From b3b32f20722790be0d093c94bf49bcd4eea69659 Mon Sep 17 00:00:00 2001
From: Tao Zhou <tao.zhou1@amd.com>
Date: Thu, 16 Dec 2021 14:34:10 +0800
Subject: drm/amdkfd: add reset queue function for RAS poison (v2)
Git-commit: dec63443380cf2ce6bc41258159cda4165fa4279
Patch-mainline: v5.17-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225

The new interface unmaps queues with reset mode for the process consumes
RAS poison, it's only for compute queue.

v2: rename the function to reset_queues.

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 .../drm/amd/amdkfd/kfd_device_queue_manager.c    | 16 ++++++++++++++++
 .../drm/amd/amdkfd/kfd_device_queue_manager.h    |  5 +++++
 2 files changed, 21 insertions(+)

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 01a2cc3928ac..19890e350107 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1476,6 +1476,21 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm,
 	return retval;
 }
 
+/* only for compute queue */
+static int reset_queues_cpsch(struct device_queue_manager *dqm,
+			uint16_t pasid)
+{
+	int retval;
+
+	dqm_lock(dqm);
+
+	retval = unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_BY_PASID,
+			pasid, true);
+
+	dqm_unlock(dqm);
+	return retval;
+}
+
 /* dqm->lock mutex has to be locked before calling this function */
 static int execute_queues_cpsch(struct device_queue_manager *dqm,
 				enum kfd_unmap_queues_filter filter,
@@ -1896,6 +1911,7 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_dev *dev)
 		dqm->ops.evict_process_queues = evict_process_queues_cpsch;
 		dqm->ops.restore_process_queues = restore_process_queues_cpsch;
 		dqm->ops.get_wave_state = get_wave_state;
+		dqm->ops.reset_queues = reset_queues_cpsch;
 		break;
 	case KFD_SCHED_POLICY_NO_HWS:
 		/* initialize dqm for no cp scheduling */
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 499fc0ea387f..e145e4deb53a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -81,6 +81,8 @@ struct device_process_node {
  *
  * @get_wave_state: Retrieves context save state and optionally copies the
  * control stack, if kept in the MQD, to the given userspace address.
+ *
+ * @reset_queues: reset queues which consume RAS poison
  */
 
 struct device_queue_manager_ops {
@@ -134,6 +136,9 @@ struct device_queue_manager_ops {
 				  void __user *ctl_stack,
 				  u32 *ctl_stack_used_size,
 				  u32 *save_area_used_size);
+
+	int (*reset_queues)(struct device_queue_manager *dqm,
+					uint16_t pasid);
 };
 
 struct device_queue_manager_asic_ops {
-- 
2.38.1