summaryrefslogtreecommitdiffstats
path: root/drivers/misc/habanalabs/goya/goya.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/misc/habanalabs/goya/goya.c')
-rw-r--r--drivers/misc/habanalabs/goya/goya.c23
1 files changed, 23 insertions, 0 deletions
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index ed566c52ccaa..a40c428fed94 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -4401,6 +4401,8 @@ static const char *_goya_get_event_desc(u16 event_type)
return "THERMAL_ENV_S";
case GOYA_ASYNC_EVENT_ID_FIX_THERMAL_ENV_E:
return "THERMAL_ENV_E";
+ case GOYA_ASYNC_EVENT_PKT_QUEUE_OUT_SYNC:
+ return "QUEUE_OUT_OF_SYNC";
default:
return "N/A";
}
@@ -4483,6 +4485,9 @@ static void goya_get_event_desc(u16 event_type, char *desc, size_t size)
index = event_type - GOYA_ASYNC_EVENT_ID_DMA_BM_CH0;
snprintf(desc, size, _goya_get_event_desc(event_type), index);
break;
+ case GOYA_ASYNC_EVENT_PKT_QUEUE_OUT_SYNC:
+ snprintf(desc, size, _goya_get_event_desc(event_type));
+ break;
default:
snprintf(desc, size, _goya_get_event_desc(event_type));
break;
@@ -4534,6 +4539,15 @@ static void goya_print_mmu_error_info(struct hl_device *hdev)
}
}
+static void goya_print_out_of_sync_info(struct hl_device *hdev,
+ struct cpucp_pkt_sync_err *sync_err)
+{
+ struct hl_hw_queue *q = &hdev->kernel_queues[GOYA_QUEUE_ID_CPU_PQ];
+
+ dev_err(hdev->dev, "Out of sync with FW, FW: pi=%u, ci=%u, LKD: pi=%u, ci=%u\n",
+ sync_err->pi, sync_err->ci, q->pi, atomic_read(&q->ci));
+}
+
static void goya_print_irq_info(struct hl_device *hdev, u16 event_type,
bool razwi)
{
@@ -4754,6 +4768,15 @@ void goya_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entry)
goya_unmask_irq(hdev, event_type);
break;
+ case GOYA_ASYNC_EVENT_PKT_QUEUE_OUT_SYNC:
+ goya_print_irq_info(hdev, event_type, false);
+ goya_print_out_of_sync_info(hdev, &eq_entry->pkt_sync_err);
+ if (hdev->hard_reset_on_fw_events)
+ hl_device_reset(hdev, true, false);
+ else
+ hl_fw_unmask_irq(hdev, event_type);
+ break;
+
default:
dev_err(hdev->dev, "Received invalid H/W interrupt %d\n",
event_type);