drm/panthor: Force an immediate reset on unrecoverable faults

If the FW reports an unrecoverable fault, we need to reset the GPU
before we can start re-using it again.

Signed-off-by: Boris Brezillon <[email protected]>
Reviewed-by: Steven Price <[email protected]>
Reviewed-by: Liviu Dudau <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

Author: bbrezillon

drivers/gpu/drm/panthor/panthor_device.c

@@ -293,6 +293,7 @@ static const struct panthor_exception_info panthor_exception_infos[] = {
 	PANTHOR_EXCEPTION(ACTIVE),
 	PANTHOR_EXCEPTION(CS_RES_TERM),
 	PANTHOR_EXCEPTION(CS_CONFIG_FAULT),
+	PANTHOR_EXCEPTION(CS_UNRECOVERABLE),
 	PANTHOR_EXCEPTION(CS_ENDPOINT_FAULT),
 	PANTHOR_EXCEPTION(CS_BUS_FAULT),
 	PANTHOR_EXCEPTION(CS_INSTR_INVALID),

drivers/gpu/drm/panthor/panthor_device.h

@@ -216,6 +216,7 @@ enum drm_panthor_exception_type {
 	DRM_PANTHOR_EXCEPTION_CS_RES_TERM = 0x0f,
 	DRM_PANTHOR_EXCEPTION_MAX_NON_FAULT = 0x3f,
 	DRM_PANTHOR_EXCEPTION_CS_CONFIG_FAULT = 0x40,
+	DRM_PANTHOR_EXCEPTION_CS_UNRECOVERABLE = 0x41,
 	DRM_PANTHOR_EXCEPTION_CS_ENDPOINT_FAULT = 0x44,
 	DRM_PANTHOR_EXCEPTION_CS_BUS_FAULT = 0x48,
 	DRM_PANTHOR_EXCEPTION_CS_INSTR_INVALID = 0x49,

drivers/gpu/drm/panthor/panthor_sched.c

@@ -1281,7 +1281,16 @@ cs_slot_process_fatal_event_locked(struct panthor_device *ptdev,
 	if (group)
 		group->fatal_queues |= BIT(cs_id);
 
-	sched_queue_delayed_work(sched, tick, 0);
+	if (CS_EXCEPTION_TYPE(fatal) == DRM_PANTHOR_EXCEPTION_CS_UNRECOVERABLE) {
+		/* If this exception is unrecoverable, queue a reset, and make
+		 * sure we stop scheduling groups until the reset has happened.
+		 */
+		panthor_device_schedule_reset(ptdev);
+		cancel_delayed_work(&sched->tick_work);
+	} else {
+		sched_queue_delayed_work(sched, tick, 0);
+	}
+
 	drm_warn(&ptdev->base,
 		 "CSG slot %d CS slot: %d\n"
 		 "CS_FATAL.EXCEPTION_TYPE: 0x%x (%s)\n"