devlink: Add health report functionality

Upon error discover, every driver can report it to the devlink health
mechanism via devlink_health_report function, using the appropriate
reporter registered to it. Driver can pass error specific context which
will be delivered to it as part of the dump / recovery callbacks.

Once an error is reported, devlink health will do the following actions:
* A log is being send to the kernel trace events buffer
* Health status and statistics are being updated for the reporter instance
* Object dump is being taken and stored at the reporter instance (as long
  as there is no other dump which is already stored)
* Auto recovery attempt is being done. Depends on:
  - Auto Recovery configuration
  - Grace period vs. Time since last recover

Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 74 insertions, 0 deletions

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 3dfe30235878..c12ad6e9095d 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -704,6 +704,8 @@ devlink_health_reporter_destroy(struct devlink_health_reporter *reporter);
 
 void *
 devlink_health_reporter_priv(struct devlink_health_reporter *reporter);
+int devlink_health_report(struct devlink_health_reporter *reporter,
+			  const char *msg, void *priv_ctx);
 
 #else
 
@@ -1173,6 +1175,13 @@ devlink_health_reporter_priv(struct devlink_health_reporter *reporter)
 {
 	return NULL;
 }
+
+static inline int
+devlink_health_report(struct devlink_health_reporter *reporter,
+		      const char *msg, void *priv_ctx)
+{
+	return 0;
+}
 #endif
 
 #if IS_REACHABLE(CONFIG_NET_DEVLINK)
diff --git a/include/trace/events/devlink.h b/include/trace/events/devlink.h
index 40705364a50f..191ddf67d769 100644
--- a/include/trace/events/devlink.h
+++ b/include/trace/events/devlink.h
@@ -75,6 +75,71 @@ TRACE_EVENT(devlink_hwerr,
 			__get_str(driver_name), __entry->err, __get_str(msg))
 );
 
+/*
+ * Tracepoint for devlink health message:
+ */
+TRACE_EVENT(devlink_health_report,
+	TP_PROTO(const struct devlink *devlink, const char *reporter_name,
+		 const char *msg),
+
+	TP_ARGS(devlink, reporter_name, msg),
+
+	TP_STRUCT__entry(
+		__string(bus_name, devlink->dev->bus->name)
+		__string(dev_name, dev_name(devlink->dev))
+		__string(driver_name, devlink->dev->driver->name)
+		__string(reporter_name, msg)
+		__string(msg, msg)
+	),
+
+	TP_fast_assign(
+		__assign_str(bus_name, devlink->dev->bus->name);
+		__assign_str(dev_name, dev_name(devlink->dev));
+		__assign_str(driver_name, devlink->dev->driver->name);
+		__assign_str(reporter_name, reporter_name);
+		__assign_str(msg, msg);
+	),
+
+	TP_printk("bus_name=%s dev_name=%s driver_name=%s reporter_name=%s: %s",
+		  __get_str(bus_name), __get_str(dev_name),
+		  __get_str(driver_name), __get_str(reporter_name),
+		  __get_str(msg))
+);
+
+/*
+ * Tracepoint for devlink health recover aborted message:
+ */
+TRACE_EVENT(devlink_health_recover_aborted,
+	TP_PROTO(const struct devlink *devlink, const char *reporter_name,
+		 bool health_state, u64 time_since_last_recover),
+
+	TP_ARGS(devlink, reporter_name, health_state, time_since_last_recover),
+
+	TP_STRUCT__entry(
+		__string(bus_name, devlink->dev->bus->name)
+		__string(dev_name, dev_name(devlink->dev))
+		__string(driver_name, devlink->dev->driver->name)
+		__string(reporter_name, reporter_name)
+		__field(bool, health_state)
+		__field(u64, time_since_last_recover)
+	),
+
+	TP_fast_assign(
+		__assign_str(bus_name, devlink->dev->bus->name);
+		__assign_str(dev_name, dev_name(devlink->dev));
+		__assign_str(driver_name, devlink->dev->driver->name);
+		__assign_str(reporter_name, reporter_name);
+		__entry->health_state = health_state;
+		__entry->time_since_last_recover = time_since_last_recover;
+	),
+
+	TP_printk("bus_name=%s dev_name=%s driver_name=%s reporter_name=%s: health_state=%d time_since_last_recover=%llu recover aborted",
+		  __get_str(bus_name), __get_str(dev_name),
+		  __get_str(driver_name), __get_str(reporter_name),
+		  __entry->health_state,
+		  __entry->time_since_last_recover)
+);
+
 #endif /* _TRACE_DEVLINK_H */
 
 /* This part must be outside protection */