Skip to contentSkip to conversation

drm/i915: Move WaBarrierPerformanceFixDisable:skl to skl code from chv code

PATCH In review [email protected] 4 participants 10 messages Jun 2, 2015 – Jun 4, 2015

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

PATCH 1/3 drm/i915: Move WaBarrierPerformanceFixDisable:skl to skl code from chv code

From: Ville Syrjälä <[email protected]>

commit 65ca7514e21adbee25b8175fc909759c735d00ff
Author: Damien Lespiau <[email protected]>
Date: Mon Feb 9 19:33:22 2015 +0000

drm/i915/skl: Implement WaBarrierPerformanceFixDisable

got misapplied and the code landed in chv_init_workarounds() instead of the intended skl_init_workarounds(). Move it over to the right place.

---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)
drivers/gpu/drm/i915/intel_ringbuffer.c +7 -7
index d934f85..edd47ba 100644
@@ -901,13 +901,6 @@ static int chv_init_workarounds(struct intel_engine_cs *ring)
 			    GEN6_WIZ_HASHING_MASK,
 			    GEN6_WIZ_HASHING_16x4);
 
-	if (INTEL_REVID(dev) == SKL_REVID_C0 ||
-	    INTEL_REVID(dev) == SKL_REVID_D0)
-		/* WaBarrierPerformanceFixDisable:skl */
-		WA_SET_BIT_MASKED(HDC_CHICKEN0,
-				  HDC_FENCE_DEST_SLM_DISABLE |
-				  HDC_BARRIER_PERFORMANCE_DISABLE);
-
 	return 0;
 }
 
@@ -1041,6 +1034,13 @@ static int skl_init_workarounds(struct intel_engine_cs *ring)
 				  HDC_FORCE_NON_COHERENT);
 	}
 
+	if (INTEL_REVID(dev) == SKL_REVID_C0 ||
+	    INTEL_REVID(dev) == SKL_REVID_D0)
+		/* WaBarrierPerformanceFixDisable:skl */
+		WA_SET_BIT_MASKED(HDC_CHICKEN0,
+				  HDC_FENCE_DEST_SLM_DISABLE |
+				  HDC_BARRIER_PERFORMANCE_DISABLE);
+
 	return skl_tune_iz_hashing(ring);
 }
 
Signature · 6 lines
2.3.6

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
#1 lore raw

PATCH 2/3 drm/i915: Set INSTPM_FORCE_ORDERING via LRI on gen8, drop it on gen9+

From: Ville Syrjälä <[email protected]>

INSTPM is saved in the logical context so we should initialize it using LRIs on gen8. It actually defaults to 1 starting from HSW, but let's keep the write around anyway.

Also drop the INSTPM_FORCE_ORDERING setup entirely on gen9+ since it's now a reserved bit.

---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)
drivers/gpu/drm/i915/intel_ringbuffer.c +5 -1
index edd47ba..06f4b22 100644
@@ -800,6 +800,8 @@ static int bdw_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);
+
 	/* WaDisablePartialInstShootdown:bdw */
 	/* WaDisableThreadStallDopClockGating:bdw (pre-production) */
 	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
@@ -861,6 +863,8 @@ static int chv_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);
+
 	/* WaDisablePartialInstShootdown:chv */
 	/* WaDisableThreadStallDopClockGating:chv */
 	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
@@ -1132,7 +1136,7 @@ static int init_render_ring(struct intel_engine_cs *ring)
 			   _MASKED_BIT_DISABLE(CM0_STC_EVICT_DISABLE_LRA_SNB));
 	}
 
-	if (INTEL_INFO(dev)->gen >= 6)
+	if (INTEL_INFO(dev)->gen >= 6 && INTEL_INFO(dev)->gen < 8)
 		I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
 
 	if (HAS_L3_DPF(dev))
Signature · 6 lines
2.3.6

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Reviewed-by on v1 2/3
#2 lore raw

Re: [PATCH 2/3] drm/i915: Set INSTPM_FORCE_ORDERING via LRI on gen8, drop it on gen9+

Quoted 10 lines · On Tue, Jun 02, 2015 at 03:37:36PM +0300, [email protected] wrote:

From: Ville Syrjälä <[email protected]>

INSTPM is saved in the logical context so we should initialize it using LRIs on gen8. It actually defaults to 1 starting from HSW, but let's keep the write around anyway.

Also drop the INSTPM_FORCE_ORDERING setup entirely on gen9+ since it's now a reserved bit.

Signature · 1 line
Damien
Quoted 42 lines
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)
drivers/gpu/drm/i915/intel_ringbuffer.c +5 -1
index edd47ba..06f4b22 100644
@@ -800,6 +800,8 @@ static int bdw_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);
+
 	/* WaDisablePartialInstShootdown:bdw */
 	/* WaDisableThreadStallDopClockGating:bdw (pre-production) */
 	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
@@ -861,6 +863,8 @@ static int chv_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);
+
 	/* WaDisablePartialInstShootdown:chv */
 	/* WaDisableThreadStallDopClockGating:chv */
 	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
@@ -1132,7 +1136,7 @@ static int init_render_ring(struct intel_engine_cs *ring)
 			   _MASKED_BIT_DISABLE(CM0_STC_EVICT_DISABLE_LRA_SNB));
 	}
 
-	if (INTEL_INFO(dev)->gen >= 6)
+	if (INTEL_INFO(dev)->gen >= 6 && INTEL_INFO(dev)->gen < 8)
 		I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
 
 	if (HAS_L3_DPF(dev))
Signature · 6 lines
2.3.6

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

#3 lore raw

PATCH 3/3 drm/i915: Apply WaDisableAsyncFlipPerfMode via LRIs on gen8

In reply to [email protected]

From: Ville Syrjälä <[email protected]>

MI_MODE is saved in the logical context so WaDisableAsyncFlipPerfMode must be applied using LRIs on gen8.

---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)
drivers/gpu/drm/i915/intel_ringbuffer.c +8 -2
index 06f4b22..b70d25b 100644
@@ -802,6 +802,9 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
 
 	WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING);
 
+	/* 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,
@@ -865,6 +868,9 @@ static int chv_init_workarounds(struct intel_engine_cs *ring)
 
 	WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING);
 
+	/* WaDisableAsyncFlipPerfMode:chv */
+	WA_SET_BIT_MASKED(MI_MODE, ASYNC_FLIP_PERF_DISABLE);
+
 	/* WaDisablePartialInstShootdown:chv */
 	/* WaDisableThreadStallDopClockGating:chv */
 	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
@@ -1109,9 +1115,9 @@ static int init_render_ring(struct intel_engine_cs *ring)
 	 * to use MI_WAIT_FOR_EVENT within the CS. It should already be
 	 * programmed to '1' on all products.
 	 *
-	 * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv,bdw,chv
+	 * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv
 	 */
-	if (INTEL_INFO(dev)->gen >= 6 && INTEL_INFO(dev)->gen < 9)
+	if (INTEL_INFO(dev)->gen >= 6 && INTEL_INFO(dev)->gen < 8)
 		I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(ASYNC_FLIP_PERF_DISABLE));
 
 	/* Required for the hardware to program scanline values for waiting */
Signature · 6 lines
2.3.6

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Tested-by on v1 3/3
#4 lore raw

Re: [PATCH 3/3] drm/i915: Apply WaDisableAsyncFlipPerfMode via LRIs on gen8

Task id: 6524 -------------------------------------Summary-------------------------------------
Platform Delta drm-intel-nightly Series Applied

PNV                                  276/276              276/276
ILK                                  303/303              303/303
SNB                 -1              315/315              314/315
IVB                                  343/343              343/343
BYT                                  287/287              287/287
BDW                                  321/321              321/321

-------------------------------------Detailed-------------------------------------
Platform Test drm-intel-nightly Series Applied
*SNB igt@pm_rpm@dpms-mode-unset-non-lpsp PASS(1) DMESG_WARN(1)
(dmesg patch applied)WARNING:at_drivers/gpu/drm/i915/intel_uncore.c:#assert_device_not_suspended[i915]()@WARNING:.* at .* assert_device_not_suspended+0x
Note: You need to pay more attention to line start with '*'
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

Reviewed-by on v1 3/3
#5 lore raw

Re: [PATCH 3/3] drm/i915: Apply WaDisableAsyncFlipPerfMode via LRIs on gen8

In reply to [email protected]
Quoted 6 lines · On Tue, Jun 02, 2015 at 03:37:37PM +0300, [email protected] wrote:

From: Ville Syrjälä <[email protected]>

MI_MODE is saved in the logical context so WaDisableAsyncFlipPerfMode must be applied using LRIs on gen8.

Signature · 1 line
Damien
Quoted 47 lines
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)
drivers/gpu/drm/i915/intel_ringbuffer.c +8 -2
index 06f4b22..b70d25b 100644
@@ -802,6 +802,9 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
 
 	WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING);
 
+	/* 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,
@@ -865,6 +868,9 @@ static int chv_init_workarounds(struct intel_engine_cs *ring)
 
 	WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING);
 
+	/* WaDisableAsyncFlipPerfMode:chv */
+	WA_SET_BIT_MASKED(MI_MODE, ASYNC_FLIP_PERF_DISABLE);
+
 	/* WaDisablePartialInstShootdown:chv */
 	/* WaDisableThreadStallDopClockGating:chv */
 	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
@@ -1109,9 +1115,9 @@ static int init_render_ring(struct intel_engine_cs *ring)
 	 * to use MI_WAIT_FOR_EVENT within the CS. It should already be
 	 * programmed to '1' on all products.
 	 *
-	 * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv,bdw,chv
+	 * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv
 	 */
-	if (INTEL_INFO(dev)->gen >= 6 && INTEL_INFO(dev)->gen < 9)
+	if (INTEL_INFO(dev)->gen >= 6 && INTEL_INFO(dev)->gen < 8)
 		I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(ASYNC_FLIP_PERF_DISABLE));
 
 	/* Required for the hardware to program scanline values for waiting */
Signature · 6 lines
2.3.6

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

maintainer
#6 lore raw

Re: [PATCH 3/3] drm/i915: Apply WaDisableAsyncFlipPerfMode via LRIs on gen8

Quoted 9 lines · Damien Lespiau
Quoted 6 lines · On Tue, Jun 02, 2015 at 03:37:37PM +0300, [email protected] wrote:

From: Ville Syrjälä <[email protected]>

MI_MODE is saved in the logical context so WaDisableAsyncFlipPerfMode must be applied using LRIs on gen8.

Thanks, pushed all patches to drm-intel-next-queued.

BR,
Jani.

Quoted 55 lines
Signature · 2 lines
-- 
Damien
Quoted 47 lines
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)
drivers/gpu/drm/i915/intel_ringbuffer.c +8 -2
index 06f4b22..b70d25b 100644
@@ -802,6 +802,9 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
 
 	WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING);
 
+	/* 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,
@@ -865,6 +868,9 @@ static int chv_init_workarounds(struct intel_engine_cs *ring)
 
 	WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING);
 
+	/* WaDisableAsyncFlipPerfMode:chv */
+	WA_SET_BIT_MASKED(MI_MODE, ASYNC_FLIP_PERF_DISABLE);
+
 	/* WaDisablePartialInstShootdown:chv */
 	/* WaDisableThreadStallDopClockGating:chv */
 	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
@@ -1109,9 +1115,9 @@ static int init_render_ring(struct intel_engine_cs *ring)
 	 * to use MI_WAIT_FOR_EVENT within the CS. It should already be
 	 * programmed to '1' on all products.
 	 *
-	 * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv,bdw,chv
+	 * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv
 	 */
-	if (INTEL_INFO(dev)->gen >= 6 && INTEL_INFO(dev)->gen < 9)
+	if (INTEL_INFO(dev)->gen >= 6 && INTEL_INFO(dev)->gen < 8)
 		I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(ASYNC_FLIP_PERF_DISABLE));
 
 	/* Required for the hardware to program scanline values for waiting */
Signature · 6 lines
2.3.6

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

Signature · 5 lines
Jani Nikula, Intel Open Source Technology Center
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Reviewed-by on v1 1/3
#7 lore raw
In reply to [email protected]
Quoted 6 lines · On Tue, Jun 02, 2015 at 03:37:35PM +0300, [email protected] wrote:

From: Ville Syrjälä <[email protected]>

commit 65ca7514e21adbee25b8175fc909759c735d00ff
Author: Damien Lespiau <[email protected]>
Date: Mon Feb 9 19:33:22 2015 +0000

Quoted 8 lines

drm/i915/skl: Implement WaBarrierPerformanceFixDisable

got misapplied and the code landed in chv_init_workarounds() instead of the intended skl_init_workarounds(). Move it over to the right place.

---

Signature · 1 line
Damien
Quoted 38 lines
 drivers/gpu/drm/i915/intel_ringbuffer.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)
drivers/gpu/drm/i915/intel_ringbuffer.c +7 -7
index d934f85..edd47ba 100644
@@ -901,13 +901,6 @@ static int chv_init_workarounds(struct intel_engine_cs *ring)
 			    GEN6_WIZ_HASHING_MASK,
 			    GEN6_WIZ_HASHING_16x4);
 
-	if (INTEL_REVID(dev) == SKL_REVID_C0 ||
-	    INTEL_REVID(dev) == SKL_REVID_D0)
-		/* WaBarrierPerformanceFixDisable:skl */
-		WA_SET_BIT_MASKED(HDC_CHICKEN0,
-				  HDC_FENCE_DEST_SLM_DISABLE |
-				  HDC_BARRIER_PERFORMANCE_DISABLE);
-
 	return 0;
 }
 
@@ -1041,6 +1034,13 @@ static int skl_init_workarounds(struct intel_engine_cs *ring)
 				  HDC_FORCE_NON_COHERENT);
 	}
 
+	if (INTEL_REVID(dev) == SKL_REVID_C0 ||
+	    INTEL_REVID(dev) == SKL_REVID_D0)
+		/* WaBarrierPerformanceFixDisable:skl */
+		WA_SET_BIT_MASKED(HDC_CHICKEN0,
+				  HDC_FENCE_DEST_SLM_DISABLE |
+				  HDC_BARRIER_PERFORMANCE_DISABLE);
+
 	return skl_tune_iz_hashing(ring);
 }
 
Signature · 1 line
2.3.6

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

maintainer
#8 lore raw
Quoted 9 lines · Damien Lespiau
Quoted 8 lines · On Tue, Jun 02, 2015 at 03:37:35PM +0300, [email protected] wrote:

From: Ville Syrjälä <[email protected]>

commit 65ca7514e21adbee25b8175fc909759c735d00ff
Author: Damien Lespiau <[email protected]>
Date: Mon Feb 9 19:33:22 2015 +0000

drm/i915/skl: Implement WaBarrierPerformanceFixDisable

Quoted 8 lines
Quoted 6 lines

got misapplied and the code landed in chv_init_workarounds() instead of the intended skl_init_workarounds(). Move it over to the right place.

---

Pushed this one patch to drm-intel-next-queued, thanks for the patch and review.

I presume the r-b was for patch 1 only, any chance you could look at the other two, Damien?

BR,
Jani.

Quoted 46 lines
Signature · 2 lines
-- 
Damien
Quoted 38 lines
 drivers/gpu/drm/i915/intel_ringbuffer.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)
drivers/gpu/drm/i915/intel_ringbuffer.c +7 -7
index d934f85..edd47ba 100644
@@ -901,13 +901,6 @@ static int chv_init_workarounds(struct intel_engine_cs *ring)
 			    GEN6_WIZ_HASHING_MASK,
 			    GEN6_WIZ_HASHING_16x4);
 
-	if (INTEL_REVID(dev) == SKL_REVID_C0 ||
-	    INTEL_REVID(dev) == SKL_REVID_D0)
-		/* WaBarrierPerformanceFixDisable:skl */
-		WA_SET_BIT_MASKED(HDC_CHICKEN0,
-				  HDC_FENCE_DEST_SLM_DISABLE |
-				  HDC_BARRIER_PERFORMANCE_DISABLE);
-
 	return 0;
 }
 
@@ -1041,6 +1034,13 @@ static int skl_init_workarounds(struct intel_engine_cs *ring)
 				  HDC_FORCE_NON_COHERENT);
 	}
 
+	if (INTEL_REVID(dev) == SKL_REVID_C0 ||
+	    INTEL_REVID(dev) == SKL_REVID_D0)
+		/* WaBarrierPerformanceFixDisable:skl */
+		WA_SET_BIT_MASKED(HDC_CHICKEN0,
+				  HDC_FENCE_DEST_SLM_DISABLE |
+				  HDC_BARRIER_PERFORMANCE_DISABLE);
+
 	return skl_tune_iz_hashing(ring);
 }
 
Signature · 1 line
2.3.6

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

Signature · 5 lines
Jani Nikula, Intel Open Source Technology Center
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
maintainer
#9 lore raw
Quoted 13 lines · Jani Nikula
Quoted 12 lines · Damien Lespiau
Quoted 11 lines · On Tue, Jun 02, 2015 at 03:37:35PM +0300, [email protected] wrote:

From: Ville Syrjälä <[email protected]>

commit 65ca7514e21adbee25b8175fc909759c735d00ff
Author: Damien Lespiau <[email protected]>
Date: Mon Feb 9 19:33:22 2015 +0000

drm/i915/skl: Implement WaBarrierPerformanceFixDisable

got misapplied and the code landed in chv_init_workarounds() instead of the intended skl_init_workarounds(). Move it over to the right place.

Quoted 8 lines
Quoted 5 lines
Quoted 3 lines

---

Pushed this one patch to drm-intel-next-queued, thanks for the patch and review.

...and cherry-picked to drm-intel-fixes because it affects CHV code.

BR,
Jani.

Quoted 58 lines

I presume the r-b was for patch 1 only, any chance you could look at the other two, Damien?

BR,
Jani.

Quoted 46 lines
Signature · 2 lines
-- 
Damien
Quoted 38 lines
 drivers/gpu/drm/i915/intel_ringbuffer.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)
drivers/gpu/drm/i915/intel_ringbuffer.c +7 -7
index d934f85..edd47ba 100644
@@ -901,13 +901,6 @@ static int chv_init_workarounds(struct intel_engine_cs *ring)
 			    GEN6_WIZ_HASHING_MASK,
 			    GEN6_WIZ_HASHING_16x4);
 
-	if (INTEL_REVID(dev) == SKL_REVID_C0 ||
-	    INTEL_REVID(dev) == SKL_REVID_D0)
-		/* WaBarrierPerformanceFixDisable:skl */
-		WA_SET_BIT_MASKED(HDC_CHICKEN0,
-				  HDC_FENCE_DEST_SLM_DISABLE |
-				  HDC_BARRIER_PERFORMANCE_DISABLE);
-
 	return 0;
 }
 
@@ -1041,6 +1034,13 @@ static int skl_init_workarounds(struct intel_engine_cs *ring)
 				  HDC_FORCE_NON_COHERENT);
 	}
 
+	if (INTEL_REVID(dev) == SKL_REVID_C0 ||
+	    INTEL_REVID(dev) == SKL_REVID_D0)
+		/* WaBarrierPerformanceFixDisable:skl */
+		WA_SET_BIT_MASKED(HDC_CHICKEN0,
+				  HDC_FENCE_DEST_SLM_DISABLE |
+				  HDC_BARRIER_PERFORMANCE_DISABLE);
+
 	return skl_tune_iz_hashing(ring);
 }
 
Signature · 1 line
2.3.6

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

Signature · 1 line
Jani Nikula, Intel Open Source Technology Center
Signature · 5 lines
Jani Nikula, Intel Open Source Technology Center
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx