summaryrefslogtreecommitdiff
path: root/net/devlink/health.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/devlink/health.c')
-rw-r--r--net/devlink/health.c109
1 files changed, 81 insertions, 28 deletions
diff --git a/net/devlink/health.c b/net/devlink/health.c
index b3ce8ecbb7fb..136a67c36a20 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 burst_period;
bool auto_recover;
bool auto_dump;
u8 health_state;
@@ -108,11 +109,14 @@ devlink_port_health_reporter_find_by_name(struct devlink_port *devlink_port,
static 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)
{
struct devlink_health_reporter *reporter;
- if (WARN_ON(graceful_period && !ops->recover))
+ if (WARN_ON(ops->default_graceful_period && !ops->recover))
+ return ERR_PTR(-EINVAL);
+
+ if (WARN_ON(ops->default_burst_period && !ops->default_graceful_period))
return ERR_PTR(-EINVAL);
reporter = kzalloc(sizeof(*reporter), GFP_KERNEL);
@@ -122,7 +126,8 @@ __devlink_health_reporter_create(struct devlink *devlink,
reporter->priv = priv;
reporter->ops = ops;
reporter->devlink = devlink;
- reporter->graceful_period = graceful_period;
+ reporter->graceful_period = ops->default_graceful_period;
+ reporter->burst_period = ops->default_burst_period;
reporter->auto_recover = !!ops->recover;
reporter->auto_dump = !!ops->dump;
return reporter;
@@ -134,13 +139,12 @@ __devlink_health_reporter_create(struct devlink *devlink,
*
* @port: devlink_port to which health reports will relate
* @ops: devlink health reporter ops
- * @graceful_period: min time (in msec) between recovery attempts
* @priv: driver priv pointer
*/
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 *reporter;
@@ -150,8 +154,7 @@ devl_port_health_reporter_create(struct devlink_port *port,
ops->name))
return ERR_PTR(-EEXIST);
- reporter = __devlink_health_reporter_create(port->devlink, ops,
- graceful_period, priv);
+ reporter = __devlink_health_reporter_create(port->devlink, ops, priv);
if (IS_ERR(reporter))
return reporter;
@@ -164,14 +167,13 @@ EXPORT_SYMBOL_GPL(devl_port_health_reporter_create);
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 *reporter;
struct devlink *devlink = port->devlink;
devl_lock(devlink);
- reporter = devl_port_health_reporter_create(port, ops,
- graceful_period, priv);
+ reporter = devl_port_health_reporter_create(port, ops, priv);
devl_unlock(devlink);
return reporter;
}
@@ -182,13 +184,12 @@ EXPORT_SYMBOL_GPL(devlink_port_health_reporter_create);
*
* @devlink: devlink instance which the health reports will relate
* @ops: devlink health reporter ops
- * @graceful_period: min time (in msec) between recovery attempts
* @priv: driver priv pointer
*/
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 *reporter;
@@ -197,8 +198,7 @@ devl_health_reporter_create(struct devlink *devlink,
if (devlink_health_reporter_find_by_name(devlink, ops->name))
return ERR_PTR(-EEXIST);
- reporter = __devlink_health_reporter_create(devlink, ops,
- graceful_period, priv);
+ reporter = __devlink_health_reporter_create(devlink, ops, priv);
if (IS_ERR(reporter))
return reporter;
@@ -210,13 +210,12 @@ EXPORT_SYMBOL_GPL(devl_health_reporter_create);
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)
{
struct devlink_health_reporter *reporter;
devl_lock(devlink);
- reporter = devl_health_reporter_create(devlink, ops,
- graceful_period, priv);
+ reporter = devl_health_reporter_create(devlink, ops, priv);
devl_unlock(devlink);
return reporter;
}
@@ -298,6 +297,10 @@ devlink_nl_health_reporter_fill(struct sk_buff *msg,
reporter->graceful_period))
goto reporter_nest_cancel;
if (reporter->ops->recover &&
+ devlink_nl_put_u64(msg, DEVLINK_ATTR_HEALTH_REPORTER_BURST_PERIOD,
+ reporter->burst_period))
+ goto reporter_nest_cancel;
+ if (reporter->ops->recover &&
nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER,
reporter->auto_recover))
goto reporter_nest_cancel;
@@ -462,16 +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_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->burst_period = 0;
+ }
+
+ if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_BURST_PERIOD]) {
+ u64 burst_period =
+ nla_get_u64(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_BURST_PERIOD]);
+
+ if (!reporter->graceful_period && burst_period) {
+ NL_SET_ERR_MSG_MOD(info->extack,
+ "Cannot set burst period without a grace period.");
+ return -EINVAL;
+ }
+
+ reporter->burst_period = burst_period;
+ }
if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER])
reporter->auto_recover =
@@ -514,11 +534,25 @@ static void devlink_recover_notify(struct devlink_health_reporter *reporter,
devlink_nl_notify_send_desc(devlink, msg, &desc);
}
+static bool
+devlink_health_reporter_in_burst(struct devlink_health_reporter *reporter)
+{
+ unsigned long burst_threshold = reporter->last_recovery_ts +
+ msecs_to_jiffies(reporter->burst_period);
+
+ return time_is_after_jiffies(burst_threshold);
+}
+
void
devlink_health_reporter_recovery_done(struct devlink_health_reporter *reporter)
{
reporter->recovery_count++;
- reporter->last_recovery_ts = jiffies;
+ if (!devlink_health_reporter_in_burst(reporter))
+ /* When burst period is set, last_recovery_ts marks the first
+ * recovery within the burst period, not necessarily the last
+ * one.
+ */
+ reporter->last_recovery_ts = jiffies;
}
EXPORT_SYMBOL_GPL(devlink_health_reporter_recovery_done);
@@ -592,12 +626,37 @@ dump_err:
return err;
}
+static bool
+devlink_health_recover_abort(struct devlink_health_reporter *reporter,
+ enum devlink_health_reporter_state prev_state)
+{
+ unsigned long recover_ts_threshold;
+
+ if (!reporter->auto_recover)
+ return false;
+
+ /* abort if the previous error wasn't recovered */
+ if (prev_state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY)
+ return true;
+
+ if (devlink_health_reporter_in_burst(reporter))
+ return false;
+
+ recover_ts_threshold = reporter->last_recovery_ts +
+ msecs_to_jiffies(reporter->burst_period) +
+ msecs_to_jiffies(reporter->graceful_period);
+ if (reporter->last_recovery_ts && reporter->recovery_count &&
+ time_is_after_jiffies(recover_ts_threshold))
+ return true;
+
+ return false;
+}
+
int devlink_health_report(struct devlink_health_reporter *reporter,
const char *msg, void *priv_ctx)
{
enum devlink_health_reporter_state prev_health_state;
struct devlink *devlink = reporter->devlink;
- unsigned long recover_ts_threshold;
int ret;
/* write a log message of the current error */
@@ -608,13 +667,7 @@ int devlink_health_report(struct devlink_health_reporter *reporter,
reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_ERROR;
devlink_recover_notify(reporter, DEVLINK_CMD_HEALTH_REPORTER_RECOVER);
- /* abort if the previous error wasn't recovered */
- recover_ts_threshold = reporter->last_recovery_ts +
- msecs_to_jiffies(reporter->graceful_period);
- if (reporter->auto_recover &&
- (prev_health_state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY ||
- (reporter->last_recovery_ts && reporter->recovery_count &&
- time_is_after_jiffies(recover_ts_threshold)))) {
+ if (devlink_health_recover_abort(reporter, prev_health_state)) {
trace_devlink_health_recover_aborted(devlink,
reporter->ops->name,
reporter->health_state,
generated by cgit v1.2.3 (git 2.46.0) at 2025-10-03 14:16:21 +0000