amdkfd: Add device queue manager module

The queue scheduler divides into two sections, one section is process bounded
and the other section is device bounded.
The device bounded section is handled by this module.
The DQM module handles queue setup, update and tear-down from the device side.
It also supports suspend/resume operation.

v3: Changed device_init, added the use of the new gart allocation functions an
Added documentation.

v4:

Fixed a race in DQM queue scheduler where dqm->lock must be held when accessing
dqm->queue_count and dqm->processes_count. This fixes runlist IB allocation
failures when DQM is under load.

Fixed race in DQM queue destruction where queues being destroyed must be
removed from qpd->queues_list prior to preemption, or concurrent queue
creation activity may reschedule them while their MQD is destroyed.

Fixed EOP queue size setting in CP_HPD_EOP_CONTROL, because the size is
specified as (log2(size_dwords)-1). The previous calculation assumed the
size was specified in bytes, which caused interference between EOP queues
when multiple MEC pipelines were active.

v5:

Move amdkfd from drm/radeon/ to drm/amd/
Change format of mqd structure to match latest KV firmware
Add support for AQL queues creation to enable working with open-source HSA
runtime
Remove unused unmap_queue function
Various fixes (Style, typos)

Signed-off-by: Ben Goz <ben.goz@amd.com>
Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@amd.com>

1 files changed, 47 insertions, 2 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
index e495b38..c3f189e8 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -42,6 +42,50 @@ struct device_process_node {
 	struct list_head list;
 };
 
+/**
+ * struct device_queue_manager
+ *
+ * @create_queue: Queue creation routine.
+ *
+ * @destroy_queue: Queue destruction routine.
+ *
+ * @update_queue: Queue update routine.
+ *
+ * @get_mqd_manager: Returns the mqd manager according to the mqd type.
+ *
+ * @exeute_queues: Dispatches the queues list to the H/W.
+ *
+ * @register_process: This routine associates a specific process with device.
+ *
+ * @unregister_process: destroys the associations between process to device.
+ *
+ * @initialize: Initializes the pipelines and memory module for that device.
+ *
+ * @start: Initializes the resources/modules the the device needs for queues
+ * execution. This function is called on device initialization and after the
+ * system woke up after suspension.
+ *
+ * @stop: This routine stops execution of all the active queue running on the
+ * H/W and basically this function called on system suspend.
+ *
+ * @uninitialize: Destroys all the device queue manager resources allocated in
+ * initialize routine.
+ *
+ * @create_kernel_queue: Creates kernel queue. Used for debug queue.
+ *
+ * @destroy_kernel_queue: Destroys kernel queue. Used for debug queue.
+ *
+ * @set_cache_memory_policy: Sets memory policy (cached/ non cached) for the
+ * memory apertures.
+ *
+ * This struct is a base class for the kfd queues scheduler in the
+ * device level. The device base class should expose the basic operations
+ * for queue creation and queue destruction. This base class hides the
+ * scheduling mode of the driver and the specific implementation of the
+ * concrete device. This class is the only class in the queues scheduler
+ * that configures the H/W.
+ */
+
 struct device_queue_manager {
 	int	(*create_queue)(struct device_queue_manager *dqm,
 				struct queue *q,
@@ -52,8 +96,9 @@ struct device_queue_manager {
 				struct queue *q);
 	int	(*update_queue)(struct device_queue_manager *dqm,
 				struct queue *q);
-	struct mqd_manager * (*get_mqd_manager)(
-					struct device_queue_manager *dqm,
+
+	struct mqd_manager * (*get_mqd_manager)
+					(struct device_queue_manager *dqm,
 					enum KFD_MQD_TYPE type);
 
 	int	(*register_process)(struct device_queue_manager *dqm,