From: Jani Nikula <jani.nikula@linux.intel.com>
To: Julia Filipchuk <julia.filipchuk@intel.com>,
intel-gfx@lists.freedesktop.org
Cc: John Harrison <John.C.Harrison@intel.com>,
Julia Filipchuk <julia.filipchuk@intel.com>
Subject: Re: [PATCH] drm/i915/guc: Enable DUAL_QUEUE_WA for newer platforms
Date: Tue, 22 Apr 2025 12:13:30 +0300 [thread overview]
Message-ID: <87ikmw1rut.fsf@intel.com> (raw)
In-Reply-To: <20250418233918.2217759-1-julia.filipchuk@intel.com>
On Fri, 18 Apr 2025, Julia Filipchuk <julia.filipchuk@intel.com> wrote:
> For newer platforms (post DG2) hardware intentionally stalls on
> submisstion of concurrent RCS and CCS of different address spaces. With
> this workaround GuC will never schedule such conlicting contexts;
> preventing detection of a stall as a hang.
>
> GuC specs recommend to enable this for all platforms starting from MTL
> supporting CCS.
>
> Signed-off-by: Julia Filipchuk <julia.filipchuk@intel.com>
> ---
> drivers/gpu/drm/i915/gt/intel_gt.h | 8 ++++++++
> drivers/gpu/drm/i915/gt/uc/intel_guc.c | 9 ++++++---
> 2 files changed, 14 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h
> index 998ca029b73a..2f86b2291826 100644
> --- a/drivers/gpu/drm/i915/gt/intel_gt.h
> +++ b/drivers/gpu/drm/i915/gt/intel_gt.h
> @@ -24,6 +24,14 @@ struct drm_printer;
> GRAPHICS_VER_FULL((gt)->i915) >= (from) && \
> GRAPHICS_VER_FULL((gt)->i915) <= (until)))
>
> +/*
> + * Check that the GT is a graphics GT and has atleast minimum IP version.
> + */
> +#define IS_GFX_GT_IP_ATLEAST(gt, from) ( \
> + BUILD_BUG_ON_ZERO((from) < IP_VER(2, 0)) + \
> + ((gt)->type != GT_MEDIA && \
> + GRAPHICS_VER_FULL((gt)->i915) >= (from)))
> +
> /*
> * Check that the GT is a media GT and has an IP version within the
> * specified range (inclusive).
> diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
> index 9df80c325fc1..70c83c1588e9 100644
> --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c
> +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
> @@ -313,8 +313,12 @@ static u32 guc_ctl_wa_flags(struct intel_guc *guc)
> *
> * The same WA bit is used for both and 22011391025 is applicable to
> * all DG2.
> + *
> + * Platforms post DG2 prevent behavior in hardware. This is implicitly
> + * enabled to give guc management over CCS scheduling.
> */
> - if (IS_DG2(gt->i915))
> + if (IS_DG2(gt->i915) ||
> + (CCS_MASK(gt) && IS_GFX_GT_IP_ATLEAST(gt, IP_VER(12, 70))))
> flags |= GUC_WA_DUAL_QUEUE;
GRAPHICS_VER_FULL((gt)->i915) >= IP_VER(12, 70)
You don't need an extra macro for a single use case that is covered by
existing macros.
BR,
Jani.
>
> /* Wa_22011802037: graphics version 11/12 */
> @@ -322,8 +326,7 @@ static u32 guc_ctl_wa_flags(struct intel_guc *guc)
> flags |= GUC_WA_PRE_PARSER;
>
> /*
> - * Wa_22012727170
> - * Wa_22012727685
> + * Wa_22012727170 Wa_22012727685
> */
> if (IS_DG2_G11(gt->i915))
> flags |= GUC_WA_CONTEXT_ISOLATION;
--
Jani Nikula, Intel
next prev parent reply other threads:[~2025-04-22 9:14 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-04-18 23:39 [PATCH] drm/i915/guc: Enable DUAL_QUEUE_WA for newer platforms Julia Filipchuk
2025-04-19 0:08 ` ✗ Fi.CI.CHECKPATCH: warning for " Patchwork
2025-04-19 0:08 ` ✗ Fi.CI.SPARSE: " Patchwork
2025-04-19 8:25 ` ✓ i915.CI.BAT: success " Patchwork
2025-04-22 9:13 ` Jani Nikula [this message]
2025-04-29 1:05 ` [PATCH] " Julia Filipchuk
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=87ikmw1rut.fsf@intel.com \
--to=jani.nikula@linux.intel.com \
--cc=John.C.Harrison@intel.com \
--cc=intel-gfx@lists.freedesktop.org \
--cc=julia.filipchuk@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 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.