diff options
| author | Maxime Ripard <maxime@cerno.tech> | 2023-01-03 08:32:12 +0100 |
|---|---|---|
| committer | Maxime Ripard <maxime@cerno.tech> | 2023-01-03 08:32:12 +0100 |
| commit | 2c55d703391acf7e9101da596d0c15ee03b318a3 (patch) | |
| tree | 422ef671343624b56d333b47d20a538eeedbfe10 /drivers/gpu/drm/i915 | |
| parent | 92d43bd3bc9728c1fb114d7011d46f5ea9489e28 (diff) | |
| parent | 88603b6dc419445847923fcb7fe5080067a30f98 (diff) | |
Merge drm/drm-fixes into drm-misc-fixes
Let's start the fixes cycle.
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Diffstat (limited to 'drivers/gpu/drm/i915')
311 files changed, 11051 insertions, 5548 deletions
diff --git a/drivers/gpu/drm/i915/Kconfig.profile b/drivers/gpu/drm/i915/Kconfig.profile index 39328567c200..7cc38d25ee5c 100644 --- a/drivers/gpu/drm/i915/Kconfig.profile +++ b/drivers/gpu/drm/i915/Kconfig.profile @@ -57,10 +57,28 @@ config DRM_I915_PREEMPT_TIMEOUT default 640 # milliseconds help How long to wait (in milliseconds) for a preemption event to occur - when submitting a new context via execlists. If the current context - does not hit an arbitration point and yield to HW before the timer - expires, the HW will be reset to allow the more important context - to execute. + when submitting a new context. If the current context does not hit + an arbitration point and yield to HW before the timer expires, the + HW will be reset to allow the more important context to execute. + + This is adjustable via + /sys/class/drm/card?/engine/*/preempt_timeout_ms + + May be 0 to disable the timeout. + + The compiled in default may get overridden at driver probe time on + certain platforms and certain engines which will be reflected in the + sysfs control. + +config DRM_I915_PREEMPT_TIMEOUT_COMPUTE + int "Preempt timeout for compute engines (ms, jiffy granularity)" + default 7500 # milliseconds + help + How long to wait (in milliseconds) for a preemption event to occur + when submitting a new context to a compute capable engine. If the + current context does not hit an arbitration point and yield to HW + before the timer expires, the HW will be reset to allow the more + important context to execute. This is adjustable via /sys/class/drm/card?/engine/*/preempt_timeout_ms diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index cea00aaca04b..01974b82d205 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -127,9 +127,11 @@ gt-y += \ gt/intel_sseu.o \ gt/intel_sseu_debugfs.o \ gt/intel_timeline.o \ + gt/intel_wopcm.o \ gt/intel_workarounds.o \ gt/shmem_utils.o \ gt/sysfs_engines.o + # x86 intel-gtt module support gt-$(CONFIG_X86) += gt/intel_ggtt_gmch.o # autogenerated null render state @@ -183,8 +185,7 @@ i915-y += \ i915_trace_points.o \ i915_ttm_buddy_manager.o \ i915_vma.o \ - i915_vma_resource.o \ - intel_wopcm.o + i915_vma_resource.o # general-purpose microcontroller (GuC) support i915-y += gt/uc/intel_uc.o \ @@ -209,6 +210,9 @@ i915-y += gt/uc/intel_uc.o \ # graphics system controller (GSC) support i915-y += gt/intel_gsc.o +# graphics hardware monitoring (HWMON) support +i915-$(CONFIG_HWMON) += i915_hwmon.o + # modesetting core code i915-y += \ display/hsw_ips.o \ @@ -244,6 +248,7 @@ i915-y += \ display/intel_global_state.o \ display/intel_hdcp.o \ display/intel_hotplug.o \ + display/intel_hti.o \ display/intel_lpe_audio.o \ display/intel_modeset_verify.o \ display/intel_modeset_setup.o \ @@ -310,15 +315,18 @@ i915-y += \ i915-y += i915_perf.o -# Protected execution platform (PXP) support -i915-$(CONFIG_DRM_I915_PXP) += \ +# Protected execution platform (PXP) support. Base support is required for HuC +i915-y += \ pxp/intel_pxp.o \ + pxp/intel_pxp_tee.o \ + pxp/intel_pxp_huc.o + +i915-$(CONFIG_DRM_I915_PXP) += \ pxp/intel_pxp_cmd.o \ pxp/intel_pxp_debugfs.o \ pxp/intel_pxp_irq.o \ pxp/intel_pxp_pm.o \ - pxp/intel_pxp_session.o \ - pxp/intel_pxp_tee.o + pxp/intel_pxp_session.o # Post-mortem debug and GPU hang state capture i915-$(CONFIG_DRM_I915_CAPTURE_ERROR) += i915_gpu_error.o diff --git a/drivers/gpu/drm/i915/display/g4x_dp.c b/drivers/gpu/drm/i915/display/g4x_dp.c index e3e3d27ffb53..24ef36ec2d3d 100644 --- a/drivers/gpu/drm/i915/display/g4x_dp.c +++ b/drivers/gpu/drm/i915/display/g4x_dp.c @@ -8,6 +8,7 @@ #include <linux/string_helpers.h> #include "g4x_dp.h" +#include "i915_reg.h" #include "intel_audio.h" #include "intel_backlight.h" #include "intel_connector.h" @@ -672,8 +673,6 @@ static void intel_enable_dp(struct intel_atomic_state *state, intel_dp_pcon_dsc_configure(intel_dp, pipe_config); intel_dp_start_link_train(intel_dp, pipe_config); intel_dp_stop_link_train(intel_dp, pipe_config); - - intel_audio_codec_enable(encoder, pipe_config, conn_state); } static void g4x_enable_dp(struct intel_atomic_state *state, @@ -682,6 +681,7 @@ static void g4x_enable_dp(struct intel_atomic_state *state, const struct drm_connector_state *conn_state) { intel_enable_dp(state, encoder, pipe_config, conn_state); + intel_audio_codec_enable(encoder, pipe_config, conn_state); intel_edp_backlight_on(pipe_config, conn_state); } @@ -690,6 +690,7 @@ static void vlv_enable_dp(struct intel_atomic_state *state, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { + intel_audio_codec_enable(encoder, pipe_config, conn_state); intel_edp_backlight_on(pipe_config, conn_state); } diff --git a/drivers/gpu/drm/i915/display/g4x_dp.h b/drivers/gpu/drm/i915/display/g4x_dp.h index e1f50263a725..a38b3e1e01d3 100644 --- a/drivers/gpu/drm/i915/display/g4x_dp.h +++ b/drivers/gpu/drm/i915/display/g4x_dp.h @@ -8,7 +8,7 @@ #include <linux/types.h> -#include "i915_reg.h" +#include "i915_reg_defs.h" enum pipe; enum port; diff --git a/drivers/gpu/drm/i915/display/g4x_hdmi.c b/drivers/gpu/drm/i915/display/g4x_hdmi.c index 2b73f5ff0d02..c3580d96765c 100644 --- a/drivers/gpu/drm/i915/display/g4x_hdmi.c +++ b/drivers/gpu/drm/i915/display/g4x_hdmi.c @@ -6,6 +6,7 @@ */ #include "g4x_hdmi.h" +#include "i915_reg.h" #include "intel_audio.h" #include "intel_connector.h" #include "intel_crtc.h" @@ -78,6 +79,18 @@ static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder, return ret; } +static int g4x_hdmi_compute_config(struct intel_encoder *encoder, + struct intel_crtc_state *crtc_state, + struct drm_connector_state *conn_state) +{ + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + + if (HAS_PCH_SPLIT(i915)) + crtc_state->has_pch_encoder = true; + + return intel_hdmi_compute_config(encoder, crtc_state, conn_state); +} + static void intel_hdmi_get_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config) { @@ -144,10 +157,8 @@ static void intel_hdmi_get_config(struct intel_encoder *encoder, &pipe_config->infoframes.hdmi); } -static void g4x_enable_hdmi(struct intel_atomic_state *state, - struct intel_encoder *encoder, - const struct intel_crtc_state *pipe_config, - const struct drm_connector_state *conn_state) +static void g4x_hdmi_enable_port(struct intel_encoder *encoder, + const struct intel_crtc_state *pipe_config) { struct drm_device *dev = encoder->base.dev; struct drm_i915_private *dev_priv = to_i915(dev); @@ -162,6 +173,16 @@ static void g4x_enable_hdmi(struct intel_atomic_state *state, intel_de_write(dev_priv, intel_hdmi->hdmi_reg, temp); intel_de_posting_read(dev_priv, intel_hdmi->hdmi_reg); +} + +static void g4x_enable_hdmi(struct intel_atomic_state *state, + struct intel_encoder *encoder, + const struct intel_crtc_state *pipe_config, + const struct drm_connector_state *conn_state) +{ + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + + g4x_hdmi_enable_port(encoder, pipe_config); drm_WARN_ON(&dev_priv->drm, pipe_config->has_audio && !pipe_config->has_hdmi_sink); @@ -281,6 +302,11 @@ static void vlv_enable_hdmi(struct intel_atomic_state *state, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + + drm_WARN_ON(&dev_priv->drm, pipe_config->has_audio && + !pipe_config->has_hdmi_sink); + intel_audio_codec_enable(encoder, pipe_config, conn_state); } static void intel_disable_hdmi(struct intel_atomic_state *state, @@ -402,7 +428,7 @@ static void vlv_hdmi_pre_enable(struct intel_atomic_state *state, pipe_config->has_infoframe, pipe_config, conn_state); - g4x_enable_hdmi(state, encoder, pipe_config, conn_state); + g4x_hdmi_enable_port(encoder, pipe_config); vlv_wait_port_ready(dev_priv, dig_port, 0x0); } @@ -479,7 +505,7 @@ static void chv_hdmi_pre_enable(struct intel_atomic_state *state, pipe_config->has_infoframe, pipe_config, conn_state); - g4x_enable_hdmi(state, encoder, pipe_config, conn_state); + g4x_hdmi_enable_port(encoder, pipe_config); vlv_wait_port_ready(dev_priv, dig_port, 0x0); @@ -543,7 +569,7 @@ void g4x_hdmi_init(struct drm_i915_private *dev_priv, "HDMI %c", port_name(port)); intel_encoder->hotplug = intel_hdmi_hotplug; - intel_encoder->compute_config = intel_hdmi_compute_config; + intel_encoder->compute_config = g4x_hdmi_compute_config; if (HAS_PCH_SPLIT(dev_priv)) { intel_encoder->disable = pch_disable_hdmi; intel_encoder->post_disable = pch_post_disable_hdmi; @@ -585,7 +611,7 @@ void g4x_hdmi_init(struct drm_i915_private *dev_priv, } else { intel_encoder->pipe_mask = ~0; } - intel_encoder->cloneable = 1 << INTEL_OUTPUT_ANALOG; + intel_encoder->cloneable = BIT(INTEL_OUTPUT_ANALOG); intel_encoder->hpd_pin = intel_hpd_pin_default(dev_priv, port); /* * BSpec is unclear about HDMI+HDMI cloning on g4x, but it seems @@ -593,7 +619,7 @@ void g4x_hdmi_init(struct drm_i915_private *dev_priv, * only one port anyway, nothing is lost by allowing it. */ if (IS_G4X(dev_priv)) - intel_encoder->cloneable |= 1 << INTEL_OUTPUT_HDMI; + intel_encoder->cloneable |= BIT(INTEL_OUTPUT_HDMI); dig_port->hdmi.hdmi_reg = hdmi_reg; dig_port->dp.output_reg = INVALID_MMIO_REG; diff --git a/drivers/gpu/drm/i915/display/hsw_ips.c b/drivers/gpu/drm/i915/display/hsw_ips.c index a5be4af792cb..83aa3800245f 100644 --- a/drivers/gpu/drm/i915/display/hsw_ips.c +++ b/drivers/gpu/drm/i915/display/hsw_ips.c @@ -104,8 +104,7 @@ static bool hsw_ips_need_disable(struct intel_atomic_state *state, * Disable IPS before we program the LUT. */ if (IS_HASWELL(i915) && - (new_crtc_state->uapi.color_mgmt_changed || - new_crtc_state->update_pipe) && + intel_crtc_needs_color_update(new_crtc_state) && new_crtc_state->gamma_mode == GAMMA_MODE_MODE_SPLIT) return true; @@ -146,8 +145,7 @@ static bool hsw_ips_need_enable(struct intel_atomic_state *state, * Re-enable IPS after the LUT has been programmed. */ if (IS_HASWELL(i915) && - (new_crtc_state->uapi.color_mgmt_changed || - new_crtc_state->update_pipe) && + intel_crtc_needs_color_update(new_crtc_state) && new_crtc_state->gamma_mode == GAMMA_MODE_MODE_SPLIT) return true; @@ -155,7 +153,7 @@ static bool hsw_ips_need_enable(struct intel_atomic_state *state, * We can't read out IPS on broadwell, assume the worst and * forcibly enable IPS on the first fastset. */ - if (new_crtc_state->update_pipe && old_crtc_state->inherited) + if (intel_crtc_needs_fastset(new_crtc_state) && old_crtc_state->inherited) return true; return !old_crtc_state->ips_enabled; diff --git a/drivers/gpu/drm/i915/display/i9xx_plane.c b/drivers/gpu/drm/i915/display/i9xx_plane.c index 5afbe3e98ee8..ecaeb7dc196b 100644 --- a/drivers/gpu/drm/i915/display/i9xx_plane.c +++ b/drivers/gpu/drm/i915/display/i9xx_plane.c @@ -8,6 +8,9 @@ #include <drm/drm_blend.h> #include <drm/drm_fourcc.h> +#include "i915_irq.h" +#include "i915_reg.h" +#include "i9xx_plane.h" #include "intel_atomic.h" #include "intel_atomic_plane.h" #include "intel_de.h" @@ -15,7 +18,6 @@ #include "intel_fb.h" #include "intel_fbc.h" #include "intel_sprite.h" -#include "i9xx_plane.h" /* Primary plane formats for gen <= 3 */ static const u32 i8xx_primary_formats[] = { diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index ed4d93942dbd..d16b30a2dded 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -29,6 +29,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_mipi_dsi.h> +#include "i915_reg.h" #include "icl_dsi.h" #include "icl_dsi_regs.h" #include "intel_atomic.h" @@ -1974,16 +1975,8 @@ static void icl_dsi_add_properties(struct intel_connector *connector) { const struct drm_display_mode *fixed_mode = intel_panel_preferred_fixed_mode(connector); - u32 allowed_scalers; - allowed_scalers = BIT(DRM_MODE_SCALE_ASPECT) | - BIT(DRM_MODE_SCALE_FULLSCREEN) | - BIT(DRM_MODE_SCALE_CENTER); - - drm_connector_attach_scaling_mode_property(&connector->base, - allowed_scalers); - - connector->base.state->scaling_mode = DRM_MODE_SCALE_ASPECT; + intel_attach_scaling_mode_property(&connector->base); drm_connector_set_panel_orientation_with_quirk(&connector->base, intel_dsi_get_panel_orientation(connector), @@ -1993,7 +1986,6 @@ static void icl_dsi_add_properties(struct intel_connector *connector) void icl_dsi_init(struct drm_i915_private *dev_priv) { - struct drm_device *dev = &dev_priv->drm; struct intel_dsi *intel_dsi; struct intel_encoder *encoder; struct intel_connector *intel_connector; @@ -2018,7 +2010,7 @@ void icl_dsi_init(struct drm_i915_private *dev_priv) connector = &intel_connector->base; /* register DSI encoder with DRM subsystem */ - drm_encoder_init(dev, &encoder->base, &gen11_dsi_encoder_funcs, + drm_encoder_init(&dev_priv->drm, &encoder->base, &gen11_dsi_encoder_funcs, DRM_MODE_ENCODER_DSI, "DSI %c", port_name(port)); encoder->pre_pll_enable = gen11_dsi_pre_pll_enable; @@ -2042,12 +2034,10 @@ void icl_dsi_init(struct drm_i915_private *dev_priv) encoder->is_clock_enabled = gen11_dsi_is_clock_enabled; /* register DSI connector with DRM subsystem */ - drm_connector_init(dev, connector, &gen11_dsi_connector_funcs, + drm_connector_init(&dev_priv->drm, connector, &gen11_dsi_connector_funcs, DRM_MODE_CONNECTOR_DSI); drm_connector_helper_add(connector, &gen11_dsi_connector_helper_funcs); connector->display_info.subpixel_order = SubPixelHorizontalRGB; - connector->interlace_allowed = false; - connector->doublescan_allowed = false; intel_connector->get_hw_state = intel_connector_get_hw_state; /* attach connector to encoder */ @@ -2055,9 +2045,9 @@ void icl_dsi_init(struct drm_i915_private *dev_priv) intel_bios_init_panel(dev_priv, &intel_connector->panel, NULL, NULL); - mutex_lock(&dev->mode_config.mutex); + mutex_lock(&dev_priv->drm.mode_config.mutex); intel_panel_add_vbt_lfp_fixed_mode(intel_connector); - mutex_unlock(&dev->mode_config.mutex); + mutex_unlock(&dev_priv->drm.mode_config.mutex); if (!intel_panel_preferred_fixed_mode(intel_connector)) { drm_err(&dev_priv->drm, "DSI fixed mode info missing\n"); diff --git a/drivers/gpu/drm/i915/display/icl_dsi_regs.h b/drivers/gpu/drm/i915/display/icl_dsi_regs.h index f78f28b8dd94..d4845ac65acc 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi_regs.h +++ b/drivers/gpu/drm/i915/display/icl_dsi_regs.h @@ -6,7 +6,7 @@ #ifndef __ICL_DSI_REGS_H__ #define __ICL_DSI_REGS_H__ -#include "i915_reg_defs.h" +#include "intel_display_reg_defs.h" /* Gen11 DSI */ #define _MMIO_DSI(tc, dsi0, dsi1) _MMIO_TRANS((tc) - TRANSCODER_DSI_0, \ diff --git a/drivers/gpu/drm/i915/display/intel_atomic.c b/drivers/gpu/drm/i915/display/intel_atomic.c index 18f0a5ae3bac..6621aa245caf 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic.c +++ b/drivers/gpu/drm/i915/display/intel_atomic.c @@ -252,6 +252,11 @@ intel_crtc_duplicate_state(struct drm_crtc *crtc) if (crtc_state->hw.gamma_lut) drm_property_blob_get(crtc_state->hw.gamma_lut); + if (crtc_state->pre_csc_lut) + drm_property_blob_get(crtc_state->pre_csc_lut); + if (crtc_state->post_csc_lut) + drm_property_blob_get(crtc_state->post_csc_lut); + crtc_state->update_pipe = false; crtc_state->disable_lp_wm = false; crtc_state->disable_cxsr = false; @@ -274,6 +279,9 @@ static void intel_crtc_put_color_blobs(struct intel_crtc_state *crtc_state) drm_property_blob_put(crtc_state->hw.degamma_lut); drm_property_blob_put(crtc_state->hw.gamma_lut); drm_property_blob_put(crtc_state->hw.ctm); + + drm_property_blob_put(crtc_state->pre_csc_lut); + drm_property_blob_put(crtc_state->post_csc_lut); } void intel_crtc_free_hw_state(struct intel_crtc_state *crtc_state) diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c index aaa6708256d5..10e1fc9d0698 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c +++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c @@ -425,6 +425,47 @@ static bool intel_plane_do_async_flip(struct intel_plane *plane, return DISPLAY_VER(i915) < 13 || old_crtc_state->uapi.async_flip; } +static bool i9xx_must_disable_cxsr(const struct intel_crtc_state *new_crtc_state, + const struct intel_plane_state *old_plane_state, + const struct intel_plane_state *new_plane_state) +{ + struct intel_plane *plane = to_intel_plane(new_plane_state->uapi.plane); + bool old_visible = old_plane_state->uapi.visible; + bool new_visible = new_plane_state->uapi.visible; + u32 old_ctl = old_plane_state->ctl; + u32 new_ctl = new_plane_state->ctl; + bool modeset, turn_on, turn_off; + + if (plane->id == PLANE_CURSOR) + return false; + + modeset = intel_crtc_needs_modeset(new_crtc_state); + turn_off = old_visible && (!new_visible || modeset); + turn_on = new_visible && (!old_visible || modeset); + + /* Must disable CxSR around plane enable/disable */ + if (turn_on || turn_off) + return true; + + if (!old_visible || !new_visible) + return false; + + /* + * Most plane control register updates are blocked while in CxSR. + * + * Tiling mode is one exception where the primary plane can + * apparently handle it, whereas the sprites can not (the + * sprite issue being only relevant on VLV/CHV where CxSR + * is actually possible with a sprite enabled). + */ + if (plane->id == PLANE_PRIMARY) { + old_ctl &= ~DISP_TILED; + new_ctl &= ~DISP_TILED; + } + + return old_ctl != new_ctl; +} + static int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_state, struct intel_crtc_state *new_crtc_state, const struct intel_plane_state *old_plane_state, @@ -482,17 +523,9 @@ static int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_cr if (turn_on) { if (DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv)) new_crtc_state->update_wm_pre = true; - - /* must disable cxsr around plane enable/disable */ - if (plane->id != PLANE_CURSOR) - new_crtc_state->disable_cxsr = true; } else if (turn_off) { if (DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv)) new_crtc_state->update_wm_post = true; - - /* must disable cxsr around plane enable/disable */ - if (plane->id != PLANE_CURSOR) - new_crtc_state->disable_cxsr = true; } else if (intel_wm_need_update(old_plane_state, new_plane_state)) { if (DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv)) { /* FIXME bollocks */ @@ -504,6 +537,10 @@ static int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_cr if (visible || was_visible) new_crtc_state->fb_bits |= plane->frontbuffer_bit; + if (HAS_GMCH(dev_priv) && + i9xx_must_disable_cxsr(new_crtc_state, old_plane_state, new_plane_state)) + new_crtc_state->disable_cxsr = true; + /* * ILK/SNB DVSACNTR/Sprite Enable * IVB SPR_CTL/Sprite Enable @@ -720,7 +757,7 @@ void intel_plane_update_noarm(struct intel_plane *plane, { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - trace_intel_plane_update_noarm(&plane->base, crtc); + trace_intel_plane_update_noarm(plane, crtc); if (plane->update_noarm) plane->update_noarm(plane, crtc_state, plane_state); @@ -732,7 +769,7 @@ void intel_plane_update_arm(struct intel_plane *plane, { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - trace_intel_plane_update_arm(&plane->base, crtc); + trace_intel_plane_update_arm(plane, crtc); if (crtc_state->do_async_flip && plane->async_flip) plane->async_flip(plane, crtc_state, plane_state, true); @@ -745,7 +782,7 @@ void intel_plane_disable_arm(struct intel_plane *plane, { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - trace_intel_plane_disable_arm(&plane->base, crtc); + trace_intel_plane_disable_arm(plane, crtc); plane->disable_arm(plane, crtc_state); } @@ -1005,7 +1042,7 @@ intel_prepare_plane_fb(struct drm_plane *_plane, */ if (intel_crtc_needs_modeset(crtc_state)) { ret = i915_sw_fence_await_reservation(&state->commit_ready, - old_obj->base.resv, NULL, + old_obj->base.resv, false, 0, GFP_KERNEL); if (ret < 0) @@ -1039,8 +1076,7 @@ intel_prepare_plane_fb(struct drm_plane *_plane, struct dma_fence *fence; ret = i915_sw_fence_await_reservation(&state->commit_ready, - obj->base.resv, NULL, - false, + obj->base.resv, false, i915_fence_timeout(dev_priv), GFP_KERNEL); if (ret < 0) diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c index aacbc6da84ef..98c3322b4549 100644 --- a/drivers/gpu/drm/i915/display/intel_audio.c +++ b/drivers/gpu/drm/i915/display/intel_audio.c @@ -250,7 +250,7 @@ static const struct hdmi_aud_ncts hdmi_aud_ncts_36bpp[] = { /* get AUD_CONFIG_PIXEL_CLOCK_HDMI_* value for mode */ static u32 audio_config_hdmi_pixel_clock(const struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode; int i; @@ -260,17 +260,17 @@ static u32 audio_config_hdmi_pixel_clock(const struct intel_crtc_state *crtc_sta break; } - if (DISPLAY_VER(dev_priv) < 12 && adjusted_mode->crtc_clock > 148500) + if (DISPLAY_VER(i915) < 12 && adjusted_mode->crtc_clock > 148500) i = ARRAY_SIZE(hdmi_audio_clock); if (i == ARRAY_SIZE(hdmi_audio_clock)) { - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(&i915->drm, "HDMI audio pixel clock setting for %d not found, falling back to defaults\n", adjusted_mode->crtc_clock); i = 1; } - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(&i915->drm, "Configuring HDMI audio for pixel clock %d (0x%08x)\n", hdmi_audio_clock[i].clock, hdmi_audio_clock[i].config); @@ -304,96 +304,67 @@ static int audio_config_hdmi_get_n(const struct intel_crtc_state *crtc_state, return 0; } -static bool intel_eld_uptodate(struct drm_connector *connector, - i915_reg_t reg_eldv, u32 bits_eldv, - i915_reg_t reg_elda, u32 bits_elda, - i915_reg_t reg_edid) +/* ELD buffer size in dwords */ +static int g4x_eld_buffer_size(struct drm_i915_private *i915) { - struct drm_i915_private *dev_priv = to_i915(connector->dev); - const u8 *eld = connector->eld; u32 tmp; - int i; - - tmp = intel_de_read(dev_priv, reg_eldv); - tmp &= bits_eldv; - - if (!tmp) - return false; - tmp = intel_de_read(dev_priv, reg_elda); - tmp &= ~bits_elda; - intel_de_write(dev_priv, reg_elda, tmp); + tmp = intel_de_read(i915, G4X_AUD_CNTL_ST); - for (i = 0; i < drm_eld_size(eld) / 4; i++) - if (intel_de_read(dev_priv, reg_edid) != *((const u32 *)eld + i)) - return false; - - return true; + return REG_FIELD_GET(G4X_ELD_BUFFER_SIZE_MASK, tmp); } static void g4x_audio_codec_disable(struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - u32 eldv, tmp; - - tmp = intel_de_read(dev_priv, G4X_AUD_VID_DID); - if (tmp == INTEL_AUDIO_DEVBLC || tmp == INTEL_AUDIO_DEVCL) - eldv = G4X_ELDV_DEVCL_DEVBLC; - else - eldv = G4X_ELDV_DEVCTG; + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc); /* Invalidate ELD */ - tmp = intel_de_read(dev_priv, G4X_AUD_CNTL_ST); - tmp &= ~eldv; - intel_de_write(dev_priv, G4X_AUD_CNTL_ST, tmp); + intel_de_rmw(i915, G4X_AUD_CNTL_ST, + G4X_ELD_VALID, 0); + + intel_crtc_wait_for_next_vblank(crtc); + intel_crtc_wait_for_next_vblank(crtc); } static void g4x_audio_codec_enable(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_connector *connector = conn_state->connector; - const u8 *eld = connector->eld; - u32 eldv; - u32 tmp; - int len, i; + const u32 *eld = (const u32 *)connector->eld; + int eld_buffer_size, len, i; - tmp = intel_de_read(dev_priv, G4X_AUD_VID_DID); - if (tmp == INTEL_AUDIO_DEVBLC || tmp == INTEL_AUDIO_DEVCL) - eldv = G4X_ELDV_DEVCL_DEVBLC; - else - eldv = G4X_ELDV_DEVCTG; + intel_crtc_wait_for_next_vblank(crtc); - if (intel_eld_uptodate(connector, - G4X_AUD_CNTL_ST, eldv, - G4X_AUD_CNTL_ST, G4X_ELD_ADDR_MASK, - G4X_HDMIW_HDMIEDID)) - return; + intel_de_rmw(i915, G4X_AUD_CNTL_ST, + G4X_ELD_VALID | G4X_ELD_ADDRESS_MASK, 0); - tmp = intel_de_read(dev_priv, G4X_AUD_CNTL_ST); - tmp &= ~(eldv | G4X_ELD_ADDR_MASK); - len = (tmp >> 9) & 0x1f; /* ELD buffer size */ - intel_de_write(dev_priv, G4X_AUD_CNTL_ST, tmp); + eld_buffer_size = g4x_eld_buffer_size(i915); + len = min(drm_eld_size(connector->eld) / 4, eld_buffer_size); - len = min(drm_eld_size(eld) / 4, len); for (i = 0; i < len; i++) - intel_de_write(dev_priv, G4X_HDMIW_HDMIEDID, - *((const u32 *)eld + i)); + intel_de_write(i915, G4X_HDMIW_HDMIEDID, eld[i]); + for (; i < eld_buffer_size; i++) + intel_de_write(i915, G4X_HDMIW_HDMIEDID, 0); - tmp = intel_de_read(dev_priv, G4X_AUD_CNTL_ST); - tmp |= eldv; - intel_de_write(dev_priv, G4X_AUD_CNTL_ST, tmp); + drm_WARN_ON(&i915->drm, + (intel_de_read(i915, G4X_AUD_CNTL_ST) & G4X_ELD_ADDRESS_MASK) != 0); + + intel_de_rmw(i915, G4X_AUD_CNTL_ST, + 0, G4X_ELD_VALID); } static void hsw_dp_audio_config_update(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - struct i915_audio_component *acomp = dev_priv->display.audio.component; + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + struct i915_audio_component *acomp = i915->display.audio.component; enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; enum port port = encoder->port; const struct dp_aud_n_m *nm; @@ -403,12 +374,12 @@ hsw_dp_audio_config_update(struct intel_encoder *encoder, rate = acomp ? acomp->aud_sample_rate[port] : 0; nm = audio_config_dp_get_n_m(crtc_state, rate); if (nm) - drm_dbg_kms(&dev_priv->drm, "using Maud %u, Naud %u\n", nm->m, + drm_dbg_kms(&i915->drm, "using Maud %u, Naud %u\n", nm->m, nm->n); else - drm_dbg_kms(&dev_priv->drm, "using automatic Maud, Naud\n"); + drm_dbg_kms(&i915->drm, "using automatic Maud, Naud\n"); - tmp = intel_de_read(dev_priv, HSW_AUD_CFG(cpu_transcoder)); + tmp = intel_de_read(i915, HSW_AUD_CFG(cpu_transcoder)); tmp &= ~AUD_CONFIG_N_VALUE_INDEX; tmp &= ~AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK; tmp &= ~AUD_CONFIG_N_PROG_ENABLE; @@ -420,9 +391,9 @@ hsw_dp_audio_config_update(struct intel_encoder *encoder, tmp |= AUD_CONFIG_N_PROG_ENABLE; } - intel_de_write(dev_priv, HSW_AUD_CFG(cpu_transcoder), tmp); + intel_de_write(i915, HSW_AUD_CFG(cpu_transcoder), tmp); - tmp = intel_de_read(dev_priv, HSW_AUD_M_CTS_ENABLE(cpu_transcoder)); + tmp = intel_de_read(i915, HSW_AUD_M_CTS_ENABLE(cpu_transcoder)); tmp &= ~AUD_CONFIG_M_MASK; tmp &= ~AUD_M_CTS_M_VALUE_INDEX; tmp &= ~AUD_M_CTS_M_PROG_ENABLE; @@ -433,15 +404,15 @@ hsw_dp_audio_config_update(struct intel_encoder *encoder, tmp |= AUD_M_CTS_M_PROG_ENABLE; } - intel_de_write(dev_priv, HSW_AUD_M_CTS_ENABLE(cpu_transcoder), tmp); + intel_de_write(i915, HSW_AUD_M_CTS_ENABLE(cpu_transcoder), tmp); } static void hsw_hdmi_audio_config_update(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - struct i915_audio_component *acomp = dev_priv->display.audio.component; + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + struct i915_audio_component *acomp = i915->display.audio.component; enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; enum port port = encoder->port; int n, rate; @@ -449,7 +420,7 @@ hsw_hdmi_audio_config_update(struct intel_encoder *encoder, rate = acomp ? acomp->aud_sample_rate[port] : 0; - tmp = intel_de_read(dev_priv, HSW_AUD_CFG(cpu_transcoder)); + tmp = intel_de_read(i915, HSW_AUD_CFG(cpu_transcoder)); tmp &= ~AUD_CONFIG_N_VALUE_INDEX; tmp &= ~AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK; tmp &= ~AUD_CONFIG_N_PROG_ENABLE; @@ -457,25 +428,25 @@ hsw_hdmi_audio_config_update(struct intel_encoder *encoder, n = audio_config_hdmi_get_n(crtc_state, rate); if (n != 0) { - drm_dbg_kms(&dev_priv->drm, "using N %d\n", n); + drm_dbg_kms(&i915->drm, "using N %d\n", n); tmp &= ~AUD_CONFIG_N_MASK; tmp |= AUD_CONFIG_N(n); tmp |= AUD_CONFIG_N_PROG_ENABLE; } else { - drm_dbg_kms(&dev_priv->drm, "using automatic N\n"); + drm_dbg_kms(&i915->drm, "using automatic N\n"); } - intel_de_write(dev_priv, HSW_AUD_CFG(cpu_transcoder), tmp); + intel_de_write(i915, HSW_AUD_CFG(cpu_transcoder), tmp); /* * Let's disable "Enable CTS or M Prog bit" * and let HW calculate the value */ - tmp = intel_de_read(dev_priv, HSW_AUD_M_CTS_ENABLE(cpu_transcoder)); + tmp = intel_de_read(i915, HSW_AUD_M_CTS_ENABLE(cpu_transcoder)); tmp &= ~AUD_M_CTS_M_PROG_ENABLE; tmp &= ~AUD_M_CTS_M_VALUE_INDEX; - intel_de_write(dev_priv, HSW_AUD_M_CTS_ENABLE(cpu_transcoder), tmp); + intel_de_write(i915, HSW_AUD_M_CTS_ENABLE(cpu_transcoder), tmp); } static void @@ -488,33 +459,48 @@ hsw_audio_config_update(struct intel_encoder *encoder, hsw_hdmi_audio_config_update(encoder, crtc_state); } +/* ELD buffer size in dwords */ +static int hsw_eld_buffer_size(struct drm_i915_private *i915, + enum transcoder cpu_transcoder) +{ + u32 tmp; + + tmp = intel_de_read(i915, HSW_AUD_DIP_ELD_CTRL(cpu_transcoder)); + + return REG_FIELD_GET(IBX_ELD_BUFFER_SIZE_MASK, tmp); +} + static void hsw_audio_codec_disable(struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc); enum transcoder cpu_transcoder = old_crtc_state->cpu_transcoder; - u32 tmp; - mutex_lock(&dev_priv->display.audio.mutex); + mutex_lock(&i915->display.audio.mutex); /* Disable timestamps */ - tmp = intel_de_read(dev_priv, HSW_AUD_CFG(cpu_transcoder)); - tmp &= ~AUD_CONFIG_N_VALUE_INDEX; - tmp |= AUD_CONFIG_N_PROG_ENABLE; - tmp &= ~AUD_CONFIG_UPPER_N_MASK; - tmp &= ~AUD_CONFIG_LOWER_N_MASK; - if (intel_crtc_has_dp_encoder(old_crtc_state)) - tmp |= AUD_CONFIG_N_VALUE_INDEX; - intel_de_write(dev_priv, HSW_AUD_CFG(cpu_transcoder), tmp); + intel_de_rmw(i915, HSW_AUD_CFG(cpu_transcoder), + AUD_CONFIG_N_VALUE_INDEX | + AUD_CONFIG_UPPER_N_MASK | + AUD_CONFIG_LOWER_N_MASK, + AUD_CONFIG_N_PROG_ENABLE | + (intel_crtc_has_dp_encoder(old_crtc_state) ? + AUD_CONFIG_N_VALUE_INDEX : 0)); /* Invalidate ELD */ - tmp = intel_de_read(dev_priv, HSW_AUD_PIN_ELD_CP_VLD); - tmp &= ~AUDIO_ELD_VALID(cpu_transcoder); - tmp &= ~AUDIO_OUTPUT_ENABLE(cpu_transcoder); - intel_de_write(dev_priv, HSW_AUD_PIN_ELD_CP_VLD, tmp); + intel_de_rmw(i915, HSW_AUD_PIN_ELD_CP_VLD, + AUDIO_ELD_VALID(cpu_transcoder), 0); + + intel_crtc_wait_for_next_vblank(crtc); + intel_crtc_wait_for_next_vblank(crtc); - mutex_unlock(&dev_priv->display.audio.mutex); + /* Disable audio presence detect */ + intel_de_rmw(i915, HSW_AUD_PIN_ELD_CP_VLD, + AUDIO_OUTPUT_ENABLE(cpu_transcoder), 0); + + mutex_unlock(&i915->display.audio.mutex); } static unsigned int calc_hblank_early_prog(struct intel_encoder *encoder, @@ -626,178 +612,190 @@ static void enable_audio_dsc_wa(struct intel_encoder *encoder, intel_de_write(i915, AUD_CONFIG_BE, val); } -#undef ROUNDING_FACTOR - static void hsw_audio_codec_enable(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_connector *connector = conn_state->connector; enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; - const u8 *eld = connector->eld; - u32 tmp; - int len, i; + const u32 *eld = (const u32 *)connector->eld; + int eld_buffer_size, len, i; - mutex_lock(&dev_priv->display.audio.mutex); + mutex_lock(&i915->display.audio.mutex); /* Enable Audio WA for 4k DSC usecases */ if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP)) enable_audio_dsc_wa(encoder, crtc_state); - /* Enable audio presence detect, invalidate ELD */ - tmp = intel_de_read(dev_priv, HSW_AUD_PIN_ELD_CP_VLD); - tmp |= AUDIO_OUTPUT_ENABLE(cpu_transcoder); - tmp &= ~AUDIO_ELD_VALID(cpu_transcoder); - intel_de_write(dev_priv, HSW_AUD_PIN_ELD_CP_VLD, tmp); + /* Enable audio presence detect */ + intel_de_rmw(i915, HSW_AUD_PIN_ELD_CP_VLD, + 0, AUDIO_OUTPUT_ENABLE(cpu_transcoder)); - /* - * FIXME: We're supposed to wait for vblank here, but we have vblanks - * disabled during the mode set. The proper fix would be to push the - * rest of the setup into a vblank work item, queued here, but the - * infrastructure is not there yet. - */ + intel_crtc_wait_for_next_vblank(crtc); + + /* Invalidate ELD */ + intel_de_rmw(i915, HSW_AUD_PIN_ELD_CP_VLD, + AUDIO_ELD_VALID(cpu_transcoder), 0); + + /* Reset ELD address */ + intel_de_rmw(i915, HSW_AUD_DIP_ELD_CTRL(cpu_transcoder), + IBX_ELD_ADDRESS_MASK, 0); - /* Reset ELD write address */ - tmp = intel_de_read(dev_priv, HSW_AUD_DIP_ELD_CTRL(cpu_transcoder)); - tmp &= ~IBX_ELD_ADDRESS_MASK; - intel_de_write(dev_priv, HSW_AUD_DIP_ELD_CTRL(cpu_transcoder), tmp); + eld_buffer_size = hsw_eld_buffer_size(i915, cpu_transcoder); + len = min(drm_eld_size(connector->eld) / 4, eld_buffer_size); - /* Up to 84 bytes of hw ELD buffer */ - len = min(drm_eld_size(eld), 84); - for (i = 0; i < len / 4; i++) - intel_de_write(dev_priv, HSW_AUD_EDID_DATA(cpu_transcoder), - *((const u32 *)eld + i)); + for (i = 0; i < len; i++) + intel_de_write(i915, HSW_AUD_EDID_DATA(cpu_transcoder), eld[i]); + for (; i < eld_buffer_size; i++) + intel_de_write(i915, HSW_AUD_EDID_DATA(cpu_transcoder), 0); + + drm_WARN_ON(&i915->drm, + (intel_de_read(i915, HSW_AUD_DIP_ELD_CTRL(cpu_transcoder)) & + IBX_ELD_ADDRESS_MASK) != 0); /* ELD valid */ - tmp = intel_de_read(dev_priv, HSW_AUD_PIN_ELD_CP_VLD); - tmp |= AUDIO_ELD_VALID(cpu_transcoder); - intel_de_write(dev_priv, HSW_AUD_PIN_ELD_CP_VLD, tmp); + intel_de_rmw(i915, HSW_AUD_PIN_ELD_CP_VLD, + 0, AUDIO_ELD_VALID(cpu_transcoder)); /* Enable timestamps */ hsw_audio_config_update(encoder, crtc_state); - mutex_unlock(&dev_priv->display.audio.mutex); + mutex_unlock(&i915->display.audio.mutex); +} + +struct ilk_audio_regs { + i915_reg_t hdmiw_hdmiedid, aud_config, aud_cntl_st, aud_cntrl_st2; +}; + +static void ilk_audio_regs_init(struct drm_i915_private *i915, + enum pipe pipe, + struct ilk_audio_regs *regs) +{ + if (HAS_PCH_IBX(i915)) { + regs->hdmiw_hdmiedid = IBX_HDMIW_HDMIEDID(pipe); + regs->aud_config = IBX_AUD_CFG(pipe); + regs->aud_cntl_st = IBX_AUD_CNTL_ST(pipe); + regs->aud_cntrl_st2 = IBX_AUD_CNTL_ST2; + } else if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) { + regs->hdmiw_hdmiedid = VLV_HDMIW_HDMIEDID(pipe); + regs->aud_config = VLV_AUD_CFG(pipe); + regs->aud_cntl_st = VLV_AUD_CNTL_ST(pipe); + regs->aud_cntrl_st2 = VLV_AUD_CNTL_ST2; + } else { + regs->hdmiw_hdmiedid = CPT_HDMIW_HDMIEDID(pipe); + regs->aud_config = CPT_AUD_CFG(pipe); + regs->aud_cntl_st = CPT_AUD_CNTL_ST(pipe); + regs->aud_cntrl_st2 = CPT_AUD_CNTRL_ST2; + } +} + +/* ELD buffer size in dwords */ +static int ilk_eld_buffer_size(struct drm_i915_private *i915, + enum pipe pipe) +{ + struct ilk_audio_regs regs; + u32 tmp; + + ilk_audio_regs_init(i915, pipe, ®s); + + tmp = intel_de_read(i915, regs.aud_cntl_st); + + return REG_FIELD_GET(IBX_ELD_BUFFER_SIZE_MASK, tmp); } static void ilk_audio_codec_disable(struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct drm_i915_private *i915 = to_i915(encoder->base.dev); struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc); - enum pipe pipe = crtc->pipe; enum port port = encoder->port; - u32 tmp, eldv; - i915_reg_t aud_config, aud_cntrl_st2; + enum pipe pipe = crtc->pipe; + struct ilk_audio_regs regs; - if (drm_WARN_ON(&dev_priv->drm, port == PORT_A)) + if (drm_WARN_ON(&i915->drm, port == PORT_A)) return; - if (HAS_PCH_IBX(dev_priv)) { - aud_config = IBX_AUD_CFG(pipe); - aud_cntrl_st2 = IBX_AUD_CNTL_ST2; - } else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { - aud_config = VLV_AUD_CFG(pipe); - aud_cntrl_st2 = VLV_AUD_CNTL_ST2; - } else { - aud_config = CPT_AUD_CFG(pipe); - aud_cntrl_st2 = CPT_AUD_CNTRL_ST2; - } + ilk_audio_regs_init(i915, pipe, ®s); - /* Disable timestamps */ - tmp = intel_de_read(dev_priv, aud_config); - tmp &= ~AUD_CONFIG_N_VALUE_INDEX; - tmp |= AUD_CONFIG_N_PROG_ENABLE; - tmp &= ~AUD_CONFIG_UPPER_N_MASK; - tmp &= ~AUD_CONFIG_LOWER_N_MASK; - if (intel_crtc_has_dp_encoder(old_crtc_state)) - tmp |= AUD_CONFIG_N_VALUE_INDEX; - intel_de_write(dev_priv, aud_config, tmp); + mutex_lock(&i915->display.audio.mutex); - eldv = IBX_ELD_VALID(port); + /* Disable timestamps */ + intel_de_rmw(i915, regs.aud_config, + AUD_CONFIG_N_VALUE_INDEX | + AUD_CONFIG_UPPER_N_MASK | + AUD_CONFIG_LOWER_N_MASK, + AUD_CONFIG_N_PROG_ENABLE | + (intel_crtc_has_dp_encoder(old_crtc_state) ? + AUD_CONFIG_N_VALUE_INDEX : 0)); /* Invalidate ELD */ - tmp = intel_de_read(dev_priv, aud_cntrl_st2); - tmp &= ~eldv; - intel_de_write(dev_priv, aud_cntrl_st2, tmp); + intel_de_rmw(i915, regs.aud_cntrl_st2, + IBX_ELD_VALID(port), 0); + + mutex_unlock(&i915->display.audio.mutex); + + intel_crtc_wait_for_next_vblank(crtc); + intel_crtc_wait_for_next_vblank(crtc); } static void ilk_audio_codec_enable(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct drm_i915_private *i915 = to_i915(encoder->base.dev); struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_connector *connector = conn_state->connector; - enum pipe pipe = crtc->pipe; + const u32 *eld = (const u32 *)connector->eld; enum port port = encoder->port; - const u8 *eld = connector->eld; - u32 tmp, eldv; - int len, i; - i915_reg_t hdmiw_hdmiedid, aud_config, aud_cntl_st, aud_cntrl_st2; + enum pipe pipe = crtc->pipe; + int eld_buffer_size, len, i; + struct ilk_audio_regs regs; - if (drm_WARN_ON(&dev_priv->drm, port == PORT_A)) + if (drm_WARN_ON(&i915->drm, port == PORT_A)) return; - /* - * FIXME: We're supposed to wait for vblank here, but we have vblanks - * disabled during the mode set. The proper fix would be to push the - * rest of the setup into a vblank work item, queued here, but the - * infrastructure is not there yet. - */ + intel_crtc_wait_for_next_vblank(crtc); - if (HAS_PCH_IBX(dev_priv)) { - hdmiw_hdmiedid = IBX_HDMIW_HDMIEDID(pipe); - aud_config = IBX_AUD_CFG(pipe); - aud_cntl_st = IBX_AUD_CNTL_ST(pipe); - aud_cntrl_st2 = IBX_AUD_CNTL_ST2; - } else if (IS_VALLEYVIEW(dev_priv) || - IS_CHERRYVIEW(dev_priv)) { - hdmiw_hdmiedid = VLV_HDMIW_HDMIEDID(pipe); - aud_config = VLV_AUD_CFG(pipe); - aud_cntl_st = VLV_AUD_CNTL_ST(pipe); - aud_cntrl_st2 = VLV_AUD_CNTL_ST2; - } else { - hdmiw_hdmiedid = CPT_HDMIW_HDMIEDID(pipe); - aud_config = CPT_AUD_CFG(pipe); - aud_cntl_st = CPT_AUD_CNTL_ST(pipe); - aud_cntrl_st2 = CPT_AUD_CNTRL_ST2; - } + ilk_audio_regs_init(i915, pipe, ®s); - eldv = IBX_ELD_VALID(port); + mutex_lock(&i915->display.audio.mutex); /* Invalidate ELD */ - tmp = intel_de_read(dev_priv, aud_cntrl_st2); - tmp &= ~eldv; - intel_de_write(dev_priv, aud_cntrl_st2, tmp); + intel_de_rmw(i915, regs.aud_cntrl_st2, + IBX_ELD_VALID(port), 0); + + /* Reset ELD address */ + intel_de_rmw(i915, regs.aud_cntl_st, + IBX_ELD_ADDRESS_MASK, 0); - /* Reset ELD write address */ - tmp = intel_de_read(dev_priv, aud_cntl_st); - tmp &= ~IBX_ELD_ADDRESS_MASK; - intel_de_write(dev_priv, aud_cntl_st, tmp); + eld_buffer_size = ilk_eld_buffer_size(i915, pipe); + len = min(drm_eld_size(connector->eld) / 4, eld_buffer_size); - /* Up to 84 bytes of hw ELD buffer */ - len = min(drm_eld_size(eld), 84); - for (i = 0; i < len / 4; i++) - intel_de_write(dev_priv, hdmiw_hdmiedid, - *((const u32 *)eld + i)); + for (i = 0; i < len; i++) + intel_de_write(i915, regs.hdmiw_hdmiedid, eld[i]); + for (; i < eld_buffer_size; i++) + intel_de_write(i915, regs.hdmiw_hdmiedid, 0); + + drm_WARN_ON(&i915->drm, + (intel_de_read(i915, regs.aud_cntl_st) & IBX_ELD_ADDRESS_MASK) != 0); /* ELD valid */ - tmp = intel_de_read(dev_priv, aud_cntrl_st2); - tmp |= eldv; - intel_de_write(dev_priv, aud_cntrl_st2, tmp); + intel_de_rmw(i915, regs.aud_cntrl_st2, + 0, IBX_ELD_VALID(port)); /* Enable timestamps */ - tmp = intel_de_read(dev_priv, aud_config); - tmp &= ~AUD_CONFIG_N_VALUE_INDEX; - tmp &= ~AUD_CONFIG_N_PROG_ENABLE; - tmp &= ~AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK; - if (intel_crtc_has_dp_encoder(crtc_state)) - tmp |= AUD_CONFIG_N_VALUE_INDEX; - else - tmp |= audio_config_hdmi_pixel_clock(crtc_state); - intel_de_write(dev_priv, aud_config, tmp); + intel_de_rmw(i915, regs.aud_config, + AUD_CONFIG_N_VALUE_INDEX | + AUD_CONFIG_N_PROG_ENABLE | + AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, + (intel_crtc_has_dp_encoder(crtc_state) ? + AUD_CONFIG_N_VALUE_INDEX : + audio_config_hdmi_pixel_clock(crtc_state))); + + mutex_unlock(&i915->display.audio.mutex); } /** @@ -813,8 +811,8 @@ void intel_audio_codec_enable(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - struct i915_audio_component *acomp = dev_priv->display.audio.component; + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + struct i915_audio_component *acomp = i915->display.audio.component; struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_connector *connector = conn_state->connector; const struct drm_display_mode *adjusted_mode = @@ -825,30 +823,30 @@ void intel_audio_codec_enable(struct intel_encoder *encoder, if (!crtc_state->has_audio) return; - drm_dbg_kms(&dev_priv->drm, "[CONNECTOR:%d:%s][ENCODER:%d:%s] Enable audio codec on pipe %c, %u bytes ELD\n", + drm_dbg_kms(&i915->drm, "[CONNECTOR:%d:%s][ENCODER:%d:%s] Enable audio codec on pipe %c, %u bytes ELD\n", connector->base.id, connector->name, encoder->base.base.id, encoder->base.name, pipe_name(pipe), drm_eld_size(connector->eld)); /* FIXME precompute the ELD in .compute_config() */ if (!connector->eld[0]) - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(&i915->drm, "Bogus ELD on [CONNECTOR:%d:%s]\n", connector->base.id, connector->name); connector->eld[6] = drm_av_sync_delay(connector, adjusted_mode) / 2; - if (dev_priv->display.funcs.audio) - dev_priv->display.funcs.audio->audio_codec_enable(encoder, - crtc_state, - conn_state); + if (i915->display.funcs.audio) + i915->display.funcs.audio->audio_codec_enable(encoder, + crtc_state, + conn_state); - mutex_lock(&dev_priv->display.audio.mutex); + mutex_lock(&i915->display.audio.mutex); encoder->audio_connector = connector; /* referred in audio callbacks */ - dev_priv->display.audio.encoder_map[pipe] = encoder; - mutex_unlock(&dev_priv->display.audio.mutex); + i915->display.audio.encoder_map[pipe] = encoder; + mutex_unlock(&i915->display.audio.mutex); if (acomp && acomp->base.audio_ops && acomp->base.audio_ops->pin_eld_notify) { @@ -856,10 +854,10 @@ void intel_audio_codec_enable(struct intel_encoder *encoder, if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST)) pipe = -1; acomp->base.audio_ops->pin_eld_notify(acomp->base.audio_ops->audio_ptr, - (int) port, (int) pipe); + (int)port, (int)pipe); } - intel_lpe_audio_notify(dev_priv, pipe, port, connector->eld, + intel_lpe_audio_notify(i915, pipe, port, connector->eld, crtc_state->port_clock, intel_crtc_has_dp_encoder(crtc_state)); } @@ -877,8 +875,8 @@ void intel_audio_codec_disable(struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - struct i915_audio_component *acomp = dev_priv->display.audio.component; + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + struct i915_audio_component *acomp = i915->display.audio.component; struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc); struct drm_connector *connector = old_conn_state->connector; enum port port = encoder->port; @@ -887,19 +885,19 @@ void intel_audio_codec_disable(struct intel_encoder *encoder, if (!old_crtc_state->has_audio) return; - drm_dbg_kms(&dev_priv->drm, "[CONNECTOR:%d:%s][ENCODER:%d:%s] Disable audio codec on pipe %c\n", + drm_dbg_kms(&i915->drm, "[CONNECTOR:%d:%s][ENCODER:%d:%s] Disable audio codec on pipe %c\n", connector->base.id, connector->name, encoder->base.base.id, encoder->base.name, pipe_name(pipe)); - if (dev_priv->display.funcs.audio) - dev_priv->display.funcs.audio->audio_codec_disable(encoder, - old_crtc_state, - old_conn_state); + if (i915->display.funcs.audio) + i915->display.funcs.audio->audio_codec_disable(encoder, + old_crtc_state, + old_conn_state); - mutex_lock(&dev_priv->display.audio.mutex); + mutex_lock(&i915->display.audio.mutex); encoder->audio_connector = NULL; - dev_priv->display.audio.encoder_map[pipe] = NULL; - mutex_unlock(&dev_priv->display.audio.mutex); + i915->display.audio.encoder_map[pipe] = NULL; + mutex_unlock(&i915->display.audio.mutex); if (acomp && acomp->base.audio_ops && acomp->base.audio_ops->pin_eld_notify) { @@ -907,10 +905,10 @@ void intel_audio_codec_disable(struct intel_encoder *encoder, if (!intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_DP_MST)) pipe = -1; acomp->base.audio_ops->pin_eld_notify(acomp->base.audio_ops->audio_ptr, - (int) port, (int) pipe); + (int)port, (int)pipe); } - intel_lpe_audio_notify(dev_priv, pipe, port, NULL, 0, false); + intel_lpe_audio_notify(i915, pipe, port, NULL, 0, false); } static const struct intel_audio_funcs g4x_audio_funcs = { @@ -930,19 +928,18 @@ static const struct intel_audio_funcs hsw_audio_funcs = { /** * intel_audio_hooks_init - Set up chip specific audio hooks - * @dev_priv: device private + * @i915: device private */ -void intel_audio_hooks_init(struct drm_i915_private *dev_priv) +void intel_audio_hooks_init(struct drm_i915_private *i915) { - if (IS_G4X(dev_priv)) { - dev_priv->display.funcs.audio = &g4x_audio_funcs; - } else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { - dev_priv->display.funcs.audio = &ilk_audio_funcs; - } else if (IS_HASWELL(dev_priv) || DISPLAY_VER(dev_priv) >= 8) { - dev_priv->display.funcs.audio = &hsw_audio_funcs; - } else if (HAS_PCH_SPLIT(dev_priv)) { - dev_priv->display.funcs.audio = &ilk_audio_funcs; - } + if (IS_G4X(i915)) + i915->display.funcs.audio = &g4x_audio_funcs; + else if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) + i915->display.funcs.audio = &ilk_audio_funcs; + else if (IS_HASWELL(i915) || DISPLAY_VER(i915) >= 8) + i915->display.funcs.audio = &hsw_audio_funcs; + else if (HAS_PCH_SPLIT(i915)) + i915->display.funcs.audio = &ilk_audio_funcs; } struct aud_ts_cdclk_m_n { @@ -1000,7 +997,7 @@ static int glk_force_audio_cdclk_commit(struct intel_atomic_state *state, return drm_atomic_commit(&state->base); } -static void glk_force_audio_cdclk(struct drm_i915_private *dev_priv, +static void glk_force_audio_cdclk(struct drm_i915_private *i915, bool enable) { struct drm_modeset_acquire_ctx ctx; @@ -1008,13 +1005,13 @@ static void glk_force_audio_cdclk(struct drm_i915_private *dev_priv, struct intel_crtc *crtc; int ret; - crtc = intel_first_crtc(dev_priv); + crtc = intel_first_crtc(i915); if (!crtc) return; drm_modeset_acquire_init(&ctx, 0); - state = drm_atomic_state_alloc(&dev_priv->drm); - if (drm_WARN_ON(&dev_priv->drm, !state)) + state = drm_atomic_state_alloc(&i915->drm); + if (drm_WARN_ON(&i915->drm, !state)) return; state->acquire_ctx = &ctx; @@ -1028,7 +1025,7 @@ retry: goto retry; } - drm_WARN_ON(&dev_priv->drm, ret); + drm_WARN_ON(&i915->drm, ret); drm_atomic_state_put(state); @@ -1038,30 +1035,30 @@ retry: static unsigned long i915_audio_component_get_power(struct device *kdev) { - struct drm_i915_private *dev_priv = kdev_to_i915(kdev); + struct drm_i915_private *i915 = kdev_to_i915(kdev); intel_wakeref_t ret; /* Catch potential impedance mismatches before they occur! */ BUILD_BUG_ON(sizeof(intel_wakeref_t) > sizeof(unsigned long)); - ret = intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO_PLAYBACK); + ret = intel_display_power_get(i915, POWER_DOMAIN_AUDIO_PLAYBACK); - if (dev_priv->display.audio.power_refcount++ == 0) { - if (DISPLAY_VER(dev_priv) >= 9) { - intel_de_write(dev_priv, AUD_FREQ_CNTRL, - dev_priv->display.audio.freq_cntrl); - drm_dbg_kms(&dev_priv->drm, + if (i915->display.audio.power_refcount++ == 0) { + if (DISPLAY_VER(i915) >= 9) { + intel_de_write(i915, AUD_FREQ_CNTRL, + i915->display.audio.freq_cntrl); + drm_dbg_kms(&i915->drm, "restored AUD_FREQ_CNTRL to 0x%x\n", - dev_priv->display.audio.freq_cntrl); + i915->display.audio.freq_cntrl); } /* Force CDCLK to 2*BCLK as long as we need audio powered. */ - if (IS_GEMINILAKE(dev_priv)) - glk_force_audio_cdclk(dev_priv, true); + if (IS_GEMINILAKE(i915)) + glk_force_audio_cdclk(i915, true); - if (DISPLAY_VER(dev_priv) >= 10) - intel_de_write(dev_priv, AUD_PIN_BUF_CTL, - (intel_de_read(dev_priv, AUD_PIN_BUF_CTL) | AUD_PIN_BUF_ENABLE)); + if (DISPLAY_VER(i915) >= 10) + intel_de_rmw(i915, AUD_PIN_BUF_CTL, + 0, AUD_PIN_BUF_ENABLE); } return ret; @@ -1070,24 +1067,23 @@ static unsigned long i915_audio_component_get_power(struct device *kdev) static void i915_audio_component_put_power(struct device *kdev, unsigned long cookie) { - struct drm_i915_private *dev_priv = kdev_to_i915(kdev); + struct drm_i915_private *i915 = kdev_to_i915(kdev); /* Stop forcing CDCLK to 2*BCLK if no need for audio to be powered. */ - if (--dev_priv->display.audio.power_refcount == 0) - if (IS_GEMINILAKE(dev_priv)) - glk_force_audio_cdclk(dev_priv, false); + if (--i915->display.audio.power_refcount == 0) + if (IS_GEMINILAKE(i915)) + glk_force_audio_cdclk(i915, false); - intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO_PLAYBACK, cookie); + intel_display_power_put(i915, POWER_DOMAIN_AUDIO_PLAYBACK, cookie); } static void i915_audio_component_codec_wake_override(struct device *kdev, bool enable) { - struct drm_i915_private *dev_priv = kdev_to_i915(kdev); + struct drm_i915_private *i915 = kdev_to_i915(kdev); unsigned long cookie; - u32 tmp; - if (DISPLAY_VER(dev_priv) < 9) + if (DISPLAY_VER(i915) < 9) return; cookie = i915_audio_component_get_power(kdev); @@ -1096,15 +1092,13 @@ static void i915_audio_component_codec_wake_override(struct device *kdev, * Enable/disable generating the codec wake signal, overriding the * internal logic to generate the codec wake to controller. */ - tmp = intel_de_read(dev_priv, HSW_AUD_CHICKENBIT); - tmp &= ~SKL_AUD_CODEC_WAKE_SIGNAL; - intel_de_write(dev_priv, HSW_AUD_CHICKENBIT, tmp); + intel_de_rmw(i915, HSW_AUD_CHICKENBIT, + SKL_AUD_CODEC_WAKE_SIGNAL, 0); usleep_range(1000, 1500); if (enable) { - tmp = intel_de_read(dev_priv, HSW_AUD_CHICKENBIT); - tmp |= SKL_AUD_CODEC_WAKE_SIGNAL; - intel_de_write(dev_priv, HSW_AUD_CHICKENBIT, tmp); + intel_de_rmw(i915, HSW_AUD_CHICKENBIT, + 0, SKL_AUD_CODEC_WAKE_SIGNAL); usleep_range(1000, 1500); } @@ -1114,12 +1108,12 @@ static void i915_audio_component_codec_wake_override(struct device *kdev, /* Get CDCLK in kHz */ static int i915_audio_component_get_cdclk_freq(struct device *kdev) { - struct drm_i915_private *dev_priv = kdev_to_i915(kdev); + struct drm_i915_private *i915 = kdev_to_i915(kdev); - if (drm_WARN_ON_ONCE(&dev_priv->drm, !HAS_DDI(dev_priv))) + if (drm_WARN_ON_ONCE(&i915->drm, !HAS_DDI(i915))) return -ENODEV; - return dev_priv->display.cdclk.hw.cdclk; + return i915->display.cdclk.hw.cdclk; } /* @@ -1132,24 +1126,24 @@ static int i915_audio_component_get_cdclk_freq(struct device *kdev) * will get the right intel_encoder with port matched * Non-MST & (pipe < 0): get the right intel_encoder with port matched */ -static struct intel_encoder *get_saved_enc(struct drm_i915_private *dev_priv, - int port, int pipe) +static struct intel_encoder *get_saved_enc(struct drm_i915_private *i915, + int port, int pipe) { - struct intel_encoder *encoder; - /* MST */ if (pipe >= 0) { - if (drm_WARN_ON(&dev_priv->drm, - pipe >= ARRAY_SIZE(dev_priv->display.audio.encoder_map))) + struct intel_encoder *encoder; + + if (drm_WARN_ON(&i915->drm, + pipe >= ARRAY_SIZE(i915->display.audio.encoder_map))) return NULL; - encoder = dev_priv->display.audio.encoder_map[pipe]; + encoder = i915->display.audio.encoder_map[pipe]; /* * when bootup, audio driver may not know it is * MST or not. So it will poll all the port & pipe * combinations */ - if (encoder != NULL && encoder->port == port && + if (encoder && encoder->port == port && encoder->type == INTEL_OUTPUT_DP_MST) return encoder; } @@ -1158,15 +1152,13 @@ static struct intel_encoder *get_saved_enc(struct drm_i915_private *dev_priv, if (pipe > 0) return NULL; - for_each_pipe(dev_priv, pipe) { - encoder = dev_priv->display.audio.encoder_map[pipe]; - if (encoder == NULL) - continue; + for_each_pipe(i915, pipe) { + struct intel_encoder *encoder; - if (encoder->type == INTEL_OUTPUT_DP_MST) - continue; + encoder = i915->display.audio.encoder_map[pipe]; - if (port == encoder->port) + if (encoder && encoder->port == port && + encoder->type != INTEL_OUTPUT_DP_MST) return encoder; } @@ -1176,23 +1168,23 @@ static struct intel_encoder *get_saved_enc(struct drm_i915_private *dev_priv, static int i915_audio_component_sync_audio_rate(struct device *kdev, int port, int pipe, int rate) { - struct drm_i915_private *dev_priv = kdev_to_i915(kdev); - struct i915_audio_component *acomp = dev_priv->display.audio.component; + struct drm_i915_private *i915 = kdev_to_i915(kdev); + struct i915_audio_component *acomp = i915->display.audio.component; struct intel_encoder *encoder; struct intel_crtc *crtc; unsigned long cookie; int err = 0; - if (!HAS_DDI(dev_priv)) + if (!HAS_DDI(i915)) return 0; cookie = i915_audio_component_get_power(kdev); - mutex_lock(&dev_priv->display.audio.mutex); + mutex_lock(&i915->display.audio.mutex); /* 1. get the pipe */ - encoder = get_saved_enc(dev_priv, port, pipe); + encoder = get_saved_enc(i915, port, pipe); if (!encoder || !encoder->base.crtc) { - drm_dbg_kms(&dev_priv->drm, "Not valid for port %c\n", + drm_dbg_kms(&i915->drm, "Not valid for port %c\n", port_name(port)); err = -ENODEV; goto unlock; @@ -1206,7 +1198,7 @@ static int i915_audio_component_sync_audio_rate(struct device *kdev, int port, hsw_audio_config_update(encoder, crtc->config); unlock: - mutex_unlock(&dev_priv->display.audio.mutex); + mutex_unlock(&i915->display.audio.mutex); i915_audio_component_put_power(kdev, cookie); return err; } @@ -1215,18 +1207,18 @@ static int i915_audio_component_get_eld(struct device *kdev, int port, int pipe, bool *enabled, unsigned char *buf, int max_bytes) { - struct drm_i915_private *dev_priv = kdev_to_i915(kdev); + struct drm_i915_private *i915 = kdev_to_i915(kdev); struct intel_encoder *intel_encoder; const u8 *eld; int ret = -EINVAL; - mutex_lock(&dev_priv->display.audio.mutex); + mutex_lock(&i915->display.audio.mutex); - intel_encoder = get_saved_enc(dev_priv, port, pipe); + intel_encoder = get_saved_enc(i915, port, pipe); if (!intel_encoder) { - drm_dbg_kms(&dev_priv->drm, "Not valid for port %c\n", + drm_dbg_kms(&i915->drm, "Not valid for port %c\n", port_name(port)); - mutex_unlock(&dev_priv->display.audio.mutex); + mutex_unlock(&i915->display.audio.mutex); return ret; } @@ -1238,7 +1230,7 @@ static int i915_audio_component_get_eld(struct device *kdev, int port, memcpy(buf, eld, min(max_bytes, ret)); } - mutex_unlock(&dev_priv->display.audio.mutex); + mutex_unlock(&i915->display.audio.mutex); return ret; } @@ -1256,25 +1248,25 @@ static int i915_audio_component_bind(struct device *i915_kdev, struct device *hda_kdev, void *data) { struct i915_audio_component *acomp = data; - struct drm_i915_private *dev_priv = kdev_to_i915(i915_kdev); + struct drm_i915_private *i915 = kdev_to_i915(i915_kdev); int i; - if (drm_WARN_ON(&dev_priv->drm, acomp->base.ops || acomp->base.dev)) + if (drm_WARN_ON(&i915->drm, acomp->base.ops || acomp->base.dev)) return -EEXIST; - if (drm_WARN_ON(&dev_priv->drm, + if (drm_WARN_ON(&i915->drm, !device_link_add(hda_kdev, i915_kdev, DL_FLAG_STATELESS))) return -ENOMEM; - drm_modeset_lock_all(&dev_priv->drm); + drm_modeset_lock_all(&i915->drm); acomp->base.ops = &i915_audio_component_ops; acomp->base.dev = i915_kdev; BUILD_BUG_ON(MAX_PORTS != I915_MAX_PORTS); for (i = 0; i < ARRAY_SIZE(acomp->aud_sample_rate); i++) acomp->aud_sample_rate[i] = 0; - dev_priv->display.audio.component = acomp; - drm_modeset_unlock_all(&dev_priv->drm); + i915->display.audio.component = acomp; + drm_modeset_unlock_all(&i915->drm); return 0; } @@ -1283,19 +1275,19 @@ static void i915_audio_component_unbind(struct device *i915_kdev, struct device *hda_kdev, void *data) { struct i915_audio_component *acomp = data; - struct drm_i915_private *dev_priv = kdev_to_i915(i915_kdev); + struct drm_i915_private *i915 = kdev_to_i915(i915_kdev); - drm_modeset_lock_all(&dev_priv->drm); + drm_modeset_lock_all(&i915->drm); acomp->base.ops = NULL; acomp->base.dev = NULL; - dev_priv->display.audio.component = NULL; - drm_modeset_unlock_all(&dev_priv->drm); + i915->display.audio.component = NULL; + drm_modeset_unlock_all(&i915->drm); device_link_remove(hda_kdev, i915_kdev); - if (dev_priv->display.audio.power_refcount) - drm_err(&dev_priv->drm, "audio power refcount %d after unbind\n", - dev_priv->display.audio.power_refcount); + if (i915->display.audio.power_refcount) + drm_err(&i915->drm, "audio power refcount %d after unbind\n", + i915->display.audio.power_refcount); } static const struct component_ops i915_audio_component_bind_ops = { @@ -1314,7 +1306,7 @@ static const struct component_ops i915_audio_component_bind_ops = { /** * i915_audio_component_init - initialize and register the audio component - * @dev_priv: i915 device instance + * @i915: i915 device instance * * This will register with the component framework a child component which * will bind dynamically to the snd_hda_intel driver's corresponding master @@ -1328,83 +1320,83 @@ static const struct component_ops i915_audio_component_bind_ops = { * We ignore any error during registration and continue with reduced * functionality (i.e. without HDMI audio). */ -static void i915_audio_component_init(struct drm_i915_private *dev_priv) +static void i915_audio_component_init(struct drm_i915_private *i915) { u32 aud_freq, aud_freq_init; int ret; - ret = component_add_typed(dev_priv->drm.dev, + ret = component_add_typed(i915->drm.dev, &i915_audio_component_bind_ops, I915_COMPONENT_AUDIO); if (ret < 0) { - drm_err(&dev_priv->drm, + drm_err(&i915->drm, "failed to add audio component (%d)\n", ret); /* continue with reduced functionality */ return; } - if (DISPLAY_VER(dev_priv) >= 9) { - aud_freq_init = intel_de_read(dev_priv, AUD_FREQ_CNTRL); + if (DISPLAY_VER(i915) >= 9) { + aud_freq_init = intel_de_read(i915, AUD_FREQ_CNTRL); - if (DISPLAY_VER(dev_priv) >= 12) + if (DISPLAY_VER(i915) >= 12) aud_freq = AUD_FREQ_GEN12; else aud_freq = aud_freq_init; /* use BIOS provided value for TGL and RKL unless it is a known bad value */ - if ((IS_TIGERLAKE(dev_priv) || IS_ROCKETLAKE(dev_priv)) && + if ((IS_TIGERLAKE(i915) || IS_ROCKETLAKE(i915)) && aud_freq_init != AUD_FREQ_TGL_BROKEN) aud_freq = aud_freq_init; - drm_dbg_kms(&dev_priv->drm, "use AUD_FREQ_CNTRL of 0x%x (init value 0x%x)\n", + drm_dbg_kms(&i915->drm, "use AUD_FREQ_CNTRL of 0x%x (init value 0x%x)\n", aud_freq, aud_freq_init); - dev_priv->display.audio.freq_cntrl = aud_freq; + i915->display.audio.freq_cntrl = aud_freq; } /* init with current cdclk */ - intel_audio_cdclk_change_post(dev_priv); + intel_audio_cdclk_change_post(i915); - dev_priv->display.audio.component_registered = true; + i915->display.audio.component_registered = true; } /** * i915_audio_component_cleanup - deregister the audio component - * @dev_priv: i915 device instance + * @i915: i915 device instance * * Deregisters the audio component, breaking any existing binding to the * corresponding snd_hda_intel driver's master component. */ -static void i915_audio_component_cleanup(struct drm_i915_private *dev_priv) +static void i915_audio_component_cleanup(struct drm_i915_private *i915) { - if (!dev_priv->display.audio.component_registered) + if (!i915->display.audio.component_registered) return; - component_del(dev_priv->drm.dev, &i915_audio_component_bind_ops); - dev_priv->display.audio.component_registered = false; + component_del(i915->drm.dev, &i915_audio_component_bind_ops); + i915->display.audio.component_registered = false; } /** * intel_audio_init() - Initialize the audio driver either using * component framework or using lpe audio bridge - * @dev_priv: the i915 drm device private data + * @i915: the i915 drm device private data * */ -void intel_audio_init(struct drm_i915_private *dev_priv) +void intel_audio_init(struct drm_i915_private *i915) { - if (intel_lpe_audio_init(dev_priv) < 0) - i915_audio_component_init(dev_priv); + if (intel_lpe_audio_init(i915) < 0) + i915_audio_component_init(i915); } /** * intel_audio_deinit() - deinitialize the audio driver - * @dev_priv: the i915 drm device private data + * @i915: the i915 drm device private data * */ -void intel_audio_deinit(struct drm_i915_private *dev_priv) +void intel_audio_deinit(struct drm_i915_private *i915) { - if (dev_priv->display.audio.lpe.platdev != NULL) - intel_lpe_audio_teardown(dev_priv); + if (i915->display.audio.lpe.platdev != NULL) + intel_lpe_audio_teardown(i915); else - i915_audio_component_cleanup(dev_priv); + i915_audio_component_cleanup(i915); } diff --git a/drivers/gpu/drm/i915/display/intel_audio_regs.h b/drivers/gpu/drm/i915/display/intel_audio_regs.h index d1e5844e3484..616e7b1275c4 100644 --- a/drivers/gpu/drm/i915/display/intel_audio_regs.h +++ b/drivers/gpu/drm/i915/display/intel_audio_regs.h @@ -6,18 +6,13 @@ #ifndef __INTEL_AUDIO_REGS_H__ #define __INTEL_AUDIO_REGS_H__ -#include "i915_reg_defs.h" - -#define G4X_AUD_VID_DID _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x62020) -#define INTEL_AUDIO_DEVCL 0x808629FB -#define INTEL_AUDIO_DEVBLC 0x80862801 -#define INTEL_AUDIO_DEVCTG 0x80862802 +#include "intel_display_reg_defs.h" #define G4X_AUD_CNTL_ST _MMIO(0x620B4) -#define G4X_ELDV_DEVCL_DEVBLC (1 << 13) -#define G4X_ELDV_DEVCTG (1 << 14) -#define G4X_ELD_ADDR_MASK (0xf << 5) -#define G4X_ELD_ACK (1 << 4) +#define G4X_ELD_VALID REG_BIT(14) +#define G4X_ELD_BUFFER_SIZE_MASK REG_GENMASK(13, 9) +#define G4X_ELD_ADDRESS_MASK REG_GENMASK(8, 5) +#define G4X_ELD_ACK REG_BIT(4) #define G4X_HDMIW_HDMIEDID _MMIO(0x6210C) #define _IBX_HDMIW_HDMIEDID_A 0xE2050 @@ -28,12 +23,12 @@ #define _IBX_AUD_CNTL_ST_B 0xE21B4 #define IBX_AUD_CNTL_ST(pipe) _MMIO_PIPE(pipe, _IBX_AUD_CNTL_ST_A, \ _IBX_AUD_CNTL_ST_B) -#define IBX_ELD_BUFFER_SIZE_MASK (0x1f << 10) -#define IBX_ELD_ADDRESS_MASK (0x1f << 5) -#define IBX_ELD_ACK (1 << 4) +#define IBX_ELD_BUFFER_SIZE_MASK REG_GENMASK(14, 10) +#define IBX_ELD_ADDRESS_MASK REG_GENMASK(9, 5) +#define IBX_ELD_ACK REG_BIT(4) #define IBX_AUD_CNTL_ST2 _MMIO(0xE20C0) -#define IBX_CP_READY(port) ((1 << 1) << (((port) - 1) * 4)) -#define IBX_ELD_VALID(port) ((1 << 0) << (((port) - 1) * 4)) +#define IBX_CP_READY(port) REG_BIT(((port) - 1) * 4 + 1) +#define IBX_ELD_VALID(port) REG_BIT(((port) - 1) * 4 + 0) #define _CPT_HDMIW_HDMIEDID_A 0xE5050 #define _CPT_HDMIW_HDMIEDID_B 0xE5150 @@ -60,34 +55,30 @@ #define _VLV_AUD_CONFIG_A (VLV_DISPLAY_BASE + 0x62000) #define _VLV_AUD_CONFIG_B (VLV_DISPLAY_BASE + 0x62100) #define VLV_AUD_CFG(pipe) _MMIO_PIPE(pipe, _VLV_AUD_CONFIG_A, _VLV_AUD_CONFIG_B) - -#define AUD_CONFIG_N_VALUE_INDEX (1 << 29) -#define AUD_CONFIG_N_PROG_ENABLE (1 << 28) -#define AUD_CONFIG_UPPER_N_SHIFT 20 -#define AUD_CONFIG_UPPER_N_MASK (0xff << 20) -#define AUD_CONFIG_LOWER_N_SHIFT 4 -#define AUD_CONFIG_LOWER_N_MASK (0xfff << 4) -#define AUD_CONFIG_N_MASK (AUD_CONFIG_UPPER_N_MASK | AUD_CONFIG_LOWER_N_MASK) -#define AUD_CONFIG_N(n) \ - (((((n) >> 12) & 0xff) << AUD_CONFIG_UPPER_N_SHIFT) | \ - (((n) & 0xfff) << AUD_CONFIG_LOWER_N_SHIFT)) -#define AUD_CONFIG_PIXEL_CLOCK_HDMI_SHIFT 16 -#define AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK (0xf << 16) -#define AUD_CONFIG_PIXEL_CLOCK_HDMI_25175 (0 << 16) -#define AUD_CONFIG_PIXEL_CLOCK_HDMI_25200 (1 << 16) -#define AUD_CONFIG_PIXEL_CLOCK_HDMI_27000 (2 << 16) -#define AUD_CONFIG_PIXEL_CLOCK_HDMI_27027 (3 << 16) -#define AUD_CONFIG_PIXEL_CLOCK_HDMI_54000 (4 << 16) -#define AUD_CONFIG_PIXEL_CLOCK_HDMI_54054 (5 << 16) -#define AUD_CONFIG_PIXEL_CLOCK_HDMI_74176 (6 << 16) -#define AUD_CONFIG_PIXEL_CLOCK_HDMI_74250 (7 << 16) -#define AUD_CONFIG_PIXEL_CLOCK_HDMI_148352 (8 << 16) -#define AUD_CONFIG_PIXEL_CLOCK_HDMI_148500 (9 << 16) -#define AUD_CONFIG_PIXEL_CLOCK_HDMI_296703 (10 << 16) -#define AUD_CONFIG_PIXEL_CLOCK_HDMI_297000 (11 << 16) -#define AUD_CONFIG_PIXEL_CLOCK_HDMI_593407 (12 << 16) -#define AUD_CONFIG_PIXEL_CLOCK_HDMI_594000 (13 << 16) -#define AUD_CONFIG_DISABLE_NCTS (1 << 3) +#define AUD_CONFIG_N_VALUE_INDEX REG_BIT(29) +#define AUD_CONFIG_N_PROG_ENABLE REG_BIT(28) +#define AUD_CONFIG_UPPER_N_MASK REG_GENMASK(27, 20) +#define AUD_CONFIG_LOWER_N_MASK REG_GENMASK(15, 4) +#define AUD_CONFIG_N_MASK (AUD_CONFIG_UPPER_N_MASK | \ + AUD_CONFIG_LOWER_N_MASK) +#define AUD_CONFIG_N(n) (REG_FIELD_PREP(AUD_CONFIG_UPPER_N_MASK, (n) >> 12) | \ + REG_FIELD_PREP(AUD_CONFIG_LOWER_N_MASK, (n) & 0xfff)) +#define AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK REG_GENMASK(19, 16) +#define AUD_CONFIG_PIXEL_CLOCK_HDMI_25175 REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 0) +#define AUD_CONFIG_PIXEL_CLOCK_HDMI_25200 REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 1) +#define AUD_CONFIG_PIXEL_CLOCK_HDMI_27000 REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 2) +#define AUD_CONFIG_PIXEL_CLOCK_HDMI_27027 REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 3) +#define AUD_CONFIG_PIXEL_CLOCK_HDMI_54000 REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 4) +#define AUD_CONFIG_PIXEL_CLOCK_HDMI_54054 REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 5) +#define AUD_CONFIG_PIXEL_CLOCK_HDMI_74176 REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 6) +#define AUD_CONFIG_PIXEL_CLOCK_HDMI_74250 REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 7) +#define AUD_CONFIG_PIXEL_CLOCK_HDMI_148352 REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 8) +#define AUD_CONFIG_PIXEL_CLOCK_HDMI_148500 REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 9) +#define AUD_CONFIG_PIXEL_CLOCK_HDMI_296703 REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 10) +#define AUD_CONFIG_PIXEL_CLOCK_HDMI_297000 REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 11) +#define AUD_CONFIG_PIXEL_CLOCK_HDMI_593407 REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 12) +#define AUD_CONFIG_PIXEL_CLOCK_HDMI_594000 REG_FIELD_PREP(AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK, 13) +#define AUD_CONFIG_DISABLE_NCTS REG_BIT(3) #define _HSW_AUD_CONFIG_A 0x65000 #define _HSW_AUD_CONFIG_B 0x65100 @@ -100,9 +91,9 @@ #define _HSW_AUD_M_CTS_ENABLE_A 0x65028 #define _HSW_AUD_M_CTS_ENABLE_B 0x65128 #define HSW_AUD_M_CTS_ENABLE(trans) _MMIO_TRANS(trans, _HSW_AUD_M_CTS_ENABLE_A, _HSW_AUD_M_CTS_ENABLE_B) -#define AUD_M_CTS_M_VALUE_INDEX (1 << 21) -#define AUD_M_CTS_M_PROG_ENABLE (1 << 20) -#define AUD_CONFIG_M_MASK 0xfffff +#define AUD_M_CTS_M_VALUE_INDEX REG_BIT(21) +#define AUD_M_CTS_M_PROG_ENABLE REG_BIT(20) +#define AUD_CONFIG_M_MASK REG_GENMASK(19, 0) #define _HSW_AUD_DIP_ELD_CTRL_ST_A 0x650b4 #define _HSW_AUD_DIP_ELD_CTRL_ST_B 0x651b4 @@ -130,11 +121,11 @@ #define AUD_DP_2DOT0_CTRL(trans) _MMIO_TRANS(trans, _AUD_TCA_DP_2DOT0_CTRL, _AUD_TCB_DP_2DOT0_CTRL) #define AUD_ENABLE_SDP_SPLIT REG_BIT(31) -#define HSW_AUD_CHICKENBIT _MMIO(0x65f10) -#define SKL_AUD_CODEC_WAKE_SIGNAL (1 << 15) +#define HSW_AUD_CHICKENBIT _MMIO(0x65f10) +#define SKL_AUD_CODEC_WAKE_SIGNAL REG_BIT(15) #define AUD_FREQ_CNTRL _MMIO(0x65900) -#define AUD_PIN_BUF_CTL _MMIO(0x48414) +#define AUD_PIN_BUF_CTL _MMIO(0x48414) #define AUD_PIN_BUF_ENABLE REG_BIT(31) #define AUD_TS_CDCLK_M _MMIO(0x65ea0) diff --git a/drivers/gpu/drm/i915/display/intel_backlight.c b/drivers/gpu/drm/i915/display/intel_backlight.c index beba39a38c87..71af88a70461 100644 --- a/drivers/gpu/drm/i915/display/intel_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_backlight.c @@ -10,6 +10,7 @@ #include <acpi/video.h> +#include "i915_reg.h" #include "intel_backlight.h" #include "intel_backlight_regs.h" #include "intel_connector.h" diff --git a/drivers/gpu/drm/i915/display/intel_backlight_regs.h b/drivers/gpu/drm/i915/display/intel_backlight_regs.h index 50c1210f6d5d..344eb8096bd2 100644 --- a/drivers/gpu/drm/i915/display/intel_backlight_regs.h +++ b/drivers/gpu/drm/i915/display/intel_backlight_regs.h @@ -6,7 +6,7 @@ #ifndef __INTEL_BACKLIGHT_REGS_H__ #define __INTEL_BACKLIGHT_REGS_H__ -#include "i915_reg_defs.h" +#include "intel_display_reg_defs.h" #define _VLV_BLC_PWM_CTL2_A (DISPLAY_MMIO_BASE(dev_priv) + 0x61250) #define _VLV_BLC_PWM_CTL2_B (DISPLAY_MMIO_BASE(dev_priv) + 0x61350) diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c index 28bdb936cd1f..572a4e3769f3 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -414,7 +414,7 @@ static void *generate_lfp_data_ptrs(struct drm_i915_private *i915, ptrs->lvds_entries++; if (size != 0 || ptrs->lvds_entries != 3) { - kfree(ptrs); + kfree(ptrs_block); return NULL; } @@ -2188,7 +2188,7 @@ static u8 map_ddc_pin(struct drm_i915_private *i915, u8 vbt_pin) const u8 *ddc_pin_map; int n_entries; - if (IS_ALDERLAKE_P(i915)) { + if (HAS_PCH_MTP(i915) || IS_ALDERLAKE_P(i915)) { ddc_pin_map = adlp_ddc_pin_map; n_entries = ARRAY_SIZE(adlp_ddc_pin_map); } else if (IS_ALDERLAKE_S(i915)) { @@ -2676,6 +2676,14 @@ static void print_ddi_port(const struct intel_bios_encoder_data *devdata, drm_dbg_kms(&i915->drm, "Port %c VBT DP max link rate: %d\n", port_name(port), dp_max_link_rate); + + /* + * FIXME need to implement support for VBT + * vswing/preemph tables should this ever trigger. + */ + drm_WARN(&i915->drm, child->use_vbt_vswing, + "Port %c asks to use VBT vswing/preemph tables\n", + port_name(port)); } static void parse_ddi_port(struct intel_bios_encoder_data *devdata) diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c index 4ace026b29bd..1c236f02b380 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.c +++ b/drivers/gpu/drm/i915/display/intel_bw.c @@ -439,7 +439,8 @@ static int tgl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel return ret; } - if (dram_info->type == INTEL_DRAM_LPDDR4 || dram_info->type == INTEL_DRAM_LPDDR5) + if (DISPLAY_VER(dev_priv) < 14 && + (dram_info->type == INTEL_DRAM_LPDDR4 || dram_info->type == INTEL_DRAM_LPDDR5)) num_channels *= 2; qi.deinterleave = qi.deinterleave ? : DIV_ROUND_UP(num_channels, is_y_tile ? 4 : 2); diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index ed05070b7307..b74e36d76013 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -24,6 +24,7 @@ #include <linux/time.h> #include "hsw_ips.h" +#include "i915_reg.h" #include "intel_atomic.h" #include "intel_atomic_plane.h" #include "intel_audio.h" @@ -1220,11 +1221,6 @@ static void skl_cdclk_uninit_hw(struct drm_i915_private *dev_priv) skl_set_cdclk(dev_priv, &cdclk_config, INVALID_PIPE); } -static bool has_cdclk_squasher(struct drm_i915_private *i915) -{ - return IS_DG2(i915); -} - struct intel_cdclk_vals { u32 cdclk; u16 refclk; @@ -1520,7 +1516,7 @@ static void bxt_get_cdclk(struct drm_i915_private *dev_priv, return; } - if (has_cdclk_squasher(dev_priv)) + if (HAS_CDCLK_SQUASH(dev_priv)) squash_ctl = intel_de_read(dev_priv, CDCLK_SQUASH_CTL); if (squash_ctl & CDCLK_SQUASH_ENABLE) { @@ -1689,6 +1685,38 @@ static u32 cdclk_squash_waveform(struct drm_i915_private *dev_priv, return 0xffff; } +static void icl_cdclk_pll_update(struct drm_i915_private *i915, int vco) +{ + if (i915->display.cdclk.hw.vco != 0 && + i915->display.cdclk.hw.vco != vco) + icl_cdclk_pll_disable(i915); + + if (i915->display.cdclk.hw.vco != vco) + icl_cdclk_pll_enable(i915, vco); +} + +static void bxt_cdclk_pll_update(struct drm_i915_private *i915, int vco) +{ + if (i915->display.cdclk.hw.vco != 0 && + i915->display.cdclk.hw.vco != vco) + bxt_de_pll_disable(i915); + + if (i915->display.cdclk.hw.vco != vco) + bxt_de_pll_enable(i915, vco); +} + +static void dg2_cdclk_squash_program(struct drm_i915_private *i915, + u16 waveform) +{ + u32 squash_ctl = 0; + + if (waveform) + squash_ctl = CDCLK_SQUASH_ENABLE | + CDCLK_SQUASH_WINDOW_SIZE(0xf) | waveform; + + intel_de_write(i915, CDCLK_SQUASH_CTL, squash_ctl); +} + static void bxt_set_cdclk(struct drm_i915_private *dev_priv, const struct intel_cdclk_config *cdclk_config, enum pipe pipe) @@ -1724,21 +1752,10 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv, if (HAS_CDCLK_CRAWL(dev_priv) && dev_priv->display.cdclk.hw.vco > 0 && vco > 0) { if (dev_priv->display.cdclk.hw.vco != vco) adlp_cdclk_pll_crawl(dev_priv, vco); - } else if (DISPLAY_VER(dev_priv) >= 11) { - if (dev_priv->display.cdclk.hw.vco != 0 && - dev_priv->display.cdclk.hw.vco != vco) - icl_cdclk_pll_disable(dev_priv); - - if (dev_priv->display.cdclk.hw.vco != vco) - icl_cdclk_pll_enable(dev_priv, vco); - } else { - if (dev_priv->display.cdclk.hw.vco != 0 && - dev_priv->display.cdclk.hw.vco != vco) - bxt_de_pll_disable(dev_priv); - - if (dev_priv->display.cdclk.hw.vco != vco) - bxt_de_pll_enable(dev_priv, vco); - } + } else if (DISPLAY_VER(dev_priv) >= 11) + icl_cdclk_pll_update(dev_priv, vco); + else + bxt_cdclk_pll_update(dev_priv, vco); waveform = cdclk_squash_waveform(dev_priv, cdclk); @@ -1747,15 +1764,8 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv, else clock = cdclk; - if (has_cdclk_squasher(dev_priv)) { - u32 squash_ctl = 0; - - if (waveform) - squash_ctl = CDCLK_SQUASH_ENABLE | - CDCLK_SQUASH_WINDOW_SIZE(0xf) | waveform; - - intel_de_write(dev_priv, CDCLK_SQUASH_CTL, squash_ctl); - } + if (HAS_CDCLK_SQUASH(dev_priv)) + dg2_cdclk_squash_program(dev_priv, waveform); val = bxt_cdclk_cd2x_div_sel(dev_priv, clock, vco) | bxt_cdclk_cd2x_pipe(dev_priv, pipe) | @@ -1845,7 +1855,7 @@ static void bxt_sanitize_cdclk(struct drm_i915_private *dev_priv) expected = skl_cdclk_decimal(cdclk); /* Figure out what CD2X divider we should be using for this cdclk */ - if (has_cdclk_squasher(dev_priv)) + if (HAS_CDCLK_SQUASH(dev_priv)) clock = dev_priv->display.cdclk.hw.vco / 2; else clock = dev_priv->display.cdclk.hw.cdclk; @@ -1976,7 +1986,7 @@ static bool intel_cdclk_can_squash(struct drm_i915_private *dev_priv, * the moment all platforms with squasher use a fixed cd2x * divider. */ - if (!has_cdclk_squasher(dev_priv)) + if (!HAS_CDCLK_SQUASH(dev_priv)) return false; return a->cdclk != b->cdclk && @@ -2028,7 +2038,7 @@ static bool intel_cdclk_can_cd2x_update(struct drm_i915_private *dev_priv, * the moment all platforms with squasher use a fixed cd2x * divider. */ - if (has_cdclk_squasher(dev_priv)) + if (HAS_CDCLK_SQUASH(dev_priv)) return false; return a->cdclk != b->cdclk && @@ -2464,10 +2474,6 @@ static int bdw_modeset_calc_cdclk(struct intel_cdclk_state *cdclk_state) if (min_cdclk < 0) return min_cdclk; - /* - * FIXME should also account for plane ratio - * once 64bpp pixel formats are supported. - */ cdclk = bdw_calc_cdclk(min_cdclk); cdclk_state->logical.cdclk = cdclk; @@ -2534,10 +2540,6 @@ static int skl_modeset_calc_cdclk(struct intel_cdclk_state *cdclk_state) vco = skl_dpll0_vco(cdclk_state); - /* - * FIXME should also account for plane ratio - * once 64bpp pixel formats are supported. - */ cdclk = skl_calc_cdclk(min_cdclk, vco); cdclk_state->logical.vco = vco; @@ -2754,7 +2756,7 @@ int intel_modeset_calc_cdclk(struct intel_atomic_state *state) if (IS_ERR(crtc_state)) return PTR_ERR(crtc_state); - if (drm_atomic_crtc_needs_modeset(&crtc_state->uapi)) + if (intel_crtc_needs_modeset(crtc_state)) pipe = INVALID_PIPE; } @@ -2762,12 +2764,12 @@ int intel_modeset_calc_cdclk(struct intel_atomic_state *state) &old_cdclk_state->actual, &new_cdclk_state->actual)) { drm_dbg_kms(&dev_priv->drm, - "Can change cdclk via squasher\n"); + "Can change cdclk via squashing\n"); } else if (intel_cdclk_can_crawl(dev_priv, &old_cdclk_state->actual, &new_cdclk_state->actual)) { drm_dbg_kms(&dev_priv->drm, - "Can change cdclk via crawl\n"); + "Can change cdclk via crawling\n"); } else if (pipe != INVALID_PIPE) { new_cdclk_state->pipe = pipe; @@ -2777,7 +2779,7 @@ int intel_modeset_calc_cdclk(struct intel_atomic_state *state) } else if (intel_cdclk_needs_modeset(&old_cdclk_state->actual, &new_cdclk_state->actual)) { /* All pipes must be switched off while we change the cdclk. */ - ret = intel_modeset_all_pipes(state); + ret = intel_modeset_all_pipes(state, "CDCLK change"); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c index 6bda4274eae9..250e83f1f5ac 100644 --- a/drivers/gpu/drm/i915/display/intel_color.c +++ b/drivers/gpu/drm/i915/display/intel_color.c @@ -22,12 +22,11 @@ * */ +#include "i915_reg.h" #include "intel_color.h" #include "intel_de.h" #include "intel_display_types.h" -#include "intel_dpll.h" #include "intel_dsb.h" -#include "vlv_dsi_pll.h" struct intel_color_funcs { int (*color_check)(struct intel_crtc_state *crtc_state); @@ -186,31 +185,31 @@ static void ilk_update_pipe_csc(struct intel_crtc *crtc, const u16 coeff[9], const u16 postoff[3]) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); enum pipe pipe = crtc->pipe; - intel_de_write_fw(dev_priv, PIPE_CSC_PREOFF_HI(pipe), preoff[0]); - intel_de_write_fw(dev_priv, PIPE_CSC_PREOFF_ME(pipe), preoff[1]); - intel_de_write_fw(dev_priv, PIPE_CSC_PREOFF_LO(pipe), preoff[2]); + intel_de_write_fw(i915, PIPE_CSC_PREOFF_HI(pipe), preoff[0]); + intel_de_write_fw(i915, PIPE_CSC_PREOFF_ME(pipe), preoff[1]); + intel_de_write_fw(i915, PIPE_CSC_PREOFF_LO(pipe), preoff[2]); - intel_de_write_fw(dev_priv, PIPE_CSC_COEFF_RY_GY(pipe), + intel_de_write_fw(i915, PIPE_CSC_COEFF_RY_GY(pipe), coeff[0] << 16 | coeff[1]); - intel_de_write_fw(dev_priv, PIPE_CSC_COEFF_BY(pipe), coeff[2] << 16); + intel_de_write_fw(i915, PIPE_CSC_COEFF_BY(pipe), coeff[2] << 16); - intel_de_write_fw(dev_priv, PIPE_CSC_COEFF_RU_GU(pipe), + intel_de_write_fw(i915, PIPE_CSC_COEFF_RU_GU(pipe), coeff[3] << 16 | coeff[4]); - intel_de_write_fw(dev_priv, PIPE_CSC_COEFF_BU(pipe), coeff[5] << 16); + intel_de_write_fw(i915, PIPE_CSC_COEFF_BU(pipe), coeff[5] << 16); - intel_de_write_fw(dev_priv, PIPE_CSC_COEFF_RV_GV(pipe), + intel_de_write_fw(i915, PIPE_CSC_COEFF_RV_GV(pipe), coeff[6] << 16 | coeff[7]); - intel_de_write_fw(dev_priv, PIPE_CSC_COEFF_BV(pipe), coeff[8] << 16); + intel_de_write_fw(i915, PIPE_CSC_COEFF_BV(pipe), coeff[8] << 16); - if (DISPLAY_VER(dev_priv) >= 7) { - intel_de_write_fw(dev_priv, PIPE_CSC_POSTOFF_HI(pipe), + if (DISPLAY_VER(i915) >= 7) { + intel_de_write_fw(i915, PIPE_CSC_POSTOFF_HI(pipe), postoff[0]); - intel_de_write_fw(dev_priv, PIPE_CSC_POSTOFF_ME(pipe), + intel_de_write_fw(i915, PIPE_CSC_POSTOFF_ME(pipe), postoff[1]); - intel_de_write_fw(dev_priv, PIPE_CSC_POSTOFF_LO(pipe), + intel_de_write_fw(i915, PIPE_CSC_POSTOFF_LO(pipe), postoff[2]); } } @@ -220,55 +219,55 @@ static void icl_update_output_csc(struct intel_crtc *crtc, const u16 coeff[9], const u16 postoff[3]) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); enum pipe pipe = crtc->pipe; - intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_PREOFF_HI(pipe), preoff[0]); - intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_PREOFF_ME(pipe), preoff[1]); - intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_PREOFF_LO(pipe), preoff[2]); + intel_de_write_fw(i915, PIPE_CSC_OUTPUT_PREOFF_HI(pipe), preoff[0]); + intel_de_write_fw(i915, PIPE_CSC_OUTPUT_PREOFF_ME(pipe), preoff[1]); + intel_de_write_fw(i915, PIPE_CSC_OUTPUT_PREOFF_LO(pipe), preoff[2]); - intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_COEFF_RY_GY(pipe), + intel_de_write_fw(i915, PIPE_CSC_OUTPUT_COEFF_RY_GY(pipe), coeff[0] << 16 | coeff[1]); - intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_COEFF_BY(pipe), + intel_de_write_fw(i915, PIPE_CSC_OUTPUT_COEFF_BY(pipe), coeff[2] << 16); - intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_COEFF_RU_GU(pipe), + intel_de_write_fw(i915, PIPE_CSC_OUTPUT_COEFF_RU_GU(pipe), coeff[3] << 16 | coeff[4]); - intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_COEFF_BU(pipe), + intel_de_write_fw(i915, PIPE_CSC_OUTPUT_COEFF_BU(pipe), coeff[5] << 16); - intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_COEFF_RV_GV(pipe), + intel_de_write_fw(i915, PIPE_CSC_OUTPUT_COEFF_RV_GV(pipe), coeff[6] << 16 | coeff[7]); - intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_COEFF_BV(pipe), + intel_de_write_fw(i915, PIPE_CSC_OUTPUT_COEFF_BV(pipe), coeff[8] << 16); - intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_POSTOFF_HI(pipe), postoff[0]); - intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_POSTOFF_ME(pipe), postoff[1]); - intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_POSTOFF_LO(pipe), postoff[2]); + intel_de_write_fw(i915, PIPE_CSC_OUTPUT_POSTOFF_HI(pipe), postoff[0]); + intel_de_write_fw(i915, PIPE_CSC_OUTPUT_POSTOFF_ME(pipe), postoff[1]); + intel_de_write_fw(i915, PIPE_CSC_OUTPUT_POSTOFF_LO(pipe), postoff[2]); } static bool ilk_csc_limited_range(const struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); /* * FIXME if there's a gamma LUT after the CSC, we should * do the range compression using the gamma LUT instead. */ return crtc_state->limited_color_range && - (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv) || - IS_DISPLAY_VER(dev_priv, 9, 10)); + (IS_HASWELL(i915) || IS_BROADWELL(i915) || + IS_DISPLAY_VER(i915, 9, 10)); } static void ilk_csc_convert_ctm(const struct intel_crtc_state *crtc_state, - u16 coeffs[9]) + u16 coeffs[9], bool limited_color_range) { const struct drm_color_ctm *ctm = crtc_state->hw.ctm->data; const u64 *input; u64 temp[9]; int i; - if (ilk_csc_limited_range(crtc_state)) + if (limited_color_range) input = ctm_mult_by_limited(temp, ctm->matrix); else input = ctm->matrix; @@ -315,13 +314,13 @@ static void ilk_csc_convert_ctm(const struct intel_crtc_state *crtc_state, static void ilk_load_csc_matrix(const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); bool limited_color_range = ilk_csc_limited_range(crtc_state); if (crtc_state->hw.ctm) { u16 coeff[9]; - ilk_csc_convert_ctm(crtc_state, coeff); + ilk_csc_convert_ctm(crtc_state, coeff, limited_color_range); ilk_update_pipe_csc(crtc, ilk_csc_off_zero, coeff, limited_color_range ? ilk_csc_postoff_limited_range : @@ -341,7 +340,7 @@ static void ilk_load_csc_matrix(const struct intel_crtc_state *crtc_state) * LUT is needed but CSC is not we need to load an * identity matrix. */ - drm_WARN_ON(&dev_priv->drm, !IS_GEMINILAKE(dev_priv)); + drm_WARN_ON(&i915->drm, !IS_GEMINILAKE(i915)); ilk_update_pipe_csc(crtc, ilk_csc_off_zero, ilk_csc_coeff_identity, @@ -356,7 +355,7 @@ static void icl_load_csc_matrix(const struct intel_crtc_state *crtc_state) if (crtc_state->hw.ctm) { u16 coeff[9]; - ilk_csc_convert_ctm(crtc_state, coeff); + ilk_csc_convert_ctm(crtc_state, coeff, false); ilk_update_pipe_csc(crtc, ilk_csc_off_zero, coeff, ilk_csc_off_zero); } @@ -375,7 +374,7 @@ static void icl_load_csc_matrix(const struct intel_crtc_state *crtc_state) static void chv_load_cgm_csc(struct intel_crtc *crtc, const struct drm_property_blob *blob) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); const struct drm_color_ctm *ctm = blob->data; enum pipe pipe = crtc->pipe; u16 coeffs[9]; @@ -399,15 +398,15 @@ static void chv_load_cgm_csc(struct intel_crtc *crtc, coeffs[i] |= (abs_coeff >> 20) & 0xfff; } - intel_de_write_fw(dev_priv, CGM_PIPE_CSC_COEFF01(pipe), + intel_de_write_fw(i915, CGM_PIPE_CSC_COEFF01(pipe), coeffs[1] << 16 | coeffs[0]); - intel_de_write_fw(dev_priv, CGM_PIPE_CSC_COEFF23(pipe), + intel_de_write_fw(i915, CGM_PIPE_CSC_COEFF23(pipe), coeffs[3] << 16 | coeffs[2]); - intel_de_write_fw(dev_priv, CGM_PIPE_CSC_COEFF45(pipe), + intel_de_write_fw(i915, CGM_PIPE_CSC_COEFF45(pipe), coeffs[5] << 16 | coeffs[4]); - intel_de_write_fw(dev_priv, CGM_PIPE_CSC_COEFF67(pipe), + intel_de_write_fw(i915, CGM_PIPE_CSC_COEFF67(pipe), coeffs[7] << 16 | coeffs[6]); - intel_de_write_fw(dev_priv, CGM_PIPE_CSC_COEFF8(pipe), + intel_de_write_fw(i915, CGM_PIPE_CSC_COEFF8(pipe), coeffs[8]); } @@ -426,32 +425,32 @@ static u32 intel_color_lut_pack(u32 val, int bit_precision) static u32 i9xx_lut_8(const struct drm_color_lut *color) { - return drm_color_lut_extract(color->red, 8) << 16 | - drm_color_lut_extract(color->green, 8) << 8 | - drm_color_lut_extract(color->blue, 8); + return REG_FIELD_PREP(PALETTE_RED_MASK, drm_color_lut_extract(color->red, 8)) | + REG_FIELD_PREP(PALETTE_GREEN_MASK, drm_color_lut_extract(color->green, 8)) | + REG_FIELD_PREP(PALETTE_BLUE_MASK, drm_color_lut_extract(color->blue, 8)); } static void i9xx_lut_8_pack(struct drm_color_lut *entry, u32 val) { - entry->red = intel_color_lut_pack(REG_FIELD_GET(LGC_PALETTE_RED_MASK, val), 8); - entry->green = intel_color_lut_pack(REG_FIELD_GET(LGC_PALETTE_GREEN_MASK, val), 8); - entry->blue = intel_color_lut_pack(REG_FIELD_GET(LGC_PALETTE_BLUE_MASK, val), 8); + entry->red = intel_color_lut_pack(REG_FIELD_GET(PALETTE_RED_MASK, val), 8); + entry->green = intel_color_lut_pack(REG_FIELD_GET(PALETTE_GREEN_MASK, val), 8); + entry->blue = intel_color_lut_pack(REG_FIELD_GET(PALETTE_BLUE_MASK, val), 8); } /* i965+ "10.6" bit interpolated format "even DW" (low 8 bits) */ static u32 i965_lut_10p6_ldw(const struct drm_color_lut *color) { - return (color->red & 0xff) << 16 | - (color->green & 0xff) << 8 | - (color->blue & 0xff); + return REG_FIELD_PREP(PALETTE_RED_MASK, color->red & 0xff) | + REG_FIELD_PREP(PALETTE_GREEN_MASK, color->green & 0xff) | + REG_FIELD_PREP(PALETTE_BLUE_MASK, color->blue & 0xff); } /* i965+ "10.6" interpolated format "odd DW" (high 8 bits) */ static u32 i965_lut_10p6_udw(const struct drm_color_lut *color) { - return (color->red >> 8) << 16 | - (color->green >> 8) << 8 | - (color->blue >> 8); + return REG_FIELD_PREP(PALETTE_RED_MASK, color->red >> 8) | + REG_FIELD_PREP(PALETTE_GREEN_MASK, color->green >> 8) | + REG_FIELD_PREP(PALETTE_BLUE_MASK, color->blue >> 8); } static void i965_lut_10p6_pack(struct drm_color_lut *entry, u32 ldw, u32 udw) @@ -472,26 +471,42 @@ static u16 i965_lut_11p6_max_pack(u32 val) static u32 ilk_lut_10(const struct drm_color_lut *color) { - return drm_color_lut_extract(color->red, 10) << 20 | - drm_color_lut_extract(color->green, 10) << 10 | - drm_color_lut_extract(color->blue, 10); + return REG_FIELD_PREP(PREC_PALETTE_10_RED_MASK, drm_color_lut_extract(color->red, 10)) | + REG_FIELD_PREP(PREC_PALETTE_10_GREEN_MASK, drm_color_lut_extract(color->green, 10)) | + REG_FIELD_PREP(PREC_PALETTE_10_BLUE_MASK, drm_color_lut_extract(color->blue, 10)); } static void ilk_lut_10_pack(struct drm_color_lut *entry, u32 val) { - entry->red = intel_color_lut_pack(REG_FIELD_GET(PREC_PALETTE_RED_MASK, val), 10); - entry->green = intel_color_lut_pack(REG_FIELD_GET(PREC_PALETTE_GREEN_MASK, val), 10); - entry->blue = intel_color_lut_pack(REG_FIELD_GET(PREC_PALETTE_BLUE_MASK, val), 10); + entry->red = intel_color_lut_pack(REG_FIELD_GET(PREC_PALETTE_10_RED_MASK, val), 10); + entry->green = intel_color_lut_pack(REG_FIELD_GET(PREC_PALETTE_10_GREEN_MASK, val), 10); + entry->blue = intel_color_lut_pack(REG_FIELD_GET(PREC_PALETTE_10_BLUE_MASK, val), 10); +} + +/* ilk+ "12.4" interpolated format (low 6 bits) */ +static u32 ilk_lut_12p4_ldw(const struct drm_color_lut *color) +{ + return REG_FIELD_PREP(PREC_PALETTE_12P4_RED_LDW_MASK, color->red & 0x3f) | + REG_FIELD_PREP(PREC_PALETTE_12P4_GREEN_LDW_MASK, color->green & 0x3f) | + REG_FIELD_PREP(PREC_PALETTE_12P4_BLUE_LDW_MASK, color->blue & 0x3f); +} + +/* ilk+ "12.4" interpolated format (high 10 bits) */ +static u32 ilk_lut_12p4_udw(const struct drm_color_lut *color) +{ + return REG_FIELD_PREP(PREC_PALETTE_12P4_RED_UDW_MASK, color->red >> 6) | + REG_FIELD_PREP(PREC_PALETTE_12P4_GREEN_UDW_MASK, color->green >> 6) | + REG_FIELD_PREP(PREC_PALETTE_12P4_BLUE_UDW_MASK, color->blue >> 6); } -static void icl_lut_multi_seg_pack(struct drm_color_lut *entry, u32 ldw, u32 udw) +static void ilk_lut_12p4_pack(struct drm_color_lut *entry, u32 ldw, u32 udw) { - entry->red = REG_FIELD_GET(PAL_PREC_MULTI_SEG_RED_UDW_MASK, udw) << 6 | - REG_FIELD_GET(PAL_PREC_MULTI_SEG_RED_LDW_MASK, ldw); - entry->green = REG_FIELD_GET(PAL_PREC_MULTI_SEG_GREEN_UDW_MASK, udw) << 6 | - REG_FIELD_GET(PAL_PREC_MULTI_SEG_GREEN_LDW_MASK, ldw); - entry->blue = REG_FIELD_GET(PAL_PREC_MULTI_SEG_BLUE_UDW_MASK, udw) << 6 | - REG_FIELD_GET(PAL_PREC_MULTI_SEG_BLUE_LDW_MASK, ldw); + entry->red = REG_FIELD_GET(PREC_PALETTE_12P4_RED_UDW_MASK, udw) << 6 | + REG_FIELD_GET(PREC_PALETTE_12P4_RED_LDW_MASK, ldw); + entry->green = REG_FIELD_GET(PREC_PALETTE_12P4_GREEN_UDW_MASK, udw) << 6 | + REG_FIELD_GET(PREC_PALETTE_12P4_GREEN_LDW_MASK, ldw); + entry->blue = REG_FIELD_GET(PREC_PALETTE_12P4_BLUE_UDW_MASK, udw) << 6 | + REG_FIELD_GET(PREC_PALETTE_12P4_BLUE_LDW_MASK, ldw); } static void icl_color_commit_noarm(const struct intel_crtc_state *crtc_state) @@ -513,31 +528,31 @@ static void i9xx_color_commit_arm(const struct intel_crtc_state *crtc_state) static void ilk_color_commit_arm(const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); /* update PIPECONF GAMMA_MODE */ ilk_set_pipeconf(crtc_state); - intel_de_write_fw(dev_priv, PIPE_CSC_MODE(crtc->pipe), + intel_de_write_fw(i915, PIPE_CSC_MODE(crtc->pipe), crtc_state->csc_mode); } static void hsw_color_commit_arm(const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); - intel_de_write(dev_priv, GAMMA_MODE(crtc->pipe), + intel_de_write(i915, GAMMA_MODE(crtc->pipe), crtc_state->gamma_mode); - intel_de_write_fw(dev_priv, PIPE_CSC_MODE(crtc->pipe), + intel_de_write_fw(i915, PIPE_CSC_MODE(crtc->pipe), crtc_state->csc_mode); } static void skl_color_commit_arm(const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); enum pipe pipe = crtc->pipe; u32 val = 0; @@ -550,15 +565,65 @@ static void skl_color_commit_arm(const struct intel_crtc_state *crtc_state) val |= SKL_BOTTOM_COLOR_GAMMA_ENABLE; if (crtc_state->csc_enable) val |= SKL_BOTTOM_COLOR_CSC_ENABLE; - intel_de_write(dev_priv, SKL_BOTTOM_COLOR(pipe), val); + intel_de_write(i915, SKL_BOTTOM_COLOR(pipe), val); - intel_de_write(dev_priv, GAMMA_MODE(crtc->pipe), + intel_de_write(i915, GAMMA_MODE(crtc->pipe), crtc_state->gamma_mode); - intel_de_write_fw(dev_priv, PIPE_CSC_MODE(crtc->pipe), + intel_de_write_fw(i915, PIPE_CSC_MODE(crtc->pipe), crtc_state->csc_mode); } +static struct drm_property_blob * +create_linear_lut(struct drm_i915_private *i915, int lut_size) +{ + struct drm_property_blob *blob; + struct drm_color_lut *lut; + int i; + + blob = drm_property_create_blob(&i915->drm, + sizeof(lut[0]) * lut_size, + NULL); + if (IS_ERR(blob)) + return blob; + + lut = blob->data; + + for (i = 0; i < lut_size; i++) { + u16 val = 0xffff * i / (lut_size - 1); + + lut[i].red = val; + lut[i].green = val; + lut[i].blue = val; + } + + return blob; +} + +static struct drm_property_blob * +create_resized_lut(struct drm_i915_private *i915, + const struct drm_property_blob *blob_in, int lut_out_size) +{ + int i, lut_in_size = drm_color_lut_size(blob_in); + struct drm_property_blob *blob_out; + const struct drm_color_lut *lut_in; + struct drm_color_lut *lut_out; + + blob_out = drm_property_create_blob(&i915->drm, + sizeof(lut_out[0]) * lut_out_size, + NULL); + if (IS_ERR(blob_out)) + return blob_out; + + lut_in = blob_in->data; + lut_out = blob_out->data; + + for (i = 0; i < lut_out_size; i++) + lut_out[i] = lut_in[i * (lut_in_size - 1) / (lut_out_size - 1)]; + + return blob_out; +} + static void i9xx_load_lut_8(struct intel_crtc *crtc, const struct drm_property_blob *blob) { @@ -580,12 +645,9 @@ static void i9xx_load_lut_8(struct intel_crtc *crtc, static void i9xx_load_luts(const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut; + const struct drm_property_blob *post_csc_lut = crtc_state->post_csc_lut; - assert_pll_enabled(dev_priv, crtc->pipe); - - i9xx_load_lut_8(crtc, gamma_lut); + i9xx_load_lut_8(crtc, post_csc_lut); } static void i965_load_lut_10p6(struct intel_crtc *crtc, @@ -611,24 +673,18 @@ static void i965_load_lut_10p6(struct intel_crtc *crtc, static void i965_load_luts(const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut; - - if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI)) - assert_dsi_pll_enabled(dev_priv); - else - assert_pll_enabled(dev_priv, crtc->pipe); + const struct drm_property_blob *post_csc_lut = crtc_state->post_csc_lut; if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT) - i9xx_load_lut_8(crtc, gamma_lut); + i9xx_load_lut_8(crtc, post_csc_lut); else - i965_load_lut_10p6(crtc, gamma_lut); + i965_load_lut_10p6(crtc, post_csc_lut); } static void ilk_load_lut_8(struct intel_crtc *crtc, const struct drm_property_blob *blob) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); const struct drm_color_lut *lut; enum pipe pipe = crtc->pipe; int i; @@ -639,34 +695,36 @@ static void ilk_load_lut_8(struct intel_crtc *crtc, lut = blob->data; for (i = 0; i < 256; i++) - intel_de_write_fw(dev_priv, LGC_PALETTE(pipe, i), + intel_de_write_fw(i915, LGC_PALETTE(pipe, i), i9xx_lut_8(&lut[i])); } static void ilk_load_lut_10(struct intel_crtc *crtc, const struct drm_property_blob *blob) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); const struct drm_color_lut *lut = blob->data; int i, lut_size = drm_color_lut_size(blob); enum pipe pipe = crtc->pipe; for (i = 0; i < lut_size; i++) - intel_de_write_fw(dev_priv, PREC_PALETTE(pipe, i), + intel_de_write_fw(i915, PREC_PALETTE(pipe, i), ilk_lut_10(&lut[i])); } static void ilk_load_luts(const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut; + const struct drm_property_blob *post_csc_lut = crtc_state->post_csc_lut; + const struct drm_property_blob *pre_csc_lut = crtc_state->pre_csc_lut; + const struct drm_property_blob *blob = post_csc_lut ?: pre_csc_lut; switch (crtc_state->gamma_mode) { case GAMMA_MODE_MODE_8BIT: - ilk_load_lut_8(crtc, gamma_lut); + ilk_load_lut_8(crtc, blob); break; case GAMMA_MODE_MODE_10BIT: - ilk_load_lut_10(crtc, gamma_lut); + ilk_load_lut_10(crtc, blob); break; default: MISSING_CASE(crtc_state->gamma_mode); @@ -691,27 +749,22 @@ static void ivb_load_lut_10(struct intel_crtc *crtc, const struct drm_property_blob *blob, u32 prec_index) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - int hw_lut_size = ivb_lut_10_size(prec_index); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); const struct drm_color_lut *lut = blob->data; int i, lut_size = drm_color_lut_size(blob); enum pipe pipe = crtc->pipe; - for (i = 0; i < hw_lut_size; i++) { - /* We discard half the user entries in split gamma mode */ - const struct drm_color_lut *entry = - &lut[i * (lut_size - 1) / (hw_lut_size - 1)]; - - intel_de_write_fw(dev_priv, PREC_PAL_INDEX(pipe), prec_index++); - intel_de_write_fw(dev_priv, PREC_PAL_DATA(pipe), - ilk_lut_10(entry)); + for (i = 0; i < lut_size; i++) { + intel_de_write_fw(i915, PREC_PAL_INDEX(pipe), prec_index++); + intel_de_write_fw(i915, PREC_PAL_DATA(pipe), + ilk_lut_10(&lut[i])); } /* * Reset the index, otherwise it prevents the legacy palette to be * written properly. */ - intel_de_write_fw(dev_priv, PREC_PAL_INDEX(pipe), 0); + intel_de_write_fw(i915, PREC_PAL_INDEX(pipe), 0); } /* On BDW+ the index auto increment mode actually works */ @@ -719,73 +772,63 @@ static void bdw_load_lut_10(struct intel_crtc *crtc, const struct drm_property_blob *blob, u32 prec_index) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - int hw_lut_size = ivb_lut_10_size(prec_index); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); const struct drm_color_lut *lut = blob->data; int i, lut_size = drm_color_lut_size(blob); enum pipe pipe = crtc->pipe; - intel_de_write_fw(dev_priv, PREC_PAL_INDEX(pipe), + intel_de_write_fw(i915, PREC_PAL_INDEX(pipe), prec_index | PAL_PREC_AUTO_INCREMENT); - for (i = 0; i < hw_lut_size; i++) { - /* We discard half the user entries in split gamma mode */ - const struct drm_color_lut *entry = - &lut[i * (lut_size - 1) / (hw_lut_size - 1)]; - - intel_de_write_fw(dev_priv, PREC_PAL_DATA(pipe), - ilk_lut_10(entry)); - } + for (i = 0; i < lut_size; i++) + intel_de_write_fw(i915, PREC_PAL_DATA(pipe), + ilk_lut_10(&lut[i])); /* * Reset the index, otherwise it prevents the legacy palette to be * written properly. */ - intel_de_write_fw(dev_priv, PREC_PAL_INDEX(pipe), 0); + intel_de_write_fw(i915, PREC_PAL_INDEX(pipe), 0); } static void ivb_load_lut_ext_max(const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum pipe pipe = crtc->pipe; /* Program the max register to clamp values > 1.0. */ intel_dsb_reg_write(crtc_state, PREC_PAL_EXT_GC_MAX(pipe, 0), 1 << 16); intel_dsb_reg_write(crtc_state, PREC_PAL_EXT_GC_MAX(pipe, 1), 1 << 16); intel_dsb_reg_write(crtc_state, PREC_PAL_EXT_GC_MAX(pipe, 2), 1 << 16); +} - /* - * Program the gc max 2 register to clamp values > 1.0. - * ToDo: Extend the ABI to be able to program values - * from 3.0 to 7.0 - */ - if (DISPLAY_VER(dev_priv) >= 10) { - intel_dsb_reg_write(crtc_state, PREC_PAL_EXT2_GC_MAX(pipe, 0), - 1 << 16); - intel_dsb_reg_write(crtc_state, PREC_PAL_EXT2_GC_MAX(pipe, 1), - 1 << 16); - intel_dsb_reg_write(crtc_state, PREC_PAL_EXT2_GC_MAX(pipe, 2), - 1 << 16); - } +static void glk_load_lut_ext2_max(const struct intel_crtc_state *crtc_state) +{ + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + enum pipe pipe = crtc->pipe; + + /* Program the max register to clamp values > 1.0. */ + intel_dsb_reg_write(crtc_state, PREC_PAL_EXT2_GC_MAX(pipe, 0), 1 << 16); + intel_dsb_reg_write(crtc_state, PREC_PAL_EXT2_GC_MAX(pipe, 1), 1 << 16); + intel_dsb_reg_write(crtc_state, PREC_PAL_EXT2_GC_MAX(pipe, 2), 1 << 16); } static void ivb_load_luts(const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut; - const struct drm_property_blob *degamma_lut = crtc_state->hw.degamma_lut; - const struct drm_property_blob *blob = gamma_lut ?: degamma_lut; + const struct drm_property_blob *post_csc_lut = crtc_state->post_csc_lut; + const struct drm_property_blob *pre_csc_lut = crtc_state->pre_csc_lut; + const struct drm_property_blob *blob = post_csc_lut ?: pre_csc_lut; switch (crtc_state->gamma_mode) { case GAMMA_MODE_MODE_8BIT: ilk_load_lut_8(crtc, blob); break; case GAMMA_MODE_MODE_SPLIT: - ivb_load_lut_10(crtc, degamma_lut, PAL_PREC_SPLIT_MODE | + ivb_load_lut_10(crtc, pre_csc_lut, PAL_PREC_SPLIT_MODE | PAL_PREC_INDEX_VALUE(0)); ivb_load_lut_ext_max(crtc_state); - ivb_load_lut_10(crtc, gamma_lut, PAL_PREC_SPLIT_MODE | + ivb_load_lut_10(crtc, post_csc_lut, PAL_PREC_SPLIT_MODE | PAL_PREC_INDEX_VALUE(512)); break; case GAMMA_MODE_MODE_10BIT: @@ -802,19 +845,19 @@ static void ivb_load_luts(const struct intel_crtc_state *crtc_state) static void bdw_load_luts(const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut; - const struct drm_property_blob *degamma_lut = crtc_state->hw.degamma_lut; - const struct drm_property_blob *blob = gamma_lut ?: degamma_lut; + const struct drm_property_blob *post_csc_lut = crtc_state->post_csc_lut; + const struct drm_property_blob *pre_csc_lut = crtc_state->pre_csc_lut; + const struct drm_property_blob *blob = post_csc_lut ?: pre_csc_lut; switch (crtc_state->gamma_mode) { case GAMMA_MODE_MODE_8BIT: ilk_load_lut_8(crtc, blob); break; case GAMMA_MODE_MODE_SPLIT: - bdw_load_lut_10(crtc, degamma_lut, PAL_PREC_SPLIT_MODE | + bdw_load_lut_10(crtc, pre_csc_lut, PAL_PREC_SPLIT_MODE | PAL_PREC_INDEX_VALUE(0)); ivb_load_lut_ext_max(crtc_state); - bdw_load_lut_10(crtc, gamma_lut, PAL_PREC_SPLIT_MODE | + bdw_load_lut_10(crtc, post_csc_lut, PAL_PREC_SPLIT_MODE | PAL_PREC_INDEX_VALUE(512)); break; case GAMMA_MODE_MODE_10BIT: @@ -837,21 +880,22 @@ static int glk_degamma_lut_size(struct drm_i915_private *i915) return 35; } -static void glk_load_degamma_lut(const struct intel_crtc_state *crtc_state) +static void glk_load_degamma_lut(const struct intel_crtc_state *crtc_state, + const struct drm_property_blob *blob) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + const struct drm_color_lut *lut = blob->data; + int i, lut_size = drm_color_lut_size(blob); enum pipe pipe = crtc->pipe; - int i, lut_size = INTEL_INFO(dev_priv)->display.color.degamma_lut_size; - const struct drm_color_lut *lut = crtc_state->hw.degamma_lut->data; /* * When setting the auto-increment bit, the hardware seems to * ignore the index bits, so we need to reset it to index 0 * separately. */ - intel_de_write_fw(dev_priv, PRE_CSC_GAMC_INDEX(pipe), 0); - intel_de_write_fw(dev_priv, PRE_CSC_GAMC_INDEX(pipe), + intel_de_write_fw(i915, PRE_CSC_GAMC_INDEX(pipe), 0); + intel_de_write_fw(i915, PRE_CSC_GAMC_INDEX(pipe), PRE_CSC_GAMC_AUTO_INCREMENT); for (i = 0; i < lut_size; i++) { @@ -868,71 +912,34 @@ static void glk_load_degamma_lut(const struct intel_crtc_state *crtc_state) * ToDo: Extend to max 7.0. Enable 32 bit input value * as compared to just 16 to achieve this. */ - intel_de_write_fw(dev_priv, PRE_CSC_GAMC_DATA(pipe), + intel_de_write_fw(i915, PRE_CSC_GAMC_DATA(pipe), lut[i].green); } /* Clamp values > 1.0. */ - while (i++ < glk_degamma_lut_size(dev_priv)) - intel_de_write_fw(dev_priv, PRE_CSC_GAMC_DATA(pipe), 1 << 16); + while (i++ < glk_degamma_lut_size(i915)) + intel_de_write_fw(i915, PRE_CSC_GAMC_DATA(pipe), 1 << 16); - intel_de_write_fw(dev_priv, PRE_CSC_GAMC_INDEX(pipe), 0); -} - -static void glk_load_degamma_lut_linear(const struct intel_crtc_state *crtc_state) -{ - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - enum pipe pipe = crtc->pipe; - int i, lut_size = INTEL_INFO(dev_priv)->display.color.degamma_lut_size; - - /* - * When setting the auto-increment bit, the hardware seems to - * ignore the index bits, so we need to reset it to index 0 - * separately. - */ - intel_de_write_fw(dev_priv, PRE_CSC_GAMC_INDEX(pipe), 0); - intel_de_write_fw(dev_priv, PRE_CSC_GAMC_INDEX(pipe), - PRE_CSC_GAMC_AUTO_INCREMENT); - - for (i = 0; i < lut_size; i++) { - u32 v = (i << 16) / (lut_size - 1); - - intel_de_write_fw(dev_priv, PRE_CSC_GAMC_DATA(pipe), v); - } - - /* Clamp values > 1.0. */ - while (i++ < 35) - intel_de_write_fw(dev_priv, PRE_CSC_GAMC_DATA(pipe), 1 << 16); - - intel_de_write_fw(dev_priv, PRE_CSC_GAMC_INDEX(pipe), 0); + intel_de_write_fw(i915, PRE_CSC_GAMC_INDEX(pipe), 0); } static void glk_load_luts(const struct intel_crtc_state *crtc_state) { - const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut; + const struct drm_property_blob *pre_csc_lut = crtc_state->pre_csc_lut; + const struct drm_property_blob *post_csc_lut = crtc_state->post_csc_lut; struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - /* - * On GLK+ both pipe CSC and degamma LUT are controlled - * by csc_enable. Hence for the cases where the CSC is - * needed but degamma LUT is not we need to load a - * linear degamma LUT. In fact we'll just always load - * the degama LUT so that we don't have to reload - * it every time the pipe CSC is being enabled. - */ - if (crtc_state->hw.degamma_lut) - glk_load_degamma_lut(crtc_state); - else - glk_load_degamma_lut_linear(crtc_state); + if (pre_csc_lut) + glk_load_degamma_lut(crtc_state, pre_csc_lut); switch (crtc_state->gamma_mode) { case GAMMA_MODE_MODE_8BIT: - ilk_load_lut_8(crtc, gamma_lut); + ilk_load_lut_8(crtc, post_csc_lut); break; case GAMMA_MODE_MODE_10BIT: - bdw_load_lut_10(crtc, gamma_lut, PAL_PREC_INDEX_VALUE(0)); + bdw_load_lut_10(crtc, post_csc_lut, PAL_PREC_INDEX_VALUE(0)); ivb_load_lut_ext_max(crtc_state); + glk_load_lut_ext2_max(crtc_state); break; default: MISSING_CASE(crtc_state->gamma_mode); @@ -940,23 +947,9 @@ static void glk_load_luts(const struct intel_crtc_state *crtc_state) } } -/* ilk+ "12.4" interpolated format (high 10 bits) */ -static u32 ilk_lut_12p4_udw(const struct drm_color_lut *color) -{ - return (color->red >> 6) << 20 | (color->green >> 6) << 10 | - (color->blue >> 6); -} - -/* ilk+ "12.4" interpolated format (low 6 bits) */ -static u32 ilk_lut_12p4_ldw(const struct drm_color_lut *color) -{ - return (color->red & 0x3f) << 24 | (color->green & 0x3f) << 14 | - (color->blue & 0x3f) << 4; -} - static void -icl_load_gcmax(const struct intel_crtc_state *crtc_state, - const struct drm_color_lut *color) +ivb_load_lut_max(const struct intel_crtc_state *crtc_state, + const struct drm_color_lut *color) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); enum pipe pipe = crtc->pipe; @@ -971,7 +964,7 @@ static void icl_program_gamma_superfine_segment(const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - const struct drm_property_blob *blob = crtc_state->hw.gamma_lut; + const struct drm_property_blob *blob = crtc_state->post_csc_lut; const struct drm_color_lut *lut = blob->data; enum pipe pipe = crtc->pipe; int i; @@ -1000,7 +993,7 @@ static void icl_program_gamma_multi_segment(const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - const struct drm_property_blob *blob = crtc_state->hw.gamma_lut; + const struct drm_property_blob *blob = crtc_state->post_csc_lut; const struct drm_color_lut *lut = blob->data; const struct drm_color_lut *entry; enum pipe pipe = crtc->pipe; @@ -1048,29 +1041,32 @@ icl_program_gamma_multi_segment(const struct intel_crtc_state *crtc_state) /* The last entry in the LUT is to be programmed in GCMAX */ entry = &lut[256 * 8 * 128]; - icl_load_gcmax(crtc_state, entry); - ivb_load_lut_ext_max(crtc_state); + ivb_load_lut_max(crtc_state, entry); } static void icl_load_luts(const struct intel_crtc_state *crtc_state) { - const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut; + const struct drm_property_blob *pre_csc_lut = crtc_state->pre_csc_lut; + const struct drm_property_blob *post_csc_lut = crtc_state->post_csc_lut; struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - if (crtc_state->hw.degamma_lut) - glk_load_degamma_lut(crtc_state); + if (pre_csc_lut) + glk_load_degamma_lut(crtc_state, pre_csc_lut); switch (crtc_state->gamma_mode & GAMMA_MODE_MODE_MASK) { case GAMMA_MODE_MODE_8BIT: - ilk_load_lut_8(crtc, gamma_lut); + ilk_load_lut_8(crtc, post_csc_lut); break; case GAMMA_MODE_MODE_12BIT_MULTI_SEGMENTED: icl_program_gamma_superfine_segment(crtc_state); icl_program_gamma_multi_segment(crtc_state); + ivb_load_lut_ext_max(crtc_state); + glk_load_lut_ext2_max(crtc_state); break; case GAMMA_MODE_MODE_10BIT: - bdw_load_lut_10(crtc, gamma_lut, PAL_PREC_INDEX_VALUE(0)); + bdw_load_lut_10(crtc, post_csc_lut, PAL_PREC_INDEX_VALUE(0)); ivb_load_lut_ext_max(crtc_state); + glk_load_lut_ext2_max(crtc_state); break; default: MISSING_CASE(crtc_state->gamma_mode); @@ -1082,61 +1078,61 @@ static void icl_load_luts(const struct intel_crtc_state *crtc_state) static u32 chv_cgm_degamma_ldw(const struct drm_color_lut *color) { - return drm_color_lut_extract(color->green, 14) << 16 | - drm_color_lut_extract(color->blue, 14); + return REG_FIELD_PREP(CGM_PIPE_DEGAMMA_GREEN_LDW_MASK, drm_color_lut_extract(color->green, 14)) | + REG_FIELD_PREP(CGM_PIPE_DEGAMMA_BLUE_LDW_MASK, drm_color_lut_extract(color->blue, 14)); } static u32 chv_cgm_degamma_udw(const struct drm_color_lut *color) { - return drm_color_lut_extract(color->red, 14); + return REG_FIELD_PREP(CGM_PIPE_DEGAMMA_RED_UDW_MASK, drm_color_lut_extract(color->red, 14)); } static void chv_load_cgm_degamma(struct intel_crtc *crtc, const struct drm_property_blob *blob) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); const struct drm_color_lut *lut = blob->data; int i, lut_size = drm_color_lut_size(blob); enum pipe pipe = crtc->pipe; for (i = 0; i < lut_size; i++) { - intel_de_write_fw(dev_priv, CGM_PIPE_DEGAMMA(pipe, i, 0), + intel_de_write_fw(i915, CGM_PIPE_DEGAMMA(pipe, i, 0), chv_cgm_degamma_ldw(&lut[i])); - intel_de_write_fw(dev_priv, CGM_PIPE_DEGAMMA(pipe, i, 1), + intel_de_write_fw(i915, CGM_PIPE_DEGAMMA(pipe, i, 1), chv_cgm_degamma_udw(&lut[i])); } } static u32 chv_cgm_gamma_ldw(const struct drm_color_lut *color) { - return drm_color_lut_extract(color->green, 10) << 16 | - drm_color_lut_extract(color->blue, 10); + return REG_FIELD_PREP(CGM_PIPE_GAMMA_GREEN_LDW_MASK, drm_color_lut_extract(color->green, 10)) | + REG_FIELD_PREP(CGM_PIPE_GAMMA_BLUE_LDW_MASK, drm_color_lut_extract(color->blue, 10)); } static u32 chv_cgm_gamma_udw(const struct drm_color_lut *color) { - return drm_color_lut_extract(color->red, 10); + return REG_FIELD_PREP(CGM_PIPE_GAMMA_RED_UDW_MASK, drm_color_lut_extract(color->red, 10)); } static void chv_cgm_gamma_pack(struct drm_color_lut *entry, u32 ldw, u32 udw) { - entry->green = intel_color_lut_pack(REG_FIELD_GET(CGM_PIPE_GAMMA_GREEN_MASK, ldw), 10); - entry->blue = intel_color_lut_pack(REG_FIELD_GET(CGM_PIPE_GAMMA_BLUE_MASK, ldw), 10); - entry->red = intel_color_lut_pack(REG_FIELD_GET(CGM_PIPE_GAMMA_RED_MASK, udw), 10); + entry->green = intel_color_lut_pack(REG_FIELD_GET(CGM_PIPE_GAMMA_GREEN_LDW_MASK, ldw), 10); + entry->blue = intel_color_lut_pack(REG_FIELD_GET(CGM_PIPE_GAMMA_BLUE_LDW_MASK, ldw), 10); + entry->red = intel_color_lut_pack(REG_FIELD_GET(CGM_PIPE_GAMMA_RED_UDW_MASK, udw), 10); } static void chv_load_cgm_gamma(struct intel_crtc *crtc, const struct drm_property_blob *blob) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); const struct drm_color_lut *lut = blob->data; int i, lut_size = drm_color_lut_size(blob); enum pipe pipe = crtc->pipe; for (i = 0; i < lut_size; i++) { - intel_de_write_fw(dev_priv, CGM_PIPE_GAMMA(pipe, i, 0), + intel_de_write_fw(i915, CGM_PIPE_GAMMA(pipe, i, 0), chv_cgm_gamma_ldw(&lut[i])); - intel_de_write_fw(dev_priv, CGM_PIPE_GAMMA(pipe, i, 1), + intel_de_write_fw(i915, CGM_PIPE_GAMMA(pipe, i, 1), chv_cgm_gamma_udw(&lut[i])); } } @@ -1144,46 +1140,46 @@ static void chv_load_cgm_gamma(struct intel_crtc *crtc, static void chv_load_luts(const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - const struct drm_property_blob *degamma_lut = crtc_state->hw.degamma_lut; - const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut; + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + const struct drm_property_blob *pre_csc_lut = crtc_state->pre_csc_lut; + const struct drm_property_blob *post_csc_lut = crtc_state->post_csc_lut; const struct drm_property_blob *ctm = crtc_state->hw.ctm; if (crtc_state->cgm_mode & CGM_PIPE_MODE_CSC) chv_load_cgm_csc(crtc, ctm); if (crtc_state->cgm_mode & CGM_PIPE_MODE_DEGAMMA) - chv_load_cgm_degamma(crtc, degamma_lut); + chv_load_cgm_degamma(crtc, pre_csc_lut); if (crtc_state->cgm_mode & CGM_PIPE_MODE_GAMMA) - chv_load_cgm_gamma(crtc, gamma_lut); + chv_load_cgm_gamma(crtc, post_csc_lut); else i965_load_luts(crtc_state); - intel_de_write_fw(dev_priv, CGM_PIPE_MODE(crtc->pipe), + intel_de_write_fw(i915, CGM_PIPE_MODE(crtc->pipe), crtc_state->cgm_mode); } void intel_color_load_luts(const struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); - dev_priv->display.funcs.color->load_luts(crtc_state); + i915->display.funcs.color->load_luts(crtc_state); } void intel_color_commit_noarm(const struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); - if (dev_priv->display.funcs.color->color_commit_noarm) - dev_priv->display.funcs.color->color_commit_noarm(crtc_state); + if (i915->display.funcs.color->color_commit_noarm) + i915->display.funcs.color->color_commit_noarm(crtc_state); } void intel_color_commit_arm(const struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); - dev_priv->display.funcs.color->color_commit_arm(crtc_state); + i915->display.funcs.color->color_commit_arm(crtc_state); } static bool intel_can_preload_luts(const struct intel_crtc_state *new_crtc_state) @@ -1194,8 +1190,8 @@ static bool intel_can_preload_luts(const struct intel_crtc_state *new_crtc_state const struct intel_crtc_state *old_crtc_state = intel_atomic_get_old_crtc_state(state, crtc); - return !old_crtc_state->hw.gamma_lut && - !old_crtc_state->hw.degamma_lut; + return !old_crtc_state->post_csc_lut && + !old_crtc_state->pre_csc_lut; } static bool chv_can_preload_luts(const struct intel_crtc_state *new_crtc_state) @@ -1214,46 +1210,28 @@ static bool chv_can_preload_luts(const struct intel_crtc_state *new_crtc_state) if (old_crtc_state->cgm_mode || new_crtc_state->cgm_mode) return false; - return !old_crtc_state->hw.gamma_lut; -} - -static bool glk_can_preload_luts(const struct intel_crtc_state *new_crtc_state) -{ - struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc); - struct intel_atomic_state *state = - to_intel_atomic_state(new_crtc_state->uapi.state); - const struct intel_crtc_state *old_crtc_state = - intel_atomic_get_old_crtc_state(state, crtc); - - /* - * The hardware degamma is active whenever the pipe - * CSC is active. Thus even if the old state has no - * software degamma we need to avoid clobbering the - * linear hardware degamma mid scanout. - */ - return !old_crtc_state->csc_enable && - !old_crtc_state->hw.gamma_lut; + return !old_crtc_state->post_csc_lut; } int intel_color_check(struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); - return dev_priv->display.funcs.color->color_check(crtc_state); + return i915->display.funcs.color->color_check(crtc_state); } void intel_color_get_config(struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); - if (dev_priv->display.funcs.color->read_luts) - dev_priv->display.funcs.color->read_luts(crtc_state); + if (i915->display.funcs.color->read_luts) + i915->display.funcs.color->read_luts(crtc_state); } static bool need_plane_update(struct intel_plane *plane, const struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + struct drm_i915_private *i915 = to_i915(plane->base.dev); /* * On pre-SKL the pipe gamma enable and pipe csc enable for @@ -1261,7 +1239,7 @@ static bool need_plane_update(struct intel_plane *plane, * We have to reconfigure that even if the plane is inactive. */ return crtc_state->active_planes & BIT(plane->id) || - (DISPLAY_VER(dev_priv) < 9 && + (DISPLAY_VER(i915) < 9 && plane->id == PLANE_PRIMARY); } @@ -1269,7 +1247,7 @@ static int intel_color_add_affected_planes(struct intel_crtc_state *new_crtc_state) { struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); struct intel_atomic_state *state = to_intel_atomic_state(new_crtc_state->uapi.state); const struct intel_crtc_state *old_crtc_state = @@ -1277,14 +1255,14 @@ intel_color_add_affected_planes(struct intel_crtc_state *new_crtc_state) struct intel_plane *plane; if (!new_crtc_state->hw.active || - drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi)) + intel_crtc_needs_modeset(new_crtc_state)) return 0; if (new_crtc_state->gamma_enable == old_crtc_state->gamma_enable && new_crtc_state->csc_enable == old_crtc_state->csc_enable) return 0; - for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) { + for_each_intel_plane_on_crtc(&i915->drm, crtc, plane) { struct intel_plane_state *plane_state; if (!need_plane_update(plane, new_crtc_state)) @@ -1295,6 +1273,10 @@ intel_color_add_affected_planes(struct intel_crtc_state *new_crtc_state) return PTR_ERR(plane_state); new_crtc_state->update_planes |= BIT(plane->id); + + /* plane control register changes blocked by CxSR */ + if (HAS_GMCH(i915)) + new_crtc_state->disable_cxsr = true; } return 0; @@ -1319,7 +1301,7 @@ static int check_lut_size(const struct drm_property_blob *lut, int expected) static int check_luts(const struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut; const struct drm_property_blob *degamma_lut = crtc_state->hw.degamma_lut; int gamma_length, degamma_length; @@ -1331,15 +1313,15 @@ static int check_luts(const struct intel_crtc_state *crtc_state) /* C8 relies on its palette being stored in the legacy LUT */ if (crtc_state->c8_planes) { - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(&i915->drm, "C8 pixelformat requires the legacy LUT\n"); return -EINVAL; } - degamma_length = INTEL_INFO(dev_priv)->display.color.degamma_lut_size; - gamma_length = INTEL_INFO(dev_priv)->display.color.gamma_lut_size; - degamma_tests = INTEL_INFO(dev_priv)->display.color.degamma_lut_tests; - gamma_tests = INTEL_INFO(dev_priv)->display.color.gamma_lut_tests; + degamma_length = INTEL_INFO(i915)->display.color.degamma_lut_size; + gamma_length = INTEL_INFO(i915)->display.color.gamma_lut_size; + degamma_tests = INTEL_INFO(i915)->display.color.degamma_lut_tests; + gamma_tests = INTEL_INFO(i915)->display.color.gamma_lut_tests; if (check_lut_size(degamma_lut, degamma_length) || check_lut_size(gamma_lut, gamma_length)) @@ -1361,6 +1343,40 @@ static u32 i9xx_gamma_mode(struct intel_crtc_state *crtc_state) return GAMMA_MODE_MODE_10BIT; /* i965+ only */ } +void intel_color_assert_luts(const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); + + /* make sure {pre,post}_csc_lut were correctly assigned */ + if (DISPLAY_VER(i915) >= 11 || HAS_GMCH(i915)) { + drm_WARN_ON(&i915->drm, + crtc_state->pre_csc_lut != crtc_state->hw.degamma_lut); + drm_WARN_ON(&i915->drm, + crtc_state->post_csc_lut != crtc_state->hw.gamma_lut); + } else if (DISPLAY_VER(i915) == 10) { + drm_WARN_ON(&i915->drm, + crtc_state->pre_csc_lut != crtc_state->hw.degamma_lut && + crtc_state->pre_csc_lut != i915->display.color.glk_linear_degamma_lut); + drm_WARN_ON(&i915->drm, + crtc_state->post_csc_lut != crtc_state->hw.gamma_lut); + } else if (crtc_state->gamma_mode != GAMMA_MODE_MODE_SPLIT) { + drm_WARN_ON(&i915->drm, + crtc_state->pre_csc_lut != crtc_state->hw.degamma_lut && + crtc_state->pre_csc_lut != crtc_state->hw.gamma_lut); + drm_WARN_ON(&i915->drm, + crtc_state->post_csc_lut != crtc_state->hw.degamma_lut && + crtc_state->post_csc_lut != crtc_state->hw.gamma_lut); + } +} + +static void intel_assign_luts(struct intel_crtc_state *crtc_state) +{ + drm_property_replace_blob(&crtc_state->pre_csc_lut, + crtc_state->hw.degamma_lut); + drm_property_replace_blob(&crtc_state->post_csc_lut, + crtc_state->hw.gamma_lut); +} + static int i9xx_color_check(struct intel_crtc_state *crtc_state) { int ret; @@ -1379,6 +1395,8 @@ static int i9xx_color_check(struct intel_crtc_state *crtc_state) if (ret) return ret; + intel_assign_luts(crtc_state); + crtc_state->preload_luts = intel_can_preload_luts(crtc_state); return 0; @@ -1433,11 +1451,27 @@ static int chv_color_check(struct intel_crtc_state *crtc_state) if (ret) return ret; + intel_assign_luts(crtc_state); + crtc_state->preload_luts = chv_can_preload_luts(crtc_state); return 0; } +static bool ilk_gamma_enable(const struct intel_crtc_state *crtc_state) +{ + return (crtc_state->hw.gamma_lut || + crtc_state->hw.degamma_lut) && + !crtc_state->c8_planes; +} + +static bool ilk_csc_enable(const struct intel_crtc_state *crtc_state) +{ + return crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB || + ilk_csc_limited_range(crtc_state) || + crtc_state->hw.ctm; +} + static u32 ilk_gamma_mode(const struct intel_crtc_state *crtc_state) { if (!crtc_state->gamma_enable || @@ -1458,28 +1492,54 @@ static u32 ilk_csc_mode(const struct intel_crtc_state *crtc_state) if (crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB) return CSC_BLACK_SCREEN_OFFSET; + if (crtc_state->hw.degamma_lut) + return CSC_MODE_YUV_TO_RGB; + return CSC_MODE_YUV_TO_RGB | CSC_POSITION_BEFORE_GAMMA; } +static void ilk_assign_luts(struct intel_crtc_state *crtc_state) +{ + if (crtc_state->hw.degamma_lut || + crtc_state->csc_mode & CSC_POSITION_BEFORE_GAMMA) { + drm_property_replace_blob(&crtc_state->pre_csc_lut, + crtc_state->hw.degamma_lut); + drm_property_replace_blob(&crtc_state->post_csc_lut, + crtc_state->hw.gamma_lut); + } else { + drm_property_replace_blob(&crtc_state->pre_csc_lut, + crtc_state->hw.gamma_lut); + drm_property_replace_blob(&crtc_state->post_csc_lut, + NULL); + } +} + static int ilk_color_check(struct intel_crtc_state *crtc_state) { + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); int ret; ret = check_luts(crtc_state); if (ret) return ret; - crtc_state->gamma_enable = - crtc_state->hw.gamma_lut && - !crtc_state->c8_planes; + if (crtc_state->hw.degamma_lut && crtc_state->hw.gamma_lut) { + drm_dbg_kms(&i915->drm, + "Degamma and gamma together are not possible\n"); + return -EINVAL; + } - /* - * We don't expose the ctm on ilk/snb currently, also RGB - * limited range output is handled by the hw automagically. - */ - crtc_state->csc_enable = - crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB; + if (crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB && + crtc_state->hw.ctm) { + drm_dbg_kms(&i915->drm, + "YCbCr and CTM together are not possible\n"); + return -EINVAL; + } + + crtc_state->gamma_enable = ilk_gamma_enable(crtc_state); + + crtc_state->csc_enable = ilk_csc_enable(crtc_state); crtc_state->gamma_mode = ilk_gamma_mode(crtc_state); @@ -1489,6 +1549,8 @@ static int ilk_color_check(struct intel_crtc_state *crtc_state) if (ret) return ret; + ilk_assign_luts(crtc_state); + crtc_state->preload_luts = intel_can_preload_luts(crtc_state); return 0; @@ -1496,14 +1558,10 @@ static int ilk_color_check(struct intel_crtc_state *crtc_state) static u32 ivb_gamma_mode(const struct intel_crtc_state *crtc_state) { - if (!crtc_state->gamma_enable || - crtc_state_is_legacy_gamma(crtc_state)) - return GAMMA_MODE_MODE_8BIT; - else if (crtc_state->hw.gamma_lut && - crtc_state->hw.degamma_lut) + if (crtc_state->hw.degamma_lut && crtc_state->hw.gamma_lut) return GAMMA_MODE_MODE_SPLIT; - else - return GAMMA_MODE_MODE_10BIT; + + return ilk_gamma_mode(crtc_state); } static u32 ivb_csc_mode(const struct intel_crtc_state *crtc_state) @@ -1522,10 +1580,41 @@ static u32 ivb_csc_mode(const struct intel_crtc_state *crtc_state) return CSC_POSITION_BEFORE_GAMMA; } +static int ivb_assign_luts(struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); + struct drm_property_blob *degamma_lut, *gamma_lut; + + if (crtc_state->gamma_mode != GAMMA_MODE_MODE_SPLIT) { + ilk_assign_luts(crtc_state); + return 0; + } + + drm_WARN_ON(&i915->drm, drm_color_lut_size(crtc_state->hw.degamma_lut) != 1024); + drm_WARN_ON(&i915->drm, drm_color_lut_size(crtc_state->hw.gamma_lut) != 1024); + + degamma_lut = create_resized_lut(i915, crtc_state->hw.degamma_lut, 512); + if (IS_ERR(degamma_lut)) + return PTR_ERR(degamma_lut); + + gamma_lut = create_resized_lut(i915, crtc_state->hw.gamma_lut, 512); + if (IS_ERR(gamma_lut)) { + drm_property_blob_put(degamma_lut); + return PTR_ERR(gamma_lut); + } + + drm_property_replace_blob(&crtc_state->pre_csc_lut, degamma_lut); + drm_property_replace_blob(&crtc_state->post_csc_lut, gamma_lut); + + drm_property_blob_put(degamma_lut); + drm_property_blob_put(gamma_lut); + + return 0; +} + static int ivb_color_check(struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); - bool limited_color_range = ilk_csc_limited_range(crtc_state); + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); int ret; ret = check_luts(crtc_state); @@ -1534,19 +1623,21 @@ static int ivb_color_check(struct intel_crtc_state *crtc_state) if (crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB && crtc_state->hw.ctm) { - drm_dbg_kms(&dev_priv->drm, - "YCBCR and CTM together are not possible\n"); + drm_dbg_kms(&i915->drm, + "YCbCr and CTM together are not possible\n"); return -EINVAL; } - crtc_state->gamma_enable = - (crtc_state->hw.gamma_lut || - crtc_state->hw.degamma_lut) && - !crtc_state->c8_planes; + if (crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB && + crtc_state->hw.degamma_lut && crtc_state->hw.gamma_lut) { + drm_dbg_kms(&i915->drm, + "YCbCr and degamma+gamma together are not possible\n"); + return -EINVAL; + } - crtc_state->csc_enable = - crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB || - crtc_state->hw.ctm || limited_color_range; + crtc_state->gamma_enable = ilk_gamma_enable(crtc_state); + + crtc_state->csc_enable = ilk_csc_enable(crtc_state); crtc_state->gamma_mode = ivb_gamma_mode(crtc_state); @@ -1556,6 +1647,10 @@ static int ivb_color_check(struct intel_crtc_state *crtc_state) if (ret) return ret; + ret = ivb_assign_luts(crtc_state); + if (ret) + return ret; + crtc_state->preload_luts = intel_can_preload_luts(crtc_state); return 0; @@ -1570,9 +1665,26 @@ static u32 glk_gamma_mode(const struct intel_crtc_state *crtc_state) return GAMMA_MODE_MODE_10BIT; } +static void glk_assign_luts(struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); + + intel_assign_luts(crtc_state); + + /* + * On GLK+ both pipe CSC and degamma LUT are controlled + * by csc_enable. Hence for the cases where the CSC is + * needed but degamma LUT is not we need to load a + * linear degamma LUT. + */ + if (crtc_state->csc_enable && !crtc_state->pre_csc_lut) + drm_property_replace_blob(&crtc_state->pre_csc_lut, + i915->display.color.glk_linear_degamma_lut); +} + static int glk_color_check(struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); int ret; ret = check_luts(crtc_state); @@ -1581,8 +1693,15 @@ static int glk_color_check(struct intel_crtc_state *crtc_state) if (crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB && crtc_state->hw.ctm) { - drm_dbg_kms(&dev_priv->drm, - "YCBCR and CTM together are not possible\n"); + drm_dbg_kms(&i915->drm, + "YCbCr and CTM together are not possible\n"); + return -EINVAL; + } + + if (crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB && + crtc_state->hw.degamma_lut && crtc_state->hw.gamma_lut) { + drm_dbg_kms(&i915->drm, + "YCbCr and degamma+gamma together are not possible\n"); return -EINVAL; } @@ -1604,7 +1723,9 @@ static int glk_color_check(struct intel_crtc_state *crtc_state) if (ret) return ret; - crtc_state->preload_luts = glk_can_preload_luts(crtc_state); + glk_assign_luts(crtc_state); + + crtc_state->preload_luts = intel_can_preload_luts(crtc_state); return 0; } @@ -1664,6 +1785,8 @@ static int icl_color_check(struct intel_crtc_state *crtc_state) crtc_state->csc_mode = icl_csc_mode(crtc_state); + intel_assign_luts(crtc_state); + crtc_state->preload_luts = intel_can_preload_luts(crtc_state); return 0; @@ -1749,19 +1872,19 @@ static int icl_gamma_precision(const struct intel_crtc_state *crtc_state) int intel_color_get_gamma_bit_precision(const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); - if (HAS_GMCH(dev_priv)) { - if (IS_CHERRYVIEW(dev_priv)) + if (HAS_GMCH(i915)) { + if (IS_CHERRYVIEW(i915)) return chv_gamma_precision(crtc_state); else return i9xx_gamma_precision(crtc_state); } else { - if (DISPLAY_VER(dev_priv) >= 11) + if (DISPLAY_VER(i915) >= 11) return icl_gamma_precision(crtc_state); - else if (DISPLAY_VER(dev_priv) == 10) + else if (DISPLAY_VER(i915) == 10) return glk_gamma_precision(crtc_state); - else if (IS_IRONLAKE(dev_priv)) + else if (IS_IRONLAKE(i915)) return ilk_gamma_precision(crtc_state); } @@ -1846,7 +1969,7 @@ static struct drm_property_blob *i9xx_read_lut_8(struct intel_crtc *crtc) int i; blob = drm_property_create_blob(&dev_priv->drm, - sizeof(struct drm_color_lut) * LEGACY_LUT_LENGTH, + sizeof(lut[0]) * LEGACY_LUT_LENGTH, NULL); if (IS_ERR(blob)) return NULL; @@ -1869,7 +1992,7 @@ static void i9xx_read_luts(struct intel_crtc_state *crtc_state) if (!crtc_state->gamma_enable) return; - crtc_state->hw.gamma_lut = i9xx_read_lut_8(crtc); + crtc_state->post_csc_lut = i9xx_read_lut_8(crtc); } static struct drm_property_blob *i965_read_lut_10p6(struct intel_crtc *crtc) @@ -1881,7 +2004,7 @@ static struct drm_property_blob *i965_read_lut_10p6(struct intel_crtc *crtc) struct drm_color_lut *lut; blob = drm_property_create_blob(&dev_priv->drm, - sizeof(struct drm_color_lut) * lut_size, + sizeof(lut[0]) * lut_size, NULL); if (IS_ERR(blob)) return NULL; @@ -1910,21 +2033,21 @@ static void i965_read_luts(struct intel_crtc_state *crtc_state) return; if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT) - crtc_state->hw.gamma_lut = i9xx_read_lut_8(crtc); + crtc_state->post_csc_lut = i9xx_read_lut_8(crtc); else - crtc_state->hw.gamma_lut = i965_read_lut_10p6(crtc); + crtc_state->post_csc_lut = i965_read_lut_10p6(crtc); } static struct drm_property_blob *chv_read_cgm_gamma(struct intel_crtc *crtc) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - int i, lut_size = INTEL_INFO(dev_priv)->display.color.gamma_lut_size; + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + int i, lut_size = INTEL_INFO(i915)->display.color.gamma_lut_size; enum pipe pipe = crtc->pipe; struct drm_property_blob *blob; struct drm_color_lut *lut; - blob = drm_property_create_blob(&dev_priv->drm, - sizeof(struct drm_color_lut) * lut_size, + blob = drm_property_create_blob(&i915->drm, + sizeof(lut[0]) * lut_size, NULL); if (IS_ERR(blob)) return NULL; @@ -1932,8 +2055,8 @@ static struct drm_property_blob *chv_read_cgm_gamma(struct intel_crtc *crtc) lut = blob->data; for (i = 0; i < lut_size; i++) { - u32 ldw = intel_de_read_fw(dev_priv, CGM_PIPE_GAMMA(pipe, i, 0)); - u32 udw = intel_de_read_fw(dev_priv, CGM_PIPE_GAMMA(pipe, i, 1)); + u32 ldw = intel_de_read_fw(i915, CGM_PIPE_GAMMA(pipe, i, 0)); + u32 udw = intel_de_read_fw(i915, CGM_PIPE_GAMMA(pipe, i, 1)); chv_cgm_gamma_pack(&lut[i], ldw, udw); } @@ -1946,21 +2069,21 @@ static void chv_read_luts(struct intel_crtc_state *crtc_state) struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); if (crtc_state->cgm_mode & CGM_PIPE_MODE_GAMMA) - crtc_state->hw.gamma_lut = chv_read_cgm_gamma(crtc); + crtc_state->post_csc_lut = chv_read_cgm_gamma(crtc); else i965_read_luts(crtc_state); } static struct drm_property_blob *ilk_read_lut_8(struct intel_crtc *crtc) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); enum pipe pipe = crtc->pipe; struct drm_property_blob *blob; struct drm_color_lut *lut; int i; - blob = drm_property_create_blob(&dev_priv->drm, - sizeof(struct drm_color_lut) * LEGACY_LUT_LENGTH, + blob = drm_property_create_blob(&i915->drm, + sizeof(lut[0]) * LEGACY_LUT_LENGTH, NULL); if (IS_ERR(blob)) return NULL; @@ -1968,7 +2091,7 @@ static struct drm_property_blob *ilk_read_lut_8(struct intel_crtc *crtc) lut = blob->data; for (i = 0; i < LEGACY_LUT_LENGTH; i++) { - u32 val = intel_de_read_fw(dev_priv, LGC_PALETTE(pipe, i)); + u32 val = intel_de_read_fw(i915, LGC_PALETTE(pipe, i)); i9xx_lut_8_pack(&lut[i], val); } @@ -1978,14 +2101,14 @@ static struct drm_property_blob *ilk_read_lut_8(struct intel_crtc *crtc) static struct drm_property_blob *ilk_read_lut_10(struct intel_crtc *crtc) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - int i, lut_size = INTEL_INFO(dev_priv)->display.color.gamma_lut_size; + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + int i, lut_size = INTEL_INFO(i915)->display.color.gamma_lut_size; enum pipe pipe = crtc->pipe; struct drm_property_blob *blob; struct drm_color_lut *lut; - blob = drm_property_create_blob(&dev_priv->drm, - sizeof(struct drm_color_lut) * lut_size, + blob = drm_property_create_blob(&i915->drm, + sizeof(lut[0]) * lut_size, NULL); if (IS_ERR(blob)) return NULL; @@ -1993,7 +2116,7 @@ static struct drm_property_blob *ilk_read_lut_10(struct intel_crtc *crtc) lut = blob->data; for (i = 0; i < lut_size; i++) { - u32 val = intel_de_read_fw(dev_priv, PREC_PALETTE(pipe, i)); + u32 val = intel_de_read_fw(i915, PREC_PALETTE(pipe, i)); ilk_lut_10_pack(&lut[i], val); } @@ -2013,10 +2136,10 @@ static void ilk_read_luts(struct intel_crtc_state *crtc_state) switch (crtc_state->gamma_mode) { case GAMMA_MODE_MODE_8BIT: - crtc_state->hw.gamma_lut = ilk_read_lut_8(crtc); + crtc_state->post_csc_lut = ilk_read_lut_8(crtc); break; case GAMMA_MODE_MODE_10BIT: - crtc_state->hw.gamma_lut = ilk_read_lut_10(crtc); + crtc_state->post_csc_lut = ilk_read_lut_10(crtc); break; default: MISSING_CASE(crtc_state->gamma_mode); @@ -2028,33 +2151,33 @@ static void ilk_read_luts(struct intel_crtc_state *crtc_state) static struct drm_property_blob *bdw_read_lut_10(struct intel_crtc *crtc, u32 prec_index) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); int i, hw_lut_size = ivb_lut_10_size(prec_index); - int lut_size = INTEL_INFO(dev_priv)->display.color.gamma_lut_size; + int lut_size = INTEL_INFO(i915)->display.color.gamma_lut_size; enum pipe pipe = crtc->pipe; struct drm_property_blob *blob; struct drm_color_lut *lut; - drm_WARN_ON(&dev_priv->drm, lut_size != hw_lut_size); + drm_WARN_ON(&i915->drm, lut_size != hw_lut_size); - blob = drm_property_create_blob(&dev_priv->drm, - sizeof(struct drm_color_lut) * lut_size, + blob = drm_property_create_blob(&i915->drm, + sizeof(lut[0]) * lut_size, NULL); if (IS_ERR(blob)) return NULL; lut = blob->data; - intel_de_write_fw(dev_priv, PREC_PAL_INDEX(pipe), + intel_de_write_fw(i915, PREC_PAL_INDEX(pipe), prec_index | PAL_PREC_AUTO_INCREMENT); for (i = 0; i < lut_size; i++) { - u32 val = intel_de_read_fw(dev_priv, PREC_PAL_DATA(pipe)); + u32 val = intel_de_read_fw(i915, PREC_PAL_DATA(pipe)); ilk_lut_10_pack(&lut[i], val); } - intel_de_write_fw(dev_priv, PREC_PAL_INDEX(pipe), 0); + intel_de_write_fw(i915, PREC_PAL_INDEX(pipe), 0); return blob; } @@ -2068,10 +2191,10 @@ static void glk_read_luts(struct intel_crtc_state *crtc_state) switch (crtc_state->gamma_mode) { case GAMMA_MODE_MODE_8BIT: - crtc_state->hw.gamma_lut = ilk_read_lut_8(crtc); + crtc_state->post_csc_lut = ilk_read_lut_8(crtc); break; case GAMMA_MODE_MODE_10BIT: - crtc_state->hw.gamma_lut = bdw_read_lut_10(crtc, PAL_PREC_INDEX_VALUE(0)); + crtc_state->post_csc_lut = bdw_read_lut_10(crtc, PAL_PREC_INDEX_VALUE(0)); break; default: MISSING_CASE(crtc_state->gamma_mode); @@ -2082,31 +2205,31 @@ static void glk_read_luts(struct intel_crtc_state *crtc_state) static struct drm_property_blob * icl_read_lut_multi_segment(struct intel_crtc *crtc) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - int i, lut_size = INTEL_INFO(dev_priv)->display.color.gamma_lut_size; + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + int i, lut_size = INTEL_INFO(i915)->display.color.gamma_lut_size; enum pipe pipe = crtc->pipe; struct drm_property_blob *blob; struct drm_color_lut *lut; - blob = drm_property_create_blob(&dev_priv->drm, - sizeof(struct drm_color_lut) * lut_size, + blob = drm_property_create_blob(&i915->drm, + sizeof(lut[0]) * lut_size, NULL); if (IS_ERR(blob)) return NULL; lut = blob->data; - intel_de_write_fw(dev_priv, PREC_PAL_MULTI_SEG_INDEX(pipe), + intel_de_write_fw(i915, PREC_PAL_MULTI_SEG_INDEX(pipe), PAL_PREC_AUTO_INCREMENT); for (i = 0; i < 9; i++) { - u32 ldw = intel_de_read_fw(dev_priv, PREC_PAL_MULTI_SEG_DATA(pipe)); - u32 udw = intel_de_read_fw(dev_priv, PREC_PAL_MULTI_SEG_DATA(pipe)); + u32 ldw = intel_de_read_fw(i915, PREC_PAL_MULTI_SEG_DATA(pipe)); + u32 udw = intel_de_read_fw(i915, PREC_PAL_MULTI_SEG_DATA(pipe)); - icl_lut_multi_seg_pack(&lut[i], ldw, udw); + ilk_lut_12p4_pack(&lut[i], ldw, udw); } - intel_de_write_fw(dev_priv, PREC_PAL_MULTI_SEG_INDEX(pipe), 0); + intel_de_write_fw(i915, PREC_PAL_MULTI_SEG_INDEX(pipe), 0); /* * FIXME readouts from PAL_PREC_DATA register aren't giving @@ -2126,13 +2249,13 @@ static void icl_read_luts(struct intel_crtc_state *crtc_state) switch (crtc_state->gamma_mode & GAMMA_MODE_MODE_MASK) { case GAMMA_MODE_MODE_8BIT: - crtc_state->hw.gamma_lut = ilk_read_lut_8(crtc); + crtc_state->post_csc_lut = ilk_read_lut_8(crtc); break; case GAMMA_MODE_MODE_10BIT: - crtc_state->hw.gamma_lut = bdw_read_lut_10(crtc, PAL_PREC_INDEX_VALUE(0)); + crtc_state->post_csc_lut = bdw_read_lut_10(crtc, PAL_PREC_INDEX_VALUE(0)); break; case GAMMA_MODE_MODE_12BIT_MULTI_SEGMENTED: - crtc_state->hw.gamma_lut = icl_read_lut_multi_segment(crtc); + crtc_state->post_csc_lut = icl_read_lut_multi_segment(crtc); break; default: MISSING_CASE(crtc_state->gamma_mode); @@ -2217,41 +2340,58 @@ static const struct intel_color_funcs ilk_color_funcs = { .read_luts = ilk_read_luts, }; -void intel_color_init(struct intel_crtc *crtc) +void intel_color_crtc_init(struct intel_crtc *crtc) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - bool has_ctm = INTEL_INFO(dev_priv)->display.color.degamma_lut_size != 0; + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + bool has_ctm = INTEL_INFO(i915)->display.color.degamma_lut_size != 0; drm_mode_crtc_set_gamma_size(&crtc->base, 256); - if (HAS_GMCH(dev_priv)) { - if (IS_CHERRYVIEW(dev_priv)) { - dev_priv->display.funcs.color = &chv_color_funcs; - } else if (DISPLAY_VER(dev_priv) >= 4) { - dev_priv->display.funcs.color = &i965_color_funcs; - } else { - dev_priv->display.funcs.color = &i9xx_color_funcs; - } - } else { - if (DISPLAY_VER(dev_priv) >= 11) - dev_priv->display.funcs.color = &icl_color_funcs; - else if (DISPLAY_VER(dev_priv) == 10) - dev_priv->display.funcs.color = &glk_color_funcs; - else if (DISPLAY_VER(dev_priv) == 9) - dev_priv->display.funcs.color = &skl_color_funcs; - else if (DISPLAY_VER(dev_priv) == 8) - dev_priv->display.funcs.color = &bdw_color_funcs; - else if (DISPLAY_VER(dev_priv) == 7) { - if (IS_HASWELL(dev_priv)) - dev_priv->display.funcs.color = &hsw_color_funcs; - else - dev_priv->display.funcs.color = &ivb_color_funcs; - } else - dev_priv->display.funcs.color = &ilk_color_funcs; - } - drm_crtc_enable_color_mgmt(&crtc->base, - INTEL_INFO(dev_priv)->display.color.degamma_lut_size, + INTEL_INFO(i915)->display.color.degamma_lut_size, has_ctm, - INTEL_INFO(dev_priv)->display.color.gamma_lut_size); + INTEL_INFO(i915)->display.color.gamma_lut_size); +} + +int intel_color_init(struct drm_i915_private *i915) +{ + struct drm_property_blob *blob; + + if (DISPLAY_VER(i915) != 10) + return 0; + + blob = create_linear_lut(i915, INTEL_INFO(i915)->display.color.degamma_lut_size); + if (IS_ERR(blob)) + return PTR_ERR(blob); + + i915->display.color.glk_linear_degamma_lut = blob; + + return 0; +} + +void intel_color_init_hooks(struct drm_i915_private *i915) +{ + if (HAS_GMCH(i915)) { + if (IS_CHERRYVIEW(i915)) + i915->display.funcs.color = &chv_color_funcs; + else if (DISPLAY_VER(i915) >= 4) + i915->display.funcs.color = &i965_color_funcs; + else + i915->display.funcs.color = &i9xx_color_funcs; + } else { + if (DISPLAY_VER(i915) >= 11) + i915->display.funcs.color = &icl_color_funcs; + else if (DISPLAY_VER(i915) == 10) + i915->display.funcs.color = &glk_color_funcs; + else if (DISPLAY_VER(i915) == 9) + i915->display.funcs.color = &skl_color_funcs; + else if (DISPLAY_VER(i915) == 8) + i915->display.funcs.color = &bdw_color_funcs; + else if (IS_HASWELL(i915)) + i915->display.funcs.color = &hsw_color_funcs; + else if (DISPLAY_VER(i915) == 7) + i915->display.funcs.color = &ivb_color_funcs; + else + i915->display.funcs.color = &ilk_color_funcs; + } } diff --git a/drivers/gpu/drm/i915/display/intel_color.h b/drivers/gpu/drm/i915/display/intel_color.h index fd873425e082..2a5ada67774d 100644 --- a/drivers/gpu/drm/i915/display/intel_color.h +++ b/drivers/gpu/drm/i915/display/intel_color.h @@ -10,9 +10,12 @@ struct intel_crtc_state; struct intel_crtc; +struct drm_i915_private; struct drm_property_blob; -void intel_color_init(struct intel_crtc *crtc); +void intel_color_init_hooks(struct drm_i915_private *i915); +int intel_color_init(struct drm_i915_private *i915); +void intel_color_crtc_init(struct intel_crtc *crtc); int intel_color_check(struct intel_crtc_state *crtc_state); void intel_color_commit_noarm(const struct intel_crtc_state *crtc_state); void intel_color_commit_arm(const struct intel_crtc_state *crtc_state); @@ -22,5 +25,6 @@ int intel_color_get_gamma_bit_precision(const struct intel_crtc_state *crtc_stat bool intel_color_lut_equal(struct drm_property_blob *blob1, struct drm_property_blob *blob2, u32 gamma_mode, u32 bit_precision); +void intel_color_assert_luts(const struct intel_crtc_state *crtc_state); #endif /* __INTEL_COLOR_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_combo_phy.c b/drivers/gpu/drm/i915/display/intel_combo_phy.c index 64890f39c3cc..8b870b2dd4f9 100644 --- a/drivers/gpu/drm/i915/display/intel_combo_phy.c +++ b/drivers/gpu/drm/i915/display/intel_combo_phy.c @@ -3,6 +3,7 @@ * Copyright © 2018 Intel Corporation */ +#include "i915_reg.h" #include "intel_combo_phy.h" #include "intel_combo_phy_regs.h" #include "intel_de.h" @@ -53,7 +54,6 @@ static const struct icl_procmon { static const struct icl_procmon * icl_get_procmon_ref_values(struct drm_i915_private *dev_priv, enum phy phy) { - const struct icl_procmon *procmon; u32 val; val = intel_de_read(dev_priv, ICL_PORT_COMP_DW3(phy)); @@ -62,23 +62,16 @@ icl_get_procmon_ref_values(struct drm_i915_private *dev_priv, enum phy phy) MISSING_CASE(val); fallthrough; case VOLTAGE_INFO_0_85V | PROCESS_INFO_DOT_0: - procmon = &icl_procmon_values[PROCMON_0_85V_DOT_0]; - break; + return &icl_procmon_values[PROCMON_0_85V_DOT_0]; case VOLTAGE_INFO_0_95V | PROCESS_INFO_DOT_0: - procmon = &icl_procmon_values[PROCMON_0_95V_DOT_0]; - break; + return &icl_procmon_values[PROCMON_0_95V_DOT_0]; case VOLTAGE_INFO_0_95V | PROCESS_INFO_DOT_1: - procmon = &icl_procmon_values[PROCMON_0_95V_DOT_1]; - break; + return &icl_procmon_values[PROCMON_0_95V_DOT_1]; case VOLTAGE_INFO_1_05V | PROCESS_INFO_DOT_0: - procmon = &icl_procmon_values[PROCMON_1_05V_DOT_0]; - break; + return &icl_procmon_values[PROCMON_1_05V_DOT_0]; case VOLTAGE_INFO_1_05V | PROCESS_INFO_DOT_1: - procmon = &icl_procmon_values[PROCMON_1_05V_DOT_1]; - break; + return &icl_procmon_values[PROCMON_1_05V_DOT_1]; } - - return procmon; } static void icl_set_procmon_ref_values(struct drm_i915_private *dev_priv, diff --git a/drivers/gpu/drm/i915/display/intel_connector.c b/drivers/gpu/drm/i915/display/intel_connector.c index 6d5cbeb8df4d..6205ddd3ded0 100644 --- a/drivers/gpu/drm/i915/display/intel_connector.c +++ b/drivers/gpu/drm/i915/display/intel_connector.c @@ -293,3 +293,21 @@ intel_attach_dp_colorspace_property(struct drm_connector *connector) if (!drm_mode_create_dp_colorspace_property(connector)) drm_connector_attach_colorspace_property(connector); } + +void +intel_attach_scaling_mode_property(struct drm_connector *connector) +{ + struct drm_i915_private *i915 = to_i915(connector->dev); + u32 scaling_modes; + + scaling_modes = BIT(DRM_MODE_SCALE_ASPECT) | + BIT(DRM_MODE_SCALE_FULLSCREEN); + + /* On GMCH platforms borders are only possible on the LVDS port */ + if (!HAS_GMCH(i915) || connector->connector_type == DRM_MODE_CONNECTOR_LVDS) + scaling_modes |= BIT(DRM_MODE_SCALE_CENTER); + + drm_connector_attach_scaling_mode_property(connector, scaling_modes); + + connector->state->scaling_mode = DRM_MODE_SCALE_ASPECT; +} diff --git a/drivers/gpu/drm/i915/display/intel_connector.h b/drivers/gpu/drm/i915/display/intel_connector.h index 661a37a3c6d8..9d2bc261b204 100644 --- a/drivers/gpu/drm/i915/display/intel_connector.h +++ b/drivers/gpu/drm/i915/display/intel_connector.h @@ -6,7 +6,7 @@ #ifndef __INTEL_CONNECTOR_H__ #define __INTEL_CONNECTOR_H__ -#include "intel_display.h" +#include <linux/types.h> struct drm_connector; struct edid; @@ -32,5 +32,6 @@ void intel_attach_broadcast_rgb_property(struct drm_connector *connector); void intel_attach_aspect_ratio_property(struct drm_connector *connector); void intel_attach_hdmi_colorspace_property(struct drm_connector *connector); void intel_attach_dp_colorspace_property(struct drm_connector *connector); +void intel_attach_scaling_mode_property(struct drm_connector *connector); #endif /* __INTEL_CONNECTOR_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c index 4a8ff2f97608..797ad9489f7e 100644 --- a/drivers/gpu/drm/i915/display/intel_crt.c +++ b/drivers/gpu/drm/i915/display/intel_crt.c @@ -34,6 +34,8 @@ #include <drm/drm_probe_helper.h> #include "i915_drv.h" +#include "i915_irq.h" +#include "i915_reg.h" #include "intel_connector.h" #include "intel_crt.h" #include "intel_crtc.h" @@ -1044,17 +1046,14 @@ void intel_crt_init(struct drm_i915_private *dev_priv) intel_connector_attach_encoder(intel_connector, &crt->base); crt->base.type = INTEL_OUTPUT_ANALOG; - crt->base.cloneable = (1 << INTEL_OUTPUT_DVO) | (1 << INTEL_OUTPUT_HDMI); + crt->base.cloneable = BIT(INTEL_OUTPUT_DVO) | BIT(INTEL_OUTPUT_HDMI); if (IS_I830(dev_priv)) crt->base.pipe_mask = BIT(PIPE_A); else crt->base.pipe_mask = ~0; - if (DISPLAY_VER(dev_priv) == 2) - connector->interlace_allowed = 0; - else - connector->interlace_allowed = 1; - connector->doublescan_allowed = 0; + if (DISPLAY_VER(dev_priv) != 2) + connector->interlace_allowed = true; crt->adpa_reg = adpa_reg; diff --git a/drivers/gpu/drm/i915/display/intel_crtc.c b/drivers/gpu/drm/i915/display/intel_crtc.c index 6792a9056f46..037fc140b585 100644 --- a/drivers/gpu/drm/i915/display/intel_crtc.c +++ b/drivers/gpu/drm/i915/display/intel_crtc.c @@ -365,9 +365,8 @@ int intel_crtc_init(struct drm_i915_private *dev_priv, enum pipe pipe) BIT(DRM_SCALING_FILTER_DEFAULT) | BIT(DRM_SCALING_FILTER_NEAREST_NEIGHBOR)); - intel_color_init(crtc); - - intel_crtc_drrs_init(crtc); + intel_color_crtc_init(crtc); + intel_drrs_crtc_init(crtc); intel_crtc_crc_init(crtc); cpu_latency_qos_add_request(&crtc->vblank_pm_qos, PM_QOS_DEFAULT_VALUE); @@ -387,8 +386,7 @@ static bool intel_crtc_needs_vblank_work(const struct intel_crtc_state *crtc_sta return crtc_state->hw.active && !intel_crtc_needs_modeset(crtc_state) && !crtc_state->preload_luts && - (crtc_state->uapi.color_mgmt_changed || - crtc_state->update_pipe); + intel_crtc_needs_color_update(crtc_state); } static void intel_crtc_vblank_work(struct kthread_work *base) diff --git a/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c b/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c index e9212f69c360..e3273fe8ddac 100644 --- a/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c +++ b/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c @@ -298,11 +298,13 @@ void intel_crtc_state_dump(const struct intel_crtc_state *pipe_config, pipe_config->csc_mode, pipe_config->gamma_mode, pipe_config->gamma_enable, pipe_config->csc_enable); - drm_dbg_kms(&i915->drm, "degamma lut: %d entries, gamma lut: %d entries\n", - pipe_config->hw.degamma_lut ? - drm_color_lut_size(pipe_config->hw.degamma_lut) : 0, - pipe_config->hw.gamma_lut ? - drm_color_lut_size(pipe_config->hw.gamma_lut) : 0); + drm_dbg_kms(&i915->drm, "pre csc lut: %s%d entries, post csc lut: %d entries\n", + pipe_config->pre_csc_lut && pipe_config->pre_csc_lut == + i915->display.color.glk_linear_degamma_lut ? "(linear) " : "", + pipe_config->pre_csc_lut ? + drm_color_lut_size(pipe_config->pre_csc_lut) : 0, + pipe_config->post_csc_lut ? + drm_color_lut_size(pipe_config->post_csc_lut) : 0); dump_planes: if (!state) diff --git a/drivers/gpu/drm/i915/display/intel_cursor.c b/drivers/gpu/drm/i915/display/intel_cursor.c index 87899e89b3a7..d190fa0d393b 100644 --- a/drivers/gpu/drm/i915/display/intel_cursor.c +++ b/drivers/gpu/drm/i915/display/intel_cursor.c @@ -10,12 +10,13 @@ #include <drm/drm_damage_helper.h> #include <drm/drm_fourcc.h> +#include "i915_reg.h" #include "intel_atomic.h" #include "intel_atomic_plane.h" #include "intel_cursor.h" #include "intel_de.h" -#include "intel_display_types.h" #include "intel_display.h" +#include "intel_display_types.h" #include "intel_fb.h" #include "intel_fb_pin.h" #include "intel_frontbuffer.h" @@ -631,8 +632,10 @@ intel_legacy_cursor_update(struct drm_plane *_plane, * * FIXME bigjoiner fastpath would be good */ - if (!crtc_state->hw.active || intel_crtc_needs_modeset(crtc_state) || - crtc_state->update_pipe || crtc_state->bigjoiner_pipes) + if (!crtc_state->hw.active || + intel_crtc_needs_modeset(crtc_state) || + intel_crtc_needs_fastset(crtc_state) || + crtc_state->bigjoiner_pipes) goto slow; /* diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 69ecf2a3d6c6..0f1ec2a98cc8 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -31,6 +31,7 @@ #include <drm/drm_privacy_screen_consumer.h> #include "i915_drv.h" +#include "i915_reg.h" #include "intel_audio.h" #include "intel_audio_regs.h" #include "intel_backlight.h" @@ -44,6 +45,7 @@ #include "intel_display_power.h" #include "intel_display_types.h" #include "intel_dkl_phy.h" +#include "intel_dkl_phy_regs.h" #include "intel_dp.h" #include "intel_dp_link_training.h" #include "intel_dp_mst.h" @@ -55,14 +57,15 @@ #include "intel_hdcp.h" #include "intel_hdmi.h" #include "intel_hotplug.h" +#include "intel_hti.h" #include "intel_lspcon.h" +#include "intel_mg_phy_regs.h" #include "intel_pps.h" #include "intel_psr.h" #include "intel_quirks.h" #include "intel_snps_phy.h" #include "intel_sprite.h" #include "intel_tc.h" -#include "intel_tc_phy_regs.h" #include "intel_vdsc.h" #include "intel_vrr.h" #include "skl_scaler.h" @@ -845,22 +848,65 @@ bool intel_ddi_get_hw_state(struct intel_encoder *encoder, } static enum intel_display_power_domain -intel_ddi_main_link_aux_domain(struct intel_digital_port *dig_port) +intel_ddi_main_link_aux_domain(struct intel_digital_port *dig_port, + const struct intel_crtc_state *crtc_state) { - /* ICL+ HW requires corresponding AUX IOs to be powered up for PSR with + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + enum phy phy = intel_port_to_phy(i915, dig_port->base.port); + + /* + * ICL+ HW requires corresponding AUX IOs to be powered up for PSR with * DC states enabled at the same time, while for driver initiated AUX * transfers we need the same AUX IOs to be powered but with DC states - * disabled. Accordingly use the AUX power domain here which leaves DC - * states enabled. - * However, for non-A AUX ports the corresponding non-EDP transcoders - * would have already enabled power well 2 and DC_OFF. This means we can - * acquire a wider POWER_DOMAIN_AUX_{B,C,D,F} reference instead of a - * specific AUX_IO reference without powering up any extra wells. - * Note that PSR is enabled only on Port A even though this function - * returns the correct domain for other ports too. + * disabled. Accordingly use the AUX_IO_<port> power domain here which + * leaves DC states enabled. + * + * Before MTL TypeC PHYs (in all TypeC modes and both DP/HDMI) also require + * AUX IO to be enabled, but all these require DC_OFF to be enabled as + * well, so we can acquire a wider AUX_<port> power domain reference + * instead of a specific AUX_IO_<port> reference without powering up any + * extra wells. */ - return dig_port->aux_ch == AUX_CH_A ? POWER_DOMAIN_AUX_IO_A : - intel_aux_power_domain(dig_port); + if (intel_encoder_can_psr(&dig_port->base)) + return intel_display_power_aux_io_domain(i915, dig_port->aux_ch); + else if (DISPLAY_VER(i915) < 14 && + (intel_crtc_has_dp_encoder(crtc_state) || + intel_phy_is_tc(i915, phy))) + return intel_aux_power_domain(dig_port); + else + return POWER_DOMAIN_INVALID; +} + +static void +main_link_aux_power_domain_get(struct intel_digital_port *dig_port, + const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + enum intel_display_power_domain domain = + intel_ddi_main_link_aux_domain(dig_port, crtc_state); + + drm_WARN_ON(&i915->drm, dig_port->aux_wakeref); + + if (domain == POWER_DOMAIN_INVALID) + return; + + dig_port->aux_wakeref = intel_display_power_get(i915, domain); +} + +static void +main_link_aux_power_domain_put(struct intel_digital_port *dig_port, + const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + enum intel_display_power_domain domain = + intel_ddi_main_link_aux_domain(dig_port, crtc_state); + intel_wakeref_t wf; + + wf = fetch_and_zero(&dig_port->aux_wakeref); + if (!wf) + return; + + intel_display_power_put(i915, domain, wf); } static void intel_ddi_get_power_domains(struct intel_encoder *encoder, @@ -868,7 +914,6 @@ static void intel_ddi_get_power_domains(struct intel_encoder *encoder, { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_digital_port *dig_port; - enum phy phy = intel_port_to_phy(dev_priv, encoder->port); /* * TODO: Add support for MST encoders. Atm, the following should never @@ -887,17 +932,7 @@ static void intel_ddi_get_power_domains(struct intel_encoder *encoder, dig_port->ddi_io_power_domain); } - /* - * AUX power is only needed for (e)DP mode, and for HDMI mode on TC - * ports. - */ - if (intel_crtc_has_dp_encoder(crtc_state) || - intel_phy_is_tc(dev_priv, phy)) { - drm_WARN_ON(&dev_priv->drm, dig_port->aux_wakeref); - dig_port->aux_wakeref = - intel_display_power_get(dev_priv, - intel_ddi_main_link_aux_domain(dig_port)); - } + main_link_aux_power_domain_get(dig_port, crtc_state); } void intel_ddi_enable_pipe_clock(struct intel_encoder *encoder, @@ -1263,11 +1298,11 @@ static void tgl_dkl_phy_set_signal_levels(struct intel_encoder *encoder, for (ln = 0; ln < 2; ln++) { int level; - intel_dkl_phy_write(dev_priv, DKL_TX_PMD_LANE_SUS(tc_port), ln, 0); + intel_dkl_phy_write(dev_priv, DKL_TX_PMD_LANE_SUS(tc_port, ln), 0); level = intel_ddi_level(encoder, crtc_state, 2*ln+0); - intel_dkl_phy_rmw(dev_priv, DKL_TX_DPCNTL0(tc_port), ln, + intel_dkl_phy_rmw(dev_priv, DKL_TX_DPCNTL0(tc_port, ln), DKL_TX_PRESHOOT_COEFF_MASK | DKL_TX_DE_EMPAHSIS_COEFF_MASK | DKL_TX_VSWING_CONTROL_MASK, @@ -1277,7 +1312,7 @@ static void tgl_dkl_phy_set_signal_levels(struct intel_encoder *encoder, level = intel_ddi_level(encoder, crtc_state, 2*ln+1); - intel_dkl_phy_rmw(dev_priv, DKL_TX_DPCNTL1(tc_port), ln, + intel_dkl_phy_rmw(dev_priv, DKL_TX_DPCNTL1(tc_port, ln), DKL_TX_PRESHOOT_COEFF_MASK | DKL_TX_DE_EMPAHSIS_COEFF_MASK | DKL_TX_VSWING_CONTROL_MASK, @@ -1285,7 +1320,7 @@ static void tgl_dkl_phy_set_signal_levels(struct intel_encoder *encoder, DKL_TX_DE_EMPHASIS_COEFF(trans->entries[level].dkl.de_emphasis) | DKL_TX_VSWING_CONTROL(trans->entries[level].dkl.vswing)); - intel_dkl_phy_rmw(dev_priv, DKL_TX_DPCNTL2(tc_port), ln, + intel_dkl_phy_rmw(dev_priv, DKL_TX_DPCNTL2(tc_port, ln), DKL_TX_DP20BITMODE, 0); if (IS_ALDERLAKE_P(dev_priv)) { @@ -1304,7 +1339,7 @@ static void tgl_dkl_phy_set_signal_levels(struct intel_encoder *encoder, val |= DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2(0); } - intel_dkl_phy_rmw(dev_priv, DKL_TX_DPCNTL2(tc_port), ln, + intel_dkl_phy_rmw(dev_priv, DKL_TX_DPCNTL2(tc_port, ln), DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1_MASK | DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2_MASK, val); @@ -2017,8 +2052,8 @@ icl_program_mg_dp_mode(struct intel_digital_port *dig_port, return; if (DISPLAY_VER(dev_priv) >= 12) { - ln0 = intel_dkl_phy_read(dev_priv, DKL_DP_MODE(tc_port), 0); - ln1 = intel_dkl_phy_read(dev_priv, DKL_DP_MODE(tc_port), 1); + ln0 = intel_dkl_phy_read(dev_priv, DKL_DP_MODE(tc_port, 0)); + ln1 = intel_dkl_phy_read(dev_priv, DKL_DP_MODE(tc_port, 1)); } else { ln0 = intel_de_read(dev_priv, MG_DP_MODE(0, tc_port)); ln1 = intel_de_read(dev_priv, MG_DP_MODE(1, tc_port)); @@ -2079,8 +2114,8 @@ icl_program_mg_dp_mode(struct intel_digital_port *dig_port, } if (DISPLAY_VER(dev_priv) >= 12) { - intel_dkl_phy_write(dev_priv, DKL_DP_MODE(tc_port), 0, ln0); - intel_dkl_phy_write(dev_priv, DKL_DP_MODE(tc_port), 1, ln1); + intel_dkl_phy_write(dev_priv, DKL_DP_MODE(tc_port, 0), ln0); + intel_dkl_phy_write(dev_priv, DKL_DP_MODE(tc_port, 1), ln1); } else { intel_de_write(dev_priv, MG_DP_MODE(0, tc_port), ln0); intel_de_write(dev_priv, MG_DP_MODE(1, tc_port), ln1); @@ -2736,10 +2771,7 @@ static void intel_ddi_post_disable(struct intel_atomic_state *state, intel_ddi_post_disable_dp(state, encoder, old_crtc_state, old_conn_state); - if (intel_crtc_has_dp_encoder(old_crtc_state) || is_tc_port) - intel_display_power_put(dev_priv, - intel_ddi_main_link_aux_domain(dig_port), - fetch_and_zero(&dig_port->aux_wakeref)); + main_link_aux_power_domain_put(dig_port, old_crtc_state); if (is_tc_port) intel_tc_port_put_link(dig_port); @@ -3060,12 +3092,7 @@ intel_ddi_pre_pll_enable(struct intel_atomic_state *state, if (is_tc_port) intel_tc_port_get_link(dig_port, crtc_state->lane_count); - if (intel_crtc_has_dp_encoder(crtc_state) || is_tc_port) { - drm_WARN_ON(&dev_priv->drm, dig_port->aux_wakeref); - dig_port->aux_wakeref = - intel_display_power_get(dev_priv, - intel_ddi_main_link_aux_domain(dig_port)); - } + main_link_aux_power_domain_get(dig_port, crtc_state); if (is_tc_port && !intel_tc_port_in_tbt_alt_mode(dig_port)) /* @@ -3085,7 +3112,7 @@ static void adlp_tbt_to_dp_alt_switch_wa(struct intel_encoder *encoder) int ln; for (ln = 0; ln < 2; ln++) - intel_dkl_phy_rmw(i915, DKL_PCS_DW5(tc_port), ln, DKL_PCS_DW5_CORE_SOFTRESET, 0); + intel_dkl_phy_rmw(i915, DKL_PCS_DW5(tc_port, ln), DKL_PCS_DW5_CORE_SOFTRESET, 0); } static void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp, @@ -3524,7 +3551,7 @@ static void icl_ddi_tc_get_clock(struct intel_encoder *encoder, if (drm_WARN_ON(&i915->drm, !pll)) return; - if (intel_get_shared_dpll_id(i915, pll) == DPLL_ID_ICL_TBTPLL) + if (pll->info->id == DPLL_ID_ICL_TBTPLL) port_dpll_id = ICL_PORT_DPLL_DEFAULT; else port_dpll_id = ICL_PORT_DPLL_MG_PHY; @@ -3537,7 +3564,7 @@ static void icl_ddi_tc_get_clock(struct intel_encoder *encoder, icl_set_active_port_dpll(crtc_state, port_dpll_id); - if (intel_get_shared_dpll_id(i915, crtc_state->shared_dpll) == DPLL_ID_ICL_TBTPLL) + if (crtc_state->shared_dpll->info->id == DPLL_ID_ICL_TBTPLL) crtc_state->port_clock = icl_calc_tbt_pll_link(i915, encoder->port); else crtc_state->port_clock = intel_dpll_get_freq(i915, crtc_state->shared_dpll, @@ -3579,7 +3606,7 @@ static void intel_ddi_sync_state(struct intel_encoder *encoder, enum phy phy = intel_port_to_phy(i915, encoder->port); if (intel_phy_is_tc(i915, phy)) - intel_tc_port_sanitize(enc_to_dig_port(encoder)); + intel_tc_port_sanitize_mode(enc_to_dig_port(encoder)); if (crtc_state && intel_crtc_has_dp_encoder(crtc_state)) intel_dp_sync_state(encoder, crtc_state); @@ -3789,11 +3816,17 @@ static void intel_ddi_encoder_destroy(struct drm_encoder *encoder) static void intel_ddi_encoder_reset(struct drm_encoder *encoder) { + struct drm_i915_private *i915 = to_i915(encoder->dev); struct intel_dp *intel_dp = enc_to_intel_dp(to_intel_encoder(encoder)); + struct intel_digital_port *dig_port = enc_to_dig_port(to_intel_encoder(encoder)); + enum phy phy = intel_port_to_phy(i915, dig_port->base.port); intel_dp->reset_link_params = true; intel_pps_encoder_reset(intel_dp); + + if (intel_phy_is_tc(i915, phy)) + intel_tc_port_init_mode(dig_port); } static const struct drm_encoder_funcs intel_ddi_funcs = { @@ -4106,12 +4139,6 @@ intel_ddi_max_lanes(struct intel_digital_port *dig_port) return max_lanes; } -static bool hti_uses_phy(struct drm_i915_private *i915, enum phy phy) -{ - return i915->hti_state & HDPORT_ENABLED && - i915->hti_state & HDPORT_DDI_USED(phy); -} - static enum hpd_pin xelpd_hpd_pin(struct drm_i915_private *dev_priv, enum port port) { @@ -4240,7 +4267,7 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port) * driver. In that case we should skip initializing the corresponding * outputs. */ - if (hti_uses_phy(dev_priv, phy)) { + if (intel_hti_uses_phy(dev_priv, phy)) { drm_dbg_kms(&dev_priv->drm, "PORT %c / PHY %c reserved by HTI\n", port_name(port), phy_name(phy)); return; diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index de77054195c6..6c2686ecb62a 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -76,6 +76,7 @@ #include "g4x_hdmi.h" #include "hsw_ips.h" #include "i915_drv.h" +#include "i915_reg.h" #include "i915_utils.h" #include "icl_dsi.h" #include "intel_acpi.h" @@ -90,6 +91,7 @@ #include "intel_display_types.h" #include "intel_dmc.h" #include "intel_dp_link_training.h" +#include "intel_dpio_phy.h" #include "intel_dpt.h" #include "intel_dsb.h" #include "intel_fbc.h" @@ -99,6 +101,7 @@ #include "intel_frontbuffer.h" #include "intel_hdcp.h" #include "intel_hotplug.h" +#include "intel_hti.h" #include "intel_modeset_verify.h" #include "intel_modeset_setup.h" #include "intel_overlay.h" @@ -831,13 +834,27 @@ intel_plane_fence_y_offset(const struct intel_plane_state *plane_state) } static int +intel_display_commit_duplicated_state(struct intel_atomic_state *state, + struct drm_modeset_acquire_ctx *ctx) +{ + struct drm_i915_private *i915 = to_i915(state->base.dev); + int ret; + + ret = drm_atomic_helper_commit_duplicated_state(&state->base, ctx); + + drm_WARN_ON(&i915->drm, ret == -EDEADLK); + + return ret; +} + +static int __intel_display_resume(struct drm_i915_private *i915, struct drm_atomic_state *state, struct drm_modeset_acquire_ctx *ctx) { struct drm_crtc_state *crtc_state; struct drm_crtc *crtc; - int i, ret; + int i; intel_modeset_setup_hw_state(i915, ctx); intel_vga_redisable(i915); @@ -863,11 +880,7 @@ __intel_display_resume(struct drm_i915_private *i915, if (!HAS_GMCH(i915)) to_intel_atomic_state(state)->skip_intermediate_wm = true; - ret = drm_atomic_helper_commit_duplicated_state(state, ctx); - - drm_WARN_ON(&i915->drm, ret == -EDEADLK); - - return ret; + return intel_display_commit_duplicated_state(to_intel_atomic_state(state), ctx); } static bool gpu_reset_clobbers_display(struct drm_i915_private *dev_priv) @@ -878,8 +891,7 @@ static bool gpu_reset_clobbers_display(struct drm_i915_private *dev_priv) void intel_display_prepare_reset(struct drm_i915_private *dev_priv) { - struct drm_device *dev = &dev_priv->drm; - struct drm_modeset_acquire_ctx *ctx = &dev_priv->reset_ctx; + struct drm_modeset_acquire_ctx *ctx = &dev_priv->display.restore.reset_ctx; struct drm_atomic_state *state; int ret; @@ -906,10 +918,10 @@ void intel_display_prepare_reset(struct drm_i915_private *dev_priv) * Need mode_config.mutex so that we don't * trample ongoing ->detect() and whatnot. */ - mutex_lock(&dev->mode_config.mutex); + mutex_lock(&dev_priv->drm.mode_config.mutex); drm_modeset_acquire_init(ctx, 0); while (1) { - ret = drm_modeset_lock_all_ctx(dev, ctx); + ret = drm_modeset_lock_all_ctx(&dev_priv->drm, ctx); if (ret != -EDEADLK) break; @@ -919,7 +931,7 @@ void intel_display_prepare_reset(struct drm_i915_private *dev_priv) * Disabling the crtcs gracefully seems nicer. Also the * g33 docs say we should at least disable all the planes. */ - state = drm_atomic_helper_duplicate_state(dev, ctx); + state = drm_atomic_helper_duplicate_state(&dev_priv->drm, ctx); if (IS_ERR(state)) { ret = PTR_ERR(state); drm_err(&dev_priv->drm, "Duplicating state failed with %i\n", @@ -927,7 +939,7 @@ void intel_display_prepare_reset(struct drm_i915_private *dev_priv) return; } - ret = drm_atomic_helper_disable_all(dev, ctx); + ret = drm_atomic_helper_disable_all(&dev_priv->drm, ctx); if (ret) { drm_err(&dev_priv->drm, "Suspending crtc's failed with %i\n", ret); @@ -935,13 +947,13 @@ void intel_display_prepare_reset(struct drm_i915_private *dev_priv) return; } - dev_priv->modeset_restore_state = state; + dev_priv->display.restore.modeset_state = state; state->acquire_ctx = ctx; } void intel_display_finish_reset(struct drm_i915_private *i915) { - struct drm_modeset_acquire_ctx *ctx = &i915->reset_ctx; + struct drm_modeset_acquire_ctx *ctx = &i915->display.restore.reset_ctx; struct drm_atomic_state *state; int ret; @@ -952,14 +964,14 @@ void intel_display_finish_reset(struct drm_i915_private *i915) if (!test_bit(I915_RESET_MODESET, &to_gt(i915)->reset.flags)) return; - state = fetch_and_zero(&i915->modeset_restore_state); + state = fetch_and_zero(&i915->display.restore.modeset_state); if (!state) goto unlock; /* reset doesn't touch the display */ if (!gpu_reset_clobbers_display(i915)) { /* for testing only restore the display */ - ret = __intel_display_resume(i915, state, ctx); + ret = intel_display_commit_duplicated_state(to_intel_atomic_state(state), ctx); if (ret) drm_err(&i915->drm, "Restoring old state failed with %i\n", ret); @@ -1252,8 +1264,6 @@ static void intel_post_plane_update(struct intel_atomic_state *state, if (needs_cursorclk_wa(old_crtc_state) && !needs_cursorclk_wa(new_crtc_state)) icl_wa_cursorclkgating(dev_priv, pipe, false); - - intel_drrs_activate(new_crtc_state); } static void intel_crtc_enable_flip_done(struct intel_atomic_state *state, @@ -2434,7 +2444,7 @@ int intel_display_suspend(struct drm_device *dev) drm_err(&dev_priv->drm, "Suspending crtc's failed with %i\n", ret); else - dev_priv->modeset_restore_state = state; + dev_priv->display.restore.modeset_state = state; return ret; } @@ -4045,20 +4055,19 @@ static bool hsw_get_pipe_config(struct intel_crtc *crtc, struct intel_crtc_state *pipe_config) { struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - struct intel_display_power_domain_set power_domain_set = { }; bool active; u32 tmp; - if (!intel_display_power_get_in_set_if_enabled(dev_priv, &power_domain_set, + if (!intel_display_power_get_in_set_if_enabled(dev_priv, &crtc->hw_readout_power_domains, POWER_DOMAIN_PIPE(crtc->pipe))) return false; pipe_config->shared_dpll = NULL; - active = hsw_get_transcoder_state(crtc, pipe_config, &power_domain_set); + active = hsw_get_transcoder_state(crtc, pipe_config, &crtc->hw_readout_power_domains); if ((IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) && - bxt_get_dsi_transcoder_state(crtc, pipe_config, &power_domain_set)) { + bxt_get_dsi_transcoder_state(crtc, pipe_config, &crtc->hw_readout_power_domains)) { drm_WARN_ON(&dev_priv->drm, active); active = true; } @@ -4117,7 +4126,7 @@ static bool hsw_get_pipe_config(struct intel_crtc *crtc, pipe_config->ips_linetime = REG_FIELD_GET(HSW_IPS_LINETIME_MASK, tmp); - if (intel_display_power_get_in_set_if_enabled(dev_priv, &power_domain_set, + if (intel_display_power_get_in_set_if_enabled(dev_priv, &crtc->hw_readout_power_domains, POWER_DOMAIN_PIPE_PANEL_FITTER(crtc->pipe))) { if (DISPLAY_VER(dev_priv) >= 9) skl_get_pfit_config(pipe_config); @@ -4148,7 +4157,7 @@ static bool hsw_get_pipe_config(struct intel_crtc *crtc, } out: - intel_display_power_put_all_in_set(dev_priv, &power_domain_set); + intel_display_power_put_all_in_set(dev_priv, &crtc->hw_readout_power_domains); return active; } @@ -4576,8 +4585,8 @@ static bool encoders_cloneable(const struct intel_encoder *a, const struct intel_encoder *b) { /* masks could be asymmetric, so check both ways */ - return a == b || (a->cloneable & (1 << b->type) && - b->cloneable & (1 << a->type)); + return a == b || (a->cloneable & BIT(b->type) && + b->cloneable & BIT(a->type)); } static bool check_single_encoder_cloning(struct intel_atomic_state *state, @@ -4828,14 +4837,14 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state, struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc); - bool mode_changed = intel_crtc_needs_modeset(crtc_state); int ret; if (DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv) && - mode_changed && !crtc_state->hw.active) + intel_crtc_needs_modeset(crtc_state) && + !crtc_state->hw.active) crtc_state->update_wm_post = true; - if (mode_changed) { + if (intel_crtc_needs_modeset(crtc_state)) { ret = intel_dpll_crtc_get_shared_dpll(state, crtc); if (ret) return ret; @@ -4848,8 +4857,7 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state, if (c8_planes_changed(crtc_state)) crtc_state->uapi.color_mgmt_changed = true; - if (mode_changed || crtc_state->update_pipe || - crtc_state->uapi.color_mgmt_changed) { + if (intel_crtc_needs_color_update(crtc_state)) { ret = intel_color_check(crtc_state); if (ret) return ret; @@ -4875,7 +4883,8 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state, } if (DISPLAY_VER(dev_priv) >= 9) { - if (mode_changed || crtc_state->update_pipe) { + if (intel_crtc_needs_modeset(crtc_state) || + intel_crtc_needs_fastset(crtc_state)) { ret = skl_update_scaler_crtc(crtc_state); if (ret) return ret; @@ -5641,39 +5650,6 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, PIPE_CONF_CHECK_I(name.y2); \ } while (0) -/* This is required for BDW+ where there is only one set of registers for - * switching between high and low RR. - * This macro can be used whenever a comparison has to be made between one - * hw state and multiple sw state variables. - */ -#define PIPE_CONF_CHECK_M_N_ALT(name, alt_name) do { \ - if (!intel_compare_link_m_n(¤t_config->name, \ - &pipe_config->name) && \ - !intel_compare_link_m_n(¤t_config->alt_name, \ - &pipe_config->name)) { \ - pipe_config_mismatch(fastset, crtc, __stringify(name), \ - "(expected tu %i data %i/%i link %i/%i, " \ - "or tu %i data %i/%i link %i/%i, " \ - "found tu %i, data %i/%i link %i/%i)", \ - current_config->name.tu, \ - current_config->name.data_m, \ - current_config->name.data_n, \ - current_config->name.link_m, \ - current_config->name.link_n, \ - current_config->alt_name.tu, \ - current_config->alt_name.data_m, \ - current_config->alt_name.data_n, \ - current_config->alt_name.link_m, \ - current_config->alt_name.link_n, \ - pipe_config->name.tu, \ - pipe_config->name.data_m, \ - pipe_config->name.data_n, \ - pipe_config->name.link_m, \ - pipe_config->name.link_n); \ - ret = false; \ - } \ -} while (0) - #define PIPE_CONF_CHECK_FLAGS(name, mask) do { \ if ((current_config->name ^ pipe_config->name) & (mask)) { \ pipe_config_mismatch(fastset, crtc, __stringify(name), \ @@ -5742,7 +5718,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, if (HAS_DOUBLE_BUFFERED_M_N(dev_priv)) { if (!fastset || !pipe_config->seamless_m_n) - PIPE_CONF_CHECK_M_N_ALT(dp_m_n, dp_m2_n2); + PIPE_CONF_CHECK_M_N(dp_m_n); } else { PIPE_CONF_CHECK_M_N(dp_m_n); PIPE_CONF_CHECK_M_N(dp_m2_n2); @@ -5819,7 +5795,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, bp_gamma = intel_color_get_gamma_bit_precision(pipe_config); if (bp_gamma) - PIPE_CONF_CHECK_COLOR_LUT(gamma_mode, hw.gamma_lut, bp_gamma); + PIPE_CONF_CHECK_COLOR_LUT(gamma_mode, post_csc_lut, bp_gamma); if (current_config->active_planes) { PIPE_CONF_CHECK_BOOL(has_psr); @@ -5941,7 +5917,8 @@ intel_verify_planes(struct intel_atomic_state *state) plane_state->uapi.visible); } -int intel_modeset_all_pipes(struct intel_atomic_state *state) +int intel_modeset_all_pipes(struct intel_atomic_state *state, + const char *reason) { struct drm_i915_private *dev_priv = to_i915(state->base.dev); struct intel_crtc *crtc; @@ -5959,10 +5936,14 @@ int intel_modeset_all_pipes(struct intel_atomic_state *state) return PTR_ERR(crtc_state); if (!crtc_state->hw.active || - drm_atomic_crtc_needs_modeset(&crtc_state->uapi)) + intel_crtc_needs_modeset(crtc_state)) continue; + drm_dbg_kms(&dev_priv->drm, "[CRTC:%d:%s] Full modeset due to %s\n", + crtc->base.base.id, crtc->base.name, reason); + crtc_state->uapi.mode_changed = true; + crtc_state->update_pipe = false; ret = drm_atomic_add_affected_connectors(&state->base, &crtc->base); @@ -6138,7 +6119,8 @@ static void intel_crtc_check_fastset(const struct intel_crtc_state *old_crtc_sta return; new_crtc_state->uapi.mode_changed = false; - new_crtc_state->update_pipe = true; + if (!intel_crtc_needs_modeset(new_crtc_state)) + new_crtc_state->update_pipe = true; } static int intel_crtc_add_planes_to_state(struct intel_atomic_state *state, @@ -6910,12 +6892,19 @@ static int intel_atomic_check(struct drm_device *dev, for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { + intel_color_assert_luts(new_crtc_state); + ret = intel_async_flip_check_hw(state, crtc); if (ret) goto fail; + /* Either full modeset or fastset (or neither), never both */ + drm_WARN_ON(&dev_priv->drm, + intel_crtc_needs_modeset(new_crtc_state) && + intel_crtc_needs_fastset(new_crtc_state)); + if (!intel_crtc_needs_modeset(new_crtc_state) && - !new_crtc_state->update_pipe) + !intel_crtc_needs_fastset(new_crtc_state)) continue; intel_crtc_state_dump(new_crtc_state, state, @@ -6951,12 +6940,8 @@ static int intel_atomic_prepare_commit(struct intel_atomic_state *state) return ret; for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) { - bool mode_changed = intel_crtc_needs_modeset(crtc_state); - - if (mode_changed || crtc_state->update_pipe || - crtc_state->uapi.color_mgmt_changed) { + if (intel_crtc_needs_color_update(crtc_state)) intel_dsb_prepare(crtc_state); - } } return 0; @@ -7037,14 +7022,13 @@ static void commit_pipe_pre_planes(struct intel_atomic_state *state, * CRTC was enabled. */ if (!modeset) { - if (new_crtc_state->uapi.color_mgmt_changed || - new_crtc_state->update_pipe) + if (intel_crtc_needs_color_update(new_crtc_state)) intel_color_commit_arm(new_crtc_state); if (DISPLAY_VER(dev_priv) >= 9 || IS_BROADWELL(dev_priv)) bdw_set_pipemisc(new_crtc_state); - if (new_crtc_state->update_pipe) + if (intel_crtc_needs_fastset(new_crtc_state)) intel_pipe_fastset(old_crtc_state, new_crtc_state); } @@ -7103,25 +7087,23 @@ static void intel_update_crtc(struct intel_atomic_state *state, if (!modeset) { if (new_crtc_state->preload_luts && - (new_crtc_state->uapi.color_mgmt_changed || - new_crtc_state->update_pipe)) + intel_crtc_needs_color_update(new_crtc_state)) intel_color_load_luts(new_crtc_state); intel_pre_plane_update(state, crtc); - if (new_crtc_state->update_pipe) + if (intel_crtc_needs_fastset(new_crtc_state)) intel_encoders_update_pipe(state, crtc); if (DISPLAY_VER(i915) >= 11 && - new_crtc_state->update_pipe) + intel_crtc_needs_fastset(new_crtc_state)) icl_set_pipe_chicken(new_crtc_state); } intel_fbc_update(state, crtc); if (!modeset && - (new_crtc_state->uapi.color_mgmt_changed || - new_crtc_state->update_pipe)) + intel_crtc_needs_color_update(new_crtc_state)) intel_color_commit_noarm(new_crtc_state); intel_crtc_planes_update_noarm(state, crtc); @@ -7143,7 +7125,7 @@ static void intel_update_crtc(struct intel_atomic_state *state, * valid pipe configuration from the BIOS we need to take care * of enabling them on the CRTC's first fastset. */ - if (new_crtc_state->update_pipe && !modeset && + if (intel_crtc_needs_fastset(new_crtc_state) && !modeset && old_crtc_state->inherited) intel_crtc_arm_fifo_underrun(crtc, new_crtc_state); } @@ -7166,9 +7148,7 @@ static void intel_old_crtc_state_disables(struct intel_atomic_state *state, intel_fbc_disable(crtc); intel_disable_shared_dpll(old_crtc_state); - /* FIXME unify this for all platforms */ - if (!new_crtc_state->hw.active && - !HAS_GMCH(dev_priv)) + if (!new_crtc_state->hw.active) intel_initial_watermarks(state, crtc); } @@ -7503,9 +7483,8 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { if (intel_crtc_needs_modeset(new_crtc_state) || - new_crtc_state->update_pipe) { + intel_crtc_needs_fastset(new_crtc_state)) intel_modeset_get_crtc_power_domains(new_crtc_state, &put_domains[crtc->pipe]); - } } intel_commit_modeset_disables(state); @@ -7609,6 +7588,12 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) intel_modeset_verify_crtc(crtc, state, old_crtc_state, new_crtc_state); /* + * Activate DRRS after state readout to avoid + * dp_m_n vs. dp_m2_n2 confusion on BDW+. + */ + intel_drrs_activate(new_crtc_state); + + /* * DSB cleanup is done in cleanup_work aligning with framebuffer * cleanup. So copy and reset the dsb structure to sync with * commit_done and later do dsb cleanup in cleanup_work. @@ -8348,6 +8333,7 @@ void intel_init_display_hooks(struct drm_i915_private *dev_priv) if (!HAS_DISPLAY(dev_priv)) return; + intel_color_init_hooks(dev_priv); intel_init_cdclk_hooks(dev_priv); intel_audio_hooks_init(dev_priv); @@ -8589,7 +8575,7 @@ static void intel_mode_config_init(struct drm_i915_private *i915) struct drm_mode_config *mode_config = &i915->drm.mode_config; drm_mode_config_init(&i915->drm); - INIT_LIST_HEAD(&i915->global_obj_list); + INIT_LIST_HEAD(&i915->display.global.obj_list); mode_config->min_width = 0; mode_config->min_height = 0; @@ -8678,6 +8664,10 @@ int intel_modeset_init_noirq(struct drm_i915_private *i915) if (ret) goto cleanup_vga_client_pw_domain_dmc; + ret = intel_color_init(i915); + if (ret) + goto cleanup_vga_client_pw_domain_dmc; + ret = intel_dbuf_init(i915); if (ret) goto cleanup_vga_client_pw_domain_dmc; @@ -8750,12 +8740,7 @@ int intel_modeset_init_nogem(struct drm_i915_private *i915) if (i915->display.cdclk.max_cdclk_freq == 0) intel_update_max_cdclk(i915); - /* - * If the platform has HTI, we need to find out whether it has reserved - * any display resources before we create our display outputs. - */ - if (INTEL_INFO(i915)->display.has_hti) - i915->hti_state = intel_de_read(i915, HDPORT_STATE); + intel_hti_init(i915); /* Just disable it once at startup */ intel_vga_disable(i915); @@ -8918,14 +8903,14 @@ void i830_disable_pipe(struct drm_i915_private *dev_priv, enum pipe pipe) void intel_display_resume(struct drm_device *dev) { struct drm_i915_private *i915 = to_i915(dev); - struct drm_atomic_state *state = i915->modeset_restore_state; + struct drm_atomic_state *state = i915->display.restore.modeset_state; struct drm_modeset_acquire_ctx ctx; int ret; if (!HAS_DISPLAY(i915)) return; - i915->modeset_restore_state = NULL; + i915->display.restore.modeset_state = NULL; if (state) state->acquire_ctx = &ctx; diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h index 884e8e67b17c..714030136b7f 100644 --- a/drivers/gpu/drm/i915/display/intel_display.h +++ b/drivers/gpu/drm/i915/display/intel_display.h @@ -53,6 +53,7 @@ struct intel_digital_port; struct intel_dp; struct intel_encoder; struct intel_initial_plane_config; +struct intel_link_m_n; struct intel_load_detect_pipe; struct intel_plane; struct intel_plane_state; @@ -61,24 +62,6 @@ struct intel_remapped_info; struct intel_rotation_info; struct pci_dev; -enum i915_gpio { - GPIOA, - GPIOB, - GPIOC, - GPIOD, - GPIOE, - GPIOF, - GPIOG, - GPIOH, - __GPIOI_UNUSED, - GPIOJ, - GPIOK, - GPIOL, - GPIOM, - GPION, - GPIOO, -}; - /* * Keep the pipe enum values fixed: the code assumes that PIPE_A=0, the * rest have consecutive values and match the enum values of transcoders @@ -279,17 +262,6 @@ enum tc_port_mode { TC_PORT_LEGACY, }; -enum dpio_channel { - DPIO_CH0, - DPIO_CH1 -}; - -enum dpio_phy { - DPIO_PHY0, - DPIO_PHY1, - DPIO_PHY2, -}; - enum aux_ch { AUX_CH_A, AUX_CH_B, @@ -316,15 +288,6 @@ enum aux_ch { #define aux_ch_name(a) ((a) + 'A') -/* Used by dp and fdi links */ -struct intel_link_m_n { - u32 tu; - u32 data_m; - u32 data_n; - u32 link_m; - u32 link_n; -}; - enum phy { PHY_NONE = -1, @@ -469,10 +432,6 @@ enum hpd_pin { list_for_each_entry((intel_encoder), &(dev)->mode_config.encoder_list, base.head) \ for_each_if((intel_encoder)->base.crtc == (__crtc)) -#define for_each_connector_on_encoder(dev, __encoder, intel_connector) \ - list_for_each_entry((intel_connector), &(dev)->mode_config.connector_list, base.head) \ - for_each_if((intel_connector)->base.encoder == (__encoder)) - #define for_each_old_intel_plane_in_state(__state, plane, old_plane_state, __i) \ for ((__i) = 0; \ (__i) < (__state)->base.dev->mode_config.num_total_plane && \ @@ -683,7 +642,8 @@ void intel_modeset_driver_remove(struct drm_i915_private *i915); void intel_modeset_driver_remove_noirq(struct drm_i915_private *i915); void intel_modeset_driver_remove_nogem(struct drm_i915_private *i915); void intel_display_resume(struct drm_device *dev); -int intel_modeset_all_pipes(struct intel_atomic_state *state); +int intel_modeset_all_pipes(struct intel_atomic_state *state, + const char *reason); void intel_modeset_get_crtc_power_domains(struct intel_crtc_state *crtc_state, struct intel_power_domain_mask *old_domains); void intel_modeset_put_crtc_power_domains(struct intel_crtc *crtc, diff --git a/drivers/gpu/drm/i915/display/intel_display_core.h b/drivers/gpu/drm/i915/display/intel_display_core.h index 9b51148e8ba5..57ddce3ba02b 100644 --- a/drivers/gpu/drm/i915/display/intel_display_core.h +++ b/drivers/gpu/drm/i915/display/intel_display_core.h @@ -14,6 +14,7 @@ #include <linux/workqueue.h> #include <drm/drm_connector.h> +#include <drm/drm_modeset_lock.h> #include "intel_cdclk.h" #include "intel_display.h" @@ -28,6 +29,7 @@ struct drm_i915_private; struct drm_property; +struct drm_property_blob; struct i915_audio_component; struct i915_hdcp_comp_master; struct intel_atomic_state; @@ -309,6 +311,10 @@ struct intel_display { } cdclk; struct { + struct drm_property_blob *glk_linear_degamma_lut; + } color; + + struct { /* The current hardware dbuf configuration */ u8 enabled_slices; @@ -340,6 +346,10 @@ struct intel_display { } fdi; struct { + struct list_head obj_list; + } global; + + struct { /* * Base address of where the gmbus and gpio blocks are located * (either on PCH or on SoC for platforms without PCH). @@ -366,6 +376,16 @@ struct intel_display { } hdcp; struct { + /* + * HTI (aka HDPORT) state read during initial hw readout. Most + * platforms don't have HTI, so this will just stay 0. Those + * that do will use this later to figure out which PLLs and PHYs + * are unavailable for driver usage. + */ + u32 state; + } hti; + + struct { struct i915_power_domains domains; /* Shadow for DISPLAY_PHY_CONTROL which can't be safely read */ @@ -392,6 +412,12 @@ struct intel_display { } quirks; struct { + /* restore state for suspend/resume and display reset */ + struct drm_atomic_state *modeset_state; + struct drm_modeset_acquire_ctx reset_ctx; + } restore; + + struct { enum { I915_SAGV_UNKNOWN = 0, I915_SAGV_DISABLED, diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs.c b/drivers/gpu/drm/i915/display/intel_display_debugfs.c index 7c7253a2541c..7bcd90384a46 100644 --- a/drivers/gpu/drm/i915/display/intel_display_debugfs.c +++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.c @@ -9,6 +9,8 @@ #include <drm/drm_fourcc.h> #include "i915_debugfs.h" +#include "i915_irq.h" +#include "i915_reg.h" #include "intel_de.h" #include "intel_display_debugfs.h" #include "intel_display_power.h" @@ -22,6 +24,7 @@ #include "intel_fbdev.h" #include "intel_hdcp.h" #include "intel_hdmi.h" +#include "intel_hotplug.h" #include "intel_panel.h" #include "intel_pm.h" #include "intel_psr.h" @@ -127,7 +130,6 @@ static int i915_vbt(struct seq_file *m, void *unused) static int i915_gem_framebuffer_info(struct seq_file *m, void *data) { struct drm_i915_private *dev_priv = node_to_i915(m->private); - struct drm_device *dev = &dev_priv->drm; struct intel_framebuffer *fbdev_fb = NULL; struct drm_framebuffer *drm_fb; @@ -146,8 +148,8 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data) } #endif - mutex_lock(&dev->mode_config.fb_lock); - drm_for_each_fb(drm_fb, dev) { + mutex_lock(&dev_priv->drm.mode_config.fb_lock); + drm_for_each_fb(drm_fb, &dev_priv->drm) { struct intel_framebuffer *fb = to_intel_framebuffer(drm_fb); if (fb == fbdev_fb) continue; @@ -162,7 +164,7 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data) i915_debugfs_describe_obj(m, intel_fb_obj(&fb->base)); seq_putc(m, '\n'); } - mutex_unlock(&dev->mode_config.fb_lock); + mutex_unlock(&dev_priv->drm.mode_config.fb_lock); return 0; } @@ -897,7 +899,6 @@ static void intel_crtc_info(struct seq_file *m, struct intel_crtc *crtc) static int i915_display_info(struct seq_file *m, void *unused) { struct drm_i915_private *dev_priv = node_to_i915(m->private); - struct drm_device *dev = &dev_priv->drm; struct intel_crtc *crtc; struct drm_connector *connector; struct drm_connector_list_iter conn_iter; @@ -905,22 +906,22 @@ static int i915_display_info(struct seq_file *m, void *unused) wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm); - drm_modeset_lock_all(dev); + drm_modeset_lock_all(&dev_priv->drm); seq_printf(m, "CRTC info\n"); seq_printf(m, "---------\n"); - for_each_intel_crtc(dev, crtc) + for_each_intel_crtc(&dev_priv->drm, crtc) intel_crtc_info(m, crtc); seq_printf(m, "\n"); seq_printf(m, "Connector info\n"); seq_printf(m, "--------------\n"); - drm_connector_list_iter_begin(dev, &conn_iter); + drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) intel_connector_info(m, connector); drm_connector_list_iter_end(&conn_iter); - drm_modeset_unlock_all(dev); + drm_modeset_unlock_all(&dev_priv->drm); intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref); @@ -930,10 +931,9 @@ static int i915_display_info(struct seq_file *m, void *unused) static int i915_shared_dplls_info(struct seq_file *m, void *unused) { struct drm_i915_private *dev_priv = node_to_i915(m->private); - struct drm_device *dev = &dev_priv->drm; int i; - drm_modeset_lock_all(dev); + drm_modeset_lock_all(&dev_priv->drm); seq_printf(m, "PLL refclks: non-SSC: %d kHz, SSC: %d kHz\n", dev_priv->display.dpll.ref_clks.nssc, @@ -978,7 +978,7 @@ static int i915_shared_dplls_info(struct seq_file *m, void *unused) seq_printf(m, " mg_pll_tdc_coldst_bias: 0x%08x\n", pll->state.hw_state.mg_pll_tdc_coldst_bias); } - drm_modeset_unlock_all(dev); + drm_modeset_unlock_all(&dev_priv->drm); return 0; } @@ -986,14 +986,13 @@ static int i915_shared_dplls_info(struct seq_file *m, void *unused) static int i915_ddb_info(struct seq_file *m, void *unused) { struct drm_i915_private *dev_priv = node_to_i915(m->private); - struct drm_device *dev = &dev_priv->drm; struct skl_ddb_entry *entry; struct intel_crtc *crtc; if (DISPLAY_VER(dev_priv) < 9) return -ENODEV; - drm_modeset_lock_all(dev); + drm_modeset_lock_all(&dev_priv->drm); seq_printf(m, "%-15s%8s%8s%8s\n", "", "Start", "End", "Size"); @@ -1017,53 +1016,7 @@ static int i915_ddb_info(struct seq_file *m, void *unused) entry->end, skl_ddb_entry_size(entry)); } - drm_modeset_unlock_all(dev); - - return 0; -} - -static int i915_drrs_status(struct seq_file *m, void *unused) -{ - struct drm_i915_private *dev_priv = node_to_i915(m->private); - struct drm_connector_list_iter conn_iter; - struct intel_connector *connector; - struct intel_crtc *crtc; - - drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter); - for_each_intel_connector_iter(connector, &conn_iter) { - seq_printf(m, "[CONNECTOR:%d:%s] DRRS type: %s\n", - connector->base.base.id, connector->base.name, - intel_drrs_type_str(intel_panel_drrs_type(connector))); - } - drm_connector_list_iter_end(&conn_iter); - - seq_puts(m, "\n"); - - for_each_intel_crtc(&dev_priv->drm, crtc) { - const struct intel_crtc_state *crtc_state = - to_intel_crtc_state(crtc->base.state); - - seq_printf(m, "[CRTC:%d:%s]:\n", - crtc->base.base.id, crtc->base.name); - - mutex_lock(&crtc->drrs.mutex); - - /* DRRS Supported */ - seq_printf(m, "\tDRRS Enabled: %s\n", - str_yes_no(crtc_state->has_drrs)); - - seq_printf(m, "\tDRRS Active: %s\n", - str_yes_no(intel_drrs_is_active(crtc))); - - seq_printf(m, "\tBusy_frontbuffer_bits: 0x%X\n", - crtc->drrs.busy_frontbuffer_bits); - - seq_printf(m, "\tDRRS refresh rate: %s\n", - crtc->drrs.refresh_rate == DRRS_REFRESH_RATE_LOW ? - "low" : "high"); - - mutex_unlock(&crtc->drrs.mutex); - } + drm_modeset_unlock_all(&dev_priv->drm); return 0; } @@ -1107,13 +1060,12 @@ static int i915_lpsp_status(struct seq_file *m, void *unused) static int i915_dp_mst_info(struct seq_file *m, void *unused) { struct drm_i915_private *dev_priv = node_to_i915(m->private); - struct drm_device *dev = &dev_priv->drm; struct intel_encoder *intel_encoder; struct intel_digital_port *dig_port; struct drm_connector *connector; struct drm_connector_list_iter conn_iter; - drm_connector_list_iter_begin(dev, &conn_iter); + drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) { if (connector->connector_type != DRM_MODE_CONNECTOR_DisplayPort) continue; @@ -1200,12 +1152,11 @@ static ssize_t i915_displayport_test_active_write(struct file *file, static int i915_displayport_test_active_show(struct seq_file *m, void *data) { struct drm_i915_private *dev_priv = m->private; - struct drm_device *dev = &dev_priv->drm; struct drm_connector *connector; struct drm_connector_list_iter conn_iter; struct intel_dp *intel_dp; - drm_connector_list_iter_begin(dev, &conn_iter); + drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) { struct intel_encoder *encoder; @@ -1250,12 +1201,11 @@ static const struct file_operations i915_displayport_test_active_fops = { static int i915_displayport_test_data_show(struct seq_file *m, void *data) { struct drm_i915_private *dev_priv = m->private; - struct drm_device *dev = &dev_priv->drm; struct drm_connector *connector; struct drm_connector_list_iter conn_iter; struct intel_dp *intel_dp; - drm_connector_list_iter_begin(dev, &conn_iter); + drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) { struct intel_encoder *encoder; @@ -1304,12 +1254,11 @@ DEFINE_SHOW_ATTRIBUTE(i915_displayport_test_data); static int i915_displayport_test_type_show(struct seq_file *m, void *data) { struct drm_i915_private *dev_priv = m->private; - struct drm_device *dev = &dev_priv->drm; struct drm_connector *connector; struct drm_connector_list_iter conn_iter; struct intel_dp *intel_dp; - drm_connector_list_iter_begin(dev, &conn_iter); + drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) { struct intel_encoder *encoder; @@ -1336,7 +1285,6 @@ DEFINE_SHOW_ATTRIBUTE(i915_displayport_test_type); static void wm_latency_show(struct seq_file *m, const u16 wm[8]) { struct drm_i915_private *dev_priv = m->private; - struct drm_device *dev = &dev_priv->drm; int level; int num_levels; @@ -1349,7 +1297,7 @@ static void wm_latency_show(struct seq_file *m, const u16 wm[8]) else num_levels = ilk_wm_max_level(dev_priv) + 1; - drm_modeset_lock_all(dev); + drm_modeset_lock_all(&dev_priv->drm); for (level = 0; level < num_levels; level++) { unsigned int latency = wm[level]; @@ -1370,7 +1318,7 @@ static void wm_latency_show(struct seq_file *m, const u16 wm[8]) level, wm[level], latency / 10, latency % 10); } - drm_modeset_unlock_all(dev); + drm_modeset_unlock_all(&dev_priv->drm); } static int pri_wm_latency_show(struct seq_file *m, void *data) @@ -1453,7 +1401,6 @@ static ssize_t wm_latency_write(struct file *file, const char __user *ubuf, { struct seq_file *m = file->private_data; struct drm_i915_private *dev_priv = m->private; - struct drm_device *dev = &dev_priv->drm; u16 new[8] = { 0 }; int num_levels; int level; @@ -1483,12 +1430,12 @@ static ssize_t wm_latency_write(struct file *file, const char __user *ubuf, if (ret != num_levels) return -EINVAL; - drm_modeset_lock_all(dev); + drm_modeset_lock_all(&dev_priv->drm); for (level = 0; level < num_levels; level++) wm[level] = new[level]; - drm_modeset_unlock_all(dev); + drm_modeset_unlock_all(&dev_priv->drm); return len; } @@ -1566,209 +1513,6 @@ static const struct file_operations i915_cur_wm_latency_fops = { .write = cur_wm_latency_write }; -static int i915_hpd_storm_ctl_show(struct seq_file *m, void *data) -{ - struct drm_i915_private *dev_priv = m->private; - struct intel_hotplug *hotplug = &dev_priv->display.hotplug; - - /* Synchronize with everything first in case there's been an HPD - * storm, but we haven't finished handling it in the kernel yet - */ - intel_synchronize_irq(dev_priv); - flush_work(&dev_priv->display.hotplug.dig_port_work); - flush_delayed_work(&dev_priv->display.hotplug.hotplug_work); - - seq_printf(m, "Threshold: %d\n", hotplug->hpd_storm_threshold); - seq_printf(m, "Detected: %s\n", - str_yes_no(delayed_work_pending(&hotplug->reenable_work))); - - return 0; -} - -static ssize_t i915_hpd_storm_ctl_write(struct file *file, - const char __user *ubuf, size_t len, - loff_t *offp) -{ - struct seq_file *m = file->private_data; - struct drm_i915_private *dev_priv = m->private; - struct intel_hotplug *hotplug = &dev_priv->display.hotplug; - unsigned int new_threshold; - int i; - char *newline; - char tmp[16]; - - if (len >= sizeof(tmp)) - return -EINVAL; - - if (copy_from_user(tmp, ubuf, len)) - return -EFAULT; - - tmp[len] = '\0'; - - /* Strip newline, if any */ - newline = strchr(tmp, '\n'); - if (newline) - *newline = '\0'; - - if (strcmp(tmp, "reset") == 0) - new_threshold = HPD_STORM_DEFAULT_THRESHOLD; - else if (kstrtouint(tmp, 10, &new_threshold) != 0) - return -EINVAL; - - if (new_threshold > 0) - drm_dbg_kms(&dev_priv->drm, - "Setting HPD storm detection threshold to %d\n", - new_threshold); - else - drm_dbg_kms(&dev_priv->drm, "Disabling HPD storm detection\n"); - - spin_lock_irq(&dev_priv->irq_lock); - hotplug->hpd_storm_threshold = new_threshold; - /* Reset the HPD storm stats so we don't accidentally trigger a storm */ - for_each_hpd_pin(i) - hotplug->stats[i].count = 0; - spin_unlock_irq(&dev_priv->irq_lock); - - /* Re-enable hpd immediately if we were in an irq storm */ - flush_delayed_work(&dev_priv->display.hotplug.reenable_work); - - return len; -} - -static int i915_hpd_storm_ctl_open(struct inode *inode, struct file *file) -{ - return single_open(file, i915_hpd_storm_ctl_show, inode->i_private); -} - -static const struct file_operations i915_hpd_storm_ctl_fops = { - .owner = THIS_MODULE, - .open = i915_hpd_storm_ctl_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = i915_hpd_storm_ctl_write -}; - -static int i915_hpd_short_storm_ctl_show(struct seq_file *m, void *data) -{ - struct drm_i915_private *dev_priv = m->private; - - seq_printf(m, "Enabled: %s\n", - str_yes_no(dev_priv->display.hotplug.hpd_short_storm_enabled)); - - return 0; -} - -static int -i915_hpd_short_storm_ctl_open(struct inode *inode, struct file *file) -{ - return single_open(file, i915_hpd_short_storm_ctl_show, - inode->i_private); -} - -static ssize_t i915_hpd_short_storm_ctl_write(struct file *file, - const char __user *ubuf, - size_t len, loff_t *offp) -{ - struct seq_file *m = file->private_data; - struct drm_i915_private *dev_priv = m->private; - struct intel_hotplug *hotplug = &dev_priv->display.hotplug; - char *newline; - char tmp[16]; - int i; - bool new_state; - - if (len >= sizeof(tmp)) - return -EINVAL; - - if (copy_from_user(tmp, ubuf, len)) - return -EFAULT; - - tmp[len] = '\0'; - - /* Strip newline, if any */ - newline = strchr(tmp, '\n'); - if (newline) - *newline = '\0'; - - /* Reset to the "default" state for this system */ - if (strcmp(tmp, "reset") == 0) - new_state = !HAS_DP_MST(dev_priv); - else if (kstrtobool(tmp, &new_state) != 0) - return -EINVAL; - - drm_dbg_kms(&dev_priv->drm, "%sabling HPD short storm detection\n", - new_state ? "En" : "Dis"); - - spin_lock_irq(&dev_priv->irq_lock); - hotplug->hpd_short_storm_enabled = new_state; - /* Reset the HPD storm stats so we don't accidentally trigger a storm */ - for_each_hpd_pin(i) - hotplug->stats[i].count = 0; - spin_unlock_irq(&dev_priv->irq_lock); - - /* Re-enable hpd immediately if we were in an irq storm */ - flush_delayed_work(&dev_priv->display.hotplug.reenable_work); - - return len; -} - -static const struct file_operations i915_hpd_short_storm_ctl_fops = { - .owner = THIS_MODULE, - .open = i915_hpd_short_storm_ctl_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = i915_hpd_short_storm_ctl_write, -}; - -static int i915_drrs_ctl_set(void *data, u64 val) -{ - struct drm_i915_private *dev_priv = data; - struct drm_device *dev = &dev_priv->drm; - struct intel_crtc *crtc; - - for_each_intel_crtc(dev, crtc) { - struct intel_crtc_state *crtc_state; - struct drm_crtc_commit *commit; - int ret; - - ret = drm_modeset_lock_single_interruptible(&crtc->base.mutex); - if (ret) - return ret; - - crtc_state = to_intel_crtc_state(crtc->base.state); - - if (!crtc_state->hw.active || - !crtc_state->has_drrs) - goto out; - - commit = crtc_state->uapi.commit; - if (commit) { - ret = wait_for_completion_interruptible(&commit->hw_done); - if (ret) - goto out; - } - - drm_dbg(&dev_priv->drm, - "Manually %sactivating DRRS\n", val ? "" : "de"); - - if (val) - intel_drrs_activate(crtc_state); - else - intel_drrs_deactivate(crtc_state); - -out: - drm_modeset_unlock(&crtc->base.mutex); - if (ret) - return ret; - } - - return 0; -} - -DEFINE_SIMPLE_ATTRIBUTE(i915_drrs_ctl_fops, NULL, i915_drrs_ctl_set, "%llu\n"); - static ssize_t i915_fifo_underrun_reset_write(struct file *filp, const char __user *ubuf, @@ -1776,7 +1520,6 @@ i915_fifo_underrun_reset_write(struct file *filp, { struct drm_i915_private *dev_priv = filp->private_data; struct intel_crtc *crtc; - struct drm_device *dev = &dev_priv->drm; int ret; bool reset; @@ -1787,7 +1530,7 @@ i915_fifo_underrun_reset_write(struct file *filp, if (!reset) return cnt; - for_each_intel_crtc(dev, crtc) { + for_each_intel_crtc(&dev_priv->drm, crtc) { struct drm_crtc_commit *commit; struct intel_crtc_state *crtc_state; @@ -1842,7 +1585,6 @@ static const struct drm_info_list intel_display_debugfs_list[] = { {"i915_shared_dplls_info", i915_shared_dplls_info, 0}, {"i915_dp_mst_info", i915_dp_mst_info, 0}, {"i915_ddb_info", i915_ddb_info, 0}, - {"i915_drrs_status", i915_drrs_status, 0}, {"i915_lpsp_status", i915_lpsp_status, 0}, }; @@ -1857,9 +1599,6 @@ static const struct { {"i915_dp_test_data", &i915_displayport_test_data_fops}, {"i915_dp_test_type", &i915_displayport_test_type_fops}, {"i915_dp_test_active", &i915_displayport_test_active_fops}, - {"i915_hpd_storm_ctl", &i915_hpd_storm_ctl_fops}, - {"i915_hpd_short_storm_ctl", &i915_hpd_short_storm_ctl_fops}, - {"i915_drrs_ctl", &i915_drrs_ctl_fops}, {"i915_edp_psr_debug", &i915_edp_psr_debug_fops}, }; @@ -1882,6 +1621,7 @@ void intel_display_debugfs_register(struct drm_i915_private *i915) intel_dmc_debugfs_register(i915); intel_fbc_debugfs_register(i915); + intel_hpd_debugfs_register(i915); skl_watermark_ipc_debugfs_register(i915); } @@ -2195,6 +1935,8 @@ void intel_connector_debugfs_add(struct intel_connector *intel_connector) if (!root) return; + intel_drrs_connector_debugfs_add(intel_connector); + if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) { debugfs_create_file("i915_panel_timings", S_IRUGO, root, connector, &i915_panel_fops); @@ -2247,6 +1989,7 @@ void intel_crtc_debugfs_add(struct drm_crtc *crtc) return; crtc_updates_add(crtc); + intel_drrs_crtc_debugfs_add(to_intel_crtc(crtc)); intel_fbc_crtc_debugfs_add(to_intel_crtc(crtc)); debugfs_create_file("i915_current_bpc", 0444, crtc->debugfs_entry, crtc, diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 1a63da28f330..3adba64937de 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -129,6 +129,18 @@ intel_display_power_domain_str(enum intel_display_power_domain domain) return "AUDIO_MMIO"; case POWER_DOMAIN_AUDIO_PLAYBACK: return "AUDIO_PLAYBACK"; + case POWER_DOMAIN_AUX_IO_A: + return "AUX_IO_A"; + case POWER_DOMAIN_AUX_IO_B: + return "AUX_IO_B"; + case POWER_DOMAIN_AUX_IO_C: + return "AUX_IO_C"; + case POWER_DOMAIN_AUX_IO_D: + return "AUX_IO_D"; + case POWER_DOMAIN_AUX_IO_E: + return "AUX_IO_E"; + case POWER_DOMAIN_AUX_IO_F: + return "AUX_IO_F"; case POWER_DOMAIN_AUX_A: return "AUX_A"; case POWER_DOMAIN_AUX_B: @@ -153,8 +165,6 @@ intel_display_power_domain_str(enum intel_display_power_domain domain) return "AUX_USBC5"; case POWER_DOMAIN_AUX_USBC6: return "AUX_USBC6"; - case POWER_DOMAIN_AUX_IO_A: - return "AUX_IO_A"; case POWER_DOMAIN_AUX_TBT1: return "AUX_TBT1"; case POWER_DOMAIN_AUX_TBT2: @@ -1148,10 +1158,9 @@ static void hsw_assert_cdclk(struct drm_i915_private *dev_priv) static void assert_can_disable_lcpll(struct drm_i915_private *dev_priv) { - struct drm_device *dev = &dev_priv->drm; struct intel_crtc *crtc; - for_each_intel_crtc(dev, crtc) + for_each_intel_crtc(&dev_priv->drm, crtc) I915_STATE_WARN(crtc->active, "CRTC for pipe %c enabled\n", pipe_name(crtc->pipe)); @@ -2290,6 +2299,7 @@ struct intel_ddi_port_domains { enum intel_display_power_domain ddi_lanes; enum intel_display_power_domain ddi_io; + enum intel_display_power_domain aux_io; enum intel_display_power_domain aux_legacy_usbc; enum intel_display_power_domain aux_tbt; }; @@ -2304,6 +2314,7 @@ i9xx_port_domains[] = { .ddi_lanes = POWER_DOMAIN_PORT_DDI_LANES_A, .ddi_io = POWER_DOMAIN_PORT_DDI_IO_A, + .aux_io = POWER_DOMAIN_AUX_IO_A, .aux_legacy_usbc = POWER_DOMAIN_AUX_A, .aux_tbt = POWER_DOMAIN_INVALID, }, @@ -2319,6 +2330,7 @@ d11_port_domains[] = { .ddi_lanes = POWER_DOMAIN_PORT_DDI_LANES_A, .ddi_io = POWER_DOMAIN_PORT_DDI_IO_A, + .aux_io = POWER_DOMAIN_AUX_IO_A, .aux_legacy_usbc = POWER_DOMAIN_AUX_A, .aux_tbt = POWER_DOMAIN_INVALID, }, { @@ -2329,6 +2341,7 @@ d11_port_domains[] = { .ddi_lanes = POWER_DOMAIN_PORT_DDI_LANES_C, .ddi_io = POWER_DOMAIN_PORT_DDI_IO_C, + .aux_io = POWER_DOMAIN_AUX_IO_C, .aux_legacy_usbc = POWER_DOMAIN_AUX_C, .aux_tbt = POWER_DOMAIN_AUX_TBT1, }, @@ -2344,6 +2357,7 @@ d12_port_domains[] = { .ddi_lanes = POWER_DOMAIN_PORT_DDI_LANES_A, .ddi_io = POWER_DOMAIN_PORT_DDI_IO_A, + .aux_io = POWER_DOMAIN_AUX_IO_A, .aux_legacy_usbc = POWER_DOMAIN_AUX_A, .aux_tbt = POWER_DOMAIN_INVALID, }, { @@ -2354,6 +2368,7 @@ d12_port_domains[] = { .ddi_lanes = POWER_DOMAIN_PORT_DDI_LANES_TC1, .ddi_io = POWER_DOMAIN_PORT_DDI_IO_TC1, + .aux_io = POWER_DOMAIN_INVALID, .aux_legacy_usbc = POWER_DOMAIN_AUX_USBC1, .aux_tbt = POWER_DOMAIN_AUX_TBT1, }, @@ -2369,6 +2384,7 @@ d13_port_domains[] = { .ddi_lanes = POWER_DOMAIN_PORT_DDI_LANES_A, .ddi_io = POWER_DOMAIN_PORT_DDI_IO_A, + .aux_io = POWER_DOMAIN_AUX_IO_A, .aux_legacy_usbc = POWER_DOMAIN_AUX_A, .aux_tbt = POWER_DOMAIN_INVALID, }, { @@ -2379,6 +2395,7 @@ d13_port_domains[] = { .ddi_lanes = POWER_DOMAIN_PORT_DDI_LANES_TC1, .ddi_io = POWER_DOMAIN_PORT_DDI_IO_TC1, + .aux_io = POWER_DOMAIN_INVALID, .aux_legacy_usbc = POWER_DOMAIN_AUX_USBC1, .aux_tbt = POWER_DOMAIN_AUX_TBT1, }, { @@ -2389,6 +2406,7 @@ d13_port_domains[] = { .ddi_lanes = POWER_DOMAIN_PORT_DDI_LANES_D, .ddi_io = POWER_DOMAIN_PORT_DDI_IO_D, + .aux_io = POWER_DOMAIN_AUX_IO_D, .aux_legacy_usbc = POWER_DOMAIN_AUX_D, .aux_tbt = POWER_DOMAIN_INVALID, }, @@ -2467,6 +2485,17 @@ intel_port_domains_for_aux_ch(struct drm_i915_private *i915, enum aux_ch aux_ch) } enum intel_display_power_domain +intel_display_power_aux_io_domain(struct drm_i915_private *i915, enum aux_ch aux_ch) +{ + const struct intel_ddi_port_domains *domains = intel_port_domains_for_aux_ch(i915, aux_ch); + + if (drm_WARN_ON(&i915->drm, !domains || domains->aux_io == POWER_DOMAIN_INVALID)) + return POWER_DOMAIN_AUX_IO_A; + + return domains->aux_io + (int)(aux_ch - domains->aux_ch_start); +} + +enum intel_display_power_domain intel_display_power_legacy_aux_domain(struct drm_i915_private *i915, enum aux_ch aux_ch) { const struct intel_ddi_port_domains *domains = intel_port_domains_for_aux_ch(i915, aux_ch); diff --git a/drivers/gpu/drm/i915/display/intel_display_power.h b/drivers/gpu/drm/i915/display/intel_display_power.h index 7136ea3f233e..2154d900b1aa 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.h +++ b/drivers/gpu/drm/i915/display/intel_display_power.h @@ -6,11 +6,12 @@ #ifndef __INTEL_DISPLAY_POWER_H__ #define __INTEL_DISPLAY_POWER_H__ -#include "intel_runtime_pm.h" +#include "intel_wakeref.h" enum aux_ch; enum dpio_channel; enum dpio_phy; +enum i915_drm_suspend_mode; enum port; struct drm_i915_private; struct i915_power_well; @@ -76,6 +77,14 @@ enum intel_display_power_domain { POWER_DOMAIN_VGA, POWER_DOMAIN_AUDIO_MMIO, POWER_DOMAIN_AUDIO_PLAYBACK, + + POWER_DOMAIN_AUX_IO_A, + POWER_DOMAIN_AUX_IO_B, + POWER_DOMAIN_AUX_IO_C, + POWER_DOMAIN_AUX_IO_D, + POWER_DOMAIN_AUX_IO_E, + POWER_DOMAIN_AUX_IO_F, + POWER_DOMAIN_AUX_A, POWER_DOMAIN_AUX_B, POWER_DOMAIN_AUX_C, @@ -90,8 +99,6 @@ enum intel_display_power_domain { POWER_DOMAIN_AUX_USBC5, POWER_DOMAIN_AUX_USBC6, - POWER_DOMAIN_AUX_IO_A, - POWER_DOMAIN_AUX_TBT1, POWER_DOMAIN_AUX_TBT2, POWER_DOMAIN_AUX_TBT3, @@ -249,6 +256,8 @@ intel_display_power_ddi_lanes_domain(struct drm_i915_private *i915, enum port po enum intel_display_power_domain intel_display_power_ddi_io_domain(struct drm_i915_private *i915, enum port port); enum intel_display_power_domain +intel_display_power_aux_io_domain(struct drm_i915_private *i915, enum aux_ch aux_ch); +enum intel_display_power_domain intel_display_power_legacy_aux_domain(struct drm_i915_private *i915, enum aux_ch aux_ch); enum intel_display_power_domain intel_display_power_tbt_aux_domain(struct drm_i915_private *i915, enum aux_ch aux_ch); diff --git a/drivers/gpu/drm/i915/display/intel_display_power_map.c b/drivers/gpu/drm/i915/display/intel_display_power_map.c index dc04afc6cc8f..f5d66ca85b19 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power_map.c +++ b/drivers/gpu/drm/i915/display/intel_display_power_map.c @@ -170,6 +170,8 @@ I915_DECL_PW_DOMAINS(vlv_pwdoms_display, POWER_DOMAIN_VGA, POWER_DOMAIN_AUDIO_MMIO, POWER_DOMAIN_AUDIO_PLAYBACK, + POWER_DOMAIN_AUX_IO_B, + POWER_DOMAIN_AUX_IO_C, POWER_DOMAIN_AUX_B, POWER_DOMAIN_AUX_C, POWER_DOMAIN_GMBUS, @@ -179,6 +181,8 @@ I915_DECL_PW_DOMAINS(vlv_pwdoms_dpio_cmn_bc, POWER_DOMAIN_PORT_DDI_LANES_B, POWER_DOMAIN_PORT_DDI_LANES_C, POWER_DOMAIN_PORT_CRT, + POWER_DOMAIN_AUX_IO_B, + POWER_DOMAIN_AUX_IO_C, POWER_DOMAIN_AUX_B, POWER_DOMAIN_AUX_C, POWER_DOMAIN_INIT); @@ -186,6 +190,8 @@ I915_DECL_PW_DOMAINS(vlv_pwdoms_dpio_cmn_bc, I915_DECL_PW_DOMAINS(vlv_pwdoms_dpio_tx_bc_lanes, POWER_DOMAIN_PORT_DDI_LANES_B, POWER_DOMAIN_PORT_DDI_LANES_C, + POWER_DOMAIN_AUX_IO_B, + POWER_DOMAIN_AUX_IO_C, POWER_DOMAIN_AUX_B, POWER_DOMAIN_AUX_C, POWER_DOMAIN_INIT); @@ -243,6 +249,9 @@ I915_DECL_PW_DOMAINS(chv_pwdoms_display, POWER_DOMAIN_VGA, POWER_DOMAIN_AUDIO_MMIO, POWER_DOMAIN_AUDIO_PLAYBACK, + POWER_DOMAIN_AUX_IO_B, + POWER_DOMAIN_AUX_IO_C, + POWER_DOMAIN_AUX_IO_D, POWER_DOMAIN_AUX_B, POWER_DOMAIN_AUX_C, POWER_DOMAIN_AUX_D, @@ -252,12 +261,15 @@ I915_DECL_PW_DOMAINS(chv_pwdoms_display, I915_DECL_PW_DOMAINS(chv_pwdoms_dpio_cmn_bc, POWER_DOMAIN_PORT_DDI_LANES_B, POWER_DOMAIN_PORT_DDI_LANES_C, + POWER_DOMAIN_AUX_IO_B, + POWER_DOMAIN_AUX_IO_C, POWER_DOMAIN_AUX_B, POWER_DOMAIN_AUX_C, POWER_DOMAIN_INIT); I915_DECL_PW_DOMAINS(chv_pwdoms_dpio_cmn_d, POWER_DOMAIN_PORT_DDI_LANES_D, + POWER_DOMAIN_AUX_IO_D, POWER_DOMAIN_AUX_D, POWER_DOMAIN_INIT); @@ -305,6 +317,9 @@ static const struct i915_power_well_desc_list chv_power_wells[] = { POWER_DOMAIN_VGA, \ POWER_DOMAIN_AUDIO_MMIO, \ POWER_DOMAIN_AUDIO_PLAYBACK, \ + POWER_DOMAIN_AUX_IO_B, \ + POWER_DOMAIN_AUX_IO_C, \ + POWER_DOMAIN_AUX_IO_D, \ POWER_DOMAIN_AUX_B, \ POWER_DOMAIN_AUX_C, \ POWER_DOMAIN_AUX_D @@ -318,6 +333,7 @@ I915_DECL_PW_DOMAINS(skl_pwdoms_dc_off, POWER_DOMAIN_AUX_A, POWER_DOMAIN_MODESET, POWER_DOMAIN_GT_IRQ, + POWER_DOMAIN_DC_OFF, POWER_DOMAIN_INIT); I915_DECL_PW_DOMAINS(skl_pwdoms_ddi_io_a_e, @@ -407,6 +423,8 @@ static const struct i915_power_well_desc_list skl_power_wells[] = { POWER_DOMAIN_VGA, \ POWER_DOMAIN_AUDIO_MMIO, \ POWER_DOMAIN_AUDIO_PLAYBACK, \ + POWER_DOMAIN_AUX_IO_B, \ + POWER_DOMAIN_AUX_IO_C, \ POWER_DOMAIN_AUX_B, \ POWER_DOMAIN_AUX_C @@ -420,16 +438,20 @@ I915_DECL_PW_DOMAINS(bxt_pwdoms_dc_off, POWER_DOMAIN_GMBUS, POWER_DOMAIN_MODESET, POWER_DOMAIN_GT_IRQ, + POWER_DOMAIN_DC_OFF, POWER_DOMAIN_INIT); I915_DECL_PW_DOMAINS(bxt_pwdoms_dpio_cmn_a, POWER_DOMAIN_PORT_DDI_LANES_A, + POWER_DOMAIN_AUX_IO_A, POWER_DOMAIN_AUX_A, POWER_DOMAIN_INIT); I915_DECL_PW_DOMAINS(bxt_pwdoms_dpio_cmn_bc, POWER_DOMAIN_PORT_DDI_LANES_B, POWER_DOMAIN_PORT_DDI_LANES_C, + POWER_DOMAIN_AUX_IO_B, + POWER_DOMAIN_AUX_IO_C, POWER_DOMAIN_AUX_B, POWER_DOMAIN_AUX_C, POWER_DOMAIN_INIT); @@ -483,6 +505,8 @@ static const struct i915_power_well_desc_list bxt_power_wells[] = { POWER_DOMAIN_VGA, \ POWER_DOMAIN_AUDIO_MMIO, \ POWER_DOMAIN_AUDIO_PLAYBACK, \ + POWER_DOMAIN_AUX_IO_B, \ + POWER_DOMAIN_AUX_IO_C, \ POWER_DOMAIN_AUX_B, \ POWER_DOMAIN_AUX_C @@ -496,6 +520,7 @@ I915_DECL_PW_DOMAINS(glk_pwdoms_dc_off, POWER_DOMAIN_GMBUS, POWER_DOMAIN_MODESET, POWER_DOMAIN_GT_IRQ, + POWER_DOMAIN_DC_OFF, POWER_DOMAIN_INIT); I915_DECL_PW_DOMAINS(glk_pwdoms_ddi_io_a, POWER_DOMAIN_PORT_DDI_IO_A); @@ -504,29 +529,34 @@ I915_DECL_PW_DOMAINS(glk_pwdoms_ddi_io_c, POWER_DOMAIN_PORT_DDI_IO_C); I915_DECL_PW_DOMAINS(glk_pwdoms_dpio_cmn_a, POWER_DOMAIN_PORT_DDI_LANES_A, + POWER_DOMAIN_AUX_IO_A, POWER_DOMAIN_AUX_A, POWER_DOMAIN_INIT); I915_DECL_PW_DOMAINS(glk_pwdoms_dpio_cmn_b, POWER_DOMAIN_PORT_DDI_LANES_B, + POWER_DOMAIN_AUX_IO_B, POWER_DOMAIN_AUX_B, POWER_DOMAIN_INIT); I915_DECL_PW_DOMAINS(glk_pwdoms_dpio_cmn_c, POWER_DOMAIN_PORT_DDI_LANES_C, + POWER_DOMAIN_AUX_IO_C, POWER_DOMAIN_AUX_C, POWER_DOMAIN_INIT); I915_DECL_PW_DOMAINS(glk_pwdoms_aux_a, - POWER_DOMAIN_AUX_A, POWER_DOMAIN_AUX_IO_A, + POWER_DOMAIN_AUX_A, POWER_DOMAIN_INIT); I915_DECL_PW_DOMAINS(glk_pwdoms_aux_b, + POWER_DOMAIN_AUX_IO_B, POWER_DOMAIN_AUX_B, POWER_DOMAIN_INIT); I915_DECL_PW_DOMAINS(glk_pwdoms_aux_c, + POWER_DOMAIN_AUX_IO_C, POWER_DOMAIN_AUX_C, POWER_DOMAIN_INIT); @@ -617,6 +647,11 @@ I915_DECL_PW_DOMAINS(icl_pwdoms_pw_4, POWER_DOMAIN_VGA, \ POWER_DOMAIN_AUDIO_MMIO, \ POWER_DOMAIN_AUDIO_PLAYBACK, \ + POWER_DOMAIN_AUX_IO_B, \ + POWER_DOMAIN_AUX_IO_C, \ + POWER_DOMAIN_AUX_IO_D, \ + POWER_DOMAIN_AUX_IO_E, \ + POWER_DOMAIN_AUX_IO_F, \ POWER_DOMAIN_AUX_B, \ POWER_DOMAIN_AUX_C, \ POWER_DOMAIN_AUX_D, \ @@ -658,13 +693,23 @@ I915_DECL_PW_DOMAINS(icl_pwdoms_ddi_io_e, POWER_DOMAIN_PORT_DDI_IO_E); I915_DECL_PW_DOMAINS(icl_pwdoms_ddi_io_f, POWER_DOMAIN_PORT_DDI_IO_F); I915_DECL_PW_DOMAINS(icl_pwdoms_aux_a, - POWER_DOMAIN_AUX_A, - POWER_DOMAIN_AUX_IO_A); -I915_DECL_PW_DOMAINS(icl_pwdoms_aux_b, POWER_DOMAIN_AUX_B); -I915_DECL_PW_DOMAINS(icl_pwdoms_aux_c, POWER_DOMAIN_AUX_C); -I915_DECL_PW_DOMAINS(icl_pwdoms_aux_d, POWER_DOMAIN_AUX_D); -I915_DECL_PW_DOMAINS(icl_pwdoms_aux_e, POWER_DOMAIN_AUX_E); -I915_DECL_PW_DOMAINS(icl_pwdoms_aux_f, POWER_DOMAIN_AUX_F); + POWER_DOMAIN_AUX_IO_A, + POWER_DOMAIN_AUX_A); +I915_DECL_PW_DOMAINS(icl_pwdoms_aux_b, + POWER_DOMAIN_AUX_IO_B, + POWER_DOMAIN_AUX_B); +I915_DECL_PW_DOMAINS(icl_pwdoms_aux_c, + POWER_DOMAIN_AUX_IO_C, + POWER_DOMAIN_AUX_C); +I915_DECL_PW_DOMAINS(icl_pwdoms_aux_d, + POWER_DOMAIN_AUX_IO_D, + POWER_DOMAIN_AUX_D); +I915_DECL_PW_DOMAINS(icl_pwdoms_aux_e, + POWER_DOMAIN_AUX_IO_E, + POWER_DOMAIN_AUX_E); +I915_DECL_PW_DOMAINS(icl_pwdoms_aux_f, + POWER_DOMAIN_AUX_IO_F, + POWER_DOMAIN_AUX_F); I915_DECL_PW_DOMAINS(icl_pwdoms_aux_tbt1, POWER_DOMAIN_AUX_TBT1); I915_DECL_PW_DOMAINS(icl_pwdoms_aux_tbt2, POWER_DOMAIN_AUX_TBT2); I915_DECL_PW_DOMAINS(icl_pwdoms_aux_tbt3, POWER_DOMAIN_AUX_TBT3); @@ -816,6 +861,7 @@ I915_DECL_PW_DOMAINS(tgl_pwdoms_dc_off, POWER_DOMAIN_AUX_B, POWER_DOMAIN_AUX_C, POWER_DOMAIN_MODESET, + POWER_DOMAIN_DC_OFF, POWER_DOMAIN_INIT); I915_DECL_PW_DOMAINS(tgl_pwdoms_ddi_io_tc1, POWER_DOMAIN_PORT_DDI_IO_TC1); @@ -1012,6 +1058,7 @@ I915_DECL_PW_DOMAINS(rkl_pwdoms_dc_off, POWER_DOMAIN_AUX_A, POWER_DOMAIN_AUX_B, POWER_DOMAIN_MODESET, + POWER_DOMAIN_DC_OFF, POWER_DOMAIN_INIT); static const struct i915_power_well_desc rkl_power_wells_main[] = { @@ -1094,6 +1141,7 @@ I915_DECL_PW_DOMAINS(dg1_pwdoms_dc_off, POWER_DOMAIN_AUX_A, POWER_DOMAIN_AUX_B, POWER_DOMAIN_MODESET, + POWER_DOMAIN_DC_OFF, POWER_DOMAIN_INIT); I915_DECL_PW_DOMAINS(dg1_pwdoms_pw_2, @@ -1215,6 +1263,9 @@ I915_DECL_PW_DOMAINS(xelpd_pwdoms_pw_a, POWER_DOMAIN_PORT_DDI_LANES_TC4, \ POWER_DOMAIN_VGA, \ POWER_DOMAIN_AUDIO_PLAYBACK, \ + POWER_DOMAIN_AUX_IO_C, \ + POWER_DOMAIN_AUX_IO_D, \ + POWER_DOMAIN_AUX_IO_E, \ POWER_DOMAIN_AUX_C, \ POWER_DOMAIN_AUX_D, \ POWER_DOMAIN_AUX_E, \ @@ -1255,6 +1306,7 @@ I915_DECL_PW_DOMAINS(xelpd_pwdoms_dc_off, POWER_DOMAIN_AUX_A, POWER_DOMAIN_AUX_B, POWER_DOMAIN_MODESET, + POWER_DOMAIN_DC_OFF, POWER_DOMAIN_INIT); static const struct i915_power_well_desc xelpd_power_wells_main[] = { @@ -1376,6 +1428,7 @@ I915_DECL_PW_DOMAINS(xelpdp_pwdoms_dc_off, POWER_DOMAIN_MODESET, POWER_DOMAIN_AUX_A, POWER_DOMAIN_AUX_B, + POWER_DOMAIN_DC_OFF, POWER_DOMAIN_INIT); I915_DECL_PW_DOMAINS(xelpdp_pwdoms_aux_tc1, diff --git a/drivers/gpu/drm/i915/display/intel_display_power_well.c b/drivers/gpu/drm/i915/display/intel_display_power_well.c index 1d18eee56253..8710dd41ffd4 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power_well.c +++ b/drivers/gpu/drm/i915/display/intel_display_power_well.c @@ -13,6 +13,7 @@ #include "intel_display_power_well.h" #include "intel_display_types.h" #include "intel_dkl_phy.h" +#include "intel_dkl_phy_regs.h" #include "intel_dmc.h" #include "intel_dpio_phy.h" #include "intel_dpll.h" @@ -531,7 +532,7 @@ icl_tc_phy_aux_power_well_enable(struct drm_i915_private *dev_priv, tc_port = TGL_AUX_PW_TO_TC_PORT(i915_power_well_instance(power_well)->hsw.idx); - if (wait_for(intel_dkl_phy_read(dev_priv, DKL_CMN_UC_DW_27(tc_port), 2) & + if (wait_for(intel_dkl_phy_read(dev_priv, DKL_CMN_UC_DW_27(tc_port)) & DKL_CMN_UC_DW27_UC_HEALTH, 1)) drm_warn(&dev_priv->drm, "Timeout waiting TC uC health\n"); diff --git a/drivers/gpu/drm/i915/display/intel_display_power_well.h b/drivers/gpu/drm/i915/display/intel_display_power_well.h index e13b521e322a..ba7cb977e7c7 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power_well.h +++ b/drivers/gpu/drm/i915/display/intel_display_power_well.h @@ -7,8 +7,8 @@ #include <linux/types.h> -#include "intel_display.h" #include "intel_display_power.h" +#include "intel_dpio_phy.h" struct drm_i915_private; struct i915_power_well; diff --git a/drivers/gpu/drm/i915/display/intel_display_reg_defs.h b/drivers/gpu/drm/i915/display/intel_display_reg_defs.h new file mode 100644 index 000000000000..02605418ff08 --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_display_reg_defs.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2022 Intel Corporation + */ + +#ifndef __INTEL_DISPLAY_REG_DEFS_H__ +#define __INTEL_DISPLAY_REG_DEFS_H__ + +#include "i915_reg_defs.h" + +#define DISPLAY_MMIO_BASE(dev_priv) (INTEL_INFO(dev_priv)->display.mmio_offset) + +#define VLV_DISPLAY_BASE 0x180000 + +/* + * Named helper wrappers around _PICK_EVEN() and _PICK(). + */ +#define _PIPE(pipe, a, b) _PICK_EVEN(pipe, a, b) +#define _PLANE(plane, a, b) _PICK_EVEN(plane, a, b) +#define _TRANS(tran, a, b) _PICK_EVEN(tran, a, b) +#define _PORT(port, a, b) _PICK_EVEN(port, a, b) +#define _PLL(pll, a, b) _PICK_EVEN(pll, a, b) +#define _PHY(phy, a, b) _PICK_EVEN(phy, a, b) + +#define _MMIO_PIPE(pipe, a, b) _MMIO(_PIPE(pipe, a, b)) +#define _MMIO_PLANE(plane, a, b) _MMIO(_PLANE(plane, a, b)) +#define _MMIO_TRANS(tran, a, b) _MMIO(_TRANS(tran, a, b)) +#define _MMIO_PORT(port, a, b) _MMIO(_PORT(port, a, b)) +#define _MMIO_PLL(pll, a, b) _MMIO(_PLL(pll, a, b)) +#define _MMIO_PHY(phy, a, b) _MMIO(_PHY(phy, a, b)) + +#define _PHY3(phy, ...) _PICK(phy, __VA_ARGS__) + +#define _MMIO_PIPE3(pipe, a, b, c) _MMIO(_PICK(pipe, a, b, c)) +#define _MMIO_PORT3(pipe, a, b, c) _MMIO(_PICK(pipe, a, b, c)) +#define _MMIO_PHY3(phy, a, b, c) _MMIO(_PHY3(phy, a, b, c)) +#define _MMIO_PLL3(pll, ...) _MMIO(_PICK(pll, __VA_ARGS__)) + +/* + * Device info offset array based helpers for groups of registers with unevenly + * spaced base offsets. + */ +#define _MMIO_PIPE2(pipe, reg) _MMIO(INTEL_INFO(dev_priv)->display.pipe_offsets[(pipe)] - \ + INTEL_INFO(dev_priv)->display.pipe_offsets[PIPE_A] + \ + DISPLAY_MMIO_BASE(dev_priv) + (reg)) +#define _MMIO_TRANS2(tran, reg) _MMIO(INTEL_INFO(dev_priv)->display.trans_offsets[(tran)] - \ + INTEL_INFO(dev_priv)->display.trans_offsets[TRANSCODER_A] + \ + DISPLAY_MMIO_BASE(dev_priv) + (reg)) +#define _MMIO_CURSOR2(pipe, reg) _MMIO(INTEL_INFO(dev_priv)->display.cursor_offsets[(pipe)] - \ + INTEL_INFO(dev_priv)->display.cursor_offsets[PIPE_A] + \ + DISPLAY_MMIO_BASE(dev_priv) + (reg)) + +#endif /* __INTEL_DISPLAY_REG_DEFS_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_display_trace.h b/drivers/gpu/drm/i915/display/intel_display_trace.h index 2dd5a4b7f5d8..725aba3fa531 100644 --- a/drivers/gpu/drm/i915/display/intel_display_trace.h +++ b/drivers/gpu/drm/i915/display/intel_display_trace.h @@ -18,11 +18,15 @@ #include "intel_crtc.h" #include "intel_display_types.h" +#define __dev_name_i915(i915) dev_name((i915)->drm.dev) +#define __dev_name_kms(obj) dev_name((obj)->base.dev->dev) + TRACE_EVENT(intel_pipe_enable, TP_PROTO(struct intel_crtc *crtc), TP_ARGS(crtc), TP_STRUCT__entry( + __string(dev, __dev_name_kms(crtc)) __array(u32, frame, 3) __array(u32, scanline, 3) __field(enum pipe, pipe) @@ -30,6 +34,7 @@ TRACE_EVENT(intel_pipe_enable, TP_fast_assign( struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); struct intel_crtc *it__; + __assign_str(dev, __dev_name_kms(crtc)); for_each_intel_crtc(&dev_priv->drm, it__) { __entry->frame[it__->pipe] = intel_crtc_get_vblank_counter(it__); __entry->scanline[it__->pipe] = intel_get_crtc_scanline(it__); @@ -37,8 +42,8 @@ TRACE_EVENT(intel_pipe_enable, __entry->pipe = crtc->pipe; ), - TP_printk("pipe %c enable, pipe A: frame=%u, scanline=%u, pipe B: frame=%u, scanline=%u, pipe C: frame=%u, scanline=%u", - pipe_name(__entry->pipe), + TP_printk("dev %s, pipe %c enable, pipe A: frame=%u, scanline=%u, pipe B: frame=%u, scanline=%u, pipe C: frame=%u, scanline=%u", + __get_str(dev), pipe_name(__entry->pipe), __entry->frame[PIPE_A], __entry->scanline[PIPE_A], __entry->frame[PIPE_B], __entry->scanline[PIPE_B], __entry->frame[PIPE_C], __entry->scanline[PIPE_C]) @@ -49,6 +54,7 @@ TRACE_EVENT(intel_pipe_disable, TP_ARGS(crtc), TP_STRUCT__entry( + __string(dev, __dev_name_kms(crtc)) __array(u32, frame, 3) __array(u32, scanline, 3) __field(enum pipe, pipe) @@ -57,6 +63,7 @@ TRACE_EVENT(intel_pipe_disable, TP_fast_assign( struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); struct intel_crtc *it__; + __assign_str(dev, __dev_name_kms(crtc)); for_each_intel_crtc(&dev_priv->drm, it__) { __entry->frame[it__->pipe] = intel_crtc_get_vblank_counter(it__); __entry->scanline[it__->pipe] = intel_get_crtc_scanline(it__); @@ -64,8 +71,8 @@ TRACE_EVENT(intel_pipe_disable, __entry->pipe = crtc->pipe; ), - TP_printk("pipe %c disable, pipe A: frame=%u, scanline=%u, pipe B: frame=%u, scanline=%u, pipe C: frame=%u, scanline=%u", - pipe_name(__entry->pipe), + TP_printk("dev %s, pipe %c disable, pipe A: frame=%u, scanline=%u, pipe B: frame=%u, scanline=%u, pipe C: frame=%u, scanline=%u", + __get_str(dev), pipe_name(__entry->pipe), __entry->frame[PIPE_A], __entry->scanline[PIPE_A], __entry->frame[PIPE_B], __entry->scanline[PIPE_B], __entry->frame[PIPE_C], __entry->scanline[PIPE_C]) @@ -76,6 +83,7 @@ TRACE_EVENT(intel_pipe_crc, TP_ARGS(crtc, crcs), TP_STRUCT__entry( + __string(dev, __dev_name_kms(crtc)) __field(enum pipe, pipe) __field(u32, frame) __field(u32, scanline) @@ -83,16 +91,19 @@ TRACE_EVENT(intel_pipe_crc, ), TP_fast_assign( + __assign_str(dev, __dev_name_kms(crtc)); __entry->pipe = crtc->pipe; __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); memcpy(__entry->crcs, crcs, sizeof(__entry->crcs)); ), - TP_printk("pipe %c, frame=%u, scanline=%u crc=%08x %08x %08x %08x %08x", - pipe_name(__entry->pipe), __entry->frame, __entry->scanline, - __entry->crcs[0], __entry->crcs[1], __entry->crcs[2], - __entry->crcs[3], __entry->crcs[4]) + TP_printk("dev %s, pipe %c, frame=%u, scanline=%u crc=%08x %08x %08x %08x %08x", + __get_str(dev), pipe_name(__entry->pipe), + __entry->frame, __entry->scanline, + __entry->crcs[0], __entry->crcs[1], + __entry->crcs[2], __entry->crcs[3], + __entry->crcs[4]) ); TRACE_EVENT(intel_cpu_fifo_underrun, @@ -100,6 +111,7 @@ TRACE_EVENT(intel_cpu_fifo_underrun, TP_ARGS(dev_priv, pipe), TP_STRUCT__entry( + __string(dev, __dev_name_i915(dev_priv)) __field(enum pipe, pipe) __field(u32, frame) __field(u32, scanline) @@ -107,13 +119,14 @@ TRACE_EVENT(intel_cpu_fifo_underrun, TP_fast_assign( struct intel_crtc *crtc = intel_crtc_for_pipe(dev_priv, pipe); + __assign_str(dev, __dev_name_kms(crtc)); __entry->pipe = pipe; __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); ), - TP_printk("pipe %c, frame=%u, scanline=%u", - pipe_name(__entry->pipe), + TP_printk("dev %s, pipe %c, frame=%u, scanline=%u", + __get_str(dev), pipe_name(__entry->pipe), __entry->frame, __entry->scanline) ); @@ -122,6 +135,7 @@ TRACE_EVENT(intel_pch_fifo_underrun, TP_ARGS(dev_priv, pch_transcoder), TP_STRUCT__entry( + __string(dev, __dev_name_i915(dev_priv)) __field(enum pipe, pipe) __field(u32, frame) __field(u32, scanline) @@ -130,13 +144,14 @@ TRACE_EVENT(intel_pch_fifo_underrun, TP_fast_assign( enum pipe pipe = pch_transcoder; struct intel_crtc *crtc = intel_crtc_for_pipe(dev_priv, pipe); + __assign_str(dev, __dev_name_i915(dev_priv)); __entry->pipe = pipe; __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); ), - TP_printk("pch transcoder %c, frame=%u, scanline=%u", - pipe_name(__entry->pipe), + TP_printk("dev %s, pch transcoder %c, frame=%u, scanline=%u", + __get_str(dev), pipe_name(__entry->pipe), __entry->frame, __entry->scanline) ); @@ -145,6 +160,7 @@ TRACE_EVENT(intel_memory_cxsr, TP_ARGS(dev_priv, old, new), TP_STRUCT__entry( + __string(dev, __dev_name_i915(dev_priv)) __array(u32, frame, 3) __array(u32, scanline, 3) __field(bool, old) @@ -153,6 +169,7 @@ TRACE_EVENT(intel_memory_cxsr, TP_fast_assign( struct intel_crtc *crtc; + __assign_str(dev, __dev_name_i915(dev_priv)); for_each_intel_crtc(&dev_priv->drm, crtc) { __entry->frame[crtc->pipe] = intel_crtc_get_vblank_counter(crtc); __entry->scanline[crtc->pipe] = intel_get_crtc_scanline(crtc); @@ -161,8 +178,8 @@ TRACE_EVENT(intel_memory_cxsr, __entry->new = new; ), - TP_printk("%s->%s, pipe A: frame=%u, scanline=%u, pipe B: frame=%u, scanline=%u, pipe C: frame=%u, scanline=%u", - str_on_off(__entry->old), str_on_off(__entry->new), + TP_printk("dev %s, cxsr %s->%s, pipe A: frame=%u, scanline=%u, pipe B: frame=%u, scanline=%u, pipe C: frame=%u, scanline=%u", + __get_str(dev), str_on_off(__entry->old), str_on_off(__entry->new), __entry->frame[PIPE_A], __entry->scanline[PIPE_A], __entry->frame[PIPE_B], __entry->scanline[PIPE_B], __entry->frame[PIPE_C], __entry->scanline[PIPE_C]) @@ -173,6 +190,7 @@ TRACE_EVENT(g4x_wm, TP_ARGS(crtc, wm), TP_STRUCT__entry( + __string(dev, __dev_name_kms(crtc)) __field(enum pipe, pipe) __field(u32, frame) __field(u32, scanline) @@ -191,6 +209,7 @@ TRACE_EVENT(g4x_wm, ), TP_fast_assign( + __assign_str(dev, __dev_name_kms(crtc)); __entry->pipe = crtc->pipe; __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); @@ -208,8 +227,9 @@ TRACE_EVENT(g4x_wm, __entry->fbc = wm->fbc_en; ), - TP_printk("pipe %c, frame=%u, scanline=%u, wm %d/%d/%d, sr %s/%d/%d/%d, hpll %s/%d/%d/%d, fbc %s", - pipe_name(__entry->pipe), __entry->frame, __entry->scanline, + TP_printk("dev %s, pipe %c, frame=%u, scanline=%u, wm %d/%d/%d, sr %s/%d/%d/%d, hpll %s/%d/%d/%d, fbc %s", + __get_str(dev), pipe_name(__entry->pipe), + __entry->frame, __entry->scanline, __entry->primary, __entry->sprite, __entry->cursor, str_yes_no(__entry->cxsr), __entry->sr_plane, __entry->sr_cursor, __entry->sr_fbc, str_yes_no(__entry->hpll), __entry->hpll_plane, __entry->hpll_cursor, __entry->hpll_fbc, @@ -221,6 +241,7 @@ TRACE_EVENT(vlv_wm, TP_ARGS(crtc, wm), TP_STRUCT__entry( + __string(dev, __dev_name_kms(crtc)) __field(enum pipe, pipe) __field(u32, frame) __field(u32, scanline) @@ -235,6 +256,7 @@ TRACE_EVENT(vlv_wm, ), TP_fast_assign( + __assign_str(dev, __dev_name_kms(crtc)); __entry->pipe = crtc->pipe; __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); @@ -248,9 +270,10 @@ TRACE_EVENT(vlv_wm, __entry->sr_cursor = wm->sr.cursor; ), - TP_printk("pipe %c, frame=%u, scanline=%u, level=%d, cxsr=%d, wm %d/%d/%d/%d, sr %d/%d", - pipe_name(__entry->pipe), __entry->frame, - __entry->scanline, __entry->level, __entry->cxsr, + TP_printk("dev %s, pipe %c, frame=%u, scanline=%u, level=%d, cxsr=%d, wm %d/%d/%d/%d, sr %d/%d", + __get_str(dev), pipe_name(__entry->pipe), + __entry->frame, __entry->scanline, + __entry->level, __entry->cxsr, __entry->primary, __entry->sprite0, __entry->sprite1, __entry->cursor, __entry->sr_plane, __entry->sr_cursor) ); @@ -260,6 +283,7 @@ TRACE_EVENT(vlv_fifo_size, TP_ARGS(crtc, sprite0_start, sprite1_start, fifo_size), TP_STRUCT__entry( + __string(dev, __dev_name_kms(crtc)) __field(enum pipe, pipe) __field(u32, frame) __field(u32, scanline) @@ -269,6 +293,7 @@ TRACE_EVENT(vlv_fifo_size, ), TP_fast_assign( + __assign_str(dev, __dev_name_kms(crtc)); __entry->pipe = crtc->pipe; __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); @@ -277,90 +302,96 @@ TRACE_EVENT(vlv_fifo_size, __entry->fifo_size = fifo_size; ), - TP_printk("pipe %c, frame=%u, scanline=%u, %d/%d/%d", - pipe_name(__entry->pipe), __entry->frame, - __entry->scanline, __entry->sprite0_start, - __entry->sprite1_start, __entry->fifo_size) + TP_printk("dev %s, pipe %c, frame=%u, scanline=%u, %d/%d/%d", + __get_str(dev), pipe_name(__entry->pipe), + __entry->frame, __entry->scanline, + __entry->sprite0_start, __entry->sprite1_start, __entry->fifo_size) ); TRACE_EVENT(intel_plane_update_noarm, - TP_PROTO(struct drm_plane *plane, struct intel_crtc *crtc), + TP_PROTO(struct intel_plane *plane, struct intel_crtc *crtc), TP_ARGS(plane, crtc), TP_STRUCT__entry( + __string(dev, __dev_name_kms(plane)) __field(enum pipe, pipe) __field(u32, frame) __field(u32, scanline) __array(int, src, 4) __array(int, dst, 4) - __string(name, plane->name) + __string(name, plane->base.name) ), TP_fast_assign( - __assign_str(name, plane->name); + __assign_str(dev, __dev_name_kms(plane)); + __assign_str(name, plane->base.name); __entry->pipe = crtc->pipe; __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); - memcpy(__entry->src, &plane->state->src, sizeof(__entry->src)); - memcpy(__entry->dst, &plane->state->dst, sizeof(__entry->dst)); + memcpy(__entry->src, &plane->base.state->src, sizeof(__entry->src)); + memcpy(__entry->dst, &plane->base.state->dst, sizeof(__entry->dst)); ), - TP_printk("pipe %c, plane %s, frame=%u, scanline=%u, " DRM_RECT_FP_FMT " -> " DRM_RECT_FMT, - pipe_name(__entry->pipe), __get_str(name), + TP_printk("dev %s, pipe %c, plane %s, frame=%u, scanline=%u, " DRM_RECT_FP_FMT " -> " DRM_RECT_FMT, + __get_str(dev), pipe_name(__entry->pipe), __get_str(name), __entry->frame, __entry->scanline, DRM_RECT_FP_ARG((const struct drm_rect *)__entry->src), DRM_RECT_ARG((const struct drm_rect *)__entry->dst)) ); TRACE_EVENT(intel_plane_update_arm, - TP_PROTO(struct drm_plane *plane, struct intel_crtc *crtc), + TP_PROTO(struct intel_plane *plane, struct intel_crtc *crtc), TP_ARGS(plane, crtc), TP_STRUCT__entry( + __string(dev, __dev_name_kms(plane)) __field(enum pipe, pipe) __field(u32, frame) __field(u32, scanline) __array(int, src, 4) __array(int, dst, 4) - __string(name, plane->name) + __string(name, plane->base.name) ), TP_fast_assign( - __assign_str(name, plane->name); + __assign_str(dev, __dev_name_kms(plane)); + __assign_str(name, plane->base.name); __entry->pipe = crtc->pipe; __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); - memcpy(__entry->src, &plane->state->src, sizeof(__entry->src)); - memcpy(__entry->dst, &plane->state->dst, sizeof(__entry->dst)); + memcpy(__entry->src, &plane->base.state->src, sizeof(__entry->src)); + memcpy(__entry->dst, &plane->base.state->dst, sizeof(__entry->dst)); ), - TP_printk("pipe %c, plane %s, frame=%u, scanline=%u, " DRM_RECT_FP_FMT " -> " DRM_RECT_FMT, - pipe_name(__entry->pipe), __get_str(name), + TP_printk("dev %s, pipe %c, plane %s, frame=%u, scanline=%u, " DRM_RECT_FP_FMT " -> " DRM_RECT_FMT, + __get_str(dev), pipe_name(__entry->pipe), __get_str(name), __entry->frame, __entry->scanline, DRM_RECT_FP_ARG((const struct drm_rect *)__entry->src), DRM_RECT_ARG((const struct drm_rect *)__entry->dst)) ); TRACE_EVENT(intel_plane_disable_arm, - TP_PROTO(struct drm_plane *plane, struct intel_crtc *crtc), + TP_PROTO(struct intel_plane *plane, struct intel_crtc *crtc), TP_ARGS(plane, crtc), TP_STRUCT__entry( + __string(dev, __dev_name_kms(plane)) __field(enum pipe, pipe) __field(u32, frame) __field(u32, scanline) - __string(name, plane->name) + __string(name, plane->base.name) ), TP_fast_assign( - __assign_str(name, plane->name); + __assign_str(dev, __dev_name_kms(plane)); + __assign_str(name, plane->base.name); __entry->pipe = crtc->pipe; __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); ), - TP_printk("pipe %c, plane %s, frame=%u, scanline=%u", - pipe_name(__entry->pipe), __get_str(name), + TP_printk("dev %s, pipe %c, plane %s, frame=%u, scanline=%u", + __get_str(dev), pipe_name(__entry->pipe), __get_str(name), __entry->frame, __entry->scanline) ); @@ -369,6 +400,8 @@ TRACE_EVENT(intel_fbc_activate, TP_ARGS(plane), TP_STRUCT__entry( + __string(dev, __dev_name_kms(plane)) + __string(name, plane->base.name) __field(enum pipe, pipe) __field(u32, frame) __field(u32, scanline) @@ -377,13 +410,16 @@ TRACE_EVENT(intel_fbc_activate, TP_fast_assign( struct intel_crtc *crtc = intel_crtc_for_pipe(to_i915(plane->base.dev), plane->pipe); + __assign_str(dev, __dev_name_kms(plane)); + __assign_str(name, plane->base.name) __entry->pipe = crtc->pipe; __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); ), - TP_printk("pipe %c, frame=%u, scanline=%u", - pipe_name(__entry->pipe), __entry->frame, __entry->scanline) + TP_printk("dev %s, pipe %c, plane %s, frame=%u, scanline=%u", + __get_str(dev), pipe_name(__entry->pipe), __get_str(name), + __entry->frame, __entry->scanline) ); TRACE_EVENT(intel_fbc_deactivate, @@ -391,6 +427,8 @@ TRACE_EVENT(intel_fbc_deactivate, TP_ARGS(plane), TP_STRUCT__entry( + __string(dev, __dev_name_kms(plane)) + __string(name, plane->base.name) __field(enum pipe, pipe) __field(u32, frame) __field(u32, scanline) @@ -399,13 +437,16 @@ TRACE_EVENT(intel_fbc_deactivate, TP_fast_assign( struct intel_crtc *crtc = intel_crtc_for_pipe(to_i915(plane->base.dev), plane->pipe); + __assign_str(dev, __dev_name_kms(plane)); + __assign_str(name, plane->base.name) __entry->pipe = crtc->pipe; __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); ), - TP_printk("pipe %c, frame=%u, scanline=%u", - pipe_name(__entry->pipe), __entry->frame, __entry->scanline) + TP_printk("dev %s, pipe %c, plane %s, frame=%u, scanline=%u", + __get_str(dev), pipe_name(__entry->pipe), __get_str(name), + __entry->frame, __entry->scanline) ); TRACE_EVENT(intel_fbc_nuke, @@ -413,6 +454,8 @@ TRACE_EVENT(intel_fbc_nuke, TP_ARGS(plane), TP_STRUCT__entry( + __string(dev, __dev_name_kms(plane)) + __string(name, plane->base.name) __field(enum pipe, pipe) __field(u32, frame) __field(u32, scanline) @@ -421,13 +464,16 @@ TRACE_EVENT(intel_fbc_nuke, TP_fast_assign( struct intel_crtc *crtc = intel_crtc_for_pipe(to_i915(plane->base.dev), plane->pipe); + __assign_str(dev, __dev_name_kms(plane)); + __assign_str(name, plane->base.name) __entry->pipe = crtc->pipe; __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); ), - TP_printk("pipe %c, frame=%u, scanline=%u", - pipe_name(__entry->pipe), __entry->frame, __entry->scanline) + TP_printk("dev %s, pipe %c, plane %s, frame=%u, scanline=%u", + __get_str(dev), pipe_name(__entry->pipe), __get_str(name), + __entry->frame, __entry->scanline) ); TRACE_EVENT(intel_crtc_vblank_work_start, @@ -435,20 +481,22 @@ TRACE_EVENT(intel_crtc_vblank_work_start, TP_ARGS(crtc), TP_STRUCT__entry( + __string(dev, __dev_name_kms(crtc)) __field(enum pipe, pipe) __field(u32, frame) __field(u32, scanline) ), TP_fast_assign( + __assign_str(dev, __dev_name_kms(crtc)); __entry->pipe = crtc->pipe; __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); ), - TP_printk("pipe %c, frame=%u, scanline=%u", - pipe_name(__entry->pipe), __entry->frame, - __entry->scanline) + TP_printk("dev %s, pipe %c, frame=%u, scanline=%u", + __get_str(dev), pipe_name(__entry->pipe), + __entry->frame, __entry->scanline) ); TRACE_EVENT(intel_crtc_vblank_work_end, @@ -456,20 +504,22 @@ TRACE_EVENT(intel_crtc_vblank_work_end, TP_ARGS(crtc), TP_STRUCT__entry( + __string(dev, __dev_name_kms(crtc)) __field(enum pipe, pipe) __field(u32, frame) __field(u32, scanline) ), TP_fast_assign( + __assign_str(dev, __dev_name_kms(crtc)); __entry->pipe = crtc->pipe; __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); ), - TP_printk("pipe %c, frame=%u, scanline=%u", - pipe_name(__entry->pipe), __entry->frame, - __entry->scanline) + TP_printk("dev %s, pipe %c, frame=%u, scanline=%u", + __get_str(dev), pipe_name(__entry->pipe), + __entry->frame, __entry->scanline) ); TRACE_EVENT(intel_pipe_update_start, @@ -477,6 +527,7 @@ TRACE_EVENT(intel_pipe_update_start, TP_ARGS(crtc), TP_STRUCT__entry( + __string(dev, __dev_name_kms(crtc)) __field(enum pipe, pipe) __field(u32, frame) __field(u32, scanline) @@ -485,6 +536,7 @@ TRACE_EVENT(intel_pipe_update_start, ), TP_fast_assign( + __assign_str(dev, __dev_name_kms(crtc)); __entry->pipe = crtc->pipe; __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); @@ -492,9 +544,10 @@ TRACE_EVENT(intel_pipe_update_start, __entry->max = crtc->debug.max_vbl; ), - TP_printk("pipe %c, frame=%u, scanline=%u, min=%u, max=%u", - pipe_name(__entry->pipe), __entry->frame, - __entry->scanline, __entry->min, __entry->max) + TP_printk("dev %s, pipe %c, frame=%u, scanline=%u, min=%u, max=%u", + __get_str(dev), pipe_name(__entry->pipe), + __entry->frame, __entry->scanline, + __entry->min, __entry->max) ); TRACE_EVENT(intel_pipe_update_vblank_evaded, @@ -502,6 +555,7 @@ TRACE_EVENT(intel_pipe_update_vblank_evaded, TP_ARGS(crtc), TP_STRUCT__entry( + __string(dev, __dev_name_kms(crtc)) __field(enum pipe, pipe) __field(u32, frame) __field(u32, scanline) @@ -510,6 +564,7 @@ TRACE_EVENT(intel_pipe_update_vblank_evaded, ), TP_fast_assign( + __assign_str(dev, __dev_name_kms(crtc)); __entry->pipe = crtc->pipe; __entry->frame = crtc->debug.start_vbl_count; __entry->scanline = crtc->debug.scanline_start; @@ -517,9 +572,10 @@ TRACE_EVENT(intel_pipe_update_vblank_evaded, __entry->max = crtc->debug.max_vbl; ), - TP_printk("pipe %c, frame=%u, scanline=%u, min=%u, max=%u", - pipe_name(__entry->pipe), __entry->frame, - __entry->scanline, __entry->min, __entry->max) + TP_printk("dev %s, pipe %c, frame=%u, scanline=%u, min=%u, max=%u", + __get_str(dev), pipe_name(__entry->pipe), + __entry->frame, __entry->scanline, + __entry->min, __entry->max) ); TRACE_EVENT(intel_pipe_update_end, @@ -527,56 +583,64 @@ TRACE_EVENT(intel_pipe_update_end, TP_ARGS(crtc, frame, scanline_end), TP_STRUCT__entry( + __string(dev, __dev_name_kms(crtc)) __field(enum pipe, pipe) __field(u32, frame) __field(u32, scanline) ), TP_fast_assign( + __assign_str(dev, __dev_name_kms(crtc)); __entry->pipe = crtc->pipe; __entry->frame = frame; __entry->scanline = scanline_end; ), - TP_printk("pipe %c, frame=%u, scanline=%u", - pipe_name(__entry->pipe), __entry->frame, - __entry->scanline) + TP_printk("dev %s, pipe %c, frame=%u, scanline=%u", + __get_str(dev), pipe_name(__entry->pipe), + __entry->frame, __entry->scanline) ); TRACE_EVENT(intel_frontbuffer_invalidate, - TP_PROTO(unsigned int frontbuffer_bits, unsigned int origin), - TP_ARGS(frontbuffer_bits, origin), + TP_PROTO(struct drm_i915_private *i915, + unsigned int frontbuffer_bits, unsigned int origin), + TP_ARGS(i915, frontbuffer_bits, origin), TP_STRUCT__entry( + __string(dev, __dev_name_i915(i915)) __field(unsigned int, frontbuffer_bits) __field(unsigned int, origin) ), TP_fast_assign( + __assign_str(dev, __dev_name_i915(i915)); __entry->frontbuffer_bits = frontbuffer_bits; __entry->origin = origin; ), - TP_printk("frontbuffer_bits=0x%08x, origin=%u", - __entry->frontbuffer_bits, __entry->origin) + TP_printk("dev %s, frontbuffer_bits=0x%08x, origin=%u", + __get_str(dev), __entry->frontbuffer_bits, __entry->origin) ); TRACE_EVENT(intel_frontbuffer_flush, - TP_PROTO(unsigned int frontbuffer_bits, unsigned int origin), - TP_ARGS(frontbuffer_bits, origin), + TP_PROTO(struct drm_i915_private *i915, + unsigned int frontbuffer_bits, unsigned int origin), + TP_ARGS(i915, frontbuffer_bits, origin), TP_STRUCT__entry( + __string(dev, __dev_name_i915(i915)) __field(unsigned int, frontbuffer_bits) __field(unsigned int, origin) ), TP_fast_assign( + __assign_str(dev, __dev_name_i915(i915)); __entry->frontbuffer_bits = frontbuffer_bits; __entry->origin = origin; ), - TP_printk("frontbuffer_bits=0x%08x, origin=%u", - __entry->frontbuffer_bits, __entry->origin) + TP_printk("dev %s, frontbuffer_bits=0x%08x, origin=%u", + __get_str(dev), __entry->frontbuffer_bits, __entry->origin) ); #endif /* __INTEL_DISPLAY_TRACE_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h index 298d00a11f47..f07395065a69 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -969,6 +969,15 @@ struct intel_mpllb_state { u32 mpllb_sscstep; }; +/* Used by dp and fdi links */ +struct intel_link_m_n { + u32 tu; + u32 data_m; + u32 data_n; + u32 link_m; + u32 link_n; +}; + struct intel_crtc_state { /* * uapi (drm) state. This is the software state shown to userspace. @@ -1001,11 +1010,15 @@ struct intel_crtc_state { */ struct { bool active, enable; + /* logical state of LUTs */ struct drm_property_blob *degamma_lut, *gamma_lut, *ctm; struct drm_display_mode mode, pipe_mode, adjusted_mode; enum drm_scaling_filter scaling_filter; } hw; + /* actual state of LUTs */ + struct drm_property_blob *pre_csc_lut, *post_csc_lut; + /** * quirks - bitfield with hw state readout quirks * @@ -1362,6 +1375,7 @@ struct intel_crtc { u16 vmax_vblank_start; struct intel_display_power_domain_set enabled_power_domains; + struct intel_display_power_domain_set hw_readout_power_domains; struct intel_overlay *overlay; struct intel_crtc_state *config; @@ -1799,51 +1813,6 @@ struct intel_dp_mst_encoder { struct intel_connector *connector; }; -static inline enum dpio_channel -vlv_dig_port_to_channel(struct intel_digital_port *dig_port) -{ - switch (dig_port->base.port) { - default: - MISSING_CASE(dig_port->base.port); - fallthrough; - case PORT_B: - case PORT_D: - return DPIO_CH0; - case PORT_C: - return DPIO_CH1; - } -} - -static inline enum dpio_phy -vlv_dig_port_to_phy(struct intel_digital_port *dig_port) -{ - switch (dig_port->base.port) { - default: - MISSING_CASE(dig_port->base.port); - fallthrough; - case PORT_B: - case PORT_C: - return DPIO_PHY0; - case PORT_D: - return DPIO_PHY1; - } -} - -static inline enum dpio_channel -vlv_pipe_to_channel(enum pipe pipe) -{ - switch (pipe) { - default: - MISSING_CASE(pipe); - fallthrough; - case PIPE_A: - case PIPE_C: - return DPIO_CH0; - case PIPE_B: - return DPIO_CH1; - } -} - struct intel_load_detect_pipe { struct drm_atomic_state *restore_state; }; @@ -2040,15 +2009,16 @@ static inline bool intel_crtc_has_type(const struct intel_crtc_state *crtc_state, enum intel_output_type type) { - return crtc_state->output_types & (1 << type); + return crtc_state->output_types & BIT(type); } + static inline bool intel_crtc_has_dp_encoder(const struct intel_crtc_state *crtc_state) { return crtc_state->output_types & - ((1 << INTEL_OUTPUT_DP) | - (1 << INTEL_OUTPUT_DP_MST) | - (1 << INTEL_OUTPUT_EDP)); + (BIT(INTEL_OUTPUT_DP) | + BIT(INTEL_OUTPUT_DP_MST) | + BIT(INTEL_OUTPUT_EDP)); } static inline bool @@ -2057,6 +2027,20 @@ intel_crtc_needs_modeset(const struct intel_crtc_state *crtc_state) return drm_atomic_crtc_needs_modeset(&crtc_state->uapi); } +static inline bool +intel_crtc_needs_fastset(const struct intel_crtc_state *crtc_state) +{ + return crtc_state->update_pipe; +} + +static inline bool +intel_crtc_needs_color_update(const struct intel_crtc_state *crtc_state) +{ + return crtc_state->uapi.color_mgmt_changed || + intel_crtc_needs_fastset(crtc_state) || + intel_crtc_needs_modeset(crtc_state); +} + static inline u32 intel_plane_ggtt_offset(const struct intel_plane_state *plane_state) { return i915_ggtt_offset(plane_state->ggtt_vma); diff --git a/drivers/gpu/drm/i915/display/intel_dkl_phy.c b/drivers/gpu/drm/i915/display/intel_dkl_phy.c index 710b030c7ed5..57cc3edba016 100644 --- a/drivers/gpu/drm/i915/display/intel_dkl_phy.c +++ b/drivers/gpu/drm/i915/display/intel_dkl_phy.c @@ -9,9 +9,10 @@ #include "intel_de.h" #include "intel_display.h" #include "intel_dkl_phy.h" +#include "intel_dkl_phy_regs.h" static void -dkl_phy_set_hip_idx(struct drm_i915_private *i915, i915_reg_t reg, int idx) +dkl_phy_set_hip_idx(struct drm_i915_private *i915, struct intel_dkl_phy_reg reg) { enum tc_port tc_port = DKL_REG_TC_PORT(reg); @@ -19,28 +20,27 @@ dkl_phy_set_hip_idx(struct drm_i915_private *i915, i915_reg_t reg, int idx) intel_de_write(i915, HIP_INDEX_REG(tc_port), - HIP_INDEX_VAL(tc_port, idx)); + HIP_INDEX_VAL(tc_port, reg.bank_idx)); } /** * intel_dkl_phy_read - read a Dekel PHY register * @i915: i915 device instance * @reg: Dekel PHY register - * @ln: lane instance of @reg * * Read the @reg Dekel PHY register. * * Returns the read value. */ u32 -intel_dkl_phy_read(struct drm_i915_private *i915, i915_reg_t reg, int ln) +intel_dkl_phy_read(struct drm_i915_private *i915, struct intel_dkl_phy_reg reg) { u32 val; spin_lock(&i915->display.dkl.phy_lock); - dkl_phy_set_hip_idx(i915, reg, ln); - val = intel_de_read(i915, reg); + dkl_phy_set_hip_idx(i915, reg); + val = intel_de_read(i915, DKL_REG_MMIO(reg)); spin_unlock(&i915->display.dkl.phy_lock); @@ -51,18 +51,17 @@ intel_dkl_phy_read(struct drm_i915_private *i915, i915_reg_t reg, int ln) * intel_dkl_phy_write - write a Dekel PHY register * @i915: i915 device instance * @reg: Dekel PHY register - * @ln: lane instance of @reg * @val: value to write * * Write @val to the @reg Dekel PHY register. */ void -intel_dkl_phy_write(struct drm_i915_private *i915, i915_reg_t reg, int ln, u32 val) +intel_dkl_phy_write(struct drm_i915_private *i915, struct intel_dkl_phy_reg reg, u32 val) { spin_lock(&i915->display.dkl.phy_lock); - dkl_phy_set_hip_idx(i915, reg, ln); - intel_de_write(i915, reg, val); + dkl_phy_set_hip_idx(i915, reg); + intel_de_write(i915, DKL_REG_MMIO(reg), val); spin_unlock(&i915->display.dkl.phy_lock); } @@ -71,7 +70,6 @@ intel_dkl_phy_write(struct drm_i915_private *i915, i915_reg_t reg, int ln, u32 v * intel_dkl_phy_rmw - read-modify-write a Dekel PHY register * @i915: i915 device instance * @reg: Dekel PHY register - * @ln: lane instance of @reg * @clear: mask to clear * @set: mask to set * @@ -79,12 +77,12 @@ intel_dkl_phy_write(struct drm_i915_private *i915, i915_reg_t reg, int ln, u32 v * this value back to the register if the value differs from the read one. */ void -intel_dkl_phy_rmw(struct drm_i915_private *i915, i915_reg_t reg, int ln, u32 clear, u32 set) +intel_dkl_phy_rmw(struct drm_i915_private *i915, struct intel_dkl_phy_reg reg, u32 clear, u32 set) { spin_lock(&i915->display.dkl.phy_lock); - dkl_phy_set_hip_idx(i915, reg, ln); - intel_de_rmw(i915, reg, clear, set); + dkl_phy_set_hip_idx(i915, reg); + intel_de_rmw(i915, DKL_REG_MMIO(reg), clear, set); spin_unlock(&i915->display.dkl.phy_lock); } @@ -93,17 +91,16 @@ intel_dkl_phy_rmw(struct drm_i915_private *i915, i915_reg_t reg, int ln, u32 cle * intel_dkl_phy_posting_read - do a posting read from a Dekel PHY register * @i915: i915 device instance * @reg: Dekel PHY register - * @ln: lane instance of @reg * * Read the @reg Dekel PHY register without returning the read value. */ void -intel_dkl_phy_posting_read(struct drm_i915_private *i915, i915_reg_t reg, int ln) +intel_dkl_phy_posting_read(struct drm_i915_private *i915, struct intel_dkl_phy_reg reg) { spin_lock(&i915->display.dkl.phy_lock); - dkl_phy_set_hip_idx(i915, reg, ln); - intel_de_posting_read(i915, reg); + dkl_phy_set_hip_idx(i915, reg); + intel_de_posting_read(i915, DKL_REG_MMIO(reg)); spin_unlock(&i915->display.dkl.phy_lock); } diff --git a/drivers/gpu/drm/i915/display/intel_dkl_phy.h b/drivers/gpu/drm/i915/display/intel_dkl_phy.h index 260ad121a0b1..570ee36f9386 100644 --- a/drivers/gpu/drm/i915/display/intel_dkl_phy.h +++ b/drivers/gpu/drm/i915/display/intel_dkl_phy.h @@ -8,17 +8,17 @@ #include <linux/types.h> -#include "i915_reg_defs.h" +#include "intel_dkl_phy_regs.h" struct drm_i915_private; u32 -intel_dkl_phy_read(struct drm_i915_private *i915, i915_reg_t reg, int ln); +intel_dkl_phy_read(struct drm_i915_private *i915, struct intel_dkl_phy_reg reg); void -intel_dkl_phy_write(struct drm_i915_private *i915, i915_reg_t reg, int ln, u32 val); +intel_dkl_phy_write(struct drm_i915_private *i915, struct intel_dkl_phy_reg reg, u32 val); void -intel_dkl_phy_rmw(struct drm_i915_private *i915, i915_reg_t reg, int ln, u32 clear, u32 set); +intel_dkl_phy_rmw(struct drm_i915_private *i915, struct intel_dkl_phy_reg reg, u32 clear, u32 set); void -intel_dkl_phy_posting_read(struct drm_i915_private *i915, i915_reg_t reg, int ln); +intel_dkl_phy_posting_read(struct drm_i915_private *i915, struct intel_dkl_phy_reg reg); #endif /* __INTEL_DKL_PHY_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_dkl_phy_regs.h b/drivers/gpu/drm/i915/display/intel_dkl_phy_regs.h new file mode 100644 index 000000000000..56085b32956d --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_dkl_phy_regs.h @@ -0,0 +1,204 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2022 Intel Corporation + */ + +#ifndef __INTEL_DKL_PHY_REGS__ +#define __INTEL_DKL_PHY_REGS__ + +#include <linux/types.h> + +struct intel_dkl_phy_reg { + u32 reg:24; + u32 bank_idx:4; +}; + +#define _DKL_PHY1_BASE 0x168000 +#define _DKL_PHY2_BASE 0x169000 +#define _DKL_PHY3_BASE 0x16A000 +#define _DKL_PHY4_BASE 0x16B000 +#define _DKL_PHY5_BASE 0x16C000 +#define _DKL_PHY6_BASE 0x16D000 + +#define DKL_REG_TC_PORT(__reg) \ + (TC_PORT_1 + ((__reg).reg - _DKL_PHY1_BASE) / (_DKL_PHY2_BASE - _DKL_PHY1_BASE)) + +/* DEKEL PHY MMIO Address = Phy base + (internal address & ~index_mask) */ +#define DKL_REG_MMIO(__reg) _MMIO((__reg).reg) + +#define _DKL_REG_PHY_BASE(tc_port) _PORT(tc_port, \ + _DKL_PHY1_BASE, \ + _DKL_PHY2_BASE) + +#define _DKL_BANK_SHIFT 12 +#define _DKL_REG_BANK_OFFSET(phy_offset) \ + ((phy_offset) & ((1 << _DKL_BANK_SHIFT) - 1)) +#define _DKL_REG_BANK_IDX(phy_offset) \ + (((phy_offset) >> _DKL_BANK_SHIFT) & 0xf) + +#define _DKL_REG(tc_port, phy_offset) \ + ((const struct intel_dkl_phy_reg) { \ + .reg = _DKL_REG_PHY_BASE(tc_port) + \ + _DKL_REG_BANK_OFFSET(phy_offset), \ + .bank_idx = _DKL_REG_BANK_IDX(phy_offset), \ + }) + +#define _DKL_REG_LN(tc_port, ln_idx, ln0_offs, ln1_offs) \ + _DKL_REG(tc_port, (ln0_offs) + (ln_idx) * ((ln1_offs) - (ln0_offs))) + +#define _DKL_PCS_DW5_LN0 0x0014 +#define _DKL_PCS_DW5_LN1 0x1014 +#define DKL_PCS_DW5(tc_port, ln) _DKL_REG_LN(tc_port, ln, \ + _DKL_PCS_DW5_LN0, \ + _DKL_PCS_DW5_LN1) +#define DKL_PCS_DW5_CORE_SOFTRESET REG_BIT(11) + +#define _DKL_PLL_DIV0 0x2200 +#define DKL_PLL_DIV0(tc_port) _DKL_REG(tc_port, \ + _DKL_PLL_DIV0) +#define DKL_PLL_DIV0_AFC_STARTUP_MASK REG_GENMASK(27, 25) +#define DKL_PLL_DIV0_AFC_STARTUP(val) REG_FIELD_PREP(DKL_PLL_DIV0_AFC_STARTUP_MASK, (val)) +#define DKL_PLL_DIV0_INTEG_COEFF(x) ((x) << 16) +#define DKL_PLL_DIV0_INTEG_COEFF_MASK (0x1F << 16) +#define DKL_PLL_DIV0_PROP_COEFF(x) ((x) << 12) +#define DKL_PLL_DIV0_PROP_COEFF_MASK (0xF << 12) +#define DKL_PLL_DIV0_FBPREDIV_SHIFT (8) +#define DKL_PLL_DIV0_FBPREDIV(x) ((x) << DKL_PLL_DIV0_FBPREDIV_SHIFT) +#define DKL_PLL_DIV0_FBPREDIV_MASK (0xF << DKL_PLL_DIV0_FBPREDIV_SHIFT) +#define DKL_PLL_DIV0_FBDIV_INT(x) ((x) << 0) +#define DKL_PLL_DIV0_FBDIV_INT_MASK (0xFF << 0) +#define DKL_PLL_DIV0_MASK (DKL_PLL_DIV0_INTEG_COEFF_MASK | \ + DKL_PLL_DIV0_PROP_COEFF_MASK | \ + DKL_PLL_DIV0_FBPREDIV_MASK | \ + DKL_PLL_DIV0_FBDIV_INT_MASK) + +#define _DKL_PLL_DIV1 0x2204 +#define DKL_PLL_DIV1(tc_port) _DKL_REG(tc_port, \ + _DKL_PLL_DIV1) +#define DKL_PLL_DIV1_IREF_TRIM(x) ((x) << 16) +#define DKL_PLL_DIV1_IREF_TRIM_MASK (0x1F << 16) +#define DKL_PLL_DIV1_TDC_TARGET_CNT(x) ((x) << 0) +#define DKL_PLL_DIV1_TDC_TARGET_CNT_MASK (0xFF << 0) + +#define _DKL_PLL_SSC 0x2210 +#define DKL_PLL_SSC(tc_port) _DKL_REG(tc_port, \ + _DKL_PLL_SSC) +#define DKL_PLL_SSC_IREF_NDIV_RATIO(x) ((x) << 29) +#define DKL_PLL_SSC_IREF_NDIV_RATIO_MASK (0x7 << 29) +#define DKL_PLL_SSC_STEP_LEN(x) ((x) << 16) +#define DKL_PLL_SSC_STEP_LEN_MASK (0xFF << 16) +#define DKL_PLL_SSC_STEP_NUM(x) ((x) << 11) +#define DKL_PLL_SSC_STEP_NUM_MASK (0x7 << 11) +#define DKL_PLL_SSC_EN (1 << 9) + +#define _DKL_PLL_BIAS 0x2214 +#define DKL_PLL_BIAS(tc_port) _DKL_REG(tc_port, \ + _DKL_PLL_BIAS) +#define DKL_PLL_BIAS_FRAC_EN_H (1 << 30) +#define DKL_PLL_BIAS_FBDIV_SHIFT (8) +#define DKL_PLL_BIAS_FBDIV_FRAC(x) ((x) << DKL_PLL_BIAS_FBDIV_SHIFT) +#define DKL_PLL_BIAS_FBDIV_FRAC_MASK (0x3FFFFF << DKL_PLL_BIAS_FBDIV_SHIFT) + +#define _DKL_PLL_TDC_COLDST_BIAS 0x2218 +#define DKL_PLL_TDC_COLDST_BIAS(tc_port) _DKL_REG(tc_port, \ + _DKL_PLL_TDC_COLDST_BIAS) +#define DKL_PLL_TDC_SSC_STEP_SIZE(x) ((x) << 8) +#define DKL_PLL_TDC_SSC_STEP_SIZE_MASK (0xFF << 8) +#define DKL_PLL_TDC_FEED_FWD_GAIN(x) ((x) << 0) +#define DKL_PLL_TDC_FEED_FWD_GAIN_MASK (0xFF << 0) + +#define _DKL_REFCLKIN_CTL 0x212C +#define DKL_REFCLKIN_CTL(tc_port) _DKL_REG(tc_port, \ + _DKL_REFCLKIN_CTL) +/* Bits are the same as MG_REFCLKIN_CTL */ + +#define _DKL_CLKTOP2_HSCLKCTL 0x20D4 +#define DKL_CLKTOP2_HSCLKCTL(rc_port) _DKL_REG(tc_port, \ + _DKL_CLKTOP2_HSCLKCTL) +/* Bits are the same as MG_CLKTOP2_HSCLKCTL */ + +#define _DKL_CLKTOP2_CORECLKCTL1 0x20D8 +#define DKL_CLKTOP2_CORECLKCTL1(tc_port) _DKL_REG(tc_port, \ + _DKL_CLKTOP2_CORECLKCTL1) +/* Bits are the same as MG_CLKTOP2_CORECLKCTL1 */ + +#define _DKL_TX_DPCNTL0_LN0 0x02C0 +#define _DKL_TX_DPCNTL0_LN1 0x12C0 +#define DKL_TX_DPCNTL0(tc_port, ln) _DKL_REG_LN(tc_port, ln, \ + _DKL_TX_DPCNTL0_LN0, \ + _DKL_TX_DPCNTL0_LN1) +#define DKL_TX_PRESHOOT_COEFF(x) ((x) << 13) +#define DKL_TX_PRESHOOT_COEFF_MASK (0x1f << 13) +#define DKL_TX_DE_EMPHASIS_COEFF(x) ((x) << 8) +#define DKL_TX_DE_EMPAHSIS_COEFF_MASK (0x1f << 8) +#define DKL_TX_VSWING_CONTROL(x) ((x) << 0) +#define DKL_TX_VSWING_CONTROL_MASK (0x7 << 0) + +#define _DKL_TX_DPCNTL1_LN0 0x02C4 +#define _DKL_TX_DPCNTL1_LN1 0x12C4 +#define DKL_TX_DPCNTL1(tc_port, ln) _DKL_REG_LN(tc_port, ln, \ + _DKL_TX_DPCNTL1_LN0, \ + _DKL_TX_DPCNTL1_LN1) +/* Bits are the same as DKL_TX_DPCNTRL0 */ + +#define _DKL_TX_DPCNTL2_LN0 0x02C8 +#define _DKL_TX_DPCNTL2_LN1 0x12C8 +#define DKL_TX_DPCNTL2(tc_port, ln) _DKL_REG_LN(tc_port, ln, \ + _DKL_TX_DPCNTL2_LN0, \ + _DKL_TX_DPCNTL2_LN1) +#define DKL_TX_DP20BITMODE REG_BIT(2) +#define DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1_MASK REG_GENMASK(4, 3) +#define DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1(val) REG_FIELD_PREP(DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1_MASK, (val)) +#define DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2_MASK REG_GENMASK(6, 5) +#define DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2(val) REG_FIELD_PREP(DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2_MASK, (val)) + +#define _DKL_TX_FW_CALIB_LN0 0x02F8 +#define _DKL_TX_FW_CALIB_LN1 0x12F8 +#define DKL_TX_FW_CALIB(tc_port, ln) _DKL_REG_LN(tc_port, ln, \ + _DKL_TX_FW_CALIB_LN0, \ + _DKL_TX_FW_CALIB_LN1) +#define DKL_TX_CFG_DISABLE_WAIT_INIT (1 << 7) + +#define _DKL_TX_PMD_LANE_SUS_LN0 0x0D00 +#define _DKL_TX_PMD_LANE_SUS_LN1 0x1D00 +#define DKL_TX_PMD_LANE_SUS(tc_port, ln) _DKL_REG_LN(tc_port, ln, \ + _DKL_TX_PMD_LANE_SUS_LN0, \ + _DKL_TX_PMD_LANE_SUS_LN1) + +#define _DKL_TX_DW17_LN0 0x0DC4 +#define _DKL_TX_DW17_LN1 0x1DC4 +#define DKL_TX_DW17(tc_port, ln) _DKL_REG_LN(tc_port, ln, \ + _DKL_TX_DW17_LN0, \ + _DKL_TX_DW17_LN1) + +#define _DKL_TX_DW18_LN0 0x0DC8 +#define _DKL_TX_DW18_LN1 0x1DC8 +#define DKL_TX_DW18(tc_port, ln) _DKL_REG_LN(tc_port, ln, \ + _DKL_TX_DW18_LN0, \ + _DKL_TX_DW18_LN1) + +#define _DKL_DP_MODE_LN0 0x00A0 +#define _DKL_DP_MODE_LN1 0x10A0 +#define DKL_DP_MODE(tc_port, ln) _DKL_REG_LN(tc_port, ln, \ + _DKL_DP_MODE_LN0, \ + _DKL_DP_MODE_LN1) + +#define _DKL_CMN_UC_DW27 0x236C +#define DKL_CMN_UC_DW_27(tc_port) _DKL_REG(tc_port, \ + _DKL_CMN_UC_DW27) +#define DKL_CMN_UC_DW27_UC_HEALTH (0x1 << 15) + +/* + * Each Dekel PHY is addressed through a 4KB aperture. Each PHY has more than + * 4KB of register space, so a separate index is programmed in HIP_INDEX_REG0 + * or HIP_INDEX_REG1, based on the port number, to set the upper 2 address + * bits that point the 4KB window into the full PHY register space. + */ +#define _HIP_INDEX_REG0 0x1010A0 +#define _HIP_INDEX_REG1 0x1010A4 +#define HIP_INDEX_REG(tc_port) _MMIO((tc_port) < 4 ? _HIP_INDEX_REG0 \ + : _HIP_INDEX_REG1) +#define _HIP_INDEX_SHIFT(tc_port) (8 * ((tc_port) % 4)) +#define HIP_INDEX_VAL(tc_port, val) ((val) << _HIP_INDEX_SHIFT(tc_port)) + +#endif /* __INTEL_DKL_PHY_REGS__ */ diff --git a/drivers/gpu/drm/i915/display/intel_dmc.c b/drivers/gpu/drm/i915/display/intel_dmc.c index e52ecc0738a6..eff3add70611 100644 --- a/drivers/gpu/drm/i915/display/intel_dmc.c +++ b/drivers/gpu/drm/i915/display/intel_dmc.c @@ -52,8 +52,8 @@ #define DISPLAY_VER12_DMC_MAX_FW_SIZE ICL_DMC_MAX_FW_SIZE -#define DG2_DMC_PATH DMC_PATH(dg2, 2, 07) -#define DG2_DMC_VERSION_REQUIRED DMC_VERSION(2, 07) +#define DG2_DMC_PATH DMC_PATH(dg2, 2, 08) +#define DG2_DMC_VERSION_REQUIRED DMC_VERSION(2, 8) MODULE_FIRMWARE(DG2_DMC_PATH); #define ADLP_DMC_PATH DMC_PATH(adlp, 2, 16) @@ -1065,12 +1065,13 @@ static int intel_dmc_debugfs_status_show(struct seq_file *m, void *unused) seq_printf(m, "fw loaded: %s\n", str_yes_no(intel_dmc_has_payload(i915))); seq_printf(m, "path: %s\n", dmc->fw_path); - seq_printf(m, "Pipe A fw support: %s\n", + seq_printf(m, "Pipe A fw needed: %s\n", str_yes_no(GRAPHICS_VER(i915) >= 12)); seq_printf(m, "Pipe A fw loaded: %s\n", str_yes_no(dmc->dmc_info[DMC_FW_PIPEA].payload)); - seq_printf(m, "Pipe B fw support: %s\n", - str_yes_no(IS_ALDERLAKE_P(i915))); + seq_printf(m, "Pipe B fw needed: %s\n", + str_yes_no(IS_ALDERLAKE_P(i915) || + DISPLAY_VER(i915) >= 14)); seq_printf(m, "Pipe B fw loaded: %s\n", str_yes_no(dmc->dmc_info[DMC_FW_PIPEB].payload)); @@ -1081,22 +1082,19 @@ static int intel_dmc_debugfs_status_show(struct seq_file *m, void *unused) DMC_VERSION_MINOR(dmc->version)); if (DISPLAY_VER(i915) >= 12) { - if (IS_DGFX(i915)) { + i915_reg_t dc3co_reg; + + if (IS_DGFX(i915) || DISPLAY_VER(i915) >= 14) { + dc3co_reg = DG1_DMC_DEBUG3; dc5_reg = DG1_DMC_DEBUG_DC5_COUNT; } else { + dc3co_reg = TGL_DMC_DEBUG3; dc5_reg = TGL_DMC_DEBUG_DC5_COUNT; dc6_reg = TGL_DMC_DEBUG_DC6_COUNT; } - /* - * NOTE: DMC_DEBUG3 is a general purpose reg. - * According to B.Specs:49196 DMC f/w reuses DC5/6 counter - * reg for DC3CO debugging and validation, - * but TGL DMC f/w is using DMC_DEBUG3 reg for DC3CO counter. - */ seq_printf(m, "DC3CO count: %d\n", - intel_de_read(i915, IS_DGFX(i915) ? - DG1_DMC_DEBUG3 : TGL_DMC_DEBUG3)); + intel_de_read(i915, dc3co_reg)); } else { dc5_reg = IS_BROXTON(i915) ? BXT_DMC_DC3_DC5_COUNT : SKL_DMC_DC3_DC5_COUNT; diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 2b5bc95a8b0d..75070eb07d4b 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -46,6 +46,7 @@ #include "g4x_dp.h" #include "i915_debugfs.h" #include "i915_drv.h" +#include "i915_reg.h" #include "intel_atomic.h" #include "intel_audio.h" #include "intel_backlight.h" @@ -2306,6 +2307,7 @@ bool intel_dp_initial_fastset_check(struct intel_encoder *encoder, { struct drm_i915_private *i915 = to_i915(encoder->base.dev); struct intel_dp *intel_dp = enc_to_intel_dp(encoder); + bool fastset = true; /* * If BIOS has set an unsupported or non-standard link rate for some @@ -2313,9 +2315,10 @@ bool intel_dp_initial_fastset_check(struct intel_encoder *encoder, */ if (intel_dp_rate_index(intel_dp->source_rates, intel_dp->num_source_rates, crtc_state->port_clock) < 0) { - drm_dbg_kms(&i915->drm, "Forcing full modeset due to unsupported link rate\n"); + drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s] Forcing full modeset due to unsupported link rate\n", + encoder->base.base.id, encoder->base.name); crtc_state->uapi.connectors_changed = true; - return false; + fastset = false; } /* @@ -2326,18 +2329,20 @@ bool intel_dp_initial_fastset_check(struct intel_encoder *encoder, * Remove once we have readout for DSC. */ if (crtc_state->dsc.compression_enable) { - drm_dbg_kms(&i915->drm, "Forcing full modeset due to DSC being enabled\n"); + drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s] Forcing full modeset due to DSC being enabled\n", + encoder->base.base.id, encoder->base.name); crtc_state->uapi.mode_changed = true; - return false; + fastset = false; } if (CAN_PSR(intel_dp)) { - drm_dbg_kms(&i915->drm, "Forcing full modeset to compute PSR state\n"); + drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s] Forcing full modeset to compute PSR state\n", + encoder->base.base.id, encoder->base.name); crtc_state->uapi.mode_changed = true; - return false; + fastset = false; } - return true; + return fastset; } static void intel_dp_get_pcon_dsc_cap(struct intel_dp *intel_dp) @@ -2686,7 +2691,6 @@ void intel_dp_configure_protocol_converter(struct intel_dp *intel_dp, str_enable_disable(tmp)); } - bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp) { u8 dprx = 0; @@ -3675,61 +3679,6 @@ static void intel_dp_phy_pattern_update(struct intel_dp *intel_dp, } } -static void -intel_dp_autotest_phy_ddi_disable(struct intel_dp *intel_dp, - const struct intel_crtc_state *crtc_state) -{ - struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); - struct drm_device *dev = dig_port->base.base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_crtc *crtc = to_intel_crtc(dig_port->base.base.crtc); - enum pipe pipe = crtc->pipe; - u32 trans_ddi_func_ctl_value, trans_conf_value, dp_tp_ctl_value; - - trans_ddi_func_ctl_value = intel_de_read(dev_priv, - TRANS_DDI_FUNC_CTL(pipe)); - trans_conf_value = intel_de_read(dev_priv, PIPECONF(pipe)); - dp_tp_ctl_value = intel_de_read(dev_priv, TGL_DP_TP_CTL(pipe)); - - trans_ddi_func_ctl_value &= ~(TRANS_DDI_FUNC_ENABLE | - TGL_TRANS_DDI_PORT_MASK); - trans_conf_value &= ~PIPECONF_ENABLE; - dp_tp_ctl_value &= ~DP_TP_CTL_ENABLE; - - intel_de_write(dev_priv, PIPECONF(pipe), trans_conf_value); - intel_de_write(dev_priv, TRANS_DDI_FUNC_CTL(pipe), - trans_ddi_func_ctl_value); - intel_de_write(dev_priv, TGL_DP_TP_CTL(pipe), dp_tp_ctl_value); -} - -static void -intel_dp_autotest_phy_ddi_enable(struct intel_dp *intel_dp, - const struct intel_crtc_state *crtc_state) -{ - struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); - struct drm_device *dev = dig_port->base.base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); - enum port port = dig_port->base.port; - struct intel_crtc *crtc = to_intel_crtc(dig_port->base.base.crtc); - enum pipe pipe = crtc->pipe; - u32 trans_ddi_func_ctl_value, trans_conf_value, dp_tp_ctl_value; - - trans_ddi_func_ctl_value = intel_de_read(dev_priv, - TRANS_DDI_FUNC_CTL(pipe)); - trans_conf_value = intel_de_read(dev_priv, PIPECONF(pipe)); - dp_tp_ctl_value = intel_de_read(dev_priv, TGL_DP_TP_CTL(pipe)); - - trans_ddi_func_ctl_value |= TRANS_DDI_FUNC_ENABLE | - TGL_TRANS_DDI_SELECT_PORT(port); - trans_conf_value |= PIPECONF_ENABLE; - dp_tp_ctl_value |= DP_TP_CTL_ENABLE; - - intel_de_write(dev_priv, PIPECONF(pipe), trans_conf_value); - intel_de_write(dev_priv, TGL_DP_TP_CTL(pipe), dp_tp_ctl_value); - intel_de_write(dev_priv, TRANS_DDI_FUNC_CTL(pipe), - trans_ddi_func_ctl_value); -} - static void intel_dp_process_phy_request(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state) { @@ -3748,14 +3697,10 @@ static void intel_dp_process_phy_request(struct intel_dp *intel_dp, intel_dp_get_adjust_train(intel_dp, crtc_state, DP_PHY_DPRX, link_status); - intel_dp_autotest_phy_ddi_disable(intel_dp, crtc_state); - intel_dp_set_signal_levels(intel_dp, crtc_state, DP_PHY_DPRX); intel_dp_phy_pattern_update(intel_dp, crtc_state); - intel_dp_autotest_phy_ddi_enable(intel_dp, crtc_state); - drm_dp_dpcd_write(&intel_dp->aux, DP_TRAINING_LANE0_SET, intel_dp->train_set, crtc_state->lane_count); @@ -4873,6 +4818,12 @@ void intel_dp_encoder_flush_work(struct drm_encoder *encoder) intel_pps_vdd_off_sync(intel_dp); + /* + * Ensure power off delay is respected on module remove, so that we can + * reduce delays at driver probe. See pps_init_timestamps(). + */ + intel_pps_wait_power_cycle(intel_dp); + intel_dp_aux_fini(intel_dp); } @@ -5174,19 +5125,6 @@ intel_dp_add_properties(struct intel_dp *intel_dp, struct drm_connector *connect if (has_gamut_metadata_dip(dev_priv, port)) drm_connector_attach_hdr_output_metadata_property(connector); - if (intel_dp_is_edp(intel_dp)) { - u32 allowed_scalers; - - allowed_scalers = BIT(DRM_MODE_SCALE_ASPECT) | BIT(DRM_MODE_SCALE_FULLSCREEN); - if (!HAS_GMCH(dev_priv)) - allowed_scalers |= BIT(DRM_MODE_SCALE_CENTER); - - drm_connector_attach_scaling_mode_property(connector, allowed_scalers); - - connector->state->scaling_mode = DRM_MODE_SCALE_ASPECT; - - } - if (HAS_VRR(dev_priv)) drm_connector_attach_vrr_capable_property(connector); } @@ -5199,8 +5137,7 @@ intel_edp_add_properties(struct intel_dp *intel_dp) const struct drm_display_mode *fixed_mode = intel_panel_preferred_fixed_mode(connector); - if (!fixed_mode) - return; + intel_attach_scaling_mode_property(&connector->base); drm_connector_set_panel_orientation_with_quirk(&connector->base, i915->display.vbt.orientation, @@ -5208,16 +5145,43 @@ intel_edp_add_properties(struct intel_dp *intel_dp) fixed_mode->vdisplay); } +static void intel_edp_backlight_setup(struct intel_dp *intel_dp, + struct intel_connector *connector) +{ + struct drm_i915_private *i915 = dp_to_i915(intel_dp); + enum pipe pipe = INVALID_PIPE; + + if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) { + /* + * Figure out the current pipe for the initial backlight setup. + * If the current pipe isn't valid, try the PPS pipe, and if that + * fails just assume pipe A. + */ + pipe = vlv_active_pipe(intel_dp); + + if (pipe != PIPE_A && pipe != PIPE_B) + pipe = intel_dp->pps.pps_pipe; + + if (pipe != PIPE_A && pipe != PIPE_B) + pipe = PIPE_A; + + drm_dbg_kms(&i915->drm, + "[CONNECTOR:%d:%s] using pipe %c for initial backlight setup\n", + connector->base.base.id, connector->base.name, + pipe_name(pipe)); + } + + intel_backlight_setup(connector, pipe); +} + static bool intel_edp_init_connector(struct intel_dp *intel_dp, struct intel_connector *intel_connector) { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); - struct drm_device *dev = &dev_priv->drm; struct drm_connector *connector = &intel_connector->base; struct drm_display_mode *fixed_mode; struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; bool has_dpcd; - enum pipe pipe = INVALID_PIPE; struct edid *edid; if (!intel_dp_is_edp(intel_dp)) @@ -5230,7 +5194,7 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp, * with an already powered-on LVDS power sequencer. */ if (intel_get_lvds_encoder(dev_priv)) { - drm_WARN_ON(dev, + drm_WARN_ON(&dev_priv->drm, !(HAS_PCH_IBX(dev_priv) || HAS_PCH_CPT(dev_priv))); drm_info(&dev_priv->drm, "LVDS was detected, not registering eDP\n"); @@ -5246,11 +5210,12 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp, if (!has_dpcd) { /* if this fails, presume the device is a ghost */ drm_info(&dev_priv->drm, - "failed to retrieve link info, disabling eDP\n"); + "[ENCODER:%d:%s] failed to retrieve link info, disabling eDP\n", + encoder->base.base.id, encoder->base.name); goto out_vdd_off; } - mutex_lock(&dev->mode_config.mutex); + mutex_lock(&dev_priv->drm.mode_config.mutex); edid = drm_get_edid(connector, &intel_dp->aux.ddc); if (!edid) { /* Fallback to EDID from ACPI OpRegion, if any */ @@ -5275,9 +5240,7 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp, intel_bios_init_panel(dev_priv, &intel_connector->panel, encoder->devdata, IS_ERR(edid) ? NULL : edid); - intel_panel_add_edid_fixed_modes(intel_connector, - intel_connector->panel.vbt.drrs_type != DRRS_TYPE_NONE || - intel_vrr_is_capable(intel_connector)); + intel_panel_add_edid_fixed_modes(intel_connector, true); /* MSO requires information from the EDID */ intel_edp_mso_init(intel_dp); @@ -5290,30 +5253,18 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp, if (!intel_panel_preferred_fixed_mode(intel_connector)) intel_panel_add_vbt_lfp_fixed_mode(intel_connector); - mutex_unlock(&dev->mode_config.mutex); - - if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { - /* - * Figure out the current pipe for the initial backlight setup. - * If the current pipe isn't valid, try the PPS pipe, and if that - * fails just assume pipe A. - */ - pipe = vlv_active_pipe(intel_dp); - - if (pipe != PIPE_A && pipe != PIPE_B) - pipe = intel_dp->pps.pps_pipe; - - if (pipe != PIPE_A && pipe != PIPE_B) - pipe = PIPE_A; + mutex_unlock(&dev_priv->drm.mode_config.mutex); - drm_dbg_kms(&dev_priv->drm, - "using pipe %c for initial backlight setup\n", - pipe_name(pipe)); + if (!intel_panel_preferred_fixed_mode(intel_connector)) { + drm_info(&dev_priv->drm, + "[ENCODER:%d:%s] failed to find fixed mode for the panel, disabling eDP\n", + encoder->base.base.id, encoder->base.name); + goto out_vdd_off; } intel_panel_init(intel_connector); - intel_backlight_setup(intel_connector, pipe); + intel_edp_backlight_setup(intel_dp, intel_connector); intel_edp_add_properties(intel_dp); @@ -5415,7 +5366,6 @@ intel_dp_init_connector(struct intel_digital_port *dig_port, if (!HAS_GMCH(dev_priv)) connector->interlace_allowed = true; - connector->doublescan_allowed = 0; intel_connector->polled = DRM_CONNECTOR_POLL_HPD; diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux.c b/drivers/gpu/drm/i915/display/intel_dp_aux.c index 48c375c65a41..664bebdecea7 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_aux.c +++ b/drivers/gpu/drm/i915/display/intel_dp_aux.c @@ -4,6 +4,7 @@ */ #include "i915_drv.h" +#include "i915_reg.h" #include "i915_trace.h" #include "intel_display_types.h" #include "intel_dp_aux.h" diff --git a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c index 88689124c013..e0c177161407 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c @@ -11,6 +11,7 @@ #include <drm/display/drm_hdcp_helper.h> #include <drm/drm_print.h> +#include "i915_reg.h" #include "intel_ddi.h" #include "intel_de.h" #include "intel_display_types.h" @@ -19,28 +20,20 @@ #include "intel_hdcp.h" #include "intel_hdcp_regs.h" -static unsigned int transcoder_to_stream_enc_status(enum transcoder cpu_transcoder) +static u32 transcoder_to_stream_enc_status(enum transcoder cpu_transcoder) { - u32 stream_enc_mask; - switch (cpu_transcoder) { case TRANSCODER_A: - stream_enc_mask = HDCP_STATUS_STREAM_A_ENC; - break; + return HDCP_STATUS_STREAM_A_ENC; case TRANSCODER_B: - stream_enc_mask = HDCP_STATUS_STREAM_B_ENC; - break; + return HDCP_STATUS_STREAM_B_ENC; case TRANSCODER_C: - stream_enc_mask = HDCP_STATUS_STREAM_C_ENC; - break; + return HDCP_STATUS_STREAM_C_ENC; case TRANSCODER_D: - stream_enc_mask = HDCP_STATUS_STREAM_D_ENC; - break; + return HDCP_STATUS_STREAM_D_ENC; default: - stream_enc_mask = 0; + return 0; } - - return stream_enc_mask; } static void intel_dp_hdcp_wait_for_cp_irq(struct intel_hdcp *hdcp, int timeout) diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index 03604a37931c..4077a979a924 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -29,6 +29,7 @@ #include <drm/drm_probe_helper.h> #include "i915_drv.h" +#include "i915_reg.h" #include "intel_atomic.h" #include "intel_audio.h" #include "intel_connector.h" @@ -793,7 +794,35 @@ static bool intel_dp_mst_get_hw_state(struct intel_connector *connector) return false; } -static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port, const char *pathprop) +static int intel_dp_mst_add_properties(struct intel_dp *intel_dp, + struct drm_connector *connector, + const char *pathprop) +{ + struct drm_i915_private *i915 = to_i915(connector->dev); + + drm_object_attach_property(&connector->base, + i915->drm.mode_config.path_property, 0); + drm_object_attach_property(&connector->base, + i915->drm.mode_config.tile_property, 0); + + intel_attach_force_audio_property(connector); + intel_attach_broadcast_rgb_property(connector); + + /* + * Reuse the prop from the SST connector because we're + * not allowed to create new props after device registration. + */ + connector->max_bpc_property = + intel_dp->attached_connector->base.max_bpc_property; + if (connector->max_bpc_property) + drm_connector_attach_max_bpc_property(connector, 6, 12); + + return drm_connector_set_path_property(connector, pathprop); +} + +static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_port *port, + const char *pathprop) { struct intel_dp *intel_dp = container_of(mgr, struct intel_dp, mst_mgr); struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); @@ -833,28 +862,14 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo goto err; } - drm_object_attach_property(&connector->base, dev->mode_config.path_property, 0); - drm_object_attach_property(&connector->base, dev->mode_config.tile_property, 0); - - ret = drm_connector_set_path_property(connector, pathprop); + ret = intel_dp_mst_add_properties(intel_dp, connector, pathprop); if (ret) goto err; - intel_attach_force_audio_property(connector); - intel_attach_broadcast_rgb_property(connector); - ret = intel_dp_hdcp_init(dig_port, intel_connector); if (ret) drm_dbg_kms(&dev_priv->drm, "[%s:%d] HDCP MST init failed, skipping.\n", connector->name, connector->base.id); - /* - * Reuse the prop from the SST connector because we're - * not allowed to create new props after device registration. - */ - connector->max_bpc_property = - intel_dp->attached_connector->base.max_bpc_property; - if (connector->max_bpc_property) - drm_connector_attach_max_bpc_property(connector, 6, 12); return connector; diff --git a/drivers/gpu/drm/i915/display/intel_dpio_phy.c b/drivers/gpu/drm/i915/display/intel_dpio_phy.c index 8732b8722ed7..7eb7440b3180 100644 --- a/drivers/gpu/drm/i915/display/intel_dpio_phy.c +++ b/drivers/gpu/drm/i915/display/intel_dpio_phy.c @@ -21,6 +21,7 @@ * DEALINGS IN THE SOFTWARE. */ +#include "i915_reg.h" #include "intel_ddi.h" #include "intel_ddi_buf_trans.h" #include "intel_de.h" @@ -655,6 +656,48 @@ bxt_ddi_phy_get_lane_lat_optim_mask(struct intel_encoder *encoder) return mask; } +enum dpio_channel vlv_dig_port_to_channel(struct intel_digital_port *dig_port) +{ + switch (dig_port->base.port) { + default: + MISSING_CASE(dig_port->base.port); + fallthrough; + case PORT_B: + case PORT_D: + return DPIO_CH0; + case PORT_C: + return DPIO_CH1; + } +} + +enum dpio_phy vlv_dig_port_to_phy(struct intel_digital_port *dig_port) +{ + switch (dig_port->base.port) { + default: + MISSING_CASE(dig_port->base.port); + fallthrough; + case PORT_B: + case PORT_C: + return DPIO_PHY0; + case PORT_D: + return DPIO_PHY1; + } +} + +enum dpio_channel vlv_pipe_to_channel(enum pipe pipe) +{ + switch (pipe) { + default: + MISSING_CASE(pipe); + fallthrough; + case PIPE_A: + case PIPE_C: + return DPIO_CH0; + case PIPE_B: + return DPIO_CH1; + } +} + void chv_set_phy_signal_level(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, u32 deemph_reg_value, u32 margin_reg_value, diff --git a/drivers/gpu/drm/i915/display/intel_dpio_phy.h b/drivers/gpu/drm/i915/display/intel_dpio_phy.h index 9c3d008e8e1a..9c7725dacb47 100644 --- a/drivers/gpu/drm/i915/display/intel_dpio_phy.h +++ b/drivers/gpu/drm/i915/display/intel_dpio_phy.h @@ -8,13 +8,24 @@ #include <linux/types.h> -enum dpio_channel; -enum dpio_phy; +enum pipe; enum port; struct drm_i915_private; struct intel_crtc_state; +struct intel_digital_port; struct intel_encoder; +enum dpio_channel { + DPIO_CH0, + DPIO_CH1, +}; + +enum dpio_phy { + DPIO_PHY0, + DPIO_PHY1, + DPIO_PHY2, +}; + void bxt_port_to_phy_channel(struct drm_i915_private *dev_priv, enum port port, enum dpio_phy *phy, enum dpio_channel *ch); void bxt_ddi_phy_set_signal_levels(struct intel_encoder *encoder, @@ -30,6 +41,10 @@ void bxt_ddi_phy_set_lane_optim_mask(struct intel_encoder *encoder, u8 lane_lat_optim_mask); u8 bxt_ddi_phy_get_lane_lat_optim_mask(struct intel_encoder *encoder); +enum dpio_channel vlv_dig_port_to_channel(struct intel_digital_port *dig_port); +enum dpio_phy vlv_dig_port_to_phy(struct intel_digital_port *dig_port); +enum dpio_channel vlv_pipe_to_channel(enum pipe pipe); + void chv_set_phy_signal_level(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, u32 deemph_reg_value, u32 margin_reg_value, diff --git a/drivers/gpu/drm/i915/display/intel_dpll.c b/drivers/gpu/drm/i915/display/intel_dpll.c index b15ba78d64d6..c236aafe9be0 100644 --- a/drivers/gpu/drm/i915/display/intel_dpll.c +++ b/drivers/gpu/drm/i915/display/intel_dpll.c @@ -6,10 +6,12 @@ #include <linux/kernel.h> #include <linux/string_helpers.h> +#include "i915_reg.h" #include "intel_crtc.h" #include "intel_de.h" #include "intel_display.h" #include "intel_display_types.h" +#include "intel_dpio_phy.h" #include "intel_dpll.h" #include "intel_lvds.h" #include "intel_panel.h" diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c index 64dd603dc69a..1974eb580ed1 100644 --- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c +++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c @@ -23,15 +23,18 @@ #include <linux/string_helpers.h> +#include "i915_reg.h" #include "intel_de.h" #include "intel_display_types.h" #include "intel_dkl_phy.h" +#include "intel_dkl_phy_regs.h" #include "intel_dpio_phy.h" #include "intel_dpll.h" #include "intel_dpll_mgr.h" +#include "intel_hti.h" +#include "intel_mg_phy_regs.h" #include "intel_pch_refclk.h" #include "intel_tc.h" -#include "intel_tc_phy_regs.h" /** * DOC: Display PLLs @@ -153,28 +156,6 @@ intel_get_shared_dpll_by_id(struct drm_i915_private *dev_priv, return &dev_priv->display.dpll.shared_dplls[id]; } -/** - * intel_get_shared_dpll_id - get the id of a DPLL - * @dev_priv: i915 device instance - * @pll: the DPLL - * - * Returns: - * The id of @pll - */ -enum intel_dpll_id -intel_get_shared_dpll_id(struct drm_i915_private *dev_priv, - struct intel_shared_dpll *pll) -{ - long pll_idx = pll - dev_priv->display.dpll.shared_dplls; - - if (drm_WARN_ON(&dev_priv->drm, - pll_idx < 0 || - pll_idx >= dev_priv->display.dpll.num_shared_dpll)) - return -1; - - return pll_idx; -} - /* For ILK+ */ void assert_shared_dpll(struct drm_i915_private *dev_priv, struct intel_shared_dpll *pll, @@ -385,20 +366,30 @@ intel_reference_shared_dpll(struct intel_atomic_state *state, if (shared_dpll[id].pipe_mask == 0) shared_dpll[id].hw_state = *pll_state; - drm_dbg(&i915->drm, "using %s for pipe %c\n", pll->info->name, - pipe_name(crtc->pipe)); + drm_WARN_ON(&i915->drm, (shared_dpll[id].pipe_mask & BIT(crtc->pipe)) != 0); shared_dpll[id].pipe_mask |= BIT(crtc->pipe); + + drm_dbg_kms(&i915->drm, "[CRTC:%d:%s] reserving %s\n", + crtc->base.base.id, crtc->base.name, pll->info->name); } static void intel_unreference_shared_dpll(struct intel_atomic_state *state, const struct intel_crtc *crtc, const struct intel_shared_dpll *pll) { + struct drm_i915_private *i915 = to_i915(state->base.dev); struct intel_shared_dpll_state *shared_dpll; + const enum intel_dpll_id id = pll->info->id; shared_dpll = intel_atomic_get_shared_dpll_state(&state->base); - shared_dpll[pll->info->id].pipe_mask &= ~BIT(crtc->pipe); + + drm_WARN_ON(&i915->drm, (shared_dpll[id].pipe_mask & BIT(crtc->pipe)) == 0); + + shared_dpll[id].pipe_mask &= ~BIT(crtc->pipe); + + drm_dbg_kms(&i915->drm, "[CRTC:%d:%s] releasing %s\n", + crtc->base.base.id, crtc->base.name, pll->info->name); } static void intel_put_dpll(struct intel_atomic_state *state, @@ -709,8 +700,6 @@ struct hsw_wrpll_rnp { static unsigned hsw_wrpll_get_budget_for_freq(int clock) { - unsigned budget; - switch (clock) { case 25175000: case 25200000: @@ -743,21 +732,18 @@ static unsigned hsw_wrpll_get_budget_for_freq(int clock) case 222750000: case 296703000: case 297000000: - budget = 0; - break; + return 0; case 233500000: case 245250000: case 247750000: case 253250000: case 298000000: - budget = 1500; - break; + return 1500; case 169128000: case 169500000: case 179500000: case 202000000: - budget = 2000; - break; + return 2000; case 256250000: case 262500000: case 270000000: @@ -767,18 +753,13 @@ static unsigned hsw_wrpll_get_budget_for_freq(int clock) case 281250000: case 286000000: case 291750000: - budget = 4000; - break; + return 4000; case 267250000: case 268500000: - budget = 5000; - break; + return 5000; default: - budget = 1000; - break; + return 1000; } - - return budget; } static void hsw_wrpll_update_rnp(u64 freq2k, unsigned int budget, @@ -3184,14 +3165,6 @@ static void icl_update_active_dpll(struct intel_atomic_state *state, icl_set_active_port_dpll(crtc_state, port_dpll_id); } -static u32 intel_get_hti_plls(struct drm_i915_private *i915) -{ - if (!(i915->hti_state & HDPORT_ENABLED)) - return 0; - - return REG_FIELD_GET(HDPORT_DPLL_USED_MASK, i915->hti_state); -} - static int icl_compute_combo_phy_dpll(struct intel_atomic_state *state, struct intel_crtc *crtc) { @@ -3266,7 +3239,7 @@ static int icl_get_combo_phy_dpll(struct intel_atomic_state *state, } /* Eliminate DPLLs from consideration if reserved by HTI */ - dpll_mask &= ~intel_get_hti_plls(dev_priv); + dpll_mask &= ~intel_hti_dpll_mask(dev_priv); port_dpll->pll = intel_find_shared_dpll(state, crtc, &port_dpll->hw_state, @@ -3510,11 +3483,11 @@ static bool dkl_pll_get_hw_state(struct drm_i915_private *dev_priv, * they are on different building blocks */ hw_state->mg_refclkin_ctl = intel_dkl_phy_read(dev_priv, - DKL_REFCLKIN_CTL(tc_port), 2); + DKL_REFCLKIN_CTL(tc_port)); hw_state->mg_refclkin_ctl &= MG_REFCLKIN_CTL_OD_2_MUX_MASK; hw_state->mg_clktop2_hsclkctl = - intel_dkl_phy_read(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port), 2); + intel_dkl_phy_read(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port)); hw_state->mg_clktop2_hsclkctl &= MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL_MASK | MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL_MASK | @@ -3522,32 +3495,32 @@ static bool dkl_pll_get_hw_state(struct drm_i915_private *dev_priv, MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO_MASK; hw_state->mg_clktop2_coreclkctl1 = - intel_dkl_phy_read(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port), 2); + intel_dkl_phy_read(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port)); hw_state->mg_clktop2_coreclkctl1 &= MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO_MASK; - hw_state->mg_pll_div0 = intel_dkl_phy_read(dev_priv, DKL_PLL_DIV0(tc_port), 2); + hw_state->mg_pll_div0 = intel_dkl_phy_read(dev_priv, DKL_PLL_DIV0(tc_port)); val = DKL_PLL_DIV0_MASK; if (dev_priv->display.vbt.override_afc_startup) val |= DKL_PLL_DIV0_AFC_STARTUP_MASK; hw_state->mg_pll_div0 &= val; - hw_state->mg_pll_div1 = intel_dkl_phy_read(dev_priv, DKL_PLL_DIV1(tc_port), 2); + hw_state->mg_pll_div1 = intel_dkl_phy_read(dev_priv, DKL_PLL_DIV1(tc_port)); hw_state->mg_pll_div1 &= (DKL_PLL_DIV1_IREF_TRIM_MASK | DKL_PLL_DIV1_TDC_TARGET_CNT_MASK); - hw_state->mg_pll_ssc = intel_dkl_phy_read(dev_priv, DKL_PLL_SSC(tc_port), 2); + hw_state->mg_pll_ssc = intel_dkl_phy_read(dev_priv, DKL_PLL_SSC(tc_port)); hw_state->mg_pll_ssc &= (DKL_PLL_SSC_IREF_NDIV_RATIO_MASK | DKL_PLL_SSC_STEP_LEN_MASK | DKL_PLL_SSC_STEP_NUM_MASK | DKL_PLL_SSC_EN); - hw_state->mg_pll_bias = intel_dkl_phy_read(dev_priv, DKL_PLL_BIAS(tc_port), 2); + hw_state->mg_pll_bias = intel_dkl_phy_read(dev_priv, DKL_PLL_BIAS(tc_port)); hw_state->mg_pll_bias &= (DKL_PLL_BIAS_FRAC_EN_H | DKL_PLL_BIAS_FBDIV_FRAC_MASK); hw_state->mg_pll_tdc_coldst_bias = - intel_dkl_phy_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port), 2); + intel_dkl_phy_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port)); hw_state->mg_pll_tdc_coldst_bias &= (DKL_PLL_TDC_SSC_STEP_SIZE_MASK | DKL_PLL_TDC_FEED_FWD_GAIN_MASK); @@ -3736,57 +3709,57 @@ static void dkl_pll_write(struct drm_i915_private *dev_priv, * though on different building block */ /* All the registers are RMW */ - val = intel_dkl_phy_read(dev_priv, DKL_REFCLKIN_CTL(tc_port), 2); + val = intel_dkl_phy_read(dev_priv, DKL_REFCLKIN_CTL(tc_port)); val &= ~MG_REFCLKIN_CTL_OD_2_MUX_MASK; val |= hw_state->mg_refclkin_ctl; - intel_dkl_phy_write(dev_priv, DKL_REFCLKIN_CTL(tc_port), 2, val); + intel_dkl_phy_write(dev_priv, DKL_REFCLKIN_CTL(tc_port), val); - val = intel_dkl_phy_read(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port), 2); + val = intel_dkl_phy_read(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port)); val &= ~MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO_MASK; val |= hw_state->mg_clktop2_coreclkctl1; - intel_dkl_phy_write(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port), 2, val); + intel_dkl_phy_write(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port), val); - val = intel_dkl_phy_read(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port), 2); + val = intel_dkl_phy_read(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port)); val &= ~(MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL_MASK | MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL_MASK | MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO_MASK | MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO_MASK); val |= hw_state->mg_clktop2_hsclkctl; - intel_dkl_phy_write(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port), 2, val); + intel_dkl_phy_write(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port), val); val = DKL_PLL_DIV0_MASK; if (dev_priv->display.vbt.override_afc_startup) val |= DKL_PLL_DIV0_AFC_STARTUP_MASK; - intel_dkl_phy_rmw(dev_priv, DKL_PLL_DIV0(tc_port), 2, val, + intel_dkl_phy_rmw(dev_priv, DKL_PLL_DIV0(tc_port), val, hw_state->mg_pll_div0); - val = intel_dkl_phy_read(dev_priv, DKL_PLL_DIV1(tc_port), 2); + val = intel_dkl_phy_read(dev_priv, DKL_PLL_DIV1(tc_port)); val &= ~(DKL_PLL_DIV1_IREF_TRIM_MASK | DKL_PLL_DIV1_TDC_TARGET_CNT_MASK); val |= hw_state->mg_pll_div1; - intel_dkl_phy_write(dev_priv, DKL_PLL_DIV1(tc_port), 2, val); + intel_dkl_phy_write(dev_priv, DKL_PLL_DIV1(tc_port), val); - val = intel_dkl_phy_read(dev_priv, DKL_PLL_SSC(tc_port), 2); + val = intel_dkl_phy_read(dev_priv, DKL_PLL_SSC(tc_port)); val &= ~(DKL_PLL_SSC_IREF_NDIV_RATIO_MASK | DKL_PLL_SSC_STEP_LEN_MASK | DKL_PLL_SSC_STEP_NUM_MASK | DKL_PLL_SSC_EN); val |= hw_state->mg_pll_ssc; - intel_dkl_phy_write(dev_priv, DKL_PLL_SSC(tc_port), 2, val); + intel_dkl_phy_write(dev_priv, DKL_PLL_SSC(tc_port), val); - val = intel_dkl_phy_read(dev_priv, DKL_PLL_BIAS(tc_port), 2); + val = intel_dkl_phy_read(dev_priv, DKL_PLL_BIAS(tc_port)); val &= ~(DKL_PLL_BIAS_FRAC_EN_H | DKL_PLL_BIAS_FBDIV_FRAC_MASK); val |= hw_state->mg_pll_bias; - intel_dkl_phy_write(dev_priv, DKL_PLL_BIAS(tc_port), 2, val); + intel_dkl_phy_write(dev_priv, DKL_PLL_BIAS(tc_port), val); - val = intel_dkl_phy_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port), 2); + val = intel_dkl_phy_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port)); val &= ~(DKL_PLL_TDC_SSC_STEP_SIZE_MASK | DKL_PLL_TDC_FEED_FWD_GAIN_MASK); val |= hw_state->mg_pll_tdc_coldst_bias; - intel_dkl_phy_write(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port), 2, val); + intel_dkl_phy_write(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port), val); - intel_dkl_phy_posting_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port), 2); + intel_dkl_phy_posting_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port)); } static void icl_pll_power_enable(struct drm_i915_private *dev_priv, @@ -4188,6 +4161,8 @@ void intel_shared_dpll_init(struct drm_i915_private *dev_priv) const struct dpll_info *dpll_info; int i; + mutex_init(&dev_priv->display.dpll.lock); + if (IS_DG2(dev_priv)) /* No shared DPLLs on DG2; port PLLs are part of the PHY */ dpll_mgr = NULL; @@ -4232,7 +4207,6 @@ void intel_shared_dpll_init(struct drm_i915_private *dev_priv) dev_priv->display.dpll.mgr = dpll_mgr; dev_priv->display.dpll.num_shared_dpll = i; - mutex_init(&dev_priv->display.dpll.lock); } /** diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.h b/drivers/gpu/drm/i915/display/intel_dpll_mgr.h index 3247dc300ae4..3854f1b4299a 100644 --- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.h +++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.h @@ -328,9 +328,6 @@ struct intel_shared_dpll { struct intel_shared_dpll * intel_get_shared_dpll_by_id(struct drm_i915_private *dev_priv, enum intel_dpll_id id); -enum intel_dpll_id -intel_get_shared_dpll_id(struct drm_i915_private *dev_priv, - struct intel_shared_dpll *pll); void assert_shared_dpll(struct drm_i915_private *dev_priv, struct intel_shared_dpll *pll, bool state); diff --git a/drivers/gpu/drm/i915/display/intel_dpt.c b/drivers/gpu/drm/i915/display/intel_dpt.c index ac587647e1f5..ad1a37b515fb 100644 --- a/drivers/gpu/drm/i915/display/intel_dpt.c +++ b/drivers/gpu/drm/i915/display/intel_dpt.c @@ -5,6 +5,7 @@ #include "gem/i915_gem_domain.h" #include "gem/i915_gem_internal.h" +#include "gem/i915_gem_lmem.h" #include "gt/gen8_ppgtt.h" #include "i915_drv.h" diff --git a/drivers/gpu/drm/i915/display/intel_drrs.c b/drivers/gpu/drm/i915/display/intel_drrs.c index 7da4a9cbe4ba..5b9e44443814 100644 --- a/drivers/gpu/drm/i915/display/intel_drrs.c +++ b/drivers/gpu/drm/i915/display/intel_drrs.c @@ -4,6 +4,7 @@ */ #include "i915_drv.h" +#include "i915_reg.h" #include "intel_atomic.h" #include "intel_de.h" #include "intel_display_types.h" @@ -284,16 +285,124 @@ void intel_drrs_flush(struct drm_i915_private *dev_priv, } /** - * intel_crtc_drrs_init - Init DRRS for CRTC + * intel_drrs_crtc_init - Init DRRS for CRTC * @crtc: crtc * * This function is called only once at driver load to initialize basic * DRRS stuff. * */ -void intel_crtc_drrs_init(struct intel_crtc *crtc) +void intel_drrs_crtc_init(struct intel_crtc *crtc) { INIT_DELAYED_WORK(&crtc->drrs.work, intel_drrs_downclock_work); mutex_init(&crtc->drrs.mutex); crtc->drrs.cpu_transcoder = INVALID_TRANSCODER; } + +static int intel_drrs_debugfs_status_show(struct seq_file *m, void *unused) +{ + struct intel_crtc *crtc = m->private; + const struct intel_crtc_state *crtc_state; + int ret; + + ret = drm_modeset_lock_single_interruptible(&crtc->base.mutex); + if (ret) + return ret; + + crtc_state = to_intel_crtc_state(crtc->base.state); + + mutex_lock(&crtc->drrs.mutex); + + seq_printf(m, "DRRS enabled: %s\n", + str_yes_no(crtc_state->has_drrs)); + + seq_printf(m, "DRRS active: %s\n", + str_yes_no(intel_drrs_is_active(crtc))); + + seq_printf(m, "DRRS refresh rate: %s\n", + crtc->drrs.refresh_rate == DRRS_REFRESH_RATE_LOW ? + "low" : "high"); + + seq_printf(m, "DRRS busy frontbuffer bits: 0x%x\n", + crtc->drrs.busy_frontbuffer_bits); + + mutex_unlock(&crtc->drrs.mutex); + + drm_modeset_unlock(&crtc->base.mutex); + + return 0; +} + +DEFINE_SHOW_ATTRIBUTE(intel_drrs_debugfs_status); + +static int intel_drrs_debugfs_ctl_set(void *data, u64 val) +{ + struct intel_crtc *crtc = data; + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + struct intel_crtc_state *crtc_state; + struct drm_crtc_commit *commit; + int ret; + + ret = drm_modeset_lock_single_interruptible(&crtc->base.mutex); + if (ret) + return ret; + + crtc_state = to_intel_crtc_state(crtc->base.state); + + if (!crtc_state->hw.active || + !crtc_state->has_drrs) + goto out; + + commit = crtc_state->uapi.commit; + if (commit) { + ret = wait_for_completion_interruptible(&commit->hw_done); + if (ret) + goto out; + } + + drm_dbg(&i915->drm, + "Manually %sactivating DRRS\n", val ? "" : "de"); + + if (val) + intel_drrs_activate(crtc_state); + else + intel_drrs_deactivate(crtc_state); + +out: + drm_modeset_unlock(&crtc->base.mutex); + + return ret; +} + +DEFINE_SIMPLE_ATTRIBUTE(intel_drrs_debugfs_ctl_fops, + NULL, intel_drrs_debugfs_ctl_set, "%llu\n"); + +void intel_drrs_crtc_debugfs_add(struct intel_crtc *crtc) +{ + debugfs_create_file("i915_drrs_status", 0444, crtc->base.debugfs_entry, + crtc, &intel_drrs_debugfs_status_fops); + + debugfs_create_file("i915_drrs_ctl", 0644, crtc->base.debugfs_entry, + crtc, &intel_drrs_debugfs_ctl_fops); +} + +static int intel_drrs_debugfs_type_show(struct seq_file *m, void *unused) +{ + struct intel_connector *connector = m->private; + + seq_printf(m, "DRRS type: %s\n", + intel_drrs_type_str(intel_panel_drrs_type(connector))); + + return 0; +} + +DEFINE_SHOW_ATTRIBUTE(intel_drrs_debugfs_type); + +void intel_drrs_connector_debugfs_add(struct intel_connector *connector) +{ + if (intel_panel_drrs_type(connector) == DRRS_TYPE_NONE) + return; + + debugfs_create_file("i915_drrs_type", 0444, connector->base.debugfs_entry, + connector, &intel_drrs_debugfs_type_fops); +} diff --git a/drivers/gpu/drm/i915/display/intel_drrs.h b/drivers/gpu/drm/i915/display/intel_drrs.h index 3ad1be1ad9c1..8ef5f93a80ff 100644 --- a/drivers/gpu/drm/i915/display/intel_drrs.h +++ b/drivers/gpu/drm/i915/display/intel_drrs.h @@ -23,6 +23,8 @@ void intel_drrs_invalidate(struct drm_i915_private *dev_priv, unsigned int frontbuffer_bits); void intel_drrs_flush(struct drm_i915_private *dev_priv, unsigned int frontbuffer_bits); -void intel_crtc_drrs_init(struct intel_crtc *crtc); +void intel_drrs_crtc_init(struct intel_crtc *crtc); +void intel_drrs_crtc_debugfs_add(struct intel_crtc *crtc); +void intel_drrs_connector_debugfs_add(struct intel_connector *connector); #endif /* __INTEL_DRRS_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c index fc9c3e41c333..1e1c6107d51b 100644 --- a/drivers/gpu/drm/i915/display/intel_dsb.c +++ b/drivers/gpu/drm/i915/display/intel_dsb.c @@ -7,6 +7,7 @@ #include "gem/i915_gem_internal.h" #include "i915_drv.h" +#include "i915_reg.h" #include "intel_de.h" #include "intel_display_types.h" #include "intel_dsb.h" diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c index 75e8cc4337c9..2cbc1292ab38 100644 --- a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c +++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c @@ -41,9 +41,11 @@ #include "i915_drv.h" #include "i915_reg.h" +#include "intel_de.h" #include "intel_display_types.h" #include "intel_dsi.h" #include "intel_dsi_vbt.h" +#include "intel_gmbus_regs.h" #include "vlv_dsi.h" #include "vlv_dsi_regs.h" #include "vlv_sideband.h" @@ -137,9 +139,9 @@ static enum port intel_dsi_seq_port_to_port(struct intel_dsi *intel_dsi, return ffs(intel_dsi->ports) - 1; if (seq_port) { - if (intel_dsi->ports & PORT_B) + if (intel_dsi->ports & BIT(PORT_B)) return PORT_B; - else if (intel_dsi->ports & PORT_C) + else if (intel_dsi->ports & BIT(PORT_C)) return PORT_C; } @@ -377,6 +379,85 @@ static void icl_exec_gpio(struct intel_connector *connector, drm_dbg_kms(&dev_priv->drm, "Skipping ICL GPIO element execution\n"); } +enum { + MIPI_RESET_1 = 0, + MIPI_AVDD_EN_1, + MIPI_BKLT_EN_1, + MIPI_AVEE_EN_1, + MIPI_VIO_EN_1, + MIPI_RESET_2, + MIPI_AVDD_EN_2, + MIPI_BKLT_EN_2, + MIPI_AVEE_EN_2, + MIPI_VIO_EN_2, +}; + +static void icl_native_gpio_set_value(struct drm_i915_private *dev_priv, + int gpio, bool value) +{ + int index; + + if (drm_WARN_ON(&dev_priv->drm, DISPLAY_VER(dev_priv) == 11 && gpio >= MIPI_RESET_2)) + return; + + switch (gpio) { + case MIPI_RESET_1: + case MIPI_RESET_2: + index = gpio == MIPI_RESET_1 ? HPD_PORT_A : HPD_PORT_B; + + /* + * Disable HPD to set the pin to output, and set output + * value. The HPD pin should not be enabled for DSI anyway, + * assuming the board design and VBT are sane, and the pin isn't + * used by a non-DSI encoder. + * + * The locking protects against concurrent SHOTPLUG_CTL_DDI + * modifications in irq setup and handling. + */ + spin_lock_irq(&dev_priv->irq_lock); + intel_de_rmw(dev_priv, SHOTPLUG_CTL_DDI, + SHOTPLUG_CTL_DDI_HPD_ENABLE(index) | + SHOTPLUG_CTL_DDI_HPD_OUTPUT_DATA(index), + value ? SHOTPLUG_CTL_DDI_HPD_OUTPUT_DATA(index) : 0); + spin_unlock_irq(&dev_priv->irq_lock); + break; + case MIPI_AVDD_EN_1: + case MIPI_AVDD_EN_2: + index = gpio == MIPI_AVDD_EN_1 ? 0 : 1; + + intel_de_rmw(dev_priv, PP_CONTROL(index), PANEL_POWER_ON, + value ? PANEL_POWER_ON : 0); + break; + case MIPI_BKLT_EN_1: + case MIPI_BKLT_EN_2: + index = gpio == MIPI_BKLT_EN_1 ? 0 : 1; + + intel_de_rmw(dev_priv, PP_CONTROL(index), EDP_BLC_ENABLE, + value ? EDP_BLC_ENABLE : 0); + break; + case MIPI_AVEE_EN_1: + case MIPI_AVEE_EN_2: + index = gpio == MIPI_AVEE_EN_1 ? 1 : 2; + + intel_de_rmw(dev_priv, GPIO(dev_priv, index), + GPIO_CLOCK_VAL_OUT, + GPIO_CLOCK_DIR_MASK | GPIO_CLOCK_DIR_OUT | + GPIO_CLOCK_VAL_MASK | (value ? GPIO_CLOCK_VAL_OUT : 0)); + break; + case MIPI_VIO_EN_1: + case MIPI_VIO_EN_2: + index = gpio == MIPI_VIO_EN_1 ? 1 : 2; + + intel_de_rmw(dev_priv, GPIO(dev_priv, index), + GPIO_DATA_VAL_OUT, + GPIO_DATA_DIR_MASK | GPIO_DATA_DIR_OUT | + GPIO_DATA_VAL_MASK | (value ? GPIO_DATA_VAL_OUT : 0)); + break; + default: + MISSING_CASE(gpio); + } +} + static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data) { struct drm_device *dev = intel_dsi->base.base.dev; @@ -384,8 +465,7 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data) struct intel_connector *connector = intel_dsi->attached_connector; u8 gpio_source, gpio_index = 0, gpio_number; bool value; - - drm_dbg_kms(&dev_priv->drm, "\n"); + bool native = DISPLAY_VER(dev_priv) >= 11; if (connector->panel.vbt.dsi.seq_version >= 3) gpio_index = *data++; @@ -398,10 +478,18 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data) else gpio_source = 0; + if (connector->panel.vbt.dsi.seq_version >= 4 && *data & BIT(1)) + native = false; + /* pull up/down */ value = *data++ & 1; - if (DISPLAY_VER(dev_priv) >= 11) + drm_dbg_kms(&dev_priv->drm, "GPIO index %u, number %u, source %u, native %s, set to %s\n", + gpio_index, gpio_number, gpio_source, str_yes_no(native), str_on_off(value)); + + if (native) + icl_native_gpio_set_value(dev_priv, gpio_number, value); + else if (DISPLAY_VER(dev_priv) >= 11) icl_exec_gpio(connector, gpio_source, gpio_index, value); else if (IS_VALLEYVIEW(dev_priv)) vlv_exec_gpio(connector, gpio_source, gpio_number, value); diff --git a/drivers/gpu/drm/i915/display/intel_dvo.c b/drivers/gpu/drm/i915/display/intel_dvo.c index 5572e43026e4..c86f9890754d 100644 --- a/drivers/gpu/drm/i915/display/intel_dvo.c +++ b/drivers/gpu/drm/i915/display/intel_dvo.c @@ -32,6 +32,7 @@ #include <drm/drm_crtc.h> #include "i915_drv.h" +#include "i915_reg.h" #include "intel_connector.h" #include "intel_de.h" #include "intel_display_types.h" @@ -491,8 +492,8 @@ void intel_dvo_init(struct drm_i915_private *dev_priv) intel_encoder->pipe_mask = ~0; if (dvo->type != INTEL_DVO_CHIP_LVDS) - intel_encoder->cloneable = (1 << INTEL_OUTPUT_ANALOG) | - (1 << INTEL_OUTPUT_DVO); + intel_encoder->cloneable = BIT(INTEL_OUTPUT_ANALOG) | + BIT(INTEL_OUTPUT_DVO); switch (dvo->type) { case INTEL_DVO_CHIP_TMDS: @@ -515,8 +516,6 @@ void intel_dvo_init(struct drm_i915_private *dev_priv) drm_connector_helper_add(connector, &intel_dvo_connector_helper_funcs); connector->display_info.subpixel_order = SubPixelHorizontalRGB; - connector->interlace_allowed = false; - connector->doublescan_allowed = false; intel_connector_attach_encoder(intel_connector, intel_encoder); if (dvo->type == INTEL_DVO_CHIP_LVDS) { diff --git a/drivers/gpu/drm/i915/display/intel_dvo_dev.h b/drivers/gpu/drm/i915/display/intel_dvo_dev.h index 50205f064d93..ecff7b190856 100644 --- a/drivers/gpu/drm/i915/display/intel_dvo_dev.h +++ b/drivers/gpu/drm/i915/display/intel_dvo_dev.h @@ -23,12 +23,12 @@ #ifndef __INTEL_DVO_DEV_H__ #define __INTEL_DVO_DEV_H__ -#include <linux/i2c.h> - -#include <drm/drm_crtc.h> - #include "i915_reg_defs.h" +enum drm_connector_status; +struct drm_display_mode; +struct i2c_adapter; + struct intel_dvo_device { const char *name; int type; diff --git a/drivers/gpu/drm/i915/display/intel_fb.c b/drivers/gpu/drm/i915/display/intel_fb.c index eefa33c555ac..63137ae5ab21 100644 --- a/drivers/gpu/drm/i915/display/intel_fb.c +++ b/drivers/gpu/drm/i915/display/intel_fb.c @@ -301,6 +301,19 @@ static bool plane_caps_contain_all(u8 caps, u8 mask) } /** + * intel_fb_is_tiled_modifier: Check if a modifier is a tiled modifier type + * @modifier: Modifier to check + * + * Returns: + * Returns %true if @modifier is a tiled modifier. + */ +bool intel_fb_is_tiled_modifier(u64 modifier) +{ + return plane_caps_contain_any(lookup_modifier(modifier)->plane_caps, + INTEL_PLANE_CAP_TILING_MASK); +} + +/** * intel_fb_is_ccs_modifier: Check if a modifier is a CCS modifier type * @modifier: Modifier to check * diff --git a/drivers/gpu/drm/i915/display/intel_fb.h b/drivers/gpu/drm/i915/display/intel_fb.h index 12386f13a4e0..4662b812b934 100644 --- a/drivers/gpu/drm/i915/display/intel_fb.h +++ b/drivers/gpu/drm/i915/display/intel_fb.h @@ -29,6 +29,7 @@ struct intel_plane_state; #define INTEL_PLANE_CAP_TILING_Yf BIT(5) #define INTEL_PLANE_CAP_TILING_4 BIT(6) +bool intel_fb_is_tiled_modifier(u64 modifier); bool intel_fb_is_ccs_modifier(u64 modifier); bool intel_fb_is_rc_ccs_cc_modifier(u64 modifier); bool intel_fb_is_mc_ccs_modifier(u64 modifier); diff --git a/drivers/gpu/drm/i915/display/intel_fb_pin.c b/drivers/gpu/drm/i915/display/intel_fb_pin.c index 1dddd6abd77b..6900acbb1381 100644 --- a/drivers/gpu/drm/i915/display/intel_fb_pin.c +++ b/drivers/gpu/drm/i915/display/intel_fb_pin.c @@ -167,7 +167,6 @@ retry: ret = i915_gem_object_attach_phys(obj, alignment); else if (!ret && HAS_LMEM(dev_priv)) ret = i915_gem_object_migrate(obj, &ww, INTEL_REGION_LMEM_0); - /* TODO: Do we need to sync when migration becomes async? */ if (!ret) ret = i915_gem_object_pin_pages(obj); if (ret) diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c index f38175304928..b5ee5ea0d010 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.c +++ b/drivers/gpu/drm/i915/display/intel_fbc.c @@ -670,6 +670,7 @@ static void intel_fbc_nuke(struct intel_fbc *fbc) { struct drm_i915_private *i915 = fbc->i915; + lockdep_assert_held(&fbc->lock); drm_WARN_ON(&i915->drm, fbc->flip_pending); trace_intel_fbc_nuke(fbc->state.plane); @@ -679,6 +680,8 @@ static void intel_fbc_nuke(struct intel_fbc *fbc) static void intel_fbc_activate(struct intel_fbc *fbc) { + lockdep_assert_held(&fbc->lock); + intel_fbc_hw_activate(fbc); intel_fbc_nuke(fbc); @@ -687,9 +690,7 @@ static void intel_fbc_activate(struct intel_fbc *fbc) static void intel_fbc_deactivate(struct intel_fbc *fbc, const char *reason) { - struct drm_i915_private *i915 = fbc->i915; - - drm_WARN_ON(&i915->drm, !mutex_is_locked(&fbc->lock)); + lockdep_assert_held(&fbc->lock); if (fbc->active) intel_fbc_hw_deactivate(fbc); @@ -1009,7 +1010,8 @@ static bool intel_fbc_is_fence_ok(const struct intel_plane_state *plane_state) { struct drm_i915_private *i915 = to_i915(plane_state->uapi.plane->dev); - /* The use of a CPU fence is one of two ways to detect writes by the + /* + * The use of a CPU fence is one of two ways to detect writes by the * CPU to the scanout and trigger updates to the FBC. * * The other method is by software tracking (see @@ -1019,12 +1021,6 @@ static bool intel_fbc_is_fence_ok(const struct intel_plane_state *plane_state) * Note that is possible for a tiled surface to be unmappable (and * so have no fence associated with it) due to aperture constraints * at the time of pinning. - * - * FIXME with 90/270 degree rotation we should use the fence on - * the normal GTT view (the rotated view doesn't even have a - * fence). Would need changes to the FBC fence Y offset as well. - * For now this will effectively disable FBC with 90/270 degree - * rotation. */ return DISPLAY_VER(i915) >= 9 || (plane_state->flags & PLANE_HAS_FENCE && @@ -1187,7 +1183,7 @@ static bool intel_fbc_can_flip_nuke(struct intel_atomic_state *state, const struct drm_framebuffer *old_fb = old_plane_state->hw.fb; const struct drm_framebuffer *new_fb = new_plane_state->hw.fb; - if (drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi)) + if (intel_crtc_needs_modeset(new_crtc_state)) return false; if (!intel_fbc_is_ok(old_plane_state) || @@ -1227,6 +1223,8 @@ static bool __intel_fbc_pre_update(struct intel_atomic_state *state, struct intel_fbc *fbc = plane->fbc; bool need_vblank_wait = false; + lockdep_assert_held(&fbc->lock); + fbc->flip_pending = true; if (intel_fbc_can_flip_nuke(state, crtc, plane)) @@ -1284,7 +1282,7 @@ static void __intel_fbc_disable(struct intel_fbc *fbc) struct drm_i915_private *i915 = fbc->i915; struct intel_plane *plane = fbc->state.plane; - drm_WARN_ON(&i915->drm, !mutex_is_locked(&fbc->lock)); + lockdep_assert_held(&fbc->lock); drm_WARN_ON(&i915->drm, fbc->active); drm_dbg_kms(&i915->drm, "Disabling FBC on [PLANE:%d:%s]\n", @@ -1299,9 +1297,9 @@ static void __intel_fbc_disable(struct intel_fbc *fbc) static void __intel_fbc_post_update(struct intel_fbc *fbc) { - struct drm_i915_private *i915 = fbc->i915; + lockdep_assert_held(&fbc->lock); - drm_WARN_ON(&i915->drm, !mutex_is_locked(&fbc->lock)); + fbc->flip_pending = false; if (!fbc->busy_bits) intel_fbc_activate(fbc); @@ -1324,10 +1322,8 @@ void intel_fbc_post_update(struct intel_atomic_state *state, mutex_lock(&fbc->lock); - if (fbc->state.plane == plane) { - fbc->flip_pending = false; + if (fbc->state.plane == plane) __intel_fbc_post_update(fbc); - } mutex_unlock(&fbc->lock); } @@ -1437,6 +1433,8 @@ static void __intel_fbc_enable(struct intel_atomic_state *state, intel_atomic_get_new_plane_state(state, plane); struct intel_fbc *fbc = plane->fbc; + lockdep_assert_held(&fbc->lock); + if (fbc->state.plane) { if (fbc->state.plane != plane) return; @@ -1522,7 +1520,8 @@ void intel_fbc_update(struct intel_atomic_state *state, mutex_lock(&fbc->lock); - if (crtc_state->update_pipe && plane_state->no_fbc_reason) { + if (intel_crtc_needs_fastset(crtc_state) && + plane_state->no_fbc_reason) { if (fbc->state.plane == plane) __intel_fbc_disable(fbc); } else { diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c index 112aa0447a0d..5575d7abdc09 100644 --- a/drivers/gpu/drm/i915/display/intel_fbdev.c +++ b/drivers/gpu/drm/i915/display/intel_fbdev.c @@ -124,6 +124,8 @@ static const struct fb_ops intelfb_ops = { .owner = THIS_MODULE, DRM_FB_HELPER_DEFAULT_OPS, .fb_set_par = intel_fbdev_set_par, + .fb_read = drm_fb_helper_cfb_read, + .fb_write = drm_fb_helper_cfb_write, .fb_fillrect = drm_fb_helper_cfb_fillrect, .fb_copyarea = drm_fb_helper_cfb_copyarea, .fb_imageblit = drm_fb_helper_cfb_imageblit, @@ -175,7 +177,7 @@ static int intelfb_alloc(struct drm_fb_helper *helper, } if (IS_ERR(obj)) { - drm_err(&dev_priv->drm, "failed to allocate framebuffer\n"); + drm_err(&dev_priv->drm, "failed to allocate framebuffer (%pe)\n", obj); return PTR_ERR(obj); } @@ -254,9 +256,9 @@ static int intelfb_create(struct drm_fb_helper *helper, goto out_unlock; } - info = drm_fb_helper_alloc_fbi(helper); + info = drm_fb_helper_alloc_info(helper); if (IS_ERR(info)) { - drm_err(&dev_priv->drm, "Failed to allocate fb_info\n"); + drm_err(&dev_priv->drm, "Failed to allocate fb_info (%pe)\n", info); ret = PTR_ERR(info); goto out_unpin; } @@ -291,7 +293,7 @@ static int intelfb_create(struct drm_fb_helper *helper, vaddr = i915_vma_pin_iomap(vma); if (IS_ERR(vaddr)) { drm_err(&dev_priv->drm, - "Failed to remap framebuffer into virtual memory\n"); + "Failed to remap framebuffer into virtual memory (%pe)\n", vaddr); ret = PTR_ERR(vaddr); goto out_unpin; } @@ -584,7 +586,7 @@ void intel_fbdev_unregister(struct drm_i915_private *dev_priv) if (!current_is_async()) intel_fbdev_sync(ifbdev); - drm_fb_helper_unregister_fbi(&ifbdev->helper); + drm_fb_helper_unregister_info(&ifbdev->helper); } void intel_fbdev_fini(struct drm_i915_private *dev_priv) @@ -627,7 +629,7 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous if (!ifbdev || !ifbdev->vma) goto set_suspend; - info = ifbdev->helper.fbdev; + info = ifbdev->helper.info; if (synchronous) { /* Flush any pending work to turn the console on, and then diff --git a/drivers/gpu/drm/i915/display/intel_fdi.c b/drivers/gpu/drm/i915/display/intel_fdi.c index 7f47e5c85c81..063f1da4f229 100644 --- a/drivers/gpu/drm/i915/display/intel_fdi.c +++ b/drivers/gpu/drm/i915/display/intel_fdi.c @@ -5,6 +5,7 @@ #include <linux/string_helpers.h> +#include "i915_reg.h" #include "intel_atomic.h" #include "intel_crtc.h" #include "intel_ddi.h" diff --git a/drivers/gpu/drm/i915/display/intel_fifo_underrun.h b/drivers/gpu/drm/i915/display/intel_fifo_underrun.h index e04f22ac1f49..2e47d7d3c101 100644 --- a/drivers/gpu/drm/i915/display/intel_fifo_underrun.h +++ b/drivers/gpu/drm/i915/display/intel_fifo_underrun.h @@ -8,9 +8,8 @@ #include <linux/types.h> -#include "intel_display.h" - struct drm_i915_private; +enum pipe; bool intel_set_cpu_fifo_underrun_reporting(struct drm_i915_private *dev_priv, enum pipe pipe, bool enable); diff --git a/drivers/gpu/drm/i915/display/intel_frontbuffer.c b/drivers/gpu/drm/i915/display/intel_frontbuffer.c index d80e3e8a9b01..17a7aa8b28c2 100644 --- a/drivers/gpu/drm/i915/display/intel_frontbuffer.c +++ b/drivers/gpu/drm/i915/display/intel_frontbuffer.c @@ -88,7 +88,7 @@ static void frontbuffer_flush(struct drm_i915_private *i915, if (!frontbuffer_bits) return; - trace_intel_frontbuffer_flush(frontbuffer_bits, origin); + trace_intel_frontbuffer_flush(i915, frontbuffer_bits, origin); might_sleep(); intel_drrs_flush(i915, frontbuffer_bits); @@ -176,7 +176,7 @@ void __intel_fb_invalidate(struct intel_frontbuffer *front, spin_unlock(&i915->display.fb_tracking.lock); } - trace_intel_frontbuffer_invalidate(frontbuffer_bits, origin); + trace_intel_frontbuffer_invalidate(i915, frontbuffer_bits, origin); might_sleep(); intel_psr_invalidate(i915, frontbuffer_bits, origin); diff --git a/drivers/gpu/drm/i915/display/intel_global_state.c b/drivers/gpu/drm/i915/display/intel_global_state.c index 7a19215ad844..02b593b1e2ea 100644 --- a/drivers/gpu/drm/i915/display/intel_global_state.c +++ b/drivers/gpu/drm/i915/display/intel_global_state.c @@ -45,14 +45,14 @@ void intel_atomic_global_obj_init(struct drm_i915_private *dev_priv, obj->state = state; obj->funcs = funcs; - list_add_tail(&obj->head, &dev_priv->global_obj_list); + list_add_tail(&obj->head, &dev_priv->display.global.obj_list); } void intel_atomic_global_obj_cleanup(struct drm_i915_private *dev_priv) { struct intel_global_obj *obj, *next; - list_for_each_entry_safe(obj, next, &dev_priv->global_obj_list, head) { + list_for_each_entry_safe(obj, next, &dev_priv->display.global.obj_list, head) { list_del(&obj->head); drm_WARN_ON(&dev_priv->drm, kref_read(&obj->state->ref) != 1); diff --git a/drivers/gpu/drm/i915/display/intel_global_state.h b/drivers/gpu/drm/i915/display/intel_global_state.h index 1f16fa3073c9..f01ee0bb3e5a 100644 --- a/drivers/gpu/drm/i915/display/intel_global_state.h +++ b/drivers/gpu/drm/i915/display/intel_global_state.h @@ -27,7 +27,7 @@ struct intel_global_obj { }; #define intel_for_each_global_obj(obj, dev_priv) \ - list_for_each_entry(obj, &(dev_priv)->global_obj_list, head) + list_for_each_entry(obj, &(dev_priv)->display.global.obj_list, head) #define for_each_new_global_obj_in_state(__state, obj, new_obj_state, __i) \ for ((__i) = 0; \ diff --git a/drivers/gpu/drm/i915/display/intel_gmbus.c b/drivers/gpu/drm/i915/display/intel_gmbus.c index 74443f57f62d..a5840a28a69d 100644 --- a/drivers/gpu/drm/i915/display/intel_gmbus.c +++ b/drivers/gpu/drm/i915/display/intel_gmbus.c @@ -34,6 +34,8 @@ #include <drm/display/drm_hdcp_helper.h> #include "i915_drv.h" +#include "i915_irq.h" +#include "i915_reg.h" #include "intel_de.h" #include "intel_display_types.h" #include "intel_gmbus.h" @@ -49,9 +51,27 @@ struct intel_gmbus { struct drm_i915_private *i915; }; +enum gmbus_gpio { + GPIOA, + GPIOB, + GPIOC, + GPIOD, + GPIOE, + GPIOF, + GPIOG, + GPIOH, + __GPIOI_UNUSED, + GPIOJ, + GPIOK, + GPIOL, + GPIOM, + GPION, + GPIOO, +}; + struct gmbus_pin { const char *name; - enum i915_gpio gpio; + enum gmbus_gpio gpio; }; /* Map gmbus pin pairs to names and registers. */ diff --git a/drivers/gpu/drm/i915/display/intel_hdcp_regs.h b/drivers/gpu/drm/i915/display/intel_hdcp_regs.h index 2a3733e8966c..8023c85c7fa0 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp_regs.h +++ b/drivers/gpu/drm/i915/display/intel_hdcp_regs.h @@ -6,7 +6,7 @@ #ifndef __INTEL_HDCP_REGS_H__ #define __INTEL_HDCP_REGS_H__ -#include "i915_reg_defs.h" +#include "intel_display_reg_defs.h" /* HDCP Key Registers */ #define HDCP_KEY_CONF _MMIO(0x66c00) diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c index 7816b2a33fee..bac85d88054f 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.c +++ b/drivers/gpu/drm/i915/display/intel_hdmi.c @@ -42,6 +42,7 @@ #include "i915_debugfs.h" #include "i915_drv.h" +#include "i915_reg.h" #include "intel_atomic.h" #include "intel_connector.h" #include "intel_ddi.h" @@ -2057,13 +2058,6 @@ static bool hdmi_bpc_possible(const struct intel_crtc_state *crtc_state, int bpc if (!intel_hdmi_source_bpc_possible(dev_priv, bpc)) return false; - /* - * HDMI deep color affects the clocks, so it's only possible - * when not cloning with other encoder types. - */ - if (bpc > 8 && crtc_state->output_types != BIT(INTEL_OUTPUT_HDMI)) - return false; - /* Display Wa_1405510057:icl,ehl */ if (intel_hdmi_is_ycbcr420(crtc_state) && bpc == 10 && DISPLAY_VER(dev_priv) == 11 && @@ -2190,9 +2184,13 @@ static bool intel_hdmi_has_audio(struct intel_encoder *encoder, } static enum intel_output_format -intel_hdmi_output_format(struct intel_connector *connector, +intel_hdmi_output_format(const struct intel_crtc_state *crtc_state, + struct intel_connector *connector, bool ycbcr_420_output) { + if (!crtc_state->has_hdmi_sink) + return INTEL_OUTPUT_FORMAT_RGB; + if (connector->base.ycbcr_420_allowed && ycbcr_420_output) return INTEL_OUTPUT_FORMAT_YCBCR420; else @@ -2211,7 +2209,8 @@ static int intel_hdmi_compute_output_format(struct intel_encoder *encoder, bool ycbcr_420_only = drm_mode_is_420_only(info, adjusted_mode); int ret; - crtc_state->output_format = intel_hdmi_output_format(connector, ycbcr_420_only); + crtc_state->output_format = + intel_hdmi_output_format(crtc_state, connector, ycbcr_420_only); if (ycbcr_420_only && !intel_hdmi_is_ycbcr420(crtc_state)) { drm_dbg_kms(&i915->drm, @@ -2226,13 +2225,19 @@ static int intel_hdmi_compute_output_format(struct intel_encoder *encoder, !drm_mode_is_420_also(info, adjusted_mode)) return ret; - crtc_state->output_format = intel_hdmi_output_format(connector, true); + crtc_state->output_format = intel_hdmi_output_format(crtc_state, connector, true); ret = intel_hdmi_compute_clock(encoder, crtc_state, respect_downstream_limits); } return ret; } +static bool intel_hdmi_is_cloned(const struct intel_crtc_state *crtc_state) +{ + return crtc_state->uapi.encoder_mask && + !is_power_of_2(crtc_state->uapi.encoder_mask); +} + int intel_hdmi_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config, struct drm_connector_state *conn_state) @@ -2248,8 +2253,9 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder, return -EINVAL; pipe_config->output_format = INTEL_OUTPUT_FORMAT_RGB; - pipe_config->has_hdmi_sink = intel_has_hdmi_sink(intel_hdmi, - conn_state); + pipe_config->has_hdmi_sink = + intel_has_hdmi_sink(intel_hdmi, conn_state) && + !intel_hdmi_is_cloned(pipe_config); if (pipe_config->has_hdmi_sink) pipe_config->has_infoframe = true; @@ -2257,9 +2263,6 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder, if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK) pipe_config->pixel_multiplier = 2; - if (HAS_PCH_SPLIT(dev_priv) && !HAS_DDI(dev_priv)) - pipe_config->has_pch_encoder = true; - pipe_config->has_audio = intel_hdmi_has_audio(encoder, pipe_config, conn_state); @@ -2355,7 +2358,7 @@ intel_hdmi_unset_edid(struct drm_connector *connector) } static void -intel_hdmi_dp_dual_mode_detect(struct drm_connector *connector, bool has_edid) +intel_hdmi_dp_dual_mode_detect(struct drm_connector *connector) { struct drm_i915_private *dev_priv = to_i915(connector->dev); struct intel_hdmi *hdmi = intel_attached_hdmi(to_intel_connector(connector)); @@ -2371,16 +2374,10 @@ intel_hdmi_dp_dual_mode_detect(struct drm_connector *connector, bool has_edid) * CONFIG1 pin, but no such luck on our hardware. * * The only method left to us is to check the VBT to see - * if the port is a dual mode capable DP port. But let's - * only do that when we sucesfully read the EDID, to avoid - * confusing log messages about DP dual mode adaptors when - * there's nothing connected to the port. + * if the port is a dual mode capable DP port. */ if (type == DRM_DP_DUAL_MODE_UNKNOWN) { - /* An overridden EDID imply that we want this port for testing. - * Make sure not to set limits for that port. - */ - if (has_edid && !connector->override_edid && + if (!connector->force && intel_bios_is_port_dp_dual_mode(dev_priv, port)) { drm_dbg_kms(&dev_priv->drm, "Assuming DP dual mode adaptor presence based on VBT\n"); @@ -2435,18 +2432,18 @@ intel_hdmi_set_edid(struct drm_connector *connector) intel_gmbus_force_bit(i2c, false); } - intel_hdmi_dp_dual_mode_detect(connector, edid != NULL); - - intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS, wakeref); - to_intel_connector(connector)->detect_edid = edid; if (edid && edid->input & DRM_EDID_INPUT_DIGITAL) { intel_hdmi->has_audio = drm_detect_monitor_audio(edid); intel_hdmi->has_hdmi_sink = drm_detect_hdmi_monitor(edid); + intel_hdmi_dp_dual_mode_detect(connector); + connected = true; } + intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS, wakeref); + cec_notifier_set_phys_addr_from_edid(intel_hdmi->cec_notifier, edid); return connected; @@ -2956,9 +2953,8 @@ void intel_hdmi_init_connector(struct intel_digital_port *dig_port, ddc); drm_connector_helper_add(connector, &intel_hdmi_connector_helper_funcs); - connector->interlace_allowed = 1; - connector->doublescan_allowed = 0; - connector->stereo_allowed = 1; + connector->interlace_allowed = true; + connector->stereo_allowed = true; if (DISPLAY_VER(dev_priv) >= 10) connector->ycbcr_420_allowed = true; diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.h b/drivers/gpu/drm/i915/display/intel_hdmi.h index 93f65a917c36..774dda2376ed 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.h +++ b/drivers/gpu/drm/i915/display/intel_hdmi.h @@ -6,20 +6,20 @@ #ifndef __INTEL_HDMI_H__ #define __INTEL_HDMI_H__ -#include <linux/hdmi.h> #include <linux/types.h> +enum hdmi_infoframe_type; +enum port; struct drm_connector; +struct drm_connector_state; struct drm_encoder; struct drm_i915_private; struct intel_connector; +struct intel_crtc_state; struct intel_digital_port; struct intel_encoder; -struct intel_crtc_state; struct intel_hdmi; -struct drm_connector_state; union hdmi_infoframe; -enum port; void intel_hdmi_init_connector(struct intel_digital_port *dig_port, struct intel_connector *intel_connector); diff --git a/drivers/gpu/drm/i915/display/intel_hotplug.c b/drivers/gpu/drm/i915/display/intel_hotplug.c index f7a2f485b177..907ab7526cb4 100644 --- a/drivers/gpu/drm/i915/display/intel_hotplug.c +++ b/drivers/gpu/drm/i915/display/intel_hotplug.c @@ -90,6 +90,9 @@ enum hpd_pin intel_hpd_pin_default(struct drm_i915_private *dev_priv, return HPD_PORT_A + port - PORT_A; } +/* Threshold == 5 for long IRQs, 50 for short */ +#define HPD_STORM_DEFAULT_THRESHOLD 50 + #define HPD_STORM_DETECT_PERIOD 1000 #define HPD_STORM_REENABLE_DELAY (2 * 60 * 1000) #define HPD_RETRY_DELAY 1000 @@ -175,14 +178,13 @@ static bool intel_hpd_irq_storm_detect(struct drm_i915_private *dev_priv, static void intel_hpd_irq_storm_switch_to_polling(struct drm_i915_private *dev_priv) { - struct drm_device *dev = &dev_priv->drm; struct drm_connector_list_iter conn_iter; struct intel_connector *connector; bool hpd_disabled = false; lockdep_assert_held(&dev_priv->irq_lock); - drm_connector_list_iter_begin(dev, &conn_iter); + drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter); for_each_intel_connector_iter(connector, &conn_iter) { enum hpd_pin pin; @@ -208,7 +210,7 @@ intel_hpd_irq_storm_switch_to_polling(struct drm_i915_private *dev_priv) /* Enable polling and queue hotplug re-enabling. */ if (hpd_disabled) { - drm_kms_helper_poll_enable(dev); + drm_kms_helper_poll_enable(&dev_priv->drm); mod_delayed_work(system_wq, &dev_priv->display.hotplug.reenable_work, msecs_to_jiffies(HPD_STORM_REENABLE_DELAY)); } @@ -219,7 +221,6 @@ static void intel_hpd_irq_storm_reenable_work(struct work_struct *work) struct drm_i915_private *dev_priv = container_of(work, typeof(*dev_priv), display.hotplug.reenable_work.work); - struct drm_device *dev = &dev_priv->drm; struct drm_connector_list_iter conn_iter; struct intel_connector *connector; intel_wakeref_t wakeref; @@ -229,7 +230,7 @@ static void intel_hpd_irq_storm_reenable_work(struct work_struct *work) spin_lock_irq(&dev_priv->irq_lock); - drm_connector_list_iter_begin(dev, &conn_iter); + drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter); for_each_intel_connector_iter(connector, &conn_iter) { pin = intel_connector_hpd_pin(connector); if (pin == HPD_NONE || @@ -367,14 +368,13 @@ static void i915_hotplug_work_func(struct work_struct *work) struct drm_i915_private *dev_priv = container_of(work, struct drm_i915_private, display.hotplug.hotplug_work.work); - struct drm_device *dev = &dev_priv->drm; struct drm_connector_list_iter conn_iter; struct intel_connector *connector; u32 changed = 0, retry = 0; u32 hpd_event_bits; u32 hpd_retry_bits; - mutex_lock(&dev->mode_config.mutex); + mutex_lock(&dev_priv->drm.mode_config.mutex); drm_dbg_kms(&dev_priv->drm, "running encoder hotplug functions\n"); spin_lock_irq(&dev_priv->irq_lock); @@ -389,7 +389,7 @@ static void i915_hotplug_work_func(struct work_struct *work) spin_unlock_irq(&dev_priv->irq_lock); - drm_connector_list_iter_begin(dev, &conn_iter); + drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter); for_each_intel_connector_iter(connector, &conn_iter) { enum hpd_pin pin; u32 hpd_bit; @@ -426,10 +426,10 @@ static void i915_hotplug_work_func(struct work_struct *work) } } drm_connector_list_iter_end(&conn_iter); - mutex_unlock(&dev->mode_config.mutex); + mutex_unlock(&dev_priv->drm.mode_config.mutex); if (changed) - drm_kms_helper_hotplug_event(dev); + drm_kms_helper_hotplug_event(&dev_priv->drm); /* Remove shared HPD pins that have changed */ retry &= ~changed; @@ -612,16 +612,15 @@ static void i915_hpd_poll_init_work(struct work_struct *work) struct drm_i915_private *dev_priv = container_of(work, struct drm_i915_private, display.hotplug.poll_init_work); - struct drm_device *dev = &dev_priv->drm; struct drm_connector_list_iter conn_iter; struct intel_connector *connector; bool enabled; - mutex_lock(&dev->mode_config.mutex); + mutex_lock(&dev_priv->drm.mode_config.mutex); enabled = READ_ONCE(dev_priv->display.hotplug.poll_enabled); - drm_connector_list_iter_begin(dev, &conn_iter); + drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter); for_each_intel_connector_iter(connector, &conn_iter) { enum hpd_pin pin; @@ -638,16 +637,16 @@ static void i915_hpd_poll_init_work(struct work_struct *work) drm_connector_list_iter_end(&conn_iter); if (enabled) - drm_kms_helper_poll_enable(dev); + drm_kms_helper_poll_enable(&dev_priv->drm); - mutex_unlock(&dev->mode_config.mutex); + mutex_unlock(&dev_priv->drm.mode_config.mutex); /* * We might have missed any hotplugs that happened while we were * in the middle of disabling polling */ if (!enabled) - drm_helper_hpd_irq_event(dev); + drm_helper_hpd_irq_event(&dev_priv->drm); } /** @@ -711,14 +710,23 @@ void intel_hpd_poll_disable(struct drm_i915_private *dev_priv) schedule_work(&dev_priv->display.hotplug.poll_init_work); } -void intel_hpd_init_work(struct drm_i915_private *dev_priv) +void intel_hpd_init_early(struct drm_i915_private *i915) { - INIT_DELAYED_WORK(&dev_priv->display.hotplug.hotplug_work, + INIT_DELAYED_WORK(&i915->display.hotplug.hotplug_work, i915_hotplug_work_func); - INIT_WORK(&dev_priv->display.hotplug.dig_port_work, i915_digport_work_func); - INIT_WORK(&dev_priv->display.hotplug.poll_init_work, i915_hpd_poll_init_work); - INIT_DELAYED_WORK(&dev_priv->display.hotplug.reenable_work, + INIT_WORK(&i915->display.hotplug.dig_port_work, i915_digport_work_func); + INIT_WORK(&i915->display.hotplug.poll_init_work, i915_hpd_poll_init_work); + INIT_DELAYED_WORK(&i915->display.hotplug.reenable_work, intel_hpd_irq_storm_reenable_work); + + i915->display.hotplug.hpd_storm_threshold = HPD_STORM_DEFAULT_THRESHOLD; + /* If we have MST support, we want to avoid doing short HPD IRQ storm + * detection, as short HPD storms will occur as a natural part of + * sideband messaging with MST. + * On older platforms however, IRQ storms can occur with both long and + * short pulses, as seen on some G4x systems. + */ + i915->display.hotplug.hpd_short_storm_enabled = !HAS_DP_MST(i915); } void intel_hpd_cancel_work(struct drm_i915_private *dev_priv) @@ -767,3 +775,169 @@ void intel_hpd_enable(struct drm_i915_private *dev_priv, enum hpd_pin pin) dev_priv->display.hotplug.stats[pin].state = HPD_ENABLED; spin_unlock_irq(&dev_priv->irq_lock); } + +static int i915_hpd_storm_ctl_show(struct seq_file *m, void *data) +{ + struct drm_i915_private *dev_priv = m->private; + struct intel_hotplug *hotplug = &dev_priv->display.hotplug; + + /* Synchronize with everything first in case there's been an HPD + * storm, but we haven't finished handling it in the kernel yet + */ + intel_synchronize_irq(dev_priv); + flush_work(&dev_priv->display.hotplug.dig_port_work); + flush_delayed_work(&dev_priv->display.hotplug.hotplug_work); + + seq_printf(m, "Threshold: %d\n", hotplug->hpd_storm_threshold); + seq_printf(m, "Detected: %s\n", + str_yes_no(delayed_work_pending(&hotplug->reenable_work))); + + return 0; +} + +static ssize_t i915_hpd_storm_ctl_write(struct file *file, + const char __user *ubuf, size_t len, + loff_t *offp) +{ + struct seq_file *m = file->private_data; + struct drm_i915_private *dev_priv = m->private; + struct intel_hotplug *hotplug = &dev_priv->display.hotplug; + unsigned int new_threshold; + int i; + char *newline; + char tmp[16]; + + if (len >= sizeof(tmp)) + return -EINVAL; + + if (copy_from_user(tmp, ubuf, len)) + return -EFAULT; + + tmp[len] = '\0'; + + /* Strip newline, if any */ + newline = strchr(tmp, '\n'); + if (newline) + *newline = '\0'; + + if (strcmp(tmp, "reset") == 0) + new_threshold = HPD_STORM_DEFAULT_THRESHOLD; + else if (kstrtouint(tmp, 10, &new_threshold) != 0) + return -EINVAL; + + if (new_threshold > 0) + drm_dbg_kms(&dev_priv->drm, + "Setting HPD storm detection threshold to %d\n", + new_threshold); + else + drm_dbg_kms(&dev_priv->drm, "Disabling HPD storm detection\n"); + + spin_lock_irq(&dev_priv->irq_lock); + hotplug->hpd_storm_threshold = new_threshold; + /* Reset the HPD storm stats so we don't accidentally trigger a storm */ + for_each_hpd_pin(i) + hotplug->stats[i].count = 0; + spin_unlock_irq(&dev_priv->irq_lock); + + /* Re-enable hpd immediately if we were in an irq storm */ + flush_delayed_work(&dev_priv->display.hotplug.reenable_work); + + return len; +} + +static int i915_hpd_storm_ctl_open(struct inode *inode, struct file *file) +{ + return single_open(file, i915_hpd_storm_ctl_show, inode->i_private); +} + +static const struct file_operations i915_hpd_storm_ctl_fops = { + .owner = THIS_MODULE, + .open = i915_hpd_storm_ctl_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + .write = i915_hpd_storm_ctl_write +}; + +static int i915_hpd_short_storm_ctl_show(struct seq_file *m, void *data) +{ + struct drm_i915_private *dev_priv = m->private; + + seq_printf(m, "Enabled: %s\n", + str_yes_no(dev_priv->display.hotplug.hpd_short_storm_enabled)); + + return 0; +} + +static int +i915_hpd_short_storm_ctl_open(struct inode *inode, struct file *file) +{ + return single_open(file, i915_hpd_short_storm_ctl_show, + inode->i_private); +} + +static ssize_t i915_hpd_short_storm_ctl_write(struct file *file, + const char __user *ubuf, + size_t len, loff_t *offp) +{ + struct seq_file *m = file->private_data; + struct drm_i915_private *dev_priv = m->private; + struct intel_hotplug *hotplug = &dev_priv->display.hotplug; + char *newline; + char tmp[16]; + int i; + bool new_state; + + if (len >= sizeof(tmp)) + return -EINVAL; + + if (copy_from_user(tmp, ubuf, len)) + return -EFAULT; + + tmp[len] = '\0'; + + /* Strip newline, if any */ + newline = strchr(tmp, '\n'); + if (newline) + *newline = '\0'; + + /* Reset to the "default" state for this system */ + if (strcmp(tmp, "reset") == 0) + new_state = !HAS_DP_MST(dev_priv); + else if (kstrtobool(tmp, &new_state) != 0) + return -EINVAL; + + drm_dbg_kms(&dev_priv->drm, "%sabling HPD short storm detection\n", + new_state ? "En" : "Dis"); + + spin_lock_irq(&dev_priv->irq_lock); + hotplug->hpd_short_storm_enabled = new_state; + /* Reset the HPD storm stats so we don't accidentally trigger a storm */ + for_each_hpd_pin(i) + hotplug->stats[i].count = 0; + spin_unlock_irq(&dev_priv->irq_lock); + + /* Re-enable hpd immediately if we were in an irq storm */ + flush_delayed_work(&dev_priv->display.hotplug.reenable_work); + + return len; +} + +static const struct file_operations i915_hpd_short_storm_ctl_fops = { + .owner = THIS_MODULE, + .open = i915_hpd_short_storm_ctl_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + .write = i915_hpd_short_storm_ctl_write, +}; + +void intel_hpd_debugfs_register(struct drm_i915_private *i915) +{ + struct drm_minor *minor = i915->drm.primary; + + debugfs_create_file("i915_hpd_storm_ctl", 0644, minor->debugfs_root, + i915, &i915_hpd_storm_ctl_fops); + debugfs_create_file("i915_hpd_short_storm_ctl", 0644, minor->debugfs_root, + i915, &i915_hpd_short_storm_ctl_fops); +} diff --git a/drivers/gpu/drm/i915/display/intel_hotplug.h b/drivers/gpu/drm/i915/display/intel_hotplug.h index b87e95d606e6..424ae5dbf5a0 100644 --- a/drivers/gpu/drm/i915/display/intel_hotplug.h +++ b/drivers/gpu/drm/i915/display/intel_hotplug.h @@ -22,11 +22,12 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv, u32 pin_mask, u32 long_mask); void intel_hpd_trigger_irq(struct intel_digital_port *dig_port); void intel_hpd_init(struct drm_i915_private *dev_priv); -void intel_hpd_init_work(struct drm_i915_private *dev_priv); +void intel_hpd_init_early(struct drm_i915_private *i915); void intel_hpd_cancel_work(struct drm_i915_private *dev_priv); enum hpd_pin intel_hpd_pin_default(struct drm_i915_private *dev_priv, enum port port); bool intel_hpd_disable(struct drm_i915_private *dev_priv, enum hpd_pin pin); void intel_hpd_enable(struct drm_i915_private *dev_priv, enum hpd_pin pin); +void intel_hpd_debugfs_register(struct drm_i915_private *i915); #endif /* __INTEL_HOTPLUG_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_hti.c b/drivers/gpu/drm/i915/display/intel_hti.c new file mode 100644 index 000000000000..12a1f4ce1a77 --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_hti.c @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2022 Intel Corporation + */ + +#include "i915_drv.h" +#include "intel_de.h" +#include "intel_display.h" +#include "intel_hti.h" +#include "intel_hti_regs.h" + +void intel_hti_init(struct drm_i915_private *i915) +{ + /* + * If the platform has HTI, we need to find out whether it has reserved + * any display resources before we create our display outputs. + */ + if (INTEL_INFO(i915)->display.has_hti) + i915->display.hti.state = intel_de_read(i915, HDPORT_STATE); +} + +bool intel_hti_uses_phy(struct drm_i915_private *i915, enum phy phy) +{ + return i915->display.hti.state & HDPORT_ENABLED && + i915->display.hti.state & HDPORT_DDI_USED(phy); +} + +u32 intel_hti_dpll_mask(struct drm_i915_private *i915) +{ + if (!(i915->display.hti.state & HDPORT_ENABLED)) + return 0; + + /* + * Note: This is subtle. The values must coincide with what's defined + * for the platform. + */ + return REG_FIELD_GET(HDPORT_DPLL_USED_MASK, i915->display.hti.state); +} diff --git a/drivers/gpu/drm/i915/display/intel_hti.h b/drivers/gpu/drm/i915/display/intel_hti.h new file mode 100644 index 000000000000..2893d6668657 --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_hti.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2022 Intel Corporation + */ + +#ifndef __INTEL_HTI_H__ +#define __INTEL_HTI_H__ + +#include <linux/types.h> + +struct drm_i915_private; +enum phy; + +void intel_hti_init(struct drm_i915_private *i915); +bool intel_hti_uses_phy(struct drm_i915_private *i915, enum phy phy); +u32 intel_hti_dpll_mask(struct drm_i915_private *i915); + +#endif /* __INTEL_HTI_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_hti_regs.h b/drivers/gpu/drm/i915/display/intel_hti_regs.h new file mode 100644 index 000000000000..e206f2837fc8 --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_hti_regs.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2022 Intel Corporation + */ + +#ifndef __INTEL_HTI_REGS_H__ +#define __INTEL_HTI_REGS_H__ + +#include "i915_reg_defs.h" + +#define HDPORT_STATE _MMIO(0x45050) +#define HDPORT_DPLL_USED_MASK REG_GENMASK(15, 12) +#define HDPORT_DDI_USED(phy) REG_BIT(2 * (phy) + 1) +#define HDPORT_ENABLED REG_BIT(0) + +#endif /* __INTEL_HTI_REGS_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_lpe_audio.c b/drivers/gpu/drm/i915/display/intel_lpe_audio.c index dca6003ccac8..8aaaef4d7856 100644 --- a/drivers/gpu/drm/i915/display/intel_lpe_audio.c +++ b/drivers/gpu/drm/i915/display/intel_lpe_audio.c @@ -71,6 +71,8 @@ #include <drm/intel_lpe_audio.h> #include "i915_drv.h" +#include "i915_irq.h" +#include "i915_reg.h" #include "intel_de.h" #include "intel_lpe_audio.h" #include "intel_pci_config.h" @@ -80,8 +82,7 @@ static struct platform_device * lpe_audio_platdev_create(struct drm_i915_private *dev_priv) { - struct drm_device *dev = &dev_priv->drm; - struct pci_dev *pdev = to_pci_dev(dev->dev); + struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); struct platform_device_info pinfo = {}; struct resource *rsc; struct platform_device *platdev; @@ -101,14 +102,14 @@ lpe_audio_platdev_create(struct drm_i915_private *dev_priv) rsc[0].flags = IORESOURCE_IRQ; rsc[0].name = "hdmi-lpe-audio-irq"; - rsc[1].start = pci_resource_start(pdev, GTTMMADR_BAR) + + rsc[1].start = pci_resource_start(pdev, GEN4_GTTMMADR_BAR) + I915_HDMI_LPE_AUDIO_BASE; - rsc[1].end = pci_resource_start(pdev, GTTMMADR_BAR) + + rsc[1].end = pci_resource_start(pdev, GEN4_GTTMMADR_BAR) + I915_HDMI_LPE_AUDIO_BASE + I915_HDMI_LPE_AUDIO_SIZE - 1; rsc[1].flags = IORESOURCE_MEM; rsc[1].name = "hdmi-lpe-audio-mmio"; - pinfo.parent = dev->dev; + pinfo.parent = dev_priv->drm.dev; pinfo.name = "hdmi-lpe-audio"; pinfo.id = -1; pinfo.res = rsc; diff --git a/drivers/gpu/drm/i915/display/intel_lspcon.c b/drivers/gpu/drm/i915/display/intel_lspcon.c index 15d59de8810e..9ff1c0b223ad 100644 --- a/drivers/gpu/drm/i915/display/intel_lspcon.c +++ b/drivers/gpu/drm/i915/display/intel_lspcon.c @@ -28,6 +28,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_edid.h> +#include "i915_reg.h" #include "intel_de.h" #include "intel_display_types.h" #include "intel_dp.h" diff --git a/drivers/gpu/drm/i915/display/intel_lvds.c b/drivers/gpu/drm/i915/display/intel_lvds.c index e5352239b2a2..7bf1bdfd03ec 100644 --- a/drivers/gpu/drm/i915/display/intel_lvds.c +++ b/drivers/gpu/drm/i915/display/intel_lvds.c @@ -39,6 +39,7 @@ #include <drm/drm_edid.h> #include "i915_drv.h" +#include "i915_reg.h" #include "intel_atomic.h" #include "intel_backlight.h" #include "intel_connector.h" @@ -78,9 +79,9 @@ struct intel_lvds_encoder { struct intel_connector *attached_connector; }; -static struct intel_lvds_encoder *to_lvds_encoder(struct drm_encoder *encoder) +static struct intel_lvds_encoder *to_lvds_encoder(struct intel_encoder *encoder) { - return container_of(encoder, struct intel_lvds_encoder, base.base); + return container_of(encoder, struct intel_lvds_encoder, base); } bool intel_lvds_port_enabled(struct drm_i915_private *dev_priv, @@ -103,7 +104,7 @@ static bool intel_lvds_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base); + struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(encoder); intel_wakeref_t wakeref; bool ret; @@ -123,7 +124,7 @@ static void intel_lvds_get_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base); + struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(encoder); u32 tmp, flags = 0; pipe_config->output_types |= BIT(INTEL_OUTPUT_LVDS); @@ -229,7 +230,7 @@ static void intel_pre_enable_lvds(struct intel_atomic_state *state, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { - struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base); + struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(encoder); struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc); const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode; @@ -312,7 +313,7 @@ static void intel_enable_lvds(struct intel_atomic_state *state, const struct drm_connector_state *conn_state) { struct drm_device *dev = encoder->base.dev; - struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base); + struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(encoder); struct drm_i915_private *dev_priv = to_i915(dev); intel_de_write(dev_priv, lvds_encoder->reg, @@ -334,7 +335,7 @@ static void intel_disable_lvds(struct intel_atomic_state *state, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { - struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base); + struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(encoder); struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); intel_de_write(dev_priv, PP_CONTROL(0), @@ -413,7 +414,7 @@ static int intel_lvds_compute_config(struct intel_encoder *intel_encoder, { struct drm_i915_private *dev_priv = to_i915(intel_encoder->base.dev); struct intel_lvds_encoder *lvds_encoder = - to_lvds_encoder(&intel_encoder->base); + to_lvds_encoder(intel_encoder); struct intel_connector *intel_connector = lvds_encoder->attached_connector; struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode; @@ -775,7 +776,7 @@ bool intel_is_dual_link_lvds(struct drm_i915_private *dev_priv) { struct intel_encoder *encoder = intel_get_lvds_encoder(dev_priv); - return encoder && to_lvds_encoder(&encoder->base)->is_dual_link; + return encoder && to_lvds_encoder(encoder)->is_dual_link; } static bool compute_is_dual_link_lvds(struct intel_lvds_encoder *lvds_encoder) @@ -814,6 +815,11 @@ static bool compute_is_dual_link_lvds(struct intel_lvds_encoder *lvds_encoder) return (val & LVDS_CLKB_POWER_MASK) == LVDS_CLKB_POWER_UP; } +static void intel_lvds_add_properties(struct drm_connector *connector) +{ + intel_attach_scaling_mode_property(connector); +} + /** * intel_lvds_init - setup LVDS connectors on this device * @dev_priv: i915 device @@ -823,7 +829,6 @@ static bool compute_is_dual_link_lvds(struct intel_lvds_encoder *lvds_encoder) */ void intel_lvds_init(struct drm_i915_private *dev_priv) { - struct drm_device *dev = &dev_priv->drm; struct intel_lvds_encoder *lvds_encoder; struct intel_encoder *intel_encoder; struct intel_connector *intel_connector; @@ -833,11 +838,10 @@ void intel_lvds_init(struct drm_i915_private *dev_priv) i915_reg_t lvds_reg; u32 lvds; u8 pin; - u32 allowed_scalers; /* Skip init on machines we know falsely report LVDS */ if (dmi_check_system(intel_no_lvds)) { - drm_WARN(dev, !dev_priv->display.vbt.int_lvds_support, + drm_WARN(&dev_priv->drm, !dev_priv->display.vbt.int_lvds_support, "Useless DMI match. Internal LVDS support disabled by VBT\n"); return; } @@ -886,10 +890,10 @@ void intel_lvds_init(struct drm_i915_private *dev_priv) intel_encoder = &lvds_encoder->base; encoder = &intel_encoder->base; connector = &intel_connector->base; - drm_connector_init(dev, &intel_connector->base, &intel_lvds_connector_funcs, + drm_connector_init(&dev_priv->drm, &intel_connector->base, &intel_lvds_connector_funcs, DRM_MODE_CONNECTOR_LVDS); - drm_encoder_init(dev, &intel_encoder->base, &intel_lvds_enc_funcs, + drm_encoder_init(&dev_priv->drm, &intel_encoder->base, &intel_lvds_enc_funcs, DRM_MODE_ENCODER_LVDS, "LVDS"); intel_encoder->enable = intel_enable_lvds; @@ -920,17 +924,10 @@ void intel_lvds_init(struct drm_i915_private *dev_priv) drm_connector_helper_add(connector, &intel_lvds_connector_helper_funcs); connector->display_info.subpixel_order = SubPixelHorizontalRGB; - connector->interlace_allowed = false; - connector->doublescan_allowed = false; lvds_encoder->reg = lvds_reg; - /* create the scaling mode property */ - allowed_scalers = BIT(DRM_MODE_SCALE_ASPECT); - allowed_scalers |= BIT(DRM_MODE_SCALE_FULLSCREEN); - allowed_scalers |= BIT(DRM_MODE_SCALE_CENTER); - drm_connector_attach_scaling_mode_property(connector, allowed_scalers); - connector->state->scaling_mode = DRM_MODE_SCALE_ASPECT; + intel_lvds_add_properties(connector); intel_lvds_pps_get_hw_state(dev_priv, &lvds_encoder->init_pps); lvds_encoder->init_lvds_val = lvds; @@ -947,7 +944,7 @@ void intel_lvds_init(struct drm_i915_private *dev_priv) * Attempt to get the fixed panel mode from DDC. Assume that the * preferred mode is the right one. */ - mutex_lock(&dev->mode_config.mutex); + mutex_lock(&dev_priv->drm.mode_config.mutex); if (vga_switcheroo_handler_flags() & VGA_SWITCHEROO_CAN_SWITCH_DDC) edid = drm_get_edid_switcheroo(connector, intel_gmbus_get_adapter(dev_priv, pin)); @@ -971,8 +968,7 @@ void intel_lvds_init(struct drm_i915_private *dev_priv) IS_ERR(edid) ? NULL : edid); /* Try EDID first */ - intel_panel_add_edid_fixed_modes(intel_connector, - intel_connector->panel.vbt.drrs_type != DRRS_TYPE_NONE); + intel_panel_add_edid_fixed_modes(intel_connector, true); /* Failed to get EDID, what about VBT? */ if (!intel_panel_preferred_fixed_mode(intel_connector)) @@ -986,7 +982,7 @@ void intel_lvds_init(struct drm_i915_private *dev_priv) if (!intel_panel_preferred_fixed_mode(intel_connector)) intel_panel_add_encoder_fixed_mode(intel_connector, intel_encoder); - mutex_unlock(&dev->mode_config.mutex); + mutex_unlock(&dev_priv->drm.mode_config.mutex); /* If we still don't have a mode after all that, give up. */ if (!intel_panel_preferred_fixed_mode(intel_connector)) diff --git a/drivers/gpu/drm/i915/display/intel_tc_phy_regs.h b/drivers/gpu/drm/i915/display/intel_mg_phy_regs.h index 5a545086f959..0e8248bce52d 100644 --- a/drivers/gpu/drm/i915/display/intel_tc_phy_regs.h +++ b/drivers/gpu/drm/i915/display/intel_mg_phy_regs.h @@ -3,10 +3,10 @@ * Copyright © 2022 Intel Corporation */ -#ifndef __INTEL_TC_PHY_REGS__ -#define __INTEL_TC_PHY_REGS__ +#ifndef __INTEL_MG_PHY_REGS__ +#define __INTEL_MG_PHY_REGS__ -#include "i915_reg_defs.h" +#include "intel_display_reg_defs.h" #define MG_PHY_PORT_LN(ln, tc_port, ln0p1, ln0p2, ln1p1) \ _MMIO(_PORT(tc_port, ln0p1, ln0p2) + (ln) * ((ln1p1) - (ln0p1))) @@ -277,4 +277,4 @@ _MG_PLL_TDC_COLDST_BIAS_PORT1, \ _MG_PLL_TDC_COLDST_BIAS_PORT2) -#endif /* __INTEL_TC_PHY_REGS__ */ +#endif /* __INTEL_MG_PHY_REGS__ */ diff --git a/drivers/gpu/drm/i915/display/intel_modeset_setup.c b/drivers/gpu/drm/i915/display/intel_modeset_setup.c index cbfabd58b75a..96395bfbd41d 100644 --- a/drivers/gpu/drm/i915/display/intel_modeset_setup.c +++ b/drivers/gpu/drm/i915/display/intel_modeset_setup.c @@ -10,6 +10,7 @@ #include <drm/drm_atomic_state_helper.h> #include "i915_drv.h" +#include "i915_reg.h" #include "intel_atomic.h" #include "intel_bw.h" #include "intel_color.h" @@ -155,6 +156,12 @@ static void intel_crtc_copy_hw_to_uapi_state(struct intel_crtc_state *crtc_state crtc_state->uapi.adjusted_mode = crtc_state->hw.adjusted_mode; crtc_state->uapi.scaling_filter = crtc_state->hw.scaling_filter; + /* assume 1:1 mapping */ + drm_property_replace_blob(&crtc_state->hw.degamma_lut, + crtc_state->pre_csc_lut); + drm_property_replace_blob(&crtc_state->hw.gamma_lut, + crtc_state->post_csc_lut); + drm_property_replace_blob(&crtc_state->uapi.degamma_lut, crtc_state->hw.degamma_lut); drm_property_replace_blob(&crtc_state->uapi.gamma_lut, @@ -205,13 +212,21 @@ static bool intel_crtc_has_encoders(struct intel_crtc *crtc) static struct intel_connector *intel_encoder_find_connector(struct intel_encoder *encoder) { - struct drm_device *dev = encoder->base.dev; + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + struct drm_connector_list_iter conn_iter; struct intel_connector *connector; + struct intel_connector *found_connector = NULL; - for_each_connector_on_encoder(dev, &encoder->base, connector) - return connector; + drm_connector_list_iter_begin(&i915->drm, &conn_iter); + for_each_intel_connector_iter(connector, &conn_iter) { + if (&encoder->base == connector->base.encoder) { + found_connector = connector; + break; + } + } + drm_connector_list_iter_end(&conn_iter); - return NULL; + return found_connector; } static void intel_sanitize_fifo_underrun_reporting(const struct intel_crtc_state *crtc_state) diff --git a/drivers/gpu/drm/i915/display/intel_modeset_verify.c b/drivers/gpu/drm/i915/display/intel_modeset_verify.c index 0fdcf2e6d57f..842d70f0dfd2 100644 --- a/drivers/gpu/drm/i915/display/intel_modeset_verify.c +++ b/drivers/gpu/drm/i915/display/intel_modeset_verify.c @@ -227,7 +227,8 @@ void intel_modeset_verify_crtc(struct intel_crtc *crtc, struct intel_crtc_state *old_crtc_state, struct intel_crtc_state *new_crtc_state) { - if (!intel_crtc_needs_modeset(new_crtc_state) && !new_crtc_state->update_pipe) + if (!intel_crtc_needs_modeset(new_crtc_state) && + !intel_crtc_needs_fastset(new_crtc_state)) return; intel_wm_state_verify(crtc, new_crtc_state); diff --git a/drivers/gpu/drm/i915/display/intel_opregion.c b/drivers/gpu/drm/i915/display/intel_opregion.c index caa07ef34f21..e0184745632c 100644 --- a/drivers/gpu/drm/i915/display/intel_opregion.c +++ b/drivers/gpu/drm/i915/display/intel_opregion.c @@ -463,7 +463,6 @@ static u32 asle_set_backlight(struct drm_i915_private *dev_priv, u32 bclp) struct intel_connector *connector; struct drm_connector_list_iter conn_iter; struct opregion_asle *asle = dev_priv->display.opregion.asle; - struct drm_device *dev = &dev_priv->drm; drm_dbg(&dev_priv->drm, "bclp = 0x%08x\n", bclp); @@ -480,7 +479,7 @@ static u32 asle_set_backlight(struct drm_i915_private *dev_priv, u32 bclp) if (bclp > 255) return ASLC_BACKLIGHT_FAILED; - drm_modeset_lock(&dev->mode_config.connection_mutex, NULL); + drm_modeset_lock(&dev_priv->drm.mode_config.connection_mutex, NULL); /* * Update backlight on all connectors that support backlight (usually @@ -488,13 +487,13 @@ static u32 asle_set_backlight(struct drm_i915_private *dev_priv, u32 bclp) */ drm_dbg_kms(&dev_priv->drm, "updating opregion backlight %d/255\n", bclp); - drm_connector_list_iter_begin(dev, &conn_iter); + drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter); for_each_intel_connector_iter(connector, &conn_iter) intel_backlight_set_acpi(connector->base.state, bclp, 255); drm_connector_list_iter_end(&conn_iter); asle->cblv = DIV_ROUND_UP(bclp * 100, 255) | ASLE_CBLV_VALID; - drm_modeset_unlock(&dev->mode_config.connection_mutex); + drm_modeset_unlock(&dev_priv->drm.mode_config.connection_mutex); return 0; diff --git a/drivers/gpu/drm/i915/display/intel_panel.c b/drivers/gpu/drm/i915/display/intel_panel.c index 41cec9dc4223..1640726bfbf6 100644 --- a/drivers/gpu/drm/i915/display/intel_panel.c +++ b/drivers/gpu/drm/i915/display/intel_panel.c @@ -31,6 +31,7 @@ #include <linux/kernel.h> #include <linux/pwm.h> +#include "i915_reg.h" #include "intel_backlight.h" #include "intel_connector.h" #include "intel_de.h" @@ -85,9 +86,10 @@ static bool is_alt_drrs_mode(const struct drm_display_mode *mode, static bool is_alt_fixed_mode(const struct drm_display_mode *mode, const struct drm_display_mode *preferred_mode) { - return drm_mode_match(mode, preferred_mode, - DRM_MODE_MATCH_FLAGS | - DRM_MODE_MATCH_3D_FLAGS) && + u32 sync_flags = DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_NHSYNC | + DRM_MODE_FLAG_PVSYNC | DRM_MODE_FLAG_NVSYNC; + + return (mode->flags & ~sync_flags) == (preferred_mode->flags & ~sync_flags) && mode->hdisplay == preferred_mode->hdisplay && mode->vdisplay == preferred_mode->vdisplay; } @@ -147,12 +149,24 @@ int intel_panel_get_modes(struct intel_connector *connector) return num_modes; } -enum drrs_type intel_panel_drrs_type(struct intel_connector *connector) +static bool has_drrs_modes(struct intel_connector *connector) { - if (list_empty(&connector->panel.fixed_modes) || - list_is_singular(&connector->panel.fixed_modes)) - return DRRS_TYPE_NONE; + const struct drm_display_mode *mode1; + + list_for_each_entry(mode1, &connector->panel.fixed_modes, head) { + const struct drm_display_mode *mode2 = mode1; + + list_for_each_entry_continue(mode2, &connector->panel.fixed_modes, head) { + if (is_alt_drrs_mode(mode1, mode2)) + return true; + } + } + + return false; +} +enum drrs_type intel_panel_drrs_type(struct intel_connector *connector) +{ return connector->panel.vbt.drrs_type; } @@ -653,6 +667,9 @@ int intel_panel_init(struct intel_connector *connector) intel_backlight_init_funcs(panel); + if (!has_drrs_modes(connector)) + connector->panel.vbt.drrs_type = DRRS_TYPE_NONE; + drm_dbg_kms(connector->base.dev, "[CONNECTOR:%d:%s] DRRS type: %s\n", connector->base.base.id, connector->base.name, diff --git a/drivers/gpu/drm/i915/display/intel_pch_display.c b/drivers/gpu/drm/i915/display/intel_pch_display.c index 837152dca063..cecc0d007cf3 100644 --- a/drivers/gpu/drm/i915/display/intel_pch_display.c +++ b/drivers/gpu/drm/i915/display/intel_pch_display.c @@ -4,6 +4,7 @@ */ #include "g4x_dp.h" +#include "i915_reg.h" #include "intel_crt.h" #include "intel_de.h" #include "intel_display_types.h" diff --git a/drivers/gpu/drm/i915/display/intel_pch_refclk.c b/drivers/gpu/drm/i915/display/intel_pch_refclk.c index a66097cdc1e0..08a94365b7d1 100644 --- a/drivers/gpu/drm/i915/display/intel_pch_refclk.c +++ b/drivers/gpu/drm/i915/display/intel_pch_refclk.c @@ -3,6 +3,7 @@ * Copyright © 2021 Intel Corporation */ +#include "i915_reg.h" #include "intel_de.h" #include "intel_display_types.h" #include "intel_panel.h" diff --git a/drivers/gpu/drm/i915/display/intel_pipe_crc.c b/drivers/gpu/drm/i915/display/intel_pipe_crc.c index 8ac263f471be..e9774670e3f6 100644 --- a/drivers/gpu/drm/i915/display/intel_pipe_crc.c +++ b/drivers/gpu/drm/i915/display/intel_pipe_crc.c @@ -24,11 +24,12 @@ * */ -#include <linux/circ_buf.h> #include <linux/ctype.h> #include <linux/debugfs.h> #include <linux/seq_file.h> +#include "i915_irq.h" +#include "i915_reg.h" #include "intel_atomic.h" #include "intel_de.h" #include "intel_display_types.h" @@ -75,7 +76,6 @@ static int i9xx_pipe_crc_auto_source(struct drm_i915_private *dev_priv, enum pipe pipe, enum intel_pipe_crc_source *source) { - struct drm_device *dev = &dev_priv->drm; struct intel_encoder *encoder; struct intel_crtc *crtc; struct intel_digital_port *dig_port; @@ -83,8 +83,8 @@ static int i9xx_pipe_crc_auto_source(struct drm_i915_private *dev_priv, *source = INTEL_PIPE_CRC_SOURCE_PIPE; - drm_modeset_lock_all(dev); - for_each_intel_encoder(dev, encoder) { + drm_modeset_lock_all(&dev_priv->drm); + for_each_intel_encoder(&dev_priv->drm, encoder) { if (!encoder->base.crtc) continue; @@ -111,7 +111,7 @@ static int i9xx_pipe_crc_auto_source(struct drm_i915_private *dev_priv, *source = INTEL_PIPE_CRC_SOURCE_DP_D; break; default: - drm_WARN(dev, 1, "nonexisting DP port %c\n", + drm_WARN(&dev_priv->drm, 1, "nonexisting DP port %c\n", port_name(dig_port->base.port)); break; } @@ -120,7 +120,7 @@ static int i9xx_pipe_crc_auto_source(struct drm_i915_private *dev_priv, break; } } - drm_modeset_unlock_all(dev); + drm_modeset_unlock_all(&dev_priv->drm); return ret; } diff --git a/drivers/gpu/drm/i915/display/intel_pps.c b/drivers/gpu/drm/i915/display/intel_pps.c index 21944f5bf3a8..9bbf41a076f7 100644 --- a/drivers/gpu/drm/i915/display/intel_pps.c +++ b/drivers/gpu/drm/i915/display/intel_pps.c @@ -5,10 +5,12 @@ #include "g4x_dp.h" #include "i915_drv.h" +#include "i915_reg.h" #include "intel_de.h" #include "intel_display_power_well.h" #include "intel_display_types.h" #include "intel_dp.h" +#include "intel_dpio_phy.h" #include "intel_dpll.h" #include "intel_lvds.h" #include "intel_pps.h" @@ -1098,7 +1100,13 @@ bool intel_pps_have_panel_power_or_vdd(struct intel_dp *intel_dp) static void pps_init_timestamps(struct intel_dp *intel_dp) { - intel_dp->pps.panel_power_off_time = ktime_get_boottime(); + /* + * Initialize panel power off time to 0, assuming panel power could have + * been toggled between kernel boot and now only by a previously loaded + * and removed i915, which has already ensured sufficient power off + * delay at module remove. + */ + intel_dp->pps.panel_power_off_time = 0; intel_dp->pps.last_power_on = jiffies; intel_dp->pps.last_backlight_off = jiffies; } diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 15c3e448aa0e..5b678916e6db 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -27,6 +27,7 @@ #include "display/intel_dp.h" #include "i915_drv.h" +#include "i915_reg.h" #include "intel_atomic.h" #include "intel_crtc.h" #include "intel_de.h" @@ -533,7 +534,7 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp) val |= psr_compute_idle_frames(intel_dp) << EDP_PSR2_IDLE_FRAME_SHIFT; - if (!IS_ALDERLAKE_P(dev_priv)) + if (DISPLAY_VER(dev_priv) <= 13 && !IS_ALDERLAKE_P(dev_priv)) val |= EDP_SU_TRACK_ENABLE; if (DISPLAY_VER(dev_priv) >= 10 && DISPLAY_VER(dev_priv) <= 12) @@ -616,7 +617,7 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp) static bool transcoder_has_psr2(struct drm_i915_private *dev_priv, enum transcoder trans) { - if (IS_ALDERLAKE_P(dev_priv)) + if (IS_ALDERLAKE_P(dev_priv) || DISPLAY_VER(dev_priv) >= 14) return trans == TRANSCODER_A || trans == TRANSCODER_B; else if (DISPLAY_VER(dev_priv) >= 12) return trans == TRANSCODER_A; @@ -696,7 +697,7 @@ dc3co_is_pipe_port_compatible(struct intel_dp *intel_dp, struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); enum port port = dig_port->base.port; - if (IS_ALDERLAKE_P(dev_priv)) + if (IS_ALDERLAKE_P(dev_priv) || DISPLAY_VER(dev_priv) >= 14) return pipe <= PIPE_B && port <= PORT_B; else return pipe == PIPE_A && port == PORT_A; @@ -779,6 +780,7 @@ static bool psr2_granularity_check(struct intel_dp *intel_dp, struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + const struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config; const int crtc_hdisplay = crtc_state->hw.adjusted_mode.crtc_hdisplay; const int crtc_vdisplay = crtc_state->hw.adjusted_mode.crtc_vdisplay; u16 y_granularity = 0; @@ -795,11 +797,11 @@ static bool psr2_granularity_check(struct intel_dp *intel_dp, return intel_dp->psr.su_y_granularity == 4; /* - * adl_p has 1 line granularity. For other platforms with SW tracking we - * can adjust the y coordinates to match sink requirement if multiple of - * 4. + * adl_p and display 14+ platforms has 1 line granularity. + * For other platforms with SW tracking we can adjust the y coordinates + * to match sink requirement if multiple of 4. */ - if (IS_ALDERLAKE_P(dev_priv)) + if (IS_ALDERLAKE_P(dev_priv) || DISPLAY_VER(dev_priv) >= 14) y_granularity = intel_dp->psr.su_y_granularity; else if (intel_dp->psr.su_y_granularity <= 2) y_granularity = 4; @@ -809,6 +811,10 @@ static bool psr2_granularity_check(struct intel_dp *intel_dp, if (y_granularity == 0 || crtc_vdisplay % y_granularity) return false; + if (crtc_state->dsc.compression_enable && + vdsc_cfg->slice_height % y_granularity) + return false; + crtc_state->su_y_granularity = y_granularity; return true; } @@ -883,7 +889,8 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp, * resolution requires DSC to be enabled, priority is given to DSC * over PSR2. */ - if (crtc_state->dsc.compression_enable) { + if (crtc_state->dsc.compression_enable && + (DISPLAY_VER(dev_priv) <= 13 && !IS_ALDERLAKE_P(dev_priv))) { drm_dbg_kms(&dev_priv->drm, "PSR2 cannot be enabled since DSC is enabled\n"); return false; @@ -1469,26 +1476,27 @@ unlock: static u32 man_trk_ctl_enable_bit_get(struct drm_i915_private *dev_priv) { - return IS_ALDERLAKE_P(dev_priv) ? 0 : PSR2_MAN_TRK_CTL_ENABLE; + return IS_ALDERLAKE_P(dev_priv) || DISPLAY_VER(dev_priv) >= 14 ? 0 : + PSR2_MAN_TRK_CTL_ENABLE; } static u32 man_trk_ctl_single_full_frame_bit_get(struct drm_i915_private *dev_priv) { - return IS_ALDERLAKE_P(dev_priv) ? + return IS_ALDERLAKE_P(dev_priv) || DISPLAY_VER(dev_priv) >= 14 ? ADLP_PSR2_MAN_TRK_CTL_SF_SINGLE_FULL_FRAME : PSR2_MAN_TRK_CTL_SF_SINGLE_FULL_FRAME; } static u32 man_trk_ctl_partial_frame_bit_get(struct drm_i915_private *dev_priv) { - return IS_ALDERLAKE_P(dev_priv) ? + return IS_ALDERLAKE_P(dev_priv) || DISPLAY_VER(dev_priv) >= 14 ? ADLP_PSR2_MAN_TRK_CTL_SF_PARTIAL_FRAME_UPDATE : PSR2_MAN_TRK_CTL_SF_PARTIAL_FRAME_UPDATE; } static u32 man_trk_ctl_continuos_full_frame(struct drm_i915_private *dev_priv) { - return IS_ALDERLAKE_P(dev_priv) ? + return IS_ALDERLAKE_P(dev_priv) || DISPLAY_VER(dev_priv) >= 14 ? ADLP_PSR2_MAN_TRK_CTL_SF_CONTINUOS_FULL_FRAME : PSR2_MAN_TRK_CTL_SF_CONTINUOS_FULL_FRAME; } @@ -1627,7 +1635,7 @@ static void psr2_man_trk_ctl_calc(struct intel_crtc_state *crtc_state, if (clip->y1 == -1) goto exit; - if (IS_ALDERLAKE_P(dev_priv)) { + if (IS_ALDERLAKE_P(dev_priv) || DISPLAY_VER(dev_priv) >= 14) { val |= ADLP_PSR2_MAN_TRK_CTL_SU_REGION_START_ADDR(clip->y1); val |= ADLP_PSR2_MAN_TRK_CTL_SU_REGION_END_ADDR(clip->y2 - 1); } else { @@ -1664,14 +1672,19 @@ static void intel_psr2_sel_fetch_pipe_alignment(const struct intel_crtc_state *c struct drm_rect *pipe_clip) { struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); - const u16 y_alignment = crtc_state->su_y_granularity; + const struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config; + u16 y_alignment; + + /* ADLP aligns the SU region to vdsc slice height in case dsc is enabled */ + if (crtc_state->dsc.compression_enable && + (IS_ALDERLAKE_P(dev_priv) || DISPLAY_VER(dev_priv) >= 14)) + y_alignment = vdsc_cfg->slice_height; + else + y_alignment = crtc_state->su_y_granularity; pipe_clip->y1 -= pipe_clip->y1 % y_alignment; if (pipe_clip->y2 % y_alignment) pipe_clip->y2 = ((pipe_clip->y2 / y_alignment) + 1) * y_alignment; - - if (IS_ALDERLAKE_P(dev_priv) && crtc_state->dsc.compression_enable) - drm_warn(&dev_priv->drm, "Missing PSR2 sel fetch alignment with DSC\n"); } /* @@ -2054,13 +2067,12 @@ static bool __psr_wait_for_idle_locked(struct intel_dp *intel_dp) static int intel_psr_fastset_force(struct drm_i915_private *dev_priv) { struct drm_connector_list_iter conn_iter; - struct drm_device *dev = &dev_priv->drm; struct drm_modeset_acquire_ctx ctx; struct drm_atomic_state *state; struct drm_connector *conn; int err = 0; - state = drm_atomic_state_alloc(dev); + state = drm_atomic_state_alloc(&dev_priv->drm); if (!state) return -ENOMEM; @@ -2069,7 +2081,7 @@ static int intel_psr_fastset_force(struct drm_i915_private *dev_priv) retry: - drm_connector_list_iter_begin(dev, &conn_iter); + drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter); drm_for_each_connector_iter(conn, &conn_iter) { struct drm_connector_state *conn_state; struct drm_crtc_state *crtc_state; diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c index 774c1dc31a52..329b9d9af667 100644 --- a/drivers/gpu/drm/i915/display/intel_sdvo.c +++ b/drivers/gpu/drm/i915/display/intel_sdvo.c @@ -37,6 +37,7 @@ #include <drm/drm_edid.h> #include "i915_drv.h" +#include "i915_reg.h" #include "intel_atomic.h" #include "intel_connector.h" #include "intel_crtc.h" @@ -199,7 +200,7 @@ to_intel_sdvo_connector(struct drm_connector *connector) container_of((conn_state), struct intel_sdvo_connector_state, base.base) static bool -intel_sdvo_output_setup(struct intel_sdvo *intel_sdvo, u16 flags); +intel_sdvo_output_setup(struct intel_sdvo *intel_sdvo); static bool intel_sdvo_tv_create_property(struct intel_sdvo *intel_sdvo, struct intel_sdvo_connector *intel_sdvo_connector, @@ -1297,13 +1298,28 @@ static bool intel_sdvo_limited_color_range(struct intel_encoder *encoder, return intel_hdmi_limited_color_range(crtc_state, conn_state); } +static bool intel_sdvo_has_audio(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state, + const struct drm_connector_state *conn_state) +{ + struct intel_sdvo *intel_sdvo = to_sdvo(encoder); + const struct intel_digital_connector_state *intel_conn_state = + to_intel_digital_connector_state(conn_state); + + if (!crtc_state->has_hdmi_sink) + return false; + + if (intel_conn_state->force_audio == HDMI_AUDIO_AUTO) + return intel_sdvo->has_hdmi_audio; + else + return intel_conn_state->force_audio == HDMI_AUDIO_ON; +} + static int intel_sdvo_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config, struct drm_connector_state *conn_state) { struct intel_sdvo *intel_sdvo = to_sdvo(encoder); - struct intel_sdvo_connector_state *intel_sdvo_state = - to_intel_sdvo_connector_state(conn_state); struct intel_sdvo_connector *intel_sdvo_connector = to_intel_sdvo_connector(conn_state->connector); struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode; @@ -1362,13 +1378,7 @@ static int intel_sdvo_compute_config(struct intel_encoder *encoder, pipe_config->has_hdmi_sink = intel_has_hdmi_sink(intel_sdvo, conn_state); - if (pipe_config->has_hdmi_sink) { - if (intel_sdvo_state->base.force_audio == HDMI_AUDIO_AUTO) - pipe_config->has_audio = intel_sdvo->has_hdmi_audio; - else - pipe_config->has_audio = - intel_sdvo_state->base.force_audio == HDMI_AUDIO_ON; - } + pipe_config->has_audio = intel_sdvo_has_audio(encoder, pipe_config, conn_state); pipe_config->limited_color_range = intel_sdvo_limited_color_range(encoder, pipe_config, @@ -2290,17 +2300,12 @@ static int intel_sdvo_get_tv_modes(struct drm_connector *connector) static int intel_sdvo_get_lvds_modes(struct drm_connector *connector) { - struct intel_sdvo *intel_sdvo = intel_attached_sdvo(to_intel_connector(connector)); struct drm_i915_private *dev_priv = to_i915(connector->dev); - int num_modes = 0; drm_dbg_kms(&dev_priv->drm, "[CONNECTOR:%d:%s]\n", connector->base.id, connector->name); - num_modes += intel_panel_get_modes(to_intel_connector(connector)); - num_modes += intel_ddc_get_modes(connector, &intel_sdvo->ddc); - - return num_modes; + return intel_panel_get_modes(to_intel_connector(connector)); } static int intel_sdvo_get_modes(struct drm_connector *connector) @@ -2627,7 +2632,7 @@ intel_sdvo_unselect_i2c_bus(struct intel_sdvo *sdvo) } static bool -intel_sdvo_is_hdmi_connector(struct intel_sdvo *intel_sdvo, int device) +intel_sdvo_is_hdmi_connector(struct intel_sdvo *intel_sdvo) { return intel_sdvo_check_supp_encode(intel_sdvo); } @@ -2689,9 +2694,8 @@ intel_sdvo_connector_init(struct intel_sdvo_connector *connector, drm_connector_helper_add(drm_connector, &intel_sdvo_connector_helper_funcs); - connector->base.base.interlace_allowed = 1; - connector->base.base.doublescan_allowed = 0; connector->base.base.display_info.subpixel_order = SubPixelHorizontalRGB; + connector->base.base.interlace_allowed = true; connector->base.get_hw_state = intel_sdvo_connector_get_hw_state; intel_connector_attach_encoder(&connector->base, &encoder->base); @@ -2733,7 +2737,7 @@ static struct intel_sdvo_connector *intel_sdvo_connector_alloc(void) } static bool -intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, int device) +intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, u16 type) { struct drm_encoder *encoder = &intel_sdvo->base.base; struct drm_connector *connector; @@ -2741,16 +2745,13 @@ intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, int device) struct intel_connector *intel_connector; struct intel_sdvo_connector *intel_sdvo_connector; - DRM_DEBUG_KMS("initialising DVI device %d\n", device); + DRM_DEBUG_KMS("initialising DVI type 0x%x\n", type); intel_sdvo_connector = intel_sdvo_connector_alloc(); if (!intel_sdvo_connector) return false; - if (device == 0) - intel_sdvo_connector->output_flag = SDVO_OUTPUT_TMDS0; - else if (device == 1) - intel_sdvo_connector->output_flag = SDVO_OUTPUT_TMDS1; + intel_sdvo_connector->output_flag = type; intel_connector = &intel_sdvo_connector->base; connector = &intel_connector->base; @@ -2770,7 +2771,7 @@ intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, int device) encoder->encoder_type = DRM_MODE_ENCODER_TMDS; connector->connector_type = DRM_MODE_CONNECTOR_DVID; - if (intel_sdvo_is_hdmi_connector(intel_sdvo, device)) { + if (intel_sdvo_is_hdmi_connector(intel_sdvo)) { connector->connector_type = DRM_MODE_CONNECTOR_HDMIA; intel_sdvo_connector->is_hdmi = true; } @@ -2787,14 +2788,14 @@ intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, int device) } static bool -intel_sdvo_tv_init(struct intel_sdvo *intel_sdvo, int type) +intel_sdvo_tv_init(struct intel_sdvo *intel_sdvo, u16 type) { struct drm_encoder *encoder = &intel_sdvo->base.base; struct drm_connector *connector; struct intel_connector *intel_connector; struct intel_sdvo_connector *intel_sdvo_connector; - DRM_DEBUG_KMS("initialising TV type %d\n", type); + DRM_DEBUG_KMS("initialising TV type 0x%x\n", type); intel_sdvo_connector = intel_sdvo_connector_alloc(); if (!intel_sdvo_connector) @@ -2826,14 +2827,14 @@ err: } static bool -intel_sdvo_analog_init(struct intel_sdvo *intel_sdvo, int device) +intel_sdvo_analog_init(struct intel_sdvo *intel_sdvo, u16 type) { struct drm_encoder *encoder = &intel_sdvo->base.base; struct drm_connector *connector; struct intel_connector *intel_connector; struct intel_sdvo_connector *intel_sdvo_connector; - DRM_DEBUG_KMS("initialising analog device %d\n", device); + DRM_DEBUG_KMS("initialising analog type 0x%x\n", type); intel_sdvo_connector = intel_sdvo_connector_alloc(); if (!intel_sdvo_connector) @@ -2845,10 +2846,7 @@ intel_sdvo_analog_init(struct intel_sdvo *intel_sdvo, int device) encoder->encoder_type = DRM_MODE_ENCODER_DAC; connector->connector_type = DRM_MODE_CONNECTOR_VGA; - if (device == 0) - intel_sdvo_connector->output_flag = SDVO_OUTPUT_RGB0; - else if (device == 1) - intel_sdvo_connector->output_flag = SDVO_OUTPUT_RGB1; + intel_sdvo_connector->output_flag = type; if (intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo) < 0) { kfree(intel_sdvo_connector); @@ -2859,7 +2857,7 @@ intel_sdvo_analog_init(struct intel_sdvo *intel_sdvo, int device) } static bool -intel_sdvo_lvds_init(struct intel_sdvo *intel_sdvo, int device) +intel_sdvo_lvds_init(struct intel_sdvo *intel_sdvo, u16 type) { struct drm_encoder *encoder = &intel_sdvo->base.base; struct drm_i915_private *i915 = to_i915(encoder->dev); @@ -2867,7 +2865,7 @@ intel_sdvo_lvds_init(struct intel_sdvo *intel_sdvo, int device) struct intel_connector *intel_connector; struct intel_sdvo_connector *intel_sdvo_connector; - DRM_DEBUG_KMS("initialising LVDS device %d\n", device); + DRM_DEBUG_KMS("initialising LVDS type 0x%x\n", type); intel_sdvo_connector = intel_sdvo_connector_alloc(); if (!intel_sdvo_connector) @@ -2878,10 +2876,7 @@ intel_sdvo_lvds_init(struct intel_sdvo *intel_sdvo, int device) encoder->encoder_type = DRM_MODE_ENCODER_LVDS; connector->connector_type = DRM_MODE_CONNECTOR_LVDS; - if (device == 0) - intel_sdvo_connector->output_flag = SDVO_OUTPUT_LVDS0; - else if (device == 1) - intel_sdvo_connector->output_flag = SDVO_OUTPUT_LVDS1; + intel_sdvo_connector->output_flag = type; if (intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo) < 0) { kfree(intel_sdvo_connector); @@ -2937,63 +2932,61 @@ static u16 intel_sdvo_filter_output_flags(u16 flags) return flags; } -static bool -intel_sdvo_output_setup(struct intel_sdvo *intel_sdvo, u16 flags) +static bool intel_sdvo_output_init(struct intel_sdvo *sdvo, u16 type) { + if (type & SDVO_TMDS_MASK) + return intel_sdvo_dvi_init(sdvo, type); + else if (type & SDVO_TV_MASK) + return intel_sdvo_tv_init(sdvo, type); + else if (type & SDVO_RGB_MASK) + return intel_sdvo_analog_init(sdvo, type); + else if (type & SDVO_LVDS_MASK) + return intel_sdvo_lvds_init(sdvo, type); + else + return false; +} + +static bool +intel_sdvo_output_setup(struct intel_sdvo *intel_sdvo) +{ + static const u16 probe_order[] = { + SDVO_OUTPUT_TMDS0, + SDVO_OUTPUT_TMDS1, + /* TV has no XXX1 function block */ + SDVO_OUTPUT_SVID0, + SDVO_OUTPUT_CVBS0, + SDVO_OUTPUT_YPRPB0, + SDVO_OUTPUT_RGB0, + SDVO_OUTPUT_RGB1, + SDVO_OUTPUT_LVDS0, + SDVO_OUTPUT_LVDS1, + }; struct drm_i915_private *i915 = to_i915(intel_sdvo->base.base.dev); + u16 flags; + int i; - flags = intel_sdvo_filter_output_flags(flags); + flags = intel_sdvo_filter_output_flags(intel_sdvo->caps.output_flags); + + if (flags == 0) { + DRM_DEBUG_KMS("%s: Unknown SDVO output type (0x%04x)\n", + SDVO_NAME(intel_sdvo), intel_sdvo->caps.output_flags); + return false; + } intel_sdvo->controlled_output = flags; intel_sdvo_select_ddc_bus(i915, intel_sdvo); - if (flags & SDVO_OUTPUT_TMDS0) - if (!intel_sdvo_dvi_init(intel_sdvo, 0)) - return false; + for (i = 0; i < ARRAY_SIZE(probe_order); i++) { + u16 type = flags & probe_order[i]; - if (flags & SDVO_OUTPUT_TMDS1) - if (!intel_sdvo_dvi_init(intel_sdvo, 1)) - return false; - - /* TV has no XXX1 function block */ - if (flags & SDVO_OUTPUT_SVID0) - if (!intel_sdvo_tv_init(intel_sdvo, SDVO_OUTPUT_SVID0)) - return false; + if (!type) + continue; - if (flags & SDVO_OUTPUT_CVBS0) - if (!intel_sdvo_tv_init(intel_sdvo, SDVO_OUTPUT_CVBS0)) + if (!intel_sdvo_output_init(intel_sdvo, type)) return false; - - if (flags & SDVO_OUTPUT_YPRPB0) - if (!intel_sdvo_tv_init(intel_sdvo, SDVO_OUTPUT_YPRPB0)) - return false; - - if (flags & SDVO_OUTPUT_RGB0) - if (!intel_sdvo_analog_init(intel_sdvo, 0)) - return false; - - if (flags & SDVO_OUTPUT_RGB1) - if (!intel_sdvo_analog_init(intel_sdvo, 1)) - return false; - - if (flags & SDVO_OUTPUT_LVDS0) - if (!intel_sdvo_lvds_init(intel_sdvo, 0)) - return false; - - if (flags & SDVO_OUTPUT_LVDS1) - if (!intel_sdvo_lvds_init(intel_sdvo, 1)) - return false; - - if (flags == 0) { - unsigned char bytes[2]; - - memcpy(bytes, &intel_sdvo->caps.output_flags, 2); - DRM_DEBUG_KMS("%s: Unknown SDVO output type (0x%02x%02x)\n", - SDVO_NAME(intel_sdvo), - bytes[0], bytes[1]); - return false; } + intel_sdvo->base.pipe_mask = ~0; return true; @@ -3369,8 +3362,7 @@ bool intel_sdvo_init(struct drm_i915_private *dev_priv, intel_sdvo->colorimetry_cap = intel_sdvo_get_colorimetry_cap(intel_sdvo); - if (intel_sdvo_output_setup(intel_sdvo, - intel_sdvo->caps.output_flags) != true) { + if (!intel_sdvo_output_setup(intel_sdvo)) { drm_dbg_kms(&dev_priv->drm, "SDVO output failed to setup on %s\n", SDVO_NAME(intel_sdvo)); @@ -3421,9 +3413,12 @@ bool intel_sdvo_init(struct drm_i915_private *dev_priv, (intel_sdvo->caps.sdvo_inputs_mask & 0x2) ? 'Y' : 'N', /* check currently supported outputs */ intel_sdvo->caps.output_flags & - (SDVO_OUTPUT_TMDS0 | SDVO_OUTPUT_RGB0) ? 'Y' : 'N', + (SDVO_OUTPUT_TMDS0 | SDVO_OUTPUT_RGB0 | + SDVO_OUTPUT_LVDS0 | SDVO_OUTPUT_SVID0 | + SDVO_OUTPUT_CVBS0 | SDVO_OUTPUT_YPRPB0) ? 'Y' : 'N', intel_sdvo->caps.output_flags & - (SDVO_OUTPUT_TMDS1 | SDVO_OUTPUT_RGB1) ? 'Y' : 'N'); + (SDVO_OUTPUT_TMDS1 | SDVO_OUTPUT_RGB1 | + SDVO_OUTPUT_LVDS1) ? 'Y' : 'N'); return true; err_output: diff --git a/drivers/gpu/drm/i915/display/intel_snps_phy.c b/drivers/gpu/drm/i915/display/intel_snps_phy.c index 937cefd6f78f..c799e891f8b5 100644 --- a/drivers/gpu/drm/i915/display/intel_snps_phy.c +++ b/drivers/gpu/drm/i915/display/intel_snps_phy.c @@ -5,6 +5,7 @@ #include <linux/util_macros.h> +#include "i915_reg.h" #include "intel_ddi.h" #include "intel_ddi_buf_trans.h" #include "intel_de.h" diff --git a/drivers/gpu/drm/i915/display/intel_snps_phy_regs.h b/drivers/gpu/drm/i915/display/intel_snps_phy_regs.h index 0543465aaf14..a04d692169d4 100644 --- a/drivers/gpu/drm/i915/display/intel_snps_phy_regs.h +++ b/drivers/gpu/drm/i915/display/intel_snps_phy_regs.h @@ -6,7 +6,7 @@ #ifndef __INTEL_SNPS_PHY_REGS__ #define __INTEL_SNPS_PHY_REGS__ -#include "i915_reg_defs.h" +#include "intel_display_reg_defs.h" #define _SNPS_PHY_A_BASE 0x168000 #define _SNPS_PHY_B_BASE 0x169000 diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c index 7649c50b5445..e6b4d24b9cd0 100644 --- a/drivers/gpu/drm/i915/display/intel_sprite.c +++ b/drivers/gpu/drm/i915/display/intel_sprite.c @@ -42,6 +42,7 @@ #include <drm/drm_rect.h> #include "i915_drv.h" +#include "i915_reg.h" #include "i915_vgpu.h" #include "i9xx_plane.h" #include "intel_atomic_plane.h" diff --git a/drivers/gpu/drm/i915/display/intel_sprite.h b/drivers/gpu/drm/i915/display/intel_sprite.h index 4f63e4967731..4635c7ad23f9 100644 --- a/drivers/gpu/drm/i915/display/intel_sprite.h +++ b/drivers/gpu/drm/i915/display/intel_sprite.h @@ -8,14 +8,13 @@ #include <linux/types.h> -#include "intel_display.h" - struct drm_device; struct drm_display_mode; struct drm_file; struct drm_i915_private; struct intel_crtc_state; struct intel_plane_state; +enum pipe; /* * FIXME: We should instead only take spinlocks once for the entire update @@ -34,12 +33,6 @@ int intel_sprite_set_colorkey_ioctl(struct drm_device *dev, void *data, int intel_plane_check_src_coordinates(struct intel_plane_state *plane_state); int chv_plane_check_rotation(const struct intel_plane_state *plane_state); -static inline u8 icl_hdr_plane_mask(void) -{ - return BIT(PLANE_PRIMARY) | - BIT(PLANE_SPRITE0) | BIT(PLANE_SPRITE1); -} - int ivb_plane_min_cdclk(const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state); int hsw_plane_min_cdclk(const struct intel_crtc_state *crtc_state, diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c index e5af955b5600..70624b4b2d38 100644 --- a/drivers/gpu/drm/i915/display/intel_tc.c +++ b/drivers/gpu/drm/i915/display/intel_tc.c @@ -8,9 +8,10 @@ #include "intel_display.h" #include "intel_display_power_map.h" #include "intel_display_types.h" +#include "intel_dkl_phy_regs.h" #include "intel_dp_mst.h" +#include "intel_mg_phy_regs.h" #include "intel_tc.h" -#include "intel_tc_phy_regs.h" static const char *tc_port_mode_name(enum tc_port_mode mode) { @@ -408,14 +409,9 @@ static bool adl_tc_phy_take_ownership(struct intel_digital_port *dig_port, struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); struct intel_uncore *uncore = &i915->uncore; enum port port = dig_port->base.port; - u32 val; - val = intel_uncore_read(uncore, DDI_BUF_CTL(port)); - if (take) - val |= DDI_BUF_CTL_TC_PHY_OWNERSHIP; - else - val &= ~DDI_BUF_CTL_TC_PHY_OWNERSHIP; - intel_uncore_write(uncore, DDI_BUF_CTL(port), val); + intel_uncore_rmw(uncore, DDI_BUF_CTL(port), DDI_BUF_CTL_TC_PHY_OWNERSHIP, + take ? DDI_BUF_CTL_TC_PHY_OWNERSHIP : 0); return true; } @@ -687,18 +683,58 @@ static void intel_tc_port_link_init_refcount(struct intel_digital_port *dig_port, int refcount) { + dig_port->tc_link_refcount = refcount; +} + +/** + * intel_tc_port_init_mode: Read out HW state and init the given port's TypeC mode + * @dig_port: digital port + * + * Read out the HW state and initialize the TypeC mode of @dig_port. The mode + * will be locked until intel_tc_port_sanitize_mode() is called. + */ +void intel_tc_port_init_mode(struct intel_digital_port *dig_port) +{ struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + intel_wakeref_t tc_cold_wref; + enum intel_display_power_domain domain; + + mutex_lock(&dig_port->tc_lock); + drm_WARN_ON(&i915->drm, dig_port->tc_mode != TC_PORT_DISCONNECTED); + drm_WARN_ON(&i915->drm, dig_port->tc_lock_wakeref); drm_WARN_ON(&i915->drm, dig_port->tc_link_refcount); - dig_port->tc_link_refcount = refcount; + + tc_cold_wref = tc_cold_block(dig_port, &domain); + + dig_port->tc_mode = intel_tc_port_get_current_mode(dig_port); + /* Prevent changing dig_port->tc_mode until intel_tc_port_sanitize_mode() is called. */ + intel_tc_port_link_init_refcount(dig_port, 1); + dig_port->tc_lock_wakeref = tc_cold_block(dig_port, &dig_port->tc_lock_power_domain); + + tc_cold_unblock(dig_port, domain, tc_cold_wref); + + drm_dbg_kms(&i915->drm, "Port %s: init mode (%s)\n", + dig_port->tc_port_name, + tc_port_mode_name(dig_port->tc_mode)); + + mutex_unlock(&dig_port->tc_lock); } -void intel_tc_port_sanitize(struct intel_digital_port *dig_port) +/** + * intel_tc_port_sanitize_mode: Sanitize the given port's TypeC mode + * @dig_port: digital port + * + * Sanitize @dig_port's TypeC mode wrt. the encoder's state right after driver + * loading and system resume: + * If the encoder is enabled keep the TypeC mode/PHY connected state locked until + * the encoder is disabled. + * If the encoder is disabled make sure the PHY is disconnected. + */ +void intel_tc_port_sanitize_mode(struct intel_digital_port *dig_port) { struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); struct intel_encoder *encoder = &dig_port->base; - intel_wakeref_t tc_cold_wref; - enum intel_display_power_domain domain; int active_links = 0; mutex_lock(&dig_port->tc_lock); @@ -708,21 +744,14 @@ void intel_tc_port_sanitize(struct intel_digital_port *dig_port) else if (encoder->base.crtc) active_links = to_intel_crtc(encoder->base.crtc)->active; - drm_WARN_ON(&i915->drm, dig_port->tc_mode != TC_PORT_DISCONNECTED); - drm_WARN_ON(&i915->drm, dig_port->tc_lock_wakeref); - - tc_cold_wref = tc_cold_block(dig_port, &domain); + drm_WARN_ON(&i915->drm, dig_port->tc_link_refcount != 1); + intel_tc_port_link_init_refcount(dig_port, active_links); - dig_port->tc_mode = intel_tc_port_get_current_mode(dig_port); if (active_links) { if (!icl_tc_phy_is_connected(dig_port)) drm_dbg_kms(&i915->drm, "Port %s: PHY disconnected with %d active link(s)\n", dig_port->tc_port_name, active_links); - intel_tc_port_link_init_refcount(dig_port, active_links); - - dig_port->tc_lock_wakeref = tc_cold_block(dig_port, - &dig_port->tc_lock_power_domain); } else { /* * TBT-alt is the default mode in any case the PHY ownership is not @@ -736,9 +765,10 @@ void intel_tc_port_sanitize(struct intel_digital_port *dig_port) dig_port->tc_port_name, tc_port_mode_name(dig_port->tc_mode)); icl_tc_phy_disconnect(dig_port); - } - tc_cold_unblock(dig_port, domain, tc_cold_wref); + tc_cold_unblock(dig_port, dig_port->tc_lock_power_domain, + fetch_and_zero(&dig_port->tc_lock_wakeref)); + } drm_dbg_kms(&i915->drm, "Port %s: sanitize mode (%s)\n", dig_port->tc_port_name, @@ -923,4 +953,6 @@ void intel_tc_port_init(struct intel_digital_port *dig_port, bool is_legacy) dig_port->tc_mode = TC_PORT_DISCONNECTED; dig_port->tc_link_refcount = 0; tc_port_load_fia_params(i915, dig_port); + + intel_tc_port_init_mode(dig_port); } diff --git a/drivers/gpu/drm/i915/display/intel_tc.h b/drivers/gpu/drm/i915/display/intel_tc.h index 6b47b29f551c..d54082e2d5e8 100644 --- a/drivers/gpu/drm/i915/display/intel_tc.h +++ b/drivers/gpu/drm/i915/display/intel_tc.h @@ -24,7 +24,8 @@ int intel_tc_port_fia_max_lane_count(struct intel_digital_port *dig_port); void intel_tc_port_set_fia_lane_count(struct intel_digital_port *dig_port, int required_lanes); -void intel_tc_port_sanitize(struct intel_digital_port *dig_port); +void intel_tc_port_init_mode(struct intel_digital_port *dig_port); +void intel_tc_port_sanitize_mode(struct intel_digital_port *dig_port); void intel_tc_port_lock(struct intel_digital_port *dig_port); void intel_tc_port_unlock(struct intel_digital_port *dig_port); void intel_tc_port_flush_work(struct intel_digital_port *dig_port); diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c index dcf89d701f0f..4d2101ca1692 100644 --- a/drivers/gpu/drm/i915/display/intel_tv.c +++ b/drivers/gpu/drm/i915/display/intel_tv.c @@ -35,6 +35,8 @@ #include <drm/drm_edid.h> #include "i915_drv.h" +#include "i915_reg.h" +#include "i915_irq.h" #include "intel_connector.h" #include "intel_crtc.h" #include "intel_de.h" @@ -1880,18 +1882,56 @@ static const struct drm_encoder_funcs intel_tv_enc_funcs = { .destroy = intel_encoder_destroy, }; +static void intel_tv_add_properties(struct drm_connector *connector) +{ + struct drm_i915_private *i915 = to_i915(connector->dev); + struct drm_connector_state *conn_state = connector->state; + const char *tv_format_names[ARRAY_SIZE(tv_modes)]; + int i; + + /* BIOS margin values */ + conn_state->tv.margins.left = 54; + conn_state->tv.margins.top = 36; + conn_state->tv.margins.right = 46; + conn_state->tv.margins.bottom = 37; + + conn_state->tv.mode = 0; + + /* Create TV properties then attach current values */ + for (i = 0; i < ARRAY_SIZE(tv_modes); i++) { + /* 1080p50/1080p60 not supported on gen3 */ + if (DISPLAY_VER(i915) == 3 && tv_modes[i].oversample == 1) + break; + + tv_format_names[i] = tv_modes[i].name; + } + drm_mode_create_tv_properties(&i915->drm, i, tv_format_names); + + drm_object_attach_property(&connector->base, + i915->drm.mode_config.tv_mode_property, + conn_state->tv.mode); + drm_object_attach_property(&connector->base, + i915->drm.mode_config.tv_left_margin_property, + conn_state->tv.margins.left); + drm_object_attach_property(&connector->base, + i915->drm.mode_config.tv_top_margin_property, + conn_state->tv.margins.top); + drm_object_attach_property(&connector->base, + i915->drm.mode_config.tv_right_margin_property, + conn_state->tv.margins.right); + drm_object_attach_property(&connector->base, + i915->drm.mode_config.tv_bottom_margin_property, + conn_state->tv.margins.bottom); +} + void intel_tv_init(struct drm_i915_private *dev_priv) { - struct drm_device *dev = &dev_priv->drm; struct drm_connector *connector; struct intel_tv *intel_tv; struct intel_encoder *intel_encoder; struct intel_connector *intel_connector; u32 tv_dac_on, tv_dac_off, save_tv_dac; - const char *tv_format_names[ARRAY_SIZE(tv_modes)]; - int i, initial_mode = 0; - struct drm_connector_state *state; if ((intel_de_read(dev_priv, TV_CTL) & TV_FUSE_STATE_MASK) == TV_FUSE_STATE_DISABLED) return; @@ -1937,7 +1977,6 @@ intel_tv_init(struct drm_i915_private *dev_priv) intel_encoder = &intel_tv->base; connector = &intel_connector->base; - state = connector->state; /* * The documentation, for the older chipsets at least, recommend @@ -1951,10 +1990,10 @@ intel_tv_init(struct drm_i915_private *dev_priv) */ intel_connector->polled = DRM_CONNECTOR_POLL_CONNECT; - drm_connector_init(dev, connector, &intel_tv_connector_funcs, + drm_connector_init(&dev_priv->drm, connector, &intel_tv_connector_funcs, DRM_MODE_CONNECTOR_SVIDEO); - drm_encoder_init(dev, &intel_encoder->base, &intel_tv_enc_funcs, + drm_encoder_init(&dev_priv->drm, &intel_encoder->base, &intel_tv_enc_funcs, DRM_MODE_ENCODER_TVDAC, "TV"); intel_encoder->compute_config = intel_tv_compute_config; @@ -1974,41 +2013,7 @@ intel_tv_init(struct drm_i915_private *dev_priv) intel_encoder->cloneable = 0; intel_tv->type = DRM_MODE_CONNECTOR_Unknown; - /* BIOS margin values */ - state->tv.margins.left = 54; - state->tv.margins.top = 36; - state->tv.margins.right = 46; - state->tv.margins.bottom = 37; - - state->tv.mode = initial_mode; - drm_connector_helper_add(connector, &intel_tv_connector_helper_funcs); - connector->interlace_allowed = false; - connector->doublescan_allowed = false; - /* Create TV properties then attach current values */ - for (i = 0; i < ARRAY_SIZE(tv_modes); i++) { - /* 1080p50/1080p60 not supported on gen3 */ - if (DISPLAY_VER(dev_priv) == 3 && - tv_modes[i].oversample == 1) - break; - - tv_format_names[i] = tv_modes[i].name; - } - drm_mode_create_tv_properties(dev, i, tv_format_names); - - drm_object_attach_property(&connector->base, dev->mode_config.tv_mode_property, - state->tv.mode); - drm_object_attach_property(&connector->base, - dev->mode_config.tv_left_margin_property, - state->tv.margins.left); - drm_object_attach_property(&connector->base, - dev->mode_config.tv_top_margin_property, - state->tv.margins.top); - drm_object_attach_property(&connector->base, - dev->mode_config.tv_right_margin_property, - state->tv.margins.right); - drm_object_attach_property(&connector->base, - dev->mode_config.tv_bottom_margin_property, - state->tv.margins.bottom); + intel_tv_add_properties(connector); } diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.c b/drivers/gpu/drm/i915/display/intel_vdsc.c index 269f9792390d..9d3b77b41b5c 100644 --- a/drivers/gpu/drm/i915/display/intel_vdsc.c +++ b/drivers/gpu/drm/i915/display/intel_vdsc.c @@ -10,6 +10,7 @@ #include <drm/display/drm_dsc_helper.h> #include "i915_drv.h" +#include "i915_reg.h" #include "intel_crtc.h" #include "intel_de.h" #include "intel_display_types.h" diff --git a/drivers/gpu/drm/i915/display/intel_vga.c b/drivers/gpu/drm/i915/display/intel_vga.c index b5d058404c14..a69bfcac9a94 100644 --- a/drivers/gpu/drm/i915/display/intel_vga.c +++ b/drivers/gpu/drm/i915/display/intel_vga.c @@ -10,6 +10,7 @@ #include <video/vga.h> #include "i915_drv.h" +#include "i915_reg.h" #include "intel_de.h" #include "intel_vga.h" diff --git a/drivers/gpu/drm/i915/display/intel_vrr.c b/drivers/gpu/drm/i915/display/intel_vrr.c index 5eac99021875..7b1357e82b69 100644 --- a/drivers/gpu/drm/i915/display/intel_vrr.c +++ b/drivers/gpu/drm/i915/display/intel_vrr.c @@ -5,6 +5,7 @@ */ #include "i915_drv.h" +#include "i915_reg.h" #include "intel_de.h" #include "intel_display_types.h" #include "intel_vrr.h" diff --git a/drivers/gpu/drm/i915/display/skl_scaler.c b/drivers/gpu/drm/i915/display/skl_scaler.c index 4092679be21e..d7390067b7d4 100644 --- a/drivers/gpu/drm/i915/display/skl_scaler.c +++ b/drivers/gpu/drm/i915/display/skl_scaler.c @@ -2,6 +2,8 @@ /* * Copyright © 2020 Intel Corporation */ + +#include "i915_reg.h" #include "intel_de.h" #include "intel_display_types.h" #include "intel_fb.h" diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c index 7cb713043408..76490cc59d8f 100644 --- a/drivers/gpu/drm/i915/display/skl_universal_plane.c +++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c @@ -9,6 +9,8 @@ #include <drm/drm_fourcc.h> #include "i915_drv.h" +#include "i915_irq.h" +#include "i915_reg.h" #include "intel_atomic_plane.h" #include "intel_de.h" #include "intel_display_types.h" @@ -246,6 +248,11 @@ bool icl_is_nv12_y_plane(struct drm_i915_private *dev_priv, icl_nv12_y_plane_mask(dev_priv) & BIT(plane_id); } +u8 icl_hdr_plane_mask(void) +{ + return BIT(PLANE_PRIMARY) | BIT(PLANE_SPRITE0) | BIT(PLANE_SPRITE1); +} + bool icl_is_hdr_plane(struct drm_i915_private *dev_priv, enum plane_id plane_id) { return DISPLAY_VER(dev_priv) >= 11 && diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.h b/drivers/gpu/drm/i915/display/skl_universal_plane.h index 351040b64dc7..be64c201f9b3 100644 --- a/drivers/gpu/drm/i915/display/skl_universal_plane.h +++ b/drivers/gpu/drm/i915/display/skl_universal_plane.h @@ -30,6 +30,7 @@ int skl_calc_main_surface_offset(const struct intel_plane_state *plane_state, bool icl_is_nv12_y_plane(struct drm_i915_private *dev_priv, enum plane_id plane_id); +u8 icl_hdr_plane_mask(void); bool icl_is_hdr_plane(struct drm_i915_private *dev_priv, enum plane_id plane_id); #endif diff --git a/drivers/gpu/drm/i915/display/skl_watermark.c b/drivers/gpu/drm/i915/display/skl_watermark.c index 18178b01375e..e0766d1be966 100644 --- a/drivers/gpu/drm/i915/display/skl_watermark.c +++ b/drivers/gpu/drm/i915/display/skl_watermark.c @@ -1706,26 +1706,10 @@ skl_compute_wm_params(const struct intel_crtc_state *crtc_state, return -EINVAL; } - wp->y_tiled = modifier == I915_FORMAT_MOD_Y_TILED || - modifier == I915_FORMAT_MOD_4_TILED || - modifier == I915_FORMAT_MOD_Yf_TILED || - modifier == I915_FORMAT_MOD_Y_TILED_CCS || - modifier == I915_FORMAT_MOD_Yf_TILED_CCS || - modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS || - modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS || - modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC || - modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS || - modifier == I915_FORMAT_MOD_4_TILED_DG2_MC_CCS || - modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS_CC; wp->x_tiled = modifier == I915_FORMAT_MOD_X_TILED; - wp->rc_surface = modifier == I915_FORMAT_MOD_Y_TILED_CCS || - modifier == I915_FORMAT_MOD_Yf_TILED_CCS || - modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS || - modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS || - modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC || - modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS || - modifier == I915_FORMAT_MOD_4_TILED_DG2_MC_CCS || - modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS_CC; + wp->y_tiled = modifier != I915_FORMAT_MOD_X_TILED && + intel_fb_is_tiled_modifier(modifier); + wp->rc_surface = intel_fb_is_ccs_modifier(modifier); wp->is_planar = intel_format_info_is_yuv_semiplanar(format, modifier); wp->width = width; @@ -2498,7 +2482,7 @@ skl_compute_ddb(struct intel_atomic_state *state) if (old_dbuf_state->joined_mbus != new_dbuf_state->joined_mbus) { /* TODO: Implement vblank synchronized MBUS joining changes */ - ret = intel_modeset_all_pipes(state); + ret = intel_modeset_all_pipes(state, "MBUS joining change"); if (ret) return ret; } @@ -2760,7 +2744,7 @@ static int skl_wm_add_affected_planes(struct intel_atomic_state *state, * power well the hardware state will go out of sync * with the software state. */ - if (!drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi) && + if (!intel_crtc_needs_modeset(new_crtc_state) && skl_plane_selected_wm_equals(plane, &old_crtc_state->wm.skl.optimal, &new_crtc_state->wm.skl.optimal)) diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c index b3f5ca280ef2..84481030883a 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi.c +++ b/drivers/gpu/drm/i915/display/vlv_dsi.c @@ -31,6 +31,7 @@ #include <drm/drm_mipi_dsi.h> #include "i915_drv.h" +#include "i915_reg.h" #include "intel_atomic.h" #include "intel_backlight.h" #include "intel_connector.h" @@ -1659,19 +1660,10 @@ static const struct drm_connector_funcs intel_dsi_connector_funcs = { static void vlv_dsi_add_properties(struct intel_connector *connector) { - struct drm_i915_private *dev_priv = to_i915(connector->base.dev); const struct drm_display_mode *fixed_mode = intel_panel_preferred_fixed_mode(connector); - u32 allowed_scalers; - allowed_scalers = BIT(DRM_MODE_SCALE_ASPECT) | BIT(DRM_MODE_SCALE_FULLSCREEN); - if (!HAS_GMCH(dev_priv)) - allowed_scalers |= BIT(DRM_MODE_SCALE_CENTER); - - drm_connector_attach_scaling_mode_property(&connector->base, - allowed_scalers); - - connector->base.state->scaling_mode = DRM_MODE_SCALE_ASPECT; + intel_attach_scaling_mode_property(&connector->base); drm_connector_set_panel_orientation_with_quirk(&connector->base, intel_dsi_get_panel_orientation(connector), @@ -1854,7 +1846,6 @@ static void vlv_dphy_param_init(struct intel_dsi *intel_dsi) void vlv_dsi_init(struct drm_i915_private *dev_priv) { - struct drm_device *dev = &dev_priv->drm; struct intel_dsi *intel_dsi; struct intel_encoder *intel_encoder; struct drm_encoder *encoder; @@ -1891,7 +1882,7 @@ void vlv_dsi_init(struct drm_i915_private *dev_priv) connector = &intel_connector->base; - drm_encoder_init(dev, encoder, &intel_dsi_funcs, DRM_MODE_ENCODER_DSI, + drm_encoder_init(&dev_priv->drm, encoder, &intel_dsi_funcs, DRM_MODE_ENCODER_DSI, "DSI %c", port_name(port)); intel_encoder->compute_config = intel_dsi_compute_config; @@ -1974,20 +1965,18 @@ void vlv_dsi_init(struct drm_i915_private *dev_priv) intel_dsi_vbt_gpio_init(intel_dsi, intel_dsi_get_hw_state(intel_encoder, &pipe)); - drm_connector_init(dev, connector, &intel_dsi_connector_funcs, + drm_connector_init(&dev_priv->drm, connector, &intel_dsi_connector_funcs, DRM_MODE_CONNECTOR_DSI); drm_connector_helper_add(connector, &intel_dsi_connector_helper_funcs); connector->display_info.subpixel_order = SubPixelHorizontalRGB; /*XXX*/ - connector->interlace_allowed = false; - connector->doublescan_allowed = false; intel_connector_attach_encoder(intel_connector, intel_encoder); - mutex_lock(&dev->mode_config.mutex); + mutex_lock(&dev_priv->drm.mode_config.mutex); intel_panel_add_vbt_lfp_fixed_mode(intel_connector); - mutex_unlock(&dev->mode_config.mutex); + mutex_unlock(&dev_priv->drm.mode_config.mutex); if (!intel_panel_preferred_fixed_mode(intel_connector)) { drm_dbg_kms(&dev_priv->drm, "no fixed mode\n"); diff --git a/drivers/gpu/drm/i915/display/vlv_dsi_regs.h b/drivers/gpu/drm/i915/display/vlv_dsi_regs.h index e065b8f2ee08..abbe427e462e 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi_regs.h +++ b/drivers/gpu/drm/i915/display/vlv_dsi_regs.h @@ -6,7 +6,7 @@ #ifndef __VLV_DSI_REGS_H__ #define __VLV_DSI_REGS_H__ -#include "i915_reg_defs.h" +#include "intel_display_reg_defs.h" #define VLV_MIPI_BASE VLV_DISPLAY_BASE #define BXT_MIPI_BASE 0x60000 diff --git a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c index 0512afdd20d8..b3b398fe689c 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c @@ -113,7 +113,7 @@ bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, clflush = clflush_work_create(obj); if (clflush) { i915_sw_fence_await_reservation(&clflush->base.chain, - obj->base.resv, NULL, true, + obj->base.resv, true, i915_fence_timeout(i915), I915_FENCE_GFP); dma_resv_add_fence(obj->base.resv, &clflush->base.dma, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index 1e29b1e6d186..7f2831efc798 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -546,7 +546,7 @@ set_proto_ctx_engines_bond(struct i915_user_extension __user *base, void *data) } if (intel_engine_uses_guc(master)) { - DRM_DEBUG("bonding extension not supported with GuC submission"); + drm_dbg(&i915->drm, "bonding extension not supported with GuC submission"); return -ENODEV; } @@ -1452,7 +1452,7 @@ static void engines_idle_release(struct i915_gem_context *ctx, int err; /* serialises with execbuf */ - set_bit(CONTEXT_CLOSED_BIT, &ce->flags); + intel_context_close(ce); if (!intel_context_pin_if_active(ce)) continue; @@ -2298,7 +2298,6 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data, } args->ctx_id = id; - drm_dbg(&i915->drm, "HW context %d created\n", args->ctx_id); return 0; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c index 824971a1ceec..fd556a076d05 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c @@ -25,43 +25,44 @@ static struct drm_i915_gem_object *dma_buf_to_obj(struct dma_buf *buf) return to_intel_bo(buf->priv); } -static struct sg_table *i915_gem_map_dma_buf(struct dma_buf_attachment *attachment, +static struct sg_table *i915_gem_map_dma_buf(struct dma_buf_attachment *attach, enum dma_data_direction dir) { - struct drm_i915_gem_object *obj = dma_buf_to_obj(attachment->dmabuf); - struct sg_table *st; + struct drm_i915_gem_object *obj = dma_buf_to_obj(attach->dmabuf); + struct sg_table *sgt; struct scatterlist *src, *dst; int ret, i; - /* Copy sg so that we make an independent mapping */ - st = kmalloc(sizeof(struct sg_table), GFP_KERNEL); - if (st == NULL) { + /* + * Make a copy of the object's sgt, so that we can make an independent + * mapping + */ + sgt = kmalloc(sizeof(*sgt), GFP_KERNEL); + if (!sgt) { ret = -ENOMEM; goto err; } - ret = sg_alloc_table(st, obj->mm.pages->orig_nents, GFP_KERNEL); + ret = sg_alloc_table(sgt, obj->mm.pages->orig_nents, GFP_KERNEL); if (ret) goto err_free; - src = obj->mm.pages->sgl; - dst = st->sgl; - for (i = 0; i < obj->mm.pages->orig_nents; i++) { + dst = sgt->sgl; + for_each_sg(obj->mm.pages->sgl, src, obj->mm.pages->orig_nents, i) { sg_set_page(dst, sg_page(src), src->length, 0); dst = sg_next(dst); - src = sg_next(src); } - ret = dma_map_sgtable(attachment->dev, st, dir, DMA_ATTR_SKIP_CPU_SYNC); + ret = dma_map_sgtable(attach->dev, sgt, dir, DMA_ATTR_SKIP_CPU_SYNC); if (ret) goto err_free_sg; - return st; + return sgt; err_free_sg: - sg_free_table(st); + sg_free_table(sgt); err_free: - kfree(st); + kfree(sgt); err: return ERR_PTR(ret); } @@ -72,7 +73,7 @@ static int i915_gem_dmabuf_vmap(struct dma_buf *dma_buf, struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf); void *vaddr; - vaddr = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WB); + vaddr = i915_gem_object_pin_map(obj, I915_MAP_WB); if (IS_ERR(vaddr)) return PTR_ERR(vaddr); @@ -96,6 +97,8 @@ static int i915_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct * struct drm_i915_private *i915 = to_i915(obj->base.dev); int ret; + dma_resv_assert_held(dma_buf->resv); + if (obj->base.size < vma->vm_end - vma->vm_start) return -EINVAL; @@ -236,15 +239,14 @@ struct dma_buf *i915_gem_prime_export(struct drm_gem_object *gem_obj, int flags) static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj) { struct drm_i915_private *i915 = to_i915(obj->base.dev); - struct sg_table *pages; - unsigned int sg_page_sizes; + struct sg_table *sgt; assert_object_held(obj); - pages = dma_buf_map_attachment(obj->base.import_attach, - DMA_BIDIRECTIONAL); - if (IS_ERR(pages)) - return PTR_ERR(pages); + sgt = dma_buf_map_attachment(obj->base.import_attach, + DMA_BIDIRECTIONAL); + if (IS_ERR(sgt)) + return PTR_ERR(sgt); /* * DG1 is special here since it still snoops transactions even with @@ -261,16 +263,15 @@ static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj) (!HAS_LLC(i915) && !IS_DG1(i915))) wbinvd_on_all_cpus(); - sg_page_sizes = i915_sg_dma_sizes(pages->sgl); - __i915_gem_object_set_pages(obj, pages, sg_page_sizes); + __i915_gem_object_set_pages(obj, sgt); return 0; } static void i915_gem_object_put_pages_dmabuf(struct drm_i915_gem_object *obj, - struct sg_table *pages) + struct sg_table *sgt) { - dma_buf_unmap_attachment(obj->base.import_attach, pages, + dma_buf_unmap_attachment(obj->base.import_attach, sgt, DMA_BIDIRECTIONAL); } @@ -313,7 +314,7 @@ struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev, get_dma_buf(dma_buf); obj = i915_gem_object_alloc(); - if (obj == NULL) { + if (!obj) { ret = -ENOMEM; goto fail_detach; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 845023c14eb3..f266b68cf012 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -30,6 +30,7 @@ #include "i915_gem_context.h" #include "i915_gem_evict.h" #include "i915_gem_ioctls.h" +#include "i915_reg.h" #include "i915_trace.h" #include "i915_user_extensions.h" @@ -53,13 +54,13 @@ enum { #define DBG_FORCE_RELOC 0 /* choose one of the above! */ }; -/* __EXEC_OBJECT_NO_RESERVE is BIT(31), defined in i915_vma.h */ -#define __EXEC_OBJECT_HAS_PIN BIT(30) -#define __EXEC_OBJECT_HAS_FENCE BIT(29) -#define __EXEC_OBJECT_USERPTR_INIT BIT(28) -#define __EXEC_OBJECT_NEEDS_MAP BIT(27) -#define __EXEC_OBJECT_NEEDS_BIAS BIT(26) -#define __EXEC_OBJECT_INTERNAL_FLAGS (~0u << 26) /* all of the above + */ +/* __EXEC_OBJECT_ flags > BIT(29) defined in i915_vma.h */ +#define __EXEC_OBJECT_HAS_PIN BIT(29) +#define __EXEC_OBJECT_HAS_FENCE BIT(28) +#define __EXEC_OBJECT_USERPTR_INIT BIT(27) +#define __EXEC_OBJECT_NEEDS_MAP BIT(26) +#define __EXEC_OBJECT_NEEDS_BIAS BIT(25) +#define __EXEC_OBJECT_INTERNAL_FLAGS (~0u << 25) /* all of the above + */ #define __EXEC_OBJECT_RESERVED (__EXEC_OBJECT_HAS_PIN | __EXEC_OBJECT_HAS_FENCE) #define __EXEC_HAS_RELOC BIT(31) @@ -729,37 +730,74 @@ static int eb_reserve(struct i915_execbuffer *eb) bool unpinned; /* - * Attempt to pin all of the buffers into the GTT. - * This is done in 2 phases: + * We have one more buffers that we couldn't bind, which could be due to + * various reasons. To resolve this we have 4 passes, with every next + * level turning the screws tighter: * - * 1. Unbind all objects that do not match the GTT constraints for - * the execbuffer (fenceable, mappable, alignment etc). - * 2. Bind new objects. + * 0. Unbind all objects that do not match the GTT constraints for the + * execbuffer (fenceable, mappable, alignment etc). Bind all new + * objects. This avoids unnecessary unbinding of later objects in order + * to make room for the earlier objects *unless* we need to defragment. * - * This avoid unnecessary unbinding of later objects in order to make - * room for the earlier objects *unless* we need to defragment. + * 1. Reorder the buffers, where objects with the most restrictive + * placement requirements go first (ignoring fixed location buffers for + * now). For example, objects needing the mappable aperture (the first + * 256M of GTT), should go first vs objects that can be placed just + * about anywhere. Repeat the previous pass. * - * Defragmenting is skipped if all objects are pinned at a fixed location. + * 2. Consider buffers that are pinned at a fixed location. Also try to + * evict the entire VM this time, leaving only objects that we were + * unable to lock. Try again to bind the buffers. (still using the new + * buffer order). + * + * 3. We likely have object lock contention for one or more stubborn + * objects in the VM, for which we need to evict to make forward + * progress (perhaps we are fighting the shrinker?). When evicting the + * VM this time around, anything that we can't lock we now track using + * the busy_bo, using the full lock (after dropping the vm->mutex to + * prevent deadlocks), instead of trylock. We then continue to evict the + * VM, this time with the stubborn object locked, which we can now + * hopefully unbind (if still bound in the VM). Repeat until the VM is + * evicted. Finally we should be able bind everything. */ - for (pass = 0; pass <= 2; pass++) { + for (pass = 0; pass <= 3; pass++) { int pin_flags = PIN_USER | PIN_VALIDATE; if (pass == 0) pin_flags |= PIN_NONBLOCK; if (pass >= 1) - unpinned = eb_unbind(eb, pass == 2); + unpinned = eb_unbind(eb, pass >= 2); if (pass == 2) { err = mutex_lock_interruptible(&eb->context->vm->mutex); if (!err) { - err = i915_gem_evict_vm(eb->context->vm, &eb->ww); + err = i915_gem_evict_vm(eb->context->vm, &eb->ww, NULL); mutex_unlock(&eb->context->vm->mutex); } if (err) return err; } + if (pass == 3) { +retry: + err = mutex_lock_interruptible(&eb->context->vm->mutex); + if (!err) { + struct drm_i915_gem_object *busy_bo = NULL; + + err = i915_gem_evict_vm(eb->context->vm, &eb->ww, &busy_bo); + mutex_unlock(&eb->context->vm->mutex); + if (err && busy_bo) { + err = i915_gem_object_lock(busy_bo, &eb->ww); + i915_gem_object_put(busy_bo); + if (!err) + goto retry; + } + } + if (err) + return err; + } + list_for_each_entry(ev, &eb->unbound, bind_link) { err = eb_reserve_vma(eb, ev, pin_flags); if (err) @@ -2101,7 +2139,8 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb) eb->composite_fence ? eb->composite_fence : &eb->requests[j]->fence, - flags | __EXEC_OBJECT_NO_RESERVE); + flags | __EXEC_OBJECT_NO_RESERVE | + __EXEC_OBJECT_NO_REQUEST_AWAIT); } } @@ -2148,7 +2187,8 @@ err_skip: return err; } -static int i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec) +static int i915_gem_check_execbuffer(struct drm_i915_private *i915, + struct drm_i915_gem_execbuffer2 *exec) { if (exec->flags & __I915_EXEC_ILLEGAL_FLAGS) return -EINVAL; @@ -2161,7 +2201,7 @@ static int i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec) } if (exec->DR4 == 0xffffffff) { - DRM_DEBUG("UXA submitting garbage DR4, fixing up\n"); + drm_dbg(&i915->drm, "UXA submitting garbage DR4, fixing up\n"); exec->DR4 = 0; } if (exec->DR1 || exec->DR4) @@ -2424,7 +2464,7 @@ gen8_dispatch_bsd_engine(struct drm_i915_private *dev_priv, /* Check whether the file_priv has already selected one ring. */ if ((int)file_priv->bsd_engine < 0) file_priv->bsd_engine = - prandom_u32_max(num_vcs_engines(dev_priv)); + get_random_u32_below(num_vcs_engines(dev_priv)); return file_priv->bsd_engine; } @@ -2799,7 +2839,8 @@ add_timeline_fence_array(struct i915_execbuffer *eb, syncobj = drm_syncobj_find(eb->file, user_fence.handle); if (!syncobj) { - DRM_DEBUG("Invalid syncobj handle provided\n"); + drm_dbg(&eb->i915->drm, + "Invalid syncobj handle provided\n"); return -ENOENT; } @@ -2807,7 +2848,8 @@ add_timeline_fence_array(struct i915_execbuffer *eb, if (!fence && user_fence.flags && !(user_fence.flags & I915_EXEC_FENCE_SIGNAL)) { - DRM_DEBUG("Syncobj handle has no fence\n"); + drm_dbg(&eb->i915->drm, + "Syncobj handle has no fence\n"); drm_syncobj_put(syncobj); return -EINVAL; } @@ -2816,7 +2858,9 @@ add_timeline_fence_array(struct i915_execbuffer *eb, err = dma_fence_chain_find_seqno(&fence, point); if (err && !(user_fence.flags & I915_EXEC_FENCE_SIGNAL)) { - DRM_DEBUG("Syncobj handle missing requested point %llu\n", point); + drm_dbg(&eb->i915->drm, + "Syncobj handle missing requested point %llu\n", + point); dma_fence_put(fence); drm_syncobj_put(syncobj); return err; @@ -2842,7 +2886,8 @@ add_timeline_fence_array(struct i915_execbuffer *eb, * 0) would break the timeline. */ if (user_fence.flags & I915_EXEC_FENCE_WAIT) { - DRM_DEBUG("Trying to wait & signal the same timeline point.\n"); + drm_dbg(&eb->i915->drm, + "Trying to wait & signal the same timeline point.\n"); dma_fence_put(fence); drm_syncobj_put(syncobj); return -EINVAL; @@ -2913,14 +2958,16 @@ static int add_fence_array(struct i915_execbuffer *eb) syncobj = drm_syncobj_find(eb->file, user_fence.handle); if (!syncobj) { - DRM_DEBUG("Invalid syncobj handle provided\n"); + drm_dbg(&eb->i915->drm, + "Invalid syncobj handle provided\n"); return -ENOENT; } if (user_fence.flags & I915_EXEC_FENCE_WAIT) { fence = drm_syncobj_fence_get(syncobj); if (!fence) { - DRM_DEBUG("Syncobj handle has no fence\n"); + drm_dbg(&eb->i915->drm, + "Syncobj handle has no fence\n"); drm_syncobj_put(syncobj); return -EINVAL; } @@ -2954,11 +3001,6 @@ await_fence_array(struct i915_execbuffer *eb, int err; for (n = 0; n < eb->num_fences; n++) { - struct drm_syncobj *syncobj; - unsigned int flags; - - syncobj = ptr_unpack_bits(eb->fences[n].syncobj, &flags, 2); - if (!eb->fences[n].dma_fence) continue; @@ -3520,7 +3562,7 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data, return -EINVAL; } - err = i915_gem_check_execbuffer(args); + err = i915_gem_check_execbuffer(i915, args); if (err) return err; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c index 629acb403a2c..f66bcefc09ec 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c @@ -35,7 +35,6 @@ static int i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj) struct drm_i915_private *i915 = to_i915(obj->base.dev); struct sg_table *st; struct scatterlist *sg; - unsigned int sg_page_sizes; unsigned int npages; int max_order = MAX_ORDER; unsigned int max_segment; @@ -64,7 +63,6 @@ create_st: sg = st->sgl; st->nents = 0; - sg_page_sizes = 0; do { int order = min(fls(npages) - 1, max_order); @@ -83,7 +81,6 @@ create_st: } while (1); sg_set_page(sg, page, PAGE_SIZE << order, 0); - sg_page_sizes |= PAGE_SIZE << order; st->nents++; npages -= 1 << order; @@ -105,7 +102,7 @@ create_st: goto err; } - __i915_gem_object_set_pages(obj, st, sg_page_sizes); + __i915_gem_object_set_pages(obj, st); return 0; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index 73d9eda1d6b7..0ad44f3868de 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -330,7 +330,7 @@ retry: if (ret) goto err_rpm; - ret = intel_gt_reset_trylock(ggtt->vm.gt, &srcu); + ret = intel_gt_reset_lock_interruptible(ggtt->vm.gt, &srcu); if (ret) goto err_pages; @@ -369,7 +369,7 @@ retry: if (vma == ERR_PTR(-ENOSPC)) { ret = mutex_lock_interruptible(&ggtt->vm.mutex); if (!ret) { - ret = i915_gem_evict_vm(&ggtt->vm, &ww); + ret = i915_gem_evict_vm(&ggtt->vm, &ww, NULL); mutex_unlock(&ggtt->vm.mutex); } if (ret) @@ -413,7 +413,7 @@ retry: vma->mmo = mmo; if (CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND) - intel_wakeref_auto(&to_gt(i915)->userfault_wakeref, + intel_wakeref_auto(&i915->runtime_pm.userfault_wakeref, msecs_to_jiffies_timeout(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND)); if (write) { @@ -557,11 +557,13 @@ void i915_gem_object_runtime_pm_release_mmap_offset(struct drm_i915_gem_object * drm_vma_node_unmap(&bo->base.vma_node, bdev->dev_mapping); - if (obj->userfault_count) { - /* rpm wakeref provide exclusive access */ - list_del(&obj->userfault_link); - obj->userfault_count = 0; - } + /* + * We have exclusive access here via runtime suspend. All other callers + * must first grab the rpm wakeref. + */ + GEM_BUG_ON(!obj->userfault_count); + list_del(&obj->userfault_link); + obj->userfault_count = 0; } void i915_gem_object_release_mmap_offset(struct drm_i915_gem_object *obj) @@ -587,13 +589,6 @@ void i915_gem_object_release_mmap_offset(struct drm_i915_gem_object *obj) spin_lock(&obj->mmo.lock); } spin_unlock(&obj->mmo.lock); - - if (obj->userfault_count) { - mutex_lock(&to_gt(to_i915(obj->base.dev))->lmem_userfault_lock); - list_del(&obj->userfault_link); - mutex_unlock(&to_gt(to_i915(obj->base.dev))->lmem_userfault_lock); - obj->userfault_count = 0; - } } static struct i915_mmap_offset * diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index 369006c5317f..1a0886b8aaa1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -290,7 +290,21 @@ void __i915_gem_object_pages_fini(struct drm_i915_gem_object *obj) __i915_gem_object_free_mmaps(obj); atomic_set(&obj->mm.pages_pin_count, 0); + + /* + * dma_buf_unmap_attachment() requires reservation to be + * locked. The imported GEM shouldn't share reservation lock + * and ttm_bo_cleanup_memtype_use() shouldn't be invoked for + * dma-buf, so it's safe to take the lock. + */ + if (obj->base.import_attach) + i915_gem_object_lock(obj, NULL); + __i915_gem_object_put_pages(obj); + + if (obj->base.import_attach) + i915_gem_object_unlock(obj); + GEM_BUG_ON(i915_gem_object_has_pages(obj)); } @@ -444,6 +458,16 @@ i915_gem_object_read_from_page_iomap(struct drm_i915_gem_object *obj, u64 offset io_mapping_unmap(src_map); } +static bool object_has_mappable_iomem(struct drm_i915_gem_object *obj) +{ + GEM_BUG_ON(!i915_gem_object_has_iomem(obj)); + + if (IS_DGFX(to_i915(obj->base.dev))) + return i915_ttm_resource_mappable(i915_gem_to_ttm(obj)->resource); + + return true; +} + /** * i915_gem_object_read_from_page - read data from the page of a GEM object * @obj: GEM object to read from @@ -466,7 +490,7 @@ int i915_gem_object_read_from_page(struct drm_i915_gem_object *obj, u64 offset, if (i915_gem_object_has_struct_page(obj)) i915_gem_object_read_from_page_kmap(obj, offset, dst, size); - else if (i915_gem_object_has_iomem(obj)) + else if (i915_gem_object_has_iomem(obj) && object_has_mappable_iomem(obj)) i915_gem_object_read_from_page_iomap(obj, offset, dst, size); else return -ENODEV; @@ -761,6 +785,9 @@ bool i915_gem_object_needs_ccs_pages(struct drm_i915_gem_object *obj) if (!HAS_FLAT_CCS(to_i915(obj->base.dev))) return false; + if (obj->flags & I915_BO_ALLOC_CCS_AUX) + return true; + for (i = 0; i < obj->mm.n_placements; i++) { /* Compression is not allowed for the objects with smem placement */ if (obj->mm.placements[i]->type == INTEL_MEMORY_SYSTEM) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index 1723af9b0f6a..3db53769864c 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -403,8 +403,7 @@ i915_gem_object_get_dma_address(struct drm_i915_gem_object *obj, unsigned long n); void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj, - struct sg_table *pages, - unsigned int sg_page_sizes); + struct sg_table *pages); int ____i915_gem_object_get_pages(struct drm_i915_gem_object *obj); int __i915_gem_object_get_pages(struct drm_i915_gem_object *obj); @@ -482,6 +481,10 @@ void *__must_check i915_gem_object_pin_map(struct drm_i915_gem_object *obj, void *__must_check i915_gem_object_pin_map_unlocked(struct drm_i915_gem_object *obj, enum i915_map_type type); +enum i915_map_type i915_coherent_map_type(struct drm_i915_private *i915, + struct drm_i915_gem_object *obj, + bool always_coherent); + void __i915_gem_object_flush_map(struct drm_i915_gem_object *obj, unsigned long offset, unsigned long size); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index d0d6772e6f36..ab4c2f90a564 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -327,16 +327,18 @@ struct drm_i915_gem_object { * dealing with userspace objects the CPU fault handler is free to ignore this. */ #define I915_BO_ALLOC_GPU_ONLY BIT(6) +#define I915_BO_ALLOC_CCS_AUX BIT(7) #define I915_BO_ALLOC_FLAGS (I915_BO_ALLOC_CONTIGUOUS | \ I915_BO_ALLOC_VOLATILE | \ I915_BO_ALLOC_CPU_CLEAR | \ I915_BO_ALLOC_USER | \ I915_BO_ALLOC_PM_VOLATILE | \ I915_BO_ALLOC_PM_EARLY | \ - I915_BO_ALLOC_GPU_ONLY) -#define I915_BO_READONLY BIT(7) -#define I915_TILING_QUIRK_BIT 8 /* unknown swizzling; do not release! */ -#define I915_BO_PROTECTED BIT(9) + I915_BO_ALLOC_GPU_ONLY | \ + I915_BO_ALLOC_CCS_AUX) +#define I915_BO_READONLY BIT(8) +#define I915_TILING_QUIRK_BIT 9 /* unknown swizzling; do not release! */ +#define I915_BO_PROTECTED BIT(10) /** * @mem_flags - Mutable placement-related flags * diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index 4df50b049cea..05a27723ebb8 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -16,8 +16,7 @@ #include "i915_gem_mman.h" void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj, - struct sg_table *pages, - unsigned int sg_page_sizes) + struct sg_table *pages) { struct drm_i915_private *i915 = to_i915(obj->base.dev); unsigned long supported = RUNTIME_INFO(i915)->page_sizes; @@ -45,8 +44,8 @@ void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj, obj->mm.pages = pages; - GEM_BUG_ON(!sg_page_sizes); - obj->mm.page_sizes.phys = sg_page_sizes; + obj->mm.page_sizes.phys = i915_sg_dma_sizes(pages->sgl); + GEM_BUG_ON(!obj->mm.page_sizes.phys); /* * Calculate the supported page-sizes which fit into the given @@ -466,6 +465,18 @@ void *i915_gem_object_pin_map_unlocked(struct drm_i915_gem_object *obj, return ret; } +enum i915_map_type i915_coherent_map_type(struct drm_i915_private *i915, + struct drm_i915_gem_object *obj, + bool always_coherent) +{ + if (i915_gem_object_is_lmem(obj)) + return I915_MAP_WC; + if (HAS_LLC(i915) || always_coherent) + return I915_MAP_WB; + else + return I915_MAP_WC; +} + void __i915_gem_object_flush_map(struct drm_i915_gem_object *obj, unsigned long offset, unsigned long size) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/i915_gem_phys.c index 0d0e46dae559..68453572275b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_phys.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_phys.c @@ -79,7 +79,7 @@ static int i915_gem_object_get_pages_phys(struct drm_i915_gem_object *obj) /* We're no longer struct page backed */ obj->mem_flags &= ~I915_BO_FLAG_STRUCT_PAGE; - __i915_gem_object_set_pages(obj, st, sg->length); + __i915_gem_object_set_pages(obj, st); return 0; @@ -209,11 +209,8 @@ static int i915_gem_object_shmem_to_phys(struct drm_i915_gem_object *obj) return 0; err_xfer: - if (!IS_ERR_OR_NULL(pages)) { - unsigned int sg_page_sizes = i915_sg_dma_sizes(pages->sgl); - - __i915_gem_object_set_pages(obj, pages, sg_page_sizes); - } + if (!IS_ERR_OR_NULL(pages)) + __i915_gem_object_set_pages(obj, pages); return err; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c index 3428f735e786..0d812f4d787d 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c @@ -22,9 +22,12 @@ void i915_gem_suspend(struct drm_i915_private *i915) { + struct intel_gt *gt; + unsigned int i; + GEM_TRACE("%s\n", dev_name(i915->drm.dev)); - intel_wakeref_auto(&to_gt(i915)->userfault_wakeref, 0); + intel_wakeref_auto(&i915->runtime_pm.userfault_wakeref, 0); flush_workqueue(i915->wq); /* @@ -36,7 +39,8 @@ void i915_gem_suspend(struct drm_i915_private *i915) * state. Fortunately, the kernel_context is disposable and we do * not rely on its state. */ - intel_gt_suspend_prepare(to_gt(i915)); + for_each_gt(gt, i915, i) + intel_gt_suspend_prepare(gt); i915_gem_drain_freed_objects(i915); } @@ -131,7 +135,9 @@ void i915_gem_suspend_late(struct drm_i915_private *i915) &i915->mm.purge_list, NULL }, **phase; + struct intel_gt *gt; unsigned long flags; + unsigned int i; bool flush = false; /* @@ -154,7 +160,8 @@ void i915_gem_suspend_late(struct drm_i915_private *i915) * machine in an unusable condition. */ - intel_gt_suspend_late(to_gt(i915)); + for_each_gt(gt, i915, i) + intel_gt_suspend_late(gt); spin_lock_irqsave(&i915->mm.obj_lock, flags); for (phase = phases; *phase; phase++) { @@ -212,7 +219,8 @@ int i915_gem_freeze_late(struct drm_i915_private *i915) void i915_gem_resume(struct drm_i915_private *i915) { - int ret; + struct intel_gt *gt; + int ret, i, j; GEM_TRACE("%s\n", dev_name(i915->drm.dev)); @@ -224,8 +232,25 @@ void i915_gem_resume(struct drm_i915_private *i915) * guarantee that the context image is complete. So let's just reset * it and start again. */ - intel_gt_resume(to_gt(i915)); + for_each_gt(gt, i915, i) + if (intel_gt_resume(gt)) + goto err_wedged; ret = lmem_restore(i915, I915_TTM_BACKUP_ALLOW_GPU); GEM_WARN_ON(ret); + + return; + +err_wedged: + for_each_gt(gt, i915, j) { + if (!intel_gt_is_wedged(gt)) { + dev_err(i915->drm.dev, + "Failed to re-initialize GPU[%u], declaring it wedged!\n", + j); + intel_gt_set_wedged(gt); + } + + if (j == i) + break; + } } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index 2f7804492cd5..9c759df700ca 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -247,7 +247,7 @@ rebuild_st: if (i915_gem_object_can_bypass_llc(obj)) obj->cache_dirty = true; - __i915_gem_object_set_pages(obj, st, i915_sg_dma_sizes(st->sgl)); + __i915_gem_object_set_pages(obj, st); return 0; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c index acc561c0f0aa..bc9521078807 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c @@ -77,22 +77,26 @@ void i915_gem_stolen_remove_node(struct drm_i915_private *i915, mutex_unlock(&i915->mm.stolen_lock); } -static int i915_adjust_stolen(struct drm_i915_private *i915, - struct resource *dsm) +static bool valid_stolen_size(struct drm_i915_private *i915, struct resource *dsm) +{ + return (dsm->start != 0 || HAS_LMEMBAR_SMEM_STOLEN(i915)) && dsm->end > dsm->start; +} + +static int adjust_stolen(struct drm_i915_private *i915, + struct resource *dsm) { struct i915_ggtt *ggtt = to_gt(i915)->ggtt; struct intel_uncore *uncore = ggtt->vm.gt->uncore; - struct resource *r; - if (dsm->start == 0 || dsm->end <= dsm->start) + if (!valid_stolen_size(i915, dsm)) return -EINVAL; /* + * Make sure we don't clobber the GTT if it's within stolen memory + * * TODO: We have yet too encounter the case where the GTT wasn't at the * end of stolen. With that assumption we could simplify this. */ - - /* Make sure we don't clobber the GTT if it's within stolen memory */ if (GRAPHICS_VER(i915) <= 4 && !IS_G33(i915) && !IS_PINEVIEW(i915) && !IS_G4X(i915)) { struct resource stolen[2] = {*dsm, *dsm}; @@ -131,12 +135,25 @@ static int i915_adjust_stolen(struct drm_i915_private *i915, } } + if (!valid_stolen_size(i915, dsm)) + return -EINVAL; + + return 0; +} + +static int request_smem_stolen(struct drm_i915_private *i915, + struct resource *dsm) +{ + struct resource *r; + /* - * With stolen lmem, we don't need to check if the address range - * overlaps with the non-stolen system memory range, since lmem is local - * to the gpu. + * With stolen lmem, we don't need to request system memory for the + * address range since it's local to the gpu. + * + * Starting MTL, in IGFX devices the stolen memory is exposed via + * LMEMBAR and shall be considered similar to stolen lmem. */ - if (HAS_LMEM(i915)) + if (HAS_LMEM(i915) || HAS_LMEMBAR_SMEM_STOLEN(i915)) return 0; /* @@ -371,8 +388,6 @@ static void icl_get_stolen_reserved(struct drm_i915_private *i915, drm_dbg(&i915->drm, "GEN6_STOLEN_RESERVED = 0x%016llx\n", reg_val); - *base = reg_val & GEN11_STOLEN_RESERVED_ADDR_MASK; - switch (reg_val & GEN8_STOLEN_RESERVED_SIZE_MASK) { case GEN8_STOLEN_RESERVED_1M: *size = 1024 * 1024; @@ -390,41 +405,30 @@ static void icl_get_stolen_reserved(struct drm_i915_private *i915, *size = 8 * 1024 * 1024; MISSING_CASE(reg_val & GEN8_STOLEN_RESERVED_SIZE_MASK); } + + if (HAS_LMEMBAR_SMEM_STOLEN(i915)) + /* the base is initialized to stolen top so subtract size to get base */ + *base -= *size; + else + *base = reg_val & GEN11_STOLEN_RESERVED_ADDR_MASK; } -static int i915_gem_init_stolen(struct intel_memory_region *mem) +/* + * Initialize i915->dsm_reserved to contain the reserved space within the Data + * Stolen Memory. This is a range on the top of DSM that is reserved, not to + * be used by driver, so must be excluded from the region passed to the + * allocator later. In the spec this is also called as WOPCM. + * + * Our expectation is that the reserved space is at the top of the stolen + * region, as it has been the case for every platform, and *never* at the + * bottom, so the calculation here can be simplified. + */ +static int init_reserved_stolen(struct drm_i915_private *i915) { - struct drm_i915_private *i915 = mem->i915; struct intel_uncore *uncore = &i915->uncore; resource_size_t reserved_base, stolen_top; - resource_size_t reserved_total, reserved_size; - - mutex_init(&i915->mm.stolen_lock); - - if (intel_vgpu_active(i915)) { - drm_notice(&i915->drm, - "%s, disabling use of stolen memory\n", - "iGVT-g active"); - return 0; - } - - if (i915_vtd_active(i915) && GRAPHICS_VER(i915) < 8) { - drm_notice(&i915->drm, - "%s, disabling use of stolen memory\n", - "DMAR active"); - return 0; - } - - if (resource_size(&mem->region) == 0) - return 0; - - i915->dsm = mem->region; - - if (i915_adjust_stolen(i915, &i915->dsm)) - return 0; - - GEM_BUG_ON(i915->dsm.start == 0); - GEM_BUG_ON(i915->dsm.end <= i915->dsm.start); + resource_size_t reserved_size; + int ret = 0; stolen_top = i915->dsm.end + 1; reserved_base = stolen_top; @@ -455,17 +459,16 @@ static int i915_gem_init_stolen(struct intel_memory_region *mem) &reserved_base, &reserved_size); } - /* - * Our expectation is that the reserved space is at the top of the - * stolen region and *never* at the bottom. If we see !reserved_base, - * it likely means we failed to read the registers correctly. - */ + /* No reserved stolen */ + if (reserved_base == stolen_top) + goto bail_out; + if (!reserved_base) { drm_err(&i915->drm, "inconsistent reservation %pa + %pa; ignoring\n", &reserved_base, &reserved_size); - reserved_base = stolen_top; - reserved_size = 0; + ret = -EINVAL; + goto bail_out; } i915->dsm_reserved = @@ -475,19 +478,55 @@ static int i915_gem_init_stolen(struct intel_memory_region *mem) drm_err(&i915->drm, "Stolen reserved area %pR outside stolen memory %pR\n", &i915->dsm_reserved, &i915->dsm); - return 0; + ret = -EINVAL; + goto bail_out; } + return 0; + +bail_out: + i915->dsm_reserved = + (struct resource)DEFINE_RES_MEM(reserved_base, 0); + + return ret; +} + +static int i915_gem_init_stolen(struct intel_memory_region *mem) +{ + struct drm_i915_private *i915 = mem->i915; + + mutex_init(&i915->mm.stolen_lock); + + if (intel_vgpu_active(i915)) { + drm_notice(&i915->drm, + "%s, disabling use of stolen memory\n", + "iGVT-g active"); + return -ENOSPC; + } + + if (i915_vtd_active(i915) && GRAPHICS_VER(i915) < 8) { + drm_notice(&i915->drm, + "%s, disabling use of stolen memory\n", + "DMAR active"); + return -ENOSPC; + } + + if (adjust_stolen(i915, &mem->region)) + return -ENOSPC; + + if (request_smem_stolen(i915, &mem->region)) + return -ENOSPC; + + i915->dsm = mem->region; + + if (init_reserved_stolen(i915)) + return -ENOSPC; + /* Exclude the reserved region from driver use */ - mem->region.end = reserved_base - 1; + mem->region.end = i915->dsm_reserved.start - 1; mem->io_size = min(mem->io_size, resource_size(&mem->region)); - /* It is possible for the reserved area to end before the end of stolen - * memory, so just consider the start. */ - reserved_total = stolen_top - reserved_base; - - i915->stolen_usable_size = - resource_size(&i915->dsm) - reserved_total; + i915->stolen_usable_size = resource_size(&mem->region); drm_dbg(&i915->drm, "Memory reserved for graphics device: %lluK, usable: %lluK\n", @@ -495,7 +534,7 @@ static int i915_gem_init_stolen(struct intel_memory_region *mem) (u64)i915->stolen_usable_size >> 10); if (i915->stolen_usable_size == 0) - return 0; + return -ENOSPC; /* Basic memrange allocator for stolen space. */ drm_mm_init(&i915->mm.stolen, 0, i915->stolen_usable_size); @@ -589,7 +628,7 @@ static int i915_gem_object_get_pages_stolen(struct drm_i915_gem_object *obj) sg_dma_len(pages->sgl), POISON_INUSE); - __i915_gem_object_set_pages(obj, pages, obj->stolen->size); + __i915_gem_object_set_pages(obj, pages); return 0; } @@ -733,11 +772,17 @@ i915_gem_object_create_stolen(struct drm_i915_private *i915, static int init_stolen_smem(struct intel_memory_region *mem) { + int err; + /* * Initialise stolen early so that we may reserve preallocated * objects for the BIOS to KMS transition. */ - return i915_gem_init_stolen(mem); + err = i915_gem_init_stolen(mem); + if (err) + drm_dbg(&mem->i915->drm, "Skip stolen region: failed to setup\n"); + + return 0; } static int release_stolen_smem(struct intel_memory_region *mem) @@ -754,26 +799,25 @@ static const struct intel_memory_region_ops i915_region_stolen_smem_ops = { static int init_stolen_lmem(struct intel_memory_region *mem) { + struct drm_i915_private *i915 = mem->i915; int err; if (GEM_WARN_ON(resource_size(&mem->region) == 0)) - return -ENODEV; + return 0; - /* - * TODO: For stolen lmem we mostly just care about populating the dsm - * related bits and setting up the drm_mm allocator for the range. - * Perhaps split up i915_gem_init_stolen() for this. - */ err = i915_gem_init_stolen(mem); - if (err) - return err; + if (err) { + drm_dbg(&mem->i915->drm, "Skip stolen region: failed to setup\n"); + return 0; + } - if (mem->io_size && !io_mapping_init_wc(&mem->iomap, - mem->io_start, - mem->io_size)) { - err = -EIO; + if (mem->io_size && + !io_mapping_init_wc(&mem->iomap, mem->io_start, mem->io_size)) goto err_cleanup; - } + + drm_dbg(&i915->drm, "Stolen Local memory IO start: %pa\n", + &mem->io_start); + drm_dbg(&i915->drm, "Stolen Local DSM base: %pa\n", &mem->region.start); return 0; @@ -796,6 +840,29 @@ static const struct intel_memory_region_ops i915_region_stolen_lmem_ops = { .init_object = _i915_gem_object_stolen_init, }; +static int mtl_get_gms_size(struct intel_uncore *uncore) +{ + u16 ggc, gms; + + ggc = intel_uncore_read16(uncore, GGC); + + /* check GGMS, should be fixed 0x3 (8MB) */ + if ((ggc & GGMS_MASK) != GGMS_MASK) + return -EIO; + + /* return valid GMS value, -EIO if invalid */ + gms = REG_FIELD_GET(GMS_MASK, ggc); + switch (gms) { + case 0x0 ... 0x04: + return gms * 32; + case 0xf0 ... 0xfe: + return (gms - 0xf0 + 1) * 4; + default: + MISSING_CASE(gms); + return -EIO; + } +} + struct intel_memory_region * i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type, u16 instance) @@ -806,6 +873,7 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type, struct intel_memory_region *mem; resource_size_t io_start, io_size; resource_size_t min_page_size; + int ret; if (WARN_ON_ONCE(instance)) return ERR_PTR(-ENODEV); @@ -813,12 +881,8 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type, if (!i915_pci_resource_valid(pdev, GEN12_LMEM_BAR)) return ERR_PTR(-ENXIO); - /* Use DSM base address instead for stolen memory */ - dsm_base = intel_uncore_read64(uncore, GEN12_DSMBASE); - if (IS_DG1(uncore->i915)) { + if (HAS_LMEMBAR_SMEM_STOLEN(i915) || IS_DG1(i915)) { lmem_size = pci_resource_len(pdev, GEN12_LMEM_BAR); - if (WARN_ON(lmem_size < dsm_base)) - return ERR_PTR(-ENODEV); } else { resource_size_t lmem_range; @@ -827,13 +891,39 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type, lmem_size *= SZ_1G; } - dsm_size = lmem_size - dsm_base; - if (pci_resource_len(pdev, GEN12_LMEM_BAR) < lmem_size) { + if (HAS_LMEMBAR_SMEM_STOLEN(i915)) { + /* + * MTL dsm size is in GGC register. + * Also MTL uses offset to DSMBASE in ptes, so i915 + * uses dsm_base = 0 to setup stolen region. + */ + ret = mtl_get_gms_size(uncore); + if (ret < 0) { + drm_err(&i915->drm, "invalid MTL GGC register setting\n"); + return ERR_PTR(ret); + } + + dsm_base = 0; + dsm_size = (resource_size_t)(ret * SZ_1M); + + GEM_BUG_ON(pci_resource_len(pdev, GEN12_LMEM_BAR) != SZ_256M); + GEM_BUG_ON((dsm_size + SZ_8M) > lmem_size); + } else { + /* Use DSM base address instead for stolen memory */ + dsm_base = intel_uncore_read64(uncore, GEN12_DSMBASE) & GEN12_BDSM_MASK; + if (WARN_ON(lmem_size < dsm_base)) + return ERR_PTR(-ENODEV); + dsm_size = lmem_size - dsm_base; + } + + io_size = dsm_size; + if (HAS_LMEMBAR_SMEM_STOLEN(i915)) { + io_start = pci_resource_start(pdev, GEN12_LMEM_BAR) + SZ_8M; + } else if (pci_resource_len(pdev, GEN12_LMEM_BAR) < lmem_size) { io_start = 0; io_size = 0; } else { io_start = pci_resource_start(pdev, GEN12_LMEM_BAR) + dsm_base; - io_size = dsm_size; } min_page_size = HAS_64K_PAGES(i915) ? I915_GTT_PAGE_SIZE_64K : @@ -847,16 +937,6 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type, if (IS_ERR(mem)) return mem; - /* - * TODO: consider creating common helper to just print all the - * interesting stuff from intel_memory_region, which we can use for all - * our probed regions. - */ - - drm_dbg(&i915->drm, "Stolen Local memory IO start: %pa\n", - &mem->io_start); - drm_dbg(&i915->drm, "Stolen Local DSM base: %pa\n", &dsm_base); - intel_memory_region_set_name(mem, "stolen-local"); mem->private = true; @@ -881,6 +961,7 @@ i915_gem_stolen_smem_setup(struct drm_i915_private *i915, u16 type, intel_memory_region_set_name(mem, "stolen-system"); mem->private = true; + return mem; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index 0d6d640225fc..1e50fb0d6bfc 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -279,7 +279,7 @@ static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo, struct i915_ttm_tt *i915_tt; int ret; - if (!obj) + if (i915_ttm_is_ghost_object(bo)) return NULL; i915_tt = kzalloc(sizeof(*i915_tt), GFP_KERNEL); @@ -362,7 +362,7 @@ static bool i915_ttm_eviction_valuable(struct ttm_buffer_object *bo, { struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); - if (!obj) + if (i915_ttm_is_ghost_object(bo)) return false; /* @@ -509,18 +509,9 @@ static int i915_ttm_shrink(struct drm_i915_gem_object *obj, unsigned int flags) static void i915_ttm_delete_mem_notify(struct ttm_buffer_object *bo) { struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); - intel_wakeref_t wakeref = 0; - - if (bo->resource && likely(obj)) { - /* ttm_bo_release() already has dma_resv_lock */ - if (i915_ttm_cpu_maps_iomem(bo->resource)) - wakeref = intel_runtime_pm_get(&to_i915(obj->base.dev)->runtime_pm); + if (bo->resource && !i915_ttm_is_ghost_object(bo)) { __i915_gem_object_pages_fini(obj); - - if (wakeref) - intel_runtime_pm_put(&to_i915(obj->base.dev)->runtime_pm, wakeref); - i915_ttm_free_cached_io_rsgt(obj); } } @@ -628,7 +619,7 @@ static void i915_ttm_swap_notify(struct ttm_buffer_object *bo) struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); int ret; - if (!obj) + if (i915_ttm_is_ghost_object(bo)) return; ret = i915_ttm_move_notify(bo); @@ -653,7 +644,7 @@ bool i915_ttm_resource_mappable(struct ttm_resource *res) if (!i915_ttm_cpu_maps_iomem(res)) return true; - return bman_res->used_visible_size == bman_res->base.num_pages; + return bman_res->used_visible_size == PFN_UP(bman_res->base.size); } static int i915_ttm_io_mem_reserve(struct ttm_device *bdev, struct ttm_resource *mem) @@ -661,7 +652,7 @@ static int i915_ttm_io_mem_reserve(struct ttm_device *bdev, struct ttm_resource struct drm_i915_gem_object *obj = i915_ttm_to_gem(mem->bo); bool unknown_state; - if (!obj) + if (i915_ttm_is_ghost_object(mem->bo)) return -EINVAL; if (!kref_get_unless_zero(&obj->base.refcount)) @@ -694,7 +685,7 @@ static unsigned long i915_ttm_io_mem_pfn(struct ttm_buffer_object *bo, unsigned long base; unsigned int ofs; - GEM_BUG_ON(!obj); + GEM_BUG_ON(i915_ttm_is_ghost_object(bo)); GEM_WARN_ON(bo->ttm); base = obj->mm.region->iomap.base - obj->mm.region->region.start; @@ -703,6 +694,50 @@ static unsigned long i915_ttm_io_mem_pfn(struct ttm_buffer_object *bo, return ((base + sg_dma_address(sg)) >> PAGE_SHIFT) + ofs; } +static int i915_ttm_access_memory(struct ttm_buffer_object *bo, + unsigned long offset, void *buf, + int len, int write) +{ + struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); + resource_size_t iomap = obj->mm.region->iomap.base - + obj->mm.region->region.start; + unsigned long page = offset >> PAGE_SHIFT; + unsigned long bytes_left = len; + + /* + * TODO: For now just let it fail if the resource is non-mappable, + * otherwise we need to perform the memcpy from the gpu here, without + * interfering with the object (like moving the entire thing). + */ + if (!i915_ttm_resource_mappable(bo->resource)) + return -EIO; + + offset -= page << PAGE_SHIFT; + do { + unsigned long bytes = min(bytes_left, PAGE_SIZE - offset); + void __iomem *ptr; + dma_addr_t daddr; + + daddr = i915_gem_object_get_dma_address(obj, page); + ptr = ioremap_wc(iomap + daddr + offset, bytes); + if (!ptr) + return -EIO; + + if (write) + memcpy_toio(ptr, buf, bytes); + else + memcpy_fromio(buf, ptr, bytes); + iounmap(ptr); + + page++; + buf += bytes; + bytes_left -= bytes; + offset = 0; + } while (bytes_left); + + return len; +} + /* * All callbacks need to take care not to downcast a struct ttm_buffer_object * without checking its subclass, since it might be a TTM ghost object. @@ -719,6 +754,7 @@ static struct ttm_device_funcs i915_ttm_bo_driver = { .delete_mem_notify = i915_ttm_delete_mem_notify, .io_mem_reserve = i915_ttm_io_mem_reserve, .io_mem_pfn = i915_ttm_io_mem_pfn, + .access_memory = i915_ttm_access_memory, }; /** @@ -783,8 +819,7 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj, GEM_BUG_ON(obj->mm.rsgt); obj->mm.rsgt = rsgt; - __i915_gem_object_set_pages(obj, &rsgt->table, - i915_sg_dma_sizes(rsgt->table.sgl)); + __i915_gem_object_set_pages(obj, &rsgt->table); } GEM_BUG_ON(bo->ttm && ((obj->base.size >> PAGE_SHIFT) < bo->ttm->num_pages)); @@ -994,15 +1029,11 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf) struct vm_area_struct *area = vmf->vma; struct ttm_buffer_object *bo = area->vm_private_data; struct drm_device *dev = bo->base.dev; - struct drm_i915_gem_object *obj; + struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); intel_wakeref_t wakeref = 0; vm_fault_t ret; int idx; - obj = i915_ttm_to_gem(bo); - if (!obj) - return VM_FAULT_SIGBUS; - /* Sanity check that we allow writing into this object */ if (unlikely(i915_gem_object_is_readonly(obj) && area->vm_flags & VM_WRITE)) @@ -1036,7 +1067,8 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf) } if (err) { - drm_dbg(dev, "Unable to make resource CPU accessible\n"); + drm_dbg(dev, "Unable to make resource CPU accessible(err = %pe)\n", + ERR_PTR(err)); dma_resv_unlock(bo->base.resv); ret = VM_FAULT_SIGBUS; goto out_rpm; @@ -1057,16 +1089,21 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf) if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) goto out_rpm; - /* ttm_bo_vm_reserve() already has dma_resv_lock */ + /* + * ttm_bo_vm_reserve() already has dma_resv_lock. + * userfault_count is protected by dma_resv lock and rpm wakeref. + */ if (ret == VM_FAULT_NOPAGE && wakeref && !obj->userfault_count) { obj->userfault_count = 1; - mutex_lock(&to_gt(to_i915(obj->base.dev))->lmem_userfault_lock); - list_add(&obj->userfault_link, &to_gt(to_i915(obj->base.dev))->lmem_userfault_list); - mutex_unlock(&to_gt(to_i915(obj->base.dev))->lmem_userfault_lock); + spin_lock(&to_i915(obj->base.dev)->runtime_pm.lmem_userfault_lock); + list_add(&obj->userfault_link, &to_i915(obj->base.dev)->runtime_pm.lmem_userfault_list); + spin_unlock(&to_i915(obj->base.dev)->runtime_pm.lmem_userfault_lock); + + GEM_WARN_ON(!i915_ttm_cpu_maps_iomem(bo->resource)); } if (wakeref & CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND) - intel_wakeref_auto(&to_gt(to_i915(obj->base.dev))->userfault_wakeref, + intel_wakeref_auto(&to_i915(obj->base.dev)->runtime_pm.userfault_wakeref, msecs_to_jiffies_timeout(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND)); i915_ttm_adjust_lru(obj); @@ -1098,7 +1135,7 @@ static void ttm_vm_open(struct vm_area_struct *vma) struct drm_i915_gem_object *obj = i915_ttm_to_gem(vma->vm_private_data); - GEM_BUG_ON(!obj); + GEM_BUG_ON(i915_ttm_is_ghost_object(vma->vm_private_data)); i915_gem_object_get(obj); } @@ -1107,7 +1144,7 @@ static void ttm_vm_close(struct vm_area_struct *vma) struct drm_i915_gem_object *obj = i915_ttm_to_gem(vma->vm_private_data); - GEM_BUG_ON(!obj); + GEM_BUG_ON(i915_ttm_is_ghost_object(vma->vm_private_data)); i915_gem_object_put(obj); } @@ -1128,7 +1165,29 @@ static u64 i915_ttm_mmap_offset(struct drm_i915_gem_object *obj) static void i915_ttm_unmap_virtual(struct drm_i915_gem_object *obj) { + struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); + intel_wakeref_t wakeref = 0; + + assert_object_held_shared(obj); + + if (i915_ttm_cpu_maps_iomem(bo->resource)) { + wakeref = intel_runtime_pm_get(&to_i915(obj->base.dev)->runtime_pm); + + /* userfault_count is protected by obj lock and rpm wakeref. */ + if (obj->userfault_count) { + spin_lock(&to_i915(obj->base.dev)->runtime_pm.lmem_userfault_lock); + list_del(&obj->userfault_link); + spin_unlock(&to_i915(obj->base.dev)->runtime_pm.lmem_userfault_lock); + obj->userfault_count = 0; + } + } + + GEM_WARN_ON(obj->userfault_count); + ttm_bo_unmap_virtual(i915_gem_to_ttm(obj)); + + if (wakeref) + intel_runtime_pm_put(&to_i915(obj->base.dev)->runtime_pm, wakeref); } static const struct drm_i915_gem_object_ops i915_gem_ttm_obj_ops = { diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.h b/drivers/gpu/drm/i915/gem/i915_gem_ttm.h index e4842b4296fc..2a94a99ef76b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.h @@ -28,18 +28,26 @@ i915_gem_to_ttm(struct drm_i915_gem_object *obj) void i915_ttm_bo_destroy(struct ttm_buffer_object *bo); /** + * i915_ttm_is_ghost_object - Check if the ttm bo is a ghost object. + * @bo: Pointer to the ttm buffer object + * + * Return: True if the ttm bo is not a i915 object but a ghost ttm object, + * False otherwise. + */ +static inline bool i915_ttm_is_ghost_object(struct ttm_buffer_object *bo) +{ + return bo->destroy != i915_ttm_bo_destroy; +} + +/** * i915_ttm_to_gem - Convert a struct ttm_buffer_object to an embedding * struct drm_i915_gem_object. * - * Return: Pointer to the embedding struct ttm_buffer_object, or NULL - * if the object was not an i915 ttm object. + * Return: Pointer to the embedding struct ttm_buffer_object. */ static inline struct drm_i915_gem_object * i915_ttm_to_gem(struct ttm_buffer_object *bo) { - if (bo->destroy != i915_ttm_bo_destroy) - return NULL; - return container_of(bo, struct drm_i915_gem_object, __do_not_access); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c index 9a7e50534b84..f59f812dc6d2 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c @@ -560,7 +560,7 @@ int i915_ttm_move(struct ttm_buffer_object *bo, bool evict, bool clear; int ret; - if (GEM_WARN_ON(!obj)) { + if (GEM_WARN_ON(i915_ttm_is_ghost_object(bo))) { ttm_bo_move_null(bo, dst_mem); return 0; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c index 07e49f22f2de..7e67742bc65e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c @@ -50,6 +50,7 @@ static int i915_ttm_backup(struct i915_gem_apply_to_region *apply, container_of(bo->bdev, typeof(*i915), bdev); struct drm_i915_gem_object *backup; struct ttm_operation_ctx ctx = {}; + unsigned int flags; int err = 0; if (bo->resource->mem_type == I915_PL_SYSTEM || obj->ttm.backup) @@ -65,7 +66,22 @@ static int i915_ttm_backup(struct i915_gem_apply_to_region *apply, if (obj->flags & I915_BO_ALLOC_PM_VOLATILE) return 0; - backup = i915_gem_object_create_shmem(i915, obj->base.size); + /* + * It seems that we might have some framebuffers still pinned at this + * stage, but for such objects we might also need to deal with the CCS + * aux state. Make sure we force the save/restore of the CCS state, + * otherwise we might observe display corruption, when returning from + * suspend. + */ + flags = 0; + if (i915_gem_object_needs_ccs_pages(obj)) { + WARN_ON_ONCE(!i915_gem_object_is_framebuffer(obj)); + WARN_ON_ONCE(!pm_apply->allow_gpu); + + flags = I915_BO_ALLOC_CCS_AUX; + } + backup = i915_gem_object_create_region(i915->mm.regions[INTEL_REGION_SMEM], + obj->base.size, 0, flags); if (IS_ERR(backup)) return PTR_ERR(backup); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index ba14b18d65f3..9348b1804d53 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -131,7 +131,6 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) const unsigned long num_pages = obj->base.size >> PAGE_SHIFT; unsigned int max_segment = i915_sg_segment_size(obj->base.dev->dev); struct sg_table *st; - unsigned int sg_page_sizes; struct page **pvec; int ret; @@ -170,8 +169,7 @@ alloc_table: if (i915_gem_object_can_bypass_llc(obj)) obj->cache_dirty = true; - sg_page_sizes = i915_sg_dma_sizes(st->sgl); - __i915_gem_object_set_pages(obj, st, sg_page_sizes); + __i915_gem_object_set_pages(obj, st); return 0; @@ -292,7 +290,7 @@ int i915_gem_object_userptr_submit_init(struct drm_i915_gem_object *obj) if (!i915_gem_object_is_readonly(obj)) gup_flags |= FOLL_WRITE; - pinned = ret = 0; + pinned = 0; while (pinned < num_pages) { ret = pin_user_pages_fast(obj->userptr.ptr + pinned * PAGE_SIZE, num_pages - pinned, gup_flags, @@ -302,7 +300,6 @@ int i915_gem_object_userptr_submit_init(struct drm_i915_gem_object *obj) pinned += ret; } - ret = 0; ret = i915_gem_object_lock_interruptible(obj, NULL); if (ret) diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c index f963b8e1e37b..cbd9b624a788 100644 --- a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c +++ b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c @@ -68,7 +68,7 @@ static int huge_get_pages(struct drm_i915_gem_object *obj) if (i915_gem_gtt_prepare_pages(obj, pages)) goto err; - __i915_gem_object_set_pages(obj, pages, PAGE_SIZE); + __i915_gem_object_set_pages(obj, pages); return 0; diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c index c570cf780079..beaf27e09e8a 100644 --- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c +++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c @@ -136,7 +136,7 @@ static int get_huge_pages(struct drm_i915_gem_object *obj) goto err; GEM_BUG_ON(sg_page_sizes != obj->mm.page_mask); - __i915_gem_object_set_pages(obj, st, sg_page_sizes); + __i915_gem_object_set_pages(obj, st); return 0; @@ -210,7 +210,6 @@ static int fake_get_huge_pages(struct drm_i915_gem_object *obj) const u64 max_len = rounddown_pow_of_two(UINT_MAX); struct sg_table *st; struct scatterlist *sg; - unsigned int sg_page_sizes; u64 rem; st = kmalloc(sizeof(*st), GFP); @@ -226,7 +225,6 @@ static int fake_get_huge_pages(struct drm_i915_gem_object *obj) rem = obj->base.size; sg = st->sgl; st->nents = 0; - sg_page_sizes = 0; do { unsigned int page_size = get_largest_page_size(i915, rem); unsigned int len = min(page_size * div_u64(rem, page_size), @@ -239,8 +237,6 @@ static int fake_get_huge_pages(struct drm_i915_gem_object *obj) sg_dma_len(sg) = len; sg_dma_address(sg) = page_size; - sg_page_sizes |= len; - st->nents++; rem -= len; @@ -254,7 +250,7 @@ static int fake_get_huge_pages(struct drm_i915_gem_object *obj) i915_sg_trim(st); - __i915_gem_object_set_pages(obj, st, sg_page_sizes); + __i915_gem_object_set_pages(obj, st); return 0; } @@ -286,7 +282,7 @@ static int fake_get_huge_pages_single(struct drm_i915_gem_object *obj) sg_dma_len(sg) = obj->base.size; sg_dma_address(sg) = page_size; - __i915_gem_object_set_pages(obj, st, sg->length); + __i915_gem_object_set_pages(obj, st); return 0; #undef GFP @@ -1161,7 +1157,8 @@ static int igt_write_huge(struct drm_i915_private *i915, GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj)); size = obj->base.size; - if (obj->mm.page_sizes.sg & I915_GTT_PAGE_SIZE_64K) + if (obj->mm.page_sizes.sg & I915_GTT_PAGE_SIZE_64K && + !HAS_64K_PAGES(i915)) size = round_up(size, I915_GTT_PAGE_SIZE_2M); n = 0; @@ -1214,6 +1211,10 @@ static int igt_write_huge(struct drm_i915_private *i915, * size and ensure the vma offset is at the start of the pt * boundary, however to improve coverage we opt for testing both * aligned and unaligned offsets. + * + * With PS64 this is no longer the case, but to ensure we + * sometimes get the compact layout for smaller objects, apply + * the round_up anyway. */ if (obj->mm.page_sizes.sg & I915_GTT_PAGE_SIZE_64K) offset_low = round_down(offset_low, @@ -1411,6 +1412,7 @@ static int igt_ppgtt_sanity_check(void *arg) { SZ_2M + SZ_4K, SZ_64K | SZ_4K }, { SZ_2M + SZ_4K, SZ_2M | SZ_4K }, { SZ_2M + SZ_64K, SZ_2M | SZ_64K }, + { SZ_2M + SZ_64K, SZ_64K }, }; int i, j; int err; @@ -1540,6 +1542,154 @@ out_put: return err; } +static int igt_ppgtt_mixed(void *arg) +{ + struct drm_i915_private *i915 = arg; + const unsigned long flags = PIN_OFFSET_FIXED | PIN_USER; + struct drm_i915_gem_object *obj, *on; + struct i915_gem_engines *engines; + struct i915_gem_engines_iter it; + struct i915_address_space *vm; + struct i915_gem_context *ctx; + struct intel_context *ce; + struct file *file; + I915_RND_STATE(prng); + LIST_HEAD(objects); + struct intel_memory_region *mr; + struct i915_vma *vma; + unsigned int count; + u32 i, addr; + int *order; + int n, err; + + /* + * Sanity check mixing 4K and 64K pages within the same page-table via + * the new PS64 TLB hint. + */ + + if (!HAS_64K_PAGES(i915)) { + pr_info("device lacks PS64, skipping\n"); + return 0; + } + + file = mock_file(i915); + if (IS_ERR(file)) + return PTR_ERR(file); + + ctx = hugepage_ctx(i915, file); + if (IS_ERR(ctx)) { + err = PTR_ERR(ctx); + goto out; + } + vm = i915_gem_context_get_eb_vm(ctx); + + i = 0; + addr = 0; + do { + u32 sz; + + sz = i915_prandom_u32_max_state(SZ_4M, &prng); + sz = max_t(u32, sz, SZ_4K); + + mr = i915->mm.regions[INTEL_REGION_LMEM_0]; + if (i & 1) + mr = i915->mm.regions[INTEL_REGION_SMEM]; + + obj = i915_gem_object_create_region(mr, sz, 0, 0); + if (IS_ERR(obj)) { + err = PTR_ERR(obj); + goto out_vm; + } + + list_add_tail(&obj->st_link, &objects); + + vma = i915_vma_instance(obj, vm, NULL); + if (IS_ERR(vma)) { + err = PTR_ERR(vma); + goto err_put; + } + + addr = round_up(addr, mr->min_page_size); + err = i915_vma_pin(vma, 0, 0, addr | flags); + if (err) + goto err_put; + + if (mr->type == INTEL_MEMORY_LOCAL && + (vma->resource->page_sizes_gtt & I915_GTT_PAGE_SIZE_4K)) { + err = -EINVAL; + goto err_put; + } + + addr += obj->base.size; + i++; + } while (addr <= SZ_16M); + + n = 0; + count = 0; + for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) { + count++; + if (!intel_engine_can_store_dword(ce->engine)) + continue; + + n++; + } + i915_gem_context_unlock_engines(ctx); + if (!n) + goto err_put; + + order = i915_random_order(count * count, &prng); + if (!order) { + err = -ENOMEM; + goto err_put; + } + + i = 0; + addr = 0; + engines = i915_gem_context_lock_engines(ctx); + list_for_each_entry(obj, &objects, st_link) { + u32 rnd = i915_prandom_u32_max_state(UINT_MAX, &prng); + + addr = round_up(addr, obj->mm.region->min_page_size); + + ce = engines->engines[order[i] % engines->num_engines]; + i = (i + 1) % (count * count); + if (!ce || !intel_engine_can_store_dword(ce->engine)) + continue; + + err = __igt_write_huge(ce, obj, obj->base.size, addr, 0, rnd); + if (err) + break; + + err = __igt_write_huge(ce, obj, obj->base.size, addr, + offset_in_page(rnd) / sizeof(u32), rnd + 1); + if (err) + break; + + err = __igt_write_huge(ce, obj, obj->base.size, addr, + (PAGE_SIZE / sizeof(u32)) - 1, + rnd + 2); + if (err) + break; + + addr += obj->base.size; + + cond_resched(); + } + + i915_gem_context_unlock_engines(ctx); + kfree(order); +err_put: + list_for_each_entry_safe(obj, on, &objects, st_link) { + list_del(&obj->st_link); + i915_gem_object_put(obj); + } +out_vm: + i915_vm_put(vm); +out: + fput(file); + return err; +} + static int igt_tmpfs_fallback(void *arg) { struct drm_i915_private *i915 = arg; @@ -1803,6 +1953,7 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *i915) SUBTEST(igt_ppgtt_smoke_huge), SUBTEST(igt_ppgtt_sanity_check), SUBTEST(igt_ppgtt_compact), + SUBTEST(igt_ppgtt_mixed), }; if (!HAS_PPGTT(i915)) { diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c index 9a6a6b5b722b..692a16914ca0 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c @@ -13,6 +13,7 @@ #include "gt/intel_gt_regs.h" #include "gem/i915_gem_lmem.h" +#include "gem/selftests/igt_gem_utils.h" #include "selftests/igt_flush_test.h" #include "selftests/mock_drm.h" #include "selftests/i915_random.h" @@ -457,21 +458,6 @@ static int verify_buffer(const struct tiled_blits *t, return ret; } -static int move_to_active(struct i915_vma *vma, - struct i915_request *rq, - unsigned int flags) -{ - int err; - - i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, false); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, flags); - i915_vma_unlock(vma); - - return err; -} - static int pin_buffer(struct i915_vma *vma, u64 addr) { int err; @@ -525,11 +511,11 @@ tiled_blit(struct tiled_blits *t, goto err_bb; } - err = move_to_active(t->batch, rq, 0); + err = igt_vma_move_to_active_unlocked(t->batch, rq, 0); if (!err) - err = move_to_active(src->vma, rq, 0); + err = igt_vma_move_to_active_unlocked(src->vma, rq, 0); if (!err) - err = move_to_active(dst->vma, rq, 0); + err = igt_vma_move_to_active_unlocked(dst->vma, rq, 0); if (!err) err = rq->engine->emit_bb_start(rq, t->batch->node.start, diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c index a666d7e610f5..c228fe4aba50 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c @@ -239,9 +239,7 @@ static int gpu_set(struct context *ctx, unsigned long offset, u32 v) } intel_ring_advance(rq, cs); - err = i915_request_await_object(rq, vma->obj, true); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); out_rq: i915_request_add(rq); diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c index c6ad67b90e8a..a0ff51d71d07 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c @@ -179,97 +179,108 @@ out_file: } struct parallel_switch { - struct task_struct *tsk; + struct kthread_worker *worker; + struct kthread_work work; struct intel_context *ce[2]; + int result; }; -static int __live_parallel_switch1(void *data) +static void __live_parallel_switch1(struct kthread_work *work) { - struct parallel_switch *arg = data; + struct parallel_switch *arg = + container_of(work, typeof(*arg), work); IGT_TIMEOUT(end_time); unsigned long count; count = 0; + arg->result = 0; do { struct i915_request *rq = NULL; - int err, n; + int n; - err = 0; - for (n = 0; !err && n < ARRAY_SIZE(arg->ce); n++) { + for (n = 0; !arg->result && n < ARRAY_SIZE(arg->ce); n++) { struct i915_request *prev = rq; rq = i915_request_create(arg->ce[n]); if (IS_ERR(rq)) { i915_request_put(prev); - return PTR_ERR(rq); + arg->result = PTR_ERR(rq); + break; } i915_request_get(rq); if (prev) { - err = i915_request_await_dma_fence(rq, &prev->fence); + arg->result = + i915_request_await_dma_fence(rq, + &prev->fence); i915_request_put(prev); } i915_request_add(rq); } + + if (IS_ERR_OR_NULL(rq)) + break; + if (i915_request_wait(rq, 0, HZ) < 0) - err = -ETIME; + arg->result = -ETIME; + i915_request_put(rq); - if (err) - return err; count++; - } while (!__igt_timeout(end_time, NULL)); + } while (!arg->result && !__igt_timeout(end_time, NULL)); - pr_info("%s: %lu switches (sync)\n", arg->ce[0]->engine->name, count); - return 0; + pr_info("%s: %lu switches (sync) <%d>\n", + arg->ce[0]->engine->name, count, arg->result); } -static int __live_parallel_switchN(void *data) +static void __live_parallel_switchN(struct kthread_work *work) { - struct parallel_switch *arg = data; + struct parallel_switch *arg = + container_of(work, typeof(*arg), work); struct i915_request *rq = NULL; IGT_TIMEOUT(end_time); unsigned long count; int n; count = 0; + arg->result = 0; do { - for (n = 0; n < ARRAY_SIZE(arg->ce); n++) { + for (n = 0; !arg->result && n < ARRAY_SIZE(arg->ce); n++) { struct i915_request *prev = rq; - int err = 0; rq = i915_request_create(arg->ce[n]); if (IS_ERR(rq)) { i915_request_put(prev); - return PTR_ERR(rq); + arg->result = PTR_ERR(rq); + break; } i915_request_get(rq); if (prev) { - err = i915_request_await_dma_fence(rq, &prev->fence); + arg->result = + i915_request_await_dma_fence(rq, + &prev->fence); i915_request_put(prev); } i915_request_add(rq); - if (err) { - i915_request_put(rq); - return err; - } } count++; - } while (!__igt_timeout(end_time, NULL)); - i915_request_put(rq); + } while (!arg->result && !__igt_timeout(end_time, NULL)); - pr_info("%s: %lu switches (many)\n", arg->ce[0]->engine->name, count); - return 0; + if (!IS_ERR_OR_NULL(rq)) + i915_request_put(rq); + + pr_info("%s: %lu switches (many) <%d>\n", + arg->ce[0]->engine->name, count, arg->result); } static int live_parallel_switch(void *arg) { struct drm_i915_private *i915 = arg; - static int (* const func[])(void *arg) = { + static void (* const func[])(struct kthread_work *) = { __live_parallel_switch1, __live_parallel_switchN, NULL, @@ -277,7 +288,7 @@ static int live_parallel_switch(void *arg) struct parallel_switch *data = NULL; struct i915_gem_engines *engines; struct i915_gem_engines_iter it; - int (* const *fn)(void *arg); + void (* const *fn)(struct kthread_work *); struct i915_gem_context *ctx; struct intel_context *ce; struct file *file; @@ -348,9 +359,22 @@ static int live_parallel_switch(void *arg) } } + for (n = 0; n < count; n++) { + struct kthread_worker *worker; + + if (!data[n].ce[0]) + continue; + + worker = kthread_create_worker(0, "igt/parallel:%s", + data[n].ce[0]->engine->name); + if (IS_ERR(worker)) + goto out; + + data[n].worker = worker; + } + for (fn = func; !err && *fn; fn++) { struct igt_live_test t; - int n; err = igt_live_test_begin(&t, i915, __func__, ""); if (err) @@ -360,30 +384,17 @@ static int live_parallel_switch(void *arg) if (!data[n].ce[0]) continue; - data[n].tsk = kthread_run(*fn, &data[n], - "igt/parallel:%s", - data[n].ce[0]->engine->name); - if (IS_ERR(data[n].tsk)) { - err = PTR_ERR(data[n].tsk); - break; - } - get_task_struct(data[n].tsk); + data[n].result = 0; + kthread_init_work(&data[n].work, *fn); + kthread_queue_work(data[n].worker, &data[n].work); } - yield(); /* start all threads before we kthread_stop() */ - for (n = 0; n < count; n++) { - int status; - - if (IS_ERR_OR_NULL(data[n].tsk)) - continue; - - status = kthread_stop(data[n].tsk); - if (status && !err) - err = status; - - put_task_struct(data[n].tsk); - data[n].tsk = NULL; + if (data[n].ce[0]) { + kthread_flush_work(&data[n].work); + if (data[n].result && !err) + err = data[n].result; + } } if (igt_live_test_end(&t)) @@ -399,6 +410,9 @@ out: intel_context_unpin(data[n].ce[m]); intel_context_put(data[n].ce[m]); } + + if (data[n].worker) + kthread_destroy_worker(data[n].worker); } kfree(data); out_file: @@ -970,15 +984,11 @@ retry: goto err_batch; } - err = i915_request_await_object(rq, batch->obj, false); - if (err == 0) - err = i915_vma_move_to_active(batch, rq, 0); + err = i915_vma_move_to_active(batch, rq, 0); if (err) goto skip_request; - err = i915_request_await_object(rq, vma->obj, true); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); if (err) goto skip_request; @@ -1539,9 +1549,7 @@ static int write_to_scratch(struct i915_gem_context *ctx, } i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, false); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, 0); + err = i915_vma_move_to_active(vma, rq, 0); i915_vma_unlock(vma); if (err) goto skip_request; @@ -1675,9 +1683,7 @@ static int read_from_scratch(struct i915_gem_context *ctx, } i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, true); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); i915_vma_unlock(vma); if (err) goto skip_request; diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c index 51ed824b020c..e57f9390076c 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c @@ -6,8 +6,12 @@ #include "i915_drv.h" #include "i915_selftest.h" +#include "gem/i915_gem_context.h" +#include "mock_context.h" #include "mock_dmabuf.h" +#include "igt_gem_utils.h" +#include "selftests/mock_drm.h" #include "selftests/mock_gem_device.h" static int igt_dmabuf_export(void *arg) @@ -140,6 +144,75 @@ out_ret: return err; } +static int verify_access(struct drm_i915_private *i915, + struct drm_i915_gem_object *native_obj, + struct drm_i915_gem_object *import_obj) +{ + struct i915_gem_engines_iter it; + struct i915_gem_context *ctx; + struct intel_context *ce; + struct i915_vma *vma; + struct file *file; + u32 *vaddr; + int err = 0, i; + + file = mock_file(i915); + if (IS_ERR(file)) + return PTR_ERR(file); + + ctx = live_context(i915, file); + if (IS_ERR(ctx)) { + err = PTR_ERR(ctx); + goto out_file; + } + + for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) { + if (intel_engine_can_store_dword(ce->engine)) + break; + } + i915_gem_context_unlock_engines(ctx); + if (!ce) + goto out_file; + + vma = i915_vma_instance(import_obj, ce->vm, NULL); + if (IS_ERR(vma)) { + err = PTR_ERR(vma); + goto out_file; + } + + err = i915_vma_pin(vma, 0, 0, PIN_USER); + if (err) + goto out_file; + + err = igt_gpu_fill_dw(ce, vma, 0, + vma->size >> PAGE_SHIFT, 0xdeadbeaf); + i915_vma_unpin(vma); + if (err) + goto out_file; + + err = i915_gem_object_wait(import_obj, 0, MAX_SCHEDULE_TIMEOUT); + if (err) + goto out_file; + + vaddr = i915_gem_object_pin_map_unlocked(native_obj, I915_MAP_WB); + if (IS_ERR(vaddr)) { + err = PTR_ERR(vaddr); + goto out_file; + } + + for (i = 0; i < native_obj->base.size / sizeof(u32); i += PAGE_SIZE / sizeof(u32)) { + if (vaddr[i] != 0xdeadbeaf) { + pr_err("Data mismatch [%d]=%u\n", i, vaddr[i]); + err = -EINVAL; + goto out_file; + } + } + +out_file: + fput(file); + return err; +} + static int igt_dmabuf_import_same_driver(struct drm_i915_private *i915, struct intel_memory_region **regions, unsigned int num_regions) @@ -154,7 +227,7 @@ static int igt_dmabuf_import_same_driver(struct drm_i915_private *i915, force_different_devices = true; - obj = __i915_gem_object_create_user(i915, PAGE_SIZE, + obj = __i915_gem_object_create_user(i915, SZ_8M, regions, num_regions); if (IS_ERR(obj)) { pr_err("__i915_gem_object_create_user failed with err=%ld\n", @@ -206,6 +279,10 @@ static int igt_dmabuf_import_same_driver(struct drm_i915_private *i915, i915_gem_object_unlock(import_obj); + err = verify_access(i915, obj, import_obj); + if (err) + goto out_import; + /* Now try a fake an importer */ import_attach = dma_buf_attach(dmabuf, obj->base.dev->dev); if (IS_ERR(import_attach)) { @@ -213,7 +290,7 @@ static int igt_dmabuf_import_same_driver(struct drm_i915_private *i915, goto out_import; } - st = dma_buf_map_attachment(import_attach, DMA_BIDIRECTIONAL); + st = dma_buf_map_attachment_unlocked(import_attach, DMA_BIDIRECTIONAL); if (IS_ERR(st)) { err = PTR_ERR(st); goto out_detach; @@ -226,7 +303,7 @@ static int igt_dmabuf_import_same_driver(struct drm_i915_private *i915, timeout = -ETIME; } err = timeout > 0 ? 0 : timeout; - dma_buf_unmap_attachment(import_attach, st, DMA_BIDIRECTIONAL); + dma_buf_unmap_attachment_unlocked(import_attach, st, DMA_BIDIRECTIONAL); out_detach: dma_buf_detach(dmabuf, import_attach); out_import: @@ -296,7 +373,7 @@ static int igt_dmabuf_import(void *arg) goto out_obj; } - err = dma_buf_vmap(dmabuf, &map); + err = dma_buf_vmap_unlocked(dmabuf, &map); dma_map = err ? NULL : map.vaddr; if (!dma_map) { pr_err("dma_buf_vmap failed\n"); @@ -337,7 +414,7 @@ static int igt_dmabuf_import(void *arg) err = 0; out_dma_map: - dma_buf_vunmap(dmabuf, &map); + dma_buf_vunmap_unlocked(dmabuf, &map); out_obj: i915_gem_object_put(obj); out_dmabuf: @@ -358,7 +435,7 @@ static int igt_dmabuf_import_ownership(void *arg) if (IS_ERR(dmabuf)) return PTR_ERR(dmabuf); - err = dma_buf_vmap(dmabuf, &map); + err = dma_buf_vmap_unlocked(dmabuf, &map); ptr = err ? NULL : map.vaddr; if (!ptr) { pr_err("dma_buf_vmap failed\n"); @@ -367,7 +444,7 @@ static int igt_dmabuf_import_ownership(void *arg) } memset(ptr, 0xc5, PAGE_SIZE); - dma_buf_vunmap(dmabuf, &map); + dma_buf_vunmap_unlocked(dmabuf, &map); obj = to_intel_bo(i915_gem_prime_import(&i915->drm, dmabuf)); if (IS_ERR(obj)) { @@ -418,7 +495,7 @@ static int igt_dmabuf_export_vmap(void *arg) } i915_gem_object_put(obj); - err = dma_buf_vmap(dmabuf, &map); + err = dma_buf_vmap_unlocked(dmabuf, &map); ptr = err ? NULL : map.vaddr; if (!ptr) { pr_err("dma_buf_vmap failed\n"); @@ -435,7 +512,7 @@ static int igt_dmabuf_export_vmap(void *arg) memset(ptr, 0xc5, dmabuf->size); err = 0; - dma_buf_vunmap(dmabuf, &map); + dma_buf_vunmap_unlocked(dmabuf, &map); out: dma_buf_put(dmabuf); return err; diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c index b73c91aa5450..3f658d5717d8 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c @@ -8,6 +8,7 @@ #include <linux/prime_numbers.h> #include "gem/i915_gem_internal.h" +#include "gem/i915_gem_lmem.h" #include "gem/i915_gem_region.h" #include "gem/i915_gem_ttm.h" #include "gem/i915_gem_ttm_move.h" @@ -16,6 +17,7 @@ #include "gt/intel_gt.h" #include "gt/intel_gt_pm.h" #include "gt/intel_migrate.h" +#include "i915_reg.h" #include "i915_ttm_buddy_manager.h" #include "huge_gem_object.h" @@ -564,10 +566,8 @@ retry: goto err_unpin; } - err = i915_request_await_object(rq, vma->obj, true); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, - EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(vma, rq, + EXEC_OBJECT_WRITE); i915_request_add(rq); err_unpin: @@ -1607,9 +1607,7 @@ retry: goto out_unpin; } - err = i915_request_await_object(rq, vma->obj, false); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, 0); + err = i915_vma_move_to_active(vma, rq, 0); err = engine->emit_bb_start(rq, vma->node.start, 0, 0); i915_request_get(rq); diff --git a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c index 3c55e77b0f1b..374b10ac430e 100644 --- a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c +++ b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c @@ -131,17 +131,13 @@ int igt_gpu_fill_dw(struct intel_context *ce, } i915_vma_lock(batch); - err = i915_request_await_object(rq, batch->obj, false); - if (err == 0) - err = i915_vma_move_to_active(batch, rq, 0); + err = i915_vma_move_to_active(batch, rq, 0); i915_vma_unlock(batch); if (err) goto skip_request; i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, true); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); i915_vma_unlock(vma); if (err) goto skip_request; diff --git a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.h b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.h index 4221cf84d175..1379fbc14431 100644 --- a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.h +++ b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.h @@ -9,6 +9,8 @@ #include <linux/types.h> +#include "i915_vma.h" + struct i915_request; struct i915_gem_context; struct i915_vma; @@ -29,4 +31,16 @@ int igt_gpu_fill_dw(struct intel_context *ce, struct i915_vma *vma, u64 offset, unsigned long count, u32 val); +static inline int __must_check +igt_vma_move_to_active_unlocked(struct i915_vma *vma, struct i915_request *rq, + unsigned int flags) +{ + int err; + + i915_vma_lock(vma); + err = _i915_vma_move_to_active(vma, rq, &rq->fence, flags); + i915_vma_unlock(vma); + return err; +} + #endif /* __IGT_GEM_UTILS_H__ */ diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index e49fa6fa6aee..e1c76e5bfa82 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -396,15 +396,17 @@ int gen8_emit_init_breadcrumb(struct i915_request *rq) return 0; } -static int __gen125_emit_bb_start(struct i915_request *rq, - u64 offset, u32 len, - const unsigned int flags, - u32 arb) +static int __xehp_emit_bb_start(struct i915_request *rq, + u64 offset, u32 len, + const unsigned int flags, + u32 arb) { struct intel_context *ce = rq->context; u32 wa_offset = lrc_indirect_bb(ce); u32 *cs; + GEM_BUG_ON(!ce->wa_bb_page); + cs = intel_ring_begin(rq, 12); if (IS_ERR(cs)) return PTR_ERR(cs); @@ -435,18 +437,18 @@ static int __gen125_emit_bb_start(struct i915_request *rq, return 0; } -int gen125_emit_bb_start_noarb(struct i915_request *rq, - u64 offset, u32 len, - const unsigned int flags) +int xehp_emit_bb_start_noarb(struct i915_request *rq, + u64 offset, u32 len, + const unsigned int flags) { - return __gen125_emit_bb_start(rq, offset, len, flags, MI_ARB_DISABLE); + return __xehp_emit_bb_start(rq, offset, len, flags, MI_ARB_DISABLE); } -int gen125_emit_bb_start(struct i915_request *rq, - u64 offset, u32 len, - const unsigned int flags) +int xehp_emit_bb_start(struct i915_request *rq, + u64 offset, u32 len, + const unsigned int flags) { - return __gen125_emit_bb_start(rq, offset, len, flags, MI_ARB_ENABLE); + return __xehp_emit_bb_start(rq, offset, len, flags, MI_ARB_ENABLE); } int gen8_emit_bb_start_noarb(struct i915_request *rq, @@ -583,6 +585,8 @@ u32 *gen8_emit_fini_breadcrumb_xcs(struct i915_request *rq, u32 *cs) u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs) { cs = gen8_emit_pipe_control(cs, + PIPE_CONTROL_CS_STALL | + PIPE_CONTROL_TLB_INVALIDATE | PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH | PIPE_CONTROL_DEPTH_CACHE_FLUSH | PIPE_CONTROL_DC_FLUSH_ENABLE, @@ -600,15 +604,21 @@ u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs) u32 *gen11_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs) { + cs = gen8_emit_pipe_control(cs, + PIPE_CONTROL_CS_STALL | + PIPE_CONTROL_TLB_INVALIDATE | + PIPE_CONTROL_TILE_CACHE_FLUSH | + PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH | + PIPE_CONTROL_DEPTH_CACHE_FLUSH | + PIPE_CONTROL_DC_FLUSH_ENABLE, + 0); + + /*XXX: Look at gen8_emit_fini_breadcrumb_rcs */ cs = gen8_emit_ggtt_write_rcs(cs, rq->fence.seqno, hwsp_offset(rq), - PIPE_CONTROL_CS_STALL | - PIPE_CONTROL_TILE_CACHE_FLUSH | - PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH | - PIPE_CONTROL_DEPTH_CACHE_FLUSH | - PIPE_CONTROL_DC_FLUSH_ENABLE | - PIPE_CONTROL_FLUSH_ENABLE); + PIPE_CONTROL_FLUSH_ENABLE | + PIPE_CONTROL_CS_STALL); return gen8_emit_fini_breadcrumb_tail(rq, cs); } @@ -715,6 +725,7 @@ u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs) { struct drm_i915_private *i915 = rq->engine->i915; u32 flags = (PIPE_CONTROL_CS_STALL | + PIPE_CONTROL_TLB_INVALIDATE | PIPE_CONTROL_TILE_CACHE_FLUSH | PIPE_CONTROL_FLUSH_L3 | PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH | @@ -731,11 +742,15 @@ u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs) else if (rq->engine->class == COMPUTE_CLASS) flags &= ~PIPE_CONTROL_3D_ENGINE_FLAGS; + cs = gen12_emit_pipe_control(cs, PIPE_CONTROL0_HDC_PIPELINE_FLUSH, flags, 0); + + /*XXX: Look at gen8_emit_fini_breadcrumb_rcs */ cs = gen12_emit_ggtt_write_rcs(cs, rq->fence.seqno, hwsp_offset(rq), - PIPE_CONTROL0_HDC_PIPELINE_FLUSH, - flags); + 0, + PIPE_CONTROL_FLUSH_ENABLE | + PIPE_CONTROL_CS_STALL); return gen12_emit_fini_breadcrumb_tail(rq, cs); } diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.h b/drivers/gpu/drm/i915/gt/gen8_engine_cs.h index e4d24c811dd6..655e5c00ddc2 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.h +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.h @@ -32,12 +32,12 @@ int gen8_emit_bb_start(struct i915_request *rq, u64 offset, u32 len, const unsigned int flags); -int gen125_emit_bb_start_noarb(struct i915_request *rq, - u64 offset, u32 len, - const unsigned int flags); -int gen125_emit_bb_start(struct i915_request *rq, - u64 offset, u32 len, - const unsigned int flags); +int xehp_emit_bb_start_noarb(struct i915_request *rq, + u64 offset, u32 len, + const unsigned int flags); +int xehp_emit_bb_start(struct i915_request *rq, + u64 offset, u32 len, + const unsigned int flags); u32 *gen8_emit_fini_breadcrumb_xcs(struct i915_request *rq, u32 *cs); u32 *gen12_emit_fini_breadcrumb_xcs(struct i915_request *rq, u32 *cs); diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c index 2128b7a72a25..4daaa6f55668 100644 --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c @@ -476,6 +476,7 @@ xehpsdv_ppgtt_insert_huge(struct i915_address_space *vm, const gen8_pte_t pte_encode = vm->pte_encode(0, cache_level, flags); unsigned int rem = sg_dma_len(iter->sg); u64 start = vma_res->start; + u64 end = start + vma_res->vma_size; GEM_BUG_ON(!i915_vm_is_4lvl(vm)); @@ -489,9 +490,10 @@ xehpsdv_ppgtt_insert_huge(struct i915_address_space *vm, gen8_pte_t encode = pte_encode; unsigned int page_size; gen8_pte_t *vaddr; - u16 index, max; + u16 index, max, nent, i; max = I915_PDES; + nent = 1; if (vma_res->bi.page_sizes.sg & I915_GTT_PAGE_SIZE_2M && IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_2M) && @@ -503,25 +505,37 @@ xehpsdv_ppgtt_insert_huge(struct i915_address_space *vm, vaddr = px_vaddr(pd); } else { - if (encode & GEN12_PPGTT_PTE_LM) { - GEM_BUG_ON(__gen8_pte_index(start, 0) % 16); - GEM_BUG_ON(rem < I915_GTT_PAGE_SIZE_64K); - GEM_BUG_ON(!IS_ALIGNED(iter->dma, - I915_GTT_PAGE_SIZE_64K)); - - index = __gen8_pte_index(start, 0) / 16; - page_size = I915_GTT_PAGE_SIZE_64K; - - max /= 16; - - vaddr = px_vaddr(pd); - vaddr[__gen8_pte_index(start, 1)] |= GEN12_PDE_64K; + index = __gen8_pte_index(start, 0); + page_size = I915_GTT_PAGE_SIZE; - pt->is_compact = true; - } else { - GEM_BUG_ON(pt->is_compact); - index = __gen8_pte_index(start, 0); - page_size = I915_GTT_PAGE_SIZE; + if (vma_res->bi.page_sizes.sg & I915_GTT_PAGE_SIZE_64K) { + /* + * Device local-memory on these platforms should + * always use 64K pages or larger (including GTT + * alignment), therefore if we know the whole + * page-table needs to be filled we can always + * safely use the compact-layout. Otherwise fall + * back to the TLB hint with PS64. If this is + * system memory we only bother with PS64. + */ + if ((encode & GEN12_PPGTT_PTE_LM) && + end - start >= SZ_2M && !index) { + index = __gen8_pte_index(start, 0) / 16; + page_size = I915_GTT_PAGE_SIZE_64K; + + max /= 16; + + vaddr = px_vaddr(pd); + vaddr[__gen8_pte_index(start, 1)] |= GEN12_PDE_64K; + + pt->is_compact = true; + } else if (IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_64K) && + rem >= I915_GTT_PAGE_SIZE_64K && + !(index % 16)) { + encode |= GEN12_PTE_PS64; + page_size = I915_GTT_PAGE_SIZE_64K; + nent = 16; + } } vaddr = px_vaddr(pt); @@ -529,7 +543,12 @@ xehpsdv_ppgtt_insert_huge(struct i915_address_space *vm, do { GEM_BUG_ON(rem < page_size); - vaddr[index++] = encode | iter->dma; + + for (i = 0; i < nent; i++) { + vaddr[index++] = + encode | (iter->dma + i * + I915_GTT_PAGE_SIZE); + } start += page_size; iter->dma += page_size; @@ -745,6 +764,8 @@ static void __xehpsdv_ppgtt_insert_entry_lm(struct i915_address_space *vm, GEM_BUG_ON(!IS_ALIGNED(addr, SZ_64K)); GEM_BUG_ON(!IS_ALIGNED(offset, SZ_64K)); + /* XXX: we don't strictly need to use this layout */ + if (!pt->is_compact) { vaddr = px_vaddr(pd); vaddr[gen8_pd_index(idx, 1)] |= GEN12_PDE_64K; @@ -929,29 +950,18 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt, */ ppgtt->vm.has_read_only = !IS_GRAPHICS_VER(gt->i915, 11, 12); - if (HAS_LMEM(gt->i915)) { + if (HAS_LMEM(gt->i915)) ppgtt->vm.alloc_pt_dma = alloc_pt_lmem; - - /* - * On some platforms the hw has dropped support for 4K GTT pages - * when dealing with LMEM, and due to the design of 64K GTT - * pages in the hw, we can only mark the *entire* page-table as - * operating in 64K GTT mode, since the enable bit is still on - * the pde, and not the pte. And since we still need to allow - * 4K GTT pages for SMEM objects, we can't have a "normal" 4K - * page-table with scratch pointing to LMEM, since that's - * undefined from the hw pov. The simplest solution is to just - * move the 64K scratch page to SMEM on such platforms and call - * it a day, since that should work for all configurations. - */ - if (HAS_64K_PAGES(gt->i915)) - ppgtt->vm.alloc_scratch_dma = alloc_pt_dma; - else - ppgtt->vm.alloc_scratch_dma = alloc_pt_lmem; - } else { + else ppgtt->vm.alloc_pt_dma = alloc_pt_dma; - ppgtt->vm.alloc_scratch_dma = alloc_pt_dma; - } + + /* + * Using SMEM here instead of LMEM has the advantage of not reserving + * high performance memory for a "never" used filler page. It also + * removes the device access that would be required to initialise the + * scratch page, reducing pressure on an even scarcer resource. + */ + ppgtt->vm.alloc_scratch_dma = alloc_pt_dma; ppgtt->vm.pte_encode = gen8_pte_encode; diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h index be09fb2e883a..fb62b7b8cbcd 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.h +++ b/drivers/gpu/drm/i915/gt/intel_context.h @@ -276,6 +276,14 @@ static inline bool intel_context_is_barrier(const struct intel_context *ce) return test_bit(CONTEXT_BARRIER_BIT, &ce->flags); } +static inline void intel_context_close(struct intel_context *ce) +{ + set_bit(CONTEXT_CLOSED_BIT, &ce->flags); + + if (ce->ops->close) + ce->ops->close(ce); +} + static inline bool intel_context_is_closed(const struct intel_context *ce) { return test_bit(CONTEXT_CLOSED_BIT, &ce->flags); diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index 04eacae1aca5..e36670f2e626 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -43,6 +43,8 @@ struct intel_context_ops { void (*revoke)(struct intel_context *ce, struct i915_request *rq, unsigned int preempt_timeout_ms); + void (*close)(struct intel_context *ce); + int (*pre_pin)(struct intel_context *ce, struct i915_gem_ww_ctx *ww, void **vaddr); int (*pin)(struct intel_context *ce, void *vaddr); void (*unpin)(struct intel_context *ce); @@ -197,8 +199,6 @@ struct intel_context { * context's submissions is complete. */ struct i915_sw_fence blocked; - /** @number_committed_requests: number of committed requests */ - int number_committed_requests; /** @requests: list of active requests on this context */ struct list_head requests; /** @prio: the context's current guc priority */ @@ -208,6 +208,11 @@ struct intel_context { * each priority bucket */ u32 prio_count[GUC_CLIENT_PRIORITY_NUM]; + /** + * @sched_disable_delay_work: worker to disable scheduling on this + * context + */ + struct delayed_work sched_disable_delay_work; } guc_state; struct { diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h index 04e435bce79b..cbc8b857d5f7 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine.h +++ b/drivers/gpu/drm/i915/gt/intel_engine.h @@ -348,4 +348,10 @@ intel_engine_get_hung_context(struct intel_engine_cs *engine) return engine->hung_ce; } +u64 intel_clamp_heartbeat_interval_ms(struct intel_engine_cs *engine, u64 value); +u64 intel_clamp_max_busywait_duration_ns(struct intel_engine_cs *engine, u64 value); +u64 intel_clamp_preempt_timeout_ms(struct intel_engine_cs *engine, u64 value); +u64 intel_clamp_stop_timeout_ms(struct intel_engine_cs *engine, u64 value); +u64 intel_clamp_timeslice_duration_ms(struct intel_engine_cs *engine, u64 value); + #endif /* _INTEL_RINGBUFFER_H_ */ diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 1f7188129cd1..c33e0d72d670 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -13,6 +13,8 @@ #include "i915_cmd_parser.h" #include "i915_drv.h" +#include "i915_irq.h" +#include "i915_reg.h" #include "intel_breadcrumbs.h" #include "intel_context.h" #include "intel_engine.h" @@ -244,6 +246,13 @@ static const struct engine_info intel_engines[] = { { .graphics_ver = 12, .base = GEN12_COMPUTE3_RING_BASE } } }, + [GSC0] = { + .class = OTHER_CLASS, + .instance = OTHER_GSC_INSTANCE, + .mmio_bases = { + { .graphics_ver = 12, .base = MTL_GSC_RING_BASE } + } + }, }; /** @@ -324,6 +333,7 @@ u32 intel_engine_context_size(struct intel_gt *gt, u8 class) case VIDEO_DECODE_CLASS: case VIDEO_ENHANCEMENT_CLASS: case COPY_ENGINE_CLASS: + case OTHER_CLASS: if (GRAPHICS_VER(gt->i915) < 8) return 0; return GEN8_LR_CONTEXT_OTHER_SIZE; @@ -415,6 +425,7 @@ static u32 get_reset_domain(u8 ver, enum intel_engine_id id) [CCS1] = GEN11_GRDOM_RENDER, [CCS2] = GEN11_GRDOM_RENDER, [CCS3] = GEN11_GRDOM_RENDER, + [GSC0] = GEN12_GRDOM_GSC, }; GEM_BUG_ON(id >= ARRAY_SIZE(engine_reset_domains) || !engine_reset_domains[id]); @@ -486,6 +497,17 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id, engine->logical_mask = BIT(logical_instance); __sprint_engine_name(engine); + if ((engine->class == COMPUTE_CLASS && !RCS_MASK(engine->gt) && + __ffs(CCS_MASK(engine->gt)) == engine->instance) || + engine->class == RENDER_CLASS) + engine->flags |= I915_ENGINE_FIRST_RENDER_COMPUTE; + + /* features common between engines sharing EUs */ + if (engine->class == RENDER_CLASS || engine->class == COMPUTE_CLASS) { + engine->flags |= I915_ENGINE_HAS_RCS_REG_STATE; + engine->flags |= I915_ENGINE_HAS_EU_PRIORITY; + } + engine->props.heartbeat_interval_ms = CONFIG_DRM_I915_HEARTBEAT_INTERVAL; engine->props.max_busywait_duration_ns = @@ -497,20 +519,34 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id, engine->props.timeslice_duration_ms = CONFIG_DRM_I915_TIMESLICE_DURATION; - /* Override to uninterruptible for OpenCL workloads. */ - if (GRAPHICS_VER(i915) == 12 && engine->class == RENDER_CLASS) - engine->props.preempt_timeout_ms = 0; - - if ((engine->class == COMPUTE_CLASS && !RCS_MASK(engine->gt) && - __ffs(CCS_MASK(engine->gt)) == engine->instance) || - engine->class == RENDER_CLASS) - engine->flags |= I915_ENGINE_FIRST_RENDER_COMPUTE; - - /* features common between engines sharing EUs */ - if (engine->class == RENDER_CLASS || engine->class == COMPUTE_CLASS) { - engine->flags |= I915_ENGINE_HAS_RCS_REG_STATE; - engine->flags |= I915_ENGINE_HAS_EU_PRIORITY; - } + /* + * Mid-thread pre-emption is not available in Gen12. Unfortunately, + * some compute workloads run quite long threads. That means they get + * reset due to not pre-empting in a timely manner. So, bump the + * pre-emption timeout value to be much higher for compute engines. + */ + if (GRAPHICS_VER(i915) == 12 && (engine->flags & I915_ENGINE_HAS_RCS_REG_STATE)) + engine->props.preempt_timeout_ms = CONFIG_DRM_I915_PREEMPT_TIMEOUT_COMPUTE; + + /* Cap properties according to any system limits */ +#define CLAMP_PROP(field) \ + do { \ + u64 clamp = intel_clamp_##field(engine, engine->props.field); \ + if (clamp != engine->props.field) { \ + drm_notice(&engine->i915->drm, \ + "Warning, clamping %s to %lld to prevent overflow\n", \ + #field, clamp); \ + engine->props.field = clamp; \ + } \ + } while (0) + + CLAMP_PROP(heartbeat_interval_ms); + CLAMP_PROP(max_busywait_duration_ns); + CLAMP_PROP(preempt_timeout_ms); + CLAMP_PROP(stop_timeout_ms); + CLAMP_PROP(timeslice_duration_ms); + +#undef CLAMP_PROP engine->defaults = engine->props; /* never to change again */ @@ -534,6 +570,55 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id, return 0; } +u64 intel_clamp_heartbeat_interval_ms(struct intel_engine_cs *engine, u64 value) +{ + value = min_t(u64, value, jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT)); + + return value; +} + +u64 intel_clamp_max_busywait_duration_ns(struct intel_engine_cs *engine, u64 value) +{ + value = min(value, jiffies_to_nsecs(2)); + + return value; +} + +u64 intel_clamp_preempt_timeout_ms(struct intel_engine_cs *engine, u64 value) +{ + /* + * NB: The GuC API only supports 32bit values. However, the limit is further + * reduced due to internal calculations which would otherwise overflow. + */ + if (intel_guc_submission_is_wanted(&engine->gt->uc.guc)) + value = min_t(u64, value, guc_policy_max_preempt_timeout_ms()); + + value = min_t(u64, value, jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT)); + + return value; +} + +u64 intel_clamp_stop_timeout_ms(struct intel_engine_cs *engine, u64 value) +{ + value = min_t(u64, value, jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT)); + + return value; +} + +u64 intel_clamp_timeslice_duration_ms(struct intel_engine_cs *engine, u64 value) +{ + /* + * NB: The GuC API only supports 32bit values. However, the limit is further + * reduced due to internal calculations which would otherwise overflow. + */ + if (intel_guc_submission_is_wanted(&engine->gt->uc.guc)) + value = min_t(u64, value, guc_policy_max_exec_quantum_ms()); + + value = min_t(u64, value, jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT)); + + return value; +} + static void __setup_engine_capabilities(struct intel_engine_cs *engine) { struct drm_i915_private *i915 = engine->i915; @@ -1274,8 +1359,13 @@ int intel_engines_init(struct intel_gt *gt) return err; err = setup(engine); - if (err) + if (err) { + intel_engine_cleanup_common(engine); return err; + } + + /* The backend should now be responsible for cleanup */ + GEM_BUG_ON(engine->release == NULL); err = engine_init_common(engine); if (err) @@ -1554,11 +1644,11 @@ void intel_engine_get_instdone(const struct intel_engine_cs *engine, for_each_ss_steering(iter, engine->gt, slice, subslice) { instdone->sampler[slice][subslice] = intel_gt_mcr_read(engine->gt, - GEN7_SAMPLER_INSTDONE, + GEN8_SAMPLER_INSTDONE, slice, subslice); instdone->row[slice][subslice] = intel_gt_mcr_read(engine->gt, - GEN7_ROW_INSTDONE, + GEN8_ROW_INSTDONE, slice, subslice); } diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c index a3698f611f45..9a527e1f5be6 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c @@ -22,9 +22,37 @@ static bool next_heartbeat(struct intel_engine_cs *engine) { + struct i915_request *rq; long delay; delay = READ_ONCE(engine->props.heartbeat_interval_ms); + + rq = engine->heartbeat.systole; + + /* + * FIXME: The final period extension is disabled if the period has been + * modified from the default. This is to prevent issues with certain + * selftests which override the value and expect specific behaviour. + * Once the selftests have been updated to either cope with variable + * heartbeat periods (or to override the pre-emption timeout as well, + * or just to add a selftest specific override of the extension), the + * generic override can be removed. + */ + if (rq && rq->sched.attr.priority >= I915_PRIORITY_BARRIER && + delay == engine->defaults.heartbeat_interval_ms) { + long longer; + + /* + * The final try is at the highest priority possible. Up until now + * a pre-emption might not even have been attempted. So make sure + * this last attempt allows enough time for a pre-emption to occur. + */ + longer = READ_ONCE(engine->props.preempt_timeout_ms) * 2; + longer = intel_clamp_heartbeat_interval_ms(engine, longer); + if (longer > delay) + delay = longer; + } + if (!delay) return false; @@ -288,6 +316,17 @@ int intel_engine_set_heartbeat(struct intel_engine_cs *engine, if (!delay && !intel_engine_has_preempt_reset(engine)) return -ENODEV; + /* FIXME: Remove together with equally marked hack in next_heartbeat. */ + if (delay != engine->defaults.heartbeat_interval_ms && + delay < 2 * engine->props.preempt_timeout_ms) { + if (intel_engine_uses_guc(engine)) + drm_notice(&engine->i915->drm, "%s heartbeat interval adjusted to a non-default value which may downgrade individual engine resets to full GPU resets!\n", + engine->name); + else + drm_notice(&engine->i915->drm, "%s heartbeat interval adjusted to a non-default value which may cause engine resets to target innocent contexts!\n", + engine->name); + } + intel_engine_pm_get(engine); err = mutex_lock_interruptible(&ce->timeline->mutex); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_regs.h b/drivers/gpu/drm/i915/gt/intel_engine_regs.h index fe1a0d5fd4b1..ee3efd06ee54 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_regs.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_regs.h @@ -201,6 +201,7 @@ #define RING_CONTEXT_STATUS_PTR(base) _MMIO((base) + 0x3a0) #define RING_CTX_TIMESTAMP(base) _MMIO((base) + 0x3a8) /* gen8+ */ #define RING_PREDICATE_RESULT(base) _MMIO((base) + 0x3b8) +#define MI_PREDICATE_RESULT_2_ENGINE(base) _MMIO((base) + 0x3bc) #define RING_FORCE_TO_NONPRIV(base, i) _MMIO(((base) + 0x4D0) + (i) * 4) #define RING_FORCE_TO_NONPRIV_DENY REG_BIT(30) #define RING_FORCE_TO_NONPRIV_ADDRESS_MASK REG_GENMASK(25, 2) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index 6b5d4ea22b67..4fd54fb8810f 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -136,6 +136,7 @@ enum intel_engine_id { CCS2, CCS3, #define _CCS(n) (CCS0 + (n)) + GSC0, I915_NUM_ENGINES #define INVALID_ENGINE ((enum intel_engine_id)-1) }; diff --git a/drivers/gpu/drm/i915/gt/intel_engine_user.c b/drivers/gpu/drm/i915/gt/intel_engine_user.c index 46a174f8aa00..cd4f1b126f75 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_user.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_user.c @@ -140,6 +140,7 @@ const char *intel_engine_class_repr(u8 class) [COPY_ENGINE_CLASS] = "bcs", [VIDEO_DECODE_CLASS] = "vcs", [VIDEO_ENHANCEMENT_CLASS] = "vecs", + [OTHER_CLASS] = "other", [COMPUTE_CLASS] = "ccs", }; @@ -190,6 +191,15 @@ static void add_legacy_ring(struct legacy_ring *ring, ring->instance++; } +static void engine_rename(struct intel_engine_cs *engine, const char *name, u16 instance) +{ + char old[sizeof(engine->name)]; + + memcpy(old, engine->name, sizeof(engine->name)); + scnprintf(engine->name, sizeof(engine->name), "%s%u", name, instance); + drm_dbg(&engine->i915->drm, "renamed %s to %s\n", old, engine->name); +} + void intel_engines_driver_register(struct drm_i915_private *i915) { struct legacy_ring ring = {}; @@ -205,11 +215,19 @@ void intel_engines_driver_register(struct drm_i915_private *i915) struct intel_engine_cs *engine = container_of((struct rb_node *)it, typeof(*engine), uabi_node); - char old[sizeof(engine->name)]; if (intel_gt_has_unrecoverable_error(engine->gt)) continue; /* ignore incomplete engines */ + /* + * We don't want to expose the GSC engine to the users, but we + * still rename it so it is easier to identify in the debug logs + */ + if (engine->id == GSC0) { + engine_rename(engine, "gsc", 0); + continue; + } + GEM_BUG_ON(engine->class >= ARRAY_SIZE(uabi_classes)); engine->uabi_class = uabi_classes[engine->class]; @@ -219,11 +237,9 @@ void intel_engines_driver_register(struct drm_i915_private *i915) i915->engine_uabi_class_count[engine->uabi_class]++; /* Replace the internal name with the final user facing name */ - memcpy(old, engine->name, sizeof(engine->name)); - scnprintf(engine->name, sizeof(engine->name), "%s%u", - intel_engine_class_repr(engine->class), - engine->uabi_instance); - DRM_DEBUG_DRIVER("renamed %s to %s\n", old, engine->name); + engine_rename(engine, + intel_engine_class_repr(engine->class), + engine->uabi_instance); rb_link_node(&engine->uabi_node, prev, p); rb_insert_color(&engine->uabi_node, &i915->uabi_engines); diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index c718e6dc40b5..2daffa7c7dfd 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -110,6 +110,7 @@ #include <linux/string_helpers.h> #include "i915_drv.h" +#include "i915_reg.h" #include "i915_trace.h" #include "i915_vgpu.h" #include "gen8_engine_cs.h" @@ -3471,9 +3472,9 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine) if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50)) { if (intel_engine_has_preemption(engine)) - engine->emit_bb_start = gen125_emit_bb_start; + engine->emit_bb_start = xehp_emit_bb_start; else - engine->emit_bb_start = gen125_emit_bb_start_noarb; + engine->emit_bb_start = xehp_emit_bb_start_noarb; } else { if (intel_engine_has_preemption(engine)) engine->emit_bb_start = gen8_emit_bb_start; @@ -3689,7 +3690,7 @@ static void virtual_engine_initial_hint(struct virtual_engine *ve) * NB This does not force us to execute on this engine, it will just * typically be the first we inspect for submission. */ - swp = prandom_u32_max(ve->num_siblings); + swp = get_random_u32_below(ve->num_siblings); if (swp) swap(ve->siblings[swp], ve->siblings[0]); } @@ -3921,6 +3922,7 @@ static struct intel_context * execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count, unsigned long flags) { + struct drm_i915_private *i915 = siblings[0]->i915; struct virtual_engine *ve; unsigned int n; int err; @@ -3929,7 +3931,7 @@ execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count, if (!ve) return ERR_PTR(-ENOMEM); - ve->base.i915 = siblings[0]->i915; + ve->base.i915 = i915; ve->base.gt = siblings[0]->gt; ve->base.uncore = siblings[0]->uncore; ve->base.id = -1; @@ -3988,8 +3990,9 @@ execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count, GEM_BUG_ON(!is_power_of_2(sibling->mask)); if (sibling->mask & ve->base.mask) { - DRM_DEBUG("duplicate %s entry in load balancer\n", - sibling->name); + drm_dbg(&i915->drm, + "duplicate %s entry in load balancer\n", + sibling->name); err = -EINVAL; goto err_put; } @@ -4023,8 +4026,9 @@ execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count, */ if (ve->base.class != OTHER_CLASS) { if (ve->base.class != sibling->class) { - DRM_DEBUG("invalid mixing of engine class, sibling %d, already %d\n", - sibling->class, ve->base.class); + drm_dbg(&i915->drm, + "invalid mixing of engine class, sibling %d, already %d\n", + sibling->class, ve->base.class); err = -EINVAL; goto err_put; } diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index 2049a00417af..8145851ad23d 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -560,7 +560,7 @@ static int init_ggtt(struct i915_ggtt *ggtt) * why. */ ggtt->pin_bias = max_t(u32, I915_GTT_PAGE_SIZE, - intel_wopcm_guc_size(&ggtt->vm.i915->wopcm)); + intel_wopcm_guc_size(&ggtt->vm.gt->wopcm)); ret = intel_vgt_balloon(ggtt); if (ret) @@ -871,8 +871,8 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size) u32 pte_flags; int ret; - GEM_WARN_ON(pci_resource_len(pdev, GTTMMADR_BAR) != gen6_gttmmadr_size(i915)); - phys_addr = pci_resource_start(pdev, GTTMMADR_BAR) + gen6_gttadr_offset(i915); + GEM_WARN_ON(pci_resource_len(pdev, GEN4_GTTMMADR_BAR) != gen6_gttmmadr_size(i915)); + phys_addr = pci_resource_start(pdev, GEN4_GTTMMADR_BAR) + gen6_gttadr_offset(i915); /* * On BXT+/ICL+ writes larger than 64 bit to the GTT pagetable range @@ -931,11 +931,11 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt) unsigned int size; u16 snb_gmch_ctl; - if (!HAS_LMEM(i915)) { - if (!i915_pci_resource_valid(pdev, GTT_APERTURE_BAR)) + if (!HAS_LMEM(i915) && !HAS_LMEMBAR_SMEM_STOLEN(i915)) { + if (!i915_pci_resource_valid(pdev, GEN4_GMADR_BAR)) return -ENXIO; - ggtt->gmadr = pci_resource(pdev, GTT_APERTURE_BAR); + ggtt->gmadr = pci_resource(pdev, GEN4_GMADR_BAR); ggtt->mappable_end = resource_size(&ggtt->gmadr); } @@ -986,7 +986,7 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt) ggtt->vm.pte_encode = gen8_ggtt_pte_encode; - setup_private_pat(ggtt->vm.gt->uncore); + setup_private_pat(ggtt->vm.gt); return ggtt_probe_common(ggtt, size); } @@ -1089,10 +1089,10 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt) unsigned int size; u16 snb_gmch_ctl; - if (!i915_pci_resource_valid(pdev, GTT_APERTURE_BAR)) + if (!i915_pci_resource_valid(pdev, GEN4_GMADR_BAR)) return -ENXIO; - ggtt->gmadr = pci_resource(pdev, GTT_APERTURE_BAR); + ggtt->gmadr = pci_resource(pdev, GEN4_GMADR_BAR); ggtt->mappable_end = resource_size(&ggtt->gmadr); /* @@ -1308,7 +1308,7 @@ void i915_ggtt_resume(struct i915_ggtt *ggtt) wbinvd_on_all_cpus(); if (GRAPHICS_VER(ggtt->vm.i915) >= 8) - setup_private_pat(ggtt->vm.gt->uncore); + setup_private_pat(ggtt->vm.gt); intel_ggtt_restore_fences(ggtt); } diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c index ea775e601686..995082d45cb2 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c @@ -816,8 +816,8 @@ i915_gem_object_save_bit_17_swizzle(struct drm_i915_gem_object *obj, if (obj->bit_17 == NULL) { obj->bit_17 = bitmap_zalloc(page_count, GFP_KERNEL); if (obj->bit_17 == NULL) { - DRM_ERROR("Failed to allocate memory for bit 17 " - "record\n"); + drm_err(&to_i915(obj->base.dev)->drm, + "Failed to allocate memory for bit 17 record\n"); return; } } diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h index d4e9702d3c8e..f50ea92910d9 100644 --- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h +++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h @@ -187,6 +187,10 @@ #define MI_BATCH_RESOURCE_STREAMER REG_BIT(10) #define MI_BATCH_PREDICATE REG_BIT(15) /* HSW+ on RCS only*/ +#define MI_OPCODE(x) (((x) >> 23) & 0x3f) +#define IS_MI_LRI_CMD(x) (MI_OPCODE(x) == MI_OPCODE(MI_INSTR(0x22, 0))) +#define MI_LRI_LEN(x) (((x) & 0xff) + 1) + /* * 3D instructions used by the kernel */ diff --git a/drivers/gpu/drm/i915/gt/intel_gsc.c b/drivers/gpu/drm/i915/gt/intel_gsc.c index 7af6db3194dd..976fdf27e790 100644 --- a/drivers/gpu/drm/i915/gt/intel_gsc.c +++ b/drivers/gpu/drm/i915/gt/intel_gsc.c @@ -7,6 +7,7 @@ #include <linux/mei_aux.h> #include "i915_drv.h" #include "i915_reg.h" +#include "gem/i915_gem_lmem.h" #include "gem/i915_gem_region.h" #include "gt/intel_gsc.h" #include "gt/intel_gt.h" @@ -142,8 +143,14 @@ static void gsc_destroy_one(struct drm_i915_private *i915, struct intel_gsc_intf *intf = &gsc->intf[intf_id]; if (intf->adev) { - auxiliary_device_delete(&intf->adev->aux_dev); - auxiliary_device_uninit(&intf->adev->aux_dev); + struct auxiliary_device *aux_dev = &intf->adev->aux_dev; + + if (intf_id == 0) + intel_huc_unregister_gsc_notifier(&gsc_to_gt(gsc)->uc.huc, + aux_dev->dev.bus); + + auxiliary_device_delete(aux_dev); + auxiliary_device_uninit(aux_dev); intf->adev = NULL; } @@ -242,14 +249,24 @@ add_device: goto fail; } + intf->adev = adev; /* needed by the notifier */ + + if (intf_id == 0) + intel_huc_register_gsc_notifier(&gsc_to_gt(gsc)->uc.huc, + aux_dev->dev.bus); + ret = auxiliary_device_add(aux_dev); if (ret < 0) { drm_err(&i915->drm, "gsc aux add failed %d\n", ret); + if (intf_id == 0) + intel_huc_unregister_gsc_notifier(&gsc_to_gt(gsc)->uc.huc, + aux_dev->dev.bus); + intf->adev = NULL; + /* adev will be freed with the put_device() and .release sequence */ auxiliary_device_uninit(aux_dev); goto fail; } - intf->adev = adev; return; fail: diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index 7caa3412a244..9c18b5f2e789 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -12,6 +12,7 @@ #include "i915_drv.h" #include "i915_perf_oa_regs.h" +#include "i915_reg.h" #include "intel_context.h" #include "intel_engine_pm.h" #include "intel_engine_regs.h" @@ -40,8 +41,6 @@ void intel_gt_common_init_early(struct intel_gt *gt) { spin_lock_init(gt->irq_lock); - INIT_LIST_HEAD(>->lmem_userfault_list); - mutex_init(>->lmem_userfault_lock); INIT_LIST_HEAD(>->closed_vma); spin_lock_init(>->closed_lock); @@ -56,6 +55,7 @@ void intel_gt_common_init_early(struct intel_gt *gt) seqcount_mutex_init(>->tlb.seqno, >->tlb.invalidate_lock); intel_gt_pm_init_early(gt); + intel_wopcm_init_early(>->wopcm); intel_uc_init_early(>->uc); intel_rps_init_early(>->rps); } @@ -192,7 +192,7 @@ int intel_gt_init_hw(struct intel_gt *gt) ret = i915_ppgtt_init_hw(gt); if (ret) { - DRM_ERROR("Enabling PPGTT failed (%d)\n", ret); + drm_err(&i915->drm, "Enabling PPGTT failed (%d)\n", ret); goto out; } @@ -231,6 +231,16 @@ static void gen6_clear_engine_error_register(struct intel_engine_cs *engine) GEN6_RING_FAULT_REG_POSTING_READ(engine); } +i915_reg_t intel_gt_perf_limit_reasons_reg(struct intel_gt *gt) +{ + /* GT0_PERF_LIMIT_REASONS is available only for Gen11+ */ + if (GRAPHICS_VER(gt->i915) < 11) + return INVALID_MMIO_REG; + + return gt->type == GT_MEDIA ? + MTL_MEDIA_PERF_LIMIT_REASONS : GT0_PERF_LIMIT_REASONS; +} + void intel_gt_clear_error_registers(struct intel_gt *gt, intel_engine_mask_t engine_mask) @@ -254,13 +264,17 @@ intel_gt_clear_error_registers(struct intel_gt *gt, * some errors might have become stuck, * mask them. */ - DRM_DEBUG_DRIVER("EIR stuck: 0x%08x, masking\n", eir); + drm_dbg(>->i915->drm, "EIR stuck: 0x%08x, masking\n", eir); rmw_set(uncore, EMR, eir); intel_uncore_write(uncore, GEN2_IIR, I915_MASTER_ERROR_INTERRUPT); } - if (GRAPHICS_VER(i915) >= 12) { + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) { + intel_gt_mcr_multicast_rmw(gt, XEHP_RING_FAULT_REG, + RING_FAULT_VALID, 0); + intel_gt_mcr_read_any(gt, XEHP_RING_FAULT_REG); + } else if (GRAPHICS_VER(i915) >= 12) { rmw_clear(uncore, GEN12_RING_FAULT_REG, RING_FAULT_VALID); intel_uncore_posting_read(uncore, GEN12_RING_FAULT_REG); } else if (GRAPHICS_VER(i915) >= 8) { @@ -298,6 +312,42 @@ static void gen6_check_faults(struct intel_gt *gt) } } +static void xehp_check_faults(struct intel_gt *gt) +{ + u32 fault; + + /* + * Although the fault register now lives in an MCR register range, + * the GAM registers are special and we only truly need to read + * the "primary" GAM instance rather than handling each instance + * individually. intel_gt_mcr_read_any() will automatically steer + * toward the primary instance. + */ + fault = intel_gt_mcr_read_any(gt, XEHP_RING_FAULT_REG); + if (fault & RING_FAULT_VALID) { + u32 fault_data0, fault_data1; + u64 fault_addr; + + fault_data0 = intel_gt_mcr_read_any(gt, XEHP_FAULT_TLB_DATA0); + fault_data1 = intel_gt_mcr_read_any(gt, XEHP_FAULT_TLB_DATA1); + + fault_addr = ((u64)(fault_data1 & FAULT_VA_HIGH_BITS) << 44) | + ((u64)fault_data0 << 12); + + drm_dbg(>->i915->drm, "Unexpected fault\n" + "\tAddr: 0x%08x_%08x\n" + "\tAddress space: %s\n" + "\tEngine ID: %d\n" + "\tSource ID: %d\n" + "\tType: %d\n", + upper_32_bits(fault_addr), lower_32_bits(fault_addr), + fault_data1 & FAULT_GTT_SEL ? "GGTT" : "PPGTT", + GEN8_RING_FAULT_ENGINE_ID(fault), + RING_FAULT_SRCID(fault), + RING_FAULT_FAULT_TYPE(fault)); + } +} + static void gen8_check_faults(struct intel_gt *gt) { struct intel_uncore *uncore = gt->uncore; @@ -344,7 +394,9 @@ void intel_gt_check_and_clear_faults(struct intel_gt *gt) struct drm_i915_private *i915 = gt->i915; /* From GEN8 onwards we only have one 'All Engine Fault Register' */ - if (GRAPHICS_VER(i915) >= 8) + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) + xehp_check_faults(gt); + else if (GRAPHICS_VER(i915) >= 8) gen8_check_faults(gt); else if (GRAPHICS_VER(i915) >= 6) gen6_check_faults(gt); @@ -812,7 +864,6 @@ static int intel_gt_tile_setup(struct intel_gt *gt, phys_addr_t phys_addr) } intel_uncore_init_early(gt->uncore, gt); - intel_wakeref_auto_init(>->userfault_wakeref, gt->uncore->rpm); ret = intel_uncore_setup_mmio(gt->uncore, phys_addr); if (ret) @@ -833,7 +884,7 @@ int intel_gt_probe_all(struct drm_i915_private *i915) unsigned int i; int ret; - mmio_bar = GRAPHICS_VER(i915) == 2 ? GEN2_GTTMMADR_BAR : GTTMMADR_BAR; + mmio_bar = intel_mmio_bar(GRAPHICS_VER(i915)); phys_addr = pci_resource_start(pdev, mmio_bar); /* @@ -944,7 +995,10 @@ void intel_gt_info_print(const struct intel_gt_info *info, } struct reg_and_bit { - i915_reg_t reg; + union { + i915_reg_t reg; + i915_mcr_reg_t mcr_reg; + }; u32 bit; }; @@ -970,6 +1024,32 @@ get_reg_and_bit(const struct intel_engine_cs *engine, const bool gen8, return rb; } +/* + * HW architecture suggest typical invalidation time at 40us, + * with pessimistic cases up to 100us and a recommendation to + * cap at 1ms. We go a bit higher just in case. + */ +#define TLB_INVAL_TIMEOUT_US 100 +#define TLB_INVAL_TIMEOUT_MS 4 + +/* + * On Xe_HP the TLB invalidation registers are located at the same MMIO offsets + * but are now considered MCR registers. Since they exist within a GAM range, + * the primary instance of the register rolls up the status from each unit. + */ +static int wait_for_invalidate(struct intel_gt *gt, struct reg_and_bit rb) +{ + if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 50)) + return intel_gt_mcr_wait_for_reg(gt, rb.mcr_reg, rb.bit, 0, + TLB_INVAL_TIMEOUT_US, + TLB_INVAL_TIMEOUT_MS); + else + return __intel_wait_for_register_fw(gt->uncore, rb.reg, rb.bit, 0, + TLB_INVAL_TIMEOUT_US, + TLB_INVAL_TIMEOUT_MS, + NULL); +} + static void mmio_invalidate_full(struct intel_gt *gt) { static const i915_reg_t gen8_regs[] = { @@ -985,6 +1065,13 @@ static void mmio_invalidate_full(struct intel_gt *gt) [COPY_ENGINE_CLASS] = GEN12_BLT_TLB_INV_CR, [COMPUTE_CLASS] = GEN12_COMPCTX_TLB_INV_CR, }; + static const i915_mcr_reg_t xehp_regs[] = { + [RENDER_CLASS] = XEHP_GFX_TLB_INV_CR, + [VIDEO_DECODE_CLASS] = XEHP_VD_TLB_INV_CR, + [VIDEO_ENHANCEMENT_CLASS] = XEHP_VE_TLB_INV_CR, + [COPY_ENGINE_CLASS] = XEHP_BLT_TLB_INV_CR, + [COMPUTE_CLASS] = XEHP_COMPCTX_TLB_INV_CR, + }; struct drm_i915_private *i915 = gt->i915; struct intel_uncore *uncore = gt->uncore; struct intel_engine_cs *engine; @@ -993,7 +1080,10 @@ static void mmio_invalidate_full(struct intel_gt *gt) const i915_reg_t *regs; unsigned int num = 0; - if (GRAPHICS_VER(i915) == 12) { + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) { + regs = NULL; + num = ARRAY_SIZE(xehp_regs); + } else if (GRAPHICS_VER(i915) == 12) { regs = gen12_regs; num = ARRAY_SIZE(gen12_regs); } else if (GRAPHICS_VER(i915) >= 8 && GRAPHICS_VER(i915) <= 11) { @@ -1018,16 +1108,28 @@ static void mmio_invalidate_full(struct intel_gt *gt) if (!intel_engine_pm_is_awake(engine)) continue; - rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num); - if (!i915_mmio_reg_offset(rb.reg)) - continue; - - if (GRAPHICS_VER(i915) == 12 && (engine->class == VIDEO_DECODE_CLASS || - engine->class == VIDEO_ENHANCEMENT_CLASS || - engine->class == COMPUTE_CLASS)) - rb.bit = _MASKED_BIT_ENABLE(rb.bit); - - intel_uncore_write_fw(uncore, rb.reg, rb.bit); + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) { + u32 val = BIT(engine->instance); + + if (engine->class == VIDEO_DECODE_CLASS || + engine->class == VIDEO_ENHANCEMENT_CLASS || + engine->class == COMPUTE_CLASS) + val = _MASKED_BIT_ENABLE(val); + intel_gt_mcr_multicast_write_fw(gt, + xehp_regs[engine->class], + val); + } else { + rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num); + if (!i915_mmio_reg_offset(rb.reg)) + continue; + + if (GRAPHICS_VER(i915) == 12 && (engine->class == VIDEO_DECODE_CLASS || + engine->class == VIDEO_ENHANCEMENT_CLASS || + engine->class == COMPUTE_CLASS)) + rb.bit = _MASKED_BIT_ENABLE(rb.bit); + + intel_uncore_write_fw(uncore, rb.reg, rb.bit); + } awake |= engine->mask; } @@ -1047,22 +1149,17 @@ static void mmio_invalidate_full(struct intel_gt *gt) for_each_engine_masked(engine, gt, awake, tmp) { struct reg_and_bit rb; - /* - * HW architecture suggest typical invalidation time at 40us, - * with pessimistic cases up to 100us and a recommendation to - * cap at 1ms. We go a bit higher just in case. - */ - const unsigned int timeout_us = 100; - const unsigned int timeout_ms = 4; - - rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num); - if (__intel_wait_for_register_fw(uncore, - rb.reg, rb.bit, 0, - timeout_us, timeout_ms, - NULL)) + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) { + rb.mcr_reg = xehp_regs[engine->class]; + rb.bit = BIT(engine->instance); + } else { + rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num); + } + + if (wait_for_invalidate(gt, rb)) drm_err_ratelimited(>->i915->drm, "%s TLB invalidation did not complete in %ums!\n", - engine->name, timeout_ms); + engine->name, TLB_INVAL_TIMEOUT_MS); } /* diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h index 2ee582e287c8..e0365d556248 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.h +++ b/drivers/gpu/drm/i915/gt/intel_gt.h @@ -60,6 +60,7 @@ void intel_gt_driver_late_release_all(struct drm_i915_private *i915); int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout); void intel_gt_check_and_clear_faults(struct intel_gt *gt); +i915_reg_t intel_gt_perf_limit_reasons_reg(struct intel_gt *gt); void intel_gt_clear_error_registers(struct intel_gt *gt, intel_engine_mask_t engine_mask); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c index 3f656d3dba9a..2a6a4ca7fdad 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c @@ -107,7 +107,7 @@ static u32 gen9_read_clock_frequency(struct intel_uncore *uncore) return freq; } -static u32 gen5_read_clock_frequency(struct intel_uncore *uncore) +static u32 gen6_read_clock_frequency(struct intel_uncore *uncore) { /* * PRMs say: @@ -119,7 +119,27 @@ static u32 gen5_read_clock_frequency(struct intel_uncore *uncore) return 12500000; } -static u32 gen2_read_clock_frequency(struct intel_uncore *uncore) +static u32 gen5_read_clock_frequency(struct intel_uncore *uncore) +{ + /* + * 63:32 increments every 1000 ns + * 31:0 mbz + */ + return 1000000000 / 1000; +} + +static u32 g4x_read_clock_frequency(struct intel_uncore *uncore) +{ + /* + * 63:20 increments every 1/4 ns + * 19:0 mbz + * + * -> 63:32 increments every 1024 ns + */ + return 1000000000 / 1024; +} + +static u32 gen4_read_clock_frequency(struct intel_uncore *uncore) { /* * PRMs say: @@ -127,8 +147,10 @@ static u32 gen2_read_clock_frequency(struct intel_uncore *uncore) * "The value in this register increments once every 16 * hclks." (through the “Clocking Configuration” * (“CLKCFG”) MCHBAR register) + * + * Testing on actual hardware has shown there is no /16. */ - return RUNTIME_INFO(uncore->i915)->rawclk_freq * 1000 / 16; + return RUNTIME_INFO(uncore->i915)->rawclk_freq * 1000; } static u32 read_clock_frequency(struct intel_uncore *uncore) @@ -137,10 +159,16 @@ static u32 read_clock_frequency(struct intel_uncore *uncore) return gen11_read_clock_frequency(uncore); else if (GRAPHICS_VER(uncore->i915) >= 9) return gen9_read_clock_frequency(uncore); - else if (GRAPHICS_VER(uncore->i915) >= 5) + else if (GRAPHICS_VER(uncore->i915) >= 6) + return gen6_read_clock_frequency(uncore); + else if (GRAPHICS_VER(uncore->i915) == 5) return gen5_read_clock_frequency(uncore); + else if (IS_G4X(uncore->i915)) + return g4x_read_clock_frequency(uncore); + else if (GRAPHICS_VER(uncore->i915) == 4) + return gen4_read_clock_frequency(uncore); else - return gen2_read_clock_frequency(uncore); + return 0; } void intel_gt_init_clock_frequency(struct intel_gt *gt) diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c index f26882fdc24c..6f6b9e04d916 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c @@ -17,6 +17,9 @@ static void guc_irq_handler(struct intel_guc *guc, u16 iir) { + if (unlikely(!guc->interrupts.enabled)) + return; + if (iir & GUC_INTR_GUC2HOST) intel_guc_to_host_event_handler(guc); } @@ -44,8 +47,9 @@ gen11_gt_engine_identity(struct intel_gt *gt, !time_after32(local_clock() >> 10, timeout_ts)); if (unlikely(!(ident & GEN11_INTR_DATA_VALID))) { - DRM_ERROR("INTR_IDENTITY_REG%u:%u 0x%08x not valid!\n", - bank, bit, ident); + drm_err(>->i915->drm, + "INTR_IDENTITY_REG%u:%u 0x%08x not valid!\n", + bank, bit, ident); return 0; } @@ -81,35 +85,27 @@ gen11_other_irq_handler(struct intel_gt *gt, const u8 instance, instance, iir); } -static void -gen11_engine_irq_handler(struct intel_gt *gt, const u8 class, - const u8 instance, const u16 iir) +static struct intel_gt *pick_gt(struct intel_gt *gt, u8 class, u8 instance) { - struct intel_engine_cs *engine; - - /* - * Platforms with standalone media have their media engines in another - * GT. - */ - if (MEDIA_VER(gt->i915) >= 13 && - (class == VIDEO_DECODE_CLASS || class == VIDEO_ENHANCEMENT_CLASS)) { - if (!gt->i915->media_gt) - goto err; + struct intel_gt *media_gt = gt->i915->media_gt; - gt = gt->i915->media_gt; + /* we expect the non-media gt to be passed in */ + GEM_BUG_ON(gt == media_gt); + + if (!media_gt) + return gt; + + switch (class) { + case VIDEO_DECODE_CLASS: + case VIDEO_ENHANCEMENT_CLASS: + return media_gt; + case OTHER_CLASS: + if (instance == OTHER_GSC_INSTANCE && HAS_ENGINE(media_gt, GSC0)) + return media_gt; + fallthrough; + default: + return gt; } - - if (instance <= MAX_ENGINE_INSTANCE) - engine = gt->engine_class[class][instance]; - else - engine = NULL; - - if (likely(engine)) - return intel_engine_cs_irq(engine, iir); - -err: - WARN_ONCE(1, "unhandled engine interrupt class=0x%x, instance=0x%x\n", - class, instance); } static void @@ -122,8 +118,17 @@ gen11_gt_identity_handler(struct intel_gt *gt, const u32 identity) if (unlikely(!intr)) return; - if (class <= COPY_ENGINE_CLASS || class == COMPUTE_CLASS) - return gen11_engine_irq_handler(gt, class, instance, intr); + /* + * Platforms with standalone media have the media and GSC engines in + * another GT. + */ + gt = pick_gt(gt, class, instance); + + if (class <= MAX_ENGINE_CLASS && instance <= MAX_ENGINE_INSTANCE) { + struct intel_engine_cs *engine = gt->engine_class[class][instance]; + if (engine) + return intel_engine_cs_irq(engine, intr); + } if (class == OTHER_CLASS) return gen11_other_irq_handler(gt, instance, intr); @@ -206,7 +211,7 @@ void gen11_gt_irq_reset(struct intel_gt *gt) intel_uncore_write(uncore, GEN11_VCS_VECS_INTR_ENABLE, 0); if (CCS_MASK(gt)) intel_uncore_write(uncore, GEN12_CCS_RSVD_INTR_ENABLE, 0); - if (HAS_HECI_GSC(gt->i915)) + if (HAS_HECI_GSC(gt->i915) || HAS_ENGINE(gt, GSC0)) intel_uncore_write(uncore, GEN11_GUNIT_CSME_INTR_ENABLE, 0); /* Restore masks irqs on RCS, BCS, VCS and VECS engines. */ @@ -233,7 +238,7 @@ void gen11_gt_irq_reset(struct intel_gt *gt) intel_uncore_write(uncore, GEN12_CCS0_CCS1_INTR_MASK, ~0); if (HAS_ENGINE(gt, CCS2) || HAS_ENGINE(gt, CCS3)) intel_uncore_write(uncore, GEN12_CCS2_CCS3_INTR_MASK, ~0); - if (HAS_HECI_GSC(gt->i915)) + if (HAS_HECI_GSC(gt->i915) || HAS_ENGINE(gt, GSC0)) intel_uncore_write(uncore, GEN11_GUNIT_CSME_INTR_MASK, ~0); intel_uncore_write(uncore, GEN11_GPM_WGBOXPERF_INTR_ENABLE, 0); @@ -249,7 +254,8 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt) { struct intel_uncore *uncore = gt->uncore; u32 irqs = GT_RENDER_USER_INTERRUPT; - const u32 gsc_mask = GSC_IRQ_INTF(0) | GSC_IRQ_INTF(1); + u32 guc_mask = intel_uc_wants_guc(>->uc) ? GUC_INTR_GUC2HOST : 0; + u32 gsc_mask = 0; u32 dmask; u32 smask; @@ -261,6 +267,11 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt) dmask = irqs << 16 | irqs; smask = irqs << 16; + if (HAS_ENGINE(gt, GSC0)) + gsc_mask = irqs; + else if (HAS_HECI_GSC(gt->i915)) + gsc_mask = GSC_IRQ_INTF(0) | GSC_IRQ_INTF(1); + BUILD_BUG_ON(irqs & 0xffff0000); /* Enable RCS, BCS, VCS and VECS class interrupts. */ @@ -268,9 +279,8 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt) intel_uncore_write(uncore, GEN11_VCS_VECS_INTR_ENABLE, dmask); if (CCS_MASK(gt)) intel_uncore_write(uncore, GEN12_CCS_RSVD_INTR_ENABLE, smask); - if (HAS_HECI_GSC(gt->i915)) - intel_uncore_write(uncore, GEN11_GUNIT_CSME_INTR_ENABLE, - gsc_mask); + if (gsc_mask) + intel_uncore_write(uncore, GEN11_GUNIT_CSME_INTR_ENABLE, gsc_mask); /* Unmask irqs on RCS, BCS, VCS and VECS engines. */ intel_uncore_write(uncore, GEN11_RCS0_RSVD_INTR_MASK, ~smask); @@ -296,9 +306,22 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt) intel_uncore_write(uncore, GEN12_CCS0_CCS1_INTR_MASK, ~dmask); if (HAS_ENGINE(gt, CCS2) || HAS_ENGINE(gt, CCS3)) intel_uncore_write(uncore, GEN12_CCS2_CCS3_INTR_MASK, ~dmask); - if (HAS_HECI_GSC(gt->i915)) + if (gsc_mask) intel_uncore_write(uncore, GEN11_GUNIT_CSME_INTR_MASK, ~gsc_mask); + if (guc_mask) { + /* the enable bit is common for both GTs but the masks are separate */ + u32 mask = gt->type == GT_MEDIA ? + REG_FIELD_PREP(ENGINE0_MASK, guc_mask) : + REG_FIELD_PREP(ENGINE1_MASK, guc_mask); + + intel_uncore_write(uncore, GEN11_GUC_SG_INTR_ENABLE, + REG_FIELD_PREP(ENGINE1_MASK, guc_mask)); + + /* we might not be the first GT to write this reg */ + intel_uncore_rmw(uncore, MTL_GUC_MGUC_INTR_MASK, mask, 0); + } + /* * RPS interrupts will get enabled/disabled on demand when RPS itself * is enabled/disabled. @@ -307,10 +330,6 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt) gt->pm_imr = ~gt->pm_ier; intel_uncore_write(uncore, GEN11_GPM_WGBOXPERF_INTR_ENABLE, 0); intel_uncore_write(uncore, GEN11_GPM_WGBOXPERF_INTR_MASK, ~0); - - /* Same thing for GuC interrupts */ - intel_uncore_write(uncore, GEN11_GUC_SG_INTR_ENABLE, 0); - intel_uncore_write(uncore, GEN11_GUC_SG_INTR_MASK, ~0); } void gen5_gt_irq_handler(struct intel_gt *gt, u32 gt_iir) @@ -359,7 +378,8 @@ void gen6_gt_irq_handler(struct intel_gt *gt, u32 gt_iir) if (gt_iir & (GT_BLT_CS_ERROR_INTERRUPT | GT_BSD_CS_ERROR_INTERRUPT | GT_CS_MASTER_ERROR_INTERRUPT)) - DRM_DEBUG("Command parser error, gt_iir 0x%08x\n", gt_iir); + drm_dbg(>->i915->drm, "Command parser error, gt_iir 0x%08x\n", + gt_iir); if (gt_iir & GT_PARITY_ERROR(gt->i915)) gen7_parity_error_irq_handler(gt, gt_iir); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c index e79405a45312..ea86c1ab5dc5 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c @@ -40,6 +40,9 @@ static const char * const intel_steering_types[] = { "L3BANK", "MSLICE", "LNCF", + "GAM", + "DSS", + "OADDRM", "INSTANCE 0", }; @@ -48,14 +51,23 @@ static const struct intel_mmio_range icl_l3bank_steering_table[] = { {}, }; +/* + * Although the bspec lists more "MSLICE" ranges than shown here, some of those + * are of a "GAM" subclass that has special rules. Thus we use a separate + * GAM table farther down for those. + */ static const struct intel_mmio_range xehpsdv_mslice_steering_table[] = { - { 0x004000, 0x004AFF }, - { 0x00C800, 0x00CFFF }, { 0x00DD00, 0x00DDFF }, { 0x00E900, 0x00FFFF }, /* 0xEA00 - OxEFFF is unused */ {}, }; +static const struct intel_mmio_range xehpsdv_gam_steering_table[] = { + { 0x004000, 0x004AFF }, + { 0x00C800, 0x00CFFF }, + {}, +}; + static const struct intel_mmio_range xehpsdv_lncf_steering_table[] = { { 0x00B000, 0x00B0FF }, { 0x00D800, 0x00D8FF }, @@ -89,9 +101,47 @@ static const struct intel_mmio_range pvc_instance0_steering_table[] = { {}, }; +static const struct intel_mmio_range xelpg_instance0_steering_table[] = { + { 0x000B00, 0x000BFF }, /* SQIDI */ + { 0x001000, 0x001FFF }, /* SQIDI */ + { 0x004000, 0x0048FF }, /* GAM */ + { 0x008700, 0x0087FF }, /* SQIDI */ + { 0x00B000, 0x00B0FF }, /* NODE */ + { 0x00C800, 0x00CFFF }, /* GAM */ + { 0x00D880, 0x00D8FF }, /* NODE */ + { 0x00DD00, 0x00DDFF }, /* OAAL2 */ + {}, +}; + +static const struct intel_mmio_range xelpg_l3bank_steering_table[] = { + { 0x00B100, 0x00B3FF }, + {}, +}; + +/* DSS steering is used for SLICE ranges as well */ +static const struct intel_mmio_range xelpg_dss_steering_table[] = { + { 0x005200, 0x0052FF }, /* SLICE */ + { 0x005500, 0x007FFF }, /* SLICE */ + { 0x008140, 0x00815F }, /* SLICE (0x8140-0x814F), DSS (0x8150-0x815F) */ + { 0x0094D0, 0x00955F }, /* SLICE (0x94D0-0x951F), DSS (0x9520-0x955F) */ + { 0x009680, 0x0096FF }, /* DSS */ + { 0x00D800, 0x00D87F }, /* SLICE */ + { 0x00DC00, 0x00DCFF }, /* SLICE */ + { 0x00DE80, 0x00E8FF }, /* DSS (0xE000-0xE0FF reserved) */ + {}, +}; + +static const struct intel_mmio_range xelpmp_oaddrm_steering_table[] = { + { 0x393200, 0x39323F }, + { 0x393400, 0x3934FF }, + {}, +}; + void intel_gt_mcr_init(struct intel_gt *gt) { struct drm_i915_private *i915 = gt->i915; + unsigned long fuse; + int i; /* * An mslice is unavailable only if both the meml3 for the slice is @@ -109,14 +159,36 @@ void intel_gt_mcr_init(struct intel_gt *gt) drm_warn(&i915->drm, "mslice mask all zero!\n"); } - if (IS_PONTEVECCHIO(i915)) { + if (MEDIA_VER(i915) >= 13 && gt->type == GT_MEDIA) { + gt->steering_table[OADDRM] = xelpmp_oaddrm_steering_table; + } else if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) { + fuse = REG_FIELD_GET(GT_L3_EXC_MASK, + intel_uncore_read(gt->uncore, XEHP_FUSE4)); + + /* + * Despite the register field being named "exclude mask" the + * bits actually represent enabled banks (two banks per bit). + */ + for_each_set_bit(i, &fuse, 3) + gt->info.l3bank_mask |= 0x3 << 2 * i; + + gt->steering_table[INSTANCE0] = xelpg_instance0_steering_table; + gt->steering_table[L3BANK] = xelpg_l3bank_steering_table; + gt->steering_table[DSS] = xelpg_dss_steering_table; + } else if (IS_PONTEVECCHIO(i915)) { gt->steering_table[INSTANCE0] = pvc_instance0_steering_table; } else if (IS_DG2(i915)) { gt->steering_table[MSLICE] = xehpsdv_mslice_steering_table; gt->steering_table[LNCF] = dg2_lncf_steering_table; + /* + * No need to hook up the GAM table since it has a dedicated + * steering control register on DG2 and can use implicit + * steering. + */ } else if (IS_XEHPSDV(i915)) { gt->steering_table[MSLICE] = xehpsdv_mslice_steering_table; gt->steering_table[LNCF] = xehpsdv_lncf_steering_table; + gt->steering_table[GAM] = xehpsdv_gam_steering_table; } else if (GRAPHICS_VER(i915) >= 11 && GRAPHICS_VER_FULL(i915) < IP_VER(12, 50)) { gt->steering_table[L3BANK] = icl_l3bank_steering_table; @@ -135,6 +207,19 @@ void intel_gt_mcr_init(struct intel_gt *gt) } /* + * Although the rest of the driver should use MCR-specific functions to + * read/write MCR registers, we still use the regular intel_uncore_* functions + * internally to implement those, so we need a way for the functions in this + * file to "cast" an i915_mcr_reg_t into an i915_reg_t. + */ +static i915_reg_t mcr_reg_cast(const i915_mcr_reg_t mcr) +{ + i915_reg_t r = { .reg = mcr.reg }; + + return r; +} + +/* * rw_with_mcr_steering_fw - Access a register with specific MCR steering * @uncore: pointer to struct intel_uncore * @reg: register being accessed @@ -148,14 +233,26 @@ void intel_gt_mcr_init(struct intel_gt *gt) * Caller needs to make sure the relevant forcewake wells are up. */ static u32 rw_with_mcr_steering_fw(struct intel_uncore *uncore, - i915_reg_t reg, u8 rw_flag, + i915_mcr_reg_t reg, u8 rw_flag, int group, int instance, u32 value) { u32 mcr_mask, mcr_ss, mcr, old_mcr, val = 0; lockdep_assert_held(&uncore->lock); - if (GRAPHICS_VER(uncore->i915) >= 11) { + if (GRAPHICS_VER_FULL(uncore->i915) >= IP_VER(12, 70)) { + /* + * Always leave the hardware in multicast mode when doing reads + * (see comment about Wa_22013088509 below) and only change it + * to unicast mode when doing writes of a specific instance. + * + * No need to save old steering reg value. + */ + intel_uncore_write_fw(uncore, MTL_MCR_SELECTOR, + REG_FIELD_PREP(MTL_MCR_GROUPID, group) | + REG_FIELD_PREP(MTL_MCR_INSTANCEID, instance) | + (rw_flag == FW_REG_READ ? GEN11_MCR_MULTICAST : 0)); + } else if (GRAPHICS_VER(uncore->i915) >= 11) { mcr_mask = GEN11_MCR_SLICE_MASK | GEN11_MCR_SUBSLICE_MASK; mcr_ss = GEN11_MCR_SLICE(group) | GEN11_MCR_SUBSLICE(instance); @@ -173,39 +270,53 @@ static u32 rw_with_mcr_steering_fw(struct intel_uncore *uncore, */ if (rw_flag == FW_REG_WRITE) mcr_mask |= GEN11_MCR_MULTICAST; + + mcr = intel_uncore_read_fw(uncore, GEN8_MCR_SELECTOR); + old_mcr = mcr; + + mcr &= ~mcr_mask; + mcr |= mcr_ss; + intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr); } else { mcr_mask = GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK; mcr_ss = GEN8_MCR_SLICE(group) | GEN8_MCR_SUBSLICE(instance); - } - old_mcr = mcr = intel_uncore_read_fw(uncore, GEN8_MCR_SELECTOR); + mcr = intel_uncore_read_fw(uncore, GEN8_MCR_SELECTOR); + old_mcr = mcr; - mcr &= ~mcr_mask; - mcr |= mcr_ss; - intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr); + mcr &= ~mcr_mask; + mcr |= mcr_ss; + intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr); + } if (rw_flag == FW_REG_READ) - val = intel_uncore_read_fw(uncore, reg); + val = intel_uncore_read_fw(uncore, mcr_reg_cast(reg)); else - intel_uncore_write_fw(uncore, reg, value); - - mcr &= ~mcr_mask; - mcr |= old_mcr & mcr_mask; + intel_uncore_write_fw(uncore, mcr_reg_cast(reg), value); - intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr); + /* + * For pre-MTL platforms, we need to restore the old value of the + * steering control register to ensure that implicit steering continues + * to behave as expected. For MTL and beyond, we need only reinstate + * the 'multicast' bit (and only if we did a write that cleared it). + */ + if (GRAPHICS_VER_FULL(uncore->i915) >= IP_VER(12, 70) && rw_flag == FW_REG_WRITE) + intel_uncore_write_fw(uncore, MTL_MCR_SELECTOR, GEN11_MCR_MULTICAST); + else if (GRAPHICS_VER_FULL(uncore->i915) < IP_VER(12, 70)) + intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, old_mcr); return val; } static u32 rw_with_mcr_steering(struct intel_uncore *uncore, - i915_reg_t reg, u8 rw_flag, + i915_mcr_reg_t reg, u8 rw_flag, int group, int instance, u32 value) { enum forcewake_domains fw_domains; u32 val; - fw_domains = intel_uncore_forcewake_for_reg(uncore, reg, + fw_domains = intel_uncore_forcewake_for_reg(uncore, mcr_reg_cast(reg), rw_flag); fw_domains |= intel_uncore_forcewake_for_reg(uncore, GEN8_MCR_SELECTOR, @@ -233,7 +344,7 @@ static u32 rw_with_mcr_steering(struct intel_uncore *uncore, * group/instance. */ u32 intel_gt_mcr_read(struct intel_gt *gt, - i915_reg_t reg, + i915_mcr_reg_t reg, int group, int instance) { return rw_with_mcr_steering(gt->uncore, reg, FW_REG_READ, group, instance, 0); @@ -250,7 +361,7 @@ u32 intel_gt_mcr_read(struct intel_gt *gt, * Write an MCR register in unicast mode after steering toward a specific * group/instance. */ -void intel_gt_mcr_unicast_write(struct intel_gt *gt, i915_reg_t reg, u32 value, +void intel_gt_mcr_unicast_write(struct intel_gt *gt, i915_mcr_reg_t reg, u32 value, int group, int instance) { rw_with_mcr_steering(gt->uncore, reg, FW_REG_WRITE, group, instance, value); @@ -265,9 +376,16 @@ void intel_gt_mcr_unicast_write(struct intel_gt *gt, i915_reg_t reg, u32 value, * Write an MCR register in multicast mode to update all instances. */ void intel_gt_mcr_multicast_write(struct intel_gt *gt, - i915_reg_t reg, u32 value) + i915_mcr_reg_t reg, u32 value) { - intel_uncore_write(gt->uncore, reg, value); + /* + * Ensure we have multicast behavior, just in case some non-i915 agent + * left the hardware in unicast mode. + */ + if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 70)) + intel_uncore_write_fw(gt->uncore, MTL_MCR_SELECTOR, GEN11_MCR_MULTICAST); + + intel_uncore_write(gt->uncore, mcr_reg_cast(reg), value); } /** @@ -281,9 +399,44 @@ void intel_gt_mcr_multicast_write(struct intel_gt *gt, * domains; use intel_gt_mcr_multicast_write() in cases where forcewake should * be obtained automatically. */ -void intel_gt_mcr_multicast_write_fw(struct intel_gt *gt, i915_reg_t reg, u32 value) +void intel_gt_mcr_multicast_write_fw(struct intel_gt *gt, i915_mcr_reg_t reg, u32 value) { - intel_uncore_write_fw(gt->uncore, reg, value); + /* + * Ensure we have multicast behavior, just in case some non-i915 agent + * left the hardware in unicast mode. + */ + if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 70)) + intel_uncore_write_fw(gt->uncore, MTL_MCR_SELECTOR, GEN11_MCR_MULTICAST); + + intel_uncore_write_fw(gt->uncore, mcr_reg_cast(reg), value); +} + +/** + * intel_gt_mcr_multicast_rmw - Performs a multicast RMW operations + * @gt: GT structure + * @reg: the MCR register to read and write + * @clear: bits to clear during RMW + * @set: bits to set during RMW + * + * Performs a read-modify-write on an MCR register in a multicast manner. + * This operation only makes sense on MCR registers where all instances are + * expected to have the same value. The read will target any non-terminated + * instance and the write will be applied to all instances. + * + * This function assumes the caller is already holding any necessary forcewake + * domains; use intel_gt_mcr_multicast_rmw() in cases where forcewake should + * be obtained automatically. + * + * Returns the old (unmodified) value read. + */ +u32 intel_gt_mcr_multicast_rmw(struct intel_gt *gt, i915_mcr_reg_t reg, + u32 clear, u32 set) +{ + u32 val = intel_gt_mcr_read_any(gt, reg); + + intel_gt_mcr_multicast_write(gt, reg, (val & ~clear) | set); + + return val; } /* @@ -301,7 +454,7 @@ void intel_gt_mcr_multicast_write_fw(struct intel_gt *gt, i915_reg_t reg, u32 va * for @type steering too. */ static bool reg_needs_read_steering(struct intel_gt *gt, - i915_reg_t reg, + i915_mcr_reg_t reg, enum intel_steering_type type) { const u32 offset = i915_mmio_reg_offset(reg); @@ -332,6 +485,8 @@ static void get_nonterminated_steering(struct intel_gt *gt, enum intel_steering_type type, u8 *group, u8 *instance) { + u32 dss; + switch (type) { case L3BANK: *group = 0; /* unused */ @@ -351,6 +506,15 @@ static void get_nonterminated_steering(struct intel_gt *gt, *group = __ffs(gt->info.mslice_mask) << 1; *instance = 0; /* unused */ break; + case GAM: + *group = IS_DG2(gt->i915) ? 1 : 0; + *instance = 0; + break; + case DSS: + dss = intel_sseu_find_first_xehp_dss(>->info.sseu, 0, 0); + *group = dss / GEN_DSS_PER_GSLICE; + *instance = dss % GEN_DSS_PER_GSLICE; + break; case INSTANCE0: /* * There are a lot of MCR types for which instance (0, 0) @@ -359,6 +523,13 @@ static void get_nonterminated_steering(struct intel_gt *gt, *group = 0; *instance = 0; break; + case OADDRM: + if ((VDBOX_MASK(gt) | VEBOX_MASK(gt) | gt->info.sfc_mask) & BIT(0)) + *group = 0; + else + *group = 1; + *instance = 0; + break; default: MISSING_CASE(type); *group = 0; @@ -380,7 +551,7 @@ static void get_nonterminated_steering(struct intel_gt *gt, * steering. */ void intel_gt_mcr_get_nonterminated_steering(struct intel_gt *gt, - i915_reg_t reg, + i915_mcr_reg_t reg, u8 *group, u8 *instance) { int type; @@ -409,7 +580,7 @@ void intel_gt_mcr_get_nonterminated_steering(struct intel_gt *gt, * * Returns the value from a non-terminated instance of @reg. */ -u32 intel_gt_mcr_read_any_fw(struct intel_gt *gt, i915_reg_t reg) +u32 intel_gt_mcr_read_any_fw(struct intel_gt *gt, i915_mcr_reg_t reg) { int type; u8 group, instance; @@ -423,7 +594,7 @@ u32 intel_gt_mcr_read_any_fw(struct intel_gt *gt, i915_reg_t reg) } } - return intel_uncore_read_fw(gt->uncore, reg); + return intel_uncore_read_fw(gt->uncore, mcr_reg_cast(reg)); } /** @@ -436,7 +607,7 @@ u32 intel_gt_mcr_read_any_fw(struct intel_gt *gt, i915_reg_t reg) * * Returns the value from a non-terminated instance of @reg. */ -u32 intel_gt_mcr_read_any(struct intel_gt *gt, i915_reg_t reg) +u32 intel_gt_mcr_read_any(struct intel_gt *gt, i915_mcr_reg_t reg) { int type; u8 group, instance; @@ -450,7 +621,7 @@ u32 intel_gt_mcr_read_any(struct intel_gt *gt, i915_reg_t reg) } } - return intel_uncore_read(gt->uncore, reg); + return intel_uncore_read(gt->uncore, mcr_reg_cast(reg)); } static void report_steering_type(struct drm_printer *p, @@ -483,11 +654,20 @@ static void report_steering_type(struct drm_printer *p, void intel_gt_mcr_report_steering(struct drm_printer *p, struct intel_gt *gt, bool dump_table) { - drm_printf(p, "Default steering: group=0x%x, instance=0x%x\n", - gt->default_steering.groupid, - gt->default_steering.instanceid); - - if (IS_PONTEVECCHIO(gt->i915)) { + /* + * Starting with MTL we no longer have default steering; + * all ranges are explicitly steered. + */ + if (GRAPHICS_VER_FULL(gt->i915) < IP_VER(12, 70)) + drm_printf(p, "Default steering: group=0x%x, instance=0x%x\n", + gt->default_steering.groupid, + gt->default_steering.instanceid); + + if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 70)) { + for (int i = 0; i < NUM_STEERING_TYPES; i++) + if (gt->steering_table[i]) + report_steering_type(p, gt, i, dump_table); + } else if (IS_PONTEVECCHIO(gt->i915)) { report_steering_type(p, gt, INSTANCE0, dump_table); } else if (HAS_MSLICE_STEERING(gt->i915)) { report_steering_type(p, gt, MSLICE, dump_table); @@ -520,3 +700,60 @@ void intel_gt_mcr_get_ss_steering(struct intel_gt *gt, unsigned int dss, return; } } + +/** + * intel_gt_mcr_wait_for_reg - wait until MCR register matches expected state + * @gt: GT structure + * @reg: the register to read + * @mask: mask to apply to register value + * @value: value to wait for + * @fast_timeout_us: fast timeout in microsecond for atomic/tight wait + * @slow_timeout_ms: slow timeout in millisecond + * + * This routine waits until the target register @reg contains the expected + * @value after applying the @mask, i.e. it waits until :: + * + * (intel_gt_mcr_read_any_fw(gt, reg) & mask) == value + * + * Otherwise, the wait will timeout after @slow_timeout_ms milliseconds. + * For atomic context @slow_timeout_ms must be zero and @fast_timeout_us + * must be not larger than 20,0000 microseconds. + * + * This function is basically an MCR-friendly version of + * __intel_wait_for_register_fw(). Generally this function will only be used + * on GAM registers which are a bit special --- although they're MCR registers, + * reads (e.g., waiting for status updates) are always directed to the primary + * instance. + * + * Note that this routine assumes the caller holds forcewake asserted, it is + * not suitable for very long waits. + * + * Return: 0 if the register matches the desired condition, or -ETIMEDOUT. + */ +int intel_gt_mcr_wait_for_reg(struct intel_gt *gt, + i915_mcr_reg_t reg, + u32 mask, + u32 value, + unsigned int fast_timeout_us, + unsigned int slow_timeout_ms) +{ + int ret; + + lockdep_assert_not_held(>->uncore->lock); + +#define done ((intel_gt_mcr_read_any(gt, reg) & mask) == value) + + /* Catch any overuse of this function */ + might_sleep_if(slow_timeout_ms); + GEM_BUG_ON(fast_timeout_us > 20000); + GEM_BUG_ON(!fast_timeout_us && !slow_timeout_ms); + + ret = -ETIMEDOUT; + if (fast_timeout_us && fast_timeout_us <= 20000) + ret = _wait_for_atomic(done, fast_timeout_us, 0); + if (ret && slow_timeout_ms) + ret = wait_for(done, slow_timeout_ms); + + return ret; +#undef done +} diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.h b/drivers/gpu/drm/i915/gt/intel_gt_mcr.h index 77a8b11c287d..ae93b20e1c17 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_mcr.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_mcr.h @@ -11,21 +11,24 @@ void intel_gt_mcr_init(struct intel_gt *gt); u32 intel_gt_mcr_read(struct intel_gt *gt, - i915_reg_t reg, + i915_mcr_reg_t reg, int group, int instance); -u32 intel_gt_mcr_read_any_fw(struct intel_gt *gt, i915_reg_t reg); -u32 intel_gt_mcr_read_any(struct intel_gt *gt, i915_reg_t reg); +u32 intel_gt_mcr_read_any_fw(struct intel_gt *gt, i915_mcr_reg_t reg); +u32 intel_gt_mcr_read_any(struct intel_gt *gt, i915_mcr_reg_t reg); void intel_gt_mcr_unicast_write(struct intel_gt *gt, - i915_reg_t reg, u32 value, + i915_mcr_reg_t reg, u32 value, int group, int instance); void intel_gt_mcr_multicast_write(struct intel_gt *gt, - i915_reg_t reg, u32 value); + i915_mcr_reg_t reg, u32 value); void intel_gt_mcr_multicast_write_fw(struct intel_gt *gt, - i915_reg_t reg, u32 value); + i915_mcr_reg_t reg, u32 value); + +u32 intel_gt_mcr_multicast_rmw(struct intel_gt *gt, i915_mcr_reg_t reg, + u32 clear, u32 set); void intel_gt_mcr_get_nonterminated_steering(struct intel_gt *gt, - i915_reg_t reg, + i915_mcr_reg_t reg, u8 *group, u8 *instance); void intel_gt_mcr_report_steering(struct drm_printer *p, struct intel_gt *gt, @@ -34,6 +37,13 @@ void intel_gt_mcr_report_steering(struct drm_printer *p, struct intel_gt *gt, void intel_gt_mcr_get_ss_steering(struct intel_gt *gt, unsigned int dss, unsigned int *group, unsigned int *instance); +int intel_gt_mcr_wait_for_reg(struct intel_gt *gt, + i915_mcr_reg_t reg, + u32 mask, + u32 value, + unsigned int fast_timeout_us, + unsigned int slow_timeout_ms); + /* * Helper for for_each_ss_steering loop. On pre-Xe_HP platforms, subslice * presence is determined by using the group/instance as direct lookups in the diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c index f553e2173bda..16db85fab0b1 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c @@ -7,6 +7,7 @@ #include <linux/suspend.h> #include "i915_drv.h" +#include "i915_irq.h" #include "i915_params.h" #include "intel_context.h" #include "intel_engine_pm.h" @@ -19,10 +20,31 @@ #include "intel_rc6.h" #include "intel_rps.h" #include "intel_wakeref.h" +#include "intel_pcode.h" #include "pxp/intel_pxp_pm.h" #define I915_GT_SUSPEND_IDLE_TIMEOUT (HZ / 2) +static void mtl_media_busy(struct intel_gt *gt) +{ + /* Wa_14017073508: mtl */ + if (IS_MTL_GRAPHICS_STEP(gt->i915, P, STEP_A0, STEP_B0) && + gt->type == GT_MEDIA) + snb_pcode_write_p(gt->uncore, PCODE_MBOX_GT_STATE, + PCODE_MBOX_GT_STATE_MEDIA_BUSY, + PCODE_MBOX_GT_STATE_DOMAIN_MEDIA, 0); +} + +static void mtl_media_idle(struct intel_gt *gt) +{ + /* Wa_14017073508: mtl */ + if (IS_MTL_GRAPHICS_STEP(gt->i915, P, STEP_A0, STEP_B0) && + gt->type == GT_MEDIA) + snb_pcode_write_p(gt->uncore, PCODE_MBOX_GT_STATE, + PCODE_MBOX_GT_STATE_MEDIA_NOT_BUSY, + PCODE_MBOX_GT_STATE_DOMAIN_MEDIA, 0); +} + static void user_forcewake(struct intel_gt *gt, bool suspend) { int count = atomic_read(>->user_wakeref); @@ -70,6 +92,9 @@ static int __gt_unpark(struct intel_wakeref *wf) GT_TRACE(gt, "\n"); + /* Wa_14017073508: mtl */ + mtl_media_busy(gt); + /* * It seems that the DMC likes to transition between the DC states a lot * when there are no connected displays (no active power domains) during @@ -119,6 +144,9 @@ static int __gt_park(struct intel_wakeref *wf) GEM_BUG_ON(!wakeref); intel_display_power_put_async(i915, POWER_DOMAIN_GT_IRQ, wakeref); + /* Wa_14017073508: mtl */ + mtl_media_idle(gt); + return 0; } diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c b/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c index 108b9e76c32e..83df4cd5e06c 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c @@ -83,19 +83,6 @@ static int fw_domains_show(struct seq_file *m, void *data) } DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(fw_domains); -static void print_rc6_res(struct seq_file *m, - const char *title, - const i915_reg_t reg) -{ - struct intel_gt *gt = m->private; - intel_wakeref_t wakeref; - - with_intel_runtime_pm(gt->uncore->rpm, wakeref) - seq_printf(m, "%s %u (%llu us)\n", title, - intel_uncore_read(gt->uncore, reg), - intel_rc6_residency_us(>->rc6, reg)); -} - static int vlv_drpc(struct seq_file *m) { struct intel_gt *gt = m->private; @@ -115,8 +102,8 @@ static int vlv_drpc(struct seq_file *m) seq_printf(m, "Media Power Well: %s\n", (pw_status & VLV_GTLC_PW_MEDIA_STATUS_MASK) ? "Up" : "Down"); - print_rc6_res(m, "Render RC6 residency since boot:", GEN6_GT_GFX_RC6); - print_rc6_res(m, "Media RC6 residency since boot:", VLV_GT_MEDIA_RC6); + intel_rc6_print_residency(m, "Render RC6 residency since boot:", INTEL_RC6_RES_RC6); + intel_rc6_print_residency(m, "Media RC6 residency since boot:", INTEL_RC6_RES_VLV_MEDIA); return fw_domains_show(m, NULL); } @@ -192,11 +179,11 @@ static int gen6_drpc(struct seq_file *m) } /* Not exactly sure what this is */ - print_rc6_res(m, "RC6 \"Locked to RPn\" residency since boot:", - GEN6_GT_GFX_RC6_LOCKED); - print_rc6_res(m, "RC6 residency since boot:", GEN6_GT_GFX_RC6); - print_rc6_res(m, "RC6+ residency since boot:", GEN6_GT_GFX_RC6p); - print_rc6_res(m, "RC6++ residency since boot:", GEN6_GT_GFX_RC6pp); + intel_rc6_print_residency(m, "RC6 \"Locked to RPn\" residency since boot:", + INTEL_RC6_RES_RC6_LOCKED); + intel_rc6_print_residency(m, "RC6 residency since boot:", INTEL_RC6_RES_RC6); + intel_rc6_print_residency(m, "RC6+ residency since boot:", INTEL_RC6_RES_RC6p); + intel_rc6_print_residency(m, "RC6++ residency since boot:", INTEL_RC6_RES_RC6pp); if (GRAPHICS_VER(i915) <= 7) { seq_printf(m, "RC6 voltage: %dmV\n", @@ -269,6 +256,61 @@ static int ilk_drpc(struct seq_file *m) return 0; } +static int mtl_drpc(struct seq_file *m) +{ + struct intel_gt *gt = m->private; + struct intel_uncore *uncore = gt->uncore; + u32 gt_core_status, rcctl1, mt_fwake_req; + u32 mtl_powergate_enable = 0, mtl_powergate_status = 0; + + mt_fwake_req = intel_uncore_read_fw(uncore, FORCEWAKE_MT); + gt_core_status = intel_uncore_read(uncore, MTL_MIRROR_TARGET_WP1); + + rcctl1 = intel_uncore_read(uncore, GEN6_RC_CONTROL); + mtl_powergate_enable = intel_uncore_read(uncore, GEN9_PG_ENABLE); + mtl_powergate_status = intel_uncore_read(uncore, + GEN9_PWRGT_DOMAIN_STATUS); + + seq_printf(m, "RC6 Enabled: %s\n", + str_yes_no(rcctl1 & GEN6_RC_CTL_RC6_ENABLE)); + if (gt->type == GT_MEDIA) { + seq_printf(m, "Media Well Gating Enabled: %s\n", + str_yes_no(mtl_powergate_enable & GEN9_MEDIA_PG_ENABLE)); + } else { + seq_printf(m, "Render Well Gating Enabled: %s\n", + str_yes_no(mtl_powergate_enable & GEN9_RENDER_PG_ENABLE)); + } + + seq_puts(m, "Current RC state: "); + switch (REG_FIELD_GET(MTL_CC_MASK, gt_core_status)) { + case MTL_CC0: + seq_puts(m, "RC0\n"); + break; + case MTL_CC6: + seq_puts(m, "RC6\n"); + break; + default: + MISSING_CASE(REG_FIELD_GET(MTL_CC_MASK, gt_core_status)); + seq_puts(m, "Unknown\n"); + break; + } + + seq_printf(m, "Multi-threaded Forcewake Request: 0x%x\n", mt_fwake_req); + if (gt->type == GT_MEDIA) + seq_printf(m, "Media Power Well: %s\n", + (mtl_powergate_status & + GEN9_PWRGT_MEDIA_STATUS_MASK) ? "Up" : "Down"); + else + seq_printf(m, "Render Power Well: %s\n", + (mtl_powergate_status & + GEN9_PWRGT_RENDER_STATUS_MASK) ? "Up" : "Down"); + + /* Works for both render and media gt's */ + intel_rc6_print_residency(m, "RC6 residency since boot:", INTEL_RC6_RES_RC6); + + return fw_domains_show(m, NULL); +} + static int drpc_show(struct seq_file *m, void *unused) { struct intel_gt *gt = m->private; @@ -277,7 +319,9 @@ static int drpc_show(struct seq_file *m, void *unused) int err = -ENODEV; with_intel_runtime_pm(gt->uncore->rpm, wakeref) { - if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) + err = mtl_drpc(m); + else if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) err = vlv_drpc(m); else if (GRAPHICS_VER(i915) >= 6) err = gen6_drpc(m); @@ -307,7 +351,7 @@ void intel_gt_pm_frequency_dump(struct intel_gt *gt, struct drm_printer *p) drm_printf(p, "Current VID: %d\n", (rgvstat & MEMSTAT_VID_MASK) >> MEMSTAT_VID_SHIFT); drm_printf(p, "Current P-state: %d\n", - (rgvstat & MEMSTAT_PSTATE_MASK) >> MEMSTAT_PSTATE_SHIFT); + REG_FIELD_GET(MEMSTAT_PSTATE_MASK, rgvstat)); } else if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) { u32 rpmodectl, freq_sts; @@ -344,162 +388,7 @@ void intel_gt_pm_frequency_dump(struct intel_gt *gt, struct drm_printer *p) drm_printf(p, "efficient (RPe) frequency: %d MHz\n", intel_gpu_freq(rps, rps->efficient_freq)); } else if (GRAPHICS_VER(i915) >= 6) { - u32 rp_state_limits; - u32 gt_perf_status; - struct intel_rps_freq_caps caps; - u32 rpmodectl, rpinclimit, rpdeclimit; - u32 rpstat, cagf, reqf; - u32 rpcurupei, rpcurup, rpprevup; - u32 rpcurdownei, rpcurdown, rpprevdown; - u32 rpupei, rpupt, rpdownei, rpdownt; - u32 pm_ier, pm_imr, pm_isr, pm_iir, pm_mask; - - rp_state_limits = intel_uncore_read(uncore, GEN6_RP_STATE_LIMITS); - gen6_rps_get_freq_caps(rps, &caps); - if (IS_GEN9_LP(i915)) - gt_perf_status = intel_uncore_read(uncore, BXT_GT_PERF_STATUS); - else - gt_perf_status = intel_uncore_read(uncore, GEN6_GT_PERF_STATUS); - - /* RPSTAT1 is in the GT power well */ - intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL); - - reqf = intel_uncore_read(uncore, GEN6_RPNSWREQ); - if (GRAPHICS_VER(i915) >= 9) { - reqf >>= 23; - } else { - reqf &= ~GEN6_TURBO_DISABLE; - if (IS_HASWELL(i915) || IS_BROADWELL(i915)) - reqf >>= 24; - else - reqf >>= 25; - } - reqf = intel_gpu_freq(rps, reqf); - - rpmodectl = intel_uncore_read(uncore, GEN6_RP_CONTROL); - rpinclimit = intel_uncore_read(uncore, GEN6_RP_UP_THRESHOLD); - rpdeclimit = intel_uncore_read(uncore, GEN6_RP_DOWN_THRESHOLD); - - rpstat = intel_uncore_read(uncore, GEN6_RPSTAT1); - rpcurupei = intel_uncore_read(uncore, GEN6_RP_CUR_UP_EI) & GEN6_CURICONT_MASK; - rpcurup = intel_uncore_read(uncore, GEN6_RP_CUR_UP) & GEN6_CURBSYTAVG_MASK; - rpprevup = intel_uncore_read(uncore, GEN6_RP_PREV_UP) & GEN6_CURBSYTAVG_MASK; - rpcurdownei = intel_uncore_read(uncore, GEN6_RP_CUR_DOWN_EI) & GEN6_CURIAVG_MASK; - rpcurdown = intel_uncore_read(uncore, GEN6_RP_CUR_DOWN) & GEN6_CURBSYTAVG_MASK; - rpprevdown = intel_uncore_read(uncore, GEN6_RP_PREV_DOWN) & GEN6_CURBSYTAVG_MASK; - - rpupei = intel_uncore_read(uncore, GEN6_RP_UP_EI); - rpupt = intel_uncore_read(uncore, GEN6_RP_UP_THRESHOLD); - - rpdownei = intel_uncore_read(uncore, GEN6_RP_DOWN_EI); - rpdownt = intel_uncore_read(uncore, GEN6_RP_DOWN_THRESHOLD); - - cagf = intel_rps_read_actual_frequency(rps); - - intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL); - - if (GRAPHICS_VER(i915) >= 11) { - pm_ier = intel_uncore_read(uncore, GEN11_GPM_WGBOXPERF_INTR_ENABLE); - pm_imr = intel_uncore_read(uncore, GEN11_GPM_WGBOXPERF_INTR_MASK); - /* - * The equivalent to the PM ISR & IIR cannot be read - * without affecting the current state of the system - */ - pm_isr = 0; - pm_iir = 0; - } else if (GRAPHICS_VER(i915) >= 8) { - pm_ier = intel_uncore_read(uncore, GEN8_GT_IER(2)); - pm_imr = intel_uncore_read(uncore, GEN8_GT_IMR(2)); - pm_isr = intel_uncore_read(uncore, GEN8_GT_ISR(2)); - pm_iir = intel_uncore_read(uncore, GEN8_GT_IIR(2)); - } else { - pm_ier = intel_uncore_read(uncore, GEN6_PMIER); - pm_imr = intel_uncore_read(uncore, GEN6_PMIMR); - pm_isr = intel_uncore_read(uncore, GEN6_PMISR); - pm_iir = intel_uncore_read(uncore, GEN6_PMIIR); - } - pm_mask = intel_uncore_read(uncore, GEN6_PMINTRMSK); - - drm_printf(p, "Video Turbo Mode: %s\n", - str_yes_no(rpmodectl & GEN6_RP_MEDIA_TURBO)); - drm_printf(p, "HW control enabled: %s\n", - str_yes_no(rpmodectl & GEN6_RP_ENABLE)); - drm_printf(p, "SW control enabled: %s\n", - str_yes_no((rpmodectl & GEN6_RP_MEDIA_MODE_MASK) == GEN6_RP_MEDIA_SW_MODE)); - - drm_printf(p, "PM IER=0x%08x IMR=0x%08x, MASK=0x%08x\n", - pm_ier, pm_imr, pm_mask); - if (GRAPHICS_VER(i915) <= 10) - drm_printf(p, "PM ISR=0x%08x IIR=0x%08x\n", - pm_isr, pm_iir); - drm_printf(p, "pm_intrmsk_mbz: 0x%08x\n", - rps->pm_intrmsk_mbz); - drm_printf(p, "GT_PERF_STATUS: 0x%08x\n", gt_perf_status); - drm_printf(p, "Render p-state ratio: %d\n", - (gt_perf_status & (GRAPHICS_VER(i915) >= 9 ? 0x1ff00 : 0xff00)) >> 8); - drm_printf(p, "Render p-state VID: %d\n", - gt_perf_status & 0xff); - drm_printf(p, "Render p-state limit: %d\n", - rp_state_limits & 0xff); - drm_printf(p, "RPSTAT1: 0x%08x\n", rpstat); - drm_printf(p, "RPMODECTL: 0x%08x\n", rpmodectl); - drm_printf(p, "RPINCLIMIT: 0x%08x\n", rpinclimit); - drm_printf(p, "RPDECLIMIT: 0x%08x\n", rpdeclimit); - drm_printf(p, "RPNSWREQ: %dMHz\n", reqf); - drm_printf(p, "CAGF: %dMHz\n", cagf); - drm_printf(p, "RP CUR UP EI: %d (%lldns)\n", - rpcurupei, - intel_gt_pm_interval_to_ns(gt, rpcurupei)); - drm_printf(p, "RP CUR UP: %d (%lldns)\n", - rpcurup, intel_gt_pm_interval_to_ns(gt, rpcurup)); - drm_printf(p, "RP PREV UP: %d (%lldns)\n", - rpprevup, intel_gt_pm_interval_to_ns(gt, rpprevup)); - drm_printf(p, "Up threshold: %d%%\n", - rps->power.up_threshold); - drm_printf(p, "RP UP EI: %d (%lldns)\n", - rpupei, intel_gt_pm_interval_to_ns(gt, rpupei)); - drm_printf(p, "RP UP THRESHOLD: %d (%lldns)\n", - rpupt, intel_gt_pm_interval_to_ns(gt, rpupt)); - - drm_printf(p, "RP CUR DOWN EI: %d (%lldns)\n", - rpcurdownei, - intel_gt_pm_interval_to_ns(gt, rpcurdownei)); - drm_printf(p, "RP CUR DOWN: %d (%lldns)\n", - rpcurdown, - intel_gt_pm_interval_to_ns(gt, rpcurdown)); - drm_printf(p, "RP PREV DOWN: %d (%lldns)\n", - rpprevdown, - intel_gt_pm_interval_to_ns(gt, rpprevdown)); - drm_printf(p, "Down threshold: %d%%\n", - rps->power.down_threshold); - drm_printf(p, "RP DOWN EI: %d (%lldns)\n", - rpdownei, intel_gt_pm_interval_to_ns(gt, rpdownei)); - drm_printf(p, "RP DOWN THRESHOLD: %d (%lldns)\n", - rpdownt, intel_gt_pm_interval_to_ns(gt, rpdownt)); - - drm_printf(p, "Lowest (RPN) frequency: %dMHz\n", - intel_gpu_freq(rps, caps.min_freq)); - drm_printf(p, "Nominal (RP1) frequency: %dMHz\n", - intel_gpu_freq(rps, caps.rp1_freq)); - drm_printf(p, "Max non-overclocked (RP0) frequency: %dMHz\n", - intel_gpu_freq(rps, caps.rp0_freq)); - drm_printf(p, "Max overclocked frequency: %dMHz\n", - intel_gpu_freq(rps, rps->max_freq)); - - drm_printf(p, "Current freq: %d MHz\n", - intel_gpu_freq(rps, rps->cur_freq)); - drm_printf(p, "Actual freq: %d MHz\n", cagf); - drm_printf(p, "Idle freq: %d MHz\n", - intel_gpu_freq(rps, rps->idle_freq)); - drm_printf(p, "Min freq: %d MHz\n", - intel_gpu_freq(rps, rps->min_freq)); - drm_printf(p, "Boost freq: %d MHz\n", - intel_gpu_freq(rps, rps->boost_freq)); - drm_printf(p, "Max freq: %d MHz\n", - intel_gpu_freq(rps, rps->max_freq)); - drm_printf(p, - "efficient (RPe) frequency: %d MHz\n", - intel_gpu_freq(rps, rps->efficient_freq)); + gen6_rps_frequency_dump(rps, p); } else { drm_puts(p, "no P-state info available\n"); } @@ -655,6 +544,44 @@ static bool rps_eval(void *data) DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(rps_boost); +static int perf_limit_reasons_get(void *data, u64 *val) +{ + struct intel_gt *gt = data; + intel_wakeref_t wakeref; + + with_intel_runtime_pm(gt->uncore->rpm, wakeref) + *val = intel_uncore_read(gt->uncore, intel_gt_perf_limit_reasons_reg(gt)); + + return 0; +} + +static int perf_limit_reasons_clear(void *data, u64 val) +{ + struct intel_gt *gt = data; + intel_wakeref_t wakeref; + + /* + * Clear the upper 16 "log" bits, the lower 16 "status" bits are + * read-only. The upper 16 "log" bits are identical to the lower 16 + * "status" bits except that the "log" bits remain set until cleared. + */ + with_intel_runtime_pm(gt->uncore->rpm, wakeref) + intel_uncore_rmw(gt->uncore, intel_gt_perf_limit_reasons_reg(gt), + GT0_PERF_LIMIT_REASONS_LOG_MASK, 0); + + return 0; +} + +static bool perf_limit_reasons_eval(void *data) +{ + struct intel_gt *gt = data; + + return i915_mmio_reg_valid(intel_gt_perf_limit_reasons_reg(gt)); +} + +DEFINE_SIMPLE_ATTRIBUTE(perf_limit_reasons_fops, perf_limit_reasons_get, + perf_limit_reasons_clear, "%llu\n"); + void intel_gt_pm_debugfs_register(struct intel_gt *gt, struct dentry *root) { static const struct intel_gt_debugfs_file files[] = { @@ -664,6 +591,7 @@ void intel_gt_pm_debugfs_register(struct intel_gt *gt, struct dentry *root) { "forcewake_user", &forcewake_user_fops, NULL}, { "llc", &llc_fops, llc_eval }, { "rps_boost", &rps_boost_fops, rps_eval }, + { "perf_limit_reasons", &perf_limit_reasons_fops, perf_limit_reasons_eval }, }; intel_gt_debugfs_register_files(root, files, ARRAY_SIZE(files), gt); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h index 2275ee47da95..c3cd92691795 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h @@ -7,6 +7,27 @@ #define __INTEL_GT_REGS__ #include "i915_reg_defs.h" +#include "display/intel_display_reg_defs.h" /* VLV_DISPLAY_BASE */ + +#define MCR_REG(offset) ((const i915_mcr_reg_t){ .reg = (offset) }) + +/* + * The perf control registers are technically multicast registers, but the + * driver never needs to read/write them directly; we only use them to build + * lists of registers (where they're mixed in with other non-MCR registers) + * and then operate on the offset directly. For now we'll just define them + * as non-multicast so we can place them on the same list, but we may want + * to try to come up with a better way to handle heterogeneous lists of + * registers in the future. + */ +#define PERF_REG(offset) _MMIO(offset) + +/* MTL workpoint reg to get core C state and actual freq of 3D, SAMedia */ +#define MTL_MIRROR_TARGET_WP1 _MMIO(0xc60) +#define MTL_CAGF_MASK REG_GENMASK(8, 0) +#define MTL_CC0 0x0 +#define MTL_CC6 0x3 +#define MTL_CC_MASK REG_GENMASK(12, 9) /* RPM unit config (Gen8+) */ #define RPM_CONFIG0 _MMIO(0xd00) @@ -39,9 +60,17 @@ #define FORCEWAKE_ACK_RENDER_GEN9 _MMIO(0xd84) #define FORCEWAKE_ACK_MEDIA_GEN9 _MMIO(0xd88) +#define FORCEWAKE_ACK_GSC _MMIO(0xdf8) +#define FORCEWAKE_ACK_GT_MTL _MMIO(0xdfc) + +#define GMD_ID_GRAPHICS _MMIO(0xd8c) +#define GMD_ID_MEDIA _MMIO(MTL_MEDIA_GSI_BASE + 0xd8c) + #define MCFG_MCR_SELECTOR _MMIO(0xfd0) +#define MTL_MCR_SELECTOR _MMIO(0xfd4) #define SF_MCR_SELECTOR _MMIO(0xfd8) #define GEN8_MCR_SELECTOR _MMIO(0xfdc) +#define GAM_MCR_SELECTOR _MMIO(0xfe0) #define GEN8_MCR_SLICE(slice) (((slice) & 3) << 26) #define GEN8_MCR_SLICE_MASK GEN8_MCR_SLICE(3) #define GEN8_MCR_SUBSLICE(subslice) (((subslice) & 3) << 24) @@ -51,6 +80,8 @@ #define GEN11_MCR_SLICE_MASK GEN11_MCR_SLICE(0xf) #define GEN11_MCR_SUBSLICE(subslice) (((subslice) & 0x7) << 24) #define GEN11_MCR_SUBSLICE_MASK GEN11_MCR_SUBSLICE(0x7) +#define MTL_MCR_GROUPID REG_GENMASK(11, 8) +#define MTL_MCR_INSTANCEID REG_GENMASK(3, 0) #define IPEIR_I965 _MMIO(0x2064) #define IPEHR_I965 _MMIO(0x2068) @@ -326,11 +357,12 @@ #define GEN7_TLB_RD_ADDR _MMIO(0x4700) #define GEN12_PAT_INDEX(index) _MMIO(0x4800 + (index) * 4) +#define XEHP_PAT_INDEX(index) MCR_REG(0x4800 + (index) * 4) -#define XEHP_TILE0_ADDR_RANGE _MMIO(0x4900) +#define XEHP_TILE0_ADDR_RANGE MCR_REG(0x4900) #define XEHP_TILE_LMEM_RANGE_SHIFT 8 -#define XEHP_FLAT_CCS_BASE_ADDR _MMIO(0x4910) +#define XEHP_FLAT_CCS_BASE_ADDR MCR_REG(0x4910) #define XEHP_CCS_BASE_SHIFT 8 #define GAMTARBMODE _MMIO(0x4a08) @@ -380,17 +412,18 @@ #define CHICKEN_RASTER_2 _MMIO(0x6208) #define TBIMR_FAST_CLIP REG_BIT(5) -#define VFLSKPD _MMIO(0x62a8) +#define VFLSKPD MCR_REG(0x62a8) #define DIS_OVER_FETCH_CACHE REG_BIT(1) #define DIS_MULT_MISS_RD_SQUASH REG_BIT(0) -#define FF_MODE2 _MMIO(0x6604) +#define GEN12_FF_MODE2 _MMIO(0x6604) +#define XEHP_FF_MODE2 MCR_REG(0x6604) #define FF_MODE2_GS_TIMER_MASK REG_GENMASK(31, 24) #define FF_MODE2_GS_TIMER_224 REG_FIELD_PREP(FF_MODE2_GS_TIMER_MASK, 224) #define FF_MODE2_TDS_TIMER_MASK REG_GENMASK(23, 16) #define FF_MODE2_TDS_TIMER_128 REG_FIELD_PREP(FF_MODE2_TDS_TIMER_MASK, 4) -#define XEHPG_INSTDONE_GEOM_SVG _MMIO(0x666c) +#define XEHPG_INSTDONE_GEOM_SVG MCR_REG(0x666c) #define CACHE_MODE_0_GEN7 _MMIO(0x7000) /* IVB+ */ #define RC_OP_FLUSH_ENABLE (1 << 0) @@ -418,6 +451,7 @@ #define HIZ_CHICKEN _MMIO(0x7018) #define CHV_HZ_8X8_MODE_IN_1X REG_BIT(15) #define DG1_HZ_READ_SUPPRESSION_OPTIMIZATION_DISABLE REG_BIT(14) +#define HZ_DEPTH_TEST_LE_GE_OPT_DISABLE REG_BIT(13) #define BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE REG_BIT(3) #define GEN8_L3CNTLREG _MMIO(0x7034) @@ -439,23 +473,16 @@ #define GEN8_HDC_CHICKEN1 _MMIO(0x7304) #define GEN11_COMMON_SLICE_CHICKEN3 _MMIO(0x7304) +#define XEHP_COMMON_SLICE_CHICKEN3 MCR_REG(0x7304) #define DG1_FLOAT_POINT_BLEND_OPT_STRICT_MODE_EN REG_BIT(12) #define XEHP_DUAL_SIMD8_SEQ_MERGE_DISABLE REG_BIT(12) #define GEN11_BLEND_EMB_FIX_DISABLE_IN_RCC REG_BIT(11) #define GEN12_DISABLE_CPS_AWARE_COLOR_PIPE REG_BIT(9) -/* GEN9 chicken */ -#define SLICE_ECO_CHICKEN0 _MMIO(0x7308) -#define PIXEL_MASK_CAMMING_DISABLE (1 << 14) - -#define GEN9_SLICE_COMMON_ECO_CHICKEN0 _MMIO(0x7308) -#define DISABLE_PIXEL_MASK_CAMMING (1 << 14) - #define GEN9_SLICE_COMMON_ECO_CHICKEN1 _MMIO(0x731c) -#define GEN11_STATE_CACHE_REDIRECT_TO_CS (1 << 11) - -#define SLICE_COMMON_ECO_CHICKEN1 _MMIO(0x731c) +#define XEHP_SLICE_COMMON_ECO_CHICKEN1 MCR_REG(0x731c) #define MSC_MSAA_REODER_BUF_BYPASS_DISABLE REG_BIT(14) +#define GEN11_STATE_CACHE_REDIRECT_TO_CS (1 << 11) #define GEN9_SLICE_PGCTL_ACK(slice) _MMIO(0x804c + (slice) * 0x4) #define GEN10_SLICE_PGCTL_ACK(slice) _MMIO(0x804c + ((slice) / 3) * 0x34 + \ @@ -482,9 +509,12 @@ #define VF_PREEMPTION _MMIO(0x83a4) #define PREEMPTION_VERTEX_COUNT REG_GENMASK(15, 0) +#define VFG_PREEMPTION_CHICKEN _MMIO(0x83b4) +#define POLYGON_TRIFAN_LINELOOP_DISABLE REG_BIT(4) + #define GEN8_RC6_CTX_INFO _MMIO(0x8504) -#define GEN12_SQCM _MMIO(0x8724) +#define XEHP_SQCM MCR_REG(0x8724) #define EN_32B_ACCESS REG_BIT(30) #define HSW_IDICR _MMIO(0x9008) @@ -516,6 +546,8 @@ #define GEN6_MBCTL_BOOT_FETCH_MECH (1 << 0) /* Fuse readout registers for GT */ +#define XEHP_FUSE4 _MMIO(0x9114) +#define GT_L3_EXC_MASK REG_GENMASK(6, 4) #define GEN10_MIRROR_FUSE3 _MMIO(0x9118) #define GEN10_L3BANK_PAIR_COUNT 4 #define GEN10_L3BANK_MASK 0x0F @@ -619,6 +651,7 @@ #define XEHPC_GRDOM_BLT3 REG_BIT(26) #define XEHPC_GRDOM_BLT2 REG_BIT(25) #define XEHPC_GRDOM_BLT1 REG_BIT(24) +#define GEN12_GRDOM_GSC REG_BIT(21) #define GEN11_GRDOM_SFC3 REG_BIT(20) #define GEN11_GRDOM_SFC2 REG_BIT(19) #define GEN11_GRDOM_SFC1 REG_BIT(18) @@ -644,6 +677,9 @@ #define GEN7_MISCCPCTL _MMIO(0x9424) #define GEN7_DOP_CLOCK_GATE_ENABLE (1 << 0) + +#define GEN8_MISCCPCTL MCR_REG(0x9424) +#define GEN8_DOP_CLOCK_GATE_ENABLE REG_BIT(0) #define GEN12_DOP_CLOCK_GATE_RENDER_ENABLE REG_BIT(1) #define GEN8_DOP_CLOCK_GATE_CFCLK_ENABLE (1 << 2) #define GEN8_DOP_CLOCK_GATE_GUC_ENABLE (1 << 4) @@ -697,7 +733,8 @@ #define GAMTLBVEBOX0_CLKGATE_DIS REG_BIT(16) #define LTCDD_CLKGATE_DIS REG_BIT(10) -#define SLICE_UNIT_LEVEL_CLKGATE _MMIO(0x94d4) +#define GEN11_SLICE_UNIT_LEVEL_CLKGATE _MMIO(0x94d4) +#define XEHP_SLICE_UNIT_LEVEL_CLKGATE MCR_REG(0x94d4) #define SARBUNIT_CLKGATE_DIS (1 << 5) #define RCCUNIT_CLKGATE_DIS (1 << 7) #define MSCUNIT_CLKGATE_DIS (1 << 10) @@ -705,27 +742,27 @@ #define L3_CLKGATE_DIS REG_BIT(16) #define L3_CR2X_CLKGATE_DIS REG_BIT(17) -#define SCCGCTL94DC _MMIO(0x94dc) +#define SCCGCTL94DC MCR_REG(0x94dc) #define CG3DDISURB REG_BIT(14) #define UNSLICE_UNIT_LEVEL_CLKGATE2 _MMIO(0x94e4) #define VSUNIT_CLKGATE_DIS_TGL REG_BIT(19) #define PSDUNIT_CLKGATE_DIS REG_BIT(5) -#define SUBSLICE_UNIT_LEVEL_CLKGATE _MMIO(0x9524) +#define GEN11_SUBSLICE_UNIT_LEVEL_CLKGATE MCR_REG(0x9524) #define DSS_ROUTER_CLKGATE_DIS REG_BIT(28) #define GWUNIT_CLKGATE_DIS REG_BIT(16) -#define SUBSLICE_UNIT_LEVEL_CLKGATE2 _MMIO(0x9528) +#define SUBSLICE_UNIT_LEVEL_CLKGATE2 MCR_REG(0x9528) #define CPSSUNIT_CLKGATE_DIS REG_BIT(9) -#define SSMCGCTL9530 _MMIO(0x9530) +#define SSMCGCTL9530 MCR_REG(0x9530) #define RTFUNIT_CLKGATE_DIS REG_BIT(18) -#define GEN10_DFR_RATIO_EN_AND_CHICKEN _MMIO(0x9550) +#define GEN10_DFR_RATIO_EN_AND_CHICKEN MCR_REG(0x9550) #define DFR_DISABLE (1 << 9) -#define INF_UNIT_LEVEL_CLKGATE _MMIO(0x9560) +#define INF_UNIT_LEVEL_CLKGATE MCR_REG(0x9560) #define CGPSF_CLKGATE_DIS (1 << 3) #define MICRO_BP0_0 _MMIO(0x9800) @@ -770,12 +807,9 @@ #define GEN6_RP_DOWN_TIMEOUT _MMIO(0xa010) #define GEN6_RP_INTERRUPT_LIMITS _MMIO(0xa014) #define GEN6_RPSTAT1 _MMIO(0xa01c) -#define GEN6_CAGF_SHIFT 8 -#define HSW_CAGF_SHIFT 7 -#define GEN9_CAGF_SHIFT 23 -#define GEN6_CAGF_MASK (0x7f << GEN6_CAGF_SHIFT) -#define HSW_CAGF_MASK (0x7f << HSW_CAGF_SHIFT) -#define GEN9_CAGF_MASK (0x1ff << GEN9_CAGF_SHIFT) +#define GEN6_CAGF_MASK REG_GENMASK(14, 8) +#define HSW_CAGF_MASK REG_GENMASK(13, 7) +#define GEN9_CAGF_MASK REG_GENMASK(31, 23) #define GEN6_RP_CONTROL _MMIO(0xa024) #define GEN6_RP_MEDIA_TURBO (1 << 11) #define GEN6_RP_MEDIA_MODE_MASK (3 << 9) @@ -898,6 +932,8 @@ #define FORCEWAKE_MEDIA_VDBOX_GEN11(n) _MMIO(0xa540 + (n) * 4) #define FORCEWAKE_MEDIA_VEBOX_GEN11(n) _MMIO(0xa560 + (n) * 4) +#define FORCEWAKE_REQ_GSC _MMIO(0xa618) + #define CHV_POWER_SS0_SIG1 _MMIO(0xa720) #define CHV_POWER_SS0_SIG2 _MMIO(0xa724) #define CHV_POWER_SS1_SIG1 _MMIO(0xa728) @@ -935,7 +971,8 @@ /* MOCS (Memory Object Control State) registers */ #define GEN9_LNCFCMOCS(i) _MMIO(0xb020 + (i) * 4) /* L3 Cache Control */ -#define GEN9_LNCFCMOCS_REG_COUNT 32 +#define XEHP_LNCFCMOCS(i) MCR_REG(0xb020 + (i) * 4) +#define LNCFCMOCS_REG_COUNT 32 #define GEN7_L3CNTLREG3 _MMIO(0xb024) @@ -951,15 +988,10 @@ #define GEN7_L3LOG(slice, i) _MMIO(0xb070 + (slice) * 0x200 + (i) * 4) #define GEN7_L3LOG_SIZE 0x80 -#define GEN10_SCRATCH_LNCF2 _MMIO(0xb0a0) -#define PMFLUSHDONE_LNICRSDROP (1 << 20) -#define PMFLUSH_GAPL3UNBLOCK (1 << 21) -#define PMFLUSHDONE_LNEBLK (1 << 22) - -#define XEHP_L3NODEARBCFG _MMIO(0xb0b4) +#define XEHP_L3NODEARBCFG MCR_REG(0xb0b4) #define XEHP_LNESPARE REG_BIT(19) -#define GEN8_L3SQCREG1 _MMIO(0xb100) +#define GEN8_L3SQCREG1 MCR_REG(0xb100) /* * Note that on CHV the following has an off-by-one error wrt. to BSpec. * Using the formula in BSpec leads to a hang, while the formula here works @@ -970,31 +1002,28 @@ #define L3_HIGH_PRIO_CREDITS(x) (((x) >> 1) << 14) #define L3_PRIO_CREDITS_MASK ((0x1f << 19) | (0x1f << 14)) -#define GEN10_L3_CHICKEN_MODE_REGISTER _MMIO(0xb114) -#define GEN11_I2M_WRITE_DISABLE (1 << 28) - -#define GEN8_L3SQCREG4 _MMIO(0xb118) +#define GEN8_L3SQCREG4 MCR_REG(0xb118) #define GEN11_LQSC_CLEAN_EVICT_DISABLE (1 << 6) #define GEN8_LQSC_RO_PERF_DIS (1 << 27) #define GEN8_LQSC_FLUSH_COHERENT_LINES (1 << 21) #define GEN8_LQSQ_NONIA_COHERENT_ATOMICS_ENABLE REG_BIT(22) -#define GEN9_SCRATCH1 _MMIO(0xb11c) +#define GEN9_SCRATCH1 MCR_REG(0xb11c) #define EVICTION_PERF_FIX_ENABLE REG_BIT(8) -#define BDW_SCRATCH1 _MMIO(0xb11c) +#define BDW_SCRATCH1 MCR_REG(0xb11c) #define GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE (1 << 2) -#define GEN11_SCRATCH2 _MMIO(0xb140) +#define GEN11_SCRATCH2 MCR_REG(0xb140) #define GEN11_COHERENT_PARTIAL_WRITE_MERGE_ENABLE (1 << 19) -#define GEN11_L3SQCREG5 _MMIO(0xb158) +#define XEHP_L3SQCREG5 MCR_REG(0xb158) #define L3_PWM_TIMER_INIT_VAL_MASK REG_GENMASK(9, 0) -#define MLTICTXCTL _MMIO(0xb170) +#define MLTICTXCTL MCR_REG(0xb170) #define TDONRENDER REG_BIT(2) -#define XEHP_L3SCQREG7 _MMIO(0xb188) +#define XEHP_L3SCQREG7 MCR_REG(0xb188) #define BLEND_FILL_CACHING_OPT_DIS REG_BIT(3) #define XEHPC_L3SCRUB _MMIO(0xb18c) @@ -1002,7 +1031,7 @@ #define SCRUB_RATE_PER_BANK_MASK REG_GENMASK(2, 0) #define SCRUB_RATE_4B_PER_CLK REG_FIELD_PREP(SCRUB_RATE_PER_BANK_MASK, 0x6) -#define L3SQCREG1_CCS0 _MMIO(0xb200) +#define L3SQCREG1_CCS0 MCR_REG(0xb200) #define FLUSHALLNONCOH REG_BIT(5) #define GEN11_GLBLINVL _MMIO(0xb404) @@ -1027,11 +1056,14 @@ #define GEN9_BLT_MOCS(i) _MMIO(__GEN9_BCS0_MOCS0 + (i) * 4) #define GEN12_FAULT_TLB_DATA0 _MMIO(0xceb8) +#define XEHP_FAULT_TLB_DATA0 MCR_REG(0xceb8) #define GEN12_FAULT_TLB_DATA1 _MMIO(0xcebc) +#define XEHP_FAULT_TLB_DATA1 MCR_REG(0xcebc) #define FAULT_VA_HIGH_BITS (0xf << 0) #define FAULT_GTT_SEL (1 << 4) #define GEN12_RING_FAULT_REG _MMIO(0xcec4) +#define XEHP_RING_FAULT_REG MCR_REG(0xcec4) #define GEN8_RING_FAULT_ENGINE_ID(x) (((x) >> 12) & 0x7) #define RING_FAULT_GTTSEL_MASK (1 << 11) #define RING_FAULT_SRCID(x) (((x) >> 3) & 0xff) @@ -1039,16 +1071,21 @@ #define RING_FAULT_VALID (1 << 0) #define GEN12_GFX_TLB_INV_CR _MMIO(0xced8) +#define XEHP_GFX_TLB_INV_CR MCR_REG(0xced8) #define GEN12_VD_TLB_INV_CR _MMIO(0xcedc) +#define XEHP_VD_TLB_INV_CR MCR_REG(0xcedc) #define GEN12_VE_TLB_INV_CR _MMIO(0xcee0) +#define XEHP_VE_TLB_INV_CR MCR_REG(0xcee0) #define GEN12_BLT_TLB_INV_CR _MMIO(0xcee4) +#define XEHP_BLT_TLB_INV_CR MCR_REG(0xcee4) #define GEN12_COMPCTX_TLB_INV_CR _MMIO(0xcf04) +#define XEHP_COMPCTX_TLB_INV_CR MCR_REG(0xcf04) -#define GEN12_MERT_MOD_CTRL _MMIO(0xcf28) -#define RENDER_MOD_CTRL _MMIO(0xcf2c) -#define COMP_MOD_CTRL _MMIO(0xcf30) -#define VDBX_MOD_CTRL _MMIO(0xcf34) -#define VEBX_MOD_CTRL _MMIO(0xcf38) +#define XEHP_MERT_MOD_CTRL MCR_REG(0xcf28) +#define RENDER_MOD_CTRL MCR_REG(0xcf2c) +#define COMP_MOD_CTRL MCR_REG(0xcf30) +#define VDBX_MOD_CTRL MCR_REG(0xcf34) +#define VEBX_MOD_CTRL MCR_REG(0xcf38) #define FORCE_MISS_FTLB REG_BIT(3) #define GEN12_GAMSTLB_CTRL _MMIO(0xcf4c) @@ -1063,48 +1100,52 @@ #define GEN12_GAM_DONE _MMIO(0xcf68) #define GEN7_HALF_SLICE_CHICKEN1 _MMIO(0xe100) /* IVB GT1 + VLV */ +#define GEN8_HALF_SLICE_CHICKEN1 MCR_REG(0xe100) #define GEN7_MAX_PS_THREAD_DEP (8 << 12) #define GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE (1 << 10) #define GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE (1 << 4) #define GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE (1 << 3) #define GEN7_SAMPLER_INSTDONE _MMIO(0xe160) +#define GEN8_SAMPLER_INSTDONE MCR_REG(0xe160) #define GEN7_ROW_INSTDONE _MMIO(0xe164) +#define GEN8_ROW_INSTDONE MCR_REG(0xe164) -#define HALF_SLICE_CHICKEN2 _MMIO(0xe180) +#define HALF_SLICE_CHICKEN2 MCR_REG(0xe180) #define GEN8_ST_PO_DISABLE (1 << 13) -#define HALF_SLICE_CHICKEN3 _MMIO(0xe184) +#define HSW_HALF_SLICE_CHICKEN3 _MMIO(0xe184) +#define GEN8_HALF_SLICE_CHICKEN3 MCR_REG(0xe184) #define HSW_SAMPLE_C_PERFORMANCE (1 << 9) #define GEN8_CENTROID_PIXEL_OPT_DIS (1 << 8) #define GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC (1 << 5) #define GEN8_SAMPLER_POWER_BYPASS_DIS (1 << 1) -#define GEN9_HALF_SLICE_CHICKEN5 _MMIO(0xe188) +#define GEN9_HALF_SLICE_CHICKEN5 MCR_REG(0xe188) #define GEN9_DG_MIRROR_FIX_ENABLE (1 << 5) #define GEN9_CCS_TLB_PREFETCH_ENABLE (1 << 3) -#define GEN10_SAMPLER_MODE _MMIO(0xe18c) +#define GEN10_SAMPLER_MODE MCR_REG(0xe18c) #define ENABLE_SMALLPL REG_BIT(15) #define SC_DISABLE_POWER_OPTIMIZATION_EBB REG_BIT(9) #define GEN11_SAMPLER_ENABLE_HEADLESS_MSG REG_BIT(5) -#define GEN9_HALF_SLICE_CHICKEN7 _MMIO(0xe194) +#define GEN9_HALF_SLICE_CHICKEN7 MCR_REG(0xe194) #define DG2_DISABLE_ROUND_ENABLE_ALLOW_FOR_SSLA REG_BIT(15) #define GEN9_SAMPLER_HASH_COMPRESSED_READ_ADDR REG_BIT(8) #define GEN9_ENABLE_YV12_BUGFIX REG_BIT(4) #define GEN9_ENABLE_GPGPU_PREEMPTION REG_BIT(2) -#define GEN10_CACHE_MODE_SS _MMIO(0xe420) +#define GEN10_CACHE_MODE_SS MCR_REG(0xe420) #define ENABLE_EU_COUNT_FOR_TDL_FLUSH REG_BIT(10) #define DISABLE_ECC REG_BIT(5) #define FLOAT_BLEND_OPTIMIZATION_ENABLE REG_BIT(4) #define ENABLE_PREFETCH_INTO_IC REG_BIT(3) -#define EU_PERF_CNTL0 _MMIO(0xe458) -#define EU_PERF_CNTL4 _MMIO(0xe45c) +#define EU_PERF_CNTL0 PERF_REG(0xe458) +#define EU_PERF_CNTL4 PERF_REG(0xe45c) -#define GEN9_ROW_CHICKEN4 _MMIO(0xe48c) +#define GEN9_ROW_CHICKEN4 MCR_REG(0xe48c) #define GEN12_DISABLE_GRF_CLEAR REG_BIT(13) #define XEHP_DIS_BBL_SYSPIPE REG_BIT(11) #define GEN12_DISABLE_TDL_PUSH REG_BIT(9) @@ -1116,7 +1157,7 @@ #define HSW_ROW_CHICKEN3 _MMIO(0xe49c) #define HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE (1 << 6) -#define GEN8_ROW_CHICKEN _MMIO(0xe4f0) +#define GEN8_ROW_CHICKEN MCR_REG(0xe4f0) #define FLOW_CONTROL_ENABLE REG_BIT(15) #define UGM_BACKUP_MODE REG_BIT(13) #define MDQ_ARBITRATION_MODE REG_BIT(12) @@ -1127,42 +1168,43 @@ #define DISABLE_EARLY_EOT REG_BIT(1) #define GEN7_ROW_CHICKEN2 _MMIO(0xe4f4) + +#define GEN8_ROW_CHICKEN2 MCR_REG(0xe4f4) #define GEN12_DISABLE_READ_SUPPRESSION REG_BIT(15) #define GEN12_DISABLE_EARLY_READ REG_BIT(14) #define GEN12_ENABLE_LARGE_GRF_MODE REG_BIT(12) #define GEN12_PUSH_CONST_DEREF_HOLD_DIS REG_BIT(8) +#define GEN12_DISABLE_DOP_GATING REG_BIT(0) -#define RT_CTRL _MMIO(0xe530) +#define RT_CTRL MCR_REG(0xe530) #define DIS_NULL_QUERY REG_BIT(10) #define STACKID_CTRL REG_GENMASK(6, 5) #define STACKID_CTRL_512 REG_FIELD_PREP(STACKID_CTRL, 0x2) -#define EU_PERF_CNTL1 _MMIO(0xe558) -#define EU_PERF_CNTL5 _MMIO(0xe55c) +#define EU_PERF_CNTL1 PERF_REG(0xe558) +#define EU_PERF_CNTL5 PERF_REG(0xe55c) -#define GEN12_HDC_CHICKEN0 _MMIO(0xe5f0) +#define XEHP_HDC_CHICKEN0 MCR_REG(0xe5f0) #define LSC_L1_FLUSH_CTL_3D_DATAPORT_FLUSH_EVENTS_MASK REG_GENMASK(13, 11) -#define ICL_HDC_MODE _MMIO(0xe5f4) +#define ICL_HDC_MODE MCR_REG(0xe5f4) -#define EU_PERF_CNTL2 _MMIO(0xe658) -#define EU_PERF_CNTL6 _MMIO(0xe65c) -#define EU_PERF_CNTL3 _MMIO(0xe758) +#define EU_PERF_CNTL2 PERF_REG(0xe658) +#define EU_PERF_CNTL6 PERF_REG(0xe65c) +#define EU_PERF_CNTL3 PERF_REG(0xe758) -#define LSC_CHICKEN_BIT_0 _MMIO(0xe7c8) +#define LSC_CHICKEN_BIT_0 MCR_REG(0xe7c8) #define DISABLE_D8_D16_COASLESCE REG_BIT(30) #define FORCE_1_SUB_MESSAGE_PER_FRAGMENT REG_BIT(15) -#define LSC_CHICKEN_BIT_0_UDW _MMIO(0xe7c8 + 4) +#define LSC_CHICKEN_BIT_0_UDW MCR_REG(0xe7c8 + 4) #define DIS_CHAIN_2XSIMD8 REG_BIT(55 - 32) #define FORCE_SLM_FENCE_SCOPE_TO_TILE REG_BIT(42 - 32) #define FORCE_UGM_FENCE_SCOPE_TO_TILE REG_BIT(41 - 32) #define MAXREQS_PER_BANK REG_GENMASK(39 - 32, 37 - 32) #define DISABLE_128B_EVICTION_COMMAND_UDW REG_BIT(36 - 32) -#define SARB_CHICKEN1 _MMIO(0xe90c) +#define SARB_CHICKEN1 MCR_REG(0xe90c) #define COMP_CKN_IN REG_GENMASK(30, 29) -#define GEN7_HALF_SLICE_CHICKEN1_GT2 _MMIO(0xf100) - #define GEN7_ROW_CHICKEN2_GT2 _MMIO(0xf4f4) #define DOP_CLOCK_GATING_DISABLE (1 << 0) #define PUSH_CONSTANT_DEREF_DISABLE (1 << 8) @@ -1339,8 +1381,7 @@ #define MEMSTAT_ILK _MMIO(0x111f8) #define MEMSTAT_VID_MASK 0x7f00 #define MEMSTAT_VID_SHIFT 8 -#define MEMSTAT_PSTATE_MASK 0x00f8 -#define MEMSTAT_PSTATE_SHIFT 3 +#define MEMSTAT_PSTATE_MASK REG_GENMASK(7, 3) #define MEMSTAT_MON_ACTV (1 << 2) #define MEMSTAT_SRC_CTL_MASK 0x0003 #define MEMSTAT_SRC_CTL_CORE 0 @@ -1481,6 +1522,8 @@ #define FORCEWAKE_MEDIA_VLV _MMIO(0x1300b8) #define FORCEWAKE_ACK_MEDIA_VLV _MMIO(0x1300bc) +#define MTL_MEDIA_MC6 _MMIO(0x138048) + #define GEN6_GT_THREAD_STATUS_REG _MMIO(0x13805c) #define GEN6_GT_THREAD_STATUS_CORE_MASK 0x7 @@ -1510,10 +1553,15 @@ #define VLV_RENDER_C0_COUNT _MMIO(0x138118) #define VLV_MEDIA_C0_COUNT _MMIO(0x13811c) +#define GEN12_RPSTAT1 _MMIO(0x1381b4) +#define GEN12_VOLTAGE_MASK REG_GENMASK(10, 0) +#define GEN12_CAGF_MASK REG_GENMASK(19, 11) + #define GEN11_GT_INTR_DW(x) _MMIO(0x190018 + ((x) * 4)) #define GEN11_CSME (31) #define GEN11_GUNIT (28) #define GEN11_GUC (25) +#define MTL_MGUC (24) #define GEN11_WDPERF (20) #define GEN11_KCR (19) #define GEN11_GTPM (16) @@ -1568,6 +1616,7 @@ #define GEN11_VECS0_VECS1_INTR_MASK _MMIO(0x1900d0) #define GEN12_VECS2_VECS3_INTR_MASK _MMIO(0x1900d4) #define GEN11_GUC_SG_INTR_MASK _MMIO(0x1900e8) +#define MTL_GUC_MGUC_INTR_MASK _MMIO(0x1900e8) /* MTL+ */ #define GEN11_GPM_WGBOXPERF_INTR_MASK _MMIO(0x1900ec) #define GEN11_CRYPTO_RSVD_INTR_MASK _MMIO(0x1900f0) #define GEN11_GUNIT_CSME_INTR_MASK _MMIO(0x1900f4) @@ -1580,6 +1629,11 @@ #define GEN12_SFC_DONE(n) _MMIO(0x1cc000 + (n) * 0x1000) +#define GT0_PACKAGE_ENERGY_STATUS _MMIO(0x250004) +#define GT0_PACKAGE_RAPL_LIMIT _MMIO(0x250008) +#define GT0_PACKAGE_POWER_SKU_UNIT _MMIO(0x250068) +#define GT0_PLATFORM_ENERGY_STATUS _MMIO(0x25006c) + /* * Standalone Media's non-engine GT registers are located at their regular GT * offsets plus 0x380000. This extra offset is stored inside the intel_uncore diff --git a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c index d651ccd0ab20..9486dd3bed99 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c @@ -22,11 +22,9 @@ bool is_object_gt(struct kobject *kobj) return !strncmp(kobj->name, "gt", 2); } -struct intel_gt *intel_gt_sysfs_get_drvdata(struct device *dev, +struct intel_gt *intel_gt_sysfs_get_drvdata(struct kobject *kobj, const char *name) { - struct kobject *kobj = &dev->kobj; - /* * We are interested at knowing from where the interface * has been called, whether it's called from gt/ or from @@ -38,6 +36,7 @@ struct intel_gt *intel_gt_sysfs_get_drvdata(struct device *dev, * "struct drm_i915_private *" type. */ if (!is_object_gt(kobj)) { + struct device *dev = kobj_to_dev(kobj); struct drm_i915_private *i915 = kdev_minor_to_i915(dev); return to_gt(i915); @@ -51,18 +50,18 @@ static struct kobject *gt_get_parent_obj(struct intel_gt *gt) return >->i915->drm.primary->kdev->kobj; } -static ssize_t id_show(struct device *dev, - struct device_attribute *attr, +static ssize_t id_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) { - struct intel_gt *gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name); + struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name); return sysfs_emit(buf, "%u\n", gt->info.id); } -static DEVICE_ATTR_RO(id); +static struct kobj_attribute attr_id = __ATTR_RO(id); static struct attribute *id_attrs[] = { - &dev_attr_id.attr, + &attr_id.attr, NULL, }; ATTRIBUTE_GROUPS(id); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.h b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.h index 6232923a420d..18bab835be02 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.h @@ -18,11 +18,6 @@ bool is_object_gt(struct kobject *kobj); struct drm_i915_private *kobj_to_i915(struct kobject *kobj); -struct kobject * -intel_gt_create_kobj(struct intel_gt *gt, - struct kobject *dir, - const char *name); - static inline struct intel_gt *kobj_to_gt(struct kobject *kobj) { return container_of(kobj, struct intel_gt, sysfs_gt); @@ -30,7 +25,7 @@ static inline struct intel_gt *kobj_to_gt(struct kobject *kobj) void intel_gt_sysfs_register(struct intel_gt *gt); void intel_gt_sysfs_unregister(struct intel_gt *gt); -struct intel_gt *intel_gt_sysfs_get_drvdata(struct device *dev, +struct intel_gt *intel_gt_sysfs_get_drvdata(struct kobject *kobj, const char *name); #endif /* SYSFS_GT_H */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c index 180dd6f3ef57..cf71305ad586 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c @@ -24,14 +24,15 @@ enum intel_gt_sysfs_op { }; static int -sysfs_gt_attribute_w_func(struct device *dev, struct device_attribute *attr, +sysfs_gt_attribute_w_func(struct kobject *kobj, struct attribute *attr, int (func)(struct intel_gt *gt, u32 val), u32 val) { struct intel_gt *gt; int ret; - if (!is_object_gt(&dev->kobj)) { + if (!is_object_gt(kobj)) { int i; + struct device *dev = kobj_to_dev(kobj); struct drm_i915_private *i915 = kdev_minor_to_i915(dev); for_each_gt(gt, i915, i) { @@ -40,7 +41,7 @@ sysfs_gt_attribute_w_func(struct device *dev, struct device_attribute *attr, break; } } else { - gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name); + gt = intel_gt_sysfs_get_drvdata(kobj, attr->name); ret = func(gt, val); } @@ -48,7 +49,7 @@ sysfs_gt_attribute_w_func(struct device *dev, struct device_attribute *attr, } static u32 -sysfs_gt_attribute_r_func(struct device *dev, struct device_attribute *attr, +sysfs_gt_attribute_r_func(struct kobject *kobj, struct attribute *attr, u32 (func)(struct intel_gt *gt), enum intel_gt_sysfs_op op) { @@ -57,8 +58,9 @@ sysfs_gt_attribute_r_func(struct device *dev, struct device_attribute *attr, ret = (op == INTEL_GT_SYSFS_MAX) ? 0 : (u32) -1; - if (!is_object_gt(&dev->kobj)) { + if (!is_object_gt(kobj)) { int i; + struct device *dev = kobj_to_dev(kobj); struct drm_i915_private *i915 = kdev_minor_to_i915(dev); for_each_gt(gt, i915, i) { @@ -77,7 +79,7 @@ sysfs_gt_attribute_r_func(struct device *dev, struct device_attribute *attr, } } } else { - gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name); + gt = intel_gt_sysfs_get_drvdata(kobj, attr->name); ret = func(gt); } @@ -92,23 +94,90 @@ sysfs_gt_attribute_r_func(struct device *dev, struct device_attribute *attr, #define sysfs_gt_attribute_r_max_func(d, a, f) \ sysfs_gt_attribute_r_func(d, a, f, INTEL_GT_SYSFS_MAX) +#define INTEL_GT_SYSFS_SHOW(_name, _attr_type) \ + static ssize_t _name##_show_common(struct kobject *kobj, \ + struct attribute *attr, char *buff) \ + { \ + u32 val = sysfs_gt_attribute_r_##_attr_type##_func(kobj, attr, \ + __##_name##_show); \ + \ + return sysfs_emit(buff, "%u\n", val); \ + } \ + static ssize_t _name##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, char *buff) \ + { \ + return _name ##_show_common(kobj, &attr->attr, buff); \ + } \ + static ssize_t _name##_dev_show(struct device *dev, \ + struct device_attribute *attr, char *buff) \ + { \ + return _name##_show_common(&dev->kobj, &attr->attr, buff); \ + } + +#define INTEL_GT_SYSFS_STORE(_name, _func) \ + static ssize_t _name##_store_common(struct kobject *kobj, \ + struct attribute *attr, \ + const char *buff, size_t count) \ + { \ + int ret; \ + u32 val; \ + \ + ret = kstrtou32(buff, 0, &val); \ + if (ret) \ + return ret; \ + \ + ret = sysfs_gt_attribute_w_func(kobj, attr, _func, val); \ + \ + return ret ?: count; \ + } \ + static ssize_t _name##_store(struct kobject *kobj, \ + struct kobj_attribute *attr, const char *buff, \ + size_t count) \ + { \ + return _name##_store_common(kobj, &attr->attr, buff, count); \ + } \ + static ssize_t _name##_dev_store(struct device *dev, \ + struct device_attribute *attr, \ + const char *buff, size_t count) \ + { \ + return _name##_store_common(&dev->kobj, &attr->attr, buff, count); \ + } + +#define INTEL_GT_SYSFS_SHOW_MAX(_name) INTEL_GT_SYSFS_SHOW(_name, max) +#define INTEL_GT_SYSFS_SHOW_MIN(_name) INTEL_GT_SYSFS_SHOW(_name, min) + +#define INTEL_GT_ATTR_RW(_name) \ + static struct kobj_attribute attr_##_name = __ATTR_RW(_name) + +#define INTEL_GT_ATTR_RO(_name) \ + static struct kobj_attribute attr_##_name = __ATTR_RO(_name) + +#define INTEL_GT_DUAL_ATTR_RW(_name) \ + static struct device_attribute dev_attr_##_name = __ATTR(_name, 0644, \ + _name##_dev_show, \ + _name##_dev_store); \ + INTEL_GT_ATTR_RW(_name) + +#define INTEL_GT_DUAL_ATTR_RO(_name) \ + static struct device_attribute dev_attr_##_name = __ATTR(_name, 0444, \ + _name##_dev_show, \ + NULL); \ + INTEL_GT_ATTR_RO(_name) + #ifdef CONFIG_PM -static u32 get_residency(struct intel_gt *gt, i915_reg_t reg) +static u32 get_residency(struct intel_gt *gt, enum intel_rc6_res_type id) { intel_wakeref_t wakeref; u64 res = 0; with_intel_runtime_pm(gt->uncore->rpm, wakeref) - res = intel_rc6_residency_us(>->rc6, reg); + res = intel_rc6_residency_us(>->rc6, id); return DIV_ROUND_CLOSEST_ULL(res, 1000); } -static ssize_t rc6_enable_show(struct device *dev, - struct device_attribute *attr, - char *buff) +static u8 get_rc6_mask(struct intel_gt *gt) { - struct intel_gt *gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name); u8 mask = 0; if (HAS_RC6(gt->i915)) @@ -118,105 +187,105 @@ static ssize_t rc6_enable_show(struct device *dev, if (HAS_RC6pp(gt->i915)) mask |= BIT(2); - return sysfs_emit(buff, "%x\n", mask); + return mask; } -static u32 __rc6_residency_ms_show(struct intel_gt *gt) +static ssize_t rc6_enable_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buff) { - return get_residency(gt, GEN6_GT_GFX_RC6); + struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name); + + return sysfs_emit(buff, "%x\n", get_rc6_mask(gt)); } -static ssize_t rc6_residency_ms_show(struct device *dev, - struct device_attribute *attr, - char *buff) +static ssize_t rc6_enable_dev_show(struct device *dev, + struct device_attribute *attr, + char *buff) { - u32 rc6_residency = sysfs_gt_attribute_r_min_func(dev, attr, - __rc6_residency_ms_show); + struct intel_gt *gt = intel_gt_sysfs_get_drvdata(&dev->kobj, attr->attr.name); - return sysfs_emit(buff, "%u\n", rc6_residency); + return sysfs_emit(buff, "%x\n", get_rc6_mask(gt)); } -static u32 __rc6p_residency_ms_show(struct intel_gt *gt) +static u32 __rc6_residency_ms_show(struct intel_gt *gt) { - return get_residency(gt, GEN6_GT_GFX_RC6p); + return get_residency(gt, INTEL_RC6_RES_RC6); } -static ssize_t rc6p_residency_ms_show(struct device *dev, - struct device_attribute *attr, - char *buff) +static u32 __rc6p_residency_ms_show(struct intel_gt *gt) { - u32 rc6p_residency = sysfs_gt_attribute_r_min_func(dev, attr, - __rc6p_residency_ms_show); - - return sysfs_emit(buff, "%u\n", rc6p_residency); + return get_residency(gt, INTEL_RC6_RES_RC6p); } static u32 __rc6pp_residency_ms_show(struct intel_gt *gt) { - return get_residency(gt, GEN6_GT_GFX_RC6pp); -} - -static ssize_t rc6pp_residency_ms_show(struct device *dev, - struct device_attribute *attr, - char *buff) -{ - u32 rc6pp_residency = sysfs_gt_attribute_r_min_func(dev, attr, - __rc6pp_residency_ms_show); - - return sysfs_emit(buff, "%u\n", rc6pp_residency); + return get_residency(gt, INTEL_RC6_RES_RC6pp); } static u32 __media_rc6_residency_ms_show(struct intel_gt *gt) { - return get_residency(gt, VLV_GT_MEDIA_RC6); + return get_residency(gt, INTEL_RC6_RES_VLV_MEDIA); } -static ssize_t media_rc6_residency_ms_show(struct device *dev, - struct device_attribute *attr, - char *buff) -{ - u32 rc6_residency = sysfs_gt_attribute_r_min_func(dev, attr, - __media_rc6_residency_ms_show); +INTEL_GT_SYSFS_SHOW_MIN(rc6_residency_ms); +INTEL_GT_SYSFS_SHOW_MIN(rc6p_residency_ms); +INTEL_GT_SYSFS_SHOW_MIN(rc6pp_residency_ms); +INTEL_GT_SYSFS_SHOW_MIN(media_rc6_residency_ms); - return sysfs_emit(buff, "%u\n", rc6_residency); -} - -static DEVICE_ATTR_RO(rc6_enable); -static DEVICE_ATTR_RO(rc6_residency_ms); -static DEVICE_ATTR_RO(rc6p_residency_ms); -static DEVICE_ATTR_RO(rc6pp_residency_ms); -static DEVICE_ATTR_RO(media_rc6_residency_ms); +INTEL_GT_DUAL_ATTR_RO(rc6_enable); +INTEL_GT_DUAL_ATTR_RO(rc6_residency_ms); +INTEL_GT_DUAL_ATTR_RO(rc6p_residency_ms); +INTEL_GT_DUAL_ATTR_RO(rc6pp_residency_ms); +INTEL_GT_DUAL_ATTR_RO(media_rc6_residency_ms); static struct attribute *rc6_attrs[] = { + &attr_rc6_enable.attr, + &attr_rc6_residency_ms.attr, + NULL +}; + +static struct attribute *rc6p_attrs[] = { + &attr_rc6p_residency_ms.attr, + &attr_rc6pp_residency_ms.attr, + NULL +}; + +static struct attribute *media_rc6_attrs[] = { + &attr_media_rc6_residency_ms.attr, + NULL +}; + +static struct attribute *rc6_dev_attrs[] = { &dev_attr_rc6_enable.attr, &dev_attr_rc6_residency_ms.attr, NULL }; -static struct attribute *rc6p_attrs[] = { +static struct attribute *rc6p_dev_attrs[] = { &dev_attr_rc6p_residency_ms.attr, &dev_attr_rc6pp_residency_ms.attr, NULL }; -static struct attribute *media_rc6_attrs[] = { +static struct attribute *media_rc6_dev_attrs[] = { &dev_attr_media_rc6_residency_ms.attr, NULL }; static const struct attribute_group rc6_attr_group[] = { { .attrs = rc6_attrs, }, - { .name = power_group_name, .attrs = rc6_attrs, }, + { .name = power_group_name, .attrs = rc6_dev_attrs, }, }; static const struct attribute_group rc6p_attr_group[] = { { .attrs = rc6p_attrs, }, - { .name = power_group_name, .attrs = rc6p_attrs, }, + { .name = power_group_name, .attrs = rc6p_dev_attrs, }, }; static const struct attribute_group media_rc6_attr_group[] = { { .attrs = media_rc6_attrs, }, - { .name = power_group_name, .attrs = media_rc6_attrs, }, + { .name = power_group_name, .attrs = media_rc6_dev_attrs, }, }; static int __intel_gt_sysfs_create_group(struct kobject *kobj, @@ -271,104 +340,34 @@ static u32 __act_freq_mhz_show(struct intel_gt *gt) return intel_rps_read_actual_frequency(>->rps); } -static ssize_t act_freq_mhz_show(struct device *dev, - struct device_attribute *attr, char *buff) -{ - u32 actual_freq = sysfs_gt_attribute_r_max_func(dev, attr, - __act_freq_mhz_show); - - return sysfs_emit(buff, "%u\n", actual_freq); -} - static u32 __cur_freq_mhz_show(struct intel_gt *gt) { return intel_rps_get_requested_frequency(>->rps); } -static ssize_t cur_freq_mhz_show(struct device *dev, - struct device_attribute *attr, char *buff) -{ - u32 cur_freq = sysfs_gt_attribute_r_max_func(dev, attr, - __cur_freq_mhz_show); - - return sysfs_emit(buff, "%u\n", cur_freq); -} - static u32 __boost_freq_mhz_show(struct intel_gt *gt) { return intel_rps_get_boost_frequency(>->rps); } -static ssize_t boost_freq_mhz_show(struct device *dev, - struct device_attribute *attr, - char *buff) -{ - u32 boost_freq = sysfs_gt_attribute_r_max_func(dev, attr, - __boost_freq_mhz_show); - - return sysfs_emit(buff, "%u\n", boost_freq); -} - static int __boost_freq_mhz_store(struct intel_gt *gt, u32 val) { return intel_rps_set_boost_frequency(>->rps, val); } -static ssize_t boost_freq_mhz_store(struct device *dev, - struct device_attribute *attr, - const char *buff, size_t count) -{ - ssize_t ret; - u32 val; - - ret = kstrtou32(buff, 0, &val); - if (ret) - return ret; - - return sysfs_gt_attribute_w_func(dev, attr, - __boost_freq_mhz_store, val) ?: count; -} - -static u32 __rp0_freq_mhz_show(struct intel_gt *gt) +static u32 __RP0_freq_mhz_show(struct intel_gt *gt) { return intel_rps_get_rp0_frequency(>->rps); } -static ssize_t RP0_freq_mhz_show(struct device *dev, - struct device_attribute *attr, char *buff) -{ - u32 rp0_freq = sysfs_gt_attribute_r_max_func(dev, attr, - __rp0_freq_mhz_show); - - return sysfs_emit(buff, "%u\n", rp0_freq); -} - -static u32 __rp1_freq_mhz_show(struct intel_gt *gt) -{ - return intel_rps_get_rp1_frequency(>->rps); -} - -static ssize_t RP1_freq_mhz_show(struct device *dev, - struct device_attribute *attr, char *buff) -{ - u32 rp1_freq = sysfs_gt_attribute_r_max_func(dev, attr, - __rp1_freq_mhz_show); - - return sysfs_emit(buff, "%u\n", rp1_freq); -} - -static u32 __rpn_freq_mhz_show(struct intel_gt *gt) +static u32 __RPn_freq_mhz_show(struct intel_gt *gt) { return intel_rps_get_rpn_frequency(>->rps); } -static ssize_t RPn_freq_mhz_show(struct device *dev, - struct device_attribute *attr, char *buff) +static u32 __RP1_freq_mhz_show(struct intel_gt *gt) { - u32 rpn_freq = sysfs_gt_attribute_r_max_func(dev, attr, - __rpn_freq_mhz_show); - - return sysfs_emit(buff, "%u\n", rpn_freq); + return intel_rps_get_rp1_frequency(>->rps); } static u32 __max_freq_mhz_show(struct intel_gt *gt) @@ -376,71 +375,21 @@ static u32 __max_freq_mhz_show(struct intel_gt *gt) return intel_rps_get_max_frequency(>->rps); } -static ssize_t max_freq_mhz_show(struct device *dev, - struct device_attribute *attr, char *buff) -{ - u32 max_freq = sysfs_gt_attribute_r_max_func(dev, attr, - __max_freq_mhz_show); - - return sysfs_emit(buff, "%u\n", max_freq); -} - static int __set_max_freq(struct intel_gt *gt, u32 val) { return intel_rps_set_max_frequency(>->rps, val); } -static ssize_t max_freq_mhz_store(struct device *dev, - struct device_attribute *attr, - const char *buff, size_t count) -{ - int ret; - u32 val; - - ret = kstrtou32(buff, 0, &val); - if (ret) - return ret; - - ret = sysfs_gt_attribute_w_func(dev, attr, __set_max_freq, val); - - return ret ?: count; -} - static u32 __min_freq_mhz_show(struct intel_gt *gt) { return intel_rps_get_min_frequency(>->rps); } -static ssize_t min_freq_mhz_show(struct device *dev, - struct device_attribute *attr, char *buff) -{ - u32 min_freq = sysfs_gt_attribute_r_min_func(dev, attr, - __min_freq_mhz_show); - - return sysfs_emit(buff, "%u\n", min_freq); -} - static int __set_min_freq(struct intel_gt *gt, u32 val) { return intel_rps_set_min_frequency(>->rps, val); } -static ssize_t min_freq_mhz_store(struct device *dev, - struct device_attribute *attr, - const char *buff, size_t count) -{ - int ret; - u32 val; - - ret = kstrtou32(buff, 0, &val); - if (ret) - return ret; - - ret = sysfs_gt_attribute_w_func(dev, attr, __set_min_freq, val); - - return ret ?: count; -} - static u32 __vlv_rpe_freq_mhz_show(struct intel_gt *gt) { struct intel_rps *rps = >->rps; @@ -448,23 +397,31 @@ static u32 __vlv_rpe_freq_mhz_show(struct intel_gt *gt) return intel_gpu_freq(rps, rps->efficient_freq); } -static ssize_t vlv_rpe_freq_mhz_show(struct device *dev, - struct device_attribute *attr, char *buff) -{ - u32 rpe_freq = sysfs_gt_attribute_r_max_func(dev, attr, - __vlv_rpe_freq_mhz_show); - - return sysfs_emit(buff, "%u\n", rpe_freq); -} - -#define INTEL_GT_RPS_SYSFS_ATTR(_name, _mode, _show, _store) \ - static struct device_attribute dev_attr_gt_##_name = __ATTR(gt_##_name, _mode, _show, _store); \ - static struct device_attribute dev_attr_rps_##_name = __ATTR(rps_##_name, _mode, _show, _store) - -#define INTEL_GT_RPS_SYSFS_ATTR_RO(_name) \ - INTEL_GT_RPS_SYSFS_ATTR(_name, 0444, _name##_show, NULL) -#define INTEL_GT_RPS_SYSFS_ATTR_RW(_name) \ - INTEL_GT_RPS_SYSFS_ATTR(_name, 0644, _name##_show, _name##_store) +INTEL_GT_SYSFS_SHOW_MAX(act_freq_mhz); +INTEL_GT_SYSFS_SHOW_MAX(boost_freq_mhz); +INTEL_GT_SYSFS_SHOW_MAX(cur_freq_mhz); +INTEL_GT_SYSFS_SHOW_MAX(RP0_freq_mhz); +INTEL_GT_SYSFS_SHOW_MAX(RP1_freq_mhz); +INTEL_GT_SYSFS_SHOW_MAX(RPn_freq_mhz); +INTEL_GT_SYSFS_SHOW_MAX(max_freq_mhz); +INTEL_GT_SYSFS_SHOW_MIN(min_freq_mhz); +INTEL_GT_SYSFS_SHOW_MAX(vlv_rpe_freq_mhz); +INTEL_GT_SYSFS_STORE(boost_freq_mhz, __boost_freq_mhz_store); +INTEL_GT_SYSFS_STORE(max_freq_mhz, __set_max_freq); +INTEL_GT_SYSFS_STORE(min_freq_mhz, __set_min_freq); + +#define INTEL_GT_RPS_SYSFS_ATTR(_name, _mode, _show, _store, _show_dev, _store_dev) \ + static struct device_attribute dev_attr_gt_##_name = __ATTR(gt_##_name, _mode, \ + _show_dev, _store_dev); \ + static struct kobj_attribute attr_rps_##_name = __ATTR(rps_##_name, _mode, \ + _show, _store) + +#define INTEL_GT_RPS_SYSFS_ATTR_RO(_name) \ + INTEL_GT_RPS_SYSFS_ATTR(_name, 0444, _name##_show, NULL, \ + _name##_dev_show, NULL) +#define INTEL_GT_RPS_SYSFS_ATTR_RW(_name) \ + INTEL_GT_RPS_SYSFS_ATTR(_name, 0644, _name##_show, _name##_store, \ + _name##_dev_show, _name##_dev_store) /* The below macros generate static structures */ INTEL_GT_RPS_SYSFS_ATTR_RO(act_freq_mhz); @@ -475,32 +432,31 @@ INTEL_GT_RPS_SYSFS_ATTR_RO(RP1_freq_mhz); INTEL_GT_RPS_SYSFS_ATTR_RO(RPn_freq_mhz); INTEL_GT_RPS_SYSFS_ATTR_RW(max_freq_mhz); INTEL_GT_RPS_SYSFS_ATTR_RW(min_freq_mhz); - -static DEVICE_ATTR_RO(vlv_rpe_freq_mhz); - -#define GEN6_ATTR(s) { \ - &dev_attr_##s##_act_freq_mhz.attr, \ - &dev_attr_##s##_cur_freq_mhz.attr, \ - &dev_attr_##s##_boost_freq_mhz.attr, \ - &dev_attr_##s##_max_freq_mhz.attr, \ - &dev_attr_##s##_min_freq_mhz.attr, \ - &dev_attr_##s##_RP0_freq_mhz.attr, \ - &dev_attr_##s##_RP1_freq_mhz.attr, \ - &dev_attr_##s##_RPn_freq_mhz.attr, \ +INTEL_GT_RPS_SYSFS_ATTR_RO(vlv_rpe_freq_mhz); + +#define GEN6_ATTR(p, s) { \ + &p##attr_##s##_act_freq_mhz.attr, \ + &p##attr_##s##_cur_freq_mhz.attr, \ + &p##attr_##s##_boost_freq_mhz.attr, \ + &p##attr_##s##_max_freq_mhz.attr, \ + &p##attr_##s##_min_freq_mhz.attr, \ + &p##attr_##s##_RP0_freq_mhz.attr, \ + &p##attr_##s##_RP1_freq_mhz.attr, \ + &p##attr_##s##_RPn_freq_mhz.attr, \ NULL, \ } -#define GEN6_RPS_ATTR GEN6_ATTR(rps) -#define GEN6_GT_ATTR GEN6_ATTR(gt) +#define GEN6_RPS_ATTR GEN6_ATTR(, rps) +#define GEN6_GT_ATTR GEN6_ATTR(dev_, gt) static const struct attribute * const gen6_rps_attrs[] = GEN6_RPS_ATTR; static const struct attribute * const gen6_gt_attrs[] = GEN6_GT_ATTR; -static ssize_t punit_req_freq_mhz_show(struct device *dev, - struct device_attribute *attr, +static ssize_t punit_req_freq_mhz_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buff) { - struct intel_gt *gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name); + struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name); u32 preq = intel_rps_read_punit_req_frequency(>->rps); return sysfs_emit(buff, "%u\n", preq); @@ -508,20 +464,20 @@ static ssize_t punit_req_freq_mhz_show(struct device *dev, struct intel_gt_bool_throttle_attr { struct attribute attr; - ssize_t (*show)(struct device *dev, struct device_attribute *attr, + ssize_t (*show)(struct kobject *kobj, struct kobj_attribute *attr, char *buf); - i915_reg_t reg32; + i915_reg_t (*reg32)(struct intel_gt *gt); u32 mask; }; -static ssize_t throttle_reason_bool_show(struct device *dev, - struct device_attribute *attr, +static ssize_t throttle_reason_bool_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buff) { - struct intel_gt *gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name); + struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name); struct intel_gt_bool_throttle_attr *t_attr = (struct intel_gt_bool_throttle_attr *) attr; - bool val = rps_read_mask_mmio(>->rps, t_attr->reg32, t_attr->mask); + bool val = rps_read_mask_mmio(>->rps, t_attr->reg32(gt), t_attr->mask); return sysfs_emit(buff, "%u\n", val); } @@ -530,11 +486,11 @@ static ssize_t throttle_reason_bool_show(struct device *dev, struct intel_gt_bool_throttle_attr attr_##sysfs_func__ = { \ .attr = { .name = __stringify(sysfs_func__), .mode = 0444 }, \ .show = throttle_reason_bool_show, \ - .reg32 = GT0_PERF_LIMIT_REASONS, \ + .reg32 = intel_gt_perf_limit_reasons_reg, \ .mask = mask__, \ } -static DEVICE_ATTR_RO(punit_req_freq_mhz); +INTEL_GT_ATTR_RO(punit_req_freq_mhz); static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_status, GT0_PERF_LIMIT_REASONS_MASK); static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_pl1, POWER_LIMIT_1_MASK); static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_pl2, POWER_LIMIT_2_MASK); @@ -597,8 +553,8 @@ static const struct attribute *throttle_reason_attrs[] = { #define U8_8_VAL_MASK 0xffff #define U8_8_SCALE_TO_VALUE "0.00390625" -static ssize_t freq_factor_scale_show(struct device *dev, - struct device_attribute *attr, +static ssize_t freq_factor_scale_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buff) { return sysfs_emit(buff, "%s\n", U8_8_SCALE_TO_VALUE); @@ -610,11 +566,11 @@ static u32 media_ratio_mode_to_factor(u32 mode) return !mode ? mode : 256 / mode; } -static ssize_t media_freq_factor_show(struct device *dev, - struct device_attribute *attr, +static ssize_t media_freq_factor_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buff) { - struct intel_gt *gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name); + struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name); struct intel_guc_slpc *slpc = >->uc.guc.slpc; intel_wakeref_t wakeref; u32 mode; @@ -641,11 +597,11 @@ static ssize_t media_freq_factor_show(struct device *dev, return sysfs_emit(buff, "%u\n", media_ratio_mode_to_factor(mode)); } -static ssize_t media_freq_factor_store(struct device *dev, - struct device_attribute *attr, +static ssize_t media_freq_factor_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buff, size_t count) { - struct intel_gt *gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name); + struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name); struct intel_guc_slpc *slpc = >->uc.guc.slpc; u32 factor, mode; int err; @@ -670,11 +626,11 @@ static ssize_t media_freq_factor_store(struct device *dev, return err ?: count; } -static ssize_t media_RP0_freq_mhz_show(struct device *dev, - struct device_attribute *attr, +static ssize_t media_RP0_freq_mhz_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buff) { - struct intel_gt *gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name); + struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name); u32 val; int err; @@ -691,11 +647,11 @@ static ssize_t media_RP0_freq_mhz_show(struct device *dev, return sysfs_emit(buff, "%u\n", val); } -static ssize_t media_RPn_freq_mhz_show(struct device *dev, - struct device_attribute *attr, +static ssize_t media_RPn_freq_mhz_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buff) { - struct intel_gt *gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name); + struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name); u32 val; int err; @@ -712,17 +668,17 @@ static ssize_t media_RPn_freq_mhz_show(struct device *dev, return sysfs_emit(buff, "%u\n", val); } -static DEVICE_ATTR_RW(media_freq_factor); -static struct device_attribute dev_attr_media_freq_factor_scale = +INTEL_GT_ATTR_RW(media_freq_factor); +static struct kobj_attribute attr_media_freq_factor_scale = __ATTR(media_freq_factor.scale, 0444, freq_factor_scale_show, NULL); -static DEVICE_ATTR_RO(media_RP0_freq_mhz); -static DEVICE_ATTR_RO(media_RPn_freq_mhz); +INTEL_GT_ATTR_RO(media_RP0_freq_mhz); +INTEL_GT_ATTR_RO(media_RPn_freq_mhz); static const struct attribute *media_perf_power_attrs[] = { - &dev_attr_media_freq_factor.attr, - &dev_attr_media_freq_factor_scale.attr, - &dev_attr_media_RP0_freq_mhz.attr, - &dev_attr_media_RPn_freq_mhz.attr, + &attr_media_freq_factor.attr, + &attr_media_freq_factor_scale.attr, + &attr_media_RP0_freq_mhz.attr, + &attr_media_RPn_freq_mhz.attr, NULL }; @@ -754,20 +710,29 @@ static const struct attribute * const rps_defaults_attrs[] = { NULL }; -static int intel_sysfs_rps_init(struct intel_gt *gt, struct kobject *kobj, - const struct attribute * const *attrs) +static int intel_sysfs_rps_init(struct intel_gt *gt, struct kobject *kobj) { + const struct attribute * const *attrs; + struct attribute *vlv_attr; int ret; if (GRAPHICS_VER(gt->i915) < 6) return 0; + if (is_object_gt(kobj)) { + attrs = gen6_rps_attrs; + vlv_attr = &attr_rps_vlv_rpe_freq_mhz.attr; + } else { + attrs = gen6_gt_attrs; + vlv_attr = &dev_attr_gt_vlv_rpe_freq_mhz.attr; + } + ret = sysfs_create_files(kobj, attrs); if (ret) return ret; if (IS_VALLEYVIEW(gt->i915) || IS_CHERRYVIEW(gt->i915)) - ret = sysfs_create_file(kobj, &dev_attr_vlv_rpe_freq_mhz.attr); + ret = sysfs_create_file(kobj, vlv_attr); return ret; } @@ -778,9 +743,7 @@ void intel_gt_sysfs_pm_init(struct intel_gt *gt, struct kobject *kobj) intel_sysfs_rc6_init(gt, kobj); - ret = is_object_gt(kobj) ? - intel_sysfs_rps_init(gt, kobj, gen6_rps_attrs) : - intel_sysfs_rps_init(gt, kobj, gen6_gt_attrs); + ret = intel_sysfs_rps_init(gt, kobj); if (ret) drm_warn(>->i915->drm, "failed to create gt%u RPS sysfs files (%pe)", @@ -790,13 +753,13 @@ void intel_gt_sysfs_pm_init(struct intel_gt *gt, struct kobject *kobj) if (!is_object_gt(kobj)) return; - ret = sysfs_create_file(kobj, &dev_attr_punit_req_freq_mhz.attr); + ret = sysfs_create_file(kobj, &attr_punit_req_freq_mhz.attr); if (ret) drm_warn(>->i915->drm, "failed to create gt%u punit_req_freq_mhz sysfs (%pe)", gt->info.id, ERR_PTR(ret)); - if (GRAPHICS_VER(gt->i915) >= 11) { + if (i915_mmio_reg_valid(intel_gt_perf_limit_reasons_reg(gt))) { ret = sysfs_create_files(kobj, throttle_reason_attrs); if (ret) drm_warn(>->i915->drm, diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h index f19c2de77ff6..c1d9cd255e06 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_types.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h @@ -20,6 +20,7 @@ #include "intel_gsc.h" #include "i915_vma.h" +#include "i915_perf_types.h" #include "intel_engine_types.h" #include "intel_gt_buffer_pool_types.h" #include "intel_hwconfig.h" @@ -30,6 +31,7 @@ #include "intel_migrate_types.h" #include "intel_wakeref.h" #include "pxp/intel_pxp_types.h" +#include "intel_wopcm.h" struct drm_i915_private; struct i915_ggtt; @@ -59,6 +61,9 @@ enum intel_steering_type { L3BANK, MSLICE, LNCF, + GAM, + DSS, + OADDRM, /* * On some platforms there are multiple types of MCR registers that @@ -97,6 +102,7 @@ struct intel_gt { struct intel_uc uc; struct intel_gsc gsc; + struct intel_wopcm wopcm; struct { /* Serialize global tlb invalidations */ @@ -141,20 +147,6 @@ struct intel_gt { struct intel_wakeref wakeref; atomic_t user_wakeref; - /** - * Protects access to lmem usefault list. - * It is required, if we are outside of the runtime suspend path, - * access to @lmem_userfault_list requires always first grabbing the - * runtime pm, to ensure we can't race against runtime suspend. - * Once we have that we also need to grab @lmem_userfault_lock, - * at which point we have exclusive access. - * The runtime suspend path is special since it doesn't really hold any locks, - * but instead has exclusive access by virtue of all other accesses requiring - * holding the runtime pm wakeref. - */ - struct mutex lmem_userfault_lock; - struct list_head lmem_userfault_list; - struct list_head closed_vma; spinlock_t closed_lock; /* guards the list of closed_vma */ @@ -170,9 +162,6 @@ struct intel_gt { */ intel_wakeref_t awake; - /* Manual runtime pm autosuspend delay for user GGTT/lmem mmaps */ - struct intel_wakeref_auto userfault_wakeref; - u32 clock_frequency; u32 clock_period_ns; @@ -286,6 +275,8 @@ struct intel_gt { /* sysfs defaults per gt */ struct gt_defaults defaults; struct kobject *sysfs_defaults; + + struct i915_perf_gt perf; }; struct intel_gt_definition { diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c index 2eaeba14319e..2ba3983984b9 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.c +++ b/drivers/gpu/drm/i915/gt/intel_gtt.c @@ -12,9 +12,11 @@ #include "gem/i915_gem_internal.h" #include "gem/i915_gem_lmem.h" +#include "i915_reg.h" #include "i915_trace.h" #include "i915_utils.h" #include "intel_gt.h" +#include "intel_gt_mcr.h" #include "intel_gt_regs.h" #include "intel_gtt.h" @@ -269,11 +271,7 @@ void i915_address_space_init(struct i915_address_space *vm, int subclass) memset64(vm->min_alignment, I915_GTT_MIN_ALIGNMENT, ARRAY_SIZE(vm->min_alignment)); - if (HAS_64K_PAGES(vm->i915) && NEEDS_COMPACT_PT(vm->i915) && - subclass == VM_CLASS_PPGTT) { - vm->min_alignment[INTEL_MEMORY_LOCAL] = I915_GTT_PAGE_SIZE_2M; - vm->min_alignment[INTEL_MEMORY_STOLEN_LOCAL] = I915_GTT_PAGE_SIZE_2M; - } else if (HAS_64K_PAGES(vm->i915)) { + if (HAS_64K_PAGES(vm->i915)) { vm->min_alignment[INTEL_MEMORY_LOCAL] = I915_GTT_PAGE_SIZE_64K; vm->min_alignment[INTEL_MEMORY_STOLEN_LOCAL] = I915_GTT_PAGE_SIZE_64K; } @@ -343,7 +341,8 @@ int setup_scratch_page(struct i915_address_space *vm) */ size = I915_GTT_PAGE_SIZE_4K; if (i915_vm_is_4lvl(vm) && - HAS_PAGE_SIZES(vm->i915, I915_GTT_PAGE_SIZE_64K)) + HAS_PAGE_SIZES(vm->i915, I915_GTT_PAGE_SIZE_64K) && + !HAS_64K_PAGES(vm->i915)) size = I915_GTT_PAGE_SIZE_64K; do { @@ -385,18 +384,6 @@ skip: if (size == I915_GTT_PAGE_SIZE_4K) return -ENOMEM; - /* - * If we need 64K minimum GTT pages for device local-memory, - * like on XEHPSDV, then we need to fail the allocation here, - * otherwise we can't safely support the insertion of - * local-memory pages for this vm, since the HW expects the - * correct physical alignment and size when the page-table is - * operating in 64K GTT mode, which includes any scratch PTEs, - * since userspace can still touch them. - */ - if (HAS_64K_PAGES(vm->i915)) - return -ENOMEM; - size = I915_GTT_PAGE_SIZE_4K; } while (1); } @@ -493,6 +480,18 @@ static void tgl_setup_private_ppat(struct intel_uncore *uncore) intel_uncore_write(uncore, GEN12_PAT_INDEX(7), GEN8_PPAT_WB); } +static void xehp_setup_private_ppat(struct intel_gt *gt) +{ + intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(0), GEN8_PPAT_WB); + intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(1), GEN8_PPAT_WC); + intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(2), GEN8_PPAT_WT); + intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(3), GEN8_PPAT_UC); + intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(4), GEN8_PPAT_WB); + intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(5), GEN8_PPAT_WB); + intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(6), GEN8_PPAT_WB); + intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(7), GEN8_PPAT_WB); +} + static void icl_setup_private_ppat(struct intel_uncore *uncore) { intel_uncore_write(uncore, @@ -585,13 +584,16 @@ static void chv_setup_private_ppat(struct intel_uncore *uncore) intel_uncore_write(uncore, GEN8_PRIVATE_PAT_HI, upper_32_bits(pat)); } -void setup_private_pat(struct intel_uncore *uncore) +void setup_private_pat(struct intel_gt *gt) { - struct drm_i915_private *i915 = uncore->i915; + struct intel_uncore *uncore = gt->uncore; + struct drm_i915_private *i915 = gt->i915; GEM_BUG_ON(GRAPHICS_VER(i915) < 8); - if (GRAPHICS_VER(i915) >= 12) + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) + xehp_setup_private_ppat(gt); + else if (GRAPHICS_VER(i915) >= 12) tgl_setup_private_ppat(uncore); else if (GRAPHICS_VER(i915) >= 11) icl_setup_private_ppat(uncore); diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h index c0ca53cba9f0..4d75ba4bb41d 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.h +++ b/drivers/gpu/drm/i915/gt/intel_gtt.h @@ -93,6 +93,7 @@ typedef u64 gen8_pte_t; #define GEN12_GGTT_PTE_LM BIT_ULL(1) #define GEN12_PDE_64K BIT(6) +#define GEN12_PTE_PS64 BIT(8) /* * Cacheability Control is a 4-bit value. The low three bits are stored in bits @@ -667,7 +668,7 @@ void ppgtt_unbind_vma(struct i915_address_space *vm, void gtt_write_workarounds(struct intel_gt *gt); -void setup_private_pat(struct intel_uncore *uncore); +void setup_private_pat(struct intel_gt *gt); int i915_vm_alloc_pt_stash(struct i915_address_space *vm, struct i915_vm_pt_stash *stash, diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 3955292483a6..7771a19008c6 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -20,6 +20,30 @@ #include "intel_ring.h" #include "shmem_utils.h" +/* + * The per-platform tables are u8-encoded in @data. Decode @data and set the + * addresses' offset and commands in @regs. The following encoding is used + * for each byte. There are 2 steps: decoding commands and decoding addresses. + * + * Commands: + * [7]: create NOPs - number of NOPs are set in lower bits + * [6]: When creating MI_LOAD_REGISTER_IMM command, allow to set + * MI_LRI_FORCE_POSTED + * [5:0]: Number of NOPs or registers to set values to in case of + * MI_LOAD_REGISTER_IMM + * + * Addresses: these are decoded after a MI_LOAD_REGISTER_IMM command by "count" + * number of registers. They are set by using the REG/REG16 macros: the former + * is used for offsets smaller than 0x200 while the latter is for values bigger + * than that. Those macros already set all the bits documented below correctly: + * + * [7]: When a register offset needs more than 6 bits, use additional bytes, to + * follow, for the lower bits + * [6:0]: Register offset, without considering the engine base. + * + * This function only tweaks the commands and register offsets. Values are not + * filled out. + */ static void set_offsets(u32 *regs, const u8 *data, const struct intel_engine_cs *engine, @@ -264,6 +288,39 @@ static const u8 dg2_xcs_offsets[] = { END }; +static const u8 mtl_xcs_offsets[] = { + NOP(1), + LRI(13, POSTED), + REG16(0x244), + REG(0x034), + REG(0x030), + REG(0x038), + REG(0x03c), + REG(0x168), + REG(0x140), + REG(0x110), + REG(0x1c0), + REG(0x1c4), + REG(0x1c8), + REG(0x180), + REG16(0x2b4), + NOP(4), + + NOP(1), + LRI(9, POSTED), + REG16(0x3a8), + REG16(0x28c), + REG16(0x288), + REG16(0x284), + REG16(0x280), + REG16(0x27c), + REG16(0x278), + REG16(0x274), + REG16(0x270), + + END +}; + static const u8 gen8_rcs_offsets[] = { NOP(1), LRI(14, POSTED), @@ -606,6 +663,49 @@ static const u8 dg2_rcs_offsets[] = { END }; +static const u8 mtl_rcs_offsets[] = { + NOP(1), + LRI(15, POSTED), + REG16(0x244), + REG(0x034), + REG(0x030), + REG(0x038), + REG(0x03c), + REG(0x168), + REG(0x140), + REG(0x110), + REG(0x1c0), + REG(0x1c4), + REG(0x1c8), + REG(0x180), + REG16(0x2b4), + REG(0x120), + REG(0x124), + + NOP(1), + LRI(9, POSTED), + REG16(0x3a8), + REG16(0x28c), + REG16(0x288), + REG16(0x284), + REG16(0x280), + REG16(0x27c), + REG16(0x278), + REG16(0x274), + REG16(0x270), + + NOP(2), + LRI(2, POSTED), + REG16(0x5a8), + REG16(0x5ac), + + NOP(6), + LRI(1, 0), + REG(0x0c8), + + END +}; + #undef END #undef REG16 #undef REG @@ -624,7 +724,9 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine) !intel_engine_has_relative_mmio(engine)); if (engine->flags & I915_ENGINE_HAS_RCS_REG_STATE) { - if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55)) + if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 70)) + return mtl_rcs_offsets; + else if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55)) return dg2_rcs_offsets; else if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50)) return xehp_rcs_offsets; @@ -637,7 +739,9 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine) else return gen8_rcs_offsets; } else { - if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55)) + if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 70)) + return mtl_xcs_offsets; + else if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55)) return dg2_xcs_offsets; else if (GRAPHICS_VER(engine->i915) >= 12) return gen12_xcs_offsets; @@ -745,19 +849,18 @@ static int lrc_ring_cmd_buf_cctl(const struct intel_engine_cs *engine) static u32 lrc_ring_indirect_offset_default(const struct intel_engine_cs *engine) { - switch (GRAPHICS_VER(engine->i915)) { - default: - MISSING_CASE(GRAPHICS_VER(engine->i915)); - fallthrough; - case 12: + if (GRAPHICS_VER(engine->i915) >= 12) return GEN12_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT; - case 11: + else if (GRAPHICS_VER(engine->i915) >= 11) return GEN11_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT; - case 9: + else if (GRAPHICS_VER(engine->i915) >= 9) return GEN9_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT; - case 8: + else if (GRAPHICS_VER(engine->i915) >= 8) return GEN8_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT; - } + + GEM_BUG_ON(GRAPHICS_VER(engine->i915) < 8); + + return 0; } static void @@ -1012,7 +1115,7 @@ __lrc_alloc_state(struct intel_context *ce, struct intel_engine_cs *engine) if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)) context_size += I915_GTT_PAGE_SIZE; /* for redzone */ - if (GRAPHICS_VER(engine->i915) == 12) { + if (GRAPHICS_VER(engine->i915) >= 12) { ce->wa_bb_page = context_size / PAGE_SIZE; context_size += PAGE_SIZE; } @@ -1718,24 +1821,16 @@ void lrc_init_wa_ctx(struct intel_engine_cs *engine) unsigned int i; int err; - if (!(engine->flags & I915_ENGINE_HAS_RCS_REG_STATE)) + if (GRAPHICS_VER(engine->i915) >= 11 || + !(engine->flags & I915_ENGINE_HAS_RCS_REG_STATE)) return; - switch (GRAPHICS_VER(engine->i915)) { - case 12: - case 11: - return; - case 9: + if (GRAPHICS_VER(engine->i915) == 9) { wa_bb_fn[0] = gen9_init_indirectctx_bb; wa_bb_fn[1] = NULL; - break; - case 8: + } else if (GRAPHICS_VER(engine->i915) == 8) { wa_bb_fn[0] = gen8_init_indirectctx_bb; wa_bb_fn[1] = NULL; - break; - default: - MISSING_CASE(GRAPHICS_VER(engine->i915)); - return; } err = lrc_create_wa_ctx(engine); diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.h b/drivers/gpu/drm/i915/gt/intel_lrc.h index a390f0813c8b..7111bae759f3 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.h +++ b/drivers/gpu/drm/i915/gt/intel_lrc.h @@ -110,6 +110,8 @@ enum { #define XEHP_SW_CTX_ID_WIDTH 16 #define XEHP_SW_COUNTER_SHIFT 58 #define XEHP_SW_COUNTER_WIDTH 6 +#define GEN12_GUC_SW_CTX_ID_SHIFT 39 +#define GEN12_GUC_SW_CTX_ID_WIDTH 16 static inline void lrc_runtime_start(struct intel_context *ce) { diff --git a/drivers/gpu/drm/i915/gt/intel_migrate.c b/drivers/gpu/drm/i915/gt/intel_migrate.c index aaaf1906026c..5fb74e71f27b 100644 --- a/drivers/gpu/drm/i915/gt/intel_migrate.c +++ b/drivers/gpu/drm/i915/gt/intel_migrate.c @@ -10,6 +10,7 @@ #include "intel_gtt.h" #include "intel_migrate.h" #include "intel_ring.h" +#include "gem/i915_gem_lmem.h" struct insert_pte_data { u64 offset; @@ -341,6 +342,16 @@ static int emit_no_arbitration(struct i915_request *rq) return 0; } +static int max_pte_pkt_size(struct i915_request *rq, int pkt) +{ + struct intel_ring *ring = rq->ring; + + pkt = min_t(int, pkt, (ring->space - rq->reserved_space) / sizeof(u32) + 5); + pkt = min_t(int, pkt, (ring->size - ring->emit) / sizeof(u32) + 5); + + return pkt; +} + static int emit_pte(struct i915_request *rq, struct sgt_dma *it, enum i915_cache_level cache_level, @@ -387,8 +398,7 @@ static int emit_pte(struct i915_request *rq, return PTR_ERR(cs); /* Pack as many PTE updates as possible into a single MI command */ - pkt = min_t(int, dword_length, ring->space / sizeof(u32) + 5); - pkt = min_t(int, pkt, (ring->size - ring->emit) / sizeof(u32) + 5); + pkt = max_pte_pkt_size(rq, dword_length); hdr = cs; *cs++ = MI_STORE_DATA_IMM | REG_BIT(21); /* as qword elements */ @@ -421,8 +431,7 @@ static int emit_pte(struct i915_request *rq, } } - pkt = min_t(int, dword_rem, ring->space / sizeof(u32) + 5); - pkt = min_t(int, pkt, (ring->size - ring->emit) / sizeof(u32) + 5); + pkt = max_pte_pkt_size(rq, dword_rem); hdr = cs; *cs++ = MI_STORE_DATA_IMM | REG_BIT(21); @@ -828,14 +837,35 @@ intel_context_migrate_copy(struct intel_context *ce, if (err) goto out_rq; - /* - * While we can't always restore/manage the CCS state, - * we still need to ensure we don't leak the CCS state - * from the previous user, so make sure we overwrite it - * with something. - */ - err = emit_copy_ccs(rq, dst_offset, INDIRECT_ACCESS, - dst_offset, DIRECT_ACCESS, len); + if (src_is_lmem) { + /* + * If the src is already in lmem, then we must + * be doing an lmem -> lmem transfer, and so + * should be safe to directly copy the CCS + * state. In this case we have either + * initialised the CCS aux state when first + * clearing the pages (since it is already + * allocated in lmem), or the user has + * potentially populated it, in which case we + * need to copy the CCS state as-is. + */ + err = emit_copy_ccs(rq, + dst_offset, INDIRECT_ACCESS, + src_offset, INDIRECT_ACCESS, + len); + } else { + /* + * While we can't always restore/manage the CCS + * state, we still need to ensure we don't leak + * the CCS state from the previous user, so make + * sure we overwrite it with something. + */ + err = emit_copy_ccs(rq, + dst_offset, INDIRECT_ACCESS, + dst_offset, DIRECT_ACCESS, + len); + } + if (err) goto out_rq; diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c index 152244d7f62a..49fdd509527a 100644 --- a/drivers/gpu/drm/i915/gt/intel_mocs.c +++ b/drivers/gpu/drm/i915/gt/intel_mocs.c @@ -7,6 +7,7 @@ #include "intel_engine.h" #include "intel_gt.h" +#include "intel_gt_mcr.h" #include "intel_gt_regs.h" #include "intel_mocs.h" #include "intel_ring.h" @@ -609,14 +610,17 @@ static u32 l3cc_combine(u16 low, u16 high) 0; \ i++) -static void init_l3cc_table(struct intel_uncore *uncore, +static void init_l3cc_table(struct intel_gt *gt, const struct drm_i915_mocs_table *table) { unsigned int i; u32 l3cc; for_each_l3cc(l3cc, table, i) - intel_uncore_write_fw(uncore, GEN9_LNCFCMOCS(i), l3cc); + if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 50)) + intel_gt_mcr_multicast_write_fw(gt, XEHP_LNCFCMOCS(i), l3cc); + else + intel_uncore_write_fw(gt->uncore, GEN9_LNCFCMOCS(i), l3cc); } void intel_mocs_init_engine(struct intel_engine_cs *engine) @@ -636,7 +640,7 @@ void intel_mocs_init_engine(struct intel_engine_cs *engine) init_mocs_table(engine, &table); if (flags & HAS_RENDER_L3CC && engine->class == RENDER_CLASS) - init_l3cc_table(engine->uncore, &table); + init_l3cc_table(engine->gt, &table); } static u32 global_mocs_offset(void) @@ -672,7 +676,7 @@ void intel_mocs_init(struct intel_gt *gt) * memory transactions including guc transactions */ if (flags & HAS_RENDER_L3CC) - init_l3cc_table(gt->uncore, &table); + init_l3cc_table(gt, &table); } #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c index f8d0523f4c18..2ee4051e4d96 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6.c +++ b/drivers/gpu/drm/i915/gt/intel_rc6.c @@ -551,6 +551,23 @@ static void __intel_rc6_disable(struct intel_rc6 *rc6) intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL); } +static void rc6_res_reg_init(struct intel_rc6 *rc6) +{ + memset(rc6->res_reg, INVALID_MMIO_REG.reg, sizeof(rc6->res_reg)); + + switch (rc6_to_gt(rc6)->type) { + case GT_MEDIA: + rc6->res_reg[INTEL_RC6_RES_RC6] = MTL_MEDIA_MC6; + break; + default: + rc6->res_reg[INTEL_RC6_RES_RC6_LOCKED] = GEN6_GT_GFX_RC6_LOCKED; + rc6->res_reg[INTEL_RC6_RES_RC6] = GEN6_GT_GFX_RC6; + rc6->res_reg[INTEL_RC6_RES_RC6p] = GEN6_GT_GFX_RC6p; + rc6->res_reg[INTEL_RC6_RES_RC6pp] = GEN6_GT_GFX_RC6pp; + break; + } +} + void intel_rc6_init(struct intel_rc6 *rc6) { struct drm_i915_private *i915 = rc6_to_i915(rc6); @@ -562,6 +579,8 @@ void intel_rc6_init(struct intel_rc6 *rc6) if (!rc6_supported(rc6)) return; + rc6_res_reg_init(rc6); + if (IS_CHERRYVIEW(i915)) err = chv_rc6_init(rc6); else if (IS_VALLEYVIEW(i915)) @@ -736,31 +755,19 @@ static u64 vlv_residency_raw(struct intel_uncore *uncore, const i915_reg_t reg) return lower | (u64)upper << 8; } -u64 intel_rc6_residency_ns(struct intel_rc6 *rc6, const i915_reg_t reg) +u64 intel_rc6_residency_ns(struct intel_rc6 *rc6, enum intel_rc6_res_type id) { struct drm_i915_private *i915 = rc6_to_i915(rc6); struct intel_uncore *uncore = rc6_to_uncore(rc6); u64 time_hw, prev_hw, overflow_hw; + i915_reg_t reg = rc6->res_reg[id]; unsigned int fw_domains; unsigned long flags; - unsigned int i; u32 mul, div; if (!rc6->supported) return 0; - /* - * Store previous hw counter values for counter wrap-around handling. - * - * There are only four interesting registers and they live next to each - * other so we can use the relative address, compared to the smallest - * one as the index into driver storage. - */ - i = (i915_mmio_reg_offset(reg) - - i915_mmio_reg_offset(GEN6_GT_GFX_RC6_LOCKED)) / sizeof(u32); - if (drm_WARN_ON_ONCE(&i915->drm, i >= ARRAY_SIZE(rc6->cur_residency))) - return 0; - fw_domains = intel_uncore_forcewake_for_reg(uncore, reg, FW_REG_READ); spin_lock_irqsave(&uncore->lock, flags); @@ -789,11 +796,11 @@ u64 intel_rc6_residency_ns(struct intel_rc6 *rc6, const i915_reg_t reg) /* * Counter wrap handling. * - * But relying on a sufficient frequency of queries otherwise counters - * can still wrap. + * Store previous hw counter values for counter wrap-around handling. But + * relying on a sufficient frequency of queries otherwise counters can still wrap. */ - prev_hw = rc6->prev_hw_residency[i]; - rc6->prev_hw_residency[i] = time_hw; + prev_hw = rc6->prev_hw_residency[id]; + rc6->prev_hw_residency[id] = time_hw; /* RC6 delta from last sample. */ if (time_hw >= prev_hw) @@ -802,8 +809,8 @@ u64 intel_rc6_residency_ns(struct intel_rc6 *rc6, const i915_reg_t reg) time_hw += overflow_hw - prev_hw; /* Add delta to RC6 extended raw driver copy. */ - time_hw += rc6->cur_residency[i]; - rc6->cur_residency[i] = time_hw; + time_hw += rc6->cur_residency[id]; + rc6->cur_residency[id] = time_hw; intel_uncore_forcewake_put__locked(uncore, fw_domains); spin_unlock_irqrestore(&uncore->lock, flags); @@ -811,9 +818,22 @@ u64 intel_rc6_residency_ns(struct intel_rc6 *rc6, const i915_reg_t reg) return mul_u64_u32_div(time_hw, mul, div); } -u64 intel_rc6_residency_us(struct intel_rc6 *rc6, i915_reg_t reg) +u64 intel_rc6_residency_us(struct intel_rc6 *rc6, enum intel_rc6_res_type id) +{ + return DIV_ROUND_UP_ULL(intel_rc6_residency_ns(rc6, id), 1000); +} + +void intel_rc6_print_residency(struct seq_file *m, const char *title, + enum intel_rc6_res_type id) { - return DIV_ROUND_UP_ULL(intel_rc6_residency_ns(rc6, reg), 1000); + struct intel_gt *gt = m->private; + i915_reg_t reg = gt->rc6.res_reg[id]; + intel_wakeref_t wakeref; + + with_intel_runtime_pm(gt->uncore->rpm, wakeref) + seq_printf(m, "%s %u (%llu us)\n", title, + intel_uncore_read(gt->uncore, reg), + intel_rc6_residency_us(>->rc6, id)); } #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.h b/drivers/gpu/drm/i915/gt/intel_rc6.h index b6fea71afc22..456fa668a276 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6.h +++ b/drivers/gpu/drm/i915/gt/intel_rc6.h @@ -6,10 +6,11 @@ #ifndef INTEL_RC6_H #define INTEL_RC6_H -#include "i915_reg_defs.h" +#include <linux/types.h> -struct intel_engine_cs; +enum intel_rc6_res_type; struct intel_rc6; +struct seq_file; void intel_rc6_init(struct intel_rc6 *rc6); void intel_rc6_fini(struct intel_rc6 *rc6); @@ -21,7 +22,9 @@ void intel_rc6_sanitize(struct intel_rc6 *rc6); void intel_rc6_enable(struct intel_rc6 *rc6); void intel_rc6_disable(struct intel_rc6 *rc6); -u64 intel_rc6_residency_ns(struct intel_rc6 *rc6, i915_reg_t reg); -u64 intel_rc6_residency_us(struct intel_rc6 *rc6, i915_reg_t reg); +u64 intel_rc6_residency_ns(struct intel_rc6 *rc6, enum intel_rc6_res_type id); +u64 intel_rc6_residency_us(struct intel_rc6 *rc6, enum intel_rc6_res_type id); +void intel_rc6_print_residency(struct seq_file *m, const char *title, + enum intel_rc6_res_type id); #endif /* INTEL_RC6_H */ diff --git a/drivers/gpu/drm/i915/gt/intel_rc6_types.h b/drivers/gpu/drm/i915/gt/intel_rc6_types.h index e747492b2f46..fa23c4dce00b 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6_types.h +++ b/drivers/gpu/drm/i915/gt/intel_rc6_types.h @@ -13,9 +13,20 @@ struct drm_i915_gem_object; +/* RC6 residency types */ +enum intel_rc6_res_type { + INTEL_RC6_RES_RC6_LOCKED, + INTEL_RC6_RES_RC6, + INTEL_RC6_RES_RC6p, + INTEL_RC6_RES_RC6pp, + INTEL_RC6_RES_MAX, + INTEL_RC6_RES_VLV_MEDIA = INTEL_RC6_RES_RC6p, +}; + struct intel_rc6 { - u64 prev_hw_residency[4]; - u64 cur_residency[4]; + i915_reg_t res_reg[INTEL_RC6_RES_MAX]; + u64 prev_hw_residency[INTEL_RC6_RES_MAX]; + u64 cur_residency[INTEL_RC6_RES_MAX]; u32 ctl_enable; diff --git a/drivers/gpu/drm/i915/gt/intel_renderstate.c b/drivers/gpu/drm/i915/gt/intel_renderstate.c index 5121e6dc2fa5..9c1ae070ee7b 100644 --- a/drivers/gpu/drm/i915/gt/intel_renderstate.c +++ b/drivers/gpu/drm/i915/gt/intel_renderstate.c @@ -215,9 +215,7 @@ int intel_renderstate_emit(struct intel_renderstate *so, if (!so->vma) return 0; - err = i915_request_await_object(rq, so->vma->obj, false); - if (err == 0) - err = i915_vma_move_to_active(so->vma, rq, 0); + err = i915_vma_move_to_active(so->vma, rq, 0); if (err) return err; diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index b36674356986..24736ebee17c 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -1278,7 +1278,7 @@ static void intel_gt_reset_global(struct intel_gt *gt, kobject_uevent_env(kobj, KOBJ_CHANGE, reset_event); /* Use a watchdog to ensure that our reset completes */ - intel_wedge_on_timeout(&w, gt, 5 * HZ) { + intel_wedge_on_timeout(&w, gt, 60 * HZ) { intel_display_prepare_reset(gt->i915); intel_gt_reset(gt, engine_mask, reason); @@ -1407,15 +1407,19 @@ out: intel_runtime_pm_put(gt->uncore->rpm, wakeref); } -int intel_gt_reset_trylock(struct intel_gt *gt, int *srcu) +static int _intel_gt_reset_lock(struct intel_gt *gt, int *srcu, bool retry) { might_lock(>->reset.backoff_srcu); - might_sleep(); + if (retry) + might_sleep(); rcu_read_lock(); while (test_bit(I915_RESET_BACKOFF, >->reset.flags)) { rcu_read_unlock(); + if (!retry) + return -EBUSY; + if (wait_event_interruptible(gt->reset.queue, !test_bit(I915_RESET_BACKOFF, >->reset.flags))) @@ -1429,6 +1433,16 @@ int intel_gt_reset_trylock(struct intel_gt *gt, int *srcu) return 0; } +int intel_gt_reset_trylock(struct intel_gt *gt, int *srcu) +{ + return _intel_gt_reset_lock(gt, srcu, false); +} + +int intel_gt_reset_lock_interruptible(struct intel_gt *gt, int *srcu) +{ + return _intel_gt_reset_lock(gt, srcu, true); +} + void intel_gt_reset_unlock(struct intel_gt *gt, int tag) __releases(>->reset.backoff_srcu) { diff --git a/drivers/gpu/drm/i915/gt/intel_reset.h b/drivers/gpu/drm/i915/gt/intel_reset.h index adc734e67387..25c975b6e8fc 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.h +++ b/drivers/gpu/drm/i915/gt/intel_reset.h @@ -39,6 +39,7 @@ int __intel_engine_reset_bh(struct intel_engine_cs *engine, void __i915_request_reset(struct i915_request *rq, bool guilty); int __must_check intel_gt_reset_trylock(struct intel_gt *gt, int *srcu); +int __must_check intel_gt_reset_lock_interruptible(struct intel_gt *gt, int *srcu); void intel_gt_reset_unlock(struct intel_gt *gt, int tag); void intel_gt_set_wedged(struct intel_gt *gt); diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c index d5d6f1fadcae..356c787e11d3 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c @@ -12,7 +12,9 @@ #include "gen6_ppgtt.h" #include "gen7_renderclear.h" #include "i915_drv.h" +#include "i915_irq.h" #include "i915_mitigations.h" +#include "i915_reg.h" #include "intel_breadcrumbs.h" #include "intel_context.h" #include "intel_engine_regs.h" diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index 6b86250c31ab..9ad3bc7201cb 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -430,7 +430,8 @@ static int __gen5_rps_set(struct intel_rps *rps, u8 val) rgvswctl = intel_uncore_read16(uncore, MEMSWCTL); if (rgvswctl & MEMCTL_CMD_STS) { - DRM_DEBUG("gpu busy, RCS change rejected\n"); + drm_dbg(&rps_to_i915(rps)->drm, + "gpu busy, RCS change rejected\n"); return -EBUSY; /* still busy with another command */ } @@ -625,9 +626,7 @@ static void gen5_rps_disable(struct intel_rps *rps) rgvswctl = intel_uncore_read16(uncore, MEMSWCTL); /* Ack interrupts, disable EFC interrupt */ - intel_uncore_write(uncore, MEMINTREN, - intel_uncore_read(uncore, MEMINTREN) & - ~MEMINT_EVAL_CHG_EN); + intel_uncore_rmw(uncore, MEMINTREN, MEMINT_EVAL_CHG_EN, 0); intel_uncore_write(uncore, MEMINTRSTS, MEMINT_EVAL_CHG); /* Go back to the starting frequency */ @@ -1016,9 +1015,15 @@ void intel_rps_boost(struct i915_request *rq) if (rps_uses_slpc(rps)) { slpc = rps_to_slpc(rps); + if (slpc->min_freq_softlimit >= slpc->boost_freq) + return; + /* Return if old value is non zero */ - if (!atomic_fetch_inc(&slpc->num_waiters)) + if (!atomic_fetch_inc(&slpc->num_waiters)) { + GT_TRACE(rps_to_gt(rps), "boost fence:%llx:%llx\n", + rq->fence.context, rq->fence.seqno); schedule_work(&slpc->boost_work); + } return; } @@ -1085,15 +1090,25 @@ static u32 intel_rps_read_state_cap(struct intel_rps *rps) return intel_uncore_read(uncore, GEN6_RP_STATE_CAP); } -/** - * gen6_rps_get_freq_caps - Get freq caps exposed by HW - * @rps: the intel_rps structure - * @caps: returned freq caps - * - * Returned "caps" frequencies should be converted to MHz using - * intel_gpu_freq() - */ -void gen6_rps_get_freq_caps(struct intel_rps *rps, struct intel_rps_freq_caps *caps) +static void +mtl_get_freq_caps(struct intel_rps *rps, struct intel_rps_freq_caps *caps) +{ + struct intel_uncore *uncore = rps_to_uncore(rps); + u32 rp_state_cap = rps_to_gt(rps)->type == GT_MEDIA ? + intel_uncore_read(uncore, MTL_MEDIAP_STATE_CAP) : + intel_uncore_read(uncore, MTL_RP_STATE_CAP); + u32 rpe = rps_to_gt(rps)->type == GT_MEDIA ? + intel_uncore_read(uncore, MTL_MPE_FREQUENCY) : + intel_uncore_read(uncore, MTL_GT_RPE_FREQUENCY); + + /* MTL values are in units of 16.67 MHz */ + caps->rp0_freq = REG_FIELD_GET(MTL_RP0_CAP_MASK, rp_state_cap); + caps->min_freq = REG_FIELD_GET(MTL_RPN_CAP_MASK, rp_state_cap); + caps->rp1_freq = REG_FIELD_GET(MTL_RPE_MASK, rpe); +} + +static void +__gen6_rps_get_freq_caps(struct intel_rps *rps, struct intel_rps_freq_caps *caps) { struct drm_i915_private *i915 = rps_to_i915(rps); u32 rp_state_cap; @@ -1128,6 +1143,24 @@ void gen6_rps_get_freq_caps(struct intel_rps *rps, struct intel_rps_freq_caps *c } } +/** + * gen6_rps_get_freq_caps - Get freq caps exposed by HW + * @rps: the intel_rps structure + * @caps: returned freq caps + * + * Returned "caps" frequencies should be converted to MHz using + * intel_gpu_freq() + */ +void gen6_rps_get_freq_caps(struct intel_rps *rps, struct intel_rps_freq_caps *caps) +{ + struct drm_i915_private *i915 = rps_to_i915(rps); + + if (IS_METEORLAKE(i915)) + return mtl_get_freq_caps(rps, caps); + else + return __gen6_rps_get_freq_caps(rps, caps); +} + static void gen6_rps_init(struct intel_rps *rps) { struct drm_i915_private *i915 = rps_to_i915(rps); @@ -1921,7 +1954,8 @@ void gen6_rps_irq_handler(struct intel_rps *rps, u32 pm_iir) intel_engine_cs_irq(gt->engine[VECS0], pm_iir >> 10); if (pm_iir & PM_VEBOX_CS_ERROR_INTERRUPT) - DRM_DEBUG("Command parser error, pm_iir 0x%08x\n", pm_iir); + drm_dbg(&rps_to_i915(rps)->drm, + "Command parser error, pm_iir 0x%08x\n", pm_iir); } void gen5_rps_irq_handler(struct intel_rps *rps) @@ -2040,22 +2074,45 @@ void intel_rps_sanitize(struct intel_rps *rps) rps_disable_interrupts(rps); } +u32 intel_rps_read_rpstat_fw(struct intel_rps *rps) +{ + struct drm_i915_private *i915 = rps_to_i915(rps); + i915_reg_t rpstat; + + rpstat = (GRAPHICS_VER(i915) >= 12) ? GEN12_RPSTAT1 : GEN6_RPSTAT1; + + return intel_uncore_read_fw(rps_to_gt(rps)->uncore, rpstat); +} + +u32 intel_rps_read_rpstat(struct intel_rps *rps) +{ + struct drm_i915_private *i915 = rps_to_i915(rps); + i915_reg_t rpstat; + + rpstat = (GRAPHICS_VER(i915) >= 12) ? GEN12_RPSTAT1 : GEN6_RPSTAT1; + + return intel_uncore_read(rps_to_gt(rps)->uncore, rpstat); +} + u32 intel_rps_get_cagf(struct intel_rps *rps, u32 rpstat) { struct drm_i915_private *i915 = rps_to_i915(rps); u32 cagf; - if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) - cagf = (rpstat >> 8) & 0xff; + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) + cagf = REG_FIELD_GET(MTL_CAGF_MASK, rpstat); + else if (GRAPHICS_VER(i915) >= 12) + cagf = REG_FIELD_GET(GEN12_CAGF_MASK, rpstat); + else if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) + cagf = REG_FIELD_GET(RPE_MASK, rpstat); else if (GRAPHICS_VER(i915) >= 9) - cagf = (rpstat & GEN9_CAGF_MASK) >> GEN9_CAGF_SHIFT; + cagf = REG_FIELD_GET(GEN9_CAGF_MASK, rpstat); else if (IS_HASWELL(i915) || IS_BROADWELL(i915)) - cagf = (rpstat & HSW_CAGF_MASK) >> HSW_CAGF_SHIFT; + cagf = REG_FIELD_GET(HSW_CAGF_MASK, rpstat); else if (GRAPHICS_VER(i915) >= 6) - cagf = (rpstat & GEN6_CAGF_MASK) >> GEN6_CAGF_SHIFT; + cagf = REG_FIELD_GET(GEN6_CAGF_MASK, rpstat); else - cagf = gen5_invert_freq(rps, (rpstat & MEMSTAT_PSTATE_MASK) >> - MEMSTAT_PSTATE_SHIFT); + cagf = gen5_invert_freq(rps, REG_FIELD_GET(MEMSTAT_PSTATE_MASK, rpstat)); return cagf; } @@ -2066,7 +2123,15 @@ static u32 read_cagf(struct intel_rps *rps) struct intel_uncore *uncore = rps_to_uncore(rps); u32 freq; - if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) { + /* + * For Gen12+ reading freq from HW does not need a forcewake and + * registers will return 0 freq when GT is in RC6 + */ + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) { + freq = intel_uncore_read(uncore, MTL_MIRROR_TARGET_WP1); + } else if (GRAPHICS_VER(i915) >= 12) { + freq = intel_uncore_read(uncore, GEN12_RPSTAT1); + } else if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) { vlv_punit_get(i915); freq = vlv_punit_read(i915, PUNIT_REG_GPU_FREQ_STS); vlv_punit_put(i915); @@ -2191,6 +2256,213 @@ u32 intel_rps_get_rpn_frequency(struct intel_rps *rps) return intel_gpu_freq(rps, rps->min_freq); } +static void rps_frequency_dump(struct intel_rps *rps, struct drm_printer *p) +{ + struct intel_gt *gt = rps_to_gt(rps); + struct drm_i915_private *i915 = gt->i915; + struct intel_uncore *uncore = gt->uncore; + struct intel_rps_freq_caps caps; + u32 rp_state_limits; + u32 gt_perf_status; + u32 rpmodectl, rpinclimit, rpdeclimit; + u32 rpstat, cagf, reqf; + u32 rpcurupei, rpcurup, rpprevup; + u32 rpcurdownei, rpcurdown, rpprevdown; + u32 rpupei, rpupt, rpdownei, rpdownt; + u32 pm_ier, pm_imr, pm_isr, pm_iir, pm_mask; + + rp_state_limits = intel_uncore_read(uncore, GEN6_RP_STATE_LIMITS); + gen6_rps_get_freq_caps(rps, &caps); + if (IS_GEN9_LP(i915)) + gt_perf_status = intel_uncore_read(uncore, BXT_GT_PERF_STATUS); + else + gt_perf_status = intel_uncore_read(uncore, GEN6_GT_PERF_STATUS); + + /* RPSTAT1 is in the GT power well */ + intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL); + + reqf = intel_uncore_read(uncore, GEN6_RPNSWREQ); + if (GRAPHICS_VER(i915) >= 9) { + reqf >>= 23; + } else { + reqf &= ~GEN6_TURBO_DISABLE; + if (IS_HASWELL(i915) || IS_BROADWELL(i915)) + reqf >>= 24; + else + reqf >>= 25; + } + reqf = intel_gpu_freq(rps, reqf); + + rpmodectl = intel_uncore_read(uncore, GEN6_RP_CONTROL); + rpinclimit = intel_uncore_read(uncore, GEN6_RP_UP_THRESHOLD); + rpdeclimit = intel_uncore_read(uncore, GEN6_RP_DOWN_THRESHOLD); + + rpstat = intel_rps_read_rpstat(rps); + rpcurupei = intel_uncore_read(uncore, GEN6_RP_CUR_UP_EI) & GEN6_CURICONT_MASK; + rpcurup = intel_uncore_read(uncore, GEN6_RP_CUR_UP) & GEN6_CURBSYTAVG_MASK; + rpprevup = intel_uncore_read(uncore, GEN6_RP_PREV_UP) & GEN6_CURBSYTAVG_MASK; + rpcurdownei = intel_uncore_read(uncore, GEN6_RP_CUR_DOWN_EI) & GEN6_CURIAVG_MASK; + rpcurdown = intel_uncore_read(uncore, GEN6_RP_CUR_DOWN) & GEN6_CURBSYTAVG_MASK; + rpprevdown = intel_uncore_read(uncore, GEN6_RP_PREV_DOWN) & GEN6_CURBSYTAVG_MASK; + + rpupei = intel_uncore_read(uncore, GEN6_RP_UP_EI); + rpupt = intel_uncore_read(uncore, GEN6_RP_UP_THRESHOLD); + + rpdownei = intel_uncore_read(uncore, GEN6_RP_DOWN_EI); + rpdownt = intel_uncore_read(uncore, GEN6_RP_DOWN_THRESHOLD); + + cagf = intel_rps_read_actual_frequency(rps); + + intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL); + + if (GRAPHICS_VER(i915) >= 11) { + pm_ier = intel_uncore_read(uncore, GEN11_GPM_WGBOXPERF_INTR_ENABLE); + pm_imr = intel_uncore_read(uncore, GEN11_GPM_WGBOXPERF_INTR_MASK); + /* + * The equivalent to the PM ISR & IIR cannot be read + * without affecting the current state of the system + */ + pm_isr = 0; + pm_iir = 0; + } else if (GRAPHICS_VER(i915) >= 8) { + pm_ier = intel_uncore_read(uncore, GEN8_GT_IER(2)); + pm_imr = intel_uncore_read(uncore, GEN8_GT_IMR(2)); + pm_isr = intel_uncore_read(uncore, GEN8_GT_ISR(2)); + pm_iir = intel_uncore_read(uncore, GEN8_GT_IIR(2)); + } else { + pm_ier = intel_uncore_read(uncore, GEN6_PMIER); + pm_imr = intel_uncore_read(uncore, GEN6_PMIMR); + pm_isr = intel_uncore_read(uncore, GEN6_PMISR); + pm_iir = intel_uncore_read(uncore, GEN6_PMIIR); + } + pm_mask = intel_uncore_read(uncore, GEN6_PMINTRMSK); + + drm_printf(p, "Video Turbo Mode: %s\n", + str_yes_no(rpmodectl & GEN6_RP_MEDIA_TURBO)); + drm_printf(p, "HW control enabled: %s\n", + str_yes_no(rpmodectl & GEN6_RP_ENABLE)); + drm_printf(p, "SW control enabled: %s\n", + str_yes_no((rpmodectl & GEN6_RP_MEDIA_MODE_MASK) == GEN6_RP_MEDIA_SW_MODE)); + + drm_printf(p, "PM IER=0x%08x IMR=0x%08x, MASK=0x%08x\n", + pm_ier, pm_imr, pm_mask); + if (GRAPHICS_VER(i915) <= 10) + drm_printf(p, "PM ISR=0x%08x IIR=0x%08x\n", + pm_isr, pm_iir); + drm_printf(p, "pm_intrmsk_mbz: 0x%08x\n", + rps->pm_intrmsk_mbz); + drm_printf(p, "GT_PERF_STATUS: 0x%08x\n", gt_perf_status); + drm_printf(p, "Render p-state ratio: %d\n", + (gt_perf_status & (GRAPHICS_VER(i915) >= 9 ? 0x1ff00 : 0xff00)) >> 8); + drm_printf(p, "Render p-state VID: %d\n", + gt_perf_status & 0xff); + drm_printf(p, "Render p-state limit: %d\n", + rp_state_limits & 0xff); + drm_printf(p, "RPSTAT1: 0x%08x\n", rpstat); + drm_printf(p, "RPMODECTL: 0x%08x\n", rpmodectl); + drm_printf(p, "RPINCLIMIT: 0x%08x\n", rpinclimit); + drm_printf(p, "RPDECLIMIT: 0x%08x\n", rpdeclimit); + drm_printf(p, "RPNSWREQ: %dMHz\n", reqf); + drm_printf(p, "CAGF: %dMHz\n", cagf); + drm_printf(p, "RP CUR UP EI: %d (%lldns)\n", + rpcurupei, + intel_gt_pm_interval_to_ns(gt, rpcurupei)); + drm_printf(p, "RP CUR UP: %d (%lldns)\n", + rpcurup, intel_gt_pm_interval_to_ns(gt, rpcurup)); + drm_printf(p, "RP PREV UP: %d (%lldns)\n", + rpprevup, intel_gt_pm_interval_to_ns(gt, rpprevup)); + drm_printf(p, "Up threshold: %d%%\n", + rps->power.up_threshold); + drm_printf(p, "RP UP EI: %d (%lldns)\n", + rpupei, intel_gt_pm_interval_to_ns(gt, rpupei)); + drm_printf(p, "RP UP THRESHOLD: %d (%lldns)\n", + rpupt, intel_gt_pm_interval_to_ns(gt, rpupt)); + + drm_printf(p, "RP CUR DOWN EI: %d (%lldns)\n", + rpcurdownei, + intel_gt_pm_interval_to_ns(gt, rpcurdownei)); + drm_printf(p, "RP CUR DOWN: %d (%lldns)\n", + rpcurdown, + intel_gt_pm_interval_to_ns(gt, rpcurdown)); + drm_printf(p, "RP PREV DOWN: %d (%lldns)\n", + rpprevdown, + intel_gt_pm_interval_to_ns(gt, rpprevdown)); + drm_printf(p, "Down threshold: %d%%\n", + rps->power.down_threshold); + drm_printf(p, "RP DOWN EI: %d (%lldns)\n", + rpdownei, intel_gt_pm_interval_to_ns(gt, rpdownei)); + drm_printf(p, "RP DOWN THRESHOLD: %d (%lldns)\n", + rpdownt, intel_gt_pm_interval_to_ns(gt, rpdownt)); + + drm_printf(p, "Lowest (RPN) frequency: %dMHz\n", + intel_gpu_freq(rps, caps.min_freq)); + drm_printf(p, "Nominal (RP1) frequency: %dMHz\n", + intel_gpu_freq(rps, caps.rp1_freq)); + drm_printf(p, "Max non-overclocked (RP0) frequency: %dMHz\n", + intel_gpu_freq(rps, caps.rp0_freq)); + drm_printf(p, "Max overclocked frequency: %dMHz\n", + intel_gpu_freq(rps, rps->max_freq)); + + drm_printf(p, "Current freq: %d MHz\n", + intel_gpu_freq(rps, rps->cur_freq)); + drm_printf(p, "Actual freq: %d MHz\n", cagf); + drm_printf(p, "Idle freq: %d MHz\n", + intel_gpu_freq(rps, rps->idle_freq)); + drm_printf(p, "Min freq: %d MHz\n", + intel_gpu_freq(rps, rps->min_freq)); + drm_printf(p, "Boost freq: %d MHz\n", + intel_gpu_freq(rps, rps->boost_freq)); + drm_printf(p, "Max freq: %d MHz\n", + intel_gpu_freq(rps, rps->max_freq)); + drm_printf(p, + "efficient (RPe) frequency: %d MHz\n", + intel_gpu_freq(rps, rps->efficient_freq)); +} + +static void slpc_frequency_dump(struct intel_rps *rps, struct drm_printer *p) +{ + struct intel_gt *gt = rps_to_gt(rps); + struct intel_uncore *uncore = gt->uncore; + struct intel_rps_freq_caps caps; + u32 pm_mask; + + gen6_rps_get_freq_caps(rps, &caps); + pm_mask = intel_uncore_read(uncore, GEN6_PMINTRMSK); + + drm_printf(p, "PM MASK=0x%08x\n", pm_mask); + drm_printf(p, "pm_intrmsk_mbz: 0x%08x\n", + rps->pm_intrmsk_mbz); + drm_printf(p, "RPSTAT1: 0x%08x\n", intel_rps_read_rpstat(rps)); + drm_printf(p, "RPNSWREQ: %dMHz\n", intel_rps_get_requested_frequency(rps)); + drm_printf(p, "Lowest (RPN) frequency: %dMHz\n", + intel_gpu_freq(rps, caps.min_freq)); + drm_printf(p, "Nominal (RP1) frequency: %dMHz\n", + intel_gpu_freq(rps, caps.rp1_freq)); + drm_printf(p, "Max non-overclocked (RP0) frequency: %dMHz\n", + intel_gpu_freq(rps, caps.rp0_freq)); + drm_printf(p, "Current freq: %d MHz\n", + intel_rps_get_requested_frequency(rps)); + drm_printf(p, "Actual freq: %d MHz\n", + intel_rps_read_actual_frequency(rps)); + drm_printf(p, "Min freq: %d MHz\n", + intel_rps_get_min_frequency(rps)); + drm_printf(p, "Boost freq: %d MHz\n", + intel_rps_get_boost_frequency(rps)); + drm_printf(p, "Max freq: %d MHz\n", + intel_rps_get_max_frequency(rps)); + drm_printf(p, + "efficient (RPe) frequency: %d MHz\n", + intel_gpu_freq(rps, caps.rp1_freq)); +} + +void gen6_rps_frequency_dump(struct intel_rps *rps, struct drm_printer *p) +{ + if (rps_uses_slpc(rps)) + return slpc_frequency_dump(rps, p); + else + return rps_frequency_dump(rps, p); +} + static int set_max_freq(struct intel_rps *rps, u32 val) { struct drm_i915_private *i915 = rps_to_i915(rps); diff --git a/drivers/gpu/drm/i915/gt/intel_rps.h b/drivers/gpu/drm/i915/gt/intel_rps.h index 4509dfdc52e0..9e1cad9ba0e9 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.h +++ b/drivers/gpu/drm/i915/gt/intel_rps.h @@ -10,6 +10,7 @@ #include "i915_reg_defs.h" struct i915_request; +struct drm_printer; void intel_rps_init_early(struct intel_rps *rps); void intel_rps_init(struct intel_rps *rps); @@ -47,6 +48,8 @@ u32 intel_rps_get_rp1_frequency(struct intel_rps *rps); u32 intel_rps_get_rpn_frequency(struct intel_rps *rps); u32 intel_rps_read_punit_req(struct intel_rps *rps); u32 intel_rps_read_punit_req_frequency(struct intel_rps *rps); +u32 intel_rps_read_rpstat(struct intel_rps *rps); +u32 intel_rps_read_rpstat_fw(struct intel_rps *rps); void gen6_rps_get_freq_caps(struct intel_rps *rps, struct intel_rps_freq_caps *caps); void intel_rps_raise_unslice(struct intel_rps *rps); void intel_rps_lower_unslice(struct intel_rps *rps); @@ -54,6 +57,8 @@ void intel_rps_lower_unslice(struct intel_rps *rps); u32 intel_rps_read_throttle_reason(struct intel_rps *rps); bool rps_read_mask_mmio(struct intel_rps *rps, i915_reg_t reg32, u32 mask); +void gen6_rps_frequency_dump(struct intel_rps *rps, struct drm_printer *p); + void gen5_rps_irq_handler(struct intel_rps *rps); void gen6_rps_irq_handler(struct intel_rps *rps, u32 pm_iir); void gen11_rps_irq_handler(struct intel_rps *rps, u32 pm_iir); diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c index 66f21c735d54..6c6198a257ac 100644 --- a/drivers/gpu/drm/i915/gt/intel_sseu.c +++ b/drivers/gpu/drm/i915/gt/intel_sseu.c @@ -677,8 +677,8 @@ u32 intel_sseu_make_rpcs(struct intel_gt *gt, * If i915/perf is active, we want a stable powergating configuration * on the system. Use the configuration pinned by i915/perf. */ - if (i915->perf.exclusive_stream) - req_sseu = &i915->perf.sseu; + if (gt->perf.exclusive_stream) + req_sseu = >->perf.sseu; slices = hweight8(req_sseu->slice_mask); subslices = hweight8(req_sseu->subslice_mask); diff --git a/drivers/gpu/drm/i915/intel_wopcm.c b/drivers/gpu/drm/i915/gt/intel_wopcm.c index 322fb9eeb880..7ebbcc191c2d 100644 --- a/drivers/gpu/drm/i915/intel_wopcm.c +++ b/drivers/gpu/drm/i915/gt/intel_wopcm.c @@ -64,9 +64,9 @@ #define GEN9_GUC_FW_RESERVED SZ_128K #define GEN9_GUC_WOPCM_OFFSET (GUC_WOPCM_RESERVED + GEN9_GUC_FW_RESERVED) -static inline struct drm_i915_private *wopcm_to_i915(struct intel_wopcm *wopcm) +static inline struct intel_gt *wopcm_to_gt(struct intel_wopcm *wopcm) { - return container_of(wopcm, struct drm_i915_private, wopcm); + return container_of(wopcm, struct intel_gt, wopcm); } /** @@ -77,7 +77,8 @@ static inline struct drm_i915_private *wopcm_to_i915(struct intel_wopcm *wopcm) */ void intel_wopcm_init_early(struct intel_wopcm *wopcm) { - struct drm_i915_private *i915 = wopcm_to_i915(wopcm); + struct intel_gt *gt = wopcm_to_gt(wopcm); + struct drm_i915_private *i915 = gt->i915; if (!HAS_GT_UC(i915)) return; @@ -157,10 +158,11 @@ static bool check_hw_restrictions(struct drm_i915_private *i915, return true; } -static bool __check_layout(struct drm_i915_private *i915, u32 wopcm_size, +static bool __check_layout(struct intel_gt *gt, u32 wopcm_size, u32 guc_wopcm_base, u32 guc_wopcm_size, u32 guc_fw_size, u32 huc_fw_size) { + struct drm_i915_private *i915 = gt->i915; const u32 ctx_rsvd = context_reserved_size(i915); u32 size; @@ -181,12 +183,14 @@ static bool __check_layout(struct drm_i915_private *i915, u32 wopcm_size, return false; } - size = huc_fw_size + WOPCM_RESERVED_SIZE; - if (unlikely(guc_wopcm_base < size)) { - drm_err(&i915->drm, "WOPCM: no space for %s: %uK < %uK\n", - intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_HUC), - guc_wopcm_base / SZ_1K, size / SZ_1K); - return false; + if (intel_uc_supports_huc(>->uc)) { + size = huc_fw_size + WOPCM_RESERVED_SIZE; + if (unlikely(guc_wopcm_base < size)) { + drm_err(&i915->drm, "WOPCM: no space for %s: %uK < %uK\n", + intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_HUC), + guc_wopcm_base / SZ_1K, size / SZ_1K); + return false; + } } return check_hw_restrictions(i915, guc_wopcm_base, guc_wopcm_size, @@ -228,8 +232,8 @@ static bool __wopcm_regs_writable(struct intel_uncore *uncore) */ void intel_wopcm_init(struct intel_wopcm *wopcm) { - struct drm_i915_private *i915 = wopcm_to_i915(wopcm); - struct intel_gt *gt = to_gt(i915); + struct intel_gt *gt = wopcm_to_gt(wopcm); + struct drm_i915_private *i915 = gt->i915; u32 guc_fw_size = intel_uc_fw_get_upload_size(>->uc.guc.fw); u32 huc_fw_size = intel_uc_fw_get_upload_size(>->uc.huc.fw); u32 ctx_rsvd = context_reserved_size(i915); @@ -275,6 +279,19 @@ void intel_wopcm_init(struct intel_wopcm *wopcm) } /* + * On platforms with a media GT, the WOPCM is partitioned between the + * two GTs, so we would have to take that into account when doing the + * math below. There is also a new section reserved for the GSC context + * that would have to be factored in. However, all platforms with a + * media GT also have GuC depriv enabled, so the WOPCM regs are + * pre-locked and therefore we don't have to do the math ourselves. + */ + if (unlikely(i915->media_gt)) { + drm_err(&i915->drm, "Unlocked WOPCM regs with media GT\n"); + return; + } + + /* * Aligned value of guc_wopcm_base will determine available WOPCM space * for HuC firmware and mandatory reserved area. */ @@ -295,7 +312,7 @@ void intel_wopcm_init(struct intel_wopcm *wopcm) guc_wopcm_base / SZ_1K, guc_wopcm_size / SZ_1K); check: - if (__check_layout(i915, wopcm_size, guc_wopcm_base, guc_wopcm_size, + if (__check_layout(gt, wopcm_size, guc_wopcm_base, guc_wopcm_size, guc_fw_size, huc_fw_size)) { wopcm->guc.base = guc_wopcm_base; wopcm->guc.size = guc_wopcm_size; diff --git a/drivers/gpu/drm/i915/intel_wopcm.h b/drivers/gpu/drm/i915/gt/intel_wopcm.h index 17d6aa86008a..17d6aa86008a 100644 --- a/drivers/gpu/drm/i915/intel_wopcm.h +++ b/drivers/gpu/drm/i915/gt/intel_wopcm.h diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index a821e3d405db..2afb4f80a954 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -4,6 +4,7 @@ */ #include "i915_drv.h" +#include "i915_reg.h" #include "intel_context.h" #include "intel_engine_pm.h" #include "intel_engine_regs.h" @@ -17,46 +18,68 @@ /** * DOC: Hardware workarounds * - * This file is intended as a central place to implement most [1]_ of the - * required workarounds for hardware to work as originally intended. They fall - * in five basic categories depending on how/when they are applied: + * Hardware workarounds are register programming documented to be executed in + * the driver that fall outside of the normal programming sequences for a + * platform. There are some basic categories of workarounds, depending on + * how/when they are applied: * - * - Workarounds that touch registers that are saved/restored to/from the HW - * context image. The list is emitted (via Load Register Immediate commands) - * everytime a new context is created. - * - GT workarounds. The list of these WAs is applied whenever these registers - * revert to default values (on GPU reset, suspend/resume [2]_, etc..). - * - Display workarounds. The list is applied during display clock-gating - * initialization. - * - Workarounds that whitelist a privileged register, so that UMDs can manage - * them directly. This is just a special case of a MMMIO workaround (as we - * write the list of these to/be-whitelisted registers to some special HW - * registers). - * - Workaround batchbuffers, that get executed automatically by the hardware - * on every HW context restore. + * - Context workarounds: workarounds that touch registers that are + * saved/restored to/from the HW context image. The list is emitted (via Load + * Register Immediate commands) once when initializing the device and saved in + * the default context. That default context is then used on every context + * creation to have a "primed golden context", i.e. a context image that + * already contains the changes needed to all the registers. * - * .. [1] Please notice that there are other WAs that, due to their nature, - * cannot be applied from a central place. Those are peppered around the rest - * of the code, as needed. + * - Engine workarounds: the list of these WAs is applied whenever the specific + * engine is reset. It's also possible that a set of engine classes share a + * common power domain and they are reset together. This happens on some + * platforms with render and compute engines. In this case (at least) one of + * them need to keeep the workaround programming: the approach taken in the + * driver is to tie those workarounds to the first compute/render engine that + * is registered. When executing with GuC submission, engine resets are + * outside of kernel driver control, hence the list of registers involved in + * written once, on engine initialization, and then passed to GuC, that + * saves/restores their values before/after the reset takes place. See + * ``drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c`` for reference. * - * .. [2] Technically, some registers are powercontext saved & restored, so they - * survive a suspend/resume. In practice, writing them again is not too - * costly and simplifies things. We can revisit this in the future. + * - GT workarounds: the list of these WAs is applied whenever these registers + * revert to their default values: on GPU reset, suspend/resume [1]_, etc. + * + * - Register whitelist: some workarounds need to be implemented in userspace, + * but need to touch privileged registers. The whitelist in the kernel + * instructs the hardware to allow the access to happen. From the kernel side, + * this is just a special case of a MMIO workaround (as we write the list of + * these to/be-whitelisted registers to some special HW registers). + * + * - Workaround batchbuffers: buffers that get executed automatically by the + * hardware on every HW context restore. These buffers are created and + * programmed in the default context so the hardware always go through those + * programming sequences when switching contexts. The support for workaround + * batchbuffers is enabled these hardware mechanisms: * - * Layout - * ~~~~~~ + * #. INDIRECT_CTX: A batchbuffer and an offset are provided in the default + * context, pointing the hardware to jump to that location when that offset + * is reached in the context restore. Workaround batchbuffer in the driver + * currently uses this mechanism for all platforms. * - * Keep things in this file ordered by WA type, as per the above (context, GT, - * display, register whitelist, batchbuffer). Then, inside each type, keep the - * following order: + * #. BB_PER_CTX_PTR: A batchbuffer is provided in the default context, + * pointing the hardware to a buffer to continue executing after the + * engine registers are restored in a context restore sequence. This is + * currently not used in the driver. * - * - Infrastructure functions and macros - * - WAs per platform in standard gen/chrono order - * - Public functions to init or apply the given workaround type. + * - Other: There are WAs that, due to their nature, cannot be applied from a + * central place. Those are peppered around the rest of the code, as needed. + * Workarounds related to the display IP are the main example. + * + * .. [1] Technically, some registers are powercontext saved & restored, so they + * survive a suspend/resume. In practice, writing them again is not too + * costly and simplifies things, so it's the approach taken in the driver. */ -static void wa_init_start(struct i915_wa_list *wal, const char *name, const char *engine_name) +static void wa_init_start(struct i915_wa_list *wal, struct intel_gt *gt, + const char *name, const char *engine_name) { + wal->gt = gt; wal->name = name; wal->engine_name = engine_name; } @@ -80,13 +103,14 @@ static void wa_init_finish(struct i915_wa_list *wal) if (!wal->count) return; - DRM_DEBUG_DRIVER("Initialized %u %s workarounds on %s\n", - wal->wa_count, wal->name, wal->engine_name); + drm_dbg(&wal->gt->i915->drm, "Initialized %u %s workarounds on %s\n", + wal->wa_count, wal->name, wal->engine_name); } static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa) { unsigned int addr = i915_mmio_reg_offset(wa->reg); + struct drm_i915_private *i915 = wal->gt->i915; unsigned int start = 0, end = wal->count; const unsigned int grow = WA_LIST_CHUNK; struct i915_wa *wa_; @@ -99,7 +123,7 @@ static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa) list = kmalloc_array(ALIGN(wal->count + 1, grow), sizeof(*wa), GFP_KERNEL); if (!list) { - DRM_ERROR("No space for workaround init!\n"); + drm_err(&i915->drm, "No space for workaround init!\n"); return; } @@ -122,9 +146,10 @@ static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa) wa_ = &wal->list[mid]; if ((wa->clr | wa_->clr) && !(wa->clr & ~wa_->clr)) { - DRM_ERROR("Discarding overwritten w/a for reg %04x (clear: %08x, set: %08x)\n", - i915_mmio_reg_offset(wa_->reg), - wa_->clr, wa_->set); + drm_err(&i915->drm, + "Discarding overwritten w/a for reg %04x (clear: %08x, set: %08x)\n", + i915_mmio_reg_offset(wa_->reg), + wa_->clr, wa_->set); wa_->set &= ~wa->clr; } @@ -166,6 +191,21 @@ static void wa_add(struct i915_wa_list *wal, i915_reg_t reg, _wa_add(wal, &wa); } +static void wa_mcr_add(struct i915_wa_list *wal, i915_mcr_reg_t reg, + u32 clear, u32 set, u32 read_mask, bool masked_reg) +{ + struct i915_wa wa = { + .mcr_reg = reg, + .clr = clear, + .set = set, + .read = read_mask, + .masked_reg = masked_reg, + .is_mcr = 1, + }; + + _wa_add(wal, &wa); +} + static void wa_write_clr_set(struct i915_wa_list *wal, i915_reg_t reg, u32 clear, u32 set) { @@ -173,6 +213,12 @@ wa_write_clr_set(struct i915_wa_list *wal, i915_reg_t reg, u32 clear, u32 set) } static void +wa_mcr_write_clr_set(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 clear, u32 set) +{ + wa_mcr_add(wal, reg, clear, set, clear, false); +} + +static void wa_write(struct i915_wa_list *wal, i915_reg_t reg, u32 set) { wa_write_clr_set(wal, reg, ~0, set); @@ -185,11 +231,23 @@ wa_write_or(struct i915_wa_list *wal, i915_reg_t reg, u32 set) } static void +wa_mcr_write_or(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 set) +{ + wa_mcr_write_clr_set(wal, reg, set, set); +} + +static void wa_write_clr(struct i915_wa_list *wal, i915_reg_t reg, u32 clr) { wa_write_clr_set(wal, reg, clr, 0); } +static void +wa_mcr_write_clr(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 clr) +{ + wa_mcr_write_clr_set(wal, reg, clr, 0); +} + /* * WA operations on "masked register". A masked register has the upper 16 bits * documented as "masked" in b-spec. Its purpose is to allow writing to just a @@ -208,18 +266,37 @@ wa_masked_en(struct i915_wa_list *wal, i915_reg_t reg, u32 val) } static void +wa_mcr_masked_en(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 val) +{ + wa_mcr_add(wal, reg, 0, _MASKED_BIT_ENABLE(val), val, true); +} + +static void wa_masked_dis(struct i915_wa_list *wal, i915_reg_t reg, u32 val) { wa_add(wal, reg, 0, _MASKED_BIT_DISABLE(val), val, true); } static void +wa_mcr_masked_dis(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 val) +{ + wa_mcr_add(wal, reg, 0, _MASKED_BIT_DISABLE(val), val, true); +} + +static void wa_masked_field_set(struct i915_wa_list *wal, i915_reg_t reg, u32 mask, u32 val) { wa_add(wal, reg, 0, _MASKED_FIELD(mask, val), mask, true); } +static void +wa_mcr_masked_field_set(struct i915_wa_list *wal, i915_mcr_reg_t reg, + u32 mask, u32 val) +{ + wa_mcr_add(wal, reg, 0, _MASKED_FIELD(mask, val), mask, true); +} + static void gen6_ctx_workarounds_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) { @@ -241,8 +318,8 @@ static void gen8_ctx_workarounds_init(struct intel_engine_cs *engine, wa_masked_en(wal, RING_MI_MODE(RENDER_RING_BASE), ASYNC_FLIP_PERF_DISABLE); /* WaDisablePartialInstShootdown:bdw,chv */ - wa_masked_en(wal, GEN8_ROW_CHICKEN, - PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE); + wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN, + PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE); /* Use Force Non-Coherent whenever executing a 3D context. This is a * workaround for a possible hang in the unlikely event a TLB @@ -288,18 +365,18 @@ static void bdw_ctx_workarounds_init(struct intel_engine_cs *engine, gen8_ctx_workarounds_init(engine, wal); /* WaDisableThreadStallDopClockGating:bdw (pre-production) */ - wa_masked_en(wal, GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE); + wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE); /* WaDisableDopClockGating:bdw * * Also see the related UCGTCL1 write in bdw_init_clock_gating() * to disable EUTC clock gating. */ - wa_masked_en(wal, GEN7_ROW_CHICKEN2, - DOP_CLOCK_GATING_DISABLE); + wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN2, + DOP_CLOCK_GATING_DISABLE); - wa_masked_en(wal, HALF_SLICE_CHICKEN3, - GEN8_SAMPLER_POWER_BYPASS_DIS); + wa_mcr_masked_en(wal, GEN8_HALF_SLICE_CHICKEN3, + GEN8_SAMPLER_POWER_BYPASS_DIS); wa_masked_en(wal, HDC_CHICKEN0, /* WaForceContextSaveRestoreNonCoherent:bdw */ @@ -314,7 +391,7 @@ static void chv_ctx_workarounds_init(struct intel_engine_cs *engine, gen8_ctx_workarounds_init(engine, wal); /* WaDisableThreadStallDopClockGating:chv */ - wa_masked_en(wal, GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE); + wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE); /* Improve HiZ throughput on CHV. */ wa_masked_en(wal, HIZ_CHICKEN, CHV_HZ_8X8_MODE_IN_1X); @@ -333,21 +410,21 @@ static void gen9_ctx_workarounds_init(struct intel_engine_cs *engine, */ wa_masked_en(wal, COMMON_SLICE_CHICKEN2, GEN9_PBE_COMPRESSED_HASH_SELECTION); - wa_masked_en(wal, GEN9_HALF_SLICE_CHICKEN7, - GEN9_SAMPLER_HASH_COMPRESSED_READ_ADDR); + wa_mcr_masked_en(wal, GEN9_HALF_SLICE_CHICKEN7, + GEN9_SAMPLER_HASH_COMPRESSED_READ_ADDR); } /* WaClearFlowControlGpgpuContextSave:skl,bxt,kbl,glk,cfl */ /* WaDisablePartialInstShootdown:skl,bxt,kbl,glk,cfl */ - wa_masked_en(wal, GEN8_ROW_CHICKEN, - FLOW_CONTROL_ENABLE | - PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE); + wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN, + FLOW_CONTROL_ENABLE | + PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE); /* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt,kbl,glk,cfl */ /* WaEnableSamplerGPGPUPreemptionSupport:skl,bxt,kbl,cfl */ - wa_masked_en(wal, GEN9_HALF_SLICE_CHICKEN7, - GEN9_ENABLE_YV12_BUGFIX | - GEN9_ENABLE_GPGPU_PREEMPTION); + wa_mcr_masked_en(wal, GEN9_HALF_SLICE_CHICKEN7, + GEN9_ENABLE_YV12_BUGFIX | + GEN9_ENABLE_GPGPU_PREEMPTION); /* Wa4x4STCOptimizationDisable:skl,bxt,kbl,glk,cfl */ /* WaDisablePartialResolveInVc:skl,bxt,kbl,cfl */ @@ -356,8 +433,8 @@ static void gen9_ctx_workarounds_init(struct intel_engine_cs *engine, GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE); /* WaCcsTlbPrefetchDisable:skl,bxt,kbl,glk,cfl */ - wa_masked_dis(wal, GEN9_HALF_SLICE_CHICKEN5, - GEN9_CCS_TLB_PREFETCH_ENABLE); + wa_mcr_masked_dis(wal, GEN9_HALF_SLICE_CHICKEN5, + GEN9_CCS_TLB_PREFETCH_ENABLE); /* WaForceContextSaveRestoreNonCoherent:skl,bxt,kbl,cfl */ wa_masked_en(wal, HDC_CHICKEN0, @@ -386,11 +463,11 @@ static void gen9_ctx_workarounds_init(struct intel_engine_cs *engine, IS_KABYLAKE(i915) || IS_COFFEELAKE(i915) || IS_COMETLAKE(i915)) - wa_masked_en(wal, HALF_SLICE_CHICKEN3, - GEN8_SAMPLER_POWER_BYPASS_DIS); + wa_mcr_masked_en(wal, GEN8_HALF_SLICE_CHICKEN3, + GEN8_SAMPLER_POWER_BYPASS_DIS); /* WaDisableSTUnitPowerOptimization:skl,bxt,kbl,glk,cfl */ - wa_masked_en(wal, HALF_SLICE_CHICKEN2, GEN8_ST_PO_DISABLE); + wa_mcr_masked_en(wal, HALF_SLICE_CHICKEN2, GEN8_ST_PO_DISABLE); /* * Supporting preemption with fine-granularity requires changes in the @@ -469,8 +546,8 @@ static void bxt_ctx_workarounds_init(struct intel_engine_cs *engine, gen9_ctx_workarounds_init(engine, wal); /* WaDisableThreadStallDopClockGating:bxt */ - wa_masked_en(wal, GEN8_ROW_CHICKEN, - STALL_DOP_GATING_DISABLE); + wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN, + STALL_DOP_GATING_DISABLE); /* WaToEnableHwFixForPushConstHWBug:bxt */ wa_masked_en(wal, COMMON_SLICE_CHICKEN2, @@ -490,8 +567,8 @@ static void kbl_ctx_workarounds_init(struct intel_engine_cs *engine, GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); /* WaDisableSbeCacheDispatchPortSharing:kbl */ - wa_masked_en(wal, GEN7_HALF_SLICE_CHICKEN1, - GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE); + wa_mcr_masked_en(wal, GEN8_HALF_SLICE_CHICKEN1, + GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE); } static void glk_ctx_workarounds_init(struct intel_engine_cs *engine, @@ -514,8 +591,8 @@ static void cfl_ctx_workarounds_init(struct intel_engine_cs *engine, GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); /* WaDisableSbeCacheDispatchPortSharing:cfl */ - wa_masked_en(wal, GEN7_HALF_SLICE_CHICKEN1, - GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE); + wa_mcr_masked_en(wal, GEN8_HALF_SLICE_CHICKEN1, + GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE); } static void icl_ctx_workarounds_init(struct intel_engine_cs *engine, @@ -534,13 +611,13 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine, * (the register is whitelisted in hardware now, so UMDs can opt in * for coherency if they have a good reason). */ - wa_masked_en(wal, ICL_HDC_MODE, HDC_FORCE_NON_COHERENT); + wa_mcr_masked_en(wal, ICL_HDC_MODE, HDC_FORCE_NON_COHERENT); /* WaEnableFloatBlendOptimization:icl */ - wa_add(wal, GEN10_CACHE_MODE_SS, 0, - _MASKED_BIT_ENABLE(FLOAT_BLEND_OPTIMIZATION_ENABLE), - 0 /* write-only, so skip validation */, - true); + wa_mcr_add(wal, GEN10_CACHE_MODE_SS, 0, + _MASKED_BIT_ENABLE(FLOAT_BLEND_OPTIMIZATION_ENABLE), + 0 /* write-only, so skip validation */, + true); /* WaDisableGPGPUMidThreadPreemption:icl */ wa_masked_field_set(wal, GEN8_CS_CHICKEN1, @@ -548,8 +625,8 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine, GEN9_PREEMPT_GPGPU_THREAD_GROUP_LEVEL); /* allow headerless messages for preemptible GPGPU context */ - wa_masked_en(wal, GEN10_SAMPLER_MODE, - GEN11_SAMPLER_ENABLE_HEADLESS_MSG); + wa_mcr_masked_en(wal, GEN10_SAMPLER_MODE, + GEN11_SAMPLER_ENABLE_HEADLESS_MSG); /* Wa_1604278689:icl,ehl */ wa_write(wal, IVB_FBC_RT_BASE, 0xFFFFFFFF & ~ILK_FBC_RT_VALID); @@ -558,7 +635,7 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine, 0xFFFFFFFF); /* Wa_1406306137:icl,ehl */ - wa_masked_en(wal, GEN9_ROW_CHICKEN4, GEN11_DIS_PICK_2ND_EU); + wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN4, GEN11_DIS_PICK_2ND_EU); } /* @@ -569,13 +646,13 @@ static void dg2_ctx_gt_tuning_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) { wa_masked_en(wal, CHICKEN_RASTER_2, TBIMR_FAST_CLIP); - wa_write_clr_set(wal, GEN11_L3SQCREG5, L3_PWM_TIMER_INIT_VAL_MASK, - REG_FIELD_PREP(L3_PWM_TIMER_INIT_VAL_MASK, 0x7f)); - wa_add(wal, - FF_MODE2, - FF_MODE2_TDS_TIMER_MASK, - FF_MODE2_TDS_TIMER_128, - 0, false); + wa_mcr_write_clr_set(wal, XEHP_L3SQCREG5, L3_PWM_TIMER_INIT_VAL_MASK, + REG_FIELD_PREP(L3_PWM_TIMER_INIT_VAL_MASK, 0x7f)); + wa_mcr_add(wal, + XEHP_FF_MODE2, + FF_MODE2_TDS_TIMER_MASK, + FF_MODE2_TDS_TIMER_128, + 0, false); } /* @@ -599,7 +676,7 @@ static void gen12_ctx_gt_tuning_init(struct intel_engine_cs *engine, * verification is ignored. */ wa_add(wal, - FF_MODE2, + GEN12_FF_MODE2, FF_MODE2_TDS_TIMER_MASK, FF_MODE2_TDS_TIMER_128, 0, false); @@ -608,6 +685,8 @@ static void gen12_ctx_gt_tuning_init(struct intel_engine_cs *engine, static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) { + struct drm_i915_private *i915 = engine->i915; + gen12_ctx_gt_tuning_init(engine, wal); /* @@ -637,10 +716,14 @@ static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine, * to Wa_1608008084. */ wa_add(wal, - FF_MODE2, + GEN12_FF_MODE2, FF_MODE2_GS_TIMER_MASK, FF_MODE2_GS_TIMER_224, 0, false); + + if (!IS_DG1(i915)) + /* Wa_1806527549 */ + wa_masked_en(wal, HIZ_CHICKEN, HZ_DEPTH_TEST_LE_GE_OPT_DISABLE); } static void dg1_ctx_workarounds_init(struct intel_engine_cs *engine, @@ -664,27 +747,27 @@ static void dg2_ctx_workarounds_init(struct intel_engine_cs *engine, /* Wa_16011186671:dg2_g11 */ if (IS_DG2_GRAPHICS_STEP(engine->i915, G11, STEP_A0, STEP_B0)) { - wa_masked_dis(wal, VFLSKPD, DIS_MULT_MISS_RD_SQUASH); - wa_masked_en(wal, VFLSKPD, DIS_OVER_FETCH_CACHE); + wa_mcr_masked_dis(wal, VFLSKPD, DIS_MULT_MISS_RD_SQUASH); + wa_mcr_masked_en(wal, VFLSKPD, DIS_OVER_FETCH_CACHE); } if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0)) { /* Wa_14010469329:dg2_g10 */ - wa_masked_en(wal, GEN11_COMMON_SLICE_CHICKEN3, - XEHP_DUAL_SIMD8_SEQ_MERGE_DISABLE); + wa_mcr_masked_en(wal, XEHP_COMMON_SLICE_CHICKEN3, + XEHP_DUAL_SIMD8_SEQ_MERGE_DISABLE); /* * Wa_22010465075:dg2_g10 * Wa_22010613112:dg2_g10 * Wa_14010698770:dg2_g10 */ - wa_masked_en(wal, GEN11_COMMON_SLICE_CHICKEN3, - GEN12_DISABLE_CPS_AWARE_COLOR_PIPE); + wa_mcr_masked_en(wal, XEHP_COMMON_SLICE_CHICKEN3, + GEN12_DISABLE_CPS_AWARE_COLOR_PIPE); } /* Wa_16013271637:dg2 */ - wa_masked_en(wal, SLICE_COMMON_ECO_CHICKEN1, - MSC_MSAA_REODER_BUF_BYPASS_DISABLE); + wa_mcr_masked_en(wal, XEHP_SLICE_COMMON_ECO_CHICKEN1, + MSC_MSAA_REODER_BUF_BYPASS_DISABLE); /* Wa_14014947963:dg2 */ if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_B0, STEP_FOREVER) || @@ -768,7 +851,7 @@ __intel_engine_init_ctx_wa(struct intel_engine_cs *engine, { struct drm_i915_private *i915 = engine->i915; - wa_init_start(wal, name, engine->name); + wa_init_start(wal, engine->gt, name, engine->name); /* Applies to all engines */ /* @@ -1076,18 +1159,23 @@ static void __set_mcr_steering(struct i915_wa_list *wal, wa_write_clr_set(wal, steering_reg, mcr_mask, mcr); } -static void __add_mcr_wa(struct intel_gt *gt, struct i915_wa_list *wal, - unsigned int slice, unsigned int subslice) +static void debug_dump_steering(struct intel_gt *gt) { struct drm_printer p = drm_debug_printer("MCR Steering:"); + if (drm_debug_enabled(DRM_UT_DRIVER)) + intel_gt_mcr_report_steering(&p, gt, false); +} + +static void __add_mcr_wa(struct intel_gt *gt, struct i915_wa_list *wal, + unsigned int slice, unsigned int subslice) +{ __set_mcr_steering(wal, GEN8_MCR_SELECTOR, slice, subslice); gt->default_steering.groupid = slice; gt->default_steering.instanceid = subslice; - if (drm_debug_enabled(DRM_UT_DRIVER)) - intel_gt_mcr_report_steering(&p, gt, false); + debug_dump_steering(gt); } static void @@ -1181,6 +1269,9 @@ xehp_init_mcr(struct intel_gt *gt, struct i915_wa_list *wal) gt->steering_table[MSLICE] = NULL; } + if (IS_XEHPSDV(gt->i915) && slice_mask & BIT(0)) + gt->steering_table[GAM] = NULL; + slice = __ffs(slice_mask); subslice = intel_sseu_find_first_xehp_dss(sseu, GEN_DSS_PER_GSLICE, slice) % GEN_DSS_PER_GSLICE; @@ -1198,6 +1289,13 @@ xehp_init_mcr(struct intel_gt *gt, struct i915_wa_list *wal) */ __set_mcr_steering(wal, MCFG_MCR_SELECTOR, 0, 2); __set_mcr_steering(wal, SF_MCR_SELECTOR, 0, 2); + + /* + * On DG2, GAM registers have a dedicated steering control register + * and must always be programmed to a hardcoded groupid of "1." + */ + if (IS_DG2(gt->i915)) + __set_mcr_steering(wal, GAM_MCR_SELECTOR, 1, 0); } static void @@ -1254,22 +1352,22 @@ icl_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) PSDUNIT_CLKGATE_DIS); /* Wa_1406680159:icl,ehl */ - wa_write_or(wal, - SUBSLICE_UNIT_LEVEL_CLKGATE, - GWUNIT_CLKGATE_DIS); + wa_mcr_write_or(wal, + GEN11_SUBSLICE_UNIT_LEVEL_CLKGATE, + GWUNIT_CLKGATE_DIS); /* Wa_1607087056:icl,ehl,jsl */ if (IS_ICELAKE(i915) || IS_JSL_EHL_GRAPHICS_STEP(i915, STEP_A0, STEP_B0)) wa_write_or(wal, - SLICE_UNIT_LEVEL_CLKGATE, + GEN11_SLICE_UNIT_LEVEL_CLKGATE, L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS); /* * This is not a documented workaround, but rather an optimization * to reduce sampler power. */ - wa_write_clr(wal, GEN10_DFR_RATIO_EN_AND_CHICKEN, DFR_DISABLE); + wa_mcr_write_clr(wal, GEN10_DFR_RATIO_EN_AND_CHICKEN, DFR_DISABLE); } /* @@ -1303,7 +1401,7 @@ gen12_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) wa_14011060649(gt, wal); /* Wa_14011059788:tgl,rkl,adl-s,dg1,adl-p */ - wa_write_or(wal, GEN10_DFR_RATIO_EN_AND_CHICKEN, DFR_DISABLE); + wa_mcr_write_or(wal, GEN10_DFR_RATIO_EN_AND_CHICKEN, DFR_DISABLE); } static void @@ -1315,14 +1413,14 @@ tgl_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) /* Wa_1409420604:tgl */ if (IS_TGL_UY_GRAPHICS_STEP(i915, STEP_A0, STEP_B0)) - wa_write_or(wal, - SUBSLICE_UNIT_LEVEL_CLKGATE2, - CPSSUNIT_CLKGATE_DIS); + wa_mcr_write_or(wal, + SUBSLICE_UNIT_LEVEL_CLKGATE2, + CPSSUNIT_CLKGATE_DIS); /* Wa_1607087056:tgl also know as BUG:1409180338 */ if (IS_TGL_UY_GRAPHICS_STEP(i915, STEP_A0, STEP_B0)) wa_write_or(wal, - SLICE_UNIT_LEVEL_CLKGATE, + GEN11_SLICE_UNIT_LEVEL_CLKGATE, L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS); /* Wa_1408615072:tgl[a0] */ @@ -1341,14 +1439,14 @@ dg1_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) /* Wa_1607087056:dg1 */ if (IS_DG1_GRAPHICS_STEP(i915, STEP_A0, STEP_B0)) wa_write_or(wal, - SLICE_UNIT_LEVEL_CLKGATE, + GEN11_SLICE_UNIT_LEVEL_CLKGATE, L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS); /* Wa_1409420604:dg1 */ if (IS_DG1(i915)) - wa_write_or(wal, - SUBSLICE_UNIT_LEVEL_CLKGATE2, - CPSSUNIT_CLKGATE_DIS); + wa_mcr_write_or(wal, + SUBSLICE_UNIT_LEVEL_CLKGATE2, + CPSSUNIT_CLKGATE_DIS); /* Wa_1408615072:dg1 */ /* Empirical testing shows this register is unaffected by engine reset. */ @@ -1365,7 +1463,7 @@ xehpsdv_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) xehp_init_mcr(gt, wal); /* Wa_1409757795:xehpsdv */ - wa_write_or(wal, SCCGCTL94DC, CG3DDISURB); + wa_mcr_write_or(wal, SCCGCTL94DC, CG3DDISURB); /* Wa_16011155590:xehpsdv */ if (IS_XEHPSDV_GRAPHICS_STEP(i915, STEP_A0, STEP_B0)) @@ -1445,8 +1543,8 @@ dg2_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) CG3DDISCFEG_CLKGATE_DIS); /* Wa_14011006942:dg2 */ - wa_write_or(wal, SUBSLICE_UNIT_LEVEL_CLKGATE, - DSS_ROUTER_CLKGATE_DIS); + wa_mcr_write_or(wal, GEN11_SUBSLICE_UNIT_LEVEL_CLKGATE, + DSS_ROUTER_CLKGATE_DIS); } if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_B0)) { @@ -1457,7 +1555,7 @@ dg2_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) wa_write_or(wal, UNSLCGCTL9444, LTCDD_CLKGATE_DIS); /* Wa_14011371254:dg2_g10 */ - wa_write_or(wal, SLICE_UNIT_LEVEL_CLKGATE, NODEDSS_CLKGATE_DIS); + wa_mcr_write_or(wal, XEHP_SLICE_UNIT_LEVEL_CLKGATE, NODEDSS_CLKGATE_DIS); /* Wa_14011431319:dg2_g10 */ wa_write_or(wal, UNSLCGCTL9440, GAMTLBOACS_CLKGATE_DIS | @@ -1493,21 +1591,21 @@ dg2_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) GAMEDIA_CLKGATE_DIS); /* Wa_14011028019:dg2_g10 */ - wa_write_or(wal, SSMCGCTL9530, RTFUNIT_CLKGATE_DIS); + wa_mcr_write_or(wal, SSMCGCTL9530, RTFUNIT_CLKGATE_DIS); } /* Wa_14014830051:dg2 */ - wa_write_clr(wal, SARB_CHICKEN1, COMP_CKN_IN); + wa_mcr_write_clr(wal, SARB_CHICKEN1, COMP_CKN_IN); /* * The following are not actually "workarounds" but rather * recommended tuning settings documented in the bspec's * performance guide section. */ - wa_write_or(wal, GEN12_SQCM, EN_32B_ACCESS); + wa_mcr_write_or(wal, XEHP_SQCM, EN_32B_ACCESS); /* Wa_14015795083 */ - wa_write_clr(wal, GEN7_MISCCPCTL, GEN12_DOP_CLOCK_GATE_RENDER_ENABLE); + wa_mcr_write_clr(wal, GEN8_MISCCPCTL, GEN12_DOP_CLOCK_GATE_RENDER_ENABLE); } static void @@ -1516,7 +1614,27 @@ pvc_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) pvc_init_mcr(gt, wal); /* Wa_14015795083 */ - wa_write_clr(wal, GEN7_MISCCPCTL, GEN12_DOP_CLOCK_GATE_RENDER_ENABLE); + wa_mcr_write_clr(wal, GEN8_MISCCPCTL, GEN12_DOP_CLOCK_GATE_RENDER_ENABLE); +} + +static void +xelpg_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) +{ + /* FIXME: Actual workarounds will be added in future patch(es) */ + + /* + * Unlike older platforms, we no longer setup implicit steering here; + * all MCR accesses are explicitly steered. + */ + debug_dump_steering(gt); +} + +static void +xelpmp_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) +{ + /* FIXME: Actual workarounds will be added in future patch(es) */ + + debug_dump_steering(gt); } static void @@ -1524,7 +1642,18 @@ gt_init_workarounds(struct intel_gt *gt, struct i915_wa_list *wal) { struct drm_i915_private *i915 = gt->i915; - if (IS_PONTEVECCHIO(i915)) + if (gt->type == GT_MEDIA) { + if (MEDIA_VER(i915) >= 13) + xelpmp_gt_workarounds_init(gt, wal); + else + MISSING_CASE(MEDIA_VER(i915)); + + return; + } + + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) + xelpg_gt_workarounds_init(gt, wal); + else if (IS_PONTEVECCHIO(i915)) pvc_gt_workarounds_init(gt, wal); else if (IS_DG2(i915)) dg2_gt_workarounds_init(gt, wal); @@ -1572,7 +1701,7 @@ void intel_gt_init_workarounds(struct intel_gt *gt) { struct i915_wa_list *wal = >->wa_list; - wa_init_start(wal, "GT", "global"); + wa_init_start(wal, gt, "GT", "global"); gt_init_workarounds(gt, wal); wa_init_finish(wal); } @@ -1594,12 +1723,14 @@ wal_get_fw_for_rmw(struct intel_uncore *uncore, const struct i915_wa_list *wal) } static bool -wa_verify(const struct i915_wa *wa, u32 cur, const char *name, const char *from) +wa_verify(struct intel_gt *gt, const struct i915_wa *wa, u32 cur, + const char *name, const char *from) { if ((cur ^ wa->set) & wa->read) { - DRM_ERROR("%s workaround lost on %s! (reg[%x]=0x%x, relevant bits were 0x%x vs expected 0x%x)\n", - name, from, i915_mmio_reg_offset(wa->reg), - cur, cur & wa->read, wa->set & wa->read); + drm_err(>->i915->drm, + "%s workaround lost on %s! (reg[%x]=0x%x, relevant bits were 0x%x vs expected 0x%x)\n", + name, from, i915_mmio_reg_offset(wa->reg), + cur, cur & wa->read, wa->set & wa->read); return false; } @@ -1607,9 +1738,9 @@ wa_verify(const struct i915_wa *wa, u32 cur, const char *name, const char *from) return true; } -static void -wa_list_apply(struct intel_gt *gt, const struct i915_wa_list *wal) +static void wa_list_apply(const struct i915_wa_list *wal) { + struct intel_gt *gt = wal->gt; struct intel_uncore *uncore = gt->uncore; enum forcewake_domains fw; unsigned long flags; @@ -1628,14 +1759,25 @@ wa_list_apply(struct intel_gt *gt, const struct i915_wa_list *wal) u32 val, old = 0; /* open-coded rmw due to steering */ - old = wa->clr ? intel_gt_mcr_read_any_fw(gt, wa->reg) : 0; + if (wa->clr) + old = wa->is_mcr ? + intel_gt_mcr_read_any_fw(gt, wa->mcr_reg) : + intel_uncore_read_fw(uncore, wa->reg); val = (old & ~wa->clr) | wa->set; - if (val != old || !wa->clr) - intel_uncore_write_fw(uncore, wa->reg, val); + if (val != old || !wa->clr) { + if (wa->is_mcr) + intel_gt_mcr_multicast_write_fw(gt, wa->mcr_reg, val); + else + intel_uncore_write_fw(uncore, wa->reg, val); + } + + if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)) { + u32 val = wa->is_mcr ? + intel_gt_mcr_read_any_fw(gt, wa->mcr_reg) : + intel_uncore_read_fw(uncore, wa->reg); - if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)) - wa_verify(wa, intel_gt_mcr_read_any_fw(gt, wa->reg), - wal->name, "application"); + wa_verify(gt, wa, val, wal->name, "application"); + } } intel_uncore_forcewake_put__locked(uncore, fw); @@ -1644,7 +1786,7 @@ wa_list_apply(struct intel_gt *gt, const struct i915_wa_list *wal) void intel_gt_apply_workarounds(struct intel_gt *gt) { - wa_list_apply(gt, >->wa_list); + wa_list_apply(>->wa_list); } static bool wa_list_verify(struct intel_gt *gt, @@ -1664,8 +1806,9 @@ static bool wa_list_verify(struct intel_gt *gt, intel_uncore_forcewake_get__locked(uncore, fw); for (i = 0, wa = wal->list; i < wal->count; i++, wa++) - ok &= wa_verify(wa, - intel_gt_mcr_read_any_fw(gt, wa->reg), + ok &= wa_verify(wal->gt, wa, wa->is_mcr ? + intel_gt_mcr_read_any_fw(gt, wa->mcr_reg) : + intel_uncore_read_fw(uncore, wa->reg), wal->name, from); intel_uncore_forcewake_put__locked(uncore, fw); @@ -1712,11 +1855,35 @@ whitelist_reg_ext(struct i915_wa_list *wal, i915_reg_t reg, u32 flags) } static void +whitelist_mcr_reg_ext(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 flags) +{ + struct i915_wa wa = { + .mcr_reg = reg, + .is_mcr = 1, + }; + + if (GEM_DEBUG_WARN_ON(wal->count >= RING_MAX_NONPRIV_SLOTS)) + return; + + if (GEM_DEBUG_WARN_ON(!is_nonpriv_flags_valid(flags))) + return; + + wa.mcr_reg.reg |= flags; + _wa_add(wal, &wa); +} + +static void whitelist_reg(struct i915_wa_list *wal, i915_reg_t reg) { whitelist_reg_ext(wal, reg, RING_FORCE_TO_NONPRIV_ACCESS_RW); } +static void +whitelist_mcr_reg(struct i915_wa_list *wal, i915_mcr_reg_t reg) +{ + whitelist_mcr_reg_ext(wal, reg, RING_FORCE_TO_NONPRIV_ACCESS_RW); +} + static void gen9_whitelist_build(struct i915_wa_list *w) { /* WaVFEStateAfterPipeControlwithMediaStateClear:skl,bxt,glk,cfl */ @@ -1742,7 +1909,7 @@ static void skl_whitelist_build(struct intel_engine_cs *engine) gen9_whitelist_build(w); /* WaDisableLSQCROPERFforOCL:skl */ - whitelist_reg(w, GEN8_L3SQCREG4); + whitelist_mcr_reg(w, GEN8_L3SQCREG4); } static void bxt_whitelist_build(struct intel_engine_cs *engine) @@ -1763,7 +1930,7 @@ static void kbl_whitelist_build(struct intel_engine_cs *engine) gen9_whitelist_build(w); /* WaDisableLSQCROPERFforOCL:kbl */ - whitelist_reg(w, GEN8_L3SQCREG4); + whitelist_mcr_reg(w, GEN8_L3SQCREG4); } static void glk_whitelist_build(struct intel_engine_cs *engine) @@ -1828,10 +1995,10 @@ static void icl_whitelist_build(struct intel_engine_cs *engine) switch (engine->class) { case RENDER_CLASS: /* WaAllowUMDToModifyHalfSliceChicken7:icl */ - whitelist_reg(w, GEN9_HALF_SLICE_CHICKEN7); + whitelist_mcr_reg(w, GEN9_HALF_SLICE_CHICKEN7); /* WaAllowUMDToModifySamplerMode:icl */ - whitelist_reg(w, GEN10_SAMPLER_MODE); + whitelist_mcr_reg(w, GEN10_SAMPLER_MODE); /* WaEnableStateCacheRedirectToCS:icl */ whitelist_reg(w, GEN9_SLICE_COMMON_ECO_CHICKEN1); @@ -1987,7 +2154,7 @@ void intel_engine_init_whitelist(struct intel_engine_cs *engine) struct drm_i915_private *i915 = engine->i915; struct i915_wa_list *w = &engine->whitelist; - wa_init_start(w, "whitelist", engine->name); + wa_init_start(w, engine->gt, "whitelist", engine->name); if (IS_PONTEVECCHIO(i915)) pvc_whitelist_build(engine); @@ -2107,24 +2274,21 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) if (IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0)) { /* Wa_14013392000:dg2_g11 */ - wa_masked_en(wal, GEN7_ROW_CHICKEN2, GEN12_ENABLE_LARGE_GRF_MODE); - - /* Wa_16011620976:dg2_g11 */ - wa_write_or(wal, LSC_CHICKEN_BIT_0_UDW, DIS_CHAIN_2XSIMD8); + wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN2, GEN12_ENABLE_LARGE_GRF_MODE); } if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_FOREVER) || IS_DG2_G11(i915) || IS_DG2_G12(i915)) { /* Wa_1509727124:dg2 */ - wa_masked_en(wal, GEN10_SAMPLER_MODE, - SC_DISABLE_POWER_OPTIMIZATION_EBB); + wa_mcr_masked_en(wal, GEN10_SAMPLER_MODE, + SC_DISABLE_POWER_OPTIMIZATION_EBB); } if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0) || IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0)) { /* Wa_14012419201:dg2 */ - wa_masked_en(wal, GEN9_ROW_CHICKEN4, - GEN12_DISABLE_HDR_PAST_PAYLOAD_HOLD_FIX); + wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN4, + GEN12_DISABLE_HDR_PAST_PAYLOAD_HOLD_FIX); } if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_C0) || @@ -2133,13 +2297,13 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) * Wa_22012826095:dg2 * Wa_22013059131:dg2 */ - wa_write_clr_set(wal, LSC_CHICKEN_BIT_0_UDW, - MAXREQS_PER_BANK, - REG_FIELD_PREP(MAXREQS_PER_BANK, 2)); + wa_mcr_write_clr_set(wal, LSC_CHICKEN_BIT_0_UDW, + MAXREQS_PER_BANK, + REG_FIELD_PREP(MAXREQS_PER_BANK, 2)); /* Wa_22013059131:dg2 */ - wa_write_or(wal, LSC_CHICKEN_BIT_0, - FORCE_1_SUB_MESSAGE_PER_FRAGMENT); + wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0, + FORCE_1_SUB_MESSAGE_PER_FRAGMENT); } /* Wa_1308578152:dg2_g10 when first gslice is fused off */ @@ -2152,19 +2316,19 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_FOREVER) || IS_DG2_G11(i915) || IS_DG2_G12(i915)) { /* Wa_22013037850:dg2 */ - wa_write_or(wal, LSC_CHICKEN_BIT_0_UDW, - DISABLE_128B_EVICTION_COMMAND_UDW); + wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0_UDW, + DISABLE_128B_EVICTION_COMMAND_UDW); /* Wa_22012856258:dg2 */ - wa_masked_en(wal, GEN7_ROW_CHICKEN2, - GEN12_DISABLE_READ_SUPPRESSION); + wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN2, + GEN12_DISABLE_READ_SUPPRESSION); /* * Wa_22010960976:dg2 * Wa_14013347512:dg2 */ - wa_masked_dis(wal, GEN12_HDC_CHICKEN0, - LSC_L1_FLUSH_CTL_3D_DATAPORT_FLUSH_EVENTS_MASK); + wa_mcr_masked_dis(wal, XEHP_HDC_CHICKEN0, + LSC_L1_FLUSH_CTL_3D_DATAPORT_FLUSH_EVENTS_MASK); } if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) { @@ -2172,8 +2336,8 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) * Wa_1608949956:dg2_g10 * Wa_14010198302:dg2_g10 */ - wa_masked_en(wal, GEN8_ROW_CHICKEN, - MDQ_ARBITRATION_MODE | UGM_BACKUP_MODE); + wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN, + MDQ_ARBITRATION_MODE | UGM_BACKUP_MODE); /* * Wa_14010918519:dg2_g10 @@ -2181,31 +2345,31 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) * LSC_CHICKEN_BIT_0 always reads back as 0 is this stepping, * so ignoring verification. */ - wa_add(wal, LSC_CHICKEN_BIT_0_UDW, 0, - FORCE_SLM_FENCE_SCOPE_TO_TILE | FORCE_UGM_FENCE_SCOPE_TO_TILE, - 0, false); + wa_mcr_add(wal, LSC_CHICKEN_BIT_0_UDW, 0, + FORCE_SLM_FENCE_SCOPE_TO_TILE | FORCE_UGM_FENCE_SCOPE_TO_TILE, + 0, false); } if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) { /* Wa_22010430635:dg2 */ - wa_masked_en(wal, - GEN9_ROW_CHICKEN4, - GEN12_DISABLE_GRF_CLEAR); + wa_mcr_masked_en(wal, + GEN9_ROW_CHICKEN4, + GEN12_DISABLE_GRF_CLEAR); /* Wa_14010648519:dg2 */ - wa_write_or(wal, XEHP_L3NODEARBCFG, XEHP_LNESPARE); + wa_mcr_write_or(wal, XEHP_L3NODEARBCFG, XEHP_LNESPARE); } /* Wa_14013202645:dg2 */ if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_C0) || IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0)) - wa_write_or(wal, RT_CTRL, DIS_NULL_QUERY); + wa_mcr_write_or(wal, RT_CTRL, DIS_NULL_QUERY); /* Wa_22012532006:dg2 */ if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_C0) || IS_DG2_GRAPHICS_STEP(engine->i915, G11, STEP_A0, STEP_B0)) - wa_masked_en(wal, GEN9_HALF_SLICE_CHICKEN7, - DG2_DISABLE_ROUND_ENABLE_ALLOW_FOR_SSLA); + wa_mcr_masked_en(wal, GEN9_HALF_SLICE_CHICKEN7, + DG2_DISABLE_ROUND_ENABLE_ALLOW_FOR_SSLA); if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0)) { /* Wa_14010680813:dg2_g10 */ @@ -2216,17 +2380,16 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0) || IS_DG2_GRAPHICS_STEP(engine->i915, G11, STEP_A0, STEP_B0)) { /* Wa_14012362059:dg2 */ - wa_write_or(wal, GEN12_MERT_MOD_CTRL, FORCE_MISS_FTLB); + wa_mcr_write_or(wal, XEHP_MERT_MOD_CTRL, FORCE_MISS_FTLB); } if (IS_DG2_GRAPHICS_STEP(i915, G11, STEP_B0, STEP_FOREVER) || IS_DG2_G10(i915)) { /* Wa_22014600077:dg2 */ - wa_add(wal, GEN10_CACHE_MODE_SS, 0, - _MASKED_BIT_ENABLE(ENABLE_EU_COUNT_FOR_TDL_FLUSH), - 0 /* Wa_14012342262 :write-only reg, so skip - verification */, - true); + wa_mcr_add(wal, GEN10_CACHE_MODE_SS, 0, + _MASKED_BIT_ENABLE(ENABLE_EU_COUNT_FOR_TDL_FLUSH), + 0 /* Wa_14012342262 write-only reg, so skip verification */, + true); } if (IS_DG1_GRAPHICS_STEP(i915, STEP_A0, STEP_B0) || @@ -2253,7 +2416,7 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) if (IS_ALDERLAKE_P(i915) || IS_ALDERLAKE_S(i915) || IS_DG1(i915) || IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) { /* Wa_1606931601:tgl,rkl,dg1,adl-s,adl-p */ - wa_masked_en(wal, GEN7_ROW_CHICKEN2, GEN12_DISABLE_EARLY_READ); + wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN2, GEN12_DISABLE_EARLY_READ); /* * Wa_1407928979:tgl A* @@ -2282,14 +2445,14 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) IS_DG1_GRAPHICS_STEP(i915, STEP_A0, STEP_B0) || IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) { /* Wa_1409804808:tgl,rkl,dg1[a0],adl-s,adl-p */ - wa_masked_en(wal, GEN7_ROW_CHICKEN2, - GEN12_PUSH_CONST_DEREF_HOLD_DIS); + wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN2, + GEN12_PUSH_CONST_DEREF_HOLD_DIS); /* * Wa_1409085225:tgl * Wa_14010229206:tgl,rkl,dg1[a0],adl-s,adl-p */ - wa_masked_en(wal, GEN9_ROW_CHICKEN4, GEN12_DISABLE_TDL_PUSH); + wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN4, GEN12_DISABLE_TDL_PUSH); } if (IS_DG1_GRAPHICS_STEP(i915, STEP_A0, STEP_B0) || @@ -2313,9 +2476,9 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) if (IS_DG1(i915) || IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915) || IS_ALDERLAKE_S(i915) || IS_ALDERLAKE_P(i915)) { /* Wa_1406941453:tgl,rkl,dg1,adl-s,adl-p */ - wa_masked_en(wal, - GEN10_SAMPLER_MODE, - ENABLE_SMALLPL); + wa_mcr_masked_en(wal, + GEN10_SAMPLER_MODE, + ENABLE_SMALLPL); } if (GRAPHICS_VER(i915) == 11) { @@ -2349,9 +2512,9 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) * Wa_1405733216:icl * Formerly known as WaDisableCleanEvicts */ - wa_write_or(wal, - GEN8_L3SQCREG4, - GEN11_LQSC_CLEAN_EVICT_DISABLE); + wa_mcr_write_or(wal, + GEN8_L3SQCREG4, + GEN11_LQSC_CLEAN_EVICT_DISABLE); /* Wa_1606682166:icl */ wa_write_or(wal, @@ -2359,10 +2522,10 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) GEN7_DISABLE_SAMPLER_PREFETCH); /* Wa_1409178092:icl */ - wa_write_clr_set(wal, - GEN11_SCRATCH2, - GEN11_COHERENT_PARTIAL_WRITE_MERGE_ENABLE, - 0); + wa_mcr_write_clr_set(wal, + GEN11_SCRATCH2, + GEN11_COHERENT_PARTIAL_WRITE_MERGE_ENABLE, + 0); /* WaEnable32PlaneMode:icl */ wa_masked_en(wal, GEN9_CSFE_CHICKEN1_RCS, @@ -2389,12 +2552,64 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) FF_DOP_CLOCK_GATE_DISABLE); } - if (IS_GRAPHICS_VER(i915, 9, 12)) { - /* FtrPerCtxtPreemptionGranularityControl:skl,bxt,kbl,cfl,cnl,icl,tgl */ + /* + * Intel platforms that support fine-grained preemption (i.e., gen9 and + * beyond) allow the kernel-mode driver to choose between two different + * options for controlling preemption granularity and behavior. + * + * Option 1 (hardware default): + * Preemption settings are controlled in a global manner via + * kernel-only register CS_DEBUG_MODE1 (0x20EC). Any granularity + * and settings chosen by the kernel-mode driver will apply to all + * userspace clients. + * + * Option 2: + * Preemption settings are controlled on a per-context basis via + * register CS_CHICKEN1 (0x2580). CS_CHICKEN1 is saved/restored on + * context switch and is writable by userspace (e.g., via + * MI_LOAD_REGISTER_IMMEDIATE instructions placed in a batch buffer) + * which allows different userspace drivers/clients to select + * different settings, or to change those settings on the fly in + * response to runtime needs. This option was known by name + * "FtrPerCtxtPreemptionGranularityControl" at one time, although + * that name is somewhat misleading as other non-granularity + * preemption settings are also impacted by this decision. + * + * On Linux, our policy has always been to let userspace drivers + * control preemption granularity/settings (Option 2). This was + * originally mandatory on gen9 to prevent ABI breakage (old gen9 + * userspace developed before object-level preemption was enabled would + * not behave well if i915 were to go with Option 1 and enable that + * preemption in a global manner). On gen9 each context would have + * object-level preemption disabled by default (see + * WaDisable3DMidCmdPreemption in gen9_ctx_workarounds_init), but + * userspace drivers could opt-in to object-level preemption as they + * saw fit. For post-gen9 platforms, we continue to utilize Option 2; + * even though it is no longer necessary for ABI compatibility when + * enabling a new platform, it does ensure that userspace will be able + * to implement any workarounds that show up requiring temporary + * adjustments to preemption behavior at runtime. + * + * Notes/Workarounds: + * - Wa_14015141709: On DG2 and early steppings of MTL, + * CS_CHICKEN1[0] does not disable object-level preemption as + * it is supposed to (nor does CS_DEBUG_MODE1[0] if we had been + * using Option 1). Effectively this means userspace is unable + * to disable object-level preemption on these platforms/steppings + * despite the setting here. + * + * - Wa_16013994831: May require that userspace program + * CS_CHICKEN1[10] when certain runtime conditions are true. + * Userspace requires Option 2 to be in effect for their update of + * CS_CHICKEN1[10] to be effective. + * + * Other workarounds may appear in the future that will also require + * Option 2 behavior to allow proper userspace implementation. + */ + if (GRAPHICS_VER(i915) >= 9) wa_masked_en(wal, GEN7_FF_SLICE_CS_CHICKEN1, GEN9_FFSC_PERCTX_PREEMPT_CTRL); - } if (IS_SKYLAKE(i915) || IS_KABYLAKE(i915) || @@ -2420,36 +2635,36 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE); /* WaEnableLbsSlaRetryTimerDecrement:skl,bxt,kbl,glk,cfl */ - wa_write_or(wal, - BDW_SCRATCH1, - GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE); + wa_mcr_write_or(wal, + BDW_SCRATCH1, + GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE); /* WaProgramL3SqcReg1DefaultForPerf:bxt,glk */ if (IS_GEN9_LP(i915)) - wa_write_clr_set(wal, - GEN8_L3SQCREG1, - L3_PRIO_CREDITS_MASK, - L3_GENERAL_PRIO_CREDITS(62) | - L3_HIGH_PRIO_CREDITS(2)); + wa_mcr_write_clr_set(wal, + GEN8_L3SQCREG1, + L3_PRIO_CREDITS_MASK, + L3_GENERAL_PRIO_CREDITS(62) | + L3_HIGH_PRIO_CREDITS(2)); /* WaOCLCoherentLineFlush:skl,bxt,kbl,cfl */ - wa_write_or(wal, - GEN8_L3SQCREG4, - GEN8_LQSC_FLUSH_COHERENT_LINES); + wa_mcr_write_or(wal, + GEN8_L3SQCREG4, + GEN8_LQSC_FLUSH_COHERENT_LINES); /* Disable atomics in L3 to prevent unrecoverable hangs */ wa_write_clr_set(wal, GEN9_SCRATCH_LNCF1, GEN9_LNCF_NONIA_COHERENT_ATOMICS_ENABLE, 0); - wa_write_clr_set(wal, GEN8_L3SQCREG4, - GEN8_LQSQ_NONIA_COHERENT_ATOMICS_ENABLE, 0); - wa_write_clr_set(wal, GEN9_SCRATCH1, - EVICTION_PERF_FIX_ENABLE, 0); + wa_mcr_write_clr_set(wal, GEN8_L3SQCREG4, + GEN8_LQSQ_NONIA_COHERENT_ATOMICS_ENABLE, 0); + wa_mcr_write_clr_set(wal, GEN9_SCRATCH1, + EVICTION_PERF_FIX_ENABLE, 0); } if (IS_HASWELL(i915)) { /* WaSampleCChickenBitEnable:hsw */ wa_masked_en(wal, - HALF_SLICE_CHICKEN3, HSW_SAMPLE_C_PERFORMANCE); + HSW_HALF_SLICE_CHICKEN3, HSW_SAMPLE_C_PERFORMANCE); wa_masked_dis(wal, CACHE_MODE_0_GEN7, @@ -2657,7 +2872,7 @@ ccs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) { if (IS_PVC_CT_STEP(engine->i915, STEP_A0, STEP_C0)) { /* Wa_14014999345:pvc */ - wa_masked_en(wal, GEN10_CACHE_MODE_SS, DISABLE_ECC); + wa_mcr_masked_en(wal, GEN10_CACHE_MODE_SS, DISABLE_ECC); } } @@ -2683,8 +2898,8 @@ add_render_compute_tuning_settings(struct drm_i915_private *i915, } if (IS_DG2(i915)) { - wa_write_or(wal, XEHP_L3SCQREG7, BLEND_FILL_CACHING_OPT_DIS); - wa_write_clr_set(wal, RT_CTRL, STACKID_CTRL, STACKID_CTRL_512); + wa_mcr_write_or(wal, XEHP_L3SCQREG7, BLEND_FILL_CACHING_OPT_DIS); + wa_mcr_write_clr_set(wal, RT_CTRL, STACKID_CTRL, STACKID_CTRL_512); /* * This is also listed as Wa_22012654132 for certain DG2 @@ -2695,10 +2910,10 @@ add_render_compute_tuning_settings(struct drm_i915_private *i915, * back for verification on DG2 (due to Wa_14012342262), so * we need to explicitly skip the readback. */ - wa_add(wal, GEN10_CACHE_MODE_SS, 0, - _MASKED_BIT_ENABLE(ENABLE_PREFETCH_INTO_IC), - 0 /* write-only, so skip validation */, - true); + wa_mcr_add(wal, GEN10_CACHE_MODE_SS, 0, + _MASKED_BIT_ENABLE(ENABLE_PREFETCH_INTO_IC), + 0 /* write-only, so skip validation */, + true); } /* @@ -2707,8 +2922,8 @@ add_render_compute_tuning_settings(struct drm_i915_private *i915, * platforms. */ if (INTEL_INFO(i915)->tuning_thread_rr_after_dep) - wa_masked_field_set(wal, GEN9_ROW_CHICKEN4, THREAD_EX_ARB_MODE, - THREAD_EX_ARB_MODE_RR_AFTER_DEP); + wa_mcr_masked_field_set(wal, GEN9_ROW_CHICKEN4, THREAD_EX_ARB_MODE, + THREAD_EX_ARB_MODE_RR_AFTER_DEP); } /* @@ -2734,30 +2949,30 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li if (IS_XEHPSDV(i915)) { /* Wa_1409954639 */ - wa_masked_en(wal, - GEN8_ROW_CHICKEN, - SYSTOLIC_DOP_CLOCK_GATING_DIS); + wa_mcr_masked_en(wal, + GEN8_ROW_CHICKEN, + SYSTOLIC_DOP_CLOCK_GATING_DIS); /* Wa_1607196519 */ - wa_masked_en(wal, - GEN9_ROW_CHICKEN4, - GEN12_DISABLE_GRF_CLEAR); + wa_mcr_masked_en(wal, + GEN9_ROW_CHICKEN4, + GEN12_DISABLE_GRF_CLEAR); /* Wa_14010670810:xehpsdv */ - wa_write_or(wal, XEHP_L3NODEARBCFG, XEHP_LNESPARE); + wa_mcr_write_or(wal, XEHP_L3NODEARBCFG, XEHP_LNESPARE); /* Wa_14010449647:xehpsdv */ - wa_masked_en(wal, GEN7_HALF_SLICE_CHICKEN1, - GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE); + wa_mcr_masked_en(wal, GEN8_HALF_SLICE_CHICKEN1, + GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE); /* Wa_18011725039:xehpsdv */ if (IS_XEHPSDV_GRAPHICS_STEP(i915, STEP_A1, STEP_B0)) { - wa_masked_dis(wal, MLTICTXCTL, TDONRENDER); - wa_write_or(wal, L3SQCREG1_CCS0, FLUSHALLNONCOH); + wa_mcr_masked_dis(wal, MLTICTXCTL, TDONRENDER); + wa_mcr_write_or(wal, L3SQCREG1_CCS0, FLUSHALLNONCOH); } /* Wa_14012362059:xehpsdv */ - wa_write_or(wal, GEN12_MERT_MOD_CTRL, FORCE_MISS_FTLB); + wa_mcr_write_or(wal, XEHP_MERT_MOD_CTRL, FORCE_MISS_FTLB); /* Wa_14014368820:xehpsdv */ wa_write_or(wal, GEN12_GAMCNTRL_CTRL, INVALIDATION_BROADCAST_MODE_DIS | @@ -2766,26 +2981,37 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li if (IS_DG2(i915) || IS_PONTEVECCHIO(i915)) { /* Wa_14015227452:dg2,pvc */ - wa_masked_en(wal, GEN9_ROW_CHICKEN4, XEHP_DIS_BBL_SYSPIPE); + wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN4, XEHP_DIS_BBL_SYSPIPE); /* Wa_22014226127:dg2,pvc */ - wa_write_or(wal, LSC_CHICKEN_BIT_0, DISABLE_D8_D16_COASLESCE); + wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0, DISABLE_D8_D16_COASLESCE); /* Wa_16015675438:dg2,pvc */ wa_masked_en(wal, FF_SLICE_CS_CHICKEN2, GEN12_PERF_FIX_BALANCING_CFE_DISABLE); /* Wa_18018781329:dg2,pvc */ - wa_write_or(wal, RENDER_MOD_CTRL, FORCE_MISS_FTLB); - wa_write_or(wal, COMP_MOD_CTRL, FORCE_MISS_FTLB); - wa_write_or(wal, VDBX_MOD_CTRL, FORCE_MISS_FTLB); - wa_write_or(wal, VEBX_MOD_CTRL, FORCE_MISS_FTLB); + wa_mcr_write_or(wal, RENDER_MOD_CTRL, FORCE_MISS_FTLB); + wa_mcr_write_or(wal, COMP_MOD_CTRL, FORCE_MISS_FTLB); + wa_mcr_write_or(wal, VDBX_MOD_CTRL, FORCE_MISS_FTLB); + wa_mcr_write_or(wal, VEBX_MOD_CTRL, FORCE_MISS_FTLB); + } + + if (IS_DG2(i915)) { + /* + * Wa_16011620976:dg2_g11 + * Wa_22015475538:dg2 + */ + wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0_UDW, DIS_CHAIN_2XSIMD8); + + /* Wa_18017747507:dg2 */ + wa_masked_en(wal, VFG_PREEMPTION_CHICKEN, POLYGON_TRIFAN_LINELOOP_DISABLE); } } static void engine_init_workarounds(struct intel_engine_cs *engine, struct i915_wa_list *wal) { - if (I915_SELFTEST_ONLY(GRAPHICS_VER(engine->i915) < 4)) + if (GRAPHICS_VER(engine->i915) < 4) return; engine_fake_wa_init(engine, wal); @@ -2810,17 +3036,14 @@ void intel_engine_init_workarounds(struct intel_engine_cs *engine) { struct i915_wa_list *wal = &engine->wa_list; - if (GRAPHICS_VER(engine->i915) < 4) - return; - - wa_init_start(wal, "engine", engine->name); + wa_init_start(wal, engine->gt, "engine", engine->name); engine_init_workarounds(engine, wal); wa_init_finish(wal); } void intel_engine_apply_workarounds(struct intel_engine_cs *engine) { - wa_list_apply(engine->gt, &engine->wa_list); + wa_list_apply(&engine->wa_list); } static const struct i915_range mcr_ranges_gen8[] = { @@ -2964,9 +3187,7 @@ retry: goto err_vma; } - err = i915_request_await_object(rq, vma->obj, true); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); if (err == 0) err = wa_list_srm(rq, wal, vma); @@ -2994,7 +3215,7 @@ retry: if (mcr_range(rq->engine->i915, i915_mmio_reg_offset(wa->reg))) continue; - if (!wa_verify(wa, results[i], wal->name, from)) + if (!wa_verify(wal->gt, wa, results[i], wal->name, from)) err = -ENXIO; } diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds_types.h b/drivers/gpu/drm/i915/gt/intel_workarounds_types.h index 8a4b6de4e754..e14188120e66 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds_types.h +++ b/drivers/gpu/drm/i915/gt/intel_workarounds_types.h @@ -10,15 +10,23 @@ #include "i915_reg_defs.h" +struct intel_gt; + struct i915_wa { - i915_reg_t reg; + union { + i915_reg_t reg; + i915_mcr_reg_t mcr_reg; + }; u32 clr; u32 set; u32 read; - bool masked_reg; + + u32 masked_reg:1; + u32 is_mcr:1; }; struct i915_wa_list { + struct intel_gt *gt; const char *name; const char *engine_name; struct i915_wa *list; diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_cs.c b/drivers/gpu/drm/i915/gt/selftest_engine_cs.c index 1b75f478d1b8..881b64f3e7b9 100644 --- a/drivers/gpu/drm/i915/gt/selftest_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/selftest_engine_cs.c @@ -39,6 +39,16 @@ static int perf_end(struct intel_gt *gt) return igt_flush_test(gt->i915); } +static i915_reg_t timestamp_reg(struct intel_engine_cs *engine) +{ + struct drm_i915_private *i915 = engine->i915; + + if (GRAPHICS_VER(i915) == 5 || IS_G4X(i915)) + return RING_TIMESTAMP_UDW(engine->mmio_base); + else + return RING_TIMESTAMP(engine->mmio_base); +} + static int write_timestamp(struct i915_request *rq, int slot) { struct intel_timeline *tl = @@ -55,7 +65,7 @@ static int write_timestamp(struct i915_request *rq, int slot) if (GRAPHICS_VER(rq->engine->i915) >= 8) cmd++; *cs++ = cmd; - *cs++ = i915_mmio_reg_offset(RING_TIMESTAMP(rq->engine->mmio_base)); + *cs++ = i915_mmio_reg_offset(timestamp_reg(rq->engine)); *cs++ = tl->hwsp_offset + slot * sizeof(u32); *cs++ = 0; @@ -125,7 +135,7 @@ static int perf_mi_bb_start(void *arg) enum intel_engine_id id; int err = 0; - if (GRAPHICS_VER(gt->i915) < 7) /* for per-engine CS_TIMESTAMP */ + if (GRAPHICS_VER(gt->i915) < 4) /* Any CS_TIMESTAMP? */ return 0; perf_begin(gt); @@ -135,6 +145,9 @@ static int perf_mi_bb_start(void *arg) u32 cycles[COUNT]; int i; + if (GRAPHICS_VER(engine->i915) < 7 && engine->id != RCS0) + continue; + intel_engine_pm_get(engine); batch = create_empty_batch(ce); @@ -249,7 +262,7 @@ static int perf_mi_noop(void *arg) enum intel_engine_id id; int err = 0; - if (GRAPHICS_VER(gt->i915) < 7) /* for per-engine CS_TIMESTAMP */ + if (GRAPHICS_VER(gt->i915) < 4) /* Any CS_TIMESTAMP? */ return 0; perf_begin(gt); @@ -259,6 +272,9 @@ static int perf_mi_noop(void *arg) u32 cycles[COUNT]; int i; + if (GRAPHICS_VER(engine->i915) < 7 && engine->id != RCS0) + continue; + intel_engine_pm_get(engine); base = create_empty_batch(ce); diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_pm.c b/drivers/gpu/drm/i915/gt/selftest_engine_pm.c index 0dcb3ed44a73..87c94314cf67 100644 --- a/drivers/gpu/drm/i915/gt/selftest_engine_pm.c +++ b/drivers/gpu/drm/i915/gt/selftest_engine_pm.c @@ -317,7 +317,7 @@ static int live_engine_busy_stats(void *arg) ENGINE_TRACE(engine, "measuring busy time\n"); preempt_disable(); de = intel_engine_get_busy_time(engine, &t[0]); - mdelay(10); + mdelay(100); de = ktime_sub(intel_engine_get_busy_time(engine, &t[1]), de); preempt_enable(); dt = ktime_sub(t[1], t[0]); diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c index 1e08b2473b99..ab2e9a6a2452 100644 --- a/drivers/gpu/drm/i915/gt/selftest_execlists.c +++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c @@ -85,8 +85,6 @@ static int wait_for_reset(struct intel_engine_cs *engine, break; } while (time_before(jiffies, timeout)); - flush_scheduled_work(); - if (rq->fence.error != -EIO) { pr_err("%s: hanging request %llx:%lld not reset\n", engine->name, @@ -2766,9 +2764,7 @@ static int create_gang(struct intel_engine_cs *engine, i915_request_get(rq); i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, false); - if (!err) - err = i915_vma_move_to_active(vma, rq, 0); + err = i915_vma_move_to_active(vma, rq, 0); if (!err) err = rq->engine->emit_bb_start(rq, vma->node.start, @@ -3182,15 +3178,11 @@ create_gpr_client(struct intel_engine_cs *engine, } i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, false); - if (!err) - err = i915_vma_move_to_active(vma, rq, 0); + err = i915_vma_move_to_active(vma, rq, 0); i915_vma_unlock(vma); i915_vma_lock(batch); if (!err) - err = i915_request_await_object(rq, batch->obj, false); - if (!err) err = i915_vma_move_to_active(batch, rq, 0); if (!err) err = rq->engine->emit_bb_start(rq, @@ -3475,12 +3467,14 @@ static int random_priority(struct rnd_state *rnd) struct preempt_smoke { struct intel_gt *gt; + struct kthread_work work; struct i915_gem_context **contexts; struct intel_engine_cs *engine; struct drm_i915_gem_object *batch; unsigned int ncontext; struct rnd_state prng; unsigned long count; + int result; }; static struct i915_gem_context *smoke_context(struct preempt_smoke *smoke) @@ -3521,9 +3515,7 @@ static int smoke_submit(struct preempt_smoke *smoke, if (vma) { i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, false); - if (!err) - err = i915_vma_move_to_active(vma, rq, 0); + err = i915_vma_move_to_active(vma, rq, 0); if (!err) err = rq->engine->emit_bb_start(rq, vma->node.start, @@ -3540,34 +3532,31 @@ unpin: return err; } -static int smoke_crescendo_thread(void *arg) +static void smoke_crescendo_work(struct kthread_work *work) { - struct preempt_smoke *smoke = arg; + struct preempt_smoke *smoke = container_of(work, typeof(*smoke), work); IGT_TIMEOUT(end_time); unsigned long count; count = 0; do { struct i915_gem_context *ctx = smoke_context(smoke); - int err; - err = smoke_submit(smoke, - ctx, count % I915_PRIORITY_MAX, - smoke->batch); - if (err) - return err; + smoke->result = smoke_submit(smoke, ctx, + count % I915_PRIORITY_MAX, + smoke->batch); count++; - } while (count < smoke->ncontext && !__igt_timeout(end_time, NULL)); + } while (!smoke->result && count < smoke->ncontext && + !__igt_timeout(end_time, NULL)); smoke->count = count; - return 0; } static int smoke_crescendo(struct preempt_smoke *smoke, unsigned int flags) #define BATCH BIT(0) { - struct task_struct *tsk[I915_NUM_ENGINES] = {}; + struct kthread_worker *worker[I915_NUM_ENGINES] = {}; struct preempt_smoke *arg; struct intel_engine_cs *engine; enum intel_engine_id id; @@ -3578,6 +3567,8 @@ static int smoke_crescendo(struct preempt_smoke *smoke, unsigned int flags) if (!arg) return -ENOMEM; + memset(arg, 0, I915_NUM_ENGINES * sizeof(*arg)); + for_each_engine(engine, smoke->gt, id) { arg[id] = *smoke; arg[id].engine = engine; @@ -3585,31 +3576,28 @@ static int smoke_crescendo(struct preempt_smoke *smoke, unsigned int flags) arg[id].batch = NULL; arg[id].count = 0; - tsk[id] = kthread_run(smoke_crescendo_thread, arg, - "igt/smoke:%d", id); - if (IS_ERR(tsk[id])) { - err = PTR_ERR(tsk[id]); + worker[id] = kthread_create_worker(0, "igt/smoke:%d", id); + if (IS_ERR(worker[id])) { + err = PTR_ERR(worker[id]); break; } - get_task_struct(tsk[id]); - } - yield(); /* start all threads before we kthread_stop() */ + kthread_init_work(&arg[id].work, smoke_crescendo_work); + kthread_queue_work(worker[id], &arg[id].work); + } count = 0; for_each_engine(engine, smoke->gt, id) { - int status; - - if (IS_ERR_OR_NULL(tsk[id])) + if (IS_ERR_OR_NULL(worker[id])) continue; - status = kthread_stop(tsk[id]); - if (status && !err) - err = status; + kthread_flush_work(&arg[id].work); + if (arg[id].result && !err) + err = arg[id].result; count += arg[id].count; - put_task_struct(tsk[id]); + kthread_destroy_worker(worker[id]); } pr_info("Submitted %lu crescendo:%x requests across %d engines and %d contexts\n", diff --git a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c index be94f863bdef..b46425aeb2f0 100644 --- a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c @@ -36,6 +36,19 @@ static int cmp_u32(const void *A, const void *B) return 0; } +static u32 read_timestamp(struct intel_engine_cs *engine) +{ + struct drm_i915_private *i915 = engine->i915; + + /* On i965 the first read tends to give a stale value */ + ENGINE_READ_FW(engine, RING_TIMESTAMP); + + if (GRAPHICS_VER(i915) == 5 || IS_G4X(i915)) + return ENGINE_READ_FW(engine, RING_TIMESTAMP_UDW); + else + return ENGINE_READ_FW(engine, RING_TIMESTAMP); +} + static void measure_clocks(struct intel_engine_cs *engine, u32 *out_cycles, ktime_t *out_dt) { @@ -45,13 +58,13 @@ static void measure_clocks(struct intel_engine_cs *engine, for (i = 0; i < 5; i++) { local_irq_disable(); - cycles[i] = -ENGINE_READ_FW(engine, RING_TIMESTAMP); + cycles[i] = -read_timestamp(engine); dt[i] = ktime_get(); udelay(1000); dt[i] = ktime_sub(ktime_get(), dt[i]); - cycles[i] += ENGINE_READ_FW(engine, RING_TIMESTAMP); + cycles[i] += read_timestamp(engine); local_irq_enable(); } @@ -78,25 +91,6 @@ static int live_gt_clocks(void *arg) if (GRAPHICS_VER(gt->i915) < 4) /* Any CS_TIMESTAMP? */ return 0; - if (GRAPHICS_VER(gt->i915) == 5) - /* - * XXX CS_TIMESTAMP low dword is dysfunctional? - * - * Ville's experiments indicate the high dword still works, - * but at a correspondingly reduced frequency. - */ - return 0; - - if (GRAPHICS_VER(gt->i915) == 4) - /* - * XXX CS_TIMESTAMP appears gibberish - * - * Ville's experiments indicate that it mostly appears 'stuck' - * in that we see the register report the same cycle count - * for a couple of reads. - */ - return 0; - intel_gt_pm_get(gt); intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_ALL); diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c index 7f3bb1d34dfb..bc05ef48c194 100644 --- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c +++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c @@ -99,22 +99,6 @@ static u64 hws_address(const struct i915_vma *hws, return hws->node.start + offset_in_page(sizeof(u32)*rq->fence.context); } -static int move_to_active(struct i915_vma *vma, - struct i915_request *rq, - unsigned int flags) -{ - int err; - - i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, - flags & EXEC_OBJECT_WRITE); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, flags); - i915_vma_unlock(vma); - - return err; -} - static struct i915_request * hang_create_request(struct hang *h, struct intel_engine_cs *engine) { @@ -175,11 +159,11 @@ hang_create_request(struct hang *h, struct intel_engine_cs *engine) goto unpin_hws; } - err = move_to_active(vma, rq, 0); + err = igt_vma_move_to_active_unlocked(vma, rq, 0); if (err) goto cancel_rq; - err = move_to_active(hws, rq, 0); + err = igt_vma_move_to_active_unlocked(hws, rq, 0); if (err) goto cancel_rq; @@ -866,10 +850,13 @@ static int igt_reset_active_engine(void *arg) } struct active_engine { - struct task_struct *task; + struct kthread_worker *worker; + struct kthread_work work; struct intel_engine_cs *engine; unsigned long resets; unsigned int flags; + bool stop; + int result; }; #define TEST_ACTIVE BIT(0) @@ -900,10 +887,10 @@ static int active_request_put(struct i915_request *rq) return err; } -static int active_engine(void *data) +static void active_engine(struct kthread_work *work) { I915_RND_STATE(prng); - struct active_engine *arg = data; + struct active_engine *arg = container_of(work, typeof(*arg), work); struct intel_engine_cs *engine = arg->engine; struct i915_request *rq[8] = {}; struct intel_context *ce[ARRAY_SIZE(rq)]; @@ -913,16 +900,17 @@ static int active_engine(void *data) for (count = 0; count < ARRAY_SIZE(ce); count++) { ce[count] = intel_context_create(engine); if (IS_ERR(ce[count])) { - err = PTR_ERR(ce[count]); - pr_err("[%s] Create context #%ld failed: %d!\n", engine->name, count, err); + arg->result = PTR_ERR(ce[count]); + pr_err("[%s] Create context #%ld failed: %d!\n", + engine->name, count, arg->result); while (--count) intel_context_put(ce[count]); - return err; + return; } } count = 0; - while (!kthread_should_stop()) { + while (!READ_ONCE(arg->stop)) { unsigned int idx = count++ & (ARRAY_SIZE(rq) - 1); struct i915_request *old = rq[idx]; struct i915_request *new; @@ -967,7 +955,7 @@ static int active_engine(void *data) intel_context_put(ce[count]); } - return err; + arg->result = err; } static int __igt_reset_engines(struct intel_gt *gt, @@ -1022,7 +1010,7 @@ static int __igt_reset_engines(struct intel_gt *gt, memset(threads, 0, sizeof(*threads) * I915_NUM_ENGINES); for_each_engine(other, gt, tmp) { - struct task_struct *tsk; + struct kthread_worker *worker; threads[tmp].resets = i915_reset_engine_count(global, other); @@ -1036,19 +1024,21 @@ static int __igt_reset_engines(struct intel_gt *gt, threads[tmp].engine = other; threads[tmp].flags = flags; - tsk = kthread_run(active_engine, &threads[tmp], - "igt/%s", other->name); - if (IS_ERR(tsk)) { - err = PTR_ERR(tsk); - pr_err("[%s] Thread spawn failed: %d!\n", engine->name, err); + worker = kthread_create_worker(0, "igt/%s", + other->name); + if (IS_ERR(worker)) { + err = PTR_ERR(worker); + pr_err("[%s] Worker create failed: %d!\n", + engine->name, err); goto unwind; } - threads[tmp].task = tsk; - get_task_struct(tsk); - } + threads[tmp].worker = worker; - yield(); /* start all threads before we begin */ + kthread_init_work(&threads[tmp].work, active_engine); + kthread_queue_work(threads[tmp].worker, + &threads[tmp].work); + } st_engine_heartbeat_disable_no_pm(engine); GEM_BUG_ON(test_and_set_bit(I915_RESET_ENGINE + id, @@ -1197,17 +1187,20 @@ unwind: for_each_engine(other, gt, tmp) { int ret; - if (!threads[tmp].task) + if (!threads[tmp].worker) continue; - ret = kthread_stop(threads[tmp].task); + WRITE_ONCE(threads[tmp].stop, true); + kthread_flush_work(&threads[tmp].work); + ret = READ_ONCE(threads[tmp].result); if (ret) { pr_err("kthread for other engine %s failed, err=%d\n", other->name, ret); if (!err) err = ret; } - put_task_struct(threads[tmp].task); + + kthread_destroy_worker(threads[tmp].worker); /* GuC based resets are not logged per engine */ if (!using_guc) { @@ -1510,18 +1503,9 @@ static int __igt_reset_evict_vma(struct intel_gt *gt, } } - i915_vma_lock(arg.vma); - err = i915_request_await_object(rq, arg.vma->obj, - flags & EXEC_OBJECT_WRITE); - if (err == 0) { - err = i915_vma_move_to_active(arg.vma, rq, flags); - if (err) - pr_err("[%s] Move to active failed: %d!\n", engine->name, err); - } else { - pr_err("[%s] Request await failed: %d!\n", engine->name, err); - } - - i915_vma_unlock(arg.vma); + err = igt_vma_move_to_active_unlocked(arg.vma, rq, flags); + if (err) + pr_err("[%s] Move to active failed: %d!\n", engine->name, err); if (flags & EXEC_OBJECT_NEEDS_FENCE) i915_vma_unpin_fence(arg.vma); diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c index 82d3f8058995..7c56ffd2c659 100644 --- a/drivers/gpu/drm/i915/gt/selftest_lrc.c +++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c @@ -452,9 +452,7 @@ retry: *cs++ = i915_ggtt_offset(scratch) + RING_TAIL_IDX * sizeof(u32); *cs++ = 0; - err = i915_request_await_object(rq, scratch->obj, true); - if (!err) - err = i915_vma_move_to_active(scratch, rq, EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(scratch, rq, EXEC_OBJECT_WRITE); i915_request_get(rq); i915_request_add(rq); @@ -602,9 +600,7 @@ __gpr_read(struct intel_context *ce, struct i915_vma *scratch, u32 *slot) } i915_vma_lock(scratch); - err = i915_request_await_object(rq, scratch->obj, true); - if (!err) - err = i915_vma_move_to_active(scratch, rq, EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(scratch, rq, EXEC_OBJECT_WRITE); i915_vma_unlock(scratch); i915_request_get(rq); @@ -1053,21 +1049,6 @@ store_context(struct intel_context *ce, struct i915_vma *scratch) return batch; } -static int move_to_active(struct i915_request *rq, - struct i915_vma *vma, - unsigned int flags) -{ - int err; - - i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, flags); - if (!err) - err = i915_vma_move_to_active(vma, rq, flags); - i915_vma_unlock(vma); - - return err; -} - static struct i915_request * record_registers(struct intel_context *ce, struct i915_vma *before, @@ -1093,19 +1074,19 @@ record_registers(struct intel_context *ce, if (IS_ERR(rq)) goto err_after; - err = move_to_active(rq, before, EXEC_OBJECT_WRITE); + err = igt_vma_move_to_active_unlocked(before, rq, EXEC_OBJECT_WRITE); if (err) goto err_rq; - err = move_to_active(rq, b_before, 0); + err = igt_vma_move_to_active_unlocked(b_before, rq, 0); if (err) goto err_rq; - err = move_to_active(rq, after, EXEC_OBJECT_WRITE); + err = igt_vma_move_to_active_unlocked(after, rq, EXEC_OBJECT_WRITE); if (err) goto err_rq; - err = move_to_active(rq, b_after, 0); + err = igt_vma_move_to_active_unlocked(b_after, rq, 0); if (err) goto err_rq; @@ -1243,7 +1224,7 @@ static int poison_registers(struct intel_context *ce, u32 poison, u32 *sema) goto err_batch; } - err = move_to_active(rq, batch, 0); + err = igt_vma_move_to_active_unlocked(batch, rq, 0); if (err) goto err_rq; diff --git a/drivers/gpu/drm/i915/gt/selftest_migrate.c b/drivers/gpu/drm/i915/gt/selftest_migrate.c index 2b0c87999949..0dc5309c90a4 100644 --- a/drivers/gpu/drm/i915/gt/selftest_migrate.c +++ b/drivers/gpu/drm/i915/gt/selftest_migrate.c @@ -6,6 +6,7 @@ #include <linux/sort.h> #include "gem/i915_gem_internal.h" +#include "gem/i915_gem_lmem.h" #include "selftests/i915_random.h" diff --git a/drivers/gpu/drm/i915/gt/selftest_mocs.c b/drivers/gpu/drm/i915/gt/selftest_mocs.c index c1d861333c44..f27cc28608d4 100644 --- a/drivers/gpu/drm/i915/gt/selftest_mocs.c +++ b/drivers/gpu/drm/i915/gt/selftest_mocs.c @@ -7,6 +7,7 @@ #include "gt/intel_gpu_commands.h" #include "i915_selftest.h" +#include "gem/selftests/igt_gem_utils.h" #include "gem/selftests/mock_context.h" #include "selftests/igt_reset.h" #include "selftests/igt_spinner.h" @@ -228,9 +229,7 @@ static int check_mocs_engine(struct live_mocs *arg, return PTR_ERR(rq); i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, true); - if (!err) - err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); i915_vma_unlock(vma); /* Read the mocs tables back using SRM */ diff --git a/drivers/gpu/drm/i915/gt/selftest_rc6.c b/drivers/gpu/drm/i915/gt/selftest_rc6.c index 8c70b7e12074..2ceeadecc639 100644 --- a/drivers/gpu/drm/i915/gt/selftest_rc6.c +++ b/drivers/gpu/drm/i915/gt/selftest_rc6.c @@ -19,11 +19,11 @@ static u64 rc6_residency(struct intel_rc6 *rc6) /* XXX VLV_GT_MEDIA_RC6? */ - result = intel_rc6_residency_ns(rc6, GEN6_GT_GFX_RC6); + result = intel_rc6_residency_ns(rc6, INTEL_RC6_RES_RC6); if (HAS_RC6p(rc6_to_i915(rc6))) - result += intel_rc6_residency_ns(rc6, GEN6_GT_GFX_RC6p); + result += intel_rc6_residency_ns(rc6, INTEL_RC6_RES_RC6p); if (HAS_RC6pp(rc6_to_i915(rc6))) - result += intel_rc6_residency_ns(rc6, GEN6_GT_GFX_RC6pp); + result += intel_rc6_residency_ns(rc6, INTEL_RC6_RES_RC6pp); return result; } diff --git a/drivers/gpu/drm/i915/gt/selftest_rps.c b/drivers/gpu/drm/i915/gt/selftest_rps.c index cfb4708dd62e..39f1b7564170 100644 --- a/drivers/gpu/drm/i915/gt/selftest_rps.c +++ b/drivers/gpu/drm/i915/gt/selftest_rps.c @@ -652,9 +652,7 @@ int live_rps_frequency_cs(void *arg) goto err_vma; } - err = i915_request_await_object(rq, vma->obj, false); - if (!err) - err = i915_vma_move_to_active(vma, rq, 0); + err = i915_vma_move_to_active(vma, rq, 0); if (!err) err = rq->engine->emit_bb_start(rq, vma->node.start, @@ -793,9 +791,7 @@ int live_rps_frequency_srm(void *arg) goto err_vma; } - err = i915_request_await_object(rq, vma->obj, false); - if (!err) - err = i915_vma_move_to_active(vma, rq, 0); + err = i915_vma_move_to_active(vma, rq, 0); if (!err) err = rq->engine->emit_bb_start(rq, vma->node.start, @@ -1107,21 +1103,27 @@ static u64 __measure_power(int duration_ms) return div64_u64(1000 * 1000 * dE, dt); } -static u64 measure_power_at(struct intel_rps *rps, int *freq) +static u64 measure_power(struct intel_rps *rps, int *freq) { u64 x[5]; int i; - *freq = rps_set_check(rps, *freq); for (i = 0; i < 5; i++) x[i] = __measure_power(5); - *freq = (*freq + read_cagf(rps)) / 2; + + *freq = (*freq + intel_rps_read_actual_frequency(rps)) / 2; /* A simple triangle filter for better result stability */ sort(x, 5, sizeof(*x), cmp_u64, NULL); return div_u64(x[1] + 2 * x[2] + x[3], 4); } +static u64 measure_power_at(struct intel_rps *rps, int *freq) +{ + *freq = rps_set_check(rps, *freq); + return measure_power(rps, freq); +} + int live_rps_power(void *arg) { struct intel_gt *gt = arg; diff --git a/drivers/gpu/drm/i915/gt/selftest_slpc.c b/drivers/gpu/drm/i915/gt/selftest_slpc.c index f8a1d27df272..bd44ce73a504 100644 --- a/drivers/gpu/drm/i915/gt/selftest_slpc.c +++ b/drivers/gpu/drm/i915/gt/selftest_slpc.c @@ -11,7 +11,16 @@ enum test_type { VARY_MIN, VARY_MAX, - MAX_GRANTED + MAX_GRANTED, + SLPC_POWER, + TILE_INTERACTION, +}; + +struct slpc_thread { + struct kthread_worker *worker; + struct kthread_work work; + struct intel_gt *gt; + int result; }; static int slpc_set_min_freq(struct intel_guc_slpc *slpc, u32 freq) @@ -41,6 +50,39 @@ static int slpc_set_max_freq(struct intel_guc_slpc *slpc, u32 freq) return ret; } +static int slpc_set_freq(struct intel_gt *gt, u32 freq) +{ + int err; + struct intel_guc_slpc *slpc = >->uc.guc.slpc; + + err = slpc_set_max_freq(slpc, freq); + if (err) { + pr_err("Unable to update max freq"); + return err; + } + + err = slpc_set_min_freq(slpc, freq); + if (err) { + pr_err("Unable to update min freq"); + return err; + } + + return err; +} + +static u64 measure_power_at_freq(struct intel_gt *gt, int *freq, u64 *power) +{ + int err = 0; + + err = slpc_set_freq(gt, *freq); + if (err) + return err; + *freq = intel_rps_read_actual_frequency(>->rps); + *power = measure_power(>->rps, freq); + + return err; +} + static int vary_max_freq(struct intel_guc_slpc *slpc, struct intel_rps *rps, u32 *max_act_freq) { @@ -113,6 +155,58 @@ static int vary_min_freq(struct intel_guc_slpc *slpc, struct intel_rps *rps, return err; } +static int slpc_power(struct intel_gt *gt, struct intel_engine_cs *engine) +{ + struct intel_guc_slpc *slpc = >->uc.guc.slpc; + struct { + u64 power; + int freq; + } min, max; + int err = 0; + + /* + * Our fundamental assumption is that running at lower frequency + * actually saves power. Let's see if our RAPL measurement supports + * that theory. + */ + if (!librapl_supported(gt->i915)) + return 0; + + min.freq = slpc->min_freq; + err = measure_power_at_freq(gt, &min.freq, &min.power); + + if (err) + return err; + + max.freq = slpc->rp0_freq; + err = measure_power_at_freq(gt, &max.freq, &max.power); + + if (err) + return err; + + pr_info("%s: min:%llumW @ %uMHz, max:%llumW @ %uMHz\n", + engine->name, + min.power, min.freq, + max.power, max.freq); + + if (10 * min.freq >= 9 * max.freq) { + pr_notice("Could not control frequency, ran at [%uMHz, %uMhz]\n", + min.freq, max.freq); + } + + if (11 * min.power > 10 * max.power) { + pr_err("%s: did not conserve power when setting lower frequency!\n", + engine->name); + err = -EINVAL; + } + + /* Restore min/max frequencies */ + slpc_set_max_freq(slpc, slpc->rp0_freq); + slpc_set_min_freq(slpc, slpc->min_freq); + + return err; +} + static int max_granted_freq(struct intel_guc_slpc *slpc, struct intel_rps *rps, u32 *max_act_freq) { struct intel_gt *gt = rps_to_gt(rps); @@ -126,7 +220,8 @@ static int max_granted_freq(struct intel_guc_slpc *slpc, struct intel_rps *rps, *max_act_freq = intel_rps_read_actual_frequency(rps); if (*max_act_freq != slpc->rp0_freq) { /* Check if there was some throttling by pcode */ - perf_limit_reasons = intel_uncore_read(gt->uncore, GT0_PERF_LIMIT_REASONS); + perf_limit_reasons = intel_uncore_read(gt->uncore, + intel_gt_perf_limit_reasons_reg(gt)); /* If not, this is an error */ if (!(perf_limit_reasons & GT0_PERF_LIMIT_REASONS_MASK)) { @@ -153,6 +248,11 @@ static int run_test(struct intel_gt *gt, int test_type) if (!intel_uc_uses_guc_slpc(>->uc)) return 0; + if (slpc->min_freq == slpc->rp0_freq) { + pr_err("Min/Max are fused to the same value\n"); + return -EINVAL; + } + if (igt_spinner_init(&spin, gt)) return -ENOMEM; @@ -167,17 +267,14 @@ static int run_test(struct intel_gt *gt, int test_type) } /* - * FIXME: With efficient frequency enabled, GuC can request - * frequencies higher than the SLPC max. While this is fixed - * in GuC, we level set these tests with RPn as min. + * Set min frequency to RPn so that we can test the whole + * range of RPn-RP0. This also turns off efficient freq + * usage and makes results more predictable. */ err = slpc_set_min_freq(slpc, slpc->min_freq); - if (err) + if (err) { + pr_err("Unable to update min freq!"); return err; - - if (slpc->min_freq == slpc->rp0_freq) { - pr_err("Min/Max are fused to the same value\n"); - return -EINVAL; } intel_gt_pm_wait_for_idle(gt); @@ -222,9 +319,10 @@ static int run_test(struct intel_gt *gt, int test_type) break; case MAX_GRANTED: + case TILE_INTERACTION: /* Media engines have a different RP0 */ - if (engine->class == VIDEO_DECODE_CLASS || - engine->class == VIDEO_ENHANCEMENT_CLASS) { + if (gt->type != GT_MEDIA && (engine->class == VIDEO_DECODE_CLASS || + engine->class == VIDEO_ENHANCEMENT_CLASS)) { igt_spinner_end(&spin); st_engine_heartbeat_enable(engine); err = 0; @@ -233,17 +331,24 @@ static int run_test(struct intel_gt *gt, int test_type) err = max_granted_freq(slpc, rps, &max_act_freq); break; - } - pr_info("Max actual frequency for %s was %d\n", - engine->name, max_act_freq); + case SLPC_POWER: + err = slpc_power(gt, engine); + break; + } - /* Actual frequency should rise above min */ - if (max_act_freq <= slpc_min_freq) { - pr_err("Actual freq did not rise above min\n"); - pr_err("Perf Limit Reasons: 0x%x\n", - intel_uncore_read(gt->uncore, GT0_PERF_LIMIT_REASONS)); - err = -EINVAL; + if (test_type != SLPC_POWER) { + pr_info("Max actual frequency for %s was %d\n", + engine->name, max_act_freq); + + /* Actual frequency should rise above min */ + if (max_act_freq <= slpc->min_freq) { + pr_err("Actual freq did not rise above min\n"); + pr_err("Perf Limit Reasons: 0x%x\n", + intel_uncore_read(gt->uncore, + intel_gt_perf_limit_reasons_reg(gt))); + err = -EINVAL; + } } igt_spinner_end(&spin); @@ -270,26 +375,116 @@ static int run_test(struct intel_gt *gt, int test_type) static int live_slpc_vary_min(void *arg) { struct drm_i915_private *i915 = arg; - struct intel_gt *gt = to_gt(i915); + struct intel_gt *gt; + unsigned int i; + int ret; + + for_each_gt(gt, i915, i) { + ret = run_test(gt, VARY_MIN); + if (ret) + return ret; + } - return run_test(gt, VARY_MIN); + return ret; } static int live_slpc_vary_max(void *arg) { struct drm_i915_private *i915 = arg; - struct intel_gt *gt = to_gt(i915); + struct intel_gt *gt; + unsigned int i; + int ret; + + for_each_gt(gt, i915, i) { + ret = run_test(gt, VARY_MAX); + if (ret) + return ret; + } - return run_test(gt, VARY_MAX); + return ret; } /* check if pcode can grant RP0 */ static int live_slpc_max_granted(void *arg) { struct drm_i915_private *i915 = arg; - struct intel_gt *gt = to_gt(i915); + struct intel_gt *gt; + unsigned int i; + int ret; + + for_each_gt(gt, i915, i) { + ret = run_test(gt, MAX_GRANTED); + if (ret) + return ret; + } + + return ret; +} + +static int live_slpc_power(void *arg) +{ + struct drm_i915_private *i915 = arg; + struct intel_gt *gt; + unsigned int i; + int ret; + + for_each_gt(gt, i915, i) { + ret = run_test(gt, SLPC_POWER); + if (ret) + return ret; + } + + return ret; +} + +static void slpc_spinner_thread(struct kthread_work *work) +{ + struct slpc_thread *thread = container_of(work, typeof(*thread), work); + + thread->result = run_test(thread->gt, TILE_INTERACTION); +} + +static int live_slpc_tile_interaction(void *arg) +{ + struct drm_i915_private *i915 = arg; + struct intel_gt *gt; + struct slpc_thread *threads; + int i = 0, ret = 0; + + threads = kcalloc(I915_MAX_GT, sizeof(*threads), GFP_KERNEL); + if (!threads) + return -ENOMEM; + + for_each_gt(gt, i915, i) { + threads[i].worker = kthread_create_worker(0, "igt/slpc_parallel:%d", gt->info.id); + + if (IS_ERR(threads[i].worker)) { + ret = PTR_ERR(threads[i].worker); + break; + } + + threads[i].gt = gt; + kthread_init_work(&threads[i].work, slpc_spinner_thread); + kthread_queue_work(threads[i].worker, &threads[i].work); + } + + for_each_gt(gt, i915, i) { + int status; + + if (IS_ERR_OR_NULL(threads[i].worker)) + continue; - return run_test(gt, MAX_GRANTED); + kthread_flush_work(&threads[i].work); + status = READ_ONCE(threads[i].result); + if (status && !ret) { + pr_err("%s GT %d failed ", __func__, gt->info.id); + ret = status; + } + kthread_destroy_worker(threads[i].worker); + } + + kfree(threads); + return ret; } int intel_slpc_live_selftests(struct drm_i915_private *i915) @@ -298,10 +493,17 @@ int intel_slpc_live_selftests(struct drm_i915_private *i915) SUBTEST(live_slpc_vary_max), SUBTEST(live_slpc_vary_min), SUBTEST(live_slpc_max_granted), + SUBTEST(live_slpc_power), + SUBTEST(live_slpc_tile_interaction), }; - if (intel_gt_is_wedged(to_gt(i915))) - return 0; + struct intel_gt *gt; + unsigned int i; + + for_each_gt(gt, i915, i) { + if (intel_gt_is_wedged(gt)) + return 0; + } return i915_live_subtests(tests, i915); } diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c index 67a9aab801dd..96e3861706d6 100644 --- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c +++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c @@ -66,14 +66,14 @@ reference_lists_init(struct intel_gt *gt, struct wa_lists *lists) memset(lists, 0, sizeof(*lists)); - wa_init_start(&lists->gt_wa_list, "GT_REF", "global"); + wa_init_start(&lists->gt_wa_list, gt, "GT_REF", "global"); gt_init_workarounds(gt, &lists->gt_wa_list); wa_init_finish(&lists->gt_wa_list); for_each_engine(engine, gt, id) { struct i915_wa_list *wal = &lists->engine[id].wa_list; - wa_init_start(wal, "REF", engine->name); + wa_init_start(wal, gt, "REF", engine->name); engine_init_workarounds(engine, wal); wa_init_finish(wal); @@ -139,9 +139,7 @@ read_nonprivs(struct intel_context *ce) } i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, true); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); i915_vma_unlock(vma); if (err) goto err_req; @@ -632,16 +630,12 @@ retry: goto err_request; } - err = i915_request_await_object(rq, batch->obj, false); - if (err == 0) - err = i915_vma_move_to_active(batch, rq, 0); + err = i915_vma_move_to_active(batch, rq, 0); if (err) goto err_request; - err = i915_request_await_object(rq, scratch->obj, true); - if (err == 0) - err = i915_vma_move_to_active(scratch, rq, - EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(scratch, rq, + EXEC_OBJECT_WRITE); if (err) goto err_request; @@ -860,9 +854,7 @@ static int read_whitelisted_registers(struct intel_context *ce, return PTR_ERR(rq); i915_vma_lock(results); - err = i915_request_await_object(rq, results->obj, true); - if (err == 0) - err = i915_vma_move_to_active(results, rq, EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(results, rq, EXEC_OBJECT_WRITE); i915_vma_unlock(results); if (err) goto err_req; @@ -944,9 +936,7 @@ static int scrub_whitelisted_registers(struct intel_context *ce) } i915_vma_lock(batch); - err = i915_request_await_object(rq, batch->obj, false); - if (err == 0) - err = i915_vma_move_to_active(batch, rq, 0); + err = i915_vma_move_to_active(batch, rq, 0); i915_vma_unlock(batch); if (err) goto err_request; @@ -991,7 +981,7 @@ static bool pardon_reg(struct drm_i915_private *i915, i915_reg_t reg) /* Alas, we must pardon some whitelists. Mistakes already made */ static const struct regmask pardon[] = { { GEN9_CTX_PREEMPT_REG, 9 }, - { GEN8_L3SQCREG4, 9 }, + { _MMIO(0xb118), 9 }, /* GEN8_L3SQCREG4 */ }; return find_reg(i915, reg, pardon, ARRAY_SIZE(pardon)); diff --git a/drivers/gpu/drm/i915/gt/sysfs_engines.c b/drivers/gpu/drm/i915/gt/sysfs_engines.c index 967031056202..f2d9858d827c 100644 --- a/drivers/gpu/drm/i915/gt/sysfs_engines.c +++ b/drivers/gpu/drm/i915/gt/sysfs_engines.c @@ -144,7 +144,7 @@ max_spin_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct intel_engine_cs *engine = kobj_to_engine(kobj); - unsigned long long duration; + unsigned long long duration, clamped; int err; /* @@ -168,7 +168,8 @@ max_spin_store(struct kobject *kobj, struct kobj_attribute *attr, if (err) return err; - if (duration > jiffies_to_nsecs(2)) + clamped = intel_clamp_max_busywait_duration_ns(engine, duration); + if (duration != clamped) return -EINVAL; WRITE_ONCE(engine->props.max_busywait_duration_ns, duration); @@ -203,7 +204,7 @@ timeslice_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct intel_engine_cs *engine = kobj_to_engine(kobj); - unsigned long long duration; + unsigned long long duration, clamped; int err; /* @@ -218,7 +219,8 @@ timeslice_store(struct kobject *kobj, struct kobj_attribute *attr, if (err) return err; - if (duration > jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT)) + clamped = intel_clamp_timeslice_duration_ms(engine, duration); + if (duration != clamped) return -EINVAL; WRITE_ONCE(engine->props.timeslice_duration_ms, duration); @@ -256,7 +258,7 @@ stop_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct intel_engine_cs *engine = kobj_to_engine(kobj); - unsigned long long duration; + unsigned long long duration, clamped; int err; /* @@ -272,7 +274,8 @@ stop_store(struct kobject *kobj, struct kobj_attribute *attr, if (err) return err; - if (duration > jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT)) + clamped = intel_clamp_stop_timeout_ms(engine, duration); + if (duration != clamped) return -EINVAL; WRITE_ONCE(engine->props.stop_timeout_ms, duration); @@ -306,7 +309,7 @@ preempt_timeout_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct intel_engine_cs *engine = kobj_to_engine(kobj); - unsigned long long timeout; + unsigned long long timeout, clamped; int err; /* @@ -322,7 +325,8 @@ preempt_timeout_store(struct kobject *kobj, struct kobj_attribute *attr, if (err) return err; - if (timeout > jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT)) + clamped = intel_clamp_preempt_timeout_ms(engine, timeout); + if (timeout != clamped) return -EINVAL; WRITE_ONCE(engine->props.preempt_timeout_ms, timeout); @@ -362,7 +366,7 @@ heartbeat_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct intel_engine_cs *engine = kobj_to_engine(kobj); - unsigned long long delay; + unsigned long long delay, clamped; int err; /* @@ -379,7 +383,8 @@ heartbeat_store(struct kobject *kobj, struct kobj_attribute *attr, if (err) return err; - if (delay >= jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT)) + clamped = intel_clamp_heartbeat_interval_ms(engine, delay); + if (delay != clamped) return -EINVAL; err = intel_engine_set_heartbeat(engine, delay); diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h index 29ef8afc8c2e..f359bef046e0 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h @@ -117,6 +117,7 @@ enum intel_guc_action { INTEL_GUC_ACTION_ENTER_S_STATE = 0x501, INTEL_GUC_ACTION_EXIT_S_STATE = 0x502, INTEL_GUC_ACTION_GLOBAL_SCHED_POLICY_CHANGE = 0x506, + INTEL_GUC_ACTION_UPDATE_SCHEDULING_POLICIES_KLV = 0x509, INTEL_GUC_ACTION_SCHED_CONTEXT = 0x1000, INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_SET = 0x1001, INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_DONE = 0x1002, diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h index 4c840a2639dc..811add10c30d 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h @@ -128,6 +128,15 @@ enum slpc_media_ratio_mode { SLPC_MEDIA_RATIO_MODE_FIXED_ONE_TO_TWO = 2, }; +enum slpc_gucrc_mode { + SLPC_GUCRC_MODE_HW = 0, + SLPC_GUCRC_MODE_GUCRC_NO_RC6 = 1, + SLPC_GUCRC_MODE_GUCRC_STATIC_TIMEOUT = 2, + SLPC_GUCRC_MODE_GUCRC_DYNAMIC_HYSTERESIS = 3, + + SLPC_GUCRC_MODE_MAX, +}; + enum slpc_event_id { SLPC_EVENT_RESET = 0, SLPC_EVENT_SHUTDOWN = 1, diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h index 4a59478c3b5c..58012edd4eb0 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h @@ -82,9 +82,16 @@ #define GUC_KLV_SELF_CFG_G2H_CTB_SIZE_LEN 1u /* + * Global scheduling policy update keys. + */ +enum { + GUC_SCHEDULING_POLICIES_KLV_ID_RENDER_COMPUTE_YIELD = 0x1001, +}; + +/* * Per context scheduling policy update keys. */ -enum { +enum { GUC_CONTEXT_POLICIES_KLV_ID_EXECUTION_QUANTUM = 0x2001, GUC_CONTEXT_POLICIES_KLV_ID_PREEMPTION_TIMEOUT = 0x2002, GUC_CONTEXT_POLICIES_KLV_ID_SCHEDULING_PRIORITY = 0x2003, diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c index bac06e3d6f2c..52aede324788 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c @@ -98,6 +98,8 @@ static void gen9_enable_guc_interrupts(struct intel_guc *guc) gt->pm_guc_events); gen6_gt_pm_enable_irq(gt, gt->pm_guc_events); spin_unlock_irq(gt->irq_lock); + + guc->interrupts.enabled = true; } static void gen9_disable_guc_interrupts(struct intel_guc *guc) @@ -105,6 +107,7 @@ static void gen9_disable_guc_interrupts(struct intel_guc *guc) struct intel_gt *gt = guc_to_gt(guc); assert_rpm_wakelock_held(>->i915->runtime_pm); + guc->interrupts.enabled = false; spin_lock_irq(gt->irq_lock); @@ -116,39 +119,39 @@ static void gen9_disable_guc_interrupts(struct intel_guc *guc) gen9_reset_guc_interrupts(guc); } +static bool __gen11_reset_guc_interrupts(struct intel_gt *gt) +{ + u32 irq = gt->type == GT_MEDIA ? MTL_MGUC : GEN11_GUC; + + lockdep_assert_held(gt->irq_lock); + return gen11_gt_reset_one_iir(gt, 0, irq); +} + static void gen11_reset_guc_interrupts(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); spin_lock_irq(gt->irq_lock); - gen11_gt_reset_one_iir(gt, 0, GEN11_GUC); + __gen11_reset_guc_interrupts(gt); spin_unlock_irq(gt->irq_lock); } static void gen11_enable_guc_interrupts(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); - u32 events = REG_FIELD_PREP(ENGINE1_MASK, GUC_INTR_GUC2HOST); spin_lock_irq(gt->irq_lock); - WARN_ON_ONCE(gen11_gt_reset_one_iir(gt, 0, GEN11_GUC)); - intel_uncore_write(gt->uncore, - GEN11_GUC_SG_INTR_ENABLE, events); - intel_uncore_write(gt->uncore, - GEN11_GUC_SG_INTR_MASK, ~events); + __gen11_reset_guc_interrupts(gt); spin_unlock_irq(gt->irq_lock); + + guc->interrupts.enabled = true; } static void gen11_disable_guc_interrupts(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); - spin_lock_irq(gt->irq_lock); - - intel_uncore_write(gt->uncore, GEN11_GUC_SG_INTR_MASK, ~0); - intel_uncore_write(gt->uncore, GEN11_GUC_SG_INTR_ENABLE, 0); - - spin_unlock_irq(gt->irq_lock); + guc->interrupts.enabled = false; intel_synchronize_irq(gt->i915); gen11_reset_guc_interrupts(guc); @@ -156,7 +159,8 @@ static void gen11_disable_guc_interrupts(struct intel_guc *guc) void intel_guc_init_early(struct intel_guc *guc) { - struct drm_i915_private *i915 = guc_to_gt(guc)->i915; + struct intel_gt *gt = guc_to_gt(guc); + struct drm_i915_private *i915 = gt->i915; intel_uc_fw_init_early(&guc->fw, INTEL_UC_FW_TYPE_GUC); intel_guc_ct_init_early(&guc->ct); @@ -168,12 +172,17 @@ void intel_guc_init_early(struct intel_guc *guc) mutex_init(&guc->send_mutex); spin_lock_init(&guc->irq_lock); if (GRAPHICS_VER(i915) >= 11) { - guc->notify_reg = GEN11_GUC_HOST_INTERRUPT; guc->interrupts.reset = gen11_reset_guc_interrupts; guc->interrupts.enable = gen11_enable_guc_interrupts; guc->interrupts.disable = gen11_disable_guc_interrupts; - guc->send_regs.base = - i915_mmio_reg_offset(GEN11_SOFT_SCRATCH(0)); + if (gt->type == GT_MEDIA) { + guc->notify_reg = MEDIA_GUC_HOST_INTERRUPT; + guc->send_regs.base = i915_mmio_reg_offset(MEDIA_SOFT_SCRATCH(0)); + } else { + guc->notify_reg = GEN11_GUC_HOST_INTERRUPT; + guc->send_regs.base = i915_mmio_reg_offset(GEN11_SOFT_SCRATCH(0)); + } + guc->send_regs.count = GEN11_SOFT_SCRATCH_COUNT; } else { @@ -441,6 +450,7 @@ err_log: err_fw: intel_uc_fw_fini(&guc->fw); out: + intel_uc_fw_change_status(&guc->fw, INTEL_UC_FIRMWARE_INIT_FAIL); i915_probe_error(gt->i915, "failed with %d\n", ret); return ret; } @@ -870,14 +880,14 @@ void intel_guc_load_status(struct intel_guc *guc, struct drm_printer *p) u32 status = intel_uncore_read(uncore, GUC_STATUS); u32 i; - drm_printf(p, "\nGuC status 0x%08x:\n", status); + drm_printf(p, "GuC status 0x%08x:\n", status); drm_printf(p, "\tBootrom status = 0x%x\n", (status & GS_BOOTROM_MASK) >> GS_BOOTROM_SHIFT); drm_printf(p, "\tuKernel status = 0x%x\n", (status & GS_UKERNEL_MASK) >> GS_UKERNEL_SHIFT); drm_printf(p, "\tMIA Core status = 0x%x\n", (status & GS_MIA_MASK) >> GS_MIA_SHIFT); - drm_puts(p, "\nScratch registers:\n"); + drm_puts(p, "Scratch registers:\n"); for (i = 0; i < 16; i++) { drm_printf(p, "\t%2d: \t0x%x\n", i, intel_uncore_read(uncore, SOFT_SCRATCH(i))); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h index 804133df1ac9..1bb3f9829286 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h @@ -78,6 +78,7 @@ struct intel_guc { /** @interrupts: pointers to GuC interrupt-managing functions. */ struct { + bool enabled; void (*reset)(struct intel_guc *guc); void (*enable)(struct intel_guc *guc); void (*disable)(struct intel_guc *guc); @@ -113,6 +114,10 @@ struct intel_guc { */ struct list_head guc_id_list; /** + * @guc_ids_in_use: Number single-lrc guc_ids in use + */ + unsigned int guc_ids_in_use; + /** * @destroyed_contexts: list of contexts waiting to be destroyed * (deregistered with the GuC) */ @@ -132,6 +137,16 @@ struct intel_guc { * @reset_fail_mask: mask of engines that failed to reset */ intel_engine_mask_t reset_fail_mask; + /** + * @sched_disable_delay_ms: schedule disable delay, in ms, for + * contexts + */ + unsigned int sched_disable_delay_ms; + /** + * @sched_disable_gucid_threshold: threshold of min remaining available + * guc_ids before we start bypassing the schedule disable delay + */ + unsigned int sched_disable_gucid_threshold; } submission_state; /** @@ -316,9 +331,11 @@ retry: return err; } +/* Only call this from the interrupt handler code */ static inline void intel_guc_to_host_event_handler(struct intel_guc *guc) { - intel_guc_ct_event_handler(&guc->ct); + if (guc->interrupts.enabled) + intel_guc_ct_event_handler(&guc->ct); } /* GuC addresses above GUC_GGTT_TOP also don't map through the GTT */ @@ -466,4 +483,6 @@ void intel_guc_write_barrier(struct intel_guc *guc); void intel_guc_dump_time_info(struct intel_guc *guc, struct drm_printer *p); +int intel_guc_sched_disable_gucid_threshold_max(struct intel_guc *guc); + #endif diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c index 74cbe8eaf531..a7f737c4792e 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c @@ -5,6 +5,7 @@ #include <linux/bsearch.h> +#include "gem/i915_gem_lmem.h" #include "gt/intel_engine_regs.h" #include "gt/intel_gt.h" #include "gt/intel_gt_mcr.h" @@ -277,24 +278,16 @@ __mmio_reg_add(struct temp_regset *regset, struct guc_mmio_reg *reg) return slot; } -#define GUC_REGSET_STEERING(group, instance) ( \ - FIELD_PREP(GUC_REGSET_STEERING_GROUP, (group)) | \ - FIELD_PREP(GUC_REGSET_STEERING_INSTANCE, (instance)) | \ - GUC_REGSET_NEEDS_STEERING \ -) - static long __must_check guc_mmio_reg_add(struct intel_gt *gt, struct temp_regset *regset, - i915_reg_t reg, u32 flags) + u32 offset, u32 flags) { u32 count = regset->storage_used - (regset->registers - regset->storage); - u32 offset = i915_mmio_reg_offset(reg); struct guc_mmio_reg entry = { .offset = offset, .flags = flags, }; struct guc_mmio_reg *slot; - u8 group, inst; /* * The mmio list is built using separate lists within the driver. @@ -306,17 +299,6 @@ static long __must_check guc_mmio_reg_add(struct intel_gt *gt, sizeof(entry), guc_mmio_reg_cmp)) return 0; - /* - * The GuC doesn't have a default steering, so we need to explicitly - * steer all registers that need steering. However, we do not keep track - * of all the steering ranges, only of those that have a chance of using - * a non-default steering from the i915 pov. Instead of adding such - * tracking, it is easier to just program the default steering for all - * regs that don't need a non-default one. - */ - intel_gt_mcr_get_nonterminated_steering(gt, reg, &group, &inst); - entry.flags |= GUC_REGSET_STEERING(group, inst); - slot = __mmio_reg_add(regset, &entry); if (IS_ERR(slot)) return PTR_ERR(slot); @@ -335,6 +317,38 @@ static long __must_check guc_mmio_reg_add(struct intel_gt *gt, #define GUC_MMIO_REG_ADD(gt, regset, reg, masked) \ guc_mmio_reg_add(gt, \ regset, \ + i915_mmio_reg_offset(reg), \ + (masked) ? GUC_REGSET_MASKED : 0) + +#define GUC_REGSET_STEERING(group, instance) ( \ + FIELD_PREP(GUC_REGSET_STEERING_GROUP, (group)) | \ + FIELD_PREP(GUC_REGSET_STEERING_INSTANCE, (instance)) | \ + GUC_REGSET_NEEDS_STEERING \ +) + +static long __must_check guc_mcr_reg_add(struct intel_gt *gt, + struct temp_regset *regset, + i915_mcr_reg_t reg, u32 flags) +{ + u8 group, inst; + + /* + * The GuC doesn't have a default steering, so we need to explicitly + * steer all registers that need steering. However, we do not keep track + * of all the steering ranges, only of those that have a chance of using + * a non-default steering from the i915 pov. Instead of adding such + * tracking, it is easier to just program the default steering for all + * regs that don't need a non-default one. + */ + intel_gt_mcr_get_nonterminated_steering(gt, reg, &group, &inst); + flags |= GUC_REGSET_STEERING(group, inst); + + return guc_mmio_reg_add(gt, regset, i915_mmio_reg_offset(reg), flags); +} + +#define GUC_MCR_REG_ADD(gt, regset, reg, masked) \ + guc_mcr_reg_add(gt, \ + regset, \ (reg), \ (masked) ? GUC_REGSET_MASKED : 0) @@ -372,8 +386,21 @@ static int guc_mmio_regset_init(struct temp_regset *regset, false); /* add in local MOCS registers */ - for (i = 0; i < GEN9_LNCFCMOCS_REG_COUNT; i++) - ret |= GUC_MMIO_REG_ADD(gt, regset, GEN9_LNCFCMOCS(i), false); + for (i = 0; i < LNCFCMOCS_REG_COUNT; i++) + if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50)) + ret |= GUC_MCR_REG_ADD(gt, regset, XEHP_LNCFCMOCS(i), false); + else + ret |= GUC_MMIO_REG_ADD(gt, regset, GEN9_LNCFCMOCS(i), false); + + if (GRAPHICS_VER(engine->i915) >= 12) { + ret |= GUC_MMIO_REG_ADD(gt, regset, EU_PERF_CNTL0, false); + ret |= GUC_MMIO_REG_ADD(gt, regset, EU_PERF_CNTL1, false); + ret |= GUC_MMIO_REG_ADD(gt, regset, EU_PERF_CNTL2, false); + ret |= GUC_MMIO_REG_ADD(gt, regset, EU_PERF_CNTL3, false); + ret |= GUC_MMIO_REG_ADD(gt, regset, EU_PERF_CNTL4, false); + ret |= GUC_MMIO_REG_ADD(gt, regset, EU_PERF_CNTL5, false); + ret |= GUC_MMIO_REG_ADD(gt, regset, EU_PERF_CNTL6, false); + } return ret ? -1 : 0; } @@ -461,6 +488,11 @@ static void fill_engine_enable_masks(struct intel_gt *gt, info_map_write(info_map, engine_enabled_masks[GUC_BLITTER_CLASS], BCS_MASK(gt)); info_map_write(info_map, engine_enabled_masks[GUC_VIDEO_CLASS], VDBOX_MASK(gt)); info_map_write(info_map, engine_enabled_masks[GUC_VIDEOENHANCE_CLASS], VEBOX_MASK(gt)); + + /* The GSC engine is an instance (6) of OTHER_CLASS */ + if (gt->engine[GSC0]) + info_map_write(info_map, engine_enabled_masks[GUC_GSC_OTHER_CLASS], + BIT(gt->engine[GSC0]->instance)); } #define LR_HW_CONTEXT_SIZE (80 * sizeof(u32)) @@ -502,9 +534,6 @@ static int guc_prep_golden_context(struct intel_guc *guc) } for (engine_class = 0; engine_class <= MAX_ENGINE_CLASS; ++engine_class) { - if (engine_class == OTHER_CLASS) - continue; - guc_class = engine_class_to_guc_class(engine_class); if (!info_map_read(&info_map, engine_enabled_masks[guc_class])) @@ -582,9 +611,6 @@ static void guc_init_golden_context(struct intel_guc *guc) addr_ggtt = intel_guc_ggtt_offset(guc, guc->ads_vma) + offset; for (engine_class = 0; engine_class <= MAX_ENGINE_CLASS; ++engine_class) { - if (engine_class == OTHER_CLASS) - continue; - guc_class = engine_class_to_guc_class(engine_class); if (!ads_blob_read(guc, system_info.engine_enabled_masks[guc_class])) continue; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c index 8f1165146013..1c1b85073b4b 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c @@ -132,6 +132,11 @@ static const struct __guc_mmio_reg_descr xe_lpd_blt_inst_regs[] = { COMMON_BASE_ENGINE_INSTANCE, }; +/* XE_LPD - GSC Per-Engine-Instance */ +static const struct __guc_mmio_reg_descr xe_lpd_gsc_inst_regs[] = { + COMMON_BASE_ENGINE_INSTANCE, +}; + /* GEN9 - Global */ static const struct __guc_mmio_reg_descr default_global_regs[] = { COMMON_BASE_GLOBAL, @@ -165,16 +170,20 @@ static const struct __guc_mmio_reg_descr empty_regs_list[] = { } /* List of lists */ -static struct __guc_mmio_reg_descr_group default_lists[] = { +static const struct __guc_mmio_reg_descr_group default_lists[] = { MAKE_REGLIST(default_global_regs, PF, GLOBAL, 0), MAKE_REGLIST(default_rc_class_regs, PF, ENGINE_CLASS, GUC_RENDER_CLASS), MAKE_REGLIST(xe_lpd_rc_inst_regs, PF, ENGINE_INSTANCE, GUC_RENDER_CLASS), + MAKE_REGLIST(default_rc_class_regs, PF, ENGINE_CLASS, GUC_COMPUTE_CLASS), + MAKE_REGLIST(xe_lpd_rc_inst_regs, PF, ENGINE_INSTANCE, GUC_COMPUTE_CLASS), MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_VIDEO_CLASS), MAKE_REGLIST(xe_lpd_vd_inst_regs, PF, ENGINE_INSTANCE, GUC_VIDEO_CLASS), MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_VIDEOENHANCE_CLASS), MAKE_REGLIST(xe_lpd_vec_inst_regs, PF, ENGINE_INSTANCE, GUC_VIDEOENHANCE_CLASS), MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_BLITTER_CLASS), MAKE_REGLIST(xe_lpd_blt_inst_regs, PF, ENGINE_INSTANCE, GUC_BLITTER_CLASS), + MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_GSC_OTHER_CLASS), + MAKE_REGLIST(xe_lpd_gsc_inst_regs, PF, ENGINE_INSTANCE, GUC_GSC_OTHER_CLASS), {} }; @@ -182,12 +191,16 @@ static const struct __guc_mmio_reg_descr_group xe_lpd_lists[] = { MAKE_REGLIST(xe_lpd_global_regs, PF, GLOBAL, 0), MAKE_REGLIST(xe_lpd_rc_class_regs, PF, ENGINE_CLASS, GUC_RENDER_CLASS), MAKE_REGLIST(xe_lpd_rc_inst_regs, PF, ENGINE_INSTANCE, GUC_RENDER_CLASS), + MAKE_REGLIST(xe_lpd_rc_class_regs, PF, ENGINE_CLASS, GUC_COMPUTE_CLASS), + MAKE_REGLIST(xe_lpd_rc_inst_regs, PF, ENGINE_INSTANCE, GUC_COMPUTE_CLASS), MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_VIDEO_CLASS), MAKE_REGLIST(xe_lpd_vd_inst_regs, PF, ENGINE_INSTANCE, GUC_VIDEO_CLASS), MAKE_REGLIST(xe_lpd_vec_class_regs, PF, ENGINE_CLASS, GUC_VIDEOENHANCE_CLASS), MAKE_REGLIST(xe_lpd_vec_inst_regs, PF, ENGINE_INSTANCE, GUC_VIDEOENHANCE_CLASS), MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_BLITTER_CLASS), MAKE_REGLIST(xe_lpd_blt_inst_regs, PF, ENGINE_INSTANCE, GUC_BLITTER_CLASS), + MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_GSC_OTHER_CLASS), + MAKE_REGLIST(xe_lpd_gsc_inst_regs, PF, ENGINE_INSTANCE, GUC_GSC_OTHER_CLASS), {} }; @@ -240,19 +253,19 @@ static void guc_capture_free_extlists(struct __guc_mmio_reg_descr_group *reglist struct __ext_steer_reg { const char *name; - i915_reg_t reg; + i915_mcr_reg_t reg; }; static const struct __ext_steer_reg xe_extregs[] = { - {"GEN7_SAMPLER_INSTDONE", GEN7_SAMPLER_INSTDONE}, - {"GEN7_ROW_INSTDONE", GEN7_ROW_INSTDONE} + {"GEN8_SAMPLER_INSTDONE", GEN8_SAMPLER_INSTDONE}, + {"GEN8_ROW_INSTDONE", GEN8_ROW_INSTDONE} }; static void __fill_ext_reg(struct __guc_mmio_reg_descr *ext, const struct __ext_steer_reg *extlist, int slice_id, int subslice_id) { - ext->reg = extlist->reg; + ext->reg = _MMIO(i915_mmio_reg_offset(extlist->reg)); ext->flags = FIELD_PREP(GUC_REGSET_STEERING_GROUP, slice_id); ext->flags |= FIELD_PREP(GUC_REGSET_STEERING_INSTANCE, subslice_id); ext->regname = extlist->name; @@ -419,6 +432,46 @@ guc_capture_get_device_reglist(struct intel_guc *guc) return default_lists; } +static const char * +__stringify_type(u32 type) +{ + switch (type) { + case GUC_CAPTURE_LIST_TYPE_GLOBAL: + return "Global"; + case GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS: + return "Class"; + case GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE: + return "Instance"; + default: + break; + } + + return "unknown"; +} + +static const char * +__stringify_engclass(u32 class) +{ + switch (class) { + case GUC_RENDER_CLASS: + return "Render"; + case GUC_VIDEO_CLASS: + return "Video"; + case GUC_VIDEOENHANCE_CLASS: + return "VideoEnhance"; + case GUC_BLITTER_CLASS: + return "Blitter"; + case GUC_COMPUTE_CLASS: + return "Compute"; + case GUC_GSC_OTHER_CLASS: + return "GSC-Other"; + default: + break; + } + + return "unknown"; +} + static int guc_capture_list_init(struct intel_guc *guc, u32 owner, u32 type, u32 classid, struct guc_mmio_reg *ptr, u16 num_entries) @@ -482,32 +535,55 @@ guc_cap_list_num_regs(struct intel_guc_state_capture *gc, u32 owner, u32 type, u return num_regs; } -int -intel_guc_capture_getlistsize(struct intel_guc *guc, u32 owner, u32 type, u32 classid, - size_t *size) +static int +guc_capture_getlistsize(struct intel_guc *guc, u32 owner, u32 type, u32 classid, + size_t *size, bool is_purpose_est) { struct intel_guc_state_capture *gc = guc->capture; + struct drm_i915_private *i915 = guc_to_gt(guc)->i915; struct __guc_capture_ads_cache *cache = &gc->ads_cache[owner][type][classid]; int num_regs; - if (!gc->reglists) + if (!gc->reglists) { + drm_warn(&i915->drm, "GuC-capture: No reglist on this device\n"); return -ENODEV; + } if (cache->is_valid) { *size = cache->size; return cache->status; } + if (!is_purpose_est && owner == GUC_CAPTURE_LIST_INDEX_PF && + !guc_capture_get_one_list(gc->reglists, owner, type, classid)) { + if (type == GUC_CAPTURE_LIST_TYPE_GLOBAL) + drm_warn(&i915->drm, "Missing GuC-Err-Cap reglist Global!\n"); + else + drm_warn(&i915->drm, "Missing GuC-Err-Cap reglist %s(%u):%s(%u)!\n", + __stringify_type(type), type, + __stringify_engclass(classid), classid); + return -ENODATA; + } + num_regs = guc_cap_list_num_regs(gc, owner, type, classid); + /* intentional empty lists can exist depending on hw config */ if (!num_regs) return -ENODATA; - *size = PAGE_ALIGN((sizeof(struct guc_debug_capture_list)) + - (num_regs * sizeof(struct guc_mmio_reg))); + if (size) + *size = PAGE_ALIGN((sizeof(struct guc_debug_capture_list)) + + (num_regs * sizeof(struct guc_mmio_reg))); return 0; } +int +intel_guc_capture_getlistsize(struct intel_guc *guc, u32 owner, u32 type, u32 classid, + size_t *size) +{ + return guc_capture_getlistsize(guc, owner, type, classid, size, false); +} + static void guc_capture_create_prealloc_nodes(struct intel_guc *guc); int @@ -606,7 +682,7 @@ guc_capture_output_min_size_est(struct intel_guc *guc) struct intel_gt *gt = guc_to_gt(guc); struct intel_engine_cs *engine; enum intel_engine_id id; - int worst_min_size = 0, num_regs = 0; + int worst_min_size = 0; size_t tmp = 0; if (!guc->capture) @@ -627,21 +703,19 @@ guc_capture_output_min_size_est(struct intel_guc *guc) worst_min_size += sizeof(struct guc_state_capture_group_header_t) + (3 * sizeof(struct guc_state_capture_header_t)); - if (!intel_guc_capture_getlistsize(guc, 0, GUC_CAPTURE_LIST_TYPE_GLOBAL, 0, &tmp)) - num_regs += tmp; + if (!guc_capture_getlistsize(guc, 0, GUC_CAPTURE_LIST_TYPE_GLOBAL, 0, &tmp, true)) + worst_min_size += tmp; - if (!intel_guc_capture_getlistsize(guc, 0, GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS, - engine->class, &tmp)) { - num_regs += tmp; + if (!guc_capture_getlistsize(guc, 0, GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS, + engine->class, &tmp, true)) { + worst_min_size += tmp; } - if (!intel_guc_capture_getlistsize(guc, 0, GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE, - engine->class, &tmp)) { - num_regs += tmp; + if (!guc_capture_getlistsize(guc, 0, GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE, + engine->class, &tmp, true)) { + worst_min_size += tmp; } } - worst_min_size += (num_regs * sizeof(struct guc_mmio_reg)); - return worst_min_size; } @@ -658,15 +732,23 @@ static void check_guc_capture_size(struct intel_guc *guc) int spare_size = min_size * GUC_CAPTURE_OVERBUFFER_MULTIPLIER; u32 buffer_size = intel_guc_log_section_size_capture(&guc->log); + /* + * NOTE: min_size is much smaller than the capture region allocation (DG2: <80K vs 1MB) + * Additionally, its based on space needed to fit all engines getting reset at once + * within the same G2H handler task slot. This is very unlikely. However, if GuC really + * does run out of space for whatever reason, we will see an separate warning message + * when processing the G2H event capture-notification, search for: + * INTEL_GUC_STATE_CAPTURE_EVENT_STATUS_NOSPACE. + */ if (min_size < 0) drm_warn(&i915->drm, "Failed to calculate GuC error state capture buffer minimum size: %d!\n", min_size); else if (min_size > buffer_size) - drm_warn(&i915->drm, "GuC error state capture buffer is too small: %d < %d\n", + drm_warn(&i915->drm, "GuC error state capture buffer maybe small: %d < %d\n", buffer_size, min_size); else if (spare_size > buffer_size) - drm_notice(&i915->drm, "GuC error state capture buffer maybe too small: %d < %d (min = %d)\n", - buffer_size, spare_size, min_size); + drm_dbg(&i915->drm, "GuC error state capture buffer lacks spare size: %d < %d (min = %d)\n", + buffer_size, spare_size, min_size); } /* diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c index 25f09a420561..7269eb0bbedf 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c @@ -71,12 +71,73 @@ static bool intel_eval_slpc_support(void *data) return intel_guc_slpc_is_used(guc); } +static int guc_sched_disable_delay_ms_get(void *data, u64 *val) +{ + struct intel_guc *guc = data; + + if (!intel_guc_submission_is_used(guc)) + return -ENODEV; + + *val = (u64)guc->submission_state.sched_disable_delay_ms; + + return 0; +} + +static int guc_sched_disable_delay_ms_set(void *data, u64 val) +{ + struct intel_guc *guc = data; + + if (!intel_guc_submission_is_used(guc)) + return -ENODEV; + + /* clamp to a practical limit, 1 minute is reasonable for a longest delay */ + guc->submission_state.sched_disable_delay_ms = min_t(u64, val, 60000); + + return 0; +} +DEFINE_SIMPLE_ATTRIBUTE(guc_sched_disable_delay_ms_fops, + guc_sched_disable_delay_ms_get, + guc_sched_disable_delay_ms_set, "%lld\n"); + +static int guc_sched_disable_gucid_threshold_get(void *data, u64 *val) +{ + struct intel_guc *guc = data; + + if (!intel_guc_submission_is_used(guc)) + return -ENODEV; + + *val = guc->submission_state.sched_disable_gucid_threshold; + return 0; +} + +static int guc_sched_disable_gucid_threshold_set(void *data, u64 val) +{ + struct intel_guc *guc = data; + + if (!intel_guc_submission_is_used(guc)) + return -ENODEV; + + if (val > intel_guc_sched_disable_gucid_threshold_max(guc)) + guc->submission_state.sched_disable_gucid_threshold = + intel_guc_sched_disable_gucid_threshold_max(guc); + else + guc->submission_state.sched_disable_gucid_threshold = val; + + return 0; +} +DEFINE_SIMPLE_ATTRIBUTE(guc_sched_disable_gucid_threshold_fops, + guc_sched_disable_gucid_threshold_get, + guc_sched_disable_gucid_threshold_set, "%lld\n"); + void intel_guc_debugfs_register(struct intel_guc *guc, struct dentry *root) { static const struct intel_gt_debugfs_file files[] = { { "guc_info", &guc_info_fops, NULL }, { "guc_registered_contexts", &guc_registered_contexts_fops, NULL }, { "guc_slpc_info", &guc_slpc_info_fops, &intel_eval_slpc_support}, + { "guc_sched_disable_delay_ms", &guc_sched_disable_delay_ms_fops, NULL }, + { "guc_sched_disable_gucid_threshold", &guc_sched_disable_gucid_threshold_fops, + NULL }, }; if (!intel_guc_is_supported(guc)) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c index a0372735cddb..5b86b2e286e0 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c @@ -10,12 +10,15 @@ */ #include "gt/intel_gt.h" +#include "gt/intel_gt_mcr.h" #include "gt/intel_gt_regs.h" #include "intel_guc_fw.h" #include "i915_drv.h" -static void guc_prepare_xfer(struct intel_uncore *uncore) +static void guc_prepare_xfer(struct intel_gt *gt) { + struct intel_uncore *uncore = gt->uncore; + u32 shim_flags = GUC_ENABLE_READ_CACHE_LOGIC | GUC_ENABLE_READ_CACHE_FOR_SRAM_DATA | GUC_ENABLE_READ_CACHE_FOR_WOPCM_DATA | @@ -35,8 +38,9 @@ static void guc_prepare_xfer(struct intel_uncore *uncore) if (GRAPHICS_VER(uncore->i915) == 9) { /* DOP Clock Gating Enable for GuC clocks */ - intel_uncore_rmw(uncore, GEN7_MISCCPCTL, - 0, GEN8_DOP_CLOCK_GATE_GUC_ENABLE); + intel_gt_mcr_multicast_write(gt, GEN8_MISCCPCTL, + GEN8_DOP_CLOCK_GATE_GUC_ENABLE | + intel_gt_mcr_read_any(gt, GEN8_MISCCPCTL)); /* allows for 5us (in 10ns units) before GT can go to RC6 */ intel_uncore_write(uncore, GUC_ARAT_C6DIS, 0x1FF); @@ -168,7 +172,7 @@ int intel_guc_fw_upload(struct intel_guc *guc) struct intel_uncore *uncore = gt->uncore; int ret; - guc_prepare_xfer(uncore); + guc_prepare_xfer(gt); /* * Note that GuC needs the CSS header plus uKernel code to be copied diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h index 323b055e5db9..4ae5fc2f6002 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h @@ -47,7 +47,8 @@ #define GUC_VIDEOENHANCE_CLASS 2 #define GUC_BLITTER_CLASS 3 #define GUC_COMPUTE_CLASS 4 -#define GUC_LAST_ENGINE_CLASS GUC_COMPUTE_CLASS +#define GUC_GSC_OTHER_CLASS 5 +#define GUC_LAST_ENGINE_CLASS GUC_GSC_OTHER_CLASS #define GUC_MAX_ENGINE_CLASSES 16 #define GUC_MAX_INSTANCES_PER_CLASS 32 @@ -169,6 +170,7 @@ static u8 engine_class_guc_class_map[] = { [COPY_ENGINE_CLASS] = GUC_BLITTER_CLASS, [VIDEO_DECODE_CLASS] = GUC_VIDEO_CLASS, [VIDEO_ENHANCEMENT_CLASS] = GUC_VIDEOENHANCE_CLASS, + [OTHER_CLASS] = GUC_GSC_OTHER_CLASS, [COMPUTE_CLASS] = GUC_COMPUTE_CLASS, }; @@ -178,12 +180,13 @@ static u8 guc_class_engine_class_map[] = { [GUC_VIDEO_CLASS] = VIDEO_DECODE_CLASS, [GUC_VIDEOENHANCE_CLASS] = VIDEO_ENHANCEMENT_CLASS, [GUC_COMPUTE_CLASS] = COMPUTE_CLASS, + [GUC_GSC_OTHER_CLASS] = OTHER_CLASS, }; static inline u8 engine_class_to_guc_class(u8 class) { BUILD_BUG_ON(ARRAY_SIZE(engine_class_guc_class_map) != MAX_ENGINE_CLASS + 1); - GEM_BUG_ON(class > MAX_ENGINE_CLASS || class == OTHER_CLASS); + GEM_BUG_ON(class > MAX_ENGINE_CLASS); return engine_class_guc_class_map[class]; } @@ -290,6 +293,25 @@ struct guc_update_context_policy { struct guc_klv_generic_dw_t klv[GUC_CONTEXT_POLICIES_KLV_NUM_IDS]; } __packed; +/* Format of the UPDATE_SCHEDULING_POLICIES H2G data packet */ +struct guc_update_scheduling_policy_header { + u32 action; +} __packed; + +/* + * Can't dynmically allocate memory for the scheduling policy KLV because + * it will be sent from within the reset path. Need a fixed size lump on + * the stack instead :(. + * + * Currently, there is only one KLV defined, which has 1 word of KL + 2 words of V. + */ +#define MAX_SCHEDULING_POLICY_SIZE 3 + +struct guc_update_scheduling_policy { + struct guc_update_scheduling_policy_header header; + u32 data[MAX_SCHEDULING_POLICY_SIZE]; +} __packed; + #define GUC_POWER_UNSPECIFIED 0 #define GUC_POWER_D0 1 #define GUC_POWER_D1 2 @@ -298,6 +320,9 @@ struct guc_update_context_policy { /* Scheduling policy settings */ +#define GLOBAL_SCHEDULE_POLICY_RC_YIELD_DURATION 100 /* in ms */ +#define GLOBAL_SCHEDULE_POLICY_RC_YIELD_RATIO 50 /* in percent */ + #define GLOBAL_POLICY_MAX_NUM_WI 15 /* Don't reset an engine upon preemption failure */ @@ -305,6 +330,27 @@ struct guc_update_context_policy { #define GLOBAL_POLICY_DEFAULT_DPC_PROMOTE_TIME_US 500000 +/* + * GuC converts the timeout to clock ticks internally. Different platforms have + * different GuC clocks. Thus, the maximum value before overflow is platform + * dependent. Current worst case scenario is about 110s. So, the spec says to + * limit to 100s to be safe. + */ +#define GUC_POLICY_MAX_EXEC_QUANTUM_US (100 * 1000 * 1000UL) +#define GUC_POLICY_MAX_PREEMPT_TIMEOUT_US (100 * 1000 * 1000UL) + +static inline u32 guc_policy_max_exec_quantum_ms(void) +{ + BUILD_BUG_ON(GUC_POLICY_MAX_EXEC_QUANTUM_US >= UINT_MAX); + return GUC_POLICY_MAX_EXEC_QUANTUM_US / 1000; +} + +static inline u32 guc_policy_max_preempt_timeout_ms(void) +{ + BUILD_BUG_ON(GUC_POLICY_MAX_PREEMPT_TIMEOUT_US >= UINT_MAX); + return GUC_POLICY_MAX_PREEMPT_TIMEOUT_US / 1000; +} + struct guc_policies { u32 submission_queue_depth[GUC_MAX_ENGINE_CLASSES]; /* In micro seconds. How much time to allow before DPC processing is diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c index 55d3ef93e86f..68331c538b0a 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c @@ -16,15 +16,15 @@ #if defined(CONFIG_DRM_I915_DEBUG_GUC) #define GUC_LOG_DEFAULT_CRASH_BUFFER_SIZE SZ_2M #define GUC_LOG_DEFAULT_DEBUG_BUFFER_SIZE SZ_16M -#define GUC_LOG_DEFAULT_CAPTURE_BUFFER_SIZE SZ_4M +#define GUC_LOG_DEFAULT_CAPTURE_BUFFER_SIZE SZ_1M #elif defined(CONFIG_DRM_I915_DEBUG_GEM) #define GUC_LOG_DEFAULT_CRASH_BUFFER_SIZE SZ_1M #define GUC_LOG_DEFAULT_DEBUG_BUFFER_SIZE SZ_2M -#define GUC_LOG_DEFAULT_CAPTURE_BUFFER_SIZE SZ_4M +#define GUC_LOG_DEFAULT_CAPTURE_BUFFER_SIZE SZ_1M #else #define GUC_LOG_DEFAULT_CRASH_BUFFER_SIZE SZ_8K #define GUC_LOG_DEFAULT_DEBUG_BUFFER_SIZE SZ_64K -#define GUC_LOG_DEFAULT_CAPTURE_BUFFER_SIZE SZ_2M +#define GUC_LOG_DEFAULT_CAPTURE_BUFFER_SIZE SZ_1M #endif static void guc_log_copy_debuglogs_for_relay(struct intel_guc_log *log); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c index 8f8dd05835c5..b5855091cf6a 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c @@ -11,9 +11,20 @@ static bool __guc_rc_supported(struct intel_guc *guc) { + struct intel_gt *gt = guc_to_gt(guc); + + /* + * Wa_14017073508: mtl + * Do not enable gucrc to avoid additional interrupts which + * may disrupt pcode wa. + */ + if (IS_MTL_GRAPHICS_STEP(gt->i915, P, STEP_A0, STEP_B0) && + gt->type == GT_MEDIA) + return false; + /* GuC RC is unavailable for pre-Gen12 */ return guc->submission_supported && - GRAPHICS_VER(guc_to_gt(guc)->i915) >= 12; + GRAPHICS_VER(gt->i915) >= 12; } static bool __guc_rc_selected(struct intel_guc *guc) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h index a7092f711e9c..9915de32e894 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h @@ -36,6 +36,7 @@ #define SOFT_SCRATCH_COUNT 16 #define GEN11_SOFT_SCRATCH(n) _MMIO(0x190240 + (n) * 4) +#define MEDIA_SOFT_SCRATCH(n) _MMIO(0x190310 + (n) * 4) #define GEN11_SOFT_SCRATCH_COUNT 4 #define UOS_RSA_SCRATCH(i) _MMIO(0xc200 + (i) * 4) @@ -101,6 +102,7 @@ #define GUC_SEND_INTERRUPT _MMIO(0xc4c8) #define GUC_SEND_TRIGGER (1<<0) #define GEN11_GUC_HOST_INTERRUPT _MMIO(0x1901f0) +#define MEDIA_GUC_HOST_INTERRUPT _MMIO(0x190304) #define GEN12_GUC_SEM_INTR_ENABLES _MMIO(0xc71c) #define GUC_SEM_INTR_ROUTE_TO_GUC BIT(31) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c index fdd895f73f9f..63464933cbce 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c @@ -137,6 +137,17 @@ static int guc_action_slpc_set_param(struct intel_guc *guc, u8 id, u32 value) return ret > 0 ? -EPROTO : ret; } +static int guc_action_slpc_unset_param(struct intel_guc *guc, u8 id) +{ + u32 request[] = { + GUC_ACTION_HOST2GUC_PC_SLPC_REQUEST, + SLPC_EVENT(SLPC_EVENT_PARAMETER_UNSET, 1), + id, + }; + + return intel_guc_send(guc, request, ARRAY_SIZE(request)); +} + static bool slpc_is_running(struct intel_guc_slpc *slpc) { return slpc_get_state(slpc) == SLPC_GLOBAL_STATE_RUNNING; @@ -190,6 +201,15 @@ static int slpc_set_param(struct intel_guc_slpc *slpc, u8 id, u32 value) return ret; } +static int slpc_unset_param(struct intel_guc_slpc *slpc, u8 id) +{ + struct intel_guc *guc = slpc_to_guc(slpc); + + GEM_BUG_ON(id >= SLPC_MAX_PARAM); + + return guc_action_slpc_unset_param(guc, id); +} + static int slpc_force_min_freq(struct intel_guc_slpc *slpc, u32 freq) { struct drm_i915_private *i915 = slpc_to_i915(slpc); @@ -263,6 +283,7 @@ int intel_guc_slpc_init(struct intel_guc_slpc *slpc) slpc->max_freq_softlimit = 0; slpc->min_freq_softlimit = 0; + slpc->min_is_rpmax = false; slpc->boost_freq = 0; atomic_set(&slpc->num_waiters, 0); @@ -588,6 +609,39 @@ static int slpc_set_softlimits(struct intel_guc_slpc *slpc) return 0; } +static bool is_slpc_min_freq_rpmax(struct intel_guc_slpc *slpc) +{ + struct drm_i915_private *i915 = slpc_to_i915(slpc); + int slpc_min_freq; + int ret; + + ret = intel_guc_slpc_get_min_freq(slpc, &slpc_min_freq); + if (ret) { + drm_err(&i915->drm, + "Failed to get min freq: (%d)\n", + ret); + return false; + } + + if (slpc_min_freq == SLPC_MAX_FREQ_MHZ) + return true; + else + return false; +} + +static void update_server_min_softlimit(struct intel_guc_slpc *slpc) +{ + /* For server parts, SLPC min will be at RPMax. + * Use min softlimit to clamp it to RP0 instead. + */ + if (!slpc->min_freq_softlimit && + is_slpc_min_freq_rpmax(slpc)) { + slpc->min_is_rpmax = true; + slpc->min_freq_softlimit = slpc->rp0_freq; + (slpc_to_gt(slpc))->defaults.min_freq = slpc->min_freq_softlimit; + } +} + static int slpc_use_fused_rp0(struct intel_guc_slpc *slpc) { /* Force SLPC to used platform rp0 */ @@ -610,6 +664,52 @@ static void slpc_get_rp_values(struct intel_guc_slpc *slpc) slpc->boost_freq = slpc->rp0_freq; } +/** + * intel_guc_slpc_override_gucrc_mode() - override GUCRC mode + * @slpc: pointer to intel_guc_slpc. + * @mode: new value of the mode. + * + * This function will override the GUCRC mode. + * + * Return: 0 on success, non-zero error code on failure. + */ +int intel_guc_slpc_override_gucrc_mode(struct intel_guc_slpc *slpc, u32 mode) +{ + int ret; + struct drm_i915_private *i915 = slpc_to_i915(slpc); + intel_wakeref_t wakeref; + + if (mode >= SLPC_GUCRC_MODE_MAX) + return -EINVAL; + + with_intel_runtime_pm(&i915->runtime_pm, wakeref) { + ret = slpc_set_param(slpc, SLPC_PARAM_PWRGATE_RC_MODE, mode); + if (ret) + drm_err(&i915->drm, + "Override gucrc mode %d failed %d\n", + mode, ret); + } + + return ret; +} + +int intel_guc_slpc_unset_gucrc_mode(struct intel_guc_slpc *slpc) +{ + struct drm_i915_private *i915 = slpc_to_i915(slpc); + intel_wakeref_t wakeref; + int ret = 0; + + with_intel_runtime_pm(&i915->runtime_pm, wakeref) { + ret = slpc_unset_param(slpc, SLPC_PARAM_PWRGATE_RC_MODE); + if (ret) + drm_err(&i915->drm, + "Unsetting gucrc mode failed %d\n", + ret); + } + + return ret; +} + /* * intel_guc_slpc_enable() - Start SLPC * @slpc: pointer to intel_guc_slpc. @@ -647,6 +747,9 @@ int intel_guc_slpc_enable(struct intel_guc_slpc *slpc) slpc_get_rp_values(slpc); + /* Handle the case where min=max=RPmax */ + update_server_min_softlimit(slpc); + /* Set SLPC max limit to RP0 */ ret = slpc_use_fused_rp0(slpc); if (unlikely(ret)) { diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h index 82a98f78f96c..17ed515f6a85 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h @@ -9,6 +9,8 @@ #include "intel_guc_submission.h" #include "intel_guc_slpc_types.h" +#define SLPC_MAX_FREQ_MHZ 4250 + struct intel_gt; struct drm_printer; @@ -42,5 +44,7 @@ int intel_guc_slpc_set_media_ratio_mode(struct intel_guc_slpc *slpc, u32 val); void intel_guc_pm_intrmsk_enable(struct intel_gt *gt); void intel_guc_slpc_boost(struct intel_guc_slpc *slpc); void intel_guc_slpc_dec_waiters(struct intel_guc_slpc *slpc); +int intel_guc_slpc_unset_gucrc_mode(struct intel_guc_slpc *slpc); +int intel_guc_slpc_override_gucrc_mode(struct intel_guc_slpc *slpc, u32 mode); #endif diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc_types.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc_types.h index 73d208123528..a6ef53b04e04 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc_types.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc_types.h @@ -19,6 +19,9 @@ struct intel_guc_slpc { bool supported; bool selected; + /* Indicates this is a server part */ + bool min_is_rpmax; + /* platform frequency limits */ u32 min_freq; u32 rp0_freq; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 1db59eeb34db..0a42f1807f52 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -6,6 +6,7 @@ #include <linux/circ_buf.h> #include "gem/i915_gem_context.h" +#include "gem/i915_gem_lmem.h" #include "gt/gen8_engine_cs.h" #include "gt/intel_breadcrumbs.h" #include "gt/intel_context.h" @@ -29,6 +30,7 @@ #include "intel_guc_submission.h" #include "i915_drv.h" +#include "i915_reg.h" #include "i915_trace.h" /** @@ -65,7 +67,13 @@ * corresponding G2H returns indicating the scheduling disable operation has * completed it is safe to unpin the context. While a disable is in flight it * isn't safe to resubmit the context so a fence is used to stall all future - * requests of that context until the G2H is returned. + * requests of that context until the G2H is returned. Because this interaction + * with the GuC takes a non-zero amount of time we delay the disabling of + * scheduling after the pin count goes to zero by a configurable period of time + * (see SCHED_DISABLE_DELAY_MS). The thought is this gives the user a window of + * time to resubmit something on the context before doing this costly operation. + * This delay is only done if the context isn't closed and the guc_id usage is + * less than a threshold (see NUM_SCHED_DISABLE_GUC_IDS_THRESHOLD). * * Context deregistration: * Before a context can be destroyed or if we steal its guc_id we must @@ -163,7 +171,8 @@ guc_create_parallel(struct intel_engine_cs **engines, #define SCHED_STATE_PENDING_ENABLE BIT(5) #define SCHED_STATE_REGISTERED BIT(6) #define SCHED_STATE_POLICY_REQUIRED BIT(7) -#define SCHED_STATE_BLOCKED_SHIFT 8 +#define SCHED_STATE_CLOSED BIT(8) +#define SCHED_STATE_BLOCKED_SHIFT 9 #define SCHED_STATE_BLOCKED BIT(SCHED_STATE_BLOCKED_SHIFT) #define SCHED_STATE_BLOCKED_MASK (0xfff << SCHED_STATE_BLOCKED_SHIFT) @@ -173,12 +182,20 @@ static inline void init_sched_state(struct intel_context *ce) ce->guc_state.sched_state &= SCHED_STATE_BLOCKED_MASK; } +/* + * Kernel contexts can have SCHED_STATE_REGISTERED after suspend. + * A context close can race with the submission path, so SCHED_STATE_CLOSED + * can be set immediately before we try to register. + */ +#define SCHED_STATE_VALID_INIT \ + (SCHED_STATE_BLOCKED_MASK | \ + SCHED_STATE_CLOSED | \ + SCHED_STATE_REGISTERED) + __maybe_unused static bool sched_state_is_init(struct intel_context *ce) { - /* Kernel contexts can have SCHED_STATE_REGISTERED after suspend. */ - return !(ce->guc_state.sched_state & - ~(SCHED_STATE_BLOCKED_MASK | SCHED_STATE_REGISTERED)); + return !(ce->guc_state.sched_state & ~SCHED_STATE_VALID_INIT); } static inline bool @@ -319,6 +336,17 @@ static inline void clr_context_policy_required(struct intel_context *ce) ce->guc_state.sched_state &= ~SCHED_STATE_POLICY_REQUIRED; } +static inline bool context_close_done(struct intel_context *ce) +{ + return ce->guc_state.sched_state & SCHED_STATE_CLOSED; +} + +static inline void set_context_close_done(struct intel_context *ce) +{ + lockdep_assert_held(&ce->guc_state.lock); + ce->guc_state.sched_state |= SCHED_STATE_CLOSED; +} + static inline u32 context_blocked(struct intel_context *ce) { return (ce->guc_state.sched_state & SCHED_STATE_BLOCKED_MASK) >> @@ -343,25 +371,6 @@ static inline void decr_context_blocked(struct intel_context *ce) ce->guc_state.sched_state -= SCHED_STATE_BLOCKED; } -static inline bool context_has_committed_requests(struct intel_context *ce) -{ - return !!ce->guc_state.number_committed_requests; -} - -static inline void incr_context_committed_requests(struct intel_context *ce) -{ - lockdep_assert_held(&ce->guc_state.lock); - ++ce->guc_state.number_committed_requests; - GEM_BUG_ON(ce->guc_state.number_committed_requests < 0); -} - -static inline void decr_context_committed_requests(struct intel_context *ce) -{ - lockdep_assert_held(&ce->guc_state.lock); - --ce->guc_state.number_committed_requests; - GEM_BUG_ON(ce->guc_state.number_committed_requests < 0); -} - static struct intel_context * request_to_scheduling_context(struct i915_request *rq) { @@ -1067,6 +1076,12 @@ static void scrub_guc_desc_for_outstanding_g2h(struct intel_guc *guc) xa_unlock(&guc->context_lookup); + if (test_bit(CONTEXT_GUC_INIT, &ce->flags) && + (cancel_delayed_work(&ce->guc_state.sched_disable_delay_work))) { + /* successful cancel so jump straight to close it */ + intel_context_sched_disable_unpin(ce); + } + spin_lock(&ce->guc_state.lock); /* @@ -1387,7 +1402,9 @@ static void guc_timestamp_ping(struct work_struct *wrk) /* * Synchronize with gt reset to make sure the worker does not - * corrupt the engine/guc stats. + * corrupt the engine/guc stats. NB: can't actually block waiting + * for a reset to complete as the reset requires flushing out + * this worker thread if started. So waiting would deadlock. */ ret = intel_gt_reset_trylock(gt, &srcu); if (ret) @@ -1994,6 +2011,9 @@ static int new_guc_id(struct intel_guc *guc, struct intel_context *ce) if (unlikely(ret < 0)) return ret; + if (!intel_context_is_parent(ce)) + ++guc->submission_state.guc_ids_in_use; + ce->guc_id.id = ret; return 0; } @@ -2003,14 +2023,16 @@ static void __release_guc_id(struct intel_guc *guc, struct intel_context *ce) GEM_BUG_ON(intel_context_is_child(ce)); if (!context_guc_id_invalid(ce)) { - if (intel_context_is_parent(ce)) + if (intel_context_is_parent(ce)) { bitmap_release_region(guc->submission_state.guc_ids_bitmap, ce->guc_id.id, order_base_2(ce->parallel.number_children + 1)); - else + } else { + --guc->submission_state.guc_ids_in_use; ida_simple_remove(&guc->submission_state.guc_ids, ce->guc_id.id); + } clr_ctx_id_mapping(guc, ce->guc_id.id); set_context_guc_id_invalid(ce); } @@ -2429,6 +2451,10 @@ static int guc_context_policy_init_v70(struct intel_context *ce, bool loop) int ret; /* NB: For both of these, zero means disabled. */ + GEM_BUG_ON(overflows_type(engine->props.timeslice_duration_ms * 1000, + execution_quantum)); + GEM_BUG_ON(overflows_type(engine->props.preempt_timeout_ms * 1000, + preemption_timeout)); execution_quantum = engine->props.timeslice_duration_ms * 1000; preemption_timeout = engine->props.preempt_timeout_ms * 1000; @@ -2462,6 +2488,10 @@ static void guc_context_policy_init_v69(struct intel_engine_cs *engine, desc->policy_flags |= CONTEXT_POLICY_FLAG_PREEMPT_TO_IDLE_V69; /* NB: For both of these, zero means disabled. */ + GEM_BUG_ON(overflows_type(engine->props.timeslice_duration_ms * 1000, + desc->execution_quantum)); + GEM_BUG_ON(overflows_type(engine->props.preempt_timeout_ms * 1000, + desc->preemption_timeout)); desc->execution_quantum = engine->props.timeslice_duration_ms * 1000; desc->preemption_timeout = engine->props.preempt_timeout_ms * 1000; } @@ -2998,41 +3028,104 @@ guc_context_revoke(struct intel_context *ce, struct i915_request *rq, } } -static void guc_context_sched_disable(struct intel_context *ce) +static void do_sched_disable(struct intel_guc *guc, struct intel_context *ce, + unsigned long flags) + __releases(ce->guc_state.lock) { - struct intel_guc *guc = ce_to_guc(ce); - unsigned long flags; struct intel_runtime_pm *runtime_pm = &ce->engine->gt->i915->runtime_pm; intel_wakeref_t wakeref; u16 guc_id; + lockdep_assert_held(&ce->guc_state.lock); + guc_id = prep_context_pending_disable(ce); + + spin_unlock_irqrestore(&ce->guc_state.lock, flags); + + with_intel_runtime_pm(runtime_pm, wakeref) + __guc_context_sched_disable(guc, ce, guc_id); +} + +static bool bypass_sched_disable(struct intel_guc *guc, + struct intel_context *ce) +{ + lockdep_assert_held(&ce->guc_state.lock); GEM_BUG_ON(intel_context_is_child(ce)); + if (submission_disabled(guc) || context_guc_id_invalid(ce) || + !ctx_id_mapped(guc, ce->guc_id.id)) { + clr_context_enabled(ce); + return true; + } + + return !context_enabled(ce); +} + +static void __delay_sched_disable(struct work_struct *wrk) +{ + struct intel_context *ce = + container_of(wrk, typeof(*ce), guc_state.sched_disable_delay_work.work); + struct intel_guc *guc = ce_to_guc(ce); + unsigned long flags; + spin_lock_irqsave(&ce->guc_state.lock, flags); + if (bypass_sched_disable(guc, ce)) { + spin_unlock_irqrestore(&ce->guc_state.lock, flags); + intel_context_sched_disable_unpin(ce); + } else { + do_sched_disable(guc, ce, flags); + } +} + +static bool guc_id_pressure(struct intel_guc *guc, struct intel_context *ce) +{ /* - * We have to check if the context has been disabled by another thread, - * check if submssion has been disabled to seal a race with reset and - * finally check if any more requests have been committed to the - * context ensursing that a request doesn't slip through the - * 'context_pending_disable' fence. + * parent contexts are perma-pinned, if we are unpinning do schedule + * disable immediately. */ - if (unlikely(!context_enabled(ce) || submission_disabled(guc) || - context_has_committed_requests(ce))) { - clr_context_enabled(ce); + if (intel_context_is_parent(ce)) + return true; + + /* + * If we are beyond the threshold for avail guc_ids, do schedule disable immediately. + */ + return guc->submission_state.guc_ids_in_use > + guc->submission_state.sched_disable_gucid_threshold; +} + +static void guc_context_sched_disable(struct intel_context *ce) +{ + struct intel_guc *guc = ce_to_guc(ce); + u64 delay = guc->submission_state.sched_disable_delay_ms; + unsigned long flags; + + spin_lock_irqsave(&ce->guc_state.lock, flags); + + if (bypass_sched_disable(guc, ce)) { + spin_unlock_irqrestore(&ce->guc_state.lock, flags); + intel_context_sched_disable_unpin(ce); + } else if (!intel_context_is_closed(ce) && !guc_id_pressure(guc, ce) && + delay) { spin_unlock_irqrestore(&ce->guc_state.lock, flags); - goto unpin; + mod_delayed_work(system_unbound_wq, + &ce->guc_state.sched_disable_delay_work, + msecs_to_jiffies(delay)); + } else { + do_sched_disable(guc, ce, flags); } - guc_id = prep_context_pending_disable(ce); +} - spin_unlock_irqrestore(&ce->guc_state.lock, flags); +static void guc_context_close(struct intel_context *ce) +{ + unsigned long flags; - with_intel_runtime_pm(runtime_pm, wakeref) - __guc_context_sched_disable(guc, ce, guc_id); + if (test_bit(CONTEXT_GUC_INIT, &ce->flags) && + cancel_delayed_work(&ce->guc_state.sched_disable_delay_work)) + __delay_sched_disable(&ce->guc_state.sched_disable_delay_work.work); - return; -unpin: - intel_context_sched_disable_unpin(ce); + spin_lock_irqsave(&ce->guc_state.lock, flags); + set_context_close_done(ce); + spin_unlock_irqrestore(&ce->guc_state.lock, flags); } static inline void guc_lrc_desc_unpin(struct intel_context *ce) @@ -3071,7 +3164,6 @@ static void __guc_context_destroy(struct intel_context *ce) ce->guc_state.prio_count[GUC_CLIENT_PRIORITY_HIGH] || ce->guc_state.prio_count[GUC_CLIENT_PRIORITY_KMD_NORMAL] || ce->guc_state.prio_count[GUC_CLIENT_PRIORITY_NORMAL]); - GEM_BUG_ON(ce->guc_state.number_committed_requests); lrc_fini(ce); intel_context_fini(ce); @@ -3340,8 +3432,6 @@ static void remove_from_context(struct i915_request *rq) guc_prio_fini(rq, ce); - decr_context_committed_requests(ce); - spin_unlock_irq(&ce->guc_state.lock); atomic_dec(&ce->guc_id.ref); @@ -3351,6 +3441,8 @@ static void remove_from_context(struct i915_request *rq) static const struct intel_context_ops guc_context_ops = { .alloc = guc_context_alloc, + .close = guc_context_close, + .pre_pin = guc_context_pre_pin, .pin = guc_context_pin, .unpin = guc_context_unpin, @@ -3433,6 +3525,10 @@ static void guc_context_init(struct intel_context *ce) rcu_read_unlock(); ce->guc_state.prio = map_i915_prio_to_guc_prio(prio); + + INIT_DELAYED_WORK(&ce->guc_state.sched_disable_delay_work, + __delay_sched_disable); + set_bit(CONTEXT_GUC_INIT, &ce->flags); } @@ -3471,6 +3567,26 @@ static int guc_request_alloc(struct i915_request *rq) guc_context_init(ce); /* + * If the context gets closed while the execbuf is ongoing, the context + * close code will race with the below code to cancel the delayed work. + * If the context close wins the race and cancels the work, it will + * immediately call the sched disable (see guc_context_close), so there + * is a chance we can get past this check while the sched_disable code + * is being executed. To make sure that code completes before we check + * the status further down, we wait for the close process to complete. + * Else, this code path could send a request down thinking that the + * context is still in a schedule-enable mode while the GuC ends up + * dropping the request completely because the disable did go from the + * context_close path right to GuC just prior. In the event the CT is + * full, we could potentially need to wait up to 1.5 seconds. + */ + if (cancel_delayed_work_sync(&ce->guc_state.sched_disable_delay_work)) + intel_context_sched_disable_unpin(ce); + else if (intel_context_is_closed(ce)) + if (wait_for(context_close_done(ce), 1500)) + drm_warn(&guc_to_gt(guc)->i915->drm, + "timed out waiting on context sched close before realloc\n"); + /* * Call pin_guc_id here rather than in the pinning step as with * dma_resv, contexts can be repeatedly pinned / unpinned trashing the * guc_id and creating horrible race conditions. This is especially bad @@ -3524,7 +3640,6 @@ out: list_add_tail(&rq->guc_fence_link, &ce->guc_state.fences); } - incr_context_committed_requests(ce); spin_unlock_irqrestore(&ce->guc_state.lock, flags); return 0; @@ -3600,6 +3715,8 @@ static int guc_virtual_context_alloc(struct intel_context *ce) static const struct intel_context_ops virtual_guc_context_ops = { .alloc = guc_virtual_context_alloc, + .close = guc_context_close, + .pre_pin = guc_virtual_context_pre_pin, .pin = guc_virtual_context_pin, .unpin = guc_virtual_context_unpin, @@ -3689,6 +3806,8 @@ static void guc_child_context_destroy(struct kref *kref) static const struct intel_context_ops virtual_parent_context_ops = { .alloc = guc_virtual_context_alloc, + .close = guc_context_close, + .pre_pin = guc_context_pre_pin, .pin = guc_parent_context_pin, .unpin = guc_parent_context_unpin, @@ -3995,6 +4114,9 @@ static inline void guc_kernel_context_pin(struct intel_guc *guc, if (context_guc_id_invalid(ce)) pin_guc_id(guc, ce); + if (!test_bit(CONTEXT_GUC_INIT, &ce->flags)) + guc_context_init(ce); + try_context_registration(ce, true); } @@ -4093,7 +4215,7 @@ static void guc_default_vfuncs(struct intel_engine_cs *engine) engine->emit_bb_start = gen8_emit_bb_start; if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50)) - engine->emit_bb_start = gen125_emit_bb_start; + engine->emit_bb_start = xehp_emit_bb_start; } static void rcs_submission_override(struct intel_engine_cs *engine) @@ -4177,6 +4299,98 @@ int intel_guc_submission_setup(struct intel_engine_cs *engine) return 0; } +struct scheduling_policy { + /* internal data */ + u32 max_words, num_words; + u32 count; + /* API data */ + struct guc_update_scheduling_policy h2g; +}; + +static u32 __guc_scheduling_policy_action_size(struct scheduling_policy *policy) +{ + u32 *start = (void *)&policy->h2g; + u32 *end = policy->h2g.data + policy->num_words; + size_t delta = end - start; + + return delta; +} + +static struct scheduling_policy *__guc_scheduling_policy_start_klv(struct scheduling_policy *policy) +{ + policy->h2g.header.action = INTEL_GUC_ACTION_UPDATE_SCHEDULING_POLICIES_KLV; + policy->max_words = ARRAY_SIZE(policy->h2g.data); + policy->num_words = 0; + policy->count = 0; + + return policy; +} + +static void __guc_scheduling_policy_add_klv(struct scheduling_policy *policy, + u32 action, u32 *data, u32 len) +{ + u32 *klv_ptr = policy->h2g.data + policy->num_words; + + GEM_BUG_ON((policy->num_words + 1 + len) > policy->max_words); + *(klv_ptr++) = FIELD_PREP(GUC_KLV_0_KEY, action) | + FIELD_PREP(GUC_KLV_0_LEN, len); + memcpy(klv_ptr, data, sizeof(u32) * len); + policy->num_words += 1 + len; + policy->count++; +} + +static int __guc_action_set_scheduling_policies(struct intel_guc *guc, + struct scheduling_policy *policy) +{ + int ret; + + ret = intel_guc_send(guc, (u32 *)&policy->h2g, + __guc_scheduling_policy_action_size(policy)); + if (ret < 0) + return ret; + + if (ret != policy->count) { + drm_warn(&guc_to_gt(guc)->i915->drm, "GuC global scheduler policy processed %d of %d KLVs!", + ret, policy->count); + if (ret > policy->count) + return -EPROTO; + } + + return 0; +} + +static int guc_init_global_schedule_policy(struct intel_guc *guc) +{ + struct scheduling_policy policy; + struct intel_gt *gt = guc_to_gt(guc); + intel_wakeref_t wakeref; + int ret = 0; + + if (GET_UC_VER(guc) < MAKE_UC_VER(70, 3, 0)) + return 0; + + __guc_scheduling_policy_start_klv(&policy); + + with_intel_runtime_pm(>->i915->runtime_pm, wakeref) { + u32 yield[] = { + GLOBAL_SCHEDULE_POLICY_RC_YIELD_DURATION, + GLOBAL_SCHEDULE_POLICY_RC_YIELD_RATIO, + }; + + __guc_scheduling_policy_add_klv(&policy, + GUC_SCHEDULING_POLICIES_KLV_ID_RENDER_COMPUTE_YIELD, + yield, ARRAY_SIZE(yield)); + + ret = __guc_action_set_scheduling_policies(guc, &policy); + if (ret) + i915_probe_error(gt->i915, + "Failed to configure global scheduling policies: %pe!\n", + ERR_PTR(ret)); + } + + return ret; +} + void intel_guc_submission_enable(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); @@ -4189,6 +4403,7 @@ void intel_guc_submission_enable(struct intel_guc *guc) guc_init_lrc_mapping(guc); guc_init_engine_stats(guc); + guc_init_global_schedule_policy(guc); } void intel_guc_submission_disable(struct intel_guc *guc) @@ -4219,6 +4434,26 @@ static bool __guc_submission_selected(struct intel_guc *guc) return i915->params.enable_guc & ENABLE_GUC_SUBMISSION; } +int intel_guc_sched_disable_gucid_threshold_max(struct intel_guc *guc) +{ + return guc->submission_state.num_guc_ids - NUMBER_MULTI_LRC_GUC_ID(guc); +} + +/* + * This default value of 33 milisecs (+1 milisec round up) ensures 30fps or higher + * workloads are able to enjoy the latency reduction when delaying the schedule-disable + * operation. This matches the 30fps game-render + encode (real world) workload this + * knob was tested against. + */ +#define SCHED_DISABLE_DELAY_MS 34 + +/* + * A threshold of 75% is a reasonable starting point considering that real world apps + * generally don't get anywhere near this. + */ +#define NUM_SCHED_DISABLE_GUCIDS_DEFAULT_THRESHOLD(__guc) \ + (((intel_guc_sched_disable_gucid_threshold_max(guc)) * 3) / 4) + void intel_guc_submission_init_early(struct intel_guc *guc) { xa_init_flags(&guc->context_lookup, XA_FLAGS_LOCK_IRQ); @@ -4235,7 +4470,10 @@ void intel_guc_submission_init_early(struct intel_guc *guc) spin_lock_init(&guc->timestamp.lock); INIT_DELAYED_WORK(&guc->timestamp.work, guc_timestamp_ping); + guc->submission_state.sched_disable_delay_ms = SCHED_DISABLE_DELAY_MS; guc->submission_state.num_guc_ids = GUC_MAX_CONTEXT_ID; + guc->submission_state.sched_disable_gucid_threshold = + NUM_SCHED_DISABLE_GUCIDS_DEFAULT_THRESHOLD(guc); guc->submission_supported = __guc_submission_supported(guc); guc->submission_selected = __guc_submission_selected(guc); } @@ -4669,7 +4907,7 @@ void intel_guc_submission_print_info(struct intel_guc *guc, drm_printf(p, "GuC Number Outstanding Submission G2H: %u\n", atomic_read(&guc->outstanding_submission_g2h)); - drm_printf(p, "GuC tasklet count: %u\n\n", + drm_printf(p, "GuC tasklet count: %u\n", atomic_read(&sched_engine->tasklet.count)); spin_lock_irqsave(&sched_engine->lock, flags); @@ -4717,7 +4955,7 @@ static inline void guc_log_context(struct drm_printer *p, atomic_read(&ce->pin_count)); drm_printf(p, "\t\tGuC ID Ref Count: %u\n", atomic_read(&ce->guc_id.ref)); - drm_printf(p, "\t\tSchedule State: 0x%x\n\n", + drm_printf(p, "\t\tSchedule State: 0x%x\n", ce->guc_state.sched_state); } @@ -4746,7 +4984,7 @@ void intel_guc_submission_print_context_info(struct intel_guc *guc, READ_ONCE(*ce->parallel.guc.wq_head)); drm_printf(p, "\t\tWQI Tail: %u\n", READ_ONCE(*ce->parallel.guc.wq_tail)); - drm_printf(p, "\t\tWQI Status: %u\n\n", + drm_printf(p, "\t\tWQI Status: %u\n", READ_ONCE(*ce->parallel.guc.wq_status)); } @@ -4754,7 +4992,7 @@ void intel_guc_submission_print_context_info(struct intel_guc *guc, emit_bb_start_parent_no_preempt_mid_batch) { u8 i; - drm_printf(p, "\t\tChildren Go: %u\n\n", + drm_printf(p, "\t\tChildren Go: %u\n", get_children_go_value(ce)); for (i = 0; i < ce->parallel.number_children; ++i) drm_printf(p, "\t\tChildren Join: %u\n", diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c index 3bb8838e325a..410905da8e97 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c @@ -10,6 +10,9 @@ #include "intel_huc.h" #include "i915_drv.h" +#include <linux/device/bus.h> +#include <linux/mei_aux.h> + /** * DOC: HuC * @@ -42,12 +45,240 @@ * HuC-specific commands. */ +/* + * MEI-GSC load is an async process. The probing of the exposed aux device + * (see intel_gsc.c) usually happens a few seconds after i915 probe, depending + * on when the kernel schedules it. Unless something goes terribly wrong, we're + * guaranteed for this to happen during boot, so the big timeout is a safety net + * that we never expect to need. + * MEI-PXP + HuC load usually takes ~300ms, but if the GSC needs to be resumed + * and/or reset, this can take longer. Note that the kernel might schedule + * other work between the i915 init/resume and the MEI one, which can add to + * the delay. + */ +#define GSC_INIT_TIMEOUT_MS 10000 +#define PXP_INIT_TIMEOUT_MS 5000 + +static int sw_fence_dummy_notify(struct i915_sw_fence *sf, + enum i915_sw_fence_notify state) +{ + return NOTIFY_DONE; +} + +static void __delayed_huc_load_complete(struct intel_huc *huc) +{ + if (!i915_sw_fence_done(&huc->delayed_load.fence)) + i915_sw_fence_complete(&huc->delayed_load.fence); +} + +static void delayed_huc_load_complete(struct intel_huc *huc) +{ + hrtimer_cancel(&huc->delayed_load.timer); + __delayed_huc_load_complete(huc); +} + +static void __gsc_init_error(struct intel_huc *huc) +{ + huc->delayed_load.status = INTEL_HUC_DELAYED_LOAD_ERROR; + __delayed_huc_load_complete(huc); +} + +static void gsc_init_error(struct intel_huc *huc) +{ + hrtimer_cancel(&huc->delayed_load.timer); + __gsc_init_error(huc); +} + +static void gsc_init_done(struct intel_huc *huc) +{ + hrtimer_cancel(&huc->delayed_load.timer); + + /* MEI-GSC init is done, now we wait for MEI-PXP to bind */ + huc->delayed_load.status = INTEL_HUC_WAITING_ON_PXP; + if (!i915_sw_fence_done(&huc->delayed_load.fence)) + hrtimer_start(&huc->delayed_load.timer, + ms_to_ktime(PXP_INIT_TIMEOUT_MS), + HRTIMER_MODE_REL); +} + +static enum hrtimer_restart huc_delayed_load_timer_callback(struct hrtimer *hrtimer) +{ + struct intel_huc *huc = container_of(hrtimer, struct intel_huc, delayed_load.timer); + + if (!intel_huc_is_authenticated(huc)) { + if (huc->delayed_load.status == INTEL_HUC_WAITING_ON_GSC) + drm_notice(&huc_to_gt(huc)->i915->drm, + "timed out waiting for MEI GSC init to load HuC\n"); + else if (huc->delayed_load.status == INTEL_HUC_WAITING_ON_PXP) + drm_notice(&huc_to_gt(huc)->i915->drm, + "timed out waiting for MEI PXP init to load HuC\n"); + else + MISSING_CASE(huc->delayed_load.status); + + __gsc_init_error(huc); + } + + return HRTIMER_NORESTART; +} + +static void huc_delayed_load_start(struct intel_huc *huc) +{ + ktime_t delay; + + GEM_BUG_ON(intel_huc_is_authenticated(huc)); + + /* + * On resume we don't have to wait for MEI-GSC to be re-probed, but we + * do need to wait for MEI-PXP to reset & re-bind + */ + switch (huc->delayed_load.status) { + case INTEL_HUC_WAITING_ON_GSC: + delay = ms_to_ktime(GSC_INIT_TIMEOUT_MS); + break; + case INTEL_HUC_WAITING_ON_PXP: + delay = ms_to_ktime(PXP_INIT_TIMEOUT_MS); + break; + default: + gsc_init_error(huc); + return; + } + + /* + * This fence is always complete unless we're waiting for the + * GSC device to come up to load the HuC. We arm the fence here + * and complete it when we confirm that the HuC is loaded from + * the PXP bind callback. + */ + GEM_BUG_ON(!i915_sw_fence_done(&huc->delayed_load.fence)); + i915_sw_fence_fini(&huc->delayed_load.fence); + i915_sw_fence_reinit(&huc->delayed_load.fence); + i915_sw_fence_await(&huc->delayed_load.fence); + i915_sw_fence_commit(&huc->delayed_load.fence); + + hrtimer_start(&huc->delayed_load.timer, delay, HRTIMER_MODE_REL); +} + +static int gsc_notifier(struct notifier_block *nb, unsigned long action, void *data) +{ + struct device *dev = data; + struct intel_huc *huc = container_of(nb, struct intel_huc, delayed_load.nb); + struct intel_gsc_intf *intf = &huc_to_gt(huc)->gsc.intf[0]; + + if (!intf->adev || &intf->adev->aux_dev.dev != dev) + return 0; + + switch (action) { + case BUS_NOTIFY_BOUND_DRIVER: /* mei driver bound to aux device */ + gsc_init_done(huc); + break; + + case BUS_NOTIFY_DRIVER_NOT_BOUND: /* mei driver fails to be bound */ + case BUS_NOTIFY_UNBIND_DRIVER: /* mei driver about to be unbound */ + drm_info(&huc_to_gt(huc)->i915->drm, + "mei driver not bound, disabling HuC load\n"); + gsc_init_error(huc); + break; + } + + return 0; +} + +void intel_huc_register_gsc_notifier(struct intel_huc *huc, struct bus_type *bus) +{ + int ret; + + if (!intel_huc_is_loaded_by_gsc(huc)) + return; + + huc->delayed_load.nb.notifier_call = gsc_notifier; + ret = bus_register_notifier(bus, &huc->delayed_load.nb); + if (ret) { + drm_err(&huc_to_gt(huc)->i915->drm, + "failed to register GSC notifier\n"); + huc->delayed_load.nb.notifier_call = NULL; + gsc_init_error(huc); + } +} + +void intel_huc_unregister_gsc_notifier(struct intel_huc *huc, struct bus_type *bus) +{ + if (!huc->delayed_load.nb.notifier_call) + return; + + delayed_huc_load_complete(huc); + + bus_unregister_notifier(bus, &huc->delayed_load.nb); + huc->delayed_load.nb.notifier_call = NULL; +} + +static void delayed_huc_load_init(struct intel_huc *huc) +{ + /* + * Initialize fence to be complete as this is expected to be complete + * unless there is a delayed HuC load in progress. + */ + i915_sw_fence_init(&huc->delayed_load.fence, + sw_fence_dummy_notify); + i915_sw_fence_commit(&huc->delayed_load.fence); + + hrtimer_init(&huc->delayed_load.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + huc->delayed_load.timer.function = huc_delayed_load_timer_callback; +} + +static void delayed_huc_load_fini(struct intel_huc *huc) +{ + /* + * the fence is initialized in init_early, so we need to clean it up + * even if HuC loading is off. + */ + delayed_huc_load_complete(huc); + i915_sw_fence_fini(&huc->delayed_load.fence); +} + +static bool vcs_supported(struct intel_gt *gt) +{ + intel_engine_mask_t mask = gt->info.engine_mask; + + /* + * We reach here from i915_driver_early_probe for the primary GT before + * its engine mask is set, so we use the device info engine mask for it; + * this means we're not taking VCS fusing into account, but if the + * primary GT supports VCS engines we expect at least one of them to + * remain unfused so we're fine. + * For other GTs we expect the GT-specific mask to be set before we + * call this function. + */ + GEM_BUG_ON(!gt_is_root(gt) && !gt->info.engine_mask); + + if (gt_is_root(gt)) + mask = RUNTIME_INFO(gt->i915)->platform_engine_mask; + else + mask = gt->info.engine_mask; + + return __ENGINE_INSTANCES_MASK(mask, VCS0, I915_MAX_VCS); +} + void intel_huc_init_early(struct intel_huc *huc) { struct drm_i915_private *i915 = huc_to_gt(huc)->i915; + struct intel_gt *gt = huc_to_gt(huc); intel_uc_fw_init_early(&huc->fw, INTEL_UC_FW_TYPE_HUC); + /* + * we always init the fence as already completed, even if HuC is not + * supported. This way we don't have to distinguish between HuC not + * supported/disabled or already loaded, and can focus on if the load + * is currently in progress (fence not complete) or not, which is what + * we care about for stalling userspace submissions. + */ + delayed_huc_load_init(huc); + + if (!vcs_supported(gt)) { + intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_NOT_SUPPORTED); + return; + } + if (GRAPHICS_VER(i915) >= 11) { huc->status.reg = GEN11_HUC_KERNEL_LOAD_INFO; huc->status.mask = HUC_LOAD_SUCCESSFUL; @@ -113,16 +344,59 @@ int intel_huc_init(struct intel_huc *huc) return 0; out: + intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_INIT_FAIL); drm_info(&i915->drm, "HuC init failed with %d\n", err); return err; } void intel_huc_fini(struct intel_huc *huc) { + /* + * the fence is initialized in init_early, so we need to clean it up + * even if HuC loading is off. + */ + delayed_huc_load_fini(huc); + + if (intel_uc_fw_is_loadable(&huc->fw)) + intel_uc_fw_fini(&huc->fw); +} + +void intel_huc_suspend(struct intel_huc *huc) +{ if (!intel_uc_fw_is_loadable(&huc->fw)) return; - intel_uc_fw_fini(&huc->fw); + /* + * in the unlikely case that we're suspending before the GSC has + * completed its loading sequence, just stop waiting. We'll restart + * on resume. + */ + delayed_huc_load_complete(huc); +} + +int intel_huc_wait_for_auth_complete(struct intel_huc *huc) +{ + struct intel_gt *gt = huc_to_gt(huc); + int ret; + + ret = __intel_wait_for_register(gt->uncore, + huc->status.reg, + huc->status.mask, + huc->status.value, + 2, 50, NULL); + + /* mark the load process as complete even if the wait failed */ + delayed_huc_load_complete(huc); + + if (ret) { + drm_err(>->i915->drm, "HuC: Firmware not verified %d\n", ret); + intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_LOAD_FAIL); + return ret; + } + + intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_RUNNING); + drm_info(>->i915->drm, "HuC authenticated\n"); + return 0; } /** @@ -161,27 +435,18 @@ int intel_huc_auth(struct intel_huc *huc) } /* Check authentication status, it should be done by now */ - ret = __intel_wait_for_register(gt->uncore, - huc->status.reg, - huc->status.mask, - huc->status.value, - 2, 50, NULL); - if (ret) { - DRM_ERROR("HuC: Firmware not verified %d\n", ret); + ret = intel_huc_wait_for_auth_complete(huc); + if (ret) goto fail; - } - intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_RUNNING); - drm_info(>->i915->drm, "HuC authenticated\n"); return 0; fail: i915_probe_error(gt->i915, "HuC: Authentication failed %d\n", ret); - intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_LOAD_FAIL); return ret; } -static bool huc_is_authenticated(struct intel_huc *huc) +bool intel_huc_is_authenticated(struct intel_huc *huc) { struct intel_gt *gt = huc_to_gt(huc); intel_wakeref_t wakeref; @@ -200,13 +465,8 @@ static bool huc_is_authenticated(struct intel_huc *huc) * This function reads status register to verify if HuC * firmware was successfully loaded. * - * Returns: - * * -ENODEV if HuC is not present on this platform, - * * -EOPNOTSUPP if HuC firmware is disabled, - * * -ENOPKG if HuC firmware was not installed, - * * -ENOEXEC if HuC firmware is invalid or mismatched, - * * 0 if HuC firmware is not running, - * * 1 if HuC firmware is authenticated and running. + * The return values match what is expected for the I915_PARAM_HUC_STATUS + * getparam. */ int intel_huc_check_status(struct intel_huc *huc) { @@ -219,11 +479,21 @@ int intel_huc_check_status(struct intel_huc *huc) return -ENOPKG; case INTEL_UC_FIRMWARE_ERROR: return -ENOEXEC; + case INTEL_UC_FIRMWARE_INIT_FAIL: + return -ENOMEM; + case INTEL_UC_FIRMWARE_LOAD_FAIL: + return -EIO; default: break; } - return huc_is_authenticated(huc); + return intel_huc_is_authenticated(huc); +} + +static bool huc_has_delayed_load(struct intel_huc *huc) +{ + return intel_huc_is_loaded_by_gsc(huc) && + (huc->delayed_load.status != INTEL_HUC_DELAYED_LOAD_ERROR); } void intel_huc_update_auth_status(struct intel_huc *huc) @@ -231,9 +501,11 @@ void intel_huc_update_auth_status(struct intel_huc *huc) if (!intel_uc_fw_is_loadable(&huc->fw)) return; - if (huc_is_authenticated(huc)) + if (intel_huc_is_authenticated(huc)) intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_RUNNING); + else if (huc_has_delayed_load(huc)) + huc_delayed_load_start(huc); } /** diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.h b/drivers/gpu/drm/i915/gt/uc/intel_huc.h index d7e25b6e879e..52db03620c60 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.h @@ -7,9 +7,21 @@ #define _INTEL_HUC_H_ #include "i915_reg_defs.h" +#include "i915_sw_fence.h" #include "intel_uc_fw.h" #include "intel_huc_fw.h" +#include <linux/notifier.h> +#include <linux/hrtimer.h> + +struct bus_type; + +enum intel_huc_delayed_load_status { + INTEL_HUC_WAITING_ON_GSC = 0, + INTEL_HUC_WAITING_ON_PXP, + INTEL_HUC_DELAYED_LOAD_ERROR, +}; + struct intel_huc { /* Generic uC firmware management */ struct intel_uc_fw fw; @@ -20,14 +32,27 @@ struct intel_huc { u32 mask; u32 value; } status; + + struct { + struct i915_sw_fence fence; + struct hrtimer timer; + struct notifier_block nb; + enum intel_huc_delayed_load_status status; + } delayed_load; }; void intel_huc_init_early(struct intel_huc *huc); int intel_huc_init(struct intel_huc *huc); void intel_huc_fini(struct intel_huc *huc); +void intel_huc_suspend(struct intel_huc *huc); int intel_huc_auth(struct intel_huc *huc); +int intel_huc_wait_for_auth_complete(struct intel_huc *huc); int intel_huc_check_status(struct intel_huc *huc); void intel_huc_update_auth_status(struct intel_huc *huc); +bool intel_huc_is_authenticated(struct intel_huc *huc); + +void intel_huc_register_gsc_notifier(struct intel_huc *huc, struct bus_type *bus); +void intel_huc_unregister_gsc_notifier(struct intel_huc *huc, struct bus_type *bus); static inline int intel_huc_sanitize(struct intel_huc *huc) { @@ -56,6 +81,12 @@ static inline bool intel_huc_is_loaded_by_gsc(const struct intel_huc *huc) return huc->fw.loaded_via_gsc; } +static inline bool intel_huc_wait_required(struct intel_huc *huc) +{ + return intel_huc_is_used(huc) && intel_huc_is_loaded_by_gsc(huc) && + !intel_huc_is_authenticated(huc); +} + void intel_huc_load_status(struct intel_huc *huc, struct drm_printer *p); #endif diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c index 9d6ab1e01639..4f246416db17 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c @@ -3,9 +3,43 @@ * Copyright © 2014-2019 Intel Corporation */ +#include "gt/intel_gsc.h" #include "gt/intel_gt.h" +#include "intel_huc.h" #include "intel_huc_fw.h" #include "i915_drv.h" +#include "pxp/intel_pxp_huc.h" + +int intel_huc_fw_load_and_auth_via_gsc(struct intel_huc *huc) +{ + int ret; + + if (!intel_huc_is_loaded_by_gsc(huc)) + return -ENODEV; + + if (!intel_uc_fw_is_loadable(&huc->fw)) + return -ENOEXEC; + + /* + * If we abort a suspend, HuC might still be loaded when the mei + * component gets re-bound and this function called again. If so, just + * mark the HuC as loaded. + */ + if (intel_huc_is_authenticated(huc)) { + intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_RUNNING); + return 0; + } + + GEM_WARN_ON(intel_uc_fw_is_loaded(&huc->fw)); + + ret = intel_pxp_huc_load_and_auth(&huc_to_gt(huc)->pxp); + if (ret) + return ret; + + intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_TRANSFERRED); + + return intel_huc_wait_for_auth_complete(huc); +} /** * intel_huc_fw_upload() - load HuC uCode to device via DMA transfer diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.h b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.h index 12f264ee3e0b..db42e238b45f 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.h @@ -8,6 +8,7 @@ struct intel_huc; +int intel_huc_fw_load_and_auth_via_gsc(struct intel_huc *huc); int intel_huc_fw_upload(struct intel_huc *huc); #endif diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c index dbd048b77e19..2a508b137e90 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c @@ -357,8 +357,8 @@ static int uc_init_wopcm(struct intel_uc *uc) { struct intel_gt *gt = uc_to_gt(uc); struct intel_uncore *uncore = gt->uncore; - u32 base = intel_wopcm_guc_base(>->i915->wopcm); - u32 size = intel_wopcm_guc_size(>->i915->wopcm); + u32 base = intel_wopcm_guc_base(>->wopcm); + u32 size = intel_wopcm_guc_size(>->wopcm); u32 huc_agent = intel_uc_uses_huc(uc) ? HUC_LOADING_AGENT_GUC : 0; u32 mask; int err; @@ -636,8 +636,10 @@ void intel_uc_runtime_suspend(struct intel_uc *uc) { struct intel_guc *guc = &uc->guc; - if (!intel_guc_is_ready(guc)) + if (!intel_guc_is_ready(guc)) { + guc->interrupts.enabled = false; return; + } /* * Wait for any outstanding CTB before tearing down communication /w the @@ -657,8 +659,10 @@ void intel_uc_suspend(struct intel_uc *uc) intel_wakeref_t wakeref; int err; - if (!intel_guc_is_ready(guc)) + if (!intel_guc_is_ready(guc)) { + guc->interrupts.enabled = false; return; + } with_intel_runtime_pm(&uc_to_gt(uc)->i915->runtime_pm, wakeref) { err = intel_guc_suspend(guc); @@ -718,6 +722,7 @@ int intel_uc_runtime_resume(struct intel_uc *uc) static const struct intel_uc_ops uc_ops_off = { .init_hw = __uc_check_hw, + .fini = __uc_fini, /* to clean-up the init_early initialization */ }; static const struct intel_uc_ops uc_ops_on = { diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c index b91ad4aede1f..2bcdd192f814 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c @@ -93,7 +93,8 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw, fw_def(BROXTON, 0, guc_mmp(bxt, 70, 1, 1)) \ fw_def(SKYLAKE, 0, guc_mmp(skl, 70, 1, 1)) -#define INTEL_HUC_FIRMWARE_DEFS(fw_def, huc_raw, huc_mmp) \ +#define INTEL_HUC_FIRMWARE_DEFS(fw_def, huc_raw, huc_mmp, huc_gsc) \ + fw_def(DG2, 0, huc_gsc(dg2)) \ fw_def(ALDERLAKE_P, 0, huc_raw(tgl)) \ fw_def(ALDERLAKE_P, 0, huc_mmp(tgl, 7, 9, 3)) \ fw_def(ALDERLAKE_S, 0, huc_raw(tgl)) \ @@ -141,6 +142,9 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw, #define MAKE_HUC_FW_PATH_BLANK(prefix_) \ __MAKE_UC_FW_PATH_BLANK(prefix_, "_huc") +#define MAKE_HUC_FW_PATH_GSC(prefix_) \ + __MAKE_UC_FW_PATH_BLANK(prefix_, "_huc_gsc") + #define MAKE_HUC_FW_PATH_MMP(prefix_, major_, minor_, patch_) \ __MAKE_UC_FW_PATH_MMP(prefix_, "_huc_", major_, minor_, patch_) @@ -153,7 +157,7 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw, MODULE_FIRMWARE(uc_); INTEL_GUC_FIRMWARE_DEFS(INTEL_UC_MODULE_FW, MAKE_GUC_FW_PATH_MAJOR, MAKE_GUC_FW_PATH_MMP) -INTEL_HUC_FIRMWARE_DEFS(INTEL_UC_MODULE_FW, MAKE_HUC_FW_PATH_BLANK, MAKE_HUC_FW_PATH_MMP) +INTEL_HUC_FIRMWARE_DEFS(INTEL_UC_MODULE_FW, MAKE_HUC_FW_PATH_BLANK, MAKE_HUC_FW_PATH_MMP, MAKE_HUC_FW_PATH_GSC) /* * The next expansion of the table macros (in __uc_fw_auto_select below) provides @@ -168,6 +172,7 @@ struct __packed uc_fw_blob { u8 major; u8 minor; u8 patch; + bool loaded_via_gsc; }; #define UC_FW_BLOB_BASE(major_, minor_, patch_, path_) \ @@ -176,16 +181,16 @@ struct __packed uc_fw_blob { .patch = patch_, \ .path = path_, -#define UC_FW_BLOB_NEW(major_, minor_, patch_, path_) \ +#define UC_FW_BLOB_NEW(major_, minor_, patch_, gsc_, path_) \ { UC_FW_BLOB_BASE(major_, minor_, patch_, path_) \ - .legacy = false } + .legacy = false, .loaded_via_gsc = gsc_ } #define UC_FW_BLOB_OLD(major_, minor_, patch_, path_) \ { UC_FW_BLOB_BASE(major_, minor_, patch_, path_) \ .legacy = true } #define GUC_FW_BLOB(prefix_, major_, minor_) \ - UC_FW_BLOB_NEW(major_, minor_, 0, \ + UC_FW_BLOB_NEW(major_, minor_, 0, false, \ MAKE_GUC_FW_PATH_MAJOR(prefix_, major_, minor_)) #define GUC_FW_BLOB_MMP(prefix_, major_, minor_, patch_) \ @@ -193,12 +198,15 @@ struct __packed uc_fw_blob { MAKE_GUC_FW_PATH_MMP(prefix_, major_, minor_, patch_)) #define HUC_FW_BLOB(prefix_) \ - UC_FW_BLOB_NEW(0, 0, 0, MAKE_HUC_FW_PATH_BLANK(prefix_)) + UC_FW_BLOB_NEW(0, 0, 0, false, MAKE_HUC_FW_PATH_BLANK(prefix_)) #define HUC_FW_BLOB_MMP(prefix_, major_, minor_, patch_) \ UC_FW_BLOB_OLD(major_, minor_, patch_, \ MAKE_HUC_FW_PATH_MMP(prefix_, major_, minor_, patch_)) +#define HUC_FW_BLOB_GSC(prefix_) \ + UC_FW_BLOB_NEW(0, 0, 0, true, MAKE_HUC_FW_PATH_GSC(prefix_)) + struct __packed uc_fw_platform_requirement { enum intel_platform p; u8 rev; /* first platform rev using this FW */ @@ -224,7 +232,7 @@ __uc_fw_auto_select(struct drm_i915_private *i915, struct intel_uc_fw *uc_fw) INTEL_GUC_FIRMWARE_DEFS(MAKE_FW_LIST, GUC_FW_BLOB, GUC_FW_BLOB_MMP) }; static const struct uc_fw_platform_requirement blobs_huc[] = { - INTEL_HUC_FIRMWARE_DEFS(MAKE_FW_LIST, HUC_FW_BLOB, HUC_FW_BLOB_MMP) + INTEL_HUC_FIRMWARE_DEFS(MAKE_FW_LIST, HUC_FW_BLOB, HUC_FW_BLOB_MMP, HUC_FW_BLOB_GSC) }; static const struct fw_blobs_by_type blobs_all[INTEL_UC_FW_NUM_TYPES] = { [INTEL_UC_FW_TYPE_GUC] = { blobs_guc, ARRAY_SIZE(blobs_guc) }, @@ -272,6 +280,7 @@ __uc_fw_auto_select(struct drm_i915_private *i915, struct intel_uc_fw *uc_fw) uc_fw->file_wanted.path = blob->path; uc_fw->file_wanted.major_ver = blob->major; uc_fw->file_wanted.minor_ver = blob->minor; + uc_fw->loaded_via_gsc = blob->loaded_via_gsc; found = true; break; } @@ -469,10 +478,11 @@ static int check_gsc_manifest(const struct firmware *fw, return 0; } -static int check_ccs_header(struct drm_i915_private *i915, +static int check_ccs_header(struct intel_gt *gt, const struct firmware *fw, struct intel_uc_fw *uc_fw) { + struct drm_i915_private *i915 = gt->i915; struct uc_css_header *css; size_t size; @@ -514,10 +524,10 @@ static int check_ccs_header(struct drm_i915_private *i915, /* Sanity check whether this fw is not larger than whole WOPCM memory */ size = __intel_uc_fw_get_upload_size(uc_fw); - if (unlikely(size >= i915->wopcm.size)) { + if (unlikely(size >= gt->wopcm.size)) { drm_warn(&i915->drm, "%s firmware %s: invalid size: %zu > %zu\n", intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path, - size, (size_t)i915->wopcm.size); + size, (size_t)gt->wopcm.size); return -E2BIG; } @@ -535,6 +545,32 @@ static int check_ccs_header(struct drm_i915_private *i915, return 0; } +static int try_firmware_load(struct intel_uc_fw *uc_fw, const struct firmware **fw) +{ + struct intel_gt *gt = __uc_fw_to_gt(uc_fw); + struct device *dev = gt->i915->drm.dev; + int err; + + err = firmware_request_nowarn(fw, uc_fw->file_selected.path, dev); + + if (err) + return err; + + if ((*fw)->size > INTEL_UC_RSVD_GGTT_PER_FW) { + drm_err(>->i915->drm, + "%s firmware %s: size (%zuKB) exceeds max supported size (%uKB)\n", + intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path, + (*fw)->size / SZ_1K, INTEL_UC_RSVD_GGTT_PER_FW / SZ_1K); + + /* try to find another blob to load */ + release_firmware(*fw); + *fw = NULL; + return -ENOENT; + } + + return 0; +} + /** * intel_uc_fw_fetch - fetch uC firmware * @uc_fw: uC firmware @@ -545,15 +581,15 @@ static int check_ccs_header(struct drm_i915_private *i915, */ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) { - struct drm_i915_private *i915 = __uc_fw_to_gt(uc_fw)->i915; + struct intel_gt *gt = __uc_fw_to_gt(uc_fw); + struct drm_i915_private *i915 = gt->i915; struct intel_uc_fw_file file_ideal; - struct device *dev = i915->drm.dev; struct drm_i915_gem_object *obj; const struct firmware *fw = NULL; bool old_ver = false; int err; - GEM_BUG_ON(!i915->wopcm.size); + GEM_BUG_ON(!gt->wopcm.size); GEM_BUG_ON(!intel_uc_fw_is_enabled(uc_fw)); err = i915_inject_probe_error(i915, -ENXIO); @@ -563,7 +599,7 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) __force_fw_fetch_failures(uc_fw, -EINVAL); __force_fw_fetch_failures(uc_fw, -ESTALE); - err = firmware_request_nowarn(&fw, uc_fw->file_selected.path, dev); + err = try_firmware_load(uc_fw, &fw); memcpy(&file_ideal, &uc_fw->file_wanted, sizeof(file_ideal)); /* Any error is terminal if overriding. Don't bother searching for older versions */ @@ -586,7 +622,7 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) break; } - err = firmware_request_nowarn(&fw, uc_fw->file_selected.path, dev); + err = try_firmware_load(uc_fw, &fw); } if (err) @@ -595,7 +631,7 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) if (uc_fw->loaded_via_gsc) err = check_gsc_manifest(fw, uc_fw); else - err = check_ccs_header(i915, fw, uc_fw); + err = check_ccs_header(gt, fw, uc_fw); if (err) goto fail; @@ -668,14 +704,30 @@ fail: static u32 uc_fw_ggtt_offset(struct intel_uc_fw *uc_fw) { - struct i915_ggtt *ggtt = __uc_fw_to_gt(uc_fw)->ggtt; + struct intel_gt *gt = __uc_fw_to_gt(uc_fw); + struct i915_ggtt *ggtt = gt->ggtt; struct drm_mm_node *node = &ggtt->uc_fw; + u32 offset = uc_fw->type * INTEL_UC_RSVD_GGTT_PER_FW; + + /* + * The media GT shares the GGTT with the root GT, which means that + * we need to use different offsets for the binaries on the media GT. + * To keep the math simple, we use 8MB for the root tile and 8MB for + * the media one. This will need to be updated if we ever have more + * than 1 media GT. + */ + BUILD_BUG_ON(INTEL_UC_FW_NUM_TYPES * INTEL_UC_RSVD_GGTT_PER_FW > SZ_8M); + GEM_BUG_ON(gt->type == GT_MEDIA && gt->info.id > 1); + if (gt->type == GT_MEDIA) + offset += SZ_8M; GEM_BUG_ON(!drm_mm_node_allocated(node)); GEM_BUG_ON(upper_32_bits(node->start)); GEM_BUG_ON(upper_32_bits(node->start + node->size - 1)); + GEM_BUG_ON(offset + uc_fw->obj->base.size > node->size); + GEM_BUG_ON(uc_fw->obj->base.size > INTEL_UC_RSVD_GGTT_PER_FW); - return lower_32_bits(node->start); + return lower_32_bits(node->start + offset); } static void uc_fw_bind_ggtt(struct intel_uc_fw *uc_fw) @@ -690,7 +742,6 @@ static void uc_fw_bind_ggtt(struct intel_uc_fw *uc_fw) dummy->bi.pages = obj->mm.pages; GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj)); - GEM_BUG_ON(dummy->node_size > ggtt->uc_fw.size); /* uc_fw->obj cache domains were not controlled across suspend */ if (i915_gem_object_has_struct_page(obj)) @@ -904,7 +955,6 @@ int intel_uc_fw_init(struct intel_uc_fw *uc_fw) out_unpin: i915_gem_object_unpin_pages(uc_fw->obj); out: - intel_uc_fw_change_status(uc_fw, INTEL_UC_FIRMWARE_INIT_FAIL); return err; } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h index cb586f7df270..bc898ba5355d 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h @@ -6,6 +6,7 @@ #ifndef _INTEL_UC_FW_H_ #define _INTEL_UC_FW_H_ +#include <linux/sizes.h> #include <linux/types.h> #include "intel_uc_fw_abi.h" #include "intel_device_info.h" @@ -114,6 +115,19 @@ struct intel_uc_fw { (uc)->fw.file_selected.minor_ver, \ (uc)->fw.file_selected.patch_ver)) +/* + * When we load the uC binaries, we pin them in a reserved section at the top of + * the GGTT, which is ~18 MBs. On multi-GT systems where the GTs share the GGTT, + * we also need to make sure that each binary is pinned to a unique location + * during load, because the different GT can go through the FW load at the same + * time (see uc_fw_ggtt_offset() for details). + * Given that the available space is much greater than what is required by the + * binaries, to keep things simple instead of dynamically partitioning the + * reserved section to make space for all the blobs we can just reserve a static + * chunk for each binary. + */ +#define INTEL_UC_RSVD_GGTT_PER_FW SZ_2M + #ifdef CONFIG_DRM_I915_DEBUG_GUC void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw, enum intel_uc_fw_status status); diff --git a/drivers/gpu/drm/i915/gt/uc/selftest_guc_hangcheck.c b/drivers/gpu/drm/i915/gt/uc/selftest_guc_hangcheck.c index 01f8cd3c3134..d91b58f70403 100644 --- a/drivers/gpu/drm/i915/gt/uc/selftest_guc_hangcheck.c +++ b/drivers/gpu/drm/i915/gt/uc/selftest_guc_hangcheck.c @@ -35,11 +35,14 @@ static int intel_hang_guc(void *arg) struct i915_request *rq; intel_wakeref_t wakeref; struct i915_gpu_error *global = >->i915->gpu_error; - struct intel_engine_cs *engine; + struct intel_engine_cs *engine = intel_selftest_find_any_engine(gt); unsigned int reset_count; u32 guc_status; u32 old_beat; + if (!engine) + return 0; + ctx = kernel_context(gt->i915, NULL); if (IS_ERR(ctx)) { drm_err(>->i915->drm, "Failed get kernel context: %ld\n", PTR_ERR(ctx)); @@ -48,14 +51,13 @@ static int intel_hang_guc(void *arg) wakeref = intel_runtime_pm_get(gt->uncore->rpm); - ce = intel_context_create(gt->engine[BCS0]); + ce = intel_context_create(engine); if (IS_ERR(ce)) { ret = PTR_ERR(ce); drm_err(>->i915->drm, "Failed to create spinner request: %d\n", ret); goto err; } - engine = ce->engine; reset_count = i915_reset_count(global); old_beat = engine->props.heartbeat_interval_ms; diff --git a/drivers/gpu/drm/i915/gvt/cfg_space.c b/drivers/gpu/drm/i915/gvt/cfg_space.c index eef3bba8a41b..9bafac1eaf48 100644 --- a/drivers/gpu/drm/i915/gvt/cfg_space.c +++ b/drivers/gpu/drm/i915/gvt/cfg_space.c @@ -244,7 +244,7 @@ static void emulate_pci_bar_write(struct intel_vgpu *vgpu, unsigned int offset, } /** - * intel_vgpu_emulate_cfg_read - emulate vGPU configuration space write + * intel_vgpu_emulate_cfg_write - emulate vGPU configuration space write * @vgpu: target vgpu * @offset: offset * @p_data: write data ptr @@ -354,9 +354,9 @@ void intel_vgpu_init_cfg_space(struct intel_vgpu *vgpu, memset(vgpu_cfg_space(vgpu) + INTEL_GVT_PCI_OPREGION, 0, 4); vgpu->cfg_space.bar[INTEL_GVT_PCI_BAR_GTTMMIO].size = - pci_resource_len(pdev, GTTMMADR_BAR); + pci_resource_len(pdev, GEN4_GTTMMADR_BAR); vgpu->cfg_space.bar[INTEL_GVT_PCI_BAR_APERTURE].size = - pci_resource_len(pdev, GTT_APERTURE_BAR); + pci_resource_len(pdev, GEN4_GMADR_BAR); memset(vgpu_cfg_space(vgpu) + PCI_ROM_ADDRESS, 0, 4); diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index de13f102d4fd..0ebf5fbf0e39 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -37,6 +37,7 @@ #include <linux/slab.h> #include "i915_drv.h" +#include "i915_reg.h" #include "gt/intel_engine_regs.h" #include "gt/intel_gpu_commands.h" #include "gt/intel_gt_regs.h" diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c index c7722c818b4d..c033249e73f4 100644 --- a/drivers/gpu/drm/i915/gvt/display.c +++ b/drivers/gpu/drm/i915/gvt/display.c @@ -36,6 +36,8 @@ #include "i915_reg.h" #include "gvt.h" +#include "display/intel_dpio_phy.h" + static int get_edp_pipe(struct intel_vgpu *vgpu) { u32 data = vgpu_vreg(vgpu, _TRANS_DDI_FUNC_CTL_EDP); diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c index 01e54b45c5c1..355f1c0e8664 100644 --- a/drivers/gpu/drm/i915/gvt/dmabuf.c +++ b/drivers/gpu/drm/i915/gvt/dmabuf.c @@ -88,7 +88,7 @@ static int vgpu_gem_get_pages( sg_dma_address(sg) = dma_addr; } - __i915_gem_object_set_pages(obj, st, PAGE_SIZE); + __i915_gem_object_set_pages(obj, st); out: if (ret) { dma_addr_t dma_addr; diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.h b/drivers/gpu/drm/i915/gvt/dmabuf.h index 5f8f03fb1d1b..3dcdb6570eda 100644 --- a/drivers/gpu/drm/i915/gvt/dmabuf.h +++ b/drivers/gpu/drm/i915/gvt/dmabuf.h @@ -48,7 +48,7 @@ struct intel_vgpu_fb_info { struct intel_vgpu_dmabuf_obj *obj; }; -/** +/* * struct intel_vgpu_dmabuf_obj- Intel vGPU device buffer object */ struct intel_vgpu_dmabuf_obj { diff --git a/drivers/gpu/drm/i915/gvt/firmware.c b/drivers/gpu/drm/i915/gvt/firmware.c index 54fe442238c6..a683c22d5b64 100644 --- a/drivers/gpu/drm/i915/gvt/firmware.c +++ b/drivers/gpu/drm/i915/gvt/firmware.c @@ -104,7 +104,7 @@ static int expose_firmware_sysfs(struct intel_gvt *gvt) memcpy(p, gvt->firmware.mmio, info->mmio_size); - crc32_start = offsetof(struct gvt_firmware_header, crc32) + 4; + crc32_start = offsetof(struct gvt_firmware_header, version); h->crc32 = crc32_le(0, firmware + crc32_start, size - crc32_start); firmware_attr.size = size; diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index ce0eb03709c3..51e5e8fb505b 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -282,11 +282,6 @@ static inline int get_next_pt_type(int type) return gtt_type_table[type].next_pt_type; } -static inline int get_pt_type(int type) -{ - return gtt_type_table[type].pt_type; -} - static inline int get_entry_type(int type) { return gtt_type_table[type].entry_type; @@ -2785,7 +2780,7 @@ int intel_gvt_init_gtt(struct intel_gvt *gvt) * intel_gvt_clean_gtt - clean up mm components of a GVT device * @gvt: GVT device * - * This function is called at the driver unloading stage, to clean up the + * This function is called at the driver unloading stage, to clean up * the mm components of a GVT device. * */ diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index dbf8d7470b2c..62823c0e13ab 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -227,8 +227,6 @@ struct intel_vgpu { unsigned long nr_cache_entries; struct mutex cache_lock; - atomic_t released; - struct kvm_page_track_notifier_node track_node; #define NR_BKT (1 << 18) struct hlist_head ptable[NR_BKT]; diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index daac2050d77d..735fc83e7026 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -43,6 +43,7 @@ #include "intel_mchbar_regs.h" #include "display/intel_display_types.h" #include "display/intel_dmc_regs.h" +#include "display/intel_dpio_phy.h" #include "display/intel_fbc.h" #include "display/vlv_dsi_pll_regs.h" #include "gt/intel_gt_regs.h" @@ -734,7 +735,7 @@ static i915_reg_t force_nonpriv_white_list[] = { _MMIO(0x770c), _MMIO(0x83a8), _MMIO(0xb110), - GEN8_L3SQCREG4,//_MMIO(0xb118) + _MMIO(0xb118), _MMIO(0xe100), _MMIO(0xe18c), _MMIO(0xe48c), @@ -2257,7 +2258,7 @@ static int init_generic_mmio_info(struct intel_gvt *gvt) MMIO_DFH(_MMIO(0x2438), D_ALL, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(_MMIO(0x243c), D_ALL, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(_MMIO(0x7018), D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); - MMIO_DFH(HALF_SLICE_CHICKEN3, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(HSW_HALF_SLICE_CHICKEN3, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); MMIO_DFH(GEN7_HALF_SLICE_CHICKEN1, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); /* display */ diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 714221f9a131..f5451adcd489 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -669,9 +669,6 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev) vgpu->attached = true; - kvmgt_protect_table_init(vgpu); - gvt_cache_init(vgpu); - vgpu->track_node.track_write = kvmgt_page_track_write; vgpu->track_node.track_flush_slot = kvmgt_page_track_flush_slot; kvm_get_kvm(vgpu->vfio_device.kvm); @@ -683,7 +680,6 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev) intel_gvt_activate_vgpu(vgpu); - atomic_set(&vgpu->released, 0); return 0; } @@ -705,9 +701,6 @@ static void intel_vgpu_close_device(struct vfio_device *vfio_dev) if (!vgpu->attached) return; - if (atomic_cmpxchg(&vgpu->released, 0, 1)) - return; - intel_gvt_release_vgpu(vgpu); debugfs_remove(debugfs_lookup(KVMGT_DEBUGFS_FILENAME, vgpu->debugfs)); @@ -719,6 +712,11 @@ static void intel_vgpu_close_device(struct vfio_device *vfio_dev) kvmgt_protect_table_destroy(vgpu); gvt_cache_destroy(vgpu); + WARN_ON(vgpu->nr_cache_entries); + + vgpu->gfn_cache = RB_ROOT; + vgpu->dma_addr_cache = RB_ROOT; + intel_vgpu_release_msi_eventfd_ctx(vgpu); vgpu->attached = false; @@ -1449,9 +1447,17 @@ static int intel_vgpu_init_dev(struct vfio_device *vfio_dev) struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev); struct intel_vgpu_type *type = container_of(mdev->type, struct intel_vgpu_type, type); + int ret; vgpu->gvt = kdev_to_i915(mdev->type->parent->dev)->gvt; - return intel_gvt_create_vgpu(vgpu, type->conf); + ret = intel_gvt_create_vgpu(vgpu, type->conf); + if (ret) + return ret; + + kvmgt_protect_table_init(vgpu); + gvt_cache_init(vgpu); + + return 0; } static void intel_vgpu_release_dev(struct vfio_device *vfio_dev) @@ -1459,7 +1465,6 @@ static void intel_vgpu_release_dev(struct vfio_device *vfio_dev) struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev); intel_gvt_destroy_vgpu(vgpu); - vfio_free_device(vfio_dev); } static const struct vfio_device_ops intel_vgpu_dev_ops = { @@ -1472,6 +1477,9 @@ static const struct vfio_device_ops intel_vgpu_dev_ops = { .mmap = intel_vgpu_mmap, .ioctl = intel_vgpu_ioctl, .dma_unmap = intel_vgpu_dma_unmap, + .bind_iommufd = vfio_iommufd_emulated_bind, + .unbind_iommufd = vfio_iommufd_emulated_unbind, + .attach_ioas = vfio_iommufd_emulated_attach_ioas, }; static int intel_vgpu_probe(struct mdev_device *mdev) diff --git a/drivers/gpu/drm/i915/gvt/mmio.c b/drivers/gpu/drm/i915/gvt/mmio.c index 9acc00505fde..5b5def6ddef7 100644 --- a/drivers/gpu/drm/i915/gvt/mmio.c +++ b/drivers/gpu/drm/i915/gvt/mmio.c @@ -37,6 +37,7 @@ #include "i915_reg.h" #include "gvt.h" +#include "display/intel_dpio_phy.h" #include "gt/intel_gt_regs.h" /** diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index 1c6e941c9666..490e8ae51228 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -34,6 +34,7 @@ */ #include "i915_drv.h" +#include "i915_reg.h" #include "gt/intel_context.h" #include "gt/intel_engine_regs.h" #include "gt/intel_gpu_commands.h" @@ -106,15 +107,15 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = { {RCS0, GEN8_CS_CHICKEN1, 0xffff, true}, /* 0x2580 */ {RCS0, COMMON_SLICE_CHICKEN2, 0xffff, true}, /* 0x7014 */ {RCS0, GEN9_CS_DEBUG_MODE1, 0xffff, false}, /* 0x20ec */ - {RCS0, GEN8_L3SQCREG4, 0, false}, /* 0xb118 */ - {RCS0, GEN9_SCRATCH1, 0, false}, /* 0xb11c */ + {RCS0, _MMIO(0xb118), 0, false}, /* GEN8_L3SQCREG4 */ + {RCS0, _MMIO(0xb11c), 0, false}, /* GEN9_SCRATCH1 */ {RCS0, GEN9_SCRATCH_LNCF1, 0, false}, /* 0xb008 */ {RCS0, GEN7_HALF_SLICE_CHICKEN1, 0xffff, true}, /* 0xe100 */ - {RCS0, HALF_SLICE_CHICKEN2, 0xffff, true}, /* 0xe180 */ - {RCS0, HALF_SLICE_CHICKEN3, 0xffff, true}, /* 0xe184 */ - {RCS0, GEN9_HALF_SLICE_CHICKEN5, 0xffff, true}, /* 0xe188 */ - {RCS0, GEN9_HALF_SLICE_CHICKEN7, 0xffff, true}, /* 0xe194 */ - {RCS0, GEN8_ROW_CHICKEN, 0xffff, true}, /* 0xe4f0 */ + {RCS0, _MMIO(0xe180), 0xffff, true}, /* HALF_SLICE_CHICKEN2 */ + {RCS0, _MMIO(0xe184), 0xffff, true}, /* GEN8_HALF_SLICE_CHICKEN3 */ + {RCS0, _MMIO(0xe188), 0xffff, true}, /* GEN9_HALF_SLICE_CHICKEN5 */ + {RCS0, _MMIO(0xe194), 0xffff, true}, /* GEN9_HALF_SLICE_CHICKEN7 */ + {RCS0, _MMIO(0xe4f0), 0xffff, true}, /* GEN8_ROW_CHICKEN */ {RCS0, TRVATTL3PTRDW(0), 0, true}, /* 0x4de0 */ {RCS0, TRVATTL3PTRDW(1), 0, true}, /* 0x4de4 */ {RCS0, TRNULLDETCT, 0, true}, /* 0x4de8 */ diff --git a/drivers/gpu/drm/i915/gvt/page_track.c b/drivers/gpu/drm/i915/gvt/page_track.c index 3375b51c75f1..df34e73cba41 100644 --- a/drivers/gpu/drm/i915/gvt/page_track.c +++ b/drivers/gpu/drm/i915/gvt/page_track.c @@ -120,7 +120,7 @@ int intel_vgpu_enable_page_track(struct intel_vgpu *vgpu, unsigned long gfn) } /** - * intel_vgpu_enable_page_track - cancel write-protection on guest page + * intel_vgpu_disable_page_track - cancel write-protection on guest page * @vgpu: a vGPU * @gfn: the gfn of guest page * diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index d6fe94cd0fdb..9cd8fcbf7cad 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -570,9 +570,8 @@ retry: if (gmadr_bytes == 8) bb->bb_start_cmd_va[2] = 0; - ret = i915_vma_move_to_active(bb->vma, - workload->req, - 0); + ret = i915_vma_move_to_active(bb->vma, workload->req, + __EXEC_OBJECT_NO_REQUEST_AWAIT); if (ret) goto err; diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 56c71474008a..3c529c2705dd 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -158,7 +158,7 @@ void intel_gvt_clean_vgpu_types(struct intel_gvt *gvt) } /** - * intel_gvt_active_vgpu - activate a virtual GPU + * intel_gvt_activate_vgpu - activate a virtual GPU * @vgpu: virtual GPU * * This function is called when user wants to activate a virtual GPU. @@ -172,7 +172,7 @@ void intel_gvt_activate_vgpu(struct intel_vgpu *vgpu) } /** - * intel_gvt_deactive_vgpu - deactivate a virtual GPU + * intel_gvt_deactivate_vgpu - deactivate a virtual GPU * @vgpu: virtual GPU * * This function is called when user wants to deactivate a virtual GPU. @@ -295,7 +295,7 @@ out_free_vgpu: } /** - * intel_gvt_destroy_vgpu - destroy an idle virtual GPU + * intel_gvt_destroy_idle_vgpu - destroy an idle virtual GPU * @vgpu: virtual GPU * * This function is called when user wants to destroy an idle virtual GPU. diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index ae987e92251d..6c7ac73b69a5 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -688,8 +688,8 @@ i915_drop_caches_set(void *data, u64 val) unsigned int flags; int ret; - DRM_DEBUG("Dropping caches: 0x%08llx [0x%08llx]\n", - val, val & DROP_ALL); + drm_dbg(&i915->drm, "Dropping caches: 0x%08llx [0x%08llx]\n", + val, val & DROP_ALL); ret = gt_drop_caches(to_gt(i915), val); if (ret) diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c index f2a15d8155f4..69103ae37779 100644 --- a/drivers/gpu/drm/i915/i915_driver.c +++ b/drivers/gpu/drm/i915/i915_driver.c @@ -81,6 +81,7 @@ #include "i915_drm_client.h" #include "i915_drv.h" #include "i915_getparam.h" +#include "i915_hwmon.h" #include "i915_ioc32.h" #include "i915_ioctl.h" #include "i915_irq.h" @@ -337,7 +338,8 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv) if (i915_inject_probe_failure(dev_priv)) return -ENODEV; - intel_device_info_subplatform_init(dev_priv); + intel_device_info_runtime_init_early(dev_priv); + intel_step_init(dev_priv); intel_uncore_mmio_debug_init_early(dev_priv); @@ -370,8 +372,6 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv) if (ret) goto err_ttm; - intel_wopcm_init_early(&dev_priv->wopcm); - ret = intel_root_gt_init_early(dev_priv); if (ret < 0) goto err_rootgt; @@ -739,7 +739,6 @@ static void i915_driver_hw_remove(struct drm_i915_private *dev_priv) */ static void i915_driver_register(struct drm_i915_private *dev_priv) { - struct drm_device *dev = &dev_priv->drm; struct intel_gt *gt; unsigned int i; @@ -749,7 +748,7 @@ static void i915_driver_register(struct drm_i915_private *dev_priv) intel_vgpu_register(dev_priv); /* Reveal our presence to userspace */ - if (drm_dev_register(dev, 0)) { + if (drm_dev_register(&dev_priv->drm, 0)) { drm_err(&dev_priv->drm, "Failed to register driver for userspace access!\n"); return; @@ -764,6 +763,8 @@ static void i915_driver_register(struct drm_i915_private *dev_priv) for_each_gt(gt, dev_priv, i) intel_gt_driver_register(gt); + i915_hwmon_register(dev_priv); + intel_display_driver_register(dev_priv); intel_power_domains_enable(dev_priv); @@ -796,6 +797,8 @@ static void i915_driver_unregister(struct drm_i915_private *dev_priv) for_each_gt(gt, dev_priv, i) intel_gt_driver_unregister(gt); + i915_hwmon_unregister(dev_priv); + i915_perf_unregister(dev_priv); i915_pmu_unregister(dev_priv); @@ -894,10 +897,6 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (IS_ERR(i915)) return PTR_ERR(i915); - /* Disable nuclear pageflip by default on pre-ILK */ - if (!i915->params.nuclear_pageflip && DISPLAY_VER(i915) < 5) - i915->drm.driver_features &= ~DRIVER_ATOMIC; - ret = pci_enable_device(pdev); if (ret) goto out_fini; @@ -1093,32 +1092,30 @@ static void i915_driver_postclose(struct drm_device *dev, struct drm_file *file) static void intel_suspend_encoders(struct drm_i915_private *dev_priv) { - struct drm_device *dev = &dev_priv->drm; struct intel_encoder *encoder; if (!HAS_DISPLAY(dev_priv)) return; - drm_modeset_lock_all(dev); - for_each_intel_encoder(dev, encoder) + drm_modeset_lock_all(&dev_priv->drm); + for_each_intel_encoder(&dev_priv->drm, encoder) if (encoder->suspend) encoder->suspend(encoder); - drm_modeset_unlock_all(dev); + drm_modeset_unlock_all(&dev_priv->drm); } static void intel_shutdown_encoders(struct drm_i915_private *dev_priv) { - struct drm_device *dev = &dev_priv->drm; struct intel_encoder *encoder; if (!HAS_DISPLAY(dev_priv)) return; - drm_modeset_lock_all(dev); - for_each_intel_encoder(dev, encoder) + drm_modeset_lock_all(&dev_priv->drm); + for_each_intel_encoder(&dev_priv->drm, encoder) if (encoder->shutdown) encoder->shutdown(encoder); - drm_modeset_unlock_all(dev); + drm_modeset_unlock_all(&dev_priv->drm); } void i915_driver_shutdown(struct drm_i915_private *i915) @@ -1662,7 +1659,8 @@ static int intel_runtime_suspend(struct device *kdev) intel_runtime_pm_enable_interrupts(dev_priv); - intel_gt_runtime_resume(to_gt(dev_priv)); + for_each_gt(gt, dev_priv, i) + intel_gt_runtime_resume(gt); enable_rpm_wakeref_asserts(rpm); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index bdc81db76dbd..a380db36d52c 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -40,7 +40,6 @@ #include "display/intel_display_core.h" #include "gem/i915_gem_context_types.h" -#include "gem/i915_gem_lmem.h" #include "gem/i915_gem_shrinker.h" #include "gem/i915_gem_stolen.h" @@ -63,7 +62,6 @@ #include "intel_runtime_pm.h" #include "intel_step.h" #include "intel_uncore.h" -#include "intel_wopcm.h" struct drm_i915_clock_gating_funcs; struct drm_i915_gem_object; @@ -75,9 +73,6 @@ struct intel_limit; struct intel_overlay_error_state; struct vlv_s0ix_state; -/* Threshold == 5 for long IRQs, 50 for short */ -#define HPD_STORM_DEFAULT_THRESHOLD 50 - #define I915_GEM_GPU_DOMAINS \ (I915_GEM_DOMAIN_RENDER | \ I915_GEM_DOMAIN_SAMPLER | \ @@ -239,8 +234,6 @@ struct drm_i915_private { struct intel_gvt *gvt; - struct intel_wopcm wopcm; - struct pci_dev *bridge_dev; struct rb_root uabi_engines; @@ -291,28 +284,13 @@ struct drm_i915_private { unsigned long gem_quirks; - struct drm_atomic_state *modeset_restore_state; - struct drm_modeset_acquire_ctx reset_ctx; - struct i915_gem_mm mm; - /* Kernel Modesetting */ - - struct list_head global_obj_list; - bool mchbar_need_disable; struct intel_l3_parity l3_parity; /* - * HTI (aka HDPORT) state read during initial hw readout. Most - * platforms don't have HTI, so this will just stay 0. Those that do - * will use this later to figure out which PLLs and PHYs are unavailable - * for driver usage. - */ - u32 hti_state; - - /* * edram size in MB. * Cannot be determined by PCIID. You must always read a register. */ @@ -353,6 +331,8 @@ struct drm_i915_private { struct i915_perf perf; + struct i915_hwmon *hwmon; + /* Abstract the submission mechanism (legacy ringbuffer or execlists) away */ struct intel_gt gt0; @@ -742,6 +722,10 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define IS_XEHPSDV_GRAPHICS_STEP(__i915, since, until) \ (IS_XEHPSDV(__i915) && IS_GRAPHICS_STEP(__i915, since, until)) +#define IS_MTL_GRAPHICS_STEP(__i915, variant, since, until) \ + (IS_SUBPLATFORM(__i915, INTEL_METEORLAKE, INTEL_SUBPLATFORM_##variant) && \ + IS_GRAPHICS_STEP(__i915, since, until)) + /* * DG2 hardware steppings are a bit unusual. The hardware design was forked to * create three variants (G10, G11, and G12) which each have distinct @@ -780,12 +764,15 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define __HAS_ENGINE(engine_mask, id) ((engine_mask) & BIT(id)) #define HAS_ENGINE(gt, id) __HAS_ENGINE((gt)->info.engine_mask, id) -#define ENGINE_INSTANCES_MASK(gt, first, count) ({ \ +#define __ENGINE_INSTANCES_MASK(mask, first, count) ({ \ unsigned int first__ = (first); \ unsigned int count__ = (count); \ - ((gt)->info.engine_mask & \ - GENMASK(first__ + count__ - 1, first__)) >> first__; \ + ((mask) & GENMASK(first__ + count__ - 1, first__)) >> first__; \ }) + +#define ENGINE_INSTANCES_MASK(gt, first, count) \ + __ENGINE_INSTANCES_MASK((gt)->info.engine_mask, first, count) + #define RCS_MASK(gt) \ ENGINE_INSTANCES_MASK(gt, RCS0, I915_MAX_RCS) #define BCS_MASK(gt) \ @@ -871,6 +858,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define HAS_DOUBLE_BUFFERED_M_N(dev_priv) (DISPLAY_VER(dev_priv) >= 9 || IS_BROADWELL(dev_priv)) #define HAS_CDCLK_CRAWL(dev_priv) (INTEL_INFO(dev_priv)->display.has_cdclk_crawl) +#define HAS_CDCLK_SQUASH(dev_priv) (INTEL_INFO(dev_priv)->display.has_cdclk_squash) #define HAS_DDI(dev_priv) (INTEL_INFO(dev_priv)->display.has_ddi) #define HAS_FPGA_DBG_UNCLAIMED(dev_priv) (INTEL_INFO(dev_priv)->display.has_fpga_dbg) #define HAS_PSR(dev_priv) (INTEL_INFO(dev_priv)->display.has_psr) @@ -900,19 +888,17 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define HAS_RUNTIME_PM(dev_priv) (INTEL_INFO(dev_priv)->has_runtime_pm) #define HAS_64BIT_RELOC(dev_priv) (INTEL_INFO(dev_priv)->has_64bit_reloc) +#define HAS_OA_BPC_REPORTING(dev_priv) \ + (INTEL_INFO(dev_priv)->has_oa_bpc_reporting) +#define HAS_OA_SLICE_CONTRIB_LIMITS(dev_priv) \ + (INTEL_INFO(dev_priv)->has_oa_slice_contrib_limits) + /* * Set this flag, when platform requires 64K GTT page sizes or larger for * device local memory access. */ #define HAS_64K_PAGES(dev_priv) (INTEL_INFO(dev_priv)->has_64k_pages) -/* - * Set this flag when platform doesn't allow both 64k pages and 4k pages in - * the same PT. this flag means we need to support compact PT layout for the - * ppGTT when using the 64K GTT pages. - */ -#define NEEDS_COMPACT_PT(dev_priv) (INTEL_INFO(dev_priv)->needs_compact_pt) - #define HAS_IPC(dev_priv) (INTEL_INFO(dev_priv)->display.has_ipc) #define HAS_REGION(i915, i) (RUNTIME_INFO(i915)->memory_regions & (i)) @@ -938,6 +924,8 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define HAS_GMCH(dev_priv) (INTEL_INFO(dev_priv)->display.has_gmch) +#define HAS_GMD_ID(i915) (INTEL_INFO(i915)->has_gmd_id) + #define HAS_LSPCON(dev_priv) (IS_DISPLAY_VER(dev_priv, 9, 10)) #define HAS_L3_CCS_READ(i915) (INTEL_INFO(i915)->has_l3_ccs_read) @@ -976,6 +964,9 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define HAS_ONE_EU_PER_FUSE_BIT(i915) (INTEL_INFO(i915)->has_one_eu_per_fuse_bit) +#define HAS_LMEMBAR_SMEM_STOLEN(i915) (!HAS_LMEM(i915) && \ + GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) + /* intel_device_info.c */ static inline struct intel_device_info * mkwrite_device_info(struct drm_i915_private *dev_priv) @@ -983,16 +974,4 @@ mkwrite_device_info(struct drm_i915_private *dev_priv) return (struct intel_device_info *)INTEL_INFO(dev_priv); } -static inline enum i915_map_type -i915_coherent_map_type(struct drm_i915_private *i915, - struct drm_i915_gem_object *obj, bool always_coherent) -{ - if (i915_gem_object_is_lmem(obj)) - return I915_MAP_WC; - if (HAS_LLC(i915) || always_coherent) - return I915_MAP_WB; - else - return I915_MAP_WC; -} - #endif diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 2bdddb61ebd7..8468ca9885fd 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -843,7 +843,7 @@ void i915_gem_runtime_suspend(struct drm_i915_private *i915) __i915_gem_object_release_mmap_gtt(obj); list_for_each_entry_safe(obj, on, - &to_gt(i915)->lmem_userfault_list, userfault_link) + &i915->runtime_pm.lmem_userfault_list, userfault_link) i915_gem_object_runtime_pm_release_mmap_offset(obj); /* @@ -1128,6 +1128,8 @@ void i915_gem_drain_workqueue(struct drm_i915_private *i915) int i915_gem_init(struct drm_i915_private *dev_priv) { + struct intel_gt *gt; + unsigned int i; int ret; /* We need to fallback to 4K pages if host doesn't support huge gtt. */ @@ -1138,8 +1140,10 @@ int i915_gem_init(struct drm_i915_private *dev_priv) if (ret) return ret; - intel_uc_fetch_firmwares(&to_gt(dev_priv)->uc); - intel_wopcm_init(&dev_priv->wopcm); + for_each_gt(gt, dev_priv, i) { + intel_uc_fetch_firmwares(>->uc); + intel_wopcm_init(>->wopcm); + } ret = i915_init_ggtt(dev_priv); if (ret) { @@ -1158,9 +1162,11 @@ int i915_gem_init(struct drm_i915_private *dev_priv) */ intel_init_clock_gating(dev_priv); - ret = intel_gt_init(to_gt(dev_priv)); - if (ret) - goto err_unlock; + for_each_gt(gt, dev_priv, i) { + ret = intel_gt_init(gt); + if (ret) + goto err_unlock; + } return 0; @@ -1173,8 +1179,13 @@ int i915_gem_init(struct drm_i915_private *dev_priv) err_unlock: i915_gem_drain_workqueue(dev_priv); - if (ret != -EIO) - intel_uc_cleanup_firmwares(&to_gt(dev_priv)->uc); + if (ret != -EIO) { + for_each_gt(gt, dev_priv, i) { + intel_gt_driver_remove(gt); + intel_gt_driver_release(gt); + intel_uc_cleanup_firmwares(>->uc); + } + } if (ret == -EIO) { /* @@ -1182,10 +1193,12 @@ err_unlock: * as wedged. But we only want to do this when the GPU is angry, * for all other failure, such as an allocation failure, bail. */ - if (!intel_gt_is_wedged(to_gt(dev_priv))) { - i915_probe_error(dev_priv, - "Failed to initialize GPU, declaring it wedged!\n"); - intel_gt_set_wedged(to_gt(dev_priv)); + for_each_gt(gt, dev_priv, i) { + if (!intel_gt_is_wedged(gt)) { + i915_probe_error(dev_priv, + "Failed to initialize GPU, declaring it wedged!\n"); + intel_gt_set_wedged(gt); + } } /* Minimal basic recovery for KMS */ @@ -1213,23 +1226,27 @@ void i915_gem_driver_unregister(struct drm_i915_private *i915) void i915_gem_driver_remove(struct drm_i915_private *dev_priv) { - intel_wakeref_auto_fini(&to_gt(dev_priv)->userfault_wakeref); + struct intel_gt *gt; + unsigned int i; i915_gem_suspend_late(dev_priv); - intel_gt_driver_remove(to_gt(dev_priv)); + for_each_gt(gt, dev_priv, i) + intel_gt_driver_remove(gt); dev_priv->uabi_engines = RB_ROOT; /* Flush any outstanding unpin_work. */ i915_gem_drain_workqueue(dev_priv); - - i915_gem_drain_freed_objects(dev_priv); } void i915_gem_driver_release(struct drm_i915_private *dev_priv) { - intel_gt_driver_release(to_gt(dev_priv)); + struct intel_gt *gt; + unsigned int i; - intel_uc_cleanup_firmwares(&to_gt(dev_priv)->uc); + for_each_gt(gt, dev_priv, i) { + intel_gt_driver_release(gt); + intel_uc_cleanup_firmwares(>->uc); + } /* Flush any outstanding work, including i915_gem_context.release_work. */ i915_gem_drain_workqueue(dev_priv); @@ -1259,7 +1276,7 @@ void i915_gem_init_early(struct drm_i915_private *dev_priv) void i915_gem_cleanup_early(struct drm_i915_private *dev_priv) { - i915_gem_drain_freed_objects(dev_priv); + i915_gem_drain_workqueue(dev_priv); GEM_BUG_ON(!llist_empty(&dev_priv->mm.free_list)); GEM_BUG_ON(atomic_read(&dev_priv->mm.free_count)); drm_WARN_ON(&dev_priv->drm, dev_priv->mm.shrink_count); @@ -1271,7 +1288,7 @@ int i915_gem_open(struct drm_i915_private *i915, struct drm_file *file) struct i915_drm_client *client; int ret = -ENOMEM; - DRM_DEBUG("\n"); + drm_dbg(&i915->drm, "\n"); file_priv = kzalloc(sizeof(*file_priv), GFP_KERNEL); if (!file_priv) diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c index f025ee4fa526..a4b4d9b7d26c 100644 --- a/drivers/gpu/drm/i915/i915_gem_evict.c +++ b/drivers/gpu/drm/i915/i915_gem_evict.c @@ -416,6 +416,11 @@ int i915_gem_evict_for_node(struct i915_address_space *vm, * @vm: Address space to cleanse * @ww: An optional struct i915_gem_ww_ctx. If not NULL, i915_gem_evict_vm * will be able to evict vma's locked by the ww as well. + * @busy_bo: Optional pointer to struct drm_i915_gem_object. If not NULL, then + * in the event i915_gem_evict_vm() is unable to trylock an object for eviction, + * then @busy_bo will point to it. -EBUSY is also returned. The caller must drop + * the vm->mutex, before trying again to acquire the contended lock. The caller + * also owns a reference to the object. * * This function evicts all vmas from a vm. * @@ -425,7 +430,8 @@ int i915_gem_evict_for_node(struct i915_address_space *vm, * To clarify: This is for freeing up virtual address space, not for freeing * memory in e.g. the shrinker. */ -int i915_gem_evict_vm(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww) +int i915_gem_evict_vm(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww, + struct drm_i915_gem_object **busy_bo) { int ret = 0; @@ -457,15 +463,22 @@ int i915_gem_evict_vm(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww) * the resv is shared among multiple objects, we still * need the object ref. */ - if (dying_vma(vma) || + if (!i915_gem_object_get_rcu(vma->obj) || (ww && (dma_resv_locking_ctx(vma->obj->base.resv) == &ww->ctx))) { __i915_vma_pin(vma); list_add(&vma->evict_link, &locked_eviction_list); continue; } - if (!i915_gem_object_trylock(vma->obj, ww)) + if (!i915_gem_object_trylock(vma->obj, ww)) { + if (busy_bo) { + *busy_bo = vma->obj; /* holds ref */ + ret = -EBUSY; + break; + } + i915_gem_object_put(vma->obj); continue; + } __i915_vma_pin(vma); list_add(&vma->evict_link, &eviction_list); @@ -473,25 +486,29 @@ int i915_gem_evict_vm(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww) if (list_empty(&eviction_list) && list_empty(&locked_eviction_list)) break; - ret = 0; /* Unbind locked objects first, before unlocking the eviction_list */ list_for_each_entry_safe(vma, vn, &locked_eviction_list, evict_link) { __i915_vma_unpin(vma); - if (ret == 0) + if (ret == 0) { ret = __i915_vma_unbind(vma); - if (ret != -EINTR) /* "Get me out of here!" */ - ret = 0; + if (ret != -EINTR) /* "Get me out of here!" */ + ret = 0; + } + if (!dying_vma(vma)) + i915_gem_object_put(vma->obj); } list_for_each_entry_safe(vma, vn, &eviction_list, evict_link) { __i915_vma_unpin(vma); - if (ret == 0) + if (ret == 0) { ret = __i915_vma_unbind(vma); - if (ret != -EINTR) /* "Get me out of here!" */ - ret = 0; + if (ret != -EINTR) /* "Get me out of here!" */ + ret = 0; + } i915_gem_object_unlock(vma->obj); + i915_gem_object_put(vma->obj); } } while (ret == 0); diff --git a/drivers/gpu/drm/i915/i915_gem_evict.h b/drivers/gpu/drm/i915/i915_gem_evict.h index e593c530f9bd..bf0ee0e4fe60 100644 --- a/drivers/gpu/drm/i915/i915_gem_evict.h +++ b/drivers/gpu/drm/i915/i915_gem_evict.h @@ -11,6 +11,7 @@ struct drm_mm_node; struct i915_address_space; struct i915_gem_ww_ctx; +struct drm_i915_gem_object; int __must_check i915_gem_evict_something(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww, @@ -23,6 +24,7 @@ int __must_check i915_gem_evict_for_node(struct i915_address_space *vm, struct drm_mm_node *node, unsigned int flags); int i915_gem_evict_vm(struct i915_address_space *vm, - struct i915_gem_ww_ctx *ww); + struct i915_gem_ww_ctx *ww, + struct drm_i915_gem_object **busy_bo); #endif /* __I915_GEM_EVICT_H__ */ diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c index 342c8ca6414e..61ef2d9cfa62 100644 --- a/drivers/gpu/drm/i915/i915_getparam.c +++ b/drivers/gpu/drm/i915/i915_getparam.c @@ -175,8 +175,11 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data, case I915_PARAM_PERF_REVISION: value = i915_perf_ioctl_version(); break; + case I915_PARAM_OA_TIMESTAMP_FREQUENCY: + value = i915_perf_oa_timestamp_frequency(i915); + break; default: - DRM_DEBUG("Unknown parameter %d\n", param->param); + drm_dbg(&i915->drm, "Unknown parameter %d\n", param->param); return -EINVAL; } diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 9ea2fe34e7d3..9d5d5a397b64 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -55,6 +55,7 @@ #include "i915_drv.h" #include "i915_gpu_error.h" #include "i915_memcpy.h" +#include "i915_reg.h" #include "i915_scatterlist.h" #include "i915_utils.h" @@ -1221,7 +1222,10 @@ static void engine_record_registers(struct intel_engine_coredump *ee) if (GRAPHICS_VER(i915) >= 6) { ee->rc_psmi = ENGINE_READ(engine, RING_PSMI_CTL); - if (GRAPHICS_VER(i915) >= 12) + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) + ee->fault_reg = intel_gt_mcr_read_any(engine->gt, + XEHP_RING_FAULT_REG); + else if (GRAPHICS_VER(i915) >= 12) ee->fault_reg = intel_uncore_read(engine->uncore, GEN12_RING_FAULT_REG); else if (GRAPHICS_VER(i915) >= 8) @@ -1820,7 +1824,12 @@ static void gt_record_global_regs(struct intel_gt_coredump *gt) if (GRAPHICS_VER(i915) == 7) gt->err_int = intel_uncore_read(uncore, GEN7_ERR_INT); - if (GRAPHICS_VER(i915) >= 12) { + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) { + gt->fault_data0 = intel_gt_mcr_read_any((struct intel_gt *)gt->_gt, + XEHP_FAULT_TLB_DATA0); + gt->fault_data1 = intel_gt_mcr_read_any((struct intel_gt *)gt->_gt, + XEHP_FAULT_TLB_DATA1); + } else if (GRAPHICS_VER(i915) >= 12) { gt->fault_data0 = intel_uncore_read(uncore, GEN12_FAULT_TLB_DATA0); gt->fault_data1 = intel_uncore_read(uncore, diff --git a/drivers/gpu/drm/i915/i915_hwmon.c b/drivers/gpu/drm/i915/i915_hwmon.c new file mode 100644 index 000000000000..c588a17f97e9 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_hwmon.c @@ -0,0 +1,732 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2022 Intel Corporation + */ + +#include <linux/hwmon.h> +#include <linux/hwmon-sysfs.h> +#include <linux/types.h> + +#include "i915_drv.h" +#include "i915_hwmon.h" +#include "i915_reg.h" +#include "intel_mchbar_regs.h" +#include "intel_pcode.h" +#include "gt/intel_gt.h" +#include "gt/intel_gt_regs.h" + +/* + * SF_* - scale factors for particular quantities according to hwmon spec. + * - voltage - millivolts + * - power - microwatts + * - curr - milliamperes + * - energy - microjoules + * - time - milliseconds + */ +#define SF_VOLTAGE 1000 +#define SF_POWER 1000000 +#define SF_CURR 1000 +#define SF_ENERGY 1000000 +#define SF_TIME 1000 + +struct hwm_reg { + i915_reg_t gt_perf_status; + i915_reg_t pkg_power_sku_unit; + i915_reg_t pkg_power_sku; + i915_reg_t pkg_rapl_limit; + i915_reg_t energy_status_all; + i915_reg_t energy_status_tile; +}; + +struct hwm_energy_info { + u32 reg_val_prev; + long accum_energy; /* Accumulated energy for energy1_input */ +}; + +struct hwm_drvdata { + struct i915_hwmon *hwmon; + struct intel_uncore *uncore; + struct device *hwmon_dev; + struct hwm_energy_info ei; /* Energy info for energy1_input */ + char name[12]; + int gt_n; +}; + +struct i915_hwmon { + struct hwm_drvdata ddat; + struct hwm_drvdata ddat_gt[I915_MAX_GT]; + struct mutex hwmon_lock; /* counter overflow logic and rmw */ + struct hwm_reg rg; + int scl_shift_power; + int scl_shift_energy; + int scl_shift_time; +}; + +static void +hwm_locked_with_pm_intel_uncore_rmw(struct hwm_drvdata *ddat, + i915_reg_t reg, u32 clear, u32 set) +{ + struct i915_hwmon *hwmon = ddat->hwmon; + struct intel_uncore *uncore = ddat->uncore; + intel_wakeref_t wakeref; + + mutex_lock(&hwmon->hwmon_lock); + + with_intel_runtime_pm(uncore->rpm, wakeref) + intel_uncore_rmw(uncore, reg, clear, set); + + mutex_unlock(&hwmon->hwmon_lock); +} + +/* + * This function's return type of u64 allows for the case where the scaling + * of the field taken from the 32-bit register value might cause a result to + * exceed 32 bits. + */ +static u64 +hwm_field_read_and_scale(struct hwm_drvdata *ddat, i915_reg_t rgadr, + u32 field_msk, int nshift, u32 scale_factor) +{ + struct intel_uncore *uncore = ddat->uncore; + intel_wakeref_t wakeref; + u32 reg_value; + + with_intel_runtime_pm(uncore->rpm, wakeref) + reg_value = intel_uncore_read(uncore, rgadr); + + reg_value = REG_FIELD_GET(field_msk, reg_value); + + return mul_u64_u32_shr(reg_value, scale_factor, nshift); +} + +static void +hwm_field_scale_and_write(struct hwm_drvdata *ddat, i915_reg_t rgadr, + int nshift, unsigned int scale_factor, long lval) +{ + u32 nval; + + /* Computation in 64-bits to avoid overflow. Round to nearest. */ + nval = DIV_ROUND_CLOSEST_ULL((u64)lval << nshift, scale_factor); + + hwm_locked_with_pm_intel_uncore_rmw(ddat, rgadr, + PKG_PWR_LIM_1, + REG_FIELD_PREP(PKG_PWR_LIM_1, nval)); +} + +/* + * hwm_energy - Obtain energy value + * + * The underlying energy hardware register is 32-bits and is subject to + * overflow. How long before overflow? For example, with an example + * scaling bit shift of 14 bits (see register *PACKAGE_POWER_SKU_UNIT) and + * a power draw of 1000 watts, the 32-bit counter will overflow in + * approximately 4.36 minutes. + * + * Examples: + * 1 watt: (2^32 >> 14) / 1 W / (60 * 60 * 24) secs/day -> 3 days + * 1000 watts: (2^32 >> 14) / 1000 W / 60 secs/min -> 4.36 minutes + * + * The function significantly increases overflow duration (from 4.36 + * minutes) by accumulating the energy register into a 'long' as allowed by + * the hwmon API. Using x86_64 128 bit arithmetic (see mul_u64_u32_shr()), + * a 'long' of 63 bits, SF_ENERGY of 1e6 (~20 bits) and + * hwmon->scl_shift_energy of 14 bits we have 57 (63 - 20 + 14) bits before + * energy1_input overflows. This at 1000 W is an overflow duration of 278 years. + */ +static void +hwm_energy(struct hwm_drvdata *ddat, long *energy) +{ + struct intel_uncore *uncore = ddat->uncore; + struct i915_hwmon *hwmon = ddat->hwmon; + struct hwm_energy_info *ei = &ddat->ei; + intel_wakeref_t wakeref; + i915_reg_t rgaddr; + u32 reg_val; + + if (ddat->gt_n >= 0) + rgaddr = hwmon->rg.energy_status_tile; + else + rgaddr = hwmon->rg.energy_status_all; + + mutex_lock(&hwmon->hwmon_lock); + + with_intel_runtime_pm(uncore->rpm, wakeref) + reg_val = intel_uncore_read(uncore, rgaddr); + + if (reg_val >= ei->reg_val_prev) + ei->accum_energy += reg_val - ei->reg_val_prev; + else + ei->accum_energy += UINT_MAX - ei->reg_val_prev + reg_val; + ei->reg_val_prev = reg_val; + + *energy = mul_u64_u32_shr(ei->accum_energy, SF_ENERGY, + hwmon->scl_shift_energy); + mutex_unlock(&hwmon->hwmon_lock); +} + +static ssize_t +hwm_power1_max_interval_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct hwm_drvdata *ddat = dev_get_drvdata(dev); + struct i915_hwmon *hwmon = ddat->hwmon; + intel_wakeref_t wakeref; + u32 r, x, y, x_w = 2; /* 2 bits */ + u64 tau4, out; + + with_intel_runtime_pm(ddat->uncore->rpm, wakeref) + r = intel_uncore_read(ddat->uncore, hwmon->rg.pkg_rapl_limit); + + x = REG_FIELD_GET(PKG_PWR_LIM_1_TIME_X, r); + y = REG_FIELD_GET(PKG_PWR_LIM_1_TIME_Y, r); + /* + * tau = 1.x * power(2,y), x = bits(23:22), y = bits(21:17) + * = (4 | x) << (y - 2) + * where (y - 2) ensures a 1.x fixed point representation of 1.x + * However because y can be < 2, we compute + * tau4 = (4 | x) << y + * but add 2 when doing the final right shift to account for units + */ + tau4 = ((1 << x_w) | x) << y; + /* val in hwmon interface units (millisec) */ + out = mul_u64_u32_shr(tau4, SF_TIME, hwmon->scl_shift_time + x_w); + + return sysfs_emit(buf, "%llu\n", out); +} + +static ssize_t +hwm_power1_max_interval_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct hwm_drvdata *ddat = dev_get_drvdata(dev); + struct i915_hwmon *hwmon = ddat->hwmon; + u32 x, y, rxy, x_w = 2; /* 2 bits */ + u64 tau4, r, max_win; + unsigned long val; + int ret; + + ret = kstrtoul(buf, 0, &val); + if (ret) + return ret; + + /* + * Max HW supported tau in '1.x * power(2,y)' format, x = 0, y = 0x12 + * The hwmon->scl_shift_time default of 0xa results in a max tau of 256 seconds + */ +#define PKG_MAX_WIN_DEFAULT 0x12ull + + /* + * val must be < max in hwmon interface units. The steps below are + * explained in i915_power1_max_interval_show() + */ + r = FIELD_PREP(PKG_MAX_WIN, PKG_MAX_WIN_DEFAULT); + x = REG_FIELD_GET(PKG_MAX_WIN_X, r); + y = REG_FIELD_GET(PKG_MAX_WIN_Y, r); + tau4 = ((1 << x_w) | x) << y; + max_win = mul_u64_u32_shr(tau4, SF_TIME, hwmon->scl_shift_time + x_w); + + if (val > max_win) + return -EINVAL; + + /* val in hw units */ + val = DIV_ROUND_CLOSEST_ULL((u64)val << hwmon->scl_shift_time, SF_TIME); + /* Convert to 1.x * power(2,y) */ + if (!val) + return -EINVAL; + y = ilog2(val); + /* x = (val - (1 << y)) >> (y - 2); */ + x = (val - (1ul << y)) << x_w >> y; + + rxy = REG_FIELD_PREP(PKG_PWR_LIM_1_TIME_X, x) | REG_FIELD_PREP(PKG_PWR_LIM_1_TIME_Y, y); + + hwm_locked_with_pm_intel_uncore_rmw(ddat, hwmon->rg.pkg_rapl_limit, + PKG_PWR_LIM_1_TIME, rxy); + return count; +} + +static SENSOR_DEVICE_ATTR(power1_max_interval, 0664, + hwm_power1_max_interval_show, + hwm_power1_max_interval_store, 0); + +static struct attribute *hwm_attributes[] = { + &sensor_dev_attr_power1_max_interval.dev_attr.attr, + NULL +}; + +static umode_t hwm_attributes_visible(struct kobject *kobj, + struct attribute *attr, int index) +{ + struct device *dev = kobj_to_dev(kobj); + struct hwm_drvdata *ddat = dev_get_drvdata(dev); + struct i915_hwmon *hwmon = ddat->hwmon; + + if (attr == &sensor_dev_attr_power1_max_interval.dev_attr.attr) + return i915_mmio_reg_valid(hwmon->rg.pkg_rapl_limit) ? attr->mode : 0; + + return 0; +} + +static const struct attribute_group hwm_attrgroup = { + .attrs = hwm_attributes, + .is_visible = hwm_attributes_visible, +}; + +static const struct attribute_group *hwm_groups[] = { + &hwm_attrgroup, + NULL +}; + +static const struct hwmon_channel_info *hwm_info[] = { + HWMON_CHANNEL_INFO(in, HWMON_I_INPUT), + HWMON_CHANNEL_INFO(power, HWMON_P_MAX | HWMON_P_RATED_MAX | HWMON_P_CRIT), + HWMON_CHANNEL_INFO(energy, HWMON_E_INPUT), + HWMON_CHANNEL_INFO(curr, HWMON_C_CRIT), + NULL +}; + +static const struct hwmon_channel_info *hwm_gt_info[] = { + HWMON_CHANNEL_INFO(energy, HWMON_E_INPUT), + NULL +}; + +/* I1 is exposed as power_crit or as curr_crit depending on bit 31 */ +static int hwm_pcode_read_i1(struct drm_i915_private *i915, u32 *uval) +{ + return snb_pcode_read_p(&i915->uncore, PCODE_POWER_SETUP, + POWER_SETUP_SUBCOMMAND_READ_I1, 0, uval); +} + +static int hwm_pcode_write_i1(struct drm_i915_private *i915, u32 uval) +{ + return snb_pcode_write_p(&i915->uncore, PCODE_POWER_SETUP, + POWER_SETUP_SUBCOMMAND_WRITE_I1, 0, uval); +} + +static umode_t +hwm_in_is_visible(const struct hwm_drvdata *ddat, u32 attr) +{ + struct drm_i915_private *i915 = ddat->uncore->i915; + + switch (attr) { + case hwmon_in_input: + return IS_DG1(i915) || IS_DG2(i915) ? 0444 : 0; + default: + return 0; + } +} + +static int +hwm_in_read(struct hwm_drvdata *ddat, u32 attr, long *val) +{ + struct i915_hwmon *hwmon = ddat->hwmon; + intel_wakeref_t wakeref; + u32 reg_value; + + switch (attr) { + case hwmon_in_input: + with_intel_runtime_pm(ddat->uncore->rpm, wakeref) + reg_value = intel_uncore_read(ddat->uncore, hwmon->rg.gt_perf_status); + /* HW register value in units of 2.5 millivolt */ + *val = DIV_ROUND_CLOSEST(REG_FIELD_GET(GEN12_VOLTAGE_MASK, reg_value) * 25, 10); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static umode_t +hwm_power_is_visible(const struct hwm_drvdata *ddat, u32 attr, int chan) +{ + struct drm_i915_private *i915 = ddat->uncore->i915; + struct i915_hwmon *hwmon = ddat->hwmon; + u32 uval; + + switch (attr) { + case hwmon_power_max: + return i915_mmio_reg_valid(hwmon->rg.pkg_rapl_limit) ? 0664 : 0; + case hwmon_power_rated_max: + return i915_mmio_reg_valid(hwmon->rg.pkg_power_sku) ? 0444 : 0; + case hwmon_power_crit: + return (hwm_pcode_read_i1(i915, &uval) || + !(uval & POWER_SETUP_I1_WATTS)) ? 0 : 0644; + default: + return 0; + } +} + +static int +hwm_power_read(struct hwm_drvdata *ddat, u32 attr, int chan, long *val) +{ + struct i915_hwmon *hwmon = ddat->hwmon; + int ret; + u32 uval; + + switch (attr) { + case hwmon_power_max: + *val = hwm_field_read_and_scale(ddat, + hwmon->rg.pkg_rapl_limit, + PKG_PWR_LIM_1, + hwmon->scl_shift_power, + SF_POWER); + return 0; + case hwmon_power_rated_max: + *val = hwm_field_read_and_scale(ddat, + hwmon->rg.pkg_power_sku, + PKG_PKG_TDP, + hwmon->scl_shift_power, + SF_POWER); + return 0; + case hwmon_power_crit: + ret = hwm_pcode_read_i1(ddat->uncore->i915, &uval); + if (ret) + return ret; + if (!(uval & POWER_SETUP_I1_WATTS)) + return -ENODEV; + *val = mul_u64_u32_shr(REG_FIELD_GET(POWER_SETUP_I1_DATA_MASK, uval), + SF_POWER, POWER_SETUP_I1_SHIFT); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int +hwm_power_write(struct hwm_drvdata *ddat, u32 attr, int chan, long val) +{ + struct i915_hwmon *hwmon = ddat->hwmon; + u32 uval; + + switch (attr) { + case hwmon_power_max: + hwm_field_scale_and_write(ddat, + hwmon->rg.pkg_rapl_limit, + hwmon->scl_shift_power, + SF_POWER, val); + return 0; + case hwmon_power_crit: + uval = DIV_ROUND_CLOSEST_ULL(val << POWER_SETUP_I1_SHIFT, SF_POWER); + return hwm_pcode_write_i1(ddat->uncore->i915, uval); + default: + return -EOPNOTSUPP; + } +} + +static umode_t +hwm_energy_is_visible(const struct hwm_drvdata *ddat, u32 attr) +{ + struct i915_hwmon *hwmon = ddat->hwmon; + i915_reg_t rgaddr; + + switch (attr) { + case hwmon_energy_input: + if (ddat->gt_n >= 0) + rgaddr = hwmon->rg.energy_status_tile; + else + rgaddr = hwmon->rg.energy_status_all; + return i915_mmio_reg_valid(rgaddr) ? 0444 : 0; + default: + return 0; + } +} + +static int +hwm_energy_read(struct hwm_drvdata *ddat, u32 attr, long *val) +{ + switch (attr) { + case hwmon_energy_input: + hwm_energy(ddat, val); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static umode_t +hwm_curr_is_visible(const struct hwm_drvdata *ddat, u32 attr) +{ + struct drm_i915_private *i915 = ddat->uncore->i915; + u32 uval; + + switch (attr) { + case hwmon_curr_crit: + return (hwm_pcode_read_i1(i915, &uval) || + (uval & POWER_SETUP_I1_WATTS)) ? 0 : 0644; + default: + return 0; + } +} + +static int +hwm_curr_read(struct hwm_drvdata *ddat, u32 attr, long *val) +{ + int ret; + u32 uval; + + switch (attr) { + case hwmon_curr_crit: + ret = hwm_pcode_read_i1(ddat->uncore->i915, &uval); + if (ret) + return ret; + if (uval & POWER_SETUP_I1_WATTS) + return -ENODEV; + *val = mul_u64_u32_shr(REG_FIELD_GET(POWER_SETUP_I1_DATA_MASK, uval), + SF_CURR, POWER_SETUP_I1_SHIFT); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int +hwm_curr_write(struct hwm_drvdata *ddat, u32 attr, long val) +{ + u32 uval; + + switch (attr) { + case hwmon_curr_crit: + uval = DIV_ROUND_CLOSEST_ULL(val << POWER_SETUP_I1_SHIFT, SF_CURR); + return hwm_pcode_write_i1(ddat->uncore->i915, uval); + default: + return -EOPNOTSUPP; + } +} + +static umode_t +hwm_is_visible(const void *drvdata, enum hwmon_sensor_types type, + u32 attr, int channel) +{ + struct hwm_drvdata *ddat = (struct hwm_drvdata *)drvdata; + + switch (type) { + case hwmon_in: + return hwm_in_is_visible(ddat, attr); + case hwmon_power: + return hwm_power_is_visible(ddat, attr, channel); + case hwmon_energy: + return hwm_energy_is_visible(ddat, attr); + case hwmon_curr: + return hwm_curr_is_visible(ddat, attr); + default: + return 0; + } +} + +static int +hwm_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, + int channel, long *val) +{ + struct hwm_drvdata *ddat = dev_get_drvdata(dev); + + switch (type) { + case hwmon_in: + return hwm_in_read(ddat, attr, val); + case hwmon_power: + return hwm_power_read(ddat, attr, channel, val); + case hwmon_energy: + return hwm_energy_read(ddat, attr, val); + case hwmon_curr: + return hwm_curr_read(ddat, attr, val); + default: + return -EOPNOTSUPP; + } +} + +static int +hwm_write(struct device *dev, enum hwmon_sensor_types type, u32 attr, + int channel, long val) +{ + struct hwm_drvdata *ddat = dev_get_drvdata(dev); + + switch (type) { + case hwmon_power: + return hwm_power_write(ddat, attr, channel, val); + case hwmon_curr: + return hwm_curr_write(ddat, attr, val); + default: + return -EOPNOTSUPP; + } +} + +static const struct hwmon_ops hwm_ops = { + .is_visible = hwm_is_visible, + .read = hwm_read, + .write = hwm_write, +}; + +static const struct hwmon_chip_info hwm_chip_info = { + .ops = &hwm_ops, + .info = hwm_info, +}; + +static umode_t +hwm_gt_is_visible(const void *drvdata, enum hwmon_sensor_types type, + u32 attr, int channel) +{ + struct hwm_drvdata *ddat = (struct hwm_drvdata *)drvdata; + + switch (type) { + case hwmon_energy: + return hwm_energy_is_visible(ddat, attr); + default: + return 0; + } +} + +static int +hwm_gt_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, + int channel, long *val) +{ + struct hwm_drvdata *ddat = dev_get_drvdata(dev); + + switch (type) { + case hwmon_energy: + return hwm_energy_read(ddat, attr, val); + default: + return -EOPNOTSUPP; + } +} + +static const struct hwmon_ops hwm_gt_ops = { + .is_visible = hwm_gt_is_visible, + .read = hwm_gt_read, +}; + +static const struct hwmon_chip_info hwm_gt_chip_info = { + .ops = &hwm_gt_ops, + .info = hwm_gt_info, +}; + +static void +hwm_get_preregistration_info(struct drm_i915_private *i915) +{ + struct i915_hwmon *hwmon = i915->hwmon; + struct intel_uncore *uncore = &i915->uncore; + struct hwm_drvdata *ddat = &hwmon->ddat; + intel_wakeref_t wakeref; + u32 val_sku_unit = 0; + struct intel_gt *gt; + long energy; + int i; + + /* Available for all Gen12+/dGfx */ + hwmon->rg.gt_perf_status = GEN12_RPSTAT1; + + if (IS_DG1(i915) || IS_DG2(i915)) { + hwmon->rg.pkg_power_sku_unit = PCU_PACKAGE_POWER_SKU_UNIT; + hwmon->rg.pkg_power_sku = PCU_PACKAGE_POWER_SKU; + hwmon->rg.pkg_rapl_limit = PCU_PACKAGE_RAPL_LIMIT; + hwmon->rg.energy_status_all = PCU_PACKAGE_ENERGY_STATUS; + hwmon->rg.energy_status_tile = INVALID_MMIO_REG; + } else if (IS_XEHPSDV(i915)) { + hwmon->rg.pkg_power_sku_unit = GT0_PACKAGE_POWER_SKU_UNIT; + hwmon->rg.pkg_power_sku = INVALID_MMIO_REG; + hwmon->rg.pkg_rapl_limit = GT0_PACKAGE_RAPL_LIMIT; + hwmon->rg.energy_status_all = GT0_PLATFORM_ENERGY_STATUS; + hwmon->rg.energy_status_tile = GT0_PACKAGE_ENERGY_STATUS; + } else { + hwmon->rg.pkg_power_sku_unit = INVALID_MMIO_REG; + hwmon->rg.pkg_power_sku = INVALID_MMIO_REG; + hwmon->rg.pkg_rapl_limit = INVALID_MMIO_REG; + hwmon->rg.energy_status_all = INVALID_MMIO_REG; + hwmon->rg.energy_status_tile = INVALID_MMIO_REG; + } + + with_intel_runtime_pm(uncore->rpm, wakeref) { + /* + * The contents of register hwmon->rg.pkg_power_sku_unit do not change, + * so read it once and store the shift values. + */ + if (i915_mmio_reg_valid(hwmon->rg.pkg_power_sku_unit)) + val_sku_unit = intel_uncore_read(uncore, + hwmon->rg.pkg_power_sku_unit); + } + + hwmon->scl_shift_power = REG_FIELD_GET(PKG_PWR_UNIT, val_sku_unit); + hwmon->scl_shift_energy = REG_FIELD_GET(PKG_ENERGY_UNIT, val_sku_unit); + hwmon->scl_shift_time = REG_FIELD_GET(PKG_TIME_UNIT, val_sku_unit); + + /* + * Initialize 'struct hwm_energy_info', i.e. set fields to the + * first value of the energy register read + */ + if (i915_mmio_reg_valid(hwmon->rg.energy_status_all)) + hwm_energy(ddat, &energy); + if (i915_mmio_reg_valid(hwmon->rg.energy_status_tile)) { + for_each_gt(gt, i915, i) + hwm_energy(&hwmon->ddat_gt[i], &energy); + } +} + +void i915_hwmon_register(struct drm_i915_private *i915) +{ + struct device *dev = i915->drm.dev; + struct i915_hwmon *hwmon; + struct device *hwmon_dev; + struct hwm_drvdata *ddat; + struct hwm_drvdata *ddat_gt; + struct intel_gt *gt; + int i; + + /* hwmon is available only for dGfx */ + if (!IS_DGFX(i915)) + return; + + hwmon = devm_kzalloc(dev, sizeof(*hwmon), GFP_KERNEL); + if (!hwmon) + return; + + i915->hwmon = hwmon; + mutex_init(&hwmon->hwmon_lock); + ddat = &hwmon->ddat; + + ddat->hwmon = hwmon; + ddat->uncore = &i915->uncore; + snprintf(ddat->name, sizeof(ddat->name), "i915"); + ddat->gt_n = -1; + + for_each_gt(gt, i915, i) { + ddat_gt = hwmon->ddat_gt + i; + + ddat_gt->hwmon = hwmon; + ddat_gt->uncore = gt->uncore; + snprintf(ddat_gt->name, sizeof(ddat_gt->name), "i915_gt%u", i); + ddat_gt->gt_n = i; + } + + hwm_get_preregistration_info(i915); + + /* hwmon_dev points to device hwmon<i> */ + hwmon_dev = devm_hwmon_device_register_with_info(dev, ddat->name, + ddat, + &hwm_chip_info, + hwm_groups); + if (IS_ERR(hwmon_dev)) { + i915->hwmon = NULL; + return; + } + + ddat->hwmon_dev = hwmon_dev; + + for_each_gt(gt, i915, i) { + ddat_gt = hwmon->ddat_gt + i; + /* + * Create per-gt directories only if a per-gt attribute is + * visible. Currently this is only energy + */ + if (!hwm_gt_is_visible(ddat_gt, hwmon_energy, hwmon_energy_input, 0)) + continue; + + hwmon_dev = devm_hwmon_device_register_with_info(dev, ddat_gt->name, + ddat_gt, + &hwm_gt_chip_info, + NULL); + if (!IS_ERR(hwmon_dev)) + ddat_gt->hwmon_dev = hwmon_dev; + } +} + +void i915_hwmon_unregister(struct drm_i915_private *i915) +{ + fetch_and_zero(&i915->hwmon); +} diff --git a/drivers/gpu/drm/i915/i915_hwmon.h b/drivers/gpu/drm/i915/i915_hwmon.h new file mode 100644 index 000000000000..7ca9cf2c34c9 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_hwmon.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: MIT */ + +/* + * Copyright © 2022 Intel Corporation + */ + +#ifndef __I915_HWMON_H__ +#define __I915_HWMON_H__ + +struct drm_i915_private; + +#if IS_REACHABLE(CONFIG_HWMON) +void i915_hwmon_register(struct drm_i915_private *i915); +void i915_hwmon_unregister(struct drm_i915_private *i915); +#else +static inline void i915_hwmon_register(struct drm_i915_private *i915) { }; +static inline void i915_hwmon_unregister(struct drm_i915_private *i915) { }; +#endif + +#endif /* __I915_HWMON_H__ */ diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 86a42d9e8041..91c533986041 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -28,7 +28,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/circ_buf.h> #include <linux/slab.h> #include <linux/sysrq.h> @@ -248,7 +247,7 @@ void gen3_irq_reset(struct intel_uncore *uncore, i915_reg_t imr, intel_uncore_posting_read(uncore, iir); } -void gen2_irq_reset(struct intel_uncore *uncore) +static void gen2_irq_reset(struct intel_uncore *uncore) { intel_uncore_write16(uncore, GEN2_IMR, 0xffff); intel_uncore_posting_read16(uncore, GEN2_IMR); @@ -309,8 +308,8 @@ void gen3_irq_init(struct intel_uncore *uncore, intel_uncore_posting_read(uncore, imr); } -void gen2_irq_init(struct intel_uncore *uncore, - u32 imr_val, u32 ier_val) +static void gen2_irq_init(struct intel_uncore *uncore, + u32 imr_val, u32 ier_val) { gen2_assert_iir_is_zero(uncore); @@ -325,15 +324,10 @@ i915_hotplug_interrupt_update_locked(struct drm_i915_private *dev_priv, u32 mask, u32 bits) { - u32 val; - lockdep_assert_held(&dev_priv->irq_lock); drm_WARN_ON(&dev_priv->drm, bits & ~mask); - val = intel_uncore_read(&dev_priv->uncore, PORT_HOTPLUG_EN); - val &= ~mask; - val |= bits; - intel_uncore_write(&dev_priv->uncore, PORT_HOTPLUG_EN, val); + intel_uncore_rmw(&dev_priv->uncore, PORT_HOTPLUG_EN, mask, bits); } /** @@ -1057,8 +1051,8 @@ static void ivb_parity_work(struct work_struct *work) if (drm_WARN_ON(&dev_priv->drm, !dev_priv->l3_parity.which_slice)) goto out; - misccpctl = intel_uncore_read(&dev_priv->uncore, GEN7_MISCCPCTL); - intel_uncore_write(&dev_priv->uncore, GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE); + misccpctl = intel_uncore_rmw(&dev_priv->uncore, GEN7_MISCCPCTL, + GEN7_DOP_CLOCK_GATE_ENABLE, 0); intel_uncore_posting_read(&dev_priv->uncore, GEN7_MISCCPCTL); while ((slice = ffs(dev_priv->l3_parity.which_slice)) != 0) { @@ -1091,8 +1085,9 @@ static void ivb_parity_work(struct work_struct *work) kobject_uevent_env(&dev_priv->drm.primary->kdev->kobj, KOBJ_CHANGE, parity_event); - DRM_DEBUG("Parity error: Slice = %d, Row = %d, Bank = %d, Sub bank = %d.\n", - slice, row, bank, subbank); + drm_dbg(&dev_priv->drm, + "Parity error: Slice = %d, Row = %d, Bank = %d, Sub bank = %d.\n", + slice, row, bank, subbank); kfree(parity_event[4]); kfree(parity_event[3]); @@ -1689,8 +1684,7 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg) * bits this time around. */ intel_uncore_write(&dev_priv->uncore, VLV_MASTER_IER, 0); - ier = intel_uncore_read(&dev_priv->uncore, VLV_IER); - intel_uncore_write(&dev_priv->uncore, VLV_IER, 0); + ier = intel_uncore_rmw(&dev_priv->uncore, VLV_IER, ~0, 0); if (gt_iir) intel_uncore_write(&dev_priv->uncore, GTIIR, gt_iir); @@ -1775,8 +1769,7 @@ static irqreturn_t cherryview_irq_handler(int irq, void *arg) * bits this time around. */ intel_uncore_write(&dev_priv->uncore, GEN8_MASTER_IRQ, 0); - ier = intel_uncore_read(&dev_priv->uncore, VLV_IER); - intel_uncore_write(&dev_priv->uncore, VLV_IER, 0); + ier = intel_uncore_rmw(&dev_priv->uncore, VLV_IER, ~0, 0); gen8_gt_irq_handler(to_gt(dev_priv), master_ctl); @@ -1981,8 +1974,10 @@ static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir) if (ddi_hotplug_trigger) { u32 dig_hotplug_reg; - dig_hotplug_reg = intel_uncore_read(&dev_priv->uncore, SHOTPLUG_CTL_DDI); - intel_uncore_write(&dev_priv->uncore, SHOTPLUG_CTL_DDI, dig_hotplug_reg); + /* Locking due to DSI native GPIO sequences */ + spin_lock(&dev_priv->irq_lock); + dig_hotplug_reg = intel_uncore_rmw(&dev_priv->uncore, SHOTPLUG_CTL_DDI, 0, 0); + spin_unlock(&dev_priv->irq_lock); intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, ddi_hotplug_trigger, dig_hotplug_reg, @@ -1993,8 +1988,7 @@ static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir) if (tc_hotplug_trigger) { u32 dig_hotplug_reg; - dig_hotplug_reg = intel_uncore_read(&dev_priv->uncore, SHOTPLUG_CTL_TC); - intel_uncore_write(&dev_priv->uncore, SHOTPLUG_CTL_TC, dig_hotplug_reg); + dig_hotplug_reg = intel_uncore_rmw(&dev_priv->uncore, SHOTPLUG_CTL_TC, 0, 0); intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, tc_hotplug_trigger, dig_hotplug_reg, @@ -2019,8 +2013,7 @@ static void spt_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir) if (hotplug_trigger) { u32 dig_hotplug_reg; - dig_hotplug_reg = intel_uncore_read(&dev_priv->uncore, PCH_PORT_HOTPLUG); - intel_uncore_write(&dev_priv->uncore, PCH_PORT_HOTPLUG, dig_hotplug_reg); + dig_hotplug_reg = intel_uncore_rmw(&dev_priv->uncore, PCH_PORT_HOTPLUG, 0, 0); intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, hotplug_trigger, dig_hotplug_reg, @@ -2031,8 +2024,7 @@ static void spt_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir) if (hotplug2_trigger) { u32 dig_hotplug_reg; - dig_hotplug_reg = intel_uncore_read(&dev_priv->uncore, PCH_PORT_HOTPLUG2); - intel_uncore_write(&dev_priv->uncore, PCH_PORT_HOTPLUG2, dig_hotplug_reg); + dig_hotplug_reg = intel_uncore_rmw(&dev_priv->uncore, PCH_PORT_HOTPLUG2, 0, 0); intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, hotplug2_trigger, dig_hotplug_reg, @@ -2052,8 +2044,7 @@ static void ilk_hpd_irq_handler(struct drm_i915_private *dev_priv, { u32 dig_hotplug_reg, pin_mask = 0, long_mask = 0; - dig_hotplug_reg = intel_uncore_read(&dev_priv->uncore, DIGITAL_PORT_HOTPLUG_CNTRL); - intel_uncore_write(&dev_priv->uncore, DIGITAL_PORT_HOTPLUG_CNTRL, dig_hotplug_reg); + dig_hotplug_reg = intel_uncore_rmw(&dev_priv->uncore, DIGITAL_PORT_HOTPLUG_CNTRL, 0, 0); intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, hotplug_trigger, dig_hotplug_reg, @@ -2232,8 +2223,7 @@ static void bxt_hpd_irq_handler(struct drm_i915_private *dev_priv, { u32 dig_hotplug_reg, pin_mask = 0, long_mask = 0; - dig_hotplug_reg = intel_uncore_read(&dev_priv->uncore, PCH_PORT_HOTPLUG); - intel_uncore_write(&dev_priv->uncore, PCH_PORT_HOTPLUG, dig_hotplug_reg); + dig_hotplug_reg = intel_uncore_rmw(&dev_priv->uncore, PCH_PORT_HOTPLUG, 0, 0); intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, hotplug_trigger, dig_hotplug_reg, @@ -2252,8 +2242,7 @@ static void gen11_hpd_irq_handler(struct drm_i915_private *dev_priv, u32 iir) if (trigger_tc) { u32 dig_hotplug_reg; - dig_hotplug_reg = intel_uncore_read(&dev_priv->uncore, GEN11_TC_HOTPLUG_CTL); - intel_uncore_write(&dev_priv->uncore, GEN11_TC_HOTPLUG_CTL, dig_hotplug_reg); + dig_hotplug_reg = intel_uncore_rmw(&dev_priv->uncore, GEN11_TC_HOTPLUG_CTL, 0, 0); intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, trigger_tc, dig_hotplug_reg, @@ -2264,8 +2253,7 @@ static void gen11_hpd_irq_handler(struct drm_i915_private *dev_priv, u32 iir) if (trigger_tbt) { u32 dig_hotplug_reg; - dig_hotplug_reg = intel_uncore_read(&dev_priv->uncore, GEN11_TBT_HOTPLUG_CTL); - intel_uncore_write(&dev_priv->uncore, GEN11_TBT_HOTPLUG_CTL, dig_hotplug_reg); + dig_hotplug_reg = intel_uncore_rmw(&dev_priv->uncore, GEN11_TBT_HOTPLUG_CTL, 0, 0); intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, trigger_tbt, dig_hotplug_reg, @@ -2355,8 +2343,7 @@ gen8_de_misc_irq_handler(struct drm_i915_private *dev_priv, u32 iir) else iir_reg = EDP_PSR_IIR; - psr_iir = intel_uncore_read(&dev_priv->uncore, iir_reg); - intel_uncore_write(&dev_priv->uncore, iir_reg, psr_iir); + psr_iir = intel_uncore_rmw(&dev_priv->uncore, iir_reg, 0, 0); if (psr_iir) found = true; @@ -2426,8 +2413,7 @@ static void gen11_dsi_te_interrupt_handler(struct drm_i915_private *dev_priv, /* clear TE in dsi IIR */ port = (te_trigger & DSI1_TE) ? PORT_B : PORT_A; - tmp = intel_uncore_read(&dev_priv->uncore, DSI_INTR_IDENT_REG(port)); - intel_uncore_write(&dev_priv->uncore, DSI_INTR_IDENT_REG(port), tmp); + tmp = intel_uncore_rmw(&dev_priv->uncore, DSI_INTR_IDENT_REG(port), 0, 0); } static u32 gen8_de_pipe_flip_done_mask(struct drm_i915_private *i915) @@ -2791,7 +2777,8 @@ static irqreturn_t dg1_irq_handler(int irq, void *arg) master_ctl = raw_reg_read(regs, GEN11_GFX_MSTR_IRQ); raw_reg_write(regs, GEN11_GFX_MSTR_IRQ, master_ctl); } else { - DRM_ERROR("Tile not supported: 0x%08x\n", master_tile_ctl); + drm_err(&i915->drm, "Tile not supported: 0x%08x\n", + master_tile_ctl); dg1_master_intr_enable(regs); return IRQ_NONE; } @@ -2884,7 +2871,6 @@ static bool gen11_dsi_configure_te(struct intel_crtc *intel_crtc, { struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev); enum port port; - u32 tmp; if (!(intel_crtc->mode_flags & (I915_MODE_FLAG_DSI_USE_TE1 | I915_MODE_FLAG_DSI_USE_TE0))) @@ -2896,16 +2882,10 @@ static bool gen11_dsi_configure_te(struct intel_crtc *intel_crtc, else port = PORT_A; - tmp = intel_uncore_read(&dev_priv->uncore, DSI_INTR_MASK_REG(port)); - if (enable) - tmp &= ~DSI_TE_EVENT; - else - tmp |= DSI_TE_EVENT; - - intel_uncore_write(&dev_priv->uncore, DSI_INTR_MASK_REG(port), tmp); + intel_uncore_rmw(&dev_priv->uncore, DSI_INTR_MASK_REG(port), DSI_TE_EVENT, + enable ? 0 : DSI_TE_EVENT); - tmp = intel_uncore_read(&dev_priv->uncore, DSI_INTR_IDENT_REG(port)); - intel_uncore_write(&dev_priv->uncore, DSI_INTR_IDENT_REG(port), tmp); + intel_uncore_rmw(&dev_priv->uncore, DSI_INTR_IDENT_REG(port), 0, 0); return true; } @@ -3020,7 +3000,7 @@ static void vlv_display_irq_reset(struct drm_i915_private *dev_priv) intel_uncore_write(uncore, DPINVGTT, DPINVGTT_STATUS_MASK_VLV); i915_hotplug_interrupt_update_locked(dev_priv, 0xffffffff, 0); - intel_uncore_write(uncore, PORT_HOTPLUG_STAT, intel_uncore_read(&dev_priv->uncore, PORT_HOTPLUG_STAT)); + intel_uncore_rmw(uncore, PORT_HOTPLUG_STAT, 0, 0); i9xx_pipestat_irq_reset(dev_priv); @@ -3118,7 +3098,7 @@ static void gen8_irq_reset(struct drm_i915_private *dev_priv) { struct intel_uncore *uncore = &dev_priv->uncore; - gen8_master_intr_disable(dev_priv->uncore.regs); + gen8_master_intr_disable(uncore->regs); gen8_gt_irq_reset(to_gt(dev_priv)); gen8_display_irq_reset(dev_priv); @@ -3250,7 +3230,7 @@ static void cherryview_irq_reset(struct drm_i915_private *dev_priv) { struct intel_uncore *uncore = &dev_priv->uncore; - intel_uncore_write(&dev_priv->uncore, GEN8_MASTER_IRQ, 0); + intel_uncore_write(uncore, GEN8_MASTER_IRQ, 0); intel_uncore_posting_read(&dev_priv->uncore, GEN8_MASTER_IRQ); gen8_gt_irq_reset(to_gt(dev_priv)); @@ -3290,23 +3270,20 @@ static u32 ibx_hotplug_enables(struct drm_i915_private *i915, static void ibx_hpd_detection_setup(struct drm_i915_private *dev_priv) { - u32 hotplug; - /* * Enable digital hotplug on the PCH, and configure the DP short pulse * duration to 2ms (which is the minimum in the Display Port spec). * The pulse duration bits are reserved on LPT+. */ - hotplug = intel_uncore_read(&dev_priv->uncore, PCH_PORT_HOTPLUG); - hotplug &= ~(PORTA_HOTPLUG_ENABLE | - PORTB_HOTPLUG_ENABLE | - PORTC_HOTPLUG_ENABLE | - PORTD_HOTPLUG_ENABLE | - PORTB_PULSE_DURATION_MASK | - PORTC_PULSE_DURATION_MASK | - PORTD_PULSE_DURATION_MASK); - hotplug |= intel_hpd_hotplug_enables(dev_priv, ibx_hotplug_enables); - intel_uncore_write(&dev_priv->uncore, PCH_PORT_HOTPLUG, hotplug); + intel_uncore_rmw(&dev_priv->uncore, PCH_PORT_HOTPLUG, + PORTA_HOTPLUG_ENABLE | + PORTB_HOTPLUG_ENABLE | + PORTC_HOTPLUG_ENABLE | + PORTD_HOTPLUG_ENABLE | + PORTB_PULSE_DURATION_MASK | + PORTC_PULSE_DURATION_MASK | + PORTD_PULSE_DURATION_MASK, + intel_hpd_hotplug_enables(dev_priv, ibx_hotplug_enables)); } static void ibx_hpd_irq_setup(struct drm_i915_private *dev_priv) @@ -3353,30 +3330,24 @@ static u32 icp_tc_hotplug_enables(struct drm_i915_private *i915, static void icp_ddi_hpd_detection_setup(struct drm_i915_private *dev_priv) { - u32 hotplug; - - hotplug = intel_uncore_read(&dev_priv->uncore, SHOTPLUG_CTL_DDI); - hotplug &= ~(SHOTPLUG_CTL_DDI_HPD_ENABLE(HPD_PORT_A) | - SHOTPLUG_CTL_DDI_HPD_ENABLE(HPD_PORT_B) | - SHOTPLUG_CTL_DDI_HPD_ENABLE(HPD_PORT_C) | - SHOTPLUG_CTL_DDI_HPD_ENABLE(HPD_PORT_D)); - hotplug |= intel_hpd_hotplug_enables(dev_priv, icp_ddi_hotplug_enables); - intel_uncore_write(&dev_priv->uncore, SHOTPLUG_CTL_DDI, hotplug); + intel_uncore_rmw(&dev_priv->uncore, SHOTPLUG_CTL_DDI, + SHOTPLUG_CTL_DDI_HPD_ENABLE(HPD_PORT_A) | + SHOTPLUG_CTL_DDI_HPD_ENABLE(HPD_PORT_B) | + SHOTPLUG_CTL_DDI_HPD_ENABLE(HPD_PORT_C) | + SHOTPLUG_CTL_DDI_HPD_ENABLE(HPD_PORT_D), + intel_hpd_hotplug_enables(dev_priv, icp_ddi_hotplug_enables)); } static void icp_tc_hpd_detection_setup(struct drm_i915_private *dev_priv) { - u32 hotplug; - - hotplug = intel_uncore_read(&dev_priv->uncore, SHOTPLUG_CTL_TC); - hotplug &= ~(ICP_TC_HPD_ENABLE(HPD_PORT_TC1) | - ICP_TC_HPD_ENABLE(HPD_PORT_TC2) | - ICP_TC_HPD_ENABLE(HPD_PORT_TC3) | - ICP_TC_HPD_ENABLE(HPD_PORT_TC4) | - ICP_TC_HPD_ENABLE(HPD_PORT_TC5) | - ICP_TC_HPD_ENABLE(HPD_PORT_TC6)); - hotplug |= intel_hpd_hotplug_enables(dev_priv, icp_tc_hotplug_enables); - intel_uncore_write(&dev_priv->uncore, SHOTPLUG_CTL_TC, hotplug); + intel_uncore_rmw(&dev_priv->uncore, SHOTPLUG_CTL_TC, + ICP_TC_HPD_ENABLE(HPD_PORT_TC1) | + ICP_TC_HPD_ENABLE(HPD_PORT_TC2) | + ICP_TC_HPD_ENABLE(HPD_PORT_TC3) | + ICP_TC_HPD_ENABLE(HPD_PORT_TC4) | + ICP_TC_HPD_ENABLE(HPD_PORT_TC5) | + ICP_TC_HPD_ENABLE(HPD_PORT_TC6), + intel_hpd_hotplug_enables(dev_priv, icp_tc_hotplug_enables)); } static void icp_hpd_irq_setup(struct drm_i915_private *dev_priv) @@ -3411,62 +3382,54 @@ static u32 gen11_hotplug_enables(struct drm_i915_private *i915, } } -static void dg1_hpd_irq_setup(struct drm_i915_private *dev_priv) +static void dg1_hpd_invert(struct drm_i915_private *i915) { - u32 val; - - val = intel_uncore_read(&dev_priv->uncore, SOUTH_CHICKEN1); - val |= (INVERT_DDIA_HPD | - INVERT_DDIB_HPD | - INVERT_DDIC_HPD | - INVERT_DDID_HPD); - intel_uncore_write(&dev_priv->uncore, SOUTH_CHICKEN1, val); + u32 val = (INVERT_DDIA_HPD | + INVERT_DDIB_HPD | + INVERT_DDIC_HPD | + INVERT_DDID_HPD); + intel_uncore_rmw(&i915->uncore, SOUTH_CHICKEN1, 0, val); +} +static void dg1_hpd_irq_setup(struct drm_i915_private *dev_priv) +{ + dg1_hpd_invert(dev_priv); icp_hpd_irq_setup(dev_priv); } static void gen11_tc_hpd_detection_setup(struct drm_i915_private *dev_priv) { - u32 hotplug; - - hotplug = intel_uncore_read(&dev_priv->uncore, GEN11_TC_HOTPLUG_CTL); - hotplug &= ~(GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC1) | - GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC2) | - GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC3) | - GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC4) | - GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC5) | - GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC6)); - hotplug |= intel_hpd_hotplug_enables(dev_priv, gen11_hotplug_enables); - intel_uncore_write(&dev_priv->uncore, GEN11_TC_HOTPLUG_CTL, hotplug); + intel_uncore_rmw(&dev_priv->uncore, GEN11_TC_HOTPLUG_CTL, + GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC1) | + GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC2) | + GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC3) | + GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC4) | + GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC5) | + GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC6), + intel_hpd_hotplug_enables(dev_priv, gen11_hotplug_enables)); } static void gen11_tbt_hpd_detection_setup(struct drm_i915_private *dev_priv) { - u32 hotplug; - - hotplug = intel_uncore_read(&dev_priv->uncore, GEN11_TBT_HOTPLUG_CTL); - hotplug &= ~(GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC1) | - GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC2) | - GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC3) | - GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC4) | - GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC5) | - GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC6)); - hotplug |= intel_hpd_hotplug_enables(dev_priv, gen11_hotplug_enables); - intel_uncore_write(&dev_priv->uncore, GEN11_TBT_HOTPLUG_CTL, hotplug); + intel_uncore_rmw(&dev_priv->uncore, GEN11_TBT_HOTPLUG_CTL, + GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC1) | + GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC2) | + GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC3) | + GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC4) | + GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC5) | + GEN11_HOTPLUG_CTL_ENABLE(HPD_PORT_TC6), + intel_hpd_hotplug_enables(dev_priv, gen11_hotplug_enables)); } static void gen11_hpd_irq_setup(struct drm_i915_private *dev_priv) { u32 hotplug_irqs, enabled_irqs; - u32 val; enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->display.hotplug.hpd); hotplug_irqs = intel_hpd_hotplug_irqs(dev_priv, dev_priv->display.hotplug.hpd); - val = intel_uncore_read(&dev_priv->uncore, GEN11_DE_HPD_IMR); - val &= ~hotplug_irqs; - val |= ~enabled_irqs & hotplug_irqs; - intel_uncore_write(&dev_priv->uncore, GEN11_DE_HPD_IMR, val); + intel_uncore_rmw(&dev_priv->uncore, GEN11_DE_HPD_IMR, hotplug_irqs, + ~enabled_irqs & hotplug_irqs); intel_uncore_posting_read(&dev_priv->uncore, GEN11_DE_HPD_IMR); gen11_tc_hpd_detection_setup(dev_priv); @@ -3506,29 +3469,22 @@ static u32 spt_hotplug2_enables(struct drm_i915_private *i915, static void spt_hpd_detection_setup(struct drm_i915_private *dev_priv) { - u32 val, hotplug; - /* Display WA #1179 WaHardHangonHotPlug: cnp */ if (HAS_PCH_CNP(dev_priv)) { - val = intel_uncore_read(&dev_priv->uncore, SOUTH_CHICKEN1); - val &= ~CHASSIS_CLK_REQ_DURATION_MASK; - val |= CHASSIS_CLK_REQ_DURATION(0xf); - intel_uncore_write(&dev_priv->uncore, SOUTH_CHICKEN1, val); + intel_uncore_rmw(&dev_priv->uncore, SOUTH_CHICKEN1, CHASSIS_CLK_REQ_DURATION_MASK, + CHASSIS_CLK_REQ_DURATION(0xf)); } /* Enable digital hotplug on the PCH */ - hotplug = intel_uncore_read(&dev_priv->uncore, PCH_PORT_HOTPLUG); - hotplug &= ~(PORTA_HOTPLUG_ENABLE | - PORTB_HOTPLUG_ENABLE | - PORTC_HOTPLUG_ENABLE | - PORTD_HOTPLUG_ENABLE); - hotplug |= intel_hpd_hotplug_enables(dev_priv, spt_hotplug_enables); - intel_uncore_write(&dev_priv->uncore, PCH_PORT_HOTPLUG, hotplug); + intel_uncore_rmw(&dev_priv->uncore, PCH_PORT_HOTPLUG, + PORTA_HOTPLUG_ENABLE | + PORTB_HOTPLUG_ENABLE | + PORTC_HOTPLUG_ENABLE | + PORTD_HOTPLUG_ENABLE, + intel_hpd_hotplug_enables(dev_priv, spt_hotplug_enables)); - hotplug = intel_uncore_read(&dev_priv->uncore, PCH_PORT_HOTPLUG2); - hotplug &= ~PORTE_HOTPLUG_ENABLE; - hotplug |= intel_hpd_hotplug_enables(dev_priv, spt_hotplug2_enables); - intel_uncore_write(&dev_priv->uncore, PCH_PORT_HOTPLUG2, hotplug); + intel_uncore_rmw(&dev_priv->uncore, PCH_PORT_HOTPLUG2, PORTE_HOTPLUG_ENABLE, + intel_hpd_hotplug_enables(dev_priv, spt_hotplug2_enables)); } static void spt_hpd_irq_setup(struct drm_i915_private *dev_priv) @@ -3560,18 +3516,14 @@ static u32 ilk_hotplug_enables(struct drm_i915_private *i915, static void ilk_hpd_detection_setup(struct drm_i915_private *dev_priv) { - u32 hotplug; - /* * Enable digital hotplug on the CPU, and configure the DP short pulse * duration to 2ms (which is the minimum in the Display Port spec) * The pulse duration bits are reserved on HSW+. */ - hotplug = intel_uncore_read(&dev_priv->uncore, DIGITAL_PORT_HOTPLUG_CNTRL); - hotplug &= ~(DIGITAL_PORTA_HOTPLUG_ENABLE | - DIGITAL_PORTA_PULSE_DURATION_MASK); - hotplug |= intel_hpd_hotplug_enables(dev_priv, ilk_hotplug_enables); - intel_uncore_write(&dev_priv->uncore, DIGITAL_PORT_HOTPLUG_CNTRL, hotplug); + intel_uncore_rmw(&dev_priv->uncore, DIGITAL_PORT_HOTPLUG_CNTRL, + DIGITAL_PORTA_HOTPLUG_ENABLE | DIGITAL_PORTA_PULSE_DURATION_MASK, + intel_hpd_hotplug_enables(dev_priv, ilk_hotplug_enables)); } static void ilk_hpd_irq_setup(struct drm_i915_private *dev_priv) @@ -3619,17 +3571,12 @@ static u32 bxt_hotplug_enables(struct drm_i915_private *i915, static void bxt_hpd_detection_setup(struct drm_i915_private *dev_priv) { - u32 hotplug; - - hotplug = intel_uncore_read(&dev_priv->uncore, PCH_PORT_HOTPLUG); - hotplug &= ~(PORTA_HOTPLUG_ENABLE | - PORTB_HOTPLUG_ENABLE | - PORTC_HOTPLUG_ENABLE | - BXT_DDIA_HPD_INVERT | - BXT_DDIB_HPD_INVERT | - BXT_DDIC_HPD_INVERT); - hotplug |= intel_hpd_hotplug_enables(dev_priv, bxt_hotplug_enables); - intel_uncore_write(&dev_priv->uncore, PCH_PORT_HOTPLUG, hotplug); + intel_uncore_rmw(&dev_priv->uncore, PCH_PORT_HOTPLUG, + PORTA_HOTPLUG_ENABLE | + PORTB_HOTPLUG_ENABLE | + PORTC_HOTPLUG_ENABLE | + BXT_DDI_HPD_INVERT_MASK, + intel_hpd_hotplug_enables(dev_priv, bxt_hotplug_enables)); } static void bxt_hpd_irq_setup(struct drm_i915_private *dev_priv) @@ -3928,7 +3875,7 @@ static void i8xx_irq_reset(struct drm_i915_private *dev_priv) i9xx_pipestat_irq_reset(dev_priv); - GEN2_IRQ_RESET(uncore); + gen2_irq_reset(uncore); dev_priv->irq_mask = ~0u; } @@ -3954,7 +3901,7 @@ static void i8xx_irq_postinstall(struct drm_i915_private *dev_priv) I915_MASTER_ERROR_INTERRUPT | I915_USER_INTERRUPT; - GEN2_IRQ_INIT(uncore, dev_priv->irq_mask, enable_mask); + gen2_irq_init(uncore, dev_priv->irq_mask, enable_mask); /* Interrupt setup is already guaranteed to be single-threaded, this is * just to make the assert_spin_locked check happy. */ @@ -3997,7 +3944,7 @@ static void i8xx_error_irq_ack(struct drm_i915_private *i915, static void i8xx_error_irq_handler(struct drm_i915_private *dev_priv, u16 eir, u16 eir_stuck) { - DRM_DEBUG("Master Error: EIR 0x%04x\n", eir); + drm_dbg(&dev_priv->drm, "Master Error: EIR 0x%04x\n", eir); if (eir_stuck) drm_dbg(&dev_priv->drm, "EIR stuck: 0x%04x, masked\n", @@ -4009,9 +3956,7 @@ static void i9xx_error_irq_ack(struct drm_i915_private *dev_priv, { u32 emr; - *eir = intel_uncore_read(&dev_priv->uncore, EIR); - - intel_uncore_write(&dev_priv->uncore, EIR, *eir); + *eir = intel_uncore_rmw(&dev_priv->uncore, EIR, 0, 0); *eir_stuck = intel_uncore_read(&dev_priv->uncore, EIR); if (*eir_stuck == 0) @@ -4027,15 +3972,14 @@ static void i9xx_error_irq_ack(struct drm_i915_private *dev_priv, * (or by a GPU reset) so we mask any bit that * remains set. */ - emr = intel_uncore_read(&dev_priv->uncore, EMR); - intel_uncore_write(&dev_priv->uncore, EMR, 0xffffffff); + emr = intel_uncore_rmw(&dev_priv->uncore, EMR, ~0, 0xffffffff); intel_uncore_write(&dev_priv->uncore, EMR, emr | *eir_stuck); } static void i9xx_error_irq_handler(struct drm_i915_private *dev_priv, u32 eir, u32 eir_stuck) { - DRM_DEBUG("Master Error, EIR 0x%08x\n", eir); + drm_dbg(&dev_priv->drm, "Master Error, EIR 0x%08x\n", eir); if (eir_stuck) drm_dbg(&dev_priv->drm, "EIR stuck: 0x%08x, masked\n", @@ -4095,7 +4039,7 @@ static void i915_irq_reset(struct drm_i915_private *dev_priv) if (I915_HAS_HOTPLUG(dev_priv)) { i915_hotplug_interrupt_update(dev_priv, 0xffffffff, 0); - intel_uncore_write(&dev_priv->uncore, PORT_HOTPLUG_STAT, intel_uncore_read(&dev_priv->uncore, PORT_HOTPLUG_STAT)); + intel_uncore_rmw(&dev_priv->uncore, PORT_HOTPLUG_STAT, 0, 0); } i9xx_pipestat_irq_reset(dev_priv); @@ -4109,8 +4053,8 @@ static void i915_irq_postinstall(struct drm_i915_private *dev_priv) struct intel_uncore *uncore = &dev_priv->uncore; u32 enable_mask; - intel_uncore_write(&dev_priv->uncore, EMR, ~(I915_ERROR_PAGE_TABLE | - I915_ERROR_MEMORY_REFRESH)); + intel_uncore_write(uncore, EMR, ~(I915_ERROR_PAGE_TABLE | + I915_ERROR_MEMORY_REFRESH)); /* Unmask the interrupts that we always want on. */ dev_priv->irq_mask = @@ -4205,7 +4149,7 @@ static void i965_irq_reset(struct drm_i915_private *dev_priv) struct intel_uncore *uncore = &dev_priv->uncore; i915_hotplug_interrupt_update(dev_priv, 0xffffffff, 0); - intel_uncore_write(&dev_priv->uncore, PORT_HOTPLUG_STAT, intel_uncore_read(&dev_priv->uncore, PORT_HOTPLUG_STAT)); + intel_uncore_rmw(uncore, PORT_HOTPLUG_STAT, 0, 0); i9xx_pipestat_irq_reset(dev_priv); @@ -4232,7 +4176,7 @@ static void i965_irq_postinstall(struct drm_i915_private *dev_priv) error_mask = ~(I915_ERROR_PAGE_TABLE | I915_ERROR_MEMORY_REFRESH); } - intel_uncore_write(&dev_priv->uncore, EMR, error_mask); + intel_uncore_write(uncore, EMR, error_mask); /* Unmask the interrupts that we always want on. */ dev_priv->irq_mask = @@ -4383,7 +4327,6 @@ void intel_hpd_irq_setup(struct drm_i915_private *i915) */ void intel_irq_init(struct drm_i915_private *dev_priv) { - struct drm_device *dev = &dev_priv->drm; int i; INIT_WORK(&dev_priv->l3_parity.error_work, ivb_parity_work); @@ -4399,9 +4342,9 @@ void intel_irq_init(struct drm_i915_private *dev_priv) intel_hpd_init_pins(dev_priv); - intel_hpd_init_work(dev_priv); + intel_hpd_init_early(dev_priv); - dev->vblank_disable_immediate = true; + dev_priv->drm.vblank_disable_immediate = true; /* Most platforms treat the display irq block as an always-on * power domain. vlv/chv can disable it at runtime and need @@ -4413,15 +4356,6 @@ void intel_irq_init(struct drm_i915_private *dev_priv) if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) dev_priv->display_irqs_enabled = false; - dev_priv->display.hotplug.hpd_storm_threshold = HPD_STORM_DEFAULT_THRESHOLD; - /* If we have MST support, we want to avoid doing short HPD IRQ storm - * detection, as short HPD storms will occur as a natural part of - * sideband messaging with MST. - * On older platforms however, IRQ storms can occur with both long and - * short pulses, as seen on some G4x systems. - */ - dev_priv->display.hotplug.hpd_short_storm_enabled = !HAS_DP_MST(dev_priv); - if (HAS_GMCH(dev_priv)) { if (I915_HAS_HOTPLUG(dev_priv)) dev_priv->display.funcs.hotplug = &i915_hpd_funcs; diff --git a/drivers/gpu/drm/i915/i915_irq.h b/drivers/gpu/drm/i915/i915_irq.h index 82639d9d7e82..9b004fc3444e 100644 --- a/drivers/gpu/drm/i915/i915_irq.h +++ b/drivers/gpu/drm/i915/i915_irq.h @@ -90,12 +90,9 @@ void i965_disable_vblank(struct drm_crtc *crtc); void ilk_disable_vblank(struct drm_crtc *crtc); void bdw_disable_vblank(struct drm_crtc *crtc); -void gen2_irq_reset(struct intel_uncore *uncore); void gen3_irq_reset(struct intel_uncore *uncore, i915_reg_t imr, i915_reg_t iir, i915_reg_t ier); -void gen2_irq_init(struct intel_uncore *uncore, - u32 imr_val, u32 ier_val); void gen3_irq_init(struct intel_uncore *uncore, i915_reg_t imr, u32 imr_val, i915_reg_t ier, u32 ier_val, @@ -111,9 +108,6 @@ void gen3_irq_init(struct intel_uncore *uncore, #define GEN3_IRQ_RESET(uncore, type) \ gen3_irq_reset((uncore), type##IMR, type##IIR, type##IER) -#define GEN2_IRQ_RESET(uncore) \ - gen2_irq_reset(uncore) - #define GEN8_IRQ_INIT_NDX(uncore, type, which, imr_val, ier_val) \ ({ \ unsigned int which_ = which; \ @@ -129,7 +123,4 @@ void gen3_irq_init(struct intel_uncore *uncore, type##IER, ier_val, \ type##IIR) -#define GEN2_IRQ_INIT(uncore, imr_val, ier_val) \ - gen2_irq_init((uncore), imr_val, ier_val) - #endif /* __I915_IRQ_H__ */ diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index cd4487a1d3be..ccd1f864aa19 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -1023,6 +1023,8 @@ static const struct intel_device_info adl_p_info = { .has_logical_ring_contexts = 1, \ .has_logical_ring_elsq = 1, \ .has_mslice_steering = 1, \ + .has_oa_bpc_reporting = 1, \ + .has_oa_slice_contrib_limits = 1, \ .has_rc6 = 1, \ .has_reset_engine = 1, \ .has_rps = 1, \ @@ -1042,7 +1044,6 @@ static const struct intel_device_info xehpsdv_info = { PLATFORM(INTEL_XEHPSDV), NO_DISPLAY, .has_64k_pages = 1, - .needs_compact_pt = 1, .has_media_ratio_mode = 1, .__runtime.platform_engine_mask = BIT(RCS0) | BIT(BCS0) | @@ -1064,8 +1065,8 @@ static const struct intel_device_info xehpsdv_info = { .has_64k_pages = 1, \ .has_guc_deprivilege = 1, \ .has_heci_pxp = 1, \ - .needs_compact_pt = 1, \ .has_media_ratio_mode = 1, \ + .display.has_cdclk_squash = 1, \ .__runtime.platform_engine_mask = \ BIT(RCS0) | BIT(BCS0) | \ BIT(VECS0) | BIT(VECS1) | \ @@ -1077,7 +1078,6 @@ static const struct intel_device_info dg2_info = { XE_LPD_FEATURES, .__runtime.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | BIT(TRANSCODER_C) | BIT(TRANSCODER_D), - .require_force_probe = 1, }; static const struct intel_device_info ats_m_info = { @@ -1129,7 +1129,6 @@ static const struct intel_gt_definition xelpmp_extra_gt[] = { {} }; -__maybe_unused static const struct intel_device_info mtl_info = { XE_HP_FEATURES, XE_LPDP_FEATURES, @@ -1144,6 +1143,9 @@ static const struct intel_device_info mtl_info = { .display.has_modular_fia = 1, .extra_gt_list = xelpmp_extra_gt, .has_flat_ccs = 0, + .has_gmd_id = 1, + .has_guc_deprivilege = 1, + .has_mslice_steering = 0, .has_snoop = 1, .__runtime.memory_regions = REGION_SMEM | REGION_STOLEN_LMEM, .__runtime.platform_engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(CCS0), @@ -1296,9 +1298,7 @@ bool i915_pci_resource_valid(struct pci_dev *pdev, int bar) static bool intel_mmio_bar_valid(struct pci_dev *pdev, struct intel_device_info *intel_info) { - int gttmmaddr_bar = intel_info->__runtime.graphics.ip.ver == 2 ? GEN2_GTTMMADR_BAR : GTTMMADR_BAR; - - return i915_pci_resource_valid(pdev, gttmmaddr_bar); + return i915_pci_resource_valid(pdev, intel_mmio_bar(intel_info->__runtime.graphics.ip.ver)); } static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 0defbb43ceea..125b6ca25a75 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -204,15 +204,18 @@ #include "gt/intel_gpu_commands.h" #include "gt/intel_gt.h" #include "gt/intel_gt_clock_utils.h" +#include "gt/intel_gt_mcr.h" #include "gt/intel_gt_regs.h" #include "gt/intel_lrc.h" #include "gt/intel_lrc_reg.h" #include "gt/intel_ring.h" +#include "gt/uc/intel_guc_slpc.h" #include "i915_drv.h" #include "i915_file_private.h" #include "i915_perf.h" #include "i915_perf_oa_regs.h" +#include "i915_reg.h" /* HW requires this to be a power of two, between 128k and 16M, though driver * is currently generally designed assuming the largest 16M size is used such @@ -286,6 +289,7 @@ static u32 i915_perf_stream_paranoid = true; #define OAREPORT_REASON_CTX_SWITCH (1<<3) #define OAREPORT_REASON_CLK_RATIO (1<<5) +#define HAS_MI_SET_PREDICATE(i915) (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) /* For sysctl proc_dointvec_minmax of i915_oa_max_sample_rate * @@ -320,6 +324,8 @@ static const struct i915_oa_format oa_formats[I915_OA_FORMAT_MAX] = { [I915_OA_FORMAT_A12] = { 0, 64 }, [I915_OA_FORMAT_A12_B8_C8] = { 2, 128 }, [I915_OA_FORMAT_A32u40_A4u32_B8_C8] = { 5, 256 }, + [I915_OAR_FORMAT_A32u40_A4u32_B8_C8] = { 5, 256 }, + [I915_OA_FORMAT_A24u40_A14u32_B8_C8] = { 5, 256 }, }; #define SAMPLE_OA_REPORT (1<<0) @@ -462,7 +468,7 @@ static u32 gen7_oa_hw_tail_read(struct i915_perf_stream *stream) static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream) { u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma); - int report_size = stream->oa_buffer.format_size; + int report_size = stream->oa_buffer.format->size; unsigned long flags; bool pollin; u32 hw_tail; @@ -525,9 +531,9 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream) if (OA_TAKEN(hw_tail, tail) > report_size && __ratelimit(&stream->perf->tail_pointer_race)) - DRM_NOTE("unlanded report(s) head=0x%x " - "tail=0x%x hw_tail=0x%x\n", - head, tail, hw_tail); + drm_notice(&stream->uncore->i915->drm, + "unlanded report(s) head=0x%x tail=0x%x hw_tail=0x%x\n", + head, tail, hw_tail); stream->oa_buffer.tail = gtt_offset + tail; stream->oa_buffer.aging_tail = gtt_offset + hw_tail; @@ -599,7 +605,7 @@ static int append_oa_sample(struct i915_perf_stream *stream, size_t *offset, const u8 *report) { - int report_size = stream->oa_buffer.format_size; + int report_size = stream->oa_buffer.format->size; struct drm_i915_perf_record_header header; header.type = DRM_I915_PERF_RECORD_SAMPLE; @@ -649,14 +655,13 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, size_t *offset) { struct intel_uncore *uncore = stream->uncore; - int report_size = stream->oa_buffer.format_size; + int report_size = stream->oa_buffer.format->size; u8 *oa_buf_base = stream->oa_buffer.vaddr; u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma); u32 mask = (OA_BUFFER_SIZE - 1); size_t start_offset = *offset; unsigned long flags; u32 head, tail; - u32 taken; int ret = 0; if (drm_WARN_ON(&uncore->i915->drm, !stream->enabled)) @@ -692,7 +697,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, for (/* none */; - (taken = OA_TAKEN(tail, head)); + OA_TAKEN(tail, head); head = (head + report_size) & mask) { u8 *report = oa_buf_base + head; u32 *report32 = (void *)report; @@ -774,7 +779,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, * switches since it's not-uncommon for periodic samples to * identify a switch before any 'context switch' report. */ - if (!stream->perf->exclusive_stream->ctx || + if (!stream->ctx || stream->specific_ctx_id == ctx_id || stream->oa_buffer.last_ctx_id == stream->specific_ctx_id || reason & OAREPORT_REASON_CTX_SWITCH) { @@ -783,7 +788,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, * While filtering for a single context we avoid * leaking the IDs of other contexts. */ - if (stream->perf->exclusive_stream->ctx && + if (stream->ctx && stream->specific_ctx_id != ctx_id) { report32[2] = INVALID_CTX_ID; } @@ -943,14 +948,13 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream, size_t *offset) { struct intel_uncore *uncore = stream->uncore; - int report_size = stream->oa_buffer.format_size; + int report_size = stream->oa_buffer.format->size; u8 *oa_buf_base = stream->oa_buffer.vaddr; u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma); u32 mask = (OA_BUFFER_SIZE - 1); size_t start_offset = *offset; unsigned long flags; u32 head, tail; - u32 taken; int ret = 0; if (drm_WARN_ON(&uncore->i915->drm, !stream->enabled)) @@ -984,7 +988,7 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream, for (/* none */; - (taken = OA_TAKEN(tail, head)); + OA_TAKEN(tail, head); head = (head + report_size) & mask) { u8 *report = oa_buf_base + head; u32 *report32 = (void *)report; @@ -1012,7 +1016,8 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream, */ if (report32[0] == 0) { if (__ratelimit(&stream->perf->spurious_report_rs)) - DRM_NOTE("Skipping spurious, invalid OA report\n"); + drm_notice(&uncore->i915->drm, + "Skipping spurious, invalid OA report\n"); continue; } @@ -1233,6 +1238,199 @@ retry: return stream->pinned_ctx; } +static int +__store_reg_to_mem(struct i915_request *rq, i915_reg_t reg, u32 ggtt_offset) +{ + u32 *cs, cmd; + + cmd = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT; + if (GRAPHICS_VER(rq->engine->i915) >= 8) + cmd++; + + cs = intel_ring_begin(rq, 4); + if (IS_ERR(cs)) + return PTR_ERR(cs); + + *cs++ = cmd; + *cs++ = i915_mmio_reg_offset(reg); + *cs++ = ggtt_offset; + *cs++ = 0; + + intel_ring_advance(rq, cs); + + return 0; +} + +static int +__read_reg(struct intel_context *ce, i915_reg_t reg, u32 ggtt_offset) +{ + struct i915_request *rq; + int err; + + rq = i915_request_create(ce); + if (IS_ERR(rq)) + return PTR_ERR(rq); + + i915_request_get(rq); + + err = __store_reg_to_mem(rq, reg, ggtt_offset); + + i915_request_add(rq); + if (!err && i915_request_wait(rq, 0, HZ / 2) < 0) + err = -ETIME; + + i915_request_put(rq); + + return err; +} + +static int +gen12_guc_sw_ctx_id(struct intel_context *ce, u32 *ctx_id) +{ + struct i915_vma *scratch; + u32 *val; + int err; + + scratch = __vm_create_scratch_for_read_pinned(&ce->engine->gt->ggtt->vm, 4); + if (IS_ERR(scratch)) + return PTR_ERR(scratch); + + err = i915_vma_sync(scratch); + if (err) + goto err_scratch; + + err = __read_reg(ce, RING_EXECLIST_STATUS_HI(ce->engine->mmio_base), + i915_ggtt_offset(scratch)); + if (err) + goto err_scratch; + + val = i915_gem_object_pin_map_unlocked(scratch->obj, I915_MAP_WB); + if (IS_ERR(val)) { + err = PTR_ERR(val); + goto err_scratch; + } + + *ctx_id = *val; + i915_gem_object_unpin_map(scratch->obj); + +err_scratch: + i915_vma_unpin_and_release(&scratch, 0); + return err; +} + +/* + * For execlist mode of submission, pick an unused context id + * 0 - (NUM_CONTEXT_TAG -1) are used by other contexts + * XXX_MAX_CONTEXT_HW_ID is used by idle context + * + * For GuC mode of submission read context id from the upper dword of the + * EXECLIST_STATUS register. Note that we read this value only once and expect + * that the value stays fixed for the entire OA use case. There are cases where + * GuC KMD implementation may deregister a context to reuse it's context id, but + * we prevent that from happening to the OA context by pinning it. + */ +static int gen12_get_render_context_id(struct i915_perf_stream *stream) +{ + u32 ctx_id, mask; + int ret; + + if (intel_engine_uses_guc(stream->engine)) { + ret = gen12_guc_sw_ctx_id(stream->pinned_ctx, &ctx_id); + if (ret) + return ret; + + mask = ((1U << GEN12_GUC_SW_CTX_ID_WIDTH) - 1) << + (GEN12_GUC_SW_CTX_ID_SHIFT - 32); + } else if (GRAPHICS_VER_FULL(stream->engine->i915) >= IP_VER(12, 50)) { + ctx_id = (XEHP_MAX_CONTEXT_HW_ID - 1) << + (XEHP_SW_CTX_ID_SHIFT - 32); + + mask = ((1U << XEHP_SW_CTX_ID_WIDTH) - 1) << + (XEHP_SW_CTX_ID_SHIFT - 32); + } else { + ctx_id = (GEN12_MAX_CONTEXT_HW_ID - 1) << + (GEN11_SW_CTX_ID_SHIFT - 32); + + mask = ((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << + (GEN11_SW_CTX_ID_SHIFT - 32); + } + stream->specific_ctx_id = ctx_id & mask; + stream->specific_ctx_id_mask = mask; + + return 0; +} + +static bool oa_find_reg_in_lri(u32 *state, u32 reg, u32 *offset, u32 end) +{ + u32 idx = *offset; + u32 len = min(MI_LRI_LEN(state[idx]) + idx, end); + bool found = false; + + idx++; + for (; idx < len; idx += 2) { + if (state[idx] == reg) { + found = true; + break; + } + } + + *offset = idx; + return found; +} + +static u32 oa_context_image_offset(struct intel_context *ce, u32 reg) +{ + u32 offset, len = (ce->engine->context_size - PAGE_SIZE) / 4; + u32 *state = ce->lrc_reg_state; + + if (drm_WARN_ON(&ce->engine->i915->drm, !state)) + return U32_MAX; + + for (offset = 0; offset < len; ) { + if (IS_MI_LRI_CMD(state[offset])) { + /* + * We expect reg-value pairs in MI_LRI command, so + * MI_LRI_LEN() should be even, if not, issue a warning. + */ + drm_WARN_ON(&ce->engine->i915->drm, + MI_LRI_LEN(state[offset]) & 0x1); + + if (oa_find_reg_in_lri(state, reg, &offset, len)) + break; + } else { + offset++; + } + } + + return offset < len ? offset : U32_MAX; +} + +static int set_oa_ctx_ctrl_offset(struct intel_context *ce) +{ + i915_reg_t reg = GEN12_OACTXCONTROL(ce->engine->mmio_base); + struct i915_perf *perf = &ce->engine->i915->perf; + u32 offset = perf->ctx_oactxctrl_offset; + + /* Do this only once. Failure is stored as offset of U32_MAX */ + if (offset) + goto exit; + + offset = oa_context_image_offset(ce, i915_mmio_reg_offset(reg)); + perf->ctx_oactxctrl_offset = offset; + + drm_dbg(&ce->engine->i915->drm, + "%s oa ctx control at 0x%08x dword offset\n", + ce->engine->name, offset); + +exit: + return offset && offset != U32_MAX ? 0 : -ENODEV; +} + +static bool engine_supports_mi_query(struct intel_engine_cs *engine) +{ + return engine->class == RENDER_CLASS; +} + /** * oa_get_render_ctx_id - determine and hold ctx hw id * @stream: An i915-perf stream opened for OA metrics @@ -1246,11 +1444,28 @@ retry: static int oa_get_render_ctx_id(struct i915_perf_stream *stream) { struct intel_context *ce; + int ret = 0; ce = oa_pin_context(stream); if (IS_ERR(ce)) return PTR_ERR(ce); + if (engine_supports_mi_query(stream->engine) && + HAS_LOGICAL_RING_CONTEXTS(stream->perf->i915)) { + /* + * We are enabling perf query here. If we don't find the context + * offset here, just return an error. + */ + ret = set_oa_ctx_ctrl_offset(ce); + if (ret) { + intel_context_unpin(ce); + drm_err(&stream->perf->i915->drm, + "Enabling perf query failed for %s\n", + stream->engine->name); + return ret; + } + } + switch (GRAPHICS_VER(ce->engine->i915)) { case 7: { /* @@ -1292,24 +1507,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream) case 11: case 12: - if (GRAPHICS_VER_FULL(ce->engine->i915) >= IP_VER(12, 50)) { - stream->specific_ctx_id_mask = - ((1U << XEHP_SW_CTX_ID_WIDTH) - 1) << - (XEHP_SW_CTX_ID_SHIFT - 32); - stream->specific_ctx_id = - (XEHP_MAX_CONTEXT_HW_ID - 1) << - (XEHP_SW_CTX_ID_SHIFT - 32); - } else { - stream->specific_ctx_id_mask = - ((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32); - /* - * Pick an unused context id - * 0 - BITS_PER_LONG are used by other contexts - * GEN12_MAX_CONTEXT_HW_ID (0x7ff) is used by idle context - */ - stream->specific_ctx_id = - (GEN12_MAX_CONTEXT_HW_ID - 1) << (GEN11_SW_CTX_ID_SHIFT - 32); - } + ret = gen12_get_render_context_id(stream); break; default: @@ -1323,7 +1521,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream) stream->specific_ctx_id, stream->specific_ctx_id_mask); - return 0; + return ret; } /** @@ -1375,8 +1573,9 @@ free_noa_wait(struct i915_perf_stream *stream) static void i915_oa_stream_destroy(struct i915_perf_stream *stream) { struct i915_perf *perf = stream->perf; + struct intel_gt *gt = stream->engine->gt; - if (WARN_ON(stream != perf->exclusive_stream)) + if (WARN_ON(stream != gt->perf.exclusive_stream)) return; /* @@ -1385,11 +1584,20 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream) * * See i915_oa_init_reg_state() and lrc_configure_all_contexts() */ - WRITE_ONCE(perf->exclusive_stream, NULL); + WRITE_ONCE(gt->perf.exclusive_stream, NULL); perf->ops.disable_metric_set(stream); free_oa_buffer(stream); + /* + * Wa_16011777198:dg2: Unset the override of GUCRC mode to enable rc6. + */ + if (intel_uc_uses_guc_rc(>->uc) && + (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_C0) || + IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_B0))) + drm_WARN_ON(>->i915->drm, + intel_guc_slpc_unset_gucrc_mode(>->uc.guc.slpc)); + intel_uncore_forcewake_put(stream->uncore, FORCEWAKE_ALL); intel_engine_pm_put(stream->engine); @@ -1400,8 +1608,9 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream) free_noa_wait(stream); if (perf->spurious_report_rs.missed) { - DRM_NOTE("%d spurious OA report notices suppressed due to ratelimiting\n", - perf->spurious_report_rs.missed); + drm_notice(>->i915->drm, + "%d spurious OA report notices suppressed due to ratelimiting\n", + perf->spurious_report_rs.missed); } } @@ -1563,6 +1772,7 @@ static void gen12_init_oa_buffer(struct i915_perf_stream *stream) static int alloc_oa_buffer(struct i915_perf_stream *stream) { struct drm_i915_private *i915 = stream->perf->i915; + struct intel_gt *gt = stream->engine->gt; struct drm_i915_gem_object *bo; struct i915_vma *vma; int ret; @@ -1582,11 +1792,22 @@ static int alloc_oa_buffer(struct i915_perf_stream *stream) i915_gem_object_set_cache_coherency(bo, I915_CACHE_LLC); /* PreHSW required 512K alignment, HSW requires 16M */ - vma = i915_gem_object_ggtt_pin(bo, NULL, 0, SZ_16M, 0); + vma = i915_vma_instance(bo, >->ggtt->vm, NULL); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto err_unref; } + + /* + * PreHSW required 512K alignment. + * HSW and onwards, align to requested size of OA buffer. + */ + ret = i915_vma_pin(vma, 0, SZ_16M, PIN_GLOBAL | PIN_HIGH); + if (ret) { + drm_err(>->i915->drm, "Failed to pin OA buffer %d\n", ret); + goto err_unref; + } + stream->oa_buffer.vma = vma; stream->oa_buffer.vaddr = @@ -1636,6 +1857,7 @@ static u32 *save_restore_register(struct i915_perf_stream *stream, u32 *cs, static int alloc_noa_wait(struct i915_perf_stream *stream) { struct drm_i915_private *i915 = stream->perf->i915; + struct intel_gt *gt = stream->engine->gt; struct drm_i915_gem_object *bo; struct i915_vma *vma; const u64 delay_ticks = 0xffffffffffffffff - @@ -1654,6 +1876,9 @@ static int alloc_noa_wait(struct i915_perf_stream *stream) DELTA_TARGET, N_CS_GPR }; + i915_reg_t mi_predicate_result = HAS_MI_SET_PREDICATE(i915) ? + MI_PREDICATE_RESULT_2_ENGINE(base) : + MI_PREDICATE_RESULT_1(RENDER_RING_BASE); bo = i915_gem_object_create_internal(i915, 4096); if (IS_ERR(bo)) { @@ -1673,12 +1898,16 @@ retry: * multiple OA config BOs will have a jump to this address and it * needs to be fixed during the lifetime of the i915/perf stream. */ - vma = i915_gem_object_ggtt_pin_ww(bo, &ww, NULL, 0, 0, PIN_HIGH); + vma = i915_vma_instance(bo, >->ggtt->vm, NULL); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto out_ww; } + ret = i915_vma_pin_ww(vma, &ww, 0, 0, PIN_GLOBAL | PIN_HIGH); + if (ret) + goto out_ww; + batch = cs = i915_gem_object_pin_map(bo, I915_MAP_WB); if (IS_ERR(batch)) { ret = PTR_ERR(batch); @@ -1691,7 +1920,7 @@ retry: stream, cs, true /* save */, CS_GPR(i), INTEL_GT_SCRATCH_FIELD_PERF_CS_GPR + 8 * i, 2); cs = save_restore_register( - stream, cs, true /* save */, MI_PREDICATE_RESULT_1(RENDER_RING_BASE), + stream, cs, true /* save */, mi_predicate_result, INTEL_GT_SCRATCH_FIELD_PERF_PREDICATE_RESULT_1, 1); /* First timestamp snapshot location. */ @@ -1745,7 +1974,10 @@ retry: */ *cs++ = MI_LOAD_REGISTER_REG | (3 - 2); *cs++ = i915_mmio_reg_offset(CS_GPR(JUMP_PREDICATE)); - *cs++ = i915_mmio_reg_offset(MI_PREDICATE_RESULT_1(RENDER_RING_BASE)); + *cs++ = i915_mmio_reg_offset(mi_predicate_result); + + if (HAS_MI_SET_PREDICATE(i915)) + *cs++ = MI_SET_PREDICATE | 1; /* Restart from the beginning if we had timestamps roll over. */ *cs++ = (GRAPHICS_VER(i915) < 8 ? @@ -1755,6 +1987,9 @@ retry: *cs++ = i915_ggtt_offset(vma) + (ts0 - batch) * 4; *cs++ = 0; + if (HAS_MI_SET_PREDICATE(i915)) + *cs++ = MI_SET_PREDICATE; + /* * Now add the diff between to previous timestamps and add it to : * (((1 * << 64) - 1) - delay_ns) @@ -1782,7 +2017,10 @@ retry: */ *cs++ = MI_LOAD_REGISTER_REG | (3 - 2); *cs++ = i915_mmio_reg_offset(CS_GPR(JUMP_PREDICATE)); - *cs++ = i915_mmio_reg_offset(MI_PREDICATE_RESULT_1(RENDER_RING_BASE)); + *cs++ = i915_mmio_reg_offset(mi_predicate_result); + + if (HAS_MI_SET_PREDICATE(i915)) + *cs++ = MI_SET_PREDICATE | 1; /* Predicate the jump. */ *cs++ = (GRAPHICS_VER(i915) < 8 ? @@ -1792,13 +2030,16 @@ retry: *cs++ = i915_ggtt_offset(vma) + (jump - batch) * 4; *cs++ = 0; + if (HAS_MI_SET_PREDICATE(i915)) + *cs++ = MI_SET_PREDICATE; + /* Restore registers. */ for (i = 0; i < N_CS_GPR; i++) cs = save_restore_register( stream, cs, false /* restore */, CS_GPR(i), INTEL_GT_SCRATCH_FIELD_PERF_CS_GPR + 8 * i, 2); cs = save_restore_register( - stream, cs, false /* restore */, MI_PREDICATE_RESULT_1(RENDER_RING_BASE), + stream, cs, false /* restore */, mi_predicate_result, INTEL_GT_SCRATCH_FIELD_PERF_PREDICATE_RESULT_1, 1); /* And return to the ring. */ @@ -2017,9 +2258,7 @@ retry: goto err_add_request; } - err = i915_request_await_object(rq, vma->obj, 0); - if (!err) - err = i915_vma_move_to_active(vma, rq, 0); + err = i915_vma_move_to_active(vma, rq, 0); if (err) goto err_add_request; @@ -2283,11 +2522,12 @@ static int gen12_configure_oar_context(struct i915_perf_stream *stream, { int err; struct intel_context *ce = stream->pinned_ctx; - u32 format = stream->oa_buffer.format; + u32 format = stream->oa_buffer.format->format; + u32 offset = stream->perf->ctx_oactxctrl_offset; struct flex regs_context[] = { { GEN8_OACTXCONTROL, - stream->perf->ctx_oactxctrl_offset + 1, + offset + 1, active ? GEN8_OA_COUNTER_RESUME : 0, }, }; @@ -2312,12 +2552,13 @@ static int gen12_configure_oar_context(struct i915_perf_stream *stream, }, }; - /* Modify the context image of pinned context with regs_context*/ + /* Modify the context image of pinned context with regs_context */ err = intel_context_lock_pinned(ce); if (err) return err; - err = gen8_modify_context(ce, regs_context, ARRAY_SIZE(regs_context)); + err = gen8_modify_context(ce, regs_context, + ARRAY_SIZE(regs_context)); intel_context_unlock_pinned(ce); if (err) return err; @@ -2359,10 +2600,11 @@ oa_configure_all_contexts(struct i915_perf_stream *stream, { struct drm_i915_private *i915 = stream->perf->i915; struct intel_engine_cs *engine; + struct intel_gt *gt = stream->engine->gt; struct i915_gem_context *ctx, *cn; int err; - lockdep_assert_held(&stream->perf->lock); + lockdep_assert_held(>->perf.lock); /* * The OA register config is setup through the context image. This image @@ -2442,6 +2684,7 @@ lrc_configure_all_contexts(struct i915_perf_stream *stream, const struct i915_oa_config *oa_config, struct i915_active *active) { + u32 ctx_oactxctrl = stream->perf->ctx_oactxctrl_offset; /* The MMIO offsets for Flex EU registers aren't contiguous */ const u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset; #define ctx_flexeuN(N) (ctx_flexeu0 + 2 * (N) + 1) @@ -2452,7 +2695,7 @@ lrc_configure_all_contexts(struct i915_perf_stream *stream, }, { GEN8_OACTXCONTROL, - stream->perf->ctx_oactxctrl_offset + 1, + ctx_oactxctrl + 1, }, { EU_PERF_CNTL0, ctx_flexeuN(0) }, { EU_PERF_CNTL1, ctx_flexeuN(1) }, @@ -2540,12 +2783,26 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream, struct i915_active *active) { + struct drm_i915_private *i915 = stream->perf->i915; struct intel_uncore *uncore = stream->uncore; struct i915_oa_config *oa_config = stream->oa_config; bool periodic = stream->periodic; u32 period_exponent = stream->period_exponent; + u32 sqcnt1; int ret; + /* + * Wa_1508761755:xehpsdv, dg2 + * EU NOA signals behave incorrectly if EU clock gating is enabled. + * Disable thread stall DOP gating and EU DOP gating. + */ + if (IS_XEHPSDV(i915) || IS_DG2(i915)) { + intel_gt_mcr_multicast_write(uncore->gt, GEN8_ROW_CHICKEN, + _MASKED_BIT_ENABLE(STALL_DOP_GATING_DISABLE)); + intel_uncore_write(uncore, GEN7_ROW_CHICKEN2, + _MASKED_BIT_ENABLE(GEN12_DISABLE_DOP_GATING)); + } + intel_uncore_write(uncore, GEN12_OAG_OA_DEBUG, /* Disable clk ratio reports, like previous Gens. */ _MASKED_BIT_ENABLE(GEN12_OAG_OA_DEBUG_DISABLE_CLK_RATIO_REPORTS | @@ -2563,6 +2820,16 @@ gen12_enable_metric_set(struct i915_perf_stream *stream, : 0); /* + * Initialize Super Queue Internal Cnt Register + * Set PMON Enable in order to collect valid metrics. + * Enable byets per clock reporting in OA for XEHPSDV onward. + */ + sqcnt1 = GEN12_SQCNT1_PMON_ENABLE | + (HAS_OA_BPC_REPORTING(i915) ? GEN12_SQCNT1_OABPC : 0); + + intel_uncore_rmw(uncore, GEN12_SQCNT1, 0, sqcnt1); + + /* * Update all contexts prior writing the mux configurations as we need * to make sure all slices/subslices are ON before writing to NOA * registers. @@ -2611,6 +2878,19 @@ static void gen11_disable_metric_set(struct i915_perf_stream *stream) static void gen12_disable_metric_set(struct i915_perf_stream *stream) { struct intel_uncore *uncore = stream->uncore; + struct drm_i915_private *i915 = stream->perf->i915; + u32 sqcnt1; + + /* + * Wa_1508761755:xehpsdv, dg2 + * Enable thread stall DOP gating and EU DOP gating. + */ + if (IS_XEHPSDV(i915) || IS_DG2(i915)) { + intel_gt_mcr_multicast_write(uncore->gt, GEN8_ROW_CHICKEN, + _MASKED_BIT_DISABLE(STALL_DOP_GATING_DISABLE)); + intel_uncore_write(uncore, GEN7_ROW_CHICKEN2, + _MASKED_BIT_DISABLE(GEN12_DISABLE_DOP_GATING)); + } /* Reset all contexts' slices/subslices configurations. */ gen12_configure_all_contexts(stream, NULL, NULL); @@ -2621,6 +2901,12 @@ static void gen12_disable_metric_set(struct i915_perf_stream *stream) /* Make sure we disable noa to save power. */ intel_uncore_rmw(uncore, RPM_CONFIG1, GEN10_GT_NOA_ENABLE, 0); + + sqcnt1 = GEN12_SQCNT1_PMON_ENABLE | + (HAS_OA_BPC_REPORTING(i915) ? GEN12_SQCNT1_OABPC : 0); + + /* Reset PMON Enable to save power. */ + intel_uncore_rmw(uncore, GEN12_SQCNT1, sqcnt1, 0); } static void gen7_oa_enable(struct i915_perf_stream *stream) @@ -2630,7 +2916,7 @@ static void gen7_oa_enable(struct i915_perf_stream *stream) u32 ctx_id = stream->specific_ctx_id; bool periodic = stream->periodic; u32 period_exponent = stream->period_exponent; - u32 report_format = stream->oa_buffer.format; + u32 report_format = stream->oa_buffer.format->format; /* * Reset buf pointers so we don't forward reports from before now. @@ -2656,7 +2942,7 @@ static void gen7_oa_enable(struct i915_perf_stream *stream) static void gen8_oa_enable(struct i915_perf_stream *stream) { struct intel_uncore *uncore = stream->uncore; - u32 report_format = stream->oa_buffer.format; + u32 report_format = stream->oa_buffer.format->format; /* * Reset buf pointers so we don't forward reports from before now. @@ -2682,7 +2968,7 @@ static void gen8_oa_enable(struct i915_perf_stream *stream) static void gen12_oa_enable(struct i915_perf_stream *stream) { struct intel_uncore *uncore = stream->uncore; - u32 report_format = stream->oa_buffer.format; + u32 report_format = stream->oa_buffer.format->format; /* * If we don't want OA reports from the OA buffer, then we don't even @@ -2838,6 +3124,30 @@ get_sseu_config(struct intel_sseu *out_sseu, return i915_gem_user_to_context_sseu(engine->gt, drm_sseu, out_sseu); } +/* + * OA timestamp frequency = CS timestamp frequency in most platforms. On some + * platforms OA unit ignores the CTC_SHIFT and the 2 timestamps differ. In such + * cases, return the adjusted CS timestamp frequency to the user. + */ +u32 i915_perf_oa_timestamp_frequency(struct drm_i915_private *i915) +{ + /* Wa_18013179988:dg2 */ + if (IS_DG2(i915)) { + intel_wakeref_t wakeref; + u32 reg, shift; + + with_intel_runtime_pm(to_gt(i915)->uncore->rpm, wakeref) + reg = intel_uncore_read(to_gt(i915)->uncore, RPM_CONFIG0); + + shift = REG_FIELD_GET(GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_MASK, + reg); + + return to_gt(i915)->clock_frequency << (3 - shift); + } + + return to_gt(i915)->clock_frequency; +} + /** * i915_oa_stream_init - validate combined props for OA stream and init * @stream: An i915 perf stream @@ -2862,7 +3172,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, { struct drm_i915_private *i915 = stream->perf->i915; struct i915_perf *perf = stream->perf; - int format_size; + struct intel_gt *gt; int ret; if (!props->engine) { @@ -2870,6 +3180,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, "OA engine not specified\n"); return -EINVAL; } + gt = props->engine->gt; /* * If the sysfs metrics/ directory wasn't registered for some @@ -2900,7 +3211,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, * counter reports and marshal to the appropriate client * we currently only allow exclusive access */ - if (perf->exclusive_stream) { + if (gt->perf.exclusive_stream) { drm_dbg(&stream->perf->i915->drm, "OA unit already in use\n"); return -EBUSY; @@ -2917,20 +3228,15 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, stream->sample_size = sizeof(struct drm_i915_perf_record_header); - format_size = perf->oa_formats[props->oa_format].size; + stream->oa_buffer.format = &perf->oa_formats[props->oa_format]; + if (drm_WARN_ON(&i915->drm, stream->oa_buffer.format->size == 0)) + return -EINVAL; stream->sample_flags = props->sample_flags; - stream->sample_size += format_size; - - stream->oa_buffer.format_size = format_size; - if (drm_WARN_ON(&i915->drm, stream->oa_buffer.format_size == 0)) - return -EINVAL; + stream->sample_size += stream->oa_buffer.format->size; stream->hold_preemption = props->hold_preemption; - stream->oa_buffer.format = - perf->oa_formats[props->oa_format].format; - stream->periodic = props->oa_periodic; if (stream->periodic) stream->period_exponent = props->oa_period_exponent; @@ -2974,14 +3280,31 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, intel_engine_pm_get(stream->engine); intel_uncore_forcewake_get(stream->uncore, FORCEWAKE_ALL); + /* + * Wa_16011777198:dg2: GuC resets render as part of the Wa. This causes + * OA to lose the configuration state. Prevent this by overriding GUCRC + * mode. + */ + if (intel_uc_uses_guc_rc(>->uc) && + (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_C0) || + IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_B0))) { + ret = intel_guc_slpc_override_gucrc_mode(>->uc.guc.slpc, + SLPC_GUCRC_MODE_GUCRC_NO_RC6); + if (ret) { + drm_dbg(&stream->perf->i915->drm, + "Unable to override gucrc mode\n"); + goto err_config; + } + } + ret = alloc_oa_buffer(stream); if (ret) goto err_oa_buf_alloc; stream->ops = &i915_oa_stream_ops; - perf->sseu = props->sseu; - WRITE_ONCE(perf->exclusive_stream, stream); + stream->engine->gt->perf.sseu = props->sseu; + WRITE_ONCE(gt->perf.exclusive_stream, stream); ret = i915_perf_stream_enable_sync(stream); if (ret) { @@ -2999,11 +3322,12 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, stream->poll_check_timer.function = oa_poll_check_timer_cb; init_waitqueue_head(&stream->poll_wq); spin_lock_init(&stream->oa_buffer.ptr_lock); + mutex_init(&stream->lock); return 0; err_enable: - WRITE_ONCE(perf->exclusive_stream, NULL); + WRITE_ONCE(gt->perf.exclusive_stream, NULL); perf->ops.disable_metric_set(stream); free_oa_buffer(stream); @@ -3033,7 +3357,7 @@ void i915_oa_init_reg_state(const struct intel_context *ce, return; /* perf.exclusive_stream serialised by lrc_configure_all_contexts() */ - stream = READ_ONCE(engine->i915->perf.exclusive_stream); + stream = READ_ONCE(engine->gt->perf.exclusive_stream); if (stream && GRAPHICS_VER(stream->perf->i915) < 12) gen8_update_reg_state_unlocked(ce, stream); } @@ -3062,7 +3386,6 @@ static ssize_t i915_perf_read(struct file *file, loff_t *ppos) { struct i915_perf_stream *stream = file->private_data; - struct i915_perf *perf = stream->perf; size_t offset = 0; int ret; @@ -3086,14 +3409,14 @@ static ssize_t i915_perf_read(struct file *file, if (ret) return ret; - mutex_lock(&perf->lock); + mutex_lock(&stream->lock); ret = stream->ops->read(stream, buf, count, &offset); - mutex_unlock(&perf->lock); + mutex_unlock(&stream->lock); } while (!offset && !ret); } else { - mutex_lock(&perf->lock); + mutex_lock(&stream->lock); ret = stream->ops->read(stream, buf, count, &offset); - mutex_unlock(&perf->lock); + mutex_unlock(&stream->lock); } /* We allow the poll checking to sometimes report false positive EPOLLIN @@ -3140,9 +3463,6 @@ static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer) * &i915_perf_stream_ops->poll_wait to call poll_wait() with a wait queue that * will be woken for new stream data. * - * Note: The &perf->lock mutex has been taken to serialize - * with any non-file-operation driver hooks. - * * Returns: any poll events that are ready without sleeping */ static __poll_t i915_perf_poll_locked(struct i915_perf_stream *stream, @@ -3181,12 +3501,11 @@ static __poll_t i915_perf_poll_locked(struct i915_perf_stream *stream, static __poll_t i915_perf_poll(struct file *file, poll_table *wait) { struct i915_perf_stream *stream = file->private_data; - struct i915_perf *perf = stream->perf; __poll_t ret; - mutex_lock(&perf->lock); + mutex_lock(&stream->lock); ret = i915_perf_poll_locked(stream, file, wait); - mutex_unlock(&perf->lock); + mutex_unlock(&stream->lock); return ret; } @@ -3285,9 +3604,6 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream, * @cmd: the ioctl request * @arg: the ioctl data * - * Note: The &perf->lock mutex has been taken to serialize - * with any non-file-operation driver hooks. - * * Returns: zero on success or a negative error code. Returns -EINVAL for * an unknown ioctl request. */ @@ -3325,12 +3641,11 @@ static long i915_perf_ioctl(struct file *file, unsigned long arg) { struct i915_perf_stream *stream = file->private_data; - struct i915_perf *perf = stream->perf; long ret; - mutex_lock(&perf->lock); + mutex_lock(&stream->lock); ret = i915_perf_ioctl_locked(stream, cmd, arg); - mutex_unlock(&perf->lock); + mutex_unlock(&stream->lock); return ret; } @@ -3342,7 +3657,7 @@ static long i915_perf_ioctl(struct file *file, * Frees all resources associated with the given i915 perf @stream, disabling * any associated data capture in the process. * - * Note: The &perf->lock mutex has been taken to serialize + * Note: The >->perf.lock mutex has been taken to serialize * with any non-file-operation driver hooks. */ static void i915_perf_destroy_locked(struct i915_perf_stream *stream) @@ -3374,10 +3689,16 @@ static int i915_perf_release(struct inode *inode, struct file *file) { struct i915_perf_stream *stream = file->private_data; struct i915_perf *perf = stream->perf; + struct intel_gt *gt = stream->engine->gt; - mutex_lock(&perf->lock); + /* + * Within this call, we know that the fd is being closed and we have no + * other user of stream->lock. Use the perf lock to destroy the stream + * here. + */ + mutex_lock(>->perf.lock); i915_perf_destroy_locked(stream); - mutex_unlock(&perf->lock); + mutex_unlock(>->perf.lock); /* Release the reference the perf stream kept on the driver. */ drm_dev_put(&perf->i915->drm); @@ -3410,7 +3731,7 @@ static const struct file_operations fops = { * See i915_perf_ioctl_open() for interface details. * * Implements further stream config validation and stream initialization on - * behalf of i915_perf_open_ioctl() with the &perf->lock mutex + * behalf of i915_perf_open_ioctl() with the >->perf.lock mutex * taken to serialize with any non-file-operation driver hooks. * * Note: at this point the @props have only been validated in isolation and @@ -3565,8 +3886,10 @@ err: static u64 oa_exponent_to_ns(struct i915_perf *perf, int exponent) { - return intel_gt_clock_interval_to_ns(to_gt(perf->i915), - 2ULL << exponent); + u64 nom = (2ULL << exponent) * NSEC_PER_SEC; + u32 den = i915_perf_oa_timestamp_frequency(perf->i915); + + return div_u64(nom + den - 1, den); } static __always_inline bool @@ -3794,7 +4117,7 @@ static int read_properties_unlocked(struct i915_perf *perf, * mutex to avoid an awkward lockdep with mmap_lock. * * Most of the implementation details are handled by - * i915_perf_open_ioctl_locked() after taking the &perf->lock + * i915_perf_open_ioctl_locked() after taking the >->perf.lock * mutex for serializing with any non-file-operation driver hooks. * * Return: A newly opened i915 Perf stream file descriptor or negative @@ -3805,6 +4128,7 @@ int i915_perf_open_ioctl(struct drm_device *dev, void *data, { struct i915_perf *perf = &to_i915(dev)->perf; struct drm_i915_perf_open_param *param = data; + struct intel_gt *gt; struct perf_open_properties props; u32 known_open_flags; int ret; @@ -3831,9 +4155,11 @@ int i915_perf_open_ioctl(struct drm_device *dev, void *data, if (ret) return ret; - mutex_lock(&perf->lock); + gt = props.engine->gt; + + mutex_lock(>->perf.lock); ret = i915_perf_open_ioctl_locked(perf, param, &props, file); - mutex_unlock(&perf->lock); + mutex_unlock(>->perf.lock); return ret; } @@ -3849,6 +4175,7 @@ int i915_perf_open_ioctl(struct drm_device *dev, void *data, void i915_perf_register(struct drm_i915_private *i915) { struct i915_perf *perf = &i915->perf; + struct intel_gt *gt = to_gt(i915); if (!perf->i915) return; @@ -3857,13 +4184,13 @@ void i915_perf_register(struct drm_i915_private *i915) * i915_perf_open_ioctl(); considering that we register after * being exposed to userspace. */ - mutex_lock(&perf->lock); + mutex_lock(>->perf.lock); perf->metrics_kobj = kobject_create_and_add("metrics", &i915->drm.primary->kdev->kobj); - mutex_unlock(&perf->lock); + mutex_unlock(>->perf.lock); } /** @@ -3939,6 +4266,11 @@ static const struct i915_range gen12_oa_b_counters[] = { {} }; +static const struct i915_range xehp_oa_b_counters[] = { + { .start = 0xdc48, .end = 0xdc48 }, /* OAA_ENABLE_REG */ + { .start = 0xdd00, .end = 0xdd48 }, /* OAG_LCE0_0 - OAA_LENABLE_REG */ +}; + static const struct i915_range gen7_oa_mux_regs[] = { { .start = 0x91b8, .end = 0x91cc }, /* OA_PERFCNT[1-2], OA_PERFMATRIX */ { .start = 0x9800, .end = 0x9888 }, /* MICRO_BP0_0 - NOA_WRITE */ @@ -4013,6 +4345,12 @@ static bool gen12_is_valid_b_counter_addr(struct i915_perf *perf, u32 addr) return reg_in_range_table(addr, gen12_oa_b_counters); } +static bool xehp_is_valid_b_counter_addr(struct i915_perf *perf, u32 addr) +{ + return reg_in_range_table(addr, xehp_oa_b_counters) || + reg_in_range_table(addr, gen12_oa_b_counters); +} + static bool gen12_is_valid_mux_addr(struct i915_perf *perf, u32 addr) { return reg_in_range_table(addr, gen12_oa_mux_regs); @@ -4411,11 +4749,47 @@ static void oa_init_supported_formats(struct i915_perf *perf) oa_format_add(perf, I915_OA_FORMAT_C4_B8); break; + case INTEL_DG2: + oa_format_add(perf, I915_OAR_FORMAT_A32u40_A4u32_B8_C8); + oa_format_add(perf, I915_OA_FORMAT_A24u40_A14u32_B8_C8); + break; + default: MISSING_CASE(platform); } } +static void i915_perf_init_info(struct drm_i915_private *i915) +{ + struct i915_perf *perf = &i915->perf; + + switch (GRAPHICS_VER(i915)) { + case 8: + perf->ctx_oactxctrl_offset = 0x120; + perf->ctx_flexeu0_offset = 0x2ce; + perf->gen8_valid_ctx_bit = BIT(25); + break; + case 9: + perf->ctx_oactxctrl_offset = 0x128; + perf->ctx_flexeu0_offset = 0x3de; + perf->gen8_valid_ctx_bit = BIT(16); + break; + case 11: + perf->ctx_oactxctrl_offset = 0x124; + perf->ctx_flexeu0_offset = 0x78e; + perf->gen8_valid_ctx_bit = BIT(16); + break; + case 12: + /* + * Calculate offset at runtime in oa_pin_context for gen12 and + * cache the value in perf->ctx_oactxctrl_offset. + */ + break; + default: + MISSING_CASE(GRAPHICS_VER(i915)); + } +} + /** * i915_perf_init - initialize i915-perf state on module bind * @i915: i915 device instance @@ -4429,12 +4803,6 @@ void i915_perf_init(struct drm_i915_private *i915) { struct i915_perf *perf = &i915->perf; - /* XXX const struct i915_perf_ops! */ - - /* i915_perf is not enabled for DG2 yet */ - if (IS_DG2(i915)) - return; - perf->oa_formats = oa_formats; if (IS_HASWELL(i915)) { perf->ops.is_valid_b_counter_reg = gen7_is_valid_b_counter_addr; @@ -4454,6 +4822,7 @@ void i915_perf_init(struct drm_i915_private *i915) * execlist mode by default. */ perf->ops.read = gen8_oa_read; + i915_perf_init_info(i915); if (IS_GRAPHICS_VER(i915, 8, 9)) { perf->ops.is_valid_b_counter_reg = @@ -4473,18 +4842,6 @@ void i915_perf_init(struct drm_i915_private *i915) perf->ops.enable_metric_set = gen8_enable_metric_set; perf->ops.disable_metric_set = gen8_disable_metric_set; perf->ops.oa_hw_tail_read = gen8_oa_hw_tail_read; - - if (GRAPHICS_VER(i915) == 8) { - perf->ctx_oactxctrl_offset = 0x120; - perf->ctx_flexeu0_offset = 0x2ce; - - perf->gen8_valid_ctx_bit = BIT(25); - } else { - perf->ctx_oactxctrl_offset = 0x128; - perf->ctx_flexeu0_offset = 0x3de; - - perf->gen8_valid_ctx_bit = BIT(16); - } } else if (GRAPHICS_VER(i915) == 11) { perf->ops.is_valid_b_counter_reg = gen7_is_valid_b_counter_addr; @@ -4498,13 +4855,10 @@ void i915_perf_init(struct drm_i915_private *i915) perf->ops.enable_metric_set = gen8_enable_metric_set; perf->ops.disable_metric_set = gen11_disable_metric_set; perf->ops.oa_hw_tail_read = gen8_oa_hw_tail_read; - - perf->ctx_oactxctrl_offset = 0x124; - perf->ctx_flexeu0_offset = 0x78e; - - perf->gen8_valid_ctx_bit = BIT(16); } else if (GRAPHICS_VER(i915) == 12) { perf->ops.is_valid_b_counter_reg = + HAS_OA_SLICE_CONTRIB_LIMITS(i915) ? + xehp_is_valid_b_counter_addr : gen12_is_valid_b_counter_addr; perf->ops.is_valid_mux_reg = gen12_is_valid_mux_addr; @@ -4516,14 +4870,15 @@ void i915_perf_init(struct drm_i915_private *i915) perf->ops.enable_metric_set = gen12_enable_metric_set; perf->ops.disable_metric_set = gen12_disable_metric_set; perf->ops.oa_hw_tail_read = gen12_oa_hw_tail_read; - - perf->ctx_flexeu0_offset = 0; - perf->ctx_oactxctrl_offset = 0x144; } } if (perf->ops.enable_metric_set) { - mutex_init(&perf->lock); + struct intel_gt *gt; + int i; + + for_each_gt(gt, i915, i) + mutex_init(>->perf.lock); /* Choose a representative limit */ oa_sample_rate_hard_limit = to_gt(i915)->clock_frequency / 2; diff --git a/drivers/gpu/drm/i915/i915_perf.h b/drivers/gpu/drm/i915/i915_perf.h index 1d1329e5af3a..f96e09a4af04 100644 --- a/drivers/gpu/drm/i915/i915_perf.h +++ b/drivers/gpu/drm/i915/i915_perf.h @@ -57,4 +57,6 @@ static inline void i915_oa_config_put(struct i915_oa_config *oa_config) kref_put(&oa_config->ref, i915_oa_config_release); } +u32 i915_perf_oa_timestamp_frequency(struct drm_i915_private *i915); + #endif /* __I915_PERF_H__ */ diff --git a/drivers/gpu/drm/i915/i915_perf_oa_regs.h b/drivers/gpu/drm/i915/i915_perf_oa_regs.h index f31c9f13a9fc..381d94101610 100644 --- a/drivers/gpu/drm/i915/i915_perf_oa_regs.h +++ b/drivers/gpu/drm/i915/i915_perf_oa_regs.h @@ -97,7 +97,7 @@ #define GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT 1 #define GEN12_OAR_OACONTROL_COUNTER_ENABLE (1 << 0) -#define GEN12_OACTXCONTROL _MMIO(0x2360) +#define GEN12_OACTXCONTROL(base) _MMIO((base) + 0x360) #define GEN12_OAR_OASTATUS _MMIO(0x2968) /* Gen12 OAG unit */ @@ -134,4 +134,8 @@ #define GDT_CHICKEN_BITS _MMIO(0x9840) #define GT_NOA_ENABLE 0x00000080 +#define GEN12_SQCNT1 _MMIO(0x8718) +#define GEN12_SQCNT1_PMON_ENABLE REG_BIT(30) +#define GEN12_SQCNT1_OABPC REG_BIT(29) + #endif /* __INTEL_PERF_OA_REGS__ */ diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h index 05cb9a335a97..ca150b7af3f2 100644 --- a/drivers/gpu/drm/i915/i915_perf_types.h +++ b/drivers/gpu/drm/i915/i915_perf_types.h @@ -147,6 +147,11 @@ struct i915_perf_stream { struct intel_engine_cs *engine; /** + * @lock: Lock associated with operations on stream + */ + struct mutex lock; + + /** * @sample_flags: Flags representing the `DRM_I915_PERF_PROP_SAMPLE_*` * properties given when opening a stream, representing the contents * of a single sample as read() by userspace. @@ -245,11 +250,10 @@ struct i915_perf_stream { * @oa_buffer: State of the OA buffer. */ struct { + const struct i915_oa_format *format; struct i915_vma *vma; u8 *vaddr; u32 last_ctx_id; - int format; - int format_size; int size_exponent; /** @@ -380,6 +384,26 @@ struct i915_oa_ops { u32 (*oa_hw_tail_read)(struct i915_perf_stream *stream); }; +struct i915_perf_gt { + /* + * Lock associated with anything below within this structure. + */ + struct mutex lock; + + /** + * @sseu: sseu configuration selected to run while perf is active, + * applies to all contexts. + */ + struct intel_sseu sseu; + + /* + * @exclusive_stream: The stream currently using the OA unit. This is + * sometimes accessed outside a syscall associated to its file + * descriptor. + */ + struct i915_perf_stream *exclusive_stream; +}; + struct i915_perf { struct drm_i915_private *i915; @@ -397,25 +421,6 @@ struct i915_perf { */ struct idr metrics_idr; - /* - * Lock associated with anything below within this structure - * except exclusive_stream. - */ - struct mutex lock; - - /* - * The stream currently using the OA unit. If accessed - * outside a syscall associated to its file - * descriptor. - */ - struct i915_perf_stream *exclusive_stream; - - /** - * @sseu: sseu configuration selected to run while perf is active, - * applies to all contexts. - */ - struct intel_sseu sseu; - /** * For rate limiting any notifications of spurious * invalid OA reports diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index 958b37123bf1..52531ab28c5f 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -148,13 +148,13 @@ static u64 __get_rc6(struct intel_gt *gt) struct drm_i915_private *i915 = gt->i915; u64 val; - val = intel_rc6_residency_ns(>->rc6, GEN6_GT_GFX_RC6); + val = intel_rc6_residency_ns(>->rc6, INTEL_RC6_RES_RC6); if (HAS_RC6p(i915)) - val += intel_rc6_residency_ns(>->rc6, GEN6_GT_GFX_RC6p); + val += intel_rc6_residency_ns(>->rc6, INTEL_RC6_RES_RC6p); if (HAS_RC6pp(i915)) - val += intel_rc6_residency_ns(>->rc6, GEN6_GT_GFX_RC6pp); + val += intel_rc6_residency_ns(>->rc6, INTEL_RC6_RES_RC6pp); return val; } @@ -371,7 +371,6 @@ static void frequency_sample(struct intel_gt *gt, unsigned int period_ns) { struct drm_i915_private *i915 = gt->i915; - struct intel_uncore *uncore = gt->uncore; struct i915_pmu *pmu = &i915->pmu; struct intel_rps *rps = >->rps; @@ -394,7 +393,7 @@ frequency_sample(struct intel_gt *gt, unsigned int period_ns) * case we assume the system is running at the intended * frequency. Fortunately, the read should rarely fail! */ - val = intel_uncore_read_fw(uncore, GEN6_RPSTAT1); + val = intel_rps_read_rpstat_fw(rps); if (val) val = intel_rps_get_cagf(rps, val); else diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c index 6ec9c9fb7b0d..00871ef99792 100644 --- a/drivers/gpu/drm/i915/i915_query.c +++ b/drivers/gpu/drm/i915/i915_query.c @@ -250,8 +250,9 @@ static int query_perf_config_data(struct drm_i915_private *i915, return total_size; if (query_item->length < total_size) { - DRM_DEBUG("Invalid query config data item size=%u expected=%u\n", - query_item->length, total_size); + drm_dbg(&i915->drm, + "Invalid query config data item size=%u expected=%u\n", + query_item->length, total_size); return -EINVAL; } @@ -418,9 +419,10 @@ static int query_perf_config_list(struct drm_i915_private *i915, } while (n_configs > alloc); if (query_item->length < sizeof_perf_config_list(n_configs)) { - DRM_DEBUG("Invalid query config list item size=%u expected=%zu\n", - query_item->length, - sizeof_perf_config_list(n_configs)); + drm_dbg(&i915->drm, + "Invalid query config list item size=%u expected=%zu\n", + query_item->length, + sizeof_perf_config_list(n_configs)); kfree(oa_config_ids); return -EINVAL; } diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index da35bb2db26b..916176872544 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -26,6 +26,7 @@ #define _I915_REG_H_ #include "i915_reg_defs.h" +#include "display/intel_display_reg_defs.h" /** * DOC: The i915 register macro definition style guide @@ -115,75 +116,6 @@ * #define GEN8_BAR _MMIO(0xb888) */ -#define DISPLAY_MMIO_BASE(dev_priv) (INTEL_INFO(dev_priv)->display.mmio_offset) - -/* - * Given the first two numbers __a and __b of arbitrarily many evenly spaced - * numbers, pick the 0-based __index'th value. - * - * Always prefer this over _PICK() if the numbers are evenly spaced. - */ -#define _PICK_EVEN(__index, __a, __b) ((__a) + (__index) * ((__b) - (__a))) - -/* - * Given the arbitrary numbers in varargs, pick the 0-based __index'th number. - * - * Always prefer _PICK_EVEN() over this if the numbers are evenly spaced. - */ -#define _PICK(__index, ...) (((const u32 []){ __VA_ARGS__ })[__index]) - -/* - * Named helper wrappers around _PICK_EVEN() and _PICK(). - */ -#define _PIPE(pipe, a, b) _PICK_EVEN(pipe, a, b) -#define _PLANE(plane, a, b) _PICK_EVEN(plane, a, b) -#define _TRANS(tran, a, b) _PICK_EVEN(tran, a, b) -#define _PORT(port, a, b) _PICK_EVEN(port, a, b) -#define _PLL(pll, a, b) _PICK_EVEN(pll, a, b) -#define _PHY(phy, a, b) _PICK_EVEN(phy, a, b) - -#define _MMIO_PIPE(pipe, a, b) _MMIO(_PIPE(pipe, a, b)) -#define _MMIO_PLANE(plane, a, b) _MMIO(_PLANE(plane, a, b)) -#define _MMIO_TRANS(tran, a, b) _MMIO(_TRANS(tran, a, b)) -#define _MMIO_PORT(port, a, b) _MMIO(_PORT(port, a, b)) -#define _MMIO_PLL(pll, a, b) _MMIO(_PLL(pll, a, b)) -#define _MMIO_PHY(phy, a, b) _MMIO(_PHY(phy, a, b)) - -#define _PHY3(phy, ...) _PICK(phy, __VA_ARGS__) - -#define _MMIO_PIPE3(pipe, a, b, c) _MMIO(_PICK(pipe, a, b, c)) -#define _MMIO_PORT3(pipe, a, b, c) _MMIO(_PICK(pipe, a, b, c)) -#define _MMIO_PHY3(phy, a, b, c) _MMIO(_PHY3(phy, a, b, c)) -#define _MMIO_PLL3(pll, ...) _MMIO(_PICK(pll, __VA_ARGS__)) - - -/* - * Device info offset array based helpers for groups of registers with unevenly - * spaced base offsets. - */ -#define _MMIO_PIPE2(pipe, reg) _MMIO(INTEL_INFO(dev_priv)->display.pipe_offsets[(pipe)] - \ - INTEL_INFO(dev_priv)->display.pipe_offsets[PIPE_A] + \ - DISPLAY_MMIO_BASE(dev_priv) + (reg)) -#define _MMIO_TRANS2(tran, reg) _MMIO(INTEL_INFO(dev_priv)->display.trans_offsets[(tran)] - \ - INTEL_INFO(dev_priv)->display.trans_offsets[TRANSCODER_A] + \ - DISPLAY_MMIO_BASE(dev_priv) + (reg)) -#define _MMIO_CURSOR2(pipe, reg) _MMIO(INTEL_INFO(dev_priv)->display.cursor_offsets[(pipe)] - \ - INTEL_INFO(dev_priv)->display.cursor_offsets[PIPE_A] + \ - DISPLAY_MMIO_BASE(dev_priv) + (reg)) - -#define __MASKED_FIELD(mask, value) ((mask) << 16 | (value)) -#define _MASKED_FIELD(mask, value) ({ \ - if (__builtin_constant_p(mask)) \ - BUILD_BUG_ON_MSG(((mask) & 0xffff0000), "Incorrect mask"); \ - if (__builtin_constant_p(value)) \ - BUILD_BUG_ON_MSG((value) & 0xffff0000, "Incorrect value"); \ - if (__builtin_constant_p(mask) && __builtin_constant_p(value)) \ - BUILD_BUG_ON_MSG((value) & ~(mask), \ - "Incorrect value for mask"); \ - __MASKED_FIELD(mask, value); }) -#define _MASKED_BIT_ENABLE(a) ({ typeof(a) _a = (a); _MASKED_FIELD(_a, _a); }) -#define _MASKED_BIT_DISABLE(a) (_MASKED_FIELD((a), 0)) - #define GU_CNTL _MMIO(0x101010) #define LMEM_INIT REG_BIT(7) @@ -970,6 +902,7 @@ #define GEN11_VEBOX2_RING_BASE 0x1d8000 #define XEHP_VEBOX3_RING_BASE 0x1e8000 #define XEHP_VEBOX4_RING_BASE 0x1f8000 +#define MTL_GSC_RING_BASE 0x11a000 #define GEN12_COMPUTE0_RING_BASE 0x1a000 #define GEN12_COMPUTE1_RING_BASE 0x1c000 #define GEN12_COMPUTE2_RING_BASE 0x1e000 @@ -1147,11 +1080,6 @@ #define MBUS_JOIN_PIPE_SELECT(pipe) REG_FIELD_PREP(MBUS_JOIN_PIPE_SELECT_MASK, pipe) #define MBUS_JOIN_PIPE_SELECT_NONE MBUS_JOIN_PIPE_SELECT(7) -#define HDPORT_STATE _MMIO(0x45050) -#define HDPORT_DPLL_USED_MASK REG_GENMASK(15, 12) -#define HDPORT_DDI_USED(phy) REG_BIT(2 * (phy) + 1) -#define HDPORT_ENABLED REG_BIT(0) - /* Make render/texture TLB fetches lower priorty than associated data * fetches. This is not turned on by default */ @@ -1781,9 +1709,10 @@ #define _PALETTE_A 0xa000 #define _PALETTE_B 0xa800 #define _CHV_PALETTE_C 0xc000 -#define PALETTE_RED_MASK REG_GENMASK(23, 16) -#define PALETTE_GREEN_MASK REG_GENMASK(15, 8) -#define PALETTE_BLUE_MASK REG_GENMASK(7, 0) +/* 8bit mode / i965+ 10.6 interpolated mode ldw/udw */ +#define PALETTE_RED_MASK REG_GENMASK(23, 16) +#define PALETTE_GREEN_MASK REG_GENMASK(15, 8) +#define PALETTE_BLUE_MASK REG_GENMASK(7, 0) #define PALETTE(pipe, i) _MMIO(DISPLAY_MMIO_BASE(dev_priv) + \ _PICK((pipe), _PALETTE_A, \ _PALETTE_B, _CHV_PALETTE_C) + \ @@ -1796,6 +1725,15 @@ #define XEHPSDV_RP_STATE_CAP _MMIO(0x250014) #define PVC_RP_STATE_CAP _MMIO(0x281014) +#define MTL_RP_STATE_CAP _MMIO(0x138000) +#define MTL_MEDIAP_STATE_CAP _MMIO(0x138020) +#define MTL_RP0_CAP_MASK REG_GENMASK(8, 0) +#define MTL_RPN_CAP_MASK REG_GENMASK(24, 16) + +#define MTL_GT_RPE_FREQUENCY _MMIO(0x13800c) +#define MTL_MPE_FREQUENCY _MMIO(0x13802c) +#define MTL_RPE_MASK REG_GENMASK(8, 0) + #define GT0_PERF_LIMIT_REASONS _MMIO(0x1381a8) #define GT0_PERF_LIMIT_REASONS_MASK 0xde3 #define PROCHOT_MASK REG_BIT(0) @@ -1806,6 +1744,8 @@ #define POWER_LIMIT_4_MASK REG_BIT(8) #define POWER_LIMIT_1_MASK REG_BIT(10) #define POWER_LIMIT_2_MASK REG_BIT(11) +#define GT0_PERF_LIMIT_REASONS_LOG_MASK REG_GENMASK(31, 16) +#define MTL_MEDIA_PERF_LIMIT_REASONS _MMIO(0x138030) #define CHV_CLK_CTL1 _MMIO(0x101100) #define VLV_CLK_CTL2 _MMIO(0x101104) @@ -3747,9 +3687,10 @@ /* Skylake+ pipe bottom (background) color */ #define _SKL_BOTTOM_COLOR_A 0x70034 +#define _SKL_BOTTOM_COLOR_B 0x71034 #define SKL_BOTTOM_COLOR_GAMMA_ENABLE REG_BIT(31) #define SKL_BOTTOM_COLOR_CSC_ENABLE REG_BIT(30) -#define SKL_BOTTOM_COLOR(pipe) _MMIO_PIPE2(pipe, _SKL_BOTTOM_COLOR_A) +#define SKL_BOTTOM_COLOR(pipe) _MMIO_PIPE(pipe, _SKL_BOTTOM_COLOR_A, _SKL_BOTTOM_COLOR_B) #define _ICL_PIPE_A_STATUS 0x70058 #define ICL_PIPESTATUS(pipe) _MMIO_PIPE2(pipe, _ICL_PIPE_A_STATUS) @@ -5367,17 +5308,24 @@ /* legacy palette */ #define _LGC_PALETTE_A 0x4a000 #define _LGC_PALETTE_B 0x4a800 -#define LGC_PALETTE_RED_MASK REG_GENMASK(23, 16) -#define LGC_PALETTE_GREEN_MASK REG_GENMASK(15, 8) -#define LGC_PALETTE_BLUE_MASK REG_GENMASK(7, 0) +/* see PALETTE_* for the bits */ #define LGC_PALETTE(pipe, i) _MMIO(_PIPE(pipe, _LGC_PALETTE_A, _LGC_PALETTE_B) + (i) * 4) /* ilk/snb precision palette */ #define _PREC_PALETTE_A 0x4b000 #define _PREC_PALETTE_B 0x4c000 -#define PREC_PALETTE_RED_MASK REG_GENMASK(29, 20) -#define PREC_PALETTE_GREEN_MASK REG_GENMASK(19, 10) -#define PREC_PALETTE_BLUE_MASK REG_GENMASK(9, 0) +/* 10bit mode */ +#define PREC_PALETTE_10_RED_MASK REG_GENMASK(29, 20) +#define PREC_PALETTE_10_GREEN_MASK REG_GENMASK(19, 10) +#define PREC_PALETTE_10_BLUE_MASK REG_GENMASK(9, 0) +/* 12.4 interpolated mode ldw */ +#define PREC_PALETTE_12P4_RED_LDW_MASK REG_GENMASK(29, 24) +#define PREC_PALETTE_12P4_GREEN_LDW_MASK REG_GENMASK(19, 14) +#define PREC_PALETTE_12P4_BLUE_LDW_MASK REG_GENMASK(9, 4) +/* 12.4 interpolated mode udw */ +#define PREC_PALETTE_12P4_RED_UDW_MASK REG_GENMASK(29, 20) +#define PREC_PALETTE_12P4_GREEN_UDW_MASK REG_GENMASK(19, 10) +#define PREC_PALETTE_12P4_BLUE_UDW_MASK REG_GENMASK(9, 0) #define PREC_PALETTE(pipe, i) _MMIO(_PIPE(pipe, _PREC_PALETTE_A, _PREC_PALETTE_B) + (i) * 4) #define _PREC_PIPEAGCMAX 0x4d000 @@ -5847,6 +5795,11 @@ #define ICL_DSSM_CDCLK_PLL_REFCLK_19_2MHz (1 << 29) #define ICL_DSSM_CDCLK_PLL_REFCLK_38_4MHz (2 << 29) +#define GMD_ID_DISPLAY _MMIO(0x510a0) +#define GMD_ID_ARCH_MASK REG_GENMASK(31, 22) +#define GMD_ID_RELEASE_MASK REG_GENMASK(21, 14) +#define GMD_ID_STEP REG_GENMASK(5, 0) + /*GEN11 chicken */ #define _PIPEA_CHICKEN 0x70038 #define _PIPEB_CHICKEN 0x71038 @@ -6035,6 +5988,7 @@ #define SHOTPLUG_CTL_DDI _MMIO(0xc4030) #define SHOTPLUG_CTL_DDI_HPD_ENABLE(hpd_pin) (0x8 << (_HPD_PIN_DDI(hpd_pin) * 4)) +#define SHOTPLUG_CTL_DDI_HPD_OUTPUT_DATA(hpd_pin) (0x4 << (_HPD_PIN_DDI(hpd_pin) * 4)) #define SHOTPLUG_CTL_DDI_HPD_STATUS_MASK(hpd_pin) (0x3 << (_HPD_PIN_DDI(hpd_pin) * 4)) #define SHOTPLUG_CTL_DDI_HPD_NO_DETECT(hpd_pin) (0x0 << (_HPD_PIN_DDI(hpd_pin) * 4)) #define SHOTPLUG_CTL_DDI_HPD_SHORT_DETECT(hpd_pin) (0x1 << (_HPD_PIN_DDI(hpd_pin) * 4)) @@ -6647,6 +6601,12 @@ #define DG1_PCODE_STATUS 0x7E #define DG1_UNCORE_GET_INIT_STATUS 0x0 #define DG1_UNCORE_INIT_STATUS_COMPLETE 0x1 +#define PCODE_POWER_SETUP 0x7C +#define POWER_SETUP_SUBCOMMAND_READ_I1 0x4 +#define POWER_SETUP_SUBCOMMAND_WRITE_I1 0x5 +#define POWER_SETUP_I1_WATTS REG_BIT(31) +#define POWER_SETUP_I1_SHIFT 6 /* 10.6 fixed point format */ +#define POWER_SETUP_I1_DATA_MASK REG_GENMASK(15, 0) #define GEN12_PCODE_READ_SAGV_BLOCK_TIME_US 0x23 #define XEHP_PCODE_FREQUENCY_CONFIG 0x6e /* xehpsdv, pvc */ /* XEHP_PCODE_FREQUENCY_CONFIG sub-commands (param1) */ @@ -6656,6 +6616,15 @@ /* XEHP_PCODE_FREQUENCY_CONFIG param2 */ #define PCODE_MBOX_DOMAIN_NONE 0x0 #define PCODE_MBOX_DOMAIN_MEDIAFF 0x3 + +/* Wa_14017210380: mtl */ +#define PCODE_MBOX_GT_STATE 0x50 +/* sub-commands (param1) */ +#define PCODE_MBOX_GT_STATE_MEDIA_BUSY 0x1 +#define PCODE_MBOX_GT_STATE_MEDIA_NOT_BUSY 0x2 +/* param2 */ +#define PCODE_MBOX_GT_STATE_DOMAIN_MEDIA 0x1 + #define GEN6_PCODE_DATA _MMIO(0x138128) #define GEN6_PCODE_FREQ_IA_RATIO_SHIFT 8 #define GEN6_PCODE_FREQ_RING_RATIO_SHIFT 16 @@ -7413,185 +7382,6 @@ enum skl_power_gate { _ADLS_DPLL4_CFGCR1, \ _ADLS_DPLL3_CFGCR1) -#define _DKL_PHY1_BASE 0x168000 -#define _DKL_PHY2_BASE 0x169000 -#define _DKL_PHY3_BASE 0x16A000 -#define _DKL_PHY4_BASE 0x16B000 -#define _DKL_PHY5_BASE 0x16C000 -#define _DKL_PHY6_BASE 0x16D000 - -#define DKL_REG_TC_PORT(__reg) \ - (TC_PORT_1 + ((__reg).reg - _DKL_PHY1_BASE) / (_DKL_PHY2_BASE - _DKL_PHY1_BASE)) - -/* DEKEL PHY MMIO Address = Phy base + (internal address & ~index_mask) */ -#define _DKL_PCS_DW5 0x14 -#define DKL_PCS_DW5(tc_port) _MMIO(_PORT(tc_port, _DKL_PHY1_BASE, \ - _DKL_PHY2_BASE) + \ - _DKL_PCS_DW5) -#define DKL_PCS_DW5_CORE_SOFTRESET REG_BIT(11) - -#define _DKL_PLL_DIV0 0x200 -#define DKL_PLL_DIV0_AFC_STARTUP_MASK REG_GENMASK(27, 25) -#define DKL_PLL_DIV0_AFC_STARTUP(val) REG_FIELD_PREP(DKL_PLL_DIV0_AFC_STARTUP_MASK, (val)) -#define DKL_PLL_DIV0_INTEG_COEFF(x) ((x) << 16) -#define DKL_PLL_DIV0_INTEG_COEFF_MASK (0x1F << 16) -#define DKL_PLL_DIV0_PROP_COEFF(x) ((x) << 12) -#define DKL_PLL_DIV0_PROP_COEFF_MASK (0xF << 12) -#define DKL_PLL_DIV0_FBPREDIV_SHIFT (8) -#define DKL_PLL_DIV0_FBPREDIV(x) ((x) << DKL_PLL_DIV0_FBPREDIV_SHIFT) -#define DKL_PLL_DIV0_FBPREDIV_MASK (0xF << DKL_PLL_DIV0_FBPREDIV_SHIFT) -#define DKL_PLL_DIV0_FBDIV_INT(x) ((x) << 0) -#define DKL_PLL_DIV0_FBDIV_INT_MASK (0xFF << 0) -#define DKL_PLL_DIV0_MASK (DKL_PLL_DIV0_INTEG_COEFF_MASK | \ - DKL_PLL_DIV0_PROP_COEFF_MASK | \ - DKL_PLL_DIV0_FBPREDIV_MASK | \ - DKL_PLL_DIV0_FBDIV_INT_MASK) -#define DKL_PLL_DIV0(tc_port) _MMIO(_PORT(tc_port, _DKL_PHY1_BASE, \ - _DKL_PHY2_BASE) + \ - _DKL_PLL_DIV0) - -#define _DKL_PLL_DIV1 0x204 -#define DKL_PLL_DIV1_IREF_TRIM(x) ((x) << 16) -#define DKL_PLL_DIV1_IREF_TRIM_MASK (0x1F << 16) -#define DKL_PLL_DIV1_TDC_TARGET_CNT(x) ((x) << 0) -#define DKL_PLL_DIV1_TDC_TARGET_CNT_MASK (0xFF << 0) -#define DKL_PLL_DIV1(tc_port) _MMIO(_PORT(tc_port, _DKL_PHY1_BASE, \ - _DKL_PHY2_BASE) + \ - _DKL_PLL_DIV1) - -#define _DKL_PLL_SSC 0x210 -#define DKL_PLL_SSC_IREF_NDIV_RATIO(x) ((x) << 29) -#define DKL_PLL_SSC_IREF_NDIV_RATIO_MASK (0x7 << 29) -#define DKL_PLL_SSC_STEP_LEN(x) ((x) << 16) -#define DKL_PLL_SSC_STEP_LEN_MASK (0xFF << 16) -#define DKL_PLL_SSC_STEP_NUM(x) ((x) << 11) -#define DKL_PLL_SSC_STEP_NUM_MASK (0x7 << 11) -#define DKL_PLL_SSC_EN (1 << 9) -#define DKL_PLL_SSC(tc_port) _MMIO(_PORT(tc_port, _DKL_PHY1_BASE, \ - _DKL_PHY2_BASE) + \ - _DKL_PLL_SSC) - -#define _DKL_PLL_BIAS 0x214 -#define DKL_PLL_BIAS_FRAC_EN_H (1 << 30) -#define DKL_PLL_BIAS_FBDIV_SHIFT (8) -#define DKL_PLL_BIAS_FBDIV_FRAC(x) ((x) << DKL_PLL_BIAS_FBDIV_SHIFT) -#define DKL_PLL_BIAS_FBDIV_FRAC_MASK (0x3FFFFF << DKL_PLL_BIAS_FBDIV_SHIFT) -#define DKL_PLL_BIAS(tc_port) _MMIO(_PORT(tc_port, _DKL_PHY1_BASE, \ - _DKL_PHY2_BASE) + \ - _DKL_PLL_BIAS) - -#define _DKL_PLL_TDC_COLDST_BIAS 0x218 -#define DKL_PLL_TDC_SSC_STEP_SIZE(x) ((x) << 8) -#define DKL_PLL_TDC_SSC_STEP_SIZE_MASK (0xFF << 8) -#define DKL_PLL_TDC_FEED_FWD_GAIN(x) ((x) << 0) -#define DKL_PLL_TDC_FEED_FWD_GAIN_MASK (0xFF << 0) -#define DKL_PLL_TDC_COLDST_BIAS(tc_port) _MMIO(_PORT(tc_port, \ - _DKL_PHY1_BASE, \ - _DKL_PHY2_BASE) + \ - _DKL_PLL_TDC_COLDST_BIAS) - -#define _DKL_REFCLKIN_CTL 0x12C -/* Bits are the same as MG_REFCLKIN_CTL */ -#define DKL_REFCLKIN_CTL(tc_port) _MMIO(_PORT(tc_port, \ - _DKL_PHY1_BASE, \ - _DKL_PHY2_BASE) + \ - _DKL_REFCLKIN_CTL) - -#define _DKL_CLKTOP2_HSCLKCTL 0xD4 -/* Bits are the same as MG_CLKTOP2_HSCLKCTL */ -#define DKL_CLKTOP2_HSCLKCTL(tc_port) _MMIO(_PORT(tc_port, \ - _DKL_PHY1_BASE, \ - _DKL_PHY2_BASE) + \ - _DKL_CLKTOP2_HSCLKCTL) - -#define _DKL_CLKTOP2_CORECLKCTL1 0xD8 -/* Bits are the same as MG_CLKTOP2_CORECLKCTL1 */ -#define DKL_CLKTOP2_CORECLKCTL1(tc_port) _MMIO(_PORT(tc_port, \ - _DKL_PHY1_BASE, \ - _DKL_PHY2_BASE) + \ - _DKL_CLKTOP2_CORECLKCTL1) - -#define _DKL_TX_DPCNTL0 0x2C0 -#define DKL_TX_PRESHOOT_COEFF(x) ((x) << 13) -#define DKL_TX_PRESHOOT_COEFF_MASK (0x1f << 13) -#define DKL_TX_DE_EMPHASIS_COEFF(x) ((x) << 8) -#define DKL_TX_DE_EMPAHSIS_COEFF_MASK (0x1f << 8) -#define DKL_TX_VSWING_CONTROL(x) ((x) << 0) -#define DKL_TX_VSWING_CONTROL_MASK (0x7 << 0) -#define DKL_TX_DPCNTL0(tc_port) _MMIO(_PORT(tc_port, \ - _DKL_PHY1_BASE, \ - _DKL_PHY2_BASE) + \ - _DKL_TX_DPCNTL0) - -#define _DKL_TX_DPCNTL1 0x2C4 -/* Bits are the same as DKL_TX_DPCNTRL0 */ -#define DKL_TX_DPCNTL1(tc_port) _MMIO(_PORT(tc_port, \ - _DKL_PHY1_BASE, \ - _DKL_PHY2_BASE) + \ - _DKL_TX_DPCNTL1) - -#define _DKL_TX_DPCNTL2 0x2C8 -#define DKL_TX_DP20BITMODE REG_BIT(2) -#define DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1_MASK REG_GENMASK(4, 3) -#define DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1(val) REG_FIELD_PREP(DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1_MASK, (val)) -#define DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2_MASK REG_GENMASK(6, 5) -#define DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2(val) REG_FIELD_PREP(DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2_MASK, (val)) -#define DKL_TX_DPCNTL2(tc_port) _MMIO(_PORT(tc_port, \ - _DKL_PHY1_BASE, \ - _DKL_PHY2_BASE) + \ - _DKL_TX_DPCNTL2) - -#define _DKL_TX_FW_CALIB 0x2F8 -#define DKL_TX_CFG_DISABLE_WAIT_INIT (1 << 7) -#define DKL_TX_FW_CALIB(tc_port) _MMIO(_PORT(tc_port, \ - _DKL_PHY1_BASE, \ - _DKL_PHY2_BASE) + \ - _DKL_TX_FW_CALIB) - -#define _DKL_TX_PMD_LANE_SUS 0xD00 -#define DKL_TX_PMD_LANE_SUS(tc_port) _MMIO(_PORT(tc_port, \ - _DKL_PHY1_BASE, \ - _DKL_PHY2_BASE) + \ - _DKL_TX_PMD_LANE_SUS) - -#define _DKL_TX_DW17 0xDC4 -#define DKL_TX_DW17(tc_port) _MMIO(_PORT(tc_port, \ - _DKL_PHY1_BASE, \ - _DKL_PHY2_BASE) + \ - _DKL_TX_DW17) - -#define _DKL_TX_DW18 0xDC8 -#define DKL_TX_DW18(tc_port) _MMIO(_PORT(tc_port, \ - _DKL_PHY1_BASE, \ - _DKL_PHY2_BASE) + \ - _DKL_TX_DW18) - -#define _DKL_DP_MODE 0xA0 -#define DKL_DP_MODE(tc_port) _MMIO(_PORT(tc_port, \ - _DKL_PHY1_BASE, \ - _DKL_PHY2_BASE) + \ - _DKL_DP_MODE) - -#define _DKL_CMN_UC_DW27 0x36C -#define DKL_CMN_UC_DW27_UC_HEALTH (0x1 << 15) -#define DKL_CMN_UC_DW_27(tc_port) _MMIO(_PORT(tc_port, \ - _DKL_PHY1_BASE, \ - _DKL_PHY2_BASE) + \ - _DKL_CMN_UC_DW27) - -/* - * Each Dekel PHY is addressed through a 4KB aperture. Each PHY has more than - * 4KB of register space, so a separate index is programmed in HIP_INDEX_REG0 - * or HIP_INDEX_REG1, based on the port number, to set the upper 2 address - * bits that point the 4KB window into the full PHY register space. - */ -#define _HIP_INDEX_REG0 0x1010A0 -#define _HIP_INDEX_REG1 0x1010A4 -#define HIP_INDEX_REG(tc_port) _MMIO((tc_port) < 4 ? _HIP_INDEX_REG0 \ - : _HIP_INDEX_REG1) -#define _HIP_INDEX_SHIFT(tc_port) (8 * ((tc_port) % 4)) -#define HIP_INDEX_VAL(tc_port, val) ((val) << _HIP_INDEX_SHIFT(tc_port)) - /* BXT display engine PLL */ #define BXT_DE_PLL_CTL _MMIO(0x6d000) #define BXT_DE_PLL_RATIO(x) (x) /* {60,65,100} * 19.2MHz */ @@ -7775,12 +7565,10 @@ enum skl_power_gate { #define _PAL_PREC_DATA_A 0x4A404 #define _PAL_PREC_DATA_B 0x4AC04 #define _PAL_PREC_DATA_C 0x4B404 +/* see PREC_PALETTE_* for the bits */ #define _PAL_PREC_GC_MAX_A 0x4A410 #define _PAL_PREC_GC_MAX_B 0x4AC10 #define _PAL_PREC_GC_MAX_C 0x4B410 -#define PREC_PAL_DATA_RED_MASK REG_GENMASK(29, 20) -#define PREC_PAL_DATA_GREEN_MASK REG_GENMASK(19, 10) -#define PREC_PAL_DATA_BLUE_MASK REG_GENMASK(9, 0) #define _PAL_PREC_EXT_GC_MAX_A 0x4A420 #define _PAL_PREC_EXT_GC_MAX_B 0x4AC20 #define _PAL_PREC_EXT_GC_MAX_C 0x4B420 @@ -7813,12 +7601,7 @@ enum skl_power_gate { #define _PAL_PREC_MULTI_SEG_DATA_A 0x4A40C #define _PAL_PREC_MULTI_SEG_DATA_B 0x4AC0C -#define PAL_PREC_MULTI_SEG_RED_LDW_MASK REG_GENMASK(29, 24) -#define PAL_PREC_MULTI_SEG_RED_UDW_MASK REG_GENMASK(29, 20) -#define PAL_PREC_MULTI_SEG_GREEN_LDW_MASK REG_GENMASK(19, 14) -#define PAL_PREC_MULTI_SEG_GREEN_UDW_MASK REG_GENMASK(19, 10) -#define PAL_PREC_MULTI_SEG_BLUE_LDW_MASK REG_GENMASK(9, 4) -#define PAL_PREC_MULTI_SEG_BLUE_UDW_MASK REG_GENMASK(9, 0) +/* see PREC_PALETTE_12P4_* for the bits */ #define PREC_PAL_MULTI_SEG_INDEX(pipe) _MMIO_PIPE(pipe, \ _PAL_PREC_MULTI_SEG_INDEX_A, \ @@ -7879,13 +7662,17 @@ enum skl_power_gate { #define _CGM_PIPE_A_CSC_COEFF67 (VLV_DISPLAY_BASE + 0x6790C) #define _CGM_PIPE_A_CSC_COEFF8 (VLV_DISPLAY_BASE + 0x67910) #define _CGM_PIPE_A_DEGAMMA (VLV_DISPLAY_BASE + 0x66000) -#define CGM_PIPE_DEGAMMA_RED_MASK REG_GENMASK(13, 0) -#define CGM_PIPE_DEGAMMA_GREEN_MASK REG_GENMASK(29, 16) -#define CGM_PIPE_DEGAMMA_BLUE_MASK REG_GENMASK(13, 0) +/* cgm degamma ldw */ +#define CGM_PIPE_DEGAMMA_GREEN_LDW_MASK REG_GENMASK(29, 16) +#define CGM_PIPE_DEGAMMA_BLUE_LDW_MASK REG_GENMASK(13, 0) +/* cgm degamma udw */ +#define CGM_PIPE_DEGAMMA_RED_UDW_MASK REG_GENMASK(13, 0) #define _CGM_PIPE_A_GAMMA (VLV_DISPLAY_BASE + 0x67000) -#define CGM_PIPE_GAMMA_RED_MASK REG_GENMASK(9, 0) -#define CGM_PIPE_GAMMA_GREEN_MASK REG_GENMASK(25, 16) -#define CGM_PIPE_GAMMA_BLUE_MASK REG_GENMASK(9, 0) +/* cgm gamma ldw */ +#define CGM_PIPE_GAMMA_GREEN_LDW_MASK REG_GENMASK(25, 16) +#define CGM_PIPE_GAMMA_BLUE_LDW_MASK REG_GENMASK(9, 0) +/* cgm gamma udw */ +#define CGM_PIPE_GAMMA_RED_UDW_MASK REG_GENMASK(9, 0) #define _CGM_PIPE_A_MODE (VLV_DISPLAY_BASE + 0x67A00) #define CGM_PIPE_MODE_GAMMA (1 << 2) #define CGM_PIPE_MODE_CSC (1 << 1) @@ -7962,8 +7749,13 @@ enum skl_power_gate { _ICL_PIPE_DSS_CTL2_PB, \ _ICL_PIPE_DSS_CTL2_PC) +#define GGC _MMIO(0x108040) +#define GMS_MASK REG_GENMASK(15, 8) +#define GGMS_MASK REG_GENMASK(7, 6) + #define GEN12_GSMBASE _MMIO(0x108100) #define GEN12_DSMBASE _MMIO(0x1080C0) +#define GEN12_BDSM_MASK REG_GENMASK64(63, 20) #define XEHP_CLOCK_GATE_DIS _MMIO(0x101014) #define SGSI_SIDECLK_DIS REG_BIT(17) @@ -8344,6 +8136,11 @@ enum skl_power_gate { #define GEN12_CULLBIT2 _MMIO(0x7030) #define GEN12_STATE_ACK_DEBUG _MMIO(0x20BC) +#define _MTL_CLKGATE_DIS_TRANS_A 0x604E8 +#define _MTL_CLKGATE_DIS_TRANS_B 0x614E8 +#define MTL_CLKGATE_DIS_TRANS(trans) _MMIO_TRANS2(trans, _MTL_CLKGATE_DIS_TRANS_A) +#define MTL_CLKGATE_DIS_TRANS_DMASC_GATING_DIS REG_BIT(7) + #define MTL_LATENCY_LP0_LP1 _MMIO(0x45780) #define MTL_LATENCY_LP2_LP3 _MMIO(0x45784) #define MTL_LATENCY_LP4_LP5 _MMIO(0x45788) @@ -8367,4 +8164,6 @@ enum skl_power_gate { #define MTL_TRAS_MASK REG_GENMASK(16, 8) #define MTL_TRDPRE_MASK REG_GENMASK(7, 0) +#define MTL_MEDIA_GSI_BASE 0x380000 + #endif /* _I915_REG_H_ */ diff --git a/drivers/gpu/drm/i915/i915_reg_defs.h b/drivers/gpu/drm/i915/i915_reg_defs.h index 8f486f77609f..be43580a6979 100644 --- a/drivers/gpu/drm/i915/i915_reg_defs.h +++ b/drivers/gpu/drm/i915/i915_reg_defs.h @@ -98,29 +98,54 @@ */ #define REG_FIELD_GET64(__mask, __val) ((u64)FIELD_GET(__mask, __val)) +#define __MASKED_FIELD(mask, value) ((mask) << 16 | (value)) +#define _MASKED_FIELD(mask, value) ({ \ + if (__builtin_constant_p(mask)) \ + BUILD_BUG_ON_MSG(((mask) & 0xffff0000), "Incorrect mask"); \ + if (__builtin_constant_p(value)) \ + BUILD_BUG_ON_MSG((value) & 0xffff0000, "Incorrect value"); \ + if (__builtin_constant_p(mask) && __builtin_constant_p(value)) \ + BUILD_BUG_ON_MSG((value) & ~(mask), \ + "Incorrect value for mask"); \ + __MASKED_FIELD(mask, value); }) +#define _MASKED_BIT_ENABLE(a) ({ typeof(a) _a = (a); _MASKED_FIELD(_a, _a); }) +#define _MASKED_BIT_DISABLE(a) (_MASKED_FIELD((a), 0)) + +/* + * Given the first two numbers __a and __b of arbitrarily many evenly spaced + * numbers, pick the 0-based __index'th value. + * + * Always prefer this over _PICK() if the numbers are evenly spaced. + */ +#define _PICK_EVEN(__index, __a, __b) ((__a) + (__index) * ((__b) - (__a))) + +/* + * Given the arbitrary numbers in varargs, pick the 0-based __index'th number. + * + * Always prefer _PICK_EVEN() over this if the numbers are evenly spaced. + */ +#define _PICK(__index, ...) (((const u32 []){ __VA_ARGS__ })[__index]) + typedef struct { u32 reg; } i915_reg_t; #define _MMIO(r) ((const i915_reg_t){ .reg = (r) }) -#define INVALID_MMIO_REG _MMIO(0) - -static __always_inline u32 i915_mmio_reg_offset(i915_reg_t reg) -{ - return reg.reg; -} - -static inline bool i915_mmio_reg_equal(i915_reg_t a, i915_reg_t b) -{ - return i915_mmio_reg_offset(a) == i915_mmio_reg_offset(b); -} +typedef struct { + u32 reg; +} i915_mcr_reg_t; -static inline bool i915_mmio_reg_valid(i915_reg_t reg) -{ - return !i915_mmio_reg_equal(reg, INVALID_MMIO_REG); -} +#define INVALID_MMIO_REG _MMIO(0) -#define VLV_DISPLAY_BASE 0x180000 +/* + * These macros can be used on either i915_reg_t or i915_mcr_reg_t since they're + * simply operations on the register's offset and don't care about the MCR vs + * non-MCR nature of the register. + */ +#define i915_mmio_reg_offset(r) \ + _Generic((r), i915_reg_t: (r).reg, i915_mcr_reg_t: (r).reg) +#define i915_mmio_reg_equal(a, b) (i915_mmio_reg_offset(a) == i915_mmio_reg_offset(b)) +#define i915_mmio_reg_valid(r) (!i915_mmio_reg_equal(r, INVALID_MMIO_REG)) #endif /* __I915_REG_DEFS__ */ diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 62fad16a55e8..f949a9495758 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1621,6 +1621,20 @@ i915_request_await_object(struct i915_request *to, return ret; } +static void i915_request_await_huc(struct i915_request *rq) +{ + struct intel_huc *huc = &rq->context->engine->gt->uc.huc; + + /* don't stall kernel submissions! */ + if (!rcu_access_pointer(rq->context->gem_context)) + return; + + if (intel_huc_wait_required(huc)) + i915_sw_fence_await_sw_fence(&rq->submit, + &huc->delayed_load.fence, + &rq->hucq); +} + static struct i915_request * __i915_request_ensure_parallel_ordering(struct i915_request *rq, struct intel_timeline *timeline) @@ -1703,6 +1717,16 @@ __i915_request_add_to_timeline(struct i915_request *rq) struct i915_request *prev; /* + * Media workloads may require HuC, so stall them until HuC loading is + * complete. Note that HuC not being loaded when a user submission + * arrives can only happen when HuC is loaded via GSC and in that case + * we still expect the window between us starting to accept submissions + * and HuC loading completion to be small (a few hundred ms). + */ + if (rq->engine->class == VIDEO_DECODE_CLASS) + i915_request_await_huc(rq); + + /* * Dependency tracking and request ordering along the timeline * is special cased so that we can eliminate redundant ordering * operations while building the request (we know that the timeline diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index 47041ec68df8..f5e1bb5e857a 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -348,6 +348,11 @@ struct i915_request { #define GUC_PRIO_FINI 0xfe u8 guc_prio; + /** + * @hucq: wait queue entry used to wait on the HuC load to complete + */ + wait_queue_entry_t hucq; + I915_SELFTEST_DECLARE(struct { struct list_head link; unsigned long delay; diff --git a/drivers/gpu/drm/i915/i915_scatterlist.c b/drivers/gpu/drm/i915/i915_scatterlist.c index dcc081874ec8..114e5e39aa72 100644 --- a/drivers/gpu/drm/i915/i915_scatterlist.c +++ b/drivers/gpu/drm/i915/i915_scatterlist.c @@ -158,7 +158,7 @@ struct i915_refct_sgt *i915_rsgt_from_buddy_resource(struct ttm_resource *res, u32 page_alignment) { struct i915_ttm_buddy_resource *bman_res = to_ttm_buddy_resource(res); - const u64 size = res->num_pages << PAGE_SHIFT; + const u64 size = res->size; const u32 max_segment = round_down(UINT_MAX, page_alignment); struct drm_buddy *mm = bman_res->mm; struct list_head *blocks = &bman_res->blocks; @@ -177,7 +177,7 @@ struct i915_refct_sgt *i915_rsgt_from_buddy_resource(struct ttm_resource *res, i915_refct_sgt_init(rsgt, size); st = &rsgt->table; - if (sg_alloc_table(st, res->num_pages, GFP_KERNEL)) { + if (sg_alloc_table(st, PFN_UP(res->size), GFP_KERNEL)) { i915_refct_sgt_put(rsgt); return ERR_PTR(-ENOMEM); } diff --git a/drivers/gpu/drm/i915/i915_selftest.h b/drivers/gpu/drm/i915/i915_selftest.h index f54de0499be7..bdf3e22c0a34 100644 --- a/drivers/gpu/drm/i915/i915_selftest.h +++ b/drivers/gpu/drm/i915/i915_selftest.h @@ -92,12 +92,14 @@ int __i915_subtests(const char *caller, T, ARRAY_SIZE(T), data) #define i915_live_subtests(T, data) ({ \ typecheck(struct drm_i915_private *, data); \ + (data)->gt[0]->uc.guc.submission_state.sched_disable_delay_ms = 0; \ __i915_subtests(__func__, \ __i915_live_setup, __i915_live_teardown, \ T, ARRAY_SIZE(T), data); \ }) #define intel_gt_live_subtests(T, data) ({ \ typecheck(struct intel_gt *, data); \ + (data)->uc.guc.submission_state.sched_disable_delay_ms = 0; \ __i915_subtests(__func__, \ __intel_gt_live_setup, __intel_gt_live_teardown, \ T, ARRAY_SIZE(T), data); \ diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c index 6fc0d1b89690..8a9aad523eec 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.c +++ b/drivers/gpu/drm/i915/i915_sw_fence.c @@ -465,7 +465,7 @@ static void irq_i915_sw_fence_work(struct irq_work *wrk) struct i915_sw_dma_fence_cb_timer *cb = container_of(wrk, typeof(*cb), work); - del_timer_sync(&cb->timer); + timer_shutdown_sync(&cb->timer); dma_fence_put(cb->dma); kfree_rcu(cb, rcu); @@ -571,7 +571,6 @@ int __i915_sw_fence_await_dma_fence(struct i915_sw_fence *fence, int i915_sw_fence_await_reservation(struct i915_sw_fence *fence, struct dma_resv *resv, - const struct dma_fence_ops *exclude, bool write, unsigned long timeout, gfp_t gfp) diff --git a/drivers/gpu/drm/i915/i915_sw_fence.h b/drivers/gpu/drm/i915/i915_sw_fence.h index 619fc5a22f0c..f752bfc7c6e1 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.h +++ b/drivers/gpu/drm/i915/i915_sw_fence.h @@ -91,7 +91,6 @@ int i915_sw_fence_await_dma_fence(struct i915_sw_fence *fence, int i915_sw_fence_await_reservation(struct i915_sw_fence *fence, struct dma_resv *resv, - const struct dma_fence_ops *exclude, bool write, unsigned long timeout, gfp_t gfp); diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c index 1e2750210831..595e8b574990 100644 --- a/drivers/gpu/drm/i915/i915_sysfs.c +++ b/drivers/gpu/drm/i915/i915_sysfs.c @@ -218,7 +218,8 @@ static const struct bin_attribute error_state_attr = { static void i915_setup_error_capture(struct device *kdev) { if (sysfs_create_bin_file(&kdev->kobj, &error_state_attr)) - DRM_ERROR("error_state sysfs setup failed\n"); + drm_err(&kdev_minor_to_i915(kdev)->drm, + "error_state sysfs setup failed\n"); } static void i915_teardown_error_capture(struct device *kdev) diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index 37b5c9e9d260..f6f9228a1351 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -15,7 +15,6 @@ #include "gt/intel_engine.h" #include "i915_drv.h" -#include "i915_irq.h" /* object tracking */ @@ -671,21 +670,6 @@ TRACE_EVENT_CONDITION(i915_reg_rw, (u32)(__entry->val >> 32)) ); -TRACE_EVENT(intel_gpu_freq_change, - TP_PROTO(u32 freq), - TP_ARGS(freq), - - TP_STRUCT__entry( - __field(u32, freq) - ), - - TP_fast_assign( - __entry->freq = freq; - ), - - TP_printk("new_freq=%u", __entry->freq) -); - /** * DOC: i915_ppgtt_create and i915_ppgtt_release tracepoints * diff --git a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c index e19452f0e100..7e611476c7a4 100644 --- a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c +++ b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c @@ -62,8 +62,8 @@ static int i915_ttm_buddy_man_alloc(struct ttm_resource_manager *man, if (place->fpfn || lpfn != man->size) bman_res->flags |= DRM_BUDDY_RANGE_ALLOCATION; - GEM_BUG_ON(!bman_res->base.num_pages); - size = bman_res->base.num_pages << PAGE_SHIFT; + GEM_BUG_ON(!bman_res->base.size); + size = bman_res->base.size; min_page_size = bman->default_page_size; if (bo->page_alignment) @@ -72,7 +72,7 @@ static int i915_ttm_buddy_man_alloc(struct ttm_resource_manager *man, GEM_BUG_ON(min_page_size < mm->chunk_size); GEM_BUG_ON(!IS_ALIGNED(size, min_page_size)); - if (place->fpfn + bman_res->base.num_pages != place->lpfn && + if (place->fpfn + PFN_UP(bman_res->base.size) != place->lpfn && place->flags & TTM_PL_FLAG_CONTIGUOUS) { unsigned long pages; @@ -108,7 +108,7 @@ static int i915_ttm_buddy_man_alloc(struct ttm_resource_manager *man, goto err_free_blocks; if (place->flags & TTM_PL_FLAG_CONTIGUOUS) { - u64 original_size = (u64)bman_res->base.num_pages << PAGE_SHIFT; + u64 original_size = (u64)bman_res->base.size; drm_buddy_block_trim(mm, original_size, @@ -116,7 +116,7 @@ static int i915_ttm_buddy_man_alloc(struct ttm_resource_manager *man, } if (lpfn <= bman->visible_size) { - bman_res->used_visible_size = bman_res->base.num_pages; + bman_res->used_visible_size = PFN_UP(bman_res->base.size); } else { struct drm_buddy_block *block; @@ -228,7 +228,7 @@ static bool i915_ttm_buddy_man_compatible(struct ttm_resource_manager *man, if (!place->fpfn && place->lpfn == i915_ttm_buddy_man_visible_size(man)) - return bman_res->used_visible_size == res->num_pages; + return bman_res->used_visible_size == PFN_UP(res->size); /* Check each drm buddy block individually */ list_for_each_entry(block, &bman_res->blocks, link) { diff --git a/drivers/gpu/drm/i915/i915_user_extensions.c b/drivers/gpu/drm/i915/i915_user_extensions.c index c822d0aafd2d..e3f808372c47 100644 --- a/drivers/gpu/drm/i915/i915_user_extensions.c +++ b/drivers/gpu/drm/i915/i915_user_extensions.c @@ -51,7 +51,7 @@ int i915_user_extensions(struct i915_user_extension __user *ext, return err; if (get_user(next, &ext->next_extension) || - overflows_type(next, ext)) + overflows_type(next, uintptr_t)) return -EFAULT; ext = u64_to_user_ptr(next); diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h index 6c14d13364bf..67a66d4d5c70 100644 --- a/drivers/gpu/drm/i915/i915_utils.h +++ b/drivers/gpu/drm/i915/i915_utils.h @@ -111,10 +111,6 @@ bool i915_error_injected(void); #define range_overflows_end_t(type, start, size, max) \ range_overflows_end((type)(start), (type)(size), (type)(max)) -/* Note we don't consider signbits :| */ -#define overflows_type(x, T) \ - (sizeof(x) > sizeof(T) && (x) >> BITS_PER_TYPE(T)) - #define ptr_mask_bits(ptr, n) ({ \ unsigned long __v = (unsigned long)(ptr); \ (typeof(ptr))(__v & -BIT(n)); \ diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index f17c09ead7d7..3a33be5401ed 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -73,14 +73,16 @@ static void vma_print_allocator(struct i915_vma *vma, const char *reason) char buf[512]; if (!vma->node.stack) { - DRM_DEBUG_DRIVER("vma.node [%08llx + %08llx] %s: unknown owner\n", - vma->node.start, vma->node.size, reason); + drm_dbg(&to_i915(vma->obj->base.dev)->drm, + "vma.node [%08llx + %08llx] %s: unknown owner\n", + vma->node.start, vma->node.size, reason); return; } stack_depot_snprint(vma->node.stack, buf, sizeof(buf), 0); - DRM_DEBUG_DRIVER("vma.node [%08llx + %08llx] %s: inserted at %s\n", - vma->node.start, vma->node.size, reason, buf); + drm_dbg(&to_i915(vma->obj->base.dev)->drm, + "vma.node [%08llx + %08llx] %s: inserted at %s\n", + vma->node.start, vma->node.size, reason, buf); } #else @@ -776,21 +778,15 @@ i915_vma_insert(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, GEM_BUG_ON(!IS_ALIGNED(end, I915_GTT_PAGE_SIZE)); alignment = max(alignment, i915_vm_obj_min_alignment(vma->vm, vma->obj)); - /* - * for compact-pt we round up the reservation to prevent - * any smaller pages being used within the same PDE - */ - if (NEEDS_COMPACT_PT(vma->vm->i915)) - size = round_up(size, alignment); /* If binding the object/GGTT view requires more space than the entire * aperture has, reject it early before evicting everything in a vain * attempt to find space. */ if (size > end) { - DRM_DEBUG("Attempting to bind an object larger than the aperture: request=%llu > %s aperture=%llu\n", - size, flags & PIN_MAPPABLE ? "mappable" : "total", - end); + drm_dbg(&to_i915(vma->obj->base.dev)->drm, + "Attempting to bind an object larger than the aperture: request=%llu > %s aperture=%llu\n", + size, flags & PIN_MAPPABLE ? "mappable" : "total", end); return -ENOSPC; } @@ -820,7 +816,8 @@ i915_vma_insert(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, * forseeable future. See also i915_ggtt_offset(). */ if (upper_32_bits(end - 1) && - vma->page_sizes.sg > I915_GTT_PAGE_SIZE) { + vma->page_sizes.sg > I915_GTT_PAGE_SIZE && + !HAS_64K_PAGES(vma->vm->i915)) { /* * We can't mix 64K and 4K PTEs in the same page-table * (2M block), and so to avoid the ugliness and @@ -1569,7 +1566,7 @@ static int __i915_ggtt_pin(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, * locked objects when called from execbuf when pinning * is removed. This would probably regress badly. */ - i915_gem_evict_vm(vm, NULL); + i915_gem_evict_vm(vm, NULL, NULL); mutex_unlock(&vm->mutex); } } while (1); @@ -1847,6 +1844,11 @@ int _i915_vma_move_to_active(struct i915_vma *vma, GEM_BUG_ON(!vma->pages); + if (!(flags & __EXEC_OBJECT_NO_REQUEST_AWAIT)) { + err = i915_request_await_object(rq, vma->obj, flags & EXEC_OBJECT_WRITE); + if (unlikely(err)) + return err; + } err = __i915_vma_move_to_active(vma, rq); if (unlikely(err)) return err; diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h index aecd9c64486b..0757977a489b 100644 --- a/drivers/gpu/drm/i915/i915_vma.h +++ b/drivers/gpu/drm/i915/i915_vma.h @@ -55,6 +55,7 @@ static inline bool i915_vma_is_active(const struct i915_vma *vma) /* do not reserve memory to prevent deadlocks */ #define __EXEC_OBJECT_NO_RESERVE BIT(31) +#define __EXEC_OBJECT_NO_REQUEST_AWAIT BIT(30) int __must_check _i915_vma_move_to_active(struct i915_vma *vma, struct i915_request *rq, diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c index 20575eb77ea7..849baf6c3b3c 100644 --- a/drivers/gpu/drm/i915/intel_device_info.c +++ b/drivers/gpu/drm/i915/intel_device_info.c @@ -29,9 +29,11 @@ #include "display/intel_cdclk.h" #include "display/intel_de.h" -#include "intel_device_info.h" +#include "gt/intel_gt_regs.h" #include "i915_drv.h" +#include "i915_reg.h" #include "i915_utils.h" +#include "intel_device_info.h" #define PLATFORM_NAME(x) [INTEL_##x] = #x static const char * const platform_names[] = { @@ -231,7 +233,7 @@ static bool find_devid(u16 id, const u16 *p, unsigned int num) return false; } -void intel_device_info_subplatform_init(struct drm_i915_private *i915) +static void intel_device_info_subplatform_init(struct drm_i915_private *i915) { const struct intel_device_info *info = INTEL_INFO(i915); const struct intel_runtime_info *rinfo = RUNTIME_INFO(i915); @@ -288,6 +290,78 @@ void intel_device_info_subplatform_init(struct drm_i915_private *i915) RUNTIME_INFO(i915)->platform_mask[pi] |= mask; } +static void ip_ver_read(struct drm_i915_private *i915, u32 offset, struct intel_ip_version *ip) +{ + struct pci_dev *pdev = to_pci_dev(i915->drm.dev); + void __iomem *addr; + u32 val; + u8 expected_ver = ip->ver; + u8 expected_rel = ip->rel; + + addr = pci_iomap_range(pdev, 0, offset, sizeof(u32)); + if (drm_WARN_ON(&i915->drm, !addr)) + return; + + val = ioread32(addr); + pci_iounmap(pdev, addr); + + ip->ver = REG_FIELD_GET(GMD_ID_ARCH_MASK, val); + ip->rel = REG_FIELD_GET(GMD_ID_RELEASE_MASK, val); + ip->step = REG_FIELD_GET(GMD_ID_STEP, val); + + /* Sanity check against expected versions from device info */ + if (IP_VER(ip->ver, ip->rel) < IP_VER(expected_ver, expected_rel)) + drm_dbg(&i915->drm, + "Hardware reports GMD IP version %u.%u (REG[0x%x] = 0x%08x) but minimum expected is %u.%u\n", + ip->ver, ip->rel, offset, val, expected_ver, expected_rel); +} + +/* + * Setup the graphics version for the current device. This must be done before + * any code that performs checks on GRAPHICS_VER or DISPLAY_VER, so this + * function should be called very early in the driver initialization sequence. + * + * Regular MMIO access is not yet setup at the point this function is called so + * we peek at the appropriate MMIO offset directly. The GMD_ID register is + * part of an 'always on' power well by design, so we don't need to worry about + * forcewake while reading it. + */ +static void intel_ipver_early_init(struct drm_i915_private *i915) +{ + struct intel_runtime_info *runtime = RUNTIME_INFO(i915); + + if (!HAS_GMD_ID(i915)) { + drm_WARN_ON(&i915->drm, RUNTIME_INFO(i915)->graphics.ip.ver > 12); + /* + * On older platforms, graphics and media share the same ip + * version and release. + */ + RUNTIME_INFO(i915)->media.ip = + RUNTIME_INFO(i915)->graphics.ip; + return; + } + + ip_ver_read(i915, i915_mmio_reg_offset(GMD_ID_GRAPHICS), + &runtime->graphics.ip); + ip_ver_read(i915, i915_mmio_reg_offset(GMD_ID_DISPLAY), + &runtime->display.ip); + ip_ver_read(i915, i915_mmio_reg_offset(GMD_ID_MEDIA), + &runtime->media.ip); +} + +/** + * intel_device_info_runtime_init_early - initialize early runtime info + * @i915: the i915 device + * + * Determine early intel_device_info fields at runtime. This function needs + * to be called before the MMIO has been setup. + */ +void intel_device_info_runtime_init_early(struct drm_i915_private *i915) +{ + intel_ipver_early_init(i915); + intel_device_info_subplatform_init(i915); +} + /** * intel_device_info_runtime_init - initialize runtime info * @dev_priv: the i915 device @@ -415,7 +489,7 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv) if (DISPLAY_VER(dev_priv) >= 11 && (dfsm & ICL_DFSM_DMC_DISABLE)) runtime->has_dmc = 0; - if (DISPLAY_VER(dev_priv) >= 10 && + if (IS_DISPLAY_VER(dev_priv, 10, 12) && (dfsm & GLK_DFSM_DISPLAY_DSC_DISABLE)) runtime->has_dsc = 0; } @@ -442,6 +516,11 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv) runtime->has_dmc = false; runtime->has_dsc = false; } + + /* Disable nuclear pageflip by default on pre-g4x */ + if (!dev_priv->params.nuclear_pageflip && + DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv)) + dev_priv->drm.driver_features &= ~DRIVER_ATOMIC; } void intel_driver_caps_print(const struct intel_driver_caps *caps, diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h index d638235e1d26..d588e5fd2eea 100644 --- a/drivers/gpu/drm/i915/intel_device_info.h +++ b/drivers/gpu/drm/i915/intel_device_info.h @@ -146,13 +146,13 @@ enum intel_ppgtt_type { /* Keep has_* in alphabetical order */ \ func(has_64bit_reloc); \ func(has_64k_pages); \ - func(needs_compact_pt); \ func(gpu_reset_clobbers_display); \ func(has_reset_engine); \ func(has_3d_pipeline); \ func(has_4tile); \ func(has_flat_ccs); \ func(has_global_mocs); \ + func(has_gmd_id); \ func(has_gt_uc); \ func(has_heci_pxp); \ func(has_heci_gscfi); \ @@ -164,6 +164,8 @@ enum intel_ppgtt_type { func(has_logical_ring_elsq); \ func(has_media_ratio_mode); \ func(has_mslice_steering); \ + func(has_oa_bpc_reporting); \ + func(has_oa_slice_contrib_limits); \ func(has_one_eu_per_fuse_bit); \ func(has_pxp); \ func(has_rc6); \ @@ -180,6 +182,7 @@ enum intel_ppgtt_type { /* Keep in alphabetical order */ \ func(cursor_needs_physical); \ func(has_cdclk_crawl); \ + func(has_cdclk_squash); \ func(has_ddi); \ func(has_dp_mst); \ func(has_dsb); \ @@ -195,20 +198,25 @@ enum intel_ppgtt_type { func(overlay_needs_physical); \ func(supports_tv); -struct ip_version { +struct intel_ip_version { u8 ver; u8 rel; + u8 step; }; struct intel_runtime_info { + /* + * Single "graphics" IP version that represents + * render, compute and copy behavior. + */ struct { - struct ip_version ip; + struct intel_ip_version ip; } graphics; struct { - struct ip_version ip; + struct intel_ip_version ip; } media; struct { - struct ip_version ip; + struct intel_ip_version ip; } display; /* @@ -308,7 +316,7 @@ struct intel_driver_caps { const char *intel_platform_name(enum intel_platform platform); -void intel_device_info_subplatform_init(struct drm_i915_private *dev_priv); +void intel_device_info_runtime_init_early(struct drm_i915_private *dev_priv); void intel_device_info_runtime_init(struct drm_i915_private *dev_priv); void intel_device_info_print(const struct intel_device_info *info, diff --git a/drivers/gpu/drm/i915/intel_gvt_mmio_table.c b/drivers/gpu/drm/i915/intel_gvt_mmio_table.c index 8279dc580a3e..ce6b3c3b636a 100644 --- a/drivers/gpu/drm/i915/intel_gvt_mmio_table.c +++ b/drivers/gpu/drm/i915/intel_gvt_mmio_table.c @@ -6,6 +6,7 @@ #include "display/intel_audio_regs.h" #include "display/intel_backlight_regs.h" #include "display/intel_dmc_regs.h" +#include "display/intel_dpio_phy.h" #include "display/vlv_dsi_pll_regs.h" #include "gt/intel_gt_regs.h" #include "gvt/gvt.h" @@ -102,7 +103,7 @@ static int iterate_generic_mmio(struct intel_gvt_mmio_table_iter *iter) MMIO_D(_MMIO(0x2438)); MMIO_D(_MMIO(0x243c)); MMIO_D(_MMIO(0x7018)); - MMIO_D(HALF_SLICE_CHICKEN3); + MMIO_D(HSW_HALF_SLICE_CHICKEN3); MMIO_D(GEN7_HALF_SLICE_CHICKEN1); /* display */ MMIO_F(_MMIO(0x60220), 0x20); diff --git a/drivers/gpu/drm/i915/intel_mchbar_regs.h b/drivers/gpu/drm/i915/intel_mchbar_regs.h index ffc702b79579..f93e9af43ac3 100644 --- a/drivers/gpu/drm/i915/intel_mchbar_regs.h +++ b/drivers/gpu/drm/i915/intel_mchbar_regs.h @@ -189,6 +189,21 @@ #define DG1_QCLK_RATIO_MASK REG_GENMASK(9, 2) #define DG1_QCLK_REFERENCE REG_BIT(10) +/* + * *_PACKAGE_POWER_SKU - SKU power and timing parameters. + */ +#define PCU_PACKAGE_POWER_SKU _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5930) +#define PKG_PKG_TDP GENMASK_ULL(14, 0) +#define PKG_MAX_WIN GENMASK_ULL(54, 48) +#define PKG_MAX_WIN_X GENMASK_ULL(54, 53) +#define PKG_MAX_WIN_Y GENMASK_ULL(52, 48) + +#define PCU_PACKAGE_POWER_SKU_UNIT _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5938) +#define PKG_PWR_UNIT REG_GENMASK(3, 0) +#define PKG_ENERGY_UNIT REG_GENMASK(12, 8) +#define PKG_TIME_UNIT REG_GENMASK(19, 16) +#define PCU_PACKAGE_ENERGY_STATUS _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x593c) + #define GEN6_GT_PERF_STATUS _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5948) #define GEN6_RP_STATE_LIMITS _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5994) #define GEN6_RP_STATE_CAP _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5998) @@ -198,6 +213,12 @@ #define GEN10_FREQ_INFO_REC _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5ef0) #define RPE_MASK REG_GENMASK(15, 8) +#define PCU_PACKAGE_RAPL_LIMIT _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x59a0) +#define PKG_PWR_LIM_1 REG_GENMASK(14, 0) +#define PKG_PWR_LIM_1_EN REG_BIT(15) +#define PKG_PWR_LIM_1_TIME REG_GENMASK(23, 17) +#define PKG_PWR_LIM_1_TIME_X REG_GENMASK(23, 22) +#define PKG_PWR_LIM_1_TIME_Y REG_GENMASK(21, 17) /* snb MCH registers for priority tuning */ #define MCH_SSKPD _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5d10) diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c index 9a4a7fb55582..b9a164efd6ae 100644 --- a/drivers/gpu/drm/i915/intel_memory_region.c +++ b/drivers/gpu/drm/i915/intel_memory_region.c @@ -38,7 +38,7 @@ static int __iopagetest(struct intel_memory_region *mem, u8 value, resource_size_t offset, const void *caller) { - int byte = prandom_u32_max(pagesize); + int byte = get_random_u32_below(pagesize); u8 result[3]; memset_io(va, value, pagesize); /* or GPF! */ @@ -92,7 +92,7 @@ static int iopagetest(struct intel_memory_region *mem, static resource_size_t random_page(resource_size_t last) { /* Limited to low 44b (16TiB), but should suffice for a spot check */ - return prandom_u32_max(last >> PAGE_SHIFT) << PAGE_SHIFT; + return get_random_u32_below(last >> PAGE_SHIFT) << PAGE_SHIFT; } static int iomemtest(struct intel_memory_region *mem, diff --git a/drivers/gpu/drm/i915/intel_pci_config.h b/drivers/gpu/drm/i915/intel_pci_config.h index 4977a524ce6f..23b8e519f333 100644 --- a/drivers/gpu/drm/i915/intel_pci_config.h +++ b/drivers/gpu/drm/i915/intel_pci_config.h @@ -7,11 +7,29 @@ #define __INTEL_PCI_CONFIG_H__ /* PCI BARs */ -#define GTTMMADR_BAR 0 -#define GEN2_GTTMMADR_BAR 1 -#define GFXMEM_BAR 2 -#define GTT_APERTURE_BAR GFXMEM_BAR -#define GEN12_LMEM_BAR GFXMEM_BAR +#define GEN2_GMADR_BAR 0 +#define GEN2_MMADR_BAR 1 /* MMIO+GTT, despite the name */ +#define GEN2_IO_BAR 2 /* 85x/865 */ + +#define GEN3_MMADR_BAR 0 /* MMIO only */ +#define GEN3_IO_BAR 1 +#define GEN3_GMADR_BAR 2 +#define GEN3_GTTADR_BAR 3 /* GTT only */ + +#define GEN4_GTTMMADR_BAR 0 /* MMIO+GTT */ +#define GEN4_GMADR_BAR 2 +#define GEN4_IO_BAR 4 + +#define GEN12_LMEM_BAR 2 + +static inline int intel_mmio_bar(int graphics_ver) +{ + switch (graphics_ver) { + case 2: return GEN2_MMADR_BAR; + case 3: return GEN3_MMADR_BAR; + default: return GEN4_GTTMMADR_BAR; + } +} /* BSM in include/drm/i915_drm.h */ diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 8f86f56e7ca4..73c88b1c9545 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -30,6 +30,8 @@ #include "display/skl_watermark.h" #include "gt/intel_engine_regs.h" +#include "gt/intel_gt.h" +#include "gt/intel_gt_mcr.h" #include "gt/intel_gt_regs.h" #include "i915_drv.h" @@ -58,25 +60,20 @@ static void gen9_init_clock_gating(struct drm_i915_private *dev_priv) * Must match Sampler, Pixel Back End, and Media. See * WaCompressedResourceSamplerPbeMediaNewHashMode. */ - intel_uncore_write(&dev_priv->uncore, CHICKEN_PAR1_1, - intel_uncore_read(&dev_priv->uncore, CHICKEN_PAR1_1) | - SKL_DE_COMPRESSED_HASH_MODE); + intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PAR1_1, 0, SKL_DE_COMPRESSED_HASH_MODE); } /* See Bspec note for PSR2_CTL bit 31, Wa#828:skl,bxt,kbl,cfl */ - intel_uncore_write(&dev_priv->uncore, CHICKEN_PAR1_1, - intel_uncore_read(&dev_priv->uncore, CHICKEN_PAR1_1) | SKL_EDP_PSR_FIX_RDWRAP); + intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PAR1_1, 0, SKL_EDP_PSR_FIX_RDWRAP); /* WaEnableChickenDCPR:skl,bxt,kbl,glk,cfl */ - intel_uncore_write(&dev_priv->uncore, GEN8_CHICKEN_DCPR_1, - intel_uncore_read(&dev_priv->uncore, GEN8_CHICKEN_DCPR_1) | MASK_WAKEMEM); + intel_uncore_rmw(&dev_priv->uncore, GEN8_CHICKEN_DCPR_1, 0, MASK_WAKEMEM); /* * WaFbcWakeMemOn:skl,bxt,kbl,glk,cfl * Display WA #0859: skl,bxt,kbl,glk,cfl */ - intel_uncore_write(&dev_priv->uncore, DISP_ARB_CTL, intel_uncore_read(&dev_priv->uncore, DISP_ARB_CTL) | - DISP_FBC_MEMORY_WAKE); + intel_uncore_rmw(&dev_priv->uncore, DISP_ARB_CTL, 0, DISP_FBC_MEMORY_WAKE); } static void bxt_init_clock_gating(struct drm_i915_private *dev_priv) @@ -84,15 +81,13 @@ static void bxt_init_clock_gating(struct drm_i915_private *dev_priv) gen9_init_clock_gating(dev_priv); /* WaDisableSDEUnitClockGating:bxt */ - intel_uncore_write(&dev_priv->uncore, GEN8_UCGCTL6, intel_uncore_read(&dev_priv->uncore, GEN8_UCGCTL6) | - GEN8_SDEUNIT_CLOCK_GATE_DISABLE); + intel_uncore_rmw(&dev_priv->uncore, GEN8_UCGCTL6, 0, GEN8_SDEUNIT_CLOCK_GATE_DISABLE); /* * FIXME: * GEN8_HDCUNIT_CLOCK_GATE_DISABLE_HDCREQ applies on 3x6 GT SKUs only. */ - intel_uncore_write(&dev_priv->uncore, GEN8_UCGCTL6, intel_uncore_read(&dev_priv->uncore, GEN8_UCGCTL6) | - GEN8_HDCUNIT_CLOCK_GATE_DISABLE_HDCREQ); + intel_uncore_rmw(&dev_priv->uncore, GEN8_UCGCTL6, 0, GEN8_HDCUNIT_CLOCK_GATE_DISABLE_HDCREQ); /* * Wa: Backlight PWM may stop in the asserted state, causing backlight @@ -113,16 +108,13 @@ static void bxt_init_clock_gating(struct drm_i915_private *dev_priv) * WaFbcTurnOffFbcWatermark:bxt * Display WA #0562: bxt */ - intel_uncore_write(&dev_priv->uncore, DISP_ARB_CTL, intel_uncore_read(&dev_priv->uncore, DISP_ARB_CTL) | - DISP_FBC_WM_DIS); + intel_uncore_rmw(&dev_priv->uncore, DISP_ARB_CTL, 0, DISP_FBC_WM_DIS); /* * WaFbcHighMemBwCorruptionAvoidance:bxt * Display WA #0883: bxt */ - intel_uncore_write(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A), - intel_uncore_read(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A)) | - DPFC_DISABLE_DUMMY0); + intel_uncore_rmw(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A), 0, DPFC_DISABLE_DUMMY0); } static void glk_init_clock_gating(struct drm_i915_private *dev_priv) @@ -895,19 +887,14 @@ static void pnv_update_wm(struct drm_i915_private *dev_priv) wm = intel_calculate_wm(pixel_rate, &pnv_cursor_wm, pnv_display_wm.fifo_size, 4, latency->cursor_sr); - reg = intel_uncore_read(&dev_priv->uncore, DSPFW3); - reg &= ~DSPFW_CURSOR_SR_MASK; - reg |= FW_WM(wm, CURSOR_SR); - intel_uncore_write(&dev_priv->uncore, DSPFW3, reg); + intel_uncore_rmw(&dev_priv->uncore, DSPFW3, DSPFW_CURSOR_SR_MASK, + FW_WM(wm, CURSOR_SR)); /* Display HPLL off SR */ wm = intel_calculate_wm(pixel_rate, &pnv_display_hplloff_wm, pnv_display_hplloff_wm.fifo_size, cpp, latency->display_hpll_disable); - reg = intel_uncore_read(&dev_priv->uncore, DSPFW3); - reg &= ~DSPFW_HPLL_SR_MASK; - reg |= FW_WM(wm, HPLL_SR); - intel_uncore_write(&dev_priv->uncore, DSPFW3, reg); + intel_uncore_rmw(&dev_priv->uncore, DSPFW3, DSPFW_HPLL_SR_MASK, FW_WM(wm, HPLL_SR)); /* cursor HPLL off SR */ wm = intel_calculate_wm(pixel_rate, &pnv_cursor_hplloff_wm, @@ -1337,34 +1324,14 @@ static bool g4x_compute_fbc_en(const struct g4x_wm_state *wm_state, return true; } -static int g4x_compute_pipe_wm(struct intel_atomic_state *state, - struct intel_crtc *crtc) +static int _g4x_compute_pipe_wm(struct intel_crtc_state *crtc_state) { - struct intel_crtc_state *crtc_state = - intel_atomic_get_new_crtc_state(state, crtc); + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct g4x_wm_state *wm_state = &crtc_state->wm.g4x.optimal; u8 active_planes = crtc_state->active_planes & ~BIT(PLANE_CURSOR); const struct g4x_pipe_wm *raw; - const struct intel_plane_state *old_plane_state; - const struct intel_plane_state *new_plane_state; - struct intel_plane *plane; enum plane_id plane_id; - int i, level; - unsigned int dirty = 0; - - for_each_oldnew_intel_plane_in_state(state, plane, - old_plane_state, - new_plane_state, i) { - if (new_plane_state->hw.crtc != &crtc->base && - old_plane_state->hw.crtc != &crtc->base) - continue; - - if (g4x_raw_plane_wm_compute(crtc_state, new_plane_state)) - dirty |= BIT(plane->id); - } - - if (!dirty) - return 0; + int level; level = G4X_WM_LEVEL_NORMAL; if (!g4x_raw_crtc_wm_is_valid(crtc_state, level)) @@ -1417,6 +1384,34 @@ static int g4x_compute_pipe_wm(struct intel_atomic_state *state, return 0; } +static int g4x_compute_pipe_wm(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + struct intel_crtc_state *crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); + const struct intel_plane_state *old_plane_state; + const struct intel_plane_state *new_plane_state; + struct intel_plane *plane; + unsigned int dirty = 0; + int i; + + for_each_oldnew_intel_plane_in_state(state, plane, + old_plane_state, + new_plane_state, i) { + if (new_plane_state->hw.crtc != &crtc->base && + old_plane_state->hw.crtc != &crtc->base) + continue; + + if (g4x_raw_plane_wm_compute(crtc_state, new_plane_state)) + dirty |= BIT(plane->id); + } + + if (!dirty) + return 0; + + return _g4x_compute_pipe_wm(crtc_state); +} + static int g4x_compute_intermediate_wm(struct intel_atomic_state *state, struct intel_crtc *crtc) { @@ -1431,7 +1426,7 @@ static int g4x_compute_intermediate_wm(struct intel_atomic_state *state, enum plane_id plane_id; if (!new_crtc_state->hw.active || - drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi)) { + intel_crtc_needs_modeset(new_crtc_state)) { *intermediate = *optimal; intermediate->cxsr = false; @@ -1857,64 +1852,17 @@ static bool vlv_raw_crtc_wm_is_valid(const struct intel_crtc_state *crtc_state, vlv_raw_plane_wm_is_valid(crtc_state, PLANE_CURSOR, level); } -static int vlv_compute_pipe_wm(struct intel_atomic_state *state, - struct intel_crtc *crtc) +static int _vlv_compute_pipe_wm(struct intel_crtc_state *crtc_state) { + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - struct intel_crtc_state *crtc_state = - intel_atomic_get_new_crtc_state(state, crtc); struct vlv_wm_state *wm_state = &crtc_state->wm.vlv.optimal; const struct vlv_fifo_state *fifo_state = &crtc_state->wm.vlv.fifo_state; u8 active_planes = crtc_state->active_planes & ~BIT(PLANE_CURSOR); int num_active_planes = hweight8(active_planes); - bool needs_modeset = drm_atomic_crtc_needs_modeset(&crtc_state->uapi); - const struct intel_plane_state *old_plane_state; - const struct intel_plane_state *new_plane_state; - struct intel_plane *plane; enum plane_id plane_id; - int level, ret, i; - unsigned int dirty = 0; - - for_each_oldnew_intel_plane_in_state(state, plane, - old_plane_state, - new_plane_state, i) { - if (new_plane_state->hw.crtc != &crtc->base && - old_plane_state->hw.crtc != &crtc->base) - continue; - - if (vlv_raw_plane_wm_compute(crtc_state, new_plane_state)) - dirty |= BIT(plane->id); - } - - /* - * DSPARB registers may have been reset due to the - * power well being turned off. Make sure we restore - * them to a consistent state even if no primary/sprite - * planes are initially active. - */ - if (needs_modeset) - crtc_state->fifo_changed = true; - - if (!dirty) - return 0; - - /* cursor changes don't warrant a FIFO recompute */ - if (dirty & ~BIT(PLANE_CURSOR)) { - const struct intel_crtc_state *old_crtc_state = - intel_atomic_get_old_crtc_state(state, crtc); - const struct vlv_fifo_state *old_fifo_state = - &old_crtc_state->wm.vlv.fifo_state; - - ret = vlv_compute_fifo(crtc_state); - if (ret) - return ret; - - if (needs_modeset || - memcmp(old_fifo_state, fifo_state, - sizeof(*fifo_state)) != 0) - crtc_state->fifo_changed = true; - } + int level; /* initially allow all levels */ wm_state->num_levels = intel_wm_num_levels(dev_priv); @@ -1961,6 +1909,66 @@ static int vlv_compute_pipe_wm(struct intel_atomic_state *state, return 0; } +static int vlv_compute_pipe_wm(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + struct intel_crtc_state *crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); + const struct intel_plane_state *old_plane_state; + const struct intel_plane_state *new_plane_state; + struct intel_plane *plane; + unsigned int dirty = 0; + int i; + + for_each_oldnew_intel_plane_in_state(state, plane, + old_plane_state, + new_plane_state, i) { + if (new_plane_state->hw.crtc != &crtc->base && + old_plane_state->hw.crtc != &crtc->base) + continue; + + if (vlv_raw_plane_wm_compute(crtc_state, new_plane_state)) + dirty |= BIT(plane->id); + } + + /* + * DSPARB registers may have been reset due to the + * power well being turned off. Make sure we restore + * them to a consistent state even if no primary/sprite + * planes are initially active. We also force a FIFO + * recomputation so that we are sure to sanitize the + * FIFO setting we took over from the BIOS even if there + * are no active planes on the crtc. + */ + if (intel_crtc_needs_modeset(crtc_state)) + dirty = ~0; + + if (!dirty) + return 0; + + /* cursor changes don't warrant a FIFO recompute */ + if (dirty & ~BIT(PLANE_CURSOR)) { + const struct intel_crtc_state *old_crtc_state = + intel_atomic_get_old_crtc_state(state, crtc); + const struct vlv_fifo_state *old_fifo_state = + &old_crtc_state->wm.vlv.fifo_state; + const struct vlv_fifo_state *new_fifo_state = + &crtc_state->wm.vlv.fifo_state; + int ret; + + ret = vlv_compute_fifo(crtc_state); + if (ret) + return ret; + + if (intel_crtc_needs_modeset(crtc_state) || + memcmp(old_fifo_state, new_fifo_state, + sizeof(*new_fifo_state)) != 0) + crtc_state->fifo_changed = true; + } + + return _vlv_compute_pipe_wm(crtc_state); +} + #define VLV_FIFO(plane, value) \ (((value) << DSPARB_ ## plane ## _SHIFT_VLV) & DSPARB_ ## plane ## _MASK_VLV) @@ -2075,7 +2083,7 @@ static int vlv_compute_intermediate_wm(struct intel_atomic_state *state, int level; if (!new_crtc_state->hw.active || - drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi)) { + intel_crtc_needs_modeset(new_crtc_state)) { *intermediate = *optimal; intermediate->cxsr = false; @@ -3133,7 +3141,7 @@ static int ilk_compute_intermediate_wm(struct intel_atomic_state *state, */ *a = new_crtc_state->wm.ilk.optimal; if (!new_crtc_state->hw.active || - drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi) || + intel_crtc_needs_modeset(new_crtc_state) || state->skip_intermediate_wm) return 0; @@ -3458,7 +3466,6 @@ static void ilk_write_wm_values(struct drm_i915_private *dev_priv, { struct ilk_wm_values *previous = &dev_priv->display.wm.hw; unsigned int dirty; - u32 val; dirty = ilk_compute_wm_dirty(dev_priv, previous, results); if (!dirty) @@ -3474,32 +3481,20 @@ static void ilk_write_wm_values(struct drm_i915_private *dev_priv, intel_uncore_write(&dev_priv->uncore, WM0_PIPE_ILK(PIPE_C), results->wm_pipe[2]); if (dirty & WM_DIRTY_DDB) { - if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) { - val = intel_uncore_read(&dev_priv->uncore, WM_MISC); - if (results->partitioning == INTEL_DDB_PART_1_2) - val &= ~WM_MISC_DATA_PARTITION_5_6; - else - val |= WM_MISC_DATA_PARTITION_5_6; - intel_uncore_write(&dev_priv->uncore, WM_MISC, val); - } else { - val = intel_uncore_read(&dev_priv->uncore, DISP_ARB_CTL2); - if (results->partitioning == INTEL_DDB_PART_1_2) - val &= ~DISP_DATA_PARTITION_5_6; - else - val |= DISP_DATA_PARTITION_5_6; - intel_uncore_write(&dev_priv->uncore, DISP_ARB_CTL2, val); - } - } - - if (dirty & WM_DIRTY_FBC) { - val = intel_uncore_read(&dev_priv->uncore, DISP_ARB_CTL); - if (results->enable_fbc_wm) - val &= ~DISP_FBC_WM_DIS; + if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) + intel_uncore_rmw(&dev_priv->uncore, WM_MISC, WM_MISC_DATA_PARTITION_5_6, + results->partitioning == INTEL_DDB_PART_1_2 ? 0 : + WM_MISC_DATA_PARTITION_5_6); else - val |= DISP_FBC_WM_DIS; - intel_uncore_write(&dev_priv->uncore, DISP_ARB_CTL, val); + intel_uncore_rmw(&dev_priv->uncore, DISP_ARB_CTL2, DISP_DATA_PARTITION_5_6, + results->partitioning == INTEL_DDB_PART_1_2 ? 0 : + DISP_DATA_PARTITION_5_6); } + if (dirty & WM_DIRTY_FBC) + intel_uncore_rmw(&dev_priv->uncore, DISP_ARB_CTL, DISP_FBC_WM_DIS, + results->enable_fbc_wm ? 0 : DISP_FBC_WM_DIS); + if (dirty & WM_DIRTY_LP(1) && previous->wm_lp_spr[0] != results->wm_lp_spr[0]) intel_uncore_write(&dev_priv->uncore, WM1S_LP_ILK, results->wm_lp_spr[0]); @@ -3824,6 +3819,8 @@ void g4x_wm_get_hw_state(struct drm_i915_private *dev_priv) plane_id, USHRT_MAX); g4x_raw_fbc_wm_set(crtc_state, level, USHRT_MAX); + g4x_invalidate_wms(crtc, active, level); + crtc_state->wm.g4x.optimal = *active; crtc_state->wm.g4x.intermediate = *active; @@ -3860,37 +3857,30 @@ void g4x_wm_sanitize(struct drm_i915_private *dev_priv) to_intel_crtc_state(crtc->base.state); struct intel_plane_state *plane_state = to_intel_plane_state(plane->base.state); - struct g4x_wm_state *wm_state = &crtc_state->wm.g4x.optimal; enum plane_id plane_id = plane->id; - int level; + int level, num_levels = intel_wm_num_levels(dev_priv); if (plane_state->uapi.visible) continue; - for (level = 0; level < 3; level++) { + for (level = 0; level < num_levels; level++) { struct g4x_pipe_wm *raw = &crtc_state->wm.g4x.raw[level]; raw->plane[plane_id] = 0; - wm_state->wm.plane[plane_id] = 0; - } - if (plane_id == PLANE_PRIMARY) { - for (level = 0; level < 3; level++) { - struct g4x_pipe_wm *raw = - &crtc_state->wm.g4x.raw[level]; + if (plane_id == PLANE_PRIMARY) raw->fbc = 0; - } - - wm_state->sr.fbc = 0; - wm_state->hpll.fbc = 0; - wm_state->fbc_en = false; } } for_each_intel_crtc(&dev_priv->drm, crtc) { struct intel_crtc_state *crtc_state = to_intel_crtc_state(crtc->base.state); + int ret; + + ret = _g4x_compute_pipe_wm(crtc_state); + drm_WARN_ON(&dev_priv->drm, ret); crtc_state->wm.g4x.intermediate = crtc_state->wm.g4x.optimal; @@ -4016,30 +4006,27 @@ void vlv_wm_sanitize(struct drm_i915_private *dev_priv) to_intel_crtc_state(crtc->base.state); struct intel_plane_state *plane_state = to_intel_plane_state(plane->base.state); - struct vlv_wm_state *wm_state = &crtc_state->wm.vlv.optimal; - const struct vlv_fifo_state *fifo_state = - &crtc_state->wm.vlv.fifo_state; enum plane_id plane_id = plane->id; - int level; + int level, num_levels = intel_wm_num_levels(dev_priv); if (plane_state->uapi.visible) continue; - for (level = 0; level < wm_state->num_levels; level++) { + for (level = 0; level < num_levels; level++) { struct g4x_pipe_wm *raw = &crtc_state->wm.vlv.raw[level]; raw->plane[plane_id] = 0; - - wm_state->wm[level].plane[plane_id] = - vlv_invert_wm_value(raw->plane[plane_id], - fifo_state->plane[plane_id]); } } for_each_intel_crtc(&dev_priv->drm, crtc) { struct intel_crtc_state *crtc_state = to_intel_crtc_state(crtc->base.state); + int ret; + + ret = _vlv_compute_pipe_wm(crtc_state); + drm_WARN_ON(&dev_priv->drm, ret); crtc_state->wm.vlv.intermediate = crtc_state->wm.vlv.optimal; @@ -4057,9 +4044,9 @@ void vlv_wm_sanitize(struct drm_i915_private *dev_priv) */ static void ilk_init_lp_watermarks(struct drm_i915_private *dev_priv) { - intel_uncore_write(&dev_priv->uncore, WM3_LP_ILK, intel_uncore_read(&dev_priv->uncore, WM3_LP_ILK) & ~WM_LP_ENABLE); - intel_uncore_write(&dev_priv->uncore, WM2_LP_ILK, intel_uncore_read(&dev_priv->uncore, WM2_LP_ILK) & ~WM_LP_ENABLE); - intel_uncore_write(&dev_priv->uncore, WM1_LP_ILK, intel_uncore_read(&dev_priv->uncore, WM1_LP_ILK) & ~WM_LP_ENABLE); + intel_uncore_rmw(&dev_priv->uncore, WM3_LP_ILK, WM_LP_ENABLE, 0); + intel_uncore_rmw(&dev_priv->uncore, WM2_LP_ILK, WM_LP_ENABLE, 0); + intel_uncore_rmw(&dev_priv->uncore, WM1_LP_ILK, WM_LP_ENABLE, 0); /* * Don't touch WM_LP_SPRITE_ENABLE here. @@ -4113,11 +4100,9 @@ static void g4x_disable_trickle_feed(struct drm_i915_private *dev_priv) enum pipe pipe; for_each_pipe(dev_priv, pipe) { - intel_uncore_write(&dev_priv->uncore, DSPCNTR(pipe), - intel_uncore_read(&dev_priv->uncore, DSPCNTR(pipe)) | - DISP_TRICKLE_FEED_DISABLE); + intel_uncore_rmw(&dev_priv->uncore, DSPCNTR(pipe), 0, DISP_TRICKLE_FEED_DISABLE); - intel_uncore_write(&dev_priv->uncore, DSPSURF(pipe), intel_uncore_read(&dev_priv->uncore, DSPSURF(pipe))); + intel_uncore_rmw(&dev_priv->uncore, DSPSURF(pipe), 0, 0); intel_uncore_posting_read(&dev_priv->uncore, DSPSURF(pipe)); } } @@ -4164,19 +4149,13 @@ static void ilk_init_clock_gating(struct drm_i915_private *dev_priv) */ if (IS_IRONLAKE_M(dev_priv)) { /* WaFbcAsynchFlipDisableFbcQueue:ilk */ - intel_uncore_write(&dev_priv->uncore, ILK_DISPLAY_CHICKEN1, - intel_uncore_read(&dev_priv->uncore, ILK_DISPLAY_CHICKEN1) | - ILK_FBCQ_DIS); - intel_uncore_write(&dev_priv->uncore, ILK_DISPLAY_CHICKEN2, - intel_uncore_read(&dev_priv->uncore, ILK_DISPLAY_CHICKEN2) | - ILK_DPARB_GATE); + intel_uncore_rmw(&dev_priv->uncore, ILK_DISPLAY_CHICKEN1, 0, ILK_FBCQ_DIS); + intel_uncore_rmw(&dev_priv->uncore, ILK_DISPLAY_CHICKEN2, 0, ILK_DPARB_GATE); } intel_uncore_write(&dev_priv->uncore, ILK_DSPCLK_GATE_D, dspclk_gate); - intel_uncore_write(&dev_priv->uncore, ILK_DISPLAY_CHICKEN2, - intel_uncore_read(&dev_priv->uncore, ILK_DISPLAY_CHICKEN2) | - ILK_ELPIN_409_SELECT); + intel_uncore_rmw(&dev_priv->uncore, ILK_DISPLAY_CHICKEN2, 0, ILK_ELPIN_409_SELECT); g4x_disable_trickle_feed(dev_priv); @@ -4196,8 +4175,7 @@ static void cpt_init_clock_gating(struct drm_i915_private *dev_priv) intel_uncore_write(&dev_priv->uncore, SOUTH_DSPCLK_GATE_D, PCH_DPLSUNIT_CLOCK_GATE_DISABLE | PCH_DPLUNIT_CLOCK_GATE_DISABLE | PCH_CPUNIT_CLOCK_GATE_DISABLE); - intel_uncore_write(&dev_priv->uncore, SOUTH_CHICKEN2, intel_uncore_read(&dev_priv->uncore, SOUTH_CHICKEN2) | - DPLS_EDP_PPS_FIX_DIS); + intel_uncore_rmw(&dev_priv->uncore, SOUTH_CHICKEN2, 0, DPLS_EDP_PPS_FIX_DIS); /* The below fixes the weird display corruption, a few pixels shifted * downward, on (only) LVDS of some HP laptops with IVY. */ @@ -4235,9 +4213,7 @@ static void gen6_init_clock_gating(struct drm_i915_private *dev_priv) intel_uncore_write(&dev_priv->uncore, ILK_DSPCLK_GATE_D, dspclk_gate); - intel_uncore_write(&dev_priv->uncore, ILK_DISPLAY_CHICKEN2, - intel_uncore_read(&dev_priv->uncore, ILK_DISPLAY_CHICKEN2) | - ILK_ELPIN_409_SELECT); + intel_uncore_rmw(&dev_priv->uncore, ILK_DISPLAY_CHICKEN2, 0, ILK_ELPIN_409_SELECT); intel_uncore_write(&dev_priv->uncore, GEN6_UCGCTL1, intel_uncore_read(&dev_priv->uncore, GEN6_UCGCTL1) | @@ -4297,14 +4273,12 @@ static void lpt_init_clock_gating(struct drm_i915_private *dev_priv) * disabled when not needed anymore in order to save power. */ if (HAS_PCH_LPT_LP(dev_priv)) - intel_uncore_write(&dev_priv->uncore, SOUTH_DSPCLK_GATE_D, - intel_uncore_read(&dev_priv->uncore, SOUTH_DSPCLK_GATE_D) | - PCH_LP_PARTITION_LEVEL_DISABLE); + intel_uncore_rmw(&dev_priv->uncore, SOUTH_DSPCLK_GATE_D, + 0, PCH_LP_PARTITION_LEVEL_DISABLE); /* WADPOClockGatingDisable:hsw */ - intel_uncore_write(&dev_priv->uncore, TRANS_CHICKEN1(PIPE_A), - intel_uncore_read(&dev_priv->uncore, TRANS_CHICKEN1(PIPE_A)) | - TRANS_CHICKEN1_DP0UNIT_GC_DISABLE); + intel_uncore_rmw(&dev_priv->uncore, TRANS_CHICKEN1(PIPE_A), + 0, TRANS_CHICKEN1_DP0UNIT_GC_DISABLE); } static void lpt_suspend_hw(struct drm_i915_private *dev_priv) @@ -4325,22 +4299,22 @@ static void gen8_set_l3sqc_credits(struct drm_i915_private *dev_priv, u32 val; /* WaTempDisableDOPClkGating:bdw */ - misccpctl = intel_uncore_read(&dev_priv->uncore, GEN7_MISCCPCTL); - intel_uncore_write(&dev_priv->uncore, GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE); + misccpctl = intel_gt_mcr_multicast_rmw(to_gt(dev_priv), GEN8_MISCCPCTL, + GEN8_DOP_CLOCK_GATE_ENABLE, 0); - val = intel_uncore_read(&dev_priv->uncore, GEN8_L3SQCREG1); + val = intel_gt_mcr_read_any(to_gt(dev_priv), GEN8_L3SQCREG1); val &= ~L3_PRIO_CREDITS_MASK; val |= L3_GENERAL_PRIO_CREDITS(general_prio_credits); val |= L3_HIGH_PRIO_CREDITS(high_prio_credits); - intel_uncore_write(&dev_priv->uncore, GEN8_L3SQCREG1, val); + intel_gt_mcr_multicast_write(to_gt(dev_priv), GEN8_L3SQCREG1, val); /* * Wait at least 100 clocks before re-enabling clock gating. * See the definition of L3SQCREG1 in BSpec. */ - intel_uncore_posting_read(&dev_priv->uncore, GEN8_L3SQCREG1); + intel_gt_mcr_read_any(to_gt(dev_priv), GEN8_L3SQCREG1); udelay(1); - intel_uncore_write(&dev_priv->uncore, GEN7_MISCCPCTL, misccpctl); + intel_gt_mcr_multicast_write(to_gt(dev_priv), GEN8_MISCCPCTL, misccpctl); } static void icl_init_clock_gating(struct drm_i915_private *dev_priv) @@ -4363,8 +4337,7 @@ static void gen12lp_init_clock_gating(struct drm_i915_private *dev_priv) /* Wa_1409825376:tgl (pre-prod)*/ if (IS_TGL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_C0)) - intel_uncore_write(&dev_priv->uncore, GEN9_CLKGATE_DIS_3, intel_uncore_read(&dev_priv->uncore, GEN9_CLKGATE_DIS_3) | - TGL_VRH_GATING_DIS); + intel_uncore_rmw(&dev_priv->uncore, GEN9_CLKGATE_DIS_3, 0, TGL_VRH_GATING_DIS); /* Wa_14013723622:tgl,rkl,dg1,adl-s */ if (DISPLAY_VER(dev_priv) == 12) @@ -4389,8 +4362,7 @@ static void dg1_init_clock_gating(struct drm_i915_private *dev_priv) /* Wa_1409836686:dg1[a0] */ if (IS_DG1_GRAPHICS_STEP(dev_priv, STEP_A0, STEP_B0)) - intel_uncore_write(&dev_priv->uncore, GEN9_CLKGATE_DIS_3, intel_uncore_read(&dev_priv->uncore, GEN9_CLKGATE_DIS_3) | - DPT_GATING_DIS); + intel_uncore_rmw(&dev_priv->uncore, GEN9_CLKGATE_DIS_3, 0, DPT_GATING_DIS); } static void xehpsdv_init_clock_gating(struct drm_i915_private *dev_priv) @@ -4432,8 +4404,7 @@ static void cnp_init_clock_gating(struct drm_i915_private *dev_priv) return; /* Display WA #1181 WaSouthDisplayDisablePWMCGEGating: cnp */ - intel_uncore_write(&dev_priv->uncore, SOUTH_DSPCLK_GATE_D, intel_uncore_read(&dev_priv->uncore, SOUTH_DSPCLK_GATE_D) | - CNP_PWM_CGE_GATING_DISABLE); + intel_uncore_rmw(&dev_priv->uncore, SOUTH_DSPCLK_GATE_D, 0, CNP_PWM_CGE_GATING_DISABLE); } static void cfl_init_clock_gating(struct drm_i915_private *dev_priv) @@ -4442,23 +4413,20 @@ static void cfl_init_clock_gating(struct drm_i915_private *dev_priv) gen9_init_clock_gating(dev_priv); /* WAC6entrylatency:cfl */ - intel_uncore_write(&dev_priv->uncore, FBC_LLC_READ_CTRL, intel_uncore_read(&dev_priv->uncore, FBC_LLC_READ_CTRL) | - FBC_LLC_FULLY_OPEN); + intel_uncore_rmw(&dev_priv->uncore, FBC_LLC_READ_CTRL, 0, FBC_LLC_FULLY_OPEN); /* * WaFbcTurnOffFbcWatermark:cfl * Display WA #0562: cfl */ - intel_uncore_write(&dev_priv->uncore, DISP_ARB_CTL, intel_uncore_read(&dev_priv->uncore, DISP_ARB_CTL) | - DISP_FBC_WM_DIS); + intel_uncore_rmw(&dev_priv->uncore, DISP_ARB_CTL, 0, DISP_FBC_WM_DIS); /* * WaFbcNukeOnHostModify:cfl * Display WA #0873: cfl */ - intel_uncore_write(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A), - intel_uncore_read(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A)) | - DPFC_NUKE_ON_ANY_MODIFICATION); + intel_uncore_rmw(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A), + 0, DPFC_NUKE_ON_ANY_MODIFICATION); } static void kbl_init_clock_gating(struct drm_i915_private *dev_priv) @@ -4466,33 +4434,30 @@ static void kbl_init_clock_gating(struct drm_i915_private *dev_priv) gen9_init_clock_gating(dev_priv); /* WAC6entrylatency:kbl */ - intel_uncore_write(&dev_priv->uncore, FBC_LLC_READ_CTRL, intel_uncore_read(&dev_priv->uncore, FBC_LLC_READ_CTRL) | - FBC_LLC_FULLY_OPEN); + intel_uncore_rmw(&dev_priv->uncore, FBC_LLC_READ_CTRL, 0, FBC_LLC_FULLY_OPEN); /* WaDisableSDEUnitClockGating:kbl */ if (IS_KBL_GRAPHICS_STEP(dev_priv, 0, STEP_C0)) - intel_uncore_write(&dev_priv->uncore, GEN8_UCGCTL6, intel_uncore_read(&dev_priv->uncore, GEN8_UCGCTL6) | - GEN8_SDEUNIT_CLOCK_GATE_DISABLE); + intel_uncore_rmw(&dev_priv->uncore, GEN8_UCGCTL6, + 0, GEN8_SDEUNIT_CLOCK_GATE_DISABLE); /* WaDisableGamClockGating:kbl */ if (IS_KBL_GRAPHICS_STEP(dev_priv, 0, STEP_C0)) - intel_uncore_write(&dev_priv->uncore, GEN6_UCGCTL1, intel_uncore_read(&dev_priv->uncore, GEN6_UCGCTL1) | - GEN6_GAMUNIT_CLOCK_GATE_DISABLE); + intel_uncore_rmw(&dev_priv->uncore, GEN6_UCGCTL1, + 0, GEN6_GAMUNIT_CLOCK_GATE_DISABLE); /* * WaFbcTurnOffFbcWatermark:kbl * Display WA #0562: kbl */ - intel_uncore_write(&dev_priv->uncore, DISP_ARB_CTL, intel_uncore_read(&dev_priv->uncore, DISP_ARB_CTL) | - DISP_FBC_WM_DIS); + intel_uncore_rmw(&dev_priv->uncore, DISP_ARB_CTL, 0, DISP_FBC_WM_DIS); /* * WaFbcNukeOnHostModify:kbl * Display WA #0873: kbl */ - intel_uncore_write(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A), - intel_uncore_read(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A)) | - DPFC_NUKE_ON_ANY_MODIFICATION); + intel_uncore_rmw(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A), + 0, DPFC_NUKE_ON_ANY_MODIFICATION); } static void skl_init_clock_gating(struct drm_i915_private *dev_priv) @@ -4500,35 +4465,30 @@ static void skl_init_clock_gating(struct drm_i915_private *dev_priv) gen9_init_clock_gating(dev_priv); /* WaDisableDopClockGating:skl */ - intel_uncore_write(&dev_priv->uncore, GEN7_MISCCPCTL, intel_uncore_read(&dev_priv->uncore, GEN7_MISCCPCTL) & - ~GEN7_DOP_CLOCK_GATE_ENABLE); + intel_gt_mcr_multicast_rmw(to_gt(dev_priv), GEN8_MISCCPCTL, + GEN8_DOP_CLOCK_GATE_ENABLE, 0); /* WAC6entrylatency:skl */ - intel_uncore_write(&dev_priv->uncore, FBC_LLC_READ_CTRL, intel_uncore_read(&dev_priv->uncore, FBC_LLC_READ_CTRL) | - FBC_LLC_FULLY_OPEN); + intel_uncore_rmw(&dev_priv->uncore, FBC_LLC_READ_CTRL, 0, FBC_LLC_FULLY_OPEN); /* * WaFbcTurnOffFbcWatermark:skl * Display WA #0562: skl */ - intel_uncore_write(&dev_priv->uncore, DISP_ARB_CTL, intel_uncore_read(&dev_priv->uncore, DISP_ARB_CTL) | - DISP_FBC_WM_DIS); + intel_uncore_rmw(&dev_priv->uncore, DISP_ARB_CTL, 0, DISP_FBC_WM_DIS); /* * WaFbcNukeOnHostModify:skl * Display WA #0873: skl */ - intel_uncore_write(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A), - intel_uncore_read(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A)) | - DPFC_NUKE_ON_ANY_MODIFICATION); + intel_uncore_rmw(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A), + 0, DPFC_NUKE_ON_ANY_MODIFICATION); /* * WaFbcHighMemBwCorruptionAvoidance:skl * Display WA #0883: skl */ - intel_uncore_write(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A), - intel_uncore_read(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A)) | - DPFC_DISABLE_DUMMY0); + intel_uncore_rmw(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A), 0, DPFC_DISABLE_DUMMY0); } static void bdw_init_clock_gating(struct drm_i915_private *dev_priv) @@ -4536,43 +4496,37 @@ static void bdw_init_clock_gating(struct drm_i915_private *dev_priv) enum pipe pipe; /* WaFbcAsynchFlipDisableFbcQueue:hsw,bdw */ - intel_uncore_write(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A), - intel_uncore_read(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A)) | - HSW_FBCQ_DIS); + intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A), 0, HSW_FBCQ_DIS); /* WaSwitchSolVfFArbitrationPriority:bdw */ - intel_uncore_write(&dev_priv->uncore, GAM_ECOCHK, intel_uncore_read(&dev_priv->uncore, GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL); + intel_uncore_rmw(&dev_priv->uncore, GAM_ECOCHK, 0, HSW_ECOCHK_ARB_PRIO_SOL); /* WaPsrDPAMaskVBlankInSRD:bdw */ - intel_uncore_write(&dev_priv->uncore, CHICKEN_PAR1_1, - intel_uncore_read(&dev_priv->uncore, CHICKEN_PAR1_1) | DPA_MASK_VBLANK_SRD); + intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PAR1_1, 0, DPA_MASK_VBLANK_SRD); for_each_pipe(dev_priv, pipe) { /* WaPsrDPRSUnmaskVBlankInSRD:bdw */ - intel_uncore_write(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe), - intel_uncore_read(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe)) | - BDW_DPRS_MASK_VBLANK_SRD); + intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe), + 0, BDW_DPRS_MASK_VBLANK_SRD); } /* WaVSRefCountFullforceMissDisable:bdw */ /* WaDSRefCountFullforceMissDisable:bdw */ - intel_uncore_write(&dev_priv->uncore, GEN7_FF_THREAD_MODE, - intel_uncore_read(&dev_priv->uncore, GEN7_FF_THREAD_MODE) & - ~(GEN8_FF_DS_REF_CNT_FFME | GEN7_FF_VS_REF_CNT_FFME)); + intel_uncore_rmw(&dev_priv->uncore, GEN7_FF_THREAD_MODE, + GEN8_FF_DS_REF_CNT_FFME | GEN7_FF_VS_REF_CNT_FFME, 0); intel_uncore_write(&dev_priv->uncore, RING_PSMI_CTL(RENDER_RING_BASE), _MASKED_BIT_ENABLE(GEN8_RC_SEMA_IDLE_MSG_DISABLE)); /* WaDisableSDEUnitClockGating:bdw */ - intel_uncore_write(&dev_priv->uncore, GEN8_UCGCTL6, intel_uncore_read(&dev_priv->uncore, GEN8_UCGCTL6) | - GEN8_SDEUNIT_CLOCK_GATE_DISABLE); + intel_uncore_rmw(&dev_priv->uncore, GEN8_UCGCTL6, 0, GEN8_SDEUNIT_CLOCK_GATE_DISABLE); /* WaProgramL3SqcReg1Default:bdw */ gen8_set_l3sqc_credits(dev_priv, 30, 2); /* WaKVMNotificationOnConfigChange:bdw */ - intel_uncore_write(&dev_priv->uncore, CHICKEN_PAR2_1, intel_uncore_read(&dev_priv->uncore, CHICKEN_PAR2_1) - | KVM_CONFIG_CHANGE_NOTIFICATION_SELECT); + intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PAR2_1, + 0, KVM_CONFIG_CHANGE_NOTIFICATION_SELECT); lpt_init_clock_gating(dev_priv); @@ -4581,38 +4535,30 @@ static void bdw_init_clock_gating(struct drm_i915_private *dev_priv) * Also see the CHICKEN2 write in bdw_init_workarounds() to disable DOP * clock gating. */ - intel_uncore_write(&dev_priv->uncore, GEN6_UCGCTL1, - intel_uncore_read(&dev_priv->uncore, GEN6_UCGCTL1) | GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE); + intel_uncore_rmw(&dev_priv->uncore, GEN6_UCGCTL1, 0, GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE); } static void hsw_init_clock_gating(struct drm_i915_private *dev_priv) { /* WaFbcAsynchFlipDisableFbcQueue:hsw,bdw */ - intel_uncore_write(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A), - intel_uncore_read(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A)) | - HSW_FBCQ_DIS); + intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A), 0, HSW_FBCQ_DIS); /* This is required by WaCatErrorRejectionIssue:hsw */ - intel_uncore_write(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG, - intel_uncore_read(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) | - GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB); + intel_uncore_rmw(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG, + 0, GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB); /* WaSwitchSolVfFArbitrationPriority:hsw */ - intel_uncore_write(&dev_priv->uncore, GAM_ECOCHK, intel_uncore_read(&dev_priv->uncore, GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL); + intel_uncore_rmw(&dev_priv->uncore, GAM_ECOCHK, 0, HSW_ECOCHK_ARB_PRIO_SOL); lpt_init_clock_gating(dev_priv); } static void ivb_init_clock_gating(struct drm_i915_private *dev_priv) { - u32 snpcr; - intel_uncore_write(&dev_priv->uncore, ILK_DSPCLK_GATE_D, ILK_VRHUNIT_CLOCK_GATE_DISABLE); /* WaFbcAsynchFlipDisableFbcQueue:ivb */ - intel_uncore_write(&dev_priv->uncore, ILK_DISPLAY_CHICKEN1, - intel_uncore_read(&dev_priv->uncore, ILK_DISPLAY_CHICKEN1) | - ILK_FBCQ_DIS); + intel_uncore_rmw(&dev_priv->uncore, ILK_DISPLAY_CHICKEN1, 0, ILK_FBCQ_DIS); /* WaDisableBackToBackFlipFix:ivb */ intel_uncore_write(&dev_priv->uncore, IVB_CHICKEN3, @@ -4638,16 +4584,13 @@ static void ivb_init_clock_gating(struct drm_i915_private *dev_priv) GEN6_RCZUNIT_CLOCK_GATE_DISABLE); /* This is required by WaCatErrorRejectionIssue:ivb */ - intel_uncore_write(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG, - intel_uncore_read(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) | - GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB); + intel_uncore_rmw(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG, + 0, GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB); g4x_disable_trickle_feed(dev_priv); - snpcr = intel_uncore_read(&dev_priv->uncore, GEN6_MBCUNIT_SNPCR); - snpcr &= ~GEN6_MBC_SNPCR_MASK; - snpcr |= GEN6_MBC_SNPCR_MED; - intel_uncore_write(&dev_priv->uncore, GEN6_MBCUNIT_SNPCR, snpcr); + intel_uncore_rmw(&dev_priv->uncore, GEN6_MBCUNIT_SNPCR, GEN6_MBC_SNPCR_MASK, + GEN6_MBC_SNPCR_MED); if (!HAS_PCH_NOP(dev_priv)) cpt_init_clock_gating(dev_priv); @@ -4667,9 +4610,8 @@ static void vlv_init_clock_gating(struct drm_i915_private *dev_priv) _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE)); /* This is required by WaCatErrorRejectionIssue:vlv */ - intel_uncore_write(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG, - intel_uncore_read(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) | - GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB); + intel_uncore_rmw(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG, + 0, GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB); /* * According to the spec, bit 13 (RCZUNIT) must be set on IVB. @@ -4681,8 +4623,7 @@ static void vlv_init_clock_gating(struct drm_i915_private *dev_priv) /* WaDisableL3Bank2xClockGate:vlv * Disabling L3 clock gating- MMIO 940c[25] = 1 * Set bit 25, to disable L3_BANK_2x_CLK_GATING */ - intel_uncore_write(&dev_priv->uncore, GEN7_UCGCTL4, - intel_uncore_read(&dev_priv->uncore, GEN7_UCGCTL4) | GEN7_L3BANK2X_CLOCK_GATE_DISABLE); + intel_uncore_rmw(&dev_priv->uncore, GEN7_UCGCTL4, 0, GEN7_L3BANK2X_CLOCK_GATE_DISABLE); /* * WaDisableVLVClockGating_VBIIssue:vlv @@ -4696,21 +4637,18 @@ static void chv_init_clock_gating(struct drm_i915_private *dev_priv) { /* WaVSRefCountFullforceMissDisable:chv */ /* WaDSRefCountFullforceMissDisable:chv */ - intel_uncore_write(&dev_priv->uncore, GEN7_FF_THREAD_MODE, - intel_uncore_read(&dev_priv->uncore, GEN7_FF_THREAD_MODE) & - ~(GEN8_FF_DS_REF_CNT_FFME | GEN7_FF_VS_REF_CNT_FFME)); + intel_uncore_rmw(&dev_priv->uncore, GEN7_FF_THREAD_MODE, + GEN8_FF_DS_REF_CNT_FFME | GEN7_FF_VS_REF_CNT_FFME, 0); /* WaDisableSemaphoreAndSyncFlipWait:chv */ intel_uncore_write(&dev_priv->uncore, RING_PSMI_CTL(RENDER_RING_BASE), _MASKED_BIT_ENABLE(GEN8_RC_SEMA_IDLE_MSG_DISABLE)); /* WaDisableCSUnitClockGating:chv */ - intel_uncore_write(&dev_priv->uncore, GEN6_UCGCTL1, intel_uncore_read(&dev_priv->uncore, GEN6_UCGCTL1) | - GEN6_CSUNIT_CLOCK_GATE_DISABLE); + intel_uncore_rmw(&dev_priv->uncore, GEN6_UCGCTL1, 0, GEN6_CSUNIT_CLOCK_GATE_DISABLE); /* WaDisableSDEUnitClockGating:chv */ - intel_uncore_write(&dev_priv->uncore, GEN8_UCGCTL6, intel_uncore_read(&dev_priv->uncore, GEN8_UCGCTL6) | - GEN8_SDEUNIT_CLOCK_GATE_DISABLE); + intel_uncore_rmw(&dev_priv->uncore, GEN8_UCGCTL6, 0, GEN8_SDEUNIT_CLOCK_GATE_DISABLE); /* * WaProgramL3SqcReg1Default:chv diff --git a/drivers/gpu/drm/i915/intel_region_ttm.c b/drivers/gpu/drm/i915/intel_region_ttm.c index 575d67bc6ffe..cf89d0c2a2d9 100644 --- a/drivers/gpu/drm/i915/intel_region_ttm.c +++ b/drivers/gpu/drm/i915/intel_region_ttm.c @@ -244,7 +244,7 @@ void intel_region_ttm_resource_free(struct intel_memory_region *mem, struct ttm_resource_manager *man = mem->region_private; struct ttm_buffer_object mock_bo = {}; - mock_bo.base.size = res->num_pages << PAGE_SHIFT; + mock_bo.base.size = res->size; mock_bo.bdev = &mem->i915->bdev; res->bo = &mock_bo; diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index 744cca507946..129746713d07 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -633,6 +633,8 @@ void intel_runtime_pm_driver_release(struct intel_runtime_pm *rpm) runtime_pm); int count = atomic_read(&rpm->wakeref_count); + intel_wakeref_auto_fini(&rpm->userfault_wakeref); + drm_WARN(&i915->drm, count, "i915 raw-wakerefs=%d wakelocks=%d on cleanup\n", intel_rpm_raw_wakeref_count(count), @@ -652,4 +654,7 @@ void intel_runtime_pm_init_early(struct intel_runtime_pm *rpm) rpm->available = HAS_RUNTIME_PM(i915); init_intel_runtime_pm_wakeref(rpm); + INIT_LIST_HEAD(&rpm->lmem_userfault_list); + spin_lock_init(&rpm->lmem_userfault_lock); + intel_wakeref_auto_init(&rpm->userfault_wakeref, rpm); } diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.h b/drivers/gpu/drm/i915/intel_runtime_pm.h index d9160e3ff4af..98b8b28baaa1 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.h +++ b/drivers/gpu/drm/i915/intel_runtime_pm.h @@ -53,6 +53,28 @@ struct intel_runtime_pm { bool irqs_enabled; bool no_wakeref_tracking; + /* + * Protects access to lmem usefault list. + * It is required, if we are outside of the runtime suspend path, + * access to @lmem_userfault_list requires always first grabbing the + * runtime pm, to ensure we can't race against runtime suspend. + * Once we have that we also need to grab @lmem_userfault_lock, + * at which point we have exclusive access. + * The runtime suspend path is special since it doesn't really hold any locks, + * but instead has exclusive access by virtue of all other accesses requiring + * holding the runtime pm wakeref. + */ + spinlock_t lmem_userfault_lock; + + /* + * Keep list of userfaulted gem obj, which require to release their + * mmap mappings at runtime suspend path. + */ + struct list_head lmem_userfault_list; + + /* Manual runtime pm autosuspend delay for user GGTT/lmem mmaps */ + struct intel_wakeref_auto userfault_wakeref; + #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM) /* * To aide detection of wakeref leaks and general misuse, we diff --git a/drivers/gpu/drm/i915/intel_step.c b/drivers/gpu/drm/i915/intel_step.c index 42b3133d8387..84a6fe736a3b 100644 --- a/drivers/gpu/drm/i915/intel_step.c +++ b/drivers/gpu/drm/i915/intel_step.c @@ -131,10 +131,27 @@ static const struct intel_step_info adls_rpls_revids[] = { [0xC] = { COMMON_GT_MEDIA_STEP(D0), .display_step = STEP_C0 }, }; +static const struct intel_step_info adlp_rplp_revids[] = { + [0x4] = { COMMON_GT_MEDIA_STEP(C0), .display_step = STEP_E0 }, +}; + static const struct intel_step_info adlp_n_revids[] = { [0x0] = { COMMON_GT_MEDIA_STEP(A0), .display_step = STEP_D0 }, }; +static u8 gmd_to_intel_step(struct drm_i915_private *i915, + struct intel_ip_version *gmd) +{ + u8 step = gmd->step + STEP_A0; + + if (step >= STEP_FUTURE) { + drm_dbg(&i915->drm, "Using future steppings\n"); + return STEP_FUTURE; + } + + return step; +} + static void pvc_step_init(struct drm_i915_private *i915, int pci_revid); void intel_step_init(struct drm_i915_private *i915) @@ -144,6 +161,18 @@ void intel_step_init(struct drm_i915_private *i915) int revid = INTEL_REVID(i915); struct intel_step_info step = {}; + if (HAS_GMD_ID(i915)) { + step.graphics_step = gmd_to_intel_step(i915, + &RUNTIME_INFO(i915)->graphics.ip); + step.media_step = gmd_to_intel_step(i915, + &RUNTIME_INFO(i915)->media.ip); + step.display_step = gmd_to_intel_step(i915, + &RUNTIME_INFO(i915)->display.ip); + RUNTIME_INFO(i915)->step = step; + + return; + } + if (IS_PONTEVECCHIO(i915)) { pvc_step_init(i915, revid); return; @@ -162,6 +191,9 @@ void intel_step_init(struct drm_i915_private *i915) } else if (IS_ADLP_N(i915)) { revids = adlp_n_revids; size = ARRAY_SIZE(adlp_n_revids); + } else if (IS_ADLP_RPLP(i915)) { + revids = adlp_rplp_revids; + size = ARRAY_SIZE(adlp_rplp_revids); } else if (IS_ALDERLAKE_P(i915)) { revids = adlp_revids; size = ARRAY_SIZE(adlp_revids); diff --git a/drivers/gpu/drm/i915/intel_step.h b/drivers/gpu/drm/i915/intel_step.h index a6b12bfa9744..96dfca4cba73 100644 --- a/drivers/gpu/drm/i915/intel_step.h +++ b/drivers/gpu/drm/i915/intel_step.h @@ -11,6 +11,10 @@ struct drm_i915_private; struct intel_step_info { + /* + * It is expected to have 4 number steps per letter. Deviation from + * the expectation breaks gmd_to_intel_step(). + */ u8 graphics_step; /* Represents the compute tile on Xe_HPC */ u8 display_step; u8 media_step; @@ -23,21 +27,43 @@ struct intel_step_info { func(A0) \ func(A1) \ func(A2) \ + func(A3) \ func(B0) \ func(B1) \ func(B2) \ func(B3) \ func(C0) \ func(C1) \ + func(C2) \ + func(C3) \ func(D0) \ func(D1) \ + func(D2) \ + func(D3) \ func(E0) \ + func(E1) \ + func(E2) \ + func(E3) \ func(F0) \ + func(F1) \ + func(F2) \ + func(F3) \ func(G0) \ + func(G1) \ + func(G2) \ + func(G3) \ func(H0) \ + func(H1) \ + func(H2) \ + func(H3) \ func(I0) \ func(I1) \ - func(J0) + func(I2) \ + func(I3) \ + func(J0) \ + func(J1) \ + func(J2) \ + func(J3) /* * Symbolic steppings that do not match the hardware. These are valid both as gt diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index 5cd423c7b646..614013745fca 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -29,6 +29,7 @@ #include "i915_drv.h" #include "i915_iosf_mbi.h" +#include "i915_reg.h" #include "i915_trace.h" #include "i915_vgpu.h" #include "intel_pm.h" @@ -104,6 +105,7 @@ static const char * const forcewake_domain_names[] = { "vebox1", "vebox2", "vebox3", + "gsc", }; const char * @@ -177,8 +179,9 @@ static inline void fw_domain_wait_ack_clear(const struct intel_uncore_forcewake_domain *d) { if (wait_ack_clear(d, FORCEWAKE_KERNEL)) { - DRM_ERROR("%s: timed out waiting for forcewake ack to clear.\n", - intel_uncore_forcewake_domain_to_str(d->id)); + drm_err(&d->uncore->i915->drm, + "%s: timed out waiting for forcewake ack to clear.\n", + intel_uncore_forcewake_domain_to_str(d->id)); add_taint_for_CI(d->uncore->i915, TAINT_WARN); /* CI now unreliable */ } } @@ -225,11 +228,12 @@ fw_domain_wait_ack_with_fallback(const struct intel_uncore_forcewake_domain *d, fw_clear(d, FORCEWAKE_KERNEL_FALLBACK); } while (!ack_detected && pass++ < 10); - DRM_DEBUG_DRIVER("%s had to use fallback to %s ack, 0x%x (passes %u)\n", - intel_uncore_forcewake_domain_to_str(d->id), - type == ACK_SET ? "set" : "clear", - fw_ack(d), - pass); + drm_dbg(&d->uncore->i915->drm, + "%s had to use fallback to %s ack, 0x%x (passes %u)\n", + intel_uncore_forcewake_domain_to_str(d->id), + type == ACK_SET ? "set" : "clear", + fw_ack(d), + pass); return ack_detected ? 0 : -ETIMEDOUT; } @@ -254,8 +258,9 @@ static inline void fw_domain_wait_ack_set(const struct intel_uncore_forcewake_domain *d) { if (wait_ack_set(d, FORCEWAKE_KERNEL)) { - DRM_ERROR("%s: timed out waiting for forcewake ack request.\n", - intel_uncore_forcewake_domain_to_str(d->id)); + drm_err(&d->uncore->i915->drm, + "%s: timed out waiting for forcewake ack request.\n", + intel_uncore_forcewake_domain_to_str(d->id)); add_taint_for_CI(d->uncore->i915, TAINT_WARN); /* CI now unreliable */ } } @@ -819,9 +824,9 @@ void intel_uncore_forcewake_flush(struct intel_uncore *uncore, } /** - * intel_uncore_forcewake_put__locked - grab forcewake domain references + * intel_uncore_forcewake_put__locked - release forcewake domain references * @uncore: the intel_uncore structure - * @fw_domains: forcewake domains to get reference on + * @fw_domains: forcewake domains to put references * * See intel_uncore_forcewake_put(). This variant places the onus * on the caller to explicitly handle the dev_priv->uncore.lock spinlock. @@ -888,10 +893,13 @@ void assert_forcewakes_active(struct intel_uncore *uncore, spin_unlock_irq(&uncore->lock); } -/* We give fast paths for the really cool registers */ +/* + * We give fast paths for the really cool registers. The second range includes + * media domains (and the GSC starting from Xe_LPM+) + */ #define NEEDS_FORCE_WAKE(reg) ({ \ u32 __reg = (reg); \ - __reg < 0x40000 || __reg >= GEN11_BSD_RING_BASE; \ + __reg < 0x40000 || __reg >= 0x116000; \ }) static int fw_range_cmp(u32 offset, const struct intel_forcewake_range *entry) @@ -1131,6 +1139,45 @@ static const struct i915_range pvc_shadowed_regs[] = { { .start = 0x1F8510, .end = 0x1F8550 }, }; +static const struct i915_range mtl_shadowed_regs[] = { + { .start = 0x2030, .end = 0x2030 }, + { .start = 0x2510, .end = 0x2550 }, + { .start = 0xA008, .end = 0xA00C }, + { .start = 0xA188, .end = 0xA188 }, + { .start = 0xA278, .end = 0xA278 }, + { .start = 0xA540, .end = 0xA56C }, + { .start = 0xC050, .end = 0xC050 }, + { .start = 0xC340, .end = 0xC340 }, + { .start = 0xC4C8, .end = 0xC4C8 }, + { .start = 0xC4E0, .end = 0xC4E0 }, + { .start = 0xC600, .end = 0xC600 }, + { .start = 0xC658, .end = 0xC658 }, + { .start = 0xCFD4, .end = 0xCFDC }, + { .start = 0x22030, .end = 0x22030 }, + { .start = 0x22510, .end = 0x22550 }, +}; + +static const struct i915_range xelpmp_shadowed_regs[] = { + { .start = 0x1C0030, .end = 0x1C0030 }, + { .start = 0x1C0510, .end = 0x1C0550 }, + { .start = 0x1C8030, .end = 0x1C8030 }, + { .start = 0x1C8510, .end = 0x1C8550 }, + { .start = 0x1D0030, .end = 0x1D0030 }, + { .start = 0x1D0510, .end = 0x1D0550 }, + { .start = 0x38A008, .end = 0x38A00C }, + { .start = 0x38A188, .end = 0x38A188 }, + { .start = 0x38A278, .end = 0x38A278 }, + { .start = 0x38A540, .end = 0x38A56C }, + { .start = 0x38A618, .end = 0x38A618 }, + { .start = 0x38C050, .end = 0x38C050 }, + { .start = 0x38C340, .end = 0x38C340 }, + { .start = 0x38C4C8, .end = 0x38C4C8 }, + { .start = 0x38C4E0, .end = 0x38C4E4 }, + { .start = 0x38C600, .end = 0x38C600 }, + { .start = 0x38C658, .end = 0x38C658 }, + { .start = 0x38CFD4, .end = 0x38CFDC }, +}; + static int mmio_range_cmp(u32 key, const struct i915_range *range) { if (key < range->start) @@ -1639,25 +1686,27 @@ static const struct intel_forcewake_range __pvc_fw_ranges[] = { GEN_FW_RANGE(0x12000, 0x12fff, 0), /* 0x12000 - 0x127ff: always on 0x12800 - 0x12fff: reserved */ - GEN_FW_RANGE(0x13000, 0x23fff, FORCEWAKE_GT), /* + GEN_FW_RANGE(0x13000, 0x19fff, FORCEWAKE_GT), /* 0x13000 - 0x135ff: gt 0x13600 - 0x147ff: reserved 0x14800 - 0x153ff: gt - 0x15400 - 0x19fff: reserved - 0x1a000 - 0x1ffff: gt - 0x20000 - 0x21fff: reserved - 0x22000 - 0x23fff: gt */ + 0x15400 - 0x19fff: reserved */ + GEN_FW_RANGE(0x1a000, 0x21fff, FORCEWAKE_RENDER), /* + 0x1a000 - 0x1ffff: render + 0x20000 - 0x21fff: reserved */ + GEN_FW_RANGE(0x22000, 0x23fff, FORCEWAKE_GT), GEN_FW_RANGE(0x24000, 0x2417f, 0), /* 24000 - 0x2407f: always on 24080 - 0x2417f: reserved */ - GEN_FW_RANGE(0x24180, 0x3ffff, FORCEWAKE_GT), /* + GEN_FW_RANGE(0x24180, 0x25fff, FORCEWAKE_GT), /* 0x24180 - 0x241ff: gt 0x24200 - 0x251ff: reserved 0x25200 - 0x252ff: gt - 0x25300 - 0x25fff: reserved - 0x26000 - 0x27fff: gt - 0x28000 - 0x2ffff: reserved - 0x30000 - 0x3ffff: gt */ + 0x25300 - 0x25fff: reserved */ + GEN_FW_RANGE(0x26000, 0x2ffff, FORCEWAKE_RENDER), /* + 0x26000 - 0x27fff: render + 0x28000 - 0x2ffff: reserved */ + GEN_FW_RANGE(0x30000, 0x3ffff, FORCEWAKE_GT), GEN_FW_RANGE(0x40000, 0x1bffff, 0), GEN_FW_RANGE(0x1c0000, 0x1c3fff, FORCEWAKE_MEDIA_VDBOX0), /* 0x1c0000 - 0x1c2bff: VD0 @@ -1679,6 +1728,162 @@ static const struct intel_forcewake_range __pvc_fw_ranges[] = { GEN_FW_RANGE(0x3e0000, 0x3effff, FORCEWAKE_GT), }; +static const struct intel_forcewake_range __mtl_fw_ranges[] = { + GEN_FW_RANGE(0x0, 0xaff, 0), + GEN_FW_RANGE(0xb00, 0xbff, FORCEWAKE_GT), + GEN_FW_RANGE(0xc00, 0xfff, 0), + GEN_FW_RANGE(0x1000, 0x1fff, FORCEWAKE_GT), + GEN_FW_RANGE(0x2000, 0x26ff, FORCEWAKE_RENDER), + GEN_FW_RANGE(0x2700, 0x2fff, FORCEWAKE_GT), + GEN_FW_RANGE(0x3000, 0x3fff, FORCEWAKE_RENDER), + GEN_FW_RANGE(0x4000, 0x51ff, FORCEWAKE_GT), /* + 0x4000 - 0x48ff: render + 0x4900 - 0x51ff: reserved */ + GEN_FW_RANGE(0x5200, 0x7fff, FORCEWAKE_RENDER), /* + 0x5200 - 0x53ff: render + 0x5400 - 0x54ff: reserved + 0x5500 - 0x7fff: render */ + GEN_FW_RANGE(0x8000, 0x813f, FORCEWAKE_GT), + GEN_FW_RANGE(0x8140, 0x817f, FORCEWAKE_RENDER), /* + 0x8140 - 0x815f: render + 0x8160 - 0x817f: reserved */ + GEN_FW_RANGE(0x8180, 0x81ff, 0), + GEN_FW_RANGE(0x8200, 0x94cf, FORCEWAKE_GT), /* + 0x8200 - 0x87ff: gt + 0x8800 - 0x8dff: reserved + 0x8e00 - 0x8f7f: gt + 0x8f80 - 0x8fff: reserved + 0x9000 - 0x947f: gt + 0x9480 - 0x94cf: reserved */ + GEN_FW_RANGE(0x94d0, 0x955f, FORCEWAKE_RENDER), + GEN_FW_RANGE(0x9560, 0x967f, 0), /* + 0x9560 - 0x95ff: always on + 0x9600 - 0x967f: reserved */ + GEN_FW_RANGE(0x9680, 0x97ff, FORCEWAKE_RENDER), /* + 0x9680 - 0x96ff: render + 0x9700 - 0x97ff: reserved */ + GEN_FW_RANGE(0x9800, 0xcfff, FORCEWAKE_GT), /* + 0x9800 - 0xb4ff: gt + 0xb500 - 0xbfff: reserved + 0xc000 - 0xcfff: gt */ + GEN_FW_RANGE(0xd000, 0xd7ff, 0), /* + 0xd000 - 0xd3ff: always on + 0xd400 - 0xd7ff: reserved */ + GEN_FW_RANGE(0xd800, 0xd87f, FORCEWAKE_RENDER), + GEN_FW_RANGE(0xd880, 0xdbff, FORCEWAKE_GT), + GEN_FW_RANGE(0xdc00, 0xdcff, FORCEWAKE_RENDER), + GEN_FW_RANGE(0xdd00, 0xde7f, FORCEWAKE_GT), /* + 0xdd00 - 0xddff: gt + 0xde00 - 0xde7f: reserved */ + GEN_FW_RANGE(0xde80, 0xe8ff, FORCEWAKE_RENDER), /* + 0xde80 - 0xdfff: render + 0xe000 - 0xe0ff: reserved + 0xe100 - 0xe8ff: render */ + GEN_FW_RANGE(0xe900, 0xe9ff, FORCEWAKE_GT), + GEN_FW_RANGE(0xea00, 0x147ff, 0), /* + 0xea00 - 0x11fff: reserved + 0x12000 - 0x127ff: always on + 0x12800 - 0x147ff: reserved */ + GEN_FW_RANGE(0x14800, 0x19fff, FORCEWAKE_GT), /* + 0x14800 - 0x153ff: gt + 0x15400 - 0x19fff: reserved */ + GEN_FW_RANGE(0x1a000, 0x21fff, FORCEWAKE_RENDER), /* + 0x1a000 - 0x1bfff: render + 0x1c000 - 0x21fff: reserved */ + GEN_FW_RANGE(0x22000, 0x23fff, FORCEWAKE_GT), + GEN_FW_RANGE(0x24000, 0x2ffff, 0), /* + 0x24000 - 0x2407f: always on + 0x24080 - 0x2ffff: reserved */ + GEN_FW_RANGE(0x30000, 0x3ffff, FORCEWAKE_GT) +}; + +/* + * Note that the register ranges here are the final offsets after + * translation of the GSI block to the 0x380000 offset. + * + * NOTE: There are a couple MCR ranges near the bottom of this table + * that need to power up either VD0 or VD2 depending on which replicated + * instance of the register we're trying to access. Our forcewake logic + * at the moment doesn't have a good way to take steering into consideration, + * and the driver doesn't even access any registers in those ranges today, + * so for now we just mark those ranges as FORCEWAKE_ALL. That will ensure + * proper operation if we do start using the ranges in the future, and we + * can determine at that time whether it's worth adding extra complexity to + * the forcewake handling to take steering into consideration. + */ +static const struct intel_forcewake_range __xelpmp_fw_ranges[] = { + GEN_FW_RANGE(0x0, 0x115fff, 0), /* render GT range */ + GEN_FW_RANGE(0x116000, 0x11ffff, FORCEWAKE_GSC), /* + 0x116000 - 0x117fff: gsc + 0x118000 - 0x119fff: reserved + 0x11a000 - 0x11efff: gsc + 0x11f000 - 0x11ffff: reserved */ + GEN_FW_RANGE(0x120000, 0x1bffff, 0), /* non-GT range */ + GEN_FW_RANGE(0x1c0000, 0x1c7fff, FORCEWAKE_MEDIA_VDBOX0), /* + 0x1c0000 - 0x1c3dff: VD0 + 0x1c3e00 - 0x1c3eff: reserved + 0x1c3f00 - 0x1c3fff: VD0 + 0x1c4000 - 0x1c7fff: reserved */ + GEN_FW_RANGE(0x1c8000, 0x1cbfff, FORCEWAKE_MEDIA_VEBOX0), /* + 0x1c8000 - 0x1ca0ff: VE0 + 0x1ca100 - 0x1cbfff: reserved */ + GEN_FW_RANGE(0x1cc000, 0x1cffff, FORCEWAKE_MEDIA_VDBOX0), /* + 0x1cc000 - 0x1cdfff: VD0 + 0x1ce000 - 0x1cffff: reserved */ + GEN_FW_RANGE(0x1d0000, 0x1d7fff, FORCEWAKE_MEDIA_VDBOX2), /* + 0x1d0000 - 0x1d3dff: VD2 + 0x1d3e00 - 0x1d3eff: reserved + 0x1d4000 - 0x1d7fff: VD2 */ + GEN_FW_RANGE(0x1d8000, 0x1da0ff, FORCEWAKE_MEDIA_VEBOX1), + GEN_FW_RANGE(0x1da100, 0x380aff, 0), /* + 0x1da100 - 0x23ffff: reserved + 0x240000 - 0x37ffff: non-GT range + 0x380000 - 0x380aff: reserved */ + GEN_FW_RANGE(0x380b00, 0x380bff, FORCEWAKE_GT), + GEN_FW_RANGE(0x380c00, 0x380fff, 0), + GEN_FW_RANGE(0x381000, 0x38817f, FORCEWAKE_GT), /* + 0x381000 - 0x381fff: gt + 0x382000 - 0x383fff: reserved + 0x384000 - 0x384aff: gt + 0x384b00 - 0x3851ff: reserved + 0x385200 - 0x3871ff: gt + 0x387200 - 0x387fff: reserved + 0x388000 - 0x38813f: gt + 0x388140 - 0x38817f: reserved */ + GEN_FW_RANGE(0x388180, 0x3882ff, 0), /* + 0x388180 - 0x3881ff: always on + 0x388200 - 0x3882ff: reserved */ + GEN_FW_RANGE(0x388300, 0x38955f, FORCEWAKE_GT), /* + 0x388300 - 0x38887f: gt + 0x388880 - 0x388fff: reserved + 0x389000 - 0x38947f: gt + 0x389480 - 0x38955f: reserved */ + GEN_FW_RANGE(0x389560, 0x389fff, 0), /* + 0x389560 - 0x3895ff: always on + 0x389600 - 0x389fff: reserved */ + GEN_FW_RANGE(0x38a000, 0x38cfff, FORCEWAKE_GT), /* + 0x38a000 - 0x38afff: gt + 0x38b000 - 0x38bfff: reserved + 0x38c000 - 0x38cfff: gt */ + GEN_FW_RANGE(0x38d000, 0x38d11f, 0), + GEN_FW_RANGE(0x38d120, 0x391fff, FORCEWAKE_GT), /* + 0x38d120 - 0x38dfff: gt + 0x38e000 - 0x38efff: reserved + 0x38f000 - 0x38ffff: gt + 0x389000 - 0x391fff: reserved */ + GEN_FW_RANGE(0x392000, 0x392fff, 0), /* + 0x392000 - 0x3927ff: always on + 0x392800 - 0x292fff: reserved */ + GEN_FW_RANGE(0x393000, 0x3931ff, FORCEWAKE_GT), + GEN_FW_RANGE(0x393200, 0x39323f, FORCEWAKE_ALL), /* instance-based, see note above */ + GEN_FW_RANGE(0x393240, 0x3933ff, FORCEWAKE_GT), + GEN_FW_RANGE(0x393400, 0x3934ff, FORCEWAKE_ALL), /* instance-based, see note above */ + GEN_FW_RANGE(0x393500, 0x393c7f, 0), /* + 0x393500 - 0x393bff: reserved + 0x393c00 - 0x393c7f: always on */ + GEN_FW_RANGE(0x393c80, 0x393dff, FORCEWAKE_GT), +}; + static void ilk_dummy_write(struct intel_uncore *uncore) { @@ -2021,6 +2226,7 @@ static int __fw_domain_init(struct intel_uncore *uncore, BUILD_BUG_ON(FORCEWAKE_MEDIA_VEBOX1 != (1 << FW_DOMAIN_ID_MEDIA_VEBOX1)); BUILD_BUG_ON(FORCEWAKE_MEDIA_VEBOX2 != (1 << FW_DOMAIN_ID_MEDIA_VEBOX2)); BUILD_BUG_ON(FORCEWAKE_MEDIA_VEBOX3 != (1 << FW_DOMAIN_ID_MEDIA_VEBOX3)); + BUILD_BUG_ON(FORCEWAKE_GSC != (1 << FW_DOMAIN_ID_GSC)); d->mask = BIT(domain_id); @@ -2085,17 +2291,26 @@ static int intel_uncore_fw_domains_init(struct intel_uncore *uncore) (ret ?: (ret = __fw_domain_init((uncore__), (id__), (set__), (ack__)))) if (GRAPHICS_VER(i915) >= 11) { - /* we'll prune the domains of missing engines later */ - intel_engine_mask_t emask = RUNTIME_INFO(i915)->platform_engine_mask; + intel_engine_mask_t emask; int i; + /* we'll prune the domains of missing engines later */ + emask = uncore->gt->info.engine_mask; + uncore->fw_get_funcs = &uncore_get_fallback; - fw_domain_init(uncore, FW_DOMAIN_ID_RENDER, - FORCEWAKE_RENDER_GEN9, - FORCEWAKE_ACK_RENDER_GEN9); - fw_domain_init(uncore, FW_DOMAIN_ID_GT, - FORCEWAKE_GT_GEN9, - FORCEWAKE_ACK_GT_GEN9); + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) + fw_domain_init(uncore, FW_DOMAIN_ID_GT, + FORCEWAKE_GT_GEN9, + FORCEWAKE_ACK_GT_MTL); + else + fw_domain_init(uncore, FW_DOMAIN_ID_GT, + FORCEWAKE_GT_GEN9, + FORCEWAKE_ACK_GT_GEN9); + + if (RCS_MASK(uncore->gt) || CCS_MASK(uncore->gt)) + fw_domain_init(uncore, FW_DOMAIN_ID_RENDER, + FORCEWAKE_RENDER_GEN9, + FORCEWAKE_ACK_RENDER_GEN9); for (i = 0; i < I915_MAX_VCS; i++) { if (!__HAS_ENGINE(emask, _VCS(i))) @@ -2113,6 +2328,10 @@ static int intel_uncore_fw_domains_init(struct intel_uncore *uncore) FORCEWAKE_MEDIA_VEBOX_GEN11(i), FORCEWAKE_ACK_MEDIA_VEBOX_GEN11(i)); } + + if (uncore->gt->type == GT_MEDIA) + fw_domain_init(uncore, FW_DOMAIN_ID_GSC, + FORCEWAKE_REQ_GSC, FORCEWAKE_ACK_GSC); } else if (IS_GRAPHICS_VER(i915, 9, 10)) { uncore->fw_get_funcs = &uncore_get_fallback; fw_domain_init(uncore, FW_DOMAIN_ID_RENDER, @@ -2300,6 +2519,22 @@ static void uncore_raw_init(struct intel_uncore *uncore) } } +static int uncore_media_forcewake_init(struct intel_uncore *uncore) +{ + struct drm_i915_private *i915 = uncore->i915; + + if (MEDIA_VER(i915) >= 13) { + ASSIGN_FW_DOMAINS_TABLE(uncore, __xelpmp_fw_ranges); + ASSIGN_SHADOW_TABLE(uncore, xelpmp_shadowed_regs); + ASSIGN_WRITE_MMIO_VFUNCS(uncore, fwtable); + } else { + MISSING_CASE(MEDIA_VER(i915)); + return -ENODEV; + } + + return 0; +} + static int uncore_forcewake_init(struct intel_uncore *uncore) { struct drm_i915_private *i915 = uncore->i915; @@ -2314,7 +2549,14 @@ static int uncore_forcewake_init(struct intel_uncore *uncore) ASSIGN_READ_MMIO_VFUNCS(uncore, fwtable); - if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 60)) { + if (uncore->gt->type == GT_MEDIA) + return uncore_media_forcewake_init(uncore); + + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) { + ASSIGN_FW_DOMAINS_TABLE(uncore, __mtl_fw_ranges); + ASSIGN_SHADOW_TABLE(uncore, mtl_shadowed_regs); + ASSIGN_WRITE_MMIO_VFUNCS(uncore, fwtable); + } else if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 60)) { ASSIGN_FW_DOMAINS_TABLE(uncore, __pvc_fw_ranges); ASSIGN_SHADOW_TABLE(uncore, pvc_shadowed_regs); ASSIGN_WRITE_MMIO_VFUNCS(uncore, fwtable); diff --git a/drivers/gpu/drm/i915/intel_uncore.h b/drivers/gpu/drm/i915/intel_uncore.h index 5022bac80b67..e9e38490815d 100644 --- a/drivers/gpu/drm/i915/intel_uncore.h +++ b/drivers/gpu/drm/i915/intel_uncore.h @@ -62,6 +62,7 @@ enum forcewake_domain_id { FW_DOMAIN_ID_MEDIA_VEBOX1, FW_DOMAIN_ID_MEDIA_VEBOX2, FW_DOMAIN_ID_MEDIA_VEBOX3, + FW_DOMAIN_ID_GSC, FW_DOMAIN_ID_COUNT }; @@ -82,6 +83,7 @@ enum forcewake_domains { FORCEWAKE_MEDIA_VEBOX1 = BIT(FW_DOMAIN_ID_MEDIA_VEBOX1), FORCEWAKE_MEDIA_VEBOX2 = BIT(FW_DOMAIN_ID_MEDIA_VEBOX2), FORCEWAKE_MEDIA_VEBOX3 = BIT(FW_DOMAIN_ID_MEDIA_VEBOX3), + FORCEWAKE_GSC = BIT(FW_DOMAIN_ID_GSC), FORCEWAKE_ALL = BIT(FW_DOMAIN_ID_COUNT) - 1, }; @@ -380,20 +382,6 @@ __uncore_write(write_notrace, 32, l, false) */ __uncore_read(read64, 64, q, true) -static inline u64 -intel_uncore_read64_2x32(struct intel_uncore *uncore, - i915_reg_t lower_reg, i915_reg_t upper_reg) -{ - u32 upper, lower, old_upper, loop = 0; - upper = intel_uncore_read(uncore, upper_reg); - do { - old_upper = upper; - lower = intel_uncore_read(uncore, lower_reg); - upper = intel_uncore_read(uncore, upper_reg); - } while (upper != old_upper && loop++ < 2); - return (u64)upper << 32 | lower; -} - #define intel_uncore_posting_read(...) ((void)intel_uncore_read_notrace(__VA_ARGS__)) #define intel_uncore_posting_read16(...) ((void)intel_uncore_read16_notrace(__VA_ARGS__)) @@ -431,15 +419,15 @@ intel_uncore_read64_2x32(struct intel_uncore *uncore, #define intel_uncore_write64_fw(...) __raw_uncore_write64(__VA_ARGS__) #define intel_uncore_posting_read_fw(...) ((void)intel_uncore_read_fw(__VA_ARGS__)) -static inline void intel_uncore_rmw(struct intel_uncore *uncore, - i915_reg_t reg, u32 clear, u32 set) +static inline u32 intel_uncore_rmw(struct intel_uncore *uncore, + i915_reg_t reg, u32 clear, u32 set) { u32 old, val; old = intel_uncore_read(uncore, reg); val = (old & ~clear) | set; - if (val != old) - intel_uncore_write(uncore, reg, val); + intel_uncore_write(uncore, reg, val); + return old; } static inline void intel_uncore_rmw_fw(struct intel_uncore *uncore, @@ -453,6 +441,36 @@ static inline void intel_uncore_rmw_fw(struct intel_uncore *uncore, intel_uncore_write_fw(uncore, reg, val); } +static inline u64 +intel_uncore_read64_2x32(struct intel_uncore *uncore, + i915_reg_t lower_reg, i915_reg_t upper_reg) +{ + u32 upper, lower, old_upper, loop = 0; + enum forcewake_domains fw_domains; + unsigned long flags; + + fw_domains = intel_uncore_forcewake_for_reg(uncore, lower_reg, + FW_REG_READ); + + fw_domains |= intel_uncore_forcewake_for_reg(uncore, upper_reg, + FW_REG_READ); + + spin_lock_irqsave(&uncore->lock, flags); + intel_uncore_forcewake_get__locked(uncore, fw_domains); + + upper = intel_uncore_read_fw(uncore, upper_reg); + do { + old_upper = upper; + lower = intel_uncore_read_fw(uncore, lower_reg); + upper = intel_uncore_read_fw(uncore, upper_reg); + } while (upper != old_upper && loop++ < 2); + + intel_uncore_forcewake_put__locked(uncore, fw_domains); + spin_unlock_irqrestore(&uncore->lock, flags); + + return (u64)upper << 32 | lower; +} + static inline int intel_uncore_write_and_verify(struct intel_uncore *uncore, i915_reg_t reg, u32 val, u32 mask, u32 expected_val) diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp.c b/drivers/gpu/drm/i915/pxp/intel_pxp.c index 69cdaaddc4a9..5efe61f67546 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp.c @@ -103,19 +103,15 @@ static int create_vcs_context(struct intel_pxp *pxp) static void destroy_vcs_context(struct intel_pxp *pxp) { - intel_engine_destroy_pinned_context(fetch_and_zero(&pxp->ce)); + if (pxp->ce) + intel_engine_destroy_pinned_context(fetch_and_zero(&pxp->ce)); } -void intel_pxp_init(struct intel_pxp *pxp) +static void pxp_init_full(struct intel_pxp *pxp) { struct intel_gt *gt = pxp_to_gt(pxp); int ret; - if (!HAS_PXP(gt->i915)) - return; - - mutex_init(&pxp->tee_mutex); - /* * we'll use the completion to check if there is a termination pending, * so we start it as completed and we reinit it when a termination @@ -124,8 +120,7 @@ void intel_pxp_init(struct intel_pxp *pxp) init_completion(&pxp->termination); complete_all(&pxp->termination); - mutex_init(&pxp->arb_mutex); - INIT_WORK(&pxp->session_work, intel_pxp_session_work); + intel_pxp_session_management_init(pxp); ret = create_vcs_context(pxp); if (ret) @@ -143,11 +138,26 @@ out_context: destroy_vcs_context(pxp); } -void intel_pxp_fini(struct intel_pxp *pxp) +void intel_pxp_init(struct intel_pxp *pxp) { - if (!intel_pxp_is_enabled(pxp)) + struct intel_gt *gt = pxp_to_gt(pxp); + + /* we rely on the mei PXP module */ + if (!IS_ENABLED(CONFIG_INTEL_MEI_PXP)) return; + /* + * If HuC is loaded by GSC but PXP is disabled, we can skip the init of + * the full PXP session/object management and just init the tee channel. + */ + if (HAS_PXP(gt->i915)) + pxp_init_full(pxp); + else if (intel_huc_is_loaded_by_gsc(>->uc.huc) && intel_uc_uses_huc(>->uc)) + intel_pxp_tee_component_init(pxp); +} + +void intel_pxp_fini(struct intel_pxp *pxp) +{ pxp->arb_is_valid = false; intel_pxp_tee_component_fini(pxp); diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp.h b/drivers/gpu/drm/i915/pxp/intel_pxp.h index 73847e535cab..2da309088c6d 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp.h @@ -12,7 +12,6 @@ struct intel_pxp; struct drm_i915_gem_object; -#ifdef CONFIG_DRM_I915_PXP struct intel_gt *pxp_to_gt(const struct intel_pxp *pxp); bool intel_pxp_is_enabled(const struct intel_pxp *pxp); bool intel_pxp_is_active(const struct intel_pxp *pxp); @@ -32,36 +31,5 @@ int intel_pxp_key_check(struct intel_pxp *pxp, bool assign); void intel_pxp_invalidate(struct intel_pxp *pxp); -#else -static inline void intel_pxp_init(struct intel_pxp *pxp) -{ -} - -static inline void intel_pxp_fini(struct intel_pxp *pxp) -{ -} - -static inline int intel_pxp_start(struct intel_pxp *pxp) -{ - return -ENODEV; -} - -static inline bool intel_pxp_is_enabled(const struct intel_pxp *pxp) -{ - return false; -} - -static inline bool intel_pxp_is_active(const struct intel_pxp *pxp) -{ - return false; -} - -static inline int intel_pxp_key_check(struct intel_pxp *pxp, - struct drm_i915_gem_object *obj, - bool assign) -{ - return -ENODEV; -} -#endif #endif /* __INTEL_PXP_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_42.h b/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_42.h new file mode 100644 index 000000000000..739f9072fa5f --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_42.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright(c) 2020, Intel Corporation. All rights reserved. + */ + +#ifndef __INTEL_PXP_FW_INTERFACE_42_H__ +#define __INTEL_PXP_FW_INTERFACE_42_H__ + +#include <linux/types.h> +#include "intel_pxp_cmd_interface_cmn.h" + +/* PXP-Opcode for Init Session */ +#define PXP42_CMDID_INIT_SESSION 0x1e + +/* PXP-Input-Packet: Init Session (Arb-Session) */ +struct pxp42_create_arb_in { + struct pxp_cmd_header header; + u32 protection_mode; +#define PXP42_ARB_SESSION_MODE_HEAVY 0x2 + u32 session_id; +} __packed; + +/* PXP-Output-Packet: Init Session */ +struct pxp42_create_arb_out { + struct pxp_cmd_header header; +} __packed; + +#endif /* __INTEL_PXP_FW_INTERFACE_42_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_43.h b/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_43.h new file mode 100644 index 000000000000..ad67e3f49c20 --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_43.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright(c) 2022, Intel Corporation. All rights reserved. + */ + +#ifndef __INTEL_PXP_FW_INTERFACE_43_H__ +#define __INTEL_PXP_FW_INTERFACE_43_H__ + +#include <linux/types.h> +#include "intel_pxp_cmd_interface_cmn.h" + +/* PXP-Cmd-Op definitions */ +#define PXP43_CMDID_START_HUC_AUTH 0x0000003A + +/* PXP-Input-Packet: HUC-Authentication */ +struct pxp43_start_huc_auth_in { + struct pxp_cmd_header header; + __le64 huc_base_address; +} __packed; + +/* PXP-Output-Packet: HUC-Authentication */ +struct pxp43_start_huc_auth_out { + struct pxp_cmd_header header; +} __packed; + +#endif /* __INTEL_PXP_FW_INTERFACE_43_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_cmn.h b/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_cmn.h new file mode 100644 index 000000000000..c2f23394f9b8 --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_cmn.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright(c) 2022, Intel Corporation. All rights reserved. + */ + +#ifndef __INTEL_PXP_FW_INTERFACE_CMN_H__ +#define __INTEL_PXP_FW_INTERFACE_CMN_H__ + +#include <linux/types.h> + +#define PXP_APIVER(x, y) (((x) & 0xFFFF) << 16 | ((y) & 0xFFFF)) + +/* + * there are a lot of status codes for PXP, but we only define the cross-API + * common ones that we actually can handle in the kernel driver. Other failure + * codes should be printed to error msg for debug. + */ +enum pxp_status { + PXP_STATUS_SUCCESS = 0x0, + PXP_STATUS_OP_NOT_PERMITTED = 0x4013 +}; + +/* Common PXP FW message header */ +struct pxp_cmd_header { + u32 api_version; + u32 command_id; + union { + u32 status; /* out */ + u32 stream_id; /* in */ + }; + /* Length of the message (excluding the header) */ + u32 buffer_len; +} __packed; + +#endif /* __INTEL_PXP_FW_INTERFACE_CMN_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_huc.c b/drivers/gpu/drm/i915/pxp/intel_pxp_huc.c new file mode 100644 index 000000000000..2e1165522950 --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_huc.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright(c) 2021-2022, Intel Corporation. All rights reserved. + */ + +#include <drm/i915_drm.h> + +#include "i915_drv.h" + +#include "gem/i915_gem_region.h" +#include "gt/intel_gt.h" + +#include "intel_pxp.h" +#include "intel_pxp_huc.h" +#include "intel_pxp_tee.h" +#include "intel_pxp_types.h" +#include "intel_pxp_cmd_interface_43.h" + +int intel_pxp_huc_load_and_auth(struct intel_pxp *pxp) +{ + struct intel_gt *gt = pxp_to_gt(pxp); + struct intel_huc *huc = >->uc.huc; + struct pxp43_start_huc_auth_in huc_in = {0}; + struct pxp43_start_huc_auth_out huc_out = {0}; + dma_addr_t huc_phys_addr; + u8 client_id = 0; + u8 fence_id = 0; + int err; + + if (!pxp->pxp_component) + return -ENODEV; + + huc_phys_addr = i915_gem_object_get_dma_address(huc->fw.obj, 0); + + /* write the PXP message into the lmem (the sg list) */ + huc_in.header.api_version = PXP_APIVER(4, 3); + huc_in.header.command_id = PXP43_CMDID_START_HUC_AUTH; + huc_in.header.status = 0; + huc_in.header.buffer_len = sizeof(huc_in.huc_base_address); + huc_in.huc_base_address = huc_phys_addr; + + err = intel_pxp_tee_stream_message(pxp, client_id, fence_id, + &huc_in, sizeof(huc_in), + &huc_out, sizeof(huc_out)); + if (err < 0) { + drm_err(>->i915->drm, + "Failed to send HuC load and auth command to GSC [%d]!\n", + err); + return err; + } + + /* + * HuC does sometimes survive suspend/resume (it depends on how "deep" + * a sleep state the device reaches) so we can end up here on resume + * with HuC already loaded, in which case the GSC will return + * PXP_STATUS_OP_NOT_PERMITTED. We can therefore consider the GuC + * correctly transferred in this scenario; if the same error is ever + * returned with HuC not loaded we'll still catch it when we check the + * authentication bit later. + */ + if (huc_out.header.status != PXP_STATUS_SUCCESS && + huc_out.header.status != PXP_STATUS_OP_NOT_PERMITTED) { + drm_err(>->i915->drm, + "HuC load failed with GSC error = 0x%x\n", + huc_out.header.status); + return -EPROTO; + } + + return 0; +} diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_huc.h b/drivers/gpu/drm/i915/pxp/intel_pxp_huc.h new file mode 100644 index 000000000000..e40847a91c39 --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_huc.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright(c) 2021-2022, Intel Corporation. All rights reserved. + */ + +#ifndef __INTEL_PXP_HUC_H__ +#define __INTEL_PXP_HUC_H__ + +struct intel_pxp; + +int intel_pxp_huc_load_and_auth(struct intel_pxp *pxp); + +#endif /* __INTEL_PXP_HUC_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_irq.h b/drivers/gpu/drm/i915/pxp/intel_pxp_irq.h index 8b5793654844..8c292dc86f68 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_irq.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_irq.h @@ -27,6 +27,14 @@ void intel_pxp_irq_handler(struct intel_pxp *pxp, u16 iir); static inline void intel_pxp_irq_handler(struct intel_pxp *pxp, u16 iir) { } + +static inline void intel_pxp_irq_enable(struct intel_pxp *pxp) +{ +} + +static inline void intel_pxp_irq_disable(struct intel_pxp *pxp) +{ +} #endif #endif /* __INTEL_PXP_IRQ_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_session.c b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c index 1bb5b5249157..85572360c71a 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_session.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c @@ -77,6 +77,7 @@ static int pxp_create_arb_session(struct intel_pxp *pxp) drm_err(>->i915->drm, "arb session failed to go in play\n"); return ret; } + drm_dbg(>->i915->drm, "PXP ARB session is alive\n"); if (!++pxp->key_instance) ++pxp->key_instance; @@ -137,7 +138,7 @@ static void pxp_terminate_complete(struct intel_pxp *pxp) complete_all(&pxp->termination); } -void intel_pxp_session_work(struct work_struct *work) +static void pxp_session_work(struct work_struct *work) { struct intel_pxp *pxp = container_of(work, typeof(*pxp), session_work); struct intel_gt *gt = pxp_to_gt(pxp); @@ -172,3 +173,9 @@ void intel_pxp_session_work(struct work_struct *work) intel_runtime_pm_put(gt->uncore->rpm, wakeref); } + +void intel_pxp_session_management_init(struct intel_pxp *pxp) +{ + mutex_init(&pxp->arb_mutex); + INIT_WORK(&pxp->session_work, pxp_session_work); +} diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_session.h b/drivers/gpu/drm/i915/pxp/intel_pxp_session.h index ba4c9d2b94b7..903ac52cffa1 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_session.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_session.h @@ -8,8 +8,13 @@ #include <linux/types.h> -struct work_struct; - -void intel_pxp_session_work(struct work_struct *work); +struct intel_pxp; +#ifdef CONFIG_DRM_I915_PXP +void intel_pxp_session_management_init(struct intel_pxp *pxp); +#else +static inline void intel_pxp_session_management_init(struct intel_pxp *pxp) +{ +} +#endif #endif /* __INTEL_PXP_SESSION_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c index 4b6f5655fab5..b0c9170b1395 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c @@ -8,11 +8,14 @@ #include <drm/i915_pxp_tee_interface.h> #include <drm/i915_component.h> +#include "gem/i915_gem_lmem.h" + #include "i915_drv.h" #include "intel_pxp.h" #include "intel_pxp_session.h" #include "intel_pxp_tee.h" -#include "intel_pxp_tee_interface.h" +#include "intel_pxp_cmd_interface_42.h" +#include "intel_pxp_huc.h" static inline struct intel_pxp *i915_dev_to_pxp(struct device *i915_kdev) { @@ -69,6 +72,47 @@ unlock: return ret; } +int intel_pxp_tee_stream_message(struct intel_pxp *pxp, + u8 client_id, u32 fence_id, + void *msg_in, size_t msg_in_len, + void *msg_out, size_t msg_out_len) +{ + /* TODO: for bigger objects we need to use a sg of 4k pages */ + const size_t max_msg_size = PAGE_SIZE; + struct drm_i915_private *i915 = pxp_to_gt(pxp)->i915; + struct i915_pxp_component *pxp_component = pxp->pxp_component; + unsigned int offset = 0; + struct scatterlist *sg; + int ret; + + if (msg_in_len > max_msg_size || msg_out_len > max_msg_size) + return -ENOSPC; + + mutex_lock(&pxp->tee_mutex); + + if (unlikely(!pxp_component || !pxp_component->ops->gsc_command)) { + ret = -ENODEV; + goto unlock; + } + + GEM_BUG_ON(!pxp->stream_cmd.obj); + + sg = i915_gem_object_get_sg_dma(pxp->stream_cmd.obj, 0, &offset); + + memcpy(pxp->stream_cmd.vaddr, msg_in, msg_in_len); + + ret = pxp_component->ops->gsc_command(pxp_component->tee_dev, client_id, + fence_id, sg, msg_in_len, sg); + if (ret < 0) + drm_err(&i915->drm, "Failed to send PXP TEE gsc command\n"); + else + memcpy(msg_out, pxp->stream_cmd.vaddr, msg_out_len); + +unlock: + mutex_unlock(&pxp->tee_mutex); + return ret; +} + /** * i915_pxp_tee_component_bind - bind function to pass the function pointers to pxp_tee * @i915_kdev: pointer to i915 kernel device @@ -84,24 +128,36 @@ static int i915_pxp_tee_component_bind(struct device *i915_kdev, { struct drm_i915_private *i915 = kdev_to_i915(i915_kdev); struct intel_pxp *pxp = i915_dev_to_pxp(i915_kdev); + struct intel_uc *uc = &pxp_to_gt(pxp)->uc; intel_wakeref_t wakeref; + int ret = 0; mutex_lock(&pxp->tee_mutex); pxp->pxp_component = data; pxp->pxp_component->tee_dev = tee_kdev; mutex_unlock(&pxp->tee_mutex); + if (intel_uc_uses_huc(uc) && intel_huc_is_loaded_by_gsc(&uc->huc)) { + with_intel_runtime_pm(&i915->runtime_pm, wakeref) { + /* load huc via pxp */ + ret = intel_huc_fw_load_and_auth_via_gsc(&uc->huc); + if (ret < 0) + drm_err(&i915->drm, "failed to load huc via gsc %d\n", ret); + } + } + /* if we are suspended, the HW will be re-initialized on resume */ wakeref = intel_runtime_pm_get_if_in_use(&i915->runtime_pm); if (!wakeref) return 0; /* the component is required to fully start the PXP HW */ - intel_pxp_init_hw(pxp); + if (intel_pxp_is_enabled(pxp)) + intel_pxp_init_hw(pxp); intel_runtime_pm_put(&i915->runtime_pm, wakeref); - return 0; + return ret; } static void i915_pxp_tee_component_unbind(struct device *i915_kdev, @@ -111,8 +167,9 @@ static void i915_pxp_tee_component_unbind(struct device *i915_kdev, struct intel_pxp *pxp = i915_dev_to_pxp(i915_kdev); intel_wakeref_t wakeref; - with_intel_runtime_pm_if_in_use(&i915->runtime_pm, wakeref) - intel_pxp_fini_hw(pxp); + if (intel_pxp_is_enabled(pxp)) + with_intel_runtime_pm_if_in_use(&i915->runtime_pm, wakeref) + intel_pxp_fini_hw(pxp); mutex_lock(&pxp->tee_mutex); pxp->pxp_component = NULL; @@ -124,22 +181,92 @@ static const struct component_ops i915_pxp_tee_component_ops = { .unbind = i915_pxp_tee_component_unbind, }; +static int alloc_streaming_command(struct intel_pxp *pxp) +{ + struct drm_i915_private *i915 = pxp_to_gt(pxp)->i915; + struct drm_i915_gem_object *obj = NULL; + void *cmd; + int err; + + pxp->stream_cmd.obj = NULL; + pxp->stream_cmd.vaddr = NULL; + + if (!IS_DGFX(i915)) + return 0; + + /* allocate lmem object of one page for PXP command memory and store it */ + obj = i915_gem_object_create_lmem(i915, PAGE_SIZE, I915_BO_ALLOC_CONTIGUOUS); + if (IS_ERR(obj)) { + drm_err(&i915->drm, "Failed to allocate pxp streaming command!\n"); + return PTR_ERR(obj); + } + + err = i915_gem_object_pin_pages_unlocked(obj); + if (err) { + drm_err(&i915->drm, "Failed to pin gsc message page!\n"); + goto out_put; + } + + /* map the lmem into the virtual memory pointer */ + cmd = i915_gem_object_pin_map_unlocked(obj, i915_coherent_map_type(i915, obj, true)); + if (IS_ERR(cmd)) { + drm_err(&i915->drm, "Failed to map gsc message page!\n"); + err = PTR_ERR(cmd); + goto out_unpin; + } + + memset(cmd, 0, obj->base.size); + + pxp->stream_cmd.obj = obj; + pxp->stream_cmd.vaddr = cmd; + + return 0; + +out_unpin: + i915_gem_object_unpin_pages(obj); +out_put: + i915_gem_object_put(obj); + return err; +} + +static void free_streaming_command(struct intel_pxp *pxp) +{ + struct drm_i915_gem_object *obj = fetch_and_zero(&pxp->stream_cmd.obj); + + if (!obj) + return; + + i915_gem_object_unpin_map(obj); + i915_gem_object_unpin_pages(obj); + i915_gem_object_put(obj); +} + int intel_pxp_tee_component_init(struct intel_pxp *pxp) { int ret; struct intel_gt *gt = pxp_to_gt(pxp); struct drm_i915_private *i915 = gt->i915; + mutex_init(&pxp->tee_mutex); + + ret = alloc_streaming_command(pxp); + if (ret) + return ret; + ret = component_add_typed(i915->drm.dev, &i915_pxp_tee_component_ops, I915_COMPONENT_PXP); if (ret < 0) { drm_err(&i915->drm, "Failed to add PXP component (%d)\n", ret); - return ret; + goto out_free; } pxp->pxp_component_added = true; return 0; + +out_free: + free_streaming_command(pxp); + return ret; } void intel_pxp_tee_component_fini(struct intel_pxp *pxp) @@ -151,20 +278,22 @@ void intel_pxp_tee_component_fini(struct intel_pxp *pxp) component_del(i915->drm.dev, &i915_pxp_tee_component_ops); pxp->pxp_component_added = false; + + free_streaming_command(pxp); } int intel_pxp_tee_cmd_create_arb_session(struct intel_pxp *pxp, int arb_session_id) { struct drm_i915_private *i915 = pxp_to_gt(pxp)->i915; - struct pxp_tee_create_arb_in msg_in = {0}; - struct pxp_tee_create_arb_out msg_out = {0}; + struct pxp42_create_arb_in msg_in = {0}; + struct pxp42_create_arb_out msg_out = {0}; int ret; - msg_in.header.api_version = PXP_TEE_APIVER; - msg_in.header.command_id = PXP_TEE_ARB_CMDID; + msg_in.header.api_version = PXP_APIVER(4, 2); + msg_in.header.command_id = PXP42_CMDID_INIT_SESSION; msg_in.header.buffer_len = sizeof(msg_in) - sizeof(msg_in.header); - msg_in.protection_mode = PXP_TEE_ARB_PROTECTION_MODE; + msg_in.protection_mode = PXP42_ARB_SESSION_MODE_HEAVY; msg_in.session_id = arb_session_id; ret = intel_pxp_tee_io_message(pxp, @@ -174,6 +303,9 @@ int intel_pxp_tee_cmd_create_arb_session(struct intel_pxp *pxp, if (ret) drm_err(&i915->drm, "Failed to send tee msg ret=[%d]\n", ret); + else if (msg_out.header.status != 0x0) + drm_warn(&i915->drm, "PXP firmware failed arb session init request ret=[0x%08x]\n", + msg_out.header.status); return ret; } diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.h b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.h index c136053ce340..aeb3dfe7ce96 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.h @@ -14,4 +14,9 @@ void intel_pxp_tee_component_fini(struct intel_pxp *pxp); int intel_pxp_tee_cmd_create_arb_session(struct intel_pxp *pxp, int arb_session_id); +int intel_pxp_tee_stream_message(struct intel_pxp *pxp, + u8 client_id, u32 fence_id, + void *msg_in, size_t msg_in_len, + void *msg_out, size_t msg_out_len); + #endif /* __INTEL_PXP_TEE_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_tee_interface.h b/drivers/gpu/drm/i915/pxp/intel_pxp_tee_interface.h deleted file mode 100644 index 36e9b0868f5c..000000000000 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_tee_interface.h +++ /dev/null @@ -1,36 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright(c) 2020, Intel Corporation. All rights reserved. - */ - -#ifndef __INTEL_PXP_TEE_INTERFACE_H__ -#define __INTEL_PXP_TEE_INTERFACE_H__ - -#include <linux/types.h> - -#define PXP_TEE_APIVER 0x40002 -#define PXP_TEE_ARB_CMDID 0x1e -#define PXP_TEE_ARB_PROTECTION_MODE 0x2 - -/* PXP TEE message header */ -struct pxp_tee_cmd_header { - u32 api_version; - u32 command_id; - u32 status; - /* Length of the message (excluding the header) */ - u32 buffer_len; -} __packed; - -/* PXP TEE message input to create a arbitrary session */ -struct pxp_tee_create_arb_in { - struct pxp_tee_cmd_header header; - u32 protection_mode; - u32 session_id; -} __packed; - -/* PXP TEE message output to create a arbitrary session */ -struct pxp_tee_create_arb_out { - struct pxp_tee_cmd_header header; -} __packed; - -#endif /* __INTEL_PXP_TEE_INTERFACE_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_types.h b/drivers/gpu/drm/i915/pxp/intel_pxp_types.h index 7ce5f37ee12e..f74b1e11a505 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_types.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_types.h @@ -53,6 +53,12 @@ struct intel_pxp { /** @tee_mutex: protects the tee channel binding and messaging. */ struct mutex tee_mutex; + /** @stream_cmd: LMEM obj used to send stream PXP commands to the GSC */ + struct { + struct drm_i915_gem_object *obj; /* contains PXP command memory */ + void *vaddr; /* virtual memory for PXP command */ + } stream_cmd; + /** * @hw_state_invalidated: if the HW perceives an attack on the integrity * of the encryption it will invalidate the keys and expect SW to diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c index 8c6517d29b8e..37068542aafe 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c @@ -344,7 +344,7 @@ static int igt_evict_vm(void *arg) /* Everything is pinned, nothing should happen */ mutex_lock(&ggtt->vm.mutex); - err = i915_gem_evict_vm(&ggtt->vm, NULL); + err = i915_gem_evict_vm(&ggtt->vm, NULL, NULL); mutex_unlock(&ggtt->vm.mutex); if (err) { pr_err("i915_gem_evict_vm on a full GGTT returned err=%d]\n", @@ -356,7 +356,7 @@ static int igt_evict_vm(void *arg) for_i915_gem_ww(&ww, err, false) { mutex_lock(&ggtt->vm.mutex); - err = i915_gem_evict_vm(&ggtt->vm, &ww); + err = i915_gem_evict_vm(&ggtt->vm, &ww, NULL); mutex_unlock(&ggtt->vm.mutex); } diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c index e050a2de5fd1..eae7d947d7de 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c @@ -27,6 +27,7 @@ #include "gem/i915_gem_context.h" #include "gem/i915_gem_internal.h" +#include "gem/i915_gem_lmem.h" #include "gem/i915_gem_region.h" #include "gem/selftests/mock_context.h" #include "gt/intel_context.h" @@ -60,7 +61,6 @@ static int fake_get_pages(struct drm_i915_gem_object *obj) #define PFN_BIAS 0x1000 struct sg_table *pages; struct scatterlist *sg; - unsigned int sg_page_sizes; typeof(obj->base.size) rem; pages = kmalloc(sizeof(*pages), GFP); @@ -73,7 +73,6 @@ static int fake_get_pages(struct drm_i915_gem_object *obj) return -ENOMEM; } - sg_page_sizes = 0; rem = obj->base.size; for (sg = pages->sgl; sg; sg = sg_next(sg)) { unsigned long len = min_t(typeof(rem), rem, BIT(31)); @@ -82,13 +81,12 @@ static int fake_get_pages(struct drm_i915_gem_object *obj) sg_set_page(sg, pfn_to_page(PFN_BIAS), len, 0); sg_dma_address(sg) = page_to_phys(sg_page(sg)); sg_dma_len(sg) = len; - sg_page_sizes |= len; rem -= len; } GEM_BUG_ON(rem); - __i915_gem_object_set_pages(obj, pages, sg_page_sizes); + __i915_gem_object_set_pages(obj, pages); return 0; #undef GFP @@ -1113,15 +1111,8 @@ static int misaligned_case(struct i915_address_space *vm, struct intel_memory_re expected_node_size = expected_vma_size; if (HAS_64K_PAGES(vm->i915) && i915_gem_object_is_lmem(obj)) { - /* - * The compact-pt should expand lmem node to 2MB for the ppGTT, - * for all other cases we should only expect 64K. - */ expected_vma_size = round_up(size, I915_GTT_PAGE_SIZE_64K); - if (NEEDS_COMPACT_PT(vm->i915) && !i915_is_ggtt(vm)) - expected_node_size = round_up(size, I915_GTT_PAGE_SIZE_2M); - else - expected_node_size = round_up(size, I915_GTT_PAGE_SIZE_64K); + expected_node_size = round_up(size, I915_GTT_PAGE_SIZE_64K); } if (vma->size != expected_vma_size || vma->node.size != expected_node_size) { diff --git a/drivers/gpu/drm/i915/selftests/i915_perf.c b/drivers/gpu/drm/i915/selftests/i915_perf.c index 429c6d73b159..24dde5531423 100644 --- a/drivers/gpu/drm/i915/selftests/i915_perf.c +++ b/drivers/gpu/drm/i915/selftests/i915_perf.c @@ -102,6 +102,12 @@ test_stream(struct i915_perf *perf) I915_OA_FORMAT_A32u40_A4u32_B8_C8 : I915_OA_FORMAT_C4_B8, }; struct i915_perf_stream *stream; + struct intel_gt *gt; + + if (!props.engine) + return NULL; + + gt = props.engine->gt; if (!oa_config) return NULL; @@ -116,12 +122,12 @@ test_stream(struct i915_perf *perf) stream->perf = perf; - mutex_lock(&perf->lock); + mutex_lock(>->perf.lock); if (i915_oa_stream_init(stream, ¶m, &props)) { kfree(stream); stream = NULL; } - mutex_unlock(&perf->lock); + mutex_unlock(>->perf.lock); i915_oa_config_put(oa_config); @@ -130,11 +136,11 @@ test_stream(struct i915_perf *perf) static void stream_destroy(struct i915_perf_stream *stream) { - struct i915_perf *perf = stream->perf; + struct intel_gt *gt = stream->engine->gt; - mutex_lock(&perf->lock); + mutex_lock(>->perf.lock); i915_perf_destroy_locked(stream); - mutex_unlock(&perf->lock); + mutex_unlock(>->perf.lock); } static int live_sanitycheck(void *arg) diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c index 818a4909c1f3..0daa8669181d 100644 --- a/drivers/gpu/drm/i915/selftests/i915_request.c +++ b/drivers/gpu/drm/i915/selftests/i915_request.c @@ -299,9 +299,18 @@ __live_request_alloc(struct intel_context *ce) return intel_context_create_request(ce); } -static int __igt_breadcrumbs_smoketest(void *arg) +struct smoke_thread { + struct kthread_worker *worker; + struct kthread_work work; + struct smoketest *t; + bool stop; + int result; +}; + +static void __igt_breadcrumbs_smoketest(struct kthread_work *work) { - struct smoketest *t = arg; + struct smoke_thread *thread = container_of(work, typeof(*thread), work); + struct smoketest *t = thread->t; const unsigned int max_batch = min(t->ncontexts, t->max_batch) - 1; const unsigned int total = 4 * t->ncontexts + 1; unsigned int num_waits = 0, num_fences = 0; @@ -320,8 +329,10 @@ static int __igt_breadcrumbs_smoketest(void *arg) */ requests = kcalloc(total, sizeof(*requests), GFP_KERNEL); - if (!requests) - return -ENOMEM; + if (!requests) { + thread->result = -ENOMEM; + return; + } order = i915_random_order(total, &prng); if (!order) { @@ -329,7 +340,7 @@ static int __igt_breadcrumbs_smoketest(void *arg) goto out_requests; } - while (!kthread_should_stop()) { + while (!READ_ONCE(thread->stop)) { struct i915_sw_fence *submit, *wait; unsigned int n, count; @@ -437,7 +448,7 @@ static int __igt_breadcrumbs_smoketest(void *arg) kfree(order); out_requests: kfree(requests); - return err; + thread->result = err; } static int mock_breadcrumbs_smoketest(void *arg) @@ -450,7 +461,7 @@ static int mock_breadcrumbs_smoketest(void *arg) .request_alloc = __mock_request_alloc }; unsigned int ncpus = num_online_cpus(); - struct task_struct **threads; + struct smoke_thread *threads; unsigned int n; int ret = 0; @@ -479,28 +490,37 @@ static int mock_breadcrumbs_smoketest(void *arg) } for (n = 0; n < ncpus; n++) { - threads[n] = kthread_run(__igt_breadcrumbs_smoketest, - &t, "igt/%d", n); - if (IS_ERR(threads[n])) { - ret = PTR_ERR(threads[n]); + struct kthread_worker *worker; + + worker = kthread_create_worker(0, "igt/%d", n); + if (IS_ERR(worker)) { + ret = PTR_ERR(worker); ncpus = n; break; } - get_task_struct(threads[n]); + threads[n].worker = worker; + threads[n].t = &t; + threads[n].stop = false; + threads[n].result = 0; + + kthread_init_work(&threads[n].work, + __igt_breadcrumbs_smoketest); + kthread_queue_work(worker, &threads[n].work); } - yield(); /* start all threads before we begin */ msleep(jiffies_to_msecs(i915_selftest.timeout_jiffies)); for (n = 0; n < ncpus; n++) { int err; - err = kthread_stop(threads[n]); + WRITE_ONCE(threads[n].stop, true); + kthread_flush_work(&threads[n].work); + err = READ_ONCE(threads[n].result); if (err < 0 && !ret) ret = err; - put_task_struct(threads[n]); + kthread_destroy_worker(threads[n].worker); } pr_info("Completed %lu waits for %lu fence across %d cpus\n", atomic_long_read(&t.num_waits), @@ -1203,9 +1223,7 @@ static int live_all_engines(void *arg) goto out_request; } - err = i915_request_await_object(request[idx], batch->obj, 0); - if (err == 0) - err = i915_vma_move_to_active(batch, request[idx], 0); + err = i915_vma_move_to_active(batch, request[idx], 0); GEM_BUG_ON(err); err = engine->emit_bb_start(request[idx], @@ -1332,10 +1350,7 @@ static int live_sequential_engines(void *arg) } } - err = i915_request_await_object(request[idx], - batch->obj, false); - if (err == 0) - err = i915_vma_move_to_active(batch, request[idx], 0); + err = i915_vma_move_to_active(batch, request[idx], 0); GEM_BUG_ON(err); err = engine->emit_bb_start(request[idx], @@ -1419,9 +1434,18 @@ out_free: return err; } -static int __live_parallel_engine1(void *arg) +struct parallel_thread { + struct kthread_worker *worker; + struct kthread_work work; + struct intel_engine_cs *engine; + int result; +}; + +static void __live_parallel_engine1(struct kthread_work *work) { - struct intel_engine_cs *engine = arg; + struct parallel_thread *thread = + container_of(work, typeof(*thread), work); + struct intel_engine_cs *engine = thread->engine; IGT_TIMEOUT(end_time); unsigned long count; int err = 0; @@ -1452,12 +1476,14 @@ static int __live_parallel_engine1(void *arg) intel_engine_pm_put(engine); pr_info("%s: %lu request + sync\n", engine->name, count); - return err; + thread->result = err; } -static int __live_parallel_engineN(void *arg) +static void __live_parallel_engineN(struct kthread_work *work) { - struct intel_engine_cs *engine = arg; + struct parallel_thread *thread = + container_of(work, typeof(*thread), work); + struct intel_engine_cs *engine = thread->engine; IGT_TIMEOUT(end_time); unsigned long count; int err = 0; @@ -1479,7 +1505,7 @@ static int __live_parallel_engineN(void *arg) intel_engine_pm_put(engine); pr_info("%s: %lu requests\n", engine->name, count); - return err; + thread->result = err; } static bool wake_all(struct drm_i915_private *i915) @@ -1505,9 +1531,11 @@ static int wait_for_all(struct drm_i915_private *i915) return -ETIME; } -static int __live_parallel_spin(void *arg) +static void __live_parallel_spin(struct kthread_work *work) { - struct intel_engine_cs *engine = arg; + struct parallel_thread *thread = + container_of(work, typeof(*thread), work); + struct intel_engine_cs *engine = thread->engine; struct igt_spinner spin; struct i915_request *rq; int err = 0; @@ -1520,7 +1548,8 @@ static int __live_parallel_spin(void *arg) if (igt_spinner_init(&spin, engine->gt)) { wake_all(engine->i915); - return -ENOMEM; + thread->result = -ENOMEM; + return; } intel_engine_pm_get(engine); @@ -1553,22 +1582,22 @@ static int __live_parallel_spin(void *arg) out_spin: igt_spinner_fini(&spin); - return err; + thread->result = err; } static int live_parallel_engines(void *arg) { struct drm_i915_private *i915 = arg; - static int (* const func[])(void *arg) = { + static void (* const func[])(struct kthread_work *) = { __live_parallel_engine1, __live_parallel_engineN, __live_parallel_spin, NULL, }; const unsigned int nengines = num_uabi_engines(i915); + struct parallel_thread *threads; struct intel_engine_cs *engine; - int (* const *fn)(void *arg); - struct task_struct **tsk; + void (* const *fn)(struct kthread_work *); int err = 0; /* @@ -1576,8 +1605,8 @@ static int live_parallel_engines(void *arg) * tests that we load up the system maximally. */ - tsk = kcalloc(nengines, sizeof(*tsk), GFP_KERNEL); - if (!tsk) + threads = kcalloc(nengines, sizeof(*threads), GFP_KERNEL); + if (!threads) return -ENOMEM; for (fn = func; !err && *fn; fn++) { @@ -1594,37 +1623,44 @@ static int live_parallel_engines(void *arg) idx = 0; for_each_uabi_engine(engine, i915) { - tsk[idx] = kthread_run(*fn, engine, - "igt/parallel:%s", - engine->name); - if (IS_ERR(tsk[idx])) { - err = PTR_ERR(tsk[idx]); + struct kthread_worker *worker; + + worker = kthread_create_worker(0, "igt/parallel:%s", + engine->name); + if (IS_ERR(worker)) { + err = PTR_ERR(worker); break; } - get_task_struct(tsk[idx++]); - } - yield(); /* start all threads before we kthread_stop() */ + threads[idx].worker = worker; + threads[idx].result = 0; + threads[idx].engine = engine; + + kthread_init_work(&threads[idx].work, *fn); + kthread_queue_work(worker, &threads[idx].work); + idx++; + } idx = 0; for_each_uabi_engine(engine, i915) { int status; - if (IS_ERR(tsk[idx])) + if (!threads[idx].worker) break; - status = kthread_stop(tsk[idx]); + kthread_flush_work(&threads[idx].work); + status = READ_ONCE(threads[idx].result); if (status && !err) err = status; - put_task_struct(tsk[idx++]); + kthread_destroy_worker(threads[idx++].worker); } if (igt_live_test_end(&t)) err = -EIO; } - kfree(tsk); + kfree(threads); return err; } @@ -1669,10 +1705,11 @@ static int live_breadcrumbs_smoketest(void *arg) { struct drm_i915_private *i915 = arg; const unsigned int nengines = num_uabi_engines(i915); - const unsigned int ncpus = num_online_cpus(); + const unsigned int ncpus = /* saturate with nengines * ncpus */ + max_t(int, 2, DIV_ROUND_UP(num_online_cpus(), nengines)); unsigned long num_waits, num_fences; struct intel_engine_cs *engine; - struct task_struct **threads; + struct smoke_thread *threads; struct igt_live_test live; intel_wakeref_t wakeref; struct smoketest *smoke; @@ -1741,28 +1778,31 @@ static int live_breadcrumbs_smoketest(void *arg) goto out_flush; } /* One ring interleaved between requests from all cpus */ - smoke[idx].max_batch /= num_online_cpus() + 1; + smoke[idx].max_batch /= ncpus + 1; pr_debug("Limiting batches to %d requests on %s\n", smoke[idx].max_batch, engine->name); for (n = 0; n < ncpus; n++) { - struct task_struct *tsk; + unsigned int i = idx * ncpus + n; + struct kthread_worker *worker; - tsk = kthread_run(__igt_breadcrumbs_smoketest, - &smoke[idx], "igt/%d.%d", idx, n); - if (IS_ERR(tsk)) { - ret = PTR_ERR(tsk); + worker = kthread_create_worker(0, "igt/%d.%d", idx, n); + if (IS_ERR(worker)) { + ret = PTR_ERR(worker); goto out_flush; } - get_task_struct(tsk); - threads[idx * ncpus + n] = tsk; + threads[i].worker = worker; + threads[i].t = &smoke[idx]; + + kthread_init_work(&threads[i].work, + __igt_breadcrumbs_smoketest); + kthread_queue_work(worker, &threads[i].work); } idx++; } - yield(); /* start all threads before we begin */ msleep(jiffies_to_msecs(i915_selftest.timeout_jiffies)); out_flush: @@ -1771,17 +1811,19 @@ out_flush: num_fences = 0; for_each_uabi_engine(engine, i915) { for (n = 0; n < ncpus; n++) { - struct task_struct *tsk = threads[idx * ncpus + n]; + unsigned int i = idx * ncpus + n; int err; - if (!tsk) + if (!threads[i].worker) continue; - err = kthread_stop(tsk); + WRITE_ONCE(threads[i].stop, true); + kthread_flush_work(&threads[i].work); + err = READ_ONCE(threads[i].result); if (err < 0 && !ret) ret = err; - put_task_struct(tsk); + kthread_destroy_worker(threads[i].worker); } num_waits += atomic_long_read(&smoke[idx].num_waits); @@ -2891,9 +2933,18 @@ out: return err; } -static int p_sync0(void *arg) +struct p_thread { + struct perf_stats p; + struct kthread_worker *worker; + struct kthread_work work; + struct intel_engine_cs *engine; + int result; +}; + +static void p_sync0(struct kthread_work *work) { - struct perf_stats *p = arg; + struct p_thread *thread = container_of(work, typeof(*thread), work); + struct perf_stats *p = &thread->p; struct intel_engine_cs *engine = p->engine; struct intel_context *ce; IGT_TIMEOUT(end_time); @@ -2902,13 +2953,16 @@ static int p_sync0(void *arg) int err = 0; ce = intel_context_create(engine); - if (IS_ERR(ce)) - return PTR_ERR(ce); + if (IS_ERR(ce)) { + thread->result = PTR_ERR(ce); + return; + } err = intel_context_pin(ce); if (err) { intel_context_put(ce); - return err; + thread->result = err; + return; } if (intel_engine_supports_stats(engine)) { @@ -2958,12 +3012,13 @@ static int p_sync0(void *arg) intel_context_unpin(ce); intel_context_put(ce); - return err; + thread->result = err; } -static int p_sync1(void *arg) +static void p_sync1(struct kthread_work *work) { - struct perf_stats *p = arg; + struct p_thread *thread = container_of(work, typeof(*thread), work); + struct perf_stats *p = &thread->p; struct intel_engine_cs *engine = p->engine; struct i915_request *prev = NULL; struct intel_context *ce; @@ -2973,13 +3028,16 @@ static int p_sync1(void *arg) int err = 0; ce = intel_context_create(engine); - if (IS_ERR(ce)) - return PTR_ERR(ce); + if (IS_ERR(ce)) { + thread->result = PTR_ERR(ce); + return; + } err = intel_context_pin(ce); if (err) { intel_context_put(ce); - return err; + thread->result = err; + return; } if (intel_engine_supports_stats(engine)) { @@ -3031,12 +3089,13 @@ static int p_sync1(void *arg) intel_context_unpin(ce); intel_context_put(ce); - return err; + thread->result = err; } -static int p_many(void *arg) +static void p_many(struct kthread_work *work) { - struct perf_stats *p = arg; + struct p_thread *thread = container_of(work, typeof(*thread), work); + struct perf_stats *p = &thread->p; struct intel_engine_cs *engine = p->engine; struct intel_context *ce; IGT_TIMEOUT(end_time); @@ -3045,13 +3104,16 @@ static int p_many(void *arg) bool busy; ce = intel_context_create(engine); - if (IS_ERR(ce)) - return PTR_ERR(ce); + if (IS_ERR(ce)) { + thread->result = PTR_ERR(ce); + return; + } err = intel_context_pin(ce); if (err) { intel_context_put(ce); - return err; + thread->result = err; + return; } if (intel_engine_supports_stats(engine)) { @@ -3092,26 +3154,23 @@ static int p_many(void *arg) intel_context_unpin(ce); intel_context_put(ce); - return err; + thread->result = err; } static int perf_parallel_engines(void *arg) { struct drm_i915_private *i915 = arg; - static int (* const func[])(void *arg) = { + static void (* const func[])(struct kthread_work *) = { p_sync0, p_sync1, p_many, NULL, }; const unsigned int nengines = num_uabi_engines(i915); + void (* const *fn)(struct kthread_work *); struct intel_engine_cs *engine; - int (* const *fn)(void *arg); struct pm_qos_request qos; - struct { - struct perf_stats p; - struct task_struct *tsk; - } *engines; + struct p_thread *engines; int err = 0; engines = kcalloc(nengines, sizeof(*engines), GFP_KERNEL); @@ -3134,36 +3193,45 @@ static int perf_parallel_engines(void *arg) idx = 0; for_each_uabi_engine(engine, i915) { + struct kthread_worker *worker; + intel_engine_pm_get(engine); memset(&engines[idx].p, 0, sizeof(engines[idx].p)); - engines[idx].p.engine = engine; - engines[idx].tsk = kthread_run(*fn, &engines[idx].p, - "igt:%s", engine->name); - if (IS_ERR(engines[idx].tsk)) { - err = PTR_ERR(engines[idx].tsk); + worker = kthread_create_worker(0, "igt:%s", + engine->name); + if (IS_ERR(worker)) { + err = PTR_ERR(worker); intel_engine_pm_put(engine); break; } - get_task_struct(engines[idx++].tsk); - } + engines[idx].worker = worker; + engines[idx].result = 0; + engines[idx].p.engine = engine; + engines[idx].engine = engine; - yield(); /* start all threads before we kthread_stop() */ + kthread_init_work(&engines[idx].work, *fn); + kthread_queue_work(worker, &engines[idx].work); + idx++; + } idx = 0; for_each_uabi_engine(engine, i915) { int status; - if (IS_ERR(engines[idx].tsk)) + if (!engines[idx].worker) break; - status = kthread_stop(engines[idx].tsk); + kthread_flush_work(&engines[idx].work); + status = READ_ONCE(engines[idx].result); if (status && !err) err = status; intel_engine_pm_put(engine); - put_task_struct(engines[idx++].tsk); + + kthread_destroy_worker(engines[idx].worker); + idx++; } if (igt_live_test_end(&t)) diff --git a/drivers/gpu/drm/i915/selftests/igt_spinner.c b/drivers/gpu/drm/i915/selftests/igt_spinner.c index 0c22594ae274..16978ac59797 100644 --- a/drivers/gpu/drm/i915/selftests/igt_spinner.c +++ b/drivers/gpu/drm/i915/selftests/igt_spinner.c @@ -119,22 +119,6 @@ static u64 hws_address(const struct i915_vma *hws, return hws->node.start + seqno_offset(rq->fence.context); } -static int move_to_active(struct i915_vma *vma, - struct i915_request *rq, - unsigned int flags) -{ - int err; - - i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, - flags & EXEC_OBJECT_WRITE); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, flags); - i915_vma_unlock(vma); - - return err; -} - struct i915_request * igt_spinner_create_request(struct igt_spinner *spin, struct intel_context *ce, @@ -165,11 +149,11 @@ igt_spinner_create_request(struct igt_spinner *spin, if (IS_ERR(rq)) return ERR_CAST(rq); - err = move_to_active(vma, rq, 0); + err = igt_vma_move_to_active_unlocked(vma, rq, 0); if (err) goto cancel_rq; - err = move_to_active(hws, rq, 0); + err = igt_vma_move_to_active_unlocked(hws, rq, 0); if (err) goto cancel_rq; diff --git a/drivers/gpu/drm/i915/selftests/intel_uncore.c b/drivers/gpu/drm/i915/selftests/intel_uncore.c index fda9bb79c049..e4281508d580 100644 --- a/drivers/gpu/drm/i915/selftests/intel_uncore.c +++ b/drivers/gpu/drm/i915/selftests/intel_uncore.c @@ -70,6 +70,8 @@ static int intel_shadow_table_check(void) { gen12_shadowed_regs, ARRAY_SIZE(gen12_shadowed_regs) }, { dg2_shadowed_regs, ARRAY_SIZE(dg2_shadowed_regs) }, { pvc_shadowed_regs, ARRAY_SIZE(pvc_shadowed_regs) }, + { mtl_shadowed_regs, ARRAY_SIZE(mtl_shadowed_regs) }, + { xelpmp_shadowed_regs, ARRAY_SIZE(xelpmp_shadowed_regs) }, }; const struct i915_range *range; unsigned int i, j; @@ -117,6 +119,8 @@ int intel_uncore_mock_selftests(void) { __gen12_fw_ranges, ARRAY_SIZE(__gen12_fw_ranges), true }, { __xehp_fw_ranges, ARRAY_SIZE(__xehp_fw_ranges), true }, { __pvc_fw_ranges, ARRAY_SIZE(__pvc_fw_ranges), true }, + { __mtl_fw_ranges, ARRAY_SIZE(__mtl_fw_ranges), true }, + { __xelpmp_fw_ranges, ARRAY_SIZE(__xelpmp_fw_ranges), true }, }; int err, i; diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c index fff11c90f1fa..f6a7c0bd2955 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c +++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c @@ -67,7 +67,6 @@ static void mock_device_release(struct drm_device *dev) intel_gt_driver_remove(to_gt(i915)); i915_gem_drain_workqueue(i915); - i915_gem_drain_freed_objects(i915); mock_fini_ggtt(to_gt(i915)->ggtt); destroy_workqueue(i915->wq); diff --git a/drivers/gpu/drm/i915/selftests/mock_region.c b/drivers/gpu/drm/i915/selftests/mock_region.c index bac21fe84ca5..6324eb32d4dd 100644 --- a/drivers/gpu/drm/i915/selftests/mock_region.c +++ b/drivers/gpu/drm/i915/selftests/mock_region.c @@ -41,7 +41,7 @@ static int mock_region_get_pages(struct drm_i915_gem_object *obj) } pages = &obj->mm.rsgt->table; - __i915_gem_object_set_pages(obj, pages, i915_sg_dma_sizes(pages->sgl)); + __i915_gem_object_set_pages(obj, pages); return 0; diff --git a/drivers/gpu/drm/i915/vlv_sideband.c b/drivers/gpu/drm/i915/vlv_sideband.c index c26001300ebd..6eea6e1a99c0 100644 --- a/drivers/gpu/drm/i915/vlv_sideband.c +++ b/drivers/gpu/drm/i915/vlv_sideband.c @@ -8,6 +8,8 @@ #include "i915_reg.h" #include "vlv_sideband.h" +#include "display/intel_dpio_phy.h" + /* * IOSF sideband, see VLV2_SidebandMsg_HAS.docx and * VLV_VLV2_PUNIT_HAS_0.8.docx diff --git a/drivers/gpu/drm/i915/vlv_suspend.c b/drivers/gpu/drm/i915/vlv_suspend.c index 664fde244f59..02e63ed77f60 100644 --- a/drivers/gpu/drm/i915/vlv_suspend.c +++ b/drivers/gpu/drm/i915/vlv_suspend.c @@ -194,7 +194,6 @@ static void vlv_restore_gunit_s0ix_state(struct drm_i915_private *i915) { struct vlv_s0ix_state *s = i915->vlv_s0ix_state; struct intel_uncore *uncore = &i915->uncore; - u32 val; int i; if (!s) @@ -262,15 +261,11 @@ static void vlv_restore_gunit_s0ix_state(struct drm_i915_private *i915) * be restored, as they are used to control the s0ix suspend/resume * sequence by the caller. */ - val = intel_uncore_read(uncore, VLV_GTLC_WAKE_CTRL); - val &= VLV_GTLC_ALLOWWAKEREQ; - val |= s->gtlc_wake_ctrl & ~VLV_GTLC_ALLOWWAKEREQ; - intel_uncore_write(uncore, VLV_GTLC_WAKE_CTRL, val); + intel_uncore_rmw(uncore, VLV_GTLC_WAKE_CTRL, ~VLV_GTLC_ALLOWWAKEREQ, + s->gtlc_wake_ctrl & ~VLV_GTLC_ALLOWWAKEREQ); - val = intel_uncore_read(uncore, VLV_GTLC_SURVIVABILITY_REG); - val &= VLV_GFX_CLK_FORCE_ON_BIT; - val |= s->gtlc_survive & ~VLV_GFX_CLK_FORCE_ON_BIT; - intel_uncore_write(uncore, VLV_GTLC_SURVIVABILITY_REG, val); + intel_uncore_rmw(uncore, VLV_GTLC_SURVIVABILITY_REG, ~VLV_GFX_CLK_FORCE_ON_BIT, + s->gtlc_survive & ~VLV_GFX_CLK_FORCE_ON_BIT); intel_uncore_write(uncore, VLV_PMWGICZ, s->pmwgicz); @@ -308,14 +303,10 @@ static int vlv_wait_for_pw_status(struct drm_i915_private *i915, static int vlv_force_gfx_clock(struct drm_i915_private *i915, bool force_on) { struct intel_uncore *uncore = &i915->uncore; - u32 val; int err; - val = intel_uncore_read(uncore, VLV_GTLC_SURVIVABILITY_REG); - val &= ~VLV_GFX_CLK_FORCE_ON_BIT; - if (force_on) - val |= VLV_GFX_CLK_FORCE_ON_BIT; - intel_uncore_write(uncore, VLV_GTLC_SURVIVABILITY_REG, val); + intel_uncore_rmw(uncore, VLV_GTLC_SURVIVABILITY_REG, VLV_GFX_CLK_FORCE_ON_BIT, + force_on ? VLV_GFX_CLK_FORCE_ON_BIT : 0); if (!force_on) return 0; @@ -340,11 +331,8 @@ static int vlv_allow_gt_wake(struct drm_i915_private *i915, bool allow) u32 val; int err; - val = intel_uncore_read(uncore, VLV_GTLC_WAKE_CTRL); - val &= ~VLV_GTLC_ALLOWWAKEREQ; - if (allow) - val |= VLV_GTLC_ALLOWWAKEREQ; - intel_uncore_write(uncore, VLV_GTLC_WAKE_CTRL, val); + intel_uncore_rmw(uncore, VLV_GTLC_WAKE_CTRL, VLV_GTLC_ALLOWWAKEREQ, + allow ? VLV_GTLC_ALLOWWAKEREQ : 0); intel_uncore_posting_read(uncore, VLV_GTLC_WAKE_CTRL); mask = VLV_GTLC_ALLOWWAKEACK; |