[PATCH] drm/amdgpu: fix CPDMA hang in PRT mode for VEGA20

Zhou1, Tao Tao.Zhou1 at amd.com
Wed Jan 9 02:23:56 UTC 2019



> -----Original Message-----
> From: amd-gfx <amd-gfx-bounces at lists.freedesktop.org> On Behalf Of
> Zhang, Jerry(Junwei)
> Sent: 2019年1月9日 9:39
> To: Zhou1, Tao <Tao.Zhou1 at amd.com>; amd-gfx at lists.freedesktop.org
> Cc: Li, Yukun1 <Yukun1.Li at amd.com>
> Subject: Re: [PATCH] drm/amdgpu: fix CPDMA hang in PRT mode for VEGA20
> 
> On 1/8/19 6:55 PM, Tao Zhou wrote:
> > Fix CPDMA hang in PRT mode for both of VEGA10 and VEGA20
> >
> > Change-Id: I0e5e089d2192063c4a04fa6dbd534f25eb0177be
> > Signed-off-by: Tao Zhou <tao.zhou1 at amd.com>
> > Tested-by: Yukun.Li <yukun1.li at amd.com>
> > ---
> >   drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 10 +++++-----
> >   1 file changed, 5 insertions(+), 5 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> > b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> > index 968b127c6c8f..fbca0494f871 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> > +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> > @@ -113,7 +113,10 @@ static const struct soc15_reg_golden
> golden_settings_gc_9_0[] =
> >   	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_HI,
> 0xffffffff, 0x4a2c0e68),
> >   	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_LO,
> 0xffffffff, 0xb5d3f197),
> >   	SOC15_REG_GOLDEN_VALUE(GC, 0, mmVGT_CACHE_INVALIDATION,
> 0x3fff3af3, 0x19200000),
> > -	SOC15_REG_GOLDEN_VALUE(GC, 0, mmVGT_GS_MAX_WAVE_ID,
> 0x00000fff, 0x000003ff)
> > +	SOC15_REG_GOLDEN_VALUE(GC, 0, mmVGT_GS_MAX_WAVE_ID,
> 0x00000fff, 0x000003ff),
> > +	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_MEC1_F32_INT_DIS,
> 0x00000000, 0x00000800),
> > +	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_MEC2_F32_INT_DIS,
> 0x00000000, 0x00000800),
> > +	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_DEBUG, 0x00000000,
> 0x00008000)
> IIRC, the CP_DEBUG is the key to fix the CPDMA hang, do we need other
> settings?
> or just to align the settings with latest status?
> 
> Jerry
> 
Set CPF_INT_DMA in reg CP_MECx_F32_INT_DIS for Compute and set 
DISABLE_GFX_HALT_ON_UTCL1_ERROR in CP_DEBUG for GFX.

All the settings are needed.

Tao

> >   };
> >
> >   static const struct soc15_reg_golden golden_settings_gc_9_0_vg10[] =
> > @@ -135,10 +138,7 @@ static const struct soc15_reg_golden
> golden_settings_gc_9_0_vg10[] =
> >   	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRMI_UTCL1_CNTL2,
> 0x00030000, 0x00020000),
> >   	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL_1,
> 0x0000000f, 0x01000107),
> >   	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTD_CNTL, 0x00001800,
> 0x00000800),
> > -	SOC15_REG_GOLDEN_VALUE(GC, 0, mmWD_UTCL1_CNTL,
> 0x08000000, 0x08000080),
> > -	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_MEC1_F32_INT_DIS,
> 0x00000000, 0x00000800),
> > -	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_MEC2_F32_INT_DIS,
> 0x00000000, 0x00000800),
> > -	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_DEBUG, 0x00000000,
> 0x00008000)
> > +	SOC15_REG_GOLDEN_VALUE(GC, 0, mmWD_UTCL1_CNTL,
> 0x08000000,
> > +0x08000080)
> >   };
> >
> >   static const struct soc15_reg_golden golden_settings_gc_9_0_vg20[] =
> 
> _______________________________________________
> amd-gfx mailing list
> amd-gfx at lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/amd-gfx


More information about the amd-gfx mailing list