diff options
Diffstat (limited to 'drivers/gpu/drm/i915/gt/intel_workarounds.c')
| -rw-r--r-- | drivers/gpu/drm/i915/gt/intel_workarounds.c | 713 |
1 files changed, 467 insertions, 246 deletions
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index a821e3d405db..2afb4f80a954 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -4,6 +4,7 @@ */ #include "i915_drv.h" +#include "i915_reg.h" #include "intel_context.h" #include "intel_engine_pm.h" #include "intel_engine_regs.h" @@ -17,46 +18,68 @@ /** * DOC: Hardware workarounds * - * This file is intended as a central place to implement most [1]_ of the - * required workarounds for hardware to work as originally intended. They fall - * in five basic categories depending on how/when they are applied: + * Hardware workarounds are register programming documented to be executed in + * the driver that fall outside of the normal programming sequences for a + * platform. There are some basic categories of workarounds, depending on + * how/when they are applied: * - * - Workarounds that touch registers that are saved/restored to/from the HW - * context image. The list is emitted (via Load Register Immediate commands) - * everytime a new context is created. - * - GT workarounds. The list of these WAs is applied whenever these registers - * revert to default values (on GPU reset, suspend/resume [2]_, etc..). - * - Display workarounds. The list is applied during display clock-gating - * initialization. - * - Workarounds that whitelist a privileged register, so that UMDs can manage - * them directly. This is just a special case of a MMMIO workaround (as we - * write the list of these to/be-whitelisted registers to some special HW - * registers). - * - Workaround batchbuffers, that get executed automatically by the hardware - * on every HW context restore. + * - Context workarounds: workarounds that touch registers that are + * saved/restored to/from the HW context image. The list is emitted (via Load + * Register Immediate commands) once when initializing the device and saved in + * the default context. That default context is then used on every context + * creation to have a "primed golden context", i.e. a context image that + * already contains the changes needed to all the registers. * - * .. [1] Please notice that there are other WAs that, due to their nature, - * cannot be applied from a central place. Those are peppered around the rest - * of the code, as needed. + * - Engine workarounds: the list of these WAs is applied whenever the specific + * engine is reset. It's also possible that a set of engine classes share a + * common power domain and they are reset together. This happens on some + * platforms with render and compute engines. In this case (at least) one of + * them need to keeep the workaround programming: the approach taken in the + * driver is to tie those workarounds to the first compute/render engine that + * is registered. When executing with GuC submission, engine resets are + * outside of kernel driver control, hence the list of registers involved in + * written once, on engine initialization, and then passed to GuC, that + * saves/restores their values before/after the reset takes place. See + * ``drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c`` for reference. * - * .. [2] Technically, some registers are powercontext saved & restored, so they - * survive a suspend/resume. In practice, writing them again is not too - * costly and simplifies things. We can revisit this in the future. + * - GT workarounds: the list of these WAs is applied whenever these registers + * revert to their default values: on GPU reset, suspend/resume [1]_, etc. + * + * - Register whitelist: some workarounds need to be implemented in userspace, + * but need to touch privileged registers. The whitelist in the kernel + * instructs the hardware to allow the access to happen. From the kernel side, + * this is just a special case of a MMIO workaround (as we write the list of + * these to/be-whitelisted registers to some special HW registers). + * + * - Workaround batchbuffers: buffers that get executed automatically by the + * hardware on every HW context restore. These buffers are created and + * programmed in the default context so the hardware always go through those + * programming sequences when switching contexts. The support for workaround + * batchbuffers is enabled these hardware mechanisms: * - * Layout - * ~~~~~~ + * #. INDIRECT_CTX: A batchbuffer and an offset are provided in the default + * context, pointing the hardware to jump to that location when that offset + * is reached in the context restore. Workaround batchbuffer in the driver + * currently uses this mechanism for all platforms. * - * Keep things in this file ordered by WA type, as per the above (context, GT, - * display, register whitelist, batchbuffer). Then, inside each type, keep the - * following order: + * #. BB_PER_CTX_PTR: A batchbuffer is provided in the default context, + * pointing the hardware to a buffer to continue executing after the + * engine registers are restored in a context restore sequence. This is + * currently not used in the driver. * - * - Infrastructure functions and macros - * - WAs per platform in standard gen/chrono order - * - Public functions to init or apply the given workaround type. + * - Other: There are WAs that, due to their nature, cannot be applied from a + * central place. Those are peppered around the rest of the code, as needed. + * Workarounds related to the display IP are the main example. + * + * .. [1] Technically, some registers are powercontext saved & restored, so they + * survive a suspend/resume. In practice, writing them again is not too + * costly and simplifies things, so it's the approach taken in the driver. */ -static void wa_init_start(struct i915_wa_list *wal, const char *name, const char *engine_name) +static void wa_init_start(struct i915_wa_list *wal, struct intel_gt *gt, + const char *name, const char *engine_name) { + wal->gt = gt; wal->name = name; wal->engine_name = engine_name; } @@ -80,13 +103,14 @@ static void wa_init_finish(struct i915_wa_list *wal) if (!wal->count) return; - DRM_DEBUG_DRIVER("Initialized %u %s workarounds on %s\n", - wal->wa_count, wal->name, wal->engine_name); + drm_dbg(&wal->gt->i915->drm, "Initialized %u %s workarounds on %s\n", + wal->wa_count, wal->name, wal->engine_name); } static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa) { unsigned int addr = i915_mmio_reg_offset(wa->reg); + struct drm_i915_private *i915 = wal->gt->i915; unsigned int start = 0, end = wal->count; const unsigned int grow = WA_LIST_CHUNK; struct i915_wa *wa_; @@ -99,7 +123,7 @@ static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa) list = kmalloc_array(ALIGN(wal->count + 1, grow), sizeof(*wa), GFP_KERNEL); if (!list) { - DRM_ERROR("No space for workaround init!\n"); + drm_err(&i915->drm, "No space for workaround init!\n"); return; } @@ -122,9 +146,10 @@ static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa) wa_ = &wal->list[mid]; if ((wa->clr | wa_->clr) && !(wa->clr & ~wa_->clr)) { - DRM_ERROR("Discarding overwritten w/a for reg %04x (clear: %08x, set: %08x)\n", - i915_mmio_reg_offset(wa_->reg), - wa_->clr, wa_->set); + drm_err(&i915->drm, + "Discarding overwritten w/a for reg %04x (clear: %08x, set: %08x)\n", + i915_mmio_reg_offset(wa_->reg), + wa_->clr, wa_->set); wa_->set &= ~wa->clr; } @@ -166,6 +191,21 @@ static void wa_add(struct i915_wa_list *wal, i915_reg_t reg, _wa_add(wal, &wa); } +static void wa_mcr_add(struct i915_wa_list *wal, i915_mcr_reg_t reg, + u32 clear, u32 set, u32 read_mask, bool masked_reg) +{ + struct i915_wa wa = { + .mcr_reg = reg, + .clr = clear, + .set = set, + .read = read_mask, + .masked_reg = masked_reg, + .is_mcr = 1, + }; + + _wa_add(wal, &wa); +} + static void wa_write_clr_set(struct i915_wa_list *wal, i915_reg_t reg, u32 clear, u32 set) { @@ -173,6 +213,12 @@ wa_write_clr_set(struct i915_wa_list *wal, i915_reg_t reg, u32 clear, u32 set) } static void +wa_mcr_write_clr_set(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 clear, u32 set) +{ + wa_mcr_add(wal, reg, clear, set, clear, false); +} + +static void wa_write(struct i915_wa_list *wal, i915_reg_t reg, u32 set) { wa_write_clr_set(wal, reg, ~0, set); @@ -185,11 +231,23 @@ wa_write_or(struct i915_wa_list *wal, i915_reg_t reg, u32 set) } static void +wa_mcr_write_or(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 set) +{ + wa_mcr_write_clr_set(wal, reg, set, set); +} + +static void wa_write_clr(struct i915_wa_list *wal, i915_reg_t reg, u32 clr) { wa_write_clr_set(wal, reg, clr, 0); } +static void +wa_mcr_write_clr(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 clr) +{ + wa_mcr_write_clr_set(wal, reg, clr, 0); +} + /* * WA operations on "masked register". A masked register has the upper 16 bits * documented as "masked" in b-spec. Its purpose is to allow writing to just a @@ -208,18 +266,37 @@ wa_masked_en(struct i915_wa_list *wal, i915_reg_t reg, u32 val) } static void +wa_mcr_masked_en(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 val) +{ + wa_mcr_add(wal, reg, 0, _MASKED_BIT_ENABLE(val), val, true); +} + +static void wa_masked_dis(struct i915_wa_list *wal, i915_reg_t reg, u32 val) { wa_add(wal, reg, 0, _MASKED_BIT_DISABLE(val), val, true); } static void +wa_mcr_masked_dis(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 val) +{ + wa_mcr_add(wal, reg, 0, _MASKED_BIT_DISABLE(val), val, true); +} + +static void wa_masked_field_set(struct i915_wa_list *wal, i915_reg_t reg, u32 mask, u32 val) { wa_add(wal, reg, 0, _MASKED_FIELD(mask, val), mask, true); } +static void +wa_mcr_masked_field_set(struct i915_wa_list *wal, i915_mcr_reg_t reg, + u32 mask, u32 val) +{ + wa_mcr_add(wal, reg, 0, _MASKED_FIELD(mask, val), mask, true); +} + static void gen6_ctx_workarounds_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) { @@ -241,8 +318,8 @@ static void gen8_ctx_workarounds_init(struct intel_engine_cs *engine, wa_masked_en(wal, RING_MI_MODE(RENDER_RING_BASE), ASYNC_FLIP_PERF_DISABLE); /* WaDisablePartialInstShootdown:bdw,chv */ - wa_masked_en(wal, GEN8_ROW_CHICKEN, - PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE); + wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN, + PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE); /* Use Force Non-Coherent whenever executing a 3D context. This is a * workaround for a possible hang in the unlikely event a TLB @@ -288,18 +365,18 @@ static void bdw_ctx_workarounds_init(struct intel_engine_cs *engine, gen8_ctx_workarounds_init(engine, wal); /* WaDisableThreadStallDopClockGating:bdw (pre-production) */ - wa_masked_en(wal, GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE); + wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE); /* WaDisableDopClockGating:bdw * * Also see the related UCGTCL1 write in bdw_init_clock_gating() * to disable EUTC clock gating. */ - wa_masked_en(wal, GEN7_ROW_CHICKEN2, - DOP_CLOCK_GATING_DISABLE); + wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN2, + DOP_CLOCK_GATING_DISABLE); - wa_masked_en(wal, HALF_SLICE_CHICKEN3, - GEN8_SAMPLER_POWER_BYPASS_DIS); + wa_mcr_masked_en(wal, GEN8_HALF_SLICE_CHICKEN3, + GEN8_SAMPLER_POWER_BYPASS_DIS); wa_masked_en(wal, HDC_CHICKEN0, /* WaForceContextSaveRestoreNonCoherent:bdw */ @@ -314,7 +391,7 @@ static void chv_ctx_workarounds_init(struct intel_engine_cs *engine, gen8_ctx_workarounds_init(engine, wal); /* WaDisableThreadStallDopClockGating:chv */ - wa_masked_en(wal, GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE); + wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE); /* Improve HiZ throughput on CHV. */ wa_masked_en(wal, HIZ_CHICKEN, CHV_HZ_8X8_MODE_IN_1X); @@ -333,21 +410,21 @@ static void gen9_ctx_workarounds_init(struct intel_engine_cs *engine, */ wa_masked_en(wal, COMMON_SLICE_CHICKEN2, GEN9_PBE_COMPRESSED_HASH_SELECTION); - wa_masked_en(wal, GEN9_HALF_SLICE_CHICKEN7, - GEN9_SAMPLER_HASH_COMPRESSED_READ_ADDR); + wa_mcr_masked_en(wal, GEN9_HALF_SLICE_CHICKEN7, + GEN9_SAMPLER_HASH_COMPRESSED_READ_ADDR); } /* WaClearFlowControlGpgpuContextSave:skl,bxt,kbl,glk,cfl */ /* WaDisablePartialInstShootdown:skl,bxt,kbl,glk,cfl */ - wa_masked_en(wal, GEN8_ROW_CHICKEN, - FLOW_CONTROL_ENABLE | - PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE); + wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN, + FLOW_CONTROL_ENABLE | + PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE); /* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt,kbl,glk,cfl */ /* WaEnableSamplerGPGPUPreemptionSupport:skl,bxt,kbl,cfl */ - wa_masked_en(wal, GEN9_HALF_SLICE_CHICKEN7, - GEN9_ENABLE_YV12_BUGFIX | - GEN9_ENABLE_GPGPU_PREEMPTION); + wa_mcr_masked_en(wal, GEN9_HALF_SLICE_CHICKEN7, + GEN9_ENABLE_YV12_BUGFIX | + GEN9_ENABLE_GPGPU_PREEMPTION); /* Wa4x4STCOptimizationDisable:skl,bxt,kbl,glk,cfl */ /* WaDisablePartialResolveInVc:skl,bxt,kbl,cfl */ @@ -356,8 +433,8 @@ static void gen9_ctx_workarounds_init(struct intel_engine_cs *engine, GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE); /* WaCcsTlbPrefetchDisable:skl,bxt,kbl,glk,cfl */ - wa_masked_dis(wal, GEN9_HALF_SLICE_CHICKEN5, - GEN9_CCS_TLB_PREFETCH_ENABLE); + wa_mcr_masked_dis(wal, GEN9_HALF_SLICE_CHICKEN5, + GEN9_CCS_TLB_PREFETCH_ENABLE); /* WaForceContextSaveRestoreNonCoherent:skl,bxt,kbl,cfl */ wa_masked_en(wal, HDC_CHICKEN0, @@ -386,11 +463,11 @@ static void gen9_ctx_workarounds_init(struct intel_engine_cs *engine, IS_KABYLAKE(i915) || IS_COFFEELAKE(i915) || IS_COMETLAKE(i915)) - wa_masked_en(wal, HALF_SLICE_CHICKEN3, - GEN8_SAMPLER_POWER_BYPASS_DIS); + wa_mcr_masked_en(wal, GEN8_HALF_SLICE_CHICKEN3, + GEN8_SAMPLER_POWER_BYPASS_DIS); /* WaDisableSTUnitPowerOptimization:skl,bxt,kbl,glk,cfl */ - wa_masked_en(wal, HALF_SLICE_CHICKEN2, GEN8_ST_PO_DISABLE); + wa_mcr_masked_en(wal, HALF_SLICE_CHICKEN2, GEN8_ST_PO_DISABLE); /* * Supporting preemption with fine-granularity requires changes in the @@ -469,8 +546,8 @@ static void bxt_ctx_workarounds_init(struct intel_engine_cs *engine, gen9_ctx_workarounds_init(engine, wal); /* WaDisableThreadStallDopClockGating:bxt */ - wa_masked_en(wal, GEN8_ROW_CHICKEN, - STALL_DOP_GATING_DISABLE); + wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN, + STALL_DOP_GATING_DISABLE); /* WaToEnableHwFixForPushConstHWBug:bxt */ wa_masked_en(wal, COMMON_SLICE_CHICKEN2, @@ -490,8 +567,8 @@ static void kbl_ctx_workarounds_init(struct intel_engine_cs *engine, GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); /* WaDisableSbeCacheDispatchPortSharing:kbl */ - wa_masked_en(wal, GEN7_HALF_SLICE_CHICKEN1, - GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE); + wa_mcr_masked_en(wal, GEN8_HALF_SLICE_CHICKEN1, + GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE); } static void glk_ctx_workarounds_init(struct intel_engine_cs *engine, @@ -514,8 +591,8 @@ static void cfl_ctx_workarounds_init(struct intel_engine_cs *engine, GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); /* WaDisableSbeCacheDispatchPortSharing:cfl */ - wa_masked_en(wal, GEN7_HALF_SLICE_CHICKEN1, - GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE); + wa_mcr_masked_en(wal, GEN8_HALF_SLICE_CHICKEN1, + GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE); } static void icl_ctx_workarounds_init(struct intel_engine_cs *engine, @@ -534,13 +611,13 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine, * (the register is whitelisted in hardware now, so UMDs can opt in * for coherency if they have a good reason). */ - wa_masked_en(wal, ICL_HDC_MODE, HDC_FORCE_NON_COHERENT); + wa_mcr_masked_en(wal, ICL_HDC_MODE, HDC_FORCE_NON_COHERENT); /* WaEnableFloatBlendOptimization:icl */ - wa_add(wal, GEN10_CACHE_MODE_SS, 0, - _MASKED_BIT_ENABLE(FLOAT_BLEND_OPTIMIZATION_ENABLE), - 0 /* write-only, so skip validation */, - true); + wa_mcr_add(wal, GEN10_CACHE_MODE_SS, 0, + _MASKED_BIT_ENABLE(FLOAT_BLEND_OPTIMIZATION_ENABLE), + 0 /* write-only, so skip validation */, + true); /* WaDisableGPGPUMidThreadPreemption:icl */ wa_masked_field_set(wal, GEN8_CS_CHICKEN1, @@ -548,8 +625,8 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine, GEN9_PREEMPT_GPGPU_THREAD_GROUP_LEVEL); /* allow headerless messages for preemptible GPGPU context */ - wa_masked_en(wal, GEN10_SAMPLER_MODE, - GEN11_SAMPLER_ENABLE_HEADLESS_MSG); + wa_mcr_masked_en(wal, GEN10_SAMPLER_MODE, + GEN11_SAMPLER_ENABLE_HEADLESS_MSG); /* Wa_1604278689:icl,ehl */ wa_write(wal, IVB_FBC_RT_BASE, 0xFFFFFFFF & ~ILK_FBC_RT_VALID); @@ -558,7 +635,7 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine, 0xFFFFFFFF); /* Wa_1406306137:icl,ehl */ - wa_masked_en(wal, GEN9_ROW_CHICKEN4, GEN11_DIS_PICK_2ND_EU); + wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN4, GEN11_DIS_PICK_2ND_EU); } /* @@ -569,13 +646,13 @@ static void dg2_ctx_gt_tuning_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) { wa_masked_en(wal, CHICKEN_RASTER_2, TBIMR_FAST_CLIP); - wa_write_clr_set(wal, GEN11_L3SQCREG5, L3_PWM_TIMER_INIT_VAL_MASK, - REG_FIELD_PREP(L3_PWM_TIMER_INIT_VAL_MASK, 0x7f)); - wa_add(wal, - FF_MODE2, - FF_MODE2_TDS_TIMER_MASK, - FF_MODE2_TDS_TIMER_128, - 0, false); + wa_mcr_write_clr_set(wal, XEHP_L3SQCREG5, L3_PWM_TIMER_INIT_VAL_MASK, + REG_FIELD_PREP(L3_PWM_TIMER_INIT_VAL_MASK, 0x7f)); + wa_mcr_add(wal, + XEHP_FF_MODE2, + FF_MODE2_TDS_TIMER_MASK, + FF_MODE2_TDS_TIMER_128, + 0, false); } /* @@ -599,7 +676,7 @@ static void gen12_ctx_gt_tuning_init(struct intel_engine_cs *engine, * verification is ignored. */ wa_add(wal, - FF_MODE2, + GEN12_FF_MODE2, FF_MODE2_TDS_TIMER_MASK, FF_MODE2_TDS_TIMER_128, 0, false); @@ -608,6 +685,8 @@ static void gen12_ctx_gt_tuning_init(struct intel_engine_cs *engine, static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) { + struct drm_i915_private *i915 = engine->i915; + gen12_ctx_gt_tuning_init(engine, wal); /* @@ -637,10 +716,14 @@ static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine, * to Wa_1608008084. */ wa_add(wal, - FF_MODE2, + GEN12_FF_MODE2, FF_MODE2_GS_TIMER_MASK, FF_MODE2_GS_TIMER_224, 0, false); + + if (!IS_DG1(i915)) + /* Wa_1806527549 */ + wa_masked_en(wal, HIZ_CHICKEN, HZ_DEPTH_TEST_LE_GE_OPT_DISABLE); } static void dg1_ctx_workarounds_init(struct intel_engine_cs *engine, @@ -664,27 +747,27 @@ static void dg2_ctx_workarounds_init(struct intel_engine_cs *engine, /* Wa_16011186671:dg2_g11 */ if (IS_DG2_GRAPHICS_STEP(engine->i915, G11, STEP_A0, STEP_B0)) { - wa_masked_dis(wal, VFLSKPD, DIS_MULT_MISS_RD_SQUASH); - wa_masked_en(wal, VFLSKPD, DIS_OVER_FETCH_CACHE); + wa_mcr_masked_dis(wal, VFLSKPD, DIS_MULT_MISS_RD_SQUASH); + wa_mcr_masked_en(wal, VFLSKPD, DIS_OVER_FETCH_CACHE); } if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0)) { /* Wa_14010469329:dg2_g10 */ - wa_masked_en(wal, GEN11_COMMON_SLICE_CHICKEN3, - XEHP_DUAL_SIMD8_SEQ_MERGE_DISABLE); + wa_mcr_masked_en(wal, XEHP_COMMON_SLICE_CHICKEN3, + XEHP_DUAL_SIMD8_SEQ_MERGE_DISABLE); /* * Wa_22010465075:dg2_g10 * Wa_22010613112:dg2_g10 * Wa_14010698770:dg2_g10 */ - wa_masked_en(wal, GEN11_COMMON_SLICE_CHICKEN3, - GEN12_DISABLE_CPS_AWARE_COLOR_PIPE); + wa_mcr_masked_en(wal, XEHP_COMMON_SLICE_CHICKEN3, + GEN12_DISABLE_CPS_AWARE_COLOR_PIPE); } /* Wa_16013271637:dg2 */ - wa_masked_en(wal, SLICE_COMMON_ECO_CHICKEN1, - MSC_MSAA_REODER_BUF_BYPASS_DISABLE); + wa_mcr_masked_en(wal, XEHP_SLICE_COMMON_ECO_CHICKEN1, + MSC_MSAA_REODER_BUF_BYPASS_DISABLE); /* Wa_14014947963:dg2 */ if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_B0, STEP_FOREVER) || @@ -768,7 +851,7 @@ __intel_engine_init_ctx_wa(struct intel_engine_cs *engine, { struct drm_i915_private *i915 = engine->i915; - wa_init_start(wal, name, engine->name); + wa_init_start(wal, engine->gt, name, engine->name); /* Applies to all engines */ /* @@ -1076,18 +1159,23 @@ static void __set_mcr_steering(struct i915_wa_list *wal, wa_write_clr_set(wal, steering_reg, mcr_mask, mcr); } -static void __add_mcr_wa(struct intel_gt *gt, struct i915_wa_list *wal, - unsigned int slice, unsigned int subslice) +static void debug_dump_steering(struct intel_gt *gt) { struct drm_printer p = drm_debug_printer("MCR Steering:"); + if (drm_debug_enabled(DRM_UT_DRIVER)) + intel_gt_mcr_report_steering(&p, gt, false); +} + +static void __add_mcr_wa(struct intel_gt *gt, struct i915_wa_list *wal, + unsigned int slice, unsigned int subslice) +{ __set_mcr_steering(wal, GEN8_MCR_SELECTOR, slice, subslice); gt->default_steering.groupid = slice; gt->default_steering.instanceid = subslice; - if (drm_debug_enabled(DRM_UT_DRIVER)) - intel_gt_mcr_report_steering(&p, gt, false); + debug_dump_steering(gt); } static void @@ -1181,6 +1269,9 @@ xehp_init_mcr(struct intel_gt *gt, struct i915_wa_list *wal) gt->steering_table[MSLICE] = NULL; } + if (IS_XEHPSDV(gt->i915) && slice_mask & BIT(0)) + gt->steering_table[GAM] = NULL; + slice = __ffs(slice_mask); subslice = intel_sseu_find_first_xehp_dss(sseu, GEN_DSS_PER_GSLICE, slice) % GEN_DSS_PER_GSLICE; @@ -1198,6 +1289,13 @@ xehp_init_mcr(struct intel_gt *gt, struct i915_wa_list *wal) */ __set_mcr_steering(wal, MCFG_MCR_SELECTOR, 0, 2); __set_mcr_steering(wal, SF_MCR_SELECTOR, 0, 2); + + /* + * On DG2, GAM registers have a dedicated steering control register + * and must always be programmed to a hardcoded groupid of "1." + */ + if (IS_DG2(gt->i915)) + __set_mcr_steering(wal, GAM_MCR_SELECTOR, 1, 0); } static void @@ -1254,22 +1352,22 @@ icl_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) PSDUNIT_CLKGATE_DIS); /* Wa_1406680159:icl,ehl */ - wa_write_or(wal, - SUBSLICE_UNIT_LEVEL_CLKGATE, - GWUNIT_CLKGATE_DIS); + wa_mcr_write_or(wal, + GEN11_SUBSLICE_UNIT_LEVEL_CLKGATE, + GWUNIT_CLKGATE_DIS); /* Wa_1607087056:icl,ehl,jsl */ if (IS_ICELAKE(i915) || IS_JSL_EHL_GRAPHICS_STEP(i915, STEP_A0, STEP_B0)) wa_write_or(wal, - SLICE_UNIT_LEVEL_CLKGATE, + GEN11_SLICE_UNIT_LEVEL_CLKGATE, L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS); /* * This is not a documented workaround, but rather an optimization * to reduce sampler power. */ - wa_write_clr(wal, GEN10_DFR_RATIO_EN_AND_CHICKEN, DFR_DISABLE); + wa_mcr_write_clr(wal, GEN10_DFR_RATIO_EN_AND_CHICKEN, DFR_DISABLE); } /* @@ -1303,7 +1401,7 @@ gen12_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) wa_14011060649(gt, wal); /* Wa_14011059788:tgl,rkl,adl-s,dg1,adl-p */ - wa_write_or(wal, GEN10_DFR_RATIO_EN_AND_CHICKEN, DFR_DISABLE); + wa_mcr_write_or(wal, GEN10_DFR_RATIO_EN_AND_CHICKEN, DFR_DISABLE); } static void @@ -1315,14 +1413,14 @@ tgl_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) /* Wa_1409420604:tgl */ if (IS_TGL_UY_GRAPHICS_STEP(i915, STEP_A0, STEP_B0)) - wa_write_or(wal, - SUBSLICE_UNIT_LEVEL_CLKGATE2, - CPSSUNIT_CLKGATE_DIS); + wa_mcr_write_or(wal, + SUBSLICE_UNIT_LEVEL_CLKGATE2, + CPSSUNIT_CLKGATE_DIS); /* Wa_1607087056:tgl also know as BUG:1409180338 */ if (IS_TGL_UY_GRAPHICS_STEP(i915, STEP_A0, STEP_B0)) wa_write_or(wal, - SLICE_UNIT_LEVEL_CLKGATE, + GEN11_SLICE_UNIT_LEVEL_CLKGATE, L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS); /* Wa_1408615072:tgl[a0] */ @@ -1341,14 +1439,14 @@ dg1_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) /* Wa_1607087056:dg1 */ if (IS_DG1_GRAPHICS_STEP(i915, STEP_A0, STEP_B0)) wa_write_or(wal, - SLICE_UNIT_LEVEL_CLKGATE, + GEN11_SLICE_UNIT_LEVEL_CLKGATE, L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS); /* Wa_1409420604:dg1 */ if (IS_DG1(i915)) - wa_write_or(wal, - SUBSLICE_UNIT_LEVEL_CLKGATE2, - CPSSUNIT_CLKGATE_DIS); + wa_mcr_write_or(wal, + SUBSLICE_UNIT_LEVEL_CLKGATE2, + CPSSUNIT_CLKGATE_DIS); /* Wa_1408615072:dg1 */ /* Empirical testing shows this register is unaffected by engine reset. */ @@ -1365,7 +1463,7 @@ xehpsdv_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) xehp_init_mcr(gt, wal); /* Wa_1409757795:xehpsdv */ - wa_write_or(wal, SCCGCTL94DC, CG3DDISURB); + wa_mcr_write_or(wal, SCCGCTL94DC, CG3DDISURB); /* Wa_16011155590:xehpsdv */ if (IS_XEHPSDV_GRAPHICS_STEP(i915, STEP_A0, STEP_B0)) @@ -1445,8 +1543,8 @@ dg2_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) CG3DDISCFEG_CLKGATE_DIS); /* Wa_14011006942:dg2 */ - wa_write_or(wal, SUBSLICE_UNIT_LEVEL_CLKGATE, - DSS_ROUTER_CLKGATE_DIS); + wa_mcr_write_or(wal, GEN11_SUBSLICE_UNIT_LEVEL_CLKGATE, + DSS_ROUTER_CLKGATE_DIS); } if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_B0)) { @@ -1457,7 +1555,7 @@ dg2_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) wa_write_or(wal, UNSLCGCTL9444, LTCDD_CLKGATE_DIS); /* Wa_14011371254:dg2_g10 */ - wa_write_or(wal, SLICE_UNIT_LEVEL_CLKGATE, NODEDSS_CLKGATE_DIS); + wa_mcr_write_or(wal, XEHP_SLICE_UNIT_LEVEL_CLKGATE, NODEDSS_CLKGATE_DIS); /* Wa_14011431319:dg2_g10 */ wa_write_or(wal, UNSLCGCTL9440, GAMTLBOACS_CLKGATE_DIS | @@ -1493,21 +1591,21 @@ dg2_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) GAMEDIA_CLKGATE_DIS); /* Wa_14011028019:dg2_g10 */ - wa_write_or(wal, SSMCGCTL9530, RTFUNIT_CLKGATE_DIS); + wa_mcr_write_or(wal, SSMCGCTL9530, RTFUNIT_CLKGATE_DIS); } /* Wa_14014830051:dg2 */ - wa_write_clr(wal, SARB_CHICKEN1, COMP_CKN_IN); + wa_mcr_write_clr(wal, SARB_CHICKEN1, COMP_CKN_IN); /* * The following are not actually "workarounds" but rather * recommended tuning settings documented in the bspec's * performance guide section. */ - wa_write_or(wal, GEN12_SQCM, EN_32B_ACCESS); + wa_mcr_write_or(wal, XEHP_SQCM, EN_32B_ACCESS); /* Wa_14015795083 */ - wa_write_clr(wal, GEN7_MISCCPCTL, GEN12_DOP_CLOCK_GATE_RENDER_ENABLE); + wa_mcr_write_clr(wal, GEN8_MISCCPCTL, GEN12_DOP_CLOCK_GATE_RENDER_ENABLE); } static void @@ -1516,7 +1614,27 @@ pvc_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) pvc_init_mcr(gt, wal); /* Wa_14015795083 */ - wa_write_clr(wal, GEN7_MISCCPCTL, GEN12_DOP_CLOCK_GATE_RENDER_ENABLE); + wa_mcr_write_clr(wal, GEN8_MISCCPCTL, GEN12_DOP_CLOCK_GATE_RENDER_ENABLE); +} + +static void +xelpg_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) +{ + /* FIXME: Actual workarounds will be added in future patch(es) */ + + /* + * Unlike older platforms, we no longer setup implicit steering here; + * all MCR accesses are explicitly steered. + */ + debug_dump_steering(gt); +} + +static void +xelpmp_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) +{ + /* FIXME: Actual workarounds will be added in future patch(es) */ + + debug_dump_steering(gt); } static void @@ -1524,7 +1642,18 @@ gt_init_workarounds(struct intel_gt *gt, struct i915_wa_list *wal) { struct drm_i915_private *i915 = gt->i915; - if (IS_PONTEVECCHIO(i915)) + if (gt->type == GT_MEDIA) { + if (MEDIA_VER(i915) >= 13) + xelpmp_gt_workarounds_init(gt, wal); + else + MISSING_CASE(MEDIA_VER(i915)); + + return; + } + + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) + xelpg_gt_workarounds_init(gt, wal); + else if (IS_PONTEVECCHIO(i915)) pvc_gt_workarounds_init(gt, wal); else if (IS_DG2(i915)) dg2_gt_workarounds_init(gt, wal); @@ -1572,7 +1701,7 @@ void intel_gt_init_workarounds(struct intel_gt *gt) { struct i915_wa_list *wal = >->wa_list; - wa_init_start(wal, "GT", "global"); + wa_init_start(wal, gt, "GT", "global"); gt_init_workarounds(gt, wal); wa_init_finish(wal); } @@ -1594,12 +1723,14 @@ wal_get_fw_for_rmw(struct intel_uncore *uncore, const struct i915_wa_list *wal) } static bool -wa_verify(const struct i915_wa *wa, u32 cur, const char *name, const char *from) +wa_verify(struct intel_gt *gt, const struct i915_wa *wa, u32 cur, + const char *name, const char *from) { if ((cur ^ wa->set) & wa->read) { - DRM_ERROR("%s workaround lost on %s! (reg[%x]=0x%x, relevant bits were 0x%x vs expected 0x%x)\n", - name, from, i915_mmio_reg_offset(wa->reg), - cur, cur & wa->read, wa->set & wa->read); + drm_err(>->i915->drm, + "%s workaround lost on %s! (reg[%x]=0x%x, relevant bits were 0x%x vs expected 0x%x)\n", + name, from, i915_mmio_reg_offset(wa->reg), + cur, cur & wa->read, wa->set & wa->read); return false; } @@ -1607,9 +1738,9 @@ wa_verify(const struct i915_wa *wa, u32 cur, const char *name, const char *from) return true; } -static void -wa_list_apply(struct intel_gt *gt, const struct i915_wa_list *wal) +static void wa_list_apply(const struct i915_wa_list *wal) { + struct intel_gt *gt = wal->gt; struct intel_uncore *uncore = gt->uncore; enum forcewake_domains fw; unsigned long flags; @@ -1628,14 +1759,25 @@ wa_list_apply(struct intel_gt *gt, const struct i915_wa_list *wal) u32 val, old = 0; /* open-coded rmw due to steering */ - old = wa->clr ? intel_gt_mcr_read_any_fw(gt, wa->reg) : 0; + if (wa->clr) + old = wa->is_mcr ? + intel_gt_mcr_read_any_fw(gt, wa->mcr_reg) : + intel_uncore_read_fw(uncore, wa->reg); val = (old & ~wa->clr) | wa->set; - if (val != old || !wa->clr) - intel_uncore_write_fw(uncore, wa->reg, val); + if (val != old || !wa->clr) { + if (wa->is_mcr) + intel_gt_mcr_multicast_write_fw(gt, wa->mcr_reg, val); + else + intel_uncore_write_fw(uncore, wa->reg, val); + } + + if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)) { + u32 val = wa->is_mcr ? + intel_gt_mcr_read_any_fw(gt, wa->mcr_reg) : + intel_uncore_read_fw(uncore, wa->reg); - if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)) - wa_verify(wa, intel_gt_mcr_read_any_fw(gt, wa->reg), - wal->name, "application"); + wa_verify(gt, wa, val, wal->name, "application"); + } } intel_uncore_forcewake_put__locked(uncore, fw); @@ -1644,7 +1786,7 @@ wa_list_apply(struct intel_gt *gt, const struct i915_wa_list *wal) void intel_gt_apply_workarounds(struct intel_gt *gt) { - wa_list_apply(gt, >->wa_list); + wa_list_apply(>->wa_list); } static bool wa_list_verify(struct intel_gt *gt, @@ -1664,8 +1806,9 @@ static bool wa_list_verify(struct intel_gt *gt, intel_uncore_forcewake_get__locked(uncore, fw); for (i = 0, wa = wal->list; i < wal->count; i++, wa++) - ok &= wa_verify(wa, - intel_gt_mcr_read_any_fw(gt, wa->reg), + ok &= wa_verify(wal->gt, wa, wa->is_mcr ? + intel_gt_mcr_read_any_fw(gt, wa->mcr_reg) : + intel_uncore_read_fw(uncore, wa->reg), wal->name, from); intel_uncore_forcewake_put__locked(uncore, fw); @@ -1712,11 +1855,35 @@ whitelist_reg_ext(struct i915_wa_list *wal, i915_reg_t reg, u32 flags) } static void +whitelist_mcr_reg_ext(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 flags) +{ + struct i915_wa wa = { + .mcr_reg = reg, + .is_mcr = 1, + }; + + if (GEM_DEBUG_WARN_ON(wal->count >= RING_MAX_NONPRIV_SLOTS)) + return; + + if (GEM_DEBUG_WARN_ON(!is_nonpriv_flags_valid(flags))) + return; + + wa.mcr_reg.reg |= flags; + _wa_add(wal, &wa); +} + +static void whitelist_reg(struct i915_wa_list *wal, i915_reg_t reg) { whitelist_reg_ext(wal, reg, RING_FORCE_TO_NONPRIV_ACCESS_RW); } +static void +whitelist_mcr_reg(struct i915_wa_list *wal, i915_mcr_reg_t reg) +{ + whitelist_mcr_reg_ext(wal, reg, RING_FORCE_TO_NONPRIV_ACCESS_RW); +} + static void gen9_whitelist_build(struct i915_wa_list *w) { /* WaVFEStateAfterPipeControlwithMediaStateClear:skl,bxt,glk,cfl */ @@ -1742,7 +1909,7 @@ static void skl_whitelist_build(struct intel_engine_cs *engine) gen9_whitelist_build(w); /* WaDisableLSQCROPERFforOCL:skl */ - whitelist_reg(w, GEN8_L3SQCREG4); + whitelist_mcr_reg(w, GEN8_L3SQCREG4); } static void bxt_whitelist_build(struct intel_engine_cs *engine) @@ -1763,7 +1930,7 @@ static void kbl_whitelist_build(struct intel_engine_cs *engine) gen9_whitelist_build(w); /* WaDisableLSQCROPERFforOCL:kbl */ - whitelist_reg(w, GEN8_L3SQCREG4); + whitelist_mcr_reg(w, GEN8_L3SQCREG4); } static void glk_whitelist_build(struct intel_engine_cs *engine) @@ -1828,10 +1995,10 @@ static void icl_whitelist_build(struct intel_engine_cs *engine) switch (engine->class) { case RENDER_CLASS: /* WaAllowUMDToModifyHalfSliceChicken7:icl */ - whitelist_reg(w, GEN9_HALF_SLICE_CHICKEN7); + whitelist_mcr_reg(w, GEN9_HALF_SLICE_CHICKEN7); /* WaAllowUMDToModifySamplerMode:icl */ - whitelist_reg(w, GEN10_SAMPLER_MODE); + whitelist_mcr_reg(w, GEN10_SAMPLER_MODE); /* WaEnableStateCacheRedirectToCS:icl */ whitelist_reg(w, GEN9_SLICE_COMMON_ECO_CHICKEN1); @@ -1987,7 +2154,7 @@ void intel_engine_init_whitelist(struct intel_engine_cs *engine) struct drm_i915_private *i915 = engine->i915; struct i915_wa_list *w = &engine->whitelist; - wa_init_start(w, "whitelist", engine->name); + wa_init_start(w, engine->gt, "whitelist", engine->name); if (IS_PONTEVECCHIO(i915)) pvc_whitelist_build(engine); @@ -2107,24 +2274,21 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) if (IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0)) { /* Wa_14013392000:dg2_g11 */ - wa_masked_en(wal, GEN7_ROW_CHICKEN2, GEN12_ENABLE_LARGE_GRF_MODE); - - /* Wa_16011620976:dg2_g11 */ - wa_write_or(wal, LSC_CHICKEN_BIT_0_UDW, DIS_CHAIN_2XSIMD8); + wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN2, GEN12_ENABLE_LARGE_GRF_MODE); } if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_FOREVER) || IS_DG2_G11(i915) || IS_DG2_G12(i915)) { /* Wa_1509727124:dg2 */ - wa_masked_en(wal, GEN10_SAMPLER_MODE, - SC_DISABLE_POWER_OPTIMIZATION_EBB); + wa_mcr_masked_en(wal, GEN10_SAMPLER_MODE, + SC_DISABLE_POWER_OPTIMIZATION_EBB); } if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0) || IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0)) { /* Wa_14012419201:dg2 */ - wa_masked_en(wal, GEN9_ROW_CHICKEN4, - GEN12_DISABLE_HDR_PAST_PAYLOAD_HOLD_FIX); + wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN4, + GEN12_DISABLE_HDR_PAST_PAYLOAD_HOLD_FIX); } if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_C0) || @@ -2133,13 +2297,13 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) * Wa_22012826095:dg2 * Wa_22013059131:dg2 */ - wa_write_clr_set(wal, LSC_CHICKEN_BIT_0_UDW, - MAXREQS_PER_BANK, - REG_FIELD_PREP(MAXREQS_PER_BANK, 2)); + wa_mcr_write_clr_set(wal, LSC_CHICKEN_BIT_0_UDW, + MAXREQS_PER_BANK, + REG_FIELD_PREP(MAXREQS_PER_BANK, 2)); /* Wa_22013059131:dg2 */ - wa_write_or(wal, LSC_CHICKEN_BIT_0, - FORCE_1_SUB_MESSAGE_PER_FRAGMENT); + wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0, + FORCE_1_SUB_MESSAGE_PER_FRAGMENT); } /* Wa_1308578152:dg2_g10 when first gslice is fused off */ @@ -2152,19 +2316,19 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_FOREVER) || IS_DG2_G11(i915) || IS_DG2_G12(i915)) { /* Wa_22013037850:dg2 */ - wa_write_or(wal, LSC_CHICKEN_BIT_0_UDW, - DISABLE_128B_EVICTION_COMMAND_UDW); + wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0_UDW, + DISABLE_128B_EVICTION_COMMAND_UDW); /* Wa_22012856258:dg2 */ - wa_masked_en(wal, GEN7_ROW_CHICKEN2, - GEN12_DISABLE_READ_SUPPRESSION); + wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN2, + GEN12_DISABLE_READ_SUPPRESSION); /* * Wa_22010960976:dg2 * Wa_14013347512:dg2 */ - wa_masked_dis(wal, GEN12_HDC_CHICKEN0, - LSC_L1_FLUSH_CTL_3D_DATAPORT_FLUSH_EVENTS_MASK); + wa_mcr_masked_dis(wal, XEHP_HDC_CHICKEN0, + LSC_L1_FLUSH_CTL_3D_DATAPORT_FLUSH_EVENTS_MASK); } if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) { @@ -2172,8 +2336,8 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) * Wa_1608949956:dg2_g10 * Wa_14010198302:dg2_g10 */ - wa_masked_en(wal, GEN8_ROW_CHICKEN, - MDQ_ARBITRATION_MODE | UGM_BACKUP_MODE); + wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN, + MDQ_ARBITRATION_MODE | UGM_BACKUP_MODE); /* * Wa_14010918519:dg2_g10 @@ -2181,31 +2345,31 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) * LSC_CHICKEN_BIT_0 always reads back as 0 is this stepping, * so ignoring verification. */ - wa_add(wal, LSC_CHICKEN_BIT_0_UDW, 0, - FORCE_SLM_FENCE_SCOPE_TO_TILE | FORCE_UGM_FENCE_SCOPE_TO_TILE, - 0, false); + wa_mcr_add(wal, LSC_CHICKEN_BIT_0_UDW, 0, + FORCE_SLM_FENCE_SCOPE_TO_TILE | FORCE_UGM_FENCE_SCOPE_TO_TILE, + 0, false); } if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) { /* Wa_22010430635:dg2 */ - wa_masked_en(wal, - GEN9_ROW_CHICKEN4, - GEN12_DISABLE_GRF_CLEAR); + wa_mcr_masked_en(wal, + GEN9_ROW_CHICKEN4, + GEN12_DISABLE_GRF_CLEAR); /* Wa_14010648519:dg2 */ - wa_write_or(wal, XEHP_L3NODEARBCFG, XEHP_LNESPARE); + wa_mcr_write_or(wal, XEHP_L3NODEARBCFG, XEHP_LNESPARE); } /* Wa_14013202645:dg2 */ if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_C0) || IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0)) - wa_write_or(wal, RT_CTRL, DIS_NULL_QUERY); + wa_mcr_write_or(wal, RT_CTRL, DIS_NULL_QUERY); /* Wa_22012532006:dg2 */ if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_C0) || IS_DG2_GRAPHICS_STEP(engine->i915, G11, STEP_A0, STEP_B0)) - wa_masked_en(wal, GEN9_HALF_SLICE_CHICKEN7, - DG2_DISABLE_ROUND_ENABLE_ALLOW_FOR_SSLA); + wa_mcr_masked_en(wal, GEN9_HALF_SLICE_CHICKEN7, + DG2_DISABLE_ROUND_ENABLE_ALLOW_FOR_SSLA); if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0)) { /* Wa_14010680813:dg2_g10 */ @@ -2216,17 +2380,16 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0) || IS_DG2_GRAPHICS_STEP(engine->i915, G11, STEP_A0, STEP_B0)) { /* Wa_14012362059:dg2 */ - wa_write_or(wal, GEN12_MERT_MOD_CTRL, FORCE_MISS_FTLB); + wa_mcr_write_or(wal, XEHP_MERT_MOD_CTRL, FORCE_MISS_FTLB); } if (IS_DG2_GRAPHICS_STEP(i915, G11, STEP_B0, STEP_FOREVER) || IS_DG2_G10(i915)) { /* Wa_22014600077:dg2 */ - wa_add(wal, GEN10_CACHE_MODE_SS, 0, - _MASKED_BIT_ENABLE(ENABLE_EU_COUNT_FOR_TDL_FLUSH), - 0 /* Wa_14012342262 :write-only reg, so skip - verification */, - true); + wa_mcr_add(wal, GEN10_CACHE_MODE_SS, 0, + _MASKED_BIT_ENABLE(ENABLE_EU_COUNT_FOR_TDL_FLUSH), + 0 /* Wa_14012342262 write-only reg, so skip verification */, + true); } if (IS_DG1_GRAPHICS_STEP(i915, STEP_A0, STEP_B0) || @@ -2253,7 +2416,7 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) if (IS_ALDERLAKE_P(i915) || IS_ALDERLAKE_S(i915) || IS_DG1(i915) || IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) { /* Wa_1606931601:tgl,rkl,dg1,adl-s,adl-p */ - wa_masked_en(wal, GEN7_ROW_CHICKEN2, GEN12_DISABLE_EARLY_READ); + wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN2, GEN12_DISABLE_EARLY_READ); /* * Wa_1407928979:tgl A* @@ -2282,14 +2445,14 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) IS_DG1_GRAPHICS_STEP(i915, STEP_A0, STEP_B0) || IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) { /* Wa_1409804808:tgl,rkl,dg1[a0],adl-s,adl-p */ - wa_masked_en(wal, GEN7_ROW_CHICKEN2, - GEN12_PUSH_CONST_DEREF_HOLD_DIS); + wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN2, + GEN12_PUSH_CONST_DEREF_HOLD_DIS); /* * Wa_1409085225:tgl * Wa_14010229206:tgl,rkl,dg1[a0],adl-s,adl-p */ - wa_masked_en(wal, GEN9_ROW_CHICKEN4, GEN12_DISABLE_TDL_PUSH); + wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN4, GEN12_DISABLE_TDL_PUSH); } if (IS_DG1_GRAPHICS_STEP(i915, STEP_A0, STEP_B0) || @@ -2313,9 +2476,9 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) if (IS_DG1(i915) || IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915) || IS_ALDERLAKE_S(i915) || IS_ALDERLAKE_P(i915)) { /* Wa_1406941453:tgl,rkl,dg1,adl-s,adl-p */ - wa_masked_en(wal, - GEN10_SAMPLER_MODE, - ENABLE_SMALLPL); + wa_mcr_masked_en(wal, + GEN10_SAMPLER_MODE, + ENABLE_SMALLPL); } if (GRAPHICS_VER(i915) == 11) { @@ -2349,9 +2512,9 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) * Wa_1405733216:icl * Formerly known as WaDisableCleanEvicts */ - wa_write_or(wal, - GEN8_L3SQCREG4, - GEN11_LQSC_CLEAN_EVICT_DISABLE); + wa_mcr_write_or(wal, + GEN8_L3SQCREG4, + GEN11_LQSC_CLEAN_EVICT_DISABLE); /* Wa_1606682166:icl */ wa_write_or(wal, @@ -2359,10 +2522,10 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) GEN7_DISABLE_SAMPLER_PREFETCH); /* Wa_1409178092:icl */ - wa_write_clr_set(wal, - GEN11_SCRATCH2, - GEN11_COHERENT_PARTIAL_WRITE_MERGE_ENABLE, - 0); + wa_mcr_write_clr_set(wal, + GEN11_SCRATCH2, + GEN11_COHERENT_PARTIAL_WRITE_MERGE_ENABLE, + 0); /* WaEnable32PlaneMode:icl */ wa_masked_en(wal, GEN9_CSFE_CHICKEN1_RCS, @@ -2389,12 +2552,64 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) FF_DOP_CLOCK_GATE_DISABLE); } - if (IS_GRAPHICS_VER(i915, 9, 12)) { - /* FtrPerCtxtPreemptionGranularityControl:skl,bxt,kbl,cfl,cnl,icl,tgl */ + /* + * Intel platforms that support fine-grained preemption (i.e., gen9 and + * beyond) allow the kernel-mode driver to choose between two different + * options for controlling preemption granularity and behavior. + * + * Option 1 (hardware default): + * Preemption settings are controlled in a global manner via + * kernel-only register CS_DEBUG_MODE1 (0x20EC). Any granularity + * and settings chosen by the kernel-mode driver will apply to all + * userspace clients. + * + * Option 2: + * Preemption settings are controlled on a per-context basis via + * register CS_CHICKEN1 (0x2580). CS_CHICKEN1 is saved/restored on + * context switch and is writable by userspace (e.g., via + * MI_LOAD_REGISTER_IMMEDIATE instructions placed in a batch buffer) + * which allows different userspace drivers/clients to select + * different settings, or to change those settings on the fly in + * response to runtime needs. This option was known by name + * "FtrPerCtxtPreemptionGranularityControl" at one time, although + * that name is somewhat misleading as other non-granularity + * preemption settings are also impacted by this decision. + * + * On Linux, our policy has always been to let userspace drivers + * control preemption granularity/settings (Option 2). This was + * originally mandatory on gen9 to prevent ABI breakage (old gen9 + * userspace developed before object-level preemption was enabled would + * not behave well if i915 were to go with Option 1 and enable that + * preemption in a global manner). On gen9 each context would have + * object-level preemption disabled by default (see + * WaDisable3DMidCmdPreemption in gen9_ctx_workarounds_init), but + * userspace drivers could opt-in to object-level preemption as they + * saw fit. For post-gen9 platforms, we continue to utilize Option 2; + * even though it is no longer necessary for ABI compatibility when + * enabling a new platform, it does ensure that userspace will be able + * to implement any workarounds that show up requiring temporary + * adjustments to preemption behavior at runtime. + * + * Notes/Workarounds: + * - Wa_14015141709: On DG2 and early steppings of MTL, + * CS_CHICKEN1[0] does not disable object-level preemption as + * it is supposed to (nor does CS_DEBUG_MODE1[0] if we had been + * using Option 1). Effectively this means userspace is unable + * to disable object-level preemption on these platforms/steppings + * despite the setting here. + * + * - Wa_16013994831: May require that userspace program + * CS_CHICKEN1[10] when certain runtime conditions are true. + * Userspace requires Option 2 to be in effect for their update of + * CS_CHICKEN1[10] to be effective. + * + * Other workarounds may appear in the future that will also require + * Option 2 behavior to allow proper userspace implementation. + */ + if (GRAPHICS_VER(i915) >= 9) wa_masked_en(wal, GEN7_FF_SLICE_CS_CHICKEN1, GEN9_FFSC_PERCTX_PREEMPT_CTRL); - } if (IS_SKYLAKE(i915) || IS_KABYLAKE(i915) || @@ -2420,36 +2635,36 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE); /* WaEnableLbsSlaRetryTimerDecrement:skl,bxt,kbl,glk,cfl */ - wa_write_or(wal, - BDW_SCRATCH1, - GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE); + wa_mcr_write_or(wal, + BDW_SCRATCH1, + GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE); /* WaProgramL3SqcReg1DefaultForPerf:bxt,glk */ if (IS_GEN9_LP(i915)) - wa_write_clr_set(wal, - GEN8_L3SQCREG1, - L3_PRIO_CREDITS_MASK, - L3_GENERAL_PRIO_CREDITS(62) | - L3_HIGH_PRIO_CREDITS(2)); + wa_mcr_write_clr_set(wal, + GEN8_L3SQCREG1, + L3_PRIO_CREDITS_MASK, + L3_GENERAL_PRIO_CREDITS(62) | + L3_HIGH_PRIO_CREDITS(2)); /* WaOCLCoherentLineFlush:skl,bxt,kbl,cfl */ - wa_write_or(wal, - GEN8_L3SQCREG4, - GEN8_LQSC_FLUSH_COHERENT_LINES); + wa_mcr_write_or(wal, + GEN8_L3SQCREG4, + GEN8_LQSC_FLUSH_COHERENT_LINES); /* Disable atomics in L3 to prevent unrecoverable hangs */ wa_write_clr_set(wal, GEN9_SCRATCH_LNCF1, GEN9_LNCF_NONIA_COHERENT_ATOMICS_ENABLE, 0); - wa_write_clr_set(wal, GEN8_L3SQCREG4, - GEN8_LQSQ_NONIA_COHERENT_ATOMICS_ENABLE, 0); - wa_write_clr_set(wal, GEN9_SCRATCH1, - EVICTION_PERF_FIX_ENABLE, 0); + wa_mcr_write_clr_set(wal, GEN8_L3SQCREG4, + GEN8_LQSQ_NONIA_COHERENT_ATOMICS_ENABLE, 0); + wa_mcr_write_clr_set(wal, GEN9_SCRATCH1, + EVICTION_PERF_FIX_ENABLE, 0); } if (IS_HASWELL(i915)) { /* WaSampleCChickenBitEnable:hsw */ wa_masked_en(wal, - HALF_SLICE_CHICKEN3, HSW_SAMPLE_C_PERFORMANCE); + HSW_HALF_SLICE_CHICKEN3, HSW_SAMPLE_C_PERFORMANCE); wa_masked_dis(wal, CACHE_MODE_0_GEN7, @@ -2657,7 +2872,7 @@ ccs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) { if (IS_PVC_CT_STEP(engine->i915, STEP_A0, STEP_C0)) { /* Wa_14014999345:pvc */ - wa_masked_en(wal, GEN10_CACHE_MODE_SS, DISABLE_ECC); + wa_mcr_masked_en(wal, GEN10_CACHE_MODE_SS, DISABLE_ECC); } } @@ -2683,8 +2898,8 @@ add_render_compute_tuning_settings(struct drm_i915_private *i915, } if (IS_DG2(i915)) { - wa_write_or(wal, XEHP_L3SCQREG7, BLEND_FILL_CACHING_OPT_DIS); - wa_write_clr_set(wal, RT_CTRL, STACKID_CTRL, STACKID_CTRL_512); + wa_mcr_write_or(wal, XEHP_L3SCQREG7, BLEND_FILL_CACHING_OPT_DIS); + wa_mcr_write_clr_set(wal, RT_CTRL, STACKID_CTRL, STACKID_CTRL_512); /* * This is also listed as Wa_22012654132 for certain DG2 @@ -2695,10 +2910,10 @@ add_render_compute_tuning_settings(struct drm_i915_private *i915, * back for verification on DG2 (due to Wa_14012342262), so * we need to explicitly skip the readback. */ - wa_add(wal, GEN10_CACHE_MODE_SS, 0, - _MASKED_BIT_ENABLE(ENABLE_PREFETCH_INTO_IC), - 0 /* write-only, so skip validation */, - true); + wa_mcr_add(wal, GEN10_CACHE_MODE_SS, 0, + _MASKED_BIT_ENABLE(ENABLE_PREFETCH_INTO_IC), + 0 /* write-only, so skip validation */, + true); } /* @@ -2707,8 +2922,8 @@ add_render_compute_tuning_settings(struct drm_i915_private *i915, * platforms. */ if (INTEL_INFO(i915)->tuning_thread_rr_after_dep) - wa_masked_field_set(wal, GEN9_ROW_CHICKEN4, THREAD_EX_ARB_MODE, - THREAD_EX_ARB_MODE_RR_AFTER_DEP); + wa_mcr_masked_field_set(wal, GEN9_ROW_CHICKEN4, THREAD_EX_ARB_MODE, + THREAD_EX_ARB_MODE_RR_AFTER_DEP); } /* @@ -2734,30 +2949,30 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li if (IS_XEHPSDV(i915)) { /* Wa_1409954639 */ - wa_masked_en(wal, - GEN8_ROW_CHICKEN, - SYSTOLIC_DOP_CLOCK_GATING_DIS); + wa_mcr_masked_en(wal, + GEN8_ROW_CHICKEN, + SYSTOLIC_DOP_CLOCK_GATING_DIS); /* Wa_1607196519 */ - wa_masked_en(wal, - GEN9_ROW_CHICKEN4, - GEN12_DISABLE_GRF_CLEAR); + wa_mcr_masked_en(wal, + GEN9_ROW_CHICKEN4, + GEN12_DISABLE_GRF_CLEAR); /* Wa_14010670810:xehpsdv */ - wa_write_or(wal, XEHP_L3NODEARBCFG, XEHP_LNESPARE); + wa_mcr_write_or(wal, XEHP_L3NODEARBCFG, XEHP_LNESPARE); /* Wa_14010449647:xehpsdv */ - wa_masked_en(wal, GEN7_HALF_SLICE_CHICKEN1, - GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE); + wa_mcr_masked_en(wal, GEN8_HALF_SLICE_CHICKEN1, + GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE); /* Wa_18011725039:xehpsdv */ if (IS_XEHPSDV_GRAPHICS_STEP(i915, STEP_A1, STEP_B0)) { - wa_masked_dis(wal, MLTICTXCTL, TDONRENDER); - wa_write_or(wal, L3SQCREG1_CCS0, FLUSHALLNONCOH); + wa_mcr_masked_dis(wal, MLTICTXCTL, TDONRENDER); + wa_mcr_write_or(wal, L3SQCREG1_CCS0, FLUSHALLNONCOH); } /* Wa_14012362059:xehpsdv */ - wa_write_or(wal, GEN12_MERT_MOD_CTRL, FORCE_MISS_FTLB); + wa_mcr_write_or(wal, XEHP_MERT_MOD_CTRL, FORCE_MISS_FTLB); /* Wa_14014368820:xehpsdv */ wa_write_or(wal, GEN12_GAMCNTRL_CTRL, INVALIDATION_BROADCAST_MODE_DIS | @@ -2766,26 +2981,37 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li if (IS_DG2(i915) || IS_PONTEVECCHIO(i915)) { /* Wa_14015227452:dg2,pvc */ - wa_masked_en(wal, GEN9_ROW_CHICKEN4, XEHP_DIS_BBL_SYSPIPE); + wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN4, XEHP_DIS_BBL_SYSPIPE); /* Wa_22014226127:dg2,pvc */ - wa_write_or(wal, LSC_CHICKEN_BIT_0, DISABLE_D8_D16_COASLESCE); + wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0, DISABLE_D8_D16_COASLESCE); /* Wa_16015675438:dg2,pvc */ wa_masked_en(wal, FF_SLICE_CS_CHICKEN2, GEN12_PERF_FIX_BALANCING_CFE_DISABLE); /* Wa_18018781329:dg2,pvc */ - wa_write_or(wal, RENDER_MOD_CTRL, FORCE_MISS_FTLB); - wa_write_or(wal, COMP_MOD_CTRL, FORCE_MISS_FTLB); - wa_write_or(wal, VDBX_MOD_CTRL, FORCE_MISS_FTLB); - wa_write_or(wal, VEBX_MOD_CTRL, FORCE_MISS_FTLB); + wa_mcr_write_or(wal, RENDER_MOD_CTRL, FORCE_MISS_FTLB); + wa_mcr_write_or(wal, COMP_MOD_CTRL, FORCE_MISS_FTLB); + wa_mcr_write_or(wal, VDBX_MOD_CTRL, FORCE_MISS_FTLB); + wa_mcr_write_or(wal, VEBX_MOD_CTRL, FORCE_MISS_FTLB); + } + + if (IS_DG2(i915)) { + /* + * Wa_16011620976:dg2_g11 + * Wa_22015475538:dg2 + */ + wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0_UDW, DIS_CHAIN_2XSIMD8); + + /* Wa_18017747507:dg2 */ + wa_masked_en(wal, VFG_PREEMPTION_CHICKEN, POLYGON_TRIFAN_LINELOOP_DISABLE); } } static void engine_init_workarounds(struct intel_engine_cs *engine, struct i915_wa_list *wal) { - if (I915_SELFTEST_ONLY(GRAPHICS_VER(engine->i915) < 4)) + if (GRAPHICS_VER(engine->i915) < 4) return; engine_fake_wa_init(engine, wal); @@ -2810,17 +3036,14 @@ void intel_engine_init_workarounds(struct intel_engine_cs *engine) { struct i915_wa_list *wal = &engine->wa_list; - if (GRAPHICS_VER(engine->i915) < 4) - return; - - wa_init_start(wal, "engine", engine->name); + wa_init_start(wal, engine->gt, "engine", engine->name); engine_init_workarounds(engine, wal); wa_init_finish(wal); } void intel_engine_apply_workarounds(struct intel_engine_cs *engine) { - wa_list_apply(engine->gt, &engine->wa_list); + wa_list_apply(&engine->wa_list); } static const struct i915_range mcr_ranges_gen8[] = { @@ -2964,9 +3187,7 @@ retry: goto err_vma; } - err = i915_request_await_object(rq, vma->obj, true); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); if (err == 0) err = wa_list_srm(rq, wal, vma); @@ -2994,7 +3215,7 @@ retry: if (mcr_range(rq->engine->i915, i915_mmio_reg_offset(wa->reg))) continue; - if (!wa_verify(wa, results[i], wal->name, from)) + if (!wa_verify(wal->gt, wa, results[i], wal->name, from)) err = -ENXIO; } |