[PATCH 1/7] drm/i915/gen8: Add gen8_init_workarounds for common WA

[PATCH 1/7] drm/i915/gen8: Add gen8_init_workarounds for common WA

[Arun Siluvery]

Signed-off-by: Arun Siluvery <arun.siluvery@linux.intel.com>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 16a4ead..10f9ea0 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -800,11 +800,22 @@ static int wa_add(struct drm_i915_private *dev_priv,
 
 #define WA_WRITE(addr, val) WA_REG(addr, 0xffffffff, val)
 
+static int gen8_init_workarounds(struct intel_engine_cs *ring)
+{
+
+	return 0;
+}
+
 static int bdw_init_workarounds(struct intel_engine_cs *ring)
 {
+	int ret;
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
+	ret = gen8_init_workarounds(ring);
+	if (ret)
+		return ret;
+
 	WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING);
 
 	/* WaDisableAsyncFlipPerfMode:bdw */
@@ -868,9 +879,14 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
 
 static int chv_init_workarounds(struct intel_engine_cs *ring)
 {
+	int ret;
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
+	ret = gen8_init_workarounds(ring);
+	if (ret)
+		return ret;
+
 	WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING);
 
 	/* WaDisableAsyncFlipPerfMode:chv */
-- 
1.9.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 2/7] drm/i915/gen8: Move INSTPM WA to common function

[Arun Siluvery]

Signed-off-by: Arun Siluvery <arun.siluvery@linux.intel.com>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 10f9ea0..4f3942f 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -802,6 +802,10 @@ static int wa_add(struct drm_i915_private *dev_priv,
 
 static int gen8_init_workarounds(struct intel_engine_cs *ring)
 {
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING);
 
 	return 0;
 }
@@ -816,8 +820,6 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
 	if (ret)
 		return ret;
 
-	WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING);
-
 	/* WaDisableAsyncFlipPerfMode:bdw */
 	WA_SET_BIT_MASKED(MI_MODE, ASYNC_FLIP_PERF_DISABLE);
 
@@ -887,8 +889,6 @@ static int chv_init_workarounds(struct intel_engine_cs *ring)
 	if (ret)
 		return ret;
 
-	WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING);
-
 	/* WaDisableAsyncFlipPerfMode:chv */
 	WA_SET_BIT_MASKED(MI_MODE, ASYNC_FLIP_PERF_DISABLE);
 
-- 
1.9.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 3/7] drm/i915/gen8: Move WaDisableAsyncFlipPerfMode to common init fn

[Arun Siluvery]

Signed-off-by: Arun Siluvery <arun.siluvery@linux.intel.com>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 4f3942f..3bc14fa 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -807,6 +807,9 @@ static int gen8_init_workarounds(struct intel_engine_cs *ring)
 
 	WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING);
 
+	/* WaDisableAsyncFlipPerfMode:bdw,chv */
+	WA_SET_BIT_MASKED(MI_MODE, ASYNC_FLIP_PERF_DISABLE);
+
 	return 0;
 }
 
@@ -820,9 +823,6 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
 	if (ret)
 		return ret;
 
-	/* WaDisableAsyncFlipPerfMode:bdw */
-	WA_SET_BIT_MASKED(MI_MODE, ASYNC_FLIP_PERF_DISABLE);
-
 	/* WaDisablePartialInstShootdown:bdw */
 	/* WaDisableThreadStallDopClockGating:bdw (pre-production) */
 	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
@@ -889,9 +889,6 @@ static int chv_init_workarounds(struct intel_engine_cs *ring)
 	if (ret)
 		return ret;
 
-	/* WaDisableAsyncFlipPerfMode:chv */
-	WA_SET_BIT_MASKED(MI_MODE, ASYNC_FLIP_PERF_DISABLE);
-
 	/* WaDisablePartialInstShootdown:chv */
 	/* WaDisableThreadStallDopClockGating:chv */
 	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
-- 
1.9.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 4/7] drm/i915/gen8: Move Wa4x4STCOptimizationDisable to common init fn

[Arun Siluvery]

Signed-off-by: Arun Siluvery <arun.siluvery@linux.intel.com>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 3bc14fa..a06788a 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -810,6 +810,9 @@ static int gen8_init_workarounds(struct intel_engine_cs *ring)
 	/* WaDisableAsyncFlipPerfMode:bdw,chv */
 	WA_SET_BIT_MASKED(MI_MODE, ASYNC_FLIP_PERF_DISABLE);
 
+	/* Wa4x4STCOptimizationDisable:bdw,chv */
+	WA_SET_BIT_MASKED(CACHE_MODE_1, GEN8_4x4_STC_OPTIMIZATION_DISABLE);
+
 	return 0;
 }
 
@@ -860,10 +863,6 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
 	 */
 	WA_CLR_BIT_MASKED(CACHE_MODE_0_GEN7, HIZ_RAW_STALL_OPT_DISABLE);
 
-	/* Wa4x4STCOptimizationDisable:bdw */
-	WA_SET_BIT_MASKED(CACHE_MODE_1,
-			  GEN8_4x4_STC_OPTIMIZATION_DISABLE);
-
 	/*
 	 * BSpec recommends 8x4 when MSAA is used,
 	 * however in practice 16x4 seems fastest.
@@ -910,10 +909,6 @@ static int chv_init_workarounds(struct intel_engine_cs *ring)
 	 */
 	WA_CLR_BIT_MASKED(CACHE_MODE_0_GEN7, HIZ_RAW_STALL_OPT_DISABLE);
 
-	/* Wa4x4STCOptimizationDisable:chv */
-	WA_SET_BIT_MASKED(CACHE_MODE_1,
-			  GEN8_4x4_STC_OPTIMIZATION_DISABLE);
-
 	/* Improve HiZ throughput on CHV. */
 	WA_SET_BIT_MASKED(HIZ_CHICKEN, CHV_HZ_8X8_MODE_IN_1X);
 
-- 
1.9.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 5/7] drm/i915/gen8: Move GEN8_ROW_CHICKEN WA to common init fn

[Arun Siluvery]

Move WaDisablePartialInstShootdown and WaDisableThreadStallDopClockGating

Signed-off-by: Arun Siluvery <arun.siluvery@linux.intel.com>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index a06788a..5d15e31 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -807,6 +807,12 @@ static int gen8_init_workarounds(struct intel_engine_cs *ring)
 
 	WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING);
 
+	/* WaDisablePartialInstShootdown:bdw,chv */
+	/* WaDisableThreadStallDopClockGating:chv, bdw (pre-production) */
+	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
+			  PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE |
+			  STALL_DOP_GATING_DISABLE);
+
 	/* WaDisableAsyncFlipPerfMode:bdw,chv */
 	WA_SET_BIT_MASKED(MI_MODE, ASYNC_FLIP_PERF_DISABLE);
 
@@ -826,12 +832,6 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
 	if (ret)
 		return ret;
 
-	/* WaDisablePartialInstShootdown:bdw */
-	/* WaDisableThreadStallDopClockGating:bdw (pre-production) */
-	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
-			  PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE |
-			  STALL_DOP_GATING_DISABLE);
-
 	/* WaDisableDopClockGating:bdw */
 	WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2,
 			  DOP_CLOCK_GATING_DISABLE);
@@ -888,12 +888,6 @@ static int chv_init_workarounds(struct intel_engine_cs *ring)
 	if (ret)
 		return ret;
 
-	/* WaDisablePartialInstShootdown:chv */
-	/* WaDisableThreadStallDopClockGating:chv */
-	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
-			  PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE |
-			  STALL_DOP_GATING_DISABLE);
-
 	/* Use Force Non-Coherent whenever executing a 3D context. This is a
 	 * workaround for a possible hang in the unlikely event a TLB
 	 * invalidation occurs during a PSD flush.
-- 
1.9.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 6/7] drm/i915/gen8: Move GEN7_GT_MODE WA to common init fn

[Arun Siluvery]

Signed-off-by: Arun Siluvery <arun.siluvery@linux.intel.com>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 36 +++++++++++----------------------
 1 file changed, 12 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 5d15e31..c681c66 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -819,6 +819,18 @@ static int gen8_init_workarounds(struct intel_engine_cs *ring)
 	/* Wa4x4STCOptimizationDisable:bdw,chv */
 	WA_SET_BIT_MASKED(CACHE_MODE_1, GEN8_4x4_STC_OPTIMIZATION_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_SET_FIELD_MASKED(GEN7_GT_MODE,
+			    GEN6_WIZ_HASHING_MASK,
+			    GEN6_WIZ_HASHING_16x4);
+
 	return 0;
 }
 
@@ -863,18 +875,6 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
 	 */
 	WA_CLR_BIT_MASKED(CACHE_MODE_0_GEN7, HIZ_RAW_STALL_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_SET_FIELD_MASKED(GEN7_GT_MODE,
-			    GEN6_WIZ_HASHING_MASK,
-			    GEN6_WIZ_HASHING_16x4);
-
 	return 0;
 }
 
@@ -906,18 +906,6 @@ static int chv_init_workarounds(struct intel_engine_cs *ring)
 	/* Improve HiZ throughput on CHV. */
 	WA_SET_BIT_MASKED(HIZ_CHICKEN, CHV_HZ_8X8_MODE_IN_1X);
 
-	/*
-	 * 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_SET_FIELD_MASKED(GEN7_GT_MODE,
-			    GEN6_WIZ_HASHING_MASK,
-			    GEN6_WIZ_HASHING_16x4);
-
 	return 0;
 }
 
-- 
1.9.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 7/7] drm/i915/gen8: Move HiZ RAW stall optimization disable WA to common init fn

[Arun Siluvery]

Signed-off-by: Arun Siluvery <arun.siluvery@linux.intel.com>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 25 ++++++++++---------------
 1 file changed, 10 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index c681c66..fdff606 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -819,6 +819,16 @@ static int gen8_init_workarounds(struct intel_engine_cs *ring)
 	/* Wa4x4STCOptimizationDisable:bdw,chv */
 	WA_SET_BIT_MASKED(CACHE_MODE_1, GEN8_4x4_STC_OPTIMIZATION_DISABLE);
 
+	/* From the Haswell PRM, Command Reference: Registers, CACHE_MODE_0:
+	 * "The Hierarchical Z RAW Stall Optimization allows non-overlapping
+	 *  polygons in the same 8x4 pixel/sample area to be processed without
+	 *  stalling waiting for the earlier ones to write to Hierarchical Z
+	 *  buffer."
+	 *
+	 * This optimization is off by default for BDW and CHV; turn it on.
+	 */
+	WA_CLR_BIT_MASKED(CACHE_MODE_0_GEN7, HIZ_RAW_STALL_OPT_DISABLE);
+
 	/*
 	 * BSpec recommends 8x4 when MSAA is used,
 	 * however in practice 16x4 seems fastest.
@@ -865,16 +875,6 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
 			  /* WaDisableFenceDestinationToSLM:bdw (pre-prod) */
 			  (IS_BDW_GT3(dev) ? HDC_FENCE_DEST_SLM_DISABLE : 0));
 
-	/* From the Haswell PRM, Command Reference: Registers, CACHE_MODE_0:
-	 * "The Hierarchical Z RAW Stall Optimization allows non-overlapping
-	 *  polygons in the same 8x4 pixel/sample area to be processed without
-	 *  stalling waiting for the earlier ones to write to Hierarchical Z
-	 *  buffer."
-	 *
-	 * This optimization is off by default for Broadwell; turn it on.
-	 */
-	WA_CLR_BIT_MASKED(CACHE_MODE_0_GEN7, HIZ_RAW_STALL_OPT_DISABLE);
-
 	return 0;
 }
 
@@ -898,11 +898,6 @@ static int chv_init_workarounds(struct intel_engine_cs *ring)
 			  HDC_FORCE_NON_COHERENT |
 			  HDC_DONOT_FETCH_MEM_WHEN_MASKED);
 
-	/* According to the CACHE_MODE_0 default value documentation, some
-	 * CHV platforms disable this optimization by default.  Turn it on.
-	 */
-	WA_CLR_BIT_MASKED(CACHE_MODE_0_GEN7, HIZ_RAW_STALL_OPT_DISABLE);
-
 	/* Improve HiZ throughput on CHV. */
 	WA_SET_BIT_MASKED(HIZ_CHICKEN, CHV_HZ_8X8_MODE_IN_1X);
 
-- 
1.9.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 5/7] drm/i915/gen8: Move GEN8_ROW_CHICKEN WA to common init fn

[Ville Syrjälä]

On Fri, Sep 25, 2015 at 02:23:32PM +0100, Arun Siluvery wrote:
> Move WaDisablePartialInstShootdown and WaDisableThreadStallDopClockGating

NAK for WaDisableThreadStallDopClockGating, we don't want it on production BDW.
Should just kill it for BDW instead.

> 
> Signed-off-by: Arun Siluvery <arun.siluvery@linux.intel.com>
> ---
>  drivers/gpu/drm/i915/intel_ringbuffer.c | 18 ++++++------------
>  1 file changed, 6 insertions(+), 12 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index a06788a..5d15e31 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -807,6 +807,12 @@ static int gen8_init_workarounds(struct intel_engine_cs *ring)
>  
>  	WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING);
>  
> +	/* WaDisablePartialInstShootdown:bdw,chv */
> +	/* WaDisableThreadStallDopClockGating:chv, bdw (pre-production) */
> +	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
> +			  PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE |
> +			  STALL_DOP_GATING_DISABLE);
> +
>  	/* WaDisableAsyncFlipPerfMode:bdw,chv */
>  	WA_SET_BIT_MASKED(MI_MODE, ASYNC_FLIP_PERF_DISABLE);
>  
> @@ -826,12 +832,6 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
>  	if (ret)
>  		return ret;
>  
> -	/* WaDisablePartialInstShootdown:bdw */
> -	/* WaDisableThreadStallDopClockGating:bdw (pre-production) */
> -	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
> -			  PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE |
> -			  STALL_DOP_GATING_DISABLE);
> -
>  	/* WaDisableDopClockGating:bdw */
>  	WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2,
>  			  DOP_CLOCK_GATING_DISABLE);
> @@ -888,12 +888,6 @@ static int chv_init_workarounds(struct intel_engine_cs *ring)
>  	if (ret)
>  		return ret;
>  
> -	/* WaDisablePartialInstShootdown:chv */
> -	/* WaDisableThreadStallDopClockGating:chv */
> -	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
> -			  PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE |
> -			  STALL_DOP_GATING_DISABLE);
> -
>  	/* Use Force Non-Coherent whenever executing a 3D context. This is a
>  	 * workaround for a possible hang in the unlikely event a TLB
>  	 * invalidation occurs during a PSD flush.
> -- 
> 1.9.1
> 
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx

-- 
Ville Syrjälä
Intel OTC
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 7/7] drm/i915/gen8: Move HiZ RAW stall optimization disable WA to common init fn

[Ville Syrjälä]

On Fri, Sep 25, 2015 at 02:23:34PM +0100, Arun Siluvery wrote:
> Signed-off-by: Arun Siluvery <arun.siluvery@linux.intel.com>
> ---
>  drivers/gpu/drm/i915/intel_ringbuffer.c | 25 ++++++++++---------------
>  1 file changed, 10 insertions(+), 15 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index c681c66..fdff606 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -819,6 +819,16 @@ static int gen8_init_workarounds(struct intel_engine_cs *ring)
>  	/* Wa4x4STCOptimizationDisable:bdw,chv */
>  	WA_SET_BIT_MASKED(CACHE_MODE_1, GEN8_4x4_STC_OPTIMIZATION_DISABLE);
>  
> +	/* From the Haswell PRM, Command Reference: Registers, CACHE_MODE_0:
> +	 * "The Hierarchical Z RAW Stall Optimization allows non-overlapping
> +	 *  polygons in the same 8x4 pixel/sample area to be processed without
> +	 *  stalling waiting for the earlier ones to write to Hierarchical Z
> +	 *  buffer."
> +	 *
> +	 * This optimization is off by default for BDW and CHV; turn it on.
> +	 */
> +	WA_CLR_BIT_MASKED(CACHE_MODE_0_GEN7, HIZ_RAW_STALL_OPT_DISABLE);
> +

Ok, so apart from the threadstall thing the rest looks reasonable.
One request though, can you put w/as into some decent order? I
suggest ordering based on the register, so eg.

instpm
mi_mode
row chicken
half slice chicken
common slice chicken
hdc chicken
cache_mode_0
cache_mode_1
gt_mode

I think that should match reasonably well what we have in most places.
Or you can come up with something better if you wish, as long as the
same/similar registers are grouped decently.

>  	/*
>  	 * BSpec recommends 8x4 when MSAA is used,
>  	 * however in practice 16x4 seems fastest.
> @@ -865,16 +875,6 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
>  			  /* WaDisableFenceDestinationToSLM:bdw (pre-prod) */
>  			  (IS_BDW_GT3(dev) ? HDC_FENCE_DEST_SLM_DISABLE : 0));
>  
> -	/* From the Haswell PRM, Command Reference: Registers, CACHE_MODE_0:
> -	 * "The Hierarchical Z RAW Stall Optimization allows non-overlapping
> -	 *  polygons in the same 8x4 pixel/sample area to be processed without
> -	 *  stalling waiting for the earlier ones to write to Hierarchical Z
> -	 *  buffer."
> -	 *
> -	 * This optimization is off by default for Broadwell; turn it on.
> -	 */
> -	WA_CLR_BIT_MASKED(CACHE_MODE_0_GEN7, HIZ_RAW_STALL_OPT_DISABLE);
> -
>  	return 0;
>  }
>  
> @@ -898,11 +898,6 @@ static int chv_init_workarounds(struct intel_engine_cs *ring)
>  			  HDC_FORCE_NON_COHERENT |
>  			  HDC_DONOT_FETCH_MEM_WHEN_MASKED);
>  
> -	/* According to the CACHE_MODE_0 default value documentation, some
> -	 * CHV platforms disable this optimization by default.  Turn it on.
> -	 */
> -	WA_CLR_BIT_MASKED(CACHE_MODE_0_GEN7, HIZ_RAW_STALL_OPT_DISABLE);
> -
>  	/* Improve HiZ throughput on CHV. */
>  	WA_SET_BIT_MASKED(HIZ_CHICKEN, CHV_HZ_8X8_MODE_IN_1X);
>  
> -- 
> 1.9.1
> 
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx

-- 
Ville Syrjälä
Intel OTC
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx