drm/amdgpu: Fix VCE 3 ring align_mask

The largest frame is 20 dwords, so 0xf mask is too small.
This was always wrong, but we were lucky with the VCE_CMD_END
commands inserted after fence and vm_flush.

Fixes: 8897ea8c76 ("drm/amdgpu: Implement insert_end for VCE 3")
Cc: stable@vger.kernel.org
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: David Rosca <david.rosca@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
David Rosca 2026-08-20 16:32:51 +02:00 committed by Alex Deucher
parent fb62f7f031
commit 2ee9836545

View File

@ -891,7 +891,7 @@ static const struct amdgpu_ring_funcs vce_v3_0_ring_phys_funcs = {
static const struct amdgpu_ring_funcs vce_v3_0_ring_vm_funcs = {
.type = AMDGPU_RING_TYPE_VCE,
.align_mask = 0xf,
.align_mask = 0x1f,
.nop = VCE_CMD_NO_OP,
.support_64bit_ptrs = false,
.no_user_fence = true,