| 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: <1547737521-29888-4-git-send-email-eranbe@mellanox.com>
Date: Thu, 17 Jan 2019 17:04:57 +0200
From: Eran Ben Elisha <eranbe@...lanox.com>
To: netdev@...r.kernel.org, Jiri Pirko <jiri@...lanox.com>,
"David S. Miller" <davem@...emloft.net>,
Ariel Almog <ariela@...lanox.com>,
Aya Levin <ayal@...lanox.com>,
Eran Ben Elisha <eranbe@...lanox.com>,
Moshe Shemesh <moshe@...lanox.com>
Subject: [PATCH net-next 03/27] devlink: Add health report functionality
Upon error discover, every driver can report it to the devlink health
mechanism via devlink_health_report function, using the appropriate
reporter registered to it. Driver can pass error specific context which
will be delivered to it as part of the dump / recovery callbacks.
Once an error is reported, devlink health will do the following actions:
* A log is being send to the kernel trace events buffer
* Health status and statistics are being updated for the reporter instance
* Object dump is being taken and stored at the reporter instance (as long
as there is no other dump which is already stored)
* Auto recovery attempt is being done. depends on:
- Auto Recovery configuration
- Grace period vs. time since last recover
Signed-off-by: Eran Ben Elisha <eranbe@...lanox.com>
Reviewed-by: Moshe Shemesh <moshe@...lanox.com>
---
include/net/devlink.h | 9 ++++
include/trace/events/devlink.h | 62 +++++++++++++++++++++++
net/core/devlink.c | 93 ++++++++++++++++++++++++++++++++++
3 files changed, 164 insertions(+)
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 7fe30d67678a..a81a1b7a67d7 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -641,6 +641,8 @@ devlink_health_reporter_destroy(struct devlink_health_reporter *reporter);
void *
devlink_health_reporter_priv(struct devlink_health_reporter *reporter);
+int devlink_health_report(struct devlink_health_reporter *reporter,
+ const char *msg, void *priv_ctx);
#else
static inline struct devlink *devlink_alloc(const struct devlink_ops *ops,
@@ -979,6 +981,13 @@ devlink_health_reporter_priv(struct devlink_health_reporter *reporter)
{
return NULL;
}
+
+static inline int
+devlink_health_report(struct devlink_health_reporter *reporter,
+ const char *msg, void *priv_ctx)
+{
+ return 0;
+}
#endif
#endif /* _NET_DEVLINK_H_ */
diff --git a/include/trace/events/devlink.h b/include/trace/events/devlink.h
index 44acfbca1266..7e39d2fc7c75 100644
--- a/include/trace/events/devlink.h
+++ b/include/trace/events/devlink.h
@@ -46,6 +46,65 @@ TRACE_EVENT(devlink_hwmsg,
(int) __entry->len, __get_dynamic_array(buf), __entry->len)
);
+TRACE_EVENT(devlink_health_report,
+ TP_PROTO(const struct devlink *devlink, const char *reporter_name,
+ const char *msg),
+
+ TP_ARGS(devlink, reporter_name, msg),
+
+ TP_STRUCT__entry(
+ __string(bus_name, devlink->dev->bus->name)
+ __string(dev_name, dev_name(devlink->dev))
+ __string(driver_name, devlink->dev->driver->name)
+ __string(reporter_name, msg)
+ __string(msg, msg)
+ ),
+
+ TP_fast_assign(
+ __assign_str(bus_name, devlink->dev->bus->name);
+ __assign_str(dev_name, dev_name(devlink->dev));
+ __assign_str(driver_name, devlink->dev->driver->name);
+ __assign_str(reporter_name, reporter_name);
+ __assign_str(msg, msg);
+ ),
+
+ TP_printk("bus_name=%s dev_name=%s driver_name=%s reporter_name=%s: %s",
+ __get_str(bus_name), __get_str(dev_name),
+ __get_str(driver_name), __get_str(reporter_name),
+ __get_str(msg))
+);
+
+TRACE_EVENT(devlink_health_recover_aborted,
+ TP_PROTO(const struct devlink *devlink, const char *reporter_name,
+ bool health_state, u64 time_since_last_recover),
+
+ TP_ARGS(devlink, reporter_name, health_state, time_since_last_recover),
+
+ TP_STRUCT__entry(
+ __string(bus_name, devlink->dev->bus->name)
+ __string(dev_name, dev_name(devlink->dev))
+ __string(driver_name, devlink->dev->driver->name)
+ __string(reporter_name, reporter_name)
+ __field(bool, health_state)
+ __field(u64, time_since_last_recover)
+ ),
+
+ TP_fast_assign(
+ __assign_str(bus_name, devlink->dev->bus->name);
+ __assign_str(dev_name, dev_name(devlink->dev));
+ __assign_str(driver_name, devlink->dev->driver->name);
+ __assign_str(reporter_name, reporter_name);
+ __entry->health_state = health_state;
+ __entry->time_since_last_recover = time_since_last_recover;
+ ),
+
+ TP_printk("bus_name=%s dev_name=%s driver_name=%s reporter_name=%s: health_state=%d time_since_last_recover = %llu recover aborted",
+ __get_str(bus_name), __get_str(dev_name),
+ __get_str(driver_name), __get_str(reporter_name),
+ __entry->health_state,
+ __entry->time_since_last_recover)
+);
+
#endif /* _TRACE_DEVLINK_H */
/* This part must be outside protection */
@@ -64,6 +123,9 @@ static inline void trace_devlink_hwmsg(const struct devlink *devlink,
{
}
+static inline void trace_devlink_health(const char *msg)
+{
+}
#endif /* _TRACE_DEVLINK_H */
#endif
diff --git a/net/core/devlink.c b/net/core/devlink.c
index fec169a28dba..943d3e7dea6a 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -4110,6 +4110,16 @@ struct devlink_health_reporter {
u64 graceful_period;
bool auto_recover;
u8 health_state;
+ u8 dump_avail;
+ u64 dump_ts;
+ u64 error_count;
+ u64 recovery_count;
+ u64 last_recovery_ts;
+};
+
+enum devlink_health_reporter_state {
+ DEVLINK_HEALTH_REPORTER_STATE_HEALTHY,
+ DEVLINK_HEALTH_REPORTER_STATE_ERROR,
};
void *
@@ -4224,6 +4234,89 @@ devlink_health_reporter_destroy(struct devlink_health_reporter *reporter)
}
EXPORT_SYMBOL_GPL(devlink_health_reporter_destroy);
+static int
+devlink_health_reporter_recover(struct devlink_health_reporter *reporter,
+ void *priv_ctx)
+{
+ int err;
+
+ if (!reporter->ops->recover)
+ return -EOPNOTSUPP;
+
+ err = reporter->ops->recover(reporter, priv_ctx);
+ if (err)
+ return err;
+
+ reporter->recovery_count++;
+ reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_HEALTHY;
+ reporter->last_recovery_ts = jiffies;
+
+ return 0;
+}
+
+static int devlink_health_do_dump(struct devlink_health_reporter *reporter,
+ void *priv_ctx)
+{
+ int err;
+
+ if (!reporter->ops->dump)
+ return 0;
+
+ if (reporter->dump_avail)
+ return 0;
+
+ devlink_health_buffers_reset(reporter->dump_buffers_array,
+ DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->dump_size));
+ err = reporter->ops->dump(reporter, reporter->dump_buffers_array,
+ DEVLINK_HEALTH_BUFFER_SIZE,
+ DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->dump_size),
+ priv_ctx);
+ if (!err) {
+ reporter->dump_avail = true;
+ reporter->dump_ts = jiffies;
+ }
+
+ return err;
+}
+
+int devlink_health_report(struct devlink_health_reporter *reporter,
+ const char *msg, void *priv_ctx)
+{
+ struct devlink *devlink = reporter->devlink;
+ int err = 0;
+
+ /* write a log message of the current error */
+ WARN_ON(!msg);
+ trace_devlink_health_report(devlink, reporter->ops->name, msg);
+ reporter->error_count++;
+
+ /* abort if the previous error wasn't recovered */
+ if (reporter->auto_recover &&
+ (reporter->health_state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY ||
+ jiffies - reporter->last_recovery_ts <
+ msecs_to_jiffies(reporter->graceful_period))) {
+ trace_devlink_health_recover_aborted(devlink,
+ reporter->ops->name,
+ reporter->health_state,
+ jiffies -
+ reporter->last_recovery_ts);
+ return -ECANCELED;
+ }
+
+ reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_ERROR;
+
+ mutex_lock(&reporter->dump_lock);
+ /* store current dump of current error, for later analysis */
+ devlink_health_do_dump(reporter, priv_ctx);
+ mutex_unlock(&reporter->dump_lock);
+
+ if (reporter->auto_recover)
+ err = devlink_health_reporter_recover(reporter, priv_ctx);
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(devlink_health_report);
+
static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING },
[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING },
--
2.17.1
Powered by blists - more mailing lists