habanalabs/gaudi: notify user process on device unavailable

When a device error occurs, user process would like to get some
indication on the error by reading some device HW info. If the
device is unavailable, user process can't perform any HW device
reading.

Signed-off-by: Tal Cohen <talcohen@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 1156ec7dacc12755e8b414002bc0b1c54ce5ee1d..939d2636b9ed481aaedafda3f56a7b07159632b8 100644 (file)
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -8063,7 +8063,10 @@ reset_device:
 
        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;
-               event_mask |= HL_NOTIFIER_EVENT_DEVICE_RESET;
+
+               /* notify on device unavailable while the reset triggered by fw */
+               event_mask |= (HL_NOTIFIER_EVENT_DEVICE_RESET |
+                                       HL_NOTIFIER_EVENT_DEVICE_UNAVAILABLE);
        } else if (hdev->hard_reset_on_fw_events) {
                flags = HL_DRV_RESET_HARD | HL_DRV_RESET_DELAY | fw_fatal_err_flag;
                event_mask |= HL_NOTIFIER_EVENT_DEVICE_RESET;

diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h
index 18f86d259421bb6064967377925f131ba15441d6..78aecea4684d4790ae191a9d0c9554fe3c15fc4a 100644 (file)
--- a/include/uapi/misc/habanalabs.h
+++ b/include/uapi/misc/habanalabs.h
@@ -1432,15 +1432,17 @@ struct hl_debug_args {
 /*
  * Notifier event values - for the notification mechanism and the HL_INFO_GET_EVENTS command
  *
- * HL_NOTIFIER_EVENT_TPC_ASSERT       - Indicates TPC assert event
- * HL_NOTIFIER_EVENT_UNDEFINED_OPCODE - Indicates undefined operation code
- * HL_NOTIFIER_EVENT_DEVICE_RESET     - Indicates device requires a reset
- * HL_NOTIFIER_EVENT_CS_TIMEOUT       - Indicates CS timeout error
+ * HL_NOTIFIER_EVENT_TPC_ASSERT                - Indicates TPC assert event
+ * HL_NOTIFIER_EVENT_UNDEFINED_OPCODE  - Indicates undefined operation code
+ * HL_NOTIFIER_EVENT_DEVICE_RESET      - Indicates device requires a reset
+ * HL_NOTIFIER_EVENT_CS_TIMEOUT                - Indicates CS timeout error
+ * HL_NOTIFIER_EVENT_DEVICE_UNAVAILABLE        - Indicates device is unavailable
  */
 #define HL_NOTIFIER_EVENT_TPC_ASSERT           (1ULL << 0)
 #define HL_NOTIFIER_EVENT_UNDEFINED_OPCODE     (1ULL << 1)
 #define HL_NOTIFIER_EVENT_DEVICE_RESET         (1ULL << 2)
-#define HL_NOTIFIER_EVENT_CS_TIMEOUT            (1ULL << 3)
+#define HL_NOTIFIER_EVENT_CS_TIMEOUT           (1ULL << 3)
+#define HL_NOTIFIER_EVENT_DEVICE_UNAVAILABLE   (1ULL << 4)
 
 /*
  * Various information operations such as: