drm/i915/gt: Move ivb GT workarounds from init_clock_gating to workarounds

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.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://patchwork.freedesktop.org/patch/msgid/20200611080140.30228-2-chris@chris-wilson.co.uk

diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index fb337e2d8a27da253432c16cf39f18f0a5d2165b..8efd337eb481a6c19e8d85f58d9ea0d4cb03910f 100644 (file)
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -714,6 +714,66 @@ int intel_engine_emit_ctx_wa(struct i915_request *rq)
        return 0;
 }
 
+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,
+                            GEN7_HALF_SLICE_CHICKEN1,
+                            GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE);
+
+       /* WaDisable_RenderCache_OperationalFlush:ivb */
+       wa_masked_dis(wal, CACHE_MODE_0_GEN7, RC_OP_FLUSH_ENABLE);
+
+       /* Apply the WaDisableRHWOOptimizationForRenderHang:ivb workaround. */
+       wa_masked_dis(wal,
+                     GEN7_COMMON_SLICE_CHICKEN1,
+                     GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC);
+
+       /* WaApplyL3ControlAndL3ChickenMode:ivb */
+       wa_write(wal, GEN7_L3CNTLREG1, GEN7_WA_FOR_GEN7_L3_CONTROL);
+       wa_write(wal, GEN7_L3_CHICKEN_MODE_REGISTER, GEN7_WA_L3_CHICKEN_MODE);
+
+       /* 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_masked_or(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
 hsw_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 {
@@ -1033,6 +1093,8 @@ gt_init_workarounds(struct drm_i915_private *i915, struct i915_wa_list *wal)
                skl_gt_workarounds_init(i915, wal);
        else if (IS_HASWELL(i915))
                hsw_gt_workarounds_init(i915, wal);
+       else if (IS_IVYBRIDGE(i915))
+               ivb_gt_workarounds_init(i915, wal);
        else if (INTEL_GEN(i915) <= 8)
                return;
        else

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 9aca6d778220dca5215f7733394dae9b8331f1da..19e1fed198c3eed3fac9d3b233b192f2071982a9 100644 (file)
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7924,7 +7924,7 @@ enum {
 
 /* GEN7 chicken */
 #define GEN7_COMMON_SLICE_CHICKEN1             _MMIO(0x7010)
-  #define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC    ((1 << 10) | (1 << 26))
+  #define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC    (1 << 10)
   #define GEN9_RHWO_OPTIMIZATION_DISABLE       (1 << 14)
 
 #define COMMON_SLICE_CHICKEN2                                  _MMIO(0x7014)

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 249ee720874ca4152d02807458b660c9cf7185de..b835e5e975153585a7c57fd12ff618a6f0ae8d27 100644 (file)
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -7338,32 +7338,11 @@ static void ivb_init_clock_gating(struct drm_i915_private *dev_priv)
 
        I915_WRITE(ILK_DSPCLK_GATE_D, ILK_VRHUNIT_CLOCK_GATE_DISABLE);
 
-       /* WaDisableEarlyCull:ivb */
-       I915_WRITE(_3D_CHICKEN3,
-                  _MASKED_BIT_ENABLE(_3D_CHICKEN_SF_DISABLE_OBJEND_CULL));
-
        /* WaDisableBackToBackFlipFix:ivb */
        I915_WRITE(IVB_CHICKEN3,
                   CHICKEN3_DGMG_REQ_OUT_FIX_DISABLE |
                   CHICKEN3_DGMG_DONE_FIX_DISABLE);
 
-       /* WaDisablePSDDualDispatchEnable:ivb */
-       if (IS_IVB_GT1(dev_priv))
-               I915_WRITE(GEN7_HALF_SLICE_CHICKEN1,
-                          _MASKED_BIT_ENABLE(GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE));
-
-       /* WaDisable_RenderCache_OperationalFlush:ivb */
-       I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
-
-       /* Apply the WaDisableRHWOOptimizationForRenderHang:ivb workaround. */
-       I915_WRITE(GEN7_COMMON_SLICE_CHICKEN1,
-                  GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC);
-
-       /* WaApplyL3ControlAndL3ChickenMode:ivb */
-       I915_WRITE(GEN7_L3CNTLREG1,
-                       GEN7_WA_FOR_GEN7_L3_CONTROL);
-       I915_WRITE(GEN7_L3_CHICKEN_MODE_REGISTER,
-                  GEN7_WA_L3_CHICKEN_MODE);
        if (IS_IVB_GT1(dev_priv))
                I915_WRITE(GEN7_ROW_CHICKEN2,
                           _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
@@ -7375,10 +7354,6 @@ static void ivb_init_clock_gating(struct drm_i915_private *dev_priv)
                           _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
        }
 
-       /* WaForceL3Serialization:ivb */
-       I915_WRITE(GEN7_L3SQCREG4, I915_READ(GEN7_L3SQCREG4) &
-                  ~L3SQ_URB_READ_CAM_MATCH_DISABLE);
-
        /*
         * According to the spec, bit 13 (RCZUNIT) must be set on IVB.
         * This implements the WaDisableRCZUnitClockGating:ivb workaround.
@@ -7393,29 +7368,6 @@ static void ivb_init_clock_gating(struct drm_i915_private *dev_priv)
 
        g4x_disable_trickle_feed(dev_priv);
 
-       gen7_setup_fixed_func_scheduler(dev_priv);
-
-       if (0) { /* causes HiZ corruption on ivb:gt1 */
-               /* enable HiZ Raw Stall Optimization */
-               I915_WRITE(CACHE_MODE_0_GEN7,
-                          _MASKED_BIT_DISABLE(HIZ_RAW_STALL_OPT_DISABLE));
-       }
-
-       /* WaDisable4x2SubspanOptimization:ivb */
-       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));
-
        snpcr = I915_READ(GEN6_MBCUNIT_SNPCR);
        snpcr &= ~GEN6_MBC_SNPCR_MASK;
        snpcr |= GEN6_MBC_SNPCR_MED;