diff options
| author | Jonathan Kim <jonathan.kim@amd.com> | 2023-07-12 16:58:55 -0400 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2023-07-25 13:35:43 -0400 |
| commit | 7a1c5c6753858cbbf0b073eaa9b53d8f56ee0927 (patch) | |
| tree | 84c104c37ff75fae773f41433f844cfa5316b625 /drivers/gpu/drm/amd/amdgpu | |
| parent | 83f24a8f0532f6d9fcdbe36e438f00a1a082fcd4 (diff) | |
| download | linux-7a1c5c6753858cbbf0b073eaa9b53d8f56ee0927.tar.gz linux-7a1c5c6753858cbbf0b073eaa9b53d8f56ee0927.tar.bz2 linux-7a1c5c6753858cbbf0b073eaa9b53d8f56ee0927.zip | |
drm/amdkfd: enable cooperative groups for gfx11
MES can concurrently schedule queues on the device that require
exclusive device access if marked exclusively_scheduled without the
requirement of GWS. Similar to the F32 HWS, MES will manage
quality of service for these queues.
Use this for cooperative groups since cooperative groups are device
occupancy limited.
Since some GFX11 devices can only be debugged with partial CUs, do not
allow the debugging of cooperative groups on these devices as the CU
occupancy limit will change on attach.
In addition, zero initialize the MES add queue submission vector for MES
initialization tests as we do not want these to be cooperative
dispatches.
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c | 2 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h | 1 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/mes_v11_0.c | 2 |
3 files changed, 5 insertions, 0 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index f808841310fd..72ab6a838bb6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -642,6 +642,8 @@ int amdgpu_mes_add_hw_queue(struct amdgpu_device *adev, int gang_id, unsigned long flags; int r; + memset(&queue_input, 0, sizeof(struct mes_add_queue_input)); + /* allocate the mes queue buffer */ queue = kzalloc(sizeof(struct amdgpu_mes_queue), GFP_KERNEL); if (!queue) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h index 2d6ac30b7135..2053954a235c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h @@ -224,6 +224,7 @@ struct mes_add_queue_input { uint32_t is_kfd_process; uint32_t is_aql_queue; uint32_t queue_size; + uint32_t exclusively_scheduled; }; struct mes_remove_queue_input { diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index 1bdaa00c0b46..8e67e965f7ea 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -214,6 +214,8 @@ static int mes_v11_0_add_hw_queue(struct amdgpu_mes *mes, mes_add_queue_pkt.is_aql_queue = input->is_aql_queue; mes_add_queue_pkt.gds_size = input->queue_size; + mes_add_queue_pkt.exclusively_scheduled = input->exclusively_scheduled; + return mes_v11_0_submit_pkt_and_poll_completion(mes, &mes_add_queue_pkt, sizeof(mes_add_queue_pkt), offsetof(union MESAPI__ADD_QUEUE, api_status)); |