ice: add fw and port health reporters

Firmware generates events for global events or port specific events.

Driver shall subscribe for health status events from firmware on supported
FW versions >= 1.7.6.
Driver shall expose those under specific health reporter, two new
reporters are introduced:
- FW health reporter shall represent global events (problems with the
image, recovery mode);
- Port health reporter shall represent port-specific events (module
failure).

Firmware only reports problems when those are detected, it does not store
active fault list.
Driver will hold only last global and last port-specific event.
Driver will report all events via devlink health report,
so in case of multiple events of the same source they can be reviewed
using devlink autodump feature.

$ devlink health

pci/0000:b1:00.3:
  reporter fw
    state healthy error 0 recover 0 auto_dump true
  reporter port
    state error error 1 recover 0 last_dump_date 2024-03-17
	last_dump_time 09:29:29 auto_dump true

$ devlink health diagnose pci/0000:b1:00.3 reporter port

  Syndrome: 262
  Description: Module is not present.
  Possible Solution: Check that the module is inserted correctly.
  Port Number: 0

Tested on Intel Corporation Ethernet Controller E810-C for SFP

Reviewed-by: Marcin Szycik <[email protected]>
Co-developed-by: Sharon Haroni <[email protected]>
Signed-off-by: Sharon Haroni <[email protected]>
Co-developed-by: Nicholas Nunley <[email protected]>
Signed-off-by: Nicholas Nunley <[email protected]>
Co-developed-by: Brett Creeley <[email protected]>
Signed-off-by: Brett Creeley <[email protected]>
Signed-off-by: Konrad Knitter <[email protected]>
Tested-by: Rinitha S <[email protected]> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <[email protected]>

Author: konradknitter

drivers/net/ethernet/intel/ice/devlink/health.c

@@ -1,12 +1,270 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2024, Intel Corporation. */
 
-#include "health.h"
 #include "ice.h"
+#include "ice_adminq_cmd.h" /* for enum ice_aqc_health_status_elem */
+#include "health.h"
 
 #define ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, obj, name) \
 	devlink_fmsg_put(fmsg, #name, (obj)->name)
 
+#define ICE_HEALTH_STATUS_DATA_SIZE 2
+
+struct ice_health_status {
+	enum ice_aqc_health_status code;
+	const char *description;
+	const char *solution;
+	const char *data_label[ICE_HEALTH_STATUS_DATA_SIZE];
+};
+
+/*
+ * In addition to the health status codes provided below, the firmware might
+ * generate Health Status Codes that are not pertinent to the end-user.
+ * For instance, Health Code 0x1002 is triggered when the command fails.
+ * Such codes should be disregarded by the end-user.
+ * The below lookup requires to be sorted by code.
+ */
+
+static const char *const ice_common_port_solutions =
+	"Check your cable connection. Change or replace the module or cable. Manually set speed and duplex.";
+static const char *const ice_port_number_label = "Port Number";
+static const char *const ice_update_nvm_solution = "Update to the latest NVM image.";
+
+static const struct ice_health_status ice_health_status_lookup[] = {
+	{ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_STRICT, "An unsupported module was detected.",
+		ice_common_port_solutions, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_MOD_TYPE, "Module type is not supported.",
+		"Change or replace the module or cable.", {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_MOD_QUAL, "Module is not qualified.",
+		ice_common_port_solutions, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_MOD_COMM,
+		"Device cannot communicate with the module.",
+		"Check your cable connection. Change or replace the module or cable. Manually set speed and duplex.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_MOD_CONFLICT, "Unresolved module conflict.",
+		"Manually set speed/duplex or change the port option. If the problem persists, use a cable/module that is found in the supported modules and cables list for this device.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_MOD_NOT_PRESENT, "Module is not present.",
+		"Check that the module is inserted correctly. If the problem persists, use a cable/module that is found in the supported modules and cables list for this device.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_INFO_MOD_UNDERUTILIZED, "Underutilized module.",
+		"Change or replace the module or cable. Change the port option.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_LENIENT, "An unsupported module was detected.",
+		ice_common_port_solutions, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_INVALID_LINK_CFG, "Invalid link configuration.",
+		NULL, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_PORT_ACCESS, "Port hardware access error.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_PORT_UNREACHABLE, "A port is unreachable.",
+		"Change the port option. Update to the latest NVM image."},
+	{ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_MOD_LIMITED, "Port speed is limited due to module.",
+		"Change the module or configure the port option to match the current module speed. Change the port option.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_PARALLEL_FAULT,
+		"All configured link modes were attempted but failed to establish link. The device will restart the process to establish link.",
+		"Check link partner connection and configuration.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_PHY_LIMITED,
+		"Port speed is limited by PHY capabilities.",
+		"Change the module to align to port option.", {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_NETLIST_TOPO, "LOM topology netlist is corrupted.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_NETLIST, "Unrecoverable netlist error.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_TOPO_CONFLICT, "Port topology conflict.",
+		"Change the port option. Update to the latest NVM image."},
+	{ICE_AQC_HEALTH_STATUS_ERR_LINK_HW_ACCESS, "Unrecoverable hardware access error.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_LINK_RUNTIME, "Unrecoverable runtime error.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_DNL_INIT, "Link management engine failed to initialize.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_PHY_FW_LOAD,
+		"Failed to load the firmware image in the external PHY.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_INFO_RECOVERY, "The device is in firmware recovery mode.",
+		ice_update_nvm_solution, {"Extended Error"}},
+	{ICE_AQC_HEALTH_STATUS_ERR_FLASH_ACCESS, "The flash chip cannot be accessed.",
+		"If issue persists, call customer support.", {"Access Type"}},
+	{ICE_AQC_HEALTH_STATUS_ERR_NVM_AUTH, "NVM authentication failed.",
+		ice_update_nvm_solution},
+	{ICE_AQC_HEALTH_STATUS_ERR_OROM_AUTH, "Option ROM authentication failed.",
+		ice_update_nvm_solution},
+	{ICE_AQC_HEALTH_STATUS_ERR_DDP_AUTH, "DDP package authentication failed.",
+		"Update to latest base driver and DDP package."},
+	{ICE_AQC_HEALTH_STATUS_ERR_NVM_COMPAT, "NVM image is incompatible.",
+		ice_update_nvm_solution},
+	{ICE_AQC_HEALTH_STATUS_ERR_OROM_COMPAT, "Option ROM is incompatible.",
+		ice_update_nvm_solution, {"Expected PCI Device ID", "Expected Module ID"}},
+	{ICE_AQC_HEALTH_STATUS_ERR_DCB_MIB,
+		"Supplied MIB file is invalid. DCB reverted to default configuration.",
+		"Disable FW-LLDP and check DCBx system configuration.",
+		{ice_port_number_label, "MIB ID"}},
+};
+
+static int ice_health_status_lookup_compare(const void *a, const void *b)
+{
+	return ((struct ice_health_status *)a)->code - ((struct ice_health_status *)b)->code;
+}
+
+static const struct ice_health_status *ice_get_health_status(u16 code)
+{
+	struct ice_health_status key = { .code = code };
+
+	return bsearch(&key, ice_health_status_lookup, ARRAY_SIZE(ice_health_status_lookup),
+		       sizeof(struct ice_health_status), ice_health_status_lookup_compare);
+}
+
+static void ice_describe_status_code(struct devlink_fmsg *fmsg,
+				     struct ice_aqc_health_status_elem *hse)
+{
+	static const char *const aux_label[] = { "Aux Data 1", "Aux Data 2" };
+	const struct ice_health_status *health_code;
+	u32 internal_data[2];
+	u16 status_code;
+
+	status_code = le16_to_cpu(hse->health_status_code);
+
+	devlink_fmsg_put(fmsg, "Syndrome", status_code);
+	if (status_code) {
+		internal_data[0] = le32_to_cpu(hse->internal_data1);
+		internal_data[1] = le32_to_cpu(hse->internal_data2);
+
+		health_code = ice_get_health_status(status_code);
+		if (!health_code)
+			return;
+
+		devlink_fmsg_string_pair_put(fmsg, "Description", health_code->description);
+		if (health_code->solution)
+			devlink_fmsg_string_pair_put(fmsg, "Possible Solution",
+						     health_code->solution);
+
+		for (size_t i = 0; i < ICE_HEALTH_STATUS_DATA_SIZE; i++) {
+			if (internal_data[i] != ICE_AQC_HEALTH_STATUS_UNDEFINED_DATA)
+				devlink_fmsg_u32_pair_put(fmsg,
+							  health_code->data_label[i] ?
+							  health_code->data_label[i] :
+							  aux_label[i],
+							  internal_data[i]);
+		}
+	}
+}
+
+static int
+ice_port_reporter_diagnose(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg,
+			   struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = devlink_health_reporter_priv(reporter);
+
+	ice_describe_status_code(fmsg, &pf->health_reporters.port_status);
+	return 0;
+}
+
+static int
+ice_port_reporter_dump(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg,
+		       void *priv_ctx, struct netlink_ext_ack __always_unused *extack)
+{
+	struct ice_pf *pf = devlink_health_reporter_priv(reporter);
+
+	ice_describe_status_code(fmsg, &pf->health_reporters.port_status);
+	return 0;
+}
+
+static int
+ice_fw_reporter_diagnose(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg,
+			 struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = devlink_health_reporter_priv(reporter);
+
+	ice_describe_status_code(fmsg, &pf->health_reporters.fw_status);
+	return 0;
+}
+
+static int
+ice_fw_reporter_dump(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg,
+		     void *priv_ctx, struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = devlink_health_reporter_priv(reporter);
+
+	ice_describe_status_code(fmsg, &pf->health_reporters.fw_status);
+	return 0;
+}
+
+static void ice_config_health_events(struct ice_pf *pf, bool enable)
+{
+	u8 enable_bits = 0;
+	int ret;
+
+	if (enable)
+		enable_bits = ICE_AQC_HEALTH_STATUS_SET_PF_SPECIFIC_MASK |
+			      ICE_AQC_HEALTH_STATUS_SET_GLOBAL_MASK;
+
+	ret = ice_aq_set_health_status_cfg(&pf->hw, enable_bits);
+	if (ret)
+		dev_err(ice_pf_to_dev(pf), "Failed to %s firmware health events, err %d aq_err %s\n",
+			str_enable_disable(enable), ret,
+			ice_aq_str(pf->hw.adminq.sq_last_status));
+}
+
+/**
+ * ice_process_health_status_event - Process the health status event from FW
+ * @pf: pointer to the PF structure
+ * @event: event structure containing the Health Status Event opcode
+ *
+ * Decode the Health Status Events and print the associated messages
+ */
+void ice_process_health_status_event(struct ice_pf *pf, struct ice_rq_event_info *event)
+{
+	const struct ice_aqc_health_status_elem *health_info;
+	u16 count;
+
+	health_info = (struct ice_aqc_health_status_elem *)event->msg_buf;
+	count = le16_to_cpu(event->desc.params.get_health_status.health_status_count);
+
+	if (count > (event->buf_len / sizeof(*health_info))) {
+		dev_err(ice_pf_to_dev(pf), "Received a health status event with invalid element count\n");
+		return;
+	}
+
+	for (size_t i = 0; i < count; i++) {
+		const struct ice_health_status *health_code;
+		u16 status_code;
+
+		status_code = le16_to_cpu(health_info->health_status_code);
+		health_code = ice_get_health_status(status_code);
+
+		if (health_code) {
+			switch (le16_to_cpu(health_info->event_source)) {
+			case ICE_AQC_HEALTH_STATUS_GLOBAL:
+				pf->health_reporters.fw_status = *health_info;
+				devlink_health_report(pf->health_reporters.fw,
+						      "FW syndrome reported", NULL);
+				break;
+			case ICE_AQC_HEALTH_STATUS_PF:
+			case ICE_AQC_HEALTH_STATUS_PORT:
+				pf->health_reporters.port_status = *health_info;
+				devlink_health_report(pf->health_reporters.port,
+						      "Port syndrome reported", NULL);
+				break;
+			default:
+				dev_err(ice_pf_to_dev(pf), "Health code with unknown source\n");
+			}
+		} else {
+			u32 data1, data2;
+			u16 source;
+
+			source = le16_to_cpu(health_info->event_source);
+			data1 = le32_to_cpu(health_info->internal_data1);
+			data2 = le32_to_cpu(health_info->internal_data2);
+			dev_dbg(ice_pf_to_dev(pf),
+				"Received internal health status code 0x%08x, source: 0x%08x, data1: 0x%08x, data2: 0x%08x",
+				status_code, source, data1, data2);
+		}
+		health_info++;
+	}
+}
+
 /**
  * ice_devlink_health_report - boilerplate to call given @reporter
  *
@@ -203,14 +461,26 @@ ice_init_devlink_rep(struct ice_pf *pf,
 	return rep;
 }
 
-#define ICE_DEFINE_HEALTH_REPORTER_OPS(_name) \
-	static const struct devlink_health_reporter_ops ice_ ## _name ## _reporter_ops = { \
+#define ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field) \
+	._field = ice_##_name##_reporter_##_field,
+
+#define ICE_DEFINE_HEALTH_REPORTER_OPS_1(_name, _field1) \
+	static const struct devlink_health_reporter_ops ice_##_name##_reporter_ops = { \
 	.name = #_name, \
-	.dump = ice_ ## _name ## _reporter_dump, \
-}
+	ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field1) \
+	}
+
+#define ICE_DEFINE_HEALTH_REPORTER_OPS_2(_name, _field1, _field2) \
+	static const struct devlink_health_reporter_ops ice_##_name##_reporter_ops = { \
+	.name = #_name, \
+	ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field1) \
+	ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field2) \
+	}
 
-ICE_DEFINE_HEALTH_REPORTER_OPS(mdd);
-ICE_DEFINE_HEALTH_REPORTER_OPS(tx_hang);
+ICE_DEFINE_HEALTH_REPORTER_OPS_1(mdd, dump);
+ICE_DEFINE_HEALTH_REPORTER_OPS_1(tx_hang, dump);
+ICE_DEFINE_HEALTH_REPORTER_OPS_2(fw, dump, diagnose);
+ICE_DEFINE_HEALTH_REPORTER_OPS_2(port, dump, diagnose);
 
 /**
  * ice_health_init - allocate and init all ice devlink health reporters and
@@ -224,6 +494,12 @@ void ice_health_init(struct ice_pf *pf)
 
 	reps->mdd = ice_init_devlink_rep(pf, &ice_mdd_reporter_ops);
 	reps->tx_hang = ice_init_devlink_rep(pf, &ice_tx_hang_reporter_ops);
+
+	if (ice_is_fw_health_report_supported(&pf->hw)) {
+		reps->fw = ice_init_devlink_rep(pf, &ice_fw_reporter_ops);
+		reps->port = ice_init_devlink_rep(pf, &ice_port_reporter_ops);
+		ice_config_health_events(pf, true);
+	}
 }
 
 /**
@@ -246,6 +522,11 @@ void ice_health_deinit(struct ice_pf *pf)
 {
 	ice_deinit_devl_reporter(pf->health_reporters.mdd);
 	ice_deinit_devl_reporter(pf->health_reporters.tx_hang);
+	if (ice_is_fw_health_report_supported(&pf->hw)) {
+		ice_deinit_devl_reporter(pf->health_reporters.fw);
+		ice_deinit_devl_reporter(pf->health_reporters.port);
+		ice_config_health_events(pf, false);
+	}
 }
 
 static

drivers/net/ethernet/intel/ice/devlink/health.h

@@ -13,8 +13,10 @@
  * devlink health mechanism for ice driver.
  */
 
+struct ice_aqc_health_status_elem;
 struct ice_pf;
 struct ice_tx_ring;
+struct ice_rq_event_info;
 
 enum ice_mdd_src {
 	ICE_MDD_SRC_TX_PQM,
@@ -25,26 +27,37 @@ enum ice_mdd_src {
 
 /**
  * struct ice_health - stores ice devlink health reporters and accompanied data
- * @tx_hang: devlink health reporter for tx_hang event
+ * @fw: devlink health reporter for FW Health Status events
  * @mdd: devlink health reporter for MDD detection event
+ * @port: devlink health reporter for Port Health Status events
+ * @tx_hang: devlink health reporter for tx_hang event
  * @tx_hang_buf: pre-allocated place to put info for Tx hang reporter from
  *               non-sleeping context
  * @tx_ring: ring that the hang occurred on
  * @head: descriptor head
  * @intr: interrupt register value
  * @vsi_num: VSI owning the queue that the hang occurred on
+ * @fw_status: buffer for last received FW Status event
+ * @port_status: buffer for last received Port Status event
  */
 struct ice_health {
+	struct devlink_health_reporter *fw;
 	struct devlink_health_reporter *mdd;
+	struct devlink_health_reporter *port;
 	struct devlink_health_reporter *tx_hang;
 	struct_group_tagged(ice_health_tx_hang_buf, tx_hang_buf,
 		struct ice_tx_ring *tx_ring;
 		u32 head;
 		u32 intr;
 		u16 vsi_num;
 	);
+	struct ice_aqc_health_status_elem fw_status;
+	struct ice_aqc_health_status_elem port_status;
 };
 
+void ice_process_health_status_event(struct ice_pf *pf,
+				     struct ice_rq_event_info *event);
+
 void ice_health_init(struct ice_pf *pf);
 void ice_health_deinit(struct ice_pf *pf);
 void ice_health_clear(struct ice_pf *pf);