net: qed: adding hw_err states and handling

Here we introduce qed device error tracking flags and error types.

qed_hw_err_notify is an entrace point to report errors.
It'll notify higher level drivers (qede/qedr/etc) to handle and recover
the error.

List of posible errors comes from hardware interfaces, but could be
extended in future.
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.h

@@ -1020,6 +1020,8 @@ u32 qed_unzip_data(struct qed_hwfn *p_hwfn,
 		   u32 input_len, u8 *input_buf,
 		   u32 max_size, u8 *unzip_buf);
 void qed_schedule_recovery_handler(struct qed_hwfn *p_hwfn);
+void qed_hw_error_occurred(struct qed_hwfn *p_hwfn,
+			   enum qed_hw_err_type err_type);
 void qed_get_protocol_stats(struct qed_dev *cdev,
 			    enum qed_mcp_protocol_type type,
 			    union qed_mcp_protocol_stats *stats);

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

@@ -837,6 +837,38 @@ int qed_dmae_host2host(struct qed_hwfn *p_hwfn,
 	return rc;
 }
 
+void qed_hw_err_notify(struct qed_hwfn *p_hwfn,
+		       struct qed_ptt *p_ptt,
+		       enum qed_hw_err_type err_type, char *fmt, ...)
+{
+	char buf[QED_HW_ERR_MAX_STR_SIZE];
+	va_list vl;
+	int len;
+
+	if (fmt) {
+		va_start(vl, fmt);
+		len = vsnprintf(buf, QED_HW_ERR_MAX_STR_SIZE, fmt, vl);
+		va_end(vl);
+
+		if (len > QED_HW_ERR_MAX_STR_SIZE - 1)
+			len = QED_HW_ERR_MAX_STR_SIZE - 1;
+
+		DP_NOTICE(p_hwfn, "%s", buf);
+	}
+
+	/* Fan failure cannot be masked by handling of another HW error */
+	if (p_hwfn->cdev->recov_in_prog &&
+	    err_type != QED_HW_ERR_FAN_FAIL) {
+		DP_VERBOSE(p_hwfn,
+			   NETIF_MSG_DRV,
+			   "Recovery is in progress. Avoid notifying about HW error %d.\n",
+			   err_type);
+		return;
+	}
+
+	qed_hw_error_occurred(p_hwfn, err_type);
+}
+
 int qed_dmae_sanity(struct qed_hwfn *p_hwfn,
 		    struct qed_ptt *p_ptt, const char *phase)
 {

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

@@ -315,4 +315,19 @@ int qed_init_fw_data(struct qed_dev *cdev,
 int qed_dmae_sanity(struct qed_hwfn *p_hwfn,
 		    struct qed_ptt *p_ptt, const char *phase);
 
+#define QED_HW_ERR_MAX_STR_SIZE 256
+
+/**
+ * @brief qed_hw_err_notify - Notify upper layer driver and management FW
+ *	about a HW error.
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param err_type
+ * @param fmt - debug data buffer to send to the MFW
+ * @param ... - buffer format args
+ */
+void qed_hw_err_notify(struct qed_hwfn *p_hwfn,
+		       struct qed_ptt *p_ptt,
+		       enum qed_hw_err_type err_type, char *fmt, ...);
 #endif

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

@@ -2468,6 +2468,35 @@ void qed_schedule_recovery_handler(struct qed_hwfn *p_hwfn)
 		ops->schedule_recovery_handler(cookie);
 }
 
+char *qed_hw_err_type_descr[] = {
+	[QED_HW_ERR_FAN_FAIL]		= "Fan Failure",
+	[QED_HW_ERR_MFW_RESP_FAIL]	= "MFW Response Failure",
+	[QED_HW_ERR_HW_ATTN]		= "HW Attention",
+	[QED_HW_ERR_DMAE_FAIL]		= "DMAE Failure",
+	[QED_HW_ERR_RAMROD_FAIL]	= "Ramrod Failure",
+	[QED_HW_ERR_FW_ASSERT]		= "FW Assertion",
+	[QED_HW_ERR_LAST]		= "Unknown",
+};
+
+void qed_hw_error_occurred(struct qed_hwfn *p_hwfn,
+			   enum qed_hw_err_type err_type)
+{
+	struct qed_common_cb_ops *ops = p_hwfn->cdev->protocol_ops.common;
+	void *cookie = p_hwfn->cdev->ops_cookie;
+	char *err_str;
+
+	if (err_type > QED_HW_ERR_LAST)
+		err_type = QED_HW_ERR_LAST;
+	err_str = qed_hw_err_type_descr[err_type];
+
+	DP_NOTICE(p_hwfn, "HW error occurred [%s]\n", err_str);
+
+	/* Call the HW error handler of the protocol driver
+	 */
+	if (ops && ops->schedule_hw_err_handler)
+		ops->schedule_hw_err_handler(cookie, err_type);
+}
+
 static int qed_set_coalesce(struct qed_dev *cdev, u16 rx_coal, u16 tx_coal,
 			    void *handle)
 {

include/linux/qed/qed_if.h

@@ -607,6 +607,16 @@ struct qed_sb_info {
 	struct qed_dev *cdev;
 };
 
+enum qed_hw_err_type {
+	QED_HW_ERR_FAN_FAIL,
+	QED_HW_ERR_MFW_RESP_FAIL,
+	QED_HW_ERR_HW_ATTN,
+	QED_HW_ERR_DMAE_FAIL,
+	QED_HW_ERR_RAMROD_FAIL,
+	QED_HW_ERR_FW_ASSERT,
+	QED_HW_ERR_LAST,
+};
+
 enum qed_dev_type {
 	QED_DEV_TYPE_BB,
 	QED_DEV_TYPE_AH,
@@ -814,6 +824,8 @@ struct qed_common_cb_ops {
 	void	(*link_update)(void			*dev,
 			       struct qed_link_output	*link);
 	void (*schedule_recovery_handler)(void *dev);
+	void (*schedule_hw_err_handler)(void *dev,
+					enum qed_hw_err_type err_type);
 	void	(*dcbx_aen)(void *dev, struct qed_dcbx_get *get, u32 mib_type);
 	void (*get_generic_tlv_data)(void *dev, struct qed_generic_tlvs *data);
 	void (*get_protocol_tlv_data)(void *dev, void *data);