drm/amdkfd: get doorbell's absolute offset based on the db_size

Here, Adding db_size in byte to find the doorbell's
absolute offset for both 32-bit and 64-bit doorbell sizes.
So that doorbell offset will be aligned based on the doorbell
size.

v2:
- Addressed the review comment from Felix.
v3:
- Adding doorbell_size as parameter to get db absolute offset.
v4:
Squash the two patches into one.

Cc: Christian Koenig <[e-mail]>
Cc: Alex Deucher <[e-mail]>
Reviewed-by: Felix Kuehling <[e-mail]>
Signed-off-by: Shashank Sharma <[e-mail]>
Signed-off-by: Arvind Yadav <[e-mail]>
Signed-off-by: Alex Deucher <[e-mail]>

drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell.h

···
 void amdgpu_doorbell_fini(struct amdgpu_device *adev);
 int amdgpu_doorbell_create_kernel_doorbells(struct amdgpu_device *adev);
 uint32_t amdgpu_doorbell_index_on_bar(struct amdgpu_device *adev,
-				       struct amdgpu_bo *db_bo,
-				       uint32_t doorbell_index);
+				      struct amdgpu_bo *db_bo,
+				      uint32_t doorbell_index,
+				      uint32_t db_size);
 
 #define RDOORBELL32(index) amdgpu_mm_rdoorbell(adev, (index))
 #define WDOORBELL32(index, v) amdgpu_mm_wdoorbell(adev, (index), (v))

drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell_mgr.c

···
  * @adev: amdgpu_device pointer
  * @db_bo: doorbell object's bo
  * @doorbell_index: doorbell relative index in this doorbell object
+ * @db_size: doorbell size is in byte
  *
  * returns doorbell's absolute index in BAR
  */
 uint32_t amdgpu_doorbell_index_on_bar(struct amdgpu_device *adev,
-				       struct amdgpu_bo *db_bo,
-				       uint32_t doorbell_index)
+				      struct amdgpu_bo *db_bo,
+				      uint32_t doorbell_index,
+				      uint32_t db_size)
 {
 	int db_bo_offset;
 
 	db_bo_offset = amdgpu_bo_gpu_offset_no_check(db_bo);
 
-	/* doorbell index is 32 bit but doorbell's size is 64-bit, so *2 */
-	return db_bo_offset / sizeof(u32) + doorbell_index * 2;
+	/* doorbell index is 32 bit but doorbell's size can be 32 bit
+	 * or 64 bit, so *db_size(in byte)/4 for alignment.
+	 */
+	return db_bo_offset / sizeof(u32) + doorbell_index *
+	       DIV_ROUND_UP(db_size, 4);
 }
 
 /**

drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c

···
 
 	q->properties.doorbell_off = amdgpu_doorbell_index_on_bar(dev->adev,
 								  qpd->proc_doorbells,
-								  q->doorbell_id);
+								  q->doorbell_id,
+								  dev->kfd->device_info.doorbell_size);
 	return 0;
 }
 

drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c

···
 	if (inx >= KFD_MAX_NUM_OF_QUEUES_PER_PROCESS)
 		return NULL;
 
-	*doorbell_off = amdgpu_doorbell_index_on_bar(kfd->adev, kfd->doorbells, inx);
+	*doorbell_off = amdgpu_doorbell_index_on_bar(kfd->adev,
+						     kfd->doorbells,
+						     inx,
+						     kfd->device_info.doorbell_size);
 	inx *= 2;
 
 	pr_debug("Get kernel queue doorbell\n"
···
 			return 0;
 	}
 
-	first_db_index = amdgpu_doorbell_index_on_bar(adev, pdd->qpd.proc_doorbells, 0);
+	first_db_index = amdgpu_doorbell_index_on_bar(adev,
+						      pdd->qpd.proc_doorbells,
+						      0,
+						      pdd->dev->kfd->device_info.doorbell_size);
 	return adev->doorbell.base + first_db_index * sizeof(uint32_t);
 }
 

drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c

···
 		 */
 		uint32_t first_db_index = amdgpu_doorbell_index_on_bar(pdd->dev->adev,
 								       pdd->qpd.proc_doorbells,
-								       0);
+								       0,
+								       pdd->dev->kfd->device_info.doorbell_size);
 
 		*p_doorbell_offset_in_process = (q->properties.doorbell_off
 						- first_db_index) * sizeof(uint32_t);