Merge branch 'x86-ras-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RAS updates from Ingo Molnar:
 "The main changes in this cycle are:

   - RAS tracing/events infrastructure, by Gong Chen.

   - Various generalizations of the APEI code to make it available to
     non-x86 architectures, by Tomasz Nowicki"

* 'x86-ras-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/ras: Fix build warnings in <linux/aer.h>
  acpi, apei, ghes: Factor out ioremap virtual memory for IRQ and NMI context.
  acpi, apei, ghes: Make NMI error notification to be GHES architecture extension.
  apei, mce: Factor out APEI architecture specific MCE calls.
  RAS, extlog: Adjust init flow
  trace, eMCA: Add a knob to adjust where to save event log
  trace, RAS: Add eMCA trace event interface
  RAS, debugfs: Add debugfs interface for RAS subsystem
  CPER: Adjust code flow of some functions
  x86, MCE: Robustify mcheck_init_device
  trace, AER: Move trace into unified interface
  trace, RAS: Add basic RAS trace event
  x86, MCE: Kill CPU_POST_DEAD
This commit is contained in:
Linus Torvalds
2014-08-04 17:21:59 -07:00
28 changed files with 656 additions and 250 deletions

View File

@@ -1,77 +0,0 @@
#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>