From: Matt Roper <matthew.d.roper@intel.com>
To: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Cc: <intel-xe@lists.freedesktop.org>, <kernel-dev@igalia.com>
Subject: Re: [PATCH 02/12] drm/xe: Fix ring flush invalidation
Date: Thu, 27 Feb 2025 15:46:22 -0800 [thread overview]
Message-ID: <20250227234622.GL5109@mdroper-desk1.amr.corp.intel.com> (raw)
In-Reply-To: <20250221101736.78986-3-tvrtko.ursulin@igalia.com>
On Fri, Feb 21, 2025 at 10:17:21AM +0000, Tvrtko Ursulin wrote:
> Emit_flush_invalidate() is incorrectly marking the write to LRC_PPHWSP as
> a GGTT write and also writing an atypical ~0 dword as the payload. Fix it.
Technically the write is a GGTT write (the PPHWSP is allocated as part
of the LRC, and the LRC is mapped to the GGTT). But the important thing
here is that bit 21 (MI_FLUSH_DW_STORE_INDEX) redefines the meaning of
the PPGTT vs GGTT bit to instead mean "index into pphwsp" vs "index into
ghwsp." And based on the name of the offset we use
(LRC_PPHWSP_FLUSH_INVAL_SCRATCH_ADDR) it sounds like the pphwsp was
indeed intended here, so dropping the 'use GTT' flag is in line with
that.
I don't think the actual destination (ghwsp vs pphwsp) or the value (~0
or 0) actually has any functional impact since there doesn't seem to be
anything watching and waiting for those writes to show up in memory. We
just have to use the OP_STOREDW flag because the TLB invalidate flag
mandates that it also be present.
But your patch makes things more consistent, so
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
>
> While at it drop the unused flags argument.
>
> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
> ---
> drivers/gpu/drm/xe/xe_ring_ops.c | 15 ++++++---------
> 1 file changed, 6 insertions(+), 9 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
> index 0c230ee53bba..a2d1fb8f0adf 100644
> --- a/drivers/gpu/drm/xe/xe_ring_ops.c
> +++ b/drivers/gpu/drm/xe/xe_ring_ops.c
> @@ -111,16 +111,13 @@ static int emit_bb_start(u64 batch_addr, u32 ppgtt_flag, u32 *dw, int i)
> return i;
> }
>
> -static int emit_flush_invalidate(u32 flag, u32 *dw, int i)
> +static int emit_flush_invalidate(u32 *dw, int i)
> {
> - dw[i] = MI_FLUSH_DW;
> - dw[i] |= flag;
> - dw[i++] |= MI_INVALIDATE_TLB | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_IMM_DW |
> - MI_FLUSH_DW_STORE_INDEX;
> -
> - dw[i++] = LRC_PPHWSP_FLUSH_INVAL_SCRATCH_ADDR | MI_FLUSH_DW_USE_GTT;
> + dw[i++] = MI_FLUSH_DW | MI_INVALIDATE_TLB | MI_FLUSH_DW_OP_STOREDW |
> + MI_FLUSH_IMM_DW | MI_FLUSH_DW_STORE_INDEX;
> + dw[i++] = LRC_PPHWSP_FLUSH_INVAL_SCRATCH_ADDR;
> + dw[i++] = 0;
> dw[i++] = 0;
> - dw[i++] = ~0U;
>
> return i;
> }
> @@ -409,7 +406,7 @@ static void emit_migration_job_gen12(struct xe_sched_job *job,
> if (!IS_SRIOV_VF(gt_to_xe(job->q->gt))) {
> /* XXX: Do we need this? Leaving for now. */
> dw[i++] = preparser_disable(true);
> - i = emit_flush_invalidate(0, dw, i);
> + i = emit_flush_invalidate(dw, i);
> dw[i++] = preparser_disable(false);
> }
>
> --
> 2.48.0
>
--
Matt Roper
Graphics Software Engineer
Linux GPU Platform Enablement
Intel Corporation
next prev parent reply other threads:[~2025-02-27 23:46 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-21 10:17 [PATCH 00/12] AuxCCS handling and render compression modifiers Tvrtko Ursulin
2025-02-21 10:17 ` [PATCH 01/12] drm/xe: Fix MOCS debugfs LNCF readout Tvrtko Ursulin
2025-02-27 20:21 ` Rodrigo Vivi
2025-02-27 23:24 ` Matt Roper
2025-02-28 8:10 ` Tvrtko Ursulin
2025-02-21 10:17 ` [PATCH 02/12] drm/xe: Fix ring flush invalidation Tvrtko Ursulin
2025-02-27 23:46 ` Matt Roper [this message]
2025-02-28 9:08 ` Tvrtko Ursulin
2025-02-21 10:17 ` [PATCH 03/12] drm/xe: Pass flags directly to emit_flush_imm_ggtt Tvrtko Ursulin
2025-02-27 23:47 ` Matt Roper
2025-02-21 10:17 ` [PATCH 04/12] drm/xe: Add ring buffer handling for AuxCCS Tvrtko Ursulin
2025-02-21 10:17 ` [PATCH 05/12] drm/xe: Use correct type width for alignment in fb pinning code Tvrtko Ursulin
2025-02-28 14:57 ` Rodrigo Vivi
2025-02-21 10:17 ` [PATCH 06/12] drm/xe: Use fb cached min alignment Tvrtko Ursulin
2025-02-28 19:21 ` Rodrigo Vivi
2025-02-21 10:17 ` [PATCH 07/12] drm/xe: Reduce DPT table alignment as in i915 Tvrtko Ursulin
2025-02-28 19:25 ` Rodrigo Vivi
2025-02-21 10:17 ` [PATCH 08/12] drm/xe: Flush GGTT writes after populating DPT Tvrtko Ursulin
2025-02-28 19:27 ` Rodrigo Vivi
2025-03-04 14:23 ` Tvrtko Ursulin
2025-02-21 10:17 ` [PATCH 09/12] drm/xe: Handle DPT in system memory Tvrtko Ursulin
2025-02-21 10:17 ` [PATCH 10/12] drm/xe: Force flush system memory AuxCCS framebuffers before scan out Tvrtko Ursulin
2025-02-28 19:34 ` Rodrigo Vivi
2025-03-04 14:21 ` Tvrtko Ursulin
2025-02-21 10:17 ` [PATCH 11/12] drm/xe/display: Add support for AuxCCS Tvrtko Ursulin
2025-02-21 10:17 ` [PATCH 12/12] drm/xe/display: Expose AuxCCS frame buffer modifiers Tvrtko Ursulin
2025-02-28 19:32 ` Rodrigo Vivi
2025-02-21 10:25 ` ✓ CI.Patch_applied: success for AuxCCS handling and render compression modifiers (rev2) Patchwork
2025-02-21 10:25 ` ✗ CI.checkpatch: warning " Patchwork
2025-02-21 10:27 ` ✓ CI.KUnit: success " Patchwork
2025-02-21 10:53 ` ✓ CI.Build: " Patchwork
2025-02-21 10:56 ` ✓ CI.Hooks: " Patchwork
2025-02-21 10:57 ` ✓ CI.checksparse: " Patchwork
2025-02-21 11:16 ` ✓ Xe.CI.BAT: " Patchwork
2025-02-22 0:13 ` ✗ Xe.CI.Full: failure " 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=20250227234622.GL5109@mdroper-desk1.amr.corp.intel.com \
--to=matthew.d.roper@intel.com \
--cc=intel-xe@lists.freedesktop.org \
--cc=kernel-dev@igalia.com \
--cc=tvrtko.ursulin@igalia.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