static void guc_prepare_xfer(struct intel_guc *guc)
{
struct drm_i915_private *dev_priv = guc_to_i915(guc);
/* Must program this register before loading the ucode with DMA */
I915_WRITE(GUC_SHIM_CONTROL, GUC_DISABLE_SRAM_INIT_TO_ZEROES |
GUC_ENABLE_READ_CACHE_LOGIC |
GUC_ENABLE_MIA_CACHING |
GUC_ENABLE_READ_CACHE_FOR_SRAM_DATA |
GUC_ENABLE_READ_CACHE_FOR_WOPCM_DATA |
GUC_ENABLE_MIA_CLOCK_GATING);
if (IS_GEN9_LP(dev_priv))
I915_WRITE(GEN9LP_GT_PM_CONFIG, GT_DOORBELL_ENABLE);
else
I915_WRITE(GEN9_GT_PM_CONFIG, GT_DOORBELL_ENABLE);
if (IS_GEN(dev_priv, 9)) {
/* DOP Clock Gating Enable for GuC clocks */
I915_WRITE(GEN7_MISCCPCTL, (GEN8_DOP_CLOCK_GATE_GUC_ENABLE |
I915_READ(GEN7_MISCCPCTL)));
/* allows for 5us (in 10ns units) before GT can go to RC6 */
I915_WRITE(GUC_ARAT_C6DIS, 0x1FF);
}
}
static void gen9_gt_workarounds_apply(struct drm_i915_private *dev_priv)
{
/* WaContextSwitchWithConcurrentTLBInvalidate:skl,bxt,kbl,glk,cfl */
I915_WRITE(GEN9_CSFE_CHICKEN1_RCS,
_MASKED_BIT_ENABLE(GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE));
/* WaEnableLbsSlaRetryTimerDecrement:skl,bxt,kbl,glk,cfl */
I915_WRITE(BDW_SCRATCH1, I915_READ(BDW_SCRATCH1) |
GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE);
/* WaDisableKillLogic:bxt,skl,kbl */
if (!IS_COFFEELAKE(dev_priv))
I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
ECOCHK_DIS_TLB);
if (HAS_LLC(dev_priv)) {
/* WaCompressedResourceSamplerPbeMediaNewHashMode:skl,kbl
*
* Must match Display Engine. See
* WaCompressedResourceDisplayNewHashMode.
*/
I915_WRITE(MMCD_MISC_CTRL,
I915_READ(MMCD_MISC_CTRL) |
MMCD_PCLA |
MMCD_HOTSPOT_EN);
}
/* WaDisableHDCInvalidation:skl,bxt,kbl,cfl */
I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
BDW_DISABLE_HDC_INVALIDATION);
/* WaProgramL3SqcReg1DefaultForPerf:bxt,glk */
if (IS_GEN9_LP(dev_priv)) {
u32 val = I915_READ(GEN8_L3SQCREG1);
val &= ~L3_PRIO_CREDITS_MASK;
val |= L3_GENERAL_PRIO_CREDITS(62) | L3_HIGH_PRIO_CREDITS(2);
I915_WRITE(GEN8_L3SQCREG1, val);
}
/* WaOCLCoherentLineFlush:skl,bxt,kbl,cfl */
I915_WRITE(GEN8_L3SQCREG4,
I915_READ(GEN8_L3SQCREG4) | GEN8_LQSC_FLUSH_COHERENT_LINES);
/* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl,cfl,[cnl] */
I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1,
_MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL));
}
static void gen9_set_dc_state_debugmask(struct drm_i915_private *dev_priv)
{
u32 val, mask;
mask = DC_STATE_DEBUG_MASK_MEMORY_UP;
if (IS_GEN9_LP(dev_priv))
mask |= DC_STATE_DEBUG_MASK_CORES;
/* The below bit doesn't need to be cleared ever afterwards */
val = I915_READ(DC_STATE_DEBUG);
if ((val & mask) != mask) {
val |= mask;
I915_WRITE(DC_STATE_DEBUG, val);
POSTING_READ(DC_STATE_DEBUG);
}
}
static int intel_dp_mst_compute_config(struct intel_encoder *encoder,
struct intel_crtc_state *pipe_config,
struct drm_connector_state *conn_state)
{
struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
struct intel_dp *intel_dp = &intel_mst->primary->dp;
struct intel_connector *connector =
to_intel_connector(conn_state->connector);
struct intel_digital_connector_state *intel_conn_state =
to_intel_digital_connector_state(conn_state);
const struct drm_display_mode *adjusted_mode =
&pipe_config->base.adjusted_mode;
void *port = connector->port;
struct link_config_limits limits;
int ret;
if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
return -EINVAL;
pipe_config->output_format = INTEL_OUTPUT_FORMAT_RGB;
pipe_config->has_pch_encoder = false;
if (intel_conn_state->force_audio == HDMI_AUDIO_AUTO)
pipe_config->has_audio =
drm_dp_mst_port_has_audio(&intel_dp->mst_mgr, port);
else
pipe_config->has_audio =
intel_conn_state->force_audio == HDMI_AUDIO_ON;
/*
* for MST we always configure max link bw - the spec doesn't
* seem to suggest we should do otherwise.
*/
limits.min_clock =
limits.max_clock = intel_dp_max_link_rate(intel_dp);
limits.min_lane_count =
limits.max_lane_count = intel_dp_max_lane_count(intel_dp);
limits.min_bpp = intel_dp_min_bpp(pipe_config);
limits.max_bpp = pipe_config->pipe_bpp;
intel_dp_adjust_compliance_config(intel_dp, pipe_config, &limits);
ret = intel_dp_mst_compute_link_config(encoder, pipe_config,
conn_state, &limits);
if (ret)
return ret;
pipe_config->limited_color_range =
intel_dp_limited_color_range(pipe_config, conn_state);
if (IS_GEN9_LP(dev_priv))
pipe_config->lane_lat_optim_mask =
bxt_ddi_phy_calc_lane_lat_optim_mask(pipe_config->lane_count);
intel_ddi_compute_min_voltage_level(dev_priv, pipe_config);
return 0;
}
static int gen9_ctx_workarounds_init(struct drm_i915_private *dev_priv)
{
if (HAS_LLC(dev_priv)) {
/* WaCompressedResourceSamplerPbeMediaNewHashMode:skl,kbl
*
* Must match Display Engine. See
* WaCompressedResourceDisplayNewHashMode.
*/
WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
GEN9_PBE_COMPRESSED_HASH_SELECTION);
WA_SET_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN7,
GEN9_SAMPLER_HASH_COMPRESSED_READ_ADDR);
}
/* WaClearFlowControlGpgpuContextSave:skl,bxt,kbl,glk,cfl */
/* WaDisablePartialInstShootdown:skl,bxt,kbl,glk,cfl */
WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
FLOW_CONTROL_ENABLE |
PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE);
/* Syncing dependencies between camera and graphics:skl,bxt,kbl */
if (!IS_COFFEELAKE(dev_priv))
WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC);
/* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt,kbl,glk,cfl */
/* WaEnableSamplerGPGPUPreemptionSupport:skl,bxt,kbl,cfl */
WA_SET_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN7,
GEN9_ENABLE_YV12_BUGFIX |
GEN9_ENABLE_GPGPU_PREEMPTION);
/* Wa4x4STCOptimizationDisable:skl,bxt,kbl,glk,cfl */
/* WaDisablePartialResolveInVc:skl,bxt,kbl,cfl */
WA_SET_BIT_MASKED(CACHE_MODE_1,
GEN8_4x4_STC_OPTIMIZATION_DISABLE |
GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE);
/* WaCcsTlbPrefetchDisable:skl,bxt,kbl,glk,cfl */
WA_CLR_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN5,
GEN9_CCS_TLB_PREFETCH_ENABLE);
/* WaForceContextSaveRestoreNonCoherent:skl,bxt,kbl,cfl */
WA_SET_BIT_MASKED(HDC_CHICKEN0,
HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT |
HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE);
/* WaForceEnableNonCoherent and WaDisableHDCInvalidation are
* both tied to WaForceContextSaveRestoreNonCoherent
* in some hsds for skl. We keep the tie for all gen9. The
* documentation is a bit hazy and so we want to get common behaviour,
* even though there is no clear evidence we would need both on kbl/bxt.
* This area has been source of system hangs so we play it safe
* and mimic the skl regardless of what bspec says.
*
* Use Force Non-Coherent whenever executing a 3D context. This
* is a workaround for a possible hang in the unlikely event
* a TLB invalidation occurs during a PSD flush.
*/
/* WaForceEnableNonCoherent:skl,bxt,kbl,cfl */
WA_SET_BIT_MASKED(HDC_CHICKEN0,
HDC_FORCE_NON_COHERENT);
/* WaDisableSamplerPowerBypassForSOPingPong:skl,bxt,kbl,cfl */
if (IS_SKYLAKE(dev_priv) ||
IS_KABYLAKE(dev_priv) ||
IS_COFFEELAKE(dev_priv))
WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
GEN8_SAMPLER_POWER_BYPASS_DIS);
/* WaDisableSTUnitPowerOptimization:skl,bxt,kbl,glk,cfl */
WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN2, GEN8_ST_PO_DISABLE);
/*
* Supporting preemption with fine-granularity requires changes in the
* batch buffer programming. Since we can't break old userspace, we
* need to set our default preemption level to safe value. Userspace is
* still able to use more fine-grained preemption levels, since in
* WaEnablePreemptionGranularityControlByUMD we're whitelisting the
* per-ctx register. As such, WaDisable{3D,GPGPU}MidCmdPreemption are
* not real HW workarounds, but merely a way to start using preemption
* while maintaining old contract with userspace.
*/
/* WaDisable3DMidCmdPreemption:skl,bxt,glk,cfl,[cnl] */
WA_CLR_BIT_MASKED(GEN8_CS_CHICKEN1, GEN9_PREEMPT_3D_OBJECT_LEVEL);
/* WaDisableGPGPUMidCmdPreemption:skl,bxt,blk,cfl,[cnl] */
WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1,
GEN9_PREEMPT_GPGPU_LEVEL_MASK,
GEN9_PREEMPT_GPGPU_COMMAND_LEVEL);
/* WaClearHIZ_WM_CHICKEN3:bxt,glk */
if (IS_GEN9_LP(dev_priv))
WA_SET_BIT_MASKED(GEN9_WM_CHICKEN3, GEN9_FACTOR_IN_CLR_VAL_HIZ);
return 0;
}
static bool intel_dp_mst_compute_config(struct intel_encoder *encoder,
struct intel_crtc_state *pipe_config,
struct drm_connector_state *conn_state)
{
struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
struct intel_digital_port *intel_dig_port = intel_mst->primary;
struct intel_dp *intel_dp = &intel_dig_port->dp;
struct intel_connector *connector =
to_intel_connector(conn_state->connector);
struct drm_atomic_state *state = pipe_config->base.state;
int bpp;
int lane_count, slots;
const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
int mst_pbn;
bool reduce_m_n = drm_dp_has_quirk(&intel_dp->desc,
DP_DPCD_QUIRK_LIMITED_M_N);
if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
return false;
pipe_config->has_pch_encoder = false;
bpp = 24;
if (intel_dp->compliance.test_data.bpc) {
bpp = intel_dp->compliance.test_data.bpc * 3;
DRM_DEBUG_KMS("Setting pipe bpp to %d\n",
bpp);
}
/*
* for MST we always configure max link bw - the spec doesn't
* seem to suggest we should do otherwise.
*/
lane_count = intel_dp_max_lane_count(intel_dp);
pipe_config->lane_count = lane_count;
pipe_config->pipe_bpp = bpp;
pipe_config->port_clock = intel_dp_max_link_rate(intel_dp);
if (drm_dp_mst_port_has_audio(&intel_dp->mst_mgr, connector->port))
pipe_config->has_audio = true;
mst_pbn = drm_dp_calc_pbn_mode(adjusted_mode->crtc_clock, bpp);
pipe_config->pbn = mst_pbn;
slots = drm_dp_atomic_find_vcpi_slots(state, &intel_dp->mst_mgr,
connector->port, mst_pbn);
if (slots < 0) {
DRM_DEBUG_KMS("failed finding vcpi slots:%d\n", slots);
return false;
}
intel_link_compute_m_n(bpp, lane_count,
adjusted_mode->crtc_clock,
pipe_config->port_clock,
&pipe_config->dp_m_n,
reduce_m_n);
pipe_config->dp_m_n.tu = slots;
if (IS_GEN9_LP(dev_priv))
pipe_config->lane_lat_optim_mask =
bxt_ddi_phy_calc_lane_lat_optim_mask(pipe_config->lane_count);
intel_ddi_compute_min_voltage_level(dev_priv, pipe_config);
return true;
}
