accel/ivpu: Use separate flag for job timeout

Use separate flag to mark a job timeout as a reason
of starting context_abort_work. This allows to distinguish
engine reset reason and clearly adjust reset procedure flow.

The flag is cleared in ivpu_prepare_for_reset(), which every
recovery and suspend path already funnels through, so that the
state is clean after recovery.

Cc: [email protected] # v7.1+
Fixes: ade00a6c90 ("accel/ivpu: Perform engine reset instead of device recovery on TDR")
Signed-off-by: Jakub Pawlak <[email protected]>
Reviewed-by: Dawid Osuchowski <[email protected]>
Signed-off-by: Karol Wachowski <[email protected]>
Link: https://patch.msgid.link/[email protected]

drivers/accel/ivpu/ivpu_drv.c

@@ -515,6 +515,7 @@ void ivpu_prepare_for_reset(struct ivpu_device *vdev)
 {
 	ivpu_hw_irq_disable(vdev);
 	disable_irq(vdev->irq);
+	atomic_set(&vdev->job_timeout_detected, 0);
 	flush_work(&vdev->irq_dct_work);
 	flush_work(&vdev->context_abort_work);
 	flush_work(&vdev->job_destroy_work);
@@ -710,7 +711,7 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 	vdev->context_xa_limit.max = IVPU_USER_CONTEXT_MAX_SSID;
 	atomic64_set(&vdev->unique_id_counter, 0);
 	atomic_set(&vdev->job_timeout_counter, 0);
-	atomic_set(&vdev->faults_detected, 0);
+	atomic_set(&vdev->job_timeout_detected, 0);
 	xa_init_flags(&vdev->context_xa, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ);
 	xa_init_flags(&vdev->submitted_jobs_xa, XA_FLAGS_ALLOC1);
 	xa_init_flags(&vdev->db_xa, XA_FLAGS_ALLOC1);

drivers/accel/ivpu/ivpu_drv.h

@@ -171,7 +171,7 @@ struct ivpu_device {
 	struct xarray submitted_jobs_xa;
 	struct ivpu_ipc_consumer job_done_consumer;
 	atomic_t job_timeout_counter;
-	atomic_t faults_detected;
+	atomic_t job_timeout_detected;
 
 	atomic64_t unique_id_counter;
 

drivers/accel/ivpu/ivpu_job.c

@@ -621,7 +621,6 @@ bool ivpu_job_handle_engine_error(struct ivpu_device *vdev, u32 job_id, u32 job_
 		 * status and ensure both are handled in the same way
 		 */
 		job->file_priv->has_mmu_faults = true;
-		atomic_set(&vdev->faults_detected, 1);
 		queue_work(system_percpu_wq, &vdev->context_abort_work);
 		return true;
 	}
@@ -1175,10 +1174,10 @@ static int reset_engine_and_mark_faulty_contexts(struct ivpu_device *vdev)
 		return ret;
 
 	/*
-	 * If faults are detected, ignore guilty contexts from engine reset as NPU may not be stuck
-	 * and could return currently running good context and faulty contexts are already marked
+	 * If job timeout is detected, read guilty context from engine reset, for other reasons
+	 * faulty context is already known
 	 */
-	if (atomic_cmpxchg(&vdev->faults_detected, 1, 0) == 1)
+	if (atomic_cmpxchg(&vdev->job_timeout_detected, 1, 0) == 0)
 		return 0;
 
 	num_impacted_contexts = resp.payload.engine_reset_done.num_impacted_contexts;

drivers/accel/ivpu/ivpu_mmu.c

@@ -964,7 +964,6 @@ void ivpu_mmu_irq_evtq_handler(struct ivpu_device *vdev)
 		file_priv = xa_load(&vdev->context_xa, ssid);
 		if (file_priv) {
 			if (!READ_ONCE(file_priv->has_mmu_faults)) {
-				atomic_set(&vdev->faults_detected, 1);
 				ivpu_mmu_dump_event(vdev, event);
 				WRITE_ONCE(file_priv->has_mmu_faults, true);
 			}

drivers/accel/ivpu/ivpu_pm.c

@@ -229,6 +229,7 @@ abort:
 
 	ivpu_jsm_state_dump(vdev);
 	ivpu_dev_coredump(vdev);
+	atomic_set(&vdev->job_timeout_detected, 1);
 	queue_work(system_percpu_wq, &vdev->context_abort_work);
 }