All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH] drm/i915/bdw: Cleanup pre prod workarounds
@ 2014-09-19 13:05 Mika Kuoppala
  2014-09-19 13:55 ` Ville Syrjälä
  0 siblings, 1 reply; 8+ messages in thread
From: Mika Kuoppala @ 2014-09-19 13:05 UTC (permalink / raw)
  To: intel-gfx

as these have been fixed in production hw and hurt performance
if applied.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=83482
Tested-by: zhoujian <jianx.zhou@intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 13 +------------
 1 file changed, 1 insertion(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 681ea86..dfb3bc6 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -722,19 +722,8 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
 	intel_ring_emit_wa(ring, GEN7_ROW_CHICKEN2,
 			   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
 
-	/*
-	 * This GEN8_CENTROID_PIXEL_OPT_DIS W/A is only needed for
-	 * pre-production hardware
-	 */
 	intel_ring_emit_wa(ring, HALF_SLICE_CHICKEN3,
-			   _MASKED_BIT_ENABLE(GEN8_CENTROID_PIXEL_OPT_DIS
-					      | GEN8_SAMPLER_POWER_BYPASS_DIS));
-
-	intel_ring_emit_wa(ring, GEN7_HALF_SLICE_CHICKEN1,
-			   _MASKED_BIT_ENABLE(GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE));
-
-	intel_ring_emit_wa(ring, COMMON_SLICE_CHICKEN2,
-			   _MASKED_BIT_ENABLE(GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE));
+			   _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));
 
 	/* Use Force Non-Coherent whenever executing a 3D context. This is a
 	 * workaround for for a possible hang in the unlikely event a TLB
-- 
1.9.1

^ permalink raw reply related	[flat|nested] 8+ messages in thread
* Re: [PATCH] drm/i915/bdw: Cleanup pre prod workarounds
  2014-09-19 13:05 [PATCH] drm/i915/bdw: Cleanup pre prod workarounds Mika Kuoppala
@ 2014-09-19 13:55 ` Ville Syrjälä
  2014-09-19 17:05   ` Mika Kuoppala
  0 siblings, 1 reply; 8+ messages in thread
From: Ville Syrjälä @ 2014-09-19 13:55 UTC (permalink / raw)
  To: Mika Kuoppala; +Cc: intel-gfx

On Fri, Sep 19, 2014 at 04:05:08PM +0300, Mika Kuoppala wrote:
> as these have been fixed in production hw and hurt performance
> if applied.
> 
> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=83482
> Tested-by: zhoujian <jianx.zhou@intel.com>
> Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
> ---
>  drivers/gpu/drm/i915/intel_ringbuffer.c | 13 +------------
>  1 file changed, 1 insertion(+), 12 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index 681ea86..dfb3bc6 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -722,19 +722,8 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
>  	intel_ring_emit_wa(ring, GEN7_ROW_CHICKEN2,
>  			   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
>  
> -	/*
> -	 * This GEN8_CENTROID_PIXEL_OPT_DIS W/A is only needed for
> -	 * pre-production hardware
> -	 */
>  	intel_ring_emit_wa(ring, HALF_SLICE_CHICKEN3,
> -			   _MASKED_BIT_ENABLE(GEN8_CENTROID_PIXEL_OPT_DIS
> -					      | GEN8_SAMPLER_POWER_BYPASS_DIS));
> -
> -	intel_ring_emit_wa(ring, GEN7_HALF_SLICE_CHICKEN1,
> -			   _MASKED_BIT_ENABLE(GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE));
> -
> -	intel_ring_emit_wa(ring, COMMON_SLICE_CHICKEN2,
> -			   _MASKED_BIT_ENABLE(GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE));
> +			   _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));

You should adjust the requested ring space too. Looks like this will
leave the number of intel_ring_emit_wa() calls even so no need to
worry about the QW tail padding quite yet.

>  
>  	/* Use Force Non-Coherent whenever executing a 3D context. This is a
>  	 * workaround for for a possible hang in the unlikely event a TLB
> -- 
> 1.9.1
> 
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx

-- 
Ville Syrjälä
Intel OTC

^ permalink raw reply	[flat|nested] 8+ messages in thread
* [PATCH] drm/i915/bdw: Cleanup pre prod workarounds
  2014-09-19 13:55 ` Ville Syrjälä
@ 2014-09-19 17:05   ` Mika Kuoppala
  2014-09-19 17:49     ` Ville Syrjälä
  0 siblings, 1 reply; 8+ messages in thread
From: Mika Kuoppala @ 2014-09-19 17:05 UTC (permalink / raw)
  To: intel-gfx

as these have been fixed in production hw and hurt performance
if applied.

v2: adjust requested ring space (Ville)

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=83482
Tested-by: zhoujian <jianx.zhou@intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 15 ++-------------
 1 file changed, 2 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 681ea86..679a3c7 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -707,7 +707,7 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
 	 * update the number of dwords required based on the
 	 * actual number of workarounds applied
 	 */
-	ret = intel_ring_begin(ring, 24);
+	ret = intel_ring_begin(ring, 18);
 	if (ret)
 		return ret;
 
@@ -722,19 +722,8 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
 	intel_ring_emit_wa(ring, GEN7_ROW_CHICKEN2,
 			   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
 
-	/*
-	 * This GEN8_CENTROID_PIXEL_OPT_DIS W/A is only needed for
-	 * pre-production hardware
-	 */
 	intel_ring_emit_wa(ring, HALF_SLICE_CHICKEN3,
-			   _MASKED_BIT_ENABLE(GEN8_CENTROID_PIXEL_OPT_DIS
-					      | GEN8_SAMPLER_POWER_BYPASS_DIS));
-
-	intel_ring_emit_wa(ring, GEN7_HALF_SLICE_CHICKEN1,
-			   _MASKED_BIT_ENABLE(GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE));
-
-	intel_ring_emit_wa(ring, COMMON_SLICE_CHICKEN2,
-			   _MASKED_BIT_ENABLE(GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE));
+			   _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));
 
 	/* Use Force Non-Coherent whenever executing a 3D context. This is a
 	 * workaround for for a possible hang in the unlikely event a TLB
-- 
1.9.1

^ permalink raw reply related	[flat|nested] 8+ messages in thread
* Re: [PATCH] drm/i915/bdw: Cleanup pre prod workarounds
  2014-09-19 17:05   ` Mika Kuoppala
@ 2014-09-19 17:49     ` Ville Syrjälä
  2014-09-23  8:20       ` Daniel Vetter
  0 siblings, 1 reply; 8+ messages in thread
From: Ville Syrjälä @ 2014-09-19 17:49 UTC (permalink / raw)
  To: Mika Kuoppala; +Cc: intel-gfx

On Fri, Sep 19, 2014 at 08:05:26PM +0300, Mika Kuoppala wrote:
> as these have been fixed in production hw and hurt performance
> if applied.
> 
> v2: adjust requested ring space (Ville)
> 
> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=83482
> Tested-by: zhoujian <jianx.zhou@intel.com>
> Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>

Documentation agrees that these can go.
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>

> ---
>  drivers/gpu/drm/i915/intel_ringbuffer.c | 15 ++-------------
>  1 file changed, 2 insertions(+), 13 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index 681ea86..679a3c7 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -707,7 +707,7 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
>  	 * update the number of dwords required based on the
>  	 * actual number of workarounds applied
>  	 */
> -	ret = intel_ring_begin(ring, 24);
> +	ret = intel_ring_begin(ring, 18);
>  	if (ret)
>  		return ret;
>  
> @@ -722,19 +722,8 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
>  	intel_ring_emit_wa(ring, GEN7_ROW_CHICKEN2,
>  			   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
>  
> -	/*
> -	 * This GEN8_CENTROID_PIXEL_OPT_DIS W/A is only needed for
> -	 * pre-production hardware
> -	 */
>  	intel_ring_emit_wa(ring, HALF_SLICE_CHICKEN3,
> -			   _MASKED_BIT_ENABLE(GEN8_CENTROID_PIXEL_OPT_DIS
> -					      | GEN8_SAMPLER_POWER_BYPASS_DIS));
> -
> -	intel_ring_emit_wa(ring, GEN7_HALF_SLICE_CHICKEN1,
> -			   _MASKED_BIT_ENABLE(GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE));
> -
> -	intel_ring_emit_wa(ring, COMMON_SLICE_CHICKEN2,
> -			   _MASKED_BIT_ENABLE(GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE));
> +			   _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));
>  
>  	/* Use Force Non-Coherent whenever executing a 3D context. This is a
>  	 * workaround for for a possible hang in the unlikely event a TLB
> -- 
> 1.9.1

-- 
Ville Syrjälä
Intel OTC

^ permalink raw reply	[flat|nested] 8+ messages in thread
* Re: [PATCH] drm/i915/bdw: Cleanup pre prod workarounds
  2014-09-19 17:49     ` Ville Syrjälä
@ 2014-09-23  8:20       ` Daniel Vetter
  2014-09-23 11:48         ` Jani Nikula
  0 siblings, 1 reply; 8+ messages in thread
From: Daniel Vetter @ 2014-09-23  8:20 UTC (permalink / raw)
  To: Ville Syrjälä; +Cc: intel-gfx

On Fri, Sep 19, 2014 at 08:49:06PM +0300, Ville Syrjälä wrote:
> On Fri, Sep 19, 2014 at 08:05:26PM +0300, Mika Kuoppala wrote:
> > as these have been fixed in production hw and hurt performance
> > if applied.
> > 
> > v2: adjust requested ring space (Ville)
> > 
> > Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=83482
> > Tested-by: zhoujian <jianx.zhou@intel.com>
> > Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
> 
> Documentation agrees that these can go.
> Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>

Cc: stable@vger.kernel.org imo. Jani?
-Daniel

> 
> > ---
> >  drivers/gpu/drm/i915/intel_ringbuffer.c | 15 ++-------------
> >  1 file changed, 2 insertions(+), 13 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> > index 681ea86..679a3c7 100644
> > --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> > +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> > @@ -707,7 +707,7 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
> >  	 * update the number of dwords required based on the
> >  	 * actual number of workarounds applied
> >  	 */
> > -	ret = intel_ring_begin(ring, 24);
> > +	ret = intel_ring_begin(ring, 18);
> >  	if (ret)
> >  		return ret;
> >  
> > @@ -722,19 +722,8 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
> >  	intel_ring_emit_wa(ring, GEN7_ROW_CHICKEN2,
> >  			   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
> >  
> > -	/*
> > -	 * This GEN8_CENTROID_PIXEL_OPT_DIS W/A is only needed for
> > -	 * pre-production hardware
> > -	 */
> >  	intel_ring_emit_wa(ring, HALF_SLICE_CHICKEN3,
> > -			   _MASKED_BIT_ENABLE(GEN8_CENTROID_PIXEL_OPT_DIS
> > -					      | GEN8_SAMPLER_POWER_BYPASS_DIS));
> > -
> > -	intel_ring_emit_wa(ring, GEN7_HALF_SLICE_CHICKEN1,
> > -			   _MASKED_BIT_ENABLE(GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE));
> > -
> > -	intel_ring_emit_wa(ring, COMMON_SLICE_CHICKEN2,
> > -			   _MASKED_BIT_ENABLE(GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE));
> > +			   _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));
> >  
> >  	/* Use Force Non-Coherent whenever executing a 3D context. This is a
> >  	 * workaround for for a possible hang in the unlikely event a TLB
> > -- 
> > 1.9.1
> 
> -- 
> Ville Syrjälä
> Intel OTC
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx

-- 
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch

^ permalink raw reply	[flat|nested] 8+ messages in thread
* Re: [PATCH] drm/i915/bdw: Cleanup pre prod workarounds
  2014-09-23  8:20       ` Daniel Vetter
@ 2014-09-23 11:48         ` Jani Nikula
  2014-09-24  8:41           ` Daniel Vetter
  0 siblings, 1 reply; 8+ messages in thread
From: Jani Nikula @ 2014-09-23 11:48 UTC (permalink / raw)
  To: Daniel Vetter, Ville Syrjälä; +Cc: intel-gfx

On Tue, 23 Sep 2014, Daniel Vetter <daniel@ffwll.ch> wrote:
> On Fri, Sep 19, 2014 at 08:49:06PM +0300, Ville Syrjälä wrote:
>> On Fri, Sep 19, 2014 at 08:05:26PM +0300, Mika Kuoppala wrote:
>> > as these have been fixed in production hw and hurt performance
>> > if applied.
>> > 
>> > v2: adjust requested ring space (Ville)
>> > 
>> > Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=83482
>> > Tested-by: zhoujian <jianx.zhou@intel.com>
>> > Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
>> 
>> Documentation agrees that these can go.
>> Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
>
> Cc: stable@vger.kernel.org imo. Jani?

This depends on

commit 86d7f23842f1bce3ab5e8c8d0c676112bbc4c99b
Author: Arun Siluvery <arun.siluvery@linux.intel.com>
Date:   Tue Aug 26 14:44:50 2014 +0100

    drm/i915/bdw: Apply workarounds in render ring init function

which brought the problem to daylight to begin with. That's not in
3.17-rc6. I'm not sure if that one has additional dependencies, but
perhaps a combined backport without an intermediate broken step is
plausible.

In any case I don't think this is something we want to rush for 3.17
now, since a release is imminent, so it'll be 3.18. Adding cc: stable is
up to you, but do note the size is beyond stable rules.


BR,
Jani.



> -Daniel
>
>> 
>> > ---
>> >  drivers/gpu/drm/i915/intel_ringbuffer.c | 15 ++-------------
>> >  1 file changed, 2 insertions(+), 13 deletions(-)
>> > 
>> > diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
>> > index 681ea86..679a3c7 100644
>> > --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
>> > +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
>> > @@ -707,7 +707,7 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
>> >  	 * update the number of dwords required based on the
>> >  	 * actual number of workarounds applied
>> >  	 */
>> > -	ret = intel_ring_begin(ring, 24);
>> > +	ret = intel_ring_begin(ring, 18);
>> >  	if (ret)
>> >  		return ret;
>> >  
>> > @@ -722,19 +722,8 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
>> >  	intel_ring_emit_wa(ring, GEN7_ROW_CHICKEN2,
>> >  			   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
>> >  
>> > -	/*
>> > -	 * This GEN8_CENTROID_PIXEL_OPT_DIS W/A is only needed for
>> > -	 * pre-production hardware
>> > -	 */
>> >  	intel_ring_emit_wa(ring, HALF_SLICE_CHICKEN3,
>> > -			   _MASKED_BIT_ENABLE(GEN8_CENTROID_PIXEL_OPT_DIS
>> > -					      | GEN8_SAMPLER_POWER_BYPASS_DIS));
>> > -
>> > -	intel_ring_emit_wa(ring, GEN7_HALF_SLICE_CHICKEN1,
>> > -			   _MASKED_BIT_ENABLE(GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE));
>> > -
>> > -	intel_ring_emit_wa(ring, COMMON_SLICE_CHICKEN2,
>> > -			   _MASKED_BIT_ENABLE(GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE));
>> > +			   _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));
>> >  
>> >  	/* Use Force Non-Coherent whenever executing a 3D context. This is a
>> >  	 * workaround for for a possible hang in the unlikely event a TLB
>> > -- 
>> > 1.9.1
>> 
>> -- 
>> Ville Syrjälä
>> Intel OTC
>> _______________________________________________
>> Intel-gfx mailing list
>> Intel-gfx@lists.freedesktop.org
>> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
>
> -- 
> Daniel Vetter
> Software Engineer, Intel Corporation
> +41 (0) 79 365 57 48 - http://blog.ffwll.ch

-- 
Jani Nikula, Intel Open Source Technology Center
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

^ permalink raw reply	[flat|nested] 8+ messages in thread
* Re: [PATCH] drm/i915/bdw: Cleanup pre prod workarounds
  2014-09-23 11:48         ` Jani Nikula
@ 2014-09-24  8:41           ` Daniel Vetter
  2014-09-24 17:46             ` Rodrigo Vivi
  0 siblings, 1 reply; 8+ messages in thread
From: Daniel Vetter @ 2014-09-24  8:41 UTC (permalink / raw)
  To: Jani Nikula; +Cc: intel-gfx

On Tue, Sep 23, 2014 at 02:48:47PM +0300, Jani Nikula wrote:
> On Tue, 23 Sep 2014, Daniel Vetter <daniel@ffwll.ch> wrote:
> > On Fri, Sep 19, 2014 at 08:49:06PM +0300, Ville Syrjälä wrote:
> >> On Fri, Sep 19, 2014 at 08:05:26PM +0300, Mika Kuoppala wrote:
> >> > as these have been fixed in production hw and hurt performance
> >> > if applied.
> >> > 
> >> > v2: adjust requested ring space (Ville)
> >> > 
> >> > Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=83482
> >> > Tested-by: zhoujian <jianx.zhou@intel.com>
> >> > Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
> >> 
> >> Documentation agrees that these can go.
> >> Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
> >
> > Cc: stable@vger.kernel.org imo. Jani?
> 
> This depends on
> 
> commit 86d7f23842f1bce3ab5e8c8d0c676112bbc4c99b
> Author: Arun Siluvery <arun.siluvery@linux.intel.com>
> Date:   Tue Aug 26 14:44:50 2014 +0100
> 
>     drm/i915/bdw: Apply workarounds in render ring init function
> 
> which brought the problem to daylight to begin with. That's not in
> 3.17-rc6. I'm not sure if that one has additional dependencies, but
> perhaps a combined backport without an intermediate broken step is
> plausible.
> 
> In any case I don't think this is something we want to rush for 3.17
> now, since a release is imminent, so it'll be 3.18. Adding cc: stable is
> up to you, but do note the size is beyond stable rules.

Hm right, so a patch for drm-intel-next-fixes (first one even!). I'll
leave out the cc: stable since backporting all the register wa stuff is a
pile of patches ...
-Daniel

> 
> 
> BR,
> Jani.
> 
> 
> 
> > -Daniel
> >
> >> 
> >> > ---
> >> >  drivers/gpu/drm/i915/intel_ringbuffer.c | 15 ++-------------
> >> >  1 file changed, 2 insertions(+), 13 deletions(-)
> >> > 
> >> > diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> >> > index 681ea86..679a3c7 100644
> >> > --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> >> > +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> >> > @@ -707,7 +707,7 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
> >> >  	 * update the number of dwords required based on the
> >> >  	 * actual number of workarounds applied
> >> >  	 */
> >> > -	ret = intel_ring_begin(ring, 24);
> >> > +	ret = intel_ring_begin(ring, 18);
> >> >  	if (ret)
> >> >  		return ret;
> >> >  
> >> > @@ -722,19 +722,8 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
> >> >  	intel_ring_emit_wa(ring, GEN7_ROW_CHICKEN2,
> >> >  			   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
> >> >  
> >> > -	/*
> >> > -	 * This GEN8_CENTROID_PIXEL_OPT_DIS W/A is only needed for
> >> > -	 * pre-production hardware
> >> > -	 */
> >> >  	intel_ring_emit_wa(ring, HALF_SLICE_CHICKEN3,
> >> > -			   _MASKED_BIT_ENABLE(GEN8_CENTROID_PIXEL_OPT_DIS
> >> > -					      | GEN8_SAMPLER_POWER_BYPASS_DIS));
> >> > -
> >> > -	intel_ring_emit_wa(ring, GEN7_HALF_SLICE_CHICKEN1,
> >> > -			   _MASKED_BIT_ENABLE(GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE));
> >> > -
> >> > -	intel_ring_emit_wa(ring, COMMON_SLICE_CHICKEN2,
> >> > -			   _MASKED_BIT_ENABLE(GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE));
> >> > +			   _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));
> >> >  
> >> >  	/* Use Force Non-Coherent whenever executing a 3D context. This is a
> >> >  	 * workaround for for a possible hang in the unlikely event a TLB
> >> > -- 
> >> > 1.9.1
> >> 
> >> -- 
> >> Ville Syrjälä
> >> Intel OTC
> >> _______________________________________________
> >> Intel-gfx mailing list
> >> Intel-gfx@lists.freedesktop.org
> >> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
> >
> > -- 
> > Daniel Vetter
> > Software Engineer, Intel Corporation
> > +41 (0) 79 365 57 48 - http://blog.ffwll.ch
> 
> -- 
> Jani Nikula, Intel Open Source Technology Center

-- 
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch

^ permalink raw reply	[flat|nested] 8+ messages in thread
* Re: [PATCH] drm/i915/bdw: Cleanup pre prod workarounds
  2014-09-24  8:41           ` Daniel Vetter
@ 2014-09-24 17:46             ` Rodrigo Vivi
  0 siblings, 0 replies; 8+ messages in thread
From: Rodrigo Vivi @ 2014-09-24 17:46 UTC (permalink / raw)
  To: Daniel Vetter; +Cc: intel-gfx


[-- Attachment #1.1: Type: text/plain, Size: 4896 bytes --]

Oh just noticed we duplicated effort on this.. [5/5] drm/i915/bdw: Remove
BDW preproduction W/As until C stepping.

After this land -nightly I rebase my series on top.

On Wed, Sep 24, 2014 at 1:41 AM, Daniel Vetter <daniel@ffwll.ch> wrote:

> On Tue, Sep 23, 2014 at 02:48:47PM +0300, Jani Nikula wrote:
> > On Tue, 23 Sep 2014, Daniel Vetter <daniel@ffwll.ch> wrote:
> > > On Fri, Sep 19, 2014 at 08:49:06PM +0300, Ville Syrjälä wrote:
> > >> On Fri, Sep 19, 2014 at 08:05:26PM +0300, Mika Kuoppala wrote:
> > >> > as these have been fixed in production hw and hurt performance
> > >> > if applied.
> > >> >
> > >> > v2: adjust requested ring space (Ville)
> > >> >
> > >> > Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=83482
> > >> > Tested-by: zhoujian <jianx.zhou@intel.com>
> > >> > Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
> > >>
> > >> Documentation agrees that these can go.
> > >> Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
> > >
> > > Cc: stable@vger.kernel.org imo. Jani?
> >
> > This depends on
> >
> > commit 86d7f23842f1bce3ab5e8c8d0c676112bbc4c99b
> > Author: Arun Siluvery <arun.siluvery@linux.intel.com>
> > Date:   Tue Aug 26 14:44:50 2014 +0100
> >
> >     drm/i915/bdw: Apply workarounds in render ring init function
> >
> > which brought the problem to daylight to begin with. That's not in
> > 3.17-rc6. I'm not sure if that one has additional dependencies, but
> > perhaps a combined backport without an intermediate broken step is
> > plausible.
> >
> > In any case I don't think this is something we want to rush for 3.17
> > now, since a release is imminent, so it'll be 3.18. Adding cc: stable is
> > up to you, but do note the size is beyond stable rules.
>
> Hm right, so a patch for drm-intel-next-fixes (first one even!). I'll
> leave out the cc: stable since backporting all the register wa stuff is a
> pile of patches ...
> -Daniel
>
> >
> >
> > BR,
> > Jani.
> >
> >
> >
> > > -Daniel
> > >
> > >>
> > >> > ---
> > >> >  drivers/gpu/drm/i915/intel_ringbuffer.c | 15 ++-------------
> > >> >  1 file changed, 2 insertions(+), 13 deletions(-)
> > >> >
> > >> > diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c
> b/drivers/gpu/drm/i915/intel_ringbuffer.c
> > >> > index 681ea86..679a3c7 100644
> > >> > --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> > >> > +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> > >> > @@ -707,7 +707,7 @@ static int bdw_init_workarounds(struct
> intel_engine_cs *ring)
> > >> >           * update the number of dwords required based on the
> > >> >           * actual number of workarounds applied
> > >> >           */
> > >> > -        ret = intel_ring_begin(ring, 24);
> > >> > +        ret = intel_ring_begin(ring, 18);
> > >> >          if (ret)
> > >> >                  return ret;
> > >> >
> > >> > @@ -722,19 +722,8 @@ static int bdw_init_workarounds(struct
> intel_engine_cs *ring)
> > >> >          intel_ring_emit_wa(ring, GEN7_ROW_CHICKEN2,
> > >> >
>  _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
> > >> >
> > >> > -        /*
> > >> > -         * This GEN8_CENTROID_PIXEL_OPT_DIS W/A is only needed for
> > >> > -         * pre-production hardware
> > >> > -         */
> > >> >          intel_ring_emit_wa(ring, HALF_SLICE_CHICKEN3,
> > >> > -
>  _MASKED_BIT_ENABLE(GEN8_CENTROID_PIXEL_OPT_DIS
> > >> > -                                              |
> GEN8_SAMPLER_POWER_BYPASS_DIS));
> > >> > -
> > >> > -        intel_ring_emit_wa(ring, GEN7_HALF_SLICE_CHICKEN1,
> > >> > -
>  _MASKED_BIT_ENABLE(GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE));
> > >> > -
> > >> > -        intel_ring_emit_wa(ring, COMMON_SLICE_CHICKEN2,
> > >> > -
>  _MASKED_BIT_ENABLE(GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE));
> > >> > +
>  _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));
> > >> >
> > >> >          /* Use Force Non-Coherent whenever executing a 3D context.
> This is a
> > >> >           * workaround for for a possible hang in the unlikely
> event a TLB
> > >> > --
> > >> > 1.9.1
> > >>
> > >> --
> > >> Ville Syrjälä
> > >> Intel OTC
> > >> _______________________________________________
> > >> Intel-gfx mailing list
> > >> Intel-gfx@lists.freedesktop.org
> > >> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
> > >
> > > --
> > > Daniel Vetter
> > > Software Engineer, Intel Corporation
> > > +41 (0) 79 365 57 48 - http://blog.ffwll.ch
> >
> > --
> > Jani Nikula, Intel Open Source Technology Center
>
> --
> Daniel Vetter
> Software Engineer, Intel Corporation
> +41 (0) 79 365 57 48 - http://blog.ffwll.ch
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
>



-- 
Rodrigo Vivi
Blog: http://blog.vivi.eng.br

[-- Attachment #1.2: Type: text/html, Size: 7765 bytes --]

[-- Attachment #2: Type: text/plain, Size: 159 bytes --]

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

^ permalink raw reply	[flat|nested] 8+ messages in thread
end of thread, other threads:[~2014-09-24 17:46 UTC | newest]

Thread overview: 8+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2014-09-19 13:05 [PATCH] drm/i915/bdw: Cleanup pre prod workarounds Mika Kuoppala
2014-09-19 13:55 ` Ville Syrjälä
2014-09-19 17:05   ` Mika Kuoppala
2014-09-19 17:49     ` Ville Syrjälä
2014-09-23  8:20       ` Daniel Vetter
2014-09-23 11:48         ` Jani Nikula
2014-09-24  8:41           ` Daniel Vetter
2014-09-24 17:46             ` Rodrigo Vivi

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.