From d2b007374551ac09db16badde575cdd698f6fc92 Mon Sep 17 00:00:00 2001 From: Shahar Shitrit Date: Sun, 24 Aug 2025 11:43:50 +0300 Subject: devlink: Move graceful period parameter to reporter ops Move the default graceful period from a parameter to devlink_health_reporter_create() to a field in the devlink_health_reporter_ops structure. This change improves consistency, as the graceful period is inherently tied to the reporter's behavior and recovery policy. It simplifies the signature of devlink_health_reporter_create() and its internal helper functions. It also centralizes the reporter configuration at the ops structure, preparing the groundwork for a downstream patch that will introduce a devlink health reporter burst period attribute whose default value will similarly be provided by the driver via the ops structure. Signed-off-by: Shahar Shitrit Reviewed-by: Jiri Pirko Signed-off-by: Mark Bloch Link: https://patch.msgid.link/20250824084354.533182-2-mbloch@nvidia.com Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/devlink.h b/include/net/devlink.h index 3119d053bc4d..c7ad7a981b39 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -746,6 +746,8 @@ enum devlink_health_reporter_state { * if priv_ctx is NULL, run a full dump * @diagnose: callback to diagnose the current status * @test: callback to trigger a test event + * @default_graceful_period: default min time (in msec) + * between recovery attempts */ struct devlink_health_reporter_ops { @@ -760,6 +762,7 @@ struct devlink_health_reporter_ops { struct netlink_ext_ack *extack); int (*test)(struct devlink_health_reporter *reporter, struct netlink_ext_ack *extack); + u64 default_graceful_period; }; /** @@ -1928,22 +1931,22 @@ void devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, struct devlink_health_reporter * devl_port_health_reporter_create(struct devlink_port *port, const struct devlink_health_reporter_ops *ops, - u64 graceful_period, void *priv); + void *priv); struct devlink_health_reporter * devlink_port_health_reporter_create(struct devlink_port *port, const struct devlink_health_reporter_ops *ops, - u64 graceful_period, void *priv); + void *priv); struct devlink_health_reporter * devl_health_reporter_create(struct devlink *devlink, const struct devlink_health_reporter_ops *ops, - u64 graceful_period, void *priv); + void *priv); struct devlink_health_reporter * devlink_health_reporter_create(struct devlink *devlink, const struct devlink_health_reporter_ops *ops, - u64 graceful_period, void *priv); + void *priv); void devl_health_reporter_destroy(struct devlink_health_reporter *reporter); -- cgit v1.2.3 From 6a06d8c40510ba1ecf27977f528b1eb74f290a60 Mon Sep 17 00:00:00 2001 From: Shahar Shitrit Date: Sun, 24 Aug 2025 11:43:52 +0300 Subject: devlink: Introduce burst period for health reporter 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 Reviewed-by: Jiri Pirko Signed-off-by: Mark Bloch Link: https://patch.msgid.link/20250824084354.533182-4-mbloch@nvidia.com Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/net') 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; }; /** -- cgit v1.2.3