| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <1752768442-264413-4-git-send-email-tariqt@nvidia.com>
Date: Thu, 17 Jul 2025 19:07:20 +0300
From: Tariq Toukan <tariqt@...dia.com>
To: Eric Dumazet <edumazet@...gle.com>, Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>, Andrew Lunn <andrew+netdev@...n.ch>, "David
S. Miller" <davem@...emloft.net>, Jiri Pirko <jiri@...nulli.us>, Jiri Pirko
<jiri@...dia.com>
CC: Saeed Mahameed <saeed@...nel.org>, Gal Pressman <gal@...dia.com>, "Leon
Romanovsky" <leon@...nel.org>, Shahar Shitrit <shshitrit@...dia.com>, "Donald
Hunter" <donald.hunter@...il.com>, Jonathan Corbet <corbet@....net>, "Brett
Creeley" <brett.creeley@....com>, Michael Chan <michael.chan@...adcom.com>,
Pavan Chebbi <pavan.chebbi@...adcom.com>, Cai Huoqing
<cai.huoqing@...ux.dev>, Tony Nguyen <anthony.l.nguyen@...el.com>, "Przemek
Kitszel" <przemyslaw.kitszel@...el.com>, Sunil Goutham
<sgoutham@...vell.com>, Linu Cherian <lcherian@...vell.com>, Geetha sowjanya
<gakula@...vell.com>, Jerin Jacob <jerinj@...vell.com>, hariprasad
<hkelam@...vell.com>, "Subbaraya Sundeep" <sbhatta@...vell.com>, Saeed
Mahameed <saeedm@...dia.com>, "Tariq Toukan" <tariqt@...dia.com>, Mark Bloch
<mbloch@...dia.com>, Ido Schimmel <idosch@...dia.com>, Petr Machata
<petrm@...dia.com>, Manish Chopra <manishc@...vell.com>,
<netdev@...r.kernel.org>, <linux-kernel@...r.kernel.org>,
<linux-doc@...r.kernel.org>, <intel-wired-lan@...ts.osuosl.org>,
<linux-rdma@...r.kernel.org>
Subject: [PATCH net-next 3/5] devlink: Introduce grace period delay for health reporter
From: Shahar Shitrit <shshitrit@...dia.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 grace period delay for devlink
health reporter. Start this delay when the first error is handled, and
allow recovery attempts for reported errors during this window. Once the
delay expires, begin the grace period to block further recoveries until
it concludes.
Timeline summary:
----|--------|------------------------------/----------------------/--
error is error is grace period delay grace period
reported recovered (recoveries allowed) (recoveries blocked)
For calculating the grace period delay duration, use the same
last_recovery_ts as the grace period. Update it on recovery only
when the delay is inactive (either disabled or at the first error).
This patch implements the framework for the grace period delay 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 grace period delay configurable.
Signed-off-by: Shahar Shitrit <shshitrit@...dia.com>
Reviewed-by: Jiri Pirko <jiri@...dia.com>
Reviewed-by: Carolina Jubran <cjubran@...dia.com>
Signed-off-by: Tariq Toukan <tariqt@...dia.com>
---
include/net/devlink.h | 4 ++++
net/devlink/health.c | 22 +++++++++++++++++++++-
2 files changed, 25 insertions(+), 1 deletion(-)
diff --git a/include/net/devlink.h b/include/net/devlink.h
index a65aa24e8df4..3ab85de9c862 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -744,6 +744,9 @@ enum devlink_health_reporter_state {
* @test: callback to trigger a test event
* @default_graceful_period: default min time (in msec)
between recovery attempts
+ * @default_graceful_period_delay: default time (in msec) for
+ * error recoveries before
+ * starting the grace period
*/
struct devlink_health_reporter_ops {
@@ -759,6 +762,7 @@ struct devlink_health_reporter_ops {
int (*test)(struct devlink_health_reporter *reporter,
struct netlink_ext_ack *extack);
u64 default_graceful_period;
+ u64 default_graceful_period_delay;
};
/**
diff --git a/net/devlink/health.c b/net/devlink/health.c
index 9d0d4a9face7..a0269975f592 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 graceful_period_delay;
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->graceful_period_delay = ops->default_graceful_period_delay;
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_delay_active(struct devlink_health_reporter *reporter)
+{
+ unsigned long delay_threshold = reporter->last_recovery_ts +
+ msecs_to_jiffies(reporter->graceful_period_delay);
+
+ return time_is_after_jiffies(delay_threshold);
+}
+
void
devlink_health_reporter_recovery_done(struct devlink_health_reporter *reporter)
{
reporter->recovery_count++;
- reporter->last_recovery_ts = jiffies;
+ if (!devlink_health_reporter_delay_active(reporter))
+ /* When grace period delay is set, last_recovery_ts marks
+ * the first recovery within the delay, 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_delay_active(reporter))
+ return false;
+
recover_ts_threshold = reporter->last_recovery_ts +
+ msecs_to_jiffies(reporter->graceful_period_delay) +
msecs_to_jiffies(reporter->graceful_period);
if (reporter->last_recovery_ts && reporter->recovery_count &&
time_is_after_jiffies(recover_ts_threshold))
--
2.31.1
Powered by blists - more mailing lists