[PATCH 3/6] drm/xe/xe3: Add initial set of workarounds

[Matt Roper]

On Fri, Oct 04, 2024 at 03:05:47PM -0700, Matt Atwood wrote:
> From: Gustavo Sousa <gustavo.sousa at intel.com>
> 
> Implement the initial set of workarounds for Xe3 IPs.
> 
> v2: correct steppings for 14021490052, 22019338487
> 
> Signed-off-by: Gustavo Sousa <gustavo.sousa at intel.com>
> Signed-off-by: Matt Atwood <matthew.s.atwood at intel.com>
> ---
>  drivers/gpu/drm/xe/regs/xe_engine_regs.h |  1 +
>  drivers/gpu/drm/xe/regs/xe_gt_regs.h     |  3 ++
>  drivers/gpu/drm/xe/xe_wa.c               | 49 +++++++++++++++++++++++-
>  drivers/gpu/drm/xe/xe_wa_oob.rules       |  3 +-
>  4 files changed, 54 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
> index 81b71903675e..7c78496e6213 100644
> --- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h
> +++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
> @@ -186,6 +186,7 @@
>  
>  #define VDBOX_CGCTL3F10(base)			XE_REG((base) + 0x3f10)
>  #define   IECPUNIT_CLKGATE_DIS			REG_BIT(22)
> +#define   RAMDFTUNIT_CLKGATE_DIS		REG_BIT(9)
>  
>  #define VDBOX_CGCTL3F18(base)			XE_REG((base) + 0x3f18)
>  #define   ALNUNIT_CLKGATE_DIS			REG_BIT(13)
> diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
> index fb80042cbe0d..ac5a9ae94eb1 100644
> --- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h
> +++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
> @@ -286,6 +286,9 @@
>  #define   GAMTLBVEBOX0_CLKGATE_DIS		REG_BIT(16)
>  #define   LTCDD_CLKGATE_DIS			REG_BIT(10)
>  
> +#define UNSLCGCTL9454				XE_REG(0x9454)
> +#define   LSCFE_CLKGATE_DIS			REG_BIT(4)
> +
>  #define XEHP_SLICE_UNIT_LEVEL_CLKGATE		XE_REG_MCR(0x94d4)
>  #define   L3_CR2X_CLKGATE_DIS			REG_BIT(17)
>  #define   L3_CLKGATE_DIS			REG_BIT(16)
> diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c
> index 94ea76b098ed..91c272041970 100644
> --- a/drivers/gpu/drm/xe/xe_wa.c
> +++ b/drivers/gpu/drm/xe/xe_wa.c
> @@ -252,6 +252,34 @@ static const struct xe_rtp_entry_sr gt_was[] = {
>  	  XE_RTP_ENTRY_FLAG(FOREACH_ENGINE),
>  	},
>  
> +	/* Xe3_LPG */
> +
> +	{ XE_RTP_NAME("14021871409"),
> +	  XE_RTP_RULES(GRAPHICS_VERSION(3000), GRAPHICS_STEP(A0, B0)),
> +	  XE_RTP_ACTIONS(SET(UNSLCGCTL9454, LSCFE_CLKGATE_DIS))
> +	},
> +
> +	/* Xe3_LPM */
> +
> +	{ XE_RTP_NAME("16021867713"),
> +	  XE_RTP_RULES(MEDIA_VERSION(3000),
> +		       ENGINE_CLASS(VIDEO_DECODE)),
> +	  XE_RTP_ACTIONS(SET(VDBOX_CGCTL3F1C(0), MFXPIPE_CLKGATE_DIS)),
> +	  XE_RTP_ENTRY_FLAG(FOREACH_ENGINE),
> +	},
> +	{ XE_RTP_NAME("16021865536"),
> +	  XE_RTP_RULES(MEDIA_VERSION(3000),
> +		       ENGINE_CLASS(VIDEO_DECODE)),
> +	  XE_RTP_ACTIONS(SET(VDBOX_CGCTL3F10(0), IECPUNIT_CLKGATE_DIS)),
> +	  XE_RTP_ENTRY_FLAG(FOREACH_ENGINE),
> +	},
> +	{ XE_RTP_NAME("14021486841"),
> +	  XE_RTP_RULES(MEDIA_VERSION(3000), MEDIA_STEP(A0, B0),
> +		       ENGINE_CLASS(VIDEO_DECODE)),
> +	  XE_RTP_ACTIONS(SET(VDBOX_CGCTL3F10(0), RAMDFTUNIT_CLKGATE_DIS)),
> +	  XE_RTP_ENTRY_FLAG(FOREACH_ENGINE),
> +	},
> +
>  	{}
>  };
>  
> @@ -568,6 +596,13 @@ static const struct xe_rtp_entry_sr engine_was[] = {
>  			     XE_RTP_ACTION_FLAG(ENGINE_BASE)))
>  	},
>  
> +	/* Xe3_LPG */
> +
> +	{ XE_RTP_NAME("14021402888"),
> +	  XE_RTP_RULES(GRAPHICS_VERSION_RANGE(3000, 3001), FUNC(xe_rtp_match_first_render_or_compute)),
> +	  XE_RTP_ACTIONS(SET(HALF_SLICE_CHICKEN7, CLEAR_OPTIMIZATION_DISABLE))
> +	},
> +
>  	{}
>  };
>  
> @@ -703,7 +738,7 @@ static const struct xe_rtp_entry_sr lrc_was[] = {
>  	  XE_RTP_ACTIONS(SET(WM_CHICKEN3, HIZ_PLANE_COMPRESSION_DIS))
>  	},
>  	{ XE_RTP_NAME("14021490052"),
> -	  XE_RTP_RULES(GRAPHICS_VERSION(2004), ENGINE_CLASS(RENDER)),
> +	  XE_RTP_RULES(GRAPHICS_VERSION(2004), ENGINE_CLASS(RENDER), GRAPHICS_STEP(A0, B0)),

This is incorrectly modifying the LNL workaround (which applies to all
steppings).  You're already adding the PTL entry farther down, which is
the one that applies to A-step only.

>  	  XE_RTP_ACTIONS(SET(FF_MODE,
>  			     DIS_MESH_PARTIAL_AUTOSTRIP |
>  			     DIS_MESH_AUTOSTRIP),
> @@ -739,6 +774,18 @@ static const struct xe_rtp_entry_sr lrc_was[] = {
>  	  XE_RTP_ACTIONS(SET(CHICKEN_RASTER_1, DIS_CLIP_NEGATIVE_BOUNDING_BOX))
>  	},
>  
> +	/* Xe3_LPG */
> +	{ XE_RTP_NAME("14021490052"),
> +	  XE_RTP_RULES(GRAPHICS_VERSION(3000), GRAPHICS_STEP(A0, B0),
> +		       ENGINE_CLASS(RENDER)),
> +	  XE_RTP_ACTIONS(SET(FF_MODE,
> +			     DIS_MESH_PARTIAL_AUTOSTRIP |
> +			     DIS_MESH_AUTOSTRIP),
> +			 SET(VFLSKPD,
> +			     DIS_PARTIAL_AUTOSTRIP |
> +			     DIS_AUTOSTRIP))
> +	},
> +
>  	{}
>  };
>  
> diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules
> index 920ca5060146..d17649ebbace 100644
> --- a/drivers/gpu/drm/xe/xe_wa_oob.rules
> +++ b/drivers/gpu/drm/xe/xe_wa_oob.rules
> @@ -32,7 +32,8 @@
>  22019794406	GRAPHICS_VERSION(2001)
>  		GRAPHICS_VERSION(2004)
>  22019338487	MEDIA_VERSION(2000)
> -		GRAPHICS_VERSION(2001)
> +		GRAPHICS_VERSION(2001), GRAPHICS_STEP(A0, B0)

The BMG graphics workaround still applies to all steppings, so this
isn't right.

> +		MEDIA_VERSION(3000)

And the PTL media workaround is the one that's A-step only.


Matt

>  22019338487_display	PLATFORM(LUNARLAKE)
>  16023588340	GRAPHICS_VERSION(2001)
>  14019789679	GRAPHICS_VERSION(1255)
> -- 
> 2.45.0
> 
> 

-- 
Matt Roper
Graphics Software Engineer
Linux GPU Platform Enablement
Intel Corporation