drm/amd: Update MEC HQD loading code for KFD

Various bug fixes and improvements that accumulated over the last two
years.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

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

@@ -270,8 +270,8 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
 	pr_debug("Loading mqd to hqd on pipe %d, queue %d\n",
 			q->pipe, q->queue);
 
-	retval = mqd->load_mqd(mqd, q->mqd, q->pipe,
-			q->queue, (uint32_t __user *) q->properties.write_ptr);
+	retval = mqd->load_mqd(mqd, q->mqd, q->pipe, q->queue, &q->properties,
+			       q->process->mm);
 	if (retval)
 		goto out_uninit_mqd;
 
@@ -587,8 +587,7 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm,
 	if (retval)
 		goto out_deallocate_sdma_queue;
 
-	retval = mqd->load_mqd(mqd, q->mqd, 0,
-				0, NULL);
+	retval = mqd->load_mqd(mqd, q->mqd, 0, 0, &q->properties, NULL);
 	if (retval)
 		goto out_uninit_mqd;
 

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

@@ -143,7 +143,8 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 		kq->queue->pipe = KFD_CIK_HIQ_PIPE;
 		kq->queue->queue = KFD_CIK_HIQ_QUEUE;
 		kq->mqd->load_mqd(kq->mqd, kq->queue->mqd, kq->queue->pipe,
-					kq->queue->queue, NULL);
+				  kq->queue->queue, &kq->queue->properties,
+				  NULL);
 	} else {
 		/* allocate fence for DIQ */
 

drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h

@@ -67,7 +67,8 @@ struct mqd_manager {
 
 	int	(*load_mqd)(struct mqd_manager *mm, void *mqd,
 				uint32_t pipe_id, uint32_t queue_id,
-				uint32_t __user *wptr);
+				struct queue_properties *p,
+				struct mm_struct *mms);
 
 	int	(*update_mqd)(struct mqd_manager *mm, void *mqd,
 				struct queue_properties *q);

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

@@ -144,15 +144,21 @@ static void uninit_mqd_sdma(struct mqd_manager *mm, void *mqd,
 }
 
 static int load_mqd(struct mqd_manager *mm, void *mqd, uint32_t pipe_id,
-			uint32_t queue_id, uint32_t __user *wptr)
+		    uint32_t queue_id, struct queue_properties *p,
+		    struct mm_struct *mms)
 {
-	return mm->dev->kfd2kgd->hqd_load
-		(mm->dev->kgd, mqd, pipe_id, queue_id, wptr);
+	/* AQL write pointer counts in 64B packets, PM4/CP counts in dwords. */
+	uint32_t wptr_shift = (p->format == KFD_QUEUE_FORMAT_AQL ? 4 : 0);
+	uint32_t wptr_mask = (uint32_t)((p->queue_size / sizeof(uint32_t)) - 1);
+
+	return mm->dev->kfd2kgd->hqd_load(mm->dev->kgd, mqd, pipe_id, queue_id,
+					  (uint32_t __user *)p->write_ptr,
+					  wptr_shift, wptr_mask, mms);
 }
 
 static int load_mqd_sdma(struct mqd_manager *mm, void *mqd,
-			uint32_t pipe_id, uint32_t queue_id,
-			uint32_t __user *wptr)
+			 uint32_t pipe_id, uint32_t queue_id,
+			 struct queue_properties *p, struct mm_struct *mms)
 {
 	return mm->dev->kfd2kgd->hqd_sdma_load(mm->dev->kgd, mqd);
 }
@@ -176,20 +182,17 @@ static int update_mqd(struct mqd_manager *mm, void *mqd,
 	m->cp_hqd_pq_base_hi = upper_32_bits((uint64_t)q->queue_address >> 8);
 	m->cp_hqd_pq_rptr_report_addr_lo = lower_32_bits((uint64_t)q->read_ptr);
 	m->cp_hqd_pq_rptr_report_addr_hi = upper_32_bits((uint64_t)q->read_ptr);
-	m->cp_hqd_pq_doorbell_control = DOORBELL_EN |
-					DOORBELL_OFFSET(q->doorbell_off);
+	m->cp_hqd_pq_doorbell_control = DOORBELL_OFFSET(q->doorbell_off);
 
 	m->cp_hqd_vmid = q->vmid;
 
 	if (q->format == KFD_QUEUE_FORMAT_AQL)
 		m->cp_hqd_pq_control |= NO_UPDATE_RPTR;
 
-	m->cp_hqd_active = 0;
 	q->is_active = false;
 	if (q->queue_size > 0 &&
 			q->queue_address != 0 &&
 			q->queue_percent > 0) {
-		m->cp_hqd_active = 1;
 		q->is_active = true;
 	}
 
@@ -239,7 +242,7 @@ static int destroy_mqd(struct mqd_manager *mm, void *mqd,
 			unsigned int timeout, uint32_t pipe_id,
 			uint32_t queue_id)
 {
-	return mm->dev->kfd2kgd->hqd_destroy(mm->dev->kgd, type, timeout,
+	return mm->dev->kfd2kgd->hqd_destroy(mm->dev->kgd, mqd, type, timeout,
 					pipe_id, queue_id);
 }
 

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

@@ -94,10 +94,15 @@ static int init_mqd(struct mqd_manager *mm, void **mqd,
 
 static int load_mqd(struct mqd_manager *mm, void *mqd,
 			uint32_t pipe_id, uint32_t queue_id,
-			uint32_t __user *wptr)
+			struct queue_properties *p, struct mm_struct *mms)
 {
-	return mm->dev->kfd2kgd->hqd_load
-		(mm->dev->kgd, mqd, pipe_id, queue_id, wptr);
+	/* AQL write pointer counts in 64B packets, PM4/CP counts in dwords. */
+	uint32_t wptr_shift = (p->format == KFD_QUEUE_FORMAT_AQL ? 4 : 0);
+	uint32_t wptr_mask = (uint32_t)((p->queue_size / sizeof(uint32_t)) - 1);
+
+	return mm->dev->kfd2kgd->hqd_load(mm->dev->kgd, mqd, pipe_id, queue_id,
+					  (uint32_t __user *)p->write_ptr,
+					  wptr_shift, wptr_mask, mms);
 }
 
 static int __update_mqd(struct mqd_manager *mm, void *mqd,
@@ -122,7 +127,6 @@ static int __update_mqd(struct mqd_manager *mm, void *mqd,
 	m->cp_hqd_pq_rptr_report_addr_hi = upper_32_bits((uint64_t)q->read_ptr);
 
 	m->cp_hqd_pq_doorbell_control =
-		1 << CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_EN__SHIFT |
 		q->doorbell_off <<
 			CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET__SHIFT;
 	pr_debug("cp_hqd_pq_doorbell_control 0x%x\n",
@@ -159,12 +163,10 @@ static int __update_mqd(struct mqd_manager *mm, void *mqd,
 				2 << CP_HQD_PQ_CONTROL__SLOT_BASED_WPTR__SHIFT;
 	}
 
-	m->cp_hqd_active = 0;
 	q->is_active = false;
 	if (q->queue_size > 0 &&
 			q->queue_address != 0 &&
 			q->queue_percent > 0) {
-		m->cp_hqd_active = 1;
 		q->is_active = true;
 	}
 
@@ -184,7 +186,7 @@ static int destroy_mqd(struct mqd_manager *mm, void *mqd,
 			uint32_t queue_id)
 {
 	return mm->dev->kfd2kgd->hqd_destroy
-		(mm->dev->kgd, type, timeout,
+		(mm->dev->kgd, mqd, type, timeout,
 		pipe_id, queue_id);
 }
 

drivers/gpu/drm/amd/amdkfd/kfd_priv.h

@@ -239,11 +239,6 @@ enum kfd_preempt_type_filter {
 	KFD_PREEMPT_TYPE_FILTER_BY_PASID
 };
 
-enum kfd_preempt_type {
-	KFD_PREEMPT_TYPE_WAVEFRONT,
-	KFD_PREEMPT_TYPE_WAVEFRONT_RESET
-};
-
 /**
  * enum kfd_queue_type
  *