devlink: Add auto dump flag to health reporter

On low memory system, run time dumps can consume too much memory. Add
administrator ability to disable auto dumps per reporter as part of the
error flow handle routine.

This attribute is not relevant while executing
DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET.

By default, auto dump is activated for any reporter that has a dump method,
as part of the reporter registration to devlink.
Signed-off-by: NEran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

include/uapi/linux/devlink.h

@@ -429,6 +429,8 @@ enum devlink_attr {
 	DEVLINK_ATTR_NETNS_FD,			/* u32 */
 	DEVLINK_ATTR_NETNS_PID,			/* u32 */
 	DEVLINK_ATTR_NETNS_ID,			/* u32 */
+
+	DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP,	/* u8 */
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,

net/core/devlink.c

@@ -5089,6 +5089,7 @@ struct devlink_health_reporter {
 	struct mutex dump_lock; /* lock parallel read/write from dump buffers */
 	u64 graceful_period;
 	bool auto_recover;
+	bool auto_dump;
 	u8 health_state;
 	u64 dump_ts;
 	u64 dump_real_ts;
@@ -5155,6 +5156,7 @@ devlink_health_reporter_create(struct devlink *devlink,
 	reporter->devlink = devlink;
 	reporter->graceful_period = graceful_period;
 	reporter->auto_recover = !!ops->recover;
+	reporter->auto_dump = !!ops->dump;
 	mutex_init(&reporter->dump_lock);
 	refcount_set(&reporter->refcount, 1);
 	list_add_tail(&reporter->list, &devlink->reporter_list);
@@ -5235,6 +5237,10 @@ devlink_nl_health_reporter_fill(struct sk_buff *msg,
 	    nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS_NS,
 			      reporter->dump_real_ts, DEVLINK_ATTR_PAD))
 		goto reporter_nest_cancel;
+	if (reporter->ops->dump &&
+	    nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP,
+		       reporter->auto_dump))
+		goto reporter_nest_cancel;
 
 	nla_nest_end(msg, reporter_attr);
 	genlmsg_end(msg, hdr);
@@ -5381,10 +5387,12 @@ int devlink_health_report(struct devlink_health_reporter *reporter,
 
 	reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_ERROR;
 
-	mutex_lock(&reporter->dump_lock);
-	/* store current dump of current error, for later analysis */
-	devlink_health_do_dump(reporter, priv_ctx, NULL);
-	mutex_unlock(&reporter->dump_lock);
+	if (reporter->auto_dump) {
+		mutex_lock(&reporter->dump_lock);
+		/* store current dump of current error, for later analysis */
+		devlink_health_do_dump(reporter, priv_ctx, NULL);
+		mutex_unlock(&reporter->dump_lock);
+	}
 
 	if (reporter->auto_recover)
 		return devlink_health_reporter_recover(reporter,
@@ -5558,6 +5566,11 @@ devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb,
 		err = -EOPNOTSUPP;
 		goto out;
 	}
+	if (!reporter->ops->dump &&
+	    info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP]) {
+		err = -EOPNOTSUPP;
+		goto out;
+	}
 
 	if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD])
 		reporter->graceful_period =
@@ -5567,6 +5580,10 @@ devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb,
 		reporter->auto_recover =
 			nla_get_u8(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]);
 
+	if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP])
+		reporter->auto_dump =
+		nla_get_u8(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP]);
+
 	devlink_health_reporter_put(reporter);
 	return 0;
 out:
@@ -6313,6 +6330,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_NETNS_PID] = { .type = NLA_U32 },
 	[DEVLINK_ATTR_NETNS_FD] = { .type = NLA_U32 },
 	[DEVLINK_ATTR_NETNS_ID] = { .type = NLA_U32 },
+	[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP] = { .type = NLA_U8 },
 };
 
 static const struct genl_ops devlink_nl_ops[] = {