[PATCH net-next V4 3/5] devlink: Introduce burst period for health reporter

[Mark Bloch <mbloch@nvidia.com>]

From: Shahar Shitrit <shshitrit@nvidia.com>

Currently, the devlink health reporter starts the grace period
immediately after handling an error, blocking any further recoveries
until it finished.

However, when a single root cause triggers multiple errors in a short
time frame, it is desirable to treat them as a bulk of errors and to
allow their recoveries, avoiding premature blocking of subsequent
related errors, and reducing the risk of inconsistent or incomplete
error handling.

To address this, introduce a configurable burst period for devlink
health reporter. Start this period when the first error is handled,
and allow recovery attempts for reported errors during this window.
Once burst period expires, begin the grace period to block further
recoveries until it concludes.

Timeline summary:

----|--------|------------------------------/----------------------/--
error is  error is       burst period           grace period
reported  recovered  (recoveries allowed)    (recoveries blocked)

For calculating the burst period duration, use the same
last_recovery_ts as the grace period. Update it on recovery only
when the burst period is inactive (either disabled or at the
first error).

This patch implements the framework for the burst period and
effectively sets its value to 0 at reporter creation, so the current
behavior remains unchanged, which ensures backward compatibility.

A downstream patch will make the burst period configurable.

Signed-off-by: Shahar Shitrit <shshitrit@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
---
 include/net/devlink.h |  3 +++
 net/devlink/health.c  | 22 +++++++++++++++++++++-
 2 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/include/net/devlink.h b/include/net/devlink.h
index c7ad7a981b39..5f44e702c25c 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -748,6 +748,8 @@ enum devlink_health_reporter_state {
  * @test: callback to trigger a test event
  * @default_graceful_period: default min time (in msec)
  *	between recovery attempts
+ * @default_burst_period: default time (in msec) for
+ *	error recoveries before starting the grace period
  */
 
 struct devlink_health_reporter_ops {
@@ -763,6 +765,7 @@ struct devlink_health_reporter_ops {
 	int (*test)(struct devlink_health_reporter *reporter,
 		    struct netlink_ext_ack *extack);
 	u64 default_graceful_period;
+	u64 default_burst_period;
 };
 
 /**
diff --git a/net/devlink/health.c b/net/devlink/health.c
index 9d0d4a9face7..94ab77f77add 100644
--- a/net/devlink/health.c
+++ b/net/devlink/health.c
@@ -60,6 +60,7 @@ struct devlink_health_reporter {
 	struct devlink_port *devlink_port;
 	struct devlink_fmsg *dump_fmsg;
 	u64 graceful_period;
+	u64 burst_period;
 	bool auto_recover;
 	bool auto_dump;
 	u8 health_state;
@@ -123,6 +124,7 @@ __devlink_health_reporter_create(struct devlink *devlink,
 	reporter->ops = ops;
 	reporter->devlink = devlink;
 	reporter->graceful_period = ops->default_graceful_period;
+	reporter->burst_period = ops->default_burst_period;
 	reporter->auto_recover = !!ops->recover;
 	reporter->auto_dump = !!ops->dump;
 	return reporter;
@@ -508,11 +510,25 @@ static void devlink_recover_notify(struct devlink_health_reporter *reporter,
 	devlink_nl_notify_send_desc(devlink, msg, &desc);
 }
 
+static bool
+devlink_health_reporter_in_burst(struct devlink_health_reporter *reporter)
+{
+	unsigned long burst_threshold = reporter->last_recovery_ts +
+		msecs_to_jiffies(reporter->burst_period);
+
+	return time_is_after_jiffies(burst_threshold);
+}
+
 void
 devlink_health_reporter_recovery_done(struct devlink_health_reporter *reporter)
 {
 	reporter->recovery_count++;
-	reporter->last_recovery_ts = jiffies;
+	if (!devlink_health_reporter_in_burst(reporter))
+		/* When burst period is set, last_recovery_ts marks the first
+		 * recovery within the burst period, not necessarily the last
+		 * one.
+		 */
+		reporter->last_recovery_ts = jiffies;
 }
 EXPORT_SYMBOL_GPL(devlink_health_reporter_recovery_done);
 
@@ -599,7 +615,11 @@ devlink_health_recover_abort(struct devlink_health_reporter *reporter,
 	if (prev_state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY)
 		return true;
 
+	if (devlink_health_reporter_in_burst(reporter))
+		return false;
+
 	recover_ts_threshold = reporter->last_recovery_ts +
+		msecs_to_jiffies(reporter->burst_period) +
 		msecs_to_jiffies(reporter->graceful_period);
 	if (reporter->last_recovery_ts && reporter->recovery_count &&
 	    time_is_after_jiffies(recover_ts_threshold))
-- 
2.34.1