From: Matt Roper <matthew.d.roper@intel.com>
To: Matt Atwood <matthew.s.atwood@intel.com>
Cc: <intel-xe@lists.freedesktop.org>,
Gustavo Sousa <gustavo.sousa@intel.com>
Subject: Re: [PATCH 4/9] drm/xe/xe3: Add initial set of workarounds
Date: Wed, 11 Sep 2024 11:03:33 -0700 [thread overview]
Message-ID: <20240911180333.GF5774@mdroper-desk1.amr.corp.intel.com> (raw)
In-Reply-To: <20240906215153.31210-5-matthew.s.atwood@intel.com>
On Fri, Sep 06, 2024 at 02:51:48PM -0700, Matt Atwood wrote:
> From: Gustavo Sousa <gustavo.sousa@intel.com>
>
> Implement the initial set of workarounds for Xe3 IPs.
>
> Signed-off-by: Gustavo Sousa <gustavo.sousa@intel.com>
> Signed-off-by: Matt Atwood <matthew.s.atwood@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 | 46 ++++++++++++++++++++++++
> drivers/gpu/drm/xe/xe_wa_oob.rules | 1 +
> 4 files changed, 51 insertions(+)
>
> 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 8ed855b31e95..259221d2f217 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 28b7f95b6c2f..d946b27ec4cd 100644
> --- a/drivers/gpu/drm/xe/xe_wa.c
> +++ b/drivers/gpu/drm/xe/xe_wa.c
> @@ -251,6 +251,34 @@ 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),
> + },
> +
> {}
> };
>
> @@ -567,6 +595,13 @@ 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))
> + },
> +
> {}
> };
>
> @@ -734,6 +769,17 @@ static const struct xe_rtp_entry_sr lrc_was[] = {
> DIS_AUTOSTRIP))
> },
>
> + /* Xe3_LPG */
> + { XE_RTP_NAME("14021490052"),
> + XE_RTP_RULES(GRAPHICS_VERSION_RANGE(3000, 3001), ENGINE_CLASS(RENDER)),
This doesn't match what I see in the workaround database. I only see
30.00 a-step as needing this workaround.
> + 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..1949f8f3d7c2 100644
> --- a/drivers/gpu/drm/xe/xe_wa_oob.rules
> +++ b/drivers/gpu/drm/xe/xe_wa_oob.rules
> @@ -33,6 +33,7 @@
> GRAPHICS_VERSION(2004)
> 22019338487 MEDIA_VERSION(2000)
> GRAPHICS_VERSION(2001)
> + MEDIA_VERSION(3000)
This one is also A-step only as far as I can see.
Matt
> 22019338487_display PLATFORM(LUNARLAKE)
> 16023588340 GRAPHICS_VERSION(2001)
> 14019789679 GRAPHICS_VERSION(1255)
> --
> 2.44.0
>
--
Matt Roper
Graphics Software Engineer
Linux GPU Platform Enablement
Intel Corporation
next prev parent reply other threads:[~2024-09-11 18:03 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-09-06 21:51 [PATCH 0/9] Add Xe3 and Panther Lake support Matt Atwood
2024-09-06 21:51 ` [PATCH 1/9] drm/xe/xe3: Xe3 uses the same PAT settings as Xe2 Matt Atwood
2024-09-06 22:39 ` Rodrigo Vivi
2024-09-06 23:12 ` Lucas De Marchi
2024-09-06 21:51 ` [PATCH 2/9] drm/xe/xe3: Define Xe3 feature flags Matt Atwood
2024-09-06 23:34 ` Matt Roper
2024-09-06 21:51 ` [PATCH 3/9] drm/xe/xe3: Generate and store the L3 bank mask Matt Atwood
2024-09-06 23:43 ` Matt Roper
2024-09-09 12:15 ` Francois Dugast
2024-09-06 21:51 ` [PATCH 4/9] drm/xe/xe3: Add initial set of workarounds Matt Atwood
2024-09-11 18:03 ` Matt Roper [this message]
2024-09-06 21:51 ` [PATCH 5/9] drm/xe/xe3: Extend wa_15015404425 for xe3 Matt Atwood
2024-09-06 23:52 ` Matt Roper
2024-09-11 20:17 ` Matt Roper
2024-09-06 21:51 ` [PATCH 6/9] drm/xe/xe3lpm: Add new "instance0" steering table Matt Atwood
2024-09-06 21:51 ` [PATCH 7/9] drm/xe/ptl: PTL re-uses Xe2 MOCS table Matt Atwood
2024-09-10 6:16 ` Chauhan, Shekhar
2024-09-06 21:51 ` [PATCH 8/9] drm/xe/ptl: Add performance tuning settings for PTL Matt Atwood
2024-09-06 23:55 ` Matt Roper
2024-09-10 6:37 ` Chauhan, Shekhar
2024-09-06 21:51 ` [PATCH 9/9] drm/xe/ptl: Add PTL platform definition Matt Atwood
2024-09-06 23:56 ` Matt Roper
2024-09-12 16:56 ` Matt Roper
2024-09-06 23:31 ` ✗ CI.checkpatch: warning for Add Xe3 and Panther Lake support Patchwork
2024-09-06 23:32 ` ✓ CI.KUnit: success " Patchwork
2024-09-06 23:44 ` ✓ CI.Build: " Patchwork
2024-09-06 23:46 ` ✓ CI.Hooks: " Patchwork
2024-09-06 23:48 ` ✓ CI.checksparse: " Patchwork
2024-09-07 0:30 ` ✓ CI.BAT: " Patchwork
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240911180333.GF5774@mdroper-desk1.amr.corp.intel.com \
--to=matthew.d.roper@intel.com \
--cc=gustavo.sousa@intel.com \
--cc=intel-xe@lists.freedesktop.org \
--cc=matthew.s.atwood@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox