From: "Christian König" <ckoenig.leichtzumerken@gmail.com>
To: Nirmoy Das <nirmoy.das@amd.com>, amd-gfx@lists.freedesktop.org
Cc: alexander.deucher@amd.com, Christian.Koenig@amd.com
Subject: Re: [RFC PATCH 1/1] drm/amdgpu: fix usable gart size calculation
Date: Fri, 13 Nov 2020 17:21:57 +0100 [thread overview]
Message-ID: <46bfa315-227c-47c2-d950-47a9a866b070@gmail.com> (raw)
In-Reply-To: <20201113161740.20685-1-nirmoy.das@amd.com>
Am 13.11.20 um 17:17 schrieb Nirmoy Das:
> amdgpu_do_test_moves() is failing because of wrong
> usable gart size calculation and throwing:
>
> [drm:amdgpu_do_test_moves [amdgpu]] *ERROR* 0000000020bdc9f3 bind failed
>
> Signed-off-by: Nirmoy Das <nirmoy.das@amd.com>
> ---
>
> This still doesn't work. As per my calculation 1st 4MB of GART is not
> accounted for in adev->gmc.gart_size - atomic64_read(&adev->gart_pin_size).
The member gart_pin_size should probably be renamed to gtt_pin_size, but
since a gtt pin is also automatically visible in the GART that should
probably be ok for now.
> What am I missing ?
The two 2MB windows in the GART which are used for buffer moves.
See AMDGPU_GTT_MAX_TRANSFER_SIZE and AMDGPU_GTT_NUM_TRANSFER_WINDOWS.
Regards,
Christian.
>
> drivers/gpu/drm/amd/amdgpu/amdgpu_test.c | 11 ++---------
> 1 file changed, 2 insertions(+), 9 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
> index 6042b3b81a4c..d983c729997f 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
> @@ -42,16 +42,9 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev)
> size = 1024 * 1024;
>
> /* Number of tests =
> - * (Total GTT - IB pool - writeback page - ring buffers) / test size
> + * (Total GTT - gart_pin_size) / test size
> */
> - n = adev->gmc.gart_size - AMDGPU_IB_POOL_SIZE;
> - for (i = 0; i < AMDGPU_MAX_RINGS; ++i)
> - if (adev->rings[i])
> - n -= adev->rings[i]->ring_size;
> - if (adev->wb.wb_obj)
> - n -= AMDGPU_GPU_PAGE_SIZE;
> - if (adev->irq.ih.ring_obj)
> - n -= adev->irq.ih.ring_size;
> + n = adev->gmc.gart_size - atomic64_read(&adev->gart_pin_size);
> n /= size;
>
> gtt_obj = kcalloc(n, sizeof(*gtt_obj), GFP_KERNEL);
> --
> 2.29.0
>
> _______________________________________________
> amd-gfx mailing list
> amd-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
next prev parent reply other threads:[~2020-11-13 16:22 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-13 16:17 [RFC PATCH 1/1] drm/amdgpu: fix usable gart size calculation Nirmoy Das
2020-11-13 16:21 ` Christian König [this message]
2020-11-13 16:51 ` Nirmoy
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=46bfa315-227c-47c2-d950-47a9a866b070@gmail.com \
--to=ckoenig.leichtzumerken@gmail.com \
--cc=Christian.Koenig@amd.com \
--cc=alexander.deucher@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=nirmoy.das@amd.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