This is a note to let you know that I've just added the patch titled
drm/amdgpu: fix number of fence calculations
to the 6.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
drm-amdgpu-fix-number-of-fence-calculations.patch
and it can be found in the queue-6.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 4de4045e2da6022a0a4b5ffaab80971ac7cea339
Author: Christian König <christian.koenig@xxxxxxx>
Date: Tue Jun 20 13:18:13 2023 +0200
drm/amdgpu: fix number of fence calculations
[ Upstream commit 570b295248b00c3cf4cf59e397de5cb2361e10c2 ]
Since adding gang submit we need to take the gang size into account
while reserving fences.
Signed-off-by: Christian König <christian.koenig@xxxxxxx>
Fixes: 4624459c84d7 ("drm/amdgpu: add gang submit frontend v6")
Reviewed-by: Alex Deucher <alexander.deucher@xxxxxxx>
Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 2eb2c66843a88..5612caf77dd65 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -133,9 +133,6 @@ static int amdgpu_cs_p1_user_fence(struct amdgpu_cs_parser *p,
bo = amdgpu_bo_ref(gem_to_amdgpu_bo(gobj));
p->uf_entry.priority = 0;
p->uf_entry.tv.bo = &bo->tbo;
- /* One for TTM and two for the CS job */
- p->uf_entry.tv.num_shared = 3;
-
drm_gem_object_put(gobj);
size = amdgpu_bo_size(bo);
@@ -882,15 +879,19 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
mutex_lock(&p->bo_list->bo_list_mutex);
- /* One for TTM and one for the CS job */
+ /* One for TTM and one for each CS job */
amdgpu_bo_list_for_each_entry(e, p->bo_list)
- e->tv.num_shared = 2;
+ e->tv.num_shared = 1 + p->gang_size;
+ p->uf_entry.tv.num_shared = 1 + p->gang_size;
amdgpu_bo_list_get_list(p->bo_list, &p->validated);
INIT_LIST_HEAD(&duplicates);
amdgpu_vm_get_pd_bo(&fpriv->vm, &p->validated, &p->vm_pd);
+ /* Two for VM updates, one for TTM and one for each CS job */
+ p->vm_pd.tv.num_shared = 3 + p->gang_size;
+
if (p->uf_entry.tv.bo && !ttm_to_amdgpu_bo(p->uf_entry.tv.bo)->parent)
list_add(&p->uf_entry.tv.head, &p->validated);
