigned int MaximumMaxVStartupLines; @@ -814,7 +814,7 @@ struct vba_vars_st { unsigned int ViewportHeightChroma[DC__NUM_DPP__MAX]; double HRatioChroma[DC__NUM_DPP__MAX]; double VRatioChroma[DC__NUM_DPP__MAX]; - long WritebackSourceWidth[DC__NUM_DPP__MAX]; + int WritebackSourceWidth[DC__NUM_DPP__MAX]; bool ModeIsSupported; bool ODMCombine4To1Supported; @@ -850,6 +850,58 @@ struct vba_vars_st { unsigned int MaxNumHDMIFRLOutputs; int AudioSampleRate[DC__NUM_DPP__MAX]; int AudioSampleLayout[DC__NUM_DPP__MAX]; + + int PercentMarginOverMinimumRequiredDCFCLK; + bool DynamicMetadataSupported[DC__VOLTAGE_STATES + 1][2]; + enum immediate_flip_requirement ImmediateFlipRequirement; + double DETBufferSizeYThisState[DC__NUM_DPP__MAX]; + double DETBufferSizeCThisState[DC__NUM_DPP__MAX]; + bool NoUrgentLatencyHiding[DC__NUM_DPP__MAX]; + bool NoUrgentLatencyHidingPre[DC__NUM_DPP__MAX]; + int swath_width_luma_ub_this_state[DC__NUM_DPP__MAX]; + int swath_width_chroma_ub_this_state[DC__NUM_DPP__MAX]; + double UrgLatency[DC__VOLTAGE_STATES + 1]; + double VActiveCursorBandwidth[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; + double VActivePixelBandwidth[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; + bool NoTimeForPrefetch[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; + bool NoTimeForDynamicMetadata[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; + double dpte_row_bandwidth[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; + double meta_row_bandwidth[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; + double DETBufferSizeYAllStates[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; + double DETBufferSizeCAllStates[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; + int swath_width_luma_ub_all_states[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; + int swath_width_chroma_ub_all_states[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; + bool NotUrgentLatencyHiding[DC__VOLTAGE_STATES + 1][2]; + unsigned int SwathHeightYAllStates[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; + unsigned int SwathHeightCAllStates[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; + unsigned int SwathWidthYAllStates[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; + unsigned int SwathWidthCAllStates[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX]; + double TotalDPTERowBandwidth[DC__VOLTAGE_STATES + 1][2]; + double TotalMetaRowBandwidth[DC__VOLTAGE_STATES + 1][2]; + double TotalVActiveCursorBandwidth[DC__VOLTAGE_STATES + 1][2]; + double TotalVActivePixelBandwidth[DC__VOLTAGE_STATES + 1][2]; + bool UseMinimumRequiredDCFCLK; + double WritebackDelayTime[DC__NUM_DPP__MAX]; + unsigned int DCCYIndependentBlock[DC__NUM_DPP__MAX]; + unsigned int DCCCIndependentBlock[DC__NUM_DPP__MAX]; + unsigned int dummyinteger15; + unsigned int dummyinteger16; + unsigned int dummyinteger17; + unsigned int dummyinteger18; + unsigned int dummyinteger19; + unsigned int dummyinteger20; + unsigned int dummyinteger21; + unsigned int dummyinteger22; + unsigned int dummyinteger23; + unsigned int dummyinteger24; + unsigned int dummyinteger25; + unsigned int dummyinteger26; + unsigned int dummyinteger27; + unsigned int dummyinteger28; + unsigned int dummyinteger29; + bool dummystring[DC__NUM_DPP__MAX]; + double BPP; + enum odm_combine_policy ODMCombinePolicy; }; bool CalculateMinAndMaxPrefetchMode( diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml_common_defs.c b/drivers/gpu/drm/amd/display/dc/dml/dml_common_defs.c index b953b02a1512..723af0b2dda0 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dml_common_defs.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dml_common_defs.c @@ -24,7 +24,7 @@ */ #include "dml_common_defs.h" -#include "../calcs/dcn_calc_math.h" +#include "dcn_calc_math.h" #include "dml_inline_defs.h" diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h b/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h index eca140da13d8..ded71ea82413 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h @@ -27,7 +27,7 @@ #define __DML_INLINE_DEFS_H__ #include "dml_common_defs.h" -#include "../calcs/dcn_calc_math.h" +#include "dcn_calc_math.h" #include "dml_logger.h" static inline double dml_min(double a, double b) diff --git a/drivers/gpu/drm/amd/display/dc/dsc/Makefile b/drivers/gpu/drm/amd/display/dc/dsc/Makefile index 641ffb7cfaed..3f66868df171 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dsc/Makefile @@ -2,7 +2,13 @@ # # Makefile for the 'dsc' sub-component of DAL. +ifdef CONFIG_X86 dsc_ccflags := -mhard-float -msse +endif + +ifdef CONFIG_PPC64 +dsc_ccflags := -mhard-float -maltivec +endif ifdef CONFIG_CC_IS_GCC ifeq ($(call cc-ifversion, -lt, 0701, y), y) @@ -10,6 +16,7 @@ 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 @@ -18,6 +25,7 @@ dsc_ccflags += -mpreferred-stack-boundary=4 else dsc_ccflags += -msse2 endif +endif CFLAGS_$(AMDDALPATH)/dc/dsc/rc_calc.o := $(dsc_ccflags) CFLAGS_$(AMDDALPATH)/dc/dsc/rc_calc_dpi.o := $(dsc_ccflags) diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c index d2423ad1fac2..87d682d25278 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c +++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c @@ -29,6 +29,9 @@ /* This module's internal functions */ +/* default DSC policy target bitrate limit is 16bpp */ +static uint32_t dsc_policy_max_target_bpp_limit = 16; + static uint32_t dc_dsc_bandwidth_in_kbps_from_timing( const struct dc_crtc_timing *timing) { @@ -221,7 +224,8 @@ static void get_dsc_enc_caps( memset(dsc_enc_caps, 0, sizeof(struct dsc_enc_caps)); if (dsc) { - dsc->funcs->dsc_get_enc_caps(dsc_enc_caps, pixel_clock_100Hz); + if (!dsc->ctx->dc->debug.disable_dsc) + dsc->funcs->dsc_get_enc_caps(dsc_enc_caps, pixel_clock_100Hz); if (dsc->ctx->dc->debug.native422_support) dsc_enc_caps->color_formats.bits.YCBCR_NATIVE_422 = 1; } @@ -757,7 +761,7 @@ done: return is_dsc_possible; } -bool dc_dsc_parse_dsc_dpcd(const uint8_t *dpcd_dsc_basic_data, const uint8_t *dpcd_dsc_ext_data, struct dsc_dec_dpcd_caps *dsc_sink_caps) +bool dc_dsc_parse_dsc_dpcd(const struct dc *dc, const uint8_t *dpcd_dsc_basic_data, const uint8_t *dpcd_dsc_ext_data, struct dsc_dec_dpcd_caps *dsc_sink_caps) { if (!dpcd_dsc_basic_data) return false; @@ -810,6 +814,23 @@ bool dc_dsc_parse_dsc_dpcd(const uint8_t *dpcd_dsc_basic_data, const uint8_t *dp if (!dsc_bpp_increment_div_from_dpcd(dpcd_dsc_basic_data[DP_DSC_BITS_PER_PIXEL_INC - DP_DSC_SUPPORT], &dsc_sink_caps->bpp_increment_div)) return false; + if (dc->debug.dsc_bpp_increment_div) { + /* dsc_bpp_increment_div should onl be 1, 2, 4, 8 or 16, but rather than rejecting invalid values, + * we'll accept all and get it into range. This also makes the above check against 0 redundant, + * but that one stresses out the override will be only used if it's not 0. + */ + if (dc->debug.dsc_bpp_increment_div >= 1) + dsc_sink_caps->bpp_increment_div = 1; + if (dc->debug.dsc_bpp_increment_div >= 2) + dsc_sink_caps->bpp_increment_div = 2; + if (dc->debug.dsc_bpp_increment_div >= 4) + dsc_sink_caps->bpp_increment_div = 4; + if (dc->debug.dsc_bpp_increment_div >= 8) + dsc_sink_caps->bpp_increment_div = 8; + if (dc->debug.dsc_bpp_increment_div >= 16) + dsc_sink_caps->bpp_increment_div = 16; + } + /* Extended caps */ if (dpcd_dsc_ext_data == NULL) { // Extended DPCD DSC data can be null, e.g. because it doesn't apply to SST dsc_sink_caps->branch_overall_throughput_0_mps = 0; @@ -951,7 +972,12 @@ void dc_dsc_get_policy_for_timing(const struct dc_crtc_timing *timing, struct dc default: return; } - /* internal upper limit to 16 bpp */ - if (policy->max_target_bpp > 16) - policy->max_target_bpp = 16; + /* internal upper limit, default 16 bpp */ + if (policy->max_target_bpp > dsc_policy_max_target_bpp_limit) + policy->max_target_bpp = dsc_policy_max_target_bpp_limit; +} + +void dc_dsc_policy_set_max_target_bpp_limit(uint32_t limit) +{ + dsc_policy_max_target_bpp_limit = limit; } diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h index 16f6ef22367b..f285b76888fb 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h +++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h @@ -212,6 +212,7 @@ struct resource_pool { struct abm *abm; struct dmcu *dmcu; + struct dmub_psr *psr; const struct resource_funcs *funcs; const struct resource_caps *res_cap; diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h index 6198bccd6199..8b1f0ce6c2a7 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h @@ -76,6 +76,8 @@ void dp_enable_mst_on_sink(struct dc_link *link, bool enable); enum dp_panel_mode dp_get_panel_mode(struct dc_link *link); void dp_set_panel_mode(struct dc_link *link, enum dp_panel_mode panel_mode); +bool dp_overwrite_extended_receiver_cap(struct dc_link *link); + void dp_set_fec_ready(struct dc_link *link, bool ready); void dp_set_fec_enable(struct dc_link *link, bool enable); bool dp_set_dsc_enable(struct pipe_ctx *pipe_ctx, bool enable); diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calc_math.h b/drivers/gpu/drm/amd/display/dc/inc/dcn_calc_math.h index 45a07eeffbb6..45a07eeffbb6 100644 --- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calc_math.h +++ b/drivers/gpu/drm/amd/display/dc/inc/dcn_calc_math.h diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h index 125e42dbd3c5..45ef390ae052 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h @@ -47,6 +47,26 @@ struct dpp_input_csc_matrix { uint16_t regval[12]; }; +static const struct dpp_input_csc_matrix dpp_input_csc_matrix[] = { + {COLOR_SPACE_SRGB, + {0x2000, 0, 0, 0, 0, 0x2000, 0, 0, 0, 0, 0x2000, 0} }, + {COLOR_SPACE_SRGB_LIMITED, + {0x2000, 0, 0, 0, 0, 0x2000, 0, 0, 0, 0, 0x2000, 0} }, + {COLOR_SPACE_YCBCR601, + {0x2cdd, 0x2000, 0, 0xe991, 0xe926, 0x2000, 0xf4fd, 0x10ef, + 0, 0x2000, 0x38b4, 0xe3a6} }, + {COLOR_SPACE_YCBCR601_LIMITED, + {0x3353, 0x2568, 0, 0xe400, 0xe5dc, 0x2568, 0xf367, 0x1108, + 0, 0x2568, 0x40de, 0xdd3a} }, + {COLOR_SPACE_YCBCR709, + {0x3265, 0x2000, 0, 0xe6ce, 0xf105, 0x2000, 0xfa01, 0xa7d, 0, + 0x2000, 0x3b61, 0xe24f} }, + + {COLOR_SPACE_YCBCR709_LIMITED, + {0x39a6, 0x2568, 0, 0xe0d6, 0xeedd, 0x2568, 0xf925, 0x9a8, 0, + 0x2568, 0x43ee, 0xdbb2} } +}; + struct dpp_grph_csc_adjustment { struct fixed31_32 temperature_matrix[CSC_TEMPERATURE_MATRIX_SIZE]; enum graphics_gamut_adjust_type gamut_adjust_type; diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dwb.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dwb.h index 735f41901b88..459f95f52486 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/dwb.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dwb.h @@ -113,7 +113,8 @@ struct dwbc { int wb_src_plane_inst;/*hubp, mpcc, inst*/ bool update_privacymask; uint32_t mask_id; - + int otg_inst; + bool mvc_cfg; }; struct dwbc_funcs { 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 85a34dde8526..2cb8466e657b 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h @@ -63,6 +63,26 @@ struct hubp { bool power_gated; }; +struct surface_flip_registers { + uint32_t DCSURF_SURFACE_CONTROL; + uint32_t DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH; + uint32_t DCSURF_PRIMARY_META_SURFACE_ADDRESS; + uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH; + uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS; + uint32_t DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH_C; + uint32_t DCSURF_PRIMARY_META_SURFACE_ADDRESS_C; + uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C; + uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_C; + uint32_t DCSURF_SECONDARY_META_SURFACE_ADDRESS_HIGH; + uint32_t DCSURF_SECONDARY_META_SURFACE_ADDRESS; + uint32_t DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH; + uint32_t DCSURF_SECONDARY_SURFACE_ADDRESS; + bool tmz_surface; + bool immediate; + uint8_t vmid; + bool grph_stereo; +}; + struct hubp_funcs { void (*hubp_setup)( struct hubp *hubp, @@ -82,9 +102,10 @@ struct hubp_funcs { void (*mem_program_viewport)( struct hubp *hubp, const struct rect *viewport, - const struct rect *viewport_c, - enum dc_rotation_angle rotation); - /* rotation needed for Renoir workaround */ + const struct rect *viewport_c); + + void (*apply_PLAT_54186_wa)(struct hubp *hubp, + const struct dc_plane_address *address); bool (*hubp_program_surface_flip_and_addr)( struct hubp *hubp, diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h index 2d3efd71fa51..e5e7d94026fc 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h @@ -208,7 +208,8 @@ struct timing_generator_funcs { bool enable, const struct dc_crtc_timing *timing); void (*set_drr)(struct timing_generator *tg, const struct drr_params *params); void (*set_static_screen_control)(struct timing_generator *tg, - uint32_t value); + uint32_t event_triggers, + uint32_t num_frames); void (*set_test_pattern)( struct timing_generator *tg, enum controller_dp_test_pattern test_pattern, diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h index e9c6021a5372..209118f9f193 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h @@ -42,7 +42,7 @@ struct dc_state; struct dc_stream_status; struct dc_writeback_info; struct dchub_init_data; -struct dc_static_screen_events; +struct dc_static_screen_params; struct resource_pool; struct dc_phy_addr_space_config; struct dc_virtual_addr_space_config; @@ -102,7 +102,7 @@ struct hw_sequencer_funcs { unsigned int vmid, unsigned int vmid_frame_number); void (*set_static_screen_control)(struct pipe_ctx **pipe_ctx, int num_pipes, - const struct dc_static_screen_events *events); + const struct dc_static_screen_params *events); /* Stream Related */ void (*enable_stream)(struct pipe_ctx *pipe_ctx); @@ -149,16 +149,18 @@ struct hw_sequencer_funcs { /* Writeback Related */ void (*update_writeback)(struct dc *dc, - const struct dc_stream_status *stream_status, struct dc_writeback_info *wb_info, struct dc_state *context); void (*enable_writeback)(struct dc *dc, - const struct dc_stream_status *stream_status, struct dc_writeback_info *wb_info, struct dc_state *context); void (*disable_writeback)(struct dc *dc, unsigned int dwb_pipe_inst); + bool (*mmhubbub_warmup)(struct dc *dc, + unsigned int num_dwb, + struct dc_writeback_info *wb_info); + /* Clock Related */ enum dc_status (*set_clock)(struct dc *dc, enum dc_clock_type clock_type, diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h index 8ba06f015975..ecf566378ccd 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h @@ -51,7 +51,7 @@ struct dc_state; struct dc_stream_status; struct dc_writeback_info; struct dchub_init_data; -struct dc_static_screen_events; +struct dc_static_screen_params; struct resource_pool; struct resource_context; struct stream_resource; diff --git a/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h b/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h index 47e307388581..2470405e996b 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h +++ b/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h @@ -458,7 +458,14 @@ uint32_t generic_reg_get8(const struct dc_context *ctx, uint32_t addr, #define IX_REG_READ(index_reg_name, data_reg_name, index) \ generic_read_indirect_reg(CTX, REG(index_reg_name), REG(data_reg_name), IND_REG(index)) +#define IX_REG_GET_N(index_reg_name, data_reg_name, index, n, ...) \ + generic_indirect_reg_get(CTX, REG(index_reg_name), REG(data_reg_name), \ + IND_REG(index), \ + n, __VA_ARGS__) +#define IX_REG_GET(index_reg_name, data_reg_name, index, field, val) \ + IX_REG_GET_N(index_reg_name, data_reg_name, index, 1, \ + FN(data_reg_name, field), val) #define IX_REG_UPDATE_N(index_reg_name, data_reg_name, index, n, ...) \ generic_indirect_reg_update_ex(CTX, \ @@ -479,6 +486,12 @@ uint32_t generic_read_indirect_reg(const struct dc_context *ctx, uint32_t addr_index, uint32_t addr_data, uint32_t index); +uint32_t generic_indirect_reg_get(const struct dc_context *ctx, + uint32_t addr_index, uint32_t addr_data, + uint32_t index, int n, + uint8_t shift1, uint32_t mask1, uint32_t *field_value1, + ...); + uint32_t generic_indirect_reg_update_ex(const struct dc_context *ctx, uint32_t addr_index, uint32_t addr_data, uint32_t index, uint32_t reg_val, int n, diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h index 7a85abc53d05..5ae8ada154ef 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/resource.h +++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h @@ -177,4 +177,6 @@ void update_audio_usage( unsigned int resource_pixel_format_to_bpp(enum surface_pixel_format format); +void get_audio_check(struct audio_info *aud_modes, + struct audio_check *aud_chk); #endif /* DRIVERS_GPU_DRM_AMD_DC_DEV_DC_INC_RESOURCE_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h index 13b9a9bb32c8..c34eba19860a 100644 --- a/drivers/gpu/drm/amd/display/dc/os_types.h +++ b/drivers/gpu/drm/amd/display/dc/os_types.h @@ -1,5 +1,6 @@ /* * Copyright 2012-16 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"), @@ -50,7 +51,38 @@ #define dm_error(fmt, ...) DRM_ERROR(fmt, ##__VA_ARGS__) #if defined(CONFIG_DRM_AMD_DC_DCN) +#if defined(CONFIG_X86) #include <asm/fpu/api.h> +#define DC_FP_START() kernel_fpu_begin() +#define DC_FP_END() kernel_fpu_end() +#elif defined(CONFIG_PPC64) +#include <asm/switch_to.h> +#include <asm/cputable.h> +#define DC_FP_START() { \ + if (cpu_has_feature(CPU_FTR_VSX_COMP)) { \ + preempt_disable(); \ + enable_kernel_vsx(); \ + } else if (cpu_has_feature(CPU_FTR_ALTIVEC_COMP)) { \ + preempt_disable(); \ + enable_kernel_altivec(); \ + } else if (!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE)) { \ + preempt_disable(); \ + enable_kernel_fp(); \ + } \ +} +#define DC_FP_END() { \ + if (cpu_has_feature(CPU_FTR_VSX_COMP)) { \ + disable_kernel_vsx(); \ + preempt_enable(); \ + } else if (cpu_has_feature(CPU_FTR_ALTIVEC_COMP)) { \ + disable_kernel_altivec(); \ + preempt_enable(); \ + } else if (!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE)) { \ + disable_kernel_fp(); \ + preempt_enable(); \ + } \ +} +#endif #endif /* diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h index b10728f33f62..cd9532b4f14d 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -36,6 +36,7 @@ #define DMUB_RB_SIZE (DMUB_RB_CMD_SIZE * DMUB_RB_MAX_ENTRY) #define REG_SET_MASK 0xFFFF + /* * Command IDs should be treated as stable ABI. * Do not reuse or modify IDs. @@ -47,6 +48,7 @@ enum dmub_cmd_type { DMUB_CMD__REG_SEQ_FIELD_UPDATE_SEQ = 2, DMUB_CMD__REG_SEQ_BURST_WRITE = 3, DMUB_CMD__REG_REG_WAIT = 4, + DMUB_CMD__PLAT_54186_WA = 5, DMUB_CMD__PSR = 64, DMUB_CMD__VBIOS = 128, }; @@ -145,6 +147,32 @@ struct dmub_rb_cmd_reg_wait { struct dmub_cmd_reg_wait_data reg_wait; }; +#ifndef PHYSICAL_ADDRESS_LOC +#define PHYSICAL_ADDRESS_LOC union large_integer +#endif + +struct dmub_cmd_PLAT_54186_wa { + uint32_t DCSURF_SURFACE_CONTROL; + uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH; + uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS; + uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C; + uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_C; + struct { + uint8_t hubp_inst : 4; + uint8_t tmz_surface : 1; + uint8_t immediate :1; + uint8_t vmid : 4; + uint8_t grph_stereo : 1; + uint32_t reserved : 21; + } flip_params; + uint32_t reserved[9]; +}; + +struct dmub_rb_cmd_PLAT_54186_wa { + struct dmub_cmd_header header; + struct dmub_cmd_PLAT_54186_wa flip; +}; + struct dmub_cmd_digx_encoder_control_data { union dig_encoder_control_parameters_v1_5 dig; }; @@ -187,9 +215,28 @@ struct dmub_rb_cmd_dpphy_init { }; struct dmub_cmd_psr_copy_settings_data { - uint32_t reg1; - uint32_t reg2; - uint32_t reg3; + uint16_t psr_level; + uint8_t hubp_inst; + uint8_t dpp_inst; + uint8_t mpcc_inst; + uint8_t opp_inst; + uint8_t otg_inst; + uint8_t digfe_inst; + uint8_t digbe_inst; + uint8_t dpphy_inst; + uint8_t aux_inst; + uint8_t hyst_frames; + uint8_t hyst_lines; + uint8_t phy_num; + uint8_t phy_type; + uint8_t aux_repeat; + uint8_t smu_optimizations_en; + uint8_t skip_wait_for_pll_lock; + uint8_t frame_delay; + uint8_t smu_phy_id; + uint8_t num_of_controllers; + uint8_t link_rate; + uint8_t frame_cap_ind; }; struct dmub_rb_cmd_psr_copy_settings { @@ -206,31 +253,17 @@ struct dmub_rb_cmd_psr_set_level { struct dmub_cmd_psr_set_level_data psr_set_level_data; }; -struct dmub_rb_cmd_psr_disable { - struct dmub_cmd_header header; -}; - struct dmub_rb_cmd_psr_enable { struct dmub_cmd_header header; }; -struct dmub_cmd_psr_notify_vblank_data { - uint32_t vblank_int; // Which vblank interrupt was triggered -}; - -struct dmub_rb_cmd_notify_vblank { - struct dmub_cmd_header header; - struct dmub_cmd_psr_notify_vblank_data psr_notify_vblank_data; -}; - -struct dmub_cmd_psr_notify_static_state_data { - uint32_t ss_int; // Which static screen interrupt was triggered - uint32_t ss_enter; // Enter (1) or exit (0) static screen +struct dmub_cmd_psr_setup_data { + enum psr_version version; // PSR version 1 or 2 }; -struct dmub_rb_cmd_psr_notify_static_state { +struct dmub_rb_cmd_psr_setup { struct dmub_cmd_header header; - struct dmub_cmd_psr_notify_static_state_data psr_notify_static_state_data; + struct dmub_cmd_psr_setup_data psr_setup_data; }; union dmub_rb_cmd { @@ -245,9 +278,10 @@ union dmub_rb_cmd { struct dmub_rb_cmd_dpphy_init dpphy_init; struct dmub_rb_cmd_dig1_transmitter_control dig1_transmitter_control; struct dmub_rb_cmd_psr_enable psr_enable; - struct dmub_rb_cmd_psr_disable psr_disable; struct dmub_rb_cmd_psr_copy_settings psr_copy_settings; struct dmub_rb_cmd_psr_set_level psr_set_level; + struct dmub_rb_cmd_PLAT_54186_wa PLAT_54186_wa; + struct dmub_rb_cmd_psr_setup psr_setup; }; #pragma pack(pop) diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd_dal.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd_dal.h index 14f13e8a6f3b..7b69eb37f762 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd_dal.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd_dal.h @@ -32,10 +32,17 @@ */ enum dmub_cmd_psr_type { - DMUB_CMD__PSR_ENABLE = 0, - DMUB_CMD__PSR_DISABLE = 1, - DMUB_CMD__PSR_COPY_SETTINGS = 2, - DMUB_CMD__PSR_SET_LEVEL = 3, + DMUB_CMD__PSR_SETUP = 0, + DMUB_CMD__PSR_COPY_SETTINGS = 1, + DMUB_CMD__PSR_ENABLE = 2, + DMUB_CMD__PSR_DISABLE = 3, + DMUB_CMD__PSR_SET_LEVEL = 4, +}; + +enum psr_version { + PSR_VERSION_1 = 0x10, // PSR Version 1 + PSR_VERSION_2 = 0x20, // PSR Version 2, includes selective update + PSR_VERSION_2_Y_COORD = 0x21, // PSR Version 2, includes Y-coordinate support for SU }; #endif /* _DMUB_CMD_DAL_H_ */ diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_fw_meta.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_fw_meta.h new file mode 100644 index 000000000000..242ec257998c --- /dev/null +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_fw_meta.h @@ -0,0 +1,63 @@ +/* + * Copyright 2019 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 _DMUB_META_H_ +#define _DMUB_META_H_ + +#include "dmub_types.h" + +#pragma pack(push, 1) + +/* Magic value for identifying dmub_fw_meta_info */ +#define DMUB_FW_META_MAGIC 0x444D5542 + +/* Offset from the end of the file to the dmub_fw_meta_info */ +#define DMUB_FW_META_OFFSET 0x24 + +/** + * struct dmub_fw_meta_info - metadata associated with fw binary + * + * NOTE: This should be considered a stable API. Fields should + * not be repurposed or reordered. New fields should be + * added instead to extend the structure. + * + * @magic_value: magic value identifying DMUB firmware meta info + * @fw_region_size: size of the firmware state region + * @trace_buffer_size: size of the tracebuffer region + */ +struct dmub_fw_meta_info { + uint32_t magic_value; + uint32_t fw_region_size; + uint32_t trace_buffer_size; +}; + +/* Ensure that the structure remains 64 bytes. */ +union dmub_fw_meta { + struct dmub_fw_meta_info info; + uint8_t reserved[64]; +}; + +#pragma pack(pop) + +#endif /* _DMUB_META_H_ */ diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_rb.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_rb.h index ac22744eaa94..df875fdd2ab0 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_rb.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_rb.h @@ -73,12 +73,17 @@ static inline bool dmub_rb_full(struct dmub_rb *rb) static inline bool dmub_rb_push_front(struct dmub_rb *rb, const struct dmub_cmd_header *cmd) { - uint8_t *wt_ptr = (uint8_t *)(rb->base_address) + rb->wrpt; + uint64_t volatile *dst = (uint64_t volatile *)(rb->base_address) + rb->wrpt / sizeof(uint64_t); + const uint64_t *src = (const uint64_t *)cmd; + int i; if (dmub_rb_full(rb)) return false; - dmub_memcpy(wt_ptr, cmd, DMUB_RB_CMD_SIZE); + // copying data + for (i = 0; i < DMUB_RB_CMD_SIZE / sizeof(uint64_t); i++) + *dst++ = *src++; + rb->wrpt += DMUB_RB_CMD_SIZE; if (rb->wrpt >= rb->capacity) @@ -113,6 +118,26 @@ static inline bool dmub_rb_pop_front(struct dmub_rb *rb) return true; } +static inline void dmub_rb_flush_pending(const struct dmub_rb *rb) +{ + uint32_t rptr = rb->rptr; + uint32_t wptr = rb->wrpt; + + while (rptr != wptr) { + uint64_t volatile *data = (uint64_t volatile *)rb->base_address + rptr / sizeof(uint64_t); + //uint64_t volatile *p = (uint64_t volatile *)data; + uint64_t temp; + int i; + + for (i = 0; i < DMUB_RB_CMD_SIZE / sizeof(uint64_t); i++) + temp = *data++; + + rptr += DMUB_RB_CMD_SIZE; + if (rptr >= rb->capacity) + rptr %= rb->capacity; + } +} + static inline void dmub_rb_init(struct dmub_rb *rb, struct dmub_rb_init_params *init_params) { diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_srv.h index 528243e35add..f8917594036a 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_srv.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_srv.h @@ -67,7 +67,6 @@ #include "dmub_types.h" #include "dmub_cmd.h" #include "dmub_rb.h" -#include "dmub_fw_state.h" #if defined(__cplusplus) extern "C" { @@ -76,7 +75,7 @@ extern "C" { /* Forward declarations */ struct dmub_srv; struct dmub_cmd_header; -struct dmcu; +struct dmub_srv_common_regs; /* enum dmub_status - return code for dmcub functions */ enum dmub_status { @@ -145,11 +144,13 @@ struct dmub_fb { * @inst_const_size: size of the fw inst const section * @bss_data_size: size of the fw bss data section * @vbios_size: size of the vbios data + * @fw_bss_data: raw firmware bss data section */ struct dmub_srv_region_params { uint32_t inst_const_size; uint32_t bss_data_size; uint32_t vbios_size; + const uint8_t *fw_bss_data; }; /** @@ -230,6 +231,8 @@ struct dmub_srv_base_funcs { struct dmub_srv_hw_funcs { /* private: internal use only */ + void (*init)(struct dmub_srv *dmub); + void (*reset)(struct dmub_srv *dmub); void (*reset_release)(struct dmub_srv *dmub); @@ -307,6 +310,8 @@ struct dmub_srv { volatile const struct dmub_fw_state *fw_state; /* private: internal use only */ + const struct dmub_srv_common_regs *regs; + struct dmub_srv_base_funcs funcs; struct dmub_srv_hw_funcs hw_funcs; struct dmub_rb inbox1_rb; @@ -414,6 +419,21 @@ enum dmub_status dmub_srv_hw_init(struct dmub_srv *dmub, const struct dmub_srv_hw_params *params); /** + * dmub_srv_hw_reset() - puts the DMUB hardware in reset state if initialized + * @dmub: the dmub service + * + * Before destroying the DMUB service or releasing the backing framebuffer + * memory we'll need to put the DMCUB into reset first. + * + * A subsequent call to dmub_srv_hw_init() will re-enable the DMCUB. + * + * Return: + * DMUB_STATUS_OK - success + * DMUB_STATUS_INVALID - unspecified error + */ +enum dmub_status dmub_srv_hw_reset(struct dmub_srv *dmub); + +/** * dmub_srv_cmd_queue() - queues a command to the DMUB * @dmub: the dmub service * @cmd: the command to queue @@ -442,25 +462,6 @@ enum dmub_status dmub_srv_cmd_queue(struct dmub_srv *dmub, enum dmub_status dmub_srv_cmd_execute(struct dmub_srv *dmub); /** - * dmub_srv_cmd_submit() - submits a command to the DMUB immediately - * @dmub: the dmub service - * @cmd: the command to submit - * @timeout_us: the maximum number of microseconds to wait - * - * Submits a command to the DMUB with an optional timeout. - * If timeout_us is given then the service will attempt to - * resubmit for the given number of microseconds. - * - * Return: - * DMUB_STATUS_OK - success - * DMUB_STATUS_TIMEOUT - wait for submit timed out - * DMUB_STATUS_INVALID - unspecified error - */ -enum dmub_status dmub_srv_cmd_submit(struct dmub_srv *dmub, - const struct dmub_cmd_header *cmd, - uint32_t timeout_us); - -/** * dmub_srv_wait_for_auto_load() - Waits for firmware auto load to complete * @dmub: the dmub service * @timeout_us: the maximum number of microseconds to wait diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.c index 951ea7053c7e..b2ca8e0dbac9 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.c @@ -25,6 +25,7 @@ #include "../inc/dmub_srv.h" #include "dmub_reg.h" +#include "dmub_dcn20.h" #include "dcn/dcn_2_0_0_offset.h" #include "dcn/dcn_2_0_0_sh_mask.h" @@ -33,36 +34,90 @@ #define BASE_INNER(seg) DCN_BASE__INST0_SEG##seg #define CTX dmub +#define REGS dmub->regs + +/* Registers. */ + +const struct dmub_srv_common_regs dmub_srv_dcn20_regs = { +#define DMUB_SR(reg) REG_OFFSET(reg), + { DMUB_COMMON_REGS() }, +#undef DMUB_SR + +#define DMUB_SF(reg, field) FD_MASK(reg, field), + { DMUB_COMMON_FIELDS() }, +#undef DMUB_SF + +#define DMUB_SF(reg, field) FD_SHIFT(reg, field), + { DMUB_COMMON_FIELDS() }, +#undef DMUB_SF +}; + +/* Shared functions. */ + +static void dmub_dcn20_get_fb_base_offset(struct dmub_srv *dmub, + uint64_t *fb_base, + uint64_t *fb_offset) +{ + uint32_t tmp; + + REG_GET(DCN_VM_FB_LOCATION_BASE, FB_BASE, &tmp); + *fb_base = (uint64_t)tmp << 24; + + REG_GET(DCN_VM_FB_OFFSET, FB_OFFSET, &tmp); + *fb_offset = (uint64_t)tmp << 24; +} + +static inline void dmub_dcn20_translate_addr(const union dmub_addr *addr_in, + uint64_t fb_base, + uint64_t fb_offset, + union dmub_addr *addr_out) +{ + addr_out->quad_part = addr_in->quad_part - fb_base + fb_offset; +} void dmub_dcn20_reset(struct dmub_srv *dmub) { REG_UPDATE(DMCUB_CNTL, DMCUB_SOFT_RESET, 1); REG_UPDATE(DMCUB_CNTL, DMCUB_ENABLE, 0); + REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 1); + REG_WRITE(DMCUB_INBOX1_RPTR, 0); + REG_WRITE(DMCUB_INBOX1_WPTR, 0); } void dmub_dcn20_reset_release(struct dmub_srv *dmub) { + REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 0); REG_WRITE(DMCUB_SCRATCH15, dmub->psp_version & 0x001100FF); REG_UPDATE_2(DMCUB_CNTL, DMCUB_ENABLE, 1, DMCUB_TRACEPORT_EN, 1); REG_UPDATE(DMCUB_CNTL, DMCUB_SOFT_RESET, 0); } -void dmub_dcn20_backdoor_load(struct dmub_srv *dmub, struct dmub_window *cw0, - struct dmub_window *cw1) +void dmub_dcn20_backdoor_load(struct dmub_srv *dmub, + const struct dmub_window *cw0, + const struct dmub_window *cw1) { + union dmub_addr offset; + uint64_t fb_base, fb_offset; + + dmub_dcn20_get_fb_base_offset(dmub, &fb_base, &fb_offset); + REG_UPDATE(DMCUB_SEC_CNTL, DMCUB_SEC_RESET, 1); - REG_UPDATE_2(DMCUB_MEM_CNTL, DMCUB_MEM_READ_SPACE, 0x4, - DMCUB_MEM_WRITE_SPACE, 0x4); + REG_UPDATE_2(DMCUB_MEM_CNTL, DMCUB_MEM_READ_SPACE, 0x3, + DMCUB_MEM_WRITE_SPACE, 0x3); + + dmub_dcn20_translate_addr(&cw0->offset, fb_base, fb_offset, &offset); - REG_WRITE(DMCUB_REGION3_CW0_OFFSET, cw0->offset.u.low_part); - REG_WRITE(DMCUB_REGION3_CW0_OFFSET_HIGH, cw0->offset.u.high_part); + REG_WRITE(DMCUB_REGION3_CW0_OFFSET, offset.u.low_part); + REG_WRITE(DMCUB_REGION3_CW0_OFFSET_HIGH, offset.u.high_part); REG_WRITE(DMCUB_REGION3_CW0_BASE_ADDRESS, cw0->region.base); REG_SET_2(DMCUB_REGION3_CW0_TOP_ADDRESS, 0, DMCUB_REGION3_CW0_TOP_ADDRESS, cw0->region.top, DMCUB_REGION3_CW0_ENABLE, 1); - REG_WRITE(DMCUB_REGION3_CW1_OFFSET, cw1->offset.u.low_part); - REG_WRITE(DMCUB_REGION3_CW1_OFFSET_HIGH, cw1->offset.u.high_part); + dmub_dcn20_translate_addr(&cw1->offset, fb_base, fb_offset, &offset); + + REG_WRITE(DMCUB_REGION3_CW1_OFFSET, offset.u.low_part); + REG_WRITE(DMCUB_REGION3_CW1_OFFSET_HIGH, offset.u.high_part); REG_WRITE(DMCUB_REGION3_CW1_BASE_ADDRESS, cw1->region.base); REG_SET_2(DMCUB_REGION3_CW1_TOP_ADDRESS, 0, DMCUB_REGION3_CW1_TOP_ADDRESS, cw1->region.top, @@ -79,37 +134,51 @@ void dmub_dcn20_setup_windows(struct dmub_srv *dmub, const struct dmub_window *cw5, const struct dmub_window *cw6) { - REG_WRITE(DMCUB_REGION3_CW2_OFFSET, cw2->offset.u.low_part); - REG_WRITE(DMCUB_REGION3_CW2_OFFSET_HIGH, cw2->offset.u.high_part); + union dmub_addr offset; + uint64_t fb_base, fb_offset; + + dmub_dcn20_get_fb_base_offset(dmub, &fb_base, &fb_offset); + + dmub_dcn20_translate_addr(&cw2->offset, fb_base, fb_offset, &offset); + + REG_WRITE(DMCUB_REGION3_CW2_OFFSET, offset.u.low_part); + REG_WRITE(DMCUB_REGION3_CW2_OFFSET_HIGH, offset.u.high_part); REG_WRITE(DMCUB_REGION3_CW2_BASE_ADDRESS, cw2->region.base); REG_SET_2(DMCUB_REGION3_CW2_TOP_ADDRESS, 0, DMCUB_REGION3_CW2_TOP_ADDRESS, cw2->region.top, DMCUB_REGION3_CW2_ENABLE, 1); - REG_WRITE(DMCUB_REGION3_CW3_OFFSET, cw3->offset.u.low_part); - REG_WRITE(DMCUB_REGION3_CW3_OFFSET_HIGH, cw3->offset.u.high_part); + dmub_dcn20_translate_addr(&cw3->offset, fb_base, fb_offset, &offset); + + REG_WRITE(DMCUB_REGION3_CW3_OFFSET, offset.u.low_part); + REG_WRITE(DMCUB_REGION3_CW3_OFFSET_HIGH, offset.u.high_part); REG_WRITE(DMCUB_REGION3_CW3_BASE_ADDRESS, cw3->region.base); REG_SET_2(DMCUB_REGION3_CW3_TOP_ADDRESS, 0, DMCUB_REGION3_CW3_TOP_ADDRESS, cw3->region.top, DMCUB_REGION3_CW3_ENABLE, 1); /* TODO: Move this to CW4. */ + dmub_dcn20_translate_addr(&cw4->offset, fb_base, fb_offset, &offset); - REG_WRITE(DMCUB_REGION4_OFFSET, cw4->offset.u.low_part); - REG_WRITE(DMCUB_REGION4_OFFSET_HIGH, cw4->offset.u.high_part); + REG_WRITE(DMCUB_REGION4_OFFSET, offset.u.low_part); + REG_WRITE(DMCUB_REGION4_OFFSET_HIGH, offset.u.high_part); REG_SET_2(DMCUB_REGION4_TOP_ADDRESS, 0, DMCUB_REGION4_TOP_ADDRESS, cw4->region.top - cw4->region.base - 1, DMCUB_REGION4_ENABLE, 1); - REG_WRITE(DMCUB_REGION3_CW5_OFFSET, cw5->offset.u.low_part); - REG_WRITE(DMCUB_REGION3_CW5_OFFSET_HIGH, cw5->offset.u.high_part); + dmub_dcn20_translate_addr(&cw5->offset, fb_base, fb_offset, &offset); + + REG_WRITE(DMCUB_REGION3_CW5_OFFSET, offset.u.low_part); + REG_WRITE(DMCUB_REGION3_CW5_OFFSET_HIGH, offset.u.high_part); REG_WRITE(DMCUB_REGION3_CW5_BASE_ADDRESS, cw5->region.base); REG_SET_2(DMCUB_REGION3_CW5_TOP_ADDRESS, 0, DMCUB_REGION3_CW5_TOP_ADDRESS, cw5->region.top, DMCUB_REGION3_CW5_ENABLE, 1); - REG_WRITE(DMCUB_REGION3_CW6_OFFSET, cw6->offset.u.low_part); - REG_WRITE(DMCUB_REGION3_CW6_OFFSET_HIGH, cw6->offset.u.high_part); + dmub_dcn20_translate_addr(&cw6->offset, fb_base, fb_offset, &offset); + + REG_WRITE(DMCUB_REGION3_CW6_OFFSET, offset.u.low_part); + REG_WRITE(DMCUB_REGION3_CW6_OFFSET_HIGH, offset.u.high_part); REG_WRITE(DMCUB_REGION3_CW6_BASE_ADDRESS, cw6->region.base); REG_SET_2(DMCUB_REGION3_CW6_TOP_ADDRESS, 0, DMCUB_REGION3_CW6_TOP_ADDRESS, cw6->region.top, @@ -123,8 +192,6 @@ void dmub_dcn20_setup_mailbox(struct dmub_srv *dmub, REG_WRITE(DMCUB_INBOX1_BASE_ADDRESS, 0x80000000); REG_WRITE(DMCUB_INBOX1_SIZE, inbox1->top - inbox1->base); - REG_WRITE(DMCUB_INBOX1_RPTR, 0); - REG_WRITE(DMCUB_INBOX1_WPTR, 0); } uint32_t dmub_dcn20_get_inbox1_rptr(struct dmub_srv *dmub) diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.h b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.h index e70a57573467..04b0fa13153d 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.h +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.h @@ -30,6 +30,129 @@ struct dmub_srv; +/* DCN20 register definitions. */ + +#define DMUB_COMMON_REGS() \ + DMUB_SR(DMCUB_CNTL) \ + DMUB_SR(DMCUB_MEM_CNTL) \ + DMUB_SR(DMCUB_SEC_CNTL) \ + DMUB_SR(DMCUB_INBOX1_BASE_ADDRESS) \ + DMUB_SR(DMCUB_INBOX1_SIZE) \ + DMUB_SR(DMCUB_INBOX1_RPTR) \ + DMUB_SR(DMCUB_INBOX1_WPTR) \ + DMUB_SR(DMCUB_REGION3_CW0_OFFSET) \ + DMUB_SR(DMCUB_REGION3_CW1_OFFSET) \ + DMUB_SR(DMCUB_REGION3_CW2_OFFSET) \ + DMUB_SR(DMCUB_REGION3_CW3_OFFSET) \ + DMUB_SR(DMCUB_REGION3_CW4_OFFSET) \ + DMUB_SR(DMCUB_REGION3_CW5_OFFSET) \ + DMUB_SR(DMCUB_REGION3_CW6_OFFSET) \ + DMUB_SR(DMCUB_REGION3_CW7_OFFSET) \ + DMUB_SR(DMCUB_REGION3_CW0_OFFSET_HIGH) \ + DMUB_SR(DMCUB_REGION3_CW1_OFFSET_HIGH) \ + DMUB_SR(DMCUB_REGION3_CW2_OFFSET_HIGH) \ + DMUB_SR(DMCUB_REGION3_CW3_OFFSET_HIGH) \ + DMUB_SR(DMCUB_REGION3_CW4_OFFSET_HIGH) \ + DMUB_SR(DMCUB_REGION3_CW5_OFFSET_HIGH) \ + DMUB_SR(DMCUB_REGION3_CW6_OFFSET_HIGH) \ + DMUB_SR(DMCUB_REGION3_CW7_OFFSET_HIGH) \ + DMUB_SR(DMCUB_REGION3_CW0_BASE_ADDRESS) \ + DMUB_SR(DMCUB_REGION3_CW1_BASE_ADDRESS) \ + DMUB_SR(DMCUB_REGION3_CW2_BASE_ADDRESS) \ + DMUB_SR(DMCUB_REGION3_CW3_BASE_ADDRESS) \ + DMUB_SR(DMCUB_REGION3_CW4_BASE_ADDRESS) \ + DMUB_SR(DMCUB_REGION3_CW5_BASE_ADDRESS) \ + DMUB_SR(DMCUB_REGION3_CW6_BASE_ADDRESS) \ + DMUB_SR(DMCUB_REGION3_CW7_BASE_ADDRESS) \ + DMUB_SR(DMCUB_REGION3_CW0_TOP_ADDRESS) \ + DMUB_SR(DMCUB_REGION3_CW1_TOP_ADDRESS) \ + DMUB_SR(DMCUB_REGION3_CW2_TOP_ADDRESS) \ + DMUB_SR(DMCUB_REGION3_CW3_TOP_ADDRESS) \ + DMUB_SR(DMCUB_REGION3_CW4_TOP_ADDRESS) \ + DMUB_SR(DMCUB_REGION3_CW5_TOP_ADDRESS) \ + DMUB_SR(DMCUB_REGION3_CW6_TOP_ADDRESS) \ + DMUB_SR(DMCUB_REGION3_CW7_TOP_ADDRESS) \ + DMUB_SR(DMCUB_REGION4_OFFSET) \ + DMUB_SR(DMCUB_REGION4_OFFSET_HIGH) \ + DMUB_SR(DMCUB_REGION4_TOP_ADDRESS) \ + DMUB_SR(DMCUB_SCRATCH0) \ + DMUB_SR(DMCUB_SCRATCH1) \ + DMUB_SR(DMCUB_SCRATCH2) \ + DMUB_SR(DMCUB_SCRATCH3) \ + DMUB_SR(DMCUB_SCRATCH4) \ + DMUB_SR(DMCUB_SCRATCH5) \ + DMUB_SR(DMCUB_SCRATCH6) \ + DMUB_SR(DMCUB_SCRATCH7) \ + DMUB_SR(DMCUB_SCRATCH8) \ + DMUB_SR(DMCUB_SCRATCH9) \ + DMUB_SR(DMCUB_SCRATCH10) \ + DMUB_SR(DMCUB_SCRATCH11) \ + DMUB_SR(DMCUB_SCRATCH12) \ + DMUB_SR(DMCUB_SCRATCH13) \ + DMUB_SR(DMCUB_SCRATCH14) \ + DMUB_SR(DMCUB_SCRATCH15) \ + DMUB_SR(CC_DC_PIPE_DIS) \ + DMUB_SR(MMHUBBUB_SOFT_RESET) \ + DMUB_SR(DCN_VM_FB_LOCATION_BASE) \ + DMUB_SR(DCN_VM_FB_OFFSET) + +#define DMUB_COMMON_FIELDS() \ + DMUB_SF(DMCUB_CNTL, DMCUB_ENABLE) \ + DMUB_SF(DMCUB_CNTL, DMCUB_SOFT_RESET) \ + DMUB_SF(DMCUB_CNTL, DMCUB_TRACEPORT_EN) \ + DMUB_SF(DMCUB_MEM_CNTL, DMCUB_MEM_READ_SPACE) \ + DMUB_SF(DMCUB_MEM_CNTL, DMCUB_MEM_WRITE_SPACE) \ + DMUB_SF(DMCUB_SEC_CNTL, DMCUB_SEC_RESET) \ + DMUB_SF(DMCUB_SEC_CNTL, DMCUB_MEM_UNIT_ID) \ + DMUB_SF(DMCUB_REGION3_CW0_TOP_ADDRESS, DMCUB_REGION3_CW0_TOP_ADDRESS) \ + DMUB_SF(DMCUB_REGION3_CW0_TOP_ADDRESS, DMCUB_REGION3_CW0_ENABLE) \ + DMUB_SF(DMCUB_REGION3_CW1_TOP_ADDRESS, DMCUB_REGION3_CW1_TOP_ADDRESS) \ + DMUB_SF(DMCUB_REGION3_CW1_TOP_ADDRESS, DMCUB_REGION3_CW1_ENABLE) \ + DMUB_SF(DMCUB_REGION3_CW2_TOP_ADDRESS, DMCUB_REGION3_CW2_TOP_ADDRESS) \ + DMUB_SF(DMCUB_REGION3_CW2_TOP_ADDRESS, DMCUB_REGION3_CW2_ENABLE) \ + DMUB_SF(DMCUB_REGION3_CW3_TOP_ADDRESS, DMCUB_REGION3_CW3_TOP_ADDRESS) \ + DMUB_SF(DMCUB_REGION3_CW3_TOP_ADDRESS, DMCUB_REGION3_CW3_ENABLE) \ + DMUB_SF(DMCUB_REGION3_CW4_TOP_ADDRESS, DMCUB_REGION3_CW4_TOP_ADDRESS) \ + DMUB_SF(DMCUB_REGION3_CW4_TOP_ADDRESS, DMCUB_REGION3_CW4_ENABLE) \ + DMUB_SF(DMCUB_REGION3_CW5_TOP_ADDRESS, DMCUB_REGION3_CW5_TOP_ADDRESS) \ + DMUB_SF(DMCUB_REGION3_CW5_TOP_ADDRESS, DMCUB_REGION3_CW5_ENABLE) \ + DMUB_SF(DMCUB_REGION3_CW6_TOP_ADDRESS, DMCUB_REGION3_CW6_TOP_ADDRESS) \ + DMUB_SF(DMCUB_REGION3_CW6_TOP_ADDRESS, DMCUB_REGION3_CW6_ENABLE) \ + DMUB_SF(DMCUB_REGION3_CW7_TOP_ADDRESS, DMCUB_REGION3_CW7_TOP_ADDRESS) \ + DMUB_SF(DMCUB_REGION3_CW7_TOP_ADDRESS, DMCUB_REGION3_CW7_ENABLE) \ + DMUB_SF(DMCUB_REGION4_TOP_ADDRESS, DMCUB_REGION4_TOP_ADDRESS) \ + DMUB_SF(DMCUB_REGION4_TOP_ADDRESS, DMCUB_REGION4_ENABLE) \ + DMUB_SF(CC_DC_PIPE_DIS, DC_DMCUB_ENABLE) \ + DMUB_SF(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET) \ + DMUB_SF(DCN_VM_FB_LOCATION_BASE, FB_BASE) \ + DMUB_SF(DCN_VM_FB_OFFSET, FB_OFFSET) + +struct dmub_srv_common_reg_offset { +#define DMUB_SR(reg) uint32_t reg; + DMUB_COMMON_REGS() +#undef DMUB_SR +}; + +struct dmub_srv_common_reg_shift { +#define DMUB_SF(reg, field) uint8_t reg##__##field; + DMUB_COMMON_FIELDS() +#undef DMUB_SF +}; + +struct dmub_srv_common_reg_mask { +#define DMUB_SF(reg, field) uint32_t reg##__##field; + DMUB_COMMON_FIELDS() +#undef DMUB_SF +}; + +struct dmub_srv_common_regs { + const struct dmub_srv_common_reg_offset offset; + const struct dmub_srv_common_reg_mask mask; + const struct dmub_srv_common_reg_shift shift; +}; + +extern const struct dmub_srv_common_regs dmub_srv_dcn20_regs; + /* Hardware functions. */ void dmub_dcn20_init(struct dmub_srv *dmub); diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.c index 9cea7a2d8dbf..5bed9fcd6b5c 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.c @@ -25,6 +25,7 @@ #include "../inc/dmub_srv.h" #include "dmub_reg.h" +#include "dmub_dcn21.h" #include "dcn/dcn_2_1_0_offset.h" #include "dcn/dcn_2_1_0_sh_mask.h" @@ -32,103 +33,25 @@ #define BASE_INNER(seg) DMU_BASE__INST0_SEG##seg #define CTX dmub +#define REGS dmub->regs -static inline void dmub_dcn21_translate_addr(const union dmub_addr *addr_in, - uint64_t fb_base, - uint64_t fb_offset, - union dmub_addr *addr_out) -{ - addr_out->quad_part = addr_in->quad_part - fb_base + fb_offset; -} - -void dmub_dcn21_backdoor_load(struct dmub_srv *dmub, - const struct dmub_window *cw0, - const struct dmub_window *cw1) -{ - union dmub_addr offset; - uint64_t fb_base = dmub->fb_base, fb_offset = dmub->fb_offset; - - REG_UPDATE(DMCUB_SEC_CNTL, DMCUB_SEC_RESET, 1); - REG_UPDATE_2(DMCUB_MEM_CNTL, DMCUB_MEM_READ_SPACE, 0x3, - DMCUB_MEM_WRITE_SPACE, 0x3); - - dmub_dcn21_translate_addr(&cw0->offset, fb_base, fb_offset, &offset); - - REG_WRITE(DMCUB_REGION3_CW0_OFFSET, offset.u.low_part); - REG_WRITE(DMCUB_REGION3_CW0_OFFSET_HIGH, offset.u.high_part); - REG_WRITE(DMCUB_REGION3_CW0_BASE_ADDRESS, cw0->region.base); - REG_SET_2(DMCUB_REGION3_CW0_TOP_ADDRESS, 0, - DMCUB_REGION3_CW0_TOP_ADDRESS, cw0->region.top, - DMCUB_REGION3_CW0_ENABLE, 1); - - dmub_dcn21_translate_addr(&cw1->offset, fb_base, fb_offset, &offset); - - REG_WRITE(DMCUB_REGION3_CW1_OFFSET, offset.u.low_part); - REG_WRITE(DMCUB_REGION3_CW1_OFFSET_HIGH, offset.u.high_part); - REG_WRITE(DMCUB_REGION3_CW1_BASE_ADDRESS, cw1->region.base); - REG_SET_2(DMCUB_REGION3_CW1_TOP_ADDRESS, 0, - DMCUB_REGION3_CW1_TOP_ADDRESS, cw1->region.top, - DMCUB_REGION3_CW1_ENABLE, 1); - - REG_UPDATE_2(DMCUB_SEC_CNTL, DMCUB_SEC_RESET, 0, DMCUB_MEM_UNIT_ID, - 0x20); -} - -void dmub_dcn21_setup_windows(struct dmub_srv *dmub, - const struct dmub_window *cw2, - const struct dmub_window *cw3, - const struct dmub_window *cw4, - const struct dmub_window *cw5, - const struct dmub_window *cw6) -{ - union dmub_addr offset; - uint64_t fb_base = dmub->fb_base, fb_offset = dmub->fb_offset; - - dmub_dcn21_translate_addr(&cw2->offset, fb_base, fb_offset, &offset); - - REG_WRITE(DMCUB_REGION3_CW2_OFFSET, offset.u.low_part); - REG_WRITE(DMCUB_REGION3_CW2_OFFSET_HIGH, offset.u.high_part); - REG_WRITE(DMCUB_REGION3_CW2_BASE_ADDRESS, cw2->region.base); - REG_SET_2(DMCUB_REGION3_CW2_TOP_ADDRESS, 0, - DMCUB_REGION3_CW2_TOP_ADDRESS, cw2->region.top, - DMCUB_REGION3_CW2_ENABLE, 1); +/* Registers. */ - dmub_dcn21_translate_addr(&cw3->offset, fb_base, fb_offset, &offset); +const struct dmub_srv_common_regs dmub_srv_dcn21_regs = { +#define DMUB_SR(reg) REG_OFFSET(reg), + { DMUB_COMMON_REGS() }, +#undef DMUB_SR - REG_WRITE(DMCUB_REGION3_CW3_OFFSET, offset.u.low_part); - REG_WRITE(DMCUB_REGION3_CW3_OFFSET_HIGH, offset.u.high_part); - REG_WRITE(DMCUB_REGION3_CW3_BASE_ADDRESS, cw3->region.base); - REG_SET_2(DMCUB_REGION3_CW3_TOP_ADDRESS, 0, - DMCUB_REGION3_CW3_TOP_ADDRESS, cw3->region.top, - DMCUB_REGION3_CW3_ENABLE, 1); +#define DMUB_SF(reg, field) FD_MASK(reg, field), + { DMUB_COMMON_FIELDS() }, +#undef DMUB_SF - /* TODO: Move this to CW4. */ - dmub_dcn21_translate_addr(&cw4->offset, fb_base, fb_offset, &offset); +#define DMUB_SF(reg, field) FD_SHIFT(reg, field), + { DMUB_COMMON_FIELDS() }, +#undef DMUB_SF +}; - REG_WRITE(DMCUB_REGION4_OFFSET, offset.u.low_part); - REG_WRITE(DMCUB_REGION4_OFFSET_HIGH, offset.u.high_part); - REG_SET_2(DMCUB_REGION4_TOP_ADDRESS, 0, DMCUB_REGION4_TOP_ADDRESS, - cw4->region.top - cw4->region.base - 1, DMCUB_REGION4_ENABLE, - 1); - - dmub_dcn21_translate_addr(&cw5->offset, fb_base, fb_offset, &offset); - - REG_WRITE(DMCUB_REGION3_CW5_OFFSET, offset.u.low_part); - REG_WRITE(DMCUB_REGION3_CW5_OFFSET_HIGH, offset.u.high_part); - REG_WRITE(DMCUB_REGION3_CW5_BASE_ADDRESS, cw5->region.base); - REG_SET_2(DMCUB_REGION3_CW5_TOP_ADDRESS, 0, - DMCUB_REGION3_CW5_TOP_ADDRESS, cw5->region.top, - DMCUB_REGION3_CW5_ENABLE, 1); - - dmub_dcn21_translate_addr(&cw6->offset, fb_base, fb_offset, &offset); - - REG_WRITE(DMCUB_REGION3_CW6_OFFSET, offset.u.low_part); - REG_WRITE(DMCUB_REGION3_CW6_OFFSET_HIGH, offset.u.high_part); - REG_WRITE(DMCUB_REGION3_CW6_BASE_ADDRESS, cw6->region.base); - REG_SET_2(DMCUB_REGION3_CW6_TOP_ADDRESS, 0, - DMCUB_REGION3_CW6_TOP_ADDRESS, cw6->region.top, - DMCUB_REGION3_CW6_ENABLE, 1); -} +/* Shared functions. */ bool dmub_dcn21_is_auto_load_done(struct dmub_srv *dmub) { diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.h b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.h index f7a93a5dcfa5..2bbea237137b 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.h +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.h @@ -28,18 +28,11 @@ #include "dmub_dcn20.h" -/* Hardware functions. */ +/* Registers. */ -void dmub_dcn21_backdoor_load(struct dmub_srv *dmub, - const struct dmub_window *cw0, - const struct dmub_window *cw1); +extern const struct dmub_srv_common_regs dmub_srv_dcn21_regs; -void dmub_dcn21_setup_windows(struct dmub_srv *dmub, - const struct dmub_window *cw2, - const struct dmub_window *cw3, - const struct dmub_window *cw4, - const struct dmub_window *cw5, - const struct dmub_window *cw6); +/* Hardware functions. */ bool dmub_dcn21_is_auto_load_done(struct dmub_srv *dmub); diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_reg.h b/drivers/gpu/drm/amd/display/dmub/src/dmub_reg.h index bac4ee8f745f..c1f4030929a4 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_reg.h +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_reg.h @@ -34,11 +34,15 @@ struct dmub_srv; #define BASE(seg) BASE_INNER(seg) -#define REG_OFFSET(base_index, addr) (BASE(base_index) + addr) +#define REG_OFFSET(reg_name) (BASE(mm##reg_name##_BASE_IDX) + mm##reg_name) -#define REG(reg_name) REG_OFFSET(mm ## reg_name ## _BASE_IDX, mm ## reg_name) +#define FD_SHIFT(reg_name, field) reg_name##__##field##__SHIFT -#define FD(reg_field) reg_field ## __SHIFT, reg_field ## _MASK +#define FD_MASK(reg_name, field) reg_name##__##field##_MASK + +#define REG(reg) (REGS)->offset.reg + +#define FD(reg_field) (REGS)->shift.reg_field, (REGS)->mask.reg_field #define FN(reg_name, field) FD(reg_name##__##field) diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c index 5f39166d3c08..85a518bf8a76 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c @@ -26,7 +26,7 @@ #include "../inc/dmub_srv.h" #include "dmub_dcn20.h" #include "dmub_dcn21.h" -#include "dmub_trace_buffer.h" +#include "dmub_fw_meta.h" #include "os_types.h" /* * Note: the DMUB service is standalone. No additional headers should be @@ -46,6 +46,11 @@ /* Mailbox size */ #define DMUB_MAILBOX_SIZE (DMUB_RB_SIZE) +/* Default state size if meta is absent. */ +#define DMUB_FW_STATE_SIZE (1024) + +/* Default tracebuffer size if meta is absent. */ +#define DMUB_TRACE_BUFFER_SIZE (1024) /* Number of windows in use. */ #define DMUB_NUM_WINDOWS (DMUB_WINDOW_6_FW_STATE + 1) @@ -62,6 +67,47 @@ static inline uint32_t dmub_align(uint32_t val, uint32_t factor) return (val + factor - 1) / factor * factor; } +static void dmub_flush_buffer_mem(const struct dmub_fb *fb) +{ + const uint8_t *base = (const uint8_t *)fb->cpu_addr; + uint8_t buf[64]; + uint32_t pos, end; + + /** + * Read 64-byte chunks since we don't want to store a + * large temporary buffer for this purpose. + */ + end = fb->size / sizeof(buf) * sizeof(buf); + + for (pos = 0; pos < end; pos += sizeof(buf)) + dmub_memcpy(buf, base + pos, sizeof(buf)); + + /* Read anything leftover into the buffer. */ + if (end < fb->size) + dmub_memcpy(buf, base + pos, fb->size - end); +} + +static const struct dmub_fw_meta_info * +dmub_get_fw_meta_info(const uint8_t *fw_bss_data, uint32_t fw_bss_data_size) +{ + const union dmub_fw_meta *meta; + + if (fw_bss_data == NULL) + return NULL; + + if (fw_bss_data_size < sizeof(union dmub_fw_meta) + DMUB_FW_META_OFFSET) + return NULL; + + meta = (const union dmub_fw_meta *)(fw_bss_data + fw_bss_data_size - + DMUB_FW_META_OFFSET - + sizeof(union dmub_fw_meta)); + + if (meta->info.magic_value != DMUB_FW_META_MAGIC) + return NULL; + + return &meta->info; +} + static bool dmub_srv_hw_setup(struct dmub_srv *dmub, enum dmub_asic asic) { struct dmub_srv_hw_funcs *funcs = &dmub->hw_funcs; @@ -69,6 +115,8 @@ static bool dmub_srv_hw_setup(struct dmub_srv *dmub, enum dmub_asic asic) switch (asic) { case DMUB_ASIC_DCN20: case DMUB_ASIC_DCN21: + dmub->regs = &dmub_srv_dcn20_regs; + funcs->reset = dmub_dcn20_reset; funcs->reset_release = dmub_dcn20_reset_release; funcs->backdoor_load = dmub_dcn20_backdoor_load; @@ -80,8 +128,8 @@ static bool dmub_srv_hw_setup(struct dmub_srv *dmub, enum dmub_asic asic) funcs->is_hw_init = dmub_dcn20_is_hw_init; if (asic == DMUB_ASIC_DCN21) { - funcs->backdoor_load = dmub_dcn21_backdoor_load; - funcs->setup_windows = dmub_dcn21_setup_windows; + dmub->regs = &dmub_srv_dcn21_regs; + funcs->is_auto_load_done = dmub_dcn21_is_auto_load_done; funcs->is_phy_init = dmub_dcn21_is_phy_init; } @@ -160,6 +208,9 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub, struct dmub_region *mail = &out->regions[DMUB_WINDOW_4_MAILBOX]; struct dmub_region *trace_buff = &out->regions[DMUB_WINDOW_5_TRACEBUFF]; struct dmub_region *fw_state = &out->regions[DMUB_WINDOW_6_FW_STATE]; + const struct dmub_fw_meta_info *fw_info; + uint32_t fw_state_size = DMUB_FW_STATE_SIZE; + uint32_t trace_buffer_size = DMUB_TRACE_BUFFER_SIZE; if (!dmub->sw_init) return DMUB_STATUS_INVALID; @@ -174,6 +225,11 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub, data->base = dmub_align(inst->top, 256); data->top = data->base + params->bss_data_size; + /* + * All cache windows below should be aligned to the size + * of the DMCUB cache line, 64 bytes. + */ + stack->base = dmub_align(data->top, 256); stack->top = stack->base + DMUB_STACK_SIZE + DMUB_CONTEXT_SIZE; @@ -183,14 +239,19 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub, mail->base = dmub_align(bios->top, 256); mail->top = mail->base + DMUB_MAILBOX_SIZE; + fw_info = dmub_get_fw_meta_info(params->fw_bss_data, + params->bss_data_size); + + if (fw_info) { + fw_state_size = fw_info->fw_region_size; + trace_buffer_size = fw_info->trace_buffer_size; + } + trace_buff->base = dmub_align(mail->top, 256); - trace_buff->top = trace_buff->base + TRACE_BUF_SIZE; + trace_buff->top = trace_buff->base + dmub_align(trace_buffer_size, 64); fw_state->base = dmub_align(trace_buff->top, 256); - - /* Align firmware state to size of cache line. */ - fw_state->top = - fw_state->base + dmub_align(sizeof(struct dmub_fw_state), 64); + fw_state->top = fw_state->base + dmub_align(fw_state_size, 64); out->fb_size = dmub_align(fw_state->top, 4096); @@ -251,6 +312,9 @@ enum dmub_status dmub_srv_is_hw_init(struct dmub_srv *dmub, bool *is_hw_init) if (!dmub->sw_init) return DMUB_STATUS_INVALID; + if (!dmub->hw_init) + return DMUB_STATUS_OK; + if (dmub->hw_funcs.is_hw_init) *is_hw_init = dmub->hw_funcs.is_hw_init(dmub); @@ -288,6 +352,13 @@ enum dmub_status dmub_srv_hw_init(struct dmub_srv *dmub, cw1.region.base = DMUB_CW1_BASE; cw1.region.top = cw1.region.base + stack_fb->size - 1; + /** + * Read back all the instruction memory so we don't hang the + * DMCUB when backdoor loading if the write from x86 hasn't been + * flushed yet. This only occurs in backdoor loading. + */ + dmub_flush_buffer_mem(inst_fb); + if (params->load_inst_const && dmub->hw_funcs.backdoor_load) dmub->hw_funcs.backdoor_load(dmub, &cw0, &cw1); } @@ -347,6 +418,22 @@ enum dmub_status dmub_srv_hw_init(struct dmub_srv *dmub, return DMUB_STATUS_OK; } +enum dmub_status dmub_srv_hw_reset(struct dmub_srv *dmub) +{ + if (!dmub->sw_init) + return DMUB_STATUS_INVALID; + + if (dmub->hw_init == false) + return DMUB_STATUS_OK; + + if (dmub->hw_funcs.reset) + dmub->hw_funcs.reset(dmub); + + dmub->hw_init = false; + + return DMUB_STATUS_OK; +} + enum dmub_status dmub_srv_cmd_queue(struct dmub_srv *dmub, const struct dmub_cmd_header *cmd) { @@ -364,33 +451,17 @@ enum dmub_status dmub_srv_cmd_execute(struct dmub_srv *dmub) if (!dmub->hw_init) return DMUB_STATUS_INVALID; + /** + * Read back all the queued commands to ensure that they've + * been flushed to framebuffer memory. Otherwise DMCUB might + * read back stale, fully invalid or partially invalid data. + */ + dmub_rb_flush_pending(&dmub->inbox1_rb); + dmub->hw_funcs.set_inbox1_wptr(dmub, dmub->inbox1_rb.wrpt); return DMUB_STATUS_OK; } -enum dmub_status dmub_srv_cmd_submit(struct dmub_srv *dmub, - const struct dmub_cmd_header *cmd, - uint32_t timeout_us) -{ - uint32_t i = 0; - - if (!dmub->hw_init) - return DMUB_STATUS_INVALID; - - for (i = 0; i <= timeout_us; ++i) { - dmub->inbox1_rb.rptr = dmub->hw_funcs.get_inbox1_rptr(dmub); - if (dmub_rb_push_front(&dmub->inbox1_rb, cmd)) { - dmub->hw_funcs.set_inbox1_wptr(dmub, - dmub->inbox1_rb.wrpt); - return DMUB_STATUS_OK; - } - - udelay(1); - } - - return DMUB_STATUS_TIMEOUT; -} - enum dmub_status dmub_srv_wait_for_auto_load(struct dmub_srv *dmub, uint32_t timeout_us) { diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h index 72b659c63aea..a2903985b9e8 100644 --- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h +++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h @@ -134,17 +134,31 @@ #define PICASSO_A0 0x41 /* DCN1_01 */ #define RAVEN2_A0 0x81 +#define RAVEN2_15D8_REV_94 0x94 +#define RAVEN2_15D8_REV_95 0x95 #define RAVEN2_15D8_REV_E3 0xE3 #define RAVEN2_15D8_REV_E4 0xE4 +#define RAVEN2_15D8_REV_E9 0xE9 +#define RAVEN2_15D8_REV_EA 0xEA +#define RAVEN2_15D8_REV_EB 0xEB #define RAVEN1_F0 0xF0 #define RAVEN_UNKNOWN 0xFF - +#ifndef ASICREV_IS_RAVEN #define ASICREV_IS_RAVEN(eChipRev) ((eChipRev >= RAVEN_A0) && eChipRev < RAVEN_UNKNOWN) +#endif + #define ASICREV_IS_PICASSO(eChipRev) ((eChipRev >= PICASSO_A0) && (eChipRev < RAVEN2_A0)) +#ifndef ASICREV_IS_RAVEN2 #define ASICREV_IS_RAVEN2(eChipRev) ((eChipRev >= RAVEN2_A0) && (eChipRev < RAVEN1_F0)) +#endif #define ASICREV_IS_RV1_F0(eChipRev) ((eChipRev >= RAVEN1_F0) && (eChipRev < RAVEN_UNKNOWN)) #define ASICREV_IS_DALI(eChipRev) ((eChipRev == RAVEN2_15D8_REV_E3) \ || (eChipRev == RAVEN2_15D8_REV_E4)) +#define ASICREV_IS_POLLOCK(eChipRev) (eChipRev == RAVEN2_15D8_REV_94 \ + || eChipRev == RAVEN2_15D8_REV_95 \ + || eChipRev == RAVEN2_15D8_REV_E9 \ + || eChipRev == RAVEN2_15D8_REV_EA \ + || eChipRev == RAVEN2_15D8_REV_EB) #define FAMILY_RV 142 /* DCN 1*/ diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c index b52c4d379651..cac09d500fda 100644 --- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c +++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c @@ -364,8 +364,10 @@ static struct fixed31_32 translate_from_linear_space( scratch_2 = dc_fixpt_mul(gamma_of_2, pow_buffer[pow_buffer_ptr%16]); - pow_buffer[pow_buffer_ptr%16] = scratch_2; - pow_buffer_ptr++; + if (pow_buffer_ptr != -1) { + pow_buffer[pow_buffer_ptr%16] = scratch_2; + pow_buffer_ptr++; + } scratch_1 = dc_fixpt_mul(scratch_1, scratch_2); scratch_1 = dc_fixpt_sub(scratch_1, args->a2); @@ -1671,129 +1673,6 @@ static bool map_regamma_hw_to_x_user( #define _EXTRA_POINTS 3 -bool mod_color_calculate_regamma_params(struct dc_transfer_func *output_tf, - const struct dc_gamma *ramp, bool mapUserRamp, bool canRomBeUsed, - const struct freesync_hdr_tf_params *fs_params) -{ - struct dc_transfer_func_distributed_points *tf_pts = &output_tf->tf_pts; - struct dividers dividers; - - struct pwl_float_data *rgb_user = NULL; - struct pwl_float_data_ex *rgb_regamma = NULL; - struct gamma_pixel *axis_x = NULL; - struct pixel_gamma_point *coeff = NULL; - enum dc_transfer_func_predefined tf = TRANSFER_FUNCTION_SRGB; - bool ret = false; - - if (output_tf->type == TF_TYPE_BYPASS) - return false; - - /* we can use hardcoded curve for plain SRGB TF */ - if (output_tf->type == TF_TYPE_PREDEFINED && canRomBeUsed == true && - output_tf->tf == TRANSFER_FUNCTION_SRGB) { - if (ramp == NULL) - return true; - if ((ramp->is_identity && ramp->type != GAMMA_CS_TFM_1D) || - (!mapUserRamp && ramp->type == GAMMA_RGB_256)) - return true; - } - - output_tf->type = TF_TYPE_DISTRIBUTED_POINTS; - - if (ramp && ramp->type != GAMMA_CS_TFM_1D && - (mapUserRamp || ramp->type != GAMMA_RGB_256)) { - rgb_user = kvcalloc(ramp->num_entries + _EXTRA_POINTS, - sizeof(*rgb_user), - GFP_KERNEL); - if (!rgb_user) - goto rgb_user_alloc_fail; - - axis_x = kvcalloc(ramp->num_entries + 3, sizeof(*axis_x), - GFP_KERNEL); - if (!axis_x) - goto axis_x_alloc_fail; - - dividers.divider1 = dc_fixpt_from_fraction(3, 2); - dividers.divider2 = dc_fixpt_from_int(2); - dividers.divider3 = dc_fixpt_from_fraction(5, 2); - - build_evenly_distributed_points( - axis_x, - ramp->num_entries, - dividers); - - if (ramp->type == GAMMA_RGB_256 && mapUserRamp) - scale_gamma(rgb_user, ramp, dividers); - else if (ramp->type == GAMMA_RGB_FLOAT_1024) - scale_gamma_dx(rgb_user, ramp, dividers); - } - - rgb_regamma = kvcalloc(MAX_HW_POINTS + _EXTRA_POINTS, - sizeof(*rgb_regamma), - GFP_KERNEL); - if (!rgb_regamma) - goto rgb_regamma_alloc_fail; - - coeff = kvcalloc(MAX_HW_POINTS + _EXTRA_POINTS, sizeof(*coeff), - GFP_KERNEL); - if (!coeff) - goto coeff_alloc_fail; - - tf = output_tf->tf; - if (tf == TRANSFER_FUNCTION_PQ) { - tf_pts->end_exponent = 7; - tf_pts->x_point_at_y1_red = 125; - tf_pts->x_point_at_y1_green = 125; - tf_pts->x_point_at_y1_blue = 125; - - build_pq(rgb_regamma, - MAX_HW_POINTS, - coordinates_x, - output_tf->sdr_ref_white_level); - } else if (tf == TRANSFER_FUNCTION_GAMMA22 && - fs_params != NULL && fs_params->skip_tm == 0) { - build_freesync_hdr(rgb_regamma, - MAX_HW_POINTS, - coordinates_x, - fs_params); - } else if (tf == TRANSFER_FUNCTION_HLG) { - build_freesync_hdr(rgb_regamma, - MAX_HW_POINTS, - coordinates_x, - fs_params); - - } else { - tf_pts->end_exponent = 0; - tf_pts->x_point_at_y1_red = 1; - tf_pts->x_point_at_y1_green = 1; - tf_pts->x_point_at_y1_blue = 1; - - build_regamma(rgb_regamma, - MAX_HW_POINTS, - coordinates_x, tf); - } - map_regamma_hw_to_x_user(ramp, coeff, rgb_user, - coordinates_x, axis_x, rgb_regamma, - MAX_HW_POINTS, tf_pts, - (mapUserRamp || (ramp && ramp->type != GAMMA_RGB_256)) && - (ramp && ramp->type != GAMMA_CS_TFM_1D)); - - if (ramp && ramp->type == GAMMA_CS_TFM_1D) - apply_lut_1d(ramp, MAX_HW_POINTS, tf_pts); - - ret = true; - - kvfree(coeff); -coeff_alloc_fail: - kvfree(rgb_regamma); -rgb_regamma_alloc_fail: - kvfree(axis_x); -axis_x_alloc_fail: - kvfree(rgb_user); -rgb_user_alloc_fail: - return ret; -} - bool calculate_user_regamma_coeff(struct dc_transfer_func *output_tf, const struct regamma_lut *regamma) { @@ -2041,14 +1920,14 @@ rgb_user_alloc_fail: return ret; } - -bool mod_color_calculate_curve(enum dc_transfer_func_predefined trans, +static bool calculate_curve(enum dc_transfer_func_predefined trans, struct dc_transfer_func_distributed_points *points, + struct pwl_float_data_ex *rgb_regamma, + const struct freesync_hdr_tf_params *fs_params, uint32_t sdr_ref_white_level) { uint32_t i; bool ret = false; - struct pwl_float_data_ex *rgb_regamma = NULL; if (trans == TRANSFER_FUNCTION_UNITY || trans == TRANSFER_FUNCTION_LINEAR) { @@ -2058,68 +1937,33 @@ bool mod_color_calculate_curve(enum dc_transfer_func_predefined trans, points->x_point_at_y1_blue = 1; for (i = 0; i <= MAX_HW_POINTS ; i++) { - points->red[i] = coordinates_x[i].x; - points->green[i] = coordinates_x[i].x; - points->blue[i] = coordinates_x[i].x; + rgb_regamma[i].r = coordinates_x[i].x; + rgb_regamma[i].g = coordinates_x[i].x; + rgb_regamma[i].b = coordinates_x[i].x; } + ret = true; } else if (trans == TRANSFER_FUNCTION_PQ) { - rgb_regamma = kvcalloc(MAX_HW_POINTS + _EXTRA_POINTS, - sizeof(*rgb_regamma), - GFP_KERNEL); - if (!rgb_regamma) - goto rgb_regamma_alloc_fail; points->end_exponent = 7; points->x_point_at_y1_red = 125; points->x_point_at_y1_green = 125; points->x_point_at_y1_blue = 125; - build_pq(rgb_regamma, MAX_HW_POINTS, coordinates_x, sdr_ref_white_level); - for (i = 0; i <= MAX_HW_POINTS ; i++) { - points->red[i] = rgb_regamma[i].r; - points->green[i] = rgb_regamma[i].g; - points->blue[i] = rgb_regamma[i].b; - } - ret = true; - kvfree(rgb_regamma); - } else if (trans == TRANSFER_FUNCTION_SRGB || - trans == TRANSFER_FUNCTION_BT709 || - trans == TRANSFER_FUNCTION_GAMMA22 || - trans == TRANSFER_FUNCTION_GAMMA24 || - trans == TRANSFER_FUNCTION_GAMMA26) { - rgb_regamma = kvcalloc(MAX_HW_POINTS + _EXTRA_POINTS, - sizeof(*rgb_regamma), - GFP_KERNEL); - if (!rgb_regamma) - goto rgb_regamma_alloc_fail; - points->end_exponent = 0; - points->x_point_at_y1_red = 1; - points->x_point_at_y1_green = 1; - points->x_point_at_y1_blue = 1; - - build_regamma(rgb_regamma, + ret = true; + } else if (trans == TRANSFER_FUNCTION_GAMMA22 && + fs_params != NULL && fs_params->skip_tm == 0) { + build_freesync_hdr(rgb_regamma, MAX_HW_POINTS, coordinates_x, - trans); - for (i = 0; i <= MAX_HW_POINTS ; i++) { - points->red[i] = rgb_regamma[i].r; - points->green[i] = rgb_regamma[i].g; - points->blue[i] = rgb_regamma[i].b; - } - ret = true; + fs_params); - kvfree(rgb_regamma); + ret = true; } else if (trans == TRANSFER_FUNCTION_HLG) { - rgb_regamma = kvcalloc(MAX_HW_POINTS + _EXTRA_POINTS, - sizeof(*rgb_regamma), - GFP_KERNEL); - if (!rgb_regamma) - goto rgb_regamma_alloc_fail; points->end_exponent = 4; points->x_point_at_y1_red = 12; points->x_point_at_y1_green = 12; @@ -2129,18 +1973,127 @@ bool mod_color_calculate_curve(enum dc_transfer_func_predefined trans, MAX_HW_POINTS, coordinates_x, 80, 1000); - for (i = 0; i <= MAX_HW_POINTS ; i++) { - points->red[i] = rgb_regamma[i].r; - points->green[i] = rgb_regamma[i].g; - points->blue[i] = rgb_regamma[i].b; - } + + ret = true; + } else { + // trans == TRANSFER_FUNCTION_SRGB + // trans == TRANSFER_FUNCTION_BT709 + // trans == TRANSFER_FUNCTION_GAMMA22 + // trans == TRANSFER_FUNCTION_GAMMA24 + // trans == TRANSFER_FUNCTION_GAMMA26 + points->end_exponent = 0; + points->x_point_at_y1_red = 1; + points->x_point_at_y1_green = 1; + points->x_point_at_y1_blue = 1; + + build_regamma(rgb_regamma, + MAX_HW_POINTS, + coordinates_x, + trans); + ret = true; - kvfree(rgb_regamma); } -rgb_regamma_alloc_fail: + return ret; } +bool mod_color_calculate_regamma_params(struct dc_transfer_func *output_tf, + const struct dc_gamma *ramp, bool mapUserRamp, bool canRomBeUsed, + const struct freesync_hdr_tf_params *fs_params) +{ + struct dc_transfer_func_distributed_points *tf_pts = &output_tf->tf_pts; + struct dividers dividers; + + struct pwl_float_data *rgb_user = NULL; + struct pwl_float_data_ex *rgb_regamma = NULL; + struct gamma_pixel *axis_x = NULL; + struct pixel_gamma_point *coeff = NULL; + enum dc_transfer_func_predefined tf = TRANSFER_FUNCTION_SRGB; + bool ret = false; + + if (output_tf->type == TF_TYPE_BYPASS) + return false; + + /* we can use hardcoded curve for plain SRGB TF */ + if (output_tf->type == TF_TYPE_PREDEFINED && canRomBeUsed == true && + output_tf->tf == TRANSFER_FUNCTION_SRGB) { + if (ramp == NULL) + return true; + if ((ramp->is_identity && ramp->type != GAMMA_CS_TFM_1D) || + (!mapUserRamp && ramp->type == GAMMA_RGB_256)) + return true; + } + + output_tf->type = TF_TYPE_DISTRIBUTED_POINTS; + + if (ramp && ramp->type != GAMMA_CS_TFM_1D && + (mapUserRamp || ramp->type != GAMMA_RGB_256)) { + rgb_user = kvcalloc(ramp->num_entries + _EXTRA_POINTS, + sizeof(*rgb_user), + GFP_KERNEL); + if (!rgb_user) + goto rgb_user_alloc_fail; + + axis_x = kvcalloc(ramp->num_entries + 3, sizeof(*axis_x), + GFP_KERNEL); + if (!axis_x) + goto axis_x_alloc_fail; + + dividers.divider1 = dc_fixpt_from_fraction(3, 2); + dividers.divider2 = dc_fixpt_from_int(2); + dividers.divider3 = dc_fixpt_from_fraction(5, 2); + + build_evenly_distributed_points( + axis_x, + ramp->num_entries, + dividers); + + if (ramp->type == GAMMA_RGB_256 && mapUserRamp) + scale_gamma(rgb_user, ramp, dividers); + else if (ramp->type == GAMMA_RGB_FLOAT_1024) + scale_gamma_dx(rgb_user, ramp, dividers); + } + + rgb_regamma = kvcalloc(MAX_HW_POINTS + _EXTRA_POINTS, + sizeof(*rgb_regamma), + GFP_KERNEL); + if (!rgb_regamma) + goto rgb_regamma_alloc_fail; + + coeff = kvcalloc(MAX_HW_POINTS + _EXTRA_POINTS, sizeof(*coeff), + GFP_KERNEL); + if (!coeff) + goto coeff_alloc_fail; + + tf = output_tf->tf; + + ret = calculate_curve(tf, + tf_pts, + rgb_regamma, + fs_params, + output_tf->sdr_ref_white_level); + + if (ret) { + map_regamma_hw_to_x_user(ramp, coeff, rgb_user, + coordinates_x, axis_x, rgb_regamma, + MAX_HW_POINTS, tf_pts, + (mapUserRamp || (ramp && ramp->type != GAMMA_RGB_256)) && + (ramp && ramp->type != GAMMA_CS_TFM_1D)); + + if (ramp && ramp->type == GAMMA_CS_TFM_1D) + apply_lut_1d(ramp, MAX_HW_POINTS, tf_pts); + } + + kvfree(coeff); +coeff_alloc_fail: + kvfree(rgb_regamma); +rgb_regamma_alloc_fail: + kvfree(axis_x); +axis_x_alloc_fail: + kvfree(rgb_user); +rgb_user_alloc_fail: + return ret; +} bool mod_color_calculate_degamma_curve(enum dc_transfer_func_predefined trans, struct dc_transfer_func_distributed_points *points) diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.h b/drivers/gpu/drm/amd/display/modules/color/color_gamma.h index 44ddea58523a..9994817a9a03 100644 --- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.h +++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.h @@ -103,10 +103,6 @@ bool mod_color_calculate_regamma_params(struct dc_transfer_func *output_tf, bool mod_color_calculate_degamma_params(struct dc_transfer_func *output_tf, const struct dc_gamma *ramp, bool mapUserRamp); -bool mod_color_calculate_curve(enum dc_transfer_func_predefined trans, - struct dc_transfer_func_distributed_points *points, - uint32_t sdr_ref_white_level); - bool mod_color_calculate_degamma_curve(enum dc_transfer_func_predefined trans, struct dc_transfer_func_distributed_points *points); diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c index a94700940fd6..b9992ebf77a6 100644 --- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c +++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c @@ -37,8 +37,8 @@ #define STATIC_SCREEN_RAMP_DELTA_REFRESH_RATE_PER_FRAME ((1000 / 60) * 65) /* Number of elements in the render times cache array */ #define RENDER_TIMES_MAX_COUNT 10 -/* Threshold to exit BTR (to avoid frequent enter-exits at the lower limit) */ -#define BTR_EXIT_MARGIN 2000 +/* Threshold to exit/exit BTR (to avoid frequent enter-exits at the lower limit) */ +#define BTR_MAX_MARGIN 2500 /* Threshold to change BTR multiplier (to avoid frequent changes) */ #define BTR_DRIFT_MARGIN 2000 /*Threshold to exit fixed refresh rate*/ @@ -254,24 +254,22 @@ static void apply_below_the_range(struct core_freesync *core_freesync, unsigned int delta_from_mid_point_in_us_1 = 0xFFFFFFFF; unsigned int delta_from_mid_point_in_us_2 = 0xFFFFFFFF; unsigned int frames_to_insert = 0; - unsigned int min_frame_duration_in_ns = 0; - unsigned int max_render_time_in_us = in_out_vrr->max_duration_in_us; unsigned int delta_from_mid_point_delta_in_us; - - min_frame_duration_in_ns = ((unsigned int) (div64_u64( - (1000000000ULL * 1000000), - in_out_vrr->max_refresh_in_uhz))); + unsigned int max_render_time_in_us = + in_out_vrr->max_duration_in_us - in_out_vrr->btr.margin_in_us; /* Program BTR */ - if (last_render_time_in_us + BTR_EXIT_MARGIN < max_render_time_in_us) { + if ((last_render_time_in_us + in_out_vrr->btr.margin_in_us / 2) < max_render_time_in_us) { /* Exit Below the Range */ if (in_out_vrr->btr.btr_active) { in_out_vrr->btr.frame_counter = 0; in_out_vrr->btr.btr_active = false; } - } else if (last_render_time_in_us > max_render_time_in_us) { + } else if (last_render_time_in_us > (max_render_time_in_us + in_out_vrr->btr.margin_in_us / 2)) { /* Enter Below the Range */ - in_out_vrr->btr.btr_active = true; + if (!in_out_vrr->btr.btr_active) { + in_out_vrr->btr.btr_active = true; + } } /* BTR set to "not active" so disengage */ @@ -327,7 +325,9 @@ static void apply_below_the_range(struct core_freesync *core_freesync, /* Choose number of frames to insert based on how close it * can get to the mid point of the variable range. */ - if (delta_from_mid_point_in_us_1 < delta_from_mid_point_in_us_2) { + if ((frame_time_in_us / mid_point_frames_ceil) > in_out_vrr->min_duration_in_us && + (delta_from_mid_point_in_us_1 < delta_from_mid_point_in_us_2 || + mid_point_frames_floor < 2)) { frames_to_insert = mid_point_frames_ceil; delta_from_mid_point_delta_in_us = delta_from_mid_point_in_us_2 - delta_from_mid_point_in_us_1; @@ -343,7 +343,7 @@ static void apply_below_the_range(struct core_freesync *core_freesync, if (in_out_vrr->btr.frames_to_insert != 0 && delta_from_mid_point_delta_in_us < BTR_DRIFT_MARGIN) { if (((last_render_time_in_us / in_out_vrr->btr.frames_to_insert) < - in_out_vrr->max_duration_in_us) && + max_render_time_in_us) && ((last_render_time_in_us / in_out_vrr->btr.frames_to_insert) > in_out_vrr->min_duration_in_us)) frames_to_insert = in_out_vrr->btr.frames_to_insert; @@ -381,7 +381,7 @@ static void apply_fixed_refresh(struct core_freesync *core_freesync, bool update = false; unsigned int max_render_time_in_us = in_out_vrr->max_duration_in_us; - //Compute the exit refresh rate and exit frame duration + /* Compute the exit refresh rate and exit frame duration */ unsigned int exit_refresh_rate_in_milli_hz = ((1000000000/max_render_time_in_us) + (1000*FIXED_REFRESH_EXIT_MARGIN_IN_HZ)); unsigned int exit_frame_duration_in_us = 1000000000/exit_refresh_rate_in_milli_hz; @@ -796,6 +796,11 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync, refresh_range = in_out_vrr->max_refresh_in_uhz - in_out_vrr->min_refresh_in_uhz; + in_out_vrr->btr.margin_in_us = in_out_vrr->max_duration_in_us - + 2 * in_out_vrr->min_duration_in_us; + if (in_out_vrr->btr.margin_in_us > BTR_MAX_MARGIN) + in_out_vrr->btr.margin_in_us = BTR_MAX_MARGIN; + in_out_vrr->supported = true; } @@ -811,6 +816,9 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync, in_out_vrr->btr.inserted_duration_in_us = 0; in_out_vrr->btr.frames_to_insert = 0; in_out_vrr->btr.frame_counter = 0; + in_out_vrr->fixed.fixed_active = false; + in_out_vrr->fixed.target_refresh_in_uhz = 0; + in_out_vrr->btr.mid_point_in_us = (in_out_vrr->min_duration_in_us + in_out_vrr->max_duration_in_us) / 2; @@ -826,6 +834,7 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync, in_out_vrr->adjust.v_total_max = stream->timing.v_total; } else if (in_out_vrr->state == VRR_STATE_ACTIVE_VARIABLE && refresh_range >= MIN_REFRESH_RANGE_IN_US) { + in_out_vrr->adjust.v_total_min = calc_v_total_from_refresh(stream, in_out_vrr->max_refresh_in_uhz); diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h index f98d3d9ecb6d..af78e4f1be68 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h @@ -63,7 +63,7 @@ struct mod_hdcp_transition_input_hdcp1 { uint8_t hdcp_capable_dp; uint8_t binfo_read_dp; uint8_t r0p_available_dp; - uint8_t link_integiry_check; + uint8_t link_integrity_check; uint8_t reauth_request_check; uint8_t stream_encryption_dp; }; diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c index 04845e43df15..37670db64855 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c @@ -283,8 +283,8 @@ static enum mod_hdcp_status wait_for_ready(struct mod_hdcp *hdcp, hdcp, "bstatus_read")) goto out; if (!mod_hdcp_execute_and_set(check_link_integrity_dp, - &input->link_integiry_check, &status, - hdcp, "link_integiry_check")) + &input->link_integrity_check, &status, + hdcp, "link_integrity_check")) goto out; if (!mod_hdcp_execute_and_set(check_no_reauthentication_request_dp, &input->reauth_request_check, &status, @@ -431,8 +431,8 @@ static enum mod_hdcp_status authenticated_dp(struct mod_hdcp *hdcp, hdcp, "bstatus_read")) goto out; if (!mod_hdcp_execute_and_set(check_link_integrity_dp, - &input->link_integiry_check, &status, - hdcp, "link_integiry_check")) + &input->link_integrity_check, &status, + hdcp, "link_integrity_check")) goto out; if (!mod_hdcp_execute_and_set(check_no_reauthentication_request_dp, &input->reauth_request_check, &status, diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_transition.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_transition.c index 136b8011ff3f..76edcbe51f71 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_transition.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_transition.c @@ -67,11 +67,19 @@ enum mod_hdcp_status mod_hdcp_hdcp1_transition(struct mod_hdcp *hdcp, break; case H1_A2_COMPUTATIONS_A3_VALIDATE_RX_A6_TEST_FOR_REPEATER: if (input->bcaps_read != PASS || - input->r0p_read != PASS || - input->rx_validation != PASS || - (!conn->is_repeater && input->encryption != PASS)) { + input->r0p_read != PASS) { + fail_and_restart_in_ms(0, &status, output); + break; + } else if (input->rx_validation != PASS) { /* 1A-06: consider invalid r0' a failure */ /* 1A-08: consider bksv listed in SRM a failure */ + /* + * some slow RX will fail rx validation when it is + * not ready. give it more time to react before retry. + */ + fail_and_restart_in_ms(1000, &status, output); + break; + } else if (!conn->is_repeater && input->encryption != PASS) { fail_and_restart_in_ms(0, &status, output); break; } @@ -212,7 +220,11 @@ enum mod_hdcp_status mod_hdcp_hdcp1_dp_transition(struct mod_hdcp *hdcp, * after 3 attempts. * 1A-08: consider bksv listed in SRM a failure */ - fail_and_restart_in_ms(0, &status, output); + /* + * some slow RX will fail rx validation when it is + * not ready. give it more time to react before retry. + */ + fail_and_restart_in_ms(1000, &status, output); } break; } else if ((!conn->is_repeater && input->encryption != PASS) || @@ -229,7 +241,7 @@ enum mod_hdcp_status mod_hdcp_hdcp1_dp_transition(struct mod_hdcp *hdcp, } break; case D1_A4_AUTHENTICATED: - if (input->link_integiry_check != PASS || + if (input->link_integrity_check != PASS || input->reauth_request_check != PASS) { /* 1A-07: restart hdcp on a link integrity failure */ fail_and_restart_in_ms(0, &status, output); @@ -237,7 +249,7 @@ enum mod_hdcp_status mod_hdcp_hdcp1_dp_transition(struct mod_hdcp *hdcp, } break; case D1_A6_WAIT_FOR_READY: - if (input->link_integiry_check == FAIL || + if (input->link_integrity_check == FAIL || input->reauth_request_check == FAIL) { fail_and_restart_in_ms(0, &status, output); break; diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_transition.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_transition.c index e8043c903a84..8cae3e3aacd5 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_transition.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_transition.c @@ -114,7 +114,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_transition(struct mod_hdcp *hdcp, if (event_ctx->event == MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) { /* 1A-11-3: consider h' timeout a failure */ - fail_and_restart_in_ms(0, &status, output); + fail_and_restart_in_ms(1000, &status, output); } else { /* continue h' polling */ callback_in_ms(100, output); @@ -166,7 +166,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_transition(struct mod_hdcp *hdcp, if (event_ctx->event == MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) { /* 1A-11-2: consider h' timeout a failure */ - fail_and_restart_in_ms(0, &status, output); + fail_and_restart_in_ms(1000, &status, output); } else { /* continue h' polling */ callback_in_ms(20, output); @@ -439,7 +439,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_dp_transition(struct mod_hdcp *hdcp, if (event_ctx->event == MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) /* 1A-10-3: consider h' timeout a failure */ - fail_and_restart_in_ms(0, &status, output); + fail_and_restart_in_ms(1000, &status, output); else increment_stay_counter(hdcp); break; @@ -484,7 +484,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_dp_transition(struct mod_hdcp *hdcp, if (event_ctx->event == MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) /* 1A-10-2: consider h' timeout a failure */ - fail_and_restart_in_ms(0, &status, output); + fail_and_restart_in_ms(1000, &status, output); else increment_stay_counter(hdcp); break; @@ -630,7 +630,10 @@ enum mod_hdcp_status mod_hdcp_hdcp2_dp_transition(struct mod_hdcp *hdcp, break; } else if (input->prepare_stream_manage != PASS || input->stream_manage_write != PASS) { - fail_and_restart_in_ms(0, &status, output); + if (event_ctx->event == MOD_HDCP_EVENT_CALLBACK) + fail_and_restart_in_ms(0, &status, output); + else + increment_stay_counter(hdcp); break; } callback_in_ms(100, output); @@ -655,10 +658,12 @@ enum mod_hdcp_status mod_hdcp_hdcp2_dp_transition(struct mod_hdcp *hdcp, */ if (hdcp->auth.count.stream_management_retry_count > 10) { fail_and_restart_in_ms(0, &status, output); - } else { + } else if (event_ctx->event == MOD_HDCP_EVENT_CALLBACK) { hdcp->auth.count.stream_management_retry_count++; callback_in_ms(0, output); set_state_id(hdcp, output, D2_A9_SEND_STREAM_MANAGEMENT); + } else { + increment_stay_counter(hdcp); } break; } diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c index ef4eb55f4474..7911dc157d5a 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c @@ -145,10 +145,11 @@ enum mod_hdcp_status mod_hdcp_hdcp1_create_session(struct mod_hdcp *hdcp) psp_hdcp_invoke(psp, hdcp_cmd->cmd_id); + hdcp->auth.id = hdcp_cmd->out_msg.hdcp1_create_session.session_handle; + if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS) return MOD_HDCP_STATUS_HDCP1_CREATE_SESSION_FAILURE; - hdcp->auth.id = hdcp_cmd->out_msg.hdcp1_create_session.session_handle; hdcp->auth.msg.hdcp1.ainfo = hdcp_cmd->out_msg.hdcp1_create_session.ainfo_primary; memcpy(hdcp->auth.msg.hdcp1.aksv, hdcp_cmd->out_msg.hdcp1_create_session.aksv_primary, sizeof(hdcp->auth.msg.hdcp1.aksv)); @@ -510,7 +511,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_validate_h_prime(struct mod_hdcp *hdcp) psp_hdcp_invoke(psp, hdcp_cmd->cmd_id); if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS) - return MOD_HDCP_STATUS_HDCP2_VALIDATE_AKE_CERT_FAILURE; + return MOD_HDCP_STATUS_HDCP2_VALIDATE_H_PRIME_FAILURE; if (msg_out->process.msg1_status != TA_HDCP2_MSG_AUTHENTICATION_STATUS__SUCCESS) return MOD_HDCP_STATUS_HDCP2_VALIDATE_H_PRIME_FAILURE; @@ -794,7 +795,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_validate_stream_ready(struct mod_hdcp *hdcp) hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_PREPARE_PROCESS_AUTHENTICATION_MSG_V2; psp_hdcp_invoke(psp, hdcp_cmd->cmd_id); - return (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS) && + return (hdcp_cmd->hdcp_status == TA_HDCP_STATUS__SUCCESS) && (msg_out->process.msg1_status == TA_HDCP2_MSG_AUTHENTICATION_STATUS__SUCCESS) ? MOD_HDCP_STATUS_SUCCESS : MOD_HDCP_STATUS_HDCP2_VALIDATE_STREAM_READY_FAILURE; diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h b/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h index dc187844d10b..dbe7835aabcf 100644 --- a/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h +++ b/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h @@ -92,6 +92,7 @@ struct mod_vrr_params_btr { uint32_t inserted_duration_in_us; uint32_t frames_to_insert; uint32_t frame_counter; + uint32_t margin_in_us; }; struct mod_vrr_params_fixed_refresh { diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c index 4e2f615c3566..e75a4bb94488 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c +++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c @@ -662,7 +662,11 @@ bool dmcu_load_iram(struct dmcu *dmcu, memset(&ram_table, 0, sizeof(ram_table)); - if (dmcu->dmcu_version.abm_version == 0x23) { + if (dmcu->dmcu_version.abm_version == 0x24) { + fill_iram_v_2_3((struct iram_table_v_2_2 *)ram_table, params); + result = dmcu->funcs->load_iram( + dmcu, 0, (char *)(&ram_table), IRAM_RESERVE_AREA_START_V2_2); + } else if (dmcu->dmcu_version.abm_version == 0x23) { fill_iram_v_2_3((struct iram_table_v_2_2 *)ram_table, params); result = dmcu->funcs->load_iram( @@ -687,3 +691,4 @@ bool dmcu_load_iram(struct dmcu *dmcu, return result; } + |