habanalabs/gaudi: handle axi errors from NIC engines

Various AXI errors can occur in the NIC engines and are reported to
the driver by the f/w. Add code to print the errors and ack them to
the f/w.

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 a60c0e2..95201d9 100644 (file)
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -7665,6 +7665,48 @@ static void gaudi_print_fw_alive_info(struct hl_device *hdev,
                fw_alive->thread_id, fw_alive->uptime_seconds);
 }
 
+static void gaudi_print_nic_axi_irq_info(struct hl_device *hdev, u16 event_type,
+                                               void *data)
+{
+       char desc[64] = "", *type;
+       struct eq_nic_sei_event *eq_nic_sei = data;
+       u16 nic_id = event_type - GAUDI_EVENT_NIC_SEI_0;
+
+       switch (eq_nic_sei->axi_error_cause) {
+       case RXB:
+               type = "RXB";
+               break;
+       case RXE:
+               type = "RXE";
+               break;
+       case TXS:
+               type = "TXS";
+               break;
+       case TXE:
+               type = "TXE";
+               break;
+       case QPC_RESP:
+               type = "QPC_RESP";
+               break;
+       case NON_AXI_ERR:
+               type = "NON_AXI_ERR";
+               break;
+       case TMR:
+               type = "TMR";
+               break;
+       default:
+               dev_err(hdev->dev, "unknown NIC AXI cause %d\n",
+                       eq_nic_sei->axi_error_cause);
+               type = "N/A";
+               break;
+       }
+
+       snprintf(desc, sizeof(desc), "NIC%d_%s%d", nic_id, type,
+                       eq_nic_sei->id);
+       dev_err_ratelimited(hdev->dev, "Received H/W interrupt %d [\"%s\"]\n",
+               event_type, desc);
+}
+
 static int gaudi_non_hard_reset_late_init(struct hl_device *hdev)
 {
        /* GAUDI doesn't support any reset except hard-reset */
@@ -7898,6 +7940,7 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
                                struct hl_eq_entry *eq_entry)
 {
        struct gaudi_device *gaudi = hdev->asic_specific;
+       u64 data = le64_to_cpu(eq_entry->data[0]);
        u32 ctl = le32_to_cpu(eq_entry->hdr.ctl);
        u32 fw_fatal_err_flag = 0;
        u16 event_type = ((ctl & EQ_CTL_EVENT_TYPE_MASK)
@@ -8095,6 +8138,11 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
                hl_fw_unmask_irq(hdev, event_type);
                break;
 
+       case GAUDI_EVENT_NIC_SEI_0 ... GAUDI_EVENT_NIC_SEI_4:
+               gaudi_print_nic_axi_irq_info(hdev, event_type, &data);
+               hl_fw_unmask_irq(hdev, event_type);
+               break;
+
        case GAUDI_EVENT_DMA_IF_SEI_0 ... GAUDI_EVENT_DMA_IF_SEI_3:
                gaudi_print_irq_info(hdev, event_type, false);
                gaudi_print_sm_sei_info(hdev, event_type,