habanalabs/gaudi: print sync manager SEI interrupt info

Driver must print sync manager SEI information upon receiving
interrupt from FW.

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 0d2edb2..d9f1b64 100644 (file)
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -225,6 +225,12 @@ gaudi_qman_arb_error_cause[GAUDI_NUM_OF_QM_ARB_ERR_CAUSE] = {
        "MSG AXI LBW returned with error"
 };
 
+enum gaudi_sm_sei_cause {
+       GAUDI_SM_SEI_SO_OVERFLOW,
+       GAUDI_SM_SEI_LBW_4B_UNALIGNED,
+       GAUDI_SM_SEI_AXI_RESPONSE_ERR
+};
+
 static enum hl_queue_type gaudi_queue_type[GAUDI_QUEUE_ID_SIZE] = {
        QUEUE_TYPE_EXT, /* GAUDI_QUEUE_ID_DMA_0_0 */
        QUEUE_TYPE_EXT, /* GAUDI_QUEUE_ID_DMA_0_1 */
@@ -6846,6 +6852,34 @@ static void gaudi_handle_qman_err_generic(struct hl_device *hdev,
        }
 }
 
+static void gaudi_print_sm_sei_info(struct hl_device *hdev, u16 event_type,
+               struct hl_eq_sm_sei_data *sei_data)
+{
+       u32 index = event_type - GAUDI_EVENT_DMA_IF_SEI_0;
+
+       switch (sei_data->sei_cause) {
+       case GAUDI_SM_SEI_SO_OVERFLOW:
+               dev_err(hdev->dev,
+                       "SM %u SEI Error: SO %u overflow/underflow",
+                       index, le16_to_cpu(sei_data->sei_log));
+               break;
+       case GAUDI_SM_SEI_LBW_4B_UNALIGNED:
+               dev_err(hdev->dev,
+                       "SM %u SEI Error: Unaligned 4B LBW access, monitor agent address low - %#x",
+                       index, le16_to_cpu(sei_data->sei_log));
+               break;
+       case GAUDI_SM_SEI_AXI_RESPONSE_ERR:
+               dev_err(hdev->dev,
+                       "SM %u SEI Error: AXI ID %u response error",
+                       index, le16_to_cpu(sei_data->sei_log));
+               break;
+       default:
+               dev_err(hdev->dev, "Unknown SM SEI cause %u",
+                               le16_to_cpu(sei_data->sei_log));
+               break;
+       }
+}
+
 static void gaudi_handle_ecc_event(struct hl_device *hdev, u16 event_type,
                struct hl_eq_ecc_data *ecc_data)
 {
@@ -7469,6 +7503,13 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
                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,
+                                       &eq_entry->sm_sei_data);
+               hl_fw_unmask_irq(hdev, event_type);
+               break;
+
        case GAUDI_EVENT_FIX_POWER_ENV_S ... GAUDI_EVENT_FIX_THERMAL_ENV_E:
                gaudi_print_clk_change_info(hdev, event_type);
                hl_fw_unmask_irq(hdev, event_type);

diff --git a/drivers/misc/habanalabs/include/common/cpucp_if.h b/drivers/misc/habanalabs/include/common/cpucp_if.h
index 00bd9b3..d75d107 100644 (file)
--- a/drivers/misc/habanalabs/include/common/cpucp_if.h
+++ b/drivers/misc/habanalabs/include/common/cpucp_if.h
@@ -58,11 +58,18 @@ struct hl_eq_ecc_data {
        __u8 pad[7];
 };
 
+struct hl_eq_sm_sei_data {
+       __le16 sei_log;
+       __u8 sei_cause;
+       __u8 pad[5];
+};
+
 struct hl_eq_entry {
        struct hl_eq_header hdr;
        union {
                struct hl_eq_ecc_data ecc_data;
                struct hl_eq_hbm_ecc_data hbm_ecc_data;
+               struct hl_eq_sm_sei_data sm_sei_data;
                __le64 data[7];
        };
 };

diff --git a/drivers/misc/habanalabs/include/gaudi/gaudi_async_events.h b/drivers/misc/habanalabs/include/gaudi/gaudi_async_events.h
index 9ccba84..49335e8 100644 (file)
--- a/drivers/misc/habanalabs/include/gaudi/gaudi_async_events.h
+++ b/drivers/misc/habanalabs/include/gaudi/gaudi_async_events.h
@@ -212,6 +212,10 @@ enum gaudi_async_event_id {
        GAUDI_EVENT_NIC_SEI_2 = 266,
        GAUDI_EVENT_NIC_SEI_3 = 267,
        GAUDI_EVENT_NIC_SEI_4 = 268,
+       GAUDI_EVENT_DMA_IF_SEI_0 = 277,
+       GAUDI_EVENT_DMA_IF_SEI_1 = 278,
+       GAUDI_EVENT_DMA_IF_SEI_2 = 279,
+       GAUDI_EVENT_DMA_IF_SEI_3 = 280,
        GAUDI_EVENT_PCIE_FLR = 290,
        GAUDI_EVENT_TPC0_BMON_SPMU = 300,
        GAUDI_EVENT_TPC0_KRN_ERR = 301,