habanalabs/gaudi: reset device upon BMC request

In case the BMC of the devices' box wants to initiate a reset of
a specific device, it must go through driver.
Once driver will receive the request it will initiate a hard reset
flow.

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

diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 8be75f7..099c513 100644 (file)
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -7575,6 +7575,10 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
                        event_type, cause);
                break;
 
+       case GAUDI_EVENT_BMC_RESET_CMD:
+               gaudi_print_irq_info(hdev, event_type, false);
+               goto reset_device;
+
        case GAUDI_EVENT_PKT_QUEUE_OUT_SYNC:
                gaudi_print_irq_info(hdev, event_type, false);
                gaudi_print_out_of_sync_info(hdev, &eq_entry->pkt_sync_err);

diff --git a/drivers/misc/habanalabs/include/gaudi/gaudi_async_events.h b/drivers/misc/habanalabs/include/gaudi/gaudi_async_events.h
index 0a0fa57..25f835b 100644 (file)
--- a/drivers/misc/habanalabs/include/gaudi/gaudi_async_events.h
+++ b/drivers/misc/habanalabs/include/gaudi/gaudi_async_events.h
@@ -303,6 +303,7 @@ enum gaudi_async_event_id {
        GAUDI_EVENT_NIC3_QP1 = 619,
        GAUDI_EVENT_NIC4_QP0 = 620,
        GAUDI_EVENT_NIC4_QP1 = 621,
+       GAUDI_EVENT_BMC_RESET_CMD = 646,
        GAUDI_EVENT_PKT_QUEUE_OUT_SYNC = 647,
        GAUDI_EVENT_FIX_POWER_ENV_S = 658,
        GAUDI_EVENT_FIX_POWER_ENV_E = 659,

diff --git a/drivers/misc/habanalabs/include/gaudi/gaudi_async_ids_map_extended.h b/drivers/misc/habanalabs/include/gaudi/gaudi_async_ids_map_extended.h
index 9106395..079be1f 100644 (file)
--- a/drivers/misc/habanalabs/include/gaudi/gaudi_async_ids_map_extended.h
+++ b/drivers/misc/habanalabs/include/gaudi/gaudi_async_ids_map_extended.h
@@ -670,7 +670,7 @@ static struct gaudi_async_events_ids_map gaudi_irq_map_table[] = {
        { .fc_id = 643, .cpu_id = 492, .valid = 0, .name = "" },
        { .fc_id = 644, .cpu_id = 493, .valid = 0, .name = "" },
        { .fc_id = 645, .cpu_id = 494, .valid = 0, .name = "" },
-       { .fc_id = 646, .cpu_id = 495, .valid = 0, .name = "" },
+       { .fc_id = 646, .cpu_id = 495, .valid = 1, .name = "BMC_RST_CMD" },
        { .fc_id = 647, .cpu_id = 496, .valid = 0, .name = "" },
        { .fc_id = 648, .cpu_id = 497, .valid = 0, .name = "" },
        { .fc_id = 649, .cpu_id = 498, .valid = 0, .name = "" },