habanalabs/gaudi2: support abrupt device reset event

In certain scenarios, firmware might encounter a fatal event for
which a device reset is required. Hence, a proper notification
is needed for driver to be aware and initiate a reset sequence.

In secured environments the reset will be performed by firmware
without an explicit request from the driver.

Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>

drivers/misc/habanalabs/gaudi2/gaudi2.c

@@ -9226,6 +9226,7 @@ static void gaudi2_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_ent
 		break;
 
 	case GAUDI2_EVENT_CPU_FP32_NOT_SUPPORTED:
+	case GAUDI2_EVENT_DEV_RESET_REQ:
 		event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
 		error_count = GAUDI2_NA_EVENT_CAUSE;
 		is_critical = true;

drivers/misc/habanalabs/include/gaudi2/gaudi2_async_events.h

@@ -958,6 +958,7 @@ enum gaudi2_async_event_id {
 	GAUDI2_EVENT_CPU11_STATUS_NIC11_ENG1 = 1318,
 	GAUDI2_EVENT_ARC_DCCM_FULL = 1319,
 	GAUDI2_EVENT_CPU_FP32_NOT_SUPPORTED = 1320,
+	GAUDI2_EVENT_DEV_RESET_REQ = 1321,
 	GAUDI2_EVENT_SIZE,
 };
 

drivers/misc/habanalabs/include/gaudi2/gaudi2_async_ids_map_extended.h

@@ -2665,6 +2665,8 @@ static struct gaudi2_async_events_ids_map gaudi2_irq_map_table[] = {
 		.msg = 1, .reset = 0, .name = "ARC_DCCM_FULL" },
 	{ .fc_id = 1320, .cpu_id = 626, .valid = 1,
 		.msg = 1, .reset = 1, .name = "FP32_NOT_SUPPORTED" },
+	{ .fc_id = 1321, .cpu_id = 627, .valid = 1,
+		.msg = 1, .reset = 1, .name = "DEV_RESET_REQ" },
 };
 
 #endif /* __GAUDI2_ASYNC_IDS_MAP_EVENTS_EXT_H_ */