[PATCH 9/9] drm/amdkfd: Improve multiple SDMA queues support per process

[Felix Kuehling]

From: shaoyunl <Shaoyun.Liu at amd.com>

HWS does not support over-subscription and the scheduler can not internally
modify the engine. Driver needs to program the correct engine ID.

Fix the queue and engine selection to create queues on alternating SDMA
engines. This allows concurrent bi-directional DMA transfers in a process
that creates two SDMA queues.

Signed-off-by: shaoyun liu <shaoyun.liu at amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling at amd.com>
---
 .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c  | 29 +++++++++++-----------
 drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c    |  2 +-
 2 files changed, 16 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index a7455db..64878b9 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -621,8 +621,8 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm,
 	if (retval)
 		return retval;
 
-	q->properties.sdma_queue_id = q->sdma_id % CIK_SDMA_QUEUES_PER_ENGINE;
-	q->properties.sdma_engine_id = q->sdma_id / CIK_SDMA_ENGINE_NUM;
+	q->properties.sdma_queue_id = q->sdma_id / CIK_SDMA_QUEUES_PER_ENGINE;
+	q->properties.sdma_engine_id = q->sdma_id % CIK_SDMA_QUEUES_PER_ENGINE;
 
 	pr_debug("SDMA id is:    %d\n", q->sdma_id);
 	pr_debug("SDMA queue id: %d\n", q->properties.sdma_queue_id);
@@ -704,6 +704,7 @@ static int initialize_cpsch(struct device_queue_manager *dqm)
 	dqm->queue_count = dqm->processes_count = 0;
 	dqm->sdma_queue_count = 0;
 	dqm->active_runlist = false;
+	dqm->sdma_bitmap = (1 << CIK_SDMA_QUEUES) - 1;
 	retval = dqm->ops_asic_specific.initialize(dqm);
 	if (retval)
 		mutex_destroy(&dqm->lock);
@@ -811,14 +812,6 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm,
 	mutex_unlock(&dqm->lock);
 }
 
-static void select_sdma_engine_id(struct queue *q)
-{
-	static int sdma_id;
-
-	q->sdma_id = sdma_id;
-	sdma_id = (sdma_id + 1) % 2;
-}
-
 static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 			struct qcm_process_device *qpd, int *allocate_vmid)
 {
@@ -839,9 +832,15 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 		goto out;
 	}
 
-	if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
-		select_sdma_engine_id(q);
-
+	if (q->properties.type == KFD_QUEUE_TYPE_SDMA) {
+		retval = allocate_sdma_queue(dqm, &q->sdma_id);
+		if (retval != 0)
+			goto out;
+		q->properties.sdma_queue_id =
+			q->sdma_id / CIK_SDMA_QUEUES_PER_ENGINE;
+		q->properties.sdma_engine_id =
+			q->sdma_id % CIK_SDMA_QUEUES_PER_ENGINE;
+	}
 	mqd = dqm->ops.get_mqd_manager(dqm,
 			get_mqd_type_from_queue_type(q->properties.type));
 
@@ -1015,8 +1014,10 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 		goto failed;
 	}
 
-	if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
+	if (q->properties.type == KFD_QUEUE_TYPE_SDMA) {
 		dqm->sdma_queue_count--;
+		deallocate_sdma_queue(dqm, q->sdma_id);
+	}
 
 	list_del(&q->list);
 	qpd->queue_count--;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
index 5d1770e..16da8ad 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
@@ -203,7 +203,7 @@ static int pm_create_map_queue(struct packet_manager *pm, uint32_t *buffer,
 			queue_type__mes_map_queues__debug_interface_queue_vi;
 		break;
 	case KFD_QUEUE_TYPE_SDMA:
-		packet->bitfields2.engine_sel =
+		packet->bitfields2.engine_sel = q->properties.sdma_engine_id +
 				engine_sel__mes_map_queues__sdma0_vi;
 		use_static = false; /* no static queues under SDMA */
 		break;
-- 
2.7.4