From: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx> commit ef50fa9bd17d13d0611e39e13b37bbd3e1ea50bf upstream. Rescue the GT workarounds from being buried inside init_clock_gating so that we remember to apply them after a GT reset, and that they are included in our verification that the workarounds are applied. v2: Leave HSW_SCRATCH to set an explicit value, not or in our disable bit. Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/2011 Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx> Cc: Mika Kuoppala <mika.kuoppala@xxxxxxxxxxxxxxx> Reviewed-by: Mika Kuoppala <mika.kuoppala@xxxxxxxxxxxxxxx> Cc: stable@xxxxxxxxxxxxxxx Link: https://patchwork.freedesktop.org/patch/msgid/20200611093015.11370-1-chris@xxxxxxxxxxxxxxxxxx (cherry picked from commit f93ec5fb563779bda4501890b1854526de58e0f1) Signed-off-by: Joonas Lahtinen <joonas.lahtinen@xxxxxxxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- drivers/gpu/drm/i915/gt/intel_workarounds.c | 48 ++++++++++++++++++++++++++++ drivers/gpu/drm/i915/intel_pm.c | 39 +--------------------- 2 files changed, 50 insertions(+), 37 deletions(-) --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -179,6 +179,12 @@ wa_write_or(struct i915_wa_list *wal, i9 } static void +wa_write_clr(struct i915_wa_list *wal, i915_reg_t reg, u32 clr) +{ + wa_write_masked_or(wal, reg, clr, 0); +} + +static void wa_masked_en(struct i915_wa_list *wal, i915_reg_t reg, u32 val) { wa_add(wal, reg, 0, _MASKED_BIT_ENABLE(val), val); @@ -698,6 +704,46 @@ int intel_engine_emit_ctx_wa(struct i915 } static void +hsw_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) +{ + /* L3 caching of data atomics doesn't work -- disable it. */ + wa_write(wal, HSW_SCRATCH1, HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE); + + wa_add(wal, + HSW_ROW_CHICKEN3, 0, + _MASKED_BIT_ENABLE(HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE), + 0 /* XXX does this reg exist? */); + + /* WaVSRefCountFullforceMissDisable:hsw */ + wa_write_clr(wal, GEN7_FF_THREAD_MODE, GEN7_FF_VS_REF_CNT_FFME); + + wa_masked_dis(wal, + CACHE_MODE_0_GEN7, + /* WaDisable_RenderCache_OperationalFlush:hsw */ + RC_OP_FLUSH_ENABLE | + /* enable HiZ Raw Stall Optimization */ + HIZ_RAW_STALL_OPT_DISABLE); + + /* WaDisable4x2SubspanOptimization:hsw */ + wa_masked_en(wal, CACHE_MODE_1, PIXEL_SUBSPAN_COLLECT_OPT_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_add(wal, GEN7_GT_MODE, 0, + _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4), + GEN6_WIZ_HASHING_16x4); + + /* WaSampleCChickenBitEnable:hsw */ + wa_masked_en(wal, HALF_SLICE_CHICKEN3, HSW_SAMPLE_C_PERFORMANCE); +} + +static void gen9_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) { /* WaDisableKillLogic:bxt,skl,kbl */ @@ -974,6 +1020,8 @@ gt_init_workarounds(struct drm_i915_priv bxt_gt_workarounds_init(i915, wal); else if (IS_SKYLAKE(i915)) skl_gt_workarounds_init(i915, wal); + else if (IS_HASWELL(i915)) + hsw_gt_workarounds_init(i915, wal); else if (INTEL_GEN(i915) <= 8) return; else --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -6992,45 +6992,10 @@ static void bdw_init_clock_gating(struct static void hsw_init_clock_gating(struct drm_i915_private *dev_priv) { - /* L3 caching of data atomics doesn't work -- disable it. */ - I915_WRITE(HSW_SCRATCH1, HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE); - I915_WRITE(HSW_ROW_CHICKEN3, - _MASKED_BIT_ENABLE(HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE)); - /* This is required by WaCatErrorRejectionIssue:hsw */ I915_WRITE(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG, - I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) | - GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB); - - /* WaVSRefCountFullforceMissDisable:hsw */ - I915_WRITE(GEN7_FF_THREAD_MODE, - I915_READ(GEN7_FF_THREAD_MODE) & ~GEN7_FF_VS_REF_CNT_FFME); - - /* WaDisable_RenderCache_OperationalFlush:hsw */ - I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE)); - - /* enable HiZ Raw Stall Optimization */ - I915_WRITE(CACHE_MODE_0_GEN7, - _MASKED_BIT_DISABLE(HIZ_RAW_STALL_OPT_DISABLE)); - - /* WaDisable4x2SubspanOptimization:hsw */ - I915_WRITE(CACHE_MODE_1, - _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_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). - */ - I915_WRITE(GEN7_GT_MODE, - _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4)); - - /* WaSampleCChickenBitEnable:hsw */ - I915_WRITE(HALF_SLICE_CHICKEN3, - _MASKED_BIT_ENABLE(HSW_SAMPLE_C_PERFORMANCE)); + I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) | + GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB); /* WaSwitchSolVfFArbitrationPriority:hsw */ I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
