diff options
Diffstat (limited to 'drivers/gpu/drm/i915/intel_engine_cs.c')
| -rw-r--r-- | drivers/gpu/drm/i915/intel_engine_cs.c | 796 |
1 files changed, 105 insertions, 691 deletions
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index 4ba139c27fba..1a8370779bbb 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -81,13 +81,17 @@ static const struct engine_class_info intel_engine_classes[] = { }, }; +#define MAX_MMIO_BASES 3 struct engine_info { unsigned int hw_id; unsigned int uabi_id; u8 class; u8 instance; - u32 mmio_base; - unsigned irq_shift; + /* mmio bases table *must* be sorted in reverse gen order */ + struct engine_mmio_base { + u32 gen : 8; + u32 base : 24; + } mmio_bases[MAX_MMIO_BASES]; }; static const struct engine_info intel_engines[] = { @@ -96,64 +100,76 @@ static const struct engine_info intel_engines[] = { .uabi_id = I915_EXEC_RENDER, .class = RENDER_CLASS, .instance = 0, - .mmio_base = RENDER_RING_BASE, - .irq_shift = GEN8_RCS_IRQ_SHIFT, + .mmio_bases = { + { .gen = 1, .base = RENDER_RING_BASE } + }, }, [BCS] = { .hw_id = BCS_HW, .uabi_id = I915_EXEC_BLT, .class = COPY_ENGINE_CLASS, .instance = 0, - .mmio_base = BLT_RING_BASE, - .irq_shift = GEN8_BCS_IRQ_SHIFT, + .mmio_bases = { + { .gen = 6, .base = BLT_RING_BASE } + }, }, [VCS] = { .hw_id = VCS_HW, .uabi_id = I915_EXEC_BSD, .class = VIDEO_DECODE_CLASS, .instance = 0, - .mmio_base = GEN6_BSD_RING_BASE, - .irq_shift = GEN8_VCS1_IRQ_SHIFT, + .mmio_bases = { + { .gen = 11, .base = GEN11_BSD_RING_BASE }, + { .gen = 6, .base = GEN6_BSD_RING_BASE }, + { .gen = 4, .base = BSD_RING_BASE } + }, }, [VCS2] = { .hw_id = VCS2_HW, .uabi_id = I915_EXEC_BSD, .class = VIDEO_DECODE_CLASS, .instance = 1, - .mmio_base = GEN8_BSD2_RING_BASE, - .irq_shift = GEN8_VCS2_IRQ_SHIFT, + .mmio_bases = { + { .gen = 11, .base = GEN11_BSD2_RING_BASE }, + { .gen = 8, .base = GEN8_BSD2_RING_BASE } + }, }, [VCS3] = { .hw_id = VCS3_HW, .uabi_id = I915_EXEC_BSD, .class = VIDEO_DECODE_CLASS, .instance = 2, - .mmio_base = GEN11_BSD3_RING_BASE, - .irq_shift = 0, /* not used */ + .mmio_bases = { + { .gen = 11, .base = GEN11_BSD3_RING_BASE } + }, }, [VCS4] = { .hw_id = VCS4_HW, .uabi_id = I915_EXEC_BSD, .class = VIDEO_DECODE_CLASS, .instance = 3, - .mmio_base = GEN11_BSD4_RING_BASE, - .irq_shift = 0, /* not used */ + .mmio_bases = { + { .gen = 11, .base = GEN11_BSD4_RING_BASE } + }, }, [VECS] = { .hw_id = VECS_HW, .uabi_id = I915_EXEC_VEBOX, .class = VIDEO_ENHANCEMENT_CLASS, .instance = 0, - .mmio_base = VEBOX_RING_BASE, - .irq_shift = GEN8_VECS_IRQ_SHIFT, + .mmio_bases = { + { .gen = 11, .base = GEN11_VEBOX_RING_BASE }, + { .gen = 7, .base = VEBOX_RING_BASE } + }, }, [VECS2] = { .hw_id = VECS2_HW, .uabi_id = I915_EXEC_VEBOX, .class = VIDEO_ENHANCEMENT_CLASS, .instance = 1, - .mmio_base = GEN11_VEBOX2_RING_BASE, - .irq_shift = 0, /* not used */ + .mmio_bases = { + { .gen = 11, .base = GEN11_VEBOX2_RING_BASE } + }, }, }; @@ -223,16 +239,36 @@ __intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class) } } +static u32 __engine_mmio_base(struct drm_i915_private *i915, + const struct engine_mmio_base *bases) +{ + int i; + + for (i = 0; i < MAX_MMIO_BASES; i++) + if (INTEL_GEN(i915) >= bases[i].gen) + break; + + GEM_BUG_ON(i == MAX_MMIO_BASES); + GEM_BUG_ON(!bases[i].base); + + return bases[i].base; +} + +static void __sprint_engine_name(char *name, const struct engine_info *info) +{ + WARN_ON(snprintf(name, INTEL_ENGINE_CS_MAX_NAME, "%s%u", + intel_engine_classes[info->class].name, + info->instance) >= INTEL_ENGINE_CS_MAX_NAME); +} + static int intel_engine_setup(struct drm_i915_private *dev_priv, enum intel_engine_id id) { const struct engine_info *info = &intel_engines[id]; - const struct engine_class_info *class_info; struct intel_engine_cs *engine; GEM_BUG_ON(info->class >= ARRAY_SIZE(intel_engine_classes)); - class_info = &intel_engine_classes[info->class]; BUILD_BUG_ON(MAX_ENGINE_CLASS >= BIT(GEN11_ENGINE_CLASS_WIDTH)); BUILD_BUG_ON(MAX_ENGINE_INSTANCE >= BIT(GEN11_ENGINE_INSTANCE_WIDTH)); @@ -253,35 +289,14 @@ intel_engine_setup(struct drm_i915_private *dev_priv, engine->id = id; engine->i915 = dev_priv; - WARN_ON(snprintf(engine->name, sizeof(engine->name), "%s%u", - class_info->name, info->instance) >= - sizeof(engine->name)); + __sprint_engine_name(engine->name, info); engine->hw_id = engine->guc_id = info->hw_id; - if (INTEL_GEN(dev_priv) >= 11) { - switch (engine->id) { - case VCS: - engine->mmio_base = GEN11_BSD_RING_BASE; - break; - case VCS2: - engine->mmio_base = GEN11_BSD2_RING_BASE; - break; - case VECS: - engine->mmio_base = GEN11_VEBOX_RING_BASE; - break; - default: - /* take the original value for all other engines */ - engine->mmio_base = info->mmio_base; - break; - } - } else { - engine->mmio_base = info->mmio_base; - } - engine->irq_shift = info->irq_shift; + engine->mmio_base = __engine_mmio_base(dev_priv, info->mmio_bases); engine->class = info->class; engine->instance = info->instance; engine->uabi_id = info->uabi_id; - engine->uabi_class = class_info->uabi_class; + engine->uabi_class = intel_engine_classes[info->class].uabi_class; engine->context_size = __intel_engine_context_size(dev_priv, engine->class); @@ -441,6 +456,11 @@ static void intel_engine_init_timeline(struct intel_engine_cs *engine) engine->timeline = &engine->i915->gt.global_timeline.engine[engine->id]; } +static void intel_engine_init_batch_pool(struct intel_engine_cs *engine) +{ + i915_gem_batch_pool_init(&engine->batch_pool, engine); +} + static bool csb_force_mmio(struct drm_i915_private *i915) { /* @@ -455,6 +475,9 @@ static bool csb_force_mmio(struct drm_i915_private *i915) if (intel_vgpu_active(i915) && !intel_vgpu_has_hwsp_emulation(i915)) return true; + if (IS_CANNONLAKE(i915)) + return true; + return false; } @@ -485,11 +508,9 @@ static void intel_engine_init_execlist(struct intel_engine_cs *engine) void intel_engine_setup_common(struct intel_engine_cs *engine) { intel_engine_init_execlist(engine); - intel_engine_init_timeline(engine); intel_engine_init_hangcheck(engine); - i915_gem_batch_pool_init(engine, &engine->batch_pool); - + intel_engine_init_batch_pool(engine); intel_engine_init_cmd_parser(engine); } @@ -782,10 +803,24 @@ static inline uint32_t read_subslice_reg(struct drm_i915_private *dev_priv, int slice, int subslice, i915_reg_t reg) { + uint32_t mcr_slice_subslice_mask; + uint32_t mcr_slice_subslice_select; uint32_t mcr; uint32_t ret; enum forcewake_domains fw_domains; + if (INTEL_GEN(dev_priv) >= 11) { + mcr_slice_subslice_mask = GEN11_MCR_SLICE_MASK | + GEN11_MCR_SUBSLICE_MASK; + mcr_slice_subslice_select = GEN11_MCR_SLICE(slice) | + GEN11_MCR_SUBSLICE(subslice); + } else { + mcr_slice_subslice_mask = GEN8_MCR_SLICE_MASK | + GEN8_MCR_SUBSLICE_MASK; + mcr_slice_subslice_select = GEN8_MCR_SLICE(slice) | + GEN8_MCR_SUBSLICE(subslice); + } + fw_domains = intel_uncore_forcewake_for_reg(dev_priv, reg, FW_REG_READ); fw_domains |= intel_uncore_forcewake_for_reg(dev_priv, @@ -800,14 +835,14 @@ read_subslice_reg(struct drm_i915_private *dev_priv, int slice, * The HW expects the slice and sublice selectors to be reset to 0 * after reading out the registers. */ - WARN_ON_ONCE(mcr & (GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK)); - mcr &= ~(GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK); - mcr |= GEN8_MCR_SLICE(slice) | GEN8_MCR_SUBSLICE(subslice); + WARN_ON_ONCE(mcr & mcr_slice_subslice_mask); + mcr &= ~mcr_slice_subslice_mask; + mcr |= mcr_slice_subslice_select; I915_WRITE_FW(GEN8_MCR_SELECTOR, mcr); ret = I915_READ_FW(reg); - mcr &= ~(GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK); + mcr &= ~mcr_slice_subslice_mask; I915_WRITE_FW(GEN8_MCR_SELECTOR, mcr); intel_uncore_forcewake_put__locked(dev_priv, fw_domains); @@ -871,640 +906,6 @@ void intel_engine_get_instdone(struct intel_engine_cs *engine, } } -static int wa_add(struct drm_i915_private *dev_priv, - i915_reg_t addr, - const u32 mask, const u32 val) -{ - const u32 idx = dev_priv->workarounds.count; - - if (WARN_ON(idx >= I915_MAX_WA_REGS)) - return -ENOSPC; - - dev_priv->workarounds.reg[idx].addr = addr; - dev_priv->workarounds.reg[idx].value = val; - dev_priv->workarounds.reg[idx].mask = mask; - - dev_priv->workarounds.count++; - - return 0; -} - -#define WA_REG(addr, mask, val) do { \ - const int r = wa_add(dev_priv, (addr), (mask), (val)); \ - if (r) \ - return r; \ - } while (0) - -#define WA_SET_BIT_MASKED(addr, mask) \ - WA_REG(addr, (mask), _MASKED_BIT_ENABLE(mask)) - -#define WA_CLR_BIT_MASKED(addr, mask) \ - WA_REG(addr, (mask), _MASKED_BIT_DISABLE(mask)) - -#define WA_SET_FIELD_MASKED(addr, mask, value) \ - WA_REG(addr, mask, _MASKED_FIELD(mask, value)) - -static int wa_ring_whitelist_reg(struct intel_engine_cs *engine, - i915_reg_t reg) -{ - struct drm_i915_private *dev_priv = engine->i915; - struct i915_workarounds *wa = &dev_priv->workarounds; - const uint32_t index = wa->hw_whitelist_count[engine->id]; - - if (WARN_ON(index >= RING_MAX_NONPRIV_SLOTS)) - return -EINVAL; - - I915_WRITE(RING_FORCE_TO_NONPRIV(engine->mmio_base, index), - i915_mmio_reg_offset(reg)); - wa->hw_whitelist_count[engine->id]++; - - return 0; -} - -static int gen8_init_workarounds(struct intel_engine_cs *engine) -{ - struct drm_i915_private *dev_priv = engine->i915; - - WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING); - - /* WaDisableAsyncFlipPerfMode:bdw,chv */ - WA_SET_BIT_MASKED(MI_MODE, ASYNC_FLIP_PERF_DISABLE); - - /* WaDisablePartialInstShootdown:bdw,chv */ - WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, - PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE); - - /* Use Force Non-Coherent whenever executing a 3D context. This is a - * workaround for for a possible hang in the unlikely event a TLB - * invalidation occurs during a PSD flush. - */ - /* WaForceEnableNonCoherent:bdw,chv */ - /* WaHdcDisableFetchWhenMasked:bdw,chv */ - WA_SET_BIT_MASKED(HDC_CHICKEN0, - HDC_DONOT_FETCH_MEM_WHEN_MASKED | - HDC_FORCE_NON_COHERENT); - - /* From the Haswell PRM, Command Reference: Registers, CACHE_MODE_0: - * "The Hierarchical Z RAW Stall Optimization allows non-overlapping - * polygons in the same 8x4 pixel/sample area to be processed without - * stalling waiting for the earlier ones to write to Hierarchical Z - * buffer." - * - * This optimization is off by default for BDW and CHV; turn it on. - */ - WA_CLR_BIT_MASKED(CACHE_MODE_0_GEN7, HIZ_RAW_STALL_OPT_DISABLE); - - /* Wa4x4STCOptimizationDisable:bdw,chv */ - WA_SET_BIT_MASKED(CACHE_MODE_1, GEN8_4x4_STC_OPTIMIZATION_DISABLE); - - /* - * BSpec recommends 8x4 when MSAA is used, - * however in practice 16x4 seems fastest. - * - * Note that PS/WM thread counts depend on the WIZ hashing - * disable bit, which we don't touch here, but it's good - * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM). - */ - WA_SET_FIELD_MASKED(GEN7_GT_MODE, - GEN6_WIZ_HASHING_MASK, - GEN6_WIZ_HASHING_16x4); - - return 0; -} - -static int bdw_init_workarounds(struct intel_engine_cs *engine) -{ - struct drm_i915_private *dev_priv = engine->i915; - int ret; - - ret = gen8_init_workarounds(engine); - if (ret) - return ret; - - /* WaDisableThreadStallDopClockGating:bdw (pre-production) */ - WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE); - - /* WaDisableDopClockGating:bdw - * - * Also see the related UCGTCL1 write in broadwell_init_clock_gating() - * to disable EUTC clock gating. - */ - WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2, - DOP_CLOCK_GATING_DISABLE); - - WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3, - GEN8_SAMPLER_POWER_BYPASS_DIS); - - WA_SET_BIT_MASKED(HDC_CHICKEN0, - /* WaForceContextSaveRestoreNonCoherent:bdw */ - HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT | - /* WaDisableFenceDestinationToSLM:bdw (pre-prod) */ - (IS_BDW_GT3(dev_priv) ? HDC_FENCE_DEST_SLM_DISABLE : 0)); - - return 0; -} - -static int chv_init_workarounds(struct intel_engine_cs *engine) -{ - struct drm_i915_private *dev_priv = engine->i915; - int ret; - - ret = gen8_init_workarounds(engine); - if (ret) - return ret; - - /* WaDisableThreadStallDopClockGating:chv */ - WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE); - - /* Improve HiZ throughput on CHV. */ - WA_SET_BIT_MASKED(HIZ_CHICKEN, CHV_HZ_8X8_MODE_IN_1X); - - return 0; -} - -static int gen9_init_workarounds(struct intel_engine_cs *engine) -{ - struct drm_i915_private *dev_priv = engine->i915; - int ret; - - /* WaConextSwitchWithConcurrentTLBInvalidate: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. - */ - 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); - - I915_WRITE(MMCD_MISC_CTRL, - I915_READ(MMCD_MISC_CTRL) | - MMCD_PCLA | - MMCD_HOTSPOT_EN); - } - - /* 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); - - /* WaDisableHDCInvalidation:skl,bxt,kbl,cfl */ - I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | - BDW_DISABLE_HDC_INVALIDATION); - - /* 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); - - /* 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)); - - /* - * 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); - - /* WaVFEStateAfterPipeControlwithMediaStateClear:skl,bxt,glk,cfl */ - ret = wa_ring_whitelist_reg(engine, GEN9_CTX_PREEMPT_REG); - if (ret) - return ret; - - /* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl,cfl,[cnl] */ - I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1, - _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL)); - ret = wa_ring_whitelist_reg(engine, GEN8_CS_CHICKEN1); - if (ret) - return ret; - - /* WaAllowUMDToModifyHDCChicken1:skl,bxt,kbl,glk,cfl */ - ret = wa_ring_whitelist_reg(engine, GEN8_HDC_CHICKEN1); - if (ret) - return ret; - - return 0; -} - -static int skl_tune_iz_hashing(struct intel_engine_cs *engine) -{ - struct drm_i915_private *dev_priv = engine->i915; - u8 vals[3] = { 0, 0, 0 }; - unsigned int i; - - for (i = 0; i < 3; i++) { - u8 ss; - - /* - * Only consider slices where one, and only one, subslice has 7 - * EUs - */ - if (!is_power_of_2(INTEL_INFO(dev_priv)->sseu.subslice_7eu[i])) - continue; - - /* - * subslice_7eu[i] != 0 (because of the check above) and - * ss_max == 4 (maximum number of subslices possible per slice) - * - * -> 0 <= ss <= 3; - */ - ss = ffs(INTEL_INFO(dev_priv)->sseu.subslice_7eu[i]) - 1; - vals[i] = 3 - ss; - } - - if (vals[0] == 0 && vals[1] == 0 && vals[2] == 0) - return 0; - - /* Tune IZ hashing. See intel_device_info_runtime_init() */ - WA_SET_FIELD_MASKED(GEN7_GT_MODE, - GEN9_IZ_HASHING_MASK(2) | - GEN9_IZ_HASHING_MASK(1) | - GEN9_IZ_HASHING_MASK(0), - GEN9_IZ_HASHING(2, vals[2]) | - GEN9_IZ_HASHING(1, vals[1]) | - GEN9_IZ_HASHING(0, vals[0])); - - return 0; -} - -static int skl_init_workarounds(struct intel_engine_cs *engine) -{ - struct drm_i915_private *dev_priv = engine->i915; - int ret; - - ret = gen9_init_workarounds(engine); - if (ret) - return ret; - - /* WaEnableGapsTsvCreditFix:skl */ - I915_WRITE(GEN8_GARBCNTL, (I915_READ(GEN8_GARBCNTL) | - GEN9_GAPS_TSV_CREDIT_DISABLE)); - - /* WaDisableGafsUnitClkGating:skl */ - I915_WRITE(GEN7_UCGCTL4, (I915_READ(GEN7_UCGCTL4) | - GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE)); - - /* WaInPlaceDecompressionHang:skl */ - if (IS_SKL_REVID(dev_priv, SKL_REVID_H0, REVID_FOREVER)) - I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, - (I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS)); - - /* WaDisableLSQCROPERFforOCL:skl */ - ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4); - if (ret) - return ret; - - return skl_tune_iz_hashing(engine); -} - -static int bxt_init_workarounds(struct intel_engine_cs *engine) -{ - struct drm_i915_private *dev_priv = engine->i915; - int ret; - - ret = gen9_init_workarounds(engine); - if (ret) - return ret; - - /* WaDisableThreadStallDopClockGating:bxt */ - WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, - STALL_DOP_GATING_DISABLE); - - /* WaDisablePooledEuLoadBalancingFix:bxt */ - I915_WRITE(FF_SLICE_CS_CHICKEN2, - _MASKED_BIT_ENABLE(GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE)); - - /* WaToEnableHwFixForPushConstHWBug:bxt */ - WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, - GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); - - /* WaInPlaceDecompressionHang:bxt */ - I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, - (I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS)); - - return 0; -} - -static int cnl_init_workarounds(struct intel_engine_cs *engine) -{ - struct drm_i915_private *dev_priv = engine->i915; - int ret; - - /* WaDisableI2mCycleOnWRPort:cnl (pre-prod) */ - if (IS_CNL_REVID(dev_priv, CNL_REVID_B0, CNL_REVID_B0)) - I915_WRITE(GAMT_CHKN_BIT_REG, - (I915_READ(GAMT_CHKN_BIT_REG) | - GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT)); - - /* WaForceContextSaveRestoreNonCoherent:cnl */ - WA_SET_BIT_MASKED(CNL_HDC_CHICKEN0, - HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT); - - /* WaThrottleEUPerfToAvoidTDBackPressure:cnl(pre-prod) */ - if (IS_CNL_REVID(dev_priv, CNL_REVID_B0, CNL_REVID_B0)) - WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, THROTTLE_12_5); - - /* WaDisableReplayBufferBankArbitrationOptimization:cnl */ - WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, - GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); - - /* WaDisableEnhancedSBEVertexCaching:cnl (pre-prod) */ - if (IS_CNL_REVID(dev_priv, 0, CNL_REVID_B0)) - WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, - GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE); - - /* WaInPlaceDecompressionHang:cnl */ - I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, - (I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS)); - - /* WaPushConstantDereferenceHoldDisable:cnl */ - WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2, PUSH_CONSTANT_DEREF_DISABLE); - - /* FtrEnableFastAnisoL1BankingFix: cnl */ - WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3, CNL_FAST_ANISO_L1_BANKING_FIX); - - /* WaDisable3DMidCmdPreemption:cnl */ - WA_CLR_BIT_MASKED(GEN8_CS_CHICKEN1, GEN9_PREEMPT_3D_OBJECT_LEVEL); - - /* WaDisableGPGPUMidCmdPreemption:cnl */ - WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1, GEN9_PREEMPT_GPGPU_LEVEL_MASK, - GEN9_PREEMPT_GPGPU_COMMAND_LEVEL); - - /* WaEnablePreemptionGranularityControlByUMD:cnl */ - I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1, - _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL)); - ret= wa_ring_whitelist_reg(engine, GEN8_CS_CHICKEN1); - if (ret) - return ret; - - /* WaDisableEarlyEOT:cnl */ - WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, DISABLE_EARLY_EOT); - - return 0; -} - -static int kbl_init_workarounds(struct intel_engine_cs *engine) -{ - struct drm_i915_private *dev_priv = engine->i915; - int ret; - - ret = gen9_init_workarounds(engine); - if (ret) - return ret; - - /* WaEnableGapsTsvCreditFix:kbl */ - I915_WRITE(GEN8_GARBCNTL, (I915_READ(GEN8_GARBCNTL) | - GEN9_GAPS_TSV_CREDIT_DISABLE)); - - /* WaDisableDynamicCreditSharing:kbl */ - if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0)) - I915_WRITE(GAMT_CHKN_BIT_REG, - (I915_READ(GAMT_CHKN_BIT_REG) | - GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING)); - - /* WaDisableFenceDestinationToSLM:kbl (pre-prod) */ - if (IS_KBL_REVID(dev_priv, KBL_REVID_A0, KBL_REVID_A0)) - WA_SET_BIT_MASKED(HDC_CHICKEN0, - HDC_FENCE_DEST_SLM_DISABLE); - - /* WaToEnableHwFixForPushConstHWBug:kbl */ - if (IS_KBL_REVID(dev_priv, KBL_REVID_C0, REVID_FOREVER)) - WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, - GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); - - /* WaDisableGafsUnitClkGating:kbl */ - I915_WRITE(GEN7_UCGCTL4, (I915_READ(GEN7_UCGCTL4) | - GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE)); - - /* WaDisableSbeCacheDispatchPortSharing:kbl */ - WA_SET_BIT_MASKED( - GEN7_HALF_SLICE_CHICKEN1, - GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE); - - /* WaInPlaceDecompressionHang:kbl */ - I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, - (I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS)); - - /* WaDisableLSQCROPERFforOCL:kbl */ - ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4); - if (ret) - return ret; - - return 0; -} - -static int glk_init_workarounds(struct intel_engine_cs *engine) -{ - struct drm_i915_private *dev_priv = engine->i915; - int ret; - - ret = gen9_init_workarounds(engine); - if (ret) - return ret; - - /* WA #0862: Userspace has to set "Barrier Mode" to avoid hangs. */ - ret = wa_ring_whitelist_reg(engine, GEN9_SLICE_COMMON_ECO_CHICKEN1); - if (ret) - return ret; - - /* WaToEnableHwFixForPushConstHWBug:glk */ - WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, - GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); - - return 0; -} - -static int cfl_init_workarounds(struct intel_engine_cs *engine) -{ - struct drm_i915_private *dev_priv = engine->i915; - int ret; - - ret = gen9_init_workarounds(engine); - if (ret) - return ret; - - /* WaEnableGapsTsvCreditFix:cfl */ - I915_WRITE(GEN8_GARBCNTL, (I915_READ(GEN8_GARBCNTL) | - GEN9_GAPS_TSV_CREDIT_DISABLE)); - - /* WaToEnableHwFixForPushConstHWBug:cfl */ - WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, - GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); - - /* WaDisableGafsUnitClkGating:cfl */ - I915_WRITE(GEN7_UCGCTL4, (I915_READ(GEN7_UCGCTL4) | - GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE)); - - /* WaDisableSbeCacheDispatchPortSharing:cfl */ - WA_SET_BIT_MASKED( - GEN7_HALF_SLICE_CHICKEN1, - GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE); - - /* WaInPlaceDecompressionHang:cfl */ - I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, - (I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS)); - - return 0; -} - -int init_workarounds_ring(struct intel_engine_cs *engine) -{ - struct drm_i915_private *dev_priv = engine->i915; - int err; - - if (GEM_WARN_ON(engine->id != RCS)) - return -EINVAL; - - dev_priv->workarounds.count = 0; - dev_priv->workarounds.hw_whitelist_count[engine->id] = 0; - - if (IS_BROADWELL(dev_priv)) - err = bdw_init_workarounds(engine); - else if (IS_CHERRYVIEW(dev_priv)) - err = chv_init_workarounds(engine); - else if (IS_SKYLAKE(dev_priv)) - err = skl_init_workarounds(engine); - else if (IS_BROXTON(dev_priv)) - err = bxt_init_workarounds(engine); - else if (IS_KABYLAKE(dev_priv)) - err = kbl_init_workarounds(engine); - else if (IS_GEMINILAKE(dev_priv)) - err = glk_init_workarounds(engine); - else if (IS_COFFEELAKE(dev_priv)) - err = cfl_init_workarounds(engine); - else if (IS_CANNONLAKE(dev_priv)) - err = cnl_init_workarounds(engine); - else - err = 0; - if (err) - return err; - - DRM_DEBUG_DRIVER("%s: Number of context specific w/a: %d\n", - engine->name, dev_priv->workarounds.count); - return 0; -} - -int intel_ring_workarounds_emit(struct i915_request *rq) -{ - struct i915_workarounds *w = &rq->i915->workarounds; - u32 *cs; - int ret, i; - - if (w->count == 0) - return 0; - - ret = rq->engine->emit_flush(rq, EMIT_BARRIER); - if (ret) - return ret; - - cs = intel_ring_begin(rq, w->count * 2 + 2); - if (IS_ERR(cs)) - return PTR_ERR(cs); - - *cs++ = MI_LOAD_REGISTER_IMM(w->count); - for (i = 0; i < w->count; i++) { - *cs++ = i915_mmio_reg_offset(w->reg[i].addr); - *cs++ = w->reg[i].value; - } - *cs++ = MI_NOOP; - - intel_ring_advance(rq, cs); - - ret = rq->engine->emit_flush(rq, EMIT_BARRIER); - if (ret) - return ret; - - return 0; -} - static bool ring_is_idle(struct intel_engine_cs *engine) { struct drm_i915_private *dev_priv = engine->i915; @@ -1655,6 +1056,9 @@ void intel_engines_park(struct drm_i915_private *i915) intel_engine_dump(engine, &p, NULL); } + /* Must be reset upon idling, or we may miss the busy wakeup. */ + GEM_BUG_ON(engine->execlists.queue_priority != INT_MIN); + if (engine->park) engine->park(engine); @@ -1713,13 +1117,15 @@ static void print_request(struct drm_printer *m, struct i915_request *rq, const char *prefix) { + const char *name = rq->fence.ops->get_timeline_name(&rq->fence); + drm_printf(m, "%s%x%s [%llx:%x] prio=%d @ %dms: %s\n", prefix, rq->global_seqno, i915_request_completed(rq) ? "!" : "", rq->fence.context, rq->fence.seqno, rq->priotree.priority, jiffies_to_msecs(jiffies - rq->emitted_jiffies), - rq->timeline->common->name); + name); } static void hexdump(struct drm_printer *m, const void *buf, size_t len) @@ -1825,12 +1231,15 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine, ptr = I915_READ(RING_CONTEXT_STATUS_PTR(engine)); read = GEN8_CSB_READ_PTR(ptr); write = GEN8_CSB_WRITE_PTR(ptr); - drm_printf(m, "\tExeclist CSB read %d [%d cached], write %d [%d from hws], interrupt posted? %s\n", + drm_printf(m, "\tExeclist CSB read %d [%d cached], write %d [%d from hws], interrupt posted? %s, tasklet queued? %s (%s)\n", read, execlists->csb_head, write, intel_read_status_page(engine, intel_hws_csb_write_index(engine->i915)), yesno(test_bit(ENGINE_IRQ_EXECLIST, - &engine->irq_posted))); + &engine->irq_posted)), + yesno(test_bit(TASKLET_STATE_SCHED, + &engine->execlists.tasklet.state)), + enableddisabled(!atomic_read(&engine->execlists.tasklet.count))); if (read >= GEN8_CSB_ENTRIES) read = 0; if (write >= GEN8_CSB_ENTRIES) @@ -1929,12 +1338,16 @@ void intel_engine_dump(struct intel_engine_cs *engine, 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); - drm_printf(m, "\t\tring->start: 0x%08x\n", + drm_printf(m, "\t\tring->start: 0x%08x\n", i915_ggtt_offset(rq->ring->vma)); - drm_printf(m, "\t\tring->head: 0x%08x\n", + drm_printf(m, "\t\tring->head: 0x%08x\n", rq->ring->head); - drm_printf(m, "\t\tring->tail: 0x%08x\n", + drm_printf(m, "\t\tring->tail: 0x%08x\n", rq->ring->tail); + drm_printf(m, "\t\tring->emit: 0x%08x\n", + rq->ring->emit); + drm_printf(m, "\t\tring->space: 0x%08x\n", + rq->ring->space); } rcu_read_unlock(); @@ -2109,4 +1522,5 @@ void intel_disable_engine_stats(struct intel_engine_cs *engine) #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "selftests/mock_engine.c" +#include "selftests/intel_engine_cs.c" #endif |