net: qed: introduce critical hardware error handler

MCP may signal driver about generic critical failure.
Driver has to collect mdump information (get_retain),
it pushes that to logs and triggers generic notification on
"hardware attention" event.
Signed-off-by: Ariel Elior <ariel.elior@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/qlogic/qed/qed_hsi.h

@@ -12400,6 +12400,13 @@ struct load_rsp_stc {
 #define LOAD_RSP_FLAGS0_DRV_EXISTS      (0x1 << 0)
 };
 
+struct mdump_retain_data_stc {
+	u32 valid;
+	u32 epoch;
+	u32 pf;
+	u32 status;
+};
+
 union drv_union_data {
 	u32 ver_str[MCP_DRV_VER_STR_SIZE_DWORD];
 	struct mcp_mac wol_mac;
@@ -12488,6 +12495,8 @@ struct public_drv_mb {
 #define DRV_MSG_CODE_BIST_TEST			0x001e0000
 #define DRV_MSG_CODE_SET_LED_MODE		0x00200000
 #define DRV_MSG_CODE_RESOURCE_CMD		0x00230000
+/* Send crash dump commands with param[3:0] - opcode */
+#define DRV_MSG_CODE_MDUMP_CMD			0x00250000
 #define DRV_MSG_CODE_GET_TLV_DONE		0x002f0000
 #define DRV_MSG_CODE_GET_ENGINE_CONFIG		0x00370000
 #define DRV_MSG_CODE_GET_PPFID_BITMAP		0x43000000
@@ -12519,6 +12528,21 @@ struct public_drv_mb {
 
 #define RESOURCE_DUMP				0
 
+/* DRV_MSG_CODE_MDUMP_CMD parameters */
+#define MDUMP_DRV_PARAM_OPCODE_MASK             0x0000000f
+#define DRV_MSG_CODE_MDUMP_ACK                  0x01
+#define DRV_MSG_CODE_MDUMP_SET_VALUES           0x02
+#define DRV_MSG_CODE_MDUMP_TRIGGER              0x03
+#define DRV_MSG_CODE_MDUMP_GET_CONFIG           0x04
+#define DRV_MSG_CODE_MDUMP_SET_ENABLE           0x05
+#define DRV_MSG_CODE_MDUMP_CLEAR_LOGS           0x06
+#define DRV_MSG_CODE_MDUMP_GET_RETAIN           0x07
+#define DRV_MSG_CODE_MDUMP_CLR_RETAIN           0x08
+
+#define DRV_MSG_CODE_HW_DUMP_TRIGGER            0x0a
+#define DRV_MSG_CODE_MDUMP_GEN_MDUMP2           0x0b
+#define DRV_MSG_CODE_MDUMP_FREE_MDUMP2          0x0c
+
 #define DRV_MSG_CODE_GET_PF_RDMA_PROTOCOL	0x002b0000
 #define DRV_MSG_CODE_OS_WOL			0x002e0000
 
@@ -12697,6 +12721,8 @@ struct public_drv_mb {
 #define FW_MSG_CODE_DEBUG_NOT_ENABLED		0xb00a0000
 #define FW_MSG_CODE_DEBUG_DATA_SEND_OK		0xb00b0000
 
+#define FW_MSG_CODE_MDUMP_INVALID_CMD		0x00030000
+
 	u32 fw_mb_param;
 #define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_MASK	0xFFFF0000
 #define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_SHIFT	16
@@ -12763,7 +12789,7 @@ enum MFW_DRV_MSG_TYPE {
 	MFW_DRV_MSG_GET_RDMA_STATS,
 	MFW_DRV_MSG_FAILURE_DETECTED,
 	MFW_DRV_MSG_TRANSCEIVER_STATE_CHANGE,
-	MFW_DRV_MSG_BW_UPDATE11,
+	MFW_DRV_MSG_CRITICAL_ERROR_OCCURRED,
 	MFW_DRV_MSG_RESERVED,
 	MFW_DRV_MSG_GET_TLV_REQ,
 	MFW_DRV_MSG_OEM_CFG_UPDATE,

drivers/net/ethernet/qlogic/qed/qed_mcp.c

@@ -1717,6 +1717,116 @@ static void qed_mcp_handle_fan_failure(struct qed_hwfn *p_hwfn,
 			  "Fan failure was detected on the network interface card and it's going to be shut down.\n");
 }
 
+struct qed_mdump_cmd_params {
+	u32 cmd;
+	void *p_data_src;
+	u8 data_src_size;
+	void *p_data_dst;
+	u8 data_dst_size;
+	u32 mcp_resp;
+};
+
+static int
+qed_mcp_mdump_cmd(struct qed_hwfn *p_hwfn,
+		  struct qed_ptt *p_ptt,
+		  struct qed_mdump_cmd_params *p_mdump_cmd_params)
+{
+	struct qed_mcp_mb_params mb_params;
+	int rc;
+
+	memset(&mb_params, 0, sizeof(mb_params));
+	mb_params.cmd = DRV_MSG_CODE_MDUMP_CMD;
+	mb_params.param = p_mdump_cmd_params->cmd;
+	mb_params.p_data_src = p_mdump_cmd_params->p_data_src;
+	mb_params.data_src_size = p_mdump_cmd_params->data_src_size;
+	mb_params.p_data_dst = p_mdump_cmd_params->p_data_dst;
+	mb_params.data_dst_size = p_mdump_cmd_params->data_dst_size;
+	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
+	if (rc)
+		return rc;
+
+	p_mdump_cmd_params->mcp_resp = mb_params.mcp_resp;
+
+	if (p_mdump_cmd_params->mcp_resp == FW_MSG_CODE_MDUMP_INVALID_CMD) {
+		DP_INFO(p_hwfn,
+			"The mdump sub command is unsupported by the MFW [mdump_cmd 0x%x]\n",
+			p_mdump_cmd_params->cmd);
+		rc = -EOPNOTSUPP;
+	} else if (p_mdump_cmd_params->mcp_resp == FW_MSG_CODE_UNSUPPORTED) {
+		DP_INFO(p_hwfn,
+			"The mdump command is not supported by the MFW\n");
+		rc = -EOPNOTSUPP;
+	}
+
+	return rc;
+}
+
+static int qed_mcp_mdump_ack(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	struct qed_mdump_cmd_params mdump_cmd_params;
+
+	memset(&mdump_cmd_params, 0, sizeof(mdump_cmd_params));
+	mdump_cmd_params.cmd = DRV_MSG_CODE_MDUMP_ACK;
+
+	return qed_mcp_mdump_cmd(p_hwfn, p_ptt, &mdump_cmd_params);
+}
+
+int
+qed_mcp_mdump_get_retain(struct qed_hwfn *p_hwfn,
+			 struct qed_ptt *p_ptt,
+			 struct mdump_retain_data_stc *p_mdump_retain)
+{
+	struct qed_mdump_cmd_params mdump_cmd_params;
+	int rc;
+
+	memset(&mdump_cmd_params, 0, sizeof(mdump_cmd_params));
+	mdump_cmd_params.cmd = DRV_MSG_CODE_MDUMP_GET_RETAIN;
+	mdump_cmd_params.p_data_dst = p_mdump_retain;
+	mdump_cmd_params.data_dst_size = sizeof(*p_mdump_retain);
+
+	rc = qed_mcp_mdump_cmd(p_hwfn, p_ptt, &mdump_cmd_params);
+	if (rc)
+		return rc;
+
+	if (mdump_cmd_params.mcp_resp != FW_MSG_CODE_OK) {
+		DP_INFO(p_hwfn,
+			"Failed to get the mdump retained data [mcp_resp 0x%x]\n",
+			mdump_cmd_params.mcp_resp);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void qed_mcp_handle_critical_error(struct qed_hwfn *p_hwfn,
+					  struct qed_ptt *p_ptt)
+{
+	struct mdump_retain_data_stc mdump_retain;
+	int rc;
+
+	/* In CMT mode - no need for more than a single acknowledgment to the
+	 * MFW, and no more than a single notification to the upper driver.
+	 */
+	if (p_hwfn != QED_LEADING_HWFN(p_hwfn->cdev))
+		return;
+
+	rc = qed_mcp_mdump_get_retain(p_hwfn, p_ptt, &mdump_retain);
+	if (rc == 0 && mdump_retain.valid)
+		DP_NOTICE(p_hwfn,
+			  "The MFW notified that a critical error occurred in the device [epoch 0x%08x, pf 0x%x, status 0x%08x]\n",
+			  mdump_retain.epoch,
+			  mdump_retain.pf, mdump_retain.status);
+	else
+		DP_NOTICE(p_hwfn,
+			  "The MFW notified that a critical error occurred in the device\n");
+
+	DP_NOTICE(p_hwfn,
+		  "Acknowledging the notification to not allow the MFW crash dump [driver debug data collection is preferable]\n");
+	qed_mcp_mdump_ack(p_hwfn, p_ptt);
+
+	qed_hw_err_notify(p_hwfn, p_ptt, QED_HW_ERR_HW_ATTN, NULL);
+}
+
 void qed_mcp_read_ufp_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
 	struct public_func shmem_info;
@@ -1866,6 +1976,9 @@ int qed_mcp_handle_events(struct qed_hwfn *p_hwfn,
 		case MFW_DRV_MSG_FAILURE_DETECTED:
 			qed_mcp_handle_fan_failure(p_hwfn, p_ptt);
 			break;
+		case MFW_DRV_MSG_CRITICAL_ERROR_OCCURRED:
+			qed_mcp_handle_critical_error(p_hwfn, p_ptt);
+			break;
 		case MFW_DRV_MSG_GET_TLV_REQ:
 			qed_mfw_tlv_req(p_hwfn);
 			break;

drivers/net/ethernet/qlogic/qed/qed_mcp.h

@@ -1016,6 +1016,19 @@ int __qed_configure_pf_min_bandwidth(struct qed_hwfn *p_hwfn,
 int qed_mcp_mask_parities(struct qed_hwfn *p_hwfn,
 			  struct qed_ptt *p_ptt, u32 mask_parities);
 
+/* @brief - Gets the mdump retained data from the MFW.
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param p_mdump_retain
+ *
+ * @param return 0 upon success.
+ */
+int
+qed_mcp_mdump_get_retain(struct qed_hwfn *p_hwfn,
+			 struct qed_ptt *p_ptt,
+			 struct mdump_retain_data_stc *p_mdump_retain);
+
 /**
  * @brief - Sets the MFW's max value for the given resource
  *