From: Shahar Shitrit Enable configuration of the grace period delay — a time window starting from the first error recovery, during which the reporter allows recovery attempts for each reported error. This feature is helpful when a single underlying issue causes multiple errors, as it delays the start of the grace period to allow sufficient time for recovering all related errors. For example, if multiple TX queues time out simultaneously, a sufficient grace period delay could allow all affected TX queues to be recovered within that window. Without this delay, only the first TX queue that reports a timeout will undergo recovery, while the remaining TX queues will be blocked once the grace period begins. Configuration example: $ devlink health set pci/0000:00:09.0 reporter tx grace_period_delay 500 Configuration example with ynl: ./tools/net/ynl/pyynl/cli.py \ --spec Documentation/netlink/specs/devlink.yaml \ --do health-reporter-set --json '{ "bus-name": "auxiliary", "dev-name": "mlx5_core.eth.0", "port-index": 65535, "health-reporter-name": "tx", "health-reporter-graceful-period-delay": 500 }' Signed-off-by: Shahar Shitrit Reviewed-by: Jiri Pirko Reviewed-by: Carolina Jubran Signed-off-by: Tariq Toukan --- Documentation/netlink/specs/devlink.yaml | 7 +++++ .../networking/devlink/devlink-health.rst | 2 +- include/uapi/linux/devlink.h | 2 ++ net/devlink/health.c | 30 +++++++++++++++++-- net/devlink/netlink_gen.c | 5 ++-- 5 files changed, 40 insertions(+), 6 deletions(-) diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml index 1c4bb0cbe5f0..c6cc0ce18685 100644 --- a/Documentation/netlink/specs/devlink.yaml +++ b/Documentation/netlink/specs/devlink.yaml @@ -848,6 +848,10 @@ attribute-sets: - name: region-direct type: flag + - + name: health-reporter-graceful-period-delay + type: u64 + - name: rate-tc-bws type: nest @@ -1228,6 +1232,8 @@ attribute-sets: name: health-reporter-dump-ts-ns - name: health-reporter-auto-dump + - + name: health-reporter-graceful-period-delay - name: dl-attr-stats @@ -1965,6 +1971,7 @@ operations: - health-reporter-graceful-period - health-reporter-auto-recover - health-reporter-auto-dump + - health-reporter-graceful-period-delay - name: health-reporter-recover diff --git a/Documentation/networking/devlink/devlink-health.rst b/Documentation/networking/devlink/devlink-health.rst index e0b8cfed610a..07602f678282 100644 --- a/Documentation/networking/devlink/devlink-health.rst +++ b/Documentation/networking/devlink/devlink-health.rst @@ -50,7 +50,7 @@ Once an error is reported, devlink health will perform the following actions: * Auto recovery attempt is being done. Depends on: - Auto-recovery configuration - - Grace period vs. time passed since last recover + - Grace period (and grace period delay) vs. time passed since last recover Devlink formatted message ========================= diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index e72bcc239afd..42a11b7e4a70 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -634,6 +634,8 @@ enum devlink_attr { DEVLINK_ATTR_REGION_DIRECT, /* flag */ + DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD_DELAY, /* u64 */ + DEVLINK_ATTR_RATE_TC_BWS, /* nested */ DEVLINK_ATTR_RATE_TC_INDEX, /* u8 */ DEVLINK_ATTR_RATE_TC_BW, /* u32 */ diff --git a/net/devlink/health.c b/net/devlink/health.c index a0269975f592..5699779fce77 100644 --- a/net/devlink/health.c +++ b/net/devlink/health.c @@ -113,7 +113,9 @@ __devlink_health_reporter_create(struct devlink *devlink, { struct devlink_health_reporter *reporter; - if (WARN_ON(ops->default_graceful_period && !ops->recover)) + if (WARN_ON(ops->default_graceful_period_delay && + !ops->default_graceful_period) || + WARN_ON(ops->default_graceful_period && !ops->recover)) return ERR_PTR(-EINVAL); reporter = kzalloc(sizeof(*reporter), GFP_KERNEL); @@ -293,6 +295,11 @@ devlink_nl_health_reporter_fill(struct sk_buff *msg, devlink_nl_put_u64(msg, DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD, reporter->graceful_period)) goto reporter_nest_cancel; + if (reporter->ops->recover && + devlink_nl_put_u64(msg, + DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD_DELAY, + reporter->graceful_period_delay)) + goto reporter_nest_cancel; if (reporter->ops->recover && nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER, reporter->auto_recover)) @@ -458,16 +465,33 @@ int devlink_nl_health_reporter_set_doit(struct sk_buff *skb, if (!reporter->ops->recover && (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] || - info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER])) + info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] || + info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD_DELAY])) return -EOPNOTSUPP; if (!reporter->ops->dump && info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP]) return -EOPNOTSUPP; - if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]) + if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]) { reporter->graceful_period = nla_get_u64(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]); + if (!reporter->graceful_period) + reporter->graceful_period_delay = 0; + } + + if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD_DELAY]) { + u64 configured_delay = + nla_get_u64(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD_DELAY]); + + if (!reporter->graceful_period && configured_delay) { + NL_SET_ERR_MSG_MOD(info->extack, + "Cannot set grace period delay without a grace period."); + return -EINVAL; + } + + reporter->graceful_period_delay = configured_delay; + } if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]) reporter->auto_recover = diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c index c50436433c18..b0f38253d163 100644 --- a/net/devlink/netlink_gen.c +++ b/net/devlink/netlink_gen.c @@ -389,7 +389,7 @@ static const struct nla_policy devlink_health_reporter_get_dump_nl_policy[DEVLIN }; /* DEVLINK_CMD_HEALTH_REPORTER_SET - do */ -static const struct nla_policy devlink_health_reporter_set_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP + 1] = { +static const struct nla_policy devlink_health_reporter_set_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD_DELAY + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, @@ -397,6 +397,7 @@ static const struct nla_policy devlink_health_reporter_set_nl_policy[DEVLINK_ATT [DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .type = NLA_U64, }, [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8, }, [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP] = { .type = NLA_U8, }, + [DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD_DELAY] = { .type = NLA_U64, }, }; /* DEVLINK_CMD_HEALTH_REPORTER_RECOVER - do */ @@ -1032,7 +1033,7 @@ const struct genl_split_ops devlink_nl_ops[74] = { .doit = devlink_nl_health_reporter_set_doit, .post_doit = devlink_nl_post_doit, .policy = devlink_health_reporter_set_nl_policy, - .maxattr = DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP, + .maxattr = DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD_DELAY, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, { -- 2.31.1