xiaomi-sm8450/android_kernel_xiaomi_sm8450
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

devlink: Add health report functionality

Browse Source 
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@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Eran Ben Elisha
2019-01-17 23:59:12 +02:00
committed by David S. Miller
parent 880ee82f03
commit c7af343b4e
3 changed files with 164 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

93
net/core/devlink.c
View File

@@ -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 },