diff options
Diffstat (limited to 'drivers/gpu/drm/i915')
39 files changed, 584 insertions, 175 deletions
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 729ec6e0d43a..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: @@ -14930,7 +14930,7 @@ static int intel_atomic_check(struct drm_device *dev, if (any_ms && !check_digital_port_conflicts(state)) { drm_dbg_kms(&dev_priv->drm, "rejecting conflicting digital port configuration\n"); - ret = EINVAL; + ret = -EINVAL; goto fail; } @@ -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_display_debugfs.c b/drivers/gpu/drm/i915/display/intel_display_debugfs.c index 3644752cc5ec..5a5cfe25085b 100644 --- a/drivers/gpu/drm/i915/display/intel_display_debugfs.c +++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.c @@ -2044,9 +2044,12 @@ DEFINE_SHOW_ATTRIBUTE(i915_hdcp_sink_capability); static int i915_lpsp_capability_show(struct seq_file *m, void *data) { struct drm_connector *connector = m->private; - struct intel_encoder *encoder = - intel_attached_encoder(to_intel_connector(connector)); struct drm_i915_private *i915 = to_i915(connector->dev); + struct intel_encoder *encoder; + + encoder = intel_attached_encoder(to_intel_connector(connector)); + if (!encoder) + return -ENODEV; if (connector->status != connector_status_connected) return -ENODEV; diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 0c713e83274d..e0fcb89c736b 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -4147,6 +4147,12 @@ static const struct i915_power_well_desc tgl_power_wells[] = { }, }, { + .name = "TC cold off", + .domains = TGL_TC_COLD_OFF_POWER_DOMAINS, + .ops = &tgl_tc_cold_off_ops, + .id = DISP_PW_ID_NONE, + }, + { .name = "AUX A", .domains = TGL_AUX_A_IO_POWER_DOMAINS, .ops = &icl_aux_power_well_ops, @@ -4332,12 +4338,6 @@ static const struct i915_power_well_desc tgl_power_wells[] = { .hsw.irq_pipe_mask = BIT(PIPE_D), }, }, - { - .name = "TC cold off", - .domains = TGL_TC_COLD_OFF_POWER_DOMAINS, - .ops = &tgl_tc_cold_off_ops, - .id = DISP_PW_ID_NONE, - }, }; static const struct i915_power_well_desc rkl_power_wells[] = { @@ -5240,10 +5240,10 @@ struct buddy_page_mask { }; static const struct buddy_page_mask tgl_buddy_page_masks[] = { - { .num_channels = 1, .type = INTEL_DRAM_LPDDR4, .page_mask = 0xE }, { .num_channels = 1, .type = INTEL_DRAM_DDR4, .page_mask = 0xF }, { .num_channels = 2, .type = INTEL_DRAM_LPDDR4, .page_mask = 0x1C }, { .num_channels = 2, .type = INTEL_DRAM_DDR4, .page_mask = 0x1F }, + { .num_channels = 4, .type = INTEL_DRAM_LPDDR4, .page_mask = 0x38 }, {} }; 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/cfg_space.c b/drivers/gpu/drm/i915/gvt/cfg_space.c index 072725a448db..ad86c5eb5bba 100644 --- a/drivers/gpu/drm/i915/gvt/cfg_space.c +++ b/drivers/gpu/drm/i915/gvt/cfg_space.c @@ -70,6 +70,7 @@ static void vgpu_pci_cfg_mem_write(struct intel_vgpu *vgpu, unsigned int off, { u8 *cfg_base = vgpu_cfg_space(vgpu); u8 mask, new, old; + pci_power_t pwr; int i = 0; for (; i < bytes && (off + i < sizeof(pci_cfg_space_rw_bmp)); i++) { @@ -91,6 +92,15 @@ static void vgpu_pci_cfg_mem_write(struct intel_vgpu *vgpu, unsigned int off, /* For other configuration space directly copy as it is. */ if (i < bytes) memcpy(cfg_base + off + i, src + i, bytes - i); + + if (off == vgpu->cfg_space.pmcsr_off && vgpu->cfg_space.pmcsr_off) { + pwr = (pci_power_t __force)(*(u16*)(&vgpu_cfg_space(vgpu)[off]) + & PCI_PM_CTRL_STATE_MASK); + if (pwr == PCI_D3hot) + vgpu->d3_entered = true; + gvt_dbg_core("vgpu-%d power status changed to %d\n", + vgpu->id, pwr); + } } /** @@ -366,6 +376,7 @@ void intel_vgpu_init_cfg_space(struct intel_vgpu *vgpu, struct intel_gvt *gvt = vgpu->gvt; const struct intel_gvt_device_info *info = &gvt->device_info; u16 *gmch_ctl; + u8 next; memcpy(vgpu_cfg_space(vgpu), gvt->firmware.cfg_space, info->cfg_space_size); @@ -401,6 +412,19 @@ void intel_vgpu_init_cfg_space(struct intel_vgpu *vgpu, pci_resource_len(gvt->gt->i915->drm.pdev, 2); memset(vgpu_cfg_space(vgpu) + PCI_ROM_ADDRESS, 0, 4); + + /* PM Support */ + vgpu->cfg_space.pmcsr_off = 0; + if (vgpu_cfg_space(vgpu)[PCI_STATUS] & PCI_STATUS_CAP_LIST) { + next = vgpu_cfg_space(vgpu)[PCI_CAPABILITY_LIST]; + do { + if (vgpu_cfg_space(vgpu)[next + PCI_CAP_LIST_ID] == PCI_CAP_ID_PM) { + vgpu->cfg_space.pmcsr_off = next + PCI_PM_CTRL; + break; + } + next = vgpu_cfg_space(vgpu)[next + PCI_CAP_LIST_NEXT]; + } while (next); + } } /** diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 210016192ce7..a3a4305eda01 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -2501,7 +2501,7 @@ int intel_vgpu_init_gtt(struct intel_vgpu *vgpu) return create_scratch_page_tree(vgpu); } -static void intel_vgpu_destroy_all_ppgtt_mm(struct intel_vgpu *vgpu) +void intel_vgpu_destroy_all_ppgtt_mm(struct intel_vgpu *vgpu) { struct list_head *pos, *n; struct intel_vgpu_mm *mm; diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h index 320b8d6ad92f..52d0d88abd86 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.h +++ b/drivers/gpu/drm/i915/gvt/gtt.h @@ -279,4 +279,6 @@ int intel_vgpu_emulate_ggtt_mmio_read(struct intel_vgpu *vgpu, int intel_vgpu_emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, void *p_data, unsigned int bytes); +void intel_vgpu_destroy_all_ppgtt_mm(struct intel_vgpu *vgpu); + #endif /* _GVT_GTT_H_ */ diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index a4a6db6b7f90..ff7f2515a6fe 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -106,6 +106,7 @@ struct intel_vgpu_pci_bar { struct intel_vgpu_cfg_space { unsigned char virtual_cfg_space[PCI_CFG_SPACE_EXP_SIZE]; struct intel_vgpu_pci_bar bar[INTEL_GVT_MAX_BAR_NUM]; + u32 pmcsr_off; }; #define vgpu_cfg_space(vgpu) ((vgpu)->cfg_space.virtual_cfg_space) @@ -198,6 +199,8 @@ struct intel_vgpu { struct intel_vgpu_submission submission; struct radix_tree_root page_track_tree; u32 hws_pga[I915_NUM_ENGINES]; + /* Set on PCI_D3, reset on DMLR, not reflecting the actual PM state */ + bool d3_entered; struct dentry *debugfs; 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 7d361623ff67..f6d7e33c7099 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -257,6 +257,7 @@ void intel_gvt_release_vgpu(struct intel_vgpu *vgpu) intel_gvt_deactivate_vgpu(vgpu); mutex_lock(&vgpu->vgpu_lock); + vgpu->d3_entered = false; intel_vgpu_clean_workloads(vgpu, ALL_ENGINES); intel_vgpu_dmabuf_cleanup(vgpu); mutex_unlock(&vgpu->vgpu_lock); @@ -367,6 +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; @@ -393,6 +395,7 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, INIT_RADIX_TREE(&vgpu->page_track_tree, GFP_KERNEL); idr_init(&vgpu->object_idr); intel_vgpu_init_cfg_space(vgpu, param->primary); + vgpu->d3_entered = false; ret = intel_vgpu_init_mmio(vgpu); if (ret) @@ -434,7 +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; @@ -557,10 +563,15 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr, /* full GPU reset or device model level reset */ if (engine_mask == ALL_ENGINES || dmlr) { intel_vgpu_select_submission_ops(vgpu, ALL_ENGINES, 0); - intel_vgpu_invalidate_ppgtt(vgpu); + if (engine_mask == ALL_ENGINES) + intel_vgpu_invalidate_ppgtt(vgpu); /*fence will not be reset during virtual reset */ if (dmlr) { - intel_vgpu_reset_gtt(vgpu); + if(!vgpu->d3_entered) { + intel_vgpu_invalidate_ppgtt(vgpu); + intel_vgpu_destroy_all_ppgtt_mm(vgpu); + } + intel_vgpu_reset_ggtt(vgpu, true); intel_vgpu_reset_resource(vgpu); } @@ -572,7 +583,14 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr, intel_vgpu_reset_cfg_space(vgpu); /* only reset the failsafe mode when dmlr reset */ vgpu->failsafe = false; - vgpu->pv_notified = false; + /* + * PCI_D0 is set before dmlr, so reset d3_entered here + * after done using. + */ + if(vgpu->d3_entered) + vgpu->d3_entered = false; + else + vgpu->pv_notified = false; } } 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 28bc5f13ae52..69c0fa20eba1 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -445,8 +445,6 @@ static void i915_pmu_event_destroy(struct perf_event *event) container_of(event->pmu, typeof(*i915), pmu.base); drm_WARN_ON(&i915->drm, event->parent); - - module_put(THIS_MODULE); } static int @@ -476,7 +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; @@ -538,10 +536,8 @@ static int i915_pmu_event_init(struct perf_event *event) if (ret) return ret; - if (!event->parent) { - __module_get(THIS_MODULE); + if (!event->parent) event->destroy = i915_pmu_event_destroy; - } return 0; } @@ -1130,6 +1126,7 @@ void i915_pmu_register(struct drm_i915_private *i915) if (!pmu->base.attr_groups) goto err_attr; + pmu->base.module = THIS_MODULE; pmu->base.task_ctx_nr = perf_invalid_context; pmu->base.event_init = i915_pmu_event_init; pmu->base.add = i915_pmu_event_add; 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/i915_buddy.c b/drivers/gpu/drm/i915/selftests/i915_buddy.c index 939a6caebb03..632b912b0bc9 100644 --- a/drivers/gpu/drm/i915/selftests/i915_buddy.c +++ b/drivers/gpu/drm/i915/selftests/i915_buddy.c @@ -8,8 +8,6 @@ #include "../i915_selftest.h" #include "i915_random.h" -#define SZ_8G (1ULL << 33) - static void __igt_dump_block(struct i915_buddy_mm *mm, struct i915_buddy_block *block, bool buddy) @@ -281,18 +279,22 @@ static int igt_check_mm(struct i915_buddy_mm *mm) static void igt_mm_config(u64 *size, u64 *chunk_size) { I915_RND_STATE(prng); - u64 s, ms; + u32 s, ms; /* Nothing fancy, just try to get an interesting bit pattern */ prandom_seed_state(&prng, i915_selftest.random_seed); - s = i915_prandom_u64_state(&prng) & (SZ_8G - 1); - ms = BIT_ULL(12 + (prandom_u32_state(&prng) % ilog2(s >> 12))); - s = max(s & -ms, ms); + /* Let size be a random number of pages up to 8 GB (2M pages) */ + s = 1 + i915_prandom_u32_max_state((BIT(33 - 12)) - 1, &prng); + /* Let the chunk size be a random power of 2 less than size */ + ms = BIT(i915_prandom_u32_max_state(ilog2(s), &prng)); + /* Round size down to the chunk size */ + s &= -ms; - *chunk_size = ms; - *size = s; + /* Convert from pages to bytes */ + *chunk_size = (u64)ms << 12; + *size = (u64)s << 12; } static int igt_buddy_alloc_smoke(void *arg) diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c index b9810bf156c3..397c313a8b69 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c +++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c @@ -78,6 +78,7 @@ static void mock_device_release(struct drm_device *dev) drm_mode_config_cleanup(&i915->drm); out: + i915_params_free(&i915->params); put_device(&i915->drm.pdev->dev); i915->drm.pdev = NULL; } @@ -117,11 +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); @@ -140,10 +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); @@ -165,6 +164,8 @@ struct drm_i915_private *mock_gem_device(void) i915->drm.pdev = pdev; drmm_add_final_kfree(&i915->drm, i915); + i915_params_copy(&i915->params, &i915_modparams); + intel_runtime_pm_init_early(&i915->runtime_pm); /* Using the global GTT may ask questions about KMS users, so prepare */ |