devlink: Add health reporter create/destroy functionality

Devlink health reporter is an instance for reporting, diagnosing and
recovering from run time errors discovered by the reporters.
Define it's data structure and supported operations.
In addition, expose devlink API to create and destroy a reporter.
Each devlink instance will hold it's own reporters list.

As part of the allocation, driver shall provide a set of callbacks which
will be used the devlink in order to handle health reports and user
commands related to this reporter. In addition, driver is entitled to
provide some priv pointer, which can be fetched from the reporter by
devlink_health_reporter_priv function.

For each reporter, devlink will hold a metadata of statistics,
buffers and status.

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

1 files changed, 127 insertions, 0 deletions

diff --git a/net/core/devlink.c b/net/core/devlink.c
index 8984501edade..fec169a28dba 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -4098,6 +4098,132 @@ nla_put_failure:
 	return err;
 }
 
+struct devlink_health_reporter {
+	struct list_head list;
+	struct devlink_health_buffer **dump_buffers_array;
+	struct mutex dump_lock; /* lock parallel read/write from dump buffers */
+	struct devlink_health_buffer **diagnose_buffers_array;
+	struct mutex diagnose_lock; /* lock parallel read/write from diagnose buffers */
+	void *priv;
+	const struct devlink_health_reporter_ops *ops;
+	struct devlink *devlink;
+	u64 graceful_period;
+	bool auto_recover;
+	u8 health_state;
+};
+
+void *
+devlink_health_reporter_priv(struct devlink_health_reporter *reporter)
+{
+	return reporter->priv;
+}
+EXPORT_SYMBOL_GPL(devlink_health_reporter_priv);
+
+static struct devlink_health_reporter *
+devlink_health_reporter_find_by_name(struct devlink *devlink,
+				     const char *reporter_name)
+{
+	struct devlink_health_reporter *reporter;
+
+	list_for_each_entry(reporter, &devlink->reporter_list, list)
+		if (!strcmp(reporter->ops->name, reporter_name))
+			return reporter;
+	return NULL;
+}
+
+/**
+ *	devlink_health_reporter_create - create devlink health reporter
+ *
+ *	@devlink: devlink
+ *	@ops: ops
+ *	@graceful_period: to avoid recovery loops, in msecs
+ *	@auto_recover: auto recover when error occurs
+ *	@priv: priv
+ */
+struct devlink_health_reporter *
+devlink_health_reporter_create(struct devlink *devlink,
+			       const struct devlink_health_reporter_ops *ops,
+			       u64 graceful_period, bool auto_recover,
+			       void *priv)
+{
+	struct devlink_health_reporter *reporter;
+
+	mutex_lock(&devlink->lock);
+	if (devlink_health_reporter_find_by_name(devlink, ops->name)) {
+		reporter = ERR_PTR(-EEXIST);
+		goto unlock;
+	}
+
+	if (WARN_ON(ops->dump && !ops->dump_size) ||
+	    WARN_ON(ops->diagnose && !ops->diagnose_size) ||
+	    WARN_ON(auto_recover && !ops->recover) ||
+	    WARN_ON(graceful_period && !ops->recover)) {
+		reporter = ERR_PTR(-EINVAL);
+		goto unlock;
+	}
+
+	reporter = kzalloc(sizeof(*reporter), GFP_KERNEL);
+	if (!reporter) {
+		reporter = ERR_PTR(-ENOMEM);
+		goto unlock;
+	}
+
+	if (ops->dump) {
+		reporter->dump_buffers_array =
+			devlink_health_buffers_create(ops->dump_size);
+		if (!reporter->dump_buffers_array) {
+			kfree(reporter);
+			reporter = ERR_PTR(-ENOMEM);
+			goto unlock;
+		}
+	}
+
+	if (ops->diagnose) {
+		reporter->diagnose_buffers_array =
+			devlink_health_buffers_create(ops->diagnose_size);
+		if (!reporter->diagnose_buffers_array) {
+			devlink_health_buffers_destroy(reporter->dump_buffers_array,
+						       DEVLINK_HEALTH_SIZE_TO_BUFFERS(ops->dump_size));
+			kfree(reporter);
+			reporter = ERR_PTR(-ENOMEM);
+			goto unlock;
+		}
+	}
+
+	list_add_tail(&reporter->list, &devlink->reporter_list);
+	mutex_init(&reporter->dump_lock);
+	mutex_init(&reporter->diagnose_lock);
+
+	reporter->priv = priv;
+	reporter->ops = ops;
+	reporter->devlink = devlink;
+	reporter->graceful_period = graceful_period;
+	reporter->auto_recover = auto_recover;
+unlock:
+	mutex_unlock(&devlink->lock);
+	return reporter;
+}
+EXPORT_SYMBOL_GPL(devlink_health_reporter_create);
+
+/**
+ *	devlink_health_reporter_destroy - destroy devlink health reporter
+ *
+ *	@reporter: devlink health reporter to destroy
+ */
+void
+devlink_health_reporter_destroy(struct devlink_health_reporter *reporter)
+{
+	mutex_lock(&reporter->devlink->lock);
+	list_del(&reporter->list);
+	devlink_health_buffers_destroy(reporter->dump_buffers_array,
+				       DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->dump_size));
+	devlink_health_buffers_destroy(reporter->diagnose_buffers_array,
+				       DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->diagnose_size));
+	kfree(reporter);
+	mutex_unlock(&reporter->devlink->lock);
+}
+EXPORT_SYMBOL_GPL(devlink_health_reporter_destroy);
+
 static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING },
@@ -4383,6 +4509,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size)
 	INIT_LIST_HEAD(&devlink->resource_list);
 	INIT_LIST_HEAD(&devlink->param_list);
 	INIT_LIST_HEAD(&devlink->region_list);
+	INIT_LIST_HEAD(&devlink->reporter_list);
 	mutex_init(&devlink->lock);
 	return devlink;
 }