From: "Christian König" <christian.koenig@amd.com>
To: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>,
Tvrtko Ursulin <tursulin@igalia.com>,
amd-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org
Cc: kernel-dev@igalia.com, Friedrich Vock <friedrich.vock@gmx.de>
Subject: Re: [RFC 2/5] drm/amdgpu: Actually respect buffer migration budget
Date: Wed, 15 May 2024 16:31:25 +0200 [thread overview]
Message-ID: <7a9a2819-a3f0-4a51-8ae8-bde6ff7b0aaa@amd.com> (raw)
In-Reply-To: <1a20c64f-cb1c-4f68-917b-9a8a34741bff@igalia.com>
Am 15.05.24 um 12:59 schrieb Tvrtko Ursulin:
>
> On 15/05/2024 08:20, Christian König wrote:
>> Am 08.05.24 um 20:09 schrieb Tvrtko Ursulin:
>>> From: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
>>>
>>> Current code appears to live in a misconception that playing with
>>> buffer
>>> allowed and preferred placements can control the decision on whether
>>> backing store migration will be attempted or not.
>>>
>>> Both from code inspection and from empirical experiments I see that not
>>> being true, and that both allowed and preferred placement are typically
>>> set to the same bitmask.
>>
>> That's not correct for the use case handled here, but see below.
>
> Which part is not correct, that bo->preferred_domains and
> bo->allower_domains are the same bitmask?
Sorry totally forgot to explain that.
This rate limit here was specially made for OpenGL applications which
over commit VRAM. In those case preferred_domains will be VRAM only and
allowed_domains will be VRAM|GTT.
RADV always uses VRAM|GTT for both (which is correct).
>
>>>
>>> As such, when the code decides to throttle the migration for a
>>> client, it
>>> is in fact not achieving anything. Buffers can still be either
>>> migrated or
>>> not migrated based on the external (to this function and facility)
>>> logic.
>>>
>>> Fix it by not changing the buffer object placements if the migration
>>> budget has been spent.
>>>
>>> FIXME:
>>> Is it still required to call validate is the question..
>>>
>>> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
>>> Cc: Christian König <christian.koenig@amd.com>
>>> Cc: Friedrich Vock <friedrich.vock@gmx.de>
>>> ---
>>> drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 12 +++++++++---
>>> 1 file changed, 9 insertions(+), 3 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
>>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
>>> index 22708954ae68..d07a1dd7c880 100644
>>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
>>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
>>> @@ -784,6 +784,7 @@ static int amdgpu_cs_bo_validate(void *param,
>>> struct amdgpu_bo *bo)
>>> .no_wait_gpu = false,
>>> .resv = bo->tbo.base.resv
>>> };
>>> + bool migration_allowed = true;
>>> struct ttm_resource *old_res;
>>> uint32_t domain;
>>> int r;
>>> @@ -805,19 +806,24 @@ static int amdgpu_cs_bo_validate(void *param,
>>> struct amdgpu_bo *bo)
>>> * visible VRAM if we've depleted our allowance to do
>>> * that.
>>> */
>>> - if (p->bytes_moved_vis < p->bytes_moved_vis_threshold)
>>> + if (p->bytes_moved_vis < p->bytes_moved_vis_threshold) {
>>> domain = bo->preferred_domains;
>>> - else
>>> + } else {
>>> domain = bo->allowed_domains;
>>> + migration_allowed = false;
>>> + }
>>> } else {
>>> domain = bo->preferred_domains;
>>> }
>>> } else {
>>> domain = bo->allowed_domains;
>>> + migration_allowed = false;
>>> }
>>> retry:
>>> - amdgpu_bo_placement_from_domain(bo, domain);
>>> + if (migration_allowed)
>>> + amdgpu_bo_placement_from_domain(bo, domain);
>>
>> That's completely invalid. Calling amdgpu_bo_placement_from_domain()
>> is a mandatory prerequisite for calling ttm_bo_validate();
>>
>> E.g. the usually code fow is:
>>
>> /* This initializes bo->placement */
>> amdgpu_bo_placement_from_domain()
>>
>> /* Eventually modify bo->placement to fit special requirements */
>> ....
>>
>> /* Apply the placement to the BO */
>> ttm_bo_validate(&bo->tbo, &bo->placement, &ctx)
>>
>> To sum it up bo->placement should be a variable on the stack instead,
>> but we never bothered to clean that up.
>
> I am not clear if you agree or not that the current method of trying
> to avoid migration doesn't really do anything?
I totally agree, but the approach you taken to fix it is just quite
broken. You can't leave bo->placement uninitialized and expect that
ttm_bo_validate() won't move the BO.
>
> On stack placements sounds plausible to force migration avoidance by
> putting a single current object placement in that list, if that is
> what you have in mind? Or a specialized flag/version of
> amdgpu_bo_placement_from_domain with an bool input like
> "allow_placement_change"?
A very rough idea with no guarantee that it actually works:
Add a TTM_PL_FLAG_RATE_LIMITED with all the TTM code to actually figure
out how many bytes have been moved and how many bytes the current
operation can move etc...
Friedrich's patches actually looked like quite a step into the right
direction for that already, so I would start from there.
Then always feed amdgpu_bo_placement_from_domain() with the
allowed_domains in the CS path and VM validation.
Finally extend amdgpu_bo_placement_from_domain() to take a closer look
at bo->preferred_domains, similar to how we do for the
TTM_PL_FLAG_FALLBACK already and set the TTM_PL_FLAG_RATE_LIMITED flag
as appropriate.
Regards,
Christian.
> Regards,
>
> Tvrtko
>
>>
>> Regards,
>> Christian.
>>
>>> +
>>> r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
>>> if (unlikely(r == -ENOMEM) && domain != bo->allowed_domains) {
>>
next prev parent reply other threads:[~2024-05-15 14:31 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-05-08 18:09 [RFC 0/5] Discussion around eviction improvements Tvrtko Ursulin
2024-05-08 18:09 ` [RFC 1/5] drm/amdgpu: Fix migration rate limiting accounting Tvrtko Ursulin
2024-05-08 19:08 ` Friedrich Vock
2024-05-09 9:19 ` Tvrtko Ursulin
2024-05-13 14:36 ` Friedrich Vock
2024-05-15 7:14 ` Christian König
2024-05-15 10:51 ` Tvrtko Ursulin
2024-05-08 18:09 ` [RFC 2/5] drm/amdgpu: Actually respect buffer migration budget Tvrtko Ursulin
2024-05-15 7:20 ` Christian König
2024-05-15 10:59 ` Tvrtko Ursulin
2024-05-15 14:31 ` Christian König [this message]
2024-05-15 15:13 ` Tvrtko Ursulin
2024-05-08 18:09 ` [RFC 3/5] drm/ttm: Add preferred placement flag Tvrtko Ursulin
2024-05-08 18:09 ` [RFC 4/5] drm/amdgpu: Use preferred placement for VRAM+GTT Tvrtko Ursulin
2024-05-08 18:09 ` [RFC 5/5] drm/amdgpu: Re-validate evicted buffers Tvrtko Ursulin
2024-05-09 12:40 ` [RFC 0/5] Discussion around eviction improvements Tvrtko Ursulin
2024-05-13 13:49 ` Tvrtko Ursulin
2024-05-14 15:14 ` Tvrtko Ursulin
2024-05-14 15:47 ` Christian König
2024-05-13 6:50 ` 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=7a9a2819-a3f0-4a51-8ae8-bde6ff7b0aaa@amd.com \
--to=christian.koenig@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=dri-devel@lists.freedesktop.org \
--cc=friedrich.vock@gmx.de \
--cc=kernel-dev@igalia.com \
--cc=tursulin@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;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).