mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-22 11:58:21 +07:00
c7af343b4e
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>
132 lines
3.8 KiB
C
132 lines
3.8 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#if IS_ENABLED(CONFIG_NET_DEVLINK)
|
|
|
|
#undef TRACE_SYSTEM
|
|
#define TRACE_SYSTEM devlink
|
|
|
|
#if !defined(_TRACE_DEVLINK_H) || defined(TRACE_HEADER_MULTI_READ)
|
|
#define _TRACE_DEVLINK_H
|
|
|
|
#include <linux/device.h>
|
|
#include <net/devlink.h>
|
|
#include <linux/tracepoint.h>
|
|
|
|
/*
|
|
* Tracepoint for devlink hardware message:
|
|
*/
|
|
TRACE_EVENT(devlink_hwmsg,
|
|
TP_PROTO(const struct devlink *devlink, bool incoming,
|
|
unsigned long type, const u8 *buf, size_t len),
|
|
|
|
TP_ARGS(devlink, incoming, type, buf, len),
|
|
|
|
TP_STRUCT__entry(
|
|
__string(bus_name, devlink->dev->bus->name)
|
|
__string(dev_name, dev_name(devlink->dev))
|
|
__string(driver_name, devlink->dev->driver->name)
|
|
__field(bool, incoming)
|
|
__field(unsigned long, type)
|
|
__dynamic_array(u8, buf, len)
|
|
__field(size_t, len)
|
|
),
|
|
|
|
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);
|
|
__entry->incoming = incoming;
|
|
__entry->type = type;
|
|
memcpy(__get_dynamic_array(buf), buf, len);
|
|
__entry->len = len;
|
|
),
|
|
|
|
TP_printk("bus_name=%s dev_name=%s driver_name=%s incoming=%d type=%lu buf=0x[%*phD] len=%zu",
|
|
__get_str(bus_name), __get_str(dev_name),
|
|
__get_str(driver_name), __entry->incoming, __entry->type,
|
|
(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 */
|
|
#include <trace/define_trace.h>
|
|
|
|
#else /* CONFIG_NET_DEVLINK */
|
|
|
|
#if !defined(_TRACE_DEVLINK_H)
|
|
#define _TRACE_DEVLINK_H
|
|
|
|
#include <net/devlink.h>
|
|
|
|
static inline void trace_devlink_hwmsg(const struct devlink *devlink,
|
|
bool incoming, unsigned long type,
|
|
const u8 *buf, size_t len)
|
|
{
|
|
}
|
|
|
|
static inline void trace_devlink_health(const char *msg)
|
|
{
|
|
}
|
|
#endif /* _TRACE_DEVLINK_H */
|
|
|
|
#endif
|