Ignore this patch. I meant to drop it when I rebased these patches.
It's not necessary.
Alex
On Thu, May 22, 2025 at 5:56 PM Alex Deucher <alexander.deuc...@amd.com> wrote:
>
> This is to make sure the CP executes this packet in
> the event of a preemption or reset.
>
> Signed-off-by: Alex Deucher <alexander.deuc...@amd.com>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
> index 802743efa3b39..d74bd6dffcbd0 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
> @@ -274,7 +274,8 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned
> int num_ibs,
> /* wrap the last IB with fence */
> if (job && job->uf_addr) {
> amdgpu_ring_emit_fence(ring, job->uf_addr, job->uf_sequence,
> - fence_flags | AMDGPU_FENCE_FLAG_64BIT);
> + fence_flags | AMDGPU_FENCE_FLAG_64BIT |
> + AMDGPU_FENCE_FLAG_EXEC);
> }
>
> if (ring->funcs->emit_gfx_shadow && ring->funcs->init_cond_exec) {
> --
> 2.49.0
>
