diff options
Diffstat (limited to 'drivers/gpu/drm')
130 files changed, 1066 insertions, 475 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c index 7e59e473a190..cdea1338c8dc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c @@ -152,7 +152,7 @@ static uint32_t get_sdma_rlc_reg_offset(struct amdgpu_device *adev, dev_warn(adev->dev, "Invalid sdma engine id (%d), using engine id 0\n", engine_id); - /* fall through */ + fallthrough; case 0: sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 0047da06041f..414548064648 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -179,6 +179,7 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags) case CHIP_VEGA20: case CHIP_ARCTURUS: case CHIP_SIENNA_CICHLID: + case CHIP_NAVY_FLOUNDER: /* enable runpm if runpm=1 */ if (amdgpu_runtime_pm > 0) adev->runpm = true; @@ -678,8 +679,12 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file * in the bitfields */ if (se_num == AMDGPU_INFO_MMR_SE_INDEX_MASK) se_num = 0xffffffff; + else if (se_num >= AMDGPU_GFX_MAX_SE) + return -EINVAL; if (sh_num == AMDGPU_INFO_MMR_SH_INDEX_MASK) sh_num = 0xffffffff; + else if (sh_num >= AMDGPU_GFX_MAX_SH_PER_SE) + return -EINVAL; if (info->read_mmr_reg.count > 128) return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 7fe564275457..06757681b2ce 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -178,7 +178,7 @@ static int psp_sw_init(void *handle) return ret; } - if (adev->asic_type == CHIP_NAVI10) { + if (adev->asic_type == CHIP_NAVI10 || adev->asic_type == CHIP_SIENNA_CICHLID) { ret= psp_sysfs_init(adev); if (ret) { return ret; @@ -522,8 +522,7 @@ static int psp_asd_load(struct psp_context *psp) * add workaround to bypass it for sriov now. * TODO: add version check to make it common */ - if (amdgpu_sriov_vf(psp->adev) || - (psp->adev->asic_type == CHIP_NAVY_FLOUNDER)) + if (amdgpu_sriov_vf(psp->adev) || !psp->asd_fw) return 0; cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 65997ffaed45..037a187aa42f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -7263,10 +7263,8 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE); data &= ~(RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK | RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGCG_OVERRIDE_MASK | - RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK); - - /* only for Vega10 & Raven1 */ - data |= RLC_CGTT_MGCG_OVERRIDE__RLC_CGTT_SCLK_OVERRIDE_MASK; + RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK | + RLC_CGTT_MGCG_OVERRIDE__ENABLE_CGTS_LEGACY_MASK); if (def != data) WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 33f1c4a46ebe..88f63d7ea371 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -3250,7 +3250,7 @@ static void gfx_v8_0_tiling_mode_table_init(struct amdgpu_device *adev) dev_warn(adev->dev, "Unknown chip type (%d) in function gfx_v8_0_tiling_mode_table_init() falling through to CHIP_CARRIZO\n", adev->asic_type); - /* fall through */ + fallthrough; case CHIP_CARRIZO: modearray[0] = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) | diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 6e4f3ff4810f..b67ba38a195f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1297,7 +1297,7 @@ static void gmc_v9_0_init_golden_registers(struct amdgpu_device *adev) case CHIP_VEGA10: if (amdgpu_sriov_vf(adev)) break; - /* fall through */ + fallthrough; case CHIP_VEGA20: soc15_program_register_sequence(adev, golden_settings_mmhub_1_0_0, diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index da8024c2826e..ca11253e787c 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -364,6 +364,7 @@ nv_asic_reset_method(struct amdgpu_device *adev) switch (adev->asic_type) { case CHIP_SIENNA_CICHLID: + case CHIP_NAVY_FLOUNDER: return AMD_RESET_METHOD_MODE1; default: if (smu_baco_is_support(smu)) diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c index e16874f30d5d..6c5d9612abcb 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c @@ -58,7 +58,7 @@ MODULE_FIRMWARE("amdgpu/arcturus_ta.bin"); MODULE_FIRMWARE("amdgpu/sienna_cichlid_sos.bin"); MODULE_FIRMWARE("amdgpu/sienna_cichlid_ta.bin"); MODULE_FIRMWARE("amdgpu/navy_flounder_sos.bin"); -MODULE_FIRMWARE("amdgpu/navy_flounder_asd.bin"); +MODULE_FIRMWARE("amdgpu/navy_flounder_ta.bin"); /* address block */ #define smnMP1_FIRMWARE_FLAGS 0x3010024 diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c index ea914b256ebd..b5986d19dc08 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c @@ -6196,7 +6196,7 @@ static void si_request_link_speed_change_before_state_change(struct amdgpu_devic si_pi->force_pcie_gen = AMDGPU_PCIE_GEN2; if (current_link_speed == AMDGPU_PCIE_GEN2) break; - /* fall through */ + fallthrough; case AMDGPU_PCIE_GEN2: if (amdgpu_acpi_pcie_performance_request(adev, PCIE_PERF_REQ_PECI_GEN2, false) == 0) break; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index e0e60b0d0669..0f4508b4903e 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -1216,6 +1216,8 @@ static int stop_cpsch(struct device_queue_manager *dqm) dqm->sched_running = false; dqm_unlock(dqm); + pm_release_ib(&dqm->packets); + kfd_gtt_sa_free(dqm->dev, dqm->fence_mem); pm_uninit(&dqm->packets, hanging); @@ -1326,7 +1328,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q, if (q->properties.is_active) { increment_queue_count(dqm, q->properties.type); - retval = execute_queues_cpsch(dqm, + execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); } 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 df9338257ae0..4ba8b54a2695 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2834,12 +2834,18 @@ static int amdgpu_dm_mode_config_init(struct amdgpu_device *adev) &dm_atomic_state_funcs); r = amdgpu_display_modeset_create_props(adev); - if (r) + if (r) { + dc_release_state(state->context); + kfree(state); return r; + } r = amdgpu_dm_audio_init(adev); - if (r) + if (r) { + dc_release_state(state->context); + kfree(state); return r; + } return 0; } @@ -2856,6 +2862,8 @@ static void amdgpu_dm_update_backlight_caps(struct amdgpu_display_manager *dm) #if defined(CONFIG_ACPI) struct amdgpu_dm_backlight_caps caps; + memset(&caps, 0, sizeof(caps)); + if (dm->backlight_caps.caps_valid) return; @@ -2894,51 +2902,50 @@ static int set_backlight_via_aux(struct dc_link *link, uint32_t brightness) return rc ? 0 : 1; } -static u32 convert_brightness(const struct amdgpu_dm_backlight_caps *caps, - const uint32_t user_brightness) +static int get_brightness_range(const struct amdgpu_dm_backlight_caps *caps, + unsigned *min, unsigned *max) { - u32 min, max, conversion_pace; - u32 brightness = user_brightness; - if (!caps) - goto out; + return 0; - if (!caps->aux_support) { - max = caps->max_input_signal; - min = caps->min_input_signal; - /* - * The brightness input is in the range 0-255 - * It needs to be rescaled to be between the - * requested min and max input signal - * It also needs to be scaled up by 0x101 to - * match the DC interface which has a range of - * 0 to 0xffff - */ - conversion_pace = 0x101; - brightness = - user_brightness - * conversion_pace - * (max - min) - / AMDGPU_MAX_BL_LEVEL - + min * conversion_pace; + if (caps->aux_support) { + // Firmware limits are in nits, DC API wants millinits. + *max = 1000 * caps->aux_max_input_signal; + *min = 1000 * caps->aux_min_input_signal; } else { - /* TODO - * We are doing a linear interpolation here, which is OK but - * does not provide the optimal result. We probably want - * something close to the Perceptual Quantizer (PQ) curve. - */ - max = caps->aux_max_input_signal; - min = caps->aux_min_input_signal; - - brightness = (AMDGPU_MAX_BL_LEVEL - user_brightness) * min - + user_brightness * max; - // Multiple the value by 1000 since we use millinits - brightness *= 1000; - brightness = DIV_ROUND_CLOSEST(brightness, AMDGPU_MAX_BL_LEVEL); + // Firmware limits are 8-bit, PWM control is 16-bit. + *max = 0x101 * caps->max_input_signal; + *min = 0x101 * caps->min_input_signal; } + return 1; +} + +static u32 convert_brightness_from_user(const struct amdgpu_dm_backlight_caps *caps, + uint32_t brightness) +{ + unsigned min, max; + + if (!get_brightness_range(caps, &min, &max)) + return brightness; + + // Rescale 0..255 to min..max + return min + DIV_ROUND_CLOSEST((max - min) * brightness, + AMDGPU_MAX_BL_LEVEL); +} + +static u32 convert_brightness_to_user(const struct amdgpu_dm_backlight_caps *caps, + uint32_t brightness) +{ + unsigned min, max; + + if (!get_brightness_range(caps, &min, &max)) + return brightness; -out: - return brightness; + if (brightness < min) + return 0; + // Rescale min..max to 0..255 + return DIV_ROUND_CLOSEST(AMDGPU_MAX_BL_LEVEL * (brightness - min), + max - min); } static int amdgpu_dm_backlight_update_status(struct backlight_device *bd) @@ -2954,7 +2961,7 @@ static int amdgpu_dm_backlight_update_status(struct backlight_device *bd) link = (struct dc_link *)dm->backlight_link; - brightness = convert_brightness(&caps, bd->props.brightness); + brightness = convert_brightness_from_user(&caps, bd->props.brightness); // Change brightness based on AUX property if (caps.aux_support) return set_backlight_via_aux(link, brightness); @@ -2971,7 +2978,7 @@ static int amdgpu_dm_backlight_get_brightness(struct backlight_device *bd) if (ret == DC_ERROR_UNEXPECTED) return bd->props.brightness; - return ret; + return convert_brightness_to_user(&dm->backlight_caps, ret); } static const struct backlight_ops amdgpu_dm_backlight_ops = { @@ -5271,19 +5278,6 @@ static void dm_crtc_helper_disable(struct drm_crtc *crtc) { } -static bool does_crtc_have_active_cursor(struct drm_crtc_state *new_crtc_state) -{ - struct drm_device *dev = new_crtc_state->crtc->dev; - struct drm_plane *plane; - - drm_for_each_plane_mask(plane, dev, new_crtc_state->plane_mask) { - if (plane->type == DRM_PLANE_TYPE_CURSOR) - return true; - } - - return false; -} - static int count_crtc_active_planes(struct drm_crtc_state *new_crtc_state) { struct drm_atomic_state *state = new_crtc_state->state; @@ -5347,19 +5341,20 @@ static int dm_crtc_helper_atomic_check(struct drm_crtc *crtc, return ret; } - /* In some use cases, like reset, no stream is attached */ - if (!dm_crtc_state->stream) - return 0; - /* - * We want at least one hardware plane enabled to use - * the stream with a cursor enabled. + * We require the primary plane to be enabled whenever the CRTC is, otherwise + * drm_mode_cursor_universal may end up trying to enable the cursor plane while all other + * planes are disabled, which is not supported by the hardware. And there is legacy + * userspace which stops using the HW cursor altogether in response to the resulting EINVAL. */ - if (state->enable && state->active && - does_crtc_have_active_cursor(state) && - dm_crtc_state->active_planes == 0) + if (state->enable && + !(state->plane_mask & drm_plane_mask(crtc->primary))) return -EINVAL; + /* In some use cases, like reset, no stream is attached */ + if (!dm_crtc_state->stream) + return 0; + if (dc_validate_stream(dc, dm_crtc_state->stream) == DC_OK) return 0; 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 e85b58f0f416..336aaa09be46 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 @@ -67,7 +67,7 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux, result = dc_link_aux_transfer_raw(TO_DM_AUX(aux)->ddc_service, &payload, &operation_result); - if (payload.write) + if (payload.write && result >= 0) result = msg->size; if (result < 0) 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 c664404a75d4..543afa34d87a 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 @@ -94,6 +94,15 @@ int rn_get_active_display_cnt_wa( return display_count; } +void rn_set_low_power_state(struct clk_mgr *clk_mgr_base) +{ + struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base); + + rn_vbios_smu_set_dcn_low_power_state(clk_mgr, DCN_PWR_STATE_LOW_POWER); + /* update power state */ + clk_mgr_base->clks.pwr_state = DCN_PWR_STATE_LOW_POWER; +} + void rn_update_clocks(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool safe_to_lower) @@ -516,6 +525,7 @@ static struct clk_mgr_funcs dcn21_funcs = { .init_clocks = rn_init_clocks, .enable_pme_wa = rn_enable_pme_wa, .are_clock_states_equal = rn_are_clock_states_equal, + .set_low_power_state = rn_set_low_power_state, .notify_wm_ranges = rn_notify_wm_ranges, .notify_link_rate_change = rn_notify_link_rate_change, }; 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 117d8aaf2a9b..437d1a7a16fe 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -763,6 +763,7 @@ static bool detect_dp(struct dc_link *link, sink_caps->signal = dp_passive_dongle_detection(link->ddc, sink_caps, audio_support); + link->dpcd_caps.dongle_type = sink_caps->dongle_type; } return true; @@ -3286,10 +3287,10 @@ void core_link_disable_stream(struct pipe_ctx *pipe_ctx) core_link_set_avmute(pipe_ctx, true); } - dc->hwss.blank_stream(pipe_ctx); #if defined(CONFIG_DRM_AMD_DC_HDCP) update_psp_stream_config(pipe_ctx, true); #endif + dc->hwss.blank_stream(pipe_ctx); if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) deallocate_mst_payload(pipe_ctx); 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 9bc03f26efda..b2be6ad5101d 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 @@ -4409,9 +4409,9 @@ bool dc_link_get_backlight_level_nits(struct dc_link *link, link->connector_signal != SIGNAL_TYPE_DISPLAY_PORT)) return false; - if (!core_link_read_dpcd(link, DP_SOURCE_BACKLIGHT_CURRENT_PEAK, + if (core_link_read_dpcd(link, DP_SOURCE_BACKLIGHT_CURRENT_PEAK, dpcd_backlight_get.raw, - sizeof(union dpcd_source_backlight_get))) + sizeof(union dpcd_source_backlight_get)) != DC_OK) return false; *backlight_millinits_avg = @@ -4450,9 +4450,9 @@ bool dc_link_read_default_bl_aux(struct dc_link *link, uint32_t *backlight_milli link->connector_signal != SIGNAL_TYPE_DISPLAY_PORT)) return false; - if (!core_link_read_dpcd(link, DP_SOURCE_BACKLIGHT_LEVEL, + if (core_link_read_dpcd(link, DP_SOURCE_BACKLIGHT_LEVEL, (uint8_t *) backlight_millinits, - sizeof(uint32_t))) + sizeof(uint32_t)) != DC_OK) return false; return true; diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index 633442bc7ef2..d9888f316da6 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -233,7 +233,7 @@ struct dc_stream_state { union stream_update_flags update_flags; }; -#define ABM_LEVEL_IMMEDIATE_DISABLE 0xFFFFFFFF +#define ABM_LEVEL_IMMEDIATE_DISABLE 255 struct dc_stream_update { struct dc_stream_state *stream; 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 a643927e272b..fa643ec5a876 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 @@ -1450,33 +1450,42 @@ void dcn10_init_hw(struct dc *dc) void dcn10_power_down_on_boot(struct dc *dc) { int i = 0; + struct dc_link *edp_link; - if (dc->config.power_down_display_on_boot) { - struct dc_link *edp_link = get_edp_link(dc); - - if (edp_link && - edp_link->link_enc->funcs->is_dig_enabled && - edp_link->link_enc->funcs->is_dig_enabled(edp_link->link_enc) && - dc->hwseq->funcs.edp_backlight_control && - dc->hwss.power_down && - dc->hwss.edp_power_control) { - dc->hwseq->funcs.edp_backlight_control(edp_link, false); - dc->hwss.power_down(dc); - dc->hwss.edp_power_control(edp_link, false); - } else { - for (i = 0; i < dc->link_count; i++) { - struct dc_link *link = dc->links[i]; - - if (link->link_enc->funcs->is_dig_enabled && - link->link_enc->funcs->is_dig_enabled(link->link_enc) && - dc->hwss.power_down) { - dc->hwss.power_down(dc); - break; - } + if (!dc->config.power_down_display_on_boot) + return; + + edp_link = get_edp_link(dc); + if (edp_link && + edp_link->link_enc->funcs->is_dig_enabled && + edp_link->link_enc->funcs->is_dig_enabled(edp_link->link_enc) && + dc->hwseq->funcs.edp_backlight_control && + dc->hwss.power_down && + dc->hwss.edp_power_control) { + dc->hwseq->funcs.edp_backlight_control(edp_link, false); + dc->hwss.power_down(dc); + dc->hwss.edp_power_control(edp_link, false); + } else { + for (i = 0; i < dc->link_count; i++) { + struct dc_link *link = dc->links[i]; + if (link->link_enc->funcs->is_dig_enabled && + link->link_enc->funcs->is_dig_enabled(link->link_enc) && + dc->hwss.power_down) { + dc->hwss.power_down(dc); + break; } + } } + + /* + * Call update_clocks with empty context + * to send DISPLAY_OFF + * Otherwise DISPLAY_OFF may not be asserted + */ + if (dc->clk_mgr->funcs->set_low_power_state) + dc->clk_mgr->funcs->set_low_power_state(dc->clk_mgr); } void dcn10_reset_hw_ctx_wrap( diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c index 17d5cb422025..8939541ad7af 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c @@ -1213,6 +1213,7 @@ static enum dc_status dcn10_validate_global(struct dc *dc, struct dc_state *cont bool video_large = false; bool desktop_large = false; bool dcc_disabled = false; + bool mpo_enabled = false; for (i = 0; i < context->stream_count; i++) { if (context->stream_status[i].plane_count == 0) @@ -1221,6 +1222,9 @@ static enum dc_status dcn10_validate_global(struct dc *dc, struct dc_state *cont if (context->stream_status[i].plane_count > 2) return DC_FAIL_UNSUPPORTED_1; + if (context->stream_status[i].plane_count > 1) + mpo_enabled = true; + for (j = 0; j < context->stream_status[i].plane_count; j++) { struct dc_plane_state *plane = context->stream_status[i].plane_states[j]; @@ -1244,6 +1248,10 @@ static enum dc_status dcn10_validate_global(struct dc *dc, struct dc_state *cont } } + /* Disable MPO in multi-display configurations. */ + if (context->stream_count > 1 && mpo_enabled) + return DC_FAIL_UNSUPPORTED_1; + /* * Workaround: On DCN10 there is UMC issue that causes underflow when * playing 4k video on 4k desktop with video downscaled and single channel 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 9140b3fc767a..f31f48dd0da2 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -409,8 +409,8 @@ static struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv14_soc = { }, }, .num_states = 5, - .sr_exit_time_us = 8.6, - .sr_enter_plus_exit_time_us = 10.9, + .sr_exit_time_us = 11.6, + .sr_enter_plus_exit_time_us = 13.9, .urgent_latency_us = 4.0, .urgent_latency_pixel_data_only_us = 4.0, .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h index 5994d2a33c40..947d6106f341 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h @@ -230,6 +230,8 @@ struct clk_mgr_funcs { int (*get_dp_ref_clk_frequency)(struct clk_mgr *clk_mgr); + void (*set_low_power_state)(struct clk_mgr *clk_mgr); + void (*init_clocks)(struct clk_mgr *clk_mgr); void (*enable_pme_wa) (struct clk_mgr *clk_mgr); diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h index d3192b9d0c3d..47f8ee2832ff 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h @@ -27,7 +27,7 @@ #define MOD_HDCP_LOG_H_ #ifdef CONFIG_DRM_AMD_DC_HDCP -#define HDCP_LOG_ERR(hdcp, ...) DRM_WARN(__VA_ARGS__) +#define HDCP_LOG_ERR(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__) #define HDCP_LOG_VER(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__) #define HDCP_LOG_FSM(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__) #define HDCP_LOG_TOP(hdcp, ...) pr_debug("[HDCP_TOP]:"__VA_ARGS__) 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 fb1161dd7ea8..3a367a5968ae 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c @@ -88,7 +88,7 @@ enum mod_hdcp_status mod_hdcp_add_display_to_topology(struct mod_hdcp *hdcp, enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS; if (!psp->dtm_context.dtm_initialized) { - DRM_ERROR("Failed to add display topology, DTM TA is not initialized."); + DRM_INFO("Failed to add display topology, DTM TA is not initialized."); display->state = MOD_HDCP_DISPLAY_INACTIVE; return MOD_HDCP_STATUS_FAILURE; } diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c index 0826625573dc..63f945f9f331 100644 --- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c @@ -1126,7 +1126,7 @@ static int smu_disable_dpms(struct smu_context *smu) */ if (smu->uploading_custom_pp_table && (adev->asic_type >= CHIP_NAVI10) && - (adev->asic_type <= CHIP_NAVI12)) + (adev->asic_type <= CHIP_NAVY_FLOUNDER)) return 0; /* @@ -1211,7 +1211,9 @@ static int smu_hw_fini(void *handle) int smu_reset(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; - int ret = 0; + int ret; + + amdgpu_gfx_off_ctrl(smu->adev, false); ret = smu_hw_fini(adev); if (ret) @@ -1222,8 +1224,12 @@ int smu_reset(struct smu_context *smu) return ret; ret = smu_late_init(adev); + if (ret) + return ret; - return ret; + amdgpu_gfx_off_ctrl(smu->adev, true); + + return 0; } static int smu_suspend(void *handle) diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c index fb962b9ceffb..9582b38162f0 100644 --- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c @@ -1840,10 +1840,14 @@ static bool arcturus_is_dpm_running(struct smu_context *smu) { int ret = 0; uint32_t feature_mask[2]; - unsigned long feature_enabled; + uint64_t feature_enabled; + ret = smu_cmn_get_enabled_mask(smu, feature_mask, 2); - feature_enabled = (unsigned long)((uint64_t)feature_mask[0] | - ((uint64_t)feature_mask[1] << 32)); + if (ret) + return false; + + feature_enabled = (uint64_t)feature_mask[1] << 32 | feature_mask[0]; + return !!(feature_enabled & SMC_DPM_FEATURE); } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c index c9cfe90a2947..9ee8cf8267c8 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c @@ -204,8 +204,7 @@ static int smu10_set_min_deep_sleep_dcefclk(struct pp_hwmgr *hwmgr, uint32_t clo { struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend); - if (smu10_data->need_min_deep_sleep_dcefclk && - smu10_data->deep_sleep_dcefclk != clock) { + if (clock && smu10_data->deep_sleep_dcefclk != clock) { smu10_data->deep_sleep_dcefclk = clock; smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetMinDeepSleepDcefclk, @@ -219,8 +218,7 @@ static int smu10_set_hard_min_dcefclk_by_freq(struct pp_hwmgr *hwmgr, uint32_t c { struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend); - if (smu10_data->dcf_actual_hard_min_freq && - smu10_data->dcf_actual_hard_min_freq != clock) { + if (clock && smu10_data->dcf_actual_hard_min_freq != clock) { smu10_data->dcf_actual_hard_min_freq = clock; smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinDcefclkByFreq, @@ -234,8 +232,7 @@ static int smu10_set_hard_min_fclk_by_freq(struct pp_hwmgr *hwmgr, uint32_t cloc { struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend); - if (smu10_data->f_actual_hard_min_freq && - smu10_data->f_actual_hard_min_freq != clock) { + if (clock && smu10_data->f_actual_hard_min_freq != clock) { smu10_data->f_actual_hard_min_freq = clock; smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinFclkByFreq, diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index ffe05b7cc1f0..4a3b64aa21ce 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -3581,7 +3581,8 @@ static int smu7_read_sensor(struct pp_hwmgr *hwmgr, int idx, case AMDGPU_PP_SENSOR_GPU_POWER: return smu7_get_gpu_power(hwmgr, (uint32_t *)value); case AMDGPU_PP_SENSOR_VDDGFX: - if ((data->vr_config & 0xff) == 0x2) + if ((data->vr_config & VRCONF_VDDGFX_MASK) == + (VR_SVI2_PLANE_2 << VRCONF_VDDGFX_SHIFT)) val_vid = PHM_READ_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_SVI2_STATUS, PLANE2_VID); else diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c index 468bdd6f6697..952cd3d7240e 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c @@ -363,17 +363,29 @@ int vega10_thermal_get_temperature(struct pp_hwmgr *hwmgr) static int vega10_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, struct PP_TemperatureRange *range) { + struct phm_ppt_v2_information *pp_table_info = + (struct phm_ppt_v2_information *)(hwmgr->pptable); + struct phm_tdp_table *tdp_table = pp_table_info->tdp_table; struct amdgpu_device *adev = hwmgr->adev; - int low = VEGA10_THERMAL_MINIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; - int high = VEGA10_THERMAL_MAXIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + int low = VEGA10_THERMAL_MINIMUM_ALERT_TEMP; + int high = VEGA10_THERMAL_MAXIMUM_ALERT_TEMP; uint32_t val; - if (low < range->min) - low = range->min; - if (high > range->max) - high = range->max; + /* compare them in unit celsius degree */ + if (low < range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES) + low = range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + + /* + * As a common sense, usSoftwareShutdownTemp should be bigger + * than ThotspotLimit. For any invalid usSoftwareShutdownTemp, + * we will just use the max possible setting VEGA10_THERMAL_MAXIMUM_ALERT_TEMP + * to avoid false alarms. + */ + if ((tdp_table->usSoftwareShutdownTemp > + range->hotspot_crit_max / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)) { + if (high > tdp_table->usSoftwareShutdownTemp) + high = tdp_table->usSoftwareShutdownTemp; + } if (low > high) return -EINVAL; @@ -382,8 +394,8 @@ static int vega10_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, MAX_IH_CREDIT, 5); val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1); - val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); - val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); + val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, high); + val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, low); val &= (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK) & (~THM_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK) & (~THM_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK); diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c index c15b9756025d..7ace439dcde7 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c @@ -170,17 +170,18 @@ int vega12_thermal_get_temperature(struct pp_hwmgr *hwmgr) static int vega12_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, struct PP_TemperatureRange *range) { + struct phm_ppt_v3_information *pptable_information = + (struct phm_ppt_v3_information *)hwmgr->pptable; struct amdgpu_device *adev = hwmgr->adev; - int low = VEGA12_THERMAL_MINIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; - int high = VEGA12_THERMAL_MAXIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + int low = VEGA12_THERMAL_MINIMUM_ALERT_TEMP; + int high = VEGA12_THERMAL_MAXIMUM_ALERT_TEMP; uint32_t val; - if (low < range->min) - low = range->min; - if (high > range->max) - high = range->max; + /* compare them in unit celsius degree */ + if (low < range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES) + low = range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + if (high > pptable_information->us_software_shutdown_temp) + high = pptable_information->us_software_shutdown_temp; if (low > high) return -EINVAL; @@ -189,8 +190,8 @@ static int vega12_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, MAX_IH_CREDIT, 5); val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1); - val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); - val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); + val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, high); + val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, low); val = val & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK); WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL, val); diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c index 7add2f60f49c..364162ddaa9c 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c @@ -240,17 +240,18 @@ int vega20_thermal_get_temperature(struct pp_hwmgr *hwmgr) static int vega20_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, struct PP_TemperatureRange *range) { + struct phm_ppt_v3_information *pptable_information = + (struct phm_ppt_v3_information *)hwmgr->pptable; struct amdgpu_device *adev = hwmgr->adev; - int low = VEGA20_THERMAL_MINIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; - int high = VEGA20_THERMAL_MAXIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + int low = VEGA20_THERMAL_MINIMUM_ALERT_TEMP; + int high = VEGA20_THERMAL_MAXIMUM_ALERT_TEMP; uint32_t val; - if (low < range->min) - low = range->min; - if (high > range->max) - high = range->max; + /* compare them in unit celsius degree */ + if (low < range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES) + low = range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + if (high > pptable_information->us_software_shutdown_temp) + high = pptable_information->us_software_shutdown_temp; if (low > high) return -EINVAL; @@ -259,8 +260,8 @@ static int vega20_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, MAX_IH_CREDIT, 5); val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1); - val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); - val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); + val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, high); + val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, low); val = val & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK); WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL, val); diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c index 9f62af9abd23..3d5eae956a23 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c @@ -1331,10 +1331,14 @@ static bool navi10_is_dpm_running(struct smu_context *smu) { int ret = 0; uint32_t feature_mask[2]; - unsigned long feature_enabled; + uint64_t feature_enabled; + ret = smu_cmn_get_enabled_mask(smu, feature_mask, 2); - feature_enabled = (unsigned long)((uint64_t)feature_mask[0] | - ((uint64_t)feature_mask[1] << 32)); + if (ret) + return false; + + feature_enabled = (uint64_t)feature_mask[1] << 32 | feature_mask[0]; + return !!(feature_enabled & SMC_DPM_FEATURE); } diff --git a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c index 3865dbed5f93..61f4ddae262d 100644 --- a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c @@ -68,7 +68,8 @@ FEATURE_MASK(FEATURE_DPM_LINK_BIT) | \ FEATURE_MASK(FEATURE_DPM_SOCCLK_BIT) | \ FEATURE_MASK(FEATURE_DPM_FCLK_BIT) | \ - FEATURE_MASK(FEATURE_DPM_DCEFCLK_BIT)) + FEATURE_MASK(FEATURE_DPM_DCEFCLK_BIT) | \ + FEATURE_MASK(FEATURE_DPM_MP0CLK_BIT)) #define SMU_11_0_7_GFX_BUSY_THRESHOLD 15 @@ -95,6 +96,7 @@ static struct cmn2asic_msg_mapping sienna_cichlid_message_map[SMU_MSG_MAX_COUNT] MSG_MAP(TransferTableSmu2Dram, PPSMC_MSG_TransferTableSmu2Dram, 0), MSG_MAP(TransferTableDram2Smu, PPSMC_MSG_TransferTableDram2Smu, 0), MSG_MAP(UseDefaultPPTable, PPSMC_MSG_UseDefaultPPTable, 0), + MSG_MAP(RunDcBtc, PPSMC_MSG_RunDcBtc, 0), MSG_MAP(EnterBaco, PPSMC_MSG_EnterBaco, 0), MSG_MAP(SetSoftMinByFreq, PPSMC_MSG_SetSoftMinByFreq, 0), MSG_MAP(SetSoftMaxByFreq, PPSMC_MSG_SetSoftMaxByFreq, 0), @@ -228,6 +230,7 @@ sienna_cichlid_get_allowed_feature_mask(struct smu_context *smu, *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_PREFETCHER_BIT) | FEATURE_MASK(FEATURE_DPM_FCLK_BIT) + | FEATURE_MASK(FEATURE_DPM_MP0CLK_BIT) | FEATURE_MASK(FEATURE_DS_SOCCLK_BIT) | FEATURE_MASK(FEATURE_DS_DCEFCLK_BIT) | FEATURE_MASK(FEATURE_DS_FCLK_BIT) @@ -775,7 +778,7 @@ static int sienna_cichlid_dpm_set_vcn_enable(struct smu_context *smu, bool enabl ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_PowerUpVcn, 0, NULL); if (ret) return ret; - if (adev->asic_type == CHIP_SIENNA_CICHLID) { + if (adev->vcn.num_vcn_inst > 1) { ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_PowerUpVcn, 0x10000, NULL); if (ret) @@ -787,7 +790,7 @@ static int sienna_cichlid_dpm_set_vcn_enable(struct smu_context *smu, bool enabl ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_PowerDownVcn, 0, NULL); if (ret) return ret; - if (adev->asic_type == CHIP_SIENNA_CICHLID) { + if (adev->vcn.num_vcn_inst > 1) { ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_PowerDownVcn, 0x10000, NULL); if (ret) @@ -1146,10 +1149,14 @@ static bool sienna_cichlid_is_dpm_running(struct smu_context *smu) { int ret = 0; uint32_t feature_mask[2]; - unsigned long feature_enabled; + uint64_t feature_enabled; + ret = smu_cmn_get_enabled_mask(smu, feature_mask, 2); - feature_enabled = (unsigned long)((uint64_t)feature_mask[0] | - ((uint64_t)feature_mask[1] << 32)); + if (ret) + return false; + + feature_enabled = (uint64_t)feature_mask[1] << 32 | feature_mask[0]; + return !!(feature_enabled & SMC_DPM_FEATURE); } @@ -1732,6 +1739,11 @@ static int sienna_cichlid_get_dpm_ultimate_freq(struct smu_context *smu, return ret; } +static int sienna_cichlid_run_btc(struct smu_context *smu) +{ + return smu_cmn_send_smc_msg(smu, SMU_MSG_RunDcBtc, NULL); +} + static bool sienna_cichlid_is_baco_supported(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; @@ -2719,6 +2731,7 @@ static const struct pptable_funcs sienna_cichlid_ppt_funcs = { .mode1_reset = smu_v11_0_mode1_reset, .get_dpm_ultimate_freq = sienna_cichlid_get_dpm_ultimate_freq, .set_soft_freq_limited_range = smu_v11_0_set_soft_freq_limited_range, + .run_btc = sienna_cichlid_run_btc, .get_pp_feature_mask = smu_cmn_get_pp_feature_mask, .set_pp_feature_mask = smu_cmn_set_pp_feature_mask, }; diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c index c18169aa59ce..e4d1f3d66ef4 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c @@ -37,6 +37,7 @@ #include "cgs_common.h" #include "atombios.h" #include "pppcielanes.h" +#include "smu7_smumgr.h" #include "smu/smu_7_0_1_d.h" #include "smu/smu_7_0_1_sh_mask.h" @@ -2948,6 +2949,7 @@ const struct pp_smumgr_func ci_smu_funcs = { .request_smu_load_specific_fw = NULL, .send_msg_to_smc = ci_send_msg_to_smc, .send_msg_to_smc_with_parameter = ci_send_msg_to_smc_with_parameter, + .get_argument = smu7_get_argument, .download_pptable_settings = NULL, .upload_pptable_settings = NULL, .get_offsetof = ci_get_offsetof, diff --git a/drivers/gpu/drm/arm/malidp_hw.c b/drivers/gpu/drm/arm/malidp_hw.c index ca570b135478..e9de542f9b7c 100644 --- a/drivers/gpu/drm/arm/malidp_hw.c +++ b/drivers/gpu/drm/arm/malidp_hw.c @@ -532,7 +532,7 @@ static int malidp500_enable_memwrite(struct malidp_hw_device *hwdev, malidp_hw_write(hwdev, lower_32_bits(addrs[1]), base + MALIDP_MW_P2_PTR_LOW); malidp_hw_write(hwdev, upper_32_bits(addrs[1]), base + MALIDP_MW_P2_PTR_HIGH); malidp_hw_write(hwdev, pitches[1], base + MALIDP_MW_P2_STRIDE); - /* fall through */ + fallthrough; case 1: malidp_hw_write(hwdev, lower_32_bits(addrs[0]), base + MALIDP_MW_P1_PTR_LOW); malidp_hw_write(hwdev, upper_32_bits(addrs[0]), base + MALIDP_MW_P1_PTR_HIGH); @@ -869,7 +869,7 @@ static int malidp550_enable_memwrite(struct malidp_hw_device *hwdev, malidp_hw_write(hwdev, lower_32_bits(addrs[1]), base + MALIDP_MW_P2_PTR_LOW); malidp_hw_write(hwdev, upper_32_bits(addrs[1]), base + MALIDP_MW_P2_PTR_HIGH); malidp_hw_write(hwdev, pitches[1], base + MALIDP_MW_P2_STRIDE); - /* fall through */ + fallthrough; case 1: malidp_hw_write(hwdev, lower_32_bits(addrs[0]), base + MALIDP_MW_P1_PTR_LOW); malidp_hw_write(hwdev, upper_32_bits(addrs[0]), base + MALIDP_MW_P1_PTR_HIGH); @@ -1324,7 +1324,7 @@ static irqreturn_t malidp_se_irq(int irq, void *arg) break; case MW_RESTART: drm_writeback_signal_completion(&malidp->mw_connector, 0); - /* fall through - to a new start */ + fallthrough; /* to a new start */ case MW_START: /* writeback started, need to emulate one-shot mode */ hw->disable_memwrite(hwdev); diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c index dd12b55d57a2..6a9fba051d13 100644 --- a/drivers/gpu/drm/ast/ast_main.c +++ b/drivers/gpu/drm/ast/ast_main.c @@ -238,7 +238,7 @@ static int ast_detect_chip(struct drm_device *dev, bool *need_post) ast->dp501_fw_addr = NULL; } } - /* fallthrough */ + fallthrough; case 0x0c: ast->tx_chip_type = AST_TX_DP501; } diff --git a/drivers/gpu/drm/bridge/nwl-dsi.c b/drivers/gpu/drm/bridge/nwl-dsi.c index ce94f797d090..66b67402f1ac 100644 --- a/drivers/gpu/drm/bridge/nwl-dsi.c +++ b/drivers/gpu/drm/bridge/nwl-dsi.c @@ -409,7 +409,6 @@ static bool nwl_dsi_read_packet(struct nwl_dsi *dsi, u32 status) switch (data_type) { case MIPI_DSI_RX_GENERIC_SHORT_READ_RESPONSE_2BYTE: - fallthrough; case MIPI_DSI_RX_DCS_SHORT_READ_RESPONSE_2BYTE: if (xfer->msg->rx_len > 1) { /* read second byte */ @@ -418,7 +417,6 @@ static bool nwl_dsi_read_packet(struct nwl_dsi *dsi, u32 status) } fallthrough; case MIPI_DSI_RX_GENERIC_SHORT_READ_RESPONSE_1BYTE: - fallthrough; case MIPI_DSI_RX_DCS_SHORT_READ_RESPONSE_1BYTE: if (xfer->msg->rx_len > 0) { /* read first byte */ diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c index d7e65c869415..9fef6413741d 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c @@ -61,10 +61,10 @@ static int dw_hdmi_i2s_hw_params(struct device *dev, void *data, switch (hparms->channels) { case 7 ... 8: conf0 |= HDMI_AUD_CONF0_I2S_EN3; - /* Fall-thru */ + fallthrough; case 5 ... 6: conf0 |= HDMI_AUD_CONF0_I2S_EN2; - /* Fall-thru */ + fallthrough; case 3 ... 4: conf0 |= HDMI_AUD_CONF0_I2S_EN1; /* Fall-thru */ diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index 86b9f0f87a14..5b6e19ecbc84 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -604,13 +604,13 @@ static void ti_sn_bridge_read_valid_rates(struct ti_sn_bridge *pdata, DRM_DEV_ERROR(pdata->dev, "Unexpected max rate (%#x); assuming 5.4 GHz\n", (int)dpcd_val); - /* fall through */ + fallthrough; case DP_LINK_BW_5_4: rate_valid[7] = 1; - /* fall through */ + fallthrough; case DP_LINK_BW_2_7: rate_valid[4] = 1; - /* fall through */ + fallthrough; case DP_LINK_BW_1_62: rate_valid[1] = 1; break; diff --git a/drivers/gpu/drm/drm_bufs.c b/drivers/gpu/drm/drm_bufs.c index a0735fbc144b..7a01d0918861 100644 --- a/drivers/gpu/drm/drm_bufs.c +++ b/drivers/gpu/drm/drm_bufs.c @@ -537,7 +537,7 @@ int drm_legacy_rmmap_locked(struct drm_device *dev, struct drm_local_map *map) switch (map->type) { case _DRM_REGISTERS: iounmap(map->handle); - /* FALLTHROUGH */ + fallthrough; case _DRM_FRAME_BUFFER: arch_phys_wc_del(map->mtrr); break; diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index a3c82e726057..092c8c985911 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -492,7 +492,7 @@ int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE], case DP_DS_16BPC: return 16; } - /* fall through */ + fallthrough; default: return 0; } diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index 14b6f7638728..501b4fe55a3d 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -1930,7 +1930,7 @@ void drm_mode_convert_to_umode(struct drm_mode_modeinfo *out, default: WARN(1, "Invalid aspect ratio (0%x) on mode\n", in->picture_aspect_ratio); - /* fall through */ + fallthrough; case HDMI_PICTURE_ASPECT_NONE: out->flags |= DRM_MODE_FLAG_PIC_AR_NONE; break; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index d5a4cd85a0f6..c6404b8d067f 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -337,9 +337,16 @@ static void etnaviv_hw_identify(struct etnaviv_gpu *gpu) gpu->identity.model = gpu_read(gpu, VIVS_HI_CHIP_MODEL); gpu->identity.revision = gpu_read(gpu, VIVS_HI_CHIP_REV); - gpu->identity.product_id = gpu_read(gpu, VIVS_HI_CHIP_PRODUCT_ID); gpu->identity.customer_id = gpu_read(gpu, VIVS_HI_CHIP_CUSTOMER_ID); - gpu->identity.eco_id = gpu_read(gpu, VIVS_HI_CHIP_ECO_ID); + + /* + * Reading these two registers on GC600 rev 0x19 result in a + * unhandled fault: external abort on non-linefetch + */ + if (!etnaviv_is_model_rev(gpu, GC600, 0x19)) { + gpu->identity.product_id = gpu_read(gpu, VIVS_HI_CHIP_PRODUCT_ID); + gpu->identity.eco_id = gpu_read(gpu, VIVS_HI_CHIP_ECO_ID); + } /* * !!!! HACK ALERT !!!! diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index 4e3e95dce6d8..cd46c882269c 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -89,12 +89,15 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) u32 dma_addr; int change; + /* block scheduler */ + drm_sched_stop(&gpu->sched, sched_job); + /* * If the GPU managed to complete this jobs fence, the timout is * spurious. Bail out. */ if (dma_fence_is_signaled(submit->out_fence)) - return; + goto out_no_timeout; /* * If the GPU is still making forward progress on the front-end (which @@ -105,12 +108,9 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) change = dma_addr - gpu->hangcheck_dma_addr; if (change < 0 || change > 16) { gpu->hangcheck_dma_addr = dma_addr; - return; + goto out_no_timeout; } - /* block scheduler */ - drm_sched_stop(&gpu->sched, sched_job); - if(sched_job) drm_sched_increase_karma(sched_job); @@ -120,6 +120,7 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) drm_sched_resubmit_jobs(&gpu->sched); +out_no_timeout: /* restart scheduler after GPU is usable again */ drm_sched_start(&gpu->sched, true); } diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c index 7a6f6df5e954..b38e9b592b8a 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c @@ -987,10 +987,10 @@ static void exynos_dsi_send_to_fifo(struct exynos_dsi *dsi, switch (length) { case 3: reg |= payload[2] << 16; - /* Fall through */ + fallthrough; case 2: reg |= payload[1] << 8; - /* Fall through */ + fallthrough; case 1: reg |= payload[0]; exynos_dsi_write(dsi, DSIM_PAYLOAD_REG, reg); @@ -1038,7 +1038,7 @@ static void exynos_dsi_read_from_fifo(struct exynos_dsi *dsi, payload[1] = reg >> 16; ++xfer->rx_done; } - /* Fall through */ + fallthrough; case MIPI_DSI_RX_GENERIC_SHORT_READ_RESPONSE_1BYTE: case MIPI_DSI_RX_DCS_SHORT_READ_RESPONSE_1BYTE: payload[0] = reg >> 8; @@ -1082,10 +1082,10 @@ static void exynos_dsi_read_from_fifo(struct exynos_dsi *dsi, switch (length) { case 3: payload[2] = (reg >> 16) & 0xff; - /* Fall through */ + fallthrough; case 2: payload[1] = (reg >> 8) & 0xff; - /* Fall through */ + fallthrough; case 1: payload[0] = reg & 0xff; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c index 56a2b47e1af7..5147f5929be7 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c @@ -92,7 +92,7 @@ static int exynos_drm_fbdev_update(struct drm_fb_helper *helper, offset = fbi->var.xoffset * fb->format->cpp[0]; offset += fbi->var.yoffset * fb->pitches[0]; - fbi->screen_base = exynos_gem->kvaddr + offset; + fbi->screen_buffer = exynos_gem->kvaddr + offset; fbi->screen_size = size; fbi->fix.smem_len = size; diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.h b/drivers/gpu/drm/exynos/exynos_drm_gem.h index 7445748288da..74e926abeff0 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gem.h +++ b/drivers/gpu/drm/exynos/exynos_drm_gem.h @@ -40,7 +40,7 @@ struct exynos_drm_gem { unsigned int flags; unsigned long size; void *cookie; - void __iomem *kvaddr; + void *kvaddr; dma_addr_t dma_addr; unsigned long dma_attrs; struct sg_table *sgt; diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c index 86fac677fe69..3c6d9f3913d5 100644 --- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c +++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c @@ -101,19 +101,19 @@ static void fsl_dcu_drm_plane_atomic_update(struct drm_plane *plane, break; case DRM_FORMAT_ARGB8888: alpha = DCU_LAYER_AB_WHOLE_FRAME; - /* fall-through */ + fallthrough; case DRM_FORMAT_XRGB8888: bpp = FSL_DCU_ARGB8888; break; case DRM_FORMAT_ARGB4444: alpha = DCU_LAYER_AB_WHOLE_FRAME; - /* fall-through */ + fallthrough; case DRM_FORMAT_XRGB4444: bpp = FSL_DCU_ARGB4444; break; case DRM_FORMAT_ARGB1555: alpha = DCU_LAYER_AB_WHOLE_FRAME; - /* fall-through */ + fallthrough; case DRM_FORMAT_XRGB1555: bpp = FSL_DCU_ARGB1555; break; diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index 8c55f5bee9ab..f4053dd6bde9 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -712,7 +712,7 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder, switch (intel_dsi->pixel_format) { default: MISSING_CASE(intel_dsi->pixel_format); - /* fallthrough */ + fallthrough; case MIPI_DSI_FMT_RGB565: tmp |= PIX_FMT_RGB565; break; @@ -739,7 +739,7 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder, switch (intel_dsi->video_mode_format) { default: MISSING_CASE(intel_dsi->video_mode_format); - /* fallthrough */ + fallthrough; case VIDEO_MODE_NON_BURST_WITH_SYNC_EVENTS: tmp |= VIDEO_MODE_SYNC_EVENT; break; @@ -792,7 +792,7 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder, switch (pipe) { default: MISSING_CASE(pipe); - /* fallthrough */ + fallthrough; case PIPE_A: tmp |= TRANS_DDI_EDP_INPUT_A_ON; break; diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c index c53c85d38fa5..a0a41ec5c341 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -905,7 +905,7 @@ parse_psr(struct drm_i915_private *dev_priv, const struct bdb_header *bdb) drm_dbg_kms(&dev_priv->drm, "VBT tp1 wakeup time value %d is outside range[0-3], defaulting to max value 2500us\n", psr_table->tp1_wakeup_time); - /* fallthrough */ + fallthrough; case 2: dev_priv->vbt.psr.tp1_wakeup_time_us = 2500; break; @@ -925,7 +925,7 @@ parse_psr(struct drm_i915_private *dev_priv, const struct bdb_header *bdb) drm_dbg_kms(&dev_priv->drm, "VBT tp2_tp3 wakeup time value %d is outside range[0-3], defaulting to max value 2500us\n", psr_table->tp2_tp3_wakeup_time); - /* fallthrough */ + fallthrough; case 2: dev_priv->vbt.psr.tp2_tp3_wakeup_time_us = 2500; break; @@ -1775,7 +1775,7 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv, switch (child->hdmi_max_data_rate) { default: MISSING_CASE(child->hdmi_max_data_rate); - /* fall through */ + fallthrough; case HDMI_MAX_DATA_RATE_PLATFORM: max_tmds_clock = 0; break; diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index bb91dace304a..91a8161e7c05 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -326,7 +326,7 @@ static void pnv_get_cdclk(struct drm_i915_private *dev_priv, default: drm_err(&dev_priv->drm, "Unknown pnv display core clock 0x%04x\n", gcfgc); - /* fall through */ + fallthrough; case GC_DISPLAY_CLOCK_133_MHZ_PNV: cdclk_config->cdclk = 133333; break; @@ -766,7 +766,7 @@ static void bdw_set_cdclk(struct drm_i915_private *dev_priv, switch (cdclk) { default: MISSING_CASE(cdclk); - /* fall through */ + fallthrough; case 337500: val |= LCPLL_CLK_FREQ_337_5_BDW; break; @@ -1042,7 +1042,7 @@ static void skl_set_cdclk(struct drm_i915_private *dev_priv, drm_WARN_ON(&dev_priv->drm, cdclk != dev_priv->cdclk.hw.bypass); drm_WARN_ON(&dev_priv->drm, vco != 0); - /* fall through */ + fallthrough; case 308571: case 337500: freq_select = CDCLK_FREQ_337_308; @@ -1333,7 +1333,7 @@ static void icl_readout_refclk(struct drm_i915_private *dev_priv, switch (dssm) { default: MISSING_CASE(dssm); - /* fall through */ + fallthrough; case ICL_DSSM_CDCLK_PLL_REFCLK_24MHz: cdclk_config->ref = 24000; break; @@ -1561,7 +1561,7 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv, drm_WARN_ON(&dev_priv->drm, cdclk != dev_priv->cdclk.hw.bypass); drm_WARN_ON(&dev_priv->drm, vco != 0); - /* fall through */ + fallthrough; case 2: divider = BXT_CDCLK_CD2X_DIV_SEL_1; break; diff --git a/drivers/gpu/drm/i915/display/intel_combo_phy.c b/drivers/gpu/drm/i915/display/intel_combo_phy.c index eccaa79cb4a9..157d8c8c605a 100644 --- a/drivers/gpu/drm/i915/display/intel_combo_phy.c +++ b/drivers/gpu/drm/i915/display/intel_combo_phy.c @@ -52,7 +52,7 @@ cnl_get_procmon_ref_values(struct drm_i915_private *dev_priv, enum phy phy) switch (val & (PROCESS_INFO_MASK | VOLTAGE_INFO_MASK)) { default: MISSING_CASE(val); - /* fall through */ + fallthrough; case VOLTAGE_INFO_0_85V | PROCESS_INFO_DOT_0: procmon = &cnl_procmon_values[PROCMON_0_85V_DOT_0]; break; @@ -258,7 +258,7 @@ static bool phy_is_master(struct drm_i915_private *dev_priv, enum phy phy) static bool icl_combo_phy_verify_state(struct drm_i915_private *dev_priv, enum phy phy) { - bool ret; + bool ret = true; u32 expected_val = 0; if (!icl_combo_phy_enabled(dev_priv, phy)) @@ -276,7 +276,7 @@ static bool icl_combo_phy_verify_state(struct drm_i915_private *dev_priv, DCC_MODE_SELECT_CONTINUOSLY); } - ret = cnl_verify_procmon_ref_values(dev_priv, phy); + ret &= cnl_verify_procmon_ref_values(dev_priv, phy); if (phy_is_master(dev_priv, phy)) { ret &= check_phy_reg(dev_priv, phy, ICL_PORT_COMP_DW8(phy), @@ -320,7 +320,7 @@ void intel_combo_phy_power_up_lanes(struct drm_i915_private *dev_priv, break; default: MISSING_CASE(lane_count); - /* fall-through */ + fallthrough; case 4: lane_mask = PWR_UP_ALL_LANES; break; @@ -337,7 +337,7 @@ void intel_combo_phy_power_up_lanes(struct drm_i915_private *dev_priv, break; default: MISSING_CASE(lane_count); - /* fall-through */ + fallthrough; case 4: lane_mask = PWR_UP_ALL_LANES; break; diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 2c484b55bcdf..a49ff3a1a63c 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -1888,7 +1888,7 @@ static void intel_ddi_get_encoder_pipes(struct intel_encoder *encoder, switch (tmp & TRANS_DDI_EDP_INPUT_MASK) { default: MISSING_CASE(tmp & TRANS_DDI_EDP_INPUT_MASK); - /* fallthrough */ + fallthrough; case TRANS_DDI_EDP_INPUT_A_ON: case TRANS_DDI_EDP_INPUT_A_ONOFF: *pipe_mask = BIT(PIPE_A); @@ -4268,7 +4268,7 @@ void intel_ddi_get_config(struct intel_encoder *encoder, pipe_config->hdmi_scrambling = true; if (temp & TRANS_DDI_HIGH_TMDS_CHAR_RATE) pipe_config->hdmi_high_tmds_clock_ratio = true; - /* fall through */ + fallthrough; case TRANS_DDI_MODE_SELECT_DVI: pipe_config->output_types |= BIT(INTEL_OUTPUT_HDMI); pipe_config->lane_count = 4; diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index b2ec3a5141cc..b18c5ac2934d 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -2029,12 +2029,12 @@ intel_tile_width_bytes(const struct drm_framebuffer *fb, int color_plane) case I915_FORMAT_MOD_Y_TILED_CCS: if (is_ccs_plane(fb, color_plane)) return 128; - /* fall through */ + fallthrough; case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS: case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS: if (is_ccs_plane(fb, color_plane)) return 64; - /* fall through */ + fallthrough; case I915_FORMAT_MOD_Y_TILED: if (IS_GEN(dev_priv, 2) || HAS_128_BYTE_Y_TILING(dev_priv)) return 128; @@ -2043,7 +2043,7 @@ intel_tile_width_bytes(const struct drm_framebuffer *fb, int color_plane) case I915_FORMAT_MOD_Yf_TILED_CCS: if (is_ccs_plane(fb, color_plane)) return 128; - /* fall through */ + fallthrough; case I915_FORMAT_MOD_Yf_TILED: switch (cpp) { case 1: @@ -2185,7 +2185,7 @@ static unsigned int intel_surf_alignment(const struct drm_framebuffer *fb, case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS: if (is_semiplanar_uv_plane(fb, color_plane)) return intel_tile_row_size(fb, color_plane); - /* Fall-through */ + fallthrough; case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS: return 16 * 1024; case I915_FORMAT_MOD_Y_TILED_CCS: @@ -2194,7 +2194,7 @@ static unsigned int intel_surf_alignment(const struct drm_framebuffer *fb, if (INTEL_GEN(dev_priv) >= 12 && is_semiplanar_uv_plane(fb, color_plane)) return intel_tile_row_size(fb, color_plane); - /* Fall-through */ + fallthrough; case I915_FORMAT_MOD_Yf_TILED: return 1 * 1024 * 1024; default: @@ -6211,7 +6211,7 @@ static int skl_update_scaler_plane(struct intel_crtc_state *crtc_state, case DRM_FORMAT_ARGB16161616F: if (INTEL_GEN(dev_priv) >= 11) break; - /* fall through */ + fallthrough; default: drm_dbg_kms(&dev_priv->drm, "[PLANE:%d:%s] FB:%d unsupported scaling format 0x%x\n", @@ -10896,7 +10896,7 @@ static void hsw_get_ddi_pll(struct drm_i915_private *dev_priv, enum port port, break; default: MISSING_CASE(ddi_pll_sel); - /* fall through */ + fallthrough; case PORT_CLK_SEL_NONE: return; } @@ -10956,10 +10956,10 @@ static bool hsw_get_transcoder_state(struct intel_crtc *crtc, drm_WARN(dev, 1, "unknown pipe linked to transcoder %s\n", transcoder_name(panel_transcoder)); - /* fall through */ + fallthrough; case TRANS_DDI_EDP_INPUT_A_ONOFF: force_thru = true; - /* fall through */ + fallthrough; case TRANS_DDI_EDP_INPUT_A_ON: trans_pipe = PIPE_A; break; @@ -13183,7 +13183,7 @@ static bool check_digital_port_conflicts(struct intel_atomic_state *state) case INTEL_OUTPUT_DDI: if (drm_WARN_ON(dev, !HAS_DDI(to_i915(dev)))) break; - /* else, fall through */ + fallthrough; case INTEL_OUTPUT_DP: case INTEL_OUTPUT_HDMI: case INTEL_OUTPUT_EDP: @@ -14956,12 +14956,6 @@ static int intel_atomic_check(struct drm_device *dev, if (dev_priv->wm.distrust_bios_wm) any_ms = true; - if (any_ms) { - ret = intel_modeset_checks(state); - if (ret) - goto fail; - } - intel_fbc_choose_crtc(dev_priv, state); ret = calc_watermark_data(state); if (ret) @@ -14976,6 +14970,10 @@ static int intel_atomic_check(struct drm_device *dev, goto fail; if (any_ms) { + ret = intel_modeset_checks(state); + if (ret) + goto fail; + ret = intel_modeset_calc_cdclk(state); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c index aeb6ee395cce..afa7a378b31d 100644 --- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c +++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c @@ -892,7 +892,7 @@ static int hsw_ddi_wrpll_get_freq(struct drm_i915_private *dev_priv, refclk = dev_priv->dpll.ref_clks.nssc; break; } - /* fall through */ + fallthrough; case WRPLL_REF_PCH_SSC: /* * We could calculate spread here, but our checking @@ -2977,7 +2977,7 @@ static bool icl_calc_tbt_pll(struct intel_crtc_state *crtc_state, switch (dev_priv->dpll.ref_clks.nssc) { default: MISSING_CASE(dev_priv->dpll.ref_clks.nssc); - /* fall-through */ + fallthrough; case 19200: *pll_params = tgl_tbt_pll_19_2MHz_values; break; @@ -2992,7 +2992,7 @@ static bool icl_calc_tbt_pll(struct intel_crtc_state *crtc_state, switch (dev_priv->dpll.ref_clks.nssc) { default: MISSING_CASE(dev_priv->dpll.ref_clks.nssc); - /* fall-through */ + fallthrough; case 19200: case 38400: *pll_params = icl_tbt_pll_19_2MHz_values; @@ -3120,7 +3120,7 @@ static bool icl_mg_pll_find_divisors(int clock_khz, bool is_dp, bool use_ssc, switch (div1) { default: MISSING_CASE(div1); - /* fall through */ + fallthrough; case 2: hsdiv = MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO_2; break; diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c index 89a4d294822d..1a0d49af2a08 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_hdcp.c @@ -336,8 +336,10 @@ int intel_hdcp_validate_v_prime(struct intel_connector *connector, /* Fill up the empty slots in sha_text and write it out */ sha_empty = sizeof(sha_text) - sha_leftovers; - for (j = 0; j < sha_empty; j++) - sha_text |= ksv[j] << ((sizeof(sha_text) - j - 1) * 8); + for (j = 0; j < sha_empty; j++) { + u8 off = ((sizeof(sha_text) - j - 1 - sha_leftovers) * 8); + sha_text |= ksv[j] << off; + } ret = intel_write_sha_text(dev_priv, sha_text); if (ret < 0) @@ -435,7 +437,7 @@ int intel_hdcp_validate_v_prime(struct intel_connector *connector, /* Write 32 bits of text */ intel_de_write(dev_priv, HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_32); - sha_text |= bstatus[0] << 24 | bstatus[1] << 16; + sha_text |= bstatus[0] << 8 | bstatus[1]; ret = intel_write_sha_text(dev_priv, sha_text); if (ret < 0) return ret; @@ -450,17 +452,29 @@ int intel_hdcp_validate_v_prime(struct intel_connector *connector, return ret; sha_idx += sizeof(sha_text); } + + /* + * Terminate the SHA-1 stream by hand. For the other leftover + * cases this is appended by the hardware. + */ + intel_de_write(dev_priv, HDCP_REP_CTL, + rep_ctl | HDCP_SHA1_TEXT_32); + sha_text = DRM_HDCP_SHA1_TERMINATOR << 24; + ret = intel_write_sha_text(dev_priv, sha_text); + if (ret < 0) + return ret; + sha_idx += sizeof(sha_text); } else if (sha_leftovers == 3) { - /* Write 32 bits of text */ + /* Write 32 bits of text (filled from LSB) */ intel_de_write(dev_priv, HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_32); - sha_text |= bstatus[0] << 24; + sha_text |= bstatus[0]; ret = intel_write_sha_text(dev_priv, sha_text); if (ret < 0) return ret; sha_idx += sizeof(sha_text); - /* Write 8 bits of text, 24 bits of M0 */ + /* Write 8 bits of text (filled from LSB), 24 bits of M0 */ intel_de_write(dev_priv, HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_8); ret = intel_write_sha_text(dev_priv, bstatus[1]); @@ -781,6 +795,7 @@ static int _intel_hdcp_disable(struct intel_connector *connector) struct intel_hdcp *hdcp = &connector->hdcp; enum port port = dig_port->base.port; enum transcoder cpu_transcoder = hdcp->cpu_transcoder; + u32 repeater_ctl; int ret; drm_dbg_kms(&dev_priv->drm, "[%s:%d] HDCP is being disabled...\n", @@ -796,6 +811,11 @@ static int _intel_hdcp_disable(struct intel_connector *connector) return -ETIMEDOUT; } + repeater_ctl = intel_hdcp_get_repeater_ctl(dev_priv, cpu_transcoder, + port); + intel_de_write(dev_priv, HDCP_REP_CTL, + intel_de_read(dev_priv, HDCP_REP_CTL) & ~repeater_ctl); + ret = hdcp->shim->toggle_signalling(dig_port, false); if (ret) { drm_err(&dev_priv->drm, "Failed to disable HDCP signalling\n"); diff --git a/drivers/gpu/drm/i915/display/intel_panel.c b/drivers/gpu/drm/i915/display/intel_panel.c index bbde3b12c311..4072d7062efd 100644 --- a/drivers/gpu/drm/i915/display/intel_panel.c +++ b/drivers/gpu/drm/i915/display/intel_panel.c @@ -229,7 +229,7 @@ int intel_pch_panel_fitting(struct intel_crtc_state *crtc_state, case DRM_MODE_SCALE_NONE: WARN_ON(adjusted_mode->crtc_hdisplay != crtc_state->pipe_src_w); WARN_ON(adjusted_mode->crtc_vdisplay != crtc_state->pipe_src_h); - /* fall through */ + fallthrough; case DRM_MODE_SCALE_FULLSCREEN: x = y = 0; width = adjusted_mode->crtc_hdisplay; diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c index 2da4388e1540..5e9fb349c829 100644 --- a/drivers/gpu/drm/i915/display/intel_sdvo.c +++ b/drivers/gpu/drm/i915/display/intel_sdvo.c @@ -1531,7 +1531,7 @@ static void intel_sdvo_pre_enable(struct intel_atomic_state *state, default: drm_WARN(&dev_priv->drm, 1, "unknown pixel multiplier specified\n"); - /* fall through */ + fallthrough; case 1: rate = SDVO_CLOCK_RATE_MULT_1X; break; case 2: rate = SDVO_CLOCK_RATE_MULT_2X; break; case 4: rate = SDVO_CLOCK_RATE_MULT_4X; break; @@ -2549,19 +2549,19 @@ intel_sdvo_guess_ddc_bus(struct intel_sdvo *sdvo) switch (sdvo->controlled_output) { case SDVO_OUTPUT_LVDS1: mask |= SDVO_OUTPUT_LVDS1; - /* fall through */ + fallthrough; case SDVO_OUTPUT_LVDS0: mask |= SDVO_OUTPUT_LVDS0; - /* fall through */ + fallthrough; case SDVO_OUTPUT_TMDS1: mask |= SDVO_OUTPUT_TMDS1; - /* fall through */ + fallthrough; case SDVO_OUTPUT_TMDS0: mask |= SDVO_OUTPUT_TMDS0; - /* fall through */ + fallthrough; case SDVO_OUTPUT_RGB1: mask |= SDVO_OUTPUT_RGB1; - /* fall through */ + fallthrough; case SDVO_OUTPUT_RGB0: mask |= SDVO_OUTPUT_RGB0; break; diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c index d03860fef2d7..c89f5f7ccb06 100644 --- a/drivers/gpu/drm/i915/display/intel_sprite.c +++ b/drivers/gpu/drm/i915/display/intel_sprite.c @@ -2147,7 +2147,7 @@ static int skl_plane_check_fb(const struct intel_crtc_state *crtc_state, case DRM_FORMAT_RGB565: if (INTEL_GEN(dev_priv) >= 11) break; - /* fall through */ + fallthrough; case DRM_FORMAT_C8: case DRM_FORMAT_XRGB16161616F: case DRM_FORMAT_XBGR16161616F: @@ -2702,7 +2702,7 @@ static bool g4x_sprite_format_mod_supported(struct drm_plane *_plane, if (modifier == DRM_FORMAT_MOD_LINEAR || modifier == I915_FORMAT_MOD_X_TILED) return true; - /* fall through */ + fallthrough; default: return false; } @@ -2733,7 +2733,7 @@ static bool snb_sprite_format_mod_supported(struct drm_plane *_plane, if (modifier == DRM_FORMAT_MOD_LINEAR || modifier == I915_FORMAT_MOD_X_TILED) return true; - /* fall through */ + fallthrough; default: return false; } @@ -2768,7 +2768,7 @@ static bool vlv_sprite_format_mod_supported(struct drm_plane *_plane, if (modifier == DRM_FORMAT_MOD_LINEAR || modifier == I915_FORMAT_MOD_X_TILED) return true; - /* fall through */ + fallthrough; default: return false; } @@ -2801,7 +2801,7 @@ static bool skl_plane_format_mod_supported(struct drm_plane *_plane, case DRM_FORMAT_ABGR8888: if (is_ccs_modifier(modifier)) return true; - /* fall through */ + fallthrough; case DRM_FORMAT_RGB565: case DRM_FORMAT_XRGB2101010: case DRM_FORMAT_XBGR2101010: @@ -2819,7 +2819,7 @@ static bool skl_plane_format_mod_supported(struct drm_plane *_plane, case DRM_FORMAT_XVYU2101010: if (modifier == I915_FORMAT_MOD_Yf_TILED) return true; - /* fall through */ + fallthrough; case DRM_FORMAT_C8: case DRM_FORMAT_XBGR16161616F: case DRM_FORMAT_ABGR16161616F: @@ -2834,7 +2834,7 @@ static bool skl_plane_format_mod_supported(struct drm_plane *_plane, modifier == I915_FORMAT_MOD_X_TILED || modifier == I915_FORMAT_MOD_Y_TILED) return true; - /* fall through */ + fallthrough; default: return false; } @@ -2860,7 +2860,7 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane, case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS: if (!gen12_plane_supports_mc_ccs(dev_priv, plane->id)) return false; - /* fall through */ + fallthrough; case DRM_FORMAT_MOD_LINEAR: case I915_FORMAT_MOD_X_TILED: case I915_FORMAT_MOD_Y_TILED: @@ -2877,7 +2877,7 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane, case DRM_FORMAT_ABGR8888: if (is_ccs_modifier(modifier)) return true; - /* fall through */ + fallthrough; case DRM_FORMAT_YUYV: case DRM_FORMAT_YVYU: case DRM_FORMAT_UYVY: @@ -2889,7 +2889,7 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane, case DRM_FORMAT_P016: if (modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS) return true; - /* fall through */ + fallthrough; case DRM_FORMAT_RGB565: case DRM_FORMAT_XRGB2101010: case DRM_FORMAT_XBGR2101010: @@ -2910,7 +2910,7 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane, modifier == I915_FORMAT_MOD_X_TILED || modifier == I915_FORMAT_MOD_Y_TILED) return true; - /* fall through */ + fallthrough; default: return false; } diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c index 5b5dc86a5737..8f67aef18b2d 100644 --- a/drivers/gpu/drm/i915/display/intel_tc.c +++ b/drivers/gpu/drm/i915/display/intel_tc.c @@ -159,7 +159,7 @@ int intel_tc_port_fia_max_lane_count(struct intel_digital_port *dig_port) switch (lane_mask) { default: MISSING_CASE(lane_mask); - /* fall-through */ + fallthrough; case 0x1: case 0x2: case 0x4: diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index d0bdb6d447ed..ef755dd5e68f 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -439,29 +439,36 @@ static bool __cancel_engine(struct intel_engine_cs *engine) return __reset_engine(engine); } -static struct intel_engine_cs *__active_engine(struct i915_request *rq) +static bool +__active_engine(struct i915_request *rq, struct intel_engine_cs **active) { struct intel_engine_cs *engine, *locked; + bool ret = false; /* * Serialise with __i915_request_submit() so that it sees * is-banned?, or we know the request is already inflight. + * + * Note that rq->engine is unstable, and so we double + * check that we have acquired the lock on the final engine. */ locked = READ_ONCE(rq->engine); spin_lock_irq(&locked->active.lock); while (unlikely(locked != (engine = READ_ONCE(rq->engine)))) { spin_unlock(&locked->active.lock); - spin_lock(&engine->active.lock); locked = engine; + spin_lock(&locked->active.lock); } - engine = NULL; - if (i915_request_is_active(rq) && rq->fence.error != -EIO) - engine = rq->engine; + if (!i915_request_completed(rq)) { + if (i915_request_is_active(rq) && rq->fence.error != -EIO) + *active = locked; + ret = true; + } spin_unlock_irq(&locked->active.lock); - return engine; + return ret; } static struct intel_engine_cs *active_engine(struct intel_context *ce) @@ -472,17 +479,16 @@ static struct intel_engine_cs *active_engine(struct intel_context *ce) if (!ce->timeline) return NULL; - mutex_lock(&ce->timeline->mutex); - list_for_each_entry_reverse(rq, &ce->timeline->requests, link) { - if (i915_request_completed(rq)) - break; + rcu_read_lock(); + list_for_each_entry_rcu(rq, &ce->timeline->requests, link) { + if (i915_request_is_active(rq) && i915_request_completed(rq)) + continue; /* Check with the backend if the request is inflight */ - engine = __active_engine(rq); - if (engine) + if (__active_engine(rq, &engine)) break; } - mutex_unlock(&ce->timeline->mutex); + rcu_read_unlock(); return engine; } @@ -713,6 +719,7 @@ __create_context(struct drm_i915_private *i915) ctx->i915 = i915; ctx->sched.priority = I915_USER_PRIORITY(I915_PRIORITY_NORMAL); mutex_init(&ctx->mutex); + INIT_LIST_HEAD(&ctx->link); spin_lock_init(&ctx->stale.lock); INIT_LIST_HEAD(&ctx->stale.engines); @@ -740,10 +747,6 @@ __create_context(struct drm_i915_private *i915) for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++) ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES; - spin_lock(&i915->gem.contexts.lock); - list_add_tail(&ctx->link, &i915->gem.contexts.list); - spin_unlock(&i915->gem.contexts.lock); - return ctx; err_free: @@ -931,6 +934,7 @@ static int gem_context_register(struct i915_gem_context *ctx, struct drm_i915_file_private *fpriv, u32 *id) { + struct drm_i915_private *i915 = ctx->i915; struct i915_address_space *vm; int ret; @@ -949,8 +953,16 @@ static int gem_context_register(struct i915_gem_context *ctx, /* And finally expose ourselves to userspace via the idr */ ret = xa_alloc(&fpriv->context_xa, id, ctx, xa_limit_32b, GFP_KERNEL); if (ret) - put_pid(fetch_and_zero(&ctx->pid)); + goto err_pid; + + spin_lock(&i915->gem.contexts.lock); + list_add_tail(&ctx->link, &i915->gem.contexts.list); + spin_unlock(&i915->gem.contexts.lock); + + return 0; +err_pid: + put_pid(fetch_and_zero(&ctx->pid)); return ret; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 6b4ec66cb558..446e76e95c38 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -45,6 +45,13 @@ struct eb_vma_array { struct eb_vma vma[]; }; +enum { + FORCE_CPU_RELOC = 1, + FORCE_GTT_RELOC, + FORCE_GPU_RELOC, +#define DBG_FORCE_RELOC 0 /* choose one of the above! */ +}; + #define __EXEC_OBJECT_HAS_PIN BIT(31) #define __EXEC_OBJECT_HAS_FENCE BIT(30) #define __EXEC_OBJECT_NEEDS_MAP BIT(29) @@ -253,6 +260,8 @@ struct i915_execbuffer { */ struct reloc_cache { struct drm_mm_node node; /** temporary GTT binding */ + unsigned long vaddr; /** Current kmap address */ + unsigned long page; /** Currently mapped page index */ unsigned int gen; /** Cached value of INTEL_GEN */ bool use_64bit_reloc : 1; bool has_llc : 1; @@ -596,6 +605,23 @@ eb_add_vma(struct i915_execbuffer *eb, } } +static inline int use_cpu_reloc(const struct reloc_cache *cache, + const struct drm_i915_gem_object *obj) +{ + if (!i915_gem_object_has_struct_page(obj)) + return false; + + if (DBG_FORCE_RELOC == FORCE_CPU_RELOC) + return true; + + if (DBG_FORCE_RELOC == FORCE_GTT_RELOC) + return false; + + return (cache->has_llc || + obj->cache_dirty || + obj->cache_level != I915_CACHE_NONE); +} + static int eb_reserve_vma(const struct i915_execbuffer *eb, struct eb_vma *ev, u64 pin_flags) @@ -926,6 +952,8 @@ relocation_target(const struct drm_i915_gem_relocation_entry *reloc, static void reloc_cache_init(struct reloc_cache *cache, struct drm_i915_private *i915) { + cache->page = -1; + cache->vaddr = 0; /* Must be a variable in the struct to allow GCC to unroll. */ cache->gen = INTEL_GEN(i915); cache->has_llc = HAS_LLC(i915); @@ -937,6 +965,25 @@ static void reloc_cache_init(struct reloc_cache *cache, cache->target = NULL; } +static inline void *unmask_page(unsigned long p) +{ + return (void *)(uintptr_t)(p & PAGE_MASK); +} + +static inline unsigned int unmask_flags(unsigned long p) +{ + return p & ~PAGE_MASK; +} + +#define KMAP 0x4 /* after CLFLUSH_FLAGS */ + +static inline struct i915_ggtt *cache_to_ggtt(struct reloc_cache *cache) +{ + struct drm_i915_private *i915 = + container_of(cache, struct i915_execbuffer, reloc_cache)->i915; + return &i915->ggtt; +} + #define RELOC_TAIL 4 static int reloc_gpu_chain(struct reloc_cache *cache) @@ -1049,6 +1096,181 @@ static int reloc_gpu_flush(struct reloc_cache *cache) return err; } +static void reloc_cache_reset(struct reloc_cache *cache) +{ + void *vaddr; + + if (!cache->vaddr) + return; + + vaddr = unmask_page(cache->vaddr); + if (cache->vaddr & KMAP) { + if (cache->vaddr & CLFLUSH_AFTER) + mb(); + + kunmap_atomic(vaddr); + i915_gem_object_finish_access((struct drm_i915_gem_object *)cache->node.mm); + } else { + struct i915_ggtt *ggtt = cache_to_ggtt(cache); + + intel_gt_flush_ggtt_writes(ggtt->vm.gt); + io_mapping_unmap_atomic((void __iomem *)vaddr); + + if (drm_mm_node_allocated(&cache->node)) { + ggtt->vm.clear_range(&ggtt->vm, + cache->node.start, + cache->node.size); + mutex_lock(&ggtt->vm.mutex); + drm_mm_remove_node(&cache->node); + mutex_unlock(&ggtt->vm.mutex); + } else { + i915_vma_unpin((struct i915_vma *)cache->node.mm); + } + } + + cache->vaddr = 0; + cache->page = -1; +} + +static void *reloc_kmap(struct drm_i915_gem_object *obj, + struct reloc_cache *cache, + unsigned long page) +{ + void *vaddr; + + if (cache->vaddr) { + kunmap_atomic(unmask_page(cache->vaddr)); + } else { + unsigned int flushes; + int err; + + err = i915_gem_object_prepare_write(obj, &flushes); + if (err) + return ERR_PTR(err); + + BUILD_BUG_ON(KMAP & CLFLUSH_FLAGS); + BUILD_BUG_ON((KMAP | CLFLUSH_FLAGS) & PAGE_MASK); + + cache->vaddr = flushes | KMAP; + cache->node.mm = (void *)obj; + if (flushes) + mb(); + } + + vaddr = kmap_atomic(i915_gem_object_get_dirty_page(obj, page)); + cache->vaddr = unmask_flags(cache->vaddr) | (unsigned long)vaddr; + cache->page = page; + + return vaddr; +} + +static void *reloc_iomap(struct drm_i915_gem_object *obj, + struct reloc_cache *cache, + unsigned long page) +{ + struct i915_ggtt *ggtt = cache_to_ggtt(cache); + unsigned long offset; + void *vaddr; + + if (cache->vaddr) { + intel_gt_flush_ggtt_writes(ggtt->vm.gt); + io_mapping_unmap_atomic((void __force __iomem *) unmask_page(cache->vaddr)); + } else { + struct i915_vma *vma; + int err; + + if (i915_gem_object_is_tiled(obj)) + return ERR_PTR(-EINVAL); + + if (use_cpu_reloc(cache, obj)) + return NULL; + + i915_gem_object_lock(obj); + err = i915_gem_object_set_to_gtt_domain(obj, true); + i915_gem_object_unlock(obj); + if (err) + return ERR_PTR(err); + + vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, + PIN_MAPPABLE | + PIN_NONBLOCK /* NOWARN */ | + PIN_NOEVICT); + if (IS_ERR(vma)) { + memset(&cache->node, 0, sizeof(cache->node)); + mutex_lock(&ggtt->vm.mutex); + err = drm_mm_insert_node_in_range + (&ggtt->vm.mm, &cache->node, + PAGE_SIZE, 0, I915_COLOR_UNEVICTABLE, + 0, ggtt->mappable_end, + DRM_MM_INSERT_LOW); + mutex_unlock(&ggtt->vm.mutex); + if (err) /* no inactive aperture space, use cpu reloc */ + return NULL; + } else { + cache->node.start = vma->node.start; + cache->node.mm = (void *)vma; + } + } + + offset = cache->node.start; + if (drm_mm_node_allocated(&cache->node)) { + ggtt->vm.insert_page(&ggtt->vm, + i915_gem_object_get_dma_address(obj, page), + offset, I915_CACHE_NONE, 0); + } else { + offset += page << PAGE_SHIFT; + } + + vaddr = (void __force *)io_mapping_map_atomic_wc(&ggtt->iomap, + offset); + cache->page = page; + cache->vaddr = (unsigned long)vaddr; + + return vaddr; +} + +static void *reloc_vaddr(struct drm_i915_gem_object *obj, + struct reloc_cache *cache, + unsigned long page) +{ + void *vaddr; + + if (cache->page == page) { + vaddr = unmask_page(cache->vaddr); + } else { + vaddr = NULL; + if ((cache->vaddr & KMAP) == 0) + vaddr = reloc_iomap(obj, cache, page); + if (!vaddr) + vaddr = reloc_kmap(obj, cache, page); + } + + return vaddr; +} + +static void clflush_write32(u32 *addr, u32 value, unsigned int flushes) +{ + if (unlikely(flushes & (CLFLUSH_BEFORE | CLFLUSH_AFTER))) { + if (flushes & CLFLUSH_BEFORE) { + clflushopt(addr); + mb(); + } + + *addr = value; + + /* + * Writes to the same cacheline are serialised by the CPU + * (including clflush). On the write path, we only require + * that it hits memory in an orderly fashion and place + * mb barriers at the start and end of the relocation phase + * to ensure ordering of clflush wrt to the system. + */ + if (flushes & CLFLUSH_AFTER) + clflushopt(addr); + } else + *addr = value; +} + static int reloc_move_to_gpu(struct i915_request *rq, struct i915_vma *vma) { struct drm_i915_gem_object *obj = vma->obj; @@ -1214,6 +1436,17 @@ static u32 *reloc_gpu(struct i915_execbuffer *eb, return cmd; } +static inline bool use_reloc_gpu(struct i915_vma *vma) +{ + if (DBG_FORCE_RELOC == FORCE_GPU_RELOC) + return true; + + if (DBG_FORCE_RELOC) + return false; + + return !dma_resv_test_signaled_rcu(vma->resv, true); +} + static unsigned long vma_phys_addr(struct i915_vma *vma, u32 offset) { struct page *page; @@ -1228,10 +1461,10 @@ static unsigned long vma_phys_addr(struct i915_vma *vma, u32 offset) return addr + offset_in_page(offset); } -static int __reloc_entry_gpu(struct i915_execbuffer *eb, - struct i915_vma *vma, - u64 offset, - u64 target_addr) +static bool __reloc_entry_gpu(struct i915_execbuffer *eb, + struct i915_vma *vma, + u64 offset, + u64 target_addr) { const unsigned int gen = eb->reloc_cache.gen; unsigned int len; @@ -1247,7 +1480,7 @@ static int __reloc_entry_gpu(struct i915_execbuffer *eb, batch = reloc_gpu(eb, vma, len); if (IS_ERR(batch)) - return PTR_ERR(batch); + return false; addr = gen8_canonical_addr(vma->node.start + offset); if (gen >= 8) { @@ -1296,21 +1529,55 @@ static int __reloc_entry_gpu(struct i915_execbuffer *eb, *batch++ = target_addr; } - return 0; + return true; +} + +static bool reloc_entry_gpu(struct i915_execbuffer *eb, + struct i915_vma *vma, + u64 offset, + u64 target_addr) +{ + if (eb->reloc_cache.vaddr) + return false; + + if (!use_reloc_gpu(vma)) + return false; + + return __reloc_entry_gpu(eb, vma, offset, target_addr); } static u64 -relocate_entry(struct i915_execbuffer *eb, - struct i915_vma *vma, +relocate_entry(struct i915_vma *vma, const struct drm_i915_gem_relocation_entry *reloc, + struct i915_execbuffer *eb, const struct i915_vma *target) { u64 target_addr = relocation_target(reloc, target); - int err; - - err = __reloc_entry_gpu(eb, vma, reloc->offset, target_addr); - if (err) - return err; + u64 offset = reloc->offset; + + if (!reloc_entry_gpu(eb, vma, offset, target_addr)) { + bool wide = eb->reloc_cache.use_64bit_reloc; + void *vaddr; + +repeat: + vaddr = reloc_vaddr(vma->obj, + &eb->reloc_cache, + offset >> PAGE_SHIFT); + if (IS_ERR(vaddr)) + return PTR_ERR(vaddr); + + GEM_BUG_ON(!IS_ALIGNED(offset, sizeof(u32))); + clflush_write32(vaddr + offset_in_page(offset), + lower_32_bits(target_addr), + eb->reloc_cache.vaddr); + + if (wide) { + offset += sizeof(u32); + target_addr >>= 32; + wide = false; + goto repeat; + } + } return target->node.start | UPDATE; } @@ -1375,7 +1642,8 @@ eb_relocate_entry(struct i915_execbuffer *eb, * If the relocation already has the right value in it, no * more work needs to be done. */ - if (gen8_canonical_addr(target->vma->node.start) == reloc->presumed_offset) + if (!DBG_FORCE_RELOC && + gen8_canonical_addr(target->vma->node.start) == reloc->presumed_offset) return 0; /* Check that the relocation address is valid... */ @@ -1407,7 +1675,7 @@ eb_relocate_entry(struct i915_execbuffer *eb, ev->flags &= ~EXEC_OBJECT_ASYNC; /* and update the user's relocation entry */ - return relocate_entry(eb, ev->vma, reloc, target->vma); + return relocate_entry(ev->vma, reloc, eb, target->vma); } static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev) @@ -1445,8 +1713,10 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev) * this is bad and so lockdep complains vehemently. */ copied = __copy_from_user(r, urelocs, count * sizeof(r[0])); - if (unlikely(copied)) - return -EFAULT; + if (unlikely(copied)) { + remain = -EFAULT; + goto out; + } remain -= count; do { @@ -1454,7 +1724,8 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev) if (likely(offset == 0)) { } else if ((s64)offset < 0) { - return (int)offset; + remain = (int)offset; + goto out; } else { /* * Note that reporting an error now @@ -1484,8 +1755,9 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev) } while (r++, --count); urelocs += ARRAY_SIZE(stack); } while (remain); - - return 0; +out: + reloc_cache_reset(&eb->reloc_cache); + return remain; } static int eb_relocate(struct i915_execbuffer *eb) @@ -2392,7 +2664,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, eb.i915 = i915; eb.file = file; eb.args = args; - if (!(args->flags & I915_EXEC_NO_RELOC)) + if (DBG_FORCE_RELOC || !(args->flags & I915_EXEC_NO_RELOC)) args->flags |= __EXEC_HAS_RELOC; eb.exec = exec; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index b23368529a40..753f82d87a31 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -209,7 +209,7 @@ static vm_fault_t i915_error_to_vmf_fault(int err) switch (err) { default: WARN_ONCE(err, "unhandled error in %s: %i\n", __func__, err); - /* fallthrough */ + fallthrough; case -EIO: /* shmemfs failure from swap device */ case -EFAULT: /* purged object */ case -ENODEV: /* bad object, how did you get here! */ diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index e5b9276d254c..9cf4ad78ece6 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -258,6 +258,10 @@ struct page * i915_gem_object_get_page(struct drm_i915_gem_object *obj, unsigned int n); +struct page * +i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj, + unsigned int n); + dma_addr_t i915_gem_object_get_dma_address_len(struct drm_i915_gem_object *obj, unsigned long n, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index 7050519c87a4..e8a083743e09 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -276,7 +276,7 @@ static void *i915_gem_object_map(struct drm_i915_gem_object *obj, switch (type) { default: MISSING_CASE(type); - /* fallthrough - to use PAGE_KERNEL anyway */ + fallthrough; /* to use PAGE_KERNEL anyway */ case I915_MAP_WB: pgprot = PAGE_KERNEL; break; @@ -548,6 +548,20 @@ i915_gem_object_get_page(struct drm_i915_gem_object *obj, unsigned int n) return nth_page(sg_page(sg), offset); } +/* Like i915_gem_object_get_page(), but mark the returned page dirty */ +struct page * +i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj, + unsigned int n) +{ + struct page *page; + + page = i915_gem_object_get_page(obj, n); + if (!obj->mm.dirty) + set_page_dirty(page); + + return page; +} + dma_addr_t i915_gem_object_get_dma_address_len(struct drm_i915_gem_object *obj, unsigned long n, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c index e0f21f12d3ce..0be5e8683337 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c @@ -249,7 +249,7 @@ static void vlv_get_stolen_reserved(struct drm_i915_private *i915, switch (reg_val & GEN7_STOLEN_RESERVED_SIZE_MASK) { default: MISSING_CASE(reg_val & GEN7_STOLEN_RESERVED_SIZE_MASK); - /* fall through */ + fallthrough; case GEN7_STOLEN_RESERVED_1M: *size = 1024 * 1024; break; @@ -416,7 +416,7 @@ static int i915_gem_init_stolen(struct drm_i915_private *i915) case 4: if (!IS_G4X(i915)) break; - /* fall through */ + fallthrough; case 5: g4x_get_stolen_reserved(i915, uncore, &reserved_base, &reserved_size); @@ -445,7 +445,7 @@ static int i915_gem_init_stolen(struct drm_i915_private *i915) break; default: MISSING_CASE(INTEL_GEN(i915)); - /* fall-through */ + fallthrough; case 11: case 12: icl_get_stolen_reserved(i915, uncore, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 2c2bf24140c9..12b30075134a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -596,14 +596,6 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); - /* - * Using __get_user_pages_fast() with a read-only - * access is questionable. A read-only page may be - * COW-broken, and then this might end up giving - * the wrong side of the COW.. - * - * We may or may not care. - */ if (pvec) { /* defer to worker if malloc fails */ if (!i915_gem_object_is_readonly(obj)) diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c index 57c14d3340cd..a49016f8ee0d 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c @@ -37,14 +37,20 @@ static int __igt_gpu_reloc(struct i915_execbuffer *eb, return err; /* 8-Byte aligned */ - err = __reloc_entry_gpu(eb, vma, offsets[0] * sizeof(u32), 0); - if (err) + if (!__reloc_entry_gpu(eb, vma, + offsets[0] * sizeof(u32), + 0)) { + err = -EIO; goto unpin_vma; + } /* !8-Byte aligned */ - err = __reloc_entry_gpu(eb, vma, offsets[1] * sizeof(u32), 1); - if (err) + if (!__reloc_entry_gpu(eb, vma, + offsets[1] * sizeof(u32), + 1)) { + err = -EIO; goto unpin_vma; + } /* Skip to the end of the cmd page */ i = PAGE_SIZE / sizeof(u32) - RELOC_TAIL - 1; @@ -54,9 +60,12 @@ static int __igt_gpu_reloc(struct i915_execbuffer *eb, eb->reloc_cache.rq_size += i; /* Force batch chaining */ - err = __reloc_entry_gpu(eb, vma, offsets[2] * sizeof(u32), 2); - if (err) + if (!__reloc_entry_gpu(eb, vma, + offsets[2] * sizeof(u32), + 2)) { + err = -EIO; goto unpin_vma; + } GEM_BUG_ON(!eb->reloc_cache.rq); rq = i915_request_get(eb->reloc_cache.rq); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index dd1a42c4d344..26087dd79782 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -213,7 +213,7 @@ u32 intel_engine_context_size(struct intel_gt *gt, u8 class) break; default: MISSING_CASE(class); - /* fall through */ + fallthrough; case VIDEO_DECODE_CLASS: case VIDEO_ENHANCEMENT_CLASS: case COPY_ENGINE_CLASS: diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index 62979ea591f0..99e28d9021e8 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -1437,7 +1437,7 @@ i915_get_ggtt_vma_pages(struct i915_vma *vma) switch (vma->ggtt_view.type) { default: GEM_BUG_ON(vma->ggtt_view.type); - /* fall through */ + fallthrough; case I915_GGTT_VIEW_NORMAL: vma->pages = vma->obj->mm.pages; return 0; diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 24322ef08aa4..9eeaca957a7e 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -2060,6 +2060,14 @@ static inline void clear_ports(struct i915_request **ports, int count) memset_p((void **)ports, NULL, count); } +static inline void +copy_ports(struct i915_request **dst, struct i915_request **src, int count) +{ + /* A memcpy_p() would be very useful here! */ + while (count--) + WRITE_ONCE(*dst++, *src++); /* avoid write tearing */ +} + static void execlists_dequeue(struct intel_engine_cs *engine) { struct intel_engine_execlists * const execlists = &engine->execlists; @@ -2648,10 +2656,9 @@ static void process_csb(struct intel_engine_cs *engine) /* switch pending to inflight */ GEM_BUG_ON(!assert_pending_valid(execlists, "promote")); - memcpy(execlists->inflight, - execlists->pending, - execlists_num_ports(execlists) * - sizeof(*execlists->pending)); + copy_ports(execlists->inflight, + execlists->pending, + execlists_num_ports(execlists)); smp_wmb(); /* complete the seqlock */ WRITE_ONCE(execlists->active, execlists->inflight); diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c index 94915f668715..898593ca4889 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c @@ -100,7 +100,7 @@ static void set_hwsp(struct intel_engine_cs *engine, u32 offset) */ default: GEM_BUG_ON(engine->id); - /* fallthrough */ + fallthrough; case RCS0: hwsp = RENDER_HWS_PGA_GEN7; break; diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 63bba7b4bb2f..05f3bc98d242 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -1226,7 +1226,7 @@ static int handle_g2v_notification(struct intel_vgpu *vgpu, int notification) switch (notification) { case VGT_G2V_PPGTT_L3_PAGE_TABLE_CREATE: root_entry_type = GTT_TYPE_PPGTT_ROOT_L3_ENTRY; - /* fall through */ + fallthrough; case VGT_G2V_PPGTT_L4_PAGE_TABLE_CREATE: mm = intel_vgpu_get_ppgtt_mm(vgpu, root_entry_type, pdps); return PTR_ERR_OR_ZERO(mm); diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 8fa9b31a2484..f6d7e33c7099 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -368,6 +368,7 @@ void intel_gvt_destroy_idle_vgpu(struct intel_vgpu *vgpu) static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, struct intel_vgpu_creation_params *param) { + struct drm_i915_private *dev_priv = gvt->gt->i915; struct intel_vgpu *vgpu; int ret; @@ -436,7 +437,10 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, if (ret) goto out_clean_sched_policy; - ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D); + if (IS_BROADWELL(dev_priv)) + ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_B); + else + ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D); if (ret) goto out_clean_sched_policy; diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 372354d33f55..5ac4a999f05a 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -1204,6 +1204,12 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj, return dst; } +static inline bool cmd_desc_is(const struct drm_i915_cmd_descriptor * const desc, + const u32 cmd) +{ + return desc->cmd.value == (cmd & desc->cmd.mask); +} + static bool check_cmd(const struct intel_engine_cs *engine, const struct drm_i915_cmd_descriptor *desc, const u32 *cmd, u32 length) @@ -1242,19 +1248,19 @@ static bool check_cmd(const struct intel_engine_cs *engine, * allowed mask/value pair given in the whitelist entry. */ if (reg->mask) { - if (desc->cmd.value == MI_LOAD_REGISTER_MEM) { + if (cmd_desc_is(desc, MI_LOAD_REGISTER_MEM)) { DRM_DEBUG("CMD: Rejected LRM to masked register 0x%08X\n", reg_addr); return false; } - if (desc->cmd.value == MI_LOAD_REGISTER_REG) { + if (cmd_desc_is(desc, MI_LOAD_REGISTER_REG)) { DRM_DEBUG("CMD: Rejected LRR to masked register 0x%08X\n", reg_addr); return false; } - if (desc->cmd.value == MI_LOAD_REGISTER_IMM(1) && + if (cmd_desc_is(desc, MI_LOAD_REGISTER_IMM(1)) && (offset + 2 > length || (cmd[offset + 1] & reg->mask) != reg->value)) { DRM_DEBUG("CMD: Rejected LRI to masked register 0x%08X\n", @@ -1478,7 +1484,7 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, break; } - if (desc->cmd.value == MI_BATCH_BUFFER_START) { + if (cmd_desc_is(desc, MI_BATCH_BUFFER_START)) { ret = check_bbstart(cmd, offset, length, batch_length, batch_addr, shadow_addr, jump_whitelist); diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 6a3a2ce0b394..3e6cbb0d1150 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1159,7 +1159,7 @@ static void engine_record_registers(struct intel_engine_coredump *ee) switch (engine->id) { default: MISSING_CASE(engine->id); - /* fall through */ + fallthrough; case RCS0: mmio = RENDER_HWS_PGA_GEN7; break; diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index 056994224c6b..69c0fa20eba1 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -474,7 +474,7 @@ config_status(struct drm_i915_private *i915, u64 config) if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) /* Requires a mutex for sampling! */ return -ENODEV; - /* Fall-through. */ + fallthrough; case I915_PMU_REQUESTED_FREQUENCY: if (INTEL_GEN(i915) < 6) return -ENODEV; diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 0b2fe55e6194..781a6783affe 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -388,17 +388,38 @@ static bool __request_in_flight(const struct i915_request *signal) * As we know that there are always preemption points between * requests, we know that only the currently executing request * may be still active even though we have cleared the flag. - * However, we can't rely on our tracking of ELSP[0] to known + * However, we can't rely on our tracking of ELSP[0] to know * which request is currently active and so maybe stuck, as * the tracking maybe an event behind. Instead assume that * if the context is still inflight, then it is still active * even if the active flag has been cleared. + * + * To further complicate matters, if there a pending promotion, the HW + * may either perform a context switch to the second inflight execlists, + * or it may switch to the pending set of execlists. In the case of the + * latter, it may send the ACK and we process the event copying the + * pending[] over top of inflight[], _overwriting_ our *active. Since + * this implies the HW is arbitrating and not struck in *active, we do + * not worry about complete accuracy, but we do require no read/write + * tearing of the pointer [the read of the pointer must be valid, even + * as the array is being overwritten, for which we require the writes + * to avoid tearing.] + * + * Note that the read of *execlists->active may race with the promotion + * of execlists->pending[] to execlists->inflight[], overwritting + * the value at *execlists->active. This is fine. The promotion implies + * that we received an ACK from the HW, and so the context is not + * stuck -- if we do not see ourselves in *active, the inflight status + * is valid. If instead we see ourselves being copied into *active, + * we are inflight and may signal the callback. */ if (!intel_context_inflight(signal->context)) return false; rcu_read_lock(); - for (port = __engine_active(signal->engine); (rq = *port); port++) { + for (port = __engine_active(signal->engine); + (rq = READ_ONCE(*port)); /* may race with promotion of pending[] */ + port++) { if (rq->context == signal->context) { inflight = i915_seqno_passed(rq->fence.seqno, signal->fence.seqno); diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c index 295b9829e2da..4cd2038cbe35 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.c +++ b/drivers/gpu/drm/i915/i915_sw_fence.c @@ -164,9 +164,13 @@ static void __i915_sw_fence_wake_up_all(struct i915_sw_fence *fence, do { list_for_each_entry_safe(pos, next, &x->head, entry) { - pos->func(pos, - TASK_NORMAL, fence->error, - &extra); + int wake_flags; + + wake_flags = fence->error; + if (pos->func == autoremove_wake_function) + wake_flags = 0; + + pos->func(pos, TASK_NORMAL, wake_flags, &extra); } if (list_empty(&extra)) diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c index f127e633f7ca..397c313a8b69 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c +++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c @@ -118,11 +118,11 @@ static struct dev_pm_domain pm_domain = { struct drm_i915_private *mock_gem_device(void) { - struct drm_i915_private *i915; - struct pci_dev *pdev; #if IS_ENABLED(CONFIG_IOMMU_API) && defined(CONFIG_INTEL_IOMMU) - struct dev_iommu iommu; + static struct dev_iommu fake_iommu = { .priv = (void *)-1 }; #endif + struct drm_i915_private *i915; + struct pci_dev *pdev; int err; pdev = kzalloc(sizeof(*pdev), GFP_KERNEL); @@ -141,10 +141,8 @@ struct drm_i915_private *mock_gem_device(void) dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); #if IS_ENABLED(CONFIG_IOMMU_API) && defined(CONFIG_INTEL_IOMMU) - /* HACK HACK HACK to disable iommu for the fake device; force identity mapping */ - memset(&iommu, 0, sizeof(iommu)); - iommu.priv = (void *)-1; - pdev->dev.iommu = &iommu; + /* HACK to disable iommu for the fake device; force identity mapping */ + pdev->dev.iommu = &fake_iommu; #endif pci_set_drvdata(pdev, i915); diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c index 6776ebb3246d..8a4235d9d9f1 100644 --- a/drivers/gpu/drm/imx/ipuv3-plane.c +++ b/drivers/gpu/drm/imx/ipuv3-plane.c @@ -447,7 +447,7 @@ static int ipu_plane_atomic_check(struct drm_plane *plane, if (fb->pitches[1] != fb->pitches[2]) return -EINVAL; - /* fall-through */ + fallthrough; case DRM_FORMAT_NV12: case DRM_FORMAT_NV16: ubo = drm_plane_state_to_ubo(state); diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index 3fc5511330b9..4d29568be3f5 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -831,13 +831,19 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev, drm_crtc_index(&mtk_crtc->base)); mtk_crtc->cmdq_client = NULL; } - ret = of_property_read_u32_index(priv->mutex_node, - "mediatek,gce-events", - drm_crtc_index(&mtk_crtc->base), - &mtk_crtc->cmdq_event); - if (ret) - dev_dbg(dev, "mtk_crtc %d failed to get mediatek,gce-events property\n", - drm_crtc_index(&mtk_crtc->base)); + + if (mtk_crtc->cmdq_client) { + ret = of_property_read_u32_index(priv->mutex_node, + "mediatek,gce-events", + drm_crtc_index(&mtk_crtc->base), + &mtk_crtc->cmdq_event); + if (ret) { + dev_dbg(dev, "mtk_crtc %d failed to get mediatek,gce-events property\n", + drm_crtc_index(&mtk_crtc->base)); + cmdq_mbox_destroy(mtk_crtc->cmdq_client); + mtk_crtc->cmdq_client = NULL; + } + } #endif return 0; } diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c index 57c88de9a329..526648885b97 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c @@ -496,6 +496,7 @@ int mtk_ddp_comp_init(struct device *dev, struct device_node *node, #if IS_REACHABLE(CONFIG_MTK_CMDQ) if (of_address_to_resource(node, 0, &res) != 0) { dev_err(dev, "Missing reg in %s node\n", node->full_name); + put_device(&larb_pdev->dev); return -EINVAL; } comp->regs_pa = res.start; diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index 040a8f393fe2..2d982740b1a4 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -27,7 +27,6 @@ #include "mtk_drm_crtc.h" #include "mtk_drm_ddp.h" -#include "mtk_drm_ddp.h" #include "mtk_drm_ddp_comp.h" #include "mtk_drm_drv.h" #include "mtk_drm_gem.h" @@ -165,7 +164,7 @@ static int mtk_drm_kms_init(struct drm_device *drm) ret = drmm_mode_config_init(drm); if (ret) - return ret; + goto put_mutex_dev; drm->mode_config.min_width = 64; drm->mode_config.min_height = 64; @@ -182,7 +181,7 @@ static int mtk_drm_kms_init(struct drm_device *drm) ret = component_bind_all(drm->dev, drm); if (ret) - return ret; + goto put_mutex_dev; /* * We currently support two fixed data streams, each optional, @@ -229,7 +228,7 @@ static int mtk_drm_kms_init(struct drm_device *drm) } if (!dma_dev->dma_parms) { ret = -ENOMEM; - goto err_component_unbind; + goto put_dma_dev; } ret = dma_set_max_seg_size(dma_dev, (unsigned int)DMA_BIT_MASK(32)); @@ -256,9 +255,12 @@ static int mtk_drm_kms_init(struct drm_device *drm) err_unset_dma_parms: if (private->dma_parms_allocated) dma_dev->dma_parms = NULL; +put_dma_dev: + put_device(private->dma_dev); err_component_unbind: component_unbind_all(drm->dev, drm); - +put_mutex_dev: + put_device(private->mutex_dev); return ret; } @@ -544,8 +546,13 @@ err_pm: pm_runtime_disable(dev); err_node: of_node_put(private->mutex_node); - for (i = 0; i < DDP_COMPONENT_ID_MAX; i++) + for (i = 0; i < DDP_COMPONENT_ID_MAX; i++) { of_node_put(private->comp_node[i]); + if (private->ddp_comp[i]) { + put_device(private->ddp_comp[i]->larb_dev); + private->ddp_comp[i] = NULL; + } + } return ret; } diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index 16fd99dcdacf..80b7a082e874 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -466,14 +466,13 @@ static void mtk_dsi_config_vdo_timing(struct mtk_dsi *dsi) horizontal_sync_active_byte = (vm->hsync_len * dsi_tmp_buf_bpp - 10); if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE) - horizontal_backporch_byte = - (vm->hback_porch * dsi_tmp_buf_bpp - 10); + horizontal_backporch_byte = vm->hback_porch * dsi_tmp_buf_bpp; else - horizontal_backporch_byte = ((vm->hback_porch + vm->hsync_len) * - dsi_tmp_buf_bpp - 10); + horizontal_backporch_byte = (vm->hback_porch + vm->hsync_len) * + dsi_tmp_buf_bpp; data_phy_cycles = timing->lpx + timing->da_hs_prepare + - timing->da_hs_zero + timing->da_hs_exit + 3; + timing->da_hs_zero + timing->da_hs_exit; if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST) { if ((vm->hfront_porch + vm->hback_porch) * dsi_tmp_buf_bpp > diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c index f2e9b429960b..a97725680d4e 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c @@ -1507,25 +1507,30 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, dev_err(dev, "Failed to get system configuration registers: %d\n", ret); - return ret; + goto put_device; } hdmi->sys_regmap = regmap; mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); hdmi->regs = devm_ioremap_resource(dev, mem); - if (IS_ERR(hdmi->regs)) - return PTR_ERR(hdmi->regs); + if (IS_ERR(hdmi->regs)) { + ret = PTR_ERR(hdmi->regs); + goto put_device; + } remote = of_graph_get_remote_node(np, 1, 0); - if (!remote) - return -EINVAL; + if (!remote) { + ret = -EINVAL; + goto put_device; + } if (!of_device_is_compatible(remote, "hdmi-connector")) { hdmi->next_bridge = of_drm_find_bridge(remote); if (!hdmi->next_bridge) { dev_err(dev, "Waiting for external bridge\n"); of_node_put(remote); - return -EPROBE_DEFER; + ret = -EPROBE_DEFER; + goto put_device; } } @@ -1534,7 +1539,8 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, dev_err(dev, "Failed to find ddc-i2c-bus node in %pOF\n", remote); of_node_put(remote); - return -EINVAL; + ret = -EINVAL; + goto put_device; } of_node_put(remote); @@ -1542,10 +1548,14 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, of_node_put(i2c_np); if (!hdmi->ddc_adpt) { dev_err(dev, "Failed to get ddc i2c adapter by node\n"); - return -EINVAL; + ret = -EINVAL; + goto put_device; } return 0; +put_device: + put_device(hdmi->cec_dev); + return ret; } /* diff --git a/drivers/gpu/drm/meson/meson_osd_afbcd.c b/drivers/gpu/drm/meson/meson_osd_afbcd.c index f12e0271f166..ffc6b584dbf8 100644 --- a/drivers/gpu/drm/meson/meson_osd_afbcd.c +++ b/drivers/gpu/drm/meson/meson_osd_afbcd.c @@ -205,7 +205,7 @@ static int meson_g12a_afbcd_pixel_fmt(u64 modifier, uint32_t format) /* YTR is forbidden for non XBGR formats */ if (modifier & AFBC_FORMAT_MOD_YTR) return -EINVAL; - /* fall through */ + fallthrough; case DRM_FORMAT_XBGR8888: case DRM_FORMAT_ABGR8888: return MAFBC_FMT_RGBA8888; diff --git a/drivers/gpu/drm/meson/meson_overlay.c b/drivers/gpu/drm/meson/meson_overlay.c index a8bcc70644df..1ffbbecafa22 100644 --- a/drivers/gpu/drm/meson/meson_overlay.c +++ b/drivers/gpu/drm/meson/meson_overlay.c @@ -654,7 +654,7 @@ static void meson_overlay_atomic_update(struct drm_plane *plane, priv->viu.vd1_addr2, priv->viu.vd1_stride2, priv->viu.vd1_height2); - /* fallthrough */ + fallthrough; case 2: gem = drm_fb_cma_get_gem_obj(fb, 1); priv->viu.vd1_addr1 = gem->paddr + fb->offsets[1]; @@ -666,7 +666,7 @@ static void meson_overlay_atomic_update(struct drm_plane *plane, priv->viu.vd1_addr1, priv->viu.vd1_stride1, priv->viu.vd1_height1); - /* fallthrough */ + fallthrough; case 1: gem = drm_fb_cma_get_gem_obj(fb, 0); priv->viu.vd1_addr0 = gem->paddr + fb->offsets[0]; diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c index 6021f8d9efd1..48fa49f69d6d 100644 --- a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c @@ -164,6 +164,11 @@ static int a2xx_hw_init(struct msm_gpu *gpu) if (ret) return ret; + gpu_write(gpu, REG_AXXX_CP_RB_CNTL, + MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE); + + gpu_write(gpu, REG_AXXX_CP_RB_BASE, lower_32_bits(gpu->rb[0]->iova)); + /* NOTE: PM4/micro-engine firmware registers look to be the same * for a2xx and a3xx.. we could possibly push that part down to * adreno_gpu base class. Or push both PM4 and PFP but diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c index 0a5ea9f56cb8..f6471145a7a6 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c @@ -211,6 +211,16 @@ static int a3xx_hw_init(struct msm_gpu *gpu) if (ret) return ret; + /* + * Use the default ringbuffer size and block size but disable the RPTR + * shadow + */ + gpu_write(gpu, REG_AXXX_CP_RB_CNTL, + MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE); + + /* Set the ringbuffer address */ + gpu_write(gpu, REG_AXXX_CP_RB_BASE, lower_32_bits(gpu->rb[0]->iova)); + /* setup access protection: */ gpu_write(gpu, REG_A3XX_CP_PROTECT_CTRL, 0x00000007); diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c index b9b26b2bf9c5..954753600625 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c @@ -267,6 +267,16 @@ static int a4xx_hw_init(struct msm_gpu *gpu) if (ret) return ret; + /* + * Use the default ringbuffer size and block size but disable the RPTR + * shadow + */ + gpu_write(gpu, REG_A4XX_CP_RB_CNTL, + MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE); + + /* Set the ringbuffer address */ + gpu_write(gpu, REG_A4XX_CP_RB_BASE, lower_32_bits(gpu->rb[0]->iova)); + /* Load PM4: */ ptr = (uint32_t *)(adreno_gpu->fw[ADRENO_FW_PM4]->data); len = adreno_gpu->fw[ADRENO_FW_PM4]->size / 4; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 9e63a190642c..91726da82ed6 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -59,7 +59,7 @@ static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit case MSM_SUBMIT_CMD_CTX_RESTORE_BUF: if (priv->lastctx == ctx) break; - /* fall-thru */ + fallthrough; case MSM_SUBMIT_CMD_BUF: /* copy commands into RB: */ obj = submit->bos[submit->cmd[i].idx].obj; @@ -150,7 +150,7 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, case MSM_SUBMIT_CMD_CTX_RESTORE_BUF: if (priv->lastctx == ctx) break; - /* fall-thru */ + fallthrough; case MSM_SUBMIT_CMD_BUF: OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3); OUT_RING(ring, lower_32_bits(submit->cmd[i].iova)); @@ -703,8 +703,6 @@ static int a5xx_hw_init(struct msm_gpu *gpu) if (ret) return ret; - a5xx_preempt_hw_init(gpu); - if (!adreno_is_a510(adreno_gpu)) a5xx_gpmu_ucode_init(gpu); @@ -712,6 +710,15 @@ static int a5xx_hw_init(struct msm_gpu *gpu) if (ret) return ret; + /* Set the ringbuffer address */ + gpu_write64(gpu, REG_A5XX_CP_RB_BASE, REG_A5XX_CP_RB_BASE_HI, + gpu->rb[0]->iova); + + gpu_write(gpu, REG_A5XX_CP_RB_CNTL, + MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE); + + a5xx_preempt_hw_init(gpu); + /* Disable the interrupts through the initial bringup stage */ gpu_write(gpu, REG_A5XX_RBBM_INT_0_MASK, A5XX_INT_MASK); @@ -1511,7 +1518,8 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) check_speed_bin(&pdev->dev); - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 4); + /* Restricting nr_rings to 1 to temporarily disable preemption */ + ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); if (ret) { a5xx_destroy(&(a5xx_gpu->base.base)); return ERR_PTR(ret); diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h index 54868d4e3958..1e5b1a15a70f 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h @@ -31,6 +31,7 @@ struct a5xx_gpu { struct msm_ringbuffer *next_ring; struct drm_gem_object *preempt_bo[MSM_GPU_MAX_RINGS]; + struct drm_gem_object *preempt_counters_bo[MSM_GPU_MAX_RINGS]; struct a5xx_preempt_record *preempt[MSM_GPU_MAX_RINGS]; uint64_t preempt_iova[MSM_GPU_MAX_RINGS]; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c index 9cf9353a7ff1..9f3fe177b00e 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c @@ -226,19 +226,31 @@ static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu, struct adreno_gpu *adreno_gpu = &a5xx_gpu->base; struct msm_gpu *gpu = &adreno_gpu->base; struct a5xx_preempt_record *ptr; - struct drm_gem_object *bo = NULL; - u64 iova = 0; + void *counters; + struct drm_gem_object *bo = NULL, *counters_bo = NULL; + u64 iova = 0, counters_iova = 0; ptr = msm_gem_kernel_new(gpu->dev, A5XX_PREEMPT_RECORD_SIZE + A5XX_PREEMPT_COUNTER_SIZE, - MSM_BO_UNCACHED, gpu->aspace, &bo, &iova); + MSM_BO_UNCACHED | MSM_BO_MAP_PRIV, gpu->aspace, &bo, &iova); if (IS_ERR(ptr)) return PTR_ERR(ptr); + /* The buffer to store counters needs to be unprivileged */ + counters = msm_gem_kernel_new(gpu->dev, + A5XX_PREEMPT_COUNTER_SIZE, + MSM_BO_UNCACHED, gpu->aspace, &counters_bo, &counters_iova); + if (IS_ERR(counters)) { + msm_gem_kernel_put(bo, gpu->aspace, true); + return PTR_ERR(counters); + } + msm_gem_object_set_name(bo, "preempt"); + msm_gem_object_set_name(counters_bo, "preempt_counters"); a5xx_gpu->preempt_bo[ring->id] = bo; + a5xx_gpu->preempt_counters_bo[ring->id] = counters_bo; a5xx_gpu->preempt_iova[ring->id] = iova; a5xx_gpu->preempt[ring->id] = ptr; @@ -249,7 +261,7 @@ static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu, ptr->data = 0; ptr->cntl = MSM_GPU_RB_CNTL_DEFAULT; ptr->rptr_addr = rbmemptr(ring, rptr); - ptr->counter = iova + A5XX_PREEMPT_RECORD_SIZE; + ptr->counter = counters_iova; return 0; } @@ -260,8 +272,11 @@ void a5xx_preempt_fini(struct msm_gpu *gpu) struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); int i; - for (i = 0; i < gpu->nr_rings; i++) + for (i = 0; i < gpu->nr_rings; i++) { msm_gem_kernel_put(a5xx_gpu->preempt_bo[i], gpu->aspace, true); + msm_gem_kernel_put(a5xx_gpu->preempt_counters_bo[i], + gpu->aspace, true); + } } void a5xx_preempt_init(struct msm_gpu *gpu) diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index b67b38c8fadf..e1c7bcd1b1eb 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -133,7 +133,7 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp) if (!gmu->legacy) { a6xx_hfi_set_freq(gmu, perf_index); - icc_set_bw(gpu->icc_path, 0, MBps_to_icc(7216)); + dev_pm_opp_set_bw(&gpu->pdev->dev, opp); pm_runtime_put(gmu->dev); return; } @@ -157,11 +157,7 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp) if (ret) dev_err(gmu->dev, "GMU set GPU frequency error: %d\n", ret); - /* - * Eventually we will want to scale the path vote with the frequency but - * for now leave it at max so that the performance is nominal. - */ - icc_set_bw(gpu->icc_path, 0, MBps_to_icc(7216)); + dev_pm_opp_set_bw(&gpu->pdev->dev, opp); pm_runtime_put(gmu->dev); } @@ -204,6 +200,16 @@ static int a6xx_gmu_start(struct a6xx_gmu *gmu) { int ret; u32 val; + u32 mask, reset_val; + + val = gmu_read(gmu, REG_A6XX_GMU_CM3_DTCM_START + 0xff8); + if (val <= 0x20010004) { + mask = 0xffffffff; + reset_val = 0xbabeface; + } else { + mask = 0x1ff; + reset_val = 0x100; + } gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 1); @@ -215,7 +221,7 @@ static int a6xx_gmu_start(struct a6xx_gmu *gmu) gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 0); ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_CM3_FW_INIT_RESULT, val, - val == 0xbabeface, 100, 10000); + (val & mask) == reset_val, 100, 10000); if (ret) DRM_DEV_ERROR(gmu->dev, "GMU firmware initialization timed out\n"); @@ -602,7 +608,7 @@ static void a6xx_gmu_power_config(struct a6xx_gmu *gmu) gmu_rmw(gmu, REG_A6XX_GMU_PWR_COL_INTER_FRAME_CTRL, 0, A6XX_GMU_PWR_COL_INTER_FRAME_CTRL_IFPC_ENABLE | A6XX_GMU_PWR_COL_INTER_FRAME_CTRL_HM_POWER_COLLAPSE_ENABLE); - /* Fall through */ + fallthrough; case GMU_IDLE_STATE_SPTP: gmu_write(gmu, REG_A6XX_GMU_PWR_COL_SPTPRAC_HYST, GMU_PWR_COL_HYST); @@ -845,10 +851,24 @@ static void a6xx_gmu_set_initial_freq(struct msm_gpu *gpu, struct a6xx_gmu *gmu) if (IS_ERR_OR_NULL(gpu_opp)) return; + gmu->freq = 0; /* so a6xx_gmu_set_freq() doesn't exit early */ a6xx_gmu_set_freq(gpu, gpu_opp); dev_pm_opp_put(gpu_opp); } +static void a6xx_gmu_set_initial_bw(struct msm_gpu *gpu, struct a6xx_gmu *gmu) +{ + struct dev_pm_opp *gpu_opp; + unsigned long gpu_freq = gmu->gpu_freqs[gmu->current_perf_index]; + + gpu_opp = dev_pm_opp_find_freq_exact(&gpu->pdev->dev, gpu_freq, true); + if (IS_ERR_OR_NULL(gpu_opp)) + return; + + dev_pm_opp_set_bw(&gpu->pdev->dev, gpu_opp); + dev_pm_opp_put(gpu_opp); +} + int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu) { struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; @@ -882,7 +902,7 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu) } /* Set the bus quota to a reasonable value for boot */ - icc_set_bw(gpu->icc_path, 0, MBps_to_icc(3072)); + a6xx_gmu_set_initial_bw(gpu, gmu); /* Enable the GMU interrupt */ gmu_write(gmu, REG_A6XX_GMU_AO_HOST_INTERRUPT_CLR, ~0); @@ -1051,7 +1071,7 @@ int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu) a6xx_gmu_shutdown(gmu); /* Remove the bus vote */ - icc_set_bw(gpu->icc_path, 0, 0); + dev_pm_opp_set_bw(&gpu->pdev->dev, NULL); /* * Make sure the GX domain is off before turning off the GMU (CX) diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index c5a3e4d4c007..66a95e22b7b3 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -117,7 +117,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, case MSM_SUBMIT_CMD_CTX_RESTORE_BUF: if (priv->lastctx == ctx) break; - /* fall-thru */ + fallthrough; case MSM_SUBMIT_CMD_BUF: OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3); OUT_RING(ring, lower_32_bits(submit->cmd[i].iova)); @@ -678,7 +678,8 @@ static int a6xx_hw_init(struct msm_gpu *gpu) A6XX_PROTECT_RDONLY(0x980, 0x4)); gpu_write(gpu, REG_A6XX_CP_PROTECT(25), A6XX_PROTECT_RW(0xa630, 0x0)); - if (adreno_is_a650(adreno_gpu)) { + /* Enable expanded apriv for targets that support it */ + if (gpu->hw_apriv) { gpu_write(gpu, REG_A6XX_CP_APRIV_CNTL, (1 << 6) | (1 << 5) | (1 << 3) | (1 << 2) | (1 << 1)); } @@ -694,6 +695,13 @@ static int a6xx_hw_init(struct msm_gpu *gpu) if (ret) goto out; + /* Set the ringbuffer address */ + gpu_write64(gpu, REG_A6XX_CP_RB_BASE, REG_A6XX_CP_RB_BASE_HI, + gpu->rb[0]->iova); + + gpu_write(gpu, REG_A6XX_CP_RB_CNTL, + MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE); + /* Always come up on rb 0 */ a6xx_gpu->cur_ring = gpu->rb[0]; @@ -1056,6 +1064,9 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) adreno_gpu->registers = NULL; adreno_gpu->reg_offsets = a6xx_register_offsets; + if (adreno_is_a650(adreno_gpu)) + adreno_gpu->base.hw_apriv = true; + ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); if (ret) { a6xx_destroy(&(a6xx_gpu->base.base)); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index 959656ad6987..b12f5b4a1bea 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -938,7 +938,8 @@ struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu) msm_gem_kernel_put(dumper.bo, gpu->aspace, true); } - a6xx_get_debugbus(gpu, a6xx_state); + if (snapshot_debugbus) + a6xx_get_debugbus(gpu, a6xx_state); return &a6xx_state->base; } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h index 846fd5b54c23..2fb58b7098e4 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h @@ -372,7 +372,7 @@ static const struct a6xx_indexed_registers { u32 data; u32 count; } a6xx_indexed_reglist[] = { - { "CP_SEQ_STAT", REG_A6XX_CP_SQE_STAT_ADDR, + { "CP_SQE_STAT", REG_A6XX_CP_SQE_STAT_ADDR, REG_A6XX_CP_SQE_STAT_DATA, 0x33 }, { "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR, REG_A6XX_CP_DRAW_STATE_DATA, 0x100 }, diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 4e84f3c76f4f..9eeb46bf2a5d 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -14,6 +14,10 @@ bool hang_debug = false; MODULE_PARM_DESC(hang_debug, "Dump registers when hang is detected (can be slow!)"); module_param_named(hang_debug, hang_debug, bool, 0600); +bool snapshot_debugbus = false; +MODULE_PARM_DESC(snapshot_debugbus, "Include debugbus sections in GPU devcoredump (if not fused off)"); +module_param_named(snapshot_debugbus, snapshot_debugbus, bool, 0600); + static const struct adreno_info gpulist[] = { { .rev = ADRENO_REV(2, 0, 0, 0), diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index e23641a5ec84..862dd35b27d3 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -396,30 +396,10 @@ int adreno_hw_init(struct msm_gpu *gpu) ring->next = ring->start; /* reset completed fence seqno: */ - ring->memptrs->fence = ring->seqno; + ring->memptrs->fence = ring->fctx->completed_fence; ring->memptrs->rptr = 0; } - /* - * Setup REG_CP_RB_CNTL. The same value is used across targets (with - * the excpetion of A430 that disables the RPTR shadow) - the cacluation - * for the ringbuffer size and block size is moved to msm_gpu.h for the - * pre-processor to deal with and the A430 variant is ORed in here - */ - adreno_gpu_write(adreno_gpu, REG_ADRENO_CP_RB_CNTL, - MSM_GPU_RB_CNTL_DEFAULT | - (adreno_is_a430(adreno_gpu) ? AXXX_CP_RB_CNTL_NO_UPDATE : 0)); - - /* Setup ringbuffer address - use ringbuffer[0] for GPU init */ - adreno_gpu_write64(adreno_gpu, REG_ADRENO_CP_RB_BASE, - REG_ADRENO_CP_RB_BASE_HI, gpu->rb[0]->iova); - - if (!adreno_is_a430(adreno_gpu)) { - adreno_gpu_write64(adreno_gpu, REG_ADRENO_CP_RB_RPTR_ADDR, - REG_ADRENO_CP_RB_RPTR_ADDR_HI, - rbmemptr(gpu->rb[0], rptr)); - } - return 0; } @@ -427,11 +407,8 @@ int adreno_hw_init(struct msm_gpu *gpu) static uint32_t get_rptr(struct adreno_gpu *adreno_gpu, struct msm_ringbuffer *ring) { - if (adreno_is_a430(adreno_gpu)) - return ring->memptrs->rptr = adreno_gpu_read( - adreno_gpu, REG_ADRENO_CP_RB_RPTR); - else - return ring->memptrs->rptr; + return ring->memptrs->rptr = adreno_gpu_read( + adreno_gpu, REG_ADRENO_CP_RB_RPTR); } struct msm_ringbuffer *adreno_active_ring(struct msm_gpu *gpu) @@ -474,7 +451,7 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, /* ignore if there has not been a ctx switch: */ if (priv->lastctx == ctx) break; - /* fall-thru */ + fallthrough; case MSM_SUBMIT_CMD_BUF: OUT_PKT3(ring, adreno_is_a4xx(adreno_gpu) ? CP_INDIRECT_BUFFER_PFE : CP_INDIRECT_BUFFER_PFD, 2); diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index 99bb468f5f24..e55abae365b5 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -21,6 +21,8 @@ #define REG_SKIP ~0 #define REG_ADRENO_SKIP(_offset) [_offset] = REG_SKIP +extern bool snapshot_debugbus; + /** * adreno_regs: List of registers that are used in across all * 3D devices. Each device type has different offset value for the same diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index f272a8d0f95b..c2729f71e2fa 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -827,7 +827,7 @@ static void dpu_crtc_enable(struct drm_crtc *crtc, { struct dpu_crtc *dpu_crtc; struct drm_encoder *encoder; - bool request_bandwidth; + bool request_bandwidth = false; if (!crtc) { DPU_ERROR("invalid crtc\n"); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index a97f6d2e5a08..bd6def436c65 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -599,7 +599,10 @@ static int dpu_encoder_virt_atomic_check( dpu_kms = to_dpu_kms(priv->kms); mode = &crtc_state->mode; adj_mode = &crtc_state->adjusted_mode; - global_state = dpu_kms_get_existing_global_state(dpu_kms); + global_state = dpu_kms_get_global_state(crtc_state->state); + if (IS_ERR(global_state)) + return PTR_ERR(global_state); + trace_dpu_enc_atomic_check(DRMID(drm_enc)); /* perform atomic check on the first physical encoder (master) */ @@ -625,12 +628,15 @@ static int dpu_encoder_virt_atomic_check( /* Reserve dynamic resources now. */ if (!ret) { /* - * Avoid reserving resources when mode set is pending. Topology - * info may not be available to complete reservation. + * Release and Allocate resources on every modeset + * Dont allocate when active is false. */ if (drm_atomic_crtc_needs_modeset(crtc_state)) { - ret = dpu_rm_reserve(&dpu_kms->rm, global_state, - drm_enc, crtc_state, topology); + dpu_rm_release(global_state, drm_enc); + + if (!crtc_state->active_changed || crtc_state->active) + ret = dpu_rm_reserve(&dpu_kms->rm, global_state, + drm_enc, crtc_state, topology); } } @@ -1181,7 +1187,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc) struct dpu_encoder_virt *dpu_enc = NULL; struct msm_drm_private *priv; struct dpu_kms *dpu_kms; - struct dpu_global_state *global_state; int i = 0; if (!drm_enc) { @@ -1200,7 +1205,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc) priv = drm_enc->dev->dev_private; dpu_kms = to_dpu_kms(priv->kms); - global_state = dpu_kms_get_existing_global_state(dpu_kms); trace_dpu_enc_disable(DRMID(drm_enc)); @@ -1230,8 +1234,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc) DPU_DEBUG_ENC(dpu_enc, "encoder disabled\n"); - dpu_rm_release(global_state, drm_enc); - mutex_unlock(&dpu_enc->enc_lock); } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index 33f6c56f01ed..29e373d2e7b5 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -866,9 +866,9 @@ static int dpu_plane_atomic_check(struct drm_plane *plane, crtc_state = drm_atomic_get_new_crtc_state(state->state, state->crtc); - min_scale = FRAC_16_16(1, pdpu->pipe_sblk->maxdwnscale); + min_scale = FRAC_16_16(1, pdpu->pipe_sblk->maxupscale); ret = drm_atomic_helper_check_plane_state(state, crtc_state, min_scale, - pdpu->pipe_sblk->maxupscale << 16, + pdpu->pipe_sblk->maxdwnscale << 16, true, true); if (ret) { DPU_DEBUG_PLANE(pdpu, "Check plane state failed (%d)\n", ret); diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c index 5ccfad794c6a..561bfa48841c 100644 --- a/drivers/gpu/drm/msm/msm_atomic.c +++ b/drivers/gpu/drm/msm/msm_atomic.c @@ -27,6 +27,34 @@ int msm_atomic_prepare_fb(struct drm_plane *plane, return msm_framebuffer_prepare(new_state->fb, kms->aspace); } +/* + * Helpers to control vblanks while we flush.. basically just to ensure + * that vblank accounting is switched on, so we get valid seqn/timestamp + * on pageflip events (if requested) + */ + +static void vblank_get(struct msm_kms *kms, unsigned crtc_mask) +{ + struct drm_crtc *crtc; + + for_each_crtc_mask(kms->dev, crtc, crtc_mask) { + if (!crtc->state->active) + continue; + drm_crtc_vblank_get(crtc); + } +} + +static void vblank_put(struct msm_kms *kms, unsigned crtc_mask) +{ + struct drm_crtc *crtc; + + for_each_crtc_mask(kms->dev, crtc, crtc_mask) { + if (!crtc->state->active) + continue; + drm_crtc_vblank_put(crtc); + } +} + static void msm_atomic_async_commit(struct msm_kms *kms, int crtc_idx) { unsigned crtc_mask = BIT(crtc_idx); @@ -44,6 +72,8 @@ static void msm_atomic_async_commit(struct msm_kms *kms, int crtc_idx) kms->funcs->enable_commit(kms); + vblank_get(kms, crtc_mask); + /* * Flush hardware updates: */ @@ -58,6 +88,8 @@ static void msm_atomic_async_commit(struct msm_kms *kms, int crtc_idx) kms->funcs->wait_flush(kms, crtc_mask); trace_msm_atomic_wait_flush_finish(crtc_mask); + vblank_put(kms, crtc_mask); + mutex_lock(&kms->commit_lock); kms->funcs->complete_commit(kms, crtc_mask); mutex_unlock(&kms->commit_lock); @@ -221,6 +253,8 @@ void msm_atomic_commit_tail(struct drm_atomic_state *state) */ kms->pending_crtc_mask &= ~crtc_mask; + vblank_get(kms, crtc_mask); + /* * Flush hardware updates: */ @@ -235,6 +269,8 @@ void msm_atomic_commit_tail(struct drm_atomic_state *state) kms->funcs->wait_flush(kms, crtc_mask); trace_msm_atomic_wait_flush_finish(crtc_mask); + vblank_put(kms, crtc_mask); + mutex_lock(&kms->commit_lock); kms->funcs->complete_commit(kms, crtc_mask); mutex_unlock(&kms->commit_lock); diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 7d641c7e3514..79333842f70a 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -1320,6 +1320,13 @@ static int msm_pdev_remove(struct platform_device *pdev) return 0; } +static void msm_pdev_shutdown(struct platform_device *pdev) +{ + struct drm_device *drm = platform_get_drvdata(pdev); + + drm_atomic_helper_shutdown(drm); +} + static const struct of_device_id dt_match[] = { { .compatible = "qcom,mdp4", .data = (void *)KMS_MDP4 }, { .compatible = "qcom,mdss", .data = (void *)KMS_MDP5 }, @@ -1332,6 +1339,7 @@ MODULE_DEVICE_TABLE(of, dt_match); static struct platform_driver msm_platform_driver = { .probe = msm_pdev_probe, .remove = msm_pdev_remove, + .shutdown = msm_pdev_shutdown, .driver = { .name = "msm", .of_match_table = dt_match, diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index d5645472b25d..57ddc9438351 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -908,7 +908,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, memptrs = msm_gem_kernel_new(drm, sizeof(struct msm_rbmemptrs) * nr_rings, - MSM_BO_UNCACHED, gpu->aspace, &gpu->memptrs_bo, + check_apriv(gpu, MSM_BO_UNCACHED), gpu->aspace, &gpu->memptrs_bo, &memptrs_iova); if (IS_ERR(memptrs)) { diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index 0db117a7339b..37cffac4cbe3 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -15,6 +15,7 @@ #include "msm_drv.h" #include "msm_fence.h" #include "msm_ringbuffer.h" +#include "msm_gem.h" struct msm_gem_submit; struct msm_gpu_perfcntr; @@ -139,6 +140,8 @@ struct msm_gpu { } devfreq; struct msm_gpu_state *crashstate; + /* True if the hardware supports expanded apriv (a650 and newer) */ + bool hw_apriv; }; /* It turns out that all targets use the same ringbuffer size */ @@ -327,4 +330,12 @@ static inline void msm_gpu_crashstate_put(struct msm_gpu *gpu) mutex_unlock(&gpu->dev->struct_mutex); } +/* + * Simple macro to semi-cleanly add the MAP_PRIV flag for targets that can + * support expanded privileges + */ +#define check_apriv(gpu, flags) \ + (((gpu)->hw_apriv ? MSM_BO_MAP_PRIV : 0) | (flags)) + + #endif /* __MSM_GPU_H__ */ diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c index e397c44cc011..935bf9b1d941 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.c +++ b/drivers/gpu/drm/msm/msm_ringbuffer.c @@ -27,7 +27,8 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id, ring->id = id; ring->start = msm_gem_kernel_new(gpu->dev, MSM_GPU_RINGBUFFER_SZ, - MSM_BO_WC, gpu->aspace, &ring->bo, &ring->iova); + check_apriv(gpu, MSM_BO_WC | MSM_BO_GPU_READONLY), + gpu->aspace, &ring->bo, &ring->iova); if (IS_ERR(ring->start)) { ret = PTR_ERR(ring->start); diff --git a/drivers/gpu/drm/nouveau/dispnv50/core507d.c b/drivers/gpu/drm/nouveau/dispnv50/core507d.c index ad1f09a143aa..248edf69e168 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/core507d.c +++ b/drivers/gpu/drm/nouveau/dispnv50/core507d.c @@ -50,7 +50,10 @@ core507d_update(struct nv50_core *core, u32 *interlock, bool ntfy) interlock[NV50_DISP_INTERLOCK_OVLY] | NVDEF(NV507D, UPDATE, NOT_DRIVER_FRIENDLY, FALSE) | NVDEF(NV507D, UPDATE, NOT_DRIVER_UNFRIENDLY, FALSE) | - NVDEF(NV507D, UPDATE, INHIBIT_INTERRUPTS, FALSE)); + NVDEF(NV507D, UPDATE, INHIBIT_INTERRUPTS, FALSE), + + SET_NOTIFIER_CONTROL, + NVDEF(NV507D, SET_NOTIFIER_CONTROL, NOTIFY, DISABLE)); return PUSH_KICK(push); } diff --git a/drivers/gpu/drm/nouveau/dispnv50/crcc37d.c b/drivers/gpu/drm/nouveau/dispnv50/crcc37d.c index 9afe9a87bde0..814e5bd97446 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/crcc37d.c +++ b/drivers/gpu/drm/nouveau/dispnv50/crcc37d.c @@ -6,7 +6,7 @@ #include "disp.h" #include "head.h" -#include <nvif/push507c.h> +#include <nvif/pushc37b.h> #include <nvhw/class/clc37d.h> diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index e7874877da85..1ed242070001 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -257,6 +257,12 @@ nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp, dmac->push->end = dmac->push->bgn; dmac->max = 0x1000/4 - 1; + /* EVO channels are affected by a HW bug where the last 12 DWORDs + * of the push buffer aren't able to be used safely. + */ + if (disp->oclass < GV100_DISP) + dmac->max -= 12; + args->pushbuf = nvif_handle(&dmac->_push.mem.object); ret = nv50_chan_create(device, disp, oclass, head, data, size, diff --git a/drivers/gpu/drm/nouveau/include/nvif/push507c.h b/drivers/gpu/drm/nouveau/include/nvif/push507c.h index 889467f13fd9..7917bead4845 100644 --- a/drivers/gpu/drm/nouveau/include/nvif/push507c.h +++ b/drivers/gpu/drm/nouveau/include/nvif/push507c.h @@ -20,6 +20,6 @@ PUSH_ASSERT(!((o) & ~DRF_SMASK(NV507C_DMA_JUMP_OFFSET)), "offset"); \ PUSH_DATA__((p), NVDEF(NV507C, DMA, OPCODE, JUMP) | \ NVVAL(NV507C, DMA, JUMP_OFFSET, (o) >> 2), \ - "jump 0x%08x - %s", (u32)(o), __func__); \ + " jump 0x%08x - %s", (u32)(o), __func__); \ } while(0) #endif diff --git a/drivers/gpu/drm/omapdrm/dss/venc.c b/drivers/gpu/drm/omapdrm/dss/venc.c index e0817934ee16..bd12eae0cb31 100644 --- a/drivers/gpu/drm/omapdrm/dss/venc.c +++ b/drivers/gpu/drm/omapdrm/dss/venc.c @@ -597,7 +597,7 @@ static void venc_bridge_mode_set(struct drm_bridge *bridge, switch (venc_mode) { default: WARN_ON_ONCE(1); - /* Fall-through */ + fallthrough; case VENC_MODE_PAL: venc->config = &venc_config_pal_trm; break; diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c index ba20c6f03719..886e9959496f 100644 --- a/drivers/gpu/drm/radeon/ci_dpm.c +++ b/drivers/gpu/drm/radeon/ci_dpm.c @@ -4856,7 +4856,7 @@ static void ci_request_link_speed_change_before_state_change(struct radeon_devic pi->force_pcie_gen = RADEON_PCIE_GEN2; if (current_link_speed == RADEON_PCIE_GEN2) break; - /* fall through */ + fallthrough; case RADEON_PCIE_GEN2: if (radeon_acpi_pcie_performance_request(rdev, PCIE_PERF_REQ_PECI_GEN2, false) == 0) break; diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c index 3b7ead5be5bf..73f67bf222e1 100644 --- a/drivers/gpu/drm/radeon/r300.c +++ b/drivers/gpu/drm/radeon/r300.c @@ -820,7 +820,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p, ((idx_value >> 21) & 0xF)); return -EINVAL; } - /* Fall through. */ + fallthrough; case 6: track->cb[i].cpp = 4; break; @@ -971,7 +971,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p, return -EINVAL; } /* The same rules apply as for DXT3/5. */ - /* Fall through. */ + fallthrough; case R300_TX_FORMAT_DXT3: case R300_TX_FORMAT_DXT5: track->textures[i].cpp = 1; diff --git a/drivers/gpu/drm/radeon/r420.c b/drivers/gpu/drm/radeon/r420.c index 1d4c04e0a449..50b89b6d9a6c 100644 --- a/drivers/gpu/drm/radeon/r420.c +++ b/drivers/gpu/drm/radeon/r420.c @@ -115,7 +115,7 @@ void r420_pipes_init(struct radeon_device *rdev) default: /* force to 1 pipe */ num_pipes = 1; - /* fall through */ + fallthrough; case 1: tmp = (0 << 1); break; diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c index 49e8266461f8..390a9621604a 100644 --- a/drivers/gpu/drm/radeon/r600_cs.c +++ b/drivers/gpu/drm/radeon/r600_cs.c @@ -487,7 +487,7 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i) return -EINVAL; } } - /* fall through */ + fallthrough; case V_0280A0_CLEAR_ENABLE: { uint32_t block_max = G_028100_CMASK_BLOCK_MAX(track->cb_color_mask[i]); @@ -1535,7 +1535,7 @@ static int r600_check_texture_resource(struct radeon_cs_parser *p, u32 idx, break; case V_038000_SQ_TEX_DIM_2D_ARRAY_MSAA: is_array = true; - /* fall through */ + fallthrough; case V_038000_SQ_TEX_DIM_2D_MSAA: array_check.nsamples = 1 << llevel; llevel = 0; diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c index 1ad5c3b86b64..57fb3eb3a4b4 100644 --- a/drivers/gpu/drm/radeon/radeon_uvd.c +++ b/drivers/gpu/drm/radeon/radeon_uvd.c @@ -454,7 +454,7 @@ static int radeon_uvd_validate_codec(struct radeon_cs_parser *p, if (p->rdev->family >= CHIP_PALM) return 0; - /* fall through */ + fallthrough; default: DRM_ERROR("UVD codec not supported by hardware %d!\n", stream_type); diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index a167e1c36d24..d1c73e9db889 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -5744,7 +5744,7 @@ static void si_request_link_speed_change_before_state_change(struct radeon_devic si_pi->force_pcie_gen = RADEON_PCIE_GEN2; if (current_link_speed == RADEON_PCIE_GEN2) break; - /* fall through */ + fallthrough; case RADEON_PCIE_GEN2: if (radeon_acpi_pcie_performance_request(rdev, PCIE_PERF_REQ_PECI_GEN2, false) == 0) break; diff --git a/drivers/gpu/drm/radeon/uvd_v1_0.c b/drivers/gpu/drm/radeon/uvd_v1_0.c index f858d8d06347..800721153d51 100644 --- a/drivers/gpu/drm/radeon/uvd_v1_0.c +++ b/drivers/gpu/drm/radeon/uvd_v1_0.c @@ -219,7 +219,7 @@ done: WREG32(RS_DQ_RD_RET_CONF, 0x3f); WREG32(MC_CONFIG, 0x1f); - /* fall through */ + fallthrough; case CHIP_RV670: case CHIP_RV635: diff --git a/drivers/gpu/drm/savage/savage_state.c b/drivers/gpu/drm/savage/savage_state.c index a2ac25c11c90..e0d40ae67d54 100644 --- a/drivers/gpu/drm/savage/savage_state.c +++ b/drivers/gpu/drm/savage/savage_state.c @@ -306,7 +306,7 @@ static int savage_dispatch_dma_prim(drm_savage_private_t * dev_priv, case SAVAGE_PRIM_TRILIST_201: reorder = 1; prim = SAVAGE_PRIM_TRILIST; - /* fall through */ + fallthrough; case SAVAGE_PRIM_TRILIST: if (n % 3 != 0) { DRM_ERROR("wrong number of vertices %u in TRILIST\n", @@ -444,7 +444,7 @@ static int savage_dispatch_vb_prim(drm_savage_private_t * dev_priv, case SAVAGE_PRIM_TRILIST_201: reorder = 1; prim = SAVAGE_PRIM_TRILIST; - /* fall through */ + fallthrough; case SAVAGE_PRIM_TRILIST: if (n % 3 != 0) { DRM_ERROR("wrong number of vertices %u in TRILIST\n", @@ -566,7 +566,7 @@ static int savage_dispatch_dma_idx(drm_savage_private_t * dev_priv, case SAVAGE_PRIM_TRILIST_201: reorder = 1; prim = SAVAGE_PRIM_TRILIST; - /* fall through */ + fallthrough; case SAVAGE_PRIM_TRILIST: if (n % 3 != 0) { DRM_ERROR("wrong number of indices %u in TRILIST\n", n); @@ -705,7 +705,7 @@ static int savage_dispatch_vb_idx(drm_savage_private_t * dev_priv, case SAVAGE_PRIM_TRILIST_201: reorder = 1; prim = SAVAGE_PRIM_TRILIST; - /* fall through */ + fallthrough; case SAVAGE_PRIM_TRILIST: if (n % 3 != 0) { DRM_ERROR("wrong number of indices %u in TRILIST\n", n); @@ -1066,7 +1066,7 @@ int savage_bci_cmdbuf(struct drm_device *dev, void *data, struct drm_file *file_ ret = -EINVAL; goto done; } - /* fall through */ + fallthrough; case SAVAGE_CMD_DMA_PRIM: case SAVAGE_CMD_VB_PRIM: if (!first_draw_cmd) diff --git a/drivers/gpu/drm/sti/sti_hdmi.c b/drivers/gpu/drm/sti/sti_hdmi.c index 008f07923bbc..38a558768e53 100644 --- a/drivers/gpu/drm/sti/sti_hdmi.c +++ b/drivers/gpu/drm/sti/sti_hdmi.c @@ -850,13 +850,13 @@ static int hdmi_audio_configure(struct sti_hdmi *hdmi) switch (info->channels) { case 8: audio_cfg |= HDMI_AUD_CFG_CH78_VALID; - /* fall through */ + fallthrough; case 6: audio_cfg |= HDMI_AUD_CFG_CH56_VALID; - /* fall through */ + fallthrough; case 4: audio_cfg |= HDMI_AUD_CFG_CH34_VALID | HDMI_AUD_CFG_8CH; - /* fall through */ + fallthrough; case 2: audio_cfg |= HDMI_AUD_CFG_CH12_VALID; break; diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index 24d95f058918..e40c542254f6 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -195,7 +195,7 @@ void sun4i_tcon_set_status(struct sun4i_tcon *tcon, switch (encoder->encoder_type) { case DRM_MODE_ENCODER_LVDS: is_lvds = true; - /* Fallthrough */ + fallthrough; case DRM_MODE_ENCODER_DSI: case DRM_MODE_ENCODER_NONE: channel = 0; @@ -342,7 +342,7 @@ static void sun4i_tcon0_mode_set_dithering(struct sun4i_tcon *tcon, /* R and B components are only 5 bits deep */ val |= SUN4I_TCON0_FRM_CTL_MODE_R; val |= SUN4I_TCON0_FRM_CTL_MODE_B; - /* Fall through */ + fallthrough; case MEDIA_BUS_FMT_RGB666_1X18: case MEDIA_BUS_FMT_RGB666_1X7X3_SPWG: /* Fall through: enable dithering */ diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c index 32d4c3f7fc4e..de8a11abd66a 100644 --- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c +++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c @@ -1027,7 +1027,7 @@ static ssize_t sun6i_dsi_transfer(struct mipi_dsi_host *host, ret = sun6i_dsi_dcs_read(dsi, msg); break; } - /* Else, fall through */ + fallthrough; default: ret = -EINVAL; diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c index 9a0b3240bc58..424ad60b4f38 100644 --- a/drivers/gpu/drm/tegra/dc.c +++ b/drivers/gpu/drm/tegra/dc.c @@ -135,7 +135,7 @@ static inline u32 compute_dda_inc(unsigned int in, unsigned int out, bool v, default: WARN_ON_ONCE(1); - /* fallthrough */ + fallthrough; case 4: max = 4; break; diff --git a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c index 1856962411c7..518220bd092a 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c @@ -386,7 +386,7 @@ static void tilcdc_crtc_set_mode(struct drm_crtc *crtc) case DRM_FORMAT_XBGR8888: case DRM_FORMAT_XRGB8888: reg |= LCDC_V2_TFT_24BPP_UNPACK; - /* fallthrough */ + fallthrough; case DRM_FORMAT_BGR888: case DRM_FORMAT_RGB888: reg |= LCDC_V2_TFT_24BPP_MODE; diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 33526c5df0e8..4732dcc80e11 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -525,7 +525,7 @@ int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr, if (unlikely(ret != 0)) return ret; } - /* fall through */ + fallthrough; case TTM_PL_TT: ret = ttm_bo_vm_access_kmap(bo, offset, buf, len, write); break; diff --git a/drivers/gpu/drm/via/via_dmablit.c b/drivers/gpu/drm/via/via_dmablit.c index 551fa31629af..5771bb53ce6a 100644 --- a/drivers/gpu/drm/via/via_dmablit.c +++ b/drivers/gpu/drm/via/via_dmablit.c @@ -179,21 +179,21 @@ via_free_sg_info(struct pci_dev *pdev, drm_via_sg_info_t *vsg) switch (vsg->state) { case dr_via_device_mapped: via_unmap_blit_from_device(pdev, vsg); - /* fall through */ + fallthrough; case dr_via_desc_pages_alloc: for (i = 0; i < vsg->num_desc_pages; ++i) { if (vsg->desc_pages[i] != NULL) free_page((unsigned long)vsg->desc_pages[i]); } kfree(vsg->desc_pages); - /* fall through */ + fallthrough; case dr_via_pages_locked: unpin_user_pages_dirty_lock(vsg->pages, vsg->num_pages, (vsg->direction == DMA_FROM_DEVICE)); - /* fall through */ + fallthrough; case dr_via_pages_alloc: vfree(vsg->pages); - /* fall through */ + fallthrough; default: vsg->state = dr_via_sg_init; } diff --git a/drivers/gpu/drm/xen/xen_drm_front.c b/drivers/gpu/drm/xen/xen_drm_front.c index 013c9e0e412c..cc93a8c9547b 100644 --- a/drivers/gpu/drm/xen/xen_drm_front.c +++ b/drivers/gpu/drm/xen/xen_drm_front.c @@ -649,9 +649,7 @@ static void displback_changed(struct xenbus_device *xb_dev, switch (backend_state) { case XenbusStateReconfiguring: - /* fall through */ case XenbusStateReconfigured: - /* fall through */ case XenbusStateInitialised: break; @@ -701,7 +699,6 @@ static void displback_changed(struct xenbus_device *xb_dev, break; case XenbusStateUnknown: - /* fall through */ case XenbusStateClosed: if (xb_dev->state == XenbusStateClosed) break; diff --git a/drivers/gpu/drm/xen/xen_drm_front_gem.c b/drivers/gpu/drm/xen/xen_drm_front_gem.c index 39ff95b75357..534daf37c97e 100644 --- a/drivers/gpu/drm/xen/xen_drm_front_gem.c +++ b/drivers/gpu/drm/xen/xen_drm_front_gem.c @@ -18,6 +18,7 @@ #include <drm/drm_probe_helper.h> #include <xen/balloon.h> +#include <xen/xen.h> #include "xen_drm_front.h" #include "xen_drm_front_gem.h" @@ -99,8 +100,8 @@ static struct xen_gem_object *gem_create(struct drm_device *dev, size_t size) * allocate ballooned pages which will be used to map * grant references provided by the backend */ - ret = alloc_xenballooned_pages(xen_obj->num_pages, - xen_obj->pages); + ret = xen_alloc_unpopulated_pages(xen_obj->num_pages, + xen_obj->pages); if (ret < 0) { DRM_ERROR("Cannot allocate %zu ballooned pages: %d\n", xen_obj->num_pages, ret); @@ -152,8 +153,8 @@ void xen_drm_front_gem_free_object_unlocked(struct drm_gem_object *gem_obj) } else { if (xen_obj->pages) { if (xen_obj->be_alloc) { - free_xenballooned_pages(xen_obj->num_pages, - xen_obj->pages); + xen_free_unpopulated_pages(xen_obj->num_pages, + xen_obj->pages); gem_free_pages_array(xen_obj); } else { drm_gem_put_pages(&xen_obj->base, diff --git a/drivers/gpu/drm/xlnx/Kconfig b/drivers/gpu/drm/xlnx/Kconfig index aa6cd889bd11..b52c6cdfc0b8 100644 --- a/drivers/gpu/drm/xlnx/Kconfig +++ b/drivers/gpu/drm/xlnx/Kconfig @@ -2,6 +2,7 @@ config DRM_ZYNQMP_DPSUB tristate "ZynqMP DisplayPort Controller Driver" depends on ARCH_ZYNQMP || COMPILE_TEST depends on COMMON_CLK && DRM && OF + depends on DMADEVICES select DMA_ENGINE select DRM_GEM_CMA_HELPER select DRM_KMS_CMA_HELPER |