drm/amdkfd: Update BadOpcode Interrupt handling with MES

Based on the recommendation of MEC FW, update BadOpcode interrupt
handling by unmapping all queues, removing the queue that got the
interrupt from scheduling and remapping rest of the queues back when
using MES scheduler. This is done to prevent the case where unmapping
of the bad queue can fail thereby causing a GPU reset.

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Acked-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 51 insertions, 0 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 5825e805da50..577d121cc6d1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -2931,6 +2931,57 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm)
 	kfree(dqm);
 }
 
+int kfd_dqm_suspend_bad_queue_mes(struct kfd_node *knode, u32 pasid, u32 doorbell_id)
+{
+	struct kfd_process_device *pdd;
+	struct kfd_process *p = kfd_lookup_process_by_pasid(pasid);
+	struct device_queue_manager *dqm = knode->dqm;
+	struct device *dev = dqm->dev->adev->dev;
+	struct qcm_process_device *qpd;
+	struct queue *q = NULL;
+	int ret = 0;
+
+	if (!p)
+		return -EINVAL;
+
+	dqm_lock(dqm);
+
+	pdd = kfd_get_process_device_data(dqm->dev, p);
+	if (pdd) {
+		qpd = &pdd->qpd;
+
+		list_for_each_entry(q, &qpd->queues_list, list) {
+			if (q->doorbell_id == doorbell_id && q->properties.is_active) {
+				ret = suspend_all_queues_mes(dqm);
+				if (ret) {
+					dev_err(dev, "Suspending all queues failed");
+					goto out;
+				}
+
+				q->properties.is_evicted = true;
+				q->properties.is_active = false;
+				decrement_queue_count(dqm, qpd, q);
+
+				ret = remove_queue_mes(dqm, q, qpd);
+				if (ret) {
+					dev_err(dev, "Removing bad queue failed");
+					goto out;
+				}
+
+				ret = resume_all_queues_mes(dqm);
+				if (ret)
+					dev_err(dev, "Resuming all queues failed");
+
+				break;
+			}
+		}
+	}
+
+out:
+	dqm_unlock(dqm);
+	return ret;
+}
+
 static int kfd_dqm_evict_pasid_mes(struct device_queue_manager *dqm,
 				   struct qcm_process_device *qpd)
 {