From: "Christian König" <christian.koenig@amd.com>
To: "Timur Kristóf" <timur.kristof@gmail.com>,
amd-gfx@lists.freedesktop.org,
"Alex Deucher" <alexander.deucher@amd.com>,
"Natalie Vock" <natalie.vock@gmx.de>,
"John Olender" <john.olender@gmail.com>,
"Liu Leo" <Leo.Liu@amd.com>
Subject: Re: [PATCH 1/5] drm/amdgpu: Respect placement requirements in amdgpu_gtt_mgr functions
Date: Tue, 19 May 2026 10:52:38 +0200 [thread overview]
Message-ID: <46ea9877-7515-43c9-80f5-ada56f608351@amd.com> (raw)
In-Reply-To: <20260519082204.60811-2-timur.kristof@gmail.com>
On 5/19/26 10:22, Timur Kristóf wrote:
> When testing intersection and compatibility, respect
> the actual placement requirements. This is a pre-requisite
> for ensuring that UVD CS BOs do not cross 256M segments.
>
> Fixes: ded910f368a5 ("drm/amdgpu: Implement intersect/compatible functions")
> Suggested-by: Christian König <christian.koenig@amd.com>
> Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c | 30 +++++++++++++++++++--
> 1 file changed, 28 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
> index 02f85802f579..19b6770a877d 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
> @@ -272,7 +272,20 @@ static bool amdgpu_gtt_mgr_intersects(struct ttm_resource_manager *man,
> const struct ttm_place *place,
> size_t size)
> {
> - return !place->lpfn || amdgpu_gtt_mgr_has_gart_addr(res);
> + const struct drm_mm_node *const node = &to_ttm_range_mgr_node(res)->mm_nodes[0];
> + const u32 num_pages = PFN_UP(size);
> +
> + if (!place->lpfn)
> + return true;
> +
> + if (!amdgpu_gtt_mgr_has_gart_addr(res))
> + return false;
> +
> + if (place->fpfn >= (node->start + num_pages) ||
> + (place->lpfn && place->lpfn <= node->start))
> + return false;
> +
> + return true;
> }
>
> /**
> @@ -290,7 +303,20 @@ static bool amdgpu_gtt_mgr_compatible(struct ttm_resource_manager *man,
> const struct ttm_place *place,
> size_t size)
> {
> - return !place->lpfn || amdgpu_gtt_mgr_has_gart_addr(res);
> + const struct drm_mm_node *const node = &to_ttm_range_mgr_node(res)->mm_nodes[0];
> + const u32 num_pages = PFN_UP(size);
> +
> + if (!place->lpfn)
> + return true;
> +
> + if (!amdgpu_gtt_mgr_has_gart_addr(res))
> + return false;
> +
> + if (node->start < place->fpfn ||
> + (place->lpfn && (node->start + num_pages) > place->lpfn))
> + return false;
> +
> + return true;
> }
>
> /**
next prev parent reply other threads:[~2026-05-19 8:52 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-05-19 8:21 [PATCH 0/5] drm/amdgpu/uvd: Fix UVD BO memory placement issues Timur Kristóf
2026-05-19 8:22 ` [PATCH 1/5] drm/amdgpu: Respect placement requirements in amdgpu_gtt_mgr functions Timur Kristóf
2026-05-19 8:52 ` Christian König [this message]
2026-05-19 8:22 ` [PATCH 2/5] drm/amdgpu: Use placements of 256M GART segments for SI/CIK Timur Kristóf
2026-05-19 8:54 ` Christian König
2026-05-19 8:59 ` Timur Kristóf
2026-05-19 9:01 ` Christian König
2026-05-19 9:16 ` Timur Kristóf
2026-05-19 8:22 ` [PATCH 3/5] drm/amdgpu/uvd: Place VCPU BO only in VRAM for UVD 4.x and older Timur Kristóf
2026-05-19 8:56 ` Christian König
2026-05-19 8:22 ` [PATCH 4/5] drm/amdgpu/uvd: Fix forcing BOs into UVD segment when it isn't at 0 Timur Kristóf
2026-05-19 9:06 ` Christian König
2026-05-19 9:32 ` Timur Kristóf
2026-05-19 8:22 ` [PATCH 5/5] drm/amdgpu/uvd: Move BOs to GTT when we can't place them in VRAM correctly Timur Kristóf
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=46ea9877-7515-43c9-80f5-ada56f608351@amd.com \
--to=christian.koenig@amd.com \
--cc=Leo.Liu@amd.com \
--cc=alexander.deucher@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=john.olender@gmail.com \
--cc=natalie.vock@gmx.de \
--cc=timur.kristof@gmail.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