[Intel-gfx] [PATCH] drm/i915: Move hsw GT w/a to engine initialisation

[Chris Wilson]

In commit b7048ea12fbb ("drm/i915: Do .init_clock_gating() earlier to
avoid it clobbering watermarks") init_clock_gating was called earlier in
the module load sequence, moving it before we acquired the forcewake
used to initialise the engines. This revealed that on Haswell, at least,
some of those GT w/as had been moved into the power context, and so as
we were now setting them outside of the power context, those settings
were being lost. Now, strictly we want to set power context registers
using LRI (that ensures there is a power context loaded!), we can
restore the earlier behaviour by moving the GT register writes back to
the same point in the module initialisation sequence.

Reported-by: Mark Janes <mark.a.janes at intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103549
Fixes: b7048ea12fbb ("drm/i915: Do .init_clock_gating() earlier to avoid it clobbering watermarks")
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Mark Janes <mark.a.janes at intel.com>
Cc: Ville Syrjälä <ville.syrjala at linux.intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst at linux.intel.com>
Cc: Daniel Vetter <daniel.vetter at ffwll.ch>
Cc: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
Cc: Oscar Mateo <oscar.mateo at intel.com>
Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
---
 drivers/gpu/drm/i915/intel_pm.c         | 38 ------------------------------
 drivers/gpu/drm/i915/intel_ringbuffer.c | 41 +++++++++++++++++++++++++++++++++
 2 files changed, 41 insertions(+), 38 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 308439dd89d4..8a72526d491e 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -8588,49 +8588,11 @@ static void hsw_init_clock_gating(struct drm_i915_private *dev_priv)
 {
 	ilk_init_lp_watermarks(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));
-
-	/* WaSwitchSolVfFArbitrationPriority:hsw */
-	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
-
 	/* WaRsPkgCStateDisplayPMReq:hsw */
 	I915_WRITE(CHICKEN_PAR1_1,
 		   I915_READ(CHICKEN_PAR1_1) | FORCE_ARB_IDLE_PLANES);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 3321b801e77d..3a2287b0d9f4 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -707,6 +707,47 @@ static int init_render_ring(struct intel_engine_cs *engine)
 	if (IS_GEN(dev_priv, 6, 7))
 		I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
 
+
+	if (IS_HASWELL(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));
+
+		/* 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));
+
+		/* WaSwitchSolVfFArbitrationPriority:hsw */
+		I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
+	}
+
 	if (INTEL_INFO(dev_priv)->gen >= 6)
 		I915_WRITE_IMR(engine, ~engine->irq_keep_mask);
 
-- 
2.15.0