From: Karol Wachowski <karol.wachowski@xxxxxxxxx>
Mark as invalid context of a job that returned HW context violation
error and queue work that aborts jobs from faulty context.
Add engine reset to the context abort thread handler to not only abort
currently executing jobs but also to ensure NPU invalid state recovery.
Signed-off-by: Karol Wachowski <karol.wachowski@xxxxxxxxx>
Signed-off-by: Maciej Falkowski <maciej.falkowski@xxxxxxxxxxxxxxx>
---
drivers/accel/ivpu/ivpu_job.c | 25 +++++++++++++++++++++++++
1 file changed, 25 insertions(+)
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index c93ea37062d7..3c162ac41a1d 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -533,6 +533,26 @@ static int ivpu_job_signal_and_destroy(struct ivpu_device *vdev, u32 job_id, u32
lockdep_assert_held(&vdev->submitted_jobs_lock);
+ job = xa_load(&vdev->submitted_jobs_xa, job_id);
+ if (!job)
+ return -ENOENT;
+
+ if (job_status == VPU_JSM_STATUS_MVNCI_CONTEXT_VIOLATION_HW) {
+ guard(mutex)(&job->file_priv->lock);
+
+ if (job->file_priv->has_mmu_faults)
+ return 0;
+
+ /*
+ * Mark context as faulty and defer destruction of the job to jobs abort thread
+ * handler to synchronize between both faults and jobs returning context violation
+ * status and ensure both are handled in the same way
+ */
+ job->file_priv->has_mmu_faults = true;
+ queue_work(system_wq, &vdev->context_abort_work);
+ return 0;
+ }
+
job = ivpu_job_remove_from_submitted_jobs(vdev, job_id);
if (!job)
return -ENOENT;
@@ -946,6 +966,9 @@ void ivpu_context_abort_work_fn(struct work_struct *work)
unsigned long ctx_id;
unsigned long id;
+ if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW)
+ ivpu_jsm_reset_engine(vdev, 0);
+
mutex_lock(&vdev->context_list_lock);
xa_for_each(&vdev->context_xa, ctx_id, file_priv) {
if (!file_priv->has_mmu_faults || file_priv->aborted)
@@ -959,6 +982,8 @@ void ivpu_context_abort_work_fn(struct work_struct *work)
if (vdev->fw->sched_mode != VPU_SCHEDULING_MODE_HW)
return;
+
+ ivpu_jsm_hws_resume_engine(vdev, 0);
/*
* In hardware scheduling mode NPU already has stopped processing jobs
* and won't send us any further notifications, thus we have to free job related resources
--
2.43.0
