From: shaoyunl <Shaoyun.Liu@amd.com>
Date: Wed, 27 Sep 2017 00:09:56 -0400
Subject: drm/amdkfd: Improve multiple SDMA queues support per process
Git-commit: e139cd2a2ff842bd4a5d089b9d251ca62f58ecac
Patch-mainline: v4.15-rc1
References: FATE#326289 FATE#326079 FATE#326049 FATE#322398 FATE#326166

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@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Acked-by: Petr Tesarik <ptesarik@suse.com>
---
 drivers/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(-)

--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -622,8 +622,8 @@ static int create_sdma_queue_nocpsch(str
 	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);
@@ -705,6 +705,7 @@ static int initialize_cpsch(struct devic
 	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);
@@ -812,14 +813,6 @@ static void destroy_kernel_queue_cpsch(s
 	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)
 {
@@ -840,9 +833,15 @@ static int create_queue_cpsch(struct dev
 		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));
 
@@ -1013,8 +1012,10 @@ static int destroy_queue_cpsch(struct de
 		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--;
--- 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 pa
 			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;