[PATCH 2/8] ivb-wa
Chris Wilson
chris at chris-wilson.co.uk
Mon Jan 4 22:49:02 UTC 2021
---
drivers/gpu/drm/i915/gt/intel_workarounds.c | 95 +++++++++------------
1 file changed, 39 insertions(+), 56 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 3b13411393f3..41a3a2802752 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -829,9 +829,6 @@ snb_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
static void
ivb_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
{
- /* WaDisableEarlyCull:ivb */
- wa_masked_en(wal, _3D_CHICKEN3, _3D_CHICKEN_SF_DISABLE_OBJEND_CULL);
-
/* WaDisablePSDDualDispatchEnable:ivb */
if (IS_IVB_GT1(i915))
wa_masked_en(wal,
@@ -853,37 +850,10 @@ ivb_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
/* WaForceL3Serialization:ivb */
wa_write_clr(wal, GEN7_L3SQCREG4, L3SQ_URB_READ_CAM_MATCH_DISABLE);
- /*
- * WaVSThreadDispatchOverride:ivb,vlv
- *
- * This actually overrides the dispatch
- * mode for all thread types.
- */
- wa_write_clr_set(wal, GEN7_FF_THREAD_MODE,
- GEN7_FF_SCHED_MASK,
- GEN7_FF_TS_SCHED_HW |
- GEN7_FF_VS_SCHED_HW |
- GEN7_FF_DS_SCHED_HW);
-
if (0) { /* causes HiZ corruption on ivb:gt1 */
/* enable HiZ Raw Stall Optimization */
wa_masked_dis(wal, CACHE_MODE_0_GEN7, HIZ_RAW_STALL_OPT_DISABLE);
}
-
- /* WaDisable4x2SubspanOptimization:ivb */
- 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);
}
static void
@@ -1896,19 +1866,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
/* 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);
}
if (IS_VALLEYVIEW(i915)) {
@@ -1936,6 +1893,45 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
CACHE_MODE_1,
PIXEL_SUBSPAN_COLLECT_OPT_DISABLE);
+ /* WaPsdDispatchEnable:vlv */
+ /* WaDisablePSDDualDispatchEnable:vlv */
+ wa_masked_en(wal,
+ GEN7_HALF_SLICE_CHICKEN1,
+ GEN7_MAX_PS_THREAD_DEP |
+ GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE);
+ }
+
+ if (IS_IVYBRIDGE(i915)) {
+ /* WaDisableEarlyCull:ivb */
+ wa_masked_en(wal,
+ _3D_CHICKEN3,
+ _3D_CHICKEN_SF_DISABLE_OBJEND_CULL);
+
+ /*
+ * WaVSThreadDispatchOverride:ivb,vlv
+ *
+ * This actually overrides the dispatch
+ * mode for all thread types.
+ */
+ wa_write_clr_set(wal,
+ GEN7_FF_THREAD_MODE,
+ GEN7_FF_SCHED_MASK,
+ GEN7_FF_TS_SCHED_HW |
+ GEN7_FF_VS_SCHED_HW |
+ GEN7_FF_DS_SCHED_HW);
+
+ /* WaDisable4x2SubspanOptimization:ivb */
+ wa_masked_en(wal,
+ CACHE_MODE_1,
+ PIXEL_SUBSPAN_COLLECT_OPT_DISABLE);
+ }
+
+ if (IS_GEN(i915, 7)) {
+ /* WaBCSVCSTlbInvalidationMode:ivb,vlv,hsw */
+ wa_masked_en(wal,
+ GFX_MODE_GEN7,
+ GFX_TLB_INVALIDATE_EXPLICIT | GFX_REPLAY_MODE);
+
/*
* BSpec recommends 8x4 when MSAA is used,
* however in practice 16x4 seems fastest.
@@ -1948,21 +1944,8 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
_MASKED_FIELD(GEN6_WIZ_HASHING_MASK,
GEN6_WIZ_HASHING_16x4),
GEN6_WIZ_HASHING_16x4);
-
- /* WaPsdDispatchEnable:vlv */
- /* WaDisablePSDDualDispatchEnable:vlv */
- wa_masked_en(wal,
- GEN7_HALF_SLICE_CHICKEN1,
- GEN7_MAX_PS_THREAD_DEP |
- GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE);
}
- if (IS_GEN(i915, 7))
- /* WaBCSVCSTlbInvalidationMode:ivb,vlv,hsw */
- wa_masked_en(wal,
- GFX_MODE_GEN7,
- GFX_TLB_INVALIDATE_EXPLICIT | GFX_REPLAY_MODE);
-
if (IS_GEN_RANGE(i915, 6, 7))
/*
* We need to disable the AsyncFlip performance optimisations in
--
2.20.1
More information about the Intel-gfx-trybot
mailing list