AMD General
Regards,
Prike
> -----Original Message-----
> From: amd-gfx <[email protected]> On Behalf Of Jesse
> Zhang
> Sent: Monday, June 1, 2026 1:49 PM
> To: [email protected]
> Cc: Deucher, Alexander <[email protected]>; Koenig, Christian
> <[email protected]>; Zhang, Jesse(Jie) <[email protected]>;
> Chen, Michael <[email protected]>; Deucher, Alexander
> <[email protected]>; Liu, Shaoyun <[email protected]>; Zhang,
> Jesse(Jie) <[email protected]>
> Subject: [PATCH v2 12/42] drm/amdgpu/mes_v12_1: use mes schedule pipe for
> legacy queues on unified MES
>
> when suspend_all_gangs is issued to pipe0 MES during system suspend or runtime
> PM, pipe0 can only suspend and resume queues it has tracked.
> KCQs registered with a non-zero pipe slot may not be correctly handled,
> leaving
> them in an inconsistent state after resume.
>
> v3: fix the schedule pipe issue
>
> Suggested-by: Michael Chen <[email protected]>
> Suggested-by: Alex Deucher <[email protected]>
> Suggested-by: Shaoyun Liu <[email protected]>
> Signed-off-by: Jesse Zhang <[email protected]>
> Signed-off-by: Alex Deucher <[email protected]>
> ---
> drivers/gpu/drm/amd/amdgpu/mes_v12_1.c | 22 ++++++++++++++++------
> 1 file changed, 16 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_1.c
> b/drivers/gpu/drm/amd/amdgpu/mes_v12_1.c
> index b169e577e583..2099beedd575 100644
> --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_1.c
> +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_1.c
> @@ -417,10 +417,15 @@ static int mes_v12_1_map_legacy_queue(struct
> amdgpu_mes *mes,
> convert_to_mes_queue_type(input->queue_type);
> mes_add_queue_pkt.map_legacy_kq = 1;
>
> - if (mes->adev->enable_uni_mes)
> - pipe = AMDGPU_MES_KIQ_PIPE;
> - else
> + if (mes->adev->enable_uni_mes) {
> + /* Keep scheduler queue on KIQ pipe; map all other kernel
> queues on
> sched pipe. */
> + if (input->queue_type == AMDGPU_RING_TYPE_MES)
> + pipe = AMDGPU_MES_KIQ_PIPE;
> + else
> + pipe = AMDGPU_MES_SCHED_PIPE;
> + } else {
> pipe = AMDGPU_MES_SCHED_PIPE;
> + }
The queue scheduler pipe calculation is generic and also used in the other
places like as the queue reset, so how about create a common function used for
calculating the queue scheduler pipe?
Without it or not, the patch is Reviewed-by: Prike Liang <[email protected]>
>
> return mes_v12_1_submit_pkt_and_poll_completion(mes,
> input->xcc_id, pipe,
> @@ -457,10 +462,15 @@ static int mes_v12_1_unmap_legacy_queue(struct
> amdgpu_mes *mes,
> convert_to_mes_queue_type(input->queue_type);
> }
>
> - if (mes->adev->enable_uni_mes)
> - pipe = AMDGPU_MES_KIQ_PIPE;
> - else
> + if (mes->adev->enable_uni_mes) {
> + /* Keep scheduler queue on KIQ pipe; map all other kernel
> queues on
> sched pipe. */
> + if (input->queue_type == AMDGPU_RING_TYPE_MES)
> + pipe = AMDGPU_MES_KIQ_PIPE;
> + else
> + pipe = AMDGPU_MES_SCHED_PIPE;
> + } else {
> pipe = AMDGPU_MES_SCHED_PIPE;
> + }
>
> return mes_v12_1_submit_pkt_and_poll_completion(mes,
> input->xcc_id, pipe,
> --
> 2.49.0
