[PATCH 1/3] aerdrv: Trace Event for AER

[Lance Ortiz]

This header file will define a new trace event that will be triggered when
a AER event occurs.  The following data will be provided to the trace 
event.

char * name -	String containing the device path

u32 status - 	Either the correctable or uncorrectable register 
		indicating what error or errors have been see.

u8 severity - 	error severity 0:NONFATAL 1:FATAL 2:CORRECTED

The trace event will also provide a trace string that may look like:

"0000:05:00.0 PCIe Bus Error:severity=Uncorrected (Non-Fatal), Poisoned
TLP"

Signed-off-by: Lance Ortiz <lance.ortiz@xxxxxx>
---

 include/ras/aer_event.h |   77 +++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 77 insertions(+), 0 deletions(-)
 create mode 100644 include/ras/aer_event.h

diff --git a/include/ras/aer_event.h b/include/ras/aer_event.h
new file mode 100644
index 0000000..735c973
--- /dev/null
+++ b/include/ras/aer_event.h
@@ -0,0 +1,77 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM aer
+#define TRACE_INCLUDE_FILE aer_event
+
+#if !defined(_TRACE_AER_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_AER_H
+
+#include <linux/tracepoint.h>
+#include <linux/edac.h>
+
+
+/*
+ * Anhance Error Reporting (AER) PCIE Report Error
+ *
+ * These events are generated when hardware detects a corrected or
+ * uncorrected event on a pci express device and reports
+ * errors.  The event reports the following data.
+ *
+ * char * dev_name -	String containing the device identification
+ * 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 correctable_error_string			\
+	{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 uncorrectable_error_string			\
+	{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 == HW_EVENT_ERR_CORRECTED) ? "Corrected" :
+			((__entry->severity == HW_EVENT_ERR_FATAL) ?
+			"Fatal" : "Uncorrected"),
+		__entry->severity == HW_EVENT_ERR_CORRECTED ?
+		__print_flags(__entry->status, "|", correctable_error_string) :
+		__print_flags(__entry->status, "|", uncorrectable_error_string))
+);
+
+#endif /* _TRACE_AER_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/