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 <marcin.szycik@linux.intel.com>
Co-developed-by: Sharon Haroni <sharon.haroni@intel.com>
Signed-off-by: Sharon Haroni <sharon.haroni@intel.com>
Co-developed-by: Nicholas Nunley <nicholas.d.nunley@intel.com>
Signed-off-by: Nicholas Nunley <nicholas.d.nunley@intel.com>
Co-developed-by: Brett Creeley <brett.creeley@intel.com>
Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Signed-off-by: Konrad Knitter <konrad.knitter@intel.com>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>

1 files changed, 87 insertions, 0 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 73f5fddf3ee9..dd41a4dcc0b9 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -2517,6 +2517,87 @@ enum ice_aqc_fw_logging_mod {
 	ICE_AQC_FW_LOG_ID_MAX,
 };
 
+enum ice_aqc_health_status_mask {
+	ICE_AQC_HEALTH_STATUS_SET_PF_SPECIFIC_MASK = BIT(0),
+	ICE_AQC_HEALTH_STATUS_SET_ALL_PF_MASK      = BIT(1),
+	ICE_AQC_HEALTH_STATUS_SET_GLOBAL_MASK      = BIT(2),
+};
+
+/* Set Health Status (direct 0xFF20) */
+struct ice_aqc_set_health_status_cfg {
+	u8 event_source;
+	u8 reserved[15];
+};
+
+enum ice_aqc_health_status {
+	ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_STRICT		= 0x101,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_TYPE			= 0x102,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_QUAL			= 0x103,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_COMM			= 0x104,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_CONFLICT			= 0x105,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_NOT_PRESENT		= 0x106,
+	ICE_AQC_HEALTH_STATUS_INFO_MOD_UNDERUTILIZED		= 0x107,
+	ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_LENIENT		= 0x108,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_DIAGNOSTIC_FEATURE	= 0x109,
+	ICE_AQC_HEALTH_STATUS_ERR_INVALID_LINK_CFG		= 0x10B,
+	ICE_AQC_HEALTH_STATUS_ERR_PORT_ACCESS			= 0x10C,
+	ICE_AQC_HEALTH_STATUS_ERR_PORT_UNREACHABLE		= 0x10D,
+	ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_MOD_LIMITED	= 0x10F,
+	ICE_AQC_HEALTH_STATUS_ERR_PARALLEL_FAULT		= 0x110,
+	ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_PHY_LIMITED	= 0x111,
+	ICE_AQC_HEALTH_STATUS_ERR_NETLIST_TOPO			= 0x112,
+	ICE_AQC_HEALTH_STATUS_ERR_NETLIST			= 0x113,
+	ICE_AQC_HEALTH_STATUS_ERR_TOPO_CONFLICT			= 0x114,
+	ICE_AQC_HEALTH_STATUS_ERR_LINK_HW_ACCESS		= 0x115,
+	ICE_AQC_HEALTH_STATUS_ERR_LINK_RUNTIME			= 0x116,
+	ICE_AQC_HEALTH_STATUS_ERR_DNL_INIT			= 0x117,
+	ICE_AQC_HEALTH_STATUS_ERR_PHY_NVM_PROG			= 0x120,
+	ICE_AQC_HEALTH_STATUS_ERR_PHY_FW_LOAD			= 0x121,
+	ICE_AQC_HEALTH_STATUS_INFO_RECOVERY			= 0x500,
+	ICE_AQC_HEALTH_STATUS_ERR_FLASH_ACCESS			= 0x501,
+	ICE_AQC_HEALTH_STATUS_ERR_NVM_AUTH			= 0x502,
+	ICE_AQC_HEALTH_STATUS_ERR_OROM_AUTH			= 0x503,
+	ICE_AQC_HEALTH_STATUS_ERR_DDP_AUTH			= 0x504,
+	ICE_AQC_HEALTH_STATUS_ERR_NVM_COMPAT			= 0x505,
+	ICE_AQC_HEALTH_STATUS_ERR_OROM_COMPAT			= 0x506,
+	ICE_AQC_HEALTH_STATUS_ERR_NVM_SEC_VIOLATION		= 0x507,
+	ICE_AQC_HEALTH_STATUS_ERR_OROM_SEC_VIOLATION		= 0x508,
+	ICE_AQC_HEALTH_STATUS_ERR_DCB_MIB			= 0x509,
+	ICE_AQC_HEALTH_STATUS_ERR_MNG_TIMEOUT			= 0x50A,
+	ICE_AQC_HEALTH_STATUS_ERR_BMC_RESET			= 0x50B,
+	ICE_AQC_HEALTH_STATUS_ERR_LAST_MNG_FAIL			= 0x50C,
+	ICE_AQC_HEALTH_STATUS_ERR_RESOURCE_ALLOC_FAIL		= 0x50D,
+	ICE_AQC_HEALTH_STATUS_ERR_FW_LOOP			= 0x1000,
+	ICE_AQC_HEALTH_STATUS_ERR_FW_PFR_FAIL			= 0x1001,
+	ICE_AQC_HEALTH_STATUS_ERR_LAST_FAIL_AQ			= 0x1002,
+};
+
+/* Get Health Status (indirect 0xFF22) */
+struct ice_aqc_get_health_status {
+	__le16 health_status_count;
+	u8 reserved[6];
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+enum ice_aqc_health_status_scope {
+	ICE_AQC_HEALTH_STATUS_PF	= 0x1,
+	ICE_AQC_HEALTH_STATUS_PORT	= 0x2,
+	ICE_AQC_HEALTH_STATUS_GLOBAL	= 0x3,
+};
+
+#define ICE_AQC_HEALTH_STATUS_UNDEFINED_DATA	0xDEADBEEF
+
+/* Get Health Status event buffer entry (0xFF22),
+ * repeated per reported health status.
+ */
+struct ice_aqc_health_status_elem {
+	__le16 health_status_code;
+	__le16 event_source;
+	__le32 internal_data1;
+	__le32 internal_data2;
+};
+
 /* Set FW Logging configuration (indirect 0xFF30)
  * Register for FW Logging (indirect 0xFF31)
  * Query FW Logging (indirect 0xFF32)
@@ -2657,6 +2738,8 @@ struct ice_aq_desc {
 		struct ice_aqc_get_link_status get_link_status;
 		struct ice_aqc_event_lan_overflow lan_overflow;
 		struct ice_aqc_get_link_topo get_link_topo;
+		struct ice_aqc_set_health_status_cfg set_health_status_cfg;
+		struct ice_aqc_get_health_status get_health_status;
 		struct ice_aqc_dnl_call_command dnl_call;
 		struct ice_aqc_i2c read_write_i2c;
 		struct ice_aqc_read_i2c_resp read_i2c_resp;
@@ -2859,6 +2942,10 @@ enum ice_adminq_opc {
 	/* Standalone Commands/Events */
 	ice_aqc_opc_event_lan_overflow			= 0x1001,
 
+	/* System Diagnostic commands */
+	ice_aqc_opc_set_health_status_cfg		= 0xFF20,
+	ice_aqc_opc_get_health_status			= 0xFF22,
+
 	/* FW Logging Commands */
 	ice_aqc_opc_fw_logs_config			= 0xFF30,
 	ice_aqc_opc_fw_logs_register			= 0xFF31,