trace, AER: Move trace into unified interface

AER uses a separate trace interface by now. To make it
consistent, move it into unified RAS trace interface.

Signed-off-by: Chen, Gong <gong.chen@linux.intel.com>
Acked-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Tony Luck <tony.luck@intel.com>

1 files changed, 64 insertions, 0 deletions

diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index 21cdb0b7b0fb..acbcbb88eaaa 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -8,6 +8,7 @@
 #include <linux/tracepoint.h>
 #include <linux/edac.h>
 #include <linux/ktime.h>
+#include <linux/aer.h>
 
 /*
  * Hardware Events Report
@@ -94,6 +95,69 @@ TRACE_EVENT(mc_event,
                   __get_str(driver_detail))
 );
 
+/*
+ * 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_HW_EVENT_MC_H */
 
 /* This part must be outside protection */