From: Shahar Shitrit Enable configuration of the error burst period — 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 error burst period could allow all affected TX queues to be recovered within that window. Without this period, 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 error_burst_period 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-error-burst-period": 500 }' Signed-off-by: Shahar Shitrit Reviewed-by: Carolina Jubran Reviewed-by: Jiri Pirko Signed-off-by: Tariq Toukan --- Documentation/netlink/specs/devlink.yaml | 6 ++++ .../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, 39 insertions(+), 6 deletions(-) diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml index bb87111d5e16..0e81640dd3b2 100644 --- a/Documentation/netlink/specs/devlink.yaml +++ b/Documentation/netlink/specs/devlink.yaml @@ -853,6 +853,9 @@ attribute-sets: type: nest multi-attr: true nested-attributes: dl-rate-tc-bws + - + name: health-reporter-error-burst-period + type: u64 - name: dl-dev-stats subset-of: devlink @@ -1216,6 +1219,8 @@ attribute-sets: name: health-reporter-dump-ts-ns - name: health-reporter-auto-dump + - + name: health-reporter-error-burst-period - name: dl-attr-stats @@ -1961,6 +1966,7 @@ operations: - health-reporter-graceful-period - health-reporter-auto-recover - health-reporter-auto-dump + - health-reporter-error-burst-period - name: health-reporter-recover diff --git a/Documentation/networking/devlink/devlink-health.rst b/Documentation/networking/devlink/devlink-health.rst index e0b8cfed610a..2279a4370003 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 error burst period) vs. time passed since last recover Devlink formatted message ========================= diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 9fcb25a0f447..458915c22990 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -636,6 +636,8 @@ enum devlink_attr { DEVLINK_ATTR_RATE_TC_BWS, /* nested */ + DEVLINK_ATTR_HEALTH_REPORTER_ERR_BURST_PERIOD, /* u64 */ + /* Add new attributes above here, update the spec in * Documentation/netlink/specs/devlink.yaml and re-generate * net/devlink/netlink_gen.c. diff --git a/net/devlink/health.c b/net/devlink/health.c index c4a028e37277..d01eb4eaf89c 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_error_burst_period && + !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_ERR_BURST_PERIOD, + reporter->error_burst_period)) + 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_ERR_BURST_PERIOD])) 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->error_burst_period = 0; + } + + if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_ERR_BURST_PERIOD]) { + u64 burst_period = + nla_get_u64(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_ERR_BURST_PERIOD]); + + if (!reporter->graceful_period && burst_period) { + NL_SET_ERR_MSG_MOD(info->extack, + "Cannot set error burst period without a grace period."); + return -EINVAL; + } + + reporter->error_burst_period = burst_period; + } 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 d97c326a9045..a02da5a0002f 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_ERR_BURST_PERIOD + 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_ERR_BURST_PERIOD] = { .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_ERR_BURST_PERIOD, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, { -- 2.31.1