[PATCH 04/17] habanalabs/gaudi: send device reset notification

From: Oded Gabbay
Date: Mon Jun 20 2022 - 09:15:04 EST


From: Tal Cohen <talcohen@xxxxxxxxx>

Device reset event, indicates that the device shall be reset -
after a short delay. In such case, the driver sends a notification
towards the User process. This allows the User process
to be able to take several debug actions for system
diagnostic purposes.

Signed-off-by: Tal Cohen <talcohen@xxxxxxxxx>
Reviewed-by: Oded Gabbay <ogabbay@xxxxxxxxxx>
Signed-off-by: Oded Gabbay <ogabbay@xxxxxxxxxx>
---
drivers/misc/habanalabs/gaudi/gaudi.c | 13 ++++++++++---
1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 8f37297b2c3b..b7460c30aa51 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -8054,13 +8054,20 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
reset_device:
reset_required = true;

- if (hdev->asic_prop.fw_security_enabled && !reset_direct)
+ if (hdev->asic_prop.fw_security_enabled && !reset_direct) {
flags = HL_DRV_RESET_HARD | HL_DRV_RESET_BYPASS_REQ_TO_FW | fw_fatal_err_flag;
- else if (hdev->hard_reset_on_fw_events)
+ event_mask |= HL_NOTIFIER_EVENT_DEVICE_RESET;
+ } else if (hdev->hard_reset_on_fw_events) {
flags = HL_DRV_RESET_HARD | HL_DRV_RESET_DELAY | fw_fatal_err_flag;
- else
+ event_mask |= HL_NOTIFIER_EVENT_DEVICE_RESET;
+ } else {
reset_required = false;
+ }

+ /* despite reset doesn't execute. a notification on
+ * occurred event needs to be sent here
+ */
+ hl_notifier_event_send_all(hdev, event_mask);
if (reset_required)
hl_device_reset(hdev, flags);
else
--
2.25.1