Merge branch 'mlxsw-Introduce-fw_fatal-health-reporter-and-test-cmd-to

-trigger-test-event'

Ido Schimmel says:

====================
mlxsw: Introduce fw_fatal health reporter and test cmd to trigger test event

Jiri says:

This patch set introduces a health reporter for mlxsw that reports FW
fatal events. Alongside that, it introduces a test command that is used
to trigger a dummy FW fatal event by user:

$ sudo devlink health test pci/0000:03:00.0 reporter fw_fatal

$ devlink health
pci/0000:03:00.0:
  reporter fw_fatal
    state error error 1 recover 0 last_dump_date 2020-07-27 last_dump_time 16:33:27 auto_dump true

$ sudo devlink health dump show pci/0000:03:00.0 reporter fw_fatal -j -p
{
    "irisc_id": 0,
    "event": [
        "id": 3 ],
    "method": "query",
    "long_process": false,
    "command_type": "mad",
    "reg_attr_id": 0
}

As a dependency, the FW validation and flashing is moved to core.c.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/mellanox/mlxsw/core.h

@@ -280,6 +280,8 @@ struct mlxsw_driver {
 	struct list_head list;
 	const char *kind;
 	size_t priv_size;
+	const struct mlxsw_fw_rev *fw_req_rev;
+	const char *fw_filename;
 	int (*init)(struct mlxsw_core *mlxsw_core,
 		    const struct mlxsw_bus_info *mlxsw_bus_info,
 		    struct netlink_ext_ack *extack);
@@ -324,9 +326,6 @@ struct mlxsw_driver {
 				       unsigned int sb_index, u16 tc_index,
 				       enum devlink_sb_pool_type pool_type,
 				       u32 *p_cur, u32 *p_max);
-	int (*flash_update)(struct mlxsw_core *mlxsw_core,
-			    const char *file_name, const char *component,
-			    struct netlink_ext_ack *extack);
 	int (*trap_init)(struct mlxsw_core *mlxsw_core,
 			 const struct devlink_trap *trap, void *trap_ctx);
 	void (*trap_fini)(struct mlxsw_core *mlxsw_core,
@@ -371,6 +370,7 @@ struct mlxsw_driver {
 	u8 txhdr_len;
 	const struct mlxsw_config_profile *profile;
 	bool res_query_enabled;
+	bool fw_fatal_enabled;
 };
 
 int mlxsw_core_kvd_sizes_get(struct mlxsw_core *mlxsw_core,
@@ -378,9 +378,6 @@ int mlxsw_core_kvd_sizes_get(struct mlxsw_core *mlxsw_core,
 			     u64 *p_single_size, u64 *p_double_size,
 			     u64 *p_linear_size);
 
-void mlxsw_core_fw_flash_start(struct mlxsw_core *mlxsw_core);
-void mlxsw_core_fw_flash_end(struct mlxsw_core *mlxsw_core);
-
 u32 mlxsw_core_read_frc_h(struct mlxsw_core *mlxsw_core);
 u32 mlxsw_core_read_frc_l(struct mlxsw_core *mlxsw_core);
 

drivers/net/ethernet/mellanox/mlxsw/reg.h

@@ -5579,6 +5579,7 @@ MLXSW_ITEM32(reg, htgt, type, 0x00, 8, 4);
 
 enum mlxsw_reg_htgt_trap_group {
 	MLXSW_REG_HTGT_TRAP_GROUP_EMAD,
+	MLXSW_REG_HTGT_TRAP_GROUP_MFDE,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_STP,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_LACP,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_LLDP,
@@ -9821,6 +9822,26 @@ static inline void mlxsw_reg_mtptptp_pack(char *payload,
 	mlxsw_reg_mtptpt_message_type_set(payload, message_type);
 }
 
+/* MFGD - Monitoring FW General Debug Register
+ * -------------------------------------------
+ */
+#define MLXSW_REG_MFGD_ID 0x90F0
+#define MLXSW_REG_MFGD_LEN 0x0C
+
+MLXSW_REG_DEFINE(mfgd, MLXSW_REG_MFGD_ID, MLXSW_REG_MFGD_LEN);
+
+/* reg_mfgd_fw_fatal_event_mode
+ * 0 - don't check FW fatal (default)
+ * 1 - check FW fatal - enable MFDE trap
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, mfgd, fatal_event_mode, 0x00, 9, 2);
+
+/* reg_mfgd_trigger_test
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, mfgd, trigger_test, 0x00, 11, 1);
+
 /* MGPIR - Management General Peripheral Information Register
  * ----------------------------------------------------------
  * MGPIR register allows software to query the hardware and
@@ -9880,6 +9901,84 @@ mlxsw_reg_mgpir_unpack(char *payload, u8 *num_of_devices,
 		*num_of_modules = mlxsw_reg_mgpir_num_of_modules_get(payload);
 }
 
+/* MFDE - Monitoring FW Debug Register
+ * -----------------------------------
+ */
+#define MLXSW_REG_MFDE_ID 0x9200
+#define MLXSW_REG_MFDE_LEN 0x18
+
+MLXSW_REG_DEFINE(mfde, MLXSW_REG_MFDE_ID, MLXSW_REG_MFDE_LEN);
+
+/* reg_mfde_irisc_id
+ * Which irisc triggered the event
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, mfde, irisc_id, 0x00, 8, 4);
+
+enum mlxsw_reg_mfde_event_id {
+	MLXSW_REG_MFDE_EVENT_ID_CRSPACE_TO = 1,
+	/* KVD insertion machine stopped */
+	MLXSW_REG_MFDE_EVENT_ID_KVD_IM_STOP,
+};
+
+/* reg_mfde_event_id
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, mfde, event_id, 0x00, 0, 8);
+
+enum mlxsw_reg_mfde_method {
+	MLXSW_REG_MFDE_METHOD_QUERY,
+	MLXSW_REG_MFDE_METHOD_WRITE,
+};
+
+/* reg_mfde_method
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, mfde, method, 0x04, 29, 1);
+
+/* reg_mfde_long_process
+ * Indicates if the command is in long_process mode.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, mfde, long_process, 0x04, 28, 1);
+
+enum mlxsw_reg_mfde_command_type {
+	MLXSW_REG_MFDE_COMMAND_TYPE_MAD,
+	MLXSW_REG_MFDE_COMMAND_TYPE_EMAD,
+	MLXSW_REG_MFDE_COMMAND_TYPE_CMDIF,
+};
+
+/* reg_mfde_command_type
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, mfde, command_type, 0x04, 24, 2);
+
+/* reg_mfde_reg_attr_id
+ * EMAD - register id, MAD - attibute id
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, mfde, reg_attr_id, 0x04, 0, 16);
+
+/* reg_mfde_log_address
+ * crspace address accessed, which resulted in timeout.
+ * Valid in case event_id == MLXSW_REG_MFDE_EVENT_ID_CRSPACE_TO
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, mfde, log_address, 0x10, 0, 32);
+
+/* reg_mfde_log_id
+ * Which irisc triggered the timeout.
+ * Valid in case event_id == MLXSW_REG_MFDE_EVENT_ID_CRSPACE_TO
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, mfde, log_id, 0x14, 0, 4);
+
+/* reg_mfde_pipes_mask
+ * Bit per kvh pipe.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, mfde, pipes_mask, 0x10, 0, 16);
+
 /* TNGCR - Tunneling NVE General Configuration Register
  * ----------------------------------------------------
  * The TNGCR register is used for setting up the NVE Tunneling configuration.
@@ -10993,7 +11092,9 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(mtpppc),
 	MLXSW_REG(mtpptr),
 	MLXSW_REG(mtptpt),
+	MLXSW_REG(mfgd),
 	MLXSW_REG(mgpir),
+	MLXSW_REG(mfde),
 	MLXSW_REG(tngcr),
 	MLXSW_REG(tnumt),
 	MLXSW_REG(tnqcr),

drivers/net/ethernet/mellanox/mlxsw/spectrum.h

@@ -162,8 +162,6 @@ struct mlxsw_sp {
 	struct mlxsw_sp_counter_pool *counter_pool;
 	struct mlxsw_sp_span *span;
 	struct mlxsw_sp_trap *trap;
-	const struct mlxsw_fw_rev *req_rev;
-	const char *fw_filename;
 	const struct mlxsw_sp_kvdl_ops *kvdl_ops;
 	const struct mlxsw_afa_ops *afa_ops;
 	const struct mlxsw_afk_ops *afk_ops;

drivers/net/ethernet/mellanox/mlxsw/trap.h

@@ -120,6 +120,8 @@ enum {
 };
 
 enum mlxsw_event_trap_id {
+	/* Fatal Event generated by FW */
+	MLXSW_TRAP_ID_MFDE = 0x3,
 	/* Port Up/Down event generated by hardware */
 	MLXSW_TRAP_ID_PUDE = 0x8,
 	/* PTP Ingress FIFO has a new entry */

include/net/devlink.h

@@ -566,6 +566,7 @@ enum devlink_health_reporter_state {
  * @dump: callback to dump an object
  *        if priv_ctx is NULL, run a full dump
  * @diagnose: callback to diagnose the current status
+ * @test: callback to trigger a test event
  */
 
 struct devlink_health_reporter_ops {
@@ -578,6 +579,8 @@ struct devlink_health_reporter_ops {
 	int (*diagnose)(struct devlink_health_reporter *reporter,
 			struct devlink_fmsg *fmsg,
 			struct netlink_ext_ack *extack);
+	int (*test)(struct devlink_health_reporter *reporter,
+		    struct netlink_ext_ack *extack);
 };
 
 /**

include/uapi/linux/devlink.h

@@ -122,6 +122,8 @@ enum devlink_command {
 	DEVLINK_CMD_TRAP_POLICER_NEW,
 	DEVLINK_CMD_TRAP_POLICER_DEL,
 
+	DEVLINK_CMD_HEALTH_REPORTER_TEST,
+
 	/* add new commands above here */
 	__DEVLINK_CMD_MAX,
 	DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1

net/core/devlink.c

@@ -6096,6 +6096,28 @@ devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb,
 	return 0;
 }
 
+static int devlink_nl_cmd_health_reporter_test_doit(struct sk_buff *skb,
+						    struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_health_reporter *reporter;
+	int err;
+
+	reporter = devlink_health_reporter_get_from_info(devlink, info);
+	if (!reporter)
+		return -EINVAL;
+
+	if (!reporter->ops->test) {
+		devlink_health_reporter_put(reporter);
+		return -EOPNOTSUPP;
+	}
+
+	err = reporter->ops->test(reporter, info->extack);
+
+	devlink_health_reporter_put(reporter);
+	return err;
+}
+
 struct devlink_stats {
 	u64 rx_bytes;
 	u64 rx_packets;
@@ -7316,6 +7338,14 @@ static const struct genl_ops devlink_nl_ops[] = {
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT |
 				  DEVLINK_NL_FLAG_NO_LOCK,
 	},
+	{
+		.cmd = DEVLINK_CMD_HEALTH_REPORTER_TEST,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_health_reporter_test_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT |
+				  DEVLINK_NL_FLAG_NO_LOCK,
+	},
 	{
 		.cmd = DEVLINK_CMD_FLASH_UPDATE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,