Use perf/event tracing to report PCI Express advanced errors.

-----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1.4.11 (GNU/Linux)
 
 iQIcBAABAgAGBQJQ5zH/AAoJEKurIx+X31iByOsP/iNc+1ltI6fKemug/z8m9QQs
 y1oNjtI9boCGglpqRpQ0+v3D9Y9w259T8hO/2wcbQ6te+KvhCzOcXaHtcA9DTN3L
 FIWkK0l5nPmEPKC0tM3EWzdWb1vUXiNCD+ouwZoXwUFRuy9Gq/Kzl00/xrYDinuK
 Ogb59DmqBdtv34cUgJozqg2vdKuBI88+Usg9ervSXwVdg4NBaEvJjnesFrmSz6dN
 U8gGW+YAY2gEpZ32KGbofMLUJUtwru0BtR1vkIgY23magvkqNkNExcODAPpRbOIf
 +Vfv2hWP/i9dRFh4cnxwVb6fSjQ9JFr7iXwK6SLQ9XvK35tN2QLTiU7z/9IfXPTd
 dZrW6HviugvKOi8vS/e7S6nb/7KfQtj1Ix5K0u9rFMWUdDKvhC1EfVMU0maBQ6ZP
 OhRmJqPMxG+1zHJ0zIhhiut/pmMrDRLK9MFs71Ger4/V78LmIwVQlZ+8fwslkA6L
 ceKzECWhBi2JRZKJKo379oJwROxYoCkx39uxcBrCEZ6RogcFQ2kyYSSBKbt7RJ24
 5f2M8H98b+i9LQSoRYrDPZN4n5TQoG6LP+GmkdwZTNKDUZ4CUjBhnLEylm1ups+s
 q8Ji1dHzJcmBnRsRhwnreef1Q7Bty3ZwALn0kqvUyeoY9y5NGuYA8tb28P8l7tVa
 WYSo98WUb7+czTgpzOIh
 =nIcy
 -----END PGP SIGNATURE-----

Merge tag 'please-pull-aer-trace' of git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras into perf/core

Use perf/event tracing to report PCI Express advanced errors, by
Tony Luck.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

include/linux/aer.h

@@ -49,8 +49,8 @@ static inline int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
 }
 #endif
 
-extern void cper_print_aer(const char *prefix, int cper_severity,
-			   struct aer_capability_regs *aer);
+extern void cper_print_aer(const char *prefix, struct pci_dev *dev,
+			   int cper_severity, struct aer_capability_regs *aer);
 extern int cper_severity_to_aer(int cper_severity);
 extern void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
 			      int severity);

include/trace/events/ras.h

@@ -0,0 +1,77 @@
+#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/edac.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 == HW_EVENT_ERR_CORRECTED ? "Corrected" :
+			__entry->severity == HW_EVENT_ERR_FATAL ?
+			"Fatal" : "Uncorrected",
+		__entry->severity == HW_EVENT_ERR_CORRECTED ?
+		__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>