diff options
Diffstat (limited to 'drivers/gpu/drm/i915')
282 files changed, 13434 insertions, 7945 deletions
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig index 84b6fc70cbf5..a4c94dc2e216 100644 --- a/drivers/gpu/drm/i915/Kconfig +++ b/drivers/gpu/drm/i915/Kconfig @@ -21,7 +21,7 @@ config DRM_I915 select ACPI_VIDEO if ACPI select ACPI_BUTTON if ACPI select SYNC_FILE - select IOSF_MBI + select IOSF_MBI if X86 select CRC32 select SND_HDA_I915 if SND_HDA_CORE select CEC_CORE if CEC_NOTIFIER diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 660bb03de6fc..1b62b9f65196 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -30,7 +30,7 @@ subdir-ccflags-y += -I$(srctree)/$(src) # Please keep these build lists sorted! # core driver code -i915-y += i915_drv.o \ +i915-y += i915_driver.o \ i915_config.o \ i915_irq.o \ i915_getparam.o \ @@ -60,7 +60,6 @@ i915-y += i915_drv.o \ # core library code i915-y += \ - dma_resv_utils.o \ i915_memcpy.o \ i915_mm.o \ i915_sw_fence.o \ @@ -154,6 +153,7 @@ gem-y += \ gem/i915_gem_throttle.o \ gem/i915_gem_tiling.o \ gem/i915_gem_ttm.o \ + gem/i915_gem_ttm_move.o \ gem/i915_gem_ttm_pm.o \ gem/i915_gem_userptr.o \ gem/i915_gem_wait.o \ @@ -163,6 +163,7 @@ i915-y += \ i915_active.o \ i915_buddy.o \ i915_cmd_parser.o \ + i915_deps.o \ i915_gem_evict.o \ i915_gem_gtt.o \ i915_gem_ww.o \ @@ -173,6 +174,7 @@ i915-y += \ i915_trace_points.o \ i915_ttm_buddy_manager.o \ i915_vma.o \ + i915_vma_snapshot.o \ intel_wopcm.o # general-purpose microcontroller (GuC) support @@ -226,6 +228,8 @@ i915-y += \ display/intel_hotplug.o \ display/intel_lpe_audio.o \ display/intel_overlay.o \ + display/intel_pch_display.o \ + display/intel_pch_refclk.o \ display/intel_plane_initial.o \ display/intel_psr.o \ display/intel_quirks.o \ @@ -256,6 +260,7 @@ i915-y += \ display/intel_crt.o \ display/intel_ddi.o \ display/intel_ddi_buf_trans.o \ + display/intel_display_trace.o \ display/intel_dp.o \ display/intel_dp_aux.o \ display/intel_dp_aux_backlight.o \ diff --git a/drivers/gpu/drm/i915/display/g4x_dp.c b/drivers/gpu/drm/i915/display/g4x_dp.c index dc41868d01ef..f37677df6ebf 100644 --- a/drivers/gpu/drm/i915/display/g4x_dp.c +++ b/drivers/gpu/drm/i915/display/g4x_dp.c @@ -9,6 +9,7 @@ #include "intel_audio.h" #include "intel_backlight.h" #include "intel_connector.h" +#include "intel_crtc.h" #include "intel_de.h" #include "intel_display_types.h" #include "intel_dp.h" diff --git a/drivers/gpu/drm/i915/display/g4x_hdmi.c b/drivers/gpu/drm/i915/display/g4x_hdmi.c index f5b4dd5b4275..06e00b1eaa7c 100644 --- a/drivers/gpu/drm/i915/display/g4x_hdmi.c +++ b/drivers/gpu/drm/i915/display/g4x_hdmi.c @@ -8,6 +8,7 @@ #include "g4x_hdmi.h" #include "intel_audio.h" #include "intel_connector.h" +#include "intel_crtc.h" #include "intel_de.h" #include "intel_display_types.h" #include "intel_dpio_phy.h" diff --git a/drivers/gpu/drm/i915/display/i9xx_plane.c b/drivers/gpu/drm/i915/display/i9xx_plane.c index b1439ba78f67..85950ff67609 100644 --- a/drivers/gpu/drm/i915/display/i9xx_plane.c +++ b/drivers/gpu/drm/i915/display/i9xx_plane.c @@ -13,6 +13,7 @@ #include "intel_de.h" #include "intel_display_types.h" #include "intel_fb.h" +#include "intel_fbc.h" #include "intel_sprite.h" #include "i9xx_plane.h" @@ -60,22 +61,11 @@ static const u32 vlv_primary_formats[] = { DRM_FORMAT_XBGR16161616F, }; -static const u64 i9xx_format_modifiers[] = { - I915_FORMAT_MOD_X_TILED, - DRM_FORMAT_MOD_LINEAR, - DRM_FORMAT_MOD_INVALID -}; - static bool i8xx_plane_format_mod_supported(struct drm_plane *_plane, u32 format, u64 modifier) { - switch (modifier) { - case DRM_FORMAT_MOD_LINEAR: - case I915_FORMAT_MOD_X_TILED: - break; - default: + if (!intel_fb_plane_supports_modifier(to_intel_plane(_plane), modifier)) return false; - } switch (format) { case DRM_FORMAT_C8: @@ -92,13 +82,8 @@ static bool i8xx_plane_format_mod_supported(struct drm_plane *_plane, static bool i965_plane_format_mod_supported(struct drm_plane *_plane, u32 format, u64 modifier) { - switch (modifier) { - case DRM_FORMAT_MOD_LINEAR: - case I915_FORMAT_MOD_X_TILED: - break; - default: + if (!intel_fb_plane_supports_modifier(to_intel_plane(_plane), modifier)) return false; - } switch (format) { case DRM_FORMAT_C8: @@ -136,6 +121,15 @@ static bool i9xx_plane_has_fbc(struct drm_i915_private *dev_priv, return i9xx_plane == PLANE_A; } +static struct intel_fbc *i9xx_plane_fbc(struct drm_i915_private *dev_priv, + enum i9xx_plane_id i9xx_plane) +{ + if (i9xx_plane_has_fbc(dev_priv, i9xx_plane)) + return dev_priv->fbc; + else + return NULL; +} + static bool i9xx_plane_has_windowing(struct intel_plane *plane) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); @@ -272,7 +266,7 @@ int i9xx_check_plane_surface(struct intel_plane_state *plane_state) u32 alignment = intel_surf_alignment(fb, 0); int cpp = fb->format->cpp[0]; - while ((src_x + src_w) * cpp > plane_state->view.color_plane[0].stride) { + while ((src_x + src_w) * cpp > plane_state->view.color_plane[0].mapping_stride) { if (offset == 0) { drm_dbg_kms(&dev_priv->drm, "Unable to find suitable display surface offset due to X-tiling\n"); @@ -418,38 +412,25 @@ static int i9xx_plane_min_cdclk(const struct intel_crtc_state *crtc_state, return DIV_ROUND_UP(pixel_rate * num, den); } -static void i9xx_update_plane(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state, - const struct intel_plane_state *plane_state) +static void i9xx_plane_update_noarm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum i9xx_plane_id i9xx_plane = plane->i9xx_plane; - u32 linear_offset; - int x = plane_state->view.color_plane[0].x; - int y = plane_state->view.color_plane[0].y; - int crtc_x = plane_state->uapi.dst.x1; - int crtc_y = plane_state->uapi.dst.y1; - int crtc_w = drm_rect_width(&plane_state->uapi.dst); - int crtc_h = drm_rect_height(&plane_state->uapi.dst); unsigned long irqflags; - u32 dspaddr_offset; - u32 dspcntr; - - dspcntr = plane_state->ctl | i9xx_plane_ctl_crtc(crtc_state); - - linear_offset = intel_fb_xy_to_linear(x, y, plane_state, 0); - - if (DISPLAY_VER(dev_priv) >= 4) - dspaddr_offset = plane_state->view.color_plane[0].offset; - else - dspaddr_offset = linear_offset; spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); intel_de_write_fw(dev_priv, DSPSTRIDE(i9xx_plane), - plane_state->view.color_plane[0].stride); + plane_state->view.color_plane[0].mapping_stride); if (DISPLAY_VER(dev_priv) < 4) { + int crtc_x = plane_state->uapi.dst.x1; + int crtc_y = plane_state->uapi.dst.y1; + int crtc_w = drm_rect_width(&plane_state->uapi.dst); + int crtc_h = drm_rect_height(&plane_state->uapi.dst); + /* * PLANE_A doesn't actually have a full window * generator but let's assume we still need to @@ -459,7 +440,39 @@ static void i9xx_update_plane(struct intel_plane *plane, (crtc_y << 16) | crtc_x); intel_de_write_fw(dev_priv, DSPSIZE(i9xx_plane), ((crtc_h - 1) << 16) | (crtc_w - 1)); - } else if (IS_CHERRYVIEW(dev_priv) && i9xx_plane == PLANE_B) { + } + + spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); +} + +static void i9xx_plane_update_arm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) +{ + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + enum i9xx_plane_id i9xx_plane = plane->i9xx_plane; + int x = plane_state->view.color_plane[0].x; + int y = plane_state->view.color_plane[0].y; + u32 dspcntr, dspaddr_offset, linear_offset; + unsigned long irqflags; + + dspcntr = plane_state->ctl | i9xx_plane_ctl_crtc(crtc_state); + + linear_offset = intel_fb_xy_to_linear(x, y, plane_state, 0); + + if (DISPLAY_VER(dev_priv) >= 4) + dspaddr_offset = plane_state->view.color_plane[0].offset; + else + dspaddr_offset = linear_offset; + + spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); + + if (IS_CHERRYVIEW(dev_priv) && i9xx_plane == PLANE_B) { + int crtc_x = plane_state->uapi.dst.x1; + int crtc_y = plane_state->uapi.dst.y1; + int crtc_w = drm_rect_width(&plane_state->uapi.dst); + int crtc_h = drm_rect_height(&plane_state->uapi.dst); + intel_de_write_fw(dev_priv, PRIMPOS(i9xx_plane), (crtc_y << 16) | crtc_x); intel_de_write_fw(dev_priv, PRIMSIZE(i9xx_plane), @@ -493,8 +506,22 @@ static void i9xx_update_plane(struct intel_plane *plane, spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); } -static void i9xx_disable_plane(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state) +static void i830_plane_update_arm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) +{ + /* + * On i830/i845 all registers are self-arming [ALM040]. + * + * Additional breakage on i830 causes register reads to return + * the last latched value instead of the last written value [ALM026]. + */ + i9xx_plane_update_noarm(plane, crtc_state, plane_state); + i9xx_plane_update_arm(plane, crtc_state, plane_state); +} + +static void i9xx_plane_disable_arm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum i9xx_plane_id i9xx_plane = plane->i9xx_plane; @@ -768,6 +795,7 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe) struct intel_plane *plane; const struct drm_plane_funcs *plane_funcs; unsigned int supported_rotations; + const u64 *modifiers; const u32 *formats; int num_formats; int ret, zpos; @@ -789,12 +817,7 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe) plane->id = PLANE_PRIMARY; plane->frontbuffer_bit = INTEL_FRONTBUFFER(pipe, plane->id); - plane->has_fbc = i9xx_plane_has_fbc(dev_priv, plane->i9xx_plane); - if (plane->has_fbc) { - struct intel_fbc *fbc = &dev_priv->fbc; - - fbc->possible_framebuffer_bits |= plane->frontbuffer_bit; - } + intel_fbc_add_plane(i9xx_plane_fbc(dev_priv, plane->i9xx_plane), plane); if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { formats = vlv_primary_formats; @@ -851,8 +874,13 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe) plane->max_stride = ilk_primary_max_stride; } - plane->update_plane = i9xx_update_plane; - plane->disable_plane = i9xx_disable_plane; + if (IS_I830(dev_priv) || IS_I845G(dev_priv)) { + plane->update_arm = i830_plane_update_arm; + } else { + plane->update_noarm = i9xx_plane_update_noarm; + plane->update_arm = i9xx_plane_update_arm; + } + plane->disable_arm = i9xx_plane_disable_arm; plane->get_hw_state = i9xx_plane_get_hw_state; plane->check_plane = i9xx_plane_check; @@ -875,21 +903,26 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe) plane->disable_flip_done = ilk_primary_disable_flip_done; } + modifiers = intel_fb_plane_get_modifiers(dev_priv, INTEL_PLANE_CAP_TILING_X); + if (DISPLAY_VER(dev_priv) >= 5 || IS_G4X(dev_priv)) ret = drm_universal_plane_init(&dev_priv->drm, &plane->base, 0, plane_funcs, formats, num_formats, - i9xx_format_modifiers, + modifiers, DRM_PLANE_TYPE_PRIMARY, "primary %c", pipe_name(pipe)); else ret = drm_universal_plane_init(&dev_priv->drm, &plane->base, 0, plane_funcs, formats, num_formats, - i9xx_format_modifiers, + modifiers, DRM_PLANE_TYPE_PRIMARY, "plane %c", plane_name(plane->i9xx_plane)); + + kfree(modifiers); + if (ret) goto fail; diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index 71fbdcddd31f..5781e9fac8b4 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -28,6 +28,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_mipi_dsi.h> +#include "icl_dsi.h" #include "intel_atomic.h" #include "intel_backlight.h" #include "intel_combo_phy.h" @@ -36,6 +37,7 @@ #include "intel_ddi.h" #include "intel_de.h" #include "intel_dsi.h" +#include "intel_dsi_vbt.h" #include "intel_panel.h" #include "intel_vdsc.h" #include "skl_scaler.h" @@ -183,6 +185,8 @@ static int dsi_send_pkt_hdr(struct intel_dsi_host *host, if (enable_lpdt) tmp |= LP_DATA_TRANSFER; + else + tmp &= ~LP_DATA_TRANSFER; tmp &= ~(PARAM_WC_MASK | VC_MASK | DT_MASK); tmp |= ((packet->header[0] & VC_MASK) << VC_SHIFT); @@ -1226,7 +1230,9 @@ static void gen11_dsi_pre_enable(struct intel_atomic_state *state, /* step5: program and powerup panel */ gen11_dsi_powerup_panel(encoder); - intel_dsc_enable(encoder, pipe_config); + intel_dsc_dsi_pps_write(encoder, pipe_config); + + intel_dsc_enable(pipe_config); /* step6c: configure transcoder timings */ gen11_dsi_set_transcoder_timings(encoder, pipe_config); @@ -1623,7 +1629,7 @@ static int gen11_dsi_dsc_compute_config(struct intel_encoder *encoder, /* FIXME: initialize from VBT */ vdsc_cfg->rc_model_size = DSC_RC_MODEL_SIZE_CONST; - ret = intel_dsc_compute_params(encoder, crtc_state); + ret = intel_dsc_compute_params(crtc_state); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/display/icl_dsi.h b/drivers/gpu/drm/i915/display/icl_dsi.h new file mode 100644 index 000000000000..b4861b56b5b2 --- /dev/null +++ b/drivers/gpu/drm/i915/display/icl_dsi.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef __ICL_DSI_H__ +#define __ICL_DSI_H__ + +struct drm_i915_private; +struct intel_crtc_state; + +void icl_dsi_init(struct drm_i915_private *i915); +void icl_dsi_frame_update(struct intel_crtc_state *crtc_state); + +#endif /* __ICL_DSI_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_atomic.c b/drivers/gpu/drm/i915/display/intel_atomic.c index b4e7ac51aa31..a62550711e98 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic.c +++ b/drivers/gpu/drm/i915/display/intel_atomic.c @@ -139,6 +139,7 @@ int intel_digital_connector_atomic_check(struct drm_connector *conn, new_conn_state->base.picture_aspect_ratio != old_conn_state->base.picture_aspect_ratio || new_conn_state->base.content_type != old_conn_state->base.content_type || new_conn_state->base.scaling_mode != old_conn_state->base.scaling_mode || + new_conn_state->base.privacy_screen_sw_state != old_conn_state->base.privacy_screen_sw_state || !drm_connector_atomic_hdr_metadata_equal(old_state, new_state)) crtc_state->mode_changed = true; diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c index 0be8c00e3db9..c2c512cd8ec0 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c +++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c @@ -35,14 +35,16 @@ #include <drm/drm_fourcc.h> #include <drm/drm_plane_helper.h> -#include "i915_trace.h" +#include "gt/intel_rps.h" + #include "intel_atomic_plane.h" #include "intel_cdclk.h" +#include "intel_display_trace.h" #include "intel_display_types.h" +#include "intel_fb.h" #include "intel_fb_pin.h" #include "intel_pm.h" #include "intel_sprite.h" -#include "gt/intel_rps.h" static void intel_plane_state_reset(struct intel_plane_state *plane_state, struct intel_plane *plane) @@ -394,7 +396,7 @@ int intel_plane_atomic_check(struct intel_atomic_state *state, const struct intel_plane_state *old_plane_state = intel_atomic_get_old_plane_state(state, plane); const struct intel_plane_state *new_master_plane_state; - struct intel_crtc *crtc = intel_get_crtc_for_pipe(i915, plane->pipe); + struct intel_crtc *crtc = intel_crtc_for_pipe(i915, plane->pipe); const struct intel_crtc_state *old_crtc_state = intel_atomic_get_old_crtc_state(state, crtc); struct intel_crtc_state *new_crtc_state = @@ -469,31 +471,72 @@ skl_next_plane_to_commit(struct intel_atomic_state *state, return NULL; } -void intel_update_plane(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state, - const struct intel_plane_state *plane_state) +void intel_plane_update_noarm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) +{ + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + + trace_intel_plane_update_noarm(&plane->base, crtc); + + if (plane->update_noarm) + plane->update_noarm(plane, crtc_state, plane_state); +} + +void intel_plane_update_arm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - trace_intel_update_plane(&plane->base, crtc); + trace_intel_plane_update_arm(&plane->base, crtc); if (crtc_state->uapi.async_flip && plane->async_flip) plane->async_flip(plane, crtc_state, plane_state, true); else - plane->update_plane(plane, crtc_state, plane_state); + plane->update_arm(plane, crtc_state, plane_state); } -void intel_disable_plane(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state) +void intel_plane_disable_arm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - trace_intel_disable_plane(&plane->base, crtc); - plane->disable_plane(plane, crtc_state); + trace_intel_plane_disable_arm(&plane->base, crtc); + plane->disable_arm(plane, crtc_state); +} + +void intel_update_planes_on_crtc(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + struct intel_crtc_state *new_crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); + u32 update_mask = new_crtc_state->update_planes; + struct intel_plane_state *new_plane_state; + struct intel_plane *plane; + int i; + + if (new_crtc_state->uapi.async_flip) + return; + + /* + * Since we only write non-arming registers here, + * the order does not matter even for skl+. + */ + for_each_new_intel_plane_in_state(state, plane, new_plane_state, i) { + if (crtc->pipe != plane->pipe || + !(update_mask & BIT(plane->id))) + continue; + + /* TODO: for mailbox updates this should be skipped */ + if (new_plane_state->uapi.visible || + new_plane_state->planar_slave) + intel_plane_update_noarm(plane, new_crtc_state, new_plane_state); + } } -void skl_update_planes_on_crtc(struct intel_atomic_state *state, - struct intel_crtc *crtc) +void skl_arm_planes_on_crtc(struct intel_atomic_state *state, + struct intel_crtc *crtc) { struct intel_crtc_state *old_crtc_state = intel_atomic_get_old_crtc_state(state, crtc); @@ -515,17 +558,20 @@ void skl_update_planes_on_crtc(struct intel_atomic_state *state, struct intel_plane_state *new_plane_state = intel_atomic_get_new_plane_state(state, plane); + /* + * TODO: for mailbox updates intel_plane_update_noarm() + * would have to be called here as well. + */ if (new_plane_state->uapi.visible || - new_plane_state->planar_slave) { - intel_update_plane(plane, new_crtc_state, new_plane_state); - } else { - intel_disable_plane(plane, new_crtc_state); - } + new_plane_state->planar_slave) + intel_plane_update_arm(plane, new_crtc_state, new_plane_state); + else + intel_plane_disable_arm(plane, new_crtc_state); } } -void i9xx_update_planes_on_crtc(struct intel_atomic_state *state, - struct intel_crtc *crtc) +void i9xx_arm_planes_on_crtc(struct intel_atomic_state *state, + struct intel_crtc *crtc) { struct intel_crtc_state *new_crtc_state = intel_atomic_get_new_crtc_state(state, crtc); @@ -539,10 +585,14 @@ void i9xx_update_planes_on_crtc(struct intel_atomic_state *state, !(update_mask & BIT(plane->id))) continue; + /* + * TODO: for mailbox updates intel_plane_update_noarm() + * would have to be called here as well. + */ if (new_plane_state->uapi.visible) - intel_update_plane(plane, new_crtc_state, new_plane_state); + intel_plane_update_arm(plane, new_crtc_state, new_plane_state); else - intel_disable_plane(plane, new_crtc_state); + intel_plane_disable_arm(plane, new_crtc_state); } } @@ -738,6 +788,7 @@ intel_prepare_plane_fb(struct drm_plane *_plane, i915_gem_object_wait_priority(obj, 0, &attr); if (!new_plane_state->uapi.fence) { /* implicit fencing */ + struct dma_resv_iter cursor; struct dma_fence *fence; ret = i915_sw_fence_await_reservation(&state->commit_ready, @@ -748,12 +799,12 @@ intel_prepare_plane_fb(struct drm_plane *_plane, if (ret < 0) goto unpin_fb; - fence = dma_resv_get_excl_unlocked(obj->base.resv); - if (fence) { + dma_resv_iter_begin(&cursor, obj->base.resv, false); + dma_resv_for_each_fence_unlocked(&cursor, fence) { add_rps_boost_after_vblank(new_plane_state->hw.crtc, fence); - dma_fence_put(fence); } + dma_resv_iter_end(&cursor); } else { add_rps_boost_after_vblank(new_plane_state->hw.crtc, new_plane_state->uapi.fence); @@ -768,7 +819,7 @@ intel_prepare_plane_fb(struct drm_plane *_plane, * maximum clocks following a vblank miss (see do_rps_boost()). */ if (!state->rps_interactive) { - intel_rps_mark_interactive(&dev_priv->gt.rps, true); + intel_rps_mark_interactive(&to_gt(dev_priv)->rps, true); state->rps_interactive = true; } @@ -802,7 +853,7 @@ intel_cleanup_plane_fb(struct drm_plane *plane, return; if (state->rps_interactive) { - intel_rps_mark_interactive(&dev_priv->gt.rps, false); + intel_rps_mark_interactive(&to_gt(dev_priv)->rps, false); state->rps_interactive = false; } diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.h b/drivers/gpu/drm/i915/display/intel_atomic_plane.h index 62e5a2a77fd4..7907f601598e 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic_plane.h +++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.h @@ -30,20 +30,25 @@ void intel_plane_copy_uapi_to_hw_state(struct intel_plane_state *plane_state, struct intel_crtc *crtc); void intel_plane_copy_hw_state(struct intel_plane_state *plane_state, const struct intel_plane_state *from_plane_state); -void intel_update_plane(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state, - const struct intel_plane_state *plane_state); -void intel_disable_plane(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state); +void intel_plane_update_noarm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state); +void intel_plane_update_arm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state); +void intel_plane_disable_arm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state); struct intel_plane *intel_plane_alloc(void); void intel_plane_free(struct intel_plane *plane); struct drm_plane_state *intel_plane_duplicate_state(struct drm_plane *plane); void intel_plane_destroy_state(struct drm_plane *plane, struct drm_plane_state *state); -void skl_update_planes_on_crtc(struct intel_atomic_state *state, - struct intel_crtc *crtc); -void i9xx_update_planes_on_crtc(struct intel_atomic_state *state, - struct intel_crtc *crtc); +void intel_update_planes_on_crtc(struct intel_atomic_state *state, + struct intel_crtc *crtc); +void skl_arm_planes_on_crtc(struct intel_atomic_state *state, + struct intel_crtc *crtc); +void i9xx_arm_planes_on_crtc(struct intel_atomic_state *state, + struct intel_crtc *crtc); int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_state, struct intel_crtc_state *crtc_state, const struct intel_plane_state *old_plane_state, diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c index 03e8c05a74f6..3bdca0fe2cee 100644 --- a/drivers/gpu/drm/i915/display/intel_audio.c +++ b/drivers/gpu/drm/i915/display/intel_audio.c @@ -31,6 +31,7 @@ #include "intel_atomic.h" #include "intel_audio.h" #include "intel_cdclk.h" +#include "intel_crtc.h" #include "intel_de.h" #include "intel_display_types.h" #include "intel_lpe_audio.h" @@ -62,6 +63,15 @@ * struct &i915_audio_component_audio_ops @audio_ops is called from i915 driver. */ +struct intel_audio_funcs { + void (*audio_codec_enable)(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state, + const struct drm_connector_state *conn_state); + void (*audio_codec_disable)(struct intel_encoder *encoder, + const struct intel_crtc_state *old_crtc_state, + const struct drm_connector_state *old_conn_state); +}; + /* DP N/M table */ #define LC_810M 810000 #define LC_540M 540000 @@ -388,7 +398,7 @@ 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->audio_component; + struct i915_audio_component *acomp = dev_priv->audio.component; enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; enum port port = encoder->port; const struct dp_aud_n_m *nm; @@ -436,7 +446,7 @@ 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->audio_component; + struct i915_audio_component *acomp = dev_priv->audio.component; enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; enum port port = encoder->port; int n, rate; @@ -494,7 +504,7 @@ static void hsw_audio_codec_disable(struct intel_encoder *encoder, drm_dbg_kms(&dev_priv->drm, "Disable audio codec on transcoder %s\n", transcoder_name(cpu_transcoder)); - mutex_lock(&dev_priv->av_mutex); + mutex_lock(&dev_priv->audio.mutex); /* Disable timestamps */ tmp = intel_de_read(dev_priv, HSW_AUD_CFG(cpu_transcoder)); @@ -512,7 +522,7 @@ static void hsw_audio_codec_disable(struct intel_encoder *encoder, tmp &= ~AUDIO_OUTPUT_ENABLE(cpu_transcoder); intel_de_write(dev_priv, HSW_AUD_PIN_ELD_CP_VLD, tmp); - mutex_unlock(&dev_priv->av_mutex); + mutex_unlock(&dev_priv->audio.mutex); } static unsigned int calc_hblank_early_prog(struct intel_encoder *encoder, @@ -641,7 +651,7 @@ static void hsw_audio_codec_enable(struct intel_encoder *encoder, "Enable audio codec on transcoder %s, %u bytes ELD\n", transcoder_name(cpu_transcoder), drm_eld_size(eld)); - mutex_lock(&dev_priv->av_mutex); + mutex_lock(&dev_priv->audio.mutex); /* Enable Audio WA for 4k DSC usecases */ if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP)) @@ -679,7 +689,7 @@ static void hsw_audio_codec_enable(struct intel_encoder *encoder, /* Enable timestamps */ hsw_audio_config_update(encoder, crtc_state); - mutex_unlock(&dev_priv->av_mutex); + mutex_unlock(&dev_priv->audio.mutex); } static void ilk_audio_codec_disable(struct intel_encoder *encoder, @@ -826,7 +836,7 @@ void intel_audio_codec_enable(struct intel_encoder *encoder, 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->audio_component; + struct i915_audio_component *acomp = dev_priv->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 = @@ -848,17 +858,17 @@ void intel_audio_codec_enable(struct intel_encoder *encoder, connector->eld[6] = drm_av_sync_delay(connector, adjusted_mode) / 2; - if (dev_priv->audio_funcs) - dev_priv->audio_funcs->audio_codec_enable(encoder, + if (dev_priv->audio.funcs) + dev_priv->audio.funcs->audio_codec_enable(encoder, crtc_state, conn_state); - mutex_lock(&dev_priv->av_mutex); + mutex_lock(&dev_priv->audio.mutex); encoder->audio_connector = connector; /* referred in audio callbacks */ - dev_priv->av_enc_map[pipe] = encoder; - mutex_unlock(&dev_priv->av_mutex); + dev_priv->audio.encoder_map[pipe] = encoder; + mutex_unlock(&dev_priv->audio.mutex); if (acomp && acomp->base.audio_ops && acomp->base.audio_ops->pin_eld_notify) { @@ -888,20 +898,20 @@ void intel_audio_codec_disable(struct intel_encoder *encoder, 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->audio_component; + struct i915_audio_component *acomp = dev_priv->audio.component; struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc); enum port port = encoder->port; enum pipe pipe = crtc->pipe; - if (dev_priv->audio_funcs) - dev_priv->audio_funcs->audio_codec_disable(encoder, + if (dev_priv->audio.funcs) + dev_priv->audio.funcs->audio_codec_disable(encoder, old_crtc_state, old_conn_state); - mutex_lock(&dev_priv->av_mutex); + mutex_lock(&dev_priv->audio.mutex); encoder->audio_connector = NULL; - dev_priv->av_enc_map[pipe] = NULL; - mutex_unlock(&dev_priv->av_mutex); + dev_priv->audio.encoder_map[pipe] = NULL; + mutex_unlock(&dev_priv->audio.mutex); if (acomp && acomp->base.audio_ops && acomp->base.audio_ops->pin_eld_notify) { @@ -931,19 +941,53 @@ static const struct intel_audio_funcs hsw_audio_funcs = { }; /** - * intel_init_audio_hooks - Set up chip specific audio hooks + * intel_audio_hooks_init - Set up chip specific audio hooks * @dev_priv: device private */ -void intel_init_audio_hooks(struct drm_i915_private *dev_priv) +void intel_audio_hooks_init(struct drm_i915_private *dev_priv) { if (IS_G4X(dev_priv)) { - dev_priv->audio_funcs = &g4x_audio_funcs; + dev_priv->audio.funcs = &g4x_audio_funcs; } else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { - dev_priv->audio_funcs = &ilk_audio_funcs; + dev_priv->audio.funcs = &ilk_audio_funcs; } else if (IS_HASWELL(dev_priv) || DISPLAY_VER(dev_priv) >= 8) { - dev_priv->audio_funcs = &hsw_audio_funcs; + dev_priv->audio.funcs = &hsw_audio_funcs; } else if (HAS_PCH_SPLIT(dev_priv)) { - dev_priv->audio_funcs = &ilk_audio_funcs; + dev_priv->audio.funcs = &ilk_audio_funcs; + } +} + +struct aud_ts_cdclk_m_n { + u8 m; + u16 n; +}; + +void intel_audio_cdclk_change_pre(struct drm_i915_private *i915) +{ + if (DISPLAY_VER(i915) >= 13) + intel_de_rmw(i915, AUD_TS_CDCLK_M, AUD_TS_CDCLK_M_EN, 0); +} + +static void get_aud_ts_cdclk_m_n(int refclk, int cdclk, struct aud_ts_cdclk_m_n *aud_ts) +{ + if (refclk == 24000) + aud_ts->m = 12; + else + aud_ts->m = 15; + + aud_ts->n = cdclk * aud_ts->m / 24000; +} + +void intel_audio_cdclk_change_post(struct drm_i915_private *i915) +{ + struct aud_ts_cdclk_m_n aud_ts; + + if (DISPLAY_VER(i915) >= 13) { + get_aud_ts_cdclk_m_n(i915->cdclk.hw.ref, i915->cdclk.hw.cdclk, &aud_ts); + + intel_de_write(i915, AUD_TS_CDCLK_N, aud_ts.n); + intel_de_write(i915, AUD_TS_CDCLK_M, aud_ts.m | AUD_TS_CDCLK_M_EN); + drm_dbg_kms(&i915->drm, "aud_ts_cdclk set to M=%u, N=%u\n", aud_ts.m, aud_ts.n); } } @@ -976,7 +1020,7 @@ static void glk_force_audio_cdclk(struct drm_i915_private *dev_priv, struct intel_crtc *crtc; int ret; - crtc = intel_get_first_crtc(dev_priv); + crtc = intel_first_crtc(dev_priv); if (!crtc) return; @@ -1014,13 +1058,13 @@ static unsigned long i915_audio_component_get_power(struct device *kdev) ret = intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO_PLAYBACK); - if (dev_priv->audio_power_refcount++ == 0) { + if (dev_priv->audio.power_refcount++ == 0) { if (DISPLAY_VER(dev_priv) >= 9) { intel_de_write(dev_priv, AUD_FREQ_CNTRL, - dev_priv->audio_freq_cntrl); + dev_priv->audio.freq_cntrl); drm_dbg_kms(&dev_priv->drm, "restored AUD_FREQ_CNTRL to 0x%x\n", - dev_priv->audio_freq_cntrl); + dev_priv->audio.freq_cntrl); } /* Force CDCLK to 2*BCLK as long as we need audio powered. */ @@ -1041,7 +1085,7 @@ static void i915_audio_component_put_power(struct device *kdev, struct drm_i915_private *dev_priv = kdev_to_i915(kdev); /* Stop forcing CDCLK to 2*BCLK if no need for audio to be powered. */ - if (--dev_priv->audio_power_refcount == 0) + if (--dev_priv->audio.power_refcount == 0) if (IS_GEMINILAKE(dev_priv)) glk_force_audio_cdclk(dev_priv, false); @@ -1093,7 +1137,7 @@ static int i915_audio_component_get_cdclk_freq(struct device *kdev) /* * get the intel_encoder according to the parameter port and pipe * intel_encoder is saved by the index of pipe - * MST & (pipe >= 0): return the av_enc_map[pipe], + * MST & (pipe >= 0): return the audio.encoder_map[pipe], * when port is matched * MST & (pipe < 0): this is invalid * Non-MST & (pipe >= 0): only pipe = 0 (the first device entry) @@ -1108,10 +1152,10 @@ static struct intel_encoder *get_saved_enc(struct drm_i915_private *dev_priv, /* MST */ if (pipe >= 0) { if (drm_WARN_ON(&dev_priv->drm, - pipe >= ARRAY_SIZE(dev_priv->av_enc_map))) + pipe >= ARRAY_SIZE(dev_priv->audio.encoder_map))) return NULL; - encoder = dev_priv->av_enc_map[pipe]; + encoder = dev_priv->audio.encoder_map[pipe]; /* * when bootup, audio driver may not know it is * MST or not. So it will poll all the port & pipe @@ -1127,7 +1171,7 @@ static struct intel_encoder *get_saved_enc(struct drm_i915_private *dev_priv, return NULL; for_each_pipe(dev_priv, pipe) { - encoder = dev_priv->av_enc_map[pipe]; + encoder = dev_priv->audio.encoder_map[pipe]; if (encoder == NULL) continue; @@ -1145,7 +1189,7 @@ 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->audio_component; + struct i915_audio_component *acomp = dev_priv->audio.component; struct intel_encoder *encoder; struct intel_crtc *crtc; unsigned long cookie; @@ -1155,7 +1199,7 @@ static int i915_audio_component_sync_audio_rate(struct device *kdev, int port, return 0; cookie = i915_audio_component_get_power(kdev); - mutex_lock(&dev_priv->av_mutex); + mutex_lock(&dev_priv->audio.mutex); /* 1. get the pipe */ encoder = get_saved_enc(dev_priv, port, pipe); @@ -1174,7 +1218,7 @@ 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->av_mutex); + mutex_unlock(&dev_priv->audio.mutex); i915_audio_component_put_power(kdev, cookie); return err; } @@ -1188,13 +1232,13 @@ static int i915_audio_component_get_eld(struct device *kdev, int port, const u8 *eld; int ret = -EINVAL; - mutex_lock(&dev_priv->av_mutex); + mutex_lock(&dev_priv->audio.mutex); intel_encoder = get_saved_enc(dev_priv, port, pipe); if (!intel_encoder) { drm_dbg_kms(&dev_priv->drm, "Not valid for port %c\n", port_name(port)); - mutex_unlock(&dev_priv->av_mutex); + mutex_unlock(&dev_priv->audio.mutex); return ret; } @@ -1206,7 +1250,7 @@ static int i915_audio_component_get_eld(struct device *kdev, int port, memcpy(buf, eld, min(max_bytes, ret)); } - mutex_unlock(&dev_priv->av_mutex); + mutex_unlock(&dev_priv->audio.mutex); return ret; } @@ -1241,7 +1285,7 @@ static int i915_audio_component_bind(struct device *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->audio_component = acomp; + dev_priv->audio.component = acomp; drm_modeset_unlock_all(&dev_priv->drm); return 0; @@ -1256,14 +1300,14 @@ static void i915_audio_component_unbind(struct device *i915_kdev, drm_modeset_lock_all(&dev_priv->drm); acomp->base.ops = NULL; acomp->base.dev = NULL; - dev_priv->audio_component = NULL; + dev_priv->audio.component = NULL; drm_modeset_unlock_all(&dev_priv->drm); device_link_remove(hda_kdev, i915_kdev); - if (dev_priv->audio_power_refcount) + if (dev_priv->audio.power_refcount) drm_err(&dev_priv->drm, "audio power refcount %d after unbind\n", - dev_priv->audio_power_refcount); + dev_priv->audio.power_refcount); } static const struct component_ops i915_audio_component_bind_ops = { @@ -1327,10 +1371,13 @@ static void i915_audio_component_init(struct drm_i915_private *dev_priv) drm_dbg_kms(&dev_priv->drm, "use AUD_FREQ_CNTRL of 0x%x (init value 0x%x)\n", aud_freq, aud_freq_init); - dev_priv->audio_freq_cntrl = aud_freq; + dev_priv->audio.freq_cntrl = aud_freq; } - dev_priv->audio_component_registered = true; + /* init with current cdclk */ + intel_audio_cdclk_change_post(dev_priv); + + dev_priv->audio.component_registered = true; } /** @@ -1342,11 +1389,11 @@ static void i915_audio_component_init(struct drm_i915_private *dev_priv) */ static void i915_audio_component_cleanup(struct drm_i915_private *dev_priv) { - if (!dev_priv->audio_component_registered) + if (!dev_priv->audio.component_registered) return; component_del(dev_priv->drm.dev, &i915_audio_component_bind_ops); - dev_priv->audio_component_registered = false; + dev_priv->audio.component_registered = false; } /** @@ -1368,7 +1415,7 @@ void intel_audio_init(struct drm_i915_private *dev_priv) */ void intel_audio_deinit(struct drm_i915_private *dev_priv) { - if ((dev_priv)->lpe_audio.platdev != NULL) + if ((dev_priv)->audio.lpe.platdev != NULL) intel_lpe_audio_teardown(dev_priv); else i915_audio_component_cleanup(dev_priv); diff --git a/drivers/gpu/drm/i915/display/intel_audio.h b/drivers/gpu/drm/i915/display/intel_audio.h index a3657c7a7ba2..63b22131dc45 100644 --- a/drivers/gpu/drm/i915/display/intel_audio.h +++ b/drivers/gpu/drm/i915/display/intel_audio.h @@ -11,13 +11,15 @@ struct drm_i915_private; struct intel_crtc_state; struct intel_encoder; -void intel_init_audio_hooks(struct drm_i915_private *dev_priv); +void intel_audio_hooks_init(struct drm_i915_private *dev_priv); void intel_audio_codec_enable(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state); 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); +void intel_audio_cdclk_change_pre(struct drm_i915_private *dev_priv); +void intel_audio_cdclk_change_post(struct drm_i915_private *dev_priv); void intel_audio_init(struct drm_i915_private *dev_priv); void intel_audio_deinit(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c index 2b1423a43437..9d989c9f5da4 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -1555,12 +1555,24 @@ static const u8 gen9bc_tgp_ddc_pin_map[] = { [DDC_BUS_DDI_D] = GMBUS_PIN_10_TC2_ICP, }; +static const u8 adlp_ddc_pin_map[] = { + [ICL_DDC_BUS_DDI_A] = GMBUS_PIN_1_BXT, + [ICL_DDC_BUS_DDI_B] = GMBUS_PIN_2_BXT, + [ADLP_DDC_BUS_PORT_TC1] = GMBUS_PIN_9_TC1_ICP, + [ADLP_DDC_BUS_PORT_TC2] = GMBUS_PIN_10_TC2_ICP, + [ADLP_DDC_BUS_PORT_TC3] = GMBUS_PIN_11_TC3_ICP, + [ADLP_DDC_BUS_PORT_TC4] = GMBUS_PIN_12_TC4_ICP, +}; + static u8 map_ddc_pin(struct drm_i915_private *i915, u8 vbt_pin) { const u8 *ddc_pin_map; int n_entries; - if (IS_ALDERLAKE_S(i915)) { + if (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)) { ddc_pin_map = adls_ddc_pin_map; n_entries = ARRAY_SIZE(adls_ddc_pin_map); } else if (INTEL_PCH_TYPE(i915) >= PCH_DG1) { diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c index 8d9d888e9316..2da4aacc956b 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.c +++ b/drivers/gpu/drm/i915/display/intel_bw.c @@ -27,6 +27,9 @@ struct intel_qgv_info { u8 num_points; u8 num_psf_points; u8 t_bl; + u8 max_numchannels; + u8 channel_width; + u8 deinterleave; }; static int dg1_mchbar_read_qgv_point_info(struct drm_i915_private *dev_priv, @@ -42,7 +45,7 @@ static int dg1_mchbar_read_qgv_point_info(struct drm_i915_private *dev_priv, dclk_reference = 6; /* 6 * 16.666 MHz = 100 MHz */ else dclk_reference = 8; /* 8 * 16.666 MHz = 133 MHz */ - sp->dclk = dclk_ratio * dclk_reference; + sp->dclk = DIV_ROUND_UP((16667 * dclk_ratio * dclk_reference) + 500, 1000); val = intel_uncore_read(&dev_priv->uncore, SKL_MC_BIOS_DATA_0_0_0_MCHBAR_PCU); if (val & DG1_GEAR_TYPE) @@ -69,6 +72,7 @@ static int icl_pcode_read_qgv_point_info(struct drm_i915_private *dev_priv, int point) { u32 val = 0, val2 = 0; + u16 dclk; int ret; ret = sandybridge_pcode_read(dev_priv, @@ -78,7 +82,8 @@ static int icl_pcode_read_qgv_point_info(struct drm_i915_private *dev_priv, if (ret) return ret; - sp->dclk = val & 0xffff; + dclk = val & 0xffff; + sp->dclk = DIV_ROUND_UP((16667 * dclk) + (DISPLAY_VER(dev_priv) > 11 ? 500 : 0), 1000); sp->t_rp = (val & 0xff0000) >> 16; sp->t_rcd = (val & 0xff000000) >> 24; @@ -133,7 +138,8 @@ int icl_pcode_restrict_qgv_points(struct drm_i915_private *dev_priv, } static int icl_get_qgv_points(struct drm_i915_private *dev_priv, - struct intel_qgv_info *qi) + struct intel_qgv_info *qi, + bool is_y_tile) { const struct dram_info *dram_info = &dev_priv->dram_info; int i, ret; @@ -141,20 +147,44 @@ static int icl_get_qgv_points(struct drm_i915_private *dev_priv, qi->num_points = dram_info->num_qgv_points; qi->num_psf_points = dram_info->num_psf_gv_points; - if (DISPLAY_VER(dev_priv) == 12) + if (DISPLAY_VER(dev_priv) >= 12) switch (dram_info->type) { case INTEL_DRAM_DDR4: - qi->t_bl = 4; + qi->t_bl = is_y_tile ? 8 : 4; + qi->max_numchannels = 2; + qi->channel_width = 64; + qi->deinterleave = is_y_tile ? 1 : 2; break; case INTEL_DRAM_DDR5: - qi->t_bl = 8; + qi->t_bl = is_y_tile ? 16 : 8; + qi->max_numchannels = 4; + qi->channel_width = 32; + qi->deinterleave = is_y_tile ? 1 : 2; + break; + case INTEL_DRAM_LPDDR4: + if (IS_ROCKETLAKE(dev_priv)) { + qi->t_bl = 8; + qi->max_numchannels = 4; + qi->channel_width = 32; + qi->deinterleave = 2; + break; + } + fallthrough; + case INTEL_DRAM_LPDDR5: + qi->t_bl = 16; + qi->max_numchannels = 8; + qi->channel_width = 16; + qi->deinterleave = is_y_tile ? 2 : 4; break; default: qi->t_bl = 16; + qi->max_numchannels = 1; break; } - else if (DISPLAY_VER(dev_priv) == 11) + else if (DISPLAY_VER(dev_priv) == 11) { qi->t_bl = dev_priv->dram_info.type == INTEL_DRAM_DDR4 ? 4 : 8; + qi->max_numchannels = 1; + } if (drm_WARN_ON(&dev_priv->drm, qi->num_points > ARRAY_SIZE(qi->points))) @@ -193,12 +223,6 @@ static int icl_get_qgv_points(struct drm_i915_private *dev_priv, return 0; } -static int icl_calc_bw(int dclk, int num, int den) -{ - /* multiples of 16.666MHz (100/6) */ - return DIV_ROUND_CLOSEST(num * dclk * 100, den * 6); -} - static int adl_calc_psf_bw(int clk) { /* @@ -240,7 +264,7 @@ static const struct intel_sa_info tgl_sa_info = { }; static const struct intel_sa_info rkl_sa_info = { - .deburst = 16, + .deburst = 8, .deprogbwlimit = 20, /* GB/s */ .displayrtids = 128, .derating = 10, @@ -265,35 +289,130 @@ static int icl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel struct intel_qgv_info qi = {}; bool is_y_tile = true; /* assume y tile may be used */ int num_channels = max_t(u8, 1, dev_priv->dram_info.num_channels); - int deinterleave; - int ipqdepth, ipqdepthpch; + int ipqdepth, ipqdepthpch = 16; int dclk_max; int maxdebw; + int num_groups = ARRAY_SIZE(dev_priv->max_bw); int i, ret; - ret = icl_get_qgv_points(dev_priv, &qi); + ret = icl_get_qgv_points(dev_priv, &qi, is_y_tile); if (ret) { drm_dbg_kms(&dev_priv->drm, "Failed to get memory subsystem information, ignoring bandwidth limits"); return ret; } - deinterleave = DIV_ROUND_UP(num_channels, is_y_tile ? 4 : 2); dclk_max = icl_sagv_max_dclk(&qi); + maxdebw = min(sa->deprogbwlimit * 1000, dclk_max * 16 * 6 / 10); + ipqdepth = min(ipqdepthpch, sa->displayrtids / num_channels); + qi.deinterleave = DIV_ROUND_UP(num_channels, is_y_tile ? 4 : 2); + + for (i = 0; i < num_groups; i++) { + struct intel_bw_info *bi = &dev_priv->max_bw[i]; + int clpchgroup; + int j; + + clpchgroup = (sa->deburst * qi.deinterleave / num_channels) << i; + bi->num_planes = (ipqdepth - clpchgroup) / clpchgroup + 1; + + bi->num_qgv_points = qi.num_points; + bi->num_psf_gv_points = qi.num_psf_points; + + for (j = 0; j < qi.num_points; j++) { + const struct intel_qgv_point *sp = &qi.points[j]; + int ct, bw; + + /* + * Max row cycle time + * + * FIXME what is the logic behind the + * assumed burst length? + */ + ct = max_t(int, sp->t_rc, sp->t_rp + sp->t_rcd + + (clpchgroup - 1) * qi.t_bl + sp->t_rdpre); + bw = DIV_ROUND_UP(sp->dclk * clpchgroup * 32 * num_channels, ct); - ipqdepthpch = 16; + bi->deratedbw[j] = min(maxdebw, + bw * (100 - sa->derating) / 100); + + drm_dbg_kms(&dev_priv->drm, + "BW%d / QGV %d: num_planes=%d deratedbw=%u\n", + i, j, bi->num_planes, bi->deratedbw[j]); + } + } + /* + * In case if SAGV is disabled in BIOS, we always get 1 + * SAGV point, but we can't send PCode commands to restrict it + * as it will fail and pointless anyway. + */ + if (qi.num_points == 1) + dev_priv->sagv_status = I915_SAGV_NOT_CONTROLLED; + else + dev_priv->sagv_status = I915_SAGV_ENABLED; + + return 0; +} + +static int tgl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel_sa_info *sa) +{ + struct intel_qgv_info qi = {}; + const struct dram_info *dram_info = &dev_priv->dram_info; + bool is_y_tile = true; /* assume y tile may be used */ + int num_channels = max_t(u8, 1, dev_priv->dram_info.num_channels); + int ipqdepth, ipqdepthpch = 16; + int dclk_max; + int maxdebw, peakbw; + int clperchgroup; + int num_groups = ARRAY_SIZE(dev_priv->max_bw); + int i, ret; + + ret = icl_get_qgv_points(dev_priv, &qi, is_y_tile); + if (ret) { + drm_dbg_kms(&dev_priv->drm, + "Failed to get memory subsystem information, ignoring bandwidth limits"); + return ret; + } + + if (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); + + if (num_channels < qi.max_numchannels && DISPLAY_VER(dev_priv) >= 12) + qi.deinterleave = max(DIV_ROUND_UP(qi.deinterleave, 2), 1); + + if (DISPLAY_VER(dev_priv) > 11 && num_channels > qi.max_numchannels) + drm_warn(&dev_priv->drm, "Number of channels exceeds max number of channels."); + if (qi.max_numchannels != 0) + num_channels = min_t(u8, num_channels, qi.max_numchannels); + + dclk_max = icl_sagv_max_dclk(&qi); + + peakbw = num_channels * DIV_ROUND_UP(qi.channel_width, 8) * dclk_max; + maxdebw = min(sa->deprogbwlimit * 1000, peakbw * 6 / 10); /* 60% */ - maxdebw = min(sa->deprogbwlimit * 1000, - icl_calc_bw(dclk_max, 16, 1) * 6 / 10); /* 60% */ ipqdepth = min(ipqdepthpch, sa->displayrtids / num_channels); + /* + * clperchgroup = 4kpagespermempage * clperchperblock, + * clperchperblock = 8 / num_channels * interleave + */ + clperchgroup = 4 * DIV_ROUND_UP(8, num_channels) * qi.deinterleave; - for (i = 0; i < ARRAY_SIZE(dev_priv->max_bw); i++) { + for (i = 0; i < num_groups; i++) { struct intel_bw_info *bi = &dev_priv->max_bw[i]; + struct intel_bw_info *bi_next; int clpchgroup; int j; - clpchgroup = (sa->deburst * deinterleave / num_channels) << i; - bi->num_planes = (ipqdepth - clpchgroup) / clpchgroup + 1; + if (i < num_groups - 1) + bi_next = &dev_priv->max_bw[i + 1]; + + clpchgroup = (sa->deburst * qi.deinterleave / num_channels) << i; + + if (i < num_groups - 1 && clpchgroup < clperchgroup) + bi_next->num_planes = (ipqdepth - clpchgroup) / clpchgroup + 1; + else + bi_next->num_planes = 0; bi->num_qgv_points = qi.num_points; bi->num_psf_gv_points = qi.num_psf_points; @@ -310,7 +429,7 @@ static int icl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel */ ct = max_t(int, sp->t_rc, sp->t_rp + sp->t_rcd + (clpchgroup - 1) * qi.t_bl + sp->t_rdpre); - bw = icl_calc_bw(sp->dclk, clpchgroup * 32 * num_channels, ct); + bw = DIV_ROUND_UP(sp->dclk * clpchgroup * 32 * num_channels, ct); bi->deratedbw[j] = min(maxdebw, bw * (100 - sa->derating) / 100); @@ -329,9 +448,6 @@ static int icl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel "BW%d / PSF GV %d: num_planes=%d bw=%u\n", i, j, bi->num_planes, bi->psf_bw[j]); } - - if (bi->num_planes == 1) - break; } /* @@ -395,6 +511,34 @@ static unsigned int icl_max_bw(struct drm_i915_private *dev_priv, return 0; } +static unsigned int tgl_max_bw(struct drm_i915_private *dev_priv, + int num_planes, int qgv_point) +{ + int i; + + /* + * Let's return max bw for 0 planes + */ + num_planes = max(1, num_planes); + + for (i = ARRAY_SIZE(dev_priv->max_bw) - 1; i >= 0; i--) { + const struct intel_bw_info *bi = + &dev_priv->max_bw[i]; + + /* + * Pcode will not expose all QGV points when + * SAGV is forced to off/min/med/max. + */ + if (qgv_point >= bi->num_qgv_points) + return UINT_MAX; + + if (num_planes <= bi->num_planes) + return bi->deratedbw[qgv_point]; + } + + return dev_priv->max_bw[0].deratedbw[qgv_point]; +} + static unsigned int adl_psf_bw(struct drm_i915_private *dev_priv, int psf_gv_point) { @@ -412,13 +556,13 @@ void intel_bw_init_hw(struct drm_i915_private *dev_priv) if (IS_DG2(dev_priv)) dg2_get_bw_info(dev_priv); else if (IS_ALDERLAKE_P(dev_priv)) - icl_get_bw_info(dev_priv, &adlp_sa_info); + tgl_get_bw_info(dev_priv, &adlp_sa_info); else if (IS_ALDERLAKE_S(dev_priv)) - icl_get_bw_info(dev_priv, &adls_sa_info); + tgl_get_bw_info(dev_priv, &adls_sa_info); else if (IS_ROCKETLAKE(dev_priv)) - icl_get_bw_info(dev_priv, &rkl_sa_info); + tgl_get_bw_info(dev_priv, &rkl_sa_info); else if (DISPLAY_VER(dev_priv) == 12) - icl_get_bw_info(dev_priv, &tgl_sa_info); + tgl_get_bw_info(dev_priv, &tgl_sa_info); else if (DISPLAY_VER(dev_priv) == 11) icl_get_bw_info(dev_priv, &icl_sa_info); } @@ -490,7 +634,7 @@ static unsigned int intel_bw_data_rate(struct drm_i915_private *dev_priv, for_each_pipe(dev_priv, pipe) data_rate += bw_state->data_rate[pipe]; - if (DISPLAY_VER(dev_priv) >= 13 && intel_vtd_active()) + if (DISPLAY_VER(dev_priv) >= 13 && intel_vtd_active(dev_priv)) data_rate = data_rate * 105 / 100; return data_rate; @@ -746,7 +890,10 @@ int intel_bw_atomic_check(struct intel_atomic_state *state) for (i = 0; i < num_qgv_points; i++) { unsigned int max_data_rate; - max_data_rate = icl_max_bw(dev_priv, num_active_planes, i); + if (DISPLAY_VER(dev_priv) > 11) + max_data_rate = tgl_max_bw(dev_priv, num_active_planes, i); + else + max_data_rate = icl_max_bw(dev_priv, num_active_planes, i); /* * We need to know which qgv point gives us * maximum bandwidth in order to disable SAGV diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index 868dd43a7542..c30cf8d2b835 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -24,8 +24,11 @@ #include <linux/time.h> #include "intel_atomic.h" +#include "intel_atomic_plane.h" +#include "intel_audio.h" #include "intel_bw.h" #include "intel_cdclk.h" +#include "intel_crtc.h" #include "intel_de.h" #include "intel_display_types.h" #include "intel_pcode.h" @@ -66,7 +69,7 @@ void intel_cdclk_get_cdclk(struct drm_i915_private *dev_priv, dev_priv->cdclk_funcs->get_cdclk(dev_priv, cdclk_config); } -int intel_cdclk_bw_calc_min_cdclk(struct intel_atomic_state *state) +static int intel_cdclk_bw_calc_min_cdclk(struct intel_atomic_state *state) { struct drm_i915_private *dev_priv = to_i915(state->base.dev); return dev_priv->cdclk_funcs->bw_calc_min_cdclk(state); @@ -1211,6 +1214,19 @@ 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; + u16 waveform; + u8 divider; /* CD2X divider * 2 */ + u8 ratio; +}; + static const struct intel_cdclk_vals bxt_cdclk_table[] = { { .refclk = 19200, .cdclk = 144000, .divider = 8, .ratio = 60 }, { .refclk = 19200, .cdclk = 288000, .divider = 4, .ratio = 60 }, @@ -1312,12 +1328,19 @@ static const struct intel_cdclk_vals adlp_cdclk_table[] = { }; static const struct intel_cdclk_vals dg2_cdclk_table[] = { - { .refclk = 38400, .cdclk = 172800, .divider = 2, .ratio = 9 }, - { .refclk = 38400, .cdclk = 192000, .divider = 2, .ratio = 10 }, - { .refclk = 38400, .cdclk = 307200, .divider = 2, .ratio = 16 }, - { .refclk = 38400, .cdclk = 326400, .divider = 4, .ratio = 34 }, - { .refclk = 38400, .cdclk = 556800, .divider = 2, .ratio = 29 }, - { .refclk = 38400, .cdclk = 652800, .divider = 2, .ratio = 34 }, + { .refclk = 38400, .cdclk = 163200, .divider = 2, .ratio = 34, .waveform = 0x8888 }, + { .refclk = 38400, .cdclk = 204000, .divider = 2, .ratio = 34, .waveform = 0x9248 }, + { .refclk = 38400, .cdclk = 244800, .divider = 2, .ratio = 34, .waveform = 0xa4a4 }, + { .refclk = 38400, .cdclk = 285600, .divider = 2, .ratio = 34, .waveform = 0xa54a }, + { .refclk = 38400, .cdclk = 326400, .divider = 2, .ratio = 34, .waveform = 0xaaaa }, + { .refclk = 38400, .cdclk = 367200, .divider = 2, .ratio = 34, .waveform = 0xad5a }, + { .refclk = 38400, .cdclk = 408000, .divider = 2, .ratio = 34, .waveform = 0xb6b6 }, + { .refclk = 38400, .cdclk = 448800, .divider = 2, .ratio = 34, .waveform = 0xdbb6 }, + { .refclk = 38400, .cdclk = 489600, .divider = 2, .ratio = 34, .waveform = 0xeeee }, + { .refclk = 38400, .cdclk = 530400, .divider = 2, .ratio = 34, .waveform = 0xf7de }, + { .refclk = 38400, .cdclk = 571200, .divider = 2, .ratio = 34, .waveform = 0xfefe }, + { .refclk = 38400, .cdclk = 612000, .divider = 2, .ratio = 34, .waveform = 0xfffe }, + { .refclk = 38400, .cdclk = 652800, .divider = 2, .ratio = 34, .waveform = 0xffff }, {} }; @@ -1453,6 +1476,7 @@ static void bxt_de_pll_readout(struct drm_i915_private *dev_priv, static void bxt_get_cdclk(struct drm_i915_private *dev_priv, struct intel_cdclk_config *cdclk_config) { + u32 squash_ctl = 0; u32 divider; int div; @@ -1490,7 +1514,21 @@ static void bxt_get_cdclk(struct drm_i915_private *dev_priv, return; } - cdclk_config->cdclk = DIV_ROUND_CLOSEST(cdclk_config->vco, div); + if (has_cdclk_squasher(dev_priv)) + squash_ctl = intel_de_read(dev_priv, CDCLK_SQUASH_CTL); + + if (squash_ctl & CDCLK_SQUASH_ENABLE) { + u16 waveform; + int size; + + size = REG_FIELD_GET(CDCLK_SQUASH_WINDOW_SIZE_MASK, squash_ctl) + 1; + waveform = REG_FIELD_GET(CDCLK_SQUASH_WAVEFORM_MASK, squash_ctl) >> (16 - size); + + cdclk_config->cdclk = DIV_ROUND_CLOSEST(hweight16(waveform) * + cdclk_config->vco, size * div); + } else { + cdclk_config->cdclk = DIV_ROUND_CLOSEST(cdclk_config->vco, div); + } out: /* @@ -1625,6 +1663,26 @@ static u32 bxt_cdclk_cd2x_div_sel(struct drm_i915_private *dev_priv, } } +static u32 cdclk_squash_waveform(struct drm_i915_private *dev_priv, + int cdclk) +{ + const struct intel_cdclk_vals *table = dev_priv->cdclk.table; + int i; + + if (cdclk == dev_priv->cdclk.hw.bypass) + return 0; + + for (i = 0; table[i].refclk; i++) + if (table[i].refclk == dev_priv->cdclk.hw.ref && + table[i].cdclk == cdclk) + return table[i].waveform; + + drm_WARN(&dev_priv->drm, 1, "cdclk %d not valid for refclk %u\n", + cdclk, dev_priv->cdclk.hw.ref); + + return 0xffff; +} + static void bxt_set_cdclk(struct drm_i915_private *dev_priv, const struct intel_cdclk_config *cdclk_config, enum pipe pipe) @@ -1632,6 +1690,8 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv, int cdclk = cdclk_config->cdclk; int vco = cdclk_config->vco; u32 val; + u16 waveform; + int clock; int ret; /* Inform power controller of upcoming frequency change. */ @@ -1675,7 +1735,24 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv, bxt_de_pll_enable(dev_priv, vco); } - val = bxt_cdclk_cd2x_div_sel(dev_priv, cdclk, vco) | + waveform = cdclk_squash_waveform(dev_priv, cdclk); + + if (waveform) + clock = vco / 2; + 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); + } + + val = bxt_cdclk_cd2x_div_sel(dev_priv, clock, vco) | bxt_cdclk_cd2x_pipe(dev_priv, pipe) | skl_cdclk_decimal(cdclk); @@ -1689,7 +1766,7 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv, intel_de_write(dev_priv, CDCLK_CTL, val); if (pipe != INVALID_PIPE) - intel_wait_for_vblank(dev_priv, pipe); + intel_crtc_wait_for_next_vblank(intel_crtc_for_pipe(dev_priv, pipe)); if (DISPLAY_VER(dev_priv) >= 11) { ret = sandybridge_pcode_write(dev_priv, SKL_PCODE_CDCLK_CONTROL, @@ -1727,7 +1804,7 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv, static void bxt_sanitize_cdclk(struct drm_i915_private *dev_priv) { u32 cdctl, expected; - int cdclk, vco; + int cdclk, clock, vco; intel_update_cdclk(dev_priv); intel_dump_cdclk_config(&dev_priv->cdclk.hw, "Current CDCLK"); @@ -1763,8 +1840,12 @@ 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 */ - expected |= bxt_cdclk_cd2x_div_sel(dev_priv, - dev_priv->cdclk.hw.cdclk, + if (has_cdclk_squasher(dev_priv)) + clock = dev_priv->cdclk.hw.vco / 2; + else + clock = dev_priv->cdclk.hw.cdclk; + + expected |= bxt_cdclk_cd2x_div_sel(dev_priv, clock, dev_priv->cdclk.hw.vco); /* @@ -1880,6 +1961,25 @@ static bool intel_cdclk_can_crawl(struct drm_i915_private *dev_priv, a->ref == b->ref; } +static bool intel_cdclk_can_squash(struct drm_i915_private *dev_priv, + const struct intel_cdclk_config *a, + const struct intel_cdclk_config *b) +{ + /* + * FIXME should store a bit more state in intel_cdclk_config + * to differentiate squasher vs. cd2x divider properly. For + * the moment all platforms with squasher use a fixed cd2x + * divider. + */ + if (!has_cdclk_squasher(dev_priv)) + return false; + + return a->cdclk != b->cdclk && + a->vco != 0 && + a->vco == b->vco && + a->ref == b->ref; +} + /** * intel_cdclk_needs_modeset - Determine if changong between the CDCLK * configurations requires a modeset on all pipes @@ -1917,7 +2017,17 @@ static bool intel_cdclk_can_cd2x_update(struct drm_i915_private *dev_priv, if (DISPLAY_VER(dev_priv) < 10 && !IS_BROXTON(dev_priv)) return false; + /* + * FIXME should store a bit more state in intel_cdclk_config + * to differentiate squasher vs. cd2x divider properly. For + * the moment all platforms with squasher use a fixed cd2x + * divider. + */ + if (has_cdclk_squasher(dev_priv)) + return false; + return a->cdclk != b->cdclk && + a->vco != 0 && a->vco == b->vco && a->ref == b->ref; } @@ -1975,6 +2085,8 @@ static void intel_set_cdclk(struct drm_i915_private *dev_priv, intel_psr_pause(intel_dp); } + intel_audio_cdclk_change_pre(dev_priv); + /* * Lock aux/gmbus while we change cdclk in case those * functions use cdclk. Not all platforms/ports do, @@ -2003,6 +2115,8 @@ static void intel_set_cdclk(struct drm_i915_private *dev_priv, intel_psr_resume(intel_dp); } + intel_audio_cdclk_change_post(dev_priv); + if (drm_WARN(&dev_priv->drm, intel_cdclk_changed(&dev_priv->cdclk.hw, cdclk_config), "cdclk state doesn't match!\n")) { @@ -2524,6 +2638,58 @@ intel_atomic_get_cdclk_state(struct intel_atomic_state *state) return to_intel_cdclk_state(cdclk_state); } +int intel_cdclk_atomic_check(struct intel_atomic_state *state, + bool *need_cdclk_calc) +{ + struct drm_i915_private *i915 = to_i915(state->base.dev); + const struct intel_cdclk_state *old_cdclk_state; + const struct intel_cdclk_state *new_cdclk_state; + struct intel_plane_state *plane_state; + struct intel_bw_state *new_bw_state; + struct intel_plane *plane; + int min_cdclk = 0; + enum pipe pipe; + int ret; + int i; + + /* + * active_planes bitmask has been updated, and potentially affected + * planes are part of the state. We can now compute the minimum cdclk + * for each plane. + */ + for_each_new_intel_plane_in_state(state, plane, plane_state, i) { + ret = intel_plane_calc_min_cdclk(state, plane, need_cdclk_calc); + if (ret) + return ret; + } + + old_cdclk_state = intel_atomic_get_old_cdclk_state(state); + new_cdclk_state = intel_atomic_get_new_cdclk_state(state); + + if (new_cdclk_state && + old_cdclk_state->force_min_cdclk != new_cdclk_state->force_min_cdclk) + *need_cdclk_calc = true; + + ret = intel_cdclk_bw_calc_min_cdclk(state); + if (ret) + return ret; + + new_bw_state = intel_atomic_get_new_bw_state(state); + + if (!new_cdclk_state || !new_bw_state) + return 0; + + for_each_pipe(i915, pipe) { + min_cdclk = max(new_cdclk_state->min_cdclk[pipe], min_cdclk); + + /* Currently do this change only if we need to increase */ + if (new_bw_state->min_cdclk > min_cdclk) + *need_cdclk_calc = true; + } + + return 0; +} + int intel_cdclk_init(struct drm_i915_private *dev_priv) { struct intel_cdclk_state *cdclk_state; @@ -2587,7 +2753,7 @@ int intel_modeset_calc_cdclk(struct intel_atomic_state *state) struct intel_crtc_state *crtc_state; pipe = ilog2(new_cdclk_state->active_pipes); - crtc = intel_get_crtc_for_pipe(dev_priv, pipe); + crtc = intel_crtc_for_pipe(dev_priv, pipe); crtc_state = intel_atomic_get_crtc_state(&state->base, crtc); if (IS_ERR(crtc_state)) @@ -2597,9 +2763,14 @@ int intel_modeset_calc_cdclk(struct intel_atomic_state *state) pipe = INVALID_PIPE; } - if (intel_cdclk_can_crawl(dev_priv, - &old_cdclk_state->actual, - &new_cdclk_state->actual)) { + if (intel_cdclk_can_squash(dev_priv, + &old_cdclk_state->actual, + &new_cdclk_state->actual)) { + drm_dbg_kms(&dev_priv->drm, + "Can change cdclk via squasher\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"); } else if (pipe != INVALID_PIPE) { diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.h b/drivers/gpu/drm/i915/display/intel_cdclk.h index 309b3f394e24..fc638522e445 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.h +++ b/drivers/gpu/drm/i915/display/intel_cdclk.h @@ -16,13 +16,6 @@ struct drm_i915_private; struct intel_atomic_state; struct intel_crtc_state; -struct intel_cdclk_vals { - u32 cdclk; - u16 refclk; - u8 divider; /* CD2X divider * 2 */ - u8 ratio; -}; - struct intel_cdclk_state { struct intel_global_state base; @@ -70,7 +63,8 @@ void intel_dump_cdclk_config(const struct intel_cdclk_config *cdclk_config, int intel_modeset_calc_cdclk(struct intel_atomic_state *state); void intel_cdclk_get_cdclk(struct drm_i915_private *dev_priv, struct intel_cdclk_config *cdclk_config); -int intel_cdclk_bw_calc_min_cdclk(struct intel_atomic_state *state); +int intel_cdclk_atomic_check(struct intel_atomic_state *state, + bool *need_cdclk_calc); struct intel_cdclk_state * intel_atomic_get_cdclk_state(struct intel_atomic_state *state); diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c index 5359b7305a78..de3ded1e327a 100644 --- a/drivers/gpu/drm/i915/display/intel_color.c +++ b/drivers/gpu/drm/i915/display/intel_color.c @@ -26,7 +26,7 @@ #include "intel_de.h" #include "intel_display_types.h" #include "intel_dpll.h" -#include "intel_dsi.h" +#include "vlv_dsi_pll.h" #define CTM_COEFF_SIGN (1ULL << 63) @@ -552,8 +552,8 @@ static void i9xx_load_lut_8(struct intel_crtc *crtc, lut = blob->data; for (i = 0; i < 256; i++) - intel_de_write(dev_priv, PALETTE(pipe, i), - i9xx_lut_8(&lut[i])); + intel_de_write_fw(dev_priv, PALETTE(pipe, i), + i9xx_lut_8(&lut[i])); } static void i9xx_load_luts(const struct intel_crtc_state *crtc_state) @@ -576,15 +576,15 @@ static void i965_load_lut_10p6(struct intel_crtc *crtc, enum pipe pipe = crtc->pipe; for (i = 0; i < lut_size - 1; i++) { - intel_de_write(dev_priv, PALETTE(pipe, 2 * i + 0), - i965_lut_10p6_ldw(&lut[i])); - intel_de_write(dev_priv, PALETTE(pipe, 2 * i + 1), - i965_lut_10p6_udw(&lut[i])); + intel_de_write_fw(dev_priv, PALETTE(pipe, 2 * i + 0), + i965_lut_10p6_ldw(&lut[i])); + intel_de_write_fw(dev_priv, PALETTE(pipe, 2 * i + 1), + i965_lut_10p6_udw(&lut[i])); } - intel_de_write(dev_priv, PIPEGCMAX(pipe, 0), lut[i].red); - intel_de_write(dev_priv, PIPEGCMAX(pipe, 1), lut[i].green); - intel_de_write(dev_priv, PIPEGCMAX(pipe, 2), lut[i].blue); + intel_de_write_fw(dev_priv, PIPEGCMAX(pipe, 0), lut[i].red); + intel_de_write_fw(dev_priv, PIPEGCMAX(pipe, 1), lut[i].green); + intel_de_write_fw(dev_priv, PIPEGCMAX(pipe, 2), lut[i].blue); } static void i965_load_luts(const struct intel_crtc_state *crtc_state) @@ -618,8 +618,8 @@ static void ilk_load_lut_8(struct intel_crtc *crtc, lut = blob->data; for (i = 0; i < 256; i++) - intel_de_write(dev_priv, LGC_PALETTE(pipe, i), - i9xx_lut_8(&lut[i])); + intel_de_write_fw(dev_priv, LGC_PALETTE(pipe, i), + i9xx_lut_8(&lut[i])); } static void ilk_load_lut_10(struct intel_crtc *crtc, @@ -631,8 +631,8 @@ static void ilk_load_lut_10(struct intel_crtc *crtc, enum pipe pipe = crtc->pipe; for (i = 0; i < lut_size; i++) - intel_de_write(dev_priv, PREC_PALETTE(pipe, i), - ilk_lut_10(&lut[i])); + intel_de_write_fw(dev_priv, PREC_PALETTE(pipe, i), + ilk_lut_10(&lut[i])); } static void ilk_load_luts(const struct intel_crtc_state *crtc_state) @@ -681,16 +681,16 @@ static void ivb_load_lut_10(struct intel_crtc *crtc, const struct drm_color_lut *entry = &lut[i * (lut_size - 1) / (hw_lut_size - 1)]; - intel_de_write(dev_priv, PREC_PAL_INDEX(pipe), prec_index++); - intel_de_write(dev_priv, PREC_PAL_DATA(pipe), - ilk_lut_10(entry)); + 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)); } /* * Reset the index, otherwise it prevents the legacy palette to be * written properly. */ - intel_de_write(dev_priv, PREC_PAL_INDEX(pipe), 0); + intel_de_write_fw(dev_priv, PREC_PAL_INDEX(pipe), 0); } /* On BDW+ the index auto increment mode actually works */ @@ -704,23 +704,23 @@ static void bdw_load_lut_10(struct intel_crtc *crtc, int i, lut_size = drm_color_lut_size(blob); enum pipe pipe = crtc->pipe; - intel_de_write(dev_priv, PREC_PAL_INDEX(pipe), - prec_index | PAL_PREC_AUTO_INCREMENT); + intel_de_write_fw(dev_priv, 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(dev_priv, PREC_PAL_DATA(pipe), - ilk_lut_10(entry)); + intel_de_write_fw(dev_priv, PREC_PAL_DATA(pipe), + ilk_lut_10(entry)); } /* * Reset the index, otherwise it prevents the legacy palette to be * written properly. */ - intel_de_write(dev_priv, PREC_PAL_INDEX(pipe), 0); + intel_de_write_fw(dev_priv, PREC_PAL_INDEX(pipe), 0); } static void ivb_load_lut_ext_max(const struct intel_crtc_state *crtc_state) @@ -808,6 +808,14 @@ static void bdw_load_luts(const struct intel_crtc_state *crtc_state) } } +static int glk_degamma_lut_size(struct drm_i915_private *i915) +{ + if (DISPLAY_VER(i915) >= 13) + return 131; + else + return 35; +} + static void glk_load_degamma_lut(const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); @@ -821,14 +829,14 @@ static void glk_load_degamma_lut(const struct intel_crtc_state *crtc_state) * ignore the index bits, so we need to reset it to index 0 * separately. */ - intel_de_write(dev_priv, PRE_CSC_GAMC_INDEX(pipe), 0); - intel_de_write(dev_priv, PRE_CSC_GAMC_INDEX(pipe), - PRE_CSC_GAMC_AUTO_INCREMENT); + 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++) { /* - * First 33 entries represent range from 0 to 1.0 - * 34th and 35th entry will represent extended range + * First lut_size entries represent range from 0 to 1.0 + * 3 additional lut entries will represent extended range * inputs 3.0 and 7.0 respectively, currently clamped * at 1.0. Since the precision is 16bit, the user * value can be directly filled to register. @@ -839,15 +847,15 @@ 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(dev_priv, PRE_CSC_GAMC_DATA(pipe), - lut[i].green); + intel_de_write_fw(dev_priv, PRE_CSC_GAMC_DATA(pipe), + lut[i].green); } /* Clamp values > 1.0. */ - while (i++ < 35) - intel_de_write(dev_priv, PRE_CSC_GAMC_DATA(pipe), 1 << 16); + while (i++ < glk_degamma_lut_size(dev_priv)) + intel_de_write_fw(dev_priv, PRE_CSC_GAMC_DATA(pipe), 1 << 16); - intel_de_write(dev_priv, PRE_CSC_GAMC_INDEX(pipe), 0); + 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) @@ -862,21 +870,21 @@ static void glk_load_degamma_lut_linear(const struct intel_crtc_state *crtc_stat * ignore the index bits, so we need to reset it to index 0 * separately. */ - intel_de_write(dev_priv, PRE_CSC_GAMC_INDEX(pipe), 0); - intel_de_write(dev_priv, PRE_CSC_GAMC_INDEX(pipe), - PRE_CSC_GAMC_AUTO_INCREMENT); + 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(dev_priv, PRE_CSC_GAMC_DATA(pipe), v); + intel_de_write_fw(dev_priv, PRE_CSC_GAMC_DATA(pipe), v); } /* Clamp values > 1.0. */ while (i++ < 35) - intel_de_write(dev_priv, PRE_CSC_GAMC_DATA(pipe), 1 << 16); + intel_de_write_fw(dev_priv, PRE_CSC_GAMC_DATA(pipe), 1 << 16); - intel_de_write(dev_priv, PRE_CSC_GAMC_INDEX(pipe), 0); + intel_de_write_fw(dev_priv, PRE_CSC_GAMC_INDEX(pipe), 0); } static void glk_load_luts(const struct intel_crtc_state *crtc_state) @@ -1071,10 +1079,10 @@ static void chv_load_cgm_degamma(struct intel_crtc *crtc, enum pipe pipe = crtc->pipe; for (i = 0; i < lut_size; i++) { - intel_de_write(dev_priv, CGM_PIPE_DEGAMMA(pipe, i, 0), - chv_cgm_degamma_ldw(&lut[i])); - intel_de_write(dev_priv, CGM_PIPE_DEGAMMA(pipe, i, 1), - chv_cgm_degamma_udw(&lut[i])); + intel_de_write_fw(dev_priv, CGM_PIPE_DEGAMMA(pipe, i, 0), + chv_cgm_degamma_ldw(&lut[i])); + intel_de_write_fw(dev_priv, CGM_PIPE_DEGAMMA(pipe, i, 1), + chv_cgm_degamma_udw(&lut[i])); } } @@ -1105,10 +1113,10 @@ static void chv_load_cgm_gamma(struct intel_crtc *crtc, enum pipe pipe = crtc->pipe; for (i = 0; i < lut_size; i++) { - intel_de_write(dev_priv, CGM_PIPE_GAMMA(pipe, i, 0), - chv_cgm_gamma_ldw(&lut[i])); - intel_de_write(dev_priv, CGM_PIPE_GAMMA(pipe, i, 1), - chv_cgm_gamma_udw(&lut[i])); + intel_de_write_fw(dev_priv, CGM_PIPE_GAMMA(pipe, i, 0), + chv_cgm_gamma_ldw(&lut[i])); + intel_de_write_fw(dev_priv, CGM_PIPE_GAMMA(pipe, i, 1), + chv_cgm_gamma_udw(&lut[i])); } } @@ -1131,8 +1139,8 @@ static void chv_load_luts(const struct intel_crtc_state *crtc_state) else i965_load_luts(crtc_state); - intel_de_write(dev_priv, CGM_PIPE_MODE(crtc->pipe), - crtc_state->cgm_mode); + intel_de_write_fw(dev_priv, CGM_PIPE_MODE(crtc->pipe), + crtc_state->cgm_mode); } void intel_color_load_luts(const struct intel_crtc_state *crtc_state) @@ -1574,6 +1582,8 @@ static int glk_color_check(struct intel_crtc_state *crtc_state) static u32 icl_gamma_mode(const struct intel_crtc_state *crtc_state) { + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); u32 gamma_mode = 0; if (crtc_state->hw.degamma_lut) @@ -1586,6 +1596,13 @@ static u32 icl_gamma_mode(const struct intel_crtc_state *crtc_state) if (!crtc_state->hw.gamma_lut || crtc_state_is_legacy_gamma(crtc_state)) gamma_mode |= GAMMA_MODE_MODE_8BIT; + /* + * Enable 10bit gamma for D13 + * ToDo: Extend to Logarithmic Gamma once the new UAPI + * is acccepted and implemented by a userspace consumer + */ + else if (DISPLAY_VER(i915) >= 13) + gamma_mode |= GAMMA_MODE_MODE_10BIT; else gamma_mode |= GAMMA_MODE_MODE_12BIT_MULTI_SEGMENTED; @@ -1808,7 +1825,7 @@ static struct drm_property_blob *i9xx_read_lut_8(struct intel_crtc *crtc) lut = blob->data; for (i = 0; i < LEGACY_LUT_LENGTH; i++) { - u32 val = intel_de_read(dev_priv, PALETTE(pipe, i)); + u32 val = intel_de_read_fw(dev_priv, PALETTE(pipe, i)); i9xx_lut_8_pack(&lut[i], val); } @@ -1843,15 +1860,15 @@ static struct drm_property_blob *i965_read_lut_10p6(struct intel_crtc *crtc) lut = blob->data; for (i = 0; i < lut_size - 1; i++) { - u32 ldw = intel_de_read(dev_priv, PALETTE(pipe, 2 * i + 0)); - u32 udw = intel_de_read(dev_priv, PALETTE(pipe, 2 * i + 1)); + u32 ldw = intel_de_read_fw(dev_priv, PALETTE(pipe, 2 * i + 0)); + u32 udw = intel_de_read_fw(dev_priv, PALETTE(pipe, 2 * i + 1)); i965_lut_10p6_pack(&lut[i], ldw, udw); } - lut[i].red = i965_lut_11p6_max_pack(intel_de_read(dev_priv, PIPEGCMAX(pipe, 0))); - lut[i].green = i965_lut_11p6_max_pack(intel_de_read(dev_priv, PIPEGCMAX(pipe, 1))); - lut[i].blue = i965_lut_11p6_max_pack(intel_de_read(dev_priv, PIPEGCMAX(pipe, 2))); + lut[i].red = i965_lut_11p6_max_pack(intel_de_read_fw(dev_priv, PIPEGCMAX(pipe, 0))); + lut[i].green = i965_lut_11p6_max_pack(intel_de_read_fw(dev_priv, PIPEGCMAX(pipe, 1))); + lut[i].blue = i965_lut_11p6_max_pack(intel_de_read_fw(dev_priv, PIPEGCMAX(pipe, 2))); return blob; } @@ -1886,8 +1903,8 @@ 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(dev_priv, CGM_PIPE_GAMMA(pipe, i, 0)); - u32 udw = intel_de_read(dev_priv, CGM_PIPE_GAMMA(pipe, i, 1)); + 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)); chv_cgm_gamma_pack(&lut[i], ldw, udw); } @@ -1922,7 +1939,7 @@ 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(dev_priv, LGC_PALETTE(pipe, i)); + u32 val = intel_de_read_fw(dev_priv, LGC_PALETTE(pipe, i)); i9xx_lut_8_pack(&lut[i], val); } @@ -1947,7 +1964,7 @@ 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(dev_priv, PREC_PALETTE(pipe, i)); + u32 val = intel_de_read_fw(dev_priv, PREC_PALETTE(pipe, i)); ilk_lut_10_pack(&lut[i], val); } @@ -1999,16 +2016,16 @@ static struct drm_property_blob *bdw_read_lut_10(struct intel_crtc *crtc, lut = blob->data; - intel_de_write(dev_priv, PREC_PAL_INDEX(pipe), - prec_index | PAL_PREC_AUTO_INCREMENT); + intel_de_write_fw(dev_priv, PREC_PAL_INDEX(pipe), + prec_index | PAL_PREC_AUTO_INCREMENT); for (i = 0; i < lut_size; i++) { - u32 val = intel_de_read(dev_priv, PREC_PAL_DATA(pipe)); + u32 val = intel_de_read_fw(dev_priv, PREC_PAL_DATA(pipe)); ilk_lut_10_pack(&lut[i], val); } - intel_de_write(dev_priv, PREC_PAL_INDEX(pipe), 0); + intel_de_write_fw(dev_priv, PREC_PAL_INDEX(pipe), 0); return blob; } @@ -2050,17 +2067,17 @@ icl_read_lut_multi_segment(struct intel_crtc *crtc) lut = blob->data; - intel_de_write(dev_priv, PREC_PAL_MULTI_SEG_INDEX(pipe), - PAL_PREC_AUTO_INCREMENT); + intel_de_write_fw(dev_priv, PREC_PAL_MULTI_SEG_INDEX(pipe), + PAL_PREC_AUTO_INCREMENT); for (i = 0; i < 9; i++) { - u32 ldw = intel_de_read(dev_priv, PREC_PAL_MULTI_SEG_DATA(pipe)); - u32 udw = intel_de_read(dev_priv, PREC_PAL_MULTI_SEG_DATA(pipe)); + 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)); icl_lut_multi_seg_pack(&lut[i], ldw, udw); } - intel_de_write(dev_priv, PREC_PAL_MULTI_SEG_INDEX(pipe), 0); + intel_de_write_fw(dev_priv, PREC_PAL_MULTI_SEG_INDEX(pipe), 0); /* * FIXME readouts from PAL_PREC_DATA register aren't giving diff --git a/drivers/gpu/drm/i915/display/intel_combo_phy.c b/drivers/gpu/drm/i915/display/intel_combo_phy.c index 634e8d449457..f628e0542933 100644 --- a/drivers/gpu/drm/i915/display/intel_combo_phy.c +++ b/drivers/gpu/drm/i915/display/intel_combo_phy.c @@ -301,7 +301,7 @@ void intel_combo_phy_power_up_lanes(struct drm_i915_private *dev_priv, val = intel_de_read(dev_priv, ICL_PORT_CL_DW10(phy)); val &= ~PWR_DOWN_LN_MASK; - val |= lane_mask << PWR_DOWN_LN_SHIFT; + val |= lane_mask; intel_de_write(dev_priv, ICL_PORT_CL_DW10(phy), val); } diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c index 1c161eeed82f..6a3893c8ff22 100644 --- a/drivers/gpu/drm/i915/display/intel_crt.c +++ b/drivers/gpu/drm/i915/display/intel_crt.c @@ -45,6 +45,7 @@ #include "intel_fifo_underrun.h" #include "intel_gmbus.h" #include "intel_hotplug.h" +#include "intel_pch_display.h" /* Here's the desired hotplug mode */ #define ADPA_HOTPLUG_BITS (ADPA_CRT_HOTPLUG_PERIOD_128 | \ @@ -143,7 +144,7 @@ static void intel_crt_get_config(struct intel_encoder *encoder, static void hsw_crt_get_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + lpt_pch_get_config(pipe_config); hsw_ddi_get_config(encoder, pipe_config); @@ -152,8 +153,6 @@ static void hsw_crt_get_config(struct intel_encoder *encoder, DRM_MODE_FLAG_PVSYNC | DRM_MODE_FLAG_NVSYNC); pipe_config->hw.adjusted_mode.flags |= intel_crt_get_flags(encoder); - - pipe_config->hw.adjusted_mode.crtc_clock = lpt_get_iclkip(dev_priv); } /* Note: The caller is required to filter out dpms modes not supported by the @@ -247,6 +246,7 @@ static void hsw_post_disable_crt(struct intel_atomic_state *state, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { + struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); intel_crtc_vblank_off(old_crtc_state); @@ -261,10 +261,9 @@ static void hsw_post_disable_crt(struct intel_atomic_state *state, pch_post_disable_crt(state, encoder, old_crtc_state, old_conn_state); - lpt_disable_pch_transcoder(dev_priv); - lpt_disable_iclkip(dev_priv); + lpt_pch_disable(state, crtc); - intel_ddi_fdi_post_disable(state, encoder, old_crtc_state, old_conn_state); + hsw_fdi_disable(encoder); drm_WARN_ON(&dev_priv->drm, !old_crtc_state->has_pch_encoder); @@ -316,14 +315,14 @@ static void hsw_enable_crt(struct intel_atomic_state *state, intel_enable_transcoder(crtc_state); - lpt_pch_enable(crtc_state); + lpt_pch_enable(state, crtc); intel_crtc_vblank_on(crtc_state); intel_crt_set_dpms(encoder, crtc_state, DRM_MODE_DPMS_ON); - intel_wait_for_vblank(dev_priv, pipe); - intel_wait_for_vblank(dev_priv, pipe); + intel_crtc_wait_for_next_vblank(crtc); + intel_crtc_wait_for_next_vblank(crtc); intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, true); intel_set_pch_fifo_underrun_reporting(dev_priv, PIPE_A, true); } @@ -722,7 +721,7 @@ intel_crt_load_detect(struct intel_crt *crt, u32 pipe) intel_uncore_posting_read(uncore, pipeconf_reg); /* Wait for next Vblank to substitue * border color for Color info */ - intel_wait_for_vblank(dev_priv, pipe); + intel_crtc_wait_for_next_vblank(intel_crtc_for_pipe(dev_priv, pipe)); st00 = intel_uncore_read8(uncore, _VGA_MSR_WRITE); status = ((st00 & (1 << 4)) != 0) ? connector_status_connected : diff --git a/drivers/gpu/drm/i915/display/intel_crtc.c b/drivers/gpu/drm/i915/display/intel_crtc.c index 254e67141a77..16c3ca66d9f0 100644 --- a/drivers/gpu/drm/i915/display/intel_crtc.c +++ b/drivers/gpu/drm/i915/display/intel_crtc.c @@ -3,29 +3,31 @@ * Copyright © 2020 Intel Corporation */ #include <linux/kernel.h> +#include <linux/pm_qos.h> #include <linux/slab.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_fourcc.h> #include <drm/drm_plane.h> #include <drm/drm_plane_helper.h> +#include <drm/drm_vblank_work.h> -#include "i915_trace.h" #include "i915_vgpu.h" - +#include "i9xx_plane.h" +#include "icl_dsi.h" #include "intel_atomic.h" #include "intel_atomic_plane.h" #include "intel_color.h" #include "intel_crtc.h" #include "intel_cursor.h" #include "intel_display_debugfs.h" +#include "intel_display_trace.h" #include "intel_display_types.h" #include "intel_dsi.h" #include "intel_pipe_crc.h" #include "intel_psr.h" #include "intel_sprite.h" #include "intel_vrr.h" -#include "i9xx_plane.h" #include "skl_universal_plane.h" static void assert_vblank_disabled(struct drm_crtc *crtc) @@ -34,6 +36,38 @@ static void assert_vblank_disabled(struct drm_crtc *crtc) drm_crtc_vblank_put(crtc); } +struct intel_crtc *intel_first_crtc(struct drm_i915_private *i915) +{ + return to_intel_crtc(drm_crtc_from_index(&i915->drm, 0)); +} + +struct intel_crtc *intel_crtc_for_pipe(struct drm_i915_private *i915, + enum pipe pipe) +{ + struct intel_crtc *crtc; + + for_each_intel_crtc(&i915->drm, crtc) { + if (crtc->pipe == pipe) + return crtc; + } + + return NULL; +} + +void intel_crtc_wait_for_next_vblank(struct intel_crtc *crtc) +{ + drm_crtc_wait_one_vblank(&crtc->base); +} + +void intel_wait_for_vblank_if_active(struct drm_i915_private *i915, + enum pipe pipe) +{ + struct intel_crtc *crtc = intel_crtc_for_pipe(i915, pipe); + + if (crtc->active) + intel_crtc_wait_for_next_vblank(crtc); +} + u32 intel_crtc_get_vblank_counter(struct intel_crtc *crtc) { struct drm_device *dev = crtc->base.dev; @@ -167,6 +201,8 @@ static void intel_crtc_destroy(struct drm_crtc *_crtc) { struct intel_crtc *crtc = to_intel_crtc(_crtc); + cpu_latency_qos_remove_request(&crtc->vblank_pm_qos); + drm_crtc_cleanup(&crtc->base); kfree(crtc); } @@ -323,18 +359,6 @@ int intel_crtc_init(struct drm_i915_private *dev_priv, enum pipe pipe) if (ret) goto fail; - BUG_ON(pipe >= ARRAY_SIZE(dev_priv->pipe_to_crtc_mapping) || - dev_priv->pipe_to_crtc_mapping[pipe] != NULL); - dev_priv->pipe_to_crtc_mapping[pipe] = crtc; - - if (DISPLAY_VER(dev_priv) < 9) { - enum i9xx_plane_id i9xx_plane = primary->i9xx_plane; - - BUG_ON(i9xx_plane >= ARRAY_SIZE(dev_priv->plane_to_crtc_mapping) || - dev_priv->plane_to_crtc_mapping[i9xx_plane] != NULL); - dev_priv->plane_to_crtc_mapping[i9xx_plane] = crtc; - } - if (DISPLAY_VER(dev_priv) >= 11) drm_crtc_create_scaling_filter_property(&crtc->base, BIT(DRM_SCALING_FILTER_DEFAULT) | @@ -344,6 +368,8 @@ int intel_crtc_init(struct drm_i915_private *dev_priv, enum pipe pipe) intel_crtc_crc_init(crtc); + cpu_latency_qos_add_request(&crtc->vblank_pm_qos, PM_QOS_DEFAULT_VALUE); + drm_WARN_ON(&dev_priv->drm, drm_crtc_index(&crtc->base) != crtc->pipe); return 0; @@ -354,6 +380,65 @@ fail: return ret; } +static bool intel_crtc_needs_vblank_work(const struct intel_crtc_state *crtc_state) +{ + 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); +} + +static void intel_crtc_vblank_work(struct kthread_work *base) +{ + struct drm_vblank_work *work = to_drm_vblank_work(base); + struct intel_crtc_state *crtc_state = + container_of(work, typeof(*crtc_state), vblank_work); + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + + trace_intel_crtc_vblank_work_start(crtc); + + intel_color_load_luts(crtc_state); + + if (crtc_state->uapi.event) { + spin_lock_irq(&crtc->base.dev->event_lock); + drm_crtc_send_vblank_event(&crtc->base, crtc_state->uapi.event); + crtc_state->uapi.event = NULL; + spin_unlock_irq(&crtc->base.dev->event_lock); + } + + trace_intel_crtc_vblank_work_end(crtc); +} + +static void intel_crtc_vblank_work_init(struct intel_crtc_state *crtc_state) +{ + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + + drm_vblank_work_init(&crtc_state->vblank_work, &crtc->base, + intel_crtc_vblank_work); + /* + * Interrupt latency is critical for getting the vblank + * work executed as early as possible during the vblank. + */ + cpu_latency_qos_update_request(&crtc->vblank_pm_qos, 0); +} + +void intel_wait_for_vblank_workers(struct intel_atomic_state *state) +{ + struct intel_crtc_state *crtc_state; + struct intel_crtc *crtc; + int i; + + for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) { + if (!intel_crtc_needs_vblank_work(crtc_state)) + continue; + + drm_vblank_work_flush(&crtc_state->vblank_work); + cpu_latency_qos_update_request(&crtc->vblank_pm_qos, + PM_QOS_DEFAULT_VALUE); + } +} + int intel_usecs_to_scanlines(const struct drm_display_mode *adjusted_mode, int usecs) { @@ -387,7 +472,7 @@ static int intel_mode_vblank_start(const struct drm_display_mode *mode) * until a subsequent call to intel_pipe_update_end(). That is done to * avoid random delays. */ -void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state) +void intel_pipe_update_start(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); @@ -402,10 +487,17 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state) if (new_crtc_state->uapi.async_flip) return; - if (new_crtc_state->vrr.enable) - vblank_start = intel_vrr_vmax_vblank_start(new_crtc_state); - else + if (intel_crtc_needs_vblank_work(new_crtc_state)) + intel_crtc_vblank_work_init(new_crtc_state); + + if (new_crtc_state->vrr.enable) { + if (intel_vrr_is_push_sent(new_crtc_state)) + vblank_start = intel_vrr_vmin_vblank_start(new_crtc_state); + else + vblank_start = intel_vrr_vmax_vblank_start(new_crtc_state); + } else { vblank_start = intel_mode_vblank_start(adjusted_mode); + } /* FIXME needs to be calibrated sensibly */ min = vblank_start - intel_usecs_to_scanlines(adjusted_mode, @@ -554,7 +646,11 @@ void intel_pipe_update_end(struct intel_crtc_state *new_crtc_state) * Would be slightly nice to just grab the vblank count and arm the * event outside of the critical section - the spinlock might spin for a * while ... */ - if (new_crtc_state->uapi.event) { + if (intel_crtc_needs_vblank_work(new_crtc_state)) { + drm_vblank_work_schedule(&new_crtc_state->vblank_work, + drm_crtc_accurate_vblank_count(&crtc->base) + 1, + false); + } else if (new_crtc_state->uapi.event) { drm_WARN_ON(&dev_priv->drm, drm_crtc_vblank_get(&crtc->base) != 0); @@ -566,11 +662,24 @@ void intel_pipe_update_end(struct intel_crtc_state *new_crtc_state) new_crtc_state->uapi.event = NULL; } - local_irq_enable(); - - /* Send VRR Push to terminate Vblank */ + /* + * Send VRR Push to terminate Vblank. If we are already in vblank + * this has to be done _after_ sampling the frame counter, as + * otherwise the push would immediately terminate the vblank and + * the sampled frame counter would correspond to the next frame + * instead of the current frame. + * + * There is a tiny race here (iff vblank evasion failed us) where + * we might sample the frame counter just before vmax vblank start + * but the push would be sent just after it. That would cause the + * push to affect the next frame instead of the current frame, + * which would cause the next frame to terminate already at vmin + * vblank start instead of vmax vblank start. + */ intel_vrr_send_push(new_crtc_state); + local_irq_enable(); + if (intel_vgpu_active(dev_priv)) return; diff --git a/drivers/gpu/drm/i915/display/intel_crtc.h b/drivers/gpu/drm/i915/display/intel_crtc.h index a5ae997581aa..73077137fb99 100644 --- a/drivers/gpu/drm/i915/display/intel_crtc.h +++ b/drivers/gpu/drm/i915/display/intel_crtc.h @@ -8,11 +8,16 @@ #include <linux/types.h> +enum i9xx_plane_id; enum pipe; +struct drm_display_mode; struct drm_i915_private; +struct intel_atomic_state; struct intel_crtc; struct intel_crtc_state; +int intel_usecs_to_scanlines(const struct drm_display_mode *adjusted_mode, + int usecs); u32 intel_crtc_max_vblank_count(const struct intel_crtc_state *crtc_state); int intel_crtc_init(struct drm_i915_private *dev_priv, enum pipe pipe); struct intel_crtc_state *intel_crtc_state_alloc(struct intel_crtc *crtc); @@ -21,5 +26,14 @@ void intel_crtc_state_reset(struct intel_crtc_state *crtc_state, u32 intel_crtc_get_vblank_counter(struct intel_crtc *crtc); void intel_crtc_vblank_on(const struct intel_crtc_state *crtc_state); void intel_crtc_vblank_off(const struct intel_crtc_state *crtc_state); +void intel_pipe_update_start(struct intel_crtc_state *new_crtc_state); +void intel_pipe_update_end(struct intel_crtc_state *new_crtc_state); +void intel_wait_for_vblank_workers(struct intel_atomic_state *state); +struct intel_crtc *intel_first_crtc(struct drm_i915_private *i915); +struct intel_crtc *intel_crtc_for_pipe(struct drm_i915_private *i915, + enum pipe pipe); +void intel_wait_for_vblank_if_active(struct drm_i915_private *i915, + enum pipe pipe); +void intel_crtc_wait_for_next_vblank(struct intel_crtc *crtc); #endif diff --git a/drivers/gpu/drm/i915/display/intel_cursor.c b/drivers/gpu/drm/i915/display/intel_cursor.c index 11842f212613..16d34685d83f 100644 --- a/drivers/gpu/drm/i915/display/intel_cursor.c +++ b/drivers/gpu/drm/i915/display/intel_cursor.c @@ -28,11 +28,6 @@ static const u32 intel_cursor_formats[] = { DRM_FORMAT_ARGB8888, }; -static const u64 cursor_format_modifiers[] = { - DRM_FORMAT_MOD_LINEAR, - DRM_FORMAT_MOD_INVALID -}; - static u32 intel_cursor_base(const struct intel_plane_state *plane_state) { struct drm_i915_private *dev_priv = @@ -195,7 +190,7 @@ static u32 i845_cursor_ctl(const struct intel_crtc_state *crtc_state, { return CURSOR_ENABLE | CURSOR_FORMAT_ARGB | - CURSOR_STRIDE(plane_state->view.color_plane[0].stride); + CURSOR_STRIDE(plane_state->view.color_plane[0].mapping_stride); } static bool i845_cursor_size_ok(const struct intel_plane_state *plane_state) @@ -234,7 +229,7 @@ static int i845_check_cursor(struct intel_crtc_state *crtc_state, } drm_WARN_ON(&i915->drm, plane_state->uapi.visible && - plane_state->view.color_plane[0].stride != fb->pitches[0]); + plane_state->view.color_plane[0].mapping_stride != fb->pitches[0]); switch (fb->pitches[0]) { case 256: @@ -253,9 +248,10 @@ static int i845_check_cursor(struct intel_crtc_state *crtc_state, return 0; } -static void i845_update_cursor(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state, - const struct intel_plane_state *plane_state) +/* TODO: split into noarm+arm pair */ +static void i845_cursor_update_arm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); u32 cntl = 0, base = 0, pos = 0, size = 0; @@ -298,10 +294,10 @@ static void i845_update_cursor(struct intel_plane *plane, spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); } -static void i845_disable_cursor(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state) +static void i845_cursor_disable_arm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state) { - i845_update_cursor(plane, crtc_state, NULL); + i845_cursor_update_arm(plane, crtc_state, NULL); } static bool i845_cursor_get_hw_state(struct intel_plane *plane, @@ -455,7 +451,7 @@ static int i9xx_check_cursor(struct intel_crtc_state *crtc_state, } drm_WARN_ON(&dev_priv->drm, plane_state->uapi.visible && - plane_state->view.color_plane[0].stride != fb->pitches[0]); + plane_state->view.color_plane[0].mapping_stride != fb->pitches[0]); if (fb->pitches[0] != drm_rect_width(&plane_state->uapi.dst) * fb->format->cpp[0]) { @@ -488,9 +484,10 @@ static int i9xx_check_cursor(struct intel_crtc_state *crtc_state, return 0; } -static void i9xx_update_cursor(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state, - const struct intel_plane_state *plane_state) +/* TODO: split into noarm+arm pair */ +static void i9xx_cursor_update_arm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum pipe pipe = plane->pipe; @@ -562,10 +559,10 @@ static void i9xx_update_cursor(struct intel_plane *plane, spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); } -static void i9xx_disable_cursor(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state) +static void i9xx_cursor_disable_arm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state) { - i9xx_update_cursor(plane, crtc_state, NULL); + i9xx_cursor_update_arm(plane, crtc_state, NULL); } static bool i9xx_cursor_get_hw_state(struct intel_plane *plane, @@ -605,8 +602,10 @@ static bool i9xx_cursor_get_hw_state(struct intel_plane *plane, static bool intel_cursor_format_mod_supported(struct drm_plane *_plane, u32 format, u64 modifier) { - return modifier == DRM_FORMAT_MOD_LINEAR && - format == DRM_FORMAT_ARGB8888; + if (!intel_fb_plane_supports_modifier(to_intel_plane(_plane), modifier)) + return false; + + return format == DRM_FORMAT_ARGB8888; } static int @@ -717,10 +716,12 @@ intel_legacy_cursor_update(struct drm_plane *_plane, */ crtc_state->active_planes = new_crtc_state->active_planes; - if (new_plane_state->uapi.visible) - intel_update_plane(plane, crtc_state, new_plane_state); - else - intel_disable_plane(plane, crtc_state); + if (new_plane_state->uapi.visible) { + intel_plane_update_noarm(plane, crtc_state, new_plane_state); + intel_plane_update_arm(plane, crtc_state, new_plane_state); + } else { + intel_plane_disable_arm(plane, crtc_state); + } intel_plane_unpin_fb(old_plane_state); @@ -754,6 +755,7 @@ intel_cursor_plane_create(struct drm_i915_private *dev_priv, { struct intel_plane *cursor; int ret, zpos; + u64 *modifiers; cursor = intel_plane_alloc(); if (IS_ERR(cursor)) @@ -766,14 +768,14 @@ intel_cursor_plane_create(struct drm_i915_private *dev_priv, if (IS_I845G(dev_priv) || IS_I865G(dev_priv)) { cursor->max_stride = i845_cursor_max_stride; - cursor->update_plane = i845_update_cursor; - cursor->disable_plane = i845_disable_cursor; + cursor->update_arm = i845_cursor_update_arm; + cursor->disable_arm = i845_cursor_disable_arm; cursor->get_hw_state = i845_cursor_get_hw_state; cursor->check_plane = i845_check_cursor; } else { cursor->max_stride = i9xx_cursor_max_stride; - cursor->update_plane = i9xx_update_cursor; - cursor->disable_plane = i9xx_disable_cursor; + cursor->update_arm = i9xx_cursor_update_arm; + cursor->disable_arm = i9xx_cursor_disable_arm; cursor->get_hw_state = i9xx_cursor_get_hw_state; cursor->check_plane = i9xx_check_cursor; } @@ -784,13 +786,18 @@ intel_cursor_plane_create(struct drm_i915_private *dev_priv, if (IS_I845G(dev_priv) || IS_I865G(dev_priv) || HAS_CUR_FBC(dev_priv)) cursor->cursor.size = ~0; + modifiers = intel_fb_plane_get_modifiers(dev_priv, INTEL_PLANE_CAP_NONE); + ret = drm_universal_plane_init(&dev_priv->drm, &cursor->base, 0, &intel_cursor_plane_funcs, intel_cursor_formats, ARRAY_SIZE(intel_cursor_formats), - cursor_format_modifiers, + modifiers, DRM_PLANE_TYPE_CURSOR, "cursor %c", pipe_name(pipe)); + + kfree(modifiers); + if (ret) goto fail; diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index cfb567df71b3..9c9d574f0b8c 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -25,6 +25,7 @@ * */ +#include <drm/drm_privacy_screen_consumer.h> #include <drm/drm_scdc_helper.h> #include "i915_drv.h" @@ -321,10 +322,11 @@ static void ddi_dotclock_get(struct intel_crtc_state *pipe_config) { int dotclock; + /* CRT dotclock is determined via other means */ if (pipe_config->has_pch_encoder) - dotclock = intel_dotclock_calculate(pipe_config->port_clock, - &pipe_config->fdi_m_n); - else if (intel_crtc_has_dp_encoder(pipe_config)) + return; + + if (intel_crtc_has_dp_encoder(pipe_config)) dotclock = intel_dotclock_calculate(pipe_config->port_clock, &pipe_config->dp_m_n); else if (pipe_config->has_hdmi_sink && pipe_config->pipe_bpp > 24) @@ -1039,7 +1041,6 @@ static void icl_ddi_combo_vswing_program(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - int level = intel_ddi_level(encoder, crtc_state, 0); const struct intel_ddi_buf_trans *trans; enum phy phy = intel_port_to_phy(dev_priv, encoder->port); int n_entries, ln; @@ -1068,32 +1069,36 @@ static void icl_ddi_combo_vswing_program(struct intel_encoder *encoder, intel_de_write(dev_priv, ICL_PORT_TX_DW5_GRP(phy), val); /* Program PORT_TX_DW2 */ - val = intel_de_read(dev_priv, ICL_PORT_TX_DW2_LN(0, phy)); - val &= ~(SWING_SEL_LOWER_MASK | SWING_SEL_UPPER_MASK | - RCOMP_SCALAR_MASK); - val |= SWING_SEL_UPPER(trans->entries[level].icl.dw2_swing_sel); - val |= SWING_SEL_LOWER(trans->entries[level].icl.dw2_swing_sel); - /* Program Rcomp scalar for every table entry */ - val |= RCOMP_SCALAR(0x98); - intel_de_write(dev_priv, ICL_PORT_TX_DW2_GRP(phy), val); + for (ln = 0; ln < 4; ln++) { + int level = intel_ddi_level(encoder, crtc_state, ln); + + intel_de_rmw(dev_priv, ICL_PORT_TX_DW2_LN(ln, phy), + SWING_SEL_UPPER_MASK | SWING_SEL_LOWER_MASK | RCOMP_SCALAR_MASK, + SWING_SEL_UPPER(trans->entries[level].icl.dw2_swing_sel) | + SWING_SEL_LOWER(trans->entries[level].icl.dw2_swing_sel) | + RCOMP_SCALAR(0x98)); + } /* Program PORT_TX_DW4 */ /* We cannot write to GRP. It would overwrite individual loadgen. */ for (ln = 0; ln < 4; ln++) { - val = intel_de_read(dev_priv, ICL_PORT_TX_DW4_LN(ln, phy)); - val &= ~(POST_CURSOR_1_MASK | POST_CURSOR_2_MASK | - CURSOR_COEFF_MASK); - val |= POST_CURSOR_1(trans->entries[level].icl.dw4_post_cursor_1); - val |= POST_CURSOR_2(trans->entries[level].icl.dw4_post_cursor_2); - val |= CURSOR_COEFF(trans->entries[level].icl.dw4_cursor_coeff); - intel_de_write(dev_priv, ICL_PORT_TX_DW4_LN(ln, phy), val); + int level = intel_ddi_level(encoder, crtc_state, ln); + + intel_de_rmw(dev_priv, ICL_PORT_TX_DW4_LN(ln, phy), + POST_CURSOR_1_MASK | POST_CURSOR_2_MASK | CURSOR_COEFF_MASK, + POST_CURSOR_1(trans->entries[level].icl.dw4_post_cursor_1) | + POST_CURSOR_2(trans->entries[level].icl.dw4_post_cursor_2) | + CURSOR_COEFF(trans->entries[level].icl.dw4_cursor_coeff)); } /* Program PORT_TX_DW7 */ - val = intel_de_read(dev_priv, ICL_PORT_TX_DW7_LN(0, phy)); - val &= ~N_SCALAR_MASK; - val |= N_SCALAR(trans->entries[level].icl.dw7_n_scalar); - intel_de_write(dev_priv, ICL_PORT_TX_DW7_GRP(phy), val); + for (ln = 0; ln < 4; ln++) { + int level = intel_ddi_level(encoder, crtc_state, ln); + + intel_de_rmw(dev_priv, ICL_PORT_TX_DW7_LN(ln, phy), + N_SCALAR_MASK, + N_SCALAR(trans->entries[level].icl.dw7_n_scalar)); + } } static void icl_combo_phy_set_signal_levels(struct intel_encoder *encoder, @@ -1124,16 +1129,14 @@ static void icl_combo_phy_set_signal_levels(struct intel_encoder *encoder, * > 6 GHz (LN0=0, LN1=0, LN2=0, LN3=0) */ for (ln = 0; ln < 4; ln++) { - val = intel_de_read(dev_priv, ICL_PORT_TX_DW4_LN(ln, phy)); - val &= ~LOADGEN_SELECT; - val |= icl_combo_phy_loadgen_select(crtc_state, ln); - intel_de_write(dev_priv, ICL_PORT_TX_DW4_LN(ln, phy), val); + intel_de_rmw(dev_priv, ICL_PORT_TX_DW4_LN(ln, phy), + LOADGEN_SELECT, + icl_combo_phy_loadgen_select(crtc_state, ln)); } /* 3. Set PORT_CL_DW5 SUS Clock Config to 11b */ - val = intel_de_read(dev_priv, ICL_PORT_CL_DW5(phy)); - val |= SUS_CLOCK_CONFIG; - intel_de_write(dev_priv, ICL_PORT_CL_DW5(phy), val); + intel_de_rmw(dev_priv, ICL_PORT_CL_DW5(phy), + 0, SUS_CLOCK_CONFIG); /* 4. Clear training enable to change swing values */ val = intel_de_read(dev_priv, ICL_PORT_TX_DW5_LN(0, phy)); @@ -1154,10 +1157,8 @@ static void icl_mg_phy_set_signal_levels(struct intel_encoder *encoder, { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); enum tc_port tc_port = intel_port_to_tc(dev_priv, encoder->port); - int level = intel_ddi_level(encoder, crtc_state, 0); const struct intel_ddi_buf_trans *trans; int n_entries, ln; - u32 val; if (intel_tc_port_in_tbt_alt_mode(enc_to_dig_port(encoder))) return; @@ -1166,53 +1167,51 @@ static void icl_mg_phy_set_signal_levels(struct intel_encoder *encoder, if (drm_WARN_ON_ONCE(&dev_priv->drm, !trans)) return; - /* Set MG_TX_LINK_PARAMS cri_use_fs32 to 0. */ for (ln = 0; ln < 2; ln++) { - val = intel_de_read(dev_priv, MG_TX1_LINK_PARAMS(ln, tc_port)); - val &= ~CRI_USE_FS32; - intel_de_write(dev_priv, MG_TX1_LINK_PARAMS(ln, tc_port), val); - - val = intel_de_read(dev_priv, MG_TX2_LINK_PARAMS(ln, tc_port)); - val &= ~CRI_USE_FS32; - intel_de_write(dev_priv, MG_TX2_LINK_PARAMS(ln, tc_port), val); + intel_de_rmw(dev_priv, MG_TX1_LINK_PARAMS(ln, tc_port), + CRI_USE_FS32, 0); + intel_de_rmw(dev_priv, MG_TX2_LINK_PARAMS(ln, tc_port), + CRI_USE_FS32, 0); } /* Program MG_TX_SWINGCTRL with values from vswing table */ for (ln = 0; ln < 2; ln++) { - val = intel_de_read(dev_priv, MG_TX1_SWINGCTRL(ln, tc_port)); - val &= ~CRI_TXDEEMPH_OVERRIDE_17_12_MASK; - val |= CRI_TXDEEMPH_OVERRIDE_17_12( - trans->entries[level].mg.cri_txdeemph_override_17_12); - intel_de_write(dev_priv, MG_TX1_SWINGCTRL(ln, tc_port), val); - - val = intel_de_read(dev_priv, MG_TX2_SWINGCTRL(ln, tc_port)); - val &= ~CRI_TXDEEMPH_OVERRIDE_17_12_MASK; - val |= CRI_TXDEEMPH_OVERRIDE_17_12( - trans->entries[level].mg.cri_txdeemph_override_17_12); - intel_de_write(dev_priv, MG_TX2_SWINGCTRL(ln, tc_port), val); + int level; + + level = intel_ddi_level(encoder, crtc_state, 2*ln+0); + + intel_de_rmw(dev_priv, MG_TX1_SWINGCTRL(ln, tc_port), + CRI_TXDEEMPH_OVERRIDE_17_12_MASK, + CRI_TXDEEMPH_OVERRIDE_17_12(trans->entries[level].mg.cri_txdeemph_override_17_12)); + + level = intel_ddi_level(encoder, crtc_state, 2*ln+1); + + intel_de_rmw(dev_priv, MG_TX2_SWINGCTRL(ln, tc_port), + CRI_TXDEEMPH_OVERRIDE_17_12_MASK, + CRI_TXDEEMPH_OVERRIDE_17_12(trans->entries[level].mg.cri_txdeemph_override_17_12)); } /* Program MG_TX_DRVCTRL with values from vswing table */ for (ln = 0; ln < 2; ln++) { - val = intel_de_read(dev_priv, MG_TX1_DRVCTRL(ln, tc_port)); - val &= ~(CRI_TXDEEMPH_OVERRIDE_11_6_MASK | - CRI_TXDEEMPH_OVERRIDE_5_0_MASK); - val |= CRI_TXDEEMPH_OVERRIDE_5_0( - trans->entries[level].mg.cri_txdeemph_override_5_0) | - CRI_TXDEEMPH_OVERRIDE_11_6( - trans->entries[level].mg.cri_txdeemph_override_11_6) | - CRI_TXDEEMPH_OVERRIDE_EN; - intel_de_write(dev_priv, MG_TX1_DRVCTRL(ln, tc_port), val); - - val = intel_de_read(dev_priv, MG_TX2_DRVCTRL(ln, tc_port)); - val &= ~(CRI_TXDEEMPH_OVERRIDE_11_6_MASK | - CRI_TXDEEMPH_OVERRIDE_5_0_MASK); - val |= CRI_TXDEEMPH_OVERRIDE_5_0( - trans->entries[level].mg.cri_txdeemph_override_5_0) | - CRI_TXDEEMPH_OVERRIDE_11_6( - trans->entries[level].mg.cri_txdeemph_override_11_6) | - CRI_TXDEEMPH_OVERRIDE_EN; - intel_de_write(dev_priv, MG_TX2_DRVCTRL(ln, tc_port), val); + int level; + + level = intel_ddi_level(encoder, crtc_state, 2*ln+0); + + intel_de_rmw(dev_priv, MG_TX1_DRVCTRL(ln, tc_port), + CRI_TXDEEMPH_OVERRIDE_11_6_MASK | + CRI_TXDEEMPH_OVERRIDE_5_0_MASK, + CRI_TXDEEMPH_OVERRIDE_11_6(trans->entries[level].mg.cri_txdeemph_override_11_6) | + CRI_TXDEEMPH_OVERRIDE_5_0(trans->entries[level].mg.cri_txdeemph_override_5_0) | + CRI_TXDEEMPH_OVERRIDE_EN); + + level = intel_ddi_level(encoder, crtc_state, 2*ln+1); + + intel_de_rmw(dev_priv, MG_TX2_DRVCTRL(ln, tc_port), + CRI_TXDEEMPH_OVERRIDE_11_6_MASK | + CRI_TXDEEMPH_OVERRIDE_5_0_MASK, + CRI_TXDEEMPH_OVERRIDE_11_6(trans->entries[level].mg.cri_txdeemph_override_11_6) | + CRI_TXDEEMPH_OVERRIDE_5_0(trans->entries[level].mg.cri_txdeemph_override_5_0) | + CRI_TXDEEMPH_OVERRIDE_EN); /* FIXME: Program CRI_LOADGEN_SEL after the spec is updated */ } @@ -1223,50 +1222,34 @@ static void icl_mg_phy_set_signal_levels(struct intel_encoder *encoder, * values from table for which TX1 and TX2 enabled. */ for (ln = 0; ln < 2; ln++) { - val = intel_de_read(dev_priv, MG_CLKHUB(ln, tc_port)); - if (crtc_state->port_clock < 300000) - val |= CFG_LOW_RATE_LKREN_EN; - else - val &= ~CFG_LOW_RATE_LKREN_EN; - intel_de_write(dev_priv, MG_CLKHUB(ln, tc_port), val); + intel_de_rmw(dev_priv, MG_CLKHUB(ln, tc_port), + CFG_LOW_RATE_LKREN_EN, + crtc_state->port_clock < 300000 ? CFG_LOW_RATE_LKREN_EN : 0); } /* Program the MG_TX_DCC<LN, port being used> based on the link frequency */ for (ln = 0; ln < 2; ln++) { - val = intel_de_read(dev_priv, MG_TX1_DCC(ln, tc_port)); - val &= ~CFG_AMI_CK_DIV_OVERRIDE_VAL_MASK; - if (crtc_state->port_clock <= 500000) { - val &= ~CFG_AMI_CK_DIV_OVERRIDE_EN; - } else { - val |= CFG_AMI_CK_DIV_OVERRIDE_EN | - CFG_AMI_CK_DIV_OVERRIDE_VAL(1); - } - intel_de_write(dev_priv, MG_TX1_DCC(ln, tc_port), val); - - val = intel_de_read(dev_priv, MG_TX2_DCC(ln, tc_port)); - val &= ~CFG_AMI_CK_DIV_OVERRIDE_VAL_MASK; - if (crtc_state->port_clock <= 500000) { - val &= ~CFG_AMI_CK_DIV_OVERRIDE_EN; - } else { - val |= CFG_AMI_CK_DIV_OVERRIDE_EN | - CFG_AMI_CK_DIV_OVERRIDE_VAL(1); - } - intel_de_write(dev_priv, MG_TX2_DCC(ln, tc_port), val); + intel_de_rmw(dev_priv, MG_TX1_DCC(ln, tc_port), + CFG_AMI_CK_DIV_OVERRIDE_VAL_MASK | + CFG_AMI_CK_DIV_OVERRIDE_EN, + crtc_state->port_clock > 500000 ? + CFG_AMI_CK_DIV_OVERRIDE_VAL(1) | + CFG_AMI_CK_DIV_OVERRIDE_EN : 0); + + intel_de_rmw(dev_priv, MG_TX2_DCC(ln, tc_port), + CFG_AMI_CK_DIV_OVERRIDE_VAL_MASK | + CFG_AMI_CK_DIV_OVERRIDE_EN, + crtc_state->port_clock > 500000 ? + CFG_AMI_CK_DIV_OVERRIDE_VAL(1) | + CFG_AMI_CK_DIV_OVERRIDE_EN : 0); } /* Program MG_TX_PISO_READLOAD with values from vswing table */ for (ln = 0; ln < 2; ln++) { - val = intel_de_read(dev_priv, - MG_TX1_PISO_READLOAD(ln, tc_port)); - val |= CRI_CALCINIT; - intel_de_write(dev_priv, MG_TX1_PISO_READLOAD(ln, tc_port), - val); - - val = intel_de_read(dev_priv, - MG_TX2_PISO_READLOAD(ln, tc_port)); - val |= CRI_CALCINIT; - intel_de_write(dev_priv, MG_TX2_PISO_READLOAD(ln, tc_port), - val); + intel_de_rmw(dev_priv, MG_TX1_PISO_READLOAD(ln, tc_port), + 0, CRI_CALCINIT); + intel_de_rmw(dev_priv, MG_TX2_PISO_READLOAD(ln, tc_port), + 0, CRI_CALCINIT); } } @@ -1275,9 +1258,7 @@ static void tgl_dkl_phy_set_signal_levels(struct intel_encoder *encoder, { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); enum tc_port tc_port = intel_port_to_tc(dev_priv, encoder->port); - int level = intel_ddi_level(encoder, crtc_state, 0); const struct intel_ddi_buf_trans *trans; - u32 val, dpcnt_mask, dpcnt_val; int n_entries, ln; if (intel_tc_port_in_tbt_alt_mode(enc_to_dig_port(encoder))) @@ -1287,33 +1268,36 @@ static void tgl_dkl_phy_set_signal_levels(struct intel_encoder *encoder, if (drm_WARN_ON_ONCE(&dev_priv->drm, !trans)) return; - dpcnt_mask = (DKL_TX_PRESHOOT_COEFF_MASK | - DKL_TX_DE_EMPAHSIS_COEFF_MASK | - DKL_TX_VSWING_CONTROL_MASK); - dpcnt_val = DKL_TX_VSWING_CONTROL(trans->entries[level].dkl.vswing); - dpcnt_val |= DKL_TX_DE_EMPHASIS_COEFF(trans->entries[level].dkl.de_emphasis); - dpcnt_val |= DKL_TX_PRESHOOT_COEFF(trans->entries[level].dkl.preshoot); - for (ln = 0; ln < 2; ln++) { + int level; + intel_de_write(dev_priv, HIP_INDEX_REG(tc_port), HIP_INDEX_VAL(tc_port, ln)); intel_de_write(dev_priv, DKL_TX_PMD_LANE_SUS(tc_port), 0); - /* All the registers are RMW */ - val = intel_de_read(dev_priv, DKL_TX_DPCNTL0(tc_port)); - val &= ~dpcnt_mask; - val |= dpcnt_val; - intel_de_write(dev_priv, DKL_TX_DPCNTL0(tc_port), val); + level = intel_ddi_level(encoder, crtc_state, 2*ln+0); + + intel_de_rmw(dev_priv, DKL_TX_DPCNTL0(tc_port), + DKL_TX_PRESHOOT_COEFF_MASK | + DKL_TX_DE_EMPAHSIS_COEFF_MASK | + DKL_TX_VSWING_CONTROL_MASK, + DKL_TX_PRESHOOT_COEFF(trans->entries[level].dkl.preshoot) | + DKL_TX_DE_EMPHASIS_COEFF(trans->entries[level].dkl.de_emphasis) | + DKL_TX_VSWING_CONTROL(trans->entries[level].dkl.vswing)); - val = intel_de_read(dev_priv, DKL_TX_DPCNTL1(tc_port)); - val &= ~dpcnt_mask; - val |= dpcnt_val; - intel_de_write(dev_priv, DKL_TX_DPCNTL1(tc_port), val); + level = intel_ddi_level(encoder, crtc_state, 2*ln+1); - val = intel_de_read(dev_priv, DKL_TX_DPCNTL2(tc_port)); - val &= ~DKL_TX_DP20BITMODE; - intel_de_write(dev_priv, DKL_TX_DPCNTL2(tc_port), val); + intel_de_rmw(dev_priv, DKL_TX_DPCNTL1(tc_port), + DKL_TX_PRESHOOT_COEFF_MASK | + DKL_TX_DE_EMPAHSIS_COEFF_MASK | + DKL_TX_VSWING_CONTROL_MASK, + DKL_TX_PRESHOOT_COEFF(trans->entries[level].dkl.preshoot) | + DKL_TX_DE_EMPHASIS_COEFF(trans->entries[level].dkl.de_emphasis) | + DKL_TX_VSWING_CONTROL(trans->entries[level].dkl.vswing)); + + intel_de_rmw(dev_priv, DKL_TX_DPCNTL2(tc_port), + DKL_TX_DP20BITMODE, 0); } } @@ -1938,7 +1922,7 @@ void intel_ddi_enable_clock(struct intel_encoder *encoder, encoder->enable_clock(encoder, crtc_state); } -static void intel_ddi_disable_clock(struct intel_encoder *encoder) +void intel_ddi_disable_clock(struct intel_encoder *encoder) { if (encoder->disable_clock) encoder->disable_clock(encoder); @@ -2385,7 +2369,10 @@ static void dg2_ddi_pre_enable_dp(struct intel_atomic_state *state, /* 5.k Configure and enable FEC if needed */ intel_ddi_enable_fec(encoder, crtc_state); - intel_dsc_enable(encoder, crtc_state); + + intel_dsc_dp_pps_write(encoder, crtc_state); + + intel_dsc_enable(crtc_state); } static void tgl_ddi_pre_enable_dp(struct intel_atomic_state *state, @@ -2519,8 +2506,11 @@ static void tgl_ddi_pre_enable_dp(struct intel_atomic_state *state, /* 7.l Configure and enable FEC if needed */ intel_ddi_enable_fec(encoder, crtc_state); + + intel_dsc_dp_pps_write(encoder, crtc_state); + if (!crtc_state->bigjoiner) - intel_dsc_enable(encoder, crtc_state); + intel_dsc_enable(crtc_state); } static void hsw_ddi_pre_enable_dp(struct intel_atomic_state *state, @@ -2585,8 +2575,10 @@ static void hsw_ddi_pre_enable_dp(struct intel_atomic_state *state, if (!is_mst) intel_ddi_enable_pipe_clock(encoder, crtc_state); + intel_dsc_dp_pps_write(encoder, crtc_state); + if (!crtc_state->bigjoiner) - intel_dsc_enable(encoder, crtc_state); + intel_dsc_enable(crtc_state); } static void intel_ddi_pre_enable_dp(struct intel_atomic_state *state, @@ -2824,12 +2816,10 @@ static void intel_ddi_post_disable(struct intel_atomic_state *state, } if (old_crtc_state->bigjoiner_linked_crtc) { - struct intel_atomic_state *state = - to_intel_atomic_state(old_crtc_state->uapi.state); - struct intel_crtc *slave = + struct intel_crtc *slave_crtc = old_crtc_state->bigjoiner_linked_crtc; const struct intel_crtc_state *old_slave_crtc_state = - intel_atomic_get_old_crtc_state(state, slave); + intel_atomic_get_old_crtc_state(state, slave_crtc); intel_crtc_vblank_off(old_slave_crtc_state); @@ -2866,41 +2856,6 @@ static void intel_ddi_post_disable(struct intel_atomic_state *state, intel_tc_port_put_link(dig_port); } -void intel_ddi_fdi_post_disable(struct intel_atomic_state *state, - 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 val; - - /* - * Bspec lists this as both step 13 (before DDI_BUF_CTL disable) - * and step 18 (after clearing PORT_CLK_SEL). Based on a BUN, - * step 13 is the correct place for it. Step 18 is where it was - * originally before the BUN. - */ - val = intel_de_read(dev_priv, FDI_RX_CTL(PIPE_A)); - val &= ~FDI_RX_ENABLE; - intel_de_write(dev_priv, FDI_RX_CTL(PIPE_A), val); - - intel_disable_ddi_buf(encoder, old_crtc_state); - intel_ddi_disable_clock(encoder); - - val = intel_de_read(dev_priv, FDI_RX_MISC(PIPE_A)); - val &= ~(FDI_RX_PWRDN_LANE1_MASK | FDI_RX_PWRDN_LANE0_MASK); - val |= FDI_RX_PWRDN_LANE1_VAL(2) | FDI_RX_PWRDN_LANE0_VAL(2); - intel_de_write(dev_priv, FDI_RX_MISC(PIPE_A), val); - - val = intel_de_read(dev_priv, FDI_RX_CTL(PIPE_A)); - val &= ~FDI_PCDCLK; - intel_de_write(dev_priv, FDI_RX_CTL(PIPE_A), val); - - val = intel_de_read(dev_priv, FDI_RX_CTL(PIPE_A)); - val &= ~FDI_RX_PLL_ENABLE; - intel_de_write(dev_priv, FDI_RX_CTL(PIPE_A), val); -} - static void trans_port_sync_stop_link_train(struct intel_atomic_state *state, struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) @@ -2951,6 +2906,7 @@ static void intel_enable_ddi_dp(struct intel_atomic_state *state, if (port == PORT_A && DISPLAY_VER(dev_priv) < 9) intel_dp_stop_link_train(intel_dp, crtc_state); + drm_connector_update_privacy_screen(conn_state); intel_edp_backlight_on(crtc_state, conn_state); if (!dig_port->lspcon.active || dig_port->dp.has_hdmi_sink) @@ -3095,6 +3051,12 @@ static void intel_disable_ddi_dp(struct intel_atomic_state *state, intel_dp->link_trained = false; + if (old_crtc_state->has_audio) + intel_audio_codec_disable(encoder, + old_crtc_state, old_conn_state); + + intel_drrs_disable(intel_dp, old_crtc_state); + intel_psr_disable(intel_dp, old_crtc_state); intel_edp_backlight_off(old_conn_state); /* Disable the decompression in DP Sink */ intel_dp_sink_set_decompression_state(intel_dp, old_crtc_state, @@ -3112,6 +3074,10 @@ static void intel_disable_ddi_hdmi(struct intel_atomic_state *state, struct drm_i915_private *i915 = to_i915(encoder->base.dev); struct drm_connector *connector = old_conn_state->connector; + if (old_crtc_state->has_audio) + intel_audio_codec_disable(encoder, + old_crtc_state, old_conn_state); + if (!intel_hdmi_handle_sink_scrambling(encoder, connector, false, false)) drm_dbg_kms(&i915->drm, @@ -3119,25 +3085,6 @@ static void intel_disable_ddi_hdmi(struct intel_atomic_state *state, connector->base.id, connector->name); } -static void intel_pre_disable_ddi(struct intel_atomic_state *state, - struct intel_encoder *encoder, - const struct intel_crtc_state *old_crtc_state, - const struct drm_connector_state *old_conn_state) -{ - struct intel_dp *intel_dp; - - if (old_crtc_state->has_audio) - intel_audio_codec_disable(encoder, old_crtc_state, - old_conn_state); - - if (intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_HDMI)) - return; - - intel_dp = enc_to_intel_dp(encoder); - intel_drrs_disable(intel_dp, old_crtc_state); - intel_psr_disable(intel_dp, old_crtc_state); -} - static void intel_disable_ddi(struct intel_atomic_state *state, struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, @@ -3166,6 +3113,7 @@ static void intel_ddi_update_pipe_dp(struct intel_atomic_state *state, intel_drrs_update(intel_dp, crtc_state); intel_backlight_update(state, encoder, crtc_state, conn_state); + drm_connector_update_privacy_screen(conn_state); } void intel_ddi_update_pipe(struct intel_atomic_state *state, @@ -3195,8 +3143,14 @@ intel_ddi_update_prepare(struct intel_atomic_state *state, intel_tc_port_get_link(enc_to_dig_port(encoder), required_lanes); - if (crtc_state && crtc_state->hw.active) + if (crtc_state && crtc_state->hw.active) { + struct intel_crtc *slave_crtc = crtc_state->bigjoiner_linked_crtc; + intel_update_active_dpll(state, crtc, encoder); + + if (slave_crtc) + intel_update_active_dpll(state, slave_crtc, encoder); + } } static void @@ -3552,18 +3506,7 @@ static void intel_ddi_get_config(struct intel_encoder *encoder, if (drm_WARN_ON(&dev_priv->drm, transcoder_is_dsi(cpu_transcoder))) return; - if (pipe_config->bigjoiner_slave) { - /* read out pipe settings from master */ - enum transcoder save = pipe_config->cpu_transcoder; - - /* Our own transcoder needs to be disabled when reading it in intel_ddi_read_func_ctl() */ - WARN_ON(pipe_config->output_types); - pipe_config->cpu_transcoder = (enum transcoder)pipe_config->bigjoiner_linked_crtc->pipe; - intel_ddi_read_func_ctl(encoder, pipe_config); - pipe_config->cpu_transcoder = save; - } else { - intel_ddi_read_func_ctl(encoder, pipe_config); - } + intel_ddi_read_func_ctl(encoder, pipe_config); intel_ddi_mso_get_config(encoder, pipe_config); @@ -3591,8 +3534,7 @@ static void intel_ddi_get_config(struct intel_encoder *encoder, dev_priv->vbt.edp.bpp = pipe_config->pipe_bpp; } - if (!pipe_config->bigjoiner_slave) - ddi_dotclock_get(pipe_config); + ddi_dotclock_get(pipe_config); if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) pipe_config->lane_lat_optim_mask = @@ -3983,6 +3925,19 @@ intel_ddi_init_dp_connector(struct intel_digital_port *dig_port) return NULL; } + if (dig_port->base.type == INTEL_OUTPUT_EDP) { + struct drm_device *dev = dig_port->base.base.dev; + struct drm_privacy_screen *privacy_screen; + + privacy_screen = drm_privacy_screen_get(dev->dev, NULL); + if (!IS_ERR(privacy_screen)) { + drm_connector_attach_privacy_screen_provider(&connector->base, + privacy_screen); + } else if (PTR_ERR(privacy_screen) != -ENODEV) { + drm_warn(dev, "Error getting privacy-screen\n"); + } + } + return connector; } @@ -4472,7 +4427,6 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port) encoder->enable = intel_enable_ddi; encoder->pre_pll_enable = intel_ddi_pre_pll_enable; encoder->pre_enable = intel_ddi_pre_enable; - encoder->pre_disable = intel_pre_disable_ddi; encoder->disable = intel_disable_ddi; encoder->post_disable = intel_ddi_post_disable; encoder->update_pipe = intel_ddi_update_pipe; diff --git a/drivers/gpu/drm/i915/display/intel_ddi.h b/drivers/gpu/drm/i915/display/intel_ddi.h index d6971717ef9c..c2fea6562917 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.h +++ b/drivers/gpu/drm/i915/display/intel_ddi.h @@ -6,11 +6,11 @@ #ifndef __INTEL_DDI_H__ #define __INTEL_DDI_H__ -#include "intel_display.h" #include "i915_reg.h" struct drm_connector_state; struct drm_i915_private; +struct intel_atomic_state; struct intel_connector; struct intel_crtc; struct intel_crtc_state; @@ -18,6 +18,8 @@ struct intel_dp; struct intel_dpll_hw_state; struct intel_encoder; struct intel_shared_dpll; +enum pipe; +enum port; enum transcoder; i915_reg_t dp_tp_ctl_reg(struct intel_encoder *encoder, @@ -30,6 +32,7 @@ void intel_ddi_fdi_post_disable(struct intel_atomic_state *state, const struct drm_connector_state *old_conn_state); void intel_ddi_enable_clock(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state); +void intel_ddi_disable_clock(struct intel_encoder *encoder); void intel_ddi_get_clock(struct intel_encoder *encoder, struct intel_crtc_state *crtc_state, struct intel_shared_dpll *pll); diff --git a/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c b/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c index 78cd8f77b49d..1e689d573512 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c +++ b/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c @@ -1032,6 +1032,21 @@ bool is_hobl_buf_trans(const struct intel_ddi_buf_trans *table) return table == &tgl_combo_phy_trans_edp_hbr2_hobl; } +static bool use_edp_hobl(struct intel_encoder *encoder) +{ + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + struct intel_dp *intel_dp = enc_to_intel_dp(encoder); + + return i915->vbt.edp.hobl && !intel_dp->hobl_failed; +} + +static bool use_edp_low_vswing(struct intel_encoder *encoder) +{ + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + + return i915->vbt.edp.low_vswing; +} + static const struct intel_ddi_buf_trans * intel_get_buf_trans(const struct intel_ddi_buf_trans *trans, int *num_entries) { @@ -1057,14 +1072,12 @@ bdw_get_buf_trans(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, int *n_entries) { - struct drm_i915_private *i915 = to_i915(encoder->base.dev); - if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_ANALOG)) return intel_get_buf_trans(&bdw_trans_fdi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) return intel_get_buf_trans(&bdw_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) && - i915->vbt.edp.low_vswing) + use_edp_low_vswing(encoder)) return intel_get_buf_trans(&bdw_trans_edp, n_entries); else return intel_get_buf_trans(&bdw_trans_dp, n_entries); @@ -1094,12 +1107,10 @@ skl_y_get_buf_trans(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, int *n_entries) { - struct drm_i915_private *i915 = to_i915(encoder->base.dev); - if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) return intel_get_buf_trans(&skl_y_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) && - i915->vbt.edp.low_vswing) + use_edp_low_vswing(encoder)) return _skl_get_buf_trans_dp(encoder, &skl_y_trans_edp, n_entries); else return _skl_get_buf_trans_dp(encoder, &skl_y_trans_dp, n_entries); @@ -1110,12 +1121,10 @@ skl_u_get_buf_trans(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, int *n_entries) { - struct drm_i915_private *i915 = to_i915(encoder->base.dev); - if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) return intel_get_buf_trans(&skl_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) && - i915->vbt.edp.low_vswing) + use_edp_low_vswing(encoder)) return _skl_get_buf_trans_dp(encoder, &skl_u_trans_edp, n_entries); else return _skl_get_buf_trans_dp(encoder, &skl_u_trans_dp, n_entries); @@ -1126,12 +1135,10 @@ skl_get_buf_trans(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, int *n_entries) { - struct drm_i915_private *i915 = to_i915(encoder->base.dev); - if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) return intel_get_buf_trans(&skl_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) && - i915->vbt.edp.low_vswing) + use_edp_low_vswing(encoder)) return _skl_get_buf_trans_dp(encoder, &skl_trans_edp, n_entries); else return _skl_get_buf_trans_dp(encoder, &skl_trans_dp, n_entries); @@ -1142,12 +1149,10 @@ kbl_y_get_buf_trans(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, int *n_entries) { - struct drm_i915_private *i915 = to_i915(encoder->base.dev); - if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) return intel_get_buf_trans(&skl_y_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) && - i915->vbt.edp.low_vswing) + use_edp_low_vswing(encoder)) return _skl_get_buf_trans_dp(encoder, &skl_y_trans_edp, n_entries); else return _skl_get_buf_trans_dp(encoder, &kbl_y_trans_dp, n_entries); @@ -1158,12 +1163,10 @@ kbl_u_get_buf_trans(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, int *n_entries) { - struct drm_i915_private *i915 = to_i915(encoder->base.dev); - if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) return intel_get_buf_trans(&skl_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) && - i915->vbt.edp.low_vswing) + use_edp_low_vswing(encoder)) return _skl_get_buf_trans_dp(encoder, &skl_u_trans_edp, n_entries); else return _skl_get_buf_trans_dp(encoder, &kbl_u_trans_dp, n_entries); @@ -1174,12 +1177,10 @@ kbl_get_buf_trans(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, int *n_entries) { - struct drm_i915_private *i915 = to_i915(encoder->base.dev); - if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) return intel_get_buf_trans(&skl_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) && - i915->vbt.edp.low_vswing) + use_edp_low_vswing(encoder)) return _skl_get_buf_trans_dp(encoder, &skl_trans_edp, n_entries); else return _skl_get_buf_trans_dp(encoder, &kbl_trans_dp, n_entries); @@ -1190,12 +1191,10 @@ bxt_get_buf_trans(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, int *n_entries) { - struct drm_i915_private *i915 = to_i915(encoder->base.dev); - if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) return intel_get_buf_trans(&bxt_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) && - i915->vbt.edp.low_vswing) + use_edp_low_vswing(encoder)) return intel_get_buf_trans(&bxt_trans_edp, n_entries); else return intel_get_buf_trans(&bxt_trans_dp, n_entries); @@ -1215,12 +1214,10 @@ icl_get_combo_buf_trans_edp(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, int *n_entries) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - if (crtc_state->port_clock > 540000) { return intel_get_buf_trans(&icl_combo_phy_trans_dp_hbr2_edp_hbr3, n_entries); - } else if (dev_priv->vbt.edp.low_vswing) { + } else if (use_edp_low_vswing(encoder)) { return intel_get_buf_trans(&icl_combo_phy_trans_edp_hbr2, n_entries); } @@ -1282,12 +1279,10 @@ ehl_get_combo_buf_trans(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, int *n_entries) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) return intel_get_buf_trans(&icl_combo_phy_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) && - dev_priv->vbt.edp.low_vswing) + use_edp_low_vswing(encoder)) return ehl_get_combo_buf_trans_edp(encoder, crtc_state, n_entries); else return intel_get_buf_trans(&ehl_combo_phy_trans_dp, n_entries); @@ -1309,12 +1304,10 @@ jsl_get_combo_buf_trans(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, int *n_entries) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) return intel_get_buf_trans(&icl_combo_phy_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) && - dev_priv->vbt.edp.low_vswing) + use_edp_low_vswing(encoder)) return jsl_get_combo_buf_trans_edp(encoder, crtc_state, n_entries); else return intel_get_buf_trans(&icl_combo_phy_trans_dp_hbr2_edp_hbr3, n_entries); @@ -1346,16 +1339,13 @@ tgl_get_combo_buf_trans_edp(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, int *n_entries) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - struct intel_dp *intel_dp = enc_to_intel_dp(encoder); - if (crtc_state->port_clock > 540000) { return intel_get_buf_trans(&icl_combo_phy_trans_dp_hbr2_edp_hbr3, n_entries); - } else if (dev_priv->vbt.edp.hobl && !intel_dp->hobl_failed) { + } else if (use_edp_hobl(encoder)) { return intel_get_buf_trans(&tgl_combo_phy_trans_edp_hbr2_hobl, n_entries); - } else if (dev_priv->vbt.edp.low_vswing) { + } else if (use_edp_low_vswing(encoder)) { return intel_get_buf_trans(&icl_combo_phy_trans_edp_hbr2, n_entries); } @@ -1394,16 +1384,13 @@ dg1_get_combo_buf_trans_edp(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, int *n_entries) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - struct intel_dp *intel_dp = enc_to_intel_dp(encoder); - if (crtc_state->port_clock > 540000) return intel_get_buf_trans(&icl_combo_phy_trans_dp_hbr2_edp_hbr3, n_entries); - else if (dev_priv->vbt.edp.hobl && !intel_dp->hobl_failed) + else if (use_edp_hobl(encoder)) return intel_get_buf_trans(&tgl_combo_phy_trans_edp_hbr2_hobl, n_entries); - else if (dev_priv->vbt.edp.low_vswing) + else if (use_edp_low_vswing(encoder)) return intel_get_buf_trans(&icl_combo_phy_trans_edp_hbr2, n_entries); else @@ -1439,16 +1426,13 @@ rkl_get_combo_buf_trans_edp(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, int *n_entries) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - struct intel_dp *intel_dp = enc_to_intel_dp(encoder); - if (crtc_state->port_clock > 540000) { return intel_get_buf_trans(&icl_combo_phy_trans_dp_hbr2_edp_hbr3, n_entries); - } else if (dev_priv->vbt.edp.hobl && !intel_dp->hobl_failed) { + } else if (use_edp_hobl(encoder)) { return intel_get_buf_trans(&tgl_combo_phy_trans_edp_hbr2_hobl, n_entries); - } else if (dev_priv->vbt.edp.low_vswing) { + } else if (use_edp_low_vswing(encoder)) { return intel_get_buf_trans(&icl_combo_phy_trans_edp_hbr2, n_entries); } @@ -1485,14 +1469,11 @@ adls_get_combo_buf_trans_edp(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, int *n_entries) { - struct drm_i915_private *i915 = to_i915(encoder->base.dev); - struct intel_dp *intel_dp = enc_to_intel_dp(encoder); - if (crtc_state->port_clock > 540000) return intel_get_buf_trans(&adls_combo_phy_trans_edp_hbr3, n_entries); - else if (i915->vbt.edp.hobl && !intel_dp->hobl_failed) + else if (use_edp_hobl(encoder)) return intel_get_buf_trans(&tgl_combo_phy_trans_edp_hbr2_hobl, n_entries); - else if (i915->vbt.edp.low_vswing) + else if (use_edp_low_vswing(encoder)) return intel_get_buf_trans(&adls_combo_phy_trans_edp_hbr2, n_entries); else return adls_get_combo_buf_trans_dp(encoder, crtc_state, n_entries); @@ -1527,16 +1508,13 @@ adlp_get_combo_buf_trans_edp(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, int *n_entries) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - struct intel_dp *intel_dp = enc_to_intel_dp(encoder); - if (crtc_state->port_clock > 540000) { return intel_get_buf_trans(&adlp_combo_phy_trans_edp_hbr3, n_entries); - } else if (dev_priv->vbt.edp.hobl && !intel_dp->hobl_failed) { + } else if (use_edp_hobl(encoder)) { return intel_get_buf_trans(&tgl_combo_phy_trans_edp_hbr2_hobl, n_entries); - } else if (dev_priv->vbt.edp.low_vswing) { + } else if (use_edp_low_vswing(encoder)) { return intel_get_buf_trans(&adlp_combo_phy_trans_edp_up_to_hbr2, n_entries); } diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index ec403e46a328..bf7ce684dd8e 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -32,6 +32,7 @@ #include <linux/module.h> #include <linux/dma-resv.h> #include <linux/slab.h> +#include <linux/vga_switcheroo.h> #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> @@ -41,6 +42,7 @@ #include <drm/drm_edid.h> #include <drm/drm_fourcc.h> #include <drm/drm_plane_helper.h> +#include <drm/drm_privacy_screen_consumer.h> #include <drm/drm_probe_helper.h> #include <drm/drm_rect.h> @@ -70,11 +72,10 @@ #include "gt/gen8_ppgtt.h" -#include "pxp/intel_pxp.h" - #include "g4x_dp.h" #include "g4x_hdmi.h" #include "i915_drv.h" +#include "icl_dsi.h" #include "intel_acpi.h" #include "intel_atomic.h" #include "intel_atomic_plane.h" @@ -96,6 +97,8 @@ #include "intel_hotplug.h" #include "intel_overlay.h" #include "intel_panel.h" +#include "intel_pch_display.h" +#include "intel_pch_refclk.h" #include "intel_pcode.h" #include "intel_pipe_crc.h" #include "intel_plane_initial.h" @@ -103,19 +106,15 @@ #include "intel_pps.h" #include "intel_psr.h" #include "intel_quirks.h" -#include "intel_sbi.h" #include "intel_sprite.h" #include "intel_tc.h" #include "intel_vga.h" #include "i9xx_plane.h" #include "skl_scaler.h" #include "skl_universal_plane.h" +#include "vlv_dsi_pll.h" #include "vlv_sideband.h" - -static void i9xx_crtc_clock_get(struct intel_crtc *crtc, - struct intel_crtc_state *pipe_config); -static void ilk_pch_clock_get(struct intel_crtc *crtc, - struct intel_crtc_state *pipe_config); +#include "vlv_dsi.h" static void intel_set_transcoder_timings(const struct intel_crtc_state *crtc_state); static void intel_set_pipe_src_size(const struct intel_crtc_state *crtc_state); @@ -341,6 +340,14 @@ is_trans_port_sync_mode(const struct intel_crtc_state *crtc_state) is_trans_port_sync_slave(crtc_state); } +static struct intel_crtc *intel_master_crtc(const struct intel_crtc_state *crtc_state) +{ + if (crtc_state->bigjoiner_slave) + return crtc_state->bigjoiner_linked_crtc; + else + return to_intel_crtc(crtc_state->uapi.crtc); +} + static bool pipe_scanline_is_moving(struct drm_i915_private *dev_priv, enum pipe pipe) { @@ -454,80 +461,6 @@ static void assert_planes_disabled(struct intel_crtc *crtc) assert_plane_disabled(plane); } -void assert_pch_transcoder_disabled(struct drm_i915_private *dev_priv, - enum pipe pipe) -{ - u32 val; - bool enabled; - - val = intel_de_read(dev_priv, PCH_TRANSCONF(pipe)); - enabled = !!(val & TRANS_ENABLE); - I915_STATE_WARN(enabled, - "transcoder assertion failed, should be off on pipe %c but is still active\n", - pipe_name(pipe)); -} - -static void assert_pch_dp_disabled(struct drm_i915_private *dev_priv, - enum pipe pipe, enum port port, - i915_reg_t dp_reg) -{ - enum pipe port_pipe; - bool state; - - state = g4x_dp_port_enabled(dev_priv, dp_reg, port, &port_pipe); - - I915_STATE_WARN(state && port_pipe == pipe, - "PCH DP %c enabled on transcoder %c, should be disabled\n", - port_name(port), pipe_name(pipe)); - - I915_STATE_WARN(HAS_PCH_IBX(dev_priv) && !state && port_pipe == PIPE_B, - "IBX PCH DP %c still using transcoder B\n", - port_name(port)); -} - -static void assert_pch_hdmi_disabled(struct drm_i915_private *dev_priv, - enum pipe pipe, enum port port, - i915_reg_t hdmi_reg) -{ - enum pipe port_pipe; - bool state; - - state = intel_sdvo_port_enabled(dev_priv, hdmi_reg, &port_pipe); - - I915_STATE_WARN(state && port_pipe == pipe, - "PCH HDMI %c enabled on transcoder %c, should be disabled\n", - port_name(port), pipe_name(pipe)); - - I915_STATE_WARN(HAS_PCH_IBX(dev_priv) && !state && port_pipe == PIPE_B, - "IBX PCH HDMI %c still using transcoder B\n", - port_name(port)); -} - -static void assert_pch_ports_disabled(struct drm_i915_private *dev_priv, - enum pipe pipe) -{ - enum pipe port_pipe; - - assert_pch_dp_disabled(dev_priv, pipe, PORT_B, PCH_DP_B); - assert_pch_dp_disabled(dev_priv, pipe, PORT_C, PCH_DP_C); - assert_pch_dp_disabled(dev_priv, pipe, PORT_D, PCH_DP_D); - - I915_STATE_WARN(intel_crt_port_enabled(dev_priv, PCH_ADPA, &port_pipe) && - port_pipe == pipe, - "PCH VGA enabled on transcoder %c, should be disabled\n", - pipe_name(pipe)); - - I915_STATE_WARN(intel_lvds_port_enabled(dev_priv, PCH_LVDS, &port_pipe) && - port_pipe == pipe, - "PCH LVDS enabled on transcoder %c, should be disabled\n", - pipe_name(pipe)); - - /* PCH SDVOB multiplex with HDMIB */ - assert_pch_hdmi_disabled(dev_priv, pipe, PORT_B, PCH_HDMIB); - assert_pch_hdmi_disabled(dev_priv, pipe, PORT_C, PCH_HDMIC); - assert_pch_hdmi_disabled(dev_priv, pipe, PORT_D, PCH_HDMID); -} - void vlv_wait_port_ready(struct drm_i915_private *dev_priv, struct intel_digital_port *dig_port, unsigned int expected_mask) @@ -562,154 +495,6 @@ void vlv_wait_port_ready(struct drm_i915_private *dev_priv, expected_mask); } -static void ilk_enable_pch_transcoder(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; - i915_reg_t reg; - u32 val, pipeconf_val; - - /* Make sure PCH DPLL is enabled */ - assert_shared_dpll_enabled(dev_priv, crtc_state->shared_dpll); - - /* FDI must be feeding us bits for PCH ports */ - assert_fdi_tx_enabled(dev_priv, pipe); - assert_fdi_rx_enabled(dev_priv, pipe); - - if (HAS_PCH_CPT(dev_priv)) { - reg = TRANS_CHICKEN2(pipe); - val = intel_de_read(dev_priv, reg); - /* - * Workaround: Set the timing override bit - * before enabling the pch transcoder. - */ - val |= TRANS_CHICKEN2_TIMING_OVERRIDE; - /* Configure frame start delay to match the CPU */ - val &= ~TRANS_CHICKEN2_FRAME_START_DELAY_MASK; - val |= TRANS_CHICKEN2_FRAME_START_DELAY(dev_priv->framestart_delay - 1); - intel_de_write(dev_priv, reg, val); - } - - reg = PCH_TRANSCONF(pipe); - val = intel_de_read(dev_priv, reg); - pipeconf_val = intel_de_read(dev_priv, PIPECONF(pipe)); - - if (HAS_PCH_IBX(dev_priv)) { - /* Configure frame start delay to match the CPU */ - val &= ~TRANS_FRAME_START_DELAY_MASK; - val |= TRANS_FRAME_START_DELAY(dev_priv->framestart_delay - 1); - - /* - * Make the BPC in transcoder be consistent with - * that in pipeconf reg. For HDMI we must use 8bpc - * here for both 8bpc and 12bpc. - */ - val &= ~PIPECONF_BPC_MASK; - if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) - val |= PIPECONF_8BPC; - else - val |= pipeconf_val & PIPECONF_BPC_MASK; - } - - val &= ~TRANS_INTERLACE_MASK; - if ((pipeconf_val & PIPECONF_INTERLACE_MASK) == PIPECONF_INTERLACED_ILK) { - if (HAS_PCH_IBX(dev_priv) && - intel_crtc_has_type(crtc_state, INTEL_OUTPUT_SDVO)) - val |= TRANS_LEGACY_INTERLACED_ILK; - else - val |= TRANS_INTERLACED; - } else { - val |= TRANS_PROGRESSIVE; - } - - intel_de_write(dev_priv, reg, val | TRANS_ENABLE); - if (intel_de_wait_for_set(dev_priv, reg, TRANS_STATE_ENABLE, 100)) - drm_err(&dev_priv->drm, "failed to enable transcoder %c\n", - pipe_name(pipe)); -} - -static void lpt_enable_pch_transcoder(struct drm_i915_private *dev_priv, - enum transcoder cpu_transcoder) -{ - u32 val, pipeconf_val; - - /* FDI must be feeding us bits for PCH ports */ - assert_fdi_tx_enabled(dev_priv, (enum pipe) cpu_transcoder); - assert_fdi_rx_enabled(dev_priv, PIPE_A); - - val = intel_de_read(dev_priv, TRANS_CHICKEN2(PIPE_A)); - /* Workaround: set timing override bit. */ - val |= TRANS_CHICKEN2_TIMING_OVERRIDE; - /* Configure frame start delay to match the CPU */ - val &= ~TRANS_CHICKEN2_FRAME_START_DELAY_MASK; - val |= TRANS_CHICKEN2_FRAME_START_DELAY(dev_priv->framestart_delay - 1); - intel_de_write(dev_priv, TRANS_CHICKEN2(PIPE_A), val); - - val = TRANS_ENABLE; - pipeconf_val = intel_de_read(dev_priv, PIPECONF(cpu_transcoder)); - - if ((pipeconf_val & PIPECONF_INTERLACE_MASK_HSW) == - PIPECONF_INTERLACED_ILK) - val |= TRANS_INTERLACED; - else - val |= TRANS_PROGRESSIVE; - - intel_de_write(dev_priv, LPT_TRANSCONF, val); - if (intel_de_wait_for_set(dev_priv, LPT_TRANSCONF, - TRANS_STATE_ENABLE, 100)) - drm_err(&dev_priv->drm, "Failed to enable PCH transcoder\n"); -} - -static void ilk_disable_pch_transcoder(struct drm_i915_private *dev_priv, - enum pipe pipe) -{ - i915_reg_t reg; - u32 val; - - /* FDI relies on the transcoder */ - assert_fdi_tx_disabled(dev_priv, pipe); - assert_fdi_rx_disabled(dev_priv, pipe); - - /* Ports must be off as well */ - assert_pch_ports_disabled(dev_priv, pipe); - - reg = PCH_TRANSCONF(pipe); - val = intel_de_read(dev_priv, reg); - val &= ~TRANS_ENABLE; - intel_de_write(dev_priv, reg, val); - /* wait for PCH transcoder off, transcoder state */ - if (intel_de_wait_for_clear(dev_priv, reg, TRANS_STATE_ENABLE, 50)) - drm_err(&dev_priv->drm, "failed to disable transcoder %c\n", - pipe_name(pipe)); - - if (HAS_PCH_CPT(dev_priv)) { - /* Workaround: Clear the timing override chicken bit again. */ - reg = TRANS_CHICKEN2(pipe); - val = intel_de_read(dev_priv, reg); - val &= ~TRANS_CHICKEN2_TIMING_OVERRIDE; - intel_de_write(dev_priv, reg, val); - } -} - -void lpt_disable_pch_transcoder(struct drm_i915_private *dev_priv) -{ - u32 val; - - val = intel_de_read(dev_priv, LPT_TRANSCONF); - val &= ~TRANS_ENABLE; - intel_de_write(dev_priv, LPT_TRANSCONF, val); - /* wait for PCH transcoder off, transcoder state */ - if (intel_de_wait_for_clear(dev_priv, LPT_TRANSCONF, - TRANS_STATE_ENABLE, 50)) - drm_err(&dev_priv->drm, "Failed to disable PCH transcoder\n"); - - /* Workaround: clear timing override bit. */ - val = intel_de_read(dev_priv, TRANS_CHICKEN2(PIPE_A)); - val &= ~TRANS_CHICKEN2_TIMING_OVERRIDE; - intel_de_write(dev_priv, TRANS_CHICKEN2(PIPE_A), val); -} - enum pipe intel_crtc_pch_transcoder(struct intel_crtc *crtc) { struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); @@ -823,14 +608,6 @@ void intel_disable_transcoder(const struct intel_crtc_state *old_crtc_state) intel_wait_for_pipe_off(old_crtc_state); } -bool -intel_format_info_is_yuv_semiplanar(const struct drm_format_info *info, - u64 modifier) -{ - return info->is_yuv && - info->num_planes == (is_ccs_modifier(modifier) ? 4 : 2); -} - unsigned int intel_rotation_info_size(const struct intel_rotation_info *rot_info) { unsigned int size = 0; @@ -850,7 +627,11 @@ unsigned int intel_remapped_info_size(const struct intel_remapped_info *rem_info for (i = 0 ; i < ARRAY_SIZE(rem_info->plane); i++) { unsigned int plane_size; - plane_size = rem_info->plane[i].dst_stride * rem_info->plane[i].height; + if (rem_info->plane[i].linear) + plane_size = rem_info->plane[i].size; + else + plane_size = rem_info->plane[i].dst_stride * rem_info->plane[i].height; + if (plane_size == 0) continue; @@ -869,7 +650,7 @@ bool intel_plane_uses_fence(const struct intel_plane_state *plane_state) struct drm_i915_private *dev_priv = to_i915(plane->base.dev); return DISPLAY_VER(dev_priv) < 4 || - (plane->has_fbc && + (plane->fbc && plane_state->view.gtt.type == I915_GGTT_VIEW_NORMAL); } @@ -885,7 +666,7 @@ u32 intel_fb_xy_to_linear(int x, int y, { const struct drm_framebuffer *fb = state->hw.fb; unsigned int cpp = fb->format->cpp[color_plane]; - unsigned int pitch = state->view.color_plane[color_plane].stride; + unsigned int pitch = state->view.color_plane[color_plane].mapping_stride; return y * pitch + x * cpp; } @@ -904,136 +685,6 @@ void intel_add_fb_offsets(int *x, int *y, *y += state->view.color_plane[color_plane].y; } -/* - * From the Sky Lake PRM: - * "The Color Control Surface (CCS) contains the compression status of - * the cache-line pairs. The compression state of the cache-line pair - * is specified by 2 bits in the CCS. Each CCS cache-line represents - * an area on the main surface of 16 x16 sets of 128 byte Y-tiled - * cache-line-pairs. CCS is always Y tiled." - * - * Since cache line pairs refers to horizontally adjacent cache lines, - * each cache line in the CCS corresponds to an area of 32x16 cache - * lines on the main surface. Since each pixel is 4 bytes, this gives - * us a ratio of one byte in the CCS for each 8x16 pixels in the - * main surface. - */ -static const struct drm_format_info skl_ccs_formats[] = { - { .format = DRM_FORMAT_XRGB8888, .depth = 24, .num_planes = 2, - .cpp = { 4, 1, }, .hsub = 8, .vsub = 16, }, - { .format = DRM_FORMAT_XBGR8888, .depth = 24, .num_planes = 2, - .cpp = { 4, 1, }, .hsub = 8, .vsub = 16, }, - { .format = DRM_FORMAT_ARGB8888, .depth = 32, .num_planes = 2, - .cpp = { 4, 1, }, .hsub = 8, .vsub = 16, .has_alpha = true, }, - { .format = DRM_FORMAT_ABGR8888, .depth = 32, .num_planes = 2, - .cpp = { 4, 1, }, .hsub = 8, .vsub = 16, .has_alpha = true, }, -}; - -/* - * Gen-12 compression uses 4 bits of CCS data for each cache line pair in the - * main surface. And each 64B CCS cache line represents an area of 4x1 Y-tiles - * in the main surface. With 4 byte pixels and each Y-tile having dimensions of - * 32x32 pixels, the ratio turns out to 1B in the CCS for every 2x32 pixels in - * the main surface. - */ -static const struct drm_format_info gen12_ccs_formats[] = { - { .format = DRM_FORMAT_XRGB8888, .depth = 24, .num_planes = 2, - .char_per_block = { 4, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 }, - .hsub = 1, .vsub = 1, }, - { .format = DRM_FORMAT_XBGR8888, .depth = 24, .num_planes = 2, - .char_per_block = { 4, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 }, - .hsub = 1, .vsub = 1, }, - { .format = DRM_FORMAT_ARGB8888, .depth = 32, .num_planes = 2, - .char_per_block = { 4, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 }, - .hsub = 1, .vsub = 1, .has_alpha = true }, - { .format = DRM_FORMAT_ABGR8888, .depth = 32, .num_planes = 2, - .char_per_block = { 4, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 }, - .hsub = 1, .vsub = 1, .has_alpha = true }, - { .format = DRM_FORMAT_YUYV, .num_planes = 2, - .char_per_block = { 2, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 }, - .hsub = 2, .vsub = 1, .is_yuv = true }, - { .format = DRM_FORMAT_YVYU, .num_planes = 2, - .char_per_block = { 2, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 }, - .hsub = 2, .vsub = 1, .is_yuv = true }, - { .format = DRM_FORMAT_UYVY, .num_planes = 2, - .char_per_block = { 2, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 }, - .hsub = 2, .vsub = 1, .is_yuv = true }, - { .format = DRM_FORMAT_VYUY, .num_planes = 2, - .char_per_block = { 2, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 }, - .hsub = 2, .vsub = 1, .is_yuv = true }, - { .format = DRM_FORMAT_XYUV8888, .num_planes = 2, - .char_per_block = { 4, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 }, - .hsub = 1, .vsub = 1, .is_yuv = true }, - { .format = DRM_FORMAT_NV12, .num_planes = 4, - .char_per_block = { 1, 2, 1, 1 }, .block_w = { 1, 1, 4, 4 }, .block_h = { 1, 1, 1, 1 }, - .hsub = 2, .vsub = 2, .is_yuv = true }, - { .format = DRM_FORMAT_P010, .num_planes = 4, - .char_per_block = { 2, 4, 1, 1 }, .block_w = { 1, 1, 2, 2 }, .block_h = { 1, 1, 1, 1 }, - .hsub = 2, .vsub = 2, .is_yuv = true }, - { .format = DRM_FORMAT_P012, .num_planes = 4, - .char_per_block = { 2, 4, 1, 1 }, .block_w = { 1, 1, 2, 2 }, .block_h = { 1, 1, 1, 1 }, - .hsub = 2, .vsub = 2, .is_yuv = true }, - { .format = DRM_FORMAT_P016, .num_planes = 4, - .char_per_block = { 2, 4, 1, 1 }, .block_w = { 1, 1, 2, 2 }, .block_h = { 1, 1, 1, 1 }, - .hsub = 2, .vsub = 2, .is_yuv = true }, -}; - -/* - * Same as gen12_ccs_formats[] above, but with additional surface used - * to pass Clear Color information in plane 2 with 64 bits of data. - */ -static const struct drm_format_info gen12_ccs_cc_formats[] = { - { .format = DRM_FORMAT_XRGB8888, .depth = 24, .num_planes = 3, - .char_per_block = { 4, 1, 0 }, .block_w = { 1, 2, 2 }, .block_h = { 1, 1, 1 }, - .hsub = 1, .vsub = 1, }, - { .format = DRM_FORMAT_XBGR8888, .depth = 24, .num_planes = 3, - .char_per_block = { 4, 1, 0 }, .block_w = { 1, 2, 2 }, .block_h = { 1, 1, 1 }, - .hsub = 1, .vsub = 1, }, - { .format = DRM_FORMAT_ARGB8888, .depth = 32, .num_planes = 3, - .char_per_block = { 4, 1, 0 }, .block_w = { 1, 2, 2 }, .block_h = { 1, 1, 1 }, - .hsub = 1, .vsub = 1, .has_alpha = true }, - { .format = DRM_FORMAT_ABGR8888, .depth = 32, .num_planes = 3, - .char_per_block = { 4, 1, 0 }, .block_w = { 1, 2, 2 }, .block_h = { 1, 1, 1 }, - .hsub = 1, .vsub = 1, .has_alpha = true }, -}; - -static const struct drm_format_info * -lookup_format_info(const struct drm_format_info formats[], - int num_formats, u32 format) -{ - int i; - - for (i = 0; i < num_formats; i++) { - if (formats[i].format == format) - return &formats[i]; - } - - return NULL; -} - -static const struct drm_format_info * -intel_get_format_info(const struct drm_mode_fb_cmd2 *cmd) -{ - switch (cmd->modifier[0]) { - case I915_FORMAT_MOD_Y_TILED_CCS: - case I915_FORMAT_MOD_Yf_TILED_CCS: - return lookup_format_info(skl_ccs_formats, - ARRAY_SIZE(skl_ccs_formats), - cmd->pixel_format); - case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS: - case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS: - return lookup_format_info(gen12_ccs_formats, - ARRAY_SIZE(gen12_ccs_formats), - cmd->pixel_format); - case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC: - return lookup_format_info(gen12_ccs_cc_formats, - ARRAY_SIZE(gen12_ccs_cc_formats), - cmd->pixel_format); - default: - return NULL; - } -} - u32 intel_plane_fb_max_stride(struct drm_i915_private *dev_priv, u32 pixel_format, u64 modifier) { @@ -1048,7 +699,7 @@ u32 intel_plane_fb_max_stride(struct drm_i915_private *dev_priv, * the highest stride limits of them all, * if in case pipe A is disabled, use the first pipe from pipe_mask. */ - crtc = intel_get_first_crtc(dev_priv); + crtc = intel_first_crtc(dev_priv); if (!crtc) return 0; @@ -1126,7 +777,7 @@ void intel_plane_disable_noatomic(struct intel_crtc *crtc, */ if (HAS_GMCH(dev_priv) && intel_set_memory_cxsr(dev_priv, false)) - intel_wait_for_vblank(dev_priv, crtc->pipe); + intel_crtc_wait_for_next_vblank(crtc); /* * Gen2 reports pipe underruns whenever all planes are disabled. @@ -1135,8 +786,8 @@ void intel_plane_disable_noatomic(struct intel_crtc *crtc, if (DISPLAY_VER(dev_priv) == 2 && !crtc_state->active_planes) intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, false); - intel_disable_plane(plane, crtc_state); - intel_wait_for_vblank(dev_priv, crtc->pipe); + intel_plane_disable_arm(plane, crtc_state); + intel_crtc_wait_for_next_vblank(crtc); } unsigned int @@ -1192,7 +843,7 @@ __intel_display_resume(struct drm_device *dev, static bool gpu_reset_clobbers_display(struct drm_i915_private *dev_priv) { return (INTEL_INFO(dev_priv)->gpu_reset_clobbers_display && - intel_has_gpu_reset(&dev_priv->gt)); + intel_has_gpu_reset(to_gt(dev_priv))); } void intel_display_prepare_reset(struct drm_i915_private *dev_priv) @@ -1211,14 +862,14 @@ void intel_display_prepare_reset(struct drm_i915_private *dev_priv) return; /* We have a modeset vs reset deadlock, defensively unbreak it. */ - set_bit(I915_RESET_MODESET, &dev_priv->gt.reset.flags); + set_bit(I915_RESET_MODESET, &to_gt(dev_priv)->reset.flags); smp_mb__after_atomic(); - wake_up_bit(&dev_priv->gt.reset.flags, I915_RESET_MODESET); + wake_up_bit(&to_gt(dev_priv)->reset.flags, I915_RESET_MODESET); if (atomic_read(&dev_priv->gpu_error.pending_fb_pin)) { drm_dbg_kms(&dev_priv->drm, "Modeset potentially stuck, unbreaking through wedging\n"); - intel_gt_set_wedged(&dev_priv->gt); + intel_gt_set_wedged(to_gt(dev_priv)); } /* @@ -1269,7 +920,7 @@ void intel_display_finish_reset(struct drm_i915_private *dev_priv) return; /* reset doesn't touch the display */ - if (!test_bit(I915_RESET_MODESET, &dev_priv->gt.reset.flags)) + if (!test_bit(I915_RESET_MODESET, &to_gt(dev_priv)->reset.flags)) return; state = fetch_and_zero(&dev_priv->modeset_restore_state); @@ -1307,27 +958,7 @@ unlock: drm_modeset_acquire_fini(ctx); mutex_unlock(&dev->mode_config.mutex); - clear_bit_unlock(I915_RESET_MODESET, &dev_priv->gt.reset.flags); -} - -static bool underrun_recovery_supported(const struct intel_crtc_state *crtc_state) -{ - if (crtc_state->pch_pfit.enabled && - (crtc_state->pipe_src_w > drm_rect_width(&crtc_state->pch_pfit.dst) || - crtc_state->pipe_src_h > drm_rect_height(&crtc_state->pch_pfit.dst) || - crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR420)) - return false; - - if (crtc_state->dsc.compression_enable) - return false; - - if (crtc_state->has_psr2) - return false; - - if (crtc_state->splitter.enable) - return false; - - return true; + clear_bit_unlock(I915_RESET_MODESET, &to_gt(dev_priv)->reset.flags); } static void icl_set_pipe_chicken(const struct intel_crtc_state *crtc_state) @@ -1353,19 +984,18 @@ static void icl_set_pipe_chicken(const struct intel_crtc_state *crtc_state) */ tmp |= PIXEL_ROUNDING_TRUNC_FB_PASSTHRU; - if (IS_DG2(dev_priv)) { - /* - * Underrun recovery must always be disabled on DG2. However - * the chicken bit meaning is inverted compared to other - * platforms. - */ + /* + * Underrun recovery must always be disabled on display 13+. + * DG2 chicken bit meaning is inverted compared to other platforms. + */ + if (IS_DG2(dev_priv)) tmp &= ~UNDERRUN_RECOVERY_ENABLE_DG2; - } else if (DISPLAY_VER(dev_priv) >= 13) { - if (underrun_recovery_supported(crtc_state)) - tmp &= ~UNDERRUN_RECOVERY_DISABLE_ADLP; - else - tmp |= UNDERRUN_RECOVERY_DISABLE_ADLP; - } + else if (DISPLAY_VER(dev_priv) >= 13) + tmp |= UNDERRUN_RECOVERY_DISABLE_ADLP; + + /* Wa_14010547955:dg2 */ + if (IS_DG2_DISPLAY_STEP(dev_priv, STEP_B0, STEP_FOREVER)) + tmp |= DG2_RENDER_CCSTAG_4_3_EN; intel_de_write(dev_priv, PIPE_CHICKEN(pipe), tmp); } @@ -1387,7 +1017,7 @@ bool intel_has_pending_fb_unpin(struct drm_i915_private *dev_priv) if (cleanup_done) continue; - drm_crtc_wait_one_vblank(crtc); + intel_crtc_wait_for_next_vblank(to_intel_crtc(crtc)); return true; } @@ -1395,158 +1025,6 @@ bool intel_has_pending_fb_unpin(struct drm_i915_private *dev_priv) return false; } -void lpt_disable_iclkip(struct drm_i915_private *dev_priv) -{ - u32 temp; - - intel_de_write(dev_priv, PIXCLK_GATE, PIXCLK_GATE_GATE); - - mutex_lock(&dev_priv->sb_lock); - - temp = intel_sbi_read(dev_priv, SBI_SSCCTL6, SBI_ICLK); - temp |= SBI_SSCCTL_DISABLE; - intel_sbi_write(dev_priv, SBI_SSCCTL6, temp, SBI_ICLK); - - mutex_unlock(&dev_priv->sb_lock); -} - -/* Program iCLKIP clock to the desired frequency */ -static void lpt_program_iclkip(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); - int clock = crtc_state->hw.adjusted_mode.crtc_clock; - u32 divsel, phaseinc, auxdiv, phasedir = 0; - u32 temp; - - lpt_disable_iclkip(dev_priv); - - /* The iCLK virtual clock root frequency is in MHz, - * but the adjusted_mode->crtc_clock in in KHz. To get the - * divisors, it is necessary to divide one by another, so we - * convert the virtual clock precision to KHz here for higher - * precision. - */ - for (auxdiv = 0; auxdiv < 2; auxdiv++) { - u32 iclk_virtual_root_freq = 172800 * 1000; - u32 iclk_pi_range = 64; - u32 desired_divisor; - - desired_divisor = DIV_ROUND_CLOSEST(iclk_virtual_root_freq, - clock << auxdiv); - divsel = (desired_divisor / iclk_pi_range) - 2; - phaseinc = desired_divisor % iclk_pi_range; - - /* - * Near 20MHz is a corner case which is - * out of range for the 7-bit divisor - */ - if (divsel <= 0x7f) - break; - } - - /* This should not happen with any sane values */ - drm_WARN_ON(&dev_priv->drm, SBI_SSCDIVINTPHASE_DIVSEL(divsel) & - ~SBI_SSCDIVINTPHASE_DIVSEL_MASK); - drm_WARN_ON(&dev_priv->drm, SBI_SSCDIVINTPHASE_DIR(phasedir) & - ~SBI_SSCDIVINTPHASE_INCVAL_MASK); - - drm_dbg_kms(&dev_priv->drm, - "iCLKIP clock: found settings for %dKHz refresh rate: auxdiv=%x, divsel=%x, phasedir=%x, phaseinc=%x\n", - clock, auxdiv, divsel, phasedir, phaseinc); - - mutex_lock(&dev_priv->sb_lock); - - /* Program SSCDIVINTPHASE6 */ - temp = intel_sbi_read(dev_priv, SBI_SSCDIVINTPHASE6, SBI_ICLK); - temp &= ~SBI_SSCDIVINTPHASE_DIVSEL_MASK; - temp |= SBI_SSCDIVINTPHASE_DIVSEL(divsel); - temp &= ~SBI_SSCDIVINTPHASE_INCVAL_MASK; - temp |= SBI_SSCDIVINTPHASE_INCVAL(phaseinc); - temp |= SBI_SSCDIVINTPHASE_DIR(phasedir); - temp |= SBI_SSCDIVINTPHASE_PROPAGATE; - intel_sbi_write(dev_priv, SBI_SSCDIVINTPHASE6, temp, SBI_ICLK); - - /* Program SSCAUXDIV */ - temp = intel_sbi_read(dev_priv, SBI_SSCAUXDIV6, SBI_ICLK); - temp &= ~SBI_SSCAUXDIV_FINALDIV2SEL(1); - temp |= SBI_SSCAUXDIV_FINALDIV2SEL(auxdiv); - intel_sbi_write(dev_priv, SBI_SSCAUXDIV6, temp, SBI_ICLK); - - /* Enable modulator and associated divider */ - temp = intel_sbi_read(dev_priv, SBI_SSCCTL6, SBI_ICLK); - temp &= ~SBI_SSCCTL_DISABLE; - intel_sbi_write(dev_priv, SBI_SSCCTL6, temp, SBI_ICLK); - - mutex_unlock(&dev_priv->sb_lock); - - /* Wait for initialization time */ - udelay(24); - - intel_de_write(dev_priv, PIXCLK_GATE, PIXCLK_GATE_UNGATE); -} - -int lpt_get_iclkip(struct drm_i915_private *dev_priv) -{ - u32 divsel, phaseinc, auxdiv; - u32 iclk_virtual_root_freq = 172800 * 1000; - u32 iclk_pi_range = 64; - u32 desired_divisor; - u32 temp; - - if ((intel_de_read(dev_priv, PIXCLK_GATE) & PIXCLK_GATE_UNGATE) == 0) - return 0; - - mutex_lock(&dev_priv->sb_lock); - - temp = intel_sbi_read(dev_priv, SBI_SSCCTL6, SBI_ICLK); - if (temp & SBI_SSCCTL_DISABLE) { - mutex_unlock(&dev_priv->sb_lock); - return 0; - } - - temp = intel_sbi_read(dev_priv, SBI_SSCDIVINTPHASE6, SBI_ICLK); - divsel = (temp & SBI_SSCDIVINTPHASE_DIVSEL_MASK) >> - SBI_SSCDIVINTPHASE_DIVSEL_SHIFT; - phaseinc = (temp & SBI_SSCDIVINTPHASE_INCVAL_MASK) >> - SBI_SSCDIVINTPHASE_INCVAL_SHIFT; - - temp = intel_sbi_read(dev_priv, SBI_SSCAUXDIV6, SBI_ICLK); - auxdiv = (temp & SBI_SSCAUXDIV_FINALDIV2SEL_MASK) >> - SBI_SSCAUXDIV_FINALDIV2SEL_SHIFT; - - mutex_unlock(&dev_priv->sb_lock); - - desired_divisor = (divsel + 2) * iclk_pi_range + phaseinc; - - return DIV_ROUND_CLOSEST(iclk_virtual_root_freq, - desired_divisor << auxdiv); -} - -static void ilk_pch_transcoder_set_timings(const struct intel_crtc_state *crtc_state, - enum pipe pch_transcoder) -{ - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; - - intel_de_write(dev_priv, PCH_TRANS_HTOTAL(pch_transcoder), - intel_de_read(dev_priv, HTOTAL(cpu_transcoder))); - intel_de_write(dev_priv, PCH_TRANS_HBLANK(pch_transcoder), - intel_de_read(dev_priv, HBLANK(cpu_transcoder))); - intel_de_write(dev_priv, PCH_TRANS_HSYNC(pch_transcoder), - intel_de_read(dev_priv, HSYNC(cpu_transcoder))); - - intel_de_write(dev_priv, PCH_TRANS_VTOTAL(pch_transcoder), - intel_de_read(dev_priv, VTOTAL(cpu_transcoder))); - intel_de_write(dev_priv, PCH_TRANS_VBLANK(pch_transcoder), - intel_de_read(dev_priv, VBLANK(cpu_transcoder))); - intel_de_write(dev_priv, PCH_TRANS_VSYNC(pch_transcoder), - intel_de_read(dev_priv, VSYNC(cpu_transcoder))); - intel_de_write(dev_priv, PCH_TRANS_VSYNCSHIFT(pch_transcoder), - intel_de_read(dev_priv, VSYNCSHIFT(cpu_transcoder))); -} - /* * Finds the encoder associated with the given CRTC. This can only be * used when we know that the CRTC isn't feeding multiple encoders! @@ -1555,15 +1033,17 @@ struct intel_encoder * intel_get_crtc_new_encoder(const struct intel_atomic_state *state, const struct intel_crtc_state *crtc_state) { - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); const struct drm_connector_state *connector_state; const struct drm_connector *connector; struct intel_encoder *encoder = NULL; + struct intel_crtc *master_crtc; int num_encoders = 0; int i; + master_crtc = intel_master_crtc(crtc_state); + for_each_new_connector_in_state(&state->base, connector, connector_state, i) { - if (connector_state->crtc != &crtc->base) + if (connector_state->crtc != &master_crtc->base) continue; encoder = to_intel_encoder(connector_state->best_encoder); @@ -1572,111 +1052,11 @@ intel_get_crtc_new_encoder(const struct intel_atomic_state *state, drm_WARN(encoder->base.dev, num_encoders != 1, "%d encoders for pipe %c\n", - num_encoders, pipe_name(crtc->pipe)); + num_encoders, pipe_name(master_crtc->pipe)); return encoder; } -/* - * Enable PCH resources required for PCH ports: - * - PCH PLLs - * - FDI training & RX/TX - * - update transcoder timings - * - DP transcoding bits - * - transcoder - */ -static void ilk_pch_enable(const struct intel_atomic_state *state, - const struct intel_crtc_state *crtc_state) -{ - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_device *dev = crtc->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); - enum pipe pipe = crtc->pipe; - u32 temp; - - assert_pch_transcoder_disabled(dev_priv, pipe); - - /* For PCH output, training FDI link */ - intel_fdi_link_train(crtc, crtc_state); - - /* We need to program the right clock selection before writing the pixel - * mutliplier into the DPLL. */ - if (HAS_PCH_CPT(dev_priv)) { - u32 sel; - - temp = intel_de_read(dev_priv, PCH_DPLL_SEL); - temp |= TRANS_DPLL_ENABLE(pipe); - sel = TRANS_DPLLB_SEL(pipe); - if (crtc_state->shared_dpll == - intel_get_shared_dpll_by_id(dev_priv, DPLL_ID_PCH_PLL_B)) - temp |= sel; - else - temp &= ~sel; - intel_de_write(dev_priv, PCH_DPLL_SEL, temp); - } - - /* XXX: pch pll's can be enabled any time before we enable the PCH - * transcoder, and we actually should do this to not upset any PCH - * transcoder that already use the clock when we share it. - * - * Note that enable_shared_dpll tries to do the right thing, but - * get_shared_dpll unconditionally resets the pll - we need that to have - * the right LVDS enable sequence. */ - intel_enable_shared_dpll(crtc_state); - - /* set transcoder timing, panel must allow it */ - assert_pps_unlocked(dev_priv, pipe); - ilk_pch_transcoder_set_timings(crtc_state, pipe); - - intel_fdi_normal_train(crtc); - - /* For PCH DP, enable TRANS_DP_CTL */ - if (HAS_PCH_CPT(dev_priv) && - intel_crtc_has_dp_encoder(crtc_state)) { - const struct drm_display_mode *adjusted_mode = - &crtc_state->hw.adjusted_mode; - u32 bpc = (intel_de_read(dev_priv, PIPECONF(pipe)) & PIPECONF_BPC_MASK) >> 5; - i915_reg_t reg = TRANS_DP_CTL(pipe); - enum port port; - - temp = intel_de_read(dev_priv, reg); - temp &= ~(TRANS_DP_PORT_SEL_MASK | - TRANS_DP_SYNC_MASK | - TRANS_DP_BPC_MASK); - temp |= TRANS_DP_OUTPUT_ENABLE; - temp |= bpc << 9; /* same format but at 11:9 */ - - if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC) - temp |= TRANS_DP_HSYNC_ACTIVE_HIGH; - if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC) - temp |= TRANS_DP_VSYNC_ACTIVE_HIGH; - - port = intel_get_crtc_new_encoder(state, crtc_state)->port; - drm_WARN_ON(dev, port < PORT_B || port > PORT_D); - temp |= TRANS_DP_PORT_SEL(port); - - intel_de_write(dev_priv, reg, temp); - } - - ilk_enable_pch_transcoder(crtc_state); -} - -void lpt_pch_enable(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 transcoder cpu_transcoder = crtc_state->cpu_transcoder; - - assert_pch_transcoder_disabled(dev_priv, PIPE_A); - - lpt_program_iclkip(crtc_state); - - /* Set transcoder timing. */ - ilk_pch_transcoder_set_timings(crtc_state, PIPE_A); - - lpt_enable_pch_transcoder(dev_priv, cpu_transcoder); -} - static void cpt_verify_modeset(struct drm_i915_private *dev_priv, enum pipe pipe) { @@ -1784,7 +1164,7 @@ void hsw_disable_ips(const struct intel_crtc_state *crtc_state) } /* We need to wait for a vblank before we can disable the plane. */ - intel_wait_for_vblank(dev_priv, crtc->pipe); + intel_crtc_wait_for_next_vblank(crtc); } static void intel_crtc_dpms_overlay_disable(struct intel_crtc *crtc) @@ -1919,7 +1299,7 @@ static bool needs_async_flip_vtd_wa(const struct intel_crtc_state *crtc_state) { struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); - return crtc_state->uapi.async_flip && intel_vtd_active() && + return crtc_state->uapi.async_flip && intel_vtd_active(i915) && (DISPLAY_VER(i915) == 9 || IS_BROADWELL(i915) || IS_HASWELL(i915)); } @@ -2015,7 +1395,6 @@ static void intel_crtc_disable_flip_done(struct intel_atomic_state *state, static void intel_crtc_async_flip_disable_wa(struct intel_atomic_state *state, struct intel_crtc *crtc) { - struct drm_i915_private *i915 = to_i915(state->base.dev); const struct intel_crtc_state *old_crtc_state = intel_atomic_get_old_crtc_state(state, crtc); const struct intel_crtc_state *new_crtc_state = @@ -2041,7 +1420,7 @@ static void intel_crtc_async_flip_disable_wa(struct intel_atomic_state *state, } if (need_vbl_wait) - intel_wait_for_vblank(i915, crtc->pipe); + intel_crtc_wait_for_next_vblank(crtc); } static void intel_pre_plane_update(struct intel_atomic_state *state, @@ -2054,11 +1433,13 @@ static void intel_pre_plane_update(struct intel_atomic_state *state, intel_atomic_get_new_crtc_state(state, crtc); enum pipe pipe = crtc->pipe; + intel_psr_pre_plane_update(state, crtc); + if (hsw_pre_update_disable_ips(old_crtc_state, new_crtc_state)) hsw_disable_ips(old_crtc_state); if (intel_fbc_pre_update(state, crtc)) - intel_wait_for_vblank(dev_priv, pipe); + intel_crtc_wait_for_next_vblank(crtc); if (!needs_async_flip_vtd_wa(old_crtc_state) && needs_async_flip_vtd_wa(new_crtc_state)) @@ -2090,7 +1471,7 @@ static void intel_pre_plane_update(struct intel_atomic_state *state, */ if (HAS_GMCH(dev_priv) && old_crtc_state->hw.active && new_crtc_state->disable_cxsr && intel_set_memory_cxsr(dev_priv, false)) - intel_wait_for_vblank(dev_priv, pipe); + intel_crtc_wait_for_next_vblank(crtc); /* * IVB workaround: must disable low power watermarks for at least @@ -2101,7 +1482,7 @@ static void intel_pre_plane_update(struct intel_atomic_state *state, */ if (old_crtc_state->hw.active && new_crtc_state->disable_lp_wm && ilk_disable_lp_wm(dev_priv)) - intel_wait_for_vblank(dev_priv, pipe); + intel_crtc_wait_for_next_vblank(crtc); /* * If we're doing a modeset we don't need to do any @@ -2165,7 +1546,7 @@ static void intel_crtc_disable_planes(struct intel_atomic_state *state, !(update_mask & BIT(plane->id))) continue; - intel_disable_plane(plane, new_crtc_state); + intel_plane_disable_arm(plane, new_crtc_state); if (old_plane_state->uapi.visible) fb_bits |= plane->frontbuffer_bit; @@ -2199,10 +1580,30 @@ intel_connector_primary_encoder(struct intel_connector *connector) static void intel_encoders_update_prepare(struct intel_atomic_state *state) { + struct drm_i915_private *i915 = to_i915(state->base.dev); + struct intel_crtc_state *new_crtc_state, *old_crtc_state; + struct intel_crtc *crtc; struct drm_connector_state *new_conn_state; struct drm_connector *connector; int i; + /* + * Make sure the DPLL state is up-to-date for fastset TypeC ports after non-blocking commits. + * TODO: Update the DPLL state for all cases in the encoder->update_prepare() hook. + */ + if (i915->dpll.mgr) { + for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { + if (intel_crtc_needs_modeset(new_crtc_state)) + continue; + + new_crtc_state->shared_dpll = old_crtc_state->shared_dpll; + new_crtc_state->dpll_hw_state = old_crtc_state->dpll_hw_state; + } + } + + if (!state->modeset) + return; + for_each_new_connector_in_state(&state->base, connector, new_conn_state, i) { struct intel_connector *intel_connector; @@ -2229,6 +1630,9 @@ static void intel_encoders_update_complete(struct intel_atomic_state *state) struct drm_connector *connector; int i; + if (!state->modeset) + return; + for_each_new_connector_in_state(&state->base, connector, new_conn_state, i) { struct intel_connector *intel_connector; @@ -2316,28 +1720,6 @@ static void intel_encoders_enable(struct intel_atomic_state *state, } } -static void intel_encoders_pre_disable(struct intel_atomic_state *state, - struct intel_crtc *crtc) -{ - const struct intel_crtc_state *old_crtc_state = - intel_atomic_get_old_crtc_state(state, crtc); - const struct drm_connector_state *old_conn_state; - struct drm_connector *conn; - int i; - - for_each_old_connector_in_state(&state->base, conn, old_conn_state, i) { - struct intel_encoder *encoder = - to_intel_encoder(old_conn_state->best_encoder); - - if (old_conn_state->crtc != &crtc->base) - continue; - - if (encoder->pre_disable) - encoder->pre_disable(state, encoder, old_crtc_state, - old_conn_state); - } -} - static void intel_encoders_disable(struct intel_atomic_state *state, struct intel_crtc *crtc) { @@ -2432,7 +1814,7 @@ static void intel_disable_primary_plane(const struct intel_crtc_state *crtc_stat struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct intel_plane *plane = to_intel_plane(crtc->base.primary); - plane->disable_plane(plane, crtc_state); + plane->disable_arm(plane, crtc_state); } static void ilk_crtc_enable(struct intel_atomic_state *state, @@ -2500,7 +1882,7 @@ static void ilk_crtc_enable(struct intel_atomic_state *state, intel_enable_transcoder(new_crtc_state); if (new_crtc_state->has_pch_encoder) - ilk_pch_enable(state, new_crtc_state); + ilk_pch_enable(state, crtc); intel_crtc_vblank_on(new_crtc_state); @@ -2516,8 +1898,8 @@ static void ilk_crtc_enable(struct intel_atomic_state *state, * in case there are more corner cases we don't know about. */ if (new_crtc_state->has_pch_encoder) { - intel_wait_for_vblank(dev_priv, pipe); - intel_wait_for_vblank(dev_priv, pipe); + intel_crtc_wait_for_next_vblank(crtc); + intel_crtc_wait_for_next_vblank(crtc); } intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, true); intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, true); @@ -2592,42 +1974,39 @@ static void hsw_set_frame_start_delay(const struct intel_crtc_state *crtc_state) static void icl_ddi_bigjoiner_pre_enable(struct intel_atomic_state *state, const struct intel_crtc_state *crtc_state) { - struct intel_crtc *master = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(master->base.dev); + struct drm_i915_private *dev_priv = to_i915(state->base.dev); struct intel_crtc_state *master_crtc_state; + struct intel_crtc *master_crtc; struct drm_connector_state *conn_state; struct drm_connector *conn; struct intel_encoder *encoder = NULL; int i; - if (crtc_state->bigjoiner_slave) - master = crtc_state->bigjoiner_linked_crtc; - - master_crtc_state = intel_atomic_get_new_crtc_state(state, master); + master_crtc = intel_master_crtc(crtc_state); + master_crtc_state = intel_atomic_get_new_crtc_state(state, master_crtc); for_each_new_connector_in_state(&state->base, conn, conn_state, i) { - if (conn_state->crtc != &master->base) + if (conn_state->crtc != &master_crtc->base) continue; encoder = to_intel_encoder(conn_state->best_encoder); break; } - if (!crtc_state->bigjoiner_slave) { - /* need to enable VDSC, which we skipped in pre-enable */ - intel_dsc_enable(encoder, crtc_state); - } else { - /* - * Enable sequence steps 1-7 on bigjoiner master - */ - intel_encoders_pre_pll_enable(state, master); - if (master_crtc_state->shared_dpll) - intel_enable_shared_dpll(master_crtc_state); - intel_encoders_pre_enable(state, master); + /* + * Enable sequence steps 1-7 on bigjoiner master + */ + if (crtc_state->bigjoiner_slave) + intel_encoders_pre_pll_enable(state, master_crtc); - /* and DSC on slave */ - intel_dsc_enable(NULL, crtc_state); - } + if (crtc_state->shared_dpll) + intel_enable_shared_dpll(crtc_state); + + if (crtc_state->bigjoiner_slave) + intel_encoders_pre_enable(state, master_crtc); + + /* need to enable VDSC, which we skipped in pre-enable */ + intel_dsc_enable(crtc_state); if (DISPLAY_VER(dev_priv) >= 13) intel_uncompressed_joiner_enable(crtc_state); @@ -2720,7 +2099,7 @@ static void hsw_crtc_enable(struct intel_atomic_state *state, intel_encoders_enable(state, crtc); if (psl_clkgate_wa) { - intel_wait_for_vblank(dev_priv, pipe); + intel_crtc_wait_for_next_vblank(crtc); glk_pipe_scaler_clock_gating_wa(dev_priv, pipe, false); } @@ -2728,8 +2107,12 @@ static void hsw_crtc_enable(struct intel_atomic_state *state, * to change the workaround. */ hsw_workaround_pipe = new_crtc_state->hsw_workaround_pipe; if (IS_HASWELL(dev_priv) && hsw_workaround_pipe != INVALID_PIPE) { - intel_wait_for_vblank(dev_priv, hsw_workaround_pipe); - intel_wait_for_vblank(dev_priv, hsw_workaround_pipe); + struct intel_crtc *wa_crtc; + + wa_crtc = intel_crtc_for_pipe(dev_priv, hsw_workaround_pipe); + + intel_crtc_wait_for_next_vblank(wa_crtc); + intel_crtc_wait_for_next_vblank(wa_crtc); } } @@ -2774,33 +2157,12 @@ static void ilk_crtc_disable(struct intel_atomic_state *state, ilk_pfit_disable(old_crtc_state); if (old_crtc_state->has_pch_encoder) - ilk_fdi_disable(crtc); + ilk_pch_disable(state, crtc); intel_encoders_post_disable(state, crtc); - if (old_crtc_state->has_pch_encoder) { - ilk_disable_pch_transcoder(dev_priv, pipe); - - if (HAS_PCH_CPT(dev_priv)) { - i915_reg_t reg; - u32 temp; - - /* disable TRANS_DP_CTL */ - reg = TRANS_DP_CTL(pipe); - temp = intel_de_read(dev_priv, reg); - temp &= ~(TRANS_DP_OUTPUT_ENABLE | - TRANS_DP_PORT_SEL_MASK); - temp |= TRANS_DP_PORT_SEL_NONE; - intel_de_write(dev_priv, reg, temp); - - /* disable DPLL_SEL */ - temp = intel_de_read(dev_priv, PCH_DPLL_SEL); - temp &= ~(TRANS_DPLL_ENABLE(pipe) | TRANS_DPLLB_SEL(pipe)); - intel_de_write(dev_priv, PCH_DPLL_SEL, temp); - } - - ilk_fdi_pll_disable(crtc); - } + if (old_crtc_state->has_pch_encoder) + ilk_pch_post_disable(state, crtc); intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, true); intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, true); @@ -2809,12 +2171,17 @@ static void ilk_crtc_disable(struct intel_atomic_state *state, static void hsw_crtc_disable(struct intel_atomic_state *state, struct intel_crtc *crtc) { + const struct intel_crtc_state *old_crtc_state = + intel_atomic_get_old_crtc_state(state, crtc); + /* * FIXME collapse everything to one hook. * Need care with mst->ddi interactions. */ - intel_encoders_disable(state, crtc); - intel_encoders_post_disable(state, crtc); + if (!old_crtc_state->bigjoiner_slave) { + intel_encoders_disable(state, crtc); + intel_encoders_post_disable(state, crtc); + } } static void i9xx_pfit_enable(const struct intel_crtc_state *crtc_state) @@ -3171,7 +2538,7 @@ static void i9xx_crtc_enable(struct intel_atomic_state *state, /* prevents spurious underruns */ if (DISPLAY_VER(dev_priv) == 2) - intel_wait_for_vblank(dev_priv, pipe); + intel_crtc_wait_for_next_vblank(crtc); } static void i9xx_pfit_disable(const struct intel_crtc_state *old_crtc_state) @@ -3202,7 +2569,7 @@ static void i9xx_crtc_disable(struct intel_atomic_state *state, * wait for planes to fully turn off before disabling the pipe. */ if (DISPLAY_VER(dev_priv) == 2) - intel_wait_for_vblank(dev_priv, pipe); + intel_crtc_wait_for_next_vblank(crtc); intel_encoders_disable(state, crtc); @@ -4306,414 +3673,6 @@ out: return ret; } -static void ilk_init_pch_refclk(struct drm_i915_private *dev_priv) -{ - struct intel_encoder *encoder; - int i; - u32 val, final; - bool has_lvds = false; - bool has_cpu_edp = false; - bool has_panel = false; - bool has_ck505 = false; - bool can_ssc = false; - bool using_ssc_source = false; - - /* We need to take the global config into account */ - for_each_intel_encoder(&dev_priv->drm, encoder) { - switch (encoder->type) { - case INTEL_OUTPUT_LVDS: - has_panel = true; - has_lvds = true; - break; - case INTEL_OUTPUT_EDP: - has_panel = true; - if (encoder->port == PORT_A) - has_cpu_edp = true; - break; - default: - break; - } - } - - if (HAS_PCH_IBX(dev_priv)) { - has_ck505 = dev_priv->vbt.display_clock_mode; - can_ssc = has_ck505; - } else { - has_ck505 = false; - can_ssc = true; - } - - /* Check if any DPLLs are using the SSC source */ - for (i = 0; i < dev_priv->dpll.num_shared_dpll; i++) { - u32 temp = intel_de_read(dev_priv, PCH_DPLL(i)); - - if (!(temp & DPLL_VCO_ENABLE)) - continue; - - if ((temp & PLL_REF_INPUT_MASK) == - PLLB_REF_INPUT_SPREADSPECTRUMIN) { - using_ssc_source = true; - break; - } - } - - drm_dbg_kms(&dev_priv->drm, - "has_panel %d has_lvds %d has_ck505 %d using_ssc_source %d\n", - has_panel, has_lvds, has_ck505, using_ssc_source); - - /* Ironlake: try to setup display ref clock before DPLL - * enabling. This is only under driver's control after - * PCH B stepping, previous chipset stepping should be - * ignoring this setting. - */ - val = intel_de_read(dev_priv, PCH_DREF_CONTROL); - - /* As we must carefully and slowly disable/enable each source in turn, - * compute the final state we want first and check if we need to - * make any changes at all. - */ - final = val; - final &= ~DREF_NONSPREAD_SOURCE_MASK; - if (has_ck505) - final |= DREF_NONSPREAD_CK505_ENABLE; - else - final |= DREF_NONSPREAD_SOURCE_ENABLE; - - final &= ~DREF_SSC_SOURCE_MASK; - final &= ~DREF_CPU_SOURCE_OUTPUT_MASK; - final &= ~DREF_SSC1_ENABLE; - - if (has_panel) { - final |= DREF_SSC_SOURCE_ENABLE; - - if (intel_panel_use_ssc(dev_priv) && can_ssc) - final |= DREF_SSC1_ENABLE; - - if (has_cpu_edp) { - if (intel_panel_use_ssc(dev_priv) && can_ssc) - final |= DREF_CPU_SOURCE_OUTPUT_DOWNSPREAD; - else - final |= DREF_CPU_SOURCE_OUTPUT_NONSPREAD; - } else - final |= DREF_CPU_SOURCE_OUTPUT_DISABLE; - } else if (using_ssc_source) { - final |= DREF_SSC_SOURCE_ENABLE; - final |= DREF_SSC1_ENABLE; - } - - if (final == val) - return; - - /* Always enable nonspread source */ - val &= ~DREF_NONSPREAD_SOURCE_MASK; - - if (has_ck505) - val |= DREF_NONSPREAD_CK505_ENABLE; - else - val |= DREF_NONSPREAD_SOURCE_ENABLE; - - if (has_panel) { - val &= ~DREF_SSC_SOURCE_MASK; - val |= DREF_SSC_SOURCE_ENABLE; - - /* SSC must be turned on before enabling the CPU output */ - if (intel_panel_use_ssc(dev_priv) && can_ssc) { - drm_dbg_kms(&dev_priv->drm, "Using SSC on panel\n"); - val |= DREF_SSC1_ENABLE; - } else - val &= ~DREF_SSC1_ENABLE; - - /* Get SSC going before enabling the outputs */ - intel_de_write(dev_priv, PCH_DREF_CONTROL, val); - intel_de_posting_read(dev_priv, PCH_DREF_CONTROL); - udelay(200); - - val &= ~DREF_CPU_SOURCE_OUTPUT_MASK; - - /* Enable CPU source on CPU attached eDP */ - if (has_cpu_edp) { - if (intel_panel_use_ssc(dev_priv) && can_ssc) { - drm_dbg_kms(&dev_priv->drm, - "Using SSC on eDP\n"); - val |= DREF_CPU_SOURCE_OUTPUT_DOWNSPREAD; - } else - val |= DREF_CPU_SOURCE_OUTPUT_NONSPREAD; - } else - val |= DREF_CPU_SOURCE_OUTPUT_DISABLE; - - intel_de_write(dev_priv, PCH_DREF_CONTROL, val); - intel_de_posting_read(dev_priv, PCH_DREF_CONTROL); - udelay(200); - } else { - drm_dbg_kms(&dev_priv->drm, "Disabling CPU source output\n"); - - val &= ~DREF_CPU_SOURCE_OUTPUT_MASK; - - /* Turn off CPU output */ - val |= DREF_CPU_SOURCE_OUTPUT_DISABLE; - - intel_de_write(dev_priv, PCH_DREF_CONTROL, val); - intel_de_posting_read(dev_priv, PCH_DREF_CONTROL); - udelay(200); - - if (!using_ssc_source) { - drm_dbg_kms(&dev_priv->drm, "Disabling SSC source\n"); - - /* Turn off the SSC source */ - val &= ~DREF_SSC_SOURCE_MASK; - val |= DREF_SSC_SOURCE_DISABLE; - - /* Turn off SSC1 */ - val &= ~DREF_SSC1_ENABLE; - - intel_de_write(dev_priv, PCH_DREF_CONTROL, val); - intel_de_posting_read(dev_priv, PCH_DREF_CONTROL); - udelay(200); - } - } - - BUG_ON(val != final); -} - -/* Implements 3 different sequences from BSpec chapter "Display iCLK - * Programming" based on the parameters passed: - * - Sequence to enable CLKOUT_DP - * - Sequence to enable CLKOUT_DP without spread - * - Sequence to enable CLKOUT_DP for FDI usage and configure PCH FDI I/O - */ -static void lpt_enable_clkout_dp(struct drm_i915_private *dev_priv, - bool with_spread, bool with_fdi) -{ - u32 reg, tmp; - - if (drm_WARN(&dev_priv->drm, with_fdi && !with_spread, - "FDI requires downspread\n")) - with_spread = true; - if (drm_WARN(&dev_priv->drm, HAS_PCH_LPT_LP(dev_priv) && - with_fdi, "LP PCH doesn't have FDI\n")) - with_fdi = false; - - mutex_lock(&dev_priv->sb_lock); - - tmp = intel_sbi_read(dev_priv, SBI_SSCCTL, SBI_ICLK); - tmp &= ~SBI_SSCCTL_DISABLE; - tmp |= SBI_SSCCTL_PATHALT; - intel_sbi_write(dev_priv, SBI_SSCCTL, tmp, SBI_ICLK); - - udelay(24); - - if (with_spread) { - tmp = intel_sbi_read(dev_priv, SBI_SSCCTL, SBI_ICLK); - tmp &= ~SBI_SSCCTL_PATHALT; - intel_sbi_write(dev_priv, SBI_SSCCTL, tmp, SBI_ICLK); - - if (with_fdi) - lpt_fdi_program_mphy(dev_priv); - } - - reg = HAS_PCH_LPT_LP(dev_priv) ? SBI_GEN0 : SBI_DBUFF0; - tmp = intel_sbi_read(dev_priv, reg, SBI_ICLK); - tmp |= SBI_GEN0_CFG_BUFFENABLE_DISABLE; - intel_sbi_write(dev_priv, reg, tmp, SBI_ICLK); - - mutex_unlock(&dev_priv->sb_lock); -} - -/* Sequence to disable CLKOUT_DP */ -void lpt_disable_clkout_dp(struct drm_i915_private *dev_priv) -{ - u32 reg, tmp; - - mutex_lock(&dev_priv->sb_lock); - - reg = HAS_PCH_LPT_LP(dev_priv) ? SBI_GEN0 : SBI_DBUFF0; - tmp = intel_sbi_read(dev_priv, reg, SBI_ICLK); - tmp &= ~SBI_GEN0_CFG_BUFFENABLE_DISABLE; - intel_sbi_write(dev_priv, reg, tmp, SBI_ICLK); - - tmp = intel_sbi_read(dev_priv, SBI_SSCCTL, SBI_ICLK); - if (!(tmp & SBI_SSCCTL_DISABLE)) { - if (!(tmp & SBI_SSCCTL_PATHALT)) { - tmp |= SBI_SSCCTL_PATHALT; - intel_sbi_write(dev_priv, SBI_SSCCTL, tmp, SBI_ICLK); - udelay(32); - } - tmp |= SBI_SSCCTL_DISABLE; - intel_sbi_write(dev_priv, SBI_SSCCTL, tmp, SBI_ICLK); - } - - mutex_unlock(&dev_priv->sb_lock); -} - -#define BEND_IDX(steps) ((50 + (steps)) / 5) - -static const u16 sscdivintphase[] = { - [BEND_IDX( 50)] = 0x3B23, - [BEND_IDX( 45)] = 0x3B23, - [BEND_IDX( 40)] = 0x3C23, - [BEND_IDX( 35)] = 0x3C23, - [BEND_IDX( 30)] = 0x3D23, - [BEND_IDX( 25)] = 0x3D23, - [BEND_IDX( 20)] = 0x3E23, - [BEND_IDX( 15)] = 0x3E23, - [BEND_IDX( 10)] = 0x3F23, - [BEND_IDX( 5)] = 0x3F23, - [BEND_IDX( 0)] = 0x0025, - [BEND_IDX( -5)] = 0x0025, - [BEND_IDX(-10)] = 0x0125, - [BEND_IDX(-15)] = 0x0125, - [BEND_IDX(-20)] = 0x0225, - [BEND_IDX(-25)] = 0x0225, - [BEND_IDX(-30)] = 0x0325, - [BEND_IDX(-35)] = 0x0325, - [BEND_IDX(-40)] = 0x0425, - [BEND_IDX(-45)] = 0x0425, - [BEND_IDX(-50)] = 0x0525, -}; - -/* - * Bend CLKOUT_DP - * steps -50 to 50 inclusive, in steps of 5 - * < 0 slow down the clock, > 0 speed up the clock, 0 == no bend (135MHz) - * change in clock period = -(steps / 10) * 5.787 ps - */ -static void lpt_bend_clkout_dp(struct drm_i915_private *dev_priv, int steps) -{ - u32 tmp; - int idx = BEND_IDX(steps); - - if (drm_WARN_ON(&dev_priv->drm, steps % 5 != 0)) - return; - - if (drm_WARN_ON(&dev_priv->drm, idx >= ARRAY_SIZE(sscdivintphase))) - return; - - mutex_lock(&dev_priv->sb_lock); - - if (steps % 10 != 0) - tmp = 0xAAAAAAAB; - else - tmp = 0x00000000; - intel_sbi_write(dev_priv, SBI_SSCDITHPHASE, tmp, SBI_ICLK); - - tmp = intel_sbi_read(dev_priv, SBI_SSCDIVINTPHASE, SBI_ICLK); - tmp &= 0xffff0000; - tmp |= sscdivintphase[idx]; - intel_sbi_write(dev_priv, SBI_SSCDIVINTPHASE, tmp, SBI_ICLK); - - mutex_unlock(&dev_priv->sb_lock); -} - -#undef BEND_IDX - -static bool spll_uses_pch_ssc(struct drm_i915_private *dev_priv) -{ - u32 fuse_strap = intel_de_read(dev_priv, FUSE_STRAP); - u32 ctl = intel_de_read(dev_priv, SPLL_CTL); - - if ((ctl & SPLL_PLL_ENABLE) == 0) - return false; - - if ((ctl & SPLL_REF_MASK) == SPLL_REF_MUXED_SSC && - (fuse_strap & HSW_CPU_SSC_ENABLE) == 0) - return true; - - if (IS_BROADWELL(dev_priv) && - (ctl & SPLL_REF_MASK) == SPLL_REF_PCH_SSC_BDW) - return true; - - return false; -} - -static bool wrpll_uses_pch_ssc(struct drm_i915_private *dev_priv, - enum intel_dpll_id id) -{ - u32 fuse_strap = intel_de_read(dev_priv, FUSE_STRAP); - u32 ctl = intel_de_read(dev_priv, WRPLL_CTL(id)); - - if ((ctl & WRPLL_PLL_ENABLE) == 0) - return false; - - if ((ctl & WRPLL_REF_MASK) == WRPLL_REF_PCH_SSC) - return true; - - if ((IS_BROADWELL(dev_priv) || IS_HSW_ULT(dev_priv)) && - (ctl & WRPLL_REF_MASK) == WRPLL_REF_MUXED_SSC_BDW && - (fuse_strap & HSW_CPU_SSC_ENABLE) == 0) - return true; - - return false; -} - -static void lpt_init_pch_refclk(struct drm_i915_private *dev_priv) -{ - struct intel_encoder *encoder; - bool has_fdi = false; - - for_each_intel_encoder(&dev_priv->drm, encoder) { - switch (encoder->type) { - case INTEL_OUTPUT_ANALOG: - has_fdi = true; - break; - default: - break; - } - } - - /* - * The BIOS may have decided to use the PCH SSC - * reference so we must not disable it until the - * relevant PLLs have stopped relying on it. We'll - * just leave the PCH SSC reference enabled in case - * any active PLL is using it. It will get disabled - * after runtime suspend if we don't have FDI. - * - * TODO: Move the whole reference clock handling - * to the modeset sequence proper so that we can - * actually enable/disable/reconfigure these things - * safely. To do that we need to introduce a real - * clock hierarchy. That would also allow us to do - * clock bending finally. - */ - dev_priv->pch_ssc_use = 0; - - if (spll_uses_pch_ssc(dev_priv)) { - drm_dbg_kms(&dev_priv->drm, "SPLL using PCH SSC\n"); - dev_priv->pch_ssc_use |= BIT(DPLL_ID_SPLL); - } - - if (wrpll_uses_pch_ssc(dev_priv, DPLL_ID_WRPLL1)) { - drm_dbg_kms(&dev_priv->drm, "WRPLL1 using PCH SSC\n"); - dev_priv->pch_ssc_use |= BIT(DPLL_ID_WRPLL1); - } - - if (wrpll_uses_pch_ssc(dev_priv, DPLL_ID_WRPLL2)) { - drm_dbg_kms(&dev_priv->drm, "WRPLL2 using PCH SSC\n"); - dev_priv->pch_ssc_use |= BIT(DPLL_ID_WRPLL2); - } - - if (dev_priv->pch_ssc_use) - return; - - if (has_fdi) { - lpt_bend_clkout_dp(dev_priv, 0); - lpt_enable_clkout_dp(dev_priv, true, true); - } else { - lpt_disable_clkout_dp(dev_priv); - } -} - -/* - * Initialize reference clocks when the driver loads - */ -void intel_init_pch_refclk(struct drm_i915_private *dev_priv) -{ - if (HAS_PCH_IBX(dev_priv) || HAS_PCH_CPT(dev_priv)) - ilk_init_pch_refclk(dev_priv); - else if (HAS_PCH_LPT(dev_priv)) - lpt_init_pch_refclk(dev_priv); -} - static void ilk_set_pipeconf(const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); @@ -4978,8 +3937,8 @@ void intel_dp_get_m_n(struct intel_crtc *crtc, &pipe_config->dp_m2_n2); } -static void ilk_get_fdi_m_n_config(struct intel_crtc *crtc, - struct intel_crtc_state *pipe_config) +void ilk_get_fdi_m_n_config(struct intel_crtc *crtc, + struct intel_crtc_state *pipe_config) { intel_cpu_transcoder_get_m_n(crtc, pipe_config->cpu_transcoder, &pipe_config->fdi_m_n, NULL); @@ -5116,50 +4075,9 @@ static bool ilk_get_pipe_config(struct intel_crtc *crtc, i9xx_get_pipe_color_config(pipe_config); intel_color_get_config(pipe_config); - if (intel_de_read(dev_priv, PCH_TRANSCONF(crtc->pipe)) & TRANS_ENABLE) { - struct intel_shared_dpll *pll; - enum intel_dpll_id pll_id; - bool pll_active; - - pipe_config->has_pch_encoder = true; - - tmp = intel_de_read(dev_priv, FDI_RX_CTL(crtc->pipe)); - pipe_config->fdi_lanes = ((FDI_DP_PORT_WIDTH_MASK & tmp) >> - FDI_DP_PORT_WIDTH_SHIFT) + 1; - - ilk_get_fdi_m_n_config(crtc, pipe_config); - - if (HAS_PCH_IBX(dev_priv)) { - /* - * The pipe->pch transcoder and pch transcoder->pll - * mapping is fixed. - */ - pll_id = (enum intel_dpll_id) crtc->pipe; - } else { - tmp = intel_de_read(dev_priv, PCH_DPLL_SEL); - if (tmp & TRANS_DPLLB_SEL(crtc->pipe)) - pll_id = DPLL_ID_PCH_PLL_B; - else - pll_id= DPLL_ID_PCH_PLL_A; - } - - pipe_config->shared_dpll = - intel_get_shared_dpll_by_id(dev_priv, pll_id); - pll = pipe_config->shared_dpll; - - pll_active = intel_dpll_get_hw_state(dev_priv, pll, - &pipe_config->dpll_hw_state); - drm_WARN_ON(dev, !pll_active); - - tmp = pipe_config->dpll_hw_state.dpll; - pipe_config->pixel_multiplier = - ((tmp & PLL_REF_SDVO_HDMI_MULTIPLIER_MASK) - >> PLL_REF_SDVO_HDMI_MULTIPLIER_SHIFT) + 1; + pipe_config->pixel_multiplier = 1; - ilk_pch_clock_get(crtc, pipe_config); - } else { - pipe_config->pixel_multiplier = 1; - } + ilk_pch_get_config(pipe_config); intel_get_transcoder_timings(crtc, pipe_config); intel_get_pipe_src_size(crtc, pipe_config); @@ -5174,6 +4092,16 @@ out: return ret; } +static u8 bigjoiner_pipes(struct drm_i915_private *i915) +{ + if (DISPLAY_VER(i915) >= 12) + return BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D); + else if (DISPLAY_VER(i915) >= 11) + return BIT(PIPE_B) | BIT(PIPE_C); + else + return 0; +} + static bool transcoder_ddi_func_is_enabled(struct drm_i915_private *dev_priv, enum transcoder cpu_transcoder) { @@ -5189,6 +4117,54 @@ static bool transcoder_ddi_func_is_enabled(struct drm_i915_private *dev_priv, return tmp & TRANS_DDI_FUNC_ENABLE; } +static u8 enabled_bigjoiner_pipes(struct drm_i915_private *dev_priv) +{ + u8 master_pipes = 0, slave_pipes = 0; + struct intel_crtc *crtc; + + for_each_intel_crtc(&dev_priv->drm, crtc) { + enum intel_display_power_domain power_domain; + enum pipe pipe = crtc->pipe; + intel_wakeref_t wakeref; + + if ((bigjoiner_pipes(dev_priv) & BIT(pipe)) == 0) + continue; + + power_domain = intel_dsc_power_domain(crtc, (enum transcoder) pipe); + with_intel_display_power_if_enabled(dev_priv, power_domain, wakeref) { + u32 tmp = intel_de_read(dev_priv, ICL_PIPE_DSS_CTL1(pipe)); + + if (!(tmp & BIG_JOINER_ENABLE)) + continue; + + if (tmp & MASTER_BIG_JOINER_ENABLE) + master_pipes |= BIT(pipe); + else + slave_pipes |= BIT(pipe); + } + + if (DISPLAY_VER(dev_priv) < 13) + continue; + + power_domain = POWER_DOMAIN_PIPE(pipe); + with_intel_display_power_if_enabled(dev_priv, power_domain, wakeref) { + u32 tmp = intel_de_read(dev_priv, ICL_PIPE_DSS_CTL1(pipe)); + + if (tmp & UNCOMPRESSED_JOINER_MASTER) + master_pipes |= BIT(pipe); + if (tmp & UNCOMPRESSED_JOINER_SLAVE) + slave_pipes |= BIT(pipe); + } + } + + /* Bigjoiner pipes should always be consecutive master and slave */ + drm_WARN(&dev_priv->drm, slave_pipes != master_pipes << 1, + "Bigjoiner misconfigured (master pipes 0x%x, slave pipes 0x%x)\n", + master_pipes, slave_pipes); + + return slave_pipes; +} + static u8 hsw_panel_transcoders(struct drm_i915_private *i915) { u8 panel_transcoder_mask = BIT(TRANSCODER_EDP); @@ -5250,10 +4226,18 @@ static u8 hsw_enabled_transcoders(struct intel_crtc *crtc) enabled_transcoders |= BIT(cpu_transcoder); } + /* single pipe or bigjoiner master */ cpu_transcoder = (enum transcoder) crtc->pipe; if (transcoder_ddi_func_is_enabled(dev_priv, cpu_transcoder)) enabled_transcoders |= BIT(cpu_transcoder); + /* bigjoiner slave -> consider the master pipe's transcoder as well */ + if (enabled_bigjoiner_pipes(dev_priv) & BIT(crtc->pipe)) { + cpu_transcoder = (enum transcoder) crtc->pipe - 1; + if (transcoder_ddi_func_is_enabled(dev_priv, cpu_transcoder)) + enabled_transcoders |= BIT(cpu_transcoder); + } + return enabled_transcoders; } @@ -5374,45 +4358,6 @@ static bool bxt_get_dsi_transcoder_state(struct intel_crtc *crtc, return transcoder_is_dsi(pipe_config->cpu_transcoder); } -static void hsw_get_ddi_port_state(struct intel_crtc *crtc, - struct intel_crtc_state *pipe_config) -{ - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - enum transcoder cpu_transcoder = pipe_config->cpu_transcoder; - enum port port; - u32 tmp; - - if (transcoder_is_dsi(cpu_transcoder)) { - port = (cpu_transcoder == TRANSCODER_DSI_A) ? - PORT_A : PORT_B; - } else { - tmp = intel_de_read(dev_priv, - TRANS_DDI_FUNC_CTL(cpu_transcoder)); - if (!(tmp & TRANS_DDI_FUNC_ENABLE)) - return; - if (DISPLAY_VER(dev_priv) >= 12) - port = TGL_TRANS_DDI_FUNC_CTL_VAL_TO_PORT(tmp); - else - port = TRANS_DDI_FUNC_CTL_VAL_TO_PORT(tmp); - } - - /* - * Haswell has only FDI/PCH transcoder A. It is which is connected to - * DDI E. So just check whether this pipe is wired to DDI E and whether - * the PCH transcoder is on. - */ - if (DISPLAY_VER(dev_priv) < 9 && - (port == PORT_E) && intel_de_read(dev_priv, LPT_TRANSCONF) & TRANS_ENABLE) { - pipe_config->has_pch_encoder = true; - - tmp = intel_de_read(dev_priv, FDI_RX_CTL(PIPE_A)); - pipe_config->fdi_lanes = ((FDI_DP_PORT_WIDTH_MASK & tmp) >> - FDI_DP_PORT_WIDTH_SHIFT) + 1; - - ilk_get_fdi_m_n_config(crtc, pipe_config); - } -} - static bool hsw_get_pipe_config(struct intel_crtc *crtc, struct intel_crtc_state *pipe_config) { @@ -5439,21 +4384,12 @@ static bool hsw_get_pipe_config(struct intel_crtc *crtc, if (DISPLAY_VER(dev_priv) >= 13 && !pipe_config->dsc.compression_enable) intel_uncompressed_joiner_get_config(pipe_config); - if (!active) { - /* bigjoiner slave doesn't enable transcoder */ - if (!pipe_config->bigjoiner_slave) - goto out; - - active = true; - pipe_config->pixel_multiplier = 1; + if (!active) + goto out; - /* we cannot read out most state, so don't bother.. */ - pipe_config->quirks |= PIPE_CONFIG_QUIRK_BIGJOINER_SLAVE; - } else if (!transcoder_is_dsi(pipe_config->cpu_transcoder) || - DISPLAY_VER(dev_priv) >= 11) { - hsw_get_ddi_port_state(crtc, pipe_config); + if (!transcoder_is_dsi(pipe_config->cpu_transcoder) || + DISPLAY_VER(dev_priv) >= 11) intel_get_transcoder_timings(crtc, pipe_config); - } if (HAS_VRR(dev_priv) && !transcoder_is_dsi(pipe_config->cpu_transcoder)) intel_vrr_get_config(crtc, pipe_config); @@ -5521,10 +4457,7 @@ static bool hsw_get_pipe_config(struct intel_crtc *crtc, } } - if (pipe_config->bigjoiner_slave) { - /* Cannot be read out as a slave, set to 0. */ - pipe_config->pixel_multiplier = 0; - } else if (pipe_config->cpu_transcoder != TRANSCODER_EDP && + if (pipe_config->cpu_transcoder != TRANSCODER_EDP && !transcoder_is_dsi(pipe_config->cpu_transcoder)) { pipe_config->pixel_multiplier = intel_de_read(dev_priv, @@ -5721,7 +4654,8 @@ found: drm_atomic_state_put(state); /* let the connector get through one full cycle before testing */ - intel_wait_for_vblank(dev_priv, crtc->pipe); + intel_crtc_wait_for_next_vblank(crtc); + return true; fail: @@ -5782,8 +4716,8 @@ static int i9xx_pll_refclk(struct drm_device *dev, } /* Returns the clock of the currently programmed mode of the given pipe. */ -static void i9xx_crtc_clock_get(struct intel_crtc *crtc, - struct intel_crtc_state *pipe_config) +void i9xx_crtc_clock_get(struct intel_crtc *crtc, + struct intel_crtc_state *pipe_config) { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = to_i915(dev); @@ -5893,24 +4827,6 @@ int intel_dotclock_calculate(int link_freq, return div_u64(mul_u32_u32(m_n->link_m, link_freq), m_n->link_n); } -static void ilk_pch_clock_get(struct intel_crtc *crtc, - struct intel_crtc_state *pipe_config) -{ - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - - /* read out port_clock from the DPLL */ - i9xx_crtc_clock_get(crtc, pipe_config); - - /* - * In case there is an active pipe without active ports, - * we may need some idea for the dotclock anyway. - * Calculate one based on the FDI configuration. - */ - pipe_config->hw.adjusted_mode.crtc_clock = - intel_dotclock_calculate(intel_fdi_link_freq(dev_priv, pipe_config), - &pipe_config->fdi_m_n); -} - /* Returns the currently programmed mode of the given encoder. */ struct drm_display_mode * intel_encoder_current_mode(struct intel_encoder *encoder) @@ -5924,7 +4840,7 @@ intel_encoder_current_mode(struct intel_encoder *encoder) if (!encoder->get_hw_state(encoder, &pipe)) return NULL; - crtc = intel_get_crtc_for_pipe(dev_priv, pipe); + crtc = intel_crtc_for_pipe(dev_priv, pipe); mode = kzalloc(sizeof(*mode), GFP_KERNEL); if (!mode) @@ -6245,6 +5161,7 @@ static int icl_check_nv12_planes(struct intel_crtc_state *crtc_state) linked_state->ctl = plane_state->ctl | PLANE_CTL_YUV420_Y_PLANE; linked_state->color_ctl = plane_state->color_ctl; linked_state->view = plane_state->view; + linked_state->decrypt = plane_state->decrypt; intel_plane_copy_hw_state(linked_state, plane_state); linked_state->uapi.src = plane_state->uapi.src; @@ -6252,13 +5169,13 @@ static int icl_check_nv12_planes(struct intel_crtc_state *crtc_state) if (icl_is_hdr_plane(dev_priv, plane->id)) { if (linked->id == PLANE_SPRITE5) - plane_state->cus_ctl |= PLANE_CUS_PLANE_7; + plane_state->cus_ctl |= PLANE_CUS_Y_PLANE_7_ICL; else if (linked->id == PLANE_SPRITE4) - plane_state->cus_ctl |= PLANE_CUS_PLANE_6; + plane_state->cus_ctl |= PLANE_CUS_Y_PLANE_6_ICL; else if (linked->id == PLANE_SPRITE3) - plane_state->cus_ctl |= PLANE_CUS_PLANE_5_RKL; + plane_state->cus_ctl |= PLANE_CUS_Y_PLANE_5_RKL; else if (linked->id == PLANE_SPRITE2) - plane_state->cus_ctl |= PLANE_CUS_PLANE_4_RKL; + plane_state->cus_ctl |= PLANE_CUS_Y_PLANE_4_RKL; else MISSING_CASE(linked->id); } @@ -6371,8 +5288,6 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state, crtc_state->update_wm_post = true; if (mode_changed && crtc_state->hw.enable && - dev_priv->dpll_funcs && - !crtc_state->bigjoiner_slave && !drm_WARN_ON(&dev_priv->drm, crtc_state->shared_dpll)) { ret = dev_priv->dpll_funcs->crtc_compute_clock(crtc_state); if (ret) @@ -6928,18 +5843,15 @@ static void intel_crtc_copy_uapi_to_hw_state_nomodeset(struct intel_atomic_state *state, struct intel_crtc_state *crtc_state) { - const struct intel_crtc_state *from_crtc_state = crtc_state; - - if (crtc_state->bigjoiner_slave) { - from_crtc_state = intel_atomic_get_new_crtc_state(state, - crtc_state->bigjoiner_linked_crtc); + const struct intel_crtc_state *master_crtc_state; + struct intel_crtc *master_crtc; - /* No need to copy state if the master state is unchanged */ - if (!from_crtc_state) - return; - } + master_crtc = intel_master_crtc(crtc_state); + master_crtc_state = intel_atomic_get_new_crtc_state(state, master_crtc); - intel_crtc_copy_color_blobs(crtc_state, from_crtc_state); + /* No need to copy state if the master state is unchanged */ + if (master_crtc_state) + intel_crtc_copy_color_blobs(crtc_state, master_crtc_state); } static void @@ -6982,7 +5894,6 @@ copy_bigjoiner_crtc_state(struct intel_crtc_state *crtc_state, const struct intel_crtc_state *from_crtc_state) { struct intel_crtc_state *saved_state; - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); saved_state = kmemdup(from_crtc_state, sizeof(*saved_state), GFP_KERNEL); if (!saved_state) @@ -7012,8 +5923,8 @@ copy_bigjoiner_crtc_state(struct intel_crtc_state *crtc_state, crtc_state->nv12_planes = crtc_state->c8_planes = crtc_state->update_planes = 0; crtc_state->bigjoiner_linked_crtc = to_intel_crtc(from_crtc_state->uapi.crtc); crtc_state->bigjoiner_slave = true; - crtc_state->cpu_transcoder = (enum transcoder)crtc->pipe; - crtc_state->has_audio = false; + crtc_state->cpu_transcoder = from_crtc_state->cpu_transcoder; + crtc_state->has_audio = from_crtc_state->has_audio; return 0; } @@ -7609,51 +6520,48 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, PIPE_CONF_CHECK_X(output_types); - /* FIXME do the readout properly and get rid of this quirk */ - if (!PIPE_CONF_QUIRK(PIPE_CONFIG_QUIRK_BIGJOINER_SLAVE)) { - PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_hdisplay); - PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_htotal); - PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_hblank_start); - PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_hblank_end); - PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_hsync_start); - PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_hsync_end); - - PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_vdisplay); - PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_vtotal); - PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_vblank_start); - PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_vblank_end); - PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_vsync_start); - PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_vsync_end); - - PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_hdisplay); - PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_htotal); - PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_hblank_start); - PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_hblank_end); - PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_hsync_start); - PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_hsync_end); - - PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vdisplay); - PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vtotal); - PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vblank_start); - PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vblank_end); - PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vsync_start); - PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vsync_end); - - PIPE_CONF_CHECK_I(pixel_multiplier); - + PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_hdisplay); + PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_htotal); + PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_hblank_start); + PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_hblank_end); + PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_hsync_start); + PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_hsync_end); + + PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_vdisplay); + PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_vtotal); + PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_vblank_start); + PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_vblank_end); + PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_vsync_start); + PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_vsync_end); + + PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_hdisplay); + PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_htotal); + PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_hblank_start); + PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_hblank_end); + PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_hsync_start); + PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_hsync_end); + + PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vdisplay); + PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vtotal); + PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vblank_start); + PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vblank_end); + PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vsync_start); + PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vsync_end); + + PIPE_CONF_CHECK_I(pixel_multiplier); + + PIPE_CONF_CHECK_FLAGS(hw.adjusted_mode.flags, + DRM_MODE_FLAG_INTERLACE); + + if (!PIPE_CONF_QUIRK(PIPE_CONFIG_QUIRK_MODE_SYNC_FLAGS)) { PIPE_CONF_CHECK_FLAGS(hw.adjusted_mode.flags, - DRM_MODE_FLAG_INTERLACE); - - if (!PIPE_CONF_QUIRK(PIPE_CONFIG_QUIRK_MODE_SYNC_FLAGS)) { - PIPE_CONF_CHECK_FLAGS(hw.adjusted_mode.flags, - DRM_MODE_FLAG_PHSYNC); - PIPE_CONF_CHECK_FLAGS(hw.adjusted_mode.flags, - DRM_MODE_FLAG_NHSYNC); - PIPE_CONF_CHECK_FLAGS(hw.adjusted_mode.flags, - DRM_MODE_FLAG_PVSYNC); - PIPE_CONF_CHECK_FLAGS(hw.adjusted_mode.flags, - DRM_MODE_FLAG_NVSYNC); - } + DRM_MODE_FLAG_PHSYNC); + PIPE_CONF_CHECK_FLAGS(hw.adjusted_mode.flags, + DRM_MODE_FLAG_NHSYNC); + PIPE_CONF_CHECK_FLAGS(hw.adjusted_mode.flags, + DRM_MODE_FLAG_PVSYNC); + PIPE_CONF_CHECK_FLAGS(hw.adjusted_mode.flags, + DRM_MODE_FLAG_NVSYNC); } PIPE_CONF_CHECK_I(output_format); @@ -7665,9 +6573,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, PIPE_CONF_CHECK_BOOL(hdmi_scrambling); PIPE_CONF_CHECK_BOOL(hdmi_high_tmds_clock_ratio); PIPE_CONF_CHECK_BOOL(has_infoframe); - /* FIXME do the readout properly and get rid of this quirk */ - if (!PIPE_CONF_QUIRK(PIPE_CONFIG_QUIRK_BIGJOINER_SLAVE)) - PIPE_CONF_CHECK_BOOL(fec_enable); + PIPE_CONF_CHECK_BOOL(fec_enable); PIPE_CONF_CHECK_BOOL_INCOMPLETE(has_audio); @@ -7696,9 +6602,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, } PIPE_CONF_CHECK_I(scaler_state.scaler_id); - /* FIXME do the readout properly and get rid of this quirk */ - if (!PIPE_CONF_QUIRK(PIPE_CONFIG_QUIRK_BIGJOINER_SLAVE)) - PIPE_CONF_CHECK_CLOCK_FUZZY(pixel_rate); + PIPE_CONF_CHECK_CLOCK_FUZZY(pixel_rate); PIPE_CONF_CHECK_X(gamma_mode); if (IS_CHERRYVIEW(dev_priv)) @@ -7725,11 +6629,9 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, PIPE_CONF_CHECK_BOOL(double_wide); - if (dev_priv->dpll.mgr) + if (dev_priv->dpll.mgr) { PIPE_CONF_CHECK_P(shared_dpll); - /* FIXME do the readout properly and get rid of this quirk */ - if (dev_priv->dpll.mgr && !PIPE_CONF_QUIRK(PIPE_CONFIG_QUIRK_BIGJOINER_SLAVE)) { PIPE_CONF_CHECK_X(dpll_hw_state.dpll); PIPE_CONF_CHECK_X(dpll_hw_state.dpll_md); PIPE_CONF_CHECK_X(dpll_hw_state.fp0); @@ -7763,19 +6665,17 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, PIPE_CONF_CHECK_X(dpll_hw_state.mg_pll_tdc_coldst_bias); } - if (!PIPE_CONF_QUIRK(PIPE_CONFIG_QUIRK_BIGJOINER_SLAVE)) { - PIPE_CONF_CHECK_X(dsi_pll.ctrl); - PIPE_CONF_CHECK_X(dsi_pll.div); + PIPE_CONF_CHECK_X(dsi_pll.ctrl); + PIPE_CONF_CHECK_X(dsi_pll.div); - if (IS_G4X(dev_priv) || DISPLAY_VER(dev_priv) >= 5) - PIPE_CONF_CHECK_I(pipe_bpp); + if (IS_G4X(dev_priv) || DISPLAY_VER(dev_priv) >= 5) + PIPE_CONF_CHECK_I(pipe_bpp); - PIPE_CONF_CHECK_CLOCK_FUZZY(hw.pipe_mode.crtc_clock); - PIPE_CONF_CHECK_CLOCK_FUZZY(hw.adjusted_mode.crtc_clock); - PIPE_CONF_CHECK_CLOCK_FUZZY(port_clock); + PIPE_CONF_CHECK_CLOCK_FUZZY(hw.pipe_mode.crtc_clock); + PIPE_CONF_CHECK_CLOCK_FUZZY(hw.adjusted_mode.crtc_clock); + PIPE_CONF_CHECK_CLOCK_FUZZY(port_clock); - PIPE_CONF_CHECK_I(min_voltage_level); - } + PIPE_CONF_CHECK_I(min_voltage_level); if (current_config->has_psr || pipe_config->has_psr) PIPE_CONF_CHECK_X_WITH_MASK(infoframes.enable, @@ -8049,7 +6949,7 @@ verify_crtc_state(struct intel_crtc *crtc, struct intel_encoder *encoder; struct intel_crtc_state *pipe_config = old_crtc_state; struct drm_atomic_state *state = old_crtc_state->uapi.state; - struct intel_crtc *master = crtc; + struct intel_crtc *master_crtc; __drm_atomic_helper_crtc_destroy_state(&old_crtc_state->uapi); intel_crtc_free_hw_state(old_crtc_state); @@ -8077,10 +6977,9 @@ verify_crtc_state(struct intel_crtc *crtc, "(expected %i, found %i)\n", new_crtc_state->hw.active, crtc->active); - if (new_crtc_state->bigjoiner_slave) - master = new_crtc_state->bigjoiner_linked_crtc; + master_crtc = intel_master_crtc(new_crtc_state); - for_each_encoder_on_crtc(dev, &master->base, encoder) { + for_each_encoder_on_crtc(dev, &master_crtc->base, encoder) { enum pipe pipe; bool active; @@ -8090,7 +6989,7 @@ verify_crtc_state(struct intel_crtc *crtc, encoder->base.base.id, active, new_crtc_state->hw.active); - I915_STATE_WARN(active && master->pipe != pipe, + I915_STATE_WARN(active && master_crtc->pipe != pipe, "Encoder connected to wrong pipe %c\n", pipe_name(pipe)); @@ -8101,10 +7000,6 @@ verify_crtc_state(struct intel_crtc *crtc, if (!new_crtc_state->hw.active) return; - if (new_crtc_state->bigjoiner_slave) - /* No PLLs set for slave */ - pipe_config->shared_dpll = NULL; - intel_pipe_config_sanity_check(dev_priv, pipe_config); if (!intel_pipe_config_compare(new_crtc_state, @@ -8223,9 +7118,6 @@ verify_mpllb_state(struct intel_atomic_state *state, if (!new_crtc_state->hw.active) return; - if (new_crtc_state->bigjoiner_slave) - return; - encoder = intel_get_crtc_new_encoder(state, new_crtc_state); intel_mpllb_readout_hw_state(encoder, &mpllb_hw_state); @@ -8607,28 +7499,13 @@ static int intel_bigjoiner_add_affected_planes(struct intel_atomic_state *state) return 0; } -static bool bo_has_valid_encryption(struct drm_i915_gem_object *obj) -{ - struct drm_i915_private *i915 = to_i915(obj->base.dev); - - return intel_pxp_key_check(&i915->gt.pxp, obj, false) == 0; -} - -static bool pxp_is_borked(struct drm_i915_gem_object *obj) -{ - return i915_gem_object_is_protected(obj) && !bo_has_valid_encryption(obj); -} - static int intel_atomic_check_planes(struct intel_atomic_state *state) { struct drm_i915_private *dev_priv = to_i915(state->base.dev); struct intel_crtc_state *old_crtc_state, *new_crtc_state; struct intel_plane_state *plane_state; struct intel_plane *plane; - struct intel_plane_state *new_plane_state; - struct intel_plane_state *old_plane_state; struct intel_crtc *crtc; - const struct drm_framebuffer *fb; int i, ret; ret = icl_add_linked_planes(state); @@ -8676,72 +7553,6 @@ static int intel_atomic_check_planes(struct intel_atomic_state *state) return ret; } - for_each_new_intel_plane_in_state(state, plane, plane_state, i) { - new_plane_state = intel_atomic_get_new_plane_state(state, plane); - old_plane_state = intel_atomic_get_old_plane_state(state, plane); - fb = new_plane_state->hw.fb; - if (fb) { - new_plane_state->decrypt = bo_has_valid_encryption(intel_fb_obj(fb)); - new_plane_state->force_black = pxp_is_borked(intel_fb_obj(fb)); - } else { - new_plane_state->decrypt = old_plane_state->decrypt; - new_plane_state->force_black = old_plane_state->force_black; - } - } - - return 0; -} - -static int intel_atomic_check_cdclk(struct intel_atomic_state *state, - bool *need_cdclk_calc) -{ - struct drm_i915_private *dev_priv = to_i915(state->base.dev); - const struct intel_cdclk_state *old_cdclk_state; - const struct intel_cdclk_state *new_cdclk_state; - struct intel_plane_state *plane_state; - struct intel_bw_state *new_bw_state; - struct intel_plane *plane; - int min_cdclk = 0; - enum pipe pipe; - int ret; - int i; - /* - * active_planes bitmask has been updated, and potentially - * affected planes are part of the state. We can now - * compute the minimum cdclk for each plane. - */ - for_each_new_intel_plane_in_state(state, plane, plane_state, i) { - ret = intel_plane_calc_min_cdclk(state, plane, need_cdclk_calc); - if (ret) - return ret; - } - - old_cdclk_state = intel_atomic_get_old_cdclk_state(state); - new_cdclk_state = intel_atomic_get_new_cdclk_state(state); - - if (new_cdclk_state && - old_cdclk_state->force_min_cdclk != new_cdclk_state->force_min_cdclk) - *need_cdclk_calc = true; - - ret = intel_cdclk_bw_calc_min_cdclk(state); - if (ret) - return ret; - - new_bw_state = intel_atomic_get_new_bw_state(state); - - if (!new_cdclk_state || !new_bw_state) - return 0; - - for_each_pipe(dev_priv, pipe) { - min_cdclk = max(new_cdclk_state->min_cdclk[pipe], min_cdclk); - - /* - * Currently do this change only if we need to increase - */ - if (new_bw_state->min_cdclk > min_cdclk) - *need_cdclk_calc = true; - } - return 0; } @@ -8790,13 +7601,13 @@ static int intel_atomic_check_bigjoiner(struct intel_atomic_state *state, struct intel_crtc_state *new_crtc_state) { struct intel_crtc_state *slave_crtc_state, *master_crtc_state; - struct intel_crtc *slave, *master; + struct intel_crtc *slave_crtc, *master_crtc; /* slave being enabled, is master is still claiming this crtc? */ if (old_crtc_state->bigjoiner_slave) { - slave = crtc; - master = old_crtc_state->bigjoiner_linked_crtc; - master_crtc_state = intel_atomic_get_new_crtc_state(state, master); + slave_crtc = crtc; + master_crtc = old_crtc_state->bigjoiner_linked_crtc; + master_crtc_state = intel_atomic_get_new_crtc_state(state, master_crtc); if (!master_crtc_state || !intel_crtc_needs_modeset(master_crtc_state)) goto claimed; } @@ -8804,17 +7615,17 @@ static int intel_atomic_check_bigjoiner(struct intel_atomic_state *state, if (!new_crtc_state->bigjoiner) return 0; - slave = intel_dsc_get_bigjoiner_secondary(crtc); - if (!slave) { + slave_crtc = intel_dsc_get_bigjoiner_secondary(crtc); + if (!slave_crtc) { DRM_DEBUG_KMS("[CRTC:%d:%s] Big joiner configuration requires " "CRTC + 1 to be used, doesn't exist\n", crtc->base.base.id, crtc->base.name); return -EINVAL; } - new_crtc_state->bigjoiner_linked_crtc = slave; - slave_crtc_state = intel_atomic_get_crtc_state(&state->base, slave); - master = crtc; + new_crtc_state->bigjoiner_linked_crtc = slave_crtc; + slave_crtc_state = intel_atomic_get_crtc_state(&state->base, slave_crtc); + master_crtc = crtc; if (IS_ERR(slave_crtc_state)) return PTR_ERR(slave_crtc_state); @@ -8823,15 +7634,15 @@ static int intel_atomic_check_bigjoiner(struct intel_atomic_state *state, goto claimed; DRM_DEBUG_KMS("[CRTC:%d:%s] Used as slave for big joiner\n", - slave->base.base.id, slave->base.name); + slave_crtc->base.base.id, slave_crtc->base.name); return copy_bigjoiner_crtc_state(slave_crtc_state, new_crtc_state); claimed: DRM_DEBUG_KMS("[CRTC:%d:%s] Slave is enabled as normal CRTC, but " "[CRTC:%d:%s] claiming this CRTC for bigjoiner.\n", - slave->base.base.id, slave->base.name, - master->base.base.id, master->base.name); + slave_crtc->base.base.id, slave_crtc->base.name, + master_crtc->base.base.id, master_crtc->base.name); return -EINVAL; } @@ -8865,35 +7676,37 @@ static void kill_bigjoiner_slave(struct intel_atomic_state *state, * correspond to the last vblank and have no relation to the actual time when * the flip done event was sent. */ -static int intel_atomic_check_async(struct intel_atomic_state *state) +static int intel_atomic_check_async(struct intel_atomic_state *state, struct intel_crtc *crtc) { struct drm_i915_private *i915 = to_i915(state->base.dev); const struct intel_crtc_state *old_crtc_state, *new_crtc_state; const struct intel_plane_state *new_plane_state, *old_plane_state; - struct intel_crtc *crtc; struct intel_plane *plane; int i; - for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, - new_crtc_state, i) { - if (intel_crtc_needs_modeset(new_crtc_state)) { - drm_dbg_kms(&i915->drm, "Modeset Required. Async flip not supported\n"); - return -EINVAL; - } + old_crtc_state = intel_atomic_get_old_crtc_state(state, crtc); + new_crtc_state = intel_atomic_get_new_crtc_state(state, crtc); - if (!new_crtc_state->hw.active) { - drm_dbg_kms(&i915->drm, "CRTC inactive\n"); - return -EINVAL; - } - if (old_crtc_state->active_planes != new_crtc_state->active_planes) { - drm_dbg_kms(&i915->drm, - "Active planes cannot be changed during async flip\n"); - return -EINVAL; - } + if (intel_crtc_needs_modeset(new_crtc_state)) { + drm_dbg_kms(&i915->drm, "Modeset Required. Async flip not supported\n"); + return -EINVAL; + } + + if (!new_crtc_state->hw.active) { + drm_dbg_kms(&i915->drm, "CRTC inactive\n"); + return -EINVAL; + } + if (old_crtc_state->active_planes != new_crtc_state->active_planes) { + drm_dbg_kms(&i915->drm, + "Active planes cannot be changed during async flip\n"); + return -EINVAL; } for_each_oldnew_intel_plane_in_state(state, plane, old_plane_state, new_plane_state, i) { + if (plane->pipe != crtc->pipe) + continue; + /* * TODO: Async flip is only supported through the page flip IOCTL * as of now. So support currently added for primary plane only. @@ -8920,8 +7733,14 @@ static int intel_atomic_check_async(struct intel_atomic_state *state) return -EINVAL; } - if (old_plane_state->view.color_plane[0].stride != - new_plane_state->view.color_plane[0].stride) { + if (new_plane_state->hw.fb->format->num_planes > 1) { + drm_dbg_kms(&i915->drm, + "Planar formats not supported with async flips\n"); + return -EINVAL; + } + + if (old_plane_state->view.color_plane[0].mapping_stride != + new_plane_state->view.color_plane[0].mapping_stride) { drm_dbg_kms(&i915->drm, "Stride cannot be changed in async flip\n"); return -EINVAL; } @@ -9177,7 +7996,6 @@ static int intel_atomic_check(struct drm_device *dev, if (ret) goto fail; - intel_fbc_choose_crtc(dev_priv, state); ret = intel_compute_global_watermarks(state); if (ret) goto fail; @@ -9186,7 +8004,7 @@ static int intel_atomic_check(struct drm_device *dev, if (ret) goto fail; - ret = intel_atomic_check_cdclk(state, &any_ms); + ret = intel_cdclk_atomic_check(state, &any_ms); if (ret) goto fail; @@ -9209,10 +8027,14 @@ static int intel_atomic_check(struct drm_device *dev, if (ret) goto fail; + ret = intel_fbc_atomic_check(state); + if (ret) + goto fail; + for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { if (new_crtc_state->uapi.async_flip) { - ret = intel_atomic_check_async(state); + ret = intel_atomic_check_async(state, crtc); if (ret) goto fail; } @@ -9417,15 +8239,17 @@ static void intel_update_crtc(struct intel_atomic_state *state, intel_fbc_update(state, crtc); + intel_update_planes_on_crtc(state, crtc); + /* Perform vblank evasion around commit operation */ intel_pipe_update_start(new_crtc_state); commit_pipe_pre_planes(state, crtc); if (DISPLAY_VER(dev_priv) >= 9) - skl_update_planes_on_crtc(state, crtc); + skl_arm_planes_on_crtc(state, crtc); else - i9xx_update_planes_on_crtc(state, crtc); + i9xx_arm_planes_on_crtc(state, crtc); commit_pipe_post_planes(state, crtc); @@ -9449,23 +8273,6 @@ static void intel_old_crtc_state_disables(struct intel_atomic_state *state, { struct drm_i915_private *dev_priv = to_i915(state->base.dev); - drm_WARN_ON(&dev_priv->drm, old_crtc_state->bigjoiner_slave); - - intel_encoders_pre_disable(state, crtc); - - intel_crtc_disable_planes(state, crtc); - - /* - * We still need special handling for disabling bigjoiner master - * and slaves since for slave we do not have encoder or plls - * so we dont need to disable those. - */ - if (old_crtc_state->bigjoiner) { - intel_crtc_disable_planes(state, - old_crtc_state->bigjoiner_linked_crtc); - old_crtc_state->bigjoiner_linked_crtc->active = false; - } - /* * We need to disable pipe CRC before disabling the pipe, * or we race against vblank off. @@ -9490,10 +8297,22 @@ static void intel_commit_modeset_disables(struct intel_atomic_state *state) u32 handled = 0; int i; + for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, + new_crtc_state, i) { + if (!intel_crtc_needs_modeset(new_crtc_state)) + continue; + + if (!old_crtc_state->hw.active) + continue; + + intel_pre_plane_update(state, crtc); + intel_crtc_disable_planes(state, crtc); + } + /* Only disable port sync and MST slaves */ for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { - if (!intel_crtc_needs_modeset(new_crtc_state) || old_crtc_state->bigjoiner) + if (!intel_crtc_needs_modeset(new_crtc_state)) continue; if (!old_crtc_state->hw.active) @@ -9505,10 +8324,10 @@ static void intel_commit_modeset_disables(struct intel_atomic_state *state) * Slave vblanks are masked till Master Vblanks. */ if (!is_trans_port_sync_slave(old_crtc_state) && - !intel_dp_mst_is_slave_trans(old_crtc_state)) + !intel_dp_mst_is_slave_trans(old_crtc_state) && + !old_crtc_state->bigjoiner_slave) continue; - intel_pre_plane_update(state, crtc); intel_old_crtc_state_disables(state, old_crtc_state, new_crtc_state, crtc); handled |= BIT(crtc->pipe); @@ -9518,21 +8337,14 @@ static void intel_commit_modeset_disables(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) || - (handled & BIT(crtc->pipe)) || - old_crtc_state->bigjoiner_slave) + (handled & BIT(crtc->pipe))) continue; - intel_pre_plane_update(state, crtc); - if (old_crtc_state->bigjoiner) { - struct intel_crtc *slave = - old_crtc_state->bigjoiner_linked_crtc; - - intel_pre_plane_update(state, slave); - } + if (!old_crtc_state->hw.active) + continue; - if (old_crtc_state->hw.active) - intel_old_crtc_state_disables(state, old_crtc_state, - new_crtc_state, crtc); + intel_old_crtc_state_disables(state, old_crtc_state, + new_crtc_state, crtc); } } @@ -9610,7 +8422,7 @@ static void skl_commit_modeset_enables(struct intel_atomic_state *state) if (!skl_ddb_entry_equal(&new_crtc_state->wm.skl.ddb, &old_crtc_state->wm.skl.ddb) && (update_pipes | modeset_pipes)) - intel_wait_for_vblank(dev_priv, pipe); + intel_crtc_wait_for_next_vblank(crtc); } } @@ -9701,19 +8513,19 @@ static void intel_atomic_commit_fence_wait(struct intel_atomic_state *intel_stat for (;;) { prepare_to_wait(&intel_state->commit_ready.wait, &wait_fence, TASK_UNINTERRUPTIBLE); - prepare_to_wait(bit_waitqueue(&dev_priv->gt.reset.flags, + prepare_to_wait(bit_waitqueue(&to_gt(dev_priv)->reset.flags, I915_RESET_MODESET), &wait_reset, TASK_UNINTERRUPTIBLE); if (i915_sw_fence_done(&intel_state->commit_ready) || - test_bit(I915_RESET_MODESET, &dev_priv->gt.reset.flags)) + test_bit(I915_RESET_MODESET, &to_gt(dev_priv)->reset.flags)) break; schedule(); } finish_wait(&intel_state->commit_ready.wait, &wait_fence); - finish_wait(bit_waitqueue(&dev_priv->gt.reset.flags, + finish_wait(bit_waitqueue(&to_gt(dev_priv)->reset.flags, I915_RESET_MODESET), &wait_reset); } @@ -9752,10 +8564,14 @@ static void intel_atomic_prepare_plane_clear_colors(struct intel_atomic_state *s for_each_new_intel_plane_in_state(state, plane, plane_state, i) { struct drm_framebuffer *fb = plane_state->hw.fb; + int cc_plane; int ret; - if (!fb || - fb->modifier != I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC) + if (!fb) + continue; + + cc_plane = intel_fb_rc_ccs_cc_plane(fb); + if (cc_plane < 0) continue; /* @@ -9772,7 +8588,7 @@ static void intel_atomic_prepare_plane_clear_colors(struct intel_atomic_state *s * GPU write on it. */ ret = i915_gem_object_read_from_page(intel_fb_obj(fb), - fb->offsets[2] + 16, + fb->offsets[cc_plane] + 16, &plane_state->ccval, sizeof(plane_state->ccval)); /* The above could only fail if the FB obj has an unexpected backing store type. */ @@ -9840,11 +8656,9 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) } } - if (state->modeset) - intel_encoders_update_prepare(state); + intel_encoders_update_prepare(state); intel_dbuf_pre_plane_update(state); - intel_psr_pre_plane_update(state); for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { if (new_crtc_state->uapi.async_flip) @@ -9854,11 +8668,12 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) /* Now enable the clocks, plane, pipe, and connectors that we set up. */ dev_priv->display->commit_modeset_enables(state); - if (state->modeset) { - intel_encoders_update_complete(state); + intel_encoders_update_complete(state); + if (state->modeset) intel_set_cdclk_post_plane_update(state); - } + + intel_wait_for_vblank_workers(state); /* FIXME: We should call drm_atomic_helper_commit_hw_done() here * already, but still need the state for the delayed optimization. To @@ -9874,13 +8689,6 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { if (new_crtc_state->uapi.async_flip) intel_crtc_disable_flip_done(state, crtc); - - if (new_crtc_state->hw.active && - !intel_crtc_needs_modeset(new_crtc_state) && - !new_crtc_state->preload_luts && - (new_crtc_state->uapi.color_mgmt_changed || - new_crtc_state->update_pipe)) - intel_color_load_luts(new_crtc_state); } /* @@ -9967,7 +8775,7 @@ static void intel_atomic_commit_work(struct work_struct *work) intel_atomic_commit_tail(state); } -static int __i915_sw_fence_call +static int intel_atomic_commit_ready(struct i915_sw_fence *fence, enum i915_sw_fence_notify notify) { @@ -10114,8 +8922,8 @@ static void intel_plane_possible_crtcs_init(struct drm_i915_private *dev_priv) struct intel_plane *plane; for_each_intel_plane(&dev_priv->drm, plane) { - struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, - plane->pipe); + struct intel_crtc *crtc = intel_crtc_for_pipe(dev_priv, + plane->pipe); plane->base.possible_crtcs = drm_crtc_mask(&crtc->base); } @@ -10580,7 +9388,7 @@ intel_mode_valid_max_plane_size(struct drm_i915_private *dev_priv, static const struct drm_mode_config_funcs intel_mode_funcs = { .fb_create = intel_user_framebuffer_create, - .get_format_info = intel_get_format_info, + .get_format_info = intel_fb_get_format_info, .output_poll_changed = intel_fbdev_output_poll_changed, .mode_valid = intel_mode_valid, .atomic_check = intel_atomic_check, @@ -10640,7 +9448,7 @@ void intel_init_display_hooks(struct drm_i915_private *dev_priv) return; intel_init_cdclk_hooks(dev_priv); - intel_init_audio_hooks(dev_priv); + intel_audio_hooks_init(dev_priv); intel_dpll_init_clock_hook(dev_priv); @@ -11108,7 +9916,7 @@ int intel_modeset_init(struct drm_i915_private *i915) void i830_enable_pipe(struct drm_i915_private *dev_priv, enum pipe pipe) { - struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe); + struct intel_crtc *crtc = intel_crtc_for_pipe(dev_priv, pipe); /* 640x480@60Hz, ~25175 kHz */ struct dpll clock = { .m1 = 18, @@ -11181,7 +9989,7 @@ void i830_enable_pipe(struct drm_i915_private *dev_priv, enum pipe pipe) void i830_disable_pipe(struct drm_i915_private *dev_priv, enum pipe pipe) { - struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe); + struct intel_crtc *crtc = intel_crtc_for_pipe(dev_priv, pipe); drm_dbg_kms(&dev_priv->drm, "disabling pipe %c due to force quirk\n", pipe_name(pipe)); @@ -11233,7 +10041,7 @@ intel_sanitize_plane_mapping(struct drm_i915_private *dev_priv) "[PLANE:%d:%s] attached to the wrong pipe, disabling plane\n", plane->base.base.id, plane->base.name); - plane_crtc = intel_get_crtc_for_pipe(dev_priv, pipe); + plane_crtc = intel_crtc_for_pipe(dev_priv, pipe); intel_plane_disable_noatomic(plane_crtc, plane); } } @@ -11486,7 +10294,7 @@ static void readout_plane_state(struct drm_i915_private *dev_priv) visible = plane->get_hw_state(plane, &pipe); - crtc = intel_get_crtc_for_pipe(dev_priv, pipe); + crtc = intel_crtc_for_pipe(dev_priv, pipe); crtc_state = to_intel_crtc_state(crtc->base.state); intel_set_plane_visible(crtc_state, plane_state, visible); @@ -11553,7 +10361,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) pipe = 0; if (encoder->get_hw_state(encoder, &pipe)) { - crtc = intel_get_crtc_for_pipe(dev_priv, pipe); + crtc = intel_crtc_for_pipe(dev_priv, pipe); crtc_state = to_intel_crtc_state(crtc->base.state); encoder->base.crtc = &crtc->base; @@ -11628,9 +10436,6 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) struct intel_plane *plane; int min_cdclk = 0; - if (crtc_state->bigjoiner_slave) - continue; - if (crtc_state->hw.active) { /* * The initial mode needs to be set in order to keep @@ -11690,39 +10495,6 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) intel_bw_crtc_update(bw_state, crtc_state); intel_pipe_config_sanity_check(dev_priv, crtc_state); - - /* discard our incomplete slave state, copy it from master */ - if (crtc_state->bigjoiner && crtc_state->hw.active) { - struct intel_crtc *slave = crtc_state->bigjoiner_linked_crtc; - struct intel_crtc_state *slave_crtc_state = - to_intel_crtc_state(slave->base.state); - - copy_bigjoiner_crtc_state(slave_crtc_state, crtc_state); - slave->base.mode = crtc->base.mode; - - cdclk_state->min_cdclk[slave->pipe] = min_cdclk; - cdclk_state->min_voltage_level[slave->pipe] = - crtc_state->min_voltage_level; - - for_each_intel_plane_on_crtc(&dev_priv->drm, slave, plane) { - const struct intel_plane_state *plane_state = - to_intel_plane_state(plane->base.state); - - /* - * FIXME don't have the fb yet, so can't - * use intel_plane_data_rate() :( - */ - if (plane_state->uapi.visible) - crtc_state->data_rate[plane->id] = - 4 * crtc_state->pixel_rate; - else - crtc_state->data_rate[plane->id] = 0; - } - - intel_bw_crtc_update(bw_state, slave_crtc_state); - drm_calc_timestamping_constants(&slave->base, - &slave_crtc_state->hw.adjusted_mode); - } } } @@ -12027,7 +10799,7 @@ void intel_modeset_driver_remove_noirq(struct drm_i915_private *i915) destroy_workqueue(i915->flip_wq); destroy_workqueue(i915->modeset_wq); - intel_fbc_cleanup_cfb(i915); + intel_fbc_cleanup(i915); } /* part #3: call after gem init */ @@ -12042,6 +10814,27 @@ void intel_modeset_driver_remove_nogem(struct drm_i915_private *i915) intel_bios_driver_remove(i915); } +bool intel_modeset_probe_defer(struct pci_dev *pdev) +{ + struct drm_privacy_screen *privacy_screen; + + /* + * apple-gmux is needed on dual GPU MacBook Pro + * to probe the panel if we're the inactive GPU. + */ + if (vga_switcheroo_client_probe_defer(pdev)) + return true; + + /* If the LCD panel has a privacy-screen, wait for it */ + privacy_screen = drm_privacy_screen_get(&pdev->dev, NULL); + if (IS_ERR(privacy_screen) && PTR_ERR(privacy_screen) == -EPROBE_DEFER) + return true; + + drm_privacy_screen_put(privacy_screen); + + return false; +} + void intel_display_driver_register(struct drm_i915_private *i915) { if (!HAS_DISPLAY(i915)) diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h index 0c76bf57f86b..b61b75248ded 100644 --- a/drivers/gpu/drm/i915/display/intel_display.h +++ b/drivers/gpu/drm/i915/display/intel_display.h @@ -57,6 +57,7 @@ struct intel_plane; struct intel_plane_state; struct intel_remapped_info; struct intel_rotation_info; +struct pci_dev; enum i915_gpio { GPIOA, @@ -346,9 +347,33 @@ enum phy_fia { FIA3, }; +enum hpd_pin { + HPD_NONE = 0, + HPD_TV = HPD_NONE, /* TV is known to be unreliable */ + HPD_CRT, + HPD_SDVO_B, + HPD_SDVO_C, + HPD_PORT_A, + HPD_PORT_B, + HPD_PORT_C, + HPD_PORT_D, + HPD_PORT_E, + HPD_PORT_TC1, + HPD_PORT_TC2, + HPD_PORT_TC3, + HPD_PORT_TC4, + HPD_PORT_TC5, + HPD_PORT_TC6, + + HPD_NUM_PINS +}; + +#define for_each_hpd_pin(__pin) \ + for ((__pin) = (HPD_NONE + 1); (__pin) < HPD_NUM_PINS; (__pin)++) + #define for_each_pipe(__dev_priv, __p) \ for ((__p) = 0; (__p) < I915_MAX_PIPES; (__p)++) \ - for_each_if(INTEL_INFO(__dev_priv)->pipe_mask & BIT(__p)) + for_each_if(INTEL_INFO(__dev_priv)->display.pipe_mask & BIT(__p)) #define for_each_pipe_masked(__dev_priv, __p, __mask) \ for_each_pipe(__dev_priv, __p) \ @@ -356,7 +381,7 @@ enum phy_fia { #define for_each_cpu_transcoder(__dev_priv, __t) \ for ((__t) = 0; (__t) < I915_MAX_TRANSCODERS; (__t)++) \ - for_each_if (INTEL_INFO(__dev_priv)->cpu_transcoder_mask & BIT(__t)) + for_each_if (INTEL_INFO(__dev_priv)->display.cpu_transcoder_mask & BIT(__t)) #define for_each_cpu_transcoder_masked(__dev_priv, __t, __mask) \ for_each_cpu_transcoder(__dev_priv, __t) \ @@ -521,7 +546,6 @@ void intel_link_compute_m_n(u16 bpp, int nlanes, int pixel_clock, int link_clock, struct intel_link_m_n *m_n, bool constant_n, bool fec_enable); -void lpt_disable_clkout_dp(struct drm_i915_private *dev_priv); u32 intel_plane_fb_max_stride(struct drm_i915_private *dev_priv, u32 pixel_format, u64 modifier); enum drm_mode_status @@ -542,9 +566,6 @@ int vlv_get_cck_clock(struct drm_i915_private *dev_priv, const char *name, u32 reg, int ref_freq); int vlv_get_cck_clock_hpll(struct drm_i915_private *dev_priv, const char *name, u32 reg); -void lpt_pch_enable(const struct intel_crtc_state *crtc_state); -void lpt_disable_pch_transcoder(struct drm_i915_private *dev_priv); -void lpt_disable_iclkip(struct drm_i915_private *dev_priv); void intel_init_display_hooks(struct drm_i915_private *dev_priv); unsigned int intel_fb_xy_to_linear(int x, int y, const struct intel_plane_state *state, @@ -580,10 +601,6 @@ struct drm_framebuffer * intel_framebuffer_create(struct drm_i915_gem_object *obj, struct drm_mode_fb_cmd2 *mode_cmd); -void assert_pch_transcoder_disabled(struct drm_i915_private *dev_priv, - enum pipe pipe); - -int lpt_get_iclkip(struct drm_i915_private *dev_priv); bool intel_fuzzy_clock_check(int clock1, int clock2); void intel_display_prepare_reset(struct drm_i915_private *dev_priv); @@ -592,8 +609,11 @@ void intel_dp_get_m_n(struct intel_crtc *crtc, struct intel_crtc_state *pipe_config); void intel_dp_set_m_n(const struct intel_crtc_state *crtc_state, enum link_m_n_set m_n); +void ilk_get_fdi_m_n_config(struct intel_crtc *crtc, + struct intel_crtc_state *pipe_config); +void i9xx_crtc_clock_get(struct intel_crtc *crtc, + struct intel_crtc_state *pipe_config); int intel_dotclock_calculate(int link_freq, const struct intel_link_m_n *m_n); - bool hsw_crtc_state_ips_capable(const struct intel_crtc_state *crtc_state); void hsw_enable_ips(const struct intel_crtc_state *crtc_state); void hsw_disable_ips(const struct intel_crtc_state *crtc_state); @@ -610,9 +630,6 @@ int bdw_get_pipemisc_bpp(struct intel_crtc *crtc); unsigned int intel_plane_fence_y_offset(const struct intel_plane_state *plane_state); bool intel_plane_uses_fence(const struct intel_plane_state *plane_state); -bool -intel_format_info_is_yuv_semiplanar(const struct drm_format_info *info, - u64 modifier); struct intel_encoder * intel_get_crtc_new_encoder(const struct intel_atomic_state *state, @@ -624,6 +641,7 @@ void intel_display_driver_register(struct drm_i915_private *i915); void intel_display_driver_unregister(struct drm_i915_private *i915); /* modesetting */ +bool intel_modeset_probe_defer(struct pci_dev *pdev); void intel_modeset_init_hw(struct drm_i915_private *i915); int intel_modeset_init_noirq(struct drm_i915_private *i915); int intel_modeset_init_nogem(struct drm_i915_private *i915); @@ -632,7 +650,6 @@ 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); -void intel_init_pch_refclk(struct drm_i915_private *dev_priv); int intel_modeset_all_pipes(struct intel_atomic_state *state); /* modesetting asserts */ diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs.c b/drivers/gpu/drm/i915/display/intel_display_debugfs.c index e04767695530..572445299b04 100644 --- a/drivers/gpu/drm/i915/display/intel_display_debugfs.c +++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.c @@ -40,83 +40,6 @@ static int i915_frontbuffer_tracking(struct seq_file *m, void *unused) return 0; } -static int i915_fbc_status(struct seq_file *m, void *unused) -{ - struct drm_i915_private *dev_priv = node_to_i915(m->private); - struct intel_fbc *fbc = &dev_priv->fbc; - intel_wakeref_t wakeref; - - if (!HAS_FBC(dev_priv)) - return -ENODEV; - - wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm); - mutex_lock(&fbc->lock); - - if (intel_fbc_is_active(dev_priv)) - seq_puts(m, "FBC enabled\n"); - else - seq_printf(m, "FBC disabled: %s\n", fbc->no_fbc_reason); - - if (intel_fbc_is_active(dev_priv)) { - u32 mask; - - if (DISPLAY_VER(dev_priv) >= 8) - mask = intel_de_read(dev_priv, IVB_FBC_STATUS2) & BDW_FBC_COMP_SEG_MASK; - else if (DISPLAY_VER(dev_priv) >= 7) - mask = intel_de_read(dev_priv, IVB_FBC_STATUS2) & IVB_FBC_COMP_SEG_MASK; - else if (DISPLAY_VER(dev_priv) >= 5) - mask = intel_de_read(dev_priv, ILK_DPFC_STATUS) & ILK_DPFC_COMP_SEG_MASK; - else if (IS_G4X(dev_priv)) - mask = intel_de_read(dev_priv, DPFC_STATUS) & DPFC_COMP_SEG_MASK; - else - mask = intel_de_read(dev_priv, FBC_STATUS) & - (FBC_STAT_COMPRESSING | FBC_STAT_COMPRESSED); - - seq_printf(m, "Compressing: %s\n", yesno(mask)); - } - - mutex_unlock(&fbc->lock); - intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref); - - return 0; -} - -static int i915_fbc_false_color_get(void *data, u64 *val) -{ - struct drm_i915_private *dev_priv = data; - - if (DISPLAY_VER(dev_priv) < 7 || !HAS_FBC(dev_priv)) - return -ENODEV; - - *val = dev_priv->fbc.false_color; - - return 0; -} - -static int i915_fbc_false_color_set(void *data, u64 val) -{ - struct drm_i915_private *dev_priv = data; - u32 reg; - - if (DISPLAY_VER(dev_priv) < 7 || !HAS_FBC(dev_priv)) - return -ENODEV; - - mutex_lock(&dev_priv->fbc.lock); - - reg = intel_de_read(dev_priv, ILK_DPFC_CONTROL); - dev_priv->fbc.false_color = val; - - intel_de_write(dev_priv, ILK_DPFC_CONTROL, - val ? (reg | FBC_CTL_FALSE_COLOR) : (reg & ~FBC_CTL_FALSE_COLOR)); - - mutex_unlock(&dev_priv->fbc.lock); - return 0; -} - -DEFINE_SIMPLE_ATTRIBUTE(i915_fbc_false_color_fops, - i915_fbc_false_color_get, i915_fbc_false_color_set, - "%llu\n"); - static int i915_ips_status(struct seq_file *m, void *unused) { struct drm_i915_private *dev_priv = node_to_i915(m->private); @@ -303,8 +226,7 @@ psr_source_status(struct intel_dp *intel_dp, struct seq_file *m) }; val = intel_de_read(dev_priv, EDP_PSR2_STATUS(intel_dp->psr.transcoder)); - status_val = (val & EDP_PSR2_STATUS_STATE_MASK) >> - EDP_PSR2_STATUS_STATE_SHIFT; + status_val = REG_FIELD_GET(EDP_PSR2_STATUS_STATE_MASK, val); if (status_val < ARRAY_SIZE(live_status)) status = live_status[status_val]; } else { @@ -503,28 +425,9 @@ DEFINE_SIMPLE_ATTRIBUTE(i915_edp_psr_debug_fops, static int i915_power_domain_info(struct seq_file *m, void *unused) { - struct drm_i915_private *dev_priv = node_to_i915(m->private); - struct i915_power_domains *power_domains = &dev_priv->power_domains; - int i; - - mutex_lock(&power_domains->lock); - - seq_printf(m, "%-25s %s\n", "Power well/domain", "Use count"); - for (i = 0; i < power_domains->power_well_count; i++) { - struct i915_power_well *power_well; - enum intel_display_power_domain power_domain; - - power_well = &power_domains->power_wells[i]; - seq_printf(m, "%-25s %d\n", power_well->desc->name, - power_well->count); - - for_each_power_domain(power_domain, power_well->desc->domains) - seq_printf(m, " %-23s %d\n", - intel_display_power_domain_str(power_domain), - power_domains->domain_use_count[power_domain]); - } + struct drm_i915_private *i915 = node_to_i915(m->private); - mutex_unlock(&power_domains->lock); + intel_display_power_debug(i915, m); return 0; } @@ -2095,9 +1998,7 @@ i915_fifo_underrun_reset_write(struct file *filp, return ret; } - ret = intel_fbc_reset_underrun(dev_priv); - if (ret) - return ret; + intel_fbc_reset_underrun(dev_priv); return cnt; } @@ -2111,7 +2012,6 @@ static const struct file_operations i915_fifo_underrun_reset_ops = { static const struct drm_info_list intel_display_debugfs_list[] = { {"i915_frontbuffer_tracking", i915_frontbuffer_tracking, 0}, - {"i915_fbc_status", i915_fbc_status, 0}, {"i915_ips_status", i915_ips_status, 0}, {"i915_sr_status", i915_sr_status, 0}, {"i915_opregion", i915_opregion, 0}, @@ -2136,7 +2036,6 @@ static const struct { {"i915_pri_wm_latency", &i915_pri_wm_latency_fops}, {"i915_spr_wm_latency", &i915_spr_wm_latency_fops}, {"i915_cur_wm_latency", &i915_cur_wm_latency_fops}, - {"i915_fbc_false_color", &i915_fbc_false_color_fops}, {"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}, @@ -2163,6 +2062,8 @@ void intel_display_debugfs_register(struct drm_i915_private *i915) drm_debugfs_create_files(intel_display_debugfs_list, ARRAY_SIZE(intel_display_debugfs_list), minor->debugfs_root, minor); + + intel_fbc_debugfs_register(i915); } static int i915_panel_show(struct seq_file *m, void *data) diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 1672604f9ef7..05babdcf5f2e 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -15,6 +15,7 @@ #include "intel_dpio_phy.h" #include "intel_dpll.h" #include "intel_hotplug.h" +#include "intel_pch_refclk.h" #include "intel_pcode.h" #include "intel_pm.h" #include "intel_pps.h" @@ -23,6 +24,98 @@ #include "intel_vga.h" #include "vlv_sideband.h" +struct i915_power_well_ops { + /* + * Synchronize the well's hw state to match the current sw state, for + * example enable/disable it based on the current refcount. Called + * during driver init and resume time, possibly after first calling + * the enable/disable handlers. + */ + void (*sync_hw)(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well); + /* + * Enable the well and resources that depend on it (for example + * interrupts located on the well). Called after the 0->1 refcount + * transition. + */ + void (*enable)(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well); + /* + * Disable the well and resources that depend on it. Called after + * the 1->0 refcount transition. + */ + void (*disable)(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well); + /* Returns the hw enabled state. */ + bool (*is_enabled)(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well); +}; + +struct i915_power_well_regs { + i915_reg_t bios; + i915_reg_t driver; + i915_reg_t kvmr; + i915_reg_t debug; +}; + +/* Power well structure for haswell */ +struct i915_power_well_desc { + const char *name; + bool always_on; + u64 domains; + /* unique identifier for this power well */ + enum i915_power_well_id id; + /* + * Arbitraty data associated with this power well. Platform and power + * well specific. + */ + union { + struct { + /* + * request/status flag index in the PUNIT power well + * control/status registers. + */ + u8 idx; + } vlv; + struct { + enum dpio_phy phy; + } bxt; + struct { + const struct i915_power_well_regs *regs; + /* + * request/status flag index in the power well + * constrol/status registers. + */ + u8 idx; + /* Mask of pipes whose IRQ logic is backed by the pw */ + u8 irq_pipe_mask; + /* + * Instead of waiting for the status bit to ack enables, + * just wait a specific amount of time and then consider + * the well enabled. + */ + u16 fixed_enable_delay; + /* The pw is backing the VGA functionality */ + bool has_vga:1; + bool has_fuses:1; + /* + * The pw is for an ICL+ TypeC PHY port in + * Thunderbolt mode. + */ + bool is_tc_tbt:1; + } hsw; + }; + const struct i915_power_well_ops *ops; +}; + +struct i915_power_well { + const struct i915_power_well_desc *desc; + /* power well enable/disable usage count */ + int count; + /* cached hw enabled state */ + bool hw_enabled; +}; + bool intel_display_power_well_is_enabled(struct drm_i915_private *dev_priv, enum i915_power_well_id power_well_id); @@ -154,8 +247,8 @@ intel_display_power_domain_str(enum intel_display_power_domain domain) return "MODESET"; case POWER_DOMAIN_GT_IRQ: return "GT_IRQ"; - case POWER_DOMAIN_DPLL_DC_OFF: - return "DPLL_DC_OFF"; + case POWER_DOMAIN_DC_OFF: + return "DC_OFF"; case POWER_DOMAIN_TC_COLD_OFF: return "TC_COLD_OFF"; default: @@ -434,6 +527,11 @@ static void hsw_power_well_enable(struct drm_i915_private *dev_priv, pg = DISPLAY_VER(dev_priv) >= 11 ? ICL_PW_CTL_IDX_TO_PG(pw_idx) : SKL_PW_CTL_IDX_TO_PG(pw_idx); + + /* Wa_16013190616:adlp */ + if (IS_ALDERLAKE_P(dev_priv) && pg == SKL_PG1) + intel_de_rmw(dev_priv, GEN8_CHICKEN_DCPR_1, 0, DISABLE_FLR_SRC); + /* * For PW1 we have to wait both for the PW0/PG0 fuse state * before enabling the power well and PW1/PG1's own fuse @@ -894,7 +992,7 @@ static u32 sanitize_target_dc_state(struct drm_i915_private *dev_priv, u32 target_dc_state) { - u32 states[] = { + static const u32 states[] = { DC_STATE_EN_UPTO_DC6, DC_STATE_EN_UPTO_DC5, DC_STATE_EN_DC3CO, @@ -2802,7 +2900,7 @@ intel_display_power_put_mask_in_set(struct drm_i915_private *i915, ICL_PW_2_POWER_DOMAINS | \ BIT_ULL(POWER_DOMAIN_MODESET) | \ BIT_ULL(POWER_DOMAIN_AUX_A) | \ - BIT_ULL(POWER_DOMAIN_DPLL_DC_OFF) | \ + BIT_ULL(POWER_DOMAIN_DC_OFF) | \ BIT_ULL(POWER_DOMAIN_INIT)) #define ICL_DDI_IO_A_POWER_DOMAINS ( \ @@ -3105,6 +3203,7 @@ intel_display_power_put_mask_in_set(struct drm_i915_private *i915, BIT_ULL(POWER_DOMAIN_MODESET) | \ BIT_ULL(POWER_DOMAIN_AUX_A) | \ BIT_ULL(POWER_DOMAIN_AUX_B) | \ + BIT_ULL(POWER_DOMAIN_PORT_DSI) | \ BIT_ULL(POWER_DOMAIN_INIT)) #define XELPD_AUX_IO_D_XELPD_POWER_DOMAINS BIT_ULL(POWER_DOMAIN_AUX_D_XELPD) @@ -5271,7 +5370,7 @@ static void gen12_dbuf_slices_config(struct drm_i915_private *dev_priv) static void icl_mbus_init(struct drm_i915_private *dev_priv) { - unsigned long abox_regs = INTEL_INFO(dev_priv)->abox_mask; + unsigned long abox_regs = INTEL_INFO(dev_priv)->display.abox_mask; u32 mask, val, i; if (IS_ALDERLAKE_P(dev_priv)) @@ -5731,7 +5830,7 @@ static void tgl_bw_buddy_init(struct drm_i915_private *dev_priv) enum intel_dram_type type = dev_priv->dram_info.type; u8 num_channels = dev_priv->dram_info.num_channels; const struct buddy_page_mask *table; - unsigned long abox_mask = INTEL_INFO(dev_priv)->abox_mask; + unsigned long abox_mask = INTEL_INFO(dev_priv)->display.abox_mask; int config, i; /* BW_BUDDY registers are not used on dgpu's beyond DG1 */ @@ -6390,3 +6489,28 @@ void intel_display_power_resume(struct drm_i915_private *i915) hsw_disable_pc8(i915); } } + +void intel_display_power_debug(struct drm_i915_private *i915, struct seq_file *m) +{ + struct i915_power_domains *power_domains = &i915->power_domains; + int i; + + mutex_lock(&power_domains->lock); + + seq_printf(m, "%-25s %s\n", "Power well/domain", "Use count"); + for (i = 0; i < power_domains->power_well_count; i++) { + struct i915_power_well *power_well; + enum intel_display_power_domain power_domain; + + power_well = &power_domains->power_wells[i]; + seq_printf(m, "%-25s %d\n", power_well->desc->name, + power_well->count); + + for_each_power_domain(power_domain, power_well->desc->domains) + seq_printf(m, " %-23s %d\n", + intel_display_power_domain_str(power_domain), + power_domains->domain_use_count[power_domain]); + } + + mutex_unlock(&power_domains->lock); +} diff --git a/drivers/gpu/drm/i915/display/intel_display_power.h b/drivers/gpu/drm/i915/display/intel_display_power.h index 0612e4b6e3c8..686d18eaa24c 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.h +++ b/drivers/gpu/drm/i915/display/intel_display_power.h @@ -6,11 +6,13 @@ #ifndef __INTEL_DISPLAY_POWER_H__ #define __INTEL_DISPLAY_POWER_H__ -#include "intel_display.h" #include "intel_runtime_pm.h" #include "i915_reg.h" +enum dpio_channel; +enum dpio_phy; struct drm_i915_private; +struct i915_power_well; struct intel_encoder; enum intel_display_power_domain { @@ -117,7 +119,7 @@ enum intel_display_power_domain { POWER_DOMAIN_GMBUS, POWER_DOMAIN_MODESET, POWER_DOMAIN_GT_IRQ, - POWER_DOMAIN_DPLL_DC_OFF, + POWER_DOMAIN_DC_OFF, POWER_DOMAIN_TC_COLD_OFF, POWER_DOMAIN_INIT, @@ -155,100 +157,6 @@ enum i915_power_well_id { ((tran) == TRANSCODER_EDP ? POWER_DOMAIN_TRANSCODER_EDP : \ (tran) + POWER_DOMAIN_TRANSCODER_A) -struct i915_power_well; - -struct i915_power_well_ops { - /* - * Synchronize the well's hw state to match the current sw state, for - * example enable/disable it based on the current refcount. Called - * during driver init and resume time, possibly after first calling - * the enable/disable handlers. - */ - void (*sync_hw)(struct drm_i915_private *dev_priv, - struct i915_power_well *power_well); - /* - * Enable the well and resources that depend on it (for example - * interrupts located on the well). Called after the 0->1 refcount - * transition. - */ - void (*enable)(struct drm_i915_private *dev_priv, - struct i915_power_well *power_well); - /* - * Disable the well and resources that depend on it. Called after - * the 1->0 refcount transition. - */ - void (*disable)(struct drm_i915_private *dev_priv, - struct i915_power_well *power_well); - /* Returns the hw enabled state. */ - bool (*is_enabled)(struct drm_i915_private *dev_priv, - struct i915_power_well *power_well); -}; - -struct i915_power_well_regs { - i915_reg_t bios; - i915_reg_t driver; - i915_reg_t kvmr; - i915_reg_t debug; -}; - -/* Power well structure for haswell */ -struct i915_power_well_desc { - const char *name; - bool always_on; - u64 domains; - /* unique identifier for this power well */ - enum i915_power_well_id id; - /* - * Arbitraty data associated with this power well. Platform and power - * well specific. - */ - union { - struct { - /* - * request/status flag index in the PUNIT power well - * control/status registers. - */ - u8 idx; - } vlv; - struct { - enum dpio_phy phy; - } bxt; - struct { - const struct i915_power_well_regs *regs; - /* - * request/status flag index in the power well - * constrol/status registers. - */ - u8 idx; - /* Mask of pipes whose IRQ logic is backed by the pw */ - u8 irq_pipe_mask; - /* - * Instead of waiting for the status bit to ack enables, - * just wait a specific amount of time and then consider - * the well enabled. - */ - u16 fixed_enable_delay; - /* The pw is backing the VGA functionality */ - bool has_vga:1; - bool has_fuses:1; - /* - * The pw is for an ICL+ TypeC PHY port in - * Thunderbolt mode. - */ - bool is_tc_tbt:1; - } hsw; - }; - const struct i915_power_well_ops *ops; -}; - -struct i915_power_well { - const struct i915_power_well_desc *desc; - /* power well enable/disable usage count */ - int count; - /* cached hw enabled state */ - bool hw_enabled; -}; - struct i915_power_domains { /* * Power wells needed for initialization at driver init and suspend @@ -391,6 +299,8 @@ intel_display_power_put_all_in_set(struct drm_i915_private *i915, intel_display_power_put_mask_in_set(i915, power_domain_set, power_domain_set->mask); } +void intel_display_power_debug(struct drm_i915_private *i915, struct seq_file *m); + /* * FIXME: We should probably switch this to a 0-based scheme to be consistent * with how we now name/number DBUF_CTL instances. diff --git a/drivers/gpu/drm/i915/display/intel_display_trace.c b/drivers/gpu/drm/i915/display/intel_display_trace.c new file mode 100644 index 000000000000..737979ada869 --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_display_trace.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef __CHECKER__ +#define CREATE_TRACE_POINTS +#include "intel_display_trace.h" +#endif diff --git a/drivers/gpu/drm/i915/display/intel_display_trace.h b/drivers/gpu/drm/i915/display/intel_display_trace.h new file mode 100644 index 000000000000..4043e1276383 --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_display_trace.h @@ -0,0 +1,587 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright © 2021 Intel Corporation + */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM i915 + +#if !defined(__INTEL_DISPLAY_TRACE_H__) || defined(TRACE_HEADER_MULTI_READ) +#define __INTEL_DISPLAY_TRACE_H__ + +#include <linux/types.h> +#include <linux/tracepoint.h> + +#include "i915_drv.h" +#include "intel_crtc.h" +#include "intel_display_types.h" + +TRACE_EVENT(intel_pipe_enable, + TP_PROTO(struct intel_crtc *crtc), + TP_ARGS(crtc), + + TP_STRUCT__entry( + __array(u32, frame, 3) + __array(u32, scanline, 3) + __field(enum pipe, pipe) + ), + TP_fast_assign( + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_crtc *it__; + 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__); + } + __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), + __entry->frame[PIPE_A], __entry->scanline[PIPE_A], + __entry->frame[PIPE_B], __entry->scanline[PIPE_B], + __entry->frame[PIPE_C], __entry->scanline[PIPE_C]) +); + +TRACE_EVENT(intel_pipe_disable, + TP_PROTO(struct intel_crtc *crtc), + TP_ARGS(crtc), + + TP_STRUCT__entry( + __array(u32, frame, 3) + __array(u32, scanline, 3) + __field(enum pipe, pipe) + ), + + TP_fast_assign( + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_crtc *it__; + 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__); + } + __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), + __entry->frame[PIPE_A], __entry->scanline[PIPE_A], + __entry->frame[PIPE_B], __entry->scanline[PIPE_B], + __entry->frame[PIPE_C], __entry->scanline[PIPE_C]) +); + +TRACE_EVENT(intel_pipe_crc, + TP_PROTO(struct intel_crtc *crtc, const u32 *crcs), + TP_ARGS(crtc, crcs), + + TP_STRUCT__entry( + __field(enum pipe, pipe) + __field(u32, frame) + __field(u32, scanline) + __array(u32, crcs, 5) + ), + + TP_fast_assign( + __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]) +); + +TRACE_EVENT(intel_cpu_fifo_underrun, + TP_PROTO(struct drm_i915_private *dev_priv, enum pipe pipe), + TP_ARGS(dev_priv, pipe), + + TP_STRUCT__entry( + __field(enum pipe, pipe) + __field(u32, frame) + __field(u32, scanline) + ), + + TP_fast_assign( + struct intel_crtc *crtc = intel_crtc_for_pipe(dev_priv, pipe); + __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), + __entry->frame, __entry->scanline) +); + +TRACE_EVENT(intel_pch_fifo_underrun, + TP_PROTO(struct drm_i915_private *dev_priv, enum pipe pch_transcoder), + TP_ARGS(dev_priv, pch_transcoder), + + TP_STRUCT__entry( + __field(enum pipe, pipe) + __field(u32, frame) + __field(u32, scanline) + ), + + TP_fast_assign( + enum pipe pipe = pch_transcoder; + struct intel_crtc *crtc = intel_crtc_for_pipe(dev_priv, pipe); + __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), + __entry->frame, __entry->scanline) +); + +TRACE_EVENT(intel_memory_cxsr, + TP_PROTO(struct drm_i915_private *dev_priv, bool old, bool new), + TP_ARGS(dev_priv, old, new), + + TP_STRUCT__entry( + __array(u32, frame, 3) + __array(u32, scanline, 3) + __field(bool, old) + __field(bool, new) + ), + + TP_fast_assign( + struct intel_crtc *crtc; + 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); + } + __entry->old = old; + __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", + onoff(__entry->old), onoff(__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]) +); + +TRACE_EVENT(g4x_wm, + TP_PROTO(struct intel_crtc *crtc, const struct g4x_wm_values *wm), + TP_ARGS(crtc, wm), + + TP_STRUCT__entry( + __field(enum pipe, pipe) + __field(u32, frame) + __field(u32, scanline) + __field(u16, primary) + __field(u16, sprite) + __field(u16, cursor) + __field(u16, sr_plane) + __field(u16, sr_cursor) + __field(u16, sr_fbc) + __field(u16, hpll_plane) + __field(u16, hpll_cursor) + __field(u16, hpll_fbc) + __field(bool, cxsr) + __field(bool, hpll) + __field(bool, fbc) + ), + + TP_fast_assign( + __entry->pipe = crtc->pipe; + __entry->frame = intel_crtc_get_vblank_counter(crtc); + __entry->scanline = intel_get_crtc_scanline(crtc); + __entry->primary = wm->pipe[crtc->pipe].plane[PLANE_PRIMARY]; + __entry->sprite = wm->pipe[crtc->pipe].plane[PLANE_SPRITE0]; + __entry->cursor = wm->pipe[crtc->pipe].plane[PLANE_CURSOR]; + __entry->sr_plane = wm->sr.plane; + __entry->sr_cursor = wm->sr.cursor; + __entry->sr_fbc = wm->sr.fbc; + __entry->hpll_plane = wm->hpll.plane; + __entry->hpll_cursor = wm->hpll.cursor; + __entry->hpll_fbc = wm->hpll.fbc; + __entry->cxsr = wm->cxsr; + __entry->hpll = wm->hpll_en; + __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, + __entry->primary, __entry->sprite, __entry->cursor, + yesno(__entry->cxsr), __entry->sr_plane, __entry->sr_cursor, __entry->sr_fbc, + yesno(__entry->hpll), __entry->hpll_plane, __entry->hpll_cursor, __entry->hpll_fbc, + yesno(__entry->fbc)) +); + +TRACE_EVENT(vlv_wm, + TP_PROTO(struct intel_crtc *crtc, const struct vlv_wm_values *wm), + TP_ARGS(crtc, wm), + + TP_STRUCT__entry( + __field(enum pipe, pipe) + __field(u32, frame) + __field(u32, scanline) + __field(u32, level) + __field(u32, cxsr) + __field(u32, primary) + __field(u32, sprite0) + __field(u32, sprite1) + __field(u32, cursor) + __field(u32, sr_plane) + __field(u32, sr_cursor) + ), + + TP_fast_assign( + __entry->pipe = crtc->pipe; + __entry->frame = intel_crtc_get_vblank_counter(crtc); + __entry->scanline = intel_get_crtc_scanline(crtc); + __entry->level = wm->level; + __entry->cxsr = wm->cxsr; + __entry->primary = wm->pipe[crtc->pipe].plane[PLANE_PRIMARY]; + __entry->sprite0 = wm->pipe[crtc->pipe].plane[PLANE_SPRITE0]; + __entry->sprite1 = wm->pipe[crtc->pipe].plane[PLANE_SPRITE1]; + __entry->cursor = wm->pipe[crtc->pipe].plane[PLANE_CURSOR]; + __entry->sr_plane = wm->sr.plane; + __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, + __entry->primary, __entry->sprite0, __entry->sprite1, __entry->cursor, + __entry->sr_plane, __entry->sr_cursor) +); + +TRACE_EVENT(vlv_fifo_size, + TP_PROTO(struct intel_crtc *crtc, u32 sprite0_start, u32 sprite1_start, u32 fifo_size), + TP_ARGS(crtc, sprite0_start, sprite1_start, fifo_size), + + TP_STRUCT__entry( + __field(enum pipe, pipe) + __field(u32, frame) + __field(u32, scanline) + __field(u32, sprite0_start) + __field(u32, sprite1_start) + __field(u32, fifo_size) + ), + + TP_fast_assign( + __entry->pipe = crtc->pipe; + __entry->frame = intel_crtc_get_vblank_counter(crtc); + __entry->scanline = intel_get_crtc_scanline(crtc); + __entry->sprite0_start = sprite0_start; + __entry->sprite1_start = sprite1_start; + __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) +); + +TRACE_EVENT(intel_plane_update_noarm, + TP_PROTO(struct drm_plane *plane, struct intel_crtc *crtc), + TP_ARGS(plane, crtc), + + TP_STRUCT__entry( + __field(enum pipe, pipe) + __field(u32, frame) + __field(u32, scanline) + __array(int, src, 4) + __array(int, dst, 4) + __string(name, plane->name) + ), + + TP_fast_assign( + __assign_str(name, plane->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)); + ), + + TP_printk("pipe %c, plane %s, frame=%u, scanline=%u, " DRM_RECT_FP_FMT " -> " DRM_RECT_FMT, + 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_ARGS(plane, crtc), + + TP_STRUCT__entry( + __field(enum pipe, pipe) + __field(u32, frame) + __field(u32, scanline) + __array(int, src, 4) + __array(int, dst, 4) + __string(name, plane->name) + ), + + TP_fast_assign( + __assign_str(name, plane->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)); + ), + + TP_printk("pipe %c, plane %s, frame=%u, scanline=%u, " DRM_RECT_FP_FMT " -> " DRM_RECT_FMT, + 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_ARGS(plane, crtc), + + TP_STRUCT__entry( + __field(enum pipe, pipe) + __field(u32, frame) + __field(u32, scanline) + __string(name, plane->name) + ), + + TP_fast_assign( + __assign_str(name, plane->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), + __entry->frame, __entry->scanline) +); + +TRACE_EVENT(intel_fbc_activate, + TP_PROTO(struct intel_plane *plane), + TP_ARGS(plane), + + TP_STRUCT__entry( + __field(enum pipe, pipe) + __field(u32, frame) + __field(u32, scanline) + ), + + TP_fast_assign( + struct intel_crtc *crtc = intel_crtc_for_pipe(to_i915(plane->base.dev), + plane->pipe); + __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) +); + +TRACE_EVENT(intel_fbc_deactivate, + TP_PROTO(struct intel_plane *plane), + TP_ARGS(plane), + + TP_STRUCT__entry( + __field(enum pipe, pipe) + __field(u32, frame) + __field(u32, scanline) + ), + + TP_fast_assign( + struct intel_crtc *crtc = intel_crtc_for_pipe(to_i915(plane->base.dev), + plane->pipe); + __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) +); + +TRACE_EVENT(intel_fbc_nuke, + TP_PROTO(struct intel_plane *plane), + TP_ARGS(plane), + + TP_STRUCT__entry( + __field(enum pipe, pipe) + __field(u32, frame) + __field(u32, scanline) + ), + + TP_fast_assign( + struct intel_crtc *crtc = intel_crtc_for_pipe(to_i915(plane->base.dev), + plane->pipe); + __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) +); + +TRACE_EVENT(intel_crtc_vblank_work_start, + TP_PROTO(struct intel_crtc *crtc), + TP_ARGS(crtc), + + TP_STRUCT__entry( + __field(enum pipe, pipe) + __field(u32, frame) + __field(u32, scanline) + ), + + TP_fast_assign( + __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) +); + +TRACE_EVENT(intel_crtc_vblank_work_end, + TP_PROTO(struct intel_crtc *crtc), + TP_ARGS(crtc), + + TP_STRUCT__entry( + __field(enum pipe, pipe) + __field(u32, frame) + __field(u32, scanline) + ), + + TP_fast_assign( + __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) +); + +TRACE_EVENT(intel_pipe_update_start, + TP_PROTO(struct intel_crtc *crtc), + TP_ARGS(crtc), + + TP_STRUCT__entry( + __field(enum pipe, pipe) + __field(u32, frame) + __field(u32, scanline) + __field(u32, min) + __field(u32, max) + ), + + TP_fast_assign( + __entry->pipe = crtc->pipe; + __entry->frame = intel_crtc_get_vblank_counter(crtc); + __entry->scanline = intel_get_crtc_scanline(crtc); + __entry->min = crtc->debug.min_vbl; + __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) +); + +TRACE_EVENT(intel_pipe_update_vblank_evaded, + TP_PROTO(struct intel_crtc *crtc), + TP_ARGS(crtc), + + TP_STRUCT__entry( + __field(enum pipe, pipe) + __field(u32, frame) + __field(u32, scanline) + __field(u32, min) + __field(u32, max) + ), + + TP_fast_assign( + __entry->pipe = crtc->pipe; + __entry->frame = crtc->debug.start_vbl_count; + __entry->scanline = crtc->debug.scanline_start; + __entry->min = crtc->debug.min_vbl; + __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) +); + +TRACE_EVENT(intel_pipe_update_end, + TP_PROTO(struct intel_crtc *crtc, u32 frame, int scanline_end), + TP_ARGS(crtc, frame, scanline_end), + + TP_STRUCT__entry( + __field(enum pipe, pipe) + __field(u32, frame) + __field(u32, scanline) + ), + + TP_fast_assign( + __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) +); + +TRACE_EVENT(intel_frontbuffer_invalidate, + TP_PROTO(unsigned int frontbuffer_bits, unsigned int origin), + TP_ARGS(frontbuffer_bits, origin), + + TP_STRUCT__entry( + __field(unsigned int, frontbuffer_bits) + __field(unsigned int, origin) + ), + + TP_fast_assign( + __entry->frontbuffer_bits = frontbuffer_bits; + __entry->origin = origin; + ), + + TP_printk("frontbuffer_bits=0x%08x, origin=%u", + __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_STRUCT__entry( + __field(unsigned int, frontbuffer_bits) + __field(unsigned int, origin) + ), + + TP_fast_assign( + __entry->frontbuffer_bits = frontbuffer_bits; + __entry->origin = origin; + ), + + TP_printk("frontbuffer_bits=0x%08x, origin=%u", + __entry->frontbuffer_bits, __entry->origin) +); + +#endif /* __INTEL_DISPLAY_TRACE_H__ */ + +/* This part must be outside protection */ +#undef TRACE_INCLUDE_PATH +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_PATH ../../drivers/gpu/drm/i915/display +#define TRACE_INCLUDE_FILE intel_display_trace +#include <trace/define_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 aa7238245b0e..c9c6efadf8b4 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -28,6 +28,7 @@ #include <linux/async.h> #include <linux/i2c.h> +#include <linux/pm_qos.h> #include <linux/pwm.h> #include <linux/sched/clock.h> @@ -35,20 +36,30 @@ #include <drm/drm_crtc.h> #include <drm/drm_dp_dual_mode_helper.h> #include <drm/drm_dp_mst_helper.h> +#include <drm/drm_dsc.h> #include <drm/drm_encoder.h> #include <drm/drm_fb_helper.h> #include <drm/drm_fourcc.h> #include <drm/drm_probe_helper.h> #include <drm/drm_rect.h> #include <drm/drm_vblank.h> +#include <drm/drm_vblank_work.h> #include <drm/i915_mei_hdcp_interface.h> #include <media/cec-notifier.h> -#include "i915_drv.h" +#include "i915_vma.h" +#include "i915_vma_types.h" +#include "intel_bios.h" +#include "intel_display.h" +#include "intel_display_power.h" +#include "intel_dpll_mgr.h" +#include "intel_pm_types.h" struct drm_printer; struct __intel_global_objs_state; struct intel_ddi_buf_trans; +struct intel_fbc; +struct intel_connector; /* * Display related stuff @@ -115,7 +126,8 @@ struct intel_fb_view { * bytes for 0/180 degree rotation * pixels for 90/270 degree rotation */ - unsigned int stride; + unsigned int mapping_stride; + unsigned int scanout_stride; } color_plane[4]; }; @@ -194,10 +206,6 @@ struct intel_encoder { void (*update_complete)(struct intel_atomic_state *, struct intel_encoder *, struct intel_crtc *); - void (*pre_disable)(struct intel_atomic_state *, - struct intel_encoder *, - const struct intel_crtc_state *, - const struct drm_connector_state *); void (*disable)(struct intel_atomic_state *, struct intel_encoder *, const struct intel_crtc_state *, @@ -687,6 +695,8 @@ struct intel_plane_state { /* Clear Color Value */ u64 ccval; + + const char *no_fbc_reason; }; struct intel_initial_plane_config { @@ -949,7 +959,6 @@ struct intel_crtc_state { * accordingly. */ #define PIPE_CONFIG_QUIRK_MODE_SYNC_FLAGS (1<<0) /* unreliable sync mode.flags */ -#define PIPE_CONFIG_QUIRK_BIGJOINER_SLAVE (1<<1) /* bigjoiner slave, partial readout */ unsigned long quirks; unsigned fb_bits; /* framebuffers to flip */ @@ -1118,8 +1127,6 @@ struct intel_crtc_state { bool crc_enabled; - bool enable_fbc; - bool double_wide; int pbn; @@ -1241,6 +1248,9 @@ struct intel_crtc_state { u8 link_count; u8 pixel_overlap; } splitter; + + /* for loading single buffered registers during vblank */ + struct drm_vblank_work vblank_work; }; enum intel_pipe_crc_source { @@ -1325,6 +1335,9 @@ struct intel_crtc { /* scalers available on this crtc */ int num_scalers; + /* for loading single buffered registers during vblank */ + struct pm_qos_request vblank_pm_qos; + #ifdef CONFIG_DEBUG_FS struct intel_pipe_crc pipe_crc; #endif @@ -1335,8 +1348,6 @@ struct intel_plane { enum i9xx_plane_id i9xx_plane; enum plane_id id; enum pipe pipe; - bool has_fbc; - bool has_ccs; bool need_async_flip_disable_wa; u32 frontbuffer_bit; @@ -1344,6 +1355,8 @@ struct intel_plane { u32 base, cntl, size; } cursor; + struct intel_fbc *fbc; + /* * NOTE: Do not place new plane state fields here (e.g., when adding * new plane properties). New runtime state should now be placed in @@ -1362,11 +1375,17 @@ struct intel_plane { unsigned int (*max_stride)(struct intel_plane *plane, u32 pixel_format, u64 modifier, unsigned int rotation); - void (*update_plane)(struct intel_plane *plane, + /* Write all non-self arming plane registers */ + void (*update_noarm)(struct intel_plane *plane, const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state); - void (*disable_plane)(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state); + /* Write all self-arming plane registers */ + void (*update_arm)(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state); + /* Disable the plane, must arm */ + void (*disable_arm)(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state); bool (*get_hw_state)(struct intel_plane *plane, enum pipe *pipe); int (*check_plane)(struct intel_crtc_state *crtc_state, struct intel_plane_state *plane_state); @@ -1563,6 +1582,8 @@ struct intel_dp { int num_sink_rates; int sink_rates[DP_MAX_SUPPORTED_RATES]; bool use_rate_select; + /* Max sink lane count as reported by DP_MAX_LANE_COUNT */ + int max_sink_lane_count; /* intersection of source and sink rates */ int num_common_rates; int common_rates[DP_MAX_SUPPORTED_RATES]; @@ -1760,35 +1781,6 @@ vlv_pipe_to_channel(enum pipe pipe) } } -static inline bool intel_pipe_valid(struct drm_i915_private *i915, enum pipe pipe) -{ - return (pipe >= 0 && - pipe < ARRAY_SIZE(i915->pipe_to_crtc_mapping) && - INTEL_INFO(i915)->pipe_mask & BIT(pipe) && - i915->pipe_to_crtc_mapping[pipe]); -} - -static inline struct intel_crtc * -intel_get_first_crtc(struct drm_i915_private *dev_priv) -{ - return to_intel_crtc(drm_crtc_from_index(&dev_priv->drm, 0)); -} - -static inline struct intel_crtc * -intel_get_crtc_for_pipe(struct drm_i915_private *dev_priv, enum pipe pipe) -{ - /* pipe_to_crtc_mapping may have hole on any of 3 display pipe system */ - drm_WARN_ON(&dev_priv->drm, - !(INTEL_INFO(dev_priv)->pipe_mask & BIT(pipe))); - return dev_priv->pipe_to_crtc_mapping[pipe]; -} - -static inline struct intel_crtc * -intel_get_crtc_for_plane(struct drm_i915_private *dev_priv, enum i9xx_plane_id plane) -{ - return dev_priv->plane_to_crtc_mapping[plane]; -} - struct intel_load_detect_pipe { struct drm_atomic_state *restore_state; }; @@ -1898,11 +1890,7 @@ dp_to_lspcon(struct intel_dp *intel_dp) return &dp_to_dig_port(intel_dp)->lspcon; } -static inline struct drm_i915_private * -dp_to_i915(struct intel_dp *intel_dp) -{ - return to_i915(dp_to_dig_port(intel_dp)->base.base.dev); -} +#define dp_to_i915(__intel_dp) to_i915(dp_to_dig_port(__intel_dp)->base.base.dev) #define CAN_PSR(intel_dp) ((intel_dp)->psr.sink_support && \ (intel_dp)->psr.source_support) @@ -2006,33 +1994,6 @@ intel_crtc_needs_modeset(const struct intel_crtc_state *crtc_state) return drm_atomic_crtc_needs_modeset(&crtc_state->uapi); } -static inline void -intel_wait_for_vblank(struct drm_i915_private *dev_priv, enum pipe pipe) -{ - struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe); - - drm_crtc_wait_one_vblank(&crtc->base); -} - -static inline void -intel_wait_for_vblank_if_active(struct drm_i915_private *dev_priv, enum pipe pipe) -{ - const struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe); - - if (crtc->active) - intel_wait_for_vblank(dev_priv, pipe); -} - -static inline bool intel_modifier_uses_dpt(struct drm_i915_private *i915, u64 modifier) -{ - return DISPLAY_VER(i915) >= 13 && modifier != DRM_FORMAT_MOD_LINEAR; -} - -static inline bool intel_fb_uses_dpt(const struct drm_framebuffer *fb) -{ - return fb && intel_modifier_uses_dpt(to_i915(fb->dev), fb->modifier); -} - static inline u32 intel_plane_ggtt_offset(const struct intel_plane_state *plane_state) { return i915_ggtt_offset(plane_state->ggtt_vma); @@ -2044,20 +2005,4 @@ to_intel_frontbuffer(struct drm_framebuffer *fb) return fb ? to_intel_framebuffer(fb)->frontbuffer : NULL; } -static inline bool is_ccs_modifier(u64 modifier) -{ - return modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS || - modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC || - modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS || - modifier == I915_FORMAT_MOD_Y_TILED_CCS || - modifier == I915_FORMAT_MOD_Yf_TILED_CCS; -} - -static inline bool is_gen12_ccs_modifier(u64 modifier) -{ - return modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS || - modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC || - modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS; -} - #endif /* __INTEL_DISPLAY_TYPES_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_dmc.c b/drivers/gpu/drm/i915/display/intel_dmc.c index aef69522f0be..a69b28d65a9b 100644 --- a/drivers/gpu/drm/i915/display/intel_dmc.c +++ b/drivers/gpu/drm/i915/display/intel_dmc.c @@ -45,8 +45,10 @@ #define GEN12_DMC_MAX_FW_SIZE ICL_DMC_MAX_FW_SIZE -#define ADLP_DMC_PATH DMC_PATH(adlp, 2, 12) -#define ADLP_DMC_VERSION_REQUIRED DMC_VERSION(2, 12) +#define GEN13_DMC_MAX_FW_SIZE 0x20000 + +#define ADLP_DMC_PATH DMC_PATH(adlp, 2, 14) +#define ADLP_DMC_VERSION_REQUIRED DMC_VERSION(2, 14) MODULE_FIRMWARE(ADLP_DMC_PATH); #define ADLS_DMC_PATH DMC_PATH(adls, 2, 01) @@ -682,7 +684,7 @@ void intel_dmc_ucode_init(struct drm_i915_private *dev_priv) if (IS_ALDERLAKE_P(dev_priv)) { dmc->fw_path = ADLP_DMC_PATH; dmc->required_version = ADLP_DMC_VERSION_REQUIRED; - dmc->max_fw_size = GEN12_DMC_MAX_FW_SIZE; + dmc->max_fw_size = GEN13_DMC_MAX_FW_SIZE; } else if (IS_ALDERLAKE_S(dev_priv)) { dmc->fw_path = ADLS_DMC_PATH; dmc->required_version = ADLS_DMC_VERSION_REQUIRED; diff --git a/drivers/gpu/drm/i915/display/intel_dmc.h b/drivers/gpu/drm/i915/display/intel_dmc.h index c3c00ff03869..b20f3441ca60 100644 --- a/drivers/gpu/drm/i915/display/intel_dmc.h +++ b/drivers/gpu/drm/i915/display/intel_dmc.h @@ -20,6 +20,8 @@ enum { DMC_FW_MAIN = 0, DMC_FW_PIPEA, DMC_FW_PIPEB, + DMC_FW_PIPEC, + DMC_FW_PIPED, DMC_FW_MAX }; diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index a552f05a67e5..b5e2508db1cf 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -47,6 +47,7 @@ #include "intel_audio.h" #include "intel_backlight.h" #include "intel_connector.h" +#include "intel_crtc.h" #include "intel_ddi.h" #include "intel_de.h" #include "intel_display_types.h" @@ -128,7 +129,7 @@ static void intel_dp_set_default_sink_rates(struct intel_dp *intel_dp) } /* update sink rates from dpcd */ -static void intel_dp_set_sink_rates(struct intel_dp *intel_dp) +static void intel_dp_set_dpcd_sink_rates(struct intel_dp *intel_dp) { static const int dp_rates[] = { 162000, 270000, 540000, 810000 @@ -198,6 +199,54 @@ static void intel_dp_set_sink_rates(struct intel_dp *intel_dp) intel_dp->num_sink_rates = i; } +static void intel_dp_set_sink_rates(struct intel_dp *intel_dp) +{ + struct intel_connector *connector = intel_dp->attached_connector; + struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); + struct intel_encoder *encoder = &intel_dig_port->base; + + intel_dp_set_dpcd_sink_rates(intel_dp); + + if (intel_dp->num_sink_rates) + return; + + drm_err(&dp_to_i915(intel_dp)->drm, + "[CONNECTOR:%d:%s][ENCODER:%d:%s] Invalid DPCD with no link rates, using defaults\n", + connector->base.base.id, connector->base.name, + encoder->base.base.id, encoder->base.name); + + intel_dp_set_default_sink_rates(intel_dp); +} + +static void intel_dp_set_default_max_sink_lane_count(struct intel_dp *intel_dp) +{ + intel_dp->max_sink_lane_count = 1; +} + +static void intel_dp_set_max_sink_lane_count(struct intel_dp *intel_dp) +{ + struct intel_connector *connector = intel_dp->attached_connector; + struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); + struct intel_encoder *encoder = &intel_dig_port->base; + + intel_dp->max_sink_lane_count = drm_dp_max_lane_count(intel_dp->dpcd); + + switch (intel_dp->max_sink_lane_count) { + case 1: + case 2: + case 4: + return; + } + + drm_err(&dp_to_i915(intel_dp)->drm, + "[CONNECTOR:%d:%s][ENCODER:%d:%s] Invalid DPCD max lane count (%d), using default\n", + connector->base.base.id, connector->base.name, + encoder->base.base.id, encoder->base.name, + intel_dp->max_sink_lane_count); + + intel_dp_set_default_max_sink_lane_count(intel_dp); +} + /* Get length of rates array potentially limited by max_rate. */ static int intel_dp_rate_limit_len(const int *rates, int len, int max_rate) { @@ -220,10 +269,19 @@ static int intel_dp_common_len_rate_limit(const struct intel_dp *intel_dp, intel_dp->num_common_rates, max_rate); } +static int intel_dp_common_rate(struct intel_dp *intel_dp, int index) +{ + if (drm_WARN_ON(&dp_to_i915(intel_dp)->drm, + index < 0 || index >= intel_dp->num_common_rates)) + return 162000; + + return intel_dp->common_rates[index]; +} + /* Theoretical max between source and sink */ static int intel_dp_max_common_rate(struct intel_dp *intel_dp) { - return intel_dp->common_rates[intel_dp->num_common_rates - 1]; + return intel_dp_common_rate(intel_dp, intel_dp->num_common_rates - 1); } /* Theoretical max between source and sink */ @@ -231,7 +289,7 @@ static int intel_dp_max_common_lane_count(struct intel_dp *intel_dp) { struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); int source_max = dig_port->max_lanes; - int sink_max = drm_dp_max_lane_count(intel_dp->dpcd); + int sink_max = intel_dp->max_sink_lane_count; int fia_max = intel_tc_port_fia_max_lane_count(dig_port); int lttpr_max = drm_dp_lttpr_max_lane_count(intel_dp->lttpr_common_caps); @@ -243,7 +301,15 @@ static int intel_dp_max_common_lane_count(struct intel_dp *intel_dp) int intel_dp_max_lane_count(struct intel_dp *intel_dp) { - return intel_dp->max_link_lane_count; + switch (intel_dp->max_link_lane_count) { + case 1: + case 2: + case 4: + return intel_dp->max_link_lane_count; + default: + MISSING_CASE(intel_dp->max_link_lane_count); + return 1; + } } /* @@ -555,13 +621,13 @@ int intel_dp_get_link_train_fallback_values(struct intel_dp *intel_dp, if (index > 0) { if (intel_dp_is_edp(intel_dp) && !intel_dp_can_link_train_fallback_for_edp(intel_dp, - intel_dp->common_rates[index - 1], + intel_dp_common_rate(intel_dp, index - 1), lane_count)) { drm_dbg_kms(&i915->drm, "Retrying Link training for eDP with same parameters\n"); return 0; } - intel_dp->max_link_rate = intel_dp->common_rates[index - 1]; + intel_dp->max_link_rate = intel_dp_common_rate(intel_dp, index - 1); intel_dp->max_link_lane_count = lane_count; } else if (lane_count > 1) { if (intel_dp_is_edp(intel_dp) && @@ -1001,14 +1067,11 @@ static void intel_dp_print_rates(struct intel_dp *intel_dp) int intel_dp_max_link_rate(struct intel_dp *intel_dp) { - struct drm_i915_private *i915 = dp_to_i915(intel_dp); int len; len = intel_dp_common_len_rate_limit(intel_dp, intel_dp->max_link_rate); - if (drm_WARN_ON(&i915->drm, len <= 0)) - return 162000; - return intel_dp->common_rates[len - 1]; + return intel_dp_common_rate(intel_dp, len - 1); } int intel_dp_rate_select(struct intel_dp *intel_dp, int rate) @@ -1205,7 +1268,7 @@ intel_dp_compute_link_config_wide(struct intel_dp *intel_dp, output_bpp); for (i = 0; i < intel_dp->num_common_rates; i++) { - link_rate = intel_dp->common_rates[i]; + link_rate = intel_dp_common_rate(intel_dp, i); if (link_rate < limits->min_rate || link_rate > limits->max_rate) continue; @@ -1284,7 +1347,7 @@ static int intel_dp_dsc_compute_params(struct intel_encoder *encoder, else vdsc_cfg->slice_height = 2; - ret = intel_dsc_compute_params(encoder, crtc_state); + ret = intel_dsc_compute_params(crtc_state); if (ret) return ret; @@ -1453,17 +1516,10 @@ intel_dp_compute_link_config(struct intel_encoder *encoder, &pipe_config->hw.adjusted_mode; struct intel_dp *intel_dp = enc_to_intel_dp(encoder); struct link_config_limits limits; - int common_len; int ret; - common_len = intel_dp_common_len_rate_limit(intel_dp, - intel_dp->max_link_rate); - - /* No common link rates between source and sink */ - drm_WARN_ON(encoder->base.dev, common_len <= 0); - - limits.min_rate = intel_dp->common_rates[0]; - limits.max_rate = intel_dp->common_rates[common_len - 1]; + limits.min_rate = intel_dp_common_rate(intel_dp, 0); + limits.max_rate = intel_dp_max_link_rate(intel_dp); limits.min_lane_count = 1; limits.max_lane_count = intel_dp_max_lane_count(intel_dp); @@ -2154,6 +2210,18 @@ static int intel_dp_hdmi_sink_max_frl(struct intel_dp *intel_dp) return max_frl_rate; } +static bool +intel_dp_pcon_is_frl_trained(struct intel_dp *intel_dp, + u8 max_frl_bw_mask, u8 *frl_trained_mask) +{ + if (drm_dp_pcon_hdmi_link_active(&intel_dp->aux) && + drm_dp_pcon_hdmi_link_mode(&intel_dp->aux, frl_trained_mask) == DP_PCON_HDMI_MODE_FRL && + *frl_trained_mask >= max_frl_bw_mask) + return true; + + return false; +} + static int intel_dp_pcon_start_frl_training(struct intel_dp *intel_dp) { #define TIMEOUT_FRL_READY_MS 500 @@ -2164,10 +2232,6 @@ static int intel_dp_pcon_start_frl_training(struct intel_dp *intel_dp) u8 max_frl_bw_mask = 0, frl_trained_mask; bool is_active; - ret = drm_dp_pcon_reset_frl_config(&intel_dp->aux); - if (ret < 0) - return ret; - max_pcon_frl_bw = intel_dp->dfp.pcon_max_frl_bw; drm_dbg(&i915->drm, "PCON max rate = %d Gbps\n", max_pcon_frl_bw); @@ -2179,6 +2243,12 @@ static int intel_dp_pcon_start_frl_training(struct intel_dp *intel_dp) if (max_frl_bw <= 0) return -EINVAL; + max_frl_bw_mask = intel_dp_pcon_set_frl_mask(max_frl_bw); + drm_dbg(&i915->drm, "MAX_FRL_BW_MASK = %u\n", max_frl_bw_mask); + + if (intel_dp_pcon_is_frl_trained(intel_dp, max_frl_bw_mask, &frl_trained_mask)) + goto frl_trained; + ret = drm_dp_pcon_frl_prepare(&intel_dp->aux, false); if (ret < 0) return ret; @@ -2188,7 +2258,6 @@ static int intel_dp_pcon_start_frl_training(struct intel_dp *intel_dp) if (!is_active) return -ETIMEDOUT; - max_frl_bw_mask = intel_dp_pcon_set_frl_mask(max_frl_bw); ret = drm_dp_pcon_frl_configure_1(&intel_dp->aux, max_frl_bw, DP_PCON_ENABLE_SEQUENTIAL_LINK); if (ret < 0) @@ -2204,19 +2273,15 @@ static int intel_dp_pcon_start_frl_training(struct intel_dp *intel_dp) * Wait for FRL to be completed * Check if the HDMI Link is up and active. */ - wait_for(is_active = drm_dp_pcon_hdmi_link_active(&intel_dp->aux) == true, TIMEOUT_HDMI_LINK_ACTIVE_MS); + wait_for(is_active = + intel_dp_pcon_is_frl_trained(intel_dp, max_frl_bw_mask, &frl_trained_mask), + TIMEOUT_HDMI_LINK_ACTIVE_MS); if (!is_active) return -ETIMEDOUT; - /* Verify HDMI Link configuration shows FRL Mode */ - if (drm_dp_pcon_hdmi_link_mode(&intel_dp->aux, &frl_trained_mask) != - DP_PCON_HDMI_MODE_FRL) { - drm_dbg(&i915->drm, "HDMI couldn't be trained in FRL Mode\n"); - return -EINVAL; - } - drm_dbg(&i915->drm, "MAX_FRL_MASK = %u, FRL_TRAINED_MASK = %u\n", max_frl_bw_mask, frl_trained_mask); - +frl_trained: + drm_dbg(&i915->drm, "FRL_TRAINED_MASK = %u\n", frl_trained_mask); intel_dp->frl.trained_rate_gbps = intel_dp_pcon_get_frl_mask(frl_trained_mask); intel_dp->frl.is_trained = true; drm_dbg(&i915->drm, "FRL trained with : %d Gbps\n", intel_dp->frl.trained_rate_gbps); @@ -2234,6 +2299,28 @@ static bool intel_dp_is_hdmi_2_1_sink(struct intel_dp *intel_dp) return false; } +static +int intel_dp_pcon_set_tmds_mode(struct intel_dp *intel_dp) +{ + int ret; + u8 buf = 0; + + /* Set PCON source control mode */ + buf |= DP_PCON_ENABLE_SOURCE_CTL_MODE; + + ret = drm_dp_dpcd_writeb(&intel_dp->aux, DP_PCON_HDMI_LINK_CONFIG_1, buf); + if (ret < 0) + return ret; + + /* Set HDMI LINK ENABLE */ + buf |= DP_PCON_ENABLE_HDMI_LINK; + ret = drm_dp_dpcd_writeb(&intel_dp->aux, DP_PCON_HDMI_LINK_CONFIG_1, buf); + if (ret < 0) + return ret; + + return 0; +} + void intel_dp_check_frl_training(struct intel_dp *intel_dp) { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); @@ -2252,7 +2339,7 @@ void intel_dp_check_frl_training(struct intel_dp *intel_dp) int ret, mode; drm_dbg(&dev_priv->drm, "Couldn't set FRL mode, continuing with TMDS mode\n"); - ret = drm_dp_pcon_reset_frl_config(&intel_dp->aux); + ret = intel_dp_pcon_set_tmds_mode(intel_dp); mode = drm_dp_pcon_hdmi_link_mode(&intel_dp->aux, NULL); if (ret < 0 || mode != DP_PCON_HDMI_MODE_TMDS) @@ -2614,6 +2701,7 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp) intel_dp->use_rate_select = true; else intel_dp_set_sink_rates(intel_dp); + intel_dp_set_max_sink_lane_count(intel_dp); intel_dp_set_common_rates(intel_dp); intel_dp_reset_max_link_params(intel_dp); @@ -2659,6 +2747,7 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp) drm_dp_is_branch(intel_dp->dpcd)); intel_dp_set_sink_rates(intel_dp); + intel_dp_set_max_sink_lane_count(intel_dp); intel_dp_set_common_rates(intel_dp); } @@ -3817,7 +3906,7 @@ int intel_dp_retrain_link(struct intel_encoder *encoder, to_intel_crtc_state(crtc->base.state); /* Keep underrun reporting disabled until things are stable */ - intel_wait_for_vblank(dev_priv, crtc->pipe); + intel_crtc_wait_for_next_vblank(crtc); intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, true); if (crtc_state->has_pch_encoder) @@ -4971,7 +5060,7 @@ static void intel_dp_modeset_retry_work_fn(struct work_struct *work) DRM_MODE_LINK_STATUS_BAD); mutex_unlock(&connector->dev->mode_config.mutex); /* Send Hotplug uevent so userspace can reprobe */ - drm_kms_helper_hotplug_event(connector->dev); + drm_kms_helper_connector_hotplug_event(connector); } bool @@ -5025,6 +5114,7 @@ intel_dp_init_connector(struct intel_digital_port *dig_port, intel_dp_set_source_rates(intel_dp); intel_dp_set_default_sink_rates(intel_dp); + intel_dp_set_default_max_sink_lane_count(intel_dp); intel_dp_set_common_rates(intel_dp); intel_dp_reset_max_link_params(intel_dp); diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c index 3897468140e0..97cf3cac0105 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c @@ -34,6 +34,7 @@ * for some reason. */ +#include "i915_drv.h" #include "intel_backlight.h" #include "intel_display_types.h" #include "intel_dp.h" @@ -287,6 +288,12 @@ intel_dp_aux_vesa_set_backlight(const struct drm_connector_state *conn_state, u3 struct intel_panel *panel = &connector->panel; struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder); + if (!panel->backlight.edp.vesa.info.aux_set) { + const u32 pwm_level = intel_backlight_level_to_pwm(connector, level); + + intel_backlight_set_pwm_level(conn_state, pwm_level); + } + drm_edp_backlight_set_level(&intel_dp->aux, &panel->backlight.edp.vesa.info, level); } @@ -299,8 +306,13 @@ intel_dp_aux_vesa_enable_backlight(const struct intel_crtc_state *crtc_state, struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder); if (!panel->backlight.edp.vesa.info.aux_enable) { - u32 pwm_level = intel_backlight_invert_pwm_level(connector, - panel->backlight.pwm_level_max); + u32 pwm_level; + + if (!panel->backlight.edp.vesa.info.aux_set) + pwm_level = intel_backlight_level_to_pwm(connector, level); + else + pwm_level = intel_backlight_invert_pwm_level(connector, + panel->backlight.pwm_level_max); panel->backlight.pwm_funcs->enable(crtc_state, conn_state, pwm_level); } @@ -337,7 +349,7 @@ static int intel_dp_aux_vesa_setup_backlight(struct intel_connector *connector, if (ret < 0) return ret; - if (!panel->backlight.edp.vesa.info.aux_enable) { + if (!panel->backlight.edp.vesa.info.aux_set || !panel->backlight.edp.vesa.info.aux_enable) { ret = panel->backlight.pwm_funcs->setup(connector, pipe); if (ret < 0) { drm_err(&i915->drm, @@ -346,14 +358,27 @@ static int intel_dp_aux_vesa_setup_backlight(struct intel_connector *connector, return ret; } } - panel->backlight.max = panel->backlight.edp.vesa.info.max; - panel->backlight.min = 0; - if (current_mode == DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD) { - panel->backlight.level = current_level; - panel->backlight.enabled = panel->backlight.level != 0; + + if (panel->backlight.edp.vesa.info.aux_set) { + panel->backlight.max = panel->backlight.edp.vesa.info.max; + panel->backlight.min = 0; + if (current_mode == DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD) { + panel->backlight.level = current_level; + panel->backlight.enabled = panel->backlight.level != 0; + } else { + panel->backlight.level = panel->backlight.max; + panel->backlight.enabled = false; + } } else { - panel->backlight.level = panel->backlight.max; - panel->backlight.enabled = false; + panel->backlight.max = panel->backlight.pwm_level_max; + panel->backlight.min = panel->backlight.pwm_level_min; + if (current_mode == DP_EDP_BACKLIGHT_CONTROL_MODE_PWM) { + panel->backlight.level = panel->backlight.pwm_funcs->get(connector, pipe); + panel->backlight.enabled = panel->backlight.pwm_enabled; + } else { + panel->backlight.level = panel->backlight.max; + panel->backlight.enabled = false; + } } return 0; @@ -437,11 +462,17 @@ int intel_dp_aux_init_backlight_funcs(struct intel_connector *connector) } /* - * A lot of eDP panels in the wild will report supporting both the - * Intel proprietary backlight control interface, and the VESA - * backlight control interface. Many of these panels are liars though, - * and will only work with the Intel interface. So, always probe for - * that first. + * Since Intel has their own backlight control interface, the majority of machines out there + * using DPCD backlight controls with Intel GPUs will be using this interface as opposed to + * the VESA interface. However, other GPUs (such as Nvidia's) will always use the VESA + * interface. This means that there's quite a number of panels out there that will advertise + * support for both interfaces, primarily systems with Intel/Nvidia hybrid GPU setups. + * + * There's a catch to this though: on many panels that advertise support for both + * interfaces, the VESA backlight interface will stop working once we've programmed the + * panel with Intel's OUI - which is also required for us to be able to detect Intel's + * backlight interface at all. This means that the only sensible way for us to detect both + * interfaces is to probe for Intel's first, and VESA's second. */ if (try_intel_interface && intel_dp_aux_supports_hdr_backlight(connector)) { drm_dbg_kms(dev, "Using Intel proprietary eDP backlight controls\n"); diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c index 85676c953e0a..9451f336f28f 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c @@ -21,11 +21,11 @@ * IN THE SOFTWARE. */ +#include "i915_drv.h" #include "intel_display_types.h" #include "intel_dp.h" #include "intel_dp_link_training.h" - static void intel_dp_reset_lttpr_common_caps(struct intel_dp *intel_dp) { memset(intel_dp->lttpr_common_caps, 0, sizeof(intel_dp->lttpr_common_caps)); @@ -301,7 +301,10 @@ static u8 intel_dp_phy_preemph_max(struct intel_dp *intel_dp, static bool has_per_lane_signal_levels(struct intel_dp *intel_dp, enum drm_dp_phy dp_phy) { - return !intel_dp_phy_is_downstream_of_source(intel_dp, dp_phy); + struct drm_i915_private *i915 = dp_to_i915(intel_dp); + + return !intel_dp_phy_is_downstream_of_source(intel_dp, dp_phy) || + DISPLAY_VER(i915) >= 11; } /* 128b/132b */ @@ -683,15 +686,6 @@ intel_dp_prepare_link_train(struct intel_dp *intel_dp, return true; } -static void intel_dp_link_training_clock_recovery_delay(struct intel_dp *intel_dp, - enum drm_dp_phy dp_phy) -{ - if (dp_phy == DP_PHY_DPRX) - drm_dp_link_train_clock_recovery_delay(&intel_dp->aux, intel_dp->dpcd); - else - drm_dp_lttpr_link_train_clock_recovery_delay(); -} - static bool intel_dp_adjust_request_changed(const struct intel_crtc_state *crtc_state, const u8 old_link_status[DP_LINK_STATUS_SIZE], const u8 new_link_status[DP_LINK_STATUS_SIZE]) @@ -750,6 +744,11 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp, u8 link_status[DP_LINK_STATUS_SIZE]; bool max_vswing_reached = false; char phy_name[10]; + int delay_us; + + delay_us = drm_dp_read_clock_recovery_delay(&intel_dp->aux, + intel_dp->dpcd, dp_phy, + intel_dp_is_uhbr(crtc_state)); intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name)); @@ -777,7 +776,7 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp, voltage_tries = 1; for (cr_tries = 0; cr_tries < max_cr_tries; ++cr_tries) { - intel_dp_link_training_clock_recovery_delay(intel_dp, dp_phy); + usleep_range(delay_us, 2 * delay_us); if (drm_dp_dpcd_read_phy_link_status(&intel_dp->aux, dp_phy, link_status) < 0) { @@ -895,19 +894,6 @@ static u32 intel_dp_training_pattern(struct intel_dp *intel_dp, return DP_TRAINING_PATTERN_2; } -static void -intel_dp_link_training_channel_equalization_delay(struct intel_dp *intel_dp, - enum drm_dp_phy dp_phy) -{ - if (dp_phy == DP_PHY_DPRX) { - drm_dp_link_train_channel_eq_delay(&intel_dp->aux, intel_dp->dpcd); - } else { - const u8 *phy_caps = intel_dp_lttpr_phy_caps(intel_dp, dp_phy); - - drm_dp_lttpr_link_train_channel_eq_delay(&intel_dp->aux, phy_caps); - } -} - /* * Perform the link training channel equalization phase on the given DP PHY * using one of training pattern 2, 3 or 4 depending on the source and @@ -925,6 +911,11 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp, u8 link_status[DP_LINK_STATUS_SIZE]; bool channel_eq = false; char phy_name[10]; + int delay_us; + + delay_us = drm_dp_read_channel_eq_delay(&intel_dp->aux, + intel_dp->dpcd, dp_phy, + intel_dp_is_uhbr(crtc_state)); intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name)); @@ -944,8 +935,8 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp, } for (tries = 0; tries < 5; tries++) { - intel_dp_link_training_channel_equalization_delay(intel_dp, - dp_phy); + usleep_range(delay_us, 2 * delay_us); + if (drm_dp_dpcd_read_phy_link_status(&intel_dp->aux, dp_phy, link_status) < 0) { drm_err(&i915->drm, diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index 89d701e8ae9d..b8bc7d397c81 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -231,6 +231,7 @@ intel_dp_mst_atomic_master_trans_check(struct intel_connector *connector, struct drm_i915_private *dev_priv = to_i915(state->base.dev); struct drm_connector_list_iter connector_list_iter; struct intel_connector *connector_iter; + int ret = 0; if (DISPLAY_VER(dev_priv) < 12) return 0; @@ -243,7 +244,6 @@ intel_dp_mst_atomic_master_trans_check(struct intel_connector *connector, struct intel_digital_connector_state *conn_iter_state; struct intel_crtc_state *crtc_state; struct intel_crtc *crtc; - int ret; if (connector_iter->mst_port != connector->mst_port || connector_iter == connector) @@ -252,8 +252,8 @@ intel_dp_mst_atomic_master_trans_check(struct intel_connector *connector, conn_iter_state = intel_atomic_get_digital_connector_state(state, connector_iter); if (IS_ERR(conn_iter_state)) { - drm_connector_list_iter_end(&connector_list_iter); - return PTR_ERR(conn_iter_state); + ret = PTR_ERR(conn_iter_state); + break; } if (!conn_iter_state->base.crtc) @@ -262,20 +262,18 @@ intel_dp_mst_atomic_master_trans_check(struct intel_connector *connector, crtc = to_intel_crtc(conn_iter_state->base.crtc); crtc_state = intel_atomic_get_crtc_state(&state->base, crtc); if (IS_ERR(crtc_state)) { - drm_connector_list_iter_end(&connector_list_iter); - return PTR_ERR(crtc_state); + ret = PTR_ERR(crtc_state); + break; } ret = drm_atomic_add_affected_planes(&state->base, &crtc->base); - if (ret) { - drm_connector_list_iter_end(&connector_list_iter); - return ret; - } + if (ret) + break; crtc_state->uapi.mode_changed = true; } drm_connector_list_iter_end(&connector_list_iter); - return 0; + return ret; } static int @@ -348,16 +346,6 @@ static void wait_for_act_sent(struct intel_encoder *encoder, drm_dp_check_act_status(&intel_dp->mst_mgr); } -static void intel_mst_pre_disable_dp(struct intel_atomic_state *state, - struct intel_encoder *encoder, - const struct intel_crtc_state *old_crtc_state, - const struct drm_connector_state *old_conn_state) -{ - if (old_crtc_state->has_audio) - intel_audio_codec_disable(encoder, old_crtc_state, - old_conn_state); -} - static void intel_mst_disable_dp(struct intel_atomic_state *state, struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, @@ -382,6 +370,9 @@ static void intel_mst_disable_dp(struct intel_atomic_state *state, if (ret) { drm_dbg_kms(&i915->drm, "failed to update payload %d\n", ret); } + if (old_crtc_state->has_audio) + intel_audio_codec_disable(encoder, + old_crtc_state, old_conn_state); } static void intel_mst_post_disable_dp(struct intel_atomic_state *state, @@ -916,7 +907,6 @@ intel_dp_create_fake_mst_encoder(struct intel_digital_port *dig_port, enum pipe intel_encoder->compute_config = intel_dp_mst_compute_config; intel_encoder->compute_config_late = intel_dp_mst_compute_config_late; - intel_encoder->pre_disable = intel_mst_pre_disable_dp; intel_encoder->disable = intel_mst_disable_dp; intel_encoder->post_disable = intel_mst_post_disable_dp; intel_encoder->update_pipe = intel_ddi_update_pipe; diff --git a/drivers/gpu/drm/i915/display/intel_dpll.c b/drivers/gpu/drm/i915/display/intel_dpll.c index 04a7af8340ca..1ce0c171f4fb 100644 --- a/drivers/gpu/drm/i915/display/intel_dpll.c +++ b/drivers/gpu/drm/i915/display/intel_dpll.c @@ -1823,7 +1823,7 @@ void chv_enable_pll(const struct intel_crtc_state *crtc_state) int vlv_force_pll_on(struct drm_i915_private *dev_priv, enum pipe pipe, const struct dpll *dpll) { - struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe); + struct intel_crtc *crtc = intel_crtc_for_pipe(dev_priv, pipe); struct intel_crtc_state *crtc_state; crtc_state = intel_crtc_state_alloc(crtc); diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c index 0a7e04db04be..fc8fda77483a 100644 --- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c +++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c @@ -26,6 +26,7 @@ #include "intel_dpio_phy.h" #include "intel_dpll.h" #include "intel_dpll_mgr.h" +#include "intel_pch_refclk.h" #include "intel_tc.h" /** @@ -3740,7 +3741,7 @@ static void combo_pll_enable(struct drm_i915_private *dev_priv, * domain. */ pll->wakeref = intel_display_power_get(dev_priv, - POWER_DOMAIN_DPLL_DC_OFF); + POWER_DOMAIN_DC_OFF); } icl_pll_power_enable(dev_priv, pll, enable_reg); @@ -3847,7 +3848,7 @@ static void combo_pll_disable(struct drm_i915_private *dev_priv, if (IS_JSL_EHL(dev_priv) && pll->info->id == DPLL_ID_EHL_DPLL4) - intel_display_power_put(dev_priv, POWER_DOMAIN_DPLL_DC_OFF, + intel_display_power_put(dev_priv, POWER_DOMAIN_DC_OFF, pll->wakeref); } @@ -4231,7 +4232,7 @@ static void readout_dpll_hw_state(struct drm_i915_private *i915, if (IS_JSL_EHL(i915) && pll->on && pll->info->id == DPLL_ID_EHL_DPLL4) { pll->wakeref = intel_display_power_get(i915, - POWER_DOMAIN_DPLL_DC_OFF); + POWER_DOMAIN_DC_OFF); } pll->state.pipe_mask = 0; diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.h b/drivers/gpu/drm/i915/display/intel_dpll_mgr.h index 2f59d863be4c..ef2889753807 100644 --- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.h +++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.h @@ -27,7 +27,6 @@ #include <linux/types.h> -#include "intel_display.h" #include "intel_wakeref.h" /*FIXME: Move this to a more appropriate place. */ @@ -37,6 +36,7 @@ (void) (&__a == &__b); \ __a > __b ? (__a - __b) : (__b - __a); }) +enum tc_port; struct drm_device; struct drm_i915_private; struct intel_atomic_state; diff --git a/drivers/gpu/drm/i915/display/intel_dpt.c b/drivers/gpu/drm/i915/display/intel_dpt.c index 8f7b1f7534a4..8f674745e7e0 100644 --- a/drivers/gpu/drm/i915/display/intel_dpt.c +++ b/drivers/gpu/drm/i915/display/intel_dpt.c @@ -167,6 +167,64 @@ void intel_dpt_unpin(struct i915_address_space *vm) i915_vma_put(dpt->vma); } +/** + * intel_dpt_resume - restore the memory mapping for all DPT FBs during system resume + * @i915: device instance + * + * Restore the memory mapping during system resume for all framebuffers which + * are mapped to HW via a GGTT->DPT page table. The content of these page + * tables are not stored in the hibernation image during S4 and S3RST->S4 + * transitions, so here we reprogram the PTE entries in those tables. + * + * This function must be called after the mappings in GGTT have been restored calling + * i915_ggtt_resume(). + */ +void intel_dpt_resume(struct drm_i915_private *i915) +{ + struct drm_framebuffer *drm_fb; + + if (!HAS_DISPLAY(i915)) + return; + + mutex_lock(&i915->drm.mode_config.fb_lock); + drm_for_each_fb(drm_fb, &i915->drm) { + struct intel_framebuffer *fb = to_intel_framebuffer(drm_fb); + + if (fb->dpt_vm) + i915_ggtt_resume_vm(fb->dpt_vm); + } + mutex_unlock(&i915->drm.mode_config.fb_lock); +} + +/** + * intel_dpt_suspend - suspend the memory mapping for all DPT FBs during system suspend + * @i915: device instance + * + * Suspend the memory mapping during system suspend for all framebuffers which + * are mapped to HW via a GGTT->DPT page table. + * + * This function must be called before the mappings in GGTT are suspended calling + * i915_ggtt_suspend(). + */ +void intel_dpt_suspend(struct drm_i915_private *i915) +{ + struct drm_framebuffer *drm_fb; + + if (!HAS_DISPLAY(i915)) + return; + + mutex_lock(&i915->drm.mode_config.fb_lock); + + drm_for_each_fb(drm_fb, &i915->drm) { + struct intel_framebuffer *fb = to_intel_framebuffer(drm_fb); + + if (fb->dpt_vm) + i915_ggtt_suspend_vm(fb->dpt_vm); + } + + mutex_unlock(&i915->drm.mode_config.fb_lock); +} + struct i915_address_space * intel_dpt_create(struct intel_framebuffer *fb) { @@ -206,7 +264,7 @@ intel_dpt_create(struct intel_framebuffer *fb) vm = &dpt->vm; - vm->gt = &i915->gt; + vm->gt = to_gt(i915); vm->i915 = i915; vm->dma = i915->drm.dev; vm->total = (size / sizeof(gen8_pte_t)) * I915_GTT_PAGE_SIZE; @@ -221,8 +279,6 @@ intel_dpt_create(struct intel_framebuffer *fb) vm->vma_ops.bind_vma = dpt_bind_vma; vm->vma_ops.unbind_vma = dpt_unbind_vma; - vm->vma_ops.set_pages = ggtt_set_pages; - vm->vma_ops.clear_pages = clear_pages; vm->pte_encode = gen8_ggtt_pte_encode; diff --git a/drivers/gpu/drm/i915/display/intel_dpt.h b/drivers/gpu/drm/i915/display/intel_dpt.h index 45142b8f849f..e18a9f767b11 100644 --- a/drivers/gpu/drm/i915/display/intel_dpt.h +++ b/drivers/gpu/drm/i915/display/intel_dpt.h @@ -6,6 +6,8 @@ #ifndef __INTEL_DPT_H__ #define __INTEL_DPT_H__ +struct drm_i915_private; + struct i915_address_space; struct i915_vma; struct intel_framebuffer; @@ -13,6 +15,8 @@ struct intel_framebuffer; void intel_dpt_destroy(struct i915_address_space *vm); struct i915_vma *intel_dpt_pin(struct i915_address_space *vm); void intel_dpt_unpin(struct i915_address_space *vm); +void intel_dpt_suspend(struct drm_i915_private *i915); +void intel_dpt_resume(struct drm_i915_private *i915); struct i915_address_space * intel_dpt_create(struct intel_framebuffer *fb); diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c index 62a8a69f9f5d..83a69a4a4fea 100644 --- a/drivers/gpu/drm/i915/display/intel_dsb.c +++ b/drivers/gpu/drm/i915/display/intel_dsb.c @@ -100,7 +100,7 @@ void intel_dsb_indexed_reg_write(const struct intel_crtc_state *crtc_state, u32 reg_val; if (!dsb) { - intel_de_write(dev_priv, reg, val); + intel_de_write_fw(dev_priv, reg, val); return; } buf = dsb->cmd_buf; @@ -177,7 +177,7 @@ void intel_dsb_reg_write(const struct intel_crtc_state *crtc_state, dsb = crtc_state->dsb; if (!dsb) { - intel_de_write(dev_priv, reg, val); + intel_de_write_fw(dev_priv, reg, val); return; } diff --git a/drivers/gpu/drm/i915/display/intel_dsi.c b/drivers/gpu/drm/i915/display/intel_dsi.c index 6b0301ba046e..a50422e03a7e 100644 --- a/drivers/gpu/drm/i915/display/intel_dsi.c +++ b/drivers/gpu/drm/i915/display/intel_dsi.c @@ -4,6 +4,8 @@ */ #include <drm/drm_mipi_dsi.h> + +#include "i915_drv.h" #include "intel_dsi.h" #include "intel_panel.h" diff --git a/drivers/gpu/drm/i915/display/intel_dsi.h b/drivers/gpu/drm/i915/display/intel_dsi.h index fbc40ffdc02e..a3a906cb097e 100644 --- a/drivers/gpu/drm/i915/display/intel_dsi.h +++ b/drivers/gpu/drm/i915/display/intel_dsi.h @@ -166,57 +166,15 @@ static inline u16 intel_dsi_encoder_ports(struct intel_encoder *encoder) return enc_to_intel_dsi(encoder)->ports; } -/* icl_dsi.c */ -void icl_dsi_init(struct drm_i915_private *dev_priv); -void icl_dsi_frame_update(struct intel_crtc_state *crtc_state); - -/* intel_dsi.c */ int intel_dsi_bitrate(const struct intel_dsi *intel_dsi); int intel_dsi_tlpx_ns(const struct intel_dsi *intel_dsi); enum drm_panel_orientation intel_dsi_get_panel_orientation(struct intel_connector *connector); - -/* vlv_dsi.c */ -void vlv_dsi_wait_for_fifo_empty(struct intel_dsi *intel_dsi, enum port port); -enum mipi_dsi_pixel_format pixel_format_from_register_bits(u32 fmt); int intel_dsi_get_modes(struct drm_connector *connector); enum drm_mode_status intel_dsi_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode); struct intel_dsi_host *intel_dsi_host_init(struct intel_dsi *intel_dsi, const struct mipi_dsi_host_ops *funcs, enum port port); -void vlv_dsi_init(struct drm_i915_private *dev_priv); - -/* vlv_dsi_pll.c */ -int vlv_dsi_pll_compute(struct intel_encoder *encoder, - struct intel_crtc_state *config); -void vlv_dsi_pll_enable(struct intel_encoder *encoder, - const struct intel_crtc_state *config); -void vlv_dsi_pll_disable(struct intel_encoder *encoder); -u32 vlv_dsi_get_pclk(struct intel_encoder *encoder, - struct intel_crtc_state *config); -void vlv_dsi_reset_clocks(struct intel_encoder *encoder, enum port port); - -bool bxt_dsi_pll_is_enabled(struct drm_i915_private *dev_priv); -int bxt_dsi_pll_compute(struct intel_encoder *encoder, - struct intel_crtc_state *config); -void bxt_dsi_pll_enable(struct intel_encoder *encoder, - const struct intel_crtc_state *config); -void bxt_dsi_pll_disable(struct intel_encoder *encoder); -u32 bxt_dsi_get_pclk(struct intel_encoder *encoder, - struct intel_crtc_state *config); -void bxt_dsi_reset_clocks(struct intel_encoder *encoder, enum port port); - -void assert_dsi_pll_enabled(struct drm_i915_private *i915); -void assert_dsi_pll_disabled(struct drm_i915_private *i915); - -/* intel_dsi_vbt.c */ -bool intel_dsi_vbt_init(struct intel_dsi *intel_dsi, u16 panel_id); -void intel_dsi_vbt_gpio_init(struct intel_dsi *intel_dsi, bool panel_is_on); -void intel_dsi_vbt_gpio_cleanup(struct intel_dsi *intel_dsi); -void intel_dsi_vbt_exec_sequence(struct intel_dsi *intel_dsi, - enum mipi_seq seq_id); -void intel_dsi_msleep(struct intel_dsi *intel_dsi, int msec); -void intel_dsi_log_params(struct intel_dsi *intel_dsi); #endif /* _INTEL_DSI_H */ diff --git a/drivers/gpu/drm/i915/display/intel_dsi_dcs_backlight.c b/drivers/gpu/drm/i915/display/intel_dsi_dcs_backlight.c index f61ed82e8867..7d234429e71e 100644 --- a/drivers/gpu/drm/i915/display/intel_dsi_dcs_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_dsi_dcs_backlight.c @@ -71,6 +71,7 @@ static void dcs_set_backlight(const struct drm_connector_state *conn_state, u32 u8 data[2] = {}; enum port port; size_t len = panel->backlight.max > U8_MAX ? 2 : 1; + unsigned long mode_flags; if (len == 1) { data[0] = level; @@ -81,8 +82,11 @@ static void dcs_set_backlight(const struct drm_connector_state *conn_state, u32 for_each_dsi_port(port, intel_dsi->dcs_backlight_ports) { dsi_device = intel_dsi->dsi_hosts[port]->device; + mode_flags = dsi_device->mode_flags; + dsi_device->mode_flags &= ~MIPI_DSI_MODE_LPM; mipi_dsi_dcs_write(dsi_device, MIPI_DCS_SET_DISPLAY_BRIGHTNESS, &data, len); + dsi_device->mode_flags = mode_flags; } } diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c index f241bedb8597..0da91849efde 100644 --- a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c +++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c @@ -41,6 +41,8 @@ #include "i915_drv.h" #include "intel_display_types.h" #include "intel_dsi.h" +#include "intel_dsi_vbt.h" +#include "vlv_dsi.h" #include "vlv_sideband.h" #define MIPI_TRANSFER_MODE_SHIFT 0 diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt.h b/drivers/gpu/drm/i915/display/intel_dsi_vbt.h new file mode 100644 index 000000000000..dc642c1fe7ef --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef __INTEL_DSI_VBT_H__ +#define __INTEL_DSI_VBT_H__ + +#include <linux/types.h> + +enum mipi_seq; +struct intel_dsi; + +bool intel_dsi_vbt_init(struct intel_dsi *intel_dsi, u16 panel_id); +void intel_dsi_vbt_gpio_init(struct intel_dsi *intel_dsi, bool panel_is_on); +void intel_dsi_vbt_gpio_cleanup(struct intel_dsi *intel_dsi); +void intel_dsi_vbt_exec_sequence(struct intel_dsi *intel_dsi, + enum mipi_seq seq_id); +void intel_dsi_msleep(struct intel_dsi *intel_dsi, int msec); +void intel_dsi_log_params(struct intel_dsi *intel_dsi); + +#endif /* __INTEL_DSI_VBT_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_fb.c b/drivers/gpu/drm/i915/display/intel_fb.c index cb511b2b7069..23cfe2e5ce2a 100644 --- a/drivers/gpu/drm/i915/display/intel_fb.c +++ b/drivers/gpu/drm/i915/display/intel_fb.c @@ -6,6 +6,7 @@ #include <drm/drm_framebuffer.h> #include <drm/drm_modeset_helper.h> +#include "i915_drv.h" #include "intel_display.h" #include "intel_display_types.h" #include "intel_dpt.h" @@ -13,26 +14,465 @@ #define check_array_bounds(i915, a, i) drm_WARN_ON(&(i915)->drm, (i) >= ARRAY_SIZE(a)) -bool is_ccs_plane(const struct drm_framebuffer *fb, int plane) +/* + * From the Sky Lake PRM: + * "The Color Control Surface (CCS) contains the compression status of + * the cache-line pairs. The compression state of the cache-line pair + * is specified by 2 bits in the CCS. Each CCS cache-line represents + * an area on the main surface of 16 x16 sets of 128 byte Y-tiled + * cache-line-pairs. CCS is always Y tiled." + * + * Since cache line pairs refers to horizontally adjacent cache lines, + * each cache line in the CCS corresponds to an area of 32x16 cache + * lines on the main surface. Since each pixel is 4 bytes, this gives + * us a ratio of one byte in the CCS for each 8x16 pixels in the + * main surface. + */ +static const struct drm_format_info skl_ccs_formats[] = { + { .format = DRM_FORMAT_XRGB8888, .depth = 24, .num_planes = 2, + .cpp = { 4, 1, }, .hsub = 8, .vsub = 16, }, + { .format = DRM_FORMAT_XBGR8888, .depth = 24, .num_planes = 2, + .cpp = { 4, 1, }, .hsub = 8, .vsub = 16, }, + { .format = DRM_FORMAT_ARGB8888, .depth = 32, .num_planes = 2, + .cpp = { 4, 1, }, .hsub = 8, .vsub = 16, .has_alpha = true, }, + { .format = DRM_FORMAT_ABGR8888, .depth = 32, .num_planes = 2, + .cpp = { 4, 1, }, .hsub = 8, .vsub = 16, .has_alpha = true, }, +}; + +/* + * Gen-12 compression uses 4 bits of CCS data for each cache line pair in the + * main surface. And each 64B CCS cache line represents an area of 4x1 Y-tiles + * in the main surface. With 4 byte pixels and each Y-tile having dimensions of + * 32x32 pixels, the ratio turns out to 1B in the CCS for every 2x32 pixels in + * the main surface. + */ +static const struct drm_format_info gen12_ccs_formats[] = { + { .format = DRM_FORMAT_XRGB8888, .depth = 24, .num_planes = 2, + .char_per_block = { 4, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 }, + .hsub = 1, .vsub = 1, }, + { .format = DRM_FORMAT_XBGR8888, .depth = 24, .num_planes = 2, + .char_per_block = { 4, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 }, + .hsub = 1, .vsub = 1, }, + { .format = DRM_FORMAT_ARGB8888, .depth = 32, .num_planes = 2, + .char_per_block = { 4, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 }, + .hsub = 1, .vsub = 1, .has_alpha = true }, + { .format = DRM_FORMAT_ABGR8888, .depth = 32, .num_planes = 2, + .char_per_block = { 4, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 }, + .hsub = 1, .vsub = 1, .has_alpha = true }, + { .format = DRM_FORMAT_YUYV, .num_planes = 2, + .char_per_block = { 2, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 }, + .hsub = 2, .vsub = 1, .is_yuv = true }, + { .format = DRM_FORMAT_YVYU, .num_planes = 2, + .char_per_block = { 2, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 }, + .hsub = 2, .vsub = 1, .is_yuv = true }, + { .format = DRM_FORMAT_UYVY, .num_planes = 2, + .char_per_block = { 2, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 }, + .hsub = 2, .vsub = 1, .is_yuv = true }, + { .format = DRM_FORMAT_VYUY, .num_planes = 2, + .char_per_block = { 2, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 }, + .hsub = 2, .vsub = 1, .is_yuv = true }, + { .format = DRM_FORMAT_XYUV8888, .num_planes = 2, + .char_per_block = { 4, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 }, + .hsub = 1, .vsub = 1, .is_yuv = true }, + { .format = DRM_FORMAT_NV12, .num_planes = 4, + .char_per_block = { 1, 2, 1, 1 }, .block_w = { 1, 1, 4, 4 }, .block_h = { 1, 1, 1, 1 }, + .hsub = 2, .vsub = 2, .is_yuv = true }, + { .format = DRM_FORMAT_P010, .num_planes = 4, + .char_per_block = { 2, 4, 1, 1 }, .block_w = { 1, 1, 2, 2 }, .block_h = { 1, 1, 1, 1 }, + .hsub = 2, .vsub = 2, .is_yuv = true }, + { .format = DRM_FORMAT_P012, .num_planes = 4, + .char_per_block = { 2, 4, 1, 1 }, .block_w = { 1, 1, 2, 2 }, .block_h = { 1, 1, 1, 1 }, + .hsub = 2, .vsub = 2, .is_yuv = true }, + { .format = DRM_FORMAT_P016, .num_planes = 4, + .char_per_block = { 2, 4, 1, 1 }, .block_w = { 1, 1, 2, 2 }, .block_h = { 1, 1, 1, 1 }, + .hsub = 2, .vsub = 2, .is_yuv = true }, +}; + +/* + * Same as gen12_ccs_formats[] above, but with additional surface used + * to pass Clear Color information in plane 2 with 64 bits of data. + */ +static const struct drm_format_info gen12_ccs_cc_formats[] = { + { .format = DRM_FORMAT_XRGB8888, .depth = 24, .num_planes = 3, + .char_per_block = { 4, 1, 0 }, .block_w = { 1, 2, 2 }, .block_h = { 1, 1, 1 }, + .hsub = 1, .vsub = 1, }, + { .format = DRM_FORMAT_XBGR8888, .depth = 24, .num_planes = 3, + .char_per_block = { 4, 1, 0 }, .block_w = { 1, 2, 2 }, .block_h = { 1, 1, 1 }, + .hsub = 1, .vsub = 1, }, + { .format = DRM_FORMAT_ARGB8888, .depth = 32, .num_planes = 3, + .char_per_block = { 4, 1, 0 }, .block_w = { 1, 2, 2 }, .block_h = { 1, 1, 1 }, + .hsub = 1, .vsub = 1, .has_alpha = true }, + { .format = DRM_FORMAT_ABGR8888, .depth = 32, .num_planes = 3, + .char_per_block = { 4, 1, 0 }, .block_w = { 1, 2, 2 }, .block_h = { 1, 1, 1 }, + .hsub = 1, .vsub = 1, .has_alpha = true }, +}; + +struct intel_modifier_desc { + u64 modifier; + struct { + u8 from; + u8 until; + } display_ver; +#define DISPLAY_VER_ALL { 0, -1 } + + const struct drm_format_info *formats; + int format_count; +#define FORMAT_OVERRIDE(format_list) \ + .formats = format_list, \ + .format_count = ARRAY_SIZE(format_list) + + u8 plane_caps; + + struct { + u8 cc_planes:3; + u8 packed_aux_planes:4; + u8 planar_aux_planes:4; + } ccs; +}; + +#define INTEL_PLANE_CAP_CCS_MASK (INTEL_PLANE_CAP_CCS_RC | \ + INTEL_PLANE_CAP_CCS_RC_CC | \ + INTEL_PLANE_CAP_CCS_MC) +#define INTEL_PLANE_CAP_TILING_MASK (INTEL_PLANE_CAP_TILING_X | \ + INTEL_PLANE_CAP_TILING_Y | \ + INTEL_PLANE_CAP_TILING_Yf) +#define INTEL_PLANE_CAP_TILING_NONE 0 + +static const struct intel_modifier_desc intel_modifiers[] = { + { + .modifier = I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS, + .display_ver = { 12, 13 }, + .plane_caps = INTEL_PLANE_CAP_TILING_Y | INTEL_PLANE_CAP_CCS_MC, + + .ccs.packed_aux_planes = BIT(1), + .ccs.planar_aux_planes = BIT(2) | BIT(3), + + FORMAT_OVERRIDE(gen12_ccs_formats), + }, { + .modifier = I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS, + .display_ver = { 12, 13 }, + .plane_caps = INTEL_PLANE_CAP_TILING_Y | INTEL_PLANE_CAP_CCS_RC, + + .ccs.packed_aux_planes = BIT(1), + + FORMAT_OVERRIDE(gen12_ccs_formats), + }, { + .modifier = I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC, + .display_ver = { 12, 13 }, + .plane_caps = INTEL_PLANE_CAP_TILING_Y | INTEL_PLANE_CAP_CCS_RC_CC, + + .ccs.cc_planes = BIT(2), + .ccs.packed_aux_planes = BIT(1), + + FORMAT_OVERRIDE(gen12_ccs_cc_formats), + }, { + .modifier = I915_FORMAT_MOD_Yf_TILED_CCS, + .display_ver = { 9, 11 }, + .plane_caps = INTEL_PLANE_CAP_TILING_Yf | INTEL_PLANE_CAP_CCS_RC, + + .ccs.packed_aux_planes = BIT(1), + + FORMAT_OVERRIDE(skl_ccs_formats), + }, { + .modifier = I915_FORMAT_MOD_Y_TILED_CCS, + .display_ver = { 9, 11 }, + .plane_caps = INTEL_PLANE_CAP_TILING_Y | INTEL_PLANE_CAP_CCS_RC, + + .ccs.packed_aux_planes = BIT(1), + + FORMAT_OVERRIDE(skl_ccs_formats), + }, { + .modifier = I915_FORMAT_MOD_Yf_TILED, + .display_ver = { 9, 11 }, + .plane_caps = INTEL_PLANE_CAP_TILING_Yf, + }, { + .modifier = I915_FORMAT_MOD_Y_TILED, + .display_ver = { 9, 13 }, + .plane_caps = INTEL_PLANE_CAP_TILING_Y, + }, { + .modifier = I915_FORMAT_MOD_X_TILED, + .display_ver = DISPLAY_VER_ALL, + .plane_caps = INTEL_PLANE_CAP_TILING_X, + }, { + .modifier = DRM_FORMAT_MOD_LINEAR, + .display_ver = DISPLAY_VER_ALL, + }, +}; + +static const struct intel_modifier_desc *lookup_modifier_or_null(u64 modifier) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(intel_modifiers); i++) + if (intel_modifiers[i].modifier == modifier) + return &intel_modifiers[i]; + + return NULL; +} + +static const struct intel_modifier_desc *lookup_modifier(u64 modifier) +{ + const struct intel_modifier_desc *md = lookup_modifier_or_null(modifier); + + if (WARN_ON(!md)) + return &intel_modifiers[0]; + + return md; +} + +static const struct drm_format_info * +lookup_format_info(const struct drm_format_info formats[], + int num_formats, u32 format) +{ + int i; + + for (i = 0; i < num_formats; i++) { + if (formats[i].format == format) + return &formats[i]; + } + + return NULL; +} + +/** + * intel_fb_get_format_info: Get a modifier specific format information + * @cmd: FB add command structure + * + * Returns: + * Returns the format information for @cmd->pixel_format specific to @cmd->modifier[0], + * or %NULL if the modifier doesn't override the format. + */ +const struct drm_format_info * +intel_fb_get_format_info(const struct drm_mode_fb_cmd2 *cmd) +{ + const struct intel_modifier_desc *md = lookup_modifier_or_null(cmd->modifier[0]); + + if (!md || !md->formats) + return NULL; + + return lookup_format_info(md->formats, md->format_count, cmd->pixel_format); +} + +static bool plane_caps_contain_any(u8 caps, u8 mask) +{ + return caps & mask; +} + +static bool plane_caps_contain_all(u8 caps, u8 mask) +{ + return (caps & mask) == mask; +} + +/** + * intel_fb_is_ccs_modifier: Check if a modifier is a CCS modifier type + * @modifier: Modifier to check + * + * Returns: + * Returns %true if @modifier is a render, render with color clear or + * media compression modifier. + */ +bool intel_fb_is_ccs_modifier(u64 modifier) +{ + return plane_caps_contain_any(lookup_modifier(modifier)->plane_caps, + INTEL_PLANE_CAP_CCS_MASK); +} + +/** + * intel_fb_is_rc_ccs_cc_modifier: Check if a modifier is an RC CCS CC modifier type + * @modifier: Modifier to check + * + * Returns: + * Returns %true if @modifier is a render with color clear modifier. + */ +bool intel_fb_is_rc_ccs_cc_modifier(u64 modifier) +{ + return plane_caps_contain_any(lookup_modifier(modifier)->plane_caps, + INTEL_PLANE_CAP_CCS_RC_CC); +} + +/** + * intel_fb_is_mc_ccs_modifier: Check if a modifier is an MC CCS modifier type + * @modifier: Modifier to check + * + * Returns: + * Returns %true if @modifier is a media compression modifier. + */ +bool intel_fb_is_mc_ccs_modifier(u64 modifier) +{ + return plane_caps_contain_any(lookup_modifier(modifier)->plane_caps, + INTEL_PLANE_CAP_CCS_MC); +} + +static bool check_modifier_display_ver_range(const struct intel_modifier_desc *md, + u8 display_ver_from, u8 display_ver_until) +{ + return md->display_ver.from <= display_ver_until && + display_ver_from <= md->display_ver.until; +} + +static bool plane_has_modifier(struct drm_i915_private *i915, + u8 plane_caps, + const struct intel_modifier_desc *md) +{ + if (!IS_DISPLAY_VER(i915, md->display_ver.from, md->display_ver.until)) + return false; + + if (!plane_caps_contain_all(plane_caps, md->plane_caps)) + return false; + + return true; +} + +/** + * intel_fb_plane_get_modifiers: Get the modifiers for the given platform and plane capabilities + * @i915: i915 device instance + * @plane_caps: capabilities for the plane the modifiers are queried for + * + * Returns: + * Returns the list of modifiers allowed by the @i915 platform and @plane_caps. + * The caller must free the returned buffer. + */ +u64 *intel_fb_plane_get_modifiers(struct drm_i915_private *i915, + u8 plane_caps) +{ + u64 *list, *p; + int count = 1; /* +1 for invalid modifier terminator */ + int i; + + for (i = 0; i < ARRAY_SIZE(intel_modifiers); i++) { + if (plane_has_modifier(i915, plane_caps, &intel_modifiers[i])) + count++; + } + + list = kmalloc_array(count, sizeof(*list), GFP_KERNEL); + if (drm_WARN_ON(&i915->drm, !list)) + return NULL; + + p = list; + for (i = 0; i < ARRAY_SIZE(intel_modifiers); i++) { + if (plane_has_modifier(i915, plane_caps, &intel_modifiers[i])) + *p++ = intel_modifiers[i].modifier; + } + *p++ = DRM_FORMAT_MOD_INVALID; + + return list; +} + +/** + * intel_fb_plane_supports_modifier: Determine if a modifier is supported by the given plane + * @plane: Plane to check the modifier support for + * @modifier: The modifier to check the support for + * + * Returns: + * %true if the @modifier is supported on @plane. + */ +bool intel_fb_plane_supports_modifier(struct intel_plane *plane, u64 modifier) +{ + int i; + + for (i = 0; i < plane->base.modifier_count; i++) + if (plane->base.modifiers[i] == modifier) + return true; + + return false; +} + +static bool format_is_yuv_semiplanar(const struct intel_modifier_desc *md, + const struct drm_format_info *info) { - if (!is_ccs_modifier(fb->modifier)) + int yuv_planes; + + if (!info->is_yuv) return false; - return plane >= fb->format->num_planes / 2; + if (plane_caps_contain_any(md->plane_caps, INTEL_PLANE_CAP_CCS_MASK)) + yuv_planes = 4; + else + yuv_planes = 2; + + return info->num_planes == yuv_planes; +} + +/** + * intel_format_info_is_yuv_semiplanar: Check if the given format is YUV semiplanar + * @info: format to check + * @modifier: modifier used with the format + * + * Returns: + * %true if @info / @modifier is YUV semiplanar. + */ +bool intel_format_info_is_yuv_semiplanar(const struct drm_format_info *info, + u64 modifier) +{ + return format_is_yuv_semiplanar(lookup_modifier(modifier), info); +} + +static u8 ccs_aux_plane_mask(const struct intel_modifier_desc *md, + const struct drm_format_info *format) +{ + if (format_is_yuv_semiplanar(md, format)) + return md->ccs.planar_aux_planes; + else + return md->ccs.packed_aux_planes; +} + +/** + * intel_fb_is_ccs_aux_plane: Check if a framebuffer color plane is a CCS AUX plane + * @fb: Framebuffer + * @color_plane: color plane index to check + * + * Returns: + * Returns %true if @fb's color plane at index @color_plane is a CCS AUX plane. + */ +bool intel_fb_is_ccs_aux_plane(const struct drm_framebuffer *fb, int color_plane) +{ + const struct intel_modifier_desc *md = lookup_modifier(fb->modifier); + + return ccs_aux_plane_mask(md, fb->format) & BIT(color_plane); +} + +/** + * intel_fb_is_gen12_ccs_aux_plane: Check if a framebuffer color plane is a GEN12 CCS AUX plane + * @fb: Framebuffer + * @color_plane: color plane index to check + * + * Returns: + * Returns %true if @fb's color plane at index @color_plane is a GEN12 CCS AUX plane. + */ +static bool intel_fb_is_gen12_ccs_aux_plane(const struct drm_framebuffer *fb, int color_plane) +{ + const struct intel_modifier_desc *md = lookup_modifier(fb->modifier); + + return check_modifier_display_ver_range(md, 12, 13) && + ccs_aux_plane_mask(md, fb->format) & BIT(color_plane); } -bool is_gen12_ccs_plane(const struct drm_framebuffer *fb, int plane) +/** + * intel_fb_rc_ccs_cc_plane: Get the CCS CC color plane index for a framebuffer + * @fb: Framebuffer + * + * Returns: + * Returns the index of the color clear plane for @fb, or -1 if @fb is not a + * framebuffer using a render compression/color clear modifier. + */ +int intel_fb_rc_ccs_cc_plane(const struct drm_framebuffer *fb) { - return is_gen12_ccs_modifier(fb->modifier) && is_ccs_plane(fb, plane); + const struct intel_modifier_desc *md = lookup_modifier(fb->modifier); + + if (!md->ccs.cc_planes) + return -1; + + drm_WARN_ON_ONCE(fb->dev, hweight8(md->ccs.cc_planes) > 1); + + return ilog2((int)md->ccs.cc_planes); } -bool is_gen12_ccs_cc_plane(const struct drm_framebuffer *fb, int plane) +static bool is_gen12_ccs_cc_plane(const struct drm_framebuffer *fb, int color_plane) { - return fb->modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC && - plane == 2; + return intel_fb_rc_ccs_cc_plane(fb) == color_plane; } -bool is_semiplanar_uv_plane(const struct drm_framebuffer *fb, int color_plane) +static bool is_semiplanar_uv_plane(const struct drm_framebuffer *fb, int color_plane) { return intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier) && color_plane == 1; @@ -41,12 +481,13 @@ bool is_semiplanar_uv_plane(const struct drm_framebuffer *fb, int color_plane) bool is_surface_linear(const struct drm_framebuffer *fb, int color_plane) { return fb->modifier == DRM_FORMAT_MOD_LINEAR || - is_gen12_ccs_plane(fb, color_plane); + intel_fb_is_gen12_ccs_aux_plane(fb, color_plane) || + is_gen12_ccs_cc_plane(fb, color_plane); } int main_to_ccs_plane(const struct drm_framebuffer *fb, int main_plane) { - drm_WARN_ON(fb->dev, !is_ccs_modifier(fb->modifier) || + drm_WARN_ON(fb->dev, !intel_fb_is_ccs_modifier(fb->modifier) || (main_plane && main_plane >= fb->format->num_planes / 2)); return fb->format->num_planes / 2 + main_plane; @@ -54,7 +495,7 @@ int main_to_ccs_plane(const struct drm_framebuffer *fb, int main_plane) int skl_ccs_to_main_plane(const struct drm_framebuffer *fb, int ccs_plane) { - drm_WARN_ON(fb->dev, !is_ccs_modifier(fb->modifier) || + drm_WARN_ON(fb->dev, !intel_fb_is_ccs_modifier(fb->modifier) || ccs_plane < fb->format->num_planes / 2); if (is_gen12_ccs_cc_plane(fb, ccs_plane)) @@ -63,35 +504,12 @@ int skl_ccs_to_main_plane(const struct drm_framebuffer *fb, int ccs_plane) return ccs_plane - fb->format->num_planes / 2; } -static unsigned int gen12_aligned_scanout_stride(const struct intel_framebuffer *fb, - int color_plane) -{ - struct drm_i915_private *i915 = to_i915(fb->base.dev); - unsigned int stride = fb->base.pitches[color_plane]; - - if (IS_ALDERLAKE_P(i915)) - return roundup_pow_of_two(max(stride, - 8u * intel_tile_width_bytes(&fb->base, color_plane))); - - return stride; -} - static unsigned int gen12_ccs_aux_stride(struct intel_framebuffer *fb, int ccs_plane) { - struct drm_i915_private *i915 = to_i915(fb->base.dev); int main_plane = skl_ccs_to_main_plane(&fb->base, ccs_plane); unsigned int main_stride = fb->base.pitches[main_plane]; unsigned int main_tile_width = intel_tile_width_bytes(&fb->base, main_plane); - /* - * On ADL-P the AUX stride must align with a power-of-two aligned main - * surface stride. The stride of the allocated main surface object can - * be less than this POT stride, which is then autopadded to the POT - * size. - */ - if (IS_ALDERLAKE_P(i915)) - main_stride = gen12_aligned_scanout_stride(fb, main_plane); - return DIV_ROUND_UP(main_stride, 4 * main_tile_width) * 64; } @@ -99,7 +517,7 @@ int skl_main_to_aux_plane(const struct drm_framebuffer *fb, int main_plane) { struct drm_i915_private *i915 = to_i915(fb->dev); - if (is_ccs_modifier(fb->modifier)) + if (intel_fb_is_ccs_modifier(fb->modifier)) return main_to_ccs_plane(fb, main_plane); else if (DISPLAY_VER(i915) < 11 && intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier)) @@ -128,13 +546,14 @@ intel_tile_width_bytes(const struct drm_framebuffer *fb, int color_plane) else return 512; case I915_FORMAT_MOD_Y_TILED_CCS: - if (is_ccs_plane(fb, color_plane)) + if (intel_fb_is_ccs_aux_plane(fb, color_plane)) return 128; fallthrough; case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS: case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC: case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS: - if (is_ccs_plane(fb, color_plane)) + if (intel_fb_is_ccs_aux_plane(fb, color_plane) || + is_gen12_ccs_cc_plane(fb, color_plane)) return 64; fallthrough; case I915_FORMAT_MOD_Y_TILED: @@ -143,7 +562,7 @@ intel_tile_width_bytes(const struct drm_framebuffer *fb, int color_plane) else return 512; case I915_FORMAT_MOD_Yf_TILED_CCS: - if (is_ccs_plane(fb, color_plane)) + if (intel_fb_is_ccs_aux_plane(fb, color_plane)) return 128; fallthrough; case I915_FORMAT_MOD_Yf_TILED: @@ -199,7 +618,7 @@ static void intel_tile_block_dims(const struct drm_framebuffer *fb, int color_pl { intel_tile_dims(fb, color_plane, tile_width, tile_height); - if (is_gen12_ccs_plane(fb, color_plane)) + if (intel_fb_is_gen12_ccs_aux_plane(fb, color_plane)) *tile_height = 1; } @@ -223,20 +642,33 @@ intel_fb_align_height(const struct drm_framebuffer *fb, static unsigned int intel_fb_modifier_to_tiling(u64 fb_modifier) { - switch (fb_modifier) { - case I915_FORMAT_MOD_X_TILED: - return I915_TILING_X; - case I915_FORMAT_MOD_Y_TILED: - case I915_FORMAT_MOD_Y_TILED_CCS: - case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS: - case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC: - case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS: + u8 tiling_caps = lookup_modifier(fb_modifier)->plane_caps & + INTEL_PLANE_CAP_TILING_MASK; + + switch (tiling_caps) { + case INTEL_PLANE_CAP_TILING_Y: return I915_TILING_Y; + case INTEL_PLANE_CAP_TILING_X: + return I915_TILING_X; + case INTEL_PLANE_CAP_TILING_Yf: + case INTEL_PLANE_CAP_TILING_NONE: + return I915_TILING_NONE; default: + MISSING_CASE(tiling_caps); return I915_TILING_NONE; } } +static bool intel_modifier_uses_dpt(struct drm_i915_private *i915, u64 modifier) +{ + return DISPLAY_VER(i915) >= 13 && modifier != DRM_FORMAT_MOD_LINEAR; +} + +bool intel_fb_uses_dpt(const struct drm_framebuffer *fb) +{ + return fb && intel_modifier_uses_dpt(to_i915(fb->dev), fb->modifier); +} + unsigned int intel_cursor_alignment(const struct drm_i915_private *i915) { if (IS_I830(i915)) @@ -271,7 +703,7 @@ unsigned int intel_surf_alignment(const struct drm_framebuffer *fb, return 512 * 4096; /* AUX_DIST needs only 4K alignment */ - if (is_ccs_plane(fb, color_plane)) + if (intel_fb_is_ccs_aux_plane(fb, color_plane)) return 4096; if (is_semiplanar_uv_plane(fb, color_plane)) { @@ -330,7 +762,7 @@ void intel_fb_plane_get_subsampling(int *hsub, int *vsub, * TODO: Deduct the subsampling from the char block for all CCS * formats and planes. */ - if (!is_gen12_ccs_plane(fb, color_plane)) { + if (!intel_fb_is_gen12_ccs_aux_plane(fb, color_plane)) { *hsub = fb->format->hsub; *vsub = fb->format->vsub; @@ -357,24 +789,13 @@ void intel_fb_plane_get_subsampling(int *hsub, int *vsub, static void intel_fb_plane_dims(const struct intel_framebuffer *fb, int color_plane, int *w, int *h) { - struct drm_i915_private *i915 = to_i915(fb->base.dev); - int main_plane = is_ccs_plane(&fb->base, color_plane) ? + int main_plane = intel_fb_is_ccs_aux_plane(&fb->base, color_plane) ? skl_ccs_to_main_plane(&fb->base, color_plane) : 0; unsigned int main_width = fb->base.width; unsigned int main_height = fb->base.height; int main_hsub, main_vsub; int hsub, vsub; - /* - * On ADL-P the CCS AUX surface layout always aligns with the - * power-of-two aligned main surface stride. The main surface - * stride in the allocated FB object may not be power-of-two - * sized, in which case it is auto-padded to the POT size. - */ - if (IS_ALDERLAKE_P(i915) && is_ccs_plane(&fb->base, color_plane)) - main_width = gen12_aligned_scanout_stride(fb, 0) / - fb->base.format->cpp[0]; - intel_fb_plane_get_subsampling(&main_hsub, &main_vsub, &fb->base, main_plane); intel_fb_plane_get_subsampling(&hsub, &vsub, &fb->base, color_plane); @@ -409,6 +830,20 @@ static u32 intel_adjust_tile_offset(int *x, int *y, return new_offset; } +static u32 intel_adjust_linear_offset(int *x, int *y, + unsigned int cpp, + unsigned int pitch, + u32 old_offset, + u32 new_offset) +{ + old_offset += *y * pitch + *x * cpp; + + *y = (old_offset - new_offset) / pitch; + *x = ((old_offset - new_offset) - *y * pitch) / cpp; + + return new_offset; +} + static u32 intel_adjust_aligned_offset(int *x, int *y, const struct drm_framebuffer *fb, int color_plane, @@ -439,10 +874,8 @@ static u32 intel_adjust_aligned_offset(int *x, int *y, tile_size, pitch_tiles, old_offset, new_offset); } else { - old_offset += *y * pitch + *x * cpp; - - *y = (old_offset - new_offset) / pitch; - *x = ((old_offset - new_offset) - *y * pitch) / cpp; + intel_adjust_linear_offset(x, y, cpp, pitch, + old_offset, new_offset); } return new_offset; @@ -459,7 +892,7 @@ u32 intel_plane_adjust_aligned_offset(int *x, int *y, { return intel_adjust_aligned_offset(x, y, state->hw.fb, color_plane, state->hw.rotation, - state->view.color_plane[color_plane].stride, + state->view.color_plane[color_plane].mapping_stride, old_offset, new_offset); } @@ -540,7 +973,7 @@ u32 intel_plane_compute_aligned_offset(int *x, int *y, struct drm_i915_private *i915 = to_i915(intel_plane->base.dev); const struct drm_framebuffer *fb = state->hw.fb; unsigned int rotation = state->hw.rotation; - int pitch = state->view.color_plane[color_plane].stride; + int pitch = state->view.color_plane[color_plane].mapping_stride; u32 alignment; if (intel_plane->id == PLANE_CURSOR) @@ -562,6 +995,7 @@ static int intel_fb_offset_to_xy(int *x, int *y, u32 alignment; if (DISPLAY_VER(i915) >= 12 && + !intel_fb_needs_pot_stride_remap(to_intel_framebuffer(fb)) && is_semiplanar_uv_plane(fb, color_plane)) alignment = intel_tile_row_size(fb, color_plane); else if (fb->modifier != DRM_FORMAT_MOD_LINEAR) @@ -610,7 +1044,7 @@ static int intel_fb_check_ccs_xy(const struct drm_framebuffer *fb, int ccs_plane int ccs_x, ccs_y; int main_x, main_y; - if (!is_ccs_plane(fb, ccs_plane) || is_gen12_ccs_cc_plane(fb, ccs_plane)) + if (!intel_fb_is_ccs_aux_plane(fb, ccs_plane)) return 0; /* @@ -673,7 +1107,7 @@ static bool intel_plane_can_remap(const struct intel_plane_state *plane_state) * The new CCS hash mode isn't compatible with remapping as * the virtual address of the pages affects the compressed data. */ - if (is_ccs_modifier(fb->modifier)) + if (intel_fb_is_ccs_modifier(fb->modifier)) return false; /* Linear needs a page aligned stride for remapping */ @@ -699,11 +1133,11 @@ bool intel_fb_needs_pot_stride_remap(const struct intel_framebuffer *fb) static int intel_fb_pitch(const struct intel_framebuffer *fb, int color_plane, unsigned int rotation) { if (drm_rotation_90_or_270(rotation)) - return fb->rotated_view.color_plane[color_plane].stride; + return fb->rotated_view.color_plane[color_plane].mapping_stride; else if (intel_fb_needs_pot_stride_remap(fb)) - return fb->remapped_view.color_plane[color_plane].stride; + return fb->remapped_view.color_plane[color_plane].mapping_stride; else - return fb->normal_view.color_plane[color_plane].stride; + return fb->normal_view.color_plane[color_plane].mapping_stride; } static bool intel_plane_needs_remap(const struct intel_plane_state *plane_state) @@ -814,18 +1248,32 @@ plane_view_dst_stride_tiles(const struct intel_framebuffer *fb, int color_plane, unsigned int pitch_tiles) { if (intel_fb_needs_pot_stride_remap(fb)) { - unsigned int min_stride = is_ccs_plane(&fb->base, color_plane) ? 2 : 8; /* * ADL_P, the only platform needing a POT stride has a minimum - * of 8 main surface and 2 CCS AUX stride tiles. + * of 8 main surface tiles. */ - return roundup_pow_of_two(max(pitch_tiles, min_stride)); + return roundup_pow_of_two(max(pitch_tiles, 8u)); } else { return pitch_tiles; } } static unsigned int +plane_view_scanout_stride(const struct intel_framebuffer *fb, int color_plane, + unsigned int tile_width, + unsigned int src_stride_tiles, unsigned int dst_stride_tiles) +{ + unsigned int stride_tiles; + + if (IS_ALDERLAKE_P(to_i915(fb->base.dev))) + stride_tiles = src_stride_tiles; + else + stride_tiles = dst_stride_tiles; + + return stride_tiles * tile_width * fb->base.format->cpp[color_plane]; +} + +static unsigned int plane_view_width_tiles(const struct intel_framebuffer *fb, int color_plane, const struct fb_plane_view_dims *dims, int x) @@ -841,11 +1289,31 @@ plane_view_height_tiles(const struct intel_framebuffer *fb, int color_plane, return DIV_ROUND_UP(y + dims->height, dims->tile_height); } +static unsigned int +plane_view_linear_tiles(const struct intel_framebuffer *fb, int color_plane, + const struct fb_plane_view_dims *dims, + int x, int y) +{ + struct drm_i915_private *i915 = to_i915(fb->base.dev); + unsigned int size; + + size = (y + dims->height) * fb->base.pitches[color_plane] + + x * fb->base.format->cpp[color_plane]; + + return DIV_ROUND_UP(size, intel_tile_size(i915)); +} + #define assign_chk_ovf(i915, var, val) ({ \ drm_WARN_ON(&(i915)->drm, overflows_type(val, var)); \ (var) = (val); \ }) +#define assign_bfld_chk_ovf(i915, var, val) ({ \ + (var) = (val); \ + drm_WARN_ON(&(i915)->drm, (var) != (val)); \ + (var); \ +}) + static u32 calc_plane_remap_info(const struct intel_framebuffer *fb, int color_plane, const struct fb_plane_view_dims *dims, u32 obj_offset, u32 gtt_offset, int x, int y, @@ -860,12 +1328,26 @@ static u32 calc_plane_remap_info(const struct intel_framebuffer *fb, int color_p struct drm_rect r; u32 size = 0; - assign_chk_ovf(i915, remap_info->offset, obj_offset); - assign_chk_ovf(i915, remap_info->src_stride, plane_view_src_stride_tiles(fb, color_plane, dims)); - assign_chk_ovf(i915, remap_info->width, plane_view_width_tiles(fb, color_plane, dims, x)); - assign_chk_ovf(i915, remap_info->height, plane_view_height_tiles(fb, color_plane, dims, y)); + assign_bfld_chk_ovf(i915, remap_info->offset, obj_offset); + + if (intel_fb_is_gen12_ccs_aux_plane(&fb->base, color_plane)) { + remap_info->linear = 1; + + assign_chk_ovf(i915, remap_info->size, + plane_view_linear_tiles(fb, color_plane, dims, x, y)); + } else { + remap_info->linear = 0; + + assign_chk_ovf(i915, remap_info->src_stride, + plane_view_src_stride_tiles(fb, color_plane, dims)); + assign_chk_ovf(i915, remap_info->width, + plane_view_width_tiles(fb, color_plane, dims, x)); + assign_chk_ovf(i915, remap_info->height, + plane_view_height_tiles(fb, color_plane, dims, y)); + } if (view->gtt.type == I915_GGTT_VIEW_ROTATED) { + drm_WARN_ON(&i915->drm, remap_info->linear); check_array_bounds(i915, view->gtt.rotated.plane, color_plane); assign_chk_ovf(i915, remap_info->dst_stride, @@ -881,7 +1363,8 @@ static u32 calc_plane_remap_info(const struct intel_framebuffer *fb, int color_p color_plane_info->x = r.x1; color_plane_info->y = r.y1; - color_plane_info->stride = remap_info->dst_stride * tile_height; + color_plane_info->mapping_stride = remap_info->dst_stride * tile_height; + color_plane_info->scanout_stride = color_plane_info->mapping_stride; size += remap_info->dst_stride * remap_info->width; @@ -900,16 +1383,29 @@ static u32 calc_plane_remap_info(const struct intel_framebuffer *fb, int color_p gtt_offset = aligned_offset; } - assign_chk_ovf(i915, remap_info->dst_stride, - plane_view_dst_stride_tiles(fb, color_plane, remap_info->width)); - color_plane_info->x = x; color_plane_info->y = y; - color_plane_info->stride = remap_info->dst_stride * tile_width * - fb->base.format->cpp[color_plane]; + if (remap_info->linear) { + color_plane_info->mapping_stride = fb->base.pitches[color_plane]; + color_plane_info->scanout_stride = color_plane_info->mapping_stride; - size += remap_info->dst_stride * remap_info->height; + size += remap_info->size; + } else { + unsigned int dst_stride = plane_view_dst_stride_tiles(fb, color_plane, + remap_info->width); + + assign_chk_ovf(i915, remap_info->dst_stride, dst_stride); + color_plane_info->mapping_stride = dst_stride * + tile_width * + fb->base.format->cpp[color_plane]; + color_plane_info->scanout_stride = + plane_view_scanout_stride(fb, color_plane, tile_width, + remap_info->src_stride, + dst_stride); + + size += dst_stride * remap_info->height; + } } /* @@ -917,10 +1413,16 @@ static u32 calc_plane_remap_info(const struct intel_framebuffer *fb, int color_p * the x/y offsets. x,y will hold the first pixel of the framebuffer * plane from the start of the remapped/rotated gtt mapping. */ - intel_adjust_tile_offset(&color_plane_info->x, &color_plane_info->y, - tile_width, tile_height, - tile_size, remap_info->dst_stride, - gtt_offset * tile_size, 0); + if (remap_info->linear) + intel_adjust_linear_offset(&color_plane_info->x, &color_plane_info->y, + fb->base.format->cpp[color_plane], + color_plane_info->mapping_stride, + gtt_offset * tile_size, 0); + else + intel_adjust_tile_offset(&color_plane_info->x, &color_plane_info->y, + tile_width, tile_height, + tile_size, remap_info->dst_stride, + gtt_offset * tile_size, 0); return size; } @@ -933,15 +1435,10 @@ calc_plane_normal_size(const struct intel_framebuffer *fb, int color_plane, const struct fb_plane_view_dims *dims, int x, int y) { - struct drm_i915_private *i915 = to_i915(fb->base.dev); unsigned int tiles; if (is_surface_linear(&fb->base, color_plane)) { - unsigned int size; - - size = (y + dims->height) * fb->base.pitches[color_plane] + - x * fb->base.format->cpp[color_plane]; - tiles = DIV_ROUND_UP(size, intel_tile_size(i915)); + tiles = plane_view_linear_tiles(fb, color_plane, dims, x, y); } else { tiles = plane_view_src_stride_tiles(fb, color_plane, dims) * plane_view_height_tiles(fb, color_plane, dims, y); @@ -1030,7 +1527,9 @@ int intel_fill_fb_info(struct drm_i915_private *i915, struct intel_framebuffer * */ fb->normal_view.color_plane[i].x = x; fb->normal_view.color_plane[i].y = y; - fb->normal_view.color_plane[i].stride = fb->base.pitches[i]; + fb->normal_view.color_plane[i].mapping_stride = fb->base.pitches[i]; + fb->normal_view.color_plane[i].scanout_stride = + fb->normal_view.color_plane[i].mapping_stride; offset = calc_plane_aligned_offset(fb, i, &x, &y); @@ -1080,7 +1579,7 @@ static void intel_plane_remap_gtt(struct intel_plane_state *plane_state) src_w = drm_rect_width(&plane_state->uapi.src) >> 16; src_h = drm_rect_height(&plane_state->uapi.src) >> 16; - drm_WARN_ON(&i915->drm, is_ccs_modifier(fb->modifier)); + drm_WARN_ON(&i915->drm, intel_fb_is_ccs_modifier(fb->modifier)); /* Make src coordinates relative to the viewport */ drm_rect_translate(&plane_state->uapi.src, @@ -1143,7 +1642,7 @@ u32 intel_fb_max_stride(struct drm_i915_private *dev_priv, * * The new CCS hash mode makes remapping impossible */ - if (DISPLAY_VER(dev_priv) < 4 || is_ccs_modifier(modifier) || + if (DISPLAY_VER(dev_priv) < 4 || intel_fb_is_ccs_modifier(modifier) || intel_modifier_uses_dpt(dev_priv, modifier)) return intel_plane_fb_max_stride(dev_priv, pixel_format, modifier); else if (DISPLAY_VER(dev_priv) >= 7) @@ -1168,27 +1667,19 @@ intel_fb_stride_alignment(const struct drm_framebuffer *fb, int color_plane) * we need the stride to be page aligned. */ if (fb->pitches[color_plane] > max_stride && - !is_ccs_modifier(fb->modifier)) + !intel_fb_is_ccs_modifier(fb->modifier)) return intel_tile_size(dev_priv); else return 64; } tile_width = intel_tile_width_bytes(fb, color_plane); - if (is_ccs_modifier(fb->modifier)) { - /* - * On ADL-P the stride must be either 8 tiles or a stride - * that is aligned to 16 tiles, required by the 16 tiles = - * 64 kbyte CCS AUX PTE granularity, allowing CCS FBs to be - * remapped. - */ - if (IS_ALDERLAKE_P(dev_priv)) - tile_width *= fb->pitches[0] <= tile_width * 8 ? 8 : 16; + if (intel_fb_is_ccs_modifier(fb->modifier)) { /* * On TGL the surface stride must be 4 tile aligned, mapped by * one 64 byte cacheline on the CCS AUX surface. */ - else if (DISPLAY_VER(dev_priv) >= 12) + if (DISPLAY_VER(dev_priv) >= 12) tile_width *= 4; /* * Display WA #0531: skl,bxt,kbl,glk @@ -1224,7 +1715,7 @@ static int intel_plane_check_stride(const struct intel_plane_state *plane_state) return 0; /* FIXME other color planes? */ - stride = plane_state->view.color_plane[0].stride; + stride = plane_state->view.color_plane[0].mapping_stride; max_stride = plane->max_stride(plane, fb->format->format, fb->modifier, rotation); @@ -1430,7 +1921,7 @@ int intel_framebuffer_init(struct intel_framebuffer *intel_fb, goto err; } - if (is_gen12_ccs_plane(fb, i) && !is_gen12_ccs_cc_plane(fb, i)) { + if (intel_fb_is_gen12_ccs_aux_plane(fb, i)) { int ccs_aux_stride = gen12_ccs_aux_stride(intel_fb, i); if (fb->pitches[i] != ccs_aux_stride) { diff --git a/drivers/gpu/drm/i915/display/intel_fb.h b/drivers/gpu/drm/i915/display/intel_fb.h index 1cbdd84502bd..ba9df8986c1e 100644 --- a/drivers/gpu/drm/i915/display/intel_fb.h +++ b/drivers/gpu/drm/i915/display/intel_fb.h @@ -6,6 +6,7 @@ #ifndef __INTEL_FB_H__ #define __INTEL_FB_H__ +#include <linux/bits.h> #include <linux/types.h> struct drm_device; @@ -16,12 +17,34 @@ struct drm_i915_private; struct drm_mode_fb_cmd2; struct intel_fb_view; struct intel_framebuffer; +struct intel_plane; struct intel_plane_state; -bool is_ccs_plane(const struct drm_framebuffer *fb, int plane); -bool is_gen12_ccs_plane(const struct drm_framebuffer *fb, int plane); -bool is_gen12_ccs_cc_plane(const struct drm_framebuffer *fb, int plane); -bool is_semiplanar_uv_plane(const struct drm_framebuffer *fb, int color_plane); +#define INTEL_PLANE_CAP_NONE 0 +#define INTEL_PLANE_CAP_CCS_RC BIT(0) +#define INTEL_PLANE_CAP_CCS_RC_CC BIT(1) +#define INTEL_PLANE_CAP_CCS_MC BIT(2) +#define INTEL_PLANE_CAP_TILING_X BIT(3) +#define INTEL_PLANE_CAP_TILING_Y BIT(4) +#define INTEL_PLANE_CAP_TILING_Yf BIT(5) + +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); + +bool intel_fb_is_ccs_aux_plane(const struct drm_framebuffer *fb, int color_plane); +int intel_fb_rc_ccs_cc_plane(const struct drm_framebuffer *fb); + +u64 *intel_fb_plane_get_modifiers(struct drm_i915_private *i915, + u8 plane_caps); +bool intel_fb_plane_supports_modifier(struct intel_plane *plane, u64 modifier); + +const struct drm_format_info * +intel_fb_get_format_info(const struct drm_mode_fb_cmd2 *cmd); + +bool +intel_format_info_is_yuv_semiplanar(const struct drm_format_info *info, + u64 modifier); bool is_surface_linear(const struct drm_framebuffer *fb, int color_plane); @@ -67,4 +90,6 @@ intel_user_framebuffer_create(struct drm_device *dev, struct drm_file *filp, const struct drm_mode_fb_cmd2 *user_mode_cmd); +bool intel_fb_uses_dpt(const struct drm_framebuffer *fb); + #endif /* __INTEL_FB_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_fb_pin.c b/drivers/gpu/drm/i915/display/intel_fb_pin.c index 3f77f3013584..31c15e5fca95 100644 --- a/drivers/gpu/drm/i915/display/intel_fb_pin.c +++ b/drivers/gpu/drm/i915/display/intel_fb_pin.c @@ -7,13 +7,13 @@ * DOC: display pinning helpers */ -#include "intel_display_types.h" -#include "intel_fb_pin.h" -#include "intel_fb.h" +#include "gem/i915_gem_object.h" +#include "i915_drv.h" +#include "intel_display_types.h" #include "intel_dpt.h" - -#include "gem/i915_gem_object.h" +#include "intel_fb.h" +#include "intel_fb_pin.h" static struct i915_vma * intel_pin_fb_obj_dpt(struct drm_framebuffer *fb, @@ -142,13 +142,11 @@ retry: if (ret) goto err; - if (!ret) { - vma = i915_gem_object_pin_to_display_plane(obj, &ww, alignment, - view, pinctl); - if (IS_ERR(vma)) { - ret = PTR_ERR(vma); - goto err_unpin; - } + vma = i915_gem_object_pin_to_display_plane(obj, &ww, alignment, + view, pinctl); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto err_unpin; } if (uses_fence && i915_vma_is_map_and_fenceable(vma)) { diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c index 1f66de77a6b1..160fd2bdafe5 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.c +++ b/drivers/gpu/drm/i915/display/intel_fbc.c @@ -41,26 +41,71 @@ #include <drm/drm_fourcc.h> #include "i915_drv.h" -#include "i915_trace.h" #include "i915_vgpu.h" +#include "intel_cdclk.h" #include "intel_de.h" +#include "intel_display_trace.h" #include "intel_display_types.h" #include "intel_fbc.h" #include "intel_frontbuffer.h" -/* - * For SKL+, the plane source size used by the hardware is based on the value we - * write to the PLANE_SIZE register. For BDW-, the hardware looks at the value - * we wrote to PIPESRC. - */ -static void intel_fbc_get_plane_source_size(const struct intel_fbc_state_cache *cache, - int *width, int *height) -{ - if (width) - *width = cache->plane.src_w; - if (height) - *height = cache->plane.src_h; -} +struct intel_fbc_funcs { + void (*activate)(struct intel_fbc *fbc); + void (*deactivate)(struct intel_fbc *fbc); + bool (*is_active)(struct intel_fbc *fbc); + bool (*is_compressing)(struct intel_fbc *fbc); + void (*nuke)(struct intel_fbc *fbc); + void (*program_cfb)(struct intel_fbc *fbc); + void (*set_false_color)(struct intel_fbc *fbc, bool enable); +}; + +struct intel_fbc_state { + struct intel_plane *plane; + unsigned int cfb_stride; + unsigned int cfb_size; + unsigned int fence_y_offset; + u16 override_cfb_stride; + u16 interval; + s8 fence_id; +}; + +struct intel_fbc { + struct drm_i915_private *i915; + const struct intel_fbc_funcs *funcs; + + /* + * This is always the inner lock when overlapping with + * struct_mutex and it's the outer lock when overlapping + * with stolen_lock. + */ + struct mutex lock; + unsigned int possible_framebuffer_bits; + unsigned int busy_bits; + + struct drm_mm_node compressed_fb; + struct drm_mm_node compressed_llb; + + u8 limit; + + bool false_color; + + bool active; + bool activated; + bool flip_pending; + + bool underrun_detected; + struct work_struct underrun_work; + + /* + * This structure contains everything that's relevant to program the + * hardware registers. When we want to figure out if we need to disable + * and re-enable FBC for a new configuration we just check if there's + * something different in the struct. The genx_fbc_activate functions + * are supposed to read from it in order to program the registers. + */ + struct intel_fbc_state state; + const char *no_fbc_reason; +}; /* plane stride in pixels */ static unsigned int intel_fbc_plane_stride(const struct intel_plane_state *plane_state) @@ -68,7 +113,7 @@ static unsigned int intel_fbc_plane_stride(const struct intel_plane_state *plane const struct drm_framebuffer *fb = plane_state->hw.fb; unsigned int stride; - stride = plane_state->view.color_plane[0].stride; + stride = plane_state->view.color_plane[0].mapping_stride; if (!drm_rotation_90_or_270(plane_state->hw.rotation)) stride /= fb->format->cpp[0]; @@ -76,24 +121,25 @@ static unsigned int intel_fbc_plane_stride(const struct intel_plane_state *plane } /* plane stride based cfb stride in bytes, assuming 1:1 compression limit */ -static unsigned int _intel_fbc_cfb_stride(const struct intel_fbc_state_cache *cache) +static unsigned int _intel_fbc_cfb_stride(const struct intel_plane_state *plane_state) { unsigned int cpp = 4; /* FBC always 4 bytes per pixel */ - return cache->fb.stride * cpp; + return intel_fbc_plane_stride(plane_state) * cpp; } /* minimum acceptable cfb stride in bytes, assuming 1:1 compression limit */ -static unsigned int skl_fbc_min_cfb_stride(struct drm_i915_private *i915, - const struct intel_fbc_state_cache *cache) +static unsigned int skl_fbc_min_cfb_stride(const struct intel_plane_state *plane_state) { + struct drm_i915_private *i915 = to_i915(plane_state->uapi.plane->dev); unsigned int limit = 4; /* 1:4 compression limit is the worst case */ unsigned int cpp = 4; /* FBC always 4 bytes per pixel */ + unsigned int width = drm_rect_width(&plane_state->uapi.src) >> 16; unsigned int height = 4; /* FBC segment is 4 lines */ unsigned int stride; /* minimum segment stride we can use */ - stride = cache->plane.src_w * cpp * height / limit; + stride = width * cpp * height / limit; /* * Wa_16011863758: icl+ @@ -113,10 +159,10 @@ static unsigned int skl_fbc_min_cfb_stride(struct drm_i915_private *i915, } /* properly aligned cfb stride in bytes, assuming 1:1 compression limit */ -static unsigned int intel_fbc_cfb_stride(struct drm_i915_private *i915, - const struct intel_fbc_state_cache *cache) +static unsigned int intel_fbc_cfb_stride(const struct intel_plane_state *plane_state) { - unsigned int stride = _intel_fbc_cfb_stride(cache); + struct drm_i915_private *i915 = to_i915(plane_state->uapi.plane->dev); + unsigned int stride = _intel_fbc_cfb_stride(plane_state); /* * At least some of the platforms require each 4 line segment to @@ -124,98 +170,202 @@ static unsigned int intel_fbc_cfb_stride(struct drm_i915_private *i915, * that regardless of the compression limit we choose later. */ if (DISPLAY_VER(i915) >= 9) - return max(ALIGN(stride, 512), skl_fbc_min_cfb_stride(i915, cache)); + return max(ALIGN(stride, 512), skl_fbc_min_cfb_stride(plane_state)); else return stride; } -static unsigned int intel_fbc_cfb_size(struct drm_i915_private *dev_priv, - const struct intel_fbc_state_cache *cache) +static unsigned int intel_fbc_cfb_size(const struct intel_plane_state *plane_state) { - int lines = cache->plane.src_h; + struct drm_i915_private *i915 = to_i915(plane_state->uapi.plane->dev); + int lines = drm_rect_height(&plane_state->uapi.src) >> 16; - if (DISPLAY_VER(dev_priv) == 7) + if (DISPLAY_VER(i915) == 7) lines = min(lines, 2048); - else if (DISPLAY_VER(dev_priv) >= 8) + else if (DISPLAY_VER(i915) >= 8) lines = min(lines, 2560); - return lines * intel_fbc_cfb_stride(dev_priv, cache); + return lines * intel_fbc_cfb_stride(plane_state); +} + +static u16 intel_fbc_override_cfb_stride(const struct intel_plane_state *plane_state) +{ + struct drm_i915_private *i915 = to_i915(plane_state->uapi.plane->dev); + unsigned int stride_aligned = intel_fbc_cfb_stride(plane_state); + unsigned int stride = _intel_fbc_cfb_stride(plane_state); + const struct drm_framebuffer *fb = plane_state->hw.fb; + + /* + * Override stride in 64 byte units per 4 line segment. + * + * Gen9 hw miscalculates cfb stride for linear as + * PLANE_STRIDE*512 instead of PLANE_STRIDE*64, so + * we always need to use the override there. + */ + if (stride != stride_aligned || + (DISPLAY_VER(i915) == 9 && fb->modifier == DRM_FORMAT_MOD_LINEAR)) + return stride_aligned * 4 / 64; + + return 0; } -static void i8xx_fbc_deactivate(struct drm_i915_private *dev_priv) +static u32 i8xx_fbc_ctl(struct intel_fbc *fbc) { + const struct intel_fbc_state *fbc_state = &fbc->state; + struct drm_i915_private *i915 = fbc->i915; + unsigned int cfb_stride; + u32 fbc_ctl; + + cfb_stride = fbc_state->cfb_stride / fbc->limit; + + /* FBC_CTL wants 32B or 64B units */ + if (DISPLAY_VER(i915) == 2) + cfb_stride = (cfb_stride / 32) - 1; + else + cfb_stride = (cfb_stride / 64) - 1; + + fbc_ctl = FBC_CTL_PERIODIC | + FBC_CTL_INTERVAL(fbc_state->interval) | + FBC_CTL_STRIDE(cfb_stride); + + if (IS_I945GM(i915)) + fbc_ctl |= FBC_CTL_C3_IDLE; /* 945 needs special SR handling */ + + if (fbc_state->fence_id >= 0) + fbc_ctl |= FBC_CTL_FENCENO(fbc_state->fence_id); + + return fbc_ctl; +} + +static u32 i965_fbc_ctl2(struct intel_fbc *fbc) +{ + const struct intel_fbc_state *fbc_state = &fbc->state; + u32 fbc_ctl2; + + fbc_ctl2 = FBC_CTL_FENCE_DBL | FBC_CTL_IDLE_IMM | + FBC_CTL_PLANE(fbc_state->plane->i9xx_plane); + + if (fbc_state->fence_id >= 0) + fbc_ctl2 |= FBC_CTL_CPU_FENCE_EN; + + return fbc_ctl2; +} + +static void i8xx_fbc_deactivate(struct intel_fbc *fbc) +{ + struct drm_i915_private *i915 = fbc->i915; u32 fbc_ctl; /* Disable compression */ - fbc_ctl = intel_de_read(dev_priv, FBC_CONTROL); + fbc_ctl = intel_de_read(i915, FBC_CONTROL); if ((fbc_ctl & FBC_CTL_EN) == 0) return; fbc_ctl &= ~FBC_CTL_EN; - intel_de_write(dev_priv, FBC_CONTROL, fbc_ctl); + intel_de_write(i915, FBC_CONTROL, fbc_ctl); /* Wait for compressing bit to clear */ - if (intel_de_wait_for_clear(dev_priv, FBC_STATUS, + if (intel_de_wait_for_clear(i915, FBC_STATUS, FBC_STAT_COMPRESSING, 10)) { - drm_dbg_kms(&dev_priv->drm, "FBC idle timed out\n"); + drm_dbg_kms(&i915->drm, "FBC idle timed out\n"); return; } } -static void i8xx_fbc_activate(struct drm_i915_private *dev_priv) +static void i8xx_fbc_activate(struct intel_fbc *fbc) { - struct intel_fbc *fbc = &dev_priv->fbc; - const struct intel_fbc_reg_params *params = &fbc->params; - int cfb_pitch; + const struct intel_fbc_state *fbc_state = &fbc->state; + struct drm_i915_private *i915 = fbc->i915; int i; - u32 fbc_ctl; - - cfb_pitch = params->cfb_stride / fbc->limit; - - /* FBC_CTL wants 32B or 64B units */ - if (DISPLAY_VER(dev_priv) == 2) - cfb_pitch = (cfb_pitch / 32) - 1; - else - cfb_pitch = (cfb_pitch / 64) - 1; /* Clear old tags */ for (i = 0; i < (FBC_LL_SIZE / 32) + 1; i++) - intel_de_write(dev_priv, FBC_TAG(i), 0); - - if (DISPLAY_VER(dev_priv) == 4) { - u32 fbc_ctl2; - - /* Set it up... */ - fbc_ctl2 = FBC_CTL_FENCE_DBL | FBC_CTL_IDLE_IMM; - fbc_ctl2 |= FBC_CTL_PLANE(params->crtc.i9xx_plane); - if (params->fence_id >= 0) - fbc_ctl2 |= FBC_CTL_CPU_FENCE; - intel_de_write(dev_priv, FBC_CONTROL2, fbc_ctl2); - intel_de_write(dev_priv, FBC_FENCE_OFF, - params->fence_y_offset); + intel_de_write(i915, FBC_TAG(i), 0); + + if (DISPLAY_VER(i915) == 4) { + intel_de_write(i915, FBC_CONTROL2, + i965_fbc_ctl2(fbc)); + intel_de_write(i915, FBC_FENCE_OFF, + fbc_state->fence_y_offset); } - /* enable it... */ - fbc_ctl = FBC_CTL_INTERVAL(params->interval); - fbc_ctl |= FBC_CTL_EN | FBC_CTL_PERIODIC; - if (IS_I945GM(dev_priv)) - fbc_ctl |= FBC_CTL_C3_IDLE; /* 945 needs special SR handling */ - fbc_ctl |= FBC_CTL_STRIDE(cfb_pitch & 0xff); - if (params->fence_id >= 0) - fbc_ctl |= FBC_CTL_FENCENO(params->fence_id); - intel_de_write(dev_priv, FBC_CONTROL, fbc_ctl); + intel_de_write(i915, FBC_CONTROL, + FBC_CTL_EN | i8xx_fbc_ctl(fbc)); +} + +static bool i8xx_fbc_is_active(struct intel_fbc *fbc) +{ + return intel_de_read(fbc->i915, FBC_CONTROL) & FBC_CTL_EN; +} + +static bool i8xx_fbc_is_compressing(struct intel_fbc *fbc) +{ + return intel_de_read(fbc->i915, FBC_STATUS) & + (FBC_STAT_COMPRESSING | FBC_STAT_COMPRESSED); +} + +static void i8xx_fbc_nuke(struct intel_fbc *fbc) +{ + struct intel_fbc_state *fbc_state = &fbc->state; + enum i9xx_plane_id i9xx_plane = fbc_state->plane->i9xx_plane; + struct drm_i915_private *dev_priv = fbc->i915; + + spin_lock_irq(&dev_priv->uncore.lock); + intel_de_write_fw(dev_priv, DSPADDR(i9xx_plane), + intel_de_read_fw(dev_priv, DSPADDR(i9xx_plane))); + spin_unlock_irq(&dev_priv->uncore.lock); } -static bool i8xx_fbc_is_active(struct drm_i915_private *dev_priv) +static void i8xx_fbc_program_cfb(struct intel_fbc *fbc) { - return intel_de_read(dev_priv, FBC_CONTROL) & FBC_CTL_EN; + struct drm_i915_private *i915 = fbc->i915; + + GEM_BUG_ON(range_overflows_end_t(u64, i915->dsm.start, + fbc->compressed_fb.start, U32_MAX)); + GEM_BUG_ON(range_overflows_end_t(u64, i915->dsm.start, + fbc->compressed_llb.start, U32_MAX)); + + intel_de_write(i915, FBC_CFB_BASE, + i915->dsm.start + fbc->compressed_fb.start); + intel_de_write(i915, FBC_LL_BASE, + i915->dsm.start + fbc->compressed_llb.start); } -static u32 g4x_dpfc_ctl_limit(struct drm_i915_private *i915) +static const struct intel_fbc_funcs i8xx_fbc_funcs = { + .activate = i8xx_fbc_activate, + .deactivate = i8xx_fbc_deactivate, + .is_active = i8xx_fbc_is_active, + .is_compressing = i8xx_fbc_is_compressing, + .nuke = i8xx_fbc_nuke, + .program_cfb = i8xx_fbc_program_cfb, +}; + +static void i965_fbc_nuke(struct intel_fbc *fbc) { - switch (i915->fbc.limit) { + struct intel_fbc_state *fbc_state = &fbc->state; + enum i9xx_plane_id i9xx_plane = fbc_state->plane->i9xx_plane; + struct drm_i915_private *dev_priv = fbc->i915; + + spin_lock_irq(&dev_priv->uncore.lock); + intel_de_write_fw(dev_priv, DSPSURF(i9xx_plane), + intel_de_read_fw(dev_priv, DSPSURF(i9xx_plane))); + spin_unlock_irq(&dev_priv->uncore.lock); +} + +static const struct intel_fbc_funcs i965_fbc_funcs = { + .activate = i8xx_fbc_activate, + .deactivate = i8xx_fbc_deactivate, + .is_active = i8xx_fbc_is_active, + .is_compressing = i8xx_fbc_is_compressing, + .nuke = i965_fbc_nuke, + .program_cfb = i8xx_fbc_program_cfb, +}; + +static u32 g4x_dpfc_ctl_limit(struct intel_fbc *fbc) +{ + switch (fbc->limit) { default: - MISSING_CASE(i915->fbc.limit); + MISSING_CASE(fbc->limit); fallthrough; case 1: return DPFC_CTL_LIMIT_1X; @@ -226,260 +376,306 @@ static u32 g4x_dpfc_ctl_limit(struct drm_i915_private *i915) } } -static void g4x_fbc_activate(struct drm_i915_private *dev_priv) +static u32 g4x_dpfc_ctl(struct intel_fbc *fbc) { - struct intel_fbc_reg_params *params = &dev_priv->fbc.params; + const struct intel_fbc_state *fbc_state = &fbc->state; + struct drm_i915_private *i915 = fbc->i915; u32 dpfc_ctl; - dpfc_ctl = DPFC_CTL_PLANE(params->crtc.i9xx_plane) | DPFC_SR_EN; + dpfc_ctl = g4x_dpfc_ctl_limit(fbc) | + DPFC_CTL_PLANE_G4X(fbc_state->plane->i9xx_plane); - dpfc_ctl |= g4x_dpfc_ctl_limit(dev_priv); + if (IS_G4X(i915)) + dpfc_ctl |= DPFC_CTL_SR_EN; - if (params->fence_id >= 0) { - dpfc_ctl |= DPFC_CTL_FENCE_EN | params->fence_id; - intel_de_write(dev_priv, DPFC_FENCE_YOFF, - params->fence_y_offset); - } else { - intel_de_write(dev_priv, DPFC_FENCE_YOFF, 0); + if (fbc_state->fence_id >= 0) { + dpfc_ctl |= DPFC_CTL_FENCE_EN_G4X; + + if (DISPLAY_VER(i915) < 6) + dpfc_ctl |= DPFC_CTL_FENCENO(fbc_state->fence_id); } - /* enable it... */ - intel_de_write(dev_priv, DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN); + return dpfc_ctl; } -static void g4x_fbc_deactivate(struct drm_i915_private *dev_priv) +static void g4x_fbc_activate(struct intel_fbc *fbc) { + const struct intel_fbc_state *fbc_state = &fbc->state; + struct drm_i915_private *i915 = fbc->i915; + + intel_de_write(i915, DPFC_FENCE_YOFF, + fbc_state->fence_y_offset); + + intel_de_write(i915, DPFC_CONTROL, + DPFC_CTL_EN | g4x_dpfc_ctl(fbc)); +} + +static void g4x_fbc_deactivate(struct intel_fbc *fbc) +{ + struct drm_i915_private *i915 = fbc->i915; u32 dpfc_ctl; /* Disable compression */ - dpfc_ctl = intel_de_read(dev_priv, DPFC_CONTROL); + dpfc_ctl = intel_de_read(i915, DPFC_CONTROL); if (dpfc_ctl & DPFC_CTL_EN) { dpfc_ctl &= ~DPFC_CTL_EN; - intel_de_write(dev_priv, DPFC_CONTROL, dpfc_ctl); + intel_de_write(i915, DPFC_CONTROL, dpfc_ctl); } } -static bool g4x_fbc_is_active(struct drm_i915_private *dev_priv) +static bool g4x_fbc_is_active(struct intel_fbc *fbc) { - return intel_de_read(dev_priv, DPFC_CONTROL) & DPFC_CTL_EN; + return intel_de_read(fbc->i915, DPFC_CONTROL) & DPFC_CTL_EN; } -static void i8xx_fbc_recompress(struct drm_i915_private *dev_priv) +static bool g4x_fbc_is_compressing(struct intel_fbc *fbc) { - struct intel_fbc_reg_params *params = &dev_priv->fbc.params; - enum i9xx_plane_id i9xx_plane = params->crtc.i9xx_plane; + return intel_de_read(fbc->i915, DPFC_STATUS) & DPFC_COMP_SEG_MASK; +} - spin_lock_irq(&dev_priv->uncore.lock); - intel_de_write_fw(dev_priv, DSPADDR(i9xx_plane), - intel_de_read_fw(dev_priv, DSPADDR(i9xx_plane))); - spin_unlock_irq(&dev_priv->uncore.lock); +static void g4x_fbc_program_cfb(struct intel_fbc *fbc) +{ + struct drm_i915_private *i915 = fbc->i915; + + intel_de_write(i915, DPFC_CB_BASE, fbc->compressed_fb.start); } -static void i965_fbc_recompress(struct drm_i915_private *dev_priv) +static const struct intel_fbc_funcs g4x_fbc_funcs = { + .activate = g4x_fbc_activate, + .deactivate = g4x_fbc_deactivate, + .is_active = g4x_fbc_is_active, + .is_compressing = g4x_fbc_is_compressing, + .nuke = i965_fbc_nuke, + .program_cfb = g4x_fbc_program_cfb, +}; + +static void ilk_fbc_activate(struct intel_fbc *fbc) { - struct intel_fbc_reg_params *params = &dev_priv->fbc.params; - enum i9xx_plane_id i9xx_plane = params->crtc.i9xx_plane; + struct intel_fbc_state *fbc_state = &fbc->state; + struct drm_i915_private *i915 = fbc->i915; - spin_lock_irq(&dev_priv->uncore.lock); - intel_de_write_fw(dev_priv, DSPSURF(i9xx_plane), - intel_de_read_fw(dev_priv, DSPSURF(i9xx_plane))); - spin_unlock_irq(&dev_priv->uncore.lock); + intel_de_write(i915, ILK_DPFC_FENCE_YOFF, + fbc_state->fence_y_offset); + + intel_de_write(i915, ILK_DPFC_CONTROL, + DPFC_CTL_EN | g4x_dpfc_ctl(fbc)); } -/* This function forces a CFB recompression through the nuke operation. */ -static void snb_fbc_recompress(struct drm_i915_private *dev_priv) +static void ilk_fbc_deactivate(struct intel_fbc *fbc) { - intel_de_write(dev_priv, MSG_FBC_REND_STATE, FBC_REND_NUKE); - intel_de_posting_read(dev_priv, MSG_FBC_REND_STATE); + struct drm_i915_private *i915 = fbc->i915; + u32 dpfc_ctl; + + /* Disable compression */ + dpfc_ctl = intel_de_read(i915, ILK_DPFC_CONTROL); + if (dpfc_ctl & DPFC_CTL_EN) { + dpfc_ctl &= ~DPFC_CTL_EN; + intel_de_write(i915, ILK_DPFC_CONTROL, dpfc_ctl); + } +} + +static bool ilk_fbc_is_active(struct intel_fbc *fbc) +{ + return intel_de_read(fbc->i915, ILK_DPFC_CONTROL) & DPFC_CTL_EN; } -static void intel_fbc_recompress(struct drm_i915_private *dev_priv) +static bool ilk_fbc_is_compressing(struct intel_fbc *fbc) { - struct intel_fbc *fbc = &dev_priv->fbc; + return intel_de_read(fbc->i915, ILK_DPFC_STATUS) & DPFC_COMP_SEG_MASK; +} - trace_intel_fbc_nuke(fbc->crtc); +static void ilk_fbc_program_cfb(struct intel_fbc *fbc) +{ + struct drm_i915_private *i915 = fbc->i915; - if (DISPLAY_VER(dev_priv) >= 6) - snb_fbc_recompress(dev_priv); - else if (DISPLAY_VER(dev_priv) >= 4) - i965_fbc_recompress(dev_priv); - else - i8xx_fbc_recompress(dev_priv); + intel_de_write(i915, ILK_DPFC_CB_BASE, fbc->compressed_fb.start); } -static void ilk_fbc_activate(struct drm_i915_private *dev_priv) +static const struct intel_fbc_funcs ilk_fbc_funcs = { + .activate = ilk_fbc_activate, + .deactivate = ilk_fbc_deactivate, + .is_active = ilk_fbc_is_active, + .is_compressing = ilk_fbc_is_compressing, + .nuke = i965_fbc_nuke, + .program_cfb = ilk_fbc_program_cfb, +}; + +static void snb_fbc_program_fence(struct intel_fbc *fbc) { - struct intel_fbc_reg_params *params = &dev_priv->fbc.params; - u32 dpfc_ctl; + const struct intel_fbc_state *fbc_state = &fbc->state; + struct drm_i915_private *i915 = fbc->i915; + u32 ctl = 0; - dpfc_ctl = DPFC_CTL_PLANE(params->crtc.i9xx_plane); + if (fbc_state->fence_id >= 0) + ctl = SNB_DPFC_FENCE_EN | SNB_DPFC_FENCENO(fbc_state->fence_id); - dpfc_ctl |= g4x_dpfc_ctl_limit(dev_priv); + intel_de_write(i915, SNB_DPFC_CTL_SA, ctl); + intel_de_write(i915, SNB_DPFC_CPU_FENCE_OFFSET, fbc_state->fence_y_offset); +} - if (params->fence_id >= 0) { - dpfc_ctl |= DPFC_CTL_FENCE_EN; - if (IS_IRONLAKE(dev_priv)) - dpfc_ctl |= params->fence_id; - if (IS_SANDYBRIDGE(dev_priv)) { - intel_de_write(dev_priv, SNB_DPFC_CTL_SA, - SNB_CPU_FENCE_ENABLE | params->fence_id); - intel_de_write(dev_priv, DPFC_CPU_FENCE_OFFSET, - params->fence_y_offset); - } - } else { - if (IS_SANDYBRIDGE(dev_priv)) { - intel_de_write(dev_priv, SNB_DPFC_CTL_SA, 0); - intel_de_write(dev_priv, DPFC_CPU_FENCE_OFFSET, 0); - } - } +static void snb_fbc_activate(struct intel_fbc *fbc) +{ + snb_fbc_program_fence(fbc); - intel_de_write(dev_priv, ILK_DPFC_FENCE_YOFF, - params->fence_y_offset); - /* enable it... */ - intel_de_write(dev_priv, ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN); + ilk_fbc_activate(fbc); } -static void ilk_fbc_deactivate(struct drm_i915_private *dev_priv) +static void snb_fbc_nuke(struct intel_fbc *fbc) { - u32 dpfc_ctl; + struct drm_i915_private *i915 = fbc->i915; - /* Disable compression */ - dpfc_ctl = intel_de_read(dev_priv, ILK_DPFC_CONTROL); - if (dpfc_ctl & DPFC_CTL_EN) { - dpfc_ctl &= ~DPFC_CTL_EN; - intel_de_write(dev_priv, ILK_DPFC_CONTROL, dpfc_ctl); - } + intel_de_write(i915, MSG_FBC_REND_STATE, FBC_REND_NUKE); + intel_de_posting_read(i915, MSG_FBC_REND_STATE); +} + +static const struct intel_fbc_funcs snb_fbc_funcs = { + .activate = snb_fbc_activate, + .deactivate = ilk_fbc_deactivate, + .is_active = ilk_fbc_is_active, + .is_compressing = ilk_fbc_is_compressing, + .nuke = snb_fbc_nuke, + .program_cfb = ilk_fbc_program_cfb, +}; + +static void glk_fbc_program_cfb_stride(struct intel_fbc *fbc) +{ + const struct intel_fbc_state *fbc_state = &fbc->state; + struct drm_i915_private *i915 = fbc->i915; + u32 val = 0; + + if (fbc_state->override_cfb_stride) + val |= FBC_STRIDE_OVERRIDE | + FBC_STRIDE(fbc_state->override_cfb_stride / fbc->limit); + + intel_de_write(i915, GLK_FBC_STRIDE, val); } -static bool ilk_fbc_is_active(struct drm_i915_private *dev_priv) +static void skl_fbc_program_cfb_stride(struct intel_fbc *fbc) { - return intel_de_read(dev_priv, ILK_DPFC_CONTROL) & DPFC_CTL_EN; + const struct intel_fbc_state *fbc_state = &fbc->state; + struct drm_i915_private *i915 = fbc->i915; + u32 val = 0; + + /* Display WA #0529: skl, kbl, bxt. */ + if (fbc_state->override_cfb_stride) + val |= CHICKEN_FBC_STRIDE_OVERRIDE | + CHICKEN_FBC_STRIDE(fbc_state->override_cfb_stride / fbc->limit); + + intel_de_rmw(i915, CHICKEN_MISC_4, + CHICKEN_FBC_STRIDE_OVERRIDE | + CHICKEN_FBC_STRIDE_MASK, val); } -static void gen7_fbc_activate(struct drm_i915_private *dev_priv) +static u32 ivb_dpfc_ctl(struct intel_fbc *fbc) { - struct intel_fbc *fbc = &dev_priv->fbc; - const struct intel_fbc_reg_params *params = &fbc->params; + const struct intel_fbc_state *fbc_state = &fbc->state; + struct drm_i915_private *i915 = fbc->i915; u32 dpfc_ctl; - if (DISPLAY_VER(dev_priv) >= 10) { - u32 val = 0; + dpfc_ctl = g4x_dpfc_ctl_limit(fbc); - if (params->override_cfb_stride) - val |= FBC_STRIDE_OVERRIDE | - FBC_STRIDE(params->override_cfb_stride / fbc->limit); + if (IS_IVYBRIDGE(i915)) + dpfc_ctl |= DPFC_CTL_PLANE_IVB(fbc_state->plane->i9xx_plane); - intel_de_write(dev_priv, GLK_FBC_STRIDE, val); - } else if (DISPLAY_VER(dev_priv) == 9) { - u32 val = 0; + if (fbc_state->fence_id >= 0) + dpfc_ctl |= DPFC_CTL_FENCE_EN_IVB; - /* Display WA #0529: skl, kbl, bxt. */ - if (params->override_cfb_stride) - val |= CHICKEN_FBC_STRIDE_OVERRIDE | - CHICKEN_FBC_STRIDE(params->override_cfb_stride / fbc->limit); + if (fbc->false_color) + dpfc_ctl |= DPFC_CTL_FALSE_COLOR; - intel_de_rmw(dev_priv, CHICKEN_MISC_4, - CHICKEN_FBC_STRIDE_OVERRIDE | - CHICKEN_FBC_STRIDE_MASK, val); - } + return dpfc_ctl; +} - dpfc_ctl = 0; - if (IS_IVYBRIDGE(dev_priv)) - dpfc_ctl |= IVB_DPFC_CTL_PLANE(params->crtc.i9xx_plane); - - dpfc_ctl |= g4x_dpfc_ctl_limit(dev_priv); - - if (params->fence_id >= 0) { - dpfc_ctl |= IVB_DPFC_CTL_FENCE_EN; - intel_de_write(dev_priv, SNB_DPFC_CTL_SA, - SNB_CPU_FENCE_ENABLE | params->fence_id); - intel_de_write(dev_priv, DPFC_CPU_FENCE_OFFSET, - params->fence_y_offset); - } else if (dev_priv->ggtt.num_fences) { - intel_de_write(dev_priv, SNB_DPFC_CTL_SA, 0); - intel_de_write(dev_priv, DPFC_CPU_FENCE_OFFSET, 0); - } +static void ivb_fbc_activate(struct intel_fbc *fbc) +{ + struct drm_i915_private *i915 = fbc->i915; + + if (DISPLAY_VER(i915) >= 10) + glk_fbc_program_cfb_stride(fbc); + else if (DISPLAY_VER(i915) == 9) + skl_fbc_program_cfb_stride(fbc); - if (dev_priv->fbc.false_color) - dpfc_ctl |= FBC_CTL_FALSE_COLOR; + if (i915->ggtt.num_fences) + snb_fbc_program_fence(fbc); - intel_de_write(dev_priv, ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN); + intel_de_write(i915, ILK_DPFC_CONTROL, + DPFC_CTL_EN | ivb_dpfc_ctl(fbc)); } -static bool intel_fbc_hw_is_active(struct drm_i915_private *dev_priv) +static bool ivb_fbc_is_compressing(struct intel_fbc *fbc) { - if (DISPLAY_VER(dev_priv) >= 5) - return ilk_fbc_is_active(dev_priv); - else if (IS_GM45(dev_priv)) - return g4x_fbc_is_active(dev_priv); - else - return i8xx_fbc_is_active(dev_priv); + return intel_de_read(fbc->i915, ILK_DPFC_STATUS2) & DPFC_COMP_SEG_MASK_IVB; } -static void intel_fbc_hw_activate(struct drm_i915_private *dev_priv) +static void ivb_fbc_set_false_color(struct intel_fbc *fbc, + bool enable) { - struct intel_fbc *fbc = &dev_priv->fbc; + intel_de_rmw(fbc->i915, ILK_DPFC_CONTROL, + DPFC_CTL_FALSE_COLOR, enable ? DPFC_CTL_FALSE_COLOR : 0); +} - trace_intel_fbc_activate(fbc->crtc); +static const struct intel_fbc_funcs ivb_fbc_funcs = { + .activate = ivb_fbc_activate, + .deactivate = ilk_fbc_deactivate, + .is_active = ilk_fbc_is_active, + .is_compressing = ivb_fbc_is_compressing, + .nuke = snb_fbc_nuke, + .program_cfb = ilk_fbc_program_cfb, + .set_false_color = ivb_fbc_set_false_color, +}; + +static bool intel_fbc_hw_is_active(struct intel_fbc *fbc) +{ + return fbc->funcs->is_active(fbc); +} + +static void intel_fbc_hw_activate(struct intel_fbc *fbc) +{ + trace_intel_fbc_activate(fbc->state.plane); fbc->active = true; fbc->activated = true; - if (DISPLAY_VER(dev_priv) >= 7) - gen7_fbc_activate(dev_priv); - else if (DISPLAY_VER(dev_priv) >= 5) - ilk_fbc_activate(dev_priv); - else if (IS_GM45(dev_priv)) - g4x_fbc_activate(dev_priv); - else - i8xx_fbc_activate(dev_priv); + fbc->funcs->activate(fbc); } -static void intel_fbc_hw_deactivate(struct drm_i915_private *dev_priv) +static void intel_fbc_hw_deactivate(struct intel_fbc *fbc) { - struct intel_fbc *fbc = &dev_priv->fbc; - - trace_intel_fbc_deactivate(fbc->crtc); + trace_intel_fbc_deactivate(fbc->state.plane); fbc->active = false; - if (DISPLAY_VER(dev_priv) >= 5) - ilk_fbc_deactivate(dev_priv); - else if (IS_GM45(dev_priv)) - g4x_fbc_deactivate(dev_priv); - else - i8xx_fbc_deactivate(dev_priv); + fbc->funcs->deactivate(fbc); } -/** - * intel_fbc_is_active - Is FBC active? - * @dev_priv: i915 device instance - * - * This function is used to verify the current state of FBC. - * - * FIXME: This should be tracked in the plane config eventually - * instead of queried at runtime for most callers. - */ -bool intel_fbc_is_active(struct drm_i915_private *dev_priv) +static bool intel_fbc_is_compressing(struct intel_fbc *fbc) +{ + return fbc->funcs->is_compressing(fbc); +} + +static void intel_fbc_nuke(struct intel_fbc *fbc) { - return dev_priv->fbc.active; + trace_intel_fbc_nuke(fbc->state.plane); + + fbc->funcs->nuke(fbc); } -static void intel_fbc_activate(struct drm_i915_private *dev_priv) +static void intel_fbc_activate(struct intel_fbc *fbc) { - intel_fbc_hw_activate(dev_priv); - intel_fbc_recompress(dev_priv); + intel_fbc_hw_activate(fbc); + intel_fbc_nuke(fbc); + + fbc->no_fbc_reason = NULL; } -static void intel_fbc_deactivate(struct drm_i915_private *dev_priv, - const char *reason) +static void intel_fbc_deactivate(struct intel_fbc *fbc, const char *reason) { - struct intel_fbc *fbc = &dev_priv->fbc; + struct drm_i915_private *i915 = fbc->i915; - drm_WARN_ON(&dev_priv->drm, !mutex_is_locked(&fbc->lock)); + drm_WARN_ON(&i915->drm, !mutex_is_locked(&fbc->lock)); if (fbc->active) - intel_fbc_hw_deactivate(dev_priv); + intel_fbc_hw_deactivate(fbc); fbc->no_fbc_reason = reason; } @@ -492,7 +688,7 @@ static u64 intel_fbc_cfb_base_max(struct drm_i915_private *i915) return BIT_ULL(32); } -static u64 intel_fbc_stolen_end(struct drm_i915_private *dev_priv) +static u64 intel_fbc_stolen_end(struct drm_i915_private *i915) { u64 end; @@ -500,24 +696,24 @@ static u64 intel_fbc_stolen_end(struct drm_i915_private *dev_priv) * reserved range size, so it always assumes the maximum (8mb) is used. * If we enable FBC using a CFB on that memory range we'll get FIFO * underruns, even if that range is not reserved by the BIOS. */ - if (IS_BROADWELL(dev_priv) || (DISPLAY_VER(dev_priv) == 9 && - !IS_BROXTON(dev_priv))) - end = resource_size(&dev_priv->dsm) - 8 * 1024 * 1024; + if (IS_BROADWELL(i915) || + (DISPLAY_VER(i915) == 9 && !IS_BROXTON(i915))) + end = resource_size(&i915->dsm) - 8 * 1024 * 1024; else end = U64_MAX; - return min(end, intel_fbc_cfb_base_max(dev_priv)); + return min(end, intel_fbc_cfb_base_max(i915)); } -static int intel_fbc_min_limit(int fb_cpp) +static int intel_fbc_min_limit(const struct intel_plane_state *plane_state) { - return fb_cpp == 2 ? 2 : 1; + return plane_state->hw.fb->format->cpp[0] == 2 ? 2 : 1; } -static int intel_fbc_max_limit(struct drm_i915_private *dev_priv) +static int intel_fbc_max_limit(struct drm_i915_private *i915) { /* WaFbcOnly1to1Ratio:ctg */ - if (IS_G4X(dev_priv)) + if (IS_G4X(i915)) return 1; /* @@ -527,23 +723,23 @@ static int intel_fbc_max_limit(struct drm_i915_private *dev_priv) return 4; } -static int find_compression_limit(struct drm_i915_private *dev_priv, +static int find_compression_limit(struct intel_fbc *fbc, unsigned int size, int min_limit) { - struct intel_fbc *fbc = &dev_priv->fbc; - u64 end = intel_fbc_stolen_end(dev_priv); + struct drm_i915_private *i915 = fbc->i915; + u64 end = intel_fbc_stolen_end(i915); int ret, limit = min_limit; size /= limit; /* Try to over-allocate to reduce reallocations and fragmentation. */ - ret = i915_gem_stolen_insert_node_in_range(dev_priv, &fbc->compressed_fb, + ret = i915_gem_stolen_insert_node_in_range(i915, &fbc->compressed_fb, size <<= 1, 4096, 0, end); if (ret == 0) return limit; - for (; limit <= intel_fbc_max_limit(dev_priv); limit <<= 1) { - ret = i915_gem_stolen_insert_node_in_range(dev_priv, &fbc->compressed_fb, + for (; limit <= intel_fbc_max_limit(i915); limit <<= 1) { + ret = i915_gem_stolen_insert_node_in_range(i915, &fbc->compressed_fb, size >>= 1, 4096, 0, end); if (ret == 0) return limit; @@ -552,34 +748,34 @@ static int find_compression_limit(struct drm_i915_private *dev_priv, return 0; } -static int intel_fbc_alloc_cfb(struct drm_i915_private *dev_priv, +static int intel_fbc_alloc_cfb(struct intel_fbc *fbc, unsigned int size, int min_limit) { - struct intel_fbc *fbc = &dev_priv->fbc; + struct drm_i915_private *i915 = fbc->i915; int ret; - drm_WARN_ON(&dev_priv->drm, + drm_WARN_ON(&i915->drm, drm_mm_node_allocated(&fbc->compressed_fb)); - drm_WARN_ON(&dev_priv->drm, + drm_WARN_ON(&i915->drm, drm_mm_node_allocated(&fbc->compressed_llb)); - if (DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv)) { - ret = i915_gem_stolen_insert_node(dev_priv, &fbc->compressed_llb, + if (DISPLAY_VER(i915) < 5 && !IS_G4X(i915)) { + ret = i915_gem_stolen_insert_node(i915, &fbc->compressed_llb, 4096, 4096); if (ret) goto err; } - ret = find_compression_limit(dev_priv, size, min_limit); + ret = find_compression_limit(fbc, size, min_limit); if (!ret) goto err_llb; else if (ret > min_limit) - drm_info_once(&dev_priv->drm, + drm_info_once(&i915->drm, "Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n"); fbc->limit = ret; - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(&i915->drm, "reserved %llu bytes of contiguous stolen space for FBC, limit: %d\n", fbc->compressed_fb.size, fbc->limit); @@ -587,83 +783,69 @@ static int intel_fbc_alloc_cfb(struct drm_i915_private *dev_priv, err_llb: if (drm_mm_node_allocated(&fbc->compressed_llb)) - i915_gem_stolen_remove_node(dev_priv, &fbc->compressed_llb); + i915_gem_stolen_remove_node(i915, &fbc->compressed_llb); err: - if (drm_mm_initialized(&dev_priv->mm.stolen)) - drm_info_once(&dev_priv->drm, "not enough stolen space for compressed buffer (need %d more bytes), disabling. Hint: you may be able to increase stolen memory size in the BIOS to avoid this.\n", size); + if (drm_mm_initialized(&i915->mm.stolen)) + drm_info_once(&i915->drm, "not enough stolen space for compressed buffer (need %d more bytes), disabling. Hint: you may be able to increase stolen memory size in the BIOS to avoid this.\n", size); return -ENOSPC; } -static void intel_fbc_program_cfb(struct drm_i915_private *dev_priv) +static void intel_fbc_program_cfb(struct intel_fbc *fbc) { - struct intel_fbc *fbc = &dev_priv->fbc; - - if (DISPLAY_VER(dev_priv) >= 5) { - intel_de_write(dev_priv, ILK_DPFC_CB_BASE, - fbc->compressed_fb.start); - } else if (IS_GM45(dev_priv)) { - intel_de_write(dev_priv, DPFC_CB_BASE, - fbc->compressed_fb.start); - } else { - GEM_BUG_ON(range_overflows_end_t(u64, dev_priv->dsm.start, - fbc->compressed_fb.start, - U32_MAX)); - GEM_BUG_ON(range_overflows_end_t(u64, dev_priv->dsm.start, - fbc->compressed_llb.start, - U32_MAX)); - - intel_de_write(dev_priv, FBC_CFB_BASE, - dev_priv->dsm.start + fbc->compressed_fb.start); - intel_de_write(dev_priv, FBC_LL_BASE, - dev_priv->dsm.start + fbc->compressed_llb.start); - } + fbc->funcs->program_cfb(fbc); } -static void __intel_fbc_cleanup_cfb(struct drm_i915_private *dev_priv) +static void __intel_fbc_cleanup_cfb(struct intel_fbc *fbc) { - struct intel_fbc *fbc = &dev_priv->fbc; + struct drm_i915_private *i915 = fbc->i915; - if (WARN_ON(intel_fbc_hw_is_active(dev_priv))) + if (WARN_ON(intel_fbc_hw_is_active(fbc))) return; if (drm_mm_node_allocated(&fbc->compressed_llb)) - i915_gem_stolen_remove_node(dev_priv, &fbc->compressed_llb); + i915_gem_stolen_remove_node(i915, &fbc->compressed_llb); if (drm_mm_node_allocated(&fbc->compressed_fb)) - i915_gem_stolen_remove_node(dev_priv, &fbc->compressed_fb); + i915_gem_stolen_remove_node(i915, &fbc->compressed_fb); } -void intel_fbc_cleanup_cfb(struct drm_i915_private *dev_priv) +void intel_fbc_cleanup(struct drm_i915_private *i915) { - struct intel_fbc *fbc = &dev_priv->fbc; + struct intel_fbc *fbc = i915->fbc; - if (!HAS_FBC(dev_priv)) + if (!fbc) return; mutex_lock(&fbc->lock); - __intel_fbc_cleanup_cfb(dev_priv); + __intel_fbc_cleanup_cfb(fbc); mutex_unlock(&fbc->lock); + + kfree(fbc); } -static bool stride_is_valid(struct drm_i915_private *dev_priv, - u64 modifier, unsigned int stride) +static bool stride_is_valid(const struct intel_plane_state *plane_state) { + struct drm_i915_private *i915 = to_i915(plane_state->uapi.plane->dev); + const struct drm_framebuffer *fb = plane_state->hw.fb; + unsigned int stride = intel_fbc_plane_stride(plane_state) * + fb->format->cpp[0]; + /* This should have been caught earlier. */ - if (drm_WARN_ON_ONCE(&dev_priv->drm, (stride & (64 - 1)) != 0)) + if (drm_WARN_ON_ONCE(&i915->drm, (stride & (64 - 1)) != 0)) return false; /* Below are the additional FBC restrictions. */ if (stride < 512) return false; - if (DISPLAY_VER(dev_priv) == 2 || DISPLAY_VER(dev_priv) == 3) + if (DISPLAY_VER(i915) == 2 || DISPLAY_VER(i915) == 3) return stride == 4096 || stride == 8192; - if (DISPLAY_VER(dev_priv) == 4 && !IS_G4X(dev_priv) && stride < 2048) + if (DISPLAY_VER(i915) == 4 && !IS_G4X(i915) && stride < 2048) return false; /* Display WA #1105: skl,bxt,kbl,cfl,glk */ - if ((DISPLAY_VER(dev_priv) == 9 || IS_GEMINILAKE(dev_priv)) && - modifier == DRM_FORMAT_MOD_LINEAR && stride & 511) + if ((DISPLAY_VER(i915) == 9 || IS_GEMINILAKE(i915)) && + fb->modifier == DRM_FORMAT_MOD_LINEAR && stride & 511) return false; if (stride > 16384) @@ -672,20 +854,22 @@ static bool stride_is_valid(struct drm_i915_private *dev_priv, return true; } -static bool pixel_format_is_valid(struct drm_i915_private *dev_priv, - u32 pixel_format) +static bool pixel_format_is_valid(const struct intel_plane_state *plane_state) { - switch (pixel_format) { + struct drm_i915_private *i915 = to_i915(plane_state->uapi.plane->dev); + const struct drm_framebuffer *fb = plane_state->hw.fb; + + switch (fb->format->format) { case DRM_FORMAT_XRGB8888: case DRM_FORMAT_XBGR8888: return true; case DRM_FORMAT_XRGB1555: case DRM_FORMAT_RGB565: /* 16bpp not supported on gen2 */ - if (DISPLAY_VER(dev_priv) == 2) + if (DISPLAY_VER(i915) == 2) return false; /* WaFbcOnly1to1Ratio:ctg */ - if (IS_G4X(dev_priv)) + if (IS_G4X(i915)) return false; return true; default: @@ -693,13 +877,16 @@ static bool pixel_format_is_valid(struct drm_i915_private *dev_priv, } } -static bool rotation_is_valid(struct drm_i915_private *dev_priv, - u32 pixel_format, unsigned int rotation) +static bool rotation_is_valid(const struct intel_plane_state *plane_state) { - if (DISPLAY_VER(dev_priv) >= 9 && pixel_format == DRM_FORMAT_RGB565 && + struct drm_i915_private *i915 = to_i915(plane_state->uapi.plane->dev); + const struct drm_framebuffer *fb = plane_state->hw.fb; + unsigned int rotation = plane_state->hw.rotation; + + if (DISPLAY_VER(i915) >= 9 && fb->format->format == DRM_FORMAT_RGB565 && drm_rotation_90_or_270(rotation)) return false; - else if (DISPLAY_VER(dev_priv) <= 4 && !IS_G4X(dev_priv) && + else if (DISPLAY_VER(i915) <= 4 && !IS_G4X(i915) && rotation != DRM_MODE_ROTATE_0) return false; @@ -712,19 +899,18 @@ static bool rotation_is_valid(struct drm_i915_private *dev_priv, * the X and Y offset registers. That's why we include the src x/y offsets * instead of just looking at the plane size. */ -static bool intel_fbc_hw_tracking_covers_screen(struct intel_crtc *crtc) +static bool intel_fbc_hw_tracking_covers_screen(const struct intel_plane_state *plane_state) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - struct intel_fbc *fbc = &dev_priv->fbc; + struct drm_i915_private *i915 = to_i915(plane_state->uapi.plane->dev); unsigned int effective_w, effective_h, max_w, max_h; - if (DISPLAY_VER(dev_priv) >= 10) { + if (DISPLAY_VER(i915) >= 10) { max_w = 5120; max_h = 4096; - } else if (DISPLAY_VER(dev_priv) >= 8 || IS_HASWELL(dev_priv)) { + } else if (DISPLAY_VER(i915) >= 8 || IS_HASWELL(i915)) { max_w = 4096; max_h = 4096; - } else if (IS_G4X(dev_priv) || DISPLAY_VER(dev_priv) >= 5) { + } else if (IS_G4X(i915) || DISPLAY_VER(i915) >= 5) { max_w = 4096; max_h = 2048; } else { @@ -732,22 +918,24 @@ static bool intel_fbc_hw_tracking_covers_screen(struct intel_crtc *crtc) max_h = 1536; } - intel_fbc_get_plane_source_size(&fbc->state_cache, &effective_w, - &effective_h); - effective_w += fbc->state_cache.plane.adjusted_x; - effective_h += fbc->state_cache.plane.adjusted_y; + effective_w = plane_state->view.color_plane[0].x + + (drm_rect_width(&plane_state->uapi.src) >> 16); + effective_h = plane_state->view.color_plane[0].y + + (drm_rect_height(&plane_state->uapi.src) >> 16); return effective_w <= max_w && effective_h <= max_h; } -static bool tiling_is_valid(struct drm_i915_private *dev_priv, - u64 modifier) +static bool tiling_is_valid(const struct intel_plane_state *plane_state) { - switch (modifier) { + struct drm_i915_private *i915 = to_i915(plane_state->uapi.plane->dev); + const struct drm_framebuffer *fb = plane_state->hw.fb; + + switch (fb->modifier) { case DRM_FORMAT_MOD_LINEAR: case I915_FORMAT_MOD_Y_TILED: case I915_FORMAT_MOD_Yf_TILED: - return DISPLAY_VER(dev_priv) >= 9; + return DISPLAY_VER(i915) >= 9; case I915_FORMAT_MOD_X_TILED: return true; default: @@ -755,210 +943,163 @@ static bool tiling_is_valid(struct drm_i915_private *dev_priv, } } -static void intel_fbc_update_state_cache(struct intel_crtc *crtc, - const struct intel_crtc_state *crtc_state, - const struct intel_plane_state *plane_state) +static void intel_fbc_update_state(struct intel_atomic_state *state, + struct intel_crtc *crtc, + struct intel_plane *plane) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - struct intel_fbc *fbc = &dev_priv->fbc; - struct intel_fbc_state_cache *cache = &fbc->state_cache; - struct drm_framebuffer *fb = plane_state->hw.fb; - - cache->plane.visible = plane_state->uapi.visible; - if (!cache->plane.visible) - return; - - cache->crtc.mode_flags = crtc_state->hw.adjusted_mode.flags; - if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) - cache->crtc.hsw_bdw_pixel_rate = crtc_state->pixel_rate; - - cache->plane.rotation = plane_state->hw.rotation; - /* - * Src coordinates are already rotated by 270 degrees for - * the 90/270 degree plane rotation cases (to match the - * GTT mapping), hence no need to account for rotation here. - */ - cache->plane.src_w = drm_rect_width(&plane_state->uapi.src) >> 16; - cache->plane.src_h = drm_rect_height(&plane_state->uapi.src) >> 16; - cache->plane.adjusted_x = plane_state->view.color_plane[0].x; - cache->plane.adjusted_y = plane_state->view.color_plane[0].y; + struct drm_i915_private *i915 = to_i915(state->base.dev); + const struct intel_crtc_state *crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); + const struct intel_plane_state *plane_state = + intel_atomic_get_new_plane_state(state, plane); + struct intel_fbc *fbc = plane->fbc; + struct intel_fbc_state *fbc_state = &fbc->state; - cache->plane.pixel_blend_mode = plane_state->hw.pixel_blend_mode; + WARN_ON(plane_state->no_fbc_reason); - cache->fb.format = fb->format; - cache->fb.modifier = fb->modifier; - cache->fb.stride = intel_fbc_plane_stride(plane_state); + fbc_state->plane = plane; /* FBC1 compression interval: arbitrary choice of 1 second */ - cache->interval = drm_mode_vrefresh(&crtc_state->hw.adjusted_mode); + fbc_state->interval = drm_mode_vrefresh(&crtc_state->hw.adjusted_mode); - cache->fence_y_offset = intel_plane_fence_y_offset(plane_state); + fbc_state->fence_y_offset = intel_plane_fence_y_offset(plane_state); - drm_WARN_ON(&dev_priv->drm, plane_state->flags & PLANE_HAS_FENCE && + drm_WARN_ON(&i915->drm, plane_state->flags & PLANE_HAS_FENCE && !plane_state->ggtt_vma->fence); if (plane_state->flags & PLANE_HAS_FENCE && plane_state->ggtt_vma->fence) - cache->fence_id = plane_state->ggtt_vma->fence->id; + fbc_state->fence_id = plane_state->ggtt_vma->fence->id; else - cache->fence_id = -1; + fbc_state->fence_id = -1; - cache->psr2_active = crtc_state->has_psr2; + fbc_state->cfb_stride = intel_fbc_cfb_stride(plane_state); + fbc_state->cfb_size = intel_fbc_cfb_size(plane_state); + fbc_state->override_cfb_stride = intel_fbc_override_cfb_stride(plane_state); } -static bool intel_fbc_cfb_size_changed(struct drm_i915_private *dev_priv) +static bool intel_fbc_is_fence_ok(const struct intel_plane_state *plane_state) { - struct intel_fbc *fbc = &dev_priv->fbc; + struct drm_i915_private *i915 = to_i915(plane_state->uapi.plane->dev); - return intel_fbc_cfb_size(dev_priv, &fbc->state_cache) > - fbc->compressed_fb.size * fbc->limit; -} - -static u16 intel_fbc_override_cfb_stride(struct drm_i915_private *dev_priv, - const struct intel_fbc_state_cache *cache) -{ - unsigned int stride = _intel_fbc_cfb_stride(cache); - unsigned int stride_aligned = intel_fbc_cfb_stride(dev_priv, cache); - - /* - * Override stride in 64 byte units per 4 line segment. + /* 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. * - * Gen9 hw miscalculates cfb stride for linear as - * PLANE_STRIDE*512 instead of PLANE_STRIDE*64, so - * we always need to use the override there. + * The other method is by software tracking (see + * intel_fbc_invalidate/flush()), it will manually notify FBC and nuke + * the current compressed buffer and recompress it. + * + * 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. */ - if (stride != stride_aligned || - (DISPLAY_VER(dev_priv) == 9 && - cache->fb.modifier == DRM_FORMAT_MOD_LINEAR)) - return stride_aligned * 4 / 64; - - return 0; + return DISPLAY_VER(i915) >= 9 || + (plane_state->flags & PLANE_HAS_FENCE && + plane_state->ggtt_vma->fence); } -static bool intel_fbc_can_enable(struct drm_i915_private *dev_priv) +static bool intel_fbc_is_cfb_ok(const struct intel_plane_state *plane_state) { - struct intel_fbc *fbc = &dev_priv->fbc; - - if (intel_vgpu_active(dev_priv)) { - fbc->no_fbc_reason = "VGPU is active"; - return false; - } - - if (!dev_priv->params.enable_fbc) { - fbc->no_fbc_reason = "disabled per module param or by default"; - return false; - } + struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); + struct intel_fbc *fbc = plane->fbc; - if (fbc->underrun_detected) { - fbc->no_fbc_reason = "underrun detected"; - return false; - } + return intel_fbc_min_limit(plane_state) <= fbc->limit && + intel_fbc_cfb_size(plane_state) <= fbc->compressed_fb.size * fbc->limit; +} - return true; +static bool intel_fbc_is_ok(const struct intel_plane_state *plane_state) +{ + return !plane_state->no_fbc_reason && + intel_fbc_is_fence_ok(plane_state) && + intel_fbc_is_cfb_ok(plane_state); } -static bool intel_fbc_can_activate(struct intel_crtc *crtc) +static int intel_fbc_check_plane(struct intel_atomic_state *state, + struct intel_plane *plane) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - struct intel_fbc *fbc = &dev_priv->fbc; - struct intel_fbc_state_cache *cache = &fbc->state_cache; + struct drm_i915_private *i915 = to_i915(state->base.dev); + struct intel_plane_state *plane_state = + intel_atomic_get_new_plane_state(state, plane); + const struct drm_framebuffer *fb = plane_state->hw.fb; + struct intel_crtc *crtc = to_intel_crtc(plane_state->uapi.crtc); + const struct intel_crtc_state *crtc_state; + struct intel_fbc *fbc = plane->fbc; - if (!intel_fbc_can_enable(dev_priv)) - return false; + if (!fbc) + return 0; - if (!cache->plane.visible) { - fbc->no_fbc_reason = "primary plane not visible"; - return false; + if (intel_vgpu_active(i915)) { + plane_state->no_fbc_reason = "VGPU active"; + return 0; } - /* We don't need to use a state cache here since this information is - * global for all CRTC. - */ - if (fbc->underrun_detected) { - fbc->no_fbc_reason = "underrun detected"; - return false; + if (!i915->params.enable_fbc) { + plane_state->no_fbc_reason = "disabled per module param or by default"; + return 0; } - if (cache->crtc.mode_flags & DRM_MODE_FLAG_INTERLACE) { - fbc->no_fbc_reason = "incompatible mode"; - return false; + if (!plane_state->uapi.visible) { + plane_state->no_fbc_reason = "plane not visible"; + return 0; } - if (!intel_fbc_hw_tracking_covers_screen(crtc)) { - fbc->no_fbc_reason = "mode too large for compression"; - return false; + crtc_state = intel_atomic_get_new_crtc_state(state, crtc); + + if (crtc_state->hw.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE) { + plane_state->no_fbc_reason = "interlaced mode not supported"; + return 0; } - /* 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 - * intel_fbc_invalidate/flush()), it will manually notify FBC and nuke - * the current compressed buffer and recompress it. - * - * 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. - */ - if (DISPLAY_VER(dev_priv) < 9 && cache->fence_id < 0) { - fbc->no_fbc_reason = "framebuffer not tiled or fenced"; - return false; + if (crtc_state->double_wide) { + plane_state->no_fbc_reason = "double wide pipe not supported"; + return 0; } - if (!pixel_format_is_valid(dev_priv, cache->fb.format->format)) { - fbc->no_fbc_reason = "pixel format is invalid"; + /* + * Display 12+ is not supporting FBC with PSR2. + * Recommendation is to keep this combination disabled + * Bspec: 50422 HSD: 14010260002 + */ + if (DISPLAY_VER(i915) >= 12 && crtc_state->has_psr2) { + plane_state->no_fbc_reason = "PSR2 enabled"; return false; } - if (!rotation_is_valid(dev_priv, cache->fb.format->format, - cache->plane.rotation)) { - fbc->no_fbc_reason = "rotation unsupported"; - return false; + if (!pixel_format_is_valid(plane_state)) { + plane_state->no_fbc_reason = "pixel format not supported"; + return 0; } - if (!tiling_is_valid(dev_priv, cache->fb.modifier)) { - fbc->no_fbc_reason = "tiling unsupported"; - return false; + if (!tiling_is_valid(plane_state)) { + plane_state->no_fbc_reason = "tiling not supported"; + return 0; } - if (!stride_is_valid(dev_priv, cache->fb.modifier, - cache->fb.stride * cache->fb.format->cpp[0])) { - fbc->no_fbc_reason = "framebuffer stride not supported"; - return false; + if (!rotation_is_valid(plane_state)) { + plane_state->no_fbc_reason = "rotation not supported"; + return 0; } - if (cache->plane.pixel_blend_mode != DRM_MODE_BLEND_PIXEL_NONE && - cache->fb.format->has_alpha) { - fbc->no_fbc_reason = "per-pixel alpha blending is incompatible with FBC"; - return false; + if (!stride_is_valid(plane_state)) { + plane_state->no_fbc_reason = "stride not supported"; + return 0; } - /* WaFbcExceedCdClockThreshold:hsw,bdw */ - if ((IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) && - cache->crtc.hsw_bdw_pixel_rate >= dev_priv->cdclk.hw.cdclk * 95 / 100) { - fbc->no_fbc_reason = "pixel rate is too big"; + if (plane_state->hw.pixel_blend_mode != DRM_MODE_BLEND_PIXEL_NONE && + fb->format->has_alpha) { + plane_state->no_fbc_reason = "per-pixel alpha not supported"; return false; } - /* It is possible for the required CFB size change without a - * crtc->disable + crtc->enable since it is possible to change the - * stride without triggering a full modeset. Since we try to - * over-allocate the CFB, there's a chance we may keep FBC enabled even - * if this happens, but if we exceed the current CFB size we'll have to - * disable FBC. Notice that it would be possible to disable FBC, wait - * for a frame, free the stolen node, then try to reenable FBC in case - * we didn't get any invalidate/deactivate calls, but this would require - * a lot of tracking just for a specific case. If we conclude it's an - * important case, we can implement it later. */ - if (intel_fbc_cfb_size_changed(dev_priv)) { - fbc->no_fbc_reason = "CFB requirements changed"; - return false; + if (!intel_fbc_hw_tracking_covers_screen(plane_state)) { + plane_state->no_fbc_reason = "plane size too big"; + return 0; } /* @@ -966,238 +1107,211 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc) * having a Y offset that isn't divisible by 4 causes FIFO underrun * and screen flicker. */ - if (DISPLAY_VER(dev_priv) >= 9 && - (fbc->state_cache.plane.adjusted_y & 3)) { - fbc->no_fbc_reason = "plane Y offset is misaligned"; + if (DISPLAY_VER(i915) >= 9 && + plane_state->view.color_plane[0].y & 3) { + plane_state->no_fbc_reason = "plane start Y offset misaligned"; return false; } /* Wa_22010751166: icl, ehl, tgl, dg1, rkl */ - if (DISPLAY_VER(dev_priv) >= 11 && - (cache->plane.src_h + cache->plane.adjusted_y) % 4) { - fbc->no_fbc_reason = "plane height + offset is non-modulo of 4"; - return false; - } - - /* - * Display 12+ is not supporting FBC with PSR2. - * Recommendation is to keep this combination disabled - * Bspec: 50422 HSD: 14010260002 - */ - if (fbc->state_cache.psr2_active && DISPLAY_VER(dev_priv) >= 12) { - fbc->no_fbc_reason = "not supported with PSR2"; + if (DISPLAY_VER(i915) >= 11 && + (plane_state->view.color_plane[0].y + drm_rect_height(&plane_state->uapi.src)) & 3) { + plane_state->no_fbc_reason = "plane end Y offset misaligned"; return false; } - return true; -} - -static void intel_fbc_get_reg_params(struct intel_crtc *crtc, - struct intel_fbc_reg_params *params) -{ - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - struct intel_fbc *fbc = &dev_priv->fbc; - struct intel_fbc_state_cache *cache = &fbc->state_cache; - - /* Since all our fields are integer types, use memset here so the - * comparison function can rely on memcmp because the padding will be - * zero. */ - memset(params, 0, sizeof(*params)); - - params->fence_id = cache->fence_id; - params->fence_y_offset = cache->fence_y_offset; - - params->interval = cache->interval; + /* WaFbcExceedCdClockThreshold:hsw,bdw */ + if (IS_HASWELL(i915) || IS_BROADWELL(i915)) { + const struct intel_cdclk_state *cdclk_state; - params->crtc.pipe = crtc->pipe; - params->crtc.i9xx_plane = to_intel_plane(crtc->base.primary)->i9xx_plane; + cdclk_state = intel_atomic_get_cdclk_state(state); + if (IS_ERR(cdclk_state)) + return PTR_ERR(cdclk_state); - params->fb.format = cache->fb.format; - params->fb.modifier = cache->fb.modifier; - params->fb.stride = cache->fb.stride; + if (crtc_state->pixel_rate >= cdclk_state->logical.cdclk * 95 / 100) { + plane_state->no_fbc_reason = "pixel rate too high"; + return 0; + } + } - params->cfb_stride = intel_fbc_cfb_stride(dev_priv, cache); - params->cfb_size = intel_fbc_cfb_size(dev_priv, cache); - params->override_cfb_stride = intel_fbc_override_cfb_stride(dev_priv, cache); + plane_state->no_fbc_reason = NULL; - params->plane_visible = cache->plane.visible; + return 0; } -static bool intel_fbc_can_flip_nuke(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 intel_fbc *fbc = &dev_priv->fbc; - const struct intel_fbc_state_cache *cache = &fbc->state_cache; - const struct intel_fbc_reg_params *params = &fbc->params; - if (drm_atomic_crtc_needs_modeset(&crtc_state->uapi)) - return false; +static bool intel_fbc_can_flip_nuke(struct intel_atomic_state *state, + struct intel_crtc *crtc, + struct intel_plane *plane) +{ + const struct intel_crtc_state *new_crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); + const struct intel_plane_state *old_plane_state = + intel_atomic_get_old_plane_state(state, plane); + const struct intel_plane_state *new_plane_state = + intel_atomic_get_new_plane_state(state, plane); + const struct drm_framebuffer *old_fb = old_plane_state->hw.fb; + const struct drm_framebuffer *new_fb = new_plane_state->hw.fb; - if (!params->plane_visible) + if (drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi)) return false; - if (!intel_fbc_can_activate(crtc)) + if (!intel_fbc_is_ok(old_plane_state) || + !intel_fbc_is_ok(new_plane_state)) return false; - if (params->fb.format != cache->fb.format) + if (old_fb->format->format != new_fb->format->format) return false; - if (params->fb.modifier != cache->fb.modifier) + if (old_fb->modifier != new_fb->modifier) return false; - if (params->fb.stride != cache->fb.stride) + if (intel_fbc_plane_stride(old_plane_state) != + intel_fbc_plane_stride(new_plane_state)) return false; - if (params->cfb_stride != intel_fbc_cfb_stride(dev_priv, cache)) + if (intel_fbc_cfb_stride(old_plane_state) != + intel_fbc_cfb_stride(new_plane_state)) return false; - if (params->cfb_size != intel_fbc_cfb_size(dev_priv, cache)) + if (intel_fbc_cfb_size(old_plane_state) != + intel_fbc_cfb_size(new_plane_state)) return false; - if (params->override_cfb_stride != intel_fbc_override_cfb_stride(dev_priv, cache)) + if (intel_fbc_override_cfb_stride(old_plane_state) != + intel_fbc_override_cfb_stride(new_plane_state)) return false; return true; } -bool intel_fbc_pre_update(struct intel_atomic_state *state, - struct intel_crtc *crtc) +static bool __intel_fbc_pre_update(struct intel_atomic_state *state, + struct intel_crtc *crtc, + struct intel_plane *plane) { - struct intel_plane *plane = to_intel_plane(crtc->base.primary); - const struct intel_crtc_state *crtc_state = - intel_atomic_get_new_crtc_state(state, crtc); - const struct intel_plane_state *plane_state = - intel_atomic_get_new_plane_state(state, plane); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - struct intel_fbc *fbc = &dev_priv->fbc; - const char *reason = "update pending"; + struct drm_i915_private *i915 = to_i915(state->base.dev); + struct intel_fbc *fbc = plane->fbc; bool need_vblank_wait = false; - if (!plane->has_fbc || !plane_state) - return need_vblank_wait; - - mutex_lock(&fbc->lock); + fbc->flip_pending = true; - if (fbc->crtc != crtc) - goto unlock; + if (intel_fbc_can_flip_nuke(state, crtc, plane)) + return need_vblank_wait; - intel_fbc_update_state_cache(crtc, crtc_state, plane_state); - fbc->flip_pending = true; + intel_fbc_deactivate(fbc, "update pending"); - if (!intel_fbc_can_flip_nuke(crtc_state)) { - intel_fbc_deactivate(dev_priv, reason); - - /* - * Display WA #1198: glk+ - * Need an extra vblank wait between FBC disable and most plane - * updates. Bspec says this is only needed for plane disable, but - * that is not true. Touching most plane registers will cause the - * corruption to appear. Also SKL/derivatives do not seem to be - * affected. - * - * TODO: could optimize this a bit by sampling the frame - * counter when we disable FBC (if it was already done earlier) - * and skipping the extra vblank wait before the plane update - * if at least one frame has already passed. - */ - if (fbc->activated && - DISPLAY_VER(dev_priv) >= 10) - need_vblank_wait = true; - fbc->activated = false; - } -unlock: - mutex_unlock(&fbc->lock); + /* + * Display WA #1198: glk+ + * Need an extra vblank wait between FBC disable and most plane + * updates. Bspec says this is only needed for plane disable, but + * that is not true. Touching most plane registers will cause the + * corruption to appear. Also SKL/derivatives do not seem to be + * affected. + * + * TODO: could optimize this a bit by sampling the frame + * counter when we disable FBC (if it was already done earlier) + * and skipping the extra vblank wait before the plane update + * if at least one frame has already passed. + */ + if (fbc->activated && DISPLAY_VER(i915) >= 10) + need_vblank_wait = true; + fbc->activated = false; return need_vblank_wait; } -/** - * __intel_fbc_disable - disable FBC - * @dev_priv: i915 device instance - * - * This is the low level function that actually disables FBC. Callers should - * grab the FBC lock. - */ -static void __intel_fbc_disable(struct drm_i915_private *dev_priv) +bool intel_fbc_pre_update(struct intel_atomic_state *state, + struct intel_crtc *crtc) { - struct intel_fbc *fbc = &dev_priv->fbc; - struct intel_crtc *crtc = fbc->crtc; + const struct intel_plane_state *plane_state; + bool need_vblank_wait = false; + struct intel_plane *plane; + int i; + + for_each_new_intel_plane_in_state(state, plane, plane_state, i) { + struct intel_fbc *fbc = plane->fbc; - drm_WARN_ON(&dev_priv->drm, !mutex_is_locked(&fbc->lock)); - drm_WARN_ON(&dev_priv->drm, !fbc->crtc); - drm_WARN_ON(&dev_priv->drm, fbc->active); + if (!fbc || plane->pipe != crtc->pipe) + continue; - drm_dbg_kms(&dev_priv->drm, "Disabling FBC on pipe %c\n", - pipe_name(crtc->pipe)); + mutex_lock(&fbc->lock); - __intel_fbc_cleanup_cfb(dev_priv); + if (fbc->state.plane == plane) + need_vblank_wait |= __intel_fbc_pre_update(state, crtc, plane); - fbc->crtc = NULL; + mutex_unlock(&fbc->lock); + } + + return need_vblank_wait; } -static void __intel_fbc_post_update(struct intel_crtc *crtc) +static void __intel_fbc_disable(struct intel_fbc *fbc) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - struct intel_fbc *fbc = &dev_priv->fbc; - - drm_WARN_ON(&dev_priv->drm, !mutex_is_locked(&fbc->lock)); + struct drm_i915_private *i915 = fbc->i915; + struct intel_plane *plane = fbc->state.plane; - if (fbc->crtc != crtc) - return; + drm_WARN_ON(&i915->drm, !mutex_is_locked(&fbc->lock)); + drm_WARN_ON(&i915->drm, fbc->active); - fbc->flip_pending = false; + drm_dbg_kms(&i915->drm, "Disabling FBC on [PLANE:%d:%s]\n", + plane->base.base.id, plane->base.name); - if (!dev_priv->params.enable_fbc) { - intel_fbc_deactivate(dev_priv, "disabled at runtime per module param"); - __intel_fbc_disable(dev_priv); + __intel_fbc_cleanup_cfb(fbc); - return; - } + fbc->state.plane = NULL; +} - intel_fbc_get_reg_params(crtc, &fbc->params); +static void __intel_fbc_post_update(struct intel_fbc *fbc) +{ + struct drm_i915_private *i915 = fbc->i915; - if (!intel_fbc_can_activate(crtc)) - return; + drm_WARN_ON(&i915->drm, !mutex_is_locked(&fbc->lock)); if (!fbc->busy_bits) - intel_fbc_activate(dev_priv); + intel_fbc_activate(fbc); else - intel_fbc_deactivate(dev_priv, "frontbuffer write"); + intel_fbc_deactivate(fbc, "frontbuffer write"); } void intel_fbc_post_update(struct intel_atomic_state *state, struct intel_crtc *crtc) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - struct intel_plane *plane = to_intel_plane(crtc->base.primary); - const struct intel_plane_state *plane_state = - intel_atomic_get_new_plane_state(state, plane); - struct intel_fbc *fbc = &dev_priv->fbc; + const struct intel_plane_state *plane_state; + struct intel_plane *plane; + int i; - if (!plane->has_fbc || !plane_state) - return; + for_each_new_intel_plane_in_state(state, plane, plane_state, i) { + struct intel_fbc *fbc = plane->fbc; - mutex_lock(&fbc->lock); - __intel_fbc_post_update(crtc); - mutex_unlock(&fbc->lock); + if (!fbc || plane->pipe != crtc->pipe) + continue; + + mutex_lock(&fbc->lock); + + if (fbc->state.plane == plane) { + fbc->flip_pending = false; + __intel_fbc_post_update(fbc); + } + + mutex_unlock(&fbc->lock); + } } static unsigned int intel_fbc_get_frontbuffer_bit(struct intel_fbc *fbc) { - if (fbc->crtc) - return to_intel_plane(fbc->crtc->base.primary)->frontbuffer_bit; + if (fbc->state.plane) + return fbc->state.plane->frontbuffer_bit; else return fbc->possible_framebuffer_bits; } -void intel_fbc_invalidate(struct drm_i915_private *dev_priv, +void intel_fbc_invalidate(struct drm_i915_private *i915, unsigned int frontbuffer_bits, enum fb_op_origin origin) { - struct intel_fbc *fbc = &dev_priv->fbc; + struct intel_fbc *fbc = i915->fbc; - if (!HAS_FBC(dev_priv)) + if (!fbc) return; if (origin == ORIGIN_FLIP || origin == ORIGIN_CURSOR_UPDATE) @@ -1207,18 +1321,18 @@ void intel_fbc_invalidate(struct drm_i915_private *dev_priv, fbc->busy_bits |= intel_fbc_get_frontbuffer_bit(fbc) & frontbuffer_bits; - if (fbc->crtc && fbc->busy_bits) - intel_fbc_deactivate(dev_priv, "frontbuffer write"); + if (fbc->state.plane && fbc->busy_bits) + intel_fbc_deactivate(fbc, "frontbuffer write"); mutex_unlock(&fbc->lock); } -void intel_fbc_flush(struct drm_i915_private *dev_priv, +void intel_fbc_flush(struct drm_i915_private *i915, unsigned int frontbuffer_bits, enum fb_op_origin origin) { - struct intel_fbc *fbc = &dev_priv->fbc; + struct intel_fbc *fbc = i915->fbc; - if (!HAS_FBC(dev_priv)) + if (!fbc) return; mutex_lock(&fbc->lock); @@ -1228,143 +1342,85 @@ void intel_fbc_flush(struct drm_i915_private *dev_priv, if (origin == ORIGIN_FLIP || origin == ORIGIN_CURSOR_UPDATE) goto out; - if (!fbc->busy_bits && fbc->crtc && + if (!fbc->busy_bits && fbc->state.plane && (frontbuffer_bits & intel_fbc_get_frontbuffer_bit(fbc))) { if (fbc->active) - intel_fbc_recompress(dev_priv); + intel_fbc_nuke(fbc); else if (!fbc->flip_pending) - __intel_fbc_post_update(fbc->crtc); + __intel_fbc_post_update(fbc); } out: mutex_unlock(&fbc->lock); } -/** - * intel_fbc_choose_crtc - select a CRTC to enable FBC on - * @dev_priv: i915 device instance - * @state: the atomic state structure - * - * This function looks at the proposed state for CRTCs and planes, then chooses - * which pipe is going to have FBC by setting intel_crtc_state->enable_fbc to - * true. - * - * Later, intel_fbc_enable is going to look for state->enable_fbc and then maybe - * enable FBC for the chosen CRTC. If it does, it will set dev_priv->fbc.crtc. - */ -void intel_fbc_choose_crtc(struct drm_i915_private *dev_priv, - struct intel_atomic_state *state) +int intel_fbc_atomic_check(struct intel_atomic_state *state) { - struct intel_fbc *fbc = &dev_priv->fbc; - struct intel_plane *plane; struct intel_plane_state *plane_state; - bool crtc_chosen = false; + struct intel_plane *plane; int i; - mutex_lock(&fbc->lock); - - /* Does this atomic commit involve the CRTC currently tied to FBC? */ - if (fbc->crtc && - !intel_atomic_get_new_crtc_state(state, fbc->crtc)) - goto out; - - if (!intel_fbc_can_enable(dev_priv)) - goto out; - - /* Simply choose the first CRTC that is compatible and has a visible - * plane. We could go for fancier schemes such as checking the plane - * size, but this would just affect the few platforms that don't tie FBC - * to pipe or plane A. */ for_each_new_intel_plane_in_state(state, plane, plane_state, i) { - struct intel_crtc_state *crtc_state; - struct intel_crtc *crtc = to_intel_crtc(plane_state->hw.crtc); - - if (!plane->has_fbc) - continue; + int ret; - if (!plane_state->uapi.visible) - continue; - - crtc_state = intel_atomic_get_new_crtc_state(state, crtc); - - crtc_state->enable_fbc = true; - crtc_chosen = true; - break; + ret = intel_fbc_check_plane(state, plane); + if (ret) + return ret; } - if (!crtc_chosen) - fbc->no_fbc_reason = "no suitable CRTC for FBC"; - -out: - mutex_unlock(&fbc->lock); + return 0; } -/** - * intel_fbc_enable: tries to enable FBC on the CRTC - * @crtc: the CRTC - * @state: corresponding &drm_crtc_state for @crtc - * - * This function checks if the given CRTC was chosen for FBC, then enables it if - * possible. Notice that it doesn't activate FBC. It is valid to call - * intel_fbc_enable multiple times for the same pipe without an - * intel_fbc_disable in the middle, as long as it is deactivated. - */ -static void intel_fbc_enable(struct intel_atomic_state *state, - struct intel_crtc *crtc) +static void __intel_fbc_enable(struct intel_atomic_state *state, + struct intel_crtc *crtc, + struct intel_plane *plane) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - struct intel_plane *plane = to_intel_plane(crtc->base.primary); - const struct intel_crtc_state *crtc_state = - intel_atomic_get_new_crtc_state(state, crtc); + struct drm_i915_private *i915 = to_i915(state->base.dev); const struct intel_plane_state *plane_state = intel_atomic_get_new_plane_state(state, plane); - struct intel_fbc *fbc = &dev_priv->fbc; - struct intel_fbc_state_cache *cache = &fbc->state_cache; - int min_limit; + struct intel_fbc *fbc = plane->fbc; - if (!plane->has_fbc || !plane_state) - return; + if (fbc->state.plane) { + if (fbc->state.plane != plane) + return; - min_limit = intel_fbc_min_limit(plane_state->hw.fb ? - plane_state->hw.fb->format->cpp[0] : 0); + if (intel_fbc_is_ok(plane_state)) { + intel_fbc_update_state(state, crtc, plane); + return; + } - mutex_lock(&fbc->lock); + __intel_fbc_disable(fbc); + } - if (fbc->crtc) { - if (fbc->crtc != crtc) - goto out; + drm_WARN_ON(&i915->drm, fbc->active); - if (fbc->limit >= min_limit && - !intel_fbc_cfb_size_changed(dev_priv)) - goto out; + fbc->no_fbc_reason = plane_state->no_fbc_reason; + if (fbc->no_fbc_reason) + return; - __intel_fbc_disable(dev_priv); + if (!intel_fbc_is_fence_ok(plane_state)) { + fbc->no_fbc_reason = "framebuffer not fenced"; + return; } - drm_WARN_ON(&dev_priv->drm, fbc->active); - - intel_fbc_update_state_cache(crtc, crtc_state, plane_state); - - /* FIXME crtc_state->enable_fbc lies :( */ - if (!cache->plane.visible) - goto out; + if (fbc->underrun_detected) { + fbc->no_fbc_reason = "FIFO underrun"; + return; + } - if (intel_fbc_alloc_cfb(dev_priv, - intel_fbc_cfb_size(dev_priv, cache), min_limit)) { - cache->plane.visible = false; + if (intel_fbc_alloc_cfb(fbc, intel_fbc_cfb_size(plane_state), + intel_fbc_min_limit(plane_state))) { fbc->no_fbc_reason = "not enough stolen memory"; - goto out; + return; } - drm_dbg_kms(&dev_priv->drm, "Enabling FBC on pipe %c\n", - pipe_name(crtc->pipe)); + drm_dbg_kms(&i915->drm, "Enabling FBC on [PLANE:%d:%s]\n", + plane->base.base.id, plane->base.name); fbc->no_fbc_reason = "FBC enabled but not active yet\n"; - fbc->crtc = crtc; + intel_fbc_update_state(state, crtc, plane); - intel_fbc_program_cfb(dev_priv); -out: - mutex_unlock(&fbc->lock); + intel_fbc_program_cfb(fbc); } /** @@ -1375,114 +1431,122 @@ out: */ void intel_fbc_disable(struct intel_crtc *crtc) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - struct intel_plane *plane = to_intel_plane(crtc->base.primary); - struct intel_fbc *fbc = &dev_priv->fbc; + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + struct intel_plane *plane; - if (!plane->has_fbc) - return; + for_each_intel_plane(&i915->drm, plane) { + struct intel_fbc *fbc = plane->fbc; - mutex_lock(&fbc->lock); - if (fbc->crtc == crtc) - __intel_fbc_disable(dev_priv); - mutex_unlock(&fbc->lock); + if (!fbc || plane->pipe != crtc->pipe) + continue; + + mutex_lock(&fbc->lock); + if (fbc->state.plane == plane) + __intel_fbc_disable(fbc); + mutex_unlock(&fbc->lock); + } } -/** - * intel_fbc_update: enable/disable FBC on the CRTC - * @state: atomic state - * @crtc: the CRTC - * - * This function checks if the given CRTC was chosen for FBC, then enables it if - * possible. Notice that it doesn't activate FBC. It is valid to call - * intel_fbc_update multiple times for the same pipe without an - * intel_fbc_disable in the middle. - */ void intel_fbc_update(struct intel_atomic_state *state, struct intel_crtc *crtc) { const struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc); + const struct intel_plane_state *plane_state; + struct intel_plane *plane; + int i; - if (crtc_state->update_pipe && !crtc_state->enable_fbc) - intel_fbc_disable(crtc); - else - intel_fbc_enable(state, crtc); + for_each_new_intel_plane_in_state(state, plane, plane_state, i) { + struct intel_fbc *fbc = plane->fbc; + + if (!fbc || plane->pipe != crtc->pipe) + continue; + + mutex_lock(&fbc->lock); + + if (crtc_state->update_pipe && plane_state->no_fbc_reason) { + if (fbc->state.plane == plane) + __intel_fbc_disable(fbc); + } else { + __intel_fbc_enable(state, crtc, plane); + } + + mutex_unlock(&fbc->lock); + } } /** * intel_fbc_global_disable - globally disable FBC - * @dev_priv: i915 device instance + * @i915: i915 device instance * * This function disables FBC regardless of which CRTC is associated with it. */ -void intel_fbc_global_disable(struct drm_i915_private *dev_priv) +void intel_fbc_global_disable(struct drm_i915_private *i915) { - struct intel_fbc *fbc = &dev_priv->fbc; + struct intel_fbc *fbc = i915->fbc; - if (!HAS_FBC(dev_priv)) + if (!fbc) return; mutex_lock(&fbc->lock); - if (fbc->crtc) { - drm_WARN_ON(&dev_priv->drm, fbc->crtc->active); - __intel_fbc_disable(dev_priv); - } + if (fbc->state.plane) + __intel_fbc_disable(fbc); mutex_unlock(&fbc->lock); } static void intel_fbc_underrun_work_fn(struct work_struct *work) { - struct drm_i915_private *dev_priv = - container_of(work, struct drm_i915_private, fbc.underrun_work); - struct intel_fbc *fbc = &dev_priv->fbc; + struct intel_fbc *fbc = container_of(work, typeof(*fbc), underrun_work); + struct drm_i915_private *i915 = fbc->i915; mutex_lock(&fbc->lock); /* Maybe we were scheduled twice. */ - if (fbc->underrun_detected || !fbc->crtc) + if (fbc->underrun_detected || !fbc->state.plane) goto out; - drm_dbg_kms(&dev_priv->drm, "Disabling FBC due to FIFO underrun.\n"); + drm_dbg_kms(&i915->drm, "Disabling FBC due to FIFO underrun.\n"); fbc->underrun_detected = true; - intel_fbc_deactivate(dev_priv, "FIFO underrun"); + intel_fbc_deactivate(fbc, "FIFO underrun"); + if (!fbc->flip_pending) + intel_crtc_wait_for_next_vblank(intel_crtc_for_pipe(i915, fbc->state.plane->pipe)); + __intel_fbc_disable(fbc); out: mutex_unlock(&fbc->lock); } /* * intel_fbc_reset_underrun - reset FBC fifo underrun status. - * @dev_priv: i915 device instance + * @i915: the i915 device * * See intel_fbc_handle_fifo_underrun_irq(). For automated testing we * want to re-enable FBC after an underrun to increase test coverage. */ -int intel_fbc_reset_underrun(struct drm_i915_private *dev_priv) +void intel_fbc_reset_underrun(struct drm_i915_private *i915) { - int ret; + struct intel_fbc *fbc = i915->fbc; - cancel_work_sync(&dev_priv->fbc.underrun_work); + if (!fbc) + return; - ret = mutex_lock_interruptible(&dev_priv->fbc.lock); - if (ret) - return ret; + cancel_work_sync(&fbc->underrun_work); - if (dev_priv->fbc.underrun_detected) { - drm_dbg_kms(&dev_priv->drm, + mutex_lock(&fbc->lock); + + if (fbc->underrun_detected) { + drm_dbg_kms(&i915->drm, "Re-allowing FBC after fifo underrun\n"); - dev_priv->fbc.no_fbc_reason = "FIFO underrun cleared"; + fbc->no_fbc_reason = "FIFO underrun cleared"; } - dev_priv->fbc.underrun_detected = false; - mutex_unlock(&dev_priv->fbc.lock); - - return 0; + fbc->underrun_detected = false; + mutex_unlock(&fbc->lock); } /** * intel_fbc_handle_fifo_underrun_irq - disable FBC when we get a FIFO underrun - * @dev_priv: i915 device instance + * @i915: i915 device * * Without FBC, most underruns are harmless and don't really cause too many * problems, except for an annoying message on dmesg. With FBC, underruns can @@ -1494,11 +1558,11 @@ int intel_fbc_reset_underrun(struct drm_i915_private *dev_priv) * * This function is called from the IRQ handler. */ -void intel_fbc_handle_fifo_underrun_irq(struct drm_i915_private *dev_priv) +void intel_fbc_handle_fifo_underrun_irq(struct drm_i915_private *i915) { - struct intel_fbc *fbc = &dev_priv->fbc; + struct intel_fbc *fbc = i915->fbc; - if (!HAS_FBC(dev_priv)) + if (!fbc) return; /* There's no guarantee that underrun_detected won't be set to true @@ -1522,26 +1586,26 @@ void intel_fbc_handle_fifo_underrun_irq(struct drm_i915_private *dev_priv) * space to change the value during runtime without sanitizing it again. IGT * relies on being able to change i915.enable_fbc at runtime. */ -static int intel_sanitize_fbc_option(struct drm_i915_private *dev_priv) +static int intel_sanitize_fbc_option(struct drm_i915_private *i915) { - if (dev_priv->params.enable_fbc >= 0) - return !!dev_priv->params.enable_fbc; + if (i915->params.enable_fbc >= 0) + return !!i915->params.enable_fbc; - if (!HAS_FBC(dev_priv)) + if (!HAS_FBC(i915)) return 0; - if (IS_BROADWELL(dev_priv) || DISPLAY_VER(dev_priv) >= 9) + if (IS_BROADWELL(i915) || DISPLAY_VER(i915) >= 9) return 1; return 0; } -static bool need_fbc_vtd_wa(struct drm_i915_private *dev_priv) +static bool need_fbc_vtd_wa(struct drm_i915_private *i915) { /* WaFbcTurnOffFbcWhenHyperVisorIsUsed:skl,bxt */ - if (intel_vtd_active() && - (IS_SKYLAKE(dev_priv) || IS_BROXTON(dev_priv))) { - drm_info(&dev_priv->drm, + if (intel_vtd_active(i915) && + (IS_SKYLAKE(i915) || IS_BROXTON(i915))) { + drm_info(&i915->drm, "Disabling framebuffer compression (FBC) to prevent screen flicker with VT-d enabled\n"); return true; } @@ -1549,38 +1613,171 @@ static bool need_fbc_vtd_wa(struct drm_i915_private *dev_priv) return false; } +void intel_fbc_add_plane(struct intel_fbc *fbc, struct intel_plane *plane) +{ + if (!fbc) + return; + + plane->fbc = fbc; + fbc->possible_framebuffer_bits |= plane->frontbuffer_bit; +} + +static struct intel_fbc *intel_fbc_create(struct drm_i915_private *i915) +{ + struct intel_fbc *fbc; + + fbc = kzalloc(sizeof(*fbc), GFP_KERNEL); + if (!fbc) + return NULL; + + fbc->i915 = i915; + INIT_WORK(&fbc->underrun_work, intel_fbc_underrun_work_fn); + mutex_init(&fbc->lock); + + if (DISPLAY_VER(i915) >= 7) + fbc->funcs = &ivb_fbc_funcs; + else if (DISPLAY_VER(i915) == 6) + fbc->funcs = &snb_fbc_funcs; + else if (DISPLAY_VER(i915) == 5) + fbc->funcs = &ilk_fbc_funcs; + else if (IS_G4X(i915)) + fbc->funcs = &g4x_fbc_funcs; + else if (DISPLAY_VER(i915) == 4) + fbc->funcs = &i965_fbc_funcs; + else + fbc->funcs = &i8xx_fbc_funcs; + + return fbc; +} + /** * intel_fbc_init - Initialize FBC - * @dev_priv: the i915 device + * @i915: the i915 device * * This function might be called during PM init process. */ -void intel_fbc_init(struct drm_i915_private *dev_priv) +void intel_fbc_init(struct drm_i915_private *i915) { - struct intel_fbc *fbc = &dev_priv->fbc; + struct intel_fbc *fbc; - INIT_WORK(&fbc->underrun_work, intel_fbc_underrun_work_fn); - mutex_init(&fbc->lock); - fbc->active = false; + if (!drm_mm_initialized(&i915->mm.stolen)) + mkwrite_device_info(i915)->display.has_fbc = false; - if (!drm_mm_initialized(&dev_priv->mm.stolen)) - mkwrite_device_info(dev_priv)->display.has_fbc = false; + if (need_fbc_vtd_wa(i915)) + mkwrite_device_info(i915)->display.has_fbc = false; - if (need_fbc_vtd_wa(dev_priv)) - mkwrite_device_info(dev_priv)->display.has_fbc = false; + i915->params.enable_fbc = intel_sanitize_fbc_option(i915); + drm_dbg_kms(&i915->drm, "Sanitized enable_fbc value: %d\n", + i915->params.enable_fbc); - dev_priv->params.enable_fbc = intel_sanitize_fbc_option(dev_priv); - drm_dbg_kms(&dev_priv->drm, "Sanitized enable_fbc value: %d\n", - dev_priv->params.enable_fbc); + if (!HAS_FBC(i915)) + return; - if (!HAS_FBC(dev_priv)) { - fbc->no_fbc_reason = "unsupported by this chipset"; + fbc = intel_fbc_create(i915); + if (!fbc) return; - } /* We still don't have any sort of hardware state readout for FBC, so * deactivate it in case the BIOS activated it to make sure software * matches the hardware state. */ - if (intel_fbc_hw_is_active(dev_priv)) - intel_fbc_hw_deactivate(dev_priv); + if (intel_fbc_hw_is_active(fbc)) + intel_fbc_hw_deactivate(fbc); + + i915->fbc = fbc; +} + +static int intel_fbc_debugfs_status_show(struct seq_file *m, void *unused) +{ + struct intel_fbc *fbc = m->private; + struct drm_i915_private *i915 = fbc->i915; + struct intel_plane *plane; + intel_wakeref_t wakeref; + + drm_modeset_lock_all(&i915->drm); + + wakeref = intel_runtime_pm_get(&i915->runtime_pm); + mutex_lock(&fbc->lock); + + if (fbc->active) { + seq_puts(m, "FBC enabled\n"); + seq_printf(m, "Compressing: %s\n", + yesno(intel_fbc_is_compressing(fbc))); + } else { + seq_printf(m, "FBC disabled: %s\n", fbc->no_fbc_reason); + } + + for_each_intel_plane(&i915->drm, plane) { + const struct intel_plane_state *plane_state = + to_intel_plane_state(plane->base.state); + + if (plane->fbc != fbc) + continue; + + seq_printf(m, "%c [PLANE:%d:%s]: %s\n", + fbc->state.plane == plane ? '*' : ' ', + plane->base.base.id, plane->base.name, + plane_state->no_fbc_reason ?: "FBC possible"); + } + + mutex_unlock(&fbc->lock); + intel_runtime_pm_put(&i915->runtime_pm, wakeref); + + drm_modeset_unlock_all(&i915->drm); + + return 0; +} + +DEFINE_SHOW_ATTRIBUTE(intel_fbc_debugfs_status); + +static int intel_fbc_debugfs_false_color_get(void *data, u64 *val) +{ + struct intel_fbc *fbc = data; + + *val = fbc->false_color; + + return 0; +} + +static int intel_fbc_debugfs_false_color_set(void *data, u64 val) +{ + struct intel_fbc *fbc = data; + + mutex_lock(&fbc->lock); + + fbc->false_color = val; + + if (fbc->active) + fbc->funcs->set_false_color(fbc, fbc->false_color); + + mutex_unlock(&fbc->lock); + + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(intel_fbc_debugfs_false_color_fops, + intel_fbc_debugfs_false_color_get, + intel_fbc_debugfs_false_color_set, + "%llu\n"); + +static void intel_fbc_debugfs_add(struct intel_fbc *fbc) +{ + struct drm_i915_private *i915 = fbc->i915; + struct drm_minor *minor = i915->drm.primary; + + debugfs_create_file("i915_fbc_status", 0444, + minor->debugfs_root, fbc, + &intel_fbc_debugfs_status_fops); + + if (fbc->funcs->set_false_color) + debugfs_create_file("i915_fbc_false_color", 0644, + minor->debugfs_root, fbc, + &intel_fbc_debugfs_false_color_fops); +} + +void intel_fbc_debugfs_register(struct drm_i915_private *i915) +{ + struct intel_fbc *fbc = i915->fbc; + + if (fbc) + intel_fbc_debugfs_add(fbc); } diff --git a/drivers/gpu/drm/i915/display/intel_fbc.h b/drivers/gpu/drm/i915/display/intel_fbc.h index b97d908738e6..07ad0411fcc3 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.h +++ b/drivers/gpu/drm/i915/display/intel_fbc.h @@ -8,22 +8,22 @@ #include <linux/types.h> -#include "intel_frontbuffer.h" - +enum fb_op_origin; struct drm_i915_private; struct intel_atomic_state; struct intel_crtc; struct intel_crtc_state; +struct intel_fbc; +struct intel_plane; struct intel_plane_state; -void intel_fbc_choose_crtc(struct drm_i915_private *dev_priv, - struct intel_atomic_state *state); -bool intel_fbc_is_active(struct drm_i915_private *dev_priv); +int intel_fbc_atomic_check(struct intel_atomic_state *state); bool intel_fbc_pre_update(struct intel_atomic_state *state, struct intel_crtc *crtc); void intel_fbc_post_update(struct intel_atomic_state *state, struct intel_crtc *crtc); void intel_fbc_init(struct drm_i915_private *dev_priv); +void intel_fbc_cleanup(struct drm_i915_private *dev_priv); void intel_fbc_update(struct intel_atomic_state *state, struct intel_crtc *crtc); void intel_fbc_disable(struct intel_crtc *crtc); @@ -33,8 +33,9 @@ void intel_fbc_invalidate(struct drm_i915_private *dev_priv, enum fb_op_origin origin); void intel_fbc_flush(struct drm_i915_private *dev_priv, unsigned int frontbuffer_bits, enum fb_op_origin origin); -void intel_fbc_cleanup_cfb(struct drm_i915_private *dev_priv); -void intel_fbc_handle_fifo_underrun_irq(struct drm_i915_private *dev_priv); -int intel_fbc_reset_underrun(struct drm_i915_private *dev_priv); +void intel_fbc_add_plane(struct intel_fbc *fbc, struct intel_plane *plane); +void intel_fbc_handle_fifo_underrun_irq(struct drm_i915_private *i915); +void intel_fbc_reset_underrun(struct drm_i915_private *i915); +void intel_fbc_debugfs_register(struct drm_i915_private *i915); #endif /* __INTEL_FBC_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_fdi.c b/drivers/gpu/drm/i915/display/intel_fdi.c index dd2cf0c59921..3d6e22923601 100644 --- a/drivers/gpu/drm/i915/display/intel_fdi.c +++ b/drivers/gpu/drm/i915/display/intel_fdi.c @@ -4,11 +4,11 @@ */ #include "intel_atomic.h" +#include "intel_crtc.h" #include "intel_ddi.h" #include "intel_de.h" #include "intel_display_types.h" #include "intel_fdi.h" -#include "intel_sbi.h" static void assert_fdi_tx(struct drm_i915_private *dev_priv, enum pipe pipe, bool state) @@ -158,7 +158,7 @@ static int ilk_check_fdi_lanes(struct drm_device *dev, enum pipe pipe, if (pipe_config->fdi_lanes <= 2) return 0; - other_crtc = intel_get_crtc_for_pipe(dev_priv, PIPE_C); + other_crtc = intel_crtc_for_pipe(dev_priv, PIPE_C); other_crtc_state = intel_atomic_get_crtc_state(state, other_crtc); if (IS_ERR(other_crtc_state)) @@ -179,7 +179,7 @@ static int ilk_check_fdi_lanes(struct drm_device *dev, enum pipe pipe, return -EINVAL; } - other_crtc = intel_get_crtc_for_pipe(dev_priv, PIPE_B); + other_crtc = intel_crtc_for_pipe(dev_priv, PIPE_B); other_crtc_state = intel_atomic_get_crtc_state(state, other_crtc); if (IS_ERR(other_crtc_state)) @@ -887,6 +887,43 @@ void hsw_fdi_link_train(struct intel_encoder *encoder, DP_TP_CTL_ENABLE); } +void hsw_fdi_disable(struct intel_encoder *encoder) +{ + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + u32 val; + + /* + * Bspec lists this as both step 13 (before DDI_BUF_CTL disable) + * and step 18 (after clearing PORT_CLK_SEL). Based on a BUN, + * step 13 is the correct place for it. Step 18 is where it was + * originally before the BUN. + */ + val = intel_de_read(dev_priv, FDI_RX_CTL(PIPE_A)); + val &= ~FDI_RX_ENABLE; + intel_de_write(dev_priv, FDI_RX_CTL(PIPE_A), val); + + val = intel_de_read(dev_priv, DDI_BUF_CTL(PORT_E)); + val &= ~DDI_BUF_CTL_ENABLE; + intel_de_write(dev_priv, DDI_BUF_CTL(PORT_E), val); + + intel_wait_ddi_buf_idle(dev_priv, PORT_E); + + intel_ddi_disable_clock(encoder); + + val = intel_de_read(dev_priv, FDI_RX_MISC(PIPE_A)); + val &= ~(FDI_RX_PWRDN_LANE1_MASK | FDI_RX_PWRDN_LANE0_MASK); + val |= FDI_RX_PWRDN_LANE1_VAL(2) | FDI_RX_PWRDN_LANE0_VAL(2); + intel_de_write(dev_priv, FDI_RX_MISC(PIPE_A), val); + + val = intel_de_read(dev_priv, FDI_RX_CTL(PIPE_A)); + val &= ~FDI_PCDCLK; + intel_de_write(dev_priv, FDI_RX_CTL(PIPE_A), val); + + val = intel_de_read(dev_priv, FDI_RX_CTL(PIPE_A)); + val &= ~FDI_RX_PLL_ENABLE; + intel_de_write(dev_priv, FDI_RX_CTL(PIPE_A), val); +} + void ilk_fdi_pll_enable(const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); @@ -1006,104 +1043,6 @@ void ilk_fdi_disable(struct intel_crtc *crtc) udelay(100); } -static void lpt_fdi_reset_mphy(struct drm_i915_private *dev_priv) -{ - u32 tmp; - - tmp = intel_de_read(dev_priv, SOUTH_CHICKEN2); - tmp |= FDI_MPHY_IOSFSB_RESET_CTL; - intel_de_write(dev_priv, SOUTH_CHICKEN2, tmp); - - if (wait_for_us(intel_de_read(dev_priv, SOUTH_CHICKEN2) & - FDI_MPHY_IOSFSB_RESET_STATUS, 100)) - drm_err(&dev_priv->drm, "FDI mPHY reset assert timeout\n"); - - tmp = intel_de_read(dev_priv, SOUTH_CHICKEN2); - tmp &= ~FDI_MPHY_IOSFSB_RESET_CTL; - intel_de_write(dev_priv, SOUTH_CHICKEN2, tmp); - - if (wait_for_us((intel_de_read(dev_priv, SOUTH_CHICKEN2) & - FDI_MPHY_IOSFSB_RESET_STATUS) == 0, 100)) - drm_err(&dev_priv->drm, "FDI mPHY reset de-assert timeout\n"); -} - -/* WaMPhyProgramming:hsw */ -void lpt_fdi_program_mphy(struct drm_i915_private *dev_priv) -{ - u32 tmp; - - lpt_fdi_reset_mphy(dev_priv); - - tmp = intel_sbi_read(dev_priv, 0x8008, SBI_MPHY); - tmp &= ~(0xFF << 24); - tmp |= (0x12 << 24); - intel_sbi_write(dev_priv, 0x8008, tmp, SBI_MPHY); - - tmp = intel_sbi_read(dev_priv, 0x2008, SBI_MPHY); - tmp |= (1 << 11); - intel_sbi_write(dev_priv, 0x2008, tmp, SBI_MPHY); - - tmp = intel_sbi_read(dev_priv, 0x2108, SBI_MPHY); - tmp |= (1 << 11); - intel_sbi_write(dev_priv, 0x2108, tmp, SBI_MPHY); - - tmp = intel_sbi_read(dev_priv, 0x206C, SBI_MPHY); - tmp |= (1 << 24) | (1 << 21) | (1 << 18); - intel_sbi_write(dev_priv, 0x206C, tmp, SBI_MPHY); - - tmp = intel_sbi_read(dev_priv, 0x216C, SBI_MPHY); - tmp |= (1 << 24) | (1 << 21) | (1 << 18); - intel_sbi_write(dev_priv, 0x216C, tmp, SBI_MPHY); - - tmp = intel_sbi_read(dev_priv, 0x2080, SBI_MPHY); - tmp &= ~(7 << 13); - tmp |= (5 << 13); - intel_sbi_write(dev_priv, 0x2080, tmp, SBI_MPHY); - - tmp = intel_sbi_read(dev_priv, 0x2180, SBI_MPHY); - tmp &= ~(7 << 13); - tmp |= (5 << 13); - intel_sbi_write(dev_priv, 0x2180, tmp, SBI_MPHY); - - tmp = intel_sbi_read(dev_priv, 0x208C, SBI_MPHY); - tmp &= ~0xFF; - tmp |= 0x1C; - intel_sbi_write(dev_priv, 0x208C, tmp, SBI_MPHY); - - tmp = intel_sbi_read(dev_priv, 0x218C, SBI_MPHY); - tmp &= ~0xFF; - tmp |= 0x1C; - intel_sbi_write(dev_priv, 0x218C, tmp, SBI_MPHY); - - tmp = intel_sbi_read(dev_priv, 0x2098, SBI_MPHY); - tmp &= ~(0xFF << 16); - tmp |= (0x1C << 16); - intel_sbi_write(dev_priv, 0x2098, tmp, SBI_MPHY); - - tmp = intel_sbi_read(dev_priv, 0x2198, SBI_MPHY); - tmp &= ~(0xFF << 16); - tmp |= (0x1C << 16); - intel_sbi_write(dev_priv, 0x2198, tmp, SBI_MPHY); - - tmp = intel_sbi_read(dev_priv, 0x20C4, SBI_MPHY); - tmp |= (1 << 27); - intel_sbi_write(dev_priv, 0x20C4, tmp, SBI_MPHY); - - tmp = intel_sbi_read(dev_priv, 0x21C4, SBI_MPHY); - tmp |= (1 << 27); - intel_sbi_write(dev_priv, 0x21C4, tmp, SBI_MPHY); - - tmp = intel_sbi_read(dev_priv, 0x20EC, SBI_MPHY); - tmp &= ~(0xF << 28); - tmp |= (4 << 28); - intel_sbi_write(dev_priv, 0x20EC, tmp, SBI_MPHY); - - tmp = intel_sbi_read(dev_priv, 0x21EC, SBI_MPHY); - tmp &= ~(0xF << 28); - tmp |= (4 << 28); - intel_sbi_write(dev_priv, 0x21EC, tmp, SBI_MPHY); -} - static const struct intel_fdi_funcs ilk_funcs = { .fdi_link_train = ilk_fdi_link_train, }; diff --git a/drivers/gpu/drm/i915/display/intel_fdi.h b/drivers/gpu/drm/i915/display/intel_fdi.h index 640d6585c137..1cdb86172702 100644 --- a/drivers/gpu/drm/i915/display/intel_fdi.h +++ b/drivers/gpu/drm/i915/display/intel_fdi.h @@ -23,8 +23,8 @@ void ilk_fdi_pll_enable(const struct intel_crtc_state *crtc_state); void intel_fdi_init_hook(struct drm_i915_private *dev_priv); void hsw_fdi_link_train(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state); +void hsw_fdi_disable(struct intel_encoder *encoder); void intel_fdi_pll_freq_update(struct drm_i915_private *i915); -void lpt_fdi_program_mphy(struct drm_i915_private *i915); void intel_fdi_link_train(struct intel_crtc *crtc, const struct intel_crtc_state *crtc_state); diff --git a/drivers/gpu/drm/i915/display/intel_fifo_underrun.c b/drivers/gpu/drm/i915/display/intel_fifo_underrun.c index eb841960840d..d636d21fa9ce 100644 --- a/drivers/gpu/drm/i915/display/intel_fifo_underrun.c +++ b/drivers/gpu/drm/i915/display/intel_fifo_underrun.c @@ -26,8 +26,8 @@ */ #include "i915_drv.h" -#include "i915_trace.h" #include "intel_de.h" +#include "intel_display_trace.h" #include "intel_display_types.h" #include "intel_fbc.h" #include "intel_fifo_underrun.h" @@ -61,7 +61,7 @@ static bool ivb_can_enable_err_int(struct drm_device *dev) lockdep_assert_held(&dev_priv->irq_lock); for_each_pipe(dev_priv, pipe) { - crtc = intel_get_crtc_for_pipe(dev_priv, pipe); + crtc = intel_crtc_for_pipe(dev_priv, pipe); if (crtc->cpu_fifo_underrun_disabled) return false; @@ -79,7 +79,7 @@ static bool cpt_can_enable_serr_int(struct drm_device *dev) lockdep_assert_held(&dev_priv->irq_lock); for_each_pipe(dev_priv, pipe) { - crtc = intel_get_crtc_for_pipe(dev_priv, pipe); + crtc = intel_crtc_for_pipe(dev_priv, pipe); if (crtc->pch_fifo_underrun_disabled) return false; @@ -279,7 +279,7 @@ static bool __intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev, enum pipe pipe, bool enable) { struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe); + struct intel_crtc *crtc = intel_crtc_for_pipe(dev_priv, pipe); bool old; lockdep_assert_held(&dev_priv->irq_lock); @@ -348,7 +348,7 @@ bool intel_set_pch_fifo_underrun_reporting(struct drm_i915_private *dev_priv, bool enable) { struct intel_crtc *crtc = - intel_get_crtc_for_pipe(dev_priv, pch_transcoder); + intel_crtc_for_pipe(dev_priv, pch_transcoder); unsigned long flags; bool old; @@ -391,7 +391,7 @@ bool intel_set_pch_fifo_underrun_reporting(struct drm_i915_private *dev_priv, void intel_cpu_fifo_underrun_irq_handler(struct drm_i915_private *dev_priv, enum pipe pipe) { - struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe); + struct intel_crtc *crtc = intel_crtc_for_pipe(dev_priv, pipe); u32 underruns = 0; /* We may be called too early in init, thanks BIOS! */ diff --git a/drivers/gpu/drm/i915/display/intel_frontbuffer.c b/drivers/gpu/drm/i915/display/intel_frontbuffer.c index 0492446cd04a..791248f812aa 100644 --- a/drivers/gpu/drm/i915/display/intel_frontbuffer.c +++ b/drivers/gpu/drm/i915/display/intel_frontbuffer.c @@ -55,14 +55,13 @@ * cancelled as soon as busyness is detected. */ -#include "display/intel_dp.h" - #include "i915_drv.h" -#include "i915_trace.h" +#include "intel_display_trace.h" #include "intel_display_types.h" +#include "intel_dp.h" +#include "intel_drrs.h" #include "intel_fbc.h" #include "intel_frontbuffer.h" -#include "intel_drrs.h" #include "intel_psr.h" /** diff --git a/drivers/gpu/drm/i915/display/intel_frontbuffer.h b/drivers/gpu/drm/i915/display/intel_frontbuffer.h index a88441edc8f9..ff0c37b079aa 100644 --- a/drivers/gpu/drm/i915/display/intel_frontbuffer.h +++ b/drivers/gpu/drm/i915/display/intel_frontbuffer.h @@ -28,7 +28,7 @@ #include <linux/kref.h> #include "gem/i915_gem_object_types.h" -#include "i915_active.h" +#include "i915_active_types.h" struct drm_i915_private; diff --git a/drivers/gpu/drm/i915/display/intel_gmbus.c b/drivers/gpu/drm/i915/display/intel_gmbus.c index ceb1bf8a8c3c..3b8b84177085 100644 --- a/drivers/gpu/drm/i915/display/intel_gmbus.c +++ b/drivers/gpu/drm/i915/display/intel_gmbus.c @@ -334,6 +334,15 @@ intel_gpio_setup(struct intel_gmbus *bus, unsigned int pin) algo->data = bus; } +static bool has_gmbus_irq(struct drm_i915_private *i915) +{ + /* + * encoder->shutdown() may want to use GMBUS + * after irqs have already been disabled. + */ + return HAS_GMBUS_IRQ(i915) && intel_irqs_enabled(i915); +} + static int gmbus_wait(struct drm_i915_private *dev_priv, u32 status, u32 irq_en) { DEFINE_WAIT(wait); @@ -344,7 +353,7 @@ static int gmbus_wait(struct drm_i915_private *dev_priv, u32 status, u32 irq_en) * we also need to check for NAKs besides the hw ready/idle signal, we * need to wake up periodically and check that ourselves. */ - if (!HAS_GMBUS_IRQ(dev_priv)) + if (!has_gmbus_irq(dev_priv)) irq_en = 0; add_wait_queue(&dev_priv->gmbus_wait_queue, &wait); @@ -375,7 +384,7 @@ gmbus_wait_idle(struct drm_i915_private *dev_priv) /* Important: The hw handles only the first bit, so set only one! */ irq_enable = 0; - if (HAS_GMBUS_IRQ(dev_priv)) + if (has_gmbus_irq(dev_priv)) irq_enable = GMBUS_IDLE_EN; add_wait_queue(&dev_priv->gmbus_wait_queue, &wait); diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c index 371736bdc01f..3b5b9e7b05b7 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.c +++ b/drivers/gpu/drm/i915/display/intel_hdmi.c @@ -1800,6 +1800,11 @@ static bool intel_has_hdmi_sink(struct intel_hdmi *hdmi, READ_ONCE(to_intel_digital_connector_state(conn_state)->force_audio) != HDMI_AUDIO_OFF_DVI; } +static bool intel_hdmi_is_ycbcr420(const struct intel_crtc_state *crtc_state) +{ + return crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR420; +} + static int hdmi_port_clock_limit(struct intel_hdmi *hdmi, bool respect_downstream_limits, bool has_hdmi_sink) @@ -1864,8 +1869,12 @@ hdmi_port_clock_valid(struct intel_hdmi *hdmi, return MODE_OK; } -static int intel_hdmi_port_clock(int clock, int bpc) +static int intel_hdmi_tmds_clock(int clock, int bpc, bool ycbcr420_output) { + /* YCBCR420 TMDS rate requirement is half the pixel clock */ + if (ycbcr420_output) + clock /= 2; + /* * Need to adjust the port link by: * 1.5x for 12bpc @@ -1874,18 +1883,29 @@ static int intel_hdmi_port_clock(int clock, int bpc) return clock * bpc / 8; } -static bool intel_hdmi_bpc_possible(struct drm_connector *connector, - int bpc, bool has_hdmi_sink, bool ycbcr420_output) +static bool intel_hdmi_source_bpc_possible(struct drm_i915_private *i915, int bpc) +{ + switch (bpc) { + case 12: + return !HAS_GMCH(i915); + case 10: + return DISPLAY_VER(i915) >= 11; + case 8: + return true; + default: + MISSING_CASE(bpc); + return false; + } +} + +static bool intel_hdmi_sink_bpc_possible(struct drm_connector *connector, + int bpc, bool has_hdmi_sink, bool ycbcr420_output) { - struct drm_i915_private *i915 = to_i915(connector->dev); const struct drm_display_info *info = &connector->display_info; const struct drm_hdmi_info *hdmi = &info->hdmi; switch (bpc) { case 12: - if (HAS_GMCH(i915)) - return false; - if (!has_hdmi_sink) return false; @@ -1894,9 +1914,6 @@ static bool intel_hdmi_bpc_possible(struct drm_connector *connector, else return info->edid_hdmi_dc_modes & DRM_EDID_HDMI_DC_36; case 10: - if (DISPLAY_VER(i915) < 11) - return false; - if (!has_hdmi_sink) return false; @@ -1916,26 +1933,26 @@ static enum drm_mode_status intel_hdmi_mode_clock_valid(struct drm_connector *connector, int clock, bool has_hdmi_sink, bool ycbcr420_output) { + struct drm_i915_private *i915 = to_i915(connector->dev); struct intel_hdmi *hdmi = intel_attached_hdmi(to_intel_connector(connector)); enum drm_mode_status status; - if (ycbcr420_output) - clock /= 2; - /* check if we can do 8bpc */ - status = hdmi_port_clock_valid(hdmi, intel_hdmi_port_clock(clock, 8), + status = hdmi_port_clock_valid(hdmi, intel_hdmi_tmds_clock(clock, 8, ycbcr420_output), true, has_hdmi_sink); /* if we can't do 8bpc we may still be able to do 12bpc */ if (status != MODE_OK && - intel_hdmi_bpc_possible(connector, 12, has_hdmi_sink, ycbcr420_output)) - status = hdmi_port_clock_valid(hdmi, intel_hdmi_port_clock(clock, 12), + intel_hdmi_source_bpc_possible(i915, 12) && + intel_hdmi_sink_bpc_possible(connector, 12, has_hdmi_sink, ycbcr420_output)) + status = hdmi_port_clock_valid(hdmi, intel_hdmi_tmds_clock(clock, 12, ycbcr420_output), true, has_hdmi_sink); /* if we can't do 8,12bpc we may still be able to do 10bpc */ if (status != MODE_OK && - intel_hdmi_bpc_possible(connector, 10, has_hdmi_sink, ycbcr420_output)) - status = hdmi_port_clock_valid(hdmi, intel_hdmi_port_clock(clock, 10), + intel_hdmi_source_bpc_possible(i915, 10) && + intel_hdmi_sink_bpc_possible(connector, 10, has_hdmi_sink, ycbcr420_output)) + status = hdmi_port_clock_valid(hdmi, intel_hdmi_tmds_clock(clock, 10, ycbcr420_output), true, has_hdmi_sink); return status; @@ -2000,7 +2017,7 @@ bool intel_hdmi_deep_color_possible(const struct intel_crtc_state *crtc_state, if (connector_state->crtc != crtc_state->uapi.crtc) continue; - if (!intel_hdmi_bpc_possible(connector, bpc, has_hdmi_sink, ycbcr420_output)) + if (!intel_hdmi_sink_bpc_possible(connector, bpc, has_hdmi_sink, ycbcr420_output)) return false; } @@ -2015,6 +2032,9 @@ static bool hdmi_deep_color_possible(const struct intel_crtc_state *crtc_state, const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode; + 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. @@ -2023,7 +2043,7 @@ static bool hdmi_deep_color_possible(const struct intel_crtc_state *crtc_state, return false; /* Display Wa_1405510057:icl,ehl */ - if (crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR420 && + if (intel_hdmi_is_ycbcr420(crtc_state) && bpc == 10 && DISPLAY_VER(dev_priv) == 11 && (adjusted_mode->crtc_hblank_end - adjusted_mode->crtc_hblank_start) % 8 == 2) @@ -2031,8 +2051,7 @@ static bool hdmi_deep_color_possible(const struct intel_crtc_state *crtc_state, return intel_hdmi_deep_color_possible(crtc_state, bpc, crtc_state->has_hdmi_sink, - crtc_state->output_format == - INTEL_OUTPUT_FORMAT_YCBCR420); + intel_hdmi_is_ycbcr420(crtc_state)); } static int intel_hdmi_compute_bpc(struct intel_encoder *encoder, @@ -2040,12 +2059,13 @@ static int intel_hdmi_compute_bpc(struct intel_encoder *encoder, int clock) { struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder); + bool ycbcr420_output = intel_hdmi_is_ycbcr420(crtc_state); int bpc; for (bpc = 12; bpc >= 10; bpc -= 2) { if (hdmi_deep_color_possible(crtc_state, bpc) && hdmi_port_clock_valid(intel_hdmi, - intel_hdmi_port_clock(clock, bpc), + intel_hdmi_tmds_clock(clock, bpc, ycbcr420_output), true, crtc_state->has_hdmi_sink) == MODE_OK) return bpc; } @@ -2065,13 +2085,10 @@ static int intel_hdmi_compute_clock(struct intel_encoder *encoder, if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK) clock *= 2; - /* YCBCR420 TMDS rate requirement is half the pixel clock */ - if (crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR420) - clock /= 2; - bpc = intel_hdmi_compute_bpc(encoder, crtc_state, clock); - crtc_state->port_clock = intel_hdmi_port_clock(clock, bpc); + crtc_state->port_clock = intel_hdmi_tmds_clock(clock, bpc, + intel_hdmi_is_ycbcr420(crtc_state)); /* * pipe_bpp could already be below 8bpc due to @@ -2141,34 +2158,44 @@ static bool intel_hdmi_has_audio(struct intel_encoder *encoder, return intel_conn_state->force_audio == HDMI_AUDIO_ON; } +static enum intel_output_format +intel_hdmi_output_format(struct intel_connector *connector, + bool ycbcr_420_output) +{ + if (connector->base.ycbcr_420_allowed && ycbcr_420_output) + return INTEL_OUTPUT_FORMAT_YCBCR420; + else + return INTEL_OUTPUT_FORMAT_RGB; +} + static int intel_hdmi_compute_output_format(struct intel_encoder *encoder, struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { - struct drm_connector *connector = conn_state->connector; - struct drm_i915_private *i915 = to_i915(connector->dev); + struct intel_connector *connector = to_intel_connector(conn_state->connector); const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode; + const struct drm_display_info *info = &connector->base.display_info; + struct drm_i915_private *i915 = to_i915(connector->base.dev); + bool ycbcr_420_only = drm_mode_is_420_only(info, adjusted_mode); int ret; - bool ycbcr_420_only; - ycbcr_420_only = drm_mode_is_420_only(&connector->display_info, adjusted_mode); - if (connector->ycbcr_420_allowed && ycbcr_420_only) { - crtc_state->output_format = INTEL_OUTPUT_FORMAT_YCBCR420; - } else { - if (!connector->ycbcr_420_allowed && ycbcr_420_only) - drm_dbg_kms(&i915->drm, - "YCbCr 4:2:0 mode but YCbCr 4:2:0 output not possible. Falling back to RGB.\n"); + crtc_state->output_format = intel_hdmi_output_format(connector, ycbcr_420_only); + + if (ycbcr_420_only && !intel_hdmi_is_ycbcr420(crtc_state)) { + drm_dbg_kms(&i915->drm, + "YCbCr 4:2:0 mode but YCbCr 4:2:0 output not possible. Falling back to RGB.\n"); crtc_state->output_format = INTEL_OUTPUT_FORMAT_RGB; } ret = intel_hdmi_compute_clock(encoder, crtc_state); if (ret) { - if (crtc_state->output_format != INTEL_OUTPUT_FORMAT_YCBCR420 && - connector->ycbcr_420_allowed && - drm_mode_is_420_also(&connector->display_info, adjusted_mode)) { - crtc_state->output_format = INTEL_OUTPUT_FORMAT_YCBCR420; - ret = intel_hdmi_compute_clock(encoder, crtc_state); - } + if (intel_hdmi_is_ycbcr420(crtc_state) || + !connector->base.ycbcr_420_allowed || + !drm_mode_is_420_also(info, adjusted_mode)) + return ret; + + crtc_state->output_format = intel_hdmi_output_format(connector, true); + ret = intel_hdmi_compute_clock(encoder, crtc_state); } return ret; @@ -2208,7 +2235,7 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder, if (ret) return ret; - if (pipe_config->output_format == INTEL_OUTPUT_FORMAT_YCBCR420) { + if (intel_hdmi_is_ycbcr420(pipe_config)) { ret = intel_panel_fitting(pipe_config, conn_state); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/display/intel_lpe_audio.c b/drivers/gpu/drm/i915/display/intel_lpe_audio.c index 7f3c638c8950..4970bf146c4a 100644 --- a/drivers/gpu/drm/i915/display/intel_lpe_audio.c +++ b/drivers/gpu/drm/i915/display/intel_lpe_audio.c @@ -74,7 +74,7 @@ #include "intel_de.h" #include "intel_lpe_audio.h" -#define HAS_LPE_AUDIO(dev_priv) ((dev_priv)->lpe_audio.platdev != NULL) +#define HAS_LPE_AUDIO(dev_priv) ((dev_priv)->audio.lpe.platdev != NULL) static struct platform_device * lpe_audio_platdev_create(struct drm_i915_private *dev_priv) @@ -96,7 +96,7 @@ lpe_audio_platdev_create(struct drm_i915_private *dev_priv) return ERR_PTR(-ENOMEM); } - rsc[0].start = rsc[0].end = dev_priv->lpe_audio.irq; + rsc[0].start = rsc[0].end = dev_priv->audio.lpe.irq; rsc[0].flags = IORESOURCE_IRQ; rsc[0].name = "hdmi-lpe-audio-irq"; @@ -148,7 +148,7 @@ static void lpe_audio_platdev_destroy(struct drm_i915_private *dev_priv) * than us fiddle with its internals. */ - platform_device_unregister(dev_priv->lpe_audio.platdev); + platform_device_unregister(dev_priv->audio.lpe.platdev); } static void lpe_audio_irq_unmask(struct irq_data *d) @@ -167,7 +167,7 @@ static struct irq_chip lpe_audio_irqchip = { static int lpe_audio_irq_init(struct drm_i915_private *dev_priv) { - int irq = dev_priv->lpe_audio.irq; + int irq = dev_priv->audio.lpe.irq; drm_WARN_ON(&dev_priv->drm, !intel_irqs_enabled(dev_priv)); irq_set_chip_and_handler_name(irq, @@ -204,15 +204,15 @@ static int lpe_audio_setup(struct drm_i915_private *dev_priv) { int ret; - dev_priv->lpe_audio.irq = irq_alloc_desc(0); - if (dev_priv->lpe_audio.irq < 0) { + dev_priv->audio.lpe.irq = irq_alloc_desc(0); + if (dev_priv->audio.lpe.irq < 0) { drm_err(&dev_priv->drm, "Failed to allocate IRQ desc: %d\n", - dev_priv->lpe_audio.irq); - ret = dev_priv->lpe_audio.irq; + dev_priv->audio.lpe.irq); + ret = dev_priv->audio.lpe.irq; goto err; } - drm_dbg(&dev_priv->drm, "irq = %d\n", dev_priv->lpe_audio.irq); + drm_dbg(&dev_priv->drm, "irq = %d\n", dev_priv->audio.lpe.irq); ret = lpe_audio_irq_init(dev_priv); @@ -223,10 +223,10 @@ static int lpe_audio_setup(struct drm_i915_private *dev_priv) goto err_free_irq; } - dev_priv->lpe_audio.platdev = lpe_audio_platdev_create(dev_priv); + dev_priv->audio.lpe.platdev = lpe_audio_platdev_create(dev_priv); - if (IS_ERR(dev_priv->lpe_audio.platdev)) { - ret = PTR_ERR(dev_priv->lpe_audio.platdev); + if (IS_ERR(dev_priv->audio.lpe.platdev)) { + ret = PTR_ERR(dev_priv->audio.lpe.platdev); drm_err(&dev_priv->drm, "Failed to create lpe audio platform device: %d\n", ret); @@ -241,10 +241,10 @@ static int lpe_audio_setup(struct drm_i915_private *dev_priv) return 0; err_free_irq: - irq_free_desc(dev_priv->lpe_audio.irq); + irq_free_desc(dev_priv->audio.lpe.irq); err: - dev_priv->lpe_audio.irq = -1; - dev_priv->lpe_audio.platdev = NULL; + dev_priv->audio.lpe.irq = -1; + dev_priv->audio.lpe.platdev = NULL; return ret; } @@ -262,7 +262,7 @@ void intel_lpe_audio_irq_handler(struct drm_i915_private *dev_priv) if (!HAS_LPE_AUDIO(dev_priv)) return; - ret = generic_handle_irq(dev_priv->lpe_audio.irq); + ret = generic_handle_irq(dev_priv->audio.lpe.irq); if (ret) drm_err_ratelimited(&dev_priv->drm, "error handling LPE audio irq: %d\n", ret); @@ -303,10 +303,10 @@ void intel_lpe_audio_teardown(struct drm_i915_private *dev_priv) lpe_audio_platdev_destroy(dev_priv); - irq_free_desc(dev_priv->lpe_audio.irq); + irq_free_desc(dev_priv->audio.lpe.irq); - dev_priv->lpe_audio.irq = -1; - dev_priv->lpe_audio.platdev = NULL; + dev_priv->audio.lpe.irq = -1; + dev_priv->audio.lpe.platdev = NULL; } /** @@ -333,7 +333,7 @@ void intel_lpe_audio_notify(struct drm_i915_private *dev_priv, if (!HAS_LPE_AUDIO(dev_priv)) return; - pdata = dev_get_platdata(&dev_priv->lpe_audio.platdev->dev); + pdata = dev_get_platdata(&dev_priv->audio.lpe.platdev->dev); ppdata = &pdata->port[port - PORT_B]; spin_lock_irqsave(&pdata->lpe_audio_slock, irqflags); @@ -361,7 +361,7 @@ void intel_lpe_audio_notify(struct drm_i915_private *dev_priv, } if (pdata->notify_audio_lpe) - pdata->notify_audio_lpe(dev_priv->lpe_audio.platdev, port - PORT_B); + pdata->notify_audio_lpe(dev_priv->audio.lpe.platdev, port - PORT_B); spin_unlock_irqrestore(&pdata->lpe_audio_slock, irqflags); } diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c index 7e3f5c6ca484..1a376e9a1ff3 100644 --- a/drivers/gpu/drm/i915/display/intel_overlay.c +++ b/drivers/gpu/drm/i915/display/intel_overlay.c @@ -1382,7 +1382,7 @@ void intel_overlay_setup(struct drm_i915_private *dev_priv) if (!HAS_OVERLAY(dev_priv)) return; - engine = dev_priv->gt.engine[RCS0]; + engine = to_gt(dev_priv)->engine[RCS0]; if (!engine || !engine->kernel_context) return; diff --git a/drivers/gpu/drm/i915/display/intel_pch_display.c b/drivers/gpu/drm/i915/display/intel_pch_display.c new file mode 100644 index 000000000000..a55c4bfacd0d --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_pch_display.c @@ -0,0 +1,501 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2021 Intel Corporation + */ + +#include "g4x_dp.h" +#include "intel_crt.h" +#include "intel_de.h" +#include "intel_display_types.h" +#include "intel_fdi.h" +#include "intel_lvds.h" +#include "intel_pch_display.h" +#include "intel_pch_refclk.h" +#include "intel_pps.h" +#include "intel_sdvo.h" + +static void assert_pch_dp_disabled(struct drm_i915_private *dev_priv, + enum pipe pipe, enum port port, + i915_reg_t dp_reg) +{ + enum pipe port_pipe; + bool state; + + state = g4x_dp_port_enabled(dev_priv, dp_reg, port, &port_pipe); + + I915_STATE_WARN(state && port_pipe == pipe, + "PCH DP %c enabled on transcoder %c, should be disabled\n", + port_name(port), pipe_name(pipe)); + + I915_STATE_WARN(HAS_PCH_IBX(dev_priv) && !state && port_pipe == PIPE_B, + "IBX PCH DP %c still using transcoder B\n", + port_name(port)); +} + +static void assert_pch_hdmi_disabled(struct drm_i915_private *dev_priv, + enum pipe pipe, enum port port, + i915_reg_t hdmi_reg) +{ + enum pipe port_pipe; + bool state; + + state = intel_sdvo_port_enabled(dev_priv, hdmi_reg, &port_pipe); + + I915_STATE_WARN(state && port_pipe == pipe, + "PCH HDMI %c enabled on transcoder %c, should be disabled\n", + port_name(port), pipe_name(pipe)); + + I915_STATE_WARN(HAS_PCH_IBX(dev_priv) && !state && port_pipe == PIPE_B, + "IBX PCH HDMI %c still using transcoder B\n", + port_name(port)); +} + +static void assert_pch_ports_disabled(struct drm_i915_private *dev_priv, + enum pipe pipe) +{ + enum pipe port_pipe; + + assert_pch_dp_disabled(dev_priv, pipe, PORT_B, PCH_DP_B); + assert_pch_dp_disabled(dev_priv, pipe, PORT_C, PCH_DP_C); + assert_pch_dp_disabled(dev_priv, pipe, PORT_D, PCH_DP_D); + + I915_STATE_WARN(intel_crt_port_enabled(dev_priv, PCH_ADPA, &port_pipe) && + port_pipe == pipe, + "PCH VGA enabled on transcoder %c, should be disabled\n", + pipe_name(pipe)); + + I915_STATE_WARN(intel_lvds_port_enabled(dev_priv, PCH_LVDS, &port_pipe) && + port_pipe == pipe, + "PCH LVDS enabled on transcoder %c, should be disabled\n", + pipe_name(pipe)); + + /* PCH SDVOB multiplex with HDMIB */ + assert_pch_hdmi_disabled(dev_priv, pipe, PORT_B, PCH_HDMIB); + assert_pch_hdmi_disabled(dev_priv, pipe, PORT_C, PCH_HDMIC); + assert_pch_hdmi_disabled(dev_priv, pipe, PORT_D, PCH_HDMID); +} + +static void assert_pch_transcoder_disabled(struct drm_i915_private *dev_priv, + enum pipe pipe) +{ + u32 val; + bool enabled; + + val = intel_de_read(dev_priv, PCH_TRANSCONF(pipe)); + enabled = !!(val & TRANS_ENABLE); + I915_STATE_WARN(enabled, + "transcoder assertion failed, should be off on pipe %c but is still active\n", + pipe_name(pipe)); +} + +static void ilk_pch_transcoder_set_timings(const struct intel_crtc_state *crtc_state, + enum pipe pch_transcoder) +{ + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; + + intel_de_write(dev_priv, PCH_TRANS_HTOTAL(pch_transcoder), + intel_de_read(dev_priv, HTOTAL(cpu_transcoder))); + intel_de_write(dev_priv, PCH_TRANS_HBLANK(pch_transcoder), + intel_de_read(dev_priv, HBLANK(cpu_transcoder))); + intel_de_write(dev_priv, PCH_TRANS_HSYNC(pch_transcoder), + intel_de_read(dev_priv, HSYNC(cpu_transcoder))); + + intel_de_write(dev_priv, PCH_TRANS_VTOTAL(pch_transcoder), + intel_de_read(dev_priv, VTOTAL(cpu_transcoder))); + intel_de_write(dev_priv, PCH_TRANS_VBLANK(pch_transcoder), + intel_de_read(dev_priv, VBLANK(cpu_transcoder))); + intel_de_write(dev_priv, PCH_TRANS_VSYNC(pch_transcoder), + intel_de_read(dev_priv, VSYNC(cpu_transcoder))); + intel_de_write(dev_priv, PCH_TRANS_VSYNCSHIFT(pch_transcoder), + intel_de_read(dev_priv, VSYNCSHIFT(cpu_transcoder))); +} + +static void ilk_enable_pch_transcoder(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; + i915_reg_t reg; + u32 val, pipeconf_val; + + /* Make sure PCH DPLL is enabled */ + assert_shared_dpll_enabled(dev_priv, crtc_state->shared_dpll); + + /* FDI must be feeding us bits for PCH ports */ + assert_fdi_tx_enabled(dev_priv, pipe); + assert_fdi_rx_enabled(dev_priv, pipe); + + if (HAS_PCH_CPT(dev_priv)) { + reg = TRANS_CHICKEN2(pipe); + val = intel_de_read(dev_priv, reg); + /* + * Workaround: Set the timing override bit + * before enabling the pch transcoder. + */ + val |= TRANS_CHICKEN2_TIMING_OVERRIDE; + /* Configure frame start delay to match the CPU */ + val &= ~TRANS_CHICKEN2_FRAME_START_DELAY_MASK; + val |= TRANS_CHICKEN2_FRAME_START_DELAY(dev_priv->framestart_delay - 1); + intel_de_write(dev_priv, reg, val); + } + + reg = PCH_TRANSCONF(pipe); + val = intel_de_read(dev_priv, reg); + pipeconf_val = intel_de_read(dev_priv, PIPECONF(pipe)); + + if (HAS_PCH_IBX(dev_priv)) { + /* Configure frame start delay to match the CPU */ + val &= ~TRANS_FRAME_START_DELAY_MASK; + val |= TRANS_FRAME_START_DELAY(dev_priv->framestart_delay - 1); + + /* + * Make the BPC in transcoder be consistent with + * that in pipeconf reg. For HDMI we must use 8bpc + * here for both 8bpc and 12bpc. + */ + val &= ~PIPECONF_BPC_MASK; + if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) + val |= PIPECONF_8BPC; + else + val |= pipeconf_val & PIPECONF_BPC_MASK; + } + + val &= ~TRANS_INTERLACE_MASK; + if ((pipeconf_val & PIPECONF_INTERLACE_MASK) == PIPECONF_INTERLACED_ILK) { + if (HAS_PCH_IBX(dev_priv) && + intel_crtc_has_type(crtc_state, INTEL_OUTPUT_SDVO)) + val |= TRANS_LEGACY_INTERLACED_ILK; + else + val |= TRANS_INTERLACED; + } else { + val |= TRANS_PROGRESSIVE; + } + + intel_de_write(dev_priv, reg, val | TRANS_ENABLE); + if (intel_de_wait_for_set(dev_priv, reg, TRANS_STATE_ENABLE, 100)) + drm_err(&dev_priv->drm, "failed to enable transcoder %c\n", + pipe_name(pipe)); +} + +static void ilk_disable_pch_transcoder(struct intel_crtc *crtc) +{ + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + enum pipe pipe = crtc->pipe; + i915_reg_t reg; + u32 val; + + /* FDI relies on the transcoder */ + assert_fdi_tx_disabled(dev_priv, pipe); + assert_fdi_rx_disabled(dev_priv, pipe); + + /* Ports must be off as well */ + assert_pch_ports_disabled(dev_priv, pipe); + + reg = PCH_TRANSCONF(pipe); + val = intel_de_read(dev_priv, reg); + val &= ~TRANS_ENABLE; + intel_de_write(dev_priv, reg, val); + /* wait for PCH transcoder off, transcoder state */ + if (intel_de_wait_for_clear(dev_priv, reg, TRANS_STATE_ENABLE, 50)) + drm_err(&dev_priv->drm, "failed to disable transcoder %c\n", + pipe_name(pipe)); + + if (HAS_PCH_CPT(dev_priv)) { + /* Workaround: Clear the timing override chicken bit again. */ + reg = TRANS_CHICKEN2(pipe); + val = intel_de_read(dev_priv, reg); + val &= ~TRANS_CHICKEN2_TIMING_OVERRIDE; + intel_de_write(dev_priv, reg, val); + } +} + +/* + * Enable PCH resources required for PCH ports: + * - PCH PLLs + * - FDI training & RX/TX + * - update transcoder timings + * - DP transcoding bits + * - transcoder + */ +void ilk_pch_enable(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + const struct intel_crtc_state *crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); + enum pipe pipe = crtc->pipe; + u32 temp; + + assert_pch_transcoder_disabled(dev_priv, pipe); + + /* For PCH output, training FDI link */ + intel_fdi_link_train(crtc, crtc_state); + + /* + * We need to program the right clock selection + * before writing the pixel multiplier into the DPLL. + */ + if (HAS_PCH_CPT(dev_priv)) { + u32 sel; + + temp = intel_de_read(dev_priv, PCH_DPLL_SEL); + temp |= TRANS_DPLL_ENABLE(pipe); + sel = TRANS_DPLLB_SEL(pipe); + if (crtc_state->shared_dpll == + intel_get_shared_dpll_by_id(dev_priv, DPLL_ID_PCH_PLL_B)) + temp |= sel; + else + temp &= ~sel; + intel_de_write(dev_priv, PCH_DPLL_SEL, temp); + } + + /* + * XXX: pch pll's can be enabled any time before we enable the PCH + * transcoder, and we actually should do this to not upset any PCH + * transcoder that already use the clock when we share it. + * + * Note that enable_shared_dpll tries to do the right thing, but + * get_shared_dpll unconditionally resets the pll - we need that + * to have the right LVDS enable sequence. + */ + intel_enable_shared_dpll(crtc_state); + + /* set transcoder timing, panel must allow it */ + assert_pps_unlocked(dev_priv, pipe); + ilk_pch_transcoder_set_timings(crtc_state, pipe); + + intel_fdi_normal_train(crtc); + + /* For PCH DP, enable TRANS_DP_CTL */ + if (HAS_PCH_CPT(dev_priv) && + intel_crtc_has_dp_encoder(crtc_state)) { + const struct drm_display_mode *adjusted_mode = + &crtc_state->hw.adjusted_mode; + u32 bpc = (intel_de_read(dev_priv, PIPECONF(pipe)) & PIPECONF_BPC_MASK) >> 5; + i915_reg_t reg = TRANS_DP_CTL(pipe); + enum port port; + + temp = intel_de_read(dev_priv, reg); + temp &= ~(TRANS_DP_PORT_SEL_MASK | + TRANS_DP_SYNC_MASK | + TRANS_DP_BPC_MASK); + temp |= TRANS_DP_OUTPUT_ENABLE; + temp |= bpc << 9; /* same format but at 11:9 */ + + if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC) + temp |= TRANS_DP_HSYNC_ACTIVE_HIGH; + if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC) + temp |= TRANS_DP_VSYNC_ACTIVE_HIGH; + + port = intel_get_crtc_new_encoder(state, crtc_state)->port; + drm_WARN_ON(&dev_priv->drm, port < PORT_B || port > PORT_D); + temp |= TRANS_DP_PORT_SEL(port); + + intel_de_write(dev_priv, reg, temp); + } + + ilk_enable_pch_transcoder(crtc_state); +} + +void ilk_pch_disable(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + ilk_fdi_disable(crtc); +} + +void ilk_pch_post_disable(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + enum pipe pipe = crtc->pipe; + + ilk_disable_pch_transcoder(crtc); + + if (HAS_PCH_CPT(dev_priv)) { + i915_reg_t reg; + u32 temp; + + /* disable TRANS_DP_CTL */ + reg = TRANS_DP_CTL(pipe); + temp = intel_de_read(dev_priv, reg); + temp &= ~(TRANS_DP_OUTPUT_ENABLE | + TRANS_DP_PORT_SEL_MASK); + temp |= TRANS_DP_PORT_SEL_NONE; + intel_de_write(dev_priv, reg, temp); + + /* disable DPLL_SEL */ + temp = intel_de_read(dev_priv, PCH_DPLL_SEL); + temp &= ~(TRANS_DPLL_ENABLE(pipe) | TRANS_DPLLB_SEL(pipe)); + intel_de_write(dev_priv, PCH_DPLL_SEL, temp); + } + + ilk_fdi_pll_disable(crtc); +} + +static void ilk_pch_clock_get(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); + + /* read out port_clock from the DPLL */ + i9xx_crtc_clock_get(crtc, crtc_state); + + /* + * In case there is an active pipe without active ports, + * we may need some idea for the dotclock anyway. + * Calculate one based on the FDI configuration. + */ + crtc_state->hw.adjusted_mode.crtc_clock = + intel_dotclock_calculate(intel_fdi_link_freq(dev_priv, crtc_state), + &crtc_state->fdi_m_n); +} + +void ilk_pch_get_config(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_shared_dpll *pll; + enum pipe pipe = crtc->pipe; + enum intel_dpll_id pll_id; + bool pll_active; + u32 tmp; + + if ((intel_de_read(dev_priv, PCH_TRANSCONF(pipe)) & TRANS_ENABLE) == 0) + return; + + crtc_state->has_pch_encoder = true; + + tmp = intel_de_read(dev_priv, FDI_RX_CTL(pipe)); + crtc_state->fdi_lanes = ((FDI_DP_PORT_WIDTH_MASK & tmp) >> + FDI_DP_PORT_WIDTH_SHIFT) + 1; + + ilk_get_fdi_m_n_config(crtc, crtc_state); + + if (HAS_PCH_IBX(dev_priv)) { + /* + * The pipe->pch transcoder and pch transcoder->pll + * mapping is fixed. + */ + pll_id = (enum intel_dpll_id) pipe; + } else { + tmp = intel_de_read(dev_priv, PCH_DPLL_SEL); + if (tmp & TRANS_DPLLB_SEL(pipe)) + pll_id = DPLL_ID_PCH_PLL_B; + else + pll_id = DPLL_ID_PCH_PLL_A; + } + + crtc_state->shared_dpll = intel_get_shared_dpll_by_id(dev_priv, pll_id); + pll = crtc_state->shared_dpll; + + pll_active = intel_dpll_get_hw_state(dev_priv, pll, + &crtc_state->dpll_hw_state); + drm_WARN_ON(&dev_priv->drm, !pll_active); + + tmp = crtc_state->dpll_hw_state.dpll; + crtc_state->pixel_multiplier = + ((tmp & PLL_REF_SDVO_HDMI_MULTIPLIER_MASK) + >> PLL_REF_SDVO_HDMI_MULTIPLIER_SHIFT) + 1; + + ilk_pch_clock_get(crtc_state); +} + +static void lpt_enable_pch_transcoder(struct drm_i915_private *dev_priv, + enum transcoder cpu_transcoder) +{ + u32 val, pipeconf_val; + + /* FDI must be feeding us bits for PCH ports */ + assert_fdi_tx_enabled(dev_priv, (enum pipe) cpu_transcoder); + assert_fdi_rx_enabled(dev_priv, PIPE_A); + + val = intel_de_read(dev_priv, TRANS_CHICKEN2(PIPE_A)); + /* Workaround: set timing override bit. */ + val |= TRANS_CHICKEN2_TIMING_OVERRIDE; + /* Configure frame start delay to match the CPU */ + val &= ~TRANS_CHICKEN2_FRAME_START_DELAY_MASK; + val |= TRANS_CHICKEN2_FRAME_START_DELAY(dev_priv->framestart_delay - 1); + intel_de_write(dev_priv, TRANS_CHICKEN2(PIPE_A), val); + + val = TRANS_ENABLE; + pipeconf_val = intel_de_read(dev_priv, PIPECONF(cpu_transcoder)); + + if ((pipeconf_val & PIPECONF_INTERLACE_MASK_HSW) == + PIPECONF_INTERLACED_ILK) + val |= TRANS_INTERLACED; + else + val |= TRANS_PROGRESSIVE; + + intel_de_write(dev_priv, LPT_TRANSCONF, val); + if (intel_de_wait_for_set(dev_priv, LPT_TRANSCONF, + TRANS_STATE_ENABLE, 100)) + drm_err(&dev_priv->drm, "Failed to enable PCH transcoder\n"); +} + +static void lpt_disable_pch_transcoder(struct drm_i915_private *dev_priv) +{ + u32 val; + + val = intel_de_read(dev_priv, LPT_TRANSCONF); + val &= ~TRANS_ENABLE; + intel_de_write(dev_priv, LPT_TRANSCONF, val); + /* wait for PCH transcoder off, transcoder state */ + if (intel_de_wait_for_clear(dev_priv, LPT_TRANSCONF, + TRANS_STATE_ENABLE, 50)) + drm_err(&dev_priv->drm, "Failed to disable PCH transcoder\n"); + + /* Workaround: clear timing override bit. */ + val = intel_de_read(dev_priv, TRANS_CHICKEN2(PIPE_A)); + val &= ~TRANS_CHICKEN2_TIMING_OVERRIDE; + intel_de_write(dev_priv, TRANS_CHICKEN2(PIPE_A), val); +} + +void lpt_pch_enable(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + const struct intel_crtc_state *crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); + enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; + + assert_pch_transcoder_disabled(dev_priv, PIPE_A); + + lpt_program_iclkip(crtc_state); + + /* Set transcoder timing. */ + ilk_pch_transcoder_set_timings(crtc_state, PIPE_A); + + lpt_enable_pch_transcoder(dev_priv, cpu_transcoder); +} + +void lpt_pch_disable(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + + lpt_disable_pch_transcoder(dev_priv); + + lpt_disable_iclkip(dev_priv); +} + +void lpt_pch_get_config(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); + u32 tmp; + + if ((intel_de_read(dev_priv, LPT_TRANSCONF) & TRANS_ENABLE) == 0) + return; + + crtc_state->has_pch_encoder = true; + + tmp = intel_de_read(dev_priv, FDI_RX_CTL(PIPE_A)); + crtc_state->fdi_lanes = ((FDI_DP_PORT_WIDTH_MASK & tmp) >> + FDI_DP_PORT_WIDTH_SHIFT) + 1; + + ilk_get_fdi_m_n_config(crtc, crtc_state); + + crtc_state->hw.adjusted_mode.crtc_clock = lpt_get_iclkip(dev_priv); +} diff --git a/drivers/gpu/drm/i915/display/intel_pch_display.h b/drivers/gpu/drm/i915/display/intel_pch_display.h new file mode 100644 index 000000000000..2c387fe3a467 --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_pch_display.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef _INTEL_PCH_DISPLAY_H_ +#define _INTEL_PCH_DISPLAY_H_ + +struct intel_atomic_state; +struct intel_crtc; +struct intel_crtc_state; + +void ilk_pch_enable(struct intel_atomic_state *state, + struct intel_crtc *crtc); +void ilk_pch_disable(struct intel_atomic_state *state, + struct intel_crtc *crtc); +void ilk_pch_post_disable(struct intel_atomic_state *state, + struct intel_crtc *crtc); +void ilk_pch_get_config(struct intel_crtc_state *crtc_state); + +void lpt_pch_enable(struct intel_atomic_state *state, + struct intel_crtc *crtc); +void lpt_pch_disable(struct intel_atomic_state *state, + struct intel_crtc *crtc); +void lpt_pch_get_config(struct intel_crtc_state *crtc_state); + +#endif diff --git a/drivers/gpu/drm/i915/display/intel_pch_refclk.c b/drivers/gpu/drm/i915/display/intel_pch_refclk.c new file mode 100644 index 000000000000..b688fd87e3da --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_pch_refclk.c @@ -0,0 +1,648 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2021 Intel Corporation + */ + +#include "intel_de.h" +#include "intel_display_types.h" +#include "intel_panel.h" +#include "intel_pch_refclk.h" +#include "intel_sbi.h" + +static void lpt_fdi_reset_mphy(struct drm_i915_private *dev_priv) +{ + u32 tmp; + + tmp = intel_de_read(dev_priv, SOUTH_CHICKEN2); + tmp |= FDI_MPHY_IOSFSB_RESET_CTL; + intel_de_write(dev_priv, SOUTH_CHICKEN2, tmp); + + if (wait_for_us(intel_de_read(dev_priv, SOUTH_CHICKEN2) & + FDI_MPHY_IOSFSB_RESET_STATUS, 100)) + drm_err(&dev_priv->drm, "FDI mPHY reset assert timeout\n"); + + tmp = intel_de_read(dev_priv, SOUTH_CHICKEN2); + tmp &= ~FDI_MPHY_IOSFSB_RESET_CTL; + intel_de_write(dev_priv, SOUTH_CHICKEN2, tmp); + + if (wait_for_us((intel_de_read(dev_priv, SOUTH_CHICKEN2) & + FDI_MPHY_IOSFSB_RESET_STATUS) == 0, 100)) + drm_err(&dev_priv->drm, "FDI mPHY reset de-assert timeout\n"); +} + +/* WaMPhyProgramming:hsw */ +static void lpt_fdi_program_mphy(struct drm_i915_private *dev_priv) +{ + u32 tmp; + + lpt_fdi_reset_mphy(dev_priv); + + tmp = intel_sbi_read(dev_priv, 0x8008, SBI_MPHY); + tmp &= ~(0xFF << 24); + tmp |= (0x12 << 24); + intel_sbi_write(dev_priv, 0x8008, tmp, SBI_MPHY); + + tmp = intel_sbi_read(dev_priv, 0x2008, SBI_MPHY); + tmp |= (1 << 11); + intel_sbi_write(dev_priv, 0x2008, tmp, SBI_MPHY); + + tmp = intel_sbi_read(dev_priv, 0x2108, SBI_MPHY); + tmp |= (1 << 11); + intel_sbi_write(dev_priv, 0x2108, tmp, SBI_MPHY); + + tmp = intel_sbi_read(dev_priv, 0x206C, SBI_MPHY); + tmp |= (1 << 24) | (1 << 21) | (1 << 18); + intel_sbi_write(dev_priv, 0x206C, tmp, SBI_MPHY); + + tmp = intel_sbi_read(dev_priv, 0x216C, SBI_MPHY); + tmp |= (1 << 24) | (1 << 21) | (1 << 18); + intel_sbi_write(dev_priv, 0x216C, tmp, SBI_MPHY); + + tmp = intel_sbi_read(dev_priv, 0x2080, SBI_MPHY); + tmp &= ~(7 << 13); + tmp |= (5 << 13); + intel_sbi_write(dev_priv, 0x2080, tmp, SBI_MPHY); + + tmp = intel_sbi_read(dev_priv, 0x2180, SBI_MPHY); + tmp &= ~(7 << 13); + tmp |= (5 << 13); + intel_sbi_write(dev_priv, 0x2180, tmp, SBI_MPHY); + + tmp = intel_sbi_read(dev_priv, 0x208C, SBI_MPHY); + tmp &= ~0xFF; + tmp |= 0x1C; + intel_sbi_write(dev_priv, 0x208C, tmp, SBI_MPHY); + + tmp = intel_sbi_read(dev_priv, 0x218C, SBI_MPHY); + tmp &= ~0xFF; + tmp |= 0x1C; + intel_sbi_write(dev_priv, 0x218C, tmp, SBI_MPHY); + + tmp = intel_sbi_read(dev_priv, 0x2098, SBI_MPHY); + tmp &= ~(0xFF << 16); + tmp |= (0x1C << 16); + intel_sbi_write(dev_priv, 0x2098, tmp, SBI_MPHY); + + tmp = intel_sbi_read(dev_priv, 0x2198, SBI_MPHY); + tmp &= ~(0xFF << 16); + tmp |= (0x1C << 16); + intel_sbi_write(dev_priv, 0x2198, tmp, SBI_MPHY); + + tmp = intel_sbi_read(dev_priv, 0x20C4, SBI_MPHY); + tmp |= (1 << 27); + intel_sbi_write(dev_priv, 0x20C4, tmp, SBI_MPHY); + + tmp = intel_sbi_read(dev_priv, 0x21C4, SBI_MPHY); + tmp |= (1 << 27); + intel_sbi_write(dev_priv, 0x21C4, tmp, SBI_MPHY); + + tmp = intel_sbi_read(dev_priv, 0x20EC, SBI_MPHY); + tmp &= ~(0xF << 28); + tmp |= (4 << 28); + intel_sbi_write(dev_priv, 0x20EC, tmp, SBI_MPHY); + + tmp = intel_sbi_read(dev_priv, 0x21EC, SBI_MPHY); + tmp &= ~(0xF << 28); + tmp |= (4 << 28); + intel_sbi_write(dev_priv, 0x21EC, tmp, SBI_MPHY); +} + +void lpt_disable_iclkip(struct drm_i915_private *dev_priv) +{ + u32 temp; + + intel_de_write(dev_priv, PIXCLK_GATE, PIXCLK_GATE_GATE); + + mutex_lock(&dev_priv->sb_lock); + + temp = intel_sbi_read(dev_priv, SBI_SSCCTL6, SBI_ICLK); + temp |= SBI_SSCCTL_DISABLE; + intel_sbi_write(dev_priv, SBI_SSCCTL6, temp, SBI_ICLK); + + mutex_unlock(&dev_priv->sb_lock); +} + +/* Program iCLKIP clock to the desired frequency */ +void lpt_program_iclkip(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); + int clock = crtc_state->hw.adjusted_mode.crtc_clock; + u32 divsel, phaseinc, auxdiv, phasedir = 0; + u32 temp; + + lpt_disable_iclkip(dev_priv); + + /* The iCLK virtual clock root frequency is in MHz, + * but the adjusted_mode->crtc_clock in KHz. To get the + * divisors, it is necessary to divide one by another, so we + * convert the virtual clock precision to KHz here for higher + * precision. + */ + for (auxdiv = 0; auxdiv < 2; auxdiv++) { + u32 iclk_virtual_root_freq = 172800 * 1000; + u32 iclk_pi_range = 64; + u32 desired_divisor; + + desired_divisor = DIV_ROUND_CLOSEST(iclk_virtual_root_freq, + clock << auxdiv); + divsel = (desired_divisor / iclk_pi_range) - 2; + phaseinc = desired_divisor % iclk_pi_range; + + /* + * Near 20MHz is a corner case which is + * out of range for the 7-bit divisor + */ + if (divsel <= 0x7f) + break; + } + + /* This should not happen with any sane values */ + drm_WARN_ON(&dev_priv->drm, SBI_SSCDIVINTPHASE_DIVSEL(divsel) & + ~SBI_SSCDIVINTPHASE_DIVSEL_MASK); + drm_WARN_ON(&dev_priv->drm, SBI_SSCDIVINTPHASE_DIR(phasedir) & + ~SBI_SSCDIVINTPHASE_INCVAL_MASK); + + drm_dbg_kms(&dev_priv->drm, + "iCLKIP clock: found settings for %dKHz refresh rate: auxdiv=%x, divsel=%x, phasedir=%x, phaseinc=%x\n", + clock, auxdiv, divsel, phasedir, phaseinc); + + mutex_lock(&dev_priv->sb_lock); + + /* Program SSCDIVINTPHASE6 */ + temp = intel_sbi_read(dev_priv, SBI_SSCDIVINTPHASE6, SBI_ICLK); + temp &= ~SBI_SSCDIVINTPHASE_DIVSEL_MASK; + temp |= SBI_SSCDIVINTPHASE_DIVSEL(divsel); + temp &= ~SBI_SSCDIVINTPHASE_INCVAL_MASK; + temp |= SBI_SSCDIVINTPHASE_INCVAL(phaseinc); + temp |= SBI_SSCDIVINTPHASE_DIR(phasedir); + temp |= SBI_SSCDIVINTPHASE_PROPAGATE; + intel_sbi_write(dev_priv, SBI_SSCDIVINTPHASE6, temp, SBI_ICLK); + + /* Program SSCAUXDIV */ + temp = intel_sbi_read(dev_priv, SBI_SSCAUXDIV6, SBI_ICLK); + temp &= ~SBI_SSCAUXDIV_FINALDIV2SEL(1); + temp |= SBI_SSCAUXDIV_FINALDIV2SEL(auxdiv); + intel_sbi_write(dev_priv, SBI_SSCAUXDIV6, temp, SBI_ICLK); + + /* Enable modulator and associated divider */ + temp = intel_sbi_read(dev_priv, SBI_SSCCTL6, SBI_ICLK); + temp &= ~SBI_SSCCTL_DISABLE; + intel_sbi_write(dev_priv, SBI_SSCCTL6, temp, SBI_ICLK); + + mutex_unlock(&dev_priv->sb_lock); + + /* Wait for initialization time */ + udelay(24); + + intel_de_write(dev_priv, PIXCLK_GATE, PIXCLK_GATE_UNGATE); +} + +int lpt_get_iclkip(struct drm_i915_private *dev_priv) +{ + u32 divsel, phaseinc, auxdiv; + u32 iclk_virtual_root_freq = 172800 * 1000; + u32 iclk_pi_range = 64; + u32 desired_divisor; + u32 temp; + + if ((intel_de_read(dev_priv, PIXCLK_GATE) & PIXCLK_GATE_UNGATE) == 0) + return 0; + + mutex_lock(&dev_priv->sb_lock); + + temp = intel_sbi_read(dev_priv, SBI_SSCCTL6, SBI_ICLK); + if (temp & SBI_SSCCTL_DISABLE) { + mutex_unlock(&dev_priv->sb_lock); + return 0; + } + + temp = intel_sbi_read(dev_priv, SBI_SSCDIVINTPHASE6, SBI_ICLK); + divsel = (temp & SBI_SSCDIVINTPHASE_DIVSEL_MASK) >> + SBI_SSCDIVINTPHASE_DIVSEL_SHIFT; + phaseinc = (temp & SBI_SSCDIVINTPHASE_INCVAL_MASK) >> + SBI_SSCDIVINTPHASE_INCVAL_SHIFT; + + temp = intel_sbi_read(dev_priv, SBI_SSCAUXDIV6, SBI_ICLK); + auxdiv = (temp & SBI_SSCAUXDIV_FINALDIV2SEL_MASK) >> + SBI_SSCAUXDIV_FINALDIV2SEL_SHIFT; + + mutex_unlock(&dev_priv->sb_lock); + + desired_divisor = (divsel + 2) * iclk_pi_range + phaseinc; + + return DIV_ROUND_CLOSEST(iclk_virtual_root_freq, + desired_divisor << auxdiv); +} + +/* Implements 3 different sequences from BSpec chapter "Display iCLK + * Programming" based on the parameters passed: + * - Sequence to enable CLKOUT_DP + * - Sequence to enable CLKOUT_DP without spread + * - Sequence to enable CLKOUT_DP for FDI usage and configure PCH FDI I/O + */ +static void lpt_enable_clkout_dp(struct drm_i915_private *dev_priv, + bool with_spread, bool with_fdi) +{ + u32 reg, tmp; + + if (drm_WARN(&dev_priv->drm, with_fdi && !with_spread, + "FDI requires downspread\n")) + with_spread = true; + if (drm_WARN(&dev_priv->drm, HAS_PCH_LPT_LP(dev_priv) && + with_fdi, "LP PCH doesn't have FDI\n")) + with_fdi = false; + + mutex_lock(&dev_priv->sb_lock); + + tmp = intel_sbi_read(dev_priv, SBI_SSCCTL, SBI_ICLK); + tmp &= ~SBI_SSCCTL_DISABLE; + tmp |= SBI_SSCCTL_PATHALT; + intel_sbi_write(dev_priv, SBI_SSCCTL, tmp, SBI_ICLK); + + udelay(24); + + if (with_spread) { + tmp = intel_sbi_read(dev_priv, SBI_SSCCTL, SBI_ICLK); + tmp &= ~SBI_SSCCTL_PATHALT; + intel_sbi_write(dev_priv, SBI_SSCCTL, tmp, SBI_ICLK); + + if (with_fdi) + lpt_fdi_program_mphy(dev_priv); + } + + reg = HAS_PCH_LPT_LP(dev_priv) ? SBI_GEN0 : SBI_DBUFF0; + tmp = intel_sbi_read(dev_priv, reg, SBI_ICLK); + tmp |= SBI_GEN0_CFG_BUFFENABLE_DISABLE; + intel_sbi_write(dev_priv, reg, tmp, SBI_ICLK); + + mutex_unlock(&dev_priv->sb_lock); +} + +/* Sequence to disable CLKOUT_DP */ +void lpt_disable_clkout_dp(struct drm_i915_private *dev_priv) +{ + u32 reg, tmp; + + mutex_lock(&dev_priv->sb_lock); + + reg = HAS_PCH_LPT_LP(dev_priv) ? SBI_GEN0 : SBI_DBUFF0; + tmp = intel_sbi_read(dev_priv, reg, SBI_ICLK); + tmp &= ~SBI_GEN0_CFG_BUFFENABLE_DISABLE; + intel_sbi_write(dev_priv, reg, tmp, SBI_ICLK); + + tmp = intel_sbi_read(dev_priv, SBI_SSCCTL, SBI_ICLK); + if (!(tmp & SBI_SSCCTL_DISABLE)) { + if (!(tmp & SBI_SSCCTL_PATHALT)) { + tmp |= SBI_SSCCTL_PATHALT; + intel_sbi_write(dev_priv, SBI_SSCCTL, tmp, SBI_ICLK); + udelay(32); + } + tmp |= SBI_SSCCTL_DISABLE; + intel_sbi_write(dev_priv, SBI_SSCCTL, tmp, SBI_ICLK); + } + + mutex_unlock(&dev_priv->sb_lock); +} + +#define BEND_IDX(steps) ((50 + (steps)) / 5) + +static const u16 sscdivintphase[] = { + [BEND_IDX( 50)] = 0x3B23, + [BEND_IDX( 45)] = 0x3B23, + [BEND_IDX( 40)] = 0x3C23, + [BEND_IDX( 35)] = 0x3C23, + [BEND_IDX( 30)] = 0x3D23, + [BEND_IDX( 25)] = 0x3D23, + [BEND_IDX( 20)] = 0x3E23, + [BEND_IDX( 15)] = 0x3E23, + [BEND_IDX( 10)] = 0x3F23, + [BEND_IDX( 5)] = 0x3F23, + [BEND_IDX( 0)] = 0x0025, + [BEND_IDX( -5)] = 0x0025, + [BEND_IDX(-10)] = 0x0125, + [BEND_IDX(-15)] = 0x0125, + [BEND_IDX(-20)] = 0x0225, + [BEND_IDX(-25)] = 0x0225, + [BEND_IDX(-30)] = 0x0325, + [BEND_IDX(-35)] = 0x0325, + [BEND_IDX(-40)] = 0x0425, + [BEND_IDX(-45)] = 0x0425, + [BEND_IDX(-50)] = 0x0525, +}; + +/* + * Bend CLKOUT_DP + * steps -50 to 50 inclusive, in steps of 5 + * < 0 slow down the clock, > 0 speed up the clock, 0 == no bend (135MHz) + * change in clock period = -(steps / 10) * 5.787 ps + */ +static void lpt_bend_clkout_dp(struct drm_i915_private *dev_priv, int steps) +{ + u32 tmp; + int idx = BEND_IDX(steps); + + if (drm_WARN_ON(&dev_priv->drm, steps % 5 != 0)) + return; + + if (drm_WARN_ON(&dev_priv->drm, idx >= ARRAY_SIZE(sscdivintphase))) + return; + + mutex_lock(&dev_priv->sb_lock); + + if (steps % 10 != 0) + tmp = 0xAAAAAAAB; + else + tmp = 0x00000000; + intel_sbi_write(dev_priv, SBI_SSCDITHPHASE, tmp, SBI_ICLK); + + tmp = intel_sbi_read(dev_priv, SBI_SSCDIVINTPHASE, SBI_ICLK); + tmp &= 0xffff0000; + tmp |= sscdivintphase[idx]; + intel_sbi_write(dev_priv, SBI_SSCDIVINTPHASE, tmp, SBI_ICLK); + + mutex_unlock(&dev_priv->sb_lock); +} + +#undef BEND_IDX + +static bool spll_uses_pch_ssc(struct drm_i915_private *dev_priv) +{ + u32 fuse_strap = intel_de_read(dev_priv, FUSE_STRAP); + u32 ctl = intel_de_read(dev_priv, SPLL_CTL); + + if ((ctl & SPLL_PLL_ENABLE) == 0) + return false; + + if ((ctl & SPLL_REF_MASK) == SPLL_REF_MUXED_SSC && + (fuse_strap & HSW_CPU_SSC_ENABLE) == 0) + return true; + + if (IS_BROADWELL(dev_priv) && + (ctl & SPLL_REF_MASK) == SPLL_REF_PCH_SSC_BDW) + return true; + + return false; +} + +static bool wrpll_uses_pch_ssc(struct drm_i915_private *dev_priv, + enum intel_dpll_id id) +{ + u32 fuse_strap = intel_de_read(dev_priv, FUSE_STRAP); + u32 ctl = intel_de_read(dev_priv, WRPLL_CTL(id)); + + if ((ctl & WRPLL_PLL_ENABLE) == 0) + return false; + + if ((ctl & WRPLL_REF_MASK) == WRPLL_REF_PCH_SSC) + return true; + + if ((IS_BROADWELL(dev_priv) || IS_HSW_ULT(dev_priv)) && + (ctl & WRPLL_REF_MASK) == WRPLL_REF_MUXED_SSC_BDW && + (fuse_strap & HSW_CPU_SSC_ENABLE) == 0) + return true; + + return false; +} + +static void lpt_init_pch_refclk(struct drm_i915_private *dev_priv) +{ + struct intel_encoder *encoder; + bool has_fdi = false; + + for_each_intel_encoder(&dev_priv->drm, encoder) { + switch (encoder->type) { + case INTEL_OUTPUT_ANALOG: + has_fdi = true; + break; + default: + break; + } + } + + /* + * The BIOS may have decided to use the PCH SSC + * reference so we must not disable it until the + * relevant PLLs have stopped relying on it. We'll + * just leave the PCH SSC reference enabled in case + * any active PLL is using it. It will get disabled + * after runtime suspend if we don't have FDI. + * + * TODO: Move the whole reference clock handling + * to the modeset sequence proper so that we can + * actually enable/disable/reconfigure these things + * safely. To do that we need to introduce a real + * clock hierarchy. That would also allow us to do + * clock bending finally. + */ + dev_priv->pch_ssc_use = 0; + + if (spll_uses_pch_ssc(dev_priv)) { + drm_dbg_kms(&dev_priv->drm, "SPLL using PCH SSC\n"); + dev_priv->pch_ssc_use |= BIT(DPLL_ID_SPLL); + } + + if (wrpll_uses_pch_ssc(dev_priv, DPLL_ID_WRPLL1)) { + drm_dbg_kms(&dev_priv->drm, "WRPLL1 using PCH SSC\n"); + dev_priv->pch_ssc_use |= BIT(DPLL_ID_WRPLL1); + } + + if (wrpll_uses_pch_ssc(dev_priv, DPLL_ID_WRPLL2)) { + drm_dbg_kms(&dev_priv->drm, "WRPLL2 using PCH SSC\n"); + dev_priv->pch_ssc_use |= BIT(DPLL_ID_WRPLL2); + } + + if (dev_priv->pch_ssc_use) + return; + + if (has_fdi) { + lpt_bend_clkout_dp(dev_priv, 0); + lpt_enable_clkout_dp(dev_priv, true, true); + } else { + lpt_disable_clkout_dp(dev_priv); + } +} + +static void ilk_init_pch_refclk(struct drm_i915_private *dev_priv) +{ + struct intel_encoder *encoder; + int i; + u32 val, final; + bool has_lvds = false; + bool has_cpu_edp = false; + bool has_panel = false; + bool has_ck505 = false; + bool can_ssc = false; + bool using_ssc_source = false; + + /* We need to take the global config into account */ + for_each_intel_encoder(&dev_priv->drm, encoder) { + switch (encoder->type) { + case INTEL_OUTPUT_LVDS: + has_panel = true; + has_lvds = true; + break; + case INTEL_OUTPUT_EDP: + has_panel = true; + if (encoder->port == PORT_A) + has_cpu_edp = true; + break; + default: + break; + } + } + + if (HAS_PCH_IBX(dev_priv)) { + has_ck505 = dev_priv->vbt.display_clock_mode; + can_ssc = has_ck505; + } else { + has_ck505 = false; + can_ssc = true; + } + + /* Check if any DPLLs are using the SSC source */ + for (i = 0; i < dev_priv->dpll.num_shared_dpll; i++) { + u32 temp = intel_de_read(dev_priv, PCH_DPLL(i)); + + if (!(temp & DPLL_VCO_ENABLE)) + continue; + + if ((temp & PLL_REF_INPUT_MASK) == + PLLB_REF_INPUT_SPREADSPECTRUMIN) { + using_ssc_source = true; + break; + } + } + + drm_dbg_kms(&dev_priv->drm, + "has_panel %d has_lvds %d has_ck505 %d using_ssc_source %d\n", + has_panel, has_lvds, has_ck505, using_ssc_source); + + /* Ironlake: try to setup display ref clock before DPLL + * enabling. This is only under driver's control after + * PCH B stepping, previous chipset stepping should be + * ignoring this setting. + */ + val = intel_de_read(dev_priv, PCH_DREF_CONTROL); + + /* As we must carefully and slowly disable/enable each source in turn, + * compute the final state we want first and check if we need to + * make any changes at all. + */ + final = val; + final &= ~DREF_NONSPREAD_SOURCE_MASK; + if (has_ck505) + final |= DREF_NONSPREAD_CK505_ENABLE; + else + final |= DREF_NONSPREAD_SOURCE_ENABLE; + + final &= ~DREF_SSC_SOURCE_MASK; + final &= ~DREF_CPU_SOURCE_OUTPUT_MASK; + final &= ~DREF_SSC1_ENABLE; + + if (has_panel) { + final |= DREF_SSC_SOURCE_ENABLE; + + if (intel_panel_use_ssc(dev_priv) && can_ssc) + final |= DREF_SSC1_ENABLE; + + if (has_cpu_edp) { + if (intel_panel_use_ssc(dev_priv) && can_ssc) + final |= DREF_CPU_SOURCE_OUTPUT_DOWNSPREAD; + else + final |= DREF_CPU_SOURCE_OUTPUT_NONSPREAD; + } else { + final |= DREF_CPU_SOURCE_OUTPUT_DISABLE; + } + } else if (using_ssc_source) { + final |= DREF_SSC_SOURCE_ENABLE; + final |= DREF_SSC1_ENABLE; + } + + if (final == val) + return; + + /* Always enable nonspread source */ + val &= ~DREF_NONSPREAD_SOURCE_MASK; + + if (has_ck505) + val |= DREF_NONSPREAD_CK505_ENABLE; + else + val |= DREF_NONSPREAD_SOURCE_ENABLE; + + if (has_panel) { + val &= ~DREF_SSC_SOURCE_MASK; + val |= DREF_SSC_SOURCE_ENABLE; + + /* SSC must be turned on before enabling the CPU output */ + if (intel_panel_use_ssc(dev_priv) && can_ssc) { + drm_dbg_kms(&dev_priv->drm, "Using SSC on panel\n"); + val |= DREF_SSC1_ENABLE; + } else { + val &= ~DREF_SSC1_ENABLE; + } + + /* Get SSC going before enabling the outputs */ + intel_de_write(dev_priv, PCH_DREF_CONTROL, val); + intel_de_posting_read(dev_priv, PCH_DREF_CONTROL); + udelay(200); + + val &= ~DREF_CPU_SOURCE_OUTPUT_MASK; + + /* Enable CPU source on CPU attached eDP */ + if (has_cpu_edp) { + if (intel_panel_use_ssc(dev_priv) && can_ssc) { + drm_dbg_kms(&dev_priv->drm, + "Using SSC on eDP\n"); + val |= DREF_CPU_SOURCE_OUTPUT_DOWNSPREAD; + } else { + val |= DREF_CPU_SOURCE_OUTPUT_NONSPREAD; + } + } else { + val |= DREF_CPU_SOURCE_OUTPUT_DISABLE; + } + + intel_de_write(dev_priv, PCH_DREF_CONTROL, val); + intel_de_posting_read(dev_priv, PCH_DREF_CONTROL); + udelay(200); + } else { + drm_dbg_kms(&dev_priv->drm, "Disabling CPU source output\n"); + + val &= ~DREF_CPU_SOURCE_OUTPUT_MASK; + + /* Turn off CPU output */ + val |= DREF_CPU_SOURCE_OUTPUT_DISABLE; + + intel_de_write(dev_priv, PCH_DREF_CONTROL, val); + intel_de_posting_read(dev_priv, PCH_DREF_CONTROL); + udelay(200); + + if (!using_ssc_source) { + drm_dbg_kms(&dev_priv->drm, "Disabling SSC source\n"); + + /* Turn off the SSC source */ + val &= ~DREF_SSC_SOURCE_MASK; + val |= DREF_SSC_SOURCE_DISABLE; + + /* Turn off SSC1 */ + val &= ~DREF_SSC1_ENABLE; + + intel_de_write(dev_priv, PCH_DREF_CONTROL, val); + intel_de_posting_read(dev_priv, PCH_DREF_CONTROL); + udelay(200); + } + } + + BUG_ON(val != final); +} + +/* + * Initialize reference clocks when the driver loads + */ +void intel_init_pch_refclk(struct drm_i915_private *dev_priv) +{ + if (HAS_PCH_IBX(dev_priv) || HAS_PCH_CPT(dev_priv)) + ilk_init_pch_refclk(dev_priv); + else if (HAS_PCH_LPT(dev_priv)) + lpt_init_pch_refclk(dev_priv); +} diff --git a/drivers/gpu/drm/i915/display/intel_pch_refclk.h b/drivers/gpu/drm/i915/display/intel_pch_refclk.h new file mode 100644 index 000000000000..12ab2c75a800 --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_pch_refclk.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef _INTEL_PCH_REFCLK_H_ +#define _INTEL_PCH_REFCLK_H_ + +#include <linux/types.h> + +struct drm_i915_private; +struct intel_crtc_state; + +void lpt_program_iclkip(const struct intel_crtc_state *crtc_state); +void lpt_disable_iclkip(struct drm_i915_private *dev_priv); +int lpt_get_iclkip(struct drm_i915_private *dev_priv); + +void intel_init_pch_refclk(struct drm_i915_private *dev_priv); +void lpt_disable_clkout_dp(struct drm_i915_private *dev_priv); + +#endif diff --git a/drivers/gpu/drm/i915/display/intel_plane_initial.c b/drivers/gpu/drm/i915/display/intel_plane_initial.c index dcd698a02da2..01ce1d72297f 100644 --- a/drivers/gpu/drm/i915/display/intel_plane_initial.c +++ b/drivers/gpu/drm/i915/display/intel_plane_initial.c @@ -3,11 +3,12 @@ * Copyright © 2021 Intel Corporation */ -#include "intel_display_types.h" -#include "intel_plane_initial.h" +#include "i915_drv.h" #include "intel_atomic_plane.h" #include "intel_display.h" +#include "intel_display_types.h" #include "intel_fb.h" +#include "intel_plane_initial.h" static bool intel_reuse_initial_plane_obj(struct drm_i915_private *i915, diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 7a205fd5023b..a1a663f362e7 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -28,13 +28,13 @@ #include "i915_drv.h" #include "intel_atomic.h" +#include "intel_crtc.h" #include "intel_de.h" #include "intel_display_types.h" #include "intel_dp_aux.h" #include "intel_hdmi.h" #include "intel_psr.h" #include "intel_snps_phy.h" -#include "intel_sprite.h" #include "skl_universal_plane.h" /** @@ -588,7 +588,9 @@ 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 (DISPLAY_VER(dev_priv) >= 12) + if (IS_ALDERLAKE_P(dev_priv)) + return trans == TRANSCODER_A || trans == TRANSCODER_B; + else if (DISPLAY_VER(dev_priv) >= 12) return trans == TRANSCODER_A; else return trans == TRANSCODER_EDP; @@ -1346,6 +1348,7 @@ void intel_psr_disable(struct intel_dp *intel_dp, */ void intel_psr_pause(struct intel_dp *intel_dp) { + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); struct intel_psr *psr = &intel_dp->psr; if (!CAN_PSR(intel_dp)) @@ -1358,6 +1361,9 @@ void intel_psr_pause(struct intel_dp *intel_dp) return; } + /* If we ever hit this, we will need to add refcount to pause/resume */ + drm_WARN_ON(&dev_priv->drm, psr->paused); + intel_psr_exit(intel_dp); intel_psr_wait_exit_locked(intel_dp); psr->paused = true; @@ -1463,10 +1469,19 @@ void intel_psr2_program_plane_sel_fetch(struct intel_plane *plane, val |= plane_state->uapi.dst.x1; intel_de_write_fw(dev_priv, PLANE_SEL_FETCH_POS(pipe, plane->id), val); - /* TODO: consider auxiliary surfaces */ - x = plane_state->uapi.src.x1 >> 16; - y = (plane_state->uapi.src.y1 >> 16) + clip->y1; + x = plane_state->view.color_plane[color_plane].x; + + /* + * From Bspec: UV surface Start Y Position = half of Y plane Y + * start position. + */ + if (!color_plane) + y = plane_state->view.color_plane[color_plane].y + clip->y1; + else + y = plane_state->view.color_plane[color_plane].y + clip->y1 / 2; + val = y << 16 | x; + intel_de_write_fw(dev_priv, PLANE_SEL_FETCH_OFFSET(pipe, plane->id), val); @@ -1558,9 +1573,6 @@ static void intel_psr2_sel_fetch_pipe_alignment(const struct intel_crtc_state *c * also planes are not updated if they have a negative X * position so for now doing a full update in this cases * - * TODO: We are missing multi-planar formats handling, until it is - * implemented it will send full frame updates. - * * Plane scaling and rotation is not supported by selective fetch and both * properties can change without a modeset, so need to be check at every * atomic commmit. @@ -1570,7 +1582,6 @@ static bool psr2_sel_fetch_plane_state_supported(const struct intel_plane_state if (plane_state->uapi.dst.y1 < 0 || plane_state->uapi.dst.x1 < 0 || plane_state->scaler_id >= 0 || - plane_state->hw.fb->format->num_planes > 1 || plane_state->uapi.rotation != DRM_MODE_ROTATE_0) return false; @@ -1696,6 +1707,7 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, for_each_oldnew_intel_plane_in_state(state, plane, old_plane_state, new_plane_state, i) { struct drm_rect *sel_fetch_area, inter; + struct intel_plane *linked = new_plane_state->planar_linked_plane; if (new_plane_state->uapi.crtc != crtc_state->uapi.crtc || !new_plane_state->uapi.visible) @@ -1714,6 +1726,24 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, sel_fetch_area->y1 = inter.y1 - new_plane_state->uapi.dst.y1; sel_fetch_area->y2 = inter.y2 - new_plane_state->uapi.dst.y1; crtc_state->update_planes |= BIT(plane->id); + + /* + * Sel_fetch_area is calculated for UV plane. Use + * same area for Y plane as well. + */ + if (linked) { + struct intel_plane_state *linked_new_plane_state; + struct drm_rect *linked_sel_fetch_area; + + linked_new_plane_state = intel_atomic_get_plane_state(state, linked); + if (IS_ERR(linked_new_plane_state)) + return PTR_ERR(linked_new_plane_state); + + linked_sel_fetch_area = &linked_new_plane_state->psr2_sel_fetch_area; + linked_sel_fetch_area->y1 = sel_fetch_area->y1; + linked_sel_fetch_area->y2 = sel_fetch_area->y2; + crtc_state->update_planes |= BIT(linked->id); + } } skip_sel_fetch_set_loop: @@ -1721,11 +1751,17 @@ skip_sel_fetch_set_loop: return 0; } -static void _intel_psr_pre_plane_update(const struct intel_atomic_state *state, - const struct intel_crtc_state *crtc_state) +void intel_psr_pre_plane_update(struct intel_atomic_state *state, + struct intel_crtc *crtc) { + struct drm_i915_private *i915 = to_i915(state->base.dev); + const struct intel_crtc_state *crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); struct intel_encoder *encoder; + if (!HAS_PSR(i915)) + return; + for_each_intel_encoder_mask_with_psr(state->base.dev, encoder, crtc_state->uapi.encoder_mask) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); @@ -1740,6 +1776,7 @@ static void _intel_psr_pre_plane_update(const struct intel_atomic_state *state, * - All planes will go inactive * - Changing between PSR versions */ + needs_to_disable |= intel_crtc_needs_modeset(crtc_state); needs_to_disable |= !crtc_state->has_psr; needs_to_disable |= !crtc_state->active_planes; needs_to_disable |= crtc_state->has_psr2 != psr->psr2_enabled; @@ -1751,20 +1788,6 @@ static void _intel_psr_pre_plane_update(const struct intel_atomic_state *state, } } -void intel_psr_pre_plane_update(const struct intel_atomic_state *state) -{ - struct drm_i915_private *dev_priv = to_i915(state->base.dev); - struct intel_crtc_state *crtc_state; - struct intel_crtc *crtc; - int i; - - if (!HAS_PSR(dev_priv)) - return; - - for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) - _intel_psr_pre_plane_update(state, crtc_state); -} - static void _intel_psr_post_plane_update(const struct intel_atomic_state *state, const struct intel_crtc_state *crtc_state) { @@ -1809,15 +1832,21 @@ void intel_psr_post_plane_update(const struct intel_atomic_state *state) _intel_psr_post_plane_update(state, crtc_state); } -/** - * psr_wait_for_idle - wait for PSR1 to idle - * @intel_dp: Intel DP - * @out_value: PSR status in case of failure - * - * Returns: 0 on success or -ETIMEOUT if PSR status does not idle. - * - */ -static int psr_wait_for_idle(struct intel_dp *intel_dp, u32 *out_value) +static int _psr2_ready_for_pipe_update_locked(struct intel_dp *intel_dp) +{ + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + + /* + * Any state lower than EDP_PSR2_STATUS_STATE_DEEP_SLEEP is enough. + * As all higher states has bit 4 of PSR2 state set we can just wait for + * EDP_PSR2_STATUS_STATE_DEEP_SLEEP to be cleared. + */ + return intel_de_wait_for_clear(dev_priv, + EDP_PSR2_STATUS(intel_dp->psr.transcoder), + EDP_PSR2_STATUS_STATE_DEEP_SLEEP, 50); +} + +static int _psr1_ready_for_pipe_update_locked(struct intel_dp *intel_dp) { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); @@ -1827,15 +1856,13 @@ static int psr_wait_for_idle(struct intel_dp *intel_dp, u32 *out_value) * exit training time + 1.5 ms of aux channel handshake. 50 ms is * defensive enough to cover everything. */ - return __intel_wait_for_register(&dev_priv->uncore, - EDP_PSR_STATUS(intel_dp->psr.transcoder), - EDP_PSR_STATUS_STATE_MASK, - EDP_PSR_STATUS_STATE_IDLE, 2, 50, - out_value); + return intel_de_wait_for_clear(dev_priv, + EDP_PSR_STATUS(intel_dp->psr.transcoder), + EDP_PSR_STATUS_STATE_MASK, 50); } /** - * intel_psr_wait_for_idle - wait for PSR1 to idle + * intel_psr_wait_for_idle - wait for PSR be ready for a pipe update * @new_crtc_state: new CRTC state * * This function is expected to be called from pipe_update_start() where it is @@ -1852,19 +1879,23 @@ void intel_psr_wait_for_idle(const struct intel_crtc_state *new_crtc_state) for_each_intel_encoder_mask_with_psr(&dev_priv->drm, encoder, new_crtc_state->uapi.encoder_mask) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); - u32 psr_status; + int ret; mutex_lock(&intel_dp->psr.lock); - if (!intel_dp->psr.enabled || intel_dp->psr.psr2_enabled) { + + if (!intel_dp->psr.enabled) { mutex_unlock(&intel_dp->psr.lock); continue; } - /* when the PSR1 is enabled */ - if (psr_wait_for_idle(intel_dp, &psr_status)) - drm_err(&dev_priv->drm, - "PSR idle timed out 0x%x, atomic update may fail\n", - psr_status); + if (intel_dp->psr.psr2_enabled) + ret = _psr2_ready_for_pipe_update_locked(intel_dp); + else + ret = _psr1_ready_for_pipe_update_locked(intel_dp); + + if (ret) + drm_err(&dev_priv->drm, "PSR wait timed out, atomic update may fail\n"); + mutex_unlock(&intel_dp->psr.lock); } } diff --git a/drivers/gpu/drm/i915/display/intel_psr.h b/drivers/gpu/drm/i915/display/intel_psr.h index facffbacd357..f6526d9ccfdc 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.h +++ b/drivers/gpu/drm/i915/display/intel_psr.h @@ -6,21 +6,23 @@ #ifndef __INTEL_PSR_H__ #define __INTEL_PSR_H__ -#include "intel_frontbuffer.h" +#include <linux/types.h> +enum fb_op_origin; struct drm_connector; struct drm_connector_state; struct drm_i915_private; +struct intel_atomic_state; +struct intel_crtc; struct intel_crtc_state; struct intel_dp; -struct intel_crtc; -struct intel_atomic_state; -struct intel_plane_state; -struct intel_plane; struct intel_encoder; +struct intel_plane; +struct intel_plane_state; void intel_psr_init_dpcd(struct intel_dp *intel_dp); -void intel_psr_pre_plane_update(const struct intel_atomic_state *state); +void intel_psr_pre_plane_update(struct intel_atomic_state *state, + struct intel_crtc *crtc); void intel_psr_post_plane_update(const struct intel_atomic_state *state); void intel_psr_disable(struct intel_dp *intel_dp, const struct intel_crtc_state *old_crtc_state); diff --git a/drivers/gpu/drm/i915/display/intel_quirks.c b/drivers/gpu/drm/i915/display/intel_quirks.c index 8a52b7a16774..c8488f5ebd04 100644 --- a/drivers/gpu/drm/i915/display/intel_quirks.c +++ b/drivers/gpu/drm/i915/display/intel_quirks.c @@ -5,6 +5,7 @@ #include <linux/dmi.h> +#include "i915_drv.h" #include "intel_display_types.h" #include "intel_quirks.h" diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c index 2dc6c3742ba2..76e1188b01d4 100644 --- a/drivers/gpu/drm/i915/display/intel_sdvo.c +++ b/drivers/gpu/drm/i915/display/intel_sdvo.c @@ -1842,7 +1842,7 @@ static void intel_enable_sdvo(struct intel_atomic_state *state, intel_sdvo_write_sdvox(intel_sdvo, temp); for (i = 0; i < 2; i++) - intel_wait_for_vblank(dev_priv, crtc->pipe); + intel_crtc_wait_for_next_vblank(crtc); success = intel_sdvo_get_trained_inputs(intel_sdvo, &input1, &input2); /* diff --git a/drivers/gpu/drm/i915/display/intel_snps_phy.c b/drivers/gpu/drm/i915/display/intel_snps_phy.c index 5e20f340730f..09f405e4d363 100644 --- a/drivers/gpu/drm/i915/display/intel_snps_phy.c +++ b/drivers/gpu/drm/i915/display/intel_snps_phy.c @@ -58,7 +58,6 @@ void intel_snps_phy_set_signal_levels(struct intel_encoder *encoder, struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); const struct intel_ddi_buf_trans *trans; enum phy phy = intel_port_to_phy(dev_priv, encoder->port); - int level = intel_ddi_level(encoder, crtc_state, 0); int n_entries, ln; trans = encoder->get_buf_trans(encoder, crtc_state, &n_entries); @@ -66,6 +65,7 @@ void intel_snps_phy_set_signal_levels(struct intel_encoder *encoder, return; for (ln = 0; ln < 4; ln++) { + int level = intel_ddi_level(encoder, crtc_state, ln); u32 val = 0; val |= REG_FIELD_PREP(SNPS_PHY_TX_EQ_MAIN, trans->entries[level].snps.vswing); @@ -186,6 +186,7 @@ static const struct intel_mpllb_state dg2_dp_uhbr10_100 = { REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | REG_FIELD_PREP(SNPS_PHY_MPLLB_WORD_DIV2_EN, 1) | REG_FIELD_PREP(SNPS_PHY_MPLLB_DP2_MODE, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_SHIM_DIV32_CLK_SEL, 1) | REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2), .mpllb_div2 = REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 2) | @@ -369,6 +370,7 @@ static const struct intel_mpllb_state dg2_dp_uhbr10_38_4 = { REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | REG_FIELD_PREP(SNPS_PHY_MPLLB_WORD_DIV2_EN, 1) | REG_FIELD_PREP(SNPS_PHY_MPLLB_DP2_MODE, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_SHIM_DIV32_CLK_SEL, 1) | REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2), .mpllb_div2 = REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c index 08116f41da26..2357a1301f48 100644 --- a/drivers/gpu/drm/i915/display/intel_sprite.c +++ b/drivers/gpu/drm/i915/display/intel_sprite.c @@ -40,14 +40,15 @@ #include <drm/drm_rect.h> #include "i915_drv.h" -#include "i915_trace.h" #include "i915_vgpu.h" +#include "i9xx_plane.h" #include "intel_atomic_plane.h" +#include "intel_crtc.h" #include "intel_de.h" #include "intel_display_types.h" +#include "intel_fb.h" #include "intel_frontbuffer.h" #include "intel_sprite.h" -#include "i9xx_plane.h" #include "intel_vrr.h" int intel_plane_check_src_coordinates(struct intel_plane_state *plane_state) @@ -118,7 +119,7 @@ static void i9xx_plane_linear_gamma(u16 gamma[8]) } static void -chv_update_csc(const struct intel_plane_state *plane_state) +chv_sprite_update_csc(const struct intel_plane_state *plane_state) { struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); struct drm_i915_private *dev_priv = to_i915(plane->base.dev); @@ -190,7 +191,7 @@ chv_update_csc(const struct intel_plane_state *plane_state) #define COS_0 1 static void -vlv_update_clrc(const struct intel_plane_state *plane_state) +vlv_sprite_update_clrc(const struct intel_plane_state *plane_state) { struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); struct drm_i915_private *dev_priv = to_i915(plane->base.dev); @@ -393,7 +394,7 @@ static u32 vlv_sprite_ctl(const struct intel_crtc_state *crtc_state, return sprctl; } -static void vlv_update_gamma(const struct intel_plane_state *plane_state) +static void vlv_sprite_update_gamma(const struct intel_plane_state *plane_state) { struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); struct drm_i915_private *dev_priv = to_i915(plane->base.dev); @@ -417,45 +418,54 @@ static void vlv_update_gamma(const struct intel_plane_state *plane_state) } static void -vlv_update_plane(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state, - const struct intel_plane_state *plane_state) +vlv_sprite_update_noarm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum pipe pipe = plane->pipe; enum plane_id plane_id = plane->id; - u32 sprsurf_offset = plane_state->view.color_plane[0].offset; - u32 linear_offset; - const struct drm_intel_sprite_colorkey *key = &plane_state->ckey; int crtc_x = plane_state->uapi.dst.x1; int crtc_y = plane_state->uapi.dst.y1; u32 crtc_w = drm_rect_width(&plane_state->uapi.dst); u32 crtc_h = drm_rect_height(&plane_state->uapi.dst); + unsigned long irqflags; + + spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); + + intel_de_write_fw(dev_priv, SPSTRIDE(pipe, plane_id), + plane_state->view.color_plane[0].mapping_stride); + intel_de_write_fw(dev_priv, SPPOS(pipe, plane_id), + (crtc_y << 16) | crtc_x); + intel_de_write_fw(dev_priv, SPSIZE(pipe, plane_id), + ((crtc_h - 1) << 16) | (crtc_w - 1)); + + spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); +} + +static void +vlv_sprite_update_arm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) +{ + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + enum pipe pipe = plane->pipe; + enum plane_id plane_id = plane->id; + const struct drm_intel_sprite_colorkey *key = &plane_state->ckey; + u32 sprsurf_offset = plane_state->view.color_plane[0].offset; u32 x = plane_state->view.color_plane[0].x; u32 y = plane_state->view.color_plane[0].y; + u32 sprctl, linear_offset; unsigned long irqflags; - u32 sprctl; sprctl = plane_state->ctl | vlv_sprite_ctl_crtc(crtc_state); - /* Sizes are 0 based */ - crtc_w--; - crtc_h--; - linear_offset = intel_fb_xy_to_linear(x, y, plane_state, 0); spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); - intel_de_write_fw(dev_priv, SPSTRIDE(pipe, plane_id), - plane_state->view.color_plane[0].stride); - intel_de_write_fw(dev_priv, SPPOS(pipe, plane_id), - (crtc_y << 16) | crtc_x); - intel_de_write_fw(dev_priv, SPSIZE(pipe, plane_id), - (crtc_h << 16) | crtc_w); - intel_de_write_fw(dev_priv, SPCONSTALPHA(pipe, plane_id), 0); - if (IS_CHERRYVIEW(dev_priv) && pipe == PIPE_B) - chv_update_csc(plane_state); + chv_sprite_update_csc(plane_state); if (key->flags) { intel_de_write_fw(dev_priv, SPKEYMINVAL(pipe, plane_id), @@ -466,6 +476,8 @@ vlv_update_plane(struct intel_plane *plane, key->max_value); } + intel_de_write_fw(dev_priv, SPCONSTALPHA(pipe, plane_id), 0); + intel_de_write_fw(dev_priv, SPLINOFF(pipe, plane_id), linear_offset); intel_de_write_fw(dev_priv, SPTILEOFF(pipe, plane_id), (y << 16) | x); @@ -478,15 +490,15 @@ vlv_update_plane(struct intel_plane *plane, intel_de_write_fw(dev_priv, SPSURF(pipe, plane_id), intel_plane_ggtt_offset(plane_state) + sprsurf_offset); - vlv_update_clrc(plane_state); - vlv_update_gamma(plane_state); + vlv_sprite_update_clrc(plane_state); + vlv_sprite_update_gamma(plane_state); spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); } static void -vlv_disable_plane(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state) +vlv_sprite_disable_arm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum pipe pipe = plane->pipe; @@ -502,8 +514,8 @@ vlv_disable_plane(struct intel_plane *plane, } static bool -vlv_plane_get_hw_state(struct intel_plane *plane, - enum pipe *pipe) +vlv_sprite_get_hw_state(struct intel_plane *plane, + enum pipe *pipe) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum intel_display_power_domain power_domain; @@ -805,7 +817,7 @@ static void ivb_sprite_linear_gamma(const struct intel_plane_state *plane_state, i++; } -static void ivb_update_gamma(const struct intel_plane_state *plane_state) +static void ivb_sprite_update_gamma(const struct intel_plane_state *plane_state) { struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); struct drm_i915_private *dev_priv = to_i915(plane->base.dev); @@ -835,48 +847,56 @@ static void ivb_update_gamma(const struct intel_plane_state *plane_state) } static void -ivb_update_plane(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state, - const struct intel_plane_state *plane_state) +ivb_sprite_update_noarm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum pipe pipe = plane->pipe; - u32 sprsurf_offset = plane_state->view.color_plane[0].offset; - u32 linear_offset; - const struct drm_intel_sprite_colorkey *key = &plane_state->ckey; int crtc_x = plane_state->uapi.dst.x1; int crtc_y = plane_state->uapi.dst.y1; u32 crtc_w = drm_rect_width(&plane_state->uapi.dst); u32 crtc_h = drm_rect_height(&plane_state->uapi.dst); - u32 x = plane_state->view.color_plane[0].x; - u32 y = plane_state->view.color_plane[0].y; u32 src_w = drm_rect_width(&plane_state->uapi.src) >> 16; u32 src_h = drm_rect_height(&plane_state->uapi.src) >> 16; - u32 sprctl, sprscale = 0; + u32 sprscale = 0; unsigned long irqflags; - sprctl = plane_state->ctl | ivb_sprite_ctl_crtc(crtc_state); - - /* Sizes are 0 based */ - src_w--; - src_h--; - crtc_w--; - crtc_h--; - if (crtc_w != src_w || crtc_h != src_h) - sprscale = SPRITE_SCALE_ENABLE | (src_w << 16) | src_h; - - linear_offset = intel_fb_xy_to_linear(x, y, plane_state, 0); + sprscale = SPRITE_SCALE_ENABLE | ((src_w - 1) << 16) | (src_h - 1); spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); intel_de_write_fw(dev_priv, SPRSTRIDE(pipe), - plane_state->view.color_plane[0].stride); + plane_state->view.color_plane[0].mapping_stride); intel_de_write_fw(dev_priv, SPRPOS(pipe), (crtc_y << 16) | crtc_x); - intel_de_write_fw(dev_priv, SPRSIZE(pipe), (crtc_h << 16) | crtc_w); + intel_de_write_fw(dev_priv, SPRSIZE(pipe), ((crtc_h - 1) << 16) | (crtc_w - 1)); if (IS_IVYBRIDGE(dev_priv)) intel_de_write_fw(dev_priv, SPRSCALE(pipe), sprscale); + spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); +} + +static void +ivb_sprite_update_arm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) +{ + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + enum pipe pipe = plane->pipe; + const struct drm_intel_sprite_colorkey *key = &plane_state->ckey; + u32 sprsurf_offset = plane_state->view.color_plane[0].offset; + u32 x = plane_state->view.color_plane[0].x; + u32 y = plane_state->view.color_plane[0].y; + u32 sprctl, linear_offset; + unsigned long irqflags; + + sprctl = plane_state->ctl | ivb_sprite_ctl_crtc(crtc_state); + + linear_offset = intel_fb_xy_to_linear(x, y, plane_state, 0); + + spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); + if (key->flags) { intel_de_write_fw(dev_priv, SPRKEYVAL(pipe), key->min_value); intel_de_write_fw(dev_priv, SPRKEYMSK(pipe), @@ -902,14 +922,14 @@ ivb_update_plane(struct intel_plane *plane, intel_de_write_fw(dev_priv, SPRSURF(pipe), intel_plane_ggtt_offset(plane_state) + sprsurf_offset); - ivb_update_gamma(plane_state); + ivb_sprite_update_gamma(plane_state); spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); } static void -ivb_disable_plane(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state) +ivb_sprite_disable_arm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum pipe pipe = plane->pipe; @@ -927,8 +947,8 @@ ivb_disable_plane(struct intel_plane *plane, } static bool -ivb_plane_get_hw_state(struct intel_plane *plane, - enum pipe *pipe) +ivb_sprite_get_hw_state(struct intel_plane *plane, + enum pipe *pipe) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum intel_display_power_domain power_domain; @@ -1106,7 +1126,7 @@ static u32 g4x_sprite_ctl(const struct intel_crtc_state *crtc_state, return dvscntr; } -static void g4x_update_gamma(const struct intel_plane_state *plane_state) +static void g4x_sprite_update_gamma(const struct intel_plane_state *plane_state) { struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); struct drm_i915_private *dev_priv = to_i915(plane->base.dev); @@ -1136,7 +1156,7 @@ static void ilk_sprite_linear_gamma(u16 gamma[17]) gamma[i] = (i << 10) / 16; } -static void ilk_update_gamma(const struct intel_plane_state *plane_state) +static void ilk_sprite_update_gamma(const struct intel_plane_state *plane_state) { struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); struct drm_i915_private *dev_priv = to_i915(plane->base.dev); @@ -1163,47 +1183,55 @@ static void ilk_update_gamma(const struct intel_plane_state *plane_state) } static void -g4x_update_plane(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state, - const struct intel_plane_state *plane_state) +g4x_sprite_update_noarm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum pipe pipe = plane->pipe; - u32 dvssurf_offset = plane_state->view.color_plane[0].offset; - u32 linear_offset; - const struct drm_intel_sprite_colorkey *key = &plane_state->ckey; int crtc_x = plane_state->uapi.dst.x1; int crtc_y = plane_state->uapi.dst.y1; u32 crtc_w = drm_rect_width(&plane_state->uapi.dst); u32 crtc_h = drm_rect_height(&plane_state->uapi.dst); - u32 x = plane_state->view.color_plane[0].x; - u32 y = plane_state->view.color_plane[0].y; u32 src_w = drm_rect_width(&plane_state->uapi.src) >> 16; u32 src_h = drm_rect_height(&plane_state->uapi.src) >> 16; - u32 dvscntr, dvsscale = 0; + u32 dvsscale = 0; unsigned long irqflags; - dvscntr = plane_state->ctl | g4x_sprite_ctl_crtc(crtc_state); - - /* Sizes are 0 based */ - src_w--; - src_h--; - crtc_w--; - crtc_h--; - if (crtc_w != src_w || crtc_h != src_h) - dvsscale = DVS_SCALE_ENABLE | (src_w << 16) | src_h; - - linear_offset = intel_fb_xy_to_linear(x, y, plane_state, 0); + dvsscale = DVS_SCALE_ENABLE | ((src_w - 1) << 16) | (src_h - 1); spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); intel_de_write_fw(dev_priv, DVSSTRIDE(pipe), - plane_state->view.color_plane[0].stride); + plane_state->view.color_plane[0].mapping_stride); intel_de_write_fw(dev_priv, DVSPOS(pipe), (crtc_y << 16) | crtc_x); - intel_de_write_fw(dev_priv, DVSSIZE(pipe), (crtc_h << 16) | crtc_w); + intel_de_write_fw(dev_priv, DVSSIZE(pipe), ((crtc_h - 1) << 16) | (crtc_w - 1)); intel_de_write_fw(dev_priv, DVSSCALE(pipe), dvsscale); + spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); +} + +static void +g4x_sprite_update_arm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) +{ + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + enum pipe pipe = plane->pipe; + const struct drm_intel_sprite_colorkey *key = &plane_state->ckey; + u32 dvssurf_offset = plane_state->view.color_plane[0].offset; + u32 x = plane_state->view.color_plane[0].x; + u32 y = plane_state->view.color_plane[0].y; + u32 dvscntr, linear_offset; + unsigned long irqflags; + + dvscntr = plane_state->ctl | g4x_sprite_ctl_crtc(crtc_state); + + linear_offset = intel_fb_xy_to_linear(x, y, plane_state, 0); + + spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); + if (key->flags) { intel_de_write_fw(dev_priv, DVSKEYVAL(pipe), key->min_value); intel_de_write_fw(dev_priv, DVSKEYMSK(pipe), @@ -1224,16 +1252,16 @@ g4x_update_plane(struct intel_plane *plane, intel_plane_ggtt_offset(plane_state) + dvssurf_offset); if (IS_G4X(dev_priv)) - g4x_update_gamma(plane_state); + g4x_sprite_update_gamma(plane_state); else - ilk_update_gamma(plane_state); + ilk_sprite_update_gamma(plane_state); spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); } static void -g4x_disable_plane(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state) +g4x_sprite_disable_arm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum pipe pipe = plane->pipe; @@ -1250,8 +1278,8 @@ g4x_disable_plane(struct intel_plane *plane, } static bool -g4x_plane_get_hw_state(struct intel_plane *plane, - enum pipe *pipe) +g4x_sprite_get_hw_state(struct intel_plane *plane, + enum pipe *pipe) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum intel_display_power_domain power_domain; @@ -1299,7 +1327,7 @@ g4x_sprite_check_scaling(struct intel_crtc_state *crtc_state, int src_x, src_w, src_h, crtc_w, crtc_h; const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode; - unsigned int stride = plane_state->view.color_plane[0].stride; + unsigned int stride = plane_state->view.color_plane[0].mapping_stride; unsigned int cpp = fb->format->cpp[0]; unsigned int width_bytes; int min_width, min_height; @@ -1540,8 +1568,8 @@ int intel_sprite_set_colorkey_ioctl(struct drm_device *dev, void *data, */ if (!ret && has_dst_key_in_primary_plane(dev_priv)) { struct intel_crtc *crtc = - intel_get_crtc_for_pipe(dev_priv, - to_intel_plane(plane)->pipe); + intel_crtc_for_pipe(dev_priv, + to_intel_plane(plane)->pipe); plane_state = drm_atomic_get_plane_state(state, crtc->base.primary); @@ -1567,7 +1595,7 @@ out: return ret; } -static const u32 g4x_plane_formats[] = { +static const u32 g4x_sprite_formats[] = { DRM_FORMAT_XRGB8888, DRM_FORMAT_YUYV, DRM_FORMAT_YVYU, @@ -1575,13 +1603,7 @@ static const u32 g4x_plane_formats[] = { DRM_FORMAT_VYUY, }; -static const u64 i9xx_plane_format_modifiers[] = { - I915_FORMAT_MOD_X_TILED, - DRM_FORMAT_MOD_LINEAR, - DRM_FORMAT_MOD_INVALID -}; - -static const u32 snb_plane_formats[] = { +static const u32 snb_sprite_formats[] = { DRM_FORMAT_XRGB8888, DRM_FORMAT_XBGR8888, DRM_FORMAT_XRGB2101010, @@ -1594,7 +1616,7 @@ static const u32 snb_plane_formats[] = { DRM_FORMAT_VYUY, }; -static const u32 vlv_plane_formats[] = { +static const u32 vlv_sprite_formats[] = { DRM_FORMAT_C8, DRM_FORMAT_RGB565, DRM_FORMAT_XRGB8888, @@ -1629,13 +1651,8 @@ static const u32 chv_pipe_b_sprite_formats[] = { static bool g4x_sprite_format_mod_supported(struct drm_plane *_plane, u32 format, u64 modifier) { - switch (modifier) { - case DRM_FORMAT_MOD_LINEAR: - case I915_FORMAT_MOD_X_TILED: - break; - default: + if (!intel_fb_plane_supports_modifier(to_intel_plane(_plane), modifier)) return false; - } switch (format) { case DRM_FORMAT_XRGB8888: @@ -1655,13 +1672,8 @@ static bool g4x_sprite_format_mod_supported(struct drm_plane *_plane, static bool snb_sprite_format_mod_supported(struct drm_plane *_plane, u32 format, u64 modifier) { - switch (modifier) { - case DRM_FORMAT_MOD_LINEAR: - case I915_FORMAT_MOD_X_TILED: - break; - default: + if (!intel_fb_plane_supports_modifier(to_intel_plane(_plane), modifier)) return false; - } switch (format) { case DRM_FORMAT_XRGB8888: @@ -1686,13 +1698,8 @@ static bool snb_sprite_format_mod_supported(struct drm_plane *_plane, static bool vlv_sprite_format_mod_supported(struct drm_plane *_plane, u32 format, u64 modifier) { - switch (modifier) { - case DRM_FORMAT_MOD_LINEAR: - case I915_FORMAT_MOD_X_TILED: - break; - default: + if (!intel_fb_plane_supports_modifier(to_intel_plane(_plane), modifier)) return false; - } switch (format) { case DRM_FORMAT_C8: @@ -1762,9 +1769,10 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv, return plane; if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { - plane->update_plane = vlv_update_plane; - plane->disable_plane = vlv_disable_plane; - plane->get_hw_state = vlv_plane_get_hw_state; + plane->update_noarm = vlv_sprite_update_noarm; + plane->update_arm = vlv_sprite_update_arm; + plane->disable_arm = vlv_sprite_disable_arm; + plane->get_hw_state = vlv_sprite_get_hw_state; plane->check_plane = vlv_sprite_check; plane->max_stride = i965_plane_max_stride; plane->min_cdclk = vlv_plane_min_cdclk; @@ -1773,16 +1781,16 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv, formats = chv_pipe_b_sprite_formats; num_formats = ARRAY_SIZE(chv_pipe_b_sprite_formats); } else { - formats = vlv_plane_formats; - num_formats = ARRAY_SIZE(vlv_plane_formats); + formats = vlv_sprite_formats; + num_formats = ARRAY_SIZE(vlv_sprite_formats); } - modifiers = i9xx_plane_format_modifiers; plane_funcs = &vlv_sprite_funcs; } else if (DISPLAY_VER(dev_priv) >= 7) { - plane->update_plane = ivb_update_plane; - plane->disable_plane = ivb_disable_plane; - plane->get_hw_state = ivb_plane_get_hw_state; + plane->update_noarm = ivb_sprite_update_noarm; + plane->update_arm = ivb_sprite_update_arm; + plane->disable_arm = ivb_sprite_disable_arm; + plane->get_hw_state = ivb_sprite_get_hw_state; plane->check_plane = g4x_sprite_check; if (IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) { @@ -1793,28 +1801,27 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv, plane->min_cdclk = ivb_sprite_min_cdclk; } - formats = snb_plane_formats; - num_formats = ARRAY_SIZE(snb_plane_formats); - modifiers = i9xx_plane_format_modifiers; + formats = snb_sprite_formats; + num_formats = ARRAY_SIZE(snb_sprite_formats); plane_funcs = &snb_sprite_funcs; } else { - plane->update_plane = g4x_update_plane; - plane->disable_plane = g4x_disable_plane; - plane->get_hw_state = g4x_plane_get_hw_state; + plane->update_noarm = g4x_sprite_update_noarm; + plane->update_arm = g4x_sprite_update_arm; + plane->disable_arm = g4x_sprite_disable_arm; + plane->get_hw_state = g4x_sprite_get_hw_state; plane->check_plane = g4x_sprite_check; plane->max_stride = g4x_sprite_max_stride; plane->min_cdclk = g4x_sprite_min_cdclk; - modifiers = i9xx_plane_format_modifiers; if (IS_SANDYBRIDGE(dev_priv)) { - formats = snb_plane_formats; - num_formats = ARRAY_SIZE(snb_plane_formats); + formats = snb_sprite_formats; + num_formats = ARRAY_SIZE(snb_sprite_formats); plane_funcs = &snb_sprite_funcs; } else { - formats = g4x_plane_formats; - num_formats = ARRAY_SIZE(g4x_plane_formats); + formats = g4x_sprite_formats; + num_formats = ARRAY_SIZE(g4x_sprite_formats); plane_funcs = &g4x_sprite_funcs; } @@ -1833,11 +1840,15 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv, plane->id = PLANE_SPRITE0 + sprite; plane->frontbuffer_bit = INTEL_FRONTBUFFER(pipe, plane->id); + modifiers = intel_fb_plane_get_modifiers(dev_priv, INTEL_PLANE_CAP_TILING_X); + ret = drm_universal_plane_init(&dev_priv->drm, &plane->base, 0, plane_funcs, formats, num_formats, modifiers, DRM_PLANE_TYPE_OVERLAY, "sprite %c", sprite_name(pipe, sprite)); + kfree(modifiers); + if (ret) goto fail; diff --git a/drivers/gpu/drm/i915/display/intel_sprite.h b/drivers/gpu/drm/i915/display/intel_sprite.h index c085eb87705c..4f63e4967731 100644 --- a/drivers/gpu/drm/i915/display/intel_sprite.h +++ b/drivers/gpu/drm/i915/display/intel_sprite.h @@ -27,14 +27,10 @@ struct intel_plane_state; #define VBLANK_EVASION_TIME_US 100 #endif -int intel_usecs_to_scanlines(const struct drm_display_mode *adjusted_mode, - int usecs); struct intel_plane *intel_sprite_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe, int plane); int intel_sprite_set_colorkey_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); -void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state); -void intel_pipe_update_end(struct intel_crtc_state *new_crtc_state); int intel_plane_check_src_coordinates(struct intel_plane_state *plane_state); int chv_plane_check_rotation(const struct intel_plane_state *plane_state); diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c index 88a398df9621..8a39989b87ad 100644 --- a/drivers/gpu/drm/i915/display/intel_tv.c +++ b/drivers/gpu/drm/i915/display/intel_tv.c @@ -36,6 +36,7 @@ #include "i915_drv.h" #include "intel_connector.h" +#include "intel_crtc.h" #include "intel_de.h" #include "intel_display_types.h" #include "intel_hotplug.h" @@ -924,8 +925,7 @@ intel_enable_tv(struct intel_atomic_state *state, struct drm_i915_private *dev_priv = to_i915(dev); /* Prevents vblank waits from timing out in intel_tv_detect_type() */ - intel_wait_for_vblank(dev_priv, - to_intel_crtc(pipe_config->uapi.crtc)->pipe); + intel_crtc_wait_for_next_vblank(to_intel_crtc(pipe_config->uapi.crtc)); intel_de_write(dev_priv, TV_CTL, intel_de_read(dev_priv, TV_CTL) | TV_ENC_ENABLE); @@ -1618,7 +1618,7 @@ intel_tv_detect_type(struct intel_tv *intel_tv, intel_de_write(dev_priv, TV_DAC, tv_dac); intel_de_posting_read(dev_priv, TV_DAC); - intel_wait_for_vblank(dev_priv, crtc->pipe); + intel_crtc_wait_for_next_vblank(crtc); type = -1; tv_dac = intel_de_read(dev_priv, TV_DAC); @@ -1651,7 +1651,7 @@ intel_tv_detect_type(struct intel_tv *intel_tv, intel_de_posting_read(dev_priv, TV_CTL); /* For unknown reasons the hw barfs if we don't do this vblank wait. */ - intel_wait_for_vblank(dev_priv, crtc->pipe); + intel_crtc_wait_for_next_vblank(crtc); /* Restore interrupt config */ if (connector->polled & DRM_CONNECTOR_POLL_HPD) { diff --git a/drivers/gpu/drm/i915/display/intel_vbt_defs.h b/drivers/gpu/drm/i915/display/intel_vbt_defs.h index a2108a8f544d..f043d85ba64d 100644 --- a/drivers/gpu/drm/i915/display/intel_vbt_defs.h +++ b/drivers/gpu/drm/i915/display/intel_vbt_defs.h @@ -330,7 +330,12 @@ enum vbt_gmbus_ddi { ADLS_DDC_BUS_PORT_TC1 = 0x2, ADLS_DDC_BUS_PORT_TC2, ADLS_DDC_BUS_PORT_TC3, - ADLS_DDC_BUS_PORT_TC4 + ADLS_DDC_BUS_PORT_TC4, + ADLP_DDC_BUS_PORT_TC1 = 0x3, + ADLP_DDC_BUS_PORT_TC2, + ADLP_DDC_BUS_PORT_TC3, + ADLP_DDC_BUS_PORT_TC4 + }; #define DP_AUX_A 0x40 diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.c b/drivers/gpu/drm/i915/display/intel_vdsc.c index 2275f99ce9d7..9b05f93ed8bc 100644 --- a/drivers/gpu/drm/i915/display/intel_vdsc.c +++ b/drivers/gpu/drm/i915/display/intel_vdsc.c @@ -6,12 +6,14 @@ * Manasi Navare <manasi.d.navare@intel.com> */ #include <linux/limits.h> + #include "i915_drv.h" +#include "intel_crtc.h" #include "intel_de.h" #include "intel_display_types.h" #include "intel_dsi.h" -#include "intel_vdsc.h" #include "intel_qp_tables.h" +#include "intel_vdsc.h" enum ROW_INDEX_BPP { ROW_INDEX_6BPP = 0, @@ -442,10 +444,10 @@ calculate_rc_params(struct rc_parameters *rc, } } -int intel_dsc_compute_params(struct intel_encoder *encoder, - struct intel_crtc_state *pipe_config) +int intel_dsc_compute_params(struct intel_crtc_state *pipe_config) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc); + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); struct drm_dsc_config *vdsc_cfg = &pipe_config->dsc.config; u16 compressed_bpp = pipe_config->dsc.compressed_bpp; const struct rc_parameters *rc_params; @@ -598,7 +600,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) pps_val |= DSC_422_ENABLE; if (vdsc_cfg->vbr_enable) pps_val |= DSC_VBR_ENABLE; - drm_info(&dev_priv->drm, "PPS0 = 0x%08x\n", pps_val); + drm_dbg_kms(&dev_priv->drm, "PPS0 = 0x%08x\n", pps_val); if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_0, pps_val); @@ -622,7 +624,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) /* Populate PICTURE_PARAMETER_SET_1 registers */ pps_val = 0; pps_val |= DSC_BPP(vdsc_cfg->bits_per_pixel); - drm_info(&dev_priv->drm, "PPS1 = 0x%08x\n", pps_val); + drm_dbg_kms(&dev_priv->drm, "PPS1 = 0x%08x\n", pps_val); if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_1, pps_val); @@ -647,7 +649,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) pps_val = 0; pps_val |= DSC_PIC_HEIGHT(vdsc_cfg->pic_height) | DSC_PIC_WIDTH(vdsc_cfg->pic_width / num_vdsc_instances); - drm_info(&dev_priv->drm, "PPS2 = 0x%08x\n", pps_val); + drm_dbg_kms(&dev_priv->drm, "PPS2 = 0x%08x\n", pps_val); if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_2, pps_val); @@ -672,7 +674,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) pps_val = 0; pps_val |= DSC_SLICE_HEIGHT(vdsc_cfg->slice_height) | DSC_SLICE_WIDTH(vdsc_cfg->slice_width); - drm_info(&dev_priv->drm, "PPS3 = 0x%08x\n", pps_val); + drm_dbg_kms(&dev_priv->drm, "PPS3 = 0x%08x\n", pps_val); if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_3, pps_val); @@ -697,7 +699,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) pps_val = 0; pps_val |= DSC_INITIAL_XMIT_DELAY(vdsc_cfg->initial_xmit_delay) | DSC_INITIAL_DEC_DELAY(vdsc_cfg->initial_dec_delay); - drm_info(&dev_priv->drm, "PPS4 = 0x%08x\n", pps_val); + drm_dbg_kms(&dev_priv->drm, "PPS4 = 0x%08x\n", pps_val); if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_4, pps_val); @@ -722,7 +724,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) pps_val = 0; pps_val |= DSC_SCALE_INC_INT(vdsc_cfg->scale_increment_interval) | DSC_SCALE_DEC_INT(vdsc_cfg->scale_decrement_interval); - drm_info(&dev_priv->drm, "PPS5 = 0x%08x\n", pps_val); + drm_dbg_kms(&dev_priv->drm, "PPS5 = 0x%08x\n", pps_val); if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_5, pps_val); @@ -749,7 +751,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) DSC_FIRST_LINE_BPG_OFFSET(vdsc_cfg->first_line_bpg_offset) | DSC_FLATNESS_MIN_QP(vdsc_cfg->flatness_min_qp) | DSC_FLATNESS_MAX_QP(vdsc_cfg->flatness_max_qp); - drm_info(&dev_priv->drm, "PPS6 = 0x%08x\n", pps_val); + drm_dbg_kms(&dev_priv->drm, "PPS6 = 0x%08x\n", pps_val); if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_6, pps_val); @@ -774,7 +776,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) pps_val = 0; pps_val |= DSC_SLICE_BPG_OFFSET(vdsc_cfg->slice_bpg_offset) | DSC_NFL_BPG_OFFSET(vdsc_cfg->nfl_bpg_offset); - drm_info(&dev_priv->drm, "PPS7 = 0x%08x\n", pps_val); + drm_dbg_kms(&dev_priv->drm, "PPS7 = 0x%08x\n", pps_val); if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_7, pps_val); @@ -799,7 +801,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) pps_val = 0; pps_val |= DSC_FINAL_OFFSET(vdsc_cfg->final_offset) | DSC_INITIAL_OFFSET(vdsc_cfg->initial_offset); - drm_info(&dev_priv->drm, "PPS8 = 0x%08x\n", pps_val); + drm_dbg_kms(&dev_priv->drm, "PPS8 = 0x%08x\n", pps_val); if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_8, pps_val); @@ -824,7 +826,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) pps_val = 0; pps_val |= DSC_RC_MODEL_SIZE(vdsc_cfg->rc_model_size) | DSC_RC_EDGE_FACTOR(DSC_RC_EDGE_FACTOR_CONST); - drm_info(&dev_priv->drm, "PPS9 = 0x%08x\n", pps_val); + drm_dbg_kms(&dev_priv->drm, "PPS9 = 0x%08x\n", pps_val); if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_9, pps_val); @@ -851,7 +853,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) DSC_RC_QUANT_INC_LIMIT1(vdsc_cfg->rc_quant_incr_limit1) | DSC_RC_TARGET_OFF_HIGH(DSC_RC_TGT_OFFSET_HI_CONST) | DSC_RC_TARGET_OFF_LOW(DSC_RC_TGT_OFFSET_LO_CONST); - drm_info(&dev_priv->drm, "PPS10 = 0x%08x\n", pps_val); + drm_dbg_kms(&dev_priv->drm, "PPS10 = 0x%08x\n", pps_val); if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_10, pps_val); @@ -879,7 +881,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) vdsc_cfg->slice_width) | DSC_SLICE_ROW_PER_FRAME(vdsc_cfg->pic_height / vdsc_cfg->slice_height); - drm_info(&dev_priv->drm, "PPS16 = 0x%08x\n", pps_val); + drm_dbg_kms(&dev_priv->drm, "PPS16 = 0x%08x\n", pps_val); if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_16, pps_val); @@ -906,8 +908,8 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) rc_buf_thresh_dword[i / 4] |= (u32)(vdsc_cfg->rc_buf_thresh[i] << BITS_PER_BYTE * (i % 4)); - drm_info(&dev_priv->drm, " RC_BUF_THRESH%d = 0x%08x\n", i, - rc_buf_thresh_dword[i / 4]); + drm_dbg_kms(&dev_priv->drm, "RC_BUF_THRESH_%d = 0x%08x\n", i, + rc_buf_thresh_dword[i / 4]); } if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_RC_BUF_THRESH_0, @@ -963,8 +965,8 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) RC_MAX_QP_SHIFT) | (vdsc_cfg->rc_range_params[i].range_min_qp << RC_MIN_QP_SHIFT)) << 16 * (i % 2)); - drm_info(&dev_priv->drm, " RC_RANGE_PARAM_%d = 0x%08x\n", i, - rc_range_params_dword[i / 2]); + drm_dbg_kms(&dev_priv->drm, "RC_RANGE_PARAM_%d = 0x%08x\n", i, + rc_range_params_dword[i / 2]); } if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_RC_RANGE_PARAMETERS_0, @@ -1055,8 +1057,8 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) } } -static void intel_dsc_dsi_pps_write(struct intel_encoder *encoder, - const struct intel_crtc_state *crtc_state) +void intel_dsc_dsi_pps_write(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state) { const struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config; struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder); @@ -1064,6 +1066,9 @@ static void intel_dsc_dsi_pps_write(struct intel_encoder *encoder, struct drm_dsc_picture_parameter_set pps; enum port port; + if (!crtc_state->dsc.compression_enable) + return; + drm_dsc_pps_payload_pack(&pps, vdsc_cfg); for_each_dsi_port(port, intel_dsi->ports) { @@ -1074,14 +1079,16 @@ static void intel_dsc_dsi_pps_write(struct intel_encoder *encoder, } } -static void intel_dsc_dp_pps_write(struct intel_encoder *encoder, - const struct intel_crtc_state *crtc_state) +void intel_dsc_dp_pps_write(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state) { - struct intel_dp *intel_dp = enc_to_intel_dp(encoder); - struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); + struct intel_digital_port *dig_port = enc_to_dig_port(encoder); const struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config; struct drm_dsc_pps_infoframe dp_dsc_pps_sdp; + if (!crtc_state->dsc.compression_enable) + return; + /* Prepare DP SDP PPS header as per DP 1.4 spec, Table 2-123 */ drm_dsc_dp_pps_header_init(&dp_dsc_pps_sdp.pps_header); @@ -1105,25 +1112,16 @@ static i915_reg_t dss_ctl2_reg(struct intel_crtc *crtc, enum transcoder cpu_tran ICL_PIPE_DSS_CTL2(crtc->pipe) : DSS_CTL2; } -static struct intel_crtc * -_get_crtc_for_pipe(struct drm_i915_private *i915, enum pipe pipe) -{ - if (!intel_pipe_valid(i915, pipe)) - return NULL; - - return intel_get_crtc_for_pipe(i915, pipe); -} - struct intel_crtc * intel_dsc_get_bigjoiner_secondary(const struct intel_crtc *primary_crtc) { - return _get_crtc_for_pipe(to_i915(primary_crtc->base.dev), primary_crtc->pipe + 1); + return intel_crtc_for_pipe(to_i915(primary_crtc->base.dev), primary_crtc->pipe + 1); } static struct intel_crtc * intel_dsc_get_bigjoiner_primary(const struct intel_crtc *secondary_crtc) { - return _get_crtc_for_pipe(to_i915(secondary_crtc->base.dev), secondary_crtc->pipe - 1); + return intel_crtc_for_pipe(to_i915(secondary_crtc->base.dev), secondary_crtc->pipe - 1); } void intel_uncompressed_joiner_enable(const struct intel_crtc_state *crtc_state) @@ -1142,8 +1140,7 @@ void intel_uncompressed_joiner_enable(const struct intel_crtc_state *crtc_state) } } -void intel_dsc_enable(struct intel_encoder *encoder, - const struct intel_crtc_state *crtc_state) +void intel_dsc_enable(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); @@ -1155,13 +1152,6 @@ void intel_dsc_enable(struct intel_encoder *encoder, intel_dsc_pps_configure(crtc_state); - if (!crtc_state->bigjoiner_slave) { - if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI)) - intel_dsc_dsi_pps_write(encoder, crtc_state); - else - intel_dsc_dp_pps_write(encoder, crtc_state); - } - dss_ctl2_val |= LEFT_BRANCH_VDSC_ENABLE; if (crtc_state->dsc.dsc_split) { dss_ctl2_val |= RIGHT_BRANCH_VDSC_ENABLE; diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.h b/drivers/gpu/drm/i915/display/intel_vdsc.h index 0c5d80a572da..4ec75f715986 100644 --- a/drivers/gpu/drm/i915/display/intel_vdsc.h +++ b/drivers/gpu/drm/i915/display/intel_vdsc.h @@ -15,15 +15,17 @@ struct intel_encoder; bool intel_dsc_source_support(const struct intel_crtc_state *crtc_state); void intel_uncompressed_joiner_enable(const struct intel_crtc_state *crtc_state); -void intel_dsc_enable(struct intel_encoder *encoder, - const struct intel_crtc_state *crtc_state); +void intel_dsc_enable(const struct intel_crtc_state *crtc_state); void intel_dsc_disable(const struct intel_crtc_state *crtc_state); -int intel_dsc_compute_params(struct intel_encoder *encoder, - struct intel_crtc_state *pipe_config); +int intel_dsc_compute_params(struct intel_crtc_state *pipe_config); void intel_uncompressed_joiner_get_config(struct intel_crtc_state *crtc_state); void intel_dsc_get_config(struct intel_crtc_state *crtc_state); enum intel_display_power_domain intel_dsc_power_domain(struct intel_crtc *crtc, enum transcoder cpu_transcoder); struct intel_crtc *intel_dsc_get_bigjoiner_secondary(const struct intel_crtc *primary_crtc); +void intel_dsc_dsi_pps_write(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state); +void intel_dsc_dp_pps_write(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state); #endif /* __INTEL_VDSC_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_vrr.c b/drivers/gpu/drm/i915/display/intel_vrr.c index c335b1dbafcf..139e8936edc5 100644 --- a/drivers/gpu/drm/i915/display/intel_vrr.c +++ b/drivers/gpu/drm/i915/display/intel_vrr.c @@ -60,7 +60,7 @@ intel_vrr_check_modeset(struct intel_atomic_state *state) * Between those two points the vblank exit starts (and hence registers get * latched) ASAP after a push is sent. * - * framestart_delay is programmable 0-3. + * framestart_delay is programmable 1-4. */ static int intel_vrr_vblank_exit_length(const struct intel_crtc_state *crtc_state) { @@ -138,13 +138,13 @@ intel_vrr_compute_config(struct intel_crtc_state *crtc_state, i915->window2_delay; else /* - * FIXME: s/4/framestart_delay+1/ to get consistent + * FIXME: s/4/framestart_delay/ to get consistent * earliest/latest points for register latching regardless * of the framestart_delay used? * * FIXME: this really needs the extra scanline to provide consistent * behaviour for all framestart_delay values. Otherwise with - * framestart_delay==3 we will end up extending the min vblank by + * framestart_delay==4 we will end up extending the min vblank by * one extra line. */ crtc_state->vrr.pipeline_full = @@ -193,6 +193,18 @@ void intel_vrr_send_push(const struct intel_crtc_state *crtc_state) TRANS_PUSH_EN | TRANS_PUSH_SEND); } +bool intel_vrr_is_push_sent(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 transcoder cpu_transcoder = crtc_state->cpu_transcoder; + + if (!crtc_state->vrr.enable) + return false; + + return intel_de_read(dev_priv, TRANS_PUSH(cpu_transcoder)) & TRANS_PUSH_SEND; +} + void intel_vrr_disable(const struct intel_crtc_state *old_crtc_state) { struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc); diff --git a/drivers/gpu/drm/i915/display/intel_vrr.h b/drivers/gpu/drm/i915/display/intel_vrr.h index 96f9c9c27ab9..1c2da572693d 100644 --- a/drivers/gpu/drm/i915/display/intel_vrr.h +++ b/drivers/gpu/drm/i915/display/intel_vrr.h @@ -23,6 +23,7 @@ void intel_vrr_compute_config(struct intel_crtc_state *crtc_state, void intel_vrr_enable(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state); void intel_vrr_send_push(const struct intel_crtc_state *crtc_state); +bool intel_vrr_is_push_sent(const struct intel_crtc_state *crtc_state); void intel_vrr_disable(const struct intel_crtc_state *old_crtc_state); void intel_vrr_get_config(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state); diff --git a/drivers/gpu/drm/i915/display/skl_scaler.c b/drivers/gpu/drm/i915/display/skl_scaler.c index 37eabeff8197..c2e94118566b 100644 --- a/drivers/gpu/drm/i915/display/skl_scaler.c +++ b/drivers/gpu/drm/i915/display/skl_scaler.c @@ -4,6 +4,7 @@ */ #include "intel_de.h" #include "intel_display_types.h" +#include "intel_fb.h" #include "skl_scaler.h" #include "skl_universal_plane.h" diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c index a0e53a3b267a..93a385396512 100644 --- a/drivers/gpu/drm/i915/display/skl_universal_plane.c +++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c @@ -13,6 +13,7 @@ #include "intel_de.h" #include "intel_display_types.h" #include "intel_fb.h" +#include "intel_fbc.h" #include "intel_pm.h" #include "intel_psr.h" #include "intel_sprite.h" @@ -163,50 +164,6 @@ static const u32 icl_hdr_plane_formats[] = { DRM_FORMAT_XVYU16161616, }; -static const u64 skl_plane_format_modifiers_noccs[] = { - I915_FORMAT_MOD_Yf_TILED, - I915_FORMAT_MOD_Y_TILED, - I915_FORMAT_MOD_X_TILED, - DRM_FORMAT_MOD_LINEAR, - DRM_FORMAT_MOD_INVALID -}; - -static const u64 skl_plane_format_modifiers_ccs[] = { - I915_FORMAT_MOD_Yf_TILED_CCS, - I915_FORMAT_MOD_Y_TILED_CCS, - I915_FORMAT_MOD_Yf_TILED, - I915_FORMAT_MOD_Y_TILED, - I915_FORMAT_MOD_X_TILED, - DRM_FORMAT_MOD_LINEAR, - DRM_FORMAT_MOD_INVALID -}; - -static const u64 gen12_plane_format_modifiers_mc_ccs[] = { - I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS, - I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS, - I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC, - I915_FORMAT_MOD_Y_TILED, - I915_FORMAT_MOD_X_TILED, - DRM_FORMAT_MOD_LINEAR, - DRM_FORMAT_MOD_INVALID -}; - -static const u64 gen12_plane_format_modifiers_rc_ccs[] = { - I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS, - I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC, - I915_FORMAT_MOD_Y_TILED, - I915_FORMAT_MOD_X_TILED, - DRM_FORMAT_MOD_LINEAR, - DRM_FORMAT_MOD_INVALID -}; - -static const u64 adlp_step_a_plane_format_modifiers[] = { - I915_FORMAT_MOD_Y_TILED, - I915_FORMAT_MOD_X_TILED, - DRM_FORMAT_MOD_LINEAR, - DRM_FORMAT_MOD_INVALID -}; - int skl_format_to_fourcc(int format, bool rgb_order, bool alpha) { switch (format) { @@ -464,9 +421,19 @@ static int icl_plane_min_width(const struct drm_framebuffer *fb, } } -static int icl_plane_max_width(const struct drm_framebuffer *fb, - int color_plane, - unsigned int rotation) +static int icl_hdr_plane_max_width(const struct drm_framebuffer *fb, + int color_plane, + unsigned int rotation) +{ + if (intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier)) + return 4096; + else + return 5120; +} + +static int icl_sdr_plane_max_width(const struct drm_framebuffer *fb, + int color_plane, + unsigned int rotation) { return 5120; } @@ -633,7 +600,7 @@ static u32 skl_plane_stride(const struct intel_plane_state *plane_state, { const struct drm_framebuffer *fb = plane_state->hw.fb; unsigned int rotation = plane_state->hw.rotation; - u32 stride = plane_state->view.color_plane[color_plane].stride; + u32 stride = plane_state->view.color_plane[color_plane].scanout_stride; if (color_plane >= fb->format->num_planes) return 0; @@ -642,8 +609,8 @@ static u32 skl_plane_stride(const struct intel_plane_state *plane_state, } static void -skl_disable_plane(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state) +skl_plane_disable_arm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum plane_id plane_id = plane->id; @@ -716,13 +683,13 @@ static u32 skl_plane_ctl_format(u32 pixel_format) case DRM_FORMAT_XYUV8888: return PLANE_CTL_FORMAT_XYUV; case DRM_FORMAT_YUYV: - return PLANE_CTL_FORMAT_YUV422 | PLANE_CTL_YUV422_YUYV; + return PLANE_CTL_FORMAT_YUV422 | PLANE_CTL_YUV422_ORDER_YUYV; case DRM_FORMAT_YVYU: - return PLANE_CTL_FORMAT_YUV422 | PLANE_CTL_YUV422_YVYU; + return PLANE_CTL_FORMAT_YUV422 | PLANE_CTL_YUV422_ORDER_YVYU; case DRM_FORMAT_UYVY: - return PLANE_CTL_FORMAT_YUV422 | PLANE_CTL_YUV422_UYVY; + return PLANE_CTL_FORMAT_YUV422 | PLANE_CTL_YUV422_ORDER_UYVY; case DRM_FORMAT_VYUY: - return PLANE_CTL_FORMAT_YUV422 | PLANE_CTL_YUV422_VYUY; + return PLANE_CTL_FORMAT_YUV422 | PLANE_CTL_YUV422_ORDER_VYUY; case DRM_FORMAT_NV12: return PLANE_CTL_FORMAT_NV12; case DRM_FORMAT_P010: @@ -985,6 +952,9 @@ static u32 glk_plane_color_ctl(const struct intel_crtc_state *crtc_state, plane_color_ctl |= PLANE_COLOR_YUV_RANGE_CORRECTION_DISABLE; } + if (plane_state->force_black) + plane_color_ctl |= PLANE_COLOR_PLANE_CSC_ENABLE; + return plane_color_ctl; } @@ -1008,74 +978,60 @@ static u32 skl_surf_address(const struct intel_plane_state *plane_state, } } -static void intel_load_plane_csc_black(struct intel_plane *intel_plane) +static u32 skl_plane_surf(const struct intel_plane_state *plane_state, + int color_plane) { - struct drm_i915_private *dev_priv = to_i915(intel_plane->base.dev); - enum pipe pipe = intel_plane->pipe; - enum plane_id plane = intel_plane->id; - u16 postoff = 0; + u32 plane_surf; - drm_dbg_kms(&dev_priv->drm, "plane color CTM to black %s:%d\n", - intel_plane->base.name, plane); - intel_de_write_fw(dev_priv, PLANE_CSC_COEFF(pipe, plane, 0), 0); - intel_de_write_fw(dev_priv, PLANE_CSC_COEFF(pipe, plane, 1), 0); + plane_surf = intel_plane_ggtt_offset(plane_state) + + skl_surf_address(plane_state, color_plane); - intel_de_write_fw(dev_priv, PLANE_CSC_COEFF(pipe, plane, 2), 0); - intel_de_write_fw(dev_priv, PLANE_CSC_COEFF(pipe, plane, 3), 0); + if (plane_state->decrypt) + plane_surf |= PLANE_SURF_DECRYPT; - intel_de_write_fw(dev_priv, PLANE_CSC_COEFF(pipe, plane, 4), 0); - intel_de_write_fw(dev_priv, PLANE_CSC_COEFF(pipe, plane, 5), 0); + return plane_surf; +} - intel_de_write_fw(dev_priv, PLANE_CSC_PREOFF(pipe, plane, 0), 0); - intel_de_write_fw(dev_priv, PLANE_CSC_PREOFF(pipe, plane, 1), 0); - intel_de_write_fw(dev_priv, PLANE_CSC_PREOFF(pipe, plane, 2), 0); +static void icl_plane_csc_load_black(struct intel_plane *plane) +{ + struct drm_i915_private *i915 = to_i915(plane->base.dev); + enum plane_id plane_id = plane->id; + enum pipe pipe = plane->pipe; + + intel_de_write_fw(i915, PLANE_CSC_COEFF(pipe, plane_id, 0), 0); + intel_de_write_fw(i915, PLANE_CSC_COEFF(pipe, plane_id, 1), 0); + + intel_de_write_fw(i915, PLANE_CSC_COEFF(pipe, plane_id, 2), 0); + intel_de_write_fw(i915, PLANE_CSC_COEFF(pipe, plane_id, 3), 0); + + intel_de_write_fw(i915, PLANE_CSC_COEFF(pipe, plane_id, 4), 0); + intel_de_write_fw(i915, PLANE_CSC_COEFF(pipe, plane_id, 5), 0); - intel_de_write_fw(dev_priv, PLANE_CSC_POSTOFF(pipe, plane, 0), postoff); - intel_de_write_fw(dev_priv, PLANE_CSC_POSTOFF(pipe, plane, 1), postoff); - intel_de_write_fw(dev_priv, PLANE_CSC_POSTOFF(pipe, plane, 2), postoff); + intel_de_write_fw(i915, PLANE_CSC_PREOFF(pipe, plane_id, 0), 0); + intel_de_write_fw(i915, PLANE_CSC_PREOFF(pipe, plane_id, 1), 0); + intel_de_write_fw(i915, PLANE_CSC_PREOFF(pipe, plane_id, 2), 0); + + intel_de_write_fw(i915, PLANE_CSC_POSTOFF(pipe, plane_id, 0), 0); + intel_de_write_fw(i915, PLANE_CSC_POSTOFF(pipe, plane_id, 1), 0); + intel_de_write_fw(i915, PLANE_CSC_POSTOFF(pipe, plane_id, 2), 0); } static void -skl_program_plane(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state, - const struct intel_plane_state *plane_state, - int color_plane) +skl_program_plane_noarm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state, + int color_plane) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum plane_id plane_id = plane->id; enum pipe pipe = plane->pipe; - const struct drm_intel_sprite_colorkey *key = &plane_state->ckey; - u32 surf_addr = skl_surf_address(plane_state, color_plane); u32 stride = skl_plane_stride(plane_state, color_plane); const struct drm_framebuffer *fb = plane_state->hw.fb; - int aux_plane = skl_main_to_aux_plane(fb, color_plane); int crtc_x = plane_state->uapi.dst.x1; int crtc_y = plane_state->uapi.dst.y1; - u32 x = plane_state->view.color_plane[color_plane].x; - u32 y = plane_state->view.color_plane[color_plane].y; u32 src_w = drm_rect_width(&plane_state->uapi.src) >> 16; u32 src_h = drm_rect_height(&plane_state->uapi.src) >> 16; - u8 alpha = plane_state->hw.alpha >> 8; - u32 plane_color_ctl = 0, aux_dist = 0; unsigned long irqflags; - u32 keymsk, keymax, plane_surf; - u32 plane_ctl = plane_state->ctl; - - plane_ctl |= skl_plane_ctl_crtc(crtc_state); - - if (DISPLAY_VER(dev_priv) >= 10) - plane_color_ctl = plane_state->color_ctl | - glk_plane_color_ctl_crtc(crtc_state); - - /* Sizes are 0 based */ - src_w--; - src_h--; - - keymax = (key->max_value & 0xffffff) | PLANE_KEYMAX_ALPHA(alpha); - - keymsk = key->channel_mask & 0x7ffffff; - if (alpha < 0xff) - keymsk |= PLANE_KEYMSK_ALPHA_ENABLE; /* The scaler will handle the output position */ if (plane_state->scaler_id >= 0) { @@ -1083,40 +1039,83 @@ skl_program_plane(struct intel_plane *plane, crtc_y = 0; } - if (aux_plane) { - aux_dist = skl_surf_address(plane_state, aux_plane) - surf_addr; - - if (DISPLAY_VER(dev_priv) < 12) - aux_dist |= skl_plane_stride(plane_state, aux_plane); - } - spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); + /* + * FIXME: pxp session invalidation can hit any time even at time of commit + * or after the commit, display content will be garbage. + */ + if (plane_state->force_black) + icl_plane_csc_load_black(plane); + intel_de_write_fw(dev_priv, PLANE_STRIDE(pipe, plane_id), stride); intel_de_write_fw(dev_priv, PLANE_POS(pipe, plane_id), (crtc_y << 16) | crtc_x); intel_de_write_fw(dev_priv, PLANE_SIZE(pipe, plane_id), - (src_h << 16) | src_w); + ((src_h - 1) << 16) | (src_w - 1)); - intel_de_write_fw(dev_priv, PLANE_AUX_DIST(pipe, plane_id), aux_dist); + if (intel_fb_is_rc_ccs_cc_modifier(fb->modifier)) { + intel_de_write_fw(dev_priv, PLANE_CC_VAL(pipe, plane_id, 0), + lower_32_bits(plane_state->ccval)); + intel_de_write_fw(dev_priv, PLANE_CC_VAL(pipe, plane_id, 1), + upper_32_bits(plane_state->ccval)); + } if (icl_is_hdr_plane(dev_priv, plane_id)) intel_de_write_fw(dev_priv, PLANE_CUS_CTL(pipe, plane_id), plane_state->cus_ctl); - if (DISPLAY_VER(dev_priv) >= 10) - intel_de_write_fw(dev_priv, PLANE_COLOR_CTL(pipe, plane_id), - plane_color_ctl); - if (fb->format->is_yuv && icl_is_hdr_plane(dev_priv, plane_id)) icl_program_input_csc(plane, crtc_state, plane_state); - if (fb->modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC) - intel_uncore_write64_fw(&dev_priv->uncore, - PLANE_CC_VAL(pipe, plane_id), plane_state->ccval); - skl_write_plane_wm(plane, crtc_state); + intel_psr2_program_plane_sel_fetch(plane, crtc_state, plane_state, color_plane); + + spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); +} + +static void +skl_program_plane_arm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state, + int color_plane) +{ + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + enum plane_id plane_id = plane->id; + enum pipe pipe = plane->pipe; + const struct drm_intel_sprite_colorkey *key = &plane_state->ckey; + const struct drm_framebuffer *fb = plane_state->hw.fb; + int aux_plane = skl_main_to_aux_plane(fb, color_plane); + u32 x = plane_state->view.color_plane[color_plane].x; + u32 y = plane_state->view.color_plane[color_plane].y; + u32 keymsk, keymax, aux_dist = 0, plane_color_ctl = 0; + u8 alpha = plane_state->hw.alpha >> 8; + u32 plane_ctl = plane_state->ctl; + unsigned long irqflags; + + plane_ctl |= skl_plane_ctl_crtc(crtc_state); + + if (DISPLAY_VER(dev_priv) >= 10) + plane_color_ctl = plane_state->color_ctl | + glk_plane_color_ctl_crtc(crtc_state); + + keymax = (key->max_value & 0xffffff) | PLANE_KEYMAX_ALPHA(alpha); + + keymsk = key->channel_mask & 0x7ffffff; + if (alpha < 0xff) + keymsk |= PLANE_KEYMSK_ALPHA_ENABLE; + + if (aux_plane) { + aux_dist = skl_surf_address(plane_state, aux_plane) - + skl_surf_address(plane_state, color_plane); + + if (DISPLAY_VER(dev_priv) < 12) + aux_dist |= skl_plane_stride(plane_state, aux_plane); + } + + spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); + intel_de_write_fw(dev_priv, PLANE_KEYVAL(pipe, plane_id), key->min_value); intel_de_write_fw(dev_priv, PLANE_KEYMSK(pipe, plane_id), keymsk); @@ -1125,17 +1124,22 @@ skl_program_plane(struct intel_plane *plane, intel_de_write_fw(dev_priv, PLANE_OFFSET(pipe, plane_id), (y << 16) | x); + intel_de_write_fw(dev_priv, PLANE_AUX_DIST(pipe, plane_id), aux_dist); + if (DISPLAY_VER(dev_priv) < 11) intel_de_write_fw(dev_priv, PLANE_AUX_OFFSET(pipe, plane_id), (plane_state->view.color_plane[1].y << 16) | plane_state->view.color_plane[1].x); - intel_psr2_program_plane_sel_fetch(plane, crtc_state, plane_state, color_plane); + if (DISPLAY_VER(dev_priv) >= 10) + intel_de_write_fw(dev_priv, PLANE_COLOR_CTL(pipe, plane_id), plane_color_ctl); /* * Enable the scaler before the plane so that we don't * get a catastrophic underrun even if the two operations * end up happening in two different frames. + * + * TODO: split into noarm+arm pair */ if (plane_state->scaler_id >= 0) skl_program_plane_scaler(plane, crtc_state, plane_state); @@ -1146,23 +1150,8 @@ skl_program_plane(struct intel_plane *plane, * the control register just before the surface register. */ intel_de_write_fw(dev_priv, PLANE_CTL(pipe, plane_id), plane_ctl); - plane_surf = intel_plane_ggtt_offset(plane_state) + surf_addr; - plane_color_ctl = intel_de_read_fw(dev_priv, PLANE_COLOR_CTL(pipe, plane_id)); - - /* - * FIXME: pxp session invalidation can hit any time even at time of commit - * or after the commit, display content will be garbage. - */ - if (plane_state->decrypt) { - plane_surf |= PLANE_SURF_DECRYPT; - } else if (plane_state->force_black) { - intel_load_plane_csc_black(plane); - plane_color_ctl |= PLANE_COLOR_PLANE_CSC_ENABLE; - } - - intel_de_write_fw(dev_priv, PLANE_COLOR_CTL(pipe, plane_id), - plane_color_ctl); - intel_de_write_fw(dev_priv, PLANE_SURF(pipe, plane_id), plane_surf); + intel_de_write_fw(dev_priv, PLANE_SURF(pipe, plane_id), + skl_plane_surf(plane_state, color_plane)); spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); } @@ -1177,7 +1166,6 @@ skl_plane_async_flip(struct intel_plane *plane, unsigned long irqflags; enum plane_id plane_id = plane->id; enum pipe pipe = plane->pipe; - u32 surf_addr = plane_state->view.color_plane[0].offset; u32 plane_ctl = plane_state->ctl; plane_ctl |= skl_plane_ctl_crtc(crtc_state); @@ -1189,15 +1177,29 @@ skl_plane_async_flip(struct intel_plane *plane, intel_de_write_fw(dev_priv, PLANE_CTL(pipe, plane_id), plane_ctl); intel_de_write_fw(dev_priv, PLANE_SURF(pipe, plane_id), - intel_plane_ggtt_offset(plane_state) + surf_addr); + skl_plane_surf(plane_state, 0)); spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); } static void -skl_update_plane(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state, - const struct intel_plane_state *plane_state) +skl_plane_update_noarm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) +{ + int color_plane = 0; + + if (plane_state->planar_linked_plane && !plane_state->planar_slave) + /* Program the UV plane on planar master */ + color_plane = 1; + + skl_program_plane_noarm(plane, crtc_state, plane_state, color_plane); +} + +static void +skl_plane_update_arm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) { int color_plane = 0; @@ -1205,7 +1207,7 @@ skl_update_plane(struct intel_plane *plane, /* Program the UV plane on planar master */ color_plane = 1; - skl_program_plane(plane, crtc_state, plane_state, color_plane); + skl_program_plane_arm(plane, crtc_state, plane_state, color_plane); } static bool intel_format_is_p01x(u32 format) @@ -1232,7 +1234,7 @@ static int skl_plane_check_fb(const struct intel_crtc_state *crtc_state, return 0; if (rotation & ~(DRM_MODE_ROTATE_0 | DRM_MODE_ROTATE_180) && - is_ccs_modifier(fb->modifier)) { + intel_fb_is_ccs_modifier(fb->modifier)) { drm_dbg_kms(&dev_priv->drm, "RC support only with 0/180 degree rotation (%x)\n", rotation); @@ -1284,13 +1286,8 @@ static int skl_plane_check_fb(const struct intel_crtc_state *crtc_state, /* Y-tiling is not supported in IF-ID Interlace mode */ if (crtc_state->hw.enable && crtc_state->hw.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE && - (fb->modifier == I915_FORMAT_MOD_Y_TILED || - fb->modifier == I915_FORMAT_MOD_Yf_TILED || - fb->modifier == I915_FORMAT_MOD_Y_TILED_CCS || - fb->modifier == I915_FORMAT_MOD_Yf_TILED_CCS || - fb->modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS || - fb->modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS || - fb->modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC)) { + fb->modifier != DRM_FORMAT_MOD_LINEAR && + fb->modifier != I915_FORMAT_MOD_X_TILED) { drm_dbg_kms(&dev_priv->drm, "Y/Yf tiling not supported in IF-ID mode\n"); return -EINVAL; @@ -1487,7 +1484,7 @@ int skl_calc_main_surface_offset(const struct intel_plane_state *plane_state, if (fb->modifier == I915_FORMAT_MOD_X_TILED) { int cpp = fb->format->cpp[0]; - while ((*x + w) * cpp > plane_state->view.color_plane[0].stride) { + while ((*x + w) * cpp > plane_state->view.color_plane[0].mapping_stride) { if (*offset == 0) { drm_dbg_kms(&dev_priv->drm, "Unable to find suitable display surface offset due to X-tiling\n"); @@ -1536,7 +1533,7 @@ static int skl_check_main_surface(struct intel_plane_state *plane_state) * CCS AUX surface doesn't have its own x/y offsets, we must make sure * they match with the main surface x/y offsets. */ - if (is_ccs_modifier(fb->modifier)) { + if (intel_fb_is_ccs_modifier(fb->modifier)) { while (!skl_check_main_ccs_coordinates(plane_state, x, y, offset, aux_plane)) { if (offset == 0) @@ -1600,7 +1597,7 @@ static int skl_check_nv12_aux_surface(struct intel_plane_state *plane_state) offset = intel_plane_compute_aligned_offset(&x, &y, plane_state, uv_plane); - if (is_ccs_modifier(fb->modifier)) { + if (intel_fb_is_ccs_modifier(fb->modifier)) { int ccs_plane = main_to_ccs_plane(fb, uv_plane); u32 aux_offset = plane_state->view.color_plane[ccs_plane].offset; u32 alignment = intel_surf_alignment(fb, uv_plane); @@ -1656,8 +1653,7 @@ static int skl_check_ccs_aux_surface(struct intel_plane_state *plane_state) int hsub, vsub; int x, y; - if (!is_ccs_plane(fb, ccs_plane) || - is_gen12_ccs_cc_plane(fb, ccs_plane)) + if (!intel_fb_is_ccs_aux_plane(fb, ccs_plane)) continue; intel_fb_plane_get_subsampling(&main_hsub, &main_vsub, fb, @@ -1699,7 +1695,7 @@ static int skl_check_plane_surface(struct intel_plane_state *plane_state) * Handle the AUX surface first since the main surface setup depends on * it. */ - if (is_ccs_modifier(fb->modifier)) { + if (intel_fb_is_ccs_modifier(fb->modifier)) { ret = skl_check_ccs_aux_surface(plane_state); if (ret) return ret; @@ -1737,6 +1733,18 @@ static bool skl_fb_scalable(const struct drm_framebuffer *fb) } } +static bool bo_has_valid_encryption(struct drm_i915_gem_object *obj) +{ + struct drm_i915_private *i915 = to_i915(obj->base.dev); + + return intel_pxp_key_check(&to_gt(i915)->pxp, obj, false) == 0; +} + +static bool pxp_is_borked(struct drm_i915_gem_object *obj) +{ + return i915_gem_object_is_protected(obj) && !bo_has_valid_encryption(obj); +} + static int skl_plane_check(struct intel_crtc_state *crtc_state, struct intel_plane_state *plane_state) { @@ -1781,6 +1789,11 @@ static int skl_plane_check(struct intel_crtc_state *crtc_state, if (ret) return ret; + if (DISPLAY_VER(dev_priv) >= 11) { + plane_state->decrypt = bo_has_valid_encryption(intel_fb_obj(fb)); + plane_state->force_black = pxp_is_borked(intel_fb_obj(fb)); + } + /* HW only has 8 bits pixel precision, disable plane if invisible */ if (!(plane_state->hw.alpha >> 8)) plane_state->uapi.visible = false; @@ -1812,6 +1825,15 @@ static bool skl_plane_has_fbc(struct drm_i915_private *dev_priv, return pipe == PIPE_A && plane_id == PLANE_PRIMARY; } +static struct intel_fbc *skl_plane_fbc(struct drm_i915_private *dev_priv, + enum pipe pipe, enum plane_id plane_id) +{ + if (skl_plane_has_fbc(dev_priv, pipe, plane_id)) + return dev_priv->fbc; + else + return NULL; +} + static bool skl_plane_has_planar(struct drm_i915_private *dev_priv, enum pipe pipe, enum plane_id plane_id) { @@ -1870,49 +1892,20 @@ static const u32 *icl_get_plane_formats(struct drm_i915_private *dev_priv, } } -static bool skl_plane_has_ccs(struct drm_i915_private *dev_priv, - enum pipe pipe, enum plane_id plane_id) -{ - if (plane_id == PLANE_CURSOR) - return false; - - if (DISPLAY_VER(dev_priv) >= 11) - return true; - - if (IS_GEMINILAKE(dev_priv)) - return pipe != PIPE_C; - - return pipe != PIPE_C && - (plane_id == PLANE_PRIMARY || - plane_id == PLANE_SPRITE0); -} - static bool skl_plane_format_mod_supported(struct drm_plane *_plane, u32 format, u64 modifier) { struct intel_plane *plane = to_intel_plane(_plane); - switch (modifier) { - case DRM_FORMAT_MOD_LINEAR: - case I915_FORMAT_MOD_X_TILED: - case I915_FORMAT_MOD_Y_TILED: - case I915_FORMAT_MOD_Yf_TILED: - break; - case I915_FORMAT_MOD_Y_TILED_CCS: - case I915_FORMAT_MOD_Yf_TILED_CCS: - if (!plane->has_ccs) - return false; - break; - default: + if (!intel_fb_plane_supports_modifier(plane, modifier)) return false; - } switch (format) { case DRM_FORMAT_XRGB8888: case DRM_FORMAT_XBGR8888: case DRM_FORMAT_ARGB8888: case DRM_FORMAT_ABGR8888: - if (is_ccs_modifier(modifier)) + if (intel_fb_is_ccs_modifier(modifier)) return true; fallthrough; case DRM_FORMAT_RGB565: @@ -1953,52 +1946,20 @@ static bool skl_plane_format_mod_supported(struct drm_plane *_plane, } } -static bool gen12_plane_supports_mc_ccs(struct drm_i915_private *dev_priv, - enum plane_id plane_id) -{ - /* Wa_14010477008:tgl[a0..c0],rkl[all],dg1[all] */ - if (IS_DG1(dev_priv) || IS_ROCKETLAKE(dev_priv) || - IS_TGL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_D0)) - return false; - - /* Wa_22011186057 */ - if (IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0)) - return false; - - return plane_id < PLANE_SPRITE4; -} - static bool gen12_plane_format_mod_supported(struct drm_plane *_plane, u32 format, u64 modifier) { - struct drm_i915_private *dev_priv = to_i915(_plane->dev); struct intel_plane *plane = to_intel_plane(_plane); - switch (modifier) { - case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS: - if (!gen12_plane_supports_mc_ccs(dev_priv, plane->id)) - return false; - fallthrough; - case DRM_FORMAT_MOD_LINEAR: - case I915_FORMAT_MOD_X_TILED: - case I915_FORMAT_MOD_Y_TILED: - break; - case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS: - case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC: - /* Wa_22011186057 */ - if (IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0)) - return false; - break; - default: + if (!intel_fb_plane_supports_modifier(plane, modifier)) return false; - } switch (format) { case DRM_FORMAT_XRGB8888: case DRM_FORMAT_XBGR8888: case DRM_FORMAT_ARGB8888: case DRM_FORMAT_ABGR8888: - if (is_ccs_modifier(modifier)) + if (intel_fb_is_ccs_modifier(modifier)) return true; fallthrough; case DRM_FORMAT_YUYV: @@ -2010,7 +1971,7 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane, case DRM_FORMAT_P010: case DRM_FORMAT_P012: case DRM_FORMAT_P016: - if (modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS) + if (intel_fb_is_mc_ccs_modifier(modifier)) return true; fallthrough; case DRM_FORMAT_RGB565: @@ -2039,18 +2000,6 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane, } } -static const u64 *gen12_get_plane_modifiers(struct drm_i915_private *dev_priv, - enum plane_id plane_id) -{ - /* Wa_22011186057 */ - if (IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0)) - return adlp_step_a_plane_format_modifiers; - else if (gen12_plane_supports_mc_ccs(dev_priv, plane_id)) - return gen12_plane_format_modifiers_mc_ccs; - else - return gen12_plane_format_modifiers_rc_ccs; -} - static const struct drm_plane_funcs skl_plane_funcs = { .update_plane = drm_atomic_helper_update_plane, .disable_plane = drm_atomic_helper_disable_plane, @@ -2091,6 +2040,64 @@ skl_plane_disable_flip_done(struct intel_plane *plane) spin_unlock_irq(&i915->irq_lock); } +static bool skl_plane_has_rc_ccs(struct drm_i915_private *i915, + enum pipe pipe, enum plane_id plane_id) +{ + /* Wa_22011186057 */ + if (IS_ADLP_DISPLAY_STEP(i915, STEP_A0, STEP_B0)) + return false; + + if (DISPLAY_VER(i915) >= 11) + return true; + + if (IS_GEMINILAKE(i915)) + return pipe != PIPE_C; + + return pipe != PIPE_C && + (plane_id == PLANE_PRIMARY || + plane_id == PLANE_SPRITE0); +} + +static bool gen12_plane_has_mc_ccs(struct drm_i915_private *i915, + enum plane_id plane_id) +{ + if (DISPLAY_VER(i915) < 12) + return false; + + /* Wa_14010477008:tgl[a0..c0],rkl[all],dg1[all] */ + if (IS_DG1(i915) || IS_ROCKETLAKE(i915) || + IS_TGL_DISPLAY_STEP(i915, STEP_A0, STEP_D0)) + return false; + + /* Wa_22011186057 */ + if (IS_ADLP_DISPLAY_STEP(i915, STEP_A0, STEP_B0)) + return false; + + return plane_id < PLANE_SPRITE4; +} + +static u8 skl_get_plane_caps(struct drm_i915_private *i915, + enum pipe pipe, enum plane_id plane_id) +{ + u8 caps = INTEL_PLANE_CAP_TILING_X; + + if (DISPLAY_VER(i915) < 13 || IS_ALDERLAKE_P(i915)) + caps |= INTEL_PLANE_CAP_TILING_Y; + if (DISPLAY_VER(i915) < 12) + caps |= INTEL_PLANE_CAP_TILING_Yf; + + if (skl_plane_has_rc_ccs(i915, pipe, plane_id)) { + caps |= INTEL_PLANE_CAP_CCS_RC; + if (DISPLAY_VER(i915) >= 12) + caps |= INTEL_PLANE_CAP_CCS_RC_CC; + } + + if (gen12_plane_has_mc_ccs(i915, plane_id)) + caps |= INTEL_PLANE_CAP_CCS_MC; + + return caps; +} + struct intel_plane * skl_universal_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe, enum plane_id plane_id) @@ -2113,16 +2120,14 @@ skl_universal_plane_create(struct drm_i915_private *dev_priv, plane->id = plane_id; plane->frontbuffer_bit = INTEL_FRONTBUFFER(pipe, plane_id); - plane->has_fbc = skl_plane_has_fbc(dev_priv, pipe, plane_id); - if (plane->has_fbc) { - struct intel_fbc *fbc = &dev_priv->fbc; - - fbc->possible_framebuffer_bits |= plane->frontbuffer_bit; - } + intel_fbc_add_plane(skl_plane_fbc(dev_priv, pipe, plane_id), plane); if (DISPLAY_VER(dev_priv) >= 11) { plane->min_width = icl_plane_min_width; - plane->max_width = icl_plane_max_width; + if (icl_is_hdr_plane(dev_priv, plane_id)) + plane->max_width = icl_hdr_plane_max_width; + else + plane->max_width = icl_sdr_plane_max_width; plane->max_height = icl_plane_max_height; plane->min_cdclk = icl_plane_min_cdclk; } else if (DISPLAY_VER(dev_priv) >= 10) { @@ -2136,8 +2141,9 @@ skl_universal_plane_create(struct drm_i915_private *dev_priv, } plane->max_stride = skl_plane_max_stride; - plane->update_plane = skl_update_plane; - plane->disable_plane = skl_disable_plane; + plane->update_noarm = skl_plane_update_noarm; + plane->update_arm = skl_plane_update_arm; + plane->disable_arm = skl_plane_disable_arm; plane->get_hw_state = skl_plane_get_hw_state; plane->check_plane = skl_plane_check; @@ -2159,29 +2165,28 @@ skl_universal_plane_create(struct drm_i915_private *dev_priv, formats = skl_get_plane_formats(dev_priv, pipe, plane_id, &num_formats); - plane->has_ccs = skl_plane_has_ccs(dev_priv, pipe, plane_id); - if (DISPLAY_VER(dev_priv) >= 12) { - modifiers = gen12_get_plane_modifiers(dev_priv, plane_id); + if (DISPLAY_VER(dev_priv) >= 12) plane_funcs = &gen12_plane_funcs; - } else { - if (plane->has_ccs) - modifiers = skl_plane_format_modifiers_ccs; - else - modifiers = skl_plane_format_modifiers_noccs; + else plane_funcs = &skl_plane_funcs; - } if (plane_id == PLANE_PRIMARY) plane_type = DRM_PLANE_TYPE_PRIMARY; else plane_type = DRM_PLANE_TYPE_OVERLAY; + modifiers = intel_fb_plane_get_modifiers(dev_priv, + skl_get_plane_caps(dev_priv, pipe, plane_id)); + ret = drm_universal_plane_init(&dev_priv->drm, &plane->base, 0, plane_funcs, formats, num_formats, modifiers, plane_type, "plane %d%c", plane_id + 1, pipe_name(pipe)); + + kfree(modifiers); + if (ret) goto fail; diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c index 07584695514b..20141f33ed64 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi.c +++ b/drivers/gpu/drm/i915/display/vlv_dsi.c @@ -38,9 +38,12 @@ #include "intel_de.h" #include "intel_display_types.h" #include "intel_dsi.h" +#include "intel_dsi_vbt.h" #include "intel_fifo_underrun.h" #include "intel_panel.h" #include "skl_scaler.h" +#include "vlv_dsi.h" +#include "vlv_dsi_pll.h" #include "vlv_sideband.h" /* return pixels in terms of txbyteclkhs */ @@ -1258,7 +1261,9 @@ static void intel_dsi_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_dsi *intel_dsi = enc_to_intel_dsi(encoder); u32 pclk; + drm_dbg_kms(&dev_priv->drm, "\n"); pipe_config->output_types |= BIT(INTEL_OUTPUT_DSI); @@ -1270,6 +1275,9 @@ static void intel_dsi_get_config(struct intel_encoder *encoder, pclk = vlv_dsi_get_pclk(encoder, pipe_config); } + if (intel_dsi->dual_link) + pclk *= 2; + if (pclk) { pipe_config->hw.adjusted_mode.crtc_clock = pclk; pipe_config->port_clock = pclk; diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.h b/drivers/gpu/drm/i915/display/vlv_dsi.h new file mode 100644 index 000000000000..0c2b279df9d4 --- /dev/null +++ b/drivers/gpu/drm/i915/display/vlv_dsi.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef __VLV_DSI_H__ +#define __VLV_DSI_H__ + +#include <linux/types.h> + +enum port; +struct drm_i915_private; +struct intel_dsi; + +void vlv_dsi_wait_for_fifo_empty(struct intel_dsi *intel_dsi, enum port port); +enum mipi_dsi_pixel_format pixel_format_from_register_bits(u32 fmt); +void vlv_dsi_init(struct drm_i915_private *dev_priv); + +#endif /* __VLV_DSI_H__ */ diff --git a/drivers/gpu/drm/i915/display/vlv_dsi_pll.c b/drivers/gpu/drm/i915/display/vlv_dsi_pll.c index 5413b52ab6ba..1b81797dd02e 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi_pll.c +++ b/drivers/gpu/drm/i915/display/vlv_dsi_pll.c @@ -31,6 +31,7 @@ #include "intel_de.h" #include "intel_display_types.h" #include "intel_dsi.h" +#include "vlv_dsi_pll.h" #include "vlv_sideband.h" static const u16 lfsr_converts[] = { diff --git a/drivers/gpu/drm/i915/display/vlv_dsi_pll.h b/drivers/gpu/drm/i915/display/vlv_dsi_pll.h new file mode 100644 index 000000000000..ab9291ad1e79 --- /dev/null +++ b/drivers/gpu/drm/i915/display/vlv_dsi_pll.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef __VLV_DSI_PLL_H__ +#define __VLV_DSI_PLL_H__ + +#include <linux/types.h> + +enum port; +struct drm_i915_private; +struct intel_crtc_state; +struct intel_encoder; + +int vlv_dsi_pll_compute(struct intel_encoder *encoder, + struct intel_crtc_state *config); +void vlv_dsi_pll_enable(struct intel_encoder *encoder, + const struct intel_crtc_state *config); +void vlv_dsi_pll_disable(struct intel_encoder *encoder); +u32 vlv_dsi_get_pclk(struct intel_encoder *encoder, + struct intel_crtc_state *config); +void vlv_dsi_reset_clocks(struct intel_encoder *encoder, enum port port); + +bool bxt_dsi_pll_is_enabled(struct drm_i915_private *dev_priv); +int bxt_dsi_pll_compute(struct intel_encoder *encoder, + struct intel_crtc_state *config); +void bxt_dsi_pll_enable(struct intel_encoder *encoder, + const struct intel_crtc_state *config); +void bxt_dsi_pll_disable(struct intel_encoder *encoder); +u32 bxt_dsi_get_pclk(struct intel_encoder *encoder, + struct intel_crtc_state *config); +void bxt_dsi_reset_clocks(struct intel_encoder *encoder, enum port port); + +void assert_dsi_pll_enabled(struct drm_i915_private *i915); +void assert_dsi_pll_disabled(struct drm_i915_private *i915); + +#endif /* __VLV_DSI_PLL_H__ */ diff --git a/drivers/gpu/drm/i915/dma_resv_utils.c b/drivers/gpu/drm/i915/dma_resv_utils.c deleted file mode 100644 index 7df91b7e4ca8..000000000000 --- a/drivers/gpu/drm/i915/dma_resv_utils.c +++ /dev/null @@ -1,17 +0,0 @@ -// SPDX-License-Identifier: MIT -/* - * Copyright © 2020 Intel Corporation - */ - -#include <linux/dma-resv.h> - -#include "dma_resv_utils.h" - -void dma_resv_prune(struct dma_resv *resv) -{ - if (dma_resv_trylock(resv)) { - if (dma_resv_test_signaled(resv, true)) - dma_resv_add_excl_fence(resv, NULL); - dma_resv_unlock(resv); - } -} diff --git a/drivers/gpu/drm/i915/dma_resv_utils.h b/drivers/gpu/drm/i915/dma_resv_utils.h deleted file mode 100644 index b9d8fb5f8367..000000000000 --- a/drivers/gpu/drm/i915/dma_resv_utils.h +++ /dev/null @@ -1,13 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2020 Intel Corporation - */ - -#ifndef DMA_RESV_UTILS_H -#define DMA_RESV_UTILS_H - -struct dma_resv; - -void dma_resv_prune(struct dma_resv *resv); - -#endif /* DMA_RESV_UTILS_H */ diff --git a/drivers/gpu/drm/i915/gem/i915_gem_busy.c b/drivers/gpu/drm/i915/gem/i915_gem_busy.c index 7358bebef15c..470fdfd61a0f 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_busy.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_busy.c @@ -115,8 +115,8 @@ i915_gem_busy_ioctl(struct drm_device *dev, void *data, { struct drm_i915_gem_busy *args = data; struct drm_i915_gem_object *obj; - struct dma_resv_list *list; - unsigned int seq; + struct dma_resv_iter cursor; + struct dma_fence *fence; int err; err = -ENOENT; @@ -142,27 +142,20 @@ i915_gem_busy_ioctl(struct drm_device *dev, void *data, * to report the overall busyness. This is what the wait-ioctl does. * */ -retry: - seq = raw_read_seqcount(&obj->base.resv->seq); - - /* Translate the exclusive fence to the READ *and* WRITE engine */ - args->busy = busy_check_writer(dma_resv_excl_fence(obj->base.resv)); - - /* Translate shared fences to READ set of engines */ - list = dma_resv_shared_list(obj->base.resv); - if (list) { - unsigned int shared_count = list->shared_count, i; - - for (i = 0; i < shared_count; ++i) { - struct dma_fence *fence = - rcu_dereference(list->shared[i]); - + args->busy = 0; + dma_resv_iter_begin(&cursor, obj->base.resv, true); + dma_resv_for_each_fence_unlocked(&cursor, fence) { + if (dma_resv_iter_is_restarted(&cursor)) + args->busy = 0; + + if (dma_resv_iter_is_exclusive(&cursor)) + /* Translate the exclusive fence to the READ *and* WRITE engine */ + args->busy |= busy_check_writer(fence); + else + /* Translate shared fences to READ set of engines */ args->busy |= busy_check_reader(fence); - } } - - if (args->busy && read_seqcount_retry(&obj->base.resv->seq, seq)) - goto retry; + dma_resv_iter_end(&cursor); err = 0; out: diff --git a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c index f0435c6feb68..8a248003dfae 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c @@ -69,10 +69,16 @@ static struct clflush *clflush_work_create(struct drm_i915_gem_object *obj) bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, unsigned int flags) { + struct drm_i915_private *i915 = to_i915(obj->base.dev); struct clflush *clflush; assert_object_held(obj); + if (IS_DGFX(i915)) { + WARN_ON_ONCE(obj->cache_dirty); + return false; + } + /* * Stolen memory is always coherent with the GPU as it is explicitly * marked as wc by the system, or the system is cache-coherent. @@ -105,16 +111,24 @@ bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, if (clflush) { i915_sw_fence_await_reservation(&clflush->base.chain, obj->base.resv, NULL, true, - i915_fence_timeout(to_i915(obj->base.dev)), + i915_fence_timeout(i915), I915_FENCE_GFP); dma_resv_add_excl_fence(obj->base.resv, &clflush->base.dma); dma_fence_work_commit(&clflush->base); + /* + * We must have successfully populated the pages(since we are + * holding a pin on the pages as per the flush worker) to reach + * this point, which must mean we have already done the required + * flush-on-acquire, hence resetting cache_dirty here should be + * safe. + */ + obj->cache_dirty = false; } else if (obj->mm.pages) { __do_clflush(obj); + obj->cache_dirty = false; } else { GEM_BUG_ON(obj->write_domain != I915_GEM_DOMAIN_CPU); } - obj->cache_dirty = false; return true; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index c37c9f0d8167..00327b750fbb 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -237,7 +237,7 @@ static int proto_context_set_persistence(struct drm_i915_private *i915, * colateral damage, and we should not pretend we can by * exposing the interface. */ - if (!intel_has_reset_engine(&i915->gt)) + if (!intel_has_reset_engine(to_gt(i915))) return -ENODEV; pc->user_flags &= ~BIT(UCONTEXT_PERSISTENCE); @@ -254,7 +254,7 @@ static int proto_context_set_protected(struct drm_i915_private *i915, if (!protected) { pc->uses_protected_content = false; - } else if (!intel_pxp_is_enabled(&i915->gt.pxp)) { + } else if (!intel_pxp_is_enabled(&to_gt(i915)->pxp)) { ret = -ENODEV; } else if ((pc->user_flags & BIT(UCONTEXT_RECOVERABLE)) || !(pc->user_flags & BIT(UCONTEXT_BANNABLE))) { @@ -268,8 +268,8 @@ static int proto_context_set_protected(struct drm_i915_private *i915, */ pc->pxp_wakeref = intel_runtime_pm_get(&i915->runtime_pm); - if (!intel_pxp_is_active(&i915->gt.pxp)) - ret = intel_pxp_start(&i915->gt.pxp); + if (!intel_pxp_is_active(&to_gt(i915)->pxp)) + ret = intel_pxp_start(&to_gt(i915)->pxp); } return ret; @@ -479,7 +479,7 @@ set_proto_ctx_engines_bond(struct i915_user_extension __user *base, void *data) if (GRAPHICS_VER(i915) >= 12 && !IS_TIGERLAKE(i915) && !IS_ROCKETLAKE(i915) && !IS_ALDERLAKE_S(i915)) { drm_dbg(&i915->drm, - "Bonding on gen12+ aside from TGL, RKL, and ADL_S not supported\n"); + "Bonding not supported on this platform\n"); return -ENODEV; } @@ -572,7 +572,7 @@ set_proto_ctx_engines_parallel_submit(struct i915_user_extension __user *base, intel_engine_mask_t prev_mask; /* FIXME: This is NIY for execlists */ - if (!(intel_uc_uses_guc_submission(&i915->gt.uc))) + if (!(intel_uc_uses_guc_submission(&to_gt(i915)->uc))) return -ENODEV; if (get_user(slot, &ext->engine_index)) @@ -833,7 +833,7 @@ static int set_proto_ctx_sseu(struct drm_i915_file_private *fpriv, sseu = &pc->legacy_rcs_sseu; } - ret = i915_gem_user_to_context_sseu(&i915->gt, &user_sseu, sseu); + ret = i915_gem_user_to_context_sseu(to_gt(i915), &user_sseu, sseu); if (ret) return ret; @@ -1001,7 +1001,7 @@ static void free_engines_rcu(struct rcu_head *rcu) free_engines(engines); } -static int __i915_sw_fence_call +static int engines_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state) { struct i915_gem_engines *engines = @@ -1044,7 +1044,7 @@ static struct i915_gem_engines *alloc_engines(unsigned int count) static struct i915_gem_engines *default_engines(struct i915_gem_context *ctx, struct intel_sseu rcs_sseu) { - const struct intel_gt *gt = &ctx->i915->gt; + const struct intel_gt *gt = to_gt(ctx->i915); struct intel_engine_cs *engine; struct i915_gem_engines *e, *err; enum intel_engine_id id; @@ -1521,7 +1521,7 @@ static int __context_set_persistence(struct i915_gem_context *ctx, bool state) * colateral damage, and we should not pretend we can by * exposing the interface. */ - if (!intel_has_reset_engine(&ctx->i915->gt)) + if (!intel_has_reset_engine(to_gt(ctx->i915))) return -ENODEV; i915_gem_context_clear_persistence(ctx); @@ -1559,7 +1559,7 @@ i915_gem_create_context(struct drm_i915_private *i915, } else if (HAS_FULL_PPGTT(i915)) { struct i915_ppgtt *ppgtt; - ppgtt = i915_ppgtt_create(&i915->gt, 0); + ppgtt = i915_ppgtt_create(to_gt(i915), 0); if (IS_ERR(ppgtt)) { drm_dbg(&i915->drm, "PPGTT setup failed (%ld)\n", PTR_ERR(ppgtt)); @@ -1742,7 +1742,7 @@ int i915_gem_vm_create_ioctl(struct drm_device *dev, void *data, if (args->flags) return -EINVAL; - ppgtt = i915_ppgtt_create(&i915->gt, 0); + ppgtt = i915_ppgtt_create(to_gt(i915), 0); if (IS_ERR(ppgtt)) return PTR_ERR(ppgtt); @@ -2194,7 +2194,7 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data, if (args->flags & I915_CONTEXT_CREATE_FLAGS_UNKNOWN) return -EINVAL; - ret = intel_gt_terminally_wedged(&i915->gt); + ret = intel_gt_terminally_wedged(to_gt(i915)); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_create.c b/drivers/gpu/drm/i915/gem/i915_gem_create.c index 8955d6abcef1..9402d4bf4ffc 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_create.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_create.c @@ -379,7 +379,7 @@ static int ext_set_protected(struct i915_user_extension __user *base, void *data if (ext.flags) return -EINVAL; - if (!intel_pxp_is_enabled(&ext_data->i915->gt.pxp)) + if (!intel_pxp_is_enabled(&to_gt(ext_data->i915)->pxp)) return -ENODEV; ext_data->flags |= I915_BO_PROTECTED; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c index e8a58c997170..1b526039a60d 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c @@ -248,8 +248,19 @@ static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj) if (IS_ERR(pages)) return PTR_ERR(pages); - /* XXX: consider doing a vmap flush or something */ - if (!HAS_LLC(i915) || i915_gem_object_can_bypass_llc(obj)) + /* + * DG1 is special here since it still snoops transactions even with + * CACHE_NONE. This is not the case with other HAS_SNOOP platforms. We + * might need to revisit this as we add new discrete platforms. + * + * XXX: Consider doing a vmap flush or something, where possible. + * Currently we just do a heavy handed wbinvd_on_all_cpus() here since + * the underlying sg_table might not even point to struct pages, so we + * can't just call drm_clflush_sg or similar, like we do elsewhere in + * the driver. + */ + if (i915_gem_object_can_bypass_llc(obj) || + (!HAS_LLC(i915) && !IS_DG1(i915))) wbinvd_on_all_cpus(); sg_page_sizes = i915_sg_dma_sizes(pages->sgl); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c index b684a62bf3b0..26532c07d467 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c @@ -18,10 +18,32 @@ static bool gpu_write_needs_clflush(struct drm_i915_gem_object *obj) { + struct drm_i915_private *i915 = to_i915(obj->base.dev); + + if (IS_DGFX(i915)) + return false; + return !(obj->cache_level == I915_CACHE_NONE || obj->cache_level == I915_CACHE_WT); } +bool i915_gem_cpu_write_needs_clflush(struct drm_i915_gem_object *obj) +{ + struct drm_i915_private *i915 = to_i915(obj->base.dev); + + if (obj->cache_dirty) + return false; + + if (!(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE)) + return true; + + if (IS_DGFX(i915)) + return false; + + /* Currently in use by HW (display engine)? Keep flushed. */ + return i915_gem_object_is_framebuffer(obj); +} + static void flush_write_domain(struct drm_i915_gem_object *obj, unsigned int flush_domains) { diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index cb0bf6ffd0e3..3a5b247be738 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -29,6 +29,7 @@ #include "i915_gem_ioctls.h" #include "i915_trace.h" #include "i915_user_extensions.h" +#include "i915_vma_snapshot.h" struct eb_vma { struct i915_vma *vma; @@ -307,11 +308,15 @@ struct i915_execbuffer { struct eb_fence *fences; unsigned long num_fences; +#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) + struct i915_capture_list *capture_lists[MAX_ENGINE_INSTANCE + 1]; +#endif }; static int eb_parse(struct i915_execbuffer *eb); static int eb_pin_engine(struct i915_execbuffer *eb, bool throttle); static void eb_unpin_engine(struct i915_execbuffer *eb); +static void eb_capture_release(struct i915_execbuffer *eb); static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb) { @@ -990,7 +995,7 @@ static int eb_validate_vmas(struct i915_execbuffer *eb) } if (!(ev->flags & EXEC_OBJECT_WRITE)) { - err = dma_resv_reserve_shared(vma->resv, 1); + err = dma_resv_reserve_shared(vma->obj->base.resv, 1); if (err) return err; } @@ -1043,6 +1048,7 @@ static void eb_release_vmas(struct i915_execbuffer *eb, bool final) i915_vma_put(vma); } + eb_capture_release(eb); eb_unpin_engine(eb); } @@ -1092,6 +1098,47 @@ static inline struct i915_ggtt *cache_to_ggtt(struct reloc_cache *cache) return &i915->ggtt; } +static void reloc_cache_unmap(struct reloc_cache *cache) +{ + void *vaddr; + + if (!cache->vaddr) + return; + + vaddr = unmask_page(cache->vaddr); + if (cache->vaddr & KMAP) + kunmap_atomic(vaddr); + else + io_mapping_unmap_atomic((void __iomem *)vaddr); +} + +static void reloc_cache_remap(struct reloc_cache *cache, + struct drm_i915_gem_object *obj) +{ + void *vaddr; + + if (!cache->vaddr) + return; + + if (cache->vaddr & KMAP) { + struct page *page = i915_gem_object_get_page(obj, cache->page); + + vaddr = kmap_atomic(page); + cache->vaddr = unmask_flags(cache->vaddr) | + (unsigned long)vaddr; + } else { + struct i915_ggtt *ggtt = cache_to_ggtt(cache); + unsigned long offset; + + offset = cache->node.start; + if (!drm_mm_node_allocated(&cache->node)) + offset += cache->page << PAGE_SHIFT; + + cache->vaddr = (unsigned long) + io_mapping_map_atomic_wc(&ggtt->iomap, offset); + } +} + static void reloc_cache_reset(struct reloc_cache *cache, struct i915_execbuffer *eb) { void *vaddr; @@ -1356,10 +1403,17 @@ eb_relocate_entry(struct i915_execbuffer *eb, * batchbuffers. */ if (reloc->write_domain == I915_GEM_DOMAIN_INSTRUCTION && - GRAPHICS_VER(eb->i915) == 6) { + GRAPHICS_VER(eb->i915) == 6 && + !i915_vma_is_bound(target->vma, I915_VMA_GLOBAL_BIND)) { + struct i915_vma *vma = target->vma; + + reloc_cache_unmap(&eb->reloc_cache); + mutex_lock(&vma->vm->mutex); err = i915_vma_bind(target->vma, target->vma->obj->cache_level, PIN_GLOBAL, NULL); + mutex_unlock(&vma->vm->mutex); + reloc_cache_remap(&eb->reloc_cache, ev->vma->obj); if (err) return err; } @@ -1880,36 +1934,113 @@ eb_find_first_request_added(struct i915_execbuffer *eb) return NULL; } -static int eb_move_to_gpu(struct i915_execbuffer *eb) +#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) + +/* Stage with GFP_KERNEL allocations before we enter the signaling critical path */ +static void eb_capture_stage(struct i915_execbuffer *eb) { const unsigned int count = eb->buffer_count; - unsigned int i = count; - int err = 0, j; + unsigned int i = count, j; + struct i915_vma_snapshot *vsnap; while (i--) { struct eb_vma *ev = &eb->vma[i]; struct i915_vma *vma = ev->vma; unsigned int flags = ev->flags; - struct drm_i915_gem_object *obj = vma->obj; - assert_vma_held(vma); + if (!(flags & EXEC_OBJECT_CAPTURE)) + continue; - if (flags & EXEC_OBJECT_CAPTURE) { + vsnap = i915_vma_snapshot_alloc(GFP_KERNEL); + if (!vsnap) + continue; + + i915_vma_snapshot_init(vsnap, vma, "user"); + for_each_batch_create_order(eb, j) { struct i915_capture_list *capture; - for_each_batch_create_order(eb, j) { - if (!eb->requests[j]) - break; + capture = kmalloc(sizeof(*capture), GFP_KERNEL); + if (!capture) + continue; - capture = kmalloc(sizeof(*capture), GFP_KERNEL); - if (capture) { - capture->next = - eb->requests[j]->capture_list; - capture->vma = vma; - eb->requests[j]->capture_list = capture; - } - } + capture->next = eb->capture_lists[j]; + capture->vma_snapshot = i915_vma_snapshot_get(vsnap); + eb->capture_lists[j] = capture; + } + i915_vma_snapshot_put(vsnap); + } +} + +/* Commit once we're in the critical path */ +static void eb_capture_commit(struct i915_execbuffer *eb) +{ + unsigned int j; + + for_each_batch_create_order(eb, j) { + struct i915_request *rq = eb->requests[j]; + + if (!rq) + break; + + rq->capture_list = eb->capture_lists[j]; + eb->capture_lists[j] = NULL; + } +} + +/* + * Release anything that didn't get committed due to errors. + * The capture_list will otherwise be freed at request retire. + */ +static void eb_capture_release(struct i915_execbuffer *eb) +{ + unsigned int j; + + for_each_batch_create_order(eb, j) { + if (eb->capture_lists[j]) { + i915_request_free_capture_list(eb->capture_lists[j]); + eb->capture_lists[j] = NULL; } + } +} + +static void eb_capture_list_clear(struct i915_execbuffer *eb) +{ + memset(eb->capture_lists, 0, sizeof(eb->capture_lists)); +} + +#else + +static void eb_capture_stage(struct i915_execbuffer *eb) +{ +} + +static void eb_capture_commit(struct i915_execbuffer *eb) +{ +} + +static void eb_capture_release(struct i915_execbuffer *eb) +{ +} + +static void eb_capture_list_clear(struct i915_execbuffer *eb) +{ +} + +#endif + +static int eb_move_to_gpu(struct i915_execbuffer *eb) +{ + const unsigned int count = eb->buffer_count; + unsigned int i = count; + int err = 0, j; + + while (i--) { + struct eb_vma *ev = &eb->vma[i]; + struct i915_vma *vma = ev->vma; + unsigned int flags = ev->flags; + struct drm_i915_gem_object *obj = vma->obj; + + assert_vma_held(vma); /* * If the GPU is not _reading_ through the CPU cache, we need @@ -1990,6 +2121,8 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb) /* Unconditionally flush any chipset caches (for streaming writes). */ intel_gt_chipset_flush(eb->gt); + eb_capture_commit(eb); + return 0; err_skip: @@ -2164,7 +2297,7 @@ static int eb_parse(struct i915_execbuffer *eb) goto err_trampoline; } - err = dma_resv_reserve_shared(shadow->resv, 1); + err = dma_resv_reserve_shared(shadow->obj->base.resv, 1); if (err) goto err_trampoline; @@ -2276,9 +2409,9 @@ static int eb_submit(struct i915_execbuffer *eb) return err; } -static int num_vcs_engines(const struct drm_i915_private *i915) +static int num_vcs_engines(struct drm_i915_private *i915) { - return hweight_long(VDBOX_MASK(&i915->gt)); + return hweight_long(VDBOX_MASK(to_gt(i915))); } /* @@ -3114,7 +3247,7 @@ eb_requests_create(struct i915_execbuffer *eb, struct dma_fence *in_fence, /* Allocate a request for this batch buffer nice and early. */ eb->requests[i] = i915_request_create(eb_find_context(eb, i)); if (IS_ERR(eb->requests[i])) { - out_fence = ERR_PTR(PTR_ERR(eb->requests[i])); + out_fence = ERR_CAST(eb->requests[i]); eb->requests[i] = NULL; return out_fence; } @@ -3132,13 +3265,14 @@ eb_requests_create(struct i915_execbuffer *eb, struct dma_fence *in_fence, } /* - * Whilst this request exists, batch_obj will be on the - * active_list, and so will hold the active reference. Only when - * this request is retired will the batch_obj be moved onto - * the inactive_list and lose its active reference. Hence we do - * not need to explicitly hold another reference here. + * Not really on stack, but we don't want to call + * kfree on the batch_snapshot when we put it, so use the + * _onstack interface. */ - eb->requests[i]->batch = eb->batches[i]->vma; + if (eb->batches[i]->vma) + i915_vma_snapshot_init_onstack(&eb->requests[i]->batch_snapshot, + eb->batches[i]->vma, + "batch"); if (eb->batch_pool) { GEM_BUG_ON(intel_context_is_parallel(eb->context)); intel_gt_buffer_pool_mark_active(eb->batch_pool, @@ -3187,6 +3321,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, eb.fences = NULL; eb.num_fences = 0; + eb_capture_list_clear(&eb); + memset(eb.requests, 0, sizeof(struct i915_request *) * ARRAY_SIZE(eb.requests)); eb.composite_fence = NULL; @@ -3273,6 +3409,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, } ww_acquire_done(&eb.ww.ctx); + eb_capture_stage(&eb); out_fence = eb_requests_create(&eb, in_fence, out_fence_fd); if (IS_ERR(out_fence)) { diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c index a57a6b7013c2..c5150a1ee3d2 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c @@ -145,24 +145,10 @@ static const struct drm_i915_gem_object_ops i915_gem_object_internal_ops = { .put_pages = i915_gem_object_put_pages_internal, }; -/** - * i915_gem_object_create_internal: create an object with volatile pages - * @i915: the i915 device - * @size: the size in bytes of backing storage to allocate for the object - * - * Creates a new object that wraps some internal memory for private use. - * This object is not backed by swappable storage, and as such its contents - * are volatile and only valid whilst pinned. If the object is reaped by the - * shrinker, its pages and data will be discarded. Equally, it is not a full - * GEM object and so not valid for access from userspace. This makes it useful - * for hardware interfaces like ringbuffers (which are pinned from the time - * the request is written to the time the hardware stops accessing it), but - * not for contexts (which need to be preserved when not active for later - * reuse). Note that it is not cleared upon allocation. - */ struct drm_i915_gem_object * -i915_gem_object_create_internal(struct drm_i915_private *i915, - phys_addr_t size) +__i915_gem_object_create_internal(struct drm_i915_private *i915, + const struct drm_i915_gem_object_ops *ops, + phys_addr_t size) { static struct lock_class_key lock_class; struct drm_i915_gem_object *obj; @@ -179,7 +165,7 @@ i915_gem_object_create_internal(struct drm_i915_private *i915, return ERR_PTR(-ENOMEM); drm_gem_private_object_init(&i915->drm, &obj->base, size); - i915_gem_object_init(obj, &i915_gem_object_internal_ops, &lock_class, 0); + i915_gem_object_init(obj, ops, &lock_class, 0); obj->mem_flags |= I915_BO_FLAG_STRUCT_PAGE; /* @@ -199,3 +185,25 @@ i915_gem_object_create_internal(struct drm_i915_private *i915, return obj; } + +/** + * i915_gem_object_create_internal: create an object with volatile pages + * @i915: the i915 device + * @size: the size in bytes of backing storage to allocate for the object + * + * Creates a new object that wraps some internal memory for private use. + * This object is not backed by swappable storage, and as such its contents + * are volatile and only valid whilst pinned. If the object is reaped by the + * shrinker, its pages and data will be discarded. Equally, it is not a full + * GEM object and so not valid for access from userspace. This makes it useful + * for hardware interfaces like ringbuffers (which are pinned from the time + * the request is written to the time the hardware stops accessing it), but + * not for contexts (which need to be preserved when not active for later + * reuse). Note that it is not cleared upon allocation. + */ +struct drm_i915_gem_object * +i915_gem_object_create_internal(struct drm_i915_private *i915, + phys_addr_t size) +{ + return __i915_gem_object_create_internal(i915, &i915_gem_object_internal_ops, size); +} diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index 65fc6ff5f59d..aaf970c37aa2 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -17,6 +17,7 @@ #include "i915_gem_ioctls.h" #include "i915_gem_object.h" #include "i915_gem_mman.h" +#include "i915_mm.h" #include "i915_trace.h" #include "i915_user_extensions.h" #include "i915_gem_ttm.h" @@ -72,7 +73,7 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data, if (args->flags & ~(I915_MMAP_WC)) return -EINVAL; - if (args->flags & I915_MMAP_WC && !boot_cpu_has(X86_FEATURE_PAT)) + if (args->flags & I915_MMAP_WC && !pat_enabled()) return -ENODEV; obj = i915_gem_object_lookup(file, args->handle); @@ -645,7 +646,7 @@ mmap_offset_attach(struct drm_i915_gem_object *obj, goto insert; /* Attempt to reap some mmap space from dead objects */ - err = intel_gt_retire_requests_timeout(&i915->gt, MAX_SCHEDULE_TIMEOUT, + err = intel_gt_retire_requests_timeout(to_gt(i915), MAX_SCHEDULE_TIMEOUT, NULL); if (err) goto err; @@ -736,7 +737,7 @@ i915_gem_dumb_mmap_offset(struct drm_file *file, if (HAS_LMEM(to_i915(dev))) mmap_type = I915_MMAP_TYPE_FIXED; - else if (boot_cpu_has(X86_FEATURE_PAT)) + else if (pat_enabled()) mmap_type = I915_MMAP_TYPE_WC; else if (!i915_ggtt_has_aperture(&to_i915(dev)->ggtt)) return -ENODEV; @@ -792,7 +793,7 @@ i915_gem_mmap_offset_ioctl(struct drm_device *dev, void *data, break; case I915_MMAP_OFFSET_WC: - if (!boot_cpu_has(X86_FEATURE_PAT)) + if (!pat_enabled()) return -ENODEV; type = I915_MMAP_TYPE_WC; break; @@ -802,7 +803,7 @@ i915_gem_mmap_offset_ioctl(struct drm_device *dev, void *data, break; case I915_MMAP_OFFSET_UC: - if (!boot_cpu_has(X86_FEATURE_PAT)) + if (!pat_enabled()) return -ENODEV; type = I915_MMAP_TYPE_UC; break; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index 1e426a42a36c..d87b508b59b1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -31,6 +31,7 @@ #include "i915_gem_context.h" #include "i915_gem_mman.h" #include "i915_gem_object.h" +#include "i915_gem_ttm.h" #include "i915_memcpy.h" #include "i915_trace.h" @@ -91,7 +92,7 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj, } /** - * i915_gem_object_fini - Clean up a GEM object initialization + * __i915_gem_object_fini - Clean up a GEM object initialization * @obj: The gem object to cleanup * * This function cleans up gem object fields that are set up by @@ -107,25 +108,29 @@ void __i915_gem_object_fini(struct drm_i915_gem_object *obj) } /** - * Mark up the object's coherency levels for a given cache_level + * i915_gem_object_set_cache_coherency - Mark up the object's coherency levels + * for a given cache_level * @obj: #drm_i915_gem_object * @cache_level: cache level */ void i915_gem_object_set_cache_coherency(struct drm_i915_gem_object *obj, unsigned int cache_level) { + struct drm_i915_private *i915 = to_i915(obj->base.dev); + obj->cache_level = cache_level; if (cache_level != I915_CACHE_NONE) obj->cache_coherent = (I915_BO_CACHE_COHERENT_FOR_READ | I915_BO_CACHE_COHERENT_FOR_WRITE); - else if (HAS_LLC(to_i915(obj->base.dev))) + else if (HAS_LLC(i915)) obj->cache_coherent = I915_BO_CACHE_COHERENT_FOR_READ; else obj->cache_coherent = 0; obj->cache_dirty = - !(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE); + !(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE) && + !IS_DGFX(i915); } bool i915_gem_object_can_bypass_llc(struct drm_i915_gem_object *obj) @@ -257,6 +262,8 @@ static void __i915_gem_object_free_mmaps(struct drm_i915_gem_object *obj) */ void __i915_gem_object_pages_fini(struct drm_i915_gem_object *obj) { + assert_object_held(obj); + if (!list_empty(&obj->vma.list)) { struct i915_vma *vma; @@ -323,7 +330,16 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915, obj->ops->delayed_free(obj); continue; } + + if (!i915_gem_object_trylock(obj, NULL)) { + /* busy, toss it back to the pile */ + if (llist_add(&obj->freed, &i915->mm.free_list)) + queue_delayed_work(i915->wq, &i915->mm.free_work, msecs_to_jiffies(10)); + continue; + } + __i915_gem_object_pages_fini(obj); + i915_gem_object_unlock(obj); __i915_gem_free_object(obj); /* But keep the pointer alive for RCU-protected lookups */ @@ -343,7 +359,7 @@ void i915_gem_flush_free_objects(struct drm_i915_private *i915) static void __i915_gem_free_work(struct work_struct *work) { struct drm_i915_private *i915 = - container_of(work, struct drm_i915_private, mm.free_work); + container_of(work, struct drm_i915_private, mm.free_work.work); i915_gem_flush_free_objects(i915); } @@ -364,15 +380,6 @@ static void i915_gem_free_object(struct drm_gem_object *gem_obj) atomic_inc(&i915->mm.free_count); /* - * This serializes freeing with the shrinker. Since the free - * is delayed, first by RCU then by the workqueue, we want the - * shrinker to be able to free pages of unreferenced objects, - * or else we may oom whilst there are plenty of deferred - * freed objects. - */ - i915_gem_object_make_unshrinkable(obj); - - /* * Since we require blocking on struct_mutex to unbind the freed * object from the GPU before releasing resources back to the * system, we can not do that directly from the RCU callback (which may @@ -384,7 +391,7 @@ static void i915_gem_free_object(struct drm_gem_object *gem_obj) */ if (llist_add(&obj->freed, &i915->mm.free_list)) - queue_work(i915->wq, &i915->mm.free_work); + queue_delayed_work(i915->wq, &i915->mm.free_work, 0); } void __i915_gem_object_flush_frontbuffer(struct drm_i915_gem_object *obj, @@ -456,7 +463,7 @@ i915_gem_object_read_from_page_iomap(struct drm_i915_gem_object *obj, u64 offset * from can't cross a page boundary. The caller must ensure that @obj pages * are pinned and that @obj is synced wrt. any related writes. * - * Returns 0 on success or -ENODEV if the type of @obj's backing store is + * Return: %0 on success or -ENODEV if the type of @obj's backing store is * unsupported. */ int i915_gem_object_read_from_page(struct drm_i915_gem_object *obj, u64 offset, void *dst, int size) @@ -709,7 +716,7 @@ bool i915_gem_object_placement_possible(struct drm_i915_gem_object *obj, void i915_gem_init__objects(struct drm_i915_private *i915) { - INIT_WORK(&i915->mm.free_work, __i915_gem_free_work); + INIT_DELAYED_WORK(&i915->mm.free_work, __i915_gem_free_work); } void i915_objects_module_exit(void) @@ -732,6 +739,57 @@ static const struct drm_gem_object_funcs i915_gem_object_funcs = { .export = i915_gem_prime_export, }; +/** + * i915_gem_object_get_moving_fence - Get the object's moving fence if any + * @obj: The object whose moving fence to get. + * + * A non-signaled moving fence means that there is an async operation + * pending on the object that needs to be waited on before setting up + * any GPU- or CPU PTEs to the object's pages. + * + * Return: A refcounted pointer to the object's moving fence if any, + * NULL otherwise. + */ +struct dma_fence * +i915_gem_object_get_moving_fence(struct drm_i915_gem_object *obj) +{ + return dma_fence_get(i915_gem_to_ttm(obj)->moving); +} + +/** + * i915_gem_object_wait_moving_fence - Wait for the object's moving fence if any + * @obj: The object whose moving fence to wait for. + * @intr: Whether to wait interruptible. + * + * If the moving fence signaled without an error, it is detached from the + * object and put. + * + * Return: 0 if successful, -ERESTARTSYS if the wait was interrupted, + * negative error code if the async operation represented by the + * moving fence failed. + */ +int i915_gem_object_wait_moving_fence(struct drm_i915_gem_object *obj, + bool intr) +{ + struct dma_fence *fence = i915_gem_to_ttm(obj)->moving; + int ret; + + assert_object_held(obj); + if (!fence) + return 0; + + ret = dma_fence_wait(fence, intr); + if (ret) + return ret; + + if (fence->error) + return fence->error; + + i915_gem_to_ttm(obj)->moving = NULL; + dma_fence_put(fence); + return 0; +} + #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "selftests/huge_gem_object.c" #include "selftests/huge_pages.c" diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index 59201801cec5..f66d46882ea7 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -93,7 +93,6 @@ void i915_gem_flush_free_objects(struct drm_i915_private *i915); struct sg_table * __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj); -void i915_gem_object_truncate(struct drm_i915_gem_object *obj); /** * i915_gem_object_lookup_rcu - look up a temporary GEM object from its handle @@ -211,9 +210,13 @@ static inline int i915_gem_object_lock_interruptible(struct drm_i915_gem_object return __i915_gem_object_lock(obj, ww, true); } -static inline bool i915_gem_object_trylock(struct drm_i915_gem_object *obj) +static inline bool i915_gem_object_trylock(struct drm_i915_gem_object *obj, + struct i915_gem_ww_ctx *ww) { - return dma_resv_trylock(obj->base.resv); + if (!ww) + return dma_resv_trylock(obj->base.resv); + else + return ww_mutex_trylock(&obj->base.resv->lock, &ww->ctx); } static inline void i915_gem_object_unlock(struct drm_i915_gem_object *obj) @@ -296,6 +299,12 @@ i915_gem_object_is_shrinkable(const struct drm_i915_gem_object *obj) } static inline bool +i915_gem_object_has_self_managed_shrink_list(const struct drm_i915_gem_object *obj) +{ + return i915_gem_object_type_has(obj, I915_GEM_OBJECT_SELF_MANAGED_SHRINK_LIST); +} + +static inline bool i915_gem_object_is_proxy(const struct drm_i915_gem_object *obj) { return i915_gem_object_type_has(obj, I915_GEM_OBJECT_IS_PROXY); @@ -449,7 +458,7 @@ i915_gem_object_unpin_pages(struct drm_i915_gem_object *obj) } int __i915_gem_object_put_pages(struct drm_i915_gem_object *obj); -void i915_gem_object_truncate(struct drm_i915_gem_object *obj); +int i915_gem_object_truncate(struct drm_i915_gem_object *obj); void i915_gem_object_writeback(struct drm_i915_gem_object *obj); /** @@ -512,11 +521,18 @@ i915_gem_object_finish_access(struct drm_i915_gem_object *obj) i915_gem_object_unpin_pages(obj); } +struct dma_fence * +i915_gem_object_get_moving_fence(struct drm_i915_gem_object *obj); + +int i915_gem_object_wait_moving_fence(struct drm_i915_gem_object *obj, + bool intr); + void i915_gem_object_set_cache_coherency(struct drm_i915_gem_object *obj, unsigned int cache_level); bool i915_gem_object_can_bypass_llc(struct drm_i915_gem_object *obj); void i915_gem_object_flush_if_display(struct drm_i915_gem_object *obj); void i915_gem_object_flush_if_display_locked(struct drm_i915_gem_object *obj); +bool i915_gem_cpu_write_needs_clflush(struct drm_i915_gem_object *obj); int __must_check i915_gem_object_set_to_wc_domain(struct drm_i915_gem_object *obj, bool write); @@ -533,25 +549,15 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj, void i915_gem_object_make_unshrinkable(struct drm_i915_gem_object *obj); void i915_gem_object_make_shrinkable(struct drm_i915_gem_object *obj); +void __i915_gem_object_make_shrinkable(struct drm_i915_gem_object *obj); +void __i915_gem_object_make_purgeable(struct drm_i915_gem_object *obj); void i915_gem_object_make_purgeable(struct drm_i915_gem_object *obj); -static inline bool cpu_write_needs_clflush(struct drm_i915_gem_object *obj) -{ - if (obj->cache_dirty) - return false; - - if (!(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE)) - return true; - - /* Currently in use by HW (display engine)? Keep flushed. */ - return i915_gem_object_is_framebuffer(obj); -} - static inline void __start_cpu_write(struct drm_i915_gem_object *obj) { obj->read_domains = I915_GEM_DOMAIN_CPU; obj->write_domain = I915_GEM_DOMAIN_CPU; - if (cpu_write_needs_clflush(obj)) + if (i915_gem_cpu_write_needs_clflush(obj)) obj->cache_dirty = true; } @@ -613,6 +619,14 @@ int i915_gem_object_wait_migration(struct drm_i915_gem_object *obj, bool i915_gem_object_placement_possible(struct drm_i915_gem_object *obj, enum intel_memory_type type); +int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st, + size_t size, struct intel_memory_region *mr, + struct address_space *mapping, + unsigned int max_segment); +void shmem_sg_free_table(struct sg_table *st, struct address_space *mapping, + bool dirty, bool backup); +void __shmem_writeback(size_t size, struct address_space *mapping); + #ifdef CONFIG_MMU_NOTIFIER static inline bool i915_gem_object_is_userptr(struct drm_i915_gem_object *obj) 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 da85169006d4..f9f7e44099fe 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -34,9 +34,11 @@ struct i915_lut_handle { struct drm_i915_gem_object_ops { unsigned int flags; -#define I915_GEM_OBJECT_IS_SHRINKABLE BIT(1) -#define I915_GEM_OBJECT_IS_PROXY BIT(2) -#define I915_GEM_OBJECT_NO_MMAP BIT(3) +#define I915_GEM_OBJECT_IS_SHRINKABLE BIT(1) +/* Skip the shrinker management in set_pages/unset_pages */ +#define I915_GEM_OBJECT_SELF_MANAGED_SHRINK_LIST BIT(2) +#define I915_GEM_OBJECT_IS_PROXY BIT(3) +#define I915_GEM_OBJECT_NO_MMAP BIT(4) /* Interface between the GEM object and its backing storage. * get_pages() is called once prior to the use of the associated set @@ -54,8 +56,11 @@ struct drm_i915_gem_object_ops { int (*get_pages)(struct drm_i915_gem_object *obj); void (*put_pages)(struct drm_i915_gem_object *obj, struct sg_table *pages); - void (*truncate)(struct drm_i915_gem_object *obj); + int (*truncate)(struct drm_i915_gem_object *obj); void (*writeback)(struct drm_i915_gem_object *obj); + int (*shrinker_release_pages)(struct drm_i915_gem_object *obj, + bool no_gpu_wait, + bool should_writeback); int (*pread)(struct drm_i915_gem_object *obj, const struct drm_i915_gem_pread *arg); @@ -486,9 +491,37 @@ struct drm_i915_gem_object { * instead go through the pin/unpin interfaces. */ atomic_t pages_pin_count; + + /** + * @shrink_pin: Prevents the pages from being made visible to + * the shrinker, while the shrink_pin is non-zero. Most users + * should pretty much never have to care about this, outside of + * some special use cases. + * + * By default most objects will start out as visible to the + * shrinker(if I915_GEM_OBJECT_IS_SHRINKABLE) as soon as the + * backing pages are attached to the object, like in + * __i915_gem_object_set_pages(). They will then be removed the + * shrinker list once the pages are released. + * + * The @shrink_pin is incremented by calling + * i915_gem_object_make_unshrinkable(), which will also remove + * the object from the shrinker list, if the pin count was zero. + * + * Callers will then typically call + * i915_gem_object_make_shrinkable() or + * i915_gem_object_make_purgeable() to decrement the pin count, + * and make the pages visible again. + */ atomic_t shrink_pin; /** + * @ttm_shrinkable: True when the object is using shmem pages + * underneath. Protected by the object lock. + */ + bool ttm_shrinkable; + + /** * Priority list of potential placements for this object. */ struct intel_memory_region **placements; @@ -512,6 +545,7 @@ struct drm_i915_gem_object { */ struct list_head region_link; + struct i915_refct_sgt *rsgt; struct sg_table *pages; void *mapping; @@ -547,7 +581,7 @@ struct drm_i915_gem_object { struct i915_gem_object_page_iter get_dma_page; /** - * Element within i915->mm.unbound_list or i915->mm.bound_list, + * Element within i915->mm.shrink_list or i915->mm.purge_list, * locked by i915->mm.obj_lock. */ struct list_head link; @@ -565,7 +599,7 @@ struct drm_i915_gem_object { } mm; struct { - struct sg_table *cached_io_st; + struct i915_refct_sgt *cached_io_rsgt; struct i915_gem_object_page_iter get_io_page; struct drm_i915_gem_object *backup; bool created:1; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index 8eb1c3a6fc9c..89b70f5cde7a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -26,6 +26,7 @@ void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj, /* Make the pages coherent with the GPU (flushing any swapin). */ if (obj->cache_dirty) { + WARN_ON_ONCE(IS_DGFX(i915)); obj->write_domain = 0; if (i915_gem_object_has_struct_page(obj)) drm_clflush_sg(pages); @@ -68,7 +69,7 @@ void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj, shrinkable = false; } - if (shrinkable) { + if (shrinkable && !i915_gem_object_has_self_managed_shrink_list(obj)) { struct list_head *list; unsigned long flags; @@ -158,11 +159,13 @@ retry: } /* Immediately discard the backing storage */ -void i915_gem_object_truncate(struct drm_i915_gem_object *obj) +int i915_gem_object_truncate(struct drm_i915_gem_object *obj) { drm_gem_free_mmap_offset(&obj->base); if (obj->ops->truncate) - obj->ops->truncate(obj); + return obj->ops->truncate(obj); + + return 0; } /* Try to discard unwanted pages */ @@ -208,7 +211,8 @@ __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj) if (i915_gem_object_is_volatile(obj)) obj->mm.madv = I915_MADV_WILLNEED; - i915_gem_object_make_unshrinkable(obj); + if (!i915_gem_object_has_self_managed_shrink_list(obj)) + i915_gem_object_make_unshrinkable(obj); if (obj->mm.mapping) { unmap_object(obj, page_mask_bits(obj->mm.mapping)); @@ -414,8 +418,13 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj, } if (!ptr) { - if (GEM_WARN_ON(type == I915_MAP_WC && - !static_cpu_has(X86_FEATURE_PAT))) + err = i915_gem_object_wait_moving_fence(obj, true); + if (err) { + ptr = ERR_PTR(err); + goto err_unpin; + } + + if (GEM_WARN_ON(type == I915_MAP_WC && !pat_enabled())) ptr = ERR_PTR(-ENODEV); else if (i915_gem_object_has_struct_page(obj)) ptr = i915_gem_object_map_page(obj, type); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/i915_gem_phys.c index 7986612f48fa..ca6faffcc496 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_phys.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_phys.c @@ -19,6 +19,7 @@ static int i915_gem_object_get_pages_phys(struct drm_i915_gem_object *obj) { struct address_space *mapping = obj->base.filp->f_mapping; + struct drm_i915_private *i915 = to_i915(obj->base.dev); struct scatterlist *sg; struct sg_table *st; dma_addr_t dma; @@ -73,7 +74,7 @@ static int i915_gem_object_get_pages_phys(struct drm_i915_gem_object *obj) dst += PAGE_SIZE; } - intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt); + intel_gt_chipset_flush(to_gt(i915)); /* We're no longer struct page backed */ obj->mem_flags &= ~I915_BO_FLAG_STRUCT_PAGE; @@ -140,6 +141,7 @@ int i915_gem_object_pwrite_phys(struct drm_i915_gem_object *obj, { void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset; char __user *user_data = u64_to_user_ptr(args->data_ptr); + struct drm_i915_private *i915 = to_i915(obj->base.dev); int err; err = i915_gem_object_wait(obj, @@ -159,7 +161,7 @@ int i915_gem_object_pwrite_phys(struct drm_i915_gem_object *obj, return -EFAULT; drm_clflush_virt_range(vaddr, args->size); - intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt); + intel_gt_chipset_flush(to_gt(i915)); i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU); return 0; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c index 726b40e1fbb0..ac56124760e1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c @@ -35,7 +35,7 @@ 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(&i915->gt); + intel_gt_suspend_prepare(to_gt(i915)); i915_gem_drain_freed_objects(i915); } @@ -153,7 +153,7 @@ void i915_gem_suspend_late(struct drm_i915_private *i915) * machine in an unusable condition. */ - intel_gt_suspend_late(&i915->gt); + intel_gt_suspend_late(to_gt(i915)); spin_lock_irqsave(&i915->mm.obj_lock, flags); for (phase = phases; *phase; phase++) { @@ -223,7 +223,7 @@ 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(&i915->gt); + intel_gt_resume(to_gt(i915)); ret = lmem_restore(i915, I915_TTM_BACKUP_ALLOW_GPU); GEM_WARN_ON(ret); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.c b/drivers/gpu/drm/i915/gem/i915_gem_region.c index a016ccec36f3..a4350227e9ae 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_region.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_region.c @@ -11,7 +11,7 @@ void i915_gem_object_init_memory_region(struct drm_i915_gem_object *obj, struct intel_memory_region *mem) { - obj->mm.region = intel_memory_region_get(mem); + obj->mm.region = mem; mutex_lock(&mem->objects.lock); list_add(&obj->mm.region_link, &mem->objects.list); @@ -25,8 +25,6 @@ void i915_gem_object_release_memory_region(struct drm_i915_gem_object *obj) mutex_lock(&mem->objects.lock); list_del(&obj->mm.region_link); mutex_unlock(&mem->objects.lock); - - intel_memory_region_put(mem); } struct drm_i915_gem_object * diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index d77da59fae04..cc9fe258fba7 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -25,62 +25,67 @@ static void check_release_pagevec(struct pagevec *pvec) cond_resched(); } -static int shmem_get_pages(struct drm_i915_gem_object *obj) +void shmem_sg_free_table(struct sg_table *st, struct address_space *mapping, + bool dirty, bool backup) { - struct drm_i915_private *i915 = to_i915(obj->base.dev); - struct intel_memory_region *mem = obj->mm.region; - const unsigned long page_count = obj->base.size / PAGE_SIZE; + struct sgt_iter sgt_iter; + struct pagevec pvec; + struct page *page; + + mapping_clear_unevictable(mapping); + + pagevec_init(&pvec); + for_each_sgt_page(page, sgt_iter, st) { + if (dirty) + set_page_dirty(page); + + if (backup) + mark_page_accessed(page); + + if (!pagevec_add(&pvec, page)) + check_release_pagevec(&pvec); + } + if (pagevec_count(&pvec)) + check_release_pagevec(&pvec); + + sg_free_table(st); +} + +int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st, + size_t size, struct intel_memory_region *mr, + struct address_space *mapping, + unsigned int max_segment) +{ + const unsigned long page_count = size / PAGE_SIZE; unsigned long i; - struct address_space *mapping; - struct sg_table *st; struct scatterlist *sg; - struct sgt_iter sgt_iter; struct page *page; unsigned long last_pfn = 0; /* suppress gcc warning */ - unsigned int max_segment = i915_sg_segment_size(); - unsigned int sg_page_sizes; gfp_t noreclaim; int ret; /* - * Assert that the object is not currently in any GPU domain. As it - * wasn't in the GTT, there shouldn't be any way it could have been in - * a GPU cache - */ - GEM_BUG_ON(obj->read_domains & I915_GEM_GPU_DOMAINS); - GEM_BUG_ON(obj->write_domain & I915_GEM_GPU_DOMAINS); - - /* * If there's no chance of allocating enough pages for the whole * object, bail early. */ - if (obj->base.size > resource_size(&mem->region)) + if (size > resource_size(&mr->region)) return -ENOMEM; - st = kmalloc(sizeof(*st), GFP_KERNEL); - if (!st) + if (sg_alloc_table(st, page_count, GFP_KERNEL)) return -ENOMEM; -rebuild_st: - if (sg_alloc_table(st, page_count, GFP_KERNEL)) { - kfree(st); - return -ENOMEM; - } - /* * Get the list of pages out of our struct file. They'll be pinned * at this point until we release them. * * Fail silently without starting the shrinker */ - mapping = obj->base.filp->f_mapping; mapping_set_unevictable(mapping); noreclaim = mapping_gfp_constraint(mapping, ~__GFP_RECLAIM); noreclaim |= __GFP_NORETRY | __GFP_NOWARN; sg = st->sgl; st->nents = 0; - sg_page_sizes = 0; for (i = 0; i < page_count; i++) { const unsigned int shrink[] = { I915_SHRINK_BOUND | I915_SHRINK_UNBOUND, @@ -135,10 +140,9 @@ rebuild_st: if (!i || sg->length >= max_segment || page_to_pfn(page) != last_pfn + 1) { - if (i) { - sg_page_sizes |= sg->length; + if (i) sg = sg_next(sg); - } + st->nents++; sg_set_page(sg, page, PAGE_SIZE, 0); } else { @@ -149,14 +153,67 @@ rebuild_st: /* Check that the i965g/gm workaround works. */ GEM_BUG_ON(gfp & __GFP_DMA32 && last_pfn >= 0x00100000UL); } - if (sg) { /* loop terminated early; short sg table */ - sg_page_sizes |= sg->length; + if (sg) /* loop terminated early; short sg table */ sg_mark_end(sg); - } /* Trim unused sg entries to avoid wasting memory. */ i915_sg_trim(st); + return 0; +err_sg: + sg_mark_end(sg); + if (sg != st->sgl) { + shmem_sg_free_table(st, mapping, false, false); + } else { + mapping_clear_unevictable(mapping); + sg_free_table(st); + } + + /* + * shmemfs first checks if there is enough memory to allocate the page + * and reports ENOSPC should there be insufficient, along with the usual + * ENOMEM for a genuine allocation failure. + * + * We use ENOSPC in our driver to mean that we have run out of aperture + * space and so want to translate the error from shmemfs back to our + * usual understanding of ENOMEM. + */ + if (ret == -ENOSPC) + ret = -ENOMEM; + + return ret; +} + +static int shmem_get_pages(struct drm_i915_gem_object *obj) +{ + struct drm_i915_private *i915 = to_i915(obj->base.dev); + struct intel_memory_region *mem = obj->mm.region; + struct address_space *mapping = obj->base.filp->f_mapping; + const unsigned long page_count = obj->base.size / PAGE_SIZE; + unsigned int max_segment = i915_sg_segment_size(); + struct sg_table *st; + struct sgt_iter sgt_iter; + struct page *page; + int ret; + + /* + * Assert that the object is not currently in any GPU domain. As it + * wasn't in the GTT, there shouldn't be any way it could have been in + * a GPU cache + */ + GEM_BUG_ON(obj->read_domains & I915_GEM_GPU_DOMAINS); + GEM_BUG_ON(obj->write_domain & I915_GEM_GPU_DOMAINS); + +rebuild_st: + st = kmalloc(sizeof(*st), GFP_KERNEL); + if (!st) + return -ENOMEM; + + ret = shmem_sg_alloc_table(i915, st, obj->base.size, mem, mapping, + max_segment); + if (ret) + goto err_st; + ret = i915_gem_gtt_prepare_pages(obj, st); if (ret) { /* @@ -168,6 +225,7 @@ rebuild_st: for_each_sgt_page(page, sgt_iter, st) put_page(page); sg_free_table(st); + kfree(st); max_segment = PAGE_SIZE; goto rebuild_st; @@ -185,28 +243,12 @@ rebuild_st: if (i915_gem_object_can_bypass_llc(obj)) obj->cache_dirty = true; - __i915_gem_object_set_pages(obj, st, sg_page_sizes); + __i915_gem_object_set_pages(obj, st, i915_sg_dma_sizes(st->sgl)); return 0; -err_sg: - sg_mark_end(sg); err_pages: - mapping_clear_unevictable(mapping); - if (sg != st->sgl) { - struct pagevec pvec; - - pagevec_init(&pvec); - for_each_sgt_page(page, sgt_iter, st) { - if (!pagevec_add(&pvec, page)) - check_release_pagevec(&pvec); - } - if (pagevec_count(&pvec)) - check_release_pagevec(&pvec); - } - sg_free_table(st); - kfree(st); - + shmem_sg_free_table(st, mapping, false, false); /* * shmemfs first checks if there is enough memory to allocate the page * and reports ENOSPC should there be insufficient, along with the usual @@ -216,13 +258,16 @@ err_pages: * space and so want to translate the error from shmemfs back to our * usual understanding of ENOMEM. */ +err_st: if (ret == -ENOSPC) ret = -ENOMEM; + kfree(st); + return ret; } -static void +static int shmem_truncate(struct drm_i915_gem_object *obj) { /* @@ -234,12 +279,12 @@ shmem_truncate(struct drm_i915_gem_object *obj) shmem_truncate_range(file_inode(obj->base.filp), 0, (loff_t)-1); obj->mm.madv = __I915_MADV_PURGED; obj->mm.pages = ERR_PTR(-EFAULT); + + return 0; } -static void -shmem_writeback(struct drm_i915_gem_object *obj) +void __shmem_writeback(size_t size, struct address_space *mapping) { - struct address_space *mapping; struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, .nr_to_write = SWAP_CLUSTER_MAX, @@ -255,10 +300,9 @@ shmem_writeback(struct drm_i915_gem_object *obj) * instead of invoking writeback so they are aged and paged out * as normal. */ - mapping = obj->base.filp->f_mapping; /* Begin writeback on each dirty page */ - for (i = 0; i < obj->base.size >> PAGE_SHIFT; i++) { + for (i = 0; i < size >> PAGE_SHIFT; i++) { struct page *page; page = find_lock_page(mapping, i); @@ -281,6 +325,12 @@ put: } } +static void +shmem_writeback(struct drm_i915_gem_object *obj) +{ + __shmem_writeback(obj->base.size, obj->base.filp->f_mapping); +} + void __i915_gem_object_release_shmem(struct drm_i915_gem_object *obj, struct sg_table *pages, @@ -313,11 +363,6 @@ __i915_gem_object_release_shmem(struct drm_i915_gem_object *obj, void i915_gem_object_put_pages_shmem(struct drm_i915_gem_object *obj, struct sg_table *pages) { - struct sgt_iter sgt_iter; - struct pagevec pvec; - struct page *page; - - GEM_WARN_ON(IS_DGFX(to_i915(obj->base.dev))); __i915_gem_object_release_shmem(obj, pages, true); i915_gem_gtt_finish_pages(obj, pages); @@ -325,25 +370,10 @@ void i915_gem_object_put_pages_shmem(struct drm_i915_gem_object *obj, struct sg_ if (i915_gem_object_needs_bit17_swizzle(obj)) i915_gem_object_save_bit_17_swizzle(obj, pages); - mapping_clear_unevictable(file_inode(obj->base.filp)->i_mapping); - - pagevec_init(&pvec); - for_each_sgt_page(page, sgt_iter, pages) { - if (obj->mm.dirty) - set_page_dirty(page); - - if (obj->mm.madv == I915_MADV_WILLNEED) - mark_page_accessed(page); - - if (!pagevec_add(&pvec, page)) - check_release_pagevec(&pvec); - } - if (pagevec_count(&pvec)) - check_release_pagevec(&pvec); - obj->mm.dirty = false; - - sg_free_table(pages); + shmem_sg_free_table(pages, file_inode(obj->base.filp)->i_mapping, + obj->mm.dirty, obj->mm.madv == I915_MADV_WILLNEED); kfree(pages); + obj->mm.dirty = false; } static void @@ -634,9 +664,10 @@ static int init_shmem(struct intel_memory_region *mem) return 0; /* Don't error, we can simply fallback to the kernel mnt */ } -static void release_shmem(struct intel_memory_region *mem) +static int release_shmem(struct intel_memory_region *mem) { i915_gemfs_fini(mem->i915); + return 0; } static const struct intel_memory_region_ops shmem_region_ops = { diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c index 5ab136ffdeb2..cc927e49d21f 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c @@ -15,7 +15,6 @@ #include "gt/intel_gt_requests.h" -#include "dma_resv_utils.h" #include "i915_trace.h" static bool swap_available(void) @@ -37,8 +36,8 @@ static bool can_release_pages(struct drm_i915_gem_object *obj) return swap_available() || obj->mm.madv == I915_MADV_DONTNEED; } -static bool unsafe_drop_pages(struct drm_i915_gem_object *obj, - unsigned long shrink, bool trylock_vm) +static int drop_pages(struct drm_i915_gem_object *obj, + unsigned long shrink, bool trylock_vm) { unsigned long flags; @@ -56,19 +55,25 @@ static bool unsafe_drop_pages(struct drm_i915_gem_object *obj, return false; } -static void try_to_writeback(struct drm_i915_gem_object *obj, - unsigned int flags) +static int try_to_writeback(struct drm_i915_gem_object *obj, unsigned int flags) { + if (obj->ops->shrinker_release_pages) + return obj->ops->shrinker_release_pages(obj, + !(flags & I915_SHRINK_ACTIVE), + flags & I915_SHRINK_WRITEBACK); + switch (obj->mm.madv) { case I915_MADV_DONTNEED: i915_gem_object_truncate(obj); - return; + return 0; case __I915_MADV_PURGED: - return; + return 0; } if (flags & I915_SHRINK_WRITEBACK) i915_gem_object_writeback(obj); + + return 0; } /** @@ -148,7 +153,7 @@ i915_gem_shrink(struct i915_gem_ww_ctx *ww, */ if (shrink & I915_SHRINK_ACTIVE) /* Retire requests to unpin all idle contexts */ - intel_gt_retire_requests(&i915->gt); + intel_gt_retire_requests(to_gt(i915)); /* * As we may completely rewrite the (un)bound list whilst unbinding @@ -209,27 +214,23 @@ i915_gem_shrink(struct i915_gem_ww_ctx *ww, spin_unlock_irqrestore(&i915->mm.obj_lock, flags); - err = 0; - if (unsafe_drop_pages(obj, shrink, trylock_vm)) { - /* May arrive from get_pages on another bo */ - if (!ww) { - if (!i915_gem_object_trylock(obj)) - goto skip; - } else { - err = i915_gem_object_lock(obj, ww); - if (err) - goto skip; - } - - if (!__i915_gem_object_put_pages(obj)) { - try_to_writeback(obj, shrink); - count += obj->base.size >> PAGE_SHIFT; - } - if (!ww) - i915_gem_object_unlock(obj); + /* May arrive from get_pages on another bo */ + if (!ww) { + if (!i915_gem_object_trylock(obj, NULL)) + goto skip; + } else { + err = i915_gem_object_lock(obj, ww); + if (err) + goto skip; } - dma_resv_prune(obj->base.resv); + if (drop_pages(obj, shrink, trylock_vm) && + !__i915_gem_object_put_pages(obj) && + !try_to_writeback(obj, shrink)) + count += obj->base.size >> PAGE_SHIFT; + + if (!ww) + i915_gem_object_unlock(obj); scanned += obj->base.size >> PAGE_SHIFT; skip: @@ -404,12 +405,18 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr list_for_each_entry_safe(vma, next, &i915->ggtt.vm.bound_list, vm_link) { unsigned long count = vma->node.size >> PAGE_SHIFT; + struct drm_i915_gem_object *obj = vma->obj; if (!vma->iomap || i915_vma_is_active(vma)) continue; + if (!i915_gem_object_trylock(obj, NULL)) + continue; + if (__i915_vma_unbind(vma) == 0) freed_pages += count; + + i915_gem_object_unlock(obj); } mutex_unlock(&i915->ggtt.vm.mutex); @@ -458,6 +465,16 @@ void i915_gem_shrinker_taints_mutex(struct drm_i915_private *i915, #define obj_to_i915(obj__) to_i915((obj__)->base.dev) +/** + * i915_gem_object_make_unshrinkable - Hide the object from the shrinker. By + * default all object types that support shrinking(see IS_SHRINKABLE), will also + * make the object visible to the shrinker after allocating the system memory + * pages. + * @obj: The GEM object. + * + * This is typically used for special kernel internal objects that can't be + * easily processed by the shrinker, like if they are perma-pinned. + */ void i915_gem_object_make_unshrinkable(struct drm_i915_gem_object *obj) { struct drm_i915_private *i915 = obj_to_i915(obj); @@ -482,13 +499,12 @@ void i915_gem_object_make_unshrinkable(struct drm_i915_gem_object *obj) spin_unlock_irqrestore(&i915->mm.obj_lock, flags); } -static void __i915_gem_object_make_shrinkable(struct drm_i915_gem_object *obj, - struct list_head *head) +static void ___i915_gem_object_make_shrinkable(struct drm_i915_gem_object *obj, + struct list_head *head) { struct drm_i915_private *i915 = obj_to_i915(obj); unsigned long flags; - GEM_BUG_ON(!i915_gem_object_has_pages(obj)); if (!i915_gem_object_is_shrinkable(obj)) return; @@ -508,14 +524,67 @@ static void __i915_gem_object_make_shrinkable(struct drm_i915_gem_object *obj, spin_unlock_irqrestore(&i915->mm.obj_lock, flags); } +/** + * __i915_gem_object_make_shrinkable - Move the object to the tail of the + * shrinkable list. Objects on this list might be swapped out. Used with + * WILLNEED objects. + * @obj: The GEM object. + * + * DO NOT USE. This is intended to be called on very special objects that don't + * yet have mm.pages, but are guaranteed to have potentially reclaimable pages + * underneath. + */ +void __i915_gem_object_make_shrinkable(struct drm_i915_gem_object *obj) +{ + ___i915_gem_object_make_shrinkable(obj, + &obj_to_i915(obj)->mm.shrink_list); +} + +/** + * __i915_gem_object_make_purgeable - Move the object to the tail of the + * purgeable list. Objects on this list might be swapped out. Used with + * DONTNEED objects. + * @obj: The GEM object. + * + * DO NOT USE. This is intended to be called on very special objects that don't + * yet have mm.pages, but are guaranteed to have potentially reclaimable pages + * underneath. + */ +void __i915_gem_object_make_purgeable(struct drm_i915_gem_object *obj) +{ + ___i915_gem_object_make_shrinkable(obj, + &obj_to_i915(obj)->mm.purge_list); +} + +/** + * i915_gem_object_make_shrinkable - Move the object to the tail of the + * shrinkable list. Objects on this list might be swapped out. Used with + * WILLNEED objects. + * @obj: The GEM object. + * + * MUST only be called on objects which have backing pages. + * + * MUST be balanced with previous call to i915_gem_object_make_unshrinkable(). + */ void i915_gem_object_make_shrinkable(struct drm_i915_gem_object *obj) { - __i915_gem_object_make_shrinkable(obj, - &obj_to_i915(obj)->mm.shrink_list); + GEM_BUG_ON(!i915_gem_object_has_pages(obj)); + __i915_gem_object_make_shrinkable(obj); } +/** + * i915_gem_object_make_purgeable - Move the object to the tail of the purgeable + * list. Used with DONTNEED objects. Unlike with shrinkable objects, the + * shrinker will attempt to discard the backing pages, instead of trying to swap + * them out. + * @obj: The GEM object. + * + * MUST only be called on objects which have backing pages. + * + * MUST be balanced with previous call to i915_gem_object_make_unshrinkable(). + */ void i915_gem_object_make_purgeable(struct drm_i915_gem_object *obj) { - __i915_gem_object_make_shrinkable(obj, - &obj_to_i915(obj)->mm.purge_list); + GEM_BUG_ON(!i915_gem_object_has_pages(obj)); + __i915_gem_object_make_purgeable(obj); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c index ddd37ccb1362..7df50fd6cc7b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c @@ -399,7 +399,7 @@ static int i915_gem_init_stolen(struct intel_memory_region *mem) return 0; } - if (intel_vtd_active() && GRAPHICS_VER(i915) < 8) { + if (intel_vtd_active(i915) && GRAPHICS_VER(i915) < 8) { drm_notice(&i915->drm, "%s, disabling use of stolen memory\n", "DMAR active"); @@ -488,6 +488,9 @@ static int i915_gem_init_stolen(struct intel_memory_region *mem) return 0; } + /* Exclude the reserved region from driver use */ + mem->region.end = reserved_base - 1; + /* 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; @@ -653,7 +656,7 @@ static int __i915_gem_object_create_stolen(struct intel_memory_region *mem, cache_level = HAS_LLC(mem->i915) ? I915_CACHE_LLC : I915_CACHE_NONE; i915_gem_object_set_cache_coherency(obj, cache_level); - if (WARN_ON(!i915_gem_object_trylock(obj))) + if (WARN_ON(!i915_gem_object_trylock(obj, NULL))) return -EBUSY; i915_gem_object_init_memory_region(obj, mem); @@ -720,9 +723,10 @@ static int init_stolen_smem(struct intel_memory_region *mem) return i915_gem_init_stolen(mem); } -static void release_stolen_smem(struct intel_memory_region *mem) +static int release_stolen_smem(struct intel_memory_region *mem) { i915_gem_cleanup_stolen(mem->i915); + return 0; } static const struct intel_memory_region_ops i915_region_stolen_smem_ops = { @@ -759,10 +763,11 @@ err_fini: return err; } -static void release_stolen_lmem(struct intel_memory_region *mem) +static int release_stolen_lmem(struct intel_memory_region *mem) { io_mapping_fini(&mem->iomap); i915_gem_cleanup_stolen(mem->i915); + return 0; } static const struct intel_memory_region_ops i915_region_stolen_lmem_ops = { @@ -778,6 +783,7 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type, struct intel_uncore *uncore = &i915->uncore; struct pci_dev *pdev = to_pci_dev(i915->drm.dev); struct intel_memory_region *mem; + resource_size_t min_page_size; resource_size_t io_start; resource_size_t lmem_size; u64 lmem_base; @@ -789,8 +795,11 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type, lmem_size = pci_resource_len(pdev, 2) - lmem_base; io_start = pci_resource_start(pdev, 2) + lmem_base; + min_page_size = HAS_64K_PAGES(i915) ? I915_GTT_PAGE_SIZE_64K : + I915_GTT_PAGE_SIZE_4K; + mem = intel_memory_region_create(i915, lmem_base, lmem_size, - I915_GTT_PAGE_SIZE_4K, io_start, + min_page_size, io_start, type, instance, &i915_region_stolen_lmem_ops); if (IS_ERR(mem)) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_throttle.c b/drivers/gpu/drm/i915/gem/i915_gem_throttle.c index 1929d6cf4150..75501db71041 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_throttle.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_throttle.c @@ -38,12 +38,13 @@ i915_gem_throttle_ioctl(struct drm_device *dev, void *data, { const unsigned long recent_enough = jiffies - DRM_I915_THROTTLE_JIFFIES; struct drm_i915_file_private *file_priv = file->driver_priv; + struct drm_i915_private *i915 = to_i915(dev); struct i915_gem_context *ctx; unsigned long idx; long ret; /* ABI: return -EIO if already wedged */ - ret = intel_gt_terminally_wedged(&to_i915(dev)->gt); + ret = intel_gt_terminally_wedged(to_gt(i915)); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index 74a1ffd0d7dd..923cc7ad8d70 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -14,13 +14,9 @@ #include "gem/i915_gem_object.h" #include "gem/i915_gem_region.h" #include "gem/i915_gem_ttm.h" +#include "gem/i915_gem_ttm_move.h" #include "gem/i915_gem_ttm_pm.h" - -#include "gt/intel_engine_pm.h" -#include "gt/intel_gt.h" -#include "gt/intel_migrate.h" - #define I915_TTM_PRIO_PURGE 0 #define I915_TTM_PRIO_NO_PAGES 1 #define I915_TTM_PRIO_HAS_PAGES 2 @@ -34,7 +30,9 @@ * struct i915_ttm_tt - TTM page vector with additional private information * @ttm: The base TTM page vector. * @dev: The struct device used for dma mapping and unmapping. - * @cached_st: The cached scatter-gather table. + * @cached_rsgt: The cached scatter-gather table. + * @is_shmem: Set if using shmem. + * @filp: The shmem file, if using shmem backend. * * Note that DMA may be going on right up to the point where the page- * vector is unpopulated in delayed destroy. Hence keep the @@ -45,7 +43,10 @@ struct i915_ttm_tt { struct ttm_tt ttm; struct device *dev; - struct sg_table *cached_st; + struct i915_refct_sgt cached_rsgt; + + bool is_shmem; + struct file *filp; }; static const struct ttm_place sys_placement_flags = { @@ -103,37 +104,15 @@ static int i915_ttm_err_to_gem(int err) return err; } -static bool gpu_binds_iomem(struct ttm_resource *mem) -{ - return mem->mem_type != TTM_PL_SYSTEM; -} - -static bool cpu_maps_iomem(struct ttm_resource *mem) -{ - /* Once / if we support GGTT, this is also false for cached ttm_tts */ - return mem->mem_type != TTM_PL_SYSTEM; -} - -static enum i915_cache_level -i915_ttm_cache_level(struct drm_i915_private *i915, struct ttm_resource *res, - struct ttm_tt *ttm) -{ - return ((HAS_LLC(i915) || HAS_SNOOP(i915)) && !gpu_binds_iomem(res) && - ttm->caching == ttm_cached) ? I915_CACHE_LLC : - I915_CACHE_NONE; -} - -static void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj); - static enum ttm_caching i915_ttm_select_tt_caching(const struct drm_i915_gem_object *obj) { /* - * Objects only allowed in system get cached cpu-mappings. - * Other objects get WC mapping for now. Even if in system. + * Objects only allowed in system get cached cpu-mappings, or when + * evicting lmem-only buffers to system for swapping. Other objects get + * WC mapping for now. Even if in system. */ - if (obj->mm.region->type == INTEL_MEMORY_SYSTEM && - obj->mm.n_placements <= 1) + if (obj->mm.n_placements <= 1) return ttm_cached; return ttm_write_combined; @@ -179,15 +158,103 @@ i915_ttm_placement_from_obj(const struct drm_i915_gem_object *obj, placement->busy_placement = busy; } +static int i915_ttm_tt_shmem_populate(struct ttm_device *bdev, + struct ttm_tt *ttm, + struct ttm_operation_ctx *ctx) +{ + struct drm_i915_private *i915 = container_of(bdev, typeof(*i915), bdev); + struct intel_memory_region *mr = i915->mm.regions[INTEL_MEMORY_SYSTEM]; + struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm); + const unsigned int max_segment = i915_sg_segment_size(); + const size_t size = (size_t)ttm->num_pages << PAGE_SHIFT; + struct file *filp = i915_tt->filp; + struct sgt_iter sgt_iter; + struct sg_table *st; + struct page *page; + unsigned long i; + int err; + + if (!filp) { + struct address_space *mapping; + gfp_t mask; + + filp = shmem_file_setup("i915-shmem-tt", size, VM_NORESERVE); + if (IS_ERR(filp)) + return PTR_ERR(filp); + + mask = GFP_HIGHUSER | __GFP_RECLAIMABLE; + + mapping = filp->f_mapping; + mapping_set_gfp_mask(mapping, mask); + GEM_BUG_ON(!(mapping_gfp_mask(mapping) & __GFP_RECLAIM)); + + i915_tt->filp = filp; + } + + st = &i915_tt->cached_rsgt.table; + err = shmem_sg_alloc_table(i915, st, size, mr, filp->f_mapping, + max_segment); + if (err) + return err; + + err = dma_map_sgtable(i915_tt->dev, st, DMA_BIDIRECTIONAL, + DMA_ATTR_SKIP_CPU_SYNC); + if (err) + goto err_free_st; + + i = 0; + for_each_sgt_page(page, sgt_iter, st) + ttm->pages[i++] = page; + + if (ttm->page_flags & TTM_TT_FLAG_SWAPPED) + ttm->page_flags &= ~TTM_TT_FLAG_SWAPPED; + + return 0; + +err_free_st: + shmem_sg_free_table(st, filp->f_mapping, false, false); + + return err; +} + +static void i915_ttm_tt_shmem_unpopulate(struct ttm_tt *ttm) +{ + struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm); + bool backup = ttm->page_flags & TTM_TT_FLAG_SWAPPED; + struct sg_table *st = &i915_tt->cached_rsgt.table; + + shmem_sg_free_table(st, file_inode(i915_tt->filp)->i_mapping, + backup, backup); +} + +static void i915_ttm_tt_release(struct kref *ref) +{ + struct i915_ttm_tt *i915_tt = + container_of(ref, typeof(*i915_tt), cached_rsgt.kref); + struct sg_table *st = &i915_tt->cached_rsgt.table; + + GEM_WARN_ON(st->sgl); + + kfree(i915_tt); +} + +static const struct i915_refct_sgt_ops tt_rsgt_ops = { + .release = i915_ttm_tt_release +}; + static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo, uint32_t page_flags) { struct ttm_resource_manager *man = ttm_manager_type(bo->bdev, bo->resource->mem_type); struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); + enum ttm_caching caching; struct i915_ttm_tt *i915_tt; int ret; + if (!obj) + return NULL; + i915_tt = kzalloc(sizeof(*i915_tt), GFP_KERNEL); if (!i915_tt) return NULL; @@ -196,38 +263,66 @@ static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo, man->use_tt) page_flags |= TTM_TT_FLAG_ZERO_ALLOC; - ret = ttm_tt_init(&i915_tt->ttm, bo, page_flags, - i915_ttm_select_tt_caching(obj)); - if (ret) { - kfree(i915_tt); - return NULL; + caching = i915_ttm_select_tt_caching(obj); + if (i915_gem_object_is_shrinkable(obj) && caching == ttm_cached) { + page_flags |= TTM_TT_FLAG_EXTERNAL | + TTM_TT_FLAG_EXTERNAL_MAPPABLE; + i915_tt->is_shmem = true; } + ret = ttm_tt_init(&i915_tt->ttm, bo, page_flags, caching); + if (ret) + goto err_free; + + __i915_refct_sgt_init(&i915_tt->cached_rsgt, bo->base.size, + &tt_rsgt_ops); + i915_tt->dev = obj->base.dev->dev; return &i915_tt->ttm; + +err_free: + kfree(i915_tt); + return NULL; +} + +static int i915_ttm_tt_populate(struct ttm_device *bdev, + struct ttm_tt *ttm, + struct ttm_operation_ctx *ctx) +{ + struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm); + + if (i915_tt->is_shmem) + return i915_ttm_tt_shmem_populate(bdev, ttm, ctx); + + return ttm_pool_alloc(&bdev->pool, ttm, ctx); } static void i915_ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm) { struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm); + struct sg_table *st = &i915_tt->cached_rsgt.table; - if (i915_tt->cached_st) { - dma_unmap_sgtable(i915_tt->dev, i915_tt->cached_st, - DMA_BIDIRECTIONAL, 0); - sg_free_table(i915_tt->cached_st); - kfree(i915_tt->cached_st); - i915_tt->cached_st = NULL; + if (st->sgl) + dma_unmap_sgtable(i915_tt->dev, st, DMA_BIDIRECTIONAL, 0); + + if (i915_tt->is_shmem) { + i915_ttm_tt_shmem_unpopulate(ttm); + } else { + sg_free_table(st); + ttm_pool_free(&bdev->pool, ttm); } - ttm_pool_free(&bdev->pool, ttm); } static void i915_ttm_tt_destroy(struct ttm_device *bdev, struct ttm_tt *ttm) { struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm); + if (i915_tt->filp) + fput(i915_tt->filp); + ttm_tt_fini(ttm); - kfree(i915_tt); + i915_refct_sgt_put(&i915_tt->cached_rsgt); } static bool i915_ttm_eviction_valuable(struct ttm_buffer_object *bo, @@ -235,6 +330,17 @@ static bool i915_ttm_eviction_valuable(struct ttm_buffer_object *bo, { struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); + if (!obj) + return false; + + /* + * EXTERNAL objects should never be swapped out by TTM, instead we need + * to handle that ourselves. TTM will already skip such objects for us, + * but we would like to avoid grabbing locks for no good reason. + */ + if (bo->ttm && bo->ttm->page_flags & TTM_TT_FLAG_EXTERNAL) + return false; + /* Will do for now. Our pinned objects are still on TTM's LRU lists */ return i915_gem_object_evictable(obj); } @@ -245,28 +351,19 @@ static void i915_ttm_evict_flags(struct ttm_buffer_object *bo, *placement = i915_sys_placement; } -static int i915_ttm_move_notify(struct ttm_buffer_object *bo) -{ - struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); - int ret; - - ret = i915_gem_object_unbind(obj, I915_GEM_OBJECT_UNBIND_ACTIVE); - if (ret) - return ret; - - ret = __i915_gem_object_put_pages(obj); - if (ret) - return ret; - - return 0; -} - -static void i915_ttm_free_cached_io_st(struct drm_i915_gem_object *obj) +/** + * i915_ttm_free_cached_io_rsgt - Free object cached LMEM information + * @obj: The GEM object + * This function frees any LMEM-related information that is cached on + * the object. For example the radix tree for fast page lookup and the + * cached refcounted sg-table + */ +void i915_ttm_free_cached_io_rsgt(struct drm_i915_gem_object *obj) { struct radix_tree_iter iter; void __rcu **slot; - if (!obj->ttm.cached_io_st) + if (!obj->ttm.cached_io_rsgt) return; rcu_read_lock(); @@ -274,93 +371,106 @@ static void i915_ttm_free_cached_io_st(struct drm_i915_gem_object *obj) radix_tree_delete(&obj->ttm.get_io_page.radix, iter.index); rcu_read_unlock(); - sg_free_table(obj->ttm.cached_io_st); - kfree(obj->ttm.cached_io_st); - obj->ttm.cached_io_st = NULL; + i915_refct_sgt_put(obj->ttm.cached_io_rsgt); + obj->ttm.cached_io_rsgt = NULL; } -static void -i915_ttm_adjust_domains_after_move(struct drm_i915_gem_object *obj) +/** + * i915_ttm_purge - Clear an object of its memory + * @obj: The object + * + * This function is called to clear an object of it's memory when it is + * marked as not needed anymore. + * + * Return: 0 on success, negative error code on failure. + */ +int i915_ttm_purge(struct drm_i915_gem_object *obj) { struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); + struct i915_ttm_tt *i915_tt = + container_of(bo->ttm, typeof(*i915_tt), ttm); + struct ttm_operation_ctx ctx = { + .interruptible = true, + .no_wait_gpu = false, + }; + struct ttm_placement place = {}; + int ret; - if (cpu_maps_iomem(bo->resource) || bo->ttm->caching != ttm_cached) { - obj->write_domain = I915_GEM_DOMAIN_WC; - obj->read_domains = I915_GEM_DOMAIN_WC; - } else { - obj->write_domain = I915_GEM_DOMAIN_CPU; - obj->read_domains = I915_GEM_DOMAIN_CPU; - } -} + if (obj->mm.madv == __I915_MADV_PURGED) + return 0; -static void i915_ttm_adjust_gem_after_move(struct drm_i915_gem_object *obj) -{ - struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); - unsigned int cache_level; - unsigned int i; + ret = ttm_bo_validate(bo, &place, &ctx); + if (ret) + return ret; - /* - * If object was moved to an allowable region, update the object - * region to consider it migrated. Note that if it's currently not - * in an allowable region, it's evicted and we don't update the - * object region. - */ - if (intel_region_to_ttm_type(obj->mm.region) != bo->resource->mem_type) { - for (i = 0; i < obj->mm.n_placements; ++i) { - struct intel_memory_region *mr = obj->mm.placements[i]; - - if (intel_region_to_ttm_type(mr) == bo->resource->mem_type && - mr != obj->mm.region) { - i915_gem_object_release_memory_region(obj); - i915_gem_object_init_memory_region(obj, mr); - break; - } - } + if (bo->ttm && i915_tt->filp) { + /* + * The below fput(which eventually calls shmem_truncate) might + * be delayed by worker, so when directly called to purge the + * pages(like by the shrinker) we should try to be more + * aggressive and release the pages immediately. + */ + shmem_truncate_range(file_inode(i915_tt->filp), + 0, (loff_t)-1); + fput(fetch_and_zero(&i915_tt->filp)); } - obj->mem_flags &= ~(I915_BO_FLAG_STRUCT_PAGE | I915_BO_FLAG_IOMEM); - - obj->mem_flags |= cpu_maps_iomem(bo->resource) ? I915_BO_FLAG_IOMEM : - I915_BO_FLAG_STRUCT_PAGE; + obj->write_domain = 0; + obj->read_domains = 0; + i915_ttm_adjust_gem_after_move(obj); + i915_ttm_free_cached_io_rsgt(obj); + obj->mm.madv = __I915_MADV_PURGED; - cache_level = i915_ttm_cache_level(to_i915(bo->base.dev), bo->resource, - bo->ttm); - i915_gem_object_set_cache_coherency(obj, cache_level); + return 0; } -static void i915_ttm_purge(struct drm_i915_gem_object *obj) +static int i915_ttm_shrinker_release_pages(struct drm_i915_gem_object *obj, + bool no_wait_gpu, + bool should_writeback) { struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); + struct i915_ttm_tt *i915_tt = + container_of(bo->ttm, typeof(*i915_tt), ttm); struct ttm_operation_ctx ctx = { .interruptible = true, - .no_wait_gpu = false, + .no_wait_gpu = no_wait_gpu, }; struct ttm_placement place = {}; int ret; - if (obj->mm.madv == __I915_MADV_PURGED) - return; + if (!bo->ttm || bo->resource->mem_type != TTM_PL_SYSTEM) + return 0; + + GEM_BUG_ON(!i915_tt->is_shmem); + + if (!i915_tt->filp) + return 0; + + ret = ttm_bo_wait_ctx(bo, &ctx); + if (ret) + return ret; - /* TTM's purge interface. Note that we might be reentering. */ + switch (obj->mm.madv) { + case I915_MADV_DONTNEED: + return i915_ttm_purge(obj); + case __I915_MADV_PURGED: + return 0; + } + + if (bo->ttm->page_flags & TTM_TT_FLAG_SWAPPED) + return 0; + + bo->ttm->page_flags |= TTM_TT_FLAG_SWAPPED; ret = ttm_bo_validate(bo, &place, &ctx); - if (!ret) { - obj->write_domain = 0; - obj->read_domains = 0; - i915_ttm_adjust_gem_after_move(obj); - i915_ttm_free_cached_io_st(obj); - obj->mm.madv = __I915_MADV_PURGED; + if (ret) { + bo->ttm->page_flags &= ~TTM_TT_FLAG_SWAPPED; + return ret; } -} -static void i915_ttm_swap_notify(struct ttm_buffer_object *bo) -{ - struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); - int ret = i915_ttm_move_notify(bo); + if (should_writeback) + __shmem_writeback(obj->base.size, i915_tt->filp->f_mapping); - GEM_WARN_ON(ret); - GEM_WARN_ON(obj->ttm.cached_io_st); - if (!ret && obj->mm.madv != I915_MADV_WILLNEED) - i915_ttm_purge(obj); + return 0; } static void i915_ttm_delete_mem_notify(struct ttm_buffer_object *bo) @@ -369,232 +479,101 @@ static void i915_ttm_delete_mem_notify(struct ttm_buffer_object *bo) if (likely(obj)) { __i915_gem_object_pages_fini(obj); - i915_ttm_free_cached_io_st(obj); + i915_ttm_free_cached_io_rsgt(obj); } } -static struct intel_memory_region * -i915_ttm_region(struct ttm_device *bdev, int ttm_mem_type) -{ - struct drm_i915_private *i915 = container_of(bdev, typeof(*i915), bdev); - - /* There's some room for optimization here... */ - GEM_BUG_ON(ttm_mem_type != I915_PL_SYSTEM && - ttm_mem_type < I915_PL_LMEM0); - if (ttm_mem_type == I915_PL_SYSTEM) - return intel_memory_region_lookup(i915, INTEL_MEMORY_SYSTEM, - 0); - - return intel_memory_region_lookup(i915, INTEL_MEMORY_LOCAL, - ttm_mem_type - I915_PL_LMEM0); -} - -static struct sg_table *i915_ttm_tt_get_st(struct ttm_tt *ttm) +static struct i915_refct_sgt *i915_ttm_tt_get_st(struct ttm_tt *ttm) { struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm); struct sg_table *st; int ret; - if (i915_tt->cached_st) - return i915_tt->cached_st; - - st = kzalloc(sizeof(*st), GFP_KERNEL); - if (!st) - return ERR_PTR(-ENOMEM); + if (i915_tt->cached_rsgt.table.sgl) + return i915_refct_sgt_get(&i915_tt->cached_rsgt); + st = &i915_tt->cached_rsgt.table; ret = sg_alloc_table_from_pages_segment(st, ttm->pages, ttm->num_pages, 0, (unsigned long)ttm->num_pages << PAGE_SHIFT, i915_sg_segment_size(), GFP_KERNEL); if (ret) { - kfree(st); + st->sgl = NULL; return ERR_PTR(ret); } ret = dma_map_sgtable(i915_tt->dev, st, DMA_BIDIRECTIONAL, 0); if (ret) { sg_free_table(st); - kfree(st); return ERR_PTR(ret); } - i915_tt->cached_st = st; - return st; + return i915_refct_sgt_get(&i915_tt->cached_rsgt); } -static struct sg_table * +/** + * i915_ttm_resource_get_st - Get a refcounted sg-table pointing to the + * resource memory + * @obj: The GEM object used for sg-table caching + * @res: The struct ttm_resource for which an sg-table is requested. + * + * This function returns a refcounted sg-table representing the memory + * pointed to by @res. If @res is the object's current resource it may also + * cache the sg_table on the object or attempt to access an already cached + * sg-table. The refcounted sg-table needs to be put when no-longer in use. + * + * Return: A valid pointer to a struct i915_refct_sgt or error pointer on + * failure. + */ +struct i915_refct_sgt * i915_ttm_resource_get_st(struct drm_i915_gem_object *obj, struct ttm_resource *res) { struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); - if (!gpu_binds_iomem(res)) + if (!i915_ttm_gtt_binds_lmem(res)) return i915_ttm_tt_get_st(bo->ttm); /* * If CPU mapping differs, we need to add the ttm_tt pages to * the resulting st. Might make sense for GGTT. */ - GEM_WARN_ON(!cpu_maps_iomem(res)); - return intel_region_ttm_resource_to_st(obj->mm.region, res); -} - -static int i915_ttm_accel_move(struct ttm_buffer_object *bo, - bool clear, - struct ttm_resource *dst_mem, - struct ttm_tt *dst_ttm, - struct sg_table *dst_st) -{ - struct drm_i915_private *i915 = container_of(bo->bdev, typeof(*i915), - bdev); - struct ttm_resource_manager *src_man = - ttm_manager_type(bo->bdev, bo->resource->mem_type); - struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); - struct sg_table *src_st; - struct i915_request *rq; - struct ttm_tt *src_ttm = bo->ttm; - enum i915_cache_level src_level, dst_level; - int ret; - - if (!i915->gt.migrate.context || intel_gt_is_wedged(&i915->gt)) - return -EINVAL; + GEM_WARN_ON(!i915_ttm_cpu_maps_iomem(res)); + if (bo->resource == res) { + if (!obj->ttm.cached_io_rsgt) { + struct i915_refct_sgt *rsgt; - dst_level = i915_ttm_cache_level(i915, dst_mem, dst_ttm); - if (clear) { - if (bo->type == ttm_bo_type_kernel) - return -EINVAL; + rsgt = intel_region_ttm_resource_to_rsgt(obj->mm.region, + res); + if (IS_ERR(rsgt)) + return rsgt; - intel_engine_pm_get(i915->gt.migrate.context->engine); - ret = intel_context_migrate_clear(i915->gt.migrate.context, NULL, - dst_st->sgl, dst_level, - gpu_binds_iomem(dst_mem), - 0, &rq); - - if (!ret && rq) { - i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT); - i915_request_put(rq); - } - intel_engine_pm_put(i915->gt.migrate.context->engine); - } else { - src_st = src_man->use_tt ? i915_ttm_tt_get_st(src_ttm) : - obj->ttm.cached_io_st; - - src_level = i915_ttm_cache_level(i915, bo->resource, src_ttm); - intel_engine_pm_get(i915->gt.migrate.context->engine); - ret = intel_context_migrate_copy(i915->gt.migrate.context, - NULL, src_st->sgl, src_level, - gpu_binds_iomem(bo->resource), - dst_st->sgl, dst_level, - gpu_binds_iomem(dst_mem), - &rq); - if (!ret && rq) { - i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT); - i915_request_put(rq); + obj->ttm.cached_io_rsgt = rsgt; } - intel_engine_pm_put(i915->gt.migrate.context->engine); + return i915_refct_sgt_get(obj->ttm.cached_io_rsgt); } - return ret; -} - -static void __i915_ttm_move(struct ttm_buffer_object *bo, bool clear, - struct ttm_resource *dst_mem, - struct ttm_tt *dst_ttm, - struct sg_table *dst_st, - bool allow_accel) -{ - int ret = -EINVAL; - - if (allow_accel) - ret = i915_ttm_accel_move(bo, clear, dst_mem, dst_ttm, dst_st); - if (ret) { - struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); - struct intel_memory_region *dst_reg, *src_reg; - union { - struct ttm_kmap_iter_tt tt; - struct ttm_kmap_iter_iomap io; - } _dst_iter, _src_iter; - struct ttm_kmap_iter *dst_iter, *src_iter; - - dst_reg = i915_ttm_region(bo->bdev, dst_mem->mem_type); - src_reg = i915_ttm_region(bo->bdev, bo->resource->mem_type); - GEM_BUG_ON(!dst_reg || !src_reg); - - dst_iter = !cpu_maps_iomem(dst_mem) ? - ttm_kmap_iter_tt_init(&_dst_iter.tt, dst_ttm) : - ttm_kmap_iter_iomap_init(&_dst_iter.io, &dst_reg->iomap, - dst_st, dst_reg->region.start); - - src_iter = !cpu_maps_iomem(bo->resource) ? - ttm_kmap_iter_tt_init(&_src_iter.tt, bo->ttm) : - ttm_kmap_iter_iomap_init(&_src_iter.io, &src_reg->iomap, - obj->ttm.cached_io_st, - src_reg->region.start); - - ttm_move_memcpy(clear, dst_mem->num_pages, dst_iter, src_iter); - } + return intel_region_ttm_resource_to_rsgt(obj->mm.region, res); } -static int i915_ttm_move(struct ttm_buffer_object *bo, bool evict, - struct ttm_operation_ctx *ctx, - struct ttm_resource *dst_mem, - struct ttm_place *hop) +static void i915_ttm_swap_notify(struct ttm_buffer_object *bo) { struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); - struct ttm_resource_manager *dst_man = - ttm_manager_type(bo->bdev, dst_mem->mem_type); - struct ttm_tt *ttm = bo->ttm; - struct sg_table *dst_st; - bool clear; int ret; - /* Sync for now. We could do the actual copy async. */ - ret = ttm_bo_wait_ctx(bo, ctx); - if (ret) - return ret; + if (!obj) + return; ret = i915_ttm_move_notify(bo); - if (ret) - return ret; - - if (obj->mm.madv != I915_MADV_WILLNEED) { + GEM_WARN_ON(ret); + GEM_WARN_ON(obj->ttm.cached_io_rsgt); + if (!ret && obj->mm.madv != I915_MADV_WILLNEED) i915_ttm_purge(obj); - ttm_resource_free(bo, &dst_mem); - return 0; - } - - /* Populate ttm with pages if needed. Typically system memory. */ - if (ttm && (dst_man->use_tt || (ttm->page_flags & TTM_TT_FLAG_SWAPPED))) { - ret = ttm_tt_populate(bo->bdev, ttm, ctx); - if (ret) - return ret; - } - - dst_st = i915_ttm_resource_get_st(obj, dst_mem); - if (IS_ERR(dst_st)) - return PTR_ERR(dst_st); - - clear = !cpu_maps_iomem(bo->resource) && (!ttm || !ttm_tt_is_populated(ttm)); - if (!(clear && ttm && !(ttm->page_flags & TTM_TT_FLAG_ZERO_ALLOC))) - __i915_ttm_move(bo, clear, dst_mem, bo->ttm, dst_st, true); - - ttm_bo_move_sync_cleanup(bo, dst_mem); - i915_ttm_adjust_domains_after_move(obj); - i915_ttm_free_cached_io_st(obj); - - if (gpu_binds_iomem(dst_mem) || cpu_maps_iomem(dst_mem)) { - obj->ttm.cached_io_st = dst_st; - obj->ttm.get_io_page.sg_pos = dst_st->sgl; - obj->ttm.get_io_page.sg_idx = 0; - } - - i915_ttm_adjust_gem_after_move(obj); - return 0; } static int i915_ttm_io_mem_reserve(struct ttm_device *bdev, struct ttm_resource *mem) { - if (!cpu_maps_iomem(mem)) + if (!i915_ttm_cpu_maps_iomem(mem)) return 0; mem->bus.caching = ttm_write_combined; @@ -607,19 +586,26 @@ static unsigned long i915_ttm_io_mem_pfn(struct ttm_buffer_object *bo, unsigned long page_offset) { struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); - unsigned long base = obj->mm.region->iomap.base - obj->mm.region->region.start; struct scatterlist *sg; + unsigned long base; unsigned int ofs; + GEM_BUG_ON(!obj); GEM_WARN_ON(bo->ttm); + base = obj->mm.region->iomap.base - obj->mm.region->region.start; sg = __i915_gem_object_get_sg(obj, &obj->ttm.get_io_page, page_offset, &ofs, true); return ((base + sg_dma_address(sg)) >> PAGE_SHIFT) + ofs; } +/* + * 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. + */ static struct ttm_device_funcs i915_ttm_bo_driver = { .ttm_tt_create = i915_ttm_tt_create, + .ttm_tt_populate = i915_ttm_tt_populate, .ttm_tt_unpopulate = i915_ttm_tt_unpopulate, .ttm_tt_destroy = i915_ttm_tt_destroy, .eviction_valuable = i915_ttm_eviction_valuable, @@ -649,7 +635,6 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj, .interruptible = true, .no_wait_gpu = false, }; - struct sg_table *st; int real_num_busy; int ret; @@ -676,7 +661,6 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj, return i915_ttm_err_to_gem(ret); } - i915_ttm_adjust_lru(obj); if (bo->ttm && !ttm_tt_is_populated(bo->ttm)) { ret = ttm_tt_populate(bo->bdev, bo->ttm, &ctx); if (ret) @@ -687,14 +671,19 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj, } if (!i915_gem_object_has_pages(obj)) { - /* Object either has a page vector or is an iomem object */ - st = bo->ttm ? i915_ttm_tt_get_st(bo->ttm) : obj->ttm.cached_io_st; - if (IS_ERR(st)) - return PTR_ERR(st); + struct i915_refct_sgt *rsgt = + i915_ttm_resource_get_st(obj, bo->resource); + + if (IS_ERR(rsgt)) + return PTR_ERR(rsgt); - __i915_gem_object_set_pages(obj, st, i915_sg_dma_sizes(st->sgl)); + 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_ttm_adjust_lru(obj); return ret; } @@ -766,12 +755,21 @@ static void i915_ttm_put_pages(struct drm_i915_gem_object *obj, * and shrinkers will move it out if needed. */ - i915_ttm_adjust_lru(obj); + if (obj->mm.rsgt) + i915_refct_sgt_put(fetch_and_zero(&obj->mm.rsgt)); } -static void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj) +/** + * i915_ttm_adjust_lru - Adjust an object's position on relevant LRU lists. + * @obj: The object + */ +void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj) { struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); + struct i915_ttm_tt *i915_tt = + container_of(bo->ttm, typeof(*i915_tt), ttm); + bool shrinkable = + bo->ttm && i915_tt->filp && ttm_tt_is_populated(bo->ttm); /* * Don't manipulate the TTM LRUs while in TTM bo destruction. @@ -781,10 +779,53 @@ static void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj) return; /* + * We skip managing the shrinker LRU in set_pages() and just manage + * everything here. This does at least solve the issue with having + * temporary shmem mappings(like with evicted lmem) not being visible to + * the shrinker. Only our shmem objects are shrinkable, everything else + * we keep as unshrinkable. + * + * To make sure everything plays nice we keep an extra shrink pin in TTM + * if the underlying pages are not currently shrinkable. Once we release + * our pin, like when the pages are moved to shmem, the pages will then + * be added to the shrinker LRU, assuming the caller isn't also holding + * a pin. + * + * TODO: consider maybe also bumping the shrinker list here when we have + * already unpinned it, which should give us something more like an LRU. + * + * TODO: There is a small window of opportunity for this function to + * get called from eviction after we've dropped the last GEM refcount, + * but before the TTM deleted flag is set on the object. Avoid + * adjusting the shrinker list in such cases, since the object is + * not available to the shrinker anyway due to its zero refcount. + * To fix this properly we should move to a TTM shrinker LRU list for + * these objects. + */ + if (kref_get_unless_zero(&obj->base.refcount)) { + if (shrinkable != obj->mm.ttm_shrinkable) { + if (shrinkable) { + if (obj->mm.madv == I915_MADV_WILLNEED) + __i915_gem_object_make_shrinkable(obj); + else + __i915_gem_object_make_purgeable(obj); + } else { + i915_gem_object_make_unshrinkable(obj); + } + + obj->mm.ttm_shrinkable = shrinkable; + } + i915_gem_object_put(obj); + } + + /* * Put on the correct LRU list depending on the MADV status */ spin_lock(&bo->bdev->lru_lock); - if (obj->mm.madv != I915_MADV_WILLNEED) { + if (shrinkable) { + /* Try to keep shmem_tt from being considered for shrinking. */ + bo->priority = TTM_MAX_BO_PRIORITY - 1; + } else if (obj->mm.madv != I915_MADV_WILLNEED) { bo->priority = I915_TTM_PRIO_PURGE; } else if (!i915_gem_object_has_pages(obj)) { if (bo->priority < I915_TTM_PRIO_HAS_PAGES) @@ -823,15 +864,39 @@ static void i915_ttm_delayed_free(struct drm_i915_gem_object *obj) static vm_fault_t vm_fault_ttm(struct vm_fault *vmf) { struct vm_area_struct *area = vmf->vma; - struct drm_i915_gem_object *obj = - i915_ttm_to_gem(area->vm_private_data); + struct ttm_buffer_object *bo = area->vm_private_data; + struct drm_device *dev = bo->base.dev; + struct drm_i915_gem_object *obj; + 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)) return VM_FAULT_SIGBUS; - return ttm_bo_vm_fault(vmf); + ret = ttm_bo_vm_reserve(bo, vmf); + if (ret) + return ret; + + if (drm_dev_enter(dev, &idx)) { + ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot, + TTM_BO_VM_NUM_PREFAULT); + drm_dev_exit(idx); + } else { + ret = ttm_bo_vm_dummy_page(vmf, vmf->vma->vm_page_prot); + } + if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) + return ret; + + i915_ttm_adjust_lru(obj); + + dma_resv_unlock(bo->base.resv); + return ret; } static int @@ -882,13 +947,18 @@ static u64 i915_ttm_mmap_offset(struct drm_i915_gem_object *obj) static const struct drm_i915_gem_object_ops i915_gem_ttm_obj_ops = { .name = "i915_gem_object_ttm", + .flags = I915_GEM_OBJECT_IS_SHRINKABLE | + I915_GEM_OBJECT_SELF_MANAGED_SHRINK_LIST, .get_pages = i915_ttm_get_pages, .put_pages = i915_ttm_put_pages, .truncate = i915_ttm_purge, + .shrinker_release_pages = i915_ttm_shrinker_release_pages, + .adjust_lru = i915_ttm_adjust_lru, .delayed_free = i915_ttm_delayed_free, .migrate = i915_ttm_migrate, + .mmap_offset = i915_ttm_mmap_offset, .mmap_ops = &vm_ops_ttm, }; @@ -901,6 +971,18 @@ void i915_ttm_bo_destroy(struct ttm_buffer_object *bo) mutex_destroy(&obj->ttm.get_io_page.lock); if (obj->ttm.created) { + /* + * We freely manage the shrinker LRU outide of the mm.pages life + * cycle. As a result when destroying the object we should be + * extra paranoid and ensure we remove it from the LRU, before + * we free the object. + * + * Touching the ttm_shrinkable outside of the object lock here + * should be safe now that the last GEM object ref was dropped. + */ + if (obj->mm.ttm_shrinkable) + i915_gem_object_make_unshrinkable(obj); + i915_ttm_backup_free(obj); /* This releases all gem object bindings to the backend. */ @@ -940,10 +1022,9 @@ int __i915_gem_ttm_object_init(struct intel_memory_region *mem, i915_gem_object_init(obj, &i915_gem_ttm_obj_ops, &lock_class, flags); /* Don't put on a region list until we're either locked or fully initialized. */ - obj->mm.region = intel_memory_region_get(mem); + obj->mm.region = mem; INIT_LIST_HEAD(&obj->mm.region_link); - i915_gem_object_make_unshrinkable(obj); INIT_RADIX_TREE(&obj->ttm.get_io_page.radix, GFP_KERNEL | __GFP_NOWARN); mutex_init(&obj->ttm.get_io_page.lock); bo_type = (obj->flags & I915_BO_ALLOC_USER) ? ttm_bo_type_device : @@ -955,6 +1036,14 @@ int __i915_gem_ttm_object_init(struct intel_memory_region *mem, GEM_BUG_ON(page_size && obj->mm.n_placements); /* + * Keep an extra shrink pin to prevent the object from being made + * shrinkable too early. If the ttm_tt is ever allocated in shmem, we + * drop the pin. The TTM backend manages the shrinker LRU itself, + * outside of the normal mm.pages life cycle. + */ + i915_gem_object_make_unshrinkable(obj); + + /* * If this function fails, it will call the destructor, but * our caller still owns the object. So no freeing in the * destructor until obj->ttm.created is true. @@ -980,6 +1069,7 @@ int __i915_gem_ttm_object_init(struct intel_memory_region *mem, static const struct intel_memory_region_ops ttm_system_region_ops = { .init_object = __i915_gem_ttm_object_init, + .release = intel_region_ttm_fini, }; struct intel_memory_region * @@ -999,50 +1089,3 @@ i915_gem_ttm_system_setup(struct drm_i915_private *i915, intel_memory_region_set_name(mr, "system-ttm"); return mr; } - -/** - * i915_gem_obj_copy_ttm - Copy the contents of one ttm-based gem object to - * another - * @dst: The destination object - * @src: The source object - * @allow_accel: Allow using the blitter. Otherwise TTM memcpy is used. - * @intr: Whether to perform waits interruptible: - * - * Note: The caller is responsible for assuring that the underlying - * TTM objects are populated if needed and locked. - * - * Return: Zero on success. Negative error code on error. If @intr == true, - * then it may return -ERESTARTSYS or -EINTR. - */ -int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst, - struct drm_i915_gem_object *src, - bool allow_accel, bool intr) -{ - struct ttm_buffer_object *dst_bo = i915_gem_to_ttm(dst); - struct ttm_buffer_object *src_bo = i915_gem_to_ttm(src); - struct ttm_operation_ctx ctx = { - .interruptible = intr, - }; - struct sg_table *dst_st; - int ret; - - assert_object_held(dst); - assert_object_held(src); - - /* - * Sync for now. This will change with async moves. - */ - ret = ttm_bo_wait_ctx(dst_bo, &ctx); - if (!ret) - ret = ttm_bo_wait_ctx(src_bo, &ctx); - if (ret) - return ret; - - dst_st = gpu_binds_iomem(dst_bo->resource) ? - dst->ttm.cached_io_st : i915_ttm_tt_get_st(dst_bo->ttm); - - __i915_ttm_move(src_bo, false, dst_bo->resource, dst_bo->ttm, - dst_st, allow_accel); - - return 0; -} diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.h b/drivers/gpu/drm/i915/gem/i915_gem_ttm.h index 0b7291dd897c..9d698ad00853 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.h @@ -5,6 +5,8 @@ #ifndef _I915_GEM_TTM_H_ #define _I915_GEM_TTM_H_ +#include <drm/ttm/ttm_placement.h> + #include "gem/i915_gem_object_types.h" /** @@ -35,7 +37,7 @@ void i915_ttm_bo_destroy(struct ttm_buffer_object *bo); static inline struct drm_i915_gem_object * i915_ttm_to_gem(struct ttm_buffer_object *bo) { - if (GEM_WARN_ON(bo->destroy != i915_ttm_bo_destroy)) + if (bo->destroy != i915_ttm_bo_destroy) return NULL; return container_of(bo, struct drm_i915_gem_object, __do_not_access); @@ -47,10 +49,6 @@ int __i915_gem_ttm_object_init(struct intel_memory_region *mem, resource_size_t page_size, unsigned int flags); -int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst, - struct drm_i915_gem_object *src, - bool allow_accel, bool intr); - /* Internal I915 TTM declarations and definitions below. */ #define I915_PL_LMEM0 TTM_PL_PRIV @@ -60,4 +58,37 @@ int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst, struct ttm_placement *i915_ttm_sys_placement(void); +void i915_ttm_free_cached_io_rsgt(struct drm_i915_gem_object *obj); + +struct i915_refct_sgt * +i915_ttm_resource_get_st(struct drm_i915_gem_object *obj, + struct ttm_resource *res); + +void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj); + +int i915_ttm_purge(struct drm_i915_gem_object *obj); + +/** + * i915_ttm_gtt_binds_lmem - Should the memory be viewed as LMEM by the GTT? + * @mem: struct ttm_resource representing the memory. + * + * Return: true if memory should be viewed as LMEM for GTT binding purposes, + * false otherwise. + */ +static inline bool i915_ttm_gtt_binds_lmem(struct ttm_resource *mem) +{ + return mem->mem_type != I915_PL_SYSTEM; +} + +/** + * i915_ttm_cpu_maps_iomem - Should the memory be viewed as IOMEM by the CPU? + * @mem: struct ttm_resource representing the memory. + * + * Return: true if memory should be viewed as IOMEM for CPU mapping purposes. + */ +static inline bool i915_ttm_cpu_maps_iomem(struct ttm_resource *mem) +{ + /* Once / if we support GGTT, this is also false for cached ttm_tts */ + return mem->mem_type != I915_PL_SYSTEM; +} #endif diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c new file mode 100644 index 000000000000..ee9612a3ee5e --- /dev/null +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c @@ -0,0 +1,627 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2021 Intel Corporation + */ + +#include <drm/ttm/ttm_bo_driver.h> + +#include "i915_deps.h" +#include "i915_drv.h" +#include "intel_memory_region.h" +#include "intel_region_ttm.h" + +#include "gem/i915_gem_object.h" +#include "gem/i915_gem_region.h" +#include "gem/i915_gem_ttm.h" +#include "gem/i915_gem_ttm_move.h" + +#include "gt/intel_engine_pm.h" +#include "gt/intel_gt.h" +#include "gt/intel_migrate.h" + +/** + * DOC: Selftest failure modes for failsafe migration: + * + * For fail_gpu_migration, the gpu blit scheduled is always a clear blit + * rather than a copy blit, and then we force the failure paths as if + * the blit fence returned an error. + * + * For fail_work_allocation we fail the kmalloc of the async worker, we + * sync the gpu blit. If it then fails, or fail_gpu_migration is set to + * true, then a memcpy operation is performed sync. + */ +#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) +static bool fail_gpu_migration; +static bool fail_work_allocation; + +void i915_ttm_migrate_set_failure_modes(bool gpu_migration, + bool work_allocation) +{ + fail_gpu_migration = gpu_migration; + fail_work_allocation = work_allocation; +} +#endif + +static enum i915_cache_level +i915_ttm_cache_level(struct drm_i915_private *i915, struct ttm_resource *res, + struct ttm_tt *ttm) +{ + return ((HAS_LLC(i915) || HAS_SNOOP(i915)) && + !i915_ttm_gtt_binds_lmem(res) && + ttm->caching == ttm_cached) ? I915_CACHE_LLC : + I915_CACHE_NONE; +} + +static struct intel_memory_region * +i915_ttm_region(struct ttm_device *bdev, int ttm_mem_type) +{ + struct drm_i915_private *i915 = container_of(bdev, typeof(*i915), bdev); + + /* There's some room for optimization here... */ + GEM_BUG_ON(ttm_mem_type != I915_PL_SYSTEM && + ttm_mem_type < I915_PL_LMEM0); + if (ttm_mem_type == I915_PL_SYSTEM) + return intel_memory_region_lookup(i915, INTEL_MEMORY_SYSTEM, + 0); + + return intel_memory_region_lookup(i915, INTEL_MEMORY_LOCAL, + ttm_mem_type - I915_PL_LMEM0); +} + +/** + * i915_ttm_adjust_domains_after_move - Adjust the GEM domains after a + * TTM move + * @obj: The gem object + */ +void i915_ttm_adjust_domains_after_move(struct drm_i915_gem_object *obj) +{ + struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); + + if (i915_ttm_cpu_maps_iomem(bo->resource) || bo->ttm->caching != ttm_cached) { + obj->write_domain = I915_GEM_DOMAIN_WC; + obj->read_domains = I915_GEM_DOMAIN_WC; + } else { + obj->write_domain = I915_GEM_DOMAIN_CPU; + obj->read_domains = I915_GEM_DOMAIN_CPU; + } +} + +/** + * i915_ttm_adjust_gem_after_move - Adjust the GEM state after a TTM move + * @obj: The gem object + * + * Adjusts the GEM object's region, mem_flags and cache coherency after a + * TTM move. + */ +void i915_ttm_adjust_gem_after_move(struct drm_i915_gem_object *obj) +{ + struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); + unsigned int cache_level; + unsigned int i; + + /* + * If object was moved to an allowable region, update the object + * region to consider it migrated. Note that if it's currently not + * in an allowable region, it's evicted and we don't update the + * object region. + */ + if (intel_region_to_ttm_type(obj->mm.region) != bo->resource->mem_type) { + for (i = 0; i < obj->mm.n_placements; ++i) { + struct intel_memory_region *mr = obj->mm.placements[i]; + + if (intel_region_to_ttm_type(mr) == bo->resource->mem_type && + mr != obj->mm.region) { + i915_gem_object_release_memory_region(obj); + i915_gem_object_init_memory_region(obj, mr); + break; + } + } + } + + obj->mem_flags &= ~(I915_BO_FLAG_STRUCT_PAGE | I915_BO_FLAG_IOMEM); + + obj->mem_flags |= i915_ttm_cpu_maps_iomem(bo->resource) ? I915_BO_FLAG_IOMEM : + I915_BO_FLAG_STRUCT_PAGE; + + cache_level = i915_ttm_cache_level(to_i915(bo->base.dev), bo->resource, + bo->ttm); + i915_gem_object_set_cache_coherency(obj, cache_level); +} + +/** + * i915_ttm_move_notify - Prepare an object for move + * @bo: The ttm buffer object. + * + * This function prepares an object for move by removing all GPU bindings, + * removing all CPU mapings and finally releasing the pages sg-table. + * + * Return: 0 if successful, negative error code on error. + */ +int i915_ttm_move_notify(struct ttm_buffer_object *bo) +{ + struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); + int ret; + + ret = i915_gem_object_unbind(obj, I915_GEM_OBJECT_UNBIND_ACTIVE); + if (ret) + return ret; + + ret = __i915_gem_object_put_pages(obj); + if (ret) + return ret; + + return 0; +} + +static struct dma_fence *i915_ttm_accel_move(struct ttm_buffer_object *bo, + bool clear, + struct ttm_resource *dst_mem, + struct ttm_tt *dst_ttm, + struct sg_table *dst_st, + const struct i915_deps *deps) +{ + struct drm_i915_private *i915 = container_of(bo->bdev, typeof(*i915), + bdev); + struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); + struct i915_request *rq; + struct ttm_tt *src_ttm = bo->ttm; + enum i915_cache_level src_level, dst_level; + int ret; + + if (!to_gt(i915)->migrate.context || intel_gt_is_wedged(to_gt(i915))) + return ERR_PTR(-EINVAL); + + /* With fail_gpu_migration, we always perform a GPU clear. */ + if (I915_SELFTEST_ONLY(fail_gpu_migration)) + clear = true; + + dst_level = i915_ttm_cache_level(i915, dst_mem, dst_ttm); + if (clear) { + if (bo->type == ttm_bo_type_kernel && + !I915_SELFTEST_ONLY(fail_gpu_migration)) + return ERR_PTR(-EINVAL); + + intel_engine_pm_get(to_gt(i915)->migrate.context->engine); + ret = intel_context_migrate_clear(to_gt(i915)->migrate.context, deps, + dst_st->sgl, dst_level, + i915_ttm_gtt_binds_lmem(dst_mem), + 0, &rq); + } else { + struct i915_refct_sgt *src_rsgt = + i915_ttm_resource_get_st(obj, bo->resource); + + if (IS_ERR(src_rsgt)) + return ERR_CAST(src_rsgt); + + src_level = i915_ttm_cache_level(i915, bo->resource, src_ttm); + intel_engine_pm_get(to_gt(i915)->migrate.context->engine); + ret = intel_context_migrate_copy(to_gt(i915)->migrate.context, + deps, src_rsgt->table.sgl, + src_level, + i915_ttm_gtt_binds_lmem(bo->resource), + dst_st->sgl, dst_level, + i915_ttm_gtt_binds_lmem(dst_mem), + &rq); + + i915_refct_sgt_put(src_rsgt); + } + + intel_engine_pm_put(to_gt(i915)->migrate.context->engine); + + if (ret && rq) { + i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT); + i915_request_put(rq); + } + + return ret ? ERR_PTR(ret) : &rq->fence; +} + +/** + * struct i915_ttm_memcpy_arg - argument for the bo memcpy functionality. + * @_dst_iter: Storage space for the destination kmap iterator. + * @_src_iter: Storage space for the source kmap iterator. + * @dst_iter: Pointer to the destination kmap iterator. + * @src_iter: Pointer to the source kmap iterator. + * @clear: Whether to clear instead of copy. + * @src_rsgt: Refcounted scatter-gather list of source memory. + * @dst_rsgt: Refcounted scatter-gather list of destination memory. + */ +struct i915_ttm_memcpy_arg { + union { + struct ttm_kmap_iter_tt tt; + struct ttm_kmap_iter_iomap io; + } _dst_iter, + _src_iter; + struct ttm_kmap_iter *dst_iter; + struct ttm_kmap_iter *src_iter; + unsigned long num_pages; + bool clear; + struct i915_refct_sgt *src_rsgt; + struct i915_refct_sgt *dst_rsgt; +}; + +/** + * struct i915_ttm_memcpy_work - Async memcpy worker under a dma-fence. + * @fence: The dma-fence. + * @work: The work struct use for the memcpy work. + * @lock: The fence lock. Not used to protect anything else ATM. + * @irq_work: Low latency worker to signal the fence since it can't be done + * from the callback for lockdep reasons. + * @cb: Callback for the accelerated migration fence. + * @arg: The argument for the memcpy functionality. + */ +struct i915_ttm_memcpy_work { + struct dma_fence fence; + struct work_struct work; + /* The fence lock */ + spinlock_t lock; + struct irq_work irq_work; + struct dma_fence_cb cb; + struct i915_ttm_memcpy_arg arg; +}; + +static void i915_ttm_move_memcpy(struct i915_ttm_memcpy_arg *arg) +{ + ttm_move_memcpy(arg->clear, arg->num_pages, + arg->dst_iter, arg->src_iter); +} + +static void i915_ttm_memcpy_init(struct i915_ttm_memcpy_arg *arg, + struct ttm_buffer_object *bo, bool clear, + struct ttm_resource *dst_mem, + struct ttm_tt *dst_ttm, + struct i915_refct_sgt *dst_rsgt) +{ + struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); + struct intel_memory_region *dst_reg, *src_reg; + + dst_reg = i915_ttm_region(bo->bdev, dst_mem->mem_type); + src_reg = i915_ttm_region(bo->bdev, bo->resource->mem_type); + GEM_BUG_ON(!dst_reg || !src_reg); + + arg->dst_iter = !i915_ttm_cpu_maps_iomem(dst_mem) ? + ttm_kmap_iter_tt_init(&arg->_dst_iter.tt, dst_ttm) : + ttm_kmap_iter_iomap_init(&arg->_dst_iter.io, &dst_reg->iomap, + &dst_rsgt->table, dst_reg->region.start); + + arg->src_iter = !i915_ttm_cpu_maps_iomem(bo->resource) ? + ttm_kmap_iter_tt_init(&arg->_src_iter.tt, bo->ttm) : + ttm_kmap_iter_iomap_init(&arg->_src_iter.io, &src_reg->iomap, + &obj->ttm.cached_io_rsgt->table, + src_reg->region.start); + arg->clear = clear; + arg->num_pages = bo->base.size >> PAGE_SHIFT; + + arg->dst_rsgt = i915_refct_sgt_get(dst_rsgt); + arg->src_rsgt = clear ? NULL : + i915_ttm_resource_get_st(obj, bo->resource); +} + +static void i915_ttm_memcpy_release(struct i915_ttm_memcpy_arg *arg) +{ + i915_refct_sgt_put(arg->src_rsgt); + i915_refct_sgt_put(arg->dst_rsgt); +} + +static void __memcpy_work(struct work_struct *work) +{ + struct i915_ttm_memcpy_work *copy_work = + container_of(work, typeof(*copy_work), work); + struct i915_ttm_memcpy_arg *arg = ©_work->arg; + bool cookie = dma_fence_begin_signalling(); + + i915_ttm_move_memcpy(arg); + dma_fence_end_signalling(cookie); + + dma_fence_signal(©_work->fence); + + i915_ttm_memcpy_release(arg); + dma_fence_put(©_work->fence); +} + +static void __memcpy_irq_work(struct irq_work *irq_work) +{ + struct i915_ttm_memcpy_work *copy_work = + container_of(irq_work, typeof(*copy_work), irq_work); + struct i915_ttm_memcpy_arg *arg = ©_work->arg; + + dma_fence_signal(©_work->fence); + i915_ttm_memcpy_release(arg); + dma_fence_put(©_work->fence); +} + +static void __memcpy_cb(struct dma_fence *fence, struct dma_fence_cb *cb) +{ + struct i915_ttm_memcpy_work *copy_work = + container_of(cb, typeof(*copy_work), cb); + + if (unlikely(fence->error || I915_SELFTEST_ONLY(fail_gpu_migration))) { + INIT_WORK(©_work->work, __memcpy_work); + queue_work(system_unbound_wq, ©_work->work); + } else { + init_irq_work(©_work->irq_work, __memcpy_irq_work); + irq_work_queue(©_work->irq_work); + } +} + +static const char *get_driver_name(struct dma_fence *fence) +{ + return "i915_ttm_memcpy_work"; +} + +static const char *get_timeline_name(struct dma_fence *fence) +{ + return "unbound"; +} + +static const struct dma_fence_ops dma_fence_memcpy_ops = { + .get_driver_name = get_driver_name, + .get_timeline_name = get_timeline_name, +}; + +static struct dma_fence * +i915_ttm_memcpy_work_arm(struct i915_ttm_memcpy_work *work, + struct dma_fence *dep) +{ + int ret; + + spin_lock_init(&work->lock); + dma_fence_init(&work->fence, &dma_fence_memcpy_ops, &work->lock, 0, 0); + dma_fence_get(&work->fence); + ret = dma_fence_add_callback(dep, &work->cb, __memcpy_cb); + if (ret) { + if (ret != -ENOENT) + dma_fence_wait(dep, false); + + return ERR_PTR(I915_SELFTEST_ONLY(fail_gpu_migration) ? -EINVAL : + dep->error); + } + + return &work->fence; +} + +static struct dma_fence * +__i915_ttm_move(struct ttm_buffer_object *bo, + const struct ttm_operation_ctx *ctx, bool clear, + struct ttm_resource *dst_mem, struct ttm_tt *dst_ttm, + struct i915_refct_sgt *dst_rsgt, bool allow_accel, + const struct i915_deps *move_deps) +{ + struct i915_ttm_memcpy_work *copy_work = NULL; + struct i915_ttm_memcpy_arg _arg, *arg = &_arg; + struct dma_fence *fence = ERR_PTR(-EINVAL); + + if (allow_accel) { + fence = i915_ttm_accel_move(bo, clear, dst_mem, dst_ttm, + &dst_rsgt->table, move_deps); + + /* + * We only need to intercept the error when moving to lmem. + * When moving to system, TTM or shmem will provide us with + * cleared pages. + */ + if (!IS_ERR(fence) && !i915_ttm_gtt_binds_lmem(dst_mem) && + !I915_SELFTEST_ONLY(fail_gpu_migration || + fail_work_allocation)) + goto out; + } + + /* If we've scheduled gpu migration. Try to arm error intercept. */ + if (!IS_ERR(fence)) { + struct dma_fence *dep = fence; + + if (!I915_SELFTEST_ONLY(fail_work_allocation)) + copy_work = kzalloc(sizeof(*copy_work), GFP_KERNEL); + + if (copy_work) { + arg = ©_work->arg; + i915_ttm_memcpy_init(arg, bo, clear, dst_mem, dst_ttm, + dst_rsgt); + fence = i915_ttm_memcpy_work_arm(copy_work, dep); + } else { + dma_fence_wait(dep, false); + fence = ERR_PTR(I915_SELFTEST_ONLY(fail_gpu_migration) ? + -EINVAL : fence->error); + } + dma_fence_put(dep); + + if (!IS_ERR(fence)) + goto out; + } else if (move_deps) { + int err = i915_deps_sync(move_deps, ctx); + + if (err) + return ERR_PTR(err); + } + + /* Error intercept failed or no accelerated migration to start with */ + if (!copy_work) + i915_ttm_memcpy_init(arg, bo, clear, dst_mem, dst_ttm, + dst_rsgt); + i915_ttm_move_memcpy(arg); + i915_ttm_memcpy_release(arg); + kfree(copy_work); + + return NULL; +out: + if (!fence && copy_work) { + i915_ttm_memcpy_release(arg); + kfree(copy_work); + } + + return fence; +} + +static int +prev_deps(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, + struct i915_deps *deps) +{ + int ret; + + ret = i915_deps_add_dependency(deps, bo->moving, ctx); + if (!ret) + ret = i915_deps_add_resv(deps, bo->base.resv, ctx); + + return ret; +} + +/** + * i915_ttm_move - The TTM move callback used by i915. + * @bo: The buffer object. + * @evict: Whether this is an eviction. + * @dst_mem: The destination ttm resource. + * @hop: If we need multihop, what temporary memory type to move to. + * + * Return: 0 if successful, negative error code otherwise. + */ +int i915_ttm_move(struct ttm_buffer_object *bo, bool evict, + struct ttm_operation_ctx *ctx, + struct ttm_resource *dst_mem, + struct ttm_place *hop) +{ + struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); + struct ttm_resource_manager *dst_man = + ttm_manager_type(bo->bdev, dst_mem->mem_type); + struct dma_fence *migration_fence = NULL; + struct ttm_tt *ttm = bo->ttm; + struct i915_refct_sgt *dst_rsgt; + bool clear; + int ret; + + if (GEM_WARN_ON(!obj)) { + ttm_bo_move_null(bo, dst_mem); + return 0; + } + + ret = i915_ttm_move_notify(bo); + if (ret) + return ret; + + if (obj->mm.madv != I915_MADV_WILLNEED) { + i915_ttm_purge(obj); + ttm_resource_free(bo, &dst_mem); + return 0; + } + + /* Populate ttm with pages if needed. Typically system memory. */ + if (ttm && (dst_man->use_tt || (ttm->page_flags & TTM_TT_FLAG_SWAPPED))) { + ret = ttm_tt_populate(bo->bdev, ttm, ctx); + if (ret) + return ret; + } + + dst_rsgt = i915_ttm_resource_get_st(obj, dst_mem); + if (IS_ERR(dst_rsgt)) + return PTR_ERR(dst_rsgt); + + clear = !i915_ttm_cpu_maps_iomem(bo->resource) && (!ttm || !ttm_tt_is_populated(ttm)); + if (!(clear && ttm && !(ttm->page_flags & TTM_TT_FLAG_ZERO_ALLOC))) { + struct i915_deps deps; + + i915_deps_init(&deps, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); + ret = prev_deps(bo, ctx, &deps); + if (ret) { + i915_refct_sgt_put(dst_rsgt); + return ret; + } + + migration_fence = __i915_ttm_move(bo, ctx, clear, dst_mem, bo->ttm, + dst_rsgt, true, &deps); + i915_deps_fini(&deps); + } + + /* We can possibly get an -ERESTARTSYS here */ + if (IS_ERR(migration_fence)) { + i915_refct_sgt_put(dst_rsgt); + return PTR_ERR(migration_fence); + } + + if (migration_fence) { + ret = ttm_bo_move_accel_cleanup(bo, migration_fence, evict, + true, dst_mem); + if (ret) { + dma_fence_wait(migration_fence, false); + ttm_bo_move_sync_cleanup(bo, dst_mem); + } + dma_fence_put(migration_fence); + } else { + ttm_bo_move_sync_cleanup(bo, dst_mem); + } + + i915_ttm_adjust_domains_after_move(obj); + i915_ttm_free_cached_io_rsgt(obj); + + if (i915_ttm_gtt_binds_lmem(dst_mem) || i915_ttm_cpu_maps_iomem(dst_mem)) { + obj->ttm.cached_io_rsgt = dst_rsgt; + obj->ttm.get_io_page.sg_pos = dst_rsgt->table.sgl; + obj->ttm.get_io_page.sg_idx = 0; + } else { + i915_refct_sgt_put(dst_rsgt); + } + + i915_ttm_adjust_lru(obj); + i915_ttm_adjust_gem_after_move(obj); + return 0; +} + +/** + * i915_gem_obj_copy_ttm - Copy the contents of one ttm-based gem object to + * another + * @dst: The destination object + * @src: The source object + * @allow_accel: Allow using the blitter. Otherwise TTM memcpy is used. + * @intr: Whether to perform waits interruptible: + * + * Note: The caller is responsible for assuring that the underlying + * TTM objects are populated if needed and locked. + * + * Return: Zero on success. Negative error code on error. If @intr == true, + * then it may return -ERESTARTSYS or -EINTR. + */ +int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst, + struct drm_i915_gem_object *src, + bool allow_accel, bool intr) +{ + struct ttm_buffer_object *dst_bo = i915_gem_to_ttm(dst); + struct ttm_buffer_object *src_bo = i915_gem_to_ttm(src); + struct ttm_operation_ctx ctx = { + .interruptible = intr, + }; + struct i915_refct_sgt *dst_rsgt; + struct dma_fence *copy_fence; + struct i915_deps deps; + int ret; + + assert_object_held(dst); + assert_object_held(src); + i915_deps_init(&deps, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); + + ret = dma_resv_reserve_shared(src_bo->base.resv, 1); + if (ret) + return ret; + + ret = i915_deps_add_resv(&deps, dst_bo->base.resv, &ctx); + if (ret) + return ret; + + ret = i915_deps_add_resv(&deps, src_bo->base.resv, &ctx); + if (ret) + return ret; + + dst_rsgt = i915_ttm_resource_get_st(dst, dst_bo->resource); + copy_fence = __i915_ttm_move(src_bo, &ctx, false, dst_bo->resource, + dst_bo->ttm, dst_rsgt, allow_accel, + &deps); + + i915_deps_fini(&deps); + i915_refct_sgt_put(dst_rsgt); + if (IS_ERR_OR_NULL(copy_fence)) + return PTR_ERR_OR_ZERO(copy_fence); + + dma_resv_add_excl_fence(dst_bo->base.resv, copy_fence); + dma_resv_add_shared_fence(src_bo->base.resv, copy_fence); + + dma_fence_put(copy_fence); + + return 0; +} diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.h b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.h new file mode 100644 index 000000000000..d2e7f149e05c --- /dev/null +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ +#ifndef _I915_GEM_TTM_MOVE_H_ +#define _I915_GEM_TTM_MOVE_H_ + +#include <linux/types.h> + +#include "i915_selftest.h" + +struct ttm_buffer_object; +struct ttm_operation_ctx; +struct ttm_place; +struct ttm_resource; +struct ttm_tt; + +struct drm_i915_gem_object; +struct i915_refct_sgt; + +int i915_ttm_move_notify(struct ttm_buffer_object *bo); + +I915_SELFTEST_DECLARE(void i915_ttm_migrate_set_failure_modes(bool gpu_migration, + bool work_allocation)); + +int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst, + struct drm_i915_gem_object *src, + bool allow_accel, bool intr); + +/* Internal I915 TTM declarations and definitions below. */ + +int i915_ttm_move(struct ttm_buffer_object *bo, bool evict, + struct ttm_operation_ctx *ctx, + struct ttm_resource *dst_mem, + struct ttm_place *hop); + +void i915_ttm_adjust_domains_after_move(struct drm_i915_gem_object *obj); + +void i915_ttm_adjust_gem_after_move(struct drm_i915_gem_object *obj); + +#endif 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 3b6d14b5c604..9aad84059d56 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c @@ -12,6 +12,7 @@ #include "gem/i915_gem_region.h" #include "gem/i915_gem_ttm.h" +#include "gem/i915_gem_ttm_move.h" #include "gem/i915_gem_ttm_pm.h" /** @@ -79,6 +80,7 @@ static int i915_ttm_backup(struct i915_gem_apply_to_region *apply, err = i915_gem_obj_copy_ttm(backup, obj, pm_apply->allow_gpu, false); GEM_WARN_ON(err); + ttm_bo_wait_ctx(backup_bo, &ctx); obj->ttm.backup = backup; return 0; @@ -169,6 +171,7 @@ static int i915_ttm_restore(struct i915_gem_apply_to_region *apply, err = i915_gem_obj_copy_ttm(obj, backup, pm_apply->allow_gpu, false); GEM_WARN_ON(err); + ttm_bo_wait_ctx(backup_bo, &ctx); obj->ttm.backup = NULL; err = 0; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 3173c9f9a040..3cc01c30dd62 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -529,7 +529,7 @@ i915_gem_userptr_ioctl(struct drm_device *dev, * On almost all of the older hw, we cannot tell the GPU that * a page is readonly. */ - if (!dev_priv->gt.vm->has_read_only) + if (!to_gt(dev_priv)->vm->has_read_only) return -ENODEV; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_wait.c b/drivers/gpu/drm/i915/gem/i915_gem_wait.c index f909aaa09d9c..dab3d30c09a0 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_wait.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_wait.c @@ -10,7 +10,6 @@ #include "gt/intel_engine.h" -#include "dma_resv_utils.h" #include "i915_gem_ioctls.h" #include "i915_gem_object.h" @@ -25,7 +24,7 @@ i915_gem_object_wait_fence(struct dma_fence *fence, return timeout; if (dma_fence_is_i915(fence)) - return i915_request_wait(to_request(fence), flags, timeout); + return i915_request_wait_timeout(to_request(fence), flags, timeout); return dma_fence_wait_timeout(fence, flags & I915_WAIT_INTERRUPTIBLE, @@ -37,58 +36,22 @@ i915_gem_object_wait_reservation(struct dma_resv *resv, unsigned int flags, long timeout) { - struct dma_fence *excl; - bool prune_fences = false; - - if (flags & I915_WAIT_ALL) { - struct dma_fence **shared; - unsigned int count, i; - int ret; - - ret = dma_resv_get_fences(resv, &excl, &count, &shared); - if (ret) - return ret; - - for (i = 0; i < count; i++) { - timeout = i915_gem_object_wait_fence(shared[i], - flags, timeout); - if (timeout < 0) - break; - - dma_fence_put(shared[i]); - } - - for (; i < count; i++) - dma_fence_put(shared[i]); - kfree(shared); + struct dma_resv_iter cursor; + struct dma_fence *fence; + long ret = timeout ?: 1; + + dma_resv_iter_begin(&cursor, resv, flags & I915_WAIT_ALL); + dma_resv_for_each_fence_unlocked(&cursor, fence) { + ret = i915_gem_object_wait_fence(fence, flags, timeout); + if (ret <= 0) + break; - /* - * If both shared fences and an exclusive fence exist, - * then by construction the shared fences must be later - * than the exclusive fence. If we successfully wait for - * all the shared fences, we know that the exclusive fence - * must all be signaled. If all the shared fences are - * signaled, we can prune the array and recover the - * floating references on the fences/requests. - */ - prune_fences = count && timeout >= 0; - } else { - excl = dma_resv_get_excl_unlocked(resv); + if (timeout) + timeout = ret; } + dma_resv_iter_end(&cursor); - if (excl && timeout >= 0) - timeout = i915_gem_object_wait_fence(excl, flags, timeout); - - dma_fence_put(excl); - - /* - * Opportunistically prune the fences iff we know they have *all* been - * signaled. - */ - if (prune_fences) - dma_resv_prune(resv); - - return timeout; + return ret; } static void fence_set_priority(struct dma_fence *fence, @@ -151,32 +114,13 @@ i915_gem_object_wait_priority(struct drm_i915_gem_object *obj, unsigned int flags, const struct i915_sched_attr *attr) { - struct dma_fence *excl; + struct dma_resv_iter cursor; + struct dma_fence *fence; - if (flags & I915_WAIT_ALL) { - struct dma_fence **shared; - unsigned int count, i; - int ret; - - ret = dma_resv_get_fences(obj->base.resv, &excl, &count, - &shared); - if (ret) - return ret; - - for (i = 0; i < count; i++) { - i915_gem_fence_wait_priority(shared[i], attr); - dma_fence_put(shared[i]); - } - - kfree(shared); - } else { - excl = dma_resv_get_excl_unlocked(obj->base.resv); - } - - if (excl) { - i915_gem_fence_wait_priority(excl, attr); - dma_fence_put(excl); - } + dma_resv_iter_begin(&cursor, obj->base.resv, flags & I915_WAIT_ALL); + dma_resv_for_each_fence_unlocked(&cursor, fence) + i915_gem_fence_wait_priority(fence, attr); + dma_resv_iter_end(&cursor); return 0; } @@ -196,7 +140,11 @@ i915_gem_object_wait(struct drm_i915_gem_object *obj, timeout = i915_gem_object_wait_reservation(obj->base.resv, flags, timeout); - return timeout < 0 ? timeout : 0; + + if (timeout < 0) + return timeout; + + return !timeout ? -ETIME : 0; } static inline unsigned long nsecs_to_jiffies_timeout(const u64 n) @@ -306,6 +254,6 @@ int i915_gem_object_wait_migration(struct drm_i915_gem_object *obj, unsigned int flags) { might_sleep(); - /* NOP for now. */ - return 0; + + return i915_gem_object_wait_moving_fence(obj, !!(flags & I915_WAIT_INTERRUPTIBLE)); } diff --git a/drivers/gpu/drm/i915/gem/i915_gemfs.c b/drivers/gpu/drm/i915/gem/i915_gemfs.c index dbdbdc344d87..7271fbf813fa 100644 --- a/drivers/gpu/drm/i915/gem/i915_gemfs.c +++ b/drivers/gpu/drm/i915/gem/i915_gemfs.c @@ -12,6 +12,7 @@ int i915_gemfs_init(struct drm_i915_private *i915) { + char huge_opt[] = "huge=within_size"; /* r/w */ struct file_system_type *type; struct vfsmount *gemfs; char *opts; @@ -31,10 +32,8 @@ int i915_gemfs_init(struct drm_i915_private *i915) */ opts = NULL; - if (intel_vtd_active()) { + if (intel_vtd_active(i915)) { if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { - static char huge_opt[] = "huge=within_size"; /* r/w */ - opts = huge_opt; drm_info(&i915->drm, "Transparent Hugepage mode '%s'\n", diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c index b2003133deaf..11f0aa65f8a3 100644 --- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c +++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c @@ -22,6 +22,22 @@ #include "selftests/mock_region.h" #include "selftests/i915_random.h" +static struct i915_gem_context *hugepage_ctx(struct drm_i915_private *i915, + struct file *file) +{ + struct i915_gem_context *ctx = live_context(i915, file); + struct i915_address_space *vm; + + if (IS_ERR(ctx)) + return ctx; + + vm = ctx->vm; + if (vm) + WRITE_ONCE(vm->scrub_64K, true); + + return ctx; +} + static const unsigned int page_sizes[] = { I915_GTT_PAGE_SIZE_2M, I915_GTT_PAGE_SIZE_64K, @@ -552,7 +568,7 @@ out_unpin: out_put: i915_gem_object_put(obj); out_region: - intel_memory_region_put(mem); + intel_memory_region_destroy(mem); return err; } @@ -959,6 +975,8 @@ static int igt_mock_ppgtt_64K(void *arg) __i915_gem_object_put_pages(obj); i915_gem_object_unlock(obj); i915_gem_object_put(obj); + + i915_gem_drain_freed_objects(i915); } } @@ -1080,10 +1098,6 @@ static int __igt_write_huge(struct intel_context *ce, if (IS_ERR(vma)) return PTR_ERR(vma); - err = i915_vma_unbind(vma); - if (err) - return err; - err = i915_vma_pin(vma, size, 0, flags | offset); if (err) { /* @@ -1117,7 +1131,7 @@ out_vma_unpin: return err; } -static int igt_write_huge(struct i915_gem_context *ctx, +static int igt_write_huge(struct drm_i915_private *i915, struct drm_i915_gem_object *obj) { struct i915_gem_engines *engines; @@ -1127,6 +1141,8 @@ static int igt_write_huge(struct i915_gem_context *ctx, IGT_TIMEOUT(end_time); unsigned int max_page_size; unsigned int count; + struct i915_gem_context *ctx; + struct file *file; u64 max; u64 num; u64 size; @@ -1134,6 +1150,16 @@ static int igt_write_huge(struct i915_gem_context *ctx, int i, n; int err = 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; + } + GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj)); size = obj->base.size; @@ -1153,7 +1179,7 @@ static int igt_write_huge(struct i915_gem_context *ctx, } i915_gem_context_unlock_engines(ctx); if (!n) - return 0; + goto out; /* * To keep things interesting when alternating between engines in our @@ -1215,6 +1241,8 @@ static int igt_write_huge(struct i915_gem_context *ctx, kfree(order); +out: + fput(file); return err; } @@ -1277,8 +1305,7 @@ static u32 igt_random_size(struct rnd_state *prng, static int igt_ppgtt_smoke_huge(void *arg) { - struct i915_gem_context *ctx = arg; - struct drm_i915_private *i915 = ctx->i915; + struct drm_i915_private *i915 = arg; struct drm_i915_gem_object *obj; I915_RND_STATE(prng); struct { @@ -1302,6 +1329,7 @@ static int igt_ppgtt_smoke_huge(void *arg) u32 min = backends[i].min; u32 max = backends[i].max; u32 size = max; + try_again: size = igt_random_size(&prng, min, rounddown_pow_of_two(size)); @@ -1336,7 +1364,7 @@ try_again: goto out_unpin; } - err = igt_write_huge(ctx, obj); + err = igt_write_huge(i915, obj); if (err) { pr_err("%s write-huge failed with size=%u, i=%d\n", __func__, size, i); @@ -1363,8 +1391,7 @@ out_put: static int igt_ppgtt_sanity_check(void *arg) { - struct i915_gem_context *ctx = arg; - struct drm_i915_private *i915 = ctx->i915; + struct drm_i915_private *i915 = arg; unsigned int supported = INTEL_INFO(i915)->page_sizes; struct { igt_create_fn fn; @@ -1431,7 +1458,7 @@ static int igt_ppgtt_sanity_check(void *arg) if (pages) obj->mm.page_sizes.sg = pages; - err = igt_write_huge(ctx, obj); + err = igt_write_huge(i915, obj); i915_gem_object_lock(obj, NULL); i915_gem_object_unpin_pages(obj); @@ -1458,15 +1485,27 @@ out: static int igt_tmpfs_fallback(void *arg) { - struct i915_gem_context *ctx = arg; - struct drm_i915_private *i915 = ctx->i915; + struct drm_i915_private *i915 = arg; + struct i915_address_space *vm; + struct i915_gem_context *ctx; struct vfsmount *gemfs = i915->mm.gemfs; - struct i915_address_space *vm = i915_gem_context_get_eb_vm(ctx); struct drm_i915_gem_object *obj; struct i915_vma *vma; + struct file *file; u32 *vaddr; int err = 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); + /* * Make sure that we don't burst into a ball of flames upon falling back * to tmpfs, which we rely on if on the off-chance we encouter a failure @@ -1510,33 +1549,47 @@ out_restore: i915->mm.gemfs = gemfs; i915_vm_put(vm); +out: + fput(file); return err; } static int igt_shrink_thp(void *arg) { - struct i915_gem_context *ctx = arg; - struct drm_i915_private *i915 = ctx->i915; - struct i915_address_space *vm = i915_gem_context_get_eb_vm(ctx); + struct drm_i915_private *i915 = arg; + struct i915_address_space *vm; + struct i915_gem_context *ctx; struct drm_i915_gem_object *obj; struct i915_gem_engines_iter it; struct intel_context *ce; struct i915_vma *vma; + struct file *file; unsigned int flags = PIN_USER; unsigned int n; bool should_swap; - int err = 0; + int err; + + if (!igt_can_allocate_thp(i915)) { + pr_info("missing THP support, 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); /* * Sanity check shrinking huge-paged object -- make sure nothing blows * up. */ - if (!igt_can_allocate_thp(i915)) { - pr_info("missing THP support, skipping\n"); - goto out_vm; - } - obj = i915_gem_object_create_shmem(i915, SZ_2M); if (IS_ERR(obj)) { err = PTR_ERR(obj); @@ -1626,7 +1679,8 @@ out_put: i915_gem_object_put(obj); out_vm: i915_vm_put(vm); - +out: + fput(file); return err; } @@ -1651,7 +1705,7 @@ int i915_gem_huge_page_mock_selftests(void) mkwrite_device_info(dev_priv)->ppgtt_type = INTEL_PPGTT_FULL; mkwrite_device_info(dev_priv)->ppgtt_size = 48; - ppgtt = i915_ppgtt_create(&dev_priv->gt, 0); + ppgtt = i915_ppgtt_create(to_gt(dev_priv), 0); if (IS_ERR(ppgtt)) { err = PTR_ERR(ppgtt); goto out_unlock; @@ -1687,36 +1741,14 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *i915) SUBTEST(igt_ppgtt_smoke_huge), SUBTEST(igt_ppgtt_sanity_check), }; - struct i915_gem_context *ctx; - struct i915_address_space *vm; - struct file *file; - int err; if (!HAS_PPGTT(i915)) { pr_info("PPGTT not supported, skipping live-selftests\n"); return 0; } - if (intel_gt_is_wedged(&i915->gt)) + if (intel_gt_is_wedged(to_gt(i915))) return 0; - 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; - } - - vm = ctx->vm; - if (vm) - WRITE_ONCE(vm->scrub_64K, true); - - err = i915_subtests(tests, ctx); - -out_file: - fput(file); - return err; + return i915_live_subtests(tests, 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 8402ed925a69..75947e9dada2 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 @@ -592,7 +592,7 @@ int i915_gem_client_blt_live_selftests(struct drm_i915_private *i915) SUBTEST(igt_client_tiled_blits), }; - if (intel_gt_is_wedged(&i915->gt)) + if (intel_gt_is_wedged(to_gt(i915))) return 0; return i915_live_subtests(tests, i915); 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 b32f7fed2d9c..3f41fe5ec9d4 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c @@ -88,9 +88,9 @@ static int live_nop_switch(void *arg) rq = i915_request_get(this); i915_request_add(this); } - if (i915_request_wait(rq, 0, HZ) < 0) { + if (i915_request_wait(rq, 0, 10 * HZ) < 0) { pr_err("Failed to populated %d contexts\n", nctx); - intel_gt_set_wedged(&i915->gt); + intel_gt_set_wedged(to_gt(i915)); i915_request_put(rq); err = -EIO; goto out_file; @@ -146,7 +146,7 @@ static int live_nop_switch(void *arg) if (i915_request_wait(rq, 0, HZ / 5) < 0) { pr_err("Switching between %ld contexts timed out\n", prime); - intel_gt_set_wedged(&i915->gt); + intel_gt_set_wedged(to_gt(i915)); i915_request_put(rq); break; } @@ -1223,7 +1223,7 @@ __igt_ctx_sseu(struct drm_i915_private *i915, return 0; if (flags & TEST_RESET) - igt_global_reset_lock(&i915->gt); + igt_global_reset_lock(to_gt(i915)); obj = i915_gem_object_create_internal(i915, PAGE_SIZE); if (IS_ERR(obj)) { @@ -1306,7 +1306,7 @@ out_put: out_unlock: if (flags & TEST_RESET) - igt_global_reset_unlock(&i915->gt); + igt_global_reset_unlock(to_gt(i915)); if (ret) pr_err("%s: Failed with %d!\n", name, ret); @@ -1481,10 +1481,10 @@ static int check_scratch(struct i915_address_space *vm, u64 offset) static int write_to_scratch(struct i915_gem_context *ctx, struct intel_engine_cs *engine, + struct drm_i915_gem_object *obj, u64 offset, u32 value) { struct drm_i915_private *i915 = ctx->i915; - struct drm_i915_gem_object *obj; struct i915_address_space *vm; struct i915_request *rq; struct i915_vma *vma; @@ -1497,15 +1497,9 @@ static int write_to_scratch(struct i915_gem_context *ctx, if (err) return err; - obj = i915_gem_object_create_internal(i915, PAGE_SIZE); - if (IS_ERR(obj)) - return PTR_ERR(obj); - cmd = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WB); - if (IS_ERR(cmd)) { - err = PTR_ERR(cmd); - goto out; - } + if (IS_ERR(cmd)) + return PTR_ERR(cmd); *cmd++ = MI_STORE_DWORD_IMM_GEN4; if (GRAPHICS_VER(i915) >= 8) { @@ -1569,17 +1563,19 @@ err_unpin: i915_vma_unpin(vma); out_vm: i915_vm_put(vm); -out: - i915_gem_object_put(obj); + + if (!err) + err = i915_gem_object_wait(obj, 0, MAX_SCHEDULE_TIMEOUT); + return err; } static int read_from_scratch(struct i915_gem_context *ctx, struct intel_engine_cs *engine, + struct drm_i915_gem_object *obj, u64 offset, u32 *value) { struct drm_i915_private *i915 = ctx->i915; - struct drm_i915_gem_object *obj; struct i915_address_space *vm; const u32 result = 0x100; struct i915_request *rq; @@ -1594,10 +1590,6 @@ static int read_from_scratch(struct i915_gem_context *ctx, if (err) return err; - obj = i915_gem_object_create_internal(i915, PAGE_SIZE); - if (IS_ERR(obj)) - return PTR_ERR(obj); - if (GRAPHICS_VER(i915) >= 8) { const u32 GPR0 = engine->mmio_base + 0x600; @@ -1615,7 +1607,7 @@ static int read_from_scratch(struct i915_gem_context *ctx, cmd = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WB); if (IS_ERR(cmd)) { err = PTR_ERR(cmd); - goto out; + goto err_unpin; } memset(cmd, POISON_INUSE, PAGE_SIZE); @@ -1651,7 +1643,7 @@ static int read_from_scratch(struct i915_gem_context *ctx, cmd = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WB); if (IS_ERR(cmd)) { err = PTR_ERR(cmd); - goto out; + goto err_unpin; } memset(cmd, POISON_INUSE, PAGE_SIZE); @@ -1722,8 +1714,10 @@ err_unpin: i915_vma_unpin(vma); out_vm: i915_vm_put(vm); -out: - i915_gem_object_put(obj); + + if (!err) + err = i915_gem_object_wait(obj, 0, MAX_SCHEDULE_TIMEOUT); + return err; } @@ -1757,6 +1751,7 @@ static int igt_vm_isolation(void *arg) { struct drm_i915_private *i915 = arg; struct i915_gem_context *ctx_a, *ctx_b; + struct drm_i915_gem_object *obj_a, *obj_b; unsigned long num_engines, count; struct intel_engine_cs *engine; struct igt_live_test t; @@ -1810,6 +1805,18 @@ static int igt_vm_isolation(void *arg) vm_total = ctx_a->vm->total; GEM_BUG_ON(ctx_b->vm->total != vm_total); + obj_a = i915_gem_object_create_internal(i915, PAGE_SIZE); + if (IS_ERR(obj_a)) { + err = PTR_ERR(obj_a); + goto out_file; + } + + obj_b = i915_gem_object_create_internal(i915, PAGE_SIZE); + if (IS_ERR(obj_b)) { + err = PTR_ERR(obj_b); + goto put_a; + } + count = 0; num_engines = 0; for_each_uabi_engine(engine, i915) { @@ -1832,13 +1839,13 @@ static int igt_vm_isolation(void *arg) I915_GTT_PAGE_SIZE, vm_total, sizeof(u32), alignof_dword); - err = write_to_scratch(ctx_a, engine, + err = write_to_scratch(ctx_a, engine, obj_a, offset, 0xdeadbeef); if (err == 0) - err = read_from_scratch(ctx_b, engine, + err = read_from_scratch(ctx_b, engine, obj_b, offset, &value); if (err) - goto out_file; + goto put_b; if (value != expected) { pr_err("%s: Read %08x from scratch (offset 0x%08x_%08x), after %lu reads!\n", @@ -1847,7 +1854,7 @@ static int igt_vm_isolation(void *arg) lower_32_bits(offset), this); err = -EINVAL; - goto out_file; + goto put_b; } this++; @@ -1858,6 +1865,10 @@ static int igt_vm_isolation(void *arg) pr_info("Checked %lu scratch offsets across %lu engines\n", count, num_engines); +put_b: + i915_gem_object_put(obj_b); +put_a: + i915_gem_object_put(obj_a); out_file: if (igt_live_test_end(&t)) err = -EIO; @@ -1877,7 +1888,7 @@ int i915_gem_context_live_selftests(struct drm_i915_private *i915) SUBTEST(igt_vm_isolation), }; - if (intel_gt_is_wedged(&i915->gt)) + if (intel_gt_is_wedged(to_gt(i915))) return 0; return i915_live_subtests(tests, i915); 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 4a6bb64c3a35..3cc74b0fed06 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c @@ -102,7 +102,7 @@ static int igt_dmabuf_import_same_driver_lmem(void *arg) obj = __i915_gem_object_create_user(i915, PAGE_SIZE, &lmem, 1); if (IS_ERR(obj)) { pr_err("__i915_gem_object_create_user failed with err=%ld\n", - PTR_ERR(dmabuf)); + PTR_ERR(obj)); err = PTR_ERR(obj); goto out_ret; } @@ -158,7 +158,7 @@ static int igt_dmabuf_import_same_driver(struct drm_i915_private *i915, regions, num_regions); if (IS_ERR(obj)) { pr_err("__i915_gem_object_create_user failed with err=%ld\n", - PTR_ERR(dmabuf)); + PTR_ERR(obj)); err = PTR_ERR(obj); goto out_ret; } diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c index 28a700f08b49..ecb691c81d1e 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c @@ -4,6 +4,7 @@ */ #include "gt/intel_migrate.h" +#include "gem/i915_gem_ttm_move.h" static int igt_fill_check_buffer(struct drm_i915_gem_object *obj, bool fill) @@ -227,17 +228,38 @@ out_put: return err; } +static int igt_lmem_pages_failsafe_migrate(void *arg) +{ + int fail_gpu, fail_alloc, ret; + + for (fail_gpu = 0; fail_gpu < 2; ++fail_gpu) { + for (fail_alloc = 0; fail_alloc < 2; ++fail_alloc) { + pr_info("Simulated failure modes: gpu: %d, alloc: %d\n", + fail_gpu, fail_alloc); + i915_ttm_migrate_set_failure_modes(fail_gpu, + fail_alloc); + ret = igt_lmem_pages_migrate(arg); + if (ret) + goto out_err; + } + } + +out_err: + i915_ttm_migrate_set_failure_modes(false, false); + return ret; +} + int i915_gem_migrate_live_selftests(struct drm_i915_private *i915) { static const struct i915_subtest tests[] = { SUBTEST(igt_smem_create_migrate), SUBTEST(igt_lmem_create_migrate), SUBTEST(igt_same_create_migrate), - SUBTEST(igt_lmem_pages_migrate), + SUBTEST(igt_lmem_pages_failsafe_migrate), }; if (!HAS_LMEM(i915)) return 0; - return intel_gt_live_subtests(tests, &i915->gt); + return intel_gt_live_subtests(tests, to_gt(i915)); } 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 6d30cdfa80f3..743e6ab2c40b 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c @@ -84,6 +84,7 @@ static int check_partial_mapping(struct drm_i915_gem_object *obj, struct rnd_state *prng) { const unsigned long npages = obj->base.size / PAGE_SIZE; + struct drm_i915_private *i915 = to_i915(obj->base.dev); struct i915_ggtt_view view; struct i915_vma *vma; unsigned long page; @@ -141,7 +142,7 @@ static int check_partial_mapping(struct drm_i915_gem_object *obj, if (offset >= obj->base.size) goto out; - intel_gt_flush_ggtt_writes(&to_i915(obj->base.dev)->gt); + intel_gt_flush_ggtt_writes(to_gt(i915)); p = i915_gem_object_get_page(obj, offset >> PAGE_SHIFT); cpu = kmap(p) + offset_in_page(offset); @@ -175,6 +176,7 @@ static int check_partial_mappings(struct drm_i915_gem_object *obj, { const unsigned int nreal = obj->scratch / PAGE_SIZE; const unsigned long npages = obj->base.size / PAGE_SIZE; + struct drm_i915_private *i915 = to_i915(obj->base.dev); struct i915_vma *vma; unsigned long page; int err; @@ -234,7 +236,7 @@ static int check_partial_mappings(struct drm_i915_gem_object *obj, if (offset >= obj->base.size) continue; - intel_gt_flush_ggtt_writes(&to_i915(obj->base.dev)->gt); + intel_gt_flush_ggtt_writes(to_gt(i915)); p = i915_gem_object_get_page(obj, offset >> PAGE_SHIFT); cpu = kmap(p) + offset_in_page(offset); @@ -616,14 +618,14 @@ static bool assert_mmap_offset(struct drm_i915_private *i915, static void disable_retire_worker(struct drm_i915_private *i915) { i915_gem_driver_unregister__shrinker(i915); - intel_gt_pm_get(&i915->gt); - cancel_delayed_work_sync(&i915->gt.requests.retire_work); + intel_gt_pm_get(to_gt(i915)); + cancel_delayed_work_sync(&to_gt(i915)->requests.retire_work); } static void restore_retire_worker(struct drm_i915_private *i915) { igt_flush_test(i915); - intel_gt_pm_put(&i915->gt); + intel_gt_pm_put(to_gt(i915)); i915_gem_driver_register__shrinker(i915); } @@ -651,8 +653,8 @@ static int igt_mmap_offset_exhaustion(void *arg) /* Disable background reaper */ disable_retire_worker(i915); - GEM_BUG_ON(!i915->gt.awake); - intel_gt_retire_requests(&i915->gt); + GEM_BUG_ON(!to_gt(i915)->awake); + intel_gt_retire_requests(to_gt(i915)); i915_gem_drain_freed_objects(i915); /* Trim the device mmap space to only a page */ @@ -728,7 +730,7 @@ static int igt_mmap_offset_exhaustion(void *arg) /* Now fill with busy dead objects that we expect to reap */ for (loop = 0; loop < 3; loop++) { - if (intel_gt_is_wedged(&i915->gt)) + if (intel_gt_is_wedged(to_gt(i915))) break; obj = i915_gem_object_create_internal(i915, PAGE_SIZE); @@ -942,7 +944,7 @@ static int __igt_mmap(struct drm_i915_private *i915, } if (type == I915_MMAP_TYPE_GTT) - intel_gt_flush_ggtt_writes(&i915->gt); + intel_gt_flush_ggtt_writes(to_gt(i915)); err = wc_check(obj); if (err == -ENXIO) @@ -1049,7 +1051,7 @@ static int __igt_mmap_access(struct drm_i915_private *i915, goto out_unmap; } - intel_gt_flush_ggtt_writes(&i915->gt); + intel_gt_flush_ggtt_writes(to_gt(i915)); err = access_process_vm(current, addr, &x, sizeof(x), 0); if (err != sizeof(x)) { @@ -1065,7 +1067,7 @@ static int __igt_mmap_access(struct drm_i915_private *i915, goto out_unmap; } - intel_gt_flush_ggtt_writes(&i915->gt); + intel_gt_flush_ggtt_writes(to_gt(i915)); err = __get_user(y, ptr); if (err) { @@ -1165,7 +1167,7 @@ static int __igt_mmap_gpu(struct drm_i915_private *i915, } if (type == I915_MMAP_TYPE_GTT) - intel_gt_flush_ggtt_writes(&i915->gt); + intel_gt_flush_ggtt_writes(to_gt(i915)); for_each_uabi_engine(engine, i915) { struct i915_request *rq; diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c index 890191f286e3..6e9292918bfc 100644 --- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c @@ -185,7 +185,6 @@ static void gen6_alloc_va_range(struct i915_address_space *vm, pt = stash->pt[0]; __i915_gem_object_pin_pages(pt->base); - i915_gem_object_make_unshrinkable(pt->base); fill32_px(pt, vm->scratch[0]->encode); @@ -262,30 +261,14 @@ static void gen6_ppgtt_cleanup(struct i915_address_space *vm) { struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm)); - __i915_vma_put(ppgtt->vma); - gen6_ppgtt_free_pd(ppgtt); free_scratch(vm); mutex_destroy(&ppgtt->flush); - mutex_destroy(&ppgtt->pin_mutex); free_pd(&ppgtt->base.vm, ppgtt->base.pd); } -static int pd_vma_set_pages(struct i915_vma *vma) -{ - vma->pages = ERR_PTR(-ENODEV); - return 0; -} - -static void pd_vma_clear_pages(struct i915_vma *vma) -{ - GEM_BUG_ON(!vma->pages); - - vma->pages = NULL; -} - static void pd_vma_bind(struct i915_address_space *vm, struct i915_vm_pt_stash *stash, struct i915_vma *vma, @@ -325,43 +308,10 @@ static void pd_vma_unbind(struct i915_address_space *vm, struct i915_vma *vma) } static const struct i915_vma_ops pd_vma_ops = { - .set_pages = pd_vma_set_pages, - .clear_pages = pd_vma_clear_pages, .bind_vma = pd_vma_bind, .unbind_vma = pd_vma_unbind, }; -static struct i915_vma *pd_vma_create(struct gen6_ppgtt *ppgtt, int size) -{ - struct i915_ggtt *ggtt = ppgtt->base.vm.gt->ggtt; - struct i915_vma *vma; - - GEM_BUG_ON(!IS_ALIGNED(size, I915_GTT_PAGE_SIZE)); - GEM_BUG_ON(size > ggtt->vm.total); - - vma = i915_vma_alloc(); - if (!vma) - return ERR_PTR(-ENOMEM); - - i915_active_init(&vma->active, NULL, NULL, 0); - - kref_init(&vma->ref); - mutex_init(&vma->pages_mutex); - vma->vm = i915_vm_get(&ggtt->vm); - vma->ops = &pd_vma_ops; - vma->private = ppgtt; - - vma->size = size; - vma->fence_size = size; - atomic_set(&vma->flags, I915_VMA_GGTT); - vma->ggtt_view.type = I915_GGTT_VIEW_ROTATED; /* prevent fencing */ - - INIT_LIST_HEAD(&vma->obj_link); - INIT_LIST_HEAD(&vma->closed_link); - - return vma; -} - int gen6_ppgtt_pin(struct i915_ppgtt *base, struct i915_gem_ww_ctx *ww) { struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base); @@ -378,42 +328,92 @@ int gen6_ppgtt_pin(struct i915_ppgtt *base, struct i915_gem_ww_ctx *ww) if (atomic_add_unless(&ppgtt->pin_count, 1, 0)) return 0; - if (mutex_lock_interruptible(&ppgtt->pin_mutex)) - return -EINTR; + /* grab the ppgtt resv to pin the object */ + err = i915_vm_lock_objects(&ppgtt->base.vm, ww); + if (err) + return err; /* * PPGTT PDEs reside in the GGTT and consists of 512 entries. The * allocator works in address space sizes, so it's multiplied by page * size. We allocate at the top of the GTT to avoid fragmentation. */ - err = 0; - if (!atomic_read(&ppgtt->pin_count)) + if (!atomic_read(&ppgtt->pin_count)) { err = i915_ggtt_pin(ppgtt->vma, ww, GEN6_PD_ALIGN, PIN_HIGH); + + GEM_BUG_ON(ppgtt->vma->fence); + clear_bit(I915_VMA_CAN_FENCE_BIT, __i915_vma_flags(ppgtt->vma)); + } if (!err) atomic_inc(&ppgtt->pin_count); - mutex_unlock(&ppgtt->pin_mutex); return err; } -void gen6_ppgtt_unpin(struct i915_ppgtt *base) +static int pd_dummy_obj_get_pages(struct drm_i915_gem_object *obj) { - struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base); + obj->mm.pages = ZERO_SIZE_PTR; + return 0; +} - GEM_BUG_ON(!atomic_read(&ppgtt->pin_count)); - if (atomic_dec_and_test(&ppgtt->pin_count)) - i915_vma_unpin(ppgtt->vma); +static void pd_dummy_obj_put_pages(struct drm_i915_gem_object *obj, + struct sg_table *pages) +{ } -void gen6_ppgtt_unpin_all(struct i915_ppgtt *base) +static const struct drm_i915_gem_object_ops pd_dummy_obj_ops = { + .name = "pd_dummy_obj", + .get_pages = pd_dummy_obj_get_pages, + .put_pages = pd_dummy_obj_put_pages, +}; + +static struct i915_page_directory * +gen6_alloc_top_pd(struct gen6_ppgtt *ppgtt) { - struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base); + struct i915_ggtt * const ggtt = ppgtt->base.vm.gt->ggtt; + struct i915_page_directory *pd; + int err; - if (!atomic_read(&ppgtt->pin_count)) - return; + pd = __alloc_pd(I915_PDES); + if (unlikely(!pd)) + return ERR_PTR(-ENOMEM); - i915_vma_unpin(ppgtt->vma); - atomic_set(&ppgtt->pin_count, 0); + pd->pt.base = __i915_gem_object_create_internal(ppgtt->base.vm.gt->i915, + &pd_dummy_obj_ops, + I915_PDES * SZ_4K); + if (IS_ERR(pd->pt.base)) { + err = PTR_ERR(pd->pt.base); + pd->pt.base = NULL; + goto err_pd; + } + + pd->pt.base->base.resv = i915_vm_resv_get(&ppgtt->base.vm); + pd->pt.base->shares_resv_from = &ppgtt->base.vm; + + ppgtt->vma = i915_vma_instance(pd->pt.base, &ggtt->vm, NULL); + if (IS_ERR(ppgtt->vma)) { + err = PTR_ERR(ppgtt->vma); + ppgtt->vma = NULL; + goto err_pd; + } + + /* The dummy object we create is special, override ops.. */ + ppgtt->vma->ops = &pd_vma_ops; + ppgtt->vma->private = ppgtt; + return pd; + +err_pd: + free_pd(&ppgtt->base.vm, pd); + return ERR_PTR(err); +} + +void gen6_ppgtt_unpin(struct i915_ppgtt *base) +{ + struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base); + + GEM_BUG_ON(!atomic_read(&ppgtt->pin_count)); + if (atomic_dec_and_test(&ppgtt->pin_count)) + i915_vma_unpin(ppgtt->vma); } struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt) @@ -427,7 +427,6 @@ struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt) return ERR_PTR(-ENOMEM); mutex_init(&ppgtt->flush); - mutex_init(&ppgtt->pin_mutex); ppgtt_init(&ppgtt->base, gt, 0); ppgtt->base.vm.pd_shift = ilog2(SZ_4K * SZ_4K / sizeof(gen6_pte_t)); @@ -440,21 +439,16 @@ struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt) ppgtt->base.vm.cleanup = gen6_ppgtt_cleanup; ppgtt->base.vm.alloc_pt_dma = alloc_pt_dma; + ppgtt->base.vm.alloc_scratch_dma = alloc_pt_dma; ppgtt->base.vm.pte_encode = ggtt->vm.pte_encode; - ppgtt->base.pd = __alloc_pd(I915_PDES); - if (!ppgtt->base.pd) { - err = -ENOMEM; - goto err_free; - } - err = gen6_ppgtt_init_scratch(ppgtt); if (err) - goto err_pd; + goto err_free; - ppgtt->vma = pd_vma_create(ppgtt, GEN6_PD_SIZE); - if (IS_ERR(ppgtt->vma)) { - err = PTR_ERR(ppgtt->vma); + ppgtt->base.pd = gen6_alloc_top_pd(ppgtt); + if (IS_ERR(ppgtt->base.pd)) { + err = PTR_ERR(ppgtt->base.pd); goto err_scratch; } @@ -462,10 +456,7 @@ struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt) err_scratch: free_scratch(&ppgtt->base.vm); -err_pd: - free_pd(&ppgtt->base.vm, ppgtt->base.pd); err_free: - mutex_destroy(&ppgtt->pin_mutex); kfree(ppgtt); return ERR_PTR(err); } diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.h b/drivers/gpu/drm/i915/gt/gen6_ppgtt.h index 6a61a5c3a85a..5e5cf2ec3309 100644 --- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.h +++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.h @@ -19,7 +19,6 @@ struct gen6_ppgtt { u32 pp_dir; atomic_t pin_count; - struct mutex pin_mutex; bool scan_for_unused_pt; }; @@ -71,7 +70,6 @@ static inline struct gen6_ppgtt *to_gen6_ppgtt(struct i915_ppgtt *base) int gen6_ppgtt_pin(struct i915_ppgtt *base, struct i915_gem_ww_ctx *ww); void gen6_ppgtt_unpin(struct i915_ppgtt *base); -void gen6_ppgtt_unpin_all(struct i915_ppgtt *base); void gen6_ppgtt_enable(struct intel_gt *gt); void gen7_ppgtt_enable(struct intel_gt *gt); struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt); diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index 461844dffd7e..e320610dd0b8 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -42,7 +42,7 @@ int gen8_emit_flush_rcs(struct i915_request *rq, u32 mode) vf_flush_wa = true; /* WaForGAMHang:kbl */ - if (IS_KBL_GT_STEP(rq->engine->i915, 0, STEP_C0)) + if (IS_KBL_GRAPHICS_STEP(rq->engine->i915, 0, STEP_C0)) dc_flush_wa = true; } diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c index 037a9a6e4889..b012c50f7ce7 100644 --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c @@ -18,7 +18,7 @@ static u64 gen8_pde_encode(const dma_addr_t addr, const enum i915_cache_level level) { - u64 pde = addr | _PAGE_PRESENT | _PAGE_RW; + u64 pde = addr | GEN8_PAGE_PRESENT | GEN8_PAGE_RW; if (level != I915_CACHE_NONE) pde |= PPAT_CACHED_PDE; @@ -32,10 +32,10 @@ static u64 gen8_pte_encode(dma_addr_t addr, enum i915_cache_level level, u32 flags) { - gen8_pte_t pte = addr | _PAGE_PRESENT | _PAGE_RW; + gen8_pte_t pte = addr | GEN8_PAGE_PRESENT | GEN8_PAGE_RW; if (unlikely(flags & PTE_READ_ONLY)) - pte &= ~_PAGE_RW; + pte &= ~GEN8_PAGE_RW; if (flags & PTE_LM) pte |= GEN12_PPGTT_PTE_LM; @@ -301,7 +301,6 @@ static void __gen8_ppgtt_alloc(struct i915_address_space * const vm, pt = stash->pt[!!lvl]; __i915_gem_object_pin_pages(pt->base); - i915_gem_object_make_unshrinkable(pt->base); fill_px(pt, vm->scratch[lvl]->encode); @@ -652,7 +651,7 @@ static int gen8_init_scratch(struct i915_address_space *vm) vm->scratch[0]->encode = gen8_pte_encode(px_dma(vm->scratch[0]), - I915_CACHE_LLC, pte_flags); + I915_CACHE_NONE, pte_flags); for (i = 1; i <= vm->top; i++) { struct drm_i915_gem_object *obj; @@ -668,7 +667,7 @@ static int gen8_init_scratch(struct i915_address_space *vm) } fill_px(obj, vm->scratch[i - 1]->encode); - obj->encode = gen8_pde_encode(px_dma(obj), I915_CACHE_LLC); + obj->encode = gen8_pde_encode(px_dma(obj), I915_CACHE_NONE); vm->scratch[i] = obj; } @@ -777,10 +776,29 @@ 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; - else + + /* + * 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 { ppgtt->vm.alloc_pt_dma = alloc_pt_dma; + ppgtt->vm.alloc_scratch_dma = alloc_pt_dma; + } err = gen8_init_scratch(&ppgtt->vm); if (err) diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index 5634d14052bc..ba083d800a08 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -219,7 +219,7 @@ int __intel_context_do_pin_ww(struct intel_context *ce, */ err = i915_gem_object_lock(ce->timeline->hwsp_ggtt->obj, ww); - if (!err && ce->ring->vma->obj) + if (!err) err = i915_gem_object_lock(ce->ring->vma->obj, ww); if (!err && ce->state) err = i915_gem_object_lock(ce->state->obj, ww); @@ -228,17 +228,17 @@ int __intel_context_do_pin_ww(struct intel_context *ce, if (err) return err; - err = i915_active_acquire(&ce->active); + err = ce->ops->pre_pin(ce, ww, &vaddr); if (err) goto err_ctx_unpin; - err = ce->ops->pre_pin(ce, ww, &vaddr); + err = i915_active_acquire(&ce->active); if (err) - goto err_release; + goto err_post_unpin; err = mutex_lock_interruptible(&ce->pin_mutex); if (err) - goto err_post_unpin; + goto err_release; intel_engine_pm_might_get(ce->engine); @@ -273,11 +273,11 @@ int __intel_context_do_pin_ww(struct intel_context *ce, err_unlock: mutex_unlock(&ce->pin_mutex); +err_release: + i915_active_release(&ce->active); err_post_unpin: if (!handoff) ce->ops->post_unpin(ce); -err_release: - i915_active_release(&ce->active); err_ctx_unpin: intel_context_post_unpin(ce); @@ -364,7 +364,7 @@ static int __intel_context_active(struct i915_active *active) return 0; } -static int __i915_sw_fence_call +static int sw_fence_dummy_notify(struct i915_sw_fence *sf, enum i915_sw_fence_notify state) { diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h index 246c37d72cd7..d8c74bbf9aae 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.h +++ b/drivers/gpu/drm/i915/gt/intel_context.h @@ -211,7 +211,8 @@ static inline void intel_context_enter(struct intel_context *ce) static inline void intel_context_mark_active(struct intel_context *ce) { - lockdep_assert_held(&ce->timeline->mutex); + lockdep_assert(lockdep_is_held(&ce->timeline->mutex) || + test_bit(CONTEXT_IS_PARKING, &ce->flags)); ++ce->active_count; } diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index 9e0177dc5484..30cd81ad8911 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -118,6 +118,7 @@ struct intel_context { #define CONTEXT_LRCA_DIRTY 9 #define CONTEXT_GUC_INIT 10 #define CONTEXT_PERMA_PIN 11 +#define CONTEXT_IS_PARKING 12 struct { u64 timeout_us; diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index ff6753ccb129..352254e001b4 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -325,6 +325,38 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id, engine->id = id; engine->legacy_idx = INVALID_ENGINE; engine->mask = BIT(id); + if (GRAPHICS_VER(gt->i915) >= 11) { + static const u32 engine_reset_domains[] = { + [RCS0] = GEN11_GRDOM_RENDER, + [BCS0] = GEN11_GRDOM_BLT, + [VCS0] = GEN11_GRDOM_MEDIA, + [VCS1] = GEN11_GRDOM_MEDIA2, + [VCS2] = GEN11_GRDOM_MEDIA3, + [VCS3] = GEN11_GRDOM_MEDIA4, + [VCS4] = GEN11_GRDOM_MEDIA5, + [VCS5] = GEN11_GRDOM_MEDIA6, + [VCS6] = GEN11_GRDOM_MEDIA7, + [VCS7] = GEN11_GRDOM_MEDIA8, + [VECS0] = GEN11_GRDOM_VECS, + [VECS1] = GEN11_GRDOM_VECS2, + [VECS2] = GEN11_GRDOM_VECS3, + [VECS3] = GEN11_GRDOM_VECS4, + }; + GEM_BUG_ON(id >= ARRAY_SIZE(engine_reset_domains) || + !engine_reset_domains[id]); + engine->reset_domain = engine_reset_domains[id]; + } else { + static const u32 engine_reset_domains[] = { + [RCS0] = GEN6_GRDOM_RENDER, + [BCS0] = GEN6_GRDOM_BLT, + [VCS0] = GEN6_GRDOM_MEDIA, + [VCS1] = GEN8_GRDOM_MEDIA2, + [VECS0] = GEN6_GRDOM_VECS, + }; + GEM_BUG_ON(id >= ARRAY_SIZE(engine_reset_domains) || + !engine_reset_domains[id]); + engine->reset_domain = engine_reset_domains[id]; + } engine->i915 = i915; engine->gt = gt; engine->uncore = gt->uncore; @@ -363,7 +395,7 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id, DRIVER_CAPS(i915)->has_logical_contexts = true; ewma__engine_latency_init(&engine->latency); - seqcount_init(&engine->stats.lock); + seqcount_init(&engine->stats.execlists.lock); ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier); @@ -1676,14 +1708,18 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine, static void print_request_ring(struct drm_printer *m, struct i915_request *rq) { + struct i915_vma_snapshot *vsnap = &rq->batch_snapshot; void *ring; int size; + if (!i915_vma_snapshot_present(vsnap)) + vsnap = NULL; + drm_printf(m, "[head %04x, postfix %04x, tail %04x, batch 0x%08x_%08x]:\n", rq->head, rq->postfix, rq->tail, - rq->batch ? upper_32_bits(rq->batch->node.start) : ~0u, - rq->batch ? lower_32_bits(rq->batch->node.start) : ~0u); + vsnap ? upper_32_bits(vsnap->gtt_offset) : ~0u, + vsnap ? lower_32_bits(vsnap->gtt_offset) : ~0u); size = rq->tail - rq->head; if (rq->tail < rq->head) @@ -1915,22 +1951,6 @@ void intel_engine_dump(struct intel_engine_cs *engine, intel_engine_print_breadcrumbs(engine, m); } -static ktime_t __intel_engine_get_busy_time(struct intel_engine_cs *engine, - ktime_t *now) -{ - ktime_t total = engine->stats.total; - - /* - * If the engine is executing something at the moment - * add it to the total. - */ - *now = ktime_get(); - if (READ_ONCE(engine->stats.active)) - total = ktime_add(total, ktime_sub(*now, engine->stats.start)); - - return total; -} - /** * intel_engine_get_busy_time() - Return current accumulated engine busyness * @engine: engine to report on @@ -1940,15 +1960,7 @@ static ktime_t __intel_engine_get_busy_time(struct intel_engine_cs *engine, */ ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine, ktime_t *now) { - unsigned int seq; - ktime_t total; - - do { - seq = read_seqcount_begin(&engine->stats.lock); - total = __intel_engine_get_busy_time(engine, now); - } while (read_seqcount_retry(&engine->stats.lock, seq)); - - return total; + return engine->busyness(engine, now); } struct intel_context * diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c index a1334b48dde7..b0a4a2dbe3ee 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c @@ -26,7 +26,7 @@ static void dbg_poison_ce(struct intel_context *ce) int type = i915_coherent_map_type(ce->engine->i915, obj, true); void *map; - if (!i915_gem_object_trylock(obj)) + if (!i915_gem_object_trylock(obj, NULL)) return; map = i915_gem_object_pin_map(obj, type); @@ -80,39 +80,6 @@ static int __engine_unpark(struct intel_wakeref *wf) return 0; } -#if IS_ENABLED(CONFIG_LOCKDEP) - -static unsigned long __timeline_mark_lock(struct intel_context *ce) -{ - unsigned long flags; - - local_irq_save(flags); - mutex_acquire(&ce->timeline->mutex.dep_map, 2, 0, _THIS_IP_); - - return flags; -} - -static void __timeline_mark_unlock(struct intel_context *ce, - unsigned long flags) -{ - mutex_release(&ce->timeline->mutex.dep_map, _THIS_IP_); - local_irq_restore(flags); -} - -#else - -static unsigned long __timeline_mark_lock(struct intel_context *ce) -{ - return 0; -} - -static void __timeline_mark_unlock(struct intel_context *ce, - unsigned long flags) -{ -} - -#endif /* !IS_ENABLED(CONFIG_LOCKDEP) */ - static void duration(struct dma_fence *fence, struct dma_fence_cb *cb) { struct i915_request *rq = to_request(fence); @@ -159,7 +126,6 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine) { struct intel_context *ce = engine->kernel_context; struct i915_request *rq; - unsigned long flags; bool result = true; /* @@ -214,7 +180,7 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine) * engine->wakeref.count, we may see the request completion and retire * it causing an underflow of the engine->wakeref. */ - flags = __timeline_mark_lock(ce); + set_bit(CONTEXT_IS_PARKING, &ce->flags); GEM_BUG_ON(atomic_read(&ce->timeline->active_count) < 0); rq = __i915_request_create(ce, GFP_NOWAIT); @@ -246,7 +212,7 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine) result = false; out_unlock: - __timeline_mark_unlock(ce, flags); + clear_bit(CONTEXT_IS_PARKING, &ce->flags); return result; } diff --git a/drivers/gpu/drm/i915/gt/intel_engine_stats.h b/drivers/gpu/drm/i915/gt/intel_engine_stats.h index 24fbdd94351a..8e762d683e50 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_stats.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_stats.h @@ -15,45 +15,46 @@ static inline void intel_engine_context_in(struct intel_engine_cs *engine) { + struct intel_engine_execlists_stats *stats = &engine->stats.execlists; unsigned long flags; - if (engine->stats.active) { - engine->stats.active++; + if (stats->active) { + stats->active++; return; } /* The writer is serialised; but the pmu reader may be from hardirq */ local_irq_save(flags); - write_seqcount_begin(&engine->stats.lock); + write_seqcount_begin(&stats->lock); - engine->stats.start = ktime_get(); - engine->stats.active++; + stats->start = ktime_get(); + stats->active++; - write_seqcount_end(&engine->stats.lock); + write_seqcount_end(&stats->lock); local_irq_restore(flags); - GEM_BUG_ON(!engine->stats.active); + GEM_BUG_ON(!stats->active); } static inline void intel_engine_context_out(struct intel_engine_cs *engine) { + struct intel_engine_execlists_stats *stats = &engine->stats.execlists; unsigned long flags; - GEM_BUG_ON(!engine->stats.active); - if (engine->stats.active > 1) { - engine->stats.active--; + GEM_BUG_ON(!stats->active); + if (stats->active > 1) { + stats->active--; return; } local_irq_save(flags); - write_seqcount_begin(&engine->stats.lock); + write_seqcount_begin(&stats->lock); - engine->stats.active--; - engine->stats.total = - ktime_add(engine->stats.total, - ktime_sub(ktime_get(), engine->stats.start)); + stats->active--; + stats->total = ktime_add(stats->total, + ktime_sub(ktime_get(), stats->start)); - write_seqcount_end(&engine->stats.lock); + write_seqcount_end(&stats->lock); local_irq_restore(flags); } diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index e0f773585c29..36365bdbe1ee 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -257,6 +257,55 @@ struct intel_engine_execlists { #define INTEL_ENGINE_CS_MAX_NAME 8 +struct intel_engine_execlists_stats { + /** + * @active: Number of contexts currently scheduled in. + */ + unsigned int active; + + /** + * @lock: Lock protecting the below fields. + */ + seqcount_t lock; + + /** + * @total: Total time this engine was busy. + * + * Accumulated time not counting the most recent block in cases where + * engine is currently busy (active > 0). + */ + ktime_t total; + + /** + * @start: Timestamp of the last idle to active transition. + * + * Idle is defined as active == 0, active is active > 0. + */ + ktime_t start; +}; + +struct intel_engine_guc_stats { + /** + * @running: Active state of the engine when busyness was last sampled. + */ + bool running; + + /** + * @prev_total: Previous value of total runtime clock cycles. + */ + u32 prev_total; + + /** + * @total_gt_clks: Total gt clock cycles this engine was busy. + */ + u64 total_gt_clks; + + /** + * @start_gt_clk: GT clock time of last idle to active transition. + */ + u64 start_gt_clk; +}; + struct intel_engine_cs { struct drm_i915_private *i915; struct intel_gt *gt; @@ -269,6 +318,7 @@ struct intel_engine_cs { unsigned int guc_id; intel_engine_mask_t mask; + u32 reset_domain; /** * @logical_mask: logical mask of engine, reported to user space via * query IOCTL and used to communicate with the GuC in logical space. @@ -439,6 +489,12 @@ struct intel_engine_cs { void (*add_active_request)(struct i915_request *rq); void (*remove_active_request)(struct i915_request *rq); + /* + * Get engine busyness and the time at which the busyness was sampled. + */ + ktime_t (*busyness)(struct intel_engine_cs *engine, + ktime_t *now); + struct intel_engine_execlists execlists; /* @@ -488,30 +544,10 @@ struct intel_engine_cs { u32 (*get_cmd_length_mask)(u32 cmd_header); struct { - /** - * @active: Number of contexts currently scheduled in. - */ - unsigned int active; - - /** - * @lock: Lock protecting the below fields. - */ - seqcount_t lock; - - /** - * @total: Total time this engine was busy. - * - * Accumulated time not counting the most recent block in cases - * where engine is currently busy (active > 0). - */ - ktime_t total; - - /** - * @start: Timestamp of the last idle to active transition. - * - * Idle is defined as active == 0, active is active > 0. - */ - ktime_t start; + union { + struct intel_engine_execlists_stats execlists; + struct intel_engine_guc_stats guc; + }; /** * @rps: Utilisation at last RPS sampling. diff --git a/drivers/gpu/drm/i915/gt/intel_engine_user.c b/drivers/gpu/drm/i915/gt/intel_engine_user.c index 8f8bea08e734..9ce85a845105 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_user.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_user.c @@ -116,7 +116,7 @@ static void set_scheduler_caps(struct drm_i915_private *i915) disabled |= (I915_SCHEDULER_CAP_ENABLED | I915_SCHEDULER_CAP_PRIORITY); - if (intel_uc_uses_guc_submission(&i915->gt.uc)) + if (intel_uc_uses_guc_submission(&to_gt(i915)->uc)) enabled |= I915_SCHEDULER_CAP_STATIC_PRIORITY_MAP; for (i = 0; i < ARRAY_SIZE(map); i++) { diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index bedb80057046..a69df5e9e77a 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -2186,7 +2186,8 @@ struct execlists_capture { static void execlists_capture_work(struct work_struct *work) { struct execlists_capture *cap = container_of(work, typeof(*cap), work); - const gfp_t gfp = GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN; + const gfp_t gfp = __GFP_KSWAPD_RECLAIM | __GFP_RETRY_MAYFAIL | + __GFP_NOWARN; struct intel_engine_cs *engine = cap->rq->engine; struct intel_gt_coredump *gt = cap->error->gt; struct intel_engine_capture_vma *vma; @@ -3293,6 +3294,38 @@ static void execlists_release(struct intel_engine_cs *engine) lrc_fini_wa_ctx(engine); } +static ktime_t __execlists_engine_busyness(struct intel_engine_cs *engine, + ktime_t *now) +{ + struct intel_engine_execlists_stats *stats = &engine->stats.execlists; + ktime_t total = stats->total; + + /* + * If the engine is executing something at the moment + * add it to the total. + */ + *now = ktime_get(); + if (READ_ONCE(stats->active)) + total = ktime_add(total, ktime_sub(*now, stats->start)); + + return total; +} + +static ktime_t execlists_engine_busyness(struct intel_engine_cs *engine, + ktime_t *now) +{ + struct intel_engine_execlists_stats *stats = &engine->stats.execlists; + unsigned int seq; + ktime_t total; + + do { + seq = read_seqcount_begin(&stats->lock); + total = __execlists_engine_busyness(engine, now); + } while (read_seqcount_retry(&stats->lock, seq)); + + return total; +} + static void logical_ring_default_vfuncs(struct intel_engine_cs *engine) { @@ -3349,6 +3382,8 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine) engine->emit_bb_start = gen8_emit_bb_start; else engine->emit_bb_start = gen8_emit_bb_start_noarb; + + engine->busyness = execlists_engine_busyness; } static void logical_ring_default_irqs(struct intel_engine_cs *engine) diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index 57c97554393b..5263dda7f8d5 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -3,12 +3,14 @@ * Copyright © 2020 Intel Corporation */ +#include <linux/agp_backend.h> #include <linux/stop_machine.h> #include <asm/set_memory.h> #include <asm/smp.h> #include <drm/i915_drm.h> +#include <drm/intel-gtt.h> #include "gem/i915_gem_lmem.h" @@ -20,9 +22,6 @@ #include "intel_gtt.h" #include "gen8_ppgtt.h" -static int -i915_get_ggtt_vma_pages(struct i915_vma *vma); - static void i915_ggtt_color_adjust(const struct drm_mm_node *node, unsigned long color, u64 *start, @@ -104,7 +103,7 @@ static bool needs_idle_maps(struct drm_i915_private *i915) * Query intel_iommu to see if we need the workaround. Presumably that * was loaded first. */ - if (!intel_vtd_active()) + if (!intel_vtd_active(i915)) return false; if (GRAPHICS_VER(i915) == 5 && IS_MOBILE(i915)) @@ -116,17 +115,26 @@ static bool needs_idle_maps(struct drm_i915_private *i915) return false; } -void i915_ggtt_suspend(struct i915_ggtt *ggtt) +/** + * i915_ggtt_suspend_vm - Suspend the memory mappings for a GGTT or DPT VM + * @vm: The VM to suspend the mappings for + * + * Suspend the memory mappings for all objects mapped to HW via the GGTT or a + * DPT page table. + */ +void i915_ggtt_suspend_vm(struct i915_address_space *vm) { struct i915_vma *vma, *vn; int open; - mutex_lock(&ggtt->vm.mutex); + drm_WARN_ON(&vm->i915->drm, !vm->is_ggtt && !vm->is_dpt); + + mutex_lock(&vm->mutex); /* Skip rewriting PTE on VMA unbind. */ - open = atomic_xchg(&ggtt->vm.open, 0); + open = atomic_xchg(&vm->open, 0); - list_for_each_entry_safe(vma, vn, &ggtt->vm.bound_list, vm_link) { + list_for_each_entry_safe(vma, vn, &vm->bound_list, vm_link) { GEM_BUG_ON(!drm_mm_node_allocated(&vma->node)); i915_vma_wait_for_bind(vma); @@ -139,11 +147,17 @@ void i915_ggtt_suspend(struct i915_ggtt *ggtt) } } - ggtt->vm.clear_range(&ggtt->vm, 0, ggtt->vm.total); - ggtt->invalidate(ggtt); - atomic_set(&ggtt->vm.open, open); + vm->clear_range(vm, 0, vm->total); - mutex_unlock(&ggtt->vm.mutex); + atomic_set(&vm->open, open); + + mutex_unlock(&vm->mutex); +} + +void i915_ggtt_suspend(struct i915_ggtt *ggtt) +{ + i915_ggtt_suspend_vm(&ggtt->vm); + ggtt->invalidate(ggtt); intel_gt_check_and_clear_faults(ggtt->vm.gt); } @@ -192,7 +206,7 @@ u64 gen8_ggtt_pte_encode(dma_addr_t addr, enum i915_cache_level level, u32 flags) { - gen8_pte_t pte = addr | _PAGE_PRESENT; + gen8_pte_t pte = addr | GEN8_PAGE_PRESENT; if (flags & PTE_LM) pte |= GEN12_GGTT_PTE_LM; @@ -875,21 +889,6 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size) return 0; } -int ggtt_set_pages(struct i915_vma *vma) -{ - int ret; - - GEM_BUG_ON(vma->pages); - - ret = i915_get_ggtt_vma_pages(vma); - if (ret) - return ret; - - vma->page_sizes = vma->obj->mm.page_sizes; - - return 0; -} - static void gen6_gmch_remove(struct i915_address_space *vm) { struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm); @@ -924,6 +923,7 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt) size = gen8_get_total_gtt_size(snb_gmch_ctl); ggtt->vm.alloc_pt_dma = alloc_pt_dma; + ggtt->vm.alloc_scratch_dma = alloc_pt_dma; ggtt->vm.lmem_pt_obj_flags = I915_BO_ALLOC_PM_EARLY; ggtt->vm.total = (size / sizeof(gen8_pte_t)) * I915_GTT_PAGE_SIZE; @@ -950,8 +950,6 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt) ggtt->vm.vma_ops.bind_vma = ggtt_bind_vma; ggtt->vm.vma_ops.unbind_vma = ggtt_unbind_vma; - ggtt->vm.vma_ops.set_pages = ggtt_set_pages; - ggtt->vm.vma_ops.clear_pages = clear_pages; ggtt->vm.pte_encode = gen8_ggtt_pte_encode; @@ -1077,6 +1075,7 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt) ggtt->vm.total = (size / sizeof(gen6_pte_t)) * I915_GTT_PAGE_SIZE; ggtt->vm.alloc_pt_dma = alloc_pt_dma; + ggtt->vm.alloc_scratch_dma = alloc_pt_dma; ggtt->vm.clear_range = nop_clear_range; if (!HAS_FULL_PPGTT(i915) || intel_scanout_needs_vtd_wa(i915)) @@ -1100,8 +1099,6 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt) ggtt->vm.vma_ops.bind_vma = ggtt_bind_vma; ggtt->vm.vma_ops.unbind_vma = ggtt_unbind_vma; - ggtt->vm.vma_ops.set_pages = ggtt_set_pages; - ggtt->vm.vma_ops.clear_pages = clear_pages; return ggtt_probe_common(ggtt, size); } @@ -1129,6 +1126,7 @@ static int i915_gmch_probe(struct i915_ggtt *ggtt) (struct resource)DEFINE_RES_MEM(gmadr_base, ggtt->mappable_end); ggtt->vm.alloc_pt_dma = alloc_pt_dma; + ggtt->vm.alloc_scratch_dma = alloc_pt_dma; if (needs_idle_maps(i915)) { drm_notice(&i915->drm, @@ -1145,8 +1143,6 @@ static int i915_gmch_probe(struct i915_ggtt *ggtt) ggtt->vm.vma_ops.bind_vma = ggtt_bind_vma; ggtt->vm.vma_ops.unbind_vma = ggtt_unbind_vma; - ggtt->vm.vma_ops.set_pages = ggtt_set_pages; - ggtt->vm.vma_ops.clear_pages = clear_pages; if (unlikely(ggtt->do_idle_maps)) drm_notice(&i915->drm, @@ -1212,11 +1208,11 @@ int i915_ggtt_probe_hw(struct drm_i915_private *i915) { int ret; - ret = ggtt_probe_hw(&i915->ggtt, &i915->gt); + ret = ggtt_probe_hw(&i915->ggtt, to_gt(i915)); if (ret) return ret; - if (intel_vtd_active()) + if (intel_vtd_active(i915)) drm_info(&i915->drm, "VT-d active for gfx access\n"); return 0; @@ -1253,368 +1249,66 @@ void i915_ggtt_disable_guc(struct i915_ggtt *ggtt) ggtt->invalidate(ggtt); } -void i915_ggtt_resume(struct i915_ggtt *ggtt) +/** + * i915_ggtt_resume_vm - Restore the memory mappings for a GGTT or DPT VM + * @vm: The VM to restore the mappings for + * + * Restore the memory mappings for all objects mapped to HW via the GGTT or a + * DPT page table. + * + * Returns %true if restoring the mapping for any object that was in a write + * domain before suspend. + */ +bool i915_ggtt_resume_vm(struct i915_address_space *vm) { struct i915_vma *vma; - bool flush = false; + bool write_domain_objs = false; int open; - intel_gt_check_and_clear_faults(ggtt->vm.gt); + drm_WARN_ON(&vm->i915->drm, !vm->is_ggtt && !vm->is_dpt); /* First fill our portion of the GTT with scratch pages */ - ggtt->vm.clear_range(&ggtt->vm, 0, ggtt->vm.total); + vm->clear_range(vm, 0, vm->total); /* Skip rewriting PTE on VMA unbind. */ - open = atomic_xchg(&ggtt->vm.open, 0); + open = atomic_xchg(&vm->open, 0); /* clflush objects bound into the GGTT and rebind them. */ - list_for_each_entry(vma, &ggtt->vm.bound_list, vm_link) { + list_for_each_entry(vma, &vm->bound_list, vm_link) { struct drm_i915_gem_object *obj = vma->obj; unsigned int was_bound = atomic_read(&vma->flags) & I915_VMA_BIND_MASK; GEM_BUG_ON(!was_bound); - vma->ops->bind_vma(&ggtt->vm, NULL, vma, + vma->ops->bind_vma(vm, NULL, vma, obj ? obj->cache_level : 0, was_bound); if (obj) { /* only used during resume => exclusive access */ - flush |= fetch_and_zero(&obj->write_domain); + write_domain_objs |= fetch_and_zero(&obj->write_domain); obj->read_domains |= I915_GEM_DOMAIN_GTT; } } - atomic_set(&ggtt->vm.open, open); - ggtt->invalidate(ggtt); - - if (flush) - wbinvd_on_all_cpus(); - - if (GRAPHICS_VER(ggtt->vm.i915) >= 8) - setup_private_pat(ggtt->vm.gt->uncore); - - intel_ggtt_restore_fences(ggtt); -} - -static struct scatterlist * -rotate_pages(struct drm_i915_gem_object *obj, unsigned int offset, - unsigned int width, unsigned int height, - unsigned int src_stride, unsigned int dst_stride, - struct sg_table *st, struct scatterlist *sg) -{ - unsigned int column, row; - unsigned int src_idx; - - for (column = 0; column < width; column++) { - unsigned int left; - - src_idx = src_stride * (height - 1) + column + offset; - for (row = 0; row < height; row++) { - st->nents++; - /* - * We don't need the pages, but need to initialize - * the entries so the sg list can be happily traversed. - * The only thing we need are DMA addresses. - */ - sg_set_page(sg, NULL, I915_GTT_PAGE_SIZE, 0); - sg_dma_address(sg) = - i915_gem_object_get_dma_address(obj, src_idx); - sg_dma_len(sg) = I915_GTT_PAGE_SIZE; - sg = sg_next(sg); - src_idx -= src_stride; - } - - left = (dst_stride - height) * I915_GTT_PAGE_SIZE; - - if (!left) - continue; - - st->nents++; - - /* - * The DE ignores the PTEs for the padding tiles, the sg entry - * here is just a conenience to indicate how many padding PTEs - * to insert at this spot. - */ - sg_set_page(sg, NULL, left, 0); - sg_dma_address(sg) = 0; - sg_dma_len(sg) = left; - sg = sg_next(sg); - } - - return sg; -} - -static noinline struct sg_table * -intel_rotate_pages(struct intel_rotation_info *rot_info, - struct drm_i915_gem_object *obj) -{ - unsigned int size = intel_rotation_info_size(rot_info); - struct drm_i915_private *i915 = to_i915(obj->base.dev); - struct sg_table *st; - struct scatterlist *sg; - int ret = -ENOMEM; - int i; - - /* Allocate target SG list. */ - st = kmalloc(sizeof(*st), GFP_KERNEL); - if (!st) - goto err_st_alloc; - - ret = sg_alloc_table(st, size, GFP_KERNEL); - if (ret) - goto err_sg_alloc; - - st->nents = 0; - sg = st->sgl; - - for (i = 0 ; i < ARRAY_SIZE(rot_info->plane); i++) - sg = rotate_pages(obj, rot_info->plane[i].offset, - rot_info->plane[i].width, rot_info->plane[i].height, - rot_info->plane[i].src_stride, - rot_info->plane[i].dst_stride, - st, sg); - - return st; - -err_sg_alloc: - kfree(st); -err_st_alloc: - - drm_dbg(&i915->drm, "Failed to create rotated mapping for object size %zu! (%ux%u tiles, %u pages)\n", - obj->base.size, rot_info->plane[0].width, - rot_info->plane[0].height, size); - - return ERR_PTR(ret); -} - -static struct scatterlist * -remap_pages(struct drm_i915_gem_object *obj, - unsigned int offset, unsigned int alignment_pad, - unsigned int width, unsigned int height, - unsigned int src_stride, unsigned int dst_stride, - struct sg_table *st, struct scatterlist *sg) -{ - unsigned int row; - - if (!width || !height) - return sg; - - if (alignment_pad) { - st->nents++; - - /* - * The DE ignores the PTEs for the padding tiles, the sg entry - * here is just a convenience to indicate how many padding PTEs - * to insert at this spot. - */ - sg_set_page(sg, NULL, alignment_pad * 4096, 0); - sg_dma_address(sg) = 0; - sg_dma_len(sg) = alignment_pad * 4096; - sg = sg_next(sg); - } - - for (row = 0; row < height; row++) { - unsigned int left = width * I915_GTT_PAGE_SIZE; - - while (left) { - dma_addr_t addr; - unsigned int length; - - /* - * We don't need the pages, but need to initialize - * the entries so the sg list can be happily traversed. - * The only thing we need are DMA addresses. - */ - - addr = i915_gem_object_get_dma_address_len(obj, offset, &length); - - length = min(left, length); - - st->nents++; - - sg_set_page(sg, NULL, length, 0); - sg_dma_address(sg) = addr; - sg_dma_len(sg) = length; - sg = sg_next(sg); - - offset += length / I915_GTT_PAGE_SIZE; - left -= length; - } - - offset += src_stride - width; - - left = (dst_stride - width) * I915_GTT_PAGE_SIZE; - - if (!left) - continue; - - st->nents++; - - /* - * The DE ignores the PTEs for the padding tiles, the sg entry - * here is just a conenience to indicate how many padding PTEs - * to insert at this spot. - */ - sg_set_page(sg, NULL, left, 0); - sg_dma_address(sg) = 0; - sg_dma_len(sg) = left; - sg = sg_next(sg); - } - - return sg; -} - -static noinline struct sg_table * -intel_remap_pages(struct intel_remapped_info *rem_info, - struct drm_i915_gem_object *obj) -{ - unsigned int size = intel_remapped_info_size(rem_info); - struct drm_i915_private *i915 = to_i915(obj->base.dev); - struct sg_table *st; - struct scatterlist *sg; - unsigned int gtt_offset = 0; - int ret = -ENOMEM; - int i; - - /* Allocate target SG list. */ - st = kmalloc(sizeof(*st), GFP_KERNEL); - if (!st) - goto err_st_alloc; - - ret = sg_alloc_table(st, size, GFP_KERNEL); - if (ret) - goto err_sg_alloc; - - st->nents = 0; - sg = st->sgl; - - for (i = 0 ; i < ARRAY_SIZE(rem_info->plane); i++) { - unsigned int alignment_pad = 0; - - if (rem_info->plane_alignment) - alignment_pad = ALIGN(gtt_offset, rem_info->plane_alignment) - gtt_offset; - - sg = remap_pages(obj, - rem_info->plane[i].offset, alignment_pad, - rem_info->plane[i].width, rem_info->plane[i].height, - rem_info->plane[i].src_stride, rem_info->plane[i].dst_stride, - st, sg); - - gtt_offset += alignment_pad + - rem_info->plane[i].dst_stride * rem_info->plane[i].height; - } - - i915_sg_trim(st); - - return st; - -err_sg_alloc: - kfree(st); -err_st_alloc: + atomic_set(&vm->open, open); - drm_dbg(&i915->drm, "Failed to create remapped mapping for object size %zu! (%ux%u tiles, %u pages)\n", - obj->base.size, rem_info->plane[0].width, - rem_info->plane[0].height, size); - - return ERR_PTR(ret); + return write_domain_objs; } -static noinline struct sg_table * -intel_partial_pages(const struct i915_ggtt_view *view, - struct drm_i915_gem_object *obj) -{ - struct sg_table *st; - struct scatterlist *sg, *iter; - unsigned int count = view->partial.size; - unsigned int offset; - int ret = -ENOMEM; - - st = kmalloc(sizeof(*st), GFP_KERNEL); - if (!st) - goto err_st_alloc; - - ret = sg_alloc_table(st, count, GFP_KERNEL); - if (ret) - goto err_sg_alloc; - - iter = i915_gem_object_get_sg_dma(obj, view->partial.offset, &offset); - GEM_BUG_ON(!iter); - - sg = st->sgl; - st->nents = 0; - do { - unsigned int len; - - len = min(sg_dma_len(iter) - (offset << PAGE_SHIFT), - count << PAGE_SHIFT); - sg_set_page(sg, NULL, len, 0); - sg_dma_address(sg) = - sg_dma_address(iter) + (offset << PAGE_SHIFT); - sg_dma_len(sg) = len; - - st->nents++; - count -= len >> PAGE_SHIFT; - if (count == 0) { - sg_mark_end(sg); - i915_sg_trim(st); /* Drop any unused tail entries. */ - - return st; - } - - sg = __sg_next(sg); - iter = __sg_next(iter); - offset = 0; - } while (1); - -err_sg_alloc: - kfree(st); -err_st_alloc: - return ERR_PTR(ret); -} - -static int -i915_get_ggtt_vma_pages(struct i915_vma *vma) +void i915_ggtt_resume(struct i915_ggtt *ggtt) { - int ret; + bool flush; - /* - * The vma->pages are only valid within the lifespan of the borrowed - * obj->mm.pages. When the obj->mm.pages sg_table is regenerated, so - * must be the vma->pages. A simple rule is that vma->pages must only - * be accessed when the obj->mm.pages are pinned. - */ - GEM_BUG_ON(!i915_gem_object_has_pinned_pages(vma->obj)); + intel_gt_check_and_clear_faults(ggtt->vm.gt); - switch (vma->ggtt_view.type) { - default: - GEM_BUG_ON(vma->ggtt_view.type); - fallthrough; - case I915_GGTT_VIEW_NORMAL: - vma->pages = vma->obj->mm.pages; - return 0; + flush = i915_ggtt_resume_vm(&ggtt->vm); - case I915_GGTT_VIEW_ROTATED: - vma->pages = - intel_rotate_pages(&vma->ggtt_view.rotated, vma->obj); - break; + ggtt->invalidate(ggtt); - case I915_GGTT_VIEW_REMAPPED: - vma->pages = - intel_remap_pages(&vma->ggtt_view.remapped, vma->obj); - break; + if (flush) + wbinvd_on_all_cpus(); - case I915_GGTT_VIEW_PARTIAL: - vma->pages = intel_partial_pages(&vma->ggtt_view, vma->obj); - break; - } + if (GRAPHICS_VER(ggtt->vm.i915) >= 8) + setup_private_pat(ggtt->vm.gt->uncore); - ret = 0; - if (IS_ERR(vma->pages)) { - ret = PTR_ERR(vma->pages); - vma->pages = NULL; - drm_err(&vma->vm->i915->drm, - "Failed to get pages for VMA view type %u (%d)!\n", - vma->ggtt_view.type, ret); - } - return ret; + intel_ggtt_restore_fences(ggtt); } diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index 1cb1948ac959..f98f0fb21efb 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -3,6 +3,8 @@ * Copyright © 2019 Intel Corporation */ +#include <drm/intel-gtt.h> + #include "intel_gt_debugfs.h" #include "gem/i915_gem_lmem.h" @@ -23,11 +25,8 @@ #include "shmem_utils.h" #include "pxp/intel_pxp.h" -void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915) +void __intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915) { - gt->i915 = i915; - gt->uncore = &i915->uncore; - spin_lock_init(>->irq_lock); INIT_LIST_HEAD(>->closed_vma); @@ -46,6 +45,12 @@ void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915) intel_rps_init_early(>->rps); } +void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915) +{ + gt->i915 = i915; + gt->uncore = &i915->uncore; +} + int intel_gt_probe_lmem(struct intel_gt *gt) { struct drm_i915_private *i915 = gt->i915; diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h index 74e771871a9b..3ace129eb2af 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.h +++ b/drivers/gpu/drm/i915/gt/intel_gt.h @@ -35,6 +35,7 @@ static inline struct intel_gt *huc_to_gt(struct intel_huc *huc) } void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915); +void __intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915); void intel_gt_init_hw_early(struct intel_gt *gt, struct i915_ggtt *ggtt); int intel_gt_probe_lmem(struct intel_gt *gt); int intel_gt_init_mmio(struct intel_gt *gt); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c index acc49c56a9f3..9db3dcbd917f 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c @@ -9,11 +9,6 @@ #include "intel_engine_pm.h" #include "intel_gt_buffer_pool.h" -static struct intel_gt *to_gt(struct intel_gt_buffer_pool *pool) -{ - return container_of(pool, struct intel_gt, buffer_pool); -} - static struct list_head * bucket_for_size(struct intel_gt_buffer_pool *pool, size_t sz) { @@ -141,7 +136,7 @@ static struct intel_gt_buffer_pool_node * node_create(struct intel_gt_buffer_pool *pool, size_t sz, enum i915_map_type type) { - struct intel_gt *gt = to_gt(pool); + struct intel_gt *gt = container_of(pool, struct intel_gt, buffer_pool); struct intel_gt_buffer_pool_node *node; struct drm_i915_gem_object *obj; diff --git a/drivers/gpu/drm/i915/gt/intel_gt_debugfs.h b/drivers/gpu/drm/i915/gt/intel_gt_debugfs.h index e307ceb99031..17e79b735cfe 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_debugfs.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_debugfs.h @@ -10,11 +10,7 @@ struct intel_gt; -#define DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(__name) \ - static int __name ## _open(struct inode *inode, struct file *file) \ -{ \ - return single_open(file, __name ## _show, inode->i_private); \ -} \ +#define __GT_DEBUGFS_ATTRIBUTE_FOPS(__name) \ static const struct file_operations __name ## _fops = { \ .owner = THIS_MODULE, \ .open = __name ## _open, \ @@ -23,6 +19,21 @@ static const struct file_operations __name ## _fops = { \ .release = single_release, \ } +#define DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(__name) \ +static int __name ## _open(struct inode *inode, struct file *file) \ +{ \ + return single_open(file, __name ## _show, inode->i_private); \ +} \ +__GT_DEBUGFS_ATTRIBUTE_FOPS(__name) + +#define DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE_WITH_SIZE(__name, __size_vf) \ +static int __name ## _open(struct inode *inode, struct file *file) \ +{ \ + return single_open_size(file, __name ## _show, inode->i_private, \ + __size_vf(inode->i_private)); \ +} \ +__GT_DEBUGFS_ATTRIBUTE_FOPS(__name) + void intel_gt_debugfs_register(struct intel_gt *gt); struct intel_gt_debugfs_file { diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c index 795689eb3fc7..c0fa41e4c803 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c @@ -86,6 +86,7 @@ static int __gt_unpark(struct intel_wakeref *wf) intel_rc6_unpark(>->rc6); intel_rps_unpark(>->rps); i915_pmu_gt_unparked(i915); + intel_guc_busyness_unpark(gt); intel_gt_unpark_requests(gt); runtime_begin(gt); @@ -104,6 +105,7 @@ static int __gt_park(struct intel_wakeref *wf) runtime_end(gt); intel_gt_park_requests(gt); + intel_guc_busyness_park(gt); i915_vma_parked(gt); i915_pmu_gt_parked(i915); intel_rps_park(>->rps); diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c index b67f620c3d93..a94be0306464 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.c +++ b/drivers/gpu/drm/i915/gt/intel_gtt.c @@ -8,6 +8,8 @@ #include <linux/fault-inject.h> #include <linux/sched/mm.h> +#include <drm/drm_cache.h> + #include "gem/i915_gem_lmem.h" #include "i915_trace.h" #include "intel_gt.h" @@ -222,19 +224,6 @@ void i915_address_space_init(struct i915_address_space *vm, int subclass) INIT_LIST_HEAD(&vm->bound_list); } -void clear_pages(struct i915_vma *vma) -{ - GEM_BUG_ON(!vma->pages); - - if (vma->pages != vma->obj->mm.pages) { - sg_free_table(vma->pages); - kfree(vma->pages); - } - vma->pages = NULL; - - memset(&vma->page_sizes, 0, sizeof(vma->page_sizes)); -} - void *__px_vaddr(struct drm_i915_gem_object *p) { enum i915_map_type type; @@ -274,6 +263,7 @@ static void poison_scratch_page(struct drm_i915_gem_object *scratch) val = POISON_FREE; memset(vaddr, val, scratch->base.size); + drm_clflush_virt_range(vaddr, scratch->base.size); } int setup_scratch_page(struct i915_address_space *vm) @@ -299,7 +289,7 @@ int setup_scratch_page(struct i915_address_space *vm) do { struct drm_i915_gem_object *obj; - obj = vm->alloc_pt_dma(vm, size); + obj = vm->alloc_scratch_dma(vm, size); if (IS_ERR(obj)) goto skip; @@ -335,6 +325,18 @@ 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); } diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h index bc6750263359..177b42b935a1 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.h +++ b/drivers/gpu/drm/i915/gt/intel_gtt.h @@ -135,6 +135,9 @@ typedef u64 gen8_pte_t; #define GEN8_PPAT_ELLC_OVERRIDE (0<<2) #define GEN8_PPAT(i, x) ((u64)(x) << ((i) * 8)) +#define GEN8_PAGE_PRESENT BIT_ULL(0) +#define GEN8_PAGE_RW BIT_ULL(1) + #define GEN8_PDE_IPS_64K BIT(11) #define GEN8_PDE_PS_2M BIT(7) @@ -206,9 +209,6 @@ struct i915_vma_ops { */ void (*unbind_vma)(struct i915_address_space *vm, struct i915_vma *vma); - - int (*set_pages)(struct i915_vma *vma); - void (*clear_pages)(struct i915_vma *vma); }; struct i915_address_space { @@ -265,6 +265,8 @@ struct i915_address_space { struct drm_i915_gem_object * (*alloc_pt_dma)(struct i915_address_space *vm, int sz); + struct drm_i915_gem_object * + (*alloc_scratch_dma)(struct i915_address_space *vm, int sz); u64 (*pte_encode)(dma_addr_t addr, enum i915_cache_level level, @@ -544,6 +546,8 @@ int i915_ppgtt_init_hw(struct intel_gt *gt); struct i915_ppgtt *i915_ppgtt_create(struct intel_gt *gt, unsigned long lmem_pt_obj_flags); +void i915_ggtt_suspend_vm(struct i915_address_space *vm); +bool i915_ggtt_resume_vm(struct i915_address_space *vm); void i915_ggtt_suspend(struct i915_ggtt *gtt); void i915_ggtt_resume(struct i915_ggtt *ggtt); @@ -594,10 +598,6 @@ release_pd_entry(struct i915_page_directory * const pd, const struct drm_i915_gem_object * const scratch); void gen6_ggtt_invalidate(struct i915_ggtt *ggtt); -int ggtt_set_pages(struct i915_vma *vma); -int ppgtt_set_pages(struct i915_vma *vma); -void clear_pages(struct i915_vma *vma); - void ppgtt_bind_vma(struct i915_address_space *vm, struct i915_vm_pt_stash *stash, struct i915_vma *vma, diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 56156cf18c41..b3489599e4de 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -1167,6 +1167,11 @@ gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs) cs = gen12_emit_cmd_buf_wa(ce, cs); cs = gen12_emit_restore_scratch(ce, cs); + /* Wa_16013000631:dg2 */ + if (IS_DG2_GRAPHICS_STEP(ce->engine->i915, G10, STEP_B0, STEP_C0) || + IS_DG2_G11(ce->engine->i915)) + cs = gen8_emit_pipe_control(cs, PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE, 0); + return cs; } diff --git a/drivers/gpu/drm/i915/gt/intel_migrate.c b/drivers/gpu/drm/i915/gt/intel_migrate.c index afb1cce9a352..18b44af56969 100644 --- a/drivers/gpu/drm/i915/gt/intel_migrate.c +++ b/drivers/gpu/drm/i915/gt/intel_migrate.c @@ -13,7 +13,6 @@ struct insert_pte_data { u64 offset; - bool is_lmem; }; #define CHUNK_SZ SZ_8M /* ~1ms at 8GiB/s preemption delay */ @@ -40,7 +39,7 @@ static void insert_pte(struct i915_address_space *vm, struct insert_pte_data *d = data; vm->insert_page(vm, px_dma(pt), d->offset, I915_CACHE_NONE, - d->is_lmem ? PTE_LM : 0); + i915_gem_object_is_lmem(pt->base) ? PTE_LM : 0); d->offset += PAGE_SIZE; } @@ -134,8 +133,7 @@ static struct i915_address_space *migrate_vm(struct intel_gt *gt) goto err_vm; /* Now allow the GPU to rewrite the PTE via its own ppGTT */ - d.is_lmem = i915_gem_object_is_lmem(vm->vm.scratch[0]); - vm->vm.foreach(&vm->vm, base, base + sz, insert_pte, &d); + vm->vm.foreach(&vm->vm, base, d.offset - base, insert_pte, &d); } return &vm->vm; @@ -281,10 +279,10 @@ static int emit_pte(struct i915_request *rq, GEM_BUG_ON(GRAPHICS_VER(rq->engine->i915) < 8); /* Compute the page directory offset for the target address range */ - offset += (u64)rq->engine->instance << 32; offset >>= 12; offset *= sizeof(u64); offset += 2 * CHUNK_SZ; + offset += (u64)rq->engine->instance << 32; cs = intel_ring_begin(rq, 6); if (IS_ERR(cs)) @@ -406,7 +404,7 @@ static int emit_copy(struct i915_request *rq, int size) int intel_context_migrate_copy(struct intel_context *ce, - struct dma_fence *await, + const struct i915_deps *deps, struct scatterlist *src, enum i915_cache_level src_cache_level, bool src_is_lmem, @@ -433,8 +431,8 @@ intel_context_migrate_copy(struct intel_context *ce, goto out_ce; } - if (await) { - err = i915_request_await_dma_fence(rq, await); + if (deps) { + err = i915_request_await_deps(rq, deps); if (err) goto out_rq; @@ -444,7 +442,7 @@ intel_context_migrate_copy(struct intel_context *ce, goto out_rq; } - await = NULL; + deps = NULL; } /* The PTE updates + copy must not be interrupted. */ @@ -527,7 +525,7 @@ static int emit_clear(struct i915_request *rq, int size, u32 value) int intel_context_migrate_clear(struct intel_context *ce, - struct dma_fence *await, + const struct i915_deps *deps, struct scatterlist *sg, enum i915_cache_level cache_level, bool is_lmem, @@ -552,8 +550,8 @@ intel_context_migrate_clear(struct intel_context *ce, goto out_ce; } - if (await) { - err = i915_request_await_dma_fence(rq, await); + if (deps) { + err = i915_request_await_deps(rq, deps); if (err) goto out_rq; @@ -563,7 +561,7 @@ intel_context_migrate_clear(struct intel_context *ce, goto out_rq; } - await = NULL; + deps = NULL; } /* The PTE updates + clear must not be interrupted. */ @@ -601,7 +599,7 @@ out_ce: int intel_migrate_copy(struct intel_migrate *m, struct i915_gem_ww_ctx *ww, - struct dma_fence *await, + const struct i915_deps *deps, struct scatterlist *src, enum i915_cache_level src_cache_level, bool src_is_lmem, @@ -626,7 +624,7 @@ int intel_migrate_copy(struct intel_migrate *m, if (err) goto out; - err = intel_context_migrate_copy(ce, await, + err = intel_context_migrate_copy(ce, deps, src, src_cache_level, src_is_lmem, dst, dst_cache_level, dst_is_lmem, out); @@ -640,7 +638,7 @@ out: int intel_migrate_clear(struct intel_migrate *m, struct i915_gem_ww_ctx *ww, - struct dma_fence *await, + const struct i915_deps *deps, struct scatterlist *sg, enum i915_cache_level cache_level, bool is_lmem, @@ -663,7 +661,7 @@ intel_migrate_clear(struct intel_migrate *m, if (err) goto out; - err = intel_context_migrate_clear(ce, await, sg, cache_level, + err = intel_context_migrate_clear(ce, deps, sg, cache_level, is_lmem, value, out); intel_context_unpin(ce); diff --git a/drivers/gpu/drm/i915/gt/intel_migrate.h b/drivers/gpu/drm/i915/gt/intel_migrate.h index 4e18e755a00b..ccc677ec4aa3 100644 --- a/drivers/gpu/drm/i915/gt/intel_migrate.h +++ b/drivers/gpu/drm/i915/gt/intel_migrate.h @@ -11,6 +11,7 @@ #include "intel_migrate_types.h" struct dma_fence; +struct i915_deps; struct i915_request; struct i915_gem_ww_ctx; struct intel_gt; @@ -23,7 +24,7 @@ struct intel_context *intel_migrate_create_context(struct intel_migrate *m); int intel_migrate_copy(struct intel_migrate *m, struct i915_gem_ww_ctx *ww, - struct dma_fence *await, + const struct i915_deps *deps, struct scatterlist *src, enum i915_cache_level src_cache_level, bool src_is_lmem, @@ -33,7 +34,7 @@ int intel_migrate_copy(struct intel_migrate *m, struct i915_request **out); int intel_context_migrate_copy(struct intel_context *ce, - struct dma_fence *await, + const struct i915_deps *deps, struct scatterlist *src, enum i915_cache_level src_cache_level, bool src_is_lmem, @@ -45,7 +46,7 @@ int intel_context_migrate_copy(struct intel_context *ce, int intel_migrate_clear(struct intel_migrate *m, struct i915_gem_ww_ctx *ww, - struct dma_fence *await, + const struct i915_deps *deps, struct scatterlist *sg, enum i915_cache_level cache_level, bool is_lmem, @@ -53,7 +54,7 @@ intel_migrate_clear(struct intel_migrate *m, struct i915_request **out); int intel_context_migrate_clear(struct intel_context *ce, - struct dma_fence *await, + const struct i915_deps *deps, struct scatterlist *sg, enum i915_cache_level cache_level, bool is_lmem, diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c index 15f9ada28a7a..9c253ba593c6 100644 --- a/drivers/gpu/drm/i915/gt/intel_mocs.c +++ b/drivers/gpu/drm/i915/gt/intel_mocs.c @@ -424,7 +424,7 @@ static unsigned int get_mocs_settings(const struct drm_i915_private *i915, table->unused_entries_index = I915_MOCS_PTE; if (IS_DG2(i915)) { - if (IS_DG2_GT_STEP(i915, G10, STEP_A0, STEP_B0)) { + if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) { table->size = ARRAY_SIZE(dg2_mocs_table_g10_ax); table->table = dg2_mocs_table_g10_ax; } else { diff --git a/drivers/gpu/drm/i915/gt/intel_ppgtt.c b/drivers/gpu/drm/i915/gt/intel_ppgtt.c index 4396bfd630d8..083b3090c69c 100644 --- a/drivers/gpu/drm/i915/gt/intel_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ppgtt.c @@ -289,16 +289,6 @@ void i915_vm_free_pt_stash(struct i915_address_space *vm, } } -int ppgtt_set_pages(struct i915_vma *vma) -{ - GEM_BUG_ON(vma->pages); - - vma->pages = vma->obj->mm.pages; - vma->page_sizes = vma->obj->mm.page_sizes; - - return 0; -} - void ppgtt_init(struct i915_ppgtt *ppgtt, struct intel_gt *gt, unsigned long lmem_pt_obj_flags) { @@ -315,6 +305,4 @@ void ppgtt_init(struct i915_ppgtt *ppgtt, struct intel_gt *gt, ppgtt->vm.vma_ops.bind_vma = ppgtt_bind_vma; ppgtt->vm.vma_ops.unbind_vma = ppgtt_unbind_vma; - ppgtt->vm.vma_ops.set_pages = ppgtt_set_pages; - ppgtt->vm.vma_ops.clear_pages = clear_pages; } diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c index 43093dd2d0c9..c3155ee58689 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6.c +++ b/drivers/gpu/drm/i915/gt/intel_rc6.c @@ -117,10 +117,17 @@ static void gen11_rc6_enable(struct intel_rc6 *rc6) GEN6_RC_CTL_RC6_ENABLE | GEN6_RC_CTL_EI_MODE(1); - pg_enable = - GEN9_RENDER_PG_ENABLE | - GEN9_MEDIA_PG_ENABLE | - GEN11_MEDIA_SAMPLER_PG_ENABLE; + /* Wa_16011777198 - Render powergating must remain disabled */ + if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_C0) || + IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_B0)) + pg_enable = + GEN9_MEDIA_PG_ENABLE | + GEN11_MEDIA_SAMPLER_PG_ENABLE; + else + pg_enable = + GEN9_RENDER_PG_ENABLE | + GEN9_MEDIA_PG_ENABLE | + GEN11_MEDIA_SAMPLER_PG_ENABLE; if (GRAPHICS_VER(gt->i915) >= 12) { for (i = 0; i < I915_MAX_VCS; i++) diff --git a/drivers/gpu/drm/i915/gt/intel_region_lmem.c b/drivers/gpu/drm/i915/gt/intel_region_lmem.c index afb35d2e5c73..fde2dcb59809 100644 --- a/drivers/gpu/drm/i915/gt/intel_region_lmem.c +++ b/drivers/gpu/drm/i915/gt/intel_region_lmem.c @@ -66,12 +66,16 @@ static void release_fake_lmem_bar(struct intel_memory_region *mem) DMA_ATTR_FORCE_CONTIGUOUS); } -static void +static int region_lmem_release(struct intel_memory_region *mem) { - intel_region_ttm_fini(mem); + int ret; + + ret = intel_region_ttm_fini(mem); io_mapping_fini(&mem->iomap); release_fake_lmem_bar(mem); + + return ret; } static int @@ -158,7 +162,7 @@ intel_gt_setup_fake_lmem(struct intel_gt *gt) static bool get_legacy_lowmem_region(struct intel_uncore *uncore, u64 *start, u32 *size) { - if (!IS_DG1_GT_STEP(uncore->i915, STEP_A0, STEP_C0)) + if (!IS_DG1_GRAPHICS_STEP(uncore->i915, STEP_A0, STEP_C0)) return false; *start = 0; @@ -193,6 +197,7 @@ static struct intel_memory_region *setup_lmem(struct intel_gt *gt) struct intel_uncore *uncore = gt->uncore; struct pci_dev *pdev = to_pci_dev(i915->drm.dev); struct intel_memory_region *mem; + resource_size_t min_page_size; resource_size_t io_start; resource_size_t lmem_size; int err; @@ -207,10 +212,12 @@ static struct intel_memory_region *setup_lmem(struct intel_gt *gt) if (GEM_WARN_ON(lmem_size > pci_resource_len(pdev, 2))) return ERR_PTR(-ENODEV); + min_page_size = HAS_64K_PAGES(i915) ? I915_GTT_PAGE_SIZE_64K : + I915_GTT_PAGE_SIZE_4K; mem = intel_memory_region_create(i915, 0, lmem_size, - I915_GTT_PAGE_SIZE_4K, + min_page_size, io_start, INTEL_MEMORY_LOCAL, 0, @@ -231,7 +238,7 @@ static struct intel_memory_region *setup_lmem(struct intel_gt *gt) return mem; err_region_put: - intel_memory_region_put(mem); + intel_memory_region_destroy(mem); return ERR_PTR(err); } diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index 91200c43951f..7be0002d9d70 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -6,7 +6,7 @@ #include <linux/sched/mm.h> #include <linux/stop_machine.h> -#include "display/intel_display_types.h" +#include "display/intel_display.h" #include "display/intel_overlay.h" #include "gem/i915_gem_context.h" @@ -297,13 +297,6 @@ static int gen6_reset_engines(struct intel_gt *gt, intel_engine_mask_t engine_mask, unsigned int retry) { - static const u32 hw_engine_mask[] = { - [RCS0] = GEN6_GRDOM_RENDER, - [BCS0] = GEN6_GRDOM_BLT, - [VCS0] = GEN6_GRDOM_MEDIA, - [VCS1] = GEN8_GRDOM_MEDIA2, - [VECS0] = GEN6_GRDOM_VECS, - }; struct intel_engine_cs *engine; u32 hw_mask; @@ -314,8 +307,7 @@ static int gen6_reset_engines(struct intel_gt *gt, hw_mask = 0; for_each_engine_masked(engine, gt, engine_mask, tmp) { - GEM_BUG_ON(engine->id >= ARRAY_SIZE(hw_engine_mask)); - hw_mask |= hw_engine_mask[engine->id]; + hw_mask |= engine->reset_domain; } } @@ -492,22 +484,6 @@ static int gen11_reset_engines(struct intel_gt *gt, intel_engine_mask_t engine_mask, unsigned int retry) { - static const u32 hw_engine_mask[] = { - [RCS0] = GEN11_GRDOM_RENDER, - [BCS0] = GEN11_GRDOM_BLT, - [VCS0] = GEN11_GRDOM_MEDIA, - [VCS1] = GEN11_GRDOM_MEDIA2, - [VCS2] = GEN11_GRDOM_MEDIA3, - [VCS3] = GEN11_GRDOM_MEDIA4, - [VCS4] = GEN11_GRDOM_MEDIA5, - [VCS5] = GEN11_GRDOM_MEDIA6, - [VCS6] = GEN11_GRDOM_MEDIA7, - [VCS7] = GEN11_GRDOM_MEDIA8, - [VECS0] = GEN11_GRDOM_VECS, - [VECS1] = GEN11_GRDOM_VECS2, - [VECS2] = GEN11_GRDOM_VECS3, - [VECS3] = GEN11_GRDOM_VECS4, - }; struct intel_engine_cs *engine; intel_engine_mask_t tmp; u32 reset_mask, unlock_mask = 0; @@ -518,8 +494,7 @@ static int gen11_reset_engines(struct intel_gt *gt, } else { reset_mask = 0; for_each_engine_masked(engine, gt, engine_mask, tmp) { - GEM_BUG_ON(engine->id >= ARRAY_SIZE(hw_engine_mask)); - reset_mask |= hw_engine_mask[engine->id]; + reset_mask |= engine->reset_domain; ret = gen11_lock_sfc(engine, &reset_mask, &unlock_mask); if (ret) goto sfc_unlock; @@ -1367,20 +1342,27 @@ void intel_gt_handle_error(struct intel_gt *gt, /* Make sure i915_reset_trylock() sees the I915_RESET_BACKOFF */ synchronize_rcu_expedited(); - /* Prevent any other reset-engine attempt. */ - for_each_engine(engine, gt, tmp) { - while (test_and_set_bit(I915_RESET_ENGINE + engine->id, - >->reset.flags)) - wait_on_bit(>->reset.flags, - I915_RESET_ENGINE + engine->id, - TASK_UNINTERRUPTIBLE); + /* + * Prevent any other reset-engine attempt. We don't do this for GuC + * submission the GuC owns the per-engine reset, not the i915. + */ + if (!intel_uc_uses_guc_submission(>->uc)) { + for_each_engine(engine, gt, tmp) { + while (test_and_set_bit(I915_RESET_ENGINE + engine->id, + >->reset.flags)) + wait_on_bit(>->reset.flags, + I915_RESET_ENGINE + engine->id, + TASK_UNINTERRUPTIBLE); + } } intel_gt_reset_global(gt, engine_mask, msg); - for_each_engine(engine, gt, tmp) - clear_bit_unlock(I915_RESET_ENGINE + engine->id, - >->reset.flags); + if (!intel_uc_uses_guc_submission(>->uc)) { + for_each_engine(engine, gt, tmp) + clear_bit_unlock(I915_RESET_ENGINE + engine->id, + >->reset.flags); + } clear_bit_unlock(I915_RESET_BACKOFF, >->reset.flags); smp_mb__after_atomic(); wake_up_all(>->reset.queue); @@ -1441,6 +1423,7 @@ void intel_gt_set_wedged_on_init(struct intel_gt *gt) BUILD_BUG_ON(I915_RESET_ENGINE + I915_NUM_ENGINES > I915_WEDGED_ON_INIT); intel_gt_set_wedged(gt); + i915_disable_error_state(gt->i915, -ENODEV); set_bit(I915_WEDGED_ON_INIT, >->reset.flags); /* Wedged on init is non-recoverable */ @@ -1450,6 +1433,7 @@ void intel_gt_set_wedged_on_init(struct intel_gt *gt) void intel_gt_set_wedged_on_fini(struct intel_gt *gt) { intel_gt_set_wedged(gt); + i915_disable_error_state(gt->i915, -ENODEV); set_bit(I915_WEDGED_ON_FINI, >->reset.flags); intel_gt_retire_requests(gt); /* cleanup any wedged requests */ } diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c index 586dca1731ce..3e6fac0340ef 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c @@ -1357,7 +1357,7 @@ retry: err = i915_gem_object_lock(timeline->hwsp_ggtt->obj, &ww); if (!err && gen7_wa_vma) err = i915_gem_object_lock(gen7_wa_vma->obj, &ww); - if (!err && engine->legacy.ring->vma->obj) + if (!err) err = i915_gem_object_lock(engine->legacy.ring->vma->obj, &ww); if (!err) err = intel_timeline_pin(timeline, &ww); diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index 5e275f8dda8c..54e7df788dbf 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -936,8 +936,70 @@ void intel_rps_park(struct intel_rps *rps) GT_TRACE(rps_to_gt(rps), "park:%x\n", rps->cur_freq); } +u32 intel_rps_get_boost_frequency(struct intel_rps *rps) +{ + struct intel_guc_slpc *slpc; + + if (rps_uses_slpc(rps)) { + slpc = rps_to_slpc(rps); + + return slpc->boost_freq; + } else { + return intel_gpu_freq(rps, rps->boost_freq); + } +} + +static int rps_set_boost_freq(struct intel_rps *rps, u32 val) +{ + bool boost = false; + + /* Validate against (static) hardware limits */ + val = intel_freq_opcode(rps, val); + if (val < rps->min_freq || val > rps->max_freq) + return -EINVAL; + + mutex_lock(&rps->lock); + if (val != rps->boost_freq) { + rps->boost_freq = val; + boost = atomic_read(&rps->num_waiters); + } + mutex_unlock(&rps->lock); + if (boost) + schedule_work(&rps->work); + + return 0; +} + +int intel_rps_set_boost_frequency(struct intel_rps *rps, u32 freq) +{ + struct intel_guc_slpc *slpc; + + if (rps_uses_slpc(rps)) { + slpc = rps_to_slpc(rps); + + return intel_guc_slpc_set_boost_freq(slpc, freq); + } else { + return rps_set_boost_freq(rps, freq); + } +} + +void intel_rps_dec_waiters(struct intel_rps *rps) +{ + struct intel_guc_slpc *slpc; + + if (rps_uses_slpc(rps)) { + slpc = rps_to_slpc(rps); + + intel_guc_slpc_dec_waiters(slpc); + } else { + atomic_dec(&rps->num_waiters); + } +} + void intel_rps_boost(struct i915_request *rq) { + struct intel_guc_slpc *slpc; + if (i915_request_signaled(rq) || i915_request_has_waitboost(rq)) return; @@ -945,6 +1007,16 @@ void intel_rps_boost(struct i915_request *rq) if (!test_and_set_bit(I915_FENCE_FLAG_BOOST, &rq->fence.flags)) { struct intel_rps *rps = &READ_ONCE(rq->engine)->gt->rps; + if (rps_uses_slpc(rps)) { + slpc = rps_to_slpc(rps); + + /* Return if old value is non zero */ + if (!atomic_fetch_inc(&slpc->num_waiters)) + schedule_work(&slpc->boost_work); + + return; + } + if (atomic_fetch_inc(&rps->num_waiters)) return; @@ -2154,6 +2226,65 @@ u32 intel_rps_read_state_cap(struct intel_rps *rps) return intel_uncore_read(uncore, GEN6_RP_STATE_CAP); } +static void intel_rps_set_manual(struct intel_rps *rps, bool enable) +{ + struct intel_uncore *uncore = rps_to_uncore(rps); + u32 state = enable ? GEN9_RPSWCTL_ENABLE : GEN9_RPSWCTL_DISABLE; + + /* Allow punit to process software requests */ + intel_uncore_write(uncore, GEN6_RP_CONTROL, state); +} + +void intel_rps_raise_unslice(struct intel_rps *rps) +{ + struct intel_uncore *uncore = rps_to_uncore(rps); + u32 rp0_unslice_req; + + mutex_lock(&rps->lock); + + if (rps_uses_slpc(rps)) { + /* RP limits have not been initialized yet for SLPC path */ + rp0_unslice_req = ((intel_rps_read_state_cap(rps) >> 0) + & 0xff) * GEN9_FREQ_SCALER; + + intel_rps_set_manual(rps, true); + intel_uncore_write(uncore, GEN6_RPNSWREQ, + ((rp0_unslice_req << + GEN9_SW_REQ_UNSLICE_RATIO_SHIFT) | + GEN9_IGNORE_SLICE_RATIO)); + intel_rps_set_manual(rps, false); + } else { + intel_rps_set(rps, rps->rp0_freq); + } + + mutex_unlock(&rps->lock); +} + +void intel_rps_lower_unslice(struct intel_rps *rps) +{ + struct intel_uncore *uncore = rps_to_uncore(rps); + u32 rpn_unslice_req; + + mutex_lock(&rps->lock); + + if (rps_uses_slpc(rps)) { + /* RP limits have not been initialized yet for SLPC path */ + rpn_unslice_req = ((intel_rps_read_state_cap(rps) >> 16) + & 0xff) * GEN9_FREQ_SCALER; + + intel_rps_set_manual(rps, true); + intel_uncore_write(uncore, GEN6_RPNSWREQ, + ((rpn_unslice_req << + GEN9_SW_REQ_UNSLICE_RATIO_SHIFT) | + GEN9_IGNORE_SLICE_RATIO)); + intel_rps_set_manual(rps, false); + } else { + intel_rps_set(rps, rps->min_freq); + } + + mutex_unlock(&rps->lock); +} + /* External interface for intel_ips.ko */ static struct drm_i915_private __rcu *ips_mchdev; @@ -2230,7 +2361,7 @@ unsigned long i915_read_mch_val(void) return 0; with_intel_runtime_pm(&i915->runtime_pm, wakeref) { - struct intel_ips *ips = &i915->gt.rps.ips; + struct intel_ips *ips = &to_gt(i915)->rps.ips; spin_lock_irq(&mchdev_lock); chipset_val = __ips_chipset_val(ips); @@ -2257,7 +2388,7 @@ bool i915_gpu_raise(void) if (!i915) return false; - rps = &i915->gt.rps; + rps = &to_gt(i915)->rps; spin_lock_irq(&mchdev_lock); if (rps->max_freq_softlimit < rps->max_freq) @@ -2284,7 +2415,7 @@ bool i915_gpu_lower(void) if (!i915) return false; - rps = &i915->gt.rps; + rps = &to_gt(i915)->rps; spin_lock_irq(&mchdev_lock); if (rps->max_freq_softlimit > rps->min_freq) @@ -2310,7 +2441,7 @@ bool i915_gpu_busy(void) if (!i915) return false; - ret = i915->gt.awake; + ret = to_gt(i915)->awake; drm_dev_put(&i915->drm); return ret; @@ -2333,11 +2464,11 @@ bool i915_gpu_turbo_disable(void) if (!i915) return false; - rps = &i915->gt.rps; + rps = &to_gt(i915)->rps; spin_lock_irq(&mchdev_lock); rps->max_freq_softlimit = rps->min_freq; - ret = !__gen5_rps_set(&i915->gt.rps, rps->min_freq); + ret = !__gen5_rps_set(&to_gt(i915)->rps, rps->min_freq); spin_unlock_irq(&mchdev_lock); drm_dev_put(&i915->drm); diff --git a/drivers/gpu/drm/i915/gt/intel_rps.h b/drivers/gpu/drm/i915/gt/intel_rps.h index 11960d64ca82..c6d76a3d1331 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.h +++ b/drivers/gpu/drm/i915/gt/intel_rps.h @@ -23,6 +23,9 @@ void intel_rps_disable(struct intel_rps *rps); void intel_rps_park(struct intel_rps *rps); void intel_rps_unpark(struct intel_rps *rps); void intel_rps_boost(struct i915_request *rq); +void intel_rps_dec_waiters(struct intel_rps *rps); +u32 intel_rps_get_boost_frequency(struct intel_rps *rps); +int intel_rps_set_boost_frequency(struct intel_rps *rps, u32 freq); int intel_rps_set(struct intel_rps *rps, u8 val); void intel_rps_mark_interactive(struct intel_rps *rps, bool interactive); @@ -42,6 +45,8 @@ 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_state_cap(struct intel_rps *rps); +void intel_rps_raise_unslice(struct intel_rps *rps); +void intel_rps_lower_unslice(struct intel_rps *rps); void gen5_rps_irq_handler(struct intel_rps *rps); void gen6_rps_irq_handler(struct intel_rps *rps, u32 pm_iir); diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 2400d6423ba5..ab3277a3d593 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -482,7 +482,7 @@ static void kbl_ctx_workarounds_init(struct intel_engine_cs *engine, gen9_ctx_workarounds_init(engine, wal); /* WaToEnableHwFixForPushConstHWBug:kbl */ - if (IS_KBL_GT_STEP(i915, STEP_C0, STEP_FOREVER)) + if (IS_KBL_GRAPHICS_STEP(i915, STEP_C0, STEP_FOREVER)) wa_masked_en(wal, COMMON_SLICE_CHICKEN2, GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); @@ -560,6 +560,22 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine, /* * These settings aren't actually workarounds, but general tuning settings that + * need to be programmed on dg2 platform. + */ +static void dg2_ctx_gt_tuning_init(struct intel_engine_cs *engine, + struct i915_wa_list *wal) +{ + 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); +} + +/* + * These settings aren't actually workarounds, but general tuning settings that * need to be programmed on several platforms. */ static void gen12_ctx_gt_tuning_init(struct intel_engine_cs *engine, @@ -637,6 +653,42 @@ static void dg1_ctx_workarounds_init(struct intel_engine_cs *engine, DG1_HZ_READ_SUPPRESSION_OPTIMIZATION_DISABLE); } +static void dg2_ctx_workarounds_init(struct intel_engine_cs *engine, + struct i915_wa_list *wal) +{ + dg2_ctx_gt_tuning_init(engine, wal); + + /* 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); + } + + 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_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_16013271637:dg2 */ + wa_masked_en(wal, SLICE_COMMON_ECO_CHICKEN1, + MSC_MSAA_REODER_BUF_BYPASS_DISABLE); + + /* 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); +} + static void fakewa_disable_nestedbb_mode(struct intel_engine_cs *engine, struct i915_wa_list *wal) { @@ -723,7 +775,11 @@ __intel_engine_init_ctx_wa(struct intel_engine_cs *engine, if (engine->class != RENDER_CLASS) goto done; - if (IS_DG1(i915)) + if (IS_DG2(i915)) + dg2_ctx_workarounds_init(engine, wal); + else if (IS_XEHPSDV(i915)) + ; /* noop; none at this time */ + else if (IS_DG1(i915)) dg1_ctx_workarounds_init(engine, wal); else if (GRAPHICS_VER(i915) == 12) gen12_ctx_workarounds_init(engine, wal); @@ -871,10 +927,51 @@ hsw_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) } static void +gen9_wa_init_mcr(struct drm_i915_private *i915, struct i915_wa_list *wal) +{ + const struct sseu_dev_info *sseu = &to_gt(i915)->info.sseu; + unsigned int slice, subslice; + u32 mcr, mcr_mask; + + GEM_BUG_ON(GRAPHICS_VER(i915) != 9); + + /* + * WaProgramMgsrForCorrectSliceSpecificMmioReads:gen9,glk,kbl,cml + * Before any MMIO read into slice/subslice specific registers, MCR + * packet control register needs to be programmed to point to any + * enabled s/ss pair. Otherwise, incorrect values will be returned. + * This means each subsequent MMIO read will be forwarded to an + * specific s/ss combination, but this is OK since these registers + * are consistent across s/ss in almost all cases. In the rare + * occasions, such as INSTDONE, where this value is dependent + * on s/ss combo, the read should be done with read_subslice_reg. + */ + slice = ffs(sseu->slice_mask) - 1; + GEM_BUG_ON(slice >= ARRAY_SIZE(sseu->subslice_mask)); + subslice = ffs(intel_sseu_get_subslices(sseu, slice)); + GEM_BUG_ON(!subslice); + subslice--; + + /* + * We use GEN8_MCR..() macros to calculate the |mcr| value for + * Gen9 to address WaProgramMgsrForCorrectSliceSpecificMmioReads + */ + mcr = GEN8_MCR_SLICE(slice) | GEN8_MCR_SUBSLICE(subslice); + mcr_mask = GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK; + + drm_dbg(&i915->drm, "MCR slice:%d/subslice:%d = %x\n", slice, subslice, mcr); + + wa_write_clr_set(wal, GEN8_MCR_SELECTOR, mcr_mask, mcr); +} + +static void gen9_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { struct drm_i915_private *i915 = gt->i915; + /* WaProgramMgsrForCorrectSliceSpecificMmioReads:glk,kbl,cml,gen9 */ + gen9_wa_init_mcr(i915, wal); + /* WaDisableKillLogic:bxt,skl,kbl */ if (!IS_COFFEELAKE(i915) && !IS_COMETLAKE(i915)) wa_write_or(wal, @@ -909,7 +1006,7 @@ skl_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); /* WaInPlaceDecompressionHang:skl */ - if (IS_SKL_GT_STEP(gt->i915, STEP_A0, STEP_H0)) + if (IS_SKL_GRAPHICS_STEP(gt->i915, STEP_A0, STEP_H0)) wa_write_or(wal, GEN9_GAMT_ECO_REG_RW_IA, GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); @@ -921,7 +1018,7 @@ kbl_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) gen9_gt_workarounds_init(gt, wal); /* WaDisableDynamicCreditSharing:kbl */ - if (IS_KBL_GT_STEP(gt->i915, 0, STEP_C0)) + if (IS_KBL_GRAPHICS_STEP(gt->i915, 0, STEP_C0)) wa_write_or(wal, GAMT_CHKN_BIT_REG, GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING); @@ -1138,7 +1235,7 @@ icl_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) /* Wa_1607087056:icl,ehl,jsl */ if (IS_ICELAKE(i915) || - IS_JSL_EHL_GT_STEP(i915, STEP_A0, STEP_B0)) + IS_JSL_EHL_GRAPHICS_STEP(i915, STEP_A0, STEP_B0)) wa_write_or(wal, SLICE_UNIT_LEVEL_CLKGATE, L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS); @@ -1192,19 +1289,19 @@ tgl_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) gen12_gt_workarounds_init(gt, wal); /* Wa_1409420604:tgl */ - if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_B0)) + if (IS_TGL_UY_GRAPHICS_STEP(i915, STEP_A0, STEP_B0)) wa_write_or(wal, SUBSLICE_UNIT_LEVEL_CLKGATE2, CPSSUNIT_CLKGATE_DIS); /* Wa_1607087056:tgl also know as BUG:1409180338 */ - if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_B0)) + if (IS_TGL_UY_GRAPHICS_STEP(i915, STEP_A0, STEP_B0)) wa_write_or(wal, SLICE_UNIT_LEVEL_CLKGATE, L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS); /* Wa_1408615072:tgl[a0] */ - if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_B0)) + if (IS_TGL_UY_GRAPHICS_STEP(i915, STEP_A0, STEP_B0)) wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE2, VSUNIT_CLKGATE_DIS_TGL); } @@ -1217,7 +1314,7 @@ dg1_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) gen12_gt_workarounds_init(gt, wal); /* Wa_1607087056:dg1 */ - if (IS_DG1_GT_STEP(i915, STEP_A0, STEP_B0)) + if (IS_DG1_GRAPHICS_STEP(i915, STEP_A0, STEP_B0)) wa_write_or(wal, SLICE_UNIT_LEVEL_CLKGATE, L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS); @@ -1238,7 +1335,179 @@ dg1_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) static void xehpsdv_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { + struct drm_i915_private *i915 = gt->i915; + + xehp_init_mcr(gt, wal); + + /* Wa_1409757795:xehpsdv */ + wa_write_or(wal, SCCGCTL94DC, CG3DDISURB); + + /* 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_16011155590:xehpsdv */ + if (IS_XEHPSDV_GRAPHICS_STEP(i915, STEP_A0, STEP_B0)) + wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE, + TSGUNIT_CLKGATE_DIS); + + /* Wa_14011780169:xehpsdv */ + if (IS_XEHPSDV_GRAPHICS_STEP(i915, STEP_B0, STEP_FOREVER)) { + wa_write_or(wal, UNSLCGCTL9440, GAMTLBOACS_CLKGATE_DIS | + GAMTLBVDBOX7_CLKGATE_DIS | + GAMTLBVDBOX6_CLKGATE_DIS | + GAMTLBVDBOX5_CLKGATE_DIS | + GAMTLBVDBOX4_CLKGATE_DIS | + GAMTLBVDBOX3_CLKGATE_DIS | + GAMTLBVDBOX2_CLKGATE_DIS | + GAMTLBVDBOX1_CLKGATE_DIS | + GAMTLBVDBOX0_CLKGATE_DIS | + GAMTLBKCR_CLKGATE_DIS | + GAMTLBGUC_CLKGATE_DIS | + GAMTLBBLT_CLKGATE_DIS); + wa_write_or(wal, UNSLCGCTL9444, GAMTLBGFXA0_CLKGATE_DIS | + GAMTLBGFXA1_CLKGATE_DIS | + GAMTLBCOMPA0_CLKGATE_DIS | + GAMTLBCOMPA1_CLKGATE_DIS | + GAMTLBCOMPB0_CLKGATE_DIS | + GAMTLBCOMPB1_CLKGATE_DIS | + GAMTLBCOMPC0_CLKGATE_DIS | + GAMTLBCOMPC1_CLKGATE_DIS | + GAMTLBCOMPD0_CLKGATE_DIS | + GAMTLBCOMPD1_CLKGATE_DIS | + GAMTLBMERT_CLKGATE_DIS | + GAMTLBVEBOX3_CLKGATE_DIS | + GAMTLBVEBOX2_CLKGATE_DIS | + GAMTLBVEBOX1_CLKGATE_DIS | + GAMTLBVEBOX0_CLKGATE_DIS); + } + + /* Wa_14012362059:xehpsdv */ + wa_write_or(wal, GEN12_MERT_MOD_CTRL, FORCE_MISS_FTLB); + + /* Wa_16012725990:xehpsdv */ + if (IS_XEHPSDV_GRAPHICS_STEP(i915, STEP_A1, STEP_FOREVER)) + wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE, VFUNIT_CLKGATE_DIS); + + /* Wa_14011060649:xehpsdv */ + wa_14011060649(gt, wal); + + /* Wa_14014368820:xehpsdv */ + wa_write_or(wal, GEN12_GAMCNTRL_CTRL, INVALIDATION_BROADCAST_MODE_DIS | + GLOBAL_INVALIDATION_MODE); +} + +static void +dg2_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) +{ + struct intel_engine_cs *engine; + int id; + xehp_init_mcr(gt, wal); + + /* Wa_14011060649:dg2 */ + wa_14011060649(gt, wal); + + /* + * Although there are per-engine instances of these registers, + * they technically exist outside the engine itself and are not + * impacted by engine resets. Furthermore, they're part of the + * GuC blacklist so trying to treat them as engine workarounds + * will result in GuC initialization failure and a wedged GPU. + */ + for_each_engine(engine, gt, id) { + if (engine->class != VIDEO_DECODE_CLASS) + continue; + + /* Wa_16010515920:dg2_g10 */ + if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_B0)) + wa_write_or(wal, VDBOX_CGCTL3F18(engine->mmio_base), + ALNUNIT_CLKGATE_DIS); + } + + if (IS_DG2_G10(gt->i915)) { + /* Wa_22010523718:dg2 */ + wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE, + CG3DDISCFEG_CLKGATE_DIS); + + /* Wa_14011006942:dg2 */ + wa_write_or(wal, SUBSLICE_UNIT_LEVEL_CLKGATE, + DSS_ROUTER_CLKGATE_DIS); + } + + if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_B0)) { + /* Wa_14010680813:dg2_g10 */ + wa_write_or(wal, GEN12_GAMSTLB_CTRL, CONTROL_BLOCK_CLKGATE_DIS | + EGRESS_BLOCK_CLKGATE_DIS | TAG_BLOCK_CLKGATE_DIS); + + /* Wa_14010948348:dg2_g10 */ + wa_write_or(wal, UNSLCGCTL9430, MSQDUNIT_CLKGATE_DIS); + + /* Wa_14011037102:dg2_g10 */ + wa_write_or(wal, UNSLCGCTL9444, LTCDD_CLKGATE_DIS); + + /* Wa_14011371254:dg2_g10 */ + wa_write_or(wal, SLICE_UNIT_LEVEL_CLKGATE, NODEDSS_CLKGATE_DIS); + + /* Wa_14011431319:dg2_g10 */ + wa_write_or(wal, UNSLCGCTL9440, GAMTLBOACS_CLKGATE_DIS | + GAMTLBVDBOX7_CLKGATE_DIS | + GAMTLBVDBOX6_CLKGATE_DIS | + GAMTLBVDBOX5_CLKGATE_DIS | + GAMTLBVDBOX4_CLKGATE_DIS | + GAMTLBVDBOX3_CLKGATE_DIS | + GAMTLBVDBOX2_CLKGATE_DIS | + GAMTLBVDBOX1_CLKGATE_DIS | + GAMTLBVDBOX0_CLKGATE_DIS | + GAMTLBKCR_CLKGATE_DIS | + GAMTLBGUC_CLKGATE_DIS | + GAMTLBBLT_CLKGATE_DIS); + wa_write_or(wal, UNSLCGCTL9444, GAMTLBGFXA0_CLKGATE_DIS | + GAMTLBGFXA1_CLKGATE_DIS | + GAMTLBCOMPA0_CLKGATE_DIS | + GAMTLBCOMPA1_CLKGATE_DIS | + GAMTLBCOMPB0_CLKGATE_DIS | + GAMTLBCOMPB1_CLKGATE_DIS | + GAMTLBCOMPC0_CLKGATE_DIS | + GAMTLBCOMPC1_CLKGATE_DIS | + GAMTLBCOMPD0_CLKGATE_DIS | + GAMTLBCOMPD1_CLKGATE_DIS | + GAMTLBMERT_CLKGATE_DIS | + GAMTLBVEBOX3_CLKGATE_DIS | + GAMTLBVEBOX2_CLKGATE_DIS | + GAMTLBVEBOX1_CLKGATE_DIS | + GAMTLBVEBOX0_CLKGATE_DIS); + + /* Wa_14010569222:dg2_g10 */ + wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE, + GAMEDIA_CLKGATE_DIS); + + /* Wa_14011028019:dg2_g10 */ + wa_write_or(wal, SSMCGCTL9530, RTFUNIT_CLKGATE_DIS); + } + + if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_B0) || + IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_B0)) { + /* Wa_14012362059:dg2 */ + wa_write_or(wal, GEN12_MERT_MOD_CTRL, FORCE_MISS_FTLB); + } + + /* Wa_1509235366:dg2 */ + wa_write_or(wal, GEN12_GAMCNTRL_CTRL, INVALIDATION_BROADCAST_MODE_DIS | + GLOBAL_INVALIDATION_MODE); + + /* Wa_14014830051:dg2 */ + wa_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, XEHP_L3SCQREG7, BLEND_FILL_CACHING_OPT_DIS); + wa_write_or(wal, GEN12_SQCM, EN_32B_ACCESS); } static void @@ -1246,7 +1515,9 @@ gt_init_workarounds(struct intel_gt *gt, struct i915_wa_list *wal) { struct drm_i915_private *i915 = gt->i915; - if (IS_XEHPSDV(i915)) + if (IS_DG2(i915)) + dg2_gt_workarounds_init(gt, wal); + else if (IS_XEHPSDV(i915)) xehpsdv_gt_workarounds_init(gt, wal); else if (IS_DG1(i915)) dg1_gt_workarounds_init(gt, wal); @@ -1520,7 +1791,7 @@ static void cfl_whitelist_build(struct intel_engine_cs *engine) RING_FORCE_TO_NONPRIV_RANGE_4); } -static void cml_whitelist_build(struct intel_engine_cs *engine) +static void allow_read_ctx_timestamp(struct intel_engine_cs *engine) { struct i915_wa_list *w = &engine->whitelist; @@ -1528,6 +1799,11 @@ static void cml_whitelist_build(struct intel_engine_cs *engine) whitelist_reg_ext(w, RING_CTX_TIMESTAMP(engine->mmio_base), RING_FORCE_TO_NONPRIV_ACCESS_RD); +} + +static void cml_whitelist_build(struct intel_engine_cs *engine) +{ + allow_read_ctx_timestamp(engine); cfl_whitelist_build(engine); } @@ -1536,6 +1812,8 @@ static void icl_whitelist_build(struct intel_engine_cs *engine) { struct i915_wa_list *w = &engine->whitelist; + allow_read_ctx_timestamp(engine); + switch (engine->class) { case RENDER_CLASS: /* WaAllowUMDToModifyHalfSliceChicken7:icl */ @@ -1571,15 +1849,9 @@ static void icl_whitelist_build(struct intel_engine_cs *engine) /* hucStatus2RegOffset */ whitelist_reg_ext(w, _MMIO(0x23B0 + engine->mmio_base), RING_FORCE_TO_NONPRIV_ACCESS_RD); - whitelist_reg_ext(w, - RING_CTX_TIMESTAMP(engine->mmio_base), - RING_FORCE_TO_NONPRIV_ACCESS_RD); break; default: - whitelist_reg_ext(w, - RING_CTX_TIMESTAMP(engine->mmio_base), - RING_FORCE_TO_NONPRIV_ACCESS_RD); break; } } @@ -1588,6 +1860,8 @@ static void tgl_whitelist_build(struct intel_engine_cs *engine) { struct i915_wa_list *w = &engine->whitelist; + allow_read_ctx_timestamp(engine); + switch (engine->class) { case RENDER_CLASS: /* @@ -1604,16 +1878,17 @@ static void tgl_whitelist_build(struct intel_engine_cs *engine) RING_FORCE_TO_NONPRIV_ACCESS_RD | RING_FORCE_TO_NONPRIV_RANGE_4); - /* Wa_1808121037:tgl */ + /* + * Wa_1808121037:tgl + * Wa_14012131227:dg1 + * Wa_1508744258:tgl,rkl,dg1,adl-s,adl-p + */ whitelist_reg(w, GEN7_COMMON_SLICE_CHICKEN1); /* Wa_1806527549:tgl */ whitelist_reg(w, HIZ_CHICKEN); break; default: - whitelist_reg_ext(w, - RING_CTX_TIMESTAMP(engine->mmio_base), - RING_FORCE_TO_NONPRIV_ACCESS_RD); break; } } @@ -1625,13 +1900,46 @@ static void dg1_whitelist_build(struct intel_engine_cs *engine) tgl_whitelist_build(engine); /* GEN:BUG:1409280441:dg1 */ - if (IS_DG1_GT_STEP(engine->i915, STEP_A0, STEP_B0) && + if (IS_DG1_GRAPHICS_STEP(engine->i915, STEP_A0, STEP_B0) && (engine->class == RENDER_CLASS || engine->class == COPY_ENGINE_CLASS)) whitelist_reg_ext(w, RING_ID(engine->mmio_base), RING_FORCE_TO_NONPRIV_ACCESS_RD); } +static void xehpsdv_whitelist_build(struct intel_engine_cs *engine) +{ + allow_read_ctx_timestamp(engine); +} + +static void dg2_whitelist_build(struct intel_engine_cs *engine) +{ + struct i915_wa_list *w = &engine->whitelist; + + allow_read_ctx_timestamp(engine); + + switch (engine->class) { + case RENDER_CLASS: + /* + * Wa_1507100340:dg2_g10 + * + * This covers 4 registers which are next to one another : + * - PS_INVOCATION_COUNT + * - PS_INVOCATION_COUNT_UDW + * - PS_DEPTH_COUNT + * - PS_DEPTH_COUNT_UDW + */ + if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0)) + whitelist_reg_ext(w, PS_INVOCATION_COUNT, + RING_FORCE_TO_NONPRIV_ACCESS_RD | + RING_FORCE_TO_NONPRIV_RANGE_4); + + break; + default: + break; + } +} + void intel_engine_init_whitelist(struct intel_engine_cs *engine) { struct drm_i915_private *i915 = engine->i915; @@ -1639,7 +1947,11 @@ void intel_engine_init_whitelist(struct intel_engine_cs *engine) wa_init_start(w, "whitelist", engine->name); - if (IS_DG1(i915)) + if (IS_DG2(i915)) + dg2_whitelist_build(engine); + else if (IS_XEHPSDV(i915)) + xehpsdv_whitelist_build(engine); + else if (IS_DG1(i915)) dg1_whitelist_build(engine); else if (GRAPHICS_VER(i915) == 12) tgl_whitelist_build(engine); @@ -1713,13 +2025,119 @@ engine_fake_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) CMD_CCTL_MOCS_OVERRIDE(mocs, mocs)); } } + +static bool needs_wa_1308578152(struct intel_engine_cs *engine) +{ + u64 dss_mask = intel_sseu_get_subslices(&engine->gt->info.sseu, 0); + + return (dss_mask & GENMASK(GEN_DSS_PER_GSLICE - 1, 0)) == 0; +} + static void rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) { struct drm_i915_private *i915 = engine->i915; - if (IS_DG1_GT_STEP(i915, STEP_A0, STEP_B0) || - IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_B0)) { + if (IS_DG2_GRAPHICS_STEP(engine->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); + } + + if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0) || + IS_DG2_GRAPHICS_STEP(engine->i915, G11, STEP_A0, STEP_B0)) { + /* Wa_14012419201:dg2 */ + wa_masked_en(wal, GEN9_ROW_CHICKEN4, + GEN12_DISABLE_HDR_PAST_PAYLOAD_HOLD_FIX); + } + + if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_B0, STEP_C0) || + IS_DG2_G11(engine->i915)) { + /* + * 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_22013059131:dg2 */ + wa_write_or(wal, LSC_CHICKEN_BIT_0, + FORCE_1_SUB_MESSAGE_PER_FRAGMENT); + } + + /* Wa_1308578152:dg2_g10 when first gslice is fused off */ + if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_B0, STEP_C0) && + needs_wa_1308578152(engine)) { + wa_masked_dis(wal, GEN12_CS_DEBUG_MODE1_CCCSUNIT_BE_COMMON, + GEN12_REPLAY_MODE_GRANULARITY); + } + + if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_B0, STEP_FOREVER) || + IS_DG2_G11(engine->i915)) { + /* Wa_22013037850:dg2 */ + wa_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_22010960976:dg2 + * Wa_14013347512:dg2 + */ + wa_masked_dis(wal, GEN12_HDC_CHICKEN0, + LSC_L1_FLUSH_CTL_3D_DATAPORT_FLUSH_EVENTS_MASK); + } + + if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0)) { + /* + * Wa_1608949956:dg2_g10 + * Wa_14010198302:dg2_g10 + */ + wa_masked_en(wal, GEN8_ROW_CHICKEN, + MDQ_ARBITRATION_MODE | UGM_BACKUP_MODE); + + /* + * Wa_14010918519:dg2_g10 + * + * 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); + } + + if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0)) { + /* Wa_22010430635:dg2 */ + wa_masked_en(wal, + GEN9_ROW_CHICKEN4, + GEN12_DISABLE_GRF_CLEAR); + + /* Wa_14010648519:dg2 */ + wa_write_or(wal, XEHP_L3NODEARBCFG, XEHP_LNESPARE); + } + + if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_C0) || + IS_DG2_G11(engine->i915)) { + /* Wa_22012654132:dg2 */ + wa_add(wal, GEN10_CACHE_MODE_SS, 0, + _MASKED_BIT_ENABLE(ENABLE_PREFETCH_INTO_IC), + 0 /* write-only, so skip validation */, + true); + } + + /* Wa_14013202645:dg2 */ + if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_B0, STEP_C0) || + IS_DG2_GRAPHICS_STEP(engine->i915, G11, STEP_A0, STEP_B0)) + wa_write_or(wal, RT_CTRL, DIS_NULL_QUERY); + + if (IS_DG1_GRAPHICS_STEP(i915, STEP_A0, STEP_B0) || + IS_TGL_UY_GRAPHICS_STEP(i915, STEP_A0, STEP_B0)) { /* * Wa_1607138336:tgl[a0],dg1[a0] * Wa_1607063988:tgl[a0],dg1[a0] @@ -1729,7 +2147,7 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) GEN12_DISABLE_POSH_BUSY_FF_DOP_CG); } - if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_B0)) { + if (IS_TGL_UY_GRAPHICS_STEP(i915, STEP_A0, STEP_B0)) { /* * Wa_1606679103:tgl * (see also Wa_1606682166:icl) @@ -1764,7 +2182,7 @@ 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_GT_STEP(i915, STEP_A0, STEP_B0) || + 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, @@ -1777,8 +2195,7 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) wa_masked_en(wal, GEN9_ROW_CHICKEN4, GEN12_DISABLE_TDL_PUSH); } - - if (IS_DG1_GT_STEP(i915, STEP_A0, STEP_B0) || + if (IS_DG1_GRAPHICS_STEP(i915, STEP_A0, STEP_B0) || IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) { /* * Wa_1607030317:tgl @@ -2131,7 +2548,7 @@ xcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) struct drm_i915_private *i915 = engine->i915; /* WaKBLVECSSemaphoreWaitPoll:kbl */ - if (IS_KBL_GT_STEP(i915, STEP_A0, STEP_F0)) { + if (IS_KBL_GRAPHICS_STEP(i915, STEP_A0, STEP_F0)) { wa_write(wal, RING_SEMA_WAIT_POLL(engine->mmio_base), 1); diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c index 8b89215afe46..c0637bf799a3 100644 --- a/drivers/gpu/drm/i915/gt/mock_engine.c +++ b/drivers/gpu/drm/i915/gt/mock_engine.c @@ -17,7 +17,7 @@ static int mock_timeline_pin(struct intel_timeline *tl) { int err; - if (WARN_ON(!i915_gem_object_trylock(tl->hwsp_ggtt->obj))) + if (WARN_ON(!i915_gem_object_trylock(tl->hwsp_ggtt->obj, NULL))) return -EBUSY; err = intel_timeline_pin_map(tl); @@ -35,9 +35,31 @@ static void mock_timeline_unpin(struct intel_timeline *tl) atomic_dec(&tl->pin_count); } +static struct i915_vma *create_ring_vma(struct i915_ggtt *ggtt, int size) +{ + struct i915_address_space *vm = &ggtt->vm; + struct drm_i915_private *i915 = vm->i915; + struct drm_i915_gem_object *obj; + struct i915_vma *vma; + + obj = i915_gem_object_create_internal(i915, size); + if (IS_ERR(obj)) + return ERR_CAST(obj); + + vma = i915_vma_instance(obj, vm, NULL); + if (IS_ERR(vma)) + goto err; + + return vma; + +err: + i915_gem_object_put(obj); + return vma; +} + static struct intel_ring *mock_ring(struct intel_engine_cs *engine) { - const unsigned long sz = PAGE_SIZE / 2; + const unsigned long sz = PAGE_SIZE; struct intel_ring *ring; ring = kzalloc(sizeof(*ring) + sz, GFP_KERNEL); @@ -50,15 +72,11 @@ static struct intel_ring *mock_ring(struct intel_engine_cs *engine) ring->vaddr = (void *)(ring + 1); atomic_set(&ring->pin_count, 1); - ring->vma = i915_vma_alloc(); - if (!ring->vma) { + ring->vma = create_ring_vma(engine->gt->ggtt, PAGE_SIZE); + if (IS_ERR(ring->vma)) { kfree(ring); return NULL; } - i915_active_init(&ring->vma->active, NULL, NULL, 0); - __set_bit(I915_VMA_GGTT_BIT, __i915_vma_flags(ring->vma)); - __set_bit(DRM_MM_NODE_ALLOCATED_BIT, &ring->vma->node.flags); - ring->vma->node.size = sz; intel_ring_update_space(ring); @@ -67,8 +85,7 @@ static struct intel_ring *mock_ring(struct intel_engine_cs *engine) static void mock_ring_free(struct intel_ring *ring) { - i915_active_fini(&ring->vma->active); - i915_vma_free(ring->vma); + i915_vma_put(ring->vma); kfree(ring); } @@ -125,6 +142,7 @@ static void mock_context_unpin(struct intel_context *ce) static void mock_context_post_unpin(struct intel_context *ce) { + i915_vma_unpin(ce->ring->vma); } static void mock_context_destroy(struct kref *ref) @@ -169,7 +187,7 @@ static int mock_context_alloc(struct intel_context *ce) static int mock_context_pre_pin(struct intel_context *ce, struct i915_gem_ww_ctx *ww, void **unused) { - return 0; + return i915_vma_pin_ww(ce->ring->vma, ww, 0, 0, PIN_GLOBAL | PIN_HIGH); } static int mock_context_pin(struct intel_context *ce, void *unused) @@ -327,7 +345,7 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915, struct mock_engine *engine; GEM_BUG_ON(id >= I915_NUM_ENGINES); - GEM_BUG_ON(!i915->gt.uncore); + GEM_BUG_ON(!to_gt(i915)->uncore); engine = kzalloc(sizeof(*engine) + PAGE_SIZE, GFP_KERNEL); if (!engine) @@ -335,8 +353,8 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915, /* minimal engine setup for requests */ engine->base.i915 = i915; - engine->base.gt = &i915->gt; - engine->base.uncore = i915->gt.uncore; + engine->base.gt = to_gt(i915); + engine->base.uncore = to_gt(i915)->uncore; snprintf(engine->base.name, sizeof(engine->base.name), "%s", name); engine->base.id = id; engine->base.mask = BIT(id); @@ -359,8 +377,8 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915, engine->base.release = mock_engine_release; - i915->gt.engine[id] = &engine->base; - i915->gt.engine_class[0][id] = &engine->base; + to_gt(i915)->engine[id] = &engine->base; + to_gt(i915)->engine_class[0][id] = &engine->base; /* fake hw queue */ spin_lock_init(&engine->hw_lock); diff --git a/drivers/gpu/drm/i915/gt/selftest_context.c b/drivers/gpu/drm/i915/gt/selftest_context.c index fa7b99a671dd..76fbae358072 100644 --- a/drivers/gpu/drm/i915/gt/selftest_context.c +++ b/drivers/gpu/drm/i915/gt/selftest_context.c @@ -442,7 +442,7 @@ int intel_context_live_selftests(struct drm_i915_private *i915) SUBTEST(live_active_context), SUBTEST(live_remote_context), }; - struct intel_gt *gt = &i915->gt; + struct intel_gt *gt = to_gt(i915); if (intel_gt_is_wedged(gt)) return 0; diff --git a/drivers/gpu/drm/i915/gt/selftest_engine.c b/drivers/gpu/drm/i915/gt/selftest_engine.c index 262764f6d90a..57fea9ea1705 100644 --- a/drivers/gpu/drm/i915/gt/selftest_engine.c +++ b/drivers/gpu/drm/i915/gt/selftest_engine.c @@ -12,7 +12,7 @@ int intel_engine_live_selftests(struct drm_i915_private *i915) live_engine_pm_selftests, NULL, }; - struct intel_gt *gt = &i915->gt; + struct intel_gt *gt = to_gt(i915); typeof(*tests) *fn; for (fn = tests; *fn; fn++) { diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_cs.c b/drivers/gpu/drm/i915/gt/selftest_engine_cs.c index 64abf5feabfa..1b75f478d1b8 100644 --- a/drivers/gpu/drm/i915/gt/selftest_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/selftest_engine_cs.c @@ -361,10 +361,10 @@ int intel_engine_cs_perf_selftests(struct drm_i915_private *i915) SUBTEST(perf_mi_noop), }; - if (intel_gt_is_wedged(&i915->gt)) + if (intel_gt_is_wedged(to_gt(i915))) return 0; - return intel_gt_live_subtests(tests, &i915->gt); + return intel_gt_live_subtests(tests, to_gt(i915)); } static int intel_mmio_bases_check(void *arg) diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c index 6e6e4d747cca..273d440a53e3 100644 --- a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c +++ b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c @@ -378,13 +378,13 @@ int intel_heartbeat_live_selftests(struct drm_i915_private *i915) int saved_hangcheck; int err; - if (intel_gt_is_wedged(&i915->gt)) + if (intel_gt_is_wedged(to_gt(i915))) return 0; saved_hangcheck = i915->params.enable_hangcheck; i915->params.enable_hangcheck = INT_MAX; - err = intel_gt_live_subtests(tests, &i915->gt); + err = intel_gt_live_subtests(tests, to_gt(i915)); i915->params.enable_hangcheck = saved_hangcheck; return err; diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_pm.c b/drivers/gpu/drm/i915/gt/selftest_engine_pm.c index 75569666105d..8af261831470 100644 --- a/drivers/gpu/drm/i915/gt/selftest_engine_pm.c +++ b/drivers/gpu/drm/i915/gt/selftest_engine_pm.c @@ -214,6 +214,31 @@ static int live_engine_timestamps(void *arg) return 0; } +static int __spin_until_busier(struct intel_engine_cs *engine, ktime_t busyness) +{ + ktime_t start, unused, dt; + + if (!intel_engine_uses_guc(engine)) + return 0; + + /* + * In GuC mode of submission, the busyness stats may get updated after + * the batch starts running. Poll for a change in busyness and timeout + * after 500 us. + */ + start = ktime_get(); + while (intel_engine_get_busy_time(engine, &unused) == busyness) { + dt = ktime_get() - start; + if (dt > 10000000) { + pr_err("active wait timed out %lld\n", dt); + ENGINE_TRACE(engine, "active wait time out %lld\n", dt); + return -ETIME; + } + } + + return 0; +} + static int live_engine_busy_stats(void *arg) { struct intel_gt *gt = arg; @@ -232,6 +257,7 @@ static int live_engine_busy_stats(void *arg) GEM_BUG_ON(intel_gt_pm_is_awake(gt)); for_each_engine(engine, gt, id) { struct i915_request *rq; + ktime_t busyness, dummy; ktime_t de, dt; ktime_t t[2]; @@ -274,16 +300,23 @@ static int live_engine_busy_stats(void *arg) } i915_request_add(rq); + busyness = intel_engine_get_busy_time(engine, &dummy); if (!igt_wait_for_spinner(&spin, rq)) { intel_gt_set_wedged(engine->gt); err = -ETIME; goto end; } + err = __spin_until_busier(engine, busyness); + if (err) { + GEM_TRACE_DUMP(); + goto end; + } + ENGINE_TRACE(engine, "measuring busy time\n"); preempt_disable(); de = intel_engine_get_busy_time(engine, &t[0]); - udelay(100); + mdelay(10); 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 b367ecfa42de..e10da897e07a 100644 --- a/drivers/gpu/drm/i915/gt/selftest_execlists.c +++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c @@ -4502,11 +4502,11 @@ int intel_execlists_live_selftests(struct drm_i915_private *i915) SUBTEST(live_virtual_reset), }; - if (i915->gt.submission_method != INTEL_SUBMISSION_ELSP) + if (to_gt(i915)->submission_method != INTEL_SUBMISSION_ELSP) return 0; - if (intel_gt_is_wedged(&i915->gt)) + if (intel_gt_is_wedged(to_gt(i915))) return 0; - return intel_gt_live_subtests(tests, &i915->gt); + return intel_gt_live_subtests(tests, to_gt(i915)); } diff --git a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c index b9441217ca3d..8bf62a5826cc 100644 --- a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c @@ -43,7 +43,7 @@ static void measure_clocks(struct intel_engine_cs *engine, int i; for (i = 0; i < 5; i++) { - preempt_disable(); + local_irq_disable(); cycles[i] = -ENGINE_READ_FW(engine, RING_TIMESTAMP); dt[i] = ktime_get(); @@ -51,7 +51,7 @@ static void measure_clocks(struct intel_engine_cs *engine, dt[i] = ktime_sub(ktime_get(), dt[i]); cycles[i] += ENGINE_READ_FW(engine, RING_TIMESTAMP); - preempt_enable(); + local_irq_enable(); } /* Use the median of both cycle/dt; close enough */ @@ -193,10 +193,10 @@ int intel_gt_pm_live_selftests(struct drm_i915_private *i915) SUBTEST(live_gt_resume), }; - if (intel_gt_is_wedged(&i915->gt)) + if (intel_gt_is_wedged(to_gt(i915))) return 0; - return intel_gt_live_subtests(tests, &i915->gt); + return intel_gt_live_subtests(tests, to_gt(i915)); } int intel_gt_pm_late_selftests(struct drm_i915_private *i915) @@ -210,8 +210,8 @@ int intel_gt_pm_late_selftests(struct drm_i915_private *i915) SUBTEST(live_rc6_ctx_wa), }; - if (intel_gt_is_wedged(&i915->gt)) + if (intel_gt_is_wedged(to_gt(i915))) return 0; - return intel_gt_live_subtests(tests, &i915->gt); + return intel_gt_live_subtests(tests, to_gt(i915)); } diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c index 7e2d99dd012d..15d63435ec4d 100644 --- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c +++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c @@ -471,7 +471,8 @@ static int igt_reset_nop_engine(void *arg) count = 0; st_engine_heartbeat_disable(engine); - set_bit(I915_RESET_ENGINE + id, >->reset.flags); + GEM_BUG_ON(test_and_set_bit(I915_RESET_ENGINE + id, + >->reset.flags)); do { int i; @@ -528,7 +529,7 @@ static int igt_reset_nop_engine(void *arg) break; } } while (time_before(jiffies, end_time)); - clear_bit(I915_RESET_ENGINE + id, >->reset.flags); + clear_and_wake_up_bit(I915_RESET_ENGINE + id, >->reset.flags); st_engine_heartbeat_enable(engine); pr_info("%s(%s): %d resets\n", __func__, engine->name, count); @@ -582,7 +583,8 @@ static int igt_reset_fail_engine(void *arg) } st_engine_heartbeat_disable(engine); - set_bit(I915_RESET_ENGINE + id, >->reset.flags); + GEM_BUG_ON(test_and_set_bit(I915_RESET_ENGINE + id, + >->reset.flags)); force_reset_timeout(engine); err = intel_engine_reset(engine, NULL); @@ -679,7 +681,7 @@ static int igt_reset_fail_engine(void *arg) out: pr_info("%s(%s): %d resets\n", __func__, engine->name, count); skip: - clear_bit(I915_RESET_ENGINE + id, >->reset.flags); + clear_and_wake_up_bit(I915_RESET_ENGINE + id, >->reset.flags); st_engine_heartbeat_enable(engine); intel_context_put(ce); @@ -734,7 +736,8 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active) reset_engine_count = i915_reset_engine_count(global, engine); st_engine_heartbeat_disable(engine); - set_bit(I915_RESET_ENGINE + id, >->reset.flags); + GEM_BUG_ON(test_and_set_bit(I915_RESET_ENGINE + id, + >->reset.flags)); count = 0; do { struct i915_request *rq = NULL; @@ -824,7 +827,7 @@ restore: if (err) break; } while (time_before(jiffies, end_time)); - clear_bit(I915_RESET_ENGINE + id, >->reset.flags); + clear_and_wake_up_bit(I915_RESET_ENGINE + id, >->reset.flags); st_engine_heartbeat_enable(engine); pr_info("%s: Completed %lu %s resets\n", engine->name, count, active ? "active" : "idle"); @@ -1042,7 +1045,8 @@ static int __igt_reset_engines(struct intel_gt *gt, yield(); /* start all threads before we begin */ st_engine_heartbeat_disable_no_pm(engine); - set_bit(I915_RESET_ENGINE + id, >->reset.flags); + GEM_BUG_ON(test_and_set_bit(I915_RESET_ENGINE + id, + >->reset.flags)); do { struct i915_request *rq = NULL; struct intel_selftest_saved_policy saved; @@ -1165,7 +1169,7 @@ restore: if (err) break; } while (time_before(jiffies, end_time)); - clear_bit(I915_RESET_ENGINE + id, >->reset.flags); + clear_and_wake_up_bit(I915_RESET_ENGINE + id, >->reset.flags); st_engine_heartbeat_enable_no_pm(engine); pr_info("i915_reset_engine(%s:%s): %lu resets\n", @@ -2014,7 +2018,7 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915) SUBTEST(igt_reset_evict_fence), SUBTEST(igt_handle_error), }; - struct intel_gt *gt = &i915->gt; + struct intel_gt *gt = to_gt(i915); intel_wakeref_t wakeref; int err; diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c index b0977a3b699b..618c905daa19 100644 --- a/drivers/gpu/drm/i915/gt/selftest_lrc.c +++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c @@ -1847,5 +1847,5 @@ int intel_lrc_live_selftests(struct drm_i915_private *i915) if (!HAS_LOGICAL_RING_CONTEXTS(i915)) return 0; - return intel_gt_live_subtests(tests, &i915->gt); + return intel_gt_live_subtests(tests, to_gt(i915)); } diff --git a/drivers/gpu/drm/i915/gt/selftest_migrate.c b/drivers/gpu/drm/i915/gt/selftest_migrate.c index 12ef2837c89b..fa4293d2944f 100644 --- a/drivers/gpu/drm/i915/gt/selftest_migrate.c +++ b/drivers/gpu/drm/i915/gt/selftest_migrate.c @@ -49,6 +49,7 @@ static int copy(struct intel_migrate *migrate, if (IS_ERR(src)) return 0; + sz = src->base.size; dst = i915_gem_object_create_internal(i915, sz); if (IS_ERR(dst)) goto err_free_src; @@ -441,7 +442,7 @@ int intel_migrate_live_selftests(struct drm_i915_private *i915) SUBTEST(thread_global_copy), SUBTEST(thread_global_clear), }; - struct intel_gt *gt = &i915->gt; + struct intel_gt *gt = to_gt(i915); if (!gt->migrate.context) return 0; @@ -464,7 +465,7 @@ create_init_lmem_internal(struct intel_gt *gt, size_t sz, bool try_lmem) return obj; } - i915_gem_object_trylock(obj); + i915_gem_object_trylock(obj, NULL); err = i915_gem_object_pin_pages(obj); if (err) { i915_gem_object_unlock(obj); @@ -657,7 +658,7 @@ int intel_migrate_perf_selftests(struct drm_i915_private *i915) SUBTEST(perf_clear_blt), SUBTEST(perf_copy_blt), }; - struct intel_gt *gt = &i915->gt; + struct intel_gt *gt = to_gt(i915); if (intel_gt_is_wedged(gt)) return 0; diff --git a/drivers/gpu/drm/i915/gt/selftest_mocs.c b/drivers/gpu/drm/i915/gt/selftest_mocs.c index 13d25bf2a94a..c1d861333c44 100644 --- a/drivers/gpu/drm/i915/gt/selftest_mocs.c +++ b/drivers/gpu/drm/i915/gt/selftest_mocs.c @@ -451,5 +451,5 @@ int intel_mocs_live_selftests(struct drm_i915_private *i915) if (!get_mocs_settings(i915, &table)) return 0; - return intel_gt_live_subtests(tests, &i915->gt); + return intel_gt_live_subtests(tests, to_gt(i915)); } diff --git a/drivers/gpu/drm/i915/gt/selftest_reset.c b/drivers/gpu/drm/i915/gt/selftest_reset.c index 7a50c9f4071b..8a873f6bda7f 100644 --- a/drivers/gpu/drm/i915/gt/selftest_reset.c +++ b/drivers/gpu/drm/i915/gt/selftest_reset.c @@ -376,7 +376,7 @@ int intel_reset_live_selftests(struct drm_i915_private *i915) SUBTEST(igt_atomic_reset), SUBTEST(igt_atomic_engine_reset), }; - struct intel_gt *gt = &i915->gt; + struct intel_gt *gt = to_gt(i915); if (!intel_has_gpu_reset(gt)) return 0; diff --git a/drivers/gpu/drm/i915/gt/selftest_ring_submission.c b/drivers/gpu/drm/i915/gt/selftest_ring_submission.c index 041954408d0f..70f9ac1ec2c7 100644 --- a/drivers/gpu/drm/i915/gt/selftest_ring_submission.c +++ b/drivers/gpu/drm/i915/gt/selftest_ring_submission.c @@ -291,8 +291,8 @@ int intel_ring_submission_live_selftests(struct drm_i915_private *i915) SUBTEST(live_ctx_switch_wa), }; - if (i915->gt.submission_method > INTEL_SUBMISSION_RING) + if (to_gt(i915)->submission_method > INTEL_SUBMISSION_RING) return 0; - return intel_gt_live_subtests(tests, &i915->gt); + return intel_gt_live_subtests(tests, to_gt(i915)); } diff --git a/drivers/gpu/drm/i915/gt/selftest_slpc.c b/drivers/gpu/drm/i915/gt/selftest_slpc.c index 9334bad131a2..b768cea5943d 100644 --- a/drivers/gpu/drm/i915/gt/selftest_slpc.c +++ b/drivers/gpu/drm/i915/gt/selftest_slpc.c @@ -39,7 +39,7 @@ static int slpc_set_max_freq(struct intel_guc_slpc *slpc, u32 freq) static int live_slpc_clamp_min(void *arg) { struct drm_i915_private *i915 = arg; - struct intel_gt *gt = &i915->gt; + struct intel_gt *gt = to_gt(i915); struct intel_guc_slpc *slpc = >->uc.guc.slpc; struct intel_rps *rps = >->rps; struct intel_engine_cs *engine; @@ -166,7 +166,7 @@ static int live_slpc_clamp_min(void *arg) static int live_slpc_clamp_max(void *arg) { struct drm_i915_private *i915 = arg; - struct intel_gt *gt = &i915->gt; + struct intel_gt *gt = to_gt(i915); struct intel_guc_slpc *slpc; struct intel_rps *rps; struct intel_engine_cs *engine; @@ -304,7 +304,7 @@ int intel_slpc_live_selftests(struct drm_i915_private *i915) SUBTEST(live_slpc_clamp_min), }; - if (intel_gt_is_wedged(&i915->gt)) + if (intel_gt_is_wedged(to_gt(i915))) return 0; return i915_live_subtests(tests, i915); diff --git a/drivers/gpu/drm/i915/gt/selftest_timeline.c b/drivers/gpu/drm/i915/gt/selftest_timeline.c index d0b6a3afcf44..e2eb686a9763 100644 --- a/drivers/gpu/drm/i915/gt/selftest_timeline.c +++ b/drivers/gpu/drm/i915/gt/selftest_timeline.c @@ -159,7 +159,7 @@ static int mock_hwsp_freelist(void *arg) INIT_RADIX_TREE(&state.cachelines, GFP_KERNEL); state.prng = I915_RND_STATE_INITIALIZER(i915_selftest.random_seed); - state.gt = &i915->gt; + state.gt = to_gt(i915); /* * Create a bunch of timelines and check that their HWSP do not overlap. @@ -1416,8 +1416,8 @@ int intel_timeline_live_selftests(struct drm_i915_private *i915) SUBTEST(live_hwsp_rollover_user), }; - if (intel_gt_is_wedged(&i915->gt)) + if (intel_gt_is_wedged(to_gt(i915))) return 0; - return intel_gt_live_subtests(tests, &i915->gt); + return intel_gt_live_subtests(tests, to_gt(i915)); } diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c index 962e91ba3be4..0287c2573c51 100644 --- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c +++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c @@ -1387,8 +1387,8 @@ int intel_workarounds_live_selftests(struct drm_i915_private *i915) SUBTEST(live_engine_reset_workarounds), }; - if (intel_gt_is_wedged(&i915->gt)) + if (intel_gt_is_wedged(to_gt(i915))) return 0; - return intel_gt_live_subtests(tests, &i915->gt); + return intel_gt_live_subtests(tests, to_gt(i915)); } 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 ba10bd374cee..fe5d7d261797 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 @@ -144,6 +144,7 @@ enum intel_guc_action { INTEL_GUC_ACTION_DEREGISTER_CONTEXT_DONE = 0x4600, INTEL_GUC_ACTION_REGISTER_CONTEXT_MULTI_LRC = 0x4601, INTEL_GUC_ACTION_RESET_CLIENT = 0x5507, + INTEL_GUC_ACTION_SET_ENG_UTIL_BUFF = 0x550A, INTEL_GUC_ACTION_LIMIT }; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h index 31cf9fb48c7e..f9240d4baa69 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h @@ -95,6 +95,11 @@ struct intel_guc { */ struct ida guc_ids; /** + * @num_guc_ids: Number of guc_ids, selftest feature to be able + * to reduce this number while testing. + */ + int num_guc_ids; + /** * @guc_ids_bitmap: used to allocate new guc_ids, multi-lrc */ unsigned long *guc_ids_bitmap; @@ -138,6 +143,8 @@ struct intel_guc { u32 ads_regset_size; /** @ads_golden_ctxt_size: size of the golden contexts in the ADS */ u32 ads_golden_ctxt_size; + /** @ads_engine_usage_size: size of engine usage in the ADS */ + u32 ads_engine_usage_size; /** @lrc_desc_pool: object allocated to hold the GuC LRC descriptor pool */ struct i915_vma *lrc_desc_pool; @@ -172,6 +179,41 @@ struct intel_guc { /** @send_mutex: used to serialize the intel_guc_send actions */ struct mutex send_mutex; + + /** + * @timestamp: GT timestamp object that stores a copy of the timestamp + * and adjusts it for overflow using a worker. + */ + struct { + /** + * @lock: Lock protecting the below fields and the engine stats. + */ + spinlock_t lock; + + /** + * @gt_stamp: 64 bit extended value of the GT timestamp. + */ + u64 gt_stamp; + + /** + * @ping_delay: Period for polling the GT timestamp for + * overflow. + */ + unsigned long ping_delay; + + /** + * @work: Periodic work to adjust GT timestamp, engine and + * context usage for overflows. + */ + struct delayed_work work; + } timestamp; + +#ifdef CONFIG_DRM_I915_SELFTEST + /** + * @number_guc_id_stolen: The number of guc_ids that have been stolen + */ + int number_guc_id_stolen; +#endif }; static inline struct intel_guc *log_to_guc(struct intel_guc_log *log) 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 621c893a009f..1a1edae67e4e 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c @@ -26,6 +26,8 @@ * | guc_policies | * +---------------------------------------+ * | guc_gt_system_info | + * +---------------------------------------+ + * | guc_engine_usage | * +---------------------------------------+ <== static * | guc_mmio_reg[countA] (engine 0.0) | * | guc_mmio_reg[countB] (engine 0.1) | @@ -47,6 +49,7 @@ struct __guc_ads_blob { struct guc_ads ads; struct guc_policies policies; struct guc_gt_system_info system_info; + struct guc_engine_usage engine_usage; /* From here on, location is dynamic! Refer to above diagram. */ struct guc_mmio_reg regset[0]; } __packed; @@ -628,3 +631,21 @@ void intel_guc_ads_reset(struct intel_guc *guc) guc_ads_private_data_reset(guc); } + +u32 intel_guc_engine_usage_offset(struct intel_guc *guc) +{ + struct __guc_ads_blob *blob = guc->ads_blob; + u32 base = intel_guc_ggtt_offset(guc, guc->ads_vma); + u32 offset = base + ptr_offset(blob, engine_usage); + + return offset; +} + +struct guc_engine_usage_record *intel_guc_engine_usage(struct intel_engine_cs *engine) +{ + struct intel_guc *guc = &engine->gt->uc.guc; + struct __guc_ads_blob *blob = guc->ads_blob; + u8 guc_class = engine_class_to_guc_class(engine->class); + + return &blob->engine_usage.engines[guc_class][ilog2(engine->logical_mask)]; +} diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.h index 3d85051d57e4..e74c110facff 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.h @@ -6,8 +6,11 @@ #ifndef _INTEL_GUC_ADS_H_ #define _INTEL_GUC_ADS_H_ +#include <linux/types.h> + struct intel_guc; struct drm_printer; +struct intel_engine_cs; int intel_guc_ads_create(struct intel_guc *guc); void intel_guc_ads_destroy(struct intel_guc *guc); @@ -15,5 +18,7 @@ void intel_guc_ads_init_late(struct intel_guc *guc); void intel_guc_ads_reset(struct intel_guc *guc); void intel_guc_ads_print_policy_info(struct intel_guc *guc, struct drm_printer *p); +struct guc_engine_usage_record *intel_guc_engine_usage(struct intel_engine_cs *engine); +u32 intel_guc_engine_usage_offset(struct intel_guc *guc); #endif diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c index a0cc34be7b56..aa6dd6415202 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c @@ -523,6 +523,15 @@ static inline bool ct_deadlocked(struct intel_guc_ct *ct) CT_ERROR(ct, "Communication stalled for %lld ms, desc status=%#x,%#x\n", ktime_ms_delta(ktime_get(), ct->stall_time), send->status, recv->status); + CT_ERROR(ct, "H2G Space: %u (Bytes)\n", + atomic_read(&ct->ctbs.send.space) * 4); + CT_ERROR(ct, "Head: %u (Dwords)\n", ct->ctbs.send.desc->head); + CT_ERROR(ct, "Tail: %u (Dwords)\n", ct->ctbs.send.desc->tail); + CT_ERROR(ct, "G2H Space: %u (Bytes)\n", + atomic_read(&ct->ctbs.recv.space) * 4); + CT_ERROR(ct, "Head: %u\n (Dwords)", ct->ctbs.recv.desc->head); + CT_ERROR(ct, "Tail: %u\n (Dwords)", ct->ctbs.recv.desc->tail); + ct->ctbs.send.broken = true; } @@ -582,12 +591,19 @@ static inline bool h2g_has_room(struct intel_guc_ct *ct, u32 len_dw) static int has_room_nb(struct intel_guc_ct *ct, u32 h2g_dw, u32 g2h_dw) { + bool h2g = h2g_has_room(ct, h2g_dw); + bool g2h = g2h_has_room(ct, g2h_dw); + lockdep_assert_held(&ct->ctbs.send.lock); - if (unlikely(!h2g_has_room(ct, h2g_dw) || !g2h_has_room(ct, g2h_dw))) { + if (unlikely(!h2g || !g2h)) { if (ct->stall_time == KTIME_MAX) ct->stall_time = ktime_get(); + /* Be paranoid and kick G2H tasklet to free credits */ + if (!g2h) + tasklet_hi_schedule(&ct->receive_tasklet); + if (unlikely(ct_deadlocked(ct))) return -EPIPE; else 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 196424be0998..31420ce1ce6b 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c @@ -40,9 +40,8 @@ static void guc_prepare_xfer(struct intel_uncore *uncore) } } -/* Copy RSA signature from the fw image to HW for verification */ -static int guc_xfer_rsa(struct intel_uc_fw *guc_fw, - struct intel_uncore *uncore) +static int guc_xfer_rsa_mmio(struct intel_uc_fw *guc_fw, + struct intel_uncore *uncore) { u32 rsa[UOS_RSA_SCRATCH_COUNT]; size_t copied; @@ -58,6 +57,27 @@ static int guc_xfer_rsa(struct intel_uc_fw *guc_fw, return 0; } +static int guc_xfer_rsa_vma(struct intel_uc_fw *guc_fw, + struct intel_uncore *uncore) +{ + struct intel_guc *guc = container_of(guc_fw, struct intel_guc, fw); + + intel_uncore_write(uncore, UOS_RSA_SCRATCH(0), + intel_guc_ggtt_offset(guc, guc_fw->rsa_data)); + + return 0; +} + +/* Copy RSA signature from the fw image to HW for verification */ +static int guc_xfer_rsa(struct intel_uc_fw *guc_fw, + struct intel_uncore *uncore) +{ + if (guc_fw->rsa_data) + return guc_xfer_rsa_vma(guc_fw, uncore); + else + return guc_xfer_rsa_mmio(guc_fw, uncore); +} + /* * Read the GuC status register (GUC_STATUS) and store it in the * specified location; then return a boolean indicating whether @@ -142,7 +162,10 @@ int intel_guc_fw_upload(struct intel_guc *guc) /* * Note that GuC needs the CSS header plus uKernel code to be copied * by the DMA engine in one operation, whereas the RSA signature is - * loaded via MMIO. + * loaded separately, either by copying it to the UOS_RSA_SCRATCH + * register (if key size <= 256) or through a ggtt-pinned vma (if key + * size > 256). The RSA size and therefore the way we provide it to the + * HW is fixed for each platform and hard-coded in the bootrom. */ ret = guc_xfer_rsa(&guc->fw, uncore); if (ret) @@ -164,6 +187,6 @@ int intel_guc_fw_upload(struct intel_guc *guc) return 0; out: - intel_uc_fw_change_status(&guc->fw, INTEL_UC_FIRMWARE_FAIL); + intel_uc_fw_change_status(&guc->fw, INTEL_UC_FIRMWARE_LOAD_FAIL); return ret; } 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 722933e26347..7072e30e99f4 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h @@ -294,6 +294,19 @@ struct guc_ads { u32 reserved[15]; } __packed; +/* Engine usage stats */ +struct guc_engine_usage_record { + u32 current_context_index; + u32 last_switch_in_stamp; + u32 reserved0; + u32 total_runtime; + u32 reserved1[4]; +} __packed; + +struct guc_engine_usage { + struct guc_engine_usage_record engines[GUC_MAX_ENGINE_CLASSES][GUC_MAX_INSTANCES_PER_CLASS]; +} __packed; + /* GuC logging structures */ enum guc_log_buffer_type { diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h index ac1ee1d5ce10..fe6ab7550a14 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h @@ -15,9 +15,12 @@ struct intel_guc; -#ifdef CONFIG_DRM_I915_DEBUG_GUC +#if defined(CONFIG_DRM_I915_DEBUG_GUC) #define CRASH_BUFFER_SIZE SZ_2M #define DEBUG_BUFFER_SIZE SZ_16M +#elif defined(CONFIG_DRM_I915_DEBUG_GEM) +#define CRASH_BUFFER_SIZE SZ_1M +#define DEBUG_BUFFER_SIZE SZ_2M #else #define CRASH_BUFFER_SIZE SZ_8K #define DEBUG_BUFFER_SIZE SZ_64K diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log_debugfs.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_log_debugfs.c index 46026c2c1722..ddfbe334689f 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log_debugfs.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log_debugfs.c @@ -10,28 +10,80 @@ #include "intel_guc.h" #include "intel_guc_log.h" #include "intel_guc_log_debugfs.h" +#include "intel_uc.h" + +static u32 obj_to_guc_log_dump_size(struct drm_i915_gem_object *obj) +{ + u32 size; + + if (!obj) + return PAGE_SIZE; + + /* "0x%08x 0x%08x 0x%08x 0x%08x\n" => 16 bytes -> 44 chars => x2.75 */ + size = ((obj->base.size * 11) + 3) / 4; + + /* Add padding for final blank line, any extra header info, etc. */ + size = PAGE_ALIGN(size + PAGE_SIZE); + + return size; +} + +static u32 guc_log_dump_size(struct intel_guc_log *log) +{ + struct intel_guc *guc = log_to_guc(log); + + if (!intel_guc_is_supported(guc)) + return PAGE_SIZE; + + if (!log->vma) + return PAGE_SIZE; + + return obj_to_guc_log_dump_size(log->vma->obj); +} static int guc_log_dump_show(struct seq_file *m, void *data) { struct drm_printer p = drm_seq_file_printer(m); + int ret; - return intel_guc_log_dump(m->private, &p, false); + ret = intel_guc_log_dump(m->private, &p, false); + + if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM) && seq_has_overflowed(m)) + pr_warn_once("preallocated size:%zx for %s exceeded\n", + m->size, __func__); + + return ret; +} +DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE_WITH_SIZE(guc_log_dump, guc_log_dump_size); + +static u32 guc_load_err_dump_size(struct intel_guc_log *log) +{ + struct intel_guc *guc = log_to_guc(log); + struct intel_uc *uc = container_of(guc, struct intel_uc, guc); + + if (!intel_guc_is_supported(guc)) + return PAGE_SIZE; + + return obj_to_guc_log_dump_size(uc->load_err_log); } -DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(guc_log_dump); static int guc_load_err_log_dump_show(struct seq_file *m, void *data) { struct drm_printer p = drm_seq_file_printer(m); + if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM) && seq_has_overflowed(m)) + pr_warn_once("preallocated size:%zx for %s exceeded\n", + m->size, __func__); + return intel_guc_log_dump(m->private, &p, true); } -DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(guc_load_err_log_dump); +DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE_WITH_SIZE(guc_load_err_log_dump, guc_load_err_dump_size); static int guc_log_level_get(void *data, u64 *val) { struct intel_guc_log *log = data; - if (!intel_guc_is_used(log_to_guc(log))) + if (!log->vma) return -ENODEV; *val = intel_guc_log_get_level(log); @@ -43,7 +95,7 @@ static int guc_log_level_set(void *data, u64 val) { struct intel_guc_log *log = data; - if (!intel_guc_is_used(log_to_guc(log))) + if (!log->vma) return -ENODEV; return intel_guc_log_set_level(log, val); 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 65a3e7fdb2b2..13b27b8ff74e 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c @@ -79,29 +79,6 @@ static void slpc_mem_set_disabled(struct slpc_shared_data *data, slpc_mem_set_param(data, enable_id, 0); } -int intel_guc_slpc_init(struct intel_guc_slpc *slpc) -{ - struct intel_guc *guc = slpc_to_guc(slpc); - struct drm_i915_private *i915 = slpc_to_i915(slpc); - u32 size = PAGE_ALIGN(sizeof(struct slpc_shared_data)); - int err; - - GEM_BUG_ON(slpc->vma); - - err = intel_guc_allocate_and_map_vma(guc, size, &slpc->vma, (void **)&slpc->vaddr); - if (unlikely(err)) { - drm_err(&i915->drm, - "Failed to allocate SLPC struct (err=%pe)\n", - ERR_PTR(err)); - return err; - } - - slpc->max_freq_softlimit = 0; - slpc->min_freq_softlimit = 0; - - return err; -} - static u32 slpc_get_state(struct intel_guc_slpc *slpc) { struct slpc_shared_data *data; @@ -203,6 +180,86 @@ static int slpc_unset_param(struct intel_guc_slpc *slpc, 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); + struct intel_guc *guc = slpc_to_guc(slpc); + intel_wakeref_t wakeref; + int ret = 0; + + lockdep_assert_held(&slpc->lock); + + if (!intel_guc_is_ready(guc)) + return -ENODEV; + + /* + * This function is a little different as compared to + * intel_guc_slpc_set_min_freq(). Softlimit will not be updated + * here since this is used to temporarily change min freq, + * for example, during a waitboost. Caller is responsible for + * checking bounds. + */ + + with_intel_runtime_pm(&i915->runtime_pm, wakeref) { + ret = slpc_set_param(slpc, + SLPC_PARAM_GLOBAL_MIN_GT_UNSLICE_FREQ_MHZ, + freq); + if (ret) + drm_err(&i915->drm, "Unable to force min freq to %u: %d", + freq, ret); + } + + return ret; +} + +static void slpc_boost_work(struct work_struct *work) +{ + struct intel_guc_slpc *slpc = container_of(work, typeof(*slpc), boost_work); + + /* + * Raise min freq to boost. It's possible that + * this is greater than current max. But it will + * certainly be limited by RP0. An error setting + * the min param is not fatal. + */ + mutex_lock(&slpc->lock); + if (atomic_read(&slpc->num_waiters)) { + slpc_force_min_freq(slpc, slpc->boost_freq); + slpc->num_boosts++; + } + mutex_unlock(&slpc->lock); +} + +int intel_guc_slpc_init(struct intel_guc_slpc *slpc) +{ + struct intel_guc *guc = slpc_to_guc(slpc); + struct drm_i915_private *i915 = slpc_to_i915(slpc); + u32 size = PAGE_ALIGN(sizeof(struct slpc_shared_data)); + int err; + + GEM_BUG_ON(slpc->vma); + + err = intel_guc_allocate_and_map_vma(guc, size, &slpc->vma, (void **)&slpc->vaddr); + if (unlikely(err)) { + drm_err(&i915->drm, + "Failed to allocate SLPC struct (err=%pe)\n", + ERR_PTR(err)); + return err; + } + + slpc->max_freq_softlimit = 0; + slpc->min_freq_softlimit = 0; + + slpc->boost_freq = 0; + atomic_set(&slpc->num_waiters, 0); + slpc->num_boosts = 0; + + mutex_init(&slpc->lock); + INIT_WORK(&slpc->boost_work, slpc_boost_work); + + return err; +} + static const char *slpc_global_state_to_string(enum slpc_global_state state) { switch (state) { @@ -393,7 +450,11 @@ int intel_guc_slpc_set_min_freq(struct intel_guc_slpc *slpc, u32 val) val > slpc->max_freq_softlimit) return -EINVAL; + /* Need a lock now since waitboost can be modifying min as well */ + mutex_lock(&slpc->lock); + with_intel_runtime_pm(&i915->runtime_pm, wakeref) { + ret = slpc_set_param(slpc, SLPC_PARAM_GLOBAL_MIN_GT_UNSLICE_FREQ_MHZ, val); @@ -406,6 +467,8 @@ int intel_guc_slpc_set_min_freq(struct intel_guc_slpc *slpc, u32 val) if (!ret) slpc->min_freq_softlimit = val; + mutex_unlock(&slpc->lock); + return ret; } @@ -522,6 +585,9 @@ static void slpc_get_rp_values(struct intel_guc_slpc *slpc) GT_FREQUENCY_MULTIPLIER; slpc->min_freq = REG_FIELD_GET(RPN_CAP_MASK, rp_state_cap) * GT_FREQUENCY_MULTIPLIER; + + if (!slpc->boost_freq) + slpc->boost_freq = slpc->rp0_freq; } /* @@ -557,7 +623,7 @@ int intel_guc_slpc_enable(struct intel_guc_slpc *slpc) if (unlikely(ret < 0)) return ret; - intel_guc_pm_intrmsk_enable(&i915->gt); + intel_guc_pm_intrmsk_enable(to_gt(i915)); slpc_get_rp_values(slpc); @@ -588,6 +654,47 @@ int intel_guc_slpc_enable(struct intel_guc_slpc *slpc) return 0; } +int intel_guc_slpc_set_boost_freq(struct intel_guc_slpc *slpc, u32 val) +{ + int ret = 0; + + if (val < slpc->min_freq || val > slpc->rp0_freq) + return -EINVAL; + + mutex_lock(&slpc->lock); + + if (slpc->boost_freq != val) { + /* Apply only if there are active waiters */ + if (atomic_read(&slpc->num_waiters)) { + ret = slpc_force_min_freq(slpc, val); + if (ret) { + ret = -EIO; + goto done; + } + } + + slpc->boost_freq = val; + } + +done: + mutex_unlock(&slpc->lock); + return ret; +} + +void intel_guc_slpc_dec_waiters(struct intel_guc_slpc *slpc) +{ + /* + * Return min back to the softlimit. + * This is called during request retire, + * so we don't need to fail that if the + * set_param fails. + */ + mutex_lock(&slpc->lock); + if (atomic_dec_and_test(&slpc->num_waiters)) + slpc_force_min_freq(slpc, slpc->min_freq_softlimit); + mutex_unlock(&slpc->lock); +} + int intel_guc_slpc_print_info(struct intel_guc_slpc *slpc, struct drm_printer *p) { struct drm_i915_private *i915 = slpc_to_i915(slpc); @@ -611,6 +718,8 @@ int intel_guc_slpc_print_info(struct intel_guc_slpc *slpc, struct drm_printer *p slpc_decode_max_freq(slpc)); drm_printf(p, "\tMin freq: %u MHz\n", slpc_decode_min_freq(slpc)); + drm_printf(p, "\twaitboosts: %u\n", + slpc->num_boosts); } } 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 e45054d5b9b4..0caa8fee3c04 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h @@ -34,9 +34,12 @@ int intel_guc_slpc_enable(struct intel_guc_slpc *slpc); void intel_guc_slpc_fini(struct intel_guc_slpc *slpc); int intel_guc_slpc_set_max_freq(struct intel_guc_slpc *slpc, u32 val); int intel_guc_slpc_set_min_freq(struct intel_guc_slpc *slpc, u32 val); +int intel_guc_slpc_set_boost_freq(struct intel_guc_slpc *slpc, u32 val); int intel_guc_slpc_get_max_freq(struct intel_guc_slpc *slpc, u32 *val); int intel_guc_slpc_get_min_freq(struct intel_guc_slpc *slpc, u32 *val); int intel_guc_slpc_print_info(struct intel_guc_slpc *slpc, struct drm_printer *p); 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); #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 41d13527666f..bf5b9a563c09 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 @@ -6,6 +6,9 @@ #ifndef _INTEL_GUC_SLPC_TYPES_H_ #define _INTEL_GUC_SLPC_TYPES_H_ +#include <linux/atomic.h> +#include <linux/workqueue.h> +#include <linux/mutex.h> #include <linux/types.h> #define SLPC_RESET_TIMEOUT_MS 5 @@ -20,10 +23,20 @@ struct intel_guc_slpc { u32 min_freq; u32 rp0_freq; u32 rp1_freq; + u32 boost_freq; /* frequency softlimits */ u32 min_freq_softlimit; u32 max_freq_softlimit; + + /* Protects set/reset of boost freq + * and value of num_waiters + */ + struct mutex lock; + + struct work_struct boost_work; + atomic_t num_waiters; + u32 num_boosts; }; #endif 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 302e9ff0602c..e7517206af82 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -13,6 +13,7 @@ #include "gt/intel_engine_heartbeat.h" #include "gt/intel_gpu_commands.h" #include "gt/intel_gt.h" +#include "gt/intel_gt_clock_utils.h" #include "gt/intel_gt_irq.h" #include "gt/intel_gt_pm.h" #include "gt/intel_gt_requests.h" @@ -21,6 +22,7 @@ #include "gt/intel_mocs.h" #include "gt/intel_ring.h" +#include "intel_guc_ads.h" #include "intel_guc_submission.h" #include "i915_drv.h" @@ -143,7 +145,8 @@ guc_create_parallel(struct intel_engine_cs **engines, * use should be low and 1/16 should be sufficient. Minimum of 32 guc_ids for * multi-lrc. */ -#define NUMBER_MULTI_LRC_GUC_ID (GUC_MAX_LRC_DESCRIPTORS / 16) +#define NUMBER_MULTI_LRC_GUC_ID(guc) \ + ((guc)->submission_state.num_guc_ids / 16) /* * Below is a set of functions which control the GuC scheduling state which @@ -1038,8 +1041,6 @@ static void scrub_guc_desc_for_outstanding_g2h(struct intel_guc *guc) spin_unlock(&ce->guc_state.lock); - GEM_BUG_ON(!do_put && !destroyed); - if (pending_enable || destroyed || deregister) { decr_outstanding_submission_g2h(guc); if (deregister) @@ -1077,6 +1078,271 @@ static void scrub_guc_desc_for_outstanding_g2h(struct intel_guc *guc) xa_unlock_irqrestore(&guc->context_lookup, flags); } +/* + * GuC stores busyness stats for each engine at context in/out boundaries. A + * context 'in' logs execution start time, 'out' adds in -> out delta to total. + * i915/kmd accesses 'start', 'total' and 'context id' from memory shared with + * GuC. + * + * __i915_pmu_event_read samples engine busyness. When sampling, if context id + * is valid (!= ~0) and start is non-zero, the engine is considered to be + * active. For an active engine total busyness = total + (now - start), where + * 'now' is the time at which the busyness is sampled. For inactive engine, + * total busyness = total. + * + * All times are captured from GUCPMTIMESTAMP reg and are in gt clock domain. + * + * The start and total values provided by GuC are 32 bits and wrap around in a + * few minutes. Since perf pmu provides busyness as 64 bit monotonically + * increasing ns values, there is a need for this implementation to account for + * overflows and extend the GuC provided values to 64 bits before returning + * busyness to the user. In order to do that, a worker runs periodically at + * frequency = 1/8th the time it takes for the timestamp to wrap (i.e. once in + * 27 seconds for a gt clock frequency of 19.2 MHz). + */ + +#define WRAP_TIME_CLKS U32_MAX +#define POLL_TIME_CLKS (WRAP_TIME_CLKS >> 3) + +static void +__extend_last_switch(struct intel_guc *guc, u64 *prev_start, u32 new_start) +{ + u32 gt_stamp_hi = upper_32_bits(guc->timestamp.gt_stamp); + u32 gt_stamp_last = lower_32_bits(guc->timestamp.gt_stamp); + + if (new_start == lower_32_bits(*prev_start)) + return; + + if (new_start < gt_stamp_last && + (new_start - gt_stamp_last) <= POLL_TIME_CLKS) + gt_stamp_hi++; + + if (new_start > gt_stamp_last && + (gt_stamp_last - new_start) <= POLL_TIME_CLKS && gt_stamp_hi) + gt_stamp_hi--; + + *prev_start = ((u64)gt_stamp_hi << 32) | new_start; +} + +static void guc_update_engine_gt_clks(struct intel_engine_cs *engine) +{ + struct guc_engine_usage_record *rec = intel_guc_engine_usage(engine); + struct intel_engine_guc_stats *stats = &engine->stats.guc; + struct intel_guc *guc = &engine->gt->uc.guc; + u32 last_switch = rec->last_switch_in_stamp; + u32 ctx_id = rec->current_context_index; + u32 total = rec->total_runtime; + + lockdep_assert_held(&guc->timestamp.lock); + + stats->running = ctx_id != ~0U && last_switch; + if (stats->running) + __extend_last_switch(guc, &stats->start_gt_clk, last_switch); + + /* + * Instead of adjusting the total for overflow, just add the + * difference from previous sample stats->total_gt_clks + */ + if (total && total != ~0U) { + stats->total_gt_clks += (u32)(total - stats->prev_total); + stats->prev_total = total; + } +} + +static void guc_update_pm_timestamp(struct intel_guc *guc, + struct intel_engine_cs *engine, + ktime_t *now) +{ + u32 gt_stamp_now, gt_stamp_hi; + + lockdep_assert_held(&guc->timestamp.lock); + + gt_stamp_hi = upper_32_bits(guc->timestamp.gt_stamp); + gt_stamp_now = intel_uncore_read(engine->uncore, + RING_TIMESTAMP(engine->mmio_base)); + *now = ktime_get(); + + if (gt_stamp_now < lower_32_bits(guc->timestamp.gt_stamp)) + gt_stamp_hi++; + + guc->timestamp.gt_stamp = ((u64)gt_stamp_hi << 32) | gt_stamp_now; +} + +/* + * Unlike the execlist mode of submission total and active times are in terms of + * gt clocks. The *now parameter is retained to return the cpu time at which the + * busyness was sampled. + */ +static ktime_t guc_engine_busyness(struct intel_engine_cs *engine, ktime_t *now) +{ + struct intel_engine_guc_stats stats_saved, *stats = &engine->stats.guc; + struct i915_gpu_error *gpu_error = &engine->i915->gpu_error; + struct intel_gt *gt = engine->gt; + struct intel_guc *guc = >->uc.guc; + u64 total, gt_stamp_saved; + unsigned long flags; + u32 reset_count; + bool in_reset; + + spin_lock_irqsave(&guc->timestamp.lock, flags); + + /* + * If a reset happened, we risk reading partially updated engine + * busyness from GuC, so we just use the driver stored copy of busyness. + * Synchronize with gt reset using reset_count and the + * I915_RESET_BACKOFF flag. Note that reset flow updates the reset_count + * after I915_RESET_BACKOFF flag, so ensure that the reset_count is + * usable by checking the flag afterwards. + */ + reset_count = i915_reset_count(gpu_error); + in_reset = test_bit(I915_RESET_BACKOFF, >->reset.flags); + + *now = ktime_get(); + + /* + * The active busyness depends on start_gt_clk and gt_stamp. + * gt_stamp is updated by i915 only when gt is awake and the + * start_gt_clk is derived from GuC state. To get a consistent + * view of activity, we query the GuC state only if gt is awake. + */ + if (!in_reset && intel_gt_pm_get_if_awake(gt)) { + stats_saved = *stats; + gt_stamp_saved = guc->timestamp.gt_stamp; + guc_update_engine_gt_clks(engine); + guc_update_pm_timestamp(guc, engine, now); + intel_gt_pm_put_async(gt); + if (i915_reset_count(gpu_error) != reset_count) { + *stats = stats_saved; + guc->timestamp.gt_stamp = gt_stamp_saved; + } + } + + total = intel_gt_clock_interval_to_ns(gt, stats->total_gt_clks); + if (stats->running) { + u64 clk = guc->timestamp.gt_stamp - stats->start_gt_clk; + + total += intel_gt_clock_interval_to_ns(gt, clk); + } + + spin_unlock_irqrestore(&guc->timestamp.lock, flags); + + return ns_to_ktime(total); +} + +static void __reset_guc_busyness_stats(struct intel_guc *guc) +{ + struct intel_gt *gt = guc_to_gt(guc); + struct intel_engine_cs *engine; + enum intel_engine_id id; + unsigned long flags; + ktime_t unused; + + cancel_delayed_work_sync(&guc->timestamp.work); + + spin_lock_irqsave(&guc->timestamp.lock, flags); + + for_each_engine(engine, gt, id) { + guc_update_pm_timestamp(guc, engine, &unused); + guc_update_engine_gt_clks(engine); + engine->stats.guc.prev_total = 0; + } + + spin_unlock_irqrestore(&guc->timestamp.lock, flags); +} + +static void __update_guc_busyness_stats(struct intel_guc *guc) +{ + struct intel_gt *gt = guc_to_gt(guc); + struct intel_engine_cs *engine; + enum intel_engine_id id; + unsigned long flags; + ktime_t unused; + + spin_lock_irqsave(&guc->timestamp.lock, flags); + for_each_engine(engine, gt, id) { + guc_update_pm_timestamp(guc, engine, &unused); + guc_update_engine_gt_clks(engine); + } + spin_unlock_irqrestore(&guc->timestamp.lock, flags); +} + +static void guc_timestamp_ping(struct work_struct *wrk) +{ + struct intel_guc *guc = container_of(wrk, typeof(*guc), + timestamp.work.work); + struct intel_uc *uc = container_of(guc, typeof(*uc), guc); + struct intel_gt *gt = guc_to_gt(guc); + intel_wakeref_t wakeref; + int srcu, ret; + + /* + * Synchronize with gt reset to make sure the worker does not + * corrupt the engine/guc stats. + */ + ret = intel_gt_reset_trylock(gt, &srcu); + if (ret) + return; + + with_intel_runtime_pm(>->i915->runtime_pm, wakeref) + __update_guc_busyness_stats(guc); + + intel_gt_reset_unlock(gt, srcu); + + mod_delayed_work(system_highpri_wq, &guc->timestamp.work, + guc->timestamp.ping_delay); +} + +static int guc_action_enable_usage_stats(struct intel_guc *guc) +{ + u32 offset = intel_guc_engine_usage_offset(guc); + u32 action[] = { + INTEL_GUC_ACTION_SET_ENG_UTIL_BUFF, + offset, + 0, + }; + + return intel_guc_send(guc, action, ARRAY_SIZE(action)); +} + +static void guc_init_engine_stats(struct intel_guc *guc) +{ + struct intel_gt *gt = guc_to_gt(guc); + intel_wakeref_t wakeref; + + mod_delayed_work(system_highpri_wq, &guc->timestamp.work, + guc->timestamp.ping_delay); + + with_intel_runtime_pm(>->i915->runtime_pm, wakeref) { + int ret = guc_action_enable_usage_stats(guc); + + if (ret) + drm_err(>->i915->drm, + "Failed to enable usage stats: %d!\n", ret); + } +} + +void intel_guc_busyness_park(struct intel_gt *gt) +{ + struct intel_guc *guc = >->uc.guc; + + if (!guc_submission_initialized(guc)) + return; + + cancel_delayed_work(&guc->timestamp.work); + __update_guc_busyness_stats(guc); +} + +void intel_guc_busyness_unpark(struct intel_gt *gt) +{ + struct intel_guc *guc = >->uc.guc; + + if (!guc_submission_initialized(guc)) + return; + + mod_delayed_work(system_highpri_wq, &guc->timestamp.work, + guc->timestamp.ping_delay); +} + static inline bool submission_disabled(struct intel_guc *guc) { @@ -1138,6 +1404,7 @@ void intel_guc_submission_reset_prepare(struct intel_guc *guc) intel_gt_park_heartbeats(guc_to_gt(guc)); disable_submission(guc); guc->interrupts.disable(guc); + __reset_guc_busyness_stats(guc); /* Flush IRQ handler */ spin_lock_irq(&guc_to_gt(guc)->irq_lock); @@ -1484,6 +1751,7 @@ static void destroyed_worker_func(struct work_struct *w); */ int intel_guc_submission_init(struct intel_guc *guc) { + struct intel_gt *gt = guc_to_gt(guc); int ret; if (guc->lrc_desc_pool) @@ -1508,10 +1776,14 @@ int intel_guc_submission_init(struct intel_guc *guc) destroyed_worker_func); guc->submission_state.guc_ids_bitmap = - bitmap_zalloc(NUMBER_MULTI_LRC_GUC_ID, GFP_KERNEL); + bitmap_zalloc(NUMBER_MULTI_LRC_GUC_ID(guc), GFP_KERNEL); if (!guc->submission_state.guc_ids_bitmap) return -ENOMEM; + spin_lock_init(&guc->timestamp.lock); + INIT_DELAYED_WORK(&guc->timestamp.work, guc_timestamp_ping); + guc->timestamp.ping_delay = (POLL_TIME_CLKS / gt->clock_frequency + 1) * HZ; + return 0; } @@ -1598,13 +1870,13 @@ static int new_guc_id(struct intel_guc *guc, struct intel_context *ce) if (intel_context_is_parent(ce)) ret = bitmap_find_free_region(guc->submission_state.guc_ids_bitmap, - NUMBER_MULTI_LRC_GUC_ID, + NUMBER_MULTI_LRC_GUC_ID(guc), order_base_2(ce->parallel.number_children + 1)); else ret = ida_simple_get(&guc->submission_state.guc_ids, - NUMBER_MULTI_LRC_GUC_ID, - GUC_MAX_LRC_DESCRIPTORS, + NUMBER_MULTI_LRC_GUC_ID(guc), + guc->submission_state.num_guc_ids, GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN); if (unlikely(ret < 0)) @@ -1670,6 +1942,10 @@ static int steal_guc_id(struct intel_guc *guc, struct intel_context *ce) set_context_guc_id_invalid(cn); +#ifdef CONFIG_DRM_I915_SELFTEST + guc->number_guc_id_stolen++; +#endif + return 0; } else { return -EAGAIN; @@ -2373,7 +2649,6 @@ static inline void guc_lrc_desc_unpin(struct intel_context *ce) unsigned long flags; bool disabled; - lockdep_assert_held(&guc->submission_state.lock); GEM_BUG_ON(!intel_gt_pm_is_awake(gt)); GEM_BUG_ON(!lrc_desc_registered(guc, ce->guc_id.id)); GEM_BUG_ON(ce != __get_context(guc, ce->guc_id.id)); @@ -2389,7 +2664,7 @@ static inline void guc_lrc_desc_unpin(struct intel_context *ce) } spin_unlock_irqrestore(&ce->guc_state.lock, flags); if (unlikely(disabled)) { - __release_guc_id(guc, ce); + release_guc_id(guc, ce); __guc_context_destroy(ce); return; } @@ -2423,36 +2698,48 @@ static void __guc_context_destroy(struct intel_context *ce) static void guc_flush_destroyed_contexts(struct intel_guc *guc) { - struct intel_context *ce, *cn; + struct intel_context *ce; unsigned long flags; GEM_BUG_ON(!submission_disabled(guc) && guc_submission_initialized(guc)); - spin_lock_irqsave(&guc->submission_state.lock, flags); - list_for_each_entry_safe(ce, cn, - &guc->submission_state.destroyed_contexts, - destroyed_link) { - list_del_init(&ce->destroyed_link); - __release_guc_id(guc, ce); + while (!list_empty(&guc->submission_state.destroyed_contexts)) { + spin_lock_irqsave(&guc->submission_state.lock, flags); + ce = list_first_entry_or_null(&guc->submission_state.destroyed_contexts, + struct intel_context, + destroyed_link); + if (ce) + list_del_init(&ce->destroyed_link); + spin_unlock_irqrestore(&guc->submission_state.lock, flags); + + if (!ce) + break; + + release_guc_id(guc, ce); __guc_context_destroy(ce); } - spin_unlock_irqrestore(&guc->submission_state.lock, flags); } static void deregister_destroyed_contexts(struct intel_guc *guc) { - struct intel_context *ce, *cn; + struct intel_context *ce; unsigned long flags; - spin_lock_irqsave(&guc->submission_state.lock, flags); - list_for_each_entry_safe(ce, cn, - &guc->submission_state.destroyed_contexts, - destroyed_link) { - list_del_init(&ce->destroyed_link); + while (!list_empty(&guc->submission_state.destroyed_contexts)) { + spin_lock_irqsave(&guc->submission_state.lock, flags); + ce = list_first_entry_or_null(&guc->submission_state.destroyed_contexts, + struct intel_context, + destroyed_link); + if (ce) + list_del_init(&ce->destroyed_link); + spin_unlock_irqrestore(&guc->submission_state.lock, flags); + + if (!ce) + break; + guc_lrc_desc_unpin(ce); } - spin_unlock_irqrestore(&guc->submission_state.lock, flags); } static void destroyed_worker_func(struct work_struct *w) @@ -3369,7 +3656,9 @@ static void guc_default_vfuncs(struct intel_engine_cs *engine) engine->emit_flush = gen12_emit_flush_xcs; } engine->set_default_submission = guc_set_default_submission; + engine->busyness = guc_engine_busyness; + engine->flags |= I915_ENGINE_SUPPORTS_STATS; engine->flags |= I915_ENGINE_HAS_PREEMPTION; engine->flags |= I915_ENGINE_HAS_TIMESLICES; @@ -3468,6 +3757,7 @@ int intel_guc_submission_setup(struct intel_engine_cs *engine) void intel_guc_submission_enable(struct intel_guc *guc) { guc_init_lrc_mapping(guc); + guc_init_engine_stats(guc); } void intel_guc_submission_disable(struct intel_guc *guc) @@ -3494,6 +3784,7 @@ static bool __guc_submission_selected(struct intel_guc *guc) void intel_guc_submission_init_early(struct intel_guc *guc) { + guc->submission_state.num_guc_ids = GUC_MAX_LRC_DESCRIPTORS; guc->submission_supported = __guc_submission_supported(guc); guc->submission_selected = __guc_submission_selected(guc); } @@ -3695,6 +3986,7 @@ int intel_guc_context_reset_process_msg(struct intel_guc *guc, const u32 *msg, u32 len) { struct intel_context *ce; + unsigned long flags; int desc_idx; if (unlikely(len != 1)) { @@ -3703,11 +3995,24 @@ int intel_guc_context_reset_process_msg(struct intel_guc *guc, } desc_idx = msg[0]; + + /* + * The context lookup uses the xarray but lookups only require an RCU lock + * not the full spinlock. So take the lock explicitly and keep it until the + * context has been reference count locked to ensure it can't be destroyed + * asynchronously until the reset is done. + */ + xa_lock_irqsave(&guc->context_lookup, flags); ce = g2h_context_lookup(guc, desc_idx); + if (ce) + intel_context_get(ce); + xa_unlock_irqrestore(&guc->context_lookup, flags); + if (unlikely(!ce)) return -EPROTO; guc_handle_context_reset(guc, ce); + intel_context_put(ce); return 0; } @@ -3728,11 +4033,12 @@ int intel_guc_engine_failure_process_msg(struct intel_guc *guc, const u32 *msg, u32 len) { struct intel_engine_cs *engine; + struct intel_gt *gt = guc_to_gt(guc); u8 guc_class, instance; u32 reason; if (unlikely(len != 3)) { - drm_err(&guc_to_gt(guc)->i915->drm, "Invalid length %u", len); + drm_err(>->i915->drm, "Invalid length %u", len); return -EPROTO; } @@ -3742,12 +4048,19 @@ int intel_guc_engine_failure_process_msg(struct intel_guc *guc, engine = guc_lookup_engine(guc, guc_class, instance); if (unlikely(!engine)) { - drm_err(&guc_to_gt(guc)->i915->drm, + drm_err(>->i915->drm, "Invalid engine %d:%d", guc_class, instance); return -EPROTO; } - intel_gt_handle_error(guc_to_gt(guc), engine->mask, + /* + * This is an unexpected failure of a hardware feature. So, log a real + * error message not just the informational that comes with the reset. + */ + drm_err(>->i915->drm, "GuC engine reset request failed on %d:%d (%s) because 0x%08X", + guc_class, instance, engine->name, reason); + + intel_gt_handle_error(gt, engine->mask, I915_ERROR_CAPTURE, "GuC failed to reset %s (reason=0x%08x)\n", engine->name, reason); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h index c7ef44fa0c36..5a95a9f0a8e3 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h @@ -28,6 +28,8 @@ void intel_guc_submission_print_context_info(struct intel_guc *guc, void intel_guc_dump_active_requests(struct intel_engine_cs *engine, struct i915_request *hung_rq, struct drm_printer *m); +void intel_guc_busyness_park(struct intel_gt *gt); +void intel_guc_busyness_unpark(struct intel_gt *gt); bool intel_guc_virtual_engine_has_heartbeat(const struct intel_engine_cs *ve); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c index ff4b6869b80b..d10b227ac4aa 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c @@ -54,65 +54,6 @@ void intel_huc_init_early(struct intel_huc *huc) } } -static int intel_huc_rsa_data_create(struct intel_huc *huc) -{ - struct intel_gt *gt = huc_to_gt(huc); - struct intel_guc *guc = >->uc.guc; - struct i915_vma *vma; - size_t copied; - void *vaddr; - int err; - - err = i915_inject_probe_error(gt->i915, -ENXIO); - if (err) - return err; - - /* - * HuC firmware will sit above GUC_GGTT_TOP and will not map - * through GTT. Unfortunately, this means GuC cannot perform - * the HuC auth. as the rsa offset now falls within the GuC - * inaccessible range. We resort to perma-pinning an additional - * vma within the accessible range that only contains the rsa - * signature. The GuC can use this extra pinning to perform - * the authentication since its GGTT offset will be GuC - * accessible. - */ - GEM_BUG_ON(huc->fw.rsa_size > PAGE_SIZE); - vma = intel_guc_allocate_vma(guc, PAGE_SIZE); - if (IS_ERR(vma)) - return PTR_ERR(vma); - - vaddr = i915_gem_object_pin_map_unlocked(vma->obj, - i915_coherent_map_type(gt->i915, - vma->obj, true)); - if (IS_ERR(vaddr)) { - i915_vma_unpin_and_release(&vma, 0); - err = PTR_ERR(vaddr); - goto unpin_out; - } - - copied = intel_uc_fw_copy_rsa(&huc->fw, vaddr, vma->size); - i915_gem_object_unpin_map(vma->obj); - - if (copied < huc->fw.rsa_size) { - err = -ENOMEM; - goto unpin_out; - } - - huc->rsa_data = vma; - - return 0; - -unpin_out: - i915_vma_unpin_and_release(&vma, 0); - return err; -} - -static void intel_huc_rsa_data_destroy(struct intel_huc *huc) -{ - i915_vma_unpin_and_release(&huc->rsa_data, 0); -} - int intel_huc_init(struct intel_huc *huc) { struct drm_i915_private *i915 = huc_to_gt(huc)->i915; @@ -122,21 +63,10 @@ int intel_huc_init(struct intel_huc *huc) if (err) goto out; - /* - * HuC firmware image is outside GuC accessible range. - * Copy the RSA signature out of the image into - * a perma-pinned region set aside for it - */ - err = intel_huc_rsa_data_create(huc); - if (err) - goto out_fini; - intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_LOADABLE); return 0; -out_fini: - intel_uc_fw_fini(&huc->fw); out: i915_probe_error(i915, "failed with %d\n", err); return err; @@ -147,7 +77,6 @@ void intel_huc_fini(struct intel_huc *huc) if (!intel_uc_fw_is_loadable(&huc->fw)) return; - intel_huc_rsa_data_destroy(huc); intel_uc_fw_fini(&huc->fw); } @@ -177,7 +106,7 @@ int intel_huc_auth(struct intel_huc *huc) goto fail; ret = intel_guc_auth_huc(guc, - intel_guc_ggtt_offset(guc, huc->rsa_data)); + intel_guc_ggtt_offset(guc, huc->fw.rsa_data)); if (ret) { DRM_ERROR("HuC: GuC did not ack Auth request %d\n", ret); goto fail; @@ -199,7 +128,7 @@ int intel_huc_auth(struct intel_huc *huc) fail: i915_probe_error(gt->i915, "HuC: Authentication failed %d\n", ret); - intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_FAIL); + intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_LOAD_FAIL); return ret; } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.h b/drivers/gpu/drm/i915/gt/uc/intel_huc.h index daee43b661d4..ae8c8a6c8cc8 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.h @@ -15,8 +15,6 @@ struct intel_huc { struct intel_uc_fw fw; /* HuC-specific additions */ - struct i915_vma *rsa_data; - struct { i915_reg_t reg; u32 mask; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c index 2fef3b0bbe95..09ed29df67bc 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c @@ -8,6 +8,7 @@ #include "intel_guc.h" #include "intel_guc_ads.h" #include "intel_guc_submission.h" +#include "gt/intel_rps.h" #include "intel_uc.h" #include "i915_drv.h" @@ -35,7 +36,7 @@ static void uc_expand_default_options(struct intel_uc *uc) } /* Intermediate platforms are HuC authentication only */ - if (IS_ALDERLAKE_S(i915)) { + if (IS_ALDERLAKE_S(i915) && !IS_ADLS_RPLS(i915)) { i915->params.enable_guc = ENABLE_GUC_LOAD_HUC; return; } @@ -462,6 +463,8 @@ static int __uc_init_hw(struct intel_uc *uc) else attempts = 1; + intel_rps_raise_unslice(&uc_to_gt(uc)->rps); + while (attempts--) { /* * Always reset the GuC just before (re)loading, so @@ -499,6 +502,9 @@ static int __uc_init_hw(struct intel_uc *uc) ret = intel_guc_slpc_enable(&guc->slpc); if (ret) goto err_submission; + } else { + /* Restore GT back to RPn for non-SLPC path */ + intel_rps_lower_unslice(&uc_to_gt(uc)->rps); } drm_info(&i915->drm, "%s firmware %s version %u.%u %s:%s\n", @@ -529,6 +535,9 @@ err_submission: err_log_capture: __uc_capture_load_err_log(uc); err_out: + /* Return GT back to RPn */ + intel_rps_lower_unslice(&uc_to_gt(uc)->rps); + __uc_sanitize(uc); if (!ret) { 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 3aa87be4f2e4..a5af05bde6f2 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c @@ -48,22 +48,39 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw, * Note that RKL and ADL-S have the same GuC/HuC device ID's and use the same * firmware as TGL. */ -#define INTEL_UC_FIRMWARE_DEFS(fw_def, guc_def, huc_def) \ - fw_def(ALDERLAKE_P, 0, guc_def(adlp, 62, 0, 3), huc_def(tgl, 7, 9, 3)) \ - fw_def(ALDERLAKE_S, 0, guc_def(tgl, 62, 0, 0), huc_def(tgl, 7, 9, 3)) \ - fw_def(DG1, 0, guc_def(dg1, 62, 0, 0), huc_def(dg1, 7, 9, 3)) \ - fw_def(ROCKETLAKE, 0, guc_def(tgl, 62, 0, 0), huc_def(tgl, 7, 9, 3)) \ - fw_def(TIGERLAKE, 0, guc_def(tgl, 62, 0, 0), huc_def(tgl, 7, 9, 3)) \ - fw_def(JASPERLAKE, 0, guc_def(ehl, 62, 0, 0), huc_def(ehl, 9, 0, 0)) \ - fw_def(ELKHARTLAKE, 0, guc_def(ehl, 62, 0, 0), huc_def(ehl, 9, 0, 0)) \ - fw_def(ICELAKE, 0, guc_def(icl, 62, 0, 0), huc_def(icl, 9, 0, 0)) \ - fw_def(COMETLAKE, 5, guc_def(cml, 62, 0, 0), huc_def(cml, 4, 0, 0)) \ - fw_def(COMETLAKE, 0, guc_def(kbl, 62, 0, 0), huc_def(kbl, 4, 0, 0)) \ - fw_def(COFFEELAKE, 0, guc_def(kbl, 62, 0, 0), huc_def(kbl, 4, 0, 0)) \ - fw_def(GEMINILAKE, 0, guc_def(glk, 62, 0, 0), huc_def(glk, 4, 0, 0)) \ - fw_def(KABYLAKE, 0, guc_def(kbl, 62, 0, 0), huc_def(kbl, 4, 0, 0)) \ - fw_def(BROXTON, 0, guc_def(bxt, 62, 0, 0), huc_def(bxt, 2, 0, 0)) \ - fw_def(SKYLAKE, 0, guc_def(skl, 62, 0, 0), huc_def(skl, 2, 0, 0)) +#define INTEL_GUC_FIRMWARE_DEFS(fw_def, guc_def) \ + fw_def(ALDERLAKE_P, 0, guc_def(adlp, 62, 0, 3)) \ + fw_def(ALDERLAKE_S, 0, guc_def(tgl, 62, 0, 0)) \ + fw_def(DG1, 0, guc_def(dg1, 62, 0, 0)) \ + fw_def(ROCKETLAKE, 0, guc_def(tgl, 62, 0, 0)) \ + fw_def(TIGERLAKE, 0, guc_def(tgl, 62, 0, 0)) \ + fw_def(JASPERLAKE, 0, guc_def(ehl, 62, 0, 0)) \ + fw_def(ELKHARTLAKE, 0, guc_def(ehl, 62, 0, 0)) \ + fw_def(ICELAKE, 0, guc_def(icl, 62, 0, 0)) \ + fw_def(COMETLAKE, 5, guc_def(cml, 62, 0, 0)) \ + fw_def(COMETLAKE, 0, guc_def(kbl, 62, 0, 0)) \ + fw_def(COFFEELAKE, 0, guc_def(kbl, 62, 0, 0)) \ + fw_def(GEMINILAKE, 0, guc_def(glk, 62, 0, 0)) \ + fw_def(KABYLAKE, 0, guc_def(kbl, 62, 0, 0)) \ + fw_def(BROXTON, 0, guc_def(bxt, 62, 0, 0)) \ + fw_def(SKYLAKE, 0, guc_def(skl, 62, 0, 0)) + +#define INTEL_HUC_FIRMWARE_DEFS(fw_def, huc_def) \ + fw_def(ALDERLAKE_P, 0, huc_def(tgl, 7, 9, 3)) \ + fw_def(ALDERLAKE_S, 0, huc_def(tgl, 7, 9, 3)) \ + fw_def(DG1, 0, huc_def(dg1, 7, 9, 3)) \ + fw_def(ROCKETLAKE, 0, huc_def(tgl, 7, 9, 3)) \ + fw_def(TIGERLAKE, 0, huc_def(tgl, 7, 9, 3)) \ + fw_def(JASPERLAKE, 0, huc_def(ehl, 9, 0, 0)) \ + fw_def(ELKHARTLAKE, 0, huc_def(ehl, 9, 0, 0)) \ + fw_def(ICELAKE, 0, huc_def(icl, 9, 0, 0)) \ + fw_def(COMETLAKE, 5, huc_def(cml, 4, 0, 0)) \ + fw_def(COMETLAKE, 0, huc_def(kbl, 4, 0, 0)) \ + fw_def(COFFEELAKE, 0, huc_def(kbl, 4, 0, 0)) \ + fw_def(GEMINILAKE, 0, huc_def(glk, 4, 0, 0)) \ + fw_def(KABYLAKE, 0, huc_def(kbl, 4, 0, 0)) \ + fw_def(BROXTON, 0, huc_def(bxt, 2, 0, 0)) \ + fw_def(SKYLAKE, 0, huc_def(skl, 2, 0, 0)) #define __MAKE_UC_FW_PATH(prefix_, name_, major_, minor_, patch_) \ "i915/" \ @@ -79,11 +96,11 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw, __MAKE_UC_FW_PATH(prefix_, "_huc_", major_, minor_, bld_num_) /* All blobs need to be declared via MODULE_FIRMWARE() */ -#define INTEL_UC_MODULE_FW(platform_, revid_, guc_, huc_) \ - MODULE_FIRMWARE(guc_); \ - MODULE_FIRMWARE(huc_); +#define INTEL_UC_MODULE_FW(platform_, revid_, uc_) \ + MODULE_FIRMWARE(uc_); -INTEL_UC_FIRMWARE_DEFS(INTEL_UC_MODULE_FW, MAKE_GUC_FW_PATH, MAKE_HUC_FW_PATH) +INTEL_GUC_FIRMWARE_DEFS(INTEL_UC_MODULE_FW, MAKE_GUC_FW_PATH) +INTEL_HUC_FIRMWARE_DEFS(INTEL_UC_MODULE_FW, MAKE_HUC_FW_PATH) /* The below structs and macros are used to iterate across the list of blobs */ struct __packed uc_fw_blob { @@ -106,31 +123,47 @@ struct __packed uc_fw_blob { struct __packed uc_fw_platform_requirement { enum intel_platform p; u8 rev; /* first platform rev using this FW */ - const struct uc_fw_blob blobs[INTEL_UC_FW_NUM_TYPES]; + const struct uc_fw_blob blob; }; -#define MAKE_FW_LIST(platform_, revid_, guc_, huc_) \ +#define MAKE_FW_LIST(platform_, revid_, uc_) \ { \ .p = INTEL_##platform_, \ .rev = revid_, \ - .blobs[INTEL_UC_FW_TYPE_GUC] = guc_, \ - .blobs[INTEL_UC_FW_TYPE_HUC] = huc_, \ + .blob = uc_, \ }, +struct fw_blobs_by_type { + const struct uc_fw_platform_requirement *blobs; + u32 count; +}; + static void __uc_fw_auto_select(struct drm_i915_private *i915, struct intel_uc_fw *uc_fw) { - static const struct uc_fw_platform_requirement fw_blobs[] = { - INTEL_UC_FIRMWARE_DEFS(MAKE_FW_LIST, GUC_FW_BLOB, HUC_FW_BLOB) + static const struct uc_fw_platform_requirement blobs_guc[] = { + INTEL_GUC_FIRMWARE_DEFS(MAKE_FW_LIST, GUC_FW_BLOB) + }; + static const struct uc_fw_platform_requirement blobs_huc[] = { + INTEL_HUC_FIRMWARE_DEFS(MAKE_FW_LIST, HUC_FW_BLOB) }; + 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) }, + [INTEL_UC_FW_TYPE_HUC] = { blobs_huc, ARRAY_SIZE(blobs_huc) }, + }; + static const struct uc_fw_platform_requirement *fw_blobs; enum intel_platform p = INTEL_INFO(i915)->platform; + u32 fw_count; u8 rev = INTEL_REVID(i915); int i; - for (i = 0; i < ARRAY_SIZE(fw_blobs) && p <= fw_blobs[i].p; i++) { + GEM_BUG_ON(uc_fw->type >= ARRAY_SIZE(blobs_all)); + fw_blobs = blobs_all[uc_fw->type].blobs; + fw_count = blobs_all[uc_fw->type].count; + + for (i = 0; i < fw_count && p <= fw_blobs[i].p; i++) { if (p == fw_blobs[i].p && rev >= fw_blobs[i].rev) { - const struct uc_fw_blob *blob = - &fw_blobs[i].blobs[uc_fw->type]; + const struct uc_fw_blob *blob = &fw_blobs[i].blob; uc_fw->path = blob->path; uc_fw->major_ver_wanted = blob->major; uc_fw->minor_ver_wanted = blob->minor; @@ -140,7 +173,7 @@ __uc_fw_auto_select(struct drm_i915_private *i915, struct intel_uc_fw *uc_fw) /* make sure the list is ordered as expected */ if (IS_ENABLED(CONFIG_DRM_I915_SELFTEST)) { - for (i = 1; i < ARRAY_SIZE(fw_blobs); i++) { + for (i = 1; i < fw_count; i++) { if (fw_blobs[i].p < fw_blobs[i - 1].p) continue; @@ -322,13 +355,6 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) uc_fw->ucode_size = (css->size_dw - css->header_size_dw) * sizeof(u32); /* now RSA */ - if (unlikely(css->key_size_dw != UOS_RSA_SCRATCH_COUNT)) { - drm_warn(&i915->drm, "%s firmware %s: unexpected key size: %u != %u\n", - intel_uc_fw_type_repr(uc_fw->type), uc_fw->path, - css->key_size_dw, UOS_RSA_SCRATCH_COUNT); - err = -EPROTO; - goto fail; - } uc_fw->rsa_size = css->key_size_dw * sizeof(u32); /* At least, it should have header, uCode and RSA. Size of all three. */ @@ -540,10 +566,79 @@ fail: i915_probe_error(gt->i915, "Failed to load %s firmware %s (%d)\n", intel_uc_fw_type_repr(uc_fw->type), uc_fw->path, err); - intel_uc_fw_change_status(uc_fw, INTEL_UC_FIRMWARE_FAIL); + intel_uc_fw_change_status(uc_fw, INTEL_UC_FIRMWARE_LOAD_FAIL); return err; } +static inline bool uc_fw_need_rsa_in_memory(struct intel_uc_fw *uc_fw) +{ + /* + * The HW reads the GuC RSA from memory if the key size is > 256 bytes, + * while it reads it from the 64 RSA registers if it is smaller. + * The HuC RSA is always read from memory. + */ + return uc_fw->type == INTEL_UC_FW_TYPE_HUC || uc_fw->rsa_size > 256; +} + +static int uc_fw_rsa_data_create(struct intel_uc_fw *uc_fw) +{ + struct intel_gt *gt = __uc_fw_to_gt(uc_fw); + struct i915_vma *vma; + size_t copied; + void *vaddr; + int err; + + err = i915_inject_probe_error(gt->i915, -ENXIO); + if (err) + return err; + + if (!uc_fw_need_rsa_in_memory(uc_fw)) + return 0; + + /* + * uC firmwares will sit above GUC_GGTT_TOP and will not map through + * GGTT. Unfortunately, this means that the GuC HW cannot perform the uC + * authentication from memory, as the RSA offset now falls within the + * GuC inaccessible range. We resort to perma-pinning an additional vma + * within the accessible range that only contains the RSA signature. + * The GuC HW can use this extra pinning to perform the authentication + * since its GGTT offset will be GuC accessible. + */ + GEM_BUG_ON(uc_fw->rsa_size > PAGE_SIZE); + vma = intel_guc_allocate_vma(>->uc.guc, PAGE_SIZE); + if (IS_ERR(vma)) + return PTR_ERR(vma); + + vaddr = i915_gem_object_pin_map_unlocked(vma->obj, + i915_coherent_map_type(gt->i915, vma->obj, true)); + if (IS_ERR(vaddr)) { + i915_vma_unpin_and_release(&vma, 0); + err = PTR_ERR(vaddr); + goto unpin_out; + } + + copied = intel_uc_fw_copy_rsa(uc_fw, vaddr, vma->size); + i915_gem_object_unpin_map(vma->obj); + + if (copied < uc_fw->rsa_size) { + err = -ENOMEM; + goto unpin_out; + } + + uc_fw->rsa_data = vma; + + return 0; + +unpin_out: + i915_vma_unpin_and_release(&vma, 0); + return err; +} + +static void uc_fw_rsa_data_destroy(struct intel_uc_fw *uc_fw) +{ + i915_vma_unpin_and_release(&uc_fw->rsa_data, 0); +} + int intel_uc_fw_init(struct intel_uc_fw *uc_fw) { int err; @@ -558,14 +653,29 @@ int intel_uc_fw_init(struct intel_uc_fw *uc_fw) if (err) { DRM_DEBUG_DRIVER("%s fw pin-pages err=%d\n", intel_uc_fw_type_repr(uc_fw->type), err); - intel_uc_fw_change_status(uc_fw, INTEL_UC_FIRMWARE_FAIL); + goto out; } + err = uc_fw_rsa_data_create(uc_fw); + if (err) { + DRM_DEBUG_DRIVER("%s fw rsa data creation failed, err=%d\n", + intel_uc_fw_type_repr(uc_fw->type), err); + goto out_unpin; + } + + return 0; + +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; } void intel_uc_fw_fini(struct intel_uc_fw *uc_fw) { + uc_fw_rsa_data_destroy(uc_fw); + if (i915_gem_object_has_pinned_pages(uc_fw->obj)) i915_gem_object_unpin_pages(uc_fw->obj); 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 1e00bf65639e..d9d1dc0b4cbb 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h @@ -32,11 +32,12 @@ struct intel_gt; * | | MISSING <--/ | \--> ERROR | * | fetch | V | * | | AVAILABLE | - * +------------+- | -+ + * +------------+- | \ -+ + * | | | \--> INIT FAIL | * | init | V | * | | /------> LOADABLE <----<-----------\ | * +------------+- \ / \ \ \ -+ - * | | FAIL <--< \--> TRANSFERRED \ | + * | | LOAD FAIL <--< \--> TRANSFERRED \ | * | upload | \ / \ / | * | | \---------/ \--> RUNNING | * +------------+---------------------------------------------------+ @@ -50,8 +51,9 @@ enum intel_uc_fw_status { INTEL_UC_FIRMWARE_MISSING, /* blob not found on the system */ INTEL_UC_FIRMWARE_ERROR, /* invalid format or version */ INTEL_UC_FIRMWARE_AVAILABLE, /* blob found and copied in mem */ + INTEL_UC_FIRMWARE_INIT_FAIL, /* failed to prepare fw objects for load */ INTEL_UC_FIRMWARE_LOADABLE, /* all fw-required objects are ready */ - INTEL_UC_FIRMWARE_FAIL, /* failed to xfer or init/auth the fw */ + INTEL_UC_FIRMWARE_LOAD_FAIL, /* failed to xfer or init/auth the fw */ INTEL_UC_FIRMWARE_TRANSFERRED, /* dma xfer done */ INTEL_UC_FIRMWARE_RUNNING /* init/auth done */ }; @@ -84,6 +86,7 @@ struct intel_uc_fw { * or during a GT reset (mutex guarantees single threaded). */ struct i915_vma dummy; + struct i915_vma *rsa_data; /* * The firmware build process will generate a version header file with major and @@ -130,10 +133,12 @@ const char *intel_uc_fw_status_repr(enum intel_uc_fw_status status) return "ERROR"; case INTEL_UC_FIRMWARE_AVAILABLE: return "AVAILABLE"; + case INTEL_UC_FIRMWARE_INIT_FAIL: + return "INIT FAIL"; case INTEL_UC_FIRMWARE_LOADABLE: return "LOADABLE"; - case INTEL_UC_FIRMWARE_FAIL: - return "FAIL"; + case INTEL_UC_FIRMWARE_LOAD_FAIL: + return "LOAD FAIL"; case INTEL_UC_FIRMWARE_TRANSFERRED: return "TRANSFERRED"; case INTEL_UC_FIRMWARE_RUNNING: @@ -155,7 +160,8 @@ static inline int intel_uc_fw_status_to_error(enum intel_uc_fw_status status) return -ENOENT; case INTEL_UC_FIRMWARE_ERROR: return -ENOEXEC; - case INTEL_UC_FIRMWARE_FAIL: + case INTEL_UC_FIRMWARE_INIT_FAIL: + case INTEL_UC_FIRMWARE_LOAD_FAIL: return -EIO; case INTEL_UC_FIRMWARE_SELECTED: return -ESTALE; diff --git a/drivers/gpu/drm/i915/gt/uc/selftest_guc.c b/drivers/gpu/drm/i915/gt/uc/selftest_guc.c index fb0e4a7bd8ca..d3327b802b76 100644 --- a/drivers/gpu/drm/i915/gt/uc/selftest_guc.c +++ b/drivers/gpu/drm/i915/gt/uc/selftest_guc.c @@ -3,8 +3,21 @@ * Copyright �� 2021 Intel Corporation */ +#include "selftests/igt_spinner.h" #include "selftests/intel_scheduler_helpers.h" +static int request_add_spin(struct i915_request *rq, struct igt_spinner *spin) +{ + int err = 0; + + i915_request_get(rq); + i915_request_add(rq); + if (spin && !igt_wait_for_spinner(spin, rq)) + err = -ETIMEDOUT; + + return err; +} + static struct i915_request *nop_user_request(struct intel_context *ce, struct i915_request *from) { @@ -110,12 +123,172 @@ err: return ret; } +/* + * intel_guc_steal_guc_ids - Test to exhaust all guc_ids and then steal one + * + * This test creates a spinner which is used to block all subsequent submissions + * until it completes. Next, a loop creates a context and a NOP request each + * iteration until the guc_ids are exhausted (request creation returns -EAGAIN). + * The spinner is ended, unblocking all requests created in the loop. At this + * point all guc_ids are exhausted but are available to steal. Try to create + * another request which should successfully steal a guc_id. Wait on last + * request to complete, idle GPU, verify a guc_id was stolen via a counter, and + * exit the test. Test also artificially reduces the number of guc_ids so the + * test runs in a timely manner. + */ +static int intel_guc_steal_guc_ids(void *arg) +{ + struct intel_gt *gt = arg; + struct intel_guc *guc = >->uc.guc; + int ret, sv, context_index = 0; + intel_wakeref_t wakeref; + struct intel_engine_cs *engine; + struct intel_context **ce; + struct igt_spinner spin; + struct i915_request *spin_rq = NULL, *rq, *last = NULL; + int number_guc_id_stolen = guc->number_guc_id_stolen; + + ce = kzalloc(sizeof(*ce) * GUC_MAX_LRC_DESCRIPTORS, GFP_KERNEL); + if (!ce) { + pr_err("Context array allocation failed\n"); + return -ENOMEM; + } + + wakeref = intel_runtime_pm_get(gt->uncore->rpm); + engine = intel_selftest_find_any_engine(gt); + sv = guc->submission_state.num_guc_ids; + guc->submission_state.num_guc_ids = 4096; + + /* Create spinner to block requests in below loop */ + ce[context_index] = intel_context_create(engine); + if (IS_ERR(ce[context_index])) { + ret = PTR_ERR(ce[context_index]); + ce[context_index] = NULL; + pr_err("Failed to create context: %d\n", ret); + goto err_wakeref; + } + ret = igt_spinner_init(&spin, engine->gt); + if (ret) { + pr_err("Failed to create spinner: %d\n", ret); + goto err_contexts; + } + spin_rq = igt_spinner_create_request(&spin, ce[context_index], + MI_ARB_CHECK); + if (IS_ERR(spin_rq)) { + ret = PTR_ERR(spin_rq); + pr_err("Failed to create spinner request: %d\n", ret); + goto err_contexts; + } + ret = request_add_spin(spin_rq, &spin); + if (ret) { + pr_err("Failed to add Spinner request: %d\n", ret); + goto err_spin_rq; + } + + /* Use all guc_ids */ + while (ret != -EAGAIN) { + ce[++context_index] = intel_context_create(engine); + if (IS_ERR(ce[context_index])) { + ret = PTR_ERR(ce[context_index--]); + ce[context_index] = NULL; + pr_err("Failed to create context: %d\n", ret); + goto err_spin_rq; + } + + rq = nop_user_request(ce[context_index], spin_rq); + if (IS_ERR(rq)) { + ret = PTR_ERR(rq); + rq = NULL; + if (ret != -EAGAIN) { + pr_err("Failed to create request, %d: %d\n", + context_index, ret); + goto err_spin_rq; + } + } else { + if (last) + i915_request_put(last); + last = rq; + } + } + + /* Release blocked requests */ + igt_spinner_end(&spin); + ret = intel_selftest_wait_for_rq(spin_rq); + if (ret) { + pr_err("Spin request failed to complete: %d\n", ret); + i915_request_put(last); + goto err_spin_rq; + } + i915_request_put(spin_rq); + igt_spinner_fini(&spin); + spin_rq = NULL; + + /* Wait for last request */ + ret = i915_request_wait(last, 0, HZ * 30); + i915_request_put(last); + if (ret < 0) { + pr_err("Last request failed to complete: %d\n", ret); + goto err_spin_rq; + } + + /* Try to steal guc_id */ + rq = nop_user_request(ce[context_index], NULL); + if (IS_ERR(rq)) { + ret = PTR_ERR(rq); + pr_err("Failed to steal guc_id, %d: %d\n", context_index, ret); + goto err_spin_rq; + } + + /* Wait for request with stolen guc_id */ + ret = i915_request_wait(rq, 0, HZ); + i915_request_put(rq); + if (ret < 0) { + pr_err("Request with stolen guc_id failed to complete: %d\n", + ret); + goto err_spin_rq; + } + + /* Wait for idle */ + ret = intel_gt_wait_for_idle(gt, HZ * 30); + if (ret < 0) { + pr_err("GT failed to idle: %d\n", ret); + goto err_spin_rq; + } + + /* Verify a guc_id was stolen */ + if (guc->number_guc_id_stolen == number_guc_id_stolen) { + pr_err("No guc_id was stolen"); + ret = -EINVAL; + } else { + ret = 0; + } + +err_spin_rq: + if (spin_rq) { + igt_spinner_end(&spin); + intel_selftest_wait_for_rq(spin_rq); + i915_request_put(spin_rq); + igt_spinner_fini(&spin); + intel_gt_wait_for_idle(gt, HZ * 30); + } +err_contexts: + for (; context_index >= 0 && ce[context_index]; --context_index) + intel_context_put(ce[context_index]); +err_wakeref: + intel_runtime_pm_put(gt->uncore->rpm, wakeref); + kfree(ce); + guc->submission_state.num_guc_ids = sv; + + return ret; +} + int intel_guc_live_selftests(struct drm_i915_private *i915) { static const struct i915_subtest tests[] = { SUBTEST(intel_guc_scrub_ctbs), + SUBTEST(intel_guc_steal_guc_ids), }; - struct intel_gt *gt = &i915->gt; + struct intel_gt *gt = to_gt(i915); if (intel_gt_is_wedged(gt)) return 0; diff --git a/drivers/gpu/drm/i915/gt/uc/selftest_guc_multi_lrc.c b/drivers/gpu/drm/i915/gt/uc/selftest_guc_multi_lrc.c index 50953c8e8b53..1297ddbf7f88 100644 --- a/drivers/gpu/drm/i915/gt/uc/selftest_guc_multi_lrc.c +++ b/drivers/gpu/drm/i915/gt/uc/selftest_guc_multi_lrc.c @@ -167,7 +167,7 @@ int intel_guc_multi_lrc_live_selftests(struct drm_i915_private *i915) static const struct i915_subtest tests[] = { SUBTEST(intel_guc_multi_lrc_basic), }; - struct intel_gt *gt = &i915->gt; + struct intel_gt *gt = to_gt(i915); if (intel_gt_is_wedged(gt)) return 0; diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.c b/drivers/gpu/drm/i915/gvt/fb_decoder.c index 11a8baba6822..9ec064199364 100644 --- a/drivers/gpu/drm/i915/gvt/fb_decoder.c +++ b/drivers/gpu/drm/i915/gvt/fb_decoder.c @@ -427,7 +427,7 @@ int intel_vgpu_decode_sprite_plane(struct intel_vgpu *vgpu, plane->tiled = !!(val & SPRITE_TILED); color_order = !!(val & SPRITE_RGB_ORDER_RGBX); - yuv_order = (val & SPRITE_YUV_BYTE_ORDER_MASK) >> + yuv_order = (val & SPRITE_YUV_ORDER_MASK) >> _SPRITE_YUV_ORDER_SHIFT; fmt = (val & SPRITE_PIXFORMAT_MASK) >> _SPRITE_FMT_SHIFT; diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 53d0cb327539..99d1781fa5f0 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -446,17 +446,17 @@ static bool gen8_gtt_test_present(struct intel_gvt_gtt_entry *e) || e->type == GTT_TYPE_PPGTT_ROOT_L4_ENTRY) return (e->val64 != 0); else - return (e->val64 & _PAGE_PRESENT); + return (e->val64 & GEN8_PAGE_PRESENT); } static void gtt_entry_clear_present(struct intel_gvt_gtt_entry *e) { - e->val64 &= ~_PAGE_PRESENT; + e->val64 &= ~GEN8_PAGE_PRESENT; } static void gtt_entry_set_present(struct intel_gvt_gtt_entry *e) { - e->val64 |= _PAGE_PRESENT; + e->val64 |= GEN8_PAGE_PRESENT; } static bool gen8_gtt_test_64k_splited(struct intel_gvt_gtt_entry *e) @@ -2439,7 +2439,7 @@ static int alloc_scratch_pages(struct intel_vgpu *vgpu, /* The entry parameters like present/writeable/cache type * set to the same as i915's scratch page tree. */ - se.val64 |= _PAGE_PRESENT | _PAGE_RW; + se.val64 |= GEN8_PAGE_PRESENT | GEN8_PAGE_RW; if (type == GTT_TYPE_PPGTT_PDE_PT) se.val64 |= PPAT_CACHED; @@ -2896,7 +2896,7 @@ void intel_gvt_restore_ggtt(struct intel_gvt *gvt) offset = vgpu_aperture_gmadr_base(vgpu) >> PAGE_SHIFT; for (idx = 0; idx < num_low; idx++) { pte = mm->ggtt_mm.host_ggtt_aperture[idx]; - if (pte & _PAGE_PRESENT) + if (pte & GEN8_PAGE_PRESENT) write_pte64(vgpu->gvt->gt->ggtt, offset + idx, pte); } @@ -2904,7 +2904,7 @@ void intel_gvt_restore_ggtt(struct intel_gvt *gvt) offset = vgpu_hidden_gmadr_base(vgpu) >> PAGE_SHIFT; for (idx = 0; idx < num_hi; idx++) { pte = mm->ggtt_mm.host_ggtt_hidden[idx]; - if (pte & _PAGE_PRESENT) + if (pte & GEN8_PAGE_PRESENT) write_pte64(vgpu->gvt->gt->ggtt, offset + idx, pte); } } diff --git a/drivers/gpu/drm/i915/gvt/gvt.c b/drivers/gpu/drm/i915/gvt/gvt.c index cbac409f6c8a..f0b69e4dcb52 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.c +++ b/drivers/gpu/drm/i915/gvt/gvt.c @@ -205,7 +205,7 @@ int intel_gvt_init_device(struct drm_i915_private *i915) spin_lock_init(&gvt->scheduler.mmio_context_lock); mutex_init(&gvt->lock); mutex_init(&gvt->sched_lock); - gvt->gt = &i915->gt; + gvt->gt = to_gt(i915); i915->gvt = gvt; init_device_info(gvt); diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 6c804102528b..42a0c9ae0a73 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -1386,7 +1386,7 @@ int intel_vgpu_setup_submission(struct intel_vgpu *vgpu) enum intel_engine_id i; int ret; - ppgtt = i915_ppgtt_create(&i915->gt, I915_BO_ALLOC_PM_EARLY); + ppgtt = i915_ppgtt_create(to_gt(i915), I915_BO_ALLOC_PM_EARLY); if (IS_ERR(ppgtt)) return PTR_ERR(ppgtt); diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c index 3103c1e1fd14..ee2b3a375362 100644 --- a/drivers/gpu/drm/i915/i915_active.c +++ b/drivers/gpu/drm/i915/i915_active.c @@ -426,8 +426,9 @@ replace_barrier(struct i915_active *ref, struct i915_active_fence *active) return true; } -int i915_active_ref(struct i915_active *ref, u64 idx, struct dma_fence *fence) +int i915_active_add_request(struct i915_active *ref, struct i915_request *rq) { + struct dma_fence *fence = &rq->fence; struct i915_active_fence *active; int err; @@ -436,7 +437,7 @@ int i915_active_ref(struct i915_active *ref, u64 idx, struct dma_fence *fence) if (err) return err; - active = active_instance(ref, idx); + active = active_instance(ref, i915_request_timeline(rq)->fence_context); if (!active) { err = -ENOMEM; goto out; @@ -477,29 +478,6 @@ __i915_active_set_fence(struct i915_active *ref, return prev; } -static struct i915_active_fence * -__active_fence(struct i915_active *ref, u64 idx) -{ - struct active_node *it; - - it = __active_lookup(ref, idx); - if (unlikely(!it)) { /* Contention with parallel tree builders! */ - spin_lock_irq(&ref->tree_lock); - it = __active_lookup(ref, idx); - spin_unlock_irq(&ref->tree_lock); - } - GEM_BUG_ON(!it); /* slot must be preallocated */ - - return &it->base; -} - -struct dma_fence * -__i915_active_ref(struct i915_active *ref, u64 idx, struct dma_fence *fence) -{ - /* Only valid while active, see i915_active_acquire_for_context() */ - return __i915_active_set_fence(ref, __active_fence(ref, idx), fence); -} - struct dma_fence * i915_active_set_exclusive(struct i915_active *ref, struct dma_fence *f) { diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h index 5fcdb0e2bc9e..7eb44132183a 100644 --- a/drivers/gpu/drm/i915/i915_active.h +++ b/drivers/gpu/drm/i915/i915_active.h @@ -164,26 +164,11 @@ void __i915_active_init(struct i915_active *ref, __i915_active_init(ref, active, retire, flags, &__mkey, &__wkey); \ } while (0) -struct dma_fence * -__i915_active_ref(struct i915_active *ref, u64 idx, struct dma_fence *fence); -int i915_active_ref(struct i915_active *ref, u64 idx, struct dma_fence *fence); - -static inline int -i915_active_add_request(struct i915_active *ref, struct i915_request *rq) -{ - return i915_active_ref(ref, - i915_request_timeline(rq)->fence_context, - &rq->fence); -} +int i915_active_add_request(struct i915_active *ref, struct i915_request *rq); struct dma_fence * i915_active_set_exclusive(struct i915_active *ref, struct dma_fence *f); -static inline bool i915_active_has_exclusive(struct i915_active *ref) -{ - return rcu_access_pointer(ref->excl.fence); -} - int __i915_active_wait(struct i915_active *ref, int state); static inline int i915_active_wait(struct i915_active *ref) { diff --git a/drivers/gpu/drm/i915/i915_active_types.h b/drivers/gpu/drm/i915/i915_active_types.h index c149f348a972..b02a78ac87db 100644 --- a/drivers/gpu/drm/i915/i915_active_types.h +++ b/drivers/gpu/drm/i915/i915_active_types.h @@ -15,8 +15,6 @@ #include <linux/rcupdate.h> #include <linux/workqueue.h> -#include "i915_utils.h" - struct i915_active_fence { struct dma_fence __rcu *fence; struct dma_fence_cb cb; diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index fe638b5da7c0..e0e052cdf8b8 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -48,7 +48,6 @@ #include "i915_debugfs_params.h" #include "i915_irq.h" #include "i915_scheduler.h" -#include "i915_trace.h" #include "intel_pm.h" static inline struct drm_i915_private *node_to_i915(struct drm_info_node *node) @@ -65,7 +64,8 @@ static int i915_capabilities(struct seq_file *m, void *data) intel_device_info_print_static(INTEL_INFO(i915), &p); intel_device_info_print_runtime(RUNTIME_INFO(i915), &p); - intel_gt_info_print(&i915->gt.info, &p); + i915_print_iommu_status(i915, &p); + intel_gt_info_print(&to_gt(i915)->info, &p); intel_driver_caps_print(&i915->caps, &p); kernel_param_lock(THIS_MODULE); @@ -293,7 +293,7 @@ static int i915_gpu_info_open(struct inode *inode, struct file *file) gpu = NULL; with_intel_runtime_pm(&i915->runtime_pm, wakeref) - gpu = i915_gpu_coredump(&i915->gt, ALL_ENGINES); + gpu = i915_gpu_coredump(to_gt(i915), ALL_ENGINES); if (IS_ERR(gpu)) return PTR_ERR(gpu); @@ -351,7 +351,7 @@ static const struct file_operations i915_error_state_fops = { static int i915_frequency_info(struct seq_file *m, void *unused) { struct drm_i915_private *i915 = node_to_i915(m->private); - struct intel_gt *gt = &i915->gt; + struct intel_gt *gt = to_gt(i915); struct drm_printer p = drm_seq_file_printer(m); intel_gt_pm_frequency_dump(gt, &p); @@ -439,11 +439,11 @@ static int i915_swizzle_info(struct seq_file *m, void *data) static int i915_rps_boost_info(struct seq_file *m, void *data) { struct drm_i915_private *dev_priv = node_to_i915(m->private); - struct intel_rps *rps = &dev_priv->gt.rps; + struct intel_rps *rps = &to_gt(dev_priv)->rps; seq_printf(m, "RPS enabled? %s\n", yesno(intel_rps_is_enabled(rps))); seq_printf(m, "RPS active? %s\n", yesno(intel_rps_is_active(rps))); - seq_printf(m, "GPU busy? %s\n", yesno(dev_priv->gt.awake)); + seq_printf(m, "GPU busy? %s\n", yesno(to_gt(dev_priv)->awake)); seq_printf(m, "Boosts outstanding? %d\n", atomic_read(&rps->num_waiters)); seq_printf(m, "Interactive? %d\n", READ_ONCE(rps->power.interactive)); @@ -476,7 +476,7 @@ static int i915_runtime_pm_status(struct seq_file *m, void *unused) seq_printf(m, "Runtime power status: %s\n", enableddisabled(!dev_priv->power_domains.init_wakeref)); - seq_printf(m, "GPU idle: %s\n", yesno(!dev_priv->gt.awake)); + seq_printf(m, "GPU idle: %s\n", yesno(!to_gt(dev_priv)->awake)); seq_printf(m, "IRQs disabled: %s\n", yesno(!intel_irqs_enabled(dev_priv))); #ifdef CONFIG_PM @@ -508,18 +508,18 @@ static int i915_engine_info(struct seq_file *m, void *unused) wakeref = intel_runtime_pm_get(&i915->runtime_pm); seq_printf(m, "GT awake? %s [%d], %llums\n", - yesno(i915->gt.awake), - atomic_read(&i915->gt.wakeref.count), - ktime_to_ms(intel_gt_get_awake_time(&i915->gt))); + yesno(to_gt(i915)->awake), + atomic_read(&to_gt(i915)->wakeref.count), + ktime_to_ms(intel_gt_get_awake_time(to_gt(i915)))); seq_printf(m, "CS timestamp frequency: %u Hz, %d ns\n", - i915->gt.clock_frequency, - i915->gt.clock_period_ns); + to_gt(i915)->clock_frequency, + to_gt(i915)->clock_period_ns); p = drm_seq_file_printer(m); for_each_uabi_engine(engine, i915) intel_engine_dump(engine, &p, "%s\n", engine->name); - intel_gt_show_timelines(&i915->gt, &p, i915_request_show_with_schedule); + intel_gt_show_timelines(to_gt(i915), &p, i915_request_show_with_schedule); intel_runtime_pm_put(&i915->runtime_pm, wakeref); @@ -558,14 +558,14 @@ static int i915_wedged_get(void *data, u64 *val) { struct drm_i915_private *i915 = data; - return intel_gt_debugfs_reset_show(&i915->gt, val); + return intel_gt_debugfs_reset_show(to_gt(i915), val); } static int i915_wedged_set(void *data, u64 val) { struct drm_i915_private *i915 = data; - return intel_gt_debugfs_reset_store(&i915->gt, val); + return intel_gt_debugfs_reset_store(to_gt(i915), val); } DEFINE_SIMPLE_ATTRIBUTE(i915_wedged_fops, @@ -581,7 +581,7 @@ i915_perf_noa_delay_set(void *data, u64 val) * This would lead to infinite waits as we're doing timestamp * difference on the CS with only 32bits. */ - if (intel_gt_ns_to_clock_interval(&i915->gt, val) > U32_MAX) + if (intel_gt_ns_to_clock_interval(to_gt(i915), val) > U32_MAX) return -EINVAL; atomic64_set(&i915->perf.noa_programming_delay, val); @@ -666,16 +666,18 @@ static int i915_drop_caches_set(void *data, u64 val) { struct drm_i915_private *i915 = data; + unsigned int flags; int ret; DRM_DEBUG("Dropping caches: 0x%08llx [0x%08llx]\n", val, val & DROP_ALL); - ret = gt_drop_caches(&i915->gt, val); + ret = gt_drop_caches(to_gt(i915), val); if (ret) return ret; fs_reclaim_acquire(GFP_KERNEL); + flags = memalloc_noreclaim_save(); if (val & DROP_BOUND) i915_gem_shrink(NULL, i915, LONG_MAX, NULL, I915_SHRINK_BOUND); @@ -684,6 +686,7 @@ i915_drop_caches_set(void *data, u64 val) if (val & DROP_SHRINK_ALL) i915_gem_shrink_all(i915); + memalloc_noreclaim_restore(flags); fs_reclaim_release(GFP_KERNEL); if (val & DROP_RCU) @@ -702,7 +705,7 @@ DEFINE_SIMPLE_ATTRIBUTE(i915_drop_caches_fops, static int i915_sseu_status(struct seq_file *m, void *unused) { struct drm_i915_private *i915 = node_to_i915(m->private); - struct intel_gt *gt = &i915->gt; + struct intel_gt *gt = to_gt(i915); return intel_sseu_status(m, gt); } @@ -711,14 +714,14 @@ static int i915_forcewake_open(struct inode *inode, struct file *file) { struct drm_i915_private *i915 = inode->i_private; - return intel_gt_pm_debugfs_forcewake_user_open(&i915->gt); + return intel_gt_pm_debugfs_forcewake_user_open(to_gt(i915)); } static int i915_forcewake_release(struct inode *inode, struct file *file) { struct drm_i915_private *i915 = inode->i_private; - return intel_gt_pm_debugfs_forcewake_user_release(&i915->gt); + return intel_gt_pm_debugfs_forcewake_user_release(to_gt(i915)); } static const struct file_operations i915_forcewake_fops = { diff --git a/drivers/gpu/drm/i915/i915_debugfs_params.c b/drivers/gpu/drm/i915/i915_debugfs_params.c index 20424275d41e..783c8676eee2 100644 --- a/drivers/gpu/drm/i915/i915_debugfs_params.c +++ b/drivers/gpu/drm/i915/i915_debugfs_params.c @@ -40,8 +40,8 @@ static int notify_guc(struct drm_i915_private *i915) { int ret = 0; - if (intel_uc_uses_guc_submission(&i915->gt.uc)) - ret = intel_guc_global_policies_update(&i915->gt.uc.guc); + if (intel_uc_uses_guc_submission(&to_gt(i915)->uc)) + ret = intel_guc_global_policies_update(&to_gt(i915)->uc.guc); return ret; } diff --git a/drivers/gpu/drm/i915/i915_deps.c b/drivers/gpu/drm/i915/i915_deps.c new file mode 100644 index 000000000000..999210b37325 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_deps.c @@ -0,0 +1,237 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2021 Intel Corporation + */ + +#include <linux/dma-fence.h> +#include <linux/slab.h> + +#include <drm/ttm/ttm_bo_api.h> + +#include "i915_deps.h" + +/** + * DOC: Set of utilities to dynamically collect dependencies into a + * structure which is fed into the GT migration code. + * + * Once we can do async unbinding, this is also needed to coalesce + * the migration fence with the unbind fences if these are coalesced + * post-migration. + * + * While collecting the individual dependencies, we store the refcounted + * struct dma_fence pointers in a realloc-managed pointer array, since + * that can be easily fed into a dma_fence_array. Other options are + * available, like for example an xarray for similarity with drm/sched. + * Can be changed easily if needed. + * + * A struct i915_deps need to be initialized using i915_deps_init(). + * If i915_deps_add_dependency() or i915_deps_add_resv() return an + * error code they will internally call i915_deps_fini(), which frees + * all internal references and allocations. + */ + +/* Min number of fence pointers in the array when an allocation occurs. */ +#define I915_DEPS_MIN_ALLOC_CHUNK 8U + +static void i915_deps_reset_fences(struct i915_deps *deps) +{ + if (deps->fences != &deps->single) + kfree(deps->fences); + deps->num_deps = 0; + deps->fences_size = 1; + deps->fences = &deps->single; +} + +/** + * i915_deps_init - Initialize an i915_deps structure + * @deps: Pointer to the i915_deps structure to initialize. + * @gfp: The allocation mode for subsequenst allocations. + */ +void i915_deps_init(struct i915_deps *deps, gfp_t gfp) +{ + deps->fences = NULL; + deps->gfp = gfp; + i915_deps_reset_fences(deps); +} + +/** + * i915_deps_fini - Finalize an i915_deps structure + * @deps: Pointer to the i915_deps structure to finalize. + * + * This function drops all fence references taken, conditionally frees and + * then resets the fences array. + */ +void i915_deps_fini(struct i915_deps *deps) +{ + unsigned int i; + + for (i = 0; i < deps->num_deps; ++i) + dma_fence_put(deps->fences[i]); + + if (deps->fences != &deps->single) + kfree(deps->fences); +} + +static int i915_deps_grow(struct i915_deps *deps, struct dma_fence *fence, + const struct ttm_operation_ctx *ctx) +{ + int ret; + + if (deps->num_deps >= deps->fences_size) { + unsigned int new_size = 2 * deps->fences_size; + struct dma_fence **new_fences; + + new_size = max(new_size, I915_DEPS_MIN_ALLOC_CHUNK); + new_fences = kmalloc_array(new_size, sizeof(*new_fences), deps->gfp); + if (!new_fences) + goto sync; + + memcpy(new_fences, deps->fences, + deps->fences_size * sizeof(*new_fences)); + swap(new_fences, deps->fences); + if (new_fences != &deps->single) + kfree(new_fences); + deps->fences_size = new_size; + } + deps->fences[deps->num_deps++] = dma_fence_get(fence); + return 0; + +sync: + if (ctx->no_wait_gpu && !dma_fence_is_signaled(fence)) { + ret = -EBUSY; + goto unref; + } + + ret = dma_fence_wait(fence, ctx->interruptible); + if (ret) + goto unref; + + ret = fence->error; + if (ret) + goto unref; + + return 0; + +unref: + i915_deps_fini(deps); + return ret; +} + +/** + * i915_deps_sync - Wait for all the fences in the dependency collection + * @deps: Pointer to the i915_deps structure the fences of which to wait for. + * @ctx: Pointer to a struct ttm_operation_ctx indicating how the waits + * should be performed. + * + * This function waits for fences in the dependency collection. If it + * encounters an error during the wait or a fence error, the wait for + * further fences is aborted and the error returned. + * + * Return: Zero if successful, Negative error code on error. + */ +int i915_deps_sync(const struct i915_deps *deps, const struct ttm_operation_ctx *ctx) +{ + struct dma_fence **fences = deps->fences; + unsigned int i; + int ret = 0; + + for (i = 0; i < deps->num_deps; ++i, ++fences) { + if (ctx->no_wait_gpu && !dma_fence_is_signaled(*fences)) { + ret = -EBUSY; + break; + } + + ret = dma_fence_wait(*fences, ctx->interruptible); + if (!ret) + ret = (*fences)->error; + if (ret) + break; + } + + return ret; +} + +/** + * i915_deps_add_dependency - Add a fence to the dependency collection + * @deps: Pointer to the i915_deps structure a fence is to be added to. + * @fence: The fence to add. + * @ctx: Pointer to a struct ttm_operation_ctx indicating how waits are to + * be performed if waiting. + * + * Adds a fence to the dependency collection, and takes a reference on it. + * If the fence context is not zero and there was a later fence from the + * same fence context already added, then the fence is not added to the + * dependency collection. If the fence context is not zero and there was + * an earlier fence already added, then the fence will replace the older + * fence from the same context and the reference on the earlier fence will + * be dropped. + * If there is a failure to allocate memory to accommodate the new fence to + * be added, the new fence will instead be waited for and an error may + * be returned; depending on the value of @ctx, or if there was a fence + * error. If an error was returned, the dependency collection will be + * finalized and all fence reference dropped. + * + * Return: 0 if success. Negative error code on error. + */ +int i915_deps_add_dependency(struct i915_deps *deps, + struct dma_fence *fence, + const struct ttm_operation_ctx *ctx) +{ + unsigned int i; + int ret; + + if (!fence) + return 0; + + if (dma_fence_is_signaled(fence)) { + ret = fence->error; + if (ret) + i915_deps_fini(deps); + return ret; + } + + for (i = 0; i < deps->num_deps; ++i) { + struct dma_fence *entry = deps->fences[i]; + + if (!entry->context || entry->context != fence->context) + continue; + + if (dma_fence_is_later(fence, entry)) { + dma_fence_put(entry); + deps->fences[i] = dma_fence_get(fence); + } + + return 0; + } + + return i915_deps_grow(deps, fence, ctx); +} + +/** + * i915_deps_add_resv - Add the fences of a reservation object to a dependency + * collection. + * @deps: Pointer to the i915_deps structure a fence is to be added to. + * @resv: The reservation object, then fences of which to add. + * @ctx: Pointer to a struct ttm_operation_ctx indicating how waits are to + * be performed if waiting. + * + * Calls i915_deps_add_depencency() on the indicated fences of @resv. + * + * Return: Zero on success. Negative error code on error. + */ +int i915_deps_add_resv(struct i915_deps *deps, struct dma_resv *resv, + const struct ttm_operation_ctx *ctx) +{ + struct dma_resv_iter iter; + struct dma_fence *fence; + + dma_resv_assert_held(resv); + dma_resv_for_each_fence(&iter, resv, true, fence) { + int ret = i915_deps_add_dependency(deps, fence, ctx); + + if (ret) + return ret; + } + + return 0; +} diff --git a/drivers/gpu/drm/i915/i915_deps.h b/drivers/gpu/drm/i915/i915_deps.h new file mode 100644 index 000000000000..d76c0106c910 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_deps.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef _I915_DEPS_H_ +#define _I915_DEPS_H_ + +#include <linux/types.h> + +struct ttm_operation_ctx; +struct dma_fence; +struct dma_resv; + +/** + * struct i915_deps - Collect dependencies into a single dma-fence + * @single: Storage for pointer if the collection is a single fence. + * @fences: Allocated array of fence pointers if more than a single fence; + * otherwise points to the address of @single. + * @num_deps: Current number of dependency fences. + * @fences_size: Size of the @fences array in number of pointers. + * @gfp: Allocation mode. + */ +struct i915_deps { + struct dma_fence *single; + struct dma_fence **fences; + unsigned int num_deps; + unsigned int fences_size; + gfp_t gfp; +}; + +void i915_deps_init(struct i915_deps *deps, gfp_t gfp); + +void i915_deps_fini(struct i915_deps *deps); + +int i915_deps_add_dependency(struct i915_deps *deps, + struct dma_fence *fence, + const struct ttm_operation_ctx *ctx); + +int i915_deps_add_resv(struct i915_deps *deps, struct dma_resv *resv, + const struct ttm_operation_ctx *ctx); + +int i915_deps_sync(const struct i915_deps *deps, + const struct ttm_operation_ctx *ctx); +#endif diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_driver.c index b18a250e5d2e..95174938b160 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_driver.c @@ -29,8 +29,8 @@ #include <linux/acpi.h> #include <linux/device.h> -#include <linux/oom.h> #include <linux/module.h> +#include <linux/oom.h> #include <linux/pci.h> #include <linux/pm.h> #include <linux/pm_runtime.h> @@ -48,12 +48,14 @@ #include "display/intel_acpi.h" #include "display/intel_bw.h" #include "display/intel_cdclk.h" -#include "display/intel_dmc.h" #include "display/intel_display_types.h" +#include "display/intel_dmc.h" #include "display/intel_dp.h" +#include "display/intel_dpt.h" #include "display/intel_fbdev.h" #include "display/intel_hotplug.h" #include "display/intel_overlay.h" +#include "display/intel_pch_refclk.h" #include "display/intel_pipe_crc.h" #include "display/intel_pps.h" #include "display/intel_sprite.h" @@ -70,6 +72,7 @@ #include "pxp/intel_pxp_pm.h" #include "i915_debugfs.h" +#include "i915_driver.h" #include "i915_drv.h" #include "i915_ioc32.h" #include "i915_irq.h" @@ -79,7 +82,6 @@ #include "i915_suspend.h" #include "i915_switcheroo.h" #include "i915_sysfs.h" -#include "i915_trace.h" #include "i915_vgpu.h" #include "intel_dram.h" #include "intel_gvt.h" @@ -89,7 +91,7 @@ #include "intel_region_ttm.h" #include "vlv_suspend.h" -static const struct drm_driver driver; +static const struct drm_driver i915_drm_driver; static int i915_get_bridge_dev(struct drm_i915_private *dev_priv) { @@ -289,7 +291,7 @@ static void intel_detect_preproduction_hw(struct drm_i915_private *dev_priv) static void sanitize_gpu(struct drm_i915_private *i915) { if (!INTEL_INFO(i915)->gpu_reset_clobbers_display) - __intel_gt_reset(&i915->gt, ALL_ENGINES); + __intel_gt_reset(to_gt(i915), ALL_ENGINES); } /** @@ -312,8 +314,9 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv) intel_device_info_subplatform_init(dev_priv); intel_step_init(dev_priv); + intel_gt_init_early(to_gt(dev_priv), dev_priv); intel_uncore_mmio_debug_init_early(&dev_priv->mmio_debug); - intel_uncore_init_early(&dev_priv->uncore, dev_priv); + intel_uncore_init_early(&dev_priv->uncore, to_gt(dev_priv)); spin_lock_init(&dev_priv->irq_lock); spin_lock_init(&dev_priv->gpu_error.lock); @@ -322,7 +325,7 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv) mutex_init(&dev_priv->sb_lock); cpu_latency_qos_add_request(&dev_priv->sb_qos, PM_QOS_DEFAULT_VALUE); - mutex_init(&dev_priv->av_mutex); + mutex_init(&dev_priv->audio.mutex); mutex_init(&dev_priv->wm.wm_mutex); mutex_init(&dev_priv->pps_mutex); mutex_init(&dev_priv->hdcp_comp_mutex); @@ -344,7 +347,7 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv) intel_wopcm_init_early(&dev_priv->wopcm); - intel_gt_init_early(&dev_priv->gt, dev_priv); + __intel_gt_init_early(to_gt(dev_priv), dev_priv); i915_gem_init_early(dev_priv); @@ -365,7 +368,7 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv) err_gem: i915_gem_cleanup_early(dev_priv); - intel_gt_driver_late_release(&dev_priv->gt); + intel_gt_driver_late_release(to_gt(dev_priv)); intel_region_ttm_device_fini(dev_priv); err_ttm: vlv_suspend_cleanup(dev_priv); @@ -384,7 +387,7 @@ static void i915_driver_late_release(struct drm_i915_private *dev_priv) intel_irq_fini(dev_priv); intel_power_domains_cleanup(dev_priv); i915_gem_cleanup_early(dev_priv); - intel_gt_driver_late_release(&dev_priv->gt); + intel_gt_driver_late_release(to_gt(dev_priv)); intel_region_ttm_device_fini(dev_priv); vlv_suspend_cleanup(dev_priv); i915_workqueues_cleanup(dev_priv); @@ -415,15 +418,19 @@ static int i915_driver_mmio_probe(struct drm_i915_private *dev_priv) if (ret < 0) return ret; - ret = intel_uncore_init_mmio(&dev_priv->uncore); + ret = intel_uncore_setup_mmio(&dev_priv->uncore); if (ret < 0) goto err_bridge; + ret = intel_uncore_init_mmio(&dev_priv->uncore); + if (ret) + goto err_mmio; + /* Try to make sure MCHBAR is enabled before poking at it */ intel_setup_mchbar(dev_priv); intel_device_info_runtime_init(dev_priv); - ret = intel_gt_init_mmio(&dev_priv->gt); + ret = intel_gt_init_mmio(to_gt(dev_priv)); if (ret) goto err_uncore; @@ -435,6 +442,8 @@ static int i915_driver_mmio_probe(struct drm_i915_private *dev_priv) err_uncore: intel_teardown_mchbar(dev_priv); intel_uncore_fini_mmio(&dev_priv->uncore); +err_mmio: + intel_uncore_cleanup_mmio(&dev_priv->uncore); err_bridge: pci_dev_put(dev_priv->bridge_dev); @@ -449,6 +458,7 @@ static void i915_driver_mmio_release(struct drm_i915_private *dev_priv) { intel_teardown_mchbar(dev_priv); intel_uncore_fini_mmio(&dev_priv->uncore); + intel_uncore_cleanup_mmio(&dev_priv->uncore); pci_dev_put(dev_priv->bridge_dev); } @@ -577,9 +587,9 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) if (ret) goto err_ggtt; - intel_gt_init_hw_early(&dev_priv->gt, &dev_priv->ggtt); + intel_gt_init_hw_early(to_gt(dev_priv), &dev_priv->ggtt); - ret = intel_gt_probe_lmem(&dev_priv->gt); + ret = intel_gt_probe_lmem(to_gt(dev_priv)); if (ret) goto err_mem_regions; @@ -692,7 +702,7 @@ static void i915_driver_register(struct drm_i915_private *dev_priv) /* Depends on sysfs having been initialized */ i915_perf_register(dev_priv); - intel_gt_driver_register(&dev_priv->gt); + intel_gt_driver_register(to_gt(dev_priv)); intel_display_driver_register(dev_priv); @@ -720,7 +730,7 @@ static void i915_driver_unregister(struct drm_i915_private *dev_priv) intel_display_driver_unregister(dev_priv); - intel_gt_driver_unregister(&dev_priv->gt); + intel_gt_driver_unregister(to_gt(dev_priv)); i915_perf_unregister(dev_priv); i915_pmu_unregister(dev_priv); @@ -731,6 +741,12 @@ static void i915_driver_unregister(struct drm_i915_private *dev_priv) i915_gem_driver_unregister(dev_priv); } +void +i915_print_iommu_status(struct drm_i915_private *i915, struct drm_printer *p) +{ + drm_printf(p, "iommu: %s\n", enableddisabled(intel_vtd_active(i915))); +} + static void i915_welcome_messages(struct drm_i915_private *dev_priv) { if (drm_debug_enabled(DRM_UT_DRIVER)) { @@ -746,7 +762,8 @@ static void i915_welcome_messages(struct drm_i915_private *dev_priv) intel_device_info_print_static(INTEL_INFO(dev_priv), &p); intel_device_info_print_runtime(RUNTIME_INFO(dev_priv), &p); - intel_gt_info_print(&dev_priv->gt.info, &p); + i915_print_iommu_status(dev_priv, &p); + intel_gt_info_print(&to_gt(dev_priv)->info, &p); } if (IS_ENABLED(CONFIG_DRM_I915_DEBUG)) @@ -766,7 +783,7 @@ i915_driver_create(struct pci_dev *pdev, const struct pci_device_id *ent) struct intel_device_info *device_info; struct drm_i915_private *i915; - i915 = devm_drm_dev_alloc(&pdev->dev, &driver, + i915 = devm_drm_dev_alloc(&pdev->dev, &i915_drm_driver, struct drm_i915_private, drm); if (IS_ERR(i915)) return i915; @@ -807,7 +824,7 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return PTR_ERR(i915); /* Disable nuclear pageflip by default on pre-ILK */ - if (!i915->params.nuclear_pageflip && match_info->graphics_ver < 5) + if (!i915->params.nuclear_pageflip && match_info->graphics.ver < 5) i915->drm.driver_features &= ~DRIVER_ATOMIC; /* @@ -1127,6 +1144,8 @@ static int i915_drm_suspend(struct drm_device *dev) intel_suspend_hw(dev_priv); + /* Must be called before GGTT is suspended. */ + intel_dpt_suspend(dev_priv); i915_ggtt_suspend(&dev_priv->ggtt); i915_save_display(dev_priv); @@ -1183,6 +1202,14 @@ static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation) goto out; } + /* + * FIXME: Temporary hammer to avoid freezing the machine on our DGFX + * This should be totally removed when we handle the pci states properly + * on runtime PM and on s2idle cases. + */ + if (suspend_to_idle(dev_priv)) + pci_d3cold_disable(pdev); + pci_disable_device(pdev); /* * During hibernation on some platforms the BIOS may try to access @@ -1207,7 +1234,8 @@ out: return ret; } -int i915_suspend_switcheroo(struct drm_i915_private *i915, pm_message_t state) +int i915_driver_suspend_switcheroo(struct drm_i915_private *i915, + pm_message_t state) { int error; @@ -1243,6 +1271,8 @@ static int i915_drm_resume(struct drm_device *dev) drm_err(&dev_priv->drm, "failed to re-enable GGTT\n"); i915_ggtt_resume(&dev_priv->ggtt); + /* Must be called after GGTT is resumed. */ + intel_dpt_resume(dev_priv); intel_dmc_ucode_resume(dev_priv); @@ -1344,6 +1374,8 @@ static int i915_drm_resume_early(struct drm_device *dev) pci_set_master(pdev); + pci_d3cold_enable(pdev); + disable_rpm_wakeref_asserts(&dev_priv->runtime_pm); ret = vlv_resume_prepare(dev_priv, false); @@ -1353,7 +1385,7 @@ static int i915_drm_resume_early(struct drm_device *dev) intel_uncore_resume_early(&dev_priv->uncore); - intel_gt_check_and_clear_faults(&dev_priv->gt); + intel_gt_check_and_clear_faults(to_gt(dev_priv)); intel_display_power_resume_early(dev_priv); @@ -1364,7 +1396,7 @@ static int i915_drm_resume_early(struct drm_device *dev) return ret; } -int i915_resume_switcheroo(struct drm_i915_private *i915) +int i915_driver_resume_switcheroo(struct drm_i915_private *i915) { int ret; @@ -1520,6 +1552,7 @@ static int intel_runtime_suspend(struct device *kdev) { struct drm_i915_private *dev_priv = kdev_to_i915(kdev); struct intel_runtime_pm *rpm = &dev_priv->runtime_pm; + struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); int ret; if (drm_WARN_ON_ONCE(&dev_priv->drm, !HAS_RUNTIME_PM(dev_priv))) @@ -1535,7 +1568,7 @@ static int intel_runtime_suspend(struct device *kdev) */ i915_gem_runtime_suspend(dev_priv); - intel_gt_runtime_suspend(&dev_priv->gt); + intel_gt_runtime_suspend(to_gt(dev_priv)); intel_runtime_pm_disable_interrupts(dev_priv); @@ -1551,7 +1584,7 @@ static int intel_runtime_suspend(struct device *kdev) intel_runtime_pm_enable_interrupts(dev_priv); - intel_gt_runtime_resume(&dev_priv->gt); + intel_gt_runtime_resume(to_gt(dev_priv)); enable_rpm_wakeref_asserts(rpm); @@ -1565,6 +1598,12 @@ static int intel_runtime_suspend(struct device *kdev) drm_err(&dev_priv->drm, "Unclaimed access detected prior to suspending\n"); + /* + * FIXME: Temporary hammer to avoid freezing the machine on our DGFX + * This should be totally removed when we handle the pci states properly + * on runtime PM and on s2idle cases. + */ + pci_d3cold_disable(pdev); rpm->suspended = true; /* @@ -1603,6 +1642,7 @@ static int intel_runtime_resume(struct device *kdev) { struct drm_i915_private *dev_priv = kdev_to_i915(kdev); struct intel_runtime_pm *rpm = &dev_priv->runtime_pm; + struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); int ret; if (drm_WARN_ON_ONCE(&dev_priv->drm, !HAS_RUNTIME_PM(dev_priv))) @@ -1615,6 +1655,7 @@ static int intel_runtime_resume(struct device *kdev) intel_opregion_notify_adapter(dev_priv, PCI_D0); rpm->suspended = false; + pci_d3cold_enable(pdev); if (intel_uncore_unclaimed_mmio(&dev_priv->uncore)) drm_dbg(&dev_priv->drm, "Unclaimed access during suspend, bios?\n"); @@ -1631,7 +1672,7 @@ static int intel_runtime_resume(struct device *kdev) * No point of rolling back things in case of an error, as the best * we can do is to hope that things will still work (and disable RPM). */ - intel_gt_runtime_resume(&dev_priv->gt); + intel_gt_runtime_resume(to_gt(dev_priv)); /* * On VLV/CHV display interrupts are part of the display @@ -1777,7 +1818,7 @@ static const struct drm_ioctl_desc i915_ioctls[] = { DRM_IOCTL_DEF_DRV(I915_GEM_VM_DESTROY, i915_gem_vm_destroy_ioctl, DRM_RENDER_ALLOW), }; -static const struct drm_driver driver = { +static const struct drm_driver i915_drm_driver = { /* Don't use MTRRs here; the Xserver or userspace app should * deal with them for Intel hardware. */ diff --git a/drivers/gpu/drm/i915/i915_driver.h b/drivers/gpu/drm/i915/i915_driver.h new file mode 100644 index 000000000000..9ef8db4aa0a6 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_driver.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2019 Intel Corporation + */ + +#ifndef __I915_DRIVER_H__ +#define __I915_DRIVER_H__ + +#include <linux/pm.h> + +struct pci_dev; +struct pci_device_id; +struct drm_i915_private; + +extern const struct dev_pm_ops i915_pm_ops; + +int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent); +void i915_driver_remove(struct drm_i915_private *i915); +void i915_driver_shutdown(struct drm_i915_private *i915); + +int i915_driver_resume_switcheroo(struct drm_i915_private *i915); +int i915_driver_suspend_switcheroo(struct drm_i915_private *i915, pm_message_t state); + +#endif /* __I915_DRIVER_H__ */ diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 12256218634f..0c70ab08fc0c 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -50,7 +50,6 @@ #include <linux/stackdepot.h> #include <linux/xarray.h> -#include <drm/intel-gtt.h> #include <drm/drm_gem.h> #include <drm/drm_auth.h> #include <drm/drm_cache.h> @@ -90,6 +89,7 @@ #include "intel_device_info.h" #include "intel_memory_region.h" #include "intel_pch.h" +#include "intel_pm_types.h" #include "intel_runtime_pm.h" #include "intel_step.h" #include "intel_uncore.h" @@ -117,30 +117,6 @@ struct drm_i915_gem_object; -enum hpd_pin { - HPD_NONE = 0, - HPD_TV = HPD_NONE, /* TV is known to be unreliable */ - HPD_CRT, - HPD_SDVO_B, - HPD_SDVO_C, - HPD_PORT_A, - HPD_PORT_B, - HPD_PORT_C, - HPD_PORT_D, - HPD_PORT_E, - HPD_PORT_TC1, - HPD_PORT_TC2, - HPD_PORT_TC3, - HPD_PORT_TC4, - HPD_PORT_TC5, - HPD_PORT_TC6, - - HPD_NUM_PINS -}; - -#define for_each_hpd_pin(__pin) \ - for ((__pin) = (HPD_NONE + 1); (__pin) < HPD_NUM_PINS; (__pin)++) - /* Threshold == 5 for long IRQs, 50 for short */ #define HPD_STORM_DEFAULT_THRESHOLD 50 @@ -191,8 +167,6 @@ struct i915_hotplug { I915_GEM_DOMAIN_VERTEX) struct drm_i915_private; -struct i915_mm_struct; -struct i915_mmu_object; struct drm_i915_file_private { struct drm_i915_private *dev_priv; @@ -364,15 +338,6 @@ struct intel_color_funcs { void (*read_luts)(struct intel_crtc_state *crtc_state); }; -struct intel_audio_funcs { - void (*audio_codec_enable)(struct intel_encoder *encoder, - const struct intel_crtc_state *crtc_state, - const struct drm_connector_state *conn_state); - void (*audio_codec_disable)(struct intel_encoder *encoder, - const struct intel_crtc_state *old_crtc_state, - const struct drm_connector_state *old_conn_state); -}; - struct intel_cdclk_funcs { void (*get_cdclk)(struct drm_i915_private *dev_priv, struct intel_cdclk_config *cdclk_config); @@ -411,102 +376,8 @@ struct drm_i915_display_funcs { void (*commit_modeset_enables)(struct intel_atomic_state *state); }; - #define I915_COLOR_UNEVICTABLE (-1) /* a non-vma sharing the address space */ -struct intel_fbc { - /* This is always the inner lock when overlapping with struct_mutex and - * it's the outer lock when overlapping with stolen_lock. */ - struct mutex lock; - unsigned int possible_framebuffer_bits; - unsigned int busy_bits; - struct intel_crtc *crtc; - - struct drm_mm_node compressed_fb; - struct drm_mm_node compressed_llb; - - u8 limit; - - bool false_color; - - bool active; - bool activated; - bool flip_pending; - - bool underrun_detected; - struct work_struct underrun_work; - - /* - * Due to the atomic rules we can't access some structures without the - * appropriate locking, so we cache information here in order to avoid - * these problems. - */ - struct intel_fbc_state_cache { - struct { - unsigned int mode_flags; - u32 hsw_bdw_pixel_rate; - } crtc; - - struct { - unsigned int rotation; - int src_w; - int src_h; - bool visible; - /* - * Display surface base address adjustement for - * pageflips. Note that on gen4+ this only adjusts up - * to a tile, offsets within a tile are handled in - * the hw itself (with the TILEOFF register). - */ - int adjusted_x; - int adjusted_y; - - u16 pixel_blend_mode; - } plane; - - struct { - const struct drm_format_info *format; - unsigned int stride; - u64 modifier; - } fb; - - unsigned int fence_y_offset; - u16 interval; - s8 fence_id; - bool psr2_active; - } state_cache; - - /* - * This structure contains everything that's relevant to program the - * hardware registers. When we want to figure out if we need to disable - * and re-enable FBC for a new configuration we just check if there's - * something different in the struct. The genx_fbc_activate functions - * are supposed to read from it in order to program the registers. - */ - struct intel_fbc_reg_params { - struct { - enum pipe pipe; - enum i9xx_plane_id i9xx_plane; - } crtc; - - struct { - const struct drm_format_info *format; - unsigned int stride; - u64 modifier; - } fb; - - unsigned int cfb_stride; - unsigned int cfb_size; - unsigned int fence_y_offset; - u16 override_cfb_stride; - u16 interval; - s8 fence_id; - bool plane_visible; - } params; - - const char *no_fbc_reason; -}; - /* * HIGH_RR is the highest eDP panel refresh rate read from EDID * LOW_RR is the lowest eDP panel refresh rate found from EDID @@ -543,7 +414,6 @@ struct i915_drrs { #define QUIRK_NO_PPS_BACKLIGHT_POWER_HOOK (1<<8) struct intel_fbdev; -struct intel_fbc_work; struct intel_gmbus { struct i2c_adapter adapter; @@ -603,7 +473,7 @@ struct i915_gem_mm { * List of objects which are pending destruction. */ struct llist_head free_list; - struct work_struct free_work; + struct delayed_work free_work; /** * Count of objects pending destructions. Used to skip needlessly * waiting on an RCU barrier if no objects are waiting to be freed. @@ -738,69 +608,6 @@ struct intel_vbt_data { struct sdvo_device_mapping sdvo_mappings[2]; }; -enum intel_ddb_partitioning { - INTEL_DDB_PART_1_2, - INTEL_DDB_PART_5_6, /* IVB+ */ -}; - -struct ilk_wm_values { - u32 wm_pipe[3]; - u32 wm_lp[3]; - u32 wm_lp_spr[3]; - bool enable_fbc_wm; - enum intel_ddb_partitioning partitioning; -}; - -struct g4x_pipe_wm { - u16 plane[I915_MAX_PLANES]; - u16 fbc; -}; - -struct g4x_sr_wm { - u16 plane; - u16 cursor; - u16 fbc; -}; - -struct vlv_wm_ddl_values { - u8 plane[I915_MAX_PLANES]; -}; - -struct vlv_wm_values { - struct g4x_pipe_wm pipe[3]; - struct g4x_sr_wm sr; - struct vlv_wm_ddl_values ddl[3]; - u8 level; - bool cxsr; -}; - -struct g4x_wm_values { - struct g4x_pipe_wm pipe[2]; - struct g4x_sr_wm sr; - struct g4x_sr_wm hpll; - bool cxsr; - bool hpll_en; - bool fbc_en; -}; - -struct skl_ddb_entry { - u16 start, end; /* in number of blocks, 'end' is exclusive */ -}; - -static inline u16 skl_ddb_entry_size(const struct skl_ddb_entry *entry) -{ - return entry->end - entry->start; -} - -static inline bool skl_ddb_entry_equal(const struct skl_ddb_entry *e1, - const struct skl_ddb_entry *e2) -{ - if (e1->start == e2->start && e1->end == e2->end) - return true; - - return false; -} - struct i915_frontbuffer_tracking { spinlock_t lock; @@ -828,6 +635,30 @@ struct i915_selftest_stash { struct ida mock_region_instances; }; +/* intel_audio.c private */ +struct intel_audio_funcs; +struct intel_audio_private { + /* Display internal audio functions */ + const struct intel_audio_funcs *funcs; + + /* hda/i915 audio component */ + struct i915_audio_component *component; + bool component_registered; + /* mutex for audio/video sync */ + struct mutex mutex; + int power_refcount; + u32 freq_cntrl; + + /* Used to save the pipe-to-encoder mapping for audio */ + struct intel_encoder *encoder_map[I915_MAX_PIPES]; + + /* necessary resource sharing with HDMI LPE audio driver. */ + struct { + struct platform_device *platdev; + int irq; + } lpe; +}; + struct drm_i915_private { struct drm_device drm; @@ -918,7 +749,7 @@ struct drm_i915_private { u32 pipestat_irq_mask[I915_MAX_PIPES]; struct i915_hotplug hotplug; - struct intel_fbc fbc; + struct intel_fbc *fbc; struct i915_drrs drrs; struct intel_opregion opregion; struct intel_vbt_data vbt; @@ -995,9 +826,6 @@ struct drm_i915_private { /* Display internal color functions */ const struct intel_color_funcs *color_funcs; - /* Display internal audio functions */ - const struct intel_audio_funcs *audio_funcs; - /* Display CDCLK functions */ const struct intel_cdclk_funcs *cdclk_funcs; @@ -1016,9 +844,6 @@ struct drm_i915_private { /* Kernel Modesetting */ - struct intel_crtc *plane_to_crtc_mapping[I915_MAX_PIPES]; - struct intel_crtc *pipe_to_crtc_mapping[I915_MAX_PIPES]; - /** * dpll and cdclk state is protected by connection_mutex * dpll.lock serializes intel_{prepare,enable,disable}_shared_dpll. @@ -1084,17 +909,6 @@ struct drm_i915_private { struct drm_property *broadcast_rgb_property; struct drm_property *force_audio_property; - /* hda/i915 audio component */ - struct i915_audio_component *audio_component; - bool audio_component_registered; - /** - * av_mutex - mutex for audio/video sync - * - */ - struct mutex av_mutex; - int audio_power_refcount; - u32 audio_freq_cntrl; - u32 fdi_rx_config; /* Shadow for DISPLAY_PHY_CONTROL which can't be safely read */ @@ -1191,7 +1005,7 @@ struct drm_i915_private { struct i915_perf perf; /* Abstract the submission mechanism (legacy ringbuffer or execlists) away */ - struct intel_gt gt; + struct intel_gt gt0; struct { struct i915_gem_contexts { @@ -1227,14 +1041,7 @@ struct drm_i915_private { bool ipc_enabled; - /* Used to save the pipe-to-encoder mapping for audio */ - struct intel_encoder *av_enc_map[I915_MAX_PIPES]; - - /* necessary resource sharing with HDMI LPE audio driver. */ - struct { - struct platform_device *platdev; - int irq; - } lpe_audio; + struct intel_audio_private audio; struct i915_pmu pmu; @@ -1270,6 +1077,11 @@ static inline struct drm_i915_private *pdev_to_i915(struct pci_dev *pdev) return pci_get_drvdata(pdev); } +static inline struct intel_gt *to_gt(struct drm_i915_private *i915) +{ + return &i915->gt0; +} + /* Simple iterator over all initialised engines */ #define for_each_engine(engine__, dev_priv__, id__) \ for ((id__) = 0; \ @@ -1327,15 +1139,15 @@ static inline struct drm_i915_private *pdev_to_i915(struct pci_dev *pdev) #define IP_VER(ver, rel) ((ver) << 8 | (rel)) -#define GRAPHICS_VER(i915) (INTEL_INFO(i915)->graphics_ver) -#define GRAPHICS_VER_FULL(i915) IP_VER(INTEL_INFO(i915)->graphics_ver, \ - INTEL_INFO(i915)->graphics_rel) +#define GRAPHICS_VER(i915) (INTEL_INFO(i915)->graphics.ver) +#define GRAPHICS_VER_FULL(i915) IP_VER(INTEL_INFO(i915)->graphics.ver, \ + INTEL_INFO(i915)->graphics.rel) #define IS_GRAPHICS_VER(i915, from, until) \ (GRAPHICS_VER(i915) >= (from) && GRAPHICS_VER(i915) <= (until)) -#define MEDIA_VER(i915) (INTEL_INFO(i915)->media_ver) -#define MEDIA_VER_FULL(i915) IP_VER(INTEL_INFO(i915)->media_ver, \ - INTEL_INFO(i915)->media_rel) +#define MEDIA_VER(i915) (INTEL_INFO(i915)->media.ver) +#define MEDIA_VER_FULL(i915) IP_VER(INTEL_INFO(i915)->media.arch, \ + INTEL_INFO(i915)->media.rel) #define IS_MEDIA_VER(i915, from, until) \ (MEDIA_VER(i915) >= (from) && MEDIA_VER(i915) <= (until)) @@ -1348,15 +1160,20 @@ static inline struct drm_i915_private *pdev_to_i915(struct pci_dev *pdev) #define HAS_DSB(dev_priv) (INTEL_INFO(dev_priv)->display.has_dsb) #define INTEL_DISPLAY_STEP(__i915) (RUNTIME_INFO(__i915)->step.display_step) -#define INTEL_GT_STEP(__i915) (RUNTIME_INFO(__i915)->step.gt_step) +#define INTEL_GRAPHICS_STEP(__i915) (RUNTIME_INFO(__i915)->step.graphics_step) +#define INTEL_MEDIA_STEP(__i915) (RUNTIME_INFO(__i915)->step.media_step) #define IS_DISPLAY_STEP(__i915, since, until) \ (drm_WARN_ON(&(__i915)->drm, INTEL_DISPLAY_STEP(__i915) == STEP_NONE), \ INTEL_DISPLAY_STEP(__i915) >= (since) && INTEL_DISPLAY_STEP(__i915) < (until)) -#define IS_GT_STEP(__i915, since, until) \ - (drm_WARN_ON(&(__i915)->drm, INTEL_GT_STEP(__i915) == STEP_NONE), \ - INTEL_GT_STEP(__i915) >= (since) && INTEL_GT_STEP(__i915) < (until)) +#define IS_GRAPHICS_STEP(__i915, since, until) \ + (drm_WARN_ON(&(__i915)->drm, INTEL_GRAPHICS_STEP(__i915) == STEP_NONE), \ + INTEL_GRAPHICS_STEP(__i915) >= (since) && INTEL_GRAPHICS_STEP(__i915) < (until)) + +#define IS_MEDIA_STEP(__i915, since, until) \ + (drm_WARN_ON(&(__i915)->drm, INTEL_MEDIA_STEP(__i915) == STEP_NONE), \ + INTEL_MEDIA_STEP(__i915) >= (since) && INTEL_MEDIA_STEP(__i915) < (until)) static __always_inline unsigned int __platform_mask_index(const struct intel_runtime_info *info, @@ -1455,7 +1272,6 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define IS_GEMINILAKE(dev_priv) IS_PLATFORM(dev_priv, INTEL_GEMINILAKE) #define IS_COFFEELAKE(dev_priv) IS_PLATFORM(dev_priv, INTEL_COFFEELAKE) #define IS_COMETLAKE(dev_priv) IS_PLATFORM(dev_priv, INTEL_COMETLAKE) -#define IS_CANNONLAKE(dev_priv) 0 #define IS_ICELAKE(dev_priv) IS_PLATFORM(dev_priv, INTEL_ICELAKE) #define IS_JSL_EHL(dev_priv) (IS_PLATFORM(dev_priv, INTEL_JASPERLAKE) || \ IS_PLATFORM(dev_priv, INTEL_ELKHARTLAKE)) @@ -1470,6 +1286,8 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, IS_SUBPLATFORM(dev_priv, INTEL_DG2, INTEL_SUBPLATFORM_G10) #define IS_DG2_G11(dev_priv) \ IS_SUBPLATFORM(dev_priv, INTEL_DG2, INTEL_SUBPLATFORM_G11) +#define IS_ADLS_RPLS(dev_priv) \ + IS_SUBPLATFORM(dev_priv, INTEL_ALDERLAKE_S, INTEL_SUBPLATFORM_RPL_S) #define IS_HSW_EARLY_SDV(dev_priv) (IS_HASWELL(dev_priv) && \ (INTEL_DEVID(dev_priv) & 0xFF00) == 0x0C00) #define IS_BDW_ULT(dev_priv) \ @@ -1530,15 +1348,15 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define IS_TGL_Y(dev_priv) \ IS_SUBPLATFORM(dev_priv, INTEL_TIGERLAKE, INTEL_SUBPLATFORM_ULX) -#define IS_SKL_GT_STEP(p, since, until) (IS_SKYLAKE(p) && IS_GT_STEP(p, since, until)) +#define IS_SKL_GRAPHICS_STEP(p, since, until) (IS_SKYLAKE(p) && IS_GRAPHICS_STEP(p, since, until)) -#define IS_KBL_GT_STEP(dev_priv, since, until) \ - (IS_KABYLAKE(dev_priv) && IS_GT_STEP(dev_priv, since, until)) +#define IS_KBL_GRAPHICS_STEP(dev_priv, since, until) \ + (IS_KABYLAKE(dev_priv) && IS_GRAPHICS_STEP(dev_priv, since, until)) #define IS_KBL_DISPLAY_STEP(dev_priv, since, until) \ (IS_KABYLAKE(dev_priv) && IS_DISPLAY_STEP(dev_priv, since, until)) -#define IS_JSL_EHL_GT_STEP(p, since, until) \ - (IS_JSL_EHL(p) && IS_GT_STEP(p, since, until)) +#define IS_JSL_EHL_GRAPHICS_STEP(p, since, until) \ + (IS_JSL_EHL(p) && IS_GRAPHICS_STEP(p, since, until)) #define IS_JSL_EHL_DISPLAY_STEP(p, since, until) \ (IS_JSL_EHL(p) && IS_DISPLAY_STEP(p, since, until)) @@ -1546,19 +1364,19 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, (IS_TIGERLAKE(__i915) && \ IS_DISPLAY_STEP(__i915, since, until)) -#define IS_TGL_UY_GT_STEP(__i915, since, until) \ +#define IS_TGL_UY_GRAPHICS_STEP(__i915, since, until) \ ((IS_TGL_U(__i915) || IS_TGL_Y(__i915)) && \ - IS_GT_STEP(__i915, since, until)) + IS_GRAPHICS_STEP(__i915, since, until)) -#define IS_TGL_GT_STEP(__i915, since, until) \ +#define IS_TGL_GRAPHICS_STEP(__i915, since, until) \ (IS_TIGERLAKE(__i915) && !(IS_TGL_U(__i915) || IS_TGL_Y(__i915)) && \ - IS_GT_STEP(__i915, since, until)) + IS_GRAPHICS_STEP(__i915, since, until)) #define IS_RKL_DISPLAY_STEP(p, since, until) \ (IS_ROCKETLAKE(p) && IS_DISPLAY_STEP(p, since, until)) -#define IS_DG1_GT_STEP(p, since, until) \ - (IS_DG1(p) && IS_GT_STEP(p, since, until)) +#define IS_DG1_GRAPHICS_STEP(p, since, until) \ + (IS_DG1(p) && IS_GRAPHICS_STEP(p, since, until)) #define IS_DG1_DISPLAY_STEP(p, since, until) \ (IS_DG1(p) && IS_DISPLAY_STEP(p, since, until)) @@ -1566,20 +1384,20 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, (IS_ALDERLAKE_S(__i915) && \ IS_DISPLAY_STEP(__i915, since, until)) -#define IS_ADLS_GT_STEP(__i915, since, until) \ +#define IS_ADLS_GRAPHICS_STEP(__i915, since, until) \ (IS_ALDERLAKE_S(__i915) && \ - IS_GT_STEP(__i915, since, until)) + IS_GRAPHICS_STEP(__i915, since, until)) #define IS_ADLP_DISPLAY_STEP(__i915, since, until) \ (IS_ALDERLAKE_P(__i915) && \ IS_DISPLAY_STEP(__i915, since, until)) -#define IS_ADLP_GT_STEP(__i915, since, until) \ +#define IS_ADLP_GRAPHICS_STEP(__i915, since, until) \ (IS_ALDERLAKE_P(__i915) && \ - IS_GT_STEP(__i915, since, until)) + IS_GRAPHICS_STEP(__i915, since, until)) -#define IS_XEHPSDV_GT_STEP(__i915, since, until) \ - (IS_XEHPSDV(__i915) && IS_GT_STEP(__i915, since, until)) +#define IS_XEHPSDV_GRAPHICS_STEP(__i915, since, until) \ + (IS_XEHPSDV(__i915) && IS_GRAPHICS_STEP(__i915, since, until)) /* * DG2 hardware steppings are a bit unusual. The hardware design was forked @@ -1595,11 +1413,11 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, * and stepping-specific logic will be applied with a general DG2-wide stepping * number. */ -#define IS_DG2_GT_STEP(__i915, variant, since, until) \ +#define IS_DG2_GRAPHICS_STEP(__i915, variant, since, until) \ (IS_SUBPLATFORM(__i915, INTEL_DG2, INTEL_SUBPLATFORM_##variant) && \ - IS_GT_STEP(__i915, since, until)) + IS_GRAPHICS_STEP(__i915, since, until)) -#define IS_DG2_DISP_STEP(__i915, since, until) \ +#define IS_DG2_DISPLAY_STEP(__i915, since, until) \ (IS_DG2(__i915) && \ IS_DISPLAY_STEP(__i915, since, until)) @@ -1696,7 +1514,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define HAS_PSR_HW_TRACKING(dev_priv) \ (INTEL_INFO(dev_priv)->display.has_psr_hw_tracking) #define HAS_PSR2_SEL_FETCH(dev_priv) (GRAPHICS_VER(dev_priv) >= 12) -#define HAS_TRANSCODER(dev_priv, trans) ((INTEL_INFO(dev_priv)->cpu_transcoder_mask & BIT(trans)) != 0) +#define HAS_TRANSCODER(dev_priv, trans) ((INTEL_INFO(dev_priv)->display.cpu_transcoder_mask & BIT(trans)) != 0) #define HAS_RC6(dev_priv) (INTEL_INFO(dev_priv)->has_rc6) #define HAS_RC6p(dev_priv) (INTEL_INFO(dev_priv)->has_rc6p) @@ -1714,6 +1532,14 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define HAS_MSLICES(dev_priv) \ (INTEL_INFO(dev_priv)->has_mslices) +/* + * Set this flag, when platform requires 64K GTT page sizes or larger for + * device local memory access. Also this flag implies that we require or + * at least support the compact PT layout for the ppGTT when using the 64K + * GTT pages. + */ +#define HAS_64K_PAGES(dev_priv) (INTEL_INFO(dev_priv)->has_64k_pages) + #define HAS_IPC(dev_priv) (INTEL_INFO(dev_priv)->display.has_ipc) #define HAS_REGION(i915, i) (INTEL_INFO(i915)->memory_regions & (i)) @@ -1727,7 +1553,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define HAS_PXP(dev_priv) ((IS_ENABLED(CONFIG_DRM_I915_PXP) && \ INTEL_INFO(dev_priv)->has_pxp) && \ - VDBOX_MASK(&dev_priv->gt)) + VDBOX_MASK(to_gt(dev_priv))) #define HAS_GMCH(dev_priv) (INTEL_INFO(dev_priv)->display.has_gmch) @@ -1741,11 +1567,11 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define GT_FREQUENCY_MULTIPLIER 50 #define GEN9_FREQ_SCALER 3 -#define INTEL_NUM_PIPES(dev_priv) (hweight8(INTEL_INFO(dev_priv)->pipe_mask)) +#define INTEL_NUM_PIPES(dev_priv) (hweight8(INTEL_INFO(dev_priv)->display.pipe_mask)) -#define HAS_DISPLAY(dev_priv) (INTEL_INFO(dev_priv)->pipe_mask != 0) +#define HAS_DISPLAY(dev_priv) (INTEL_INFO(dev_priv)->display.pipe_mask != 0) -#define HAS_VRR(i915) (GRAPHICS_VER(i915) >= 12) +#define HAS_VRR(i915) (GRAPHICS_VER(i915) >= 11) #define HAS_ASYNC_FLIPS(i915) (DISPLAY_VER(i915) >= 5) @@ -1761,26 +1587,27 @@ static inline bool run_as_guest(void) #define HAS_D12_PLANE_MINIMIZATION(dev_priv) (IS_ROCKETLAKE(dev_priv) || \ IS_ALDERLAKE_S(dev_priv)) -static inline bool intel_vtd_active(void) +static inline bool intel_vtd_active(struct drm_i915_private *i915) { -#ifdef CONFIG_INTEL_IOMMU - if (intel_iommu_gfx_mapped) + if (device_iommu_mapped(i915->drm.dev)) return true; -#endif /* Running as a guest, we assume the host is enforcing VT'd */ return run_as_guest(); } +void +i915_print_iommu_status(struct drm_i915_private *i915, struct drm_printer *p); + static inline bool intel_scanout_needs_vtd_wa(struct drm_i915_private *dev_priv) { - return GRAPHICS_VER(dev_priv) >= 6 && intel_vtd_active(); + return GRAPHICS_VER(dev_priv) >= 6 && intel_vtd_active(dev_priv); } static inline bool intel_ggtt_update_needs_vtd_wa(struct drm_i915_private *i915) { - return IS_BROXTON(i915) && intel_vtd_active(); + return IS_BROXTON(i915) && intel_vtd_active(i915); } static inline bool @@ -1789,16 +1616,7 @@ intel_vm_no_concurrent_access_wa(struct drm_i915_private *i915) return IS_CHERRYVIEW(i915) || intel_ggtt_update_needs_vtd_wa(i915); } -/* i915_drv.c */ -extern const struct dev_pm_ops i915_pm_ops; - -int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent); -void i915_driver_remove(struct drm_i915_private *i915); -void i915_driver_shutdown(struct drm_i915_private *i915); - -int i915_resume_switcheroo(struct drm_i915_private *i915); -int i915_suspend_switcheroo(struct drm_i915_private *i915, pm_message_t state); - +/* i915_getparam.c */ int i915_getparam_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); @@ -1818,7 +1636,8 @@ static inline void i915_gem_drain_freed_objects(struct drm_i915_private *i915) * armed the work again. */ while (atomic_read(&i915->mm.free_count)) { - flush_work(&i915->mm.free_work); + flush_delayed_work(&i915->mm.free_work); + flush_delayed_work(&i915->bdev.wq); rcu_barrier(); } } @@ -1851,13 +1670,10 @@ i915_gem_object_ggtt_pin_ww(struct drm_i915_gem_object *obj, const struct i915_ggtt_view *view, u64 size, u64 alignment, u64 flags); -static inline struct i915_vma * __must_check +struct i915_vma * __must_check i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj, const struct i915_ggtt_view *view, - u64 size, u64 alignment, u64 flags) -{ - return i915_gem_object_ggtt_pin_ww(obj, NULL, view, size, alignment, flags); -} + u64 size, u64 alignment, u64 flags); int i915_gem_object_unbind(struct drm_i915_gem_object *obj, unsigned long flags); @@ -1933,6 +1749,10 @@ int i915_gem_evict_vm(struct i915_address_space *vm); struct drm_i915_gem_object * i915_gem_object_create_internal(struct drm_i915_private *dev_priv, phys_addr_t size); +struct drm_i915_gem_object * +__i915_gem_object_create_internal(struct drm_i915_private *dev_priv, + const struct drm_i915_gem_object_ops *ops, + phys_addr_t size); /* i915_gem_tiling.c */ static inline bool i915_gem_object_needs_bit17_swizzle(struct drm_i915_gem_object *obj) @@ -1972,14 +1792,6 @@ mkwrite_device_info(struct drm_i915_private *dev_priv) int i915_reg_read_ioctl(struct drm_device *dev, void *data, struct drm_file *file); -/* i915_mm.c */ -int remap_io_mapping(struct vm_area_struct *vma, - unsigned long addr, unsigned long pfn, unsigned long size, - struct io_mapping *iomap); -int remap_io_sg(struct vm_area_struct *vma, - unsigned long addr, unsigned long size, - struct scatterlist *sgl, resource_size_t iobase); - static inline int intel_hws_csb_write_index(struct drm_i915_private *i915) { if (GRAPHICS_VER(i915) >= 11) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 981e383d1a5d..915bf431f320 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -764,7 +764,7 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data, * perspective, requiring manual detiling by the client. */ if (!i915_gem_object_has_struct_page(obj) || - cpu_write_needs_clflush(obj)) + i915_gem_cpu_write_needs_clflush(obj)) /* Note that the gtt paths might fail with non-page-backed user * pointers (e.g. gtt mappings when moving data between * textures). Fallback to the shmem path in that case. @@ -877,6 +877,8 @@ i915_gem_object_ggtt_pin_ww(struct drm_i915_gem_object *obj, struct i915_vma *vma; int ret; + GEM_WARN_ON(!ww); + if (flags & PIN_MAPPABLE && (!view || view->type == I915_GGTT_VIEW_NORMAL)) { /* @@ -936,10 +938,7 @@ new_vma: return ERR_PTR(ret); } - if (ww) - ret = i915_vma_pin_ww(vma, ww, size, alignment, flags | PIN_GLOBAL); - else - ret = i915_vma_pin(vma, size, alignment, flags | PIN_GLOBAL); + ret = i915_vma_pin_ww(vma, ww, size, alignment, flags | PIN_GLOBAL); if (ret) return ERR_PTR(ret); @@ -959,6 +958,29 @@ new_vma: return vma; } +struct i915_vma * __must_check +i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj, + const struct i915_ggtt_view *view, + u64 size, u64 alignment, u64 flags) +{ + struct i915_gem_ww_ctx ww; + struct i915_vma *ret; + int err; + + for_i915_gem_ww(&ww, err, true) { + err = i915_gem_object_lock(obj, &ww); + if (err) + continue; + + ret = i915_gem_object_ggtt_pin_ww(obj, &ww, view, size, + alignment, flags); + if (IS_ERR(ret)) + err = PTR_ERR(ret); + } + + return err ? ERR_PTR(err) : ret; +} + int i915_gem_madvise_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) @@ -1005,7 +1027,8 @@ i915_gem_madvise_ioctl(struct drm_device *dev, void *data, obj->ops->adjust_lru(obj); } - if (i915_gem_object_has_pages(obj)) { + if (i915_gem_object_has_pages(obj) || + i915_gem_object_has_self_managed_shrink_list(obj)) { unsigned long flags; spin_lock_irqsave(&i915->mm.obj_lock, flags); @@ -1048,7 +1071,7 @@ int i915_gem_init(struct drm_i915_private *dev_priv) if (ret) return ret; - intel_uc_fetch_firmwares(&dev_priv->gt.uc); + intel_uc_fetch_firmwares(&to_gt(dev_priv)->uc); intel_wopcm_init(&dev_priv->wopcm); ret = i915_init_ggtt(dev_priv); @@ -1068,7 +1091,7 @@ int i915_gem_init(struct drm_i915_private *dev_priv) */ intel_init_clock_gating(dev_priv); - ret = intel_gt_init(&dev_priv->gt); + ret = intel_gt_init(to_gt(dev_priv)); if (ret) goto err_unlock; @@ -1084,7 +1107,7 @@ err_unlock: i915_gem_drain_workqueue(dev_priv); if (ret != -EIO) - intel_uc_cleanup_firmwares(&dev_priv->gt.uc); + intel_uc_cleanup_firmwares(&to_gt(dev_priv)->uc); if (ret == -EIO) { /* @@ -1092,10 +1115,10 @@ 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(&dev_priv->gt)) { + 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(&dev_priv->gt); + intel_gt_set_wedged(to_gt(dev_priv)); } /* Minimal basic recovery for KMS */ @@ -1126,7 +1149,7 @@ void i915_gem_driver_remove(struct drm_i915_private *dev_priv) intel_wakeref_auto_fini(&dev_priv->ggtt.userfault_wakeref); i915_gem_suspend_late(dev_priv); - intel_gt_driver_remove(&dev_priv->gt); + intel_gt_driver_remove(to_gt(dev_priv)); dev_priv->uabi_engines = RB_ROOT; /* Flush any outstanding unpin_work. */ @@ -1137,9 +1160,9 @@ void i915_gem_driver_remove(struct drm_i915_private *dev_priv) void i915_gem_driver_release(struct drm_i915_private *dev_priv) { - intel_gt_driver_release(&dev_priv->gt); + intel_gt_driver_release(to_gt(dev_priv)); - intel_uc_cleanup_firmwares(&dev_priv->gt.uc); + intel_uc_cleanup_firmwares(&to_gt(dev_priv)->uc); i915_gem_drain_freed_objects(dev_priv); diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c index 77490cb5ff9c..7f80ad247bc8 100644 --- a/drivers/gpu/drm/i915/i915_getparam.c +++ b/drivers/gpu/drm/i915/i915_getparam.c @@ -13,7 +13,7 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data, { struct drm_i915_private *i915 = to_i915(dev); struct pci_dev *pdev = to_pci_dev(dev->dev); - const struct sseu_dev_info *sseu = &i915->gt.info.sseu; + const struct sseu_dev_info *sseu = &to_gt(i915)->info.sseu; drm_i915_getparam_t *param = data; int value = 0; @@ -82,8 +82,8 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data, break; case I915_PARAM_HAS_GPU_RESET: value = i915->params.enable_hangcheck && - intel_has_gpu_reset(&i915->gt); - if (value && intel_has_reset_engine(&i915->gt)) + intel_has_gpu_reset(to_gt(i915)); + if (value && intel_has_reset_engine(to_gt(i915))) value = 2; break; case I915_PARAM_HAS_RESOURCE_STREAMER: @@ -96,7 +96,7 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data, value = sseu->min_eu_in_pool; break; case I915_PARAM_HUC_STATUS: - value = intel_huc_check_status(&i915->gt.uc.huc); + value = intel_huc_check_status(&to_gt(i915)->uc.huc); if (value < 0) return value; break; @@ -158,7 +158,7 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data, return -ENODEV; break; case I915_PARAM_CS_TIMESTAMP_FREQUENCY: - value = i915->gt.clock_frequency; + value = to_gt(i915)->clock_frequency; break; case I915_PARAM_MMAP_GTT_COHERENT: value = INTEL_INFO(i915)->has_coherent_ggtt; diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 2a2d7643b551..5ae812d60abe 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -48,8 +48,9 @@ #include "i915_gpu_error.h" #include "i915_memcpy.h" #include "i915_scatterlist.h" +#include "i915_vma_snapshot.h" -#define ALLOW_FAIL (GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN) +#define ALLOW_FAIL (__GFP_KSWAPD_RECLAIM | __GFP_RETRY_MAYFAIL | __GFP_NOWARN) #define ATOMIC_MAYFAIL (GFP_ATOMIC | __GFP_NOWARN) static void __sg_set_buf(struct scatterlist *sg, @@ -275,16 +276,16 @@ static bool compress_start(struct i915_vma_compress *c) static void *compress_next_page(struct i915_vma_compress *c, struct i915_vma_coredump *dst) { - void *page; + void *page_addr; + struct page *page; - if (dst->page_count >= dst->num_pages) - return ERR_PTR(-ENOSPC); - - page = pool_alloc(&c->pool, ALLOW_FAIL); - if (!page) + page_addr = pool_alloc(&c->pool, ALLOW_FAIL); + if (!page_addr) return ERR_PTR(-ENOMEM); - return dst->pages[dst->page_count++] = page; + page = virt_to_page(page_addr); + list_add_tail(&page->lru, &dst->page_list); + return page_addr; } static int compress_page(struct i915_vma_compress *c, @@ -397,7 +398,7 @@ static int compress_page(struct i915_vma_compress *c, if (!(wc && i915_memcpy_from_wc(ptr, src, PAGE_SIZE))) memcpy(ptr, src, PAGE_SIZE); - dst->pages[dst->page_count++] = ptr; + list_add_tail(&virt_to_page(ptr)->lru, &dst->page_list); cond_resched(); return 0; @@ -504,7 +505,7 @@ static void error_print_context(struct drm_i915_error_state_buf *m, const char *header, const struct i915_gem_context_coredump *ctx) { - const u32 period = m->i915->gt.clock_period_ns; + const u32 period = to_gt(m->i915)->clock_period_ns; err_printf(m, "%s%s[%d] prio %d, guilty %d active %d, runtime total %lluns, avg %lluns\n", header, ctx->comm, ctx->pid, ctx->sched_attr.priority, @@ -614,7 +615,7 @@ static void print_error_vma(struct drm_i915_error_state_buf *m, const struct i915_vma_coredump *vma) { char out[ASCII85_BUFSZ]; - int page; + struct page *page; if (!vma) return; @@ -628,16 +629,17 @@ static void print_error_vma(struct drm_i915_error_state_buf *m, err_printf(m, "gtt_page_sizes = 0x%08x\n", vma->gtt_page_sizes); err_compression_marker(m); - for (page = 0; page < vma->page_count; page++) { + list_for_each_entry(page, &vma->page_list, lru) { int i, len; + const u32 *addr = page_address(page); len = PAGE_SIZE; - if (page == vma->page_count - 1) + if (page == list_last_entry(&vma->page_list, typeof(*page), lru)) len -= vma->unused; len = ascii85_encode_len(len); for (i = 0; i < len; i++) - err_puts(m, ascii85_encode(vma->pages[page][i], out)); + err_puts(m, ascii85_encode(addr[i], out)); } err_puts(m, "\n"); } @@ -946,10 +948,12 @@ static void i915_vma_coredump_free(struct i915_vma_coredump *vma) { while (vma) { struct i915_vma_coredump *next = vma->next; - int page; + struct page *page, *n; - for (page = 0; page < vma->page_count; page++) - free_page((unsigned long)vma->pages[page]); + list_for_each_entry_safe(page, n, &vma->page_list, lru) { + list_del_init(&page->lru); + __free_page(page); + } kfree(vma); vma = next; @@ -1009,25 +1013,21 @@ void __i915_gpu_coredump_free(struct kref *error_ref) static struct i915_vma_coredump * i915_vma_coredump_create(const struct intel_gt *gt, - const struct i915_vma *vma, - const char *name, + const struct i915_vma_snapshot *vsnap, struct i915_vma_compress *compress) { struct i915_ggtt *ggtt = gt->ggtt; const u64 slot = ggtt->error_capture.start; struct i915_vma_coredump *dst; - unsigned long num_pages; struct sgt_iter iter; int ret; might_sleep(); - if (!vma || !vma->pages || !compress) + if (!vsnap || !vsnap->pages || !compress) return NULL; - num_pages = min_t(u64, vma->size, vma->obj->base.size) >> PAGE_SHIFT; - num_pages = DIV_ROUND_UP(10 * num_pages, 8); /* worstcase zlib growth */ - dst = kmalloc(sizeof(*dst) + num_pages * sizeof(u32 *), ALLOW_FAIL); + dst = kmalloc(sizeof(*dst), ALLOW_FAIL); if (!dst) return NULL; @@ -1036,14 +1036,13 @@ i915_vma_coredump_create(const struct intel_gt *gt, return NULL; } - strcpy(dst->name, name); + INIT_LIST_HEAD(&dst->page_list); + strcpy(dst->name, vsnap->name); dst->next = NULL; - dst->gtt_offset = vma->node.start; - dst->gtt_size = vma->node.size; - dst->gtt_page_sizes = vma->page_sizes.gtt; - dst->num_pages = num_pages; - dst->page_count = 0; + dst->gtt_offset = vsnap->gtt_offset; + dst->gtt_size = vsnap->gtt_size; + dst->gtt_page_sizes = vsnap->page_sizes; dst->unused = 0; ret = -EINVAL; @@ -1051,7 +1050,7 @@ i915_vma_coredump_create(const struct intel_gt *gt, void __iomem *s; dma_addr_t dma; - for_each_sgt_daddr(dma, iter, vma->pages) { + for_each_sgt_daddr(dma, iter, vsnap->pages) { mutex_lock(&ggtt->error_mutex); ggtt->vm.insert_page(&ggtt->vm, dma, slot, I915_CACHE_NONE, 0); @@ -1069,11 +1068,11 @@ i915_vma_coredump_create(const struct intel_gt *gt, if (ret) break; } - } else if (__i915_gem_object_is_lmem(vma->obj)) { - struct intel_memory_region *mem = vma->obj->mm.region; + } else if (vsnap->mr && vsnap->mr->type != INTEL_MEMORY_SYSTEM) { + struct intel_memory_region *mem = vsnap->mr; dma_addr_t dma; - for_each_sgt_daddr(dma, iter, vma->pages) { + for_each_sgt_daddr(dma, iter, vsnap->pages) { void __iomem *s; s = io_mapping_map_wc(&mem->iomap, @@ -1089,7 +1088,7 @@ i915_vma_coredump_create(const struct intel_gt *gt, } else { struct page *page; - for_each_sgt_page(page, iter, vma->pages) { + for_each_sgt_page(page, iter, vsnap->pages) { void *s; drm_clflush_pages(&page, 1); @@ -1106,8 +1105,13 @@ i915_vma_coredump_create(const struct intel_gt *gt, } if (ret || compress_flush(compress, dst)) { - while (dst->page_count--) - pool_free(&compress->pool, dst->pages[dst->page_count]); + struct page *page, *n; + + list_for_each_entry_safe_reverse(page, n, &dst->page_list, lru) { + list_del_init(&page->lru); + pool_free(&compress->pool, page_address(page)); + } + kfree(dst); dst = NULL; } @@ -1320,38 +1324,72 @@ static bool record_context(struct i915_gem_context_coredump *e, struct intel_engine_capture_vma { struct intel_engine_capture_vma *next; - struct i915_vma *vma; + struct i915_vma_snapshot *vsnap; char name[16]; + bool lockdep_cookie; }; static struct intel_engine_capture_vma * -capture_vma(struct intel_engine_capture_vma *next, - struct i915_vma *vma, - const char *name, - gfp_t gfp) +capture_vma_snapshot(struct intel_engine_capture_vma *next, + struct i915_vma_snapshot *vsnap, + gfp_t gfp) { struct intel_engine_capture_vma *c; - if (!vma) + if (!i915_vma_snapshot_present(vsnap)) return next; c = kmalloc(sizeof(*c), gfp); if (!c) return next; - if (!i915_active_acquire_if_busy(&vma->active)) { + if (!i915_vma_snapshot_resource_pin(vsnap, &c->lockdep_cookie)) { kfree(c); return next; } - strcpy(c->name, name); - c->vma = vma; /* reference held while active */ + strcpy(c->name, vsnap->name); + c->vsnap = vsnap; + i915_vma_snapshot_get(vsnap); c->next = next; return c; } static struct intel_engine_capture_vma * +capture_vma(struct intel_engine_capture_vma *next, + struct i915_vma *vma, + const char *name, + gfp_t gfp) +{ + struct i915_vma_snapshot *vsnap; + + if (!vma) + return next; + + /* + * If the vma isn't pinned, then the vma should be snapshotted + * to a struct i915_vma_snapshot at command submission time. + * Not here. + */ + GEM_WARN_ON(!i915_vma_is_pinned(vma)); + if (!i915_vma_is_pinned(vma)) + return next; + + vsnap = i915_vma_snapshot_alloc(gfp); + if (!vsnap) + return next; + + i915_vma_snapshot_init(vsnap, vma, name); + next = capture_vma_snapshot(next, vsnap, gfp); + + /* FIXME: Replace on async unbind. */ + i915_vma_snapshot_put(vsnap); + + return next; +} + +static struct intel_engine_capture_vma * capture_user(struct intel_engine_capture_vma *capture, const struct i915_request *rq, gfp_t gfp) @@ -1359,7 +1397,7 @@ capture_user(struct intel_engine_capture_vma *capture, struct i915_capture_list *c; for (c = rq->capture_list; c; c = c->next) - capture = capture_vma(capture, c->vma, "user", gfp); + capture = capture_vma_snapshot(capture, c->vma_snapshot, gfp); return capture; } @@ -1373,6 +1411,33 @@ static void add_vma(struct intel_engine_coredump *ee, } } +static struct i915_vma_coredump * +create_vma_coredump(const struct intel_gt *gt, struct i915_vma *vma, + const char *name, struct i915_vma_compress *compress) +{ + struct i915_vma_coredump *ret; + struct i915_vma_snapshot tmp; + + if (!vma) + return NULL; + + GEM_WARN_ON(!i915_vma_is_pinned(vma)); + i915_vma_snapshot_init_onstack(&tmp, vma, name); + ret = i915_vma_coredump_create(gt, &tmp, compress); + i915_vma_snapshot_put_onstack(&tmp); + + return ret; +} + +static void add_vma_coredump(struct intel_engine_coredump *ee, + const struct intel_gt *gt, + struct i915_vma *vma, + const char *name, + struct i915_vma_compress *compress) +{ + add_vma(ee, create_vma_coredump(gt, vma, name, compress)); +} + struct intel_engine_coredump * intel_engine_coredump_alloc(struct intel_engine_cs *engine, gfp_t gfp) { @@ -1406,7 +1471,7 @@ intel_engine_coredump_add_request(struct intel_engine_coredump *ee, * as the simplest method to avoid being overwritten * by userspace. */ - vma = capture_vma(vma, rq->batch, "batch", gfp); + vma = capture_vma_snapshot(vma, &rq->batch_snapshot, gfp); vma = capture_user(vma, rq, gfp); vma = capture_vma(vma, rq->ring->vma, "ring", gfp); vma = capture_vma(vma, rq->context->state, "HW context", gfp); @@ -1427,30 +1492,24 @@ intel_engine_coredump_add_vma(struct intel_engine_coredump *ee, while (capture) { struct intel_engine_capture_vma *this = capture; - struct i915_vma *vma = this->vma; + struct i915_vma_snapshot *vsnap = this->vsnap; add_vma(ee, i915_vma_coredump_create(engine->gt, - vma, this->name, - compress)); + vsnap, compress)); - i915_active_release(&vma->active); + i915_vma_snapshot_resource_unpin(vsnap, this->lockdep_cookie); + i915_vma_snapshot_put(vsnap); capture = this->next; kfree(this); } - add_vma(ee, - i915_vma_coredump_create(engine->gt, - engine->status_page.vma, - "HW Status", - compress)); + add_vma_coredump(ee, engine->gt, engine->status_page.vma, + "HW Status", compress); - add_vma(ee, - i915_vma_coredump_create(engine->gt, - engine->wa_ctx.vma, - "WA context", - compress)); + add_vma_coredump(ee, engine->gt, engine->wa_ctx.vma, + "WA context", compress); } static struct intel_engine_coredump * @@ -1486,17 +1545,25 @@ capture_engine(struct intel_engine_cs *engine, } } if (rq) - capture = intel_engine_coredump_add_request(ee, rq, - ATOMIC_MAYFAIL); + rq = i915_request_get_rcu(rq); + + if (!rq) + goto no_request_capture; + + capture = intel_engine_coredump_add_request(ee, rq, ATOMIC_MAYFAIL); if (!capture) { -no_request_capture: - kfree(ee); - return NULL; + i915_request_put(rq); + goto no_request_capture; } intel_engine_coredump_add_vma(ee, capture, compress); + i915_request_put(rq); return ee; + +no_request_capture: + kfree(ee); + return NULL; } static void @@ -1550,10 +1617,8 @@ gt_record_uc(struct intel_gt_coredump *gt, */ error_uc->guc_fw.path = kstrdup(uc->guc.fw.path, ALLOW_FAIL); error_uc->huc_fw.path = kstrdup(uc->huc.fw.path, ALLOW_FAIL); - error_uc->guc_log = - i915_vma_coredump_create(gt->_gt, - uc->guc.log.vma, "GuC log buffer", - compress); + error_uc->guc_log = create_vma_coredump(gt->_gt, uc->guc.log.vma, + "GuC log buffer", compress); return error_uc; } @@ -1750,10 +1815,7 @@ static void capture_gen(struct i915_gpu_coredump *error) error->wakelock = atomic_read(&i915->runtime_pm.wakeref_count); error->suspended = i915->runtime_pm.suspended; - error->iommu = -1; -#ifdef CONFIG_INTEL_IOMMU - error->iommu = intel_iommu_gfx_mapped; -#endif + error->iommu = intel_vtd_active(i915); error->reset_count = i915_reset_count(&i915->gpu_error); error->suspend_count = i915->suspend_count; @@ -1784,7 +1846,7 @@ i915_gpu_coredump_alloc(struct drm_i915_private *i915, gfp_t gfp) error->time = ktime_get_real(); error->boottime = ktime_get_boottime(); - error->uptime = ktime_sub(ktime_get(), i915->gt.last_init_time); + error->uptime = ktime_sub(ktime_get(), to_gt(i915)->last_init_time); error->capture = jiffies; capture_gen(error); @@ -1839,8 +1901,8 @@ void i915_vma_capture_finish(struct intel_gt_coredump *gt, kfree(compress); } -struct i915_gpu_coredump * -i915_gpu_coredump(struct intel_gt *gt, intel_engine_mask_t engine_mask) +static struct i915_gpu_coredump * +__i915_gpu_coredump(struct intel_gt *gt, intel_engine_mask_t engine_mask) { struct drm_i915_private *i915 = gt->i915; struct i915_gpu_coredump *error; @@ -1881,6 +1943,22 @@ i915_gpu_coredump(struct intel_gt *gt, intel_engine_mask_t engine_mask) return error; } +struct i915_gpu_coredump * +i915_gpu_coredump(struct intel_gt *gt, intel_engine_mask_t engine_mask) +{ + static DEFINE_MUTEX(capture_mutex); + int ret = mutex_lock_interruptible(&capture_mutex); + struct i915_gpu_coredump *dump; + + if (ret) + return ERR_PTR(ret); + + dump = __i915_gpu_coredump(gt, engine_mask); + mutex_unlock(&capture_mutex); + + return dump; +} + void i915_error_state_store(struct i915_gpu_coredump *error) { struct drm_i915_private *i915; diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h index b98d8cdbe4f2..5aedf5129814 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.h +++ b/drivers/gpu/drm/i915/i915_gpu_error.h @@ -39,10 +39,8 @@ struct i915_vma_coredump { u64 gtt_size; u32 gtt_page_sizes; - int num_pages; - int page_count; int unused; - u32 *pages[]; + struct list_head page_list; }; struct i915_request_coredump { diff --git a/drivers/gpu/drm/i915/i915_iosf_mbi.h b/drivers/gpu/drm/i915/i915_iosf_mbi.h new file mode 100644 index 000000000000..8f81b7603d37 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_iosf_mbi.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef __I915_IOSF_MBI_H__ +#define __I915_IOSF_MBI_H__ + +#if IS_ENABLED(CONFIG_IOSF_MBI) +#include <asm/iosf_mbi.h> +#else + +/* Stubs to compile for all non-x86 archs */ +#define MBI_PMIC_BUS_ACCESS_BEGIN 1 +#define MBI_PMIC_BUS_ACCESS_END 2 + +struct notifier_block; + +static inline void iosf_mbi_punit_acquire(void) {} +static inline void iosf_mbi_punit_release(void) {} +static inline void iosf_mbi_assert_punit_acquired(void) {} + +static inline +int iosf_mbi_register_pmic_bus_access_notifier(struct notifier_block *nb) +{ + return 0; +} + +static inline int +iosf_mbi_unregister_pmic_bus_access_notifier_unlocked(struct notifier_block *nb) +{ + return 0; +} + +static inline +int iosf_mbi_unregister_pmic_bus_access_notifier(struct notifier_block *nb) +{ + return 0; +} +#endif + +#endif /* __I915_IOSF_MBI_H__ */ diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 77680bca46ee..21f75b069fa8 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -35,6 +35,7 @@ #include <drm/drm_drv.h> #include "display/intel_de.h" +#include "display/intel_display_trace.h" #include "display/intel_display_types.h" #include "display/intel_fifo_underrun.h" #include "display/intel_hotplug.h" @@ -49,7 +50,6 @@ #include "i915_drv.h" #include "i915_irq.h" -#include "i915_trace.h" #include "intel_pm.h" /** @@ -224,7 +224,7 @@ static void intel_hpd_init_pins(struct drm_i915_private *dev_priv) static void intel_handle_vblank(struct drm_i915_private *dev_priv, enum pipe pipe) { - struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe); + struct intel_crtc *crtc = intel_crtc_for_pipe(dev_priv, pipe); drm_crtc_handle_vblank(&crtc->base); } @@ -1040,7 +1040,7 @@ static void ivb_parity_work(struct work_struct *work) { struct drm_i915_private *dev_priv = container_of(work, typeof(*dev_priv), l3_parity.error_work); - struct intel_gt *gt = &dev_priv->gt; + struct intel_gt *gt = to_gt(dev_priv); u32 error_status, row, bank, subbank; char *parity_event[6]; u32 misccpctl; @@ -1318,7 +1318,7 @@ static void display_pipe_crc_irq_handler(struct drm_i915_private *dev_priv, u32 crc2, u32 crc3, u32 crc4) { - struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe); + struct intel_crtc *crtc = intel_crtc_for_pipe(dev_priv, pipe); struct intel_pipe_crc *pipe_crc = &crtc->pipe_crc; u32 crcs[5] = { crc0, crc1, crc2, crc3, crc4 }; @@ -1357,7 +1357,7 @@ display_pipe_crc_irq_handler(struct drm_i915_private *dev_priv, static void flip_done_handler(struct drm_i915_private *i915, enum pipe pipe) { - struct intel_crtc *crtc = intel_get_crtc_for_pipe(i915, pipe); + struct intel_crtc *crtc = intel_crtc_for_pipe(i915, pipe); struct drm_crtc_state *crtc_state = crtc->base.state; struct drm_pending_vblank_event *e = crtc_state->event; struct drm_device *dev = &i915->drm; @@ -1718,9 +1718,9 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg) intel_uncore_write(&dev_priv->uncore, VLV_MASTER_IER, MASTER_INTERRUPT_ENABLE); if (gt_iir) - gen6_gt_irq_handler(&dev_priv->gt, gt_iir); + gen6_gt_irq_handler(to_gt(dev_priv), gt_iir); if (pm_iir) - gen6_rps_irq_handler(&dev_priv->gt.rps, pm_iir); + gen6_rps_irq_handler(&to_gt(dev_priv)->rps, pm_iir); if (hotplug_status) i9xx_hpd_irq_handler(dev_priv, hotplug_status); @@ -1777,7 +1777,7 @@ static irqreturn_t cherryview_irq_handler(int irq, void *arg) ier = intel_uncore_read(&dev_priv->uncore, VLV_IER); intel_uncore_write(&dev_priv->uncore, VLV_IER, 0); - gen8_gt_irq_handler(&dev_priv->gt, master_ctl); + gen8_gt_irq_handler(to_gt(dev_priv), master_ctl); if (iir & I915_DISPLAY_PORT_INTERRUPT) hotplug_status = i9xx_hpd_irq_ack(dev_priv); @@ -2108,7 +2108,7 @@ static void ilk_display_irq_handler(struct drm_i915_private *dev_priv, } if (DISPLAY_VER(dev_priv) == 5 && de_iir & DE_PCU_EVENT) - gen5_rps_irq_handler(&dev_priv->gt.rps); + gen5_rps_irq_handler(&to_gt(dev_priv)->rps); } static void ivb_display_irq_handler(struct drm_i915_private *dev_priv, @@ -2189,9 +2189,9 @@ static irqreturn_t ilk_irq_handler(int irq, void *arg) if (gt_iir) { raw_reg_write(regs, GTIIR, gt_iir); if (GRAPHICS_VER(i915) >= 6) - gen6_gt_irq_handler(&i915->gt, gt_iir); + gen6_gt_irq_handler(to_gt(i915), gt_iir); else - gen5_gt_irq_handler(&i915->gt, gt_iir); + gen5_gt_irq_handler(to_gt(i915), gt_iir); ret = IRQ_HANDLED; } @@ -2209,7 +2209,7 @@ static irqreturn_t ilk_irq_handler(int irq, void *arg) u32 pm_iir = raw_reg_read(regs, GEN6_PMIIR); if (pm_iir) { raw_reg_write(regs, GEN6_PMIIR, pm_iir); - gen6_rps_irq_handler(&i915->gt.rps, pm_iir); + gen6_rps_irq_handler(&to_gt(i915)->rps, pm_iir); ret = IRQ_HANDLED; } } @@ -2635,7 +2635,7 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg) } /* Find, queue (onto bottom-halves), then clear each source */ - gen8_gt_irq_handler(&dev_priv->gt, master_ctl); + gen8_gt_irq_handler(to_gt(dev_priv), master_ctl); /* IRQs are synced during runtime_suspend, we don't require a wakeref */ if (master_ctl & ~GEN8_GT_IRQS) { @@ -2715,7 +2715,7 @@ static irqreturn_t gen11_irq_handler(int irq, void *arg) { struct drm_i915_private *i915 = arg; void __iomem * const regs = i915->uncore.regs; - struct intel_gt *gt = &i915->gt; + struct intel_gt *gt = to_gt(i915); u32 master_ctl; u32 gu_misc_iir; @@ -2771,8 +2771,8 @@ static inline void dg1_master_intr_enable(void __iomem * const regs) static irqreturn_t dg1_irq_handler(int irq, void *arg) { struct drm_i915_private * const i915 = arg; - struct intel_gt *gt = &i915->gt; - void __iomem * const regs = i915->uncore.regs; + struct intel_gt *gt = to_gt(i915); + void __iomem * const regs = gt->uncore->regs; u32 master_tile_ctl, master_ctl; u32 gu_misc_iir; @@ -3016,7 +3016,7 @@ static void vlv_display_irq_reset(struct drm_i915_private *dev_priv) if (IS_CHERRYVIEW(dev_priv)) intel_uncore_write(uncore, DPINVGTT, DPINVGTT_STATUS_MASK_CHV); else - intel_uncore_write(uncore, DPINVGTT, DPINVGTT_STATUS_MASK); + 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)); @@ -3075,7 +3075,7 @@ static void ilk_irq_reset(struct drm_i915_private *dev_priv) intel_uncore_write(uncore, EDP_PSR_IIR, 0xffffffff); } - gen5_gt_irq_reset(&dev_priv->gt); + gen5_gt_irq_reset(to_gt(dev_priv)); ibx_irq_reset(dev_priv); } @@ -3085,7 +3085,7 @@ static void valleyview_irq_reset(struct drm_i915_private *dev_priv) intel_uncore_write(&dev_priv->uncore, VLV_MASTER_IER, 0); intel_uncore_posting_read(&dev_priv->uncore, VLV_MASTER_IER); - gen5_gt_irq_reset(&dev_priv->gt); + gen5_gt_irq_reset(to_gt(dev_priv)); spin_lock_irq(&dev_priv->irq_lock); if (dev_priv->display_irqs_enabled) @@ -3119,7 +3119,7 @@ static void gen8_irq_reset(struct drm_i915_private *dev_priv) gen8_master_intr_disable(dev_priv->uncore.regs); - gen8_gt_irq_reset(&dev_priv->gt); + gen8_gt_irq_reset(to_gt(dev_priv)); gen8_display_irq_reset(dev_priv); GEN3_IRQ_RESET(uncore, GEN8_PCU_); @@ -3173,11 +3173,12 @@ static void gen11_display_irq_reset(struct drm_i915_private *dev_priv) static void gen11_irq_reset(struct drm_i915_private *dev_priv) { - struct intel_uncore *uncore = &dev_priv->uncore; + struct intel_gt *gt = to_gt(dev_priv); + struct intel_uncore *uncore = gt->uncore; gen11_master_intr_disable(dev_priv->uncore.regs); - gen11_gt_irq_reset(&dev_priv->gt); + gen11_gt_irq_reset(gt); gen11_display_irq_reset(dev_priv); GEN3_IRQ_RESET(uncore, GEN11_GU_MISC_); @@ -3186,11 +3187,12 @@ static void gen11_irq_reset(struct drm_i915_private *dev_priv) static void dg1_irq_reset(struct drm_i915_private *dev_priv) { - struct intel_uncore *uncore = &dev_priv->uncore; + struct intel_gt *gt = to_gt(dev_priv); + struct intel_uncore *uncore = gt->uncore; dg1_master_intr_disable(dev_priv->uncore.regs); - gen11_gt_irq_reset(&dev_priv->gt); + gen11_gt_irq_reset(gt); gen11_display_irq_reset(dev_priv); GEN3_IRQ_RESET(uncore, GEN11_GU_MISC_); @@ -3250,7 +3252,7 @@ static void cherryview_irq_reset(struct drm_i915_private *dev_priv) intel_uncore_write(&dev_priv->uncore, GEN8_MASTER_IRQ, 0); intel_uncore_posting_read(&dev_priv->uncore, GEN8_MASTER_IRQ); - gen8_gt_irq_reset(&dev_priv->gt); + gen8_gt_irq_reset(to_gt(dev_priv)); GEN3_IRQ_RESET(uncore, GEN8_PCU_); @@ -3707,7 +3709,7 @@ static void ilk_irq_postinstall(struct drm_i915_private *dev_priv) ibx_irq_postinstall(dev_priv); - gen5_gt_irq_postinstall(&dev_priv->gt); + gen5_gt_irq_postinstall(to_gt(dev_priv)); GEN3_IRQ_INIT(uncore, DE, dev_priv->irq_mask, display_mask | extra_mask); @@ -3744,7 +3746,7 @@ void valleyview_disable_display_irqs(struct drm_i915_private *dev_priv) static void valleyview_irq_postinstall(struct drm_i915_private *dev_priv) { - gen5_gt_irq_postinstall(&dev_priv->gt); + gen5_gt_irq_postinstall(to_gt(dev_priv)); spin_lock_irq(&dev_priv->irq_lock); if (dev_priv->display_irqs_enabled) @@ -3850,7 +3852,7 @@ static void gen8_irq_postinstall(struct drm_i915_private *dev_priv) else if (HAS_PCH_SPLIT(dev_priv)) ibx_irq_postinstall(dev_priv); - gen8_gt_irq_postinstall(&dev_priv->gt); + gen8_gt_irq_postinstall(to_gt(dev_priv)); gen8_de_irq_postinstall(dev_priv); gen8_master_intr_enable(dev_priv->uncore.regs); @@ -3869,13 +3871,14 @@ static void gen11_de_irq_postinstall(struct drm_i915_private *dev_priv) static void gen11_irq_postinstall(struct drm_i915_private *dev_priv) { - struct intel_uncore *uncore = &dev_priv->uncore; + struct intel_gt *gt = to_gt(dev_priv); + struct intel_uncore *uncore = gt->uncore; u32 gu_misc_masked = GEN11_GU_MISC_GSE; if (INTEL_PCH_TYPE(dev_priv) >= PCH_ICP) icp_irq_postinstall(dev_priv); - gen11_gt_irq_postinstall(&dev_priv->gt); + gen11_gt_irq_postinstall(gt); gen11_de_irq_postinstall(dev_priv); GEN3_IRQ_INIT(uncore, GEN11_GU_MISC_, ~gu_misc_masked, gu_misc_masked); @@ -3886,10 +3889,11 @@ static void gen11_irq_postinstall(struct drm_i915_private *dev_priv) static void dg1_irq_postinstall(struct drm_i915_private *dev_priv) { - struct intel_uncore *uncore = &dev_priv->uncore; + struct intel_gt *gt = to_gt(dev_priv); + struct intel_uncore *uncore = gt->uncore; u32 gu_misc_masked = GEN11_GU_MISC_GSE; - gen11_gt_irq_postinstall(&dev_priv->gt); + gen11_gt_irq_postinstall(gt); GEN3_IRQ_INIT(uncore, GEN11_GU_MISC_, ~gu_misc_masked, gu_misc_masked); @@ -3900,13 +3904,13 @@ static void dg1_irq_postinstall(struct drm_i915_private *dev_priv) GEN11_DISPLAY_IRQ_ENABLE); } - dg1_master_intr_enable(dev_priv->uncore.regs); - intel_uncore_posting_read(&dev_priv->uncore, DG1_MSTR_TILE_INTR); + dg1_master_intr_enable(uncore->regs); + intel_uncore_posting_read(uncore, DG1_MSTR_TILE_INTR); } static void cherryview_irq_postinstall(struct drm_i915_private *dev_priv) { - gen8_gt_irq_postinstall(&dev_priv->gt); + gen8_gt_irq_postinstall(to_gt(dev_priv)); spin_lock_irq(&dev_priv->irq_lock); if (dev_priv->display_irqs_enabled) @@ -4069,7 +4073,7 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg) intel_uncore_write16(&dev_priv->uncore, GEN2_IIR, iir); if (iir & I915_USER_INTERRUPT) - intel_engine_cs_irq(dev_priv->gt.engine[RCS0], iir); + intel_engine_cs_irq(to_gt(dev_priv)->engine[RCS0], iir); if (iir & I915_MASTER_ERROR_INTERRUPT) i8xx_error_irq_handler(dev_priv, eir, eir_stuck); @@ -4177,7 +4181,7 @@ static irqreturn_t i915_irq_handler(int irq, void *arg) intel_uncore_write(&dev_priv->uncore, GEN2_IIR, iir); if (iir & I915_USER_INTERRUPT) - intel_engine_cs_irq(dev_priv->gt.engine[RCS0], iir); + intel_engine_cs_irq(to_gt(dev_priv)->engine[RCS0], iir); if (iir & I915_MASTER_ERROR_INTERRUPT) i9xx_error_irq_handler(dev_priv, eir, eir_stuck); @@ -4322,11 +4326,11 @@ static irqreturn_t i965_irq_handler(int irq, void *arg) intel_uncore_write(&dev_priv->uncore, GEN2_IIR, iir); if (iir & I915_USER_INTERRUPT) - intel_engine_cs_irq(dev_priv->gt.engine[RCS0], + intel_engine_cs_irq(to_gt(dev_priv)->engine[RCS0], iir); if (iir & I915_BSD_USER_INTERRUPT) - intel_engine_cs_irq(dev_priv->gt.engine[VCS0], + intel_engine_cs_irq(to_gt(dev_priv)->engine[VCS0], iir >> 25); if (iir & I915_MASTER_ERROR_INTERRUPT) @@ -4377,7 +4381,7 @@ void intel_irq_init(struct drm_i915_private *dev_priv) /* pre-gen11 the guc irqs bits are in the upper 16 bits of the pm reg */ if (HAS_GT_UC(dev_priv) && GRAPHICS_VER(dev_priv) < 11) - dev_priv->gt.pm_guc_events = GUC_INTR_GUC2HOST << 16; + to_gt(dev_priv)->pm_guc_events = GUC_INTR_GUC2HOST << 16; if (!HAS_DISPLAY(dev_priv)) return; diff --git a/drivers/gpu/drm/i915/i915_mm.c b/drivers/gpu/drm/i915/i915_mm.c index 666808cb3a32..7998bc74ab49 100644 --- a/drivers/gpu/drm/i915/i915_mm.c +++ b/drivers/gpu/drm/i915/i915_mm.c @@ -27,6 +27,7 @@ #include "i915_drv.h" +#include "i915_mm.h" struct remap_pfn { struct mm_struct *mm; @@ -37,17 +38,6 @@ struct remap_pfn { resource_size_t iobase; }; -static int remap_pfn(pte_t *pte, unsigned long addr, void *data) -{ - struct remap_pfn *r = data; - - /* Special PTE are not associated with any struct page */ - set_pte_at(r->mm, addr, pte, pte_mkspecial(pfn_pte(r->pfn, r->prot))); - r->pfn++; - - return 0; -} - #define use_dma(io) ((io) != -1) static inline unsigned long sgt_pfn(const struct remap_pfn *r) @@ -77,6 +67,20 @@ static int remap_sg(pte_t *pte, unsigned long addr, void *data) return 0; } +#define EXPECTED_FLAGS (VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP) + +#if IS_ENABLED(CONFIG_X86) +static int remap_pfn(pte_t *pte, unsigned long addr, void *data) +{ + struct remap_pfn *r = data; + + /* Special PTE are not associated with any struct page */ + set_pte_at(r->mm, addr, pte, pte_mkspecial(pfn_pte(r->pfn, r->prot))); + r->pfn++; + + return 0; +} + /** * remap_io_mapping - remap an IO mapping to userspace * @vma: user vma to map to @@ -94,7 +98,6 @@ int remap_io_mapping(struct vm_area_struct *vma, struct remap_pfn r; int err; -#define EXPECTED_FLAGS (VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP) GEM_BUG_ON((vma->vm_flags & EXPECTED_FLAGS) != EXPECTED_FLAGS); /* We rely on prevalidation of the io-mapping to skip track_pfn(). */ @@ -111,6 +114,7 @@ int remap_io_mapping(struct vm_area_struct *vma, return 0; } +#endif /** * remap_io_sg - remap an IO mapping to userspace diff --git a/drivers/gpu/drm/i915/i915_mm.h b/drivers/gpu/drm/i915/i915_mm.h new file mode 100644 index 000000000000..76f1d53bdf34 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_mm.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef __I915_MM_H__ +#define __I915_MM_H__ + +#include <linux/types.h> + +struct vm_area_struct; +struct io_mapping; +struct scatterlist; + +#if IS_ENABLED(CONFIG_X86) +int remap_io_mapping(struct vm_area_struct *vma, + unsigned long addr, unsigned long pfn, unsigned long size, + struct io_mapping *iomap); +#else +static inline +int remap_io_mapping(struct vm_area_struct *vma, + unsigned long addr, unsigned long pfn, unsigned long size, + struct io_mapping *iomap) +{ + pr_err("Architecture has no %s() and shouldn't be calling this function\n", __func__); + WARN_ON_ONCE(1); + return 0; +} +#endif + +int remap_io_sg(struct vm_area_struct *vma, + unsigned long addr, unsigned long size, + struct scatterlist *sgl, resource_size_t iobase); + +#endif /* __I915_MM_H__ */ diff --git a/drivers/gpu/drm/i915/i915_module.c b/drivers/gpu/drm/i915/i915_module.c index ab2295dd4500..f6bcd2f89257 100644 --- a/drivers/gpu/drm/i915/i915_module.c +++ b/drivers/gpu/drm/i915/i915_module.c @@ -4,7 +4,7 @@ * Copyright © 2021 Intel Corporation */ -#include <linux/console.h> +#include <drm/drm_drv.h> #include "gem/i915_gem_context.h" #include "gem/i915_gem_object.h" @@ -24,14 +24,14 @@ static int i915_check_nomodeset(void) /* * Enable KMS by default, unless explicitly overriden by - * either the i915.modeset prarameter or by the - * vga_text_mode_force boot option. + * either the i915.modeset parameter or by the + * nomodeset boot option. */ if (i915_modparams.modeset == 0) use_kms = false; - if (vgacon_text_force() && i915_modparams.modeset == -1) + if (drm_firmware_drivers_only() && i915_modparams.modeset == -1) use_kms = false; if (!use_kms) { diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c index e07f4cfea63a..525ae832aa9a 100644 --- a/drivers/gpu/drm/i915/i915_params.c +++ b/drivers/gpu/drm/i915/i915_params.c @@ -140,6 +140,9 @@ i915_param_named_unsafe(invert_brightness, int, 0400, i915_param_named(disable_display, bool, 0400, "Disable display (default: false)"); +i915_param_named(memtest, bool, 0400, + "Perform a read/write test of all device memory on module load (default: off)"); + i915_param_named(mmio_debug, int, 0400, "Enable the MMIO debug code for the first N failures (default: off). " "This may negatively affect performance."); diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h index 8d725b64592d..c9d53ff910a0 100644 --- a/drivers/gpu/drm/i915/i915_params.h +++ b/drivers/gpu/drm/i915/i915_params.h @@ -64,6 +64,7 @@ struct drm_printer; param(char *, guc_firmware_path, NULL, 0400) \ param(char *, huc_firmware_path, NULL, 0400) \ param(char *, dmc_firmware_path, NULL, 0400) \ + param(bool, memtest, false, 0400) \ param(int, mmio_debug, -IS_ENABLED(CONFIG_DRM_I915_DEBUG_MMIO), 0600) \ param(int, edp_vswing, 0, 0400) \ param(unsigned int, reset, 3, 0600) \ diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 169837de395d..261294df535c 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -22,18 +22,17 @@ * */ -#include <linux/vga_switcheroo.h> - #include <drm/drm_drv.h> #include <drm/i915_pciids.h> +#include "i915_driver.h" #include "i915_drv.h" #include "i915_pci.h" #define PLATFORM(x) .platform = (x) #define GEN(x) \ - .graphics_ver = (x), \ - .media_ver = (x), \ + .graphics.ver = (x), \ + .media.ver = (x), \ .display.ver = (x) #define I845_PIPE_OFFSETS \ @@ -145,6 +144,12 @@ .degamma_lut_tests = DRM_COLOR_LUT_NON_DECREASING | \ DRM_COLOR_LUT_EQUAL_CHANNELS, \ } +#define ICL_COLORS \ + .color = { .degamma_lut_size = 33, .gamma_lut_size = 262145, \ + .degamma_lut_tests = DRM_COLOR_LUT_NON_DECREASING | \ + DRM_COLOR_LUT_EQUAL_CHANNELS, \ + .gamma_lut_tests = DRM_COLOR_LUT_NON_DECREASING, \ + } /* Keep in gen based order, and chronological order within a gen */ @@ -157,8 +162,8 @@ #define I830_FEATURES \ GEN(2), \ .is_mobile = 1, \ - .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ - .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ + .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ + .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ .display.has_overlay = 1, \ .display.cursor_needs_physical = 1, \ .display.overlay_needs_physical = 1, \ @@ -178,8 +183,8 @@ #define I845_FEATURES \ GEN(2), \ - .pipe_mask = BIT(PIPE_A), \ - .cpu_transcoder_mask = BIT(TRANSCODER_A), \ + .display.pipe_mask = BIT(PIPE_A), \ + .display.cpu_transcoder_mask = BIT(TRANSCODER_A), \ .display.has_overlay = 1, \ .display.overlay_needs_physical = 1, \ .display.has_gmch = 1, \ @@ -220,8 +225,8 @@ static const struct intel_device_info i865g_info = { #define GEN3_FEATURES \ GEN(3), \ - .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ - .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ + .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ + .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ .display.has_gmch = 1, \ .gpu_reset_clobbers_display = true, \ .platform_engine_mask = BIT(RCS0), \ @@ -310,8 +315,8 @@ static const struct intel_device_info pnv_m_info = { #define GEN4_FEATURES \ GEN(4), \ - .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ - .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ + .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ + .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ .display.has_hotplug = 1, \ .display.has_gmch = 1, \ .gpu_reset_clobbers_display = true, \ @@ -363,8 +368,8 @@ static const struct intel_device_info gm45_info = { #define GEN5_FEATURES \ GEN(5), \ - .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ - .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ + .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ + .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ .display.has_hotplug = 1, \ .platform_engine_mask = BIT(RCS0) | BIT(VCS0), \ .has_snoop = true, \ @@ -393,8 +398,8 @@ static const struct intel_device_info ilk_m_info = { #define GEN6_FEATURES \ GEN(6), \ - .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ - .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ + .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ + .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ .display.has_hotplug = 1, \ .display.has_fbc = 1, \ .platform_engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0), \ @@ -444,8 +449,8 @@ static const struct intel_device_info snb_m_gt2_info = { #define GEN7_FEATURES \ GEN(7), \ - .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), \ - .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | BIT(TRANSCODER_C), \ + .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), \ + .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | BIT(TRANSCODER_C), \ .display.has_hotplug = 1, \ .display.has_fbc = 1, \ .platform_engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0), \ @@ -499,8 +504,8 @@ static const struct intel_device_info ivb_q_info = { GEN7_FEATURES, PLATFORM(INTEL_IVYBRIDGE), .gt = 2, - .pipe_mask = 0, /* legal, last one wins */ - .cpu_transcoder_mask = 0, + .display.pipe_mask = 0, /* legal, last one wins */ + .display.cpu_transcoder_mask = 0, .has_l3_dpf = 1, }; @@ -508,8 +513,8 @@ static const struct intel_device_info vlv_info = { PLATFORM(INTEL_VALLEYVIEW), GEN(7), .is_lp = 1, - .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), - .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), + .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), + .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), .has_runtime_pm = 1, .has_rc6 = 1, .has_reset_engine = true, @@ -533,7 +538,7 @@ static const struct intel_device_info vlv_info = { #define G75_FEATURES \ GEN7_FEATURES, \ .platform_engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0), \ - .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \ + .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \ BIT(TRANSCODER_C) | BIT(TRANSCODER_EDP), \ .display.has_ddi = 1, \ .display.has_fpga_dbg = 1, \ @@ -603,8 +608,8 @@ static const struct intel_device_info bdw_gt3_info = { static const struct intel_device_info chv_info = { PLATFORM(INTEL_CHERRYVIEW), GEN(8), - .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), - .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | BIT(TRANSCODER_C), + .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), + .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | BIT(TRANSCODER_C), .display.has_hotplug = 1, .is_lp = 1, .platform_engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0), @@ -681,8 +686,8 @@ static const struct intel_device_info skl_gt4_info = { .dbuf.slice_mask = BIT(DBUF_S1), \ .display.has_hotplug = 1, \ .platform_engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0), \ - .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), \ - .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \ + .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), \ + .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \ BIT(TRANSCODER_C) | BIT(TRANSCODER_EDP) | \ BIT(TRANSCODER_DSI_A) | BIT(TRANSCODER_DSI_C), \ .has_64bit_reloc = 1, \ @@ -790,8 +795,8 @@ static const struct intel_device_info cml_gt2_info = { #define GEN11_FEATURES \ GEN9_FEATURES, \ GEN11_DEFAULT_PAGE_SIZES, \ - .abox_mask = BIT(0), \ - .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \ + .display.abox_mask = BIT(0), \ + .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \ BIT(TRANSCODER_C) | BIT(TRANSCODER_EDP) | \ BIT(TRANSCODER_DSI_0) | BIT(TRANSCODER_DSI_1), \ .pipe_offsets = { \ @@ -811,7 +816,7 @@ static const struct intel_device_info cml_gt2_info = { [TRANSCODER_DSI_1] = TRANSCODER_DSI1_OFFSET, \ }, \ GEN(11), \ - .color = { .degamma_lut_size = 33, .gamma_lut_size = 262145 }, \ + ICL_COLORS, \ .dbuf.size = 2048, \ .dbuf.slice_mask = BIT(DBUF_S1) | BIT(DBUF_S2), \ .display.has_dsc = 1, \ @@ -842,9 +847,9 @@ static const struct intel_device_info jsl_info = { #define GEN12_FEATURES \ GEN11_FEATURES, \ GEN(12), \ - .abox_mask = GENMASK(2, 1), \ - .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), \ - .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \ + .display.abox_mask = GENMASK(2, 1), \ + .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), \ + .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \ BIT(TRANSCODER_C) | BIT(TRANSCODER_D) | \ BIT(TRANSCODER_DSI_0) | BIT(TRANSCODER_DSI_1), \ .pipe_offsets = { \ @@ -866,7 +871,7 @@ static const struct intel_device_info jsl_info = { TGL_CURSOR_OFFSETS, \ .has_global_mocs = 1, \ .has_pxp = 1, \ - .display.has_dsb = 1 + .display.has_dsb = 0 /* FIXME: LUT load is broken with DSB */ static const struct intel_device_info tgl_info = { GEN12_FEATURES, @@ -879,9 +884,9 @@ static const struct intel_device_info tgl_info = { static const struct intel_device_info rkl_info = { GEN12_FEATURES, PLATFORM(INTEL_ROCKETLAKE), - .abox_mask = BIT(0), - .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), - .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | + .display.abox_mask = BIT(0), + .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), + .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | BIT(TRANSCODER_C), .display.has_hti = 1, .display.has_psr_hw_tracking = 0, @@ -899,9 +904,9 @@ static const struct intel_device_info rkl_info = { static const struct intel_device_info dg1_info = { GEN12_FEATURES, DGFX_FEATURES, - .graphics_rel = 10, + .graphics.rel = 10, PLATFORM(INTEL_DG1), - .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), + .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), .require_force_probe = 1, .platform_engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | @@ -913,7 +918,7 @@ static const struct intel_device_info dg1_info = { static const struct intel_device_info adl_s_info = { GEN12_FEATURES, PLATFORM(INTEL_ALDERLAKE_S), - .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), + .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), .display.has_hti = 1, .display.has_psr_hw_tracking = 0, .platform_engine_mask = @@ -930,10 +935,11 @@ static const struct intel_device_info adl_s_info = { } #define XE_LPD_FEATURES \ - .abox_mask = GENMASK(1, 0), \ - .color = { .degamma_lut_size = 0, .gamma_lut_size = 0 }, \ - .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \ - BIT(TRANSCODER_C) | BIT(TRANSCODER_D), \ + .display.abox_mask = GENMASK(1, 0), \ + .color = { .degamma_lut_size = 128, .gamma_lut_size = 1024, \ + .degamma_lut_tests = DRM_COLOR_LUT_NON_DECREASING | \ + DRM_COLOR_LUT_EQUAL_CHANNELS, \ + }, \ .dbuf.size = 4096, \ .dbuf.slice_mask = BIT(DBUF_S1) | BIT(DBUF_S2) | BIT(DBUF_S3) | \ BIT(DBUF_S4), \ @@ -949,18 +955,22 @@ static const struct intel_device_info adl_s_info = { .display.has_ipc = 1, \ .display.has_psr = 1, \ .display.ver = 13, \ - .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), \ + .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), \ .pipe_offsets = { \ [TRANSCODER_A] = PIPE_A_OFFSET, \ [TRANSCODER_B] = PIPE_B_OFFSET, \ [TRANSCODER_C] = PIPE_C_OFFSET, \ [TRANSCODER_D] = PIPE_D_OFFSET, \ + [TRANSCODER_DSI_0] = PIPE_DSI0_OFFSET, \ + [TRANSCODER_DSI_1] = PIPE_DSI1_OFFSET, \ }, \ .trans_offsets = { \ [TRANSCODER_A] = TRANSCODER_A_OFFSET, \ [TRANSCODER_B] = TRANSCODER_B_OFFSET, \ [TRANSCODER_C] = TRANSCODER_C_OFFSET, \ [TRANSCODER_D] = TRANSCODER_D_OFFSET, \ + [TRANSCODER_DSI_0] = TRANSCODER_DSI0_OFFSET, \ + [TRANSCODER_DSI_1] = TRANSCODER_DSI1_OFFSET, \ }, \ XE_LPD_CURSOR_OFFSETS @@ -968,7 +978,9 @@ static const struct intel_device_info adl_p_info = { GEN12_FEATURES, XE_LPD_FEATURES, PLATFORM(INTEL_ALDERLAKE_P), - .require_force_probe = 1, + .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | + BIT(TRANSCODER_C) | BIT(TRANSCODER_D) | + BIT(TRANSCODER_DSI_0) | BIT(TRANSCODER_DSI_1), .display.has_cdclk_crawl = 1, .display.has_modular_fia = 1, .display.has_psr_hw_tracking = 0, @@ -986,8 +998,8 @@ static const struct intel_device_info adl_p_info = { I915_GTT_PAGE_SIZE_2M #define XE_HP_FEATURES \ - .graphics_ver = 12, \ - .graphics_rel = 50, \ + .graphics.ver = 12, \ + .graphics.rel = 50, \ XE_HP_PAGE_SIZES, \ .dma_mask_size = 46, \ .has_64bit_reloc = 1, \ @@ -1005,8 +1017,8 @@ static const struct intel_device_info adl_p_info = { .ppgtt_type = INTEL_PPGTT_FULL #define XE_HPM_FEATURES \ - .media_ver = 12, \ - .media_rel = 50 + .media.ver = 12, \ + .media.rel = 50 __maybe_unused static const struct intel_device_info xehpsdv_info = { @@ -1015,7 +1027,7 @@ static const struct intel_device_info xehpsdv_info = { DGFX_FEATURES, PLATFORM(INTEL_XEHPSDV), .display = { }, - .pipe_mask = 0, + .has_64k_pages = 1, .platform_engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VECS1) | BIT(VECS2) | BIT(VECS3) | @@ -1030,14 +1042,17 @@ static const struct intel_device_info dg2_info = { XE_HPM_FEATURES, XE_LPD_FEATURES, DGFX_FEATURES, - .graphics_rel = 55, - .media_rel = 55, + .graphics.rel = 55, + .media.rel = 55, PLATFORM(INTEL_DG2), + .has_64k_pages = 1, .platform_engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VECS1) | BIT(VCS0) | BIT(VCS2), .require_force_probe = 1, + .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | + BIT(TRANSCODER_C) | BIT(TRANSCODER_D), }; #undef PLATFORM @@ -1117,6 +1132,7 @@ static const struct pci_device_id pciidlist[] = { INTEL_ADLS_IDS(&adl_s_info), INTEL_ADLP_IDS(&adl_p_info), INTEL_DG1_IDS(&dg1_info), + INTEL_RPLS_IDS(&adl_s_info), {0, 0, 0} }; MODULE_DEVICE_TABLE(pci, pciidlist); @@ -1189,11 +1205,8 @@ static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (PCI_FUNC(pdev->devfn)) return -ENODEV; - /* - * apple-gmux is needed on dual GPU MacBook Pro - * to probe the panel if we're the inactive GPU. - */ - if (vga_switcheroo_client_probe_defer(pdev)) + /* Detect if we need to wait for other drivers early on */ + if (intel_modeset_probe_defer(pdev)) return -EPROBE_DEFER; err = i915_driver_probe(pdev, ent); diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 2f01b8c0284c..170bba913c30 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -4443,7 +4443,7 @@ void i915_perf_init(struct drm_i915_private *i915) mutex_init(&perf->lock); /* Choose a representative limit */ - oa_sample_rate_hard_limit = i915->gt.clock_frequency / 2; + oa_sample_rate_hard_limit = to_gt(i915)->clock_frequency / 2; mutex_init(&perf->metrics_lock); idr_init_base(&perf->metrics_idr, 1); diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index 0b488d49694c..ea655161793e 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -210,8 +210,8 @@ static void init_rc6(struct i915_pmu *pmu) struct drm_i915_private *i915 = container_of(pmu, typeof(*i915), pmu); intel_wakeref_t wakeref; - with_intel_runtime_pm(i915->gt.uncore->rpm, wakeref) { - pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(&i915->gt); + with_intel_runtime_pm(to_gt(i915)->uncore->rpm, wakeref) { + pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(to_gt(i915)); pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur = pmu->sample[__I915_SAMPLE_RC6].cur; pmu->sleep_last = ktime_get_raw(); @@ -222,7 +222,7 @@ static void park_rc6(struct drm_i915_private *i915) { struct i915_pmu *pmu = &i915->pmu; - pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(&i915->gt); + pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(to_gt(i915)); pmu->sleep_last = ktime_get_raw(); } @@ -419,7 +419,7 @@ static enum hrtimer_restart i915_sample(struct hrtimer *hrtimer) struct drm_i915_private *i915 = container_of(hrtimer, struct drm_i915_private, pmu.timer); struct i915_pmu *pmu = &i915->pmu; - struct intel_gt *gt = &i915->gt; + struct intel_gt *gt = to_gt(i915); unsigned int period_ns; ktime_t now; @@ -476,7 +476,7 @@ engine_event_status(struct intel_engine_cs *engine, static int config_status(struct drm_i915_private *i915, u64 config) { - struct intel_gt *gt = &i915->gt; + struct intel_gt *gt = to_gt(i915); switch (config) { case I915_PMU_ACTUAL_FREQUENCY: @@ -601,10 +601,10 @@ static u64 __i915_pmu_event_read(struct perf_event *event) val = READ_ONCE(pmu->irq_count); break; case I915_PMU_RC6_RESIDENCY: - val = get_rc6(&i915->gt); + val = get_rc6(to_gt(i915)); break; case I915_PMU_SOFTWARE_GT_AWAKE_TIME: - val = ktime_to_ns(intel_gt_get_awake_time(&i915->gt)); + val = ktime_to_ns(intel_gt_get_awake_time(to_gt(i915))); break; } } diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c index 51b368be0fc4..2dfbc22857a3 100644 --- a/drivers/gpu/drm/i915/i915_query.c +++ b/drivers/gpu/drm/i915/i915_query.c @@ -31,7 +31,7 @@ static int copy_query_item(void *query_hdr, size_t query_sz, static int query_topology_info(struct drm_i915_private *dev_priv, struct drm_i915_query_item *query_item) { - const struct sseu_dev_info *sseu = &dev_priv->gt.info.sseu; + const struct sseu_dev_info *sseu = &to_gt(dev_priv)->info.sseu; struct drm_i915_query_topology_info topo; u32 slice_length, subslice_length, eu_length, total_length; int ret; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index bcee121bec5a..4c28dadf8d69 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -371,6 +371,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define VLV_G3DCTL _MMIO(0x9024) #define VLV_GSCKGCTL _MMIO(0x9028) +#define FBC_LLC_READ_CTRL _MMIO(0x9044) +#define FBC_LLC_FULLY_OPEN REG_BIT(30) + #define GEN6_MBCTL _MMIO(0x0907c) #define GEN6_MBCTL_ENABLE_BOOT_FETCH (1 << 4) #define GEN6_MBCTL_CTX_FETCH_NEEDED (1 << 3) @@ -498,6 +501,18 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define ECOBITS_PPGTT_CACHE64B (3 << 8) #define ECOBITS_PPGTT_CACHE4B (0 << 8) +#define GEN12_GAMCNTRL_CTRL _MMIO(0xcf54) +#define INVALIDATION_BROADCAST_MODE_DIS REG_BIT(12) +#define GLOBAL_INVALIDATION_MODE REG_BIT(2) + +#define GEN12_GAMSTLB_CTRL _MMIO(0xcf4c) +#define CONTROL_BLOCK_CLKGATE_DIS REG_BIT(12) +#define EGRESS_BLOCK_CLKGATE_DIS REG_BIT(11) +#define TAG_BLOCK_CLKGATE_DIS REG_BIT(7) + +#define GEN12_MERT_MOD_CTRL _MMIO(0xcf28) +#define FORCE_MISS_FTLB REG_BIT(3) + #define GAB_CTL _MMIO(0x24000) #define GAB_CTL_CONT_AFTER_PAGEFAULT (1 << 8) @@ -719,6 +734,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GEN12_OA_TLB_INV_CR _MMIO(0xceec) +#define GEN12_SQCM _MMIO(0x8724) +#define EN_32B_ACCESS REG_BIT(30) + /* Gen12 OAR unit */ #define GEN12_OAR_OACONTROL _MMIO(0x2960) #define GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT 1 @@ -770,6 +788,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define EU_PERF_CNTL5 _MMIO(0xe55c) #define EU_PERF_CNTL6 _MMIO(0xe65c) +#define RT_CTRL _MMIO(0xe530) +#define DIS_NULL_QUERY REG_BIT(10) + /* * OA Boolean state */ @@ -2244,6 +2265,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define SNPS_PHY_MPLLB_DP2_MODE REG_BIT(9) #define SNPS_PHY_MPLLB_WORD_DIV2_EN REG_BIT(8) #define SNPS_PHY_MPLLB_TX_CLK_DIV REG_GENMASK(7, 5) +#define SNPS_PHY_MPLLB_SHIM_DIV32_CLK_SEL REG_BIT(0) #define SNPS_PHY_MPLLB_FRACN1(phy) _MMIO_SNPS(phy, 0x168008) #define SNPS_PHY_MPLLB_FRACN_EN REG_BIT(31) @@ -2662,6 +2684,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define RING_WAIT (1 << 11) /* gen3+, PRBx_CTL */ #define RING_WAIT_SEMAPHORE (1 << 10) /* gen6+ */ +#define GUCPMTIMESTAMP _MMIO(0xC3E8) + /* There are 16 64-bit CS General Purpose Registers per-engine on Gen8+ */ #define GEN8_RING_CS_GPR(base, n) _MMIO((base) + 0x600 + (n) * 8) #define GEN8_RING_CS_GPR_UDW(base, n) _MMIO((base) + 0x600 + (n) * 8 + 4) @@ -2772,6 +2796,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define VDBOX_CGCTL3F10(base) _MMIO((base) + 0x3f10) #define IECPUNIT_CLKGATE_DIS REG_BIT(22) +#define VDBOX_CGCTL3F18(base) _MMIO((base) + 0x3f18) +#define ALNUNIT_CLKGATE_DIS REG_BIT(13) + #define ERROR_GEN6 _MMIO(0x40a0) #define GEN7_ERR_INT _MMIO(0x44040) #define ERR_INT_POISON (1 << 31) @@ -2795,12 +2822,12 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GEN12_AUX_ERR_DBG _MMIO(0x43f4) #define FPGA_DBG _MMIO(0x42300) -#define FPGA_DBG_RM_NOCLAIM (1 << 31) +#define FPGA_DBG_RM_NOCLAIM REG_BIT(31) #define CLAIM_ER _MMIO(VLV_DISPLAY_BASE + 0x2028) -#define CLAIM_ER_CLR (1 << 31) -#define CLAIM_ER_OVERFLOW (1 << 16) -#define CLAIM_ER_CTR_MASK 0xffff +#define CLAIM_ER_CLR REG_BIT(31) +#define CLAIM_ER_OVERFLOW REG_BIT(16) +#define CLAIM_ER_CTR_MASK REG_GENMASK(15, 0) #define DERRMR _MMIO(0x44050) /* Note that HBLANK events are reserved on bdw+ */ @@ -2870,6 +2897,15 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE (1 << 2) #define GEN11_ENABLE_32_PLANE_MODE (1 << 7) +#define SCCGCTL94DC _MMIO(0x94dc) +#define CG3DDISURB REG_BIT(14) + +#define MLTICTXCTL _MMIO(0xb170) +#define TDONRENDER REG_BIT(2) + +#define L3SQCREG1_CCS0 _MMIO(0xb200) +#define FLUSHALLNONCOH REG_BIT(5) + /* WaClearTdlStateAckDirtyBits */ #define GEN8_STATE_ACK _MMIO(0x20F0) #define GEN9_STATE_ACK_SLICE1 _MMIO(0x20F8) @@ -3106,7 +3142,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GEN9_RCS_FE_FSM2 _MMIO(0x22a4) #define GEN10_CACHE_MODE_SS _MMIO(0xe420) -#define FLOAT_BLEND_OPTIMIZATION_ENABLE (1 << 4) +#define ENABLE_PREFETCH_INTO_IC REG_BIT(3) +#define FLOAT_BLEND_OPTIMIZATION_ENABLE REG_BIT(4) /* Fuse readout registers for GT */ #define HSW_PAVP_FUSE1 _MMIO(0x911C) @@ -3307,93 +3344,98 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define FBC_CFB_BASE _MMIO(0x3200) /* 4k page aligned */ #define FBC_LL_BASE _MMIO(0x3204) /* 4k page aligned */ #define FBC_CONTROL _MMIO(0x3208) -#define FBC_CTL_EN REG_BIT(31) -#define FBC_CTL_PERIODIC REG_BIT(30) -#define FBC_CTL_INTERVAL_MASK REG_GENMASK(29, 16) -#define FBC_CTL_INTERVAL(x) REG_FIELD_PREP(FBC_CTL_INTERVAL_MASK, (x)) -#define FBC_CTL_STOP_ON_MOD REG_BIT(15) -#define FBC_CTL_UNCOMPRESSIBLE REG_BIT(14) /* i915+ */ -#define FBC_CTL_C3_IDLE REG_BIT(13) /* i945gm */ -#define FBC_CTL_STRIDE_MASK REG_GENMASK(12, 5) -#define FBC_CTL_STRIDE(x) REG_FIELD_PREP(FBC_CTL_STRIDE_MASK, (x)) -#define FBC_CTL_FENCENO_MASK REG_GENMASK(3, 0) -#define FBC_CTL_FENCENO(x) REG_FIELD_PREP(FBC_CTL_FENCENO_MASK, (x)) +#define FBC_CTL_EN REG_BIT(31) +#define FBC_CTL_PERIODIC REG_BIT(30) +#define FBC_CTL_INTERVAL_MASK REG_GENMASK(29, 16) +#define FBC_CTL_INTERVAL(x) REG_FIELD_PREP(FBC_CTL_INTERVAL_MASK, (x)) +#define FBC_CTL_STOP_ON_MOD REG_BIT(15) +#define FBC_CTL_UNCOMPRESSIBLE REG_BIT(14) /* i915+ */ +#define FBC_CTL_C3_IDLE REG_BIT(13) /* i945gm only */ +#define FBC_CTL_STRIDE_MASK REG_GENMASK(12, 5) +#define FBC_CTL_STRIDE(x) REG_FIELD_PREP(FBC_CTL_STRIDE_MASK, (x)) +#define FBC_CTL_FENCENO_MASK REG_GENMASK(3, 0) +#define FBC_CTL_FENCENO(x) REG_FIELD_PREP(FBC_CTL_FENCENO_MASK, (x)) #define FBC_COMMAND _MMIO(0x320c) -#define FBC_CMD_COMPRESS (1 << 0) +#define FBC_CMD_COMPRESS REG_BIT(0) #define FBC_STATUS _MMIO(0x3210) -#define FBC_STAT_COMPRESSING (1 << 31) -#define FBC_STAT_COMPRESSED (1 << 30) -#define FBC_STAT_MODIFIED (1 << 29) -#define FBC_STAT_CURRENT_LINE_SHIFT (0) -#define FBC_CONTROL2 _MMIO(0x3214) -#define FBC_CTL_FENCE_DBL (0 << 4) -#define FBC_CTL_IDLE_IMM (0 << 2) -#define FBC_CTL_IDLE_FULL (1 << 2) -#define FBC_CTL_IDLE_LINE (2 << 2) -#define FBC_CTL_IDLE_DEBUG (3 << 2) -#define FBC_CTL_CPU_FENCE (1 << 1) -#define FBC_CTL_PLANE(plane) ((plane) << 0) -#define FBC_FENCE_OFF _MMIO(0x3218) /* BSpec typo has 321Bh */ -#define FBC_TAG(i) _MMIO(0x3300 + (i) * 4) +#define FBC_STAT_COMPRESSING REG_BIT(31) +#define FBC_STAT_COMPRESSED REG_BIT(30) +#define FBC_STAT_MODIFIED REG_BIT(29) +#define FBC_STAT_CURRENT_LINE_MASK REG_GENMASK(10, 0) +#define FBC_CONTROL2 _MMIO(0x3214) /* i965gm only */ +#define FBC_CTL_FENCE_DBL REG_BIT(4) +#define FBC_CTL_IDLE_MASK REG_GENMASK(3, 2) +#define FBC_CTL_IDLE_IMM REG_FIELD_PREP(FBC_CTL_IDLE_MASK, 0) +#define FBC_CTL_IDLE_FULL REG_FIELD_PREP(FBC_CTL_IDLE_MASK, 1) +#define FBC_CTL_IDLE_LINE REG_FIELD_PREP(FBC_CTL_IDLE_MASK, 2) +#define FBC_CTL_IDLE_DEBUG REG_FIELD_PREP(FBC_CTL_IDLE_MASK, 3) +#define FBC_CTL_CPU_FENCE_EN REG_BIT(1) +#define FBC_CTL_PLANE_MASK REG_GENMASK(1, 0) +#define FBC_CTL_PLANE(i9xx_plane) REG_FIELD_PREP(FBC_CTL_PLANE_MASK, (i9xx_plane)) +#define FBC_FENCE_OFF _MMIO(0x3218) /* i965gm only, BSpec typo has 321Bh */ +#define FBC_MOD_NUM _MMIO(0x3220) /* i965gm only */ +#define FBC_MOD_NUM_MASK REG_GENMASK(31, 1) +#define FBC_MOD_NUM_VALID REG_BIT(0) +#define FBC_TAG(i) _MMIO(0x3300 + (i) * 4) /* 49 reisters */ +#define FBC_TAG_MASK REG_GENMASK(1, 0) /* 16 tags per register */ +#define FBC_TAG_MODIFIED REG_FIELD_PREP(FBC_TAG_MASK, 0) +#define FBC_TAG_UNCOMPRESSED REG_FIELD_PREP(FBC_TAG_MASK, 1) +#define FBC_TAG_UNCOMPRESSIBLE REG_FIELD_PREP(FBC_TAG_MASK, 2) +#define FBC_TAG_COMPRESSED REG_FIELD_PREP(FBC_TAG_MASK, 3) #define FBC_LL_SIZE (1536) -#define FBC_LLC_READ_CTRL _MMIO(0x9044) -#define FBC_LLC_FULLY_OPEN (1 << 30) - /* Framebuffer compression for GM45+ */ #define DPFC_CB_BASE _MMIO(0x3200) +#define ILK_DPFC_CB_BASE _MMIO(0x43200) #define DPFC_CONTROL _MMIO(0x3208) -#define DPFC_CTL_EN (1 << 31) -#define DPFC_CTL_PLANE(plane) ((plane) << 30) -#define IVB_DPFC_CTL_PLANE(plane) ((plane) << 29) -#define DPFC_CTL_FENCE_EN (1 << 29) -#define IVB_DPFC_CTL_FENCE_EN (1 << 28) -#define DPFC_CTL_PERSISTENT_MODE (1 << 25) -#define DPFC_SR_EN (1 << 10) -#define DPFC_CTL_LIMIT_1X (0 << 6) -#define DPFC_CTL_LIMIT_2X (1 << 6) -#define DPFC_CTL_LIMIT_4X (2 << 6) +#define ILK_DPFC_CONTROL _MMIO(0x43208) +#define DPFC_CTL_EN REG_BIT(31) +#define DPFC_CTL_PLANE_MASK_G4X REG_BIT(30) /* g4x-snb */ +#define DPFC_CTL_PLANE_G4X(i9xx_plane) REG_FIELD_PREP(DPFC_CTL_PLANE_MASK_G4X, (i9xx_plane)) +#define DPFC_CTL_FENCE_EN_G4X REG_BIT(29) /* g4x-snb */ +#define DPFC_CTL_PLANE_MASK_IVB REG_GENMASK(30, 29) /* ivb only */ +#define DPFC_CTL_PLANE_IVB(i9xx_plane) REG_FIELD_PREP(DPFC_CTL_PLANE_MASK_IVB, (i9xx_plane)) +#define DPFC_CTL_FENCE_EN_IVB REG_BIT(28) /* ivb+ */ +#define DPFC_CTL_PERSISTENT_MODE REG_BIT(25) /* g4x-snb */ +#define DPFC_CTL_FALSE_COLOR REG_BIT(10) /* ivb+ */ +#define DPFC_CTL_SR_EN REG_BIT(10) /* g4x only */ +#define DPFC_CTL_SR_EXIT_DIS REG_BIT(9) /* g4x only */ +#define DPFC_CTL_LIMIT_MASK REG_GENMASK(7, 6) +#define DPFC_CTL_LIMIT_1X REG_FIELD_PREP(DPFC_CTL_LIMIT_MASK, 0) +#define DPFC_CTL_LIMIT_2X REG_FIELD_PREP(DPFC_CTL_LIMIT_MASK, 1) +#define DPFC_CTL_LIMIT_4X REG_FIELD_PREP(DPFC_CTL_LIMIT_MASK, 2) +#define DPFC_CTL_FENCENO_MASK REG_GENMASK(3, 0) +#define DPFC_CTL_FENCENO(fence) REG_FIELD_PREP(DPFC_CTL_FENCENO_MASK, (fence)) #define DPFC_RECOMP_CTL _MMIO(0x320c) -#define DPFC_RECOMP_STALL_EN (1 << 27) -#define DPFC_RECOMP_STALL_WM_SHIFT (16) -#define DPFC_RECOMP_STALL_WM_MASK (0x07ff0000) -#define DPFC_RECOMP_TIMER_COUNT_SHIFT (0) -#define DPFC_RECOMP_TIMER_COUNT_MASK (0x0000003f) +#define ILK_DPFC_RECOMP_CTL _MMIO(0x4320c) +#define DPFC_RECOMP_STALL_EN REG_BIT(27) +#define DPFC_RECOMP_STALL_WM_MASK REG_GENMASK(26, 16) +#define DPFC_RECOMP_TIMER_COUNT_MASK REG_GENMASK(5, 0) #define DPFC_STATUS _MMIO(0x3210) -#define DPFC_INVAL_SEG_SHIFT (16) -#define DPFC_INVAL_SEG_MASK (0x07ff0000) -#define DPFC_COMP_SEG_SHIFT (0) -#define DPFC_COMP_SEG_MASK (0x000007ff) +#define ILK_DPFC_STATUS _MMIO(0x43210) +#define DPFC_INVAL_SEG_MASK REG_GENMASK(26, 16) +#define DPFC_COMP_SEG_MASK REG_GENMASK(10, 0) #define DPFC_STATUS2 _MMIO(0x3214) +#define ILK_DPFC_STATUS2 _MMIO(0x43214) +#define DPFC_COMP_SEG_MASK_IVB REG_GENMASK(11, 0) #define DPFC_FENCE_YOFF _MMIO(0x3218) -#define DPFC_CHICKEN _MMIO(0x3224) -#define DPFC_HT_MODIFY (1 << 31) - -/* Framebuffer compression for Ironlake */ -#define ILK_DPFC_CB_BASE _MMIO(0x43200) -#define ILK_DPFC_CONTROL _MMIO(0x43208) -#define FBC_CTL_FALSE_COLOR (1 << 10) -/* The bit 28-8 is reserved */ -#define DPFC_RESERVED (0x1FFFFF00) -#define ILK_DPFC_RECOMP_CTL _MMIO(0x4320c) -#define ILK_DPFC_STATUS _MMIO(0x43210) -#define ILK_DPFC_COMP_SEG_MASK 0x7ff -#define IVB_FBC_STATUS2 _MMIO(0x43214) -#define IVB_FBC_COMP_SEG_MASK 0x7ff -#define BDW_FBC_COMP_SEG_MASK 0xfff #define ILK_DPFC_FENCE_YOFF _MMIO(0x43218) +#define DPFC_CHICKEN _MMIO(0x3224) #define ILK_DPFC_CHICKEN _MMIO(0x43224) -#define ILK_DPFC_DISABLE_DUMMY0 (1 << 8) -#define ILK_DPFC_CHICKEN_COMP_DUMMY_PIXEL (1 << 14) -#define ILK_DPFC_NUKE_ON_ANY_MODIFICATION (1 << 23) +#define DPFC_HT_MODIFY REG_BIT(31) /* pre-ivb */ +#define DPFC_NUKE_ON_ANY_MODIFICATION REG_BIT(23) /* bdw+ */ +#define DPFC_CHICKEN_COMP_DUMMY_PIXEL REG_BIT(14) /* glk+ */ +#define DPFC_DISABLE_DUMMY0 REG_BIT(8) /* ivb+ */ + #define GLK_FBC_STRIDE _MMIO(0x43228) #define FBC_STRIDE_OVERRIDE REG_BIT(15) #define FBC_STRIDE_MASK REG_GENMASK(14, 0) #define FBC_STRIDE(x) REG_FIELD_PREP(FBC_STRIDE_MASK, (x)) + #define ILK_FBC_RT_BASE _MMIO(0x2128) -#define ILK_FBC_RT_VALID (1 << 0) -#define SNB_FBC_FRONT_BUFFER (1 << 1) +#define ILK_FBC_RT_VALID REG_BIT(0) +#define SNB_FBC_FRONT_BUFFER REG_BIT(1) #define ILK_DISPLAY_CHICKEN1 _MMIO(0x42000) #define ILK_FBCQ_DIS (1 << 22) @@ -3417,8 +3459,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) * The following two registers are of type GTTMMADR */ #define SNB_DPFC_CTL_SA _MMIO(0x100100) -#define SNB_CPU_FENCE_ENABLE (1 << 29) -#define DPFC_CPU_FENCE_OFFSET _MMIO(0x100104) +#define SNB_DPFC_FENCE_EN REG_BIT(29) +#define SNB_DPFC_FENCENO_MASK REG_GENMASK(4, 0) +#define SNB_DPFC_FENCENO(fence) REG_FIELD_PREP(SNB_DPFC_FENCENO_MASK, (fence)) +#define SNB_DPFC_CPU_FENCE_OFFSET _MMIO(0x100104) /* Framebuffer compression for Ivybridge */ #define IVB_FBC_RT_BASE _MMIO(0x7020) @@ -3428,8 +3472,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define IPS_ENABLE (1 << 31) #define MSG_FBC_REND_STATE _MMIO(0x50380) -#define FBC_REND_NUKE (1 << 2) -#define FBC_REND_CACHE_CLEAN (1 << 1) +#define FBC_REND_NUKE REG_BIT(2) +#define FBC_REND_CACHE_CLEAN REG_BIT(1) /* * GPIO regs @@ -4278,21 +4322,62 @@ enum { /* * GEN10 clock gating regs */ + +#define UNSLCGCTL9440 _MMIO(0x9440) +#define GAMTLBOACS_CLKGATE_DIS REG_BIT(28) +#define GAMTLBVDBOX5_CLKGATE_DIS REG_BIT(27) +#define GAMTLBVDBOX6_CLKGATE_DIS REG_BIT(26) +#define GAMTLBVDBOX3_CLKGATE_DIS REG_BIT(24) +#define GAMTLBVDBOX4_CLKGATE_DIS REG_BIT(23) +#define GAMTLBVDBOX7_CLKGATE_DIS REG_BIT(22) +#define GAMTLBVDBOX2_CLKGATE_DIS REG_BIT(21) +#define GAMTLBVDBOX0_CLKGATE_DIS REG_BIT(17) +#define GAMTLBKCR_CLKGATE_DIS REG_BIT(16) +#define GAMTLBGUC_CLKGATE_DIS REG_BIT(15) +#define GAMTLBBLT_CLKGATE_DIS REG_BIT(14) +#define GAMTLBVDBOX1_CLKGATE_DIS REG_BIT(6) + +#define UNSLCGCTL9444 _MMIO(0x9444) +#define GAMTLBGFXA0_CLKGATE_DIS REG_BIT(30) +#define GAMTLBGFXA1_CLKGATE_DIS REG_BIT(29) +#define GAMTLBCOMPA0_CLKGATE_DIS REG_BIT(28) +#define GAMTLBCOMPA1_CLKGATE_DIS REG_BIT(27) +#define GAMTLBCOMPB0_CLKGATE_DIS REG_BIT(26) +#define GAMTLBCOMPB1_CLKGATE_DIS REG_BIT(25) +#define GAMTLBCOMPC0_CLKGATE_DIS REG_BIT(24) +#define GAMTLBCOMPC1_CLKGATE_DIS REG_BIT(23) +#define GAMTLBCOMPD0_CLKGATE_DIS REG_BIT(22) +#define GAMTLBCOMPD1_CLKGATE_DIS REG_BIT(21) +#define GAMTLBMERT_CLKGATE_DIS REG_BIT(20) +#define GAMTLBVEBOX3_CLKGATE_DIS REG_BIT(19) +#define GAMTLBVEBOX2_CLKGATE_DIS REG_BIT(18) +#define GAMTLBVEBOX1_CLKGATE_DIS REG_BIT(17) +#define GAMTLBVEBOX0_CLKGATE_DIS REG_BIT(16) +#define LTCDD_CLKGATE_DIS REG_BIT(10) + #define SLICE_UNIT_LEVEL_CLKGATE _MMIO(0x94d4) #define SARBUNIT_CLKGATE_DIS (1 << 5) #define RCCUNIT_CLKGATE_DIS (1 << 7) #define MSCUNIT_CLKGATE_DIS (1 << 10) +#define NODEDSS_CLKGATE_DIS REG_BIT(12) #define L3_CLKGATE_DIS REG_BIT(16) #define L3_CR2X_CLKGATE_DIS REG_BIT(17) #define SUBSLICE_UNIT_LEVEL_CLKGATE _MMIO(0x9524) -#define GWUNIT_CLKGATE_DIS (1 << 16) +#define DSS_ROUTER_CLKGATE_DIS REG_BIT(28) +#define GWUNIT_CLKGATE_DIS REG_BIT(16) #define SUBSLICE_UNIT_LEVEL_CLKGATE2 _MMIO(0x9528) #define CPSSUNIT_CLKGATE_DIS REG_BIT(9) +#define SSMCGCTL9530 _MMIO(0x9530) +#define RTFUNIT_CLKGATE_DIS REG_BIT(18) + #define UNSLICE_UNIT_LEVEL_CLKGATE _MMIO(0x9434) #define VFUNIT_CLKGATE_DIS REG_BIT(20) +#define TSGUNIT_CLKGATE_DIS REG_BIT(17) /* XEHPSDV */ +#define CG3DDISCFEG_CLKGATE_DIS REG_BIT(17) /* DG2 */ +#define GAMEDIA_CLKGATE_DIS REG_BIT(11) #define HSUNIT_CLKGATE_DIS REG_BIT(8) #define VSUNIT_CLKGATE_DIS REG_BIT(3) @@ -4309,47 +4394,52 @@ enum { /* Pipe A CRC regs */ #define _PIPE_CRC_CTL_A 0x60050 -#define PIPE_CRC_ENABLE (1 << 31) +#define PIPE_CRC_ENABLE REG_BIT(31) /* skl+ source selection */ -#define PIPE_CRC_SOURCE_PLANE_1_SKL (0 << 28) -#define PIPE_CRC_SOURCE_PLANE_2_SKL (2 << 28) -#define PIPE_CRC_SOURCE_DMUX_SKL (4 << 28) -#define PIPE_CRC_SOURCE_PLANE_3_SKL (6 << 28) -#define PIPE_CRC_SOURCE_PLANE_4_SKL (7 << 28) -#define PIPE_CRC_SOURCE_PLANE_5_SKL (5 << 28) -#define PIPE_CRC_SOURCE_PLANE_6_SKL (3 << 28) -#define PIPE_CRC_SOURCE_PLANE_7_SKL (1 << 28) +#define PIPE_CRC_SOURCE_MASK_SKL REG_GENMASK(30, 28) +#define PIPE_CRC_SOURCE_PLANE_1_SKL REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_SKL, 0) +#define PIPE_CRC_SOURCE_PLANE_2_SKL REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_SKL, 2) +#define PIPE_CRC_SOURCE_DMUX_SKL REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_SKL, 4) +#define PIPE_CRC_SOURCE_PLANE_3_SKL REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_SKL, 6) +#define PIPE_CRC_SOURCE_PLANE_4_SKL REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_SKL, 7) +#define PIPE_CRC_SOURCE_PLANE_5_SKL REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_SKL, 5) +#define PIPE_CRC_SOURCE_PLANE_6_SKL REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_SKL, 3) +#define PIPE_CRC_SOURCE_PLANE_7_SKL REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_SKL, 1) /* ivb+ source selection */ -#define PIPE_CRC_SOURCE_PRIMARY_IVB (0 << 29) -#define PIPE_CRC_SOURCE_SPRITE_IVB (1 << 29) -#define PIPE_CRC_SOURCE_PF_IVB (2 << 29) +#define PIPE_CRC_SOURCE_MASK_IVB REG_GENMASK(30, 29) +#define PIPE_CRC_SOURCE_PRIMARY_IVB REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_IVB, 0) +#define PIPE_CRC_SOURCE_SPRITE_IVB REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_IVB, 1) +#define PIPE_CRC_SOURCE_PF_IVB REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_IVB, 2) /* ilk+ source selection */ -#define PIPE_CRC_SOURCE_PRIMARY_ILK (0 << 28) -#define PIPE_CRC_SOURCE_SPRITE_ILK (1 << 28) -#define PIPE_CRC_SOURCE_PIPE_ILK (2 << 28) -/* embedded DP port on the north display block, reserved on ivb */ -#define PIPE_CRC_SOURCE_PORT_A_ILK (4 << 28) -#define PIPE_CRC_SOURCE_FDI_ILK (5 << 28) /* reserved on ivb */ +#define PIPE_CRC_SOURCE_MASK_ILK REG_GENMASK(30, 28) +#define PIPE_CRC_SOURCE_PRIMARY_ILK REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_ILK, 0) +#define PIPE_CRC_SOURCE_SPRITE_ILK REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_ILK, 1) +#define PIPE_CRC_SOURCE_PIPE_ILK REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_ILK, 2) +/* embedded DP port on the north display block */ +#define PIPE_CRC_SOURCE_PORT_A_ILK REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_ILK, 4) +#define PIPE_CRC_SOURCE_FDI_ILK REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_ILK, 5) /* vlv source selection */ -#define PIPE_CRC_SOURCE_PIPE_VLV (0 << 27) -#define PIPE_CRC_SOURCE_HDMIB_VLV (1 << 27) -#define PIPE_CRC_SOURCE_HDMIC_VLV (2 << 27) +#define PIPE_CRC_SOURCE_MASK_VLV REG_GENMASK(30, 27) +#define PIPE_CRC_SOURCE_PIPE_VLV REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_VLV, 0) +#define PIPE_CRC_SOURCE_HDMIB_VLV REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_VLV, 1) +#define PIPE_CRC_SOURCE_HDMIC_VLV REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_VLV, 2) /* with DP port the pipe source is invalid */ -#define PIPE_CRC_SOURCE_DP_D_VLV (3 << 27) -#define PIPE_CRC_SOURCE_DP_B_VLV (6 << 27) -#define PIPE_CRC_SOURCE_DP_C_VLV (7 << 27) +#define PIPE_CRC_SOURCE_DP_D_VLV REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_VLV, 3) +#define PIPE_CRC_SOURCE_DP_B_VLV REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_VLV, 6) +#define PIPE_CRC_SOURCE_DP_C_VLV REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_VLV, 7) /* gen3+ source selection */ -#define PIPE_CRC_SOURCE_PIPE_I9XX (0 << 28) -#define PIPE_CRC_SOURCE_SDVOB_I9XX (1 << 28) -#define PIPE_CRC_SOURCE_SDVOC_I9XX (2 << 28) +#define PIPE_CRC_SOURCE_MASK_I9XX REG_GENMASK(30, 28) +#define PIPE_CRC_SOURCE_PIPE_I9XX REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_I9XX, 0) +#define PIPE_CRC_SOURCE_SDVOB_I9XX REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_I9XX, 1) +#define PIPE_CRC_SOURCE_SDVOC_I9XX REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_I9XX, 2) /* with DP/TV port the pipe source is invalid */ -#define PIPE_CRC_SOURCE_DP_D_G4X (3 << 28) -#define PIPE_CRC_SOURCE_TV_PRE (4 << 28) -#define PIPE_CRC_SOURCE_TV_POST (5 << 28) -#define PIPE_CRC_SOURCE_DP_B_G4X (6 << 28) -#define PIPE_CRC_SOURCE_DP_C_G4X (7 << 28) +#define PIPE_CRC_SOURCE_DP_D_G4X REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_I9XX, 3) +#define PIPE_CRC_SOURCE_TV_PRE REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_I9XX, 4) +#define PIPE_CRC_SOURCE_TV_POST REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_I9XX, 5) +#define PIPE_CRC_SOURCE_DP_B_G4X REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_I9XX, 6) +#define PIPE_CRC_SOURCE_DP_C_G4X REG_FIELD_PREP(PIPE_CRC_SOURCE_MASK_I9XX, 7) /* gen2 doesn't have source selection bits */ -#define PIPE_CRC_INCLUDE_BORDER_I8XX (1 << 30) +#define PIPE_CRC_INCLUDE_BORDER_I8XX REG_BIT(30) #define _PIPE_CRC_RES_1_A_IVB 0x60064 #define _PIPE_CRC_RES_2_A_IVB 0x60068 @@ -4698,11 +4788,11 @@ enum { #define PSR_EVENT_LPSP_MODE_EXIT (1 << 1) #define PSR_EVENT_PSR_DISABLE (1 << 0) -#define _PSR2_STATUS_A 0x60940 -#define _PSR2_STATUS_EDP 0x6f940 -#define EDP_PSR2_STATUS(tran) _MMIO_TRANS2(tran, _PSR2_STATUS_A) -#define EDP_PSR2_STATUS_STATE_MASK (0xf << 28) -#define EDP_PSR2_STATUS_STATE_SHIFT 28 +#define _PSR2_STATUS_A 0x60940 +#define _PSR2_STATUS_EDP 0x6f940 +#define EDP_PSR2_STATUS(tran) _MMIO_TRANS2(tran, _PSR2_STATUS_A) +#define EDP_PSR2_STATUS_STATE_MASK REG_GENMASK(31, 28) +#define EDP_PSR2_STATUS_STATE_DEEP_SLEEP REG_FIELD_PREP(EDP_PSR2_STATUS_STATE_MASK, 0x8) #define _PSR2_SU_STATUS_A 0x60914 #define _PSR2_SU_STATUS_EDP 0x6f914 @@ -4999,9 +5089,9 @@ enum { #define PORT_DFT2_G4X _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x61154) #define DC_BALANCE_RESET_VLV (1 << 31) #define PIPE_SCRAMBLE_RESET_MASK ((1 << 14) | (0x3 << 0)) -#define PIPE_C_SCRAMBLE_RESET (1 << 14) /* chv */ -#define PIPE_B_SCRAMBLE_RESET (1 << 1) -#define PIPE_A_SCRAMBLE_RESET (1 << 0) +#define PIPE_C_SCRAMBLE_RESET REG_BIT(14) /* chv */ +#define PIPE_B_SCRAMBLE_RESET REG_BIT(1) +#define PIPE_A_SCRAMBLE_RESET REG_BIT(0) /* Gen 3 SDVO bits: */ #define SDVO_ENABLE (1 << 31) @@ -6266,55 +6356,55 @@ enum { #define PIPE_STATUS_PORT_UNDERRUN_XELPD REG_BIT(26) #define VLV_DPFLIPSTAT _MMIO(VLV_DISPLAY_BASE + 0x70028) -#define PIPEB_LINE_COMPARE_INT_EN (1 << 29) -#define PIPEB_HLINE_INT_EN (1 << 28) -#define PIPEB_VBLANK_INT_EN (1 << 27) -#define SPRITED_FLIP_DONE_INT_EN (1 << 26) -#define SPRITEC_FLIP_DONE_INT_EN (1 << 25) -#define PLANEB_FLIP_DONE_INT_EN (1 << 24) -#define PIPE_PSR_INT_EN (1 << 22) -#define PIPEA_LINE_COMPARE_INT_EN (1 << 21) -#define PIPEA_HLINE_INT_EN (1 << 20) -#define PIPEA_VBLANK_INT_EN (1 << 19) -#define SPRITEB_FLIP_DONE_INT_EN (1 << 18) -#define SPRITEA_FLIP_DONE_INT_EN (1 << 17) -#define PLANEA_FLIPDONE_INT_EN (1 << 16) -#define PIPEC_LINE_COMPARE_INT_EN (1 << 13) -#define PIPEC_HLINE_INT_EN (1 << 12) -#define PIPEC_VBLANK_INT_EN (1 << 11) -#define SPRITEF_FLIPDONE_INT_EN (1 << 10) -#define SPRITEE_FLIPDONE_INT_EN (1 << 9) -#define PLANEC_FLIPDONE_INT_EN (1 << 8) +#define PIPEB_LINE_COMPARE_INT_EN REG_BIT(29) +#define PIPEB_HLINE_INT_EN REG_BIT(28) +#define PIPEB_VBLANK_INT_EN REG_BIT(27) +#define SPRITED_FLIP_DONE_INT_EN REG_BIT(26) +#define SPRITEC_FLIP_DONE_INT_EN REG_BIT(25) +#define PLANEB_FLIP_DONE_INT_EN REG_BIT(24) +#define PIPE_PSR_INT_EN REG_BIT(22) +#define PIPEA_LINE_COMPARE_INT_EN REG_BIT(21) +#define PIPEA_HLINE_INT_EN REG_BIT(20) +#define PIPEA_VBLANK_INT_EN REG_BIT(19) +#define SPRITEB_FLIP_DONE_INT_EN REG_BIT(18) +#define SPRITEA_FLIP_DONE_INT_EN REG_BIT(17) +#define PLANEA_FLIPDONE_INT_EN REG_BIT(16) +#define PIPEC_LINE_COMPARE_INT_EN REG_BIT(13) +#define PIPEC_HLINE_INT_EN REG_BIT(12) +#define PIPEC_VBLANK_INT_EN REG_BIT(11) +#define SPRITEF_FLIPDONE_INT_EN REG_BIT(10) +#define SPRITEE_FLIPDONE_INT_EN REG_BIT(9) +#define PLANEC_FLIPDONE_INT_EN REG_BIT(8) #define DPINVGTT _MMIO(VLV_DISPLAY_BASE + 0x7002c) /* VLV/CHV only */ -#define SPRITEF_INVALID_GTT_INT_EN (1 << 27) -#define SPRITEE_INVALID_GTT_INT_EN (1 << 26) -#define PLANEC_INVALID_GTT_INT_EN (1 << 25) -#define CURSORC_INVALID_GTT_INT_EN (1 << 24) -#define CURSORB_INVALID_GTT_INT_EN (1 << 23) -#define CURSORA_INVALID_GTT_INT_EN (1 << 22) -#define SPRITED_INVALID_GTT_INT_EN (1 << 21) -#define SPRITEC_INVALID_GTT_INT_EN (1 << 20) -#define PLANEB_INVALID_GTT_INT_EN (1 << 19) -#define SPRITEB_INVALID_GTT_INT_EN (1 << 18) -#define SPRITEA_INVALID_GTT_INT_EN (1 << 17) -#define PLANEA_INVALID_GTT_INT_EN (1 << 16) -#define DPINVGTT_EN_MASK 0xff0000 -#define DPINVGTT_EN_MASK_CHV 0xfff0000 -#define SPRITEF_INVALID_GTT_STATUS (1 << 11) -#define SPRITEE_INVALID_GTT_STATUS (1 << 10) -#define PLANEC_INVALID_GTT_STATUS (1 << 9) -#define CURSORC_INVALID_GTT_STATUS (1 << 8) -#define CURSORB_INVALID_GTT_STATUS (1 << 7) -#define CURSORA_INVALID_GTT_STATUS (1 << 6) -#define SPRITED_INVALID_GTT_STATUS (1 << 5) -#define SPRITEC_INVALID_GTT_STATUS (1 << 4) -#define PLANEB_INVALID_GTT_STATUS (1 << 3) -#define SPRITEB_INVALID_GTT_STATUS (1 << 2) -#define SPRITEA_INVALID_GTT_STATUS (1 << 1) -#define PLANEA_INVALID_GTT_STATUS (1 << 0) -#define DPINVGTT_STATUS_MASK 0xff -#define DPINVGTT_STATUS_MASK_CHV 0xfff +#define DPINVGTT_EN_MASK_CHV REG_GENMASK(27, 16) +#define DPINVGTT_EN_MASK_VLV REG_GENMASK(23, 16) +#define SPRITEF_INVALID_GTT_INT_EN REG_BIT(27) +#define SPRITEE_INVALID_GTT_INT_EN REG_BIT(26) +#define PLANEC_INVALID_GTT_INT_EN REG_BIT(25) +#define CURSORC_INVALID_GTT_INT_EN REG_BIT(24) +#define CURSORB_INVALID_GTT_INT_EN REG_BIT(23) +#define CURSORA_INVALID_GTT_INT_EN REG_BIT(22) +#define SPRITED_INVALID_GTT_INT_EN REG_BIT(21) +#define SPRITEC_INVALID_GTT_INT_EN REG_BIT(20) +#define PLANEB_INVALID_GTT_INT_EN REG_BIT(19) +#define SPRITEB_INVALID_GTT_INT_EN REG_BIT(18) +#define SPRITEA_INVALID_GTT_INT_EN REG_BIT(17) +#define PLANEA_INVALID_GTT_INT_EN REG_BIT(16) +#define DPINVGTT_STATUS_MASK_CHV REG_GENMASK(11, 0) +#define DPINVGTT_STATUS_MASK_VLV REG_GENMASK(7, 0) +#define SPRITEF_INVALID_GTT_STATUS REG_BIT(11) +#define SPRITEE_INVALID_GTT_STATUS REG_BIT(10) +#define PLANEC_INVALID_GTT_STATUS REG_BIT(9) +#define CURSORC_INVALID_GTT_STATUS REG_BIT(8) +#define CURSORB_INVALID_GTT_STATUS REG_BIT(7) +#define CURSORA_INVALID_GTT_STATUS REG_BIT(6) +#define SPRITED_INVALID_GTT_STATUS REG_BIT(5) +#define SPRITEC_INVALID_GTT_STATUS REG_BIT(4) +#define PLANEB_INVALID_GTT_STATUS REG_BIT(3) +#define SPRITEB_INVALID_GTT_STATUS REG_BIT(2) +#define SPRITEA_INVALID_GTT_STATUS REG_BIT(1) +#define PLANEA_INVALID_GTT_STATUS REG_BIT(0) #define DSPARB _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x70030) #define DSPARB_CSTART_MASK (0x7f << 7) @@ -6877,7 +6967,7 @@ enum { #define DVS_SOURCE_KEY (1 << 22) #define DVS_RGB_ORDER_XBGR (1 << 20) #define DVS_YUV_FORMAT_BT709 (1 << 18) -#define DVS_YUV_BYTE_ORDER_MASK (3 << 16) +#define DVS_YUV_ORDER_MASK (3 << 16) #define DVS_YUV_ORDER_YUYV (0 << 16) #define DVS_YUV_ORDER_UYVY (1 << 16) #define DVS_YUV_ORDER_YVYU (2 << 16) @@ -6956,7 +7046,7 @@ enum { #define SPRITE_RGB_ORDER_RGBX (1 << 20) /* only for 888 and 161616 */ #define SPRITE_YUV_TO_RGB_CSC_DISABLE (1 << 19) #define SPRITE_YUV_TO_RGB_CSC_FORMAT_BT709 (1 << 18) /* 0 is BT601 */ -#define SPRITE_YUV_BYTE_ORDER_MASK (3 << 16) +#define SPRITE_YUV_ORDER_MASK (3 << 16) #define SPRITE_YUV_ORDER_YUYV (0 << 16) #define SPRITE_YUV_ORDER_UYVY (1 << 16) #define SPRITE_YUV_ORDER_YVYU (2 << 16) @@ -7041,7 +7131,7 @@ enum { #define SP_ALPHA_PREMULTIPLY (1 << 23) /* CHV pipe B */ #define SP_SOURCE_KEY (1 << 22) #define SP_YUV_FORMAT_BT709 (1 << 18) -#define SP_YUV_BYTE_ORDER_MASK (3 << 16) +#define SP_YUV_ORDER_MASK (3 << 16) #define SP_YUV_ORDER_YUYV (0 << 16) #define SP_YUV_ORDER_UYVY (1 << 16) #define SP_YUV_ORDER_YVYU (2 << 16) @@ -7182,10 +7272,10 @@ enum { #define PLANE_CTL_YUV420_Y_PLANE (1 << 19) #define PLANE_CTL_YUV_TO_RGB_CSC_FORMAT_BT709 (1 << 18) #define PLANE_CTL_YUV422_ORDER_MASK (0x3 << 16) -#define PLANE_CTL_YUV422_YUYV (0 << 16) -#define PLANE_CTL_YUV422_UYVY (1 << 16) -#define PLANE_CTL_YUV422_YVYU (2 << 16) -#define PLANE_CTL_YUV422_VYUY (3 << 16) +#define PLANE_CTL_YUV422_ORDER_YUYV (0 << 16) +#define PLANE_CTL_YUV422_ORDER_UYVY (1 << 16) +#define PLANE_CTL_YUV422_ORDER_YVYU (2 << 16) +#define PLANE_CTL_YUV422_ORDER_VYUY (3 << 16) #define PLANE_CTL_RENDER_DECOMPRESSION_ENABLE (1 << 15) #define PLANE_CTL_TRICKLE_FEED_DISABLE (1 << 14) #define PLANE_CTL_CLEAR_COLOR_DISABLE (1 << 13) /* TGL+ */ @@ -7239,10 +7329,10 @@ enum { #define _PLANE_CUS_CTL_1_A 0x701c8 #define _PLANE_CUS_CTL_2_A 0x702c8 #define PLANE_CUS_ENABLE (1 << 31) -#define PLANE_CUS_PLANE_4_RKL (0 << 30) -#define PLANE_CUS_PLANE_5_RKL (1 << 30) -#define PLANE_CUS_PLANE_6 (0 << 30) -#define PLANE_CUS_PLANE_7 (1 << 30) +#define PLANE_CUS_Y_PLANE_4_RKL (0 << 30) +#define PLANE_CUS_Y_PLANE_5_RKL (1 << 30) +#define PLANE_CUS_Y_PLANE_6_ICL (0 << 30) +#define PLANE_CUS_Y_PLANE_7_ICL (1 << 30) #define PLANE_CUS_HPHASE_SIGN_NEGATIVE (1 << 19) #define PLANE_CUS_HPHASE_0 (0 << 16) #define PLANE_CUS_HPHASE_0_25 (1 << 16) @@ -7274,12 +7364,12 @@ enum { #define _PLANE_NV12_BUF_CFG_1_A 0x70278 #define _PLANE_NV12_BUF_CFG_2_A 0x70378 -#define _PLANE_CC_VAL_1_B 0x711b4 -#define _PLANE_CC_VAL_2_B 0x712b4 -#define _PLANE_CC_VAL_1(pipe) _PIPE(pipe, _PLANE_CC_VAL_1_A, _PLANE_CC_VAL_1_B) -#define _PLANE_CC_VAL_2(pipe) _PIPE(pipe, _PLANE_CC_VAL_2_A, _PLANE_CC_VAL_2_B) -#define PLANE_CC_VAL(pipe, plane) \ - _MMIO_PLANE(plane, _PLANE_CC_VAL_1(pipe), _PLANE_CC_VAL_2(pipe)) +#define _PLANE_CC_VAL_1_B 0x711b4 +#define _PLANE_CC_VAL_2_B 0x712b4 +#define _PLANE_CC_VAL_1(pipe, dw) (_PIPE(pipe, _PLANE_CC_VAL_1_A, _PLANE_CC_VAL_1_B) + (dw) * 4) +#define _PLANE_CC_VAL_2(pipe, dw) (_PIPE(pipe, _PLANE_CC_VAL_2_A, _PLANE_CC_VAL_2_B) + (dw) * 4) +#define PLANE_CC_VAL(pipe, plane, dw) \ + _MMIO_PLANE((plane), _PLANE_CC_VAL_1((pipe), (dw)), _PLANE_CC_VAL_2((pipe), (dw))) /* Input CSC Register Definitions */ #define _PLANE_INPUT_CSC_RY_GY_1_A 0x701E0 @@ -8263,7 +8353,7 @@ enum { /* * The below are numbered starting from "S1" on gen11/gen12, but starting - * with gen13 display, the bspec switches to a 0-based numbering scheme + * with display 13, the bspec switches to a 0-based numbering scheme * (although the addresses stay the same so new S0 = old S1, new S1 = old S2). * We'll just use the 0-based numbering here for all platforms since it's the * way things will be named by the hardware team going forward, plus it's more @@ -8308,9 +8398,10 @@ enum { #define RESET_PCH_HANDSHAKE_ENABLE (1 << 4) #define GEN8_CHICKEN_DCPR_1 _MMIO(0x46430) -#define SKL_SELECT_ALTERNATE_DC_EXIT (1 << 30) -#define ICL_DELAY_PMRSP (1 << 22) -#define MASK_WAKEMEM (1 << 13) +#define SKL_SELECT_ALTERNATE_DC_EXIT REG_BIT(30) +#define ICL_DELAY_PMRSP REG_BIT(22) +#define DISABLE_FLR_SRC REG_BIT(15) +#define MASK_WAKEMEM REG_BIT(13) #define GEN11_CHICKEN_DCPR_2 _MMIO(0x46434) #define DCPR_MASK_MAXLATENCY_MEMUP_CLR REG_BIT(27) @@ -8351,6 +8442,9 @@ enum { #define GEN9_CTX_PREEMPT_REG _MMIO(0x2248) #define GEN12_DISABLE_POSH_BUSY_FF_DOP_CG REG_BIT(11) +#define GEN12_CS_DEBUG_MODE1_CCCSUNIT_BE_COMMON _MMIO(0x20EC) +#define GEN12_REPLAY_MODE_GRANULARITY REG_BIT(0) + #define GEN8_CS_CHICKEN1 _MMIO(0x2580) #define GEN9_PREEMPT_3D_OBJECT_LEVEL (1 << 0) #define GEN9_PREEMPT_GPGPU_LEVEL(hi, lo) (((hi) << 2) | ((lo) << 1)) @@ -8374,9 +8468,10 @@ enum { #define GEN8_ERRDETBCTRL (1 << 9) #define GEN11_COMMON_SLICE_CHICKEN3 _MMIO(0x7304) - #define DG1_FLOAT_POINT_BLEND_OPT_STRICT_MODE_EN REG_BIT(12) - #define GEN11_BLEND_EMB_FIX_DISABLE_IN_RCC REG_BIT(11) - #define GEN12_DISABLE_CPS_AWARE_COLOR_PIPE REG_BIT(9) +#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) #define HIZ_CHICKEN _MMIO(0x7018) # define CHV_HZ_8X8_MODE_IN_1X REG_BIT(15) @@ -8430,6 +8525,12 @@ enum { #define GEN8_LQSC_FLUSH_COHERENT_LINES (1 << 21) #define GEN8_LQSQ_NONIA_COHERENT_ATOMICS_ENABLE REG_BIT(22) +#define GEN11_L3SQCREG5 _MMIO(0xb158) +#define L3_PWM_TIMER_INIT_VAL_MASK REG_GENMASK(9, 0) + +#define XEHP_L3SCQREG7 _MMIO(0xb188) +#define BLEND_FILL_CACHING_OPT_DIS REG_BIT(3) + /* GEN8 chicken */ #define HDC_CHICKEN0 _MMIO(0x7300) #define ICL_HDC_MODE _MMIO(0xE5F4) @@ -8440,6 +8541,12 @@ enum { #define HDC_FORCE_NON_COHERENT (1 << 4) #define HDC_BARRIER_PERFORMANCE_DISABLE (1 << 10) +#define GEN12_HDC_CHICKEN0 _MMIO(0xE5F0) +#define LSC_L1_FLUSH_CTL_3D_DATAPORT_FLUSH_EVENTS_MASK REG_GENMASK(13, 11) + +#define SARB_CHICKEN1 _MMIO(0xe90c) +#define COMP_CKN_IN REG_GENMASK(30, 29) + #define GEN8_HDC_CHICKEN1 _MMIO(0x7304) /* GEN9 chicken */ @@ -8467,8 +8574,13 @@ enum { _PIPEB_CHICKEN) #define UNDERRUN_RECOVERY_DISABLE_ADLP REG_BIT(30) #define UNDERRUN_RECOVERY_ENABLE_DG2 REG_BIT(30) -#define PIXEL_ROUNDING_TRUNC_FB_PASSTHRU (1 << 15) -#define PER_PIXEL_ALPHA_BYPASS_EN (1 << 7) +#define PIXEL_ROUNDING_TRUNC_FB_PASSTHRU REG_BIT(15) +#define DG2_RENDER_CCSTAG_4_3_EN REG_BIT(12) +#define PER_PIXEL_ALPHA_BYPASS_EN REG_BIT(7) + +#define VFLSKPD _MMIO(0x62a8) +#define DIS_OVER_FETCH_CACHE REG_BIT(1) +#define DIS_MULT_MISS_RD_SQUASH REG_BIT(0) #define FF_MODE2 _MMIO(0x6604) #define FF_MODE2_GS_TIMER_MASK REG_GENMASK(31, 24) @@ -9293,6 +9405,9 @@ enum { #define GEN8_SDEUNIT_CLOCK_GATE_DISABLE (1 << 14) #define GEN8_HDCUNIT_CLOCK_GATE_DISABLE_HDCREQ (1 << 28) +#define UNSLCGCTL9430 _MMIO(0x9430) +#define MSQDUNIT_CLKGATE_DIS REG_BIT(3) + #define GEN6_GFXPAUSE _MMIO(0xA000) #define GEN6_RPNSWREQ _MMIO(0xA008) #define GEN6_TURBO_DISABLE (1 << 31) @@ -9302,6 +9417,7 @@ enum { #define GEN6_OFFSET(x) ((x) << 19) #define GEN6_AGGRESSIVE_TURBO (0 << 15) #define GEN9_SW_REQ_UNSLICE_RATIO_SHIFT 23 +#define GEN9_IGNORE_SLICE_RATIO (0 << 0) #define GEN6_RC_VIDEO_FREQ _MMIO(0xA00C) #define GEN6_RC_CONTROL _MMIO(0xA090) @@ -9337,6 +9453,9 @@ enum { #define GEN6_RP_UP_BUSY_CONT (0x4 << 3) #define GEN6_RP_DOWN_IDLE_AVG (0x2 << 0) #define GEN6_RP_DOWN_IDLE_CONT (0x1 << 0) +#define GEN6_RPSWCTL_SHIFT 9 +#define GEN9_RPSWCTL_ENABLE (0x2 << GEN6_RPSWCTL_SHIFT) +#define GEN9_RPSWCTL_DISABLE (0x0 << GEN6_RPSWCTL_SHIFT) #define GEN6_RP_UP_THRESHOLD _MMIO(0xA02C) #define GEN6_RP_DOWN_THRESHOLD _MMIO(0xA030) #define GEN6_RP_CUR_UP_EI _MMIO(0xA050) @@ -9608,24 +9727,39 @@ enum { #define GEN9_CCS_TLB_PREFETCH_ENABLE (1 << 3) #define GEN8_ROW_CHICKEN _MMIO(0xe4f0) -#define FLOW_CONTROL_ENABLE (1 << 15) -#define PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE (1 << 8) -#define STALL_DOP_GATING_DISABLE (1 << 5) -#define THROTTLE_12_5 (7 << 2) -#define DISABLE_EARLY_EOT (1 << 1) +#define FLOW_CONTROL_ENABLE REG_BIT(15) +#define UGM_BACKUP_MODE REG_BIT(13) +#define MDQ_ARBITRATION_MODE REG_BIT(12) +#define PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE REG_BIT(8) +#define STALL_DOP_GATING_DISABLE REG_BIT(5) +#define THROTTLE_12_5 REG_GENMASK(4, 2) +#define DISABLE_EARLY_EOT REG_BIT(1) #define GEN7_ROW_CHICKEN2 _MMIO(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 LSC_CHICKEN_BIT_0 _MMIO(0xe7c8) +#define FORCE_1_SUB_MESSAGE_PER_FRAGMENT REG_BIT(15) +#define LSC_CHICKEN_BIT_0_UDW _MMIO(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 GEN7_ROW_CHICKEN2_GT2 _MMIO(0xf4f4) #define DOP_CLOCK_GATING_DISABLE (1 << 0) #define PUSH_CONSTANT_DEREF_DISABLE (1 << 8) #define GEN11_TDL_CLOCK_GATING_FIX_DISABLE (1 << 1) -#define GEN9_ROW_CHICKEN4 _MMIO(0xe48c) -#define GEN12_DISABLE_TDL_PUSH REG_BIT(9) -#define GEN11_DIS_PICK_2ND_EU REG_BIT(7) +#define GEN9_ROW_CHICKEN4 _MMIO(0xe48c) +#define GEN12_DISABLE_GRF_CLEAR REG_BIT(13) +#define GEN12_DISABLE_TDL_PUSH REG_BIT(9) +#define GEN11_DIS_PICK_2ND_EU REG_BIT(7) +#define GEN12_DISABLE_HDR_PAST_PAYLOAD_HOLD_FIX REG_BIT(4) #define HSW_ROW_CHICKEN3 _MMIO(0xe49c) #define HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE (1 << 6) @@ -9640,9 +9774,10 @@ enum { #define GEN8_SAMPLER_POWER_BYPASS_DIS (1 << 1) #define GEN9_HALF_SLICE_CHICKEN7 _MMIO(0xe194) -#define GEN9_SAMPLER_HASH_COMPRESSED_READ_ADDR (1 << 8) -#define GEN9_ENABLE_YV12_BUGFIX (1 << 4) -#define GEN9_ENABLE_GPGPU_PREEMPTION (1 << 2) +#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) /* Audio */ #define G4X_AUD_VID_DID _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x62020) @@ -9781,6 +9916,10 @@ enum { #define AUD_PIN_BUF_CTL _MMIO(0x48414) #define AUD_PIN_BUF_ENABLE REG_BIT(31) +#define AUD_TS_CDCLK_M _MMIO(0x65ea0) +#define AUD_TS_CDCLK_M_EN REG_BIT(31) +#define AUD_TS_CDCLK_N _MMIO(0x65ea4) + /* Display Audio Config Reg */ #define AUD_CONFIG_BE _MMIO(0x65ef0) #define HBLANK_EARLY_ENABLE_ICL(pipe) (0x1 << (20 - (pipe))) @@ -10212,8 +10351,6 @@ enum skl_power_gate { #define TGL_TRANS_DDI_PORT_MASK (0xf << TGL_TRANS_DDI_PORT_SHIFT) #define TRANS_DDI_SELECT_PORT(x) ((x) << TRANS_DDI_PORT_SHIFT) #define TGL_TRANS_DDI_SELECT_PORT(x) (((x) + 1) << TGL_TRANS_DDI_PORT_SHIFT) -#define TRANS_DDI_FUNC_CTL_VAL_TO_PORT(val) (((val) & TRANS_DDI_PORT_MASK) >> TRANS_DDI_PORT_SHIFT) -#define TGL_TRANS_DDI_FUNC_CTL_VAL_TO_PORT(val) ((((val) & TGL_TRANS_DDI_PORT_MASK) >> TGL_TRANS_DDI_PORT_SHIFT) - 1) #define TRANS_DDI_MODE_SELECT_MASK (7 << 24) #define TRANS_DDI_MODE_SELECT_HDMI (0 << 24) #define TRANS_DDI_MODE_SELECT_DVI (1 << 24) @@ -10523,6 +10660,14 @@ enum skl_power_gate { #define BXT_CDCLK_SSA_PRECHARGE_ENABLE (1 << 16) #define CDCLK_FREQ_DECIMAL_MASK (0x7ff) +/* CDCLK_SQUASH_CTL */ +#define CDCLK_SQUASH_CTL _MMIO(0x46008) +#define CDCLK_SQUASH_ENABLE REG_BIT(31) +#define CDCLK_SQUASH_WINDOW_SIZE_MASK REG_GENMASK(27, 24) +#define CDCLK_SQUASH_WINDOW_SIZE(x) REG_FIELD_PREP(CDCLK_SQUASH_WINDOW_SIZE_MASK, (x)) +#define CDCLK_SQUASH_WAVEFORM_MASK REG_GENMASK(15, 0) +#define CDCLK_SQUASH_WAVEFORM(x) REG_FIELD_PREP(CDCLK_SQUASH_WAVEFORM_MASK, (x)) + /* LCPLL_CTL */ #define LCPLL1_CTL _MMIO(0x46010) #define LCPLL2_CTL _MMIO(0x46014) @@ -12466,11 +12611,19 @@ enum skl_power_gate { #define PMFLUSH_GAPL3UNBLOCK (1 << 21) #define PMFLUSHDONE_LNEBLK (1 << 22) +#define XEHP_L3NODEARBCFG _MMIO(0xb0b4) +#define XEHP_LNESPARE REG_BIT(19) + #define GEN12_GLOBAL_MOCS(i) _MMIO(0x4000 + (i) * 4) /* Global MOCS regs */ #define GEN12_GSMBASE _MMIO(0x108100) #define GEN12_DSMBASE _MMIO(0x1080C0) +#define XEHP_CLOCK_GATE_DIS _MMIO(0x101014) +#define SGSI_SIDECLK_DIS REG_BIT(17) +#define SGGI_DIS REG_BIT(15) +#define SGR_DIS REG_BIT(13) + /* gamt regs */ #define GEN8_L3_LRA_1_GPGPU _MMIO(0x4dd4) #define GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_BDW 0x67F1427F /* max/min for LRA1/2 */ @@ -12847,4 +13000,7 @@ enum skl_power_gate { #define CLKGATE_DIS_MISC _MMIO(0x46534) #define CLKGATE_DIS_MISC_DMASC_GATING_DIS REG_BIT(21) +#define SLICE_COMMON_ECO_CHICKEN1 _MMIO(0x731C) +#define MSC_MSAA_REODER_BUF_BYPASS_DISABLE REG_BIT(14) + #endif /* _I915_REG_H_ */ diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 89cccefeea63..76cf5ac91e94 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -42,6 +42,7 @@ #include "gt/intel_rps.h" #include "i915_active.h" +#include "i915_deps.h" #include "i915_drv.h" #include "i915_trace.h" #include "intel_pm.h" @@ -97,9 +98,9 @@ static signed long i915_fence_wait(struct dma_fence *fence, bool interruptible, signed long timeout) { - return i915_request_wait(to_request(fence), - interruptible | I915_WAIT_PRIORITY, - timeout); + return i915_request_wait_timeout(to_request(fence), + interruptible | I915_WAIT_PRIORITY, + timeout); } struct kmem_cache *i915_request_slab_cache(void) @@ -114,6 +115,10 @@ static void i915_fence_release(struct dma_fence *fence) GEM_BUG_ON(rq->guc_prio != GUC_PRIO_INIT && rq->guc_prio != GUC_PRIO_FINI); + i915_request_free_capture_list(fetch_and_zero(&rq->capture_list)); + if (i915_vma_snapshot_present(&rq->batch_snapshot)) + i915_vma_snapshot_put_onstack(&rq->batch_snapshot); + /* * The request is put onto a RCU freelist (i.e. the address * is immediately reused), mark the fences as being freed now. @@ -187,19 +192,6 @@ void i915_request_notify_execute_cb_imm(struct i915_request *rq) __notify_execute_cb(rq, irq_work_imm); } -static void free_capture_list(struct i915_request *request) -{ - struct i915_capture_list *capture; - - capture = fetch_and_zero(&request->capture_list); - while (capture) { - struct i915_capture_list *next = capture->next; - - kfree(capture); - capture = next; - } -} - static void __i915_request_fill(struct i915_request *rq, u8 val) { void *vaddr = rq->ring->vaddr; @@ -304,6 +296,38 @@ static void __rq_cancel_watchdog(struct i915_request *rq) i915_request_put(rq); } +#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) + +/** + * i915_request_free_capture_list - Free a capture list + * @capture: Pointer to the first list item or NULL + * + */ +void i915_request_free_capture_list(struct i915_capture_list *capture) +{ + while (capture) { + struct i915_capture_list *next = capture->next; + + i915_vma_snapshot_put(capture->vma_snapshot); + kfree(capture); + capture = next; + } +} + +#define assert_capture_list_is_null(_rq) GEM_BUG_ON((_rq)->capture_list) + +#define clear_capture_list(_rq) ((_rq)->capture_list = NULL) + +#else + +#define i915_request_free_capture_list(_a) do {} while (0) + +#define assert_capture_list_is_null(_a) do {} while (0) + +#define clear_capture_list(_rq) do {} while (0) + +#endif + bool i915_request_retire(struct i915_request *rq) { if (!__i915_request_is_complete(rq)) @@ -340,7 +364,7 @@ bool i915_request_retire(struct i915_request *rq) } if (test_and_set_bit(I915_FENCE_FLAG_BOOST, &rq->fence.flags)) - atomic_dec(&rq->engine->gt->rps.num_waiters); + intel_rps_dec_waiters(&rq->engine->gt->rps); /* * We only loosely track inflight requests across preemption, @@ -360,7 +384,6 @@ bool i915_request_retire(struct i915_request *rq) intel_context_exit(rq->context); intel_context_unpin(rq->context); - free_capture_list(rq); i915_sched_node_fini(&rq->sched); i915_request_put(rq); @@ -720,7 +743,7 @@ void i915_request_cancel(struct i915_request *rq, int error) intel_context_cancel_request(rq->context, rq); } -static int __i915_sw_fence_call +static int submit_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state) { struct i915_request *request = @@ -756,7 +779,7 @@ submit_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state) return NOTIFY_DONE; } -static int __i915_sw_fence_call +static int semaphore_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state) { struct i915_request *rq = container_of(fence, typeof(*rq), semaphore); @@ -830,11 +853,18 @@ static void __i915_request_ctor(void *arg) i915_sw_fence_init(&rq->submit, submit_notify); i915_sw_fence_init(&rq->semaphore, semaphore_notify); - rq->capture_list = NULL; + clear_capture_list(rq); + rq->batch_snapshot.present = false; init_llist_head(&rq->execute_cb); } +#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) +#define clear_batch_ptr(_rq) ((_rq)->batch = NULL) +#else +#define clear_batch_ptr(_a) do {} while (0) +#endif + struct i915_request * __i915_request_create(struct intel_context *ce, gfp_t gfp) { @@ -926,10 +956,11 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp) i915_sched_node_reinit(&rq->sched); /* No zalloc, everything must be cleared after use */ - rq->batch = NULL; + clear_batch_ptr(rq); __rq_init_watchdog(rq); - GEM_BUG_ON(rq->capture_list); + assert_capture_list_is_null(rq); GEM_BUG_ON(!llist_empty(&rq->execute_cb)); + GEM_BUG_ON(i915_vma_snapshot_present(&rq->batch_snapshot)); /* * Reserve space in the ring buffer for all the commands required to @@ -1514,6 +1545,27 @@ i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence) } /** + * i915_request_await_deps - set this request to (async) wait upon a struct + * i915_deps dma_fence collection + * @rq: request we are wishing to use + * @deps: The struct i915_deps containing the dependencies. + * + * Returns 0 if successful, negative error code on error. + */ +int i915_request_await_deps(struct i915_request *rq, const struct i915_deps *deps) +{ + int i, err; + + for (i = 0; i < deps->num_deps; ++i) { + err = i915_request_await_dma_fence(rq, deps->fences[i]); + if (err) + return err; + } + + return 0; +} + +/** * i915_request_await_object - set this request to (async) wait upon a bo * @to: request we are wishing to use * @obj: object which may be in use on another ring. @@ -1858,23 +1910,27 @@ static void request_wait_wake(struct dma_fence *fence, struct dma_fence_cb *cb) } /** - * i915_request_wait - wait until execution of request has finished + * i915_request_wait_timeout - wait until execution of request has finished * @rq: the request to wait upon * @flags: how to wait * @timeout: how long to wait in jiffies * - * i915_request_wait() waits for the request to be completed, for a + * i915_request_wait_timeout() waits for the request to be completed, for a * maximum of @timeout jiffies (with MAX_SCHEDULE_TIMEOUT implying an * unbounded wait). * * Returns the remaining time (in jiffies) if the request completed, which may - * be zero or -ETIME if the request is unfinished after the timeout expires. + * be zero if the request is unfinished after the timeout expires. + * If the timeout is 0, it will return 1 if the fence is signaled. + * * May return -EINTR is called with I915_WAIT_INTERRUPTIBLE and a signal is * pending before the request completes. + * + * NOTE: This function has the same wait semantics as dma-fence. */ -long i915_request_wait(struct i915_request *rq, - unsigned int flags, - long timeout) +long i915_request_wait_timeout(struct i915_request *rq, + unsigned int flags, + long timeout) { const int state = flags & I915_WAIT_INTERRUPTIBLE ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE; @@ -1884,7 +1940,7 @@ long i915_request_wait(struct i915_request *rq, GEM_BUG_ON(timeout < 0); if (dma_fence_is_signaled(&rq->fence)) - return timeout; + return timeout ?: 1; if (!timeout) return -ETIME; @@ -1993,6 +2049,39 @@ out: return timeout; } +/** + * i915_request_wait - wait until execution of request has finished + * @rq: the request to wait upon + * @flags: how to wait + * @timeout: how long to wait in jiffies + * + * i915_request_wait() waits for the request to be completed, for a + * maximum of @timeout jiffies (with MAX_SCHEDULE_TIMEOUT implying an + * unbounded wait). + * + * Returns the remaining time (in jiffies) if the request completed, which may + * be zero or -ETIME if the request is unfinished after the timeout expires. + * May return -EINTR is called with I915_WAIT_INTERRUPTIBLE and a signal is + * pending before the request completes. + * + * NOTE: This function behaves differently from dma-fence wait semantics for + * timeout = 0. It returns 0 on success, and -ETIME if not signaled. + */ +long i915_request_wait(struct i915_request *rq, + unsigned int flags, + long timeout) +{ + long ret = i915_request_wait_timeout(rq, flags, timeout); + + if (!ret) + return -ETIME; + + if (ret > 0 && !timeout) + return 0; + + return ret; +} + static int print_sched_attr(const struct i915_sched_attr *attr, char *buf, int x, int len) { diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index dc359242d1ae..170ee78c2858 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -40,19 +40,27 @@ #include "i915_scheduler.h" #include "i915_selftest.h" #include "i915_sw_fence.h" +#include "i915_vma_snapshot.h" #include <uapi/drm/i915_drm.h> struct drm_file; struct drm_i915_gem_object; struct drm_printer; +struct i915_deps; struct i915_request; +#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) struct i915_capture_list { + struct i915_vma_snapshot *vma_snapshot; struct i915_capture_list *next; - struct i915_vma *vma; }; +void i915_request_free_capture_list(struct i915_capture_list *capture); +#else +#define i915_request_free_capture_list(_a) do {} while (0) +#endif + #define RQ_TRACE(rq, fmt, ...) do { \ const struct i915_request *rq__ = (rq); \ ENGINE_TRACE(rq__->engine, "fence %llx:%lld, current %d " fmt, \ @@ -289,10 +297,12 @@ struct i915_request { /** Preallocate space in the ring for the emitting the request */ u32 reserved_space; - /** Batch buffer related to this request if any (used for - * error state dump only). - */ - struct i915_vma *batch; + /** Batch buffer pointer for selftest internal use. */ + I915_SELFTEST_DECLARE(struct i915_vma *batch); + + struct i915_vma_snapshot batch_snapshot; + +#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) /** * Additional buffers requested by userspace to be captured upon * a GPU hang. The vma/obj on this list are protected by their @@ -300,6 +310,7 @@ struct i915_request { * on the active_list (of their final request). */ struct i915_capture_list *capture_list; +#endif /** Time at which this request was emitted, in jiffies. */ unsigned long emitted_jiffies; @@ -401,6 +412,7 @@ int i915_request_await_object(struct i915_request *to, bool write); int i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence); +int i915_request_await_deps(struct i915_request *rq, const struct i915_deps *deps); int i915_request_await_execution(struct i915_request *rq, struct dma_fence *fence); @@ -414,6 +426,11 @@ void i915_request_unsubmit(struct i915_request *request); void i915_request_cancel(struct i915_request *rq, int error); +long i915_request_wait_timeout(struct i915_request *rq, + unsigned int flags, + long timeout) + __attribute__((nonnull(1))); + long i915_request_wait(struct i915_request *rq, unsigned int flags, long timeout) @@ -642,7 +659,8 @@ i915_request_timeline(const struct i915_request *rq) { /* Valid only while the request is being constructed (or retired). */ return rcu_dereference_protected(rq->timeline, - lockdep_is_held(&rcu_access_pointer(rq->timeline)->mutex)); + lockdep_is_held(&rcu_access_pointer(rq->timeline)->mutex) || + test_bit(CONTEXT_IS_PARKING, &rq->context->flags)); } static inline struct i915_gem_context * diff --git a/drivers/gpu/drm/i915/i915_scatterlist.c b/drivers/gpu/drm/i915/i915_scatterlist.c index 4a6712dca838..41f2adb6a583 100644 --- a/drivers/gpu/drm/i915/i915_scatterlist.c +++ b/drivers/gpu/drm/i915/i915_scatterlist.c @@ -41,8 +41,32 @@ bool i915_sg_trim(struct sg_table *orig_st) return true; } +static void i915_refct_sgt_release(struct kref *ref) +{ + struct i915_refct_sgt *rsgt = + container_of(ref, typeof(*rsgt), kref); + + sg_free_table(&rsgt->table); + kfree(rsgt); +} + +static const struct i915_refct_sgt_ops rsgt_ops = { + .release = i915_refct_sgt_release +}; + +/** + * i915_refct_sgt_init - Initialize a struct i915_refct_sgt with default ops + * @rsgt: The struct i915_refct_sgt to initialize. + * size: The size of the underlying memory buffer. + */ +void i915_refct_sgt_init(struct i915_refct_sgt *rsgt, size_t size) +{ + __i915_refct_sgt_init(rsgt, size, &rsgt_ops); +} + /** - * i915_sg_from_mm_node - Create an sg_table from a struct drm_mm_node + * i915_rsgt_from_mm_node - Create a refcounted sg_table from a struct + * drm_mm_node * @node: The drm_mm_node. * @region_start: An offset to add to the dma addresses of the sg list. * @@ -50,25 +74,28 @@ bool i915_sg_trim(struct sg_table *orig_st) * taking a maximum segment length into account, splitting into segments * if necessary. * - * Return: A pointer to a kmalloced struct sg_table on success, negative + * Return: A pointer to a kmalloced struct i915_refct_sgt on success, negative * error code cast to an error pointer on failure. */ -struct sg_table *i915_sg_from_mm_node(const struct drm_mm_node *node, - u64 region_start) +struct i915_refct_sgt *i915_rsgt_from_mm_node(const struct drm_mm_node *node, + u64 region_start) { const u64 max_segment = SZ_1G; /* Do we have a limit on this? */ u64 segment_pages = max_segment >> PAGE_SHIFT; u64 block_size, offset, prev_end; + struct i915_refct_sgt *rsgt; struct sg_table *st; struct scatterlist *sg; - st = kmalloc(sizeof(*st), GFP_KERNEL); - if (!st) + rsgt = kmalloc(sizeof(*rsgt), GFP_KERNEL); + if (!rsgt) return ERR_PTR(-ENOMEM); + i915_refct_sgt_init(rsgt, node->size << PAGE_SHIFT); + st = &rsgt->table; if (sg_alloc_table(st, DIV_ROUND_UP(node->size, segment_pages), GFP_KERNEL)) { - kfree(st); + i915_refct_sgt_put(rsgt); return ERR_PTR(-ENOMEM); } @@ -104,11 +131,11 @@ struct sg_table *i915_sg_from_mm_node(const struct drm_mm_node *node, sg_mark_end(sg); i915_sg_trim(st); - return st; + return rsgt; } /** - * i915_sg_from_buddy_resource - Create an sg_table from a struct + * i915_rsgt_from_buddy_resource - Create a refcounted sg_table from a struct * i915_buddy_block list * @res: The struct i915_ttm_buddy_resource. * @region_start: An offset to add to the dma addresses of the sg list. @@ -117,11 +144,11 @@ struct sg_table *i915_sg_from_mm_node(const struct drm_mm_node *node, * taking a maximum segment length into account, splitting into segments * if necessary. * - * Return: A pointer to a kmalloced struct sg_table on success, negative + * Return: A pointer to a kmalloced struct i915_refct_sgts on success, negative * error code cast to an error pointer on failure. */ -struct sg_table *i915_sg_from_buddy_resource(struct ttm_resource *res, - u64 region_start) +struct i915_refct_sgt *i915_rsgt_from_buddy_resource(struct ttm_resource *res, + u64 region_start) { struct i915_ttm_buddy_resource *bman_res = to_ttm_buddy_resource(res); const u64 size = res->num_pages << PAGE_SHIFT; @@ -129,18 +156,21 @@ struct sg_table *i915_sg_from_buddy_resource(struct ttm_resource *res, struct i915_buddy_mm *mm = bman_res->mm; struct list_head *blocks = &bman_res->blocks; struct i915_buddy_block *block; + struct i915_refct_sgt *rsgt; struct scatterlist *sg; struct sg_table *st; resource_size_t prev_end; GEM_BUG_ON(list_empty(blocks)); - st = kmalloc(sizeof(*st), GFP_KERNEL); - if (!st) + rsgt = kmalloc(sizeof(*rsgt), GFP_KERNEL); + if (!rsgt) return ERR_PTR(-ENOMEM); + i915_refct_sgt_init(rsgt, size); + st = &rsgt->table; if (sg_alloc_table(st, res->num_pages, GFP_KERNEL)) { - kfree(st); + i915_refct_sgt_put(rsgt); return ERR_PTR(-ENOMEM); } @@ -181,7 +211,7 @@ struct sg_table *i915_sg_from_buddy_resource(struct ttm_resource *res, sg_mark_end(sg); i915_sg_trim(st); - return st; + return rsgt; } #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) diff --git a/drivers/gpu/drm/i915/i915_scatterlist.h b/drivers/gpu/drm/i915/i915_scatterlist.h index b8bd5925b03f..12c6a1684081 100644 --- a/drivers/gpu/drm/i915/i915_scatterlist.h +++ b/drivers/gpu/drm/i915/i915_scatterlist.h @@ -144,10 +144,78 @@ static inline unsigned int i915_sg_segment_size(void) bool i915_sg_trim(struct sg_table *orig_st); -struct sg_table *i915_sg_from_mm_node(const struct drm_mm_node *node, - u64 region_start); +/** + * struct i915_refct_sgt_ops - Operations structure for struct i915_refct_sgt + */ +struct i915_refct_sgt_ops { + /** + * release() - Free the memory of the struct i915_refct_sgt + * @ref: struct kref that is embedded in the struct i915_refct_sgt + */ + void (*release)(struct kref *ref); +}; + +/** + * struct i915_refct_sgt - A refcounted scatter-gather table + * @kref: struct kref for refcounting + * @table: struct sg_table holding the scatter-gather table itself. Note that + * @table->sgl = NULL can be used to determine whether a scatter-gather table + * is present or not. + * @size: The size in bytes of the underlying memory buffer + * @ops: The operations structure. + */ +struct i915_refct_sgt { + struct kref kref; + struct sg_table table; + size_t size; + const struct i915_refct_sgt_ops *ops; +}; + +/** + * i915_refct_sgt_put - Put a refcounted sg-table + * @rsgt the struct i915_refct_sgt to put. + */ +static inline void i915_refct_sgt_put(struct i915_refct_sgt *rsgt) +{ + if (rsgt) + kref_put(&rsgt->kref, rsgt->ops->release); +} + +/** + * i915_refct_sgt_get - Get a refcounted sg-table + * @rsgt the struct i915_refct_sgt to get. + */ +static inline struct i915_refct_sgt * +i915_refct_sgt_get(struct i915_refct_sgt *rsgt) +{ + kref_get(&rsgt->kref); + return rsgt; +} + +/** + * __i915_refct_sgt_init - Initialize a refcounted sg-list with a custom + * operations structure + * @rsgt The struct i915_refct_sgt to initialize. + * @size: Size in bytes of the underlying memory buffer. + * @ops: A customized operations structure in case the refcounted sg-list + * is embedded into another structure. + */ +static inline void __i915_refct_sgt_init(struct i915_refct_sgt *rsgt, + size_t size, + const struct i915_refct_sgt_ops *ops) +{ + kref_init(&rsgt->kref); + rsgt->table.sgl = NULL; + rsgt->size = size; + rsgt->ops = ops; +} + +void i915_refct_sgt_init(struct i915_refct_sgt *rsgt, size_t size); + +struct i915_refct_sgt *i915_rsgt_from_mm_node(const struct drm_mm_node *node, + u64 region_start); -struct sg_table *i915_sg_from_buddy_resource(struct ttm_resource *res, - u64 region_start); +struct i915_refct_sgt *i915_rsgt_from_buddy_resource(struct ttm_resource *res, + u64 region_start); #endif diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c index c589a681da77..2a74a9a1cafe 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.c +++ b/drivers/gpu/drm/i915/i915_sw_fence.c @@ -18,7 +18,9 @@ #define I915_SW_FENCE_BUG_ON(expr) BUILD_BUG_ON_INVALID(expr) #endif +#ifdef CONFIG_DRM_I915_SW_FENCE_CHECK_DAG static DEFINE_SPINLOCK(i915_sw_fence_lock); +#endif #define WQ_FLAG_BITS \ BITS_PER_TYPE(typeof_member(struct wait_queue_entry, flags)) @@ -34,7 +36,7 @@ enum { static void *i915_sw_fence_debug_hint(void *addr) { - return (void *)(((struct i915_sw_fence *)addr)->flags & I915_SW_FENCE_MASK); + return (void *)(((struct i915_sw_fence *)addr)->fn); } #ifdef CONFIG_DRM_I915_SW_FENCE_DEBUG_OBJECTS @@ -126,10 +128,7 @@ static inline void debug_fence_assert(struct i915_sw_fence *fence) static int __i915_sw_fence_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state) { - i915_sw_fence_notify_t fn; - - fn = (i915_sw_fence_notify_t)(fence->flags & I915_SW_FENCE_MASK); - return fn(fence, state); + return fence->fn(fence, state); } #ifdef CONFIG_DRM_I915_SW_FENCE_DEBUG_OBJECTS @@ -242,10 +241,13 @@ void __i915_sw_fence_init(struct i915_sw_fence *fence, const char *name, struct lock_class_key *key) { - BUG_ON(!fn || (unsigned long)fn & ~I915_SW_FENCE_MASK); + BUG_ON(!fn); __init_waitqueue_head(&fence->wait, name, key); - fence->flags = (unsigned long)fn; + fence->fn = fn; +#ifdef CONFIG_DRM_I915_SW_FENCE_CHECK_DAG + fence->flags = 0; +#endif i915_sw_fence_reinit(fence); } @@ -257,7 +259,6 @@ void i915_sw_fence_reinit(struct i915_sw_fence *fence) atomic_set(&fence->pending, 1); fence->error = 0; - I915_SW_FENCE_BUG_ON(!fence->flags); I915_SW_FENCE_BUG_ON(!list_empty(&fence->wait.head)); } @@ -279,6 +280,7 @@ static int i915_sw_fence_wake(wait_queue_entry_t *wq, unsigned mode, int flags, return 0; } +#ifdef CONFIG_DRM_I915_SW_FENCE_CHECK_DAG static bool __i915_sw_fence_check_if_after(struct i915_sw_fence *fence, const struct i915_sw_fence * const signaler) { @@ -322,9 +324,6 @@ static bool i915_sw_fence_check_if_after(struct i915_sw_fence *fence, unsigned long flags; bool err; - if (!IS_ENABLED(CONFIG_DRM_I915_SW_FENCE_CHECK_DAG)) - return false; - spin_lock_irqsave(&i915_sw_fence_lock, flags); err = __i915_sw_fence_check_if_after(fence, signaler); __i915_sw_fence_clear_checked_bit(fence); @@ -332,6 +331,13 @@ static bool i915_sw_fence_check_if_after(struct i915_sw_fence *fence, return err; } +#else +static bool i915_sw_fence_check_if_after(struct i915_sw_fence *fence, + const struct i915_sw_fence * const signaler) +{ + return false; +} +#endif static int __i915_sw_fence_await_sw_fence(struct i915_sw_fence *fence, struct i915_sw_fence *signaler, @@ -572,56 +578,25 @@ int i915_sw_fence_await_reservation(struct i915_sw_fence *fence, unsigned long timeout, gfp_t gfp) { - struct dma_fence *excl; + struct dma_resv_iter cursor; + struct dma_fence *f; int ret = 0, pending; debug_fence_assert(fence); might_sleep_if(gfpflags_allow_blocking(gfp)); - if (write) { - struct dma_fence **shared; - unsigned int count, i; - - ret = dma_resv_get_fences(resv, &excl, &count, &shared); - if (ret) - return ret; - - for (i = 0; i < count; i++) { - if (shared[i]->ops == exclude) - continue; - - pending = i915_sw_fence_await_dma_fence(fence, - shared[i], - timeout, - gfp); - if (pending < 0) { - ret = pending; - break; - } - - ret |= pending; - } - - for (i = 0; i < count; i++) - dma_fence_put(shared[i]); - kfree(shared); - } else { - excl = dma_resv_get_excl_unlocked(resv); - } - - if (ret >= 0 && excl && excl->ops != exclude) { - pending = i915_sw_fence_await_dma_fence(fence, - excl, - timeout, + dma_resv_iter_begin(&cursor, resv, write); + dma_resv_for_each_fence_unlocked(&cursor, f) { + pending = i915_sw_fence_await_dma_fence(fence, f, timeout, gfp); - if (pending < 0) + if (pending < 0) { ret = pending; - else - ret |= pending; - } - - dma_fence_put(excl); + break; + } + ret |= pending; + } + dma_resv_iter_end(&cursor); return ret; } diff --git a/drivers/gpu/drm/i915/i915_sw_fence.h b/drivers/gpu/drm/i915/i915_sw_fence.h index 30a863353ee6..a7c603bc1b01 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.h +++ b/drivers/gpu/drm/i915/i915_sw_fence.h @@ -17,26 +17,27 @@ struct completion; struct dma_resv; +struct i915_sw_fence; + +enum i915_sw_fence_notify { + FENCE_COMPLETE, + FENCE_FREE +}; + +typedef int (*i915_sw_fence_notify_t)(struct i915_sw_fence *, + enum i915_sw_fence_notify state); struct i915_sw_fence { wait_queue_head_t wait; + i915_sw_fence_notify_t fn; +#ifdef CONFIG_DRM_I915_SW_FENCE_CHECK_DAG unsigned long flags; +#endif atomic_t pending; int error; }; #define I915_SW_FENCE_CHECKED_BIT 0 /* used internally for DAG checking */ -#define I915_SW_FENCE_PRIVATE_BIT 1 /* available for use by owner */ -#define I915_SW_FENCE_MASK (~3) - -enum i915_sw_fence_notify { - FENCE_COMPLETE, - FENCE_FREE -}; - -typedef int (*i915_sw_fence_notify_t)(struct i915_sw_fence *, - enum i915_sw_fence_notify state); -#define __i915_sw_fence_call __aligned(4) void __i915_sw_fence_init(struct i915_sw_fence *fence, i915_sw_fence_notify_t fn, diff --git a/drivers/gpu/drm/i915/i915_sw_fence_work.c b/drivers/gpu/drm/i915/i915_sw_fence_work.c index 5b33ef23d54c..d2e56b387993 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence_work.c +++ b/drivers/gpu/drm/i915/i915_sw_fence_work.c @@ -23,7 +23,7 @@ static void fence_work(struct work_struct *work) dma_fence_put(&f->dma); } -static int __i915_sw_fence_call +static int fence_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state) { struct dma_fence_work *f = container_of(fence, typeof(*f), chain); diff --git a/drivers/gpu/drm/i915/i915_switcheroo.c b/drivers/gpu/drm/i915/i915_switcheroo.c index de0e224b56ce..23777d500cdf 100644 --- a/drivers/gpu/drm/i915/i915_switcheroo.c +++ b/drivers/gpu/drm/i915/i915_switcheroo.c @@ -5,6 +5,7 @@ #include <linux/vga_switcheroo.h> +#include "i915_driver.h" #include "i915_drv.h" #include "i915_switcheroo.h" @@ -24,12 +25,12 @@ static void i915_switcheroo_set_state(struct pci_dev *pdev, i915->drm.switch_power_state = DRM_SWITCH_POWER_CHANGING; /* i915 resume handler doesn't set to D0 */ pci_set_power_state(pdev, PCI_D0); - i915_resume_switcheroo(i915); + i915_driver_resume_switcheroo(i915); i915->drm.switch_power_state = DRM_SWITCH_POWER_ON; } else { drm_info(&i915->drm, "switched off\n"); i915->drm.switch_power_state = DRM_SWITCH_POWER_CHANGING; - i915_suspend_switcheroo(i915, pmm); + i915_driver_suspend_switcheroo(i915, pmm); i915->drm.switch_power_state = DRM_SWITCH_POWER_OFF; } } diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c index 1804f4142740..fae4d1f4f275 100644 --- a/drivers/gpu/drm/i915/i915_sysfs.c +++ b/drivers/gpu/drm/i915/i915_sysfs.c @@ -52,7 +52,7 @@ static u32 calc_residency(struct drm_i915_private *dev_priv, u64 res = 0; with_intel_runtime_pm(&dev_priv->runtime_pm, wakeref) - res = intel_rc6_residency_us(&dev_priv->gt.rc6, reg); + res = intel_rc6_residency_us(&to_gt(dev_priv)->rc6, reg); return DIV_ROUND_CLOSEST_ULL(res, 1000); } @@ -260,7 +260,7 @@ static ssize_t gt_act_freq_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf) { struct drm_i915_private *i915 = kdev_minor_to_i915(kdev); - struct intel_rps *rps = &i915->gt.rps; + struct intel_rps *rps = &to_gt(i915)->rps; return sysfs_emit(buf, "%d\n", intel_rps_read_actual_frequency(rps)); } @@ -269,7 +269,7 @@ static ssize_t gt_cur_freq_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf) { struct drm_i915_private *i915 = kdev_minor_to_i915(kdev); - struct intel_rps *rps = &i915->gt.rps; + struct intel_rps *rps = &to_gt(i915)->rps; return sysfs_emit(buf, "%d\n", intel_rps_get_requested_frequency(rps)); } @@ -277,9 +277,9 @@ static ssize_t gt_cur_freq_mhz_show(struct device *kdev, static ssize_t gt_boost_freq_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf) { struct drm_i915_private *i915 = kdev_minor_to_i915(kdev); - struct intel_rps *rps = &i915->gt.rps; + struct intel_rps *rps = &to_gt(i915)->rps; - return sysfs_emit(buf, "%d\n", intel_gpu_freq(rps, rps->boost_freq)); + return sysfs_emit(buf, "%d\n", intel_rps_get_boost_frequency(rps)); } static ssize_t gt_boost_freq_mhz_store(struct device *kdev, @@ -287,8 +287,7 @@ static ssize_t gt_boost_freq_mhz_store(struct device *kdev, const char *buf, size_t count) { struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev); - struct intel_rps *rps = &dev_priv->gt.rps; - bool boost = false; + struct intel_rps *rps = &to_gt(dev_priv)->rps; ssize_t ret; u32 val; @@ -296,28 +295,16 @@ static ssize_t gt_boost_freq_mhz_store(struct device *kdev, if (ret) return ret; - /* Validate against (static) hardware limits */ - val = intel_freq_opcode(rps, val); - if (val < rps->min_freq || val > rps->max_freq) - return -EINVAL; - - mutex_lock(&rps->lock); - if (val != rps->boost_freq) { - rps->boost_freq = val; - boost = atomic_read(&rps->num_waiters); - } - mutex_unlock(&rps->lock); - if (boost) - schedule_work(&rps->work); + ret = intel_rps_set_boost_frequency(rps, val); - return count; + return ret ?: count; } static ssize_t vlv_rpe_freq_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf) { struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev); - struct intel_rps *rps = &dev_priv->gt.rps; + struct intel_rps *rps = &to_gt(dev_priv)->rps; return sysfs_emit(buf, "%d\n", intel_gpu_freq(rps, rps->efficient_freq)); } @@ -325,7 +312,7 @@ static ssize_t vlv_rpe_freq_mhz_show(struct device *kdev, static ssize_t gt_max_freq_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf) { struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev); - struct intel_gt *gt = &dev_priv->gt; + struct intel_gt *gt = to_gt(dev_priv); struct intel_rps *rps = >->rps; return sysfs_emit(buf, "%d\n", intel_rps_get_max_frequency(rps)); @@ -336,7 +323,7 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev, const char *buf, size_t count) { struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev); - struct intel_gt *gt = &dev_priv->gt; + struct intel_gt *gt = to_gt(dev_priv); struct intel_rps *rps = >->rps; ssize_t ret; u32 val; @@ -353,7 +340,7 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev, static ssize_t gt_min_freq_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf) { struct drm_i915_private *i915 = kdev_minor_to_i915(kdev); - struct intel_gt *gt = &i915->gt; + struct intel_gt *gt = to_gt(i915); struct intel_rps *rps = >->rps; return sysfs_emit(buf, "%d\n", intel_rps_get_min_frequency(rps)); @@ -364,7 +351,7 @@ static ssize_t gt_min_freq_mhz_store(struct device *kdev, const char *buf, size_t count) { struct drm_i915_private *i915 = kdev_minor_to_i915(kdev); - struct intel_rps *rps = &i915->gt.rps; + struct intel_rps *rps = &to_gt(i915)->rps; ssize_t ret; u32 val; @@ -394,7 +381,7 @@ static DEVICE_ATTR(gt_RPn_freq_mhz, S_IRUGO, gt_rp_mhz_show, NULL); static ssize_t gt_rp_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf) { struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev); - struct intel_rps *rps = &dev_priv->gt.rps; + struct intel_rps *rps = &to_gt(dev_priv)->rps; u32 val; if (attr == &dev_attr_gt_RP0_freq_mhz) diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index 8104981a6604..37b5c9e9d260 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -1,4 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM i915 + #if !defined(_I915_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ) #define _I915_TRACE_H_ @@ -8,511 +12,11 @@ #include <drm/drm_drv.h> -#include "display/intel_crtc.h" -#include "display/intel_display_types.h" #include "gt/intel_engine.h" #include "i915_drv.h" #include "i915_irq.h" -#undef TRACE_SYSTEM -#define TRACE_SYSTEM i915 -#define TRACE_INCLUDE_FILE i915_trace - -/* watermark/fifo updates */ - -TRACE_EVENT(intel_pipe_enable, - TP_PROTO(struct intel_crtc *crtc), - TP_ARGS(crtc), - - TP_STRUCT__entry( - __array(u32, frame, 3) - __array(u32, scanline, 3) - __field(enum pipe, pipe) - ), - TP_fast_assign( - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - struct intel_crtc *it__; - 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__); - } - __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), - __entry->frame[PIPE_A], __entry->scanline[PIPE_A], - __entry->frame[PIPE_B], __entry->scanline[PIPE_B], - __entry->frame[PIPE_C], __entry->scanline[PIPE_C]) -); - -TRACE_EVENT(intel_pipe_disable, - TP_PROTO(struct intel_crtc *crtc), - TP_ARGS(crtc), - - TP_STRUCT__entry( - __array(u32, frame, 3) - __array(u32, scanline, 3) - __field(enum pipe, pipe) - ), - - TP_fast_assign( - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - struct intel_crtc *it__; - 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__); - } - __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), - __entry->frame[PIPE_A], __entry->scanline[PIPE_A], - __entry->frame[PIPE_B], __entry->scanline[PIPE_B], - __entry->frame[PIPE_C], __entry->scanline[PIPE_C]) -); - -TRACE_EVENT(intel_pipe_crc, - TP_PROTO(struct intel_crtc *crtc, const u32 *crcs), - TP_ARGS(crtc, crcs), - - TP_STRUCT__entry( - __field(enum pipe, pipe) - __field(u32, frame) - __field(u32, scanline) - __array(u32, crcs, 5) - ), - - TP_fast_assign( - __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]) -); - -TRACE_EVENT(intel_cpu_fifo_underrun, - TP_PROTO(struct drm_i915_private *dev_priv, enum pipe pipe), - TP_ARGS(dev_priv, pipe), - - TP_STRUCT__entry( - __field(enum pipe, pipe) - __field(u32, frame) - __field(u32, scanline) - ), - - TP_fast_assign( - struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe); - __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), - __entry->frame, __entry->scanline) -); - -TRACE_EVENT(intel_pch_fifo_underrun, - TP_PROTO(struct drm_i915_private *dev_priv, enum pipe pch_transcoder), - TP_ARGS(dev_priv, pch_transcoder), - - TP_STRUCT__entry( - __field(enum pipe, pipe) - __field(u32, frame) - __field(u32, scanline) - ), - - TP_fast_assign( - enum pipe pipe = pch_transcoder; - struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe); - __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), - __entry->frame, __entry->scanline) -); - -TRACE_EVENT(intel_memory_cxsr, - TP_PROTO(struct drm_i915_private *dev_priv, bool old, bool new), - TP_ARGS(dev_priv, old, new), - - TP_STRUCT__entry( - __array(u32, frame, 3) - __array(u32, scanline, 3) - __field(bool, old) - __field(bool, new) - ), - - TP_fast_assign( - struct intel_crtc *crtc; - 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); - } - __entry->old = old; - __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", - onoff(__entry->old), onoff(__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]) -); - -TRACE_EVENT(g4x_wm, - TP_PROTO(struct intel_crtc *crtc, const struct g4x_wm_values *wm), - TP_ARGS(crtc, wm), - - TP_STRUCT__entry( - __field(enum pipe, pipe) - __field(u32, frame) - __field(u32, scanline) - __field(u16, primary) - __field(u16, sprite) - __field(u16, cursor) - __field(u16, sr_plane) - __field(u16, sr_cursor) - __field(u16, sr_fbc) - __field(u16, hpll_plane) - __field(u16, hpll_cursor) - __field(u16, hpll_fbc) - __field(bool, cxsr) - __field(bool, hpll) - __field(bool, fbc) - ), - - TP_fast_assign( - __entry->pipe = crtc->pipe; - __entry->frame = intel_crtc_get_vblank_counter(crtc); - __entry->scanline = intel_get_crtc_scanline(crtc); - __entry->primary = wm->pipe[crtc->pipe].plane[PLANE_PRIMARY]; - __entry->sprite = wm->pipe[crtc->pipe].plane[PLANE_SPRITE0]; - __entry->cursor = wm->pipe[crtc->pipe].plane[PLANE_CURSOR]; - __entry->sr_plane = wm->sr.plane; - __entry->sr_cursor = wm->sr.cursor; - __entry->sr_fbc = wm->sr.fbc; - __entry->hpll_plane = wm->hpll.plane; - __entry->hpll_cursor = wm->hpll.cursor; - __entry->hpll_fbc = wm->hpll.fbc; - __entry->cxsr = wm->cxsr; - __entry->hpll = wm->hpll_en; - __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, - __entry->primary, __entry->sprite, __entry->cursor, - yesno(__entry->cxsr), __entry->sr_plane, __entry->sr_cursor, __entry->sr_fbc, - yesno(__entry->hpll), __entry->hpll_plane, __entry->hpll_cursor, __entry->hpll_fbc, - yesno(__entry->fbc)) -); - -TRACE_EVENT(vlv_wm, - TP_PROTO(struct intel_crtc *crtc, const struct vlv_wm_values *wm), - TP_ARGS(crtc, wm), - - TP_STRUCT__entry( - __field(enum pipe, pipe) - __field(u32, frame) - __field(u32, scanline) - __field(u32, level) - __field(u32, cxsr) - __field(u32, primary) - __field(u32, sprite0) - __field(u32, sprite1) - __field(u32, cursor) - __field(u32, sr_plane) - __field(u32, sr_cursor) - ), - - TP_fast_assign( - __entry->pipe = crtc->pipe; - __entry->frame = intel_crtc_get_vblank_counter(crtc); - __entry->scanline = intel_get_crtc_scanline(crtc); - __entry->level = wm->level; - __entry->cxsr = wm->cxsr; - __entry->primary = wm->pipe[crtc->pipe].plane[PLANE_PRIMARY]; - __entry->sprite0 = wm->pipe[crtc->pipe].plane[PLANE_SPRITE0]; - __entry->sprite1 = wm->pipe[crtc->pipe].plane[PLANE_SPRITE1]; - __entry->cursor = wm->pipe[crtc->pipe].plane[PLANE_CURSOR]; - __entry->sr_plane = wm->sr.plane; - __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, - __entry->primary, __entry->sprite0, __entry->sprite1, __entry->cursor, - __entry->sr_plane, __entry->sr_cursor) -); - -TRACE_EVENT(vlv_fifo_size, - TP_PROTO(struct intel_crtc *crtc, u32 sprite0_start, u32 sprite1_start, u32 fifo_size), - TP_ARGS(crtc, sprite0_start, sprite1_start, fifo_size), - - TP_STRUCT__entry( - __field(enum pipe, pipe) - __field(u32, frame) - __field(u32, scanline) - __field(u32, sprite0_start) - __field(u32, sprite1_start) - __field(u32, fifo_size) - ), - - TP_fast_assign( - __entry->pipe = crtc->pipe; - __entry->frame = intel_crtc_get_vblank_counter(crtc); - __entry->scanline = intel_get_crtc_scanline(crtc); - __entry->sprite0_start = sprite0_start; - __entry->sprite1_start = sprite1_start; - __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) -); - -/* plane updates */ - -TRACE_EVENT(intel_update_plane, - TP_PROTO(struct drm_plane *plane, struct intel_crtc *crtc), - TP_ARGS(plane, crtc), - - TP_STRUCT__entry( - __field(enum pipe, pipe) - __field(u32, frame) - __field(u32, scanline) - __array(int, src, 4) - __array(int, dst, 4) - __string(name, plane->name) - ), - - TP_fast_assign( - __assign_str(name, plane->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)); - ), - - TP_printk("pipe %c, plane %s, frame=%u, scanline=%u, " DRM_RECT_FP_FMT " -> " DRM_RECT_FMT, - 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_disable_plane, - TP_PROTO(struct drm_plane *plane, struct intel_crtc *crtc), - TP_ARGS(plane, crtc), - - TP_STRUCT__entry( - __field(enum pipe, pipe) - __field(u32, frame) - __field(u32, scanline) - __string(name, plane->name) - ), - - TP_fast_assign( - __assign_str(name, plane->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), - __entry->frame, __entry->scanline) -); - -/* fbc */ - -TRACE_EVENT(intel_fbc_activate, - TP_PROTO(struct intel_crtc *crtc), - TP_ARGS(crtc), - - TP_STRUCT__entry( - __field(enum pipe, pipe) - __field(u32, frame) - __field(u32, scanline) - ), - - TP_fast_assign( - __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) -); - -TRACE_EVENT(intel_fbc_deactivate, - TP_PROTO(struct intel_crtc *crtc), - TP_ARGS(crtc), - - TP_STRUCT__entry( - __field(enum pipe, pipe) - __field(u32, frame) - __field(u32, scanline) - ), - - TP_fast_assign( - __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) -); - -TRACE_EVENT(intel_fbc_nuke, - TP_PROTO(struct intel_crtc *crtc), - TP_ARGS(crtc), - - TP_STRUCT__entry( - __field(enum pipe, pipe) - __field(u32, frame) - __field(u32, scanline) - ), - - TP_fast_assign( - __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) -); - -/* pipe updates */ - -TRACE_EVENT(intel_pipe_update_start, - TP_PROTO(struct intel_crtc *crtc), - TP_ARGS(crtc), - - TP_STRUCT__entry( - __field(enum pipe, pipe) - __field(u32, frame) - __field(u32, scanline) - __field(u32, min) - __field(u32, max) - ), - - TP_fast_assign( - __entry->pipe = crtc->pipe; - __entry->frame = intel_crtc_get_vblank_counter(crtc); - __entry->scanline = intel_get_crtc_scanline(crtc); - __entry->min = crtc->debug.min_vbl; - __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) -); - -TRACE_EVENT(intel_pipe_update_vblank_evaded, - TP_PROTO(struct intel_crtc *crtc), - TP_ARGS(crtc), - - TP_STRUCT__entry( - __field(enum pipe, pipe) - __field(u32, frame) - __field(u32, scanline) - __field(u32, min) - __field(u32, max) - ), - - TP_fast_assign( - __entry->pipe = crtc->pipe; - __entry->frame = crtc->debug.start_vbl_count; - __entry->scanline = crtc->debug.scanline_start; - __entry->min = crtc->debug.min_vbl; - __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) -); - -TRACE_EVENT(intel_pipe_update_end, - TP_PROTO(struct intel_crtc *crtc, u32 frame, int scanline_end), - TP_ARGS(crtc, frame, scanline_end), - - TP_STRUCT__entry( - __field(enum pipe, pipe) - __field(u32, frame) - __field(u32, scanline) - ), - - TP_fast_assign( - __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) -); - -/* frontbuffer tracking */ - -TRACE_EVENT(intel_frontbuffer_invalidate, - TP_PROTO(unsigned int frontbuffer_bits, unsigned int origin), - TP_ARGS(frontbuffer_bits, origin), - - TP_STRUCT__entry( - __field(unsigned int, frontbuffer_bits) - __field(unsigned int, origin) - ), - - TP_fast_assign( - __entry->frontbuffer_bits = frontbuffer_bits; - __entry->origin = origin; - ), - - TP_printk("frontbuffer_bits=0x%08x, origin=%u", - __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_STRUCT__entry( - __field(unsigned int, frontbuffer_bits) - __field(unsigned int, origin) - ), - - TP_fast_assign( - __entry->frontbuffer_bits = frontbuffer_bits; - __entry->origin = origin; - ), - - TP_printk("frontbuffer_bits=0x%08x, origin=%u", - __entry->frontbuffer_bits, __entry->origin) -); - /* object tracking */ TRACE_EVENT(i915_gem_object_create, @@ -1260,5 +764,7 @@ DEFINE_EVENT(i915_context, i915_context_free, /* This part must be outside protection */ #undef TRACE_INCLUDE_PATH +#undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_PATH ../../drivers/gpu/drm/i915 +#define TRACE_INCLUDE_FILE i915_trace #include <trace/define_trace.h> diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index bef795e265a6..29a858c53bdd 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -40,12 +40,12 @@ static struct kmem_cache *slab_vmas; -struct i915_vma *i915_vma_alloc(void) +static struct i915_vma *i915_vma_alloc(void) { return kmem_cache_zalloc(slab_vmas, GFP_KERNEL); } -void i915_vma_free(struct i915_vma *vma) +static void i915_vma_free(struct i915_vma *vma) { return kmem_cache_free(slab_vmas, vma); } @@ -109,11 +109,9 @@ vma_create(struct drm_i915_gem_object *obj, return ERR_PTR(-ENOMEM); kref_init(&vma->ref); - mutex_init(&vma->pages_mutex); vma->vm = i915_vm_get(vm); vma->ops = &vm->vma_ops; vma->obj = obj; - vma->resv = obj->base.resv; vma->size = obj->base.size; vma->display_alignment = I915_GTT_MIN_ALIGNMENT; @@ -346,7 +344,7 @@ int i915_vma_wait_for_bind(struct i915_vma *vma) fence = dma_fence_get_rcu_safe(&vma->active.excl.fence); rcu_read_unlock(); if (fence) { - err = dma_fence_wait(fence, MAX_SCHEDULE_TIMEOUT); + err = dma_fence_wait(fence, true); dma_fence_put(fence); } } @@ -354,6 +352,28 @@ int i915_vma_wait_for_bind(struct i915_vma *vma) return err; } +#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM) +static int i915_vma_verify_bind_complete(struct i915_vma *vma) +{ + struct dma_fence *fence = i915_active_fence_get(&vma->active.excl); + int err; + + if (!fence) + return 0; + + if (dma_fence_is_signaled(fence)) + err = fence->error; + else + err = -EBUSY; + + dma_fence_put(fence); + + return err; +} +#else +#define i915_vma_verify_bind_complete(_vma) 0 +#endif + /** * i915_vma_bind - Sets up PTEs for an VMA in it's corresponding address space. * @vma: VMA to map @@ -373,6 +393,7 @@ int i915_vma_bind(struct i915_vma *vma, u32 bind_flags; u32 vma_flags; + lockdep_assert_held(&vma->vm->mutex); GEM_BUG_ON(!drm_mm_node_allocated(&vma->node)); GEM_BUG_ON(vma->size > vma->node.size); @@ -394,7 +415,7 @@ int i915_vma_bind(struct i915_vma *vma, if (bind_flags == 0) return 0; - GEM_BUG_ON(!vma->pages); + GEM_BUG_ON(!atomic_read(&vma->pages_count)); trace_i915_vma_bind(vma, bind_flags); if (work && bind_flags & vma->vm->bind_async_flags) { @@ -423,11 +444,16 @@ int i915_vma_bind(struct i915_vma *vma, work->base.dma.error = 0; /* enable the queue_work() */ + __i915_gem_object_pin_pages(vma->obj); + work->pinned = i915_gem_object_get(vma->obj); + } else { if (vma->obj) { - __i915_gem_object_pin_pages(vma->obj); - work->pinned = i915_gem_object_get(vma->obj); + int ret; + + ret = i915_gem_object_wait_moving_fence(vma->obj, true); + if (ret) + return ret; } - } else { vma->ops->bind_vma(vma->vm, NULL, vma, cache_level, bind_flags); } @@ -449,6 +475,7 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma) GEM_BUG_ON(!i915_vma_is_ggtt(vma)); GEM_BUG_ON(!i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND)); + GEM_BUG_ON(i915_vma_verify_bind_complete(vma)); ptr = READ_ONCE(vma->iomap); if (ptr == NULL) { @@ -667,7 +694,7 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags) } color = 0; - if (vma->obj && i915_vm_has_cache_coloring(vma->vm)) + if (i915_vm_has_cache_coloring(vma->vm)) color = vma->obj->cache_level; if (flags & PIN_OFFSET_FIXED) { @@ -789,40 +816,356 @@ unpinned: return pinned; } -static int vma_get_pages(struct i915_vma *vma) +static struct scatterlist * +rotate_pages(struct drm_i915_gem_object *obj, unsigned int offset, + unsigned int width, unsigned int height, + unsigned int src_stride, unsigned int dst_stride, + struct sg_table *st, struct scatterlist *sg) { - int err = 0; - bool pinned_pages = false; + unsigned int column, row; + unsigned int src_idx; - if (atomic_add_unless(&vma->pages_count, 1, 0)) - return 0; + for (column = 0; column < width; column++) { + unsigned int left; - if (vma->obj) { - err = i915_gem_object_pin_pages(vma->obj); - if (err) - return err; - pinned_pages = true; + src_idx = src_stride * (height - 1) + column + offset; + for (row = 0; row < height; row++) { + st->nents++; + /* + * We don't need the pages, but need to initialize + * the entries so the sg list can be happily traversed. + * The only thing we need are DMA addresses. + */ + sg_set_page(sg, NULL, I915_GTT_PAGE_SIZE, 0); + sg_dma_address(sg) = + i915_gem_object_get_dma_address(obj, src_idx); + sg_dma_len(sg) = I915_GTT_PAGE_SIZE; + sg = sg_next(sg); + src_idx -= src_stride; + } + + left = (dst_stride - height) * I915_GTT_PAGE_SIZE; + + if (!left) + continue; + + st->nents++; + + /* + * The DE ignores the PTEs for the padding tiles, the sg entry + * here is just a conenience to indicate how many padding PTEs + * to insert at this spot. + */ + sg_set_page(sg, NULL, left, 0); + sg_dma_address(sg) = 0; + sg_dma_len(sg) = left; + sg = sg_next(sg); + } + + return sg; +} + +static noinline struct sg_table * +intel_rotate_pages(struct intel_rotation_info *rot_info, + struct drm_i915_gem_object *obj) +{ + unsigned int size = intel_rotation_info_size(rot_info); + struct drm_i915_private *i915 = to_i915(obj->base.dev); + struct sg_table *st; + struct scatterlist *sg; + int ret = -ENOMEM; + int i; + + /* Allocate target SG list. */ + st = kmalloc(sizeof(*st), GFP_KERNEL); + if (!st) + goto err_st_alloc; + + ret = sg_alloc_table(st, size, GFP_KERNEL); + if (ret) + goto err_sg_alloc; + + st->nents = 0; + sg = st->sgl; + + for (i = 0 ; i < ARRAY_SIZE(rot_info->plane); i++) + sg = rotate_pages(obj, rot_info->plane[i].offset, + rot_info->plane[i].width, rot_info->plane[i].height, + rot_info->plane[i].src_stride, + rot_info->plane[i].dst_stride, + st, sg); + + return st; + +err_sg_alloc: + kfree(st); +err_st_alloc: + + drm_dbg(&i915->drm, "Failed to create rotated mapping for object size %zu! (%ux%u tiles, %u pages)\n", + obj->base.size, rot_info->plane[0].width, + rot_info->plane[0].height, size); + + return ERR_PTR(ret); +} + +static struct scatterlist * +remap_pages(struct drm_i915_gem_object *obj, + unsigned int offset, unsigned int alignment_pad, + unsigned int width, unsigned int height, + unsigned int src_stride, unsigned int dst_stride, + struct sg_table *st, struct scatterlist *sg) +{ + unsigned int row; + + if (!width || !height) + return sg; + + if (alignment_pad) { + st->nents++; + + /* + * The DE ignores the PTEs for the padding tiles, the sg entry + * here is just a convenience to indicate how many padding PTEs + * to insert at this spot. + */ + sg_set_page(sg, NULL, alignment_pad * 4096, 0); + sg_dma_address(sg) = 0; + sg_dma_len(sg) = alignment_pad * 4096; + sg = sg_next(sg); } - /* Allocations ahoy! */ - if (mutex_lock_interruptible(&vma->pages_mutex)) { - err = -EINTR; - goto unpin; + for (row = 0; row < height; row++) { + unsigned int left = width * I915_GTT_PAGE_SIZE; + + while (left) { + dma_addr_t addr; + unsigned int length; + + /* + * We don't need the pages, but need to initialize + * the entries so the sg list can be happily traversed. + * The only thing we need are DMA addresses. + */ + + addr = i915_gem_object_get_dma_address_len(obj, offset, &length); + + length = min(left, length); + + st->nents++; + + sg_set_page(sg, NULL, length, 0); + sg_dma_address(sg) = addr; + sg_dma_len(sg) = length; + sg = sg_next(sg); + + offset += length / I915_GTT_PAGE_SIZE; + left -= length; + } + + offset += src_stride - width; + + left = (dst_stride - width) * I915_GTT_PAGE_SIZE; + + if (!left) + continue; + + st->nents++; + + /* + * The DE ignores the PTEs for the padding tiles, the sg entry + * here is just a conenience to indicate how many padding PTEs + * to insert at this spot. + */ + sg_set_page(sg, NULL, left, 0); + sg_dma_address(sg) = 0; + sg_dma_len(sg) = left; + sg = sg_next(sg); } - if (!atomic_read(&vma->pages_count)) { - err = vma->ops->set_pages(vma); - if (err) - goto unlock; - pinned_pages = false; + return sg; +} + +static noinline struct sg_table * +intel_remap_pages(struct intel_remapped_info *rem_info, + struct drm_i915_gem_object *obj) +{ + unsigned int size = intel_remapped_info_size(rem_info); + struct drm_i915_private *i915 = to_i915(obj->base.dev); + struct sg_table *st; + struct scatterlist *sg; + unsigned int gtt_offset = 0; + int ret = -ENOMEM; + int i; + + /* Allocate target SG list. */ + st = kmalloc(sizeof(*st), GFP_KERNEL); + if (!st) + goto err_st_alloc; + + ret = sg_alloc_table(st, size, GFP_KERNEL); + if (ret) + goto err_sg_alloc; + + st->nents = 0; + sg = st->sgl; + + for (i = 0 ; i < ARRAY_SIZE(rem_info->plane); i++) { + unsigned int alignment_pad = 0; + + if (rem_info->plane_alignment) + alignment_pad = ALIGN(gtt_offset, rem_info->plane_alignment) - gtt_offset; + + sg = remap_pages(obj, + rem_info->plane[i].offset, alignment_pad, + rem_info->plane[i].width, rem_info->plane[i].height, + rem_info->plane[i].src_stride, rem_info->plane[i].dst_stride, + st, sg); + + gtt_offset += alignment_pad + + rem_info->plane[i].dst_stride * rem_info->plane[i].height; + } + + i915_sg_trim(st); + + return st; + +err_sg_alloc: + kfree(st); +err_st_alloc: + + drm_dbg(&i915->drm, "Failed to create remapped mapping for object size %zu! (%ux%u tiles, %u pages)\n", + obj->base.size, rem_info->plane[0].width, + rem_info->plane[0].height, size); + + return ERR_PTR(ret); +} + +static noinline struct sg_table * +intel_partial_pages(const struct i915_ggtt_view *view, + struct drm_i915_gem_object *obj) +{ + struct sg_table *st; + struct scatterlist *sg, *iter; + unsigned int count = view->partial.size; + unsigned int offset; + int ret = -ENOMEM; + + st = kmalloc(sizeof(*st), GFP_KERNEL); + if (!st) + goto err_st_alloc; + + ret = sg_alloc_table(st, count, GFP_KERNEL); + if (ret) + goto err_sg_alloc; + + iter = i915_gem_object_get_sg_dma(obj, view->partial.offset, &offset); + GEM_BUG_ON(!iter); + + sg = st->sgl; + st->nents = 0; + do { + unsigned int len; + + len = min(sg_dma_len(iter) - (offset << PAGE_SHIFT), + count << PAGE_SHIFT); + sg_set_page(sg, NULL, len, 0); + sg_dma_address(sg) = + sg_dma_address(iter) + (offset << PAGE_SHIFT); + sg_dma_len(sg) = len; + + st->nents++; + count -= len >> PAGE_SHIFT; + if (count == 0) { + sg_mark_end(sg); + i915_sg_trim(st); /* Drop any unused tail entries. */ + + return st; + } + + sg = __sg_next(sg); + iter = __sg_next(iter); + offset = 0; + } while (1); + +err_sg_alloc: + kfree(st); +err_st_alloc: + return ERR_PTR(ret); +} + +static int +__i915_vma_get_pages(struct i915_vma *vma) +{ + struct sg_table *pages; + int ret; + + /* + * The vma->pages are only valid within the lifespan of the borrowed + * obj->mm.pages. When the obj->mm.pages sg_table is regenerated, so + * must be the vma->pages. A simple rule is that vma->pages must only + * be accessed when the obj->mm.pages are pinned. + */ + GEM_BUG_ON(!i915_gem_object_has_pinned_pages(vma->obj)); + + switch (vma->ggtt_view.type) { + default: + GEM_BUG_ON(vma->ggtt_view.type); + fallthrough; + case I915_GGTT_VIEW_NORMAL: + pages = vma->obj->mm.pages; + break; + + case I915_GGTT_VIEW_ROTATED: + pages = + intel_rotate_pages(&vma->ggtt_view.rotated, vma->obj); + break; + + case I915_GGTT_VIEW_REMAPPED: + pages = + intel_remap_pages(&vma->ggtt_view.remapped, vma->obj); + break; + + case I915_GGTT_VIEW_PARTIAL: + pages = intel_partial_pages(&vma->ggtt_view, vma->obj); + break; } + + ret = 0; + if (IS_ERR(pages)) { + ret = PTR_ERR(pages); + pages = NULL; + drm_err(&vma->vm->i915->drm, + "Failed to get pages for VMA view type %u (%d)!\n", + vma->ggtt_view.type, ret); + } + + vma->pages = pages; + + return ret; +} + +I915_SELFTEST_EXPORT int i915_vma_get_pages(struct i915_vma *vma) +{ + int err; + + if (atomic_add_unless(&vma->pages_count, 1, 0)) + return 0; + + err = i915_gem_object_pin_pages(vma->obj); + if (err) + return err; + + err = __i915_vma_get_pages(vma); + if (err) + goto err_unpin; + + vma->page_sizes = vma->obj->mm.page_sizes; atomic_inc(&vma->pages_count); -unlock: - mutex_unlock(&vma->pages_mutex); -unpin: - if (pinned_pages) - __i915_gem_object_unpin_pages(vma->obj); + return 0; + +err_unpin: + __i915_gem_object_unpin_pages(vma->obj); return err; } @@ -830,18 +1173,31 @@ unpin: static void __vma_put_pages(struct i915_vma *vma, unsigned int count) { /* We allocate under vma_get_pages, so beware the shrinker */ - mutex_lock_nested(&vma->pages_mutex, SINGLE_DEPTH_NESTING); + struct sg_table *pages = READ_ONCE(vma->pages); + GEM_BUG_ON(atomic_read(&vma->pages_count) < count); + if (atomic_sub_return(count, &vma->pages_count) == 0) { - vma->ops->clear_pages(vma); - GEM_BUG_ON(vma->pages); - if (vma->obj) - i915_gem_object_unpin_pages(vma->obj); + /* + * The atomic_sub_return is a read barrier for the READ_ONCE of + * vma->pages above. + * + * READ_ONCE is safe because this is either called from the same + * function (i915_vma_pin_ww), or guarded by vma->vm->mutex. + * + * TODO: We're leaving vma->pages dangling, until vma->obj->resv + * lock is required. + */ + if (pages != vma->obj->mm.pages) { + sg_free_table(pages); + kfree(pages); + } + + i915_gem_object_unpin_pages(vma->obj); } - mutex_unlock(&vma->pages_mutex); } -static void vma_put_pages(struct i915_vma *vma) +I915_SELFTEST_EXPORT void i915_vma_put_pages(struct i915_vma *vma) { if (atomic_add_unless(&vma->pages_count, -1, 1)) return; @@ -867,14 +1223,13 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, u64 size, u64 alignment, u64 flags) { struct i915_vma_work *work = NULL; + struct dma_fence *moving = NULL; intel_wakeref_t wakeref = 0; unsigned int bound; int err; -#ifdef CONFIG_PROVE_LOCKING - if (debug_locks && !WARN_ON(!ww) && vma->resv) - assert_vma_held(vma); -#endif + assert_vma_held(vma); + GEM_BUG_ON(!ww); BUILD_BUG_ON(PIN_GLOBAL != I915_VMA_GLOBAL_BIND); BUILD_BUG_ON(PIN_USER != I915_VMA_LOCAL_BIND); @@ -885,14 +1240,15 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, if (try_qad_pin(vma, flags & I915_VMA_BIND_MASK)) return 0; - err = vma_get_pages(vma); + err = i915_vma_get_pages(vma); if (err) return err; if (flags & PIN_GLOBAL) wakeref = intel_runtime_pm_get(&vma->vm->i915->runtime_pm); - if (flags & vma->vm->bind_async_flags) { + moving = vma->obj ? i915_gem_object_get_moving_fence(vma->obj) : NULL; + if (flags & vma->vm->bind_async_flags || moving) { /* lock VM */ err = i915_vm_lock_objects(vma->vm, ww); if (err) @@ -906,6 +1262,8 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, work->vm = i915_vm_get(vma->vm); + dma_fence_work_chain(&work->base, moving); + /* Allocate enough page directories to used PTE */ if (vma->vm->allocate_va_range) { err = i915_vm_alloc_pt_stash(vma->vm, @@ -980,7 +1338,7 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, GEM_BUG_ON(!vma->pages); err = i915_vma_bind(vma, - vma->obj ? vma->obj->cache_level : 0, + vma->obj->cache_level, flags, work); if (err) goto err_remove; @@ -1010,7 +1368,11 @@ err_fence: err_rpm: if (wakeref) intel_runtime_pm_put(&vma->vm->i915->runtime_pm, wakeref); - vma_put_pages(vma); + + if (moving) + dma_fence_put(moving); + + i915_vma_put_pages(vma); return err; } @@ -1025,23 +1387,15 @@ static void flush_idle_contexts(struct intel_gt *gt) intel_gt_wait_for_idle(gt, MAX_SCHEDULE_TIMEOUT); } -int i915_ggtt_pin(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, - u32 align, unsigned int flags) +static int __i915_ggtt_pin(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, + u32 align, unsigned int flags) { struct i915_address_space *vm = vma->vm; int err; - GEM_BUG_ON(!i915_vma_is_ggtt(vma)); - -#ifdef CONFIG_LOCKDEP - WARN_ON(!ww && vma->resv && dma_resv_held(vma->resv)); -#endif - do { - if (ww) - err = i915_vma_pin_ww(vma, ww, 0, align, flags | PIN_GLOBAL); - else - err = i915_vma_pin(vma, 0, align, flags | PIN_GLOBAL); + err = i915_vma_pin_ww(vma, ww, 0, align, flags | PIN_GLOBAL); + if (err != -ENOSPC) { if (!err) { err = i915_vma_wait_for_bind(vma); @@ -1060,6 +1414,30 @@ int i915_ggtt_pin(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, } while (1); } +int i915_ggtt_pin(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, + u32 align, unsigned int flags) +{ + struct i915_gem_ww_ctx _ww; + int err; + + GEM_BUG_ON(!i915_vma_is_ggtt(vma)); + + if (ww) + return __i915_ggtt_pin(vma, ww, align, flags); + +#ifdef CONFIG_LOCKDEP + WARN_ON(dma_resv_held(vma->obj->base.resv)); +#endif + + for_i915_gem_ww(&_ww, err, true) { + err = i915_gem_object_lock(vma->obj, &_ww); + if (!err) + err = __i915_ggtt_pin(vma, &_ww, align, flags); + } + + return err; +} + static void __vma_close(struct i915_vma *vma, struct intel_gt *gt) { /* @@ -1113,6 +1491,7 @@ void i915_vma_reopen(struct i915_vma *vma) void i915_vma_release(struct kref *ref) { struct i915_vma *vma = container_of(ref, typeof(*vma), ref); + struct drm_i915_gem_object *obj = vma->obj; if (drm_mm_node_allocated(&vma->node)) { mutex_lock(&vma->vm->mutex); @@ -1123,15 +1502,11 @@ void i915_vma_release(struct kref *ref) } GEM_BUG_ON(i915_vma_is_active(vma)); - if (vma->obj) { - struct drm_i915_gem_object *obj = vma->obj; - - spin_lock(&obj->vma.lock); - list_del(&vma->obj_link); - if (!RB_EMPTY_NODE(&vma->obj_node)) - rb_erase(&vma->obj_node, &obj->vma.tree); - spin_unlock(&obj->vma.lock); - } + spin_lock(&obj->vma.lock); + list_del(&vma->obj_link); + if (!RB_EMPTY_NODE(&vma->obj_node)) + rb_erase(&vma->obj_node, &obj->vma.tree); + spin_unlock(&obj->vma.lock); __i915_vma_remove_closed(vma); i915_vm_put(vma->vm); @@ -1217,7 +1592,7 @@ __i915_request_await_bind(struct i915_request *rq, struct i915_vma *vma) return __i915_request_await_exclusive(rq, &vma->active); } -int __i915_vma_move_to_active(struct i915_vma *vma, struct i915_request *rq) +static int __i915_vma_move_to_active(struct i915_vma *vma, struct i915_request *rq) { int err; @@ -1256,19 +1631,19 @@ int _i915_vma_move_to_active(struct i915_vma *vma, } if (fence) { - dma_resv_add_excl_fence(vma->resv, fence); + dma_resv_add_excl_fence(vma->obj->base.resv, fence); obj->write_domain = I915_GEM_DOMAIN_RENDER; obj->read_domains = 0; } } else { if (!(flags & __EXEC_OBJECT_NO_RESERVE)) { - err = dma_resv_reserve_shared(vma->resv, 1); + err = dma_resv_reserve_shared(vma->obj->base.resv, 1); if (unlikely(err)) return err; } if (fence) { - dma_resv_add_shared_fence(vma->resv, fence); + dma_resv_add_shared_fence(vma->obj->base.resv, fence); obj->write_domain = 0; } } diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h index 648dbe744c96..32719431b3df 100644 --- a/drivers/gpu/drm/i915/i915_vma.h +++ b/drivers/gpu/drm/i915/i915_vma.h @@ -55,8 +55,6 @@ 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) -int __must_check __i915_vma_move_to_active(struct i915_vma *vma, - struct i915_request *rq); int __must_check _i915_vma_move_to_active(struct i915_vma *vma, struct i915_request *rq, struct dma_fence *fence, @@ -234,16 +232,16 @@ static inline void __i915_vma_put(struct i915_vma *vma) kref_put(&vma->ref, i915_vma_release); } -#define assert_vma_held(vma) dma_resv_assert_held((vma)->resv) +#define assert_vma_held(vma) dma_resv_assert_held((vma)->obj->base.resv) static inline void i915_vma_lock(struct i915_vma *vma) { - dma_resv_lock(vma->resv, NULL); + dma_resv_lock(vma->obj->base.resv, NULL); } static inline void i915_vma_unlock(struct i915_vma *vma) { - dma_resv_unlock(vma->resv); + dma_resv_unlock(vma->obj->base.resv); } int __must_check @@ -418,9 +416,6 @@ static inline void i915_vma_clear_scanout(struct i915_vma *vma) list_for_each_entry(V, &(OBJ)->vma.list, obj_link) \ for_each_until(!i915_vma_is_ggtt(V)) -struct i915_vma *i915_vma_alloc(void); -void i915_vma_free(struct i915_vma *vma); - struct i915_vma *i915_vma_make_unshrinkable(struct i915_vma *vma); void i915_vma_make_shrinkable(struct i915_vma *vma); void i915_vma_make_purgeable(struct i915_vma *vma); @@ -436,4 +431,7 @@ static inline int i915_vma_sync(struct i915_vma *vma) void i915_vma_module_exit(void); int i915_vma_module_init(void); +I915_SELFTEST_DECLARE(int i915_vma_get_pages(struct i915_vma *vma)); +I915_SELFTEST_DECLARE(void i915_vma_put_pages(struct i915_vma *vma)); + #endif diff --git a/drivers/gpu/drm/i915/i915_vma_snapshot.c b/drivers/gpu/drm/i915/i915_vma_snapshot.c new file mode 100644 index 000000000000..2949ceea9884 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_vma_snapshot.c @@ -0,0 +1,134 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2021 Intel Corporation + */ + +#include "i915_vma_snapshot.h" +#include "i915_vma_types.h" +#include "i915_vma.h" + +/** + * i915_vma_snapshot_init - Initialize a struct i915_vma_snapshot from + * a struct i915_vma. + * @vsnap: The i915_vma_snapshot to init. + * @vma: A struct i915_vma used to initialize @vsnap. + * @name: Name associated with the snapshot. The character pointer needs to + * stay alive over the lifitime of the shapsot + */ +void i915_vma_snapshot_init(struct i915_vma_snapshot *vsnap, + struct i915_vma *vma, + const char *name) +{ + if (!i915_vma_is_pinned(vma)) + assert_object_held(vma->obj); + + vsnap->name = name; + vsnap->size = vma->size; + vsnap->obj_size = vma->obj->base.size; + vsnap->gtt_offset = vma->node.start; + vsnap->gtt_size = vma->node.size; + vsnap->page_sizes = vma->page_sizes.gtt; + vsnap->pages = vma->pages; + vsnap->pages_rsgt = NULL; + vsnap->mr = NULL; + if (vma->obj->mm.rsgt) + vsnap->pages_rsgt = i915_refct_sgt_get(vma->obj->mm.rsgt); + vsnap->mr = vma->obj->mm.region; + kref_init(&vsnap->kref); + vsnap->vma_resource = &vma->active; + vsnap->onstack = false; + vsnap->present = true; +} + +/** + * i915_vma_snapshot_init_onstack - Initialize a struct i915_vma_snapshot from + * a struct i915_vma, but avoid kfreeing it on last put. + * @vsnap: The i915_vma_snapshot to init. + * @vma: A struct i915_vma used to initialize @vsnap. + * @name: Name associated with the snapshot. The character pointer needs to + * stay alive over the lifitime of the shapsot + */ +void i915_vma_snapshot_init_onstack(struct i915_vma_snapshot *vsnap, + struct i915_vma *vma, + const char *name) +{ + i915_vma_snapshot_init(vsnap, vma, name); + vsnap->onstack = true; +} + +static void vma_snapshot_release(struct kref *ref) +{ + struct i915_vma_snapshot *vsnap = + container_of(ref, typeof(*vsnap), kref); + + vsnap->present = false; + if (vsnap->pages_rsgt) + i915_refct_sgt_put(vsnap->pages_rsgt); + if (!vsnap->onstack) + kfree(vsnap); +} + +/** + * i915_vma_snapshot_put - Put an i915_vma_snapshot pointer reference + * @vsnap: The pointer reference + */ +void i915_vma_snapshot_put(struct i915_vma_snapshot *vsnap) +{ + kref_put(&vsnap->kref, vma_snapshot_release); +} + +/** + * i915_vma_snapshot_put_onstack - Put an onstcak i915_vma_snapshot pointer + * reference and varify that the structure is released + * @vsnap: The pointer reference + * + * This function is intended to be paired with a i915_vma_init_onstack() + * and should be called before exiting the scope that declared or + * freeing the structure that embedded @vsnap to verify that all references + * have been released. + */ +void i915_vma_snapshot_put_onstack(struct i915_vma_snapshot *vsnap) +{ + if (!kref_put(&vsnap->kref, vma_snapshot_release)) + GEM_BUG_ON(1); +} + +/** + * i915_vma_snapshot_resource_pin - Temporarily block the memory the + * vma snapshot is pointing to from being released. + * @vsnap: The vma snapshot. + * @lockdep_cookie: Pointer to bool needed for lockdep support. This needs + * to be passed to the paired i915_vma_snapshot_resource_unpin. + * + * This function will temporarily try to hold up a fence or similar structure + * and will therefore enter a fence signaling critical section. + * + * Return: true if we succeeded in blocking the memory from being released, + * false otherwise. + */ +bool i915_vma_snapshot_resource_pin(struct i915_vma_snapshot *vsnap, + bool *lockdep_cookie) +{ + bool pinned = i915_active_acquire_if_busy(vsnap->vma_resource); + + if (pinned) + *lockdep_cookie = dma_fence_begin_signalling(); + + return pinned; +} + +/** + * i915_vma_snapshot_resource_unpin - Unblock vma snapshot memory from + * being released. + * @vsnap: The vma snapshot. + * @lockdep_cookie: Cookie returned from matching i915_vma_resource_pin(). + * + * Might leave a fence signalling critical section and signal a fence. + */ +void i915_vma_snapshot_resource_unpin(struct i915_vma_snapshot *vsnap, + bool lockdep_cookie) +{ + dma_fence_end_signalling(lockdep_cookie); + + return i915_active_release(vsnap->vma_resource); +} diff --git a/drivers/gpu/drm/i915/i915_vma_snapshot.h b/drivers/gpu/drm/i915/i915_vma_snapshot.h new file mode 100644 index 000000000000..940581df4622 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_vma_snapshot.h @@ -0,0 +1,112 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ +#ifndef _I915_VMA_SNAPSHOT_H_ +#define _I915_VMA_SNAPSHOT_H_ + +#include <linux/kref.h> +#include <linux/slab.h> +#include <linux/types.h> + +struct i915_active; +struct i915_refct_sgt; +struct i915_vma; +struct intel_memory_region; +struct sg_table; + +/** + * DOC: Simple utilities for snapshotting GPU vma metadata, later used for + * error capture. Vi use a separate header for this to avoid issues due to + * recursive header includes. + */ + +/** + * struct i915_vma_snapshot - Snapshot of vma metadata. + * @size: The vma size in bytes. + * @obj_size: The size of the underlying object in bytes. + * @gtt_offset: The gtt offset the vma is bound to. + * @gtt_size: The size in bytes allocated for the vma in the GTT. + * @pages: The struct sg_table pointing to the pages bound. + * @pages_rsgt: The refcounted sg_table holding the reference for @pages if any. + * @mr: The memory region pointed for the pages bound. + * @kref: Reference for this structure. + * @vma_resource: FIXME: A means to keep the unbind fence from signaling. + * Temporarily while we have only sync unbinds, and still use the vma + * active, we use that. With async unbinding we need a signaling refcount + * for the unbind fence. + * @page_sizes: The vma GTT page sizes information. + * @onstack: Whether the structure shouldn't be freed on final put. + * @present: Whether the structure is present and initialized. + */ +struct i915_vma_snapshot { + const char *name; + size_t size; + size_t obj_size; + size_t gtt_offset; + size_t gtt_size; + struct sg_table *pages; + struct i915_refct_sgt *pages_rsgt; + struct intel_memory_region *mr; + struct kref kref; + struct i915_active *vma_resource; + u32 page_sizes; + bool onstack:1; + bool present:1; +}; + +void i915_vma_snapshot_init(struct i915_vma_snapshot *vsnap, + struct i915_vma *vma, + const char *name); + +void i915_vma_snapshot_init_onstack(struct i915_vma_snapshot *vsnap, + struct i915_vma *vma, + const char *name); + +void i915_vma_snapshot_put(struct i915_vma_snapshot *vsnap); + +void i915_vma_snapshot_put_onstack(struct i915_vma_snapshot *vsnap); + +bool i915_vma_snapshot_resource_pin(struct i915_vma_snapshot *vsnap, + bool *lockdep_cookie); + +void i915_vma_snapshot_resource_unpin(struct i915_vma_snapshot *vsnap, + bool lockdep_cookie); + +/** + * i915_vma_snapshot_alloc - Allocate a struct i915_vma_snapshot + * @gfp: Allocation mode. + * + * Return: A pointer to a struct i915_vma_snapshot if successful. + * NULL otherwise. + */ +static inline struct i915_vma_snapshot *i915_vma_snapshot_alloc(gfp_t gfp) +{ + return kmalloc(sizeof(struct i915_vma_snapshot), gfp); +} + +/** + * i915_vma_snapshot_get - Take a reference on a struct i915_vma_snapshot + * + * Return: A pointer to a struct i915_vma_snapshot. + */ +static inline struct i915_vma_snapshot * +i915_vma_snapshot_get(struct i915_vma_snapshot *vsnap) +{ + kref_get(&vsnap->kref); + return vsnap; +} + +/** + * i915_vma_snapshot_present - Whether a struct i915_vma_snapshot is + * present and initialized. + * + * Return: true if present and initialized; false otherwise. + */ +static inline bool +i915_vma_snapshot_present(const struct i915_vma_snapshot *vsnap) +{ + return vsnap && vsnap->present; +} + +#endif diff --git a/drivers/gpu/drm/i915/i915_vma_types.h b/drivers/gpu/drm/i915/i915_vma_types.h index 80e93bf00f2e..ca575e129ced 100644 --- a/drivers/gpu/drm/i915/i915_vma_types.h +++ b/drivers/gpu/drm/i915/i915_vma_types.h @@ -97,11 +97,20 @@ enum i915_cache_level; struct intel_remapped_plane_info { /* in gtt pages */ - u32 offset; - u16 width; - u16 height; - u16 src_stride; - u16 dst_stride; + u32 offset:31; + u32 linear:1; + union { + /* in gtt pages for !linear */ + struct { + u16 width; + u16 height; + u16 src_stride; + u16 dst_stride; + }; + + /* in gtt pages for linear */ + u32 size; + }; } __packed; struct intel_remapped_info { @@ -178,7 +187,6 @@ struct i915_vma { const struct i915_vma_ops *ops; struct drm_i915_gem_object *obj; - struct dma_resv *resv; /** Alias of obj->resv */ struct sg_table *pages; void __iomem *iomap; @@ -262,7 +270,6 @@ struct i915_vma { #define I915_VMA_PAGES_BIAS 24 #define I915_VMA_PAGES_ACTIVE (BIT(24) | 1) atomic_t pages_count; /* number of active binds to the pages */ - struct mutex pages_mutex; /* protect acquire/release of backing pages */ /** * Support different GGTT views into the same object. diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c index 305facedd284..04fd266d70e2 100644 --- a/drivers/gpu/drm/i915/intel_device_info.c +++ b/drivers/gpu/drm/i915/intel_device_info.c @@ -83,33 +83,26 @@ const char *intel_platform_name(enum intel_platform platform) return platform_names[platform]; } -static const char *iommu_name(void) -{ - const char *msg = "n/a"; - -#ifdef CONFIG_INTEL_IOMMU - msg = enableddisabled(intel_iommu_gfx_mapped); -#endif - - return msg; -} - void intel_device_info_print_static(const struct intel_device_info *info, struct drm_printer *p) { - if (info->graphics_rel) - drm_printf(p, "graphics version: %u.%02u\n", info->graphics_ver, info->graphics_rel); + if (info->graphics.rel) + drm_printf(p, "graphics version: %u.%02u\n", info->graphics.ver, + info->graphics.rel); else - drm_printf(p, "graphics version: %u\n", info->graphics_ver); + drm_printf(p, "graphics version: %u\n", info->graphics.ver); - if (info->media_rel) - drm_printf(p, "media version: %u.%02u\n", info->media_ver, info->media_rel); + if (info->media.rel) + drm_printf(p, "media version: %u.%02u\n", info->media.ver, info->media.rel); else - drm_printf(p, "media version: %u\n", info->media_ver); + drm_printf(p, "media version: %u\n", info->media.ver); + + if (info->display.rel) + drm_printf(p, "display version: %u.%02u\n", info->display.ver, info->display.rel); + else + drm_printf(p, "display version: %u\n", info->display.ver); - drm_printf(p, "display version: %u\n", info->display.ver); drm_printf(p, "gt: %d\n", info->gt); - drm_printf(p, "iommu: %s\n", iommu_name()); drm_printf(p, "memory-regions: %x\n", info->memory_regions); drm_printf(p, "page-sizes: %x\n", info->page_sizes); drm_printf(p, "platform: %s\n", intel_platform_name(info->platform)); @@ -177,6 +170,10 @@ static const u16 subplatform_portf_ids[] = { INTEL_ICL_PORT_F_IDS(0), }; +static const u16 subplatform_rpls_ids[] = { + INTEL_RPLS_IDS(0), +}; + static bool find_devid(u16 id, const u16 *p, unsigned int num) { for (; num; num--, p++) { @@ -213,6 +210,9 @@ void intel_device_info_subplatform_init(struct drm_i915_private *i915) } else if (find_devid(devid, subplatform_portf_ids, ARRAY_SIZE(subplatform_portf_ids))) { mask = BIT(INTEL_SUBPLATFORM_PORTF); + } else if (find_devid(devid, subplatform_rpls_ids, + ARRAY_SIZE(subplatform_rpls_ids))) { + mask = BIT(INTEL_SUBPLATFORM_RPL_S); } if (IS_TIGERLAKE(i915)) { @@ -326,33 +326,33 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv) !(sfuse_strap & SFUSE_STRAP_FUSE_LOCK))) { drm_info(&dev_priv->drm, "Display fused off, disabling\n"); - info->pipe_mask = 0; - info->cpu_transcoder_mask = 0; + info->display.pipe_mask = 0; + info->display.cpu_transcoder_mask = 0; } else if (fuse_strap & IVB_PIPE_C_DISABLE) { drm_info(&dev_priv->drm, "PipeC fused off\n"); - info->pipe_mask &= ~BIT(PIPE_C); - info->cpu_transcoder_mask &= ~BIT(TRANSCODER_C); + info->display.pipe_mask &= ~BIT(PIPE_C); + info->display.cpu_transcoder_mask &= ~BIT(TRANSCODER_C); } } else if (HAS_DISPLAY(dev_priv) && DISPLAY_VER(dev_priv) >= 9) { u32 dfsm = intel_de_read(dev_priv, SKL_DFSM); if (dfsm & SKL_DFSM_PIPE_A_DISABLE) { - info->pipe_mask &= ~BIT(PIPE_A); - info->cpu_transcoder_mask &= ~BIT(TRANSCODER_A); + info->display.pipe_mask &= ~BIT(PIPE_A); + info->display.cpu_transcoder_mask &= ~BIT(TRANSCODER_A); } if (dfsm & SKL_DFSM_PIPE_B_DISABLE) { - info->pipe_mask &= ~BIT(PIPE_B); - info->cpu_transcoder_mask &= ~BIT(TRANSCODER_B); + info->display.pipe_mask &= ~BIT(PIPE_B); + info->display.cpu_transcoder_mask &= ~BIT(TRANSCODER_B); } if (dfsm & SKL_DFSM_PIPE_C_DISABLE) { - info->pipe_mask &= ~BIT(PIPE_C); - info->cpu_transcoder_mask &= ~BIT(TRANSCODER_C); + info->display.pipe_mask &= ~BIT(PIPE_C); + info->display.cpu_transcoder_mask &= ~BIT(TRANSCODER_C); } if (DISPLAY_VER(dev_priv) >= 12 && (dfsm & TGL_DFSM_PIPE_D_DISABLE)) { - info->pipe_mask &= ~BIT(PIPE_D); - info->cpu_transcoder_mask &= ~BIT(TRANSCODER_D); + info->display.pipe_mask &= ~BIT(PIPE_D); + info->display.cpu_transcoder_mask &= ~BIT(TRANSCODER_D); } if (dfsm & SKL_DFSM_DISPLAY_HDCP_DISABLE) @@ -369,7 +369,7 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv) info->display.has_dsc = 0; } - if (GRAPHICS_VER(dev_priv) == 6 && intel_vtd_active()) { + if (GRAPHICS_VER(dev_priv) == 6 && intel_vtd_active(dev_priv)) { drm_info(&dev_priv->drm, "Disabling ppGTT for VT-d support\n"); info->ppgtt_type = INTEL_PPGTT_NONE; diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h index 8e6f48d1eb7b..78597d382445 100644 --- a/drivers/gpu/drm/i915/intel_device_info.h +++ b/drivers/gpu/drm/i915/intel_device_info.h @@ -110,6 +110,9 @@ enum intel_platform { #define INTEL_SUBPLATFORM_G10 0 #define INTEL_SUBPLATFORM_G11 1 +/* ADL-S */ +#define INTEL_SUBPLATFORM_RPL_S 0 + enum intel_ppgtt_type { INTEL_PPGTT_NONE = I915_GEM_PPGTT_NONE, INTEL_PPGTT_ALIASING = I915_GEM_PPGTT_ALIASING, @@ -123,6 +126,7 @@ enum intel_ppgtt_type { func(is_dgfx); \ /* Keep has_* in alphabetical order */ \ func(has_64bit_reloc); \ + func(has_64k_pages); \ func(gpu_reset_clobbers_display); \ func(has_reset_engine); \ func(has_global_mocs); \ @@ -166,11 +170,14 @@ enum intel_ppgtt_type { func(overlay_needs_physical); \ func(supports_tv); +struct ip_version { + u8 ver; + u8 rel; +}; + struct intel_device_info { - u8 graphics_ver; - u8 graphics_rel; - u8 media_ver; - u8 media_rel; + struct ip_version graphics; + struct ip_version media; intel_engine_mask_t platform_engine_mask; /* Engines supported by the HW */ @@ -189,17 +196,17 @@ struct intel_device_info { u8 gt; /* GT number, 0 if undefined */ - u8 pipe_mask; - u8 cpu_transcoder_mask; - - u8 abox_mask; - #define DEFINE_FLAG(name) u8 name:1 DEV_INFO_FOR_EACH_FLAG(DEFINE_FLAG); #undef DEFINE_FLAG struct { u8 ver; + u8 rel; + + u8 pipe_mask; + u8 cpu_transcoder_mask; + u8 abox_mask; #define DEFINE_FLAG(name) u8 name:1 DEV_INFO_DISPLAY_FOR_EACH_FLAG(DEFINE_FLAG); diff --git a/drivers/gpu/drm/i915/intel_gvt.c b/drivers/gpu/drm/i915/intel_gvt.c index 4e70c1a9ef2e..cf6e98962d82 100644 --- a/drivers/gpu/drm/i915/intel_gvt.c +++ b/drivers/gpu/drm/i915/intel_gvt.c @@ -109,7 +109,7 @@ int intel_gvt_init(struct drm_i915_private *dev_priv) return 0; } - if (intel_uc_wants_guc_submission(&dev_priv->gt.uc)) { + if (intel_uc_wants_guc_submission(&to_gt(dev_priv)->uc)) { drm_err(&dev_priv->drm, "i915 GVT-g loading failed due to Graphics virtualization is not yet supported with GuC submission\n"); return -EIO; diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c index e7f7e6627750..c70d7e286a51 100644 --- a/drivers/gpu/drm/i915/intel_memory_region.c +++ b/drivers/gpu/drm/i915/intel_memory_region.c @@ -3,6 +3,8 @@ * Copyright © 2019 Intel Corporation */ +#include <linux/prandom.h> + #include "intel_memory_region.h" #include "i915_drv.h" #include "i915_ttm_buddy_manager.h" @@ -29,6 +31,110 @@ static const struct { }, }; +static int __iopagetest(struct intel_memory_region *mem, + u8 __iomem *va, int pagesize, + u8 value, resource_size_t offset, + const void *caller) +{ + int byte = prandom_u32_max(pagesize); + u8 result[3]; + + memset_io(va, value, pagesize); /* or GPF! */ + wmb(); + + result[0] = ioread8(va); + result[1] = ioread8(va + byte); + result[2] = ioread8(va + pagesize - 1); + if (memchr_inv(result, value, sizeof(result))) { + dev_err(mem->i915->drm.dev, + "Failed to read back from memory region:%pR at [%pa + %pa] for %ps; wrote %x, read (%x, %x, %x)\n", + &mem->region, &mem->io_start, &offset, caller, + value, result[0], result[1], result[2]); + return -EINVAL; + } + + return 0; +} + +static int iopagetest(struct intel_memory_region *mem, + resource_size_t offset, + const void *caller) +{ + const u8 val[] = { 0x0, 0xa5, 0xc3, 0xf0 }; + void __iomem *va; + int err; + int i; + + va = ioremap_wc(mem->io_start + offset, PAGE_SIZE); + if (!va) { + dev_err(mem->i915->drm.dev, + "Failed to ioremap memory region [%pa + %pa] for %ps\n", + &mem->io_start, &offset, caller); + return -EFAULT; + } + + for (i = 0; i < ARRAY_SIZE(val); i++) { + err = __iopagetest(mem, va, PAGE_SIZE, val[i], offset, caller); + if (err) + break; + + err = __iopagetest(mem, va, PAGE_SIZE, ~val[i], offset, caller); + if (err) + break; + } + + iounmap(va); + return err; +} + +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; +} + +static int iomemtest(struct intel_memory_region *mem, + bool test_all, + const void *caller) +{ + resource_size_t last = resource_size(&mem->region) - PAGE_SIZE; + resource_size_t page; + int err; + + /* + * Quick test to check read/write access to the iomap (backing store). + * + * Write a byte, read it back. If the iomapping fails, we expect + * a GPF preventing further execution. If the backing store does not + * exist, the read back will return garbage. We check a couple of pages, + * the first and last of the specified region to confirm the backing + * store + iomap does cover the entire memory region; and we check + * a random offset within as a quick spot check for bad memory. + */ + + if (test_all) { + for (page = 0; page <= last; page += PAGE_SIZE) { + err = iopagetest(mem, page, caller); + if (err) + return err; + } + } else { + err = iopagetest(mem, 0, caller); + if (err) + return err; + + err = iopagetest(mem, last, caller); + if (err) + return err; + + err = iopagetest(mem, random_page(last), caller); + if (err) + return err; + } + + return 0; +} + struct intel_memory_region * intel_memory_region_lookup(struct drm_i915_private *i915, u16 class, u16 instance) @@ -90,6 +196,21 @@ void intel_memory_region_debug(struct intel_memory_region *mr, &mr->total, &mr->avail); } +static int intel_memory_region_memtest(struct intel_memory_region *mem, + void *caller) +{ + struct drm_i915_private *i915 = mem->i915; + int err = 0; + + if (!mem->io_start) + return 0; + + if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM) || i915->params.memtest) + err = iomemtest(mem, i915->params.memtest, caller); + + return err; +} + struct intel_memory_region * intel_memory_region_create(struct drm_i915_private *i915, resource_size_t start, @@ -126,9 +247,15 @@ intel_memory_region_create(struct drm_i915_private *i915, goto err_free; } - kref_init(&mem->kref); + err = intel_memory_region_memtest(mem, (void *)_RET_IP_); + if (err) + goto err_release; + return mem; +err_release: + if (mem->ops->release) + mem->ops->release(mem); err_free: kfree(mem); return ERR_PTR(err); @@ -144,28 +271,17 @@ void intel_memory_region_set_name(struct intel_memory_region *mem, va_end(ap); } -static void __intel_memory_region_destroy(struct kref *kref) +void intel_memory_region_destroy(struct intel_memory_region *mem) { - struct intel_memory_region *mem = - container_of(kref, typeof(*mem), kref); + int ret = 0; if (mem->ops->release) - mem->ops->release(mem); + ret = mem->ops->release(mem); + GEM_WARN_ON(!list_empty_careful(&mem->objects.list)); mutex_destroy(&mem->objects.lock); - kfree(mem); -} - -struct intel_memory_region * -intel_memory_region_get(struct intel_memory_region *mem) -{ - kref_get(&mem->kref); - return mem; -} - -void intel_memory_region_put(struct intel_memory_region *mem) -{ - kref_put(&mem->kref, __intel_memory_region_destroy); + if (!ret) + kfree(mem); } /* Global memory region registration -- only slight layer inversions! */ @@ -234,7 +350,7 @@ void intel_memory_regions_driver_release(struct drm_i915_private *i915) fetch_and_zero(&i915->mm.regions[i]); if (region) - intel_memory_region_put(region); + intel_memory_region_destroy(region); } } diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h index 3feae3353d33..5625c9c38993 100644 --- a/drivers/gpu/drm/i915/intel_memory_region.h +++ b/drivers/gpu/drm/i915/intel_memory_region.h @@ -6,7 +6,6 @@ #ifndef __INTEL_MEMORY_REGION_H__ #define __INTEL_MEMORY_REGION_H__ -#include <linux/kref.h> #include <linux/ioport.h> #include <linux/mutex.h> #include <linux/io-mapping.h> @@ -51,7 +50,7 @@ struct intel_memory_region_ops { unsigned int flags; int (*init)(struct intel_memory_region *mem); - void (*release)(struct intel_memory_region *mem); + int (*release)(struct intel_memory_region *mem); int (*init_object)(struct intel_memory_region *mem, struct drm_i915_gem_object *obj, @@ -71,8 +70,6 @@ struct intel_memory_region { /* For fake LMEM */ struct drm_mm_node fake_mappable; - struct kref kref; - resource_size_t io_start; resource_size_t min_page_size; resource_size_t total; @@ -110,9 +107,7 @@ intel_memory_region_create(struct drm_i915_private *i915, u16 instance, const struct intel_memory_region_ops *ops); -struct intel_memory_region * -intel_memory_region_get(struct intel_memory_region *mem); -void intel_memory_region_put(struct intel_memory_region *mem); +void intel_memory_region_destroy(struct intel_memory_region *mem); int intel_memory_regions_hw_probe(struct drm_i915_private *i915); void intel_memory_regions_driver_release(struct drm_i915_private *i915); diff --git a/drivers/gpu/drm/i915/intel_pch.c b/drivers/gpu/drm/i915/intel_pch.c index d1d4b97b86f5..da8f82c2342f 100644 --- a/drivers/gpu/drm/i915/intel_pch.c +++ b/drivers/gpu/drm/i915/intel_pch.c @@ -129,6 +129,7 @@ intel_pch_type(const struct drm_i915_private *dev_priv, unsigned short id) return PCH_JSP; case INTEL_PCH_ADP_DEVICE_ID_TYPE: case INTEL_PCH_ADP2_DEVICE_ID_TYPE: + case INTEL_PCH_ADP3_DEVICE_ID_TYPE: drm_dbg_kms(&dev_priv->drm, "Found Alder Lake PCH\n"); drm_WARN_ON(&dev_priv->drm, !IS_ALDERLAKE_S(dev_priv) && !IS_ALDERLAKE_P(dev_priv)); diff --git a/drivers/gpu/drm/i915/intel_pch.h b/drivers/gpu/drm/i915/intel_pch.h index 7c0d83d292dc..6bff77521094 100644 --- a/drivers/gpu/drm/i915/intel_pch.h +++ b/drivers/gpu/drm/i915/intel_pch.h @@ -57,6 +57,7 @@ enum intel_pch { #define INTEL_PCH_JSP2_DEVICE_ID_TYPE 0x3880 #define INTEL_PCH_ADP_DEVICE_ID_TYPE 0x7A80 #define INTEL_PCH_ADP2_DEVICE_ID_TYPE 0x5180 +#define INTEL_PCH_ADP3_DEVICE_ID_TYPE 0x7A00 #define INTEL_PCH_P2X_DEVICE_ID_TYPE 0x7100 #define INTEL_PCH_P3X_DEVICE_ID_TYPE 0x7000 #define INTEL_PCH_QEMU_DEVICE_ID_TYPE 0x2900 /* qemu q35 has 2918 */ diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index ecbb3d141632..434b1f8b7fe3 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -36,7 +36,9 @@ #include "display/intel_atomic_plane.h" #include "display/intel_bw.h" #include "display/intel_de.h" +#include "display/intel_display_trace.h" #include "display/intel_display_types.h" +#include "display/intel_fb.h" #include "display/intel_fbc.h" #include "display/intel_sprite.h" #include "display/skl_universal_plane.h" @@ -46,7 +48,6 @@ #include "i915_drv.h" #include "i915_fixed.h" #include "i915_irq.h" -#include "i915_trace.h" #include "intel_pcode.h" #include "intel_pm.h" #include "vlv_sideband.h" @@ -97,7 +98,7 @@ static void gen9_init_clock_gating(struct drm_i915_private *dev_priv) * "Plane N strech max must be programmed to 11b (x1) * when Async flips are enabled on that plane." */ - if (!IS_GEMINILAKE(dev_priv) && intel_vtd_active()) + if (!IS_GEMINILAKE(dev_priv) && intel_vtd_active(dev_priv)) intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe), SKL_PLANE1_STRETCH_MAX_MASK, SKL_PLANE1_STRETCH_MAX_X1); } @@ -160,7 +161,7 @@ static void bxt_init_clock_gating(struct drm_i915_private *dev_priv) * Display WA #0883: bxt */ intel_uncore_write(&dev_priv->uncore, ILK_DPFC_CHICKEN, intel_uncore_read(&dev_priv->uncore, ILK_DPFC_CHICKEN) | - ILK_DPFC_DISABLE_DUMMY0); + DPFC_DISABLE_DUMMY0); } static void glk_init_clock_gating(struct drm_i915_private *dev_priv) @@ -988,7 +989,7 @@ static void g4x_write_wm_values(struct drm_i915_private *dev_priv, enum pipe pipe; for_each_pipe(dev_priv, pipe) - trace_g4x_wm(intel_get_crtc_for_pipe(dev_priv, pipe), wm); + trace_g4x_wm(intel_crtc_for_pipe(dev_priv, pipe), wm); intel_uncore_write(&dev_priv->uncore, DSPFW1, FW_WM(wm->sr.plane, SR) | @@ -1020,7 +1021,7 @@ static void vlv_write_wm_values(struct drm_i915_private *dev_priv, enum pipe pipe; for_each_pipe(dev_priv, pipe) { - trace_vlv_wm(intel_get_crtc_for_pipe(dev_priv, pipe), wm); + trace_vlv_wm(intel_crtc_for_pipe(dev_priv, pipe), wm); intel_uncore_write(&dev_priv->uncore, VLV_DDL(pipe), (wm->ddl[pipe].plane[PLANE_CURSOR] << DDL_CURSOR_SHIFT) | @@ -2335,6 +2336,20 @@ static void i965_update_wm(struct drm_i915_private *dev_priv) #undef FW_WM +static struct intel_crtc *intel_crtc_for_plane(struct drm_i915_private *i915, + enum i9xx_plane_id i9xx_plane) +{ + struct intel_plane *plane; + + for_each_intel_plane(&i915->drm, plane) { + if (plane->id == PLANE_PRIMARY && + plane->i9xx_plane == i9xx_plane) + return intel_crtc_for_pipe(i915, plane->pipe); + } + + return NULL; +} + static void i9xx_update_wm(struct drm_i915_private *dev_priv) { const struct intel_watermark_params *wm_info; @@ -2356,7 +2371,7 @@ static void i9xx_update_wm(struct drm_i915_private *dev_priv) fifo_size = i830_get_fifo_size(dev_priv, PLANE_A); else fifo_size = i9xx_get_fifo_size(dev_priv, PLANE_A); - crtc = intel_get_crtc_for_plane(dev_priv, PLANE_A); + crtc = intel_crtc_for_plane(dev_priv, PLANE_A); if (intel_crtc_active(crtc)) { const struct drm_display_mode *pipe_mode = &crtc->config->hw.pipe_mode; @@ -2386,7 +2401,7 @@ static void i9xx_update_wm(struct drm_i915_private *dev_priv) fifo_size = i830_get_fifo_size(dev_priv, PLANE_B); else fifo_size = i9xx_get_fifo_size(dev_priv, PLANE_B); - crtc = intel_get_crtc_for_plane(dev_priv, PLANE_B); + crtc = intel_crtc_for_plane(dev_priv, PLANE_B); if (intel_crtc_active(crtc)) { const struct drm_display_mode *pipe_mode = &crtc->config->hw.pipe_mode; @@ -3062,9 +3077,9 @@ static void snb_wm_latency_quirk(struct drm_i915_private *dev_priv) * The BIOS provided WM memory latency values are often * inadequate for high resolution displays. Adjust them. */ - changed = ilk_increase_wm_latency(dev_priv, dev_priv->wm.pri_latency, 12) | - ilk_increase_wm_latency(dev_priv, dev_priv->wm.spr_latency, 12) | - ilk_increase_wm_latency(dev_priv, dev_priv->wm.cur_latency, 12); + changed = ilk_increase_wm_latency(dev_priv, dev_priv->wm.pri_latency, 12); + changed |= ilk_increase_wm_latency(dev_priv, dev_priv->wm.spr_latency, 12); + changed |= ilk_increase_wm_latency(dev_priv, dev_priv->wm.cur_latency, 12); if (!changed) return; @@ -3368,13 +3383,8 @@ static void ilk_wm_merge(struct drm_i915_private *dev_priv, } /* ILK: LP2+ must be disabled when FBC WM is disabled but FBC enabled */ - /* - * FIXME this is racy. FBC might get enabled later. - * What we should check here is whether FBC can be - * enabled sometime later. - */ - if (DISPLAY_VER(dev_priv) == 5 && !merged->fbc_wm_enabled && - intel_fbc_is_active(dev_priv)) { + if (DISPLAY_VER(dev_priv) == 5 && HAS_FBC(dev_priv) && + dev_priv->params.enable_fbc && !merged->fbc_wm_enabled) { for (level = 2; level <= max_level; level++) { struct intel_wm_level *wm = &merged->wm[level]; @@ -5094,6 +5104,18 @@ skl_check_nv12_wm_level(struct skl_wm_level *wm, struct skl_wm_level *uv_wm, } } +static bool icl_need_wm1_wa(struct drm_i915_private *i915, + enum plane_id plane_id) +{ + /* + * Wa_1408961008:icl, ehl + * Wa_14012656716:tgl, adl + * Underruns with WM1+ disabled + */ + return DISPLAY_VER(i915) == 11 || + (IS_DISPLAY_VER(i915, 12, 13) && plane_id == PLANE_CURSOR); +} + static int skl_allocate_plane_ddb(struct intel_atomic_state *state, struct intel_crtc *crtc) @@ -5264,11 +5286,7 @@ skl_allocate_plane_ddb(struct intel_atomic_state *state, skl_check_nv12_wm_level(&wm->wm[level], &wm->uv_wm[level], total[plane_id], uv_total[plane_id]); - /* - * Wa_1408961008:icl, ehl - * Underruns with WM1+ disabled - */ - if (DISPLAY_VER(dev_priv) == 11 && + if (icl_need_wm1_wa(dev_priv, plane_id) && level == 1 && wm->wm[0].enable) { wm->wm[level].blocks = wm->wm[0].blocks; wm->wm[level].lines = wm->wm[0].lines; @@ -6900,7 +6918,7 @@ void g4x_wm_sanitize(struct drm_i915_private *dev_priv) for_each_intel_plane(&dev_priv->drm, plane) { struct intel_crtc *crtc = - intel_get_crtc_for_pipe(dev_priv, plane->pipe); + intel_crtc_for_pipe(dev_priv, plane->pipe); struct intel_crtc_state *crtc_state = to_intel_crtc_state(crtc->base.state); struct intel_plane_state *plane_state = @@ -7056,7 +7074,7 @@ void vlv_wm_sanitize(struct drm_i915_private *dev_priv) for_each_intel_plane(&dev_priv->drm, plane) { struct intel_crtc *crtc = - intel_get_crtc_for_pipe(dev_priv, plane->pipe); + intel_crtc_for_pipe(dev_priv, plane->pipe); struct intel_crtc_state *crtc_state = to_intel_crtc_state(crtc->base.state); struct intel_plane_state *plane_state = @@ -7434,7 +7452,7 @@ static void icl_init_clock_gating(struct drm_i915_private *dev_priv) { /* Wa_1409120013:icl,ehl */ intel_uncore_write(&dev_priv->uncore, ILK_DPFC_CHICKEN, - ILK_DPFC_CHICKEN_COMP_DUMMY_PIXEL); + DPFC_CHICKEN_COMP_DUMMY_PIXEL); /*Wa_14010594013:icl, ehl */ intel_uncore_rmw(&dev_priv->uncore, GEN8_CHICKEN_DCPR_1, @@ -7443,11 +7461,11 @@ static void icl_init_clock_gating(struct drm_i915_private *dev_priv) static void gen12lp_init_clock_gating(struct drm_i915_private *dev_priv) { - /* Wa_1409120013:tgl,rkl,adl-s,dg1 */ + /* Wa_1409120013:tgl,rkl,adl-s,dg1,dg2 */ if (IS_TIGERLAKE(dev_priv) || IS_ROCKETLAKE(dev_priv) || - IS_ALDERLAKE_S(dev_priv) || IS_DG1(dev_priv)) + IS_ALDERLAKE_S(dev_priv) || IS_DG1(dev_priv) || IS_DG2(dev_priv)) intel_uncore_write(&dev_priv->uncore, ILK_DPFC_CHICKEN, - ILK_DPFC_CHICKEN_COMP_DUMMY_PIXEL); + DPFC_CHICKEN_COMP_DUMMY_PIXEL); /* Wa_1409825376:tgl (pre-prod)*/ if (IS_TGL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_C0)) @@ -7473,11 +7491,34 @@ static void dg1_init_clock_gating(struct drm_i915_private *dev_priv) gen12lp_init_clock_gating(dev_priv); /* Wa_1409836686:dg1[a0] */ - if (IS_DG1_GT_STEP(dev_priv, STEP_A0, STEP_B0)) + 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); } +static void xehpsdv_init_clock_gating(struct drm_i915_private *dev_priv) +{ + /* Wa_22010146351:xehpsdv */ + if (IS_XEHPSDV_GRAPHICS_STEP(dev_priv, STEP_A0, STEP_B0)) + intel_uncore_rmw(&dev_priv->uncore, XEHP_CLOCK_GATE_DIS, 0, SGR_DIS); +} + +static void dg2_init_clock_gating(struct drm_i915_private *i915) +{ + /* Wa_22010954014:dg2_g10 */ + if (IS_DG2_G10(i915)) + intel_uncore_rmw(&i915->uncore, XEHP_CLOCK_GATE_DIS, 0, + SGSI_SIDECLK_DIS); + + /* + * Wa_14010733611:dg2_g10 + * Wa_22010146351:dg2_g10 + */ + if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) + intel_uncore_rmw(&i915->uncore, XEHP_CLOCK_GATE_DIS, 0, + SGR_DIS | SGGI_DIS); +} + static void cnp_init_clock_gating(struct drm_i915_private *dev_priv) { if (!HAS_PCH_CNP(dev_priv)) @@ -7509,7 +7550,7 @@ static void cfl_init_clock_gating(struct drm_i915_private *dev_priv) * Display WA #0873: cfl */ intel_uncore_write(&dev_priv->uncore, ILK_DPFC_CHICKEN, intel_uncore_read(&dev_priv->uncore, ILK_DPFC_CHICKEN) | - ILK_DPFC_NUKE_ON_ANY_MODIFICATION); + DPFC_NUKE_ON_ANY_MODIFICATION); } static void kbl_init_clock_gating(struct drm_i915_private *dev_priv) @@ -7521,12 +7562,12 @@ static void kbl_init_clock_gating(struct drm_i915_private *dev_priv) FBC_LLC_FULLY_OPEN); /* WaDisableSDEUnitClockGating:kbl */ - if (IS_KBL_GT_STEP(dev_priv, 0, STEP_C0)) + 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); /* WaDisableGamClockGating:kbl */ - if (IS_KBL_GT_STEP(dev_priv, 0, STEP_C0)) + 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); @@ -7542,7 +7583,7 @@ static void kbl_init_clock_gating(struct drm_i915_private *dev_priv) * Display WA #0873: kbl */ intel_uncore_write(&dev_priv->uncore, ILK_DPFC_CHICKEN, intel_uncore_read(&dev_priv->uncore, ILK_DPFC_CHICKEN) | - ILK_DPFC_NUKE_ON_ANY_MODIFICATION); + DPFC_NUKE_ON_ANY_MODIFICATION); } static void skl_init_clock_gating(struct drm_i915_private *dev_priv) @@ -7569,14 +7610,14 @@ static void skl_init_clock_gating(struct drm_i915_private *dev_priv) * Display WA #0873: skl */ intel_uncore_write(&dev_priv->uncore, ILK_DPFC_CHICKEN, intel_uncore_read(&dev_priv->uncore, ILK_DPFC_CHICKEN) | - ILK_DPFC_NUKE_ON_ANY_MODIFICATION); + DPFC_NUKE_ON_ANY_MODIFICATION); /* * WaFbcHighMemBwCorruptionAvoidance:skl * Display WA #0883: skl */ intel_uncore_write(&dev_priv->uncore, ILK_DPFC_CHICKEN, intel_uncore_read(&dev_priv->uncore, ILK_DPFC_CHICKEN) | - ILK_DPFC_DISABLE_DUMMY0); + DPFC_DISABLE_DUMMY0); } static void bdw_init_clock_gating(struct drm_i915_private *dev_priv) @@ -7888,6 +7929,8 @@ static const struct drm_i915_clock_gating_funcs platform##_clock_gating_funcs = .init_clock_gating = platform##_init_clock_gating, \ } +CG_FUNCS(dg2); +CG_FUNCS(xehpsdv); CG_FUNCS(adlp); CG_FUNCS(dg1); CG_FUNCS(gen12lp); @@ -7924,7 +7967,11 @@ CG_FUNCS(nop); */ void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv) { - if (IS_ALDERLAKE_P(dev_priv)) + if (IS_DG2(dev_priv)) + dev_priv->clock_gating_funcs = &dg2_clock_gating_funcs; + else if (IS_XEHPSDV(dev_priv)) + dev_priv->clock_gating_funcs = &xehpsdv_clock_gating_funcs; + else if (IS_ALDERLAKE_P(dev_priv)) dev_priv->clock_gating_funcs = &adlp_clock_gating_funcs; else if (IS_DG1(dev_priv)) dev_priv->clock_gating_funcs = &dg1_clock_gating_funcs; diff --git a/drivers/gpu/drm/i915/intel_pm_types.h b/drivers/gpu/drm/i915/intel_pm_types.h new file mode 100644 index 000000000000..211632f58751 --- /dev/null +++ b/drivers/gpu/drm/i915/intel_pm_types.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef __INTEL_PM_TYPES_H__ +#define __INTEL_PM_TYPES_H__ + +#include <linux/types.h> + +#include "display/intel_display.h" + +enum intel_ddb_partitioning { + INTEL_DDB_PART_1_2, + INTEL_DDB_PART_5_6, /* IVB+ */ +}; + +struct ilk_wm_values { + u32 wm_pipe[3]; + u32 wm_lp[3]; + u32 wm_lp_spr[3]; + bool enable_fbc_wm; + enum intel_ddb_partitioning partitioning; +}; + +struct g4x_pipe_wm { + u16 plane[I915_MAX_PLANES]; + u16 fbc; +}; + +struct g4x_sr_wm { + u16 plane; + u16 cursor; + u16 fbc; +}; + +struct vlv_wm_ddl_values { + u8 plane[I915_MAX_PLANES]; +}; + +struct vlv_wm_values { + struct g4x_pipe_wm pipe[3]; + struct g4x_sr_wm sr; + struct vlv_wm_ddl_values ddl[3]; + u8 level; + bool cxsr; +}; + +struct g4x_wm_values { + struct g4x_pipe_wm pipe[2]; + struct g4x_sr_wm sr; + struct g4x_sr_wm hpll; + bool cxsr; + bool hpll_en; + bool fbc_en; +}; + +struct skl_ddb_entry { + u16 start, end; /* in number of blocks, 'end' is exclusive */ +}; + +static inline u16 skl_ddb_entry_size(const struct skl_ddb_entry *entry) +{ + return entry->end - entry->start; +} + +static inline bool skl_ddb_entry_equal(const struct skl_ddb_entry *e1, + const struct skl_ddb_entry *e2) +{ + if (e1->start == e2->start && e1->end == e2->end) + return true; + + return false; +} + +#endif /* __INTEL_PM_TYPES_H__ */ diff --git a/drivers/gpu/drm/i915/intel_region_ttm.c b/drivers/gpu/drm/i915/intel_region_ttm.c index 98c7339bf8ba..f2b888c16958 100644 --- a/drivers/gpu/drm/i915/intel_region_ttm.c +++ b/drivers/gpu/drm/i915/intel_region_ttm.c @@ -104,19 +104,50 @@ int intel_region_ttm_init(struct intel_memory_region *mem) * memory region, and if it was registered with the TTM device, * removes that registration. */ -void intel_region_ttm_fini(struct intel_memory_region *mem) +int intel_region_ttm_fini(struct intel_memory_region *mem) { - int ret; + struct ttm_resource_manager *man = mem->region_private; + int ret = -EBUSY; + int count; + + /* + * Put the region's move fences. This releases requests that + * may hold on to contexts and vms that may hold on to buffer + * objects placed in this region. + */ + if (man) + ttm_resource_manager_cleanup(man); + + /* Flush objects from region. */ + for (count = 0; count < 10; ++count) { + i915_gem_flush_free_objects(mem->i915); + + mutex_lock(&mem->objects.lock); + if (list_empty(&mem->objects.list)) + ret = 0; + mutex_unlock(&mem->objects.lock); + if (!ret) + break; + + msleep(20); + flush_delayed_work(&mem->i915->bdev.wq); + } + + /* If we leaked objects, Don't free the region causing use after free */ + if (ret || !man) + return ret; ret = i915_ttm_buddy_man_fini(&mem->i915->bdev, intel_region_to_ttm_type(mem)); GEM_WARN_ON(ret); mem->region_private = NULL; + + return ret; } /** - * intel_region_ttm_resource_to_st - Convert an opaque TTM resource manager resource - * to an sg_table. + * intel_region_ttm_resource_to_rsgt - + * Convert an opaque TTM resource manager resource to a refcounted sg_table. * @mem: The memory region. * @res: The resource manager resource obtained from the TTM resource manager. * @@ -126,17 +157,18 @@ void intel_region_ttm_fini(struct intel_memory_region *mem) * * Return: A malloced sg_table on success, an error pointer on failure. */ -struct sg_table *intel_region_ttm_resource_to_st(struct intel_memory_region *mem, - struct ttm_resource *res) +struct i915_refct_sgt * +intel_region_ttm_resource_to_rsgt(struct intel_memory_region *mem, + struct ttm_resource *res) { if (mem->is_range_manager) { struct ttm_range_mgr_node *range_node = to_ttm_range_mgr_node(res); - return i915_sg_from_mm_node(&range_node->mm_nodes[0], - mem->region.start); + return i915_rsgt_from_mm_node(&range_node->mm_nodes[0], + mem->region.start); } else { - return i915_sg_from_buddy_resource(res, mem->region.start); + return i915_rsgt_from_buddy_resource(res, mem->region.start); } } diff --git a/drivers/gpu/drm/i915/intel_region_ttm.h b/drivers/gpu/drm/i915/intel_region_ttm.h index 6f44075920f2..fdee5e7bd46c 100644 --- a/drivers/gpu/drm/i915/intel_region_ttm.h +++ b/drivers/gpu/drm/i915/intel_region_ttm.h @@ -20,10 +20,11 @@ void intel_region_ttm_device_fini(struct drm_i915_private *dev_priv); int intel_region_ttm_init(struct intel_memory_region *mem); -void intel_region_ttm_fini(struct intel_memory_region *mem); +int intel_region_ttm_fini(struct intel_memory_region *mem); -struct sg_table *intel_region_ttm_resource_to_st(struct intel_memory_region *mem, - struct ttm_resource *res); +struct i915_refct_sgt * +intel_region_ttm_resource_to_rsgt(struct intel_memory_region *mem, + struct ttm_resource *res); void intel_region_ttm_resource_free(struct intel_memory_region *mem, struct ttm_resource *res); diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index 0d85f3c5c526..22dab36afcb6 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -590,6 +590,9 @@ void intel_runtime_pm_enable(struct intel_runtime_pm *rpm) pm_runtime_use_autosuspend(kdev); } + /* Enable by default */ + pm_runtime_allow(kdev); + /* * The core calls the driver load handler with an RPM reference held. * We drop that here and will reacquire it during unloading in diff --git a/drivers/gpu/drm/i915/intel_step.c b/drivers/gpu/drm/i915/intel_step.c index 6cf967631395..a4b16b9e2e55 100644 --- a/drivers/gpu/drm/i915/intel_step.c +++ b/drivers/gpu/drm/i915/intel_step.c @@ -23,7 +23,8 @@ * use a macro to define these to make it easier to identify the platforms * where the two steppings can deviate. */ -#define COMMON_STEP(x) .gt_step = STEP_##x, .display_step = STEP_##x +#define COMMON_STEP(x) .graphics_step = STEP_##x, .display_step = STEP_##x, .media_step = STEP_##x +#define COMMON_GT_MEDIA_STEP(x) .graphics_step = STEP_##x, .media_step = STEP_##x static const struct intel_step_info skl_revids[] = { [0x6] = { COMMON_STEP(G0) }, @@ -33,13 +34,13 @@ static const struct intel_step_info skl_revids[] = { }; static const struct intel_step_info kbl_revids[] = { - [1] = { .gt_step = STEP_B0, .display_step = STEP_B0 }, - [2] = { .gt_step = STEP_C0, .display_step = STEP_B0 }, - [3] = { .gt_step = STEP_D0, .display_step = STEP_B0 }, - [4] = { .gt_step = STEP_F0, .display_step = STEP_C0 }, - [5] = { .gt_step = STEP_C0, .display_step = STEP_B1 }, - [6] = { .gt_step = STEP_D1, .display_step = STEP_B1 }, - [7] = { .gt_step = STEP_G0, .display_step = STEP_C0 }, + [1] = { COMMON_GT_MEDIA_STEP(B0), .display_step = STEP_B0 }, + [2] = { COMMON_GT_MEDIA_STEP(C0), .display_step = STEP_B0 }, + [3] = { COMMON_GT_MEDIA_STEP(D0), .display_step = STEP_B0 }, + [4] = { COMMON_GT_MEDIA_STEP(F0), .display_step = STEP_C0 }, + [5] = { COMMON_GT_MEDIA_STEP(C0), .display_step = STEP_B1 }, + [6] = { COMMON_GT_MEDIA_STEP(D1), .display_step = STEP_B1 }, + [7] = { COMMON_GT_MEDIA_STEP(G0), .display_step = STEP_C0 }, }; static const struct intel_step_info bxt_revids[] = { @@ -63,16 +64,16 @@ static const struct intel_step_info jsl_ehl_revids[] = { }; static const struct intel_step_info tgl_uy_revids[] = { - [0] = { .gt_step = STEP_A0, .display_step = STEP_A0 }, - [1] = { .gt_step = STEP_B0, .display_step = STEP_C0 }, - [2] = { .gt_step = STEP_B1, .display_step = STEP_C0 }, - [3] = { .gt_step = STEP_C0, .display_step = STEP_D0 }, + [0] = { COMMON_GT_MEDIA_STEP(A0), .display_step = STEP_A0 }, + [1] = { COMMON_GT_MEDIA_STEP(B0), .display_step = STEP_C0 }, + [2] = { COMMON_GT_MEDIA_STEP(B1), .display_step = STEP_C0 }, + [3] = { COMMON_GT_MEDIA_STEP(C0), .display_step = STEP_D0 }, }; /* Same GT stepping between tgl_uy_revids and tgl_revids don't mean the same HW */ static const struct intel_step_info tgl_revids[] = { - [0] = { .gt_step = STEP_A0, .display_step = STEP_B0 }, - [1] = { .gt_step = STEP_B0, .display_step = STEP_D0 }, + [0] = { COMMON_GT_MEDIA_STEP(A0), .display_step = STEP_B0 }, + [1] = { COMMON_GT_MEDIA_STEP(B0), .display_step = STEP_D0 }, }; static const struct intel_step_info rkl_revids[] = { @@ -87,38 +88,38 @@ static const struct intel_step_info dg1_revids[] = { }; static const struct intel_step_info adls_revids[] = { - [0x0] = { .gt_step = STEP_A0, .display_step = STEP_A0 }, - [0x1] = { .gt_step = STEP_A0, .display_step = STEP_A2 }, - [0x4] = { .gt_step = STEP_B0, .display_step = STEP_B0 }, - [0x8] = { .gt_step = STEP_C0, .display_step = STEP_B0 }, - [0xC] = { .gt_step = STEP_D0, .display_step = STEP_C0 }, + [0x0] = { COMMON_GT_MEDIA_STEP(A0), .display_step = STEP_A0 }, + [0x1] = { COMMON_GT_MEDIA_STEP(A0), .display_step = STEP_A2 }, + [0x4] = { COMMON_GT_MEDIA_STEP(B0), .display_step = STEP_B0 }, + [0x8] = { COMMON_GT_MEDIA_STEP(C0), .display_step = STEP_B0 }, + [0xC] = { COMMON_GT_MEDIA_STEP(D0), .display_step = STEP_C0 }, }; static const struct intel_step_info adlp_revids[] = { - [0x0] = { .gt_step = STEP_A0, .display_step = STEP_A0 }, - [0x4] = { .gt_step = STEP_B0, .display_step = STEP_B0 }, - [0x8] = { .gt_step = STEP_C0, .display_step = STEP_C0 }, - [0xC] = { .gt_step = STEP_C0, .display_step = STEP_D0 }, + [0x0] = { COMMON_GT_MEDIA_STEP(A0), .display_step = STEP_A0 }, + [0x4] = { COMMON_GT_MEDIA_STEP(B0), .display_step = STEP_B0 }, + [0x8] = { COMMON_GT_MEDIA_STEP(C0), .display_step = STEP_C0 }, + [0xC] = { COMMON_GT_MEDIA_STEP(C0), .display_step = STEP_D0 }, }; static const struct intel_step_info xehpsdv_revids[] = { - [0x0] = { .gt_step = STEP_A0 }, - [0x1] = { .gt_step = STEP_A1 }, - [0x4] = { .gt_step = STEP_B0 }, - [0x8] = { .gt_step = STEP_C0 }, + [0x0] = { COMMON_GT_MEDIA_STEP(A0) }, + [0x1] = { COMMON_GT_MEDIA_STEP(A1) }, + [0x4] = { COMMON_GT_MEDIA_STEP(B0) }, + [0x8] = { COMMON_GT_MEDIA_STEP(C0) }, }; static const struct intel_step_info dg2_g10_revid_step_tbl[] = { - [0x0] = { .gt_step = STEP_A0, .display_step = STEP_A0 }, - [0x1] = { .gt_step = STEP_A1, .display_step = STEP_A0 }, - [0x4] = { .gt_step = STEP_B0, .display_step = STEP_B0 }, - [0x8] = { .gt_step = STEP_C0, .display_step = STEP_C0 }, + [0x0] = { COMMON_GT_MEDIA_STEP(A0), .display_step = STEP_A0 }, + [0x1] = { COMMON_GT_MEDIA_STEP(A1), .display_step = STEP_A0 }, + [0x4] = { COMMON_GT_MEDIA_STEP(B0), .display_step = STEP_B0 }, + [0x8] = { COMMON_GT_MEDIA_STEP(C0), .display_step = STEP_C0 }, }; static const struct intel_step_info dg2_g11_revid_step_tbl[] = { - [0x0] = { .gt_step = STEP_A0, .display_step = STEP_B0 }, - [0x4] = { .gt_step = STEP_B0, .display_step = STEP_C0 }, - [0x5] = { .gt_step = STEP_B1, .display_step = STEP_C0 }, + [0x0] = { COMMON_GT_MEDIA_STEP(A0), .display_step = STEP_B0 }, + [0x4] = { COMMON_GT_MEDIA_STEP(B0), .display_step = STEP_C0 }, + [0x5] = { COMMON_GT_MEDIA_STEP(B1), .display_step = STEP_C0 }, }; void intel_step_init(struct drm_i915_private *i915) @@ -179,7 +180,7 @@ void intel_step_init(struct drm_i915_private *i915) if (!revids) return; - if (revid < size && revids[revid].gt_step != STEP_NONE) { + if (revid < size && revids[revid].graphics_step != STEP_NONE) { step = revids[revid]; } else { drm_warn(&i915->drm, "Unknown revid 0x%02x\n", revid); @@ -192,7 +193,7 @@ void intel_step_init(struct drm_i915_private *i915) * steppings in the array are not monotonically increasing, but * it's better than defaulting to 0. */ - while (revid < size && revids[revid].gt_step == STEP_NONE) + while (revid < size && revids[revid].graphics_step == STEP_NONE) revid++; if (revid < size) { @@ -201,12 +202,12 @@ void intel_step_init(struct drm_i915_private *i915) step = revids[revid]; } else { drm_dbg(&i915->drm, "Using future steppings\n"); - step.gt_step = STEP_FUTURE; + step.graphics_step = STEP_FUTURE; step.display_step = STEP_FUTURE; } } - if (drm_WARN_ON(&i915->drm, step.gt_step == STEP_NONE)) + if (drm_WARN_ON(&i915->drm, step.graphics_step == STEP_NONE)) return; RUNTIME_INFO(i915)->step = step; diff --git a/drivers/gpu/drm/i915/intel_step.h b/drivers/gpu/drm/i915/intel_step.h index f6641e2a3c77..d71a99bd5179 100644 --- a/drivers/gpu/drm/i915/intel_step.h +++ b/drivers/gpu/drm/i915/intel_step.h @@ -11,8 +11,9 @@ struct drm_i915_private; struct intel_step_info { - u8 gt_step; + u8 graphics_step; u8 display_step; + u8 media_step; }; #define STEP_ENUM_VAL(name) STEP_##name, diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index e072054adac5..fc25ebf1a593 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -22,11 +22,11 @@ */ #include <linux/pm_runtime.h> -#include <asm/iosf_mbi.h> #include "gt/intel_lrc_reg.h" /* for shadow reg list */ #include "i915_drv.h" +#include "i915_iosf_mbi.h" #include "i915_trace.h" #include "i915_vgpu.h" #include "intel_pm.h" @@ -2020,7 +2020,7 @@ static int i915_pmic_bus_access_notifier(struct notifier_block *nb, return NOTIFY_OK; } -static int uncore_mmio_setup(struct intel_uncore *uncore) +int intel_uncore_setup_mmio(struct intel_uncore *uncore) { struct drm_i915_private *i915 = uncore->i915; struct pci_dev *pdev = to_pci_dev(i915->drm.dev); @@ -2053,7 +2053,7 @@ static int uncore_mmio_setup(struct intel_uncore *uncore) return 0; } -static void uncore_mmio_cleanup(struct intel_uncore *uncore) +void intel_uncore_cleanup_mmio(struct intel_uncore *uncore) { struct pci_dev *pdev = to_pci_dev(uncore->i915->drm.dev); @@ -2061,12 +2061,13 @@ static void uncore_mmio_cleanup(struct intel_uncore *uncore) } void intel_uncore_init_early(struct intel_uncore *uncore, - struct drm_i915_private *i915) + struct intel_gt *gt) { spin_lock_init(&uncore->lock); - uncore->i915 = i915; - uncore->rpm = &i915->runtime_pm; - uncore->debug = &i915->mmio_debug; + uncore->i915 = gt->i915; + uncore->gt = gt; + uncore->rpm = >->i915->runtime_pm; + uncore->debug = >->i915->mmio_debug; } static void uncore_raw_init(struct intel_uncore *uncore) @@ -2146,10 +2147,6 @@ int intel_uncore_init_mmio(struct intel_uncore *uncore) struct drm_i915_private *i915 = uncore->i915; int ret; - ret = uncore_mmio_setup(uncore); - if (ret) - return ret; - /* * The boot firmware initializes local memory and assesses its health. * If memory training fails, the punit will have been instructed to @@ -2170,7 +2167,7 @@ int intel_uncore_init_mmio(struct intel_uncore *uncore) } else { ret = uncore_forcewake_init(uncore); if (ret) - goto out_mmio_cleanup; + return ret; } /* make sure fw funcs are set if and only if we have fw*/ @@ -2192,11 +2189,6 @@ int intel_uncore_init_mmio(struct intel_uncore *uncore) drm_dbg(&i915->drm, "unclaimed mmio detected on uncore init, clearing\n"); return 0; - -out_mmio_cleanup: - uncore_mmio_cleanup(uncore); - - return ret; } /* @@ -2261,8 +2253,6 @@ void intel_uncore_fini_mmio(struct intel_uncore *uncore) intel_uncore_fw_domains_fini(uncore); iosf_mbi_punit_release(); } - - uncore_mmio_cleanup(uncore); } static const struct reg_whitelist { diff --git a/drivers/gpu/drm/i915/intel_uncore.h b/drivers/gpu/drm/i915/intel_uncore.h index 3248e4e2c540..210fe2a71612 100644 --- a/drivers/gpu/drm/i915/intel_uncore.h +++ b/drivers/gpu/drm/i915/intel_uncore.h @@ -129,6 +129,7 @@ struct intel_uncore { void __iomem *regs; struct drm_i915_private *i915; + struct intel_gt *gt; struct intel_runtime_pm *rpm; spinlock_t lock; /** lock is also taken in irq contexts. */ @@ -217,12 +218,14 @@ u32 intel_uncore_read_with_mcr_steering(struct intel_uncore *uncore, void intel_uncore_mmio_debug_init_early(struct intel_uncore_mmio_debug *mmio_debug); void intel_uncore_init_early(struct intel_uncore *uncore, - struct drm_i915_private *i915); + struct intel_gt *gt); +int intel_uncore_setup_mmio(struct intel_uncore *uncore); int intel_uncore_init_mmio(struct intel_uncore *uncore); void intel_uncore_prune_engine_fw_domains(struct intel_uncore *uncore, struct intel_gt *gt); bool intel_uncore_unclaimed_mmio(struct intel_uncore *uncore); bool intel_uncore_arm_unclaimed_mmio_detection(struct intel_uncore *uncore); +void intel_uncore_cleanup_mmio(struct intel_uncore *uncore); void intel_uncore_fini_mmio(struct intel_uncore *uncore); void intel_uncore_suspend(struct intel_uncore *uncore); void intel_uncore_resume_early(struct intel_uncore *uncore); diff --git a/drivers/gpu/drm/i915/intel_wopcm.c b/drivers/gpu/drm/i915/intel_wopcm.c index 5e511bb891f9..f06d21005106 100644 --- a/drivers/gpu/drm/i915/intel_wopcm.c +++ b/drivers/gpu/drm/i915/intel_wopcm.c @@ -220,7 +220,7 @@ static bool __wopcm_regs_locked(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 = &i915->gt; + struct intel_gt *gt = to_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); diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp.c b/drivers/gpu/drm/i915/pxp/intel_pxp.c index e2314ad9546d..15311eaed848 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp.c @@ -44,6 +44,11 @@ struct intel_gt *pxp_to_gt(const struct intel_pxp *pxp) return container_of(pxp, struct intel_gt, pxp); } +bool intel_pxp_is_enabled(const struct intel_pxp *pxp) +{ + return pxp->ce; +} + bool intel_pxp_is_active(const struct intel_pxp *pxp) { return pxp->arb_is_valid; diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp.h b/drivers/gpu/drm/i915/pxp/intel_pxp.h index aa262258d4d4..73847e535cab 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp.h @@ -6,17 +6,15 @@ #ifndef __INTEL_PXP_H__ #define __INTEL_PXP_H__ -#include "intel_pxp_types.h" +#include <linux/errno.h> +#include <linux/types.h> +struct intel_pxp; struct drm_i915_gem_object; -static inline bool intel_pxp_is_enabled(const struct intel_pxp *pxp) -{ - return pxp->ce; -} - #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); void intel_pxp_init(struct intel_pxp *pxp); @@ -48,6 +46,11 @@ 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; diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_session.c b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c index d02732f04757..598840b73dfa 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_session.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c @@ -3,7 +3,8 @@ * Copyright(c) 2020, Intel Corporation. All rights reserved. */ -#include "drm/i915_drm.h" +#include <drm/i915_drm.h> + #include "i915_drv.h" #include "intel_pxp.h" diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c index 49508f31dcb7..195b2323ec00 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c @@ -4,8 +4,10 @@ */ #include <linux/component.h> -#include "drm/i915_pxp_tee_interface.h" -#include "drm/i915_component.h" + +#include <drm/i915_pxp_tee_interface.h> +#include <drm/i915_component.h> + #include "i915_drv.h" #include "intel_pxp.h" #include "intel_pxp_session.h" @@ -14,7 +16,9 @@ static inline struct intel_pxp *i915_dev_to_pxp(struct device *i915_kdev) { - return &kdev_to_i915(i915_kdev)->gt.pxp; + struct drm_i915_private *i915 = kdev_to_i915(i915_kdev); + + return &to_gt(i915)->pxp; } static int intel_pxp_tee_io_message(struct intel_pxp *pxp, diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_types.h b/drivers/gpu/drm/i915/pxp/intel_pxp_types.h index 73ef7d1754e1..7ce5f37ee12e 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_types.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_types.h @@ -7,9 +7,7 @@ #define __INTEL_PXP_TYPES_H__ #include <linux/completion.h> -#include <linux/list.h> #include <linux/mutex.h> -#include <linux/spinlock.h> #include <linux/types.h> #include <linux/workqueue.h> diff --git a/drivers/gpu/drm/i915/selftests/i915_active.c b/drivers/gpu/drm/i915/selftests/i915_active.c index 61bf4560d8af..2dac9be1de58 100644 --- a/drivers/gpu/drm/i915/selftests/i915_active.c +++ b/drivers/gpu/drm/i915/selftests/i915_active.c @@ -254,7 +254,7 @@ int i915_active_live_selftests(struct drm_i915_private *i915) SUBTEST(live_active_barrier), }; - if (intel_gt_is_wedged(&i915->gt)) + if (intel_gt_is_wedged(to_gt(i915))) return 0; return i915_subtests(tests, i915); diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c index 152d9ab135b1..b5576888cd78 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem.c @@ -248,7 +248,7 @@ int i915_gem_live_selftests(struct drm_i915_private *i915) SUBTEST(igt_gem_ww_ctx), }; - if (intel_gt_is_wedged(&i915->gt)) + if (intel_gt_is_wedged(to_gt(i915))) return 0; return i915_live_subtests(tests, i915); diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c index f99bb0113726..75b709c26dd3 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c @@ -442,6 +442,7 @@ static int igt_evict_contexts(void *arg) /* Overfill the GGTT with context objects and so try to evict one. */ for_each_engine(engine, gt, id) { struct i915_sw_fence fence; + struct i915_request *last = NULL; count = 0; onstack_fence_init(&fence); @@ -479,6 +480,9 @@ static int igt_evict_contexts(void *arg) i915_request_add(rq); count++; + if (last) + i915_request_put(last); + last = i915_request_get(rq); err = 0; } while(1); onstack_fence_fini(&fence); @@ -486,6 +490,21 @@ static int igt_evict_contexts(void *arg) count, engine->name); if (err) break; + if (last) { + if (i915_request_wait(last, 0, HZ) < 0) { + err = -EIO; + i915_request_put(last); + pr_err("Failed waiting for last request (on %s)", + engine->name); + break; + } + i915_request_put(last); + } + err = intel_gt_wait_for_idle(engine->gt, HZ * 3); + if (err) { + pr_err("Failed to idle GT (on %s)", engine->name); + break; + } } mutex_lock(&ggtt->vm.mutex); @@ -526,7 +545,7 @@ int i915_gem_evict_mock_selftests(void) return -ENOMEM; with_intel_runtime_pm(&i915->runtime_pm, wakeref) - err = i915_subtests(tests, &i915->gt); + err = i915_subtests(tests, to_gt(i915)); mock_destroy_device(i915); return err; @@ -538,8 +557,8 @@ int i915_gem_evict_live_selftests(struct drm_i915_private *i915) SUBTEST(igt_evict_contexts), }; - if (intel_gt_is_wedged(&i915->gt)) + if (intel_gt_is_wedged(to_gt(i915))) return 0; - return intel_gt_live_subtests(tests, &i915->gt); + return intel_gt_live_subtests(tests, to_gt(i915)); } diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c index 46f4236039a9..575705c3bce9 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c @@ -155,7 +155,7 @@ static int igt_ppgtt_alloc(void *arg) if (!HAS_PPGTT(dev_priv)) return 0; - ppgtt = i915_ppgtt_create(&dev_priv->gt, 0); + ppgtt = i915_ppgtt_create(to_gt(dev_priv), 0); if (IS_ERR(ppgtt)) return PTR_ERR(ppgtt); @@ -1053,7 +1053,7 @@ static int exercise_ppgtt(struct drm_i915_private *dev_priv, if (IS_ERR(file)) return PTR_ERR(file); - ppgtt = i915_ppgtt_create(&dev_priv->gt, 0); + ppgtt = i915_ppgtt_create(to_gt(dev_priv), 0); if (IS_ERR(ppgtt)) { err = PTR_ERR(ppgtt); goto out_free; @@ -1275,7 +1275,7 @@ static void track_vma_bind(struct i915_vma *vma) __i915_gem_object_pin_pages(obj); - GEM_BUG_ON(vma->pages); + GEM_BUG_ON(atomic_read(&vma->pages_count)); atomic_set(&vma->pages_count, I915_VMA_PAGES_ACTIVE); __i915_gem_object_pin_pages(obj); vma->pages = obj->mm.pages; @@ -1953,7 +1953,9 @@ static int igt_cs_tlb(void *arg) goto end; } - err = vma->ops->set_pages(vma); + i915_gem_object_lock(bbe, NULL); + err = i915_vma_get_pages(vma); + i915_gem_object_unlock(bbe); if (err) goto end; @@ -1994,7 +1996,7 @@ end_ww: i915_request_put(rq); } - vma->ops->clear_pages(vma); + i915_vma_put_pages(vma); err = context_sync(ce); if (err) { @@ -2009,7 +2011,9 @@ end_ww: goto end; } - err = vma->ops->set_pages(vma); + i915_gem_object_lock(act, NULL); + err = i915_vma_get_pages(vma); + i915_gem_object_unlock(act); if (err) goto end; @@ -2047,7 +2051,7 @@ end_ww: } end_spin(batch, count - 1); - vma->ops->clear_pages(vma); + i915_vma_put_pages(vma); err = context_sync(ce); if (err) { diff --git a/drivers/gpu/drm/i915/selftests/i915_perf.c b/drivers/gpu/drm/i915/selftests/i915_perf.c index 9e9a6cb1d9e5..88db2e3d81d0 100644 --- a/drivers/gpu/drm/i915/selftests/i915_perf.c +++ b/drivers/gpu/drm/i915/selftests/i915_perf.c @@ -424,7 +424,7 @@ int i915_perf_live_selftests(struct drm_i915_private *i915) if (!perf->metrics_kobj || !perf->ops.enable_metric_set) return 0; - if (intel_gt_is_wedged(&i915->gt)) + if (intel_gt_is_wedged(to_gt(i915))) return 0; err = alloc_empty_config(&i915->perf); diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c index d67710d10615..92a859b34190 100644 --- a/drivers/gpu/drm/i915/selftests/i915_request.c +++ b/drivers/gpu/drm/i915/selftests/i915_request.c @@ -209,6 +209,10 @@ static int igt_request_rewind(void *arg) int err = -EINVAL; ctx[0] = mock_context(i915, "A"); + if (!ctx[0]) { + err = -ENOMEM; + goto err_ctx_0; + } ce = i915_gem_context_get_engine(ctx[0], RCS0); GEM_BUG_ON(IS_ERR(ce)); @@ -223,6 +227,10 @@ static int igt_request_rewind(void *arg) i915_request_add(request); ctx[1] = mock_context(i915, "B"); + if (!ctx[1]) { + err = -ENOMEM; + goto err_ctx_1; + } ce = i915_gem_context_get_engine(ctx[1], RCS0); GEM_BUG_ON(IS_ERR(ce)); @@ -261,9 +269,11 @@ err: i915_request_put(vip); err_context_1: mock_context_close(ctx[1]); +err_ctx_1: i915_request_put(request); err_context_0: mock_context_close(ctx[0]); +err_ctx_0: mock_device_flush(i915); return err; } @@ -831,7 +841,7 @@ static struct i915_vma *empty_batch(struct drm_i915_private *i915) __i915_gem_object_flush_map(obj, 0, 64); i915_gem_object_unpin_map(obj); - intel_gt_chipset_flush(&i915->gt); + intel_gt_chipset_flush(to_gt(i915)); vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL); if (IS_ERR(vma)) { @@ -972,7 +982,7 @@ static struct i915_vma *recursive_batch(struct drm_i915_private *i915) if (IS_ERR(obj)) return ERR_CAST(obj); - vma = i915_vma_instance(obj, i915->gt.vm, NULL); + vma = i915_vma_instance(obj, to_gt(i915)->vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto err; @@ -1004,7 +1014,7 @@ static struct i915_vma *recursive_batch(struct drm_i915_private *i915) __i915_gem_object_flush_map(obj, 0, 64); i915_gem_object_unpin_map(obj); - intel_gt_chipset_flush(&i915->gt); + intel_gt_chipset_flush(to_gt(i915)); return vma; @@ -1690,7 +1700,7 @@ int i915_request_live_selftests(struct drm_i915_private *i915) SUBTEST(live_breadcrumbs_smoketest), }; - if (intel_gt_is_wedged(&i915->gt)) + if (intel_gt_is_wedged(to_gt(i915))) return 0; return i915_subtests(tests, i915); @@ -2805,7 +2815,7 @@ static int p_sync0(void *arg) i915_request_add(rq); err = 0; - if (i915_request_wait(rq, 0, HZ / 5) < 0) + if (i915_request_wait(rq, 0, HZ) < 0) err = -ETIME; i915_request_put(rq); if (err) @@ -2876,7 +2886,7 @@ static int p_sync1(void *arg) i915_request_add(rq); err = 0; - if (prev && i915_request_wait(prev, 0, HZ / 5) < 0) + if (prev && i915_request_wait(prev, 0, HZ) < 0) err = -ETIME; i915_request_put(prev); prev = rq; @@ -3081,7 +3091,7 @@ int i915_request_perf_selftests(struct drm_i915_private *i915) SUBTEST(perf_parallel_engines), }; - if (intel_gt_is_wedged(&i915->gt)) + if (intel_gt_is_wedged(to_gt(i915))) return 0; return i915_subtests(tests, i915); diff --git a/drivers/gpu/drm/i915/selftests/i915_selftest.c b/drivers/gpu/drm/i915/selftests/i915_selftest.c index 484759c9409c..2d6d7bd13c3c 100644 --- a/drivers/gpu/drm/i915/selftests/i915_selftest.c +++ b/drivers/gpu/drm/i915/selftests/i915_selftest.c @@ -298,10 +298,10 @@ int __i915_live_setup(void *data) struct drm_i915_private *i915 = data; /* The selftests expect an idle system */ - if (intel_gt_pm_wait_for_idle(&i915->gt)) + if (intel_gt_pm_wait_for_idle(to_gt(i915))) return -EIO; - return intel_gt_terminally_wedged(&i915->gt); + return intel_gt_terminally_wedged(to_gt(i915)); } int __i915_live_teardown(int err, void *data) diff --git a/drivers/gpu/drm/i915/selftests/i915_sw_fence.c b/drivers/gpu/drm/i915/selftests/i915_sw_fence.c index cbf45d85cbff..daa985e5a19b 100644 --- a/drivers/gpu/drm/i915/selftests/i915_sw_fence.c +++ b/drivers/gpu/drm/i915/selftests/i915_sw_fence.c @@ -28,7 +28,7 @@ #include "../i915_selftest.h" -static int __i915_sw_fence_call +static int fence_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state) { switch (state) { diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c index 1f10fe36619b..5c5809dfe9b2 100644 --- a/drivers/gpu/drm/i915/selftests/i915_vma.c +++ b/drivers/gpu/drm/i915/selftests/i915_vma.c @@ -691,7 +691,11 @@ static int igt_vma_rotate_remap(void *arg) } i915_vma_unpin(vma); - + err = i915_vma_unbind(vma); + if (err) { + pr_err("Unbinding returned %i\n", err); + goto out_object; + } cond_resched(); } } @@ -848,6 +852,11 @@ static int igt_vma_partial(void *arg) i915_vma_unpin(vma); nvma++; + err = i915_vma_unbind(vma); + if (err) { + pr_err("Unbinding returned %i\n", err); + goto out_object; + } cond_resched(); } @@ -882,6 +891,12 @@ static int igt_vma_partial(void *arg) i915_vma_unpin(vma); + err = i915_vma_unbind(vma); + if (err) { + pr_err("Unbinding returned %i\n", err); + goto out_object; + } + count = 0; list_for_each_entry(vma, &obj->vma.list, obj_link) count++; diff --git a/drivers/gpu/drm/i915/selftests/igt_flush_test.c b/drivers/gpu/drm/i915/selftests/igt_flush_test.c index a6c71fca61aa..b84594601d30 100644 --- a/drivers/gpu/drm/i915/selftests/igt_flush_test.c +++ b/drivers/gpu/drm/i915/selftests/igt_flush_test.c @@ -14,7 +14,7 @@ int igt_flush_test(struct drm_i915_private *i915) { - struct intel_gt *gt = &i915->gt; + struct intel_gt *gt = to_gt(i915); int ret = intel_gt_is_wedged(gt) ? -EIO : 0; cond_resched(); diff --git a/drivers/gpu/drm/i915/selftests/igt_live_test.c b/drivers/gpu/drm/i915/selftests/igt_live_test.c index 1c721542e277..72b58b66692a 100644 --- a/drivers/gpu/drm/i915/selftests/igt_live_test.c +++ b/drivers/gpu/drm/i915/selftests/igt_live_test.c @@ -16,7 +16,7 @@ int igt_live_test_begin(struct igt_live_test *t, const char *func, const char *name) { - struct intel_gt *gt = &i915->gt; + struct intel_gt *gt = to_gt(i915); struct intel_engine_cs *engine; enum intel_engine_id id; int err; @@ -57,7 +57,7 @@ int igt_live_test_end(struct igt_live_test *t) return -EIO; } - for_each_engine(engine, &i915->gt, id) { + for_each_engine(engine, to_gt(i915), id) { if (t->reset_engine[id] == i915_reset_engine_count(&i915->gpu_error, engine)) continue; diff --git a/drivers/gpu/drm/i915/selftests/igt_reset.c b/drivers/gpu/drm/i915/selftests/igt_reset.c index 9f8590b868a9..a2838c65f8a5 100644 --- a/drivers/gpu/drm/i915/selftests/igt_reset.c +++ b/drivers/gpu/drm/i915/selftests/igt_reset.c @@ -36,7 +36,7 @@ void igt_global_reset_unlock(struct intel_gt *gt) enum intel_engine_id id; for_each_engine(engine, gt, id) - clear_bit(I915_RESET_ENGINE + id, >->reset.flags); + clear_and_wake_up_bit(I915_RESET_ENGINE + id, >->reset.flags); clear_bit(I915_RESET_BACKOFF, >->reset.flags); wake_up_all(>->reset.queue); diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c index 418caae84759..8255561ff853 100644 --- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c +++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c @@ -225,7 +225,7 @@ static int igt_mock_reserve(void *arg) out_close: close_objects(mem, &objects); - intel_memory_region_put(mem); + intel_memory_region_destroy(mem); out_free_order: kfree(order); return err; @@ -439,7 +439,7 @@ static int igt_mock_splintered_region(void *arg) out_close: close_objects(mem, &objects); out_put: - intel_memory_region_put(mem); + intel_memory_region_destroy(mem); return err; } @@ -507,7 +507,7 @@ static int igt_mock_max_segment(void *arg) out_close: close_objects(mem, &objects); out_put: - intel_memory_region_put(mem); + intel_memory_region_destroy(mem); return err; } @@ -1196,7 +1196,7 @@ int intel_memory_region_mock_selftests(void) err = i915_subtests(tests, mem); - intel_memory_region_put(mem); + intel_memory_region_destroy(mem); out_unref: mock_destroy_device(i915); return err; @@ -1217,7 +1217,7 @@ int intel_memory_region_live_selftests(struct drm_i915_private *i915) return 0; } - if (intel_gt_is_wedged(&i915->gt)) + if (intel_gt_is_wedged(to_gt(i915))) return 0; return i915_live_subtests(tests, i915); @@ -1229,7 +1229,7 @@ int intel_memory_region_perf_selftests(struct drm_i915_private *i915) SUBTEST(perf_memcpy), }; - if (intel_gt_is_wedged(&i915->gt)) + if (intel_gt_is_wedged(to_gt(i915))) return 0; return i915_live_subtests(tests, i915); diff --git a/drivers/gpu/drm/i915/selftests/intel_uncore.c b/drivers/gpu/drm/i915/selftests/intel_uncore.c index bc8128170a99..cdd196783535 100644 --- a/drivers/gpu/drm/i915/selftests/intel_uncore.c +++ b/drivers/gpu/drm/i915/selftests/intel_uncore.c @@ -344,5 +344,5 @@ int intel_uncore_live_selftests(struct drm_i915_private *i915) SUBTEST(live_forcewake_domains), }; - return intel_gt_live_subtests(tests, &i915->gt); + return intel_gt_live_subtests(tests, to_gt(i915)); } diff --git a/drivers/gpu/drm/i915/selftests/lib_sw_fence.c b/drivers/gpu/drm/i915/selftests/lib_sw_fence.c index 080b90b63d16..bf2752cc1e0b 100644 --- a/drivers/gpu/drm/i915/selftests/lib_sw_fence.c +++ b/drivers/gpu/drm/i915/selftests/lib_sw_fence.c @@ -26,7 +26,7 @@ /* Small library of different fence types useful for writing tests */ -static int __i915_sw_fence_call +static int nop_fence_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state) { return NOTIFY_DONE; @@ -41,12 +41,12 @@ void __onstack_fence_init(struct i915_sw_fence *fence, __init_waitqueue_head(&fence->wait, name, key); atomic_set(&fence->pending, 1); fence->error = 0; - fence->flags = (unsigned long)nop_fence_notify; + fence->fn = nop_fence_notify; } void onstack_fence_fini(struct i915_sw_fence *fence) { - if (!fence->flags) + if (!fence->fn) return; i915_sw_fence_commit(fence); @@ -89,7 +89,7 @@ struct heap_fence { }; }; -static int __i915_sw_fence_call +static int heap_fence_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state) { struct heap_fence *h = container_of(fence, typeof(*h), fence); diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c index 4f8180146888..8aa7b1d33865 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c +++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c @@ -45,7 +45,7 @@ void mock_device_flush(struct drm_i915_private *i915) { - struct intel_gt *gt = &i915->gt; + struct intel_gt *gt = to_gt(i915); struct intel_engine_cs *engine; enum intel_engine_id id; @@ -64,7 +64,7 @@ static void mock_device_release(struct drm_device *dev) goto out; mock_device_flush(i915); - intel_gt_driver_remove(&i915->gt); + intel_gt_driver_remove(to_gt(i915)); i915_gem_drain_workqueue(i915); i915_gem_drain_freed_objects(i915); @@ -73,7 +73,7 @@ static void mock_device_release(struct drm_device *dev) destroy_workqueue(i915->wq); intel_region_ttm_device_fini(i915); - intel_gt_driver_late_release(&i915->gt); + intel_gt_driver_late_release(to_gt(i915)); intel_memory_regions_driver_release(i915); drm_mode_config_cleanup(&i915->drm); @@ -165,7 +165,7 @@ struct drm_i915_private *mock_gem_device(void) /* Using the global GTT may ask questions about KMS users, so prepare */ drm_mode_config_init(&i915->drm); - mkwrite_device_info(i915)->graphics_ver = -1; + mkwrite_device_info(i915)->graphics.ver = -1; mkwrite_device_info(i915)->page_sizes = I915_GTT_PAGE_SIZE_4K | @@ -175,12 +175,14 @@ struct drm_i915_private *mock_gem_device(void) mkwrite_device_info(i915)->memory_regions = REGION_SMEM; intel_memory_regions_hw_probe(i915); - mock_uncore_init(&i915->uncore, i915); + spin_lock_init(&i915->gpu_error.lock); i915_gem_init__mm(i915); - intel_gt_init_early(&i915->gt, i915); - atomic_inc(&i915->gt.wakeref.count); /* disable; no hw support */ - i915->gt.awake = -ENODEV; + intel_gt_init_early(to_gt(i915), i915); + __intel_gt_init_early(to_gt(i915), i915); + mock_uncore_init(&i915->uncore, i915); + atomic_inc(&to_gt(i915)->wakeref.count); /* disable; no hw support */ + to_gt(i915)->awake = -ENODEV; ret = intel_region_ttm_device_init(i915); if (ret) @@ -193,19 +195,19 @@ struct drm_i915_private *mock_gem_device(void) mock_init_contexts(i915); mock_init_ggtt(i915, &i915->ggtt); - i915->gt.vm = i915_vm_get(&i915->ggtt.vm); + to_gt(i915)->vm = i915_vm_get(&i915->ggtt.vm); mkwrite_device_info(i915)->platform_engine_mask = BIT(0); - i915->gt.info.engine_mask = BIT(0); + to_gt(i915)->info.engine_mask = BIT(0); - i915->gt.engine[RCS0] = mock_engine(i915, "mock", RCS0); - if (!i915->gt.engine[RCS0]) + to_gt(i915)->engine[RCS0] = mock_engine(i915, "mock", RCS0); + if (!to_gt(i915)->engine[RCS0]) goto err_unlock; - if (mock_engine_init(i915->gt.engine[RCS0])) + if (mock_engine_init(to_gt(i915)->engine[RCS0])) goto err_context; - __clear_bit(I915_WEDGED, &i915->gt.reset.flags); + __clear_bit(I915_WEDGED, &to_gt(i915)->reset.flags); intel_engines_driver_register(i915); i915->do_release = true; @@ -214,13 +216,13 @@ struct drm_i915_private *mock_gem_device(void) return i915; err_context: - intel_gt_driver_remove(&i915->gt); + intel_gt_driver_remove(to_gt(i915)); err_unlock: destroy_workqueue(i915->wq); err_drv: intel_region_ttm_device_fini(i915); err_ttm: - intel_gt_driver_late_release(&i915->gt); + intel_gt_driver_late_release(to_gt(i915)); intel_memory_regions_driver_release(i915); drm_mode_config_cleanup(&i915->drm); mock_destroy_device(i915); diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c index cc047ec594f9..1802baf80a17 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gtt.c +++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c @@ -70,7 +70,7 @@ struct i915_ppgtt *mock_ppgtt(struct drm_i915_private *i915, const char *name) if (!ppgtt) return NULL; - ppgtt->vm.gt = &i915->gt; + ppgtt->vm.gt = to_gt(i915); ppgtt->vm.i915 = i915; ppgtt->vm.total = round_down(U64_MAX, PAGE_SIZE); ppgtt->vm.dma = i915->drm.dev; @@ -78,6 +78,7 @@ struct i915_ppgtt *mock_ppgtt(struct drm_i915_private *i915, const char *name) i915_address_space_init(&ppgtt->vm, VM_CLASS_PPGTT); ppgtt->vm.alloc_pt_dma = alloc_pt_dma; + ppgtt->vm.alloc_scratch_dma = alloc_pt_dma; ppgtt->vm.clear_range = mock_clear_range; ppgtt->vm.insert_page = mock_insert_page; @@ -86,8 +87,6 @@ struct i915_ppgtt *mock_ppgtt(struct drm_i915_private *i915, const char *name) ppgtt->vm.vma_ops.bind_vma = mock_bind_ppgtt; ppgtt->vm.vma_ops.unbind_vma = mock_unbind_ppgtt; - ppgtt->vm.vma_ops.set_pages = ppgtt_set_pages; - ppgtt->vm.vma_ops.clear_pages = clear_pages; return ppgtt; } @@ -109,7 +108,7 @@ void mock_init_ggtt(struct drm_i915_private *i915, struct i915_ggtt *ggtt) { memset(ggtt, 0, sizeof(*ggtt)); - ggtt->vm.gt = &i915->gt; + ggtt->vm.gt = to_gt(i915); ggtt->vm.i915 = i915; ggtt->vm.is_ggtt = true; @@ -118,6 +117,7 @@ void mock_init_ggtt(struct drm_i915_private *i915, struct i915_ggtt *ggtt) ggtt->vm.total = 4096 * PAGE_SIZE; ggtt->vm.alloc_pt_dma = alloc_pt_dma; + ggtt->vm.alloc_scratch_dma = alloc_pt_dma; ggtt->vm.clear_range = mock_clear_range; ggtt->vm.insert_page = mock_insert_page; @@ -126,11 +126,9 @@ void mock_init_ggtt(struct drm_i915_private *i915, struct i915_ggtt *ggtt) ggtt->vm.vma_ops.bind_vma = mock_bind_ggtt; ggtt->vm.vma_ops.unbind_vma = mock_unbind_ggtt; - ggtt->vm.vma_ops.set_pages = ggtt_set_pages; - ggtt->vm.vma_ops.clear_pages = clear_pages; i915_address_space_init(&ggtt->vm, VM_CLASS_GGTT); - i915->gt.ggtt = ggtt; + to_gt(i915)->ggtt = ggtt; } void mock_fini_ggtt(struct i915_ggtt *ggtt) diff --git a/drivers/gpu/drm/i915/selftests/mock_region.c b/drivers/gpu/drm/i915/selftests/mock_region.c index 75793008c4ef..19bff8afcaaa 100644 --- a/drivers/gpu/drm/i915/selftests/mock_region.c +++ b/drivers/gpu/drm/i915/selftests/mock_region.c @@ -15,9 +15,9 @@ static void mock_region_put_pages(struct drm_i915_gem_object *obj, struct sg_table *pages) { + i915_refct_sgt_put(obj->mm.rsgt); + obj->mm.rsgt = NULL; intel_region_ttm_resource_free(obj->mm.region, obj->mm.res); - sg_free_table(pages); - kfree(pages); } static int mock_region_get_pages(struct drm_i915_gem_object *obj) @@ -36,12 +36,14 @@ static int mock_region_get_pages(struct drm_i915_gem_object *obj) if (IS_ERR(obj->mm.res)) return PTR_ERR(obj->mm.res); - pages = intel_region_ttm_resource_to_st(obj->mm.region, obj->mm.res); - if (IS_ERR(pages)) { - err = PTR_ERR(pages); + obj->mm.rsgt = intel_region_ttm_resource_to_rsgt(obj->mm.region, + obj->mm.res); + if (IS_ERR(obj->mm.rsgt)) { + err = PTR_ERR(obj->mm.rsgt); goto err_free_resource; } + pages = &obj->mm.rsgt->table; __i915_gem_object_set_pages(obj, pages, i915_sg_dma_sizes(pages->sgl)); return 0; @@ -82,13 +84,16 @@ static int mock_object_init(struct intel_memory_region *mem, return 0; } -static void mock_region_fini(struct intel_memory_region *mem) +static int mock_region_fini(struct intel_memory_region *mem) { struct drm_i915_private *i915 = mem->i915; int instance = mem->instance; + int ret; - intel_region_ttm_fini(mem); + ret = intel_region_ttm_fini(mem); ida_free(&i915->selftest.mock_region_instances, instance); + + return ret; } static const struct intel_memory_region_ops mock_region_ops = { diff --git a/drivers/gpu/drm/i915/selftests/mock_uncore.c b/drivers/gpu/drm/i915/selftests/mock_uncore.c index ca57e4008701..f2d6be5e1230 100644 --- a/drivers/gpu/drm/i915/selftests/mock_uncore.c +++ b/drivers/gpu/drm/i915/selftests/mock_uncore.c @@ -42,7 +42,7 @@ __nop_read(64) void mock_uncore_init(struct intel_uncore *uncore, struct drm_i915_private *i915) { - intel_uncore_init_early(uncore, i915); + intel_uncore_init_early(uncore, to_gt(i915)); ASSIGN_RAW_WRITE_MMIO_VFUNCS(uncore, nop); ASSIGN_RAW_READ_MMIO_VFUNCS(uncore, nop); diff --git a/drivers/gpu/drm/i915/vlv_sideband.c b/drivers/gpu/drm/i915/vlv_sideband.c index 35380738a951..ed2ac5752ac4 100644 --- a/drivers/gpu/drm/i915/vlv_sideband.c +++ b/drivers/gpu/drm/i915/vlv_sideband.c @@ -3,9 +3,8 @@ * Copyright © 2013-2021 Intel Corporation */ -#include <asm/iosf_mbi.h> - #include "i915_drv.h" +#include "i915_iosf_mbi.h" #include "vlv_sideband.h" /* |