All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH] drm/amdgpu: Limit the maximum size of contiguous VRAM that can be encapsulated by an instance of DRM memory node
@ 2021-01-28 17:43 Ramesh Errabolu
  2021-01-29 11:27 ` Christian König
  0 siblings, 1 reply; 2+ messages in thread
From: Ramesh Errabolu @ 2021-01-28 17:43 UTC (permalink / raw)
  To: amd-gfx; +Cc: Ramesh Errabolu

[Why]
Enable 1:1 mapping between VRAM of a DRM node and a scatterlist node

[How]
Ensure construction of DRM node to not exceed specified limit

Signed-off-by: Ramesh Errabolu <Ramesh.Errabolu@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 20747d8b1135..21d18efca277 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -476,6 +476,9 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 	for (i = 0; pages_left >= pages_per_node; ++i) {
 		unsigned long pages = rounddown_pow_of_two(pages_left);
 
+		/* Limit maximum size to 2GB due to SG table limitations */
+		pages = min(pages, (2UL << (30 - PAGE_SHIFT)));
+
 		r = drm_mm_insert_node_in_range(mm, &nodes[i], pages,
 						pages_per_node, 0,
 						place->fpfn, lpfn,
-- 
2.29.2

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

^ permalink raw reply related	[flat|nested] 2+ messages in thread

* Re: [PATCH] drm/amdgpu: Limit the maximum size of contiguous VRAM that can be encapsulated by an instance of DRM memory node
  2021-01-28 17:43 [PATCH] drm/amdgpu: Limit the maximum size of contiguous VRAM that can be encapsulated by an instance of DRM memory node Ramesh Errabolu
@ 2021-01-29 11:27 ` Christian König
  0 siblings, 0 replies; 2+ messages in thread
From: Christian König @ 2021-01-29 11:27 UTC (permalink / raw)
  To: Ramesh Errabolu, amd-gfx

Am 28.01.21 um 18:43 schrieb Ramesh Errabolu:
> [Why]
> Enable 1:1 mapping between VRAM of a DRM node and a scatterlist node
>
> [How]
> Ensure construction of DRM node to not exceed specified limit
>
> Signed-off-by: Ramesh Errabolu <Ramesh.Errabolu@amd.com>

Reviewed-by: Christian König <christian.koenig@amd.com>

> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 3 +++
>   1 file changed, 3 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
> index 20747d8b1135..21d18efca277 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
> @@ -476,6 +476,9 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
>   	for (i = 0; pages_left >= pages_per_node; ++i) {
>   		unsigned long pages = rounddown_pow_of_two(pages_left);
>   
> +		/* Limit maximum size to 2GB due to SG table limitations */
> +		pages = min(pages, (2UL << (30 - PAGE_SHIFT)));
> +
>   		r = drm_mm_insert_node_in_range(mm, &nodes[i], pages,
>   						pages_per_node, 0,
>   						place->fpfn, lpfn,

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2021-01-29 11:27 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2021-01-28 17:43 [PATCH] drm/amdgpu: Limit the maximum size of contiguous VRAM that can be encapsulated by an instance of DRM memory node Ramesh Errabolu
2021-01-29 11:27 ` Christian König

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.