[PATCH v9 06/14] drm/amdgpu: create context space for usermode queue

[Sharma, Shashank]

On 01/05/2024 23:11, Alex Deucher wrote:
> On Fri, Apr 26, 2024 at 10:07 AM Shashank Sharma
> <shashank.sharma at amd.com> wrote:
>> The FW expects us to allocate at least one page as context
>> space to process gang, process, GDS and FW  related work.
>> This patch creates a joint object for the same, and calculates
>> GPU space offsets of these spaces.
>>
>> V1: Addressed review comments on RFC patch:
>>      Alex: Make this function IP specific
>>
>> V2: Addressed review comments from Christian
>>      - Allocate only one object for total FW space, and calculate
>>        offsets for each of these objects.
>>
>> V3: Integration with doorbell manager
>>
>> V4: Review comments:
>>      - Remove shadow from FW space list from cover letter (Alex)
>>      - Alignment of macro (Luben)
>>
>> V5: Merged patches 5 and 6 into this single patch
>>      Addressed review comments:
>>      - Use lower_32_bits instead of mask (Christian)
>>      - gfx_v11_0 instead of gfx_v11 in function names (Alex)
>>      - Shadow and GDS objects are now coming from userspace (Christian,
>>        Alex)
>>
>> V6:
>>      - Add a comment to replace amdgpu_bo_create_kernel() with
>>        amdgpu_bo_create() during fw_ctx object creation (Christian).
>>      - Move proc_ctx_gpu_addr, gang_ctx_gpu_addr and fw_ctx_gpu_addr out
>>        of generic queue structure and make it gen11 specific (Alex).
>>
>> V7:
>>     - Using helper function to create/destroy userqueue objects.
>>     - Removed FW object space allocation.
>>
>> V8:
>>     - Updating FW object address from user values.
>>
>> V9:
>>     - uppdated function name from gfx_v11_* to mes_v11_*
>>
>> Cc: Alex Deucher <alexander.deucher at amd.com>
>> Cc: Christian Koenig <christian.koenig at amd.com>
>> Signed-off-by: Shashank Sharma <shashank.sharma at amd.com>
>> Signed-off-by: Arvind Yadav <arvind.yadav at amd.com>
>> ---
>>   .../gpu/drm/amd/amdgpu/mes_v11_0_userqueue.c  | 43 +++++++++++++++++++
>>   .../gpu/drm/amd/include/amdgpu_userqueue.h    |  1 +
>>   2 files changed, 44 insertions(+)
>>
>> diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0_userqueue.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0_userqueue.c
>> index 9e7dee77d344..9f9fdcb9c294 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0_userqueue.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0_userqueue.c
>> @@ -27,6 +27,41 @@
>>   #include "mes_v11_0.h"
>>   #include "amdgpu_userqueue.h"
>>
>> +#define AMDGPU_USERQ_PROC_CTX_SZ PAGE_SIZE
>> +#define AMDGPU_USERQ_GANG_CTX_SZ PAGE_SIZE
>> +
>> +static int mes_v11_0_userq_create_ctx_space(struct amdgpu_userq_mgr *uq_mgr,
>> +                                           struct amdgpu_usermode_queue *queue,
>> +                                           struct drm_amdgpu_userq_mqd *mqd_user)
>> +{
>> +       struct amdgpu_userq_obj *ctx = &queue->fw_obj;
>> +       struct v11_gfx_mqd *mqd = queue->mqd.cpu_ptr;
>> +       int r, size;
>> +
>> +       /*
>> +        * The FW expects at least one page space allocated for
>> +        * process ctx and gang ctx each. Create an object
>> +        * for the same.
>> +        */
>> +       size = AMDGPU_USERQ_PROC_CTX_SZ + AMDGPU_USERQ_GANG_CTX_SZ;
>> +       r = amdgpu_userqueue_create_object(uq_mgr, ctx, size);
> Is this per queue or per context?  I.e., is this shared with all
> queues associated with an fd?

This is per queue object, required for MES mapping of a queue.

- Shashank

> Alex
>
>> +       if (r) {
>> +               DRM_ERROR("Failed to allocate ctx space bo for userqueue, err:%d\n", r);
>> +               return r;
>> +       }
>> +
>> +       /* Shadow and GDS objects come directly from userspace */
>> +       mqd->shadow_base_lo = mqd_user->shadow_va & 0xFFFFFFFC;
>> +       mqd->shadow_base_hi = upper_32_bits(mqd_user->shadow_va);
>> +
>> +       mqd->gds_bkup_base_lo = mqd_user->gds_va & 0xFFFFFFFC;
>> +       mqd->gds_bkup_base_hi = upper_32_bits(mqd_user->gds_va);
>> +
>> +       mqd->fw_work_area_base_lo = mqd_user->csa_va & 0xFFFFFFFC;
>> +       mqd->fw_work_area_base_hi = upper_32_bits(mqd_user->csa_va);
>> +       return 0;
>> +}
>> +
>>   static int mes_v11_0_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr,
>>                                        struct drm_amdgpu_userq_in *args_in,
>>                                        struct amdgpu_usermode_queue *queue)
>> @@ -82,6 +117,13 @@ static int mes_v11_0_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr,
>>                  goto free_mqd;
>>          }
>>
>> +       /* Create BO for FW operations */
>> +       r = mes_v11_0_userq_create_ctx_space(uq_mgr, queue, mqd_user);
>> +       if (r) {
>> +               DRM_ERROR("Failed to allocate BO for userqueue (%d)", r);
>> +               goto free_mqd;
>> +       }
>> +
>>          return 0;
>>
>>   free_mqd:
>> @@ -100,6 +142,7 @@ static void
>>   mes_v11_0_userq_mqd_destroy(struct amdgpu_userq_mgr *uq_mgr,
>>                              struct amdgpu_usermode_queue *queue)
>>   {
>> +       amdgpu_userqueue_destroy_object(uq_mgr, &queue->fw_obj);
>>          kfree(queue->userq_prop);
>>          amdgpu_userqueue_destroy_object(uq_mgr, &queue->mqd);
>>   }
>> diff --git a/drivers/gpu/drm/amd/include/amdgpu_userqueue.h b/drivers/gpu/drm/amd/include/amdgpu_userqueue.h
>> index bbd29f68b8d4..643f31474bd8 100644
>> --- a/drivers/gpu/drm/amd/include/amdgpu_userqueue.h
>> +++ b/drivers/gpu/drm/amd/include/amdgpu_userqueue.h
>> @@ -44,6 +44,7 @@ struct amdgpu_usermode_queue {
>>          struct amdgpu_userq_mgr *userq_mgr;
>>          struct amdgpu_vm        *vm;
>>          struct amdgpu_userq_obj mqd;
>> +       struct amdgpu_userq_obj fw_obj;
>>   };
>>
>>   struct amdgpu_userq_funcs {
>> --
>> 2.43.2
>>