From: jsg <jsg@openbsd.org>
Date: Thu, 18 Apr 2024 00:56:11 +0000 (+0000)
Subject: drm/amdkfd: Reset GPU on queue preemption failure
X-Git-Url: http://artulab.com/gitweb/?a=commitdiff_plain;h=afba13e901c91144c54246060d7eabdd2d6bb2b1;p=openbsd

drm/amdkfd: Reset GPU on queue preemption failure

From Harish Kasiviswanathan
4d87f08eb75513334a85458306373d7560af1017 in linux-6.6.y/6.6.28
8bdfb4ea95ca738d33ef71376c21eba20130f2eb in mainline linux
---

diff --git a/sys/dev/pci/drm/amd/amdkfd/kfd_device_queue_manager.c b/sys/dev/pci/drm/amd/amdkfd/kfd_device_queue_manager.c
index e07652e7249..60d98301ef0 100644
--- a/sys/dev/pci/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/sys/dev/pci/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1980,6 +1980,7 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm,
 		pr_err("HIQ MQD's queue_doorbell_id0 is not 0, Queue preemption time out\n");
 		while (halt_if_hws_hang)
 			schedule();
+		kfd_hws_hang(dqm);
 		return -ETIME;
 	}