AMD-GFX Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: "Timur Kristóf" <timur.kristof@gmail.com>
To: natalie.vock@gmx.de, honghuan@amd.com, Alexander.Deucher@amd.com,
	Felix.Kuehling@amd.com, Philip.Yang@amd.com, cascardo@igalia.com,
	tvrtko.ursulin@igalia.com, olivier.kaloudoff@gmail.com,
	christian.koenig@amd.com
Cc: amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH 3/8] drm/amdgpu: add amdgpu_vm_pt_leaves() v3
Date: Tue, 06 Oct 2026 19:51:27 +0200	[thread overview]
Message-ID: <8sm4C_zRRSWvGVYa3WR82Q@gmail.com> (raw)
In-Reply-To: <20260930133315.12270-3-christian.koenig@amd.com>

On Wednesday, September 30, 2026 3:33:09 PM Central European Summer Time 
Christian König wrote:
> Add a new function amdgpu_vm_update_leaves() to avoid memory allocation
> on page faults.
> 
> The idea is to only update the leave PDEs/PTEs to let them point to the
> dummy page.
> 
> v2: fix of by one, rework the function to work correctly on PTB as well.
> v3: use NUM_LEVELS, don't overwrite vm->last_update
> 
> Signed-off-by: Christian König <christian.koenig@amd.com>

Hi Christian,

I just tested this again and this patch still regresses retry faults.
Please fix.

Thanks,
Timur





  reply	other threads:[~2026-10-06 17:51 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-30 13:33 [PATCH 1/8] drm/amdgpu: fix cleared PDE/PTE flag generation Christian König
2026-09-30 13:33 ` [PATCH 2/8] drm/amdgpu: allocate and fill dummy PDs/PTs v2 Christian König
2026-09-30 13:33 ` [PATCH 3/8] drm/amdgpu: add amdgpu_vm_pt_leaves() v3 Christian König
2026-10-06 17:51   ` Timur Kristóf [this message]
2026-09-30 13:33 ` [PATCH 4/8] drm/amdgpu: drop immediate updates from amdgpu_vm_update_range Christian König
2026-09-30 13:33 ` [PATCH 5/8] drm/amdgpu: drop immediate updates from amdgpu_vm_update_pdes Christian König
2026-09-30 13:33 ` [PATCH 6/8] drm/amdgpu: split amdgpu_vm_update_range v3 Christian König
2026-10-06 17:32   ` Timur Kristóf
2026-09-30 13:33 ` [PATCH 7/8] drm/amdgpu: fix the HMM range handling for KFD SVM v2 Christian König
2026-09-30 13:33 ` [PATCH 8/8] drm/amdgpu: use range unmap in amdgpu_vm_clear_freed Christian König

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=8sm4C_zRRSWvGVYa3WR82Q@gmail.com \
    --to=timur.kristof@gmail.com \
    --cc=Alexander.Deucher@amd.com \
    --cc=Felix.Kuehling@amd.com \
    --cc=Philip.Yang@amd.com \
    --cc=amd-gfx@lists.freedesktop.org \
    --cc=cascardo@igalia.com \
    --cc=christian.koenig@amd.com \
    --cc=honghuan@amd.com \
    --cc=natalie.vock@gmx.de \
    --cc=olivier.kaloudoff@gmail.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