mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-17 01:34:00 +08:00
545104dd2b
There's inconsistency between dmesg and the trace event output.
When dmesg says "severity=Corrected", the trace event says
"severity=Fatal". What happens is that HW_EVENT_ERR_CORRECTED is
defined in edac.h:
enum hw_event_mc_err_type {
HW_EVENT_ERR_CORRECTED,
HW_EVENT_ERR_UNCORRECTED,
HW_EVENT_ERR_FATAL,
HW_EVENT_ERR_INFO,
};
while aer_print_error() uses aer_error_severity_string[] defined as:
static const char *aer_error_severity_string[] = {
"Uncorrected (Non-Fatal)",
"Uncorrected (Fatal)",
"Corrected"
};
In this case dmesg is correct because info->severity is assigned in
aer_isr_one_error() using the definitions in include/linux/ras.h:
Signed-off-by: Rui Wang <rui.y.wang@intel.com>
Acked-by: Ethan Zhao <ethan.kernel@gmail.com>
Link: http://lkml.kernel.org/r/CANVTcTaP18CiGOSEcX5Ch_wPw9mEhkgokfp+d+ZOMFD+Ce4juA@mail.gmail.com
Signed-off-by: Borislav Petkov <bp@suse.de>
78 lines
2.1 KiB
C
78 lines
2.1 KiB
C
#undef TRACE_SYSTEM
|
|
#define TRACE_SYSTEM ras
|
|
|
|
#if !defined(_TRACE_AER_H) || defined(TRACE_HEADER_MULTI_READ)
|
|
#define _TRACE_AER_H
|
|
|
|
#include <linux/tracepoint.h>
|
|
#include <linux/aer.h>
|
|
|
|
|
|
/*
|
|
* PCIe AER Trace event
|
|
*
|
|
* These events are generated when hardware detects a corrected or
|
|
* uncorrected event on a PCIe device. The event report has
|
|
* the following structure:
|
|
*
|
|
* char * dev_name - The name of the slot where the device resides
|
|
* ([domain:]bus:device.function).
|
|
* u32 status - Either the correctable or uncorrectable register
|
|
* indicating what error or errors have been seen
|
|
* u8 severity - error severity 0:NONFATAL 1:FATAL 2:CORRECTED
|
|
*/
|
|
|
|
#define aer_correctable_errors \
|
|
{BIT(0), "Receiver Error"}, \
|
|
{BIT(6), "Bad TLP"}, \
|
|
{BIT(7), "Bad DLLP"}, \
|
|
{BIT(8), "RELAY_NUM Rollover"}, \
|
|
{BIT(12), "Replay Timer Timeout"}, \
|
|
{BIT(13), "Advisory Non-Fatal"}
|
|
|
|
#define aer_uncorrectable_errors \
|
|
{BIT(4), "Data Link Protocol"}, \
|
|
{BIT(12), "Poisoned TLP"}, \
|
|
{BIT(13), "Flow Control Protocol"}, \
|
|
{BIT(14), "Completion Timeout"}, \
|
|
{BIT(15), "Completer Abort"}, \
|
|
{BIT(16), "Unexpected Completion"}, \
|
|
{BIT(17), "Receiver Overflow"}, \
|
|
{BIT(18), "Malformed TLP"}, \
|
|
{BIT(19), "ECRC"}, \
|
|
{BIT(20), "Unsupported Request"}
|
|
|
|
TRACE_EVENT(aer_event,
|
|
TP_PROTO(const char *dev_name,
|
|
const u32 status,
|
|
const u8 severity),
|
|
|
|
TP_ARGS(dev_name, status, severity),
|
|
|
|
TP_STRUCT__entry(
|
|
__string( dev_name, dev_name )
|
|
__field( u32, status )
|
|
__field( u8, severity )
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__assign_str(dev_name, dev_name);
|
|
__entry->status = status;
|
|
__entry->severity = severity;
|
|
),
|
|
|
|
TP_printk("%s PCIe Bus Error: severity=%s, %s\n",
|
|
__get_str(dev_name),
|
|
__entry->severity == AER_CORRECTABLE ? "Corrected" :
|
|
__entry->severity == AER_FATAL ?
|
|
"Fatal" : "Uncorrected, non-fatal",
|
|
__entry->severity == AER_CORRECTABLE ?
|
|
__print_flags(__entry->status, "|", aer_correctable_errors) :
|
|
__print_flags(__entry->status, "|", aer_uncorrectable_errors))
|
|
);
|
|
|
|
#endif /* _TRACE_AER_H */
|
|
|
|
/* This part must be outside protection */
|
|
#include <trace/define_trace.h>
|