diff options
Diffstat (limited to 'drivers/gpu/drm/i915')
-rw-r--r-- | drivers/gpu/drm/i915/Makefile | 1 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/display/icl_dsi.c | 4 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/display/intel_display_types.h | 3 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/display/intel_dp.c | 8 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/display/intel_panel.c | 9 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/display/vlv_dsi.c | 16 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 4 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gt/gen7_renderclear.c | 157 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gt/intel_ring_submission.c | 6 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c | 1 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gvt/display.c | 81 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gvt/vgpu.c | 5 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/i915_cmd_parser.c | 27 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/i915_drv.c | 9 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/i915_drv.h | 3 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/i915_mitigations.c | 146 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/i915_mitigations.h | 13 |
17 files changed, 361 insertions, 132 deletions
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index e5574e506a5c..6d9e81ea67f4 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -38,6 +38,7 @@ i915-y += i915_drv.o \ i915_config.o \ i915_irq.o \ i915_getparam.o \ + i915_mitigations.o \ i915_params.o \ i915_pci.o \ i915_scatterlist.o \ diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index a9439b415603..b3533a32f8ba 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -1616,10 +1616,6 @@ static void gen11_dsi_get_power_domains(struct intel_encoder *encoder, get_dsi_io_power_domains(i915, enc_to_intel_dsi(encoder)); - - if (crtc_state->dsc.compression_enable) - intel_display_power_get(i915, - intel_dsc_power_domain(crtc_state)); } static bool gen11_dsi_get_hw_state(struct intel_encoder *encoder, diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h index ce82d654d0f2..34d78c654df3 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -1436,6 +1436,9 @@ struct intel_dp { bool ycbcr_444_to_420; } dfp; + /* To control wakeup latency, e.g. for irq-driven dp aux transfers. */ + struct pm_qos_request pm_qos; + /* Display stream compression testing */ bool force_dsc_en; diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 2165398d2c7c..37f1a10fd021 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -1489,7 +1489,7 @@ intel_dp_aux_xfer(struct intel_dp *intel_dp, * lowest possible wakeup latency and so prevent the cpu from going into * deep sleep states. */ - cpu_latency_qos_update_request(&i915->pm_qos, 0); + cpu_latency_qos_update_request(&intel_dp->pm_qos, 0); intel_dp_check_edp(intel_dp); @@ -1622,7 +1622,7 @@ done: ret = recv_bytes; out: - cpu_latency_qos_update_request(&i915->pm_qos, PM_QOS_DEFAULT_VALUE); + cpu_latency_qos_update_request(&intel_dp->pm_qos, PM_QOS_DEFAULT_VALUE); if (vdd) edp_panel_vdd_off(intel_dp, false); @@ -1898,6 +1898,9 @@ static i915_reg_t tgl_aux_data_reg(struct intel_dp *intel_dp, int index) static void intel_dp_aux_fini(struct intel_dp *intel_dp) { + if (cpu_latency_qos_request_active(&intel_dp->pm_qos)) + cpu_latency_qos_remove_request(&intel_dp->pm_qos); + kfree(intel_dp->aux.name); } @@ -1950,6 +1953,7 @@ intel_dp_aux_init(struct intel_dp *intel_dp) encoder->base.name); intel_dp->aux.transfer = intel_dp_aux_transfer; + cpu_latency_qos_add_request(&intel_dp->pm_qos, PM_QOS_DEFAULT_VALUE); } bool intel_dp_source_supports_hbr2(struct intel_dp *intel_dp) diff --git a/drivers/gpu/drm/i915/display/intel_panel.c b/drivers/gpu/drm/i915/display/intel_panel.c index 9f23bac0d792..d64fce1a17cb 100644 --- a/drivers/gpu/drm/i915/display/intel_panel.c +++ b/drivers/gpu/drm/i915/display/intel_panel.c @@ -1650,16 +1650,13 @@ static int lpt_setup_backlight(struct intel_connector *connector, enum pipe unus val = pch_get_backlight(connector); else val = lpt_get_backlight(connector); - val = intel_panel_compute_brightness(connector, val); - panel->backlight.level = clamp(val, panel->backlight.min, - panel->backlight.max); if (cpu_mode) { drm_dbg_kms(&dev_priv->drm, "CPU backlight register was enabled, switching to PCH override\n"); /* Write converted CPU PWM value to PCH override register */ - lpt_set_backlight(connector->base.state, panel->backlight.level); + lpt_set_backlight(connector->base.state, val); intel_de_write(dev_priv, BLC_PWM_PCH_CTL1, pch_ctl1 | BLM_PCH_OVERRIDE_ENABLE); @@ -1667,6 +1664,10 @@ static int lpt_setup_backlight(struct intel_connector *connector, enum pipe unus cpu_ctl2 & ~BLM_PWM_ENABLE); } + val = intel_panel_compute_brightness(connector, val); + panel->backlight.level = clamp(val, panel->backlight.min, + panel->backlight.max); + return 0; } diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c index d52f9c177908..f94025ec603a 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi.c +++ b/drivers/gpu/drm/i915/display/vlv_dsi.c @@ -812,10 +812,20 @@ static void intel_dsi_pre_enable(struct intel_atomic_state *state, intel_dsi_prepare(encoder, pipe_config); intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_POWER_ON); - intel_dsi_msleep(intel_dsi, intel_dsi->panel_on_delay); - /* Deassert reset */ - intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DEASSERT_RESET); + /* + * Give the panel time to power-on and then deassert its reset. + * Depending on the VBT MIPI sequences version the deassert-seq + * may contain the necessary delay, intel_dsi_msleep() will skip + * the delay in that case. If there is no deassert-seq, then an + * unconditional msleep is used to give the panel time to power-on. + */ + if (dev_priv->vbt.dsi.sequence[MIPI_SEQ_DEASSERT_RESET]) { + intel_dsi_msleep(intel_dsi, intel_dsi->panel_on_delay); + intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DEASSERT_RESET); + } else { + msleep(intel_dsi->panel_on_delay); + } if (IS_GEMINILAKE(dev_priv)) { glk_cold_boot = glk_dsi_enable_io(encoder); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index bcc80f428172..bd3046e5a934 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -1046,7 +1046,7 @@ static void reloc_gpu_flush(struct i915_execbuffer *eb, struct reloc_cache *cach GEM_BUG_ON(cache->rq_size >= obj->base.size / sizeof(u32)); cache->rq_cmd[cache->rq_size] = MI_BATCH_BUFFER_END; - __i915_gem_object_flush_map(obj, 0, sizeof(u32) * (cache->rq_size + 1)); + i915_gem_object_flush_map(obj); i915_gem_object_unpin_map(obj); intel_gt_chipset_flush(cache->rq->engine->gt); @@ -1296,6 +1296,8 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb, goto err_pool; } + memset32(cmd, 0, pool->obj->base.size / sizeof(u32)); + batch = i915_vma_instance(pool->obj, vma->vm, NULL); if (IS_ERR(batch)) { err = PTR_ERR(batch); diff --git a/drivers/gpu/drm/i915/gt/gen7_renderclear.c b/drivers/gpu/drm/i915/gt/gen7_renderclear.c index d93d85cd3027..94465374ca2f 100644 --- a/drivers/gpu/drm/i915/gt/gen7_renderclear.c +++ b/drivers/gpu/drm/i915/gt/gen7_renderclear.c @@ -7,8 +7,6 @@ #include "i915_drv.h" #include "intel_gpu_commands.h" -#define MAX_URB_ENTRIES 64 -#define STATE_SIZE (4 * 1024) #define GT3_INLINE_DATA_DELAYS 0x1E00 #define batch_advance(Y, CS) GEM_BUG_ON((Y)->end != (CS)) @@ -34,38 +32,59 @@ struct batch_chunk { }; struct batch_vals { - u32 max_primitives; - u32 max_urb_entries; - u32 cmd_size; - u32 state_size; + u32 max_threads; u32 state_start; - u32 batch_size; + u32 surface_start; u32 surface_height; u32 surface_width; - u32 scratch_size; - u32 max_size; + u32 size; }; +static inline int num_primitives(const struct batch_vals *bv) +{ + /* + * We need to saturate the GPU with work in order to dispatch + * a shader on every HW thread, and clear the thread-local registers. + * In short, we have to dispatch work faster than the shaders can + * run in order to fill the EU and occupy each HW thread. + */ + return bv->max_threads; +} + static void batch_get_defaults(struct drm_i915_private *i915, struct batch_vals *bv) { if (IS_HASWELL(i915)) { - bv->max_primitives = 280; - bv->max_urb_entries = MAX_URB_ENTRIES; + switch (INTEL_INFO(i915)->gt) { + default: + case 1: + bv->max_threads = 70; + break; + case 2: + bv->max_threads = 140; + break; + case 3: + bv->max_threads = 280; + break; + } bv->surface_height = 16 * 16; bv->surface_width = 32 * 2 * 16; } else { - bv->max_primitives = 128; - bv->max_urb_entries = MAX_URB_ENTRIES / 2; + switch (INTEL_INFO(i915)->gt) { + default: + case 1: /* including vlv */ + bv->max_threads = 36; + break; + case 2: + bv->max_threads = 128; + break; + } bv->surface_height = 16 * 8; bv->surface_width = 32 * 16; } - bv->cmd_size = bv->max_primitives * 4096; - bv->state_size = STATE_SIZE; - bv->state_start = bv->cmd_size; - bv->batch_size = bv->cmd_size + bv->state_size; - bv->scratch_size = bv->surface_height * bv->surface_width; - bv->max_size = bv->batch_size + bv->scratch_size; + bv->state_start = round_up(SZ_1K + num_primitives(bv) * 64, SZ_4K); + bv->surface_start = bv->state_start + SZ_4K; + bv->size = bv->surface_start + bv->surface_height * bv->surface_width; } static void batch_init(struct batch_chunk *bc, @@ -155,7 +174,8 @@ static u32 gen7_fill_binding_table(struct batch_chunk *state, const struct batch_vals *bv) { - u32 surface_start = gen7_fill_surface_state(state, bv->batch_size, bv); + u32 surface_start = + gen7_fill_surface_state(state, bv->surface_start, bv); u32 *cs = batch_alloc_items(state, 32, 8); u32 offset = batch_offset(state, cs); @@ -214,9 +234,9 @@ static void gen7_emit_state_base_address(struct batch_chunk *batch, u32 surface_state_base) { - u32 *cs = batch_alloc_items(batch, 0, 12); + u32 *cs = batch_alloc_items(batch, 0, 10); - *cs++ = STATE_BASE_ADDRESS | (12 - 2); + *cs++ = STATE_BASE_ADDRESS | (10 - 2); /* general */ *cs++ = batch_addr(batch) | BASE_ADDRESS_MODIFY; /* surface */ @@ -233,8 +253,6 @@ gen7_emit_state_base_address(struct batch_chunk *batch, *cs++ = BASE_ADDRESS_MODIFY; *cs++ = 0; *cs++ = BASE_ADDRESS_MODIFY; - *cs++ = 0; - *cs++ = 0; batch_advance(batch, cs); } @@ -244,8 +262,7 @@ gen7_emit_vfe_state(struct batch_chunk *batch, u32 urb_size, u32 curbe_size, u32 mode) { - u32 urb_entries = bv->max_urb_entries; - u32 threads = bv->max_primitives - 1; + u32 threads = bv->max_threads - 1; u32 *cs = batch_alloc_items(batch, 32, 8); *cs++ = MEDIA_VFE_STATE | (8 - 2); @@ -254,7 +271,7 @@ gen7_emit_vfe_state(struct batch_chunk *batch, *cs++ = 0; /* number of threads & urb entries for GPGPU vs Media Mode */ - *cs++ = threads << 16 | urb_entries << 8 | mode << 2; + *cs++ = threads << 16 | 1 << 8 | mode << 2; *cs++ = 0; @@ -293,17 +310,12 @@ gen7_emit_media_object(struct batch_chunk *batch, { unsigned int x_offset = (media_object_index % 16) * 64; unsigned int y_offset = (media_object_index / 16) * 16; - unsigned int inline_data_size; - unsigned int media_batch_size; - unsigned int i; + unsigned int pkt = 6 + 3; u32 *cs; - inline_data_size = 112 * 8; - media_batch_size = inline_data_size + 6; - - cs = batch_alloc_items(batch, 8, media_batch_size); + cs = batch_alloc_items(batch, 8, pkt); - *cs++ = MEDIA_OBJECT | (media_batch_size - 2); + *cs++ = MEDIA_OBJECT | (pkt - 2); /* interface descriptor offset */ *cs++ = 0; @@ -317,25 +329,44 @@ gen7_emit_media_object(struct batch_chunk *batch, *cs++ = 0; /* inline */ - *cs++ = (y_offset << 16) | (x_offset); + *cs++ = y_offset << 16 | x_offset; *cs++ = 0; *cs++ = GT3_INLINE_DATA_DELAYS; - for (i = 3; i < inline_data_size; i++) - *cs++ = 0; batch_advance(batch, cs); } static void gen7_emit_pipeline_flush(struct batch_chunk *batch) { - u32 *cs = batch_alloc_items(batch, 0, 5); + u32 *cs = batch_alloc_items(batch, 0, 4); - *cs++ = GFX_OP_PIPE_CONTROL(5); - *cs++ = PIPE_CONTROL_STATE_CACHE_INVALIDATE | - PIPE_CONTROL_GLOBAL_GTT_IVB; + *cs++ = GFX_OP_PIPE_CONTROL(4); + *cs++ = PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH | + PIPE_CONTROL_DEPTH_CACHE_FLUSH | + PIPE_CONTROL_DC_FLUSH_ENABLE | + PIPE_CONTROL_CS_STALL; *cs++ = 0; *cs++ = 0; + + batch_advance(batch, cs); +} + +static void gen7_emit_pipeline_invalidate(struct batch_chunk *batch) +{ + u32 *cs = batch_alloc_items(batch, 0, 8); + + /* ivb: Stall before STATE_CACHE_INVALIDATE */ + *cs++ = GFX_OP_PIPE_CONTROL(4); + *cs++ = PIPE_CONTROL_STALL_AT_SCOREBOARD | + PIPE_CONTROL_CS_STALL; + *cs++ = 0; + *cs++ = 0; + + *cs++ = GFX_OP_PIPE_CONTROL(4); + *cs++ = PIPE_CONTROL_STATE_CACHE_INVALIDATE; *cs++ = 0; + *cs++ = 0; + batch_advance(batch, cs); } @@ -344,34 +375,34 @@ static void emit_batch(struct i915_vma * const vma, const struct batch_vals *bv) { struct drm_i915_private *i915 = vma->vm->i915; - unsigned int desc_count = 64; - const u32 urb_size = 112; + const unsigned int desc_count = 1; + const unsigned int urb_size = 1; struct batch_chunk cmds, state; - u32 interface_descriptor; + u32 descriptors; unsigned int i; - batch_init(&cmds, vma, start, 0, bv->cmd_size); - batch_init(&state, vma, start, bv->state_start, bv->state_size); + batch_init(&cmds, vma, start, 0, bv->state_start); + batch_init(&state, vma, start, bv->state_start, SZ_4K); - interface_descriptor = - gen7_fill_interface_descriptor(&state, bv, - IS_HASWELL(i915) ? - &cb_kernel_hsw : - &cb_kernel_ivb, - desc_count); - gen7_emit_pipeline_flush(&cmds); + descriptors = gen7_fill_interface_descriptor(&state, bv, + IS_HASWELL(i915) ? + &cb_kernel_hsw : + &cb_kernel_ivb, + desc_count); + + gen7_emit_pipeline_invalidate(&cmds); batch_add(&cmds, PIPELINE_SELECT | PIPELINE_SELECT_MEDIA); batch_add(&cmds, MI_NOOP); - gen7_emit_state_base_address(&cmds, interface_descriptor); + gen7_emit_pipeline_invalidate(&cmds); + gen7_emit_pipeline_flush(&cmds); + gen7_emit_state_base_address(&cmds, descriptors); + gen7_emit_pipeline_invalidate(&cmds); gen7_emit_vfe_state(&cmds, bv, urb_size - 1, 0, 0); + gen7_emit_interface_descriptor_load(&cmds, descriptors, desc_count); - gen7_emit_interface_descriptor_load(&cmds, - interface_descriptor, - desc_count); - - for (i = 0; i < bv->max_primitives; i++) + for (i = 0; i < num_primitives(bv); i++) gen7_emit_media_object(&cmds, i); batch_add(&cmds, MI_BATCH_BUFFER_END); @@ -385,15 +416,15 @@ int gen7_setup_clear_gpr_bb(struct intel_engine_cs * const engine, batch_get_defaults(engine->i915, &bv); if (!vma) - return bv.max_size; + return bv.size; - GEM_BUG_ON(vma->obj->base.size < bv.max_size); + GEM_BUG_ON(vma->obj->base.size < bv.size); batch = i915_gem_object_pin_map(vma->obj, I915_MAP_WC); if (IS_ERR(batch)) return PTR_ERR(batch); - emit_batch(vma, memset(batch, 0, bv.max_size), &bv); + emit_batch(vma, memset(batch, 0, bv.size), &bv); i915_gem_object_flush_map(vma->obj); __i915_gem_object_release_map(vma->obj); diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c index a41b43f445b8..ecf3a6118a6d 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c @@ -32,6 +32,7 @@ #include "gen6_ppgtt.h" #include "gen7_renderclear.h" #include "i915_drv.h" +#include "i915_mitigations.h" #include "intel_breadcrumbs.h" #include "intel_context.h" #include "intel_gt.h" @@ -886,7 +887,8 @@ static int switch_context(struct i915_request *rq) GEM_BUG_ON(HAS_EXECLISTS(engine->i915)); if (engine->wa_ctx.vma && ce != engine->kernel_context) { - if (engine->wa_ctx.vma->private != ce) { + if (engine->wa_ctx.vma->private != ce && + i915_mitigate_clear_residuals()) { ret = clear_residuals(rq); if (ret) return ret; @@ -1290,7 +1292,7 @@ int intel_ring_submission_setup(struct intel_engine_cs *engine) GEM_BUG_ON(timeline->hwsp_ggtt != engine->status_page.vma); - if (IS_HASWELL(engine->i915) && engine->class == RENDER_CLASS) { + if (IS_GEN(engine->i915, 7) && engine->class == RENDER_CLASS) { err = gen7_ctx_switch_bb_init(engine); if (err) goto err_ring_unpin; 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 180c23e2e25e..602f1a0bc587 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c @@ -53,6 +53,7 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw, fw_def(ELKHARTLAKE, 0, guc_def(ehl, 49, 0, 1), huc_def(ehl, 9, 0, 0)) \ fw_def(ICELAKE, 0, guc_def(icl, 49, 0, 1), huc_def(icl, 9, 0, 0)) \ fw_def(COMETLAKE, 5, guc_def(cml, 49, 0, 1), huc_def(cml, 4, 0, 0)) \ + fw_def(COMETLAKE, 0, guc_def(kbl, 49, 0, 1), huc_def(kbl, 4, 0, 0)) \ fw_def(COFFEELAKE, 0, guc_def(kbl, 49, 0, 1), huc_def(kbl, 4, 0, 0)) \ fw_def(GEMINILAKE, 0, guc_def(glk, 49, 0, 1), huc_def(glk, 4, 0, 0)) \ fw_def(KABYLAKE, 0, guc_def(kbl, 49, 0, 1), huc_def(kbl, 4, 0, 0)) \ diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c index a15f87539657..62a5b0dd2003 100644 --- a/drivers/gpu/drm/i915/gvt/display.c +++ b/drivers/gpu/drm/i915/gvt/display.c @@ -217,6 +217,15 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) DDI_BUF_CTL_ENABLE); vgpu_vreg_t(vgpu, DDI_BUF_CTL(port)) |= DDI_BUF_IS_IDLE; } + vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &= + ~(PORTA_HOTPLUG_ENABLE | PORTA_HOTPLUG_STATUS_MASK); + vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &= + ~(PORTB_HOTPLUG_ENABLE | PORTB_HOTPLUG_STATUS_MASK); + vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &= + ~(PORTC_HOTPLUG_ENABLE | PORTC_HOTPLUG_STATUS_MASK); + /* No hpd_invert set in vgpu vbt, need to clear invert mask */ + vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &= ~BXT_DDI_HPD_INVERT_MASK; + vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &= ~BXT_DE_PORT_HOTPLUG_MASK; vgpu_vreg_t(vgpu, BXT_P_CR_GT_DISP_PWRON) &= ~(BIT(0) | BIT(1)); vgpu_vreg_t(vgpu, BXT_PORT_CL1CM_DW0(DPIO_PHY0)) &= @@ -273,6 +282,8 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_EDP)) |= (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST | TRANS_DDI_FUNC_ENABLE); + vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |= + PORTA_HOTPLUG_ENABLE; vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |= GEN8_DE_PORT_HOTPLUG(HPD_PORT_A); } @@ -301,6 +312,8 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST | (PORT_B << TRANS_DDI_PORT_SHIFT) | TRANS_DDI_FUNC_ENABLE); + vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |= + PORTB_HOTPLUG_ENABLE; vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |= GEN8_DE_PORT_HOTPLUG(HPD_PORT_B); } @@ -329,6 +342,8 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST | (PORT_B << TRANS_DDI_PORT_SHIFT) | TRANS_DDI_FUNC_ENABLE); + vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |= + PORTC_HOTPLUG_ENABLE; vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |= GEN8_DE_PORT_HOTPLUG(HPD_PORT_C); } @@ -661,44 +676,62 @@ void intel_vgpu_emulate_hotplug(struct intel_vgpu *vgpu, bool connected) PORTD_HOTPLUG_STATUS_MASK; intel_vgpu_trigger_virtual_event(vgpu, DP_D_HOTPLUG); } else if (IS_BROXTON(i915)) { - if (connected) { - if (intel_vgpu_has_monitor_on_port(vgpu, PORT_A)) { + if (intel_vgpu_has_monitor_on_port(vgpu, PORT_A)) { + if (connected) { vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |= GEN8_DE_PORT_HOTPLUG(HPD_PORT_A); + } else { + vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &= + ~GEN8_DE_PORT_HOTPLUG(HPD_PORT_A); } - if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) { - vgpu_vreg_t(vgpu, SFUSE_STRAP) |= - SFUSE_STRAP_DDIB_DETECTED; + vgpu_vreg_t(vgpu, GEN8_DE_PORT_IIR) |= + GEN8_DE_PORT_HOTPLUG(HPD_PORT_A); + vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &= + ~PORTA_HOTPLUG_STATUS_MASK; + vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |= + PORTA_HOTPLUG_LONG_DETECT; + intel_vgpu_trigger_virtual_event(vgpu, DP_A_HOTPLUG); + } + if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) { + if (connected) { vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |= GEN8_DE_PORT_HOTPLUG(HPD_PORT_B); - } - if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) { vgpu_vreg_t(vgpu, SFUSE_STRAP) |= - SFUSE_STRAP_DDIC_DETECTED; - vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |= - GEN8_DE_PORT_HOTPLUG(HPD_PORT_C); - } - } else { - if (intel_vgpu_has_monitor_on_port(vgpu, PORT_A)) { + SFUSE_STRAP_DDIB_DETECTED; + } else { vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &= - ~GEN8_DE_PORT_HOTPLUG(HPD_PORT_A); - } - if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) { + ~GEN8_DE_PORT_HOTPLUG(HPD_PORT_B); vgpu_vreg_t(vgpu, SFUSE_STRAP) &= ~SFUSE_STRAP_DDIB_DETECTED; - vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &= - ~GEN8_DE_PORT_HOTPLUG(HPD_PORT_B); } - if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) { - vgpu_vreg_t(vgpu, SFUSE_STRAP) &= - ~SFUSE_STRAP_DDIC_DETECTED; + vgpu_vreg_t(vgpu, GEN8_DE_PORT_IIR) |= + GEN8_DE_PORT_HOTPLUG(HPD_PORT_B); + vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &= + ~PORTB_HOTPLUG_STATUS_MASK; + vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |= + PORTB_HOTPLUG_LONG_DETECT; + intel_vgpu_trigger_virtual_event(vgpu, DP_B_HOTPLUG); + } + if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) { + if (connected) { + vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |= + GEN8_DE_PORT_HOTPLUG(HPD_PORT_C); + vgpu_vreg_t(vgpu, SFUSE_STRAP) |= + SFUSE_STRAP_DDIC_DETECTED; + } else { vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &= ~GEN8_DE_PORT_HOTPLUG(HPD_PORT_C); + vgpu_vreg_t(vgpu, SFUSE_STRAP) &= + ~SFUSE_STRAP_DDIC_DETECTED; } + vgpu_vreg_t(vgpu, GEN8_DE_PORT_IIR) |= + GEN8_DE_PORT_HOTPLUG(HPD_PORT_C); + vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &= + ~PORTC_HOTPLUG_STATUS_MASK; + vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |= + PORTC_HOTPLUG_LONG_DETECT; + intel_vgpu_trigger_virtual_event(vgpu, DP_C_HOTPLUG); } - vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |= - PORTB_HOTPLUG_STATUS_MASK; - intel_vgpu_trigger_virtual_event(vgpu, DP_B_HOTPLUG); } } diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index e49944fde333..cbe5931906e0 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -437,10 +437,9 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, if (ret) goto out_clean_sched_policy; - if (IS_BROADWELL(dev_priv)) + if (IS_BROADWELL(dev_priv) || IS_BROXTON(dev_priv)) ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_B); - /* FixMe: Re-enable APL/BXT once vfio_edid enabled */ - else if (!IS_BROXTON(dev_priv)) + else ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D); if (ret) goto out_clean_sched_policy; diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 93265951fdbb..b0899b665e85 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -1166,7 +1166,7 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj, } } if (IS_ERR(src)) { - unsigned long x, n; + unsigned long x, n, remain; void *ptr; /* @@ -1177,14 +1177,15 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj, * We don't care about copying too much here as we only * validate up to the end of the batch. */ + remain = length; if (!(dst_obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ)) - length = round_up(length, + remain = round_up(remain, boot_cpu_data.x86_clflush_size); ptr = dst; x = offset_in_page(offset); - for (n = offset >> PAGE_SHIFT; length; n++) { - int len = min(length, PAGE_SIZE - x); + for (n = offset >> PAGE_SHIFT; remain; n++) { + int len = min(remain, PAGE_SIZE - x); src = kmap_atomic(i915_gem_object_get_page(src_obj, n)); if (needs_clflush) @@ -1193,13 +1194,15 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj, kunmap_atomic(src); ptr += len; - length -= len; + remain -= len; x = 0; } } i915_gem_object_unpin_pages(src_obj); + memset32(dst + length, 0, (dst_obj->base.size - length) / sizeof(u32)); + /* dst_obj is returned with vmap pinned */ return dst; } @@ -1392,11 +1395,6 @@ static unsigned long *alloc_whitelist(u32 batch_length) #define LENGTH_BIAS 2 -static bool shadow_needs_clflush(struct drm_i915_gem_object *obj) -{ - return !(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE); -} - /** * intel_engine_cmd_parser() - parse a batch buffer for privilege violations * @engine: the engine on which the batch is to execute @@ -1538,16 +1536,9 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, ret = 0; /* allow execution */ } } - - if (shadow_needs_clflush(shadow->obj)) - drm_clflush_virt_range(batch_end, 8); } - if (shadow_needs_clflush(shadow->obj)) { - void *ptr = page_mask_bits(shadow->obj->mm.mapping); - - drm_clflush_virt_range(ptr, (void *)(cmd + 1) - ptr); - } + i915_gem_object_flush_map(shadow->obj); if (!IS_ERR_OR_NULL(jump_whitelist)) kfree(jump_whitelist); diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 320856b665a1..99eb0d7bbc44 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -578,8 +578,6 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) pci_set_master(pdev); - cpu_latency_qos_add_request(&dev_priv->pm_qos, PM_QOS_DEFAULT_VALUE); - intel_gt_init_workarounds(dev_priv); /* On the 945G/GM, the chipset reports the MSI capability on the @@ -626,7 +624,6 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) err_msi: if (pdev->msi_enabled) pci_disable_msi(pdev); - cpu_latency_qos_remove_request(&dev_priv->pm_qos); err_mem_regions: intel_memory_regions_driver_release(dev_priv); err_ggtt: @@ -648,8 +645,6 @@ static void i915_driver_hw_remove(struct drm_i915_private *dev_priv) if (pdev->msi_enabled) pci_disable_msi(pdev); - - cpu_latency_qos_remove_request(&dev_priv->pm_qos); } /** @@ -1052,6 +1047,8 @@ static void intel_shutdown_encoders(struct drm_i915_private *dev_priv) void i915_driver_shutdown(struct drm_i915_private *i915) { + disable_rpm_wakeref_asserts(&i915->runtime_pm); + i915_gem_suspend(i915); drm_kms_helper_poll_disable(&i915->drm); @@ -1065,6 +1062,8 @@ void i915_driver_shutdown(struct drm_i915_private *i915) intel_suspend_encoders(i915); intel_shutdown_encoders(i915); + + enable_rpm_wakeref_asserts(&i915->runtime_pm); } static bool suspend_to_idle(struct drm_i915_private *dev_priv) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 0a3ee4f9dc0a..632c713227dc 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -891,9 +891,6 @@ struct drm_i915_private { bool display_irqs_enabled; - /* To control wakeup latency, e.g. for irq-driven dp aux transfers. */ - struct pm_qos_request pm_qos; - /* Sideband mailbox protection */ struct mutex sb_lock; struct pm_qos_request sb_qos; diff --git a/drivers/gpu/drm/i915/i915_mitigations.c b/drivers/gpu/drm/i915/i915_mitigations.c new file mode 100644 index 000000000000..84f12598d145 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_mitigations.c @@ -0,0 +1,146 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2021 Intel Corporation + */ + +#include <linux/kernel.h> +#include <linux/moduleparam.h> +#include <linux/slab.h> +#include <linux/string.h> + +#include "i915_drv.h" +#include "i915_mitigations.h" + +static unsigned long mitigations __read_mostly = ~0UL; + +enum { + CLEAR_RESIDUALS = 0, +}; + +static const char * const names[] = { + [CLEAR_RESIDUALS] = "residuals", +}; + +bool i915_mitigate_clear_residuals(void) +{ + return READ_ONCE(mitigations) & BIT(CLEAR_RESIDUALS); +} + +static int mitigations_set(const char *val, const struct kernel_param *kp) +{ + unsigned long new = ~0UL; + char *str, *sep, *tok; + bool first = true; + int err = 0; + + BUILD_BUG_ON(ARRAY_SIZE(names) >= BITS_PER_TYPE(mitigations)); + + str = kstrdup(val, GFP_KERNEL); + if (!str) + return -ENOMEM; + + for (sep = str; (tok = strsep(&sep, ","));) { + bool enable = true; + int i; + + /* Be tolerant of leading/trailing whitespace */ + tok = strim(tok); + + if (first) { + first = false; + + if (!strcmp(tok, "auto")) + continue; + + new = 0; + if (!strcmp(tok, "off")) + continue; + } + + if (*tok == '!') { + enable = !enable; + tok++; + } + + if (!strncmp(tok, "no", 2)) { + enable = !enable; + tok += 2; + } + + if (*tok == '\0') + continue; + + for (i = 0; i < ARRAY_SIZE(names); i++) { + if (!strcmp(tok, names[i])) { + if (enable) + new |= BIT(i); + else + new &= ~BIT(i); + break; + } + } + if (i == ARRAY_SIZE(names)) { + pr_err("Bad \"%s.mitigations=%s\", '%s' is unknown\n", + DRIVER_NAME, val, tok); + err = -EINVAL; + break; + } + } + kfree(str); + if (err) + return err; + + WRITE_ONCE(mitigations, new); + return 0; +} + +static int mitigations_get(char *buffer, const struct kernel_param *kp) +{ + unsigned long local = READ_ONCE(mitigations); + int count, i; + bool enable; + + if (!local) + return scnprintf(buffer, PAGE_SIZE, "%s\n", "off"); + + if (local & BIT(BITS_PER_LONG - 1)) { + count = scnprintf(buffer, PAGE_SIZE, "%s,", "auto"); + enable = false; + } else { + enable = true; + count = 0; + } + + for (i = 0; i < ARRAY_SIZE(names); i++) { + if ((local & BIT(i)) != enable) + continue; + + count += scnprintf(buffer + count, PAGE_SIZE - count, + "%s%s,", enable ? "" : "!", names[i]); + } + + buffer[count - 1] = '\n'; + return count; +} + +static const struct kernel_param_ops ops = { + .set = mitigations_set, + .get = mitigations_get, +}; + +module_param_cb_unsafe(mitigations, &ops, NULL, 0600); +MODULE_PARM_DESC(mitigations, +"Selectively enable security mitigations for all Intel® GPUs in the system.\n" +"\n" +" auto -- enables all mitigations required for the platform [default]\n" +" off -- disables all mitigations\n" +"\n" +"Individual mitigations can be enabled by passing a comma-separated string,\n" +"e.g. mitigations=residuals to enable only clearing residuals or\n" +"mitigations=auto,noresiduals to disable only the clear residual mitigation.\n" +"Either '!' or 'no' may be used to switch from enabling the mitigation to\n" +"disabling it.\n" +"\n" +"Active mitigations for Ivybridge, Baytrail, Haswell:\n" +" residuals -- clear all thread-local registers between contexts" +); diff --git a/drivers/gpu/drm/i915/i915_mitigations.h b/drivers/gpu/drm/i915/i915_mitigations.h new file mode 100644 index 000000000000..1359d8135287 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_mitigations.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef __I915_MITIGATIONS_H__ +#define __I915_MITIGATIONS_H__ + +#include <linux/types.h> + +bool i915_mitigate_clear_residuals(void); + +#endif /* __I915_MITIGATIONS_H__ */ |